1683 files changed, 68719 insertions, 20532 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..533ff5c68970 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4846,3 +4846,8 @@
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
+
+	xhci-hcd.quirks		[USB,KNL]
+			A hex value specifying bitmask with supplemental xhci
+			host controller quirks. Meaning of each bit can be
+			consulted in header drivers/usb/host/xhci.h.
diff --git a/Documentation/device-mapper/writecache.txt b/Documentation/device-mapper/writecache.txt
index 4424fa2c67d7..01532b3008ae 100644
--- a/Documentation/device-mapper/writecache.txt
+++ b/Documentation/device-mapper/writecache.txt
@@ -15,6 +15,8 @@ Constructor parameters:
    size)
 5. the number of optional parameters (the parameters with an argument
    count as two)
+	start_sector n		(default: 0)
+		offset from the start of cache device in 512-byte sectors
 	high_watermark n	(default: 50)
 		start writeback when the number of used blocks reach this
 		watermark
diff --git a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
index bdadc3da9556..6970f30a3770 100644
--- a/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/samsung-boards.txt
@@ -66,7 +66,7 @@ Required root node properties:
 	- "insignal,arndale-octa" - for Exynos5420-based Insignal Arndale
 				    Octa board.
 	- "insignal,origen"       - for Exynos4210-based Insignal Origen board.
-	- "insignal,origen4412    - for Exynos4412-based Insignal Origen board.
+	- "insignal,origen4412"   - for Exynos4412-based Insignal Origen board.
 
 
 Optional nodes:
diff --git a/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt b/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
index 284e2b14cfbe..26649b4c4dd8 100644
--- a/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
+++ b/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
@@ -74,6 +74,12 @@ Required properties for DSI:
 		The 3 clocks output from the DSI analog PHY: dsi[01]_byte,
 		dsi[01]_ddr2, and dsi[01]_ddr
 
+Required properties for the TXP (writeback) block:
+- compatible:	Should be "brcm,bcm2835-txp"
+- reg:		Physical base address and length of the TXP block's registers
+- interrupts:	The interrupt number
+		  See bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
+
 [1] Documentation/devicetree/bindings/media/video-interfaces.txt
 
 Example:
diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
index 383183a89164..8469de510001 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
@@ -40,7 +40,7 @@ Required properties (all function blocks):
 	"mediatek,<chip>-dpi"        - DPI controller, see mediatek,dpi.txt
 	"mediatek,<chip>-disp-mutex" - display mutex
 	"mediatek,<chip>-disp-od"    - overdrive
-  the supported chips are mt2701 and mt8173.
+  the supported chips are mt2701, mt2712 and mt8173.
 - reg: Physical base address and length of the function block register space
 - interrupts: The interrupt signal from the function block (required, except for
   merge and split function blocks).
diff --git a/Documentation/devicetree/bindings/display/msm/dpu.txt b/Documentation/devicetree/bindings/display/msm/dpu.txt
new file mode 100644
index 000000000000..ad2e8830324e
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/msm/dpu.txt
@@ -0,0 +1,131 @@
+Qualcomm Technologies, Inc. DPU KMS
+
+Description:
+
+Device tree bindings for MSM Mobile Display Subsytem(MDSS) that encapsulates
+sub-blocks like DPU display controller, DSI and DP interfaces etc.
+The DPU display controller is found in SDM845 SoC.
+
+MDSS:
+Required properties:
+- compatible: "qcom,sdm845-mdss"
+- reg: physical base address and length of contoller's registers.
+- reg-names: register region names. The following region is required:
+  * "mdss"
+- power-domains: a power domain consumer specifier according to
+  Documentation/devicetree/bindings/power/power_domain.txt
+- clocks: list of clock specifiers for clocks needed by the device.
+- clock-names: device clock names, must be in same order as clocks property.
+  The following clocks are required:
+  * "iface"
+  * "bus"
+  * "core"
+- interrupts: interrupt signal from MDSS.
+- interrupt-controller: identifies the node as an interrupt controller.
+- #interrupt-cells: specifies the number of cells needed to encode an interrupt
+  source, should be 1.
+- iommus: phandle of iommu device node.
+- #address-cells: number of address cells for the MDSS children. Should be 1.
+- #size-cells: Should be 1.
+- ranges: parent bus address space is the same as the child bus address space.
+
+Optional properties:
+- assigned-clocks: list of clock specifiers for clocks needing rate assignment
+- assigned-clock-rates: list of clock frequencies sorted in the same order as
+  the assigned-clocks property.
+
+MDP:
+Required properties:
+- compatible: "qcom,sdm845-dpu"
+- reg: physical base address and length of controller's registers.
+- reg-names : register region names. The following region is required:
+  * "mdp"
+  * "vbif"
+- clocks: list of clock specifiers for clocks needed by the device.
+- clock-names: device clock names, must be in same order as clocks property.
+  The following clocks are required.
+  * "bus"
+  * "iface"
+  * "core"
+  * "vsync"
+- interrupts: interrupt line from DPU to MDSS.
+- ports: contains the list of output ports from DPU device. These ports connect
+  to interfaces that are external to the DPU hardware, such as DSI, DP etc.
+
+  Each output port contains an endpoint that describes how it is connected to an
+  external interface. These are described by the standard properties documented
+  here:
+	Documentation/devicetree/bindings/graph.txt
+	Documentation/devicetree/bindings/media/video-interfaces.txt
+
+	Port 0 -> DPU_INTF1 (DSI1)
+	Port 1 -> DPU_INTF2 (DSI2)
+
+Optional properties:
+- assigned-clocks: list of clock specifiers for clocks needing rate assignment
+- assigned-clock-rates: list of clock frequencies sorted in the same order as
+  the assigned-clocks property.
+
+Example:
+
+	mdss: mdss@ae00000 {
+		compatible = "qcom,sdm845-mdss";
+		reg = <0xae00000 0x1000>;
+		reg-names = "mdss";
+
+		power-domains = <&clock_dispcc 0>;
+
+		clocks = <&gcc GCC_DISP_AHB_CLK>, <&gcc GCC_DISP_AXI_CLK>,
+			 <&clock_dispcc DISP_CC_MDSS_MDP_CLK>;
+		clock-names = "iface", "bus", "core";
+
+		assigned-clocks = <&clock_dispcc DISP_CC_MDSS_MDP_CLK>;
+		assigned-clock-rates = <300000000>;
+
+		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		iommus = <&apps_iommu 0>;
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0xae00000 0xb2008>;
+
+		mdss_mdp: mdp@ae01000 {
+			compatible = "qcom,sdm845-dpu";
+			reg = <0 0x1000 0x8f000>, <0 0xb0000 0x2008>;
+			reg-names = "mdp", "vbif";
+
+			clocks = <&clock_dispcc DISP_CC_MDSS_AHB_CLK>,
+				 <&clock_dispcc DISP_CC_MDSS_AXI_CLK>,
+				 <&clock_dispcc DISP_CC_MDSS_MDP_CLK>,
+				 <&clock_dispcc DISP_CC_MDSS_VSYNC_CLK>;
+			clock-names = "iface", "bus", "core", "vsync";
+
+			assigned-clocks = <&clock_dispcc DISP_CC_MDSS_MDP_CLK>,
+					  <&clock_dispcc DISP_CC_MDSS_VSYNC_CLK>;
+			assigned-clock-rates = <0 0 300000000 19200000>;
+
+			interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					dpu_intf1_out: endpoint {
+						remote-endpoint = <&dsi0_in>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					dpu_intf2_out: endpoint {
+						remote-endpoint = <&dsi1_in>;
+					};
+				};
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt
index 518e9cdf0d4b..d22237a88eae 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/display/msm/dsi.txt
@@ -121,6 +121,20 @@ Required properties:
 Optional properties:
 - qcom,dsi-phy-regulator-ldo-mode: Boolean value indicating if the LDO mode PHY
   regulator is wanted.
+- qcom,mdss-mdp-transfer-time-us:	Specifies the dsi transfer time for command mode
+					panels in microseconds. Driver uses this number to adjust
+					the clock rate according to the expected transfer time.
+					Increasing this value would slow down the mdp processing
+					and can result in slower performance.
+					Decreasing this value can speed up the mdp processing,
+					but this can also impact power consumption.
+					As a rule this time should not be higher than the time
+					that would be expected with the processing at the
+					dsi link rate since anyways this would be the maximum
+					transfer time that could be achieved.
+					If ping pong split is enabled, this time should not be higher
+					than two times the dsi link rate time.
+					If the property is not specified, then the default value is 14000 us.
 
 [1] Documentation/devicetree/bindings/clock/clock-bindings.txt
 [2] Documentation/devicetree/bindings/graph.txt
@@ -171,6 +185,8 @@ Example:
 		qcom,master-dsi;
 		qcom,sync-dual-dsi;
 
+		qcom,mdss-mdp-transfer-time-us = <12000>;
+
 		pinctrl-names = "default", "sleep";
 		pinctrl-0 = <&dsi_active>;
 		pinctrl-1 = <&dsi_suspend>;
diff --git a/Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt b/Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt
new file mode 100644
index 000000000000..55183d360032
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt
@@ -0,0 +1,28 @@
+BOE HV070WSA-100 7.01" WSVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "boe,hv070wsa-100"
+- power-supply: regulator to provide the VCC supply voltage (3.3 volts)
+- enable-gpios: GPIO pin to enable and disable panel (active high)
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
+
+The device node can contain one 'port' child node with one child
+'endpoint' node, according to the bindings defined in [1]. This
+node should describe panel's video bus.
+
+[1]: Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+
+	panel: panel {
+		compatible = "boe,hv070wsa-100";
+		power-supply = <&vcc_3v3_reg>;
+		enable-gpios = <&gpd1 3 GPIO_ACTIVE_HIGH>;
+		port {
+			panel_ep: endpoint {
+				remote-endpoint = <&bridge_out_ep>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt b/Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt
new file mode 100644
index 000000000000..897085ee3cd4
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt
@@ -0,0 +1,8 @@
+DataImage, Inc. 7" WVGA (800x480) TFT LCD panel with 24-bit parallel interface.
+
+Required properties:
+- compatible: should be "dataimage,scf0700c48ggu18"
+- power-supply: 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/dlc,dlc0700yzg-1.txt b/Documentation/devicetree/bindings/display/panel/dlc,dlc0700yzg-1.txt
new file mode 100644
index 000000000000..bf06bb025b08
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/dlc,dlc0700yzg-1.txt
@@ -0,0 +1,13 @@
+DLC Display Co. DLC0700YZG-1 7.0" WSVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "dlc,dlc0700yzg-1"
+- power-supply: See simple-panel.txt
+
+Optional properties:
+- reset-gpios: See panel-common.txt
+- enable-gpios: See simple-panel.txt
+- backlight: See simple-panel.txt
+
+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/edt,et-series.txt b/Documentation/devicetree/bindings/display/panel/edt,et-series.txt
new file mode 100644
index 000000000000..f56b99ebd9be
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/edt,et-series.txt
@@ -0,0 +1,39 @@
+Emerging Display Technology Corp. Displays
+==========================================
+
+
+Display bindings for EDT Display Technology Corp. Displays which are
+compatible with the simple-panel binding, which is specified in
+simple-panel.txt
+
+
+5,7" WVGA TFT Panels
+--------------------
+
++-----------------+---------------------+-------------------------------------+
+| Identifier      | compatbile          | description                         |
++=================+=====================+=====================================+
+| ET057090DHU     | edt,et057090dhu     | 5.7" VGA TFT LCD panel              |
++-----------------+---------------------+-------------------------------------+
+
+
+7,0" WVGA TFT Panels
+--------------------
+
++-----------------+---------------------+-------------------------------------+
+| Identifier      | compatbile          | description                         |
++=================+=====================+=====================================+
+| ETM0700G0DH6    | edt,etm070080dh6    | WVGA TFT Display with capacitive    |
+|                 |                     | Touchscreen                         |
++-----------------+---------------------+-------------------------------------+
+| ETM0700G0BDH6   | edt,etm070080bdh6   | Same as ETM0700G0DH6 but with       |
+|                 |                     | inverted pixel clock.               |
++-----------------+---------------------+-------------------------------------+
+| ETM0700G0EDH6   | edt,etm070080edh6   | Same display as the ETM0700G0BDH6,  |
+|                 |                     | but with changed Hardware for the   |
+|                 |                     | backlight and the touch interface   |
++-----------------+---------------------+-------------------------------------+
+| ET070080DH6     | edt,etm070080dh6    | Same timings as the ETM0700G0DH6,   |
+|                 |                     | but with resistive touch.           |
++-----------------+---------------------+-------------------------------------+
+
diff --git a/Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt b/Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt
deleted file mode 100644
index 20cb38e836e4..000000000000
--- a/Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-Emerging Display Technology Corp. ET070080DH6 7.0" WVGA TFT LCD panel
-
-Required properties:
-- compatible: should be "edt,et070080dh6"
-
-This panel is the same as ETM0700G0DH6 except for the touchscreen.
-ET070080DH6 is the model with resistive touch.
-
-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/edt,etm0700g0dh6.txt b/Documentation/devicetree/bindings/display/panel/edt,etm0700g0dh6.txt
deleted file mode 100644
index ee4b18053e40..000000000000
--- a/Documentation/devicetree/bindings/display/panel/edt,etm0700g0dh6.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-Emerging Display Technology Corp. ETM0700G0DH6 7.0" WVGA TFT LCD panel
-
-Required properties:
-- compatible: should be "edt,etm0700g0dh6"
-
-This panel is the same as ET070080DH6 except for the touchscreen.
-ETM0700G0DH6 is the model with capacitive multitouch.
-
-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/innolux,g070y2-l01.txt b/Documentation/devicetree/bindings/display/panel/innolux,g070y2-l01.txt
new file mode 100644
index 000000000000..7c234cf68e11
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/innolux,g070y2-l01.txt
@@ -0,0 +1,12 @@
+Innolux G070Y2-L01 7" WVGA (800x480) TFT LCD panel
+
+Required properties:
+- compatible: should be "innolux,g070y2-l01"
+- 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/innolux,p097pfg.txt b/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt
new file mode 100644
index 000000000000..595d9dfeffd3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt
@@ -0,0 +1,24 @@
+Innolux P097PFG 9.7" 1536x2048 TFT LCD panel
+
+Required properties:
+- compatible: should be "innolux,p097pfg"
+- reg: DSI virtual channel of the peripheral
+- avdd-supply: phandle of the regulator that provides positive voltage
+- avee-supply: phandle of the regulator that provides negative voltage
+- enable-gpios: panel enable gpio
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+
+	&mipi_dsi {
+		panel {
+			compatible = "innolux,p079zca";
+			reg = <0>;
+			avdd-supply = <...>;
+			avee-supply = <...>;
+			backlight = <&backlight>;
+			enable-gpios = <&gpio1 13 GPIO_ACTIVE_HIGH>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt
new file mode 100644
index 000000000000..164a5fa236da
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt
@@ -0,0 +1,22 @@
+Kingdisplay KD097D04 9.7" 1536x2048 TFT LCD panel
+
+Required properties:
+- compatible: should be "kingdisplay,kd097d04"
+- reg: DSI virtual channel of the peripheral
+- power-supply: phandle of the regulator that provides the supply voltage
+- enable-gpios: panel enable gpio
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+
+	&mipi_dsi {
+		panel {
+			compatible = "kingdisplay,kd097d04";
+			reg = <0>;
+			power-supply = <...>;
+			backlight = <&backlight>;
+			enable-gpios = <&gpio1 13 GPIO_ACTIVE_HIGH>;
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/edt,et057090dhu.txt b/Documentation/devicetree/bindings/display/panel/newhaven,nhd-4.3-480272ef-atxl.txt
index 4903d7b1d947..e78292b1a131 100644
--- a/Documentation/devicetree/bindings/display/panel/edt,et057090dhu.txt
+++ b/Documentation/devicetree/bindings/display/panel/newhaven,nhd-4.3-480272ef-atxl.txt
@@ -1,7 +1,7 @@
-Emerging Display Technology Corp. 5.7" VGA TFT LCD panel
+Newhaven Display International 480 x 272 TFT LCD panel
 
 Required properties:
-- compatible: should be "edt,et057090dhu"
+- compatible: should be "newhaven,nhd-4.3-480272ef-atxl"
 
 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/rocktech,rk070er9427.txt b/Documentation/devicetree/bindings/display/panel/rocktech,rk070er9427.txt
new file mode 100644
index 000000000000..eb1fb9f8d1f4
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/rocktech,rk070er9427.txt
@@ -0,0 +1,25 @@
+Rocktech Display Ltd. RK070ER9427 800(RGB)x480 TFT LCD panel
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
+
+Required properties:
+- compatible: should be "rocktech,rk070er9427"
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Optional nodes:
+- Video port for LCD panel input.
+
+Example:
+	panel {
+		compatible = "rocktech,rk070er9427";
+		backlight = <&backlight_lcd>;
+
+		port {
+			lcd_panel_in: endpoint {
+				remote-endpoint = <&lcd_display_out>;
+			};
+		};
+	};
diff --git a/Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt b/Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt
new file mode 100644
index 000000000000..0753f6967279
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt
@@ -0,0 +1,12 @@
+Sharp LQ035Q7DB03 3.5" QVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "sharp,lq035q7db03"
+- power-supply: phandle of the regulator that provides the supply voltage
+
+Optional properties:
+- enable-gpios: GPIO pin to enable or disable the panel
+- backlight: phandle of the backlight device attached to the panel
+
+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/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index 5a9319ad8861..f8773ecb7525 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -101,9 +101,9 @@ DWC HDMI PHY
 
 Required properties:
   - compatible: value must be one of:
-    * allwinner,sun50i-a64-hdmi-phy
     * allwinner,sun8i-a83t-hdmi-phy
     * allwinner,sun8i-h3-hdmi-phy
+    * allwinner,sun50i-a64-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
@@ -147,6 +147,7 @@ Required properties:
    * 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
@@ -181,7 +182,7 @@ For TCONs with channel 0, there is one more clock required:
 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 TCON on A83T and those found
+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
 
@@ -399,6 +400,7 @@ Required properties:
     * 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
 
diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
index 6fddb4f4f71a..3055d5c2c04e 100644
--- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
+++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
@@ -36,7 +36,7 @@ Optional nodes:
 
  - port/ports: to describe a connection to an external encoder. The
    binding follows Documentation/devicetree/bindings/graph.txt and
-   suppors a single port with a single endpoint.
+   supports a single port with a single endpoint.
 
  - See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and
    Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting
diff --git a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
index 20fc72d9e61e..45a61b462287 100644
--- a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
@@ -1,7 +1,7 @@
 Nintendo Wii (Hollywood) GPIO controller
 
 Required properties:
-- compatible: "nintendo,hollywood-gpio
+- compatible: "nintendo,hollywood-gpio"
 - reg: Physical base address and length of the controller's registers.
 - gpio-controller: Marks the device node as a GPIO controller.
 - #gpio-cells: Should be <2>. The first cell is the pin number and the
diff --git a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
index 121d9b7c79a2..1063c30d53f7 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
@@ -32,7 +32,7 @@ i2c@00000000 {
 		reg = <0x6c>;
 		interrupt-parent = <&gpx1>;
 		interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
-		vdd-supply = <&ldo15_reg>";
+		vdd-supply = <&ldo15_reg>;
 		vid-supply = <&ldo18_reg>;
 		reset-gpios = <&gpx1 5 0>;
 		touchscreen-size-x = <1080>;
diff --git a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
index 1099fe0788fa..f246ccbf8838 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
@@ -15,7 +15,7 @@ Required properties:
   include "nvidia,tegra30-ictlr".	
 - reg : Specifies base physical address and size of the registers.
   Each controller must be described separately (Tegra20 has 4 of them,
-  whereas Tegra30 and later have 5"  
+  whereas Tegra30 and later have 5).
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value must be 3.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
index 136bd612bd83..6a36bf66d932 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,stm32-exti.txt
@@ -12,7 +12,7 @@ Required properties:
   specifier, shall be 2
 - interrupts: interrupts references to primary interrupt controller
   (only needed for exti controller with multiple exti under
-  same parent interrupt: st,stm32-exti and st,stm32h7-exti")
+  same parent interrupt: st,stm32-exti and st,stm32h7-exti)
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mips/brcm/soc.txt b/Documentation/devicetree/bindings/mips/brcm/soc.txt
index 356c29789cf5..3a66d3c483e1 100644
--- a/Documentation/devicetree/bindings/mips/brcm/soc.txt
+++ b/Documentation/devicetree/bindings/mips/brcm/soc.txt
@@ -152,7 +152,7 @@ Required properties:
 - compatible	: should contain one of:
 		  "brcm,bcm7425-timers"
 		  "brcm,bcm7429-timers"
-		  "brcm,bcm7435-timers and
+		  "brcm,bcm7435-timers" and
 		  "brcm,brcmstb-timers"
 - reg		: the timers register range
 - interrupts	: the interrupt line for this timer block
diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index df873d1f3b7c..f8c33890bc29 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -238,7 +238,7 @@ PROPERTIES
 		Must include one of the following:
 		- "fsl,fman-dtsec" for dTSEC MAC
 		- "fsl,fman-xgec" for XGEC MAC
-		- "fsl,fman-memac for mEMAC MAC
+		- "fsl,fman-memac" for mEMAC MAC
 
 - cell-index
 		Usage: required
diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 9b387f861aed..7dec508987c7 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -133,7 +133,7 @@ located inside a PM domain with index 0 of a power controller represented by a
 node with the label "power".
 In the second example the consumer device are partitioned across two PM domains,
 the first with index 0 and the second with index 1, of a power controller that
-is represented by a node with the label "power.
+is represented by a node with the label "power".
 
 Optional properties:
 - required-opps: This contains phandle to an OPP node in another device's OPP
diff --git a/Documentation/devicetree/bindings/regulator/tps65090.txt b/Documentation/devicetree/bindings/regulator/tps65090.txt
index ca69f5e3040c..ae326f263597 100644
--- a/Documentation/devicetree/bindings/regulator/tps65090.txt
+++ b/Documentation/devicetree/bindings/regulator/tps65090.txt
@@ -16,7 +16,7 @@ Required properties:
 Optional properties:
 - ti,enable-ext-control: This is applicable for DCDC1, DCDC2 and DCDC3.
   If DCDCs are externally controlled then this property should be there.
-- "dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3.
+- dcdc-ext-control-gpios: This is applicable for DCDC1, DCDC2 and DCDC3.
   If DCDCs are externally controlled and if it is from GPIO then GPIO
   number should be provided. If it is externally controlled and no GPIO
   entry then driver will just configure this rails as external control
diff --git a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
index a21658f18fe6..3661e6153a92 100644
--- a/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
+++ b/Documentation/devicetree/bindings/reset/st,sti-softreset.txt
@@ -15,7 +15,7 @@ Please refer to reset.txt in this directory for common reset
 controller binding usage.
 
 Required properties:
-- compatible: Should be st,stih407-softreset";
+- compatible: Should be "st,stih407-softreset";
 - #reset-cells: 1, see below
 
 example:
diff --git a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt
index d330c73de9a2..68b7d6207e3d 100644
--- a/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt
+++ b/Documentation/devicetree/bindings/soc/qcom/qcom,geni-se.txt
@@ -39,7 +39,7 @@ Required properties:
 
 Optional property:
 - clock-frequency:	Desired I2C bus clock frequency in Hz.
-			When missing default to 400000Hz.
+			When missing default to 100000Hz.
 
 Child nodes should conform to I2C bus binding as described in i2c.txt.
 
diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt
index 6a4aadc4ce06..84b28dbe9f15 100644
--- a/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,apq8016-sbc.txt
@@ -30,7 +30,7 @@ Required properties:
 
 			  Board connectors:
 			  * Headset Mic
-			  * Secondary Mic",
+			  * Secondary Mic
 			  * DMIC
 			  * Ext Spk
 
diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
index aa54e49fc8a2..c7600a93ab39 100644
--- a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
@@ -35,7 +35,7 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio.
 			"Digital Mic3"
 
 		Audio pins and MicBias on WCD9335 Codec:
-			"MIC_BIAS1
+			"MIC_BIAS1"
 			"MIC_BIAS2"
 			"MIC_BIAS3"
 			"MIC_BIAS4"
diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
index 252a05c5d976..c8c4b00ecb94 100644
--- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
@@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of
 the node is not important. The content of the node is defined in dwc3.txt.
 
 Phy documentation is provided in the following places:
-Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt
+Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY
+Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt     - Type-C PHY
 
 Example device nodes:
 
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 698453943789..2afaa633ffc8 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -86,6 +86,7 @@ cubietech	Cubietech, Ltd.
 cypress	Cypress Semiconductor Corporation
 cznic	CZ.NIC, z.s.p.o.
 dallas	Maxim Integrated Products (formerly Dallas Semiconductor)
+dataimage	DataImage, Inc.
 davicom	DAVICOM Semiconductor, Inc.
 delta	Delta Electronics, Inc.
 denx	Denx Software Engineering
@@ -94,6 +95,7 @@ dh	DH electronics GmbH
 digi	Digi International Inc.
 digilent	Diglent, Inc.
 dioo	Dioo Microcircuit Co., Ltd
+dlc	DLC Display Co., Ltd.
 dlg	Dialog Semiconductor
 dlink	D-Link Corporation
 dmo	Data Modul AG
@@ -189,6 +191,7 @@ keymile	Keymile GmbH
 khadas	Khadas
 kiebackpeter    Kieback & Peter GmbH
 kinetic Kinetic Technologies
+kingdisplay	King & Display Technology Co., Ltd.
 kingnovel	Kingnovel Technology Co., Ltd.
 koe	Kaohsiung Opto-Electronics Inc.
 kosagi	Sutajio Ko-Usagi PTE Ltd.
diff --git a/Documentation/devicetree/bindings/w1/w1-gpio.txt b/Documentation/devicetree/bindings/w1/w1-gpio.txt
index 6e09c35d9f1a..37091902a021 100644
--- a/Documentation/devicetree/bindings/w1/w1-gpio.txt
+++ b/Documentation/devicetree/bindings/w1/w1-gpio.txt
@@ -15,7 +15,7 @@ Optional properties:
 
 Examples:
 
-	onewire@0 {
+	onewire {
 		compatible = "w1-gpio";
 		gpios = <&gpio 126 0>, <&gpio 105 0>;
 	};
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index e52d0ce186fe..a740e491dfcc 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -5,6 +5,13 @@
 The drm/amdgpu driver supports all AMD Radeon GPUs based on the Graphics Core
 Next (GCN) architecture.
 
+Module Parameters
+=================
+
+The amdgpu driver supports the following module parameters:
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+
 Core Driver Infrastructure
 ==========================
 
@@ -115,3 +122,8 @@ pp_power_profile_mode
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
    :doc: pp_power_profile_mode
 
+busy_percent
+~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: busy_percent
diff --git a/Documentation/gpu/drm-client.rst b/Documentation/gpu/drm-client.rst
new file mode 100644
index 000000000000..7e672063e7eb
--- /dev/null
+++ b/Documentation/gpu/drm-client.rst
@@ -0,0 +1,12 @@
+=================
+Kernel clients
+=================
+
+.. kernel-doc:: drivers/gpu/drm/drm_client.c
+   :doc: overview
+
+.. kernel-doc:: include/drm/drm_client.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_client.c
+   :export:
diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst
index e37557b30f62..f9cfcdcdf024 100644
--- a/Documentation/gpu/drm-kms-helpers.rst
+++ b/Documentation/gpu/drm-kms-helpers.rst
@@ -109,6 +109,15 @@ Framebuffer CMA Helper Functions Reference
 
 .. _drm_bridges:
 
+Framebuffer GEM Helper Reference
+================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
+   :doc: overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
+   :export:
+
 Bridges
 =======
 
@@ -169,6 +178,15 @@ Display Port Helper Functions Reference
 .. kernel-doc:: drivers/gpu/drm/drm_dp_helper.c
    :export:
 
+Display Port CEC Helper Functions Reference
+===========================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_cec.c
+   :doc: dp cec helpers
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_cec.c
+   :export:
+
 Display Port Dual Mode Adaptor Helper Functions Reference
 =========================================================
 
@@ -282,13 +300,13 @@ Auxiliary Modeset Helpers
 .. kernel-doc:: drivers/gpu/drm/drm_modeset_helper.c
    :export:
 
-Framebuffer GEM Helper Reference
-================================
+OF/DT Helpers
+=============
 
-.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
+.. kernel-doc:: drivers/gpu/drm/drm_of.c
    :doc: overview
 
-.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
+.. kernel-doc:: drivers/gpu/drm/drm_of.c
    :export:
 
 Legacy Plane Helper Reference
diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 514939433004..5dee6b8a4c12 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -56,11 +56,12 @@ Overview
 
 The basic object structure KMS presents to userspace is fairly simple.
 Framebuffers (represented by :c:type:`struct drm_framebuffer <drm_framebuffer>`,
-see `Frame Buffer Abstraction`_) feed into planes. One or more (or even no)
-planes feed their pixel data into a CRTC (represented by :c:type:`struct
-drm_crtc <drm_crtc>`, see `CRTC Abstraction`_) for blending. The precise
-blending step is explained in more detail in `Plane Composition Properties`_ and
-related chapters.
+see `Frame Buffer Abstraction`_) feed into planes. Planes are represented by
+:c:type:`struct drm_plane <drm_plane>`, see `Plane Abstraction`_ for more
+details. One or more (or even no) planes feed their pixel data into a CRTC
+(represented by :c:type:`struct drm_crtc <drm_crtc>`, see `CRTC Abstraction`_)
+for blending. The precise blending step is explained in more detail in `Plane
+Composition Properties`_ and related chapters.
 
 For the output routing the first step is encoders (represented by
 :c:type:`struct drm_encoder <drm_encoder>`, see `Encoder Abstraction`_). Those
@@ -466,7 +467,7 @@ Output discovery and initialization example
         drm_encoder_init(dev, &intel_output->enc, &intel_crt_enc_funcs,
                  DRM_MODE_ENCODER_DAC);
 
-        drm_mode_connector_attach_encoder(&intel_output->base,
+        drm_connector_attach_encoder(&intel_output->base,
                           &intel_output->enc);
 
         /* Set up the DDC bus. */
diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst
index 00288f34c5a6..1fcf8e851e15 100644
--- a/Documentation/gpu/index.rst
+++ b/Documentation/gpu/index.rst
@@ -10,6 +10,7 @@ Linux GPU Driver Developer's Guide
    drm-kms
    drm-kms-helpers
    drm-uapi
+   drm-client
    drivers
    vga-switcheroo
    vgaarbiter
diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst
new file mode 100644
index 000000000000..757cd257e0d8
--- /dev/null
+++ b/Documentation/gpu/msm-crash-dump.rst
@@ -0,0 +1,96 @@
+=====================
+MSM Crash Dump Format
+=====================
+
+Following a GPU hang the MSM driver outputs debugging information via
+/sys/kernel/dri/X/show or via devcoredump (/sys/class/devcoredump/dcdX/data).
+This document describes how the output is formatted.
+
+Each entry is in the form key: value. Sections headers will not have a value
+and all the contents of a section will be indented two spaces from the header.
+Each section might have multiple array entries the start of which is designated
+by a (-).
+
+Mappings
+--------
+
+kernel
+	The kernel version that generated the dump (UTS_RELEASE).
+
+module
+	The module that generated the crashdump.
+
+time
+	The kernel time at crash formated as seconds.microseconds.
+
+comm
+	Comm string for the binary that generated the fault.
+
+cmdline
+	Command line for the binary that generated the fault.
+
+revision
+	ID of the GPU that generated the crash formatted as
+	core.major.minor.patchlevel separated by dots.
+
+rbbm-status
+	The current value of RBBM_STATUS which shows what top level GPU
+	components are in use at the time of crash.
+
+ringbuffer
+	Section containing the contents of each ringbuffer. Each ringbuffer is
+	identified with an id number.
+
+	id
+		Ringbuffer ID (0 based index).  Each ringbuffer in the section
+		will have its own unique id.
+	iova
+		GPU address of the ringbuffer.
+
+	last-fence
+		The last fence that was issued on the ringbuffer
+
+	retired-fence
+		The last fence retired on the ringbuffer.
+
+	rptr
+		The current read pointer (rptr) for the ringbuffer.
+
+	wptr
+		The current write pointer (wptr) for the ringbuffer.
+
+	size
+		Maximum size of the ringbuffer programmed in the hardware.
+
+	data
+		The contents of the ring encoded as ascii85.  Only the used
+		portions of the ring will be printed.
+
+bo
+	List of buffers from the hanging submission if available.
+	Each buffer object will have a uinque iova.
+
+	iova
+		GPU address of the buffer object.
+
+	size
+		Allocated size of the buffer object.
+
+	data
+		The contents of the buffer object encoded with ascii85.  Only
+		Trailing zeros at the end of the buffer will be skipped.
+
+registers
+	Set of registers values. Each entry is on its own line enclosed
+	by brackets { }.
+
+	offset
+		Byte offset of the register from the start of the
+		GPU memory region.
+
+	value
+		Hexadecimal value of the register.
+
+registers-hlsq
+		(5xx only) Register values from the HLSQ aperture.
+		Same format as the register section.
diff --git a/Documentation/gpu/v3d.rst b/Documentation/gpu/v3d.rst
new file mode 100644
index 000000000000..543f7fbf526e
--- /dev/null
+++ b/Documentation/gpu/v3d.rst
@@ -0,0 +1,28 @@
+=====================================
+ drm/v3d Broadcom V3D Graphics Driver
+=====================================
+
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_drv.c
+   :doc: Broadcom V3D Graphics Driver
+
+GPU buffer object (BO) management
+---------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_bo.c
+   :doc: V3D GEM BO management support
+
+Address space management
+===========================================
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_mmu.c
+   :doc: Broadcom V3D MMU
+
+GPU Scheduling
+===========================================
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_sched.c
+   :doc: Broadcom V3D scheduling
+
+Interrupts
+--------------
+
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_irq.c
+   :doc: Interrupt management for the V3D engine
diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt
index 6c9c69ec3986..114c7ce7b58d 100644
--- a/Documentation/kbuild/kbuild.txt
+++ b/Documentation/kbuild/kbuild.txt
@@ -50,6 +50,11 @@ LDFLAGS_MODULE
 --------------------------------------------------
 Additional options used for $(LD) when linking modules.
 
+KBUILD_KCONFIG
+--------------------------------------------------
+Set the top-level Kconfig file to the value of this environment
+variable.  The default name is "Kconfig".
+
 KBUILD_VERBOSE
 --------------------------------------------------
 Set the kbuild verbosity. Can be assigned same values as "V=...".
@@ -88,7 +93,8 @@ In most cases the name of the architecture is the same as the
 directory name found in the arch/ directory.
 But some architectures such as x86 and sparc have aliases.
 x86: i386 for 32 bit, x86_64 for 64 bit
-sparc: sparc for 32 bit, sparc64 for 64 bit
+sh: sh for 32 bit, sh64 for 64 bit
+sparc: sparc32 for 32 bit, sparc64 for 64 bit
 
 CROSS_COMPILE
 --------------------------------------------------
@@ -148,15 +154,6 @@ stripped after they are installed.  If INSTALL_MOD_STRIP is '1', then
 the default option --strip-debug will be used.  Otherwise,
 INSTALL_MOD_STRIP value will be used as the options to the strip command.
 
-INSTALL_FW_PATH
---------------------------------------------------
-INSTALL_FW_PATH specifies where to install the firmware blobs.
-The default value is:
-
-    $(INSTALL_MOD_PATH)/lib/firmware
-
-The value can be overridden in which case the default value is ignored.
-
 INSTALL_HDR_PATH
 --------------------------------------------------
 INSTALL_HDR_PATH specifies where to install user space headers when
diff --git a/Documentation/kbuild/kconfig.txt b/Documentation/kbuild/kconfig.txt
index 7233118f3a05..68c82914c0f3 100644
--- a/Documentation/kbuild/kconfig.txt
+++ b/Documentation/kbuild/kconfig.txt
@@ -2,9 +2,9 @@ This file contains some assistance for using "make *config".
 
 Use "make help" to list all of the possible configuration targets.
 
-The xconfig ('qconf') and menuconfig ('mconf') programs also
-have embedded help text.  Be sure to check it for navigation,
-search, and other general help text.
+The xconfig ('qconf'), menuconfig ('mconf'), and nconfig ('nconf')
+programs also have embedded help text.  Be sure to check that for
+navigation, search, and other general help text.
 
 ======================================================================
 General
@@ -17,13 +17,16 @@ this happens, using a previously working .config file and running
 for you, so you may find that you need to see what NEW kernel
 symbols have been introduced.
 
-To see a list of new config symbols when using "make oldconfig", use
+To see a list of new config symbols, use
 
 	cp user/some/old.config .config
 	make listnewconfig
 
 and the config program will list any new symbols, one per line.
 
+Alternatively, you can use the brute force method:
+
+	make oldconfig
 	scripts/diffconfig .config.old .config | less
 
 ______________________________________________________________________
@@ -160,7 +163,7 @@ Searching in menuconfig:
 		This lists all config symbols that contain "hotplug",
 		e.g., HOTPLUG_CPU, MEMORY_HOTPLUG.
 
-	For search help, enter / followed TAB-TAB-TAB (to highlight
+	For search help, enter / followed by TAB-TAB (to highlight
 	<Help>) and Enter.  This will tell you that you can also use
 	regular expressions (regexes) in the search string, so if you
 	are not interested in MEMORY_HOTPLUG, you could try
@@ -203,6 +206,39 @@ Example:
 
 
 ======================================================================
+nconfig
+--------------------------------------------------
+
+nconfig is an alternate text-based configurator.  It lists function
+keys across the bottom of the terminal (window) that execute commands.
+You can also just use the corresponding numeric key to execute the
+commands unless you are in a data entry window.  E.g., instead of F6
+for Save, you can just press 6.
+
+Use F1 for Global help or F3 for the Short help menu.
+
+Searching in nconfig:
+
+	You can search either in the menu entry "prompt" strings
+	or in the configuration symbols.
+
+	Use / to begin a search through the menu entries.  This does
+	not support regular expressions.  Use <Down> or <Up> for
+	Next hit and Previous hit, respectively.  Use <Esc> to
+	terminate the search mode.
+
+	F8 (SymSearch) searches the configuration symbols for the
+	given string or regular expression (regex).
+
+NCONFIG_MODE
+--------------------------------------------------
+This mode shows all sub-menus in one large tree.
+
+Example:
+	make NCONFIG_MODE=single_menu nconfig
+
+
+======================================================================
 xconfig
 --------------------------------------------------
 
@@ -230,8 +266,7 @@ gconfig
 
 Searching in gconfig:
 
-	None (gconfig isn't maintained as well as xconfig or menuconfig);
-	however, gconfig does have a few more viewing choices than
-	xconfig does.
+	There is no search command in gconfig.  However, gconfig does
+	have several different viewing choices, modes, and options.
 
 ###
diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt
index c13214d073a4..d3e5dd26db12 100644
--- a/Documentation/networking/bonding.txt
+++ b/Documentation/networking/bonding.txt
@@ -1490,7 +1490,7 @@ To remove an ARP target:
 
 To configure the interval between learning packet transmits:
 # echo 12 > /sys/class/net/bond0/bonding/lp_interval
-	NOTE: the lp_inteval is the number of seconds between instances where
+	NOTE: the lp_interval is the number of seconds between instances where
 the bonding driver sends learning packets to each slaves peer switch.  The
 default interval is 1 second.
 
diff --git a/Documentation/networking/e100.rst b/Documentation/networking/e100.rst
index 9708f5fa76de..f81111eba9c5 100644
--- a/Documentation/networking/e100.rst
+++ b/Documentation/networking/e100.rst
@@ -47,41 +47,45 @@ Driver Configuration Parameters
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
-Rx Descriptors: Number of receive descriptors. A receive descriptor is a data
+Rx Descriptors:
+   Number of receive descriptors. A receive descriptor is a data
    structure that describes a receive buffer and its attributes to the network
    controller. The data in the descriptor is used by the controller to write
    data from the controller to host memory. In the 3.x.x driver the valid range
    for this parameter is 64-256. The default value is 256. This parameter can be
    changed using the command::
 
-   ethtool -G eth? rx n
+     ethtool -G eth? rx n
 
    Where n is the number of desired Rx descriptors.
 
-Tx Descriptors: Number of transmit descriptors. A transmit descriptor is a data
+Tx Descriptors:
+   Number of transmit descriptors. A transmit descriptor is a data
    structure that describes a transmit buffer and its attributes to the network
    controller. The data in the descriptor is used by the controller to read
    data from the host memory to the controller. In the 3.x.x driver the valid
    range for this parameter is 64-256. The default value is 128. This parameter
    can be changed using the command::
 
-   ethtool -G eth? tx n
+     ethtool -G eth? tx n
 
    Where n is the number of desired Tx descriptors.
 
-Speed/Duplex: The driver auto-negotiates the link speed and duplex settings by
+Speed/Duplex:
+   The driver auto-negotiates the link speed and duplex settings by
    default. The ethtool utility can be used as follows to force speed/duplex.::
 
-   ethtool -s eth?  autoneg off speed {10|100} duplex {full|half}
+     ethtool -s eth?  autoneg off speed {10|100} duplex {full|half}
 
    NOTE: setting the speed/duplex to incorrect values will cause the link to
    fail.
 
-Event Log Message Level:  The driver uses the message level flag to log events
+Event Log Message Level:
+   The driver uses the message level flag to log events
    to syslog. The message level can be set at driver load time. It can also be
    set using the command::
 
-   ethtool -s eth? msglvl n
+     ethtool -s eth? msglvl n
 
 
 Additional Configurations
@@ -92,7 +96,7 @@ Configuring the Driver on Different Distributions
 
 Configuring a network driver to load properly when the system is started
 is distribution dependent.  Typically, the configuration process involves
-adding an alias line to /etc/modprobe.d/*.conf as well as editing other
+adding an alias line to `/etc/modprobe.d/*.conf` as well as editing other
 system startup scripts and/or configuration files.  Many popular Linux
 distributions ship with tools to make these changes for you.  To learn
 the proper way to configure a network device for your system, refer to
@@ -160,7 +164,10 @@ This results in unbalanced receive traffic.
 If you have multiple interfaces in a server, either turn on ARP
 filtering by
 
-(1) entering:: echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+(1) entering::
+
+	echo 1 > /proc/sys/net/ipv4/conf/all/arp_filter
+
     (this only works if your kernel's version is higher than 2.4.5), or
 
 (2) installing the interfaces in separate broadcast domains (either
diff --git a/Documentation/networking/e1000.rst b/Documentation/networking/e1000.rst
index 144b87eef153..f10dd4086921 100644
--- a/Documentation/networking/e1000.rst
+++ b/Documentation/networking/e1000.rst
@@ -34,7 +34,8 @@ Command Line Parameters
 The default value for each parameter is generally the recommended setting,
 unless otherwise noted.
 
-NOTES:  For more information about the AutoNeg, Duplex, and Speed
+NOTES:
+	For more information about the AutoNeg, Duplex, and Speed
         parameters, see the "Speed and Duplex Configuration" section in
         this document.
 
@@ -45,22 +46,27 @@ NOTES:  For more information about the AutoNeg, Duplex, and Speed
 
 AutoNeg
 -------
+
 (Supported only on adapters with copper connections)
-Valid Range:   0x01-0x0F, 0x20-0x2F
-Default Value: 0x2F
+
+:Valid Range:   0x01-0x0F, 0x20-0x2F
+:Default Value: 0x2F
 
 This parameter is a bit-mask that specifies the speed and duplex settings
 advertised by the adapter.  When this parameter is used, the Speed and
 Duplex parameters must not be specified.
 
-NOTE:  Refer to the Speed and Duplex section of this readme for more
+NOTE:
+       Refer to the Speed and Duplex section of this readme for more
        information on the AutoNeg parameter.
 
 Duplex
 ------
+
 (Supported only on adapters with copper connections)
-Valid Range:   0-2 (0=auto-negotiate, 1=half, 2=full)
-Default Value: 0
+
+:Valid Range:   0-2 (0=auto-negotiate, 1=half, 2=full)
+:Default Value: 0
 
 This defines the direction in which data is allowed to flow.  Can be
 either one or two-directional.  If both Duplex and the link partner are
@@ -70,18 +76,22 @@ duplex.
 
 FlowControl
 -----------
-Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
-Default Value: Reads flow control settings from the EEPROM
+
+:Valid Range:   0-3 (0=none, 1=Rx only, 2=Tx only, 3=Rx&Tx)
+:Default Value: Reads flow control settings from the EEPROM
 
 This parameter controls the automatic generation(Tx) and response(Rx)
 to Ethernet PAUSE frames.
 
 InterruptThrottleRate
 ---------------------
+
 (not supported on Intel(R) 82542, 82543 or 82544-based adapters)
-Valid Range:   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
-                                 4=simplified balancing)
-Default Value: 3
+
+:Valid Range:
+   0,1,3,4,100-100000 (0=off, 1=dynamic, 3=dynamic conservative,
+   4=simplified balancing)
+:Default Value: 3
 
 The driver can limit the amount of interrupts per second that the adapter
 will generate for incoming packets. It does this by writing a value to the
@@ -135,13 +145,15 @@ Setting InterruptThrottleRate to 0 turns off any interrupt moderation
 and may improve small packet latency, but is generally not suitable
 for bulk throughput traffic.
 
-NOTE:  InterruptThrottleRate takes precedence over the TxAbsIntDelay and
+NOTE:
+       InterruptThrottleRate takes precedence over the TxAbsIntDelay and
        RxAbsIntDelay parameters.  In other words, minimizing the receive
        and/or transmit absolute delays does not force the controller to
        generate more interrupts than what the Interrupt Throttle Rate
        allows.
 
-CAUTION:  If you are using the Intel(R) PRO/1000 CT Network Connection
+CAUTION:
+          If you are using the Intel(R) PRO/1000 CT Network Connection
           (controller 82547), setting InterruptThrottleRate to a value
           greater than 75,000, may hang (stop transmitting) adapters
           under certain network conditions.  If this occurs a NETDEV
@@ -151,7 +163,8 @@ CAUTION:  If you are using the Intel(R) PRO/1000 CT Network Connection
           hang, ensure that InterruptThrottleRate is set no greater
           than 75,000 and is not set to 0.
 
-NOTE:  When e1000 is loaded with default settings and multiple adapters
+NOTE:
+       When e1000 is loaded with default settings and multiple adapters
        are in use simultaneously, the CPU utilization may increase non-
        linearly.  In order to limit the CPU utilization without impacting
        the overall throughput, we recommend that you load the driver as
@@ -168,9 +181,11 @@ NOTE:  When e1000 is loaded with default settings and multiple adapters
 
 RxDescriptors
 -------------
-Valid Range:   48-256 for 82542 and 82543-based adapters
-               48-4096 for all other supported adapters
-Default Value: 256
+
+:Valid Range:
+ - 48-256 for 82542 and 82543-based adapters
+ - 48-4096 for all other supported adapters
+:Default Value: 256
 
 This value specifies the number of receive buffer descriptors allocated
 by the driver.  Increasing this value allows the driver to buffer more
@@ -180,15 +195,17 @@ Each descriptor is 16 bytes.  A receive buffer is also allocated for each
 descriptor and can be either 2048, 4096, 8192, or 16384 bytes, depending
 on the MTU setting. The maximum MTU size is 16110.
 
-NOTE:  MTU designates the frame size.  It only needs to be set for Jumbo
+NOTE:
+       MTU designates the frame size.  It only needs to be set for Jumbo
        Frames.  Depending on the available system resources, the request
        for a higher number of receive descriptors may be denied.  In this
        case, use a lower number.
 
 RxIntDelay
 ----------
-Valid Range:   0-65535 (0=off)
-Default Value: 0
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 0
 
 This value delays the generation of receive interrupts in units of 1.024
 microseconds.  Receive interrupt reduction can improve CPU efficiency if
@@ -198,7 +215,8 @@ of TCP traffic.  If the system is reporting dropped receives, this value
 may be set too high, causing the driver to run out of available receive
 descriptors.
 
-CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
+CAUTION:
+          When setting RxIntDelay to a value other than 0, adapters may
           hang (stop transmitting) under certain network conditions.  If
           this occurs a NETDEV WATCHDOG message is logged in the system
           event log.  In addition, the controller is automatically reset,
@@ -207,9 +225,11 @@ CAUTION:  When setting RxIntDelay to a value other than 0, adapters may
 
 RxAbsIntDelay
 -------------
+
 (This parameter is supported only on 82540, 82545 and later adapters.)
-Valid Range:   0-65535 (0=off)
-Default Value: 128
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 128
 
 This value, in units of 1.024 microseconds, limits the delay in which a
 receive interrupt is generated.  Useful only if RxIntDelay is non-zero,
@@ -220,9 +240,11 @@ conditions.
 
 Speed
 -----
+
 (This parameter is supported only on adapters with copper connections.)
-Valid Settings: 0, 10, 100, 1000
-Default Value:  0 (auto-negotiate at all supported speeds)
+
+:Valid Settings: 0, 10, 100, 1000
+:Default Value:  0 (auto-negotiate at all supported speeds)
 
 Speed forces the line speed to the specified value in megabits per second
 (Mbps).  If this parameter is not specified or is set to 0 and the link
@@ -231,22 +253,26 @@ speed.  Duplex should also be set when Speed is set to either 10 or 100.
 
 TxDescriptors
 -------------
-Valid Range:   48-256 for 82542 and 82543-based adapters
-               48-4096 for all other supported adapters
-Default Value: 256
+
+:Valid Range:
+  - 48-256 for 82542 and 82543-based adapters
+  - 48-4096 for all other supported adapters
+:Default Value: 256
 
 This value is the number of transmit descriptors allocated by the driver.
 Increasing this value allows the driver to queue more transmits.  Each
 descriptor is 16 bytes.
 
-NOTE:  Depending on the available system resources, the request for a
+NOTE:
+       Depending on the available system resources, the request for a
        higher number of transmit descriptors may be denied.  In this case,
        use a lower number.
 
 TxIntDelay
 ----------
-Valid Range:   0-65535 (0=off)
-Default Value: 8
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 8
 
 This value delays the generation of transmit interrupts in units of
 1.024 microseconds.  Transmit interrupt reduction can improve CPU
@@ -256,9 +282,11 @@ causing the driver to run out of available transmit descriptors.
 
 TxAbsIntDelay
 -------------
+
 (This parameter is supported only on 82540, 82545 and later adapters.)
-Valid Range:   0-65535 (0=off)
-Default Value: 32
+
+:Valid Range:   0-65535 (0=off)
+:Default Value: 32
 
 This value, in units of 1.024 microseconds, limits the delay in which a
 transmit interrupt is generated.  Useful only if TxIntDelay is non-zero,
@@ -269,18 +297,21 @@ network conditions.
 
 XsumRX
 ------
+
 (This parameter is NOT supported on the 82542-based adapter.)
-Valid Range:   0-1
-Default Value: 1
+
+:Valid Range:   0-1
+:Default Value: 1
 
 A value of '1' indicates that the driver should enable IP checksum
 offload for received packets (both UDP and TCP) to the adapter hardware.
 
 Copybreak
 ---------
-Valid Range:   0-xxxxxxx (0=off)
-Default Value: 256
-Usage: modprobe e1000.ko copybreak=128
+
+:Valid Range:   0-xxxxxxx (0=off)
+:Default Value: 256
+:Usage: modprobe e1000.ko copybreak=128
 
 Driver copies all packets below or equaling this size to a fresh RX
 buffer before handing it up the stack.
@@ -292,8 +323,9 @@ it is also available during runtime at
 
 SmartPowerDownEnable
 --------------------
-Valid Range: 0-1
-Default Value:  0 (disabled)
+
+:Valid Range: 0-1
+:Default Value:  0 (disabled)
 
 Allows PHY to turn off in lower power states. The user can turn off
 this parameter in supported chipsets.
@@ -309,14 +341,14 @@ fiber interface board only links at 1000 Mbps full-duplex.
 
 For copper-based boards, the keywords interact as follows:
 
-  The default operation is auto-negotiate.  The board advertises all
+- The default operation is auto-negotiate.  The board advertises all
   supported speed and duplex combinations, and it links at the highest
   common speed and duplex mode IF the link partner is set to auto-negotiate.
 
-  If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
+- If Speed = 1000, limited auto-negotiation is enabled and only 1000 Mbps
   is advertised (The 1000BaseT spec requires auto-negotiation.)
 
-  If Speed = 10 or 100, then both Speed and Duplex should be set.  Auto-
+- If Speed = 10 or 100, then both Speed and Duplex should be set.  Auto-
   negotiation is disabled, and the AutoNeg parameter is ignored.  Partner
   SHOULD also be forced.
 
@@ -328,13 +360,15 @@ process.
 The parameter may be specified as either a decimal or hexadecimal value as
 determined by the bitmap below.
 
+============== ====== ====== ======= ======= ====== ====== ======= ======
 Bit position   7      6      5       4       3      2      1       0
 Decimal Value  128    64     32      16      8      4      2       1
 Hex value      80     40     20      10      8      4      2       1
 Speed (Mbps)   N/A    N/A    1000    N/A     100    100    10      10
 Duplex                       Full            Full   Half   Full    Half
+============== ====== ====== ======= ======= ====== ====== ======= ======
 
-Some examples of using AutoNeg:
+Some examples of using AutoNeg::
 
   modprobe e1000 AutoNeg=0x01 (Restricts autonegotiation to 10 Half)
   modprobe e1000 AutoNeg=1 (Same as above)
@@ -357,56 +391,59 @@ Additional Configurations
 
 Jumbo Frames
 ------------
-Jumbo Frames support is enabled by changing the MTU to a value larger
-than the default of 1500.  Use the ifconfig command to increase the MTU
-size.  For example::
+
+  Jumbo Frames support is enabled by changing the MTU to a value larger than
+  the default of 1500.  Use the ifconfig command to increase the MTU size.
+  For example::
 
        ifconfig eth<x> mtu 9000 up
 
-This setting is not saved across reboots.  It can be made permanent if
-you add::
+  This setting is not saved across reboots.  It can be made permanent if
+  you add::
 
        MTU=9000
 
-to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
-applies to the Red Hat distributions; other distributions may store this
-setting in a different location.
+  to the file /etc/sysconfig/network-scripts/ifcfg-eth<x>.  This example
+  applies to the Red Hat distributions; other distributions may store this
+  setting in a different location.
+
+Notes:
+  Degradation in throughput performance may be observed in some Jumbo frames
+  environments. If this is observed, increasing the application's socket buffer
+  size and/or increasing the /proc/sys/net/ipv4/tcp_*mem entry values may help.
+  See the specific application manual and /usr/src/linux*/Documentation/
+  networking/ip-sysctl.txt for more details.
 
-Notes: Degradation in throughput performance may be observed in some
-Jumbo frames environments.  If this is observed, increasing the
-application's socket buffer size and/or increasing the
-/proc/sys/net/ipv4/tcp_*mem entry values may help.  See the specific
-application manual and /usr/src/linux*/Documentation/
-networking/ip-sysctl.txt for more details.
+  - The maximum MTU setting for Jumbo Frames is 16110.  This value coincides
+    with the maximum Jumbo Frames size of 16128.
 
-- The maximum MTU setting for Jumbo Frames is 16110.  This value
-  coincides with the maximum Jumbo Frames size of 16128.
+  - Using Jumbo frames at 10 or 100 Mbps is not supported and may result in
+    poor performance or loss of link.
 
-- Using Jumbo frames at 10 or 100 Mbps is not supported and may result
-  in poor performance or loss of link.
+  - Adapters based on the Intel(R) 82542 and 82573V/E controller do not
+    support Jumbo Frames. These correspond to the following product names::
 
-- Adapters based on the Intel(R) 82542 and 82573V/E controller do not
-  support Jumbo Frames.  These correspond to the following product names:
-  Intel(R) PRO/1000 Gigabit Server Adapter Intel(R) PRO/1000 PM Network
-  Connection
+     Intel(R) PRO/1000 Gigabit Server Adapter
+     Intel(R) PRO/1000 PM Network Connection
 
 ethtool
 -------
-The driver utilizes the ethtool interface for driver configuration and
-diagnostics, as well as displaying statistical information.  The ethtool
-version 1.6 or later is required for this functionality.
 
-The latest release of ethtool can be found from
-https://www.kernel.org/pub/software/network/ethtool/
+  The driver utilizes the ethtool interface for driver configuration and
+  diagnostics, as well as displaying statistical information.  The ethtool
+  version 1.6 or later is required for this functionality.
+
+  The latest release of ethtool can be found from
+  https://www.kernel.org/pub/software/network/ethtool/
 
 Enabling Wake on LAN* (WoL)
 ---------------------------
-WoL is configured through the ethtool* utility.
 
-WoL will be enabled on the system during the next shut down or reboot.
-For this driver version, in order to enable WoL, the e1000 driver must be
-loaded when shutting down or rebooting the system.
+  WoL is configured through the ethtool* utility.
 
+  WoL will be enabled on the system during the next shut down or reboot.
+  For this driver version, in order to enable WoL, the e1000 driver must be
+  loaded when shutting down or rebooting the system.
 
 Support
 =======
diff --git a/MAINTAINERS b/MAINTAINERS
index 07d1576fc766..9b2bf134964e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -581,7 +581,7 @@ W:	https://www.infradead.org/~dhowells/kafs/
 
 AGPGART DRIVER
 M:	David Airlie <airlied@linux.ie>
-T:	git git://people.freedesktop.org/~airlied/linux (part of drm maint)
+T:	git git://anongit.freedesktop.org/drm/drm
 S:	Maintained
 F:	drivers/char/agp/
 F:	include/linux/agp*
@@ -728,6 +728,14 @@ S:	Supported
 F:	drivers/crypto/ccp/
 F:	include/linux/ccp.h
 
+AMD DISPLAY CORE
+M:	Harry Wentland <harry.wentland@amd.com>
+M:	Leo Li <sunpeng.li@amd.com>
+L:	amd-gfx@lists.freedesktop.org
+T:	git git://people.freedesktop.org/~agd5f/linux
+S:	Supported
+F:	drivers/gpu/drm/amd/display/
+
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
 M:	Huang Rui <ray.huang@amd.com>
 L:	linux-hwmon@vger.kernel.org
@@ -777,6 +785,14 @@ F:	drivers/gpu/drm/amd/include/vi_structs.h
 F:	drivers/gpu/drm/amd/include/v9_structs.h
 F:	include/uapi/linux/kfd_ioctl.h
 
+AMD POWERPLAY
+M:	Rex Zhu <rex.zhu@amd.com>
+M:	Evan Quan <evan.quan@amd.com>
+L:	amd-gfx@lists.freedesktop.org
+S:	Supported
+F:	drivers/gpu/drm/amd/powerplay/
+T:	git git://people.freedesktop.org/~agd5f/linux
+
 AMD SEATTLE DEVICE TREE SUPPORT
 M:	Brijesh Singh <brijeshkumar.singh@amd.com>
 M:	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
@@ -2523,7 +2539,7 @@ S:	Supported
 F:	drivers/scsi/esas2r
 
 ATUSB IEEE 802.15.4 RADIO DRIVER
-M:	Stefan Schmidt <stefan@osg.samsung.com>
+M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ieee802154/atusb.c
@@ -4460,6 +4476,7 @@ F:	Documentation/blockdev/drbd/
 
 DRIVER CORE, KOBJECTS, DEBUGFS AND SYSFS
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+R:	"Rafael J. Wysocki" <rafael@kernel.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core.git
 S:	Supported
 F:	Documentation/kobject.txt
@@ -4630,7 +4647,7 @@ F:	include/uapi/drm/vmwgfx_drm.h
 DRM DRIVERS
 M:	David Airlie <airlied@linux.ie>
 L:	dri-devel@lists.freedesktop.org
-T:	git git://people.freedesktop.org/~airlied/linux
+T:	git git://anongit.freedesktop.org/drm/drm
 B:	https://bugs.freedesktop.org/
 C:	irc://chat.freenode.net/dri-devel
 S:	Maintained
@@ -4883,7 +4900,8 @@ F:	Documentation/gpu/xen-front.rst
 
 DRM TTM SUBSYSTEM
 M:	Christian Koenig <christian.koenig@amd.com>
-M:	Roger He <Hongbo.He@amd.com>
+M:	Huang Rui <ray.huang@amd.com>
+M:	Junwei Zhang <Jerry.Zhang@amd.com>
 T:	git git://people.freedesktop.org/~agd5f/linux
 S:	Maintained
 L:	dri-devel@lists.freedesktop.org
@@ -5789,7 +5807,6 @@ F:	include/linux/fsl/
 
 FREESCALE SOC FS_ENET DRIVER
 M:	Pantelis Antoniou <pantelis.antoniou@gmail.com>
-M:	Vitaly Bordug <vbordug@ru.mvista.com>
 L:	linuxppc-dev@lists.ozlabs.org
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -6908,7 +6925,7 @@ F:	drivers/clk/clk-versaclock5.c
 
 IEEE 802.15.4 SUBSYSTEM
 M:	Alexander Aring <alex.aring@gmail.com>
-M:	Stefan Schmidt <stefan@osg.samsung.com>
+M:	Stefan Schmidt <stefan@datenfreihafen.org>
 L:	linux-wpan@vger.kernel.org
 W:	http://wpan.cakelab.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sschmidt/wpan.git
@@ -7095,6 +7112,7 @@ F:	include/uapi/linux/input.h
 F:	include/uapi/linux/input-event-codes.h
 F:	include/linux/input/
 F:	Documentation/devicetree/bindings/input/
+F:	Documentation/devicetree/bindings/serio/
 F:	Documentation/input/
 
 INPUT MULTITOUCH (MT) PROTOCOL
@@ -8628,7 +8646,7 @@ MARVELL MWIFIEX WIRELESS DRIVER
 M:	Amitkumar Karwar <amitkarwar@gmail.com>
 M:	Nishant Sarmukadam <nishants@marvell.com>
 M:	Ganapathi Bhat <gbhat@marvell.com>
-M:	Xinming Hu <huxm@marvell.com>
+M:	Xinming Hu <huxinming820@gmail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 F:	drivers/net/wireless/marvell/mwifiex/
@@ -9074,7 +9092,7 @@ S:	Maintained
 F:	drivers/usb/mtu3/
 
 MEGACHIPS STDPXXXX-GE-B850V3-FW LVDS/DP++ BRIDGES
-M:	Peter Senna Tschudin <peter.senna@collabora.com>
+M:	Peter Senna Tschudin <peter.senna@gmail.com>
 M:	Martin Donnelly <martin.donnelly@ge.com>
 M:	Martyn Welch <martyn.welch@collabora.co.uk>
 S:	Maintained
@@ -10213,11 +10231,13 @@ F:	sound/soc/codecs/sgtl5000*
 
 NXP TDA998X DRM DRIVER
 M:	Russell King <linux@armlinux.org.uk>
-S:	Supported
+S:	Maintained
 T:	git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-devel
 T:	git git://git.armlinux.org.uk/~rmk/linux-arm.git drm-tda998x-fixes
 F:	drivers/gpu/drm/i2c/tda998x_drv.c
 F:	include/drm/i2c/tda998x.h
+F:	include/dt-bindings/display/tda998x.h
+K:	"nxp,tda998x"
 
 NXP TFA9879 DRIVER
 M:	Peter Rosin <peda@axentia.se>
@@ -11835,7 +11855,7 @@ S:	Supported
 F:	arch/hexagon/
 
 QUALCOMM HIDMA DRIVER
-M:	Sinan Kaya <okaya@codeaurora.org>
+M:	Sinan Kaya <okaya@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org
 L:	linux-arm-msm@vger.kernel.org
 L:	dmaengine@vger.kernel.org
diff --git a/Makefile b/Makefile
index c5ce55cbc543..85f3481a56d6 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 18
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc7
 NAME = Merciless Moray
 
 # *DOCUMENTATION*
@@ -353,9 +353,9 @@ CONFIG_SHELL := $(shell if [ -x "$$BASH" ]; then echo $$BASH; \
 	  else if [ -x /bin/bash ]; then echo /bin/bash; \
 	  else echo sh; fi ; fi)
 
-HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS)
-HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS)
-HOST_LFS_LIBS := $(shell getconf LFS_LIBS)
+HOST_LFS_CFLAGS := $(shell getconf LFS_CFLAGS 2>/dev/null)
+HOST_LFS_LDFLAGS := $(shell getconf LFS_LDFLAGS 2>/dev/null)
+HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null)
 
 HOSTCC       = gcc
 HOSTCXX      = g++
@@ -507,11 +507,6 @@ ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-goto.sh $(CC) $(KBUILD_CFLA
   KBUILD_AFLAGS += -DCC_HAVE_ASM_GOTO
 endif
 
-ifeq ($(shell $(CONFIG_SHELL) $(srctree)/scripts/cc-can-link.sh $(CC)), y)
-  CC_CAN_LINK := y
-  export CC_CAN_LINK
-endif
-
 # The expansion should be delayed until arch/$(SRCARCH)/Makefile is included.
 # Some architectures define CROSS_COMPILE in arch/$(SRCARCH)/Makefile.
 # CC_VERSION_TEXT is referenced from Kconfig (so it needs export),
@@ -1717,6 +1712,6 @@ endif	# skip-makefile
 PHONY += FORCE
 FORCE:
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
+# Declare the contents of the PHONY variable as phony.  We keep that
 # information in a variable so we can use it in if_changed and friends.
 .PHONY: $(PHONY)
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c
index 6e921754c8fc..c210a25dd6da 100644
--- a/arch/alpha/kernel/osf_sys.c
+++ b/arch/alpha/kernel/osf_sys.c
@@ -1180,13 +1180,10 @@ SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru)
 SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options,
 		struct rusage32 __user *, ur)
 {
-	unsigned int status = 0;
 	struct rusage r;
-	long err = kernel_wait4(pid, &status, options, &r);
+	long err = kernel_wait4(pid, ustatus, options, &r);
 	if (err <= 0)
 		return err;
-	if (put_user(status, ustatus))
-		return -EFAULT;
 	if (!ur)
 		return err;
 	if (put_tv_to_tv32(&ur->ru_utime, &r.ru_utime))
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e81bcd271be7..9cf59fc60eab 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -413,7 +413,7 @@ config ARC_HAS_DIV_REM
 
 config ARC_HAS_ACCL_REGS
 	bool "Reg Pair ACCL:ACCH (FPU and/or MPY > 6)"
-	default n
+	default y
 	help
 	  Depending on the configuration, CPU can contain accumulator reg-pair
 	  (also referred to as r58:r59). These can also be used by gcc as GPR so
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index d37f49d6a27f..6c1b20dd76ad 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -16,7 +16,7 @@ endif
 
 KBUILD_DEFCONFIG := nsim_700_defconfig
 
-cflags-y	+= -fno-common -pipe -fno-builtin -D__linux__
+cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
 cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
 
@@ -140,16 +140,3 @@ dtbs: scripts
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
-
-# Hacks to enable final link due to absence of link-time branch relexation
-# and gcc choosing optimal(shorter) branches at -O3
-#
-# vineetg Feb 2010: -mlong-calls switched off for overall kernel build
-# However lib/decompress_inflate.o (.init.text) calls
-# zlib_inflate_workspacesize (.text) causing relocation errors.
-# Thus forcing all exten calls in this file to be long calls
-export CFLAGS_decompress_inflate.o = -mmedium-calls
-export CFLAGS_initramfs.o = -mmedium-calls
-ifdef CONFIG_SMP
-export CFLAGS_core.o = -mmedium-calls
-endif
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 09f85154c5a4..a635ea972304 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 09fed3ef22b6..aa507e423075 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index ea2f6d817d1a..eba07f468654 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig
index ab231c040efe..098b19fbaa51 100644
--- a/arch/arc/configs/haps_hs_defconfig
+++ b/arch/arc/configs/haps_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EXPERT=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index cf449cbf440d..0104c404d897 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 1b54c72f4296..6491be0ddbc9 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig
index 31c2c70b34a1..99e05cf63fca 100644
--- a/arch/arc/configs/nsim_700_defconfig
+++ b/arch/arc/configs/nsim_700_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig
index a578c721d50f..0dc4f9b737e7 100644
--- a/arch/arc/configs/nsim_hs_defconfig
+++ b/arch/arc/configs/nsim_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig
index 37d7395f3272..be3c30a15e54 100644
--- a/arch/arc/configs/nsim_hs_smp_defconfig
+++ b/arch/arc/configs/nsim_hs_smp_defconfig
@@ -9,7 +9,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig
index 1e1470e2a7f0..3a74b9b21772 100644
--- a/arch/arc/configs/nsimosci_defconfig
+++ b/arch/arc/configs/nsimosci_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig
index 084a6e42685b..ea2834b4dc1d 100644
--- a/arch/arc/configs/nsimosci_hs_defconfig
+++ b/arch/arc/configs/nsimosci_hs_defconfig
@@ -11,7 +11,6 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_KALLSYMS_ALL=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig
index f36d47990415..80a5a1b4924b 100644
--- a/arch/arc/configs/nsimosci_hs_smp_defconfig
+++ b/arch/arc/configs/nsimosci_hs_smp_defconfig
@@ -9,7 +9,6 @@ CONFIG_IKCONFIG_PROC=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
-CONFIG_INITRAMFS_SOURCE="../arc_initramfs_hs/"
 CONFIG_PERF_EVENTS=y
 # CONFIG_COMPAT_BRK is not set
 CONFIG_KPROBES=y
diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig
index 1aca2e8fd1ba..2cc87f909747 100644
--- a/arch/arc/configs/tb10x_defconfig
+++ b/arch/arc/configs/tb10x_defconfig
@@ -56,7 +56,6 @@ CONFIG_STMMAC_ETH=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
-CONFIG_DEVPTS_MULTIPLE_INSTANCES=y
 # CONFIG_LEGACY_PTYS is not set
 # CONFIG_DEVKMEM is not set
 CONFIG_SERIAL_8250=y
diff --git a/arch/arc/include/asm/entry-compact.h b/arch/arc/include/asm/entry-compact.h
index ec36d5b6d435..29f3988c9424 100644
--- a/arch/arc/include/asm/entry-compact.h
+++ b/arch/arc/include/asm/entry-compact.h
@@ -234,6 +234,9 @@
 	POP	gp
 	RESTORE_R12_TO_R0
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld	r25, [sp, 12]
+#endif
 	ld  sp, [sp] /* restore original sp */
 	/* orig_r0, ECR, user_r25 skipped automatically */
 .endm
@@ -315,6 +318,9 @@
 	POP	gp
 	RESTORE_R12_TO_R0
 
+#ifdef CONFIG_ARC_CURR_IN_REG
+	ld	r25, [sp, 12]
+#endif
 	ld  sp, [sp] /* restore original sp */
 	/* orig_r0, ECR, user_r25 skipped automatically */
 .endm
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index 51597f344a62..302b0db8ea2b 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -86,9 +86,6 @@
 	POP	r1
 	POP	r0
 
-#ifdef CONFIG_ARC_CURR_IN_REG
-	ld	r25, [sp, 12]
-#endif
 .endm
 
 /*--------------------------------------------------------------
diff --git a/arch/arc/include/asm/mach_desc.h b/arch/arc/include/asm/mach_desc.h
index c28e6c347b49..871f3cb16af9 100644
--- a/arch/arc/include/asm/mach_desc.h
+++ b/arch/arc/include/asm/mach_desc.h
@@ -34,9 +34,7 @@ struct machine_desc {
 	const char		*name;
 	const char		**dt_compat;
 	void			(*init_early)(void);
-#ifdef CONFIG_SMP
 	void			(*init_per_cpu)(unsigned int);
-#endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
 
diff --git a/arch/arc/include/asm/page.h b/arch/arc/include/asm/page.h
index 109baa06831c..09ddddf71cc5 100644
--- a/arch/arc/include/asm/page.h
+++ b/arch/arc/include/asm/page.h
@@ -105,7 +105,7 @@ typedef pte_t * pgtable_t;
 #define virt_addr_valid(kaddr)  pfn_valid(virt_to_pfn(kaddr))
 
 /* Default Permissions for stack/heaps pages (Non Executable) */
-#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE)
+#define VM_DATA_DEFAULT_FLAGS   (VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #define WANT_PAGE_VIRTUAL   1
 
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 8ec5599a0957..cf4be70d5892 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -377,7 +377,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
 
 /* Decode a PTE containing swap "identifier "into constituents */
 #define __swp_type(pte_lookalike)	(((pte_lookalike).val) & 0x1f)
-#define __swp_offset(pte_lookalike)	((pte_lookalike).val << 13)
+#define __swp_offset(pte_lookalike)	((pte_lookalike).val >> 13)
 
 /* NOPs, to keep generic kernel happy */
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
diff --git a/arch/arc/kernel/irq.c b/arch/arc/kernel/irq.c
index 538b36afe89e..62b185057c04 100644
--- a/arch/arc/kernel/irq.c
+++ b/arch/arc/kernel/irq.c
@@ -31,10 +31,10 @@ void __init init_IRQ(void)
 	/* a SMP H/w block could do IPI IRQ request here */
 	if (plat_smp_ops.init_per_cpu)
 		plat_smp_ops.init_per_cpu(smp_processor_id());
+#endif
 
 	if (machine_desc->init_per_cpu)
 		machine_desc->init_per_cpu(smp_processor_id());
-#endif
 }
 
 /*
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 5ac3b547453f..4674541eba3f 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -47,7 +47,8 @@ SYSCALL_DEFINE0(arc_gettls)
 SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 {
 	struct pt_regs *regs = current_pt_regs();
-	int uval = -EFAULT;
+	u32 uval;
+	int ret;
 
 	/*
 	 * This is only for old cores lacking LLOCK/SCOND, which by defintion
@@ -60,23 +61,47 @@ SYSCALL_DEFINE3(arc_usr_cmpxchg, int *, uaddr, int, expected, int, new)
 	/* Z indicates to userspace if operation succeded */
 	regs->status32 &= ~STATUS_Z_MASK;
 
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
+	ret = access_ok(VERIFY_WRITE, uaddr, sizeof(*uaddr));
+	if (!ret)
+		 goto fail;
 
+again:
 	preempt_disable();
 
-	if (__get_user(uval, uaddr))
-		goto done;
+	ret = __get_user(uval, uaddr);
+	if (ret)
+		 goto fault;
 
-	if (uval == expected) {
-		if (!__put_user(new, uaddr))
-			regs->status32 |= STATUS_Z_MASK;
-	}
+	if (uval != expected)
+		 goto out;
 
-done:
-	preempt_enable();
+	ret = __put_user(new, uaddr);
+	if (ret)
+		 goto fault;
+
+	regs->status32 |= STATUS_Z_MASK;
 
+out:
+	preempt_enable();
 	return uval;
+
+fault:
+	preempt_enable();
+
+	if (unlikely(ret != -EFAULT))
+		 goto fail;
+
+	down_read(&current->mm->mmap_sem);
+	ret = fixup_user_fault(current, current->mm, (unsigned long) uaddr,
+			       FAULT_FLAG_WRITE, NULL);
+	up_read(&current->mm->mmap_sem);
+
+	if (likely(!ret))
+		 goto again;
+
+fail:
+	force_sig(SIGSEGV, current);
+	return ret;
 }
 
 #ifdef CONFIG_ISA_ARCV2
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 19ab3cf98f0f..9356753c2ed8 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -7,5 +7,8 @@
 
 menuconfig ARC_SOC_HSDK
 	bool "ARC HS Development Kit SOC"
+	depends on ISA_ARCV2
+	select ARC_HAS_ACCL_REGS
 	select CLK_HSDK
 	select RESET_HSDK
+	select MIGHT_HAVE_PCI
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index 2958aedb649a..2588b842407c 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -42,6 +42,66 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
 #define SDIO_UHS_REG_EXT	(SDIO_BASE + 0x108)
 #define SDIO_UHS_REG_EXT_DIV_2	(2 << 30)
 
+#define HSDK_GPIO_INTC          (ARC_PERIPHERAL_BASE + 0x3000)
+
+static void __init hsdk_enable_gpio_intc_wire(void)
+{
+	/*
+	 * Peripherals on CPU Card are wired to cpu intc via intermediate
+	 * DW APB GPIO blocks (mainly for debouncing)
+	 *
+	 *         ---------------------
+	 *        |  snps,archs-intc  |
+	 *        ---------------------
+	 *                  |
+	 *        ----------------------
+	 *        | snps,archs-idu-intc |
+	 *        ----------------------
+	 *         |   |     |   |    |
+	 *         | [eth] [USB]    [... other peripherals]
+	 *         |
+	 * -------------------
+	 * | snps,dw-apb-intc |
+	 * -------------------
+	 *  |      |   |   |
+	 * [Bt] [HAPS]   [... other peripherals]
+	 *
+	 * Current implementation of "irq-dw-apb-ictl" driver doesn't work well
+	 * with stacked INTCs. In particular problem happens if its master INTC
+	 * not yet instantiated. See discussion here -
+	 * https://lkml.org/lkml/2015/3/4/755
+	 *
+	 * So setup the first gpio block as a passive pass thru and hide it from
+	 * DT hardware topology - connect intc directly to cpu intc
+	 * The GPIO "wire" needs to be init nevertheless (here)
+	 *
+	 * One side adv is that peripheral interrupt handling avoids one nested
+	 * intc ISR hop
+	 *
+	 * According to HSDK User's Manual [1], "Table 2 Interrupt Mapping"
+	 * we have the following GPIO input lines used as sources of interrupt:
+	 * - GPIO[0] - Bluetooth interrupt of RS9113 module
+	 * - GPIO[2] - HAPS interrupt (on HapsTrak 3 connector)
+	 * - GPIO[3] - Audio codec (MAX9880A) interrupt
+	 * - GPIO[8-23] - Available on Arduino and PMOD_x headers
+	 * For now there's no use of Arduino and PMOD_x headers in Linux
+	 * use-case so we only enable lines 0, 2 and 3.
+	 *
+	 * [1] https://github.com/foss-for-synopsys-dwc-arc-processors/ARC-Development-Systems-Forum/wiki/docs/ARC_HSDK_User_Guide.pdf
+	 */
+#define GPIO_INTEN              (HSDK_GPIO_INTC + 0x30)
+#define GPIO_INTMASK            (HSDK_GPIO_INTC + 0x34)
+#define GPIO_INTTYPE_LEVEL      (HSDK_GPIO_INTC + 0x38)
+#define GPIO_INT_POLARITY       (HSDK_GPIO_INTC + 0x3c)
+#define GPIO_INT_CONNECTED_MASK	0x0d
+
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INTMASK);
+	iowrite32(~GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTMASK);
+	iowrite32(0x00000000, (void __iomem *) GPIO_INTTYPE_LEVEL);
+	iowrite32(0xffffffff, (void __iomem *) GPIO_INT_POLARITY);
+	iowrite32(GPIO_INT_CONNECTED_MASK, (void __iomem *) GPIO_INTEN);
+}
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -62,6 +122,8 @@ static void __init hsdk_init_early(void)
 	 * minimum possible div-by-2.
 	 */
 	iowrite32(SDIO_UHS_REG_EXT_DIV_2, (void __iomem *) SDIO_UHS_REG_EXT);
+
+	hsdk_enable_gpio_intc_wire();
 }
 
 static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi
index f9e8667f5886..73b514dddf65 100644
--- a/arch/arm/boot/dts/am335x-bone-common.dtsi
+++ b/arch/arm/boot/dts/am335x-bone-common.dtsi
@@ -168,7 +168,6 @@
 			AM33XX_IOPAD(0x8f0, PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_dat3.mmc0_dat3 */
 			AM33XX_IOPAD(0x904, PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_cmd.mmc0_cmd */
 			AM33XX_IOPAD(0x900, PIN_INPUT_PULLUP | MUX_MODE0)	/* mmc0_clk.mmc0_clk */
-			AM33XX_IOPAD(0x9a0, PIN_INPUT | MUX_MODE4)		/* mcasp0_aclkr.mmc0_sdwp */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/am3517.dtsi b/arch/arm/boot/dts/am3517.dtsi
index ca294914bbb1..23ea381d363f 100644
--- a/arch/arm/boot/dts/am3517.dtsi
+++ b/arch/arm/boot/dts/am3517.dtsi
@@ -39,6 +39,8 @@
 			ti,davinci-ctrl-ram-size = <0x2000>;
 			ti,davinci-rmii-en = /bits/ 8 <1>;
 			local-mac-address = [ 00 00 00 00 00 00 ];
+			clocks = <&emac_ick>;
+			clock-names = "ick";
 		};
 
 		davinci_mdio: ethernet@5c030000 {
@@ -49,6 +51,8 @@
 			bus_freq = <1000000>;
 			#address-cells = <1>;
 			#size-cells = <0>;
+			clocks = <&emac_fck>;
+			clock-names = "fck";
 		};
 
 		uart4: serial@4809e000 {
@@ -87,6 +91,11 @@
 	};
 };
 
+/* Table Table 5-79 of the TRM shows 480ab000 is reserved */
+&usb_otg_hs {
+	status = "disabled";
+};
+
 &iva {
 	status = "disabled";
 };
diff --git a/arch/arm/boot/dts/am437x-sk-evm.dts b/arch/arm/boot/dts/am437x-sk-evm.dts
index 440351ad0b80..d4be3fd0b6f4 100644
--- a/arch/arm/boot/dts/am437x-sk-evm.dts
+++ b/arch/arm/boot/dts/am437x-sk-evm.dts
@@ -610,6 +610,8 @@
 
 		touchscreen-size-x = <480>;
 		touchscreen-size-y = <272>;
+
+		wakeup-source;
 	};
 
 	tlv320aic3106: tlv320aic3106@1b {
diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi
index 18edc9bc7927..929459c42760 100644
--- a/arch/arm/boot/dts/armada-38x.dtsi
+++ b/arch/arm/boot/dts/armada-38x.dtsi
@@ -547,7 +547,7 @@
 
 			thermal: thermal@e8078 {
 				compatible = "marvell,armada380-thermal";
-				reg = <0xe4078 0x4>, <0xe4074 0x4>;
+				reg = <0xe4078 0x4>, <0xe4070 0x8>;
 				status = "okay";
 			};
 
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 9dcd14edc202..e03495a799ce 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -1580,7 +1580,6 @@
 				dr_mode = "otg";
 				snps,dis_u3_susphy_quirk;
 				snps,dis_u2_susphy_quirk;
-				snps,dis_metastability_quirk;
 			};
 		};
 
@@ -1608,6 +1607,7 @@
 				dr_mode = "otg";
 				snps,dis_u3_susphy_quirk;
 				snps,dis_u2_susphy_quirk;
+				snps,dis_metastability_quirk;
 			};
 		};
 
diff --git a/arch/arm/boot/dts/imx51-zii-rdu1.dts b/arch/arm/boot/dts/imx51-zii-rdu1.dts
index df9eca94d812..8a878687197b 100644
--- a/arch/arm/boot/dts/imx51-zii-rdu1.dts
+++ b/arch/arm/boot/dts/imx51-zii-rdu1.dts
@@ -770,7 +770,7 @@
 
 	pinctrl_ts: tsgrp {
 		fsl,pins = <
-			MX51_PAD_CSI1_D8__GPIO3_12		0x85
+			MX51_PAD_CSI1_D8__GPIO3_12		0x04
 			MX51_PAD_CSI1_D9__GPIO3_13		0x85
 		>;
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
index 19a075aee19e..f14df0baf2ab 100644
--- a/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-zii-rdu2.dtsi
@@ -692,7 +692,7 @@
 			dsa,member = <0 0>;
 			eeprom-length = <512>;
 			interrupt-parent = <&gpio6>;
-			interrupts = <3 IRQ_TYPE_EDGE_FALLING>;
+			interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
 
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index bdf73cbcec3a..e7c3c563ff8f 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -159,13 +159,7 @@
 
 		dais = <&mcbsp2_port>, <&mcbsp3_port>;
 	};
-};
-
-&dss {
-	status = "okay";
-};
 
-&gpio6 {
 	pwm8: dmtimer-pwm-8 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&vibrator_direction_pin>;
@@ -192,7 +186,10 @@
 		pwm-names = "enable", "direction";
 		direction-duty-cycle-ns = <10000000>;
 	};
+};
 
+&dss {
+	status = "okay";
 };
 
 &dsi1 {
diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig
index 054591dc9a00..4cd2f4a2bff4 100644
--- a/arch/arm/configs/imx_v4_v5_defconfig
+++ b/arch/arm/configs/imx_v4_v5_defconfig
@@ -141,9 +141,11 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
 CONFIG_NOP_USB_XCEIV=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_ETH=m
+CONFIG_USB_ULPI_BUS=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index f70507ab91ee..200ebda47e0c 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -302,6 +302,7 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_CHIPIDEA=y
 CONFIG_USB_CHIPIDEA_UDC=y
 CONFIG_USB_CHIPIDEA_HOST=y
+CONFIG_USB_CHIPIDEA_ULPI=y
 CONFIG_USB_SERIAL=m
 CONFIG_USB_SERIAL_GENERIC=y
 CONFIG_USB_SERIAL_FTDI_SIO=m
@@ -338,6 +339,7 @@ CONFIG_USB_GADGETFS=m
 CONFIG_USB_FUNCTIONFS=m
 CONFIG_USB_MASS_STORAGE=m
 CONFIG_USB_G_SERIAL=m
+CONFIG_USB_ULPI_BUS=y
 CONFIG_MMC=y
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
diff --git a/arch/arm/crypto/speck-neon-core.S b/arch/arm/crypto/speck-neon-core.S
index 3c1e203e53b9..57caa742016e 100644
--- a/arch/arm/crypto/speck-neon-core.S
+++ b/arch/arm/crypto/speck-neon-core.S
@@ -272,9 +272,11 @@
 	 * Allocate stack space to store 128 bytes worth of tweaks.  For
 	 * performance, this space is aligned to a 16-byte boundary so that we
 	 * can use the load/store instructions that declare 16-byte alignment.
+	 * For Thumb2 compatibility, don't do the 'bic' directly on 'sp'.
 	 */
-	sub		sp, #128
-	bic		sp, #0xf
+	sub		r12, sp, #128
+	bic		r12, #0xf
+	mov		sp, r12
 
 .if \n == 64
 	// Load first tweak
diff --git a/arch/arm/firmware/Makefile b/arch/arm/firmware/Makefile
index a71f16536b6c..6e41336b0bc4 100644
--- a/arch/arm/firmware/Makefile
+++ b/arch/arm/firmware/Makefile
@@ -1 +1,4 @@
 obj-$(CONFIG_TRUSTED_FOUNDATIONS)	+= trusted_foundations.o
+
+# tf_generic_smc() fails to build with -fsanitize-coverage=trace-pc
+KCOV_INSTRUMENT                := n
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index dd546d65a383..7a9b86978ee1 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -177,7 +177,7 @@ M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
 	bic	r0, r0, #CR_I
 #endif
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
-	isb
+	instr_sync
 #elif defined (CONFIG_CPU_V7M)
 #ifdef CONFIG_ARM_MPU
 	ldreq	r3, [r12, MPU_CTRL]
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 225d1c58d2de..d9c299133111 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -338,6 +338,7 @@ static struct vm_area_struct gate_vma = {
 
 static int __init gate_vma_init(void)
 {
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 69df3620eca5..1c73694c871a 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -109,6 +109,45 @@ void omap5_erratum_workaround_801819(void)
 static inline void omap5_erratum_workaround_801819(void) { }
 #endif
 
+#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+/*
+ * Configure ACR and enable ACTLR[0] (Enable invalidates of BTB with
+ * ICIALLU) to activate the workaround for secondary Core.
+ * NOTE: it is assumed that the primary core's configuration is done
+ * by the boot loader (kernel will detect a misconfiguration and complain
+ * if this is not done).
+ *
+ * In General Purpose(GP) devices, ACR bit settings can only be done
+ * by ROM code in "secure world" using the smc call and there is no
+ * option to update the "firmware" on such devices. This also works for
+ * High security(HS) devices, as a backup option in case the
+ * "update" is not done in the "security firmware".
+ */
+static void omap5_secondary_harden_predictor(void)
+{
+	u32 acr, acr_mask;
+
+	asm volatile ("mrc p15, 0, %0, c1, c0, 1" : "=r" (acr));
+
+	/*
+	 * ACTLR[0] (Enable invalidates of BTB with ICIALLU)
+	 */
+	acr_mask = BIT(0);
+
+	/* Do we already have it done.. if yes, skip expensive smc */
+	if ((acr & acr_mask) == acr_mask)
+		return;
+
+	acr |= acr_mask;
+	omap_smc1(OMAP5_DRA7_MON_SET_ACR_INDEX, acr);
+
+	pr_debug("%s: ARM ACR setup for CVE_2017_5715 applied on CPU%d\n",
+		 __func__, smp_processor_id());
+}
+#else
+static inline void omap5_secondary_harden_predictor(void) { }
+#endif
+
 static void omap4_secondary_init(unsigned int cpu)
 {
 	/*
@@ -131,6 +170,8 @@ static void omap4_secondary_init(unsigned int cpu)
 		set_cntfreq();
 		/* Configure ACR to disable streaming WA for 801819 */
 		omap5_erratum_workaround_801819();
+		/* Enable ACR to allow for ICUALLU workaround */
+		omap5_secondary_harden_predictor();
 	}
 
 	/*
diff --git a/arch/arm/mach-pxa/irq.c b/arch/arm/mach-pxa/irq.c
index 9c10248fadcc..4e8c2116808e 100644
--- a/arch/arm/mach-pxa/irq.c
+++ b/arch/arm/mach-pxa/irq.c
@@ -185,7 +185,7 @@ static int pxa_irq_suspend(void)
 {
 	int i;
 
-	for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+	for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
 		void __iomem *base = irq_base(i);
 
 		saved_icmr[i] = __raw_readl(base + ICMR);
@@ -204,7 +204,7 @@ static void pxa_irq_resume(void)
 {
 	int i;
 
-	for (i = 0; i < pxa_internal_irq_nr / 32; i++) {
+	for (i = 0; i < DIV_ROUND_UP(pxa_internal_irq_nr, 32); i++) {
 		void __iomem *base = irq_base(i);
 
 		__raw_writel(saved_icmr[i], base + ICMR);
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index 39aef4876ed4..8db62cc54a6a 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -237,8 +237,8 @@ static void ecard_init_pgtables(struct mm_struct *mm)
 
 	memcpy(dst_pgd, src_pgd, sizeof(pgd_t) * (EASI_SIZE / PGDIR_SIZE));
 
+	vma_init(&vma, mm);
 	vma.vm_flags = VM_EXEC;
-	vma.vm_mm = mm;
 
 	flush_tlb_range(&vma, IO_START, IO_START + IO_SIZE);
 	flush_tlb_range(&vma, EASI_START, EASI_START + EASI_SIZE);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index be0fa7e39c26..ba0e786c952e 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1151,6 +1151,11 @@ int arm_dma_supported(struct device *dev, u64 mask)
 	return __dma_supported(dev, mask, false);
 }
 
+static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
+{
+	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
+}
+
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
 static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
@@ -2296,7 +2301,7 @@ void arm_iommu_detach_device(struct device *dev)
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
 	to_dma_iommu_mapping(dev) = NULL;
-	set_dma_ops(dev, NULL);
+	set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent));
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
@@ -2357,11 +2362,6 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
-static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
-{
-	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
-}
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index c186474422f3..0cc8e04295a4 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -736,20 +736,29 @@ static int __mark_rodata_ro(void *unused)
 	return 0;
 }
 
+static int kernel_set_to_readonly __read_mostly;
+
 void mark_rodata_ro(void)
 {
+	kernel_set_to_readonly = 1;
 	stop_machine(__mark_rodata_ro, NULL, NULL);
 	debug_checkwx();
 }
 
 void set_kernel_text_rw(void)
 {
+	if (!kernel_set_to_readonly)
+		return;
+
 	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
 				current->active_mm);
 }
 
 void set_kernel_text_ro(void)
 {
+	if (!kernel_set_to_readonly)
+		return;
+
 	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
 				current->active_mm);
 }
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6e8b71613039..f6a62ae44a65 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1844,7 +1844,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 		/* there are 2 passes here */
 		bpf_jit_dump(prog->len, image_size, 2, ctx.target);
 
-	set_memory_ro((unsigned long)header, header->pages);
+	bpf_jit_binary_lock_ro(header);
 	prog->bpf_func = (void *)ctx.target;
 	prog->jited = 1;
 	prog->jited_len = image_size;
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 45272266dafb..e7101b19d590 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -10,7 +10,7 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-LDFLAGS_vmlinux	:=-p --no-undefined -X
+LDFLAGS_vmlinux	:=--no-undefined -X
 CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 GZFLAGS		:=-9
 
@@ -60,15 +60,15 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
 AS		+= -EB
-LD		+= -EB
-LDFLAGS		+= -maarch64linuxb
+# We must use the linux target here, since distributions don't tend to package
+# the ELF linker scripts with binutils, and this results in a build failure.
+LDFLAGS		+= -EB -maarch64linuxb
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__AARCH64EL__
 AS		+= -EL
-LD		+= -EL
-LDFLAGS		+= -maarch64linux
+LDFLAGS		+= -EL -maarch64linux # See comment above
 UTS_MACHINE	:= aarch64
 endif
 
diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
index fa8b3fe932e6..6495cc51246f 100644
--- a/arch/arm64/include/asm/simd.h
+++ b/arch/arm64/include/asm/simd.h
@@ -29,20 +29,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy);
 static __must_check inline bool may_use_simd(void)
 {
 	/*
-	 * The raw_cpu_read() is racy if called with preemption enabled.
-	 * This is not a bug: kernel_neon_busy is only set when
-	 * preemption is disabled, so we cannot migrate to another CPU
-	 * while it is set, nor can we migrate to a CPU where it is set.
-	 * So, if we find it clear on some CPU then we're guaranteed to
-	 * find it clear on any CPU we could migrate to.
-	 *
-	 * If we are in between kernel_neon_begin()...kernel_neon_end(),
-	 * the flag will be set, but preemption is also disabled, so we
-	 * can't migrate to another CPU and spuriously see it become
-	 * false.
+	 * kernel_neon_busy is only set while preemption is disabled,
+	 * and is clear whenever preemption is enabled. Since
+	 * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy
+	 * cannot change under our feet -- if it's set we cannot be
+	 * migrated, and if it's clear we cannot be migrated to a CPU
+	 * where it is set.
 	 */
 	return !in_irq() && !irqs_disabled() && !in_nmi() &&
-		!raw_cpu_read(kernel_neon_busy);
+		!this_cpu_read(kernel_neon_busy);
 }
 
 #else /* ! CONFIG_KERNEL_MODE_NEON */
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index ffdaea7954bb..d87f2d646caa 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -37,7 +37,9 @@ static inline void __tlb_remove_table(void *_table)
 
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-	struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+	struct vm_area_struct vma;
+
+	vma_init(&vma, tlb->mm);
 
 	/*
 	 * The ASID allocator will either invalidate the ASID or mark
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f24892a40d2c..c6d80743f4ed 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1351,9 +1351,9 @@ static void __update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 
 static void update_cpu_capabilities(u16 scope_mask)
 {
-	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
 	__update_cpu_capabilities(arm64_errata, scope_mask,
 				  "enabling workaround for");
+	__update_cpu_capabilities(arm64_features, scope_mask, "detected:");
 }
 
 static int __enable_cpu_capability(void *arg)
@@ -1408,8 +1408,8 @@ __enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 
 static void __init enable_cpu_capabilities(u16 scope_mask)
 {
-	__enable_cpu_capabilities(arm64_features, scope_mask);
 	__enable_cpu_capabilities(arm64_errata, scope_mask);
+	__enable_cpu_capabilities(arm64_features, scope_mask);
 }
 
 /*
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index ecc6818191df..1854e49aa18a 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -108,11 +108,13 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
+	struct vm_area_struct vma;
 	pte_t orig_pte = huge_ptep_get(ptep);
 	bool valid = pte_valid(orig_pte);
 	unsigned long i, saddr = addr;
 
+	vma_init(&vma, mm);
+
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
 		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
 
@@ -145,9 +147,10 @@ static void clear_flush(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	struct vm_area_struct vma = { .vm_mm = mm };
+	struct vm_area_struct vma;
 	unsigned long i, saddr = addr;
 
+	vma_init(&vma, mm);
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
 		pte_clear(mm, addr, ptep);
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 325cfb3b858a..9abf8a1e7b25 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -611,11 +611,13 @@ void __init mem_init(void)
 	BUILD_BUG_ON(TASK_SIZE_32			> TASK_SIZE_64);
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	/*
 	 * Make sure we chose the upper bound of sizeof(struct page)
-	 * correctly.
+	 * correctly when sizing the VMEMMAP array.
 	 */
 	BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
+#endif
 
 	if (PAGE_SIZE >= 16384 && get_num_physpages() <= 128) {
 		extern int sysctl_overcommit_memory;
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index 44f0ac0df308..db89e7306081 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -120,7 +120,7 @@ ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned
 		 */
 		struct vm_area_struct vma;
 
-		vma.vm_mm = tlb->mm;
+		vma_init(&vma, tlb->mm);
 		/* flush the address range from the tlb: */
 		flush_tlb_range(&vma, start, end);
 		/* now flush the virt. page-table area mapping the address range: */
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 3b38c717008a..46bff1661836 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2278,17 +2278,15 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	DPRINT(("smpl_buf @%p\n", smpl_buf));
 
 	/* allocate vma */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		DPRINT(("Cannot allocate vma\n"));
 		goto error_kmem;
 	}
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	/*
 	 * partially initialize the vma for the sampling buffer
 	 */
-	vma->vm_mm	     = mm;
 	vma->vm_file	     = get_file(filp);
 	vma->vm_flags	     = VM_READ|VM_MAYREAD|VM_DONTEXPAND|VM_DONTDUMP;
 	vma->vm_page_prot    = PAGE_READONLY; /* XXX may need to change */
@@ -2346,7 +2344,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	return 0;
 
 error:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 error_kmem:
 	pfm_rvfree(smpl_buf, size);
 
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 18278b448530..e6c6dfd98de2 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -114,10 +114,8 @@ ia64_init_addr_space (void)
 	 * the problem.  When the process attempts to write to the register backing store
 	 * for the first time, it will get a SEGFAULT in this case.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (vma) {
-		INIT_LIST_HEAD(&vma->anon_vma_chain);
-		vma->vm_mm = current->mm;
 		vma->vm_start = current->thread.rbs_bot & PAGE_MASK;
 		vma->vm_end = vma->vm_start + PAGE_SIZE;
 		vma->vm_flags = VM_DATA_DEFAULT_FLAGS|VM_GROWSUP|VM_ACCOUNT;
@@ -125,7 +123,7 @@ ia64_init_addr_space (void)
 		down_write(&current->mm->mmap_sem);
 		if (insert_vm_struct(current->mm, vma)) {
 			up_write(&current->mm->mmap_sem);
-			kmem_cache_free(vm_area_cachep, vma);
+			vm_area_free(vma);
 			return;
 		}
 		up_write(&current->mm->mmap_sem);
@@ -133,10 +131,8 @@ ia64_init_addr_space (void)
 
 	/* map NaT-page at address zero to speed up speculative dereferencing of NULL: */
 	if (!(current->personality & MMAP_PAGE_ZERO)) {
-		vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+		vma = vm_area_alloc(current->mm);
 		if (vma) {
-			INIT_LIST_HEAD(&vma->anon_vma_chain);
-			vma->vm_mm = current->mm;
 			vma->vm_end = PAGE_SIZE;
 			vma->vm_page_prot = __pgprot(pgprot_val(PAGE_READONLY) | _PAGE_MA_NAT);
 			vma->vm_flags = VM_READ | VM_MAYREAD | VM_IO |
@@ -144,7 +140,7 @@ ia64_init_addr_space (void)
 			down_write(&current->mm->mmap_sem);
 			if (insert_vm_struct(current->mm, vma)) {
 				up_write(&current->mm->mmap_sem);
-				kmem_cache_free(vm_area_cachep, vma);
+				vm_area_free(vma);
 				return;
 			}
 			up_write(&current->mm->mmap_sem);
@@ -277,7 +273,7 @@ static struct vm_area_struct gate_vma;
 
 static int __init gate_vma_init(void)
 {
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/arch/m68k/include/asm/mcf_pgalloc.h b/arch/m68k/include/asm/mcf_pgalloc.h
index 8b707c249026..12fe700632f4 100644
--- a/arch/m68k/include/asm/mcf_pgalloc.h
+++ b/arch/m68k/include/asm/mcf_pgalloc.h
@@ -44,6 +44,7 @@ extern inline pmd_t *pmd_alloc_kernel(pgd_t *pgd, unsigned long address)
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t page,
 				  unsigned long address)
 {
+	pgtable_page_dtor(page);
 	__free_page(page);
 }
 
@@ -74,8 +75,9 @@ static inline struct page *pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-extern inline void pte_free(struct mm_struct *mm, struct page *page)
+static inline void pte_free(struct mm_struct *mm, struct page *page)
 {
+	pgtable_page_dtor(page);
 	__free_page(page);
 }
 
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index 10a405d593df..c782b10ddf50 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -58,7 +58,7 @@ EXPORT_SYMBOL_GPL(ath79_ddr_ctrl_init);
 
 void ath79_ddr_wb_flush(u32 reg)
 {
-	void __iomem *flush_reg = ath79_ddr_wb_flush_base + reg;
+	void __iomem *flush_reg = ath79_ddr_wb_flush_base + (reg * 4);
 
 	/* Flush the DDR write buffer. */
 	__raw_writel(0x1, flush_reg);
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 8c9cbf13d32a..6054d49e608e 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -212,12 +212,6 @@ static int __init bcm47xx_cpu_fixes(void)
 		 */
 		if (bcm47xx_bus.bcma.bus.chipinfo.id == BCMA_CHIP_ID_BCM4706)
 			cpu_wait = NULL;
-
-		/*
-		 * BCM47XX Erratum "R10: PCIe Transactions Periodically Fail"
-		 * Enable ExternalSync for sync instruction to take effect
-		 */
-		set_c0_config7(MIPS_CONF7_ES);
 		break;
 #endif
 	}
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 0bc270806ec5..ae461d91cd1f 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -681,8 +681,6 @@
 #define MIPS_CONF7_WII		(_ULCAST_(1) << 31)
 
 #define MIPS_CONF7_RPS		(_ULCAST_(1) << 2)
-/* ExternalSync */
-#define MIPS_CONF7_ES		(_ULCAST_(1) << 8)
 
 #define MIPS_CONF7_IAR		(_ULCAST_(1) << 10)
 #define MIPS_CONF7_AR		(_ULCAST_(1) << 16)
@@ -2767,7 +2765,6 @@ __BUILD_SET_C0(status)
 __BUILD_SET_C0(cause)
 __BUILD_SET_C0(config)
 __BUILD_SET_C0(config5)
-__BUILD_SET_C0(config7)
 __BUILD_SET_C0(intcontrol)
 __BUILD_SET_C0(intctl)
 __BUILD_SET_C0(srsmap)
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 8d85046adcc8..9670e70139fd 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/kallsyms.h>
 #include <linux/random.h>
 #include <linux/prctl.h>
+#include <linux/nmi.h>
 
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
@@ -655,28 +656,42 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ALMASK;
 }
 
-static void arch_dump_stack(void *info)
+static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
+static struct cpumask backtrace_csd_busy;
+
+static void handle_backtrace(void *info)
 {
-	struct pt_regs *regs;
+	nmi_cpu_backtrace(get_irq_regs());
+	cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
+}
 
-	regs = get_irq_regs();
+static void raise_backtrace(cpumask_t *mask)
+{
+	call_single_data_t *csd;
+	int cpu;
 
-	if (regs)
-		show_regs(regs);
+	for_each_cpu(cpu, mask) {
+		/*
+		 * If we previously sent an IPI to the target CPU & it hasn't
+		 * cleared its bit in the busy cpumask then it didn't handle
+		 * our previous IPI & it's not safe for us to reuse the
+		 * call_single_data_t.
+		 */
+		if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
+			pr_warn("Unable to send backtrace IPI to CPU%u - perhaps it hung?\n",
+				cpu);
+			continue;
+		}
 
-	dump_stack();
+		csd = &per_cpu(backtrace_csd, cpu);
+		csd->func = handle_backtrace;
+		smp_call_function_single_async(cpu, csd);
+	}
 }
 
 void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
 {
-	long this_cpu = get_cpu();
-
-	if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
-		dump_stack();
-
-	smp_call_function_many(mask, arch_dump_stack, NULL, 1);
-
-	put_cpu();
+	nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
 }
 
 int mips_get_process_fp_mode(struct task_struct *task)
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d67fa74622ee..8d505a21396e 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -351,6 +351,7 @@ static void __show_regs(const struct pt_regs *regs)
 void show_regs(struct pt_regs *regs)
 {
 	__show_regs((struct pt_regs *)regs);
+	dump_stack();
 }
 
 void show_registers(struct pt_regs *regs)
diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
index 1986e09fb457..1601d90b087b 100644
--- a/arch/mips/mm/ioremap.c
+++ b/arch/mips/mm/ioremap.c
@@ -9,6 +9,7 @@
 #include <linux/export.h>
 #include <asm/addrspace.h>
 #include <asm/byteorder.h>
+#include <linux/ioport.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
@@ -98,6 +99,20 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 	return error;
 }
 
+static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages,
+			       void *arg)
+{
+	unsigned long i;
+
+	for (i = 0; i < nr_pages; i++) {
+		if (pfn_valid(start_pfn + i) &&
+		    !PageReserved(pfn_to_page(start_pfn + i)))
+			return 1;
+	}
+
+	return 0;
+}
+
 /*
  * Generic mapping function (not visible outside):
  */
@@ -116,8 +131,8 @@ static int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 
 void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long flags)
 {
+	unsigned long offset, pfn, last_pfn;
 	struct vm_struct * area;
-	unsigned long offset;
 	phys_addr_t last_addr;
 	void * addr;
 
@@ -137,18 +152,16 @@ void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned long
 		return (void __iomem *) CKSEG1ADDR(phys_addr);
 
 	/*
-	 * Don't allow anybody to remap normal RAM that we're using..
+	 * Don't allow anybody to remap RAM that may be allocated by the page
+	 * allocator, since that could lead to races & data clobbering.
 	 */
-	if (phys_addr < virt_to_phys(high_memory)) {
-		char *t_addr, *t_end;
-		struct page *page;
-
-		t_addr = __va(phys_addr);
-		t_end = t_addr + (size - 1);
-
-		for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); page++)
-			if(!PageReserved(page))
-				return NULL;
+	pfn = PFN_DOWN(phys_addr);
+	last_pfn = PFN_DOWN(last_addr);
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+				  __ioremap_check_ram) == 1) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
+		return NULL;
 	}
 
 	/*
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index 9632436d74d7..c2e94cf5ecda 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -54,5 +54,5 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
 	phys_addr_t size = resource_size(rsrc);
 
 	*start = fixup_bigphys_addr(rsrc->start, size);
-	*end = rsrc->start + size;
+	*end = rsrc->start + size - 1;
 }
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 6aed974276d8..34f7222c5efe 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -12,17 +12,17 @@ config NDS32
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select DMA_NONCOHERENT_OPS
-	select GENERIC_ASHLDI3
-	select GENERIC_ASHRDI3
-	select GENERIC_LSHRDI3
-	select GENERIC_CMPDI2
-	select GENERIC_MULDI3
-	select GENERIC_UCMPDI2
 	select GENERIC_ATOMIC64
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_SHOW
+	select GENERIC_LIB_ASHLDI3
+	select GENERIC_LIB_ASHRDI3
+	select GENERIC_LIB_CMPDI2
+	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_MULDI3
+	select GENERIC_LIB_UCMPDI2
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
 	select GENERIC_TIME_VSYSCALL
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 513bb2e9baf9..031c676821ff 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -34,10 +34,12 @@ ifdef CONFIG_CPU_LITTLE_ENDIAN
 KBUILD_CFLAGS   += $(call cc-option, -EL)
 KBUILD_AFLAGS   += $(call cc-option, -EL)
 LDFLAGS         += $(call cc-option, -EL)
+CHECKFLAGS      += -D__NDS32_EL__
 else
 KBUILD_CFLAGS   += $(call cc-option, -EB)
 KBUILD_AFLAGS   += $(call cc-option, -EB)
 LDFLAGS         += $(call cc-option, -EB)
+CHECKFLAGS      += -D__NDS32_EB__
 endif
 
 boot := arch/nds32/boot
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 10b48f0d8e85..8b26198d51bb 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -8,6 +8,8 @@
 
 #define PG_dcache_dirty PG_arch_1
 
+void flush_icache_range(unsigned long start, unsigned long end);
+void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #ifdef CONFIG_CPU_CACHE_ALIASING
 void flush_cache_mm(struct mm_struct *mm);
 void flush_cache_dup_mm(struct mm_struct *mm);
@@ -34,13 +36,16 @@ void flush_anon_page(struct vm_area_struct *vma,
 void flush_kernel_dcache_page(struct page *page);
 void flush_kernel_vmap_range(void *addr, int size);
 void invalidate_kernel_vmap_range(void *addr, int size);
-void flush_icache_range(unsigned long start, unsigned long end);
-void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
 #define flush_dcache_mmap_unlock(mapping) xa_unlock_irq(&(mapping)->i_pages)
 
 #else
 #include <asm-generic/cacheflush.h>
+#undef flush_icache_range
+#undef flush_icache_page
+#undef flush_icache_user_range
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len);
 #endif
 
 #endif /* __NDS32_CACHEFLUSH_H__ */
diff --git a/arch/nds32/include/asm/futex.h b/arch/nds32/include/asm/futex.h
index eab5e84bd991..cb6cb91cfdf8 100644
--- a/arch/nds32/include/asm/futex.h
+++ b/arch/nds32/include/asm/futex.h
@@ -16,7 +16,7 @@
 	"	.popsection\n"					\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"4:	move	%0, " err_reg "\n"			\
-	"	j	3b\n"					\
+	"	b	3b\n"					\
 	"	.popsection"
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index 2f5b2ccebe47..63a1a5ef5219 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -278,7 +278,8 @@ static void __init setup_memory(void)
 
 void __init setup_arch(char **cmdline_p)
 {
-	early_init_devtree( __dtb_start);
+	early_init_devtree(__atags_pointer ? \
+		phys_to_virt(__atags_pointer) : __dtb_start);
 
 	setup_cpuinfo();
 
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index ce8fd34497bf..254703653b6f 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -13,7 +13,39 @@
 
 extern struct cache_info L1_cache_info[2];
 
-#ifndef CONFIG_CPU_CACHE_ALIASING
+void flush_icache_range(unsigned long start, unsigned long end)
+{
+	unsigned long line_size, flags;
+	line_size = L1_cache_info[DCACHE].line_size;
+	start = start & ~(line_size - 1);
+	end = (end + line_size - 1) & ~(line_size - 1);
+	local_irq_save(flags);
+	cpu_cache_wbinval_range(start, end, 1);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+void flush_icache_page(struct vm_area_struct *vma, struct page *page)
+{
+	unsigned long flags;
+	unsigned long kaddr;
+	local_irq_save(flags);
+	kaddr = (unsigned long)kmap_atomic(page);
+	cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+	kunmap_atomic((void *)kaddr);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_icache_page);
+
+void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
+	                     unsigned long addr, int len)
+{
+	unsigned long kaddr;
+	kaddr = (unsigned long)kmap_atomic(page) + (addr & ~PAGE_MASK);
+	flush_icache_range(kaddr, kaddr + len);
+	kunmap_atomic((void *)kaddr);
+}
+
 void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 		      pte_t * pte)
 {
@@ -35,19 +67,15 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 
 	if ((test_and_clear_bit(PG_dcache_dirty, &page->flags)) ||
 	    (vma->vm_flags & VM_EXEC)) {
-
-		if (!PageHighMem(page)) {
-			cpu_cache_wbinval_page((unsigned long)
-					       page_address(page),
-					       vma->vm_flags & VM_EXEC);
-		} else {
-			unsigned long kaddr = (unsigned long)kmap_atomic(page);
-			cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
-			kunmap_atomic((void *)kaddr);
-		}
+		unsigned long kaddr;
+		local_irq_save(flags);
+		kaddr = (unsigned long)kmap_atomic(page);
+		cpu_cache_wbinval_page(kaddr, vma->vm_flags & VM_EXEC);
+		kunmap_atomic((void *)kaddr);
+		local_irq_restore(flags);
 	}
 }
-#else
+#ifdef CONFIG_CPU_CACHE_ALIASING
 extern pte_t va_present(struct mm_struct *mm, unsigned long addr);
 
 static inline unsigned long aliasing(unsigned long addr, unsigned long page)
@@ -317,52 +345,4 @@ void invalidate_kernel_vmap_range(void *addr, int size)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(invalidate_kernel_vmap_range);
-
-void flush_icache_range(unsigned long start, unsigned long end)
-{
-	unsigned long line_size, flags;
-	line_size = L1_cache_info[DCACHE].line_size;
-	start = start & ~(line_size - 1);
-	end = (end + line_size - 1) & ~(line_size - 1);
-	local_irq_save(flags);
-	cpu_cache_wbinval_range(start, end, 1);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(flush_icache_range);
-
-void flush_icache_page(struct vm_area_struct *vma, struct page *page)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	cpu_cache_wbinval_page((unsigned long)page_address(page),
-			       vma->vm_flags & VM_EXEC);
-	local_irq_restore(flags);
-}
-
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
-		      pte_t * pte)
-{
-	struct page *page;
-	unsigned long flags;
-	unsigned long pfn = pte_pfn(*pte);
-
-	if (!pfn_valid(pfn))
-		return;
-
-	if (vma->vm_mm == current->active_mm) {
-		local_irq_save(flags);
-		__nds32__mtsr_dsb(addr, NDS32_SR_TLB_VPN);
-		__nds32__tlbop_rwr(*pte);
-		__nds32__isb();
-		local_irq_restore(flags);
-	}
-
-	page = pfn_to_page(pfn);
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags) ||
-	    (vma->vm_flags & VM_EXEC)) {
-		local_irq_save(flags);
-		cpu_dcache_wbinval_page((unsigned long)page_address(page));
-		local_irq_restore(flags);
-	}
-}
 #endif
diff --git a/arch/openrisc/include/asm/pgalloc.h b/arch/openrisc/include/asm/pgalloc.h
index 3e1a46615120..8999b9226512 100644
--- a/arch/openrisc/include/asm/pgalloc.h
+++ b/arch/openrisc/include/asm/pgalloc.h
@@ -98,8 +98,12 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte)
 	__free_page(pte);
 }
 
+#define __pte_free_tlb(tlb, pte, addr)	\
+do {					\
+	pgtable_page_dtor(pte);		\
+	tlb_remove_page((tlb), (pte));	\
+} while (0)
 
-#define __pte_free_tlb(tlb, pte, addr) tlb_remove_page((tlb), (pte))
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
 #define check_pgt_cache()          do { } while (0)
diff --git a/arch/openrisc/kernel/entry.S b/arch/openrisc/kernel/entry.S
index 690d55272ba6..0c826ad6e994 100644
--- a/arch/openrisc/kernel/entry.S
+++ b/arch/openrisc/kernel/entry.S
@@ -277,12 +277,6 @@ EXCEPTION_ENTRY(_data_page_fault_handler)
 	l.addi  r3,r1,0                    // pt_regs
 	/* r4 set be EXCEPTION_HANDLE */   // effective address of fault
 
-	/*
-	 * __PHX__: TODO
-	 *
-	 * all this can be written much simpler. look at
-	 * DTLB miss handler in the CONFIG_GUARD_PROTECTED_CORE part
-	 */
 #ifdef CONFIG_OPENRISC_NO_SPR_SR_DSX
 	l.lwz   r6,PT_PC(r3)               // address of an offending insn
 	l.lwz   r6,0(r6)                   // instruction that caused pf
@@ -314,7 +308,7 @@ EXCEPTION_ENTRY(_data_page_fault_handler)
 
 #else
 
-	l.lwz   r6,PT_SR(r3)               // SR
+	l.mfspr r6,r0,SPR_SR               // SR
 	l.andi  r6,r6,SPR_SR_DSX           // check for delay slot exception
 	l.sfne  r6,r0                      // exception happened in delay slot
 	l.bnf   7f
diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S
index fb02b2a1d6f2..9fc6b60140f0 100644
--- a/arch/openrisc/kernel/head.S
+++ b/arch/openrisc/kernel/head.S
@@ -210,8 +210,7 @@
  *	 r4  - EEAR     exception EA
  *	 r10 - current	pointing to current_thread_info struct
  *	 r12 - syscall  0, since we didn't come from syscall
- *	 r13 - temp	it actually contains new SR, not needed anymore
- *	 r31 - handler	address of the handler we'll jump to
+ *	 r30 - handler	address of the handler we'll jump to
  *
  *	 handler has to save remaining registers to the exception
  *	 ksp frame *before* tainting them!
@@ -244,6 +243,7 @@
 	/* r1 is KSP, r30 is __pa(KSP) */			;\
 	tophys  (r30,r1)					;\
 	l.sw    PT_GPR12(r30),r12				;\
+	/* r4 use for tmp before EA */				;\
 	l.mfspr r12,r0,SPR_EPCR_BASE				;\
 	l.sw    PT_PC(r30),r12					;\
 	l.mfspr r12,r0,SPR_ESR_BASE				;\
@@ -263,7 +263,10 @@
 	/* r12 == 1 if we come from syscall */			;\
 	CLEAR_GPR(r12)						;\
 	/* ----- turn on MMU ----- */				;\
-	l.ori	r30,r0,(EXCEPTION_SR)				;\
+	/* Carry DSX into exception SR */			;\
+	l.mfspr r30,r0,SPR_SR					;\
+	l.andi	r30,r30,SPR_SR_DSX				;\
+	l.ori	r30,r30,(EXCEPTION_SR)				;\
 	l.mtspr	r0,r30,SPR_ESR_BASE				;\
 	/* r30:	EA address of handler */			;\
 	LOAD_SYMBOL_2_GPR(r30,handler)				;\
diff --git a/arch/openrisc/kernel/traps.c b/arch/openrisc/kernel/traps.c
index fac246e6f37a..d8981cbb852a 100644
--- a/arch/openrisc/kernel/traps.c
+++ b/arch/openrisc/kernel/traps.c
@@ -300,7 +300,7 @@ static inline int in_delay_slot(struct pt_regs *regs)
 		return 0;
 	}
 #else
-	return regs->sr & SPR_SR_DSX;
+	return mfspr(SPR_SR) & SPR_SR_DSX;
 #endif
 }
 
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 2ea575cb3401..fb96206de317 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -243,6 +243,7 @@ endif
 cpu-as-$(CONFIG_4xx)		+= -Wa,-m405
 cpu-as-$(CONFIG_ALTIVEC)	+= $(call as-option,-Wa$(comma)-maltivec)
 cpu-as-$(CONFIG_E200)		+= -Wa,-me200
+cpu-as-$(CONFIG_E500)		+= -Wa,-me500
 cpu-as-$(CONFIG_PPC_BOOK3S_64)	+= -Wa,-mpower4
 cpu-as-$(CONFIG_PPC_E500MC)	+= $(call as-option,-Wa$(comma)-me500mc)
 
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 896efa559996..79d570cbf332 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index e734f6e45abc..689306118b48 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -144,7 +144,9 @@ power9_restore_additional_sprs:
 	mtspr	SPRN_MMCR1, r4
 
 	ld	r3, STOP_MMCR2(r13)
+	ld	r4, PACA_SPRG_VDSO(r13)
 	mtspr	SPRN_MMCR2, r3
+	mtspr	SPRN_SPRG3, r4
 	blr
 
 /*
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index d066e37551ec..8c456fa691a5 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
 		return H_HARDWARE;
 
 	if (mm_iommu_mapped_inc(mem))
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 925fc316a104..5b298f5a1a14 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (!mem)
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+			&hpa)))
 		return H_HARDWARE;
 
 	pua = (void *) vmalloc_to_phys(pua);
@@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
 		if (mem)
-			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
 	}
 
 	if (!prereg) {
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index abb43646927a..a4ca57612558 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -19,6 +19,7 @@
 #include <linux/hugetlb.h>
 #include <linux/swap.h>
 #include <asm/mmu_context.h>
+#include <asm/pte-walk.h>
 
 static DEFINE_MUTEX(mem_list_mutex);
 
@@ -27,6 +28,7 @@ struct mm_iommu_table_group_mem_t {
 	struct rcu_head rcu;
 	unsigned long used;
 	atomic64_t mapped;
+	unsigned int pageshift;
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
@@ -125,6 +127,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
+	unsigned int pageshift;
+	unsigned long flags;
 	struct page *page = NULL;
 
 	mutex_lock(&mem_list_mutex);
@@ -159,6 +163,12 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	/*
+	 * For a starting point for a maximum page size calculation
+	 * we use @ua and @entries natural alignment to allow IOMMU pages
+	 * smaller than huge pages but still bigger than PAGE_SIZE.
+	 */
+	mem->pageshift = __ffs(ua | (entries << PAGE_SHIFT));
 	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
 	if (!mem->hpas) {
 		kfree(mem);
@@ -199,6 +209,23 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 			}
 		}
 populate:
+		pageshift = PAGE_SHIFT;
+		if (PageCompound(page)) {
+			pte_t *pte;
+			struct page *head = compound_head(page);
+			unsigned int compshift = compound_order(head);
+
+			local_irq_save(flags); /* disables as well */
+			pte = find_linux_pte(mm->pgd, ua, NULL, &pageshift);
+			local_irq_restore(flags);
+
+			/* Double check it is still the same pinned page */
+			if (pte && pte_page(*pte) == head &&
+					pageshift == compshift)
+				pageshift = max_t(unsigned int, pageshift,
+						PAGE_SHIFT);
+		}
+		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
@@ -349,7 +376,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 EXPORT_SYMBOL_GPL(mm_iommu_find);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	u64 *va = &mem->hpas[entry];
@@ -357,6 +384,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	*hpa = *va | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -364,7 +394,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
 long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	void *va = &mem->hpas[entry];
@@ -373,6 +403,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	pa = (void *) vmalloc_to_phys(va);
 	if (!pa)
 		return -EFAULT;
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 380cbf9a40d9..c0a9bcd28356 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -286,6 +286,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image,
 		u64 imm64;
 		u8 *func;
 		u32 true_cond;
+		u32 tmp_idx;
 
 		/*
 		 * addrs[] maps a BPF bytecode address into a real offset from
@@ -637,11 +638,7 @@ emit_clear:
 		case BPF_STX | BPF_XADD | BPF_W:
 			/* Get EA into TMP_REG_1 */
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not word-aligned */
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x03);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + 12);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
+			tmp_idx = ctx->idx * 4;
 			/* load value from memory into TMP_REG_2 */
 			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			/* add value from src_reg into this */
@@ -649,32 +646,16 @@ emit_clear:
 			/* store result back */
 			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
 			/* we're done if this succeeded */
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
-			/* otherwise, let's try once more */
-			PPC_BPF_LWARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STWCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			/* exit if the store was not successful */
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
 		/* *(u64 *)(dst + off) += src */
 		case BPF_STX | BPF_XADD | BPF_DW:
 			PPC_ADDI(b2p[TMP_REG_1], dst_reg, off);
-			/* error if EA is not doubleword-aligned */
-			PPC_ANDI(b2p[TMP_REG_2], b2p[TMP_REG_1], 0x07);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (3*4));
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_JMP(exit_addr);
-			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
-			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
-			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_BCC_SHORT(COND_EQ, (ctx->idx * 4) + (7*4));
+			tmp_idx = ctx->idx * 4;
 			PPC_BPF_LDARX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1], 0);
 			PPC_ADD(b2p[TMP_REG_2], b2p[TMP_REG_2], src_reg);
 			PPC_BPF_STDCX(b2p[TMP_REG_2], 0, b2p[TMP_REG_1]);
-			PPC_LI(b2p[BPF_REG_0], 0);
-			PPC_BCC(COND_NE, exit_addr);
+			PPC_BCC_SHORT(COND_NE, tmp_idx);
 			break;
 
 		/*
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 47166ad2a669..196978733e64 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2734,7 +2734,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 {
 	int nr, dotted;
 	unsigned long first_adr;
-	unsigned long inst, last_inst = 0;
+	unsigned int inst, last_inst = 0;
 	unsigned char val[4];
 
 	dotted = 0;
@@ -2758,7 +2758,7 @@ generic_inst_dump(unsigned long adr, long count, int praddr,
 		dotted = 0;
 		last_inst = inst;
 		if (praddr)
-			printf(REG"  %.8lx", adr, inst);
+			printf(REG"  %.8x", adr, inst);
 		printf("\t");
 		dump_func(inst, adr);
 		printf("\n");
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index f12680c9b947..4764fdeb4f1f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -107,6 +107,7 @@ config ARCH_RV32I
 	select GENERIC_LIB_ASHLDI3
 	select GENERIC_LIB_ASHRDI3
 	select GENERIC_LIB_LSHRDI3
+	select GENERIC_LIB_UCMPDI2
 
 config ARCH_RV64I
 	bool "RV64I"
diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h
index 5cae4c30cd8e..1e0dfc36aab9 100644
--- a/arch/riscv/include/uapi/asm/elf.h
+++ b/arch/riscv/include/uapi/asm/elf.h
@@ -21,8 +21,13 @@ typedef struct user_regs_struct elf_gregset_t;
 
 typedef union __riscv_fp_state elf_fpregset_t;
 
-#define ELF_RISCV_R_SYM(r_info) ((r_info) >> 32)
-#define ELF_RISCV_R_TYPE(r_info) ((r_info) & 0xffffffff)
+#if __riscv_xlen == 64
+#define ELF_RISCV_R_SYM(r_info)		ELF64_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info)	ELF64_R_TYPE(r_info)
+#else
+#define ELF_RISCV_R_SYM(r_info)		ELF32_R_SYM(r_info)
+#define ELF_RISCV_R_TYPE(r_info)	ELF32_R_TYPE(r_info)
+#endif
 
 /*
  * RISC-V relocation types
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index b74cbfbce2d0..7bcdaed15703 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -16,10 +16,6 @@
 #include <linux/irqchip.h>
 #include <linux/irqdomain.h>
 
-#ifdef CONFIG_RISCV_INTC
-#include <linux/irqchip/irq-riscv-intc.h>
-#endif
-
 void __init init_IRQ(void)
 {
 	irqchip_init();
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index 1d5e9b934b8c..3303ed2cd419 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -37,7 +37,7 @@ static int apply_r_riscv_64_rela(struct module *me, u32 *location, Elf_Addr v)
 static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
 				     Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u32 imm12 = (offset & 0x1000) << (31 - 12);
 	u32 imm11 = (offset & 0x800) >> (11 - 7);
 	u32 imm10_5 = (offset & 0x7e0) << (30 - 10);
@@ -50,7 +50,7 @@ static int apply_r_riscv_branch_rela(struct module *me, u32 *location,
 static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
 				  Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u32 imm20 = (offset & 0x100000) << (31 - 20);
 	u32 imm19_12 = (offset & 0xff000);
 	u32 imm11 = (offset & 0x800) << (20 - 11);
@@ -63,7 +63,7 @@ static int apply_r_riscv_jal_rela(struct module *me, u32 *location,
 static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
 					 Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u16 imm8 = (offset & 0x100) << (12 - 8);
 	u16 imm7_6 = (offset & 0xc0) >> (6 - 5);
 	u16 imm5 = (offset & 0x20) >> (5 - 2);
@@ -78,7 +78,7 @@ static int apply_r_riscv_rcv_branch_rela(struct module *me, u32 *location,
 static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
 				       Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	u16 imm11 = (offset & 0x800) << (12 - 11);
 	u16 imm10 = (offset & 0x400) >> (10 - 8);
 	u16 imm9_8 = (offset & 0x300) << (12 - 11);
@@ -96,7 +96,7 @@ static int apply_r_riscv_rvc_jump_rela(struct module *me, u32 *location,
 static int apply_r_riscv_pcrel_hi20_rela(struct module *me, u32 *location,
 					 Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 hi20;
 
 	if (offset != (s32)offset) {
@@ -178,7 +178,7 @@ static int apply_r_riscv_lo12_s_rela(struct module *me, u32 *location,
 static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 				       Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 hi20;
 
 	/* Always emit the got entry */
@@ -200,7 +200,7 @@ static int apply_r_riscv_got_hi20_rela(struct module *me, u32 *location,
 static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 				       Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 fill_v = offset;
 	u32 hi20, lo12;
 
@@ -227,7 +227,7 @@ static int apply_r_riscv_call_plt_rela(struct module *me, u32 *location,
 static int apply_r_riscv_call_rela(struct module *me, u32 *location,
 				   Elf_Addr v)
 {
-	s64 offset = (void *)v - (void *)location;
+	ptrdiff_t offset = (void *)v - (void *)location;
 	s32 fill_v = offset;
 	u32 hi20, lo12;
 
@@ -263,14 +263,14 @@ static int apply_r_riscv_align_rela(struct module *me, u32 *location,
 static int apply_r_riscv_add32_rela(struct module *me, u32 *location,
 				    Elf_Addr v)
 {
-	*(u32 *)location += (*(u32 *)v);
+	*(u32 *)location += (u32)v;
 	return 0;
 }
 
 static int apply_r_riscv_sub32_rela(struct module *me, u32 *location,
 				    Elf_Addr v)
 {
-	*(u32 *)location -= (*(u32 *)v);
+	*(u32 *)location -= (u32)v;
 	return 0;
 }
 
@@ -347,7 +347,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 			unsigned int j;
 
 			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
-				u64 hi20_loc =
+				unsigned long hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
 				u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info);
@@ -360,12 +360,12 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 					Elf_Sym *hi20_sym =
 						(Elf_Sym *)sechdrs[symindex].sh_addr
 						+ ELF_RISCV_R_SYM(rel[j].r_info);
-					u64 hi20_sym_val =
+					unsigned long hi20_sym_val =
 						hi20_sym->st_value
 						+ rel[j].r_addend;
 
 					/* Calculate lo12 */
-					u64 offset = hi20_sym_val - hi20_loc;
+					size_t offset = hi20_sym_val - hi20_loc;
 					if (IS_ENABLED(CONFIG_MODULE_SECTIONS)
 					    && hi20_type == R_RISCV_GOT_HI20) {
 						offset = module_emit_got_entry(
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index ba3e80712797..9f82a7e34c64 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -50,7 +50,7 @@ static int riscv_gpr_set(struct task_struct *target,
 	struct pt_regs *regs;
 
 	regs = task_pt_regs(target);
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &regs, 0, -1);
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1);
 	return ret;
 }
 
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index ee44a48faf79..f0d2070866d4 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -220,8 +220,3 @@ void __init setup_arch(char **cmdline_p)
 	riscv_fill_hwcap();
 }
 
-static int __init riscv_device_init(void)
-{
-	return of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-subsys_initcall_sync(riscv_device_init);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index c77df8142be2..58a522f9bcc3 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -28,7 +28,9 @@ static void __init zone_sizes_init(void)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
 
+#ifdef CONFIG_ZONE_DMA32
 	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+#endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
 	free_area_init_nodes(max_zone_pfns);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index baed39772c84..8a1863d9ed53 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -140,7 +140,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_GCC_PLUGINS
+	select HAVE_GCC_PLUGINS if BROKEN
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
@@ -160,6 +160,7 @@ config S390
 	select HAVE_OPROFILE
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select MODULES_USE_ELF_RELA
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
index 607c5e9fba3d..2ce28bf0c5ec 100644
--- a/arch/s390/kernel/compat_wrapper.c
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -183,3 +183,4 @@ COMPAT_SYSCALL_WRAP2(s390_guarded_storage, int, command, struct gs_cb *, gs_cb);
 COMPAT_SYSCALL_WRAP5(statx, int, dfd, const char __user *, path, unsigned, flags, unsigned, mask, struct statx __user *, buffer);
 COMPAT_SYSCALL_WRAP4(s390_sthyi, unsigned long, code, void __user *, info, u64 __user *, rc, unsigned long, flags);
 COMPAT_SYSCALL_WRAP5(kexec_file_load, int, kernel_fd, int, initrd_fd, unsigned long, cmdline_len, const char __user *, cmdline_ptr, unsigned long, flags)
+COMPAT_SYSCALL_WRAP4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32, sig)
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index f03402efab4b..150130c897c3 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -357,6 +357,10 @@ ENTRY(system_call)
 	stg	%r2,__PT_R2(%r11)		# store return value
 
 .Lsysc_return:
+#ifdef CONFIG_DEBUG_RSEQ
+	lgr	%r2,%r11
+	brasl	%r14,rseq_syscall
+#endif
 	LOCKDEP_SYS_EXIT
 .Lsysc_tif:
 	TSTMSK	__PT_FLAGS(%r11),_PIF_WORK
@@ -1265,7 +1269,7 @@ cleanup_critical:
 	jl	0f
 	clg	%r9,BASED(.Lcleanup_table+104)	# .Lload_fpu_regs_end
 	jl	.Lcleanup_load_fpu_regs
-0:	BR_EX	%r14
+0:	BR_EX	%r14,%r11
 
 	.align	8
 .Lcleanup_table:
@@ -1301,7 +1305,7 @@ cleanup_critical:
 	ni	__SIE_PROG0C+3(%r9),0xfe	# no longer in SIE
 	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	larl	%r9,sie_exit			# skip forward to sie_exit
-	BR_EX	%r14
+	BR_EX	%r14,%r11
 #endif
 
 .Lcleanup_system_call:
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 2d2960ab3e10..22f08245aa5d 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -498,7 +498,7 @@ void do_signal(struct pt_regs *regs)
 		}
 		/* No longer in a system call */
 		clear_pt_regs_flag(regs, PIF_SYSCALL);
-
+		rseq_signal_deliver(&ksig, regs);
 		if (is_compat_task())
 			handle_signal32(&ksig, oldset, regs);
 		else
@@ -537,4 +537,5 @@ void do_notify_resume(struct pt_regs *regs)
 {
 	clear_thread_flag(TIF_NOTIFY_RESUME);
 	tracehook_notify_resume(regs);
+	rseq_handle_notify_resume(NULL, regs);
 }
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index 8b210ead7956..022fc099b628 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -389,3 +389,5 @@
 379  common	statx			sys_statx			compat_sys_statx
 380  common	s390_sthyi		sys_s390_sthyi			compat_sys_s390_sthyi
 381  common	kexec_file_load		sys_kexec_file_load		compat_sys_kexec_file_load
+382  common	io_pgetevents		sys_io_pgetevents		compat_sys_io_pgetevents
+383  common	rseq			sys_rseq			compat_sys_rseq
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 84bd6329a88d..e3bd5627afef 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -252,6 +252,8 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
 		spin_unlock_bh(&mm->context.lock);
 		if (mask != 0)
 			return;
+	} else {
+		atomic_xor_bits(&page->_refcount, 3U << 24);
 	}
 
 	pgtable_page_dtor(page);
@@ -304,6 +306,8 @@ static void __tlb_remove_table(void *_table)
 			break;
 		/* fallthrough */
 	case 3:		/* 4K page table with pgstes */
+		if (mask & 3)
+			atomic_xor_bits(&page->_refcount, 3 << 24);
 		pgtable_page_dtor(page);
 		__free_page(page);
 		break;
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d2db8acb1a55..5f0234ec8038 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -1286,6 +1286,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 		goto free_addrs;
 	}
 	if (bpf_jit_prog(&jit, fp)) {
+		bpf_jit_binary_free(header);
 		fp = orig_fp;
 		goto free_addrs;
 	}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..887d3a7bb646 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -63,7 +63,7 @@ config X86
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_REFCOUNT
 	select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
-	select ARCH_HAS_UACCESS_MCSAFE		if X86_64
+	select ARCH_HAS_UACCESS_MCSAFE		if X86_64 && X86_MCE
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index e57665b4ba1c..e98522ea6f09 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -114,18 +114,12 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 	struct pci_setup_rom *rom = NULL;
 	efi_status_t status;
 	unsigned long size;
-	uint64_t attributes, romsize;
+	uint64_t romsize;
 	void *romimage;
 
-	status = efi_call_proto(efi_pci_io_protocol, attributes, pci,
-				EfiPciIoAttributeOperationGet, 0ULL,
-				&attributes);
-	if (status != EFI_SUCCESS)
-		return status;
-
 	/*
-	 * Some firmware images contain EFI function pointers at the place where the
-	 * romimage and romsize fields are supposed to be. Typically the EFI
+	 * Some firmware images contain EFI function pointers at the place where
+	 * the romimage and romsize fields are supposed to be. Typically the EFI
 	 * code is mapped at high addresses, translating to an unrealistically
 	 * large romsize. The UEFI spec limits the size of option ROMs to 16
 	 * MiB so we reject any ROMs over 16 MiB in size to catch this.
diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 9254e0b6cc06..717bf0776421 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -535,6 +535,7 @@ ENTRY(crypto_aegis128_aesni_enc_tail)
 	movdqu STATE3, 0x40(STATEP)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_aegis128_aesni_enc_tail)
 
 .macro decrypt_block a s0 s1 s2 s3 s4 i
diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S
index 9263c344f2c7..4eda2b8db9e1 100644
--- a/arch/x86/crypto/aegis128l-aesni-asm.S
+++ b/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -645,6 +645,7 @@ ENTRY(crypto_aegis128l_aesni_enc_tail)
 	state_store0
 
 	FRAME_END
+	ret
 ENDPROC(crypto_aegis128l_aesni_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S
index 1d977d515bf9..32aae8397268 100644
--- a/arch/x86/crypto/aegis256-aesni-asm.S
+++ b/arch/x86/crypto/aegis256-aesni-asm.S
@@ -543,6 +543,7 @@ ENTRY(crypto_aegis256_aesni_enc_tail)
 	state_store0
 
 	FRAME_END
+	ret
 ENDPROC(crypto_aegis256_aesni_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S
index 37d422e77931..07653d4582a6 100644
--- a/arch/x86/crypto/morus1280-avx2-asm.S
+++ b/arch/x86/crypto/morus1280-avx2-asm.S
@@ -453,6 +453,7 @@ ENTRY(crypto_morus1280_avx2_enc_tail)
 	vmovdqu STATE4, (4 * 32)(%rdi)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_morus1280_avx2_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S
index 1fe637c7be9d..bd1aa1b60869 100644
--- a/arch/x86/crypto/morus1280-sse2-asm.S
+++ b/arch/x86/crypto/morus1280-sse2-asm.S
@@ -652,6 +652,7 @@ ENTRY(crypto_morus1280_sse2_enc_tail)
 	movdqu STATE4_HI, (9 * 16)(%rdi)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_morus1280_sse2_enc_tail)
 
 /*
diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S
index 71c72a0a0862..efa02816d921 100644
--- a/arch/x86/crypto/morus640-sse2-asm.S
+++ b/arch/x86/crypto/morus640-sse2-asm.S
@@ -437,6 +437,7 @@ ENTRY(crypto_morus640_sse2_enc_tail)
 	movdqu STATE4, (4 * 16)(%rdi)
 
 	FRAME_END
+	ret
 ENDPROC(crypto_morus640_sse2_enc_tail)
 
 /*
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8a10a045b57b..8cf03f101938 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -408,9 +408,11 @@ static int alloc_bts_buffer(int cpu)
 	ds->bts_buffer_base = (unsigned long) cea;
 	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
-	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
+	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
+	ds->bts_absolute_maximum = ds->bts_buffer_base +
+					max * BTS_RECORD_SIZE;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
+					(max / 16) * BTS_RECORD_SIZE;
 	return 0;
 }
 
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index f68855499391..402338365651 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -114,6 +114,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 		nr_bank = cpumask_to_vpset(&(ipi_arg->vp_set), mask);
 	}
+	if (nr_bank < 0)
+		goto ipi_mask_ex_done;
 	if (!nr_bank)
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
 
@@ -158,6 +160,9 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 
 	for_each_cpu(cur_cpu, mask) {
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
+		if (vcpu == VP_INVAL)
+			goto ipi_mask_done;
+
 		/*
 		 * This particular version of the IPI hypercall can
 		 * only target upto 64 CPUs.
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 4c431e1c1eff..1ff420217298 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -265,7 +265,7 @@ void __init hyperv_init(void)
 {
 	u64 guest_id, required_msrs;
 	union hv_x64_msr_hypercall_contents hypercall_msr;
-	int cpuhp;
+	int cpuhp, i;
 
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return;
@@ -293,6 +293,9 @@ void __init hyperv_init(void)
 	if (!hv_vp_index)
 		return;
 
+	for (i = 0; i < num_possible_cpus(); i++)
+		hv_vp_index[i] = VP_INVAL;
+
 	hv_vp_assist_page = kcalloc(num_possible_cpus(),
 				    sizeof(*hv_vp_assist_page), GFP_KERNEL);
 	if (!hv_vp_assist_page) {
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index c356098b6fb9..4d4015ddcf26 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -7,8 +7,6 @@
 #ifndef _ASM_X86_MACH_DEFAULT_APM_H
 #define _ASM_X86_MACH_DEFAULT_APM_H
 
-#include <asm/nospec-branch.h>
-
 #ifdef APM_ZERO_SEGS
 #	define APM_DO_ZERO_SEGS \
 		"pushl %%ds\n\t" \
@@ -34,7 +32,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -47,7 +44,6 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		  "=S" (*esi)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 }
 
 static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
@@ -60,7 +56,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 	 * N.B. We do NOT need a cld after the BIOS call
 	 * because we always save and restore the flags.
 	 */
-	firmware_restrict_branch_speculation_start();
 	__asm__ __volatile__(APM_DO_ZERO_SEGS
 		"pushl %%edi\n\t"
 		"pushl %%ebp\n\t"
@@ -73,7 +68,6 @@ static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
 		  "=S" (si)
 		: "a" (func), "b" (ebx_in), "c" (ecx_in)
 		: "memory", "cc");
-	firmware_restrict_branch_speculation_end();
 	return error;
 }
 
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 219faaec51df..990770f9e76b 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -46,6 +46,65 @@
 #define _ASM_SI		__ASM_REG(si)
 #define _ASM_DI		__ASM_REG(di)
 
+#ifndef __x86_64__
+/* 32 bit */
+
+#define _ASM_ARG1	_ASM_AX
+#define _ASM_ARG2	_ASM_DX
+#define _ASM_ARG3	_ASM_CX
+
+#define _ASM_ARG1L	eax
+#define _ASM_ARG2L	edx
+#define _ASM_ARG3L	ecx
+
+#define _ASM_ARG1W	ax
+#define _ASM_ARG2W	dx
+#define _ASM_ARG3W	cx
+
+#define _ASM_ARG1B	al
+#define _ASM_ARG2B	dl
+#define _ASM_ARG3B	cl
+
+#else
+/* 64 bit */
+
+#define _ASM_ARG1	_ASM_DI
+#define _ASM_ARG2	_ASM_SI
+#define _ASM_ARG3	_ASM_DX
+#define _ASM_ARG4	_ASM_CX
+#define _ASM_ARG5	r8
+#define _ASM_ARG6	r9
+
+#define _ASM_ARG1Q	rdi
+#define _ASM_ARG2Q	rsi
+#define _ASM_ARG3Q	rdx
+#define _ASM_ARG4Q	rcx
+#define _ASM_ARG5Q	r8
+#define _ASM_ARG6Q	r9
+
+#define _ASM_ARG1L	edi
+#define _ASM_ARG2L	esi
+#define _ASM_ARG3L	edx
+#define _ASM_ARG4L	ecx
+#define _ASM_ARG5L	r8d
+#define _ASM_ARG6L	r9d
+
+#define _ASM_ARG1W	di
+#define _ASM_ARG2W	si
+#define _ASM_ARG3W	dx
+#define _ASM_ARG4W	cx
+#define _ASM_ARG5W	r8w
+#define _ASM_ARG6W	r9w
+
+#define _ASM_ARG1B	dil
+#define _ASM_ARG2B	sil
+#define _ASM_ARG3B	dl
+#define _ASM_ARG4B	cl
+#define _ASM_ARG5B	r8b
+#define _ASM_ARG6B	r9b
+
+#endif
+
 /*
  * Macros to generate condition code outputs from inline assembly,
  * The output operand must be type "bool".
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 89f08955fff7..c4fc17220df9 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -13,7 +13,7 @@
  * Interrupt control:
  */
 
-static inline unsigned long native_save_fl(void)
+extern inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;
 
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 3cd14311edfa..5a7375ed5f7c 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -9,6 +9,8 @@
 #include <asm/hyperv-tlfs.h>
 #include <asm/nospec-branch.h>
 
+#define VP_INVAL	U32_MAX
+
 struct ms_hyperv_info {
 	u32 features;
 	u32 misc_features;
@@ -20,7 +22,6 @@ struct ms_hyperv_info {
 
 extern struct ms_hyperv_info ms_hyperv;
 
-
 /*
  * Generate the guest ID.
  */
@@ -281,6 +282,8 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	 */
 	for_each_cpu(cpu, cpus) {
 		vcpu = hv_cpu_number_to_vp_number(cpu);
+		if (vcpu == VP_INVAL)
+			return -1;
 		vcpu_bank = vcpu / 64;
 		vcpu_offset = vcpu % 64;
 		__set_bit(vcpu_offset, (unsigned long *)
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 62acb613114b..a9d637bc301d 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -52,7 +52,12 @@ copy_to_user_mcsafe(void *to, const void *from, unsigned len)
 	unsigned long ret;
 
 	__uaccess_begin();
-	ret = memcpy_mcsafe(to, from, len);
+	/*
+	 * Note, __memcpy_mcsafe() is explicitly used since it can
+	 * handle exceptions / faults.  memcpy_mcsafe() may fall back to
+	 * memcpy() which lacks this handling.
+	 */
+	ret = __memcpy_mcsafe(to, from, len);
 	__uaccess_end();
 	return ret;
 }
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 02d6f5cf4e70..8824d01c0c35 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -61,6 +61,7 @@ obj-y			+= alternative.o i8253.o hw_breakpoint.o
 obj-y			+= tsc.o tsc_msr.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
 obj-y			+= resource.o
+obj-y			+= irqflags.o
 
 obj-y				+= process.o
 obj-y				+= fpu/
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 5d0de79fdab0..ec00d1ff5098 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -240,6 +240,7 @@
 #include <asm/olpc.h>
 #include <asm/paravirt.h>
 #include <asm/reboot.h>
+#include <asm/nospec-branch.h>
 
 #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
 extern int (*console_blank_hook)(int);
@@ -614,11 +615,13 @@ static long __apm_bios_call(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	apm_bios_call_asm(call->func, call->ebx, call->ecx,
 			  &call->eax, &call->ebx, &call->ecx, &call->edx,
 			  &call->esi);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
@@ -690,10 +693,12 @@ static long __apm_bios_call_simple(void *_call)
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
+	firmware_restrict_branch_speculation_start();
 	APM_DO_SAVE_SEGS;
 	error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
 					 &call->eax);
 	APM_DO_RESTORE_SEGS;
+	firmware_restrict_branch_speculation_end();
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 082d7875cef8..38915fbfae73 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -543,7 +543,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		nodes_per_socket = ((value >> 3) & 7) + 1;
 	}
 
-	if (c->x86 >= 0x15 && c->x86 <= 0x17) {
+	if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) &&
+	    !boot_cpu_has(X86_FEATURE_VIRT_SSBD) &&
+	    c->x86 >= 0x15 && c->x86 <= 0x17) {
 		unsigned int bit;
 
 		switch (c->x86) {
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 404df26b7de8..5c0ea39311fe 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -155,7 +155,8 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
 		guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;
 
 		/* SSBD controlled in MSR_SPEC_CTRL */
-		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD))
+		if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) ||
+		    static_cpu_has(X86_FEATURE_AMD_SSBD))
 			hostval |= ssbd_tif_to_spec_ctrl(ti->flags);
 
 		if (hostval != guestval) {
@@ -533,9 +534,10 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
 		 * Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
 		 * use a completely different MSR and bit dependent on family.
 		 */
-		if (!static_cpu_has(X86_FEATURE_MSR_SPEC_CTRL))
+		if (!static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) &&
+		    !static_cpu_has(X86_FEATURE_AMD_SSBD)) {
 			x86_amd_ssb_disable();
-		else {
+		} else {
 			x86_spec_ctrl_base |= SPEC_CTRL_SSBD;
 			x86_spec_ctrl_mask |= SPEC_CTRL_SSBD;
 			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index c102ad51025e..8c50754c09c1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2165,9 +2165,6 @@ static ssize_t store_int_with_restart(struct device *s,
 	if (check_interval == old_check_interval)
 		return ret;
 
-	if (check_interval < 1)
-		check_interval = 1;
-
 	mutex_lock(&mce_sysfs_mutex);
 	mce_restart();
 	mutex_unlock(&mce_sysfs_mutex);
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index 4021d3859499..40eee6cc4124 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -106,7 +106,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 
 	memset(line, 0, LINE_SIZE);
 
-	length = strncpy_from_user(line, buf, LINE_SIZE - 1);
+	len = min_t(size_t, len, LINE_SIZE - 1);
+	length = strncpy_from_user(line, buf, len);
 	if (length < 0)
 		return length;
 
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index da5d8ac60062..50d5848bf22e 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -338,6 +338,18 @@ static resource_size_t __init gen3_stolen_base(int num, int slot, int func,
 	return bsm & INTEL_BSM_MASK;
 }
 
+static resource_size_t __init gen11_stolen_base(int num, int slot, int func,
+						resource_size_t stolen_size)
+{
+	u64 bsm;
+
+	bsm = read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW0);
+	bsm &= INTEL_BSM_MASK;
+	bsm |= (u64)read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW1) << 32;
+
+	return bsm;
+}
+
 static resource_size_t __init i830_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
@@ -498,6 +510,11 @@ static const struct intel_early_ops chv_early_ops __initconst = {
 	.stolen_size = chv_stolen_size,
 };
 
+static const struct intel_early_ops gen11_early_ops __initconst = {
+	.stolen_base = gen11_stolen_base,
+	.stolen_size = gen9_stolen_size,
+};
+
 static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_I830_IDS(&i830_early_ops),
 	INTEL_I845G_IDS(&i845_early_ops),
@@ -529,6 +546,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_CFL_IDS(&gen9_early_ops),
 	INTEL_GLK_IDS(&gen9_early_ops),
 	INTEL_CNL_IDS(&gen9_early_ops),
+	INTEL_ICL_11_IDS(&gen11_early_ops),
 };
 
 struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S
new file mode 100644
index 000000000000..ddeeaac8adda
--- /dev/null
+++ b/arch/x86/kernel/irqflags.S
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/asm.h>
+#include <asm/export.h>
+#include <linux/linkage.h>
+
+/*
+ * unsigned long native_save_fl(void)
+ */
+ENTRY(native_save_fl)
+	pushf
+	pop %_ASM_AX
+	ret
+ENDPROC(native_save_fl)
+EXPORT_SYMBOL(native_save_fl)
+
+/*
+ * void native_restore_fl(unsigned long flags)
+ * %eax/%rdi: flags
+ */
+ENTRY(native_restore_fl)
+	push %_ASM_ARG1
+	popf
+	ret
+ENDPROC(native_restore_fl)
+EXPORT_SYMBOL(native_restore_fl)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index bf8d1eb7fca3..3b8e7c13c614 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -138,6 +138,7 @@ static unsigned long kvm_get_tsc_khz(void)
 	src = &hv_clock[cpu].pvti;
 	tsc_khz = pvclock_tsc_khz(src);
 	put_cpu();
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
 	return tsc_khz;
 }
 
@@ -319,6 +320,8 @@ void __init kvmclock_init(void)
 	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
+	pvclock_set_pvti_cpu0_va(hv_clock);
+
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
@@ -366,14 +369,11 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 	vcpu_time = &hv_clock[cpu].pvti;
 	flags = pvclock_read_flags(vcpu_time);
 
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT)) {
-		put_cpu();
-		return 1;
-	}
-
-	pvclock_set_pvti_cpu0_va(hv_clock);
 	put_cpu();
 
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+		return 1;
+
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
 #endif
 	return 0;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2f7d1d2a5c3..db9656e13ea0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -221,6 +221,11 @@ static void notrace start_secondary(void *unused)
 #ifdef CONFIG_X86_32
 	/* switch away from the initial page table */
 	load_cr3(swapper_pg_dir);
+	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
 	__flush_tlb_all();
 #endif
 	load_current_idt();
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 92fd433c50b9..1bbec387d289 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -85,7 +85,7 @@ config KVM_AMD_SEV
 	def_bool y
 	bool "AMD Secure Encrypted Virtualization (SEV) support"
 	depends on KVM_AMD && X86_64
-	depends on CRYPTO_DEV_CCP && CRYPTO_DEV_CCP_DD && CRYPTO_DEV_SP_PSP
+	depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m)
 	---help---
 	Provides support for launching Encrypted VMs on AMD processors.
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d594690d8b95..6b8f11521c41 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -890,7 +890,7 @@ static int mmu_topup_memory_cache_page(struct kvm_mmu_memory_cache *cache,
 	if (cache->nobjs >= min)
 		return 0;
 	while (cache->nobjs < ARRAY_SIZE(cache->objects)) {
-		page = (void *)__get_free_page(GFP_KERNEL);
+		page = (void *)__get_free_page(GFP_KERNEL_ACCOUNT);
 		if (!page)
 			return -ENOMEM;
 		cache->objects[cache->nobjs++] = page;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1689f433f3a0..e30da9a2430c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2571,6 +2571,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 #ifdef CONFIG_X86_64
 	int cpu = raw_smp_processor_id();
+	unsigned long fs_base, kernel_gs_base;
 #endif
 	int i;
 
@@ -2586,12 +2587,20 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	vmx->host_state.gs_ldt_reload_needed = vmx->host_state.ldt_sel;
 
 #ifdef CONFIG_X86_64
-	save_fsgs_for_kvm();
-	vmx->host_state.fs_sel = current->thread.fsindex;
-	vmx->host_state.gs_sel = current->thread.gsindex;
-#else
-	savesegment(fs, vmx->host_state.fs_sel);
-	savesegment(gs, vmx->host_state.gs_sel);
+	if (likely(is_64bit_mm(current->mm))) {
+		save_fsgs_for_kvm();
+		vmx->host_state.fs_sel = current->thread.fsindex;
+		vmx->host_state.gs_sel = current->thread.gsindex;
+		fs_base = current->thread.fsbase;
+		kernel_gs_base = current->thread.gsbase;
+	} else {
+#endif
+		savesegment(fs, vmx->host_state.fs_sel);
+		savesegment(gs, vmx->host_state.gs_sel);
+#ifdef CONFIG_X86_64
+		fs_base = read_msr(MSR_FS_BASE);
+		kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+	}
 #endif
 	if (!(vmx->host_state.fs_sel & 7)) {
 		vmcs_write16(HOST_FS_SELECTOR, vmx->host_state.fs_sel);
@@ -2611,10 +2620,10 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	savesegment(ds, vmx->host_state.ds_sel);
 	savesegment(es, vmx->host_state.es_sel);
 
-	vmcs_writel(HOST_FS_BASE, current->thread.fsbase);
+	vmcs_writel(HOST_FS_BASE, fs_base);
 	vmcs_writel(HOST_GS_BASE, cpu_kernelmode_gs_base(cpu));
 
-	vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+	vmx->msr_host_kernel_gs_base = kernel_gs_base;
 	if (is_long_mode(&vmx->vcpu))
 		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #else
@@ -4322,11 +4331,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	vmcs_conf->order = get_order(vmcs_conf->size);
 	vmcs_conf->basic_cap = vmx_msr_high & ~0x1fff;
 
-	/* KVM supports Enlightened VMCS v1 only */
-	if (static_branch_unlikely(&enable_evmcs))
-		vmcs_conf->revision_id = KVM_EVMCS_VERSION;
-	else
-		vmcs_conf->revision_id = vmx_msr_low;
+	vmcs_conf->revision_id = vmx_msr_low;
 
 	vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
 	vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
@@ -4396,7 +4401,13 @@ static struct vmcs *alloc_vmcs_cpu(int cpu)
 		return NULL;
 	vmcs = page_address(pages);
 	memset(vmcs, 0, vmcs_config.size);
-	vmcs->revision_id = vmcs_config.revision_id; /* vmcs revision id */
+
+	/* KVM supports Enlightened VMCS v1 only */
+	if (static_branch_unlikely(&enable_evmcs))
+		vmcs->revision_id = KVM_EVMCS_VERSION;
+	else
+		vmcs->revision_id = vmcs_config.revision_id;
+
 	return vmcs;
 }
 
@@ -4564,6 +4575,19 @@ static __init int alloc_kvm_area(void)
 			return -ENOMEM;
 		}
 
+		/*
+		 * When eVMCS is enabled, alloc_vmcs_cpu() sets
+		 * vmcs->revision_id to KVM_EVMCS_VERSION instead of
+		 * revision_id reported by MSR_IA32_VMX_BASIC.
+		 *
+		 * However, even though not explictly documented by
+		 * TLFS, VMXArea passed as VMXON argument should
+		 * still be marked with revision_id reported by
+		 * physical CPU.
+		 */
+		if (static_branch_unlikely(&enable_evmcs))
+			vmcs->revision_id = vmcs_config.revision_id;
+
 		per_cpu(vmxarea, cpu) = vmcs;
 	}
 	return 0;
@@ -11753,7 +11777,6 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
-	u32 msr_entry_idx;
 	u32 exit_qual;
 	int r;
 
@@ -11775,10 +11798,10 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu)
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
 	r = EXIT_REASON_MSR_LOAD_FAIL;
-	msr_entry_idx = nested_vmx_load_msr(vcpu,
-					    vmcs12->vm_entry_msr_load_addr,
-					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx)
+	exit_qual = nested_vmx_load_msr(vcpu,
+					vmcs12->vm_entry_msr_load_addr,
+					vmcs12->vm_entry_msr_load_count);
+	if (exit_qual)
 		goto fail;
 
 	/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0046aa70205a..2b812b3c5088 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1097,6 +1097,7 @@ static u32 msr_based_features[] = {
 
 	MSR_F10H_DECFG,
 	MSR_IA32_UCODE_REV,
+	MSR_IA32_ARCH_CAPABILITIES,
 };
 
 static unsigned int num_msr_based_features;
@@ -1105,7 +1106,8 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	switch (msr->index) {
 	case MSR_IA32_UCODE_REV:
-		rdmsrl(msr->index, msr->data);
+	case MSR_IA32_ARCH_CAPABILITIES:
+		rdmsrl_safe(msr->index, &msr->data);
 		break;
 	default:
 		if (kvm_x86_ops->get_msr_feature(msr))
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 2e9ee023e6bc..81a8e33115ad 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -6,7 +6,7 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o sha256.o entry64.o string
 targets += $(purgatory-y)
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z nodefaultlib
diff --git a/arch/x86/um/mem_32.c b/arch/x86/um/mem_32.c
index 744afdc18cf3..56c44d865f7b 100644
--- a/arch/x86/um/mem_32.c
+++ b/arch/x86/um/mem_32.c
@@ -16,7 +16,7 @@ static int __init gate_vma_init(void)
 	if (!FIXADDR_USER_START)
 		return 0;
 
-	gate_vma.vm_mm = NULL;
+	vma_init(&gate_vma, NULL);
 	gate_vma.vm_start = FIXADDR_USER_START;
 	gate_vma.vm_end = FIXADDR_USER_END;
 	gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 8d4e2e1ae60b..439a94bf89ad 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1207,12 +1207,20 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	xen_setup_features();
 
-	xen_setup_machphys_mapping();
-
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_init_ops.patch = paravirt_patch_default;
 	pv_cpu_ops = xen_cpu_ops;
+	xen_init_irq_ops();
+
+	/*
+	 * Setup xen_vcpu early because it is needed for
+	 * local_irq_disable(), irqs_disabled(), e.g. in printk().
+	 *
+	 * Don't do the full vcpu_info placement stuff until we have
+	 * the cpu_possible_mask and a non-dummy shared_info.
+	 */
+	xen_vcpu_info_reset(0);
 
 	x86_platform.get_nmi_reason = xen_get_nmi_reason;
 
@@ -1225,10 +1233,12 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 * Set up some pagetable state before starting to set any ptes.
 	 */
 
+	xen_setup_machphys_mapping();
 	xen_init_mmu_ops();
 
 	/* Prevent unwanted bits from being set in PTEs. */
 	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	__default_kernel_pte_mask &= ~_PAGE_GLOBAL;
 
 	/*
 	 * Prevent page tables from being allocated in highmem, even
@@ -1249,20 +1259,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
-	xen_init_irq_ops();
-
 	/* Let's presume PV guests always boot on vCPU with id 0. */
 	per_cpu(xen_vcpu_id, 0) = 0;
 
-	/*
-	 * Setup xen_vcpu early because idt_setup_early_handler needs it for
-	 * local_irq_disable(), irqs_disabled().
-	 *
-	 * Don't do the full vcpu_info placement stuff until we have
-	 * the cpu_possible_mask and a non-dummy shared_info.
-	 */
-	xen_vcpu_info_reset(0);
-
 	idt_setup_early_handler();
 
 	xen_init_capabilities();
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index 74179852e46c..7515a19fd324 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -128,8 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = {
 
 void __init xen_init_irq_ops(void)
 {
-	/* For PVH we use default pv_irq_ops settings. */
-	if (!xen_feature(XENFEAT_hvm_callback_vector))
-		pv_irq_ops = xen_irq_ops;
+	pv_irq_ops = xen_irq_ops;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 }
diff --git a/block/bio.c b/block/bio.c
index 67eff5eddc49..047c5dca6d90 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -903,25 +903,27 @@ int bio_add_page(struct bio *bio, struct page *page,
 EXPORT_SYMBOL(bio_add_page);
 
 /**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
  * @bio: bio to add pages to
  * @iter: iov iterator describing the region to be mapped
  *
- * Pins as many pages from *iter and appends them to @bio's bvec array. The
+ * Pins pages from *iter and appends them to @bio's bvec array. The
  * pages will have to be released using put_page() when done.
+ * For multi-segment *iter, this function only adds pages from the
+ * the next non-empty segment of the iov iterator.
  */
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
-	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
-	size_t offset, diff;
+	size_t offset;
 	ssize_t size;
 
 	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
-	nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
+	idx = nr_pages = (size + offset + PAGE_SIZE - 1) / PAGE_SIZE;
 
 	/*
 	 * Deep magic below:  We need to walk the pinned pages backwards
@@ -934,21 +936,46 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	bio->bi_iter.bi_size += size;
 	bio->bi_vcnt += nr_pages;
 
-	diff = (nr_pages * PAGE_SIZE - offset) - size;
-	while (nr_pages--) {
-		bv[nr_pages].bv_page = pages[nr_pages];
-		bv[nr_pages].bv_len = PAGE_SIZE;
-		bv[nr_pages].bv_offset = 0;
+	while (idx--) {
+		bv[idx].bv_page = pages[idx];
+		bv[idx].bv_len = PAGE_SIZE;
+		bv[idx].bv_offset = 0;
 	}
 
 	bv[0].bv_offset += offset;
 	bv[0].bv_len -= offset;
-	if (diff)
-		bv[bio->bi_vcnt - 1].bv_len -= diff;
+	bv[nr_pages - 1].bv_len -= nr_pages * PAGE_SIZE - offset - size;
 
 	iov_iter_advance(iter, size);
 	return 0;
 }
+
+/**
+ * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * @bio: bio to add pages to
+ * @iter: iov iterator describing the region to be mapped
+ *
+ * Pins pages from *iter and appends them to @bio's bvec array. The
+ * pages will have to be released using put_page() when done.
+ * The function tries, but does not guarantee, to pin as many pages as
+ * fit into the bio, or are requested in *iter, whatever is smaller.
+ * If MM encounters an error pinning the requested pages, it stops.
+ * Error is returned only if 0 pages could be pinned.
+ */
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
+{
+	unsigned short orig_vcnt = bio->bi_vcnt;
+
+	do {
+		int ret = __bio_iov_iter_get_pages(bio, iter);
+
+		if (unlikely(ret))
+			return bio->bi_vcnt > orig_vcnt ? 0 : ret;
+
+	} while (iov_iter_count(iter) && !bio_full(bio));
+
+	return 0;
+}
 EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages);
 
 static void submit_bio_wait_endio(struct bio *bio)
@@ -1866,6 +1893,7 @@ struct bio *bio_split(struct bio *bio, int sectors,
 		bio_integrity_trim(split);
 
 	bio_advance(bio, split->bi_iter.bi_size);
+	bio->bi_iter.bi_done = 0;
 
 	if (bio_flagged(bio, BIO_TRACE_COMPLETION))
 		bio_set_flag(split, BIO_TRACE_COMPLETION);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 95919268564b..654b0dc7e001 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -558,10 +558,8 @@ static void __blk_mq_complete_request(struct request *rq)
 	bool shared = false;
 	int cpu;
 
-	if (cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) !=
-			MQ_RQ_IN_FLIGHT)
+	if (!blk_mq_mark_complete(rq))
 		return;
-
 	if (rq->internal_tag != -1)
 		blk_mq_sched_completed_request(rq);
 
diff --git a/block/bsg.c b/block/bsg.c
index 66602c489956..3da540faf673 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -267,8 +267,6 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, fmode_t mode)
 	} else if (hdr->din_xfer_len) {
 		ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr->din_xferp),
 				hdr->din_xfer_len, GFP_KERNEL);
-	} else {
-		ret = blk_rq_map_user(q, rq, NULL, NULL, 0, GFP_KERNEL);
 	}
 
 	if (ret)
diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index 314c52c967e5..c166f424871c 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1155,8 +1155,10 @@ int af_alg_get_rsgl(struct sock *sk, struct msghdr *msg, int flags,
 
 		/* make one iovec available as scatterlist */
 		err = af_alg_make_sg(&rsgl->sgl, &msg->msg_iter, seglen);
-		if (err < 0)
+		if (err < 0) {
+			rsgl->sg_num_bytes = 0;
 			return err;
+		}
 
 		/* chain the new scatterlist with previous one */
 		if (areq->last_rsgl)
diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
index fc0c2e2328cd..fe9d46d81750 100644
--- a/drivers/acpi/acpica/hwsleep.c
+++ b/drivers/acpi/acpica/hwsleep.c
@@ -51,16 +51,23 @@ acpi_status acpi_hw_legacy_sleep(u8 sleep_state)
 		return_ACPI_STATUS(status);
 	}
 
-	/*
-	 * 1) Disable all GPEs
-	 * 2) Enable all wakeup GPEs
-	 */
+	/* Disable all GPEs */
 	status = acpi_hw_disable_all_gpes();
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
+	/*
+	 * If the target sleep state is S5, clear all GPEs and fixed events too
+	 */
+	if (sleep_state == ACPI_STATE_S5) {
+		status = acpi_hw_clear_acpi_status();
+		if (ACPI_FAILURE(status)) {
+			return_ACPI_STATUS(status);
+		}
+	}
 	acpi_gbl_system_awake_and_running = FALSE;
 
+	 /* Enable all wakeup GPEs */
 	status = acpi_hw_enable_all_wakeup_gpes();
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
diff --git a/drivers/acpi/acpica/psloop.c b/drivers/acpi/acpica/psloop.c
index bc5f05906bd1..ee840be150b5 100644
--- a/drivers/acpi/acpica/psloop.c
+++ b/drivers/acpi/acpica/psloop.c
@@ -497,6 +497,18 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state)
 			status =
 			    acpi_ps_create_op(walk_state, aml_op_start, &op);
 			if (ACPI_FAILURE(status)) {
+				/*
+				 * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by
+				 * executing it as a control method. However, if we encounter
+				 * an error while loading the table, we need to keep trying to
+				 * load the table rather than aborting the table load. Set the
+				 * status to AE_OK to proceed with the table load.
+				 */
+				if ((walk_state->
+				     parse_flags & ACPI_PARSE_MODULE_LEVEL)
+				    && status == AE_ALREADY_EXISTS) {
+					status = AE_OK;
+				}
 				if (status == AE_CTRL_PARSE_CONTINUE) {
 					continue;
 				}
@@ -694,6 +706,20 @@ acpi_status acpi_ps_parse_loop(struct acpi_walk_state *walk_state)
 			    acpi_ps_next_parse_state(walk_state, op, status);
 			if (status == AE_CTRL_PENDING) {
 				status = AE_OK;
+			} else
+			    if ((walk_state->
+				 parse_flags & ACPI_PARSE_MODULE_LEVEL)
+				&& ACPI_FAILURE(status)) {
+				/*
+				 * ACPI_PARSE_MODULE_LEVEL means that we are loading a table by
+				 * executing it as a control method. However, if we encounter
+				 * an error while loading the table, we need to keep trying to
+				 * load the table rather than aborting the table load. Set the
+				 * status to AE_OK to proceed with the table load. If we get a
+				 * failure at this point, it means that the dispatcher got an
+				 * error while processing Op (most likely an AML operand error.
+				 */
+				status = AE_OK;
 			}
 		}
 
diff --git a/drivers/acpi/acpica/uterror.c b/drivers/acpi/acpica/uterror.c
index 5a64ddaed8a3..e47430272692 100644
--- a/drivers/acpi/acpica/uterror.c
+++ b/drivers/acpi/acpica/uterror.c
@@ -182,19 +182,19 @@ acpi_ut_prefixed_namespace_error(const char *module_name,
 	switch (lookup_status) {
 	case AE_ALREADY_EXISTS:
 
-		acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
 		message = "Failure creating";
 		break;
 
 	case AE_NOT_FOUND:
 
-		acpi_os_printf("\n" ACPI_MSG_BIOS_ERROR);
+		acpi_os_printf(ACPI_MSG_BIOS_ERROR);
 		message = "Could not resolve";
 		break;
 
 	default:
 
-		acpi_os_printf("\n" ACPI_MSG_ERROR);
+		acpi_os_printf(ACPI_MSG_ERROR);
 		message = "Failure resolving";
 		break;
 	}
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b0113a5802a3..d79ad844c78f 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -717,10 +717,11 @@ void battery_hook_register(struct acpi_battery_hook *hook)
 			 */
 			pr_err("extension failed to load: %s", hook->name);
 			__battery_hook_unregister(hook, 0);
-			return;
+			goto end;
 		}
 	}
 	pr_info("new extension: %s\n", hook->name);
+end:
 	mutex_unlock(&hook_mutex);
 }
 EXPORT_SYMBOL_GPL(battery_hook_register);
@@ -732,7 +733,7 @@ EXPORT_SYMBOL_GPL(battery_hook_register);
 */
 static void battery_hook_add_battery(struct acpi_battery *battery)
 {
-	struct acpi_battery_hook *hook_node;
+	struct acpi_battery_hook *hook_node, *tmp;
 
 	mutex_lock(&hook_mutex);
 	INIT_LIST_HEAD(&battery->list);
@@ -744,15 +745,15 @@ static void battery_hook_add_battery(struct acpi_battery *battery)
 	 * when a battery gets hotplugged or initialized
 	 * during the battery module initialization.
 	 */
-	list_for_each_entry(hook_node, &battery_hook_list, list) {
+	list_for_each_entry_safe(hook_node, tmp, &battery_hook_list, list) {
 		if (hook_node->add_battery(battery->bat)) {
 			/*
 			 * The notification of the extensions has failed, to
 			 * prevent further errors we will unload the extension.
 			 */
-			__battery_hook_unregister(hook_node, 0);
 			pr_err("error in extension, unloading: %s",
 					hook_node->name);
+			__battery_hook_unregister(hook_node, 0);
 		}
 	}
 	mutex_unlock(&hook_mutex);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 442a9e24f439..917f77f4cb55 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2042,7 +2042,7 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 		.ident = "Thinkpad X1 Carbon 6th",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "20KGS3JF01"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"),
 		},
 	},
 	{ },
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index d15814e1727f..7c479002e798 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -408,6 +408,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 	const guid_t *guid;
 	int rc, i;
 
+	if (cmd_rc)
+		*cmd_rc = -EINVAL;
 	func = cmd;
 	if (cmd == ND_CMD_CALL) {
 		call_pkg = buf;
@@ -518,6 +520,8 @@ int acpi_nfit_ctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		 * If we return an error (like elsewhere) then caller wouldn't
 		 * be able to rely upon data returned to make calculation.
 		 */
+		if (cmd_rc)
+			*cmd_rc = 0;
 		return 0;
 	}
 
@@ -1273,7 +1277,7 @@ static ssize_t scrub_show(struct device *dev,
 
 		mutex_lock(&acpi_desc->init_mutex);
 		rc = sprintf(buf, "%d%s", acpi_desc->scrub_count,
-				work_busy(&acpi_desc->dwork.work)
+				acpi_desc->scrub_busy
 				&& !acpi_desc->cancel ? "+\n" : "\n");
 		mutex_unlock(&acpi_desc->init_mutex);
 	}
@@ -2939,6 +2943,32 @@ static unsigned int __acpi_nfit_scrub(struct acpi_nfit_desc *acpi_desc,
 	return 0;
 }
 
+static void __sched_ars(struct acpi_nfit_desc *acpi_desc, unsigned int tmo)
+{
+	lockdep_assert_held(&acpi_desc->init_mutex);
+
+	acpi_desc->scrub_busy = 1;
+	/* note this should only be set from within the workqueue */
+	if (tmo)
+		acpi_desc->scrub_tmo = tmo;
+	queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
+}
+
+static void sched_ars(struct acpi_nfit_desc *acpi_desc)
+{
+	__sched_ars(acpi_desc, 0);
+}
+
+static void notify_ars_done(struct acpi_nfit_desc *acpi_desc)
+{
+	lockdep_assert_held(&acpi_desc->init_mutex);
+
+	acpi_desc->scrub_busy = 0;
+	acpi_desc->scrub_count++;
+	if (acpi_desc->scrub_count_state)
+		sysfs_notify_dirent(acpi_desc->scrub_count_state);
+}
+
 static void acpi_nfit_scrub(struct work_struct *work)
 {
 	struct acpi_nfit_desc *acpi_desc;
@@ -2949,14 +2979,10 @@ static void acpi_nfit_scrub(struct work_struct *work)
 	mutex_lock(&acpi_desc->init_mutex);
 	query_rc = acpi_nfit_query_poison(acpi_desc);
 	tmo = __acpi_nfit_scrub(acpi_desc, query_rc);
-	if (tmo) {
-		queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
-		acpi_desc->scrub_tmo = tmo;
-	} else {
-		acpi_desc->scrub_count++;
-		if (acpi_desc->scrub_count_state)
-			sysfs_notify_dirent(acpi_desc->scrub_count_state);
-	}
+	if (tmo)
+		__sched_ars(acpi_desc, tmo);
+	else
+		notify_ars_done(acpi_desc);
 	memset(acpi_desc->ars_status, 0, acpi_desc->max_ars);
 	mutex_unlock(&acpi_desc->init_mutex);
 }
@@ -3037,7 +3063,7 @@ static int acpi_nfit_register_regions(struct acpi_nfit_desc *acpi_desc)
 			break;
 		}
 
-	queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
+	sched_ars(acpi_desc);
 	return 0;
 }
 
@@ -3239,7 +3265,7 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc, unsigned long flags)
 		}
 	}
 	if (scheduled) {
-		queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
+		sched_ars(acpi_desc);
 		dev_dbg(dev, "ars_scan triggered\n");
 	}
 	mutex_unlock(&acpi_desc->init_mutex);
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index 7d15856a739f..a97ff42fe311 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -203,6 +203,7 @@ struct acpi_nfit_desc {
 	unsigned int max_ars;
 	unsigned int scrub_count;
 	unsigned int scrub_mode;
+	unsigned int scrub_busy:1;
 	unsigned int cancel:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
diff --git a/drivers/acpi/pptt.c b/drivers/acpi/pptt.c
index e5ea1974d1e3..d1e26cb599bf 100644
--- a/drivers/acpi/pptt.c
+++ b/drivers/acpi/pptt.c
@@ -481,8 +481,14 @@ static int topology_get_acpi_cpu_tag(struct acpi_table_header *table,
 	if (cpu_node) {
 		cpu_node = acpi_find_processor_package_id(table, cpu_node,
 							  level, flag);
-		/* Only the first level has a guaranteed id */
-		if (level == 0)
+		/*
+		 * As per specification if the processor structure represents
+		 * an actual processor, then ACPI processor ID must be valid.
+		 * For processor containers ACPI_PPTT_ACPI_PROCESSOR_ID_VALID
+		 * should be set if the UID is valid
+		 */
+		if (level == 0 ||
+		    cpu_node->flags & ACPI_PPTT_ACPI_PROCESSOR_ID_VALID)
 			return cpu_node->acpi_processor_id;
 		return ACPI_PTR_DIFF(cpu_node, table);
 	}
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 2b16e7c8fff3..39b181d6bd0d 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -398,7 +398,6 @@ config SATA_DWC_VDEBUG
 
 config SATA_HIGHBANK
 	tristate "Calxeda Highbank SATA support"
-	depends on HAS_DMA
 	depends on ARCH_HIGHBANK || COMPILE_TEST
 	help
 	  This option enables support for the Calxeda Highbank SoC's
@@ -408,7 +407,6 @@ config SATA_HIGHBANK
 
 config SATA_MV
 	tristate "Marvell SATA support"
-	depends on HAS_DMA
 	depends on PCI || ARCH_DOVE || ARCH_MV78XX0 || \
 		   ARCH_MVEBU || ARCH_ORION5X || COMPILE_TEST
 	select GENERIC_PHY
diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 738fb22978dd..b2b9eba1d214 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -400,6 +400,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
 	{ PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
 	{ PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */
+	{ PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI */
 
 	/* JMicron 360/1/3/5/6, match class to avoid IDE function */
 	{ PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
@@ -1280,6 +1281,59 @@ static bool ahci_broken_suspend(struct pci_dev *pdev)
 	return strcmp(buf, dmi->driver_data) < 0;
 }
 
+static bool ahci_broken_lpm(struct pci_dev *pdev)
+{
+	static const struct dmi_system_id sysids[] = {
+		/* Various Lenovo 50 series have LPM issues with older BIOSen */
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X250"),
+			},
+			.driver_data = "20180406", /* 1.31 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L450"),
+			},
+			.driver_data = "20180420", /* 1.28 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad T450s"),
+			},
+			.driver_data = "20180315", /* 1.33 */
+		},
+		{
+			.matches = {
+				DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+				DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
+			},
+			/*
+			 * Note date based on release notes, 2.35 has been
+			 * reported to be good, but I've been unable to get
+			 * a hold of the reporter to get the DMI BIOS date.
+			 * TODO: fix this.
+			 */
+			.driver_data = "20180310", /* 2.35 */
+		},
+		{ }	/* terminate list */
+	};
+	const struct dmi_system_id *dmi = dmi_first_match(sysids);
+	int year, month, date;
+	char buf[9];
+
+	if (!dmi)
+		return false;
+
+	dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
+	snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
+
+	return strcmp(buf, dmi->driver_data) < 0;
+}
+
 static bool ahci_broken_online(struct pci_dev *pdev)
 {
 #define ENCODE_BUSDEVFN(bus, slot, func)			\
@@ -1694,6 +1748,12 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			"quirky BIOS, skipping spindown on poweroff\n");
 	}
 
+	if (ahci_broken_lpm(pdev)) {
+		pi.flags |= ATA_FLAG_NO_LPM;
+		dev_warn(&pdev->dev,
+			 "BIOS update required for Link Power Management support\n");
+	}
+
 	if (ahci_broken_suspend(pdev)) {
 		hpriv->flags |= AHCI_HFLAG_NO_SUSPEND;
 		dev_warn(&pdev->dev,
diff --git a/drivers/ata/ahci_mvebu.c b/drivers/ata/ahci_mvebu.c
index 0045dacd814b..72d90b4c3aae 100644
--- a/drivers/ata/ahci_mvebu.c
+++ b/drivers/ata/ahci_mvebu.c
@@ -82,7 +82,7 @@ static void ahci_mvebu_regret_option(struct ahci_host_priv *hpriv)
  *
  * Return: 0 on success; Error code otherwise.
  */
-int ahci_mvebu_stop_engine(struct ata_port *ap)
+static int ahci_mvebu_stop_engine(struct ata_port *ap)
 {
 	void __iomem *port_mmio = ahci_port_base(ap);
 	u32 tmp, port_fbs;
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 965842a08743..09620c2ffa0f 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/nospec.h>
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -1146,10 +1147,12 @@ static ssize_t ahci_led_store(struct ata_port *ap, const char *buf,
 
 	/* get the slot number from the message */
 	pmp = (state & EM_MSG_LED_PMP_SLOT) >> 8;
-	if (pmp < EM_MAX_SLOTS)
+	if (pmp < EM_MAX_SLOTS) {
+		pmp = array_index_nospec(pmp, EM_MAX_SLOTS);
 		emp = &pp->em_priv[pmp];
-	else
+	} else {
 		return -EINVAL;
+	}
 
 	/* mask off the activity bits if we are in sw_activity
 	 * mode, user should turn off sw_activity before setting
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 27d15ed7fa3d..cc71c63df381 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2493,6 +2493,9 @@ int ata_dev_configure(struct ata_device *dev)
 	    (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
 		dev->horkage |= ATA_HORKAGE_NOLPM;
 
+	if (ap->flags & ATA_FLAG_NO_LPM)
+		dev->horkage |= ATA_HORKAGE_NOLPM;
+
 	if (dev->horkage & ATA_HORKAGE_NOLPM) {
 		ata_dev_warn(dev, "LPM support broken, forcing max_power\n");
 		dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index d5412145d76d..01306c018398 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -614,8 +614,7 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
 		list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
 			struct ata_queued_cmd *qc;
 
-			for (i = 0; i < ATA_MAX_QUEUE; i++) {
-				qc = __ata_qc_from_tag(ap, i);
+			ata_qc_for_each_raw(ap, qc, i) {
 				if (qc->flags & ATA_QCFLAG_ACTIVE &&
 				    qc->scsicmd == scmd)
 					break;
@@ -818,14 +817,13 @@ EXPORT_SYMBOL_GPL(ata_port_wait_eh);
 
 static int ata_eh_nr_in_flight(struct ata_port *ap)
 {
+	struct ata_queued_cmd *qc;
 	unsigned int tag;
 	int nr = 0;
 
 	/* count only non-internal commands */
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		if (ata_tag_internal(tag))
-			continue;
-		if (ata_qc_from_tag(ap, tag))
+	ata_qc_for_each(ap, qc, tag) {
+		if (qc)
 			nr++;
 	}
 
@@ -847,13 +845,13 @@ void ata_eh_fastdrain_timerfn(struct timer_list *t)
 		goto out_unlock;
 
 	if (cnt == ap->fastdrain_cnt) {
+		struct ata_queued_cmd *qc;
 		unsigned int tag;
 
 		/* No progress during the last interval, tag all
 		 * in-flight qcs as timed out and freeze the port.
 		 */
-		for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-			struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
+		ata_qc_for_each(ap, qc, tag) {
 			if (qc)
 				qc->err_mask |= AC_ERR_TIMEOUT;
 		}
@@ -999,6 +997,7 @@ void ata_port_schedule_eh(struct ata_port *ap)
 
 static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
 {
+	struct ata_queued_cmd *qc;
 	int tag, nr_aborted = 0;
 
 	WARN_ON(!ap->ops->error_handler);
@@ -1007,9 +1006,7 @@ static int ata_do_link_abort(struct ata_port *ap, struct ata_link *link)
 	ata_eh_set_pending(ap, 0);
 
 	/* include internal tag in iteration */
-	for (tag = 0; tag <= ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_with_internal(ap, qc, tag) {
 		if (qc && (!link || qc->dev->link == link)) {
 			qc->flags |= ATA_QCFLAG_FAILED;
 			ata_qc_complete(qc);
@@ -1712,9 +1709,7 @@ void ata_eh_analyze_ncq_error(struct ata_link *link)
 		return;
 
 	/* has LLDD analyzed already? */
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED))
 			continue;
 
@@ -2136,6 +2131,7 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 {
 	struct ata_port *ap = link->ap;
 	struct ata_eh_context *ehc = &link->eh_context;
+	struct ata_queued_cmd *qc;
 	struct ata_device *dev;
 	unsigned int all_err_mask = 0, eflags = 0;
 	int tag, nr_failed = 0, nr_quiet = 0;
@@ -2168,9 +2164,7 @@ static void ata_eh_link_autopsy(struct ata_link *link)
 
 	all_err_mask |= ehc->i.err_mask;
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED) ||
 		    ata_dev_phys_link(qc->dev) != link)
 			continue;
@@ -2436,6 +2430,7 @@ static void ata_eh_link_report(struct ata_link *link)
 {
 	struct ata_port *ap = link->ap;
 	struct ata_eh_context *ehc = &link->eh_context;
+	struct ata_queued_cmd *qc;
 	const char *frozen, *desc;
 	char tries_buf[6] = "";
 	int tag, nr_failed = 0;
@@ -2447,9 +2442,7 @@ static void ata_eh_link_report(struct ata_link *link)
 	if (ehc->i.desc[0] != '\0')
 		desc = ehc->i.desc;
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED) ||
 		    ata_dev_phys_link(qc->dev) != link ||
 		    ((qc->flags & ATA_QCFLAG_QUIET) &&
@@ -2511,8 +2504,7 @@ static void ata_eh_link_report(struct ata_link *link)
 		  ehc->i.serror & SERR_DEV_XCHG ? "DevExch " : "");
 #endif
 
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
+	ata_qc_for_each_raw(ap, qc, tag) {
 		struct ata_taskfile *cmd = &qc->tf, *res = &qc->result_tf;
 		char data_buf[20] = "";
 		char cdb_buf[70] = "";
@@ -3992,12 +3984,11 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
  */
 void ata_eh_finish(struct ata_port *ap)
 {
+	struct ata_queued_cmd *qc;
 	int tag;
 
 	/* retry or finish qcs */
-	for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-		struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
-
+	ata_qc_for_each_raw(ap, qc, tag) {
 		if (!(qc->flags & ATA_QCFLAG_FAILED))
 			continue;
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 6a91d04351d9..aad1b01447de 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -3805,10 +3805,20 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
 		 */
 		goto invalid_param_len;
 	}
-	if (block > dev->n_sectors)
-		goto out_of_range;
 
 	all = cdb[14] & 0x1;
+	if (all) {
+		/*
+		 * Ignore the block address (zone ID) as defined by ZBC.
+		 */
+		block = 0;
+	} else if (block >= dev->n_sectors) {
+		/*
+		 * Block must be a valid zone ID (a zone start LBA).
+		 */
+		fp = 2;
+		goto invalid_fld;
+	}
 
 	if (ata_ncq_enabled(qc->dev) &&
 	    ata_fpdma_zac_mgmt_out_supported(qc->dev)) {
@@ -3837,10 +3847,6 @@ static unsigned int ata_scsi_zbc_out_xlat(struct ata_queued_cmd *qc)
  invalid_fld:
 	ata_scsi_set_invalid_field(qc->dev, scmd, fp, 0xff);
 	return 1;
- out_of_range:
-	/* "Logical Block Address out of range" */
-	ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x21, 0x00);
-	return 1;
 invalid_param_len:
 	/* "Parameter list length error" */
 	ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x1a, 0x0);
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index b8d9cfc60374..4dc528bf8e85 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -395,12 +395,6 @@ static inline unsigned int sata_fsl_tag(unsigned int tag,
 {
 	/* We let libATA core do actual (queue) tag allocation */
 
-	/* all non NCQ/queued commands should have tag#0 */
-	if (ata_tag_internal(tag)) {
-		DPRINTK("mapping internal cmds to tag#0\n");
-		return 0;
-	}
-
 	if (unlikely(tag >= SATA_FSL_QUEUE_DEPTH)) {
 		DPRINTK("tag %d invalid : out of range\n", tag);
 		return 0;
@@ -1229,8 +1223,7 @@ static void sata_fsl_host_intr(struct ata_port *ap)
 
 	/* Workaround for data length mismatch errata */
 	if (unlikely(hstatus & INT_ON_DATA_LENGTH_MISMATCH)) {
-		for (tag = 0; tag < ATA_MAX_QUEUE; tag++) {
-			qc = ata_qc_from_tag(ap, tag);
+		ata_qc_for_each_with_internal(ap, qc, tag) {
 			if (qc && ata_is_atapi(qc->tf.protocol)) {
 				u32 hcontrol;
 				/* Set HControl[27] to clear error registers */
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index 10ae11aa1926..72c9b922a77b 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -675,7 +675,6 @@ static int nv_adma_slave_config(struct scsi_device *sdev)
 	struct ata_port *ap = ata_shost_to_port(sdev->host);
 	struct nv_adma_port_priv *pp = ap->private_data;
 	struct nv_adma_port_priv *port0, *port1;
-	struct scsi_device *sdev0, *sdev1;
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
 	unsigned long segment_boundary, flags;
 	unsigned short sg_tablesize;
@@ -736,8 +735,6 @@ static int nv_adma_slave_config(struct scsi_device *sdev)
 
 	port0 = ap->host->ports[0]->private_data;
 	port1 = ap->host->ports[1]->private_data;
-	sdev0 = ap->host->ports[0]->link.device[0].sdev;
-	sdev1 = ap->host->ports[1]->link.device[0].sdev;
 	if ((port0->flags & NV_ADMA_ATAPI_SETUP_COMPLETE) ||
 	    (port1->flags & NV_ADMA_ATAPI_SETUP_COMPLETE)) {
 		/*
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index ff81a576347e..82532c299bb5 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -1618,7 +1618,7 @@ static int rx_init(struct atm_dev *dev)
 	skb_queue_head_init(&iadev->rx_dma_q);  
 	iadev->rx_free_desc_qhead = NULL;   
 
-	iadev->rx_open = kcalloc(4, iadev->num_vc, GFP_KERNEL);
+	iadev->rx_open = kcalloc(iadev->num_vc, sizeof(void *), GFP_KERNEL);
 	if (!iadev->rx_open) {
 		printk(KERN_ERR DEV_LABEL "itf %d couldn't get free page\n",
 		dev->number);  
diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index a8d2eb0ceb8d..2c288d1f42bb 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1483,6 +1483,8 @@ static int zatm_ioctl(struct atm_dev *dev,unsigned int cmd,void __user *arg)
 					return -EFAULT;
 				if (pool < 0 || pool > ZATM_LAST_POOL)
 					return -EINVAL;
+				pool = array_index_nospec(pool,
+							  ZATM_LAST_POOL + 1);
 				if (copy_from_user(&info,
 				    &((struct zatm_pool_req __user *) arg)->info,
 				    sizeof(info))) return -EFAULT;
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 1435d7281c66..6ebcd65d64b6 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -434,14 +434,6 @@ re_probe:
 			goto probe_failed;
 	}
 
-	/*
-	 * Ensure devices are listed in devices_kset in correct order
-	 * It's important to move Dev to the end of devices_kset before
-	 * calling .probe, because it could be recursive and parent Dev
-	 * should always go first
-	 */
-	devices_kset_move_last(dev);
-
 	if (dev->bus->probe) {
 		ret = dev->bus->probe(dev);
 		if (ret)
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index c298de8a8308..9e8484189034 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2235,7 +2235,7 @@ static void genpd_dev_pm_sync(struct device *dev)
 }
 
 static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
-				 unsigned int index)
+				 unsigned int index, bool power_on)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
@@ -2271,9 +2271,11 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device_node *np,
 	dev->pm_domain->detach = genpd_dev_pm_detach;
 	dev->pm_domain->sync = genpd_dev_pm_sync;
 
-	genpd_lock(pd);
-	ret = genpd_power_on(pd, 0);
-	genpd_unlock(pd);
+	if (power_on) {
+		genpd_lock(pd);
+		ret = genpd_power_on(pd, 0);
+		genpd_unlock(pd);
+	}
 
 	if (ret)
 		genpd_remove_device(pd, dev);
@@ -2307,7 +2309,7 @@ int genpd_dev_pm_attach(struct device *dev)
 				       "#power-domain-cells") != 1)
 		return 0;
 
-	return __genpd_dev_pm_attach(dev, dev->of_node, 0);
+	return __genpd_dev_pm_attach(dev, dev->of_node, 0, true);
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 
@@ -2359,14 +2361,14 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	}
 
 	/* Try to attach the device to the PM domain at the specified index. */
-	ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index);
+	ret = __genpd_dev_pm_attach(genpd_dev, dev->of_node, index, false);
 	if (ret < 1) {
 		device_unregister(genpd_dev);
 		return ret ? ERR_PTR(ret) : NULL;
 	}
 
-	pm_runtime_set_active(genpd_dev);
 	pm_runtime_enable(genpd_dev);
+	genpd_queue_power_off_work(dev_to_genpd(genpd_dev));
 
 	return genpd_dev;
 }
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 1476cb3439f4..5e793dd7adfb 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -282,8 +282,8 @@ void drbd_request_endio(struct bio *bio)
 		what = COMPLETED_OK;
 	}
 
-	bio_put(req->private_bio);
 	req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status));
+	bio_put(bio);
 
 	/* not req_mod(), we need irqsave here! */
 	spin_lock_irqsave(&device->resource->req_lock, flags);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d6b6f434fd4b..4cb1d1be3cfb 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1613,6 +1613,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 		arg = (unsigned long) compat_ptr(arg);
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
+	case LOOP_SET_BLOCK_SIZE:
 		err = lo_ioctl(bdev, mode, cmd, arg);
 		break;
 	default:
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 74a05561b620..3fb95c8d9fd8 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -112,12 +112,16 @@ struct nbd_device {
 	struct task_struct *task_setup;
 };
 
+#define NBD_CMD_REQUEUED	1
+
 struct nbd_cmd {
 	struct nbd_device *nbd;
+	struct mutex lock;
 	int index;
 	int cookie;
-	struct completion send_complete;
 	blk_status_t status;
+	unsigned long flags;
+	u32 cmd_cookie;
 };
 
 #if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -146,6 +150,35 @@ static inline struct device *nbd_to_dev(struct nbd_device *nbd)
 	return disk_to_dev(nbd->disk);
 }
 
+static void nbd_requeue_cmd(struct nbd_cmd *cmd)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+
+	if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags))
+		blk_mq_requeue_request(req, true);
+}
+
+#define NBD_COOKIE_BITS 32
+
+static u64 nbd_cmd_handle(struct nbd_cmd *cmd)
+{
+	struct request *req = blk_mq_rq_from_pdu(cmd);
+	u32 tag = blk_mq_unique_tag(req);
+	u64 cookie = cmd->cmd_cookie;
+
+	return (cookie << NBD_COOKIE_BITS) | tag;
+}
+
+static u32 nbd_handle_to_tag(u64 handle)
+{
+	return (u32)handle;
+}
+
+static u32 nbd_handle_to_cookie(u64 handle)
+{
+	return (u32)(handle >> NBD_COOKIE_BITS);
+}
+
 static const char *nbdcmd_to_ascii(int cmd)
 {
 	switch (cmd) {
@@ -319,6 +352,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 	config = nbd->config;
 
+	if (!mutex_trylock(&cmd->lock))
+		return BLK_EH_RESET_TIMER;
+
 	if (config->num_connections > 1) {
 		dev_err_ratelimited(nbd_to_dev(nbd),
 				    "Connection timed out, retrying (%d/%d alive)\n",
@@ -343,7 +379,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 					nbd_mark_nsock_dead(nbd, nsock, 1);
 				mutex_unlock(&nsock->tx_lock);
 			}
-			blk_mq_requeue_request(req, true);
+			mutex_unlock(&cmd->lock);
+			nbd_requeue_cmd(cmd);
 			nbd_config_put(nbd);
 			return BLK_EH_DONE;
 		}
@@ -353,6 +390,7 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	}
 	set_bit(NBD_TIMEDOUT, &config->runtime_flags);
 	cmd->status = BLK_STS_IOERR;
+	mutex_unlock(&cmd->lock);
 	sock_shutdown(nbd);
 	nbd_config_put(nbd);
 done:
@@ -430,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 	struct iov_iter from;
 	unsigned long size = blk_rq_bytes(req);
 	struct bio *bio;
+	u64 handle;
 	u32 type;
 	u32 nbd_cmd_flags = 0;
-	u32 tag = blk_mq_unique_tag(req);
 	int sent = nsock->sent, skip = 0;
 
 	iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
@@ -474,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 			goto send_pages;
 		}
 		iov_iter_advance(&from, sent);
+	} else {
+		cmd->cmd_cookie++;
 	}
 	cmd->index = index;
 	cmd->cookie = nsock->cookie;
@@ -482,7 +522,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 		request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
 		request.len = htonl(size);
 	}
-	memcpy(request.handle, &tag, sizeof(tag));
+	handle = nbd_cmd_handle(cmd);
+	memcpy(request.handle, &handle, sizeof(handle));
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n",
 		req, nbdcmd_to_ascii(type),
@@ -500,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
 				nsock->pending = req;
 				nsock->sent = sent;
 			}
+			set_bit(NBD_CMD_REQUEUED, &cmd->flags);
 			return BLK_STS_RESOURCE;
 		}
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
@@ -541,6 +583,7 @@ send_pages:
 					 */
 					nsock->pending = req;
 					nsock->sent = sent;
+					set_bit(NBD_CMD_REQUEUED, &cmd->flags);
 					return BLK_STS_RESOURCE;
 				}
 				dev_err(disk_to_dev(nbd->disk),
@@ -573,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 	struct nbd_reply reply;
 	struct nbd_cmd *cmd;
 	struct request *req = NULL;
+	u64 handle;
 	u16 hwq;
 	u32 tag;
 	struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)};
 	struct iov_iter to;
+	int ret = 0;
 
 	reply.magic = 0;
 	iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
@@ -594,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return ERR_PTR(-EPROTO);
 	}
 
-	memcpy(&tag, reply.handle, sizeof(u32));
-
+	memcpy(&handle, reply.handle, sizeof(handle));
+	tag = nbd_handle_to_tag(handle);
 	hwq = blk_mq_unique_tag_to_hwq(tag);
 	if (hwq < nbd->tag_set.nr_hw_queues)
 		req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq],
@@ -606,11 +651,25 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		return ERR_PTR(-ENOENT);
 	}
 	cmd = blk_mq_rq_to_pdu(req);
+
+	mutex_lock(&cmd->lock);
+	if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) {
+		dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n",
+			req, cmd->cmd_cookie, nbd_handle_to_cookie(handle));
+		ret = -ENOENT;
+		goto out;
+	}
+	if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) {
+		dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n",
+			req);
+		ret = -ENOENT;
+		goto out;
+	}
 	if (ntohl(reply.error)) {
 		dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
 			ntohl(reply.error));
 		cmd->status = BLK_STS_IOERR;
-		return cmd;
+		goto out;
 	}
 
 	dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req);
@@ -635,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 				if (nbd_disconnected(config) ||
 				    config->num_connections <= 1) {
 					cmd->status = BLK_STS_IOERR;
-					return cmd;
+					goto out;
 				}
-				return ERR_PTR(-EIO);
+				ret = -EIO;
+				goto out;
 			}
 			dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
 				req, bvec.bv_len);
 		}
-	} else {
-		/* See the comment in nbd_queue_rq. */
-		wait_for_completion(&cmd->send_complete);
 	}
-	return cmd;
+out:
+	mutex_unlock(&cmd->lock);
+	return ret ? ERR_PTR(ret) : cmd;
 }
 
 static void recv_work(struct work_struct *work)
@@ -805,7 +864,7 @@ again:
 	 */
 	blk_mq_start_request(req);
 	if (unlikely(nsock->pending && nsock->pending != req)) {
-		blk_mq_requeue_request(req, true);
+		nbd_requeue_cmd(cmd);
 		ret = 0;
 		goto out;
 	}
@@ -818,7 +877,7 @@ again:
 		dev_err_ratelimited(disk_to_dev(nbd->disk),
 				    "Request send failed, requeueing\n");
 		nbd_mark_nsock_dead(nbd, nsock, 1);
-		blk_mq_requeue_request(req, true);
+		nbd_requeue_cmd(cmd);
 		ret = 0;
 	}
 out:
@@ -842,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * that the server is misbehaving (or there was an error) before we're
 	 * done sending everything over the wire.
 	 */
-	init_completion(&cmd->send_complete);
+	mutex_lock(&cmd->lock);
+	clear_bit(NBD_CMD_REQUEUED, &cmd->flags);
 
 	/* We can be called directly from the user space process, which means we
 	 * could possibly have signals pending so our sendmsg will fail.  In
@@ -854,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 		ret = BLK_STS_IOERR;
 	else if (!ret)
 		ret = BLK_STS_OK;
-	complete(&cmd->send_complete);
+	mutex_unlock(&cmd->lock);
 
 	return ret;
 }
@@ -1460,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq,
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq);
 	cmd->nbd = set->driver_data;
+	cmd->flags = 0;
+	mutex_init(&cmd->lock);
 	return 0;
 }
 
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index 1cc29629d238..80d60f43db56 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -169,9 +169,9 @@ static int sysc_get_clocks(struct sysc *ddata)
 	const char *name;
 	int nr_fck = 0, nr_ick = 0, i, error = 0;
 
-	ddata->clock_roles = devm_kzalloc(ddata->dev,
-					  sizeof(*ddata->clock_roles) *
+	ddata->clock_roles = devm_kcalloc(ddata->dev,
 					  SYSC_MAX_CLOCKS,
+					  sizeof(*ddata->clock_roles),
 					  GFP_KERNEL);
 	if (!ddata->clock_roles)
 		return -ENOMEM;
@@ -200,8 +200,8 @@ static int sysc_get_clocks(struct sysc *ddata)
 		return -EINVAL;
 	}
 
-	ddata->clocks = devm_kzalloc(ddata->dev,
-				     sizeof(*ddata->clocks) * ddata->nr_clocks,
+	ddata->clocks = devm_kcalloc(ddata->dev,
+				     ddata->nr_clocks, sizeof(*ddata->clocks),
 				     GFP_KERNEL);
 	if (!ddata->clocks)
 		return -ENOMEM;
diff --git a/drivers/char/agp/alpha-agp.c b/drivers/char/agp/alpha-agp.c
index 53fe633df1e8..c9bf2c219841 100644
--- a/drivers/char/agp/alpha-agp.c
+++ b/drivers/char/agp/alpha-agp.c
@@ -11,7 +11,7 @@
 
 #include "agp.h"
 
-static int alpha_core_agp_vm_fault(struct vm_fault *vmf)
+static vm_fault_t alpha_core_agp_vm_fault(struct vm_fault *vmf)
 {
 	alpha_agp_info *agp = agp_bridge->dev_private_data;
 	dma_addr_t dma_addr;
diff --git a/drivers/char/agp/amd64-agp.c b/drivers/char/agp/amd64-agp.c
index e50c29c97ca7..c69e39fdd02b 100644
--- a/drivers/char/agp/amd64-agp.c
+++ b/drivers/char/agp/amd64-agp.c
@@ -156,7 +156,7 @@ static u64 amd64_configure(struct pci_dev *hammer, u64 gatt_table)
 
 	/* Address to map to */
 	pci_read_config_dword(hammer, AMD64_GARTAPERTUREBASE, &tmp);
-	aperturebase = tmp << 25;
+	aperturebase = (u64)tmp << 25;
 	aper_base = (aperturebase & PCI_BASE_ADDRESS_MEM_MASK);
 
 	enable_gart_translation(hammer, gatt_table);
@@ -277,7 +277,7 @@ static int fix_northbridge(struct pci_dev *nb, struct pci_dev *agp, u16 cap)
 	pci_read_config_dword(nb, AMD64_GARTAPERTURECTL, &nb_order);
 	nb_order = (nb_order >> 1) & 7;
 	pci_read_config_dword(nb, AMD64_GARTAPERTUREBASE, &nb_base);
-	nb_aper = nb_base << 25;
+	nb_aper = (u64)nb_base << 25;
 
 	/* Northbridge seems to contain crap. Try the AGP bridge. */
 
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index ad353be871bf..90ec010bffbd 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -2088,8 +2088,10 @@ static int try_smi_init(struct smi_info *new_smi)
 	return 0;
 
 out_err:
-	ipmi_unregister_smi(new_smi->intf);
-	new_smi->intf = NULL;
+	if (new_smi->intf) {
+		ipmi_unregister_smi(new_smi->intf);
+		new_smi->intf = NULL;
+	}
 
 	kfree(init_name);
 
diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c
index fbfc05e3f3d1..bb882ab161fe 100644
--- a/drivers/char/ipmi/kcs_bmc.c
+++ b/drivers/char/ipmi/kcs_bmc.c
@@ -210,34 +210,23 @@ static void kcs_bmc_handle_cmd(struct kcs_bmc *kcs_bmc)
 int kcs_bmc_handle_event(struct kcs_bmc *kcs_bmc)
 {
 	unsigned long flags;
-	int ret = 0;
+	int ret = -ENODATA;
 	u8 status;
 
 	spin_lock_irqsave(&kcs_bmc->lock, flags);
 
-	if (!kcs_bmc->running) {
-		kcs_force_abort(kcs_bmc);
-		ret = -ENODEV;
-		goto out_unlock;
-	}
-
-	status = read_status(kcs_bmc) & (KCS_STATUS_IBF | KCS_STATUS_CMD_DAT);
-
-	switch (status) {
-	case KCS_STATUS_IBF | KCS_STATUS_CMD_DAT:
-		kcs_bmc_handle_cmd(kcs_bmc);
-		break;
-
-	case KCS_STATUS_IBF:
-		kcs_bmc_handle_data(kcs_bmc);
-		break;
+	status = read_status(kcs_bmc);
+	if (status & KCS_STATUS_IBF) {
+		if (!kcs_bmc->running)
+			kcs_force_abort(kcs_bmc);
+		else if (status & KCS_STATUS_CMD_DAT)
+			kcs_bmc_handle_cmd(kcs_bmc);
+		else
+			kcs_bmc_handle_data(kcs_bmc);
 
-	default:
-		ret = -ENODATA;
-		break;
+		ret = 0;
 	}
 
-out_unlock:
 	spin_unlock_irqrestore(&kcs_bmc->lock, flags);
 
 	return ret;
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index ffeb60d3434c..df66a9dd0aae 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -708,6 +708,7 @@ static int mmap_zero(struct file *file, struct vm_area_struct *vma)
 #endif
 	if (vma->vm_flags & VM_SHARED)
 		return shmem_zero_setup(vma);
+	vma_set_anonymous(vma);
 	return 0;
 }
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index cd888d4ee605..bd449ad52442 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1895,14 +1895,22 @@ static int
 write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
 {
 	size_t bytes;
-	__u32 buf[16];
+	__u32 t, buf[16];
 	const char __user *p = buffer;
 
 	while (count > 0) {
+		int b, i = 0;
+
 		bytes = min(count, sizeof(buf));
 		if (copy_from_user(&buf, p, bytes))
 			return -EFAULT;
 
+		for (b = bytes ; b > 0 ; b -= sizeof(__u32), i++) {
+			if (!arch_get_random_int(&t))
+				break;
+			buf[i] ^= t;
+		}
+
 		count -= bytes;
 		p += bytes;
 
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index ae40cbe770f0..0bb25dd009d1 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -96,7 +96,7 @@ obj-$(CONFIG_ARCH_SPRD)			+= sprd/
 obj-$(CONFIG_ARCH_STI)			+= st/
 obj-$(CONFIG_ARCH_STRATIX10)		+= socfpga/
 obj-$(CONFIG_ARCH_SUNXI)		+= sunxi/
-obj-$(CONFIG_ARCH_SUNXI)		+= sunxi-ng/
+obj-$(CONFIG_SUNXI_CCU)			+= sunxi-ng/
 obj-$(CONFIG_ARCH_TEGRA)		+= tegra/
 obj-y					+= ti/
 obj-$(CONFIG_CLK_UNIPHIER)		+= uniphier/
diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c
index 38b366b00c57..7b70a074095d 100644
--- a/drivers/clk/clk-aspeed.c
+++ b/drivers/clk/clk-aspeed.c
@@ -24,7 +24,7 @@
 #define ASPEED_MPLL_PARAM	0x20
 #define ASPEED_HPLL_PARAM	0x24
 #define  AST2500_HPLL_BYPASS_EN	BIT(20)
-#define  AST2400_HPLL_STRAPPED	BIT(18)
+#define  AST2400_HPLL_PROGRAMMED BIT(18)
 #define  AST2400_HPLL_BYPASS_EN	BIT(17)
 #define ASPEED_MISC_CTRL	0x2c
 #define  UART_DIV13_EN		BIT(12)
@@ -91,8 +91,8 @@ static const struct aspeed_gate_data aspeed_gates[] = {
 	[ASPEED_CLK_GATE_GCLK] =	{  1,  7, "gclk-gate",		NULL,	0 }, /* 2D engine */
 	[ASPEED_CLK_GATE_MCLK] =	{  2, -1, "mclk-gate",		"mpll",	CLK_IS_CRITICAL }, /* SDRAM */
 	[ASPEED_CLK_GATE_VCLK] =	{  3,  6, "vclk-gate",		NULL,	0 }, /* Video Capture */
-	[ASPEED_CLK_GATE_BCLK] =	{  4,  8, "bclk-gate",		"bclk",	0 }, /* PCIe/PCI */
-	[ASPEED_CLK_GATE_DCLK] =	{  5, -1, "dclk-gate",		NULL,	0 }, /* DAC */
+	[ASPEED_CLK_GATE_BCLK] =	{  4,  8, "bclk-gate",		"bclk",	CLK_IS_CRITICAL }, /* PCIe/PCI */
+	[ASPEED_CLK_GATE_DCLK] =	{  5, -1, "dclk-gate",		NULL,	CLK_IS_CRITICAL }, /* DAC */
 	[ASPEED_CLK_GATE_REFCLK] =	{  6, -1, "refclk-gate",	"clkin", CLK_IS_CRITICAL },
 	[ASPEED_CLK_GATE_USBPORT2CLK] =	{  7,  3, "usb-port2-gate",	NULL,	0 }, /* USB2.0 Host port 2 */
 	[ASPEED_CLK_GATE_LCLK] =	{  8,  5, "lclk-gate",		NULL,	0 }, /* LPC */
@@ -212,9 +212,22 @@ static int aspeed_clk_is_enabled(struct clk_hw *hw)
 {
 	struct aspeed_clk_gate *gate = to_aspeed_clk_gate(hw);
 	u32 clk = BIT(gate->clock_idx);
+	u32 rst = BIT(gate->reset_idx);
 	u32 enval = (gate->flags & CLK_GATE_SET_TO_DISABLE) ? 0 : clk;
 	u32 reg;
 
+	/*
+	 * If the IP is in reset, treat the clock as not enabled,
+	 * this happens with some clocks such as the USB one when
+	 * coming from cold reset. Without this, aspeed_clk_enable()
+	 * will fail to lift the reset.
+	 */
+	if (gate->reset_idx >= 0) {
+		regmap_read(gate->map, ASPEED_RESET_CTRL, &reg);
+		if (reg & rst)
+			return 0;
+	}
+
 	regmap_read(gate->map, ASPEED_CLK_STOP_CTRL, &reg);
 
 	return ((reg & clk) == enval) ? 1 : 0;
@@ -565,29 +578,45 @@ builtin_platform_driver(aspeed_clk_driver);
 static void __init aspeed_ast2400_cc(struct regmap *map)
 {
 	struct clk_hw *hw;
-	u32 val, freq, div;
+	u32 val, div, clkin, hpll;
+	const u16 hpll_rates[][4] = {
+		{384, 360, 336, 408},
+		{400, 375, 350, 425},
+	};
+	int rate;
 
 	/*
 	 * CLKIN is the crystal oscillator, 24, 48 or 25MHz selected by
 	 * strapping
 	 */
 	regmap_read(map, ASPEED_STRAP, &val);
-	if (val & CLKIN_25MHZ_EN)
-		freq = 25000000;
-	else if (val & AST2400_CLK_SOURCE_SEL)
-		freq = 48000000;
-	else
-		freq = 24000000;
-	hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, freq);
-	pr_debug("clkin @%u MHz\n", freq / 1000000);
+	rate = (val >> 8) & 3;
+	if (val & CLKIN_25MHZ_EN) {
+		clkin = 25000000;
+		hpll = hpll_rates[1][rate];
+	} else if (val & AST2400_CLK_SOURCE_SEL) {
+		clkin = 48000000;
+		hpll = hpll_rates[0][rate];
+	} else {
+		clkin = 24000000;
+		hpll = hpll_rates[0][rate];
+	}
+	hw = clk_hw_register_fixed_rate(NULL, "clkin", NULL, 0, clkin);
+	pr_debug("clkin @%u MHz\n", clkin / 1000000);
 
 	/*
 	 * High-speed PLL clock derived from the crystal. This the CPU clock,
-	 * and we assume that it is enabled
+	 * and we assume that it is enabled. It can be configured through the
+	 * HPLL_PARAM register, or set to a specified frequency by strapping.
 	 */
 	regmap_read(map, ASPEED_HPLL_PARAM, &val);
-	WARN(val & AST2400_HPLL_STRAPPED, "hpll is strapped not configured");
-	aspeed_clk_data->hws[ASPEED_CLK_HPLL] = aspeed_ast2400_calc_pll("hpll", val);
+	if (val & AST2400_HPLL_PROGRAMMED)
+		hw = aspeed_ast2400_calc_pll("hpll", val);
+	else
+		hw = clk_hw_register_fixed_rate(NULL, "hpll", "clkin", 0,
+				hpll * 1000000);
+
+	aspeed_clk_data->hws[ASPEED_CLK_HPLL] = hw;
 
 	/*
 	 * Strap bits 11:10 define the CPU/AHB clock frequency ratio (aka HCLK)
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 9760b526ca31..e2ed078abd90 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -24,7 +24,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/sched.h>
 #include <linux/clkdev.h>
-#include <linux/stringify.h>
 
 #include "clk.h"
 
@@ -2559,7 +2558,7 @@ static const struct {
 	unsigned long flag;
 	const char *name;
 } clk_flags[] = {
-#define ENTRY(f) { f, __stringify(f) }
+#define ENTRY(f) { f, #f }
 	ENTRY(CLK_SET_RATE_GATE),
 	ENTRY(CLK_SET_PARENT_GATE),
 	ENTRY(CLK_SET_RATE_PARENT),
diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c
index aae62a5b8734..d1bbee19ed0f 100644
--- a/drivers/clk/davinci/da8xx-cfgchip.c
+++ b/drivers/clk/davinci/da8xx-cfgchip.c
@@ -672,7 +672,7 @@ static int of_da8xx_usb_phy_clk_init(struct device *dev, struct regmap *regmap)
 
 	usb1 = da8xx_cfgchip_register_usb1_clk48(dev, regmap);
 	if (IS_ERR(usb1)) {
-		if (PTR_ERR(usb0) == -EPROBE_DEFER)
+		if (PTR_ERR(usb1) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 
 		dev_warn(dev, "Failed to register usb1_clk48 (%ld)\n",
diff --git a/drivers/clk/davinci/psc.h b/drivers/clk/davinci/psc.h
index 6a42529d31a9..cc5614567a70 100644
--- a/drivers/clk/davinci/psc.h
+++ b/drivers/clk/davinci/psc.h
@@ -107,7 +107,7 @@ extern const struct davinci_psc_init_data of_da850_psc1_init_data;
 #ifdef CONFIG_ARCH_DAVINCI_DM355
 extern const struct davinci_psc_init_data dm355_psc_init_data;
 #endif
-#ifdef CONFIG_ARCH_DAVINCI_DM356
+#ifdef CONFIG_ARCH_DAVINCI_DM365
 extern const struct davinci_psc_init_data dm365_psc_init_data;
 #endif
 #ifdef CONFIG_ARCH_DAVINCI_DM644x
diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c
index 58f546e04807..e4cf96ba704e 100644
--- a/drivers/clk/meson/clk-audio-divider.c
+++ b/drivers/clk/meson/clk-audio-divider.c
@@ -51,7 +51,7 @@ static unsigned long audio_divider_recalc_rate(struct clk_hw *hw,
 	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
 	unsigned long divider;
 
-	divider = meson_parm_read(clk->map, &adiv->div);
+	divider = meson_parm_read(clk->map, &adiv->div) + 1;
 
 	return DIV_ROUND_UP_ULL((u64)parent_rate, divider);
 }
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 240658404367..177fffb9ebef 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -498,6 +498,7 @@ static struct clk_regmap gxbb_fclk_div2 = {
 		.ops = &clk_regmap_gate_ops,
 		.parent_names = (const char *[]){ "fclk_div2_div" },
 		.num_parents = 1,
+		.flags = CLK_IS_CRITICAL,
 	},
 };
 
diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 6860bd5a37c5..44e4e27eddad 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -35,6 +35,7 @@
 #define CLK_SEL		0x10
 #define CLK_DIS		0x14
 
+#define  ARMADA_37XX_DVFS_LOAD_1 1
 #define LOAD_LEVEL_NR	4
 
 #define ARMADA_37XX_NB_L0L1	0x18
@@ -507,6 +508,40 @@ static long clk_pm_cpu_round_rate(struct clk_hw *hw, unsigned long rate,
 	return -EINVAL;
 }
 
+/*
+ * Switching the CPU from the L2 or L3 frequencies (300 and 200 Mhz
+ * respectively) to L0 frequency (1.2 Ghz) requires a significant
+ * amount of time to let VDD stabilize to the appropriate
+ * voltage. This amount of time is large enough that it cannot be
+ * covered by the hardware countdown register. Due to this, the CPU
+ * might start operating at L0 before the voltage is stabilized,
+ * leading to CPU stalls.
+ *
+ * To work around this problem, we prevent switching directly from the
+ * L2/L3 frequencies to the L0 frequency, and instead switch to the L1
+ * frequency in-between. The sequence therefore becomes:
+ * 1. First switch from L2/L3(200/300MHz) to L1(600MHZ)
+ * 2. Sleep 20ms for stabling VDD voltage
+ * 3. Then switch from L1(600MHZ) to L0(1200Mhz).
+ */
+static void clk_pm_cpu_set_rate_wa(unsigned long rate, struct regmap *base)
+{
+	unsigned int cur_level;
+
+	if (rate != 1200 * 1000 * 1000)
+		return;
+
+	regmap_read(base, ARMADA_37XX_NB_CPU_LOAD, &cur_level);
+	cur_level &= ARMADA_37XX_NB_CPU_LOAD_MASK;
+	if (cur_level <= ARMADA_37XX_DVFS_LOAD_1)
+		return;
+
+	regmap_update_bits(base, ARMADA_37XX_NB_CPU_LOAD,
+			   ARMADA_37XX_NB_CPU_LOAD_MASK,
+			   ARMADA_37XX_DVFS_LOAD_1);
+	msleep(20);
+}
+
 static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
 			       unsigned long parent_rate)
 {
@@ -537,6 +572,9 @@ static int clk_pm_cpu_set_rate(struct clk_hw *hw, unsigned long rate,
 			 */
 			reg = ARMADA_37XX_NB_CPU_LOAD;
 			mask = ARMADA_37XX_NB_CPU_LOAD_MASK;
+
+			clk_pm_cpu_set_rate_wa(rate, base);
+
 			regmap_update_bits(base, reg, mask, load_level);
 
 			return rate;
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index 9f35b3fe1d97..ff8d66fd94e6 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -2781,6 +2781,7 @@ static struct clk_branch gcc_ufs_rx_cfg_clk = {
 
 static struct clk_branch gcc_ufs_tx_symbol_0_clk = {
 	.halt_reg = 0x75018,
+	.halt_check = BRANCH_HALT_SKIP,
 	.clkr = {
 		.enable_reg = 0x75018,
 		.enable_mask = BIT(0),
diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c
index 1a25ee4f3658..4b20d1b67a1b 100644
--- a/drivers/clk/qcom/mmcc-msm8996.c
+++ b/drivers/clk/qcom/mmcc-msm8996.c
@@ -2910,6 +2910,7 @@ static struct gdsc mmagic_bimc_gdsc = {
 		.name = "mmagic_bimc",
 	},
 	.pwrsts = PWRSTS_OFF_ON,
+	.flags = ALWAYS_ON,
 };
 
 static struct gdsc mmagic_video_gdsc = {
diff --git a/drivers/clk/sunxi-ng/Makefile b/drivers/clk/sunxi-ng/Makefile
index acaa14cfa25c..49454700f2e5 100644
--- a/drivers/clk/sunxi-ng/Makefile
+++ b/drivers/clk/sunxi-ng/Makefile
@@ -1,24 +1,24 @@
 # SPDX-License-Identifier: GPL-2.0
 # Common objects
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_common.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mmc_timing.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_reset.o
+obj-y				+= ccu_common.o
+obj-y				+= ccu_mmc_timing.o
+obj-y				+= ccu_reset.o
 
 # Base clock types
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_div.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_frac.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_gate.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mux.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mult.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_phase.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_sdm.o
+obj-y				+= ccu_div.o
+obj-y				+= ccu_frac.o
+obj-y				+= ccu_gate.o
+obj-y				+= ccu_mux.o
+obj-y				+= ccu_mult.o
+obj-y				+= ccu_phase.o
+obj-y				+= ccu_sdm.o
 
 # Multi-factor clocks
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nk.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nkm.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nkmp.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_nm.o
-lib-$(CONFIG_SUNXI_CCU)		+= ccu_mp.o
+obj-y				+= ccu_nk.o
+obj-y				+= ccu_nkm.o
+obj-y				+= ccu_nkmp.o
+obj-y				+= ccu_nm.o
+obj-y				+= ccu_mp.o
 
 # SoC support
 obj-$(CONFIG_SUN50I_A64_CCU)	+= ccu-sun50i-a64.o
@@ -38,12 +38,3 @@ obj-$(CONFIG_SUN8I_R40_CCU)	+= ccu-sun8i-r40.o
 obj-$(CONFIG_SUN9I_A80_CCU)	+= ccu-sun9i-a80.o
 obj-$(CONFIG_SUN9I_A80_CCU)	+= ccu-sun9i-a80-de.o
 obj-$(CONFIG_SUN9I_A80_CCU)	+= ccu-sun9i-a80-usb.o
-
-# The lib-y file goals is supposed to work only in arch/*/lib or lib/. In our
-# case, we want to use that goal, but even though lib.a will be properly
-# generated, it will not be linked in, eventually resulting in a linker error
-# for missing symbols.
-#
-# We can work around that by explicitly adding lib.a to the obj-y goal. This is
-# an undocumented behaviour, but works well for now.
-obj-$(CONFIG_SUNXI_CCU)		+= lib.a
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 57cb2f00fc07..d8c7f5750cdb 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -735,7 +735,7 @@ static void __arch_timer_setup(unsigned type,
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
 		clk->rating = 400;
-		clk->cpumask = cpu_all_mask;
+		clk->cpumask = cpu_possible_mask;
 		if (arch_timer_mem_use_virtual) {
 			clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ece120da3353..3c3971256130 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2394,6 +2394,18 @@ static bool __init intel_pstate_no_acpi_pss(void)
 	return true;
 }
 
+static bool __init intel_pstate_no_acpi_pcch(void)
+{
+	acpi_status status;
+	acpi_handle handle;
+
+	status = acpi_get_handle(NULL, "\\_SB", &handle);
+	if (ACPI_FAILURE(status))
+		return true;
+
+	return !acpi_has_method(handle, "PCCH");
+}
+
 static bool __init intel_pstate_has_acpi_ppc(void)
 {
 	int i;
@@ -2453,7 +2465,10 @@ static bool __init intel_pstate_platform_pwr_mgmt_exists(void)
 
 	switch (plat_info[idx].data) {
 	case PSS:
-		return intel_pstate_no_acpi_pss();
+		if (!intel_pstate_no_acpi_pss())
+			return false;
+
+		return intel_pstate_no_acpi_pcch();
 	case PPC:
 		return intel_pstate_has_acpi_ppc() && !force_load;
 	}
diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 3f0ce2ae35ee..0c56c9759672 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -580,6 +580,10 @@ static int __init pcc_cpufreq_init(void)
 {
 	int ret;
 
+	/* Skip initialization if another cpufreq driver is there. */
+	if (cpufreq_get_current_driver())
+		return 0;
+
 	if (acpi_disabled)
 		return 0;
 
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index 29389accf3e9..efc9a7ae4857 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -183,6 +183,7 @@ static struct platform_driver qcom_cpufreq_kryo_driver = {
 static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
+	{}
 };
 
 /*
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index de2f8297a210..108c37fca782 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -189,14 +189,16 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 
 	/* prevent private mappings from being established */
 	if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
-		dev_info(dev, "%s: %s: fail, attempted private mapping\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, attempted private mapping\n",
 				current->comm, func);
 		return -EINVAL;
 	}
 
 	mask = dax_region->align - 1;
 	if (vma->vm_start & mask || vma->vm_end & mask) {
-		dev_info(dev, "%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
 				current->comm, func, vma->vm_start, vma->vm_end,
 				mask);
 		return -EINVAL;
@@ -204,13 +206,15 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 
 	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
 			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
-		dev_info(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, dax range requires MADV_DONTFORK\n",
 				current->comm, func);
 		return -EINVAL;
 	}
 
 	if (!vma_is_dax(vma)) {
-		dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, vma is not DAX capable\n",
 				current->comm, func);
 		return -EINVAL;
 	}
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 20bf90f4ee63..6c95f61a32e7 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -141,6 +141,7 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
 	if (signaled) {
 		RCU_INIT_POINTER(fobj->shared[signaled_idx], fence);
 	} else {
+		BUG_ON(fobj->shared_count >= fobj->shared_max);
 		RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
 		fobj->shared_count++;
 	}
@@ -230,10 +231,9 @@ void reservation_object_add_shared_fence(struct reservation_object *obj,
 	old = reservation_object_get_list(obj);
 	obj->staged = NULL;
 
-	if (!fobj) {
-		BUG_ON(old->shared_count >= old->shared_max);
+	if (!fobj)
 		reservation_object_add_shared_inplace(obj, old, fence);
-	} else
+	else
 		reservation_object_add_shared_replace(obj, old, fobj, fence);
 }
 EXPORT_SYMBOL(reservation_object_add_shared_fence);
diff --git a/drivers/dma/k3dma.c b/drivers/dma/k3dma.c
index fa31cccbe04f..6bfa217ed6d0 100644
--- a/drivers/dma/k3dma.c
+++ b/drivers/dma/k3dma.c
@@ -794,7 +794,7 @@ static struct dma_chan *k3_of_dma_simple_xlate(struct of_phandle_args *dma_spec,
 	struct k3_dma_dev *d = ofdma->of_dma_data;
 	unsigned int request = dma_spec->args[0];
 
-	if (request > d->dma_requests)
+	if (request >= d->dma_requests)
 		return NULL;
 
 	return dma_get_slave_channel(&(d->chans[request].vc.chan));
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index defcdde4d358..de0957fe9668 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -3033,7 +3033,7 @@ pl330_probe(struct amba_device *adev, const struct amba_id *id)
 	pd->src_addr_widths = PL330_DMA_BUSWIDTHS;
 	pd->dst_addr_widths = PL330_DMA_BUSWIDTHS;
 	pd->directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
-	pd->residue_granularity = DMA_RESIDUE_GRANULARITY_SEGMENT;
+	pd->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	pd->max_burst = ((pl330->quirks & PL330_QUIRK_BROKEN_NO_FLUSHP) ?
 			 1 : PL330_MAX_BURST);
 
diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
index 9b5ca8691f27..a4a931ddf6f6 100644
--- a/drivers/dma/ti/omap-dma.c
+++ b/drivers/dma/ti/omap-dma.c
@@ -1485,7 +1485,11 @@ static int omap_dma_probe(struct platform_device *pdev)
 	od->ddev.src_addr_widths = OMAP_DMA_BUSWIDTHS;
 	od->ddev.dst_addr_widths = OMAP_DMA_BUSWIDTHS;
 	od->ddev.directions = BIT(DMA_DEV_TO_MEM) | BIT(DMA_MEM_TO_DEV);
-	od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
+	if (__dma_omap15xx(od->plat->dma_attr))
+		od->ddev.residue_granularity =
+				DMA_RESIDUE_GRANULARITY_DESCRIPTOR;
+	else
+		od->ddev.residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;
 	od->ddev.max_burst = SZ_16M - 1; /* CCEN: 24bit unsigned */
 	od->ddev.dev = &pdev->dev;
 	INIT_LIST_HEAD(&od->ddev.channels);
diff --git a/drivers/fpga/altera-cvp.c b/drivers/fpga/altera-cvp.c
index dd4edd8f22ce..7fa793672a7a 100644
--- a/drivers/fpga/altera-cvp.c
+++ b/drivers/fpga/altera-cvp.c
@@ -455,8 +455,10 @@ static int altera_cvp_probe(struct pci_dev *pdev,
 
 	mgr = fpga_mgr_create(&pdev->dev, conf->mgr_name,
 			      &altera_cvp_ops, conf);
-	if (!mgr)
-		return -ENOMEM;
+	if (!mgr) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
 
 	pci_set_drvdata(pdev, mgr);
 
diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c
index d3cf9502e7e7..58faeb1cef63 100644
--- a/drivers/gpio/gpio-uniphier.c
+++ b/drivers/gpio/gpio-uniphier.c
@@ -181,7 +181,11 @@ static int uniphier_gpio_to_irq(struct gpio_chip *chip, unsigned int offset)
 	fwspec.fwnode = of_node_to_fwnode(chip->parent->of_node);
 	fwspec.param_count = 2;
 	fwspec.param[0] = offset - UNIPHIER_GPIO_IRQ_OFFSET;
-	fwspec.param[1] = IRQ_TYPE_NONE;
+	/*
+	 * IRQ_TYPE_NONE is rejected by the parent irq domain. Set LEVEL_HIGH
+	 * temporarily. Anyway, ->irq_set_type() will override it later.
+	 */
+	fwspec.param[1] = IRQ_TYPE_LEVEL_HIGH;
 
 	return irq_create_fwspec_mapping(&fwspec);
 }
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 28d968088131..53a14ee8ad6d 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -64,7 +64,8 @@ static void of_gpio_flags_quirks(struct device_node *np,
 	 * Note that active low is the default.
 	 */
 	if (IS_ENABLED(CONFIG_REGULATOR) &&
-	    (of_device_is_compatible(np, "reg-fixed-voltage") ||
+	    (of_device_is_compatible(np, "regulator-fixed") ||
+	     of_device_is_compatible(np, "reg-fixed-voltage") ||
 	     of_device_is_compatible(np, "regulator-gpio"))) {
 		/*
 		 * The regulator GPIO handles are specified such that the
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2a72d2feb76d..cb88528e7b10 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -122,6 +122,16 @@ config DRM_LOAD_EDID_FIRMWARE
 	  default case is N. Details and instructions how to build your own
 	  EDID data are given in Documentation/EDID/HOWTO.txt.
 
+config DRM_DP_CEC
+	bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support"
+	select CEC_CORE
+	help
+	  Choose this option if you want to enable HDMI CEC support for
+	  DisplayPort/USB-C to HDMI adapters.
+
+	  Note: not all adapters support this feature, and even for those
+	  that do support this they often do not hook up the CEC pin.
+
 config DRM_TTM
 	tristate
 	depends on DRM && MMU
@@ -213,6 +223,17 @@ config DRM_VGEM
 	  as used by Mesa's software renderer for enhanced performance.
 	  If M is selected the module will be called vgem.
 
+config DRM_VKMS
+	tristate "Virtual KMS (EXPERIMENTAL)"
+	depends on DRM
+	select DRM_KMS_HELPER
+	default n
+	help
+	  Virtual Kernel Mode-Setting (VKMS) is used for testing or for
+	  running GPU in a headless machines. Choose this option to get
+	  a VKMS.
+
+	  If M is selected the module will be called vkms.
 
 source "drivers/gpu/drm/exynos/Kconfig"
 
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 69c13517ea3a..a6771cef85e2 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -18,7 +18,7 @@ drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_encoder.o drm_mode_object.o drm_property.o \
 		drm_plane.o drm_color_mgmt.o drm_print.o \
 		drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \
-		drm_syncobj.o drm_lease.o drm_writeback.o
+		drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o
 
 drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
 drm-$(CONFIG_DRM_VM) += drm_vm.o
@@ -41,6 +41,7 @@ drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o
 drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o
 drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o
 drm_kms_helper-$(CONFIG_DRM_DP_AUX_CHARDEV) += drm_dp_aux_dev.o
+drm_kms_helper-$(CONFIG_DRM_DP_CEC) += drm_dp_cec.o
 
 obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o
 obj-$(CONFIG_DRM_DEBUG_SELFTEST) += selftests/
@@ -69,6 +70,7 @@ obj-$(CONFIG_DRM_SAVAGE)+= savage/
 obj-$(CONFIG_DRM_VMWGFX)+= vmwgfx/
 obj-$(CONFIG_DRM_VIA)	+=via/
 obj-$(CONFIG_DRM_VGEM)	+= vgem/
+obj-$(CONFIG_DRM_VKMS)	+= vkms/
 obj-$(CONFIG_DRM_NOUVEAU) +=nouveau/
 obj-$(CONFIG_DRM_EXYNOS) +=exynos/
 obj-$(CONFIG_DRM_ROCKCHIP) +=rockchip/
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 71b9b861f60e..0283e2b3c851 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -73,6 +73,7 @@
 #include "amdgpu_virt.h"
 #include "amdgpu_gart.h"
 #include "amdgpu_debugfs.h"
+#include "amdgpu_job.h"
 
 /*
  * Modules parameters.
@@ -105,11 +106,8 @@ extern int amdgpu_vm_fault_stop;
 extern int amdgpu_vm_debug;
 extern int amdgpu_vm_update_mode;
 extern int amdgpu_dc;
-extern int amdgpu_dc_log;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
-extern int amdgpu_no_evict;
-extern int amdgpu_direct_gma_size;
 extern uint amdgpu_pcie_gen_cap;
 extern uint amdgpu_pcie_lane_cap;
 extern uint amdgpu_cg_mask;
@@ -190,6 +188,7 @@ struct amdgpu_job;
 struct amdgpu_irq_src;
 struct amdgpu_fpriv;
 struct amdgpu_bo_va_mapping;
+struct amdgpu_atif;
 
 enum amdgpu_cp_irq {
 	AMDGPU_CP_IRQ_GFX_EOP = 0,
@@ -599,17 +598,6 @@ struct amdgpu_ib {
 
 extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
-int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
-		     struct amdgpu_job **job, struct amdgpu_vm *vm);
-int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
-			     struct amdgpu_job **job);
-
-void amdgpu_job_free_resources(struct amdgpu_job *job);
-void amdgpu_job_free(struct amdgpu_job *job);
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f);
-
 /*
  * Queue manager
  */
@@ -683,8 +671,8 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id);
 
 void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr);
-void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
+void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
 
@@ -731,6 +719,14 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 			     struct list_head *validated);
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
 void amdgpu_bo_list_free(struct amdgpu_bo_list *list);
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param);
+
+int amdgpu_bo_list_create(struct amdgpu_device *adev,
+				 struct drm_file *filp,
+				 struct drm_amdgpu_bo_list_entry *info,
+				 unsigned num_entries,
+				 struct amdgpu_bo_list **list);
 
 /*
  * GFX stuff
@@ -930,6 +926,11 @@ struct amdgpu_ngg {
 	bool			init;
 };
 
+struct sq_work {
+	struct work_struct	work;
+	unsigned ih_data;
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gfx_config	config;
@@ -970,6 +971,8 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_inst_irq;
 	struct amdgpu_irq_src		cp_ecc_error_irq;
 	struct amdgpu_irq_src		sq_irq;
+	struct sq_work			sq_work;
+
 	/* gfx status */
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
@@ -1021,6 +1024,7 @@ struct amdgpu_cs_parser {
 
 	/* scheduler job object */
 	struct amdgpu_job	*job;
+	struct amdgpu_ring	*ring;
 
 	/* buffer objects */
 	struct ww_acquire_ctx		ticket;
@@ -1042,40 +1046,6 @@ struct amdgpu_cs_parser {
 	struct drm_syncobj **post_dep_syncobjs;
 };
 
-#define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0) /* bit set means command submit involves a preamble IB */
-#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1) /* bit set means preamble IB is first presented in belonging context */
-#define AMDGPU_HAVE_CTX_SWITCH              (1 << 2) /* bit set means context switch occured */
-
-struct amdgpu_job {
-	struct drm_sched_job    base;
-	struct amdgpu_device	*adev;
-	struct amdgpu_vm	*vm;
-	struct amdgpu_ring	*ring;
-	struct amdgpu_sync	sync;
-	struct amdgpu_sync	sched_sync;
-	struct amdgpu_ib	*ibs;
-	struct dma_fence	*fence; /* the hw fence */
-	uint32_t		preamble_status;
-	uint32_t		num_ibs;
-	void			*owner;
-	uint64_t		fence_ctx; /* the fence_context this job uses */
-	bool                    vm_needs_flush;
-	uint64_t		vm_pd_addr;
-	unsigned		vmid;
-	unsigned		pasid;
-	uint32_t		gds_base, gds_size;
-	uint32_t		gws_base, gws_size;
-	uint32_t		oa_base, oa_size;
-	uint32_t		vram_lost_counter;
-
-	/* user fence handling */
-	uint64_t		uf_addr;
-	uint64_t		uf_sequence;
-
-};
-#define to_amdgpu_job(sched_job)		\
-		container_of((sched_job), struct amdgpu_job, base)
-
 static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
 				      uint32_t ib_idx, int idx)
 {
@@ -1271,43 +1241,6 @@ struct amdgpu_vram_scratch {
 /*
  * ACPI
  */
-struct amdgpu_atif_notification_cfg {
-	bool enabled;
-	int command_code;
-};
-
-struct amdgpu_atif_notifications {
-	bool display_switch;
-	bool expansion_mode_change;
-	bool thermal_state;
-	bool forced_power_state;
-	bool system_power_state;
-	bool display_conf_change;
-	bool px_gfx_switch;
-	bool brightness_change;
-	bool dgpu_display_event;
-};
-
-struct amdgpu_atif_functions {
-	bool system_params;
-	bool sbios_requests;
-	bool select_active_disp;
-	bool lid_state;
-	bool get_tv_standard;
-	bool set_tv_standard;
-	bool get_panel_expansion_mode;
-	bool set_panel_expansion_mode;
-	bool temperature_change;
-	bool graphics_device_types;
-};
-
-struct amdgpu_atif {
-	struct amdgpu_atif_notifications notifications;
-	struct amdgpu_atif_functions functions;
-	struct amdgpu_atif_notification_cfg notification_cfg;
-	struct amdgpu_encoder *encoder_for_bl;
-};
-
 struct amdgpu_atcs_functions {
 	bool get_ext_state;
 	bool pcie_perf_req;
@@ -1427,6 +1360,7 @@ enum amd_hw_ip_block_type {
 	PWR_HWIP,
 	NBIF_HWIP,
 	THM_HWIP,
+	CLK_HWIP,
 	MAX_HWIP
 };
 
@@ -1468,7 +1402,7 @@ struct amdgpu_device {
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 #endif
-	struct amdgpu_atif		atif;
+	struct amdgpu_atif		*atif;
 	struct amdgpu_atcs		atcs;
 	struct mutex			srbm_mutex;
 	/* GRBM index mutex. Protects concurrent access to GRBM index */
@@ -1617,9 +1551,9 @@ struct amdgpu_device {
 	DECLARE_HASHTABLE(mn_hash, 7);
 
 	/* tracking pinned memory */
-	u64 vram_pin_size;
-	u64 invisible_pin_size;
-	u64 gart_pin_size;
+	atomic64_t vram_pin_size;
+	atomic64_t visible_pin_size;
+	atomic64_t gart_pin_size;
 
 	/* amdkfd interface */
 	struct kfd_dev          *kfd;
@@ -1867,8 +1801,6 @@ void amdgpu_display_update_priority(struct amdgpu_device *adev);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
 				  u64 num_vis_bytes);
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
-bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 void amdgpu_device_vram_location(struct amdgpu_device *adev,
 				 struct amdgpu_gmc *mc, u64 base);
 void amdgpu_device_gart_location(struct amdgpu_device *adev,
@@ -1896,6 +1828,12 @@ static inline bool amdgpu_atpx_dgpu_req_power_for_displays(void) { return false;
 static inline bool amdgpu_has_atpx(void) { return false; }
 #endif
 
+#if defined(CONFIG_VGA_SWITCHEROO) && defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void);
+#else
+static inline void *amdgpu_atpx_get_dhandle(void) { return NULL; }
+#endif
+
 /*
  * KMS
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index f4c474a95875..71efcf38f11b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -57,6 +57,10 @@
 #define ACP_I2S_COMP2_CAP_REG_OFFSET		0xa8
 #define ACP_I2S_COMP1_PLAY_REG_OFFSET		0x6c
 #define ACP_I2S_COMP2_PLAY_REG_OFFSET		0x68
+#define ACP_BT_PLAY_REGS_START			0x14970
+#define ACP_BT_PLAY_REGS_END			0x14a24
+#define ACP_BT_COMP1_REG_OFFSET			0xac
+#define ACP_BT_COMP2_REG_OFFSET			0xa8
 
 #define mmACP_PGFSM_RETAIN_REG			0x51c9
 #define mmACP_PGFSM_CONFIG_REG			0x51ca
@@ -77,7 +81,7 @@
 #define ACP_SOFT_RESET_DONE_TIME_OUT_VALUE	0x000000FF
 
 #define ACP_TIMEOUT_LOOP			0x000000FF
-#define ACP_DEVS				3
+#define ACP_DEVS				4
 #define ACP_SRC_ID				162
 
 enum {
@@ -316,14 +320,13 @@ static int acp_hw_init(void *handle)
 	if (adev->acp.acp_cell == NULL)
 		return -ENOMEM;
 
-	adev->acp.acp_res = kcalloc(4, sizeof(struct resource), GFP_KERNEL);
-
+	adev->acp.acp_res = kcalloc(5, sizeof(struct resource), GFP_KERNEL);
 	if (adev->acp.acp_res == NULL) {
 		kfree(adev->acp.acp_cell);
 		return -ENOMEM;
 	}
 
-	i2s_pdata = kcalloc(2, sizeof(struct i2s_platform_data), GFP_KERNEL);
+	i2s_pdata = kcalloc(3, sizeof(struct i2s_platform_data), GFP_KERNEL);
 	if (i2s_pdata == NULL) {
 		kfree(adev->acp.acp_res);
 		kfree(adev->acp.acp_cell);
@@ -358,6 +361,20 @@ static int acp_hw_init(void *handle)
 	i2s_pdata[1].i2s_reg_comp1 = ACP_I2S_COMP1_CAP_REG_OFFSET;
 	i2s_pdata[1].i2s_reg_comp2 = ACP_I2S_COMP2_CAP_REG_OFFSET;
 
+	i2s_pdata[2].quirks = DW_I2S_QUIRK_COMP_REG_OFFSET;
+	switch (adev->asic_type) {
+	case CHIP_STONEY:
+		i2s_pdata[2].quirks |= DW_I2S_QUIRK_16BIT_IDX_OVERRIDE;
+		break;
+	default:
+		break;
+	}
+
+	i2s_pdata[2].cap = DWC_I2S_PLAY | DWC_I2S_RECORD;
+	i2s_pdata[2].snd_rates = SNDRV_PCM_RATE_8000_96000;
+	i2s_pdata[2].i2s_reg_comp1 = ACP_BT_COMP1_REG_OFFSET;
+	i2s_pdata[2].i2s_reg_comp2 = ACP_BT_COMP2_REG_OFFSET;
+
 	adev->acp.acp_res[0].name = "acp2x_dma";
 	adev->acp.acp_res[0].flags = IORESOURCE_MEM;
 	adev->acp.acp_res[0].start = acp_base;
@@ -373,13 +390,18 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_res[2].start = acp_base + ACP_I2S_CAP_REGS_START;
 	adev->acp.acp_res[2].end = acp_base + ACP_I2S_CAP_REGS_END;
 
-	adev->acp.acp_res[3].name = "acp2x_dma_irq";
-	adev->acp.acp_res[3].flags = IORESOURCE_IRQ;
-	adev->acp.acp_res[3].start = amdgpu_irq_create_mapping(adev, 162);
-	adev->acp.acp_res[3].end = adev->acp.acp_res[3].start;
+	adev->acp.acp_res[3].name = "acp2x_dw_bt_i2s_play_cap";
+	adev->acp.acp_res[3].flags = IORESOURCE_MEM;
+	adev->acp.acp_res[3].start = acp_base + ACP_BT_PLAY_REGS_START;
+	adev->acp.acp_res[3].end = acp_base + ACP_BT_PLAY_REGS_END;
+
+	adev->acp.acp_res[4].name = "acp2x_dma_irq";
+	adev->acp.acp_res[4].flags = IORESOURCE_IRQ;
+	adev->acp.acp_res[4].start = amdgpu_irq_create_mapping(adev, 162);
+	adev->acp.acp_res[4].end = adev->acp.acp_res[4].start;
 
 	adev->acp.acp_cell[0].name = "acp_audio_dma";
-	adev->acp.acp_cell[0].num_resources = 4;
+	adev->acp.acp_cell[0].num_resources = 5;
 	adev->acp.acp_cell[0].resources = &adev->acp.acp_res[0];
 	adev->acp.acp_cell[0].platform_data = &adev->asic_type;
 	adev->acp.acp_cell[0].pdata_size = sizeof(adev->asic_type);
@@ -396,6 +418,12 @@ static int acp_hw_init(void *handle)
 	adev->acp.acp_cell[2].platform_data = &i2s_pdata[1];
 	adev->acp.acp_cell[2].pdata_size = sizeof(struct i2s_platform_data);
 
+	adev->acp.acp_cell[3].name = "designware-i2s";
+	adev->acp.acp_cell[3].num_resources = 1;
+	adev->acp.acp_cell[3].resources = &adev->acp.acp_res[3];
+	adev->acp.acp_cell[3].platform_data = &i2s_pdata[2];
+	adev->acp.acp_cell[3].pdata_size = sizeof(struct i2s_platform_data);
+
 	r = mfd_add_hotplug_devices(adev->acp.parent, adev->acp.acp_cell,
 								ACP_DEVS);
 	if (r)
@@ -451,7 +479,6 @@ static int acp_hw_init(void *handle)
 	val = cgs_read_register(adev->acp.cgs_device, mmACP_SOFT_RESET);
 	val &= ~ACP_SOFT_RESET__SoftResetAud_MASK;
 	cgs_write_register(adev->acp.cgs_device, mmACP_SOFT_RESET, val);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 8fa850a070e0..353993218f21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -34,6 +34,45 @@
 #include "amd_acpi.h"
 #include "atom.h"
 
+struct amdgpu_atif_notification_cfg {
+	bool enabled;
+	int command_code;
+};
+
+struct amdgpu_atif_notifications {
+	bool display_switch;
+	bool expansion_mode_change;
+	bool thermal_state;
+	bool forced_power_state;
+	bool system_power_state;
+	bool display_conf_change;
+	bool px_gfx_switch;
+	bool brightness_change;
+	bool dgpu_display_event;
+};
+
+struct amdgpu_atif_functions {
+	bool system_params;
+	bool sbios_requests;
+	bool select_active_disp;
+	bool lid_state;
+	bool get_tv_standard;
+	bool set_tv_standard;
+	bool get_panel_expansion_mode;
+	bool set_panel_expansion_mode;
+	bool temperature_change;
+	bool graphics_device_types;
+};
+
+struct amdgpu_atif {
+	acpi_handle handle;
+
+	struct amdgpu_atif_notifications notifications;
+	struct amdgpu_atif_functions functions;
+	struct amdgpu_atif_notification_cfg notification_cfg;
+	struct amdgpu_encoder *encoder_for_bl;
+};
+
 /* Call the ATIF method
  */
 /**
@@ -46,8 +85,9 @@
  * Executes the requested ATIF function (all asics).
  * Returns a pointer to the acpi output buffer.
  */
-static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
-		struct acpi_buffer *params)
+static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
+					   int function,
+					   struct acpi_buffer *params)
 {
 	acpi_status status;
 	union acpi_object atif_arg_elements[2];
@@ -70,7 +110,8 @@ static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
 		atif_arg_elements[1].integer.value = 0;
 	}
 
-	status = acpi_evaluate_object(handle, "ATIF", &atif_arg, &buffer);
+	status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
+				      &buffer);
 
 	/* Fail only if calling the method fails and ATIF is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
@@ -141,15 +182,14 @@ static void amdgpu_atif_parse_functions(struct amdgpu_atif_functions *f, u32 mas
  * (all asics).
  * returns 0 on success, error on failure.
  */
-static int amdgpu_atif_verify_interface(acpi_handle handle,
-		struct amdgpu_atif *atif)
+static int amdgpu_atif_verify_interface(struct amdgpu_atif *atif)
 {
 	union acpi_object *info;
 	struct atif_verify_interface output;
 	size_t size;
 	int err = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
 	if (!info)
 		return -EIO;
 
@@ -176,6 +216,35 @@ out:
 	return err;
 }
 
+static acpi_handle amdgpu_atif_probe_handle(acpi_handle dhandle)
+{
+	acpi_handle handle = NULL;
+	char acpi_method_name[255] = { 0 };
+	struct acpi_buffer buffer = { sizeof(acpi_method_name), acpi_method_name };
+	acpi_status status;
+
+	/* For PX/HG systems, ATIF and ATPX are in the iGPU's namespace, on dGPU only
+	 * systems, ATIF is in the dGPU's namespace.
+	 */
+	status = acpi_get_handle(dhandle, "ATIF", &handle);
+	if (ACPI_SUCCESS(status))
+		goto out;
+
+	if (amdgpu_has_atpx()) {
+		status = acpi_get_handle(amdgpu_atpx_get_dhandle(), "ATIF",
+					 &handle);
+		if (ACPI_SUCCESS(status))
+			goto out;
+	}
+
+	DRM_DEBUG_DRIVER("No ATIF handle found\n");
+	return NULL;
+out:
+	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+	DRM_DEBUG_DRIVER("Found ATIF handle %s\n", acpi_method_name);
+	return handle;
+}
+
 /**
  * amdgpu_atif_get_notification_params - determine notify configuration
  *
@@ -188,15 +257,16 @@ out:
  * where n is specified in the result if a notifier is used.
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_atif_get_notification_params(acpi_handle handle,
-		struct amdgpu_atif_notification_cfg *n)
+static int amdgpu_atif_get_notification_params(struct amdgpu_atif *atif)
 {
 	union acpi_object *info;
+	struct amdgpu_atif_notification_cfg *n = &atif->notification_cfg;
 	struct atif_system_params params;
 	size_t size;
 	int err = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS,
+				NULL);
 	if (!info) {
 		err = -EIO;
 		goto out;
@@ -250,14 +320,15 @@ out:
  * (all asics).
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_atif_get_sbios_requests(acpi_handle handle,
-		struct atif_sbios_requests *req)
+static int amdgpu_atif_get_sbios_requests(struct amdgpu_atif *atif,
+					  struct atif_sbios_requests *req)
 {
 	union acpi_object *info;
 	size_t size;
 	int count = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS,
+				NULL);
 	if (!info)
 		return -EIO;
 
@@ -290,11 +361,9 @@ out:
  * Returns NOTIFY code
  */
 static int amdgpu_atif_handler(struct amdgpu_device *adev,
-			struct acpi_bus_event *event)
+			       struct acpi_bus_event *event)
 {
-	struct amdgpu_atif *atif = &adev->atif;
-	struct atif_sbios_requests req;
-	acpi_handle handle;
+	struct amdgpu_atif *atif = adev->atif;
 	int count;
 
 	DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
@@ -303,48 +372,54 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
 		return NOTIFY_DONE;
 
-	if (!atif->notification_cfg.enabled ||
+	if (!atif ||
+	    !atif->notification_cfg.enabled ||
 	    event->type != atif->notification_cfg.command_code)
 		/* Not our event */
 		return NOTIFY_DONE;
 
-	/* Check pending SBIOS requests */
-	handle = ACPI_HANDLE(&adev->pdev->dev);
-	count = amdgpu_atif_get_sbios_requests(handle, &req);
+	if (atif->functions.sbios_requests) {
+		struct atif_sbios_requests req;
 
-	if (count <= 0)
-		return NOTIFY_DONE;
+		/* Check pending SBIOS requests */
+		count = amdgpu_atif_get_sbios_requests(atif, &req);
 
-	DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
+		if (count <= 0)
+			return NOTIFY_DONE;
 
-	if (req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) {
-		struct amdgpu_encoder *enc = atif->encoder_for_bl;
+		DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
 
-		if (enc) {
-			struct amdgpu_encoder_atom_dig *dig = enc->enc_priv;
+		/* todo: add DC handling */
+		if ((req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) &&
+		    !amdgpu_device_has_dc_support(adev)) {
+			struct amdgpu_encoder *enc = atif->encoder_for_bl;
 
-			DRM_DEBUG_DRIVER("Changing brightness to %d\n",
-					req.backlight_level);
+			if (enc) {
+				struct amdgpu_encoder_atom_dig *dig = enc->enc_priv;
+
+				DRM_DEBUG_DRIVER("Changing brightness to %d\n",
+						 req.backlight_level);
 
-			amdgpu_display_backlight_set_level(adev, enc, req.backlight_level);
+				amdgpu_display_backlight_set_level(adev, enc, req.backlight_level);
 
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
-			backlight_force_update(dig->bl_dev,
-					       BACKLIGHT_UPDATE_HOTKEY);
+				backlight_force_update(dig->bl_dev,
+						       BACKLIGHT_UPDATE_HOTKEY);
 #endif
+			}
 		}
-	}
-	if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
-		if ((adev->flags & AMD_IS_PX) &&
-		    amdgpu_atpx_dgpu_req_power_for_displays()) {
-			pm_runtime_get_sync(adev->ddev->dev);
-			/* Just fire off a uevent and let userspace tell us what to do */
-			drm_helper_hpd_irq_event(adev->ddev);
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+		if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
+			if ((adev->flags & AMD_IS_PX) &&
+			    amdgpu_atpx_dgpu_req_power_for_displays()) {
+				pm_runtime_get_sync(adev->ddev->dev);
+				/* Just fire off a uevent and let userspace tell us what to do */
+				drm_helper_hpd_irq_event(adev->ddev);
+				pm_runtime_mark_last_busy(adev->ddev->dev);
+				pm_runtime_put_autosuspend(adev->ddev->dev);
+			}
 		}
+		/* TODO: check other events */
 	}
-	/* TODO: check other events */
 
 	/* We've handled the event, stop the notifier chain. The ACPI interface
 	 * overloads ACPI_VIDEO_NOTIFY_PROBE, we don't want to send that to
@@ -641,8 +716,8 @@ static int amdgpu_acpi_event(struct notifier_block *nb,
  */
 int amdgpu_acpi_init(struct amdgpu_device *adev)
 {
-	acpi_handle handle;
-	struct amdgpu_atif *atif = &adev->atif;
+	acpi_handle handle, atif_handle;
+	struct amdgpu_atif *atif;
 	struct amdgpu_atcs *atcs = &adev->atcs;
 	int ret;
 
@@ -658,12 +733,26 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 		DRM_DEBUG_DRIVER("Call to ATCS verify_interface failed: %d\n", ret);
 	}
 
+	/* Probe for ATIF, and initialize it if found */
+	atif_handle = amdgpu_atif_probe_handle(handle);
+	if (!atif_handle)
+		goto out;
+
+	atif = kzalloc(sizeof(*atif), GFP_KERNEL);
+	if (!atif) {
+		DRM_WARN("Not enough memory to initialize ATIF\n");
+		goto out;
+	}
+	atif->handle = atif_handle;
+
 	/* Call the ATIF method */
-	ret = amdgpu_atif_verify_interface(handle, atif);
+	ret = amdgpu_atif_verify_interface(atif);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Call to ATIF verify_interface failed: %d\n", ret);
+		kfree(atif);
 		goto out;
 	}
+	adev->atif = atif;
 
 	if (atif->notifications.brightness_change) {
 		struct drm_encoder *tmp;
@@ -693,8 +782,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 	}
 
 	if (atif->functions.system_params) {
-		ret = amdgpu_atif_get_notification_params(handle,
-				&atif->notification_cfg);
+		ret = amdgpu_atif_get_notification_params(atif);
 		if (ret) {
 			DRM_DEBUG_DRIVER("Call to GET_SYSTEM_PARAMS failed: %d\n",
 					ret);
@@ -720,4 +808,6 @@ out:
 void amdgpu_acpi_fini(struct amdgpu_device *adev)
 {
 	unregister_acpi_notifier(&adev->acpi_nb);
+	if (adev->atif)
+		kfree(adev->atif);
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 305143fcc1ce..f8bbbb3a9504 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -243,6 +243,33 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 	return r;
 }
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->pre_reset(adev->kfd);
+
+	return r;
+}
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->post_reset(adev->kfd);
+
+	return r;
+}
+
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_device_gpu_recover(adev, NULL, false);
+}
+
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
@@ -251,7 +278,6 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	struct amdgpu_bo *bo = NULL;
 	struct amdgpu_bo_param bp;
 	int r;
-	uint64_t gpu_addr_tmp = 0;
 	void *cpu_ptr_tmp = NULL;
 
 	memset(&bp, 0, sizeof(bp));
@@ -275,13 +301,18 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 		goto allocate_mem_reserve_bo_failed;
 	}
 
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT,
-				&gpu_addr_tmp);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to pin bo for amdkfd\n", r);
 		goto allocate_mem_pin_bo_failed;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&bo->tbo);
+	if (r) {
+		dev_err(adev->dev, "%p bind failed\n", bo);
+		goto allocate_mem_kmap_bo_failed;
+	}
+
 	r = amdgpu_bo_kmap(bo, &cpu_ptr_tmp);
 	if (r) {
 		dev_err(adev->dev,
@@ -290,7 +321,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	}
 
 	*mem_obj = bo;
-	*gpu_addr = gpu_addr_tmp;
+	*gpu_addr = amdgpu_bo_gpu_offset(bo);
 	*cpu_ptr = cpu_ptr_tmp;
 
 	amdgpu_bo_unreserve(bo);
@@ -457,6 +488,14 @@ err:
 	return ret;
 }
 
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_dpm_switch_power_profile(adev,
+					PP_SMC_POWER_PROFILE_COMPUTE, !idle);
+}
+
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 {
 	if (adev->kfd) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index a8418a3f4e9d..2f379c183ed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -119,6 +119,7 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len);
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
@@ -126,6 +127,12 @@ struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
+
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);
+
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
@@ -183,6 +190,9 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence **ef);
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *info);
+
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo);
 
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 ea79908dac4c..ea3f698aef5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -145,6 +145,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t page_table_base);
 static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
 static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd);
 
 /* Because of REG_GET_FIELD() being used, we put this function in the
  * asic specific file.
@@ -216,6 +217,10 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
@@ -571,6 +576,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	unsigned long flags, end_jiffies;
 	int retry;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, 0);
 
@@ -882,6 +890,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	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;
@@ -911,3 +922,19 @@ static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
 	RREG32(mmVM_INVALIDATE_RESPONSE);
 	return 0;
 }
+
+ /**
+  * read_vmid_from_vmfault_reg - read vmid from register
+  *
+  * adev: amdgpu_device pointer
+  * @vmid: vmid pointer
+  * read vmid from register (CIK).
+  */
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
+
+	return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID);
+}
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 19dd665e7307..f6e53e9352bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -176,6 +176,9 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
@@ -568,6 +571,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	int retry;
 	struct vi_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
@@ -844,6 +850,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	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;
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 1db60aa5b7f0..8efedfcb9dfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -213,6 +213,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
@@ -679,6 +681,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
@@ -866,6 +871,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	if (ring->ready)
 		return invalidate_tlbs_with_kiq(adev, pasid);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index ff8fd75f7ca5..8a707d8bbb1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -334,7 +334,7 @@ static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
 		 "Called with userptr BO"))
 		return -EINVAL;
 
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
@@ -622,7 +622,7 @@ static int init_user_pages(struct kgd_mem *mem, struct mm_struct *mm,
 		pr_err("%s: Failed to reserve BO\n", __func__);
 		goto release_out;
 	}
-	amdgpu_ttm_placement_from_domain(bo, mem->domain);
+	amdgpu_bo_placement_from_domain(bo, mem->domain);
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
 		pr_err("%s: failed to validate BO\n", __func__);
@@ -1587,7 +1587,7 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 		goto bo_reserve_failed;
 	}
 
-	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (ret) {
 		pr_err("Failed to pin bo. ret %d\n", ret);
 		goto pin_failed;
@@ -1621,6 +1621,20 @@ bo_reserve_failed:
 	return ret;
 }
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *mem)
+{
+	struct amdgpu_device *adev;
+
+	adev = (struct amdgpu_device *)kgd;
+	if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) {
+		*mem = *adev->gmc.vm_fault_info;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+	}
+	return 0;
+}
+
 /* Evict a userptr BO by stopping the queues if necessary
  *
  * Runs in MMU notifier, may be in RECLAIM_FS context. This means it
@@ -1680,7 +1694,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 
 		if (amdgpu_bo_reserve(bo, true))
 			return -EAGAIN;
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
 		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (ret) {
@@ -1824,7 +1838,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 		if (mem->user_pages[0]) {
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
 						     mem->user_pages);
-			amdgpu_ttm_placement_from_domain(bo, mem->domain);
+			amdgpu_bo_placement_from_domain(bo, mem->domain);
 			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (ret) {
 				pr_err("%s: failed to validate BO\n", __func__);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index daa06e7c5bb7..a028661d9e20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -32,7 +32,7 @@ struct amdgpu_atpx_functions {
 	bool switch_start;
 	bool switch_end;
 	bool disp_connectors_mapping;
-	bool disp_detetion_ports;
+	bool disp_detection_ports;
 };
 
 struct amdgpu_atpx {
@@ -90,6 +90,12 @@ bool amdgpu_atpx_dgpu_req_power_for_displays(void) {
 	return amdgpu_atpx_priv.atpx.dgpu_req_power_for_displays;
 }
 
+#if defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void) {
+	return amdgpu_atpx_priv.dhandle;
+}
+#endif
+
 /**
  * amdgpu_atpx_call - call an ATPX method
  *
@@ -156,7 +162,7 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas
 	f->switch_start = mask & ATPX_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION_SUPPORTED;
 	f->switch_end = mask & ATPX_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION_SUPPORTED;
 	f->disp_connectors_mapping = mask & ATPX_GET_DISPLAY_CONNECTORS_MAPPING_SUPPORTED;
-	f->disp_detetion_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
+	f->disp_detection_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
 }
 
 /**
@@ -569,6 +575,7 @@ static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = {
 	{ 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX },
+	{ 0x1002, 0x6900, 0x1025, 0x125A, AMDGPU_PX_QUIRK_FORCE_ATPX },
 	{ 0, 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 19cfff31f2e1..3079ea8523c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -95,11 +95,17 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	r = amdgpu_bo_reserve(sobj, false);
 	if (unlikely(r != 0))
 		goto out_cleanup;
-	r = amdgpu_bo_pin(sobj, sdomain, &saddr);
+	r = amdgpu_bo_pin(sobj, sdomain);
+	if (r) {
+		amdgpu_bo_unreserve(sobj);
+		goto out_cleanup;
+	}
+	r = amdgpu_ttm_alloc_gart(&sobj->tbo);
 	amdgpu_bo_unreserve(sobj);
 	if (r) {
 		goto out_cleanup;
 	}
+	saddr = amdgpu_bo_gpu_offset(sobj);
 	bp.domain = ddomain;
 	r = amdgpu_bo_create(adev, &bp, &dobj);
 	if (r) {
@@ -108,11 +114,17 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	r = amdgpu_bo_reserve(dobj, false);
 	if (unlikely(r != 0))
 		goto out_cleanup;
-	r = amdgpu_bo_pin(dobj, ddomain, &daddr);
+	r = amdgpu_bo_pin(dobj, ddomain);
+	if (r) {
+		amdgpu_bo_unreserve(sobj);
+		goto out_cleanup;
+	}
+	r = amdgpu_ttm_alloc_gart(&dobj->tbo);
 	amdgpu_bo_unreserve(dobj);
 	if (r) {
 		goto out_cleanup;
 	}
+	daddr = amdgpu_bo_gpu_offset(dobj);
 
 	if (adev->mman.buffer_funcs) {
 		time = amdgpu_benchmark_do_move(adev, size, saddr, daddr, n);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 92be7f6de197..7679c068c89a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -55,15 +55,15 @@ static void amdgpu_bo_list_release_rcu(struct kref *ref)
 	kfree_rcu(list, rhead);
 }
 
-static int amdgpu_bo_list_create(struct amdgpu_device *adev,
+int amdgpu_bo_list_create(struct amdgpu_device *adev,
 				 struct drm_file *filp,
 				 struct drm_amdgpu_bo_list_entry *info,
 				 unsigned num_entries,
-				 int *id)
+				 struct amdgpu_bo_list **list_out)
 {
-	int r;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_bo_list *list;
+	int r;
+
 
 	list = kzalloc(sizeof(struct amdgpu_bo_list), GFP_KERNEL);
 	if (!list)
@@ -78,16 +78,7 @@ static int amdgpu_bo_list_create(struct amdgpu_device *adev,
 		return r;
 	}
 
-	/* idr alloc should be called only after initialization of bo list. */
-	mutex_lock(&fpriv->bo_list_lock);
-	r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
-	mutex_unlock(&fpriv->bo_list_lock);
-	if (r < 0) {
-		amdgpu_bo_list_free(list);
-		return r;
-	}
-	*id = r;
-
+	*list_out = list;
 	return 0;
 }
 
@@ -263,55 +254,79 @@ void amdgpu_bo_list_free(struct amdgpu_bo_list *list)
 	kfree(list);
 }
 
-int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *filp)
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param)
 {
+	const void __user *uptr = u64_to_user_ptr(in->bo_info_ptr);
 	const uint32_t info_size = sizeof(struct drm_amdgpu_bo_list_entry);
-
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	union drm_amdgpu_bo_list *args = data;
-	uint32_t handle = args->in.list_handle;
-	const void __user *uptr = u64_to_user_ptr(args->in.bo_info_ptr);
-
 	struct drm_amdgpu_bo_list_entry *info;
-	struct amdgpu_bo_list *list;
-
 	int r;
 
-	info = kvmalloc_array(args->in.bo_number,
-			     sizeof(struct drm_amdgpu_bo_list_entry), GFP_KERNEL);
+	info = kvmalloc_array(in->bo_number, info_size, GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
 	/* copy the handle array from userspace to a kernel buffer */
 	r = -EFAULT;
-	if (likely(info_size == args->in.bo_info_size)) {
-		unsigned long bytes = args->in.bo_number *
-			args->in.bo_info_size;
+	if (likely(info_size == in->bo_info_size)) {
+		unsigned long bytes = in->bo_number *
+			in->bo_info_size;
 
 		if (copy_from_user(info, uptr, bytes))
 			goto error_free;
 
 	} else {
-		unsigned long bytes = min(args->in.bo_info_size, info_size);
+		unsigned long bytes = min(in->bo_info_size, info_size);
 		unsigned i;
 
-		memset(info, 0, args->in.bo_number * info_size);
-		for (i = 0; i < args->in.bo_number; ++i) {
+		memset(info, 0, in->bo_number * info_size);
+		for (i = 0; i < in->bo_number; ++i) {
 			if (copy_from_user(&info[i], uptr, bytes))
 				goto error_free;
 
-			uptr += args->in.bo_info_size;
+			uptr += in->bo_info_size;
 		}
 	}
 
+	*info_param = info;
+	return 0;
+
+error_free:
+	kvfree(info);
+	return r;
+}
+
+int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *filp)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	union drm_amdgpu_bo_list *args = data;
+	uint32_t handle = args->in.list_handle;
+	struct drm_amdgpu_bo_list_entry *info = NULL;
+	struct amdgpu_bo_list *list;
+	int r;
+
+	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
+	if (r)
+		goto error_free;
+
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
 		r = amdgpu_bo_list_create(adev, filp, info, args->in.bo_number,
-					  &handle);
+					  &list);
 		if (r)
 			goto error_free;
+
+		mutex_lock(&fpriv->bo_list_lock);
+		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
+		mutex_unlock(&fpriv->bo_list_lock);
+		if (r < 0) {
+			amdgpu_bo_list_free(list);
+			return r;
+		}
+
+		handle = r;
 		break;
 
 	case AMDGPU_BO_LIST_OP_DESTROY:
@@ -345,6 +360,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 	return 0;
 
 error_free:
-	kvfree(info);
+	if (info)
+		kvfree(info);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index e950730f1933..693ec5ea4950 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -314,17 +314,17 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 					(adev->pdev->revision == 0x81) ||
 					(adev->pdev->device == 0x665f)) {
 					info->is_kicker = true;
-					strcpy(fw_name, "radeon/bonaire_k_smc.bin");
+					strcpy(fw_name, "amdgpu/bonaire_k_smc.bin");
 				} else {
-					strcpy(fw_name, "radeon/bonaire_smc.bin");
+					strcpy(fw_name, "amdgpu/bonaire_smc.bin");
 				}
 				break;
 			case CHIP_HAWAII:
 				if (adev->pdev->revision == 0x80) {
 					info->is_kicker = true;
-					strcpy(fw_name, "radeon/hawaii_k_smc.bin");
+					strcpy(fw_name, "amdgpu/hawaii_k_smc.bin");
 				} else {
-					strcpy(fw_name, "radeon/hawaii_smc.bin");
+					strcpy(fw_name, "amdgpu/hawaii_smc.bin");
 				}
 				break;
 			case CHIP_TOPAZ:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 8e66851eb427..c770d73352a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -212,30 +212,21 @@ static void
 amdgpu_connector_update_scratch_regs(struct drm_connector *connector,
 				      enum drm_connector_status status)
 {
-	struct drm_encoder *best_encoder = NULL;
-	struct drm_encoder *encoder = NULL;
+	struct drm_encoder *best_encoder;
+	struct drm_encoder *encoder;
 	const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private;
 	bool connected;
 	int i;
 
 	best_encoder = connector_funcs->best_encoder(connector);
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if ((encoder == best_encoder) && (status == connector_status_connected))
 			connected = true;
 		else
 			connected = false;
 
 		amdgpu_atombios_encoder_set_bios_scratch_regs(connector, encoder, connected);
-
 	}
 }
 
@@ -246,17 +237,11 @@ amdgpu_connector_find_encoder(struct drm_connector *connector,
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == encoder_type)
 			return encoder;
 	}
+
 	return NULL;
 }
 
@@ -349,22 +334,24 @@ static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (amdgpu_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, amdgpu_connector->edid);
+		drm_connector_update_edid_property(connector, amdgpu_connector->edid);
 		ret = drm_add_edid_modes(connector, amdgpu_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(connector, NULL);
+	drm_connector_update_edid_property(connector, NULL);
 	return 0;
 }
 
 static struct drm_encoder *
 amdgpu_connector_best_single_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
+	struct drm_encoder *encoder;
+	int i;
+
+	/* pick the first one */
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
 
-	/* pick the encoder ids */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
 	return NULL;
 }
 
@@ -985,9 +972,8 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
-	struct drm_encoder *encoder = NULL;
 	const struct drm_encoder_helper_funcs *encoder_funcs;
-	int i, r;
+	int r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
@@ -1077,14 +1063,10 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 
 	/* find analog encoder */
 	if (amdgpu_connector->dac_load_detect) {
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == 0)
-				break;
-
-			encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-			if (!encoder)
-				continue;
+		struct drm_encoder *encoder;
+		int i;
 
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
 			if (encoder->encoder_type != DRM_MODE_ENCODER_DAC &&
 			    encoder->encoder_type != DRM_MODE_ENCODER_TVDAC)
 				continue;
@@ -1132,18 +1114,11 @@ exit:
 static struct drm_encoder *
 amdgpu_connector_dvi_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct drm_encoder *encoder;
 	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
 
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (amdgpu_connector->use_digital == true) {
 			if (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)
 				return encoder;
@@ -1158,8 +1133,9 @@ amdgpu_connector_dvi_encoder(struct drm_connector *connector)
 
 	/* then check use digitial */
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -1296,15 +1272,7 @@ u16 amdgpu_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
 	struct amdgpu_encoder *amdgpu_encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 
 		switch (amdgpu_encoder->encoder_id) {
@@ -1326,14 +1294,7 @@ static bool amdgpu_connector_encoder_is_hbr2(struct drm_connector *connector)
 	int i;
 	bool found = false;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 		if (amdgpu_encoder->caps & ATOM_ENCODER_CAP_RECORD_HBR2)
 			found = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 7a625f3989a0..178d9ce4eba1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -66,11 +66,35 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 	return 0;
 }
 
-static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
+static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p,
+				      struct drm_amdgpu_bo_list_in *data)
+{
+	int r;
+	struct drm_amdgpu_bo_list_entry *info = NULL;
+
+	r = amdgpu_bo_create_list_entry_array(data, &info);
+	if (r)
+		return r;
+
+	r = amdgpu_bo_list_create(p->adev, p->filp, info, data->bo_number,
+				  &p->bo_list);
+	if (r)
+		goto error_free;
+
+	kvfree(info);
+	return 0;
+
+error_free:
+	if (info)
+		kvfree(info);
+
+	return r;
+}
+
+static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
-	union drm_amdgpu_cs *cs = data;
 	uint64_t *chunk_array_user;
 	uint64_t *chunk_array;
 	unsigned size, num_ibs = 0;
@@ -164,6 +188,19 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 
 			break;
 
+		case AMDGPU_CHUNK_ID_BO_HANDLES:
+			size = sizeof(struct drm_amdgpu_bo_list_in);
+			if (p->chunks[i].length_dw * sizeof(uint32_t) < size) {
+				ret = -EINVAL;
+				goto free_partial_kdata;
+			}
+
+			ret = amdgpu_cs_bo_handles_chunk(p, p->chunks[i].kdata);
+			if (ret)
+				goto free_partial_kdata;
+
+			break;
+
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
@@ -187,6 +224,10 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 	if (p->uf_entry.robj)
 		p->job->uf_addr = uf_offset;
 	kfree(chunk_array);
+
+	/* Use this opportunity to fill in task info for the vm */
+	amdgpu_vm_set_task_info(vm);
+
 	return 0;
 
 free_all_kdata:
@@ -258,7 +299,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 		return;
 	}
 
-	total_vram = adev->gmc.real_vram_size - adev->vram_pin_size;
+	total_vram = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size);
 	used_vram = amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 	free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram;
 
@@ -378,7 +419,7 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	}
 
 retry:
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 
 	p->bytes_moved += ctx.bytes_moved;
@@ -437,7 +478,7 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 		update_bytes_moved_vis =
 				!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 				amdgpu_bo_in_cpu_visible_vram(bo);
-		amdgpu_ttm_placement_from_domain(bo, other);
+		amdgpu_bo_placement_from_domain(bo, other);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		p->bytes_moved += ctx.bytes_moved;
 		if (update_bytes_moved_vis)
@@ -491,8 +532,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		/* Check if we have user pages and nobody bound the BO already */
 		if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm) &&
 		    lobj->user_pages) {
-			amdgpu_ttm_placement_from_domain(bo,
-							 AMDGPU_GEM_DOMAIN_CPU);
+			amdgpu_bo_placement_from_domain(bo,
+							AMDGPU_GEM_DOMAIN_CPU);
 			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (r)
 				return r;
@@ -530,7 +571,12 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	INIT_LIST_HEAD(&p->validated);
 
-	p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
+	/* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */
+	if (!p->bo_list)
+		p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
+	else
+		mutex_lock(&p->bo_list->lock);
+
 	if (p->bo_list) {
 		amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 		if (p->bo_list->first_userptr != p->bo_list->num_entries)
@@ -866,11 +912,11 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_ring *ring = p->ring;
 	int r;
 
 	/* Only for UVD/VCE VM emulation */
-	if (p->job->ring->funcs->parse_cs) {
+	if (p->ring->funcs->parse_cs) {
 		unsigned i, j;
 
 		for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) {
@@ -928,6 +974,10 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 		r = amdgpu_bo_vm_update_pte(p);
 		if (r)
 			return r;
+
+		r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv);
+		if (r)
+			return r;
 	}
 
 	return amdgpu_cs_sync_rings(p);
@@ -980,10 +1030,10 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 			}
 		}
 
-		if (parser->job->ring && parser->job->ring != ring)
+		if (parser->ring && parser->ring != ring)
 			return -EINVAL;
 
-		parser->job->ring = ring;
+		parser->ring = ring;
 
 		r =  amdgpu_ib_get(adev, vm,
 					ring->funcs->parse_cs ? chunk_ib->ib_bytes : 0,
@@ -1002,11 +1052,11 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 
 	/* UVD & VCE fw doesn't support user fences */
 	if (parser->job->uf_addr && (
-	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
-	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
+	    parser->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
+	    parser->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
 		return -EINVAL;
 
-	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->job->ring->idx);
+	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->ring->idx);
 }
 
 static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
@@ -1157,8 +1207,9 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
-	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_ring *ring = p->ring;
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
+	enum drm_sched_priority priority;
 	struct amdgpu_job *job;
 	unsigned i;
 	uint64_t seq;
@@ -1181,7 +1232,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job = p->job;
 	p->job = NULL;
 
-	r = drm_sched_job_init(&job->base, &ring->sched, entity, p->filp);
+	r = drm_sched_job_init(&job->base, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		amdgpu_mn_unlock(p->mn);
@@ -1189,7 +1240,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	}
 
 	job->owner = p->filp;
-	job->fence_ctx = entity->fence_context;
 	p->fence = dma_fence_get(&job->base.s_fence->finished);
 
 	r = amdgpu_ctx_add_fence(p->ctx, ring, p->fence, &seq);
@@ -1207,11 +1257,14 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job->uf_sequence = seq;
 
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
 
 	trace_amdgpu_cs_ioctl(job);
+	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
+	ring = to_amdgpu_ring(entity->rq->sched);
+	amdgpu_ring_priority_get(ring, priority);
+
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	amdgpu_mn_unlock(p->mn);
 
@@ -1602,7 +1655,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 
 	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
 		(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
-		amdgpu_ttm_placement_from_domain(*bo, (*bo)->allowed_domains);
+		amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
 		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
 		if (r)
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 64b3a1ed04dc..df6965761046 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -90,8 +90,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 		if (ring == &adev->gfx.kiq.ring)
 			continue;
 
-		r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
-					  rq, &ctx->guilty);
+		r = drm_sched_entity_init(&ctx->rings[i].entity,
+					  &rq, 1, &ctx->guilty);
 		if (r)
 			goto failed;
 	}
@@ -104,8 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 
 failed:
 	for (j = 0; j < i; j++)
-		drm_sched_entity_fini(&adev->rings[j]->sched,
-				      &ctx->rings[j].entity);
+		drm_sched_entity_destroy(&ctx->rings[j].entity);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
 	return r;
@@ -178,8 +177,7 @@ static void amdgpu_ctx_do_release(struct kref *ref)
 		if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 			continue;
 
-		drm_sched_entity_fini(&ctx->adev->rings[i]->sched,
-			&ctx->rings[i].entity);
+		drm_sched_entity_destroy(&ctx->rings[i].entity);
 	}
 
 	amdgpu_ctx_fini(ref);
@@ -444,7 +442,7 @@ void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
 	idr_init(&mgr->ctx_handles);
 }
 
-void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
+void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
@@ -466,14 +464,14 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 				continue;
 
-			max_wait = drm_sched_entity_do_release(&ctx->adev->rings[i]->sched,
-					  &ctx->rings[i].entity, max_wait);
+			max_wait = drm_sched_entity_flush(&ctx->rings[i].entity,
+							  max_wait);
 		}
 	}
 	mutex_unlock(&mgr->lock);
 }
 
-void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
+void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
@@ -492,8 +490,7 @@ void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
 				continue;
 
 			if (kref_read(&ctx->refcount) == 1)
-				drm_sched_entity_cleanup(&ctx->adev->rings[i]->sched,
-					&ctx->rings[i].entity);
+				drm_sched_entity_fini(&ctx->rings[i].entity);
 			else
 				DRM_ERROR("ctx %p is still alive\n", ctx);
 		}
@@ -506,7 +503,7 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 	struct idr *idp;
 	uint32_t id;
 
-	amdgpu_ctx_mgr_entity_cleanup(mgr);
+	amdgpu_ctx_mgr_entity_fini(mgr);
 
 	idp = &mgr->ctx_handles;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d82d0d314285..e839470880d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1076,7 +1076,7 @@ static const struct vga_switcheroo_client_ops amdgpu_switcheroo_ops = {
 /**
  * amdgpu_device_ip_set_clockgating_state - set the CG state
  *
- * @adev: amdgpu_device pointer
+ * @dev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
  * @state: clockgating state (gate or ungate)
  *
@@ -1110,7 +1110,7 @@ int amdgpu_device_ip_set_clockgating_state(void *dev,
 /**
  * amdgpu_device_ip_set_powergating_state - set the PG state
  *
- * @adev: amdgpu_device pointer
+ * @dev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
  * @state: powergating state (gate or ungate)
  *
@@ -1221,7 +1221,7 @@ bool amdgpu_device_ip_is_idle(struct amdgpu_device *adev,
  * amdgpu_device_ip_get_ip_block - get a hw IP pointer
  *
  * @adev: amdgpu_device pointer
- * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
+ * @type: Type of hardware IP (SMU, GFX, UVD, etc.)
  *
  * Returns a pointer to the hardware IP block structure
  * if it exists for the asic, otherwise NULL.
@@ -1707,10 +1707,6 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 	if (amdgpu_emu_mode == 1)
 		return 0;
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
-
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -1730,17 +1726,34 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 		}
 	}
 
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK) {
-		/* enable gfx powergating */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_GFX,
-						       AMD_PG_STATE_GATE);
-		/* enable gfxoff */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_PG_STATE_GATE);
-	}
+	return 0;
+}
 
+static int amdgpu_device_ip_late_set_pg_state(struct amdgpu_device *adev)
+{
+	int i = 0, r;
+
+	if (amdgpu_emu_mode == 1)
+		return 0;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.valid)
+			continue;
+		/* skip CG for VCE/UVD, it's handled specially */
+		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->funcs->set_powergating_state) {
+			/* enable powergating to save power */
+			r = adev->ip_blocks[i].version->funcs->set_powergating_state((void *)adev,
+										     AMD_PG_STATE_GATE);
+			if (r) {
+				DRM_ERROR("set_powergating_state(gate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+				return r;
+			}
+		}
+	}
 	return 0;
 }
 
@@ -1774,6 +1787,9 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		}
 	}
 
+	amdgpu_device_ip_late_set_cg_state(adev);
+	amdgpu_device_ip_late_set_pg_state(adev);
+
 	queue_delayed_work(system_wq, &adev->late_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
@@ -1812,6 +1828,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 					  adev->ip_blocks[i].version->funcs->name, r);
 				return r;
 			}
+			if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+				amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false);
 			r = adev->ip_blocks[i].version->funcs->hw_fini((void *)adev);
 			/* XXX handle errors */
 			if (r) {
@@ -1900,11 +1918,15 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, late_init_work.work);
-	amdgpu_device_ip_late_set_cg_state(adev);
+	int r;
+
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
+		DRM_ERROR("ib ring test failed (%d).\n", r);
 }
 
 /**
- * amdgpu_device_ip_suspend - run suspend for hardware IPs
+ * amdgpu_device_ip_suspend_phase1 - run suspend for hardware IPs (phase 1)
  *
  * @adev: amdgpu_device pointer
  *
@@ -1914,18 +1936,60 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
  * in each IP into a state suitable for suspend.
  * Returns 0 on success, negative error code on failure.
  */
-int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
 {
 	int i, r;
 
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_request_full_gpu(adev, false);
 
-	/* ungate SMC block powergating */
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_PG_STATE_UNGATE);
+	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
+		if (!adev->ip_blocks[i].status.valid)
+			continue;
+		/* displays are handled separately */
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) {
+			/* ungate blocks so that suspend can properly shut them down */
+			if (adev->ip_blocks[i].version->funcs->set_clockgating_state) {
+				r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
+											     AMD_CG_STATE_UNGATE);
+				if (r) {
+					DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n",
+						  adev->ip_blocks[i].version->funcs->name, r);
+				}
+			}
+			/* XXX handle errors */
+			r = adev->ip_blocks[i].version->funcs->suspend(adev);
+			/* XXX handle errors */
+			if (r) {
+				DRM_ERROR("suspend of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+			}
+		}
+	}
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, false);
+
+	return 0;
+}
+
+/**
+ * amdgpu_device_ip_suspend_phase2 - run suspend for hardware IPs (phase 2)
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main suspend function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked, clockgating is disabled and the
+ * suspend callbacks are run.  suspend puts the hardware and software state
+ * in each IP into a state suitable for suspend.
+ * Returns 0 on success, negative error code on failure.
+ */
+static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_request_full_gpu(adev, false);
 
 	/* ungate SMC block first */
 	r = amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
@@ -1934,9 +1998,16 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 		DRM_ERROR("set_clockgating_state(ungate) SMC failed %d\n", r);
 	}
 
+	/* call smu to disable gfx off feature first when suspend */
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false);
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
+		/* displays are handled in phase1 */
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)
+			continue;
 		/* ungate blocks so that suspend can properly shut them down */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_SMC &&
 			adev->ip_blocks[i].version->funcs->set_clockgating_state) {
@@ -1962,6 +2033,29 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_device_ip_suspend - run suspend for hardware IPs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main suspend function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked, clockgating is disabled and the
+ * suspend callbacks are run.  suspend puts the hardware and software state
+ * in each IP into a state suitable for suspend.
+ * Returns 0 on success, negative error code on failure.
+ */
+int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_device_ip_suspend_phase1(adev);
+	if (r)
+		return r;
+	r = amdgpu_device_ip_suspend_phase2(adev);
+
+	return r;
+}
+
 static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 {
 	int i, r;
@@ -1984,7 +2078,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
-			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
 		}
@@ -2019,7 +2113,7 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
-			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
 		}
@@ -2180,7 +2274,7 @@ 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)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 #endif
 		return amdgpu_dc != 0;
@@ -2209,7 +2303,7 @@ bool amdgpu_device_has_dc_support(struct amdgpu_device *adev)
  * amdgpu_device_init - initialize the driver
  *
  * @adev: amdgpu_device pointer
- * @pdev: drm dev pointer
+ * @ddev: drm dev pointer
  * @pdev: pci dev pointer
  * @flags: driver flags
  *
@@ -2582,8 +2676,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 /**
  * amdgpu_device_suspend - initiate device suspend
  *
- * @pdev: drm dev pointer
- * @state: suspend state
+ * @dev: drm dev pointer
+ * @suspend: suspend state
+ * @fbcon : notify the fbdev of suspend
  *
  * Puts the hw in the suspend state (all asics).
  * Returns 0 for success or an error on failure.
@@ -2607,6 +2702,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 
 	drm_kms_helper_poll_disable(dev);
 
+	if (fbcon)
+		amdgpu_fbdev_set_suspend(adev, 1);
+
 	if (!amdgpu_device_has_dc_support(adev)) {
 		/* turn off display hw */
 		drm_modeset_lock_all(dev);
@@ -2614,44 +2712,46 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 		}
 		drm_modeset_unlock_all(dev);
-	}
-
-	amdgpu_amdkfd_suspend(adev);
-
-	/* unpin the front buffers and cursors */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-		struct drm_framebuffer *fb = crtc->primary->fb;
-		struct amdgpu_bo *robj;
-
-		if (amdgpu_crtc->cursor_bo) {
-			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-			r = amdgpu_bo_reserve(aobj, true);
-			if (r == 0) {
-				amdgpu_bo_unpin(aobj);
-				amdgpu_bo_unreserve(aobj);
+			/* unpin the front buffers and cursors */
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+			struct drm_framebuffer *fb = crtc->primary->fb;
+			struct amdgpu_bo *robj;
+
+			if (amdgpu_crtc->cursor_bo) {
+				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+				r = amdgpu_bo_reserve(aobj, true);
+				if (r == 0) {
+					amdgpu_bo_unpin(aobj);
+					amdgpu_bo_unreserve(aobj);
+				}
 			}
-		}
 
-		if (fb == NULL || fb->obj[0] == NULL) {
-			continue;
-		}
-		robj = gem_to_amdgpu_bo(fb->obj[0]);
-		/* don't unpin kernel fb objects */
-		if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
-			r = amdgpu_bo_reserve(robj, true);
-			if (r == 0) {
-				amdgpu_bo_unpin(robj);
-				amdgpu_bo_unreserve(robj);
+			if (fb == NULL || fb->obj[0] == NULL) {
+				continue;
+			}
+			robj = gem_to_amdgpu_bo(fb->obj[0]);
+			/* don't unpin kernel fb objects */
+			if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
+				r = amdgpu_bo_reserve(robj, true);
+				if (r == 0) {
+					amdgpu_bo_unpin(robj);
+					amdgpu_bo_unreserve(robj);
+				}
 			}
 		}
 	}
+
+	amdgpu_amdkfd_suspend(adev);
+
+	r = amdgpu_device_ip_suspend_phase1(adev);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
 	amdgpu_fence_driver_suspend(adev);
 
-	r = amdgpu_device_ip_suspend(adev);
+	r = amdgpu_device_ip_suspend_phase2(adev);
 
 	/* evict remaining vram memory
 	 * This second call to evict vram is to evict the gart page table
@@ -2670,18 +2770,15 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			DRM_ERROR("amdgpu asic reset failed\n");
 	}
 
-	if (fbcon) {
-		console_lock();
-		amdgpu_fbdev_set_suspend(adev, 1);
-		console_unlock();
-	}
 	return 0;
 }
 
 /**
  * amdgpu_device_resume - initiate device resume
  *
- * @pdev: drm dev pointer
+ * @dev: drm dev pointer
+ * @resume: resume state
+ * @fbcon : notify the fbdev of resume
  *
  * Bring the hw back to operating state (all asics).
  * Returns 0 for success or an error on failure.
@@ -2697,15 +2794,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (fbcon)
-		console_lock();
-
 	if (resume) {
 		pci_set_power_state(dev->pdev, PCI_D0);
 		pci_restore_state(dev->pdev);
 		r = pci_enable_device(dev->pdev);
 		if (r)
-			goto unlock;
+			return r;
 	}
 
 	/* post card */
@@ -2718,29 +2812,30 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	r = amdgpu_device_ip_resume(adev);
 	if (r) {
 		DRM_ERROR("amdgpu_device_ip_resume failed (%d).\n", r);
-		goto unlock;
+		return r;
 	}
 	amdgpu_fence_driver_resume(adev);
 
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		goto unlock;
-
-	/* pin cursors */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-		if (amdgpu_crtc->cursor_bo) {
-			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-			r = amdgpu_bo_reserve(aobj, true);
-			if (r == 0) {
-				r = amdgpu_bo_pin(aobj,
-						  AMDGPU_GEM_DOMAIN_VRAM,
-						  &amdgpu_crtc->cursor_addr);
-				if (r != 0)
-					DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
-				amdgpu_bo_unreserve(aobj);
+		return r;
+
+	if (!amdgpu_device_has_dc_support(adev)) {
+		/* pin cursors */
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+			if (amdgpu_crtc->cursor_bo) {
+				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+				r = amdgpu_bo_reserve(aobj, true);
+				if (r == 0) {
+					r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
+					if (r != 0)
+						DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+					amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
+					amdgpu_bo_unreserve(aobj);
+				}
 			}
 		}
 	}
@@ -2748,6 +2843,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (r)
 		return r;
 
+	/* Make sure IB tests flushed */
+	flush_delayed_work(&adev->late_init_work);
+
 	/* blat the mode back in */
 	if (fbcon) {
 		if (!amdgpu_device_has_dc_support(adev)) {
@@ -2761,6 +2859,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			}
 			drm_modeset_unlock_all(dev);
 		}
+		amdgpu_fbdev_set_suspend(adev, 0);
 	}
 
 	drm_kms_helper_poll_enable(dev);
@@ -2784,15 +2883,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 #ifdef CONFIG_PM
 	dev->dev->power.disable_depth--;
 #endif
-
-	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 0);
-
-unlock:
-	if (fbcon)
-		console_unlock();
-
-	return r;
+	return 0;
 }
 
 /**
@@ -3069,7 +3160,7 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
  * @adev: amdgpu device pointer
  *
  * attempt to do soft-reset or full-reset and reinitialize Asic
- * return 0 means successed otherwise failed
+ * return 0 means succeeded otherwise failed
  */
 static int amdgpu_device_reset(struct amdgpu_device *adev)
 {
@@ -3144,9 +3235,10 @@ out:
  * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
  *
  * @adev: amdgpu device pointer
+ * @from_hypervisor: request from hypervisor
  *
  * do VF FLR and reinitialize Asic
- * return 0 means successed otherwise failed
+ * return 0 means succeeded otherwise failed
  */
 static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 				     bool from_hypervisor)
@@ -3191,7 +3283,7 @@ error:
  *
  * @adev: amdgpu device pointer
  * @job: which job trigger hang
- * @force forces reset regardless of amdgpu_gpu_recovery
+ * @force: forces reset regardless of amdgpu_gpu_recovery
  *
  * Attempt to reset the GPU if it has hung (all asics).
  * Returns 0 for success or an error on failure.
@@ -3218,6 +3310,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	atomic_inc(&adev->gpu_reset_counter);
 	adev->in_gpu_reset = 1;
 
+	/* Block kfd */
+	amdgpu_amdkfd_pre_reset(adev);
+
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
@@ -3230,10 +3325,10 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		kthread_park(ring->sched.thread);
 
-		if (job && job->ring->idx != i)
+		if (job && job->base.sched == &ring->sched)
 			continue;
 
-		drm_sched_hw_job_reset(&ring->sched, &job->base);
+		drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
@@ -3254,7 +3349,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		 * or all rings (in the case @job is NULL)
 		 * after above amdgpu_reset accomplished
 		 */
-		if ((!job || job->ring->idx == i) && !r)
+		if ((!job || job->base.sched == &ring->sched) && !r)
 			drm_sched_job_recovery(&ring->sched);
 
 		kthread_unpark(ring->sched.thread);
@@ -3271,9 +3366,11 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		dev_info(adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
 	} else {
-		dev_info(adev->dev, "GPU reset(%d) successed!\n",atomic_read(&adev->gpu_reset_counter));
+		dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter));
 	}
 
+	/*unlock kfd */
+	amdgpu_amdkfd_post_reset(adev);
 	amdgpu_vf_error_trans_all(adev);
 	adev->in_gpu_reset = 0;
 	mutex_unlock(&adev->lock_reset);
@@ -3291,8 +3388,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
  */
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 {
-	u32 mask;
-	int ret;
+	struct pci_dev *pdev;
+	enum pci_bus_speed speed_cap;
+	enum pcie_link_width link_width;
 
 	if (amdgpu_pcie_gen_cap)
 		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
@@ -3310,27 +3408,61 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 	}
 
 	if (adev->pm.pcie_gen_mask == 0) {
-		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-		if (!ret) {
-			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+		/* asic caps */
+		pdev = adev->pdev;
+		speed_cap = pcie_get_speed_cap(pdev);
+		if (speed_cap == PCI_SPEED_UNKNOWN) {
+			adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-			if (mask & DRM_PCIE_SPEED_25)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-			if (mask & DRM_PCIE_SPEED_50)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-			if (mask & DRM_PCIE_SPEED_80)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
 		} else {
-			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+			if (speed_cap == PCIE_SPEED_16_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4);
+			else if (speed_cap == PCIE_SPEED_8_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+			else if (speed_cap == PCIE_SPEED_5_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2);
+			else
+				adev->pm.pcie_gen_mask |= CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1;
+		}
+		/* platform caps */
+		pdev = adev->ddev->pdev->bus->self;
+		speed_cap = pcie_get_speed_cap(pdev);
+		if (speed_cap == PCI_SPEED_UNKNOWN) {
+			adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2);
+		} else {
+			if (speed_cap == PCIE_SPEED_16_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4);
+			else if (speed_cap == PCIE_SPEED_8_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3);
+			else if (speed_cap == PCIE_SPEED_5_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2);
+			else
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+
 		}
 	}
 	if (adev->pm.pcie_mlw_mask == 0) {
-		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-		if (!ret) {
-			switch (mask) {
-			case 32:
+		pdev = adev->ddev->pdev->bus->self;
+		link_width = pcie_get_width_cap(pdev);
+		if (link_width == PCIE_LNK_WIDTH_UNKNOWN) {
+			adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_PCIE_MLW_MASK;
+		} else {
+			switch (link_width) {
+			case PCIE_LNK_X32:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
@@ -3339,7 +3471,7 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 16:
+			case PCIE_LNK_X16:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
@@ -3347,36 +3479,34 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 12:
+			case PCIE_LNK_X12:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 8:
+			case PCIE_LNK_X8:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 4:
+			case PCIE_LNK_X4:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 2:
+			case PCIE_LNK_X2:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 1:
+			case PCIE_LNK_X1:
 				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
 				break;
 			default:
 				break;
 			}
-		} else {
-			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 76ee8e04ff11..6748cd7fc129 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -157,7 +157,6 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	struct amdgpu_bo *new_abo;
 	unsigned long flags;
 	u64 tiling_flags;
-	u64 base;
 	int i, r;
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
@@ -189,12 +188,18 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 		goto cleanup;
 	}
 
-	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev), &base);
+	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev));
 	if (unlikely(r != 0)) {
 		DRM_ERROR("failed to pin new abo buffer before flip\n");
 		goto unreserve;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&new_abo->tbo);
+	if (unlikely(r != 0)) {
+		DRM_ERROR("%p bind failed\n", new_abo);
+		goto unpin;
+	}
+
 	r = reservation_object_get_fences_rcu(new_abo->tbo.resv, &work->excl,
 					      &work->shared_count,
 					      &work->shared);
@@ -206,7 +211,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	amdgpu_bo_get_tiling_flags(new_abo, &tiling_flags);
 	amdgpu_bo_unreserve(new_abo);
 
-	work->base = base;
+	work->base = amdgpu_bo_gpu_offset(new_abo);
 	work->target_vblank = target - (uint32_t)drm_crtc_vblank_count(crtc) +
 		amdgpu_get_vblank_counter_kms(dev, work->crtc_id);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 77ad59ade85c..1c4595562f8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -28,6 +28,7 @@
 #include "amdgpu_i2c.h"
 #include "amdgpu_dpm.h"
 #include "atom.h"
+#include "amd_pcie.h"
 
 void amdgpu_dpm_print_class_info(u32 class, u32 class2)
 {
@@ -936,9 +937,11 @@ enum amdgpu_pcie_gen amdgpu_get_pcie_gen_support(struct amdgpu_device *adev,
 	case AMDGPU_PCIE_GEN3:
 		return AMDGPU_PCIE_GEN3;
 	default:
-		if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == AMDGPU_PCIE_GEN3))
+		if ((sys_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) &&
+		    (default_gen == AMDGPU_PCIE_GEN3))
 			return AMDGPU_PCIE_GEN3;
-		else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == AMDGPU_PCIE_GEN2))
+		else if ((sys_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) &&
+			 (default_gen == AMDGPU_PCIE_GEN2))
 			return AMDGPU_PCIE_GEN2;
 		else
 			return AMDGPU_PCIE_GEN1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 9acfbee91c40..ff24e1cc5b65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -287,12 +287,6 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_force_performance_level(adev, l) \
 		((adev)->powerplay.pp_funcs->force_performance_level((adev)->powerplay.pp_handle, (l)))
 
-#define amdgpu_dpm_powergate_uvd(adev, g) \
-		((adev)->powerplay.pp_funcs->powergate_uvd((adev)->powerplay.pp_handle, (g)))
-
-#define amdgpu_dpm_powergate_vce(adev, g) \
-		((adev)->powerplay.pp_funcs->powergate_vce((adev)->powerplay.pp_handle, (g)))
-
 #define amdgpu_dpm_get_current_power_state(adev) \
 		((adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle))
 
@@ -347,6 +341,10 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
 
+#define amdgpu_dpm_set_powergating_by_smu(adev, block_type, gate) \
+		((adev)->powerplay.pp_funcs->set_powergating_by_smu(\
+			(adev)->powerplay.pp_handle, block_type, gate))
+
 #define amdgpu_dpm_get_power_profile_mode(adev, buf) \
 		((adev)->powerplay.pp_funcs->get_power_profile_mode(\
 			(adev)->powerplay.pp_handle, buf))
@@ -359,10 +357,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
 
-#define amdgpu_dpm_set_mmhub_powergating_by_smu(adev) \
-		((adev)->powerplay.pp_funcs->set_mmhub_powergating_by_smu( \
-		(adev)->powerplay.pp_handle))
-
 struct amdgpu_dpm {
 	struct amdgpu_ps        *ps;
 	/* number of valid power states */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index a549483032b0..8843a06360fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1,10 +1,3 @@
-/**
- * \file amdgpu_drv.c
- * AMD Amdgpu driver
- *
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * All Rights Reserved.
@@ -76,9 +69,10 @@
  * - 3.24.0 - Add high priority compute support for gfx9
  * - 3.25.0 - Add support for sensor query info (stable pstate sclk/mclk).
  * - 3.26.0 - GFX9: Process AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE.
+ * - 3.27.0 - Add new chunk to to AMDGPU_CS to enable BO_LIST creation.
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	26
+#define KMS_DRIVER_MINOR	27
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
@@ -110,11 +104,8 @@ int amdgpu_vram_page_split = 512;
 int amdgpu_vm_update_mode = -1;
 int amdgpu_exp_hw_support = 0;
 int amdgpu_dc = -1;
-int amdgpu_dc_log = 0;
 int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
-int amdgpu_no_evict = 0;
-int amdgpu_direct_gma_size = 0;
 uint amdgpu_pcie_gen_cap = 0;
 uint amdgpu_pcie_lane_cap = 0;
 uint amdgpu_cg_mask = 0xffffffff;
@@ -122,7 +113,8 @@ uint amdgpu_pg_mask = 0xffffffff;
 uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu = NULL;
 char *amdgpu_virtual_display = NULL;
-uint amdgpu_pp_feature_mask = 0xffff3fff; /* gfxoff (bit 15) disabled by default */
+/* OverDrive(bit 14),gfxoff(bit 15),stutter mode(bit 17) disabled by default*/
+uint amdgpu_pp_feature_mask = 0xfffd3fff;
 int amdgpu_ngg = 0;
 int amdgpu_prim_buf_per_se = 0;
 int amdgpu_pos_buf_per_se = 0;
@@ -135,163 +127,368 @@ int amdgpu_gpu_recovery = -1; /* auto */
 int amdgpu_emu_mode = 0;
 uint amdgpu_smu_memory_pool_size = 0;
 
+/**
+ * DOC: vramlimit (int)
+ * Restrict the total amount of VRAM in MiB for testing.  The default is 0 (Use full VRAM).
+ */
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
 
+/**
+ * DOC: vis_vramlimit (int)
+ * Restrict the amount of CPU visible VRAM in MiB for testing.  The default is 0 (Use full CPU visible VRAM).
+ */
 MODULE_PARM_DESC(vis_vramlimit, "Restrict visible VRAM for testing, in megabytes");
 module_param_named(vis_vramlimit, amdgpu_vis_vram_limit, int, 0444);
 
+/**
+ * DOC: gartsize (uint)
+ * Restrict the size of GART in Mib (32, 64, etc.) for testing. The default is -1 (The size depends on asic).
+ */
 MODULE_PARM_DESC(gartsize, "Size of GART to setup in megabytes (32, 64, etc., -1=auto)");
 module_param_named(gartsize, amdgpu_gart_size, uint, 0600);
 
+/**
+ * DOC: gttsize (int)
+ * Restrict the size of GTT domain in MiB for testing. The default is -1 (It's VRAM size if 3GB < VRAM < 3/4 RAM,
+ * otherwise 3/4 RAM size).
+ */
 MODULE_PARM_DESC(gttsize, "Size of the GTT domain in megabytes (-1 = auto)");
 module_param_named(gttsize, amdgpu_gtt_size, int, 0600);
 
+/**
+ * DOC: moverate (int)
+ * Set maximum buffer migration rate in MB/s. The default is -1 (8 MB/s).
+ */
 MODULE_PARM_DESC(moverate, "Maximum buffer migration rate in MB/s. (32, 64, etc., -1=auto, 0=1=disabled)");
 module_param_named(moverate, amdgpu_moverate, int, 0600);
 
+/**
+ * DOC: benchmark (int)
+ * Run benchmarks. The default is 0 (Skip benchmarks).
+ */
 MODULE_PARM_DESC(benchmark, "Run benchmark");
 module_param_named(benchmark, amdgpu_benchmarking, int, 0444);
 
+/**
+ * DOC: test (int)
+ * Test BO GTT->VRAM and VRAM->GTT GPU copies. The default is 0 (Skip test, only set 1 to run test).
+ */
 MODULE_PARM_DESC(test, "Run tests");
 module_param_named(test, amdgpu_testing, int, 0444);
 
+/**
+ * DOC: audio (int)
+ * Set HDMI/DPAudio. Only affects non-DC display handling. The default is -1 (Enabled), set 0 to disabled it.
+ */
 MODULE_PARM_DESC(audio, "Audio enable (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(audio, amdgpu_audio, int, 0444);
 
+/**
+ * DOC: disp_priority (int)
+ * Set display Priority (1 = normal, 2 = high). Only affects non-DC display handling. The default is 0 (auto).
+ */
 MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)");
 module_param_named(disp_priority, amdgpu_disp_priority, int, 0444);
 
+/**
+ * DOC: hw_i2c (int)
+ * To enable hw i2c engine. Only affects non-DC display handling. The default is 0 (Disabled).
+ */
 MODULE_PARM_DESC(hw_i2c, "hw i2c engine enable (0 = disable)");
 module_param_named(hw_i2c, amdgpu_hw_i2c, int, 0444);
 
+/**
+ * DOC: pcie_gen2 (int)
+ * To disable PCIE Gen2/3 mode (0 = disable, 1 = enable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(pcie_gen2, "PCIE Gen2 mode (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(pcie_gen2, amdgpu_pcie_gen2, int, 0444);
 
+/**
+ * DOC: msi (int)
+ * To disable Message Signaled Interrupts (MSI) functionality (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(msi, amdgpu_msi, int, 0444);
 
+/**
+ * DOC: lockup_timeout (int)
+ * Set GPU scheduler timeout value in ms. Value 0 is invalidated, will be adjusted to 10000.
+ * Negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET). The default is 10000.
+ */
 MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms > 0 (default 10000)");
 module_param_named(lockup_timeout, amdgpu_lockup_timeout, int, 0444);
 
+/**
+ * DOC: dpm (int)
+ * Override for dynamic power management setting (1 = enable, 0 = disable). The default is -1 (auto).
+ */
 MODULE_PARM_DESC(dpm, "DPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(dpm, amdgpu_dpm, int, 0444);
 
+/**
+ * DOC: fw_load_type (int)
+ * Set different firmware loading type for debugging (0 = direct, 1 = SMU, 2 = PSP). The default is -1 (auto).
+ */
 MODULE_PARM_DESC(fw_load_type, "firmware loading type (0 = direct, 1 = SMU, 2 = PSP, -1 = auto)");
 module_param_named(fw_load_type, amdgpu_fw_load_type, int, 0444);
 
+/**
+ * DOC: aspm (int)
+ * To disable ASPM (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(aspm, amdgpu_aspm, int, 0444);
 
+/**
+ * DOC: runpm (int)
+ * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down
+ * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality.
+ */
 MODULE_PARM_DESC(runpm, "PX runtime pm (1 = force enable, 0 = disable, -1 = PX only default)");
 module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
 
+/**
+ * DOC: ip_block_mask (uint)
+ * Override what IP blocks are enabled on the GPU. Each GPU is a collection of IP blocks (gfx, display, video, etc.).
+ * Use this parameter to disable specific blocks. Note that the IP blocks do not have a fixed index. Some asics may not have
+ * some IPs or may include multiple instances of an IP so the ordering various from asic to asic. See the driver output in
+ * the kernel log for the list of IPs on the asic. The default is 0xffffffff (enable all blocks on a device).
+ */
 MODULE_PARM_DESC(ip_block_mask, "IP Block Mask (all blocks enabled (default))");
 module_param_named(ip_block_mask, amdgpu_ip_block_mask, uint, 0444);
 
+/**
+ * DOC: bapm (int)
+ * Bidirectional Application Power Management (BAPM) used to dynamically share TDP between CPU and GPU. Set value 0 to disable it.
+ * The default -1 (auto, enabled)
+ */
 MODULE_PARM_DESC(bapm, "BAPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(bapm, amdgpu_bapm, int, 0444);
 
+/**
+ * DOC: deep_color (int)
+ * Set 1 to enable Deep Color support. Only affects non-DC display handling. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(deep_color, "Deep Color support (1 = enable, 0 = disable (default))");
 module_param_named(deep_color, amdgpu_deep_color, int, 0444);
 
+/**
+ * DOC: vm_size (int)
+ * Override the size of the GPU's per client virtual address space in GiB.  The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_size, "VM address space size in gigabytes (default 64GB)");
 module_param_named(vm_size, amdgpu_vm_size, int, 0444);
 
+/**
+ * DOC: vm_fragment_size (int)
+ * Override VM fragment size in bits (4, 5, etc. 4 = 64K, 9 = 2M). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_fragment_size, "VM fragment size in bits (4, 5, etc. 4 = 64K (default), Max 9 = 2M)");
 module_param_named(vm_fragment_size, amdgpu_vm_fragment_size, int, 0444);
 
+/**
+ * DOC: vm_block_size (int)
+ * Override VM page table size in bits (default depending on vm_size and hw setup). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_block_size, "VM page table size in bits (default depending on vm_size)");
 module_param_named(vm_block_size, amdgpu_vm_block_size, int, 0444);
 
+/**
+ * DOC: vm_fault_stop (int)
+ * Stop on VM fault for debugging (0 = never, 1 = print first, 2 = always). The default is 0 (No stop).
+ */
 MODULE_PARM_DESC(vm_fault_stop, "Stop on VM fault (0 = never (default), 1 = print first, 2 = always)");
 module_param_named(vm_fault_stop, amdgpu_vm_fault_stop, int, 0444);
 
+/**
+ * DOC: vm_debug (int)
+ * Debug VM handling (0 = disabled, 1 = enabled). The default is 0 (Disabled).
+ */
 MODULE_PARM_DESC(vm_debug, "Debug VM handling (0 = disabled (default), 1 = enabled)");
 module_param_named(vm_debug, amdgpu_vm_debug, int, 0644);
 
+/**
+ * DOC: vm_update_mode (int)
+ * Override VM update mode. VM updated by using CPU (0 = never, 1 = Graphics only, 2 = Compute only, 3 = Both). The default
+ * is -1 (Only in large BAR(LB) systems Compute VM tables will be updated by CPU, otherwise 0, never).
+ */
 MODULE_PARM_DESC(vm_update_mode, "VM update using CPU (0 = never (default except for large BAR(LB)), 1 = Graphics only, 2 = Compute only (default for LB), 3 = Both");
 module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444);
 
+/**
+ * DOC: vram_page_split (int)
+ * Override the number of pages after we split VRAM allocations (default 512, -1 = disable). The default is 512.
+ */
 MODULE_PARM_DESC(vram_page_split, "Number of pages after we split VRAM allocations (default 512, -1 = disable)");
 module_param_named(vram_page_split, amdgpu_vram_page_split, int, 0444);
 
+/**
+ * DOC: exp_hw_support (int)
+ * Enable experimental hw support (1 = enable). The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))");
 module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
 
+/**
+ * DOC: dc (int)
+ * Disable/Enable Display Core driver for debugging (1 = enable, 0 = disable). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(dc, "Display Core driver (1 = enable, 0 = disable, -1 = auto (default))");
 module_param_named(dc, amdgpu_dc, int, 0444);
 
-MODULE_PARM_DESC(dc_log, "Display Core Log Level (0 = minimal (default), 1 = chatty");
-module_param_named(dc_log, amdgpu_dc_log, int, 0444);
-
+/**
+ * DOC: sched_jobs (int)
+ * Override the max number of jobs supported in the sw queue. The default is 32.
+ */
 MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 32)");
 module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444);
 
+/**
+ * DOC: sched_hw_submission (int)
+ * Override the max number of HW submissions. The default is 2.
+ */
 MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)");
 module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 
+/**
+ * DOC: ppfeaturemask (uint)
+ * Override power features enabled. See enum PP_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
+ * The default is the current set of stable power features.
+ */
 MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
 module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
 
-MODULE_PARM_DESC(no_evict, "Support pinning request from user space (1 = enable, 0 = disable (default))");
-module_param_named(no_evict, amdgpu_no_evict, int, 0444);
-
-MODULE_PARM_DESC(direct_gma_size, "Direct GMA size in megabytes (max 96MB)");
-module_param_named(direct_gma_size, amdgpu_direct_gma_size, int, 0444);
-
+/**
+ * DOC: pcie_gen_cap (uint)
+ * Override PCIE gen speed capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
+ * The default is 0 (automatic for each asic).
+ */
 MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
 module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
 
+/**
+ * DOC: pcie_lane_cap (uint)
+ * Override PCIE lanes capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
+ * The default is 0 (automatic for each asic).
+ */
 MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
 module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
 
+/**
+ * DOC: cg_mask (uint)
+ * Override Clockgating features enabled on GPU (0 = disable clock gating). See the AMD_CG_SUPPORT flags in
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ */
 MODULE_PARM_DESC(cg_mask, "Clockgating flags mask (0 = disable clock gating)");
 module_param_named(cg_mask, amdgpu_cg_mask, uint, 0444);
 
+/**
+ * DOC: pg_mask (uint)
+ * Override Powergating features enabled on GPU (0 = disable power gating). See the AMD_PG_SUPPORT flags in
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ */
 MODULE_PARM_DESC(pg_mask, "Powergating flags mask (0 = disable power gating)");
 module_param_named(pg_mask, amdgpu_pg_mask, uint, 0444);
 
+/**
+ * DOC: sdma_phase_quantum (uint)
+ * Override SDMA context switch phase quantum (x 1K GPU clock cycles, 0 = no change). The default is 32.
+ */
 MODULE_PARM_DESC(sdma_phase_quantum, "SDMA context switch phase quantum (x 1K GPU clock cycles, 0 = no change (default 32))");
 module_param_named(sdma_phase_quantum, amdgpu_sdma_phase_quantum, uint, 0444);
 
+/**
+ * DOC: disable_cu (charp)
+ * Set to disable CUs (It's set like se.sh.cu,...). The default is NULL.
+ */
 MODULE_PARM_DESC(disable_cu, "Disable CUs (se.sh.cu,...)");
 module_param_named(disable_cu, amdgpu_disable_cu, charp, 0444);
 
+/**
+ * DOC: virtual_display (charp)
+ * Set to enable virtual display feature. This feature provides a virtual display hardware on headless boards
+ * or in virtualized environments. It will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x. It's the pci address of
+ * the device, plus the number of crtcs to expose. E.g., 0000:26:00.0,4 would enable 4 virtual crtcs on the pci
+ * device at 26:00.0. The default is NULL.
+ */
 MODULE_PARM_DESC(virtual_display,
 		 "Enable virtual display feature (the virtual_display will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x)");
 module_param_named(virtual_display, amdgpu_virtual_display, charp, 0444);
 
+/**
+ * DOC: ngg (int)
+ * Set to enable Next Generation Graphics (1 = enable). The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(ngg, "Next Generation Graphics (1 = enable, 0 = disable(default depending on gfx))");
 module_param_named(ngg, amdgpu_ngg, int, 0444);
 
+/**
+ * DOC: prim_buf_per_se (int)
+ * Override the size of Primitive Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(prim_buf_per_se, "the size of Primitive Buffer per Shader Engine (default depending on gfx)");
 module_param_named(prim_buf_per_se, amdgpu_prim_buf_per_se, int, 0444);
 
+/**
+ * DOC: pos_buf_per_se (int)
+ * Override the size of Position Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(pos_buf_per_se, "the size of Position Buffer per Shader Engine (default depending on gfx)");
 module_param_named(pos_buf_per_se, amdgpu_pos_buf_per_se, int, 0444);
 
+/**
+ * DOC: cntl_sb_buf_per_se (int)
+ * Override the size of Control Sideband per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(cntl_sb_buf_per_se, "the size of Control Sideband per Shader Engine (default depending on gfx)");
 module_param_named(cntl_sb_buf_per_se, amdgpu_cntl_sb_buf_per_se, int, 0444);
 
+/**
+ * DOC: param_buf_per_se (int)
+ * Override the size of Off-Chip Pramater Cache per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(param_buf_per_se, "the size of Off-Chip Pramater Cache per Shader Engine (default depending on gfx)");
 module_param_named(param_buf_per_se, amdgpu_param_buf_per_se, int, 0444);
 
+/**
+ * DOC: job_hang_limit (int)
+ * Set how much time allow a job hang and not drop it. The default is 0.
+ */
 MODULE_PARM_DESC(job_hang_limit, "how much time allow a job hang and not drop it (default 0)");
 module_param_named(job_hang_limit, amdgpu_job_hang_limit, int ,0444);
 
+/**
+ * DOC: lbpw (int)
+ * Override Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(lbpw, "Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(lbpw, amdgpu_lbpw, int, 0444);
 
 MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
 
+/**
+ * DOC: gpu_recovery (int)
+ * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV).
+ */
 MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
 
+/**
+ * DOC: emu_mode (int)
+ * Set value 1 to enable emulation mode. This is only needed when running on an emulator. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(emu_mode, "Emulation mode, (1 = enable, 0 = disable)");
 module_param_named(emu_mode, amdgpu_emu_mode, int, 0444);
 
+/**
+ * DOC: si_support (int)
+ * Set SI support driver. This parameter works after set config CONFIG_DRM_AMDGPU_SI. For SI asic, when radeon driver is enabled,
+ * set value 0 to use radeon driver, while set value 1 to use amdgpu driver. The default is using radeon driver when it available,
+ * otherwise using amdgpu driver.
+ */
 #ifdef CONFIG_DRM_AMDGPU_SI
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -305,6 +502,12 @@ MODULE_PARM_DESC(si_support, "SI support (1 = enabled (default), 0 = disabled)")
 module_param_named(si_support, amdgpu_si_support, int, 0444);
 #endif
 
+/**
+ * DOC: cik_support (int)
+ * Set CIK support driver. This parameter works after set config CONFIG_DRM_AMDGPU_CIK. For CIK asic, when radeon driver is enabled,
+ * set value 0 to use radeon driver, while set value 1 to use amdgpu driver. The default is using radeon driver when it available,
+ * otherwise using amdgpu driver.
+ */
 #ifdef CONFIG_DRM_AMDGPU_CIK
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -318,6 +521,11 @@ MODULE_PARM_DESC(cik_support, "CIK support (1 = enabled (default), 0 = disabled)
 module_param_named(cik_support, amdgpu_cik_support, int, 0444);
 #endif
 
+/**
+ * DOC: smu_memory_pool_size (uint)
+ * It is used to reserve gtt for smu debug usage, setting value 0 to disable it. The actual size is value * 256MiB.
+ * E.g. 0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(smu_memory_pool_size,
 	"reserve gtt for smu debug usage, 0 = disable,"
 		"0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte");
@@ -664,7 +872,7 @@ retry_init:
 err_pci:
 	pci_disable_device(pdev);
 err_free:
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	return ret;
 }
 
@@ -674,7 +882,7 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
 	drm_dev_unregister(dev);
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
@@ -860,7 +1068,7 @@ static int amdgpu_flush(struct file *f, fl_owner_t id)
 	struct drm_file *file_priv = f->private_data;
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
 
-	amdgpu_ctx_mgr_entity_fini(&fpriv->ctx_mgr);
+	amdgpu_ctx_mgr_entity_flush(&fpriv->ctx_mgr);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
index 94138abe093b..ae8fac34f7a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
@@ -46,7 +46,7 @@ amdgpu_link_encoder_connector(struct drm_device *dev)
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			amdgpu_encoder = to_amdgpu_encoder(encoder);
 			if (amdgpu_encoder->devices & amdgpu_connector->devices) {
-				drm_mode_connector_attach_encoder(connector, encoder);
+				drm_connector_attach_encoder(connector, encoder);
 				if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
 					amdgpu_atombios_encoder_init_backlight(amdgpu_encoder, connector);
 					adev->mode_info.bl_encoder = amdgpu_encoder;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index bc5fd8ebab5d..69c5d22f29bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 				       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 				       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
 				       AMDGPU_GEM_CREATE_VRAM_CLEARED,
-				       true, NULL, &gobj);
+				       ttm_bo_type_kernel, NULL, &gobj);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
 		return -ENOMEM;
@@ -168,11 +168,19 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	}
 
 
-	ret = amdgpu_bo_pin(abo, domain, NULL);
+	ret = amdgpu_bo_pin(abo, domain);
 	if (ret) {
 		amdgpu_bo_unreserve(abo);
 		goto out_unref;
 	}
+
+	ret = amdgpu_ttm_alloc_gart(&abo->tbo);
+	if (ret) {
+		amdgpu_bo_unreserve(abo);
+		dev_err(adev->dev, "%p bind failed\n", abo);
+		goto out_unref;
+	}
+
 	ret = amdgpu_bo_kmap(abo, NULL);
 	amdgpu_bo_unreserve(abo);
 	if (ret) {
@@ -365,8 +373,8 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev)
 void amdgpu_fbdev_set_suspend(struct amdgpu_device *adev, int state)
 {
 	if (adev->mode_info.rfbdev)
-		drm_fb_helper_set_suspend(&adev->mode_info.rfbdev->helper,
-			state);
+		drm_fb_helper_set_suspend_unlocked(&adev->mode_info.rfbdev->helper,
+						   state);
 }
 
 int amdgpu_fbdev_total_size(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index dd11b7313ca0..a54d5655a191 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -143,14 +143,12 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
  */
 int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
 {
-	uint64_t gpu_addr;
 	int r;
 
 	r = amdgpu_bo_reserve(adev->gart.robj, false);
 	if (unlikely(r != 0))
 		return r;
-	r = amdgpu_bo_pin(adev->gart.robj,
-				AMDGPU_GEM_DOMAIN_VRAM, &gpu_addr);
+	r = amdgpu_bo_pin(adev->gart.robj, AMDGPU_GEM_DOMAIN_VRAM);
 	if (r) {
 		amdgpu_bo_unreserve(adev->gart.robj);
 		return r;
@@ -159,7 +157,7 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
 	if (r)
 		amdgpu_bo_unpin(adev->gart.robj);
 	amdgpu_bo_unreserve(adev->gart.robj);
-	adev->gart.table_addr = gpu_addr;
+	adev->gart.table_addr = amdgpu_bo_gpu_offset(adev->gart.robj);
 	return r;
 }
 
@@ -234,7 +232,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 	}
 
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
-	p = t / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++) {
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 		adev->gart.pages[p] = NULL;
@@ -243,7 +241,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 		if (!adev->gart.ptr)
 			continue;
 
-		for (j = 0; j < (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE); j++, t++) {
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
 			amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr,
 					       t, page_base, flags);
 			page_base += AMDGPU_GPU_PAGE_SIZE;
@@ -282,7 +280,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 
 	for (i = 0; i < pages; i++) {
 		page_base = dma_addr[i];
-		for (j = 0; j < (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE); j++, t++) {
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
 			amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
 			page_base += AMDGPU_GPU_PAGE_SIZE;
 		}
@@ -319,7 +317,7 @@ int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
-	p = t / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++)
 		adev->gart.pages[p] = pagelist ? pagelist[i] : NULL;
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index 456295c00291..9f9e9dc87da1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -37,6 +37,8 @@ struct amdgpu_bo;
 #define AMDGPU_GPU_PAGE_SHIFT 12
 #define AMDGPU_GPU_PAGE_ALIGN(a) (((a) + AMDGPU_GPU_PAGE_MASK) & ~AMDGPU_GPU_PAGE_MASK)
 
+#define AMDGPU_GPU_PAGES_IN_CPU_PAGE (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE)
+
 struct amdgpu_gart {
 	u64				table_addr;
 	struct amdgpu_bo		*robj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 89743cdc1c2c..71792d820ae0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -265,7 +265,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
 				     (u32)(0xffffffff & args->in.domains),
-				     flags, false, resv, &gobj);
+				     flags, ttm_bo_type_device, resv, &gobj);
 	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
 		if (!r) {
 			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);
@@ -317,7 +317,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 	/* create a gem object to contain this object in */
 	r = amdgpu_gem_object_create(adev, args->size, 0, AMDGPU_GEM_DOMAIN_CPU,
-				     0, 0, NULL, &gobj);
+				     0, ttm_bo_type_device, NULL, &gobj);
 	if (r)
 		return r;
 
@@ -344,7 +344,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 		if (r)
 			goto free_pages;
 
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (r)
@@ -766,7 +766,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 				amdgpu_display_supported_domains(adev));
 	r = amdgpu_gem_object_create(adev, args->size, 0, domain,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     false, NULL, &gobj);
+				     ttm_bo_type_device, NULL, &gobj);
 	if (r)
 		return -ENOMEM;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 6cb4948233cb..bb5a47a45790 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -105,6 +105,8 @@ struct amdgpu_gmc {
 	/* protects concurrent invalidation */
 	spinlock_t		invalidate_lock;
 	bool			translate_further;
+	struct kfd_vm_fault_info *vm_fault_info;
+	atomic_t		vm_fault_info_updated;
 
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 31f8170313b4..5518e623fed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -139,7 +139,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* ring tests don't use a job */
 	if (job) {
 		vm = job->vm;
-		fence_ctx = job->fence_ctx;
+		fence_ctx = job->base.s_fence->scheduled.context;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
@@ -231,6 +231,12 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
 		fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
 
+	/* wrap the last IB with fence */
+	if (job && job->uf_addr) {
+		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
+				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
+	}
+
 	r = amdgpu_fence_emit(ring, f, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
@@ -243,12 +249,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ring->funcs->insert_end)
 		ring->funcs->insert_end(ring);
 
-	/* wrap the last IB with fence */
-	if (job && job->uf_addr) {
-		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
-				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
-	}
-
 	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
 		amdgpu_ring_patch_cond_exec(ring, patch_offset);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index a1c78f90eadf..3a072a7a39f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -578,11 +578,6 @@ void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
 			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
 		}
 	}
-
-	adev->vm_manager.fence_context =
-		dma_fence_context_alloc(AMDGPU_MAX_RINGS);
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
-		adev->vm_manager.seqno[i] = 0;
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 2bd56760c744..391e2f7c03aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -30,14 +30,14 @@
 
 static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
+	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
-	DRM_ERROR("ring %s timeout, last signaled seq=%u, last emitted seq=%u\n",
-		  job->base.sched->name,
-		  atomic_read(&job->ring->fence_drv.last_seq),
-		  job->ring->fence_drv.sync_seq);
+	DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
+		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
+		  ring->fence_drv.sync_seq);
 
-	amdgpu_device_gpu_recover(job->adev, job, false);
+	amdgpu_device_gpu_recover(ring->adev, job, false);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
@@ -54,7 +54,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	if (!*job)
 		return -ENOMEM;
 
-	(*job)->adev = adev;
+	/*
+	 * Initialize the scheduler to at least some ring so that we always
+	 * have a pointer to adev.
+	 */
+	(*job)->base.sched = &adev->rings[0]->sched;
 	(*job)->vm = vm;
 	(*job)->ibs = (void *)&(*job)[1];
 	(*job)->num_ibs = num_ibs;
@@ -86,6 +90,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 
 void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	struct dma_fence *f;
 	unsigned i;
 
@@ -93,14 +98,15 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
 
 	for (i = 0; i < job->num_ibs; ++i)
-		amdgpu_ib_free(job->adev, &job->ibs[i], f);
+		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }
 
 static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
+	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
-	amdgpu_ring_priority_put(job->ring, s_job->s_priority);
+	amdgpu_ring_priority_put(ring, s_job->s_priority);
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
@@ -117,50 +123,68 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	kfree(job);
 }
 
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f)
+int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
+		      void *owner, struct dma_fence **f)
 {
+	enum drm_sched_priority priority;
+	struct amdgpu_ring *ring;
 	int r;
-	job->ring = ring;
 
 	if (!f)
 		return -EINVAL;
 
-	r = drm_sched_job_init(&job->base, &ring->sched, entity, owner);
+	r = drm_sched_job_init(&job->base, entity, owner);
 	if (r)
 		return r;
 
 	job->owner = owner;
-	job->fence_ctx = entity->fence_context;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
+	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
+	ring = to_amdgpu_ring(entity->rq->sched);
+	amdgpu_ring_priority_get(ring, priority);
+
+	return 0;
+}
+
+int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
+			     struct dma_fence **fence)
+{
+	int r;
+
+	job->base.sched = &ring->sched;
+	r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, NULL, fence);
+	job->fence = dma_fence_get(*fence);
+	if (r)
+		return r;
+
+	amdgpu_job_free(job);
 	return 0;
 }
 
 static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 					       struct drm_sched_entity *s_entity)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched);
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
+	struct dma_fence *fence;
 	bool explicit = false;
 	int r;
-	struct dma_fence *fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 
+	fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 	if (fence && explicit) {
 		if (drm_sched_dependency_optimized(fence, s_entity)) {
-			r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence, false);
+			r = amdgpu_sync_fence(ring->adev, &job->sched_sync,
+					      fence, false);
 			if (r)
-				DRM_ERROR("Error adding fence to sync (%d)\n", r);
+				DRM_ERROR("Error adding fence (%d)\n", r);
 		}
 	}
 
 	while (fence == NULL && vm && !job->vmid) {
-		struct amdgpu_ring *ring = job->ring;
-
 		r = amdgpu_vmid_grab(vm, ring, &job->sync,
 				     &job->base.s_fence->finished,
 				     job);
@@ -175,30 +199,25 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 
 static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
-	struct amdgpu_device *adev;
 	struct amdgpu_job *job;
 	int r;
 
-	if (!sched_job) {
-		DRM_ERROR("job is null\n");
-		return NULL;
-	}
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
-	adev = job->adev;
 
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
 
-	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+	if (job->vram_lost_counter != atomic_read(&ring->adev->vram_lost_counter))
 		dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */
 
 	if (finished->error < 0) {
 		DRM_INFO("Skip scheduling IBs!\n");
 	} else {
-		r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
+		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job,
 				       &fence);
 		if (r)
 			DRM_ERROR("Error scheduling IBs (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
new file mode 100644
index 000000000000..57cfe78a262b
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -0,0 +1,74 @@
+/*
+ * 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.
+ *
+ */
+#ifndef __AMDGPU_JOB_H__
+#define __AMDGPU_JOB_H__
+
+/* bit set means command submit involves a preamble IB */
+#define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0)
+/* bit set means preamble IB is first presented in belonging context */
+#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1)
+/* bit set means context switch occured */
+#define AMDGPU_HAVE_CTX_SWITCH              (1 << 2)
+
+#define to_amdgpu_job(sched_job)		\
+		container_of((sched_job), struct amdgpu_job, base)
+
+struct amdgpu_fence;
+
+struct amdgpu_job {
+	struct drm_sched_job    base;
+	struct amdgpu_vm	*vm;
+	struct amdgpu_sync	sync;
+	struct amdgpu_sync	sched_sync;
+	struct amdgpu_ib	*ibs;
+	struct dma_fence	*fence; /* the hw fence */
+	uint32_t		preamble_status;
+	uint32_t		num_ibs;
+	void			*owner;
+	bool                    vm_needs_flush;
+	uint64_t		vm_pd_addr;
+	unsigned		vmid;
+	unsigned		pasid;
+	uint32_t		gds_base, gds_size;
+	uint32_t		gws_base, gws_size;
+	uint32_t		oa_base, oa_size;
+	uint32_t		vram_lost_counter;
+
+	/* user fence handling */
+	uint64_t		uf_addr;
+	uint64_t		uf_sequence;
+
+};
+
+int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
+		     struct amdgpu_job **job, struct amdgpu_vm *vm);
+int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
+			     struct amdgpu_job **job);
+
+void amdgpu_job_free_resources(struct amdgpu_job *job);
+void amdgpu_job_free(struct amdgpu_job *job);
+int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
+		      void *owner, struct dma_fence **f);
+int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
+			     struct dma_fence **fence);
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 2060f208e60b..c7dce14fd47d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -286,7 +286,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	struct drm_crtc *crtc;
 	uint32_t ui32 = 0;
 	uint64_t ui64 = 0;
-	int i, j, found;
+	int i, found;
 	int ui32_size = sizeof(ui32);
 
 	if (!info->return_size || !info->return_pointer)
@@ -328,64 +328,61 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		case AMDGPU_HW_IP_GFX:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_gfx_rings; i++)
-				ring_mask |= ((adev->gfx.gfx_ring[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->gfx.gfx_ring[i].ready << i;
 			ib_start_alignment = 32;
 			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_COMPUTE:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_compute_rings; i++)
-				ring_mask |= ((adev->gfx.compute_ring[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->gfx.compute_ring[i].ready << i;
 			ib_start_alignment = 32;
 			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_DMA:
 			type = AMD_IP_BLOCK_TYPE_SDMA;
 			for (i = 0; i < adev->sdma.num_instances; i++)
-				ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i);
+				ring_mask |= adev->sdma.instance[i].ring.ready << i;
 			ib_start_alignment = 256;
 			ib_size_alignment = 4;
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
-				ring_mask |= ((adev->uvd.inst[i].ring.ready ? 1 : 0) << i);
+			ring_mask |= adev->uvd.inst[0].ring.ready;
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCE:
 			type = AMD_IP_BLOCK_TYPE_VCE;
 			for (i = 0; i < adev->vce.num_rings; i++)
-				ring_mask |= ((adev->vce.ring[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->vce.ring[i].ready << i;
 			ib_start_alignment = 4;
 			ib_size_alignment = 1;
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
-				for (j = 0; j < adev->uvd.num_enc_rings; j++)
-					ring_mask |=
-					((adev->uvd.inst[i].ring_enc[j].ready ? 1 : 0) <<
-					(j + i * adev->uvd.num_enc_rings));
+			for (i = 0; i < adev->uvd.num_enc_rings; i++)
+				ring_mask |=
+					adev->uvd.inst[0].ring_enc[i].ready << i;
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
-			ring_mask = adev->vcn.ring_dec.ready ? 1 : 0;
+			ring_mask = adev->vcn.ring_dec.ready;
 			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
 		case AMDGPU_HW_IP_VCN_ENC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			for (i = 0; i < adev->vcn.num_enc_rings; i++)
-				ring_mask |= ((adev->vcn.ring_enc[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->vcn.ring_enc[i].ready << i;
 			ib_start_alignment = 64;
 			ib_size_alignment = 1;
 			break;
 		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
-			ring_mask = adev->vcn.ring_jpeg.ready ? 1 : 0;
+			ring_mask = adev->vcn.ring_jpeg.ready;
 			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
@@ -501,13 +498,13 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	case AMDGPU_INFO_VRAM_GTT: {
 		struct drm_amdgpu_info_vram_gtt vram_gtt;
 
-		vram_gtt.vram_size = adev->gmc.real_vram_size;
-		vram_gtt.vram_size -= adev->vram_pin_size;
-		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size;
-		vram_gtt.vram_cpu_accessible_size -= (adev->vram_pin_size - adev->invisible_pin_size);
+		vram_gtt.vram_size = adev->gmc.real_vram_size -
+			atomic64_read(&adev->vram_pin_size);
+		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size -
+			atomic64_read(&adev->visible_pin_size);
 		vram_gtt.gtt_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		vram_gtt.gtt_size *= PAGE_SIZE;
-		vram_gtt.gtt_size -= adev->gart_pin_size;
+		vram_gtt.gtt_size -= atomic64_read(&adev->gart_pin_size);
 		return copy_to_user(out, &vram_gtt,
 				    min((size_t)size, sizeof(vram_gtt))) ? -EFAULT : 0;
 	}
@@ -516,17 +513,16 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		memset(&mem, 0, sizeof(mem));
 		mem.vram.total_heap_size = adev->gmc.real_vram_size;
-		mem.vram.usable_heap_size =
-			adev->gmc.real_vram_size - adev->vram_pin_size;
+		mem.vram.usable_heap_size = adev->gmc.real_vram_size -
+			atomic64_read(&adev->vram_pin_size);
 		mem.vram.heap_usage =
 			amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.vram.max_allocation = mem.vram.usable_heap_size * 3 / 4;
 
 		mem.cpu_accessible_vram.total_heap_size =
 			adev->gmc.visible_vram_size;
-		mem.cpu_accessible_vram.usable_heap_size =
-			adev->gmc.visible_vram_size -
-			(adev->vram_pin_size - adev->invisible_pin_size);
+		mem.cpu_accessible_vram.usable_heap_size = adev->gmc.visible_vram_size -
+			atomic64_read(&adev->visible_pin_size);
 		mem.cpu_accessible_vram.heap_usage =
 			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.cpu_accessible_vram.max_allocation =
@@ -534,8 +530,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		mem.gtt.total_heap_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		mem.gtt.total_heap_size *= PAGE_SIZE;
-		mem.gtt.usable_heap_size = mem.gtt.total_heap_size
-			- adev->gart_pin_size;
+		mem.gtt.usable_heap_size = mem.gtt.total_heap_size -
+			atomic64_read(&adev->gart_pin_size);
 		mem.gtt.heap_usage =
 			amdgpu_gtt_mgr_usage(&adev->mman.bdev.man[TTM_PL_TT]);
 		mem.gtt.max_allocation = mem.gtt.usable_heap_size * 3 / 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 72a3e8c68876..a365ea2383d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -58,7 +58,8 @@
  *
  * @adev: amdgpu device pointer
  * @mm: process address space
- * @mn: MMU notifier structur
+ * @mn: MMU notifier structure
+ * @type: type of MMU notifier
  * @work: destruction work item
  * @node: hash table node to find structure by adev and mn
  * @lock: rw semaphore protecting the notifier nodes
@@ -266,7 +267,7 @@ static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
  * amdgpu_mn_invalidate_range_start_hsa - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 512f59836436..21bfa2d8039e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -51,7 +51,7 @@
  *
  */
 
-static bool amdgpu_need_backup(struct amdgpu_device *adev)
+static bool amdgpu_bo_need_backup(struct amdgpu_device *adev)
 {
 	if (adev->flags & AMD_IS_APU)
 		return false;
@@ -63,11 +63,35 @@ static bool amdgpu_need_backup(struct amdgpu_device *adev)
 	return true;
 }
 
-static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
+/**
+ * amdgpu_bo_subtract_pin_size - Remove BO from pin_size accounting
+ *
+ * @bo: &amdgpu_bo buffer object
+ *
+ * This function is called when a BO stops being pinned, and updates the
+ * &amdgpu_device pin_size values accordingly.
+ */
+static void amdgpu_bo_subtract_pin_size(struct amdgpu_bo *bo)
+{
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
+		atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
+	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
+		atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
+	}
+}
+
+static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
 
+	if (bo->pin_count > 0)
+		amdgpu_bo_subtract_pin_size(bo);
+
 	if (bo->kfd_bo)
 		amdgpu_amdkfd_unreserve_system_memory_limit(bo);
 
@@ -87,7 +111,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 }
 
 /**
- * amdgpu_ttm_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo
+ * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo
  * @bo: buffer object to be checked
  *
  * Uses destroy function associated with the object to determine if this is
@@ -96,22 +120,22 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
  * Returns:
  * true if the object belongs to &amdgpu_bo, false if not.
  */
-bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
+bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 {
-	if (bo->destroy == &amdgpu_ttm_bo_destroy)
+	if (bo->destroy == &amdgpu_bo_destroy)
 		return true;
 	return false;
 }
 
 /**
- * amdgpu_ttm_placement_from_domain - set buffer's placement
+ * amdgpu_bo_placement_from_domain - set buffer's placement
  * @abo: &amdgpu_bo buffer object whose placement is to be set
  * @domain: requested domain
  *
  * Sets buffer's placement according to requested domain and the buffer's
  * flags.
  */
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
+void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
 	struct ttm_placement *placement = &abo->placement;
@@ -192,6 +216,8 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
+	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+
 	placement->num_placement = c;
 	placement->placement = places;
 
@@ -252,22 +278,33 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 		goto error_free;
 	}
 
-	r = amdgpu_bo_pin(*bo_ptr, domain, gpu_addr);
+	r = amdgpu_bo_pin(*bo_ptr, domain);
 	if (r) {
 		dev_err(adev->dev, "(%d) kernel bo pin failed\n", r);
 		goto error_unreserve;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&(*bo_ptr)->tbo);
+	if (r) {
+		dev_err(adev->dev, "%p bind failed\n", *bo_ptr);
+		goto error_unpin;
+	}
+
+	if (gpu_addr)
+		*gpu_addr = amdgpu_bo_gpu_offset(*bo_ptr);
+
 	if (cpu_addr) {
 		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
 		if (r) {
 			dev_err(adev->dev, "(%d) kernel bo map failed\n", r);
-			goto error_unreserve;
+			goto error_unpin;
 		}
 	}
 
 	return 0;
 
+error_unpin:
+	amdgpu_bo_unpin(*bo_ptr);
 error_unreserve:
 	amdgpu_bo_unreserve(*bo_ptr);
 
@@ -453,13 +490,13 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 #endif
 
 	bo->tbo.bdev = &adev->mman.bdev;
-	amdgpu_ttm_placement_from_domain(bo, bp->domain);
+	amdgpu_bo_placement_from_domain(bo, bp->domain);
 	if (bp->type == ttm_bo_type_kernel)
 		bo->tbo.priority = 1;
 
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type,
 				 &bo->placement, page_align, &ctx, acc_size,
-				 NULL, bp->resv, &amdgpu_ttm_bo_destroy);
+				 NULL, bp->resv, &amdgpu_bo_destroy);
 	if (unlikely(r != 0))
 		return r;
 
@@ -559,7 +596,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) {
+	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_bo_need_backup(adev)) {
 		if (!bp->resv)
 			WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv,
 							NULL));
@@ -647,7 +684,7 @@ int amdgpu_bo_validate(struct amdgpu_bo *bo)
 	domain = bo->preferred_domains;
 
 retry:
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
 		domain = bo->allowed_domains;
@@ -817,7 +854,6 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
  * @domain: domain to be pinned to
  * @min_offset: the start of requested address range
  * @max_offset: the end of requested address range
- * @gpu_addr: GPU offset of the &amdgpu_bo buffer object
  *
  * Pins the buffer object according to requested domain and address range. If
  * the memory is unbound gart memory, binds the pages into gart table. Adjusts
@@ -835,8 +871,7 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
  * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
-			     u64 min_offset, u64 max_offset,
-			     u64 *gpu_addr)
+			     u64 min_offset, u64 max_offset)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_operation_ctx ctx = { false, false };
@@ -868,8 +903,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			return -EINVAL;
 
 		bo->pin_count++;
-		if (gpu_addr)
-			*gpu_addr = amdgpu_bo_gpu_offset(bo);
 
 		if (max_offset != 0) {
 			u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset;
@@ -884,7 +917,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	/* force to pin into visible video ram */
 	if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
 		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		unsigned fpfn, lpfn;
 
@@ -905,22 +938,15 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		goto error;
 	}
 
-	r = amdgpu_ttm_alloc_gart(&bo->tbo);
-	if (unlikely(r)) {
-		dev_err(adev->dev, "%p bind failed\n", bo);
-		goto error;
-	}
-
 	bo->pin_count = 1;
-	if (gpu_addr != NULL)
-		*gpu_addr = amdgpu_bo_gpu_offset(bo);
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
-		adev->vram_pin_size += amdgpu_bo_size(bo);
-		adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo);
+		atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
 	} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
-		adev->gart_pin_size += amdgpu_bo_size(bo);
+		atomic64_add(amdgpu_bo_size(bo), &adev->gart_pin_size);
 	}
 
 error:
@@ -931,7 +957,6 @@ error:
  * amdgpu_bo_pin - pin an &amdgpu_bo buffer object
  * @bo: &amdgpu_bo buffer object to be pinned
  * @domain: domain to be pinned to
- * @gpu_addr: GPU offset of the &amdgpu_bo buffer object
  *
  * A simple wrapper to amdgpu_bo_pin_restricted().
  * Provides a simpler API for buffers that do not have any strict restrictions
@@ -940,9 +965,9 @@ error:
  * Returns:
  * 0 for success or a negative error code on failure.
  */
-int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
+int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain)
 {
-	return amdgpu_bo_pin_restricted(bo, domain, 0, 0, gpu_addr);
+	return amdgpu_bo_pin_restricted(bo, domain, 0, 0);
 }
 
 /**
@@ -969,12 +994,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	if (bo->pin_count)
 		return 0;
 
-	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
-		adev->vram_pin_size -= amdgpu_bo_size(bo);
-		adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo);
-	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
-		adev->gart_pin_size -= amdgpu_bo_size(bo);
-	}
+	amdgpu_bo_subtract_pin_size(bo);
 
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		bo->placements[i].lpfn = 0;
@@ -1228,7 +1248,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	struct amdgpu_bo *abo;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return;
 
 	abo = ttm_to_amdgpu_bo(bo);
@@ -1245,7 +1265,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 		return;
 
 	/* move_notify is called before move happens */
-	trace_amdgpu_ttm_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
+	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
 /**
@@ -1267,7 +1287,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	unsigned long offset, size;
 	int r;
 
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return 0;
 
 	abo = ttm_to_amdgpu_bo(bo);
@@ -1289,8 +1309,8 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	/* hurrah the memory is not visible ! */
 	atomic64_inc(&adev->num_vram_cpu_page_faults);
-	amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
-					 AMDGPU_GEM_DOMAIN_GTT);
+	amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
+					AMDGPU_GEM_DOMAIN_GTT);
 
 	/* Avoid costly evictions; only set GTT as a busy placement */
 	abo->placement.num_busy_placement = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 731748033878..18945dd6982d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -32,6 +32,7 @@
 #include "amdgpu.h"
 
 #define AMDGPU_BO_INVALID_OFFSET	LONG_MAX
+#define AMDGPU_BO_MAX_PLACEMENTS	3
 
 struct amdgpu_bo_param {
 	unsigned long			size;
@@ -77,7 +78,7 @@ struct amdgpu_bo {
 	/* Protected by tbo.reserved */
 	u32				preferred_domains;
 	u32				allowed_domains;
-	struct ttm_place		placements[AMDGPU_GEM_DOMAIN_MAX + 1];
+	struct ttm_place		placements[AMDGPU_BO_MAX_PLACEMENTS];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
@@ -234,6 +235,9 @@ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
 	return bo->flags & AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
 }
 
+bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
+void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
+
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr);
@@ -252,10 +256,9 @@ void *amdgpu_bo_kptr(struct amdgpu_bo *bo);
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo);
 struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo);
 void amdgpu_bo_unref(struct amdgpu_bo **bo);
-int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr);
+int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain);
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
-			     u64 min_offset, u64 max_offset,
-			     u64 *gpu_addr);
+			     u64 min_offset, u64 max_offset);
 int amdgpu_bo_unpin(struct amdgpu_bo *bo);
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev);
 int amdgpu_bo_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 113edffb5960..15a1192c1ec5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -606,40 +606,59 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 		return snprintf(buf, PAGE_SIZE, "\n");
 }
 
-static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf,
-		size_t count)
+/*
+ * Worst case: 32 bits individually specified, in octal at 12 characters
+ * per line (+1 for \n).
+ */
+#define AMDGPU_MASK_BUF_MAX	(32 * 13)
+
+static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask)
 {
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
 	long level;
-	uint32_t mask = 0;
 	char *sub_str = NULL;
 	char *tmp;
-	char buf_cpy[count];
+	char buf_cpy[AMDGPU_MASK_BUF_MAX + 1];
 	const char delimiter[3] = {' ', '\n', '\0'};
+	size_t bytes;
 
-	memcpy(buf_cpy, buf, count+1);
+	*mask = 0;
+
+	bytes = min(count, sizeof(buf_cpy) - 1);
+	memcpy(buf_cpy, buf, bytes);
+	buf_cpy[bytes] = '\0';
 	tmp = buf_cpy;
 	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
+		sub_str = strsep(&tmp, delimiter);
 		if (strlen(sub_str)) {
 			ret = kstrtol(sub_str, 0, &level);
-
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
+			if (ret)
+				return -EINVAL;
+			*mask |= 1 << level;
 		} else
 			break;
 	}
+
+	return 0;
+}
+
+static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t count)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int ret;
+	uint32_t mask = 0;
+
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
+
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
-fail:
 	return count;
 }
 
@@ -664,32 +683,15 @@ 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;
-	long level;
 	uint32_t mask = 0;
-	char *sub_str = NULL;
-	char *tmp;
-	char buf_cpy[count];
-	const char delimiter[3] = {' ', '\n', '\0'};
 
-	memcpy(buf_cpy, buf, count+1);
-	tmp = buf_cpy;
-	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
-		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
 
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
-		} else
-			break;
-	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
-fail:
 	return count;
 }
 
@@ -714,33 +716,15 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
-	long level;
 	uint32_t mask = 0;
-	char *sub_str = NULL;
-	char *tmp;
-	char buf_cpy[count];
-	const char delimiter[3] = {' ', '\n', '\0'};
-
-	memcpy(buf_cpy, buf, count+1);
-	tmp = buf_cpy;
 
-	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
-		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
 
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
-		} else
-			break;
-	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
 
-fail:
 	return count;
 }
 
@@ -918,6 +902,36 @@ fail:
 	return -EINVAL;
 }
 
+/**
+ * DOC: busy_percent
+ *
+ * The amdgpu driver provides a sysfs API for reading how busy the GPU
+ * is as a percentage.  The file gpu_busy_percent is used for this.
+ * The SMU firmware computes a percentage of load based on the
+ * aggregate activity level in the IP cores.
+ */
+static ssize_t amdgpu_get_busy_percent(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int r, value, size = sizeof(value);
+
+	/* sanity check PP is enabled */
+	if (!(adev->powerplay.pp_funcs &&
+	      adev->powerplay.pp_funcs->read_sensor))
+		return -EINVAL;
+
+	/* read the IP busy sensor */
+	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_LOAD,
+				   (void *)&value, &size);
+	if (r)
+		return r;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", value);
+}
+
 static DEVICE_ATTR(power_dpm_state, S_IRUGO | S_IWUSR, amdgpu_get_dpm_state, amdgpu_set_dpm_state);
 static DEVICE_ATTR(power_dpm_force_performance_level, S_IRUGO | S_IWUSR,
 		   amdgpu_get_dpm_forced_performance_level,
@@ -951,6 +965,8 @@ static DEVICE_ATTR(pp_power_profile_mode, S_IRUGO | S_IWUSR,
 static DEVICE_ATTR(pp_od_clk_voltage, S_IRUGO | S_IWUSR,
 		amdgpu_get_pp_od_clk_voltage,
 		amdgpu_set_pp_od_clk_voltage);
+static DEVICE_ATTR(gpu_busy_percent, S_IRUGO,
+		amdgpu_get_busy_percent, NULL);
 
 static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
@@ -1697,10 +1713,10 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
 
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->powerplay.pp_funcs->powergate_uvd) {
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
 		/* enable/disable UVD */
 		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_powergate_uvd(adev, !enable);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
 		mutex_unlock(&adev->pm.mutex);
 	} else {
 		if (enable) {
@@ -1719,10 +1735,10 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->powerplay.pp_funcs->powergate_vce) {
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
 		/* enable/disable VCE */
 		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_powergate_vce(adev, !enable);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
 		mutex_unlock(&adev->pm.mutex);
 	} else {
 		if (enable) {
@@ -1854,6 +1870,13 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 				"pp_od_clk_voltage\n");
 		return ret;
 	}
+	ret = device_create_file(adev->dev,
+			&dev_attr_gpu_busy_percent);
+	if (ret) {
+		DRM_ERROR("failed to create device file	"
+				"gpu_busy_level\n");
+		return ret;
+	}
 	ret = amdgpu_debugfs_pm_init(adev);
 	if (ret) {
 		DRM_ERROR("Failed to register debugfs file for dpm!\n");
@@ -1889,6 +1912,7 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
 			&dev_attr_pp_power_profile_mode);
 	device_remove_file(adev->dev,
 			&dev_attr_pp_od_clk_voltage);
+	device_remove_file(adev->dev, &dev_attr_gpu_busy_percent);
 }
 
 void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
@@ -1919,7 +1943,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 		if (!amdgpu_device_has_dc_support(adev)) {
 			mutex_lock(&adev->pm.mutex);
 			amdgpu_dpm_get_active_displays(adev);
-			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtcs;
+			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count;
 			adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
 			adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
 			/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index b2286bc41aec..1c5d97f4b4dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -191,7 +191,6 @@ error:
 /**
  * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
  * @dma_buf: shared DMA buffer
- * @target_dev: target device
  * @attach: DMA-buf attachment
  *
  * Makes sure that the shared DMA buffer can be accessed by the target device.
@@ -233,7 +232,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 	}
 
 	/* pin buffer into GTT */
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r)
 		goto error_unreserve;
 
@@ -324,7 +323,7 @@ static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 		return ret;
 
 	if (!bo->pin_count && (bo->allowed_domains & AMDGPU_GEM_DOMAIN_GTT)) {
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index ea9850c9224d..d8357290ad09 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -66,8 +66,6 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 			       u32 ring,
 			       struct amdgpu_ring **out_ring)
 {
-	u32 instance;
-
 	switch (mapper->hw_ip) {
 	case AMDGPU_HW_IP_GFX:
 		*out_ring = &adev->gfx.gfx_ring[ring];
@@ -79,16 +77,13 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 		*out_ring = &adev->sdma.instance[ring].ring;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		instance = ring;
-		*out_ring = &adev->uvd.inst[instance].ring;
+		*out_ring = &adev->uvd.inst[0].ring;
 		break;
 	case AMDGPU_HW_IP_VCE:
 		*out_ring = &adev->vce.ring[ring];
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
-		instance = ring / adev->uvd.num_enc_rings;
-		*out_ring =
-		&adev->uvd.inst[instance].ring_enc[ring%adev->uvd.num_enc_rings];
+		*out_ring = &adev->uvd.inst[0].ring_enc[ring];
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		*out_ring = &adev->vcn.ring_dec;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 19e45a3953e0..93794a85f83d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -211,7 +211,8 @@ void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
 	if (!ring->funcs->set_priority)
 		return;
 
-	atomic_inc(&ring->num_jobs[priority]);
+	if (atomic_inc_return(&ring->num_jobs[priority]) <= 0)
+		return;
 
 	mutex_lock(&ring->priority_mutex);
 	if (priority <= ring->priority)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index a293f4e6760d..5018c0b6bf1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -44,6 +44,8 @@
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
 #define AMDGPU_FENCE_FLAG_TC_WB_ONLY    (1 << 2)
 
+#define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
+
 enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_GFX,
 	AMDGPU_RING_TYPE_COMPUTE,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index e3878256743a..8904e62dca7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright 2009 VMware, Inc.
  *
@@ -75,11 +76,12 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 	r = amdgpu_bo_reserve(vram_obj, false);
 	if (unlikely(r != 0))
 		goto out_unref;
-	r = amdgpu_bo_pin(vram_obj, AMDGPU_GEM_DOMAIN_VRAM, &vram_addr);
+	r = amdgpu_bo_pin(vram_obj, AMDGPU_GEM_DOMAIN_VRAM);
 	if (r) {
 		DRM_ERROR("Failed to pin VRAM object\n");
 		goto out_unres;
 	}
+	vram_addr = amdgpu_bo_gpu_offset(vram_obj);
 	for (i = 0; i < n; i++) {
 		void *gtt_map, *vram_map;
 		void **gart_start, **gart_end;
@@ -96,11 +98,17 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		r = amdgpu_bo_reserve(gtt_obj[i], false);
 		if (unlikely(r != 0))
 			goto out_lclean_unref;
-		r = amdgpu_bo_pin(gtt_obj[i], AMDGPU_GEM_DOMAIN_GTT, &gart_addr);
+		r = amdgpu_bo_pin(gtt_obj[i], AMDGPU_GEM_DOMAIN_GTT);
 		if (r) {
 			DRM_ERROR("Failed to pin GTT object %d\n", i);
 			goto out_lclean_unres;
 		}
+		r = amdgpu_ttm_alloc_gart(&gtt_obj[i]->tbo);
+		if (r) {
+			DRM_ERROR("%p bind failed\n", gtt_obj[i]);
+			goto out_lclean_unpin;
+		}
+		gart_addr = amdgpu_bo_gpu_offset(gtt_obj[i]);
 
 		r = amdgpu_bo_kmap(gtt_obj[i], &gtt_map);
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index e96e26d3f3b0..11f262f15200 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -150,10 +150,10 @@ TRACE_EVENT(amdgpu_cs,
 
 	    TP_fast_assign(
 			   __entry->bo_list = p->bo_list;
-			   __entry->ring = p->job->ring->idx;
+			   __entry->ring = p->ring->idx;
 			   __entry->dw = p->job->ibs[i].length_dw;
 			   __entry->fences = amdgpu_fence_count_emitted(
-				p->job->ring);
+				p->ring);
 			   ),
 	    TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
 		      __entry->bo_list, __entry->ring, __entry->dw,
@@ -178,7 +178,7 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = job->ring->name;
+			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -203,7 +203,7 @@ TRACE_EVENT(amdgpu_sched_run_job,
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = job->ring->name;
+			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -436,7 +436,7 @@ TRACE_EVENT(amdgpu_cs_bo_status,
 			__entry->total_bo, __entry->total_size)
 );
 
-TRACE_EVENT(amdgpu_ttm_bo_move,
+TRACE_EVENT(amdgpu_bo_move,
 	    TP_PROTO(struct amdgpu_bo* bo, uint32_t new_placement, uint32_t old_placement),
 	    TP_ARGS(bo, new_placement, old_placement),
 	    TP_STRUCT__entry(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 0c084d3d0865..8c4358e36c87 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -104,8 +104,6 @@ static void amdgpu_ttm_mem_global_release(struct drm_global_reference *ref)
 static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 {
 	struct drm_global_reference *global_ref;
-	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	int r;
 
 	/* ensure reference is false in case init fails */
@@ -138,21 +136,10 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 
 	mutex_init(&adev->mman.gtt_window_lock);
 
-	ring = adev->mman.buffer_funcs_ring;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-	r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
-				  rq, NULL);
-	if (r) {
-		DRM_ERROR("Failed setting up TTM BO move run queue.\n");
-		goto error_entity;
-	}
-
 	adev->mman.mem_global_referenced = true;
 
 	return 0;
 
-error_entity:
-	drm_global_item_unref(&adev->mman.bo_global_ref.ref);
 error_bo:
 	drm_global_item_unref(&adev->mman.mem_global_ref);
 error_mem:
@@ -162,8 +149,6 @@ error_mem:
 static void amdgpu_ttm_global_fini(struct amdgpu_device *adev)
 {
 	if (adev->mman.mem_global_referenced) {
-		drm_sched_entity_fini(adev->mman.entity.sched,
-				      &adev->mman.entity);
 		mutex_destroy(&adev->mman.gtt_window_lock);
 		drm_global_item_unref(&adev->mman.bo_global_ref.ref);
 		drm_global_item_unref(&adev->mman.mem_global_ref);
@@ -263,7 +248,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	}
 
 	/* Object isn't an AMDGPU object so ignore */
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo)) {
+	if (!amdgpu_bo_is_amdgpu_bo(bo)) {
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
@@ -276,7 +261,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	case TTM_PL_VRAM:
 		if (!adev->mman.buffer_funcs_enabled) {
 			/* Move to system memory */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
 		} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
 			   amdgpu_bo_in_cpu_visible_vram(abo)) {
@@ -286,7 +271,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 * BO will be evicted to GTT rather than causing other
 			 * BOs to be evicted from VRAM
 			 */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
 							 AMDGPU_GEM_DOMAIN_GTT);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
@@ -294,12 +279,12 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			abo->placement.num_busy_placement = 1;
 		} else {
 			/* Move to GTT memory */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
 		}
 		break;
 	case TTM_PL_TT:
 	default:
-		amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+		amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
 	}
 	*placement = abo->placement;
 }
@@ -1695,7 +1680,7 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 			AMDGPU_GEM_DOMAIN_VRAM,
 			adev->fw_vram_usage.start_offset,
 			(adev->fw_vram_usage.start_offset +
-			adev->fw_vram_usage.size), NULL);
+			adev->fw_vram_usage.size));
 		if (r)
 			goto error_pin;
 		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
@@ -1921,10 +1906,30 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 {
 	struct ttm_mem_type_manager *man = &adev->mman.bdev.man[TTM_PL_VRAM];
 	uint64_t size;
+	int r;
 
-	if (!adev->mman.initialized || adev->in_gpu_reset)
+	if (!adev->mman.initialized || adev->in_gpu_reset ||
+	    adev->mman.buffer_funcs_enabled == enable)
 		return;
 
+	if (enable) {
+		struct amdgpu_ring *ring;
+		struct drm_sched_rq *rq;
+
+		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);
+		if (r) {
+			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
+				  r);
+			return;
+		}
+	} else {
+		drm_sched_entity_destroy(&adev->mman.entity);
+		dma_fence_put(man->move);
+		man->move = NULL;
+	}
+
 	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
 	if (enable)
 		size = adev->gmc.real_vram_size;
@@ -2002,7 +2007,7 @@ static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
 	if (r)
 		goto error_free;
 
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
 	if (r)
 		goto error_free;
@@ -2071,24 +2076,19 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	if (direct_submit) {
-		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs,
-				       NULL, fence);
-		job->fence = dma_fence_get(*fence);
-		if (r)
-			DRM_ERROR("Error scheduling IBs (%d)\n", r);
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	if (direct_submit)
+		r = amdgpu_job_submit_direct(job, ring, fence);
+	else
+		r = amdgpu_job_submit(job, &adev->mman.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
-		if (r)
-			goto error_free;
-	}
+	if (r)
+		goto error_free;
 
 	return r;
 
 error_free:
 	amdgpu_job_free(job);
+	DRM_ERROR("Error scheduling IBs (%d)\n", r);
 	return r;
 }
 
@@ -2171,7 +2171,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
 	if (r)
 		goto error_free;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index e5da4654b630..8b3cc6687769 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -73,7 +73,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
 int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
 
-u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo);
+u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
 uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
 uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index cc15d3230402..fca86d71fafc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -53,11 +53,11 @@
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
-#define FIRMWARE_BONAIRE	"radeon/bonaire_uvd.bin"
-#define FIRMWARE_KABINI	"radeon/kabini_uvd.bin"
-#define FIRMWARE_KAVERI	"radeon/kaveri_uvd.bin"
-#define FIRMWARE_HAWAII	"radeon/hawaii_uvd.bin"
-#define FIRMWARE_MULLINS	"radeon/mullins_uvd.bin"
+#define FIRMWARE_BONAIRE	"amdgpu/bonaire_uvd.bin"
+#define FIRMWARE_KABINI	"amdgpu/kabini_uvd.bin"
+#define FIRMWARE_KAVERI	"amdgpu/kaveri_uvd.bin"
+#define FIRMWARE_HAWAII	"amdgpu/hawaii_uvd.bin"
+#define FIRMWARE_MULLINS	"amdgpu/mullins_uvd.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_uvd.bin"
 #define FIRMWARE_CARRIZO	"amdgpu/carrizo_uvd.bin"
@@ -263,21 +263,20 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 			dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
 			return r;
 		}
+	}
 
-		ring = &adev->uvd.inst[j].ring;
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity,
-					  rq, NULL);
-		if (r != 0) {
-			DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j);
-			return r;
-		}
-
-		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			atomic_set(&adev->uvd.inst[j].handles[i], 0);
-			adev->uvd.inst[j].filp[i] = NULL;
-		}
+	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);
+	if (r) {
+		DRM_ERROR("Failed setting up UVD kernel entity.\n");
+		return r;
 	}
+	for (i = 0; i < adev->uvd.max_handles; ++i) {
+		atomic_set(&adev->uvd.handles[i], 0);
+		adev->uvd.filp[i] = NULL;
+	}
+
 	/* from uvd v5.0 HW addressing capacity increased to 64 bits */
 	if (!amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
 		adev->uvd.address_64_bit = true;
@@ -306,11 +305,11 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
+	drm_sched_entity_destroy(&adev->uvd.entity);
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		kfree(adev->uvd.inst[j].saved_bo);
 
-		drm_sched_entity_fini(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity);
-
 		amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo,
 				      &adev->uvd.inst[j].gpu_addr,
 				      (void **)&adev->uvd.inst[j].cpu_addr);
@@ -333,20 +332,20 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 
 	cancel_delayed_work_sync(&adev->uvd.idle_work);
 
+	/* only valid for physical mode */
+	if (adev->asic_type < CHIP_POLARIS10) {
+		for (i = 0; i < adev->uvd.max_handles; ++i)
+			if (atomic_read(&adev->uvd.handles[i]))
+				break;
+
+		if (i == adev->uvd.max_handles)
+			return 0;
+	}
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		if (adev->uvd.inst[j].vcpu_bo == NULL)
 			continue;
 
-		/* only valid for physical mode */
-		if (adev->asic_type < CHIP_POLARIS10) {
-			for (i = 0; i < adev->uvd.max_handles; ++i)
-				if (atomic_read(&adev->uvd.inst[j].handles[i]))
-					break;
-
-			if (i == adev->uvd.max_handles)
-				continue;
-		}
-
 		size = amdgpu_bo_size(adev->uvd.inst[j].vcpu_bo);
 		ptr = adev->uvd.inst[j].cpu_addr;
 
@@ -398,30 +397,27 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 
 void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 {
-	struct amdgpu_ring *ring;
-	int i, j, r;
-
-	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-		ring = &adev->uvd.inst[j].ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst[0].ring;
+	int i, r;
 
-		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			uint32_t handle = atomic_read(&adev->uvd.inst[j].handles[i]);
-			if (handle != 0 && adev->uvd.inst[j].filp[i] == filp) {
-				struct dma_fence *fence;
-
-				r = amdgpu_uvd_get_destroy_msg(ring, handle,
-							       false, &fence);
-				if (r) {
-					DRM_ERROR("Error destroying UVD(%d) %d!\n", j, r);
-					continue;
-				}
+	for (i = 0; i < adev->uvd.max_handles; ++i) {
+		uint32_t handle = atomic_read(&adev->uvd.handles[i]);
 
-				dma_fence_wait(fence, false);
-				dma_fence_put(fence);
+		if (handle != 0 && adev->uvd.filp[i] == filp) {
+			struct dma_fence *fence;
 
-				adev->uvd.inst[j].filp[i] = NULL;
-				atomic_set(&adev->uvd.inst[j].handles[i], 0);
+			r = amdgpu_uvd_get_destroy_msg(ring, handle, false,
+						       &fence);
+			if (r) {
+				DRM_ERROR("Error destroying UVD %d!\n", r);
+				continue;
 			}
+
+			dma_fence_wait(fence, false);
+			dma_fence_put(fence);
+
+			adev->uvd.filp[i] = NULL;
+			atomic_set(&adev->uvd.handles[i], 0);
 		}
 	}
 }
@@ -476,7 +472,7 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx)
 		if (cmd == 0x0 || cmd == 0x3) {
 			/* yes, force it into VRAM */
 			uint32_t domain = AMDGPU_GEM_DOMAIN_VRAM;
-			amdgpu_ttm_placement_from_domain(bo, domain);
+			amdgpu_bo_placement_from_domain(bo, domain);
 		}
 		amdgpu_uvd_force_into_uvd_segment(bo);
 
@@ -696,16 +692,15 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	void *ptr;
 	long r;
 	int i;
-	uint32_t ip_instance = ctx->parser->job->ring->me;
 
 	if (offset & 0x3F) {
-		DRM_ERROR("UVD(%d) messages must be 64 byte aligned!\n", ip_instance);
+		DRM_ERROR("UVD messages must be 64 byte aligned!\n");
 		return -EINVAL;
 	}
 
 	r = amdgpu_bo_kmap(bo, &ptr);
 	if (r) {
-		DRM_ERROR("Failed mapping the UVD(%d) message (%ld)!\n", ip_instance, r);
+		DRM_ERROR("Failed mapping the UVD) message (%ld)!\n", r);
 		return r;
 	}
 
@@ -715,7 +710,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	handle = msg[2];
 
 	if (handle == 0) {
-		DRM_ERROR("Invalid UVD(%d) handle!\n", ip_instance);
+		DRM_ERROR("Invalid UVD handle!\n");
 		return -EINVAL;
 	}
 
@@ -726,18 +721,19 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* try to alloc a new handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
-				DRM_ERROR("(%d)Handle 0x%x already in use!\n", ip_instance, handle);
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				DRM_ERROR(")Handle 0x%x already in use!\n",
+					  handle);
 				return -EINVAL;
 			}
 
-			if (!atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], 0, handle)) {
-				adev->uvd.inst[ip_instance].filp[i] = ctx->parser->filp;
+			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
+				adev->uvd.filp[i] = ctx->parser->filp;
 				return 0;
 			}
 		}
 
-		DRM_ERROR("No more free UVD(%d) handles!\n", ip_instance);
+		DRM_ERROR("No more free UVD handles!\n");
 		return -ENOSPC;
 
 	case 1:
@@ -749,27 +745,27 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* validate the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
-				if (adev->uvd.inst[ip_instance].filp[i] != ctx->parser->filp) {
-					DRM_ERROR("UVD(%d) handle collision detected!\n", ip_instance);
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				if (adev->uvd.filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
 					return -EINVAL;
 				}
 				return 0;
 			}
 		}
 
-		DRM_ERROR("Invalid UVD(%d) handle 0x%x!\n", ip_instance, handle);
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
 		return -ENOENT;
 
 	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i)
-			atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], handle, 0);
+			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
 
 	default:
-		DRM_ERROR("Illegal UVD(%d) message type (%d)!\n", ip_instance, msg_type);
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
 		return -EINVAL;
 	}
 	BUG();
@@ -1017,7 +1013,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	if (!ring->adev->uvd.address_64_bit) {
 		struct ttm_operation_ctx ctx = { true, false };
 
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
 		amdgpu_uvd_force_into_uvd_segment(bo);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (r)
@@ -1062,19 +1058,16 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		if (r < 0)
 			goto err_free;
 
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
+		r = amdgpu_job_submit_direct(job, ring, &f);
 		if (r)
 			goto err_free;
-
-		amdgpu_job_free(job);
 	} else {
 		r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.resv,
 				     AMDGPU_FENCE_OWNER_UNDEFINED, false);
 		if (r)
 			goto err_free;
 
-		r = amdgpu_job_submit(job, ring, &adev->uvd.inst[ring->me].entity,
+		r = amdgpu_job_submit(job, &adev->uvd.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err_free;
@@ -1276,7 +1269,7 @@ uint32_t amdgpu_uvd_used_handles(struct amdgpu_device *adev)
 		 * necessarily linear. So we need to count
 		 * all non-zero handles.
 		 */
-		if (atomic_read(&adev->uvd.inst->handles[i]))
+		if (atomic_read(&adev->uvd.handles[i]))
 			used_handles++;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 8b23a1b00c76..66872286ab12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -42,13 +42,9 @@ struct amdgpu_uvd_inst {
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
 	void			*saved_bo;
-	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
-	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
 	struct amdgpu_ring	ring;
 	struct amdgpu_ring	ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
-	struct drm_sched_entity entity;
-	struct drm_sched_entity entity_enc;
 	uint32_t                srbm_soft_reset;
 };
 
@@ -57,10 +53,13 @@ struct amdgpu_uvd {
 	unsigned		fw_version;
 	unsigned		max_handles;
 	unsigned		num_enc_rings;
-	uint8_t		num_uvd_inst;
+	uint8_t			num_uvd_inst;
 	bool			address_64_bit;
 	bool			use_ctx_buf;
-	struct amdgpu_uvd_inst		inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct amdgpu_uvd_inst	inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
+	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
+	struct drm_sched_entity entity;
 	struct delayed_work	idle_work;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 23d960ec1cf2..b6ab4f5350c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -40,11 +40,11 @@
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
-#define FIRMWARE_BONAIRE	"radeon/bonaire_vce.bin"
-#define FIRMWARE_KABINI	"radeon/kabini_vce.bin"
-#define FIRMWARE_KAVERI	"radeon/kaveri_vce.bin"
-#define FIRMWARE_HAWAII	"radeon/hawaii_vce.bin"
-#define FIRMWARE_MULLINS	"radeon/mullins_vce.bin"
+#define FIRMWARE_BONAIRE	"amdgpu/bonaire_vce.bin"
+#define FIRMWARE_KABINI	"amdgpu/kabini_vce.bin"
+#define FIRMWARE_KAVERI	"amdgpu/kaveri_vce.bin"
+#define FIRMWARE_HAWAII	"amdgpu/hawaii_vce.bin"
+#define FIRMWARE_MULLINS	"amdgpu/mullins_vce.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_vce.bin"
 #define FIRMWARE_CARRIZO	"amdgpu/carrizo_vce.bin"
@@ -190,8 +190,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 
 	ring = &adev->vce.ring[0];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->vce.entity,
-				  rq, NULL);
+	r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
@@ -222,7 +221,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
-	drm_sched_entity_fini(&adev->vce.ring[0].sched, &adev->vce.entity);
+	drm_sched_entity_destroy(&adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
 		(void **)&adev->vce.cpu_addr);
@@ -470,12 +469,10 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -532,19 +529,13 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index a66cd521a875..798648a19710 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -211,6 +211,8 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		fences += amdgpu_fence_count_emitted(&adev->vcn.ring_enc[i]);
 	}
 
+	fences += amdgpu_fence_count_emitted(&adev->vcn.ring_jpeg);
+
 	if (fences == 0) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, false);
@@ -227,7 +229,7 @@ void amdgpu_vcn_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 && adev->pm.dpm_enabled) {
+	if (set_clocks) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, true);
 		else
@@ -306,13 +308,10 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
 	}
 	ib->length_dw = 16;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err_free;
 
-	amdgpu_job_free(job);
-
 	amdgpu_bo_fence(bo, f, false);
 	amdgpu_bo_unreserve(bo);
 	amdgpu_bo_unref(&bo);
@@ -497,12 +496,10 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -551,12 +548,10 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -664,12 +659,10 @@ static int amdgpu_vcn_jpeg_set_reg(struct amdgpu_ring *ring, uint32_t handle,
 	}
 	ib->length_dw = 16;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 422d1a434db4..9eedc9810004 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -156,6 +156,9 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 		return;
 	list_add_tail(&base->bo_list, &bo->va);
 
+	if (bo->tbo.type == ttm_bo_type_kernel)
+		list_move(&base->vm_status, &vm->relocated);
+
 	if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
 		return;
 
@@ -384,7 +387,7 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 		ats_entries = 0;
 	}
 
-	ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
 	r = reservation_object_reserve_shared(bo->tbo.resv);
 	if (r)
@@ -422,8 +425,8 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	r = amdgpu_job_submit(job, ring, &vm->entity,
-			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
+	r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_UNDEFINED,
+			      &fence);
 	if (r)
 		goto error_free;
 
@@ -492,11 +495,12 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 	eaddr = eaddr & ((1 << shift) - 1);
 
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	if (vm->root.base.bo->shadow)
+		flags |= AMDGPU_GEM_CREATE_SHADOW;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	else
-		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-				AMDGPU_GEM_CREATE_SHADOW);
+		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
 
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = from; pt_idx <= to; ++pt_idx) {
@@ -540,7 +544,6 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 			pt->parent = amdgpu_bo_ref(parent->base.bo);
 
 			amdgpu_vm_bo_base_init(&entry->base, vm, pt);
-			list_move(&entry->base.vm_status, &vm->relocated);
 		}
 
 		if (level < AMDGPU_VM_PTB) {
@@ -1082,7 +1085,7 @@ restart:
 					   struct amdgpu_vm_bo_base,
 					   vm_status);
 		bo_base->moved = false;
-		list_move(&bo_base->vm_status, &vm->idle);
+		list_del_init(&bo_base->vm_status);
 
 		bo = bo_base->bo->parent;
 		if (!bo)
@@ -1111,15 +1114,15 @@ restart:
 		struct amdgpu_ring *ring;
 		struct dma_fence *fence;
 
-		ring = container_of(vm->entity.sched, struct amdgpu_ring,
+		ring = container_of(vm->entity.rq->sched, struct amdgpu_ring,
 				    sched);
 
 		amdgpu_ring_pad_ib(ring, params.ib);
 		amdgpu_sync_resv(adev, &job->sync, root->tbo.resv,
 				 AMDGPU_FENCE_OWNER_VM, false);
 		WARN_ON(params.ib->length_dw > ndw);
-		r = amdgpu_job_submit(job, ring, &vm->entity,
-				      AMDGPU_FENCE_OWNER_VM, &fence);
+		r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_VM,
+				      &fence);
 		if (r)
 			goto error;
 
@@ -1401,7 +1404,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 					   addr, flags);
 	}
 
-	ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
 	nptes = last - start + 1;
 
@@ -1483,8 +1486,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 
 	amdgpu_ring_pad_ib(ring, params.ib);
 	WARN_ON(params.ib->length_dw > ndw);
-	r = amdgpu_job_submit(job, ring, &vm->entity,
-			      AMDGPU_FENCE_OWNER_VM, &f);
+	r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_VM, &f);
 	if (r)
 		goto error_free;
 
@@ -1567,7 +1569,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (nodes) {
 			addr = nodes->start << PAGE_SHIFT;
 			max_entries = (nodes->size - pfn) *
-				(PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+				AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 		} else {
 			addr = 0;
 			max_entries = S64_MAX;
@@ -1578,7 +1580,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 
 			max_entries = min(max_entries, 16ull * 1024ull);
 			for (count = 1;
-			     count < max_entries / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+			     count < max_entries / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			     ++count) {
 				uint64_t idx = pfn + count;
 
@@ -1592,7 +1594,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				dma_addr = pages_addr;
 			} else {
 				addr = pages_addr[pfn];
-				max_entries = count * (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+				max_entries = count * AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			}
 
 		} else if (flags & AMDGPU_PTE_VALID) {
@@ -1607,7 +1609,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (r)
 			return r;
 
-		pfn += (last - start + 1) / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+		pfn += (last - start + 1) / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 		if (nodes && nodes->size == pfn) {
 			pfn = 0;
 			++nodes;
@@ -1645,18 +1647,17 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	uint64_t flags;
 	int r;
 
-	if (clear || !bo_va->base.bo) {
+	if (clear || !bo) {
 		mem = NULL;
 		nodes = NULL;
 		exclusive = NULL;
 	} else {
 		struct ttm_dma_tt *ttm;
 
-		mem = &bo_va->base.bo->tbo.mem;
+		mem = &bo->tbo.mem;
 		nodes = mem->mm_node;
 		if (mem->mem_type == TTM_PL_TT) {
-			ttm = container_of(bo_va->base.bo->tbo.ttm,
-					   struct ttm_dma_tt, ttm);
+			ttm = container_of(bo->tbo.ttm, struct ttm_dma_tt, ttm);
 			pages_addr = ttm->dma_address;
 		}
 		exclusive = reservation_object_get_excl(bo->tbo.resv);
@@ -2562,8 +2563,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	ring_instance %= adev->vm_manager.vm_pte_num_rings;
 	ring = adev->vm_manager.vm_pte_rings[ring_instance];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-	r = drm_sched_entity_init(&ring->sched, &vm->entity,
-				  rq, NULL);
+	r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL);
 	if (r)
 		return r;
 
@@ -2588,7 +2588,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	else
+	else if (vm_context != AMDGPU_VM_CONTEXT_COMPUTE)
 		flags |= AMDGPU_GEM_CREATE_SHADOW;
 
 	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
@@ -2643,7 +2643,7 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_sched_entity:
-	drm_sched_entity_fini(&ring->sched, &vm->entity);
+	drm_sched_entity_destroy(&vm->entity);
 
 	return r;
 }
@@ -2663,8 +2663,7 @@ error_free_sched_entity:
  * - pasid (old PASID is released, because compute manages its own PASIDs)
  *
  * Reinitializes the page directory to reflect the changed ATS
- * setting. May leave behind an unused shadow BO for the page
- * directory when switching from SDMA updates to CPU updates.
+ * setting.
  *
  * Returns:
  * 0 for success, -errno for errors.
@@ -2714,6 +2713,9 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		vm->pasid = 0;
 	}
 
+	/* Free the shadow bo for compute VM */
+	amdgpu_bo_unref(&vm->root.base.bo->shadow);
+
 error:
 	amdgpu_bo_unreserve(vm->root.base.bo);
 	return r;
@@ -2780,7 +2782,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 
-	drm_sched_entity_fini(vm->entity.sched, &vm->entity);
+	drm_sched_entity_destroy(&vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
@@ -2942,3 +2944,42 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	return 0;
 }
+
+/**
+ * amdgpu_vm_get_task_info - Extracts task info for a PASID.
+ *
+ * @dev: drm device pointer
+ * @pasid: PASID identifier for VM
+ * @task_info: task_info to fill.
+ */
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+			 struct amdgpu_task_info *task_info)
+{
+	struct amdgpu_vm *vm;
+
+	spin_lock(&adev->vm_manager.pasid_lock);
+
+	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	if (vm)
+		*task_info = vm->task_info;
+
+	spin_unlock(&adev->vm_manager.pasid_lock);
+}
+
+/**
+ * amdgpu_vm_set_task_info - Sets VMs task info.
+ *
+ * @vm: vm for which to set the info
+ */
+void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
+{
+	if (!vm->task_info.pid) {
+		vm->task_info.pid = current->pid;
+		get_task_comm(vm->task_info.task_name, current);
+
+		if (current->group_leader->mm == current->mm) {
+			vm->task_info.tgid = current->group_leader->pid;
+			get_task_comm(vm->task_info.process_name, current->group_leader);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 061b99a18cb8..d416f895233d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -164,6 +164,14 @@ struct amdgpu_vm_pt {
 #define AMDGPU_VM_FAULT_PASID(fault) ((u64)(fault) >> 48)
 #define AMDGPU_VM_FAULT_ADDR(fault)  ((u64)(fault) & 0xfffffffff000ULL)
 
+
+struct amdgpu_task_info {
+	char	process_name[TASK_COMM_LEN];
+	char	task_name[TASK_COMM_LEN];
+	pid_t	pid;
+	pid_t	tgid;
+};
+
 struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
 	struct rb_root_cached	va;
@@ -215,6 +223,9 @@ struct amdgpu_vm {
 
 	/* Valid while the PD is reserved or fenced */
 	uint64_t		pd_phys_addr;
+
+	/* Some basic info about the task */
+	struct amdgpu_task_info task_info;
 };
 
 struct amdgpu_vm_manager {
@@ -317,4 +328,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+			 struct amdgpu_task_info *task_info);
+
+void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index b6333f92ba45..9cfa8a9ada92 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -97,33 +97,29 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_vram_mgr_bo_invisible_size - CPU invisible BO size
+ * amdgpu_vram_mgr_bo_visible_size - CPU visible BO size
  *
  * @bo: &amdgpu_bo buffer object (must be in VRAM)
  *
  * Returns:
- * How much of the given &amdgpu_bo buffer object lies in CPU invisible VRAM.
+ * How much of the given &amdgpu_bo buffer object lies in CPU visible VRAM.
  */
-u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo)
+u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_mem_reg *mem = &bo->tbo.mem;
 	struct drm_mm_node *nodes = mem->mm_node;
 	unsigned pages = mem->num_pages;
-	u64 usage = 0;
+	u64 usage;
 
-	if (adev->gmc.visible_vram_size == adev->gmc.real_vram_size)
-		return 0;
+	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
+		return amdgpu_bo_size(bo);
 
 	if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
-		return amdgpu_bo_size(bo);
+		return 0;
 
-	while (nodes && pages) {
-		usage += nodes->size << PAGE_SHIFT;
-		usage -= amdgpu_vram_mgr_vis_size(adev, nodes);
-		pages -= nodes->size;
-		++nodes;
-	}
+	for (usage = 0; nodes && pages; pages -= nodes->size, nodes++)
+		usage += amdgpu_vram_mgr_vis_size(adev, nodes);
 
 	return usage;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index b18c31a701e2..e9934de1b9cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -1221,7 +1221,7 @@ static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index,
 	ectx.abort = false;
 	ectx.last_jump = 0;
 	if (ws)
-		ectx.ws = kcalloc(4, ws, GFP_ATOMIC);
+		ectx.ws = kcalloc(4, ws, GFP_KERNEL);
 	else
 		ectx.ws = NULL;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index c9d45cffca56..d2469453dca2 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -49,10 +49,10 @@
 #include "gmc/gmc_7_1_d.h"
 #include "gmc/gmc_7_1_sh_mask.h"
 
-MODULE_FIRMWARE("radeon/bonaire_smc.bin");
-MODULE_FIRMWARE("radeon/bonaire_k_smc.bin");
-MODULE_FIRMWARE("radeon/hawaii_smc.bin");
-MODULE_FIRMWARE("radeon/hawaii_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_smc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_smc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_k_smc.bin");
 
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
@@ -5815,7 +5815,7 @@ static int ci_dpm_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
 	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -5846,8 +5846,7 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	adev->pm.dpm.priv = pi;
 
 	pi->sys_pcie_mask =
-		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
-		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+		adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK;
 
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
@@ -6767,6 +6766,19 @@ static int ci_dpm_read_sensor(void *handle, int idx,
 	}
 }
 
+static int ci_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+		ci_dpm_powergate_uvd(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 static const struct amd_ip_funcs ci_dpm_ip_funcs = {
 	.name = "ci_dpm",
 	.early_init = ci_dpm_early_init,
@@ -6804,7 +6816,7 @@ static const struct amd_pm_funcs ci_dpm_funcs = {
 	.debugfs_print_current_performance_level = &ci_dpm_debugfs_print_current_performance_level,
 	.force_performance_level = &ci_dpm_force_performance_level,
 	.vblank_too_short = &ci_dpm_vblank_too_short,
-	.powergate_uvd = &ci_dpm_powergate_uvd,
+	.set_powergating_by_smu = &ci_set_powergating_by_smu,
 	.set_fan_control_mode = &ci_dpm_set_fan_control_mode,
 	.get_fan_control_mode = &ci_dpm_get_fan_control_mode,
 	.set_fan_speed_percent = &ci_dpm_set_fan_speed_percent,
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 702e257a483f..78ab939ae5d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1476,7 +1476,7 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev)
 				tmp |= PCIE_LC_CNTL4__LC_REDO_EQ_MASK;
 				WREG32_PCIE(ixPCIE_LC_CNTL4, tmp);
 
-				mdelay(100);
+				msleep(100);
 
 				/* linkctl */
 				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL, &tmp16);
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index a7576255cc30..d0fa2aac2388 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -54,16 +54,16 @@ static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
 static int cik_sdma_soft_reset(void *handle);
 
-MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
-MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
-MODULE_FIRMWARE("radeon/hawaii_sdma.bin");
-MODULE_FIRMWARE("radeon/hawaii_sdma1.bin");
-MODULE_FIRMWARE("radeon/kaveri_sdma.bin");
-MODULE_FIRMWARE("radeon/kaveri_sdma1.bin");
-MODULE_FIRMWARE("radeon/kabini_sdma.bin");
-MODULE_FIRMWARE("radeon/kabini_sdma1.bin");
-MODULE_FIRMWARE("radeon/mullins_sdma.bin");
-MODULE_FIRMWARE("radeon/mullins_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_sdma.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_sdma.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_sdma.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/kabini_sdma.bin");
+MODULE_FIRMWARE("amdgpu/kabini_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/mullins_sdma.bin");
+MODULE_FIRMWARE("amdgpu/mullins_sdma1.bin");
 
 u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev);
 
@@ -132,9 +132,9 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		if (i == 0)
-			snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name);
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
 		else
-			snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma1.bin", chip_name);
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
 		err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
 		if (err)
 			goto out;
@@ -177,9 +177,8 @@ static uint64_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-	return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) & 0x3fffc) >> 2;
+	return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) & 0x3fffc) >> 2;
 }
 
 /**
@@ -192,9 +191,8 @@ static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
 static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me],
+	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me],
 		       	(lower_32_bits(ring->wptr) << 2) & 0x3fffc);
 }
 
@@ -248,7 +246,7 @@ static void cik_sdma_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
 	u32 ref_and_mask;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA0_MASK;
 	else
 		ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA1_MASK;
@@ -1290,8 +1288,10 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &cik_sdma_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs cik_sdma_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index ada241bfeee9..308f9f238bc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -41,6 +41,8 @@
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void dce_v10_0_set_display_funcs(struct amdgpu_device *adev);
 static void dce_v10_0_set_irq_funcs(struct amdgpu_device *adev);
 
@@ -1855,15 +1857,14 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2370,13 +2371,14 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v10_0_lock_cursor(crtc, true);
 
@@ -2737,14 +2739,14 @@ static int dce_v10_0_sw_init(void *handle)
 			return r;
 	}
 
-	for (i = 8; i < 20; i += 2) {
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) {
 		r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i, &adev->pageflip_irq);
 		if (r)
 			return r;
 	}
 
 	/* HPD hotplug */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 42, &adev->hpd_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index a5b96eac3033..76dfb76f7900 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -41,6 +41,8 @@
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void dce_v11_0_set_display_funcs(struct amdgpu_device *adev);
 static void dce_v11_0_set_irq_funcs(struct amdgpu_device *adev);
 
@@ -1897,15 +1899,14 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2449,13 +2450,14 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v11_0_lock_cursor(crtc, true);
 
@@ -2858,14 +2860,14 @@ static int dce_v11_0_sw_init(void *handle)
 			return r;
 	}
 
-	for (i = 8; i < 20; i += 2) {
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) {
 		r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i, &adev->pageflip_irq);
 		if (r)
 			return r;
 	}
 
 	/* HPD hotplug */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 42, &adev->hpd_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 394cc1e8fe20..c9adc627305d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1811,15 +1811,14 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2263,13 +2262,14 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v6_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index c9b9ab8f1b05..50cd03beac7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1786,15 +1786,14 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2274,13 +2273,14 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v8_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index dbf2ccd0c744..15257634a53a 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -36,6 +36,7 @@
 #include "dce_v10_0.h"
 #include "dce_v11_0.h"
 #include "dce_virtual.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 #define DCE_VIRTUAL_VBLANK_PERIOD 16666666
 
@@ -269,25 +270,18 @@ static int dce_virtual_early_init(void *handle)
 static struct drm_encoder *
 dce_virtual_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL)
 			return encoder;
 	}
 
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -378,7 +372,7 @@ static int dce_virtual_sw_init(void *handle)
 	int r, i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 229, &adev->crtc_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER, &adev->crtc_irq);
 	if (r)
 		return r;
 
@@ -634,7 +628,7 @@ static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 	drm_connector_register(connector);
 
 	/* link them */
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	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 cd6bf291a853..de184a886057 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -44,30 +44,30 @@ static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/tahiti_pfp.bin");
-MODULE_FIRMWARE("radeon/tahiti_me.bin");
-MODULE_FIRMWARE("radeon/tahiti_ce.bin");
-MODULE_FIRMWARE("radeon/tahiti_rlc.bin");
-
-MODULE_FIRMWARE("radeon/pitcairn_pfp.bin");
-MODULE_FIRMWARE("radeon/pitcairn_me.bin");
-MODULE_FIRMWARE("radeon/pitcairn_ce.bin");
-MODULE_FIRMWARE("radeon/pitcairn_rlc.bin");
-
-MODULE_FIRMWARE("radeon/verde_pfp.bin");
-MODULE_FIRMWARE("radeon/verde_me.bin");
-MODULE_FIRMWARE("radeon/verde_ce.bin");
-MODULE_FIRMWARE("radeon/verde_rlc.bin");
-
-MODULE_FIRMWARE("radeon/oland_pfp.bin");
-MODULE_FIRMWARE("radeon/oland_me.bin");
-MODULE_FIRMWARE("radeon/oland_ce.bin");
-MODULE_FIRMWARE("radeon/oland_rlc.bin");
-
-MODULE_FIRMWARE("radeon/hainan_pfp.bin");
-MODULE_FIRMWARE("radeon/hainan_me.bin");
-MODULE_FIRMWARE("radeon/hainan_ce.bin");
-MODULE_FIRMWARE("radeon/hainan_rlc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_pfp.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_me.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_ce.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/pitcairn_pfp.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_me.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_ce.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/verde_pfp.bin");
+MODULE_FIRMWARE("amdgpu/verde_me.bin");
+MODULE_FIRMWARE("amdgpu/verde_ce.bin");
+MODULE_FIRMWARE("amdgpu/verde_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/oland_pfp.bin");
+MODULE_FIRMWARE("amdgpu/oland_me.bin");
+MODULE_FIRMWARE("amdgpu/oland_ce.bin");
+MODULE_FIRMWARE("amdgpu/oland_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/hainan_pfp.bin");
+MODULE_FIRMWARE("amdgpu/hainan_me.bin");
+MODULE_FIRMWARE("amdgpu/hainan_ce.bin");
+MODULE_FIRMWARE("amdgpu/hainan_rlc.bin");
 
 static u32 gfx_v6_0_get_csb_size(struct amdgpu_device *adev);
 static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer);
@@ -335,7 +335,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -346,7 +346,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -357,7 +357,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -368,7 +368,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 42b6144c1fd5..95452c5a9df6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -57,36 +57,36 @@ static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
-MODULE_FIRMWARE("radeon/bonaire_me.bin");
-MODULE_FIRMWARE("radeon/bonaire_ce.bin");
-MODULE_FIRMWARE("radeon/bonaire_rlc.bin");
-MODULE_FIRMWARE("radeon/bonaire_mec.bin");
-
-MODULE_FIRMWARE("radeon/hawaii_pfp.bin");
-MODULE_FIRMWARE("radeon/hawaii_me.bin");
-MODULE_FIRMWARE("radeon/hawaii_ce.bin");
-MODULE_FIRMWARE("radeon/hawaii_rlc.bin");
-MODULE_FIRMWARE("radeon/hawaii_mec.bin");
-
-MODULE_FIRMWARE("radeon/kaveri_pfp.bin");
-MODULE_FIRMWARE("radeon/kaveri_me.bin");
-MODULE_FIRMWARE("radeon/kaveri_ce.bin");
-MODULE_FIRMWARE("radeon/kaveri_rlc.bin");
-MODULE_FIRMWARE("radeon/kaveri_mec.bin");
-MODULE_FIRMWARE("radeon/kaveri_mec2.bin");
-
-MODULE_FIRMWARE("radeon/kabini_pfp.bin");
-MODULE_FIRMWARE("radeon/kabini_me.bin");
-MODULE_FIRMWARE("radeon/kabini_ce.bin");
-MODULE_FIRMWARE("radeon/kabini_rlc.bin");
-MODULE_FIRMWARE("radeon/kabini_mec.bin");
-
-MODULE_FIRMWARE("radeon/mullins_pfp.bin");
-MODULE_FIRMWARE("radeon/mullins_me.bin");
-MODULE_FIRMWARE("radeon/mullins_ce.bin");
-MODULE_FIRMWARE("radeon/mullins_rlc.bin");
-MODULE_FIRMWARE("radeon/mullins_mec.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_pfp.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_me.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_ce.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_rlc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/hawaii_pfp.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_me.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_ce.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_rlc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/kaveri_pfp.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_me.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_ce.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_rlc.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_mec.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_mec2.bin");
+
+MODULE_FIRMWARE("amdgpu/kabini_pfp.bin");
+MODULE_FIRMWARE("amdgpu/kabini_me.bin");
+MODULE_FIRMWARE("amdgpu/kabini_ce.bin");
+MODULE_FIRMWARE("amdgpu/kabini_rlc.bin");
+MODULE_FIRMWARE("amdgpu/kabini_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/mullins_pfp.bin");
+MODULE_FIRMWARE("amdgpu/mullins_me.bin");
+MODULE_FIRMWARE("amdgpu/mullins_ce.bin");
+MODULE_FIRMWARE("amdgpu/mullins_rlc.bin");
+MODULE_FIRMWARE("amdgpu/mullins_mec.bin");
 
 static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
 {
@@ -925,7 +925,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -933,7 +933,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -941,7 +941,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -949,7 +949,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -958,7 +958,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 		goto out;
 
 	if (adev->asic_type == CHIP_KAVERI) {
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec2.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
 		err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 		if (err)
 			goto out;
@@ -967,7 +967,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 			goto out;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 807ee0dd623c..5cd45210113f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -51,6 +51,8 @@
 
 #include "smu/smu_7_1_3_d.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_MEC_HPD_SIZE 2048
 
@@ -704,6 +706,17 @@ static const u32 stoney_mgcg_cgcg_init[] =
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96940200,
 };
 
+
+static const char * const sq_edc_source_names[] = {
+	"SQ_EDC_INFO_SOURCE_INVALID: No EDC error has occurred",
+	"SQ_EDC_INFO_SOURCE_INST: EDC source is Instruction Fetch",
+	"SQ_EDC_INFO_SOURCE_SGPR: EDC source is SGPR or SQC data return",
+	"SQ_EDC_INFO_SOURCE_VGPR: EDC source is VGPR",
+	"SQ_EDC_INFO_SOURCE_LDS: EDC source is LDS",
+	"SQ_EDC_INFO_SOURCE_GDS: EDC source is GDS",
+	"SQ_EDC_INFO_SOURCE_TA: EDC source is TA",
+};
+
 static void gfx_v8_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev);
@@ -2006,6 +2019,8 @@ static int gfx_v8_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 	return 0;
 }
 
+static void gfx_v8_0_sq_irq_work_func(struct work_struct *work);
+
 static int gfx_v8_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id;
@@ -2034,41 +2049,43 @@ static int gfx_v8_0_sw_init(void *handle)
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
 	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 178, &adev->gfx.kiq.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_INT_IB2, &adev->gfx.kiq.irq);
 	if (r)
 		return r;
 
 	/* EOP Event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 181, &adev->gfx.eop_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_END_OF_PIPE, &adev->gfx.eop_irq);
 	if (r)
 		return r;
 
 	/* Privileged reg */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 184,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_PRIV_REG_FAULT,
 			      &adev->gfx.priv_reg_irq);
 	if (r)
 		return r;
 
 	/* Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 185,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_PRIV_INSTR_FAULT,
 			      &adev->gfx.priv_inst_irq);
 	if (r)
 		return r;
 
 	/* Add CP EDC/ECC irq  */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 197,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_ECC_ERROR,
 			      &adev->gfx.cp_ecc_error_irq);
 	if (r)
 		return r;
 
 	/* SQ interrupts. */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 239,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SQ_INTERRUPT_MSG,
 			      &adev->gfx.sq_irq);
 	if (r) {
 		DRM_ERROR("amdgpu_irq_add() for SQ failed: %d\n", r);
 		return r;
 	}
 
+	INIT_WORK(&adev->gfx.sq_work.work, gfx_v8_0_sq_irq_work_func);
+
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
 	gfx_v8_0_scratch_init(adev);
@@ -5581,24 +5598,18 @@ static int gfx_v8_0_late_init(void *handle)
 		return r;
 	}
 
-	amdgpu_device_ip_set_powergating_state(adev,
-					       AMD_IP_BLOCK_TYPE_GFX,
-					       AMD_PG_STATE_GATE);
-
 	return 0;
 }
 
 static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
 						       bool enable)
 {
-	if ((adev->asic_type == CHIP_POLARIS11) ||
+	if (((adev->asic_type == CHIP_POLARIS11) ||
 	    (adev->asic_type == CHIP_POLARIS12) ||
-	    (adev->asic_type == CHIP_VEGAM))
+	    (adev->asic_type == CHIP_VEGAM)) &&
+	    adev->powerplay.pp_funcs->set_powergating_by_smu)
 		/* Send msg to SMU via Powerplay */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       enable ?
-						       AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, enable);
 
 	WREG32_FIELD(RLC_PG_CNTL, STATIC_PER_CU_PG_ENABLE, enable ? 1 : 0);
 }
@@ -6955,16 +6966,14 @@ static int gfx_v8_0_cp_ecc_error_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
-			   struct amdgpu_irq_src *source,
-			   struct amdgpu_iv_entry *entry)
+static void gfx_v8_0_parse_sq_irq(struct amdgpu_device *adev, unsigned ih_data)
 {
-	u8 enc, se_id;
+	u32 enc, se_id, sh_id, cu_id;
 	char type[20];
+	int sq_edc_source = -1;
 
-	/* Parse all fields according to SQ_INTERRUPT* registers */
-	enc = (entry->src_data[0] >> 26) & 0x3;
-	se_id = (entry->src_data[0] >> 24) & 0x3;
+	enc = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, ENCODING);
+	se_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, SE_ID);
 
 	switch (enc) {
 		case 0:
@@ -6974,19 +6983,37 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 					"reg_timestamp %d, thread_trace_buff_full %d,"
 					"wlt %d, thread_trace %d.\n",
 					se_id,
-					(entry->src_data[0] >> 7) & 0x1,
-					(entry->src_data[0] >> 6) & 0x1,
-					(entry->src_data[0] >> 5) & 0x1,
-					(entry->src_data[0] >> 4) & 0x1,
-					(entry->src_data[0] >> 3) & 0x1,
-					(entry->src_data[0] >> 2) & 0x1,
-					(entry->src_data[0] >> 1) & 0x1,
-					entry->src_data[0] & 0x1
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, IMMED_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, HOST_REG_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, HOST_CMD_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, CMD_TIMESTAMP),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, REG_TIMESTAMP),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, THREAD_TRACE_BUF_FULL),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, WLT),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, THREAD_TRACE)
 					);
 			break;
 		case 1:
 		case 2:
 
+			cu_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, CU_ID);
+			sh_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SH_ID);
+
+			/*
+			 * This function can be called either directly from ISR
+			 * or from BH in which case we can access SQ_EDC_INFO
+			 * instance
+			 */
+			if (in_task()) {
+				mutex_lock(&adev->grbm_idx_mutex);
+				gfx_v8_0_select_se_sh(adev, se_id, sh_id, cu_id);
+
+				sq_edc_source = REG_GET_FIELD(RREG32(mmSQ_EDC_INFO), SQ_EDC_INFO, SOURCE);
+
+				gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+				mutex_unlock(&adev->grbm_idx_mutex);
+			}
+
 			if (enc == 1)
 				sprintf(type, "instruction intr");
 			else
@@ -6994,17 +7021,46 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 
 			DRM_INFO(
 				"SQ %s detected: "
-					"se_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d\n",
-					type, se_id,
-					(entry->src_data[0] >> 20) & 0xf,
-					(entry->src_data[0] >> 18) & 0x3,
-					(entry->src_data[0] >> 14) & 0xf,
-					(entry->src_data[0] >> 10) & 0xf
-					);
+					"se_id %d, sh_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d "
+					"trap %s, sq_ed_info.source %s.\n",
+					type, se_id, sh_id, cu_id,
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SIMD_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, WAVE_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, VM_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, PRIV) ? "true" : "false",
+					(sq_edc_source != -1) ? sq_edc_source_names[sq_edc_source] : "unavailable"
+				);
 			break;
 		default:
 			DRM_ERROR("SQ invalid encoding type\n.");
-			return -EINVAL;
+	}
+}
+
+static void gfx_v8_0_sq_irq_work_func(struct work_struct *work)
+{
+
+	struct amdgpu_device *adev = container_of(work, struct amdgpu_device, gfx.sq_work.work);
+	struct sq_work *sq_work = container_of(work, struct sq_work, work);
+
+	gfx_v8_0_parse_sq_irq(adev, sq_work->ih_data);
+}
+
+static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
+			   struct amdgpu_irq_src *source,
+			   struct amdgpu_iv_entry *entry)
+{
+	unsigned ih_data = entry->src_data[0];
+
+	/*
+	 * Try to submit work so SQ_EDC_INFO can be accessed from
+	 * BH. If previous work submission hasn't finished yet
+	 * just print whatever info is possible directly from the ISR.
+	 */
+	if (work_pending(&adev->gfx.sq_work.work)) {
+		gfx_v8_0_parse_sq_irq(adev, ih_data);
+	} else {
+		adev->gfx.sq_work.ih_data = ih_data;
+		schedule_work(&adev->gfx.sq_work.work);
 	}
 
 	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 a69153435ea7..ef00d14f8645 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -38,6 +38,8 @@
 #include "clearstate_gfx9.h"
 #include "v9_structs.h"
 
+#include "ivsrcid/gfx/irqsrcs_gfx_9_0.h"
+
 #define GFX9_NUM_GFX_RINGS     1
 #define GFX9_MEC_HPD_SIZE 2048
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L
@@ -102,11 +104,22 @@ static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL, 0x0000f000, 0x00012107),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPC_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPG_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xffff77ff, 0x2a114042),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG_READ, 0xffff77ff, 0x2a114042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmIA_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00008000, 0x00048000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_0, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_1, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_2, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_SPM_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00020000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x0000000f, 0x01000107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
@@ -648,7 +661,10 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		if (adev->gfx.rlc.is_rlc_v2_1) {
+		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 &&
+		    adev->gfx.rlc.save_restore_list_srm_size_bytes) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL];
 			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL;
 			info->fw = adev->gfx.rlc_fw;
@@ -943,6 +959,7 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 		dst_ptr = adev->gfx.rlc.cs_ptr;
 		gfx_v9_0_get_csb_buffer(adev, dst_ptr);
 		amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
+		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
 		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
 	}
 
@@ -971,6 +988,39 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
+	if (unlikely(r != 0))
+		return r;
+
+	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
+			AMDGPU_GEM_DOMAIN_VRAM);
+	if (!r)
+		adev->gfx.rlc.clear_state_gpu_addr =
+			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
+
+	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+
+	return r;
+}
+
+static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (!adev->gfx.rlc.clear_state_obj)
+		return;
+
+	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
+	if (likely(r == 0)) {
+		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
+		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+	}
+}
+
 static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -1451,23 +1501,23 @@ static int gfx_v9_0_sw_init(void *handle)
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
 	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 178, &adev->gfx.kiq.irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT, &adev->gfx.kiq.irq);
 	if (r)
 		return r;
 
 	/* EOP Event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 181, &adev->gfx.eop_irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_EOP_INTERRUPT, &adev->gfx.eop_irq);
 	if (r)
 		return r;
 
 	/* Privileged reg */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 184,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_PRIV_REG_FAULT,
 			      &adev->gfx.priv_reg_irq);
 	if (r)
 		return r;
 
 	/* Privileged inst */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 185,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_PRIV_INSTR_FAULT,
 			      &adev->gfx.priv_inst_irq);
 	if (r)
 		return r;
@@ -2148,8 +2198,16 @@ static void gfx_v9_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *ad
 
 static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 {
-	if (!adev->gfx.rlc.is_rlc_v2_1)
-		return;
+	gfx_v9_0_init_csb(adev);
+
+	/*
+	 * Rlc save restore list is workable since v2_1.
+	 * And it's needed by gfxoff feature.
+	 */
+	if (adev->gfx.rlc.is_rlc_v2_1) {
+		gfx_v9_1_init_rlc_save_restore_list(adev);
+		gfx_v9_0_enable_save_restore_machine(adev);
+	}
 
 	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
 			      AMD_PG_SUPPORT_GFX_SMG |
@@ -2157,10 +2215,6 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 			      AMD_PG_SUPPORT_CP |
 			      AMD_PG_SUPPORT_GDS |
 			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
-		gfx_v9_0_init_csb(adev);
-		gfx_v9_1_init_rlc_save_restore_list(adev);
-		gfx_v9_0_enable_save_restore_machine(adev);
-
 		WREG32(mmRLC_JUMP_TABLE_RESTORE,
 		       adev->gfx.rlc.cp_table_gpu_addr >> 8);
 		gfx_v9_0_init_gfx_power_gating(adev);
@@ -2252,9 +2306,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 	/* disable CG */
 	WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, 0);
 
-	/* disable PG */
-	WREG32_SOC15(GC, 0, mmRLC_PG_CNTL, 0);
-
 	gfx_v9_0_rlc_reset(adev);
 
 	gfx_v9_0_init_pg(adev);
@@ -3116,6 +3167,10 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_gpu_init(adev);
 
+	r = gfx_v9_0_csb_vram_pin(adev);
+	if (r)
+		return r;
+
 	r = gfx_v9_0_rlc_resume(adev);
 	if (r)
 		return r;
@@ -3224,6 +3279,8 @@ static int gfx_v9_0_hw_fini(void *handle)
 	gfx_v9_0_cp_enable(adev, false);
 	gfx_v9_0_rlc_stop(adev);
 
+	gfx_v9_0_csb_vram_unpin(adev);
+
 	return 0;
 }
 
@@ -3433,7 +3490,7 @@ static void gfx_v9_0_enter_rlc_safe_mode(struct amdgpu_device *adev)
 
 		/* wait for RLC_SAFE_MODE */
 		for (i = 0; i < adev->usec_timeout; i++) {
-			if (!REG_GET_FIELD(SOC15_REG_OFFSET(GC, 0, mmRLC_SAFE_MODE), RLC_SAFE_MODE, CMD))
+			if (!REG_GET_FIELD(RREG32_SOC15(GC, 0, mmRLC_SAFE_MODE), RLC_SAFE_MODE, CMD))
 				break;
 			udelay(1);
 		}
@@ -3510,8 +3567,11 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 1 - RLC_CGTT_MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
-		data &= ~(RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK |
-			  RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
+
+		if (adev->asic_type != CHIP_VEGA12)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK;
+
+		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
 
@@ -3541,11 +3601,15 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev
 	} else {
 		/* 1 - MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
-		data |= (RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK |
-			 RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
+
+		if (adev->asic_type != CHIP_VEGA12)
+			data |= RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK;
+
+		data |= (RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
@@ -3581,9 +3645,11 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev,
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
-		/* enable 3Dcgcg FSM(0x0020003f) */
+
+		/* enable 3Dcgcg FSM(0x0000363f) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
-		data = (0x2000 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+
+		data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
 			RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
@@ -3630,9 +3696,10 @@ static void gfx_v9_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
-		/* enable cgcg FSM(0x0020003F) */
+		/* enable cgcg FSM(0x0000363F) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
-		data = (0x2000 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+
+		data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
 			RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
@@ -3714,6 +3781,15 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 
 		/* update mgcg state */
 		gfx_v9_0_update_gfx_mg_power_gating(adev, enable);
+
+		/* set gfx off through smu */
+		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
+		break;
+	case CHIP_VEGA12:
+		/* set gfx off through smu */
+		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 79f9ac29019b..75317f283c69 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -41,11 +41,11 @@ static void gmc_v6_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v6_0_wait_for_idle(void *handle);
 
-MODULE_FIRMWARE("radeon/tahiti_mc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
-MODULE_FIRMWARE("radeon/verde_mc.bin");
-MODULE_FIRMWARE("radeon/oland_mc.bin");
-MODULE_FIRMWARE("radeon/si58_mc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_mc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_mc.bin");
+MODULE_FIRMWARE("amdgpu/verde_mc.bin");
+MODULE_FIRMWARE("amdgpu/oland_mc.bin");
+MODULE_FIRMWARE("amdgpu/si58_mc.bin");
 
 #define MC_SEQ_MISC0__MT__MASK   0xf0000000
 #define MC_SEQ_MISC0__MT__GDDR1  0x10000000
@@ -134,9 +134,9 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev)
 		is_58_fw = true;
 
 	if (is_58_fw)
-		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/si58_mc.bin");
 	else
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
 	err = request_firmware(&adev->gmc.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 7147bfe25a23..36dc367c4b45 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -28,6 +28,7 @@
 #include "cik.h"
 #include "gmc_v7_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "bif/bif_4_1_d.h"
 #include "bif/bif_4_1_sh_mask.h"
@@ -43,12 +44,14 @@
 
 #include "amdgpu_atombios.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void gmc_v7_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v7_0_wait_for_idle(void *handle);
 
-MODULE_FIRMWARE("radeon/bonaire_mc.bin");
-MODULE_FIRMWARE("radeon/hawaii_mc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_mc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_mc.bin");
 MODULE_FIRMWARE("amdgpu/topaz_mc.bin");
 
 static const u32 golden_settings_iceland_a11[] =
@@ -147,10 +150,7 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	if (adev->asic_type == CHIP_TOPAZ)
-		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
-	else
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
 
 	err = request_firmware(&adev->gmc.fw, fw_name, adev->dev);
 	if (err)
@@ -999,11 +999,11 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->gmc.vram_type = gmc_v7_0_convert_vram_type(tmp);
 	}
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 146, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 147, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
@@ -1079,6 +1079,12 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1088,6 +1094,7 @@ static int gmc_v7_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v7_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1277,7 +1284,7 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
 	status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
@@ -1302,6 +1309,29 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1edbe6b477b5..70fc97b59b4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "gmc_v8_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
@@ -44,6 +45,7 @@
 
 #include "amdgpu_atombios.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 static void gmc_v8_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -1101,11 +1103,11 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->gmc.vram_type = gmc_v8_0_convert_vram_type(tmp);
 	}
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 146, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 147, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
@@ -1181,6 +1183,12 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1190,6 +1198,7 @@ static int gmc_v8_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v8_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1425,7 +1434,7 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	if (amdgpu_sriov_vf(adev)) {
 		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
@@ -1447,8 +1456,13 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 		gmc_v8_0_set_fault_enable_default(adev, false);
 
 	if (printk_ratelimit()) {
-		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
-			entry->src_id, entry->src_data[0]);
+		struct amdgpu_task_info task_info = { 0 };
+
+		amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
+		dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
+			entry->src_id, entry->src_data[0], task_info.process_name,
+			task_info.tgid, task_info.task_name, task_info.pid);
 		dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 			addr);
 		dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
@@ -1457,6 +1471,29 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3c0a85d4e4ab..399a5db27649 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -43,6 +43,8 @@
 #include "gfxhub_v1_0.h"
 #include "mmhub_v1_0.h"
 
+#include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
+
 /* add these here since we already include dce12 headers and these are for DCN */
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION                                                          0x055d
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_BASE_IDX                                                 2
@@ -257,12 +259,17 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	}
 
 	if (printk_ratelimit()) {
+		struct amdgpu_task_info task_info = { 0 };
+
+		amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
 		dev_err(adev->dev,
-			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
+			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u, for process %s pid %d thread %s pid %d\n)\n",
 			entry->vmid_src ? "mmhub" : "gfxhub",
 			entry->src_id, entry->ring_id, entry->vmid,
-			entry->pasid);
-		dev_err(adev->dev, "  at page 0x%016llx from %d\n",
+			entry->pasid, task_info.process_name, task_info.tgid,
+			task_info.task_name, task_info.pid);
+		dev_err(adev->dev, "  at address 0x%016llx from %d\n",
 			addr, entry->client_id);
 		if (!amdgpu_sriov_vf(adev))
 			dev_err(adev->dev,
@@ -872,9 +879,9 @@ static int gmc_v9_0_sw_init(void *handle)
 	}
 
 	/* This interrupt is VMC page fault.*/
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, 0,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, VMC_1_0__SRCID__VM_FAULT,
 				&adev->gmc.vm_fault);
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, 0,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, UTCL2_1_0__SRCID__FAULT,
 				&adev->gmc.vm_fault);
 
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 46de1fd18a7b..3f57f6463dc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -3306,6 +3306,19 @@ static int kv_dpm_read_sensor(void *handle, int idx,
 	}
 }
 
+static int kv_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+		kv_dpm_powergate_uvd(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 static const struct amd_ip_funcs kv_dpm_ip_funcs = {
 	.name = "kv_dpm",
 	.early_init = kv_dpm_early_init,
@@ -3342,7 +3355,7 @@ static const struct amd_pm_funcs kv_dpm_funcs = {
 	.print_power_state = &kv_dpm_print_power_state,
 	.debugfs_print_current_performance_level = &kv_dpm_debugfs_print_current_performance_level,
 	.force_performance_level = &kv_dpm_force_performance_level,
-	.powergate_uvd = &kv_dpm_powergate_uvd,
+	.set_powergating_by_smu = kv_set_powergating_by_smu,
 	.enable_bapm = &kv_dpm_enable_bapm,
 	.get_vce_clock_state = amdgpu_get_vce_clock_state,
 	.check_state_equal = kv_check_state_equal,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 3d53c4413f13..e70a0d4d6db4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -471,8 +471,8 @@ void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
 						RENG_EXECUTE_ON_REG_UPDATE, 1);
 		WREG32_SOC15(MMHUB, 0, mmPCTL1_RENG_EXECUTE, pctl1_reng_execute);
 
-		if (adev->powerplay.pp_funcs->set_mmhub_powergating_by_smu)
-			amdgpu_dpm_set_mmhub_powergating_by_smu(adev);
+		if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
 
 	} else {
 		pctl0_reng_execute = REG_SET_FIELD(pctl0_reng_execute,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index c7190c39c4f5..15ae4bc9c072 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -44,6 +44,8 @@
 
 #include "iceland_sdma_pkt_open.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -202,8 +204,7 @@ static uint64_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-	u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
+	u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 
 	return wptr;
 }
@@ -218,9 +219,8 @@ static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
 static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
 
-	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
+	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me], lower_32_bits(ring->wptr) << 2);
 }
 
 static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
@@ -273,7 +273,7 @@ static void sdma_v2_4_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	u32 ref_and_mask = 0;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
 	else
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@@ -898,7 +898,7 @@ static int sdma_v2_4_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -910,7 +910,7 @@ static int sdma_v2_4_sw_init(void *handle)
 		return r;
 
 	/* SDMA Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
 			      &adev->sdma.illegal_inst_irq);
 	if (r)
 		return r;
@@ -1213,8 +1213,10 @@ static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v2_4_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v2_4_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index aa9ab299fd32..1e07ff274d73 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -44,6 +44,8 @@
 
 #include "tonga_sdma_pkt_open.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -365,9 +367,7 @@ static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 		/* XXX check if swapping is necessary on BE */
 		wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
-		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
+		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 	}
 
 	return wptr;
@@ -394,9 +394,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
-		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
+		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me], lower_32_bits(ring->wptr) << 2);
 	}
 }
 
@@ -450,7 +448,7 @@ static void sdma_v3_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	u32 ref_and_mask = 0;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
 	else
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@@ -1179,7 +1177,7 @@ static int sdma_v3_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -1191,7 +1189,7 @@ static int sdma_v3_0_sw_init(void *handle)
 		return r;
 
 	/* SDMA Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
 			      &adev->sdma.illegal_inst_irq);
 	if (r)
 		return r;
@@ -1655,8 +1653,10 @@ static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v3_0_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v3_0_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ca53b3fba422..e7ca4623cfb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -38,6 +38,9 @@
 #include "soc15.h"
 #include "vega10_sdma_pkt_open.h"
 
+#include "ivsrcid/sdma0/irqsrcs_sdma0_4_0.h"
+#include "ivsrcid/sdma1/irqsrcs_sdma1_4_0.h"
+
 MODULE_FIRMWARE("amdgpu/vega10_sdma.bin");
 MODULE_FIRMWARE("amdgpu/vega10_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/vega12_sdma.bin");
@@ -296,13 +299,12 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		u32 lowbit, highbit;
-		int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
+		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
+		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
 
 		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				me, highbit, lowbit);
+				ring->me, highbit, lowbit);
 		wptr = highbit;
 		wptr = wptr << 32;
 		wptr |= lowbit;
@@ -339,17 +341,15 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
 		DRM_DEBUG("Not using doorbell -- "
 				"mmSDMA%i_GFX_RB_WPTR == 0x%08x "
 				"mmSDMA%i_GFX_RB_WPTR_HI == 0x%08x\n",
-				me,
+				ring->me,
 				lower_32_bits(ring->wptr << 2),
-				me,
+				ring->me,
 				upper_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
 	}
 }
 
@@ -430,7 +430,7 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	u32 ref_and_mask = 0;
 	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0;
 	else
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma1;
@@ -1228,13 +1228,13 @@ static int sdma_v4_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, 224,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, SDMA0_4_0__SRCID__SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, 224,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, SDMA1_4_0__SRCID__SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -1651,8 +1651,10 @@ static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v4_0_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v4_0_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index d51318c695e6..db327b412562 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -56,16 +56,16 @@
 
 #define BIOS_SCRATCH_4                                    0x5cd
 
-MODULE_FIRMWARE("radeon/tahiti_smc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_smc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_k_smc.bin");
-MODULE_FIRMWARE("radeon/verde_smc.bin");
-MODULE_FIRMWARE("radeon/verde_k_smc.bin");
-MODULE_FIRMWARE("radeon/oland_smc.bin");
-MODULE_FIRMWARE("radeon/oland_k_smc.bin");
-MODULE_FIRMWARE("radeon/hainan_smc.bin");
-MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
-MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_smc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_smc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/verde_smc.bin");
+MODULE_FIRMWARE("amdgpu/verde_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/oland_smc.bin");
+MODULE_FIRMWARE("amdgpu/oland_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/hainan_smc.bin");
+MODULE_FIRMWARE("amdgpu/hainan_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/banks_k_2_smc.bin");
 
 static const struct amd_pm_funcs si_dpm_funcs;
 
@@ -7318,8 +7318,7 @@ static int si_dpm_init(struct amdgpu_device *adev)
 	pi = &eg_pi->rv7xx;
 
 	si_pi->sys_pcie_mask =
-		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
-		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+		adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK;
 	si_pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 	si_pi->boot_pcie_gen = si_get_current_pcie_speed(adev);
 
@@ -7667,7 +7666,7 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
 	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 341ee6d55ce8..aeaa1ca46a99 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -35,6 +35,7 @@
 #include "vi.h"
 #include "smu/smu_7_1_2_d.h"
 #include "smu/smu_7_1_2_sh_mask.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v5_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -104,7 +105,7 @@ static int uvd_v5_0_sw_init(void *handle)
 	int r;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index bfddf97dd13e..598dbeaba636 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -36,6 +36,7 @@
 #include "bif/bif_5_1_d.h"
 #include "gmc/gmc_8_1_d.h"
 #include "vi.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 /* Polaris10/11/12 firmware version */
 #define FW_1_130_16 ((1 << 24) | (130 << 16) | (16 << 8))
@@ -247,12 +248,10 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -311,19 +310,13 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
@@ -400,14 +393,14 @@ static int uvd_v6_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
 	/* UVD ENC TRAP */
 	if (uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + 119, &adev->uvd.inst->irq);
+			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + VISLANDS30_IV_SRCID_UVD_ENC_GEN_PURP, &adev->uvd.inst->irq);
 			if (r)
 				return r;
 		}
@@ -425,16 +418,6 @@ static int uvd_v6_0_sw_init(void *handle)
 		adev->uvd.num_enc_rings = 0;
 
 		DRM_INFO("UVD ENC is disabled\n");
-	} else {
-		struct drm_sched_rq *rq;
-		ring = &adev->uvd.inst->ring_enc[0];
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst->entity_enc,
-					  rq, NULL);
-		if (r) {
-			DRM_ERROR("Failed setting up UVD ENC run queue.\n");
-			return r;
-		}
 	}
 
 	r = amdgpu_uvd_resume(adev);
@@ -470,8 +453,6 @@ static int uvd_v6_0_sw_fini(void *handle)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
-		drm_sched_entity_fini(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc);
-
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst->ring_enc[i]);
 	}
@@ -1569,7 +1550,6 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_phys_funcs = {
 static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(mmUVD_NO_OP, 0),
 	.support_64bit_ptrs = false,
 	.get_rptr = uvd_v6_0_ring_get_rptr,
 	.get_wptr = uvd_v6_0_ring_get_wptr,
@@ -1587,7 +1567,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
 	.test_ring = uvd_v6_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v6_0_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 57d32f21b3a6..db5f3d78ab12 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -39,6 +39,7 @@
 #include "hdp/hdp_4_0_offset.h"
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
+#include "ivsrcid/uvd/irqsrcs_uvd_7_0.h"
 
 #define UVD7_MAX_HW_INSTANCES_VEGA20			2
 
@@ -249,12 +250,10 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -312,19 +311,13 @@ int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
@@ -396,19 +389,18 @@ static int uvd_v7_0_early_init(void *handle)
 static int uvd_v7_0_sw_init(void *handle)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	int i, j, r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
 		/* UVD TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], 124, &adev->uvd.inst[j].irq);
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->uvd.inst[j].irq);
 		if (r)
 			return r;
 
 		/* UVD ENC TRAP */
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + 119, &adev->uvd.inst[j].irq);
+			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + UVD_7_0__SRCID__UVD_ENC_GEN_PURP, &adev->uvd.inst[j].irq);
 			if (r)
 				return r;
 		}
@@ -428,17 +420,6 @@ static int uvd_v7_0_sw_init(void *handle)
 		DRM_INFO("PSP loading UVD firmware\n");
 	}
 
-	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-		ring = &adev->uvd.inst[j].ring_enc[0];
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity_enc,
-					  rq, NULL);
-		if (r) {
-			DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j);
-			return r;
-		}
-	}
-
 	r = amdgpu_uvd_resume(adev);
 	if (r)
 		return r;
@@ -491,8 +472,6 @@ static int uvd_v7_0_sw_fini(void *handle)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
-		drm_sched_entity_fini(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc);
-
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 47f70827195b..d48e877b682e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -56,7 +56,7 @@ static uint64_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(mmVCE_RB_RPTR);
 	else
 		return RREG32(mmVCE_RB_RPTR2);
@@ -73,7 +73,7 @@ static uint64_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(mmVCE_RB_WPTR);
 	else
 		return RREG32(mmVCE_RB_WPTR2);
@@ -90,7 +90,7 @@ static void vce_v2_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
@@ -627,8 +627,10 @@ static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vce.num_rings; i++)
+	for (i = 0; i < adev->vce.num_rings; i++) {
 		adev->vce.ring[i].funcs = &vce_v2_0_ring_funcs;
+		adev->vce.ring[i].me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs vce_v2_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 0999c843f623..cc6ce6cc03f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -39,6 +39,7 @@
 #include "smu/smu_7_1_2_sh_mask.h"
 #include "gca/gfx_8_0_d.h"
 #include "gca/gfx_8_0_sh_mask.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
@@ -86,9 +87,9 @@ static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		v = RREG32(mmVCE_RB_RPTR);
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		v = RREG32(mmVCE_RB_RPTR2);
 	else
 		v = RREG32(mmVCE_RB_RPTR3);
@@ -118,9 +119,9 @@ static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		v = RREG32(mmVCE_RB_WPTR);
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		v = RREG32(mmVCE_RB_WPTR2);
 	else
 		v = RREG32(mmVCE_RB_WPTR3);
@@ -149,9 +150,9 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
@@ -422,7 +423,7 @@ static int vce_v3_0_sw_init(void *handle)
 	int r, i;
 
 	/* VCE */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 167, &adev->vce.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_VCE_TRAP, &adev->vce.irq);
 	if (r)
 		return r;
 
@@ -900,7 +901,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_phys_funcs = {
 	.emit_frame_size =
 		4 + /* vce_v3_0_emit_pipeline_sync */
 		6, /* amdgpu_vce_ring_emit_fence x1 no user fence */
-	.emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
+	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
 	.emit_ib = amdgpu_vce_ring_emit_ib,
 	.emit_fence = amdgpu_vce_ring_emit_fence,
 	.test_ring = amdgpu_vce_ring_test_ring,
@@ -924,7 +925,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_vm_funcs = {
 		6 + /* vce_v3_0_emit_vm_flush */
 		4 + /* vce_v3_0_emit_pipeline_sync */
 		6 + 6, /* amdgpu_vce_ring_emit_fence x2 vm fence */
-	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
+	.emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
 	.emit_ib = vce_v3_0_ring_emit_ib,
 	.emit_vm_flush = vce_v3_0_emit_vm_flush,
 	.emit_pipeline_sync = vce_v3_0_emit_pipeline_sync,
@@ -942,12 +943,16 @@ static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev)
 	int i;
 
 	if (adev->asic_type >= CHIP_STONEY) {
-		for (i = 0; i < adev->vce.num_rings; i++)
+		for (i = 0; i < adev->vce.num_rings; i++) {
 			adev->vce.ring[i].funcs = &vce_v3_0_ring_vm_funcs;
+			adev->vce.ring[i].me = i;
+		}
 		DRM_INFO("VCE enabled in VM mode\n");
 	} else {
-		for (i = 0; i < adev->vce.num_rings; i++)
+		for (i = 0; i < adev->vce.num_rings; i++) {
 			adev->vce.ring[i].funcs = &vce_v3_0_ring_phys_funcs;
+			adev->vce.ring[i].me = i;
+		}
 		DRM_INFO("VCE enabled in physical mode\n");
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 8fd1b742985a..65f8860169e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -39,6 +39,8 @@
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
 
+#include "ivsrcid/vce/irqsrcs_vce_4_0.h"
+
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V4_0_FW_SIZE	(384 * 1024)
@@ -60,9 +62,9 @@ static uint64_t vce_v4_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR2));
 	else
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR3));
@@ -82,9 +84,9 @@ static uint64_t vce_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell)
 		return adev->wb.wb[ring->wptr_offs];
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR2));
 	else
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR3));
@@ -108,10 +110,10 @@ static void vce_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 		return;
 	}
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR),
 			lower_32_bits(ring->wptr));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR2),
 			lower_32_bits(ring->wptr));
 	else
@@ -1088,8 +1090,10 @@ static void vce_v4_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vce.num_rings; i++)
+	for (i = 0; i < adev->vce.num_rings; i++) {
 		adev->vce.ring[i].funcs = &vce_v4_0_ring_vm_funcs;
+		adev->vce.ring[i].me = i;
+	}
 	DRM_INFO("VCE enabled in VM mode\n");
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index b82c92084b6f..2ce91a748c40 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -35,6 +35,8 @@
 #include "mmhub/mmhub_9_1_offset.h"
 #include "mmhub/mmhub_9_1_sh_mask.h"
 
+#include "ivsrcid/vcn/irqsrcs_vcn_1_0.h"
+
 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);
@@ -77,13 +79,13 @@ static int vcn_v1_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* VCN DEC TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 124, &adev->vcn.irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_1_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->vcn.irq);
 	if (r)
 		return r;
 
 	/* VCN ENC TRAP */
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + 119,
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE,
 					&adev->vcn.irq);
 		if (r)
 			return r;
@@ -600,12 +602,12 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
 
-	vcn_v1_0_mc_resume(adev);
-
 	vcn_1_0_disable_static_power_gating(adev);
 	/* disable clock gating */
 	vcn_v1_0_disable_clock_gating(adev);
 
+	vcn_v1_0_mc_resume(adev);
+
 	/* disable interupt */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0,
 			~UVD_MASTINT_EN__VCPU_EN_MASK);
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
index 45aafca7f315..c5c9b2bc190d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
@@ -51,6 +51,7 @@ int vega10_reg_base_init(struct amdgpu_device *adev)
 		adev->reg_offset[PWR_HWIP][i] = (uint32_t *)(&(PWR_BASE.instance[i]));
 		adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIF_BASE.instance[i]));
 		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i]));
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 4ac1288ab7df..42c8ad105b05 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1363,11 +1363,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_MC_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) {
-			pp_support_state = AMD_CG_SUPPORT_MC_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_MC_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1382,11 +1382,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_SDMA_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS) {
-			pp_support_state = AMD_CG_SUPPORT_SDMA_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_SDMA_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1401,11 +1401,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
-			pp_support_state = AMD_CG_SUPPORT_HDP_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_HDP_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 49df6c791cfc..5d2475d5392c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -25,12 +25,39 @@
 #include "cik_int.h"
 
 static bool cik_event_interrupt_isr(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
+	const struct kfd2kgd_calls *f2g = dev->kfd2kgd;
 	unsigned int vmid, pasid;
 
+	/* This workaround is due to HW/FW limitation on Hawaii that
+	 * VMID and PASID are not written into ih_ring_entry
+	 */
+	if ((ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) &&
+		dev->device_info->asic_family == CHIP_HAWAII) {
+		struct cik_ih_ring_entry *tmp_ihre =
+			(struct cik_ih_ring_entry *)patched_ihre;
+
+		*patched_flag = true;
+		*tmp_ihre = *ihre;
+
+		vmid = f2g->read_vmid_from_vmfault_reg(dev->kgd);
+		pasid = f2g->get_atc_vmid_pasid_mapping_pasid(dev->kgd, vmid);
+
+		tmp_ihre->ring_id &= 0x000000ff;
+		tmp_ihre->ring_id |= vmid << 8;
+		tmp_ihre->ring_id |= pasid << 16;
+
+		return (pasid != 0) &&
+			vmid >= dev->vm_info.first_vmid_kfd &&
+			vmid <= dev->vm_info.last_vmid_kfd;
+	}
+
 	/* Only handle interrupts from KFD VMIDs */
 	vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
 	if (vmid < dev->vm_info.first_vmid_kfd ||
@@ -48,18 +75,19 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 	return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
 		ihre->source_id == CIK_INTSRC_SDMA_TRAP ||
 		ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG ||
-		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE;
+		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE ||
+		ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT;
 }
 
 static void cik_event_interrupt_wq(struct kfd_dev *dev,
 					const uint32_t *ih_ring_entry)
 {
-	unsigned int pasid;
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
-
-	pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
+	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
@@ -72,6 +100,22 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 		kfd_signal_event_interrupt(pasid, context_id & 0xff, 8);
 	else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE)
 		kfd_signal_hw_exception_event(pasid);
+	else if (ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) {
+		struct kfd_vm_fault_info info;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+
+		memset(&info, 0, sizeof(info));
+		dev->kfd2kgd->get_vm_fault_info(dev->kgd, &info);
+		if (!info.page_addr && !info.status)
+			return;
+
+		if (info.vmid == vmid)
+			kfd_signal_vm_fault_event(dev, pasid, &info);
+		else
+			kfd_signal_vm_fault_event(dev, pasid, NULL);
+	}
 }
 
 const struct kfd_event_interrupt_class event_interrupt_class_cik = {
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h
index 109298b9d507..76f8677a7926 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h
@@ -20,8 +20,8 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#ifndef HSA_RADEON_CIK_INT_H_INCLUDED
-#define HSA_RADEON_CIK_INT_H_INCLUDED
+#ifndef CIK_INT_H_INCLUDED
+#define CIK_INT_H_INCLUDED
 
 #include <linux/types.h>
 
@@ -34,9 +34,10 @@ struct cik_ih_ring_entry {
 
 #define CIK_INTSRC_CP_END_OF_PIPE	0xB5
 #define CIK_INTSRC_CP_BAD_OPCODE	0xB7
-#define CIK_INTSRC_DEQUEUE_COMPLETE	0xC6
 #define CIK_INTSRC_SDMA_TRAP		0xE0
 #define CIK_INTSRC_SQ_INTERRUPT_MSG	0xEF
+#define CIK_INTSRC_GFX_PAGE_INV_FAULT	0x92
+#define CIK_INTSRC_GFX_MEM_PROT_FAULT	0x93
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index f68aef02fc1f..3621efbd5759 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -21,18 +21,21 @@
  */
 
 static const uint32_t cwsr_trap_gfx8_hex[] = {
-	0xbf820001, 0xbf820125,
+	0xbf820001, 0xbf82012b,
 	0xb8f4f802, 0x89748674,
 	0xb8f5f803, 0x8675ff75,
-	0x00000400, 0xbf850011,
+	0x00000400, 0xbf850017,
 	0xc00a1e37, 0x00000000,
 	0xbf8c007f, 0x87777978,
-	0xbf840002, 0xb974f802,
-	0xbe801d78, 0xb8f5f803,
-	0x8675ff75, 0x000001ff,
-	0xbf850002, 0x80708470,
-	0x82718071, 0x8671ff71,
-	0x0000ffff, 0xb974f802,
+	0xbf840005, 0x8f728374,
+	0xb972e0c2, 0xbf800002,
+	0xb9740002, 0xbe801d78,
+	0xb8f5f803, 0x8675ff75,
+	0x000001ff, 0xbf850002,
+	0x80708470, 0x82718071,
+	0x8671ff71, 0x0000ffff,
+	0x8f728374, 0xb972e0c2,
+	0xbf800002, 0xb9740002,
 	0xbe801f70, 0xb8f5f803,
 	0x8675ff75, 0x00000100,
 	0xbf840006, 0xbefa0080,
@@ -168,7 +171,7 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 	0x807c847c, 0x806eff6e,
 	0x00000400, 0xbf0a757c,
 	0xbf85ffef, 0xbf9c0000,
-	0xbf8200ca, 0xbef8007e,
+	0xbf8200cd, 0xbef8007e,
 	0x8679ff7f, 0x0000ffff,
 	0x8779ff79, 0x00040000,
 	0xbefa0080, 0xbefb00ff,
@@ -268,16 +271,18 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 	0x8f739773, 0xb976f807,
 	0x8671ff71, 0x0000ffff,
 	0x86fe7e7e, 0x86ea6a6a,
-	0xb974f802, 0xbf8a0000,
-	0x95807370, 0xbf810000,
+	0x8f768374, 0xb976e0c2,
+	0xbf800002, 0xb9740002,
+	0xbf8a0000, 0x95807370,
+	0xbf810000, 0x00000000,
 };
 
 
 static const uint32_t cwsr_trap_gfx9_hex[] = {
-	0xbf820001, 0xbf82015a,
+	0xbf820001, 0xbf82015d,
 	0xb8f8f802, 0x89788678,
 	0xb8f1f803, 0x866eff71,
-	0x00000400, 0xbf850034,
+	0x00000400, 0xbf850037,
 	0x866eff71, 0x00000800,
 	0xbf850003, 0x866eff71,
 	0x00000100, 0xbf840008,
@@ -303,258 +308,261 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x8f6e8b77, 0x866eff6e,
 	0x001f8000, 0xb96ef807,
 	0x86fe7e7e, 0x86ea6a6a,
-	0xb978f802, 0xbe801f6c,
-	0x866dff6d, 0x0000ffff,
-	0xbef00080, 0xb9700283,
-	0xb8f02407, 0x8e709c70,
-	0x876d706d, 0xb8f003c7,
-	0x8e709b70, 0x876d706d,
-	0xb8f0f807, 0x8670ff70,
-	0x00007fff, 0xb970f807,
-	0xbeee007e, 0xbeef007f,
-	0xbefe0180, 0xbf900004,
-	0x87708478, 0xb970f802,
-	0xbf8e0002, 0xbf88fffe,
-	0xb8f02a05, 0x80708170,
-	0x8e708a70, 0xb8f11605,
-	0x80718171, 0x8e718671,
-	0x80707170, 0x80707e70,
-	0x8271807f, 0x8671ff71,
-	0x0000ffff, 0xc0471cb8,
-	0x00000040, 0xbf8cc07f,
-	0xc04b1d38, 0x00000048,
-	0xbf8cc07f, 0xc0431e78,
-	0x00000058, 0xbf8cc07f,
-	0xc0471eb8, 0x0000005c,
-	0xbf8cc07f, 0xbef4007e,
-	0x8675ff7f, 0x0000ffff,
-	0x8775ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x00807fac, 0x8670ff7f,
-	0x08000000, 0x8f708370,
-	0x87777077, 0x8670ff7f,
-	0x70000000, 0x8f708170,
-	0x87777077, 0xbefb007c,
-	0xbefa0080, 0xb8fa2a05,
-	0x807a817a, 0x8e7a8a7a,
-	0xb8f01605, 0x80708170,
-	0x8e708670, 0x807a707a,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xbefe007c,
-	0xbefc007a, 0xc0611efa,
-	0x0000007c, 0xbf8cc07f,
-	0x807a847a, 0xbefc007e,
+	0x8f6e8378, 0xb96ee0c2,
+	0xbf800002, 0xb9780002,
+	0xbe801f6c, 0x866dff6d,
+	0x0000ffff, 0xbef00080,
+	0xb9700283, 0xb8f02407,
+	0x8e709c70, 0x876d706d,
+	0xb8f003c7, 0x8e709b70,
+	0x876d706d, 0xb8f0f807,
+	0x8670ff70, 0x00007fff,
+	0xb970f807, 0xbeee007e,
+	0xbeef007f, 0xbefe0180,
+	0xbf900004, 0x87708478,
+	0xb970f802, 0xbf8e0002,
+	0xbf88fffe, 0xb8f02a05,
+	0x80708170, 0x8e708a70,
+	0xb8f11605, 0x80718171,
+	0x8e718671, 0x80707170,
+	0x80707e70, 0x8271807f,
+	0x8671ff71, 0x0000ffff,
+	0xc0471cb8, 0x00000040,
+	0xbf8cc07f, 0xc04b1d38,
+	0x00000048, 0xbf8cc07f,
+	0xc0431e78, 0x00000058,
+	0xbf8cc07f, 0xc0471eb8,
+	0x0000005c, 0xbf8cc07f,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0x8670ff7f, 0x08000000,
+	0x8f708370, 0x87777077,
+	0x8670ff7f, 0x70000000,
+	0x8f708170, 0x87777077,
+	0xbefb007c, 0xbefa0080,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f01605,
+	0x80708170, 0x8e708670,
+	0x807a707a, 0xbef60084,
+	0xbef600ff, 0x01000000,
 	0xbefe007c, 0xbefc007a,
-	0xc0611b3a, 0x0000007c,
+	0xc0611efa, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611b7a,
+	0xbefc007a, 0xc0611b3a,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611bba, 0x0000007c,
+	0xc0611b7a, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611bfa,
+	0xbefc007a, 0xc0611bba,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611e3a, 0x0000007c,
-	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0xb8f1f803,
-	0xbefe007c, 0xbefc007a,
-	0xc0611c7a, 0x0000007c,
+	0xc0611bfa, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611a3a,
+	0xbefc007a, 0xc0611e3a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xb8f1f803, 0xbefe007c,
+	0xbefc007a, 0xc0611c7a,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611a7a, 0x0000007c,
-	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0xb8fbf801,
-	0xbefe007c, 0xbefc007a,
-	0xc0611efa, 0x0000007c,
+	0xc0611a3a, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0x8670ff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f70, 0xb8fa2a05,
+	0xbefc007e, 0xbefe007c,
+	0xbefc007a, 0xc0611a7a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xb8fbf801, 0xbefe007c,
+	0xbefc007a, 0xc0611efa,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0x8670ff7f, 0x04000000,
+	0xbeef0080, 0x876f6f70,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f11605,
+	0x80718171, 0x8e718471,
+	0x8e768271, 0xbef600ff,
+	0x01000000, 0xbef20174,
+	0x80747a74, 0x82758075,
+	0xbefc0080, 0xbf800000,
+	0xbe802b00, 0xbe822b02,
+	0xbe842b04, 0xbe862b06,
+	0xbe882b08, 0xbe8a2b0a,
+	0xbe8c2b0c, 0xbe8e2b0e,
+	0xc06b003a, 0x00000000,
+	0xbf8cc07f, 0xc06b013a,
+	0x00000010, 0xbf8cc07f,
+	0xc06b023a, 0x00000020,
+	0xbf8cc07f, 0xc06b033a,
+	0x00000030, 0xbf8cc07f,
+	0x8074c074, 0x82758075,
+	0x807c907c, 0xbf0a717c,
+	0xbf85ffe7, 0xbef40172,
+	0xbefa0080, 0xbefe00c1,
+	0xbeff00c1, 0xbee80080,
+	0xbee90080, 0xbef600ff,
+	0x01000000, 0xe0724000,
+	0x7a1d0000, 0xe0724100,
+	0x7a1d0100, 0xe0724200,
+	0x7a1d0200, 0xe0724300,
+	0x7a1d0300, 0xbefe00c1,
+	0xbeff00c1, 0xb8f14306,
+	0x8671c171, 0xbf84002c,
+	0xbf8a0000, 0x8670ff6f,
+	0x04000000, 0xbf840028,
+	0x8e718671, 0x8e718271,
+	0xbef60071, 0xb8fa2a05,
 	0x807a817a, 0x8e7a8a7a,
-	0xb8f11605, 0x80718171,
-	0x8e718471, 0x8e768271,
+	0xb8f01605, 0x80708170,
+	0x8e708670, 0x807a707a,
+	0x807aff7a, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xbef20174, 0x80747a74,
-	0x82758075, 0xbefc0080,
-	0xbf800000, 0xbe802b00,
-	0xbe822b02, 0xbe842b04,
-	0xbe862b06, 0xbe882b08,
-	0xbe8a2b0a, 0xbe8c2b0c,
-	0xbe8e2b0e, 0xc06b003a,
-	0x00000000, 0xbf8cc07f,
-	0xc06b013a, 0x00000010,
-	0xbf8cc07f, 0xc06b023a,
-	0x00000020, 0xbf8cc07f,
-	0xc06b033a, 0x00000030,
-	0xbf8cc07f, 0x8074c074,
-	0x82758075, 0x807c907c,
-	0xbf0a717c, 0xbf85ffe7,
-	0xbef40172, 0xbefa0080,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0xd1060002,
+	0x00011103, 0x7e0602ff,
+	0x00000200, 0xbefc00ff,
+	0x00010000, 0xbe800077,
+	0x8677ff77, 0xff7fffff,
+	0x8777ff77, 0x00058000,
+	0xd8ec0000, 0x00000002,
+	0xbf8cc07f, 0xe0765000,
+	0x7a1d0002, 0x68040702,
+	0xd0c9006a, 0x0000e302,
+	0xbf87fff7, 0xbef70000,
+	0xbefa00ff, 0x00000400,
 	0xbefe00c1, 0xbeff00c1,
-	0xbee80080, 0xbee90080,
+	0xb8f12a05, 0x80718171,
+	0x8e718271, 0x8e768871,
 	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a717c,
+	0xbf840015, 0xbf11017c,
+	0x8071ff71, 0x00001000,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0xe0724000, 0x7a1d0000,
 	0xe0724100, 0x7a1d0100,
 	0xe0724200, 0x7a1d0200,
 	0xe0724300, 0x7a1d0300,
+	0x807c847c, 0x807aff7a,
+	0x00000400, 0xbf0a717c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbf8200dc, 0xbef4007e,
+	0x8675ff7f, 0x0000ffff,
+	0x8775ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x00807fac, 0x866eff7f,
+	0x08000000, 0x8f6e836e,
+	0x87776e77, 0x866eff7f,
+	0x70000000, 0x8f6e816e,
+	0x87776e77, 0x866eff7f,
+	0x04000000, 0xbf84001e,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8f14306, 0x8671c171,
-	0xbf84002c, 0xbf8a0000,
-	0x8670ff6f, 0x04000000,
-	0xbf840028, 0x8e718671,
-	0x8e718271, 0xbef60071,
-	0xb8fa2a05, 0x807a817a,
-	0x8e7a8a7a, 0xb8f01605,
-	0x80708170, 0x8e708670,
-	0x807a707a, 0x807aff7a,
+	0xb8ef4306, 0x866fc16f,
+	0xbf840019, 0x8e6f866f,
+	0x8e6f826f, 0xbef6006f,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0x8078ff78,
 	0x00000080, 0xbef600ff,
 	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
-	0xd1060002, 0x00011103,
-	0x7e0602ff, 0x00000200,
-	0xbefc00ff, 0x00010000,
-	0xbe800077, 0x8677ff77,
-	0xff7fffff, 0x8777ff77,
-	0x00058000, 0xd8ec0000,
-	0x00000002, 0xbf8cc07f,
-	0xe0765000, 0x7a1d0002,
-	0x68040702, 0xd0c9006a,
-	0x0000e302, 0xbf87fff7,
-	0xbef70000, 0xbefa00ff,
-	0x00000400, 0xbefe00c1,
-	0xbeff00c1, 0xb8f12a05,
-	0x80718171, 0x8e718271,
-	0x8e768871, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a717c, 0xbf840015,
-	0xbf11017c, 0x8071ff71,
-	0x00001000, 0x7e000300,
+	0xe0510000, 0x781d0000,
+	0xe0510100, 0x781d0000,
+	0x807cff7c, 0x00000200,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7c, 0xbf85fff6,
+	0xbef80080, 0xbefe00c1,
+	0xbeff00c1, 0xb8ef2a05,
+	0x806f816f, 0x8e6f826f,
+	0x8e76886f, 0xbef600ff,
+	0x01000000, 0xbeee0078,
+	0x8078ff78, 0x00000400,
+	0xbefc0084, 0xbf11087c,
+	0x806fff6f, 0x00008000,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0x7e000300,
 	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x7a1d0000, 0xe0724100,
-	0x7a1d0100, 0xe0724200,
-	0x7a1d0200, 0xe0724300,
-	0x7a1d0300, 0x807c847c,
-	0x807aff7a, 0x00000400,
-	0xbf0a717c, 0xbf85ffef,
-	0xbf9c0000, 0xbf8200d9,
-	0xbef4007e, 0x8675ff7f,
-	0x0000ffff, 0x8775ff75,
-	0x00040000, 0xbef60080,
-	0xbef700ff, 0x00807fac,
-	0x866eff7f, 0x08000000,
-	0x8f6e836e, 0x87776e77,
-	0x866eff7f, 0x70000000,
-	0x8f6e816e, 0x87776e77,
-	0x866eff7f, 0x04000000,
-	0xbf84001e, 0xbefe00c1,
-	0xbeff00c1, 0xb8ef4306,
-	0x866fc16f, 0xbf840019,
-	0x8e6f866f, 0x8e6f826f,
-	0xbef6006f, 0xb8f82a05,
+	0x7e060303, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffee,
+	0xbf9c0000, 0xe0524000,
+	0x6e1d0000, 0xe0524100,
+	0x6e1d0100, 0xe0524200,
+	0x6e1d0200, 0xe0524300,
+	0x6e1d0300, 0xb8f82a05,
 	0x80788178, 0x8e788a78,
 	0xb8ee1605, 0x806e816e,
 	0x8e6e866e, 0x80786e78,
-	0x8078ff78, 0x00000080,
-	0xbef600ff, 0x01000000,
-	0xbefc0080, 0xe0510000,
-	0x781d0000, 0xe0510100,
-	0x781d0000, 0x807cff7c,
-	0x00000200, 0x8078ff78,
-	0x00000200, 0xbf0a6f7c,
-	0xbf85fff6, 0xbef80080,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8ef2a05, 0x806f816f,
-	0x8e6f826f, 0x8e76886f,
-	0xbef600ff, 0x01000000,
-	0xbeee0078, 0x8078ff78,
-	0x00000400, 0xbefc0084,
-	0xbf11087c, 0x806fff6f,
-	0x00008000, 0xe0524000,
-	0x781d0000, 0xe0524100,
-	0x781d0100, 0xe0524200,
-	0x781d0200, 0xe0524300,
-	0x781d0300, 0xbf8c0f70,
-	0x7e000300, 0x7e020301,
-	0x7e040302, 0x7e060303,
-	0x807c847c, 0x8078ff78,
-	0x00000400, 0xbf0a6f7c,
-	0xbf85ffee, 0xbf9c0000,
-	0xe0524000, 0x6e1d0000,
-	0xe0524100, 0x6e1d0100,
-	0xe0524200, 0x6e1d0200,
-	0xe0524300, 0x6e1d0300,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
 	0xb8f82a05, 0x80788178,
 	0x8e788a78, 0xb8ee1605,
 	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
+	0x80786e78, 0xbef60084,
 	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0xb8ee1605, 0x806e816e,
-	0x8e6e866e, 0x80786e78,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xc0211bfa,
+	0xc0211bfa, 0x00000078,
+	0x80788478, 0xc0211b3a,
 	0x00000078, 0x80788478,
-	0xc0211b3a, 0x00000078,
-	0x80788478, 0xc0211b7a,
+	0xc0211b7a, 0x00000078,
+	0x80788478, 0xc0211eba,
 	0x00000078, 0x80788478,
-	0xc0211eba, 0x00000078,
-	0x80788478, 0xc0211efa,
+	0xc0211efa, 0x00000078,
+	0x80788478, 0xc0211c3a,
 	0x00000078, 0x80788478,
-	0xc0211c3a, 0x00000078,
-	0x80788478, 0xc0211c7a,
+	0xc0211c7a, 0x00000078,
+	0x80788478, 0xc0211a3a,
 	0x00000078, 0x80788478,
-	0xc0211a3a, 0x00000078,
-	0x80788478, 0xc0211a7a,
+	0xc0211a7a, 0x00000078,
+	0x80788478, 0xc0211cfa,
 	0x00000078, 0x80788478,
-	0xc0211cfa, 0x00000078,
-	0x80788478, 0xbf8cc07f,
-	0xbefc006f, 0xbefe007a,
-	0xbeff007b, 0x866f71ff,
-	0x000003ff, 0xb96f4803,
-	0x866f71ff, 0xfffff800,
-	0x8f6f8b6f, 0xb96fa2c3,
-	0xb973f801, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc0071cb7, 0x00000040,
-	0xc00b1d37, 0x00000048,
-	0xc0031e77, 0x00000058,
-	0xc0071eb7, 0x0000005c,
-	0xbf8cc07f, 0x866fff6d,
-	0xf0000000, 0x8f6f9c6f,
-	0x8e6f906f, 0xbeee0080,
-	0x876e6f6e, 0x866fff6d,
-	0x08000000, 0x8f6f9b6f,
-	0x8e6f8f6f, 0x876e6f6e,
-	0x866fff70, 0x00800000,
-	0x8f6f976f, 0xb96ef807,
-	0x866dff6d, 0x0000ffff,
-	0x86fe7e7e, 0x86ea6a6a,
-	0xb970f802, 0xbf8a0000,
+	0xbf8cc07f, 0xbefc006f,
+	0xbefe007a, 0xbeff007b,
+	0x866f71ff, 0x000003ff,
+	0xb96f4803, 0x866f71ff,
+	0xfffff800, 0x8f6f8b6f,
+	0xb96fa2c3, 0xb973f801,
+	0xb8ee2a05, 0x806e816e,
+	0x8e6e8a6e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc0071cb7,
+	0x00000040, 0xc00b1d37,
+	0x00000048, 0xc0031e77,
+	0x00000058, 0xc0071eb7,
+	0x0000005c, 0xbf8cc07f,
+	0x866fff6d, 0xf0000000,
+	0x8f6f9c6f, 0x8e6f906f,
+	0xbeee0080, 0x876e6f6e,
+	0x866fff6d, 0x08000000,
+	0x8f6f9b6f, 0x8e6f8f6f,
+	0x876e6f6e, 0x866fff70,
+	0x00800000, 0x8f6f976f,
+	0xb96ef807, 0x866dff6d,
+	0x0000ffff, 0x86fe7e7e,
+	0x86ea6a6a, 0x8f6e8370,
+	0xb96ee0c2, 0xbf800002,
+	0xb9700002, 0xbf8a0000,
 	0x95806f6c, 0xbf810000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
index a2a04bb64096..abe1a5da29fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
 var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT    = 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE     = 9
@@ -251,7 +255,7 @@ if (!EMU_RUN_HACK)
     s_waitcnt lgkmcnt(0)
     s_or_b32        ttmp7, ttmp8, ttmp9
     s_cbranch_scc0  L_NO_NEXT_TRAP //next level trap handler not been set
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_setpc_b64     [ttmp8,ttmp9] //jump to next level trap handler
 
 L_NO_NEXT_TRAP:
@@ -262,7 +266,7 @@ L_NO_NEXT_TRAP:
     s_addc_u32  ttmp1, ttmp1, 0
 L_EXCP_CASE:
     s_and_b32   ttmp1, ttmp1, 0xFFFF
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_rfe_b64       [ttmp0, ttmp1]
 end
     // *********        End handling of non-CWSR traps   *******************
@@ -1053,7 +1057,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
     s_and_b64    exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64    vcc, vcc, vcc  // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status     // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier                                                   //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1134,3 +1138,11 @@ end
 function get_hwreg_size_bytes
     return 128 //HWREG size 128 bytes
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index 998be96be736..0bb9c577b3a2 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
 var SQ_WAVE_STATUS_HALT_MASK       = 0x2000
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT	= 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE	= 9
@@ -317,7 +321,7 @@ L_EXCP_CASE:
     // Restore SQ_WAVE_STATUS.
     s_and_b64       exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64       vcc, vcc, vcc    // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status
+    set_status_without_spi_prio(s_save_status, ttmp2)
 
     s_rfe_b64       [ttmp0, ttmp1]
 end
@@ -1120,7 +1124,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff	//pc[47:32]	   //Do it here in order not to affect STATUS
     s_and_b64	 exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64	 vcc, vcc, vcc	// Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status	 // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier							//barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1212,3 +1216,11 @@ function ack_sqc_store_workaround
         s_waitcnt lgkmcnt(0)
     end
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index f64c5551cdba..297b36c26a05 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -122,6 +122,9 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
+	if (kfd_is_locked())
+		return -EAGAIN;
+
 	dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n",
 		process->pasid, process->is_32bit_user_mode);
 
@@ -389,6 +392,61 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
 	return retval;
 }
 
+static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p,
+					void *data)
+{
+	int retval;
+	const int max_num_cus = 1024;
+	struct kfd_ioctl_set_cu_mask_args *args = data;
+	struct queue_properties properties;
+	uint32_t __user *cu_mask_ptr = (uint32_t __user *)args->cu_mask_ptr;
+	size_t cu_mask_size = sizeof(uint32_t) * (args->num_cu_mask / 32);
+
+	if ((args->num_cu_mask % 32) != 0) {
+		pr_debug("num_cu_mask 0x%x must be a multiple of 32",
+				args->num_cu_mask);
+		return -EINVAL;
+	}
+
+	properties.cu_mask_count = args->num_cu_mask;
+	if (properties.cu_mask_count == 0) {
+		pr_debug("CU mask cannot be 0");
+		return -EINVAL;
+	}
+
+	/* To prevent an unreasonably large CU mask size, set an arbitrary
+	 * limit of max_num_cus bits.  We can then just drop any CU mask bits
+	 * past max_num_cus bits and just use the first max_num_cus bits.
+	 */
+	if (properties.cu_mask_count > max_num_cus) {
+		pr_debug("CU mask cannot be greater than 1024 bits");
+		properties.cu_mask_count = max_num_cus;
+		cu_mask_size = sizeof(uint32_t) * (max_num_cus/32);
+	}
+
+	properties.cu_mask = kzalloc(cu_mask_size, GFP_KERNEL);
+	if (!properties.cu_mask)
+		return -ENOMEM;
+
+	retval = copy_from_user(properties.cu_mask, cu_mask_ptr, cu_mask_size);
+	if (retval) {
+		pr_debug("Could not copy CU mask from userspace");
+		kfree(properties.cu_mask);
+		return -EFAULT;
+	}
+
+	mutex_lock(&p->mutex);
+
+	retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties);
+
+	mutex_unlock(&p->mutex);
+
+	if (retval)
+		kfree(properties.cu_mask);
+
+	return retval;
+}
+
 static int kfd_ioctl_set_memory_policy(struct file *filep,
 					struct kfd_process *p, void *data)
 {
@@ -754,7 +812,6 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 {
 	struct kfd_ioctl_get_clock_counters_args *args = data;
 	struct kfd_dev *dev;
-	struct timespec64 time;
 
 	dev = kfd_device_by_id(args->gpu_id);
 	if (dev)
@@ -766,11 +823,8 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 		args->gpu_clock_counter = 0;
 
 	/* No access to rdtsc. Using raw monotonic time */
-	getrawmonotonic64(&time);
-	args->cpu_clock_counter = (uint64_t)timespec64_to_ns(&time);
-
-	get_monotonic_boottime64(&time);
-	args->system_clock_counter = (uint64_t)timespec64_to_ns(&time);
+	args->cpu_clock_counter = ktime_get_raw_ns();
+	args->system_clock_counter = ktime_get_boot_ns();
 
 	/* Since the counter is in nano-seconds we use 1GHz frequency */
 	args->system_clock_freq = 1000000000;
@@ -1558,6 +1612,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU,
 			kfd_ioctl_unmap_memory_from_gpu, 0),
 
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_CU_MASK,
+			kfd_ioctl_set_cu_mask, 0),
+
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 296b3f230280..ee4996029a86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -189,6 +189,21 @@ static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu,
 	return 0;
 }
 
+static struct kfd_mem_properties *
+find_subtype_mem(uint32_t heap_type, uint32_t flags, uint32_t width,
+		struct kfd_topology_device *dev)
+{
+	struct kfd_mem_properties *props;
+
+	list_for_each_entry(props, &dev->mem_props, list) {
+		if (props->heap_type == heap_type
+				&& props->flags == flags
+				&& props->width == width)
+			return props;
+	}
+
+	return NULL;
+}
 /* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct
  * topology device present in the device_list
  */
@@ -197,36 +212,56 @@ static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem,
 {
 	struct kfd_mem_properties *props;
 	struct kfd_topology_device *dev;
+	uint32_t heap_type;
+	uint64_t size_in_bytes;
+	uint32_t flags = 0;
+	uint32_t width;
 
 	pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n",
 			mem->proximity_domain);
 	list_for_each_entry(dev, device_list, list) {
 		if (mem->proximity_domain == dev->proximity_domain) {
-			props = kfd_alloc_struct(props);
-			if (!props)
-				return -ENOMEM;
-
 			/* We're on GPU node */
 			if (dev->node_props.cpu_cores_count == 0) {
 				/* APU */
 				if (mem->visibility_type == 0)
-					props->heap_type =
+					heap_type =
 						HSA_MEM_HEAP_TYPE_FB_PRIVATE;
 				/* dGPU */
 				else
-					props->heap_type = mem->visibility_type;
+					heap_type = mem->visibility_type;
 			} else
-				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
+				heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
 
 			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
-				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
+				flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
 			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
-				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
+				flags |= HSA_MEM_FLAGS_NON_VOLATILE;
 
-			props->size_in_bytes =
+			size_in_bytes =
 				((uint64_t)mem->length_high << 32) +
 							mem->length_low;
-			props->width = mem->width;
+			width = mem->width;
+
+			/* Multiple banks of the same type are aggregated into
+			 * one. User mode doesn't care about multiple physical
+			 * memory segments. It's managed as a single virtual
+			 * heap for user mode.
+			 */
+			props = find_subtype_mem(heap_type, flags, width, dev);
+			if (props) {
+				props->size_in_bytes += size_in_bytes;
+				break;
+			}
+
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->heap_type = heap_type;
+			props->flags = flags;
+			props->size_in_bytes = size_in_bytes;
+			props->width = width;
 
 			dev->node_props.mem_banks_count++;
 			list_add_tail(&props->list, &dev->mem_props);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index afb26f205d29..a3441b0e385b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -38,7 +38,6 @@
 #include "kfd_dbgmgr.h"
 #include "kfd_dbgdev.h"
 #include "kfd_device_queue_manager.h"
-#include "../../radeon/cik_reg.h"
 
 static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
index 03424c20920c..0619c777b47e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
@@ -60,6 +60,9 @@ enum {
 	SH_REG_SIZE = SH_REG_END - SH_REG_BASE
 };
 
+/* SQ_CMD definitions */
+#define SQ_CMD						0x8DEC
+
 enum SQ_IND_CMD_CMD {
 	SQ_IND_CMD_CMD_NULL = 0x00000000,
 	SQ_IND_CMD_CMD_HALT = 0x00000001,
@@ -190,4 +193,38 @@ union ULARGE_INTEGER {
 void kfd_dbgdev_init(struct kfd_dbgdev *pdbgdev, struct kfd_dev *pdev,
 			enum DBGDEV_TYPE type);
 
+union TCP_WATCH_CNTL_BITS {
+	struct {
+		uint32_t mask:24;
+		uint32_t vmid:4;
+		uint32_t atc:1;
+		uint32_t mode:2;
+		uint32_t valid:1;
+	} bitfields, bits;
+	uint32_t u32All;
+	signed int i32All;
+	float f32All;
+};
+
+enum {
+	ADDRESS_WATCH_REG_CNTL_ATC_BIT = 0x10000000UL,
+	ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK = 0x00FFFFFF,
+	ADDRESS_WATCH_REG_ADDLOW_MASK_EXTENSION = 0x03000000,
+	/* extend the mask to 26 bits in order to match the low address field */
+	ADDRESS_WATCH_REG_ADDLOW_SHIFT = 6,
+	ADDRESS_WATCH_REG_ADDHIGH_MASK = 0xFFFF
+};
+
+enum {
+	MAX_TRAPID = 8,		/* 3 bits in the bitfield. */
+	MAX_WATCH_ADDRESSES = 4
+};
+
+enum {
+	ADDRESS_WATCH_REG_ADDR_HI = 0,
+	ADDRESS_WATCH_REG_ADDR_LO,
+	ADDRESS_WATCH_REG_CNTL,
+	ADDRESS_WATCH_REG_MAX
+};
+
 #endif	/* KFD_DBGDEV_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 4bd6ebfaf425..ab37d36d9cd6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -21,6 +21,8 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
+
 #include "kfd_priv.h"
 
 static struct dentry *debugfs_root;
@@ -32,6 +34,38 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file)
 	return single_open(file, show, NULL);
 }
 
+static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
+	const char __user *user_buf, size_t size, loff_t *ppos)
+{
+	struct kfd_dev *dev;
+	char tmp[16];
+	uint32_t gpu_id;
+	int ret = -EINVAL;
+
+	memset(tmp, 0, 16);
+	if (size >= 16) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	if (copy_from_user(tmp, user_buf, size)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	if (kstrtoint(tmp, 10, &gpu_id)) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	dev = kfd_device_by_id(gpu_id);
+	if (dev) {
+		kfd_debugfs_hang_hws(dev);
+		ret = size;
+	} else
+		pr_err("Cannot find device %d.\n", gpu_id);
+
+out:
+	return ret;
+}
+
 static const struct file_operations kfd_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.open = kfd_debugfs_open,
@@ -40,6 +74,15 @@ static const struct file_operations kfd_debugfs_fops = {
 	.release = single_release,
 };
 
+static const struct file_operations kfd_debugfs_hang_hws_fops = {
+	.owner = THIS_MODULE,
+	.open = kfd_debugfs_open,
+	.read = seq_read,
+	.write = kfd_debugfs_hang_hws_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 void kfd_debugfs_init(void)
 {
 	struct dentry *ent;
@@ -65,6 +108,11 @@ void kfd_debugfs_init(void)
 	ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 				  kfd_debugfs_rls_by_device,
 				  &kfd_debugfs_fops);
+
+	ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+				  NULL,
+				  &kfd_debugfs_hang_hws_fops);
+
 	if (!ent)
 		pr_warn("Failed to create rls in kfd debugfs\n");
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 7ee6cec2c060..1b048715ab8a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -30,7 +30,13 @@
 #include "kfd_iommu.h"
 
 #define MQD_SIZE_ALIGNED 768
-static atomic_t kfd_device_suspended = ATOMIC_INIT(0);
+
+/*
+ * kfd_locked is used to lock the kfd driver during suspend or reset
+ * once locked, kfd driver will stop any further GPU execution.
+ * create process (open) will return -EAGAIN.
+ */
+static atomic_t kfd_locked = ATOMIC_INIT(0);
 
 #ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
@@ -46,6 +52,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -61,6 +68,22 @@ static const struct kfd_device_info carrizo_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
+};
+
+static const struct kfd_device_info raven_device_info = {
+	.asic_family = CHIP_RAVEN,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
+	.needs_iommu_device = true,
+	.needs_pci_atomics = true,
+	.num_sdma_engines = 1,
 };
 #endif
 
@@ -77,6 +100,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_device_info = {
@@ -91,6 +115,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_vf_device_info = {
@@ -105,6 +130,7 @@ static const struct kfd_device_info tonga_vf_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_device_info = {
@@ -119,6 +145,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_vf_device_info = {
@@ -133,6 +160,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -148,6 +176,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris10_vf_device_info = {
@@ -162,6 +191,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris11_device_info = {
@@ -176,6 +206,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_device_info = {
@@ -190,6 +221,7 @@ static const struct kfd_device_info vega10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_vf_device_info = {
@@ -204,6 +236,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -241,6 +274,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x9875, &carrizo_device_info },	/* Carrizo */
 	{ 0x9876, &carrizo_device_info },	/* Carrizo */
 	{ 0x9877, &carrizo_device_info },	/* Carrizo */
+	{ 0x15DD, &raven_device_info },		/* Raven */
 #endif
 	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
 	{ 0x67A1, &hawaii_device_info },	/* Hawaii */
@@ -514,13 +548,54 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 	kfree(kfd);
 }
 
+int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+{
+	if (!kfd->init_complete)
+		return 0;
+	kgd2kfd_suspend(kfd);
+
+	/* hold dqm->lock to prevent further execution*/
+	dqm_lock(kfd->dqm);
+
+	kfd_signal_reset_event(kfd);
+	return 0;
+}
+
+/*
+ * Fix me. KFD won't be able to resume existing process for now.
+ * We will keep all existing process in a evicted state and
+ * wait the process to be terminated.
+ */
+
+int kgd2kfd_post_reset(struct kfd_dev *kfd)
+{
+	int ret, count;
+
+	if (!kfd->init_complete)
+		return 0;
+
+	dqm_unlock(kfd->dqm);
+
+	ret = kfd_resume(kfd);
+	if (ret)
+		return ret;
+	count = atomic_dec_return(&kfd_locked);
+	WARN_ONCE(count != 0, "KFD reset ref. error");
+	return 0;
+}
+
+bool kfd_is_locked(void)
+{
+	return  (atomic_read(&kfd_locked) > 0);
+}
+
 void kgd2kfd_suspend(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
 		return;
 
 	/* For first KFD device suspend all the KFD processes */
-	if (atomic_inc_return(&kfd_device_suspended) == 1)
+	if (atomic_inc_return(&kfd_locked) == 1)
 		kfd_suspend_all_processes();
 
 	kfd->dqm->ops.stop(kfd->dqm);
@@ -539,7 +614,7 @@ int kgd2kfd_resume(struct kfd_dev *kfd)
 	if (ret)
 		return ret;
 
-	count = atomic_dec_return(&kfd_device_suspended);
+	count = atomic_dec_return(&kfd_locked);
 	WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
 	if (count == 0)
 		ret = kfd_resume_all_processes();
@@ -577,14 +652,24 @@ dqm_start_error:
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
+	uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE];
+	bool is_patched = false;
+
 	if (!kfd->init_complete)
 		return;
 
+	if (kfd->device_info->ih_ring_entry_size > sizeof(patched_ihre)) {
+		dev_err_once(kfd_device, "Ring entry too small\n");
+		return;
+	}
+
 	spin_lock(&kfd->interrupt_lock);
 
 	if (kfd->interrupts_active
-	    && interrupt_is_wanted(kfd, ih_ring_entry)
-	    && enqueue_ih_ring_entry(kfd, ih_ring_entry))
+	    && interrupt_is_wanted(kfd, 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);
 
 	spin_unlock(&kfd->interrupt_lock);
@@ -739,8 +824,8 @@ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
 	if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size)
 		return -ENOMEM;
 
-	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
-	if ((*mem_obj) == NULL)
+	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
+	if (!(*mem_obj))
 		return -ENOMEM;
 
 	pr_debug("Allocated mem_obj = %p for size = %d\n", *mem_obj, size);
@@ -857,3 +942,26 @@ int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj)
 	kfree(mem_obj);
 	return 0;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+/* This function will send a package to HIQ to hang the HWS
+ * which will trigger a GPU reset and bring the HWS back to normal state
+ */
+int kfd_debugfs_hang_hws(struct kfd_dev *dev)
+{
+	int r = 0;
+
+	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
+		pr_err("HWS is not enabled");
+		return -EINVAL;
+	}
+
+	r = pm_debugfs_hang_hws(&dev->dqm->packets);
+	if (!r)
+		r = dqm_debugfs_execute_queues(dev->dqm);
+
+	return r;
+}
+
+#endif
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 668ad07ebe1f..ec0d62a16e53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -61,6 +61,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id);
 
+static void kfd_process_hw_exception(struct work_struct *work);
+
 static inline
 enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type)
 {
@@ -99,6 +101,17 @@ unsigned int get_pipes_per_mec(struct device_queue_manager *dqm)
 	return dqm->dev->shared_resources.num_pipe_per_mec;
 }
 
+static unsigned int get_num_sdma_engines(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines;
+}
+
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines
+			* KFD_SDMA_QUEUES_PER_ENGINE;
+}
+
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
@@ -240,7 +253,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
 	print_queue(q);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
@@ -297,7 +310,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 			dqm->total_queue_count);
 
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -346,10 +359,10 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
-	mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
-	if (!mqd)
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	retval = allocate_hqd(dqm, q);
@@ -360,7 +373,7 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		goto out_deallocate_hqd;
 
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
@@ -374,15 +387,15 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (!q->properties.is_active)
 		return 0;
 
-	retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties,
-			       q->process->mm);
+	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+			&q->properties, q->process->mm);
 	if (retval)
 		goto out_uninit_mqd;
 
 	return 0;
 
 out_uninit_mqd:
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_hqd:
@@ -399,11 +412,11 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 				struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 		get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd)
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) {
@@ -420,14 +433,14 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 
 	deallocate_doorbell(qpd, q);
 
-	retval = mqd->destroy_mqd(mqd, q->mqd,
+	retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 				KFD_UNMAP_LATENCY_MS,
 				q->pipe, q->queue);
 	if (retval == -ETIME)
 		qpd->reset_wavefronts = true;
 
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 
 	list_del(&q->list);
 	if (list_empty(&qpd->queues_list)) {
@@ -457,9 +470,9 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	retval = destroy_queue_nocpsch_locked(dqm, qpd, q);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 }
@@ -467,19 +480,19 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	bool prev_active = false;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	pdd = kfd_get_process_device_data(q->device, q->process);
 	if (!pdd) {
 		retval = -ENODEV;
 		goto out_unlock;
 	}
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto out_unlock;
 	}
@@ -506,7 +519,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	} else if (prev_active &&
 		   (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		    q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
-		retval = mqd->destroy_mqd(mqd, q->mqd,
+		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval) {
@@ -515,7 +528,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		}
 	}
 
-	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
+	retval = mqd_mgr->update_mqd(mqd_mgr, q->mqd, &q->properties);
 
 	/*
 	 * check active state vs. the previous state and modify
@@ -533,44 +546,44 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	else if (q->properties.is_active &&
 		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		  q->properties.type == KFD_QUEUE_TYPE_SDMA))
-		retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue,
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
 				       &q->properties, q->process->mm);
 
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
 static struct mqd_manager *get_mqd_manager(
 		struct device_queue_manager *dqm, enum KFD_MQD_TYPE type)
 {
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
 	pr_debug("mqd type %d\n", type);
 
-	mqd = dqm->mqds[type];
-	if (!mqd) {
-		mqd = mqd_manager_init(type, dqm->dev);
-		if (!mqd)
+	mqd_mgr = dqm->mqd_mgrs[type];
+	if (!mqd_mgr) {
+		mqd_mgr = mqd_manager_init(type, dqm->dev);
+		if (!mqd_mgr)
 			pr_err("mqd manager is NULL");
-		dqm->mqds[type] = mqd;
+		dqm->mqd_mgrs[type] = mqd_mgr;
 	}
 
-	return mqd;
+	return mqd_mgr;
 }
 
 static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	struct queue *q;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (qpd->evicted++ > 0) /* already evicted, do nothing */
 		goto out;
 
@@ -582,16 +595,16 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_active)
 			continue;
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) { /* should not be here */
+		if (!mqd_mgr) { /* should not be here */
 			pr_err("Cannot evict queue, mqd mgr is NULL\n");
 			retval = -ENOMEM;
 			goto out;
 		}
 		q->properties.is_evicted = true;
 		q->properties.is_active = false;
-		retval = mqd->destroy_mqd(mqd, q->mqd,
+		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval)
@@ -600,7 +613,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	}
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -611,7 +624,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (qpd->evicted++ > 0) /* already evicted, do nothing */
 		goto out;
 
@@ -633,7 +646,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -641,7 +654,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 					  struct qcm_process_device *qpd)
 {
 	struct queue *q;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	uint32_t pd_base;
 	int retval = 0;
@@ -650,7 +663,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
 		goto out;
 	if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */
@@ -677,16 +690,16 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_evicted)
 			continue;
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) { /* should not be here */
+		if (!mqd_mgr) { /* should not be here */
 			pr_err("Cannot restore queue, mqd mgr is NULL\n");
 			retval = -ENOMEM;
 			goto out;
 		}
 		q->properties.is_evicted = false;
 		q->properties.is_active = true;
-		retval = mqd->load_mqd(mqd, q->mqd, q->pipe,
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
 				       q->queue, &q->properties,
 				       q->process->mm);
 		if (retval)
@@ -695,7 +708,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	}
 	qpd->evicted = 0;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -711,7 +724,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
 		goto out;
 	if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */
@@ -739,7 +752,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	if (!retval)
 		qpd->evicted = 0;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -761,7 +774,7 @@ static int register_process(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	list_add(&n->list, &dqm->queues);
 
 	/* Update PD Base in QPD */
@@ -769,9 +782,10 @@ static int register_process(struct device_queue_manager *dqm,
 
 	retval = dqm->asic_ops.update_qpd(dqm, qpd);
 
-	dqm->processes_count++;
+	if (dqm->processes_count++ == 0)
+		dqm->dev->kfd2kgd->set_compute_idle(dqm->dev->kgd, false);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 }
@@ -786,20 +800,22 @@ static int unregister_process(struct device_queue_manager *dqm,
 			list_empty(&qpd->queues_list) ? "empty" : "not empty");
 
 	retval = 0;
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	list_for_each_entry_safe(cur, next, &dqm->queues, list) {
 		if (qpd == cur->qpd) {
 			list_del(&cur->list);
 			kfree(cur);
-			dqm->processes_count--;
+			if (--dqm->processes_count == 0)
+				dqm->dev->kfd2kgd->set_compute_idle(
+					dqm->dev->kgd, true);
 			goto out;
 		}
 	}
 	/* qpd not found in dqm list */
 	retval = 1;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -838,7 +854,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	if (!dqm->allocated_queues)
 		return -ENOMEM;
 
-	mutex_init(&dqm->lock);
+	mutex_init(&dqm->lock_hidden);
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->next_pipe_to_allocate = 0;
 	dqm->sdma_queue_count = 0;
@@ -853,7 +869,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	}
 
 	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
 
 	return 0;
 }
@@ -866,8 +882,8 @@ static void uninitialize(struct device_queue_manager *dqm)
 
 	kfree(dqm->allocated_queues);
 	for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++)
-		kfree(dqm->mqds[i]);
-	mutex_destroy(&dqm->lock);
+		kfree(dqm->mqd_mgrs[i]);
+	mutex_destroy(&dqm->lock_hidden);
 	kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem);
 }
 
@@ -901,7 +917,7 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id)
 {
-	if (sdma_queue_id >= CIK_SDMA_QUEUES)
+	if (sdma_queue_id >= get_num_sdma_queues(dqm))
 		return;
 	dqm->sdma_bitmap |= (1 << sdma_queue_id);
 }
@@ -910,19 +926,19 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
 					struct qcm_process_device *qpd)
 {
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	int retval;
 
-	mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
-	if (!mqd)
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	retval = allocate_sdma_queue(dqm, &q->sdma_id);
 	if (retval)
 		return retval;
 
-	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
-	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+	q->properties.sdma_queue_id = q->sdma_id / get_num_sdma_engines(dqm);
+	q->properties.sdma_engine_id = q->sdma_id % get_num_sdma_engines(dqm);
 
 	retval = allocate_doorbell(qpd, q);
 	if (retval)
@@ -933,19 +949,20 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id);
 
 	dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
 
-	retval = mqd->load_mqd(mqd, q->mqd, 0, 0, &q->properties, NULL);
+	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, 0, 0, &q->properties,
+				NULL);
 	if (retval)
 		goto out_uninit_mqd;
 
 	return 0;
 
 out_uninit_mqd:
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
@@ -1003,12 +1020,14 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 {
 	pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm));
 
-	mutex_init(&dqm->lock);
+	mutex_init(&dqm->lock_hidden);
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
 	dqm->active_runlist = false;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
+
+	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
 	return 0;
 }
@@ -1041,9 +1060,11 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	init_interrupts(dqm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
+	/* clear hang status when driver try to start the hw scheduler */
+	dqm->is_hws_hang = false;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return 0;
 fail_allocate_vidmem:
@@ -1055,9 +1076,9 @@ fail_packet_manager_init:
 
 static int stop_cpsch(struct device_queue_manager *dqm)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets);
@@ -1069,11 +1090,11 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
 					struct qcm_process_device *qpd)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new kernel queue because %d queues were already created\n",
 				dqm->total_queue_count);
-		mutex_unlock(&dqm->lock);
+		dqm_unlock(dqm);
 		return -EPERM;
 	}
 
@@ -1089,7 +1110,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->queue_count++;
 	qpd->is_debug = true;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return 0;
 }
@@ -1098,7 +1119,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
 					struct qcm_process_device *qpd)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	list_del(&kq->list);
 	dqm->queue_count--;
 	qpd->is_debug = false;
@@ -1110,18 +1131,18 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->total_queue_count--;
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 }
 
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 			struct qcm_process_device *qpd)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
 	retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
@@ -1135,19 +1156,19 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		if (retval)
 			goto out_unlock;
 		q->properties.sdma_queue_id =
-			q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id / get_num_sdma_engines(dqm);
 		q->properties.sdma_engine_id =
-			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id % get_num_sdma_engines(dqm);
 	}
 
 	retval = allocate_doorbell(qpd, q);
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto out_deallocate_doorbell;
 	}
@@ -1164,7 +1185,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	q->properties.tba_addr = qpd->tba_addr;
 	q->properties.tma_addr = qpd->tma_addr;
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
@@ -1188,7 +1209,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 
 out_deallocate_doorbell:
@@ -1197,7 +1218,8 @@ out_deallocate_sdma_queue:
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		deallocate_sdma_queue(dqm, q->sdma_id);
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
+
 	return retval;
 }
 
@@ -1210,6 +1232,13 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
 	while (*fence_addr != fence_value) {
 		if (time_after(jiffies, end_jiffies)) {
 			pr_err("qcm fence wait loop timeout expired\n");
+			/* In HWS case, this is used to halt the driver thread
+			 * in order not to mess up CP states before doing
+			 * scandumps for FW debugging.
+			 */
+			while (halt_if_hws_hang)
+				schedule();
+
 			return -ETIME;
 		}
 		schedule();
@@ -1254,6 +1283,8 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval = 0;
 
+	if (dqm->is_hws_hang)
+		return -EIO;
 	if (!dqm->active_runlist)
 		return retval;
 
@@ -1292,9 +1323,13 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 
+	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);
 		return retval;
 	}
 
@@ -1306,7 +1341,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 				struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	bool preempt_all_queues;
 
 	preempt_all_queues = false;
@@ -1314,7 +1349,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	retval = 0;
 
 	/* remove queue from list to prevent rescheduling after preemption */
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (qpd->is_debug) {
 		/*
@@ -1326,9 +1361,9 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	}
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto failed;
 	}
@@ -1350,7 +1385,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 			qpd->reset_wavefronts = true;
 	}
 
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 
 	/*
 	 * Unconditionally decrement this counter, regardless of the queue's
@@ -1360,14 +1395,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 
 failed:
 failed_try_destroy_debugged_queue:
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1391,7 +1426,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 	if (!dqm->asic_ops.set_cache_memory_policy)
 		return retval;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (alternate_aperture_size == 0) {
 		/* base > limit disables APE1 */
@@ -1437,7 +1472,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 		qpd->sh_mem_ape1_limit);
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1468,7 +1503,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 	struct device_process_node *cur, *next_dpn;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	/* Clear all user mode queues */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
@@ -1489,7 +1524,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 		}
 	}
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1500,14 +1535,14 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	int retval;
 	struct queue *q, *next;
 	struct kernel_queue *kq, *kq_next;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct device_process_node *cur, *next_dpn;
 	enum kfd_unmap_queues_filter filter =
 		KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES;
 
 	retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	/* Clean all kernel queues */
 	list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) {
@@ -1542,7 +1577,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	}
 
 	retval = execute_queues_cpsch(dqm, filter, 0);
-	if (retval || qpd->reset_wavefronts) {
+	if ((!dqm->is_hws_hang) && (retval || qpd->reset_wavefronts)) {
 		pr_warn("Resetting wave fronts (cpsch) on dev %p\n", dqm->dev);
 		dbgdev_wave_reset_wavefronts(dqm->dev, qpd->pqm->process);
 		qpd->reset_wavefronts = false;
@@ -1550,19 +1585,19 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 
 	/* lastly, free mqd resources */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) {
+		if (!mqd_mgr) {
 			retval = -ENOMEM;
 			goto out;
 		}
 		list_del(&q->list);
 		qpd->queue_count--;
-		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 	}
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1683,6 +1718,30 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
+int kfd_process_vm_fault(struct device_queue_manager *dqm,
+			 unsigned int pasid)
+{
+	struct kfd_process_device *pdd;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	int ret = 0;
+
+	if (!p)
+		return -EINVAL;
+	pdd = kfd_get_process_device_data(dqm->dev, p);
+	if (pdd)
+		ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd);
+	kfd_unref_process(p);
+
+	return ret;
+}
+
+static void kfd_process_hw_exception(struct work_struct *work)
+{
+	struct device_queue_manager *dqm = container_of(work,
+			struct device_queue_manager, hw_exception_work);
+	dqm->dev->kfd2kgd->gpu_recover(dqm->dev->kgd);
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static void seq_reg_dump(struct seq_file *m,
@@ -1746,8 +1805,8 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 		}
 	}
 
-	for (pipe = 0; pipe < CIK_SDMA_ENGINE_NUM; pipe++) {
-		for (queue = 0; queue < CIK_SDMA_QUEUES_PER_ENGINE; queue++) {
+	for (pipe = 0; pipe < get_num_sdma_engines(dqm); pipe++) {
+		for (queue = 0; queue < KFD_SDMA_QUEUES_PER_ENGINE; queue++) {
 			r = dqm->dev->kfd2kgd->hqd_sdma_dump(
 				dqm->dev->kgd, pipe, queue, &dump, &n_regs);
 			if (r)
@@ -1764,4 +1823,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	return r;
 }
 
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm)
+{
+	int r = 0;
+
+	dqm_lock(dqm);
+	dqm->active_runlist = true;
+	r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	dqm_unlock(dqm);
+
+	return r;
+}
+
 #endif
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 59a6b1956932..00da3169a004 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -26,15 +26,14 @@
 
 #include <linux/rwsem.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 
 #define KFD_UNMAP_LATENCY_MS			(4000)
 #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000)
-
-#define CIK_SDMA_QUEUES				(4)
-#define CIK_SDMA_QUEUES_PER_ENGINE		(2)
-#define CIK_SDMA_ENGINE_NUM			(2)
+#define KFD_SDMA_QUEUES_PER_ENGINE		(2)
 
 struct device_process_node {
 	struct qcm_process_device *qpd;
@@ -170,11 +169,12 @@ struct device_queue_manager {
 	struct device_queue_manager_ops ops;
 	struct device_queue_manager_asic_ops asic_ops;
 
-	struct mqd_manager	*mqds[KFD_MQD_TYPE_MAX];
+	struct mqd_manager	*mqd_mgrs[KFD_MQD_TYPE_MAX];
 	struct packet_manager	packets;
 	struct kfd_dev		*dev;
-	struct mutex		lock;
+	struct mutex		lock_hidden; /* use dqm_lock/unlock(dqm) */
 	struct list_head	queues;
+	unsigned int		saved_flags;
 	unsigned int		processes_count;
 	unsigned int		queue_count;
 	unsigned int		sdma_queue_count;
@@ -190,6 +190,10 @@ struct device_queue_manager {
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;
+
+	/* hw exception  */
+	bool			is_hws_hang;
+	struct work_struct	hw_exception_work;
 };
 
 void device_queue_manager_init_cik(
@@ -207,6 +211,7 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
 unsigned int get_queues_num(struct device_queue_manager *dqm);
 unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
@@ -219,4 +224,19 @@ get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd)
 	return (pdd->lds_base >> 60) & 0x0E;
 }
 
+/* The DQM 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 dqm_lock(struct device_queue_manager *dqm)
+{
+	mutex_lock(&dqm->lock_hidden);
+	dqm->saved_flags = memalloc_nofs_save();
+}
+static inline void dqm_unlock(struct device_queue_manager *dqm)
+{
+	memalloc_nofs_restore(dqm->saved_flags);
+	mutex_unlock(&dqm->lock_hidden);
+}
+
 #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 79e5bcf6367c..417515332c35 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -60,7 +60,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 		qpd->sh_mem_config =
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
-		if (vega10_noretry &&
+		if (noretry &&
 		    !dqm->dev->device_info->needs_iommu_device)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index c3744d89352c..ebe79bf00145 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -188,9 +188,9 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	*doorbell_off = kfd->doorbell_id_offset + inx;
 
 	pr_debug("Get kernel queue doorbell\n"
-			 "     doorbell offset   == 0x%08X\n"
-			 "     kernel address    == %p\n",
-		*doorbell_off, (kfd->doorbell_kernel_ptr + inx));
+			"     doorbell offset   == 0x%08X\n"
+			"     doorbell index    == 0x%x\n",
+		*doorbell_off, inx);
 
 	return kfd->doorbell_kernel_ptr + inx;
 }
@@ -199,7 +199,8 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 {
 	unsigned int inx;
 
-	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr)
+		* sizeof(u32) / kfd->device_info->doorbell_size;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_available_index);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 5562e94e786a..e9f0e0a1b41c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -850,6 +850,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 				ev->memory_exception_data = *ev_data;
 		}
 
+	if (type == KFD_EVENT_TYPE_MEMORY) {
+		dev_warn(kfd_device,
+			"Sending SIGSEGV to HSA Process with PID %d ",
+				p->lead_thread->pid);
+		send_sig(SIGSEGV, p->lead_thread, 0);
+	}
+
 	/* Send SIGTERM no event of type "type" has been found*/
 	if (send_signal) {
 		if (send_sigterm) {
@@ -904,34 +911,41 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	memory_exception_data.failure.NotPresent = 1;
 	memory_exception_data.failure.NoExecute = 0;
 	memory_exception_data.failure.ReadOnly = 0;
-	if (vma) {
-		if (vma->vm_start > address) {
-			memory_exception_data.failure.NotPresent = 1;
-			memory_exception_data.failure.NoExecute = 0;
+	if (vma && address >= vma->vm_start) {
+		memory_exception_data.failure.NotPresent = 0;
+
+		if (is_write_requested && !(vma->vm_flags & VM_WRITE))
+			memory_exception_data.failure.ReadOnly = 1;
+		else
 			memory_exception_data.failure.ReadOnly = 0;
-		} else {
-			memory_exception_data.failure.NotPresent = 0;
-			if (is_write_requested && !(vma->vm_flags & VM_WRITE))
-				memory_exception_data.failure.ReadOnly = 1;
-			else
-				memory_exception_data.failure.ReadOnly = 0;
-			if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
-				memory_exception_data.failure.NoExecute = 1;
-			else
-				memory_exception_data.failure.NoExecute = 0;
-		}
+
+		if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
+			memory_exception_data.failure.NoExecute = 1;
+		else
+			memory_exception_data.failure.NoExecute = 0;
 	}
 
 	up_read(&mm->mmap_sem);
 	mmput(mm);
 
-	mutex_lock(&p->event_mutex);
+	pr_debug("notpresent %d, noexecute %d, readonly %d\n",
+			memory_exception_data.failure.NotPresent,
+			memory_exception_data.failure.NoExecute,
+			memory_exception_data.failure.ReadOnly);
 
-	/* Lookup events by type and signal them */
-	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
-			&memory_exception_data);
+	/* Workaround on Raven to not kill the process when memory is freed
+	 * before IOMMU is able to finish processing all the excessive PPRs
+	 */
+	if (dev->device_info->asic_family != CHIP_RAVEN) {
+		mutex_lock(&p->event_mutex);
+
+		/* Lookup events by type and signal them */
+		lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
+				&memory_exception_data);
+
+		mutex_unlock(&p->event_mutex);
+	}
 
-	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
@@ -956,3 +970,67 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
+
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info)
+{
+	struct kfd_event *ev;
+	uint32_t id;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	struct kfd_hsa_memory_exception_data memory_exception_data;
+
+	if (!p)
+		return; /* Presumably process exited. */
+	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
+	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.failure.imprecise = 1;
+	/* Set failure reason */
+	if (info) {
+		memory_exception_data.va = (info->page_addr) << PAGE_SHIFT;
+		memory_exception_data.failure.NotPresent =
+			info->prot_valid ? 1 : 0;
+		memory_exception_data.failure.NoExecute =
+			info->prot_exec ? 1 : 0;
+		memory_exception_data.failure.ReadOnly =
+			info->prot_write ? 1 : 0;
+		memory_exception_data.failure.imprecise = 0;
+	}
+	mutex_lock(&p->event_mutex);
+
+	id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+	idr_for_each_entry_continue(&p->event_idr, ev, id)
+		if (ev->type == KFD_EVENT_TYPE_MEMORY) {
+			ev->memory_exception_data = memory_exception_data;
+			set_event(ev);
+		}
+
+	mutex_unlock(&p->event_mutex);
+	kfd_unref_process(p);
+}
+
+void kfd_signal_reset_event(struct kfd_dev *dev)
+{
+	struct kfd_hsa_hw_exception_data hw_exception_data;
+	struct kfd_process *p;
+	struct kfd_event *ev;
+	unsigned int temp;
+	uint32_t id, idx;
+
+	/* Whole gpu reset caused by GPU hang and memory is lost */
+	memset(&hw_exception_data, 0, sizeof(hw_exception_data));
+	hw_exception_data.gpu_id = dev->id;
+	hw_exception_data.memory_lost = 1;
+
+	idx = srcu_read_lock(&kfd_processes_srcu);
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		mutex_lock(&p->event_mutex);
+		id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+		idr_for_each_entry_continue(&p->event_idr, ev, id)
+			if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
+				ev->hw_exception_data = hw_exception_data;
+				set_event(ev);
+			}
+		mutex_unlock(&p->event_mutex);
+	}
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index abca5bfebbff..c7ac6c73af86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -66,6 +66,7 @@ struct kfd_event {
 	/* type specific data */
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};
 };
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 37029baa3346..f836897bbf58 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -26,7 +26,9 @@
 
 
 static bool event_interrupt_isr_v9(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	uint16_t source_id, client_id, pasid, vmid;
 	const uint32_t *data = ih_ring_entry;
@@ -57,7 +59,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev,
 	return source_id == SOC15_INTSRC_CP_END_OF_PIPE ||
 		source_id == SOC15_INTSRC_SDMA_TRAP ||
 		source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG ||
-		source_id == SOC15_INTSRC_CP_BAD_OPCODE;
+		source_id == SOC15_INTSRC_CP_BAD_OPCODE ||
+		client_id == SOC15_IH_CLIENTID_VMC ||
+		client_id == SOC15_IH_CLIENTID_UTCL2;
 }
 
 static void event_interrupt_wq_v9(struct kfd_dev *dev,
@@ -82,7 +86,19 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 		kfd_signal_hw_exception_event(pasid);
 	else if (client_id == SOC15_IH_CLIENTID_VMC ||
 		 client_id == SOC15_IH_CLIENTID_UTCL2) {
-		/* TODO */
+		struct kfd_vm_fault_info info = {0};
+		uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry);
+
+		info.vmid = vmid;
+		info.mc_id = client_id;
+		info.page_addr = ih_ring_entry[4] |
+			(uint64_t)(ih_ring_entry[5] & 0xf) << 32;
+		info.prot_valid = ring_id & 0x08;
+		info.prot_read  = ring_id & 0x10;
+		info.prot_write = ring_id & 0x20;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+		kfd_signal_vm_fault_event(dev, pasid, &info);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index db6d9336b80d..c56ac47cd318 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -151,13 +151,15 @@ static void interrupt_wq(struct work_struct *work)
 								ih_ring_entry);
 }
 
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry)
+bool interrupt_is_wanted(struct kfd_dev *dev,
+			const uint32_t *ih_ring_entry,
+			uint32_t *patched_ihre, bool *flag)
 {
 	/* integer and bitwise OR so there is no boolean short-circuiting */
 	unsigned int wanted = 0;
 
 	wanted |= dev->device_info->event_interrupt_class->interrupt_isr(dev,
-								ih_ring_entry);
+					 ih_ring_entry, patched_ihre, flag);
 
 	return wanted != 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index c71817963eea..7a61f38c09e6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -190,7 +190,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 {
 	struct kfd_dev *dev;
 
-	dev_warn(kfd_device,
+	dev_warn_ratelimited(kfd_device,
 			"Invalid PPR device %x:%x.%x pasid %d address 0x%lX flags 0x%X",
 			PCI_BUS_NUM(pdev->devfn),
 			PCI_SLOT(pdev->devfn),
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 476951d8c91c..9f84b4d9fb88 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -59,7 +59,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	switch (type) {
 	case KFD_QUEUE_TYPE_DIQ:
 	case KFD_QUEUE_TYPE_HIQ:
-		kq->mqd = dev->dqm->ops.get_mqd_manager(dev->dqm,
+		kq->mqd_mgr = dev->dqm->ops.get_mqd_manager(dev->dqm,
 						KFD_MQD_TYPE_HIQ);
 		break;
 	default:
@@ -67,7 +67,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		return false;
 	}
 
-	if (!kq->mqd)
+	if (!kq->mqd_mgr)
 		return false;
 
 	prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off);
@@ -123,6 +123,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	prop.write_ptr = (uint32_t *) kq->wptr_gpu_addr;
 	prop.eop_ring_buffer_address = kq->eop_gpu_addr;
 	prop.eop_ring_buffer_size = PAGE_SIZE;
+	prop.cu_mask = NULL;
 
 	if (init_queue(&kq->queue, &prop) != 0)
 		goto err_init_queue;
@@ -130,7 +131,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->queue->device = dev;
 	kq->queue->process = kfd_get_process(current);
 
-	retval = kq->mqd->init_mqd(kq->mqd, &kq->queue->mqd,
+	retval = kq->mqd_mgr->init_mqd(kq->mqd_mgr, &kq->queue->mqd,
 					&kq->queue->mqd_mem_obj,
 					&kq->queue->gart_mqd_addr,
 					&kq->queue->properties);
@@ -142,9 +143,9 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		pr_debug("Assigning hiq to hqd\n");
 		kq->queue->pipe = KFD_CIK_HIQ_PIPE;
 		kq->queue->queue = KFD_CIK_HIQ_QUEUE;
-		kq->mqd->load_mqd(kq->mqd, kq->queue->mqd, kq->queue->pipe,
-				  kq->queue->queue, &kq->queue->properties,
-				  NULL);
+		kq->mqd_mgr->load_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->pipe, kq->queue->queue,
+				&kq->queue->properties, NULL);
 	} else {
 		/* allocate fence for DIQ */
 
@@ -182,7 +183,7 @@ err_get_kernel_doorbell:
 static void uninitialize(struct kernel_queue *kq)
 {
 	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
-		kq->mqd->destroy_mqd(kq->mqd,
+		kq->mqd_mgr->destroy_mqd(kq->mqd_mgr,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 					KFD_UNMAP_LATENCY_MS,
@@ -191,7 +192,8 @@ static void uninitialize(struct kernel_queue *kq)
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
 		kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj);
 
-	kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj);
+	kq->mqd_mgr->uninit_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->mqd_mem_obj);
 
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
index 97aff2041a5d..a7116a939029 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
@@ -70,7 +70,7 @@ struct kernel_queue {
 
 	/* data */
 	struct kfd_dev		*dev;
-	struct mqd_manager	*mqd;
+	struct mqd_manager	*mqd_mgr;
 	struct queue		*queue;
 	uint64_t		pending_wptr64;
 	uint32_t		pending_wptr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 76bf2dc8aec4..6e1f5c7c2d4b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -47,6 +47,8 @@ static const struct kgd2kfd_calls kgd2kfd = {
 	.resume_mm	= kgd2kfd_resume_mm,
 	.schedule_evict_and_restore_process =
 			  kgd2kfd_schedule_evict_and_restore_process,
+	.pre_reset	= kgd2kfd_pre_reset,
+	.post_reset	= kgd2kfd_post_reset,
 };
 
 int sched_policy = KFD_SCHED_POLICY_HWS;
@@ -61,7 +63,7 @@ MODULE_PARM_DESC(hws_max_conc_proc,
 
 int cwsr_enable = 1;
 module_param(cwsr_enable, int, 0444);
-MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = Off, 1 = On (Default))");
+MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = off, 1 = on (default))");
 
 int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
 module_param(max_num_of_queues_per_device, int, 0444);
@@ -83,13 +85,19 @@ module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
 	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
 
-int vega10_noretry;
-module_param_named(noretry, vega10_noretry, int, 0644);
+int noretry;
+module_param(noretry, int, 0644);
 MODULE_PARM_DESC(noretry,
-	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
+	"Set sh_mem_config.retry_disable on GFXv9+ dGPUs (0 = retry enabled (default), 1 = retry disabled)");
+
+int halt_if_hws_hang;
+module_param(halt_if_hws_hang, int, 0644);
+MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
+
 
 static int amdkfd_init_completed;
 
+
 int kgd2kfd_init(unsigned int interface_version,
 		const struct kgd2kfd_calls **g2f)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 4b8eb506642b..3bc25ab84f34 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -21,7 +21,7 @@
  *
  */
 
-#include "kfd_priv.h"
+#include "kfd_mqd_manager.h"
 
 struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 					struct kfd_dev *dev)
@@ -48,3 +48,42 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 
 	return NULL;
 }
+
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask)
+{
+	struct kfd_cu_info cu_info;
+	uint32_t cu_per_sh[4] = {0};
+	int i, se, cu = 0;
+
+	mm->dev->kfd2kgd->get_cu_info(mm->dev->kgd, &cu_info);
+
+	if (cu_mask_count > cu_info.cu_active_number)
+		cu_mask_count = cu_info.cu_active_number;
+
+	for (se = 0; se < cu_info.num_shader_engines; se++)
+		for (i = 0; i < 4; i++)
+			cu_per_sh[se] += hweight32(cu_info.cu_bitmap[se][i]);
+
+	/* Symmetrically map cu_mask to all SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0;
+	 * cu_mask[0] bit1 -> se_mask[1] bit0;
+	 * ... (if # SE is 4)
+	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+	 * ...
+	 */
+	se = 0;
+	for (i = 0; i < cu_mask_count; i++) {
+		if (cu_mask[i / 32] & (1 << (i % 32)))
+			se_mask[se] |= 1 << cu;
+
+		do {
+			se++;
+			if (se == cu_info.num_shader_engines) {
+				se = 0;
+				cu++;
+			}
+		} while (cu >= cu_per_sh[se] && cu < 32);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 8972bcfbf701..4e84052d4e21 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -93,4 +93,8 @@ struct mqd_manager {
 	struct kfd_dev	*dev;
 };
 
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask);
+
 #endif /* KFD_MQD_MANAGER_H_ */
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 06eaa218eba6..47243165a082 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -41,6 +41,31 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
 	return (struct cik_sdma_rlc_registers *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct cik_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	if (q->format == KFD_QUEUE_FORMAT_AQL)
 		m->cp_hqd_pq_control |= NO_UPDATE_RPTR;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -408,7 +435,7 @@ struct mqd_manager *mqd_manager_init_cik(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;
 
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 684054ff02cd..f5fc3675f21e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -41,6 +41,31 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct v9_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct v9_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -55,7 +80,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 	 * 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 -ENOMEM;
 		retval = kfd->kfd2kgd->init_gtt_mem_allocation(kfd->kgd,
@@ -198,6 +223,8 @@ static int update_mqd(struct mqd_manager *mm, void *mqd,
 	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address)
 		m->cp_hqd_ctx_save_control = 0;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -393,7 +420,7 @@ struct mqd_manager *mqd_manager_init_v9(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;
 
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 481307b8b4db..b81fda3754da 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -43,6 +43,31 @@ static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct vi_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct vi_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 			atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT |
 			mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
@@ -394,7 +421,7 @@ struct mqd_manager *mqd_manager_init_vi(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;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index c317feb43f69..1092631765cb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -418,4 +418,30 @@ out:
 	return 0;
 }
 
+int pm_debugfs_hang_hws(struct packet_manager *pm)
+{
+	uint32_t *buffer, size;
+	int r = 0;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	pm->priv_queue->ops.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");
+		r = -ENOMEM;
+		goto out;
+	}
+	memset(buffer, 0x55, size);
+	pm->priv_queue->ops.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],
+		buffer[4], buffer[5], buffer[6]);
+out:
+	mutex_unlock(&pm->lock);
+	return r;
+}
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 5e3990bb4c4b..f971710f1c91 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -73,7 +73,7 @@
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
- * the radeon driver to a fixed hqd slot, here are the fixed HIQ hqd slot
+ * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot
  * definitions for Kaveri. In Kaveri only the first ME queues participates
  * in the cp scheduling taking that in mind we set the HIQ slot in the
  * second ME.
@@ -142,7 +142,12 @@ extern int ignore_crat;
 /*
  * Set sh_mem_config.retry_disable on Vega10
  */
-extern int vega10_noretry;
+extern int noretry;
+
+/*
+ * Halt if HWS hang is detected
+ */
+extern int halt_if_hws_hang;
 
 /**
  * enum kfd_sched_policy
@@ -180,9 +185,10 @@ enum cache_policy {
 
 struct kfd_event_interrupt_class {
 	bool (*interrupt_isr)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry, uint32_t *patched_ihre,
+			bool *patched_flag);
 	void (*interrupt_wq)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry);
 };
 
 struct kfd_device_info {
@@ -197,6 +203,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	unsigned int num_sdma_engines;
 };
 
 struct kfd_mem_obj {
@@ -415,6 +422,9 @@ struct queue_properties {
 	uint32_t ctl_stack_size;
 	uint64_t tba_addr;
 	uint64_t tma_addr;
+	/* Relevant for CU */
+	uint32_t cu_mask_count; /* Must be a multiple of 32 */
+	uint32_t *cu_mask;
 };
 
 /**
@@ -806,12 +816,18 @@ int kfd_interrupt_init(struct kfd_dev *dev);
 void kfd_interrupt_exit(struct kfd_dev *dev);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 bool enqueue_ih_ring_entry(struct kfd_dev *kfd,	const void *ih_ring_entry);
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry);
+bool interrupt_is_wanted(struct kfd_dev *dev,
+				const uint32_t *ih_ring_entry,
+				uint32_t *patched_ihre, bool *flag);
 
 /* Power Management */
 void kgd2kfd_suspend(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd);
 
+/* GPU reset */
+int kgd2kfd_pre_reset(struct kfd_dev *kfd);
+int kgd2kfd_post_reset(struct kfd_dev *kfd);
+
 /* amdkfd Apertures */
 int kfd_init_apertures(struct kfd_process *process);
 
@@ -838,6 +854,7 @@ 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);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -858,6 +875,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 			struct queue_properties *p);
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p);
 struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm,
 						unsigned int qid);
 
@@ -964,10 +983,17 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info);
+
+void kfd_signal_reset_event(struct kfd_dev *dev);
+
 void kfd_flush_tlb(struct kfd_process_device *pdd);
 
 int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
+bool kfd_is_locked(void);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
@@ -980,6 +1006,10 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data);
 int kfd_debugfs_rls_by_device(struct seq_file *m, void *data);
 int pm_debugfs_runlist(struct seq_file *m, void *data);
 
+int kfd_debugfs_hang_hws(struct kfd_dev *dev);
+int pm_debugfs_hang_hws(struct packet_manager *pm);
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm);
+
 #else
 
 static inline void kfd_debugfs_init(void) {}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 1d80b4f7c681..4694386cc623 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -244,6 +244,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread)
 		return ERR_PTR(-EINVAL);
 
 	process = find_process(thread);
+	if (!process)
+		return ERR_PTR(-EINVAL);
 
 	return process;
 }
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 d65ce0436b31..c8cad9c078ae 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -186,8 +186,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
-		if (dev->dqm->queue_count >=
-			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+		if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) {
 			pr_err("Over-subscription is not allowed for SDMA.\n");
 			retval = -EPERM;
 			goto err_create_queue;
@@ -209,7 +208,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		     KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
 		((dev->dqm->processes_count >= dev->vm_info.vmid_num_kfd) ||
 		(dev->dqm->queue_count >= get_queues_num(dev->dqm)))) {
-			pr_err("Over-subscription is not allowed in radeon_kfd.sched_policy == 1\n");
+			pr_debug("Over-subscription is not allowed when amdkfd.sched_policy == 1\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
@@ -326,6 +325,8 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 			if (retval != -ETIME)
 				goto err_destroy_queue;
 		}
+		kfree(pqn->q->properties.cu_mask);
+		pqn->q->properties.cu_mask = NULL;
 		uninit_queue(pqn->q);
 	}
 
@@ -366,6 +367,34 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 	return 0;
 }
 
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p)
+{
+	int retval;
+	struct process_queue_node *pqn;
+
+	pqn = get_queue_by_qid(pqm, qid);
+	if (!pqn) {
+		pr_debug("No queue %d exists for update operation\n", qid);
+		return -EFAULT;
+	}
+
+	/* Free the old CU mask memory if it is already allocated, then
+	 * allocate memory for the new CU mask.
+	 */
+	kfree(pqn->q->properties.cu_mask);
+
+	pqn->q->properties.cu_mask_count = p->cu_mask_count;
+	pqn->q->properties.cu_mask = p->cu_mask;
+
+	retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
+							pqn->q);
+	if (retval != 0)
+		return retval;
+
+	return 0;
+}
+
 struct kernel_queue *pqm_get_kernel_queue(
 					struct process_queue_manager *pqm,
 					unsigned int qid)
@@ -387,7 +416,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 	struct process_queue_node *pqn;
 	struct queue *q;
 	enum KFD_MQD_TYPE mqd_type;
-	struct mqd_manager *mqd_manager;
+	struct mqd_manager *mqd_mgr;
 	int r = 0;
 
 	list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
@@ -410,11 +439,11 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 					   q->properties.type, q->device->id);
 				continue;
 			}
-			mqd_manager = q->device->dqm->ops.get_mqd_manager(
+			mqd_mgr = q->device->dqm->ops.get_mqd_manager(
 				q->device->dqm, mqd_type);
 		} else if (pqn->kq) {
 			q = pqn->kq->queue;
-			mqd_manager = pqn->kq->mqd;
+			mqd_mgr = pqn->kq->mqd_mgr;
 			switch (q->properties.type) {
 			case KFD_QUEUE_TYPE_DIQ:
 				seq_printf(m, "  DIQ on device %x\n",
@@ -434,7 +463,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 			continue;
 		}
 
-		r = mqd_manager->debugfs_show_mqd(m, q->mqd);
+		r = mqd_mgr->debugfs_show_mqd(m, q->mqd);
 		if (r != 0)
 			break;
 	}
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 4c35625eb2c7..325083b0297e 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -9,14 +9,6 @@ config DRM_AMD_DC
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_DCN1_0
-	bool "DCN 1.0 Raven family"
-	depends on DRM_AMD_DC && X86
-	default y
-	help
-	  Choose this option if you want to have
-	  RV family for display engine
-
 config DEBUG_KERNEL_DC
 	bool "Enable kgdb break in DC"
 	depends on DRM_AMD_DC
diff --git a/drivers/gpu/drm/amd/display/TODO b/drivers/gpu/drm/amd/display/TODO
index 357d59648401..a8a6c106e8c7 100644
--- a/drivers/gpu/drm/amd/display/TODO
+++ b/drivers/gpu/drm/amd/display/TODO
@@ -97,10 +97,10 @@ share it with drivers. But that's a very long term goal, and by far not just an
 issue with DC - other drivers, especially around DP sink handling, are equally
 guilty.
 
-19. The DC logger is still a rather sore thing, but I know that the DRM_DEBUG
-stuff just isn't up to the challenges either. We need to figure out something
-that integrates better with DRM and linux debug printing, while not being
-useless with filtering output. dynamic debug printing might be an option.
+19. DONE - The DC logger is still a rather sore thing, but I know that the
+DRM_DEBUG stuff just isn't up to the challenges either. We need to figure out
+something that integrates better with DRM and linux debug printing, while not
+being useless with filtering output. dynamic debug printing might be an option.
 
 20. Use kernel i2c device to program HDMI retimer. Some boards have an HDMI
 retimer that we need to program to pass PHY compliance. Currently that's
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index af16973f2c41..94911871eb9b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -28,11 +28,11 @@
 AMDGPUDM = amdgpu_dm.o amdgpu_dm_irq.o amdgpu_dm_mst_types.o amdgpu_dm_color.o
 
 ifneq ($(CONFIG_DRM_AMD_DC),)
-AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o
+AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o
 endif
 
 ifneq ($(CONFIG_DEBUG_FS),)
-AMDGPUDM += amdgpu_dm_crc.o
+AMDGPUDM += amdgpu_dm_crc.o amdgpu_dm_debugfs.o
 endif
 
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc
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 66bd3cc3e387..45e062022461 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -39,6 +39,9 @@
 #include "dm_helpers.h"
 #include "dm_services_types.h"
 #include "amdgpu_dm_mst_types.h"
+#if defined(CONFIG_DEBUG_FS)
+#include "amdgpu_dm_debugfs.h"
+#endif
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
@@ -57,7 +60,7 @@
 
 #include "modules/inc/mod_freesync.h"
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "ivsrcid/irqsrcs_dcn_1_0.h"
 
 #include "dcn/dcn_1_0_offset.h"
@@ -900,14 +903,14 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector)
 				(struct edid *) sink->dc_edid.raw_edid;
 
 
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 					aconnector->edid);
 		}
 		amdgpu_dm_add_sink_to_freesync_module(connector, aconnector->edid);
 
 	} else {
 		amdgpu_dm_remove_sink_from_freesync_module(connector);
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		aconnector->num_modes = 0;
 		aconnector->dc_sink = NULL;
 		aconnector->edid = NULL;
@@ -1038,7 +1041,7 @@ static void handle_hpd_rx_irq(void *param)
 	if (dc_link->type != dc_connection_mst_branch)
 		mutex_lock(&aconnector->hpd_lock);
 
-	if (dc_link_handle_hpd_rx_irq(dc_link, NULL) &&
+	if (dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL) &&
 			!is_mst_root_connector) {
 		/* Downstream Port status changed. */
 		if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) {
@@ -1189,7 +1192,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 	return 0;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 /* Register IRQ sources and initialize IRQ callbacks */
 static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 {
@@ -1523,16 +1526,12 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 		if (dcn10_register_irq_handlers(dm->adev)) {
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
 			goto fail;
 		}
-		/*
-		 * Temporary disable until pplib/smu interaction is implemented
-		 */
-		dm->dc->debug.disable_stutter = true;
 		break;
 #endif
 	default:
@@ -1540,6 +1539,9 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		goto fail;
 	}
 
+	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
+		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
+
 	return 0;
 fail:
 	kfree(aencoder);
@@ -1571,18 +1573,6 @@ static void dm_bandwidth_update(struct amdgpu_device *adev)
 	/* TODO: implement later */
 }
 
-static void dm_set_backlight_level(struct amdgpu_encoder *amdgpu_encoder,
-				     u8 level)
-{
-	/* TODO: translate amdgpu_encoder to display_index and call DAL */
-}
-
-static u8 dm_get_backlight_level(struct amdgpu_encoder *amdgpu_encoder)
-{
-	/* TODO: translate amdgpu_encoder to display_index and call DAL */
-	return 0;
-}
-
 static int amdgpu_notify_freesync(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
@@ -1611,10 +1601,8 @@ static int amdgpu_notify_freesync(struct drm_device *dev, void *data,
 static const struct amdgpu_display_funcs dm_display_funcs = {
 	.bandwidth_update = dm_bandwidth_update, /* called unconditionally */
 	.vblank_get_counter = dm_vblank_get_counter,/* called unconditionally */
-	.backlight_set_level =
-		dm_set_backlight_level,/* called unconditionally */
-	.backlight_get_level =
-		dm_get_backlight_level,/* called unconditionally */
+	.backlight_set_level = NULL, /* never called for DC */
+	.backlight_get_level = NULL, /* never called for DC */
 	.hpd_sense = NULL,/* called unconditionally */
 	.hpd_set_polarity = NULL, /* called unconditionally */
 	.hpd_get_gpio_reg = NULL, /* VBIOS parsing. DAL does it. */
@@ -1722,7 +1710,7 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_dig = 6;
 		adev->mode_info.plane_type = dm_plane_type_default;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
@@ -2173,6 +2161,46 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing)
 	return color_space;
 }
 
+static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
+{
+	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+		return;
+
+	timing_out->display_color_depth--;
+}
+
+static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
+						const struct drm_display_info *info)
+{
+	int normalized_clk;
+	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+		return;
+	do {
+		normalized_clk = timing_out->pix_clk_khz;
+		/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
+		if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			normalized_clk /= 2;
+		/* Adjusting pix clock following on HDMI spec based on colour depth */
+		switch (timing_out->display_color_depth) {
+		case COLOR_DEPTH_101010:
+			normalized_clk = (normalized_clk * 30) / 24;
+			break;
+		case COLOR_DEPTH_121212:
+			normalized_clk = (normalized_clk * 36) / 24;
+			break;
+		case COLOR_DEPTH_161616:
+			normalized_clk = (normalized_clk * 48) / 24;
+			break;
+		default:
+			return;
+		}
+		if (normalized_clk <= info->max_tmds_clock)
+			return;
+		reduce_mode_colour_depth(timing_out);
+
+	} while (timing_out->display_color_depth > COLOR_DEPTH_888);
+
+}
 /*****************************************************************************/
 
 static void
@@ -2181,6 +2209,7 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 					     const struct drm_connector *connector)
 {
 	struct dc_crtc_timing *timing_out = &stream->timing;
+	const struct drm_display_info *info = &connector->display_info;
 
 	memset(timing_out, 0, sizeof(struct dc_crtc_timing));
 
@@ -2189,8 +2218,10 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 	timing_out->v_border_top = 0;
 	timing_out->v_border_bottom = 0;
 	/* TODO: un-hardcode */
-
-	if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
+	if (drm_mode_is_420_only(info, mode_in)
+			&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+	else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
 			&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR444;
 	else
@@ -2226,6 +2257,8 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 
 	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
 	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
+	if (stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		adjust_colour_depth_from_display_info(timing_out, info);
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
@@ -3046,14 +3079,24 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	else
 		domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-	r = amdgpu_bo_pin(rbo, domain, &afb->address);
-	amdgpu_bo_unreserve(rbo);
-
+	r = amdgpu_bo_pin(rbo, domain);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to pin framebuffer with error %d\n", r);
+		amdgpu_bo_unreserve(rbo);
+		return r;
+	}
+
+	r = amdgpu_ttm_alloc_gart(&rbo->tbo);
+	if (unlikely(r != 0)) {
+		amdgpu_bo_unpin(rbo);
+		amdgpu_bo_unreserve(rbo);
+		DRM_ERROR("%p bind failed\n", rbo);
 		return r;
 	}
+	amdgpu_bo_unreserve(rbo);
+
+	afb->address = amdgpu_bo_gpu_offset(rbo);
 
 	amdgpu_bo_ref(rbo);
 
@@ -3451,7 +3494,6 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	aconnector->base.stereo_allowed = false;
 	aconnector->base.dpms = DRM_MODE_DPMS_OFF;
 	aconnector->hpd.hpd = AMDGPU_HPD_NONE; /* not used */
-
 	mutex_init(&aconnector->hpd_lock);
 
 	/* configure support HPD hot plug connector_>polled default value is 0
@@ -3460,9 +3502,13 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	switch (connector_type) {
 	case DRM_MODE_CONNECTOR_HDMIA:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
+		aconnector->base.ycbcr_420_allowed =
+			link->link_enc->features.ycbcr420_supported ? true : false;
 		break;
 	case DRM_MODE_CONNECTOR_DisplayPort:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
+		aconnector->base.ycbcr_420_allowed =
+			link->link_enc->features.ycbcr420_supported ? true : false;
 		break;
 	case DRM_MODE_CONNECTOR_DVID:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
@@ -3615,10 +3661,17 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 		link,
 		link_index);
 
-	drm_mode_connector_attach_encoder(
+	drm_connector_attach_encoder(
 		&aconnector->base, &aencoder->base);
 
 	drm_connector_register(&aconnector->base);
+#if defined(CONFIG_DEBUG_FS)
+	res = connector_debugfs_init(aconnector);
+	if (res) {
+		DRM_ERROR("Failed to create debugfs for connector");
+		goto out_free;
+	}
+#endif
 
 	if (connector_type == DRM_MODE_CONNECTOR_DisplayPort
 		|| connector_type == DRM_MODE_CONNECTOR_eDP)
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
new file mode 100644
index 000000000000..0d9e410ca01e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -0,0 +1,722 @@
+/*
+ * 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/debugfs.h>
+
+#include "dc.h"
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "amdgpu_dm_debugfs.h"
+
+/* function description
+ * get/ set DP configuration: lane_count, link_rate, spread_spectrum
+ *
+ * valid lane count value: 1, 2, 4
+ * valid link rate value:
+ * 06h = 1.62Gbps per lane
+ * 0Ah = 2.7Gbps per lane
+ * 0Ch = 3.24Gbps per lane
+ * 14h = 5.4Gbps per lane
+ * 1Eh = 8.1Gbps per lane
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x/link_settings
+ *
+ * --- to get dp configuration
+ *
+ * cat link_settings
+ *
+ * It will list current, verified, reported, preferred dp configuration.
+ * current -- for current video mode
+ * verified --- maximum configuration which pass link training
+ * reported --- DP rx report caps (DPCD register offset 0, 1 2)
+ * preferred --- user force settings
+ *
+ * --- set (or force) dp configuration
+ *
+ * echo <lane_count>  <link_rate> > link_settings
+ *
+ * for example, to force to  2 lane, 2.7GHz,
+ * echo 4 0xa > link_settings
+ *
+ * spread_spectrum could not be changed dynamically.
+ *
+ * in case invalid lane count, link rate are force, no hw programming will be
+ * done. please check link settings after force operation to see if HW get
+ * programming.
+ *
+ * cat link_settings
+ *
+ * check current and preferred settings.
+ *
+ */
+static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *rd_buf = NULL;
+	char *rd_buf_ptr = NULL;
+	const uint32_t rd_buf_size = 100;
+	uint32_t result = 0;
+	uint8_t str_len = 0;
+	int r;
+
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
+
+	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
+	if (!rd_buf)
+		return 0;
+
+	rd_buf_ptr = rd_buf;
+
+	str_len = strlen("Current:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+			link->cur_link_settings.lane_count,
+			link->cur_link_settings.link_rate,
+			link->cur_link_settings.link_spread);
+	rd_buf_ptr += str_len;
+
+	str_len = strlen("Verified:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+			link->verified_link_cap.lane_count,
+			link->verified_link_cap.link_rate,
+			link->verified_link_cap.link_spread);
+	rd_buf_ptr += str_len;
+
+	str_len = strlen("Reported:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+			link->reported_link_cap.lane_count,
+			link->reported_link_cap.link_rate,
+			link->reported_link_cap.link_spread);
+	rd_buf_ptr += str_len;
+
+	str_len = strlen("Preferred:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
+			link->preferred_link_setting.lane_count,
+			link->preferred_link_setting.link_rate,
+			link->preferred_link_setting.link_spread);
+
+	while (size) {
+		if (*pos >= rd_buf_size)
+			break;
+
+		r = put_user(*(rd_buf + result), buf);
+		if (r)
+			return r; /* r = -EFAULT */
+
+		buf += 1;
+		size -= 1;
+		*pos += 1;
+		result += 1;
+	}
+
+	kfree(rd_buf);
+	return result;
+}
+
+static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	struct dc *dc = (struct dc *)link->dc;
+	struct dc_link_settings prefer_link_settings;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	const uint32_t wr_buf_size = 40;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	/* 0: lane_count; 1: link_rate */
+	uint8_t param_index = 0;
+	long param[2];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	bool valid_input = false;
+
+	if (size == 0)
+		return -EINVAL;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return -EINVAL;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not read\n");
+		return -EINVAL;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 2)) {
+
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+	}
+
+	switch (param[0]) {
+	case LANE_COUNT_ONE:
+	case LANE_COUNT_TWO:
+	case LANE_COUNT_FOUR:
+		valid_input = true;
+		break;
+	default:
+		break;
+	}
+
+	switch (param[1]) {
+	case LINK_RATE_LOW:
+	case LINK_RATE_HIGH:
+	case LINK_RATE_RBR2:
+	case LINK_RATE_HIGH2:
+	case LINK_RATE_HIGH3:
+		valid_input = true;
+		break;
+	default:
+		break;
+	}
+
+	if (!valid_input) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input value No HW will be programmed\n");
+		return bytes_from_user;
+	}
+
+	/* save user force lane_count, link_rate to preferred settings
+	 * spread spectrum will not be changed
+	 */
+	prefer_link_settings.link_spread = link->cur_link_settings.link_spread;
+	prefer_link_settings.lane_count = param[0];
+	prefer_link_settings.link_rate = param[1];
+
+	dc_link_set_preferred_link_settings(dc, &prefer_link_settings, link);
+
+	kfree(wr_buf);
+	return bytes_from_user;
+}
+
+/* function: get current DP PHY settings: voltage swing, pre-emphasis,
+ * post-cursor2 (defined by VESA DP specification)
+ *
+ * valid values
+ * voltage swing: 0,1,2,3
+ * pre-emphasis : 0,1,2,3
+ * post cursor2 : 0,1,2,3
+ *
+ *
+ * how to use this debugfs
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x
+ *
+ * there will be directories, like DP-1, DP-2,DP-3, etc. for DP display
+ *
+ * To figure out which DP-x is the display for DP to be check,
+ * cd DP-x
+ * ls -ll
+ * There should be debugfs file, like link_settings, phy_settings.
+ * cat link_settings
+ * from lane_count, link_rate to figure which DP-x is for display to be worked
+ * on
+ *
+ * To get current DP PHY settings,
+ * cat phy_settings
+ *
+ * To change DP PHY settings,
+ * echo <voltage_swing> <pre-emphasis> <post_cursor2> > phy_settings
+ * for examle, to change voltage swing to 2, pre-emphasis to 3, post_cursor2 to
+ * 0,
+ * echo 2 3 0 > phy_settings
+ *
+ * To check if change be applied, get current phy settings by
+ * cat phy_settings
+ *
+ * In case invalid values are set by user, like
+ * echo 1 4 0 > phy_settings
+ *
+ * HW will NOT be programmed by these settings.
+ * cat phy_settings will show the previous valid settings.
+ */
+static ssize_t dp_phy_settings_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *rd_buf = NULL;
+	const uint32_t rd_buf_size = 20;
+	uint32_t result = 0;
+	int r;
+
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
+
+	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
+	if (!rd_buf)
+		return -EINVAL;
+
+	snprintf(rd_buf, rd_buf_size, "  %d  %d  %d  ",
+			link->cur_lane_setting.VOLTAGE_SWING,
+			link->cur_lane_setting.PRE_EMPHASIS,
+			link->cur_lane_setting.POST_CURSOR2);
+
+	while (size) {
+		if (*pos >= rd_buf_size)
+			break;
+
+		r = put_user((*(rd_buf + result)), buf);
+		if (r)
+			return r; /* r = -EFAULT */
+
+		buf += 1;
+		size -= 1;
+		*pos += 1;
+		result += 1;
+	}
+
+	kfree(rd_buf);
+	return result;
+}
+
+static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	struct dc *dc = (struct dc *)link->dc;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 40;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	uint8_t param_index = 0;
+	long param[3];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	bool use_prefer_link_setting;
+	struct link_training_settings link_lane_settings;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 3)) {
+
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+	}
+
+	if ((param[0] > VOLTAGE_SWING_MAX_LEVEL) ||
+			(param[1] > PRE_EMPHASIS_MAX_LEVEL) ||
+			(param[2] > POST_CURSOR2_MAX_LEVEL)) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input No HW will be programmed\n");
+		return bytes_from_user;
+	}
+
+	/* get link settings: lane count, link rate */
+	use_prefer_link_setting =
+		((link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) &&
+		(link->test_pattern_enabled));
+
+	memset(&link_lane_settings, 0, sizeof(link_lane_settings));
+
+	if (use_prefer_link_setting) {
+		link_lane_settings.link_settings.lane_count =
+				link->preferred_link_setting.lane_count;
+		link_lane_settings.link_settings.link_rate =
+				link->preferred_link_setting.link_rate;
+		link_lane_settings.link_settings.link_spread =
+				link->preferred_link_setting.link_spread;
+	} else {
+		link_lane_settings.link_settings.lane_count =
+				link->cur_link_settings.lane_count;
+		link_lane_settings.link_settings.link_rate =
+				link->cur_link_settings.link_rate;
+		link_lane_settings.link_settings.link_spread =
+				link->cur_link_settings.link_spread;
+	}
+
+	/* apply phy settings from user */
+	for (r = 0; r < link_lane_settings.link_settings.lane_count; r++) {
+		link_lane_settings.lane_settings[r].VOLTAGE_SWING =
+				(enum dc_voltage_swing) (param[0]);
+		link_lane_settings.lane_settings[r].PRE_EMPHASIS =
+				(enum dc_pre_emphasis) (param[1]);
+		link_lane_settings.lane_settings[r].POST_CURSOR2 =
+				(enum dc_post_cursor2) (param[2]);
+	}
+
+	/* program ASIC registers and DPCD registers */
+	dc_link_set_drive_settings(dc, &link_lane_settings, link);
+
+	kfree(wr_buf);
+	return bytes_from_user;
+}
+
+/* function description
+ *
+ * set PHY layer or Link layer test pattern
+ * PHY test pattern is used for PHY SI check.
+ * Link layer test will not affect PHY SI.
+ *
+ * Reset Test Pattern:
+ * 0 = DP_TEST_PATTERN_VIDEO_MODE
+ *
+ * PHY test pattern supported:
+ * 1 = DP_TEST_PATTERN_D102
+ * 2 = DP_TEST_PATTERN_SYMBOL_ERROR
+ * 3 = DP_TEST_PATTERN_PRBS7
+ * 4 = DP_TEST_PATTERN_80BIT_CUSTOM
+ * 5 = DP_TEST_PATTERN_CP2520_1
+ * 6 = DP_TEST_PATTERN_CP2520_2 = DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE
+ * 7 = DP_TEST_PATTERN_CP2520_3
+ *
+ * DP PHY Link Training Patterns
+ * 8 = DP_TEST_PATTERN_TRAINING_PATTERN1
+ * 9 = DP_TEST_PATTERN_TRAINING_PATTERN2
+ * a = DP_TEST_PATTERN_TRAINING_PATTERN3
+ * b = DP_TEST_PATTERN_TRAINING_PATTERN4
+ *
+ * DP Link Layer Test pattern
+ * c = DP_TEST_PATTERN_COLOR_SQUARES
+ * d = DP_TEST_PATTERN_COLOR_SQUARES_CEA
+ * e = DP_TEST_PATTERN_VERTICAL_BARS
+ * f = DP_TEST_PATTERN_HORIZONTAL_BARS
+ * 10= DP_TEST_PATTERN_COLOR_RAMP
+ *
+ * debugfs phy_test_pattern is located at /syskernel/debug/dri/0/DP-x
+ *
+ * --- set test pattern
+ * echo <test pattern #> > test_pattern
+ *
+ * If test pattern # is not supported, NO HW programming will be done.
+ * for DP_TEST_PATTERN_80BIT_CUSTOM, it needs extra 10 bytes of data
+ * for the user pattern. input 10 bytes data are separated by space
+ *
+ * echo 0x4 0x11 0x22 0x33 0x44 0x55 0x66 0x77 0x88 0x99 0xaa > test_pattern
+ *
+ * --- reset test pattern
+ * echo 0 > test_pattern
+ *
+ * --- HPD detection is disabled when set PHY test pattern
+ *
+ * when PHY test pattern (pattern # within [1,7]) is set, HPD pin of HW ASIC
+ * is disable. User could unplug DP display from DP connected and plug scope to
+ * check test pattern PHY SI.
+ * If there is need unplug scope and plug DP display back, do steps below:
+ * echo 0 > phy_test_pattern
+ * unplug scope
+ * plug DP display.
+ *
+ * "echo 0 > phy_test_pattern" will re-enable HPD pin again so that video sw
+ * driver could detect "unplug scope" and "plug DP display"
+ */
+static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 100;
+	uint32_t wr_buf_count = 0;
+	int r;
+	int bytes_from_user;
+	char *sub_str = NULL;
+	uint8_t param_index = 0;
+	uint8_t param_nums = 0;
+	long param[11] = {0x0};
+	const char delimiter[3] = {' ', '\n', '\0'};
+	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
+	bool disable_hpd = false;
+	bool valid_test_pattern = false;
+	/* init with defalut 80bit custom pattern */
+	uint8_t custom_pattern[10] = {
+			0x1f, 0x7c, 0xf0, 0xc1, 0x07,
+			0x1f, 0x7c, 0xf0, 0xc1, 0x07
+			};
+	struct dc_link_settings prefer_link_settings = {LANE_COUNT_UNKNOWN,
+			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
+	struct dc_link_settings cur_link_settings = {LANE_COUNT_UNKNOWN,
+			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
+	struct link_training_settings link_training_settings;
+	int i;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	/* check number of parameters. isspace could not differ space and \n */
+	while ((*wr_buf_ptr != 0xa) && (wr_buf_count < wr_buf_size)) {
+		/* skip space*/
+		while (isspace(*wr_buf_ptr) && (wr_buf_count < wr_buf_size)) {
+			wr_buf_ptr++;
+			wr_buf_count++;
+			}
+
+		if (wr_buf_count == wr_buf_size)
+			break;
+
+		/* skip non-space*/
+		while ((!isspace(*wr_buf_ptr)) && (wr_buf_count < wr_buf_size)) {
+			wr_buf_ptr++;
+			wr_buf_count++;
+			}
+
+		param_nums++;
+
+		if (wr_buf_count == wr_buf_size)
+			break;
+	}
+
+	/* max 11 parameters */
+	if (param_nums > 11)
+		param_nums = 11;
+
+	wr_buf_ptr = wr_buf; /* reset buf pinter */
+	wr_buf_count = 0; /* number of char already checked */
+
+	while (isspace(*wr_buf_ptr) && (wr_buf_count < wr_buf_size)) {
+		wr_buf_ptr++;
+		wr_buf_count++;
+	}
+
+	while (param_index < param_nums) {
+		/* after strsep, wr_buf_ptr will be moved to after space */
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+	}
+
+	test_pattern = param[0];
+
+	switch (test_pattern) {
+	case DP_TEST_PATTERN_VIDEO_MODE:
+	case DP_TEST_PATTERN_COLOR_SQUARES:
+	case DP_TEST_PATTERN_COLOR_SQUARES_CEA:
+	case DP_TEST_PATTERN_VERTICAL_BARS:
+	case DP_TEST_PATTERN_HORIZONTAL_BARS:
+	case DP_TEST_PATTERN_COLOR_RAMP:
+		valid_test_pattern = true;
+		break;
+
+	case DP_TEST_PATTERN_D102:
+	case DP_TEST_PATTERN_SYMBOL_ERROR:
+	case DP_TEST_PATTERN_PRBS7:
+	case DP_TEST_PATTERN_80BIT_CUSTOM:
+	case DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE:
+	case DP_TEST_PATTERN_TRAINING_PATTERN4:
+		disable_hpd = true;
+		valid_test_pattern = true;
+		break;
+
+	default:
+		valid_test_pattern = false;
+		test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
+		break;
+	}
+
+	if (!valid_test_pattern) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Test Pattern Parameters\n");
+		return bytes_from_user;
+	}
+
+	if (test_pattern == DP_TEST_PATTERN_80BIT_CUSTOM) {
+		for (i = 0; i < 10; i++) {
+			if ((uint8_t) param[i + 1] != 0x0)
+				break;
+		}
+
+		if (i < 10) {
+			/* not use default value */
+			for (i = 0; i < 10; i++)
+				custom_pattern[i] = (uint8_t) param[i + 1];
+		}
+	}
+
+	/* Usage: set DP physical test pattern using debugfs with normal DP
+	 * panel. Then plug out DP panel and connect a scope to measure
+	 * For normal video mode and test pattern generated from CRCT,
+	 * they are visibile to user. So do not disable HPD.
+	 * Video Mode is also set to clear the test pattern, so enable HPD
+	 * because it might have been disabled after a test pattern was set.
+	 * AUX depends on HPD * sequence dependent, do not move!
+	 */
+	if (!disable_hpd)
+		dc_link_enable_hpd(link);
+
+	prefer_link_settings.lane_count = link->verified_link_cap.lane_count;
+	prefer_link_settings.link_rate = link->verified_link_cap.link_rate;
+	prefer_link_settings.link_spread = link->verified_link_cap.link_spread;
+
+	cur_link_settings.lane_count = link->cur_link_settings.lane_count;
+	cur_link_settings.link_rate = link->cur_link_settings.link_rate;
+	cur_link_settings.link_spread = link->cur_link_settings.link_spread;
+
+	link_training_settings.link_settings = cur_link_settings;
+
+
+	if (test_pattern != DP_TEST_PATTERN_VIDEO_MODE) {
+		if (prefer_link_settings.lane_count != LANE_COUNT_UNKNOWN &&
+			prefer_link_settings.link_rate !=  LINK_RATE_UNKNOWN &&
+			(prefer_link_settings.lane_count != cur_link_settings.lane_count ||
+			prefer_link_settings.link_rate != cur_link_settings.link_rate))
+			link_training_settings.link_settings = prefer_link_settings;
+	}
+
+	for (i = 0; i < (unsigned int)(link_training_settings.link_settings.lane_count); i++)
+		link_training_settings.lane_settings[i] = link->cur_lane_setting;
+
+	dc_link_set_test_pattern(
+		link,
+		test_pattern,
+		&link_training_settings,
+		custom_pattern,
+		10);
+
+	/* Usage: Set DP physical test pattern using AMDDP with normal DP panel
+	 * Then plug out DP panel and connect a scope to measure DP PHY signal.
+	 * Need disable interrupt to avoid SW driver disable DP output. This is
+	 * done after the test pattern is set.
+	 */
+	if (valid_test_pattern && disable_hpd)
+		dc_link_disable_hpd(link);
+
+	kfree(wr_buf);
+
+	return bytes_from_user;
+}
+
+static const struct file_operations dp_link_settings_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_link_settings_read,
+	.write = dp_link_settings_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_phy_settings_debugfs_fop = {
+	.owner = THIS_MODULE,
+	.read = dp_phy_settings_read,
+	.write = dp_phy_settings_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_phy_test_pattern_fops = {
+	.owner = THIS_MODULE,
+	.write = dp_phy_test_pattern_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct {
+	char *name;
+	const struct file_operations *fops;
+} dp_debugfs_entries[] = {
+		{"link_settings", &dp_link_settings_debugfs_fops},
+		{"phy_settings", &dp_phy_settings_debugfs_fop},
+		{"test_pattern", &dp_phy_test_pattern_fops}
+};
+
+int connector_debugfs_init(struct amdgpu_dm_connector *connector)
+{
+	int i;
+	struct dentry *ent, *dir = connector->base.debugfs_entry;
+
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		for (i = 0; i < ARRAY_SIZE(dp_debugfs_entries); i++) {
+			ent = debugfs_create_file(dp_debugfs_entries[i].name,
+						  0644,
+						  dir,
+						  connector,
+						  dp_debugfs_entries[i].fops);
+			if (IS_ERR(ent))
+				return PTR_ERR(ent);
+		}
+	}
+
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
new file mode 100644
index 000000000000..d9ed1b2aa811
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
@@ -0,0 +1,34 @@
+/*
+ * 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 __AMDGPU_DM_DEBUGFS_H__
+#define __AMDGPU_DM_DEBUGFS_H__
+
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+
+int connector_debugfs_init(struct amdgpu_dm_connector *connector);
+
+#endif
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 b19dc4cfc030..8403b6a9a77b 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
@@ -169,6 +169,11 @@ static void get_payload_table(
 	mutex_unlock(&mst_mgr->payload_lock);
 }
 
+void dm_helpers_dp_update_branch_info(
+	struct dc_context *ctx,
+	const struct dc_link *link)
+{}
+
 /*
  * Writes payload allocation table in immediate downstream device.
  */
@@ -454,6 +459,22 @@ bool dm_helpers_submit_i2c(
 	return result;
 }
 
+bool dm_helpers_is_dp_sink_present(struct dc_link *link)
+{
+	bool dp_sink_present;
+	struct amdgpu_dm_connector *aconnector = link->priv;
+
+	if (!aconnector) {
+		BUG_ON("Failed to found connector for link!");
+		return true;
+	}
+
+	mutex_lock(&aconnector->dm_dp_aux.aux.hw_mutex);
+	dp_sink_present = dc_link_is_dp_sink_present(link);
+	mutex_unlock(&aconnector->dm_dp_aux.aux.hw_mutex);
+	return dp_sink_present;
+}
+
 enum dc_edid_status dm_helpers_read_local_edid(
 		struct dc_context *ctx,
 		struct dc_link *link,
@@ -498,8 +519,8 @@ enum dc_edid_status dm_helpers_read_local_edid(
 				edid_status,
 				aconnector->base.name);
 	if (link->aux_mode) {
-		union test_request test_request = {0};
-		union test_response test_response = {0};
+		union test_request test_request = { {0} };
+		union test_response test_response = { {0} };
 
 		dm_helpers_dp_read_dpcd(ctx,
 					link,
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 4304d9e408b8..9a300732ba37 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
@@ -80,55 +80,72 @@ static void log_dpcd(uint8_t type,
 static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				  struct drm_dp_aux_msg *msg)
 {
-	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
-		I2C_MOT_TRUE : I2C_MOT_FALSE;
-	enum ddc_result res;
-	uint32_t read_bytes = msg->size;
+	ssize_t result = 0;
+	enum i2caux_transaction_action action;
+	enum aux_transaction_type type;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		res = dal_ddc_service_read_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				false,
-				I2C_MOT_UNDEF,
-				msg->address,
-				msg->buffer,
-				msg->size,
-				&read_bytes);
+		type = AUX_TRANSACTION_TYPE_DP;
+		action = I2CAUX_TRANSACTION_ACTION_DP_READ;
+
+		result = dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+					      msg->address,
+					      &msg->reply,
+					      msg->buffer,
+					      msg->size,
+					      type,
+					      action);
 		break;
 	case DP_AUX_NATIVE_WRITE:
-		res = dal_ddc_service_write_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				false,
-				I2C_MOT_UNDEF,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_DP;
+		action = I2CAUX_TRANSACTION_ACTION_DP_WRITE;
+
+		dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+				     msg->address,
+				     &msg->reply,
+				     msg->buffer,
+				     msg->size,
+				     type,
+				     action);
+		result = msg->size;
 		break;
 	case DP_AUX_I2C_READ:
-		res = dal_ddc_service_read_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				true,
-				mot,
-				msg->address,
-				msg->buffer,
-				msg->size,
-				&read_bytes);
+		type = AUX_TRANSACTION_TYPE_I2C;
+		if (msg->request & DP_AUX_I2C_MOT)
+			action = I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT;
+		else
+			action = I2CAUX_TRANSACTION_ACTION_I2C_READ;
+
+		result = dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+					      msg->address,
+					      &msg->reply,
+					      msg->buffer,
+					      msg->size,
+					      type,
+					      action);
 		break;
 	case DP_AUX_I2C_WRITE:
-		res = dal_ddc_service_write_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				true,
-				mot,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_I2C;
+		if (msg->request & DP_AUX_I2C_MOT)
+			action = I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT;
+		else
+			action = I2CAUX_TRANSACTION_ACTION_I2C_WRITE;
+
+		dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+				     msg->address,
+				     &msg->reply,
+				     msg->buffer,
+				     msg->size,
+				     type,
+				     action);
+		result = msg->size;
 		break;
 	default:
-		return 0;
+		return -EINVAL;
 	}
 
 #ifdef TRACE_DPCD
@@ -139,9 +156,10 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 		 r == DDC_RESULT_SUCESSFULL);
 #endif
 
-	if (res != DDC_RESULT_SUCESSFULL)
-		return -EIO;
-	return read_bytes;
+	if (result < 0) /* DC doesn't know about kernel error codes */
+		result = -EIO;
+
+	return result;
 }
 
 static enum drm_connector_status
@@ -233,7 +251,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
 
 		if (!edid) {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 				&aconnector->base,
 				NULL);
 			return ret;
@@ -261,7 +279,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 					connector, aconnector->edid);
 	}
 
-	drm_mode_connector_update_edid_property(
+	drm_connector_update_edid_property(
 					&aconnector->base, aconnector->edid);
 
 	ret = drm_add_edid_modes(connector, aconnector->edid);
@@ -345,7 +363,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 						aconnector, connector->base.id, aconnector->mst_port);
 
 			aconnector->port = port;
-			drm_mode_connector_set_path_property(connector, pathprop);
+			drm_connector_set_path_property(connector, pathprop);
 
 			drm_connector_list_iter_end(&conn_iter);
 			aconnector->mst_connected = true;
@@ -393,7 +411,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		dev->mode_config.tile_property,
 		0);
 
-	drm_mode_connector_set_path_property(connector, pathprop);
+	drm_connector_set_path_property(connector, pathprop);
 
 	/*
 	 * Initialize connector state before adding the connectror to drm and
@@ -441,7 +459,7 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 static void dm_dp_mst_link_status_reset(struct drm_connector *connector)
 {
 	mutex_lock(&connector->dev->mode_config.mutex);
-	drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
+	drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
 	mutex_unlock(&connector->dev->mode_config.mutex);
 }
 
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
new file mode 100644
index 000000000000..fbe878ae1e8c
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -0,0 +1,562 @@
+/*
+ * 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/string.h>
+#include <linux/acpi.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/amdgpu_drm.h>
+#include "dm_services.h"
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "amdgpu_dm_irq.h"
+#include "amdgpu_pm.h"
+#include "dm_pp_smu.h"
+
+
+bool dm_pp_apply_display_requirements(
+		const struct dc_context *ctx,
+		const struct dm_pp_display_configuration *pp_display_cfg)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	int i;
+
+	if (adev->pm.dpm_enabled) {
+
+		memset(&adev->pm.pm_display_cfg, 0,
+				sizeof(adev->pm.pm_display_cfg));
+
+		adev->pm.pm_display_cfg.cpu_cc6_disable =
+			pp_display_cfg->cpu_cc6_disable;
+
+		adev->pm.pm_display_cfg.cpu_pstate_disable =
+			pp_display_cfg->cpu_pstate_disable;
+
+		adev->pm.pm_display_cfg.cpu_pstate_separation_time =
+			pp_display_cfg->cpu_pstate_separation_time;
+
+		adev->pm.pm_display_cfg.nb_pstate_switch_disable =
+			pp_display_cfg->nb_pstate_switch_disable;
+
+		adev->pm.pm_display_cfg.num_display =
+				pp_display_cfg->display_count;
+		adev->pm.pm_display_cfg.num_path_including_non_display =
+				pp_display_cfg->display_count;
+
+		adev->pm.pm_display_cfg.min_core_set_clock =
+				pp_display_cfg->min_engine_clock_khz/10;
+		adev->pm.pm_display_cfg.min_core_set_clock_in_sr =
+				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
+		adev->pm.pm_display_cfg.min_mem_set_clock =
+				pp_display_cfg->min_memory_clock_khz/10;
+
+		adev->pm.pm_display_cfg.min_dcef_deep_sleep_set_clk =
+				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
+		adev->pm.pm_display_cfg.min_dcef_set_clk =
+				pp_display_cfg->min_dcfclock_khz/10;
+
+		adev->pm.pm_display_cfg.multi_monitor_in_sync =
+				pp_display_cfg->all_displays_in_sync;
+		adev->pm.pm_display_cfg.min_vblank_time =
+				pp_display_cfg->avail_mclk_switch_time_us;
+
+		adev->pm.pm_display_cfg.display_clk =
+				pp_display_cfg->disp_clk_khz/10;
+
+		adev->pm.pm_display_cfg.dce_tolerable_mclk_in_active_latency =
+				pp_display_cfg->avail_mclk_switch_time_in_disp_active_us;
+
+		adev->pm.pm_display_cfg.crtc_index = pp_display_cfg->crtc_index;
+		adev->pm.pm_display_cfg.line_time_in_us =
+				pp_display_cfg->line_time_in_us;
+
+		adev->pm.pm_display_cfg.vrefresh = pp_display_cfg->disp_configs[0].v_refresh;
+		adev->pm.pm_display_cfg.crossfire_display_index = -1;
+		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
+
+		for (i = 0; i < pp_display_cfg->display_count; i++) {
+			const struct dm_pp_single_disp_config *dc_cfg =
+						&pp_display_cfg->disp_configs[i];
+			adev->pm.pm_display_cfg.displays[i].controller_id = dc_cfg->pipe_idx + 1;
+		}
+
+		/* TODO: complete implementation of
+		 * pp_display_configuration_change().
+		 * Follow example of:
+		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
+		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
+		if (adev->powerplay.pp_funcs->display_configuration_change)
+			adev->powerplay.pp_funcs->display_configuration_change(
+				adev->powerplay.pp_handle,
+				&adev->pm.pm_display_cfg);
+
+		/* TODO: replace by a separate call to 'apply display cfg'? */
+		amdgpu_pm_compute_clocks(adev);
+	}
+
+	return true;
+}
+
+static void get_default_clock_levels(
+		enum dm_pp_clock_type clk_type,
+		struct dm_pp_clock_levels *clks)
+{
+	uint32_t disp_clks_in_khz[6] = {
+			300000, 400000, 496560, 626090, 685720, 757900 };
+	uint32_t sclks_in_khz[6] = {
+			300000, 360000, 423530, 514290, 626090, 720000 };
+	uint32_t mclks_in_khz[2] = { 333000, 800000 };
+
+	switch (clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		clks->num_levels = 6;
+		memmove(clks->clocks_in_khz, disp_clks_in_khz,
+				sizeof(disp_clks_in_khz));
+		break;
+	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
+		clks->num_levels = 6;
+		memmove(clks->clocks_in_khz, sclks_in_khz,
+				sizeof(sclks_in_khz));
+		break;
+	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
+		clks->num_levels = 2;
+		memmove(clks->clocks_in_khz, mclks_in_khz,
+				sizeof(mclks_in_khz));
+		break;
+	default:
+		clks->num_levels = 0;
+		break;
+	}
+}
+
+static enum amd_pp_clock_type dc_to_pp_clock_type(
+		enum dm_pp_clock_type dm_pp_clk_type)
+{
+	enum amd_pp_clock_type amd_pp_clk_type = 0;
+
+	switch (dm_pp_clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		amd_pp_clk_type = amd_pp_disp_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
+		amd_pp_clk_type = amd_pp_sys_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
+		amd_pp_clk_type = amd_pp_mem_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCEFCLK:
+		amd_pp_clk_type  = amd_pp_dcef_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCFCLK:
+		amd_pp_clk_type = amd_pp_dcf_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_PIXELCLK:
+		amd_pp_clk_type = amd_pp_pixel_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_FCLK:
+		amd_pp_clk_type = amd_pp_f_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
+		amd_pp_clk_type = amd_pp_phy_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DPPCLK:
+		amd_pp_clk_type = amd_pp_dpp_clock;
+		break;
+	default:
+		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
+				dm_pp_clk_type);
+		break;
+	}
+
+	return amd_pp_clk_type;
+}
+
+static enum dm_pp_clocks_state pp_to_dc_powerlevel_state(
+			enum PP_DAL_POWERLEVEL max_clocks_state)
+{
+	switch (max_clocks_state) {
+	case PP_DAL_POWERLEVEL_0:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_0;
+	case PP_DAL_POWERLEVEL_1:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_1;
+	case PP_DAL_POWERLEVEL_2:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_2;
+	case PP_DAL_POWERLEVEL_3:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_3;
+	case PP_DAL_POWERLEVEL_4:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_4;
+	case PP_DAL_POWERLEVEL_5:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_5;
+	case PP_DAL_POWERLEVEL_6:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_6;
+	case PP_DAL_POWERLEVEL_7:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_7;
+	default:
+		DRM_ERROR("DM_PPLIB: invalid powerlevel state: %d!\n",
+				max_clocks_state);
+		return DM_PP_CLOCKS_STATE_INVALID;
+	}
+}
+
+static void pp_to_dc_clock_levels(
+		const struct amd_pp_clocks *pp_clks,
+		struct dm_pp_clock_levels *dc_clks,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->count > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->count,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		dc_clks->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		dc_clks->num_levels = pp_clks->count;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < dc_clks->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
+		dc_clks->clocks_in_khz[i] = pp_clks->clock[i];
+	}
+}
+
+static void pp_to_dc_clock_levels_with_latency(
+		const struct pp_clock_levels_with_latency *pp_clks,
+		struct dm_pp_clock_levels_with_latency *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_DEBUG("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_DEBUG("DM_PPLIB:\t %d in kHz\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
+	}
+}
+
+static void pp_to_dc_clock_levels_with_voltage(
+		const struct pp_clock_levels_with_voltage *pp_clks,
+		struct dm_pp_clock_levels_with_voltage *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d in kHz\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
+	}
+}
+
+bool dm_pp_get_clock_levels_by_type(
+		const struct dc_context *ctx,
+		enum dm_pp_clock_type clk_type,
+		struct dm_pp_clock_levels *dc_clks)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct amd_pp_clocks pp_clks = { 0 };
+	struct amd_pp_simple_clock_info validation_clks = { 0 };
+	uint32_t i;
+
+	if (adev->powerplay.pp_funcs->get_clock_by_type) {
+		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
+			dc_to_pp_clock_type(clk_type), &pp_clks)) {
+		/* Error in pplib. Provide default values. */
+			get_default_clock_levels(clk_type, dc_clks);
+			return true;
+		}
+	}
+
+	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
+
+	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
+		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
+						pp_handle, &validation_clks)) {
+			/* Error in pplib. Provide default values. */
+			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
+			validation_clks.engine_max_clock = 72000;
+			validation_clks.memory_max_clock = 80000;
+			validation_clks.level = 0;
+		}
+	}
+
+	DRM_INFO("DM_PPLIB: Validation clocks:\n");
+	DRM_INFO("DM_PPLIB:    engine_max_clock: %d\n",
+			validation_clks.engine_max_clock);
+	DRM_INFO("DM_PPLIB:    memory_max_clock: %d\n",
+			validation_clks.memory_max_clock);
+	DRM_INFO("DM_PPLIB:    level           : %d\n",
+			validation_clks.level);
+
+	/* Translate 10 kHz to kHz. */
+	validation_clks.engine_max_clock *= 10;
+	validation_clks.memory_max_clock *= 10;
+
+	/* Determine the highest non-boosted level from the Validation Clocks */
+	if (clk_type == DM_PP_CLOCK_TYPE_ENGINE_CLK) {
+		for (i = 0; i < dc_clks->num_levels; i++) {
+			if (dc_clks->clocks_in_khz[i] > validation_clks.engine_max_clock) {
+				/* This clock is higher the validation clock.
+				 * Than means the previous one is the highest
+				 * non-boosted one. */
+				DRM_INFO("DM_PPLIB: reducing engine clock level from %d to %d\n",
+						dc_clks->num_levels, i);
+				dc_clks->num_levels = i > 0 ? i : 1;
+				break;
+			}
+		}
+	} else if (clk_type == DM_PP_CLOCK_TYPE_MEMORY_CLK) {
+		for (i = 0; i < dc_clks->num_levels; i++) {
+			if (dc_clks->clocks_in_khz[i] > validation_clks.memory_max_clock) {
+				DRM_INFO("DM_PPLIB: reducing memory clock level from %d to %d\n",
+						dc_clks->num_levels, i);
+				dc_clks->num_levels = i > 0 ? i : 1;
+				break;
+			}
+		}
+	}
+
+	return true;
+}
+
+bool dm_pp_get_clock_levels_by_type_with_latency(
+	const struct dc_context *ctx,
+	enum dm_pp_clock_type clk_type,
+	struct dm_pp_clock_levels_with_latency *clk_level_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_latency pp_clks = { 0 };
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
+		return false;
+
+	if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clks))
+		return false;
+
+	pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
+
+	return true;
+}
+
+bool dm_pp_get_clock_levels_by_type_with_voltage(
+	const struct dc_context *ctx,
+	enum dm_pp_clock_type clk_type,
+	struct dm_pp_clock_levels_with_voltage *clk_level_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_voltage pp_clk_info = {0};
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs->get_clock_by_type_with_voltage(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clk_info))
+		return false;
+
+	pp_to_dc_clock_levels_with_voltage(&pp_clk_info, clk_level_info, clk_type);
+
+	return true;
+}
+
+bool dm_pp_notify_wm_clock_changes(
+	const struct dc_context *ctx,
+	struct dm_pp_wm_sets_with_clock_ranges *wm_with_clock_ranges)
+{
+	/* TODO: to be implemented */
+	return false;
+}
+
+bool dm_pp_apply_power_level_change_request(
+	const struct dc_context *ctx,
+	struct dm_pp_power_level_change_request *level_change_req)
+{
+	/* TODO: to be implemented */
+	return false;
+}
+
+bool dm_pp_apply_clock_for_voltage_request(
+	const struct dc_context *ctx,
+	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct pp_display_clock_request pp_clock_request = {0};
+	int ret = 0;
+
+	pp_clock_request.clock_type = dc_to_pp_clock_type(clock_for_voltage_req->clk_type);
+	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
+
+	if (!pp_clock_request.clock_type)
+		return false;
+
+	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
+		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
+			adev->powerplay.pp_handle,
+			&pp_clock_request);
+	if (ret)
+		return false;
+	return true;
+}
+
+bool dm_pp_get_static_clocks(
+	const struct dc_context *ctx,
+	struct dm_pp_static_clock_info *static_clk_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct amd_pp_clock_info pp_clk_info = {0};
+	int ret = 0;
+
+	if (adev->powerplay.pp_funcs->get_current_clocks)
+		ret = adev->powerplay.pp_funcs->get_current_clocks(
+			adev->powerplay.pp_handle,
+			&pp_clk_info);
+	if (ret)
+		return false;
+
+	static_clk_info->max_clocks_state = pp_to_dc_powerlevel_state(pp_clk_info.max_clocks_state);
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
+
+	return true;
+}
+
+void pp_rv_set_display_requirement(struct pp_smu *pp,
+		struct pp_smu_display_requirement_rv *req)
+{
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->display_configuration_changed)
+		return;
+
+	amdgpu_dpm_display_configuration_changed(adev);
+}
+
+void pp_rv_set_wm_ranges(struct pp_smu *pp,
+		struct pp_smu_wm_range_sets *ranges)
+{
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges;
+	struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks = wm_with_clock_ranges.wm_dmif_clocks_ranges;
+	struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks = wm_with_clock_ranges.wm_mcif_clocks_ranges;
+	int32_t i;
+
+	wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets;
+	wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets;
+
+	for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) {
+		if (ranges->reader_wm_sets[i].wm_inst > 3)
+			wm_dce_clocks[i].wm_set_id = WM_SET_A;
+		else
+			wm_dce_clocks[i].wm_set_id =
+					ranges->reader_wm_sets[i].wm_inst;
+		wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz =
+				ranges->reader_wm_sets[i].max_drain_clk_khz;
+		wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz =
+				ranges->reader_wm_sets[i].min_drain_clk_khz;
+		wm_dce_clocks[i].wm_max_mem_clk_in_khz =
+				ranges->reader_wm_sets[i].max_fill_clk_khz;
+		wm_dce_clocks[i].wm_min_mem_clk_in_khz =
+				ranges->reader_wm_sets[i].min_fill_clk_khz;
+	}
+
+	for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) {
+		if (ranges->writer_wm_sets[i].wm_inst > 3)
+			wm_soc_clocks[i].wm_set_id = WM_SET_A;
+		else
+			wm_soc_clocks[i].wm_set_id =
+					ranges->writer_wm_sets[i].wm_inst;
+		wm_soc_clocks[i].wm_max_socclk_clk_in_khz =
+				ranges->writer_wm_sets[i].max_fill_clk_khz;
+		wm_soc_clocks[i].wm_min_socclk_clk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_khz;
+		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
+				ranges->writer_wm_sets[i].max_drain_clk_khz;
+		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
+				ranges->writer_wm_sets[i].min_drain_clk_khz;
+	}
+
+	pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, &wm_with_clock_ranges);
+}
+
+void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
+{
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->notify_smu_enable_pwe)
+		return;
+
+	pp_funcs->notify_smu_enable_pwe(pp_handle);
+}
+
+void dm_pp_get_funcs_rv(
+		struct dc_context *ctx,
+		struct pp_smu_funcs_rv *funcs)
+{
+	funcs->pp_smu.ctx = ctx;
+	funcs->set_display_requirement = pp_rv_set_display_requirement;
+	funcs->set_wm_ranges = pp_rv_set_wm_ranges;
+	funcs->set_pme_wa_enable = pp_rv_set_pme_wa_enable;
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index e861929dd981..516795342dd2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -35,6 +35,8 @@
 #include "amdgpu_dm_irq.h"
 #include "amdgpu_pm.h"
 
+
+
 unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
 		unsigned long long current_time_stamp,
 		unsigned long long last_time_stamp)
@@ -72,326 +74,3 @@ bool dm_read_persistent_data(struct dc_context *ctx,
 
 /**** power component interfaces ****/
 
-bool dm_pp_apply_display_requirements(
-		const struct dc_context *ctx,
-		const struct dm_pp_display_configuration *pp_display_cfg)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-
-	if (adev->pm.dpm_enabled) {
-
-		memset(&adev->pm.pm_display_cfg, 0,
-				sizeof(adev->pm.pm_display_cfg));
-
-		adev->pm.pm_display_cfg.cpu_cc6_disable =
-			pp_display_cfg->cpu_cc6_disable;
-
-		adev->pm.pm_display_cfg.cpu_pstate_disable =
-			pp_display_cfg->cpu_pstate_disable;
-
-		adev->pm.pm_display_cfg.cpu_pstate_separation_time =
-			pp_display_cfg->cpu_pstate_separation_time;
-
-		adev->pm.pm_display_cfg.nb_pstate_switch_disable =
-			pp_display_cfg->nb_pstate_switch_disable;
-
-		adev->pm.pm_display_cfg.num_display =
-				pp_display_cfg->display_count;
-		adev->pm.pm_display_cfg.num_path_including_non_display =
-				pp_display_cfg->display_count;
-
-		adev->pm.pm_display_cfg.min_core_set_clock =
-				pp_display_cfg->min_engine_clock_khz/10;
-		adev->pm.pm_display_cfg.min_core_set_clock_in_sr =
-				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
-		adev->pm.pm_display_cfg.min_mem_set_clock =
-				pp_display_cfg->min_memory_clock_khz/10;
-
-		adev->pm.pm_display_cfg.multi_monitor_in_sync =
-				pp_display_cfg->all_displays_in_sync;
-		adev->pm.pm_display_cfg.min_vblank_time =
-				pp_display_cfg->avail_mclk_switch_time_us;
-
-		adev->pm.pm_display_cfg.display_clk =
-				pp_display_cfg->disp_clk_khz/10;
-
-		adev->pm.pm_display_cfg.dce_tolerable_mclk_in_active_latency =
-				pp_display_cfg->avail_mclk_switch_time_in_disp_active_us;
-
-		adev->pm.pm_display_cfg.crtc_index = pp_display_cfg->crtc_index;
-		adev->pm.pm_display_cfg.line_time_in_us =
-				pp_display_cfg->line_time_in_us;
-
-		adev->pm.pm_display_cfg.vrefresh = pp_display_cfg->disp_configs[0].v_refresh;
-		adev->pm.pm_display_cfg.crossfire_display_index = -1;
-		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
-
-		/* TODO: complete implementation of
-		 * pp_display_configuration_change().
-		 * Follow example of:
-		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
-		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
-		if (adev->powerplay.pp_funcs->display_configuration_change)
-			adev->powerplay.pp_funcs->display_configuration_change(
-				adev->powerplay.pp_handle,
-				&adev->pm.pm_display_cfg);
-
-		/* TODO: replace by a separate call to 'apply display cfg'? */
-		amdgpu_pm_compute_clocks(adev);
-	}
-
-	return true;
-}
-
-static void get_default_clock_levels(
-		enum dm_pp_clock_type clk_type,
-		struct dm_pp_clock_levels *clks)
-{
-	uint32_t disp_clks_in_khz[6] = {
-			300000, 400000, 496560, 626090, 685720, 757900 };
-	uint32_t sclks_in_khz[6] = {
-			300000, 360000, 423530, 514290, 626090, 720000 };
-	uint32_t mclks_in_khz[2] = { 333000, 800000 };
-
-	switch (clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		clks->num_levels = 6;
-		memmove(clks->clocks_in_khz, disp_clks_in_khz,
-				sizeof(disp_clks_in_khz));
-		break;
-	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
-		clks->num_levels = 6;
-		memmove(clks->clocks_in_khz, sclks_in_khz,
-				sizeof(sclks_in_khz));
-		break;
-	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
-		clks->num_levels = 2;
-		memmove(clks->clocks_in_khz, mclks_in_khz,
-				sizeof(mclks_in_khz));
-		break;
-	default:
-		clks->num_levels = 0;
-		break;
-	}
-}
-
-static enum amd_pp_clock_type dc_to_pp_clock_type(
-		enum dm_pp_clock_type dm_pp_clk_type)
-{
-	enum amd_pp_clock_type amd_pp_clk_type = 0;
-
-	switch (dm_pp_clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		amd_pp_clk_type = amd_pp_disp_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
-		amd_pp_clk_type = amd_pp_sys_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
-		amd_pp_clk_type = amd_pp_mem_clock;
-		break;
-	default:
-		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
-				dm_pp_clk_type);
-		break;
-	}
-
-	return amd_pp_clk_type;
-}
-
-static void pp_to_dc_clock_levels(
-		const struct amd_pp_clocks *pp_clks,
-		struct dm_pp_clock_levels *dc_clks,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->count > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->count,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		dc_clks->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		dc_clks->num_levels = pp_clks->count;
-
-	DRM_INFO("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < dc_clks->num_levels; i++) {
-		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
-		/* translate 10kHz to kHz */
-		dc_clks->clocks_in_khz[i] = pp_clks->clock[i] * 10;
-	}
-}
-
-static void pp_to_dc_clock_levels_with_latency(
-		const struct pp_clock_levels_with_latency *pp_clks,
-		struct dm_pp_clock_levels_with_latency *clk_level_info,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->num_levels,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		clk_level_info->num_levels = pp_clks->num_levels;
-
-	DRM_DEBUG("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_DEBUG("DM_PPLIB:\t %d\n", pp_clks->data[i].clocks_in_khz);
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
-		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
-	}
-}
-
-bool dm_pp_get_clock_levels_by_type(
-		const struct dc_context *ctx,
-		enum dm_pp_clock_type clk_type,
-		struct dm_pp_clock_levels *dc_clks)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct amd_pp_clocks pp_clks = { 0 };
-	struct amd_pp_simple_clock_info validation_clks = { 0 };
-	uint32_t i;
-
-	if (adev->powerplay.pp_funcs->get_clock_by_type) {
-		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
-			dc_to_pp_clock_type(clk_type), &pp_clks)) {
-		/* Error in pplib. Provide default values. */
-			get_default_clock_levels(clk_type, dc_clks);
-			return true;
-		}
-	}
-
-	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
-
-	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
-		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
-						pp_handle, &validation_clks)) {
-			/* Error in pplib. Provide default values. */
-			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
-			validation_clks.engine_max_clock = 72000;
-			validation_clks.memory_max_clock = 80000;
-			validation_clks.level = 0;
-		}
-	}
-
-	DRM_INFO("DM_PPLIB: Validation clocks:\n");
-	DRM_INFO("DM_PPLIB:    engine_max_clock: %d\n",
-			validation_clks.engine_max_clock);
-	DRM_INFO("DM_PPLIB:    memory_max_clock: %d\n",
-			validation_clks.memory_max_clock);
-	DRM_INFO("DM_PPLIB:    level           : %d\n",
-			validation_clks.level);
-
-	/* Translate 10 kHz to kHz. */
-	validation_clks.engine_max_clock *= 10;
-	validation_clks.memory_max_clock *= 10;
-
-	/* Determine the highest non-boosted level from the Validation Clocks */
-	if (clk_type == DM_PP_CLOCK_TYPE_ENGINE_CLK) {
-		for (i = 0; i < dc_clks->num_levels; i++) {
-			if (dc_clks->clocks_in_khz[i] > validation_clks.engine_max_clock) {
-				/* This clock is higher the validation clock.
-				 * Than means the previous one is the highest
-				 * non-boosted one. */
-				DRM_INFO("DM_PPLIB: reducing engine clock level from %d to %d\n",
-						dc_clks->num_levels, i);
-				dc_clks->num_levels = i > 0 ? i : 1;
-				break;
-			}
-		}
-	} else if (clk_type == DM_PP_CLOCK_TYPE_MEMORY_CLK) {
-		for (i = 0; i < dc_clks->num_levels; i++) {
-			if (dc_clks->clocks_in_khz[i] > validation_clks.memory_max_clock) {
-				DRM_INFO("DM_PPLIB: reducing memory clock level from %d to %d\n",
-						dc_clks->num_levels, i);
-				dc_clks->num_levels = i > 0 ? i : 1;
-				break;
-			}
-		}
-	}
-
-	return true;
-}
-
-bool dm_pp_get_clock_levels_by_type_with_latency(
-	const struct dc_context *ctx,
-	enum dm_pp_clock_type clk_type,
-	struct dm_pp_clock_levels_with_latency *clk_level_info)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct pp_clock_levels_with_latency pp_clks = { 0 };
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
-		return false;
-
-	if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
-						     dc_to_pp_clock_type(clk_type),
-						     &pp_clks))
-		return false;
-
-	pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
-
-	return true;
-}
-
-bool dm_pp_get_clock_levels_by_type_with_voltage(
-	const struct dc_context *ctx,
-	enum dm_pp_clock_type clk_type,
-	struct dm_pp_clock_levels_with_voltage *clk_level_info)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_notify_wm_clock_changes(
-	const struct dc_context *ctx,
-	struct dm_pp_wm_sets_with_clock_ranges *wm_with_clock_ranges)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_apply_power_level_change_request(
-	const struct dc_context *ctx,
-	struct dm_pp_power_level_change_request *level_change_req)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_apply_clock_for_voltage_request(
-	const struct dc_context *ctx,
-	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_get_static_clocks(
-	const struct dc_context *ctx,
-	struct dm_pp_static_clock_info *static_clk_info)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-void dm_pp_get_funcs_rv(
-		struct dc_context *ctx,
-		struct pp_smu_funcs_rv *funcs)
-{}
-
-/**** end of power component interfaces ****/
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index aed538a4d1ba..532a515fda9a 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -25,7 +25,7 @@
 
 DC_LIBS = basics bios calcs dce gpio i2caux irq virtual
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 DC_LIBS += dcn10 dml
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index b49ea96b5dae..a50a76471107 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 \
-	logger.o log_helpers.o vector.o
+	log_helpers.o vector.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
index f6c00a51d51a..26583f346c39 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
@@ -28,77 +28,12 @@
 #include "include/logger_interface.h"
 #include "dm_helpers.h"
 
-#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
-
-struct dc_signal_type_info {
-	enum signal_type type;
-	char name[MAX_NAME_LEN];
-};
-
-static const struct dc_signal_type_info signal_type_info_tbl[] = {
-		{SIGNAL_TYPE_NONE,             "NC"},
-		{SIGNAL_TYPE_DVI_SINGLE_LINK,  "DVI"},
-		{SIGNAL_TYPE_DVI_DUAL_LINK,    "DDVI"},
-		{SIGNAL_TYPE_HDMI_TYPE_A,      "HDMIA"},
-		{SIGNAL_TYPE_LVDS,             "LVDS"},
-		{SIGNAL_TYPE_RGB,              "VGA"},
-		{SIGNAL_TYPE_DISPLAY_PORT,     "DP"},
-		{SIGNAL_TYPE_DISPLAY_PORT_MST, "MST"},
-		{SIGNAL_TYPE_EDP,              "eDP"},
-		{SIGNAL_TYPE_VIRTUAL,          "Virtual"}
-};
-
-void dc_conn_log(struct dc_context *ctx,
-		const struct dc_link *link,
-		uint8_t *hex_data,
-		int hex_data_count,
-		enum dc_log_type event,
-		const char *msg,
-		...)
+void dc_conn_log_hex_linux(const uint8_t *hex_data, int hex_data_count)
 {
 	int i;
-	va_list args;
-	struct log_entry entry = { 0 };
-	enum signal_type signal;
-
-	if (link->local_sink)
-		signal = link->local_sink->sink_signal;
-	else
-		signal = link->connector_signal;
-
-	if (link->type == dc_connection_mst_branch)
-		signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
-
-	dm_logger_open(ctx->logger, &entry, event);
-
-	for (i = 0; i < NUM_ELEMENTS(signal_type_info_tbl); i++)
-		if (signal == signal_type_info_tbl[i].type)
-			break;
-
-	if (i == NUM_ELEMENTS(signal_type_info_tbl))
-		goto fail;
-
-	dm_logger_append_heading(&entry);
-
-	dm_logger_append(&entry, "[%s][ConnIdx:%d] ",
-			signal_type_info_tbl[i].name,
-			link->link_index);
-
-	va_start(args, msg);
-	dm_logger_append_va(&entry, msg, args);
-
-	if (entry.buf_offset > 0 &&
-	    entry.buf[entry.buf_offset - 1] == '\n')
-		entry.buf_offset--;
 
 	if (hex_data)
 		for (i = 0; i < hex_data_count; i++)
-			dm_logger_append(&entry, "%2.2X ", hex_data[i]);
-
-	dm_logger_append(&entry, "^\n");
-
-fail:
-	dm_logger_close(&entry);
-
-	va_end(args);
+			DC_LOG_DEBUG("%2.2X ", hex_data[i]);
 }
+
diff --git a/drivers/gpu/drm/amd/display/dc/basics/logger.c b/drivers/gpu/drm/amd/display/dc/basics/logger.c
deleted file mode 100644
index a3c56cd8b396..000000000000
--- a/drivers/gpu/drm/amd/display/dc/basics/logger.c
+++ /dev/null
@@ -1,406 +0,0 @@
-/*
- * 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 "dm_services.h"
-#include "include/logger_interface.h"
-#include "logger.h"
-
-
-#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
-
-static const struct dc_log_type_info log_type_info_tbl[] = {
-		{LOG_ERROR,                 "Error"},
-		{LOG_WARNING,               "Warning"},
-		{LOG_DEBUG,                 "Debug"},
-		{LOG_DC,                    "DC_Interface"},
-		{LOG_DTN,                   "DTN"},
-		{LOG_SURFACE,               "Surface"},
-		{LOG_HW_HOTPLUG,            "HW_Hotplug"},
-		{LOG_HW_LINK_TRAINING,      "HW_LKTN"},
-		{LOG_HW_SET_MODE,           "HW_Mode"},
-		{LOG_HW_RESUME_S3,          "HW_Resume"},
-		{LOG_HW_AUDIO,              "HW_Audio"},
-		{LOG_HW_HPD_IRQ,            "HW_HPDIRQ"},
-		{LOG_MST,                   "MST"},
-		{LOG_SCALER,                "Scaler"},
-		{LOG_BIOS,                  "BIOS"},
-		{LOG_BANDWIDTH_CALCS,       "BWCalcs"},
-		{LOG_BANDWIDTH_VALIDATION,  "BWValidation"},
-		{LOG_I2C_AUX,               "I2C_AUX"},
-		{LOG_SYNC,                  "Sync"},
-		{LOG_BACKLIGHT,             "Backlight"},
-		{LOG_FEATURE_OVERRIDE,      "Override"},
-		{LOG_DETECTION_EDID_PARSER, "Edid"},
-		{LOG_DETECTION_DP_CAPS,     "DP_Caps"},
-		{LOG_RESOURCE,              "Resource"},
-		{LOG_DML,                   "DML"},
-		{LOG_EVENT_MODE_SET,        "Mode"},
-		{LOG_EVENT_DETECTION,       "Detect"},
-		{LOG_EVENT_LINK_TRAINING,   "LKTN"},
-		{LOG_EVENT_LINK_LOSS,       "LinkLoss"},
-		{LOG_EVENT_UNDERFLOW,       "Underflow"},
-		{LOG_IF_TRACE,              "InterfaceTrace"},
-		{LOG_PERF_TRACE,            "PerfTrace"},
-		{LOG_DISPLAYSTATS,          "DisplayStats"}
-};
-
-
-/* ----------- Object init and destruction ----------- */
-static bool construct(struct dc_context *ctx, struct dal_logger *logger,
-		      uint32_t log_mask)
-{
-	/* malloc buffer and init offsets */
-	logger->log_buffer_size = DAL_LOGGER_BUFFER_MAX_SIZE;
-	logger->log_buffer = kcalloc(logger->log_buffer_size, sizeof(char),
-				     GFP_KERNEL);
-	if (!logger->log_buffer)
-		return false;
-
-	/* Initialize both offsets to start of buffer (empty) */
-	logger->buffer_read_offset = 0;
-	logger->buffer_write_offset = 0;
-
-	logger->open_count = 0;
-
-	logger->flags.bits.ENABLE_CONSOLE = 1;
-	logger->flags.bits.ENABLE_BUFFER = 0;
-
-	logger->ctx = ctx;
-
-	logger->mask = log_mask;
-
-	return true;
-}
-
-static void destruct(struct dal_logger *logger)
-{
-	if (logger->log_buffer) {
-		kfree(logger->log_buffer);
-		logger->log_buffer = NULL;
-	}
-}
-
-struct dal_logger *dal_logger_create(struct dc_context *ctx, uint32_t log_mask)
-{
-	/* malloc struct */
-	struct dal_logger *logger = kzalloc(sizeof(struct dal_logger),
-					    GFP_KERNEL);
-
-	if (!logger)
-		return NULL;
-	if (!construct(ctx, logger, log_mask)) {
-		kfree(logger);
-		return NULL;
-	}
-
-	return logger;
-}
-
-uint32_t dal_logger_destroy(struct dal_logger **logger)
-{
-	if (logger == NULL || *logger == NULL)
-		return 1;
-	destruct(*logger);
-	kfree(*logger);
-	*logger = NULL;
-
-	return 0;
-}
-
-/* ------------------------------------------------------------------------ */
-void dm_logger_append_heading(struct log_entry *entry)
-{
-	int j;
-
-	for (j = 0; j < NUM_ELEMENTS(log_type_info_tbl); j++) {
-
-		const struct dc_log_type_info *info = &log_type_info_tbl[j];
-
-		if (info->type == entry->type)
-			dm_logger_append(entry, "[%s]\t", info->name);
-	}
-}
-
-
-/* Print everything unread existing in log_buffer to debug console*/
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn)
-{
-	char *string_start = &logger->log_buffer[logger->buffer_read_offset];
-
-	if (should_warn)
-		dm_output_to_console(
-			"---------------- FLUSHING LOG BUFFER ----------------\n");
-	while (logger->buffer_read_offset < logger->buffer_write_offset) {
-
-		if (logger->log_buffer[logger->buffer_read_offset] == '\0') {
-			dm_output_to_console("%s", string_start);
-			string_start = logger->log_buffer + logger->buffer_read_offset + 1;
-		}
-		logger->buffer_read_offset++;
-	}
-	if (should_warn)
-		dm_output_to_console(
-			"-------------- END FLUSHING LOG BUFFER --------------\n\n");
-}
-/* ------------------------------------------------------------------------ */
-
-/* Warning: Be careful that 'msg' is null terminated and the total size is
- * less than DAL_LOGGER_BUFFER_MAX_LOG_LINE_SIZE (256) including '\0'
- */
-static bool dal_logger_should_log(
-	struct dal_logger *logger,
-	enum dc_log_type log_type)
-{
-	if (logger->mask & (1 << log_type))
-		return true;
-
-	return false;
-}
-
-static void log_to_debug_console(struct log_entry *entry)
-{
-	struct dal_logger *logger = entry->logger;
-
-	if (logger->flags.bits.ENABLE_CONSOLE == 0)
-		return;
-
-	if (entry->buf_offset) {
-		switch (entry->type) {
-		case LOG_ERROR:
-			dm_error("%s", entry->buf);
-			break;
-		default:
-			dm_output_to_console("%s", entry->buf);
-			break;
-		}
-	}
-}
-
-
-static void log_to_internal_buffer(struct log_entry *entry)
-{
-
-	uint32_t size = entry->buf_offset;
-	struct dal_logger *logger = entry->logger;
-
-	if (logger->flags.bits.ENABLE_BUFFER == 0)
-		return;
-
-	if (logger->log_buffer == NULL)
-		return;
-
-	if (size > 0 && size < logger->log_buffer_size) {
-
-		int buffer_space = logger->log_buffer_size -
-				logger->buffer_write_offset;
-
-		if (logger->buffer_write_offset == logger->buffer_read_offset) {
-			/* Buffer is empty, start writing at beginning */
-			buffer_space = logger->log_buffer_size;
-			logger->buffer_write_offset = 0;
-			logger->buffer_read_offset = 0;
-		}
-
-		if (buffer_space > size) {
-			/* No wrap around, copy 'size' bytes
-			 * from 'entry->buf' to 'log_buffer'
-			 */
-			memmove(logger->log_buffer +
-					logger->buffer_write_offset,
-					entry->buf, size);
-			logger->buffer_write_offset += size;
-
-		} else {
-			/* Not enough room remaining, we should flush
-			 * existing logs */
-
-			/* Flush existing unread logs to console */
-			dm_logger_flush_buffer(logger, true);
-
-			/* Start writing to beginning of buffer */
-			memmove(logger->log_buffer, entry->buf, size);
-			logger->buffer_write_offset = size;
-			logger->buffer_read_offset = 0;
-		}
-
-	}
-}
-
-static void append_entry(
-		struct log_entry *entry,
-		char *buffer,
-		uint32_t buf_size)
-{
-	if (!entry->buf ||
-		entry->buf_offset + buf_size > entry->max_buf_bytes
-	) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	/* Todo: check if off by 1 byte due to \0 anywhere */
-	memmove(entry->buf + entry->buf_offset, buffer, buf_size);
-	entry->buf_offset += buf_size;
-}
-
-
-void dm_logger_write(
-	struct dal_logger *logger,
-	enum dc_log_type log_type,
-	const char *msg,
-	...)
-{
-	if (logger && dal_logger_should_log(logger, log_type)) {
-		uint32_t size;
-		va_list args;
-		char buffer[LOG_MAX_LINE_SIZE];
-		struct log_entry entry;
-
-		va_start(args, msg);
-
-		entry.logger = logger;
-
-		entry.buf = buffer;
-
-		entry.buf_offset = 0;
-		entry.max_buf_bytes = DAL_LOGGER_BUFFER_MAX_SIZE * sizeof(char);
-
-		entry.type = log_type;
-
-		dm_logger_append_heading(&entry);
-
-		size = dm_log_to_buffer(
-			buffer, LOG_MAX_LINE_SIZE - 1, msg, args);
-
-		buffer[entry.buf_offset + size] = '\0';
-		entry.buf_offset += size + 1;
-
-		/* --Flush log_entry buffer-- */
-		/* print to kernel console */
-		log_to_debug_console(&entry);
-		/* log internally for dsat */
-		log_to_internal_buffer(&entry);
-
-		va_end(args);
-	}
-}
-
-/* Same as dm_logger_write, except without open() and close(), which must
- * be done separately.
- */
-void dm_logger_append(
-	struct log_entry *entry,
-	const char *msg,
-	...)
-{
-	va_list args;
-
-	va_start(args, msg);
-	dm_logger_append_va(entry, msg, args);
-	va_end(args);
-}
-
-void dm_logger_append_va(
-	struct log_entry *entry,
-	const char *msg,
-	va_list args)
-{
-	struct dal_logger *logger;
-
-	if (!entry) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	logger = entry->logger;
-
-	if (logger && logger->open_count > 0 &&
-		dal_logger_should_log(logger, entry->type)) {
-
-		uint32_t size;
-		char buffer[LOG_MAX_LINE_SIZE];
-
-		size = dm_log_to_buffer(
-			buffer, LOG_MAX_LINE_SIZE, msg, args);
-
-		if (size < LOG_MAX_LINE_SIZE - 1) {
-			append_entry(entry, buffer, size);
-		} else {
-			append_entry(entry, "LOG_ERROR, line too long\n", 27);
-		}
-	}
-}
-
-void dm_logger_open(
-		struct dal_logger *logger,
-		struct log_entry *entry, /* out */
-		enum dc_log_type log_type)
-{
-	if (!entry) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	entry->type = log_type;
-	entry->logger = logger;
-
-	entry->buf = kzalloc(DAL_LOGGER_BUFFER_MAX_SIZE,
-			     GFP_KERNEL);
-
-	entry->buf_offset = 0;
-	entry->max_buf_bytes = DAL_LOGGER_BUFFER_MAX_SIZE * sizeof(char);
-
-	logger->open_count++;
-
-	dm_logger_append_heading(entry);
-}
-
-void dm_logger_close(struct log_entry *entry)
-{
-	struct dal_logger *logger = entry->logger;
-
-	if (logger && logger->open_count > 0) {
-		logger->open_count--;
-	} else {
-		BREAK_TO_DEBUGGER();
-		goto cleanup;
-	}
-
-	/* --Flush log_entry buffer-- */
-	/* print to kernel console */
-	log_to_debug_console(entry);
-	/* log internally for dsat */
-	log_to_internal_buffer(entry);
-
-	/* TODO: Write end heading */
-
-cleanup:
-	if (entry->buf) {
-		kfree(entry->buf);
-		entry->buf = NULL;
-		entry->buf_offset = 0;
-		entry->max_buf_bytes = 0;
-	}
-}
-
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 c7f0b27e457e..be8a2494355a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -3762,6 +3762,200 @@ static struct integrated_info *bios_parser_create_integrated_info(
 	return NULL;
 }
 
+enum bp_result update_slot_layout_info(
+	struct dc_bios *dcb,
+	unsigned int i,
+	struct slot_layout_info *slot_layout_info,
+	unsigned int record_offset)
+{
+	unsigned int j;
+	struct bios_parser *bp;
+	ATOM_BRACKET_LAYOUT_RECORD *record;
+	ATOM_COMMON_RECORD_HEADER *record_header;
+	enum bp_result result = BP_RESULT_NORECORD;
+
+	bp = BP_FROM_DCB(dcb);
+	record = NULL;
+	record_header = NULL;
+
+	for (;;) {
+
+		record_header = (ATOM_COMMON_RECORD_HEADER *)
+			GET_IMAGE(ATOM_COMMON_RECORD_HEADER, record_offset);
+		if (record_header == NULL) {
+			result = BP_RESULT_BADBIOSTABLE;
+			break;
+		}
+
+		/* the end of the list */
+		if (record_header->ucRecordType == 0xff ||
+			record_header->ucRecordSize == 0)	{
+			break;
+		}
+
+		if (record_header->ucRecordType ==
+			ATOM_BRACKET_LAYOUT_RECORD_TYPE &&
+			sizeof(ATOM_BRACKET_LAYOUT_RECORD)
+			<= record_header->ucRecordSize) {
+			record = (ATOM_BRACKET_LAYOUT_RECORD *)
+				(record_header);
+			result = BP_RESULT_OK;
+			break;
+		}
+
+		record_offset += record_header->ucRecordSize;
+	}
+
+	/* return if the record not found */
+	if (result != BP_RESULT_OK)
+		return result;
+
+	/* get slot sizes */
+	slot_layout_info->length = record->ucLength;
+	slot_layout_info->width = record->ucWidth;
+
+	/* get info for each connector in the slot */
+	slot_layout_info->num_of_connectors = record->ucConnNum;
+	for (j = 0; j < slot_layout_info->num_of_connectors; ++j) {
+		slot_layout_info->connectors[j].connector_type =
+			(enum connector_layout_type)
+			(record->asConnInfo[j].ucConnectorType);
+		switch (record->asConnInfo[j].ucConnectorType) {
+		case CONNECTOR_TYPE_DVI_D:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DVI_D;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DVI;
+			break;
+
+		case CONNECTOR_TYPE_HDMI:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_HDMI;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_HDMI;
+			break;
+
+		case CONNECTOR_TYPE_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DP;
+			break;
+
+		case CONNECTOR_TYPE_MINI_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_MINI_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_MINI_DP;
+			break;
+
+		default:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_UNKNOWN;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_UNKNOWN;
+		}
+
+		slot_layout_info->connectors[j].position =
+			record->asConnInfo[j].ucPosition;
+		slot_layout_info->connectors[j].connector_id =
+			object_id_from_bios_object_id(
+				record->asConnInfo[j].usConnectorObjectId);
+	}
+	return result;
+}
+
+
+enum bp_result get_bracket_layout_record(
+	struct dc_bios *dcb,
+	unsigned int bracket_layout_id,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int i;
+	unsigned int record_offset;
+	struct bios_parser *bp;
+	enum bp_result result;
+	ATOM_OBJECT *object;
+	ATOM_OBJECT_TABLE *object_table;
+	unsigned int genericTableOffset;
+
+	bp = BP_FROM_DCB(dcb);
+	object = NULL;
+	if (slot_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid slot_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+
+	genericTableOffset = bp->object_info_tbl_offset +
+		bp->object_info_tbl.v1_3->usMiscObjectTableOffset;
+	object_table = (ATOM_OBJECT_TABLE *)
+		GET_IMAGE(ATOM_OBJECT_TABLE, genericTableOffset);
+	if (!object_table)
+		return BP_RESULT_FAILURE;
+
+	result = BP_RESULT_NORECORD;
+	for (i = 0; i < object_table->ucNumberOfObjects; ++i) {
+
+		if (bracket_layout_id ==
+			object_table->asObjects[i].usObjectID) {
+
+			object = &object_table->asObjects[i];
+			record_offset = object->usRecordOffset +
+				bp->object_info_tbl_offset;
+
+			result = update_slot_layout_info(dcb, i,
+				slot_layout_info, record_offset);
+			break;
+		}
+	}
+	return result;
+}
+
+static enum bp_result bios_get_board_layout_info(
+	struct dc_bios *dcb,
+	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] = {
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1,
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2,
+		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;
+	}
+
+	board_layout_info->num_of_slots = 0;
+
+	for (i = 0; i < MAX_BOARD_SLOTS; ++i) {
+		record_result = get_bracket_layout_record(dcb,
+			slot_index_to_vbios_id[i],
+			&board_layout_info->slots[i]);
+
+		if (record_result == BP_RESULT_NORECORD && i > 0)
+			break; /* no more slots present in bios */
+		else if (record_result != BP_RESULT_OK)
+			return record_result;  /* fail */
+
+		++board_layout_info->num_of_slots;
+	}
+
+	/* all data is valid */
+	board_layout_info->is_number_of_slots_valid = 1;
+	board_layout_info->is_slots_size_valid = 1;
+	board_layout_info->is_connector_offsets_valid = 1;
+	board_layout_info->is_connector_lengths_valid = 1;
+
+	return BP_RESULT_OK;
+}
+
 /******************************************************************************/
 
 static const struct dc_vbios_funcs vbios_funcs = {
@@ -3836,6 +4030,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.post_init = bios_parser_post_init,  /* patch vbios table for mxm module by reading i2c */
 
 	.bios_parser_destroy = bios_parser_destroy,
+
+	.get_board_layout_info = bios_get_board_layout_info,
 };
 
 static bool bios_parser_construct(
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 b8cef7af3c4a..eab007e1793c 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -43,6 +43,29 @@
 #include "bios_parser_interface.h"
 
 #include "bios_parser_common.h"
+
+/* Temporarily add in defines until ObjectID.h patch is updated in a few days */
+#ifndef GENERIC_OBJECT_ID_BRACKET_LAYOUT
+#define GENERIC_OBJECT_ID_BRACKET_LAYOUT          0x05
+#endif /* GENERIC_OBJECT_ID_BRACKET_LAYOUT */
+
+#ifndef GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1	\
+	(GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+	GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+	GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+#endif /* GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1 */
+
+#ifndef GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2	\
+	(GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+	GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
+	GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+#endif /* GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2 */
+
+#define DC_LOGGER \
+	bp->base.ctx->logger
+
 #define LAST_RECORD_TYPE 0xff
 #define SMU9_SYSPLL0_ID  0
 
@@ -86,7 +109,6 @@ 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)
 {
 	kfree(bp->base.bios_local_image);
@@ -656,7 +678,7 @@ static enum bp_result bios_parser_get_gpio_pin_info(
 		return BP_RESULT_BADBIOSTABLE;
 
 	if (sizeof(struct atom_common_table_header) +
-			sizeof(struct atom_gpio_pin_lut_v2_1)
+			sizeof(struct atom_gpio_pin_assignment)
 			> le16_to_cpu(header->table_header.structuresize))
 		return BP_RESULT_BADBIOSTABLE;
 
@@ -1854,6 +1876,198 @@ static struct integrated_info *bios_parser_create_integrated_info(
 	return NULL;
 }
 
+static enum bp_result update_slot_layout_info(
+	struct dc_bios *dcb,
+	unsigned int i,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int record_offset;
+	unsigned int j;
+	struct atom_display_object_path_v2 *object;
+	struct atom_bracket_layout_record *record;
+	struct atom_common_record_header *record_header;
+	enum bp_result result;
+	struct bios_parser *bp;
+	struct object_info_table *tbl;
+	struct display_object_info_table_v1_4 *v1_4;
+
+	record = NULL;
+	record_header = NULL;
+	result = BP_RESULT_NORECORD;
+
+	bp = BP_FROM_DCB(dcb);
+	tbl = &bp->object_info_tbl;
+	v1_4 = tbl->v1_4;
+
+	object = &v1_4->display_path[i];
+	record_offset = (unsigned int)
+		(object->disp_recordoffset) +
+		(unsigned int)(bp->object_info_tbl_offset);
+
+	for (;;) {
+
+		record_header = (struct atom_common_record_header *)
+			GET_IMAGE(struct atom_common_record_header,
+			record_offset);
+		if (record_header == NULL) {
+			result = BP_RESULT_BADBIOSTABLE;
+			break;
+		}
+
+		/* the end of the list */
+		if (record_header->record_type == 0xff ||
+			record_header->record_size == 0)	{
+			break;
+		}
+
+		if (record_header->record_type ==
+			ATOM_BRACKET_LAYOUT_RECORD_TYPE &&
+			sizeof(struct atom_bracket_layout_record)
+			<= record_header->record_size) {
+			record = (struct atom_bracket_layout_record *)
+				(record_header);
+			result = BP_RESULT_OK;
+			break;
+		}
+
+		record_offset += record_header->record_size;
+	}
+
+	/* return if the record not found */
+	if (result != BP_RESULT_OK)
+		return result;
+
+	/* get slot sizes */
+	slot_layout_info->length = record->bracketlen;
+	slot_layout_info->width = record->bracketwidth;
+
+	/* get info for each connector in the slot */
+	slot_layout_info->num_of_connectors = record->conn_num;
+	for (j = 0; j < slot_layout_info->num_of_connectors; ++j) {
+		slot_layout_info->connectors[j].connector_type =
+			(enum connector_layout_type)
+			(record->conn_info[j].connector_type);
+		switch (record->conn_info[j].connector_type) {
+		case CONNECTOR_TYPE_DVI_D:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DVI_D;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DVI;
+			break;
+
+		case CONNECTOR_TYPE_HDMI:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_HDMI;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_HDMI;
+			break;
+
+		case CONNECTOR_TYPE_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DP;
+			break;
+
+		case CONNECTOR_TYPE_MINI_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_MINI_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_MINI_DP;
+			break;
+
+		default:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_UNKNOWN;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_UNKNOWN;
+		}
+
+		slot_layout_info->connectors[j].position =
+			record->conn_info[j].position;
+		slot_layout_info->connectors[j].connector_id =
+			object_id_from_bios_object_id(
+				record->conn_info[j].connectorobjid);
+	}
+	return result;
+}
+
+
+static enum bp_result get_bracket_layout_record(
+	struct dc_bios *dcb,
+	unsigned int bracket_layout_id,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp = BP_FROM_DCB(dcb);
+	enum bp_result result;
+	struct object_info_table *tbl;
+	struct display_object_info_table_v1_4 *v1_4;
+
+	if (slot_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid slot_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+	tbl = &bp->object_info_tbl;
+	v1_4 = tbl->v1_4;
+
+	result = BP_RESULT_NORECORD;
+	for (i = 0; i < v1_4->number_of_path; ++i)	{
+
+		if (bracket_layout_id ==
+			v1_4->display_path[i].display_objid) {
+			result = update_slot_layout_info(dcb, i,
+				slot_layout_info);
+			break;
+		}
+	}
+	return result;
+}
+
+static enum bp_result bios_get_board_layout_info(
+	struct dc_bios *dcb,
+	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] = {
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1,
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2,
+		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;
+	}
+
+	board_layout_info->num_of_slots = 0;
+
+	for (i = 0; i < MAX_BOARD_SLOTS; ++i) {
+		record_result = get_bracket_layout_record(dcb,
+			slot_index_to_vbios_id[i],
+			&board_layout_info->slots[i]);
+
+		if (record_result == BP_RESULT_NORECORD && i > 0)
+			break; /* no more slots present in bios */
+		else if (record_result != BP_RESULT_OK)
+			return record_result;  /* fail */
+
+		++board_layout_info->num_of_slots;
+	}
+
+	/* all data is valid */
+	board_layout_info->is_number_of_slots_valid = 1;
+	board_layout_info->is_slots_size_valid = 1;
+	board_layout_info->is_connector_offsets_valid = 1;
+	board_layout_info->is_connector_lengths_valid = 1;
+
+	return BP_RESULT_OK;
+}
+
 static const struct dc_vbios_funcs vbios_funcs = {
 	.get_connectors_number = bios_parser_get_connectors_number,
 
@@ -1925,6 +2139,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.bios_parser_destroy = firmware_parser_destroy,
 
 	.get_smu_clock_info = bios_parser_get_smu_clock_info,
+
+	.get_board_layout_info = bios_get_board_layout_info,
 };
 
 static bool bios_parser_construct(
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 752b08a42d3e..2b5dc499a35e 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -59,36 +59,7 @@
 	bios_cmd_table_para_revision(bp->base.ctx->driver_context, \
 			GET_INDEX_INTO_MASTER_TABLE(command, fname))
 
-static void init_dig_encoder_control(struct bios_parser *bp);
-static void init_transmitter_control(struct bios_parser *bp);
-static void init_set_pixel_clock(struct bios_parser *bp);
 
-static void init_set_crtc_timing(struct bios_parser *bp);
-
-static void init_select_crtc_source(struct bios_parser *bp);
-static void init_enable_crtc(struct bios_parser *bp);
-
-static void init_external_encoder_control(struct bios_parser *bp);
-static void init_enable_disp_power_gating(struct bios_parser *bp);
-static void init_set_dce_clock(struct bios_parser *bp);
-static void init_get_smu_clock_info(struct bios_parser *bp);
-
-void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
-{
-	init_dig_encoder_control(bp);
-	init_transmitter_control(bp);
-	init_set_pixel_clock(bp);
-
-	init_set_crtc_timing(bp);
-
-	init_select_crtc_source(bp);
-	init_enable_crtc(bp);
-
-	init_external_encoder_control(bp);
-	init_enable_disp_power_gating(bp);
-	init_set_dce_clock(bp);
-	init_get_smu_clock_info(bp);
-}
 
 static uint32_t bios_cmd_table_para_revision(void *dev,
 					     uint32_t index)
@@ -829,3 +800,20 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id)
 	return 0;
 }
 
+void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
+{
+	init_dig_encoder_control(bp);
+	init_transmitter_control(bp);
+	init_set_pixel_clock(bp);
+
+	init_set_crtc_timing(bp);
+
+	init_select_crtc_source(bp);
+	init_enable_crtc(bp);
+
+	init_external_encoder_control(bp);
+	init_enable_disp_power_gating(bp);
+	init_set_dce_clock(bp);
+	init_get_smu_clock_info(bp);
+
+}
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 bbbcef566c55..770ff89ba7e1 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
@@ -55,7 +55,7 @@ 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)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 95f332ee3e7e..416500e51b8d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -38,7 +38,7 @@ CFLAGS_dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare
 
 BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 BW_CALCS += dcn_calcs.o dcn_calc_math.o dcn_calc_auto.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
index fc3f98fb09ea..62435bfc274d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
+++ b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
@@ -25,10 +25,9 @@
 
 #ifndef _CALCS_CALCS_LOGGER_H_
 #define _CALCS_CALCS_LOGGER_H_
-#define DC_LOGGER \
-	logger
+#define DC_LOGGER ctx->logger
 
-static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calcs_dceip *dceip)
+static void print_bw_calcs_dceip(struct dc_context *ctx, const struct bw_calcs_dceip *dceip)
 {
 
 	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
@@ -122,7 +121,7 @@ static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calc
 
 }
 
-static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calcs_vbios *vbios)
+static void print_bw_calcs_vbios(struct dc_context *ctx, const struct bw_calcs_vbios *vbios)
 {
 
 	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
@@ -181,7 +180,7 @@ static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calc
 
 }
 
-static void print_bw_calcs_data(struct dal_logger *logger, struct bw_calcs_data *data)
+static void print_bw_calcs_data(struct dc_context *ctx, struct bw_calcs_data *data)
 {
 
 	int i, j, k;
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 2c4e8f0cb2dc..160d11a15eac 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -3010,9 +3010,9 @@ bool bw_calcs(struct dc_context *ctx,
 		struct bw_fixed low_yclk = vbios->low_yclk;
 
 		if (ctx->dc->debug.bandwidth_calcs_trace) {
-			print_bw_calcs_dceip(ctx->logger, dceip);
-			print_bw_calcs_vbios(ctx->logger, vbios);
-			print_bw_calcs_data(ctx->logger, data);
+			print_bw_calcs_dceip(ctx, dceip);
+			print_bw_calcs_vbios(ctx, vbios);
+			print_bw_calcs_data(ctx, data);
 		}
 		calculate_bandwidth(dceip, vbios, data);
 
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 49a4ea45466d..bd039322f697 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -31,6 +31,8 @@
 
 #include "resource.h"
 #include "dcn10/dcn10_resource.h"
+#include "dcn10/dcn10_hubbub.h"
+
 #include "dcn_calc_math.h"
 
 #define DC_LOGGER \
@@ -248,7 +250,24 @@ static void pipe_ctx_to_e2e_pipe_params (
 	else if (pipe->bottom_pipe != NULL && pipe->bottom_pipe->plane_state == pipe->plane_state)
 		input->src.is_hsplit = true;
 
-	input->src.dcc                 = pipe->plane_state->dcc.enable;
+	if (pipe->plane_res.dpp->ctx->dc->debug.optimized_watermark) {
+		/*
+		 * this method requires us to always re-calculate watermark when dcc change
+		 * between flip.
+		 */
+		input->src.dcc = pipe->plane_state->dcc.enable ? 1 : 0;
+	} else {
+		/*
+		 * allow us to disable dcc on the fly without re-calculating WM
+		 *
+		 * extra overhead for DCC is quite small.  for 1080p WM without
+		 * DCC is only 0.417us lower (urgent goes from 6.979us to 6.562us)
+		 */
+		unsigned int bpe;
+
+		input->src.dcc = pipe->plane_res.dpp->ctx->dc->res_pool->hubbub->funcs->
+			dcc_support_pixel_format(pipe->plane_state->format, &bpe) ? 1 : 0;
+	}
 	input->src.dcc_rate            = 1;
 	input->src.meta_pitch          = pipe->plane_state->dcc.grph.meta_pitch;
 	input->src.source_scan         = dm_horz;
@@ -423,6 +442,10 @@ static void dcn_bw_calc_rq_dlg_ttu(
 	int total_flip_bytes = 0;
 	int i;
 
+	memset(dlg_regs, 0, sizeof(*dlg_regs));
+	memset(ttu_regs, 0, sizeof(*ttu_regs));
+	memset(rq_regs, 0, sizeof(*rq_regs));
+
 	for (i = 0; i < number_of_planes; i++) {
 		total_active_bw += v->read_bandwidth[i];
 		total_prefetch_bw += v->prefetch_bandwidth[i];
@@ -501,6 +524,7 @@ static void split_stream_across_pipes(
 	resource_build_scaling_params(secondary_pipe);
 }
 
+#if 0
 static void calc_wm_sets_and_perf_params(
 		struct dc_state *context,
 		struct dcn_bw_internal_vars *v)
@@ -582,6 +606,7 @@ static void calc_wm_sets_and_perf_params(
 	if (v->voltage_level >= 3)
 		context->bw.dcn.watermarks.d = context->bw.dcn.watermarks.a;
 }
+#endif
 
 static bool dcn_bw_apply_registry_override(struct dc *dc)
 {
@@ -651,7 +676,7 @@ static void hack_force_pipe_split(struct dcn_bw_internal_vars *v,
 }
 
 static void hack_bounding_box(struct dcn_bw_internal_vars *v,
-		struct dc_debug *dbg,
+		struct dc_debug_options *dbg,
 		struct dc_state *context)
 {
 	if (dbg->pipe_split_policy == MPC_SPLIT_AVOID)
@@ -883,7 +908,26 @@ bool dcn_validate_bandwidth(
 				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dc_fixpt_one.value
 					|| v->scaler_rec_out_width[input_idx] == v->viewport_height[input_idx]);
 			}
-			v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
+
+			if (dc->debug.optimized_watermark) {
+				/*
+				 * this method requires us to always re-calculate watermark when dcc change
+				 * between flip.
+				 */
+				v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
+			} else {
+				/*
+				 * allow us to disable dcc on the fly without re-calculating WM
+				 *
+				 * extra overhead for DCC is quite small.  for 1080p WM without
+				 * DCC is only 0.417us lower (urgent goes from 6.979us to 6.562us)
+				 */
+				unsigned int bpe;
+
+				v->dcc_enable[input_idx] = dc->res_pool->hubbub->funcs->dcc_support_pixel_format(
+						pipe->plane_state->format, &bpe) ? dcn_bw_yes : dcn_bw_no;
+			}
+
 			v->source_pixel_format[input_idx] = tl_pixel_format_to_bw_defs(
 					pipe->plane_state->format);
 			v->source_surface_mode[input_idx] = tl_sw_mode_to_bw_defs(
@@ -976,43 +1020,60 @@ bool dcn_validate_bandwidth(
 				bw_consumed = v->fabric_and_dram_bandwidth;
 
 		display_pipe_configuration(v);
-		calc_wm_sets_and_perf_params(context, v);
-		context->bw.dcn.calc_clk.fclk_khz = (int)(bw_consumed * 1000000 /
+		/*calc_wm_sets_and_perf_params(context, v);*/
+		/* Only 1 set is used by dcn since no noticeable
+		 * performance improvement was measured and due to hw bug DEGVIDCN10-254
+		 */
+		dispclkdppclkdcfclk_deep_sleep_prefetch_parameters_watermarks_and_performance_calculation(v);
+
+		context->bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns =
+			v->stutter_exit_watermark * 1000;
+		context->bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns =
+				v->stutter_enter_plus_exit_watermark * 1000;
+		context->bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns =
+				v->dram_clock_change_watermark * 1000;
+		context->bw.dcn.watermarks.a.pte_meta_urgent_ns = v->ptemeta_urgent_watermark * 1000;
+		context->bw.dcn.watermarks.a.urgent_ns = v->urgent_watermark * 1000;
+		context->bw.dcn.watermarks.b = context->bw.dcn.watermarks.a;
+		context->bw.dcn.watermarks.c = context->bw.dcn.watermarks.a;
+		context->bw.dcn.watermarks.d = context->bw.dcn.watermarks.a;
+
+		context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 /
 				(ddr4_dram_factor_single_Channel * v->number_of_channels));
 		if (bw_consumed == v->fabric_and_dram_bandwidth_vmin0p65) {
-			context->bw.dcn.calc_clk.fclk_khz = (int)(bw_consumed * 1000000 / 32);
+			context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 / 32);
 		}
 
-		context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz = (int)(v->dcf_clk_deep_sleep * 1000);
-		context->bw.dcn.calc_clk.dcfclk_khz = (int)(v->dcfclk * 1000);
+		context->bw.dcn.clk.dcfclk_deep_sleep_khz = (int)(v->dcf_clk_deep_sleep * 1000);
+		context->bw.dcn.clk.dcfclk_khz = (int)(v->dcfclk * 1000);
 
-		context->bw.dcn.calc_clk.dispclk_khz = (int)(v->dispclk * 1000);
+		context->bw.dcn.clk.dispclk_khz = (int)(v->dispclk * 1000);
 		if (dc->debug.max_disp_clk == true)
-			context->bw.dcn.calc_clk.dispclk_khz = (int)(dc->dcn_soc->max_dispclk_vmax0p9 * 1000);
+			context->bw.dcn.clk.dispclk_khz = (int)(dc->dcn_soc->max_dispclk_vmax0p9 * 1000);
 
-		if (context->bw.dcn.calc_clk.dispclk_khz <
+		if (context->bw.dcn.clk.dispclk_khz <
 				dc->debug.min_disp_clk_khz) {
-			context->bw.dcn.calc_clk.dispclk_khz =
+			context->bw.dcn.clk.dispclk_khz =
 					dc->debug.min_disp_clk_khz;
 		}
 
-		context->bw.dcn.calc_clk.dppclk_khz = context->bw.dcn.calc_clk.dispclk_khz / v->dispclk_dppclk_ratio;
-
+		context->bw.dcn.clk.dppclk_khz = context->bw.dcn.clk.dispclk_khz / v->dispclk_dppclk_ratio;
+		context->bw.dcn.clk.phyclk_khz = v->phyclk_per_state[v->voltage_level];
 		switch (v->voltage_level) {
 		case 0:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmin0p65 * 1000);
 			break;
 		case 1:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmid0p72 * 1000);
 			break;
 		case 2:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vnom0p8 * 1000);
 			break;
 		default:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmax0p9 * 1000);
 			break;
 		}
@@ -1225,27 +1286,27 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 
 unsigned int dcn_find_dcfclk_suits_all(
 	const struct dc *dc,
-	struct clocks_value *clocks)
+	struct dc_clocks *clocks)
 {
 	unsigned vdd_level, vdd_level_temp;
 	unsigned dcf_clk;
 
 	/*find a common supported voltage level*/
 	vdd_level = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DISPLAY_CLK, clocks->dispclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DISPLAY_CLK, clocks->dispclk_khz);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DISPLAYPHYCLK, clocks->phyclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DISPLAYPHYCLK, clocks->phyclk_khz);
 
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DPPCLK, clocks->dppclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DPPCLK, clocks->dppclk_khz);
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_MEMORY_CLK, clocks->dcfclock_in_khz);
+		dc, DM_PP_CLOCK_TYPE_MEMORY_CLK, clocks->fclk_khz);
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DCFCLK, clocks->dcfclock_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DCFCLK, clocks->dcfclk_khz);
 
 	/*find that level conresponding dcfclk*/
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
@@ -1331,21 +1392,14 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 {
 	struct pp_smu_funcs_rv *pp = dc->res_pool->pp_smu;
 	struct pp_smu_wm_range_sets ranges = {0};
-	int max_fclk_khz, nom_fclk_khz, mid_fclk_khz, min_fclk_khz;
-	int max_dcfclk_khz, min_dcfclk_khz;
-	int socclk_khz;
+	int min_fclk_khz, min_dcfclk_khz, socclk_khz;
 	const int overdrive = 5000000; /* 5 GHz to cover Overdrive */
-	unsigned factor = (ddr4_dram_factor_single_Channel * dc->dcn_soc->number_of_channels);
 
 	if (!pp->set_wm_ranges)
 		return;
 
 	kernel_fpu_begin();
-	max_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 * 1000000 / factor;
-	nom_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 * 1000000 / factor;
-	mid_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 * 1000000 / factor;
 	min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32;
-	max_dcfclk_khz = dc->dcn_soc->dcfclkv_max0p9 * 1000;
 	min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000;
 	socclk_khz = dc->dcn_soc->socclk * 1000;
 	kernel_fpu_end();
@@ -1353,105 +1407,46 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	/* 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
 	 * Memory clock member variables for Watermarks calculations for each
-	 * Watermark Set
+	 * Watermark Set. Only one watermark set for dcn1 due to hw bug DEGVIDCN10-254.
 	 */
 	/* SOCCLK does not affect anytihng but writeback for DCN so for now we dont
 	 * care what the value is, hence min to overdrive level
 	 */
-	ranges.num_reader_wm_sets = WM_COUNT;
-	ranges.num_writer_wm_sets = WM_COUNT;
+	ranges.num_reader_wm_sets = WM_SET_COUNT;
+	ranges.num_writer_wm_sets = WM_SET_COUNT;
 	ranges.reader_wm_sets[0].wm_inst = WM_A;
 	ranges.reader_wm_sets[0].min_drain_clk_khz = min_dcfclk_khz;
-	ranges.reader_wm_sets[0].max_drain_clk_khz = max_dcfclk_khz;
+	ranges.reader_wm_sets[0].max_drain_clk_khz = overdrive;
 	ranges.reader_wm_sets[0].min_fill_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[0].max_fill_clk_khz = min_fclk_khz;
+	ranges.reader_wm_sets[0].max_fill_clk_khz = overdrive;
 	ranges.writer_wm_sets[0].wm_inst = WM_A;
 	ranges.writer_wm_sets[0].min_fill_clk_khz = socclk_khz;
 	ranges.writer_wm_sets[0].max_fill_clk_khz = overdrive;
 	ranges.writer_wm_sets[0].min_drain_clk_khz = min_fclk_khz;
-	ranges.writer_wm_sets[0].max_drain_clk_khz = min_fclk_khz;
-
-	ranges.reader_wm_sets[1].wm_inst = WM_B;
-	ranges.reader_wm_sets[1].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[1].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[1].min_fill_clk_khz = mid_fclk_khz;
-	ranges.reader_wm_sets[1].max_fill_clk_khz = mid_fclk_khz;
-	ranges.writer_wm_sets[1].wm_inst = WM_B;
-	ranges.writer_wm_sets[1].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[1].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[1].min_drain_clk_khz = mid_fclk_khz;
-	ranges.writer_wm_sets[1].max_drain_clk_khz = mid_fclk_khz;
-
-
-	ranges.reader_wm_sets[2].wm_inst = WM_C;
-	ranges.reader_wm_sets[2].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[2].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[2].min_fill_clk_khz = nom_fclk_khz;
-	ranges.reader_wm_sets[2].max_fill_clk_khz = nom_fclk_khz;
-	ranges.writer_wm_sets[2].wm_inst = WM_C;
-	ranges.writer_wm_sets[2].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[2].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[2].min_drain_clk_khz = nom_fclk_khz;
-	ranges.writer_wm_sets[2].max_drain_clk_khz = nom_fclk_khz;
-
-	ranges.reader_wm_sets[3].wm_inst = WM_D;
-	ranges.reader_wm_sets[3].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[3].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[3].min_fill_clk_khz = max_fclk_khz;
-	ranges.reader_wm_sets[3].max_fill_clk_khz = max_fclk_khz;
-	ranges.writer_wm_sets[3].wm_inst = WM_D;
-	ranges.writer_wm_sets[3].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[3].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[3].min_drain_clk_khz = max_fclk_khz;
-	ranges.writer_wm_sets[3].max_drain_clk_khz = max_fclk_khz;
+	ranges.writer_wm_sets[0].max_drain_clk_khz = overdrive;
 
 	if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) {
 		ranges.reader_wm_sets[0].wm_inst = WM_A;
 		ranges.reader_wm_sets[0].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[0].max_drain_clk_khz = 654000;
+		ranges.reader_wm_sets[0].max_drain_clk_khz = 5000000;
 		ranges.reader_wm_sets[0].min_fill_clk_khz = 800000;
-		ranges.reader_wm_sets[0].max_fill_clk_khz = 800000;
+		ranges.reader_wm_sets[0].max_fill_clk_khz = 5000000;
 		ranges.writer_wm_sets[0].wm_inst = WM_A;
 		ranges.writer_wm_sets[0].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[0].max_fill_clk_khz = 757000;
+		ranges.writer_wm_sets[0].max_fill_clk_khz = 5000000;
 		ranges.writer_wm_sets[0].min_drain_clk_khz = 800000;
-		ranges.writer_wm_sets[0].max_drain_clk_khz = 800000;
-
-		ranges.reader_wm_sets[1].wm_inst = WM_B;
-		ranges.reader_wm_sets[1].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[1].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[1].min_fill_clk_khz = 933000;
-		ranges.reader_wm_sets[1].max_fill_clk_khz = 933000;
-		ranges.writer_wm_sets[1].wm_inst = WM_B;
-		ranges.writer_wm_sets[1].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[1].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[1].min_drain_clk_khz = 933000;
-		ranges.writer_wm_sets[1].max_drain_clk_khz = 933000;
-
-
-		ranges.reader_wm_sets[2].wm_inst = WM_C;
-		ranges.reader_wm_sets[2].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[2].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[2].min_fill_clk_khz = 1067000;
-		ranges.reader_wm_sets[2].max_fill_clk_khz = 1067000;
-		ranges.writer_wm_sets[2].wm_inst = WM_C;
-		ranges.writer_wm_sets[2].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[2].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[2].min_drain_clk_khz = 1067000;
-		ranges.writer_wm_sets[2].max_drain_clk_khz = 1067000;
-
-		ranges.reader_wm_sets[3].wm_inst = WM_D;
-		ranges.reader_wm_sets[3].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[3].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[3].min_fill_clk_khz = 1200000;
-		ranges.reader_wm_sets[3].max_fill_clk_khz = 1200000;
-		ranges.writer_wm_sets[3].wm_inst = WM_D;
-		ranges.writer_wm_sets[3].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[3].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[3].min_drain_clk_khz = 1200000;
-		ranges.writer_wm_sets[3].max_drain_clk_khz = 1200000;
+		ranges.writer_wm_sets[0].max_drain_clk_khz = 5000000;
 	}
 
+	ranges.reader_wm_sets[1] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[1].wm_inst = WM_B;
+
+	ranges.reader_wm_sets[2] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[2].wm_inst = WM_C;
+
+	ranges.reader_wm_sets[3] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[3].wm_inst = WM_D;
+
 	/* Notify PP Lib/SMU which Watermarks to use for which clock ranges */
 	pp->set_wm_ranges(&pp->pp_smu, &ranges);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 53ce7fa864b4..733ac224e7fd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -384,6 +384,71 @@ void dc_stream_set_static_screen_events(struct dc *dc,
 	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events);
 }
 
+void dc_link_set_drive_settings(struct dc *dc,
+				struct link_training_settings *lt_settings,
+				const struct dc_link *link)
+{
+
+	int i;
+
+	for (i = 0; i < dc->link_count; i++) {
+		if (dc->links[i] == link)
+			break;
+	}
+
+	if (i >= dc->link_count)
+		ASSERT_CRITICAL(false);
+
+	dc_link_dp_set_drive_settings(dc->links[i], lt_settings);
+}
+
+void dc_link_perform_link_training(struct dc *dc,
+				   struct dc_link_settings *link_setting,
+				   bool skip_video_pattern)
+{
+	int i;
+
+	for (i = 0; i < dc->link_count; i++)
+		dc_link_dp_perform_link_training(
+			dc->links[i],
+			link_setting,
+			skip_video_pattern);
+}
+
+void dc_link_set_preferred_link_settings(struct dc *dc,
+					 struct dc_link_settings *link_setting,
+					 struct dc_link *link)
+{
+	link->preferred_link_setting = *link_setting;
+	dp_retrain_link_dp_test(link, link_setting, false);
+}
+
+void dc_link_enable_hpd(const struct dc_link *link)
+{
+	dc_link_dp_enable_hpd(link);
+}
+
+void dc_link_disable_hpd(const struct dc_link *link)
+{
+	dc_link_dp_disable_hpd(link);
+}
+
+
+void dc_link_set_test_pattern(struct dc_link *link,
+			      enum dp_test_pattern test_pattern,
+			      const struct link_training_settings *p_link_settings,
+			      const unsigned char *p_custom_pattern,
+			      unsigned int cust_pattern_size)
+{
+	if (link != NULL)
+		dc_link_dp_set_test_pattern(
+			link,
+			test_pattern,
+			p_link_settings,
+			p_custom_pattern,
+			cust_pattern_size);
+}
+
 static void destruct(struct dc *dc)
 {
 	dc_release_state(dc->current_state);
@@ -402,9 +467,6 @@ static void destruct(struct dc *dc)
 	if (dc->ctx->created_bios)
 		dal_bios_parser_destroy(&dc->ctx->dc_bios);
 
-	if (dc->ctx->logger)
-		dal_logger_destroy(&dc->ctx->logger);
-
 	kfree(dc->ctx);
 	dc->ctx = NULL;
 
@@ -414,7 +476,7 @@ static void destruct(struct dc *dc)
 	kfree(dc->bw_dceip);
 	dc->bw_dceip = NULL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	kfree(dc->dcn_soc);
 	dc->dcn_soc = NULL;
 
@@ -427,11 +489,10 @@ static void destruct(struct dc *dc)
 static bool construct(struct dc *dc,
 		const struct dc_init_data *init_params)
 {
-	struct dal_logger *logger;
 	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_X86
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 #endif
@@ -453,7 +514,7 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->bw_vbios = dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	dcn_soc = kzalloc(sizeof(*dcn_soc), GFP_KERNEL);
 	if (!dcn_soc) {
 		dm_error("%s: failed to create dcn_soc\n", __func__);
@@ -492,14 +553,7 @@ static bool construct(struct dc *dc,
 	}
 
 	/* Create logger */
-	logger = dal_logger_create(dc_ctx, init_params->log_mask);
 
-	if (!logger) {
-		/* can *not* call logger. call base driver 'print error' */
-		dm_error("%s: failed to create Logger!\n", __func__);
-		goto fail;
-	}
-	dc_ctx->logger = logger;
 	dc_ctx->dce_environment = init_params->dce_environment;
 
 	dc_version = resource_parse_asic_id(init_params->asic_id);
@@ -918,9 +972,7 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	for (i = 0; i < context->stream_count; i++) {
 		struct dc_stream_state *stream = context->streams[i];
 
-		dc_stream_log(stream,
-				dc->ctx->logger,
-				LOG_DC);
+		dc_stream_log(dc, stream);
 	}
 
 	result = dc_commit_state_no_check(dc, context);
@@ -944,12 +996,7 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 
 	dc->optimized_required = false;
 
-	/* 3rd param should be true, temp w/a for RV*/
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	dc->hwss.set_bandwidth(dc, context, dc->ctx->dce_version < DCN_VERSION_1_0);
-#else
 	dc->hwss.set_bandwidth(dc, context, true);
-#endif
 	return true;
 }
 
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 267c76766dea..caece7c13bc6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -348,23 +348,23 @@ void context_clock_trace(
 		struct dc *dc,
 		struct dc_state *context)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	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",
-			context->bw.dcn.calc_clk.dispclk_khz,
-			context->bw.dcn.calc_clk.dppclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz,
-			context->bw.dcn.calc_clk.socclk_khz);
+			context->bw.dcn.clk.dispclk_khz,
+			context->bw.dcn.clk.dppclk_khz,
+			context->bw.dcn.clk.dcfclk_khz,
+			context->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			context->bw.dcn.clk.fclk_khz,
+			context->bw.dcn.clk.socclk_khz);
 	CLOCK_TRACE("Calculated: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
-			context->bw.dcn.calc_clk.dispclk_khz,
-			context->bw.dcn.calc_clk.dppclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz,
-			context->bw.dcn.calc_clk.socclk_khz);
+			context->bw.dcn.clk.dispclk_khz,
+			context->bw.dcn.clk.dppclk_khz,
+			context->bw.dcn.clk.dcfclk_khz,
+			context->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			context->bw.dcn.clk.fclk_khz,
+			context->bw.dcn.clk.socclk_khz);
 #endif
 }
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 08b7ee526f0f..388a0635c38d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -33,6 +33,7 @@
 #include "dc_link_dp.h"
 #include "dc_link_ddc.h"
 #include "link_hwss.h"
+#include "opp.h"
 
 #include "link_encoder.h"
 #include "hw_sequencer.h"
@@ -312,7 +313,7 @@ static enum signal_type get_basic_signal_type(
  * @brief
  * Check whether there is a dongle on DP connector
  */
-static bool is_dp_sink_present(struct dc_link *link)
+bool dc_link_is_dp_sink_present(struct dc_link *link)
 {
 	enum gpio_result gpio_result;
 	uint32_t clock_pin = 0;
@@ -405,7 +406,7 @@ static enum signal_type link_detect_sink(
 			 * we assume signal is DVI; it could be corrected
 			 * to HDMI after dongle detection
 			 */
-			if (!is_dp_sink_present(link))
+			if (!dm_helpers_is_dp_sink_present(link))
 				result = SIGNAL_TYPE_DVI_SINGLE_LINK;
 		}
 	}
@@ -497,6 +498,10 @@ static bool detect_dp(
 			sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
 			link->type = dc_connection_mst_branch;
 
+			dal_ddc_service_set_transaction_type(
+							link->ddc,
+							sink_caps->transaction_type);
+
 			/*
 			 * This call will initiate MST topology discovery. Which
 			 * will detect MST ports and add new DRM connector DRM
@@ -524,6 +529,10 @@ static bool detect_dp(
 			if (reason == DETECT_REASON_BOOT)
 				boot = true;
 
+			dm_helpers_dp_update_branch_info(
+				link->ctx,
+				link);
+
 			if (!dm_helpers_dp_mst_start_top_mgr(
 				link->ctx,
 				link, boot)) {
@@ -751,7 +760,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				 */
 
 				/* deal with non-mst cases */
-				dp_hbr_verify_link_cap(link, &link->reported_link_cap);
+				dp_verify_link_cap(link, &link->reported_link_cap);
 			}
 
 			/* HDMI-DVI Dongle */
@@ -1284,29 +1293,15 @@ static enum dc_status enable_link_dp(
 		max_link_rate = LINK_RATE_HIGH3;
 
 	if (link_settings.link_rate == max_link_rate) {
-		if (state->dis_clk->funcs->set_min_clocks_state) {
-			if (state->dis_clk->cur_min_clks_state < DM_PP_CLOCKS_STATE_NOMINAL)
-				state->dis_clk->funcs->set_min_clocks_state(
-					state->dis_clk, DM_PP_CLOCKS_STATE_NOMINAL);
-		} else {
-			uint32_t dp_phyclk_in_khz;
-			const struct clocks_value clocks_value =
-					state->dis_clk->cur_clocks_value;
-
-			/* 27mhz = 27000000hz= 27000khz */
-			dp_phyclk_in_khz = link_settings.link_rate * 27000;
-
-			if (((clocks_value.max_non_dp_phyclk_in_khz != 0) &&
-				(dp_phyclk_in_khz > clocks_value.max_non_dp_phyclk_in_khz)) ||
-				(dp_phyclk_in_khz > clocks_value.max_dp_phyclk_in_khz)) {
-				state->dis_clk->funcs->apply_clock_voltage_request(
-						state->dis_clk,
-						DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-						dp_phyclk_in_khz,
-						false,
-						true);
-			}
-		}
+		struct dc_clocks clocks = state->bw.dcn.clk;
+
+		/* dce/dcn compat, do not update dispclk */
+		clocks.dispclk_khz = 0;
+		/* 27mhz = 27000000hz= 27000khz */
+		clocks.phyclk_khz = link_settings.link_rate * 27000;
+
+		state->dis_clk->funcs->update_clocks(
+				state->dis_clk, &clocks, false);
 	}
 
 	dp_enable_link_phy(
@@ -2396,9 +2391,10 @@ void core_link_enable_stream(
 	core_dc->hwss.enable_audio_stream(pipe_ctx);
 
 	/* turn off otg test pattern if enable */
-	pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
-			CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
-			COLOR_DEPTH_UNDEFINED);
+	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_DP_TEST_PATTERN_VIDEOMODE,
+				COLOR_DEPTH_UNDEFINED);
 
 	core_dc->hwss.enable_stream(pipe_ctx);
 
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 ae48d603ebd6..4019fe07d291 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
@@ -33,6 +33,8 @@
 #include "include/vector.h"
 #include "core_types.h"
 #include "dc_link_ddc.h"
+#include "engine.h"
+#include "aux_engine.h"
 
 #define AUX_POWER_UP_WA_DELAY 500
 #define I2C_OVER_AUX_DEFER_WA_DELAY 70
@@ -629,83 +631,62 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
-	struct ddc_service *ddc,
-	bool i2c,
-	enum i2c_mot_mode mot,
-	uint32_t address,
-	uint8_t *data,
-	uint32_t len,
-	uint32_t *read)
+int dc_link_aux_transfer(struct ddc_service *ddc,
+			     unsigned int address,
+			     uint8_t *reply,
+			     void *buffer,
+			     unsigned int size,
+			     enum aux_transaction_type type,
+			     enum i2caux_transaction_action action)
 {
-	struct aux_payload read_payload = {
-		.i2c_over_aux = i2c,
-		.write = false,
-		.address = address,
-		.length = len,
-		.data = data,
-	};
-	struct aux_command command = {
-		.payloads = &read_payload,
-		.number_of_payloads = 1,
-		.defer_delay = 0,
-		.max_defer_write_retry = 0,
-		.mot = mot
-	};
-
-	*read = 0;
-
-	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
-		BREAK_TO_DEBUGGER();
-		return DDC_RESULT_FAILED_INVALID_OPERATION;
-	}
-
-	if (dal_i2caux_submit_aux_command(
-		ddc->ctx->i2caux,
-		ddc->ddc_pin,
-		&command)) {
-		*read = command.payloads->length;
-		return DDC_RESULT_SUCESSFULL;
-	}
-
-	return DDC_RESULT_FAILED_OPERATION;
-}
+	struct ddc *ddc_pin = ddc->ddc_pin;
+	struct engine *engine;
+	struct aux_engine *aux_engine;
+	enum aux_channel_operation_result operation_result;
+	struct aux_request_transaction_data aux_req;
+	struct aux_reply_transaction_data aux_rep;
+	uint8_t returned_bytes = 0;
+	int res = -1;
+	uint32_t status;
+
+	memset(&aux_req, 0, sizeof(aux_req));
+	memset(&aux_rep, 0, sizeof(aux_rep));
+
+	engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
+	aux_engine = engine->funcs->acquire(engine, ddc_pin);
+
+	aux_req.type = type;
+	aux_req.action = action;
+
+	aux_req.address = address;
+	aux_req.delay = 0;
+	aux_req.length = size;
+	aux_req.data = buffer;
+
+	aux_engine->funcs->submit_channel_request(aux_engine, &aux_req);
+	operation_result = aux_engine->funcs->get_channel_status(aux_engine, &returned_bytes);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		res = returned_bytes;
+
+		if (res <= size && res >= 0)
+			res = aux_engine->funcs->read_channel_reply(aux_engine, size,
+								buffer, reply,
+								&status);
 
-enum ddc_result dal_ddc_service_write_dpcd_data(
-	struct ddc_service *ddc,
-	bool i2c,
-	enum i2c_mot_mode mot,
-	uint32_t address,
-	const uint8_t *data,
-	uint32_t len)
-{
-	struct aux_payload write_payload = {
-		.i2c_over_aux = i2c,
-		.write = true,
-		.address = address,
-		.length = len,
-		.data = (uint8_t *)data,
-	};
-	struct aux_command command = {
-		.payloads = &write_payload,
-		.number_of_payloads = 1,
-		.defer_delay = 0,
-		.max_defer_write_retry = 0,
-		.mot = mot
-	};
-
-	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
-		BREAK_TO_DEBUGGER();
-		return DDC_RESULT_FAILED_INVALID_OPERATION;
+		break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		res = 0;
+		break;
+	case AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN:
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		res = -1;
+		break;
 	}
-
-	if (dal_i2caux_submit_aux_command(
-		ddc->ctx->i2caux,
-		ddc->ddc_pin,
-		&command))
-		return DDC_RESULT_SUCESSFULL;
-
-	return DDC_RESULT_FAILED_OPERATION;
+	aux_engine->base.funcs->release_engine(&aux_engine->base);
+	return res;
 }
 
 /*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 509f265663d2..af9386ee5a93 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
@@ -3,6 +3,7 @@
 #include "dc.h"
 #include "dc_link_dp.h"
 #include "dm_helpers.h"
+#include "opp.h"
 
 #include "inc/core_types.h"
 #include "link_hwss.h"
@@ -38,7 +39,7 @@ static bool decide_fallback_link_setting(
 		struct dc_link_settings initial_link_settings,
 		struct dc_link_settings *current_link_setting,
 		enum link_training_result training_result);
-static struct dc_link_settings get_common_supported_link_settings (
+static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b);
 
@@ -93,8 +94,8 @@ static void dpcd_set_link_settings(
 	uint8_t rate = (uint8_t)
 	(lt_settings->link_settings.link_rate);
 
-	union down_spread_ctrl downspread = {{0}};
-	union lane_count_set lane_count_set = {{0}};
+	union down_spread_ctrl downspread = { {0} };
+	union lane_count_set lane_count_set = { {0} };
 	uint8_t link_set_buffer[2];
 
 	downspread.raw = (uint8_t)
@@ -164,11 +165,11 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 	const struct link_training_settings *lt_settings,
 	enum hw_dp_training_pattern pattern)
 {
-	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = {{{0}}};
+	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = { { {0} } };
 	const uint32_t dpcd_base_lt_offset =
 	DP_TRAINING_PATTERN_SET;
 	uint8_t dpcd_lt_buffer[5] = {0};
-	union dpcd_training_pattern dpcd_pattern = {{0}};
+	union dpcd_training_pattern dpcd_pattern = { {0} };
 	uint32_t lane;
 	uint32_t size_in_bytes;
 	bool edp_workaround = false; /* TODO link_prop.INTERNAL */
@@ -232,7 +233,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 			link,
 			DP_TRAINING_PATTERN_SET,
 			&dpcd_pattern.raw,
-			sizeof(dpcd_pattern.raw) );
+			sizeof(dpcd_pattern.raw));
 
 		core_link_write_dpcd(
 			link,
@@ -246,7 +247,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 				link,
 				dpcd_base_lt_offset,
 				dpcd_lt_buffer,
-				size_in_bytes + sizeof(dpcd_pattern.raw) );
+				size_in_bytes + sizeof(dpcd_pattern.raw));
 
 	link->cur_lane_setting = lt_settings->lane_settings[0];
 }
@@ -428,8 +429,8 @@ static void get_lane_status_and_drive_settings(
 	struct link_training_settings *req_settings)
 {
 	uint8_t dpcd_buf[6] = {0};
-	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = {{{0}}};
-	struct link_training_settings request_settings = {{0}};
+	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } };
+	struct link_training_settings request_settings = { {0} };
 	uint32_t lane;
 
 	memset(req_settings, '\0', sizeof(struct link_training_settings));
@@ -651,7 +652,7 @@ static bool perform_post_lt_adj_req_sequence(
 
 			if (req_drv_setting_changed) {
 				update_drive_settings(
-					lt_settings,req_settings);
+					lt_settings, req_settings);
 
 				dc_link_dp_set_drive_settings(link,
 						lt_settings);
@@ -724,8 +725,8 @@ static enum link_training_result perform_channel_equalization_sequence(
 	enum hw_dp_training_pattern hw_tr_pattern;
 	uint32_t retries_ch_eq;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
-	union lane_align_status_updated dpcd_lane_status_updated = {{0}};
-	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}};
+	union lane_align_status_updated dpcd_lane_status_updated = { {0} };
+	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } };
 
 	hw_tr_pattern = get_supported_tp(link);
 
@@ -1027,6 +1028,9 @@ enum link_training_result dc_link_dp_perform_link_training(
 			lt_settings.lane_settings[0].VOLTAGE_SWING,
 			lt_settings.lane_settings[0].PRE_EMPHASIS);
 
+	if (status != LINK_TRAINING_SUCCESS)
+		link->ctx->dc->debug_data.ltFailCount++;
+
 	return status;
 }
 
@@ -1082,7 +1086,7 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 	return max_link_cap;
 }
 
-bool dp_hbr_verify_link_cap(
+bool dp_verify_link_cap(
 	struct dc_link *link,
 	struct dc_link_settings *known_limit_link_setting)
 {
@@ -1097,6 +1101,11 @@ bool dp_hbr_verify_link_cap(
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
 	enum link_training_result status;
 
+	if (link->dc->debug.skip_detection_link_training) {
+		link->verified_link_cap = *known_limit_link_setting;
+		return true;
+	}
+
 	success = false;
 	skip_link_training = false;
 
@@ -1182,7 +1191,7 @@ bool dp_hbr_verify_link_cap(
 	return success;
 }
 
-static struct dc_link_settings get_common_supported_link_settings (
+static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b)
 {
@@ -1428,6 +1437,7 @@ static uint32_t bandwidth_in_kbps_from_link_settings(
 
 	uint32_t lane_count  = link_setting->lane_count;
 	uint32_t kbps = link_rate_in_kbps;
+
 	kbps *= lane_count;
 	kbps *= 8;   /* 8 bits per byte*/
 
@@ -1445,9 +1455,9 @@ bool dp_validate_mode_timing(
 	const struct dc_link_settings *link_setting;
 
 	/*always DP fail safe mode*/
-	if (timing->pix_clk_khz == (uint32_t)25175 &&
-		timing->h_addressable == (uint32_t)640 &&
-		timing->v_addressable == (uint32_t)480)
+	if (timing->pix_clk_khz == (uint32_t) 25175 &&
+		timing->h_addressable == (uint32_t) 640 &&
+		timing->v_addressable == (uint32_t) 480)
 		return true;
 
 	/* We always use verified link settings */
@@ -1771,12 +1781,10 @@ static void dp_test_send_link_training(struct dc_link *link)
 	dp_retrain_link_dp_test(link, &link_settings, false);
 }
 
-/* TODO hbr2 compliance eye output is unstable
+/* TODO Raven hbr2 compliance eye output is unstable
  * (toggling on and off) with debugger break
  * This caueses intermittent PHY automation failure
  * Need to look into the root cause */
-static uint8_t force_tps4_for_cp2520 = 1;
-
 static void dp_test_send_phy_test_pattern(struct dc_link *link)
 {
 	union phy_test_pattern dpcd_test_pattern;
@@ -1836,13 +1844,13 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link)
 		break;
 	case PHY_TEST_PATTERN_CP2520_1:
 		/* CP2520 pattern is unstable, temporarily use TPS4 instead */
-		test_pattern = (force_tps4_for_cp2520 == 1) ?
+		test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
 				DP_TEST_PATTERN_TRAINING_PATTERN4 :
 				DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
 		break;
 	case PHY_TEST_PATTERN_CP2520_2:
 		/* CP2520 pattern is unstable, temporarily use TPS4 instead */
-		test_pattern = (force_tps4_for_cp2520 == 1) ?
+		test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
 				DP_TEST_PATTERN_TRAINING_PATTERN4 :
 				DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
 		break;
@@ -1995,12 +2003,16 @@ static void handle_automated_test(struct dc_link *link)
 			sizeof(test_response));
 }
 
-bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data)
+bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss)
 {
-	union hpd_irq_data hpd_irq_dpcd_data = {{{{0}}}};
+	union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } };
 	union device_service_irq device_service_clear = { { 0 } };
-	enum dc_status result = DDC_RESULT_UNKNOWN;
+	enum dc_status result;
+
 	bool status = false;
+
+	if (out_link_loss)
+		*out_link_loss = false;
 	/* For use cases related to down stream connection status change,
 	 * PSR and device auto test, refer to function handle_sst_hpd_irq
 	 * in DAL2.1*/
@@ -2075,6 +2087,8 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 			true, LINK_TRAINING_ATTEMPTS);
 
 		status = false;
+		if (out_link_loss)
+			*out_link_loss = true;
 	}
 
 	if (link->type == dc_connection_active_dongle &&
@@ -2261,6 +2275,11 @@ static void get_active_converter_info(
 
 		link->dpcd_caps.branch_hw_revision =
 			dp_hw_fw_revision.ieee_hw_rev;
+
+		memmove(
+			link->dpcd_caps.branch_fw_revision,
+			dp_hw_fw_revision.ieee_fw_rev,
+			sizeof(dp_hw_fw_revision.ieee_fw_rev));
 	}
 }
 
@@ -2316,6 +2335,7 @@ static bool retrieve_link_cap(struct dc_link *link)
 	enum dc_status status = DC_ERROR_UNEXPECTED;
 	uint32_t read_dpcd_retry_cnt = 3;
 	int i;
+	struct dp_sink_hw_fw_revision dp_hw_fw_revision;
 
 	memset(dpcd_data, '\0', sizeof(dpcd_data));
 	memset(&down_strm_port_count,
@@ -2407,6 +2427,25 @@ static bool retrieve_link_cap(struct dc_link *link)
 			(sink_id.ieee_oui[1] << 8) +
 			(sink_id.ieee_oui[2]);
 
+	memmove(
+		link->dpcd_caps.sink_dev_id_str,
+		sink_id.ieee_device_id,
+		sizeof(sink_id.ieee_device_id));
+
+	core_link_read_dpcd(
+		link,
+		DP_SINK_HW_REVISION_START,
+		(uint8_t *)&dp_hw_fw_revision,
+		sizeof(dp_hw_fw_revision));
+
+	link->dpcd_caps.sink_hw_revision =
+		dp_hw_fw_revision.ieee_hw_rev;
+
+	memmove(
+		link->dpcd_caps.sink_fw_revision,
+		dp_hw_fw_revision.ieee_fw_rev,
+		sizeof(dp_hw_fw_revision.ieee_fw_rev));
+
 	/* Connectivity log: detection */
 	CONN_DATA_DETECT(link, dpcd_data, sizeof(dpcd_data), "Rx Caps: ");
 
@@ -2511,8 +2550,8 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		pipe_ctx->stream->bit_depth_params = params;
 		pipe_ctx->stream_res.opp->funcs->
 			opp_program_bit_depth_reduction(pipe_ctx->stream_res.opp, &params);
-
-		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+		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);
 	}
 	break;
@@ -2524,8 +2563,8 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		pipe_ctx->stream->bit_depth_params = params;
 		pipe_ctx->stream_res.opp->funcs->
 			opp_program_bit_depth_reduction(pipe_ctx->stream_res.opp, &params);
-
-		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+		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_DP_TEST_PATTERN_VIDEOMODE,
 				color_depth);
 	}
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 fca22550417a..2e65715f76a1 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -41,7 +41,7 @@
 #include "dce100/dce100_resource.h"
 #include "dce110/dce110_resource.h"
 #include "dce112/dce112_resource.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/dcn10_resource.h"
 #endif
 #include "dce120/dce120_resource.h"
@@ -85,7 +85,7 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 	case FAMILY_AI:
 		dc_version = DCE_VERSION_12_0;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case FAMILY_RV:
 		dc_version = DCN_VERSION_1_0;
 		break;
@@ -136,7 +136,7 @@ struct resource_pool *dc_create_resource_pool(
 			num_virtual_links, dc);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		res_pool = dcn10_create_resource_pool(
 				num_virtual_links, dc);
@@ -1213,7 +1213,7 @@ static struct pipe_ctx *acquire_free_pipe_for_stream(
 
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static int acquire_first_split_pipe(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -1284,7 +1284,7 @@ bool dc_add_plane_to_context(
 
 	free_pipe = acquire_free_pipe_for_stream(context, pool, stream);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (!free_pipe) {
 		int pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 		if (pipe_idx >= 0)
@@ -1705,8 +1705,8 @@ enum dc_status dc_add_stream_to_ctx(
 	struct dc_context *dc_ctx = dc->ctx;
 	enum dc_status res;
 
-	if (new_ctx->stream_count >= dc->res_pool->pipe_count) {
-		DC_ERROR("Max streams reached, can add stream %p !\n", stream);
+	if (new_ctx->stream_count >= dc->res_pool->timing_generator_count) {
+		DC_ERROR("Max streams reached, can't add stream %p !\n", stream);
 		return DC_ERROR_UNEXPECTED;
 	}
 
@@ -1882,7 +1882,7 @@ 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_X86
 	if (pipe_idx < 0)
 		pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 #endif
@@ -1948,7 +1948,7 @@ void dc_resource_state_construct(
 		const struct dc *dc,
 		struct dc_state *dst_ctx)
 {
-	dst_ctx->dis_clk = dc->res_pool->display_clock;
+	dst_ctx->dis_clk = dc->res_pool->dccg;
 }
 
 enum dc_status dc_validate_global_state(
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 3732a1de9d6c..fdcc8ab19bf3 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -30,6 +30,8 @@
 #include "ipp.h"
 #include "timing_generator.h"
 
+#define DC_LOGGER dc->ctx->logger
+
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
@@ -212,6 +214,8 @@ bool dc_stream_set_cursor_attributes(
 		}
 
 		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);
 	}
 
 	if (pipe_to_program)
@@ -317,16 +321,10 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 	return ret;
 }
 
-
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dm_logger,
-	enum dc_log_type log_type)
+void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream)
 {
-
-	dm_logger_write(dm_logger,
-			log_type,
-			"core_stream 0x%x: src: %d, %d, %d, %d; dst: %d, %d, %d, %d, colorSpace:%d\n",
+	DC_LOG_DC(
+			"core_stream 0x%p: src: %d, %d, %d, %d; dst: %d, %d, %d, %d, colorSpace:%d\n",
 			stream,
 			stream->src.x,
 			stream->src.y,
@@ -337,21 +335,18 @@ void dc_stream_log(
 			stream->dst.width,
 			stream->dst.height,
 			stream->output_color_space);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tpix_clk_khz: %d, h_total: %d, v_total: %d, pixelencoder:%d, displaycolorDepth:%d\n",
 			stream->timing.pix_clk_khz,
 			stream->timing.h_total,
 			stream->timing.v_total,
 			stream->timing.pixel_encoding,
 			stream->timing.display_color_depth);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tsink name: %s, serial: %d\n",
 			stream->sink->edid_caps.display_name,
 			stream->sink->edid_caps.serial_number);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tlink: %d\n",
 			stream->sink->link->link_index);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 7ebce7669eea..b91f14989aef 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.47"
+#define DC_VER "3.1.58"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
@@ -77,6 +77,7 @@ struct dc_caps {
 	bool is_apu;
 	bool dual_link_dvi;
 	bool post_blend_color_processing;
+	bool force_dp_tps4_for_cp2520;
 };
 
 struct dc_dcc_surface_param {
@@ -169,6 +170,12 @@ struct dc_config {
 	bool disable_disp_pll_sharing;
 };
 
+enum visual_confirm {
+	VISUAL_CONFIRM_DISABLE = 0,
+	VISUAL_CONFIRM_SURFACE = 1,
+	VISUAL_CONFIRM_HDR = 2,
+};
+
 enum dcc_option {
 	DCC_ENABLE = 0,
 	DCC_DISABLE = 1,
@@ -186,6 +193,10 @@ enum wm_report_mode {
 	WM_REPORT_OVERRIDE = 1,
 };
 
+/*
+ * For any clocks that may differ per pipe
+ * only the max is stored in this structure
+ */
 struct dc_clocks {
 	int dispclk_khz;
 	int max_supported_dppclk_khz;
@@ -194,10 +205,11 @@ struct dc_clocks {
 	int socclk_khz;
 	int dcfclk_deep_sleep_khz;
 	int fclk_khz;
+	int phyclk_khz;
 };
 
-struct dc_debug {
-	bool surface_visual_confirm;
+struct dc_debug_options {
+	enum visual_confirm visual_confirm;
 	bool sanity_checks;
 	bool max_disp_clk;
 	bool surface_trace;
@@ -228,6 +240,7 @@ struct dc_debug {
 	int urgent_latency_ns;
 	int percent_of_ideal_drambw;
 	int dram_clock_change_latency_ns;
+	bool optimized_watermark;
 	int always_scale;
 	bool disable_pplib_clock_request;
 	bool disable_clock_gate;
@@ -243,8 +256,19 @@ struct dc_debug {
 	bool always_use_regamma;
 	bool p010_mpo_support;
 	bool recovery_enabled;
+	bool avoid_vbios_exec_table;
+	bool scl_reset_length10;
+	bool hdmi20_disable;
+	bool skip_detection_link_training;
+};
 
+struct dc_debug_data {
+	uint32_t ltFailCount;
+	uint32_t i2cErrorCount;
+	uint32_t auxErrorCount;
 };
+
+
 struct dc_state;
 struct resource_pool;
 struct dce_hwseq;
@@ -253,8 +277,7 @@ struct dc {
 	struct dc_caps caps;
 	struct dc_cap_funcs cap_funcs;
 	struct dc_config config;
-	struct dc_debug debug;
-
+	struct dc_debug_options debug;
 	struct dc_context *ctx;
 
 	uint8_t link_count;
@@ -269,7 +292,7 @@ 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_X86
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 	struct display_mode_lib dml;
@@ -290,6 +313,8 @@ struct dc {
 
 	/* FBC compressor */
 	struct compressor *fbc_compressor;
+
+	struct dc_debug_data debug_data;
 };
 
 enum frame_buffer_mode {
@@ -378,7 +403,8 @@ enum dc_transfer_func_predefined {
 	TRANSFER_FUNCTION_LINEAR,
 	TRANSFER_FUNCTION_UNITY,
 	TRANSFER_FUNCTION_HLG,
-	TRANSFER_FUNCTION_HLG12
+	TRANSFER_FUNCTION_HLG12,
+	TRANSFER_FUNCTION_GAMMA22
 };
 
 struct dc_transfer_func {
@@ -621,9 +647,14 @@ struct dpcd_caps {
 	struct dc_dongle_caps dongle_caps;
 
 	uint32_t sink_dev_id;
+	int8_t sink_dev_id_str[6];
+	int8_t sink_hw_revision;
+	int8_t sink_fw_revision[2];
+
 	uint32_t branch_dev_id;
 	int8_t branch_dev_name[6];
 	int8_t branch_hw_revision;
+	int8_t branch_fw_revision[2];
 
 	bool allow_invalid_MSA_timing_param;
 	bool panel_mode_edp;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
index d9b84ec7954c..90082bab71f0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
@@ -198,6 +198,10 @@ struct dc_vbios_funcs {
 	void (*post_init)(struct dc_bios *bios);
 
 	void (*bios_parser_destroy)(struct dc_bios **dcb);
+
+	enum bp_result (*get_board_layout_info)(
+		struct dc_bios *dcb,
+		struct board_layout_info *board_layout_info);
 };
 
 struct bios_registers {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index bd0fda0ceb91..e68077e65565 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -255,3 +255,54 @@ uint32_t generic_reg_wait(const struct dc_context *ctx,
 
 	return reg_val;
 }
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data)
+{
+	dm_write_reg(ctx, addr_index, index);
+	dm_write_reg(ctx, addr_data, data);
+}
+
+uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index)
+{
+	uint32_t value = 0;
+
+	dm_write_reg(ctx, addr_index, index);
+	value = dm_read_reg(ctx, addr_data);
+
+	return value;
+}
+
+
+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,
+		...)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	reg_val = set_reg_field_value_ex(reg_val, 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);
+
+		reg_val = set_reg_field_value_ex(reg_val, field_value, mask, shift);
+		i++;
+	}
+
+	generic_write_indirect_reg(ctx, addr_index, addr_data, index, reg_val);
+	va_end(ap);
+
+	return reg_val;
+}
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 d31023d57b58..1d1f2d5ece51 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -192,13 +192,14 @@ enum surface_pixel_format {
 	/*swaped & float*/
 	SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F,
 	/*grow graphics here if necessary */
-
+	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr =
 		SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb,
+		SURFACE_PIXEL_FORMAT_SUBSAMPLE_END,
 	SURFACE_PIXEL_FORMAT_INVALID
 
 	/*grow 444 video here if necessary */
@@ -403,9 +404,11 @@ struct dc_cursor_position {
 struct dc_cursor_mi_param {
 	unsigned int pixel_clk_khz;
 	unsigned int ref_clk_khz;
-	unsigned int viewport_x_start;
-	unsigned int viewport_width;
+	struct rect viewport;
 	struct fixed31_32 h_scale_ratio;
+	struct fixed31_32 v_scale_ratio;
+	enum dc_rotation_angle rotation;
+	bool mirror;
 };
 
 /* IPP related types */
@@ -489,6 +492,7 @@ struct dc_cursor_attributes {
 	uint32_t height;
 
 	enum dc_cursor_color_format color_format;
+	uint32_t sdr_white_level; // for boosting (SDR) cursor in HDR mode
 
 	/* In case we support HW Cursor rotation in the future */
 	enum dc_rotation_angle rotation_angle;
@@ -496,6 +500,11 @@ struct dc_cursor_attributes {
 	union dc_cursor_attribute_flags attribute_flags;
 };
 
+struct dpp_cursor_attributes {
+	int bias;
+	int scale;
+};
+
 /* OPP */
 
 enum dc_color_space {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 8a716baa1203..070a56926308 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -172,7 +172,7 @@ bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
  * false - no change in Downstream port status. No further action required
  * from DM. */
 bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
-		union hpd_irq_data *hpd_irq_dpcd_data);
+		union hpd_irq_data *hpd_irq_dpcd_data, bool *out_link_loss);
 
 struct dc_sink_init_data;
 
@@ -210,10 +210,29 @@ bool dc_link_dp_set_test_pattern(
 
 void dc_link_enable_hpd_filter(struct dc_link *link, bool enable);
 
+bool dc_link_is_dp_sink_present(struct dc_link *link);
+
 /*
  * DPCD access interfaces
  */
 
+void dc_link_set_drive_settings(struct dc *dc,
+				struct link_training_settings *lt_settings,
+				const struct dc_link *link);
+void dc_link_perform_link_training(struct dc *dc,
+				   struct dc_link_settings *link_setting,
+				   bool skip_video_pattern);
+void dc_link_set_preferred_link_settings(struct dc *dc,
+					 struct dc_link_settings *link_setting,
+					 struct dc_link *link);
+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,
+			const struct link_training_settings *p_link_settings,
+			const unsigned char *p_custom_pattern,
+			unsigned int cust_pattern_size);
+
 bool dc_submit_i2c(
 		struct dc *dc,
 		uint32_t link_index,
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index af503e0286a7..cbfe418006cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -100,6 +100,7 @@ struct dc_stream_state {
 
 	struct dc_cursor_attributes cursor_attributes;
 	struct dc_cursor_position cursor_position;
+	uint32_t sdr_white_level; // for boosting (SDR) cursor in HDR mode
 
 	/* from stream struct */
 	struct kref refcount;
@@ -147,10 +148,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 /*
  * Log the current stream state.
  */
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dc_logger,
-	enum dc_log_type log_type);
+void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream);
 
 uint8_t dc_get_current_stream_count(struct dc *dc);
 struct dc_stream_state *dc_get_stream_at_index(struct dc *dc, uint8_t i);
@@ -258,6 +256,7 @@ bool dc_stream_set_cursor_position(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_position *position);
 
+
 bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 				struct dc_stream_state **stream,
 				int num_streams,
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index c96e526d07bb..8c6eb78b0c3b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -77,8 +77,6 @@ struct dc_context {
 	struct dc *dc;
 
 	void *driver_context; /* e.g. amdgpu_device */
-
-	struct dal_logger *logger;
 	void *cgs_device;
 
 	enum dce_environment dce_environment;
@@ -194,6 +192,7 @@ union display_content_support {
 
 struct dc_panel_patch {
 	unsigned int dppowerup_delay;
+	unsigned int extra_t12_ms;
 };
 
 struct dc_edid_caps {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/Makefile b/drivers/gpu/drm/amd/display/dc/dce/Makefile
index 11401fd8e535..825537bd4545 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce/Makefile
@@ -28,7 +28,7 @@
 
 DCE = dce_audio.o dce_stream_encoder.o dce_link_encoder.o dce_hwseq.o \
 dce_mem_input.o dce_clock_source.o dce_scl_filters.o dce_transform.o \
-dce_clocks.o dce_opp.o dce_dmcu.o dce_abm.o dce_ipp.o
+dce_clocks.o dce_opp.o dce_dmcu.o dce_abm.o dce_ipp.o dce_aux.o
 
 
 AMD_DAL_DCE = $(addprefix $(AMDDALPATH)/dc/dce/,$(DCE))
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
new file mode 100644
index 000000000000..b28e2120767e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -0,0 +1,942 @@
+/*
+ * 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 "dm_services.h"
+#include "dce_aux.h"
+#include "dce/dce_11_0_sh_mask.h"
+
+#define CTX \
+	aux110->base.base.ctx
+#define REG(reg_name)\
+	(aux110->regs->reg_name)
+
+#define DC_LOGGER \
+	engine->base.ctx->logger
+
+#include "reg_helper.h"
+
+#define FROM_AUX_ENGINE(ptr) \
+	container_of((ptr), struct aux_engine_dce110, base)
+
+#define FROM_ENGINE(ptr) \
+	FROM_AUX_ENGINE(container_of((ptr), struct aux_engine, base))
+
+#define FROM_AUX_ENGINE_ENGINE(ptr) \
+	container_of((ptr), struct aux_engine, base)
+enum {
+	AUX_INVALID_REPLY_RETRY_COUNTER = 1,
+	AUX_TIMED_OUT_RETRY_COUNTER = 2,
+	AUX_DEFER_RETRY_COUNTER = 6
+};
+static void release_engine(
+	struct engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_ENGINE(engine);
+
+	dal_ddc_close(engine->ddc);
+
+	engine->ddc = NULL;
+
+	REG_UPDATE(AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, 1);
+}
+
+#define SW_CAN_ACCESS_AUX 1
+#define DMCU_CAN_ACCESS_AUX 2
+
+static bool is_engine_available(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value = REG_READ(AUX_ARB_CONTROL);
+	uint32_t field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+
+	return (field != DMCU_CAN_ACCESS_AUX);
+}
+static bool acquire_engine(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value = REG_READ(AUX_ARB_CONTROL);
+	uint32_t field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+	if (field == DMCU_CAN_ACCESS_AUX)
+		return false;
+	/* enable AUX before request SW to access AUX */
+	value = REG_READ(AUX_CONTROL);
+	field = get_reg_field_value(value,
+				AUX_CONTROL,
+				AUX_EN);
+
+	if (field == 0) {
+		set_reg_field_value(
+				value,
+				1,
+				AUX_CONTROL,
+				AUX_EN);
+
+		if (REG(AUX_RESET_MASK)) {
+			/*DP_AUX block as part of the enable sequence*/
+			set_reg_field_value(
+				value,
+				1,
+				AUX_CONTROL,
+				AUX_RESET);
+		}
+
+		REG_WRITE(AUX_CONTROL, value);
+
+		if (REG(AUX_RESET_MASK)) {
+			/*poll HW to make sure reset it done*/
+
+			REG_WAIT(AUX_CONTROL, AUX_RESET_DONE, 1,
+					1, 11);
+
+			set_reg_field_value(
+				value,
+				0,
+				AUX_CONTROL,
+				AUX_RESET);
+
+			REG_WRITE(AUX_CONTROL, value);
+
+			REG_WAIT(AUX_CONTROL, AUX_RESET_DONE, 0,
+					1, 11);
+		}
+	} /*if (field)*/
+
+	/* request SW to access AUX */
+	REG_UPDATE(AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, 1);
+
+	value = REG_READ(AUX_ARB_CONTROL);
+	field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+
+	return (field == SW_CAN_ACCESS_AUX);
+}
+
+#define COMPOSE_AUX_SW_DATA_16_20(command, address) \
+	((command) | ((0xF0000 & (address)) >> 16))
+
+#define COMPOSE_AUX_SW_DATA_8_15(address) \
+	((0xFF00 & (address)) >> 8)
+
+#define COMPOSE_AUX_SW_DATA_0_7(address) \
+	(0xFF & (address))
+
+static void submit_channel_request(
+	struct aux_engine *engine,
+	struct aux_request_transaction_data *request)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t value;
+	uint32_t length;
+
+	bool is_write =
+		((request->type == AUX_TRANSACTION_TYPE_DP) &&
+		 (request->action == I2CAUX_TRANSACTION_ACTION_DP_WRITE)) ||
+		((request->type == AUX_TRANSACTION_TYPE_I2C) &&
+		((request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE) ||
+		 (request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT)));
+	if (REG(AUXN_IMPCAL)) {
+		/* clear_aux_error */
+		REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
+				1,
+				0);
+
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
+				1,
+				0);
+
+		/* force_default_calibrate */
+		REG_UPDATE_1BY1_2(AUXN_IMPCAL,
+				AUXN_IMPCAL_ENABLE, 1,
+				AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
+
+		/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
+
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
+				1,
+				0);
+	}
+	/* set the delay and the number of bytes to write */
+
+	/* The length include
+	 * the 4 bit header and the 20 bit address
+	 * (that is 3 byte).
+	 * If the requested length is non zero this means
+	 * an addition byte specifying the length is required.
+	 */
+
+	length = request->length ? 4 : 3;
+	if (is_write)
+		length += request->length;
+
+	REG_UPDATE_2(AUX_SW_CONTROL,
+			AUX_SW_START_DELAY, request->delay,
+			AUX_SW_WR_BYTES, length);
+
+	/* program action and address and payload data (if 'is_write') */
+	value = REG_UPDATE_4(AUX_SW_DATA,
+			AUX_SW_INDEX, 0,
+			AUX_SW_DATA_RW, 0,
+			AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_16_20(request->action, request->address));
+
+	value = REG_SET_2(AUX_SW_DATA, value,
+			AUX_SW_AUTOINCREMENT_DISABLE, 0,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_8_15(request->address));
+
+	value = REG_SET(AUX_SW_DATA, value,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_0_7(request->address));
+
+	if (request->length) {
+		value = REG_SET(AUX_SW_DATA, value,
+				AUX_SW_DATA, request->length - 1);
+	}
+
+	if (is_write) {
+		/* Load the HW buffer with the Data to be sent.
+		 * This is relevant for write operation.
+		 * For read, the data recived data will be
+		 * processed in process_channel_reply().
+		 */
+		uint32_t i = 0;
+
+		while (i < request->length) {
+			value = REG_SET(AUX_SW_DATA, value,
+					AUX_SW_DATA, request->data[i]);
+
+			++i;
+		}
+	}
+
+	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+				10, aux110->timeout_period/10);
+	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
+}
+
+static int read_channel_reply(struct aux_engine *engine, uint32_t size,
+			      uint8_t *buffer, uint8_t *reply_result,
+			      uint32_t *sw_status)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t bytes_replied;
+	uint32_t reply_result_32;
+
+	*sw_status = REG_GET(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT,
+			     &bytes_replied);
+
+	/* In case HPD is LOW, exit AUX transaction */
+	if ((*sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return -1;
+
+	/* Need at least the status byte */
+	if (!bytes_replied)
+		return -1;
+
+	REG_UPDATE_1BY1_3(AUX_SW_DATA,
+			  AUX_SW_INDEX, 0,
+			  AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			  AUX_SW_DATA_RW, 1);
+
+	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	reply_result_32 = reply_result_32 >> 4;
+	*reply_result = (uint8_t)reply_result_32;
+
+	if (reply_result_32 == 0) { /* ACK */
+		uint32_t i = 0;
+
+		/* First byte was already used to get the command status */
+		--bytes_replied;
+
+		/* Do not overflow buffer */
+		if (bytes_replied > size)
+			return -1;
+
+		while (i < bytes_replied) {
+			uint32_t aux_sw_data_val;
+
+			REG_GET(AUX_SW_DATA, AUX_SW_DATA, &aux_sw_data_val);
+			buffer[i] = aux_sw_data_val;
+			++i;
+		}
+
+		return i;
+	}
+
+	return 0;
+}
+
+static void process_channel_reply(
+	struct aux_engine *engine,
+	struct aux_reply_transaction_data *reply)
+{
+	int bytes_replied;
+	uint8_t reply_result;
+	uint32_t sw_status;
+
+	bytes_replied = read_channel_reply(engine, reply->length, reply->data,
+					   &reply_result, &sw_status);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		return;
+	}
+
+	if (bytes_replied < 0) {
+		/* Need to handle an error case...
+		 * Hopefully, upper layer function won't call this function if
+		 * the number of bytes in the reply was 0, because there was
+		 * surely an error that was asserted that should have been
+		 * handled for hot plug case, this could happens
+		 */
+		if (!(sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+			ASSERT_CRITICAL(false);
+			return;
+		}
+	} else {
+
+		switch (reply_result) {
+		case 0: /* ACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
+		break;
+		case 1: /* NACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_NACK;
+		break;
+		case 2: /* DEFER */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_DEFER;
+		break;
+		case 4: /* AUX ACK / I2C NACK */
+			reply->status = AUX_TRANSACTION_REPLY_I2C_NACK;
+		break;
+		case 8: /* AUX ACK / I2C DEFER */
+			reply->status = AUX_TRANSACTION_REPLY_I2C_DEFER;
+		break;
+		default:
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+		}
+	}
+}
+
+static enum aux_channel_operation_result get_channel_status(
+	struct aux_engine *engine,
+	uint8_t *returned_bytes)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value;
+
+	if (returned_bytes == NULL) {
+		/*caller pass NULL pointer*/
+		ASSERT_CRITICAL(false);
+		return AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN;
+	}
+	*returned_bytes = 0;
+
+	/* poll to make sure that SW_DONE is asserted */
+	value = REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 1,
+				10, aux110->timeout_period/10);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+
+	/* Note that the following bits are set in 'status.bits'
+	 * during CTS 4.2.1.2 (FW 3.3.1):
+	 * AUX_SW_RX_MIN_COUNT_VIOL, AUX_SW_RX_INVALID_STOP,
+	 * AUX_SW_RX_RECV_NO_DET, AUX_SW_RX_RECV_INVALID_H.
+	 *
+	 * AUX_SW_RX_MIN_COUNT_VIOL is an internal,
+	 * HW debugging bit and should be ignored.
+	 */
+	if (value & AUX_SW_STATUS__AUX_SW_DONE_MASK) {
+		if ((value & AUX_SW_STATUS__AUX_SW_RX_TIMEOUT_STATE_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_TIMEOUT_MASK))
+			return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
+
+		else if ((value & AUX_SW_STATUS__AUX_SW_RX_INVALID_STOP_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_RECV_NO_DET_MASK) ||
+			(value &
+				AUX_SW_STATUS__AUX_SW_RX_RECV_INVALID_H_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_RECV_INVALID_L_MASK))
+			return AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY;
+
+		*returned_bytes = get_reg_field_value(value,
+				AUX_SW_STATUS,
+				AUX_SW_REPLY_BYTE_COUNT);
+
+		if (*returned_bytes == 0)
+			return
+			AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY;
+		else {
+			*returned_bytes -= 1;
+			return AUX_CHANNEL_OPERATION_SUCCEEDED;
+		}
+	} else {
+		/*time_elapsed >= aux_engine->timeout_period
+		 *  AUX_SW_STATUS__AUX_SW_HPD_DISCON = at this point
+		 */
+		ASSERT_CRITICAL(false);
+		return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
+	}
+}
+static void process_read_reply(
+	struct aux_engine *engine,
+	struct read_command_context *ctx)
+{
+	engine->funcs->process_channel_reply(engine, &ctx->reply);
+
+	switch (ctx->reply.status) {
+	case AUX_TRANSACTION_REPLY_AUX_ACK:
+		ctx->defer_retry_aux = 0;
+		if (ctx->returned_byte > ctx->current_read_length) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else if (ctx->returned_byte < ctx->current_read_length) {
+			ctx->current_read_length -= ctx->returned_byte;
+
+			ctx->offset += ctx->returned_byte;
+
+			++ctx->invalid_reply_retry_aux_on_ack;
+
+			if (ctx->invalid_reply_retry_aux_on_ack >
+				AUX_INVALID_REPLY_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+				ctx->operation_succeeded = false;
+			}
+		} else {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
+			ctx->transaction_complete = true;
+			ctx->operation_succeeded = true;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_NACK:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_NACK;
+		ctx->operation_succeeded = false;
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_DEFER:
+		++ctx->defer_retry_aux;
+
+		if (ctx->defer_retry_aux > AUX_DEFER_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_I2C_DEFER:
+		ctx->defer_retry_aux = 0;
+
+		++ctx->defer_retry_i2c;
+
+		if (ctx->defer_retry_i2c > AUX_DEFER_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static void process_read_request(
+	struct aux_engine *engine,
+	struct read_command_context *ctx)
+{
+	enum aux_channel_operation_result operation_result;
+
+	engine->funcs->submit_channel_request(engine, &ctx->request);
+
+	operation_result = engine->funcs->get_channel_status(
+		engine, &ctx->returned_byte);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		if (ctx->returned_byte > ctx->current_read_length) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else {
+			ctx->timed_out_retry_aux = 0;
+			ctx->invalid_reply_retry_aux = 0;
+
+			ctx->reply.length = ctx->returned_byte;
+			ctx->reply.data = ctx->buffer;
+
+			process_read_reply(engine, ctx);
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		++ctx->invalid_reply_retry_aux;
+
+		if (ctx->invalid_reply_retry_aux >
+			AUX_INVALID_REPLY_RETRY_COUNTER) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else
+			udelay(400);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		++ctx->timed_out_retry_aux;
+
+		if (ctx->timed_out_retry_aux > AUX_TIMED_OUT_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		} else {
+			/* DP 1.2a, table 2-58:
+			 * "S3: AUX Request CMD PENDING:
+			 * retry 3 times, with 400usec wait on each"
+			 * The HW timeout is set to 550usec,
+			 * so we should not wait here
+			 */
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static bool read_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct read_command_context ctx;
+
+	ctx.buffer = request->payload.data;
+	ctx.current_read_length = request->payload.length;
+	ctx.offset = 0;
+	ctx.timed_out_retry_aux = 0;
+	ctx.invalid_reply_retry_aux = 0;
+	ctx.defer_retry_aux = 0;
+	ctx.defer_retry_i2c = 0;
+	ctx.invalid_reply_retry_aux_on_ack = 0;
+	ctx.transaction_complete = false;
+	ctx.operation_succeeded = true;
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_DP;
+		ctx.request.action = I2CAUX_TRANSACTION_ACTION_DP_READ;
+		ctx.request.address = request->payload.address;
+	} else if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_I2C;
+		ctx.request.action = middle_of_transaction ?
+			I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_READ;
+		ctx.request.address = request->payload.address >> 1;
+	} else {
+		/* in DAL2, there was no return in such case */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	ctx.request.delay = 0;
+
+	do {
+		memset(ctx.buffer + ctx.offset, 0, ctx.current_read_length);
+
+		ctx.request.data = ctx.buffer + ctx.offset;
+		ctx.request.length = ctx.current_read_length;
+
+		process_read_request(engine, &ctx);
+
+		request->status = ctx.status;
+
+		if (ctx.operation_succeeded && !ctx.transaction_complete)
+			if (ctx.request.type == AUX_TRANSACTION_TYPE_I2C)
+				msleep(engine->delay);
+	} while (ctx.operation_succeeded && !ctx.transaction_complete);
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		DC_LOG_I2C_AUX("READ: addr:0x%x  value:0x%x Result:%d",
+				request->payload.address,
+				request->payload.data[0],
+				ctx.operation_succeeded);
+	}
+
+	return ctx.operation_succeeded;
+}
+
+static void process_write_reply(
+	struct aux_engine *engine,
+	struct write_command_context *ctx)
+{
+	engine->funcs->process_channel_reply(engine, &ctx->reply);
+
+	switch (ctx->reply.status) {
+	case AUX_TRANSACTION_REPLY_AUX_ACK:
+		ctx->operation_succeeded = true;
+
+		if (ctx->returned_byte) {
+			ctx->request.action = ctx->mot ?
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST;
+
+			ctx->current_write_length = 0;
+
+			++ctx->ack_m_retry;
+
+			if (ctx->ack_m_retry > AUX_DEFER_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+				ctx->operation_succeeded = false;
+			} else
+				udelay(300);
+		} else {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
+			ctx->defer_retry_aux = 0;
+			ctx->ack_m_retry = 0;
+			ctx->transaction_complete = true;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_NACK:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_NACK;
+		ctx->operation_succeeded = false;
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_DEFER:
+		++ctx->defer_retry_aux;
+
+		if (ctx->defer_retry_aux > ctx->max_defer_retry) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_I2C_DEFER:
+		ctx->defer_retry_aux = 0;
+		ctx->current_write_length = 0;
+
+		ctx->request.action = ctx->mot ?
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST;
+
+		++ctx->defer_retry_i2c;
+
+		if (ctx->defer_retry_i2c > ctx->max_defer_retry) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static void process_write_request(
+	struct aux_engine *engine,
+	struct write_command_context *ctx)
+{
+	enum aux_channel_operation_result operation_result;
+
+	engine->funcs->submit_channel_request(engine, &ctx->request);
+
+	operation_result = engine->funcs->get_channel_status(
+		engine, &ctx->returned_byte);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		ctx->timed_out_retry_aux = 0;
+		ctx->invalid_reply_retry_aux = 0;
+
+		ctx->reply.length = ctx->returned_byte;
+		ctx->reply.data = ctx->reply_data;
+
+		process_write_reply(engine, ctx);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		++ctx->invalid_reply_retry_aux;
+
+		if (ctx->invalid_reply_retry_aux >
+			AUX_INVALID_REPLY_RETRY_COUNTER) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else
+			udelay(400);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		++ctx->timed_out_retry_aux;
+
+		if (ctx->timed_out_retry_aux > AUX_TIMED_OUT_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		} else {
+			/* DP 1.2a, table 2-58:
+			 * "S3: AUX Request CMD PENDING:
+			 * retry 3 times, with 400usec wait on each"
+			 * The HW timeout is set to 550usec,
+			 * so we should not wait here
+			 */
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static bool write_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct write_command_context ctx;
+
+	ctx.mot = middle_of_transaction;
+	ctx.buffer = request->payload.data;
+	ctx.current_write_length = request->payload.length;
+	ctx.timed_out_retry_aux = 0;
+	ctx.invalid_reply_retry_aux = 0;
+	ctx.defer_retry_aux = 0;
+	ctx.defer_retry_i2c = 0;
+	ctx.ack_m_retry = 0;
+	ctx.transaction_complete = false;
+	ctx.operation_succeeded = true;
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_DP;
+		ctx.request.action = I2CAUX_TRANSACTION_ACTION_DP_WRITE;
+		ctx.request.address = request->payload.address;
+	} else if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_I2C;
+		ctx.request.action = middle_of_transaction ?
+			I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_WRITE;
+		ctx.request.address = request->payload.address >> 1;
+	} else {
+		/* in DAL2, there was no return in such case */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	ctx.request.delay = 0;
+
+	ctx.max_defer_retry =
+		(engine->max_defer_write_retry > AUX_DEFER_RETRY_COUNTER) ?
+			engine->max_defer_write_retry : AUX_DEFER_RETRY_COUNTER;
+
+	do {
+		ctx.request.data = ctx.buffer;
+		ctx.request.length = ctx.current_write_length;
+
+		process_write_request(engine, &ctx);
+
+		request->status = ctx.status;
+
+		if (ctx.operation_succeeded && !ctx.transaction_complete)
+			if (ctx.request.type == AUX_TRANSACTION_TYPE_I2C)
+				msleep(engine->delay);
+	} while (ctx.operation_succeeded && !ctx.transaction_complete);
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		DC_LOG_I2C_AUX("WRITE: addr:0x%x  value:0x%x Result:%d",
+				request->payload.address,
+				request->payload.data[0],
+				ctx.operation_succeeded);
+	}
+
+	return ctx.operation_succeeded;
+}
+static bool end_of_transaction_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request)
+{
+	struct i2caux_transaction_request dummy_request;
+	uint8_t dummy_data;
+
+	/* [tcheng] We only need to send the stop (read with MOT = 0)
+	 * for I2C-over-Aux, not native AUX
+	 */
+
+	if (request->payload.address_space !=
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C)
+		return false;
+
+	dummy_request.operation = request->operation;
+	dummy_request.payload.address_space = request->payload.address_space;
+	dummy_request.payload.address = request->payload.address;
+
+	/*
+	 * Add a dummy byte due to some receiver quirk
+	 * where one byte is sent along with MOT = 0.
+	 * Ideally this should be 0.
+	 */
+
+	dummy_request.payload.length = 0;
+	dummy_request.payload.data = &dummy_data;
+
+	if (request->operation == I2CAUX_TRANSACTION_READ)
+		return read_command(engine, &dummy_request, false);
+	else
+		return write_command(engine, &dummy_request, false);
+
+	/* according Syed, it does not need now DoDummyMOT */
+}
+bool submit_request(
+	struct engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct aux_engine *aux_engine = FROM_AUX_ENGINE_ENGINE(engine);
+
+	bool result;
+	bool mot_used = true;
+
+	switch (request->operation) {
+	case I2CAUX_TRANSACTION_READ:
+		result = read_command(aux_engine, request, mot_used);
+	break;
+	case I2CAUX_TRANSACTION_WRITE:
+		result = write_command(aux_engine, request, mot_used);
+	break;
+	default:
+		result = false;
+	}
+
+	/* [tcheng]
+	 * need to send stop for the last transaction to free up the AUX
+	 * if the above command fails, this would be the last transaction
+	 */
+
+	if (!middle_of_transaction || !result)
+		end_of_transaction_command(aux_engine, request);
+
+	/* mask AUX interrupt */
+
+	return result;
+}
+enum i2caux_engine_type get_engine_type(
+		const struct engine *engine)
+{
+	return I2CAUX_ENGINE_TYPE_AUX;
+}
+
+static struct aux_engine *acquire(
+	struct engine *engine,
+	struct ddc *ddc)
+{
+	struct aux_engine *aux_engine = FROM_AUX_ENGINE_ENGINE(engine);
+	enum gpio_result result;
+
+	if (aux_engine->funcs->is_engine_available) {
+		/*check whether SW could use the engine*/
+		if (!aux_engine->funcs->is_engine_available(aux_engine))
+			return NULL;
+	}
+
+	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
+		GPIO_DDC_CONFIG_TYPE_MODE_AUX);
+
+	if (result != GPIO_RESULT_OK)
+		return NULL;
+
+	if (!aux_engine->funcs->acquire_engine(aux_engine)) {
+		dal_ddc_close(ddc);
+		return NULL;
+	}
+
+	engine->ddc = ddc;
+
+	return aux_engine;
+}
+
+static const struct aux_engine_funcs aux_engine_funcs = {
+	.acquire_engine = acquire_engine,
+	.submit_channel_request = submit_channel_request,
+	.process_channel_reply = process_channel_reply,
+	.read_channel_reply = read_channel_reply,
+	.get_channel_status = get_channel_status,
+	.is_engine_available = is_engine_available,
+};
+
+static const struct engine_funcs engine_funcs = {
+	.release_engine = release_engine,
+	.destroy_engine = dce110_engine_destroy,
+	.submit_request = submit_request,
+	.get_engine_type = get_engine_type,
+	.acquire = acquire,
+};
+
+void dce110_engine_destroy(struct engine **engine)
+{
+
+	struct aux_engine_dce110 *engine110 = FROM_ENGINE(*engine);
+
+	kfree(engine110);
+	*engine = NULL;
+
+}
+struct aux_engine *dce110_aux_engine_construct(struct aux_engine_dce110 *aux_engine110,
+		struct dc_context *ctx,
+		uint32_t inst,
+		uint32_t timeout_period,
+		const struct dce110_aux_registers *regs)
+{
+	aux_engine110->base.base.ddc = NULL;
+	aux_engine110->base.base.ctx = ctx;
+	aux_engine110->base.delay = 0;
+	aux_engine110->base.max_defer_write_retry = 0;
+	aux_engine110->base.base.funcs = &engine_funcs;
+	aux_engine110->base.funcs = &aux_engine_funcs;
+	aux_engine110->base.base.inst = inst;
+	aux_engine110->timeout_period = timeout_period;
+	aux_engine110->regs = regs;
+
+	return &aux_engine110->base;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
new file mode 100644
index 000000000000..c6b2aec2e367
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -0,0 +1,111 @@
+/*
+ * 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
+ *
+ */
+
+#ifndef __DAL_AUX_ENGINE_DCE110_H__
+#define __DAL_AUX_ENGINE_DCE110_H__
+#include "aux_engine.h"
+
+#define AUX_COMMON_REG_LIST(id)\
+	SRI(AUX_CONTROL, DP_AUX, id), \
+	SRI(AUX_ARB_CONTROL, DP_AUX, id), \
+	SRI(AUX_SW_DATA, DP_AUX, id), \
+	SRI(AUX_SW_CONTROL, DP_AUX, id), \
+	SRI(AUX_INTERRUPT_CONTROL, DP_AUX, id), \
+	SRI(AUX_SW_STATUS, DP_AUX, id), \
+	SR(AUXN_IMPCAL), \
+	SR(AUXP_IMPCAL)
+
+struct dce110_aux_registers {
+	uint32_t AUX_CONTROL;
+	uint32_t AUX_ARB_CONTROL;
+	uint32_t AUX_SW_DATA;
+	uint32_t AUX_SW_CONTROL;
+	uint32_t AUX_INTERRUPT_CONTROL;
+	uint32_t AUX_SW_STATUS;
+	uint32_t AUXN_IMPCAL;
+	uint32_t AUXP_IMPCAL;
+
+	uint32_t AUX_RESET_MASK;
+};
+
+enum {	/* This is the timeout as defined in DP 1.2a,
+	 * 2.3.4 "Detailed uPacket TX AUX CH State Description".
+	 */
+	AUX_TIMEOUT_PERIOD = 400,
+
+	/* Ideally, the SW timeout should be just above 550usec
+	 * which is programmed in HW.
+	 * But the SW timeout of 600usec is not reliable,
+	 * because on some systems, delay_in_microseconds()
+	 * returns faster than it should.
+	 * EPR #379763: by trial-and-error on different systems,
+	 * 700usec is the minimum reliable SW timeout for polling
+	 * the AUX_SW_STATUS.AUX_SW_DONE bit.
+	 * This timeout expires *only* when there is
+	 * AUX Error or AUX Timeout conditions - not during normal operation.
+	 * During normal operation, AUX_SW_STATUS.AUX_SW_DONE bit is set
+	 * at most within ~240usec. That means,
+	 * increasing this timeout will not affect normal operation,
+	 * and we'll timeout after
+	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+	 * This timeout is especially important for
+	 * resume from S3 and CTS.
+	 */
+	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+};
+struct aux_engine_dce110 {
+	struct aux_engine base;
+	const struct dce110_aux_registers *regs;
+	struct {
+		uint32_t aux_control;
+		uint32_t aux_arb_control;
+		uint32_t aux_sw_data;
+		uint32_t aux_sw_control;
+		uint32_t aux_interrupt_control;
+		uint32_t aux_sw_status;
+	} addr;
+	uint32_t timeout_period;
+};
+
+struct aux_engine_dce110_init_data {
+	uint32_t engine_id;
+	uint32_t timeout_period;
+	struct dc_context *ctx;
+	const struct dce110_aux_registers *regs;
+};
+
+struct aux_engine *dce110_aux_engine_construct(
+		struct aux_engine_dce110 *aux_engine110,
+		struct dc_context *ctx,
+		uint32_t inst,
+		uint32_t timeout_period,
+		const struct dce110_aux_registers *regs);
+
+void dce110_engine_destroy(struct engine **engine);
+
+bool dce110_aux_engine_acquire(
+	struct engine *aux_engine,
+	struct ddc *ddc);
+#endif
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 88b09dd758ba..439dcf3b596c 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
@@ -133,7 +133,7 @@ static bool calculate_fb_and_fractional_fb_divider(
 	uint64_t feedback_divider;
 
 	feedback_divider =
-		(uint64_t)(target_pix_clk_khz * ref_divider * post_divider);
+		(uint64_t)target_pix_clk_khz * ref_divider * post_divider;
 	feedback_divider *= 10;
 	/* additional factor, since we divide by 10 afterwards */
 	feedback_divider *= (uint64_t)(calc_pll_cs->fract_fb_divider_factor);
@@ -145,8 +145,8 @@ static bool calculate_fb_and_fractional_fb_divider(
  * of fractional feedback decimal point and the fractional FB Divider precision
  * is 2 then the equation becomes (ullfeedbackDivider + 5*100) / (10*100))*/
 
-	feedback_divider += (uint64_t)
-			(5 * calc_pll_cs->fract_fb_divider_precision_factor);
+	feedback_divider += 5ULL *
+			    calc_pll_cs->fract_fb_divider_precision_factor;
 	feedback_divider =
 		div_u64(feedback_divider,
 			calc_pll_cs->fract_fb_divider_precision_factor * 10);
@@ -203,8 +203,8 @@ static bool calc_fb_divider_checking_tolerance(
 			&fract_feedback_divider);
 
 	/*Actual calculated value*/
-	actual_calc_clk_khz = (uint64_t)(feedback_divider *
-					calc_pll_cs->fract_fb_divider_factor) +
+	actual_calc_clk_khz = (uint64_t)feedback_divider *
+					calc_pll_cs->fract_fb_divider_factor +
 							fract_feedback_divider;
 	actual_calc_clk_khz *= calc_pll_cs->ref_freq_khz;
 	actual_calc_clk_khz =
@@ -592,7 +592,7 @@ static uint32_t dce110_get_pix_clk_dividers(
 	case DCE_VERSION_11_2:
 	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 #endif
 
@@ -909,7 +909,7 @@ static bool dce110_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)
+#ifdef CONFIG_X86
 	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_kHz = 700000;
@@ -982,7 +982,7 @@ static bool dce110_program_pix_clk(
 	case DCE_VERSION_11_2:
 	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 #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 c45e2f76189e..801bb65707b3 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 +55,7 @@
 	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_DCN1_0)
+#ifdef CONFIG_X86
 
 #define CS_COMMON_REG_LIST_DCN1_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 8a581c67bf2d..0db8d1da3d0e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -30,7 +30,7 @@
 #include "bios_parser_interface.h"
 #include "dc.h"
 #include "dmcu.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn_calcs.h"
 #endif
 #include "core_types.h"
@@ -38,7 +38,7 @@
 #include "dal_asic_id.h"
 
 #define TO_DCE_CLOCKS(clocks)\
-	container_of(clocks, struct dce_disp_clk, base)
+	container_of(clocks, struct dce_dccg, base)
 
 #define REG(reg) \
 	(clk_dce->regs->reg)
@@ -101,99 +101,78 @@ static const struct state_dependent_clocks dce120_max_clks_by_state[] = {
 /*ClocksStatePerformance*/
 { .display_clk_khz = 1133000, .pixel_clk_khz = 600000 } };
 
-/* Starting point for each divider range.*/
-enum dce_divider_range_start {
-	DIVIDER_RANGE_01_START = 200, /* 2.00*/
-	DIVIDER_RANGE_02_START = 1600, /* 16.00*/
-	DIVIDER_RANGE_03_START = 3200, /* 32.00*/
-	DIVIDER_RANGE_SCALE_FACTOR = 100 /* Results are scaled up by 100.*/
+/* Starting DID for each range */
+enum dentist_base_divider_id {
+	DENTIST_BASE_DID_1 = 0x08,
+	DENTIST_BASE_DID_2 = 0x40,
+	DENTIST_BASE_DID_3 = 0x60,
+	DENTIST_MAX_DID    = 0x80
 };
 
-/* Ranges for divider identifiers (Divider ID or DID)
- mmDENTIST_DISPCLK_CNTL.DENTIST_DISPCLK_WDIVIDER*/
-enum dce_divider_id_register_setting {
-	DIVIDER_RANGE_01_BASE_DIVIDER_ID = 0X08,
-	DIVIDER_RANGE_02_BASE_DIVIDER_ID = 0X40,
-	DIVIDER_RANGE_03_BASE_DIVIDER_ID = 0X60,
-	DIVIDER_RANGE_MAX_DIVIDER_ID = 0X80
+/* Starting point and step size for each divider range.*/
+enum dentist_divider_range {
+	DENTIST_DIVIDER_RANGE_1_START = 8,   /* 2.00  */
+	DENTIST_DIVIDER_RANGE_1_STEP  = 1,   /* 0.25  */
+	DENTIST_DIVIDER_RANGE_2_START = 64,  /* 16.00 */
+	DENTIST_DIVIDER_RANGE_2_STEP  = 2,   /* 0.50  */
+	DENTIST_DIVIDER_RANGE_3_START = 128, /* 32.00 */
+	DENTIST_DIVIDER_RANGE_3_STEP  = 4,   /* 1.00  */
+	DENTIST_DIVIDER_RANGE_SCALE_FACTOR = 4
 };
 
-/* Step size between each divider within a range.
- Incrementing the DENTIST_DISPCLK_WDIVIDER by one
- will increment the divider by this much.*/
-enum dce_divider_range_step_size {
-	DIVIDER_RANGE_01_STEP_SIZE = 25, /* 0.25*/
-	DIVIDER_RANGE_02_STEP_SIZE = 50, /* 0.50*/
-	DIVIDER_RANGE_03_STEP_SIZE = 100 /* 1.00 */
-};
-
-static bool dce_divider_range_construct(
-	struct dce_divider_range *div_range,
-	int range_start,
-	int range_step,
-	int did_min,
-	int did_max)
+static int dentist_get_divider_from_did(int did)
 {
-	div_range->div_range_start = range_start;
-	div_range->div_range_step = range_step;
-	div_range->did_min = did_min;
-	div_range->did_max = did_max;
-
-	if (div_range->div_range_step == 0) {
-		div_range->div_range_step = 1;
-		/*div_range_step cannot be zero*/
-		BREAK_TO_DEBUGGER();
+	if (did < DENTIST_BASE_DID_1)
+		did = DENTIST_BASE_DID_1;
+	if (did > DENTIST_MAX_DID)
+		did = DENTIST_MAX_DID;
+
+	if (did < DENTIST_BASE_DID_2) {
+		return DENTIST_DIVIDER_RANGE_1_START + DENTIST_DIVIDER_RANGE_1_STEP
+							* (did - DENTIST_BASE_DID_1);
+	} else if (did < DENTIST_BASE_DID_3) {
+		return DENTIST_DIVIDER_RANGE_2_START + DENTIST_DIVIDER_RANGE_2_STEP
+							* (did - DENTIST_BASE_DID_2);
+	} else {
+		return DENTIST_DIVIDER_RANGE_3_START + DENTIST_DIVIDER_RANGE_3_STEP
+							* (did - DENTIST_BASE_DID_3);
 	}
-	/* Calculate this based on the other inputs.*/
-	/* See DividerRange.h for explanation of */
-	/* the relationship between divider id (DID) and a divider.*/
-	/* Number of Divider IDs = (Maximum Divider ID - Minimum Divider ID)*/
-	/* Maximum divider identified in this range =
-	 * (Number of Divider IDs)*Step size between dividers
-	 *  + The start of this range.*/
-	div_range->div_range_end = (did_max - did_min) * range_step
-		+ range_start;
-	return true;
-}
-
-static int dce_divider_range_calc_divider(
-	struct dce_divider_range *div_range,
-	int did)
-{
-	/* Is this DID within our range?*/
-	if ((did < div_range->did_min) || (did >= div_range->did_max))
-		return INVALID_DIVIDER;
-
-	return ((did - div_range->did_min) * div_range->div_range_step)
-			+ div_range->div_range_start;
-
 }
 
-static int dce_divider_range_get_divider(
-	struct dce_divider_range *div_range,
-	int ranges_num,
-	int did)
+/* SW will adjust DP REF Clock average value for all purposes
+ * (DP DTO / DP Audio DTO and DP GTC)
+ if clock is spread for all cases:
+ -if SS enabled on DP Ref clock and HW de-spreading enabled with SW
+ calculations for DS_INCR/DS_MODULO (this is planned to be default case)
+ -if SS enabled on DP Ref clock and HW de-spreading enabled with HW
+ calculations (not planned to be used, but average clock should still
+ be valid)
+ -if SS enabled on DP Ref clock and HW de-spreading disabled
+ (should not be case with CIK) then SW should program all rates
+ generated according to average value (case as with previous ASICs)
+  */
+static int dccg_adjust_dp_ref_freq_for_ss(struct dce_dccg *clk_dce, int dp_ref_clk_khz)
 {
-	int div = INVALID_DIVIDER;
-	int i;
+	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
+		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
+				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
+							clk_dce->dprefclk_ss_divider), 200);
+		struct fixed31_32 adj_dp_ref_clk_khz;
 
-	for (i = 0; i < ranges_num; i++) {
-		/* Calculate divider with given divider ID*/
-		div = dce_divider_range_calc_divider(&div_range[i], did);
-		/* Found a valid return divider*/
-		if (div != INVALID_DIVIDER)
-			break;
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
+		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
+		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
 	}
-	return div;
+	return dp_ref_clk_khz;
 }
 
-static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
+static int dce_get_dp_ref_freq_khz(struct dccg *clk)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int dprefclk_wdivider;
 	int dprefclk_src_sel;
 	int dp_ref_clk_khz = 600000;
-	int target_div = INVALID_DIVIDER;
+	int target_div;
 
 	/* ASSERT DP Reference Clock source is from DFS*/
 	REG_GET(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, &dprefclk_src_sel);
@@ -204,80 +183,27 @@ static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
 	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider);
 
 	/* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/
-	target_div = dce_divider_range_get_divider(
-			clk_dce->divider_ranges,
-			DIVIDER_RANGE_MAX,
-			dprefclk_wdivider);
-
-	if (target_div != INVALID_DIVIDER) {
-		/* Calculate the current DFS clock, in kHz.*/
-		dp_ref_clk_khz = (DIVIDER_RANGE_SCALE_FACTOR
-			* clk_dce->dentist_vco_freq_khz) / target_div;
-	}
+	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
 
-	/* SW will adjust DP REF Clock average value for all purposes
-	 * (DP DTO / DP Audio DTO and DP GTC)
-	 if clock is spread for all cases:
-	 -if SS enabled on DP Ref clock and HW de-spreading enabled with SW
-	 calculations for DS_INCR/DS_MODULO (this is planned to be default case)
-	 -if SS enabled on DP Ref clock and HW de-spreading enabled with HW
-	 calculations (not planned to be used, but average clock should still
-	 be valid)
-	 -if SS enabled on DP Ref clock and HW de-spreading disabled
-	 (should not be case with CIK) then SW should program all rates
-	 generated according to average value (case as with previous ASICs)
-	  */
-	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(
-						clk_dce->dprefclk_ss_percentage,
-						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed31_32 adj_dp_ref_clk_khz;
+	/* Calculate the current DFS clock, in kHz.*/
+	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
+		* clk_dce->dentist_vco_freq_khz) / target_div;
 
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
-								ss_percentage);
-		adj_dp_ref_clk_khz =
-			dc_fixpt_mul_int(
-				ss_percentage,
-				dp_ref_clk_khz);
-		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
-	}
-
-	return dp_ref_clk_khz;
+	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, dp_ref_clk_khz);
 }
 
-/* TODO: This is DCN DPREFCLK: it could be program by DENTIST by VBIOS
- * or CLK0_CLK11 by SMU. For DCE120, it is wlays 600Mhz. Will re-visit
- * clock implementation
- */
-static int dce_clocks_get_dp_ref_freq_wrkaround(struct display_clock *clk)
+static int dce12_get_dp_ref_freq_khz(struct dccg *clk)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
-	int dp_ref_clk_khz = 600000;
-
-	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(
-						clk_dce->dprefclk_ss_percentage,
-						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed31_32 adj_dp_ref_clk_khz;
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
-								ss_percentage);
-		adj_dp_ref_clk_khz =
-			dc_fixpt_mul_int(
-				ss_percentage,
-				dp_ref_clk_khz);
-		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
-	}
-
-	return dp_ref_clk_khz;
+	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, 600000);
 }
+
 static enum dm_pp_clocks_state dce_get_required_clocks_state(
-	struct display_clock *clk,
-	struct state_dependent_clocks *req_clocks)
+	struct dccg *clk,
+	struct dc_clocks *req_clocks)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int i;
 	enum dm_pp_clocks_state low_req_clk;
 
@@ -286,53 +212,30 @@ static enum dm_pp_clocks_state dce_get_required_clocks_state(
 	 * all required clocks
 	 */
 	for (i = clk->max_clks_state; i >= DM_PP_CLOCKS_STATE_ULTRA_LOW; i--)
-		if (req_clocks->display_clk_khz >
+		if (req_clocks->dispclk_khz >
 				clk_dce->max_clks_by_state[i].display_clk_khz
-			|| req_clocks->pixel_clk_khz >
+			|| req_clocks->phyclk_khz >
 				clk_dce->max_clks_by_state[i].pixel_clk_khz)
 			break;
 
 	low_req_clk = i + 1;
 	if (low_req_clk > clk->max_clks_state) {
-		DC_LOG_WARNING("%s: clocks unsupported disp_clk %d pix_clk %d",
-				__func__,
-				req_clocks->display_clk_khz,
-				req_clocks->pixel_clk_khz);
-		low_req_clk = DM_PP_CLOCKS_STATE_INVALID;
+		/* set max clock state for high phyclock, invalid on exceeding display clock */
+		if (clk_dce->max_clks_by_state[clk->max_clks_state].display_clk_khz
+				< req_clocks->dispclk_khz)
+			low_req_clk = DM_PP_CLOCKS_STATE_INVALID;
+		else
+			low_req_clk = clk->max_clks_state;
 	}
 
 	return low_req_clk;
 }
 
-static bool dce_clock_set_min_clocks_state(
-	struct display_clock *clk,
-	enum dm_pp_clocks_state clocks_state)
-{
-	struct dm_pp_power_level_change_request level_change_req = {
-			clocks_state };
-
-	if (clocks_state > clk->max_clks_state) {
-		/*Requested state exceeds max supported state.*/
-		DC_LOG_WARNING("Requested state exceeds max supported state");
-		return false;
-	} else if (clocks_state == clk->cur_min_clks_state) {
-		/*if we're trying to set the same state, we can just return
-		 * since nothing needs to be done*/
-		return true;
-	}
-
-	/* get max clock state from PPLIB */
-	if (dm_pp_apply_power_level_change_request(clk->ctx, &level_change_req))
-		clk->cur_min_clks_state = clocks_state;
-
-	return true;
-}
-
 static int dce_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct bp_pixel_clock_parameters pxl_clk_params = { 0 };
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	int actual_clock = requested_clk_khz;
@@ -364,10 +267,10 @@ static int dce_set_clock(
 }
 
 static int dce_psr_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct dc_context *ctx = clk_dce->base.ctx;
 	struct dc *core_dc = ctx->dc;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
@@ -380,10 +283,10 @@ static int dce_psr_set_clock(
 }
 
 static int dce112_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	struct dc *core_dc = clk->ctx->dc;
@@ -432,9 +335,9 @@ static int dce112_set_clock(
 	return actual_clock;
 }
 
-static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
+static void dce_clock_read_integrated_info(struct dce_dccg *clk_dce)
 {
-	struct dc_debug *debug = &clk_dce->base.ctx->dc->debug;
+	struct dc_debug_options *debug = &clk_dce->base.ctx->dc->debug;
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
 	struct integrated_info info = { { { 0 } } };
 	struct dc_firmware_info fw_info = { { 0 } };
@@ -488,11 +391,9 @@ static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
 	if (!debug->disable_dfs_bypass && bp->integrated_info)
 		if (bp->integrated_info->gpu_cap_info & DFS_BYPASS_ENABLE)
 			clk_dce->dfs_bypass_enabled = true;
-
-	clk_dce->use_max_disp_clk = debug->max_disp_clk;
 }
 
-static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
+static void dce_clock_read_ss_info(struct dce_dccg *clk_dce)
 {
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
 	int ss_info_num = bp->funcs->get_ss_entry_number(
@@ -548,139 +449,263 @@ static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
 	}
 }
 
-static bool dce_apply_clock_voltage_request(
-	struct display_clock *clk,
-	enum dm_pp_clock_type clocks_type,
-	int clocks_in_khz,
-	bool pre_mode_set,
-	bool update_dp_phyclk)
+static inline bool should_set_clock(bool safe_to_lower, int calc_clk, int cur_clk)
+{
+	return ((safe_to_lower && calc_clk < cur_clk) || calc_clk > cur_clk);
+}
+
+static void dce12_update_clocks(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
 {
-	bool send_request = false;
 	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
 
-	switch (clocks_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-	case DM_PP_CLOCK_TYPE_PIXELCLK:
-	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-		break;
-	default:
-		BREAK_TO_DEBUGGER();
-		return false;
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
 
-	clock_voltage_req.clk_type = clocks_type;
-	clock_voltage_req.clocks_in_khz = clocks_in_khz;
-
-	/* to pplib */
-	if (pre_mode_set) {
-		switch (clocks_type) {
-		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (clocks_in_khz > clk->cur_clocks_value.dispclk_in_khz) {
-				clk->cur_clocks_value.dispclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.dispclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.dispclk_in_khz = clocks_in_khz;
-			break;
-		case DM_PP_CLOCK_TYPE_PIXELCLK:
-			if (clocks_in_khz > clk->cur_clocks_value.max_pixelclk_in_khz) {
-				clk->cur_clocks_value.pixelclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.pixelclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.max_pixelclk_in_khz = clocks_in_khz;
-			break;
-		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (clocks_in_khz > clk->cur_clocks_value.max_non_dp_phyclk_in_khz) {
-				clk->cur_clocks_value.phyclk_notigy_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.phyclk_notigy_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.max_non_dp_phyclk_in_khz = clocks_in_khz;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+	}
+}
+
+#ifdef CONFIG_X86
+static int dcn1_determine_dppclk_threshold(struct dccg *dccg, struct dc_clocks *new_clocks)
+{
+	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
+	bool dispclk_increase = new_clocks->dispclk_khz > dccg->clks.dispclk_khz;
+	int disp_clk_threshold = new_clocks->max_supported_dppclk_khz;
+	bool cur_dpp_div = dccg->clks.dispclk_khz > dccg->clks.dppclk_khz;
+
+	/* increase clock, looking for div is 0 for current, request div is 1*/
+	if (dispclk_increase) {
+		/* already divided by 2, no need to reach target clk with 2 steps*/
+		if (cur_dpp_div)
+			return new_clocks->dispclk_khz;
+
+		/* request disp clk is lower than maximum supported dpp clk,
+		 * no need to reach target clk with two steps.
+		 */
+		if (new_clocks->dispclk_khz <= disp_clk_threshold)
+			return new_clocks->dispclk_khz;
+
+		/* target dpp clk not request divided by 2, still within threshold */
+		if (!request_dpp_div)
+			return new_clocks->dispclk_khz;
 
 	} else {
-		switch (clocks_type) {
-		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (!clk->cur_clocks_value.dispclk_notify_pplib_done)
-				send_request = true;
-			break;
-		case DM_PP_CLOCK_TYPE_PIXELCLK:
-			if (!clk->cur_clocks_value.pixelclk_notify_pplib_done)
-				send_request = true;
-			break;
-		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (!clk->cur_clocks_value.phyclk_notigy_pplib_done)
-				send_request = true;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+		/* decrease clock, looking for current dppclk divided by 2,
+		 * request dppclk not divided by 2.
+		 */
+
+		/* current dpp clk not divided by 2, no need to ramp*/
+		if (!cur_dpp_div)
+			return new_clocks->dispclk_khz;
+
+		/* current disp clk is lower than current maximum dpp clk,
+		 * no need to ramp
+		 */
+		if (dccg->clks.dispclk_khz <= disp_clk_threshold)
+			return new_clocks->dispclk_khz;
+
+		/* request dpp clk need to be divided by 2 */
+		if (request_dpp_div)
+			return new_clocks->dispclk_khz;
 	}
-	if (send_request) {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-		if (clk->ctx->dce_version >= DCN_VERSION_1_0) {
-			struct dc *core_dc = clk->ctx->dc;
-			/*use dcfclk request voltage*/
-			clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-			clock_voltage_req.clocks_in_khz =
-				dcn_find_dcfclk_suits_all(core_dc, &clk->cur_clocks_value);
-		}
+
+	return disp_clk_threshold;
+}
+
+static void dcn1_ramp_up_dispclk_with_dpp(struct dccg *dccg, struct dc_clocks *new_clocks)
+{
+	struct dc *dc = dccg->ctx->dc;
+	int dispclk_to_dpp_threshold = dcn1_determine_dppclk_threshold(dccg, new_clocks);
+	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
+	int i;
+
+	/* set disp clk to dpp clk threshold */
+	dccg->funcs->set_dispclk(dccg, dispclk_to_dpp_threshold);
+
+	/* update request dpp clk division option */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx->plane_state)
+			continue;
+
+		pipe_ctx->plane_res.dpp->funcs->dpp_dppclk_control(
+				pipe_ctx->plane_res.dpp,
+				request_dpp_div,
+				true);
+	}
+
+	/* If target clk not same as dppclk threshold, set to target clock */
+	if (dispclk_to_dpp_threshold != new_clocks->dispclk_khz)
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+
+	dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+	dccg->clks.dppclk_khz = new_clocks->dppclk_khz;
+	dccg->clks.max_supported_dppclk_khz = new_clocks->max_supported_dppclk_khz;
+}
+
+static void dcn1_update_clocks(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
+{
+	struct dc *dc = dccg->ctx->dc;
+	struct pp_smu_display_requirement_rv *smu_req_cur =
+			&dc->res_pool->pp_smu_req;
+	struct pp_smu_display_requirement_rv smu_req = *smu_req_cur;
+	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
+	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
+	bool send_request_to_increase = false;
+	bool send_request_to_lower = false;
+
+	if (new_clocks->phyclk_khz)
+		smu_req.display_count = 1;
+	else
+		smu_req.display_count = 0;
+
+	if (new_clocks->dispclk_khz > dccg->clks.dispclk_khz
+			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz
+			|| new_clocks->fclk_khz > dccg->clks.fclk_khz
+			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz)
+		send_request_to_increase = true;
+
+	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (should_set_clock(safe_to_lower, new_clocks->fclk_khz, dccg->clks.fclk_khz)) {
+		dccg->clks.fclk_khz = new_clocks->fclk_khz;
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_FCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->fclk_khz;
+		smu_req.hard_min_fclk_khz = new_clocks->fclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		send_request_to_lower = true;
+	}
+
+	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, dccg->clks.dcfclk_khz)) {
+		dccg->clks.dcfclk_khz = new_clocks->dcfclk_khz;
+		smu_req.hard_min_dcefclk_khz = new_clocks->dcfclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (should_set_clock(safe_to_lower,
+			new_clocks->dcfclk_deep_sleep_khz, dccg->clks.dcfclk_deep_sleep_khz)) {
+		dccg->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz;
+		smu_req.min_deep_sleep_dcefclk_mhz = new_clocks->dcfclk_deep_sleep_khz;
+
+		send_request_to_lower = true;
+	}
+
+	/* make sure dcf clk is before dpp clk to
+	 * make sure we have enough voltage to run dpp clk
+	 */
+	if (send_request_to_increase) {
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		if (pp_smu->set_display_requirement)
+			pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+	}
+
+	/* dcn1 dppclk is tied to dispclk */
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (!send_request_to_increase && send_request_to_lower) {
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		if (pp_smu->set_display_requirement)
+			pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+	}
+
+
+	*smu_req_cur = smu_req;
+}
 #endif
-		dm_pp_apply_clock_for_voltage_request(
-			clk->ctx, &clock_voltage_req);
+
+static void dce_update_clocks(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
+{
+	struct dm_pp_power_level_change_request level_change_req;
+
+	level_change_req.power_level = dce_get_required_clocks_state(dccg, new_clocks);
+	/* get max clock state from PPLIB */
+	if ((level_change_req.power_level < dccg->cur_min_clks_state && safe_to_lower)
+			|| level_change_req.power_level > dccg->cur_min_clks_state) {
+		if (dm_pp_apply_power_level_change_request(dccg->ctx, &level_change_req))
+			dccg->cur_min_clks_state = level_change_req.power_level;
 	}
-	if (update_dp_phyclk && (clocks_in_khz >
-	clk->cur_clocks_value.max_dp_phyclk_in_khz))
-		clk->cur_clocks_value.max_dp_phyclk_in_khz = clocks_in_khz;
 
-	return true;
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+	}
 }
 
+#ifdef CONFIG_X86
+static const struct display_clock_funcs dcn1_funcs = {
+	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dcn1_update_clocks
+};
+#endif
 
 static const struct display_clock_funcs dce120_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
-	.apply_clock_voltage_request = dce_apply_clock_voltage_request,
-	.set_clock = dce112_set_clock
+	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dce12_update_clocks
 };
 
 static const struct display_clock_funcs dce112_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce112_set_clock
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce110_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce_psr_set_clock
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
+	.set_dispclk = dce_psr_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce_set_clock
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
+	.set_dispclk = dce_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
-static void dce_disp_clk_construct(
-	struct dce_disp_clk *clk_dce,
+static void dce_dccg_construct(
+	struct dce_dccg *clk_dce,
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct display_clock *base = &clk_dce->base;
+	struct dccg *base = &clk_dce->base;
 
 	base->ctx = ctx;
 	base->funcs = &dce_funcs;
@@ -700,34 +725,15 @@ static void dce_disp_clk_construct(
 
 	dce_clock_read_integrated_info(clk_dce);
 	dce_clock_read_ss_info(clk_dce);
-
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_01],
-		DIVIDER_RANGE_01_START,
-		DIVIDER_RANGE_01_STEP_SIZE,
-		DIVIDER_RANGE_01_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_02_BASE_DIVIDER_ID);
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_02],
-		DIVIDER_RANGE_02_START,
-		DIVIDER_RANGE_02_STEP_SIZE,
-		DIVIDER_RANGE_02_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_03_BASE_DIVIDER_ID);
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_03],
-		DIVIDER_RANGE_03_START,
-		DIVIDER_RANGE_03_STEP_SIZE,
-		DIVIDER_RANGE_03_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_MAX_DIVIDER_ID);
 }
 
-struct display_clock *dce_disp_clk_create(
+struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -738,19 +744,19 @@ struct display_clock *dce_disp_clk_create(
 		dce80_max_clks_by_state,
 		sizeof(dce80_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	return &clk_dce->base;
 }
 
-struct display_clock *dce110_disp_clk_create(
+struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -761,7 +767,7 @@ struct display_clock *dce110_disp_clk_create(
 		dce110_max_clks_by_state,
 		sizeof(dce110_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	clk_dce->base.funcs = &dce110_funcs;
@@ -769,13 +775,13 @@ struct display_clock *dce110_disp_clk_create(
 	return &clk_dce->base;
 }
 
-struct display_clock *dce112_disp_clk_create(
+struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -786,7 +792,7 @@ struct display_clock *dce112_disp_clk_create(
 		dce112_max_clks_by_state,
 		sizeof(dce112_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	clk_dce->base.funcs = &dce112_funcs;
@@ -794,10 +800,9 @@ struct display_clock *dce112_disp_clk_create(
 	return &clk_dce->base;
 }
 
-struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
+struct dccg *dce120_dccg_create(struct dc_context *ctx)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
-	struct dm_pp_clock_levels_with_voltage clk_level_info = {0};
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -808,28 +813,59 @@ struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
 		dce120_max_clks_by_state,
 		sizeof(dce120_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, NULL, NULL, NULL);
 
 	clk_dce->base.funcs = &dce120_funcs;
 
-	/* new in dce120 */
-	if (!ctx->dc->debug.disable_pplib_clock_request  &&
-			dm_pp_get_clock_levels_by_type_with_voltage(
-			ctx, DM_PP_CLOCK_TYPE_DISPLAY_CLK, &clk_level_info)
-						&& clk_level_info.num_levels)
-		clk_dce->max_displ_clk_in_khz =
-			clk_level_info.data[clk_level_info.num_levels - 1].clocks_in_khz;
-	else
-		clk_dce->max_displ_clk_in_khz = 1133000;
+	return &clk_dce->base;
+}
+
+#ifdef CONFIG_X86
+struct dccg *dcn1_dccg_create(struct dc_context *ctx)
+{
+	struct dc_debug_options *debug = &ctx->dc->debug;
+	struct dc_bios *bp = ctx->dc_bios;
+	struct dc_firmware_info fw_info = { { 0 } };
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+
+	if (clk_dce == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	clk_dce->base.ctx = ctx;
+	clk_dce->base.funcs = &dcn1_funcs;
+
+	clk_dce->dfs_bypass_disp_clk = 0;
+
+	clk_dce->dprefclk_ss_percentage = 0;
+	clk_dce->dprefclk_ss_divider = 1000;
+	clk_dce->ss_on_dprefclk = false;
+
+	if (bp->integrated_info)
+		clk_dce->dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
+	if (clk_dce->dentist_vco_freq_khz == 0) {
+		bp->funcs->get_firmware_info(bp, &fw_info);
+		clk_dce->dentist_vco_freq_khz = fw_info.smu_gpu_pll_output_freq;
+		if (clk_dce->dentist_vco_freq_khz == 0)
+			clk_dce->dentist_vco_freq_khz = 3600000;
+	}
+
+	if (!debug->disable_dfs_bypass && bp->integrated_info)
+		if (bp->integrated_info->gpu_cap_info & DFS_BYPASS_ENABLE)
+			clk_dce->dfs_bypass_enabled = true;
+
+	dce_clock_read_ss_info(clk_dce);
 
 	return &clk_dce->base;
 }
+#endif
 
-void dce_disp_clk_destroy(struct display_clock **disp_clk)
+void dce_dccg_destroy(struct dccg **dccg)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(*disp_clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(*dccg);
 
 	kfree(clk_dce);
-	*disp_clk = NULL;
+	*dccg = NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 0e717e0dc8f0..e5e44adc6c27 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -33,6 +33,9 @@
 	.DPREFCLK_CNTL = mmDPREFCLK_CNTL, \
 	.DENTIST_DISPCLK_CNTL = mmDENTIST_DISPCLK_CNTL
 
+#define CLK_COMMON_REG_LIST_DCN_BASE() \
+	SR(DENTIST_DISPCLK_CNTL)
+
 #define CLK_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -40,58 +43,37 @@
 	CLK_SF(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, mask_sh), \
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, mask_sh)
 
+#define CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh) \
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh),\
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh)
+
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
-	type DENTIST_DPREFCLK_WDIVIDER;
+	type DENTIST_DPREFCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_CHG_DONE;
 
-struct dce_disp_clk_shift {
+struct dccg_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
 };
 
-struct dce_disp_clk_mask {
+struct dccg_mask {
 	CLK_REG_FIELD_LIST(uint32_t)
 };
 
-struct dce_disp_clk_registers {
+struct dccg_registers {
 	uint32_t DPREFCLK_CNTL;
 	uint32_t DENTIST_DISPCLK_CNTL;
 };
 
-/* Array identifiers and count for the divider ranges.*/
-enum dce_divider_range_count {
-	DIVIDER_RANGE_01 = 0,
-	DIVIDER_RANGE_02,
-	DIVIDER_RANGE_03,
-	DIVIDER_RANGE_MAX /* == 3*/
-};
-
-enum dce_divider_error_types {
-	INVALID_DID = 0,
-	INVALID_DIVIDER = 1
-};
-
-struct dce_divider_range {
-	int div_range_start;
-	/* The end of this range of dividers.*/
-	int div_range_end;
-	/* The distance between each divider in this range.*/
-	int div_range_step;
-	/* The divider id for the lowest divider.*/
-	int did_min;
-	/* The divider id for the highest divider.*/
-	int did_max;
-};
-
-struct dce_disp_clk {
-	struct display_clock base;
-	const struct dce_disp_clk_registers *regs;
-	const struct dce_disp_clk_shift *clk_shift;
-	const struct dce_disp_clk_mask *clk_mask;
+struct dce_dccg {
+	struct dccg base;
+	const struct dccg_registers *regs;
+	const struct dccg_shift *clk_shift;
+	const struct dccg_mask *clk_mask;
 
 	struct state_dependent_clocks max_clks_by_state[DM_PP_CLOCKS_MAX_STATES];
-	struct dce_divider_range divider_ranges[DIVIDER_RANGE_MAX];
 
-	bool use_max_disp_clk;
 	int dentist_vco_freq_khz;
 
 	/* Cache the status of DFS-bypass feature*/
@@ -106,32 +88,33 @@ struct dce_disp_clk {
 	int dprefclk_ss_percentage;
 	/* DPREFCLK SS percentage Divider (100 or 1000) */
 	int dprefclk_ss_divider;
-
-	/* max disp_clk from PPLIB for max validation display clock*/
-	int max_displ_clk_in_khz;
 };
 
 
-struct display_clock *dce_disp_clk_create(
+struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
-struct display_clock *dce110_disp_clk_create(
+struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
-struct display_clock *dce112_disp_clk_create(
+struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
+
+struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
-struct display_clock *dce120_disp_clk_create(struct dc_context *ctx);
+#ifdef CONFIG_X86
+struct dccg *dcn1_dccg_create(struct dc_context *ctx);
+#endif
 
-void dce_disp_clk_destroy(struct display_clock **disp_clk);
+void dce_dccg_destroy(struct dccg **dccg);
 
 #endif /* _DCE_CLOCKS_H_ */
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 a576b8bbb3cd..062a46543887 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -314,7 +314,7 @@ static void dce_get_psr_wait_loop(
 	return;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static void dcn10_get_dmcu_state(struct dmcu *dmcu)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
@@ -735,7 +735,7 @@ static const struct dmcu_funcs dce_funcs = {
 	.is_dmcu_initialized = dce_is_dmcu_initialized
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static const struct dmcu_funcs dcn10_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -787,7 +787,7 @@ struct dmcu *dce_dmcu_create(
 	return &dmcu_dce->base;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 struct dmcu *dcn10_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
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 057b8afd74bc..64dc75378541 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -147,6 +147,7 @@
 	SR(DCCG_GATE_DISABLE_CNTL2), \
 	SR(DCFCLK_CNTL),\
 	SR(DCFCLK_CNTL), \
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL), \
 	/* todo:  get these from GVM instead of reading registers ourselves */\
 	MMHUB_SR(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32),\
 	MMHUB_SR(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32),\
@@ -249,7 +250,6 @@ struct dce_hwseq_registers {
 	uint32_t DISPCLK_FREQ_CHANGE_CNTL;
 	uint32_t RBBMIF_TIMEOUT_DIS;
 	uint32_t RBBMIF_TIMEOUT_DIS_2;
-	uint32_t DENTIST_DISPCLK_CNTL;
 	uint32_t DCHUBBUB_CRC_CTRL;
 	uint32_t DPP_TOP0_DPP_CRC_CTRL;
 	uint32_t DPP_TOP0_DPP_CRC_VAL_R_G;
@@ -276,6 +276,8 @@ struct dce_hwseq_registers {
 	uint32_t MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB;
 	uint32_t MC_VM_SYSTEM_APERTURE_LOW_ADDR;
 	uint32_t MC_VM_SYSTEM_APERTURE_HIGH_ADDR;
+	uint32_t AZALIA_AUDIO_DTO;
+	uint32_t AZALIA_CONTROLLER_CLOCK_GATING;
 };
  /* set field name */
 #define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@@ -362,7 +364,8 @@ struct dce_hwseq_registers {
 	HWSEQ_PIXEL_RATE_MASK_SH_LIST(mask_sh, OTG0_),\
 	HWS_SF1(OTG0_, PHYPLL_PIXEL_RATE_CNTL, PHYPLL_PIXEL_RATE_SOURCE, mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, mask_sh), \
-	HWS_SF(, DCFCLK_CNTL, DCFCLK_GATE_DIS, mask_sh)
+	HWS_SF(, DCFCLK_CNTL, DCFCLK_GATE_DIS, mask_sh), \
+	HWS_SF(, DC_MEM_GLOBAL_PWR_REQ_CNTL, DC_MEM_GLOBAL_PWR_REQ_DIS, mask_sh)
 
 #define HWSEQ_DCN1_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
@@ -496,14 +499,13 @@ struct dce_hwseq_registers {
 	type DOMAIN7_PGFSM_PWR_STATUS; \
 	type DCFCLK_GATE_DIS; \
 	type DCHUBBUB_GLOBAL_TIMER_REFDIV; \
-	type DENTIST_DPPCLK_WDIVIDER; \
-	type DENTIST_DISPCLK_WDIVIDER; \
 	type VGA_TEST_ENABLE; \
 	type VGA_TEST_RENDER_START; \
 	type D1VGA_MODE_ENABLE; \
 	type D2VGA_MODE_ENABLE; \
 	type D3VGA_MODE_ENABLE; \
-	type D4VGA_MODE_ENABLE;
+	type D4VGA_MODE_ENABLE; \
+	type AZALIA_AUDIO_DTO_MODULE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index dbe3b26b6d9e..60e3c6a73d37 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -646,6 +646,9 @@ static bool dce110_link_encoder_validate_hdmi_output(
 	if (!enc110->base.features.flags.bits.HDMI_6GB_EN &&
 		adjusted_pix_clk_khz >= 300000)
 		return false;
+	if (enc110->base.ctx->dc->debug.hdmi20_disable &&
+		crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 	return true;
 }
 
@@ -773,6 +776,9 @@ void dce110_link_encoder_construct(
 				__func__,
 				result);
 	}
+	if (enc110->base.ctx->dc->debug.hdmi20_disable) {
+		enc110->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
 }
 
 bool dce110_link_encoder_validate_output_with_stream(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index b235a75355b8..85686d917636 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -729,7 +729,7 @@ static bool dce_mi_program_surface_flip_and_addr(
 	return true;
 }
 
-static struct mem_input_funcs dce_mi_funcs = {
+static const struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_program_display_marks = dce_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
@@ -741,6 +741,29 @@ static struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
+static const struct mem_input_funcs dce112_mi_funcs = {
+	.mem_input_program_display_marks = dce112_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
+
+static const struct mem_input_funcs dce120_mi_funcs = {
+	.mem_input_program_display_marks = dce120_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
 
 void dce_mem_input_construct(
 	struct dce_mem_input *dce_mi,
@@ -769,7 +792,7 @@ void dce112_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
-	dce_mi->base.funcs->mem_input_program_display_marks = dce112_mi_program_display_marks;
+	dce_mi->base.funcs = &dce112_mi_funcs;
 }
 
 void dce120_mem_input_construct(
@@ -781,5 +804,5 @@ void dce120_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
-	dce_mi->base.funcs->mem_input_program_display_marks = dce120_mi_program_display_marks;
+	dce_mi->base.funcs = &dce120_mi_funcs;
 }
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 91642e684858..b139b4017820 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
@@ -135,7 +135,7 @@ 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)
+#ifdef CONFIG_X86
 	if (REG(AFMT_VBI_PACKET_CONTROL1)) {
 		switch (packet_index) {
 		case 0:
@@ -229,7 +229,7 @@ static void dce110_update_hdmi_info_packet(
 				HDMI_GENERIC1_SEND, send,
 				HDMI_GENERIC1_LINE, line);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case 4:
 		if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 			REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
@@ -274,7 +274,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	uint32_t h_active_start;
 	uint32_t v_active_start;
 	uint32_t misc0 = 0;
@@ -317,7 +317,7 @@ 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)
+#ifdef CONFIG_X86
 		if (enc110->se_mask->DP_VID_N_MUL)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 #endif
@@ -328,7 +328,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (REG(DP_MSA_MISC))
 		misc1 = REG_READ(DP_MSA_MISC);
 #endif
@@ -362,7 +362,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	/* set dynamic range and YCbCr range */
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_666:
 		colorimetry_bpc = 0;
@@ -441,7 +441,7 @@ 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)
+#ifdef CONFIG_X86
 		if (REG(DP_MSA_COLORIMETRY))
 			REG_SET(DP_MSA_COLORIMETRY, 0, DP_MSA_MISC0, misc0);
 
@@ -476,7 +476,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				crtc_timing->v_front_porch;
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		/* start at begining of left border */
 		if (REG(DP_MSA_TIMING_PARAM2))
 			REG_SET_2(DP_MSA_TIMING_PARAM2, 0,
@@ -751,7 +751,7 @@ 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)
+#ifdef CONFIG_X86
 	if (enc110->se_mask->HDMI_DB_DISABLE) {
 		/* for bring up, disable dp double  TODO */
 		if (REG(HDMI_DB_CONTROL))
@@ -789,7 +789,7 @@ 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)
+#ifdef CONFIG_X86
 	/* 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/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index a02e719d7794..ab63d0d0304c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -155,7 +155,7 @@ static void program_overscan(
 	int overscan_bottom = data->v_active
 			- data->recout.y - data->recout.height;
 
-	if (xfm_dce->base.ctx->dc->debug.surface_visual_confirm) {
+	if (xfm_dce->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 		overscan_bottom += 2;
 		overscan_right += 2;
 	}
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 41f83ecd7469..74c05e878807 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
@@ -125,17 +125,50 @@ static void dce100_pplib_apply_display_requirements(
 	dc->prev_display_config = *pp_display_cfg;
 }
 
+/* unit: in_khz before mode set, get pixel clock from context. ASIC register
+ * may not be programmed yet
+ */
+static uint32_t get_max_pixel_clock_for_all_paths(
+	struct dc *dc,
+	struct dc_state *context)
+{
+	uint32_t max_pix_clk = 0;
+	int i;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		/* do not check under lay */
+		if (pipe_ctx->top_pipe)
+			continue;
+
+		if (pipe_ctx->stream_res.pix_clk_params.requested_pix_clk > max_pix_clk)
+			max_pix_clk =
+				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
+	}
+	return max_pix_clk;
+}
+
 void dce100_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	if (decrease_allowed || context->bw.dce.dispclk_khz > dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-		dc->current_state->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz;
-	}
+	struct dc_clocks req_clks;
+
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
+	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
+
+	dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
+
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
+			&req_clks,
+			decrease_allowed);
+
 	dce100_pplib_apply_display_requirements(dc, context);
 }
 
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 38ec0d609297..c34c9531915e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -52,6 +52,7 @@
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 
 #ifndef mmMC_HUB_RDREQ_DMIF_LIMIT
@@ -135,15 +136,15 @@ static const struct dce110_timing_generator_offsets dce100_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -279,7 +280,20 @@ static const struct dce_opp_shift opp_shift = {
 static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_100(_MASK)
 };
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
 
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
 
 #define audio_regs(id)\
 [id] = {\
@@ -572,6 +586,23 @@ struct output_pixel_processor *dce100_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce100_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 struct clock_source *dce100_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -624,6 +655,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -644,8 +679,8 @@ static void destruct(struct dce110_resource_pool *pool)
 			dce_aud_destroy(&pool->base.audios[i]);
 	}
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.abm != NULL)
 				dce_abm_destroy(&pool->base.abm);
@@ -678,9 +713,22 @@ bool dce100_validate_bandwidth(
 	struct dc  *dc,
 	struct dc_state *context)
 {
-	/* TODO implement when needed but for now hardcode max value*/
-	context->bw.dce.dispclk_khz = 681000;
-	context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+	int i;
+	bool at_least_one_pipe = false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].stream)
+			at_least_one_pipe = true;
+	}
+
+	if (at_least_one_pipe) {
+		/* TODO implement when needed but for now hardcode max value*/
+		context->bw.dce.dispclk_khz = 681000;
+		context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+	} else {
+		context->bw.dce.dispclk_khz = 0;
+		context->bw.dce.yclk_khz = 0;
+	}
 
 	return true;
 }
@@ -817,11 +865,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -851,7 +899,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 	{
 		struct irq_service_init_data init_data;
@@ -915,6 +963,13 @@ static bool construct(
 				"DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+		pool->base.engines[i] = dce100_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
index df027013e50c..1f7f25013217 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
@@ -143,7 +143,7 @@ static void wait_for_fbc_state_changed(
 	struct dce110_compressor *cp110,
 	bool enabled)
 {
-	uint16_t counter = 0;
+	uint32_t counter = 0;
 	uint32_t addr = mmFBC_STATUS;
 	uint32_t value;
 
@@ -158,7 +158,7 @@ static void wait_for_fbc_state_changed(
 		counter++;
 	}
 
-	if (counter == 10) {
+	if (counter == 1000) {
 		DC_LOG_WARNING("%s: wait counter exceeded, changes to HW not applied",
 			__func__);
 	} else {
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 353ffcbdf5ba..33a14e163f88 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
@@ -864,17 +864,22 @@ void hwss_edp_power_control(
 		if (power_up) {
 			unsigned long long current_ts = dm_get_timestamp(ctx);
 			unsigned long long duration_in_ms =
-					dm_get_elapse_time_in_ns(
+					div64_u64(dm_get_elapse_time_in_ns(
 							ctx,
 							current_ts,
-							div64_u64(link->link_trace.time_stamp.edp_poweroff, 1000000));
+							link->link_trace.time_stamp.edp_poweroff), 1000000);
 			unsigned long long wait_time_ms = 0;
 
 			/* max 500ms from LCDVDD off to on */
+			unsigned long long edp_poweroff_time_ms = 500;
+
+			if (link->local_sink != NULL)
+				edp_poweroff_time_ms =
+						500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms;
 			if (link->link_trace.time_stamp.edp_poweroff == 0)
-				wait_time_ms = 500;
-			else if (duration_in_ms < 500)
-				wait_time_ms = 500 - duration_in_ms;
+				wait_time_ms = edp_poweroff_time_ms;
+			else if (duration_in_ms < edp_poweroff_time_ms)
+				wait_time_ms = edp_poweroff_time_ms - duration_in_ms;
 
 			if (wait_time_ms) {
 				msleep(wait_time_ms);
@@ -1245,13 +1250,13 @@ static void program_scaler(const struct dc *dc,
 {
 	struct tg_color color = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	/* TOFPGA */
 	if (pipe_ctx->plane_res.xfm->funcs->transform_set_pixel_storage_depth == NULL)
 		return;
 #endif
 
-	if (dc->debug.surface_visual_confirm)
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE)
 		get_surface_visual_confirm_color(pipe_ctx, &color);
 	else
 		color_space_to_black_color(dc,
@@ -1475,7 +1480,7 @@ static void power_down_controllers(struct dc *dc)
 {
 	int i;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		dc->res_pool->timing_generators[i]->funcs->disable_crtc(
 				dc->res_pool->timing_generators[i]);
 	}
@@ -1515,12 +1520,13 @@ static void disable_vga_and_power_gate_all_controllers(
 	struct timing_generator *tg;
 	struct dc_context *ctx = dc->ctx;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		tg = dc->res_pool->timing_generators[i];
 
 		if (tg->funcs->disable_vga)
 			tg->funcs->disable_vga(tg);
-
+	}
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		/* Enable CLOCK gating for each pipe BEFORE controller
 		 * powergating. */
 		enable_display_pipe_clock_gating(ctx,
@@ -1663,7 +1669,7 @@ static void dce110_set_displaymarks(
 	}
 }
 
-static void set_safe_displaymarks(
+void dce110_set_safe_displaymarks(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool)
 {
@@ -1755,23 +1761,15 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 }
 
 /* unit: in_khz before mode set, get pixel clock from context. ASIC register
- * may not be programmed yet.
- * TODO: after mode set, pre_mode_set = false,
- * may read PLL register to get pixel clock
+ * may not be programmed yet
  */
 static uint32_t get_max_pixel_clock_for_all_paths(
 	struct dc *dc,
-	struct dc_state *context,
-	bool pre_mode_set)
+	struct dc_state *context)
 {
 	uint32_t max_pix_clk = 0;
 	int i;
 
-	if (!pre_mode_set) {
-		/* TODO: read ASIC register to get pixel clock */
-		ASSERT(0);
-	}
-
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
@@ -1787,95 +1785,10 @@ static uint32_t get_max_pixel_clock_for_all_paths(
 				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
 	}
 
-	if (max_pix_clk == 0)
-		ASSERT(0);
-
 	return max_pix_clk;
 }
 
 /*
- * Find clock state based on clock requested. if clock value is 0, simply
- * set clock state as requested without finding clock state by clock value
- */
-
-static void apply_min_clocks(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dm_pp_clocks_state *clocks_state,
-	bool pre_mode_set)
-{
-	struct state_dependent_clocks req_clocks = {0};
-
-	if (!pre_mode_set) {
-		/* set clock_state without verification */
-		if (context->dis_clk->funcs->set_min_clocks_state) {
-			context->dis_clk->funcs->set_min_clocks_state(
-						context->dis_clk, *clocks_state);
-			return;
-		}
-
-		/* TODO: This is incorrect. Figure out how to fix. */
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				context->dis_clk->cur_clocks_value.dispclk_in_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_PIXELCLK,
-				context->dis_clk->cur_clocks_value.max_pixelclk_in_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				context->dis_clk->cur_clocks_value.max_non_dp_phyclk_in_khz,
-				pre_mode_set,
-				false);
-		return;
-	}
-
-	/* get the required state based on state dependent clocks:
-	 * display clock and pixel clock
-	 */
-	req_clocks.display_clk_khz = context->bw.dce.dispclk_khz;
-
-	req_clocks.pixel_clk_khz = get_max_pixel_clock_for_all_paths(
-			dc, context, true);
-
-	if (context->dis_clk->funcs->get_required_clocks_state) {
-		*clocks_state = context->dis_clk->funcs->get_required_clocks_state(
-				context->dis_clk, &req_clocks);
-		context->dis_clk->funcs->set_min_clocks_state(
-			context->dis_clk, *clocks_state);
-	} else {
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				req_clocks.display_clk_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_PIXELCLK,
-				req_clocks.pixel_clk_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				req_clocks.pixel_clk_khz,
-				pre_mode_set,
-				false);
-	}
-}
-
-/*
  *  Check if FBC can be enabled
  */
 static bool should_enable_fbc(struct dc *dc,
@@ -2093,7 +2006,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 	struct dc_bios *dcb = dc->ctx->dc_bios;
 	enum dc_status status;
 	int i;
-	enum dm_pp_clocks_state clocks_state = DM_PP_CLOCKS_STATE_INVALID;
 
 	/* Reset old context */
 	/* look up the targets that have been removed since last commit */
@@ -2127,55 +2039,9 @@ enum dc_status dce110_apply_ctx_to_hw(
 				PIPE_GATING_CONTROL_DISABLE);
 	}
 
-	set_safe_displaymarks(&context->res_ctx, dc->res_pool);
-
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
 
-	/*TODO: when pplib works*/
-	apply_min_clocks(dc, context, &clocks_state, true);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	if (dc->ctx->dce_version >= DCN_VERSION_1_0) {
-		if (context->bw.dcn.calc_clk.fclk_khz
-				> dc->current_state->bw.dcn.cur_clk.fclk_khz) {
-			struct dm_pp_clock_for_voltage_req clock;
-
-			clock.clk_type = DM_PP_CLOCK_TYPE_FCLK;
-			clock.clocks_in_khz = context->bw.dcn.calc_clk.fclk_khz;
-			dm_pp_apply_clock_for_voltage_request(dc->ctx, &clock);
-			dc->current_state->bw.dcn.cur_clk.fclk_khz = clock.clocks_in_khz;
-			context->bw.dcn.cur_clk.fclk_khz = clock.clocks_in_khz;
-		}
-		if (context->bw.dcn.calc_clk.dcfclk_khz
-				> dc->current_state->bw.dcn.cur_clk.dcfclk_khz) {
-			struct dm_pp_clock_for_voltage_req clock;
-
-			clock.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-			clock.clocks_in_khz = context->bw.dcn.calc_clk.dcfclk_khz;
-			dm_pp_apply_clock_for_voltage_request(dc->ctx, &clock);
-			dc->current_state->bw.dcn.cur_clk.dcfclk_khz = clock.clocks_in_khz;
-			context->bw.dcn.cur_clk.dcfclk_khz = clock.clocks_in_khz;
-		}
-		if (context->bw.dcn.calc_clk.dispclk_khz
-				> dc->current_state->bw.dcn.cur_clk.dispclk_khz) {
-			dc->res_pool->display_clock->funcs->set_clock(
-					dc->res_pool->display_clock,
-					context->bw.dcn.calc_clk.dispclk_khz);
-			dc->current_state->bw.dcn.cur_clk.dispclk_khz =
-					context->bw.dcn.calc_clk.dispclk_khz;
-			context->bw.dcn.cur_clk.dispclk_khz =
-					context->bw.dcn.calc_clk.dispclk_khz;
-		}
-	} else
-#endif
-	if (context->bw.dce.dispclk_khz
-			> dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-	}
-
 	dce110_setup_audio_dto(dc, context);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -2204,9 +2070,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 			return status;
 	}
 
-	/* to save power */
-	apply_min_clocks(dc, context, &clocks_state, false);
-
 	dcb->funcs->set_scratch_critical_state(dcb, false);
 
 	if (dc->fbc_compressor)
@@ -2694,15 +2557,20 @@ static void dce110_set_bandwidth(
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	dce110_set_displaymarks(dc, context);
+	struct dc_clocks req_clks;
 
-	if (decrease_allowed || context->bw.dce.dispclk_khz > dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-		dc->current_state->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz;
-	}
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
+	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
+
+	if (decrease_allowed)
+		dce110_set_displaymarks(dc, context);
+	else
+		dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
 
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
+			&req_clks,
+			decrease_allowed);
 	pplib_apply_display_requirements(dc, context);
 }
 
@@ -2938,9 +2806,11 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	struct dc_cursor_mi_param param = {
 		.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz,
 		.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz,
-		.viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x,
-		.viewport_width = pipe_ctx->plane_res.scl_data.viewport.width,
-		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz
+		.viewport = pipe_ctx->plane_res.scl_data.viewport,
+		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
+		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
+		.rotation = pipe_ctx->plane_state->rotation,
+		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
 	if (pipe_ctx->plane_state->address.type
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 f48d5a68d238..d6db3dbd9015 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
@@ -60,6 +60,10 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context);
 
 void dce110_power_down(struct dc *dc);
 
+void dce110_set_safe_displaymarks(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool);
+
 void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
index 0564c8e31252..9b9fc3d96c07 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
@@ -1011,7 +1011,7 @@ void dce110_free_mem_input_v(
 {
 }
 
-static struct mem_input_funcs dce110_mem_input_v_funcs = {
+static const struct mem_input_funcs dce110_mem_input_v_funcs = {
 	.mem_input_program_display_marks =
 			dce_mem_input_v_program_display_marks,
 	.mem_input_program_chroma_display_marks =
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 20c029089551..4a665a29191b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -49,6 +49,7 @@
 #include "dce/dce_clock_source.h"
 #include "dce/dce_hwseq.h"
 #include "dce110/dce110_hw_sequencer.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
 
@@ -146,15 +147,15 @@ static const struct dce110_timing_generator_offsets dce110_tg_offsets[] = {
 #define SRI(reg_name, block, id)\
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -306,6 +307,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_110(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -588,6 +604,23 @@ static struct output_pixel_processor *dce110_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce110_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 struct clock_source *dce110_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -651,6 +684,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -679,8 +716,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -794,43 +831,38 @@ static bool dce110_validate_bandwidth(
 
 	if (memcmp(&dc->current_state->bw.dce,
 			&context->bw.dce, sizeof(context->bw.dce))) {
-		struct log_entry log_entry;
-		dm_logger_open(
-			dc->ctx->logger,
-			&log_entry,
-			LOG_BANDWIDTH_CALCS);
-		dm_logger_append(&log_entry, "%s: finish,\n"
+
+		DC_LOG_BANDWIDTH_CALCS(
+			"%s: finish,\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
 			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n"
+			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
+			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n"
+			,
 			__func__,
 			context->bw.dce.nbp_state_change_wm_ns[0].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[0].a_mark,
 			context->bw.dce.urgent_wm_ns[0].b_mark,
 			context->bw.dce.urgent_wm_ns[0].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[0].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[0].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[0].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].a_mark,
 			context->bw.dce.urgent_wm_ns[1].b_mark,
 			context->bw.dce.urgent_wm_ns[1].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[1].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[1].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[1].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].a_mark,
 			context->bw.dce.urgent_wm_ns[2].b_mark,
 			context->bw.dce.urgent_wm_ns[2].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].b_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].a_mark,
-			context->bw.dce.stutter_mode_enable);
-		dm_logger_append(&log_entry,
-			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
-			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n",
+			context->bw.dce.stutter_mode_enable,
 			context->bw.dce.cpuc_state_change_enable,
 			context->bw.dce.cpup_state_change_enable,
 			context->bw.dce.nbp_state_change_enable,
@@ -840,7 +872,6 @@ static bool dce110_validate_bandwidth(
 			context->bw.dce.sclk_deep_sleep_khz,
 			context->bw.dce.yclk_khz,
 			context->bw.dce.blackout_recovery_time_us);
-		dm_logger_close(&log_entry);
 	}
 	return result;
 }
@@ -1179,11 +1210,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce110_disp_clk_create(ctx,
+	pool->base.dccg = dce110_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1213,7 +1244,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 				static_clk_info.max_clocks_state;
 
 	{
@@ -1264,6 +1295,14 @@ static bool construct(
 				"DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+
+		pool->base.engines[i] = dce110_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->fbc_compressor = dce110_compressor_create(ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
index a7dce060204f..aa8d6b10d2c3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
@@ -235,7 +235,7 @@ static void program_overscan(
 	int overscan_right = data->h_active - data->recout.x - data->recout.width;
 	int overscan_bottom = data->v_active - data->recout.y - data->recout.height;
 
-	if (xfm_dce->base.ctx->dc->debug.surface_visual_confirm) {
+	if (xfm_dce->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 		overscan_bottom += 2;
 		overscan_right += 2;
 	}
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 00c0a1ef15eb..caf90ae2cbb0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -49,6 +49,7 @@
 #include "dce112/dce112_hw_sequencer.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 #include "reg_helper.h"
 
@@ -146,15 +147,15 @@ static const struct dce110_timing_generator_offsets dce112_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -314,6 +315,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_112(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -588,6 +604,23 @@ struct output_pixel_processor *dce112_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce112_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 struct clock_source *dce112_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -625,6 +658,9 @@ static void destruct(struct dce110_resource_pool *pool)
 		if (pool->base.opps[i] != NULL)
 			dce110_opp_destroy(&pool->base.opps[i]);
 
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 		if (pool->base.transforms[i] != NULL)
 			dce112_transform_destroy(&pool->base.transforms[i]);
 
@@ -640,6 +676,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -668,8 +708,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -744,43 +784,38 @@ bool dce112_validate_bandwidth(
 
 	if (memcmp(&dc->current_state->bw.dce,
 			&context->bw.dce, sizeof(context->bw.dce))) {
-		struct log_entry log_entry;
-		dm_logger_open(
-			dc->ctx->logger,
-			&log_entry,
-			LOG_BANDWIDTH_CALCS);
-		dm_logger_append(&log_entry, "%s: finish,\n"
+
+		DC_LOG_BANDWIDTH_CALCS(
+			"%s: finish,\n"
 			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n"
+			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
+			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n"
+			,
 			__func__,
 			context->bw.dce.nbp_state_change_wm_ns[0].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[0].a_mark,
 			context->bw.dce.urgent_wm_ns[0].b_mark,
 			context->bw.dce.urgent_wm_ns[0].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[0].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[0].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[0].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].a_mark,
 			context->bw.dce.urgent_wm_ns[1].b_mark,
 			context->bw.dce.urgent_wm_ns[1].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[1].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[1].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[1].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].a_mark,
 			context->bw.dce.urgent_wm_ns[2].b_mark,
 			context->bw.dce.urgent_wm_ns[2].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].b_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].a_mark,
-			context->bw.dce.stutter_mode_enable);
-		dm_logger_append(&log_entry,
-			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
-			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n",
+			context->bw.dce.stutter_mode_enable,
 			context->bw.dce.cpuc_state_change_enable,
 			context->bw.dce.cpup_state_change_enable,
 			context->bw.dce.nbp_state_change_enable,
@@ -790,7 +825,6 @@ bool dce112_validate_bandwidth(
 			context->bw.dce.sclk_deep_sleep_khz,
 			context->bw.dce.yclk_khz,
 			context->bw.dce.blackout_recovery_time_us);
-		dm_logger_close(&log_entry);
 	}
 	return result;
 }
@@ -1000,7 +1034,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[0].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[0].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -1010,7 +1044,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[1].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[1].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[1].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[1].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -1020,7 +1054,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[2].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[2].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[2].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[2].wm_max_mem_clk_in_khz = 5000000;
@@ -1030,7 +1064,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[3].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[3].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_mem_clk_in_khz = 5000000;
@@ -1124,11 +1158,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce112_disp_clk_create(ctx,
+	pool->base.dccg = dce112_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1158,7 +1192,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 				static_clk_info.max_clocks_state;
 
 	{
@@ -1214,6 +1248,13 @@ static bool construct(
 				"DC:failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+		pool->base.engines[i] = dce112_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
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 2d58daccc005..f7d02f2190d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -53,6 +53,7 @@
 #include "dce/dce_hwseq.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 #include "dce/dce_12_0_offset.h"
 #include "dce/dce_12_0_sh_mask.h"
@@ -297,6 +298,20 @@ static const struct dce_opp_shift opp_shift = {
 static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_120(_MASK)
 };
+ #define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
 
 #define audio_regs(id)\
 [id] = {\
@@ -361,6 +376,22 @@ struct output_pixel_processor *dce120_opp_create(
 			     ctx, inst, &opp_regs[inst], &opp_shift, &opp_mask);
 	return &opp->base;
 }
+struct engine *dce120_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
 
 static const struct bios_registers bios_regs = {
 	.BIOS_SCRATCH_6 = mmBIOS_SCRATCH_6 + NBIO_BASE(mmBIOS_SCRATCH_6_BASE_IDX)
@@ -373,7 +404,7 @@ static const struct resource_caps res_cap = {
 		.num_pll = 6,
 };
 
-static const struct dc_debug debug_defaults = {
+static const struct dc_debug_options debug_defaults = {
 		.disable_clock_gate = true,
 };
 
@@ -467,6 +498,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.audio_count; i++) {
@@ -494,8 +529,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 }
 
 static void read_dce_straps(
@@ -775,7 +810,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[0].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[0].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -785,7 +820,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[1].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[1].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[1].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[1].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -795,7 +830,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[2].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[2].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[2].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[2].wm_max_mem_clk_in_khz = 5000000;
@@ -805,7 +840,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[3].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[3].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_mem_clk_in_khz = 5000000;
@@ -894,11 +929,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce120_disp_clk_create(ctx);
-	if (pool->base.display_clock == NULL) {
+	pool->base.dccg = dce120_dccg_create(ctx);
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
-		goto disp_clk_create_fail;
+		goto dccg_create_fail;
 	}
 
 	pool->base.dmcu = dce_dmcu_create(ctx,
@@ -984,6 +1019,13 @@ static bool construct(
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
 		}
+		pool->base.engines[i] = dce120_aux_engine_create(ctx, i);
+				if (pool->base.engines[i] == NULL) {
+					BREAK_TO_DEBUGGER();
+					dm_error(
+						"DC:failed to create aux engine!!\n");
+					goto res_create_fail;
+				}
 
 		/* check next valid pipe */
 		j++;
@@ -1011,7 +1053,7 @@ static bool construct(
 
 irqs_create_fail:
 controller_create_fail:
-disp_clk_create_fail:
+dccg_create_fail:
 clk_src_create_fail:
 res_create_fail:
 
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 48a068964722..6fb33ad2d3c8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -54,6 +54,7 @@
 #include "reg_helper.h"
 
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 /* TODO remove this include */
 
@@ -153,15 +154,15 @@ static const struct dce110_timing_generator_offsets dce80_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
@@ -298,6 +299,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_80(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -448,6 +464,23 @@ static struct output_pixel_processor *dce80_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce80_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 static struct stream_encoder *dce80_stream_encoder_create(
 	enum engine_id eng_id,
 	struct dc_context *ctx)
@@ -655,6 +688,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -683,8 +719,8 @@ static void destruct(struct dce110_resource_pool *pool)
 		}
 	}
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -822,11 +858,11 @@ static bool dce80_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -852,7 +888,7 @@ static bool dce80_construct(
 		goto res_create_fail;
 	}
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -899,6 +935,14 @@ static bool dce80_construct(
 			dm_error("DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+
+		pool->base.engines[i] = dce80_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
@@ -1006,11 +1050,11 @@ static bool dce81_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1037,7 +1081,7 @@ static bool dce81_construct(
 	}
 
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -1187,11 +1231,11 @@ static bool dce83_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1218,7 +1262,7 @@ static bool dce83_construct(
 	}
 
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
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 c69fa4bfab0a..bf8b68f8db4f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -145,10 +145,10 @@ static bool dpp_get_optimal_number_of_taps(
 		pixel_width = scl_data->viewport.width;
 
 	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
-	if (scl_data->viewport.width  != scl_data->h_active &&
-		scl_data->viewport.height != scl_data->v_active &&
+	if (scl_data->format == PIXEL_FORMAT_FP16 &&
 		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
-		scl_data->format == PIXEL_FORMAT_FP16)
+		scl_data->ratios.horz.value != dc_fixpt_one.value &&
+		scl_data->ratios.vert.value != dc_fixpt_one.value)
 		return false;
 
 	if (scl_data->viewport.width > scl_data->h_active &&
@@ -445,10 +445,10 @@ void dpp1_set_cursor_position(
 		uint32_t width)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	int src_x_offset = pos->x - pos->x_hotspot - param->viewport_x_start;
+	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
 	uint32_t cur_en = pos->enable ? 1 : 0;
 
-	if (src_x_offset >= (int)param->viewport_width)
+	if (src_x_offset >= (int)param->viewport.width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
 	if (src_x_offset + (int)width <= 0)
@@ -459,6 +459,18 @@ void dpp1_set_cursor_position(
 
 }
 
+void dpp1_cnv_set_optional_cursor_attributes(
+		struct dpp *dpp_base,
+		struct dpp_cursor_attributes *attr)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	if (attr) {
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_BIAS,  attr->bias);
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_SCALE, attr->scale);
+	}
+}
+
 void dpp1_dppclk_control(
 		struct dpp *dpp_base,
 		bool dppclk_div,
@@ -499,6 +511,7 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_full_bypass		= dpp1_full_bypass,
 		.set_cursor_attributes = dpp1_set_cursor_attributes,
 		.set_cursor_position = dpp1_set_cursor_position,
+		.set_optional_cursor_attributes = dpp1_cnv_set_optional_cursor_attributes,
 		.dpp_dppclk_control = dpp1_dppclk_control,
 		.dpp_set_hdr_multiplier = dpp1_set_hdr_multiplier,
 };
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 e862cafa6501..e2889e61b18c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -119,6 +119,7 @@
 	SRI(CURSOR0_CONTROL, CNVC_CUR, id), \
 	SRI(CURSOR0_COLOR0, CNVC_CUR, id), \
 	SRI(CURSOR0_COLOR1, CNVC_CUR, id), \
+	SRI(CURSOR0_FP_SCALE_BIAS, CNVC_CUR, id), \
 	SRI(DPP_CONTROL, DPP_TOP, id), \
 	SRI(CM_HDR_MULT_COEF, CM, id)
 
@@ -324,6 +325,8 @@
 	TF_SF(CNVC_CUR0_CURSOR0_CONTROL, CUR0_ENABLE, mask_sh), \
 	TF_SF(CNVC_CUR0_CURSOR0_COLOR0, CUR0_COLOR0, mask_sh), \
 	TF_SF(CNVC_CUR0_CURSOR0_COLOR1, CUR0_COLOR1, mask_sh), \
+	TF_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_BIAS, mask_sh), \
+	TF_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, mask_sh), \
 	TF_SF(DPP_TOP0_DPP_CONTROL, DPP_CLOCK_ENABLE, mask_sh), \
 	TF_SF(CM0_CM_HDR_MULT_COEF, CM_HDR_MULT_COEF, mask_sh)
 
@@ -1076,7 +1079,9 @@
 	type CUR0_COLOR1; \
 	type DPPCLK_RATE_CONTROL; \
 	type DPP_CLOCK_ENABLE; \
-	type CM_HDR_MULT_COEF;
+	type CM_HDR_MULT_COEF; \
+	type CUR0_FP_BIAS; \
+	type CUR0_FP_SCALE;
 
 struct dcn_dpp_shift {
 	TF_REG_FIELD_LIST(uint8_t)
@@ -1329,7 +1334,8 @@ struct dcn_dpp_mask {
 	uint32_t CURSOR0_COLOR0; \
 	uint32_t CURSOR0_COLOR1; \
 	uint32_t DPP_CONTROL; \
-	uint32_t CM_HDR_MULT_COEF;
+	uint32_t CM_HDR_MULT_COEF; \
+	uint32_t CURSOR0_FP_SCALE_BIAS;
 
 struct dcn_dpp_registers {
 	DPP_COMMON_REG_VARIABLE_LIST
@@ -1370,6 +1376,10 @@ void dpp1_set_cursor_position(
 		const struct dc_cursor_mi_param *param,
 		uint32_t width);
 
+void dpp1_cnv_set_optional_cursor_attributes(
+			struct dpp *dpp_base,
+			struct dpp_cursor_attributes *attr);
+
 bool dpp1_dscl_is_lb_conf_valid(
 		int ceil_vratio,
 		int num_partitions,
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 f862fd148cca..4a863a5dab41 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
@@ -621,6 +621,10 @@ static void dpp1_dscl_set_manual_ratio_init(
 static void dpp1_dscl_set_recout(
 			struct dcn10_dpp *dpp, const struct rect *recout)
 {
+	int visual_confirm_on = 0;
+	if (dpp->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE)
+		visual_confirm_on = 1;
+
 	REG_SET_2(RECOUT_START, 0,
 		/* First pixel of RECOUT */
 			 RECOUT_START_X, recout->x,
@@ -632,8 +636,7 @@ static void dpp1_dscl_set_recout(
 			 RECOUT_WIDTH, recout->width,
 		/* Number of RECOUT vertical lines */
 			 RECOUT_HEIGHT, recout->height
-			 - dpp->base.ctx->dc->debug.surface_visual_confirm * 4 *
-			 (dpp->base.inst + 1));
+			 - visual_confirm_on * 4 * (dpp->base.inst + 1));
 }
 
 /* Main function to program scaler and line buffer in manual scaling mode */
@@ -655,6 +658,12 @@ void dpp1_dscl_set_scaler_manual_scale(
 
 	dpp->scl_data = *scl_data;
 
+	/* Autocal off */
+	REG_SET_3(DSCL_AUTOCAL, 0,
+		AUTOCAL_MODE, AUTOCAL_MODE_OFF,
+		AUTOCAL_NUM_PIPE, 0,
+		AUTOCAL_PIPE_ID, 0);
+
 	/* Recout */
 	dpp1_dscl_set_recout(dpp, &scl_data->recout);
 
@@ -678,12 +687,6 @@ void dpp1_dscl_set_scaler_manual_scale(
 	if (dscl_mode == DSCL_MODE_SCALING_444_BYPASS)
 		return;
 
-	/* Autocal off */
-	REG_SET_3(DSCL_AUTOCAL, 0,
-		AUTOCAL_MODE, AUTOCAL_MODE_OFF,
-		AUTOCAL_NUM_PIPE, 0,
-		AUTOCAL_PIPE_ID, 0);
-
 	/* Black offsets */
 	if (ycbcr)
 		REG_SET_2(SCL_BLACK_OFFSET, 0,
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 943143efbb82..1ea91e153d3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -190,10 +190,17 @@ static uint32_t convert_and_clamp(
 }
 
 
+void hubbub1_wm_change_req_wa(struct hubbub *hubbub)
+{
+	REG_UPDATE_SEQ(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0, 1);
+}
+
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz)
+		unsigned int refclk_mhz,
+		bool safe_to_lower)
 {
 	uint32_t force_en = hubbub->ctx->dc->debug.disable_stutter ? 1 : 0;
 	/*
@@ -202,191 +209,259 @@ void hubbub1_program_watermarks(
 	 */
 	uint32_t prog_wm_value;
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0);
 
 	/* Repeat for water mark set A, B, C and D. */
 	/* clock state A */
-	prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
-
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->a.urgent_ns > hubbub->watermarks.a.urgent_ns) {
+		hubbub->watermarks.a.urgent_ns = watermarks->a.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
 
-	prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->a.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->a.pte_meta_urgent_ns > hubbub->watermarks.a.pte_meta_urgent_ns) {
+		hubbub->watermarks.a.pte_meta_urgent_ns = watermarks->a.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+	}
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
+		if (safe_to_lower || watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->a.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.a.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.a.cstate_pstate.cstate_exit_ns =
+					watermarks->a.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->a.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_A calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->a.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.a.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.a.cstate_pstate.pstate_change_ns =
+				watermarks->a.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_exit_ns,
+				watermarks->a.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_A calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->a.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-
 	/* clock state B */
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->b.urgent_ns > hubbub->watermarks.b.urgent_ns) {
+		hubbub->watermarks.b.urgent_ns = watermarks->b.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->b.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->b.pte_meta_urgent_ns > hubbub->watermarks.b.pte_meta_urgent_ns) {
+		hubbub->watermarks.b.pte_meta_urgent_ns = watermarks->b.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_B calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+	}
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
+		if (safe_to_lower || watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_B calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->b.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.b.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.b.cstate_pstate.cstate_exit_ns =
+					watermarks->b.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->b.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_B calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->b.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.b.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.b.cstate_pstate.pstate_change_ns =
+				watermarks->b.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_exit_ns,
+				watermarks->b.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_B calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	/* clock state C */
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->c.urgent_ns > hubbub->watermarks.c.urgent_ns) {
+		hubbub->watermarks.c.urgent_ns = watermarks->c.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->c.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->c.pte_meta_urgent_ns > hubbub->watermarks.c.pte_meta_urgent_ns) {
+		hubbub->watermarks.c.pte_meta_urgent_ns = watermarks->c.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_C calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
+		if (safe_to_lower || watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_C calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
+
+		if (safe_to_lower || watermarks->c.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.c.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.c.cstate_pstate.cstate_exit_ns =
+					watermarks->c.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->c.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_C calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->c.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.c.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.c.cstate_pstate.pstate_change_ns =
+				watermarks->c.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_exit_ns,
+				watermarks->c.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_C calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	/* clock state D */
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.urgent_ns, prog_wm_value);
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.pte_meta_urgent_ns, prog_wm_value);
-
-
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->d.urgent_ns > hubbub->watermarks.d.urgent_ns) {
+		hubbub->watermarks.d.urgent_ns = watermarks->d.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_D calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->d.urgent_ns, prog_wm_value);
+	}
 
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_exit_ns,
+	if (safe_to_lower || watermarks->d.pte_meta_urgent_ns > hubbub->watermarks.d.pte_meta_urgent_ns) {
+		hubbub->watermarks.d.pte_meta_urgent_ns = watermarks->d.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_D calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+			watermarks->d.pte_meta_urgent_ns, prog_wm_value);
 	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
+		if (safe_to_lower || watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_D calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
+		if (safe_to_lower || watermarks->d.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.d.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.d.cstate_pstate.cstate_exit_ns =
+					watermarks->d.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->d.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_D calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
+	if (safe_to_lower || watermarks->d.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.d.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.d.cstate_pstate.pstate_change_ns =
+				watermarks->d.cstate_pstate.pstate_change_ns;
+		prog_wm_value = convert_and_clamp(
+				watermarks->d.cstate_pstate.pstate_change_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
+	}
 
 	REG_UPDATE(DCHUBBUB_ARB_SAT_LEVEL,
 			DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
@@ -408,6 +483,11 @@ void hubbub1_update_dchub(
 	struct hubbub *hubbub,
 	struct dchub_init_data *dh_data)
 {
+	if (REG(DCHUBBUB_SDPIF_FB_TOP) == 0) {
+		ASSERT(false);
+		/*should not come here*/
+		return;
+	}
 	/* TODO: port code from dal2 */
 	switch (dh_data->fb_mode) {
 	case FRAME_BUFFER_MODE_ZFB_ONLY:
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 6315a0e6b0d6..d6e596eef4c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -185,6 +185,7 @@ struct hubbub {
 	const struct dcn_hubbub_shift *shifts;
 	const struct dcn_hubbub_mask *masks;
 	unsigned int debug_test_index_pstate;
+	struct dcn_watermark_set watermarks;
 };
 
 void hubbub1_update_dchub(
@@ -194,10 +195,13 @@ void hubbub1_update_dchub(
 bool hubbub1_verify_allow_pstate_change_high(
 	struct hubbub *hubbub);
 
+void hubbub1_wm_change_req_wa(struct hubbub *hubbub);
+
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz);
+		unsigned int refclk_mhz,
+		bool safe_to_lower);
 
 void hubbub1_toggle_watermark_change_req(
 		struct hubbub *hubbub);
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 c28085be39ff..2138cd3c5d1d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -152,21 +152,19 @@ void hubp1_program_tiling(
 			PIPE_ALIGNED, info->gfx9.pipe_aligned);
 }
 
-void hubp1_program_size_and_rotation(
+void hubp1_program_size(
 	struct hubp *hubp,
-	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
-	struct dc_plane_dcc_param *dcc,
-	bool horizontal_mirror)
+	struct dc_plane_dcc_param *dcc)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c, mirror;
+	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c;
 
 	/* Program data and meta surface pitch (calculation from addrlib)
 	 * 444 or 420 luma
 	 */
-	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
+	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN && format < SURFACE_PIXEL_FORMAT_SUBSAMPLE_END) {
 		ASSERT(plane_size->video.chroma_pitch != 0);
 		/* Chroma pitch zero can cause system hang! */
 
@@ -192,13 +190,22 @@ void hubp1_program_size_and_rotation(
 	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
 		REG_UPDATE_2(DCSURF_SURFACE_PITCH_C,
 			PITCH_C, pitch_c, META_PITCH_C, meta_pitch_c);
+}
+
+void hubp1_program_rotation(
+	struct hubp *hubp,
+	enum dc_rotation_angle rotation,
+	bool horizontal_mirror)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+	uint32_t mirror;
+
 
 	if (horizontal_mirror)
 		mirror = 1;
 	else
 		mirror = 0;
 
-
 	/* Program rotation angle and horz mirror - no mirror */
 	if (rotation == ROTATION_ANGLE_0)
 		REG_UPDATE_2(DCSURF_SURFACE_CONFIG,
@@ -287,6 +294,10 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 66);
 		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888:
+		REG_UPDATE(DCSURF_SURFACE_CONFIG,
+				SURFACE_PIXEL_FORMAT, 12);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
@@ -450,9 +461,6 @@ bool hubp1_program_surface_flip_and_addr(
 
 	hubp->request_address = *address;
 
-	if (flip_immediate)
-		hubp->current_address = *address;
-
 	return true;
 }
 
@@ -481,8 +489,8 @@ void hubp1_program_surface_config(
 {
 	hubp1_dcc_control(hubp, dcc->enable, dcc->grph.independent_64b_blks);
 	hubp1_program_tiling(hubp, tiling_info, format);
-	hubp1_program_size_and_rotation(
-			hubp, rotation, format, plane_size, dcc, horizontal_mirror);
+	hubp1_program_size(hubp, format, plane_size, dcc);
+	hubp1_program_rotation(hubp, rotation, horizontal_mirror);
 	hubp1_program_pixel_format(hubp, format);
 }
 
@@ -688,7 +696,6 @@ bool hubp1_is_flip_pending(struct hubp *hubp)
 	if (earliest_inuse_address.grph.addr.quad_part != hubp->request_address.grph.addr.quad_part)
 		return true;
 
-	hubp->current_address = hubp->request_address;
 	return false;
 }
 
@@ -1061,9 +1068,11 @@ void hubp1_cursor_set_position(
 		const struct dc_cursor_mi_param *param)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	int src_x_offset = pos->x - pos->x_hotspot - param->viewport_x_start;
+	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
+	int x_hotspot = pos->x_hotspot;
+	int y_hotspot = pos->y_hotspot;
+	uint32_t dst_x_offset;
 	uint32_t cur_en = pos->enable ? 1 : 0;
-	uint32_t dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 
 	/*
 	 * Guard aganst cursor_set_position() from being called with invalid
@@ -1075,6 +1084,18 @@ void hubp1_cursor_set_position(
 	if (hubp->curs_attr.address.quad_part == 0)
 		return;
 
+	if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) {
+		src_x_offset = pos->y - pos->y_hotspot - param->viewport.x;
+		y_hotspot = pos->x_hotspot;
+		x_hotspot = pos->y_hotspot;
+	}
+
+	if (param->mirror) {
+		x_hotspot = param->viewport.width - x_hotspot;
+		src_x_offset = param->viewport.x + param->viewport.width - src_x_offset;
+	}
+
+	dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 	dst_x_offset *= param->ref_clk_khz;
 	dst_x_offset /= param->pixel_clk_khz;
 
@@ -1085,7 +1106,7 @@ void hubp1_cursor_set_position(
 				dc_fixpt_from_int(dst_x_offset),
 				param->h_scale_ratio));
 
-	if (src_x_offset >= (int)param->viewport_width)
+	if (src_x_offset >= (int)param->viewport.width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
 	if (src_x_offset + (int)hubp->curs_attr.width <= 0)
@@ -1102,8 +1123,8 @@ void hubp1_cursor_set_position(
 			CURSOR_Y_POSITION, pos->y);
 
 	REG_SET_2(CURSOR_HOT_SPOT, 0,
-			CURSOR_HOT_SPOT_X, pos->x_hotspot,
-			CURSOR_HOT_SPOT_Y, pos->y_hotspot);
+			CURSOR_HOT_SPOT_X, x_hotspot,
+			CURSOR_HOT_SPOT_Y, y_hotspot);
 
 	REG_SET(CURSOR_DST_OFFSET, 0,
 			CURSOR_DST_X_OFFSET, dst_x_offset);
@@ -1125,7 +1146,7 @@ void hubp1_vtg_sel(struct hubp *hubp, uint32_t otg_inst)
 	REG_UPDATE(DCHUBP_CNTL, HUBP_VTG_SEL, otg_inst);
 }
 
-static struct hubp_funcs dcn10_hubp_funcs = {
+static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_program_surface_flip_and_addr =
 			hubp1_program_surface_flip_and_addr,
 	.hubp_program_surface_config =
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 d901d5092969..f689feace82d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -268,8 +268,6 @@
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, META_PITCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, PITCH_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, META_PITCH_C, mask_sh),\
-	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
-	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, SURFACE_PIXEL_FORMAT, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_TYPE, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, mask_sh),\
@@ -388,6 +386,8 @@
 #define HUBP_MASK_SH_LIST_DCN10(mask_sh)\
 	HUBP_MASK_SH_LIST_DCN(mask_sh),\
 	HUBP_MASK_SH_LIST_DCN_VM(mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, DST_Y_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, VRATIO_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS_C, VRATIO_PREFETCH_C, mask_sh),\
@@ -679,12 +679,15 @@ void hubp1_program_pixel_format(
 	struct hubp *hubp,
 	enum surface_pixel_format format);
 
-void hubp1_program_size_and_rotation(
+void hubp1_program_size(
 	struct hubp *hubp,
-	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
-	struct dc_plane_dcc_param *dcc,
+	struct dc_plane_dcc_param *dcc);
+
+void hubp1_program_rotation(
+	struct hubp *hubp,
+	enum dc_rotation_angle rotation,
 	bool horizontal_mirror);
 
 void hubp1_program_tiling(
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 03eb736a312f..c87f6e603055 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
@@ -337,13 +337,13 @@ void dcn10_log_hw_state(struct dc *dc)
 
 	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",
-			dc->current_state->bw.dcn.calc_clk.dcfclk_khz,
-			dc->current_state->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			dc->current_state->bw.dcn.calc_clk.dispclk_khz,
-			dc->current_state->bw.dcn.calc_clk.dppclk_khz,
-			dc->current_state->bw.dcn.calc_clk.max_supported_dppclk_khz,
-			dc->current_state->bw.dcn.calc_clk.fclk_khz,
-			dc->current_state->bw.dcn.calc_clk.socclk_khz);
+			dc->current_state->bw.dcn.clk.dcfclk_khz,
+			dc->current_state->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			dc->current_state->bw.dcn.clk.dispclk_khz,
+			dc->current_state->bw.dcn.clk.dppclk_khz,
+			dc->current_state->bw.dcn.clk.max_supported_dppclk_khz,
+			dc->current_state->bw.dcn.clk.fclk_khz,
+			dc->current_state->bw.dcn.clk.socclk_khz);
 
 	log_mpc_crc(dc);
 
@@ -415,6 +415,8 @@ static void dpp_pg_control(
 
 	if (hws->ctx->dc->debug.disable_dpp_power_gate)
 		return;
+	if (REG(DOMAIN1_PG_CONFIG) == 0)
+		return;
 
 	switch (dpp_inst) {
 	case 0: /* DPP0 */
@@ -465,6 +467,8 @@ static void hubp_pg_control(
 
 	if (hws->ctx->dc->debug.disable_hubp_power_gate)
 		return;
+	if (REG(DOMAIN0_PG_CONFIG) == 0)
+		return;
 
 	switch (hubp_inst) {
 	case 0: /* DCHUBP0 */
@@ -830,7 +834,7 @@ static bool dcn10_hw_wa_force_recovery(struct dc *dc)
 }
 
 
-static void dcn10_verify_allow_pstate_change_high(struct dc *dc)
+void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 {
 	static bool should_log_hw_state; /* prevent hw state log by default */
 
@@ -865,7 +869,8 @@ void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		return;
 
 	mpc->funcs->remove_mpcc(mpc, mpc_tree_params, mpcc_to_remove);
-	opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
+	if (opp != NULL)
+		opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 
 	dc->optimized_required = true;
 
@@ -1010,7 +1015,7 @@ static void dcn10_init_hw(struct dc *dc)
 	/* Reset all MPCC muxes */
 	dc->res_pool->mpc->funcs->mpc_init(dc->res_pool->mpc);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		struct timing_generator *tg = dc->res_pool->timing_generators[i];
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 		struct hubp *hubp = dc->res_pool->hubps[i];
@@ -1152,12 +1157,19 @@ static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_c
 
 	if (plane_state == NULL)
 		return;
+
 	addr_patched = patch_address_for_sbs_tb_stereo(pipe_ctx, &addr);
+
 	pipe_ctx->plane_res.hubp->funcs->hubp_program_surface_flip_and_addr(
 			pipe_ctx->plane_res.hubp,
 			&plane_state->address,
 			plane_state->flip_immediate);
+
 	plane_state->status.requested_address = plane_state->address;
+
+	if (plane_state->flip_immediate)
+		plane_state->status.current_address = plane_state->address;
+
 	if (addr_patched)
 		pipe_ctx->plane_state->address.grph_stereo.left_addr = addr;
 }
@@ -1343,10 +1355,11 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 
 	DC_SYNC_INFO("Setting up\n");
 	for (i = 0; i < group_size; i++)
-		grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
-				grouped_pipes[i]->stream_res.tg,
-				grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
-				&grouped_pipes[i]->stream->triggered_crtc_reset);
+		if (grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset)
+			grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
+					grouped_pipes[i]->stream_res.tg,
+					grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
+					&grouped_pipes[i]->stream->triggered_crtc_reset);
 
 	DC_SYNC_INFO("Waiting for trigger\n");
 
@@ -1762,6 +1775,43 @@ static void dcn10_get_surface_visual_confirm_color(
 	}
 }
 
+static void dcn10_get_hdr_visual_confirm_color(
+		struct pipe_ctx *pipe_ctx,
+		struct tg_color *color)
+{
+	uint32_t color_value = MAX_TG_COLOR_VALUE;
+
+	// Determine the overscan color based on the top-most (desktop) plane's context
+	struct pipe_ctx *top_pipe_ctx  = pipe_ctx;
+
+	while (top_pipe_ctx->top_pipe != NULL)
+		top_pipe_ctx = top_pipe_ctx->top_pipe;
+
+	switch (top_pipe_ctx->plane_res.scl_data.format) {
+	case PIXEL_FORMAT_ARGB2101010:
+		if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_UNITY) {
+			/* HDR10, ARGB2101010 - set boarder color to red */
+			color->color_r_cr = color_value;
+		}
+		break;
+	case PIXEL_FORMAT_FP16:
+		if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_PQ) {
+			/* HDR10, FP16 - set boarder color to blue */
+			color->color_b_cb = color_value;
+		} else if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) {
+			/* FreeSync 2 HDR - set boarder color to green */
+			color->color_g_y = color_value;
+		}
+		break;
+	default:
+		/* SDR - set boarder color to Gray */
+		color->color_r_cr = color_value/2;
+		color->color_b_cb = color_value/2;
+		color->color_g_y = color_value/2;
+		break;
+	}
+}
+
 static uint16_t fixed_point_to_int_frac(
 	struct fixed31_32 arg,
 	uint8_t integer_bits,
@@ -1842,11 +1892,10 @@ static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 		dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 }
 
-
-static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
-	struct mpcc_blnd_cfg blnd_cfg;
+	struct mpcc_blnd_cfg blnd_cfg = {0};
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
 	int mpcc_id;
 	struct mpcc *new_mpcc;
@@ -1857,13 +1906,17 @@ static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 
 	/* TODO: proper fix once fpga works */
 
-	if (dc->debug.surface_visual_confirm)
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
+		dcn10_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(
 				pipe_ctx, &blnd_cfg.black_color);
-	else
+	} else {
 		color_space_to_black_color(
-			dc, pipe_ctx->stream->output_color_space,
-			&blnd_cfg.black_color);
+				dc, pipe_ctx->stream->output_color_space,
+				&blnd_cfg.black_color);
+	}
 
 	if (per_pixel_alpha)
 		blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA;
@@ -1952,18 +2005,17 @@ static void update_dchubp_dpp(
 	 * divided by 2
 	 */
 	if (plane_state->update_flags.bits.full_update) {
-		bool should_divided_by_2 = context->bw.dcn.calc_clk.dppclk_khz <=
-				context->bw.dcn.cur_clk.dispclk_khz / 2;
+		bool should_divided_by_2 = context->bw.dcn.clk.dppclk_khz <=
+				dc->res_pool->dccg->clks.dispclk_khz / 2;
 
 		dpp->funcs->dpp_dppclk_control(
 				dpp,
 				should_divided_by_2,
 				true);
 
-		dc->current_state->bw.dcn.cur_clk.dppclk_khz =
-				should_divided_by_2 ?
-				context->bw.dcn.cur_clk.dispclk_khz / 2 :
-				context->bw.dcn.cur_clk.dispclk_khz;
+		dc->res_pool->dccg->clks.dppclk_khz = should_divided_by_2 ?
+						dc->res_pool->dccg->clks.dispclk_khz / 2 :
+							dc->res_pool->dccg->clks.dispclk_khz;
 	}
 
 	/* TODO: Need input parameter to tell current DCHUB pipe tie to which OTG
@@ -1989,7 +2041,7 @@ static void update_dchubp_dpp(
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change)
-		update_mpcc(dc, pipe_ctx);
+		dc->hwss.update_mpcc(dc, pipe_ctx);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
@@ -2099,6 +2151,33 @@ static void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, hw_mult);
 }
 
+void dcn10_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context)
+{
+	if (pipe_ctx->plane_state->update_flags.bits.full_update)
+		dcn10_enable_plane(dc, pipe_ctx, context);
+
+	update_dchubp_dpp(dc, pipe_ctx, context);
+
+	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);
+
+	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
+	 * only do gamma programming for full update.
+	 * TODO: This can be further optimized/cleaned up
+	 * Always call this for now since it does memcmp inside before
+	 * 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);
+}
+
 static void program_all_pipe_in_tree(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
@@ -2117,29 +2196,11 @@ static void program_all_pipe_in_tree(
 				pipe_ctx->stream_res.tg);
 
 		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+
 	}
 
 	if (pipe_ctx->plane_state != NULL) {
-		if (pipe_ctx->plane_state->update_flags.bits.full_update)
-			dcn10_enable_plane(dc, pipe_ctx, context);
-
-		update_dchubp_dpp(dc, pipe_ctx, context);
-
-		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);
-
-		/* dcn10_translate_regamma_to_hw_format takes 750us to finish
-		 * only do gamma programming for full update.
-		 * TODO: This can be further optimized/cleaned up
-		 * Always call this for now since it does memcmp inside before
-		 * 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);
+		dcn10_program_pipe(dc, pipe_ctx, context);
 	}
 
 	if (pipe_ctx->bottom_pipe != NULL && pipe_ctx->bottom_pipe != pipe_ctx) {
@@ -2153,12 +2214,12 @@ static void dcn10_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->min_engine_clock_khz = context->bw.dcn.cur_clk.dcfclk_khz;
-	pp_display_cfg->min_memory_clock_khz = context->bw.dcn.cur_clk.fclk_khz;
-	pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz;
-	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz;
-	pp_display_cfg->min_dcfclock_khz = context->bw.dcn.cur_clk.dcfclk_khz;
-	pp_display_cfg->disp_clk_khz = context->bw.dcn.cur_clk.dispclk_khz;
+	pp_display_cfg->min_engine_clock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
+	pp_display_cfg->min_memory_clock_khz = dc->res_pool->dccg->clks.fclk_khz;
+	pp_display_cfg->min_engine_clock_deep_sleep_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
+	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
+	pp_display_cfg->min_dcfclock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
+	pp_display_cfg->disp_clk_khz = dc->res_pool->dccg->clks.dispclk_khz;
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->prev_display_config, pp_display_cfg, sizeof(
@@ -2220,8 +2281,6 @@ static void dcn10_apply_ctx_for_surface(
 	int i;
 	struct timing_generator *tg;
 	bool removed_pipe[4] = { false };
-	unsigned int ref_clk_mhz = dc->res_pool->ref_clock_inKhz/1000;
-	bool program_water_mark = false;
 	struct pipe_ctx *top_pipe_to_program =
 			find_top_pipe_for_stream(dc, context, stream);
 	DC_LOGGER_INIT(dc->ctx->logger);
@@ -2266,11 +2325,10 @@ static void dcn10_apply_ctx_for_surface(
 			old_pipe_ctx->plane_state &&
 			old_pipe_ctx->stream_res.tg == tg) {
 
-			hwss1_plane_atomic_disconnect(dc, old_pipe_ctx);
+			dc->hwss.plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
-			DC_LOG_DC(
-					"Reset mpcc for pipe %d\n",
+			DC_LOG_DC("Reset mpcc for pipe %d\n",
 					old_pipe_ctx->pipe_idx);
 		}
 	}
@@ -2283,248 +2341,41 @@ static void dcn10_apply_ctx_for_surface(
 	if (num_planes == 0)
 		false_optc_underflow_wa(dc, stream, tg);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *old_pipe_ctx =
-				&dc->current_state->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-		if (pipe_ctx->stream == stream &&
-				pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.full_update)
-			program_water_mark = true;
-
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (removed_pipe[i])
-			dcn10_disable_plane(dc, old_pipe_ctx);
-	}
-
-	if (program_water_mark) {
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			dcn10_verify_allow_pstate_change_high(dc);
-		}
-
-		/* watermark is for all pipes */
-		hubbub1_program_watermarks(dc->res_pool->hubbub,
-				&context->bw.dcn.watermarks, ref_clk_mhz);
-
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			dcn10_verify_allow_pstate_change_high(dc);
-		}
-	}
-/*	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
-			"\n============== Watermark parameters ==============\n"
-			"a.urgent_ns: %d \n"
-			"a.cstate_enter_plus_exit: %d \n"
-			"a.cstate_exit: %d \n"
-			"a.pstate_change: %d \n"
-			"a.pte_meta_urgent: %d \n"
-			"b.urgent_ns: %d \n"
-			"b.cstate_enter_plus_exit: %d \n"
-			"b.cstate_exit: %d \n"
-			"b.pstate_change: %d \n"
-			"b.pte_meta_urgent: %d \n",
-			context->bw.dcn.watermarks.a.urgent_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.a.pte_meta_urgent_ns,
-			context->bw.dcn.watermarks.b.urgent_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.b.pte_meta_urgent_ns
-			);
-	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
-			"\nc.urgent_ns: %d \n"
-			"c.cstate_enter_plus_exit: %d \n"
-			"c.cstate_exit: %d \n"
-			"c.pstate_change: %d \n"
-			"c.pte_meta_urgent: %d \n"
-			"d.urgent_ns: %d \n"
-			"d.cstate_enter_plus_exit: %d \n"
-			"d.cstate_exit: %d \n"
-			"d.pstate_change: %d \n"
-			"d.pte_meta_urgent: %d \n"
-			"========================================================\n",
-			context->bw.dcn.watermarks.c.urgent_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.c.pte_meta_urgent_ns,
-			context->bw.dcn.watermarks.d.urgent_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.d.pte_meta_urgent_ns
-			);
-*/
-}
-
-static inline bool should_set_clock(bool decrease_allowed, int calc_clk, int cur_clk)
-{
-	return ((decrease_allowed && calc_clk < cur_clk) || calc_clk > cur_clk);
-}
-
-static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
-{
-	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
-			context->bw.dcn.calc_clk.dppclk_khz;
-	bool dispclk_increase = context->bw.dcn.calc_clk.dispclk_khz >
-			context->bw.dcn.cur_clk.dispclk_khz;
-	int disp_clk_threshold = context->bw.dcn.calc_clk.max_supported_dppclk_khz;
-	bool cur_dpp_div = context->bw.dcn.cur_clk.dispclk_khz >
-			context->bw.dcn.cur_clk.dppclk_khz;
-
-	/* increase clock, looking for div is 0 for current, request div is 1*/
-	if (dispclk_increase) {
-		/* already divided by 2, no need to reach target clk with 2 steps*/
-		if (cur_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* request disp clk is lower than maximum supported dpp clk,
-		 * no need to reach target clk with two steps.
-		 */
-		if (context->bw.dcn.calc_clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* target dpp clk not request divided by 2, still within threshold */
-		if (!request_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-	} else {
-		/* decrease clock, looking for current dppclk divided by 2,
-		 * request dppclk not divided by 2.
-		 */
-
-		/* current dpp clk not divided by 2, no need to ramp*/
-		if (!cur_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+			dcn10_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 
-		/* current disp clk is lower than current maximum dpp clk,
-		 * no need to ramp
-		 */
-		if (context->bw.dcn.cur_clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-
-		/* request dpp clk need to be divided by 2 */
-		if (request_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
-	}
-
-	return disp_clk_threshold;
-}
-
-static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
-{
-	int i;
-	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
-				context->bw.dcn.calc_clk.dppclk_khz;
-
-	int dispclk_to_dpp_threshold = determine_dppclk_threshold(dc, context);
-
-	/* set disp clk to dpp clk threshold */
-	dc->res_pool->display_clock->funcs->set_clock(
-			dc->res_pool->display_clock,
-			dispclk_to_dpp_threshold);
-
-	/* update request dpp clk division option */
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
-
-		if (!pipe_ctx->plane_state)
-			continue;
-
-		pipe_ctx->plane_res.dpp->funcs->dpp_dppclk_control(
-				pipe_ctx->plane_res.dpp,
-				request_dpp_div,
-				true);
-	}
-
-	/* If target clk not same as dppclk threshold, set to target clock */
-	if (dispclk_to_dpp_threshold != context->bw.dcn.calc_clk.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dcn.calc_clk.dispclk_khz);
-	}
-
-	context->bw.dcn.cur_clk.dispclk_khz =
-			context->bw.dcn.calc_clk.dispclk_khz;
-	context->bw.dcn.cur_clk.dppclk_khz =
-			context->bw.dcn.calc_clk.dppclk_khz;
-	context->bw.dcn.cur_clk.max_supported_dppclk_khz =
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz;
+	if (dc->hwseq->wa.DEGVIDCN10_254)
+		hubbub1_wm_change_req_wa(dc->res_pool->hubbub);
 }
 
 static void dcn10_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
-		bool decrease_allowed)
+		bool safe_to_lower)
 {
-	struct pp_smu_display_requirement_rv *smu_req_cur =
-			&dc->res_pool->pp_smu_req;
-	struct pp_smu_display_requirement_rv smu_req = *smu_req_cur;
-	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
-
-	if (dc->debug.sanity_checks) {
+	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
-	}
 
-	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		return;
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			dc->current_state->bw.dcn.cur_clk.dcfclk_khz)) {
-		context->bw.dcn.cur_clk.dcfclk_khz =
-				context->bw.dcn.calc_clk.dcfclk_khz;
-		smu_req.hard_min_dcefclk_khz =
-				context->bw.dcn.calc_clk.dcfclk_khz;
-	}
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			dc->current_state->bw.dcn.cur_clk.dcfclk_deep_sleep_khz)) {
-		context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz =
-				context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz;
-	}
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.fclk_khz,
-			dc->current_state->bw.dcn.cur_clk.fclk_khz)) {
-		context->bw.dcn.cur_clk.fclk_khz =
-				context->bw.dcn.calc_clk.fclk_khz;
-		smu_req.hard_min_fclk_khz = context->bw.dcn.calc_clk.fclk_khz;
-	}
-
-	smu_req.display_count = context->stream_count;
-
-	if (pp_smu->set_display_requirement)
-		pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		if (context->stream_count == 0)
+			context->bw.dcn.clk.phyclk_khz = 0;
 
-	*smu_req_cur = smu_req;
+		dc->res_pool->dccg->funcs->update_clocks(
+				dc->res_pool->dccg,
+				&context->bw.dcn.clk,
+				safe_to_lower);
 
-	/* make sure dcf clk is before dpp clk to
-	 * make sure we have enough voltage to run dpp clk
-	 */
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dispclk_khz,
-			dc->current_state->bw.dcn.cur_clk.dispclk_khz)) {
-
-		ramp_up_dispclk_with_dpp(dc, context);
+		dcn10_pplib_apply_display_requirements(dc, context);
 	}
 
-	dcn10_pplib_apply_display_requirements(dc, context);
+	hubbub1_program_watermarks(dc->res_pool->hubbub,
+			&context->bw.dcn.watermarks,
+			dc->res_pool->ref_clock_inKhz / 1000,
+			true);
 
-	if (dc->debug.sanity_checks) {
+	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
-	}
-
-	/* need to fix this function.  not doing the right thing here */
 }
 
 static void set_drr(struct pipe_ctx **pipe_ctx,
@@ -2689,16 +2540,20 @@ static 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;
+	bool flip_pending;
 
 	if (plane_state == NULL)
 		return;
 
-	plane_state->status.is_flip_pending =
-			pipe_ctx->plane_res.hubp->funcs->hubp_is_flip_pending(
+	flip_pending = pipe_ctx->plane_res.hubp->funcs->hubp_is_flip_pending(
 					pipe_ctx->plane_res.hubp);
 
-	plane_state->status.current_address = pipe_ctx->plane_res.hubp->current_address;
-	if (pipe_ctx->plane_res.hubp->current_address.type == PLN_ADDR_TYPE_GRPH_STEREO &&
+	plane_state->status.is_flip_pending = flip_pending;
+
+	if (!flip_pending)
+		plane_state->status.current_address = plane_state->status.requested_address;
+
+	if (plane_state->status.current_address.type == PLN_ADDR_TYPE_GRPH_STEREO &&
 			tg->funcs->is_stereo_left_eye) {
 		plane_state->status.is_right_eye =
 				!tg->funcs->is_stereo_left_eye(pipe_ctx->stream_res.tg);
@@ -2707,8 +2562,14 @@ 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)
 {
-	if (hws->ctx->dc->res_pool->hubbub != NULL)
-		hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+	if (hws->ctx->dc->res_pool->hubbub != NULL) {
+		struct hubp *hubp = hws->ctx->dc->res_pool->hubps[0];
+
+		if (hubp->funcs->hubp_update_dchub)
+			hubp->funcs->hubp_update_dchub(hubp, dh_data);
+		else
+			hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+	}
 }
 
 static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
@@ -2719,9 +2580,11 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	struct dc_cursor_mi_param param = {
 		.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz,
 		.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz,
-		.viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x,
-		.viewport_width = pipe_ctx->plane_res.scl_data.viewport.width,
-		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz
+		.viewport = pipe_ctx->plane_res.scl_data.viewport,
+		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
+		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
+		.rotation = pipe_ctx->plane_state->rotation,
+		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
 	if (pipe_ctx->plane_state->address.type
@@ -2745,6 +2608,33 @@ static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 		pipe_ctx->plane_res.dpp, attributes->color_format);
 }
 
+static 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;
+	struct dpp_cursor_attributes opt_attr = { 0 };
+	uint32_t hw_scale = 0x3c00; // 1.0 default multiplier
+	struct custom_float_format fmt;
+
+	if (!pipe_ctx->plane_res.dpp->funcs->set_optional_cursor_attributes)
+		return;
+
+	fmt.exponenta_bits = 5;
+	fmt.mantissa_bits = 10;
+	fmt.sign = true;
+
+	if (sdr_white_level > 80) {
+		multiplier = dc_fixpt_from_fraction(sdr_white_level, 80);
+		convert_to_custom_float_format(multiplier, &fmt, &hw_scale);
+	}
+
+	opt_attr.scale = hw_scale;
+	opt_attr.bias = 0;
+
+	pipe_ctx->plane_res.dpp->funcs->set_optional_cursor_attributes(
+			pipe_ctx->plane_res.dpp, &opt_attr);
+}
+
 static const struct hw_sequencer_funcs dcn10_funcs = {
 	.program_gamut_remap = program_gamut_remap,
 	.program_csc_matrix = program_csc_matrix,
@@ -2752,7 +2642,9 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.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,
@@ -2790,7 +2682,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.edp_power_control = hwss_edp_power_control,
 	.edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
-	.set_cursor_attribute = dcn10_set_cursor_attribute
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level
 };
 
 
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 44f734b73f9e..7139fb73e966 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
@@ -39,4 +39,11 @@ 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);
+
+void dcn10_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
+
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index 21fa40ac0786..6f675206a136 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -65,11 +65,6 @@ enum {
 	DP_MST_UPDATE_MAX_RETRY = 50
 };
 
-
-
-static void aux_initialize(struct dcn10_link_encoder *enc10);
-
-
 static const struct link_encoder_funcs dcn10_lnk_enc_funcs = {
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
@@ -445,12 +440,11 @@ static uint8_t get_frontend_source(
 	}
 }
 
-static void configure_encoder(
+void configure_encoder(
 	struct dcn10_link_encoder *enc10,
 	const struct dc_link_settings *link_settings)
 {
 	/* set number of lanes */
-
 	REG_SET(DP_CONFIG, 0,
 			DP_UDI_LANES, link_settings->lane_count - LANE_COUNT_ONE);
 
@@ -602,6 +596,9 @@ static bool dcn10_link_encoder_validate_hdmi_output(
 	if (!enc10->base.features.flags.bits.HDMI_6GB_EN &&
 		adjusted_pix_clk_khz >= 300000)
 		return false;
+	if (enc10->base.ctx->dc->debug.hdmi20_disable &&
+		crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 	return true;
 }
 
@@ -734,6 +731,9 @@ void dcn10_link_encoder_construct(
 				__func__,
 				result);
 	}
+	if (enc10->base.ctx->dc->debug.hdmi20_disable) {
+		enc10->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
 }
 
 bool dcn10_link_encoder_validate_output_with_stream(
@@ -812,7 +812,7 @@ void dcn10_link_encoder_hw_init(
 		ASSERT(result == BP_RESULT_OK);
 
 	}
-	aux_initialize(enc10);
+	dcn10_aux_initialize(enc10);
 
 	/* reinitialize HPD.
 	 * hpd_initialize() will pass DIG_FE id to HW context.
@@ -995,6 +995,8 @@ void dcn10_link_encoder_disable_output(
 
 	if (!dcn10_is_dig_enabled(enc)) {
 		/* OF_SKIP_POWER_DOWN_INACTIVE_ENCODER */
+	/*in DP_Alt_No_Connect case, we turn off the dig already,
+	after excuation the PHY w/a sequence, not allow touch PHY any more*/
 		return;
 	}
 	/* Power-down RX and disable GPU PHY should be paired.
@@ -1347,8 +1349,7 @@ void dcn10_link_encoder_disable_hpd(struct link_encoder *enc)
 				FN(reg, f1), v1,\
 				FN(reg, f2), v2)
 
-static void aux_initialize(
-	struct dcn10_link_encoder *enc10)
+void dcn10_aux_initialize(struct dcn10_link_encoder *enc10)
 {
 	enum hpd_source_id hpd_source = enc10->base.hpd_source;
 
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 2a97cdb2cfbb..49ead12b2532 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
@@ -42,6 +42,7 @@
 #define LE_DCN_COMMON_REG_LIST(id) \
 	SRI(DIG_BE_CNTL, DIG, id), \
 	SRI(DIG_BE_EN_CNTL, DIG, id), \
+	SRI(TMDS_CTL_BITS, DIG, id), \
 	SRI(DP_CONFIG, DP, id), \
 	SRI(DP_DPHY_CNTL, DP, id), \
 	SRI(DP_DPHY_PRBS_CNTL, DP, id), \
@@ -64,6 +65,7 @@
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
 	SRI(DP_DPHY_HBR2_PATTERN_CONTROL, DP, id)
 
+
 #define LE_DCN10_REG_LIST(id)\
 	LE_DCN_COMMON_REG_LIST(id)
 
@@ -100,6 +102,7 @@ struct dcn10_link_enc_registers {
 	uint32_t DP_DPHY_BS_SR_SWAP_CNTL;
 	uint32_t DP_DPHY_HBR2_PATTERN_CONTROL;
 	uint32_t DP_SEC_CNTL1;
+	uint32_t TMDS_CTL_BITS;
 };
 
 #define LE_SF(reg_name, field_name, post_fix)\
@@ -110,6 +113,7 @@ struct dcn10_link_enc_registers {
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_HPD_SELECT, mask_sh),\
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_MODE, mask_sh),\
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_FE_SOURCE_SELECT, mask_sh),\
+	LE_SF(DIG0_TMDS_CTL_BITS, TMDS_CTL0, mask_sh), \
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_BYPASS, mask_sh),\
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE0, mask_sh),\
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE1, mask_sh),\
@@ -198,10 +202,11 @@ struct dcn10_link_enc_registers {
 	type DP_MSE_SAT_SLOT_COUNT3;\
 	type DP_MSE_SAT_UPDATE;\
 	type DP_MSE_16_MTP_KEEPOUT;\
+	type DC_HPD_EN;\
+	type TMDS_CTL0;\
 	type AUX_HPD_SEL;\
 	type AUX_LS_READ_EN;\
-	type AUX_RX_RECEIVE_WINDOW;\
-	type DC_HPD_EN
+	type AUX_RX_RECEIVE_WINDOW
 
 struct dcn10_link_enc_shift {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
@@ -266,6 +271,10 @@ void dcn10_link_encoder_setup(
 	struct link_encoder *enc,
 	enum signal_type signal);
 
+void configure_encoder(
+	struct dcn10_link_encoder *enc10,
+	const struct dc_link_settings *link_settings);
+
 /* enables TMDS PHY output */
 /* TODO: still need depth or just pass in adjusted pixel clock? */
 void dcn10_link_encoder_enable_tmds_output(
@@ -327,4 +336,6 @@ void dcn10_psr_program_secondary_packet(struct link_encoder *enc,
 
 bool dcn10_is_dig_enabled(struct link_encoder *enc);
 
+void dcn10_aux_initialize(struct dcn10_link_encoder *enc10);
+
 #endif /* __DC_LINK_ENCODER__DCN10_H__ */
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 9ca51ae46de7..958994edf2c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -428,7 +428,7 @@ void mpc1_read_mpcc_state(
 			MPCC_BUSY, &s->busy);
 }
 
-const struct mpc_funcs dcn10_mpc_funcs = {
+static const struct mpc_funcs dcn10_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
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 77a1a9d541a4..ab958cff3b76 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -385,7 +385,7 @@ void opp1_destroy(struct output_pixel_processor **opp)
 	*opp = NULL;
 }
 
-static struct opp_funcs dcn10_opp_funcs = {
+static const struct opp_funcs dcn10_opp_funcs = {
 		.opp_set_dyn_expansion = opp1_set_dyn_expansion,
 		.opp_program_fmt = opp1_program_fmt,
 		.opp_program_bit_depth_reduction = opp1_program_bit_depth_reduction,
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 e6a3ade154b9..411f89218e01 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -1324,6 +1324,72 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
 	return (underflow_occurred == 1);
 }
 
+bool optc1_configure_crc(struct timing_generator *optc,
+			  const struct crc_params *params)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	/* Cannot configure crc on a CRTC that is disabled */
+	if (!optc1_is_tg_enabled(optc))
+		return false;
+
+	REG_WRITE(OTG_CRC_CNTL, 0);
+
+	if (!params->enable)
+		return true;
+
+	/* Program frame boundaries */
+	/* Window A x axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL,
+			OTG_CRC0_WINDOWA_X_START, params->windowa_x_start,
+			OTG_CRC0_WINDOWA_X_END, params->windowa_x_end);
+
+	/* Window A y axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL,
+			OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start,
+			OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end);
+
+	/* Window B x axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL,
+			OTG_CRC0_WINDOWB_X_START, params->windowb_x_start,
+			OTG_CRC0_WINDOWB_X_END, params->windowb_x_end);
+
+	/* Window B y axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL,
+			OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start,
+			OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end);
+
+	/* Set crc mode and selection, and enable. Only using CRC0*/
+	REG_UPDATE_3(OTG_CRC_CNTL,
+			OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0,
+			OTG_CRC0_SELECT, params->selection,
+			OTG_CRC_EN, 1);
+
+	return true;
+}
+
+bool optc1_get_crc(struct timing_generator *optc,
+		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb)
+{
+	uint32_t field = 0;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	REG_GET(OTG_CRC_CNTL, OTG_CRC_EN, &field);
+
+	/* Early return if CRC is not enabled for this CRTC */
+	if (!field)
+		return false;
+
+	REG_GET_2(OTG_CRC0_DATA_RG,
+			CRC0_R_CR, r_cr,
+			CRC0_G_Y, g_y);
+
+	REG_GET(OTG_CRC0_DATA_B,
+			CRC0_B_CB, b_cb);
+
+	return true;
+}
+
 static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.validate_timing = optc1_validate_timing,
 		.program_timing = optc1_program_timing,
@@ -1360,6 +1426,8 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.is_tg_enabled = optc1_is_tg_enabled,
 		.is_optc_underflow_occurred = optc1_is_optc_underflow_occurred,
 		.clear_optc_underflow = optc1_clear_optc_underflow,
+		.get_crc = optc1_get_crc,
+		.configure_crc = optc1_configure_crc,
 };
 
 void dcn10_timing_generator_init(struct optc *optc1)
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 59ed272e0c49..c1b114209fe8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -75,7 +75,14 @@
 	SRI(CONTROL, VTG, inst),\
 	SRI(OTG_VERT_SYNC_CONTROL, OTG, inst),\
 	SRI(OTG_MASTER_UPDATE_MODE, OTG, inst),\
-	SRI(OTG_GSL_CONTROL, OTG, inst)
+	SRI(OTG_GSL_CONTROL, OTG, inst),\
+	SRI(OTG_CRC_CNTL, OTG, inst),\
+	SRI(OTG_CRC0_DATA_RG, OTG, inst),\
+	SRI(OTG_CRC0_DATA_B, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWA_X_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWA_Y_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWB_X_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWB_Y_CONTROL, OTG, inst)
 
 #define TG_COMMON_REG_LIST_DCN1_0(inst) \
 	TG_COMMON_REG_LIST_DCN(inst),\
@@ -138,6 +145,13 @@ struct dcn_optc_registers {
 	uint32_t OTG_GSL_WINDOW_X;
 	uint32_t OTG_GSL_WINDOW_Y;
 	uint32_t OTG_VUPDATE_KEEPOUT;
+	uint32_t OTG_CRC_CNTL;
+	uint32_t OTG_CRC0_DATA_RG;
+	uint32_t OTG_CRC0_DATA_B;
+	uint32_t OTG_CRC0_WINDOWA_X_CONTROL;
+	uint32_t OTG_CRC0_WINDOWA_Y_CONTROL;
+	uint32_t OTG_CRC0_WINDOWB_X_CONTROL;
+	uint32_t OTG_CRC0_WINDOWB_Y_CONTROL;
 };
 
 #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\
@@ -232,7 +246,21 @@ struct dcn_optc_registers {
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL2_EN, mask_sh),\
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_MASTER_EN, mask_sh),\
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_FORCE_DELAY, mask_sh),\
-	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh)
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC_CONT_EN, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC0_SELECT, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC_EN, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_RG, CRC0_R_CR, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_RG, CRC0_G_Y, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_B, CRC0_B_CB, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_X_CONTROL, OTG_CRC0_WINDOWA_X_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_X_CONTROL, OTG_CRC0_WINDOWA_X_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_Y_CONTROL, OTG_CRC0_WINDOWA_Y_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_Y_CONTROL, OTG_CRC0_WINDOWA_Y_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_END, mask_sh)
 
 
 #define TG_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
@@ -363,7 +391,22 @@ struct dcn_optc_registers {
 	type OTG_MASTER_UPDATE_LOCK_GSL_EN;\
 	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET;\
 	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET;\
-	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;
+	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;\
+	type OTG_CRC_CONT_EN;\
+	type OTG_CRC0_SELECT;\
+	type OTG_CRC_EN;\
+	type CRC0_R_CR;\
+	type CRC0_G_Y;\
+	type CRC0_B_CB;\
+	type OTG_CRC0_WINDOWA_X_START;\
+	type OTG_CRC0_WINDOWA_X_END;\
+	type OTG_CRC0_WINDOWA_Y_START;\
+	type OTG_CRC0_WINDOWA_Y_END;\
+	type OTG_CRC0_WINDOWB_X_START;\
+	type OTG_CRC0_WINDOWB_X_END;\
+	type OTG_CRC0_WINDOWB_Y_START;\
+	type OTG_CRC0_WINDOWB_Y_END;
+
 
 #define TG_REG_FIELD_LIST(type) \
 	TG_REG_FIELD_LIST_DCN1_0(type)
@@ -511,4 +554,15 @@ bool optc1_get_otg_active_size(struct timing_generator *optc,
 		uint32_t *otg_active_width,
 		uint32_t *otg_active_height);
 
+void optc1_enable_crtc_reset(
+		struct timing_generator *optc,
+		int source_tg_inst,
+		struct crtc_trigger_info *crtc_tp);
+
+bool optc1_configure_crc(struct timing_generator *optc,
+			  const struct crc_params *params);
+
+bool optc1_get_crc(struct timing_generator *optc,
+		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb);
+
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
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 2da325ce781b..c39934f8677f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -64,6 +64,69 @@
 #include "reg_helper.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
+
+const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs = 42,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 589824,
+	.max_line_buffer_lines = 12,
+	.IsLineBufferBppFixed = 0,
+	.LineBufferFixedBpp = -1,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.max_num_dpp = 4,
+	.max_num_wb = 2,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 4,
+	.max_vscl_ratio = 4,
+	.hscl_mults = 4,
+	.vscl_mults = 4,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dispclk_ramp_margin_percent = 1,
+	.underscan_factor = 1.10,
+	.min_vblank_lines = 14,
+	.dppclk_delay_subtotal = 90,
+	.dispclk_delay_subtotal = 42,
+	.dcfclk_cstate_latency = 10,
+	.max_inter_dcn_tile_repeaters = 8,
+	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
+	.bug_forcing_LC_req_same_size_fixed = 0,
+};
+
+const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.urgent_latency_us = 4.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 80.0,
+	.max_request_size_bytes = 256,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 128,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 2,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 17.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+};
 
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL		0x210f
@@ -294,6 +357,21 @@ static const struct dcn10_opp_mask opp_mask = {
 		OPP_MASK_SH_LIST_DCN10(_MASK),
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN10(id),\
@@ -424,7 +502,7 @@ static const struct resource_caps res_cap = {
 		.num_pll = 4,
 };
 
-static const struct dc_debug debug_defaults_drv = {
+static const struct dc_debug_options debug_defaults_drv = {
 		.sanity_checks = true,
 		.disable_dmcu = true,
 		.force_abm_enable = false,
@@ -437,7 +515,7 @@ static const struct dc_debug debug_defaults_drv = {
 		 */
 		.min_disp_clk_khz = 100000,
 
-		.disable_pplib_clock_request = true,
+		.disable_pplib_clock_request = false,
 		.disable_pplib_wm_range = false,
 		.pplib_wm_report_mode = WM_REPORT_DEFAULT,
 		.pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
@@ -452,7 +530,7 @@ static const struct dc_debug debug_defaults_drv = {
 		.max_downscale_src_width = 3840,
 };
 
-static const struct dc_debug debug_defaults_diags = {
+static const struct dc_debug_options debug_defaults_diags = {
 		.disable_dmcu = true,
 		.force_abm_enable = false,
 		.timing_trace = true,
@@ -516,6 +594,23 @@ static struct output_pixel_processor *dcn10_opp_create(
 	return &opp->base;
 }
 
+struct engine *dcn10_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 static struct mpc *dcn10_mpc_create(struct dc_context *ctx)
 {
 	struct dcn10_mpc *mpc10 = kzalloc(sizeof(struct dcn10_mpc),
@@ -681,6 +776,7 @@ static struct dce_hwseq *dcn10_hwseq_create(
 		hws->masks = &hwseq_mask;
 		hws->wa.DEGVIDCN10_253 = true;
 		hws->wa.false_optc_underflow = true;
+		hws->wa.DEGVIDCN10_254 = true;
 	}
 	return hws;
 }
@@ -763,6 +859,9 @@ static void destruct(struct dcn10_resource_pool *pool)
 			kfree(DCN10TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			pool->base.engines[i]->funcs->destroy_engine(&pool->base.engines[i]);
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++)
@@ -791,8 +890,8 @@ static void destruct(struct dcn10_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	kfree(pool->base.pp_smu);
 }
@@ -972,11 +1071,11 @@ static enum dc_status dcn10_validate_plane(const struct dc_plane_state *plane_st
 	return DC_OK;
 }
 
-static struct dc_cap_funcs cap_funcs = {
+static const struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn10_get_dcc_compression_cap
 };
 
-static struct resource_funcs dcn10_res_pool_funcs = {
+static const struct resource_funcs dcn10_res_pool_funcs = {
 	.destroy = dcn10_destroy_resource_pool,
 	.link_enc_create = dcn10_link_encoder_create,
 	.validate_bandwidth = dcn_validate_bandwidth,
@@ -1005,8 +1104,7 @@ static bool construct(
 
 	ctx->dc_bios->regs = &bios_regs;
 
-		pool->base.res_cap = &res_cap;
-
+	pool->base.res_cap = &res_cap;
 	pool->base.funcs = &dcn10_res_pool_funcs;
 
 	/*
@@ -1029,6 +1127,8 @@ static bool construct(
 	dc->caps.max_slave_planes = 1;
 	dc->caps.is_apu = true;
 	dc->caps.post_blend_color_processing = false;
+	/* Raven DP PHY HBR2 eye diagram pattern is not stable. Use TP4 */
+	dc->caps.force_dp_tps4_for_cp2520 = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
@@ -1072,8 +1172,8 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce120_disp_clk_create(ctx);
-	if (pool->base.display_clock == NULL) {
+	pool->base.dccg = dcn1_dccg_create(ctx);
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto fail;
@@ -1193,6 +1293,14 @@ static bool construct(
 			goto fail;
 		}
 
+		pool->base.engines[i] = dcn10_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto fail;
+		}
+
 		/* check next valid pipe */
 		j++;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index 034369fbb9e2..5d4527d03045 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -40,6 +40,14 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 	const struct dc_edid *edid,
 	struct dc_edid_caps *edid_caps);
 
+
+/*
+ * Update DP branch info
+ */
+void dm_helpers_dp_update_branch_info(
+		struct dc_context *ctx,
+		const struct dc_link *link);
+
 /*
  * Writes payload allocation table in immediate downstream device.
  */
@@ -103,6 +111,9 @@ bool dm_helpers_submit_i2c(
 		const struct dc_link *link,
 		struct i2c_command *cmd);
 
+bool dm_helpers_is_dp_sink_present(
+		struct dc_link *link);
+
 enum dc_edid_status dm_helpers_read_local_edid(
 		struct dc_context *ctx,
 		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 eac4bfe12257..58ed2055ef9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -40,7 +40,7 @@ enum wm_set_id {
 	WM_B,
 	WM_C,
 	WM_D,
-	WM_COUNT,
+	WM_SET_COUNT,
 };
 
 struct pp_smu_wm_set_range {
@@ -53,10 +53,10 @@ struct pp_smu_wm_set_range {
 
 struct pp_smu_wm_range_sets {
 	uint32_t num_reader_wm_sets;
-	struct pp_smu_wm_set_range reader_wm_sets[WM_COUNT];
+	struct pp_smu_wm_set_range reader_wm_sets[WM_SET_COUNT];
 
 	uint32_t num_writer_wm_sets;
-	struct pp_smu_wm_set_range writer_wm_sets[WM_COUNT];
+	struct pp_smu_wm_set_range writer_wm_sets[WM_SET_COUNT];
 };
 
 struct pp_smu_display_requirement_rv {
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 ab8c77d4e6df..2b83f922ac02 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
@@ -137,7 +137,7 @@ struct dm_pp_clock_range_for_wm_set {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_eng_clk_in_khz;
 	uint32_t wm_max_eng_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
@@ -150,7 +150,7 @@ struct dm_pp_clock_range_for_dmif_wm_set_soc15 {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_dcfclk_clk_in_khz;
 	uint32_t wm_max_dcfclk_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
@@ -158,7 +158,7 @@ struct dm_pp_clock_range_for_mcif_wm_set_soc15 {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_socclk_clk_in_khz;
 	uint32_t wm_max_socclk_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index f83a608f93e9..d97ca6528f9d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -36,11 +36,10 @@ CFLAGS_display_mode_lib.o := $(dml_ccflags)
 CFLAGS_display_pipe_clocks.o := $(dml_ccflags)
 CFLAGS_dml1_display_rq_dlg_calc.o := $(dml_ccflags)
 CFLAGS_display_rq_dlg_helpers.o := $(dml_ccflags)
-CFLAGS_soc_bounding_box.o := $(dml_ccflags)
 CFLAGS_dml_common_defs.o := $(dml_ccflags)
 
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
-	  soc_bounding_box.o dml_common_defs.o
+	dml_common_defs.o
 
 AMD_DAL_DML = $(addprefix $(AMDDALPATH)/dc/dml/,$(DML))
 
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 fd9d97aab071..dddeb0d4db8f 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
@@ -26,67 +26,8 @@
 #include "display_mode_lib.h"
 #include "dc_features.h"
 
-static const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
-	.rob_buffer_size_kbytes = 64,
-	.det_buffer_size_kbytes = 164,
-	.dpte_buffer_size_in_pte_reqs = 42,
-	.dpp_output_buffer_pixels = 2560,
-	.opp_output_buffer_lines = 1,
-	.pixel_chunk_size_kbytes = 8,
-	.pte_enable = 1,
-	.pte_chunk_size_kbytes = 2,
-	.meta_chunk_size_kbytes = 2,
-	.writeback_chunk_size_kbytes = 2,
-	.line_buffer_size_bits = 589824,
-	.max_line_buffer_lines = 12,
-	.IsLineBufferBppFixed = 0,
-	.LineBufferFixedBpp = -1,
-	.writeback_luma_buffer_size_kbytes = 12,
-	.writeback_chroma_buffer_size_kbytes = 8,
-	.max_num_dpp = 4,
-	.max_num_wb = 2,
-	.max_dchub_pscl_bw_pix_per_clk = 4,
-	.max_pscl_lb_bw_pix_per_clk = 2,
-	.max_lb_vscl_bw_pix_per_clk = 4,
-	.max_vscl_hscl_bw_pix_per_clk = 4,
-	.max_hscl_ratio = 4,
-	.max_vscl_ratio = 4,
-	.hscl_mults = 4,
-	.vscl_mults = 4,
-	.max_hscl_taps = 8,
-	.max_vscl_taps = 8,
-	.dispclk_ramp_margin_percent = 1,
-	.underscan_factor = 1.10,
-	.min_vblank_lines = 14,
-	.dppclk_delay_subtotal = 90,
-	.dispclk_delay_subtotal = 42,
-	.dcfclk_cstate_latency = 10,
-	.max_inter_dcn_tile_repeaters = 8,
-	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
-	.bug_forcing_LC_req_same_size_fixed = 0,
-};
-
-static const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.urgent_latency_us = 4.0,
-	.writeback_latency_us = 12.0,
-	.ideal_dram_bw_after_urgent_percent = 80.0,
-	.max_request_size_bytes = 256,
-	.downspread_percent = 0.5,
-	.dram_page_open_time_ns = 50.0,
-	.dram_rw_turnaround_time_ns = 17.5,
-	.dram_return_buffer_per_channel_bytes = 8192,
-	.round_trip_ping_latency_dcfclk_cycles = 128,
-	.urgent_out_of_order_return_per_channel_bytes = 256,
-	.channel_interleave_bytes = 256,
-	.num_banks = 8,
-	.num_chans = 2,
-	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 17.0,
-	.writeback_dram_clock_change_latency_us = 23.0,
-	.return_bus_width_bytes = 64,
-};
+extern const struct _vcs_dpi_ip_params_st dcn1_0_ip;
+extern const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc;
 
 static void set_soc_bounding_box(struct _vcs_dpi_soc_bounding_box_st *soc, enum dml_project project)
 {
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 3c2abcb8a1b0..635206248889 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
@@ -27,7 +27,6 @@
 
 
 #include "dml_common_defs.h"
-#include "soc_bounding_box.h"
 #include "dml1_display_rq_dlg_calc.h"
 
 enum dml_project {
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 7fa0375939ae..cbafce649e33 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
@@ -64,10 +64,9 @@ struct _vcs_dpi_voltage_scaling_st {
 	double dscclk_mhz;
 	double dcfclk_mhz;
 	double socclk_mhz;
-	double dram_speed_mhz;
+	double dram_speed_mts;
 	double fabricclk_mhz;
 	double dispclk_mhz;
-	double dram_bw_per_chan_gbps;
 	double phyclk_mhz;
 	double dppclk_mhz;
 };
@@ -112,6 +111,8 @@ struct _vcs_dpi_soc_bounding_box_st {
 	double xfc_bus_transport_time_us;
 	double xfc_xbuf_latency_tolerance_us;
 	int use_urgent_burst_bw;
+	double max_hscl_ratio;
+	double max_vscl_ratio;
 	struct _vcs_dpi_voltage_scaling_st clock_limits[7];
 };
 
@@ -304,6 +305,7 @@ struct _vcs_dpi_display_pipe_dest_params_st {
 	unsigned char otg_inst;
 	unsigned char odm_split_cnt;
 	unsigned char odm_combine;
+	unsigned char use_maximum_vstartup;
 };
 
 struct _vcs_dpi_display_pipe_params_st {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c b/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
deleted file mode 100644
index 324239c77958..000000000000
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2017 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 "soc_bounding_box.h"
-#include "display_mode_lib.h"
-#include "dc_features.h"
-
-#include "dml_inline_defs.h"
-
-/*
- * NOTE:
- *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
- *
- * It doesn't adhere to Linux kernel style and sometimes will do things in odd
- * ways. Unless there is something clearly wrong with it the code should
- * remain as-is as it provides us with a guarantee from HW that it is correct.
- */
-
-void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box)
-{
-	to_box->dram_clock_change_latency_us = from_box->dram_clock_change_latency_us;
-	to_box->sr_exit_time_us = from_box->sr_exit_time_us;
-	to_box->sr_enter_plus_exit_time_us = from_box->sr_enter_plus_exit_time_us;
-	to_box->urgent_latency_us = from_box->urgent_latency_us;
-	to_box->writeback_latency_us = from_box->writeback_latency_us;
-}
-
-voltage_scaling_st dml_socbb_voltage_scaling(
-		const soc_bounding_box_st *soc,
-		enum voltage_state voltage)
-{
-	const voltage_scaling_st *voltage_state;
-	const voltage_scaling_st * const voltage_end = soc->clock_limits + DC__VOLTAGE_STATES;
-
-	for (voltage_state = soc->clock_limits;
-			voltage_state < voltage_end && voltage_state->state != voltage;
-			voltage_state++) {
-	}
-
-	if (voltage_state < voltage_end)
-		return *voltage_state;
-	return soc->clock_limits[DC__VOLTAGE_STATES - 1];
-}
-
-double dml_socbb_return_bw_mhz(soc_bounding_box_st *box, enum voltage_state voltage)
-{
-	double return_bw;
-
-	voltage_scaling_st state = dml_socbb_voltage_scaling(box, voltage);
-
-	return_bw = dml_min((double) box->return_bus_width_bytes * state.dcfclk_mhz,
-			state.dram_bw_per_chan_gbps * 1000.0 * (double) box->num_chans
-					* box->ideal_dram_bw_after_urgent_percent / 100.0);
-
-	return_bw = dml_min((double) box->return_bus_width_bytes * state.fabricclk_mhz, return_bw);
-
-	return return_bw;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index 562ee189d780..b9d9930a4974 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -61,7 +61,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCE120)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 GPIO_DCN10 = hw_translate_dcn10.o hw_factory_dcn10.o
 
 AMD_DAL_GPIO_DCN10 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn10/,$(GPIO_DCN10))
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 9c4a56c738c0..bf40725f982f 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
@@ -82,13 +82,16 @@
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0
 
-#define DDC_MASK_SH_LIST(mask_sh) \
+#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),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_MODE, mask_sh),\
 		SF_DDC(DC_GPIO_DDC1_MASK, DC_GPIO_DDC1DATA_PD_EN, mask_sh),\
 		SF_DDC(DC_GPIO_DDC1_MASK, DC_GPIO_DDC1CLK_PD_EN, mask_sh),\
-		SF_DDC(DC_GPIO_DDC1_MASK, AUX_PAD1_MODE, mask_sh),\
+		SF_DDC(DC_GPIO_DDC1_MASK, AUX_PAD1_MODE, mask_sh)
+
+#define DDC_MASK_SH_LIST(mask_sh) \
+		DDC_MASK_SH_LIST_COMMON(mask_sh),\
 		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)
 
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
index ab5483c0c502..f20161c5706d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
@@ -375,6 +375,7 @@ struct gpio *dal_gpio_create_irq(
 	case GPIO_ID_GPIO_PAD:
 	break;
 	default:
+		id = GPIO_ID_HPD;
 		ASSERT_CRITICAL(false);
 		return NULL;
 	}
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 0caee3523017..83df779984e5 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -43,7 +43,7 @@
 #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)
+#ifdef CONFIG_X86
 #include "dcn10/hw_factory_dcn10.h"
 #endif
 
@@ -81,7 +81,7 @@ bool dal_hw_factory_init(
 	case DCE_VERSION_12_0:
 		dal_hw_factory_dce120_init(factory);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		dal_hw_factory_dcn10_init(factory);
 		return true;
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 55c707488541..e7541310480b 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -43,7 +43,7 @@
 #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)
+#ifdef CONFIG_X86
 #include "dcn10/hw_translate_dcn10.h"
 #endif
 
@@ -78,7 +78,7 @@ bool dal_hw_translate_init(
 	case DCE_VERSION_12_0:
 		dal_hw_translate_dce120_init(translate);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		dal_hw_translate_dcn10_init(translate);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
index 352885cb4d07..a851d07f0190 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
@@ -71,7 +71,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_I2CAUX_DCE112)
 ###############################################################################
 # DCN 1.0 family
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 I2CAUX_DCN1 = i2caux_dcn10.o
 
 AMD_DAL_I2CAUX_DCN1 = $(addprefix $(AMDDALPATH)/dc/i2caux/dcn10/,$(I2CAUX_DCN1))
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
index 1d7309611978..0afd2fa57bbe 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
@@ -128,8 +128,20 @@ static void process_read_reply(
 			ctx->status =
 				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
 			ctx->operation_succeeded = false;
+		} else if (ctx->returned_byte < ctx->current_read_length) {
+			ctx->current_read_length -= ctx->returned_byte;
+
+			ctx->offset += ctx->returned_byte;
+
+			++ctx->invalid_reply_retry_aux_on_ack;
+
+			if (ctx->invalid_reply_retry_aux_on_ack >
+				AUX_INVALID_REPLY_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+				ctx->operation_succeeded = false;
+			}
 		} else {
-			ctx->current_read_length = ctx->returned_byte;
 			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
 			ctx->transaction_complete = true;
 			ctx->operation_succeeded = true;
@@ -290,7 +302,6 @@ static bool read_command(
 				ctx.operation_succeeded);
 	}
 
-	request->payload.length = ctx.reply.length;
 	return ctx.operation_succeeded;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
index b01488f710d5..c33a2898d967 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
@@ -44,6 +44,12 @@ struct aux_engine_funcs {
 	void (*process_channel_reply)(
 		struct aux_engine *engine,
 		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
 	enum aux_channel_operation_result (*get_channel_status)(
 		struct aux_engine *engine,
 		uint8_t *returned_bytes);
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
index e8d3781deaed..8b704ab0471c 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
@@ -97,6 +97,7 @@ struct i2caux *dal_i2caux_dce100_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce100_aux_regs),
 				    dce100_aux_regs,
 				    dce100_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 2b927f25937b..ae5caa97caca 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -275,61 +275,92 @@ static void submit_channel_request(
 	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
 }
 
-static void process_channel_reply(
-	struct aux_engine *engine,
-	struct aux_reply_transaction_data *reply)
+static int read_channel_reply(struct aux_engine *engine, uint32_t size,
+			      uint8_t *buffer, uint8_t *reply_result,
+			      uint32_t *sw_status)
 {
 	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t bytes_replied;
+	uint32_t reply_result_32;
 
-	/* Need to do a read to get the number of bytes to process
-	 * Alternatively, this information can be passed -
-	 * but that causes coupling which isn't good either. */
+	*sw_status = REG_GET(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT,
+			     &bytes_replied);
 
-	uint32_t bytes_replied;
-	uint32_t value;
+	/* In case HPD is LOW, exit AUX transaction */
+	if ((*sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return -1;
 
-	value = REG_GET(AUX_SW_STATUS,
-			AUX_SW_REPLY_BYTE_COUNT, &bytes_replied);
+	/* Need at least the status byte */
+	if (!bytes_replied)
+		return -1;
 
-	/* in case HPD is LOW, exit AUX transaction */
-	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
-		reply->status = AUX_TRANSACTION_REPLY_HPD_DISCON;
-		return;
-	}
+	REG_UPDATE_1BY1_3(AUX_SW_DATA,
+			  AUX_SW_INDEX, 0,
+			  AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			  AUX_SW_DATA_RW, 1);
 
-	if (bytes_replied) {
-		uint32_t reply_result;
+	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	reply_result_32 = reply_result_32 >> 4;
+	*reply_result = (uint8_t)reply_result_32;
 
-		REG_UPDATE_1BY1_3(AUX_SW_DATA,
-				AUX_SW_INDEX, 0,
-				AUX_SW_AUTOINCREMENT_DISABLE, 1,
-				AUX_SW_DATA_RW, 1);
+	if (reply_result_32 == 0) { /* ACK */
+		uint32_t i = 0;
 
-		REG_GET(AUX_SW_DATA,
-				AUX_SW_DATA, &reply_result);
+		/* First byte was already used to get the command status */
+		--bytes_replied;
 
-		reply_result = reply_result >> 4;
+		/* Do not overflow buffer */
+		if (bytes_replied > size)
+			return -1;
 
-		switch (reply_result) {
-		case 0: /* ACK */ {
-			uint32_t i = 0;
+		while (i < bytes_replied) {
+			uint32_t aux_sw_data_val;
 
-			/* first byte was already used
-			 * to get the command status */
-			--bytes_replied;
+			REG_GET(AUX_SW_DATA, AUX_SW_DATA, &aux_sw_data_val);
+			buffer[i] = aux_sw_data_val;
+			++i;
+		}
+
+		return i;
+	}
+
+	return 0;
+}
+
+static void process_channel_reply(
+	struct aux_engine *engine,
+	struct aux_reply_transaction_data *reply)
+{
+	int bytes_replied;
+	uint8_t reply_result;
+	uint32_t sw_status;
 
-			while (i < bytes_replied) {
-				uint32_t aux_sw_data_val;
+	bytes_replied = read_channel_reply(engine, reply->length, reply->data,
+					   &reply_result, &sw_status);
 
-				REG_GET(AUX_SW_DATA,
-						AUX_SW_DATA, &aux_sw_data_val);
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		return;
+	}
 
-				reply->data[i] = aux_sw_data_val;
-				++i;
-			}
+	if (bytes_replied < 0) {
+		/* Need to handle an error case...
+		 * Hopefully, upper layer function won't call this function if
+		 * the number of bytes in the reply was 0, because there was
+		 * surely an error that was asserted that should have been
+		 * handled for hot plug case, this could happens
+		 */
+		if (!(sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+			ASSERT_CRITICAL(false);
+			return;
+		}
+	} else {
 
+		switch (reply_result) {
+		case 0: /* ACK */
 			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
-		}
 		break;
 		case 1: /* NACK */
 			reply->status = AUX_TRANSACTION_REPLY_AUX_NACK;
@@ -346,17 +377,6 @@ static void process_channel_reply(
 		default:
 			reply->status = AUX_TRANSACTION_REPLY_INVALID;
 		}
-	} else {
-		/* Need to handle an error case...
-		 * hopefully, upper layer function won't call this function
-		 * if the number of bytes in the reply was 0
-		 * because there was surely an error that was asserted
-		 * that should have been handled
-		 * for hot plug case, this could happens*/
-		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
-			reply->status = AUX_TRANSACTION_REPLY_INVALID;
-			ASSERT_CRITICAL(false);
-		}
 	}
 }
 
@@ -427,6 +447,7 @@ static const struct aux_engine_funcs aux_engine_funcs = {
 	.acquire_engine = acquire_engine,
 	.submit_channel_request = submit_channel_request,
 	.process_channel_reply = process_channel_reply,
+	.read_channel_reply = read_channel_reply,
 	.get_channel_status = get_channel_status,
 	.is_engine_available = is_engine_available,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
index b7256f595052..9cbe1a7a6bcb 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
@@ -62,12 +62,7 @@ enum dc_i2c_arbitration {
 	DC_I2C_ARBITRATION__DC_I2C_SW_PRIORITY_HIGH
 };
 
-enum {
-	/* No timeout in HW
-	 * (timeout implemented in SW by querying status) */
-	I2C_SETUP_TIME_LIMIT = 255,
-	I2C_HW_BUFFER_SIZE = 538
-};
+
 
 /*
  * @brief
@@ -152,6 +147,11 @@ static bool setup_engine(
 	struct i2c_engine *i2c_engine)
 {
 	struct i2c_hw_engine_dce110 *hw_engine = FROM_I2C_ENGINE(i2c_engine);
+	uint32_t i2c_setup_limit = I2C_SETUP_TIME_LIMIT_DCE;
+	uint32_t  reset_length = 0;
+
+	if (hw_engine->base.base.setup_limit != 0)
+		i2c_setup_limit = hw_engine->base.base.setup_limit;
 
 	/* Program pin select */
 	REG_UPDATE_6(
@@ -164,11 +164,15 @@ static bool setup_engine(
 			DC_I2C_DDC_SELECT, hw_engine->engine_id);
 
 	/* Program time limit */
-	REG_UPDATE_N(
-			SETUP, 2,
-			FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), I2C_SETUP_TIME_LIMIT,
-			FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-
+	if (hw_engine->base.base.send_reset_length == 0) {
+		/*pre-dcn*/
+		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);
+	} else {
+		reset_length = hw_engine->base.base.send_reset_length;
+	}
 	/* Program HW priority
 	 * set to High - interrupt software I2C at any time
 	 * Enable restart of SW I2C that was interrupted by HW
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
index 5bb04085f670..fea2946906ed 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
@@ -192,6 +192,7 @@ struct i2c_hw_engine_dce110 {
 	/* number of pending transactions (before GO) */
 	uint32_t transaction_count;
 	uint32_t engine_keep_power_up_count;
+	uint32_t i2_setup_time_limit;
 };
 
 struct i2c_hw_engine_dce110_create_arg {
@@ -207,4 +208,11 @@ struct i2c_hw_engine_dce110_create_arg {
 struct i2c_engine *dal_i2c_hw_engine_dce110_create(
 	const struct i2c_hw_engine_dce110_create_arg *arg);
 
+enum {
+	I2C_SETUP_TIME_LIMIT_DCE = 255,
+	I2C_SETUP_TIME_LIMIT_DCN = 3,
+	I2C_HW_BUFFER_SIZE = 538,
+	I2C_SEND_RESET_LENGTH_9 = 9,
+	I2C_SEND_RESET_LENGTH_10 = 10,
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
index 2a047f8ca0e9..1d748ac1d6d6 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
@@ -43,6 +43,9 @@
 #include "i2c_sw_engine_dce110.h"
 #include "i2c_hw_engine_dce110.h"
 #include "aux_engine_dce110.h"
+#include "../../dc.h"
+#include "dc_types.h"
+
 
 /*
  * Post-requisites: headers required by this unit
@@ -199,6 +202,7 @@ static const struct dce110_i2c_hw_engine_mask i2c_mask = {
 void dal_i2caux_dce110_construct(
 	struct i2caux_dce110 *i2caux_dce110,
 	struct dc_context *ctx,
+	unsigned int num_i2caux_inst,
 	const struct dce110_aux_registers aux_regs[],
 	const struct dce110_i2c_hw_engine_registers i2c_hw_engine_regs[],
 	const struct dce110_i2c_hw_engine_shift *i2c_shift,
@@ -249,9 +253,22 @@ void dal_i2caux_dce110_construct(
 
 		base->i2c_hw_engines[line_id] =
 			dal_i2c_hw_engine_dce110_create(&hw_arg_dce110);
-
+		if (base->i2c_hw_engines[line_id] != NULL) {
+			switch (ctx->dce_version) {
+			case DCN_VERSION_1_0:
+				base->i2c_hw_engines[line_id]->setup_limit =
+					I2C_SETUP_TIME_LIMIT_DCN;
+				base->i2c_hw_engines[line_id]->send_reset_length  = 0;
+			break;
+			default:
+				base->i2c_hw_engines[line_id]->setup_limit =
+					I2C_SETUP_TIME_LIMIT_DCE;
+				base->i2c_hw_engines[line_id]->send_reset_length  = 0;
+				break;
+			}
+		}
 		++i;
-	} while (i < ARRAY_SIZE(hw_ddc_lines));
+	} while (i < num_i2caux_inst);
 
 	/* Create AUX engines for all lines which has assisted HW AUX
 	 * 'i' (loop counter) used as DDC/AUX engine_id */
@@ -272,7 +289,7 @@ void dal_i2caux_dce110_construct(
 			dal_aux_engine_dce110_create(&aux_init_data);
 
 		++i;
-	} while (i < ARRAY_SIZE(hw_aux_lines));
+	} while (i < num_i2caux_inst);
 
 	/*TODO Generic I2C SW and HW*/
 }
@@ -303,6 +320,7 @@ struct i2caux *dal_i2caux_dce110_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce110_aux_regs),
 				    dce110_aux_regs,
 				    i2c_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
index 1b1f71c60ac9..d3d8cc58666a 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
@@ -45,6 +45,7 @@ struct i2caux *dal_i2caux_dce110_create(
 void dal_i2caux_dce110_construct(
 	struct i2caux_dce110 *i2caux_dce110,
 	struct dc_context *ctx,
+	unsigned int num_i2caux_inst,
 	const struct dce110_aux_registers *aux_regs,
 	const struct dce110_i2c_hw_engine_registers *i2c_hw_engine_regs,
 	const struct dce110_i2c_hw_engine_shift *i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
index dafc1a727f7f..a9db04738724 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
@@ -93,6 +93,7 @@ static void construct(
 {
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce112_aux_regs),
 				    dce112_aux_regs,
 				    dce112_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
index 0e7b18260027..6a4f344c1db4 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
@@ -111,6 +111,7 @@ struct i2caux *dal_i2caux_dce120_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce120_aux_regs),
 				    dce120_aux_regs,
 				    dce120_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
index e44a8901f38b..a59c1f50c1e8 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
@@ -111,6 +111,7 @@ struct i2caux *dal_i2caux_dcn10_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dcn10_aux_regs),
 				    dcn10_aux_regs,
 				    dcn10_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
index 1e8a1585e401..b16fb1ff687d 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
@@ -96,6 +96,7 @@ struct engine_funcs {
 
 struct engine {
 	const struct engine_funcs *funcs;
+	uint32_t inst;
 	struct ddc *ddc;
 	struct dc_context *ctx;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
index 58fc0f25eceb..ded6ea34b714 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
@@ -86,6 +86,8 @@ struct i2c_engine {
 	struct engine base;
 	const struct i2c_engine_funcs *funcs;
 	uint32_t timeout_delay;
+	uint32_t setup_limit;
+	uint32_t send_reset_length;
 };
 
 void dal_i2c_engine_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
index 14dc8c94d862..f7ed355fc84f 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
@@ -59,7 +59,7 @@
 
 #include "dce120/i2caux_dce120.h"
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/i2caux_dcn10.h"
 #endif
 
@@ -91,7 +91,7 @@ struct i2caux *dal_i2caux_create(
 		return dal_i2caux_dce100_create(ctx);
 	case DCE_VERSION_12_0:
 		return dal_i2caux_dce120_create(ctx);
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		return dal_i2caux_dcn10_create(ctx);
 #endif
@@ -254,7 +254,6 @@ bool dal_i2caux_submit_aux_command(
 			break;
 		}
 
-		cmd->payloads->length = request.payload.length;
 		++index_of_payload;
 	}
 
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 4beddca0180c..0fa385872ed3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -33,7 +33,7 @@
 #include "dc_bios_types.h"
 #include "mem_input.h"
 #include "hubp.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "mpc.h"
 #endif
 
@@ -138,7 +138,7 @@ struct resource_pool {
 	struct output_pixel_processor *opps[MAX_PIPES];
 	struct timing_generator *timing_generators[MAX_PIPES];
 	struct stream_encoder *stream_enc[MAX_PIPES * 2];
-
+	struct engine *engines[MAX_PIPES];
 	struct hubbub *hubbub;
 	struct mpc *mpc;
 	struct pp_smu_funcs_rv *pp_smu;
@@ -148,7 +148,6 @@ struct resource_pool {
 	unsigned int underlay_pipe_index;
 	unsigned int stream_enc_count;
 	unsigned int ref_clock_inKhz;
-	unsigned int dentist_vco_freq_khz;
 	unsigned int timing_generator_count;
 
 	/*
@@ -163,7 +162,7 @@ struct resource_pool {
 	unsigned int audio_count;
 	struct audio_support audio_support;
 
-	struct display_clock *display_clock;
+	struct dccg *dccg;
 	struct irq_service *irqs;
 
 	struct abm *abm;
@@ -222,7 +221,7 @@ struct pipe_ctx {
 	struct pipe_ctx *top_pipe;
 	struct pipe_ctx *bottom_pipe;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	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;
@@ -256,8 +255,7 @@ struct dce_bw_output {
 };
 
 struct dcn_bw_output {
-	struct dc_clocks cur_clk;
-	struct dc_clocks calc_clk;
+	struct dc_clocks clk;
 	struct dcn_watermark_set watermarks;
 };
 
@@ -278,11 +276,11 @@ 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_X86
 	struct dcn_bw_internal_vars dcn_bw_vars;
 #endif
 
-	struct display_clock *dis_clk;
+	struct dccg *dis_clk;
 
 	struct kref refcount;
 };
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 30b3a08b91be..538b83303b86 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
@@ -102,22 +102,13 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
-		struct ddc_service *ddc,
-		bool i2c,
-		enum i2c_mot_mode mot,
-		uint32_t address,
-		uint8_t *data,
-		uint32_t len,
-		uint32_t *read);
-
-enum ddc_result dal_ddc_service_write_dpcd_data(
-		struct ddc_service *ddc,
-		bool i2c,
-		enum i2c_mot_mode mot,
-		uint32_t address,
-		const uint8_t *data,
-		uint32_t len);
+int dc_link_aux_transfer(struct ddc_service *ddc,
+			     unsigned int address,
+			     uint8_t *reply,
+			     void *buffer,
+			     unsigned int size,
+			     enum aux_transaction_type type,
+			     enum i2caux_transaction_action action);
 
 void dal_ddc_service_write_scdc_data(
 		struct ddc_service *ddc_service,
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 2f783c650084..697b5ee73845 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
@@ -33,7 +33,7 @@ struct dc_link;
 struct dc_stream_state;
 struct dc_link_settings;
 
-bool dp_hbr_verify_link_cap(
+bool dp_verify_link_cap(
 	struct dc_link *link,
 	struct dc_link_settings *known_limit_link_setting);
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
index 132d18d4b293..ddbb673caa08 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
@@ -625,7 +625,7 @@ bool dcn_validate_bandwidth(
 
 unsigned int dcn_find_dcfclk_suits_all(
 	const struct dc *dc,
-	struct clocks_value *clocks);
+	struct dc_clocks *clocks);
 
 void dcn_bw_update_from_pplib(struct dc *dc);
 void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
new file mode 100644
index 000000000000..06d7e5d4cf21
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
@@ -0,0 +1,113 @@
+/*
+ * 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
+ *
+ */
+
+#ifndef __DAL_AUX_ENGINE_H__
+#define __DAL_AUX_ENGINE_H__
+
+#include "engine.h"
+#include "include/i2caux_interface.h"
+
+struct aux_engine;
+union aux_config;
+struct aux_engine_funcs {
+	void (*destroy)(
+		struct aux_engine **ptr);
+	bool (*acquire_engine)(
+		struct aux_engine *engine);
+	void (*configure)(
+		struct aux_engine *engine,
+		union aux_config cfg);
+	void (*submit_channel_request)(
+		struct aux_engine *engine,
+		struct aux_request_transaction_data *request);
+	void (*process_channel_reply)(
+		struct aux_engine *engine,
+		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
+	enum aux_channel_operation_result (*get_channel_status)(
+		struct aux_engine *engine,
+		uint8_t *returned_bytes);
+	bool (*is_engine_available)(struct aux_engine *engine);
+};
+struct engine;
+struct aux_engine {
+	struct engine base;
+	const struct aux_engine_funcs *funcs;
+	/* following values are expressed in milliseconds */
+	uint32_t delay;
+	uint32_t max_defer_write_retry;
+
+	bool acquire_reset;
+};
+struct read_command_context {
+	uint8_t *buffer;
+	uint32_t current_read_length;
+	uint32_t offset;
+	enum i2caux_transaction_status status;
+
+	struct aux_request_transaction_data request;
+	struct aux_reply_transaction_data reply;
+
+	uint8_t returned_byte;
+
+	uint32_t timed_out_retry_aux;
+	uint32_t invalid_reply_retry_aux;
+	uint32_t defer_retry_aux;
+	uint32_t defer_retry_i2c;
+	uint32_t invalid_reply_retry_aux_on_ack;
+
+	bool transaction_complete;
+	bool operation_succeeded;
+};
+struct write_command_context {
+	bool mot;
+
+	uint8_t *buffer;
+	uint32_t current_write_length;
+	enum i2caux_transaction_status status;
+
+	struct aux_request_transaction_data request;
+	struct aux_reply_transaction_data reply;
+
+	uint8_t returned_byte;
+
+	uint32_t timed_out_retry_aux;
+	uint32_t invalid_reply_retry_aux;
+	uint32_t defer_retry_aux;
+	uint32_t defer_retry_i2c;
+	uint32_t max_defer_retry;
+	uint32_t ack_m_retry;
+
+	uint8_t reply_data[DEFAULT_AUX_MAX_DATA_SIZE];
+
+	bool transaction_complete;
+	bool operation_succeeded;
+};
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
index f5f69cd81f6f..3c7ccb68ecdb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
@@ -27,23 +27,7 @@
 #define __DISPLAY_CLOCK_H__
 
 #include "dm_services_types.h"
-
-
-struct clocks_value {
-	int dispclk_in_khz;
-	int max_pixelclk_in_khz;
-	int max_non_dp_phyclk_in_khz;
-	int max_dp_phyclk_in_khz;
-	bool dispclk_notify_pplib_done;
-	bool pixelclk_notify_pplib_done;
-	bool phyclk_notigy_pplib_done;
-	int dcfclock_in_khz;
-	int dppclk_in_khz;
-	int mclk_in_khz;
-	int phyclk_in_khz;
-	int common_vdd_level;
-};
-
+#include "dc.h"
 
 /* Structure containing all state-dependent clocks
  * (dependent on "enum clocks_state") */
@@ -52,34 +36,23 @@ struct state_dependent_clocks {
 	int pixel_clk_khz;
 };
 
-struct display_clock {
+struct dccg {
 	struct dc_context *ctx;
 	const struct display_clock_funcs *funcs;
 
 	enum dm_pp_clocks_state max_clks_state;
 	enum dm_pp_clocks_state cur_min_clks_state;
-	struct clocks_value cur_clocks_value;
+	struct dc_clocks clks;
 };
 
 struct display_clock_funcs {
-	int (*set_clock)(struct display_clock *disp_clk,
+	void (*update_clocks)(struct dccg *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower);
+	int (*set_dispclk)(struct dccg *dccg,
 		int requested_clock_khz);
 
-	enum dm_pp_clocks_state (*get_required_clocks_state)(
-		struct display_clock *disp_clk,
-		struct state_dependent_clocks *req_clocks);
-
-	bool (*set_min_clocks_state)(struct display_clock *disp_clk,
-		enum dm_pp_clocks_state dm_pp_clocks_state);
-
-	int (*get_dp_ref_clk_frequency)(struct display_clock *disp_clk);
-
-	bool (*apply_clock_voltage_request)(
-		struct display_clock *disp_clk,
-		enum dm_pp_clock_type clocks_type,
-		int clocks_in_khz,
-		bool pre_mode_set,
-		bool update_dp_phyclk);
+	int (*get_dp_ref_clk_frequency)(struct dccg *dccg);
 };
 
 #endif /* __DISPLAY_CLOCK_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 582458f028f8..74ad94b0e4f0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -151,6 +151,9 @@ struct dpp_funcs {
 	void (*dpp_set_hdr_multiplier)(
 			struct dpp *dpp_base,
 			uint32_t multiplier);
+	void (*set_optional_cursor_attributes)(
+			struct dpp *dpp_base,
+			struct dpp_cursor_attributes *attr);
 
 	void (*dpp_dppclk_control)(
 			struct dpp *dpp_base,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h
new file mode 100644
index 000000000000..1f5476f41236
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h
@@ -0,0 +1,106 @@
+/*
+ * 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
+ *
+ */
+
+#ifndef __DAL_ENGINE_H__
+#define __DAL_ENGINE_H__
+
+#include "dc_ddc_types.h"
+
+enum i2caux_transaction_operation {
+	I2CAUX_TRANSACTION_READ,
+	I2CAUX_TRANSACTION_WRITE
+};
+
+enum i2caux_transaction_address_space {
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C = 1,
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD
+};
+
+struct i2caux_transaction_payload {
+	enum i2caux_transaction_address_space address_space;
+	uint32_t address;
+	uint32_t length;
+	uint8_t *data;
+};
+
+enum i2caux_transaction_status {
+	I2CAUX_TRANSACTION_STATUS_UNKNOWN = (-1L),
+	I2CAUX_TRANSACTION_STATUS_SUCCEEDED,
+	I2CAUX_TRANSACTION_STATUS_FAILED_CHANNEL_BUSY,
+	I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT,
+	I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR,
+	I2CAUX_TRANSACTION_STATUS_FAILED_NACK,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
+	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
+	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
+};
+
+struct i2caux_transaction_request {
+	enum i2caux_transaction_operation operation;
+	struct i2caux_transaction_payload payload;
+	enum i2caux_transaction_status status;
+};
+
+enum i2caux_engine_type {
+	I2CAUX_ENGINE_TYPE_UNKNOWN = (-1L),
+	I2CAUX_ENGINE_TYPE_AUX,
+	I2CAUX_ENGINE_TYPE_I2C_DDC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_GENERIC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_SW
+};
+
+enum i2c_default_speed {
+	I2CAUX_DEFAULT_I2C_HW_SPEED = 50,
+	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
+};
+
+struct engine;
+
+struct engine_funcs {
+	enum i2caux_engine_type (*get_engine_type)(
+		const struct engine *engine);
+	struct aux_engine* (*acquire)(
+		struct engine *engine,
+		struct ddc *ddc);
+	bool (*submit_request)(
+		struct engine *engine,
+		struct i2caux_transaction_request *request,
+		bool middle_of_transaction);
+	void (*release_engine)(
+		struct engine *engine);
+	void (*destroy_engine)(
+		struct engine **engine);
+};
+
+struct engine {
+	const struct engine_funcs *funcs;
+	uint32_t inst;
+	struct ddc *ddc;
+	struct dc_context *ctx;
+};
+
+#endif
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 97df82cddf82..4f3f9e68ccfa 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -43,10 +43,9 @@ enum cursor_lines_per_chunk {
 };
 
 struct hubp {
-	struct hubp_funcs *funcs;
+	const struct hubp_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
-	struct dc_plane_address current_address;
 	int inst;
 
 	/* run time states */
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 47f1dc5a43b7..da89c2edb07c 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
@@ -64,7 +64,7 @@ struct stutter_modes {
 };
 
 struct mem_input {
-	struct mem_input_funcs *funcs;
+	const struct mem_input_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
 	struct dc_plane_address current_address;
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 a71770ed4b9f..a14ce4de80b2 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -44,6 +44,7 @@ struct dce_hwseq_wa {
 	bool blnd_crtc_trigger;
 	bool DEGVIDCN10_253;
 	bool false_optc_underflow;
+	bool DEGVIDCN10_254;
 };
 
 struct hwseq_wa_state {
@@ -101,10 +102,18 @@ struct hw_sequencer_funcs {
 		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);
 
+	void (*update_mpcc)(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx);
+
 	void (*update_pending_status)(
 			struct pipe_ctx *pipe_ctx);
 
@@ -171,7 +180,7 @@ struct hw_sequencer_funcs {
 	void (*set_bandwidth)(
 			struct dc *dc,
 			struct dc_state *context,
-			bool decrease_allowed);
+			bool safe_to_lower);
 
 	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
 			int vmin, int vmax);
@@ -214,6 +223,7 @@ struct hw_sequencer_funcs {
 
 	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);
 
 };
 
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 3306e7b0b3e3..cf5a84b9e27c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
@@ -445,4 +445,50 @@ uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
 		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
 		uint8_t shift7, uint32_t mask7, uint32_t *field_value7,
 		uint8_t shift8, uint32_t mask8, uint32_t *field_value8);
+
+
+/* indirect register access */
+
+#define IX_REG_SET_N(index_reg_name, data_reg_name, index, n, initial_val, ...)	\
+		generic_indirect_reg_update_ex(CTX, \
+				REG(index_reg_name), REG(data_reg_name), IND_REG(index), \
+				initial_val, \
+				n, __VA_ARGS__)
+
+#define IX_REG_SET_2(index_reg_name, data_reg_name, index, init_value, f1, v1, f2, v2)	\
+		IX_REG_SET_N(index_reg_name, data_reg_name, index, 2, init_value, \
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+
+#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_UPDATE_N(index_reg_name, data_reg_name, index, n, ...)	\
+		generic_indirect_reg_update_ex(CTX, \
+				REG(index_reg_name), REG(data_reg_name), IND_REG(index), \
+				IX_REG_READ(index_reg_name, data_reg_name, index), \
+				n, __VA_ARGS__)
+
+#define IX_REG_UPDATE_2(index_reg_name, data_reg_name, index, f1, v1, f2, v2)	\
+		IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, 2,\
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data);
+
+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_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,
+		...);
+
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_REG_HELPER_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index 498515aad4a5..a76ee600ecee 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -60,7 +60,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCE12)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 IRQ_DCN1 = irq_service_dcn10.o
 
 AMD_DAL_IRQ_DCN1 = $(addprefix $(AMDDALPATH)/dc/irq/dcn10/,$(IRQ_DCN1))
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 dcdfa0f01551..ae3fd0a235ba 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -36,7 +36,7 @@
 #include "dce120/irq_service_dce120.h"
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/irq_service_dcn10.h"
 #endif
 
@@ -78,7 +78,7 @@ const struct irq_source_info *find_irq_source_info(
 	struct irq_service *irq_service,
 	enum dc_irq_source source)
 {
-	if (source > DAL_IRQ_SOURCES_NUMBER || source < DC_IRQ_SOURCE_INVALID)
+	if (source >= DAL_IRQ_SOURCES_NUMBER || source < DC_IRQ_SOURCE_INVALID)
 		return NULL;
 
 	return &irq_service->info[source];
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index a407892905af..c9fce9066ad8 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -48,7 +48,7 @@
 
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include <asm/fpu/api.h>
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
index d8e52e3b8e3c..1c66166d0a94 100644
--- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h
+++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
@@ -27,6 +27,9 @@
 #define __DAL_DPCD_DEFS_H__
 
 #include <drm/drm_dp_helper.h>
+#ifndef DP_SINK_HW_REVISION_START // can remove this once the define gets into linux drm_dp_helper.h
+#define DP_SINK_HW_REVISION_START 0x409
+#endif
 
 enum dpcd_revision {
 	DPCD_REV_10 = 0x10,
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_defs.h
index 2941b882b0b6..58bb42ed85ca 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_defs.h
@@ -37,6 +37,10 @@
  * ********************************************************************
  */
 
+#define MAX_CONNECTOR_NUMBER_PER_SLOT	(16)
+#define MAX_BOARD_SLOTS					(4)
+#define INVALID_CONNECTOR_INDEX			((unsigned int)(-1))
+
 /* HPD unit id - HW direct translation */
 enum hpd_source_id {
 	HPD_SOURCEID1 = 0,
@@ -136,5 +140,47 @@ enum sync_source {
 	SYNC_SOURCE_DUAL_GPU_PIN
 };
 
+/* connector sizes in millimeters - from BiosParserTypes.hpp */
+#define CONNECTOR_SIZE_DVI			40
+#define CONNECTOR_SIZE_VGA			32
+#define CONNECTOR_SIZE_HDMI			16
+#define CONNECTOR_SIZE_DP			16
+#define CONNECTOR_SIZE_MINI_DP			9
+#define CONNECTOR_SIZE_UNKNOWN			30
+
+enum connector_layout_type {
+	CONNECTOR_LAYOUT_TYPE_UNKNOWN,
+	CONNECTOR_LAYOUT_TYPE_DVI_D,
+	CONNECTOR_LAYOUT_TYPE_DVI_I,
+	CONNECTOR_LAYOUT_TYPE_VGA,
+	CONNECTOR_LAYOUT_TYPE_HDMI,
+	CONNECTOR_LAYOUT_TYPE_DP,
+	CONNECTOR_LAYOUT_TYPE_MINI_DP,
+};
+struct connector_layout_info {
+	struct graphics_object_id connector_id;
+	enum connector_layout_type connector_type;
+	unsigned int length;
+	unsigned int position;  /* offset in mm from right side of the board */
+};
+
+/* length and width in mm */
+struct slot_layout_info {
+	unsigned int length;
+	unsigned int width;
+	unsigned int num_of_connectors;
+	struct connector_layout_info connectors[MAX_CONNECTOR_NUMBER_PER_SLOT];
+};
+
+struct board_layout_info {
+	unsigned int num_of_slots;
 
+	/* indicates valid information in bracket layout structure. */
+	unsigned int is_number_of_slots_valid : 1;
+	unsigned int is_slots_size_valid : 1;
+	unsigned int is_connector_offsets_valid : 1;
+	unsigned int is_connector_lengths_valid : 1;
+
+	struct slot_layout_info slots[MAX_BOARD_SLOTS];
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_id.h b/drivers/gpu/drm/amd/display/include/grph_object_id.h
index c4197432eb7c..33b3d755fe65 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_id.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_id.h
@@ -197,6 +197,11 @@ enum transmitter_color_depth {
 	TRANSMITTER_COLOR_DEPTH_48       /* 16 bits */
 };
 
+enum dp_alt_mode {
+	DP_Alt_mode__Unknown = 0,
+	DP_Alt_mode__Connect,
+	DP_Alt_mode__NoConnect,
+};
 /*
  *****************************************************************************
  * graphics_object_id struct
@@ -287,4 +292,15 @@ static inline enum engine_id dal_graphics_object_id_get_engine_id(
 		return (enum engine_id) id.id;
 	return ENGINE_ID_UNKNOWN;
 }
+
+static inline bool dal_graphics_object_id_equal(
+	struct graphics_object_id id_1,
+	struct graphics_object_id id_2)
+{
+	if ((id_1.id == id_2.id) && (id_1.enum_id == id_2.enum_id) &&
+		(id_1.type == id_2.type)) {
+		return true;
+	}
+	return false;
+}
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h
index 0f10ed710e0d..e3c79616682d 100644
--- a/drivers/gpu/drm/amd/display/include/logger_interface.h
+++ b/drivers/gpu/drm/amd/display/include/logger_interface.h
@@ -40,49 +40,7 @@ struct dc_state;
  *
  */
 
-struct dal_logger *dal_logger_create(struct dc_context *ctx, uint32_t log_mask);
-
-uint32_t dal_logger_destroy(struct dal_logger **logger);
-
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn);
-
-void dm_logger_write(
-		struct dal_logger *logger,
-		enum dc_log_type log_type,
-		const char *msg,
-		...);
-
-void dm_logger_append(
-		struct log_entry *entry,
-		const char *msg,
-		...);
-
-void dm_logger_append_va(
-		struct log_entry *entry,
-		const char *msg,
-		va_list args);
-
-void dm_logger_append_heading(struct log_entry *entry);
-
-void dm_logger_open(
-		struct dal_logger *logger,
-		struct log_entry *entry,
-		enum dc_log_type log_type);
-
-void dm_logger_close(struct log_entry *entry);
-
-void dc_conn_log(struct dc_context *ctx,
-		const struct dc_link *link,
-		uint8_t *hex_data,
-		int hex_data_count,
-		enum dc_log_type event,
-		const char *msg,
-		...);
-
-void logger_write(struct dal_logger *logger,
-		enum dc_log_type log_type,
-		const char *msg,
-		void *paralist);
+void dc_conn_log_hex_linux(const uint8_t *hex_data, int hex_data_count);
 
 void pre_surface_trace(
 		struct dc *dc,
@@ -108,28 +66,31 @@ void context_clock_trace(
  * marked by this macro.
  * Note that the message will be printed exactly once for every function
  * it is used in order to avoid repeating of the same message. */
+
 #define DAL_LOGGER_NOT_IMPL(fmt, ...) \
-{ \
-	static bool print_not_impl = true; \
-\
-	if (print_not_impl == true) { \
-		print_not_impl = false; \
-		dm_logger_write(ctx->logger, LOG_WARNING, \
-		"DAL_NOT_IMPL: " fmt, ##__VA_ARGS__); \
-	} \
-}
+	do { \
+		static bool print_not_impl = true; \
+		if (print_not_impl == true) { \
+			print_not_impl = false; \
+			DRM_WARN("DAL_NOT_IMPL: " fmt, ##__VA_ARGS__); \
+		} \
+	} while (0)
 
 /******************************************************************************
  * Convenience macros to save on typing.
  *****************************************************************************/
 
 #define DC_ERROR(...) \
-	dm_logger_write(dc_ctx->logger, LOG_ERROR, \
-		__VA_ARGS__)
+		do { \
+			(void)(dc_ctx); \
+			DC_LOG_ERROR(__VA_ARGS__); \
+		} while (0)
 
 #define DC_SYNC_INFO(...) \
-	dm_logger_write(dc_ctx->logger, LOG_SYNC, \
-		__VA_ARGS__)
+		do { \
+			(void)(dc_ctx); \
+			DC_LOG_SYNC(__VA_ARGS__); \
+		} while (0)
 
 /* Connectivity log format:
  * [time stamp]   [drm] [Major_minor] [connector name] message.....
@@ -139,20 +100,30 @@ void context_clock_trace(
  */
 
 #define CONN_DATA_DETECT(link, hex_data, hex_len, ...) \
-		dc_conn_log(link->ctx, link, hex_data, hex_len, \
-				LOG_EVENT_DETECTION, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			dc_conn_log_hex_linux(hex_data, hex_len); \
+			DC_LOG_EVENT_DETECTION(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_DATA_LINK_LOSS(link, hex_data, hex_len, ...) \
-		dc_conn_log(link->ctx, link, hex_data, hex_len, \
-				LOG_EVENT_LINK_LOSS, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			dc_conn_log_hex_linux(hex_data, hex_len); \
+			DC_LOG_EVENT_LINK_LOSS(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_MSG_LT(link, ...) \
-		dc_conn_log(link->ctx, link, NULL, 0, \
-				LOG_EVENT_LINK_TRAINING, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			DC_LOG_EVENT_LINK_TRAINING(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_MSG_MODE(link, ...) \
-		dc_conn_log(link->ctx, link, NULL, 0, \
-				LOG_EVENT_MODE_SET, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			DC_LOG_EVENT_MODE_SET(__VA_ARGS__); \
+		} while (0)
 
 /*
  * Display Test Next logging
@@ -167,38 +138,21 @@ void context_clock_trace(
 	dm_dtn_log_end(dc_ctx)
 
 #define PERFORMANCE_TRACE_START() \
-	unsigned long long perf_trc_start_stmp = dm_get_timestamp(dc->ctx); \
-	unsigned long long perf_trc_start_log_msk = dc->ctx->logger->mask; \
-	unsigned int perf_trc_start_log_flags = dc->ctx->logger->flags.value; \
-	if (dc->debug.performance_trace) {\
-		dm_logger_flush_buffer(dc->ctx->logger, false);\
-		dc->ctx->logger->mask = 1<<LOG_PERF_TRACE;\
-		dc->ctx->logger->flags.bits.ENABLE_CONSOLE = 0;\
-		dc->ctx->logger->flags.bits.ENABLE_BUFFER = 1;\
-	}
-
-#define PERFORMANCE_TRACE_END() do {\
-	unsigned long long perf_trc_end_stmp = dm_get_timestamp(dc->ctx);\
-	if (dc->debug.performance_trace) {\
-		dm_logger_write(dc->ctx->logger, \
-				LOG_PERF_TRACE, \
-				"%s duration: %d ticks\n", __func__,\
+	unsigned long long perf_trc_start_stmp = dm_get_timestamp(dc->ctx)
+
+#define PERFORMANCE_TRACE_END() \
+	do { \
+		unsigned long long perf_trc_end_stmp = dm_get_timestamp(dc->ctx); \
+		if (dc->debug.performance_trace) { \
+			DC_LOG_PERF_TRACE("%s duration: %lld ticks\n", __func__, \
 				perf_trc_end_stmp - perf_trc_start_stmp); \
-		if (perf_trc_start_log_msk != 1<<LOG_PERF_TRACE) {\
-			dc->ctx->logger->mask = perf_trc_start_log_msk;\
-			dc->ctx->logger->flags.value = perf_trc_start_log_flags;\
-			dm_logger_flush_buffer(dc->ctx->logger, false);\
 		} \
-	} \
-} while (0)
+	} while (0)
 
-#define DISPLAY_STATS_BEGIN(entry) \
-	dm_logger_open(dc->ctx->logger, &entry, LOG_DISPLAYSTATS)
+#define DISPLAY_STATS_BEGIN(entry) (void)(entry)
 
-#define DISPLAY_STATS(msg, ...) \
-	dm_logger_append(&log_entry, msg, ##__VA_ARGS__)
+#define DISPLAY_STATS(msg, ...) DC_LOG_PERF_TRACE(msg, __VA_ARGS__)
 
-#define DISPLAY_STATS_END(entry) \
-	dm_logger_close(&entry)
+#define DISPLAY_STATS_END(entry) (void)(entry)
 
 #endif /* __DAL_LOGGER_INTERFACE_H__ */
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index 0a540b9897a6..ad3695e67b76 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -138,63 +138,4 @@ enum dc_log_type {
 		(1 << LOG_HW_AUDIO)| \
 		(1 << LOG_BANDWIDTH_CALCS)*/
 
-union logger_flags {
-	struct {
-		uint32_t ENABLE_CONSOLE:1; /* Print to console */
-		uint32_t ENABLE_BUFFER:1; /* Print to buffer */
-		uint32_t RESERVED:30;
-	} bits;
-	uint32_t value;
-};
-
-struct log_entry {
-	struct dal_logger *logger;
-	enum dc_log_type type;
-
-	char *buf;
-	uint32_t buf_offset;
-	uint32_t max_buf_bytes;
-};
-
-/**
-* Structure for enumerating log types
-*/
-struct dc_log_type_info {
-	enum dc_log_type type;
-	char name[MAX_NAME_LEN];
-};
-
-/* Structure for keeping track of offsets, buffer, etc */
-
-#define DAL_LOGGER_BUFFER_MAX_SIZE 2048
-
-/*Connectivity log needs to output EDID, which needs at lease 256x3 bytes,
- * change log line size to 896 to meet the request.
- */
-#define LOG_MAX_LINE_SIZE 896
-
-struct dal_logger {
-
-	/* How far into the circular buffer has been read by dsat
-	 * Read offset should never cross write offset. Write \0's to
-	 * read data just to be sure?
-	 */
-	uint32_t buffer_read_offset;
-
-	/* How far into the circular buffer we have written
-	 * Write offset should never cross read offset
-	 */
-	uint32_t buffer_write_offset;
-
-	uint32_t open_count;
-
-	char *log_buffer;	/* Pointer to malloc'ed buffer */
-	uint32_t log_buffer_size; /* Size of circular buffer */
-
-	uint32_t mask; /*array of masks for major elements*/
-
-	union logger_flags flags;
-	struct dc_context *ctx;
-};
-
 #endif /* __DAL_LOGGER_TYPES_H__ */
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 98edaefa2b47..ee69c949bfbf 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -1723,8 +1723,8 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		kvfree(rgb_regamma);
 	} else if (trans == TRANSFER_FUNCTION_HLG ||
 		trans == TRANSFER_FUNCTION_HLG12) {
-		rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
-				       (MAX_HW_POINTS + _EXTRA_POINTS),
+		rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS,
+				       sizeof(*rgb_regamma),
 				       GFP_KERNEL);
 		if (!rgb_regamma)
 			goto rgb_regamma_alloc_fail;
@@ -1802,8 +1802,8 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		kvfree(rgb_degamma);
 	} else if (trans == TRANSFER_FUNCTION_HLG ||
 		trans == TRANSFER_FUNCTION_HLG12) {
-		rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
-				       (MAX_HW_POINTS + _EXTRA_POINTS),
+		rgb_degamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS,
+				       sizeof(*rgb_degamma),
 				       GFP_KERNEL);
 		if (!rgb_degamma)
 			goto rgb_degamma_alloc_fail;
diff --git a/drivers/gpu/drm/amd/display/modules/color/luts_1d.h b/drivers/gpu/drm/amd/display/modules/color/luts_1d.h
new file mode 100644
index 000000000000..66b1fad572ac
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/color/luts_1d.h
@@ -0,0 +1,51 @@
+/*
+ * 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 LUTS_1D_H
+#define LUTS_1D_H
+
+#include "hw_shared.h"
+
+struct point_config {
+	uint32_t custom_float_x;
+	uint32_t custom_float_y;
+	uint32_t custom_float_slope;
+};
+
+struct lut_point {
+	uint32_t red;
+	uint32_t green;
+	uint32_t blue;
+	uint32_t delta_red;
+	uint32_t delta_green;
+	uint32_t delta_blue;
+};
+
+struct pwl_1dlut_parameter {
+	struct gamma_curve	arr_curve_points[34];
+	struct point_config	arr_points[2];
+	struct lut_point rgb_resulted[256];
+	uint32_t hw_points_num;
+};
+#endif // LUTS_1D_H
diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h
index 5eb895fd98bf..9cb9ceb4d74d 100644
--- a/drivers/gpu/drm/amd/include/amd_pcie.h
+++ b/drivers/gpu/drm/amd/include/amd_pcie.h
@@ -27,6 +27,7 @@
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1        0x00010000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2        0x00020000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3        0x00040000
+#define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4        0x00080000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_MASK        0xFFFF0000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT       16
 
@@ -34,6 +35,7 @@
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1   0x00000001
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2   0x00000002
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3   0x00000004
+#define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4   0x00000008
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_MASK   0x0000FFFF
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_SHIFT  0
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index b178176b72ac..265621d8945c 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -128,47 +128,57 @@ enum PP_FEATURE_MASK {
 	PP_OVERDRIVE_MASK = 0x4000,
 	PP_GFXOFF_MASK = 0x8000,
 	PP_ACG_MASK = 0x10000,
+	PP_STUTTER_MODE = 0x20000,
 };
 
+/**
+ * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks
+ */
 struct amd_ip_funcs {
-	/* Name of IP block */
+	/** @name: Name of IP block */
 	char *name;
-	/* sets up early driver state (pre sw_init), does not configure hw - Optional */
+	/**
+	 * @early_init:
+	 *
+	 * sets up early driver state (pre sw_init),
+	 * does not configure hw - Optional
+	 */
 	int (*early_init)(void *handle);
-	/* sets up late driver/hw state (post hw_init) - Optional */
+	/** @late_init: sets up late driver/hw state (post hw_init) - Optional */
 	int (*late_init)(void *handle);
-	/* sets up driver state, does not configure hw */
+	/** @sw_init: sets up driver state, does not configure hw */
 	int (*sw_init)(void *handle);
-	/* tears down driver state, does not configure hw */
+	/** @sw_fini: tears down driver state, does not configure hw */
 	int (*sw_fini)(void *handle);
-	/* sets up the hw state */
+	/** @hw_init: sets up the hw state */
 	int (*hw_init)(void *handle);
-	/* tears down the hw state */
+	/** @hw_fini: tears down the hw state */
 	int (*hw_fini)(void *handle);
+	/** @late_fini: final cleanup */
 	void (*late_fini)(void *handle);
-	/* handles IP specific hw/sw changes for suspend */
+	/** @suspend: handles IP specific hw/sw changes for suspend */
 	int (*suspend)(void *handle);
-	/* handles IP specific hw/sw changes for resume */
+	/** @resume: handles IP specific hw/sw changes for resume */
 	int (*resume)(void *handle);
-	/* returns current IP block idle status */
+	/** @is_idle: returns current IP block idle status */
 	bool (*is_idle)(void *handle);
-	/* poll for idle */
+	/** @wait_for_idle: poll for idle */
 	int (*wait_for_idle)(void *handle);
-	/* check soft reset the IP block */
+	/** @check_soft_reset: check soft reset the IP block */
 	bool (*check_soft_reset)(void *handle);
-	/* pre soft reset the IP block */
+	/** @pre_soft_reset: pre soft reset the IP block */
 	int (*pre_soft_reset)(void *handle);
-	/* soft reset the IP block */
+	/** @soft_reset: soft reset the IP block */
 	int (*soft_reset)(void *handle);
-	/* post soft reset the IP block */
+	/** @post_soft_reset: post soft reset the IP block */
 	int (*post_soft_reset)(void *handle);
-	/* enable/disable cg for the IP block */
+	/** @set_clockgating_state: enable/disable cg for the IP block */
 	int (*set_clockgating_state)(void *handle,
 				     enum amd_clockgating_state state);
-	/* enable/disable pg for the IP block */
+	/** @set_powergating_state: enable/disable pg for the IP block */
 	int (*set_powergating_state)(void *handle,
 				     enum amd_powergating_state state);
-	/* get current clockgating status */
+	/** @get_clockgating_state: get current clockgating status */
 	void (*get_clockgating_state)(void *handle, u32 *flags);
 };
 
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 092d800b703a..33b4de4ad66e 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -1433,7 +1433,10 @@ struct atom_smc_dpm_info_v4_1
 	uint8_t  acggfxclkspreadpercent;
 	uint16_t acggfxclkspreadfreq;
 
-	uint32_t boardreserved[10];
+	uint8_t Vr2_I2C_address;
+	uint8_t padding_vr2[3];
+
+	uint32_t boardreserved[9];
 };
 
 /* 
diff --git a/drivers/gpu/drm/amd/include/dm_pp_interface.h b/drivers/gpu/drm/amd/include/dm_pp_interface.h
index 7852952d1fde..1d93a0c574c9 100644
--- a/drivers/gpu/drm/amd/include/dm_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/dm_pp_interface.h
@@ -23,6 +23,8 @@
 #ifndef _DM_PP_INTERFACE_
 #define _DM_PP_INTERFACE_
 
+#include "dm_services_types.h"
+
 #define PP_MAX_CLOCK_LEVELS 16
 
 enum amd_pp_display_config_type{
@@ -189,39 +191,4 @@ struct pp_display_clock_request {
 	uint32_t clock_freq_in_khz;
 };
 
-#define PP_MAX_WM_SETS 4
-
-enum pp_wm_set_id {
-	DC_WM_SET_A = 0,
-	DC_WM_SET_B,
-	DC_WM_SET_C,
-	DC_WM_SET_D,
-	DC_WM_SET_INVALID = 0xffff,
-};
-
-struct pp_wm_set_with_dmif_clock_range_soc15 {
-	enum pp_wm_set_id wm_set_id;
-	uint32_t wm_min_dcefclk_in_khz;
-	uint32_t wm_max_dcefclk_in_khz;
-	uint32_t wm_min_memclk_in_khz;
-	uint32_t wm_max_memclk_in_khz;
-};
-
-struct pp_wm_set_with_mcif_clock_range_soc15 {
-	enum pp_wm_set_id wm_set_id;
-	uint32_t wm_min_socclk_in_khz;
-	uint32_t wm_max_socclk_in_khz;
-	uint32_t wm_min_memclk_in_khz;
-	uint32_t wm_max_memclk_in_khz;
-};
-
-struct pp_wm_sets_with_clock_ranges_soc15 {
-	uint32_t num_wm_sets_dmif;
-	uint32_t num_wm_sets_mcif;
-	struct pp_wm_set_with_dmif_clock_range_soc15
-		wm_sets_dmif[PP_MAX_WM_SETS];
-	struct pp_wm_set_with_mcif_clock_range_soc15
-		wm_sets_mcif[PP_MAX_WM_SETS];
-};
-
 #endif /* _DM_PP_INTERFACE_ */
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
new file mode 100644
index 000000000000..36306c57a2b4
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_GFX_9_0_H__
+#define __IRQSRCS_GFX_9_0_H__
+
+
+#define GFX_9_0__SRCID__CP_RB_INTERRUPT_PKT					176		/* B0 CP_INTERRUPT pkt in RB */
+#define GFX_9_0__SRCID__CP_IB1_INTERRUPT_PKT				177		/* B1 CP_INTERRUPT pkt in IB1 */
+#define GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT				178		/* B2 CP_INTERRUPT pkt in IB2 */
+#define GFX_9_0__SRCID__CP_PM4_PKT_RSVD_BIT_ERROR			180		/* B4 PM4 Pkt Rsvd Bits Error */
+#define GFX_9_0__SRCID__CP_EOP_INTERRUPT					181		/* B5 End-of-Pipe Interrupt */
+#define GFX_9_0__SRCID__CP_BAD_OPCODE_ERROR					183		/* B7 Bad Opcode Error */
+#define GFX_9_0__SRCID__CP_PRIV_REG_FAULT					184		/* B8 Privileged Register Fault */
+#define GFX_9_0__SRCID__CP_PRIV_INSTR_FAULT					185		/* B9 Privileged Instr Fault */
+#define GFX_9_0__SRCID__CP_WAIT_MEM_SEM_FAULT				186		/* BA Wait Memory Semaphore Fault (Synchronization Object Fault) */
+#define GFX_9_0__SRCID__CP_CTX_EMPTY_INTERRUPT				187		/* BB Context Empty Interrupt */
+#define GFX_9_0__SRCID__CP_CTX_BUSY_INTERRUPT				188		/* BC Context Busy Interrupt */
+#define GFX_9_0__SRCID__CP_ME_WAIT_REG_MEM_POLL_TIMEOUT		192		/* C0 CP.ME Wait_Reg_Mem Poll Timeout */
+#define GFX_9_0__SRCID__CP_SIG_INCOMPLETE					193		/* C1 "Surface Probe Fault Signal Incomplete" */
+#define GFX_9_0__SRCID__CP_PREEMPT_ACK					    194		/* C2 Preemption Ack-wledge */
+#define GFX_9_0__SRCID__CP_GPF					            195		/* C3 General Protection Fault (GPF) */
+#define GFX_9_0__SRCID__CP_GDS_ALLOC_ERROR					196		/* C4 GDS Alloc Error */
+#define GFX_9_0__SRCID__CP_ECC_ERROR					    197		/* C5 ECC  Error */
+#define GFX_9_0__SRCID__CP_COMPUTE_QUERY_STATUS             199     /* C7 Compute query status */
+#define GFX_9_0__SRCID__CP_VM_DOORBELL					    200		/* C8 Unattached VM Doorbell Received */
+#define GFX_9_0__SRCID__CP_FUE_ERROR					    201		/* C9 ECC FUE Error */
+#define GFX_9_0__SRCID__RLC_STRM_PERF_MONITOR_INTERRUPT		202		/* CA Streaming Perf Monitor Interrupt */
+#define GFX_9_0__SRCID__GRBM_RD_TIMEOUT_ERROR				232		/* E8 CRead timeout error */
+#define GFX_9_0__SRCID__GRBM_REG_GUI_IDLE					233		/* E9 Register GUI Idle */
+#define GFX_9_0__SRCID__SQ_INTERRUPT_ID					    239		/* EF SQ Interrupt (ttrace wrap, errors) */
+
+#endif /* __IRQSRCS_GFX_9_0_H__ */
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h b/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
index c6b6f97de9de..aaed7f59e0e2 100644
--- a/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
+++ b/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
@@ -198,4 +198,102 @@
 #define VISLANDS30_IV_SRCID_HPD_RX_F		                    42	    // 0x2a		
 #define VISLANDS30_IV_EXTID_HPD_RX_F                         11
 
+#define VISLANDS30_IV_SRCID_GPIO_19                            0x00000053  /* 83 */
+
+#define VISLANDS30_IV_SRCID_SRBM_READ_TIMEOUT_ERR              0x00000060  /* 96 */
+#define VISLANDS30_IV_SRCID_SRBM_CTX_SWITCH                    0x00000061  /* 97 */
+
+#define VISLANDS30_IV_SRBM_REG_ACCESS_ERROR                    0x00000062  /* 98 */
+
+
+#define VISLANDS30_IV_SRCID_UVD_ENC_GEN_PURP                   0x00000077  /* 119 */
+#define VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE                 0x0000007c  /* 124 */
+
+#define VISLANDS30_IV_SRCID_BIF_PF_VF_MSGBUF_VALID             0x00000087  /* 135 */
+
+#define VISLANDS30_IV_SRCID_BIF_VF_PF_MSGBUF_ACK               0x0000008a  /* 138 */
+
+#define VISLANDS30_IV_SRCID_SYS_PAGE_INV_FAULT                 0x0000008c  /* 140 */
+#define VISLANDS30_IV_SRCID_SYS_MEM_PROT_FAULT                 0x0000008d  /* 141 */
+
+#define VISLANDS30_IV_SRCID_SEM_PAGE_INV_FAULT                 0x00000090  /* 144 */
+#define VISLANDS30_IV_SRCID_SEM_MEM_PROT_FAULT                 0x00000091  /* 145 */
+
+#define VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT                 0x00000092  /* 146 */
+#define VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT                 0x00000093  /* 147 */
+
+#define VISLANDS30_IV_SRCID_ACP                                0x000000a2  /* 162 */
+
+#define VISLANDS30_IV_SRCID_VCE_TRAP                           0x000000a7  /* 167 */
+#define VISLANDS30_IV_EXTID_VCE_TRAP_GENERAL_PURPOSE           0
+#define VISLANDS30_IV_EXTID_VCE_TRAP_LOW_LATENCY               1
+#define VISLANDS30_IV_EXTID_VCE_TRAP_REAL_TIME                 2
+
+#define VISLANDS30_IV_SRCID_CP_INT_RB                          0x000000b0  /* 176 */
+#define VISLANDS30_IV_SRCID_CP_INT_IB1                         0x000000b1  /* 177 */
+#define VISLANDS30_IV_SRCID_CP_INT_IB2                         0x000000b2  /* 178 */
+#define VISLANDS30_IV_SRCID_CP_PM4_RES_BITS_ERR                0x000000b4  /* 180 */
+#define VISLANDS30_IV_SRCID_CP_END_OF_PIPE                     0x000000b5  /* 181 */
+#define VISLANDS30_IV_SRCID_CP_BAD_OPCODE                      0x000000b7  /* 183 */
+#define VISLANDS30_IV_SRCID_CP_PRIV_REG_FAULT                  0x000000b8  /* 184 */
+#define VISLANDS30_IV_SRCID_CP_PRIV_INSTR_FAULT                0x000000b9  /* 185 */
+#define VISLANDS30_IV_SRCID_CP_WAIT_MEM_SEM_FAULT              0x000000ba  /* 186 */
+#define VISLANDS30_IV_SRCID_CP_GUI_IDLE                        0x000000bb  /* 187 */
+#define VISLANDS30_IV_SRCID_CP_GUI_BUSY                        0x000000bc  /* 188 */
+
+#define VISLANDS30_IV_SRCID_CP_COMPUTE_QUERY_STATUS            0x000000bf  /* 191 */
+#define VISLANDS30_IV_SRCID_CP_ECC_ERROR                       0x000000c5  /* 197 */
+
+#define CARRIZO_IV_SRCID_CP_COMPUTE_QUERY_STATUS               0x000000c7  /* 199 */
+
+#define VISLANDS30_IV_SRCID_CP_WAIT_REG_MEM_POLL_TIMEOUT       0x000000c0  /* 192 */
+#define VISLANDS30_IV_SRCID_CP_SEM_SIG_INCOMPL                 0x000000c1  /* 193 */
+#define VISLANDS30_IV_SRCID_CP_PREEMPT_ACK                     0x000000c2  /* 194 */
+#define VISLANDS30_IV_SRCID_CP_GENERAL_PROT_FAULT              0x000000c3  /* 195 */
+#define VISLANDS30_IV_SRCID_CP_GDS_ALLOC_ERROR                 0x000000c4  /* 196 */
+#define VISLANDS30_IV_SRCID_CP_ECC_ERROR                       0x000000c5  /* 197 */
+
+#define VISLANDS30_IV_SRCID_RLC_STRM_PERF_MONITOR              0x000000ca  /* 202 */
+
+#define VISLANDS30_IV_SDMA_ATOMIC_SRC_ID                       0x000000da  /* 218 */
+
+#define VISLANDS30_IV_SRCID_SDMA_ECC_ERROR                     0x000000dc  /* 220 */
+
+#define VISLANDS30_IV_SRCID_SDMA_TRAP          	               0x000000e0  /* 224 */
+#define VISLANDS30_IV_SRCID_SDMA_SEM_INCOMPLETE                0x000000e1  /* 225 */
+#define VISLANDS30_IV_SRCID_SDMA_SEM_WAIT                      0x000000e2  /* 226 */
+
+
+#define VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER            0x000000e5  /* 229 */
+
+#define VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH         0x000000e6  /* 230 */
+#define VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW         0x000000e7  /* 231 */
+
+#define VISLANDS30_IV_SRCID_GRBM_READ_TIMEOUT_ERR              0x000000e8  /* 232 */
+#define VISLANDS30_IV_SRCID_GRBM_REG_GUI_IDLE                  0x000000e9  /* 233 */
+
+#define VISLANDS30_IV_SRCID_SQ_INTERRUPT_MSG                   0x000000ef  /* 239 */
+
+#define VISLANDS30_IV_SRCID_SDMA_PREEMPT                       0x000000f0  /* 240 */
+#define VISLANDS30_IV_SRCID_SDMA_VM_HOLE                       0x000000f2  /* 242 */
+#define VISLANDS30_IV_SRCID_SDMA_CTXEMPTY                      0x000000f3  /* 243 */
+#define VISLANDS30_IV_SRCID_SDMA_DOORBELL_INVALID              0x000000f4  /* 244 */
+#define VISLANDS30_IV_SRCID_SDMA_FROZEN                        0x000000f5  /* 245 */
+#define VISLANDS30_IV_SRCID_SDMA_POLL_TIMEOUT                  0x000000f6  /* 246 */
+#define VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE                    0x000000f7  /* 247 */
+
+#define VISLANDS30_IV_SRCID_CG_THERMAL_TRIG                    0x000000f8  /* 248 */
+
+#define VISLANDS30_IV_SRCID_SMU_DISP_TIMER_TRIGGER             0x000000fd  /* 253 */
+
+/* These are not "real" source ids defined by HW */
+#define VISLANDS30_IV_SRCID_VM_CONTEXT_ALL                     0x00000100  /* 256 */
+#define VISLANDS30_IV_EXTID_VM_CONTEXT0_ALL                    0
+#define VISLANDS30_IV_EXTID_VM_CONTEXT1_ALL                    1
+
+
+/* IV Extended IDs */
+#define VISLANDS30_IV_EXTID_NONE                               0x00000000
+#define VISLANDS30_IV_EXTID_INVALID                            0xffffffff
+
 #endif // _IVSRCID_VISLANDS30_H_
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
new file mode 100644
index 000000000000..802413832fe8
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_SDMA0_4_0_H__
+#define __IRQSRCS_SDMA0_4_0_H__
+
+#define SDMA0_4_0__SRCID__SDMA_ATOMIC_RTN_DONE                         217             /* 0xD9 SDMA atomic*_rtn ops complete  */
+#define SDMA0_4_0__SRCID__SDMA_ATOMIC_TIMEOUT                          218             /* 0xDA SDMA atomic CMPSWAP loop timeout  */
+#define SDMA0_4_0__SRCID__SDMA_IB_PREEMPT                                      219             /* 0xDB sdma mid-command buffer preempt interrupt  */
+#define SDMA0_4_0__SRCID__SDMA_ECC                                             220             /* 0xDC ECC  Error  */
+#define SDMA0_4_0__SRCID__SDMA_PAGE_FAULT                                      221             /* 0xDD Page Fault Error from UTCL2 when nack=3  */
+#define SDMA0_4_0__SRCID__SDMA_PAGE_NULL                                       222             /* 0xDE Page Null from UTCL2 when nack=2  */
+#define SDMA0_4_0__SRCID__SDMA_XNACK                                       223         /* 0xDF Page retry  timeout after UTCL2 return nack=1  */
+#define SDMA0_4_0__SRCID__SDMA_TRAP                                            224             /* 0xE0 Trap  */
+#define SDMA0_4_0__SRCID__SDMA_SEM_INCOMPLETE_TIMEOUT          225             /* 0xE1 0xDAGPF (Sem incomplete timeout)  */
+#define SDMA0_4_0__SRCID__SDMA_SEM_WAIT_FAIL_TIMEOUT           226             /* 0xE2 Semaphore wait fail timeout  */
+#define SDMA0_4_0__SRCID__SDMA_SRAM_ECC                                            228         /* 0xE4 SRAM ECC Error  */
+#define SDMA0_4_0__SRCID__SDMA_PREEMPT                                     240         /* 0xF0 SDMA New Run List  */
+#define SDMA0_4_0__SRCID__SDMA_VM_HOLE                                     242         /* 0xF2 MC or SEM address in VM hole  */
+#define SDMA0_4_0__SRCID__SDMA_CTXEMPTY                                            243         /* 0xF3 Context Empty  */
+#define SDMA0_4_0__SRCID__SDMA_DOORBELL_INVALID                                244             /* 0xF4 Doorbell BE invalid  */
+#define SDMA0_4_0__SRCID__SDMA_FROZEN                                      245         /* 0xF5 SDMA Frozen  */
+#define SDMA0_4_0__SRCID__SDMA_POLL_TIMEOUT                                    246             /* 0xF6 SRBM read poll timeout  */
+#define SDMA0_4_0__SRCID__SDMA_SRBMWRITE                                       247             /* 0xF7 SRBM write Protection  */
+
+#endif /* __IRQSRCS_SDMA_4_0_H__ */
+
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
new file mode 100644
index 000000000000..d12a35619f9a
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_SDMA1_4_0_H__
+#define __IRQSRCS_SDMA1_4_0_H__
+
+#define SDMA1_4_0__SRCID__SDMA_ATOMIC_RTN_DONE                         217             /* 0xD9 SDMA atomic*_rtn ops complete  */
+#define SDMA1_4_0__SRCID__SDMA_ATOMIC_TIMEOUT                          218             /* 0xDA SDMA atomic CMPSWAP loop timeout  */
+#define SDMA1_4_0__SRCID__SDMA_IB_PREEMPT                                      219             /* 0xDB sdma mid-command buffer preempt interrupt  */
+#define SDMA1_4_0__SRCID__SDMA_ECC                                             220             /* 0xDC ECC  Error  */
+#define SDMA1_4_0__SRCID__SDMA_PAGE_FAULT                                      221             /* 0xDD Page Fault Error from UTCL2 when nack=3  */
+#define SDMA1_4_0__SRCID__SDMA_PAGE_NULL                                       222             /* 0xDE Page Null from UTCL2 when nack=2  */
+#define SDMA1_4_0__SRCID__SDMA_XNACK                                       223         /* 0xDF Page retry  timeout after UTCL2 return nack=1  */
+#define SDMA1_4_0__SRCID__SDMA_TRAP                                            224             /* 0xE0 Trap  */
+#define SDMA1_4_0__SRCID__SDMA_SEM_INCOMPLETE_TIMEOUT          225             /* 0xE1 0xDAGPF (Sem incomplete timeout)  */
+#define SDMA1_4_0__SRCID__SDMA_SEM_WAIT_FAIL_TIMEOUT           226             /* 0xE2 Semaphore wait fail timeout  */
+#define SDMA1_4_0__SRCID__SDMA_SRAM_ECC                                            228         /* 0xE4 SRAM ECC Error  */
+#define SDMA1_4_0__SRCID__SDMA_PREEMPT                                     240         /* 0xF0 SDMA New Run List  */
+#define SDMA1_4_0__SRCID__SDMA_VM_HOLE                                     242         /* 0xF2 MC or SEM address in VM hole  */
+#define SDMA1_4_0__SRCID__SDMA_CTXEMPTY                                            243         /* 0xF3 Context Empty  */
+#define SDMA1_4_0__SRCID__SDMA_DOORBELL_INVALID                                244             /* 0xF4 Doorbell BE invalid  */
+#define SDMA1_4_0__SRCID__SDMA_FROZEN                                      245         /* 0xF5 SDMA Frozen  */
+#define SDMA1_4_0__SRCID__SDMA_POLL_TIMEOUT                                    246             /* 0xF6 SRBM read poll timeout  */
+#define SDMA1_4_0__SRCID__SDMA_SRBMWRITE                                       247             /* 0xF7 SRBM write Protection  */
+
+#endif /* __IRQSRCS_SDMA1_4_0_H__ */
+
+
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h b/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
index 7a65206a6d21..02bab4673cd4 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h
+++ b/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
@@ -23,13 +23,10 @@
  *
  */
 
-#ifndef __SOC_BOUNDING_BOX_H__
-#define __SOC_BOUNDING_BOX_H__
+#ifndef __IRQSRCS_SMUIO_9_0_H__
+#define __IRQSRCS_SMUIO_9_0_H__
 
-#include "dml_common_defs.h"
+#define SMUIO_9_0__SRCID__SMUIO_GPIO19			83		/* GPIO19 interrupt  */
 
-void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box);
-voltage_scaling_st dml_socbb_voltage_scaling(const soc_bounding_box_st *box, enum voltage_state voltage);
-double dml_socbb_return_bw_mhz(soc_bounding_box_st *box, enum voltage_state voltage);
+#endif /* __IRQSRCS_SMUIO_9_0_H__ */
 
-#endif
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
new file mode 100644
index 000000000000..5218bc53fb2d
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_THM_9_0_H__
+#define __IRQSRCS_THM_9_0_H__
+
+#define THM_9_0__SRCID__THM_DIG_THERM_L2H		0		/* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH  */
+#define THM_9_0__SRCID__THM_DIG_THERM_H2L		1		/* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL  */
+
+#endif /* __IRQSRCS_THM_9_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h b/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
new file mode 100644
index 000000000000..fb041aee6c66
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_UVD_7_0_H__
+#define __IRQSRCS_UVD_7_0_H__
+
+#define UVD_7_0__SRCID__UVD_ENC_GEN_PURP                119
+#define UVD_7_0__SRCID__UVD_ENC_LOW_LATENCY             120
+#define UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT	124		/* UVD system message interrupt  */
+
+#endif /* __IRQSRCS_UVD_7_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
new file mode 100644
index 000000000000..3440bab565af
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_VCE_4_0_H__
+#define __IRQSRCS_VCE_4_0_H__
+
+#define VCE_4_0__CTXID__VCE_TRAP_GENERAL_PURPOSE               0
+#define VCE_4_0__CTXID__VCE_TRAP_LOW_LATENCY                   1
+#define VCE_4_0__CTXID__VCE_TRAP_REAL_TIME                     2
+
+#endif /* __IRQSRCS_VCE_4_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
new file mode 100644
index 000000000000..e5951709bfc3
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_VCN_1_0_H__
+#define __IRQSRCS_VCN_1_0_H__
+
+#define VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE                 119     /* 0x77 Encoder General Purpose  */
+#define VCN_1_0__SRCID__UVD_ENC_LOW_LATENCY                     120     /* 0x78 Encoder Low Latency  */
+#define VCN_1_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT	        124		/* 0x7c UVD system message interrupt  */
+
+#endif /* __IRQSRCS_VCN_1_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h
new file mode 100644
index 000000000000..d130936c9989
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2017 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 __IRQSRCS_VMC_1_0_H__
+#define __IRQSRCS_VMC_1_0_H__
+
+
+#define VMC_1_0__SRCID__VM_FAULT                            0
+#define VMC_1_0__SRCID__VM_CONTEXT0_ALL                     256
+#define VMC_1_0__SRCID__VM_CONTEXT1_ALL                     257
+
+#define UTCL2_1_0__SRCID__FAULT                             0       /* UTC L2 has encountered a fault or retry scenario */
+
+
+#endif /* __IRQSRCS_VMC_1_0_H__ */
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 5733fbee07f7..14391b06080c 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -47,6 +47,17 @@ enum kfd_preempt_type {
 	KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 };
 
+struct kfd_vm_fault_info {
+	uint64_t	page_addr;
+	uint32_t	vmid;
+	uint32_t	mc_id;
+	uint32_t	status;
+	bool		prot_valid;
+	bool		prot_read;
+	bool		prot_write;
+	bool		prot_exec;
+};
+
 struct kfd_cu_info {
 	uint32_t num_shader_engines;
 	uint32_t num_shader_arrays_per_engine;
@@ -259,6 +270,21 @@ struct tile_config {
  * IB to the corresponding ring (ring type). The IB is executed with the
  * specified VMID in a user mode context.
  *
+ * @get_vm_fault_info: Return information about a recent VM fault on
+ * GFXv7 and v8. If multiple VM faults occurred since the last call of
+ * this function, it will return information about the first of those
+ * faults. On GFXv9 VM fault information is fully contained in the IH
+ * packet and this function is not needed.
+ *
+ * @read_vmid_from_vmfault_reg: On Hawaii the VMID is not set in the
+ * IH ring entry. This function allows the KFD ISR to get the VMID
+ * from the fault status register as early as possible.
+ *
+ * @gpu_recover: let kgd reset gpu after kfd detect CPC hang
+ *
+ * @set_compute_idle: Indicates that compute is idle on a device. This
+ * can be used to change power profiles depending on compute activity.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -374,6 +400,14 @@ struct kfd2kgd_calls {
 	int (*submit_ib)(struct kgd_dev *kgd, enum kgd_engine_type engine,
 			uint32_t vmid, uint64_t gpu_addr,
 			uint32_t *ib_cmd, uint32_t ib_len);
+
+	int (*get_vm_fault_info)(struct kgd_dev *kgd,
+			struct kfd_vm_fault_info *info);
+	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
+
+	void (*gpu_recover)(struct kgd_dev *kgd);
+
+	void (*set_compute_idle)(struct kgd_dev *kgd, bool idle);
 };
 
 /**
@@ -399,6 +433,10 @@ struct kfd2kgd_calls {
  * @schedule_evict_and_restore_process: Schedules work queue that will prepare
  * for safe eviction of KFD BOs that belong to the specified process.
  *
+ * @pre_reset: Notifies amdkfd that amdgpu about to reset the gpu
+ *
+ * @post_reset: Notify amdkfd that amgpu successfully reseted the gpu
+ *
  * This structure contains function callback pointers so the kgd driver
  * will notify to the amdkfd about certain status changes.
  *
@@ -417,6 +455,8 @@ struct kgd2kfd_calls {
 	int (*resume_mm)(struct mm_struct *mm);
 	int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
 			struct dma_fence *fence);
+	int  (*pre_reset)(struct kfd_dev *kfd);
+	int  (*post_reset)(struct kfd_dev *kfd);
 };
 
 int kgd2kfd_init(unsigned interface_version,
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 06f08f34a110..6a41b81c7325 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -192,7 +192,6 @@ struct amd_pp_simple_clock_info;
 struct amd_pp_display_configuration;
 struct amd_pp_clock_info;
 struct pp_display_clock_request;
-struct pp_wm_sets_with_clock_ranges_soc15;
 struct pp_clock_levels_with_voltage;
 struct pp_clock_levels_with_latency;
 struct amd_pp_clocks;
@@ -232,16 +231,19 @@ struct amd_pm_funcs {
 	void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
 	int (*switch_power_profile)(void *handle, enum PP_SMC_POWER_PROFILE type, bool en);
 /* export to amdgpu */
-	void (*powergate_uvd)(void *handle, bool gate);
-	void (*powergate_vce)(void *handle, bool gate);
 	struct amd_vce_state *(*get_vce_clock_state)(void *handle, u32 idx);
 	int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
 			enum amd_pm_state_type *user_state);
 	int (*load_firmware)(void *handle);
 	int (*wait_for_fw_loading_complete)(void *handle);
+	int (*set_powergating_by_smu)(void *handle,
+				uint32_t block_type, bool gate);
 	int (*set_clockgating_by_smu)(void *handle, uint32_t msg_id);
 	int (*set_power_limit)(void *handle, uint32_t n);
 	int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit);
+	int (*get_power_profile_mode)(void *handle, char *buf);
+	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
+	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
 /* export to DC */
 	u32 (*get_sclk)(void *handle, bool low);
 	u32 (*get_mclk)(void *handle, bool low);
@@ -261,15 +263,12 @@ struct amd_pm_funcs {
 		enum amd_pp_clock_type type,
 		struct pp_clock_levels_with_voltage *clocks);
 	int (*set_watermarks_for_clocks_ranges)(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+						void *clock_ranges);
 	int (*display_clock_voltage_request)(void *handle,
 				struct pp_display_clock_request *clock);
 	int (*get_display_mode_validation_clocks)(void *handle,
 		struct amd_pp_simple_clock_info *clocks);
-	int (*get_power_profile_mode)(void *handle, char *buf);
-	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
-	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
-	int (*set_mmhub_powergating_by_smu)(void *handle);
+	int (*notify_smu_enable_pwe)(void *handle);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index d567be49c31b..7a646f94b478 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -221,29 +221,7 @@ static int pp_sw_reset(void *handle)
 static int pp_set_powergating_state(void *handle,
 				    enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = handle;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret;
-
-	if (!hwmgr || !hwmgr->pm_en)
-		return 0;
-
-	if (hwmgr->hwmgr_func->gfx_off_control) {
-		/* Enable/disable GFX off through SMU */
-		ret = hwmgr->hwmgr_func->gfx_off_control(hwmgr,
-							 state == AMD_PG_STATE_GATE);
-		if (ret)
-			pr_err("gfx off control failed!\n");
-	}
-
-	if (hwmgr->hwmgr_func->enable_per_cu_power_gating == NULL) {
-		pr_debug("%s was not implemented.\n", __func__);
-		return 0;
-	}
-
-	/* Enable/disable GFX per cu powergating through SMU */
-	return hwmgr->hwmgr_func->enable_per_cu_power_gating(hwmgr,
-			state == AMD_PG_STATE_GATE);
+	return 0;
 }
 
 static int pp_suspend(void *handle)
@@ -1020,7 +998,7 @@ static int pp_get_display_power_level(void *handle,
 static int pp_get_current_clocks(void *handle,
 		struct amd_pp_clock_info *clocks)
 {
-	struct amd_pp_simple_clock_info simple_clocks;
+	struct amd_pp_simple_clock_info simple_clocks = { 0 };
 	struct pp_clock_info hw_clocks;
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
@@ -1056,7 +1034,10 @@ static int pp_get_current_clocks(void *handle,
 	clocks->max_engine_clock_in_sr = hw_clocks.max_eng_clk;
 	clocks->min_engine_clock_in_sr = hw_clocks.min_eng_clk;
 
-	clocks->max_clocks_state = simple_clocks.level;
+	if (simple_clocks.level == 0)
+		clocks->max_clocks_state = PP_DAL_POWERLEVEL_7;
+	else
+		clocks->max_clocks_state = simple_clocks.level;
 
 	if (0 == phm_get_current_shallow_sleep_clocks(hwmgr, &hwmgr->current_ps->hardware, &hw_clocks)) {
 		clocks->max_engine_clock_in_sr = hw_clocks.max_eng_clk;
@@ -1118,17 +1099,17 @@ static int pp_get_clock_by_type_with_voltage(void *handle,
 }
 
 static int pp_set_watermarks_for_clocks_ranges(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		void *clock_ranges)
 {
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	if (!hwmgr || !hwmgr->pm_en ||!wm_with_clock_ranges)
+	if (!hwmgr || !hwmgr->pm_en || !clock_ranges)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	ret = phm_set_watermarks_for_clocks_ranges(hwmgr,
-			wm_with_clock_ranges);
+			clock_ranges);
 	mutex_unlock(&hwmgr->smu_lock);
 
 	return ret;
@@ -1159,6 +1140,8 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	if (!hwmgr || !hwmgr->pm_en ||!clocks)
 		return -EINVAL;
 
+	clocks->level = PP_DAL_POWERLEVEL_7;
+
 	mutex_lock(&hwmgr->smu_lock);
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DynamicPatchPowerState))
@@ -1168,19 +1151,78 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	return ret;
 }
 
-static int pp_set_mmhub_powergating_by_smu(void *handle)
+static int pp_dpm_powergate_mmhub(void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
-	if (hwmgr->hwmgr_func->set_mmhub_powergating_by_smu == NULL) {
+	if (hwmgr->hwmgr_func->powergate_mmhub == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->powergate_mmhub(hwmgr);
+}
+
+static int pp_dpm_powergate_gfx(void *handle, bool gate)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
+
+	if (hwmgr->hwmgr_func->powergate_gfx == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
 		return 0;
 	}
 
-	return hwmgr->hwmgr_func->set_mmhub_powergating_by_smu(hwmgr);
+	return hwmgr->hwmgr_func->powergate_gfx(hwmgr, gate);
+}
+
+static int pp_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	int ret = 0;
+
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+	case AMD_IP_BLOCK_TYPE_VCN:
+		pp_dpm_powergate_uvd(handle, gate);
+		break;
+	case AMD_IP_BLOCK_TYPE_VCE:
+		pp_dpm_powergate_vce(handle, gate);
+		break;
+	case AMD_IP_BLOCK_TYPE_GMC:
+		pp_dpm_powergate_mmhub(handle);
+		break;
+	case AMD_IP_BLOCK_TYPE_GFX:
+		ret = pp_dpm_powergate_gfx(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
+static int pp_notify_smu_enable_pwe(void *handle)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;
+
+	if (hwmgr->hwmgr_func->smus_notify_pwe == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return -EINVAL;;
+	}
+
+	mutex_lock(&hwmgr->smu_lock);
+	hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return 0;
 }
 
 static const struct amd_pm_funcs pp_dpm_funcs = {
@@ -1189,8 +1231,6 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.force_performance_level = pp_dpm_force_performance_level,
 	.get_performance_level = pp_dpm_get_performance_level,
 	.get_current_power_state = pp_dpm_get_current_power_state,
-	.powergate_vce = pp_dpm_powergate_vce,
-	.powergate_uvd = pp_dpm_powergate_uvd,
 	.dispatch_tasks = pp_dpm_dispatch_tasks,
 	.set_fan_control_mode = pp_dpm_set_fan_control_mode,
 	.get_fan_control_mode = pp_dpm_get_fan_control_mode,
@@ -1210,6 +1250,7 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.get_vce_clock_state = pp_dpm_get_vce_clock_state,
 	.switch_power_profile = pp_dpm_switch_power_profile,
 	.set_clockgating_by_smu = pp_set_clockgating_by_smu,
+	.set_powergating_by_smu = pp_set_powergating_by_smu,
 	.get_power_profile_mode = pp_get_power_profile_mode,
 	.set_power_profile_mode = pp_set_power_profile_mode,
 	.odn_edit_dpm_table = pp_odn_edit_dpm_table,
@@ -1227,5 +1268,5 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_watermarks_for_clocks_ranges = pp_set_watermarks_for_clocks_ranges,
 	.display_clock_voltage_request = pp_display_clock_voltage_request,
 	.get_display_mode_validation_clocks = pp_get_display_mode_validation_clocks,
-	.set_mmhub_powergating_by_smu = pp_set_mmhub_powergating_by_smu,
+	.notify_smu_enable_pwe = pp_notify_smu_enable_pwe,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index a0bb921fac22..53207e76b0f3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -435,7 +435,7 @@ int phm_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+					void *clock_ranges)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
@@ -443,7 +443,7 @@ int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	return hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr,
-			wm_with_clock_ranges);
+								clock_ranges);
 }
 
 int phm_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 9b675d9bd162..8994aa5c8cf8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -147,10 +147,10 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		smu7_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_AI:
-		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_VEGA10:
 		case CHIP_VEGA20:
+			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega10_smu_funcs;
 			vega10_hwmgr_init(hwmgr);
 			break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 7047e29755c3..01dc46dc9c8a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1544,14 +1544,14 @@ void atomctrl_get_voltage_range(struct pp_hwmgr *hwmgr, uint32_t *max_vddc,
 		switch (hwmgr->chip_id) {
 		case CHIP_TONGA:
 		case CHIP_FIJI:
-			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc/4);
-			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc/4);
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc) / 4;
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc) / 4;
 			return;
 		case CHIP_POLARIS11:
 		case CHIP_POLARIS10:
 		case CHIP_POLARIS12:
-			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc/100);
-			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc/100);
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc) / 100;
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc) / 100;
 			return;
 		default:
 			break;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
index 5325661fedff..d27c1c9df286 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
@@ -512,14 +512,82 @@ int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, BIOS_CLKI
 	return 0;
 }
 
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_2(struct pp_hwmgr *hwmgr,
+			struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+			struct atom_firmware_info_v3_2 *fw_info)
+{
+	uint32_t frequency = 0;
+
+	boot_values->ulRevision = fw_info->firmware_revision;
+	boot_values->ulGfxClk   = fw_info->bootup_sclk_in10khz;
+	boot_values->ulUClk     = fw_info->bootup_mclk_in10khz;
+	boot_values->usVddc     = fw_info->bootup_vddc_mv;
+	boot_values->usVddci    = fw_info->bootup_vddci_mv;
+	boot_values->usMvddc    = fw_info->bootup_mvddc_mv;
+	boot_values->usVddGfx   = fw_info->bootup_vddgfx_mv;
+	boot_values->ucCoolingID = fw_info->coolingsolution_id;
+	boot_values->ulSocClk   = 0;
+	boot_values->ulDCEFClk   = 0;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_SOCCLK_ID, &frequency))
+		boot_values->ulSocClk   = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCEFCLK_ID, &frequency))
+		boot_values->ulDCEFClk  = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_ECLK_ID, &frequency))
+		boot_values->ulEClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_VCLK_ID, &frequency))
+		boot_values->ulVClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCLK_ID, &frequency))
+		boot_values->ulDClk     = frequency;
+}
+
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_1(struct pp_hwmgr *hwmgr,
+			struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+			struct atom_firmware_info_v3_1 *fw_info)
+{
+	uint32_t frequency = 0;
+
+	boot_values->ulRevision = fw_info->firmware_revision;
+	boot_values->ulGfxClk   = fw_info->bootup_sclk_in10khz;
+	boot_values->ulUClk     = fw_info->bootup_mclk_in10khz;
+	boot_values->usVddc     = fw_info->bootup_vddc_mv;
+	boot_values->usVddci    = fw_info->bootup_vddci_mv;
+	boot_values->usMvddc    = fw_info->bootup_mvddc_mv;
+	boot_values->usVddGfx   = fw_info->bootup_vddgfx_mv;
+	boot_values->ucCoolingID = fw_info->coolingsolution_id;
+	boot_values->ulSocClk   = 0;
+	boot_values->ulDCEFClk   = 0;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_SOCCLK_ID, &frequency))
+		boot_values->ulSocClk   = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCEFCLK_ID, &frequency))
+		boot_values->ulDCEFClk  = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_ECLK_ID, &frequency))
+		boot_values->ulEClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_VCLK_ID, &frequency))
+		boot_values->ulVClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCLK_ID, &frequency))
+		boot_values->ulDClk     = frequency;
+}
+
 int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 			struct pp_atomfwctrl_bios_boot_up_values *boot_values)
 {
-	struct atom_firmware_info_v3_1 *info = NULL;
+	struct atom_firmware_info_v3_2 *fwinfo_3_2;
+	struct atom_firmware_info_v3_1 *fwinfo_3_1;
+	struct atom_common_table_header *info = NULL;
 	uint16_t ix;
 
 	ix = GetIndexIntoMasterDataTable(firmwareinfo);
-	info = (struct atom_firmware_info_v3_1 *)
+	info = (struct atom_common_table_header *)
 		smu_atom_get_data_table(hwmgr->adev,
 				ix, NULL, NULL, NULL);
 
@@ -528,16 +596,18 @@ int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 	}
 
-	boot_values->ulRevision = info->firmware_revision;
-	boot_values->ulGfxClk   = info->bootup_sclk_in10khz;
-	boot_values->ulUClk     = info->bootup_mclk_in10khz;
-	boot_values->usVddc     = info->bootup_vddc_mv;
-	boot_values->usVddci    = info->bootup_vddci_mv;
-	boot_values->usMvddc    = info->bootup_mvddc_mv;
-	boot_values->usVddGfx   = info->bootup_vddgfx_mv;
-	boot_values->ucCoolingID = info->coolingsolution_id;
-	boot_values->ulSocClk   = 0;
-	boot_values->ulDCEFClk   = 0;
+	if ((info->format_revision == 3) && (info->content_revision == 2)) {
+		fwinfo_3_2 = (struct atom_firmware_info_v3_2 *)info;
+		pp_atomfwctrl_copy_vbios_bootup_values_3_2(hwmgr,
+				boot_values, fwinfo_3_2);
+	} else if ((info->format_revision == 3) && (info->content_revision == 1)) {
+		fwinfo_3_1 = (struct atom_firmware_info_v3_1 *)info;
+		pp_atomfwctrl_copy_vbios_bootup_values_3_1(hwmgr,
+				boot_values, fwinfo_3_1);
+	} else {
+		pr_info("Fw info table revision does not match!");
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -629,5 +699,7 @@ int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr,
 	param->acggfxclkspreadpercent = info->acggfxclkspreadpercent;
 	param->acggfxclkspreadfreq = info->acggfxclkspreadfreq;
 
+	param->Vr2_I2C_address = info->Vr2_I2C_address;
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
index fe10aa4db5e6..22e21668c93a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
@@ -136,6 +136,9 @@ struct pp_atomfwctrl_bios_boot_up_values {
 	uint32_t   ulUClk;
 	uint32_t   ulSocClk;
 	uint32_t   ulDCEFClk;
+	uint32_t   ulEClk;
+	uint32_t   ulVClk;
+	uint32_t   ulDClk;
 	uint16_t   usVddc;
 	uint16_t   usVddci;
 	uint16_t   usMvddc;
@@ -207,6 +210,8 @@ struct pp_atomfwctrl_smc_dpm_parameters
 	uint8_t  acggfxclkspreadenabled;
 	uint8_t  acggfxclkspreadpercent;
 	uint16_t acggfxclkspreadfreq;
+
+	uint8_t Vr2_I2C_address;
 };
 
 int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index 35bd9870ab10..4e1fd5393845 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -183,10 +183,10 @@ static int get_vddc_lookup_table(
 					ATOM_Tonga_Voltage_Lookup_Record,
 					entries, vddc_lookup_pp_tables, i);
 		record->us_calculated = 0;
-		record->us_vdd = atom_record->usVdd;
-		record->us_cac_low = atom_record->usCACLow;
-		record->us_cac_mid = atom_record->usCACMid;
-		record->us_cac_high = atom_record->usCACHigh;
+		record->us_vdd = le16_to_cpu(atom_record->usVdd);
+		record->us_cac_low = le16_to_cpu(atom_record->usCACLow);
+		record->us_cac_mid = le16_to_cpu(atom_record->usCACMid);
+		record->us_cac_high = le16_to_cpu(atom_record->usCACHigh);
 	}
 
 	*lookup_table = table;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index d4bc83e81389..a63e00653324 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -993,7 +993,7 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = latency_required ?
 						smu10_get_mem_latency(hwmgr,
 						pclk_vol_table->entries[i].clk) :
@@ -1044,7 +1044,7 @@ static int smu10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
 		clocks->data[i].voltage_in_mv = pclk_vol_table->entries[i].vol;
 		clocks->num_levels++;
 	}
@@ -1108,9 +1108,10 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 }
 
 static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		void *clock_ranges)
 {
 	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;
 
@@ -1126,7 +1127,7 @@ static int smu10_smus_notify_pwe(struct pp_hwmgr *hwmgr)
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_SetRccPfcPmeRestoreRegister);
 }
 
-static int smu10_set_mmhub_powergating_by_smu(struct pp_hwmgr *hwmgr)
+static int smu10_powergate_mmhub(struct pp_hwmgr *hwmgr)
 {
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerGateMmHub);
 }
@@ -1182,10 +1183,11 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.asic_setup = smu10_setup_asic_task,
 	.power_state_set = smu10_set_power_state_tasks,
 	.dynamic_state_management_disable = smu10_disable_dpm_tasks,
-	.set_mmhub_powergating_by_smu = smu10_set_mmhub_powergating_by_smu,
+	.powergate_mmhub = smu10_powergate_mmhub,
 	.smus_notify_pwe = smu10_smus_notify_pwe,
 	.gfx_off_control = smu10_gfx_off_control,
 	.display_clock_voltage_request = smu10_display_clock_voltage_request,
+	.powergate_gfx = smu10_gfx_off_control,
 };
 
 int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 41495621d94a..683b29a99366 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -416,7 +416,7 @@ int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
  * Powerplay will only control the static per CU Power Gating.
  * Dynamic per CU Power Gating will be done in gfx.
  */
-int smu7_enable_per_cu_power_gating(struct pp_hwmgr *hwmgr, bool enable)
+int smu7_powergate_gfx(struct pp_hwmgr *hwmgr, bool enable)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
index be7f66d2b234..fc8f8a6acc72 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
@@ -33,6 +33,6 @@ int smu7_powergate_acp(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr);
 int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
 					const uint32_t *msg_id);
-int smu7_enable_per_cu_power_gating(struct pp_hwmgr *hwmgr, bool enable);
+int smu7_powergate_gfx(struct pp_hwmgr *hwmgr, bool enable);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index b89d6fb8559b..052e60dfaf9f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -48,6 +48,8 @@
 #include "processpptables.h"
 #include "pp_thermal.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
 #define MC_CG_ARB_FREQ_F2           0x0c
@@ -1578,7 +1580,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	data->current_profile_setting.sclk_up_hyst = 0;
 	data->current_profile_setting.sclk_down_hyst = 100;
 	data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
-	data->current_profile_setting.bupdate_sclk = 1;
+	data->current_profile_setting.bupdate_mclk = 1;
 	data->current_profile_setting.mclk_up_hyst = 0;
 	data->current_profile_setting.mclk_down_hyst = 100;
 	data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
@@ -3183,7 +3185,7 @@ static int smu7_get_pp_table_entry_callback_func_v1(struct pp_hwmgr *hwmgr,
 	performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
 			state_entry->ucPCIEGenLow);
 	performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap,
-			state_entry->ucPCIELaneHigh);
+			state_entry->ucPCIELaneLow);
 
 	performance_level = &(smu7_power_state->performance_levels
 			[smu7_power_state->performance_level_count++]);
@@ -4105,17 +4107,17 @@ static int smu7_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			230,
+			VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH,
 			source);
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			231,
+			VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW,
 			source);
 
 	/* Register CTF(GPIO_19) interrupt */
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			83,
+			VISLANDS30_IV_SRCID_GPIO_19,
 			source);
 
 	return 0;
@@ -4610,12 +4612,12 @@ static int smu7_get_sclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 			return -EINVAL;
 		dep_sclk_table = table_info->vdd_dep_on_sclk;
 		for (i = 0; i < dep_sclk_table->count; i++)
-			clocks->clock[i] = dep_sclk_table->entries[i].clk;
+			clocks->clock[i] = dep_sclk_table->entries[i].clk * 10;
 		clocks->count = dep_sclk_table->count;
 	} else if (hwmgr->pp_table_version == PP_TABLE_V0) {
 		sclk_table = hwmgr->dyn_state.vddc_dependency_on_sclk;
 		for (i = 0; i < sclk_table->count; i++)
-			clocks->clock[i] = sclk_table->entries[i].clk;
+			clocks->clock[i] = sclk_table->entries[i].clk * 10;
 		clocks->count = sclk_table->count;
 	}
 
@@ -4647,7 +4649,7 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 			return -EINVAL;
 		dep_mclk_table = table_info->vdd_dep_on_mclk;
 		for (i = 0; i < dep_mclk_table->count; i++) {
-			clocks->clock[i] = dep_mclk_table->entries[i].clk;
+			clocks->clock[i] = dep_mclk_table->entries[i].clk * 10;
 			clocks->latency[i] = smu7_get_mem_latency(hwmgr,
 						dep_mclk_table->entries[i].clk);
 		}
@@ -4655,7 +4657,7 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 	} else if (hwmgr->pp_table_version == PP_TABLE_V0) {
 		mclk_table = hwmgr->dyn_state.vddc_dependency_on_mclk;
 		for (i = 0; i < mclk_table->count; i++)
-			clocks->clock[i] = mclk_table->entries[i].clk;
+			clocks->clock[i] = mclk_table->entries[i].clk * 10;
 		clocks->count = mclk_table->count;
 	}
 	return 0;
@@ -5044,7 +5046,7 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = {
 	.get_fan_control_mode = smu7_get_fan_control_mode,
 	.force_clock_level = smu7_force_clock_level,
 	.print_clock_levels = smu7_print_clock_levels,
-	.enable_per_cu_power_gating = smu7_enable_per_cu_power_gating,
+	.powergate_gfx = smu7_powergate_gfx,
 	.get_sclk_od = smu7_get_sclk_od,
 	.set_sclk_od = smu7_set_sclk_od,
 	.get_mclk_od = smu7_get_mclk_od,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
index 50690c72b2ea..288802f209dd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
@@ -1604,17 +1604,17 @@ static int smu8_get_clock_by_type(struct pp_hwmgr *hwmgr, enum amd_pp_clock_type
 	switch (type) {
 	case amd_pp_disp_clock:
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = data->sys_info.display_clock[i];
+			clocks->clock[i] = data->sys_info.display_clock[i] * 10;
 		break;
 	case amd_pp_sys_clock:
 		table = hwmgr->dyn_state.vddc_dependency_on_sclk;
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = table->entries[i].clk;
+			clocks->clock[i] = table->entries[i].clk * 10;
 		break;
 	case amd_pp_mem_clock:
 		clocks->count = SMU8_NUM_NBPMEMORYCLOCK;
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = data->sys_info.nbp_memory_clock[clocks->count - 1 - i];
+			clocks->clock[i] = data->sys_info.nbp_memory_clock[clocks->count - 1 - i] * 10;
 		break;
 	default:
 		return -1;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 93a3d022ba47..2aab1b475945 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -25,6 +25,9 @@
 #include "ppatomctrl.h"
 #include "ppsmc.h"
 #include "atom.h"
+#include "ivsrcid/thm/irqsrcs_thm_9_0.h"
+#include "ivsrcid/smuio/irqsrcs_smuio_9_0.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 uint8_t convert_to_vid(uint16_t vddc)
 {
@@ -543,17 +546,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 	uint32_t src_id = entry->src_id;
 
 	if (client_id == AMDGPU_IH_CLIENTID_LEGACY) {
-		if (src_id == 230)
+		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH)
 			pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
 						PCI_BUS_NUM(adev->pdev->devfn),
 						PCI_SLOT(adev->pdev->devfn),
 						PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == 231)
+		else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
 			pr_warn("GPU under temperature range detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == 83)
+		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19)
 			pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
@@ -594,17 +597,17 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
-			0,
+			THM_9_0__SRCID__THM_DIG_THERM_L2H,
 			source);
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
-			1,
+			THM_9_0__SRCID__THM_DIG_THERM_H2L,
 			source);
 
 	/* Register CTF(GPIO_19) interrupt */
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_ROM_SMUIO,
-			83,
+			SMUIO_9_0__SRCID__SMUIO_GPIO19,
 			source);
 
 	return 0;
@@ -652,7 +655,7 @@ int smu_get_voltage_dependency_table_ppt_v1(
 }
 
 int smu_set_watermarks_for_clocks_ranges(void *wt_table,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
 {
 	uint32_t i;
 	struct watermarks *table = wt_table;
@@ -660,49 +663,49 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table,
 	if (!table || !wm_with_clock_ranges)
 		return -EINVAL;
 
-	if (wm_with_clock_ranges->num_wm_sets_dmif > 4 || wm_with_clock_ranges->num_wm_sets_mcif > 4)
+	if (wm_with_clock_ranges->num_wm_dmif_sets > 4 || wm_with_clock_ranges->num_wm_mcif_sets > 4)
 		return -EINVAL;
 
-	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
+	for (i = 0; i < wm_with_clock_ranges->num_wm_dmif_sets; i++) {
 		table->WatermarkRow[1][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz) /
 			100);
 		table->WatermarkRow[1][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].WmSetting = (uint8_t)
-				wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
+				wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
 	}
 
-	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
+	for (i = 0; i < wm_with_clock_ranges->num_wm_mcif_sets; i++) {
 		table->WatermarkRow[0][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].WmSetting = (uint8_t)
-				wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
+				wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
index 916cc01e7652..5454289d5226 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
@@ -107,7 +107,7 @@ int smu_get_voltage_dependency_table_ppt_v1(
 		struct phm_ppt_v1_clock_voltage_dependency_table *dep_table);
 
 int smu_set_watermarks_for_clocks_ranges(void *wt_table,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
 
 #define PHM_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
 #define PHM_FIELD_MASK(reg, field) reg##__##field##_MASK
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 3b8d36df52e9..fb86c24394ff 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -55,12 +55,6 @@
 
 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
 
-#define MEM_FREQ_LOW_LATENCY        25000
-#define MEM_FREQ_HIGH_LATENCY       80000
-#define MEM_LATENCY_HIGH            245
-#define MEM_LATENCY_LOW             35
-#define MEM_LATENCY_ERR             0xFFFF
-
 #define mmDF_CS_AON0_DramBaseAddress0                                                                  0x0044
 #define mmDF_CS_AON0_DramBaseAddress0_BASE_IDX                                                         0
 
@@ -295,7 +289,15 @@ static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
 	struct phm_ppt_v1_voltage_lookup_table *vddc_lookup_table;
 	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table[3];
 	struct phm_ppt_v1_clock_voltage_dependency_table *od_table[3];
+	struct pp_atomfwctrl_avfs_parameters avfs_params = {0};
 	uint32_t i;
+	int result;
+
+	result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
+	if (!result) {
+		data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
+		data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
+	}
 
 	od_lookup_table = &odn_table->vddc_lookup_table;
 	vddc_lookup_table = table_info->vddc_lookup_table;
@@ -2078,9 +2080,6 @@ static int vega10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
 	if (data->smu_features[GNLD_AVFS].supported) {
 		result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
 		if (!result) {
-			data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
-			data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
-
 			pp_table->MinVoltageVid = (uint8_t)
 					convert_to_vid((uint16_t)(avfs_params.ulMinVddc));
 			pp_table->MaxVoltageVid = (uint8_t)
@@ -2902,11 +2901,6 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 	vega10_enable_disable_PCC_limit_feature(hwmgr, true);
 
-	if ((hwmgr->smu_version == 0x001c2c00) ||
-			(hwmgr->smu_version == 0x001c2d00))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_UpdatePkgPwrPidAlpha, 1);
-
 	smum_send_msg_to_smc_with_parameter(hwmgr,
 		PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
 
@@ -3223,7 +3217,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 		/* Find the lowest MCLK frequency that is within
 		 * the tolerable latency defined in DAL
 		 */
-		latency = 0;
+		latency = hwmgr->display_config->dce_tolerable_mclk_in_active_latency;
 		for (i = 0; i < data->mclk_latency_table.count; i++) {
 			if ((data->mclk_latency_table.entries[i].latency <= latency) &&
 				(data->mclk_latency_table.entries[i].frequency >=
@@ -3265,10 +3259,25 @@ static int vega10_populate_and_upload_sclk_mclk_dpm_levels(
 {
 	int result = 0;
 	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_dpm_table *dpm_table = &data->dpm_table;
+	struct vega10_odn_dpm_table *odn_table = &data->odn_dpm_table;
+	struct vega10_odn_clock_voltage_dependency_table *odn_clk_table = &odn_table->vdd_dep_on_sclk;
+	int count;
 
 	if (!data->need_update_dpm_table)
 		return 0;
 
+	if (hwmgr->od_enabled && data->need_update_dpm_table & DPMTABLE_OD_UPDATE_SCLK) {
+		for (count = 0; count < dpm_table->gfx_table.count; count++)
+			dpm_table->gfx_table.dpm_levels[count].value = odn_clk_table->entries[count].clk;
+	}
+
+	odn_clk_table = &odn_table->vdd_dep_on_mclk;
+	if (hwmgr->od_enabled && data->need_update_dpm_table & DPMTABLE_OD_UPDATE_MCLK) {
+		for (count = 0; count < dpm_table->mem_table.count; count++)
+			dpm_table->mem_table.dpm_levels[count].value = odn_clk_table->entries[count].clk;
+	}
+
 	if (data->need_update_dpm_table &
 			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK + DPMTABLE_UPDATE_SOCCLK)) {
 		result = vega10_populate_all_graphic_levels(hwmgr);
@@ -3716,7 +3725,7 @@ static void vega10_notify_smc_display_change(struct pp_hwmgr *hwmgr,
 {
 	smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 0 : 1);
+			has_disp ? 1 : 0);
 }
 
 int vega10_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
@@ -3791,7 +3800,9 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 	uint32_t i;
 	struct pp_display_clock_request clock_req;
 
-	if (hwmgr->display_config->num_display > 1)
+	if ((hwmgr->display_config->num_display > 1) &&
+	     !hwmgr->display_config->multi_monitor_in_sync &&
+	     !hwmgr->display_config->nb_pstate_switch_disable)
 		vega10_notify_smc_display_change(hwmgr, false);
 	else
 		vega10_notify_smc_display_change(hwmgr, true);
@@ -3807,7 +3818,7 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 
 	if (i < dpm_table->count) {
 		clock_req.clock_type = amd_pp_dcef_clock;
-		clock_req.clock_freq_in_khz = dpm_table->dpm_levels[i].value;
+		clock_req.clock_freq_in_khz = dpm_table->dpm_levels[i].value * 10;
 		if (!vega10_display_clock_voltage_request(hwmgr, &clock_req)) {
 			smum_send_msg_to_smc_with_parameter(
 					hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk,
@@ -4064,28 +4075,17 @@ static void vega10_get_sclks(struct pp_hwmgr *hwmgr,
 			table_info->vdd_dep_on_sclk;
 	uint32_t i;
 
+	clocks->num_levels = 0;
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
 			clocks->data[clocks->num_levels].clocks_in_khz =
-					dep_table->entries[i].clk;
+					dep_table->entries[i].clk * 10;
 			clocks->num_levels++;
 		}
 	}
 
 }
 
-static uint32_t vega10_get_mem_latency(struct pp_hwmgr *hwmgr,
-		uint32_t clock)
-{
-	if (clock >= MEM_FREQ_LOW_LATENCY &&
-			clock < MEM_FREQ_HIGH_LATENCY)
-		return MEM_LATENCY_HIGH;
-	else if (clock >= MEM_FREQ_HIGH_LATENCY)
-		return MEM_LATENCY_LOW;
-	else
-		return MEM_LATENCY_ERR;
-}
-
 static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 		struct pp_clock_levels_with_latency *clocks)
 {
@@ -4094,26 +4094,22 @@ static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table =
 			table_info->vdd_dep_on_mclk;
 	struct vega10_hwmgr *data = hwmgr->backend;
+	uint32_t j = 0;
 	uint32_t i;
 
-	clocks->num_levels = 0;
-	data->mclk_latency_table.count = 0;
-
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
-			clocks->data[clocks->num_levels].clocks_in_khz =
-			data->mclk_latency_table.entries
-			[data->mclk_latency_table.count].frequency =
-					dep_table->entries[i].clk;
-			clocks->data[clocks->num_levels].latency_in_us =
-			data->mclk_latency_table.entries
-			[data->mclk_latency_table.count].latency =
-					vega10_get_mem_latency(hwmgr,
-						dep_table->entries[i].clk);
-			clocks->num_levels++;
-			data->mclk_latency_table.count++;
+
+			clocks->data[j].clocks_in_khz =
+						dep_table->entries[i].clk * 10;
+			data->mclk_latency_table.entries[j].frequency =
+							dep_table->entries[i].clk;
+			clocks->data[j].latency_in_us =
+				data->mclk_latency_table.entries[j].latency = 25;
+			j++;
 		}
 	}
+	clocks->num_levels = data->mclk_latency_table.count = j;
 }
 
 static void vega10_get_dcefclocks(struct pp_hwmgr *hwmgr,
@@ -4126,7 +4122,7 @@ static void vega10_get_dcefclocks(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = 0;
 		clocks->num_levels++;
 	}
@@ -4142,7 +4138,7 @@ static void vega10_get_socclocks(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = 0;
 		clocks->num_levels++;
 	}
@@ -4202,7 +4198,7 @@ static int vega10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 	}
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk  * 10;
 		clocks->data[i].voltage_in_mv = (uint32_t)(table_info->vddc_lookup_table->
 				entries[dep_table->entries[i].vddInd].us_vdd);
 		clocks->num_levels++;
@@ -4215,9 +4211,10 @@ static int vega10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+							void *clock_range)
 {
 	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;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 782e2098824d..0789d64246ca 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -81,6 +81,7 @@ static void vega12_set_default_registry_data(struct pp_hwmgr *hwmgr)
 
 	data->registry_data.disallowed_features = 0x0;
 	data->registry_data.od_state_in_dc_support = 0;
+	data->registry_data.thermal_support = 1;
 	data->registry_data.skip_baco_hardware = 0;
 
 	data->registry_data.log_avfs_param = 0;
@@ -422,6 +423,11 @@ static int vega12_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 			hwmgr->thermal_controller.advanceFanControlParameters.usFanPWMMinLimit *
 			hwmgr->thermal_controller.fanInfo.ulMaxRPM / 100;
 
+	if (hwmgr->feature_mask & PP_GFXOFF_MASK)
+		data->gfxoff_controlled_by_driver = true;
+	else
+		data->gfxoff_controlled_by_driver = false;
+
 	return result;
 }
 
@@ -453,43 +459,36 @@ static int vega12_setup_asic_task(struct pp_hwmgr *hwmgr)
  */
 static void vega12_init_dpm_state(struct vega12_dpm_state *dpm_state)
 {
-	dpm_state->soft_min_level = 0xff;
-	dpm_state->soft_max_level = 0xff;
-	dpm_state->hard_min_level = 0xff;
-	dpm_state->hard_max_level = 0xff;
+	dpm_state->soft_min_level = 0x0;
+	dpm_state->soft_max_level = 0xffff;
+	dpm_state->hard_min_level = 0x0;
+	dpm_state->hard_max_level = 0xffff;
 }
 
-static int vega12_get_number_dpm_level(struct pp_hwmgr *hwmgr,
-		PPCLK_e clkID, uint32_t *num_dpm_level)
+static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
+		PPCLK_e clk_id, uint32_t *num_of_levels)
 {
-	int result;
-	/*
-	 * SMU expects the Clock ID to be in the top 16 bits.
-	 * Lower 16 bits specify the level however 0xFF is a
-	 * special argument the returns the total number of levels
-	 */
-	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
-		PPSMC_MSG_GetDpmFreqByIndex, (clkID << 16 | 0xFF)) == 0,
-		"[GetNumberDpmLevel] Failed to get DPM levels from SMU for CLKID!",
-		return -EINVAL);
-
-	result = vega12_read_arg_from_smc(hwmgr, num_dpm_level);
+	int ret = 0;
 
-	PP_ASSERT_WITH_CODE(*num_dpm_level < MAX_REGULAR_DPM_NUMBER,
-		"[GetNumberDPMLevel] Number of DPM levels is greater than limit",
-		return -EINVAL);
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_GetDpmFreqByIndex,
+			(clk_id << 16 | 0xFF));
+	PP_ASSERT_WITH_CODE(!ret,
+			"[GetNumOfDpmLevel] failed to get dpm levels!",
+			return ret);
 
-	PP_ASSERT_WITH_CODE(*num_dpm_level != 0,
-		"[GetNumberDPMLevel] Number of CLK Levels is zero!",
-		return -EINVAL);
+	*num_of_levels = smum_get_argument(hwmgr);
+	PP_ASSERT_WITH_CODE(*num_of_levels > 0,
+			"[GetNumOfDpmLevel] number of clk levels is invalid!",
+			return -EINVAL);
 
-	return result;
+	return ret;
 }
 
 static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		PPCLK_e clkID, uint32_t index, uint32_t *clock)
 {
-	int result;
+	int result = 0;
 
 	/*
 	 *SMU expects the Clock ID to be in the top 16 bits.
@@ -500,15 +499,36 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		"[GetDpmFrequencyByIndex] Failed to get dpm frequency from SMU!",
 		return -EINVAL);
 
-	result = vega12_read_arg_from_smc(hwmgr, clock);
-
-	PP_ASSERT_WITH_CODE(*clock != 0,
-		"[GetDPMFrequencyByIndex] Failed to get dpm frequency by index.!",
-		return -EINVAL);
+	*clock = smum_get_argument(hwmgr);
 
 	return result;
 }
 
+static int vega12_setup_single_dpm_table(struct pp_hwmgr *hwmgr,
+		struct vega12_single_dpm_table *dpm_table, PPCLK_e clk_id)
+{
+	int ret = 0;
+	uint32_t i, num_of_levels, clk;
+
+	ret = vega12_get_number_of_dpm_level(hwmgr, clk_id, &num_of_levels);
+	PP_ASSERT_WITH_CODE(!ret,
+			"[SetupSingleDpmTable] failed to get clk levels!",
+			return ret);
+
+	dpm_table->count = num_of_levels;
+
+	for (i = 0; i < num_of_levels; i++) {
+		ret = vega12_get_dpm_frequency_by_index(hwmgr, clk_id, i, &clk);
+		PP_ASSERT_WITH_CODE(!ret,
+			"[SetupSingleDpmTable] failed to get clk of specific level!",
+			return ret);
+		dpm_table->dpm_levels[i].value = clk;
+		dpm_table->dpm_levels[i].enabled = true;
+	}
+
+	return ret;
+}
+
 /*
  * This function is to initialize all DPM state tables
  * for SMU based on the dependency table.
@@ -519,224 +539,136 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
  */
 static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 {
-	uint32_t num_levels, i, clock;
 
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
-
 	struct vega12_single_dpm_table *dpm_table;
+	int ret = 0;
 
 	memset(&data->dpm_table, 0, sizeof(data->dpm_table));
 
-	/* Initialize Sclk DPM and SOC DPM table based on allow Sclk values */
+	/* socclk */
 	dpm_table = &(data->dpm_table.soc_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_SOCCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for SOCCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_SOCCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for SOCCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_SOCCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get socclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.soc_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* gfxclk */
 	dpm_table = &(data->dpm_table.gfx_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_GFXCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for GFXCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_GFXCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for GFXCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_GFXCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get gfxclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.gfx_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
-	/* Initialize Mclk DPM table based on allow Mclk values */
-	dpm_table = &(data->dpm_table.mem_table);
 
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_UCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for UCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_UCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for UCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	/* memclk */
+	dpm_table = &(data->dpm_table.mem_table);
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_UCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get memclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.mem_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* eclk */
 	dpm_table = &(data->dpm_table.eclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_ECLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for ECLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-		PPCLK_ECLK, i, &clock) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for ECLK!",
-		return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_ECLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get eclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.eclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* vclk */
 	dpm_table = &(data->dpm_table.vclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_VCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for VCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_VCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for VCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_VCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get vclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.vclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* dclk */
 	dpm_table = &(data->dpm_table.dclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_DCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DCLK, i, &clock) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCLK!",
-		return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.dclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
-	/* Assume there is no headless Vega12 for now */
+	/* dcefclk */
 	dpm_table = &(data->dpm_table.dcef_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_DCEFCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCEFCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DCEFCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCEFCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DCEFCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dcefclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.dcef_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* pixclk */
 	dpm_table = &(data->dpm_table.pixel_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_PIXCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PIXCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_PIXCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PIXCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_PIXCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get pixclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* dispclk */
 	dpm_table = &(data->dpm_table.display_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_DISPCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DISPCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DISPCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DISPCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DISPCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dispclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* phyclk */
 	dpm_table = &(data->dpm_table.phy_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_PHYCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PHYCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_PHYCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PHYCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_PHYCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get phyclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
 	/* save a copy of the default DPM table */
@@ -803,6 +735,9 @@ static int vega12_init_smc_table(struct pp_hwmgr *hwmgr)
 		data->vbios_boot_state.soc_clock = boot_up_values.ulSocClk;
 		data->vbios_boot_state.dcef_clock = boot_up_values.ulDCEFClk;
 		data->vbios_boot_state.uc_cooling_id = boot_up_values.ucCoolingID;
+		data->vbios_boot_state.eclock = boot_up_values.ulEClk;
+		data->vbios_boot_state.dclock = boot_up_values.ulDClk;
+		data->vbios_boot_state.vclock = boot_up_values.ulVClk;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetMinDeepSleepDcefclk,
 			(uint32_t)(data->vbios_boot_state.dcef_clock / 100));
@@ -844,6 +779,21 @@ static int vega12_set_allowed_featuresmask(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static void vega12_init_powergate_state(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+
+	data->uvd_power_gated = true;
+	data->vce_power_gated = true;
+
+	if (data->smu_features[GNLD_DPM_UVD].enabled)
+		data->uvd_power_gated = false;
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled)
+		data->vce_power_gated = false;
+}
+
 static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data =
@@ -862,12 +812,11 @@ static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 			enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? true : false;
 			data->smu_features[i].enabled = enabled;
 			data->smu_features[i].supported = enabled;
-			PP_ASSERT(
-				!data->smu_features[i].allowed || enabled,
-				"[EnableAllSMUFeatures] Enabled feature is different from allowed, expected disabled!");
 		}
 	}
 
+	vega12_init_powergate_state(hwmgr);
+
 	return 0;
 }
 
@@ -923,6 +872,48 @@ static int vega12_power_control_set_level(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static int vega12_get_all_clock_ranges_helper(struct pp_hwmgr *hwmgr,
+		PPCLK_e clkid, struct vega12_clock_range *clock)
+{
+	/* AC Max */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get max ac clock from SMC!",
+		return -EINVAL);
+	clock->ACMax = smum_get_argument(hwmgr);
+
+	/* AC Min */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get min ac clock from SMC!",
+		return -EINVAL);
+	clock->ACMin = smum_get_argument(hwmgr);
+
+	/* DC Max */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDcModeMaxDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get max dc clock from SMC!",
+		return -EINVAL);
+	clock->DCMax = smum_get_argument(hwmgr);
+
+	return 0;
+}
+
+static int vega12_get_all_clock_ranges(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t i;
+
+	for (i = 0; i < PPCLK_COUNT; i++)
+		PP_ASSERT_WITH_CODE(!vega12_get_all_clock_ranges_helper(hwmgr,
+					i, &(data->clk_range[i])),
+				"Failed to get clk range from SMC!",
+				return -EINVAL);
+
+	return 0;
+}
+
 static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
@@ -950,6 +941,11 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 			"Failed to power control set level!",
 			result = tmp_result);
 
+	result = vega12_get_all_clock_ranges(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to get all clock ranges!",
+			return result);
+
 	result = vega12_odn_initialize_default_settings(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to power control set level!",
@@ -978,76 +974,172 @@ static uint32_t vega12_find_lowest_dpm_level(
 			break;
 	}
 
+	if (i >= table->count) {
+		i = 0;
+		table->dpm_levels[i].enabled = true;
+	}
+
 	return i;
 }
 
 static uint32_t vega12_find_highest_dpm_level(
 		struct vega12_single_dpm_table *table)
 {
-	uint32_t i = 0;
+	int32_t i = 0;
+	PP_ASSERT_WITH_CODE(table->count <= MAX_REGULAR_DPM_NUMBER,
+			"[FindHighestDPMLevel] DPM Table has too many entries!",
+			return MAX_REGULAR_DPM_NUMBER - 1);
 
-	if (table->count <= MAX_REGULAR_DPM_NUMBER) {
-		for (i = table->count; i > 0; i--) {
-			if (table->dpm_levels[i - 1].enabled)
-				return i - 1;
-		}
-	} else {
-		pr_info("DPM Table Has Too Many Entries!");
-		return MAX_REGULAR_DPM_NUMBER - 1;
+	for (i = table->count - 1; i >= 0; i--) {
+		if (table->dpm_levels[i].enabled)
+			break;
 	}
 
-	return i;
+	if (i < 0) {
+		i = 0;
+		table->dpm_levels[i].enabled = true;
+	}
+
+	return (uint32_t)i;
 }
 
 static int vega12_upload_dpm_min_level(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = hwmgr->backend;
-	if (data->smc_state_table.gfx_boot_level !=
-			data->dpm_table.gfx_table.dpm_state.soft_min_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMinByFreq,
-			PPCLK_GFXCLK<<16 | data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_boot_level].value);
-		data->dpm_table.gfx_table.dpm_state.soft_min_level =
-				data->smc_state_table.gfx_boot_level;
+	uint32_t min_freq;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		min_freq = data->dpm_table.gfx_table.dpm_state.soft_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_GFXCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min gfxclk !",
+					return ret);
 	}
 
-	if (data->smc_state_table.mem_boot_level !=
-			data->dpm_table.mem_table.dpm_state.soft_min_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMinByFreq,
-			PPCLK_UCLK<<16 | data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_boot_level].value);
-		data->dpm_table.mem_table.dpm_state.soft_min_level =
-				data->smc_state_table.mem_boot_level;
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		min_freq = data->dpm_table.mem_table.dpm_state.soft_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_UCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min memclk !",
+					return ret);
+
+		min_freq = data->dpm_table.mem_table.dpm_state.hard_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetHardMinByFreq,
+					(PPCLK_UCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set hard min memclk !",
+					return ret);
 	}
 
-	return 0;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		min_freq = data->dpm_table.vclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_VCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min vclk!",
+					return ret);
+
+		min_freq = data->dpm_table.dclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_DCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min dclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		min_freq = data->dpm_table.eclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_ECLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min eclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		min_freq = data->dpm_table.soc_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_SOCCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min socclk!",
+					return ret);
+	}
+
+	return ret;
 
 }
 
 static int vega12_upload_dpm_max_level(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = hwmgr->backend;
-	if (data->smc_state_table.gfx_max_level !=
-		data->dpm_table.gfx_table.dpm_state.soft_max_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMaxByFreq,
-			/* plus the vale by 1 to align the resolution */
-			PPCLK_GFXCLK<<16 | (data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_max_level].value + 1));
-		data->dpm_table.gfx_table.dpm_state.soft_max_level =
-				data->smc_state_table.gfx_max_level;
+	uint32_t max_freq;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		max_freq = data->dpm_table.gfx_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_GFXCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max gfxclk!",
+					return ret);
 	}
 
-	if (data->smc_state_table.mem_max_level !=
-		data->dpm_table.mem_table.dpm_state.soft_max_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMaxByFreq,
-			/* plus the vale by 1 to align the resolution */
-			PPCLK_UCLK<<16 | (data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_max_level].value + 1));
-		data->dpm_table.mem_table.dpm_state.soft_max_level =
-				data->smc_state_table.mem_max_level;
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		max_freq = data->dpm_table.mem_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_UCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max memclk!",
+					return ret);
 	}
 
-	return 0;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		max_freq = data->dpm_table.vclk_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_VCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max vclk!",
+					return ret);
+
+		max_freq = data->dpm_table.dclk_table.dpm_state.soft_max_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_DCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max dclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		max_freq = data->dpm_table.eclk_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_ECLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max eclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		max_freq = data->dpm_table.soc_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_SOCCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max socclk!",
+					return ret);
+	}
+
+	return ret;
 }
 
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable)
@@ -1123,7 +1215,7 @@ static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query)
 			"Failed to get current package power!",
 			return -EINVAL);
 
-	vega12_read_arg_from_smc(hwmgr, &value);
+	value = smum_get_argument(hwmgr);
 	/* power value is an integer */
 	*query = value << 8;
 #endif
@@ -1136,14 +1228,11 @@ static int vega12_get_current_gfx_clk_freq(struct pp_hwmgr *hwmgr, uint32_t *gfx
 
 	*gfx_freq = 0;
 
-	PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
+	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
 			"[GetCurrentGfxClkFreq] Attempt to get Current GFXCLK Frequency Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(
-			vega12_read_arg_from_smc(hwmgr, &gfx_clk) == 0,
-			"[GetCurrentGfxClkFreq] Attempt to read arg from SMC Failed",
-			return -1);
+			return -EINVAL);
+	gfx_clk = smum_get_argument(hwmgr);
 
 	*gfx_freq = gfx_clk * 100;
 
@@ -1159,11 +1248,8 @@ static int vega12_get_current_mclk_freq(struct pp_hwmgr *hwmgr, uint32_t *mclk_f
 	PP_ASSERT_WITH_CODE(
 			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDpmClockFreq, (PPCLK_UCLK << 16)) == 0,
 			"[GetCurrentMClkFreq] Attempt to get Current MCLK Frequency Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(
-			vega12_read_arg_from_smc(hwmgr, &mem_clk) == 0,
-			"[GetCurrentMClkFreq] Attempt to read arg from SMC Failed",
-			return -1);
+			return -EINVAL);
+	mem_clk = smum_get_argument(hwmgr);
 
 	*mclk_freq = mem_clk * 100;
 
@@ -1180,16 +1266,12 @@ static int vega12_get_current_activity_percent(
 #if 0
 	ret = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetAverageGfxActivity, 0);
 	if (!ret) {
-		ret = vega12_read_arg_from_smc(hwmgr, &current_activity);
-		if (!ret) {
-			if (current_activity > 100) {
-				PP_ASSERT(false,
-					"[GetCurrentActivityPercent] Activity Percentage Exceeds 100!");
-				current_activity = 100;
-			}
-		} else
+		current_activity = smum_get_argument(hwmgr);
+		if (current_activity > 100) {
 			PP_ASSERT(false,
-				"[GetCurrentActivityPercent] Attempt To Read Average Graphics Activity from SMU Failed!");
+				  "[GetCurrentActivityPercent] Activity Percentage Exceeds 100!");
+			current_activity = 100;
+		}
 	} else
 		PP_ASSERT(false,
 			"[GetCurrentActivityPercent] Attempt To Send Get Average Graphics Activity to SMU Failed!");
@@ -1252,7 +1334,7 @@ static int vega12_notify_smc_display_change(struct pp_hwmgr *hwmgr,
 	if (data->smu_features[GNLD_DPM_UCLK].enabled)
 		return smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 0 : 1);
+			has_disp ? 1 : 0);
 
 	return 0;
 }
@@ -1270,7 +1352,6 @@ int vega12_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
 		switch (clk_type) {
 		case amd_pp_dcef_clock:
-			clk_freq = clock_req->clock_freq_in_khz / 100;
 			clk_select = PPCLK_DCEFCLK;
 			break;
 		case amd_pp_disp_clock:
@@ -1306,9 +1387,10 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	struct PP_Clocks min_clocks = {0};
 	struct pp_display_clock_request clock_req;
-	uint32_t clk_request;
 
-	if (hwmgr->display_config->num_display > 1)
+	if ((hwmgr->display_config->num_display > 1) &&
+	     !hwmgr->display_config->multi_monitor_in_sync &&
+	     !hwmgr->display_config->nb_pstate_switch_disable)
 		vega12_notify_smc_display_change(hwmgr, false);
 	else
 		vega12_notify_smc_display_change(hwmgr, true);
@@ -1319,7 +1401,7 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 
 	if (data->smu_features[GNLD_DPM_DCEFCLK].supported) {
 		clock_req.clock_type = amd_pp_dcef_clock;
-		clock_req.clock_freq_in_khz = min_clocks.dcefClock;
+		clock_req.clock_freq_in_khz = min_clocks.dcefClock/10;
 		if (!vega12_display_clock_voltage_request(hwmgr, &clock_req)) {
 			if (data->smu_features[GNLD_DS_DCEFCLK].supported)
 				PP_ASSERT_WITH_CODE(
@@ -1333,15 +1415,6 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 		}
 	}
 
-	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
-		clk_request = (PPCLK_UCLK << 16) | (min_clocks.memoryClock) / 100;
-		PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinByFreq, clk_request) == 0,
-			"[PhwVega12_NotifySMCDisplayConfigAfterPowerStateAdjustment] Attempt to set UCLK HardMin Failed!",
-			return -1);
-		data->dpm_table.mem_table.dpm_state.hard_min_level = min_clocks.memoryClock;
-	}
-
 	return 0;
 }
 
@@ -1350,12 +1423,19 @@ static int vega12_force_dpm_highest(struct pp_hwmgr *hwmgr)
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 
-	data->smc_state_table.gfx_boot_level =
-	data->smc_state_table.gfx_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-	data->smc_state_table.mem_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
+	uint32_t soft_level;
+
+	soft_level = vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
+
+	data->dpm_table.gfx_table.dpm_state.soft_min_level =
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+		data->dpm_table.gfx_table.dpm_levels[soft_level].value;
+
+	soft_level = vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
+
+	data->dpm_table.mem_table.dpm_state.soft_min_level =
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+		data->dpm_table.mem_table.dpm_levels[soft_level].value;
 
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload boot level to highest!",
@@ -1372,13 +1452,19 @@ static int vega12_force_dpm_lowest(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t soft_level;
+
+	soft_level = vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
+
+	data->dpm_table.gfx_table.dpm_state.soft_min_level =
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+		data->dpm_table.gfx_table.dpm_levels[soft_level].value;
 
-	data->smc_state_table.gfx_boot_level =
-	data->smc_state_table.gfx_max_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-	data->smc_state_table.mem_max_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+	soft_level = vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+
+	data->dpm_table.mem_table.dpm_state.soft_min_level =
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+		data->dpm_table.mem_table.dpm_levels[soft_level].value;
 
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload boot level to highest!",
@@ -1394,17 +1480,6 @@ static int vega12_force_dpm_lowest(struct pp_hwmgr *hwmgr)
 
 static int vega12_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 {
-	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
-
-	data->smc_state_table.gfx_boot_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.gfx_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
-	data->smc_state_table.mem_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
-
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload DPM Bootup Levels!",
 			return -1);
@@ -1412,22 +1487,28 @@ static int vega12_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
 			"Failed to upload DPM Max Levels!",
 			return -1);
+
 	return 0;
 }
 
-#if 0
 static int vega12_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_level level,
 				uint32_t *sclk_mask, uint32_t *mclk_mask, uint32_t *soc_mask)
 {
-	struct phm_ppt_v2_information *table_info =
-			(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *gfx_dpm_table = &(data->dpm_table.gfx_table);
+	struct vega12_single_dpm_table *mem_dpm_table = &(data->dpm_table.mem_table);
+	struct vega12_single_dpm_table *soc_dpm_table = &(data->dpm_table.soc_table);
 
-	if (table_info->vdd_dep_on_sclk->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
-		table_info->vdd_dep_on_socclk->count > VEGA12_UMD_PSTATE_SOCCLK_LEVEL &&
-		table_info->vdd_dep_on_mclk->count > VEGA12_UMD_PSTATE_MCLK_LEVEL) {
+	*sclk_mask = 0;
+	*mclk_mask = 0;
+	*soc_mask  = 0;
+
+	if (gfx_dpm_table->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
+	    mem_dpm_table->count > VEGA12_UMD_PSTATE_MCLK_LEVEL &&
+	    soc_dpm_table->count > VEGA12_UMD_PSTATE_SOCCLK_LEVEL) {
 		*sclk_mask = VEGA12_UMD_PSTATE_GFXCLK_LEVEL;
-		*soc_mask = VEGA12_UMD_PSTATE_SOCCLK_LEVEL;
 		*mclk_mask = VEGA12_UMD_PSTATE_MCLK_LEVEL;
+		*soc_mask  = VEGA12_UMD_PSTATE_SOCCLK_LEVEL;
 	}
 
 	if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
@@ -1435,13 +1516,13 @@ static int vega12_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;
-		*soc_mask = table_info->vdd_dep_on_socclk->count - 1;
-		*mclk_mask = table_info->vdd_dep_on_mclk->count - 1;
+		*sclk_mask = gfx_dpm_table->count - 1;
+		*mclk_mask = mem_dpm_table->count - 1;
+		*soc_mask  = soc_dpm_table->count - 1;
 	}
+
 	return 0;
 }
-#endif
 
 static void vega12_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
@@ -1465,11 +1546,9 @@ static int vega12_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 				enum amd_dpm_forced_level level)
 {
 	int ret = 0;
-#if 0
 	uint32_t sclk_mask = 0;
 	uint32_t mclk_mask = 0;
 	uint32_t soc_mask = 0;
-#endif
 
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_HIGH:
@@ -1485,27 +1564,18 @@ static int vega12_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-#if 0
 		ret = vega12_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask);
 		if (ret)
 			return ret;
-		vega12_force_clock_level(hwmgr, PP_SCLK, 1<<sclk_mask);
-		vega12_force_clock_level(hwmgr, PP_MCLK, 1<<mclk_mask);
-#endif
+		vega12_force_clock_level(hwmgr, PP_SCLK, 1 << sclk_mask);
+		vega12_force_clock_level(hwmgr, PP_MCLK, 1 << mclk_mask);
 		break;
 	case AMD_DPM_FORCED_LEVEL_MANUAL:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
 		break;
 	}
-#if 0
-	if (!ret) {
-		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			vega12_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_NONE);
-		else if (level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			vega12_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_AUTO);
-	}
-#endif
+
 	return ret;
 }
 
@@ -1539,24 +1609,14 @@ static int vega12_get_clock_ranges(struct pp_hwmgr *hwmgr,
 		PPCLK_e clock_select,
 		bool max)
 {
-	int result;
-	*clock = 0;
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
-	if (max) {
-		 PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clock_select << 16)) == 0,
-			"[GetClockRanges] Failed to get max clock from SMC!",
-			return -1);
-		result = vega12_read_arg_from_smc(hwmgr, clock);
-	} else {
-		PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clock_select << 16)) == 0,
-			"[GetClockRanges] Failed to get min clock from SMC!",
-			return -1);
-		result = vega12_read_arg_from_smc(hwmgr, clock);
-	}
+	if (max)
+		*clock = data->clk_range[clock_select].ACMax;
+	else
+		*clock = data->clk_range[clock_select].ACMin;
 
-	return result;
+	return 0;
 }
 
 static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
@@ -1571,12 +1631,12 @@ static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
 		return -1;
 
 	dpm_table = &(data->dpm_table.gfx_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1603,13 +1663,12 @@ static int vega12_get_memclocks(struct pp_hwmgr *hwmgr,
 		return -1;
 
 	dpm_table = &(data->dpm_table.mem_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_UCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_UCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
-		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
-
+		clocks->data[i].clocks_in_khz = dpm_table->dpm_levels[i].value * 1000;
+		data->mclk_latency_table.entries[i].frequency = dpm_table->dpm_levels[i].value * 100;
 		clocks->data[i].latency_in_us =
 			data->mclk_latency_table.entries[i].latency =
 			vega12_get_mem_latency(hwmgr, dpm_table->dpm_levels[i].value);
@@ -1633,12 +1692,12 @@ static int vega12_get_dcefclocks(struct pp_hwmgr *hwmgr,
 
 
 	dpm_table = &(data->dpm_table.dcef_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1661,12 +1720,12 @@ static int vega12_get_socclocks(struct pp_hwmgr *hwmgr,
 
 
 	dpm_table = &(data->dpm_table.soc_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1713,99 +1772,69 @@ static int vega12_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+							void *clock_ranges)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
-	int result = 0;
-	uint32_t i;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 
 	if (!data->registry_data.disable_water_mark &&
 			data->smu_features[GNLD_DPM_DCEFCLK].supported &&
 			data->smu_features[GNLD_DPM_SOCCLK].supported) {
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
-			table->WatermarkRow[WM_DCEFCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
-		}
-
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
-			table->WatermarkRow[WM_SOCCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
-		}
+		smu_set_watermarks_for_clocks_ranges(table, wm_with_clock_ranges);
 		data->water_marks_bitmap |= WaterMarksExist;
 		data->water_marks_bitmap &= ~WaterMarksLoaded;
 	}
 
-	return result;
+	return 0;
 }
 
 static int vega12_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
-
-	if (hwmgr->request_dpm_level & (AMD_DPM_FORCED_LEVEL_AUTO |
-				AMD_DPM_FORCED_LEVEL_LOW |
-				AMD_DPM_FORCED_LEVEL_HIGH))
-		return -EINVAL;
+	uint32_t soft_min_level, soft_max_level;
+	int ret = 0;
 
 	switch (type) {
 	case PP_SCLK:
-		data->smc_state_table.gfx_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.gfx_max_level = mask ? (fls(mask) - 1) : 0;
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
+
+		data->dpm_table.gfx_table.dpm_state.soft_min_level =
+			data->dpm_table.gfx_table.dpm_levels[soft_min_level].value;
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+			data->dpm_table.gfx_table.dpm_levels[soft_max_level].value;
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
+		ret = vega12_upload_dpm_min_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload boot level to lowest!",
-			return -EINVAL);
+			return ret);
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
+		ret = vega12_upload_dpm_max_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
+			return ret);
 		break;
 
 	case PP_MCLK:
-		data->smc_state_table.mem_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.mem_max_level = mask ? (fls(mask) - 1) : 0;
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
+		data->dpm_table.mem_table.dpm_state.soft_min_level =
+			data->dpm_table.mem_table.dpm_levels[soft_min_level].value;
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+			data->dpm_table.mem_table.dpm_levels[soft_max_level].value;
+
+		ret = vega12_upload_dpm_min_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload boot level to lowest!",
-			return -EINVAL);
+			return ret);
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
+		ret = vega12_upload_dpm_max_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
+			return ret);
 
 		break;
 
@@ -1838,8 +1867,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
-				i, clocks.data[i].clocks_in_khz / 100,
-				(clocks.data[i].clocks_in_khz == now) ? "*" : "");
+				i, clocks.data[i].clocks_in_khz / 1000,
+				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
 
 	case PP_MCLK:
@@ -1854,8 +1883,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
-				i, clocks.data[i].clocks_in_khz / 100,
-				(clocks.data[i].clocks_in_khz == now) ? "*" : "");
+				i, clocks.data[i].clocks_in_khz / 1000,
+				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
 
 	case PP_PCIE:
@@ -1867,6 +1896,205 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 	return size;
 }
 
+static int vega12_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *dpm_table;
+	bool vblank_too_short = false;
+	bool disable_mclk_switching;
+	uint32_t i, latency;
+
+	disable_mclk_switching = ((1 < hwmgr->display_config->num_display) &&
+			          !hwmgr->display_config->multi_monitor_in_sync) ||
+			          vblank_too_short;
+	latency = hwmgr->display_config->dce_tolerable_mclk_in_active_latency;
+
+	/* gfxclk */
+	dpm_table = &(data->dpm_table.gfx_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_GFXCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[0].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* memclk */
+	dpm_table = &(data->dpm_table.mem_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_MCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[0].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* honour DAL's UCLK Hardmin */
+	if (dpm_table->dpm_state.hard_min_level < (hwmgr->display_config->min_mem_set_clock / 100))
+		dpm_table->dpm_state.hard_min_level = hwmgr->display_config->min_mem_set_clock / 100;
+
+	/* Hardmin is dependent on displayconfig */
+	if (disable_mclk_switching) {
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		for (i = 0; i < data->mclk_latency_table.count - 1; i++) {
+			if (data->mclk_latency_table.entries[i].latency <= latency) {
+				if (dpm_table->dpm_levels[i].value >= (hwmgr->display_config->min_mem_set_clock / 100)) {
+					dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[i].value;
+					break;
+				}
+			}
+		}
+	}
+
+	if (hwmgr->display_config->nb_pstate_switch_disable)
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	/* vclk */
+	dpm_table = &(data->dpm_table.vclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_UVDCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* dclk */
+	dpm_table = &(data->dpm_table.dclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_UVDCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* socclk */
+	dpm_table = &(data->dpm_table.soc_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_SOCCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_SOCCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_SOCCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* eclk */
+	dpm_table = &(data->dpm_table.eclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_VCEMCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_VCEMCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_VCEMCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	return 0;
+}
+
+static int vega12_set_uclk_to_highest_dpm_level(struct pp_hwmgr *hwmgr,
+		struct vega12_single_dpm_table *dpm_table)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		PP_ASSERT_WITH_CODE(dpm_table->count > 0,
+				"[SetUclkToHightestDpmLevel] Dpm table has no entry!",
+				return -EINVAL);
+		PP_ASSERT_WITH_CODE(dpm_table->count <= NUM_UCLK_DPM_LEVELS,
+				"[SetUclkToHightestDpmLevel] Dpm table has too many entries!",
+				return -EINVAL);
+
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_SetHardMinByFreq,
+				(PPCLK_UCLK << 16 ) | dpm_table->dpm_state.hard_min_level)),
+				"[SetUclkToHightestDpmLevel] Set hard min uclk failed!",
+				return ret);
+	}
+
+	return ret;
+}
+
+static int vega12_pre_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_NumOfDisplays, 0);
+
+	ret = vega12_set_uclk_to_highest_dpm_level(hwmgr,
+			&data->dpm_table.mem_table);
+
+	return ret;
+}
+
 static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
@@ -1911,6 +2139,9 @@ static void vega12_power_gate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
+	if (data->vce_power_gated == bgate)
+		return;
+
 	data->vce_power_gated = bgate;
 	vega12_enable_disable_vce_dpm(hwmgr, !bgate);
 }
@@ -1919,6 +2150,9 @@ static void vega12_power_gate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
+	if (data->uvd_power_gated == bgate)
+		return;
+
 	data->uvd_power_gated = bgate;
 	vega12_enable_disable_uvd_dpm(hwmgr, !bgate);
 }
@@ -2086,6 +2320,38 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int vega12_enable_gfx_off(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->gfxoff_controlled_by_driver)
+		ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_AllowGfxOff);
+
+	return ret;
+}
+
+static int vega12_disable_gfx_off(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->gfxoff_controlled_by_driver)
+		ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisallowGfxOff);
+
+	return ret;
+}
+
+static int vega12_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable)
+{
+	if (enable)
+		return vega12_enable_gfx_off(hwmgr);
+	else
+		return vega12_disable_gfx_off(hwmgr);
+}
+
 static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.backend_init = vega12_hwmgr_backend_init,
 	.backend_fini = vega12_hwmgr_backend_fini,
@@ -2113,6 +2379,10 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.display_clock_voltage_request = vega12_display_clock_voltage_request,
 	.force_clock_level = vega12_force_clock_level,
 	.print_clock_levels = vega12_print_clock_levels,
+	.apply_clocks_adjust_rules =
+		vega12_apply_clocks_adjust_rules,
+	.pre_display_config_changed =
+		vega12_pre_display_configuration_changed_task,
 	.display_config_changed = vega12_display_configuration_changed_task,
 	.powergate_uvd = vega12_power_gate_uvd,
 	.powergate_vce = vega12_power_gate_vce,
@@ -2131,6 +2401,7 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.get_thermal_temperature_range = vega12_get_thermal_temperature_range,
 	.register_irq_handlers = smu9_register_irq_handlers,
 	.start_thermal_controller = vega12_start_thermal_controller,
+	.powergate_gfx = vega12_gfx_off_control,
 };
 
 int vega12_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index e81ded1ec198..b3e424d28994 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -167,6 +167,9 @@ struct vega12_vbios_boot_state {
 	uint32_t    mem_clock;
 	uint32_t    soc_clock;
 	uint32_t    dcef_clock;
+	uint32_t    eclock;
+	uint32_t    dclock;
+	uint32_t    vclock;
 };
 
 #define DPMTABLE_OD_UPDATE_SCLK     0x00000001
@@ -301,6 +304,12 @@ struct vega12_odn_fan_table {
 	bool		force_fan_pwm;
 };
 
+struct vega12_clock_range {
+	uint32_t	ACMax;
+	uint32_t	ACMin;
+	uint32_t	DCMax;
+};
+
 struct vega12_hwmgr {
 	struct vega12_dpm_table          dpm_table;
 	struct vega12_dpm_table          golden_dpm_table;
@@ -382,6 +391,11 @@ struct vega12_hwmgr {
 	uint32_t                       smu_version;
 	struct smu_features            smu_features[GNLD_FEATURES_MAX];
 	struct vega12_smc_state_table  smc_state_table;
+
+	struct vega12_clock_range      clk_range[PPCLK_COUNT];
+
+	/* ---- Gfxoff ---- */
+	bool                           gfxoff_controlled_by_driver;
 };
 
 #define VEGA12_DPM2_NEAR_TDP_DEC                      10
@@ -432,6 +446,8 @@ struct vega12_hwmgr {
 #define VEGA12_UMD_PSTATE_GFXCLK_LEVEL         0x3
 #define VEGA12_UMD_PSTATE_SOCCLK_LEVEL         0x3
 #define VEGA12_UMD_PSTATE_MCLK_LEVEL           0x2
+#define VEGA12_UMD_PSTATE_UVDCLK_LEVEL         0x3
+#define VEGA12_UMD_PSTATE_VCEMCLK_LEVEL        0x3
 
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable);
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index 888ddca902d8..cb3a5b1737c8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -224,11 +224,9 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable
 	ppsmc_pptable->AcgGfxclkSpreadPercent = smc_dpm_table.acggfxclkspreadpercent;
 	ppsmc_pptable->AcgGfxclkSpreadFreq = smc_dpm_table.acggfxclkspreadfreq;
 
-	/* 0xFFFF will disable the ACG feature */
-	if (!(hwmgr->feature_mask & PP_ACG_MASK)) {
-		ppsmc_pptable->AcgThresholdFreqHigh = 0xFFFF;
-		ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
-	}
+	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
+
+	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
index cfd9e6ccb790..904eb2c9155b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
@@ -34,11 +34,9 @@ static int vega12_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
 	PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
 				PPSMC_MSG_GetCurrentRpm),
 			"Attempt to get current RPM from SMC Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(!vega12_read_arg_from_smc(hwmgr,
-			current_rpm),
-			"Attempt to read current RPM from SMC Failed!",
-			return -1);
+			return -EINVAL);
+	*current_rpm = smum_get_argument(hwmgr);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
index a202247c9894..429c9c4322da 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
@@ -455,7 +455,7 @@ extern int phm_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 		enum amd_pp_clock_type type,
 		struct pp_clock_levels_with_voltage *clocks);
 extern int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+						void *clock_ranges);
 extern int phm_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 		struct pp_display_clock_request *clock);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 40c98ca5feb7..d3d96260f440 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -194,7 +194,7 @@ struct pp_smumgr_func {
 	int (*request_smu_load_fw)(struct pp_hwmgr  *hwmgr);
 	int (*request_smu_load_specific_fw)(struct pp_hwmgr  *hwmgr,
 					    uint32_t firmware);
-	int (*get_argument)(struct pp_hwmgr  *hwmgr);
+	uint32_t (*get_argument)(struct pp_hwmgr  *hwmgr);
 	int (*send_msg_to_smc)(struct pp_hwmgr  *hwmgr, uint16_t msg);
 	int (*send_msg_to_smc_with_parameter)(struct pp_hwmgr  *hwmgr,
 					  uint16_t msg, uint32_t parameter);
@@ -293,8 +293,7 @@ struct pp_hwmgr_func {
 	int (*get_clock_by_type_with_voltage)(struct pp_hwmgr *hwmgr,
 			enum amd_pp_clock_type type,
 			struct pp_clock_levels_with_voltage *clocks);
-	int (*set_watermarks_for_clocks_ranges)(struct pp_hwmgr *hwmgr,
-			struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+	int (*set_watermarks_for_clocks_ranges)(struct pp_hwmgr *hwmgr, void *clock_ranges);
 	int (*display_clock_voltage_request)(struct pp_hwmgr *hwmgr,
 			struct pp_display_clock_request *clock);
 	int (*get_max_high_clocks)(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks);
@@ -302,7 +301,7 @@ struct pp_hwmgr_func {
 	int (*power_off_asic)(struct pp_hwmgr *hwmgr);
 	int (*force_clock_level)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf);
-	int (*enable_per_cu_power_gating)(struct pp_hwmgr *hwmgr, bool enable);
+	int (*powergate_gfx)(struct pp_hwmgr *hwmgr, bool enable);
 	int (*get_sclk_od)(struct pp_hwmgr *hwmgr);
 	int (*set_sclk_od)(struct pp_hwmgr *hwmgr, uint32_t value);
 	int (*get_mclk_od)(struct pp_hwmgr *hwmgr);
@@ -327,7 +326,7 @@ struct pp_hwmgr_func {
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size);
 	int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n);
-	int (*set_mmhub_powergating_by_smu)(struct pp_hwmgr *hwmgr);
+	int (*powergate_mmhub)(struct pp_hwmgr *hwmgr);
 	int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr);
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index 89dfbf53c7e6..82550a8a3a3f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -80,7 +80,7 @@ enum SMU10_TABLE_ID {
 	SMU10_CLOCKTABLE,
 };
 
-extern int smum_get_argument(struct pp_hwmgr *hwmgr);
+extern uint32_t smum_get_argument(struct pp_hwmgr *hwmgr);
 
 extern int smum_download_powerplay_table(struct pp_hwmgr *hwmgr, void **table);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index 2f8a3b983cce..b6ffd08784e7 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -412,10 +412,10 @@ typedef struct {
   QuadraticInt_t    ReservedEquation2;
   QuadraticInt_t    ReservedEquation3;
 
-	uint16_t     MinVoltageUlvGfx;
-	uint16_t     MinVoltageUlvSoc;
+  uint16_t     MinVoltageUlvGfx;
+  uint16_t     MinVoltageUlvSoc;
 
-	uint32_t     Reserved[14];
+  uint32_t     Reserved[14];
 
 
 
@@ -483,9 +483,9 @@ typedef struct {
   uint8_t      padding8_4;
 
 
-	uint8_t      PllGfxclkSpreadEnabled;
-	uint8_t      PllGfxclkSpreadPercent;
-	uint16_t     PllGfxclkSpreadFreq;
+  uint8_t      PllGfxclkSpreadEnabled;
+  uint8_t      PllGfxclkSpreadPercent;
+  uint16_t     PllGfxclkSpreadFreq;
 
   uint8_t      UclkSpreadEnabled;
   uint8_t      UclkSpreadPercent;
@@ -495,11 +495,14 @@ typedef struct {
   uint8_t      SocclkSpreadPercent;
   uint16_t     SocclkSpreadFreq;
 
-	uint8_t      AcgGfxclkSpreadEnabled;
-	uint8_t      AcgGfxclkSpreadPercent;
-	uint16_t     AcgGfxclkSpreadFreq;
+  uint8_t      AcgGfxclkSpreadEnabled;
+  uint8_t      AcgGfxclkSpreadPercent;
+  uint16_t     AcgGfxclkSpreadFreq;
 
-	uint32_t     BoardReserved[10];
+  uint8_t      Vr2_I2C_address;
+  uint8_t      padding_vr2[3];
+
+  uint32_t     BoardReserved[9];
 
 
   uint32_t     MmHubPadding[7];
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
index 0a200406a1ec..8d557accaef2 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
@@ -26,7 +26,7 @@
 SMU_MGR = smumgr.o smu8_smumgr.o tonga_smumgr.o fiji_smumgr.o \
 	  polaris10_smumgr.o iceland_smumgr.o \
 	  smu7_smumgr.o vega10_smumgr.o smu10_smumgr.o ci_smumgr.o \
-	  vega12_smumgr.o vegam_smumgr.o
+	  vega12_smumgr.o vegam_smumgr.o smu9_smumgr.o
 
 AMD_PP_SMUMGR = $(addprefix $(AMD_PP_PATH)/smumgr/,$(SMU_MGR))
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index 0a563f6fe9ea..bb07d43f3874 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -68,7 +68,7 @@ static int smu10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
+static uint32_t smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index d644a9bb9078..a029e47c2319 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -379,8 +379,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_smumgr *smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
 	uint32_t fw_to_load;
-	int result = 0;
-	struct SMU_DRAMData_TOC *toc;
+	int r = 0;
 
 	if (!hwmgr->reload_fw) {
 		pr_info("skip reloading...\n");
@@ -421,49 +420,62 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 			   + UCODE_ID_CP_MEC_JT2_MASK;
 	}
 
-	toc = (struct SMU_DRAMData_TOC *)smu_data->header;
-	toc->num_entries = 0;
-	toc->structure_version = 1;
+	if (!smu_data->toc) {
+		struct SMU_DRAMData_TOC *toc;
+
+		smu_data->toc = kzalloc(sizeof(struct SMU_DRAMData_TOC), GFP_KERNEL);
+		if (!smu_data->toc)
+			return -ENOMEM;
+		toc = smu_data->toc;
+		toc->num_entries = 0;
+		toc->structure_version = 1;
 
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	if (!hwmgr->not_vf)
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
 		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		if (!hwmgr->not_vf)
+			PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
 				UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+	}
+	memcpy_toio(smu_data->header_buffer.kaddr, smu_data->toc,
+		    sizeof(struct SMU_DRAMData_TOC));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
 
 	if (smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_LoadUcodes, fw_to_load))
 		pr_err("Fail to Request SMU Load uCode");
 
-	return result;
+	return r;
+
+failed:
+	kfree(smu_data->toc);
+	smu_data->toc = NULL;
+	return r;
 }
 
 /* Check if the FW has been loaded, SMU will not return if loading has not finished. */
@@ -570,7 +582,6 @@ int smu7_setup_pwr_virus(struct pp_hwmgr *hwmgr)
 int smu7_init(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_smumgr *smu_data;
-	uint64_t mc_addr = 0;
 	int r;
 	/* Allocate memory for backend private data */
 	smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
@@ -584,15 +595,12 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 		PAGE_SIZE,
 		AMDGPU_GEM_DOMAIN_VRAM,
 		&smu_data->header_buffer.handle,
-		&mc_addr,
+		&smu_data->header_buffer.mc_addr,
 		&smu_data->header_buffer.kaddr);
 
 	if (r)
 		return -EINVAL;
 
-	smu_data->header = smu_data->header_buffer.kaddr;
-	smu_data->header_buffer.mc_addr = mc_addr;
-
 	if (!hwmgr->not_vf)
 		return 0;
 
@@ -602,7 +610,7 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 		PAGE_SIZE,
 		AMDGPU_GEM_DOMAIN_VRAM,
 		&smu_data->smu_buffer.handle,
-		&mc_addr,
+		&smu_data->smu_buffer.mc_addr,
 		&smu_data->smu_buffer.kaddr);
 
 	if (r) {
@@ -611,7 +619,6 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 					&smu_data->header_buffer.kaddr);
 		return -EINVAL;
 	}
-	smu_data->smu_buffer.mc_addr = mc_addr;
 
 	if (smum_is_hw_avfs_present(hwmgr))
 		hwmgr->avfs_supported = true;
@@ -633,6 +640,9 @@ int smu7_smu_fini(struct pp_hwmgr *hwmgr)
 					&smu_data->smu_buffer.mc_addr,
 					&smu_data->smu_buffer.kaddr);
 
+
+	kfree(smu_data->toc);
+	smu_data->toc = NULL;
 	kfree(hwmgr->smu_backend);
 	hwmgr->smu_backend = NULL;
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
index 39c9bfda0ab4..01f0538fba6b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
@@ -37,10 +37,9 @@ struct smu7_buffer_entry {
 };
 
 struct smu7_smumgr {
-	uint8_t *header;
-	uint8_t *mec_image;
 	struct smu7_buffer_entry smu_buffer;
 	struct smu7_buffer_entry header_buffer;
+	struct SMU_DRAMData_TOC *toc;
 
 	uint32_t                             soft_regs_start;
 	uint32_t                             dpm_table_start;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
index c861d3023474..f7e3bc22bb93 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
@@ -52,10 +52,10 @@ static const enum smu8_scratch_entry firmware_list[] = {
 	SMU8_SCRATCH_ENTRY_UCODE_ID_RLC_G,
 };
 
-static int smu8_get_argument(struct pp_hwmgr *hwmgr)
+static uint32_t smu8_get_argument(struct pp_hwmgr *hwmgr)
 {
 	if (hwmgr == NULL || hwmgr->device == NULL)
-		return -EINVAL;
+		return 0;
 
 	return cgs_read_register(hwmgr->device,
 					mmSMU_MP1_SRBM2P_ARG_0);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
new file mode 100644
index 000000000000..079fc8e8f709
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
@@ -0,0 +1,150 @@
+/*
+ * 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 "smumgr.h"
+#include "vega10_inc.h"
+#include "soc15_common.h"
+#include "pp_debug.h"
+
+
+/* MP Apertures */
+#define MP0_Public                  0x03800000
+#define MP0_SRAM                    0x03900000
+#define MP1_Public                  0x03b00000
+#define MP1_SRAM                    0x03c00004
+
+#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
+
+bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t mp1_fw_flags;
+
+	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
+			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
+
+	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
+
+	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check if SMC has responded to previous message.
+ *
+ * @param    smumgr  the address of the powerplay hardware manager.
+ * @return   TRUE    SMC has responded, FALSE otherwise.
+ */
+static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t reg;
+	uint32_t ret;
+
+	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);
+}
+
+/*
+ * Send a message to the SMC, and do not wait for its response.
+ * @param    smumgr  the address of the powerplay hardware manager.
+ * @param    msg the message to send.
+ * @return   Always return 0.
+ */
+static int smu9_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
+						uint16_t msg)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+
+	return 0;
+}
+
+/*
+ * Send a message to the SMC, and wait for its response.
+ * @param    hwmgr  the address of the powerplay hardware manager.
+ * @param    msg the message to send.
+ * @return   Always return 0.
+ */
+int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t ret;
+
+	smu9_wait_for_response(hwmgr);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+
+	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
+
+	ret = smu9_wait_for_response(hwmgr);
+	if (ret != 1)
+		pr_err("Failed to send message: 0x%x, ret value: 0x%x\n", msg, ret);
+
+	return 0;
+}
+
+/*
+ * Send a message to the SMC with parameter
+ * @param    hwmgr:  the address of the powerplay hardware manager.
+ * @param    msg: the message to send.
+ * @param    parameter: the parameter to send
+ * @return   Always return 0.
+ */
+int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
+					uint16_t msg, uint32_t parameter)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t ret;
+
+	smu9_wait_for_response(hwmgr);
+
+	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);
+
+	ret = smu9_wait_for_response(hwmgr);
+	if (ret != 1)
+		pr_err("Failed message: 0x%x, input parameter: 0x%x, error code: 0x%x\n", msg, parameter, ret);
+
+	return 0;
+}
+
+uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
new file mode 100644
index 000000000000..1462279ca128
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
@@ -0,0 +1,32 @@
+/*
+ * 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.
+ *
+ */
+#ifndef _SMU9_SMUMANAGER_H_
+#define _SMU9_SMUMANAGER_H_
+
+bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr);
+int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg);
+int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
+					uint16_t msg, uint32_t parameter);
+uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c9837935f0f5..99d5e4f98f49 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -96,7 +96,7 @@ int smum_process_firmware_header(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-int smum_get_argument(struct pp_hwmgr *hwmgr)
+uint32_t smum_get_argument(struct pp_hwmgr *hwmgr)
 {
 	if (NULL != hwmgr->smumgr_funcs->get_argument)
 		return hwmgr->smumgr_funcs->get_argument(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index e84669c448a3..5d19115f410c 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -28,142 +28,11 @@
 #include "vega10_hwmgr.h"
 #include "vega10_ppsmc.h"
 #include "smu9_driver_if.h"
+#include "smu9_smumgr.h"
 #include "ppatomctrl.h"
 #include "pp_debug.h"
 
 
-#define AVFS_EN_MSB		1568
-#define AVFS_EN_LSB		1568
-
-/* Microcode file is stored in this buffer */
-#define BUFFER_SIZE                 80000
-#define MAX_STRING_SIZE             15
-#define BUFFER_SIZETWO              131072 /* 128 *1024 */
-
-/* MP Apertures */
-#define MP0_Public                  0x03800000
-#define MP0_SRAM                    0x03900000
-#define MP1_Public                  0x03b00000
-#define MP1_SRAM                    0x03c00004
-
-#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
-#define smnMP0_FW_INTF                                                                                  0x3010104
-#define smnMP1_PUB_CTRL                                                                                 0x3010b14
-
-static bool vega10_is_smc_ram_running(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t mp1_fw_flags;
-
-	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
-			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
-
-	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
-
-	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
-		return true;
-
-	return false;
-}
-
-/*
- * Check if SMC has responded to previous message.
- *
- * @param    smumgr  the address of the powerplay hardware manager.
- * @return   TRUE    SMC has responded, FALSE otherwise.
- */
-static uint32_t vega10_wait_for_response(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
-	uint32_t ret;
-
-	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);
-}
-
-/*
- * Send a message to the SMC, and do not wait for its response.
- * @param    smumgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
-		uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC, and wait for its response.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t ret;
-
-	vega10_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	ret = vega10_wait_for_response(hwmgr);
-	if (ret != 1)
-		pr_err("Failed to send message: 0x%x, ret value: 0x%x\n", msg, ret);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC with parameter
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
-		uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t ret;
-
-	vega10_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
-
-	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	ret = vega10_wait_for_response(hwmgr);
-	if (ret != 1)
-		pr_err("Failed message: 0x%x, input parameter: 0x%x, error code: 0x%x\n", msg, parameter, ret);
-
-	return 0;
-}
-
-static int vega10_get_argument(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
-}
-
 static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id)
 {
@@ -175,13 +44,13 @@ static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			"Invalid SMU Table version!", return -EINVAL);
 	PP_ASSERT_WITH_CODE(priv->smu_tables.entry[table_id].size != 0,
 			"Invalid SMU Table Length!", return -EINVAL);
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableSmu2Dram,
 			priv->smu_tables.entry[table_id].table_id);
 
@@ -206,13 +75,13 @@ 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);
 
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableDram2Smu,
 			priv->smu_tables.entry[table_id].table_id);
 
@@ -225,8 +94,8 @@ static int vega10_get_smc_features(struct pp_hwmgr *hwmgr,
 	if (features_enabled == NULL)
 		return -EINVAL;
 
-	vega10_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures);
-	*features_enabled = vega10_get_argument(hwmgr);
+	smu9_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures);
+	*features_enabled = smu9_get_argument(hwmgr);
 
 	return 0;
 }
@@ -248,10 +117,10 @@ static int vega10_set_tools_address(struct pp_hwmgr *hwmgr)
 	struct vega10_smumgr *priv = hwmgr->smu_backend;
 
 	if (priv->smu_tables.entry[TOOLSTABLE].mc_addr) {
-		vega10_send_msg_to_smc_with_parameter(hwmgr,
+		smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrHigh,
 				upper_32_bits(priv->smu_tables.entry[TOOLSTABLE].mc_addr));
-		vega10_send_msg_to_smc_with_parameter(hwmgr,
+		smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrLow,
 				lower_32_bits(priv->smu_tables.entry[TOOLSTABLE].mc_addr));
 	}
@@ -265,11 +134,11 @@ static int vega10_verify_smc_interface(struct pp_hwmgr *hwmgr)
 	uint32_t dev_id;
 	uint32_t rev_id;
 
-	PP_ASSERT_WITH_CODE(!vega10_send_msg_to_smc(hwmgr,
+	PP_ASSERT_WITH_CODE(!smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetDriverIfVersion),
 			"Attempt to get SMC IF Version Number Failed!",
 			return -EINVAL);
-	smc_driver_if_version = vega10_get_argument(hwmgr);
+	smc_driver_if_version = smu9_get_argument(hwmgr);
 
 	dev_id = adev->pdev->device;
 	rev_id = adev->pdev->revision;
@@ -441,7 +310,7 @@ static int vega10_smu_fini(struct pp_hwmgr *hwmgr)
 
 static int vega10_start_smu(struct pp_hwmgr *hwmgr)
 {
-	if (!vega10_is_smc_ram_running(hwmgr))
+	if (!smu9_is_smc_ram_running(hwmgr))
 		return -EINVAL;
 
 	PP_ASSERT_WITH_CODE(!vega10_verify_smc_interface(hwmgr),
@@ -453,7 +322,8 @@ static int vega10_start_smu(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int vega10_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw)
+static int vega10_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table,
+				    uint16_t table_id, bool rw)
 {
 	int ret;
 
@@ -470,11 +340,11 @@ const struct pp_smumgr_func vega10_smu_funcs = {
 	.smu_fini = &vega10_smu_fini,
 	.start_smu = &vega10_start_smu,
 	.request_smu_load_specific_fw = NULL,
-	.send_msg_to_smc = &vega10_send_msg_to_smc,
-	.send_msg_to_smc_with_parameter = &vega10_send_msg_to_smc_with_parameter,
+	.send_msg_to_smc = &smu9_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = &smu9_send_msg_to_smc_with_parameter,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.is_dpm_running = vega10_is_dpm_running,
-	.get_argument = vega10_get_argument,
+	.get_argument = smu9_get_argument,
 	.smc_table_manager = vega10_smc_table_manager,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 7d9b40e8b1bf..7f0e2109f40d 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -24,157 +24,14 @@
 #include "smumgr.h"
 #include "vega12_inc.h"
 #include "soc15_common.h"
+#include "smu9_smumgr.h"
 #include "vega12_smumgr.h"
 #include "vega12_ppsmc.h"
 #include "vega12/smu9_driver_if.h"
-
 #include "ppatomctrl.h"
 #include "pp_debug.h"
 
 
-/* MP Apertures */
-#define MP0_Public                  0x03800000
-#define MP0_SRAM                    0x03900000
-#define MP1_Public                  0x03b00000
-#define MP1_SRAM                    0x03c00004
-
-#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
-#define smnMP0_FW_INTF                                                                                  0x3010104
-#define smnMP1_PUB_CTRL                                                                                 0x3010b14
-
-static bool vega12_is_smc_ram_running(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t mp1_fw_flags;
-
-	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
-			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
-
-	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
-
-	if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >>
-				MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT)
-		return true;
-
-	return false;
-}
-
-/*
- * Check if SMC has responded to previous message.
- *
- * @param    smumgr  the address of the powerplay hardware manager.
- * @return   TRUE    SMC has responded, FALSE otherwise.
- */
-static uint32_t vega12_wait_for_response(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
-
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
-
-	phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
-}
-
-/*
- * Send a message to the SMC, and do not wait for its response.
- * @param    smumgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
-		uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC, and wait for its response.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	vega12_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	if (vega12_wait_for_response(hwmgr) != 1)
-		pr_err("Failed to send message: 0x%x\n", msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC with parameter
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
-		uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	vega12_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
-
-	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	if (vega12_wait_for_response(hwmgr) != 1)
-		pr_err("Failed to send message: 0x%x\n", msg);
-
-	return 0;
-}
-
-
-/*
- * Send a message to the SMC with parameter, do not wait for response
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   The response that came from the SMC.
- */
-int vega12_send_msg_to_smc_with_parameter_without_waiting(
-		struct pp_hwmgr *hwmgr, uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, parameter);
-
-	return vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-}
-
-/*
- * Retrieve an argument from SMC.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    arg     pointer to store the argument from SMC.
- * @return   Always return 0.
- */
-int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	*arg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
-
-	return 0;
-}
-
 /*
  * Copy table from SMC into driver FB
  * @param   hwmgr    the address of the HW manager
@@ -192,16 +49,16 @@ int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			"Invalid SMU Table version!", return -EINVAL);
 	PP_ASSERT_WITH_CODE(priv->smu_tables.entry[table_id].size != 0,
 			"Invalid SMU Table Length!", return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	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,
 			"[CopyTableFromSMC] Attempt to Set Dram Addr High Failed!", return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableFromSMC] Attempt to Set Dram Addr Low Failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableSmu2Dram,
 			table_id) == 0,
 			"[CopyTableFromSMC] Attempt to Transfer Table From SMU Failed!",
@@ -234,17 +91,17 @@ 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);
 
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	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,
 			"[CopyTableToSMC] Attempt to Set Dram Addr High Failed!",
 			return -EINVAL;);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableToSMC] Attempt to Set Dram Addr Low Failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableDram2Smu,
 			table_id) == 0,
 			"[CopyTableToSMC] Attempt to Transfer Table To SMU Failed!",
@@ -262,20 +119,20 @@ int vega12_enable_smc_features(struct pp_hwmgr *hwmgr,
 	smu_features_high = (uint32_t)((feature_mask & SMU_FEATURES_HIGH_MASK) >> SMU_FEATURES_HIGH_SHIFT);
 
 	if (enable) {
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_EnableSmuFeaturesLow, smu_features_low) == 0,
 				"[EnableDisableSMCFeatures] Attemp to enable SMU features Low failed!",
 				return -EINVAL);
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_EnableSmuFeaturesHigh, smu_features_high) == 0,
 				"[EnableDisableSMCFeatures] Attemp to enable SMU features High failed!",
 				return -EINVAL);
 	} else {
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_DisableSmuFeaturesLow, smu_features_low) == 0,
 				"[EnableDisableSMCFeatures] Attemp to disable SMU features Low failed!",
 				return -EINVAL);
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_DisableSmuFeaturesHigh, smu_features_high) == 0,
 				"[EnableDisableSMCFeatures] Attemp to disable SMU features High failed!",
 				return -EINVAL);
@@ -292,22 +149,17 @@ int vega12_get_enabled_smc_features(struct pp_hwmgr *hwmgr,
 	if (features_enabled == NULL)
 		return -EINVAL;
 
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetEnabledSmuFeaturesLow) == 0,
 			"[GetEnabledSMCFeatures] Attemp to get SMU features Low failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_read_arg_from_smc(hwmgr,
-			&smc_features_low) == 0,
-			"[GetEnabledSMCFeatures] Attemp to read SMU features Low argument failed!",
-			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc(hwmgr,
+	smc_features_low = smu9_get_argument(hwmgr);
+
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetEnabledSmuFeaturesHigh) == 0,
 			"[GetEnabledSMCFeatures] Attemp to get SMU features High failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_read_arg_from_smc(hwmgr,
-			&smc_features_high) == 0,
-			"[GetEnabledSMCFeatures] Attemp to read SMU features High argument failed!",
-			return -EINVAL);
+	smc_features_high = smu9_get_argument(hwmgr);
 
 	*features_enabled = ((((uint64_t)smc_features_low << SMU_FEATURES_LOW_SHIFT) & SMU_FEATURES_LOW_MASK) |
 			(((uint64_t)smc_features_high << SMU_FEATURES_HIGH_SHIFT) & SMU_FEATURES_HIGH_MASK));
@@ -333,39 +185,16 @@ static int vega12_set_tools_address(struct pp_hwmgr *hwmgr)
 			(struct vega12_smumgr *)(hwmgr->smu_backend);
 
 	if (priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr) {
-		if (!vega12_send_msg_to_smc_with_parameter(hwmgr,
+		if (!smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrHigh,
 				upper_32_bits(priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr)))
-			vega12_send_msg_to_smc_with_parameter(hwmgr,
+			smu9_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetToolsDramAddrLow,
 					lower_32_bits(priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr));
 	}
 	return 0;
 }
 
-#if 0 /* tentatively remove */
-static int vega12_verify_smc_interface(struct pp_hwmgr *hwmgr)
-{
-	uint32_t smc_driver_if_version;
-
-	PP_ASSERT_WITH_CODE(!vega12_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_GetDriverIfVersion),
-			"Attempt to get SMC IF Version Number Failed!",
-			return -EINVAL);
-	vega12_read_arg_from_smc(hwmgr, &smc_driver_if_version);
-
-	if (smc_driver_if_version != SMU9_DRIVER_IF_VERSION) {
-		pr_err("Your firmware(0x%x) doesn't match \
-			SMU9_DRIVER_IF_VERSION(0x%x). \
-			Please update your firmware!\n",
-			smc_driver_if_version, SMU9_DRIVER_IF_VERSION);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-#endif
-
 static int vega12_smu_init(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_smumgr *priv;
@@ -513,16 +342,10 @@ static int vega12_smu_fini(struct pp_hwmgr *hwmgr)
 
 static int vega12_start_smu(struct pp_hwmgr *hwmgr)
 {
-	PP_ASSERT_WITH_CODE(vega12_is_smc_ram_running(hwmgr),
+	PP_ASSERT_WITH_CODE(smu9_is_smc_ram_running(hwmgr),
 			"SMC is not running!",
 			return -EINVAL);
 
-#if 0 /* tentatively remove */
-	PP_ASSERT_WITH_CODE(!vega12_verify_smc_interface(hwmgr),
-			"Failed to verify SMC interface!",
-			return -EINVAL);
-#endif
-
 	vega12_set_tools_address(hwmgr);
 
 	return 0;
@@ -533,9 +356,10 @@ const struct pp_smumgr_func vega12_smu_funcs = {
 	.smu_fini = &vega12_smu_fini,
 	.start_smu = &vega12_start_smu,
 	.request_smu_load_specific_fw = NULL,
-	.send_msg_to_smc = &vega12_send_msg_to_smc,
-	.send_msg_to_smc_with_parameter = &vega12_send_msg_to_smc_with_parameter,
+	.send_msg_to_smc = &smu9_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = &smu9_send_msg_to_smc_with_parameter,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.is_dpm_running = vega12_is_dpm_running,
+	.get_argument = smu9_get_argument,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
index 2810d387b611..b285cbc04019 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
@@ -48,7 +48,6 @@ struct vega12_smumgr {
 #define SMU_FEATURES_HIGH_MASK       0xFFFFFFFF00000000
 #define SMU_FEATURES_HIGH_SHIFT      32
 
-int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg);
 int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id);
 int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/arc/arcpgu_sim.c b/drivers/gpu/drm/arc/arcpgu_sim.c
index b8f6f9a5dfbe..68629e614990 100644
--- a/drivers/gpu/drm/arc/arcpgu_sim.c
+++ b/drivers/gpu/drm/arc/arcpgu_sim.c
@@ -99,7 +99,7 @@ int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
 		goto error_encoder_cleanup;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0) {
 		dev_err(drm->dev, "could not attach connector to encoder\n");
 		drm_connector_unregister(connector);
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index f3f08cd6e9ef..e4d67b70244d 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -229,6 +229,8 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = {
 static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *state)
 {
+	int i;
+	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	u32 src_h = state->src_h >> 16;
 
@@ -238,20 +240,17 @@ static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
-	if (!state->fb || !state->crtc)
-		return 0;
-
-	crtc_state = drm_atomic_get_existing_crtc_state(state->state,
-							state->crtc);
-	if (!crtc_state) {
-		DRM_DEBUG_KMS("Invalid crtc state\n");
-		return -EINVAL;
+	for_each_new_crtc_in_state(state->state, crtc, crtc_state, i) {
+		/* we cannot disable the plane while the CRTC is active */
+		if (!state->fb && crtc_state->active)
+			return -EINVAL;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
+						DRM_PLANE_HELPER_NO_SCALING,
+						DRM_PLANE_HELPER_NO_SCALING,
+						false, true);
 	}
 
-	return drm_atomic_helper_check_plane_state(state, crtc_state,
-						   DRM_PLANE_HELPER_NO_SCALING,
-						   DRM_PLANE_HELPER_NO_SCALING,
-						   false, true);
+	return 0;
 }
 
 static void hdlcd_plane_atomic_update(struct drm_plane *plane,
@@ -280,16 +279,10 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
 	.atomic_update = hdlcd_plane_atomic_update,
 };
 
-static void hdlcd_plane_destroy(struct drm_plane *plane)
-{
-	drm_plane_helper_disable(plane, NULL);
-	drm_plane_cleanup(plane);
-}
-
 static const struct drm_plane_funcs hdlcd_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
-	.destroy		= hdlcd_plane_destroy,
+	.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,
@@ -334,10 +327,8 @@ int hdlcd_setup_crtc(struct drm_device *drm)
 
 	ret = drm_crtc_init_with_planes(drm, &hdlcd->crtc, primary, NULL,
 					&hdlcd_crtc_funcs, NULL);
-	if (ret) {
-		hdlcd_plane_destroy(primary);
+	if (ret)
 		return ret;
-	}
 
 	drm_crtc_helper_add(&hdlcd->crtc, &hdlcd_crtc_helper_funcs);
 	return 0;
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index feaa8bc3d7b7..0ed1cde98cf8 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -27,6 +27,7 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_modeset_helper.h>
 #include <drm/drm_of.h>
 
 #include "hdlcd_drv.h"
@@ -100,16 +101,9 @@ setup_fail:
 	return ret;
 }
 
-static void hdlcd_fb_output_poll_changed(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-
-	drm_fbdev_cma_hotplug_event(hdlcd->fbdev);
-}
-
 static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = {
 	.fb_create = drm_gem_fb_create,
-	.output_poll_changed = hdlcd_fb_output_poll_changed,
+	.output_poll_changed = drm_fb_helper_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
@@ -124,13 +118,6 @@ static void hdlcd_setup_mode_config(struct drm_device *drm)
 	drm->mode_config.funcs = &hdlcd_mode_config_funcs;
 }
 
-static void hdlcd_lastclose(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-
-	drm_fbdev_cma_restore_mode(hdlcd->fbdev);
-}
-
 static irqreturn_t hdlcd_irq(int irq, void *arg)
 {
 	struct drm_device *drm = arg;
@@ -246,7 +233,7 @@ static struct drm_driver hdlcd_driver = {
 	.driver_features = DRIVER_HAVE_IRQ | DRIVER_GEM |
 			   DRIVER_MODESET | DRIVER_PRIME |
 			   DRIVER_ATOMIC,
-	.lastclose = hdlcd_lastclose,
+	.lastclose = drm_fb_helper_lastclose,
 	.irq_handler = hdlcd_irq,
 	.irq_preinstall = hdlcd_irq_preinstall,
 	.irq_postinstall = hdlcd_irq_postinstall,
@@ -321,14 +308,9 @@ static int hdlcd_drm_bind(struct device *dev)
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
 
-	hdlcd->fbdev = drm_fbdev_cma_init(drm, 32,
-					  drm->mode_config.num_connector);
-
-	if (IS_ERR(hdlcd->fbdev)) {
-		ret = PTR_ERR(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
+	ret = drm_fb_cma_fbdev_init(drm, 32, 0);
+	if (ret)
 		goto err_fbdev;
-	}
 
 	ret = drm_dev_register(drm, 0);
 	if (ret)
@@ -337,15 +319,13 @@ static int hdlcd_drm_bind(struct device *dev)
 	return 0;
 
 err_register:
-	if (hdlcd->fbdev) {
-		drm_fbdev_cma_fini(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
-	}
+	drm_fb_cma_fbdev_fini(drm);
 err_fbdev:
 	drm_kms_helper_poll_fini(drm);
 err_vblank:
 	pm_runtime_disable(drm->dev);
 err_pm_active:
+	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
 err_unload:
 	of_node_put(hdlcd->crtc.port);
@@ -366,23 +346,23 @@ static void hdlcd_drm_unbind(struct device *dev)
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
 
 	drm_dev_unregister(drm);
-	if (hdlcd->fbdev) {
-		drm_fbdev_cma_fini(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
-	}
+	drm_fb_cma_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 	component_unbind_all(dev, drm);
 	of_node_put(hdlcd->crtc.port);
 	hdlcd->crtc.port = NULL;
-	pm_runtime_get_sync(drm->dev);
+	pm_runtime_get_sync(dev);
+	drm_crtc_vblank_off(&hdlcd->crtc);
 	drm_irq_uninstall(drm);
-	pm_runtime_put_sync(drm->dev);
-	pm_runtime_disable(drm->dev);
-	of_reserved_mem_device_release(drm->dev);
+	drm_atomic_helper_shutdown(drm);
+	pm_runtime_put(dev);
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	of_reserved_mem_device_release(dev);
 	drm_mode_config_cleanup(drm);
-	drm_dev_put(drm);
 	drm->dev_private = NULL;
 	dev_set_drvdata(dev, NULL);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops hdlcd_master_ops = {
@@ -427,35 +407,15 @@ MODULE_DEVICE_TABLE(of, hdlcd_of_match);
 static int __maybe_unused hdlcd_pm_suspend(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
-
-	if (!hdlcd)
-		return 0;
 
-	drm_kms_helper_poll_disable(drm);
-	drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 1);
-
-	hdlcd->state = drm_atomic_helper_suspend(drm);
-	if (IS_ERR(hdlcd->state)) {
-		drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
-		drm_kms_helper_poll_enable(drm);
-		return PTR_ERR(hdlcd->state);
-	}
-
-	return 0;
+	return drm_mode_config_helper_suspend(drm);
 }
 
 static int __maybe_unused hdlcd_pm_resume(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
-
-	if (!hdlcd)
-		return 0;
 
-	drm_atomic_helper_resume(drm, hdlcd->state);
-	drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
-	drm_kms_helper_poll_enable(drm);
+	drm_mode_config_helper_resume(drm);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index 56f34dfff640..fd438d177b64 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -9,10 +9,8 @@
 struct hdlcd_drm_private {
 	void __iomem			*mmio;
 	struct clk			*clk;
-	struct drm_fbdev_cma		*fbdev;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
-	struct drm_atomic_state		*state;
 #ifdef CONFIG_DEBUG_FS
 	atomic_t buffer_underrun_count;
 	atomic_t bus_error_count;
diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 5b7260557391..08b5bb219816 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -616,6 +616,7 @@ static int malidp_bind(struct device *dev)
 	struct malidp_hw_device *hwdev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct of_device_id const *dev_id;
+	struct drm_encoder *encoder;
 	/* number of lines for the R, G and B output */
 	u8 output_width[MAX_OUTPUT_CHANNELS];
 	int ret = 0, i;
@@ -737,6 +738,15 @@ static int malidp_bind(struct device *dev)
 		goto bind_fail;
 	}
 
+	/* We expect to have a maximum of two encoders one for the actual
+	 * display and a virtual one for the writeback connector
+	 */
+	WARN_ON(drm->mode_config.num_encoder > 2);
+	list_for_each_entry(encoder, &drm->mode_config.encoder_list, head) {
+		encoder->possible_clones =
+				(1 << drm->mode_config.num_encoder) -  1;
+	}
+
 	ret = malidp_irq_init(pdev);
 	if (ret < 0)
 		goto irq_init_fail;
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index cfd718e7e97c..ba6ae66387c9 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -73,7 +73,7 @@ static void malidp_mw_connector_reset(struct drm_connector *connector)
 static enum drm_connector_status
 malidp_mw_connector_detect(struct drm_connector *connector, bool force)
 {
-	return connector_status_disconnected;
+	return connector_status_connected;
 }
 
 static void malidp_mw_connector_destroy(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/armada/Makefile b/drivers/gpu/drm/armada/Makefile
index ecf25cf9f9f5..9bc3c3213724 100644
--- a/drivers/gpu/drm/armada/Makefile
+++ b/drivers/gpu/drm/armada/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 armada-y	:= armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \
-		   armada_gem.o armada_overlay.o armada_trace.o
+		   armada_gem.o armada_overlay.o armada_plane.o armada_trace.o
 armada-y	+= armada_510.o
 armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o
 
diff --git a/drivers/gpu/drm/armada/armada_510.c b/drivers/gpu/drm/armada/armada_510.c
index 41a784f5a5e6..2f7c048c5361 100644
--- a/drivers/gpu/drm/armada/armada_510.c
+++ b/drivers/gpu/drm/armada/armada_510.c
@@ -27,6 +27,10 @@ static int armada510_crtc_init(struct armada_crtc *dcrtc, struct device *dev)
 	/* Lower the watermark so to eliminate jitter at higher bandwidths */
 	armada_updatel(0x20, (1 << 11) | 0xff, dcrtc->base + LCD_CFG_RDREG4F);
 
+	/* Initialise SPU register */
+	writel_relaxed(ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND,
+		       dcrtc->base + LCD_SPU_ADV_REG);
+
 	return 0;
 }
 
@@ -75,9 +79,27 @@ static int armada510_crtc_compute_clock(struct armada_crtc *dcrtc,
 	return 0;
 }
 
+static void armada510_crtc_disable(struct armada_crtc *dcrtc)
+{
+	if (!IS_ERR(dcrtc->clk)) {
+		clk_disable_unprepare(dcrtc->clk);
+		dcrtc->clk = ERR_PTR(-EINVAL);
+	}
+}
+
+static void armada510_crtc_enable(struct armada_crtc *dcrtc,
+	const struct drm_display_mode *mode)
+{
+	if (IS_ERR(dcrtc->clk)) {
+		dcrtc->clk = dcrtc->extclk[0];
+		WARN_ON(clk_prepare_enable(dcrtc->clk));
+	}
+}
+
 const struct armada_variant armada510_ops = {
 	.has_spu_adv_reg = true,
-	.spu_adv_reg = ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND,
 	.init = armada510_crtc_init,
 	.compute_clock = armada510_crtc_compute_clock,
+	.disable = armada510_crtc_disable,
+	.enable = armada510_crtc_enable,
 };
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 03eeee11dd5b..da9360688b55 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -11,6 +11,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_atomic_helper.h>
@@ -19,33 +20,9 @@
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
+#include "armada_plane.h"
 #include "armada_trace.h"
 
-enum csc_mode {
-	CSC_AUTO = 0,
-	CSC_YUV_CCIR601 = 1,
-	CSC_YUV_CCIR709 = 2,
-	CSC_RGB_COMPUTER = 1,
-	CSC_RGB_STUDIO = 2,
-};
-
-static const uint32_t armada_primary_formats[] = {
-	DRM_FORMAT_UYVY,
-	DRM_FORMAT_YUYV,
-	DRM_FORMAT_VYUY,
-	DRM_FORMAT_YVYU,
-	DRM_FORMAT_ARGB8888,
-	DRM_FORMAT_ABGR8888,
-	DRM_FORMAT_XRGB8888,
-	DRM_FORMAT_XBGR8888,
-	DRM_FORMAT_RGB888,
-	DRM_FORMAT_BGR888,
-	DRM_FORMAT_ARGB1555,
-	DRM_FORMAT_ABGR1555,
-	DRM_FORMAT_RGB565,
-	DRM_FORMAT_BGR565,
-};
-
 /*
  * A note about interlacing.  Let's consider HDMI 1920x1080i.
  * The timing parameters we have from X are:
@@ -115,15 +92,13 @@ armada_drm_crtc_update_regs(struct armada_crtc *dcrtc, struct armada_regs *regs)
 	}
 }
 
-#define dpms_blanked(dpms)	((dpms) != DRM_MODE_DPMS_ON)
-
-static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
+static void armada_drm_crtc_update(struct armada_crtc *dcrtc, bool enable)
 {
 	uint32_t dumb_ctrl;
 
 	dumb_ctrl = dcrtc->cfg_dumb_ctrl;
 
-	if (!dpms_blanked(dcrtc->dpms))
+	if (enable)
 		dumb_ctrl |= CFG_DUMB_ENA;
 
 	/*
@@ -132,295 +107,26 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
 	 * force LCD_D[23:0] to output blank color, overriding the GPIO or
 	 * SPI usage.  So leave it as-is unless in DUMB24_RGB888_0 mode.
 	 */
-	if (dpms_blanked(dcrtc->dpms) &&
-	    (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
+	if (!enable && (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
 		dumb_ctrl &= ~DUMB_MASK;
 		dumb_ctrl |= DUMB_BLANK;
 	}
 
-	/*
-	 * The documentation doesn't indicate what the normal state of
-	 * the sync signals are.  Sebastian Hesselbart kindly probed
-	 * these signals on his board to determine their state.
-	 *
-	 * The non-inverted state of the sync signals is active high.
-	 * Setting these bits makes the appropriate signal active low.
-	 */
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NCSYNC)
-		dumb_ctrl |= CFG_INV_CSYNC;
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NHSYNC)
-		dumb_ctrl |= CFG_INV_HSYNC;
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NVSYNC)
-		dumb_ctrl |= CFG_INV_VSYNC;
-
-	if (dcrtc->dumb_ctrl != dumb_ctrl) {
-		dcrtc->dumb_ctrl = dumb_ctrl;
-		writel_relaxed(dumb_ctrl, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
-}
-
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y)
-{
-	const struct drm_format_info *format = fb->format;
-	unsigned int num_planes = format->num_planes;
-	u32 addr = drm_fb_obj(fb)->dev_addr;
-	int i;
-
-	if (num_planes > 3)
-		num_planes = 3;
-
-	addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] +
-		   x * format->cpp[0];
-
-	y /= format->vsub;
-	x /= format->hsub;
-
-	for (i = 1; i < num_planes; i++)
-		addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] +
-			     x * format->cpp[i];
-	for (; i < 3; i++)
-		addrs[i] = 0;
-}
-
-static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb,
-	int x, int y, struct armada_regs *regs, bool interlaced)
-{
-	unsigned pitch = fb->pitches[0];
-	u32 addrs[3], addr_odd, addr_even;
-	unsigned i = 0;
-
-	DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n",
-		pitch, x, y, fb->format->cpp[0] * 8);
-
-	armada_drm_plane_calc_addrs(addrs, fb, x, y);
-
-	addr_odd = addr_even = addrs[0];
-
-	if (interlaced) {
-		addr_even += pitch;
-		pitch *= 2;
-	}
-
-	/* write offset, base, and pitch */
-	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
-	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
-	armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH);
-
-	return i;
-}
-
-static void armada_drm_plane_work_call(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work,
-	void (*fn)(struct armada_crtc *, struct armada_plane_work *))
-{
-	struct armada_plane *dplane = drm_to_armada_plane(work->plane);
-	struct drm_pending_vblank_event *event;
-	struct drm_framebuffer *fb;
-
-	if (fn)
-		fn(dcrtc, work);
-	drm_crtc_vblank_put(&dcrtc->crtc);
-
-	event = work->event;
-	fb = work->old_fb;
-	if (event || fb) {
-		struct drm_device *dev = dcrtc->crtc.dev;
-		unsigned long flags;
-
-		spin_lock_irqsave(&dev->event_lock, flags);
-		if (event)
-			drm_crtc_send_vblank_event(&dcrtc->crtc, event);
-		if (fb)
-			__armada_drm_queue_unref_work(dev, fb);
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-	}
-
-	if (work->need_kfree)
-		kfree(work);
-
-	wake_up(&dplane->frame_wait);
+	armada_updatel(dumb_ctrl,
+		       ~(CFG_INV_CSYNC | CFG_INV_HSYNC | CFG_INV_VSYNC),
+		       dcrtc->base + LCD_SPU_DUMB_CTRL);
 }
 
-static void armada_drm_plane_work_run(struct armada_crtc *dcrtc,
-	struct drm_plane *plane)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_plane_work *work = xchg(&dplane->work, NULL);
-
-	/* Handle any pending frame work. */
-	if (work)
-		armada_drm_plane_work_call(dcrtc, work, work->fn);
-}
-
-int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	struct armada_plane *plane = drm_to_armada_plane(work->plane);
-	int ret;
-
-	ret = drm_crtc_vblank_get(&dcrtc->crtc);
-	if (ret)
-		return ret;
-
-	ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0;
-	if (ret)
-		drm_crtc_vblank_put(&dcrtc->crtc);
-
-	return ret;
-}
-
-int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout)
-{
-	return wait_event_timeout(plane->frame_wait, !plane->work, timeout);
-}
-
-void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
-	struct armada_plane *dplane)
-{
-	struct armada_plane_work *work = xchg(&dplane->work, NULL);
-
-	if (work)
-		armada_drm_plane_work_call(dcrtc, work, work->cancel);
-}
-
-static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-static void armada_drm_crtc_complete_disable_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	if (dcrtc->plane == work->plane)
-		dcrtc->plane = NULL;
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-static struct armada_plane_work *
-armada_drm_crtc_alloc_plane_work(struct drm_plane *plane)
-{
-	struct armada_plane_work *work;
-	int i = 0;
-
-	work = kzalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return NULL;
-
-	work->plane = plane;
-	work->fn = armada_drm_crtc_complete_frame_work;
-	work->need_kfree = true;
-	armada_reg_queue_end(work->regs, i);
-
-	return work;
-}
-
-static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc,
-	struct drm_framebuffer *fb, bool force)
-{
-	struct armada_plane_work *work;
-
-	if (!fb)
-		return;
-
-	if (force) {
-		/* Display is disabled, so just drop the old fb */
-		drm_framebuffer_put(fb);
-		return;
-	}
-
-	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
-	if (work) {
-		work->old_fb = fb;
-
-		if (armada_drm_plane_work_queue(dcrtc, work) == 0)
-			return;
-
-		kfree(work);
-	}
-
-	/*
-	 * Oops - just drop the reference immediately and hope for
-	 * the best.  The worst that will happen is the buffer gets
-	 * reused before it has finished being displayed.
-	 */
-	drm_framebuffer_put(fb);
-}
-
-static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
-{
-	/*
-	 * Tell the DRM core that vblank IRQs aren't going to happen for
-	 * a while.  This cleans up any pending vblank events for us.
-	 */
-	drm_crtc_vblank_off(&dcrtc->crtc);
-	armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-}
-
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-
-	if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) {
-		if (dpms_blanked(dpms))
-			armada_drm_vblank_off(dcrtc);
-		else if (!IS_ERR(dcrtc->clk))
-			WARN_ON(clk_prepare_enable(dcrtc->clk));
-		dcrtc->dpms = dpms;
-		armada_drm_crtc_update(dcrtc);
-		if (!dpms_blanked(dpms))
-			drm_crtc_vblank_on(&dcrtc->crtc);
-		else if (!IS_ERR(dcrtc->clk))
-			clk_disable_unprepare(dcrtc->clk);
-	} else if (dcrtc->dpms != dpms) {
-		dcrtc->dpms = dpms;
-	}
-}
-
-/*
- * Prepare for a mode set.  Turn off overlay to ensure that we don't end
- * up with the overlay size being bigger than the active screen size.
- * We rely upon X refreshing this state after the mode set has completed.
- *
- * The mode_config.mutex will be held for this call
- */
-static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct drm_plane *plane;
-
-	/*
-	 * If we have an overlay plane associated with this CRTC, disable
-	 * it before the modeset to avoid its coordinates being outside
-	 * the new mode parameters.
-	 */
-	plane = dcrtc->plane;
-	if (plane) {
-		drm_plane_force_disable(plane);
-		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
-						    HZ));
-	}
-}
-
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_commit(struct drm_crtc *crtc)
+static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_pending_vblank_event *event;
 
-	if (dcrtc->dpms != DRM_MODE_DPMS_ON) {
-		dcrtc->dpms = DRM_MODE_DPMS_ON;
-		armada_drm_crtc_update(dcrtc);
+	/* If we have an event, we need vblank events enabled */
+	event = xchg(&crtc->state->event, NULL);
+	if (event) {
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+		dcrtc->event = event;
 	}
 }
 
@@ -465,8 +171,8 @@ static void armada_drm_crtc_enable_irq(struct armada_crtc *dcrtc, u32 mask)
 
 static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 {
+	struct drm_pending_vblank_event *event;
 	void __iomem *base = dcrtc->base;
-	struct drm_plane *ovl_plane;
 
 	if (stat & DMA_FF_UNDERFLOW)
 		DRM_ERROR("video underflow on crtc %u\n", dcrtc->num);
@@ -476,10 +182,6 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 	if (stat & VSYNC_IRQ)
 		drm_crtc_handle_vblank(&dcrtc->crtc);
 
-	ovl_plane = dcrtc->plane;
-	if (ovl_plane)
-		armada_drm_plane_work_run(dcrtc, ovl_plane);
-
 	spin_lock(&dcrtc->irq_lock);
 	if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) {
 		int i = stat & GRA_FRAME_IRQ0 ? 0 : 1;
@@ -495,22 +197,35 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 		writel_relaxed(val, base + LCD_SPU_ADV_REG);
 	}
 
-	if (stat & DUMB_FRAMEDONE && dcrtc->cursor_update) {
-		writel_relaxed(dcrtc->cursor_hw_pos,
-			       base + LCD_SPU_HWC_OVSA_HPXL_VLN);
-		writel_relaxed(dcrtc->cursor_hw_sz,
-			       base + LCD_SPU_HWC_HPXL_VLN);
-		armada_updatel(CFG_HWC_ENA,
-			       CFG_HWC_ENA | CFG_HWC_1BITMOD | CFG_HWC_1BITENA,
-			       base + LCD_SPU_DMA_CTRL0);
-		dcrtc->cursor_update = false;
+	if (stat & dcrtc->irq_ena & DUMB_FRAMEDONE) {
+		if (dcrtc->update_pending) {
+			armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+			dcrtc->update_pending = false;
+		}
+		if (dcrtc->cursor_update) {
+			writel_relaxed(dcrtc->cursor_hw_pos,
+				       base + LCD_SPU_HWC_OVSA_HPXL_VLN);
+			writel_relaxed(dcrtc->cursor_hw_sz,
+				       base + LCD_SPU_HWC_HPXL_VLN);
+			armada_updatel(CFG_HWC_ENA,
+				       CFG_HWC_ENA | CFG_HWC_1BITMOD |
+				       CFG_HWC_1BITENA,
+				       base + LCD_SPU_DMA_CTRL0);
+			dcrtc->cursor_update = false;
+		}
 		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 	}
-
 	spin_unlock(&dcrtc->irq_lock);
 
-	if (stat & GRA_FRAME_IRQ)
-		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
+	if (stat & VSYNC_IRQ && !dcrtc->update_pending) {
+		event = xchg(&dcrtc->event, NULL);
+		if (event) {
+			spin_lock(&dcrtc->crtc.dev->event_lock);
+			drm_crtc_send_vblank_event(&dcrtc->crtc, event);
+			spin_unlock(&dcrtc->crtc.dev->event_lock);
+			drm_crtc_vblank_put(&dcrtc->crtc);
+		}
+	}
 }
 
 static irqreturn_t armada_drm_irq(int irq, void *arg)
@@ -519,8 +234,9 @@ static irqreturn_t armada_drm_irq(int irq, void *arg)
 	u32 v, stat = readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
 
 	/*
-	 * This is rediculous - rather than writing bits to clear, we
-	 * have to set the actual status register value.  This is racy.
+	 * Reading the ISR appears to clear bits provided CLEAN_SPU_IRQ_ISR
+	 * is set.  Writing has some other effect to acknowledge the IRQ -
+	 * without this, we only get a single IRQ.
 	 */
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
 
@@ -536,107 +252,16 @@ static irqreturn_t armada_drm_irq(int irq, void *arg)
 	return IRQ_NONE;
 }
 
-static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc)
-{
-	struct drm_display_mode *adj = &dcrtc->crtc.mode;
-	uint32_t val = 0;
-
-	if (dcrtc->csc_yuv_mode == CSC_YUV_CCIR709)
-		val |= CFG_CSC_YUV_CCIR709;
-	if (dcrtc->csc_rgb_mode == CSC_RGB_STUDIO)
-		val |= CFG_CSC_RGB_STUDIO;
-
-	/*
-	 * In auto mode, set the colorimetry, based upon the HDMI spec.
-	 * 1280x720p, 1920x1080p and 1920x1080i use ITU709, others use
-	 * ITU601.  It may be more appropriate to set this depending on
-	 * the source - but what if the graphic frame is YUV and the
-	 * video frame is RGB?
-	 */
-	if ((adj->hdisplay == 1280 && adj->vdisplay == 720 &&
-	     !(adj->flags & DRM_MODE_FLAG_INTERLACE)) ||
-	    (adj->hdisplay == 1920 && adj->vdisplay == 1080)) {
-		if (dcrtc->csc_yuv_mode == CSC_AUTO)
-			val |= CFG_CSC_YUV_CCIR709;
-	}
-
-	/*
-	 * We assume we're connected to a TV-like device, so the YUV->RGB
-	 * conversion should produce a limited range.  We should set this
-	 * depending on the connectors attached to this CRTC, and what
-	 * kind of device they report being connected.
-	 */
-	if (dcrtc->csc_rgb_mode == CSC_AUTO)
-		val |= CFG_CSC_RGB_STUDIO;
-
-	return val;
-}
-
-static void armada_drm_gra_plane_regs(struct armada_regs *regs,
-	struct drm_framebuffer *fb, struct armada_plane_state *state,
-	int x, int y, bool interlaced)
-{
-	unsigned int i;
-	u32 ctrl0;
-
-	i = armada_drm_crtc_calc_fb(fb, x, y, regs, interlaced);
-	armada_reg_queue_set(regs, i, state->dst_yx, LCD_SPU_GRA_OVSA_HPXL_VLN);
-	armada_reg_queue_set(regs, i, state->src_hw, LCD_SPU_GRA_HPXL_VLN);
-	armada_reg_queue_set(regs, i, state->dst_hw, LCD_SPU_GZM_HPXL_VLN);
-
-	ctrl0 = state->ctrl0;
-	if (interlaced)
-		ctrl0 |= CFG_GRA_FTOGGLE;
-
-	armada_reg_queue_mod(regs, i, ctrl0, CFG_GRAFORMAT |
-			     CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
-					 CFG_SWAPYU | CFG_YUV2RGB) |
-			     CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
-			     CFG_GRA_HSMOOTH | CFG_GRA_ENA,
-			     LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_end(regs, i);
-}
-
-static void armada_drm_primary_set(struct drm_crtc *crtc,
-	struct drm_plane *plane, int x, int y)
-{
-	struct armada_plane_state *state = &drm_to_armada_plane(plane)->state;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_regs regs[8];
-	bool interlaced = dcrtc->interlaced;
-
-	armada_drm_gra_plane_regs(regs, plane->fb, state, x, y, interlaced);
-	armada_drm_crtc_update_regs(dcrtc, regs);
-}
-
 /* The mode_config.mutex will be held for this call */
-static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
-	struct drm_display_mode *mode, struct drm_display_mode *adj,
-	int x, int y, struct drm_framebuffer *old_fb)
+static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
+	struct drm_display_mode *adj = &crtc->state->adjusted_mode;
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 	struct armada_regs regs[17];
 	uint32_t lm, rm, tm, bm, val, sclk;
 	unsigned long flags;
 	unsigned i;
-	bool interlaced;
-
-	drm_framebuffer_get(crtc->primary->fb);
-
-	interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
-
-	val = CFG_GRA_ENA;
-	val |= CFG_GRA_FMT(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt);
-	val |= CFG_GRA_MOD(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->mod);
-
-	if (drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt > CFG_420)
-		val |= CFG_PALETTE_ENA;
-
-	drm_to_armada_plane(crtc->primary)->state.ctrl0 = val;
-	drm_to_armada_plane(crtc->primary)->state.src_hw =
-	drm_to_armada_plane(crtc->primary)->state.dst_hw =
-		adj->crtc_vdisplay << 16 | adj->crtc_hdisplay;
-	drm_to_armada_plane(crtc->primary)->state.dst_yx = 0;
+	bool interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
 
 	i = 0;
 	rm = adj->crtc_hsync_start - adj->crtc_hdisplay;
@@ -644,35 +269,15 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	bm = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	tm = adj->crtc_vtotal - adj->crtc_vsync_end;
 
-	DRM_DEBUG_DRIVER("H: %d %d %d %d lm %d rm %d\n",
-		adj->crtc_hdisplay,
-		adj->crtc_hsync_start,
-		adj->crtc_hsync_end,
-		adj->crtc_htotal, lm, rm);
-	DRM_DEBUG_DRIVER("V: %d %d %d %d tm %d bm %d\n",
-		adj->crtc_vdisplay,
-		adj->crtc_vsync_start,
-		adj->crtc_vsync_end,
-		adj->crtc_vtotal, tm, bm);
-
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
-
-	drm_crtc_vblank_off(crtc);
-
-	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
-	if (val != dcrtc->dumb_ctrl) {
-		dcrtc->dumb_ctrl = val;
-		writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
-
-	/*
-	 * If we are blanked, we would have disabled the clock.  Re-enable
-	 * it so that compute_clock() does the right thing.
-	 */
-	if (!IS_ERR(dcrtc->clk) && dpms_blanked(dcrtc->dpms))
-		WARN_ON(clk_prepare_enable(dcrtc->clk));
+	DRM_DEBUG_KMS("[CRTC:%d:%s] mode " DRM_MODE_FMT "\n",
+		      crtc->base.id, crtc->name,
+		      adj->base.id, adj->name, adj->vrefresh, adj->clock,
+		      adj->crtc_hdisplay, adj->crtc_hsync_start,
+		      adj->crtc_hsync_end, adj->crtc_htotal,
+		      adj->crtc_vdisplay, adj->crtc_vsync_start,
+		      adj->crtc_vsync_end, adj->crtc_vtotal,
+		      adj->type, adj->flags);
+	DRM_DEBUG_KMS("lm %d rm %d tm %d bm %d\n", lm, rm, tm, bm);
 
 	/* Now compute the divider for real */
 	dcrtc->variant->compute_clock(dcrtc, adj, &sclk);
@@ -689,25 +294,20 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 
 	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 
-	/* Ensure graphic fifo is enabled */
-	armada_reg_queue_mod(regs, i, 0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
-
 	/* Even interlaced/progressive frame */
 	dcrtc->v[1].spu_v_h_total = adj->crtc_vtotal << 16 |
 				    adj->crtc_htotal;
 	dcrtc->v[1].spu_v_porch = tm << 16 | bm;
 	val = adj->crtc_hsync_start;
-	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN |
-		dcrtc->variant->spu_adv_reg;
+	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
 
 	if (interlaced) {
 		/* Odd interlaced frame */
+		val -= adj->crtc_htotal / 2;
+		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
 		dcrtc->v[0].spu_v_h_total = dcrtc->v[1].spu_v_h_total +
 						(1 << 16);
 		dcrtc->v[0].spu_v_porch = dcrtc->v[1].spu_v_porch + 1;
-		val = adj->crtc_hsync_start - adj->crtc_htotal / 2;
-		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN |
-			dcrtc->variant->spu_adv_reg;
 	} else {
 		dcrtc->v[0] = dcrtc->v[1];
 	}
@@ -720,77 +320,136 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	armada_reg_queue_set(regs, i, dcrtc->v[0].spu_v_h_total,
 			   LCD_SPUT_V_H_TOTAL);
 
-	if (dcrtc->variant->has_spu_adv_reg) {
+	if (dcrtc->variant->has_spu_adv_reg)
 		armada_reg_queue_mod(regs, i, dcrtc->v[0].spu_adv_reg,
 				     ADV_VSYNC_L_OFF | ADV_VSYNC_H_OFF |
 				     ADV_VSYNCOFFEN, LCD_SPU_ADV_REG);
-	}
 
 	val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0;
 	armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1);
 
-	val = dcrtc->spu_iopad_ctrl | armada_drm_crtc_calculate_csc(dcrtc);
-	armada_reg_queue_set(regs, i, val, LCD_SPU_IOPAD_CONTROL);
+	/*
+	 * The documentation doesn't indicate what the normal state of
+	 * the sync signals are.  Sebastian Hesselbart kindly probed
+	 * these signals on his board to determine their state.
+	 *
+	 * The non-inverted state of the sync signals is active high.
+	 * Setting these bits makes the appropriate signal active low.
+	 */
+	val = 0;
+	if (adj->flags & DRM_MODE_FLAG_NCSYNC)
+		val |= CFG_INV_CSYNC;
+	if (adj->flags & DRM_MODE_FLAG_NHSYNC)
+		val |= CFG_INV_HSYNC;
+	if (adj->flags & DRM_MODE_FLAG_NVSYNC)
+		val |= CFG_INV_VSYNC;
+	armada_reg_queue_mod(regs, i, val, CFG_INV_CSYNC | CFG_INV_HSYNC |
+			     CFG_INV_VSYNC, LCD_SPU_DUMB_CTRL);
 	armada_reg_queue_end(regs, i);
 
 	armada_drm_crtc_update_regs(dcrtc, regs);
-
-	armada_drm_primary_set(crtc, crtc->primary, x, y);
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+}
 
-	armada_drm_crtc_update(dcrtc);
+static void armada_drm_crtc_atomic_begin(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 
-	drm_crtc_vblank_on(crtc);
-	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	return 0;
+	dcrtc->regs_idx = 0;
+	dcrtc->regs = dcrtc->atomic_regs;
 }
 
-/* The mode_config.mutex will be held for this call */
-static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
-	struct drm_framebuffer *old_fb)
+static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_regs regs[4];
-	unsigned i;
 
-	i = armada_drm_crtc_calc_fb(crtc->primary->fb, crtc->x, crtc->y, regs,
-				    dcrtc->interlaced);
-	armada_reg_queue_end(regs, i);
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
+
+	/*
+	 * If we aren't doing a full modeset, then we need to queue
+	 * the event here.
+	 */
+	if (!drm_atomic_crtc_needs_modeset(crtc->state)) {
+		dcrtc->update_pending = true;
+		armada_drm_crtc_queue_state_event(crtc);
+		spin_lock_irq(&dcrtc->irq_lock);
+		armada_drm_crtc_enable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
+		spin_unlock_irq(&dcrtc->irq_lock);
+	} else {
+		spin_lock_irq(&dcrtc->irq_lock);
+		armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+		spin_unlock_irq(&dcrtc->irq_lock);
+	}
+}
 
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
+static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
+					   struct drm_crtc_state *old_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_pending_vblank_event *event;
 
-	/* Take a reference to the new fb as we're using it */
-	drm_framebuffer_get(crtc->primary->fb);
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	/* Update the base in the CRTC */
-	armada_drm_crtc_update_regs(dcrtc, regs);
+	drm_crtc_vblank_off(crtc);
+	armada_drm_crtc_update(dcrtc, false);
 
-	/* Drop our previously held reference */
-	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+	if (!crtc->state->active) {
+		/*
+		 * This modeset will be leaving the CRTC disabled, so
+		 * call the backend to disable upstream clocks etc.
+		 */
+		if (dcrtc->variant->disable)
+			dcrtc->variant->disable(dcrtc);
 
-	return 0;
+		/*
+		 * We will not receive any further vblank events.
+		 * Send the flip_done event manually.
+		 */
+		event = crtc->state->event;
+		crtc->state->event = NULL;
+		if (event) {
+			spin_lock_irq(&crtc->dev->event_lock);
+			drm_crtc_send_vblank_event(crtc, event);
+			spin_unlock_irq(&crtc->dev->event_lock);
+		}
+	}
 }
 
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_disable(struct drm_crtc *crtc)
+static void armada_drm_crtc_atomic_enable(struct drm_crtc *crtc,
+					  struct drm_crtc_state *old_state)
 {
-	armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	if (!old_state->active) {
+		/*
+		 * This modeset is enabling the CRTC after it having
+		 * been disabled.  Reverse the call to ->disable in
+		 * the atomic_disable().
+		 */
+		if (dcrtc->variant->enable)
+			dcrtc->variant->enable(dcrtc, &crtc->state->adjusted_mode);
+	}
+	armada_drm_crtc_update(dcrtc, true);
+	drm_crtc_vblank_on(crtc);
 
-	/* Disable our primary plane when we disable the CRTC. */
-	crtc->primary->funcs->disable_plane(crtc->primary, NULL);
+	armada_drm_crtc_queue_state_event(crtc);
 }
 
 static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
-	.dpms		= armada_drm_crtc_dpms,
-	.prepare	= armada_drm_crtc_prepare,
-	.commit		= armada_drm_crtc_commit,
 	.mode_fixup	= armada_drm_crtc_mode_fixup,
-	.mode_set	= armada_drm_crtc_mode_set,
-	.mode_set_base	= armada_drm_crtc_mode_set_base,
-	.disable	= armada_drm_crtc_disable,
+	.mode_set_nofb	= armada_drm_crtc_mode_set_nofb,
+	.atomic_begin	= armada_drm_crtc_atomic_begin,
+	.atomic_flush	= armada_drm_crtc_atomic_flush,
+	.atomic_disable	= armada_drm_crtc_atomic_disable,
+	.atomic_enable	= armada_drm_crtc_atomic_enable,
 };
 
 static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix,
@@ -883,7 +542,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload)
 
 	if (!dcrtc->cursor_obj || !h || !w) {
 		spin_lock_irq(&dcrtc->irq_lock);
-		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 		dcrtc->cursor_update = false;
 		armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
 		spin_unlock_irq(&dcrtc->irq_lock);
@@ -907,7 +565,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload)
 
 	if (dcrtc->cursor_hw_sz != (h << 16 | w)) {
 		spin_lock_irq(&dcrtc->irq_lock);
-		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 		dcrtc->cursor_update = false;
 		armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
 		spin_unlock_irq(&dcrtc->irq_lock);
@@ -1015,8 +672,8 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
 	priv->dcrtc[dcrtc->num] = NULL;
 	drm_crtc_cleanup(&dcrtc->crtc);
 
-	if (!IS_ERR(dcrtc->clk))
-		clk_disable_unprepare(dcrtc->clk);
+	if (dcrtc->variant->disable)
+		dcrtc->variant->disable(dcrtc);
 
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ENA);
 
@@ -1025,361 +682,51 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
 	kfree(dcrtc);
 }
 
-/*
- * The mode_config lock is held here, to prevent races between this
- * and a mode_set.
- */
-static int armada_drm_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 armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane_work *work;
-	unsigned i;
-	int ret;
-
-	/* We don't support changing the pixel format */
-	if (fb->format != crtc->primary->fb->format)
-		return -EINVAL;
-
-	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
-	if (!work)
-		return -ENOMEM;
-
-	work->event = event;
-	work->old_fb = dcrtc->crtc.primary->fb;
-
-	i = armada_drm_crtc_calc_fb(fb, crtc->x, crtc->y, work->regs,
-				    dcrtc->interlaced);
-	armada_reg_queue_end(work->regs, i);
-
-	/*
-	 * Ensure that we hold a reference on the new framebuffer.
-	 * This has to match the behaviour in mode_set.
-	 */
-	drm_framebuffer_get(fb);
-
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		/* Undo our reference above */
-		drm_framebuffer_put(fb);
-		kfree(work);
-		return ret;
-	}
-
-	/*
-	 * Don't take a reference on the new framebuffer;
-	 * drm_mode_page_flip_ioctl() has already grabbed a reference and
-	 * will _not_ drop that reference on successful return from this
-	 * function.  Simply mark this new framebuffer as the current one.
-	 */
-	dcrtc->crtc.primary->fb = fb;
-
-	/*
-	 * Finally, if the display is blanked, we won't receive an
-	 * interrupt, so complete it now.
-	 */
-	if (dpms_blanked(dcrtc->dpms))
-		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-
-	return 0;
-}
-
-static int
-armada_drm_crtc_set_property(struct drm_crtc *crtc,
-	struct drm_property *property, uint64_t val)
-{
-	struct armada_private *priv = crtc->dev->dev_private;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	bool update_csc = false;
-
-	if (property == priv->csc_yuv_prop) {
-		dcrtc->csc_yuv_mode = val;
-		update_csc = true;
-	} else if (property == priv->csc_rgb_prop) {
-		dcrtc->csc_rgb_mode = val;
-		update_csc = true;
-	}
-
-	if (update_csc) {
-		uint32_t val;
-
-		val = dcrtc->spu_iopad_ctrl |
-		      armada_drm_crtc_calculate_csc(dcrtc);
-		writel_relaxed(val, dcrtc->base + LCD_SPU_IOPAD_CONTROL);
-	}
-
-	return 0;
-}
-
 /* These are called under the vbl_lock. */
 static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 	armada_drm_crtc_enable_irq(dcrtc, VSYNC_IRQ_ENA);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 	return 0;
 }
 
 static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 	armada_drm_crtc_disable_irq(dcrtc, VSYNC_IRQ_ENA);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 }
 
 static const struct drm_crtc_funcs armada_crtc_funcs = {
+	.reset		= drm_atomic_helper_crtc_reset,
 	.cursor_set	= armada_drm_crtc_cursor_set,
 	.cursor_move	= armada_drm_crtc_cursor_move,
 	.destroy	= armada_drm_crtc_destroy,
-	.set_config	= drm_crtc_helper_set_config,
-	.page_flip	= armada_drm_crtc_page_flip,
-	.set_property	= armada_drm_crtc_set_property,
+	.set_config	= drm_atomic_helper_set_config,
+	.page_flip	= drm_atomic_helper_page_flip,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
 	.enable_vblank	= armada_drm_crtc_enable_vblank,
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
-static void armada_drm_primary_update_state(struct drm_plane_state *state,
-	struct armada_regs *regs)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(state->plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb);
-	bool was_disabled;
-	unsigned int idx = 0;
-	u32 val;
-
-	val = CFG_GRA_FMT(dfb->fmt) | CFG_GRA_MOD(dfb->mod);
-	if (dfb->fmt > CFG_420)
-		val |= CFG_PALETTE_ENA;
-	if (state->visible)
-		val |= CFG_GRA_ENA;
-	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
-		val |= CFG_GRA_HSMOOTH;
-
-	was_disabled = !(dplane->state.ctrl0 & CFG_GRA_ENA);
-	if (was_disabled)
-		armada_reg_queue_mod(regs, idx,
-				     0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
-
-	dplane->state.ctrl0 = val;
-	dplane->state.src_hw = (drm_rect_height(&state->src) & 0xffff0000) |
-				drm_rect_width(&state->src) >> 16;
-	dplane->state.dst_hw = drm_rect_height(&state->dst) << 16 |
-			       drm_rect_width(&state->dst);
-	dplane->state.dst_yx = state->dst.y1 << 16 | state->dst.x1;
-
-	armada_drm_gra_plane_regs(regs + idx, &dfb->fb, &dplane->state,
-				  state->src.x1 >> 16, state->src.y1 >> 16,
-				  dcrtc->interlaced);
-
-	dplane->state.vsync_update = !was_disabled;
-	dplane->state.changed = true;
-}
-
-static int armada_drm_primary_update(struct drm_plane *plane,
-	struct drm_crtc *crtc, struct drm_framebuffer *fb,
-	int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h,
-	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
-	struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane_work *work;
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-	struct drm_crtc_state crtc_state = {
-		.crtc = crtc,
-		.enable = crtc->enabled,
-		.mode = crtc->mode,
-	};
-	int ret;
-
-	ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0,
-						  INT_MAX, true, false);
-	if (ret)
-		return ret;
-
-	work = &dplane->works[dplane->next_work];
-	work->fn = armada_drm_crtc_complete_frame_work;
-
-	if (plane->fb != fb) {
-		/*
-		 * Take a reference on the new framebuffer - we want to
-		 * hold on to it while the hardware is displaying it.
-		 */
-		drm_framebuffer_reference(fb);
-
-		work->old_fb = plane->fb;
-	} else {
-		work->old_fb = NULL;
-	}
-
-	armada_drm_primary_update_state(&state, work->regs);
-
-	if (!dplane->state.changed)
-		return 0;
-
-	/* Wait for pending work to complete */
-	if (armada_drm_plane_work_wait(dplane, HZ / 10) == 0)
-		armada_drm_plane_work_cancel(dcrtc, dplane);
-
-	if (!dplane->state.vsync_update) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-		return 0;
-	}
-
-	/* Queue it for update on the next interrupt if we are enabled */
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-	}
-
-	dplane->next_work = !dplane->next_work;
-
-	return 0;
-}
-
-int armada_drm_plane_disable(struct drm_plane *plane,
-			     struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc;
-	struct armada_plane_work *work;
-	unsigned int idx = 0;
-	u32 sram_para1, enable_mask;
-
-	if (!plane->crtc)
-		return 0;
-
-	/*
-	 * Arrange to power down most RAMs and FIFOs if this is the primary
-	 * plane, otherwise just the YUV FIFOs for the overlay plane.
-	 */
-	if (plane->type == DRM_PLANE_TYPE_PRIMARY) {
-		sram_para1 = CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
-			     CFG_PDWN32x32 | CFG_PDWN64x66;
-		enable_mask = CFG_GRA_ENA;
-	} else {
-		sram_para1 = CFG_PDWN16x66 | CFG_PDWN32x66;
-		enable_mask = CFG_DMA_ENA;
-	}
-
-	dplane->state.ctrl0 &= ~enable_mask;
-
-	dcrtc = drm_to_armada_crtc(plane->crtc);
-
-	/*
-	 * Try to disable the plane and drop our ref on the framebuffer
-	 * at the next frame update. If we fail for any reason, disable
-	 * the plane immediately.
-	 */
-	work = &dplane->works[dplane->next_work];
-	work->fn = armada_drm_crtc_complete_disable_work;
-	work->cancel = armada_drm_crtc_complete_disable_work;
-	work->old_fb = plane->fb;
-
-	armada_reg_queue_mod(work->regs, idx,
-			     0, enable_mask, LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_mod(work->regs, idx,
-			     sram_para1, 0, LCD_SPU_SRAM_PARA1);
-	armada_reg_queue_end(work->regs, idx);
-
-	/* Wait for any preceding work to complete, but don't wedge */
-	if (WARN_ON(!armada_drm_plane_work_wait(dplane, HZ)))
-		armada_drm_plane_work_cancel(dcrtc, dplane);
-
-	if (armada_drm_plane_work_queue(dcrtc, work)) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-	}
-
-	dplane->next_work = !dplane->next_work;
-
-	return 0;
-}
-
-static const struct drm_plane_funcs armada_primary_plane_funcs = {
-	.update_plane	= armada_drm_primary_update,
-	.disable_plane	= armada_drm_plane_disable,
-	.destroy	= drm_primary_helper_destroy,
-};
-
-int armada_drm_plane_init(struct armada_plane *plane)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(plane->works); i++)
-		plane->works[i].plane = &plane->base;
-
-	init_waitqueue_head(&plane->frame_wait);
-
-	return 0;
-}
-
-static const struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = {
-	{ CSC_AUTO,        "Auto" },
-	{ CSC_YUV_CCIR601, "CCIR601" },
-	{ CSC_YUV_CCIR709, "CCIR709" },
-};
-
-static const struct drm_prop_enum_list armada_drm_csc_rgb_enum_list[] = {
-	{ CSC_AUTO,         "Auto" },
-	{ CSC_RGB_COMPUTER, "Computer system" },
-	{ CSC_RGB_STUDIO,   "Studio" },
-};
-
-static int armada_drm_crtc_create_properties(struct drm_device *dev)
-{
-	struct armada_private *priv = dev->dev_private;
-
-	if (priv->csc_yuv_prop)
-		return 0;
-
-	priv->csc_yuv_prop = drm_property_create_enum(dev, 0,
-				"CSC_YUV", armada_drm_csc_yuv_enum_list,
-				ARRAY_SIZE(armada_drm_csc_yuv_enum_list));
-	priv->csc_rgb_prop = drm_property_create_enum(dev, 0,
-				"CSC_RGB", armada_drm_csc_rgb_enum_list,
-				ARRAY_SIZE(armada_drm_csc_rgb_enum_list));
-
-	if (!priv->csc_yuv_prop || !priv->csc_rgb_prop)
-		return -ENOMEM;
-
-	return 0;
-}
-
 static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	struct resource *res, int irq, const struct armada_variant *variant,
 	struct device_node *port)
 {
 	struct armada_private *priv = drm->dev_private;
 	struct armada_crtc *dcrtc;
-	struct armada_plane *primary;
+	struct drm_plane *primary;
 	void __iomem *base;
 	int ret;
 
-	ret = armada_drm_crtc_create_properties(drm);
-	if (ret)
-		return ret;
-
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
@@ -1397,8 +744,6 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	dcrtc->base = base;
 	dcrtc->num = drm->mode_config.num_crtc;
 	dcrtc->clk = ERR_PTR(-EINVAL);
-	dcrtc->csc_yuv_mode = CSC_AUTO;
-	dcrtc->csc_rgb_mode = CSC_AUTO;
 	dcrtc->cfg_dumb_ctrl = DUMB24_RGB888_0;
 	dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24;
 	spin_lock_init(&dcrtc->irq_lock);
@@ -1415,6 +760,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		       CFG_PDWN64x66, dcrtc->base + LCD_SPU_SRAM_PARA1);
 	writel_relaxed(0x2032ff81, dcrtc->base + LCD_SPU_DMA_CTRL1);
 	writel_relaxed(dcrtc->irq_ena, dcrtc->base + LCD_SPU_IRQ_ENA);
+	readl_relaxed(dcrtc->base + LCD_SPU_IRQ_ISR);
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ISR);
 
 	ret = devm_request_irq(dev, irq, armada_drm_irq, 0, "armada_drm_crtc",
@@ -1441,39 +787,23 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		goto err_crtc;
 	}
 
-	ret = armada_drm_plane_init(primary);
-	if (ret) {
-		kfree(primary);
-		goto err_crtc;
-	}
-
-	ret = drm_universal_plane_init(drm, &primary->base, 0,
-				       &armada_primary_plane_funcs,
-				       armada_primary_formats,
-				       ARRAY_SIZE(armada_primary_formats),
-				       NULL,
-				       DRM_PLANE_TYPE_PRIMARY, NULL);
+	ret = armada_drm_primary_plane_init(drm, primary);
 	if (ret) {
 		kfree(primary);
 		goto err_crtc;
 	}
 
-	ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, &primary->base, NULL,
+	ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, primary, NULL,
 					&armada_crtc_funcs, NULL);
 	if (ret)
 		goto err_crtc_init;
 
 	drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs);
 
-	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop,
-				   dcrtc->csc_yuv_mode);
-	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_rgb_prop,
-				   dcrtc->csc_rgb_mode);
-
 	return armada_overlay_plane_create(drm, 1 << dcrtc->num);
 
 err_crtc_init:
-	primary->base.funcs->destroy(&primary->base);
+	primary->funcs->destroy(primary);
 err_crtc:
 	kfree(dcrtc);
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 445829b8877a..7ebd337b60af 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -32,49 +32,8 @@ struct armada_regs {
 	armada_reg_queue_mod(_r, _i, 0, 0, ~0)
 
 struct armada_crtc;
-struct armada_plane;
 struct armada_variant;
 
-struct armada_plane_work {
-	void (*fn)(struct armada_crtc *, struct armada_plane_work *);
-	void (*cancel)(struct armada_crtc *, struct armada_plane_work *);
-	bool need_kfree;
-	struct drm_plane *plane;
-	struct drm_framebuffer *old_fb;
-	struct drm_pending_vblank_event *event;
-	struct armada_regs regs[14];
-};
-
-struct armada_plane_state {
-	u16 src_x;
-	u16 src_y;
-	u32 src_hw;
-	u32 dst_hw;
-	u32 dst_yx;
-	u32 ctrl0;
-	bool changed;
-	bool vsync_update;
-};
-
-struct armada_plane {
-	struct drm_plane	base;
-	wait_queue_head_t	frame_wait;
-	bool			next_work;
-	struct armada_plane_work works[2];
-	struct armada_plane_work *work;
-	struct armada_plane_state state;
-};
-#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
-
-int armada_drm_plane_init(struct armada_plane *plane);
-int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work);
-int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout);
-void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
-	struct armada_plane *plane);
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y);
-
 struct armada_crtc {
 	struct drm_crtc		crtc;
 	const struct armada_variant *variant;
@@ -89,10 +48,6 @@ struct armada_crtc {
 	} v[2];
 	bool			interlaced;
 	bool			cursor_update;
-	uint8_t			csc_yuv_mode;
-	uint8_t			csc_rgb_mode;
-
-	struct drm_plane	*plane;
 
 	struct armada_gem_object	*cursor_obj;
 	int			cursor_x;
@@ -102,21 +57,22 @@ struct armada_crtc {
 	uint32_t		cursor_w;
 	uint32_t		cursor_h;
 
-	int			dpms;
 	uint32_t		cfg_dumb_ctrl;
-	uint32_t		dumb_ctrl;
 	uint32_t		spu_iopad_ctrl;
 
 	spinlock_t		irq_lock;
 	uint32_t		irq_ena;
+
+	bool			update_pending;
+	struct drm_pending_vblank_event *event;
+	struct armada_regs	atomic_regs[32];
+	struct armada_regs	*regs;
+	unsigned int		regs_idx;
 };
 #define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc)
 
 void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *);
 
-int armada_drm_plane_disable(struct drm_plane *plane,
-			     struct drm_modeset_acquire_ctx *ctx);
-
 extern struct platform_driver armada_lcd_platform_driver;
 
 #endif
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index cc4c557c9f66..f09083ff15d3 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -42,11 +42,12 @@ struct armada_private;
 
 struct armada_variant {
 	bool has_spu_adv_reg;
-	uint32_t spu_adv_reg;
 	int (*init)(struct armada_crtc *, struct device *);
 	int (*compute_clock)(struct armada_crtc *,
 			     const struct drm_display_mode *,
 			     uint32_t *);
+	void (*disable)(struct armada_crtc *);
+	void (*enable)(struct armada_crtc *, const struct drm_display_mode *);
 };
 
 /* Variant ops */
@@ -54,14 +55,10 @@ extern const struct armada_variant armada510_ops;
 
 struct armada_private {
 	struct drm_device	drm;
-	struct work_struct	fb_unref_work;
-	DECLARE_KFIFO(fb_unref, struct drm_framebuffer *, 8);
 	struct drm_fb_helper	*fbdev;
 	struct armada_crtc	*dcrtc[2];
 	struct drm_mm		linear; /* protected by linear_lock */
 	struct mutex		linear_lock;
-	struct drm_property	*csc_yuv_prop;
-	struct drm_property	*csc_rgb_prop;
 	struct drm_property	*colorkey_prop;
 	struct drm_property	*colorkey_min_prop;
 	struct drm_property	*colorkey_max_prop;
@@ -76,13 +73,6 @@ struct armada_private {
 #endif
 };
 
-void __armada_drm_queue_unref_work(struct drm_device *,
-	struct drm_framebuffer *);
-void armada_drm_queue_unref_work(struct drm_device *,
-	struct drm_framebuffer *);
-
-extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs;
-
 int armada_fbdev_init(struct drm_device *);
 void armada_fbdev_fini(struct drm_device *);
 
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 4b11b6b52f1d..fa31589b4fc0 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -9,46 +9,18 @@
 #include <linux/component.h>
 #include <linux/module.h>
 #include <linux/of_graph.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_of.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_gem.h"
+#include "armada_fb.h"
 #include "armada_hw.h"
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
 
-static void armada_drm_unref_work(struct work_struct *work)
-{
-	struct armada_private *priv =
-		container_of(work, struct armada_private, fb_unref_work);
-	struct drm_framebuffer *fb;
-
-	while (kfifo_get(&priv->fb_unref, &fb))
-		drm_framebuffer_put(fb);
-}
-
-/* Must be called with dev->event_lock held */
-void __armada_drm_queue_unref_work(struct drm_device *dev,
-	struct drm_framebuffer *fb)
-{
-	struct armada_private *priv = dev->dev_private;
-
-	WARN_ON(!kfifo_put(&priv->fb_unref, fb));
-	schedule_work(&priv->fb_unref_work);
-}
-
-void armada_drm_queue_unref_work(struct drm_device *dev,
-	struct drm_framebuffer *fb)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-	__armada_drm_queue_unref_work(dev, fb);
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-}
-
 static struct drm_ioctl_desc armada_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(ARMADA_GEM_CREATE, armada_gem_create_ioctl,0),
 	DRM_IOCTL_DEF_DRV(ARMADA_GEM_MMAP, armada_gem_mmap_ioctl, 0),
@@ -72,11 +44,18 @@ static struct drm_driver armada_drm_driver = {
 	.desc			= "Armada SoC DRM",
 	.date			= "20120730",
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET |
-				  DRIVER_PRIME,
+				  DRIVER_PRIME | DRIVER_ATOMIC,
 	.ioctls			= armada_ioctls,
 	.fops			= &armada_drm_fops,
 };
 
+static const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
+	.fb_create		= armada_fb_create,
+	.output_poll_changed	= drm_fb_helper_output_poll_changed,
+	.atomic_check		= drm_atomic_helper_check,
+	.atomic_commit		= drm_atomic_helper_commit,
+};
+
 static int armada_drm_bind(struct device *dev)
 {
 	struct armada_private *priv;
@@ -109,7 +88,7 @@ static int armada_drm_bind(struct device *dev)
 
 	/*
 	 * The drm_device structure must be at the start of
-	 * armada_private for drm_dev_unref() to work correctly.
+	 * armada_private for drm_dev_put() to work correctly.
 	 */
 	BUILD_BUG_ON(offsetof(struct armada_private, drm) != 0);
 
@@ -125,9 +104,6 @@ static int armada_drm_bind(struct device *dev)
 
 	dev_set_drvdata(dev, &priv->drm);
 
-	INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work);
-	INIT_KFIFO(priv->fb_unref);
-
 	/* Mode setting support */
 	drm_mode_config_init(&priv->drm);
 	priv->drm.mode_config.min_width = 320;
@@ -155,6 +131,8 @@ static int armada_drm_bind(struct device *dev)
 
 	priv->drm.irq_enabled = true;
 
+	drm_mode_config_reset(&priv->drm);
+
 	ret = armada_fbdev_init(&priv->drm);
 	if (ret)
 		goto err_comp;
@@ -179,8 +157,7 @@ static int armada_drm_bind(struct device *dev)
  err_kms:
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
-	flush_work(&priv->fb_unref_work);
-	drm_dev_unref(&priv->drm);
+	drm_dev_put(&priv->drm);
 	return ret;
 }
 
@@ -198,9 +175,8 @@ static void armada_drm_unbind(struct device *dev)
 
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
-	flush_work(&priv->fb_unref_work);
 
-	drm_dev_unref(&priv->drm);
+	drm_dev_put(&priv->drm);
 }
 
 static int compare_of(struct device *dev, void *data)
diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c
index edd15126bde9..6bd638a54579 100644
--- a/drivers/gpu/drm/armada/armada_fb.c
+++ b/drivers/gpu/drm/armada/armada_fb.c
@@ -84,7 +84,7 @@ struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
 	return dfb;
 }
 
-static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode)
 {
 	struct armada_gem_object *obj;
@@ -138,8 +138,3 @@ static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
 	return ERR_PTR(ret);
 }
-
-const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
-	.fb_create		= armada_fb_create,
-	.output_poll_changed	= drm_fb_helper_output_poll_changed,
-};
diff --git a/drivers/gpu/drm/armada/armada_fb.h b/drivers/gpu/drm/armada/armada_fb.h
index 5c130ff5da77..476daad0a36a 100644
--- a/drivers/gpu/drm/armada/armada_fb.h
+++ b/drivers/gpu/drm/armada/armada_fb.h
@@ -19,5 +19,6 @@ struct armada_framebuffer {
 
 struct armada_framebuffer *armada_framebuffer_create(struct drm_device *,
 	const struct drm_mode_fb_cmd2 *, struct armada_gem_object *);
-
+struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+	struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode);
 #endif
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index 2a59db0994b2..8d23700848df 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -24,7 +24,7 @@ static /*const*/ struct fb_ops armada_fb_ops = {
 	.fb_imageblit	= drm_fb_helper_cfb_imageblit,
 };
 
-static int armada_fb_create(struct drm_fb_helper *fbh,
+static int armada_fbdev_create(struct drm_fb_helper *fbh,
 	struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_device *dev = fbh->dev;
@@ -108,7 +108,7 @@ static int armada_fb_probe(struct drm_fb_helper *fbh,
 	int ret = 0;
 
 	if (!fbh->fb) {
-		ret = armada_fb_create(fbh, sizes);
+		ret = armada_fbdev_create(fbh, sizes);
 		if (ret == 0)
 			ret = 1;
 	}
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 3fb37c75c065..892c1d9304bb 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -13,25 +13,14 @@
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
 
-static int armada_gem_vm_fault(struct vm_fault *vmf)
+static vm_fault_t armada_gem_vm_fault(struct vm_fault *vmf)
 {
 	struct drm_gem_object *gobj = vmf->vma->vm_private_data;
 	struct armada_gem_object *obj = drm_to_armada_gem(gobj);
 	unsigned long pfn = obj->phys_addr >> PAGE_SHIFT;
-	int ret;
 
 	pfn += (vmf->address - vmf->vma->vm_start) >> PAGE_SHIFT;
-	ret = vm_insert_pfn(vmf->vma, vmf->address, pfn);
-
-	switch (ret) {
-	case 0:
-	case -EBUSY:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_pfn(vmf->vma, vmf->address, pfn);
 }
 
 const struct vm_operations_struct armada_gem_vm_ops = {
diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h
index 27319a8335e2..277580b36758 100644
--- a/drivers/gpu/drm/armada/armada_hw.h
+++ b/drivers/gpu/drm/armada/armada_hw.h
@@ -160,6 +160,7 @@ enum {
 	CFG_ALPHAM_GRA		= 0x1 << 16,
 	CFG_ALPHAM_CFG		= 0x2 << 16,
 	CFG_ALPHA_MASK		= 0xff << 8,
+#define CFG_ALPHA(x)		((x) << 8)
 	CFG_PIXCMD_MASK		= 0xff,
 };
 
@@ -315,4 +316,19 @@ enum {
 	PWRDN_IRQ_LEVEL		= 1 << 0,
 };
 
+static inline u32 armada_rect_hw_fp(struct drm_rect *r)
+{
+	return (drm_rect_height(r) & 0xffff0000) | drm_rect_width(r) >> 16;
+}
+
+static inline u32 armada_rect_hw(struct drm_rect *r)
+{
+	return drm_rect_height(r) << 16 | (drm_rect_width(r) & 0x0000ffff);
+}
+
+static inline u32 armada_rect_yx(struct drm_rect *r)
+{
+	return (r)->y1 << 16 | ((r)->x1 & 0x0000ffff);
+}
+
 #endif
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index c391955009d6..eb7dfb65ef47 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -7,346 +7,468 @@
  * published by the Free Software Foundation.
  */
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include <drm/armada_drm.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
-#include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
+#include "armada_plane.h"
 #include "armada_trace.h"
 
-struct armada_ovl_plane_properties {
-	uint32_t colorkey_yr;
-	uint32_t colorkey_ug;
-	uint32_t colorkey_vb;
-#define K2R(val) (((val) >> 0) & 0xff)
-#define K2G(val) (((val) >> 8) & 0xff)
-#define K2B(val) (((val) >> 16) & 0xff)
-	int16_t  brightness;
-	uint16_t contrast;
-	uint16_t saturation;
-	uint32_t colorkey_mode;
-};
-
-struct armada_ovl_plane {
-	struct armada_plane base;
-	struct armada_ovl_plane_properties prop;
+#define DEFAULT_BRIGHTNESS	0
+#define DEFAULT_CONTRAST	0x4000
+#define DEFAULT_SATURATION	0x4000
+#define DEFAULT_ENCODING	DRM_COLOR_YCBCR_BT601
+
+struct armada_overlay_state {
+	struct drm_plane_state base;
+	u32 colorkey_yr;
+	u32 colorkey_ug;
+	u32 colorkey_vb;
+	u32 colorkey_mode;
+	u32 colorkey_enable;
+	s16 brightness;
+	u16 contrast;
+	u16 saturation;
 };
-#define drm_to_armada_ovl_plane(p) \
-	container_of(p, struct armada_ovl_plane, base.base)
-
+#define drm_to_overlay_state(s) \
+	container_of(s, struct armada_overlay_state, base)
 
-static void
-armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
-	struct armada_crtc *dcrtc)
+static inline u32 armada_spu_contrast(struct drm_plane_state *state)
 {
-	writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y);
-	writel_relaxed(prop->colorkey_ug, dcrtc->base + LCD_SPU_COLORKEY_U);
-	writel_relaxed(prop->colorkey_vb, dcrtc->base + LCD_SPU_COLORKEY_V);
+	return drm_to_overlay_state(state)->brightness << 16 |
+	       drm_to_overlay_state(state)->contrast;
+}
 
-	writel_relaxed(prop->brightness << 16 | prop->contrast,
-		       dcrtc->base + LCD_SPU_CONTRAST);
+static inline u32 armada_spu_saturation(struct drm_plane_state *state)
+{
 	/* Docs say 15:0, but it seems to actually be 31:16 on Armada 510 */
-	writel_relaxed(prop->saturation << 16,
-		       dcrtc->base + LCD_SPU_SATURATION);
-	writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE);
-
-	spin_lock_irq(&dcrtc->irq_lock);
-	armada_updatel(prop->colorkey_mode | CFG_ALPHAM_GRA,
-		     CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
-		     dcrtc->base + LCD_SPU_DMA_CTRL1);
+	return drm_to_overlay_state(state)->saturation << 16;
+}
 
-	armada_updatel(ADV_GRACOLORKEY, 0, dcrtc->base + LCD_SPU_ADV_REG);
-	spin_unlock_irq(&dcrtc->irq_lock);
+static inline u32 armada_csc(struct drm_plane_state *state)
+{
+	/*
+	 * The CFG_CSC_RGB_* settings control the output of the colour space
+	 * converter, setting the range of output values it produces.  Since
+	 * we will be blending with the full-range graphics, we need to
+	 * produce full-range RGB output from the conversion.
+	 */
+	return CFG_CSC_RGB_COMPUTER |
+	       (state->color_encoding == DRM_COLOR_YCBCR_BT709 ?
+			CFG_CSC_YUV_CCIR709 : CFG_CSC_YUV_CCIR601);
 }
 
 /* === Plane support === */
-static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
+static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
 {
-	unsigned long flags;
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx;
+	u32 cfg, cfg_mask, val;
 
-	trace_armada_ovl_plane_work(&dcrtc->crtc, work->plane);
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
 
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-static void armada_ovl_plane_update_state(struct drm_plane_state *state,
-	struct armada_regs *regs)
-{
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(state->plane);
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb);
-	const struct drm_format_info *format;
-	unsigned int idx = 0;
-	bool fb_changed;
-	u32 val, ctrl0;
-	u16 src_x, src_y;
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
 
-	ctrl0 = CFG_DMA_FMT(dfb->fmt) | CFG_DMA_MOD(dfb->mod) | CFG_CBSH_ENA;
-	if (state->visible)
-		ctrl0 |= CFG_DMA_ENA;
-	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
-		ctrl0 |= CFG_DMA_HSMOOTH;
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
 
-	/*
-	 * Shifting a YUV packed format image by one pixel causes the U/V
-	 * planes to swap.  Compensate for it by also toggling the UV swap.
-	 */
-	format = dfb->fb.format;
-	if (format->num_planes == 1 && state->src.x1 >> 16 & (format->hsub - 1))
-		ctrl0 ^= CFG_DMA_MOD(CFG_SWAPUV);
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
 
-	if (~dplane->base.state.ctrl0 & ctrl0 & CFG_DMA_ENA) {
-		/* Power up the Y/U/V FIFOs on ENA 0->1 transitions */
+	idx = 0;
+	if (!old_state->visible && state->visible)
 		armada_reg_queue_mod(regs, idx,
 				     0, CFG_PDWN16x66 | CFG_PDWN32x66,
 				     LCD_SPU_SRAM_PARA1);
-	}
-
-	fb_changed = dplane->base.base.fb != &dfb->fb ||
-		     dplane->base.state.src_x != state->src.x1 >> 16 ||
-	             dplane->base.state.src_y != state->src.y1 >> 16;
-
-	dplane->base.state.vsync_update = fb_changed;
-
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DZM_HPXL_VLN);
 	/* FIXME: overlay on an interlaced display */
-	if (fb_changed) {
-		u32 addrs[3];
-
-		dplane->base.state.src_y = src_y = state->src.y1 >> 16;
-		dplane->base.state.src_x = src_x = state->src.x1 >> 16;
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb) {
+		const struct drm_format_info *format;
+		u16 src_x, pitches[3];
+		u32 addrs[2][3];
 
-		armada_drm_plane_calc_addrs(addrs, &dfb->fb, src_x, src_y);
+		armada_drm_plane_calc(state, addrs, pitches, false);
 
-		armada_reg_queue_set(regs, idx, addrs[0],
+		armada_reg_queue_set(regs, idx, addrs[0][0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
-		armada_reg_queue_set(regs, idx, addrs[1],
+		armada_reg_queue_set(regs, idx, addrs[0][1],
 				     LCD_SPU_DMA_START_ADDR_U0);
-		armada_reg_queue_set(regs, idx, addrs[2],
+		armada_reg_queue_set(regs, idx, addrs[0][2],
 				     LCD_SPU_DMA_START_ADDR_V0);
-		armada_reg_queue_set(regs, idx, addrs[0],
+		armada_reg_queue_set(regs, idx, addrs[1][0],
 				     LCD_SPU_DMA_START_ADDR_Y1);
-		armada_reg_queue_set(regs, idx, addrs[1],
+		armada_reg_queue_set(regs, idx, addrs[1][1],
 				     LCD_SPU_DMA_START_ADDR_U1);
-		armada_reg_queue_set(regs, idx, addrs[2],
+		armada_reg_queue_set(regs, idx, addrs[1][2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
-		val = dfb->fb.pitches[0] << 16 | dfb->fb.pitches[0];
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_PITCH_YC);
-		val = dfb->fb.pitches[1] << 16 | dfb->fb.pitches[2];
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_PITCH_UV);
-	}
+		val = pitches[0] << 16 | pitches[0];
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_YC);
+		val = pitches[1] << 16 | pitches[2];
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_UV);
 
-	val = (drm_rect_height(&state->src) & 0xffff0000) |
-	       drm_rect_width(&state->src) >> 16;
-	if (dplane->base.state.src_hw != val) {
-		dplane->base.state.src_hw = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_HPXL_VLN);
-	}
+		cfg = CFG_DMA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_DMA_MOD(drm_fb_to_armada_fb(state->fb)->mod) |
+		      CFG_CBSH_ENA;
+		if (state->visible)
+			cfg |= CFG_DMA_ENA;
 
-	val = drm_rect_height(&state->dst) << 16 | drm_rect_width(&state->dst);
-	if (dplane->base.state.dst_hw != val) {
-		dplane->base.state.dst_hw = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DZM_HPXL_VLN);
+		/*
+		 * Shifting a YUV packed format image by one pixel causes the
+		 * U/V planes to swap.  Compensate for it by also toggling
+		 * the UV swap.
+		 */
+		format = state->fb->format;
+		src_x = state->src.x1 >> 16;
+		if (format->num_planes == 1 && src_x & (format->hsub - 1))
+			cfg ^= CFG_DMA_MOD(CFG_SWAPUV);
+		cfg_mask = CFG_CBSH_ENA | CFG_DMAFORMAT |
+			   CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_DMA_FTOGGLE | CFG_DMA_TSTMODE |
+			   CFG_DMA_ENA;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_DMA_ENA : 0;
+		cfg_mask = CFG_DMA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
 	}
-
-	val = state->dst.y1 << 16 | state->dst.x1;
-	if (dplane->base.state.dst_yx != val) {
-		dplane->base.state.dst_yx = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_OVSA_HPXL_VLN);
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_DMA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_DMA_HSMOOTH;
 	}
 
-	if (dplane->base.state.ctrl0 != ctrl0) {
-		dplane->base.state.ctrl0 = ctrl0;
-		armada_reg_queue_mod(regs, idx, ctrl0,
-			CFG_CBSH_ENA | CFG_DMAFORMAT | CFG_DMA_FTOGGLE |
-			CFG_DMA_HSMOOTH | CFG_DMA_TSTMODE |
-			CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV | CFG_SWAPYU |
-			CFG_YUV2RGB) | CFG_DMA_ENA,
-			LCD_SPU_DMA_CTRL0);
-		dplane->base.state.vsync_update = true;
-	}
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
+
+	val = armada_spu_contrast(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_spu_contrast(old_state) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_CONTRAST);
+	val = armada_spu_saturation(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_spu_saturation(old_state) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_SATURATION);
+	if (!old_state->visible && state->visible)
+		armada_reg_queue_set(regs, idx, 0x00002000, LCD_SPU_CBSH_HUE);
+	val = armada_csc(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_csc(old_state) != val)
+		armada_reg_queue_mod(regs, idx, val, CFG_CSC_MASK,
+				     LCD_SPU_IOPAD_CONTROL);
+	val = drm_to_overlay_state(state)->colorkey_yr;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_yr != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_Y);
+	val = drm_to_overlay_state(state)->colorkey_ug;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_ug != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_U);
+	val = drm_to_overlay_state(state)->colorkey_vb;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_vb != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_V);
+	val = drm_to_overlay_state(state)->colorkey_mode;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_mode != val)
+		armada_reg_queue_mod(regs, idx, val, CFG_CKMODE_MASK |
+				     CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
+				     LCD_SPU_DMA_CTRL1);
+	val = drm_to_overlay_state(state)->colorkey_enable;
+	if (((!old_state->visible && state->visible) ||
+	     drm_to_overlay_state(old_state)->colorkey_enable != val) &&
+	    dcrtc->variant->has_spu_adv_reg)
+		armada_reg_queue_mod(regs, idx, val, ADV_GRACOLORKEY |
+				     ADV_VIDCOLORKEY, LCD_SPU_ADV_REG);
+
+	dcrtc->regs_idx += idx;
+}
+
+static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!old_state->crtc)
+		return;
 
-	dplane->base.state.changed = idx != 0;
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
 
-	armada_reg_queue_end(regs, idx);
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	/* Disable plane and power down the YUV FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_DMA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN16x66 | CFG_PDWN32x66, 0,
+			     LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
 }
 
+static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_overlay_plane_atomic_update,
+	.atomic_disable	= armada_drm_overlay_plane_atomic_disable,
+};
+
 static int
-armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+armada_overlay_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_framebuffer *fb,
 	int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
 	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
 	struct drm_modeset_acquire_ctx *ctx)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane_work *work;
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-	struct drm_crtc_state crtc_state = {
-		.crtc = crtc,
-		.enable = crtc->enabled,
-		.mode = crtc->mode,
-	};
-	int ret;
+	struct drm_atomic_state *state;
+	struct drm_plane_state *plane_state;
+	int ret = 0;
 
 	trace_armada_ovl_plane_update(plane, crtc, fb,
 				 crtc_x, crtc_y, crtc_w, crtc_h,
 				 src_x, src_y, src_w, src_h);
 
-	ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0,
-						  INT_MAX, true, false);
-	if (ret)
-		return ret;
-
-	work = &dplane->base.works[dplane->base.next_work];
-
-	if (plane->fb != fb) {
-		/*
-		 * Take a reference on the new framebuffer - we want to
-		 * hold on to it while the hardware is displaying it.
-		 */
-		drm_framebuffer_reference(fb);
+	state = drm_atomic_state_alloc(plane->dev);
+	if (!state)
+		return -ENOMEM;
 
-		work->old_fb = plane->fb;
-	} else {
-		work->old_fb = NULL;
+	state->acquire_ctx = ctx;
+	plane_state = drm_atomic_get_plane_state(state, plane);
+	if (IS_ERR(plane_state)) {
+		ret = PTR_ERR(plane_state);
+		goto fail;
 	}
 
-	armada_ovl_plane_update_state(&state, work->regs);
-
-	if (!dplane->base.state.changed)
-		return 0;
-
-	/* Wait for pending work to complete */
-	if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0)
-		armada_drm_plane_work_cancel(dcrtc, &dplane->base);
+	ret = drm_atomic_set_crtc_for_plane(plane_state, crtc);
+	if (ret != 0)
+		goto fail;
+
+	drm_atomic_set_fb_for_plane(plane_state, fb);
+	plane_state->crtc_x = crtc_x;
+	plane_state->crtc_y = crtc_y;
+	plane_state->crtc_h = crtc_h;
+	plane_state->crtc_w = crtc_w;
+	plane_state->src_x = src_x;
+	plane_state->src_y = src_y;
+	plane_state->src_h = src_h;
+	plane_state->src_w = src_w;
+
+	ret = drm_atomic_nonblocking_commit(state);
+fail:
+	drm_atomic_state_put(state);
+	return ret;
+}
 
-	/* Just updating the position/size? */
-	if (!dplane->base.state.vsync_update) {
-		armada_ovl_plane_work(dcrtc, work);
-		return 0;
-	}
+static void armada_ovl_plane_destroy(struct drm_plane *plane)
+{
+	drm_plane_cleanup(plane);
+	kfree(plane);
+}
 
-	if (!dcrtc->plane) {
-		dcrtc->plane = plane;
-		armada_ovl_update_attr(&dplane->prop, dcrtc);
+static void armada_overlay_reset(struct drm_plane *plane)
+{
+	struct armada_overlay_state *state;
+
+	if (plane->state)
+		__drm_atomic_helper_plane_destroy_state(plane->state);
+	kfree(plane->state);
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (state) {
+		state->base.plane = plane;
+		state->base.color_encoding = DEFAULT_ENCODING;
+		state->base.color_range = DRM_COLOR_YCBCR_LIMITED_RANGE;
+		state->base.rotation = DRM_MODE_ROTATE_0;
+		state->colorkey_yr = 0xfefefe00;
+		state->colorkey_ug = 0x01010100;
+		state->colorkey_vb = 0x01010100;
+		state->colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
+				       CFG_ALPHAM_GRA | CFG_ALPHA(0);
+		state->colorkey_enable = ADV_GRACOLORKEY;
+		state->brightness = DEFAULT_BRIGHTNESS;
+		state->contrast = DEFAULT_CONTRAST;
+		state->saturation = DEFAULT_SATURATION;
 	}
-
-	/* Queue it for update on the next interrupt if we are enabled */
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret)
-		DRM_ERROR("failed to queue plane work: %d\n", ret);
-
-	dplane->base.next_work = !dplane->base.next_work;
-
-	return 0;
+	plane->state = &state->base;
 }
 
-static void armada_ovl_plane_destroy(struct drm_plane *plane)
+struct drm_plane_state *
+armada_overlay_duplicate_state(struct drm_plane *plane)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
+	struct armada_overlay_state *state;
 
-	drm_plane_cleanup(plane);
+	if (WARN_ON(!plane->state))
+		return NULL;
 
-	kfree(dplane);
+	state = kmemdup(plane->state, sizeof(*state), GFP_KERNEL);
+	if (state)
+		__drm_atomic_helper_plane_duplicate_state(plane, &state->base);
+	return &state->base;
 }
 
-static int armada_ovl_plane_set_property(struct drm_plane *plane,
-	struct drm_property *property, uint64_t val)
+static int armada_overlay_set_property(struct drm_plane *plane,
+	struct drm_plane_state *state, struct drm_property *property,
+	uint64_t val)
 {
 	struct armada_private *priv = plane->dev->dev_private;
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	bool update_attr = false;
 
+#define K2R(val) (((val) >> 0) & 0xff)
+#define K2G(val) (((val) >> 8) & 0xff)
+#define K2B(val) (((val) >> 16) & 0xff)
 	if (property == priv->colorkey_prop) {
 #define CCC(v) ((v) << 24 | (v) << 16 | (v) << 8)
-		dplane->prop.colorkey_yr = CCC(K2R(val));
-		dplane->prop.colorkey_ug = CCC(K2G(val));
-		dplane->prop.colorkey_vb = CCC(K2B(val));
+		drm_to_overlay_state(state)->colorkey_yr = CCC(K2R(val));
+		drm_to_overlay_state(state)->colorkey_ug = CCC(K2G(val));
+		drm_to_overlay_state(state)->colorkey_vb = CCC(K2B(val));
 #undef CCC
-		update_attr = true;
 	} else if (property == priv->colorkey_min_prop) {
-		dplane->prop.colorkey_yr &= ~0x00ff0000;
-		dplane->prop.colorkey_yr |= K2R(val) << 16;
-		dplane->prop.colorkey_ug &= ~0x00ff0000;
-		dplane->prop.colorkey_ug |= K2G(val) << 16;
-		dplane->prop.colorkey_vb &= ~0x00ff0000;
-		dplane->prop.colorkey_vb |= K2B(val) << 16;
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 16;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 16;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 16;
 	} else if (property == priv->colorkey_max_prop) {
-		dplane->prop.colorkey_yr &= ~0xff000000;
-		dplane->prop.colorkey_yr |= K2R(val) << 24;
-		dplane->prop.colorkey_ug &= ~0xff000000;
-		dplane->prop.colorkey_ug |= K2G(val) << 24;
-		dplane->prop.colorkey_vb &= ~0xff000000;
-		dplane->prop.colorkey_vb |= K2B(val) << 24;
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 24;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 24;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 24;
 	} else if (property == priv->colorkey_val_prop) {
-		dplane->prop.colorkey_yr &= ~0x0000ff00;
-		dplane->prop.colorkey_yr |= K2R(val) << 8;
-		dplane->prop.colorkey_ug &= ~0x0000ff00;
-		dplane->prop.colorkey_ug |= K2G(val) << 8;
-		dplane->prop.colorkey_vb &= ~0x0000ff00;
-		dplane->prop.colorkey_vb |= K2B(val) << 8;
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 8;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 8;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 8;
 	} else if (property == priv->colorkey_alpha_prop) {
-		dplane->prop.colorkey_yr &= ~0x000000ff;
-		dplane->prop.colorkey_yr |= K2R(val);
-		dplane->prop.colorkey_ug &= ~0x000000ff;
-		dplane->prop.colorkey_ug |= K2G(val);
-		dplane->prop.colorkey_vb &= ~0x000000ff;
-		dplane->prop.colorkey_vb |= K2B(val);
-		update_attr = true;
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val);
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val);
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val);
 	} else if (property == priv->colorkey_mode_prop) {
-		dplane->prop.colorkey_mode &= ~CFG_CKMODE_MASK;
-		dplane->prop.colorkey_mode |= CFG_CKMODE(val);
-		update_attr = true;
+		if (val == CKMODE_DISABLE) {
+			drm_to_overlay_state(state)->colorkey_mode =
+				CFG_CKMODE(CKMODE_DISABLE) |
+				CFG_ALPHAM_CFG | CFG_ALPHA(255);
+			drm_to_overlay_state(state)->colorkey_enable = 0;
+		} else {
+			drm_to_overlay_state(state)->colorkey_mode =
+				CFG_CKMODE(val) |
+				CFG_ALPHAM_GRA | CFG_ALPHA(0);
+			drm_to_overlay_state(state)->colorkey_enable =
+				ADV_GRACOLORKEY;
+		}
 	} else if (property == priv->brightness_prop) {
-		dplane->prop.brightness = val - 256;
-		update_attr = true;
+		drm_to_overlay_state(state)->brightness = val - 256;
 	} else if (property == priv->contrast_prop) {
-		dplane->prop.contrast = val;
-		update_attr = true;
+		drm_to_overlay_state(state)->contrast = val;
 	} else if (property == priv->saturation_prop) {
-		dplane->prop.saturation = val;
-		update_attr = true;
+		drm_to_overlay_state(state)->saturation = val;
+	} else {
+		return -EINVAL;
 	}
+	return 0;
+}
 
-	if (update_attr && dplane->base.base.crtc)
-		armada_ovl_update_attr(&dplane->prop,
-				       drm_to_armada_crtc(dplane->base.base.crtc));
+static int armada_overlay_get_property(struct drm_plane *plane,
+	const struct drm_plane_state *state, struct drm_property *property,
+	uint64_t *val)
+{
+	struct armada_private *priv = plane->dev->dev_private;
 
+#define C2K(c,s)	(((c) >> (s)) & 0xff)
+#define R2BGR(r,g,b,s)	(C2K(r,s) << 0 | C2K(g,s) << 8 | C2K(b,s) << 16)
+	if (property == priv->colorkey_prop) {
+		/* Do best-efforts here for this property */
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 16);
+		/* If min != max, or min != val, error out */
+		if (*val != R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+				  drm_to_overlay_state(state)->colorkey_ug,
+				  drm_to_overlay_state(state)->colorkey_vb, 24) ||
+		    *val != R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+				  drm_to_overlay_state(state)->colorkey_ug,
+				  drm_to_overlay_state(state)->colorkey_vb, 8))
+			return -EINVAL;
+	} else if (property == priv->colorkey_min_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 16);
+	} else if (property == priv->colorkey_max_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 24);
+	} else if (property == priv->colorkey_val_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 8);
+	} else if (property == priv->colorkey_alpha_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 0);
+	} else if (property == priv->colorkey_mode_prop) {
+		*val = (drm_to_overlay_state(state)->colorkey_mode &
+			CFG_CKMODE_MASK) >> ffs(CFG_CKMODE_MASK);
+	} else if (property == priv->brightness_prop) {
+		*val = drm_to_overlay_state(state)->brightness + 256;
+	} else if (property == priv->contrast_prop) {
+		*val = drm_to_overlay_state(state)->contrast;
+	} else if (property == priv->saturation_prop) {
+		*val = drm_to_overlay_state(state)->saturation;
+	} else {
+		return -EINVAL;
+	}
 	return 0;
 }
 
 static const struct drm_plane_funcs armada_ovl_plane_funcs = {
-	.update_plane	= armada_ovl_plane_update,
-	.disable_plane	= armada_drm_plane_disable,
+	.update_plane	= armada_overlay_plane_update,
+	.disable_plane	= drm_atomic_helper_disable_plane,
 	.destroy	= armada_ovl_plane_destroy,
-	.set_property	= armada_ovl_plane_set_property,
+	.reset		= armada_overlay_reset,
+	.atomic_duplicate_state = armada_overlay_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.atomic_set_property = armada_overlay_set_property,
+	.atomic_get_property = armada_overlay_get_property,
 };
 
 static const uint32_t armada_ovl_formats[] = {
@@ -419,46 +541,31 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 {
 	struct armada_private *priv = dev->dev_private;
 	struct drm_mode_object *mobj;
-	struct armada_ovl_plane *dplane;
+	struct drm_plane *overlay;
 	int ret;
 
 	ret = armada_overlay_create_properties(dev);
 	if (ret)
 		return ret;
 
-	dplane = kzalloc(sizeof(*dplane), GFP_KERNEL);
-	if (!dplane)
+	overlay = kzalloc(sizeof(*overlay), GFP_KERNEL);
+	if (!overlay)
 		return -ENOMEM;
 
-	ret = armada_drm_plane_init(&dplane->base);
-	if (ret) {
-		kfree(dplane);
-		return ret;
-	}
-
-	dplane->base.works[0].fn = armada_ovl_plane_work;
-	dplane->base.works[1].fn = armada_ovl_plane_work;
+	drm_plane_helper_add(overlay, &armada_overlay_plane_helper_funcs);
 
-	ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs,
+	ret = drm_universal_plane_init(dev, overlay, crtcs,
 				       &armada_ovl_plane_funcs,
 				       armada_ovl_formats,
 				       ARRAY_SIZE(armada_ovl_formats),
 				       NULL,
 				       DRM_PLANE_TYPE_OVERLAY, NULL);
 	if (ret) {
-		kfree(dplane);
+		kfree(overlay);
 		return ret;
 	}
 
-	dplane->prop.colorkey_yr = 0xfefefe00;
-	dplane->prop.colorkey_ug = 0x01010100;
-	dplane->prop.colorkey_vb = 0x01010100;
-	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB);
-	dplane->prop.brightness = 0;
-	dplane->prop.contrast = 0x4000;
-	dplane->prop.saturation = 0x4000;
-
-	mobj = &dplane->base.base.base;
+	mobj = &overlay->base;
 	drm_object_attach_property(mobj, priv->colorkey_prop,
 				   0x0101fe);
 	drm_object_attach_property(mobj, priv->colorkey_min_prop,
@@ -471,11 +578,19 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 				   0x000000);
 	drm_object_attach_property(mobj, priv->colorkey_mode_prop,
 				   CKMODE_RGB);
-	drm_object_attach_property(mobj, priv->brightness_prop, 256);
+	drm_object_attach_property(mobj, priv->brightness_prop,
+				   256 + DEFAULT_BRIGHTNESS);
 	drm_object_attach_property(mobj, priv->contrast_prop,
-				   dplane->prop.contrast);
+				   DEFAULT_CONTRAST);
 	drm_object_attach_property(mobj, priv->saturation_prop,
-				   dplane->prop.saturation);
+				   DEFAULT_SATURATION);
 
-	return 0;
+	ret = drm_plane_create_color_properties(overlay,
+						BIT(DRM_COLOR_YCBCR_BT601) |
+						BIT(DRM_COLOR_YCBCR_BT709),
+						BIT(DRM_COLOR_YCBCR_LIMITED_RANGE),
+						DEFAULT_ENCODING,
+						DRM_COLOR_YCBCR_LIMITED_RANGE);
+
+	return ret;
 }
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
new file mode 100644
index 000000000000..9f36423dd394
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -0,0 +1,289 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+#include "armada_plane.h"
+#include "armada_trace.h"
+
+static const uint32_t armada_primary_formats[] = {
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+};
+
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
+	u16 pitches[3], bool interlaced)
+{
+	struct drm_framebuffer *fb = state->fb;
+	const struct drm_format_info *format = fb->format;
+	unsigned int num_planes = format->num_planes;
+	unsigned int x = state->src.x1 >> 16;
+	unsigned int y = state->src.y1 >> 16;
+	u32 addr = drm_fb_obj(fb)->dev_addr;
+	int i;
+
+	DRM_DEBUG_KMS("pitch %u x %d y %d bpp %d\n",
+		      fb->pitches[0], x, y, format->cpp[0] * 8);
+
+	if (num_planes > 3)
+		num_planes = 3;
+
+	addrs[0][0] = addr + fb->offsets[0] + y * fb->pitches[0] +
+		      x * format->cpp[0];
+	pitches[0] = fb->pitches[0];
+
+	y /= format->vsub;
+	x /= format->hsub;
+
+	for (i = 1; i < num_planes; i++) {
+		addrs[0][i] = addr + fb->offsets[i] + y * fb->pitches[i] +
+			      x * format->cpp[i];
+		pitches[i] = fb->pitches[i];
+	}
+	for (; i < 3; i++) {
+		addrs[0][i] = 0;
+		pitches[i] = 0;
+	}
+	if (interlaced) {
+		for (i = 0; i < 3; i++) {
+			addrs[1][i] = addrs[0][i] + pitches[i];
+			pitches[i] *= 2;
+		}
+	} else {
+		for (i = 0; i < 3; i++)
+			addrs[1][i] = addrs[0][i];
+	}
+}
+
+static unsigned armada_drm_crtc_calc_fb(struct drm_plane_state *state,
+	struct armada_regs *regs, bool interlaced)
+{
+	u16 pitches[3];
+	u32 addrs[2][3];
+	unsigned i = 0;
+
+	armada_drm_plane_calc(state, addrs, pitches, interlaced);
+
+	/* write offset, base, and pitch */
+	armada_reg_queue_set(regs, i, addrs[0][0], LCD_CFG_GRA_START_ADDR0);
+	armada_reg_queue_set(regs, i, addrs[1][0], LCD_CFG_GRA_START_ADDR1);
+	armada_reg_queue_mod(regs, i, pitches[0], 0xffff, LCD_CFG_GRA_PITCH);
+
+	return i;
+}
+
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		state->fb ? state->fb->base.id : 0);
+
+	/*
+	 * Take a reference on the new framebuffer - we want to
+	 * hold on to it while the hardware is displaying it.
+	 */
+	if (state->fb)
+		drm_framebuffer_get(state->fb);
+	return 0;
+}
+
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->fb ? old_state->fb->base.id : 0);
+
+	if (old_state->fb)
+		drm_framebuffer_put(old_state->fb);
+}
+
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	if (state->fb && !WARN_ON(!state->crtc)) {
+		struct drm_crtc *crtc = state->crtc;
+		struct drm_crtc_state *crtc_state;
+
+		if (state->state)
+			crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc);
+		else
+			crtc_state = crtc->state;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
+							   0, INT_MAX,
+							   true, false);
+	} else {
+		state->visible = false;
+	}
+	return 0;
+}
+
+static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	u32 cfg, cfg_mask, val;
+	unsigned int idx;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
+
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	idx = 0;
+	if (!old_state->visible && state->visible) {
+		val = CFG_PDWN64x66;
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			val |= CFG_PDWN256x24;
+		armada_reg_queue_mod(regs, idx, 0, val, LCD_SPU_SRAM_PARA1);
+	}
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN);
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb ||
+	    state->crtc->state->mode_changed) {
+		idx += armada_drm_crtc_calc_fb(state, regs + idx,
+					       dcrtc->interlaced);
+	}
+	if (old_state->fb != state->fb ||
+	    state->crtc->state->mode_changed) {
+		cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod);
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			cfg |= CFG_PALETTE_ENA;
+		if (state->visible)
+			cfg |= CFG_GRA_ENA;
+		if (dcrtc->interlaced)
+			cfg |= CFG_GRA_FTOGGLE;
+		cfg_mask = CFG_GRAFORMAT |
+			   CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
+			   CFG_GRA_ENA;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_GRA_ENA : 0;
+		cfg_mask = CFG_GRA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
+	}
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_GRA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_GRA_HSMOOTH;
+	}
+
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
+
+	dcrtc->regs_idx += idx;
+}
+
+static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!old_state->crtc)
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
+
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	/* Disable plane and power down most RAMs and FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_GRA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN256x32 | CFG_PDWN256x24 |
+			     CFG_PDWN256x8 | CFG_PDWN32x32 | CFG_PDWN64x66,
+			     0, LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
+}
+
+static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_primary_plane_atomic_update,
+	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
+};
+
+static const struct drm_plane_funcs armada_primary_plane_funcs = {
+	.update_plane	= drm_atomic_helper_update_plane,
+	.disable_plane	= drm_atomic_helper_disable_plane,
+	.destroy	= drm_primary_helper_destroy,
+	.reset		= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+int armada_drm_primary_plane_init(struct drm_device *drm,
+	struct drm_plane *primary)
+{
+	int ret;
+
+	drm_plane_helper_add(primary, &armada_primary_plane_helper_funcs);
+
+	ret = drm_universal_plane_init(drm, primary, 0,
+				       &armada_primary_plane_funcs,
+				       armada_primary_formats,
+				       ARRAY_SIZE(armada_primary_formats),
+				       NULL,
+				       DRM_PLANE_TYPE_PRIMARY, NULL);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
new file mode 100644
index 000000000000..ff4281ba7fad
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -0,0 +1,15 @@
+#ifndef ARMADA_PLANE_H
+#define ARMADA_PLANE_H
+
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
+	u16 pitches[3], bool interlaced);
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state);
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state);
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state);
+int armada_drm_primary_plane_init(struct drm_device *drm,
+	struct drm_plane *primary);
+
+#endif
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 036dff8a1f33..5e77d456d9bb 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -790,12 +790,12 @@ static int ast_get_modes(struct drm_connector *connector)
 	if (!flags)
 		edid = drm_get_edid(connector, &ast_connector->i2c->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(&ast_connector->base, edid);
+		drm_connector_update_edid_property(&ast_connector->base, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 		return ret;
 	} else
-		drm_mode_connector_update_edid_property(&ast_connector->base, NULL);
+		drm_connector_update_edid_property(&ast_connector->base, NULL);
 	return 0;
 }
 
@@ -900,7 +900,7 @@ static int ast_connector_init(struct drm_device *dev)
 	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
 	encoder = list_first_entry(&dev->mode_config.encoder_list, struct drm_encoder, head);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ast_connector->i2c = ast_i2c_create(dev);
 	if (!ast_connector->i2c)
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 233980a78591..ca5a9afdd5cf 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -259,7 +259,7 @@ int bochs_kms_init(struct bochs_device *bochs)
 	bochs_crtc_init(bochs->dev);
 	bochs_encoder_init(bochs->dev);
 	bochs_connector_init(bochs->dev);
-	drm_mode_connector_attach_encoder(&bochs->connector,
+	drm_connector_attach_encoder(&bochs->connector,
 					  &bochs->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 73021b388e12..6437b878724a 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -601,7 +601,7 @@ static int adv7511_get_modes(struct adv7511 *adv7511,
 		__adv7511_power_off(adv7511);
 
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	count = drm_add_edid_modes(connector, edid);
 
 	adv7511_set_config_csc(adv7511, connector, adv7511->rgb,
@@ -860,7 +860,7 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge)
 	}
 	drm_connector_helper_add(&adv->connector,
 				 &adv7511_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(&adv->connector, bridge->encoder);
+	drm_connector_attach_encoder(&adv->connector, bridge->encoder);
 
 	if (adv->type == ADV7533)
 		ret = adv7533_attach_dsi(adv);
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index b49043866be6..f8433c93f463 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -969,8 +969,8 @@ static int anx78xx_get_modes(struct drm_connector *connector)
 		goto unlock;
 	}
 
-	err = drm_mode_connector_update_edid_property(connector,
-						      anx78xx->edid);
+	err = drm_connector_update_edid_property(connector,
+						 anx78xx->edid);
 	if (err) {
 		DRM_ERROR("Failed to update EDID property: %d\n", err);
 		goto unlock;
@@ -1048,8 +1048,8 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge)
 
 	anx78xx->connector.polled = DRM_CONNECTOR_POLL_HPD;
 
-	err = drm_mode_connector_attach_encoder(&anx78xx->connector,
-						bridge->encoder);
+	err = drm_connector_attach_encoder(&anx78xx->connector,
+					   bridge->encoder);
 	if (err) {
 		DRM_ERROR("Failed to link up connector to encoder: %d\n", err);
 		return err;
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 2bcbfadb6ac5..d68986cea132 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1119,8 +1119,8 @@ static int analogix_dp_get_modes(struct drm_connector *connector)
 		edid = drm_get_edid(connector, &dp->aux.ddc);
 		pm_runtime_put(dp->dev);
 		if (edid) {
-			drm_mode_connector_update_edid_property(&dp->connector,
-								edid);
+			drm_connector_update_edid_property(&dp->connector,
+							   edid);
 			num_modes += drm_add_edid_modes(&dp->connector, edid);
 			kfree(edid);
 		}
@@ -1210,7 +1210,7 @@ static int analogix_dp_bridge_attach(struct drm_bridge *bridge)
 
 		drm_connector_helper_add(connector,
 					 &analogix_dp_connector_helper_funcs);
-		drm_mode_connector_attach_encoder(connector, encoder);
+		drm_connector_attach_encoder(connector, encoder);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index f2d43f24acfb..ce9496d13986 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -1152,7 +1152,7 @@ static int cdns_dsi_attach(struct mipi_dsi_host *host,
 		np = of_node_get(dev->dev.of_node);
 
 	panel = of_drm_find_panel(np);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_DSI);
 	} else {
 		bridge = of_drm_find_bridge(dev->dev.of_node);
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index 9837c8d69e69..9b706789a341 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -55,7 +55,7 @@ static int dumb_vga_get_modes(struct drm_connector *connector)
 		goto fallback;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 	return ret;
@@ -122,7 +122,7 @@ static int dumb_vga_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&vga->connector,
+	drm_connector_attach_encoder(&vga->connector,
 					  bridge->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/lvds-encoder.c b/drivers/gpu/drm/bridge/lvds-encoder.c
index 75b0d3f6e4de..f56c92f7af7c 100644
--- a/drivers/gpu/drm/bridge/lvds-encoder.c
+++ b/drivers/gpu/drm/bridge/lvds-encoder.c
@@ -68,9 +68,9 @@ static int lvds_encoder_probe(struct platform_device *pdev)
 
 	panel = of_drm_find_panel(panel_node);
 	of_node_put(panel_node);
-	if (!panel) {
+	if (IS_ERR(panel)) {
 		dev_dbg(&pdev->dev, "panel not found, deferring probe\n");
-		return -EPROBE_DEFER;
+		return PTR_ERR(panel);
 	}
 
 	lvds_encoder->panel_bridge =
diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
index 7ccadba7c98c..2136c97aeb8e 100644
--- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
+++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
@@ -152,7 +152,7 @@ static int ge_b850v3_lvds_get_modes(struct drm_connector *connector)
 	ge_b850v3_lvds_ptr->edid = (struct edid *)stdp2690_get_edid(client);
 
 	if (ge_b850v3_lvds_ptr->edid) {
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 						      ge_b850v3_lvds_ptr->edid);
 		num_modes = drm_add_edid_modes(connector,
 					       ge_b850v3_lvds_ptr->edid);
@@ -241,7 +241,7 @@ static int ge_b850v3_lvds_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, bridge->encoder);
+	ret = drm_connector_attach_encoder(connector, bridge->encoder);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c
index d64a3283822a..a3e817abace1 100644
--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c
+++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c
@@ -222,7 +222,7 @@ static int ptn3460_get_modes(struct drm_connector *connector)
 	}
 
 	ptn_bridge->edid = (struct edid *)edid;
-	drm_mode_connector_update_edid_property(connector, ptn_bridge->edid);
+	drm_connector_update_edid_property(connector, ptn_bridge->edid);
 
 	num_modes = drm_add_edid_modes(connector, ptn_bridge->edid);
 
@@ -265,7 +265,7 @@ static int ptn3460_bridge_attach(struct drm_bridge *bridge)
 	drm_connector_helper_add(&ptn_bridge->connector,
 					&ptn3460_connector_helper_funcs);
 	drm_connector_register(&ptn_bridge->connector);
-	drm_mode_connector_attach_encoder(&ptn_bridge->connector,
+	drm_connector_attach_encoder(&ptn_bridge->connector,
 							bridge->encoder);
 
 	if (ptn_bridge->panel)
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 6d99d4a3beb3..7cbaba213ef6 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -79,7 +79,7 @@ static int panel_bridge_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&panel_bridge->connector,
+	drm_connector_attach_encoder(&panel_bridge->connector,
 					  bridge->encoder);
 
 	ret = drm_panel_attach(panel_bridge->panel, &panel_bridge->connector);
diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c
index 81198f5e9afa..7334d1b62b71 100644
--- a/drivers/gpu/drm/bridge/parade-ps8622.c
+++ b/drivers/gpu/drm/bridge/parade-ps8622.c
@@ -503,7 +503,7 @@ static int ps8622_attach(struct drm_bridge *bridge)
 	drm_connector_helper_add(&ps8622->connector,
 					&ps8622_connector_helper_funcs);
 	drm_connector_register(&ps8622->connector);
-	drm_mode_connector_attach_encoder(&ps8622->connector,
+	drm_connector_attach_encoder(&ps8622->connector,
 							bridge->encoder);
 
 	if (ps8622->panel)
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 60373d7eb220..e59a13542333 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -170,7 +170,7 @@ static int sii902x_get_modes(struct drm_connector *connector)
 		return ret;
 
 	edid = drm_get_edid(connector, sii902x->i2c->adapter);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	if (edid) {
 		num = drm_add_edid_modes(connector, edid);
 		kfree(edid);
@@ -324,7 +324,7 @@ static int sii902x_bridge_attach(struct drm_bridge *bridge)
 	else
 		sii902x->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
 
-	drm_mode_connector_attach_encoder(&sii902x->connector, bridge->encoder);
+	drm_connector_attach_encoder(&sii902x->connector, bridge->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/sil-sii8620.c b/drivers/gpu/drm/bridge/sil-sii8620.c
index 250effa0e6b8..a6e8f4591e63 100644
--- a/drivers/gpu/drm/bridge/sil-sii8620.c
+++ b/drivers/gpu/drm/bridge/sil-sii8620.c
@@ -14,6 +14,7 @@
 #include <drm/bridge/mhl.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_edid.h>
+#include <drm/drm_encoder.h>
 
 #include <linux/clk.h>
 #include <linux/delay.h>
@@ -72,9 +73,7 @@ struct sii8620 {
 	struct regulator_bulk_data supplies[2];
 	struct mutex lock; /* context lock, protects fields below */
 	int error;
-	int pixel_clock;
 	unsigned int use_packed_pixel:1;
-	int video_code;
 	enum sii8620_mode mode;
 	enum sii8620_sink_type sink_type;
 	u8 cbus_status;
@@ -82,7 +81,6 @@ struct sii8620 {
 	u8 xstat[MHL_XDS_SIZE];
 	u8 devcap[MHL_DCAP_SIZE];
 	u8 xdevcap[MHL_XDC_SIZE];
-	u8 avif[HDMI_INFOFRAME_SIZE(AVI)];
 	bool feature_complete;
 	bool devcap_read;
 	bool sink_detected;
@@ -1017,21 +1015,36 @@ static void sii8620_stop_video(struct sii8620 *ctx)
 
 static void sii8620_set_format(struct sii8620 *ctx)
 {
+	u8 out_fmt;
+
 	if (sii8620_is_mhl3(ctx)) {
 		sii8620_setbits(ctx, REG_M3_P0CTRL,
 				BIT_M3_P0CTRL_MHL3_P0_PIXEL_MODE_PACKED,
 				ctx->use_packed_pixel ? ~0 : 0);
 	} else {
+		if (ctx->use_packed_pixel) {
+			sii8620_write_seq_static(ctx,
+				REG_VID_MODE, BIT_VID_MODE_M1080P,
+				REG_MHL_TOP_CTL, BIT_MHL_TOP_CTL_MHL_PP_SEL | 1,
+				REG_MHLTX_CTL6, 0x60
+			);
+		} else {
 			sii8620_write_seq_static(ctx,
 				REG_VID_MODE, 0,
 				REG_MHL_TOP_CTL, 1,
 				REG_MHLTX_CTL6, 0xa0
 			);
+		}
 	}
 
+	if (ctx->use_packed_pixel)
+		out_fmt = VAL_TPI_FORMAT(YCBCR422, FULL);
+	else
+		out_fmt = VAL_TPI_FORMAT(RGB, FULL);
+
 	sii8620_write_seq(ctx,
 		REG_TPI_INPUT, VAL_TPI_FORMAT(RGB, FULL),
-		REG_TPI_OUTPUT, VAL_TPI_FORMAT(RGB, FULL),
+		REG_TPI_OUTPUT, out_fmt,
 	);
 }
 
@@ -1082,18 +1095,28 @@ static ssize_t mhl3_infoframe_pack(struct mhl3_infoframe *frame,
 	return frm_len;
 }
 
-static void sii8620_set_infoframes(struct sii8620 *ctx)
+static void sii8620_set_infoframes(struct sii8620 *ctx,
+				   struct drm_display_mode *mode)
 {
 	struct mhl3_infoframe mhl_frm;
 	union hdmi_infoframe frm;
 	u8 buf[31];
 	int ret;
 
+	ret = drm_hdmi_avi_infoframe_from_display_mode(&frm.avi,
+						       mode,
+						       true);
+	if (ctx->use_packed_pixel)
+		frm.avi.colorspace = HDMI_COLORSPACE_YUV422;
+
+	if (!ret)
+		ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf));
+	if (ret > 0)
+		sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3);
+
 	if (!sii8620_is_mhl3(ctx) || !ctx->use_packed_pixel) {
 		sii8620_write(ctx, REG_TPI_SC,
 			BIT_TPI_SC_TPI_OUTPUT_MODE_0_HDMI);
-		sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, ctx->avif + 3,
-			ARRAY_SIZE(ctx->avif) - 3);
 		sii8620_write(ctx, REG_PKT_FILTER_0,
 			BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT |
 			BIT_PKT_FILTER_0_DROP_MPEG_PKT |
@@ -1102,16 +1125,6 @@ static void sii8620_set_infoframes(struct sii8620 *ctx)
 		return;
 	}
 
-	ret = hdmi_avi_infoframe_init(&frm.avi);
-	frm.avi.colorspace = HDMI_COLORSPACE_YUV422;
-	frm.avi.active_aspect = HDMI_ACTIVE_ASPECT_PICTURE;
-	frm.avi.picture_aspect = HDMI_PICTURE_ASPECT_16_9;
-	frm.avi.colorimetry = HDMI_COLORIMETRY_ITU_709;
-	frm.avi.video_code = ctx->video_code;
-	if (!ret)
-		ret = hdmi_avi_infoframe_pack(&frm.avi, buf, ARRAY_SIZE(buf));
-	if (ret > 0)
-		sii8620_write_buf(ctx, REG_TPI_AVI_CHSUM, buf + 3, ret - 3);
 	sii8620_write(ctx, REG_PKT_FILTER_0,
 		BIT_PKT_FILTER_0_DROP_CEA_GAMUT_PKT |
 		BIT_PKT_FILTER_0_DROP_MPEG_PKT |
@@ -1131,6 +1144,9 @@ static void sii8620_set_infoframes(struct sii8620 *ctx)
 
 static void sii8620_start_video(struct sii8620 *ctx)
 {
+	struct drm_display_mode *mode =
+		&ctx->bridge.encoder->crtc->state->adjusted_mode;
+
 	if (!sii8620_is_mhl3(ctx))
 		sii8620_stop_video(ctx);
 
@@ -1149,8 +1165,14 @@ static void sii8620_start_video(struct sii8620 *ctx)
 	sii8620_set_format(ctx);
 
 	if (!sii8620_is_mhl3(ctx)) {
-		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
-			MHL_DST_LM_CLK_MODE_NORMAL | MHL_DST_LM_PATH_ENABLED);
+		u8 link_mode = MHL_DST_LM_PATH_ENABLED;
+
+		if (ctx->use_packed_pixel)
+			link_mode |= MHL_DST_LM_CLK_MODE_PACKED_PIXEL;
+		else
+			link_mode |= MHL_DST_LM_CLK_MODE_NORMAL;
+
+		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE), link_mode);
 		sii8620_set_auto_zone(ctx);
 	} else {
 		static const struct {
@@ -1167,7 +1189,7 @@ static void sii8620_start_video(struct sii8620 *ctx)
 			  MHL_XDS_LINK_RATE_6_0_GBPS, 0x40 },
 		};
 		u8 p0_ctrl = BIT_M3_P0CTRL_MHL3_P0_PORT_EN;
-		int clk = ctx->pixel_clock * (ctx->use_packed_pixel ? 2 : 3);
+		int clk = mode->clock * (ctx->use_packed_pixel ? 2 : 3);
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(clk_spec) - 1; ++i)
@@ -1196,7 +1218,7 @@ static void sii8620_start_video(struct sii8620 *ctx)
 			clk_spec[i].link_rate);
 	}
 
-	sii8620_set_infoframes(ctx);
+	sii8620_set_infoframes(ctx, mode);
 }
 
 static void sii8620_disable_hpd(struct sii8620 *ctx)
@@ -1661,14 +1683,18 @@ static void sii8620_status_dcap_ready(struct sii8620 *ctx)
 
 static void sii8620_status_changed_path(struct sii8620 *ctx)
 {
-	if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED) {
-		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
-				      MHL_DST_LM_CLK_MODE_NORMAL
-				      | MHL_DST_LM_PATH_ENABLED);
-	} else {
-		sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
-				      MHL_DST_LM_CLK_MODE_NORMAL);
-	}
+	u8 link_mode;
+
+	if (ctx->use_packed_pixel)
+		link_mode = MHL_DST_LM_CLK_MODE_PACKED_PIXEL;
+	else
+		link_mode = MHL_DST_LM_CLK_MODE_NORMAL;
+
+	if (ctx->stat[MHL_DST_LINK_MODE] & MHL_DST_LM_PATH_ENABLED)
+		link_mode |= MHL_DST_LM_PATH_ENABLED;
+
+	sii8620_mt_write_stat(ctx, MHL_DST_REG(LINK_MODE),
+			      link_mode);
 }
 
 static void sii8620_msc_mr_write_stat(struct sii8620 *ctx)
@@ -2242,8 +2268,6 @@ static bool sii8620_mode_fixup(struct drm_bridge *bridge,
 	mutex_lock(&ctx->lock);
 
 	ctx->use_packed_pixel = sii8620_is_packing_required(ctx, adjusted_mode);
-	ctx->video_code = drm_match_cea_mode(adjusted_mode);
-	ctx->pixel_clock = adjusted_mode->clock;
 
 	mutex_unlock(&ctx->lock);
 
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 3c136f2b954f..5971976284bf 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1922,7 +1922,7 @@ static int dw_hdmi_connector_get_modes(struct drm_connector *connector)
 
 		hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 		hdmi->sink_has_audio = drm_detect_monitor_audio(edid);
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		cec_notifier_set_phys_addr_from_edid(hdmi->cec_notifier, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
@@ -1974,7 +1974,7 @@ static int dw_hdmi_bridge_attach(struct drm_bridge *bridge)
 	drm_connector_init(bridge->dev, connector, &dw_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 0fd9cf27542c..8e28e738cb52 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1140,7 +1140,7 @@ static int tc_connector_get_modes(struct drm_connector *connector)
 	if (!edid)
 		return 0;
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	count = drm_add_edid_modes(connector, edid);
 
 	return count;
@@ -1195,7 +1195,7 @@ static int tc_bridge_attach(struct drm_bridge *bridge)
 
 	drm_display_info_set_bus_formats(&tc->connector.display_info,
 					 &bus_format, 1);
-	drm_mode_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
+	drm_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c
index acb857030951..c3e32138c6bb 100644
--- a/drivers/gpu/drm/bridge/ti-tfp410.c
+++ b/drivers/gpu/drm/bridge/ti-tfp410.c
@@ -62,7 +62,7 @@ static int tfp410_get_modes(struct drm_connector *connector)
 		goto fallback;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	return drm_add_edid_modes(connector, edid);
 fallback:
@@ -132,7 +132,7 @@ static int tfp410_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&dvi->connector,
+	drm_connector_attach_encoder(&dvi->connector,
 					  bridge->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index b529f8c8e2a6..336bfda40125 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -530,7 +530,7 @@ int cirrus_modeset_init(struct cirrus_device *cdev)
 		return -1;
 	}
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ret = cirrus_fbdev_init(cdev);
 	if (ret) {
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 4215be9a9fc5..3eb061e11e2e 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1111,6 +1111,7 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
 	drm_printf(p, "\tcrtc-pos=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&dest));
 	drm_printf(p, "\tsrc-pos=" DRM_RECT_FP_FMT "\n", DRM_RECT_FP_ARG(&src));
 	drm_printf(p, "\trotation=%x\n", state->rotation);
+	drm_printf(p, "\tnormalized-zpos=%x\n", state->normalized_zpos);
 	drm_printf(p, "\tcolor-encoding=%s\n",
 		   drm_get_color_encoding_name(state->color_encoding));
 	drm_printf(p, "\tcolor-range=%s\n",
@@ -2427,6 +2428,7 @@ static int prepare_signaling(struct drm_device *dev,
 	}
 
 	for_each_new_connector_in_state(state, conn, conn_state, i) {
+		struct drm_writeback_connector *wb_conn;
 		struct drm_writeback_job *job;
 		struct drm_out_fence_state *f;
 		struct dma_fence *fence;
@@ -2450,7 +2452,8 @@ static int prepare_signaling(struct drm_device *dev,
 		f[*num_fences].out_fence_ptr = fence_ptr;
 		*fence_state = f;
 
-		fence = drm_writeback_get_out_fence((struct drm_writeback_connector *)conn);
+		wb_conn = drm_connector_to_writeback(conn);
+		fence = drm_writeback_get_out_fence(wb_conn);
 		if (!fence)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 8008a7de2e10..866a2cc72ef6 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -645,7 +645,7 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 		if (ret)
 			return ret;
 
-		connectors_mask += BIT(i);
+		connectors_mask |= BIT(i);
 	}
 
 	/*
@@ -1184,10 +1184,12 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
 		const struct drm_connector_helper_funcs *funcs;
 
 		funcs = connector->helper_private;
+		if (!funcs->atomic_commit)
+			continue;
 
 		if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) {
 			WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
-			funcs->atomic_commit(connector, new_conn_state->writeback_job);
+			funcs->atomic_commit(connector, new_conn_state);
 		}
 	}
 }
@@ -1448,6 +1450,8 @@ void drm_atomic_helper_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
+	drm_atomic_helper_fake_vblank(old_state);
+
 	drm_atomic_helper_commit_hw_done(old_state);
 
 	drm_atomic_helper_wait_for_vblanks(dev, old_state);
@@ -1477,6 +1481,8 @@ void drm_atomic_helper_commit_tail_rpm(struct drm_atomic_state *old_state)
 	drm_atomic_helper_commit_planes(dev, old_state,
 					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
+	drm_atomic_helper_fake_vblank(old_state);
+
 	drm_atomic_helper_commit_hw_done(old_state);
 
 	drm_atomic_helper_wait_for_vblanks(dev, old_state);
@@ -2052,6 +2058,45 @@ void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *old_state)
 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
+ * &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
+ * when a job is queued, and any change to the pipeline that does not touch the
+ * connector is leading to timeouts when calling
+ * drm_atomic_helper_wait_for_vblanks() or
+ * drm_atomic_helper_wait_for_flip_done().
+ *
+ * This is part of the atomic helper support for nonblocking commits, see
+ * drm_atomic_helper_setup_commit() for an overview.
+ */
+void drm_atomic_helper_fake_vblank(struct drm_atomic_state *old_state)
+{
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
+	int i;
+
+	for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) {
+		unsigned long flags;
+
+		if (!new_crtc_state->no_vblank)
+			continue;
+
+		spin_lock_irqsave(&old_state->dev->event_lock, flags);
+		if (new_crtc_state->event) {
+			drm_crtc_send_vblank_event(crtc,
+						   new_crtc_state->event);
+			new_crtc_state->event = NULL;
+		}
+		spin_unlock_irqrestore(&old_state->dev->event_lock, flags);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_fake_vblank);
+
+/**
  * drm_atomic_helper_commit_hw_done - setup possible nonblocking commit
  * @old_state: atomic state object with old state structures
  *
@@ -2822,7 +2867,7 @@ static int update_output_state(struct drm_atomic_state *state,
  * resets the "link-status" property to GOOD, to force any link
  * re-training. The SETCRTC ioctl does not define whether an update does
  * need a full modeset or just a plane update, hence we're allowed to do
- * that. See also drm_mode_connector_set_link_status_property().
+ * that. See also drm_connector_set_link_status_property().
  *
  * Returns:
  * Returns 0 on success, negative errno numbers on failure.
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
new file mode 100644
index 000000000000..baff50a4c234
--- /dev/null
+++ b/drivers/gpu/drm/drm_client.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Noralf Trønnes
+ */
+
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+
+#include <drm/drm_client.h>
+#include <drm/drm_debugfs.h>
+#include <drm/drm_device.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_print.h>
+#include <drm/drmP.h>
+
+#include "drm_crtc_internal.h"
+#include "drm_internal.h"
+
+/**
+ * DOC: overview
+ *
+ * This library provides support for clients running in the kernel like fbdev and bootsplash.
+ * Currently it's only partially implemented, just enough to support fbdev.
+ *
+ * GEM drivers which provide a GEM based dumb buffer with a virtual address are supported.
+ */
+
+static int drm_client_open(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+	struct drm_file *file;
+
+	file = drm_file_alloc(dev->primary);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&dev->filelist_mutex);
+	list_add(&file->lhead, &dev->filelist_internal);
+	mutex_unlock(&dev->filelist_mutex);
+
+	client->file = file;
+
+	return 0;
+}
+
+static void drm_client_close(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+
+	mutex_lock(&dev->filelist_mutex);
+	list_del(&client->file->lhead);
+	mutex_unlock(&dev->filelist_mutex);
+
+	drm_file_free(client->file);
+}
+EXPORT_SYMBOL(drm_client_close);
+
+/**
+ * drm_client_new - Create a DRM client
+ * @dev: DRM device
+ * @client: DRM client
+ * @name: Client name
+ * @funcs: DRM client functions (optional)
+ *
+ * The caller needs to hold a reference on @dev before calling this function.
+ * The client is freed when the &drm_device is unregistered. See drm_client_release().
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
+		   const char *name, const struct drm_client_funcs *funcs)
+{
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET) ||
+	    !dev->driver->dumb_create || !dev->driver->gem_prime_vmap)
+		return -ENOTSUPP;
+
+	if (funcs && !try_module_get(funcs->owner))
+		return -ENODEV;
+
+	client->dev = dev;
+	client->name = name;
+	client->funcs = funcs;
+
+	ret = drm_client_open(client);
+	if (ret)
+		goto err_put_module;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_add(&client->list, &dev->clientlist);
+	mutex_unlock(&dev->clientlist_mutex);
+
+	drm_dev_get(dev);
+
+	return 0;
+
+err_put_module:
+	if (funcs)
+		module_put(funcs->owner);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_client_new);
+
+/**
+ * drm_client_release - Release DRM client resources
+ * @client: DRM client
+ *
+ * Releases resources by closing the &drm_file that was opened by drm_client_new().
+ * It is called automatically if the &drm_client_funcs.unregister callback is _not_ set.
+ *
+ * This function should only be called from the unregister callback. An exception
+ * is fbdev which cannot free the buffer if userspace has open file descriptors.
+ *
+ * Note:
+ * Clients cannot initiate a release by themselves. This is done to keep the code simple.
+ * The driver has to be unloaded before the client can be unloaded.
+ */
+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_client_close(client);
+	drm_dev_put(dev);
+	if (client->funcs)
+		module_put(client->funcs->owner);
+}
+EXPORT_SYMBOL(drm_client_release);
+
+void drm_client_dev_unregister(struct drm_device *dev)
+{
+	struct drm_client_dev *client, *tmp;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry_safe(client, tmp, &dev->clientlist, list) {
+		list_del(&client->list);
+		if (client->funcs && client->funcs->unregister) {
+			client->funcs->unregister(client);
+		} else {
+			drm_client_release(client);
+			kfree(client);
+		}
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+
+/**
+ * drm_client_dev_hotplug - Send hotplug event to clients
+ * @dev: DRM device
+ *
+ * This function calls the &drm_client_funcs.hotplug callback on the attached clients.
+ *
+ * drm_kms_helper_hotplug_event() calls this function, so drivers that use it
+ * don't need to call this function themselves.
+ */
+void drm_client_dev_hotplug(struct drm_device *dev)
+{
+	struct drm_client_dev *client;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list) {
+		if (!client->funcs || !client->funcs->hotplug)
+			continue;
+
+		ret = client->funcs->hotplug(client);
+		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+EXPORT_SYMBOL(drm_client_dev_hotplug);
+
+void drm_client_dev_restore(struct drm_device *dev)
+{
+	struct drm_client_dev *client;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list) {
+		if (!client->funcs || !client->funcs->restore)
+			continue;
+
+		ret = client->funcs->restore(client);
+		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		if (!ret) /* The first one to return zero gets the privilege to restore */
+			break;
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+
+static void drm_client_buffer_delete(struct drm_client_buffer *buffer)
+{
+	struct drm_device *dev = buffer->client->dev;
+
+	if (buffer->vaddr && dev->driver->gem_prime_vunmap)
+		dev->driver->gem_prime_vunmap(buffer->gem, buffer->vaddr);
+
+	if (buffer->gem)
+		drm_gem_object_put_unlocked(buffer->gem);
+
+	if (buffer->handle)
+		drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file);
+
+	kfree(buffer);
+}
+
+static struct drm_client_buffer *
+drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+{
+	struct drm_mode_create_dumb dumb_args = { };
+	struct drm_device *dev = client->dev;
+	struct drm_client_buffer *buffer;
+	struct drm_gem_object *obj;
+	void *vaddr;
+	int ret;
+
+	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	buffer->client = client;
+
+	dumb_args.width = width;
+	dumb_args.height = height;
+	dumb_args.bpp = drm_format_plane_cpp(format, 0) * 8;
+	ret = drm_mode_create_dumb(dev, &dumb_args, client->file);
+	if (ret)
+		goto err_delete;
+
+	buffer->handle = dumb_args.handle;
+	buffer->pitch = dumb_args.pitch;
+
+	obj = drm_gem_object_lookup(client->file, dumb_args.handle);
+	if (!obj)  {
+		ret = -ENOENT;
+		goto err_delete;
+	}
+
+	buffer->gem = obj;
+
+	/*
+	 * FIXME: The dependency on GEM here isn't required, we could
+	 * convert the driver handle to a dma-buf instead and use the
+	 * backend-agnostic dma-buf vmap support instead. This would
+	 * require that the handle2fd prime ioctl is reworked to pull the
+	 * fd_install step out of the driver backend hooks, to make that
+	 * final step optional for internal users.
+	 */
+	vaddr = dev->driver->gem_prime_vmap(obj);
+	if (!vaddr) {
+		ret = -ENOMEM;
+		goto err_delete;
+	}
+
+	buffer->vaddr = vaddr;
+
+	return buffer;
+
+err_delete:
+	drm_client_buffer_delete(buffer);
+
+	return ERR_PTR(ret);
+}
+
+static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer)
+{
+	int ret;
+
+	if (!buffer->fb)
+		return;
+
+	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);
+
+	buffer->fb = NULL;
+}
+
+static int drm_client_buffer_addfb(struct drm_client_buffer *buffer,
+				   u32 width, u32 height, u32 format)
+{
+	struct drm_client_dev *client = buffer->client;
+	struct drm_mode_fb_cmd fb_req = { };
+	const struct drm_format_info *info;
+	int ret;
+
+	info = drm_format_info(format);
+	fb_req.bpp = info->cpp[0] * 8;
+	fb_req.depth = info->depth;
+	fb_req.width = width;
+	fb_req.height = height;
+	fb_req.handle = buffer->handle;
+	fb_req.pitch = buffer->pitch;
+
+	ret = drm_mode_addfb(client->dev, &fb_req, client->file);
+	if (ret)
+		return ret;
+
+	buffer->fb = drm_framebuffer_lookup(client->dev, buffer->client->file, fb_req.fb_id);
+	if (WARN_ON(!buffer->fb))
+		return -ENOENT;
+
+	/* drop the reference we picked up in framebuffer lookup */
+	drm_framebuffer_put(buffer->fb);
+
+	strscpy(buffer->fb->comm, client->name, TASK_COMM_LEN);
+
+	return 0;
+}
+
+/**
+ * drm_client_framebuffer_create - Create a client framebuffer
+ * @client: DRM client
+ * @width: Framebuffer width
+ * @height: Framebuffer height
+ * @format: Buffer format
+ *
+ * This function creates a &drm_client_buffer which consists of a
+ * &drm_framebuffer backed by a dumb buffer.
+ * Call drm_client_framebuffer_delete() to free the buffer.
+ *
+ * Returns:
+ * Pointer to a client buffer or an error pointer on failure.
+ */
+struct drm_client_buffer *
+drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+{
+	struct drm_client_buffer *buffer;
+	int ret;
+
+	buffer = drm_client_buffer_create(client, width, height, format);
+	if (IS_ERR(buffer))
+		return buffer;
+
+	ret = drm_client_buffer_addfb(buffer, width, height, format);
+	if (ret) {
+		drm_client_buffer_delete(buffer);
+		return ERR_PTR(ret);
+	}
+
+	return buffer;
+}
+EXPORT_SYMBOL(drm_client_framebuffer_create);
+
+/**
+ * drm_client_framebuffer_delete - Delete a client framebuffer
+ * @buffer: DRM client buffer (can be NULL)
+ */
+void drm_client_framebuffer_delete(struct drm_client_buffer *buffer)
+{
+	if (!buffer)
+		return;
+
+	drm_client_buffer_rmfb(buffer);
+	drm_client_buffer_delete(buffer);
+}
+EXPORT_SYMBOL(drm_client_framebuffer_delete);
+
+#ifdef CONFIG_DEBUG_FS
+static int drm_client_debugfs_internal_clients(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_printer p = drm_seq_file_printer(m);
+	struct drm_client_dev *client;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list)
+		drm_printf(&p, "%s\n", client->name);
+	mutex_unlock(&dev->clientlist_mutex);
+
+	return 0;
+}
+
+static const struct drm_info_list drm_client_debugfs_list[] = {
+	{ "internal_clients", drm_client_debugfs_internal_clients, 0 },
+};
+
+int drm_client_debugfs_init(struct drm_minor *minor)
+{
+	return drm_debugfs_create_files(drm_client_debugfs_list,
+					ARRAY_SIZE(drm_client_debugfs_list),
+					minor->debugfs_root, minor);
+}
+#endif
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index b09b3a3e4024..6011d769d50b 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -48,7 +48,7 @@
  *
  * Connectors must be attached to an encoder to be used. For devices that map
  * connectors to encoders 1:1, the connector should be attached at
- * initialization time with a call to drm_mode_connector_attach_encoder(). The
+ * initialization time with a call to drm_connector_attach_encoder(). The
  * driver must also set the &drm_connector.encoder field to point to the
  * attached encoder.
  *
@@ -291,7 +291,7 @@ out_put:
 EXPORT_SYMBOL(drm_connector_init);
 
 /**
- * drm_mode_connector_attach_encoder - attach a connector to an encoder
+ * drm_connector_attach_encoder - attach a connector to an encoder
  * @connector: connector to attach
  * @encoder: encoder to attach @connector to
  *
@@ -302,8 +302,8 @@ EXPORT_SYMBOL(drm_connector_init);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_attach_encoder(struct drm_connector *connector,
-				      struct drm_encoder *encoder)
+int drm_connector_attach_encoder(struct drm_connector *connector,
+				 struct drm_encoder *encoder)
 {
 	int i;
 
@@ -321,7 +321,7 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 	if (WARN_ON(connector->encoder))
 		return -EINVAL;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
+	for (i = 0; i < ARRAY_SIZE(connector->encoder_ids); i++) {
 		if (connector->encoder_ids[i] == 0) {
 			connector->encoder_ids[i] = encoder->base.id;
 			return 0;
@@ -329,7 +329,30 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 	}
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(drm_mode_connector_attach_encoder);
+EXPORT_SYMBOL(drm_connector_attach_encoder);
+
+/**
+ * drm_connector_has_possible_encoder - check if the connector and encoder are assosicated with each other
+ * @connector: the connector
+ * @encoder: the encoder
+ *
+ * Returns:
+ * True if @encoder is one of the possible encoders for @connector.
+ */
+bool drm_connector_has_possible_encoder(struct drm_connector *connector,
+					struct drm_encoder *encoder)
+{
+	struct drm_encoder *enc;
+	int i;
+
+	drm_connector_for_each_possible_encoder(connector, enc, i) {
+		if (enc == encoder)
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(drm_connector_has_possible_encoder);
 
 static void drm_mode_remove(struct drm_connector *connector,
 			    struct drm_display_mode *mode)
@@ -583,7 +606,7 @@ __drm_connector_put_safe(struct drm_connector *conn)
 
 /**
  * drm_connector_list_iter_next - return next connector
- * @iter: connectr_list iterator
+ * @iter: connector_list iterator
  *
  * Returns the next connector for @iter, or NULL when the list walk has
  * completed.
@@ -791,7 +814,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * 	Blob property which contains the current EDID read from the sink. This
  * 	is useful to parse sink identification information like vendor, model
  * 	and serial. Drivers should update this property by calling
- * 	drm_mode_connector_update_edid_property(), usually after having parsed
+ * 	drm_connector_update_edid_property(), usually after having parsed
  * 	the EDID using drm_add_edid_modes(). Userspace cannot change this
  * 	property.
  * DPMS:
@@ -829,7 +852,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * PATH:
  * 	Connector path property to identify how this sink is physically
  * 	connected. Used by DP MST. This should be set by calling
- * 	drm_mode_connector_set_path_property(), in the case of DP MST with the
+ * 	drm_connector_set_path_property(), in the case of DP MST with the
  * 	path property the MST manager created. Userspace cannot change this
  * 	property.
  * TILE:
@@ -840,14 +863,14 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * 	are not gen-locked. Note that for tiled panels which are genlocked, like
  * 	dual-link LVDS or dual-link DSI, the driver should try to not expose the
  * 	tiling and virtualize both &drm_crtc and &drm_plane if needed. Drivers
- * 	should update this value using drm_mode_connector_set_tile_property().
+ * 	should update this value using drm_connector_set_tile_property().
  * 	Userspace cannot change this property.
  * link-status:
  *      Connector link-status property to indicate the status of link. The
  *      default value of link-status is "GOOD". If something fails during or
  *      after modeset, the kernel driver may set this to "BAD" and issue a
  *      hotplug uevent. Drivers should update this value using
- *      drm_mode_connector_set_link_status_property().
+ *      drm_connector_set_link_status_property().
  * non_desktop:
  * 	Indicates the output should be ignored for purposes of displaying a
  * 	standard desktop environment or console. This is most likely because
@@ -1402,7 +1425,7 @@ int drm_mode_create_suggested_offset_properties(struct drm_device *dev)
 EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties);
 
 /**
- * drm_mode_connector_set_path_property - set tile property on connector
+ * drm_connector_set_path_property - set tile property on connector
  * @connector: connector to set property on.
  * @path: path to use for property; must not be NULL.
  *
@@ -1414,8 +1437,8 @@ EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_set_path_property(struct drm_connector *connector,
-					 const char *path)
+int drm_connector_set_path_property(struct drm_connector *connector,
+				    const char *path)
 {
 	struct drm_device *dev = connector->dev;
 	int ret;
@@ -1428,10 +1451,10 @@ int drm_mode_connector_set_path_property(struct drm_connector *connector,
 	                                       dev->mode_config.path_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_set_path_property);
+EXPORT_SYMBOL(drm_connector_set_path_property);
 
 /**
- * drm_mode_connector_set_tile_property - set tile property on connector
+ * drm_connector_set_tile_property - set tile property on connector
  * @connector: connector to set property on.
  *
  * This looks up the tile information for a connector, and creates a
@@ -1441,7 +1464,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_path_property);
  * Returns:
  * Zero on success, errno on failure.
  */
-int drm_mode_connector_set_tile_property(struct drm_connector *connector)
+int drm_connector_set_tile_property(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	char tile[256];
@@ -1471,10 +1494,10 @@ int drm_mode_connector_set_tile_property(struct drm_connector *connector)
 	                                       dev->mode_config.tile_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
+EXPORT_SYMBOL(drm_connector_set_tile_property);
 
 /**
- * drm_mode_connector_update_edid_property - update the edid property of a connector
+ * drm_connector_update_edid_property - update the edid property of a connector
  * @connector: drm connector
  * @edid: new value of the edid property
  *
@@ -1484,8 +1507,8 @@ EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_update_edid_property(struct drm_connector *connector,
-					    const struct edid *edid)
+int drm_connector_update_edid_property(struct drm_connector *connector,
+				       const struct edid *edid)
 {
 	struct drm_device *dev = connector->dev;
 	size_t size = 0;
@@ -1523,10 +1546,10 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 	                                       dev->mode_config.edid_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_update_edid_property);
+EXPORT_SYMBOL(drm_connector_update_edid_property);
 
 /**
- * drm_mode_connector_set_link_status_property - Set link status property of a connector
+ * drm_connector_set_link_status_property - Set link status property of a connector
  * @connector: drm connector
  * @link_status: new value of link status property (0: Good, 1: Bad)
  *
@@ -1544,8 +1567,8 @@ EXPORT_SYMBOL(drm_mode_connector_update_edid_property);
  * it is not limited to DP or link training. For example, if we implement
  * asynchronous setcrtc, this property can be used to report any failures in that.
  */
-void drm_mode_connector_set_link_status_property(struct drm_connector *connector,
-						 uint64_t link_status)
+void drm_connector_set_link_status_property(struct drm_connector *connector,
+					    uint64_t link_status)
 {
 	struct drm_device *dev = connector->dev;
 
@@ -1553,7 +1576,7 @@ void drm_mode_connector_set_link_status_property(struct drm_connector *connector
 	connector->state->link_status = link_status;
 	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 }
-EXPORT_SYMBOL(drm_mode_connector_set_link_status_property);
+EXPORT_SYMBOL(drm_connector_set_link_status_property);
 
 /**
  * drm_connector_init_panel_orientation_property -
@@ -1606,7 +1629,7 @@ int drm_connector_init_panel_orientation_property(
 }
 EXPORT_SYMBOL(drm_connector_init_panel_orientation_property);
 
-int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
+int drm_connector_set_obj_prop(struct drm_mode_object *obj,
 				    struct drm_property *property,
 				    uint64_t value)
 {
@@ -1624,8 +1647,8 @@ int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
 	return ret;
 }
 
-int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-				       void *data, struct drm_file *file_priv)
+int drm_connector_property_set_ioctl(struct drm_device *dev,
+				     void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_connector_set_property *conn_set_prop = data;
 	struct drm_mode_obj_set_property obj_set_prop = {
@@ -1706,22 +1729,19 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	if (!connector)
 		return -ENOENT;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++)
-		if (connector->encoder_ids[i] != 0)
-			encoders_count++;
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		encoders_count++;
 
 	if ((out_resp->count_encoders >= encoders_count) && encoders_count) {
 		copied = 0;
 		encoder_ptr = (uint32_t __user *)(unsigned long)(out_resp->encoders_ptr);
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] != 0) {
-				if (put_user(connector->encoder_ids[i],
-					     encoder_ptr + copied)) {
-					ret = -EFAULT;
-					goto out;
-				}
-				copied++;
+
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
+			if (put_user(encoder->base.id, encoder_ptr + copied)) {
+				ret = -EFAULT;
+				goto out;
 			}
+			copied++;
 		}
 	}
 	out_resp->count_encoders = encoders_count;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index a6906c4ab880..bae43938c8f6 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -461,6 +461,8 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	struct drm_crtc *tmp;
 	int ret;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(crtc->dev));
+
 	/*
 	 * NOTE: ->set_config can also disable other crtcs (if we steal all
 	 * connectors from it), hence we need to refcount the fbs across all
@@ -478,10 +480,8 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	if (ret == 0) {
 		struct drm_plane *plane = crtc->primary;
 
-		if (!plane->state) {
-			plane->crtc = fb ? crtc : NULL;
-			plane->fb = fb;
-		}
+		plane->crtc = fb ? crtc : NULL;
+		plane->fb = fb;
 	}
 
 	drm_for_each_crtc(tmp, crtc->dev) {
@@ -496,6 +496,7 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 
 	return ret;
 }
+
 /**
  * drm_mode_set_config_internal - helper to call &drm_mode_config_funcs.set_config
  * @set: modeset config to set
@@ -740,7 +741,11 @@ retry:
 	set.connectors = connector_set;
 	set.num_connectors = crtc_req->count_connectors;
 	set.fb = fb;
-	ret = __drm_mode_set_config_internal(&set, &ctx);
+
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = crtc->funcs->set_config(&set, &ctx);
+	else
+		ret = __drm_mode_set_config_internal(&set, &ctx);
 
 out:
 	if (fb)
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 235d40fce8b5..b61322763394 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -148,7 +148,7 @@ void drm_connector_ida_init(void);
 void drm_connector_ida_destroy(void);
 void drm_connector_unregister_all(struct drm_device *dev);
 int drm_connector_register_all(struct drm_device *dev);
-int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
+int drm_connector_set_obj_prop(struct drm_mode_object *obj,
 				    struct drm_property *property,
 				    uint64_t value);
 int drm_connector_create_standard_properties(struct drm_device *dev);
@@ -156,8 +156,8 @@ const char *drm_get_connector_force_name(enum drm_connector_force force);
 void drm_connector_free_work_fn(struct work_struct *work);
 
 /* IOCTL */
-int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-					  void *data, struct drm_file *file_priv);
+int drm_connector_property_set_ioctl(struct drm_device *dev,
+				     void *data, struct drm_file *file_priv);
 int drm_mode_getconnector(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv);
 
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index b2482818fee8..6f28fe58f169 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_debugfs.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_atomic.h>
@@ -164,6 +165,12 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id,
 			DRM_ERROR("Failed to create framebuffer debugfs file\n");
 			return ret;
 		}
+
+		ret = drm_client_debugfs_init(minor);
+		if (ret) {
+			DRM_ERROR("Failed to create client debugfs file\n");
+			return ret;
+		}
 	}
 
 	if (dev->driver->debugfs_init) {
@@ -307,13 +314,13 @@ static ssize_t edid_write(struct file *file, const char __user *ubuf,
 
 	if (len == 5 && !strncmp(buf, "reset", 5)) {
 		connector->override_edid = false;
-		ret = drm_mode_connector_update_edid_property(connector, NULL);
+		ret = drm_connector_update_edid_property(connector, NULL);
 	} else if (len < EDID_LENGTH ||
 		   EDID_LENGTH * (1 + edid->extensions) > len)
 		ret = -EINVAL;
 	else {
 		connector->override_edid = false;
-		ret = drm_mode_connector_update_edid_property(connector, edid);
+		ret = drm_connector_update_edid_property(connector, edid);
 		if (!ret)
 			connector->override_edid = true;
 	}
diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index 9f8312137cad..99961192bf03 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -139,6 +139,7 @@ static int crtc_crc_data_count(struct drm_crtc_crc *crc)
 static void crtc_crc_cleanup(struct drm_crtc_crc *crc)
 {
 	kfree(crc->entries);
+	crc->overflow = false;
 	crc->entries = NULL;
 	crc->head = 0;
 	crc->tail = 0;
@@ -391,8 +392,14 @@ int drm_crtc_add_crc_entry(struct drm_crtc *crtc, bool has_frame,
 	tail = crc->tail;
 
 	if (CIRC_SPACE(head, tail, DRM_CRC_ENTRIES_NR) < 1) {
+		bool was_overflow = crc->overflow;
+
+		crc->overflow = true;
 		spin_unlock(&crc->lock);
-		DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n");
+
+		if (!was_overflow)
+			DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n");
+
 		return -ENOBUFS;
 	}
 
diff --git a/drivers/gpu/drm/drm_dp_cec.c b/drivers/gpu/drm/drm_dp_cec.c
new file mode 100644
index 000000000000..ddb1c5adebb9
--- /dev/null
+++ b/drivers/gpu/drm/drm_dp_cec.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DisplayPort CEC-Tunneling-over-AUX support
+ *
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <drm/drm_dp_helper.h>
+#include <media/cec.h>
+
+/*
+ * Unfortunately it turns out that we have a chicken-and-egg situation
+ * here. Quite a few active (mini-)DP-to-HDMI or USB-C-to-HDMI adapters
+ * have a converter chip that supports CEC-Tunneling-over-AUX (usually the
+ * Parade PS176), but they do not wire up the CEC pin, thus making CEC
+ * useless.
+ *
+ * Sadly there is no way for this driver to know this. What happens is
+ * that a /dev/cecX device is created that is isolated and unable to see
+ * any of the other CEC devices. Quite literally the CEC wire is cut
+ * (or in this case, never connected in the first place).
+ *
+ * The reason so few adapters support this is that this tunneling protocol
+ * was never supported by any OS. So there was no easy way of testing it,
+ * and no incentive to correctly wire up the CEC pin.
+ *
+ * Hopefully by creating this driver it will be easier for vendors to
+ * finally fix their adapters and test the CEC functionality.
+ *
+ * I keep a list of known working adapters here:
+ *
+ * https://hverkuil.home.xs4all.nl/cec-status.txt
+ *
+ * Please mail me (hverkuil@xs4all.nl) if you find an adapter that works
+ * and is not yet listed there.
+ *
+ * Note that the current implementation does not support CEC over an MST hub.
+ * As far as I can see there is no mechanism defined in the DisplayPort
+ * standard to transport CEC interrupts over an MST device. It might be
+ * possible to do this through polling, but I have not been able to get that
+ * to work.
+ */
+
+/**
+ * DOC: dp cec helpers
+ *
+ * These functions take care of supporting the CEC-Tunneling-over-AUX
+ * feature of DisplayPort-to-HDMI adapters.
+ */
+
+/*
+ * When the EDID is unset because the HPD went low, then the CEC DPCD registers
+ * typically can no longer be read (true for a DP-to-HDMI adapter since it is
+ * powered by the HPD). However, some displays toggle the HPD off and on for a
+ * short period for one reason or another, and that would cause the CEC adapter
+ * to be removed and added again, even though nothing else changed.
+ *
+ * This module parameter sets a delay in seconds before the CEC adapter is
+ * actually unregistered. Only if the HPD does not return within that time will
+ * the CEC adapter be unregistered.
+ *
+ * If it is set to a value >= NEVER_UNREG_DELAY, then the CEC adapter will never
+ * be unregistered for as long as the connector remains registered.
+ *
+ * If it is set to 0, then the CEC adapter will be unregistered immediately as
+ * soon as the HPD disappears.
+ *
+ * The default is one second to prevent short HPD glitches from unregistering
+ * the CEC adapter.
+ *
+ * Note that for integrated HDMI branch devices that support CEC the DPCD
+ * registers remain available even if the HPD goes low since it is not powered
+ * by the HPD. In that case the CEC adapter will never be unregistered during
+ * the life time of the connector. At least, this is the theory since I do not
+ * have hardware with an integrated HDMI branch device that supports CEC.
+ */
+#define NEVER_UNREG_DELAY 1000
+static unsigned int drm_dp_cec_unregister_delay = 1;
+module_param(drm_dp_cec_unregister_delay, uint, 0600);
+MODULE_PARM_DESC(drm_dp_cec_unregister_delay,
+		 "CEC unregister delay in seconds, 0: no delay, >= 1000: never unregister");
+
+static int drm_dp_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	u32 val = enable ? DP_CEC_TUNNELING_ENABLE : 0;
+	ssize_t err = 0;
+
+	err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val);
+	return (enable && err < 0) ? err : 0;
+}
+
+static int drm_dp_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	/* Bit 15 (logical address 15) should always be set */
+	u16 la_mask = 1 << CEC_LOG_ADDR_BROADCAST;
+	u8 mask[2];
+	ssize_t err;
+
+	if (addr != CEC_LOG_ADDR_INVALID)
+		la_mask |= adap->log_addrs.log_addr_mask | (1 << addr);
+	mask[0] = la_mask & 0xff;
+	mask[1] = la_mask >> 8;
+	err = drm_dp_dpcd_write(aux, DP_CEC_LOGICAL_ADDRESS_MASK, mask, 2);
+	return (addr != CEC_LOG_ADDR_INVALID && err < 0) ? err : 0;
+}
+
+static int drm_dp_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				    u32 signal_free_time, struct cec_msg *msg)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	unsigned int retries = min(5, attempts - 1);
+	ssize_t err;
+
+	err = drm_dp_dpcd_write(aux, DP_CEC_TX_MESSAGE_BUFFER,
+				msg->msg, msg->len);
+	if (err < 0)
+		return err;
+
+	err = drm_dp_dpcd_writeb(aux, DP_CEC_TX_MESSAGE_INFO,
+				 (msg->len - 1) | (retries << 4) |
+				 DP_CEC_TX_MESSAGE_SEND);
+	return err < 0 ? err : 0;
+}
+
+static int drm_dp_cec_adap_monitor_all_enable(struct cec_adapter *adap,
+					      bool enable)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	ssize_t err;
+	u8 val;
+
+	if (!(adap->capabilities & CEC_CAP_MONITOR_ALL))
+		return 0;
+
+	err = drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CONTROL, &val);
+	if (err >= 0) {
+		if (enable)
+			val |= DP_CEC_SNOOPING_ENABLE;
+		else
+			val &= ~DP_CEC_SNOOPING_ENABLE;
+		err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val);
+	}
+	return (enable && err < 0) ? err : 0;
+}
+
+static void drm_dp_cec_adap_status(struct cec_adapter *adap,
+				   struct seq_file *file)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	struct drm_dp_desc desc;
+	struct drm_dp_dpcd_ident *id = &desc.ident;
+
+	if (drm_dp_read_desc(aux, &desc, true))
+		return;
+	seq_printf(file, "OUI: %*pdH\n",
+		   (int)sizeof(id->oui), id->oui);
+	seq_printf(file, "ID: %*pE\n",
+		   (int)strnlen(id->device_id, sizeof(id->device_id)),
+		   id->device_id);
+	seq_printf(file, "HW Rev: %d.%d\n", id->hw_rev >> 4, id->hw_rev & 0xf);
+	/*
+	 * Show this both in decimal and hex: at least one vendor
+	 * always reports this in hex.
+	 */
+	seq_printf(file, "FW/SW Rev: %d.%d (0x%02x.0x%02x)\n",
+		   id->sw_major_rev, id->sw_minor_rev,
+		   id->sw_major_rev, id->sw_minor_rev);
+}
+
+static const struct cec_adap_ops drm_dp_cec_adap_ops = {
+	.adap_enable = drm_dp_cec_adap_enable,
+	.adap_log_addr = drm_dp_cec_adap_log_addr,
+	.adap_transmit = drm_dp_cec_adap_transmit,
+	.adap_monitor_all_enable = drm_dp_cec_adap_monitor_all_enable,
+	.adap_status = drm_dp_cec_adap_status,
+};
+
+static int drm_dp_cec_received(struct drm_dp_aux *aux)
+{
+	struct cec_adapter *adap = aux->cec.adap;
+	struct cec_msg msg;
+	u8 rx_msg_info;
+	ssize_t err;
+
+	err = drm_dp_dpcd_readb(aux, DP_CEC_RX_MESSAGE_INFO, &rx_msg_info);
+	if (err < 0)
+		return err;
+
+	if (!(rx_msg_info & DP_CEC_RX_MESSAGE_ENDED))
+		return 0;
+
+	msg.len = (rx_msg_info & DP_CEC_RX_MESSAGE_LEN_MASK) + 1;
+	err = drm_dp_dpcd_read(aux, DP_CEC_RX_MESSAGE_BUFFER, msg.msg, msg.len);
+	if (err < 0)
+		return err;
+
+	cec_received_msg(adap, &msg);
+	return 0;
+}
+
+static void drm_dp_cec_handle_irq(struct drm_dp_aux *aux)
+{
+	struct cec_adapter *adap = aux->cec.adap;
+	u8 flags;
+
+	if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, &flags) < 0)
+		return;
+
+	if (flags & DP_CEC_RX_MESSAGE_INFO_VALID)
+		drm_dp_cec_received(aux);
+
+	if (flags & DP_CEC_TX_MESSAGE_SENT)
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_OK);
+	else if (flags & DP_CEC_TX_LINE_ERROR)
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_ERROR |
+						CEC_TX_STATUS_MAX_RETRIES);
+	else if (flags &
+		 (DP_CEC_TX_ADDRESS_NACK_ERROR | DP_CEC_TX_DATA_NACK_ERROR))
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_NACK |
+						CEC_TX_STATUS_MAX_RETRIES);
+	drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, flags);
+}
+
+/**
+ * drm_dp_cec_irq() - handle CEC interrupt, if any
+ * @aux: DisplayPort AUX channel
+ *
+ * Should be called when handling an IRQ_HPD request. If CEC-tunneling-over-AUX
+ * is present, then it will check for a CEC_IRQ and handle it accordingly.
+ */
+void drm_dp_cec_irq(struct drm_dp_aux *aux)
+{
+	u8 cec_irq;
+	int ret;
+
+	mutex_lock(&aux->cec.lock);
+	if (!aux->cec.adap)
+		goto unlock;
+
+	ret = drm_dp_dpcd_readb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1,
+				&cec_irq);
+	if (ret < 0 || !(cec_irq & DP_CEC_IRQ))
+		goto unlock;
+
+	drm_dp_cec_handle_irq(aux);
+	drm_dp_dpcd_writeb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1, DP_CEC_IRQ);
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_irq);
+
+static bool drm_dp_cec_cap(struct drm_dp_aux *aux, u8 *cec_cap)
+{
+	u8 cap = 0;
+
+	if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CAPABILITY, &cap) != 1 ||
+	    !(cap & DP_CEC_TUNNELING_CAPABLE))
+		return false;
+	if (cec_cap)
+		*cec_cap = cap;
+	return true;
+}
+
+/*
+ * Called if the HPD was low for more than drm_dp_cec_unregister_delay
+ * seconds. This unregisters the CEC adapter.
+ */
+static void drm_dp_cec_unregister_work(struct work_struct *work)
+{
+	struct drm_dp_aux *aux = container_of(work, struct drm_dp_aux,
+					      cec.unregister_work.work);
+
+	mutex_lock(&aux->cec.lock);
+	cec_unregister_adapter(aux->cec.adap);
+	aux->cec.adap = NULL;
+	mutex_unlock(&aux->cec.lock);
+}
+
+/*
+ * A new EDID is set. If there is no CEC adapter, then create one. If
+ * there was a CEC adapter, then check if the CEC adapter properties
+ * were unchanged and just update the CEC physical address. Otherwise
+ * unregister the old CEC adapter and create a new one.
+ */
+void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
+{
+	u32 cec_caps = CEC_CAP_DEFAULTS | CEC_CAP_NEEDS_HPD;
+	unsigned int num_las = 1;
+	u8 cap;
+
+#ifndef CONFIG_MEDIA_CEC_RC
+	/*
+	 * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by
+	 * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined.
+	 *
+	 * Do this here as well to ensure the tests against cec_caps are
+	 * correct.
+	 */
+	cec_caps &= ~CEC_CAP_RC;
+#endif
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+
+	mutex_lock(&aux->cec.lock);
+	if (!drm_dp_cec_cap(aux, &cap)) {
+		/* CEC is not supported, unregister any existing adapter */
+		cec_unregister_adapter(aux->cec.adap);
+		aux->cec.adap = NULL;
+		goto unlock;
+	}
+
+	if (cap & DP_CEC_SNOOPING_CAPABLE)
+		cec_caps |= CEC_CAP_MONITOR_ALL;
+	if (cap & DP_CEC_MULTIPLE_LA_CAPABLE)
+		num_las = CEC_MAX_LOG_ADDRS;
+
+	if (aux->cec.adap) {
+		if (aux->cec.adap->capabilities == cec_caps &&
+		    aux->cec.adap->available_log_addrs == num_las) {
+			/* Unchanged, so just set the phys addr */
+			cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+			goto unlock;
+		}
+		/*
+		 * The capabilities changed, so unregister the old
+		 * adapter first.
+		 */
+		cec_unregister_adapter(aux->cec.adap);
+	}
+
+	/* Create a new adapter */
+	aux->cec.adap = cec_allocate_adapter(&drm_dp_cec_adap_ops,
+					     aux, aux->cec.name, cec_caps,
+					     num_las);
+	if (IS_ERR(aux->cec.adap)) {
+		aux->cec.adap = NULL;
+		goto unlock;
+	}
+	if (cec_register_adapter(aux->cec.adap, aux->cec.parent)) {
+		cec_delete_adapter(aux->cec.adap);
+		aux->cec.adap = NULL;
+	} else {
+		/*
+		 * Update the phys addr for the new CEC adapter. When called
+		 * from drm_dp_cec_register_connector() edid == NULL, so in
+		 * that case the phys addr is just invalidated.
+		 */
+		cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+	}
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_set_edid);
+
+/*
+ * The EDID disappeared (likely because of the HPD going down).
+ */
+void drm_dp_cec_unset_edid(struct drm_dp_aux *aux)
+{
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+
+	mutex_lock(&aux->cec.lock);
+	if (!aux->cec.adap)
+		goto unlock;
+
+	cec_phys_addr_invalidate(aux->cec.adap);
+	/*
+	 * We're done if we want to keep the CEC device
+	 * (drm_dp_cec_unregister_delay is >= NEVER_UNREG_DELAY) or if the
+	 * DPCD still indicates the CEC capability (expected for an integrated
+	 * HDMI branch device).
+	 */
+	if (drm_dp_cec_unregister_delay < NEVER_UNREG_DELAY &&
+	    !drm_dp_cec_cap(aux, NULL)) {
+		/*
+		 * Unregister the CEC adapter after drm_dp_cec_unregister_delay
+		 * seconds. This to debounce short HPD off-and-on cycles from
+		 * displays.
+		 */
+		schedule_delayed_work(&aux->cec.unregister_work,
+				      drm_dp_cec_unregister_delay * HZ);
+	}
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_unset_edid);
+
+/**
+ * drm_dp_cec_register_connector() - register a new connector
+ * @aux: DisplayPort AUX channel
+ * @name: name of the CEC device
+ * @parent: parent device
+ *
+ * A new connector was registered with associated CEC adapter name and
+ * CEC adapter parent device. After registering the name and parent
+ * drm_dp_cec_set_edid() is called to check if the connector supports
+ * CEC and to register a CEC adapter if that is the case.
+ */
+void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name,
+				   struct device *parent)
+{
+	WARN_ON(aux->cec.adap);
+	aux->cec.name = name;
+	aux->cec.parent = parent;
+	INIT_DELAYED_WORK(&aux->cec.unregister_work,
+			  drm_dp_cec_unregister_work);
+
+	drm_dp_cec_set_edid(aux, NULL);
+}
+EXPORT_SYMBOL(drm_dp_cec_register_connector);
+
+/**
+ * drm_dp_cec_unregister_connector() - unregister the CEC adapter, if any
+ * @aux: DisplayPort AUX channel
+ */
+void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux)
+{
+	if (!aux->cec.adap)
+		return;
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+	cec_unregister_adapter(aux->cec.adap);
+	aux->cec.adap = NULL;
+}
+EXPORT_SYMBOL(drm_dp_cec_unregister_connector);
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index a7ba602a43a8..0cccbcb2d03e 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -185,6 +185,20 @@ EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate);
 
 #define AUX_RETRY_INTERVAL 500 /* us */
 
+static inline void
+drm_dp_dump_access(const struct drm_dp_aux *aux,
+		   u8 request, uint offset, void *buffer, int ret)
+{
+	const char *arrow = request == DP_AUX_NATIVE_READ ? "->" : "<-";
+
+	if (ret > 0)
+		drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d) %*ph\n",
+			aux->name, offset, arrow, ret, min(ret, 20), buffer);
+	else
+		drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d)\n",
+			aux->name, offset, arrow, ret);
+}
+
 /**
  * DOC: dp helpers
  *
@@ -288,10 +302,14 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, buffer,
 				 1);
 	if (ret != 1)
-		return ret;
+		goto out;
 
-	return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
-				  size);
+	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);
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_dpcd_read);
 
@@ -312,8 +330,12 @@ EXPORT_SYMBOL(drm_dp_dpcd_read);
 ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset,
 			  void *buffer, size_t size)
 {
-	return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
-				  size);
+	int ret;
+
+	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;
 }
 EXPORT_SYMBOL(drm_dp_dpcd_write);
 
@@ -1087,6 +1109,7 @@ static void drm_dp_aux_crc_work(struct work_struct *work)
 void drm_dp_aux_init(struct drm_dp_aux *aux)
 {
 	mutex_init(&aux->hw_mutex);
+	mutex_init(&aux->cec.lock);
 	INIT_WORK(&aux->crc_work, drm_dp_aux_crc_work);
 
 	aux->ddc.algo = &drm_dp_i2c_algo;
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 658830620ca3..7780567aa669 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1215,7 +1215,7 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 		     port->pdt == DP_PEER_DEVICE_SST_SINK) &&
 		    port->port_num >= DP_MST_LOGICAL_PORT_0) {
 			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
-			drm_mode_connector_set_tile_property(port->connector);
+			drm_connector_set_tile_property(port->connector);
 		}
 		(*mstb->mgr->cbs->register_connector)(port->connector);
 	}
@@ -2559,7 +2559,7 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 		edid = drm_edid_duplicate(port->cached_edid);
 	else {
 		edid = drm_get_edid(connector, &port->aux.ddc);
-		drm_mode_connector_set_tile_property(connector);
+		drm_connector_set_tile_property(connector);
 	}
 	port->has_audio = drm_detect_monitor_audio(edid);
 	drm_dp_put_port(port);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 7af748ed1c58..ea4941da9b27 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/srcu.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_drv.h>
 #include <drm/drmP.h>
 
@@ -53,13 +54,14 @@ MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl");
 MODULE_DESCRIPTION("DRM shared core routines");
 MODULE_LICENSE("GPL and additional rights");
 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"
-"\t\tBit 1 (0x02) will enable DRIVER messages (drm controller code)\n"
-"\t\tBit 2 (0x04) will enable KMS messages (modesetting code)\n"
-"\t\tBit 3 (0x08) will enable PRIME messages (prime code)\n"
-"\t\tBit 4 (0x10) will enable ATOMIC messages (atomic code)\n"
-"\t\tBit 5 (0x20) will enable VBL messages (vblank code)\n"
-"\t\tBit 7 (0x80) will enable LEASE messages (leasing code)");
+"\t\tBit 0 (0x01)  will enable CORE messages (drm core code)\n"
+"\t\tBit 1 (0x02)  will enable DRIVER messages (drm controller code)\n"
+"\t\tBit 2 (0x04)  will enable KMS messages (modesetting code)\n"
+"\t\tBit 3 (0x08)  will enable PRIME messages (prime code)\n"
+"\t\tBit 4 (0x10)  will enable ATOMIC messages (atomic code)\n"
+"\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);
 
 static DEFINE_SPINLOCK(drm_minor_lock);
@@ -505,6 +507,8 @@ int drm_dev_init(struct drm_device *dev,
 	dev->driver = driver;
 
 	INIT_LIST_HEAD(&dev->filelist);
+	INIT_LIST_HEAD(&dev->filelist_internal);
+	INIT_LIST_HEAD(&dev->clientlist);
 	INIT_LIST_HEAD(&dev->ctxlist);
 	INIT_LIST_HEAD(&dev->vmalist);
 	INIT_LIST_HEAD(&dev->maplist);
@@ -514,6 +518,7 @@ int drm_dev_init(struct drm_device *dev,
 	spin_lock_init(&dev->event_lock);
 	mutex_init(&dev->struct_mutex);
 	mutex_init(&dev->filelist_mutex);
+	mutex_init(&dev->clientlist_mutex);
 	mutex_init(&dev->ctxlist_mutex);
 	mutex_init(&dev->master_mutex);
 
@@ -569,6 +574,7 @@ err_minors:
 err_free:
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
+	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
 	mutex_destroy(&dev->struct_mutex);
 	return ret;
@@ -603,6 +609,7 @@ void drm_dev_fini(struct drm_device *dev)
 
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
+	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
 	mutex_destroy(&dev->struct_mutex);
 	kfree(dev->unique);
@@ -858,6 +865,8 @@ void drm_dev_unregister(struct drm_device *dev)
 
 	dev->registered = false;
 
+	drm_client_dev_unregister(dev);
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_modeset_unregister_all(dev);
 
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 186d00adfb5f..9da36a6271d3 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -18,6 +18,7 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_client.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -26,11 +27,8 @@
 #include <drm/drm_print.h>
 #include <linux/module.h>
 
-#define DEFAULT_FBDEFIO_DELAY_MS 50
-
 struct drm_fbdev_cma {
 	struct drm_fb_helper	fb_helper;
-	const struct drm_framebuffer_funcs *fb_funcs;
 };
 
 /**
@@ -44,36 +42,6 @@ struct drm_fbdev_cma {
  *
  * An fbdev framebuffer backed by cma is also available by calling
  * drm_fb_cma_fbdev_init(). drm_fb_cma_fbdev_fini() tears it down.
- * If the &drm_framebuffer_funcs.dirty callback is set, fb_deferred_io will be
- * set up automatically. &drm_framebuffer_funcs.dirty is called by
- * drm_fb_helper_deferred_io() in process context (&struct delayed_work).
- *
- * Example fbdev deferred io code::
- *
- *     static int driver_fb_dirty(struct drm_framebuffer *fb,
- *                                struct drm_file *file_priv,
- *                                unsigned flags, unsigned color,
- *                                struct drm_clip_rect *clips,
- *                                unsigned num_clips)
- *     {
- *         struct drm_gem_cma_object *cma = drm_fb_cma_get_gem_obj(fb, 0);
- *         ... push changes ...
- *         return 0;
- *     }
- *
- *     static struct drm_framebuffer_funcs driver_fb_funcs = {
- *         .destroy       = drm_gem_fb_destroy,
- *         .create_handle = drm_gem_fb_create_handle,
- *         .dirty         = driver_fb_dirty,
- *     };
- *
- * Initialize::
- *
- *     fbdev = drm_fb_cma_fbdev_init_with_funcs(dev, 16,
- *                                           dev->mode_config.num_crtc,
- *                                           dev->mode_config.num_connector,
- *                                           &driver_fb_funcs);
- *
  */
 
 static inline struct drm_fbdev_cma *to_fbdev_cma(struct drm_fb_helper *helper)
@@ -131,236 +99,28 @@ dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb,
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr);
 
-static int drm_fb_cma_mmap(struct fb_info *info, struct vm_area_struct *vma)
-{
-	return dma_mmap_writecombine(info->device, vma, info->screen_base,
-				     info->fix.smem_start, info->fix.smem_len);
-}
-
-static struct fb_ops drm_fbdev_cma_ops = {
-	.owner		= THIS_MODULE,
-	DRM_FB_HELPER_DEFAULT_OPS,
-	.fb_fillrect	= drm_fb_helper_sys_fillrect,
-	.fb_copyarea	= drm_fb_helper_sys_copyarea,
-	.fb_imageblit	= drm_fb_helper_sys_imageblit,
-	.fb_mmap	= drm_fb_cma_mmap,
-};
-
-static int drm_fbdev_cma_deferred_io_mmap(struct fb_info *info,
-					  struct vm_area_struct *vma)
-{
-	fb_deferred_io_mmap(info, vma);
-	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
-	return 0;
-}
-
-static int drm_fbdev_cma_defio_init(struct fb_info *fbi,
-				    struct drm_gem_cma_object *cma_obj)
-{
-	struct fb_deferred_io *fbdefio;
-	struct fb_ops *fbops;
-
-	/*
-	 * Per device structures are needed because:
-	 * fbops: fb_deferred_io_cleanup() clears fbops.fb_mmap
-	 * fbdefio: individual delays
-	 */
-	fbdefio = kzalloc(sizeof(*fbdefio), GFP_KERNEL);
-	fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
-	if (!fbdefio || !fbops) {
-		kfree(fbdefio);
-		kfree(fbops);
-		return -ENOMEM;
-	}
-
-	/* can't be offset from vaddr since dirty() uses cma_obj */
-	fbi->screen_buffer = cma_obj->vaddr;
-	/* fb_deferred_io_fault() needs a physical address */
-	fbi->fix.smem_start = page_to_phys(virt_to_page(fbi->screen_buffer));
-
-	*fbops = *fbi->fbops;
-	fbi->fbops = fbops;
-
-	fbdefio->delay = msecs_to_jiffies(DEFAULT_FBDEFIO_DELAY_MS);
-	fbdefio->deferred_io = drm_fb_helper_deferred_io;
-	fbi->fbdefio = fbdefio;
-	fb_deferred_io_init(fbi);
-	fbi->fbops->fb_mmap = drm_fbdev_cma_deferred_io_mmap;
-
-	return 0;
-}
-
-static void drm_fbdev_cma_defio_fini(struct fb_info *fbi)
-{
-	if (!fbi->fbdefio)
-		return;
-
-	fb_deferred_io_cleanup(fbi);
-	kfree(fbi->fbdefio);
-	kfree(fbi->fbops);
-}
-
-static int
-drm_fbdev_cma_create(struct drm_fb_helper *helper,
-	struct drm_fb_helper_surface_size *sizes)
-{
-	struct drm_fbdev_cma *fbdev_cma = to_fbdev_cma(helper);
-	struct drm_device *dev = helper->dev;
-	struct drm_gem_cma_object *obj;
-	struct drm_framebuffer *fb;
-	unsigned int bytes_per_pixel;
-	unsigned long offset;
-	struct fb_info *fbi;
-	size_t size;
-	int ret;
-
-	DRM_DEBUG_KMS("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);
-	size = sizes->surface_width * sizes->surface_height * bytes_per_pixel;
-	obj = drm_gem_cma_create(dev, size);
-	if (IS_ERR(obj))
-		return -ENOMEM;
-
-	fbi = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(fbi)) {
-		ret = PTR_ERR(fbi);
-		goto err_gem_free_object;
-	}
-
-	fb = drm_gem_fbdev_fb_create(dev, sizes, 0, &obj->base,
-				     fbdev_cma->fb_funcs);
-	if (IS_ERR(fb)) {
-		dev_err(dev->dev, "Failed to allocate DRM framebuffer.\n");
-		ret = PTR_ERR(fb);
-		goto err_fb_info_destroy;
-	}
-
-	helper->fb = fb;
-
-	fbi->par = helper;
-	fbi->flags = FBINFO_FLAG_DEFAULT;
-	fbi->fbops = &drm_fbdev_cma_ops;
-
-	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth);
-	drm_fb_helper_fill_var(fbi, helper, sizes->fb_width, sizes->fb_height);
-
-	offset = fbi->var.xoffset * bytes_per_pixel;
-	offset += fbi->var.yoffset * fb->pitches[0];
-
-	dev->mode_config.fb_base = (resource_size_t)obj->paddr;
-	fbi->screen_base = obj->vaddr + offset;
-	fbi->fix.smem_start = (unsigned long)(obj->paddr + offset);
-	fbi->screen_size = size;
-	fbi->fix.smem_len = size;
-
-	if (fb->funcs->dirty) {
-		ret = drm_fbdev_cma_defio_init(fbi, obj);
-		if (ret)
-			goto err_cma_destroy;
-	}
-
-	return 0;
-
-err_cma_destroy:
-	drm_framebuffer_remove(fb);
-err_fb_info_destroy:
-	drm_fb_helper_fini(helper);
-err_gem_free_object:
-	drm_gem_object_put_unlocked(&obj->base);
-	return ret;
-}
-
-static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = {
-	.fb_probe = drm_fbdev_cma_create,
-};
-
 /**
- * drm_fb_cma_fbdev_init_with_funcs() - Allocate and initialize fbdev emulation
+ * drm_fb_cma_fbdev_init() - Allocate and initialize fbdev emulation
  * @dev: DRM device
  * @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.
  *                  @dev->mode_config.num_connector is used if this is zero.
- * @funcs: Framebuffer functions, in particular a custom dirty() callback.
- *         Can be NULL.
  *
  * Returns:
  * Zero on success or negative error code on failure.
  */
-int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs)
+int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
+			  unsigned int max_conn_count)
 {
 	struct drm_fbdev_cma *fbdev_cma;
-	struct drm_fb_helper *fb_helper;
-	int ret;
-
-	if (!preferred_bpp)
-		preferred_bpp = dev->mode_config.preferred_depth;
-	if (!preferred_bpp)
-		preferred_bpp = 32;
-
-	if (!max_conn_count)
-		max_conn_count = dev->mode_config.num_connector;
-
-	fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL);
-	if (!fbdev_cma)
-		return -ENOMEM;
 
-	fbdev_cma->fb_funcs = funcs;
-	fb_helper = &fbdev_cma->fb_helper;
-
-	drm_fb_helper_prepare(dev, fb_helper, &drm_fb_cma_helper_funcs);
-
-	ret = drm_fb_helper_init(dev, fb_helper, max_conn_count);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to initialize fbdev helper.\n");
-		goto err_free;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(fb_helper);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to add connectors.\n");
-		goto err_drm_fb_helper_fini;
-	}
-
-	ret = drm_fb_helper_initial_config(fb_helper, preferred_bpp);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to set fbdev configuration.\n");
-		goto err_drm_fb_helper_fini;
-	}
+	/* dev->fb_helper will indirectly point to fbdev_cma after this call */
+	fbdev_cma = drm_fbdev_cma_init(dev, preferred_bpp, max_conn_count);
+	if (IS_ERR(fbdev_cma))
+		return PTR_ERR(fbdev_cma);
 
 	return 0;
-
-err_drm_fb_helper_fini:
-	drm_fb_helper_fini(fb_helper);
-err_free:
-	kfree(fbdev_cma);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs);
-
-/**
- * drm_fb_cma_fbdev_init() - Allocate and initialize fbdev emulation
- * @dev: DRM device
- * @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.
- *                  @dev->mode_config.num_connector is used if this is zero.
- *
- * Returns:
- * Zero on success or negative error code on failure.
- */
-int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
-			  unsigned int max_conn_count)
-{
-	return drm_fb_cma_fbdev_init_with_funcs(dev, preferred_bpp,
-						max_conn_count, NULL);
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init);
 
@@ -370,104 +130,54 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init);
  */
 void drm_fb_cma_fbdev_fini(struct drm_device *dev)
 {
-	struct drm_fb_helper *fb_helper = dev->fb_helper;
-
-	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)
-		drm_fbdev_cma_defio_fini(fb_helper->fbdev);
-
-	if (fb_helper->fb)
-		drm_framebuffer_remove(fb_helper->fb);
-
-	drm_fb_helper_fini(fb_helper);
-	kfree(to_fbdev_cma(fb_helper));
+	if (dev->fb_helper)
+		drm_fbdev_cma_fini(to_fbdev_cma(dev->fb_helper));
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_fini);
 
+static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = {
+	.fb_probe = drm_fb_helper_generic_probe,
+};
+
 /**
- * drm_fbdev_cma_init_with_funcs() - Allocate and initializes a drm_fbdev_cma struct
+ * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct
  * @dev: DRM device
  * @preferred_bpp: Preferred bits per pixel for the device
  * @max_conn_count: Maximum number of connectors
- * @funcs: fb helper functions, in particular a custom dirty() callback
  *
  * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR.
  */
-struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs)
+struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
+	unsigned int preferred_bpp, unsigned int max_conn_count)
 {
 	struct drm_fbdev_cma *fbdev_cma;
-	struct drm_fb_helper *helper;
+	struct drm_fb_helper *fb_helper;
 	int ret;
 
 	fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL);
-	if (!fbdev_cma) {
-		dev_err(dev->dev, "Failed to allocate drm fbdev.\n");
+	if (!fbdev_cma)
 		return ERR_PTR(-ENOMEM);
-	}
-	fbdev_cma->fb_funcs = funcs;
 
-	helper = &fbdev_cma->fb_helper;
-
-	drm_fb_helper_prepare(dev, helper, &drm_fb_cma_helper_funcs);
+	fb_helper = &fbdev_cma->fb_helper;
 
-	ret = drm_fb_helper_init(dev, helper, max_conn_count);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to initialize drm fb helper.\n");
+	ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL);
+	if (ret)
 		goto err_free;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(helper);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to add connectors.\n");
-		goto err_drm_fb_helper_fini;
-
-	}
 
-	ret = drm_fb_helper_initial_config(helper, preferred_bpp);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to set initial hw configuration.\n");
-		goto err_drm_fb_helper_fini;
-	}
+	ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_cma_helper_funcs,
+					preferred_bpp, max_conn_count);
+	if (ret)
+		goto err_client_put;
 
 	return fbdev_cma;
 
-err_drm_fb_helper_fini:
-	drm_fb_helper_fini(helper);
+err_client_put:
+	drm_client_release(&fb_helper->client);
 err_free:
 	kfree(fbdev_cma);
 
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(drm_fbdev_cma_init_with_funcs);
-
-static const struct drm_framebuffer_funcs drm_fb_cma_funcs = {
-	.destroy	= drm_gem_fb_destroy,
-	.create_handle	= drm_gem_fb_create_handle,
-};
-
-/**
- * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct
- * @dev: DRM device
- * @preferred_bpp: Preferred bits per pixel for the device
- * @max_conn_count: Maximum number of connectors
- *
- * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR.
- */
-struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count)
-{
-	return drm_fbdev_cma_init_with_funcs(dev, preferred_bpp,
-					     max_conn_count,
-					     &drm_fb_cma_funcs);
-}
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_init);
 
 /**
@@ -477,14 +187,7 @@ EXPORT_SYMBOL_GPL(drm_fbdev_cma_init);
 void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma)
 {
 	drm_fb_helper_unregister_fbi(&fbdev_cma->fb_helper);
-	if (fbdev_cma->fb_helper.fbdev)
-		drm_fbdev_cma_defio_fini(fbdev_cma->fb_helper.fbdev);
-
-	if (fbdev_cma->fb_helper.fb)
-		drm_framebuffer_remove(fbdev_cma->fb_helper.fb);
-
-	drm_fb_helper_fini(&fbdev_cma->fb_helper);
-	kfree(fbdev_cma);
+	/* All resources have now been freed by drm_fbdev_fb_destroy() */
 }
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_fini);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index cab14f253384..4b0dd20bccb8 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -30,6 +30,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/console.h>
+#include <linux/dma-buf.h>
 #include <linux/kernel.h>
 #include <linux/sysrq.h>
 #include <linux/slab.h>
@@ -66,6 +67,9 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  * helper functions used by many drivers to implement the kernel mode setting
  * interfaces.
  *
+ * Drivers that support a dumb buffer with a virtual address and mmap support,
+ * should try out the generic fbdev emulation using drm_fbdev_generic_setup().
+ *
  * Setup fbdev emulation by calling drm_fb_helper_fbdev_setup() and tear it
  * down by calling drm_fb_helper_fbdev_teardown().
  *
@@ -738,6 +742,24 @@ static void drm_fb_helper_resume_worker(struct work_struct *work)
 	console_unlock();
 }
 
+static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper,
+					  struct drm_clip_rect *clip)
+{
+	struct drm_framebuffer *fb = fb_helper->fb;
+	unsigned int cpp = drm_format_plane_cpp(fb->format->format, 0);
+	size_t offset = clip->y1 * fb->pitches[0] + clip->x1 * cpp;
+	void *src = fb_helper->fbdev->screen_buffer + offset;
+	void *dst = fb_helper->buffer->vaddr + offset;
+	size_t len = (clip->x2 - clip->x1) * cpp;
+	unsigned int y;
+
+	for (y = clip->y1; y < clip->y2; y++) {
+		memcpy(dst, src, len);
+		src += fb->pitches[0];
+		dst += fb->pitches[0];
+	}
+}
+
 static void drm_fb_helper_dirty_work(struct work_struct *work)
 {
 	struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper,
@@ -753,8 +775,12 @@ static void drm_fb_helper_dirty_work(struct work_struct *work)
 	spin_unlock_irqrestore(&helper->dirty_lock, flags);
 
 	/* call dirty callback only when it has been really touched */
-	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2)
+	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) {
+		/* Generic fbdev uses a shadow buffer */
+		if (helper->buffer)
+			drm_fb_helper_dirty_blit_real(helper, &clip_copy);
 		helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
+	}
 }
 
 /**
@@ -2323,6 +2349,20 @@ retry:
 	return true;
 }
 
+static bool connector_has_possible_crtc(struct drm_connector *connector,
+					struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	int i;
+
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
+		if (encoder->possible_crtcs & drm_crtc_mask(crtc))
+			return true;
+	}
+
+	return false;
+}
+
 static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			  struct drm_fb_helper_crtc **best_crtcs,
 			  struct drm_display_mode **modes,
@@ -2331,7 +2371,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	int c, o;
 	struct drm_connector *connector;
 	const struct drm_connector_helper_funcs *connector_funcs;
-	struct drm_encoder *encoder;
 	int my_score, best_score, score;
 	struct drm_fb_helper_crtc **crtcs, *crtc;
 	struct drm_fb_helper_connector *fb_helper_conn;
@@ -2363,27 +2402,14 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	connector_funcs = connector->helper_private;
 
 	/*
-	 * If the DRM device implements atomic hooks and ->best_encoder() is
-	 * NULL we fallback to the default drm_atomic_helper_best_encoder()
-	 * helper.
-	 */
-	if (drm_drv_uses_atomic_modeset(fb_helper->dev) &&
-	    !connector_funcs->best_encoder)
-		encoder = drm_atomic_helper_best_encoder(connector);
-	else
-		encoder = connector_funcs->best_encoder(connector);
-
-	if (!encoder)
-		goto out;
-
-	/*
 	 * select a crtc for this connector and then attempt to configure
 	 * remaining connectors
 	 */
 	for (c = 0; c < fb_helper->crtc_count; c++) {
 		crtc = &fb_helper->crtc_info[c];
 
-		if ((encoder->possible_crtcs & (1 << c)) == 0)
+		if (!connector_has_possible_crtc(connector,
+						 crtc->mode_set.crtc))
 			continue;
 
 		for (o = 0; o < n; o++)
@@ -2410,7 +2436,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			       sizeof(struct drm_fb_helper_crtc *));
 		}
 	}
-out:
+
 	kfree(crtcs);
 	return best_score;
 }
@@ -2921,6 +2947,294 @@ void drm_fb_helper_output_poll_changed(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_fb_helper_output_poll_changed);
 
+/* @user: 1=userspace, 0=fbcon */
+static int drm_fbdev_fb_open(struct fb_info *info, int user)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	if (!try_module_get(fb_helper->dev->driver->fops->owner))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int drm_fbdev_fb_release(struct fb_info *info, int user)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	module_put(fb_helper->dev->driver->fops->owner);
+
+	return 0;
+}
+
+/*
+ * fb_ops.fb_destroy is called by the last put_fb_info() call at the end of
+ * unregister_framebuffer() or fb_release().
+ */
+static void drm_fbdev_fb_destroy(struct fb_info *info)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+	struct fb_info *fbi = fb_helper->fbdev;
+	struct fb_ops *fbops = NULL;
+	void *shadow = NULL;
+
+	if (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);
+	}
+
+	drm_client_framebuffer_delete(fb_helper->buffer);
+	/*
+	 * FIXME:
+	 * Remove conditional when all CMA drivers have been moved over to using
+	 * drm_fbdev_generic_setup().
+	 */
+	if (fb_helper->client.funcs) {
+		drm_client_release(&fb_helper->client);
+		kfree(fb_helper);
+	}
+}
+
+static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	if (fb_helper->dev->driver->gem_prime_mmap)
+		return fb_helper->dev->driver->gem_prime_mmap(fb_helper->buffer->gem, vma);
+	else
+		return -ENODEV;
+}
+
+static struct fb_ops drm_fbdev_fb_ops = {
+	.owner		= THIS_MODULE,
+	DRM_FB_HELPER_DEFAULT_OPS,
+	.fb_open	= drm_fbdev_fb_open,
+	.fb_release	= drm_fbdev_fb_release,
+	.fb_destroy	= drm_fbdev_fb_destroy,
+	.fb_mmap	= drm_fbdev_fb_mmap,
+	.fb_read	= drm_fb_helper_sys_read,
+	.fb_write	= drm_fb_helper_sys_write,
+	.fb_fillrect	= drm_fb_helper_sys_fillrect,
+	.fb_copyarea	= drm_fb_helper_sys_copyarea,
+	.fb_imageblit	= drm_fb_helper_sys_imageblit,
+};
+
+static struct fb_deferred_io drm_fbdev_defio = {
+	.delay		= HZ / 20,
+	.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 crate 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)
+{
+	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_client_buffer *buffer;
+	struct drm_framebuffer *fb;
+	struct fb_info *fbi;
+	u32 format;
+	int ret;
+
+	DRM_DEBUG_KMS("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,
+					       sizes->surface_height, format);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
+
+	fb_helper->buffer = buffer;
+	fb_helper->fb = buffer->fb;
+	fb = buffer->fb;
+
+	fbi = drm_fb_helper_alloc_fbi(fb_helper);
+	if (IS_ERR(fbi)) {
+		ret = PTR_ERR(fbi);
+		goto err_free_buffer;
+	}
+
+	fbi->par = fb_helper;
+	fbi->fbops = &drm_fbdev_fb_ops;
+	fbi->screen_size = fb->height * fb->pitches[0];
+	fbi->fix.smem_len = fbi->screen_size;
+	fbi->screen_buffer = buffer->vaddr;
+	strcpy(fbi->fix.id, "DRM emulated");
+
+	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth);
+	drm_fb_helper_fill_var(fbi, fb_helper, sizes->fb_width, sizes->fb_height);
+
+	if (fb->funcs->dirty) {
+		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);
+			ret = -ENOMEM;
+			goto err_fb_info_destroy;
+		}
+
+		*fbops = *fbi->fbops;
+		fbi->fbops = fbops;
+		fbi->screen_buffer = shadow;
+		fbi->fbdefio = &drm_fbdev_defio;
+
+		fb_deferred_io_init(fbi);
+	}
+
+	return 0;
+
+err_fb_info_destroy:
+	drm_fb_helper_fini(fb_helper);
+err_free_buffer:
+	drm_client_framebuffer_delete(buffer);
+
+	return ret;
+}
+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,
+};
+
+static void drm_fbdev_client_unregister(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	if (fb_helper->fbdev) {
+		drm_fb_helper_unregister_fbi(fb_helper);
+		/* drm_fbdev_fb_destroy() takes care of cleanup */
+		return;
+	}
+
+	/* Did drm_fb_helper_fbdev_setup() run? */
+	if (fb_helper->dev)
+		drm_fb_helper_fini(fb_helper);
+
+	drm_client_release(client);
+	kfree(fb_helper);
+}
+
+static int drm_fbdev_client_restore(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
+
+	return 0;
+}
+
+static int drm_fbdev_client_hotplug(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+	struct drm_device *dev = client->dev;
+	int ret;
+
+	/* If drm_fb_helper_fbdev_setup() failed, we only try once */
+	if (!fb_helper->dev && fb_helper->funcs)
+		return 0;
+
+	if (dev->fb_helper)
+		return drm_fb_helper_hotplug_event(dev->fb_helper);
+
+	if (!dev->mode_config.num_connector)
+		return 0;
+
+	ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_helper_generic_funcs,
+					fb_helper->preferred_bpp, 0);
+	if (ret) {
+		fb_helper->dev = NULL;
+		fb_helper->fbdev = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct drm_client_funcs drm_fbdev_client_funcs = {
+	.owner		= THIS_MODULE,
+	.unregister	= drm_fbdev_client_unregister,
+	.restore	= drm_fbdev_client_restore,
+	.hotplug	= drm_fbdev_client_hotplug,
+};
+
+/**
+ * drm_fb_helper_generic_fbdev_setup() - Setup generic fbdev emulation
+ * @dev: DRM device
+ * @preferred_bpp: Preferred bits per pixel for the device.
+ *                 @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.
+ *
+ * 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.
+ * Simple drivers might use drm_mode_config_helper_suspend().
+ *
+ * Drivers that set the dirty callback on their framebuffer will get a shadow
+ * fbdev buffer that is blitted onto the real buffer. This is done in order to
+ * make deferred I/O work with all kinds of buffers.
+ *
+ * This function is safe to call even when there are no connectors present.
+ * Setup will be retried on the next hotplug event.
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
+{
+	struct drm_fb_helper *fb_helper;
+	int ret;
+
+	if (!drm_fbdev_emulation)
+		return 0;
+
+	fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL);
+	if (!fb_helper)
+		return -ENOMEM;
+
+	ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
+	if (ret) {
+		kfree(fb_helper);
+		return ret;
+	}
+
+	fb_helper->preferred_bpp = preferred_bpp;
+
+	drm_fbdev_client_hotplug(&fb_helper->client);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_fbdev_generic_setup);
+
 /* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT)
  * but the module doesn't depend on any fb console symbols.  At least
  * attempt to load fbcon to avoid leaving the system without a usable console.
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 66bb403dc8ab..ffa8dc35515f 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_file.h>
 #include <drm/drmP.h>
 
@@ -444,6 +445,8 @@ void drm_lastclose(struct drm_device * dev)
 
 	if (drm_core_check_feature(dev, DRIVER_LEGACY))
 		drm_legacy_dev_reinit(dev);
+
+	drm_client_dev_restore(dev);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 5ca6395cd4d3..35c1e2742c27 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -152,27 +152,27 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_XBGR8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_RGBX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_BGRX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
-		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
-		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
-		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUV420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_YVU420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_YUV422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUV444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV12,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_NV21,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_NV16,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV61,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV24,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV42,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUYV,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV12,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV21,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV16,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV61,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV24,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV42,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUYV,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true, .is_yuv = true },
 	};
 
 	unsigned int i;
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 4a16d7b26c89..bf90625df3c5 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1036,6 +1036,15 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return -EACCES;
 	}
 
+	if (node->readonly) {
+		if (vma->vm_flags & VM_WRITE) {
+			drm_gem_object_put_unlocked(obj);
+			return -EINVAL;
+		}
+
+		vma->vm_flags &= ~VM_MAYWRITE;
+	}
+
 	ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT,
 			       vma);
 
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 3c125041a597..ea10e9a26aad 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -641,7 +641,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb_ioctl, DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index 50c73c0a20b9..d638c0fb3418 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -553,24 +553,13 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	path_get(&lessor_file->f_path);
-	lessee_file = alloc_file(&lessor_file->f_path,
-				 lessor_file->f_mode,
-				 fops_get(lessor_file->f_inode->i_fop));
-
+	lessee_file = filp_clone_open(lessor_file);
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;
 	}
 
-	/* Initialize the new file for DRM */
-	DRM_DEBUG_LEASE("Initializing the file with %p\n", lessee_file->f_op->open);
-	ret = lessee_file->f_op->open(lessee_file->f_inode, lessee_file);
-	if (ret)
-		goto out_lessee_file;
-
 	lessee_priv = lessee_file->private_data;
-
 	/* Change the file to a master one */
 	drm_master_put(&lessee_priv->master);
 	lessee_priv->master = lessee;
@@ -588,9 +577,6 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 	DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
 	return 0;
 
-out_lessee_file:
-	fput(lessee_file);
-
 out_lessee:
 	drm_master_put(&lessee);
 
diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index bc73b7f5b9fc..80b75501f5c6 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -392,6 +392,7 @@ 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_SET_MAXIMUM_RETURN_PACKET_SIZE:
 		return true;
 	}
@@ -410,6 +411,7 @@ 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:
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index ce4d2fb32810..fcb0ab0abb75 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -433,8 +433,7 @@ static int set_property_legacy(struct drm_mode_object *obj,
 	drm_modeset_lock_all(dev);
 	switch (obj->type) {
 	case DRM_MODE_OBJECT_CONNECTOR:
-		ret = drm_mode_connector_set_obj_prop(obj, prop,
-						      prop_value);
+		ret = drm_connector_set_obj_prop(obj, prop, prop_value);
 		break;
 	case DRM_MODE_OBJECT_CRTC:
 		ret = drm_mode_crtc_set_obj_prop(obj, prop, prop_value);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 7f552d5fa88e..02db9ac82d7a 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -659,10 +659,12 @@ EXPORT_SYMBOL_GPL(drm_display_mode_to_videomode);
  * drm_bus_flags_from_videomode - extract information about pixelclk and
  * DE polarity from videomode and store it in a separate variable
  * @vm: videomode structure to use
- * @bus_flags: information about pixelclk and DE polarity will be stored here
+ * @bus_flags: information about pixelclk, sync and DE polarity will be stored
+ * here
  *
- * Sets DRM_BUS_FLAG_DE_(LOW|HIGH) and DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE
- * in @bus_flags according to DISPLAY_FLAGS found in @vm
+ * Sets DRM_BUS_FLAG_DE_(LOW|HIGH),  DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE and
+ * DISPLAY_FLAGS_SYNC_(POS|NEG)EDGE in @bus_flags according to DISPLAY_FLAGS
+ * found in @vm
  */
 void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags)
 {
@@ -672,6 +674,11 @@ void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags)
 	if (vm->flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE)
 		*bus_flags |= DRM_BUS_FLAG_PIXDATA_NEGEDGE;
 
+	if (vm->flags & DISPLAY_FLAGS_SYNC_POSEDGE)
+		*bus_flags |= DRM_BUS_FLAG_SYNC_POSEDGE;
+	if (vm->flags & DISPLAY_FLAGS_SYNC_NEGEDGE)
+		*bus_flags |= DRM_BUS_FLAG_SYNC_NEGEDGE;
+
 	if (vm->flags & DISPLAY_FLAGS_DE_LOW)
 		*bus_flags |= DRM_BUS_FLAG_DE_LOW;
 	if (vm->flags & DISPLAY_FLAGS_DE_HIGH)
@@ -684,7 +691,7 @@ EXPORT_SYMBOL_GPL(drm_bus_flags_from_videomode);
  * of_get_drm_display_mode - get a drm_display_mode from devicetree
  * @np: device_node with the timing specification
  * @dmode: will be set to the return value
- * @bus_flags: information about pixelclk and DE polarity
+ * @bus_flags: information about pixelclk, sync and DE polarity
  * @index: index into the list of display timings in devicetree
  *
  * This function is expensive and should only be used, if only one mode is to be
@@ -1346,7 +1353,7 @@ void drm_mode_sort(struct list_head *mode_list)
 EXPORT_SYMBOL(drm_mode_sort);
 
 /**
- * drm_mode_connector_list_update - update the mode list for the connector
+ * drm_connector_list_update - update the mode list for the connector
  * @connector: the connector to update
  *
  * This moves the modes from the @connector probed_modes list
@@ -1356,7 +1363,7 @@ EXPORT_SYMBOL(drm_mode_sort);
  * This is just a helper functions doesn't validate any modes itself and also
  * doesn't prune any invalid modes. Callers need to do that themselves.
  */
-void drm_mode_connector_list_update(struct drm_connector *connector)
+void drm_connector_list_update(struct drm_connector *connector)
 {
 	struct drm_display_mode *pmode, *pt;
 
@@ -1405,7 +1412,7 @@ void drm_mode_connector_list_update(struct drm_connector *connector)
 		}
 	}
 }
-EXPORT_SYMBOL(drm_mode_connector_list_update);
+EXPORT_SYMBOL(drm_connector_list_update);
 
 /**
  * drm_mode_parse_command_line_for_connector - parse command line modeline for connector
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 3b8c7a6a5720..2763a5ec845b 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -9,6 +9,13 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_of.h>
 
+/**
+ * DOC: overview
+ *
+ * A set of helper functions to aid DRM drivers in parsing standard DT
+ * properties.
+ */
+
 static void drm_release_of(struct device *dev, void *data)
 {
 	of_node_put(data);
@@ -94,7 +101,7 @@ EXPORT_SYMBOL_GPL(drm_of_component_match_add);
  * drm_of_component_probe - Generic probe function for a component based master
  * @dev: master device containing the OF node
  * @compare_of: compare function used for matching components
- * @master_ops: component master ops to be used
+ * @m_ops: component master ops to be used
  *
  * Parse the platform device OF node and bind all the components associated
  * with the master. Interface ports are added before the encoders in order to
@@ -239,10 +246,17 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 	if (!remote)
 		return -ENODEV;
 
+	if (!of_device_is_available(remote)) {
+		of_node_put(remote);
+		return -ENODEV;
+	}
+
 	if (panel) {
 		*panel = of_drm_find_panel(remote);
-		if (*panel)
+		if (!IS_ERR(*panel))
 			ret = 0;
+		else
+			*panel = NULL;
 	}
 
 	/* No panel found yet, check for a bridge next. */
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 965530a6f4cd..b902361dee6e 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -151,12 +151,19 @@ EXPORT_SYMBOL(drm_panel_detach);
  * tree node. If a matching panel is found, return a pointer to it.
  *
  * Return: A pointer to the panel registered for the specified device tree
- * node or NULL if no panel matching the device tree node can be found.
+ * node or an ERR_PTR() if no panel matching the device tree node can be found.
+ * Possible error codes returned by this function:
+ * - EPROBE_DEFER: the panel device has not been probed yet, and the caller
+ *   should retry later
+ * - ENODEV: the device is not available (status != "okay" or "ok")
  */
 struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
 	struct drm_panel *panel;
 
+	if (!of_device_is_available(np))
+		return ERR_PTR(-ENODEV);
+
 	mutex_lock(&panel_lock);
 
 	list_for_each_entry(panel, &panel_list, list) {
@@ -167,7 +174,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np)
 	}
 
 	mutex_unlock(&panel_lock);
-	return NULL;
+	return ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL(of_drm_find_panel);
 #endif
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 4db9c515b74f..896e42a34895 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -326,64 +326,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 }
 EXPORT_SYMBOL(drm_legacy_pci_init);
 
-int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *mask)
-{
-	struct pci_dev *root;
-	u32 lnkcap, lnkcap2;
-
-	*mask = 0;
-	if (!dev->pdev)
-		return -EINVAL;
-
-	root = dev->pdev->bus->self;
-
-	/* we've been informed via and serverworks don't make the cut */
-	if (root->vendor == PCI_VENDOR_ID_VIA ||
-	    root->vendor == PCI_VENDOR_ID_SERVERWORKS)
-		return -EINVAL;
-
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP2, &lnkcap2);
-
-	if (lnkcap2) {	/* PCIe r3.0-compliant */
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB)
-			*mask |= DRM_PCIE_SPEED_25;
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB)
-			*mask |= DRM_PCIE_SPEED_50;
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
-			*mask |= DRM_PCIE_SPEED_80;
-	} else {	/* pre-r3.0 */
-		if (lnkcap & PCI_EXP_LNKCAP_SLS_2_5GB)
-			*mask |= DRM_PCIE_SPEED_25;
-		if (lnkcap & PCI_EXP_LNKCAP_SLS_5_0GB)
-			*mask |= (DRM_PCIE_SPEED_25 | DRM_PCIE_SPEED_50);
-	}
-
-	DRM_INFO("probing gen 2 caps for device %x:%x = %x/%x\n", root->vendor, root->device, lnkcap, lnkcap2);
-	return 0;
-}
-EXPORT_SYMBOL(drm_pcie_get_speed_cap_mask);
-
-int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw)
-{
-	struct pci_dev *root;
-	u32 lnkcap;
-
-	*mlw = 0;
-	if (!dev->pdev)
-		return -EINVAL;
-
-	root = dev->pdev->bus->self;
-
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
-
-	*mlw = (lnkcap & PCI_EXP_LNKCAP_MLW) >> 4;
-
-	DRM_INFO("probing mlw for device %x:%x = %x\n", root->vendor, root->device, lnkcap);
-	return 0;
-}
-EXPORT_SYMBOL(drm_pcie_get_max_link_width);
-
 #else
 
 void drm_pci_agp_destroy(struct drm_device *dev) {}
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index df0b4ebbedbf..6153cbda239f 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -583,6 +583,52 @@ int drm_plane_check_pixel_format(struct drm_plane *plane,
 	return 0;
 }
 
+static int __setplane_check(struct drm_plane *plane,
+			    struct drm_crtc *crtc,
+			    struct drm_framebuffer *fb,
+			    int32_t crtc_x, int32_t crtc_y,
+			    uint32_t crtc_w, uint32_t crtc_h,
+			    uint32_t src_x, uint32_t src_y,
+			    uint32_t src_w, uint32_t src_h)
+{
+	int ret;
+
+	/* Check whether this plane is usable on this CRTC */
+	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
+		DRM_DEBUG_KMS("Invalid crtc for plane\n");
+		return -EINVAL;
+	}
+
+	/* Check whether this plane supports the fb pixel format. */
+	ret = drm_plane_check_pixel_format(plane, fb->format->format,
+					   fb->modifier);
+	if (ret) {
+		struct drm_format_name_buf format_name;
+
+		DRM_DEBUG_KMS("Invalid pixel format %s, modifier 0x%llx\n",
+			      drm_get_format_name(fb->format->format,
+						  &format_name),
+			      fb->modifier);
+		return ret;
+	}
+
+	/* Give drivers some help against integer overflows */
+	if (crtc_w > INT_MAX ||
+	    crtc_x > INT_MAX - (int32_t) crtc_w ||
+	    crtc_h > INT_MAX ||
+	    crtc_y > INT_MAX - (int32_t) crtc_h) {
+		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
+			      crtc_w, crtc_h, crtc_x, crtc_y);
+		return -ERANGE;
+	}
+
+	ret = drm_framebuffer_check_src_coords(src_x, src_y, src_w, src_h, fb);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 /*
  * __setplane_internal - setplane handler for internal callers
  *
@@ -603,6 +649,8 @@ static int __setplane_internal(struct drm_plane *plane,
 {
 	int ret = 0;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(plane->dev));
+
 	/* No fb means shut it down */
 	if (!fb) {
 		plane->old_fb = plane->fb;
@@ -616,37 +664,9 @@ static int __setplane_internal(struct drm_plane *plane,
 		goto out;
 	}
 
-	/* Check whether this plane is usable on this CRTC */
-	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
-		DRM_DEBUG_KMS("Invalid crtc for plane\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* Check whether this plane supports the fb pixel format. */
-	ret = drm_plane_check_pixel_format(plane, fb->format->format,
-					   fb->modifier);
-	if (ret) {
-		struct drm_format_name_buf format_name;
-		DRM_DEBUG_KMS("Invalid pixel format %s, modifier 0x%llx\n",
-			      drm_get_format_name(fb->format->format,
-						  &format_name),
-			      fb->modifier);
-		goto out;
-	}
-
-	/* Give drivers some help against integer overflows */
-	if (crtc_w > INT_MAX ||
-	    crtc_x > INT_MAX - (int32_t) crtc_w ||
-	    crtc_h > INT_MAX ||
-	    crtc_y > INT_MAX - (int32_t) crtc_h) {
-		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
-			      crtc_w, crtc_h, crtc_x, crtc_y);
-		ret = -ERANGE;
-		goto out;
-	}
-
-	ret = drm_framebuffer_check_src_coords(src_x, src_y, src_w, src_h, fb);
+	ret = __setplane_check(plane, crtc, fb,
+			       crtc_x, crtc_y, crtc_w, crtc_h,
+			       src_x, src_y, src_w, src_h);
 	if (ret)
 		goto out;
 
@@ -655,11 +675,9 @@ static int __setplane_internal(struct drm_plane *plane,
 					 crtc_x, crtc_y, crtc_w, crtc_h,
 					 src_x, src_y, src_w, src_h, ctx);
 	if (!ret) {
-		if (!plane->state) {
-			plane->crtc = crtc;
-			plane->fb = fb;
-			drm_framebuffer_get(plane->fb);
-		}
+		plane->crtc = crtc;
+		plane->fb = fb;
+		drm_framebuffer_get(plane->fb);
 	} else {
 		plane->old_fb = NULL;
 	}
@@ -672,6 +690,41 @@ out:
 	return ret;
 }
 
+static int __setplane_atomic(struct drm_plane *plane,
+			     struct drm_crtc *crtc,
+			     struct drm_framebuffer *fb,
+			     int32_t crtc_x, int32_t crtc_y,
+			     uint32_t crtc_w, uint32_t crtc_h,
+			     uint32_t src_x, uint32_t src_y,
+			     uint32_t src_w, uint32_t src_h,
+			     struct drm_modeset_acquire_ctx *ctx)
+{
+	int ret;
+
+	WARN_ON(!drm_drv_uses_atomic_modeset(plane->dev));
+
+	/* No fb means shut it down */
+	if (!fb)
+		return plane->funcs->disable_plane(plane, ctx);
+
+	/*
+	 * FIXME: This is redundant with drm_atomic_plane_check(),
+	 * but the legacy cursor/"async" .update_plane() tricks
+	 * don't call that so we still need this here. Should remove
+	 * this when all .update_plane() implementations have been
+	 * fixed to call drm_atomic_plane_check().
+	 */
+	ret = __setplane_check(plane, crtc, fb,
+			       crtc_x, crtc_y, crtc_w, crtc_h,
+			       src_x, src_y, src_w, src_h);
+	if (ret)
+		return ret;
+
+	return plane->funcs->update_plane(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  src_x, src_y, src_w, src_h, ctx);
+}
+
 static int setplane_internal(struct drm_plane *plane,
 			     struct drm_crtc *crtc,
 			     struct drm_framebuffer *fb,
@@ -689,9 +742,15 @@ retry:
 	ret = drm_modeset_lock_all_ctx(plane->dev, &ctx);
 	if (ret)
 		goto fail;
-	ret = __setplane_internal(plane, crtc, fb,
-				  crtc_x, crtc_y, crtc_w, crtc_h,
-				  src_x, src_y, src_w, src_h, &ctx);
+
+	if (drm_drv_uses_atomic_modeset(plane->dev))
+		ret = __setplane_atomic(plane, crtc, fb,
+					crtc_x, crtc_y, crtc_w, crtc_h,
+					src_x, src_y, src_w, src_h, &ctx);
+	else
+		ret = __setplane_internal(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  src_x, src_y, src_w, src_h, &ctx);
 
 fail:
 	if (ret == -EDEADLK) {
@@ -823,9 +882,14 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 		src_h = fb->height << 16;
 	}
 
-	ret = __setplane_internal(plane, crtc, fb,
-				  crtc_x, crtc_y, crtc_w, crtc_h,
-				  0, 0, src_w, src_h, ctx);
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = __setplane_atomic(plane, crtc, fb,
+					crtc_x, crtc_y, crtc_w, crtc_h,
+					0, 0, src_w, src_h, ctx);
+	else
+		ret = __setplane_internal(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  0, 0, src_w, src_h, ctx);
 
 	if (fb)
 		drm_framebuffer_put(fb);
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index b25f98f33f6c..0e7fc3e7dfb4 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -30,6 +30,100 @@
 #include <drm/drmP.h>
 #include <drm/drm_print.h>
 
+void __drm_puts_coredump(struct drm_printer *p, const char *str)
+{
+	struct drm_print_iterator *iterator = p->arg;
+	ssize_t len;
+
+	if (!iterator->remain)
+		return;
+
+	if (iterator->offset < iterator->start) {
+		ssize_t copy;
+
+		len = strlen(str);
+
+		if (iterator->offset + len <= iterator->start) {
+			iterator->offset += len;
+			return;
+		}
+
+		copy = len - (iterator->start - iterator->offset);
+
+		if (copy > iterator->remain)
+			copy = iterator->remain;
+
+		/* Copy out the bit of the string that we need */
+		memcpy(iterator->data,
+			str + (iterator->start - iterator->offset), copy);
+
+		iterator->offset = iterator->start + copy;
+		iterator->remain -= copy;
+	} else {
+		ssize_t pos = iterator->offset - iterator->start;
+
+		len = min_t(ssize_t, strlen(str), iterator->remain);
+
+		memcpy(iterator->data + pos, str, len);
+
+		iterator->offset += len;
+		iterator->remain -= len;
+	}
+}
+EXPORT_SYMBOL(__drm_puts_coredump);
+
+void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
+{
+	struct drm_print_iterator *iterator = p->arg;
+	size_t len;
+	char *buf;
+
+	if (!iterator->remain)
+		return;
+
+	/* Figure out how big the string will be */
+	len = snprintf(NULL, 0, "%pV", vaf);
+
+	/* This is the easiest path, we've already advanced beyond the offset */
+	if (iterator->offset + len <= iterator->start) {
+		iterator->offset += len;
+		return;
+	}
+
+	/* Then check if we can directly copy into the target buffer */
+	if ((iterator->offset >= iterator->start) && (len < iterator->remain)) {
+		ssize_t pos = iterator->offset - iterator->start;
+
+		snprintf(((char *) iterator->data) + pos,
+			iterator->remain, "%pV", vaf);
+
+		iterator->offset += len;
+		iterator->remain -= len;
+
+		return;
+	}
+
+	/*
+	 * Finally, hit the slow path and make a temporary string to copy over
+	 * using _drm_puts_coredump
+	 */
+	buf = kmalloc(len + 1, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+	if (!buf)
+		return;
+
+	snprintf(buf, len + 1, "%pV", vaf);
+	__drm_puts_coredump(p, (const char *) buf);
+
+	kfree(buf);
+}
+EXPORT_SYMBOL(__drm_printfn_coredump);
+
+void __drm_puts_seq_file(struct drm_printer *p, const char *str)
+{
+	seq_puts(p->arg, str);
+}
+EXPORT_SYMBOL(__drm_puts_seq_file);
+
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf)
 {
 	seq_printf(p->arg, "%pV", vaf);
@@ -49,6 +143,23 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf)
 EXPORT_SYMBOL(__drm_printfn_debug);
 
 /**
+ * drm_puts - print a const string to a &drm_printer stream
+ * @p: the &drm printer
+ * @str: const string
+ *
+ * Allow &drm_printer types that have a constant string
+ * option to use it.
+ */
+void drm_puts(struct drm_printer *p, const char *str)
+{
+	if (p->puts)
+		p->puts(p, str);
+	else
+		drm_printf(p, "%s", str);
+}
+EXPORT_SYMBOL(drm_puts);
+
+/**
  * drm_printf - print to a &drm_printer stream
  * @p: the &drm_printer
  * @f: format string
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 527743394150..a1bb157bfdfa 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -33,6 +33,7 @@
 #include <linux/moduleparam.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_client.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_crtc_helper.h>
@@ -88,9 +89,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 			    struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	uint32_t *ids = connector->encoder_ids;
 	enum drm_mode_status ret = MODE_OK;
-	unsigned int i;
+	struct drm_encoder *encoder;
+	int i;
 
 	/* Step 1: Validate against connector */
 	ret = drm_connector_mode_valid(connector, mode);
@@ -98,13 +99,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 		return ret;
 
 	/* Step 2: Validate against encoders and crtcs */
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		struct drm_encoder *encoder = drm_encoder_find(dev, NULL, ids[i]);
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		struct drm_crtc *crtc;
 
-		if (!encoder)
-			continue;
-
 		ret = drm_encoder_mode_valid(encoder, mode);
 		if (ret != MODE_OK) {
 			/* No point in continuing for crtc check as this encoder
@@ -363,7 +360,7 @@ EXPORT_SYMBOL(drm_helper_probe_detect);
  *    using the VESA GTF/CVT formulas.
  *
  * 3. Modes are moved from the probed_modes list to the modes list. Potential
- *    duplicates are merged together (see drm_mode_connector_list_update()).
+ *    duplicates are merged together (see drm_connector_list_update()).
  *    After this step the probed_modes list will be empty again.
  *
  * 4. Any non-stale mode on the modes list then undergoes validation
@@ -475,7 +472,7 @@ retry:
 	if (connector->status == connector_status_disconnected) {
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
 			connector->base.id, connector->name);
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		verbose_prune = false;
 		goto prune;
 	}
@@ -488,7 +485,7 @@ retry:
 	if (count == 0)
 		goto prune;
 
-	drm_mode_connector_list_update(connector);
+	drm_connector_list_update(connector);
 
 	if (connector->interlace_allowed)
 		mode_flags |= DRM_MODE_FLAG_INTERLACE;
@@ -563,6 +560,8 @@ void drm_kms_helper_hotplug_event(struct drm_device *dev)
 	drm_sysfs_hotplug_event(dev);
 	if (dev->mode_config.funcs->output_poll_changed)
 		dev->mode_config.funcs->output_poll_changed(dev);
+
+	drm_client_dev_hotplug(dev);
 }
 EXPORT_SYMBOL(drm_kms_helper_hotplug_event);
 
diff --git a/drivers/gpu/drm/drm_property.c b/drivers/gpu/drm/drm_property.c
index 1f8031e30f53..cdb10f885a4f 100644
--- a/drivers/gpu/drm/drm_property.c
+++ b/drivers/gpu/drm/drm_property.c
@@ -532,7 +532,7 @@ static void drm_property_free_blob(struct kref *kref)
 
 	drm_mode_object_unregister(blob->dev, &blob->base);
 
-	kfree(blob);
+	kvfree(blob);
 }
 
 /**
@@ -559,7 +559,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length,
 	if (!length || length > ULONG_MAX - sizeof(struct drm_property_blob))
 		return ERR_PTR(-EINVAL);
 
-	blob = kzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
+	blob = kvzalloc(sizeof(struct drm_property_blob)+length, GFP_KERNEL);
 	if (!blob)
 		return ERR_PTR(-ENOMEM);
 
@@ -576,7 +576,7 @@ drm_property_create_blob(struct drm_device *dev, size_t length,
 	ret = __drm_mode_object_add(dev, &blob->base, DRM_MODE_OBJECT_BLOB,
 				    true, drm_property_free_blob);
 	if (ret) {
-		kfree(blob);
+		kvfree(blob);
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index b72fcf1e9605..51fa978f0d23 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -287,7 +287,7 @@ int drm_simple_display_pipe_init(struct drm_device *dev,
 	if (ret || !connector)
 		return ret;
 
-	return drm_mode_connector_attach_encoder(connector, encoder);
+	return drm_connector_attach_encoder(connector, encoder);
 }
 EXPORT_SYMBOL(drm_simple_display_pipe_init);
 
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index 827395071f0b..c20e6fe00cb3 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -22,10 +22,13 @@
  * Writeback connectors are used to expose hardware which can write the output
  * from a CRTC to a memory buffer. They are used and act similarly to other
  * types of connectors, with some important differences:
- *  - Writeback connectors don't provide a way to output visually to the user.
- *  - Writeback connectors should always report as "disconnected" (so that
- *    clients which don't understand them will ignore them).
- *  - Writeback connectors don't have EDID.
+ *
+ * * Writeback connectors don't provide a way to output visually to the user.
+ *
+ * * Writeback connectors are visible to userspace only when the client sets
+ *   DRM_CLIENT_CAP_WRITEBACK_CONNECTORS.
+ *
+ * * Writeback connectors don't have EDID.
  *
  * A framebuffer may only be attached to a writeback connector when the
  * connector is attached to a CRTC. The WRITEBACK_FB_ID property which sets the
@@ -199,7 +202,7 @@ int drm_writeback_connector_init(struct drm_device *dev,
 	if (ret)
 		goto connector_fail;
 
-	ret = drm_mode_connector_attach_encoder(connector,
+	ret = drm_connector_attach_encoder(connector,
 						&wb_connector->encoder);
 	if (ret)
 		goto attach_fail;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index e5013a999147..9b2720b41571 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -49,12 +49,12 @@ 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;
 
 		if (gpu) {
-			drm_sched_entity_init(&gpu->sched,
-				&ctx->sched_entity[i],
-				&gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				NULL);
+			rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+			drm_sched_entity_init(&ctx->sched_entity[i],
+					      &rq, 1, NULL);
 			}
 	}
 
@@ -78,8 +78,7 @@ static void etnaviv_postclose(struct drm_device *dev, struct drm_file *file)
 				gpu->lastctx = NULL;
 			mutex_unlock(&gpu->lock);
 
-			drm_sched_entity_fini(&gpu->sched,
-					      &ctx->sched_entity[i]);
+			drm_sched_entity_destroy(&ctx->sched_entity[i]);
 		}
 	}
 
@@ -631,8 +630,11 @@ static struct platform_driver etnaviv_platform_driver = {
 	},
 };
 
+static struct platform_device *etnaviv_drm;
+
 static int __init etnaviv_init(void)
 {
+	struct platform_device *pdev;
 	int ret;
 	struct device_node *np;
 
@@ -644,7 +646,7 @@ static int __init etnaviv_init(void)
 
 	ret = platform_driver_register(&etnaviv_platform_driver);
 	if (ret != 0)
-		platform_driver_unregister(&etnaviv_gpu_driver);
+		goto unregister_gpu_driver;
 
 	/*
 	 * If the DT contains at least one available GPU device, instantiate
@@ -653,20 +655,33 @@ static int __init etnaviv_init(void)
 	for_each_compatible_node(np, NULL, "vivante,gc") {
 		if (!of_device_is_available(np))
 			continue;
-
-		platform_device_register_simple("etnaviv", -1, NULL, 0);
+		pdev = platform_device_register_simple("etnaviv", -1,
+						       NULL, 0);
+		if (IS_ERR(pdev)) {
+			ret = PTR_ERR(pdev);
+			of_node_put(np);
+			goto unregister_platform_driver;
+		}
+		etnaviv_drm = pdev;
 		of_node_put(np);
 		break;
 	}
 
+	return 0;
+
+unregister_platform_driver:
+	platform_driver_unregister(&etnaviv_platform_driver);
+unregister_gpu_driver:
+	platform_driver_unregister(&etnaviv_gpu_driver);
 	return ret;
 }
 module_init(etnaviv_init);
 
 static void __exit etnaviv_exit(void)
 {
-	platform_driver_unregister(&etnaviv_gpu_driver);
+	platform_device_unregister(etnaviv_drm);
 	platform_driver_unregister(&etnaviv_platform_driver);
+	platform_driver_unregister(&etnaviv_gpu_driver);
 }
 module_exit(etnaviv_exit);
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index dd430f0f8ff5..90f17ff7888e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -131,6 +131,9 @@ struct etnaviv_gpu {
 	struct work_struct sync_point_work;
 	int sync_point_event;
 
+	/* hang detection */
+	u32 hangcheck_dma_addr;
+
 	void __iomem *mmio;
 	int irq;
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index a74eb57af15b..3949f18afb35 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -10,6 +10,7 @@
 #include "etnaviv_gem.h"
 #include "etnaviv_gpu.h"
 #include "etnaviv_sched.h"
+#include "state.xml.h"
 
 static int etnaviv_job_hang_limit = 0;
 module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444);
@@ -85,6 +86,29 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 {
 	struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
 	struct etnaviv_gpu *gpu = submit->gpu;
+	u32 dma_addr;
+	int change;
+
+	/*
+	 * If the GPU managed to complete this jobs fence, the timout is
+	 * spurious. Bail out.
+	 */
+	if (fence_completed(gpu, submit->out_fence->seqno))
+		return;
+
+	/*
+	 * If the GPU is still making forward progress on the front-end (which
+	 * should never loop) we shift out the timeout to give it a chance to
+	 * finish the job.
+	 */
+	dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS);
+	change = dma_addr - gpu->hangcheck_dma_addr;
+	if (change < 0 || change > 16) {
+		gpu->hangcheck_dma_addr = dma_addr;
+		schedule_delayed_work(&sched_job->work_tdr,
+				      sched_job->sched->timeout);
+		return;
+	}
 
 	/* block scheduler */
 	kthread_park(gpu->sched.thread);
@@ -118,8 +142,8 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity,
 {
 	int ret;
 
-	ret = drm_sched_job_init(&submit->sched_job, &submit->gpu->sched,
-				 sched_entity, submit->cmdbuf.ctx);
+	ret = drm_sched_job_init(&submit->sched_job, sched_entity,
+				 submit->cmdbuf.ctx);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/exynos/Makefile b/drivers/gpu/drm/exynos/Makefile
index 3b323f1e0475..2ad146bbf4f5 100644
--- a/drivers/gpu/drm/exynos/Makefile
+++ b/drivers/gpu/drm/exynos/Makefile
@@ -4,7 +4,7 @@
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
 exynosdrm-y := exynos_drm_drv.o exynos_drm_crtc.o exynos_drm_fb.o \
-		exynos_drm_gem.o exynos_drm_core.o exynos_drm_plane.o
+		exynos_drm_gem.o exynos_drm_plane.o
 
 exynosdrm-$(CONFIG_DRM_FBDEV_EMULATION) += exynos_drm_fbdev.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_IOMMU) += exynos_drm_iommu.o
diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index 82c95c34447f..94529aa82339 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -265,7 +265,7 @@ static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win,
 	unsigned long val;
 
 	val = readl(ctx->addr + DECON_WINCONx(win));
-	val &= ~WINCONx_BPPMODE_MASK;
+	val &= WINCONx_ENWIN_F;
 
 	switch (fb->format->format) {
 	case DRM_FORMAT_XRGB1555:
@@ -356,8 +356,8 @@ static void decon_update_plane(struct exynos_drm_crtc *crtc,
 		writel(val, ctx->addr + DECON_VIDOSDxB(win));
 	}
 
-	val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) |
-		VIDOSD_Wx_ALPHA_B_F(0x0);
+	val = VIDOSD_Wx_ALPHA_R_F(0xff) | VIDOSD_Wx_ALPHA_G_F(0xff) |
+		VIDOSD_Wx_ALPHA_B_F(0xff);
 	writel(val, ctx->addr + DECON_VIDOSDxC(win));
 
 	val = VIDOSD_Wx_ALPHA_R_F(0x0) | VIDOSD_Wx_ALPHA_G_F(0x0) |
@@ -673,6 +673,8 @@ err:
 static const struct dev_pm_ops exynos5433_decon_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos5433_decon_suspend, exynos5433_decon_resume,
 			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static const struct of_device_id exynos5433_decon_driver_dt_match[] = {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 3931d5e33fe0..88cbd000eb09 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -832,6 +832,8 @@ static int exynos7_decon_resume(struct device *dev)
 static const struct dev_pm_ops exynos7_decon_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos7_decon_suspend, exynos7_decon_resume,
 			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver decon_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 86330f396784..c8449ae4f4fe 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/of_graph.h>
 #include <linux/component.h>
+#include <linux/pm_runtime.h>
 #include <video/of_display_timing.h>
 #include <video/of_videomode.h>
 #include <video/videomode.h>
@@ -232,9 +233,11 @@ static int exynos_dp_probe(struct platform_device *pdev)
 	np = of_parse_phandle(dev->of_node, "panel", 0);
 	if (np) {
 		dp->plat_data.panel = of_drm_find_panel(np);
+
 		of_node_put(np);
-		if (!dp->plat_data.panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(dp->plat_data.panel))
+			return PTR_ERR(dp->plat_data.panel);
+
 		goto out;
 	}
 
@@ -276,6 +279,8 @@ static int exynos_dp_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_dp_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_dp_suspend, exynos_dp_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static const struct of_device_id exynos_dp_match[] = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
deleted file mode 100644
index b0c0621fcdf7..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ /dev/null
@@ -1,119 +0,0 @@
-/* exynos_drm_core.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Author:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <drm/drmP.h>
-
-#include "exynos_drm_drv.h"
-#include "exynos_drm_crtc.h"
-
-static LIST_HEAD(exynos_drm_subdrv_list);
-
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_add_tail(&subdrv->list, &exynos_drm_subdrv_list);
-
-	return 0;
-}
-
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_del(&subdrv->list);
-
-	return 0;
-}
-
-int exynos_drm_device_subdrv_probe(struct drm_device *dev)
-{
-	struct exynos_drm_subdrv *subdrv, *n;
-	int err;
-
-	if (!dev)
-		return -EINVAL;
-
-	list_for_each_entry_safe(subdrv, n, &exynos_drm_subdrv_list, list) {
-		if (subdrv->probe) {
-			subdrv->drm_dev = dev;
-
-			/*
-			 * this probe callback would be called by sub driver
-			 * after setting of all resources to this sub driver,
-			 * such as clock, irq and register map are done.
-			 */
-			err = subdrv->probe(dev, subdrv->dev);
-			if (err) {
-				DRM_DEBUG("exynos drm subdrv probe failed.\n");
-				list_del(&subdrv->list);
-				continue;
-			}
-		}
-	}
-
-	return 0;
-}
-
-int exynos_drm_device_subdrv_remove(struct drm_device *dev)
-{
-	struct exynos_drm_subdrv *subdrv;
-
-	if (!dev) {
-		WARN(1, "Unexpected drm device unregister!\n");
-		return -EINVAL;
-	}
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->remove)
-			subdrv->remove(dev, subdrv->dev);
-	}
-
-	return 0;
-}
-
-int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file)
-{
-	struct exynos_drm_subdrv *subdrv;
-	int ret;
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->open) {
-			ret = subdrv->open(dev, subdrv->dev, file);
-			if (ret)
-				goto err;
-		}
-	}
-
-	return 0;
-
-err:
-	list_for_each_entry_continue_reverse(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->close)
-			subdrv->close(dev, subdrv->dev, file);
-	}
-	return ret;
-}
-
-void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file)
-{
-	struct exynos_drm_subdrv *subdrv;
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->close)
-			subdrv->close(dev, subdrv->dev, file);
-	}
-}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 66945e0dc57f..2f0babb67c51 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -113,7 +113,7 @@ static int exynos_dpi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &exynos_dpi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
@@ -240,8 +240,8 @@ struct drm_encoder *exynos_dpi_probe(struct device *dev)
 
 	if (ctx->panel_node) {
 		ctx->panel = of_drm_find_panel(ctx->panel_node);
-		if (!ctx->panel)
-			return ERR_PTR(-EPROBE_DEFER);
+		if (IS_ERR(ctx->panel))
+			return ERR_CAST(ctx->panel);
 	}
 
 	return &ctx->encoder;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index a81b4a5e24a7..b599f74692e5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -55,8 +55,7 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 		return -ENOMEM;
 
 	file->driver_priv = file_priv;
-
-	ret = exynos_drm_subdrv_open(dev, file);
+	ret = g2d_open(dev, file);
 	if (ret)
 		goto err_file_priv_free;
 
@@ -70,7 +69,7 @@ err_file_priv_free:
 
 static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 {
-	exynos_drm_subdrv_close(dev, file);
+	g2d_close(dev, file);
 	kfree(file->driver_priv);
 	file->driver_priv = NULL;
 }
@@ -147,13 +146,12 @@ static struct drm_driver exynos_drm_driver = {
 	.minor	= DRIVER_MINOR,
 };
 
-#ifdef CONFIG_PM_SLEEP
 static int exynos_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
-	if (pm_runtime_suspended(dev) || !drm_dev)
+	if (!drm_dev)
 		return 0;
 
 	private = drm_dev->dev_private;
@@ -170,25 +168,23 @@ static int exynos_drm_suspend(struct device *dev)
 	return 0;
 }
 
-static int exynos_drm_resume(struct device *dev)
+static void exynos_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
-	if (pm_runtime_suspended(dev) || !drm_dev)
-		return 0;
+	if (!drm_dev)
+		return;
 
 	private = drm_dev->dev_private;
 	drm_atomic_helper_resume(drm_dev, private->suspend_state);
 	exynos_drm_fbdev_resume(drm_dev);
 	drm_kms_helper_poll_enable(drm_dev);
-
-	return 0;
 }
-#endif
 
 static const struct dev_pm_ops exynos_drm_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(exynos_drm_suspend, exynos_drm_resume)
+	.prepare = exynos_drm_suspend,
+	.complete = exynos_drm_resume,
 };
 
 /* forward declaration */
@@ -240,6 +236,7 @@ static struct exynos_drm_driver_info exynos_drm_drivers[] = {
 		DRM_COMPONENT_DRIVER | DRM_VIRTUAL_DEVICE
 	}, {
 		DRV_PTR(g2d_driver, CONFIG_DRM_EXYNOS_G2D),
+		DRM_COMPONENT_DRIVER
 	}, {
 		DRV_PTR(fimc_driver, CONFIG_DRM_EXYNOS_FIMC),
 		DRM_COMPONENT_DRIVER | DRM_FIMC_DEVICE,
@@ -376,11 +373,6 @@ static int exynos_drm_bind(struct device *dev)
 	if (ret)
 		goto err_unbind_all;
 
-	/* Probe non kms sub drivers and virtual display driver. */
-	ret = exynos_drm_device_subdrv_probe(drm);
-	if (ret)
-		goto err_unbind_all;
-
 	drm_mode_config_reset(drm);
 
 	/*
@@ -411,7 +403,6 @@ err_cleanup_fbdev:
 	exynos_drm_fbdev_fini(drm);
 err_cleanup_poll:
 	drm_kms_helper_poll_fini(drm);
-	exynos_drm_device_subdrv_remove(drm);
 err_unbind_all:
 	component_unbind_all(drm->dev, drm);
 err_mode_config_cleanup:
@@ -420,7 +411,7 @@ err_mode_config_cleanup:
 err_free_private:
 	kfree(private);
 err_free_drm:
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 
 	return ret;
 }
@@ -431,8 +422,6 @@ static void exynos_drm_unbind(struct device *dev)
 
 	drm_dev_unregister(drm);
 
-	exynos_drm_device_subdrv_remove(drm);
-
 	exynos_drm_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 
@@ -444,7 +433,7 @@ static void exynos_drm_unbind(struct device *dev)
 	drm->dev_private = NULL;
 	dev_set_drvdata(dev, NULL);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops exynos_drm_ops = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 0f6d079a55c9..c737c4bd2c19 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -179,17 +179,13 @@ static inline void exynos_drm_pipe_clk_enable(struct exynos_drm_crtc *crtc,
 		crtc->pipe_clk->enable(crtc->pipe_clk, enable);
 }
 
-struct exynos_drm_g2d_private {
-	struct device		*dev;
+struct drm_exynos_file_private {
+	/* for g2d api */
 	struct list_head	inuse_cmdlist;
 	struct list_head	event_list;
 	struct list_head	userptr_list;
 };
 
-struct drm_exynos_file_private {
-	struct exynos_drm_g2d_private	*g2d_priv;
-};
-
 /*
  * Exynos drm private structure.
  *
@@ -201,6 +197,7 @@ struct exynos_drm_private {
 	struct drm_fb_helper *fb_helper;
 	struct drm_atomic_state *suspend_state;
 
+	struct device *g2d_dev;
 	struct device *dma_dev;
 	void *mapping;
 
@@ -217,44 +214,6 @@ static inline struct device *to_dma_dev(struct drm_device *dev)
 	return priv->dma_dev;
 }
 
-/*
- * Exynos drm sub driver structure.
- *
- * @list: sub driver has its own list object to register to exynos drm driver.
- * @dev: pointer to device object for subdrv device driver.
- * @drm_dev: pointer to drm_device and this pointer would be set
- *	when sub driver calls exynos_drm_subdrv_register().
- * @probe: this callback would be called by exynos drm driver after
- *     subdrv is registered to it.
- * @remove: this callback is used to release resources created
- *     by probe callback.
- * @open: this would be called with drm device file open.
- * @close: this would be called with drm device file close.
- */
-struct exynos_drm_subdrv {
-	struct list_head list;
-	struct device *dev;
-	struct drm_device *drm_dev;
-
-	int (*probe)(struct drm_device *drm_dev, struct device *dev);
-	void (*remove)(struct drm_device *drm_dev, struct device *dev);
-	int (*open)(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file);
-	void (*close)(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file);
-};
-
- /* This function would be called by non kms drivers such as g2d and ipp. */
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *drm_subdrv);
-
-/* this function removes subdrv list from exynos drm driver */
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *drm_subdrv);
-
-int exynos_drm_device_subdrv_probe(struct drm_device *dev);
-int exynos_drm_device_subdrv_remove(struct drm_device *dev);
-int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file);
-void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file);
-
 #ifdef CONFIG_DRM_EXYNOS_DPI
 struct drm_encoder *exynos_dpi_probe(struct device *dev);
 int exynos_dpi_remove(struct drm_encoder *encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 6d29777884f9..781b82c2c579 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1479,7 +1479,7 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder)
 
 	connector->status = connector_status_disconnected;
 	drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
@@ -1519,6 +1519,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
+	if (IS_ERR(dsi->panel))
+		dsi->panel = NULL;
+
 	if (dsi->panel) {
 		drm_panel_attach(dsi->panel, &dsi->connector);
 		dsi->connector.status = connector_status_connected;
@@ -1860,6 +1863,8 @@ err_clk:
 
 static const struct dev_pm_ops exynos_dsi_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_dsi_suspend, exynos_dsi_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver dsi_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 7fcc1a7ab1a0..9f52382e19ee 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -101,7 +101,6 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 {
 	const struct drm_format_info *info = drm_get_format_info(dev, mode_cmd);
 	struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
-	struct drm_gem_object *obj;
 	struct drm_framebuffer *fb;
 	int i;
 	int ret;
@@ -112,15 +111,14 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		unsigned long size = height * mode_cmd->pitches[i] +
 				     mode_cmd->offsets[i];
 
-		obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]);
-		if (!obj) {
+		exynos_gem[i] = exynos_drm_gem_get(file_priv,
+						   mode_cmd->handles[i]);
+		if (!exynos_gem[i]) {
 			DRM_ERROR("failed to lookup gem object\n");
 			ret = -ENOENT;
 			goto err;
 		}
 
-		exynos_gem[i] = to_exynos_gem(obj);
-
 		if (size > exynos_gem[i]->size) {
 			i++;
 			ret = -EINVAL;
@@ -138,7 +136,7 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 
 err:
 	while (i--)
-		drm_gem_object_unreference_unlocked(&exynos_gem[i]->base);
+		exynos_drm_gem_put(exynos_gem[i]);
 
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 6127ef25acd6..e8d0670bb5f8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -470,17 +470,18 @@ static void fimc_src_set_transf(struct fimc_context *ctx, unsigned int rotation)
 static void fimc_set_window(struct fimc_context *ctx,
 			    struct exynos_drm_ipp_buffer *buf)
 {
+	unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 	u32 cfg, h1, h2, v1, v2;
 
 	/* cropped image */
 	h1 = buf->rect.x;
-	h2 = buf->buf.width - buf->rect.w - buf->rect.x;
+	h2 = real_width - buf->rect.w - buf->rect.x;
 	v1 = buf->rect.y;
 	v2 = buf->buf.height - buf->rect.h - buf->rect.y;
 
 	DRM_DEBUG_KMS("x[%d]y[%d]w[%d]h[%d]hsize[%d]vsize[%d]\n",
 		buf->rect.x, buf->rect.y, buf->rect.w, buf->rect.h,
-		buf->buf.width, buf->buf.height);
+		real_width, buf->buf.height);
 	DRM_DEBUG_KMS("h1[%d]h2[%d]v1[%d]v2[%d]\n", h1, h2, v1, v2);
 
 	/*
@@ -503,12 +504,13 @@ static void fimc_set_window(struct fimc_context *ctx,
 static void fimc_src_set_size(struct fimc_context *ctx,
 			      struct exynos_drm_ipp_buffer *buf)
 {
+	unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 	u32 cfg;
 
-	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
+	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", real_width, buf->buf.height);
 
 	/* original size */
-	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(buf->buf.width) |
+	cfg = (EXYNOS_ORGISIZE_HORIZONTAL(real_width) |
 		EXYNOS_ORGISIZE_VERTICAL(buf->buf.height));
 
 	fimc_write(ctx, cfg, EXYNOS_ORGISIZE);
@@ -529,7 +531,7 @@ static void fimc_src_set_size(struct fimc_context *ctx,
 	 * for now, we support only ITU601 8 bit mode
 	 */
 	cfg = (EXYNOS_CISRCFMT_ITU601_8BIT |
-		EXYNOS_CISRCFMT_SOURCEHSIZE(buf->buf.width) |
+		EXYNOS_CISRCFMT_SOURCEHSIZE(real_width) |
 		EXYNOS_CISRCFMT_SOURCEVSIZE(buf->buf.height));
 	fimc_write(ctx, cfg, EXYNOS_CISRCFMT);
 
@@ -842,12 +844,13 @@ static void fimc_set_scaler(struct fimc_context *ctx, struct fimc_scaler *sc)
 static void fimc_dst_set_size(struct fimc_context *ctx,
 			     struct exynos_drm_ipp_buffer *buf)
 {
+	unsigned int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 	u32 cfg, cfg_ext;
 
-	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", buf->buf.width, buf->buf.height);
+	DRM_DEBUG_KMS("hsize[%d]vsize[%d]\n", real_width, buf->buf.height);
 
 	/* original size */
-	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(buf->buf.width) |
+	cfg = (EXYNOS_ORGOSIZE_HORIZONTAL(real_width) |
 		EXYNOS_ORGOSIZE_VERTICAL(buf->buf.height));
 
 	fimc_write(ctx, cfg, EXYNOS_ORGOSIZE);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 01b1570d0c3a..b7f56935a46b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -1192,6 +1192,8 @@ static int exynos_fimd_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_fimd_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_fimd_suspend, exynos_fimd_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver fimd_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index f68ef1b3a28c..f2481a2014bb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/component.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -190,7 +191,7 @@ struct g2d_buf_desc {
 struct g2d_buf_info {
 	unsigned int		map_nr;
 	enum g2d_reg_type	reg_types[MAX_REG_TYPE_NR];
-	unsigned long		handles[MAX_REG_TYPE_NR];
+	void			*obj[MAX_REG_TYPE_NR];
 	unsigned int		types[MAX_REG_TYPE_NR];
 	struct g2d_buf_desc	descs[MAX_REG_TYPE_NR];
 };
@@ -237,7 +238,7 @@ struct g2d_data {
 	int				irq;
 	struct workqueue_struct		*g2d_workq;
 	struct work_struct		runqueue_work;
-	struct exynos_drm_subdrv	subdrv;
+	struct drm_device		*drm_dev;
 	unsigned long			flags;
 
 	/* cmdlist */
@@ -268,14 +269,13 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 {
 	struct device *dev = g2d->dev;
 	struct g2d_cmdlist_node *node = g2d->cmdlist_node;
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
 	int nr;
 	int ret;
 	struct g2d_buf_info *buf_info;
 
 	g2d->cmdlist_dma_attrs = DMA_ATTR_WRITE_COMBINE;
 
-	g2d->cmdlist_pool_virt = dma_alloc_attrs(to_dma_dev(subdrv->drm_dev),
+	g2d->cmdlist_pool_virt = dma_alloc_attrs(to_dma_dev(g2d->drm_dev),
 						G2D_CMDLIST_POOL_SIZE,
 						&g2d->cmdlist_pool, GFP_KERNEL,
 						g2d->cmdlist_dma_attrs);
@@ -308,7 +308,7 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 	return 0;
 
 err:
-	dma_free_attrs(to_dma_dev(subdrv->drm_dev), G2D_CMDLIST_POOL_SIZE,
+	dma_free_attrs(to_dma_dev(g2d->drm_dev), G2D_CMDLIST_POOL_SIZE,
 			g2d->cmdlist_pool_virt,
 			g2d->cmdlist_pool, g2d->cmdlist_dma_attrs);
 	return ret;
@@ -316,12 +316,10 @@ err:
 
 static void g2d_fini_cmdlist(struct g2d_data *g2d)
 {
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
-
 	kfree(g2d->cmdlist_node);
 
 	if (g2d->cmdlist_pool_virt && g2d->cmdlist_pool) {
-		dma_free_attrs(to_dma_dev(subdrv->drm_dev),
+		dma_free_attrs(to_dma_dev(g2d->drm_dev),
 				G2D_CMDLIST_POOL_SIZE,
 				g2d->cmdlist_pool_virt,
 				g2d->cmdlist_pool, g2d->cmdlist_dma_attrs);
@@ -355,32 +353,31 @@ static void g2d_put_cmdlist(struct g2d_data *g2d, struct g2d_cmdlist_node *node)
 	mutex_unlock(&g2d->cmdlist_mutex);
 }
 
-static void g2d_add_cmdlist_to_inuse(struct exynos_drm_g2d_private *g2d_priv,
+static void g2d_add_cmdlist_to_inuse(struct drm_exynos_file_private *file_priv,
 				     struct g2d_cmdlist_node *node)
 {
 	struct g2d_cmdlist_node *lnode;
 
-	if (list_empty(&g2d_priv->inuse_cmdlist))
+	if (list_empty(&file_priv->inuse_cmdlist))
 		goto add_to_list;
 
 	/* this links to base address of new cmdlist */
-	lnode = list_entry(g2d_priv->inuse_cmdlist.prev,
+	lnode = list_entry(file_priv->inuse_cmdlist.prev,
 				struct g2d_cmdlist_node, list);
 	lnode->cmdlist->data[lnode->cmdlist->last] = node->dma_addr;
 
 add_to_list:
-	list_add_tail(&node->list, &g2d_priv->inuse_cmdlist);
+	list_add_tail(&node->list, &file_priv->inuse_cmdlist);
 
 	if (node->event)
-		list_add_tail(&node->event->base.link, &g2d_priv->event_list);
+		list_add_tail(&node->event->base.link, &file_priv->event_list);
 }
 
-static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
-					unsigned long obj,
+static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
+					void *obj,
 					bool force)
 {
-	struct g2d_cmdlist_userptr *g2d_userptr =
-					(struct g2d_cmdlist_userptr *)obj;
+	struct g2d_cmdlist_userptr *g2d_userptr = obj;
 	struct page **pages;
 
 	if (!obj)
@@ -398,7 +395,7 @@ static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
 		return;
 
 out:
-	dma_unmap_sg(to_dma_dev(drm_dev), g2d_userptr->sgt->sgl,
+	dma_unmap_sg(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt->sgl,
 			g2d_userptr->sgt->nents, DMA_BIDIRECTIONAL);
 
 	pages = frame_vector_pages(g2d_userptr->vec);
@@ -419,16 +416,14 @@ out:
 	kfree(g2d_userptr);
 }
 
-static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
+static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 					unsigned long userptr,
 					unsigned long size,
 					struct drm_file *filp,
-					unsigned long *obj)
+					void **obj)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr;
-	struct g2d_data *g2d;
 	struct sg_table	*sgt;
 	unsigned long start, end;
 	unsigned int npages, offset;
@@ -439,10 +434,8 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	g2d = dev_get_drvdata(g2d_priv->dev);
-
 	/* check if userptr already exists in userptr_list. */
-	list_for_each_entry(g2d_userptr, &g2d_priv->userptr_list, list) {
+	list_for_each_entry(g2d_userptr, &file_priv->userptr_list, list) {
 		if (g2d_userptr->userptr == userptr) {
 			/*
 			 * also check size because there could be same address
@@ -450,7 +443,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 			 */
 			if (g2d_userptr->size == size) {
 				atomic_inc(&g2d_userptr->refcount);
-				*obj = (unsigned long)g2d_userptr;
+				*obj = g2d_userptr;
 
 				return &g2d_userptr->dma_addr;
 			}
@@ -517,7 +510,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 
 	g2d_userptr->sgt = sgt;
 
-	if (!dma_map_sg(to_dma_dev(drm_dev), sgt->sgl, sgt->nents,
+	if (!dma_map_sg(to_dma_dev(g2d->drm_dev), sgt->sgl, sgt->nents,
 				DMA_BIDIRECTIONAL)) {
 		DRM_ERROR("failed to map sgt with dma region.\n");
 		ret = -ENOMEM;
@@ -527,14 +520,14 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 	g2d_userptr->dma_addr = sgt->sgl[0].dma_address;
 	g2d_userptr->userptr = userptr;
 
-	list_add_tail(&g2d_userptr->list, &g2d_priv->userptr_list);
+	list_add_tail(&g2d_userptr->list, &file_priv->userptr_list);
 
 	if (g2d->current_pool + (npages << PAGE_SHIFT) < g2d->max_pool) {
 		g2d->current_pool += npages << PAGE_SHIFT;
 		g2d_userptr->in_pool = true;
 	}
 
-	*obj = (unsigned long)g2d_userptr;
+	*obj = g2d_userptr;
 
 	return &g2d_userptr->dma_addr;
 
@@ -556,19 +549,14 @@ err_free:
 	return ERR_PTR(ret);
 }
 
-static void g2d_userptr_free_all(struct drm_device *drm_dev,
-					struct g2d_data *g2d,
-					struct drm_file *filp)
+static void g2d_userptr_free_all(struct g2d_data *g2d, struct drm_file *filp)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr, *n;
 
-	list_for_each_entry_safe(g2d_userptr, n, &g2d_priv->userptr_list, list)
+	list_for_each_entry_safe(g2d_userptr, n, &file_priv->userptr_list, list)
 		if (g2d_userptr->in_pool)
-			g2d_userptr_put_dma_addr(drm_dev,
-						(unsigned long)g2d_userptr,
-						true);
+			g2d_userptr_put_dma_addr(g2d, g2d_userptr, true);
 
 	g2d->current_pool = 0;
 }
@@ -723,26 +711,23 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 		buf_desc = &buf_info->descs[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM) {
-			unsigned long size;
+			struct exynos_drm_gem *exynos_gem;
 
-			size = exynos_drm_gem_get_size(drm_dev, handle, file);
-			if (!size) {
+			exynos_gem = exynos_drm_gem_get(file, handle);
+			if (!exynos_gem) {
 				ret = -EFAULT;
 				goto err;
 			}
 
-			if (!g2d_check_buf_desc_is_valid(buf_desc, reg_type,
-									size)) {
+			if (!g2d_check_buf_desc_is_valid(buf_desc,
+							 reg_type, exynos_gem->size)) {
+				exynos_drm_gem_put(exynos_gem);
 				ret = -EFAULT;
 				goto err;
 			}
 
-			addr = exynos_drm_gem_get_dma_addr(drm_dev, handle,
-								file);
-			if (IS_ERR(addr)) {
-				ret = -EFAULT;
-				goto err;
-			}
+			addr = &exynos_gem->dma_addr;
+			buf_info->obj[reg_type] = exynos_gem;
 		} else {
 			struct drm_exynos_g2d_userptr g2d_userptr;
 
@@ -758,11 +743,11 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 				goto err;
 			}
 
-			addr = g2d_userptr_get_dma_addr(drm_dev,
+			addr = g2d_userptr_get_dma_addr(g2d,
 							g2d_userptr.userptr,
 							g2d_userptr.size,
 							file,
-							&handle);
+							&buf_info->obj[reg_type]);
 			if (IS_ERR(addr)) {
 				ret = -EFAULT;
 				goto err;
@@ -771,7 +756,6 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 
 		cmdlist->data[reg_pos + 1] = *addr;
 		buf_info->reg_types[i] = reg_type;
-		buf_info->handles[reg_type] = handle;
 	}
 
 	return 0;
@@ -785,29 +769,26 @@ static void g2d_unmap_cmdlist_gem(struct g2d_data *g2d,
 				  struct g2d_cmdlist_node *node,
 				  struct drm_file *filp)
 {
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
 	struct g2d_buf_info *buf_info = &node->buf_info;
 	int i;
 
 	for (i = 0; i < buf_info->map_nr; i++) {
 		struct g2d_buf_desc *buf_desc;
 		enum g2d_reg_type reg_type;
-		unsigned long handle;
+		void *obj;
 
 		reg_type = buf_info->reg_types[i];
 
 		buf_desc = &buf_info->descs[reg_type];
-		handle = buf_info->handles[reg_type];
+		obj = buf_info->obj[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM)
-			exynos_drm_gem_put_dma_addr(subdrv->drm_dev, handle,
-							filp);
+			exynos_drm_gem_put(obj);
 		else
-			g2d_userptr_put_dma_addr(subdrv->drm_dev, handle,
-							false);
+			g2d_userptr_put_dma_addr(g2d, obj, false);
 
 		buf_info->reg_types[i] = REG_TYPE_NONE;
-		buf_info->handles[reg_type] = 0;
+		buf_info->obj[reg_type] = NULL;
 		buf_info->types[reg_type] = 0;
 		memset(buf_desc, 0x00, sizeof(*buf_desc));
 	}
@@ -922,7 +903,7 @@ static void g2d_runqueue_worker(struct work_struct *work)
 
 static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no)
 {
-	struct drm_device *drm_dev = g2d->subdrv.drm_dev;
+	struct drm_device *drm_dev = g2d->drm_dev;
 	struct g2d_runqueue_node *runqueue_node = g2d->runqueue_node;
 	struct drm_exynos_pending_g2d_event *e;
 	struct timespec64 now;
@@ -1031,7 +1012,7 @@ out:
 	mutex_unlock(&g2d->runqueue_mutex);
 }
 
-static int g2d_check_reg_offset(struct device *dev,
+static int g2d_check_reg_offset(struct g2d_data *g2d,
 				struct g2d_cmdlist_node *node,
 				int nr, bool for_addr)
 {
@@ -1131,7 +1112,7 @@ static int g2d_check_reg_offset(struct device *dev,
 	return 0;
 
 err:
-	dev_err(dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
+	dev_err(g2d->dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
 	return -EINVAL;
 }
 
@@ -1139,23 +1120,8 @@ err:
 int exynos_g2d_get_ver_ioctl(struct drm_device *drm_dev, void *data,
 			     struct drm_file *file)
 {
-	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
 	struct drm_exynos_g2d_get_ver *ver = data;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	ver->major = G2D_HW_MAJOR_VER;
 	ver->minor = G2D_HW_MINOR_VER;
 
@@ -1166,9 +1132,8 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 				 struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	struct g2d_data *g2d = dev_get_drvdata(priv->g2d_dev);
 	struct drm_exynos_g2d_set_cmdlist *req = data;
 	struct drm_exynos_g2d_cmd *cmd;
 	struct drm_exynos_pending_g2d_event *e;
@@ -1177,17 +1142,6 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	int size;
 	int ret;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	node = g2d_get_cmdlist(g2d);
 	if (!node)
 		return -ENOMEM;
@@ -1199,7 +1153,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	 */
 	if (req->cmd_nr > G2D_CMDLIST_DATA_NUM ||
 	    req->cmd_buf_nr > G2D_CMDLIST_DATA_NUM) {
-		dev_err(dev, "number of submitted G2D commands exceeds limit\n");
+		dev_err(g2d->dev, "number of submitted G2D commands exceeds limit\n");
 		return -EINVAL;
 	}
 
@@ -1267,7 +1221,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	 */
 	size = cmdlist->last + req->cmd_nr * 2 + req->cmd_buf_nr * 2 + 2;
 	if (size > G2D_CMDLIST_DATA_NUM) {
-		dev_err(dev, "cmdlist size is too big\n");
+		dev_err(g2d->dev, "cmdlist size is too big\n");
 		ret = -EINVAL;
 		goto err_free_event;
 	}
@@ -1282,7 +1236,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	}
 	cmdlist->last += req->cmd_nr * 2;
 
-	ret = g2d_check_reg_offset(dev, node, req->cmd_nr, false);
+	ret = g2d_check_reg_offset(g2d, node, req->cmd_nr, false);
 	if (ret < 0)
 		goto err_free_event;
 
@@ -1301,7 +1255,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 		}
 		cmdlist->last += req->cmd_buf_nr * 2;
 
-		ret = g2d_check_reg_offset(dev, node, req->cmd_buf_nr, true);
+		ret = g2d_check_reg_offset(g2d, node, req->cmd_buf_nr, true);
 		if (ret < 0)
 			goto err_free_event;
 
@@ -1319,7 +1273,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	/* tail */
 	cmdlist->data[cmdlist->last] = 0;
 
-	g2d_add_cmdlist_to_inuse(g2d_priv, node);
+	g2d_add_cmdlist_to_inuse(file_priv, node);
 
 	return 0;
 
@@ -1337,25 +1291,13 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 			  struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	struct g2d_data *g2d = dev_get_drvdata(priv->g2d_dev);
 	struct drm_exynos_g2d_exec *req = data;
 	struct g2d_runqueue_node *runqueue_node;
 	struct list_head *run_cmdlist;
 	struct list_head *event_list;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	runqueue_node = kmem_cache_alloc(g2d->runqueue_slab, GFP_KERNEL);
 	if (!runqueue_node)
 		return -ENOMEM;
@@ -1367,11 +1309,11 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 	init_completion(&runqueue_node->complete);
 	runqueue_node->async = req->async;
 
-	list_splice_init(&g2d_priv->inuse_cmdlist, run_cmdlist);
-	list_splice_init(&g2d_priv->event_list, event_list);
+	list_splice_init(&file_priv->inuse_cmdlist, run_cmdlist);
+	list_splice_init(&file_priv->event_list, event_list);
 
 	if (list_empty(run_cmdlist)) {
-		dev_err(dev, "there is no inuse cmdlist\n");
+		dev_err(g2d->dev, "there is no inuse cmdlist\n");
 		kmem_cache_free(g2d->runqueue_slab, runqueue_node);
 		return -EPERM;
 	}
@@ -1395,71 +1337,28 @@ out:
 	return 0;
 }
 
-static int g2d_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
-{
-	struct g2d_data *g2d;
-	int ret;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
-	/* allocate dma-aware cmdlist buffer. */
-	ret = g2d_init_cmdlist(g2d);
-	if (ret < 0) {
-		dev_err(dev, "cmdlist init failed\n");
-		return ret;
-	}
-
-	ret = drm_iommu_attach_device(drm_dev, dev);
-	if (ret < 0) {
-		dev_err(dev, "failed to enable iommu.\n");
-		g2d_fini_cmdlist(g2d);
-	}
-
-	return ret;
-
-}
-
-static void g2d_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
-{
-	drm_iommu_detach_device(drm_dev, dev);
-}
-
-static int g2d_open(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file)
+int g2d_open(struct drm_device *drm_dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv;
-
-	g2d_priv = kzalloc(sizeof(*g2d_priv), GFP_KERNEL);
-	if (!g2d_priv)
-		return -ENOMEM;
 
-	g2d_priv->dev = dev;
-	file_priv->g2d_priv = g2d_priv;
-
-	INIT_LIST_HEAD(&g2d_priv->inuse_cmdlist);
-	INIT_LIST_HEAD(&g2d_priv->event_list);
-	INIT_LIST_HEAD(&g2d_priv->userptr_list);
+	INIT_LIST_HEAD(&file_priv->inuse_cmdlist);
+	INIT_LIST_HEAD(&file_priv->event_list);
+	INIT_LIST_HEAD(&file_priv->userptr_list);
 
 	return 0;
 }
 
-static void g2d_close(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file)
+void g2d_close(struct drm_device *drm_dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
 	struct g2d_data *g2d;
 	struct g2d_cmdlist_node *node, *n;
 
-	if (!dev)
+	if (!priv->g2d_dev)
 		return;
 
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return;
+	g2d = dev_get_drvdata(priv->g2d_dev);
 
 	/* Remove the runqueue nodes that belong to us. */
 	mutex_lock(&g2d->runqueue_mutex);
@@ -1480,24 +1379,70 @@ static void g2d_close(struct drm_device *drm_dev, struct device *dev,
 	 * Properly unmap these buffers here.
 	 */
 	mutex_lock(&g2d->cmdlist_mutex);
-	list_for_each_entry_safe(node, n, &g2d_priv->inuse_cmdlist, list) {
+	list_for_each_entry_safe(node, n, &file_priv->inuse_cmdlist, list) {
 		g2d_unmap_cmdlist_gem(g2d, node, file);
 		list_move_tail(&node->list, &g2d->free_cmdlist);
 	}
 	mutex_unlock(&g2d->cmdlist_mutex);
 
 	/* release all g2d_userptr in pool. */
-	g2d_userptr_free_all(drm_dev, g2d, file);
+	g2d_userptr_free_all(g2d, file);
+}
+
+static int g2d_bind(struct device *dev, struct device *master, void *data)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	int ret;
+
+	g2d->drm_dev = drm_dev;
 
-	kfree(file_priv->g2d_priv);
+	/* allocate dma-aware cmdlist buffer. */
+	ret = g2d_init_cmdlist(g2d);
+	if (ret < 0) {
+		dev_err(dev, "cmdlist init failed\n");
+		return ret;
+	}
+
+	ret = drm_iommu_attach_device(drm_dev, dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable iommu.\n");
+		g2d_fini_cmdlist(g2d);
+		return ret;
+	}
+	priv->g2d_dev = dev;
+
+	dev_info(dev, "The Exynos G2D (ver %d.%d) successfully registered.\n",
+			G2D_HW_MAJOR_VER, G2D_HW_MINOR_VER);
+	return 0;
+}
+
+static void g2d_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+
+	/* Suspend operation and wait for engine idle. */
+	set_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
+	g2d_wait_finish(g2d, NULL);
+	priv->g2d_dev = NULL;
+
+	cancel_work_sync(&g2d->runqueue_work);
+	drm_iommu_detach_device(g2d->drm_dev, dev);
 }
 
+static const struct component_ops g2d_component_ops = {
+	.bind	= g2d_bind,
+	.unbind = g2d_unbind,
+};
+
 static int g2d_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct g2d_data *g2d;
-	struct exynos_drm_subdrv *subdrv;
 	int ret;
 
 	g2d = devm_kzalloc(dev, sizeof(*g2d), GFP_KERNEL);
@@ -1564,22 +1509,12 @@ static int g2d_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, g2d);
 
-	subdrv = &g2d->subdrv;
-	subdrv->dev = dev;
-	subdrv->probe = g2d_subdrv_probe;
-	subdrv->remove = g2d_subdrv_remove;
-	subdrv->open = g2d_open;
-	subdrv->close = g2d_close;
-
-	ret = exynos_drm_subdrv_register(subdrv);
+	ret = component_add(dev, &g2d_component_ops);
 	if (ret < 0) {
 		dev_err(dev, "failed to register drm g2d device\n");
 		goto err_put_clk;
 	}
 
-	dev_info(dev, "The Exynos G2D (ver %d.%d) successfully probed.\n",
-			G2D_HW_MAJOR_VER, G2D_HW_MINOR_VER);
-
 	return 0;
 
 err_put_clk:
@@ -1595,12 +1530,7 @@ static int g2d_remove(struct platform_device *pdev)
 {
 	struct g2d_data *g2d = platform_get_drvdata(pdev);
 
-	/* Suspend operation and wait for engine idle. */
-	set_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
-	g2d_wait_finish(g2d, NULL);
-
-	cancel_work_sync(&g2d->runqueue_work);
-	exynos_drm_subdrv_unregister(&g2d->subdrv);
+	component_del(&pdev->dev, &g2d_component_ops);
 
 	/* There should be no locking needed here. */
 	g2d_remove_runqueue_nodes(g2d, NULL);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h
index 1a9c7ca8c15b..287b2ed8f178 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h
@@ -14,6 +14,9 @@ extern int exynos_g2d_set_cmdlist_ioctl(struct drm_device *dev, void *data,
 					struct drm_file *file_priv);
 extern int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
+
+extern int g2d_open(struct drm_device *drm_dev, struct drm_file *file);
+extern void g2d_close(struct drm_device *drm_dev, struct drm_file *file);
 #else
 static inline int exynos_g2d_get_ver_ioctl(struct drm_device *dev, void *data,
 					   struct drm_file *file_priv)
@@ -33,4 +36,12 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data,
 {
 	return -ENODEV;
 }
+
+int g2d_open(struct drm_device *drm_dev, struct drm_file *file)
+{
+	return 0;
+}
+
+void g2d_close(struct drm_device *drm_dev, struct drm_file *file)
+{ }
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index 6e1494fa71b4..34ace85feb68 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -143,7 +143,7 @@ static int exynos_drm_gem_handle_create(struct drm_gem_object *obj,
 	DRM_DEBUG_KMS("gem handle = 0x%x\n", *handle);
 
 	/* drop reference from allocate - handle holds it now. */
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return 0;
 }
@@ -171,26 +171,6 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem *exynos_gem)
 	kfree(exynos_gem);
 }
 
-unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
-						unsigned int gem_handle,
-						struct drm_file *file_priv)
-{
-	struct exynos_drm_gem *exynos_gem;
-	struct drm_gem_object *obj;
-
-	obj = drm_gem_object_lookup(file_priv, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return 0;
-	}
-
-	exynos_gem = to_exynos_gem(obj);
-
-	drm_gem_object_unreference_unlocked(obj);
-
-	return exynos_gem->size;
-}
-
 static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 						  unsigned long size)
 {
@@ -299,43 +279,15 @@ int exynos_drm_gem_map_ioctl(struct drm_device *dev, void *data,
 				       &args->offset);
 }
 
-dma_addr_t *exynos_drm_gem_get_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp)
-{
-	struct exynos_drm_gem *exynos_gem;
-	struct drm_gem_object *obj;
-
-	obj = drm_gem_object_lookup(filp, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	exynos_gem = to_exynos_gem(obj);
-
-	return &exynos_gem->dma_addr;
-}
-
-void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp)
+struct exynos_drm_gem *exynos_drm_gem_get(struct drm_file *filp,
+					  unsigned int gem_handle)
 {
 	struct drm_gem_object *obj;
 
 	obj = drm_gem_object_lookup(filp, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return;
-	}
-
-	drm_gem_object_unreference_unlocked(obj);
-
-	/*
-	 * decrease obj->refcount one more time because we has already
-	 * increased it at exynos_drm_gem_get_dma_addr().
-	 */
-	drm_gem_object_unreference_unlocked(obj);
+	if (!obj)
+		return NULL;
+	return to_exynos_gem(obj);
 }
 
 static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
@@ -383,7 +335,7 @@ int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 	args->flags = exynos_gem->flags;
 	args->size = exynos_gem->size;
 
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 9057d7f1d6ed..d46a62c30812 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -77,32 +77,26 @@ int exynos_drm_gem_map_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 
 /*
- * get dma address from gem handle and this function could be used for
+ * get exynos drm object from gem handle, this function could be used for
  * other drivers such as 2d/3d acceleration drivers.
  * with this function call, gem object reference count would be increased.
  */
-dma_addr_t *exynos_drm_gem_get_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp);
+struct exynos_drm_gem *exynos_drm_gem_get(struct drm_file *filp,
+					  unsigned int gem_handle);
 
 /*
- * put dma address from gem handle and this function could be used for
- * other drivers such as 2d/3d acceleration drivers.
- * with this function call, gem object reference count would be decreased.
+ * put exynos drm object acquired from exynos_drm_gem_get(),
+ * gem object reference count would be decreased.
  */
-void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp);
+static inline void exynos_drm_gem_put(struct exynos_drm_gem *exynos_gem)
+{
+	drm_gem_object_put_unlocked(&exynos_gem->base);
+}
 
 /* get buffer information to memory region allocated by gem. */
 int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
 
-/* get buffer size to gem handle. */
-unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
-						unsigned int gem_handle,
-						struct drm_file *file_priv);
-
 /* free gem object. */
 void exynos_drm_gem_free_object(struct drm_gem_object *obj);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 35ac66730563..7ba414b52faa 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -492,21 +492,25 @@ static void gsc_src_set_fmt(struct gsc_context *ctx, u32 fmt)
 			GSC_IN_CHROMA_ORDER_CRCB);
 		break;
 	case DRM_FORMAT_NV21:
+		cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV420_2P);
+		break;
 	case DRM_FORMAT_NV61:
-		cfg |= (GSC_IN_CHROMA_ORDER_CRCB |
-			GSC_IN_YUV420_2P);
+		cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV422_2P);
 		break;
 	case DRM_FORMAT_YUV422:
 		cfg |= GSC_IN_YUV422_3P;
 		break;
 	case DRM_FORMAT_YUV420:
+		cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV420_3P);
+		break;
 	case DRM_FORMAT_YVU420:
-		cfg |= GSC_IN_YUV420_3P;
+		cfg |= (GSC_IN_CHROMA_ORDER_CRCB | GSC_IN_YUV420_3P);
 		break;
 	case DRM_FORMAT_NV12:
+		cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV420_2P);
+		break;
 	case DRM_FORMAT_NV16:
-		cfg |= (GSC_IN_CHROMA_ORDER_CBCR |
-			GSC_IN_YUV420_2P);
+		cfg |= (GSC_IN_CHROMA_ORDER_CBCR | GSC_IN_YUV422_2P);
 		break;
 	}
 
@@ -523,30 +527,30 @@ static void gsc_src_set_transf(struct gsc_context *ctx, unsigned int rotation)
 
 	switch (degree) {
 	case DRM_MODE_ROTATE_0:
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg |= GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg |= GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= GSC_IN_ROT_YFLIP;
 		break;
 	case DRM_MODE_ROTATE_90:
 		cfg |= GSC_IN_ROT_90;
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg |= GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg |= GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg |= GSC_IN_ROT_YFLIP;
 		break;
 	case DRM_MODE_ROTATE_180:
 		cfg |= GSC_IN_ROT_180;
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg &= ~GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg &= ~GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~GSC_IN_ROT_YFLIP;
 		break;
 	case DRM_MODE_ROTATE_270:
 		cfg |= GSC_IN_ROT_270;
-		if (rotation & DRM_MODE_REFLECT_Y)
-			cfg &= ~GSC_IN_ROT_XFLIP;
 		if (rotation & DRM_MODE_REFLECT_X)
+			cfg &= ~GSC_IN_ROT_XFLIP;
+		if (rotation & DRM_MODE_REFLECT_Y)
 			cfg &= ~GSC_IN_ROT_YFLIP;
 		break;
 	}
@@ -577,7 +581,7 @@ static void gsc_src_set_size(struct gsc_context *ctx,
 	cfg &= ~(GSC_SRCIMG_HEIGHT_MASK |
 		GSC_SRCIMG_WIDTH_MASK);
 
-	cfg |= (GSC_SRCIMG_WIDTH(buf->buf.width) |
+	cfg |= (GSC_SRCIMG_WIDTH(buf->buf.pitch[0] / buf->format->cpp[0]) |
 		GSC_SRCIMG_HEIGHT(buf->buf.height));
 
 	gsc_write(cfg, GSC_SRCIMG_SIZE);
@@ -672,18 +676,25 @@ static void gsc_dst_set_fmt(struct gsc_context *ctx, u32 fmt)
 			GSC_OUT_CHROMA_ORDER_CRCB);
 		break;
 	case DRM_FORMAT_NV21:
-	case DRM_FORMAT_NV61:
 		cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV420_2P);
 		break;
+	case DRM_FORMAT_NV61:
+		cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV422_2P);
+		break;
 	case DRM_FORMAT_YUV422:
+		cfg |= GSC_OUT_YUV422_3P;
+		break;
 	case DRM_FORMAT_YUV420:
+		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV420_3P);
+		break;
 	case DRM_FORMAT_YVU420:
-		cfg |= GSC_OUT_YUV420_3P;
+		cfg |= (GSC_OUT_CHROMA_ORDER_CRCB | GSC_OUT_YUV420_3P);
 		break;
 	case DRM_FORMAT_NV12:
+		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV420_2P);
+		break;
 	case DRM_FORMAT_NV16:
-		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR |
-			GSC_OUT_YUV420_2P);
+		cfg |= (GSC_OUT_CHROMA_ORDER_CBCR | GSC_OUT_YUV422_2P);
 		break;
 	}
 
@@ -868,7 +879,7 @@ static void gsc_dst_set_size(struct gsc_context *ctx,
 	/* original size */
 	cfg = gsc_read(GSC_DSTIMG_SIZE);
 	cfg &= ~(GSC_DSTIMG_HEIGHT_MASK | GSC_DSTIMG_WIDTH_MASK);
-	cfg |= GSC_DSTIMG_WIDTH(buf->buf.width) |
+	cfg |= GSC_DSTIMG_WIDTH(buf->buf.pitch[0] / buf->format->cpp[0]) |
 	       GSC_DSTIMG_HEIGHT(buf->buf.height);
 	gsc_write(cfg, GSC_DSTIMG_SIZE);
 
@@ -1341,7 +1352,7 @@ static const struct drm_exynos_ipp_limit gsc_5420_limits[] = {
 };
 
 static const struct drm_exynos_ipp_limit gsc_5433_limits[] = {
-	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 2 }, .v = { 16, 8191, 2 }) },
+	{ IPP_SIZE_LIMIT(BUFFER, .h = { 32, 8191, 16 }, .v = { 16, 8191, 2 }) },
 	{ IPP_SIZE_LIMIT(AREA, .h = { 16, 4800, 1 }, .v = { 8, 3344, 1 }) },
 	{ IPP_SIZE_LIMIT(ROTATED, .h = { 32, 2047 }, .v = { 8, 8191 }) },
 	{ IPP_SCALE_LIMIT(.h = { (1 << 16) / 16, (1 << 16) * 8 },
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index 26374e58c557..23226a0212e8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -345,39 +345,18 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 	int ret = 0;
 	int i;
 
-	/* basic checks */
-	if (buf->buf.width == 0 || buf->buf.height == 0)
-		return -EINVAL;
-	buf->format = drm_format_info(buf->buf.fourcc);
-	for (i = 0; i < buf->format->num_planes; i++) {
-		unsigned int width = (i == 0) ? buf->buf.width :
-			     DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
-
-		if (buf->buf.pitch[i] == 0)
-			buf->buf.pitch[i] = width * buf->format->cpp[i];
-		if (buf->buf.pitch[i] < width * buf->format->cpp[i])
-			return -EINVAL;
-		if (!buf->buf.gem_id[i])
-			return -ENOENT;
-	}
-
-	/* pitch for additional planes must match */
-	if (buf->format->num_planes > 2 &&
-	    buf->buf.pitch[1] != buf->buf.pitch[2])
-		return -EINVAL;
-
 	/* get GEM buffers and check their size */
 	for (i = 0; i < buf->format->num_planes; i++) {
 		unsigned int height = (i == 0) ? buf->buf.height :
 			     DIV_ROUND_UP(buf->buf.height, buf->format->vsub);
 		unsigned long size = height * buf->buf.pitch[i];
-		struct drm_gem_object *obj = drm_gem_object_lookup(filp,
+		struct exynos_drm_gem *gem = exynos_drm_gem_get(filp,
 							    buf->buf.gem_id[i]);
-		if (!obj) {
+		if (!gem) {
 			ret = -ENOENT;
 			goto gem_free;
 		}
-		buf->exynos_gem[i] = to_exynos_gem(obj);
+		buf->exynos_gem[i] = gem;
 
 		if (size + buf->buf.offset[i] > buf->exynos_gem[i]->size) {
 			i++;
@@ -391,7 +370,7 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 	return 0;
 gem_free:
 	while (i--) {
-		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		exynos_drm_gem_put(buf->exynos_gem[i]);
 		buf->exynos_gem[i] = NULL;
 	}
 	return ret;
@@ -404,7 +383,7 @@ static void exynos_drm_ipp_task_release_buf(struct exynos_drm_ipp_buffer *buf)
 	if (!buf->exynos_gem[0])
 		return;
 	for (i = 0; i < buf->format->num_planes; i++)
-		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		exynos_drm_gem_put(buf->exynos_gem[i]);
 }
 
 static void exynos_drm_ipp_task_free(struct exynos_drm_ipp *ipp,
@@ -428,7 +407,7 @@ enum drm_ipp_size_id {
 	IPP_LIMIT_BUFFER, IPP_LIMIT_AREA, IPP_LIMIT_ROTATED, IPP_LIMIT_MAX
 };
 
-static const enum drm_ipp_size_id limit_id_fallback[IPP_LIMIT_MAX][4] = {
+static const enum drm_exynos_ipp_limit_type limit_id_fallback[IPP_LIMIT_MAX][4] = {
 	[IPP_LIMIT_BUFFER]  = { DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
 	[IPP_LIMIT_AREA]    = { DRM_EXYNOS_IPP_LIMIT_SIZE_AREA,
 				DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER },
@@ -495,12 +474,13 @@ static int exynos_drm_ipp_check_size_limits(struct exynos_drm_ipp_buffer *buf,
 	enum drm_ipp_size_id id = rotate ? IPP_LIMIT_ROTATED : IPP_LIMIT_AREA;
 	struct drm_ipp_limit l;
 	struct drm_exynos_ipp_limit_val *lh = &l.h, *lv = &l.v;
+	int real_width = buf->buf.pitch[0] / buf->format->cpp[0];
 
 	if (!limits)
 		return 0;
 
 	__get_size_limit(limits, num_limits, IPP_LIMIT_BUFFER, &l);
-	if (!__size_limit_check(buf->buf.width, &l.h) ||
+	if (!__size_limit_check(real_width, &l.h) ||
 	    !__size_limit_check(buf->buf.height, &l.v))
 		return -EINVAL;
 
@@ -560,10 +540,62 @@ static int exynos_drm_ipp_check_scale_limits(
 	return 0;
 }
 
+static int exynos_drm_ipp_check_format(struct exynos_drm_ipp_task *task,
+				       struct exynos_drm_ipp_buffer *buf,
+				       struct exynos_drm_ipp_buffer *src,
+				       struct exynos_drm_ipp_buffer *dst,
+				       bool rotate, bool swap)
+{
+	const struct exynos_drm_ipp_formats *fmt;
+	int ret, i;
+
+	fmt = __ipp_format_get(task->ipp, buf->buf.fourcc, buf->buf.modifier,
+			       buf == src ? DRM_EXYNOS_IPP_FORMAT_SOURCE :
+					    DRM_EXYNOS_IPP_FORMAT_DESTINATION);
+	if (!fmt) {
+		DRM_DEBUG_DRIVER("Task %pK: %s format not supported\n", task,
+				 buf == src ? "src" : "dst");
+		return -EINVAL;
+	}
+
+	/* basic checks */
+	if (buf->buf.width == 0 || buf->buf.height == 0)
+		return -EINVAL;
+
+	buf->format = drm_format_info(buf->buf.fourcc);
+	for (i = 0; i < buf->format->num_planes; i++) {
+		unsigned int width = (i == 0) ? buf->buf.width :
+			     DIV_ROUND_UP(buf->buf.width, buf->format->hsub);
+
+		if (buf->buf.pitch[i] == 0)
+			buf->buf.pitch[i] = width * buf->format->cpp[i];
+		if (buf->buf.pitch[i] < width * buf->format->cpp[i])
+			return -EINVAL;
+		if (!buf->buf.gem_id[i])
+			return -ENOENT;
+	}
+
+	/* pitch for additional planes must match */
+	if (buf->format->num_planes > 2 &&
+	    buf->buf.pitch[1] != buf->buf.pitch[2])
+		return -EINVAL;
+
+	/* check driver limits */
+	ret = exynos_drm_ipp_check_size_limits(buf, fmt->limits,
+					       fmt->num_limits,
+					       rotate,
+					       buf == dst ? swap : false);
+	if (ret)
+		return ret;
+	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
+						fmt->limits,
+						fmt->num_limits, swap);
+	return ret;
+}
+
 static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 {
 	struct exynos_drm_ipp *ipp = task->ipp;
-	const struct exynos_drm_ipp_formats *src_fmt, *dst_fmt;
 	struct exynos_drm_ipp_buffer *src = &task->src, *dst = &task->dst;
 	unsigned int rotation = task->transform.rotation;
 	int ret = 0;
@@ -607,37 +639,11 @@ static int exynos_drm_ipp_task_check(struct exynos_drm_ipp_task *task)
 		return -EINVAL;
 	}
 
-	src_fmt = __ipp_format_get(ipp, src->buf.fourcc, src->buf.modifier,
-				   DRM_EXYNOS_IPP_FORMAT_SOURCE);
-	if (!src_fmt) {
-		DRM_DEBUG_DRIVER("Task %pK: src format not supported\n", task);
-		return -EINVAL;
-	}
-	ret = exynos_drm_ipp_check_size_limits(src, src_fmt->limits,
-					       src_fmt->num_limits,
-					       rotate, false);
-	if (ret)
-		return ret;
-	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
-						src_fmt->limits,
-						src_fmt->num_limits, swap);
+	ret = exynos_drm_ipp_check_format(task, src, src, dst, rotate, swap);
 	if (ret)
 		return ret;
 
-	dst_fmt = __ipp_format_get(ipp, dst->buf.fourcc, dst->buf.modifier,
-				   DRM_EXYNOS_IPP_FORMAT_DESTINATION);
-	if (!dst_fmt) {
-		DRM_DEBUG_DRIVER("Task %pK: dst format not supported\n", task);
-		return -EINVAL;
-	}
-	ret = exynos_drm_ipp_check_size_limits(dst, dst_fmt->limits,
-					       dst_fmt->num_limits,
-					       false, swap);
-	if (ret)
-		return ret;
-	ret = exynos_drm_ipp_check_scale_limits(&src->rect, &dst->rect,
-						dst_fmt->limits,
-						dst_fmt->num_limits, swap);
+	ret = exynos_drm_ipp_check_format(task, dst, src, dst, false, swap);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 2174814273e2..2fd299a58297 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -367,6 +367,8 @@ static int exynos_mic_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_mic_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_mic_suspend, exynos_mic_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static int exynos_mic_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index eb9915da7dec..dba29aec59b4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -132,7 +132,7 @@ static void exynos_drm_plane_reset(struct drm_plane *plane)
 	if (plane->state) {
 		exynos_state = to_exynos_plane_state(plane->state);
 		if (exynos_state->base.fb)
-			drm_framebuffer_unreference(exynos_state->base.fb);
+			drm_framebuffer_put(exynos_state->base.fb);
 		kfree(exynos_state);
 		plane->state = NULL;
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
index 1a76dd3d52e1..a820a68429b9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c
@@ -168,9 +168,9 @@ static void rotator_dst_set_transf(struct rot_context *rot,
 	val &= ~ROT_CONTROL_FLIP_MASK;
 
 	if (rotation & DRM_MODE_REFLECT_X)
-		val |= ROT_CONTROL_FLIP_HORIZONTAL;
-	if (rotation & DRM_MODE_REFLECT_Y)
 		val |= ROT_CONTROL_FLIP_VERTICAL;
+	if (rotation & DRM_MODE_REFLECT_Y)
+		val |= ROT_CONTROL_FLIP_HORIZONTAL;
 
 	val &= ~ROT_CONTROL_ROT_MASK;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_scaler.c b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
index 91d4382343d0..0ddb6eec7b11 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_scaler.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_scaler.c
@@ -30,6 +30,7 @@
 #define scaler_write(cfg, offset)	writel(cfg, scaler->regs + (offset))
 #define SCALER_MAX_CLK			4
 #define SCALER_AUTOSUSPEND_DELAY	2000
+#define SCALER_RESET_WAIT_RETRIES	100
 
 struct scaler_data {
 	const char	*clk_name[SCALER_MAX_CLK];
@@ -51,9 +52,9 @@ struct scaler_context {
 static u32 scaler_get_format(u32 drm_fmt)
 {
 	switch (drm_fmt) {
-	case DRM_FORMAT_NV21:
-		return SCALER_YUV420_2P_UV;
 	case DRM_FORMAT_NV12:
+		return SCALER_YUV420_2P_UV;
+	case DRM_FORMAT_NV21:
 		return SCALER_YUV420_2P_VU;
 	case DRM_FORMAT_YUV420:
 		return SCALER_YUV420_3P;
@@ -63,15 +64,15 @@ static u32 scaler_get_format(u32 drm_fmt)
 		return SCALER_YUV422_1P_UYVY;
 	case DRM_FORMAT_YVYU:
 		return SCALER_YUV422_1P_YVYU;
-	case DRM_FORMAT_NV61:
-		return SCALER_YUV422_2P_UV;
 	case DRM_FORMAT_NV16:
+		return SCALER_YUV422_2P_UV;
+	case DRM_FORMAT_NV61:
 		return SCALER_YUV422_2P_VU;
 	case DRM_FORMAT_YUV422:
 		return SCALER_YUV422_3P;
-	case DRM_FORMAT_NV42:
-		return SCALER_YUV444_2P_UV;
 	case DRM_FORMAT_NV24:
+		return SCALER_YUV444_2P_UV;
+	case DRM_FORMAT_NV42:
 		return SCALER_YUV444_2P_VU;
 	case DRM_FORMAT_YUV444:
 		return SCALER_YUV444_3P;
@@ -100,6 +101,23 @@ static u32 scaler_get_format(u32 drm_fmt)
 	return 0;
 }
 
+static inline int scaler_reset(struct scaler_context *scaler)
+{
+	int retry = SCALER_RESET_WAIT_RETRIES;
+
+	scaler_write(SCALER_CFG_SOFT_RESET, SCALER_CFG);
+	do {
+		cpu_relax();
+	} while (retry > 1 &&
+		 scaler_read(SCALER_CFG) & SCALER_CFG_SOFT_RESET);
+	do {
+		cpu_relax();
+		scaler_write(1, SCALER_INT_EN);
+	} while (retry > 0 && scaler_read(SCALER_INT_EN) != 1);
+
+	return retry ? 0 : -EIO;
+}
+
 static inline void scaler_enable_int(struct scaler_context *scaler)
 {
 	u32 val;
@@ -354,9 +372,13 @@ static int scaler_commit(struct exynos_drm_ipp *ipp,
 	u32 dst_fmt = scaler_get_format(task->dst.buf.fourcc);
 	struct drm_exynos_ipp_task_rect *dst_pos = &task->dst.rect;
 
-	scaler->task = task;
-
 	pm_runtime_get_sync(scaler->dev);
+	if (scaler_reset(scaler)) {
+		pm_runtime_put(scaler->dev);
+		return -EIO;
+	}
+
+	scaler->task = task;
 
 	scaler_set_src_fmt(scaler, src_fmt);
 	scaler_set_src_base(scaler, &task->src);
@@ -394,7 +416,11 @@ static inline void scaler_disable_int(struct scaler_context *scaler)
 
 static inline u32 scaler_get_int_status(struct scaler_context *scaler)
 {
-	return scaler_read(SCALER_INT_STATUS);
+	u32 val = scaler_read(SCALER_INT_STATUS);
+
+	scaler_write(val, SCALER_INT_STATUS);
+
+	return val;
 }
 
 static inline int scaler_task_done(u32 val)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index e6b0940b1ac2..19697c1362d8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -319,7 +319,7 @@ static int vidi_get_modes(struct drm_connector *connector)
 		return -ENOMEM;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	return drm_add_edid_modes(connector, edid);
 }
@@ -344,7 +344,7 @@ static int vidi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &vidi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index db91932550cf..2092a650df7d 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -888,7 +888,7 @@ static int hdmi_get_modes(struct drm_connector *connector)
 		(hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"),
 		edid->width_cm, edid->height_cm);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_notifier_set_phys_addr_from_edid(hdata->notifier, edid);
 
 	ret = drm_add_edid_modes(connector, edid);
@@ -951,7 +951,7 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &hdmi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	if (hdata->bridge) {
 		ret = drm_bridge_attach(encoder, hdata->bridge, NULL);
@@ -2093,6 +2093,8 @@ static int __maybe_unused exynos_hdmi_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_hdmi_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_hdmi_suspend, exynos_hdmi_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver hdmi_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 272c79f5f5bf..ffbf4a950f69 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -837,8 +837,6 @@ static int mixer_initialize(struct mixer_context *mixer_ctx,
 			struct drm_device *drm_dev)
 {
 	int ret;
-	struct exynos_drm_private *priv;
-	priv = drm_dev->dev_private;
 
 	mixer_ctx->drm_dev = drm_dev;
 
@@ -1271,6 +1269,8 @@ static int __maybe_unused exynos_mixer_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_mixer_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_mixer_suspend, exynos_mixer_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver mixer_driver = {
diff --git a/drivers/gpu/drm/exynos/regs-gsc.h b/drivers/gpu/drm/exynos/regs-gsc.h
index 4704a993cbb7..16b39734115c 100644
--- a/drivers/gpu/drm/exynos/regs-gsc.h
+++ b/drivers/gpu/drm/exynos/regs-gsc.h
@@ -138,6 +138,7 @@
 #define GSC_OUT_YUV420_3P		(3 << 4)
 #define GSC_OUT_YUV422_1P		(4 << 4)
 #define GSC_OUT_YUV422_2P		(5 << 4)
+#define GSC_OUT_YUV422_3P		(6 << 4)
 #define GSC_OUT_YUV444			(7 << 4)
 #define GSC_OUT_TILE_TYPE_MASK		(1 << 2)
 #define GSC_OUT_TILE_C_16x8		(0 << 2)
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 c54806d08dd7..2298ed2a9e1c 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -117,7 +117,7 @@ static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev,
 	if (ret < 0)
 		goto err_cleanup;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		goto err_sysfs;
 
@@ -148,8 +148,9 @@ int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev)
 	if (panel_node) {
 		fsl_dev->connector.panel = of_drm_find_panel(panel_node);
 		of_node_put(panel_node);
-		if (!fsl_dev->connector.panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(fsl_dev->connector.panel))
+			return PTR_ERR(fsl_dev->connector.panel);
+
 		return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel);
 	}
 
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 5ea785f07ba8..90ed20083009 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -1770,7 +1770,7 @@ static int cdv_intel_dp_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &intel_dp->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
index f0878998526a..4e4e4a66eaee 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
@@ -216,7 +216,7 @@ static int cdv_hdmi_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &gma_encoder->i2c_bus->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index 08f17f85b801..09c1161a7ac6 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -665,7 +665,7 @@ void gma_connector_attach_encoder(struct gma_connector *connector,
 				  struct gma_encoder *encoder)
 {
 	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
+	drm_connector_attach_encoder(&connector->base,
 					  &encoder->base);
 }
 
diff --git a/drivers/gpu/drm/gma500/intel_bios.h b/drivers/gpu/drm/gma500/intel_bios.h
index 978ae4b25e82..e0ccf1d19a4d 100644
--- a/drivers/gpu/drm/gma500/intel_bios.h
+++ b/drivers/gpu/drm/gma500/intel_bios.h
@@ -34,7 +34,7 @@ struct vbt_header {
 	u8 reserved0;
 	u32 bdb_offset;			/**< from beginning of VBT */
 	u32 aim_offset[4];		/**< from beginning of VBT */
-} __attribute__((packed));
+} __packed;
 
 
 struct bdb_header {
@@ -61,7 +61,7 @@ struct vbios_data {
 	u8 rsvd4; /* popup memory size */
 	u8 resize_pci_bios;
 	u8 rsvd5; /* is crt already on ddc2 */
-} __attribute__((packed));
+} __packed;
 
 /*
  * There are several types of BIOS data blocks (BDBs), each block has
@@ -133,7 +133,7 @@ struct bdb_general_features {
 	u8 dp_ssc_enb:1;	/* PCH attached eDP supports SSC */
 	u8 dp_ssc_freq:1;	/* SSC freq for PCH attached eDP */
 	u8 rsvd11:3; /* finish byte */
-} __attribute__((packed));
+} __packed;
 
 /* pre-915 */
 #define GPIO_PIN_DVI_LVDS	0x03 /* "DVI/LVDS DDC GPIO pins" */
@@ -213,7 +213,7 @@ struct child_device_config {
 	u8  dvo2_wiring;
 	u16 extended_type;
 	u8  dvo_function;
-} __attribute__((packed));
+} __packed;
 
 
 struct bdb_general_definitions {
@@ -256,7 +256,7 @@ struct bdb_lvds_options {
 	u8 lvds_edid:1;
 	u8 rsvd2:1;
 	u8 rsvd4;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_backlight {
 	u8 type:2;
@@ -268,7 +268,7 @@ struct bdb_lvds_backlight {
 	u8 i2caddr;
 	u8 brightnesscmd;
 	/*FIXME: more...*/
-} __attribute__((packed));
+} __packed;
 
 /* LFP pointer table contains entries to the struct below */
 struct bdb_lvds_lfp_data_ptr {
@@ -278,12 +278,12 @@ struct bdb_lvds_lfp_data_ptr {
 	u8 dvo_table_size;
 	u16 panel_pnp_id_offset;
 	u8 pnp_table_size;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_ptrs {
 	u8 lvds_entries; /* followed by one or more lvds_data_ptr structs */
 	struct bdb_lvds_lfp_data_ptr ptr[16];
-} __attribute__((packed));
+} __packed;
 
 /* LFP data has 3 blocks per entry */
 struct lvds_fp_timing {
@@ -300,7 +300,7 @@ struct lvds_fp_timing {
 	u32 pfit_reg;
 	u32 pfit_reg_val;
 	u16 terminator;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_dvo_timing {
 	u16 clock;		/**< In 10khz */
@@ -328,7 +328,7 @@ struct lvds_dvo_timing {
 	u8 vsync_positive:1;
 	u8 hsync_positive:1;
 	u8 rsvd2:1;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_pnp_id {
 	u16 mfg_name;
@@ -336,17 +336,17 @@ struct lvds_pnp_id {
 	u32 serial;
 	u8 mfg_week;
 	u8 mfg_year;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_entry {
 	struct lvds_fp_timing fp_timing;
 	struct lvds_dvo_timing dvo_timing;
 	struct lvds_pnp_id pnp_id;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data {
 	struct bdb_lvds_lfp_data_entry data[16];
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_header {
 	char signature[16];
@@ -354,12 +354,12 @@ struct aimdb_header {
 	u16 aimdb_version;
 	u16 aimdb_header_size;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_block {
 	u8 aimdb_id;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_panel_data {
 	u16 fp_timing_offset;
@@ -370,12 +370,12 @@ struct vch_panel_data {
 	u8 text_fitting_size;
 	u16 graphics_fitting_offset;
 	u8 graphics_fitting_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_bdb_22 {
 	struct aimdb_block aimdb_block;
 	struct vch_panel_data panels[16];
-} __attribute__((packed));
+} __packed;
 
 struct bdb_sdvo_lvds_options {
 	u8 panel_backlight;
@@ -391,7 +391,7 @@ struct bdb_sdvo_lvds_options {
 	u8 panel_misc_bits_2;
 	u8 panel_misc_bits_3;
 	u8 panel_misc_bits_4;
-} __attribute__((packed));
+} __packed;
 
 #define BDB_DRIVER_FEATURE_NO_LVDS		0
 #define BDB_DRIVER_FEATURE_INT_LVDS		1
@@ -436,7 +436,7 @@ struct bdb_driver_features {
 
 	u8 hdmi_termination;
 	u8 custom_vbt_version;
-} __attribute__((packed));
+} __packed;
 
 #define EDP_18BPP	0
 #define EDP_24BPP	1
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
index a05c020602bd..d0bf5a1e94e8 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
@@ -999,7 +999,7 @@ struct mdfld_dsi_encoder *mdfld_dsi_dpi_init(struct drm_device *dev,
 				p_funcs->encoder_helper_funcs);
 
 	/*attach to given connector*/
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	/*set possible crtcs and clones*/
 	if (dsi_connector->pipe) {
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 78566a80ad25..c6d72de1c054 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -578,7 +578,7 @@ static int oaktrail_hdmi_get_modes(struct drm_connector *connector)
 	}
 
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 	}
 	return ret;
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index e6943fef0611..83babb815a5d 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -376,7 +376,7 @@ void oaktrail_lvds_init(struct drm_device *dev,
 	 * preferred mode is the right one.
 	 */
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		drm_add_edid_modes(connector, edid);
 		kfree(edid);
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_modes.c b/drivers/gpu/drm/gma500/psb_intel_modes.c
index e5360726d80b..fb4da3cd6681 100644
--- a/drivers/gpu/drm/gma500/psb_intel_modes.c
+++ b/drivers/gpu/drm/gma500/psb_intel_modes.c
@@ -66,7 +66,7 @@ int psb_intel_ddc_get_modes(struct drm_connector *connector,
 
 	edid = drm_get_edid(connector, adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index 1d40746ab625..dd3cec0e3190 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -1472,7 +1472,7 @@ static void psb_intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 		bool connector_is_digital = !!IS_TMDS(psb_intel_sdvo_connector);
 
 		if (connector_is_digital == monitor_is_digital) {
-			drm_mode_connector_update_edid_property(connector, edid);
+			drm_connector_update_edid_property(connector, edid);
 			drm_add_edid_modes(connector, edid);
 		}
 
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
index d2f4749ebf8d..744956cea749 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
@@ -133,7 +133,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv)
 	}
 
 	drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 0df86e928191..a7c39f39793f 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1222,7 +1222,7 @@ static int tda998x_connector_get_modes(struct drm_connector *connector)
 		return 0;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid);
 
 	mutex_lock(&priv->audio_mutex);
@@ -1269,8 +1269,8 @@ static int tda998x_connector_init(struct tda998x_priv *priv,
 	if (ret)
 		return ret;
 
-	drm_mode_connector_attach_encoder(&priv->connector,
-					  priv->bridge.encoder);
+	drm_connector_attach_encoder(&priv->connector,
+				     priv->bridge.encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 9de8b1c51a5c..459f8f88a34c 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -51,6 +51,18 @@ config DRM_I915_DEBUG_GEM
 
           If in doubt, say "N".
 
+config DRM_I915_ERRLOG_GEM
+	bool "Insert extra logging (very verbose) for common GEM errors"
+	default n
+	depends on DRM_I915_DEBUG_GEM
+	help
+	  Enable additional logging that may help track down the cause of
+	  principally userspace errors.
+
+	  Recommended for driver developers only.
+
+	  If in doubt, say "N".
+
 config DRM_I915_TRACE_GEM
 	bool "Insert extra ftrace output from the GEM internals"
 	depends on DRM_I915_DEBUG_GEM
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4c6adae23e18..5794f102f9b8 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -135,15 +135,14 @@ i915-y += dvo_ch7017.o \
 	  dvo_ns2501.o \
 	  dvo_sil164.o \
 	  dvo_tfp410.o \
+	  icl_dsi.o \
 	  intel_crt.o \
 	  intel_ddi.o \
 	  intel_dp_aux_backlight.o \
 	  intel_dp_link_training.o \
 	  intel_dp_mst.o \
 	  intel_dp.o \
-	  intel_dsi.o \
 	  intel_dsi_dcs_backlight.o \
-	  intel_dsi_pll.o \
 	  intel_dsi_vbt.o \
 	  intel_dvo.o \
 	  intel_hdmi.o \
@@ -152,7 +151,9 @@ i915-y += dvo_ch7017.o \
 	  intel_lvds.o \
 	  intel_panel.o \
 	  intel_sdvo.o \
-	  intel_tv.o
+	  intel_tv.o \
+	  vlv_dsi.o \
+	  vlv_dsi_pll.o
 
 # Post-mortem debug and GPU hang state capture
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 0651e63b25fb..45e89b1e0481 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -863,6 +863,7 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 {
 	struct intel_vgpu *vgpu = s->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
+	u32 ctx_sr_ctl;
 
 	if (offset + 4 > gvt->device_info.mmio_size) {
 		gvt_vgpu_err("%s access to (%x) outside of MMIO range\n",
@@ -895,6 +896,28 @@ static int cmd_reg_handler(struct parser_exec_state *s,
 		patch_value(s, cmd_ptr(s, index), VGT_PVINFO_PAGE);
 	}
 
+	/* TODO
+	 * Right now only scan LRI command on KBL and in inhibit context.
+	 * It's good enough to support initializing mmio by lri command in
+	 * vgpu inhibit context on KBL.
+	 */
+	if (IS_KABYLAKE(s->vgpu->gvt->dev_priv) &&
+			intel_gvt_mmio_is_in_ctx(gvt, offset) &&
+			!strncmp(cmd, "lri", 3)) {
+		intel_gvt_hypervisor_read_gpa(s->vgpu,
+			s->workload->ring_context_gpa + 12, &ctx_sr_ctl, 4);
+		/* check inhibit context */
+		if (ctx_sr_ctl & 1) {
+			u32 data = cmd_val(s, index + 1);
+
+			if (intel_gvt_mmio_has_mode_mask(s->vgpu->gvt, offset))
+				intel_vgpu_mask_mmio_write(vgpu,
+							offset, &data, 4);
+			else
+				vgpu_vreg(vgpu, offset) = data;
+		}
+	}
+
 	/* TODO: Update the global mask if this MMIO is a masked-MMIO */
 	intel_gvt_mmio_set_cmd_accessed(gvt, offset);
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6ee50cb328f8..3019dbc39aef 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -219,7 +219,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_B << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
@@ -239,7 +239,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_C << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
@@ -259,7 +259,7 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 			~(TRANS_DDI_BPC_MASK | TRANS_DDI_MODE_SELECT_MASK |
 			TRANS_DDI_PORT_MASK);
 		vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_A)) |=
-			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
+			(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DVI |
 			(PORT_D << TRANS_DDI_PORT_SHIFT) |
 			TRANS_DDI_FUNC_ENABLE);
 		if (IS_BROADWELL(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 642e216e0a5b..00aad8164dec 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -216,16 +216,22 @@ static struct gtt_type_table_entry gtt_type_table[] = {
 			GTT_TYPE_PPGTT_PDE_PT,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_PPGTT_PTE_2M_ENTRY),
+	/* We take IPS bit as 'PSE' for PTE level. */
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_INVALID,
-			GTT_TYPE_INVALID),
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_INVALID,
-			GTT_TYPE_INVALID),
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
+	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
+			GTT_TYPE_PPGTT_PTE_PT,
+			GTT_TYPE_INVALID,
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_2M_ENTRY,
 			GTT_TYPE_PPGTT_PDE_ENTRY,
 			GTT_TYPE_PPGTT_PDE_PT,
@@ -339,8 +345,14 @@ static inline int gtt_set_entry64(void *pt,
 
 #define ADDR_1G_MASK	GENMASK_ULL(GTT_HAW - 1, 30)
 #define ADDR_2M_MASK	GENMASK_ULL(GTT_HAW - 1, 21)
+#define ADDR_64K_MASK	GENMASK_ULL(GTT_HAW - 1, 16)
 #define ADDR_4K_MASK	GENMASK_ULL(GTT_HAW - 1, 12)
 
+#define GTT_SPTE_FLAG_MASK GENMASK_ULL(62, 52)
+#define GTT_SPTE_FLAG_64K_SPLITED BIT(52) /* splited 64K gtt entry */
+
+#define GTT_64K_PTE_STRIDE 16
+
 static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 {
 	unsigned long pfn;
@@ -349,6 +361,8 @@ static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 		pfn = (e->val64 & ADDR_1G_MASK) >> PAGE_SHIFT;
 	else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY)
 		pfn = (e->val64 & ADDR_2M_MASK) >> PAGE_SHIFT;
+	else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY)
+		pfn = (e->val64 & ADDR_64K_MASK) >> PAGE_SHIFT;
 	else
 		pfn = (e->val64 & ADDR_4K_MASK) >> PAGE_SHIFT;
 	return pfn;
@@ -362,6 +376,9 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn)
 	} else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY) {
 		e->val64 &= ~ADDR_2M_MASK;
 		pfn &= (ADDR_2M_MASK >> PAGE_SHIFT);
+	} else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY) {
+		e->val64 &= ~ADDR_64K_MASK;
+		pfn &= (ADDR_64K_MASK >> PAGE_SHIFT);
 	} else {
 		e->val64 &= ~ADDR_4K_MASK;
 		pfn &= (ADDR_4K_MASK >> PAGE_SHIFT);
@@ -372,16 +389,41 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn)
 
 static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e)
 {
-	/* Entry doesn't have PSE bit. */
-	if (get_pse_type(e->type) == GTT_TYPE_INVALID)
-		return false;
+	return !!(e->val64 & _PAGE_PSE);
+}
 
-	e->type = get_entry_type(e->type);
-	if (!(e->val64 & _PAGE_PSE))
+static void gen8_gtt_clear_pse(struct intel_gvt_gtt_entry *e)
+{
+	if (gen8_gtt_test_pse(e)) {
+		switch (e->type) {
+		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+			e->val64 &= ~_PAGE_PSE;
+			e->type = GTT_TYPE_PPGTT_PDE_ENTRY;
+			break;
+		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
+			e->type = GTT_TYPE_PPGTT_PDP_ENTRY;
+			e->val64 &= ~_PAGE_PSE;
+			break;
+		default:
+			WARN_ON(1);
+		}
+	}
+}
+
+static bool gen8_gtt_test_ips(struct intel_gvt_gtt_entry *e)
+{
+	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
 		return false;
 
-	e->type = get_pse_type(e->type);
-	return true;
+	return !!(e->val64 & GEN8_PDE_IPS_64K);
+}
+
+static void gen8_gtt_clear_ips(struct intel_gvt_gtt_entry *e)
+{
+	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
+		return;
+
+	e->val64 &= ~GEN8_PDE_IPS_64K;
 }
 
 static bool gen8_gtt_test_present(struct intel_gvt_gtt_entry *e)
@@ -408,6 +450,21 @@ static void gtt_entry_set_present(struct intel_gvt_gtt_entry *e)
 	e->val64 |= _PAGE_PRESENT;
 }
 
+static bool gen8_gtt_test_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	return !!(e->val64 & GTT_SPTE_FLAG_64K_SPLITED);
+}
+
+static void gen8_gtt_set_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	e->val64 |= GTT_SPTE_FLAG_64K_SPLITED;
+}
+
+static void gen8_gtt_clear_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	e->val64 &= ~GTT_SPTE_FLAG_64K_SPLITED;
+}
+
 /*
  * Per-platform GMA routines.
  */
@@ -440,6 +497,12 @@ static struct intel_gvt_gtt_pte_ops gen8_gtt_pte_ops = {
 	.set_present = gtt_entry_set_present,
 	.test_present = gen8_gtt_test_present,
 	.test_pse = gen8_gtt_test_pse,
+	.clear_pse = gen8_gtt_clear_pse,
+	.clear_ips = gen8_gtt_clear_ips,
+	.test_ips = gen8_gtt_test_ips,
+	.clear_64k_splited = gen8_gtt_clear_64k_splited,
+	.set_64k_splited = gen8_gtt_set_64k_splited,
+	.test_64k_splited = gen8_gtt_test_64k_splited,
 	.get_pfn = gen8_gtt_get_pfn,
 	.set_pfn = gen8_gtt_set_pfn,
 };
@@ -453,6 +516,27 @@ static struct intel_gvt_gtt_gma_ops gen8_gtt_gma_ops = {
 	.gma_to_pml4_index = gen8_gma_to_pml4_index,
 };
 
+/* Update entry type per pse and ips bit. */
+static void update_entry_type_for_real(struct intel_gvt_gtt_pte_ops *pte_ops,
+	struct intel_gvt_gtt_entry *entry, bool ips)
+{
+	switch (entry->type) {
+	case GTT_TYPE_PPGTT_PDE_ENTRY:
+	case GTT_TYPE_PPGTT_PDP_ENTRY:
+		if (pte_ops->test_pse(entry))
+			entry->type = get_pse_type(entry->type);
+		break;
+	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
+		if (ips)
+			entry->type = get_pse_type(entry->type);
+		break;
+	default:
+		GEM_BUG_ON(!gtt_type_is_entry(entry->type));
+	}
+
+	GEM_BUG_ON(entry->type == GTT_TYPE_INVALID);
+}
+
 /*
  * MM helpers.
  */
@@ -468,8 +552,7 @@ static void _ppgtt_get_root_entry(struct intel_vgpu_mm *mm,
 	pte_ops->get_entry(guest ? mm->ppgtt_mm.guest_pdps :
 			   mm->ppgtt_mm.shadow_pdps,
 			   entry, index, false, 0, mm->vgpu);
-
-	pte_ops->test_pse(entry);
+	update_entry_type_for_real(pte_ops, entry, false);
 }
 
 static inline void ppgtt_get_guest_root_entry(struct intel_vgpu_mm *mm,
@@ -574,7 +657,8 @@ static inline int ppgtt_spt_get_entry(
 	if (ret)
 		return ret;
 
-	ops->test_pse(e);
+	update_entry_type_for_real(ops, e, guest ?
+				   spt->guest_page.pde_ips : false);
 
 	gvt_vdbg_mm("read ppgtt entry, spt type %d, entry type %d, index %lu, value %llx\n",
 		    type, e->type, index, e->val64);
@@ -653,10 +737,12 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt)
 
 	radix_tree_delete(&spt->vgpu->gtt.spt_tree, spt->shadow_page.mfn);
 
-	if (spt->guest_page.oos_page)
-		detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
+	if (spt->guest_page.gfn) {
+		if (spt->guest_page.oos_page)
+			detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
 
-	intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+		intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+	}
 
 	list_del_init(&spt->post_shadow_list);
 	free_spt(spt);
@@ -717,8 +803,9 @@ static inline struct intel_vgpu_ppgtt_spt *intel_vgpu_find_spt_by_mfn(
 
 static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
 
+/* Allocate shadow page table without guest page. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
-		struct intel_vgpu *vgpu, int type, unsigned long gfn)
+		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type)
 {
 	struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
@@ -753,26 +840,12 @@ retry:
 	spt->shadow_page.vaddr = page_address(spt->shadow_page.page);
 	spt->shadow_page.mfn = daddr >> I915_GTT_PAGE_SHIFT;
 
-	/*
-	 * Init guest_page.
-	 */
-	spt->guest_page.type = type;
-	spt->guest_page.gfn = gfn;
-
-	ret = intel_vgpu_register_page_track(vgpu, spt->guest_page.gfn,
-					ppgtt_write_protection_handler, spt);
-	if (ret)
-		goto err_unmap_dma;
-
 	ret = radix_tree_insert(&vgpu->gtt.spt_tree, spt->shadow_page.mfn, spt);
 	if (ret)
-		goto err_unreg_page_track;
+		goto err_unmap_dma;
 
-	trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
 	return spt;
 
-err_unreg_page_track:
-	intel_vgpu_unregister_page_track(vgpu, spt->guest_page.gfn);
 err_unmap_dma:
 	dma_unmap_page(kdev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 err_free_spt:
@@ -780,6 +853,37 @@ err_free_spt:
 	return ERR_PTR(ret);
 }
 
+/* Allocate shadow page table associated with specific gfn. */
+static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
+		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type,
+		unsigned long gfn, bool guest_pde_ips)
+{
+	struct intel_vgpu_ppgtt_spt *spt;
+	int ret;
+
+	spt = ppgtt_alloc_spt(vgpu, type);
+	if (IS_ERR(spt))
+		return spt;
+
+	/*
+	 * Init guest_page.
+	 */
+	ret = intel_vgpu_register_page_track(vgpu, gfn,
+			ppgtt_write_protection_handler, spt);
+	if (ret) {
+		ppgtt_free_spt(spt);
+		return ERR_PTR(ret);
+	}
+
+	spt->guest_page.type = type;
+	spt->guest_page.gfn = gfn;
+	spt->guest_page.pde_ips = guest_pde_ips;
+
+	trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
+
+	return spt;
+}
+
 #define pt_entry_size_shift(spt) \
 	((spt)->vgpu->gvt->device_info.gtt_entry_size_shift)
 
@@ -787,24 +891,38 @@ err_free_spt:
 	(I915_GTT_PAGE_SIZE >> pt_entry_size_shift(spt))
 
 #define for_each_present_guest_entry(spt, e, i) \
-	for (i = 0; i < pt_entries(spt); i++) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += spt->guest_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
 		if (!ppgtt_get_guest_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
 #define for_each_present_shadow_entry(spt, e, i) \
-	for (i = 0; i < pt_entries(spt); i++) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
 		if (!ppgtt_get_shadow_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
-static void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
+#define for_each_shadow_entry(spt, e, i) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += (spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1)) \
+		if (!ppgtt_get_shadow_entry(spt, e, i))
+
+static inline void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
 {
 	int v = atomic_read(&spt->refcount);
 
 	trace_spt_refcount(spt->vgpu->id, "inc", spt, v, (v + 1));
-
 	atomic_inc(&spt->refcount);
 }
 
+static inline int ppgtt_put_spt(struct intel_vgpu_ppgtt_spt *spt)
+{
+	int v = atomic_read(&spt->refcount);
+
+	trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
+	return atomic_dec_return(&spt->refcount);
+}
+
 static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt);
 
 static int ppgtt_invalidate_spt_by_shadow_entry(struct intel_vgpu *vgpu,
@@ -843,7 +961,8 @@ static inline void ppgtt_invalidate_pte(struct intel_vgpu_ppgtt_spt *spt,
 	pfn = ops->get_pfn(entry);
 	type = spt->shadow_page.type;
 
-	if (pfn == vgpu->gtt.scratch_pt[type].page_mfn)
+	/* Uninitialized spte or unshadowed spte. */
+	if (!pfn || pfn == vgpu->gtt.scratch_pt[type].page_mfn)
 		return;
 
 	intel_gvt_hypervisor_dma_unmap_guest_page(vgpu, pfn << PAGE_SHIFT);
@@ -855,14 +974,11 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 	struct intel_gvt_gtt_entry e;
 	unsigned long index;
 	int ret;
-	int v = atomic_read(&spt->refcount);
 
 	trace_spt_change(spt->vgpu->id, "die", spt,
 			spt->guest_page.gfn, spt->shadow_page.type);
 
-	trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
-
-	if (atomic_dec_return(&spt->refcount) > 0)
+	if (ppgtt_put_spt(spt) > 0)
 		return 0;
 
 	for_each_present_shadow_entry(spt, &e, index) {
@@ -871,9 +987,15 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 			gvt_vdbg_mm("invalidate 4K entry\n");
 			ppgtt_invalidate_pte(spt, &e);
 			break;
+		case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+			/* We don't setup 64K shadow entry so far. */
+			WARN(1, "suspicious 64K gtt entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+			gvt_vdbg_mm("invalidate 2M entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-			WARN(1, "GVT doesn't support 2M/1GB page\n");
+			WARN(1, "GVT doesn't support 1GB page\n");
 			continue;
 		case GTT_TYPE_PPGTT_PML4_ENTRY:
 		case GTT_TYPE_PPGTT_PDP_ENTRY:
@@ -899,6 +1021,22 @@ fail:
 	return ret;
 }
 
+static bool vgpu_ips_enabled(struct intel_vgpu *vgpu)
+{
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+
+	if (INTEL_GEN(dev_priv) == 9 || INTEL_GEN(dev_priv) == 10) {
+		u32 ips = vgpu_vreg_t(vgpu, GEN8_GAMW_ECO_DEV_RW_IA) &
+			GAMW_ECO_ENABLE_64K_IPS_FIELD;
+
+		return ips == GAMW_ECO_ENABLE_64K_IPS_FIELD;
+	} else if (INTEL_GEN(dev_priv) >= 11) {
+		/* 64K paging only controlled by IPS bit in PTE now. */
+		return true;
+	} else
+		return false;
+}
+
 static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt);
 
 static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
@@ -906,35 +1044,54 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 {
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
+	bool ips = false;
 	int ret;
 
 	GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(we->type)));
 
+	if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+
 	spt = intel_vgpu_find_spt_by_gfn(vgpu, ops->get_pfn(we));
-	if (spt)
+	if (spt) {
 		ppgtt_get_spt(spt);
-	else {
+
+		if (ips != spt->guest_page.pde_ips) {
+			spt->guest_page.pde_ips = ips;
+
+			gvt_dbg_mm("reshadow PDE since ips changed\n");
+			clear_page(spt->shadow_page.vaddr);
+			ret = ppgtt_populate_spt(spt);
+			if (ret) {
+				ppgtt_put_spt(spt);
+				goto err;
+			}
+		}
+	} else {
 		int type = get_next_pt_type(we->type);
 
-		spt = ppgtt_alloc_spt(vgpu, type, ops->get_pfn(we));
+		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
-			goto fail;
+			goto err;
 		}
 
 		ret = intel_vgpu_enable_page_track(vgpu, spt->guest_page.gfn);
 		if (ret)
-			goto fail;
+			goto err_free_spt;
 
 		ret = ppgtt_populate_spt(spt);
 		if (ret)
-			goto fail;
+			goto err_free_spt;
 
 		trace_spt_change(vgpu->id, "new", spt, spt->guest_page.gfn,
 				 spt->shadow_page.type);
 	}
 	return spt;
-fail:
+
+err_free_spt:
+	ppgtt_free_spt(spt);
+err:
 	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
 		     spt, we->val64, we->type);
 	return ERR_PTR(ret);
@@ -948,16 +1105,118 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se,
 	se->type = ge->type;
 	se->val64 = ge->val64;
 
+	/* Because we always split 64KB pages, so clear IPS in shadow PDE. */
+	if (se->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ops->clear_ips(se);
+
 	ops->set_pfn(se, s->shadow_page.mfn);
 }
 
+/**
+ * Return 1 if 2MB huge gtt shadowing is possilbe, 0 if miscondition,
+ * negtive if found err.
+ */
+static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
+	struct intel_gvt_gtt_entry *entry)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	unsigned long pfn;
+
+	if (!HAS_PAGE_SIZES(vgpu->gvt->dev_priv, I915_GTT_PAGE_SIZE_2M))
+		return 0;
+
+	pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, ops->get_pfn(entry));
+	if (pfn == INTEL_GVT_INVALID_ADDR)
+		return -EINVAL;
+
+	return PageTransHuge(pfn_to_page(pfn));
+}
+
+static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_vgpu_ppgtt_spt *sub_spt;
+	struct intel_gvt_gtt_entry sub_se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	unsigned long sub_index;
+	int ret;
+
+	gvt_dbg_mm("Split 2M gtt entry, index %lu\n", index);
+
+	start_gfn = ops->get_pfn(se);
+
+	sub_spt = ppgtt_alloc_spt(vgpu, GTT_TYPE_PPGTT_PTE_PT);
+	if (IS_ERR(sub_spt))
+		return PTR_ERR(sub_spt);
+
+	for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+				start_gfn + sub_index, PAGE_SIZE, &dma_addr);
+		if (ret) {
+			ppgtt_invalidate_spt(spt);
+			return ret;
+		}
+		sub_se.val64 = se->val64;
+
+		/* Copy the PAT field from PDE. */
+		sub_se.val64 &= ~_PAGE_PAT;
+		sub_se.val64 |= (se->val64 & _PAGE_PAT_LARGE) >> 5;
+
+		ops->set_pfn(&sub_se, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(sub_spt, &sub_se, sub_index);
+	}
+
+	/* Clear dirty field. */
+	se->val64 &= ~_PAGE_DIRTY;
+
+	ops->clear_pse(se);
+	ops->clear_ips(se);
+	ops->set_pfn(se, sub_spt->shadow_page.mfn);
+	ppgtt_set_shadow_entry(spt, se, index);
+	return 0;
+}
+
+static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_gvt_gtt_entry entry = *se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	int i, ret;
+
+	gvt_vdbg_mm("Split 64K gtt entry, index %lu\n", index);
+
+	GEM_BUG_ON(index % GTT_64K_PTE_STRIDE);
+
+	start_gfn = ops->get_pfn(se);
+
+	entry.type = GTT_TYPE_PPGTT_PTE_4K_ENTRY;
+	ops->set_64k_splited(&entry);
+
+	for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+					start_gfn + i, PAGE_SIZE, &dma_addr);
+		if (ret)
+			return ret;
+
+		ops->set_pfn(&entry, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(spt, &entry, index + i);
+	}
+	return 0;
+}
+
 static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
 	struct intel_gvt_gtt_entry *ge)
 {
 	struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry se = *ge;
-	unsigned long gfn;
+	unsigned long gfn, page_size = PAGE_SIZE;
 	dma_addr_t dma_addr;
 	int ret;
 
@@ -970,16 +1229,33 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
 		gvt_vdbg_mm("shadow 4K gtt entry\n");
 		break;
+	case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+		gvt_vdbg_mm("shadow 64K gtt entry\n");
+		/*
+		 * The layout of 64K page is special, the page size is
+		 * controlled by uper PDE. To be simple, we always split
+		 * 64K page to smaller 4K pages in shadow PT.
+		 */
+		return split_64KB_gtt_entry(vgpu, spt, index, &se);
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+		gvt_vdbg_mm("shadow 2M gtt entry\n");
+		ret = is_2MB_gtt_possible(vgpu, ge);
+		if (ret == 0)
+			return split_2MB_gtt_entry(vgpu, spt, index, &se);
+		else if (ret < 0)
+			return ret;
+		page_size = I915_GTT_PAGE_SIZE_2M;
+		break;
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-		gvt_vgpu_err("GVT doesn't support 2M/1GB entry\n");
+		gvt_vgpu_err("GVT doesn't support 1GB entry\n");
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
 	};
 
 	/* direct shadow */
-	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, &dma_addr);
+	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, page_size,
+						      &dma_addr);
 	if (ret)
 		return -ENXIO;
 
@@ -1062,8 +1338,12 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_ppgtt_spt *spt,
 		ret = ppgtt_invalidate_spt(s);
 		if (ret)
 			goto fail;
-	} else
+	} else {
+		/* We don't setup 64K shadow entry so far. */
+		WARN(se->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+		     "suspicious 64K entry\n");
 		ppgtt_invalidate_pte(spt, se);
+	}
 
 	return 0;
 fail:
@@ -1286,7 +1566,7 @@ static int ppgtt_handle_guest_write_page_table(
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry old_se;
 	int new_present;
-	int ret;
+	int i, ret;
 
 	new_present = ops->test_present(we);
 
@@ -1308,8 +1588,27 @@ static int ppgtt_handle_guest_write_page_table(
 		goto fail;
 
 	if (!new_present) {
-		ops->set_pfn(&old_se, vgpu->gtt.scratch_pt[type].page_mfn);
-		ppgtt_set_shadow_entry(spt, &old_se, index);
+		/* For 64KB splited entries, we need clear them all. */
+		if (ops->test_64k_splited(&old_se) &&
+		    !(index % GTT_64K_PTE_STRIDE)) {
+			gvt_vdbg_mm("remove splited 64K shadow entries\n");
+			for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+				ops->clear_64k_splited(&old_se);
+				ops->set_pfn(&old_se,
+					vgpu->gtt.scratch_pt[type].page_mfn);
+				ppgtt_set_shadow_entry(spt, &old_se, index + i);
+			}
+		} else if (old_se.type == GTT_TYPE_PPGTT_PTE_2M_ENTRY ||
+			   old_se.type == GTT_TYPE_PPGTT_PTE_1G_ENTRY) {
+			ops->clear_pse(&old_se);
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
+		} else {
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
+		}
 	}
 
 	return 0;
@@ -1391,7 +1690,17 @@ static int ppgtt_handle_guest_write_page_table_bytes(
 
 	ppgtt_get_guest_entry(spt, &we, index);
 
-	ops->test_pse(&we);
+	/*
+	 * For page table which has 64K gtt entry, only PTE#0, PTE#16,
+	 * PTE#32, ... PTE#496 are used. Unused PTEs update should be
+	 * ignored.
+	 */
+	if (we.type == GTT_TYPE_PPGTT_PTE_64K_ENTRY &&
+	    (index % GTT_64K_PTE_STRIDE)) {
+		gvt_vdbg_mm("Ignore write to unused PTE entry, index %lu\n",
+			    index);
+		return 0;
+	}
 
 	if (bytes == info->gtt_entry_size) {
 		ret = ppgtt_handle_guest_write_page_table(spt, &we, index);
@@ -1592,6 +1901,7 @@ static struct intel_vgpu_mm *intel_vgpu_create_ggtt_mm(struct intel_vgpu *vgpu)
 		vgpu_free_mm(mm);
 		return ERR_PTR(-ENOMEM);
 	}
+	mm->ggtt_mm.last_partial_off = -1UL;
 
 	return mm;
 }
@@ -1616,6 +1926,7 @@ void _intel_vgpu_mm_release(struct kref *mm_ref)
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);
+		mm->ggtt_mm.last_partial_off = -1UL;
 	}
 
 	vgpu_free_mm(mm);
@@ -1868,6 +2179,62 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 	memcpy((void *)&e.val64 + (off & (info->gtt_entry_size - 1)), p_data,
 			bytes);
 
+	/* If ggtt entry size is 8 bytes, and it's split into two 4 bytes
+	 * write, we assume the two 4 bytes writes are consecutive.
+	 * Otherwise, we abort and report error
+	 */
+	if (bytes < info->gtt_entry_size) {
+		if (ggtt_mm->ggtt_mm.last_partial_off == -1UL) {
+			/* the first partial part*/
+			ggtt_mm->ggtt_mm.last_partial_off = off;
+			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+			return 0;
+		} else if ((g_gtt_index ==
+				(ggtt_mm->ggtt_mm.last_partial_off >>
+				info->gtt_entry_size_shift)) &&
+			(off !=	ggtt_mm->ggtt_mm.last_partial_off)) {
+			/* the second partial part */
+
+			int last_off = ggtt_mm->ggtt_mm.last_partial_off &
+				(info->gtt_entry_size - 1);
+
+			memcpy((void *)&e.val64 + last_off,
+				(void *)&ggtt_mm->ggtt_mm.last_partial_data +
+				last_off, bytes);
+
+			ggtt_mm->ggtt_mm.last_partial_off = -1UL;
+		} else {
+			int last_offset;
+
+			gvt_vgpu_err("failed to populate guest ggtt entry: abnormal ggtt entry write sequence, last_partial_off=%lx, offset=%x, bytes=%d, ggtt entry size=%d\n",
+					ggtt_mm->ggtt_mm.last_partial_off, off,
+					bytes, info->gtt_entry_size);
+
+			/* set host ggtt entry to scratch page and clear
+			 * virtual ggtt entry as not present for last
+			 * partially write offset
+			 */
+			last_offset = ggtt_mm->ggtt_mm.last_partial_off &
+					(~(info->gtt_entry_size - 1));
+
+			ggtt_get_host_entry(ggtt_mm, &m, last_offset);
+			ggtt_invalidate_pte(vgpu, &m);
+			ops->set_pfn(&m, gvt->gtt.scratch_mfn);
+			ops->clear_present(&m);
+			ggtt_set_host_entry(ggtt_mm, &m, last_offset);
+			ggtt_invalidate(gvt->dev_priv);
+
+			ggtt_get_guest_entry(ggtt_mm, &e, last_offset);
+			ops->clear_present(&e);
+			ggtt_set_guest_entry(ggtt_mm, &e, last_offset);
+
+			ggtt_mm->ggtt_mm.last_partial_off = off;
+			ggtt_mm->ggtt_mm.last_partial_data = e.val64;
+
+			return 0;
+		}
+	}
+
 	if (ops->test_present(&e)) {
 		gfn = ops->get_pfn(&e);
 		m = e;
@@ -1881,7 +2248,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		}
 
 		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn,
-							      &dma_addr);
+							PAGE_SIZE, &dma_addr);
 		if (ret) {
 			gvt_vgpu_err("fail to populate guest ggtt entry\n");
 			/* guest driver may read/write the entry when partial
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 3792f2b7f4ff..7a9b36176efb 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -63,6 +63,12 @@ struct intel_gvt_gtt_pte_ops {
 	void (*clear_present)(struct intel_gvt_gtt_entry *e);
 	void (*set_present)(struct intel_gvt_gtt_entry *e);
 	bool (*test_pse)(struct intel_gvt_gtt_entry *e);
+	void (*clear_pse)(struct intel_gvt_gtt_entry *e);
+	bool (*test_ips)(struct intel_gvt_gtt_entry *e);
+	void (*clear_ips)(struct intel_gvt_gtt_entry *e);
+	bool (*test_64k_splited)(struct intel_gvt_gtt_entry *e);
+	void (*clear_64k_splited)(struct intel_gvt_gtt_entry *e);
+	void (*set_64k_splited)(struct intel_gvt_gtt_entry *e);
 	void (*set_pfn)(struct intel_gvt_gtt_entry *e, unsigned long pfn);
 	unsigned long (*get_pfn)(struct intel_gvt_gtt_entry *e);
 };
@@ -95,6 +101,7 @@ typedef enum {
 	GTT_TYPE_GGTT_PTE,
 
 	GTT_TYPE_PPGTT_PTE_4K_ENTRY,
+	GTT_TYPE_PPGTT_PTE_64K_ENTRY,
 	GTT_TYPE_PPGTT_PTE_2M_ENTRY,
 	GTT_TYPE_PPGTT_PTE_1G_ENTRY,
 
@@ -150,6 +157,8 @@ struct intel_vgpu_mm {
 		} ppgtt_mm;
 		struct {
 			void *virtual_ggtt;
+			unsigned long last_partial_off;
+			u64 last_partial_data;
 		} ggtt_mm;
 	};
 };
@@ -220,6 +229,7 @@ struct intel_vgpu_ppgtt_spt {
 
 	struct {
 		intel_gvt_gtt_type_t type;
+		bool pde_ips; /* for 64KB PTEs */
 		void *vaddr;
 		struct page *page;
 		unsigned long mfn;
@@ -227,6 +237,7 @@ struct intel_vgpu_ppgtt_spt {
 
 	struct {
 		intel_gvt_gtt_type_t type;
+		bool pde_ips; /* for 64KB PTEs */
 		unsigned long gfn;
 		unsigned long write_cnt;
 		struct intel_vgpu_oos_page *oos_page;
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 4e65266e7b95..712f9d14e720 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -468,3 +468,7 @@ out_clean_idr:
 	kfree(gvt);
 	return ret;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
+MODULE_SOFTDEP("pre: kvmgt");
+#endif
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index de2a3a2580be..9a9671522774 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -274,6 +274,8 @@ struct intel_gvt_mmio {
 #define F_CMD_ACCESSED	(1 << 5)
 /* This reg could be accessed by unaligned address */
 #define F_UNALIGN	(1 << 6)
+/* This reg is saved/restored in context */
+#define F_IN_CTX	(1 << 7)
 
 	struct gvt_mmio_block *mmio_block;
 	unsigned int num_mmio_block;
@@ -655,6 +657,33 @@ static inline bool intel_gvt_mmio_has_mode_mask(
 	return gvt->mmio.mmio_attribute[offset >> 2] & F_MODE_MASK;
 }
 
+/**
+ * intel_gvt_mmio_is_in_ctx - check if a MMIO has in-ctx mask
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ * Returns:
+ * True if a MMIO has a in-context mask, false if it isn't.
+ *
+ */
+static inline bool intel_gvt_mmio_is_in_ctx(
+			struct intel_gvt *gvt, unsigned int offset)
+{
+	return gvt->mmio.mmio_attribute[offset >> 2] & F_IN_CTX;
+}
+
+/**
+ * intel_gvt_mmio_set_in_ctx - mask a MMIO in logical context
+ * @gvt: a GVT device
+ * @offset: register offset
+ *
+ */
+static inline void intel_gvt_mmio_set_in_ctx(
+			struct intel_gvt *gvt, unsigned int offset)
+{
+	gvt->mmio.mmio_attribute[offset >> 2] |= F_IN_CTX;
+}
+
 int intel_gvt_debugfs_add_vgpu(struct intel_vgpu *vgpu);
 void intel_gvt_debugfs_remove_vgpu(struct intel_vgpu *vgpu);
 int intel_gvt_debugfs_init(struct intel_gvt *gvt);
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index e39492aaff6c..7a58ca555197 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -210,6 +210,31 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int gamw_echo_dev_rw_ia_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 ips = (*(u32 *)p_data) & GAMW_ECO_ENABLE_64K_IPS_FIELD;
+
+	if (INTEL_GEN(vgpu->gvt->dev_priv) <= 10) {
+		if (ips == GAMW_ECO_ENABLE_64K_IPS_FIELD)
+			gvt_dbg_core("vgpu%d: ips enabled\n", vgpu->id);
+		else if (!ips)
+			gvt_dbg_core("vgpu%d: ips disabled\n", vgpu->id);
+		else {
+			/* All engines must be enabled together for vGPU,
+			 * since we don't know which engine the ppgtt will
+			 * bind to when shadowing.
+			 */
+			gvt_vgpu_err("Unsupported IPS setting %x, cannot enable 64K gtt.\n",
+				     ips);
+			return -EINVAL;
+		}
+	}
+
+	write_vreg(vgpu, offset, p_data, bytes);
+	return 0;
+}
+
 static int fence_mmio_read(struct intel_vgpu *vgpu, unsigned int off,
 		void *p_data, unsigned int bytes)
 {
@@ -1564,6 +1589,13 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	vgpu_vreg(vgpu, offset) = 0;
+	return 0;
+}
+
 static int mmio_read_from_hw(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
@@ -1774,7 +1806,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_DH(GEN8_GAMW_ECO_DEV_RW_IA, D_BDW_PLUS, NULL,
+		gamw_echo_dev_rw_ia_write);
+
 	MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
@@ -3160,6 +3194,9 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT);
 	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT);
 
+	MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
+	MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
+
 	MMIO_D(RC6_CTX_BASE, D_BXT);
 
 	MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT);
@@ -3351,6 +3388,30 @@ int intel_vgpu_default_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 }
 
 /**
+ * intel_vgpu_mask_mmio_write - write mask register
+ * @vgpu: a vGPU
+ * @offset: access offset
+ * @p_data: write data buffer
+ * @bytes: access data length
+ *
+ * Returns:
+ * Zero on success, negative error code if failed.
+ */
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+		void *p_data, unsigned int bytes)
+{
+	u32 mask, old_vreg;
+
+	old_vreg = vgpu_vreg(vgpu, offset);
+	write_vreg(vgpu, offset, p_data, bytes);
+	mask = vgpu_vreg(vgpu, offset) >> 16;
+	vgpu_vreg(vgpu, offset) = (old_vreg & ~mask) |
+				(vgpu_vreg(vgpu, offset) & mask);
+
+	return 0;
+}
+
+/**
  * intel_gvt_in_force_nonpriv_whitelist - if a mmio is in whitelist to be
  * force-nopriv register
  *
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index f6dd9f717888..5af11cf1b482 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -53,7 +53,7 @@ struct intel_gvt_mpt {
 	unsigned long (*gfn_to_mfn)(unsigned long handle, unsigned long gfn);
 
 	int (*dma_map_guest_page)(unsigned long handle, unsigned long gfn,
-				  dma_addr_t *dma_addr);
+				  unsigned long size, dma_addr_t *dma_addr);
 	void (*dma_unmap_guest_page)(unsigned long handle, dma_addr_t dma_addr);
 
 	int (*map_gfn_to_mfn)(unsigned long handle, unsigned long gfn,
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index df4e4a07db3d..718ab307a500 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -94,6 +94,7 @@ struct gvt_dma {
 	struct rb_node dma_addr_node;
 	gfn_t gfn;
 	dma_addr_t dma_addr;
+	unsigned long size;
 	struct kref ref;
 };
 
@@ -106,22 +107,83 @@ static int kvmgt_guest_init(struct mdev_device *mdev);
 static void intel_vgpu_release_work(struct work_struct *work);
 static bool kvmgt_guest_exit(struct kvmgt_guest_info *info);
 
+static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		unsigned long size)
+{
+	int total_pages;
+	int npage;
+	int ret;
+
+	total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+
+	for (npage = 0; npage < total_pages; npage++) {
+		unsigned long cur_gfn = gfn + npage;
+
+		ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1);
+		WARN_ON(ret != 1);
+	}
+}
+
+/* Pin a normal or compound guest page for dma. */
+static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		unsigned long size, struct page **page)
+{
+	unsigned long base_pfn = 0;
+	int total_pages;
+	int npage;
+	int ret;
+
+	total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+	/*
+	 * We pin the pages one-by-one to avoid allocating a big arrary
+	 * on stack to hold pfns.
+	 */
+	for (npage = 0; npage < total_pages; npage++) {
+		unsigned long cur_gfn = gfn + npage;
+		unsigned long pfn;
+
+		ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1,
+				     IOMMU_READ | IOMMU_WRITE, &pfn);
+		if (ret != 1) {
+			gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n",
+				     cur_gfn, ret);
+			goto err;
+		}
+
+		if (!pfn_valid(pfn)) {
+			gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
+			npage++;
+			ret = -EFAULT;
+			goto err;
+		}
+
+		if (npage == 0)
+			base_pfn = pfn;
+		else if (base_pfn + npage != pfn) {
+			gvt_vgpu_err("The pages are not continuous\n");
+			ret = -EINVAL;
+			npage++;
+			goto err;
+		}
+	}
+
+	*page = pfn_to_page(base_pfn);
+	return 0;
+err:
+	gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);
+	return ret;
+}
+
 static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn,
-		dma_addr_t *dma_addr)
+		dma_addr_t *dma_addr, unsigned long size)
 {
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
-	struct page *page;
-	unsigned long pfn;
+	struct page *page = NULL;
 	int ret;
 
-	/* Pin the page first. */
-	ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1,
-			     IOMMU_READ | IOMMU_WRITE, &pfn);
-	if (ret != 1) {
-		gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n",
-			     gfn, ret);
-		return -EINVAL;
-	}
+	ret = gvt_pin_guest_page(vgpu, gfn, size, &page);
+	if (ret)
+		return ret;
 
 	if (!pfn_valid(pfn)) {
 		gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
@@ -130,27 +192,24 @@ static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn,
 	}
 
 	/* Setup DMA mapping. */
-	page = pfn_to_page(pfn);
-	*dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE,
-				 PCI_DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, *dma_addr)) {
-		gvt_vgpu_err("DMA mapping failed for gfn 0x%lx\n", gfn);
-		vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-		return -ENOMEM;
+	*dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL);
+	ret = dma_mapping_error(dev, *dma_addr);
+	if (ret) {
+		gvt_vgpu_err("DMA mapping failed for pfn 0x%lx, ret %d\n",
+			     page_to_pfn(page), ret);
+		gvt_unpin_guest_page(vgpu, gfn, size);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void gvt_dma_unmap_page(struct intel_vgpu *vgpu, unsigned long gfn,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long size)
 {
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
-	int ret;
 
-	dma_unmap_page(dev, dma_addr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-	WARN_ON(ret != 1);
+	dma_unmap_page(dev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
+	gvt_unpin_guest_page(vgpu, gfn, size);
 }
 
 static struct gvt_dma *__gvt_cache_find_dma_addr(struct intel_vgpu *vgpu,
@@ -191,7 +250,7 @@ static struct gvt_dma *__gvt_cache_find_gfn(struct intel_vgpu *vgpu, gfn_t gfn)
 }
 
 static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long size)
 {
 	struct gvt_dma *new, *itr;
 	struct rb_node **link, *parent = NULL;
@@ -203,6 +262,7 @@ static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
 	new->vgpu = vgpu;
 	new->gfn = gfn;
 	new->dma_addr = dma_addr;
+	new->size = size;
 	kref_init(&new->ref);
 
 	/* gfn_cache maps gfn to struct gvt_dma. */
@@ -260,7 +320,7 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu)
 			break;
 		}
 		dma = rb_entry(node, struct gvt_dma, gfn_node);
-		gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr);
+		gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr, dma->size);
 		__gvt_cache_remove_entry(vgpu, dma);
 		mutex_unlock(&vgpu->vdev.cache_lock);
 	}
@@ -515,7 +575,8 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
 			if (!entry)
 				continue;
 
-			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr);
+			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr,
+					   entry->size);
 			__gvt_cache_remove_entry(vgpu, entry);
 		}
 		mutex_unlock(&vgpu->vdev.cache_lock);
@@ -1648,7 +1709,7 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
 }
 
 int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
-		dma_addr_t *dma_addr)
+		unsigned long size, dma_addr_t *dma_addr)
 {
 	struct kvmgt_guest_info *info;
 	struct intel_vgpu *vgpu;
@@ -1665,11 +1726,11 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
 
 	entry = __gvt_cache_find_gfn(info->vgpu, gfn);
 	if (!entry) {
-		ret = gvt_dma_map_page(vgpu, gfn, dma_addr);
+		ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size);
 		if (ret)
 			goto err_unlock;
 
-		ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr);
+		ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size);
 		if (ret)
 			goto err_unmap;
 	} else {
@@ -1681,7 +1742,7 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
 	return 0;
 
 err_unmap:
-	gvt_dma_unmap_page(vgpu, gfn, *dma_addr);
+	gvt_dma_unmap_page(vgpu, gfn, *dma_addr, size);
 err_unlock:
 	mutex_unlock(&info->vgpu->vdev.cache_lock);
 	return ret;
@@ -1691,7 +1752,8 @@ static void __gvt_dma_release(struct kref *ref)
 {
 	struct gvt_dma *entry = container_of(ref, typeof(*entry), ref);
 
-	gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr);
+	gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr,
+			   entry->size);
 	__gvt_cache_remove_entry(entry->vgpu, entry);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index e474188b46d2..1ffc69eba30e 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -99,4 +99,6 @@ bool intel_gvt_in_force_nonpriv_whitelist(struct intel_gvt *gvt,
 int intel_vgpu_mmio_reg_rw(struct intel_vgpu *vgpu, unsigned int offset,
 			   void *pdata, unsigned int bytes, bool is_read);
 
+int intel_vgpu_mask_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
+				  void *p_data, unsigned int bytes);
 #endif
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 20be9a92600f..42e1e6bdcc2c 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -587,7 +587,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt)
 
 	for (mmio = gvt->engine_mmio_list.mmio;
 	     i915_mmio_reg_valid(mmio->reg); mmio++) {
-		if (mmio->in_context)
+		if (mmio->in_context) {
 			gvt->engine_mmio_list.ctx_mmio_count[mmio->ring_id]++;
+			intel_gvt_mmio_set_in_ctx(gvt, mmio->reg.reg);
+		}
 	}
 }
diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h
index 32ffcd566cdd..67f19992b226 100644
--- a/drivers/gpu/drm/i915/gvt/mpt.h
+++ b/drivers/gpu/drm/i915/gvt/mpt.h
@@ -230,17 +230,18 @@ static inline unsigned long intel_gvt_hypervisor_gfn_to_mfn(
 /**
  * intel_gvt_hypervisor_dma_map_guest_page - setup dma map for guest page
  * @vgpu: a vGPU
- * @gpfn: guest pfn
+ * @gfn: guest pfn
+ * @size: page size
  * @dma_addr: retrieve allocated dma addr
  *
  * Returns:
  * 0 on success, negative error code if failed.
  */
 static inline int intel_gvt_hypervisor_dma_map_guest_page(
-		struct intel_vgpu *vgpu, unsigned long gfn,
+		struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size,
 		dma_addr_t *dma_addr)
 {
-	return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn,
+	return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn, size,
 						      dma_addr);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 928818f218f7..b0e566956b8d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -476,7 +476,11 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			i915_gem_obj_finish_shmem_access(bb->obj);
 			bb->accessing = false;
 
-			i915_vma_move_to_active(bb->vma, workload->req, 0);
+			ret = i915_vma_move_to_active(bb->vma,
+						      workload->req,
+						      0);
+			if (ret)
+				goto err;
 		}
 	}
 	return 0;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 83a43970783f..f6fa916517c3 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -46,6 +46,7 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 
 	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) = VGT_CAPS_FULL_48BIT_PPGTT;
 	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HWSP_EMULATION;
+	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HUGE_GTT;
 
 	vgpu_vreg_t(vgpu, vgtif_reg(avail_rs.mappable_gmadr.base)) =
 		vgpu_aperture_gmadr_base(vgpu);
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c400f42a54ec..b3aefd623557 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1659,11 +1659,6 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	else
 		seq_printf(m, "FBC disabled: %s\n", fbc->no_fbc_reason);
 
-	if (fbc->work.scheduled)
-		seq_printf(m, "FBC worker scheduled on vblank %llu, now %llu\n",
-			   fbc->work.scheduled_vblank,
-			   drm_crtc_vblank_count(&fbc->crtc->base));
-
 	if (intel_fbc_is_active(dev_priv)) {
 		u32 mask;
 
@@ -2597,31 +2592,9 @@ static const struct file_operations i915_guc_log_relay_fops = {
 	.release = i915_guc_log_relay_release,
 };
 
-static const char *psr2_live_status(u32 val)
-{
-	static const char * const live_status[] = {
-		"IDLE",
-		"CAPTURE",
-		"CAPTURE_FS",
-		"SLEEP",
-		"BUFON_FW",
-		"ML_UP",
-		"SU_STANDBY",
-		"FAST_SLEEP",
-		"DEEP_SLEEP",
-		"BUF_ON",
-		"TG_ON"
-	};
-
-	val = (val & EDP_PSR2_STATUS_STATE_MASK) >> EDP_PSR2_STATUS_STATE_SHIFT;
-	if (val < ARRAY_SIZE(live_status))
-		return live_status[val];
-
-	return "unknown";
-}
-
-static const char *psr_sink_status(u8 val)
+static int i915_psr_sink_status_show(struct seq_file *m, void *data)
 {
+	u8 val;
 	static const char * const sink_status[] = {
 		"inactive",
 		"transition to active, capture and display",
@@ -2630,14 +2603,79 @@ static const char *psr_sink_status(u8 val)
 		"transition to inactive, capture and display, timing re-sync",
 		"reserved",
 		"reserved",
-		"sink internal error"
+		"sink internal error",
 	};
+	struct drm_connector *connector = m->private;
+	struct intel_dp *intel_dp =
+		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
 
-	val &= DP_PSR_SINK_STATE_MASK;
-	if (val < ARRAY_SIZE(sink_status))
-		return sink_status[val];
+	if (connector->status != connector_status_connected)
+		return -ENODEV;
 
-	return "unknown";
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) == 1) {
+		const char *str = "unknown";
+
+		val &= DP_PSR_SINK_STATE_MASK;
+		if (val < ARRAY_SIZE(sink_status))
+			str = sink_status[val];
+		seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, str);
+	} else {
+		DRM_ERROR("dpcd read (at %u) failed\n", DP_PSR_STATUS);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(i915_psr_sink_status);
+
+static void
+psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
+{
+	u32 val, psr_status;
+
+	if (dev_priv->psr.psr2_enabled) {
+		static const char * const live_status[] = {
+			"IDLE",
+			"CAPTURE",
+			"CAPTURE_FS",
+			"SLEEP",
+			"BUFON_FW",
+			"ML_UP",
+			"SU_STANDBY",
+			"FAST_SLEEP",
+			"DEEP_SLEEP",
+			"BUF_ON",
+			"TG_ON"
+		};
+		psr_status = I915_READ(EDP_PSR2_STATUS);
+		val = (psr_status & EDP_PSR2_STATUS_STATE_MASK) >>
+			EDP_PSR2_STATUS_STATE_SHIFT;
+		if (val < ARRAY_SIZE(live_status)) {
+			seq_printf(m, "Source PSR status: 0x%x [%s]\n",
+				   psr_status, live_status[val]);
+			return;
+		}
+	} else {
+		static const char * const live_status[] = {
+			"IDLE",
+			"SRDONACK",
+			"SRDENT",
+			"BUFOFF",
+			"BUFON",
+			"AUXACK",
+			"SRDOFFACK",
+			"SRDENT_ON",
+		};
+		psr_status = I915_READ(EDP_PSR_STATUS);
+		val = (psr_status & EDP_PSR_STATUS_STATE_MASK) >>
+			EDP_PSR_STATUS_STATE_SHIFT;
+		if (val < ARRAY_SIZE(live_status)) {
+			seq_printf(m, "Source PSR status: 0x%x [%s]\n",
+				   psr_status, live_status[val]);
+			return;
+		}
+	}
+
+	seq_printf(m, "Source PSR status: 0x%x [%s]\n", psr_status, "unknown");
 }
 
 static int i915_edp_psr_status(struct seq_file *m, void *data)
@@ -2681,21 +2719,8 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 		seq_printf(m, "Performance_Counter: %u\n", psrperf);
 	}
-	if (dev_priv->psr.psr2_enabled) {
-		u32 psr2 = I915_READ(EDP_PSR2_STATUS);
-
-		seq_printf(m, "EDP_PSR2_STATUS: %x [%s]\n",
-			   psr2, psr2_live_status(psr2));
-	}
 
-	if (dev_priv->psr.enabled) {
-		struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux;
-		u8 val;
-
-		if (drm_dp_dpcd_readb(aux, DP_PSR_STATUS, &val) == 1)
-			seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val,
-				   psr_sink_status(val));
-	}
+	psr_source_status(dev_priv, m);
 	mutex_unlock(&dev_priv->psr.lock);
 
 	if (READ_ONCE(dev_priv->psr.debug)) {
@@ -2742,86 +2767,6 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops,
 			i915_edp_psr_debug_get, i915_edp_psr_debug_set,
 			"%llu\n");
 
-static int i915_sink_crc(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_connector *connector;
-	struct drm_connector_list_iter conn_iter;
-	struct intel_dp *intel_dp = NULL;
-	struct drm_modeset_acquire_ctx ctx;
-	int ret;
-	u8 crc[6];
-
-	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
-
-	drm_connector_list_iter_begin(dev, &conn_iter);
-
-	for_each_intel_connector_iter(connector, &conn_iter) {
-		struct drm_crtc *crtc;
-		struct drm_connector_state *state;
-		struct intel_crtc_state *crtc_state;
-
-		if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP)
-			continue;
-
-retry:
-		ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx);
-		if (ret)
-			goto err;
-
-		state = connector->base.state;
-		if (!state->best_encoder)
-			continue;
-
-		crtc = state->crtc;
-		ret = drm_modeset_lock(&crtc->mutex, &ctx);
-		if (ret)
-			goto err;
-
-		crtc_state = to_intel_crtc_state(crtc->state);
-		if (!crtc_state->base.active)
-			continue;
-
-		/*
-		 * We need to wait for all crtc updates to complete, to make
-		 * sure any pending modesets and plane updates are completed.
-		 */
-		if (crtc_state->base.commit) {
-			ret = wait_for_completion_interruptible(&crtc_state->base.commit->hw_done);
-
-			if (ret)
-				goto err;
-		}
-
-		intel_dp = enc_to_intel_dp(state->best_encoder);
-
-		ret = intel_dp_sink_crc(intel_dp, crtc_state, crc);
-		if (ret)
-			goto err;
-
-		seq_printf(m, "%02x%02x%02x%02x%02x%02x\n",
-			   crc[0], crc[1], crc[2],
-			   crc[3], crc[4], crc[5]);
-		goto out;
-
-err:
-		if (ret == -EDEADLK) {
-			ret = drm_modeset_backoff(&ctx);
-			if (!ret)
-				goto retry;
-		}
-		goto out;
-	}
-	ret = -ENODEV;
-out:
-	drm_connector_list_iter_end(&conn_iter);
-	drm_modeset_drop_locks(&ctx);
-	drm_modeset_acquire_fini(&ctx);
-
-	return ret;
-}
-
 static int i915_energy_uJ(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -4086,7 +4031,8 @@ fault_irq_set(struct drm_i915_private *i915,
 
 	err = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_LOCKED |
-				     I915_WAIT_INTERRUPTIBLE);
+				     I915_WAIT_INTERRUPTIBLE,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		goto err_unlock;
 
@@ -4191,7 +4137,8 @@ i915_drop_caches_set(void *data, u64 val)
 		if (val & DROP_ACTIVE)
 			ret = i915_gem_wait_for_idle(dev_priv,
 						     I915_WAIT_INTERRUPTIBLE |
-						     I915_WAIT_LOCKED);
+						     I915_WAIT_LOCKED,
+						     MAX_SCHEDULE_TIMEOUT);
 
 		if (val & DROP_RETIRE)
 			i915_retire_requests(dev_priv);
@@ -4765,7 +4712,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
-	{"i915_sink_crc_eDP1", i915_sink_crc, 0},
 	{"i915_energy_uJ", i915_energy_uJ, 0},
 	{"i915_runtime_pm_status", i915_runtime_pm_status, 0},
 	{"i915_power_domain_info", i915_power_domain_info, 0},
@@ -4799,7 +4745,6 @@ static const struct i915_debugfs_files {
 #endif
 	{"i915_fifo_underrun_reset", &i915_fifo_underrun_reset_ops},
 	{"i915_next_seqno", &i915_next_seqno_fops},
-	{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
 	{"i915_spr_wm_latency", &i915_spr_wm_latency_fops},
 	{"i915_cur_wm_latency", &i915_cur_wm_latency_fops},
@@ -4819,7 +4764,7 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 {
 	struct drm_minor *minor = dev_priv->drm.primary;
 	struct dentry *ent;
-	int ret, i;
+	int i;
 
 	ent = debugfs_create_file("i915_forcewake_user", S_IRUSR,
 				  minor->debugfs_root, to_i915(minor->dev),
@@ -4827,10 +4772,6 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 	if (!ent)
 		return -ENOMEM;
 
-	ret = intel_pipe_crc_create(minor);
-	if (ret)
-		return ret;
-
 	for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) {
 		ent = debugfs_create_file(i915_debugfs_files[i].name,
 					  S_IRUGO | S_IWUSR,
@@ -4952,9 +4893,12 @@ int i915_debugfs_connector_add(struct drm_connector *connector)
 		debugfs_create_file("i915_dpcd", S_IRUGO, root,
 				    connector, &i915_dpcd_fops);
 
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		debugfs_create_file("i915_panel_timings", S_IRUGO, root,
 				    connector, &i915_panel_fops);
+		debugfs_create_file("i915_psr_sink_status", S_IRUGO, root,
+				    connector, &i915_psr_sink_status_fops);
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index beb0951001ce..f8cfd16be534 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -104,8 +104,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV",
-		   __builtin_return_address(0), &vaf);
+	if (is_error)
+		dev_printk(level, kdev, "%pV", &vaf);
+	else
+		dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV",
+			   __builtin_return_address(0), &vaf);
+
+	va_end(args);
 
 	if (is_error && !shown_bug_once) {
 		/*
@@ -117,8 +122,6 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 			dev_notice(kdev, "%s", FDO_BUG_MSG);
 		shown_bug_once = true;
 	}
-
-	va_end(args);
 }
 
 /* Map PCH device id to PCH type, or PCH_NONE if unknown. */
@@ -679,7 +682,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	ret = i915_gem_init(dev_priv);
 	if (ret)
-		goto cleanup_irq;
+		goto cleanup_modeset;
 
 	intel_setup_overlay(dev_priv);
 
@@ -699,6 +702,8 @@ cleanup_gem:
 	if (i915_gem_suspend(dev_priv))
 		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
 	i915_gem_fini(dev_priv);
+cleanup_modeset:
+	intel_modeset_cleanup(dev);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 	intel_teardown_gmbus(dev_priv);
@@ -895,7 +900,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 	spin_lock_init(&dev_priv->uncore.lock);
 
 	mutex_init(&dev_priv->sb_lock);
-	mutex_init(&dev_priv->modeset_restore_lock);
 	mutex_init(&dev_priv->av_mutex);
 	mutex_init(&dev_priv->wm.wm_mutex);
 	mutex_init(&dev_priv->pps_mutex);
@@ -1149,8 +1153,6 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	intel_uncore_sanitize(dev_priv);
 
-	intel_opregion_setup(dev_priv);
-
 	i915_gem_load_init_fences(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
@@ -1165,6 +1167,12 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 	 * get lost on g4x as well, and interrupt delivery seems to stay
 	 * properly dead afterwards. So we'll just disable them for all
 	 * pre-gen5 chipsets.
+	 *
+	 * dp aux and gmbus irq on gen4 seems to be able to generate legacy
+	 * interrupts even when in MSI mode. This results in spurious
+	 * interrupt warnings if the legacy irq no. is shared with another
+	 * device. The kernel then disables that interrupt source and so
+	 * prevents the other device from working properly.
 	 */
 	if (INTEL_GEN(dev_priv) >= 5) {
 		if (pci_enable_msi(pdev) < 0)
@@ -1173,10 +1181,16 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	ret = intel_gvt_init(dev_priv);
 	if (ret)
-		goto err_ggtt;
+		goto err_msi;
+
+	intel_opregion_setup(dev_priv);
 
 	return 0;
 
+err_msi:
+	if (pdev->msi_enabled)
+		pci_disable_msi(pdev);
+	pm_qos_remove_request(&dev_priv->pm_qos);
 err_ggtt:
 	i915_ggtt_cleanup_hw(dev_priv);
 err_perf:
@@ -1409,6 +1423,7 @@ out_fini:
 	drm_dev_fini(&dev_priv->drm);
 out_free:
 	kfree(dev_priv);
+	pci_set_drvdata(pdev, NULL);
 	return ret;
 }
 
@@ -1554,11 +1569,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	pci_power_t opregion_target_state;
 
-	/* ignore lid events during suspend */
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	dev_priv->modeset_restore = MODESET_SUSPENDED;
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-
 	disable_rpm_wakeref_asserts(dev_priv);
 
 	/* We do a lot of poking in a lot of registers, make sure they work
@@ -1571,7 +1581,7 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_display_suspend(dev);
 
-	intel_dp_mst_suspend(dev);
+	intel_dp_mst_suspend(dev_priv);
 
 	intel_runtime_pm_disable_interrupts(dev_priv);
 	intel_hpd_cancel_work(dev_priv);
@@ -1736,7 +1746,7 @@ static int i915_drm_resume(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	intel_dp_mst_resume(dev);
+	intel_dp_mst_resume(dev_priv);
 
 	intel_display_resume(dev);
 
@@ -1754,10 +1764,6 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false);
 
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	dev_priv->modeset_restore = MODESET_DONE;
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-
 	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 
 	enable_rpm_wakeref_asserts(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f4751b383858..0f49f9988dfa 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -86,8 +86,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180620"
-#define DRIVER_TIMESTAMP	1529529048
+#define DRIVER_DATE		"20180719"
+#define DRIVER_TIMESTAMP	1532015279
 
 /* 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
@@ -299,7 +299,6 @@ struct i915_hotplug {
 	u32 event_bits;
 	struct delayed_work reenable_work;
 
-	struct intel_digital_port *irq_port[I915_MAX_PORTS];
 	u32 long_port_mask;
 	u32 short_port_mask;
 	struct work_struct dig_port_work;
@@ -512,6 +511,7 @@ struct intel_fbc {
 
 	bool enabled;
 	bool active;
+	bool flip_pending;
 
 	bool underrun_detected;
 	struct work_struct underrun_work;
@@ -579,12 +579,6 @@ struct intel_fbc {
 		unsigned int gen9_wa_cfb_stride;
 	} params;
 
-	struct intel_fbc_work {
-		bool scheduled;
-		u64 scheduled_vblank;
-		struct work_struct work;
-	} work;
-
 	const char *no_fbc_reason;
 };
 
@@ -631,14 +625,6 @@ struct i915_psr {
 	bool debug;
 	ktime_t last_entry_attempt;
 	ktime_t last_exit;
-
-	void (*enable_source)(struct intel_dp *,
-			      const struct intel_crtc_state *);
-	void (*disable_source)(struct intel_dp *,
-			       const struct intel_crtc_state *);
-	void (*enable_sink)(struct intel_dp *);
-	void (*activate)(struct intel_dp *);
-	void (*setup_vsc)(struct intel_dp *, const struct intel_crtc_state *);
 };
 
 enum intel_pch {
@@ -663,6 +649,7 @@ enum intel_sbi_destination {
 #define QUIRK_BACKLIGHT_PRESENT (1<<3)
 #define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
 #define QUIRK_INCREASE_T12_DELAY (1<<6)
+#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
 
 struct intel_fbdev;
 struct intel_fbc_work;
@@ -965,7 +952,7 @@ struct i915_gem_mm {
 	/**
 	 * Small stash of WC pages
 	 */
-	struct pagevec wc_stash;
+	struct pagestash wc_stash;
 
 	/**
 	 * tmpfs instance used for shmem backed objects
@@ -1015,12 +1002,6 @@ struct i915_gem_mm {
 
 #define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
 
-enum modeset_restore {
-	MODESET_ON_LID_OPEN,
-	MODESET_DONE,
-	MODESET_SUSPENDED,
-};
-
 #define DP_AUX_A 0x40
 #define DP_AUX_B 0x10
 #define DP_AUX_C 0x20
@@ -1284,20 +1265,11 @@ enum intel_pipe_crc_source {
 	INTEL_PIPE_CRC_SOURCE_MAX,
 };
 
-struct intel_pipe_crc_entry {
-	uint32_t frame;
-	uint32_t crc[5];
-};
-
 #define INTEL_PIPE_CRC_ENTRIES_NR	128
 struct intel_pipe_crc {
 	spinlock_t lock;
-	bool opened;		/* exclusive access to the result file */
-	struct intel_pipe_crc_entry *entries;
-	enum intel_pipe_crc_source source;
-	int head, tail;
-	wait_queue_head_t wq;
 	int skipped;
+	enum intel_pipe_crc_source source;
 };
 
 struct i915_frontbuffer_tracking {
@@ -1752,12 +1724,9 @@ struct drm_i915_private {
 
 	unsigned long quirks;
 
-	enum modeset_restore modeset_restore;
-	struct mutex modeset_restore_lock;
 	struct drm_atomic_state *modeset_restore_state;
 	struct drm_modeset_acquire_ctx reset_ctx;
 
-	struct list_head vm_list; /* Global list of all address spaces */
 	struct i915_ggtt ggtt; /* VM representing the global address space */
 
 	struct i915_gem_mm mm;
@@ -2326,6 +2295,7 @@ intel_info(const struct drm_i915_private *dev_priv)
 }
 
 #define INTEL_INFO(dev_priv)	intel_info((dev_priv))
+#define DRIVER_CAPS(dev_priv)	(&(dev_priv)->caps)
 
 #define INTEL_GEN(dev_priv)	((dev_priv)->info.gen)
 #define INTEL_DEVID(dev_priv)	((dev_priv)->info.device_id)
@@ -2578,17 +2548,10 @@ intel_info(const struct drm_i915_private *dev_priv)
 	(IS_CANNONLAKE(dev_priv) || \
 	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
 
-/*
- * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
- * even when in MSI mode. This results in spurious interrupt warnings if the
- * legacy irq no. is shared with another device. The kernel then disables that
- * interrupt source and so prevents the other device from working properly.
- *
- * Since we don't enable MSI anymore on gen4, we can always use GMBUS/AUX
- * interrupts.
- */
-#define HAS_AUX_IRQ(dev_priv)   true
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
+#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
+					IS_GEMINILAKE(dev_priv) || \
+					IS_KABYLAKE(dev_priv))
 
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
@@ -2771,8 +2734,6 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 void intel_hpd_init(struct drm_i915_private *dev_priv);
 void intel_hpd_init_work(struct drm_i915_private *dev_priv);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
-enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
-				enum hpd_pin pin);
 enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
 				   enum port port);
 bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
@@ -3119,9 +3080,6 @@ i915_gem_obj_finish_shmem_access(struct drm_i915_gem_object *obj)
 }
 
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
-void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct i915_request *rq,
-			     unsigned int flags);
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
@@ -3189,7 +3147,7 @@ void i915_gem_init_swizzling(struct drm_i915_private *dev_priv);
 void i915_gem_fini(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_engines(struct drm_i915_private *dev_priv);
 int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
-			   unsigned int flags);
+			   unsigned int flags, long timeout);
 int __must_check 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);
@@ -3339,7 +3297,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *i915,
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915);
 void i915_gem_shrinker_register(struct drm_i915_private *i915);
 void i915_gem_shrinker_unregister(struct drm_i915_private *i915);
-
+void i915_gem_shrinker_taints_mutex(struct mutex *mutex);
 
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 858d188dd33b..fcc73a6ab503 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -802,7 +802,7 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv)
 	 * that was!).
 	 */
 
-	wmb();
+	i915_gem_chipset_flush(dev_priv);
 
 	intel_runtime_pm_get(dev_priv);
 	spin_lock_irq(&dev_priv->uncore.lock);
@@ -837,6 +837,10 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 		}
 		break;
 
+	case I915_GEM_DOMAIN_WC:
+		wmb();
+		break;
+
 	case I915_GEM_DOMAIN_CPU:
 		i915_gem_clflush_object(obj, I915_CLFLUSH_SYNC);
 		break;
@@ -1623,6 +1627,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto err;
 	}
 
+	/* Writes not allowed into this read-only object */
+	if (i915_gem_object_is_readonly(obj)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
 	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
 	ret = -ENODEV;
@@ -2006,9 +2016,12 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
 	struct i915_vma *vma;
 	pgoff_t page_offset;
-	unsigned int flags;
 	int ret;
 
+	/* Sanity check that we allow writing into this object */
+	if (i915_gem_object_is_readonly(obj) && write)
+		return VM_FAULT_SIGBUS;
+
 	/* We don't use vmf->pgoff since that has the fake offset */
 	page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
 
@@ -2042,27 +2055,34 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		goto err_unlock;
 	}
 
-	/* If the object is smaller than a couple of partial vma, it is
-	 * not worth only creating a single partial vma - we may as well
-	 * clear enough space for the full object.
-	 */
-	flags = PIN_MAPPABLE;
-	if (obj->base.size > 2 * MIN_CHUNK_PAGES << PAGE_SHIFT)
-		flags |= PIN_NONBLOCK | PIN_NONFAULT;
 
 	/* Now pin it into the GTT as needed */
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, flags);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+				       PIN_MAPPABLE |
+				       PIN_NONBLOCK |
+				       PIN_NONFAULT);
 	if (IS_ERR(vma)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =
 			compute_partial_view(obj, page_offset, MIN_CHUNK_PAGES);
+		unsigned int flags;
+
+		flags = PIN_MAPPABLE;
+		if (view.type == I915_GGTT_VIEW_NORMAL)
+			flags |= PIN_NONBLOCK; /* avoid warnings for pinned */
 
-		/* Userspace is now writing through an untracked VMA, abandon
+		/*
+		 * Userspace is now writing through an untracked VMA, abandon
 		 * all hope that the hardware is able to track future writes.
 		 */
 		obj->frontbuffer_ggtt_origin = ORIGIN_CPU;
 
-		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		if (IS_ERR(vma) && !view.type) {
+			flags = PIN_MAPPABLE;
+			view.type = I915_GGTT_VIEW_PARTIAL;
+			vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		}
 	}
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
@@ -2114,6 +2134,7 @@ err:
 		 */
 		if (!i915_terminally_wedged(&dev_priv->gpu_error))
 			return VM_FAULT_SIGBUS;
+		/* else: fall through */
 	case -EAGAIN:
 		/*
 		 * EAGAIN means the gpu is hung and we'll wait for the error
@@ -2256,7 +2277,9 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 
 	/* Attempt to reap some mmap space from dead objects */
 	do {
-		err = i915_gem_wait_for_idle(dev_priv, I915_WAIT_INTERRUPTIBLE);
+		err = i915_gem_wait_for_idle(dev_priv,
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (err)
 			break;
 
@@ -3074,25 +3097,6 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 	return err;
 }
 
-static void skip_request(struct i915_request *request)
-{
-	void *vaddr = request->ring->vaddr;
-	u32 head;
-
-	/* As this request likely depends on state from the lost
-	 * context, clear out all the user operations leaving the
-	 * breadcrumb at the end (so we get the fence notifications).
-	 */
-	head = request->head;
-	if (request->postfix < head) {
-		memset(vaddr + head, 0, request->ring->size - head);
-		head = 0;
-	}
-	memset(vaddr + head, 0, request->postfix - head);
-
-	dma_fence_set_error(&request->fence, -EIO);
-}
-
 static void engine_skip_context(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
@@ -3103,14 +3107,14 @@ static void engine_skip_context(struct i915_request *request)
 	GEM_BUG_ON(timeline == &engine->timeline);
 
 	spin_lock_irqsave(&engine->timeline.lock, flags);
-	spin_lock_nested(&timeline->lock, SINGLE_DEPTH_NESTING);
+	spin_lock(&timeline->lock);
 
 	list_for_each_entry_continue(request, &engine->timeline.requests, link)
 		if (request->gem_context == hung_ctx)
-			skip_request(request);
+			i915_request_skip(request, -EIO);
 
 	list_for_each_entry(request, &timeline->requests, link)
-		skip_request(request);
+		i915_request_skip(request, -EIO);
 
 	spin_unlock(&timeline->lock);
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
@@ -3153,7 +3157,7 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 
 	if (stalled) {
 		i915_gem_context_mark_guilty(request->gem_context);
-		skip_request(request);
+		i915_request_skip(request, -EIO);
 
 		/* If this context is now banned, skip all pending requests. */
 		if (i915_gem_context_is_banned(request->gem_context))
@@ -3750,14 +3754,14 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	return ret;
 }
 
-static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
+static long wait_for_timeline(struct i915_timeline *tl,
+			      unsigned int flags, long timeout)
 {
 	struct i915_request *rq;
-	long ret;
 
 	rq = i915_gem_active_get_unlocked(&tl->last_request);
 	if (!rq)
-		return 0;
+		return timeout;
 
 	/*
 	 * "Race-to-idle".
@@ -3771,10 +3775,10 @@ static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
 	if (flags & I915_WAIT_FOR_IDLE_BOOST)
 		gen6_rps_boost(rq, NULL);
 
-	ret = i915_request_wait(rq, flags, MAX_SCHEDULE_TIMEOUT);
+	timeout = i915_request_wait(rq, flags, timeout);
 	i915_request_put(rq);
 
-	return ret < 0 ? ret : 0;
+	return timeout;
 }
 
 static int wait_for_engines(struct drm_i915_private *i915)
@@ -3790,10 +3794,12 @@ static int wait_for_engines(struct drm_i915_private *i915)
 	return 0;
 }
 
-int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
+int i915_gem_wait_for_idle(struct drm_i915_private *i915,
+			   unsigned int flags, long timeout)
 {
-	GEM_TRACE("flags=%x (%s)\n",
-		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked");
+	GEM_TRACE("flags=%x (%s), timeout=%ld%s\n",
+		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked",
+		  timeout, timeout == MAX_SCHEDULE_TIMEOUT ? " (forever)" : "");
 
 	/* If the device is asleep, we have no requests outstanding */
 	if (!READ_ONCE(i915->gt.awake))
@@ -3806,27 +3812,31 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 		lockdep_assert_held(&i915->drm.struct_mutex);
 
 		list_for_each_entry(tl, &i915->gt.timelines, link) {
-			err = wait_for_timeline(tl, flags);
-			if (err)
-				return err;
+			timeout = wait_for_timeline(tl, flags, timeout);
+			if (timeout < 0)
+				return timeout;
 		}
+
+		err = wait_for_engines(i915);
+		if (err)
+			return err;
+
 		i915_retire_requests(i915);
 		GEM_BUG_ON(i915->gt.active_requests);
-
-		return wait_for_engines(i915);
 	} else {
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
-		int err;
 
 		for_each_engine(engine, i915, id) {
-			err = wait_for_timeline(&engine->timeline, flags);
-			if (err)
-				return err;
-		}
+			struct i915_timeline *tl = &engine->timeline;
 
-		return 0;
+			timeout = wait_for_timeline(tl, flags, timeout);
+			if (timeout < 0)
+				return timeout;
+		}
 	}
+
+	return 0;
 }
 
 static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
@@ -5029,65 +5039,70 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	mutex_unlock(&i915->drm.struct_mutex);
 }
 
-int i915_gem_suspend(struct drm_i915_private *dev_priv)
+int i915_gem_suspend(struct drm_i915_private *i915)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 
 	GEM_TRACE("\n");
 
-	intel_runtime_pm_get(dev_priv);
-	intel_suspend_gt_powersave(dev_priv);
+	intel_runtime_pm_get(i915);
+	intel_suspend_gt_powersave(i915);
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&i915->drm.struct_mutex);
 
-	/* We have to flush all the executing contexts to main memory so
+	/*
+	 * We have to flush all the executing contexts to main memory so
 	 * that they can saved in the hibernation image. To ensure the last
 	 * context image is coherent, we have to switch away from it. That
-	 * leaves the dev_priv->kernel_context still active when
+	 * leaves the i915->kernel_context still active when
 	 * we actually suspend, and its image in memory may not match the GPU
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-		ret = i915_gem_switch_to_kernel_context(dev_priv);
+	if (!i915_terminally_wedged(&i915->gpu_error)) {
+		ret = i915_gem_switch_to_kernel_context(i915);
 		if (ret)
 			goto err_unlock;
 
-		ret = i915_gem_wait_for_idle(dev_priv,
+		ret = i915_gem_wait_for_idle(i915,
 					     I915_WAIT_INTERRUPTIBLE |
 					     I915_WAIT_LOCKED |
-					     I915_WAIT_FOR_IDLE_BOOST);
+					     I915_WAIT_FOR_IDLE_BOOST,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret && ret != -EIO)
 			goto err_unlock;
 
-		assert_kernel_context_is_current(dev_priv);
+		assert_kernel_context_is_current(i915);
 	}
-	mutex_unlock(&dev->struct_mutex);
+	i915_retire_requests(i915); /* ensure we flush after wedging */
 
-	intel_uc_suspend(dev_priv);
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	intel_uc_suspend(i915);
 
-	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
-	cancel_delayed_work_sync(&dev_priv->gt.retire_work);
+	cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work);
+	cancel_delayed_work_sync(&i915->gt.retire_work);
 
-	/* As the idle_work is rearming if it detects a race, play safe and
+	/*
+	 * As the idle_work is rearming if it detects a race, play safe and
 	 * repeat the flush until it is definitely idle.
 	 */
-	drain_delayed_work(&dev_priv->gt.idle_work);
+	drain_delayed_work(&i915->gt.idle_work);
 
-	/* Assert that we sucessfully flushed all the work and
+	/*
+	 * Assert that we successfully flushed all the work and
 	 * reset the GPU back to its idle, low power state.
 	 */
-	WARN_ON(dev_priv->gt.awake);
-	if (WARN_ON(!intel_engines_are_idle(dev_priv)))
-		i915_gem_set_wedged(dev_priv); /* no hope, discard everything */
+	WARN_ON(i915->gt.awake);
+	if (WARN_ON(!intel_engines_are_idle(i915)))
+		i915_gem_set_wedged(i915); /* no hope, discard everything */
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(i915);
 	return 0;
 
 err_unlock:
-	mutex_unlock(&dev->struct_mutex);
-	intel_runtime_pm_put(dev_priv);
+	mutex_unlock(&i915->drm.struct_mutex);
+	intel_runtime_pm_put(i915);
 	return ret;
 }
 
@@ -5310,13 +5325,17 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 	ret = __i915_gem_restart_engines(dev_priv);
 	if (ret)
 		goto cleanup_uc;
-out:
+
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	return ret;
+
+	return 0;
 
 cleanup_uc:
 	intel_uc_fini_hw(dev_priv);
-	goto out;
+out:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
+	return ret;
 }
 
 static int __intel_engines_record_defaults(struct drm_i915_private *i915)
@@ -5361,9 +5380,11 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	if (err)
 		goto err_active;
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
-	if (err)
+	if (i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED, HZ / 5)) {
+		i915_gem_set_wedged(i915);
+		err = -EIO; /* Caller will declare us wedged */
 		goto err_active;
+	}
 
 	assert_kernel_context_is_current(i915);
 
@@ -5426,7 +5447,9 @@ err_active:
 	if (WARN_ON(i915_gem_switch_to_kernel_context(i915)))
 		goto out_ctx;
 
-	if (WARN_ON(i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED)))
+	if (WARN_ON(i915_gem_wait_for_idle(i915,
+					   I915_WAIT_LOCKED,
+					   MAX_SCHEDULE_TIMEOUT)))
 		goto out_ctx;
 
 	i915_gem_contexts_lost(i915);
@@ -5456,13 +5479,13 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
-	ret = intel_wopcm_init(&dev_priv->wopcm);
+	ret = intel_uc_init_misc(dev_priv);
 	if (ret)
 		return ret;
 
-	ret = intel_uc_init_misc(dev_priv);
+	ret = intel_wopcm_init(&dev_priv->wopcm);
 	if (ret)
-		return ret;
+		goto err_uc_misc;
 
 	/* This is just a security blanket to placate dragons.
 	 * On some systems, we very sporadically observe that the first TLBs
@@ -5543,6 +5566,8 @@ err_init_hw:
 	WARN_ON(i915_gem_suspend(dev_priv));
 	i915_gem_suspend_late(dev_priv);
 
+	i915_gem_drain_workqueue(dev_priv);
+
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uc_fini_hw(dev_priv);
 err_uc_init:
@@ -5560,6 +5585,7 @@ err_unlock:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
+err_uc_misc:
 	intel_uc_fini_misc(dev_priv);
 
 	if (ret != -EIO)
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 261da577829a..e46592956872 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -88,4 +88,9 @@ static inline void __tasklet_enable_sync_once(struct tasklet_struct *t)
 		tasklet_kill(t);
 }
 
+static inline bool __tasklet_is_enabled(const struct tasklet_struct *t)
+{
+	return !atomic_read(&t->count);
+}
+
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index ccf463ab6562..b10770cfccd2 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -374,7 +374,7 @@ i915_gem_create_context(struct drm_i915_private *dev_priv,
 	if (USES_FULL_PPGTT(dev_priv)) {
 		struct i915_hw_ppgtt *ppgtt;
 
-		ppgtt = i915_ppgtt_create(dev_priv, file_priv, ctx->name);
+		ppgtt = i915_ppgtt_create(dev_priv, file_priv);
 		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
@@ -512,8 +512,8 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 	}
 
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
-			 dev_priv->engine[RCS]->context_size ? "logical" :
-			 "fake");
+			 DRIVER_CAPS(dev_priv)->has_logical_contexts ?
+			 "logical" : "fake");
 	return 0;
 }
 
@@ -720,7 +720,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	struct i915_gem_context *ctx;
 	int ret;
 
-	if (!dev_priv->engine[RCS]->context_size)
+	if (!DRIVER_CAPS(dev_priv)->has_logical_contexts)
 		return -ENODEV;
 
 	if (args->pad != 0)
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 54814a196ee4..02b83a5ed96c 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -69,7 +69,8 @@ static int ggtt_flush(struct drm_i915_private *i915)
 
 	err = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 60dc2a865f5f..3f0c612d42e7 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -66,6 +66,15 @@ enum {
 #define __I915_EXEC_ILLEGAL_FLAGS \
 	(__I915_EXEC_UNKNOWN_FLAGS | I915_EXEC_CONSTANTS_MASK)
 
+/* Catch emission of unexpected errors for CI! */
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+#undef EINVAL
+#define EINVAL ({ \
+	DRM_DEBUG_DRIVER("EINVAL at %s:%d\n", __func__, __LINE__); \
+	22; \
+})
+#endif
+
 /**
  * DOC: User command execution
  *
@@ -534,7 +543,8 @@ eb_add_vma(struct i915_execbuffer *eb,
 	 * paranoia do it everywhere.
 	 */
 	if (i == batch_idx) {
-		if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+		if (entry->relocation_count &&
+		    !(eb->flags[i] & EXEC_OBJECT_PINNED))
 			eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
 		if (eb->reloc_cache.has_fence)
 			eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
@@ -1155,18 +1165,16 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto err_request;
 
 	GEM_BUG_ON(!reservation_object_test_signaled_rcu(batch->resv, true));
-	i915_vma_move_to_active(batch, rq, 0);
-	reservation_object_lock(batch->resv, NULL);
-	reservation_object_add_excl_fence(batch->resv, &rq->fence);
-	reservation_object_unlock(batch->resv);
-	i915_vma_unpin(batch);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
 
 	rq->batch = batch;
+	i915_vma_unpin(batch);
 
 	cache->rq = rq;
 	cache->rq_cmd = cmd;
@@ -1175,6 +1183,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	/* Return with batch mapping (cmd) still pinned */
 	return 0;
 
+skip_request:
+	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
@@ -1761,25 +1771,6 @@ slow:
 	return eb_relocate_slow(eb);
 }
 
-static void eb_export_fence(struct i915_vma *vma,
-			    struct i915_request *rq,
-			    unsigned int flags)
-{
-	struct reservation_object *resv = vma->resv;
-
-	/*
-	 * Ignore errors from failing to allocate the new fence, we can't
-	 * handle an error right now. Worst case should be missed
-	 * synchronisation leading to rendering corruption.
-	 */
-	reservation_object_lock(resv, NULL);
-	if (flags & EXEC_OBJECT_WRITE)
-		reservation_object_add_excl_fence(resv, &rq->fence);
-	else if (reservation_object_reserve_shared(resv) == 0)
-		reservation_object_add_shared_fence(resv, &rq->fence);
-	reservation_object_unlock(resv);
-}
-
 static int eb_move_to_gpu(struct i915_execbuffer *eb)
 {
 	const unsigned int count = eb->buffer_count;
@@ -1833,8 +1824,11 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 		unsigned int flags = eb->flags[i];
 		struct i915_vma *vma = eb->vma[i];
 
-		i915_vma_move_to_active(vma, eb->request, flags);
-		eb_export_fence(vma, eb->request, flags);
+		err = i915_vma_move_to_active(vma, eb->request, flags);
+		if (unlikely(err)) {
+			i915_request_skip(eb->request, err);
+			return err;
+		}
 
 		__eb_unreserve_vma(vma, flags);
 		vma->exec_flags = NULL;
@@ -1874,45 +1868,6 @@ static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 	return true;
 }
 
-void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct i915_request *rq,
-			     unsigned int flags)
-{
-	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned int idx = rq->engine->id;
-
-	lockdep_assert_held(&rq->i915->drm.struct_mutex);
-	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-
-	/*
-	 * Add a reference if we're newly entering the active list.
-	 * The order in which we add operations to the retirement queue is
-	 * vital here: mark_active adds to the start of the callback list,
-	 * such that subsequent callbacks are called first. Therefore we
-	 * add the active reference first and queue for it to be dropped
-	 * *last*.
-	 */
-	if (!i915_vma_is_active(vma))
-		obj->active_count++;
-	i915_vma_set_active(vma, idx);
-	i915_gem_active_set(&vma->last_read[idx], rq);
-	list_move_tail(&vma->vm_link, &vma->vm->active_list);
-
-	obj->write_domain = 0;
-	if (flags & EXEC_OBJECT_WRITE) {
-		obj->write_domain = I915_GEM_DOMAIN_RENDER;
-
-		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
-			i915_gem_active_set(&obj->frontbuffer_write, rq);
-
-		obj->read_domains = 0;
-	}
-	obj->read_domains |= I915_GEM_GPU_DOMAINS;
-
-	if (flags & EXEC_OBJECT_NEEDS_FENCE)
-		i915_gem_active_set(&vma->last_fence, rq);
-}
-
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 {
 	u32 *cs;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index c6aa761ca085..f00c7fbef79e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -204,9 +204,9 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 			return err;
 	}
 
-	/* Currently applicable only to VLV */
+	/* Applicable to VLV, and gen8+ */
 	pte_flags = 0;
-	if (vma->obj->gt_ro)
+	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
@@ -244,10 +244,13 @@ static void clear_pages(struct i915_vma *vma)
 }
 
 static gen8_pte_t gen8_pte_encode(dma_addr_t addr,
-				  enum i915_cache_level level)
+				  enum i915_cache_level level,
+				  u32 flags)
 {
-	gen8_pte_t pte = _PAGE_PRESENT | _PAGE_RW;
-	pte |= addr;
+	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~_PAGE_RW;
 
 	switch (level) {
 	case I915_CACHE_NONE:
@@ -375,37 +378,70 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr,
 	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)
+{
+	int nr;
+
+	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
+
+	nr = min_t(int, 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 *pvec = &vm->free_pages;
-	struct pagevec stash;
+	struct pagevec stack;
+	struct page *page;
 
 	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
 		i915_gem_shrink_all(vm->i915);
 
-	if (likely(pvec->nr))
-		return pvec->pages[--pvec->nr];
+	page = stash_pop_page(&vm->free_pages);
+	if (page)
+		return page;
 
 	if (!vm->pt_kmap_wc)
 		return alloc_page(gfp);
 
-	/* A placeholder for a specific mutex to guard the WC stash */
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
-
 	/* Look in our global stash of WC pages... */
-	pvec = &vm->i915->mm.wc_stash;
-	if (likely(pvec->nr))
-		return pvec->pages[--pvec->nr];
+	page = stash_pop_page(&vm->i915->mm.wc_stash);
+	if (page)
+		return page;
 
 	/*
-	 * Otherwise batch allocate pages to amoritize cost of set_pages_wc.
+	 * 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(&stash);
+	pagevec_init(&stack);
 	do {
 		struct page *page;
 
@@ -413,59 +449,67 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			break;
 
-		stash.pages[stash.nr++] = page;
-	} while (stash.nr < pagevec_space(pvec));
+		stack.pages[stack.nr++] = page;
+	} while (pagevec_space(&stack));
 
-	if (stash.nr) {
-		int nr = min_t(int, stash.nr, pagevec_space(pvec));
-		struct page **pages = stash.pages + stash.nr - nr;
+	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
+		page = stack.pages[--stack.nr];
 
-		if (nr && !set_pages_array_wc(pages, nr)) {
-			memcpy(pvec->pages + pvec->nr,
-			       pages, sizeof(pages[0]) * nr);
-			pvec->nr += nr;
-			stash.nr -= nr;
-		}
+		/* Merge spare WC pages to the global stash */
+		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);
+	}
 
-		pagevec_release(&stash);
+	/* Return unwanted leftovers */
+	if (unlikely(stack.nr)) {
+		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
+		__pagevec_release(&stack);
 	}
 
-	return likely(pvec->nr) ? pvec->pages[--pvec->nr] : NULL;
+	return page;
 }
 
 static void vm_free_pages_release(struct i915_address_space *vm,
 				  bool immediate)
 {
-	struct pagevec *pvec = &vm->free_pages;
+	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) {
-		struct pagevec *stash = &vm->i915->mm.wc_stash;
-
-		/* When we use WC, first fill up the global stash and then
+		/*
+		 * 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);
 
-		lockdep_assert_held(&vm->i915->drm.struct_mutex);
-		if (pagevec_space(stash)) {
-			do {
-				stash->pages[stash->nr++] =
-					pvec->pages[--pvec->nr];
-				if (!pvec->nr)
-					return;
-			} while (pagevec_space(stash));
-
-			/* 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 (!immediate)
-				return;
-		}
+		/*
+		 * 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);
@@ -481,8 +525,45 @@ static void vm_free_page(struct i915_address_space *vm, struct page *page)
 	 * unconditional might_sleep() for everybody.
 	 */
 	might_sleep();
-	if (!pagevec_add(&vm->free_pages, page))
+	spin_lock(&vm->free_pages.lock);
+	if (!pagevec_add(&vm->free_pages.pvec, page))
 		vm_free_pages_release(vm, false);
+	spin_unlock(&vm->free_pages.lock);
+}
+
+static void i915_address_space_init(struct i915_address_space *vm,
+				    struct drm_i915_private *dev_priv)
+{
+	/*
+	 * 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);
+	i915_gem_shrinker_taints_mutex(&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->active_list);
+	INIT_LIST_HEAD(&vm->inactive_list);
+	INIT_LIST_HEAD(&vm->unbound_list);
+}
+
+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);
 }
 
 static int __setup_page_dma(struct i915_address_space *vm,
@@ -493,8 +574,11 @@ static int __setup_page_dma(struct i915_address_space *vm,
 	if (unlikely(!p->page))
 		return -ENOMEM;
 
-	p->daddr = dma_map_page(vm->dma, p->page, 0, PAGE_SIZE,
-				PCI_DMA_BIDIRECTIONAL);
+	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;
@@ -575,8 +659,11 @@ setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			goto skip;
 
-		addr = dma_map_page(vm->dma, page, 0, size,
-				    PCI_DMA_BIDIRECTIONAL);
+		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;
 
@@ -637,7 +724,7 @@ static void gen8_initialize_pt(struct i915_address_space *vm,
 			       struct i915_page_table *pt)
 {
 	fill_px(vm, pt,
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC));
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0));
 }
 
 static void gen6_initialize_pt(struct gen6_hw_ppgtt *ppgtt,
@@ -785,7 +872,7 @@ static bool gen8_ppgtt_clear_pt(struct i915_address_space *vm,
 	unsigned int pte = gen8_pte_index(start);
 	unsigned int pte_end = pte + num_entries;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	gen8_pte_t *vaddr;
 
 	GEM_BUG_ON(num_entries > pt->used_ptes);
@@ -957,10 +1044,11 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 			      struct i915_page_directory_pointer *pdp,
 			      struct sgt_dma *iter,
 			      struct gen8_insert_pte *idx,
-			      enum i915_cache_level cache_level)
+			      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);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
 	gen8_pte_t *vaddr;
 	bool ret;
 
@@ -1011,14 +1099,14 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
-				   u32 unused)
+				   u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma);
 	struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 	gen8_ppgtt_insert_pte_entries(ppgtt, &ppgtt->pdp, &iter, &idx,
-				      cache_level);
+				      cache_level, flags);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 }
@@ -1026,9 +1114,10 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 					   struct i915_page_directory_pointer **pdps,
 					   struct sgt_dma *iter,
-					   enum i915_cache_level cache_level)
+					   enum i915_cache_level cache_level,
+					   u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	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;
 
@@ -1144,19 +1233,21 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
-				   u32 unused)
+				   u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma);
 	struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
 
 	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level);
+		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level,
+					       flags);
 	} else {
 		struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 		while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++],
-						     &iter, &idx, cache_level))
+						     &iter, &idx, cache_level,
+						     flags))
 			GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
 
 		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
@@ -1494,7 +1585,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 {
 	struct i915_address_space *vm = &ppgtt->vm;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	u64 start = 0, length = ppgtt->vm.total;
 
 	if (use_4lvl(vm)) {
@@ -1562,6 +1653,8 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	if (!ppgtt)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&ppgtt->ref);
+
 	ppgtt->vm.i915 = i915;
 	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
@@ -1569,6 +1662,15 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 		1ULL << 48 :
 		1ULL << 32;
 
+	/*
+	 * From bdw, there is support for read-only pages in the PPGTT.
+	 *
+	 * XXX GVT is not honouring the lack of RW in the PTE bits.
+	 */
+	ppgtt->vm.has_read_only = !intel_vgpu_active(i915);
+
+	i915_address_space_init(&ppgtt->vm, i915);
+
 	/* There are only few exceptions for gen >=6. chv and bxt.
 	 * And we are not sure about the latter so play safe for now.
 	 */
@@ -1996,7 +2098,6 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	struct drm_i915_private *i915 = ppgtt->base.vm.i915;
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct i915_vma *vma;
-	int i;
 
 	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(size > ggtt->vm.total);
@@ -2005,14 +2106,14 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	if (!vma)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		init_request_active(&vma->last_read[i], NULL);
 	init_request_active(&vma->last_fence, NULL);
 
 	vma->vm = &ggtt->vm;
 	vma->ops = &pd_vma_ops;
 	vma->private = ppgtt;
 
+	vma->active = RB_ROOT;
+
 	vma->size = size;
 	vma->fence_size = size;
 	vma->flags = I915_VMA_GGTT;
@@ -2068,11 +2169,15 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	if (!ppgtt)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&ppgtt->base.ref);
+
 	ppgtt->base.vm.i915 = i915;
 	ppgtt->base.vm.dma = &i915->drm.pdev->dev;
 
 	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
+	i915_address_space_init(&ppgtt->base.vm, i915);
+
 	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;
@@ -2105,30 +2210,6 @@ err_free:
 	return ERR_PTR(err);
 }
 
-static void i915_address_space_init(struct i915_address_space *vm,
-				    struct drm_i915_private *dev_priv,
-				    const char *name)
-{
-	drm_mm_init(&vm->mm, 0, vm->total);
-	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
-
-	INIT_LIST_HEAD(&vm->active_list);
-	INIT_LIST_HEAD(&vm->inactive_list);
-	INIT_LIST_HEAD(&vm->unbound_list);
-
-	list_add_tail(&vm->global_link, &dev_priv->vm_list);
-	pagevec_init(&vm->free_pages);
-}
-
-static void i915_address_space_fini(struct i915_address_space *vm)
-{
-	if (pagevec_count(&vm->free_pages))
-		vm_free_pages_release(vm, true);
-
-	drm_mm_takedown(&vm->mm);
-	list_del(&vm->global_link);
-}
-
 static void gtt_write_workarounds(struct drm_i915_private *dev_priv)
 {
 	/* This function is for gtt related workarounds. This function is
@@ -2199,8 +2280,7 @@ __hw_ppgtt_create(struct drm_i915_private *i915)
 
 struct i915_hw_ppgtt *
 i915_ppgtt_create(struct drm_i915_private *i915,
-		  struct drm_i915_file_private *fpriv,
-		  const char *name)
+		  struct drm_i915_file_private *fpriv)
 {
 	struct i915_hw_ppgtt *ppgtt;
 
@@ -2208,8 +2288,6 @@ i915_ppgtt_create(struct drm_i915_private *i915,
 	if (IS_ERR(ppgtt))
 		return ppgtt;
 
-	kref_init(&ppgtt->ref);
-	i915_address_space_init(&ppgtt->vm, i915, name);
 	ppgtt->vm.file = fpriv;
 
 	trace_i915_ppgtt_create(&ppgtt->vm);
@@ -2397,7 +2475,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 	gen8_pte_t __iomem *pte =
 		(gen8_pte_t __iomem *)ggtt->gsm + (offset >> PAGE_SHIFT);
 
-	gen8_set_pte(pte, gen8_pte_encode(addr, level));
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
 
 	ggtt->invalidate(vm->i915);
 }
@@ -2405,14 +2483,19 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma *vma,
 				     enum i915_cache_level level,
-				     u32 unused)
+				     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);
+	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 >> PAGE_SHIFT;
 	for_each_sgt_dma(addr, sgt_iter, vma->pages)
@@ -2478,7 +2561,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	gen8_pte_t __iomem *gtt_base =
 		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
 	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
@@ -2539,13 +2622,14 @@ 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, 0);
+	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
@@ -2554,9 +2638,9 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
 					     struct i915_vma *vma,
 					     enum i915_cache_level level,
-					     u32 unused)
+					     u32 flags)
 {
-	struct insert_entries arg = { vm, vma, level };
+	struct insert_entries arg = { vm, vma, level, flags };
 
 	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
 }
@@ -2647,9 +2731,9 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	struct drm_i915_gem_object *obj = vma->obj;
 	u32 pte_flags;
 
-	/* Currently applicable only to VLV */
+	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
 	pte_flags = 0;
-	if (obj->gt_ro)
+	if (i915_gem_object_is_readonly(obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	intel_runtime_pm_get(i915);
@@ -2687,7 +2771,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
-	if (vma->obj->gt_ro)
+	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	if (flags & I915_VMA_LOCAL_BIND) {
@@ -2739,7 +2823,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 
 	if (unlikely(ggtt->do_idle_maps)) {
-		if (i915_gem_wait_for_idle(dev_priv, 0)) {
+		if (i915_gem_wait_for_idle(dev_priv, 0, MAX_SCHEDULE_TIMEOUT)) {
 			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
@@ -2788,7 +2872,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 	struct i915_hw_ppgtt *ppgtt;
 	int err;
 
-	ppgtt = i915_ppgtt_create(i915, ERR_PTR(-EPERM), "[alias]");
+	ppgtt = i915_ppgtt_create(i915, ERR_PTR(-EPERM));
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -2918,7 +3002,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 
 	ggtt->vm.cleanup(&ggtt->vm);
 
-	pvec = &dev_priv->mm.wc_stash;
+	pvec = &dev_priv->mm.wc_stash.pvec;
 	if (pvec->nr) {
 		set_pages_array_wb(pvec->pages, pvec->nr);
 		__pagevec_release(pvec);
@@ -3518,7 +3602,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
-	INIT_LIST_HEAD(&dev_priv->vm_list);
+	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
@@ -3526,7 +3610,11 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	 * and beyond the end of the GTT if we do not provide a guard.
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_address_space_init(&ggtt->vm, dev_priv, "[global]");
+	i915_address_space_init(&ggtt->vm, dev_priv);
+
+	/* Only VLV supports read-only GGTT mappings */
+	ggtt->vm.has_read_only = IS_VALLEYVIEW(dev_priv);
+
 	if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv))
 		ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 9a4824cae68d..2a116a91420b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -270,6 +270,11 @@ struct i915_vma_ops {
 	void (*clear_pages)(struct i915_vma *vma);
 };
 
+struct pagestash {
+	spinlock_t lock;
+	struct pagevec pvec;
+};
+
 struct i915_address_space {
 	struct drm_mm mm;
 	struct drm_i915_private *i915;
@@ -283,12 +288,13 @@ struct i915_address_space {
 	 * assign blame.
 	 */
 	struct drm_i915_file_private *file;
-	struct list_head global_link;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
 
 	bool closed;
 
+	struct mutex mutex; /* protects vma and our lists */
+
 	struct i915_page_dma scratch_page;
 	struct i915_page_table *scratch_pt;
 	struct i915_page_directory *scratch_pd;
@@ -324,8 +330,13 @@ struct i915_address_space {
 	 */
 	struct list_head unbound_list;
 
-	struct pagevec free_pages;
-	bool pt_kmap_wc;
+	struct pagestash free_pages;
+
+	/* 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;
 
 	/* FIXME: Need a more generic return type */
 	gen6_pte_t (*pte_encode)(dma_addr_t addr,
@@ -615,8 +626,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv);
 int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv);
 void i915_ppgtt_release(struct kref *kref);
 struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv,
-					struct drm_i915_file_private *fpriv,
-					const char *name);
+					struct drm_i915_file_private *fpriv);
 void i915_ppgtt_close(struct i915_address_space *vm);
 static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 54f00b350779..83e5e01fa9ea 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -141,7 +141,6 @@ struct drm_i915_gem_object {
 	 * Is the object to be mapped as read-only to the GPU
 	 * Only honoured if hardware has relevant pte bit
 	 */
-	unsigned long gt_ro:1;
 	unsigned int cache_level:3;
 	unsigned int cache_coherent:2;
 #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0)
@@ -268,7 +267,6 @@ struct drm_i915_gem_object {
 	union {
 		struct i915_gem_userptr {
 			uintptr_t ptr;
-			unsigned read_only :1;
 
 			struct i915_mm_struct *mm;
 			struct i915_mmu_object *mmu_object;
@@ -337,26 +335,17 @@ __attribute__((nonnull))
 static inline struct drm_i915_gem_object *
 i915_gem_object_get(struct drm_i915_gem_object *obj)
 {
-	drm_gem_object_reference(&obj->base);
+	drm_gem_object_get(&obj->base);
 	return obj;
 }
 
-__deprecated
-extern void drm_gem_object_reference(struct drm_gem_object *);
-
 __attribute__((nonnull))
 static inline void
 i915_gem_object_put(struct drm_i915_gem_object *obj)
 {
-	__drm_gem_object_unreference(&obj->base);
+	__drm_gem_object_put(&obj->base);
 }
 
-__deprecated
-extern void drm_gem_object_unreference(struct drm_gem_object *);
-
-__deprecated
-extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *);
-
 static inline void i915_gem_object_lock(struct drm_i915_gem_object *obj)
 {
 	reservation_object_lock(obj->resv, NULL);
@@ -367,6 +356,18 @@ static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj)
 	reservation_object_unlock(obj->resv);
 }
 
+static inline void
+i915_gem_object_set_readonly(struct drm_i915_gem_object *obj)
+{
+	obj->base.vma_node.readonly = true;
+}
+
+static inline bool
+i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
+{
+	return obj->base.vma_node.readonly;
+}
+
 static inline bool
 i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 3210cedfa46c..90baf9086d0a 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -222,7 +222,7 @@ int i915_gem_render_state_emit(struct i915_request *rq)
 			goto err_unpin;
 	}
 
-	i915_vma_move_to_active(so.vma, rq, 0);
+	err = i915_vma_move_to_active(so.vma, rq, 0);
 err_unpin:
 	i915_vma_unpin(so.vma);
 err_vma:
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 55e84e71f526..ea90d3a0d511 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/oom.h>
+#include <linux/sched/mm.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -172,7 +173,9 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	 * we will free as much as we can and hope to get a second chance.
 	 */
 	if (flags & I915_SHRINK_ACTIVE)
-		i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+		i915_gem_wait_for_idle(i915,
+				       I915_WAIT_LOCKED,
+				       MAX_SCHEDULE_TIMEOUT);
 
 	trace_i915_gem_shrink(i915, target, flags);
 	i915_retire_requests(i915);
@@ -392,7 +395,8 @@ shrinker_lock_uninterruptible(struct drm_i915_private *i915, bool *unlock,
 	unsigned long timeout = jiffies + msecs_to_jiffies_timeout(timeout_ms);
 
 	do {
-		if (i915_gem_wait_for_idle(i915, 0) == 0 &&
+		if (i915_gem_wait_for_idle(i915,
+					   0, MAX_SCHEDULE_TIMEOUT) == 0 &&
 		    shrinker_lock(i915, unlock))
 			break;
 
@@ -466,7 +470,9 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		return NOTIFY_DONE;
 
 	/* Force everything onto the inactive lists */
-	ret = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	ret = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		goto out;
 
@@ -526,3 +532,14 @@ void i915_gem_shrinker_unregister(struct drm_i915_private *i915)
 	WARN_ON(unregister_oom_notifier(&i915->mm.oom_notifier));
 	unregister_shrinker(&i915->mm.shrinker);
 }
+
+void i915_gem_shrinker_taints_mutex(struct mutex *mutex)
+{
+	if (!IS_ENABLED(CONFIG_LOCKDEP))
+		return;
+
+	fs_reclaim_acquire(GFP_KERNEL);
+	mutex_lock(mutex);
+	mutex_unlock(mutex);
+	fs_reclaim_release(GFP_KERNEL);
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 79a347295e00..53440bf87650 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -254,6 +254,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) {
 	default:
 		MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK);
+		/* fall through */
 	case GEN7_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;
 		break;
@@ -343,6 +344,35 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*size = stolen_top - *base;
 }
 
+static void icl_get_stolen_reserved(struct drm_i915_private *dev_priv,
+				    resource_size_t *base,
+				    resource_size_t *size)
+{
+	u64 reg_val = I915_READ64(GEN6_STOLEN_RESERVED);
+
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
+
+	*base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK;
+
+	switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
+	case GEN8_STOLEN_RESERVED_1M:
+		*size = 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_2M:
+		*size = 2 * 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_4M:
+		*size = 4 * 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_8M:
+		*size = 8 * 1024 * 1024;
+		break;
+	default:
+		*size = 8 * 1024 * 1024;
+		MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK);
+	}
+}
+
 int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 {
 	resource_size_t reserved_base, stolen_top;
@@ -399,7 +429,9 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			gen7_get_stolen_reserved(dev_priv,
 						 &reserved_base, &reserved_size);
 		break;
-	default:
+	case 8:
+	case 9:
+	case 10:
 		if (IS_LP(dev_priv))
 			chv_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
@@ -407,6 +439,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			bdw_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
 		break;
+	case 11:
+	default:
+		icl_get_stolen_reserved(dev_priv, &reserved_base,
+					&reserved_size);
+		break;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 854bd51b9478..dcd6e230d16a 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 		struct mm_struct *mm = obj->userptr.mm->mm;
 		unsigned int flags = 0;
 
-		if (!obj->userptr.read_only)
+		if (!i915_gem_object_is_readonly(obj))
 			flags |= FOLL_WRITE;
 
 		ret = -EFAULT;
@@ -643,7 +643,7 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 		if (pvec) /* defer to worker if malloc fails */
 			pinned = __get_user_pages_fast(obj->userptr.ptr,
 						       num_pages,
-						       !obj->userptr.read_only,
+						       !i915_gem_object_is_readonly(obj),
 						       pvec);
 	}
 
@@ -789,10 +789,15 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -EFAULT;
 
 	if (args->flags & I915_USERPTR_READ_ONLY) {
-		/* On almost all of the current hw, we cannot tell the GPU that a
-		 * page is readonly, so this is just a placeholder in the uAPI.
+		struct i915_hw_ppgtt *ppgtt;
+
+		/*
+		 * On almost all of the older hw, we cannot tell the GPU that
+		 * a page is readonly.
 		 */
-		return -ENODEV;
+		ppgtt = dev_priv->kernel_context->ppgtt;
+		if (!ppgtt || !ppgtt->vm.has_read_only)
+			return -ENODEV;
 	}
 
 	obj = i915_gem_object_alloc(dev_priv);
@@ -806,7 +811,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
 
 	obj->userptr.ptr = args->user_ptr;
-	obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY);
+	if (args->flags & I915_USERPTR_READ_ONLY)
+		i915_gem_object_set_readonly(obj);
 
 	/* And keep a pointer to the current->mm for resolving the user pages
 	 * at binding. This means that we need to hook into the mmu_notifier
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index df524c9cad40..f7f2aa71d8d9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -31,6 +31,7 @@
 #include <linux/stop_machine.h>
 #include <linux/zlib.h>
 #include <drm/drm_print.h>
+#include <linux/ascii85.h>
 
 #include "i915_gpu_error.h"
 #include "i915_drv.h"
@@ -335,21 +336,16 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				struct drm_i915_error_buffer *err,
 				int count)
 {
-	int i;
-
 	err_printf(m, "%s [%d]:\n", name, count);
 
 	while (count--) {
-		err_printf(m, "    %08x_%08x %8u %02x %02x [ ",
+		err_printf(m, "    %08x_%08x %8u %02x %02x %02x",
 			   upper_32_bits(err->gtt_offset),
 			   lower_32_bits(err->gtt_offset),
 			   err->size,
 			   err->read_domains,
-			   err->write_domain);
-		for (i = 0; i < I915_NUM_ENGINES; i++)
-			err_printf(m, "%02x ", err->rseqno[i]);
-
-		err_printf(m, "] %02x", err->wseqno);
+			   err->write_domain,
+			   err->wseqno);
 		err_puts(m, tiling_flag(err->tiling));
 		err_puts(m, dirty_flag(err->dirty));
 		err_puts(m, purgeable_flag(err->purgeable));
@@ -522,35 +518,12 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-static int
-ascii85_encode_len(int len)
-{
-	return DIV_ROUND_UP(len, 4);
-}
-
-static bool
-ascii85_encode(u32 in, char *out)
-{
-	int i;
-
-	if (in == 0)
-		return false;
-
-	out[5] = '\0';
-	for (i = 5; i--; ) {
-		out[i] = '!' + in % 85;
-		in /= 85;
-	}
-
-	return true;
-}
-
 static void print_error_obj(struct drm_i915_error_state_buf *m,
 			    struct intel_engine_cs *engine,
 			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
-	char out[6];
+	char out[ASCII85_BUFSZ];
 	int page;
 
 	if (!obj)
@@ -572,12 +545,8 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 			len -= obj->unused;
 		len = ascii85_encode_len(len);
 
-		for (i = 0; i < len; i++) {
-			if (ascii85_encode(obj->pages[page][i], out))
-				err_puts(m, out);
-			else
-				err_puts(m, "z");
-		}
+		for (i = 0; i < len; i++)
+			err_puts(m, ascii85_encode(obj->pages[page][i], out));
 	}
 	err_puts(m, "\n");
 }
@@ -1021,13 +990,10 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 		       struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	int i;
 
 	err->size = obj->base.size;
 	err->name = obj->base.name;
 
-	for (i = 0; i < I915_NUM_ENGINES; i++)
-		err->rseqno[i] = __active_get_seqno(&vma->last_read[i]);
 	err->wseqno = __active_get_seqno(&obj->frontbuffer_write);
 	err->engine = __active_get_engine_id(&obj->frontbuffer_write);
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 58910f1dc67c..f893a4e8b783 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -177,7 +177,7 @@ struct i915_gpu_state {
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;
-		u32 rseqno[I915_NUM_ENGINES], wseqno;
+		u32 wseqno;
 		u64 gtt_offset;
 		u32 read_domains;
 		u32 write_domain;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 46aaef5c1851..5dadefca2ad2 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -122,6 +122,15 @@ static const u32 hpd_gen11[HPD_NUM_PINS] = {
 	[HPD_PORT_F] = GEN11_TC4_HOTPLUG | GEN11_TBT4_HOTPLUG
 };
 
+static const u32 hpd_icp[HPD_NUM_PINS] = {
+	[HPD_PORT_A] = SDE_DDIA_HOTPLUG_ICP,
+	[HPD_PORT_B] = SDE_DDIB_HOTPLUG_ICP,
+	[HPD_PORT_C] = SDE_TC1_HOTPLUG_ICP,
+	[HPD_PORT_D] = SDE_TC2_HOTPLUG_ICP,
+	[HPD_PORT_E] = SDE_TC3_HOTPLUG_ICP,
+	[HPD_PORT_F] = SDE_TC4_HOTPLUG_ICP
+};
+
 /* IIR can theoretically queue up two events. Be paranoid. */
 #define GEN8_IRQ_RESET_NDX(type, which) do { \
 	I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
@@ -254,9 +263,9 @@ static u32
 gen11_gt_engine_identity(struct drm_i915_private * const i915,
 			 const unsigned int bank, const unsigned int bit);
 
-bool gen11_reset_one_iir(struct drm_i915_private * const i915,
-			 const unsigned int bank,
-			 const unsigned int bit)
+static bool gen11_reset_one_iir(struct drm_i915_private * const i915,
+				const unsigned int bank,
+				const unsigned int bit)
 {
 	void __iomem * const regs = i915->regs;
 	u32 dw;
@@ -1145,21 +1154,21 @@ static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv)
 
 static void notify_ring(struct intel_engine_cs *engine)
 {
+	const u32 seqno = intel_engine_get_seqno(engine);
 	struct i915_request *rq = NULL;
+	struct task_struct *tsk = NULL;
 	struct intel_wait *wait;
 
-	if (!engine->breadcrumbs.irq_armed)
+	if (unlikely(!engine->breadcrumbs.irq_armed))
 		return;
 
-	atomic_inc(&engine->irq_count);
-	set_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
+	rcu_read_lock();
 
 	spin_lock(&engine->breadcrumbs.irq_lock);
 	wait = engine->breadcrumbs.irq_wait;
 	if (wait) {
-		bool wakeup = engine->irq_seqno_barrier;
-
-		/* We use a callback from the dma-fence to submit
+		/*
+		 * We use a callback from the dma-fence to submit
 		 * requests after waiting on our own requests. To
 		 * ensure minimum delay in queuing the next request to
 		 * hardware, signal the fence now rather than wait for
@@ -1170,19 +1179,26 @@ static void notify_ring(struct intel_engine_cs *engine)
 		 * and to handle coalescing of multiple seqno updates
 		 * and many waiters.
 		 */
-		if (i915_seqno_passed(intel_engine_get_seqno(engine),
-				      wait->seqno)) {
+		if (i915_seqno_passed(seqno, wait->seqno)) {
 			struct i915_request *waiter = wait->request;
 
-			wakeup = true;
-			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+			if (waiter &&
+			    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 				      &waiter->fence.flags) &&
 			    intel_wait_check_request(wait, waiter))
 				rq = i915_request_get(waiter);
+
+			tsk = wait->tsk;
+		} else {
+			if (engine->irq_seqno_barrier &&
+			    i915_seqno_passed(seqno, wait->seqno - 1)) {
+				set_bit(ENGINE_IRQ_BREADCRUMB,
+					&engine->irq_posted);
+				tsk = wait->tsk;
+			}
 		}
 
-		if (wakeup)
-			wake_up_process(wait->tsk);
+		engine->breadcrumbs.irq_count++;
 	} else {
 		if (engine->breadcrumbs.irq_armed)
 			__intel_engine_disarm_breadcrumbs(engine);
@@ -1190,11 +1206,19 @@ static void notify_ring(struct intel_engine_cs *engine)
 	spin_unlock(&engine->breadcrumbs.irq_lock);
 
 	if (rq) {
-		dma_fence_signal(&rq->fence);
+		spin_lock(&rq->lock);
+		dma_fence_signal_locked(&rq->fence);
 		GEM_BUG_ON(!i915_request_completed(rq));
+		spin_unlock(&rq->lock);
+
 		i915_request_put(rq);
 	}
 
+	if (tsk && tsk->state & TASK_NORMAL)
+		wake_up_process(tsk);
+
+	rcu_read_unlock();
+
 	trace_intel_engine_notify(engine, wait);
 }
 
@@ -1469,14 +1493,10 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 static void
 gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	bool tasklet = false;
 
-	if (iir & GT_CONTEXT_SWITCH_INTERRUPT) {
-		if (READ_ONCE(engine->execlists.active))
-			tasklet = !test_and_set_bit(ENGINE_IRQ_EXECLIST,
-						    &engine->irq_posted);
-	}
+	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
+		tasklet = true;
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
 		notify_ring(engine);
@@ -1484,7 +1504,7 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 	}
 
 	if (tasklet)
-		tasklet_hi_schedule(&execlists->tasklet);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
 }
 
 static void gen8_gt_irq_ack(struct drm_i915_private *i915,
@@ -1556,94 +1576,122 @@ static void gen8_gt_irq_handler(struct drm_i915_private *i915,
 	}
 }
 
-static bool gen11_port_hotplug_long_detect(enum port port, u32 val)
+static bool gen11_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_C:
+	switch (pin) {
+	case HPD_PORT_C:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1);
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2);
-	case PORT_E:
+	case HPD_PORT_E:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3);
-	case PORT_F:
+	case HPD_PORT_F:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4);
 	default:
 		return false;
 	}
 }
 
-static bool bxt_port_hotplug_long_detect(enum port port, u32 val)
+static bool bxt_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & PORTA_HOTPLUG_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool spt_port_hotplug2_long_detect(enum port port, u32 val)
+static bool icp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_E:
+	switch (pin) {
+	case HPD_PORT_A:
+		return val & ICP_DDIA_HPD_LONG_DETECT;
+	case HPD_PORT_B:
+		return val & ICP_DDIB_HPD_LONG_DETECT;
+	default:
+		return false;
+	}
+}
+
+static bool icp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
+{
+	switch (pin) {
+	case HPD_PORT_C:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1);
+	case HPD_PORT_D:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2);
+	case HPD_PORT_E:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3);
+	case HPD_PORT_F:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4);
+	default:
+		return false;
+	}
+}
+
+static bool spt_port_hotplug2_long_detect(enum hpd_pin pin, u32 val)
+{
+	switch (pin) {
+	case HPD_PORT_E:
 		return val & PORTE_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool spt_port_hotplug_long_detect(enum port port, u32 val)
+static bool spt_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & PORTA_HOTPLUG_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool ilk_port_hotplug_long_detect(enum port port, u32 val)
+static bool ilk_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & DIGITAL_PORTA_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool pch_port_hotplug_long_detect(enum port port, u32 val)
+static bool pch_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_B:
+	switch (pin) {
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool i9xx_port_hotplug_long_detect(enum port port, u32 val)
+static bool i9xx_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_B:
+	switch (pin) {
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_INT_LONG_PULSE;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_INT_LONG_PULSE;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_INT_LONG_PULSE;
 	default:
 		return false;
@@ -1661,27 +1709,22 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
 			       u32 *pin_mask, u32 *long_mask,
 			       u32 hotplug_trigger, u32 dig_hotplug_reg,
 			       const u32 hpd[HPD_NUM_PINS],
-			       bool long_pulse_detect(enum port port, u32 val))
+			       bool long_pulse_detect(enum hpd_pin pin, u32 val))
 {
-	enum port port;
-	int i;
+	enum hpd_pin pin;
 
-	for_each_hpd_pin(i) {
-		if ((hpd[i] & hotplug_trigger) == 0)
+	for_each_hpd_pin(pin) {
+		if ((hpd[pin] & hotplug_trigger) == 0)
 			continue;
 
-		*pin_mask |= BIT(i);
-
-		port = intel_hpd_pin_to_port(dev_priv, i);
-		if (port == PORT_NONE)
-			continue;
+		*pin_mask |= BIT(pin);
 
-		if (long_pulse_detect(port, dig_hotplug_reg))
-			*long_mask |= BIT(i);
+		if (long_pulse_detect(pin, dig_hotplug_reg))
+			*long_mask |= BIT(pin);
 	}
 
-	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x\n",
-			 hotplug_trigger, dig_hotplug_reg, *pin_mask);
+	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x, long 0x%08x\n",
+			 hotplug_trigger, dig_hotplug_reg, *pin_mask, *long_mask);
 
 }
 
@@ -1703,69 +1746,34 @@ static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
 					 uint32_t crc4)
 {
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	struct intel_pipe_crc_entry *entry;
 	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-	struct drm_driver *driver = dev_priv->drm.driver;
 	uint32_t crcs[5];
-	int head, tail;
 
 	spin_lock(&pipe_crc->lock);
-	if (pipe_crc->source && !crtc->base.crc.opened) {
-		if (!pipe_crc->entries) {
-			spin_unlock(&pipe_crc->lock);
-			DRM_DEBUG_KMS("spurious interrupt\n");
-			return;
-		}
-
-		head = pipe_crc->head;
-		tail = pipe_crc->tail;
-
-		if (CIRC_SPACE(head, tail, INTEL_PIPE_CRC_ENTRIES_NR) < 1) {
-			spin_unlock(&pipe_crc->lock);
-			DRM_ERROR("CRC buffer overflowing\n");
-			return;
-		}
-
-		entry = &pipe_crc->entries[head];
-
-		entry->frame = driver->get_vblank_counter(&dev_priv->drm, pipe);
-		entry->crc[0] = crc0;
-		entry->crc[1] = crc1;
-		entry->crc[2] = crc2;
-		entry->crc[3] = crc3;
-		entry->crc[4] = crc4;
-
-		head = (head + 1) & (INTEL_PIPE_CRC_ENTRIES_NR - 1);
-		pipe_crc->head = head;
-
-		spin_unlock(&pipe_crc->lock);
-
-		wake_up_interruptible(&pipe_crc->wq);
-	} else {
-		/*
-		 * For some not yet identified reason, the first CRC is
-		 * bonkers. So let's just wait for the next vblank and read
-		 * out the buggy result.
-		 *
-		 * On GEN8+ sometimes the second CRC is bonkers as well, so
-		 * don't trust that one either.
-		 */
-		if (pipe_crc->skipped <= 0 ||
-		    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
-			pipe_crc->skipped++;
-			spin_unlock(&pipe_crc->lock);
-			return;
-		}
+	/*
+	 * For some not yet identified reason, the first CRC is
+	 * bonkers. So let's just wait for the next vblank and read
+	 * out the buggy result.
+	 *
+	 * On GEN8+ sometimes the second CRC is bonkers as well, so
+	 * don't trust that one either.
+	 */
+	if (pipe_crc->skipped <= 0 ||
+	    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
+		pipe_crc->skipped++;
 		spin_unlock(&pipe_crc->lock);
-		crcs[0] = crc0;
-		crcs[1] = crc1;
-		crcs[2] = crc2;
-		crcs[3] = crc3;
-		crcs[4] = crc4;
-		drm_crtc_add_crc_entry(&crtc->base, true,
-				       drm_crtc_accurate_vblank_count(&crtc->base),
-				       crcs);
+		return;
 	}
+	spin_unlock(&pipe_crc->lock);
+
+	crcs[0] = crc0;
+	crcs[1] = crc1;
+	crcs[2] = crc2;
+	crcs[3] = crc3;
+	crcs[4] = crc4;
+	drm_crtc_add_crc_entry(&crtc->base, true,
+				drm_crtc_accurate_vblank_count(&crtc->base),
+				crcs);
 }
 #else
 static inline void
@@ -2021,10 +2029,38 @@ static void valleyview_pipestat_irq_handler(struct drm_i915_private *dev_priv,
 
 static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+	u32 hotplug_status = 0, hotplug_status_mask;
+	int i;
+
+	if (IS_G4X(dev_priv) ||
+	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		hotplug_status_mask = HOTPLUG_INT_STATUS_G4X |
+			DP_AUX_CHANNEL_MASK_INT_STATUS_G4X;
+	else
+		hotplug_status_mask = HOTPLUG_INT_STATUS_I915;
+
+	/*
+	 * We absolutely have to clear all the pending interrupt
+	 * bits in PORT_HOTPLUG_STAT. Otherwise the ISR port
+	 * interrupt bit won't have an edge, and the i965/g4x
+	 * edge triggered IIR will not notice that an interrupt
+	 * is still pending. We can't use PORT_HOTPLUG_EN to
+	 * guarantee the edge as the act of toggling the enable
+	 * bits can itself generate a new hotplug interrupt :(
+	 */
+	for (i = 0; i < 10; i++) {
+		u32 tmp = I915_READ(PORT_HOTPLUG_STAT) & hotplug_status_mask;
+
+		if (tmp == 0)
+			return hotplug_status;
 
-	if (hotplug_status)
+		hotplug_status |= tmp;
 		I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+	}
+
+	WARN_ONCE(1,
+		  "PORT_HOTPLUG_STAT did not clear (0x%08x)\n",
+		  I915_READ(PORT_HOTPLUG_STAT));
 
 	return hotplug_status;
 }
@@ -2131,7 +2167,6 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(VLV_IER, ier);
 		I915_WRITE(VLV_MASTER_IER, MASTER_INTERRUPT_ENABLE);
-		POSTING_READ(VLV_MASTER_IER);
 
 		if (gt_iir)
 			snb_gt_irq_handler(dev_priv, gt_iir);
@@ -2216,7 +2251,6 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(VLV_IER, ier);
 		I915_WRITE(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
-		POSTING_READ(GEN8_MASTER_IRQ);
 
 		gen8_gt_irq_handler(dev_priv, master_ctl, gt_iir);
 
@@ -2385,6 +2419,43 @@ static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		cpt_serr_int_handler(dev_priv);
 }
 
+static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
+{
+	u32 ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
+	u32 tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP;
+	u32 pin_mask = 0, long_mask = 0;
+
+	if (ddi_hotplug_trigger) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_DDI);
+		I915_WRITE(SHOTPLUG_CTL_DDI, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   ddi_hotplug_trigger,
+				   dig_hotplug_reg, hpd_icp,
+				   icp_ddi_port_hotplug_long_detect);
+	}
+
+	if (tc_hotplug_trigger) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_TC);
+		I915_WRITE(SHOTPLUG_CTL_TC, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   tc_hotplug_trigger,
+				   dig_hotplug_reg, hpd_icp,
+				   icp_tc_port_hotplug_long_detect);
+	}
+
+	if (pin_mask)
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
+
+	if (pch_iir & SDE_GMBUS_ICP)
+		gmbus_irq_handler(dev_priv);
+}
+
 static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT &
@@ -2548,7 +2619,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	/* disable master interrupt before clearing iir  */
 	de_ier = I915_READ(DEIER);
 	I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL);
-	POSTING_READ(DEIER);
 
 	/* Disable south interrupts. We'll only write to SDEIIR once, so further
 	 * interrupts will will be stored on its back queue, and then we'll be
@@ -2558,7 +2628,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (!HAS_PCH_NOP(dev_priv)) {
 		sde_ier = I915_READ(SDEIER);
 		I915_WRITE(SDEIER, 0);
-		POSTING_READ(SDEIER);
 	}
 
 	/* Find, clear, then process each source of interrupt */
@@ -2593,11 +2662,8 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	}
 
 	I915_WRITE(DEIER, de_ier);
-	POSTING_READ(DEIER);
-	if (!HAS_PCH_NOP(dev_priv)) {
+	if (!HAS_PCH_NOP(dev_priv))
 		I915_WRITE(SDEIER, sde_ier);
-		POSTING_READ(SDEIER);
-	}
 
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	enable_rpm_wakeref_asserts(dev_priv);
@@ -2804,8 +2870,11 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv) ||
-			    HAS_PCH_CNP(dev_priv))
+			if (HAS_PCH_ICP(dev_priv))
+				icp_irq_handler(dev_priv, iir);
+			else if (HAS_PCH_SPT(dev_priv) ||
+				 HAS_PCH_KBP(dev_priv) ||
+				 HAS_PCH_CNP(dev_priv))
 				spt_irq_handler(dev_priv, iir);
 			else
 				cpt_irq_handler(dev_priv, iir);
@@ -3170,7 +3239,7 @@ static void i915_clear_error_registers(struct drm_i915_private *dev_priv)
 		 */
 		DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir);
 		I915_WRITE(EMR, I915_READ(EMR) | eir);
-		I915_WRITE(IIR, I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		I915_WRITE(IIR, I915_MASTER_ERROR_INTERRUPT);
 	}
 }
 
@@ -3584,6 +3653,9 @@ static void gen11_irq_reset(struct drm_device *dev)
 	GEN3_IRQ_RESET(GEN11_DE_HPD_);
 	GEN3_IRQ_RESET(GEN11_GU_MISC_);
 	GEN3_IRQ_RESET(GEN8_PCU_);
+
+	if (HAS_PCH_ICP(dev_priv))
+		GEN3_IRQ_RESET(SDE);
 }
 
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
@@ -3700,6 +3772,35 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	ibx_hpd_detection_setup(dev_priv);
 }
 
+static void icp_hpd_detection_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug;
+
+	hotplug = I915_READ(SHOTPLUG_CTL_DDI);
+	hotplug |= ICP_DDIA_HPD_ENABLE |
+		   ICP_DDIB_HPD_ENABLE;
+	I915_WRITE(SHOTPLUG_CTL_DDI, hotplug);
+
+	hotplug = I915_READ(SHOTPLUG_CTL_TC);
+	hotplug |= ICP_TC_HPD_ENABLE(PORT_TC1) |
+		   ICP_TC_HPD_ENABLE(PORT_TC2) |
+		   ICP_TC_HPD_ENABLE(PORT_TC3) |
+		   ICP_TC_HPD_ENABLE(PORT_TC4);
+	I915_WRITE(SHOTPLUG_CTL_TC, hotplug);
+}
+
+static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug_irqs, enabled_irqs;
+
+	hotplug_irqs = SDE_DDI_MASK_ICP | SDE_TC_MASK_ICP;
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_icp);
+
+	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
+
+	icp_hpd_detection_setup(dev_priv);
+}
+
 static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug;
@@ -3733,6 +3834,9 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	POSTING_READ(GEN11_DE_HPD_IMR);
 
 	gen11_hpd_detection_setup(dev_priv);
+
+	if (HAS_PCH_ICP(dev_priv))
+		icp_hpd_irq_setup(dev_priv);
 }
 
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
@@ -4168,11 +4272,29 @@ static void gen11_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_MASK,  ~0);
 }
 
+static void icp_irq_postinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 mask = SDE_GMBUS_ICP;
+
+	WARN_ON(I915_READ(SDEIER) != 0);
+	I915_WRITE(SDEIER, 0xffffffff);
+	POSTING_READ(SDEIER);
+
+	gen3_assert_iir_is_zero(dev_priv, SDEIIR);
+	I915_WRITE(SDEIMR, ~mask);
+
+	icp_hpd_detection_setup(dev_priv);
+}
+
 static int gen11_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 gu_misc_masked = GEN11_GU_MISC_GSE;
 
+	if (HAS_PCH_ICP(dev_priv))
+		icp_irq_postinstall(dev);
+
 	gen11_gt_irq_postinstall(dev_priv);
 	gen8_de_irq_postinstall(dev_priv);
 
@@ -4225,11 +4347,13 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 	/* Unmask the interrupts that we always want on. */
 	dev_priv->irq_mask =
 		~(I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	GEN2_IRQ_INIT(, dev_priv->irq_mask, enable_mask);
@@ -4244,6 +4368,81 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 	return 0;
 }
 
+static void i8xx_error_irq_ack(struct drm_i915_private *dev_priv,
+			       u16 *eir, u16 *eir_stuck)
+{
+	u16 emr;
+
+	*eir = I915_READ16(EIR);
+
+	if (*eir)
+		I915_WRITE16(EIR, *eir);
+
+	*eir_stuck = I915_READ16(EIR);
+	if (*eir_stuck == 0)
+		return;
+
+	/*
+	 * Toggle all EMR bits to make sure we get an edge
+	 * in the ISR master error bit if we don't clear
+	 * all the EIR bits. Otherwise the edge triggered
+	 * IIR on i965/g4x wouldn't notice that an interrupt
+	 * is still pending. Also some EIR bits can't be
+	 * cleared except by handling the underlying error
+	 * (or by a GPU reset) so we mask any bit that
+	 * remains set.
+	 */
+	emr = I915_READ16(EMR);
+	I915_WRITE16(EMR, 0xffff);
+	I915_WRITE16(EMR, emr | *eir_stuck);
+}
+
+static void i8xx_error_irq_handler(struct drm_i915_private *dev_priv,
+				   u16 eir, u16 eir_stuck)
+{
+	DRM_DEBUG("Master Error: EIR 0x%04x\n", eir);
+
+	if (eir_stuck)
+		DRM_DEBUG_DRIVER("EIR stuck: 0x%04x, masked\n", eir_stuck);
+}
+
+static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv,
+			       u32 *eir, u32 *eir_stuck)
+{
+	u32 emr;
+
+	*eir = I915_READ(EIR);
+
+	I915_WRITE(EIR, *eir);
+
+	*eir_stuck = I915_READ(EIR);
+	if (*eir_stuck == 0)
+		return;
+
+	/*
+	 * Toggle all EMR bits to make sure we get an edge
+	 * in the ISR master error bit if we don't clear
+	 * all the EIR bits. Otherwise the edge triggered
+	 * IIR on i965/g4x wouldn't notice that an interrupt
+	 * is still pending. Also some EIR bits can't be
+	 * cleared except by handling the underlying error
+	 * (or by a GPU reset) so we mask any bit that
+	 * remains set.
+	 */
+	emr = I915_READ(EMR);
+	I915_WRITE(EMR, 0xffffffff);
+	I915_WRITE(EMR, emr | *eir_stuck);
+}
+
+static void i9xx_error_irq_handler(struct drm_i915_private *dev_priv,
+				   u32 eir, u32 eir_stuck)
+{
+	DRM_DEBUG("Master Error, EIR 0x%08x\n", eir);
+
+	if (eir_stuck)
+		DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masked\n", eir_stuck);
+}
+
 static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
@@ -4258,6 +4457,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u16 eir = 0, eir_stuck = 0;
 		u16 iir;
 
 		iir = I915_READ16(IIR);
@@ -4270,13 +4470,16 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i8xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE16(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[RCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		i8xx_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
@@ -4314,12 +4517,14 @@ static int i915_irq_postinstall(struct drm_device *dev)
 	dev_priv->irq_mask =
 		~(I915_ASLE_INTERRUPT |
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (I915_HAS_HOTPLUG(dev_priv)) {
@@ -4357,6 +4562,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u32 eir = 0, eir_stuck = 0;
 		u32 hotplug_status = 0;
 		u32 iir;
 
@@ -4374,13 +4580,16 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[RCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
@@ -4434,14 +4643,14 @@ static int i965_irq_postinstall(struct drm_device *dev)
 		  I915_DISPLAY_PORT_INTERRUPT |
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		  I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PORT_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (IS_G4X(dev_priv))
@@ -4501,6 +4710,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u32 eir = 0, eir_stuck = 0;
 		u32 hotplug_status = 0;
 		u32 iir;
 
@@ -4517,6 +4727,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
@@ -4525,8 +4738,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		if (iir & I915_BSD_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[VCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 49fcc4679db6..295e981e4a39 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -44,10 +44,6 @@ i915_param_named(modeset, int, 0400,
 	"Use kernel modesetting [KMS] (0=disable, "
 	"1=on, -1=force vga console preference [default])");
 
-i915_param_named_unsafe(panel_ignore_lid, int, 0600,
-	"Override lid status (0=autodetect, 1=autodetect disabled [default], "
-	"-1=force lid closed, -2=force lid open)");
-
 i915_param_named_unsafe(enable_dc, int, 0400,
 	"Enable power-saving display C-states. "
 	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)");
@@ -92,7 +88,7 @@ i915_param_named_unsafe(enable_ppgtt, int, 0400,
 
 i915_param_named_unsafe(enable_psr, int, 0600,
 	"Enable PSR "
-	"(0=disabled, 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode) "
+	"(0=disabled, 1=enabled) "
 	"Default: -1 (use per-chip default)");
 
 i915_param_named_unsafe(alpha_support, bool, 0400,
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index aebe0469ddaa..6c4d4a21474b 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -36,7 +36,6 @@ struct drm_printer;
 #define I915_PARAMS_FOR_EACH(param) \
 	param(char *, vbt_firmware, NULL) \
 	param(int, modeset, -1) \
-	param(int, panel_ignore_lid, 1) \
 	param(int, lvds_channel_mode, 0) \
 	param(int, panel_use_ssc, -1) \
 	param(int, vbt_sdvo_panel_type, -1) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 55543f1b0236..6a4d1388ad2d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -674,10 +674,16 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static void i915_pci_remove(struct pci_dev *pdev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct drm_device *dev;
+
+	dev = pci_get_drvdata(pdev);
+	if (!dev) /* driver load aborted, nothing to cleanup */
+		return;
 
 	i915_driver_unload(dev);
 	drm_dev_put(dev);
+
+	pci_set_drvdata(pdev, NULL);
 }
 
 static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -712,6 +718,11 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		return err;
 
+	if (i915_inject_load_failure()) {
+		i915_pci_remove(pdev);
+		return -ENODEV;
+	}
+
 	err = i915_live_selftests(pdev);
 	if (err) {
 		i915_pci_remove(pdev);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 447407fee3b8..6bf10952c724 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1836,7 +1836,9 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 	 * So far the best way to work around this issue seems to be draining
 	 * the GPU from any submitted work.
 	 */
-	ret = i915_gem_wait_for_idle(dev_priv, wait_flags);
+	ret = i915_gem_wait_for_idle(dev_priv,
+				     wait_flags,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4bfd7a9bd75f..8af945d8a995 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -139,19 +139,35 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 	return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG);
 }
 
+/*
+ * Given the first two numbers __a and __b of arbitrarily many evenly spaced
+ * numbers, pick the 0-based __index'th value.
+ *
+ * Always prefer this over _PICK() if the numbers are evenly spaced.
+ */
+#define _PICK_EVEN(__index, __a, __b) ((__a) + (__index) * ((__b) - (__a)))
+
+/*
+ * Given the arbitrary numbers in varargs, pick the 0-based __index'th number.
+ *
+ * Always prefer _PICK_EVEN() over this if the numbers are evenly spaced.
+ */
 #define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index])
 
-#define _PIPE(pipe, a, b) ((a) + (pipe) * ((b) - (a)))
+/*
+ * Named helper wrappers around _PICK_EVEN() and _PICK().
+ */
+#define _PIPE(pipe, a, b) _PICK_EVEN(pipe, a, b)
 #define _MMIO_PIPE(pipe, a, b) _MMIO(_PIPE(pipe, a, b))
-#define _PLANE(plane, a, b) _PIPE(plane, a, b)
+#define _PLANE(plane, a, b) _PICK_EVEN(plane, a, b)
 #define _MMIO_PLANE(plane, a, b) _MMIO_PIPE(plane, a, b)
-#define _TRANS(tran, a, b) ((a) + (tran) * ((b) - (a)))
+#define _TRANS(tran, a, b) _PICK_EVEN(tran, a, b)
 #define _MMIO_TRANS(tran, a, b) _MMIO(_TRANS(tran, a, b))
-#define _PORT(port, a, b) ((a) + (port) * ((b) - (a)))
+#define _PORT(port, a, b) _PICK_EVEN(port, a, b)
 #define _MMIO_PORT(port, a, b) _MMIO(_PORT(port, a, b))
 #define _MMIO_PIPE3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
 #define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
-#define _PLL(pll, a, b) ((a) + (pll) * ((b) - (a)))
+#define _PLL(pll, a, b) _PICK_EVEN(pll, a, b)
 #define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b))
 #define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
 #define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
@@ -396,6 +412,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN8_STOLEN_RESERVED_4M		(2 << 7)
 #define GEN8_STOLEN_RESERVED_8M		(3 << 7)
 #define GEN6_STOLEN_RESERVED_ENABLE	(1 << 0)
+#define GEN11_STOLEN_RESERVED_ADDR_MASK	(0xFFFFFFFFFFFULL << 20)
 
 /* VGA stuff */
 
@@ -1045,13 +1062,13 @@ enum i915_power_well_id {
 
 	/*
 	 * HSW/BDW
-	 *  - HSW_PWR_WELL_CTL_DRIVER(0) (status bit: id*2, req bit: id*2+1)
+	 *  - _HSW_PWR_WELL_CTL1-4 (status bit: id*2, req bit: id*2+1)
 	 */
 	HSW_DISP_PW_GLOBAL = 15,
 
 	/*
 	 * GEN9+
-	 *  - HSW_PWR_WELL_CTL_DRIVER(0) (status bit: id*2, req bit: id*2+1)
+	 *  - _HSW_PWR_WELL_CTL1-4 (status bit: id*2, req bit: id*2+1)
 	 */
 	SKL_DISP_PW_MISC_IO = 0,
 	SKL_DISP_PW_DDI_A_E,
@@ -1075,17 +1092,54 @@ enum i915_power_well_id {
 	SKL_DISP_PW_2,
 
 	/* - custom power wells */
-	SKL_DISP_PW_DC_OFF,
 	BXT_DPIO_CMN_A,
 	BXT_DPIO_CMN_BC,
-	GLK_DPIO_CMN_C,			/* 19 */
+	GLK_DPIO_CMN_C,			/* 18 */
+
+	/*
+	 * GEN11+
+	 *  - _HSW_PWR_WELL_CTL1-4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_1 = 0,
+	ICL_DISP_PW_2,
+	ICL_DISP_PW_3,
+	ICL_DISP_PW_4,
+
+	/*
+	 *  - _HSW_PWR_WELL_CTL_AUX1/2/4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_AUX_A = 16,
+	ICL_DISP_PW_AUX_B,
+	ICL_DISP_PW_AUX_C,
+	ICL_DISP_PW_AUX_D,
+	ICL_DISP_PW_AUX_E,
+	ICL_DISP_PW_AUX_F,
+
+	ICL_DISP_PW_AUX_TBT1 = 24,
+	ICL_DISP_PW_AUX_TBT2,
+	ICL_DISP_PW_AUX_TBT3,
+	ICL_DISP_PW_AUX_TBT4,
+
+	/*
+	 *  - _HSW_PWR_WELL_CTL_DDI1/2/4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_DDI_A = 32,
+	ICL_DISP_PW_DDI_B,
+	ICL_DISP_PW_DDI_C,
+	ICL_DISP_PW_DDI_D,
+	ICL_DISP_PW_DDI_E,
+	ICL_DISP_PW_DDI_F,                      /* 37 */
 
 	/*
 	 * Multiple platforms.
 	 * Must start following the highest ID of any platform.
 	 * - custom power wells
 	 */
-	I915_DISP_PW_ALWAYS_ON = 20,
+	SKL_DISP_PW_DC_OFF = 38,
+	I915_DISP_PW_ALWAYS_ON,
 };
 
 #define PUNIT_REG_PWRGT_CTRL			0x60
@@ -1667,6 +1721,26 @@ enum i915_power_well_id {
 #define ICL_PORT_CL_DW5(port)	_MMIO_PORT(port, _ICL_PORT_CL_DW5_A, \
 						 _ICL_PORT_CL_DW5_B)
 
+#define _CNL_PORT_CL_DW10_A		0x162028
+#define _ICL_PORT_CL_DW10_B		0x6c028
+#define ICL_PORT_CL_DW10(port)		_MMIO_PORT(port,	\
+						   _CNL_PORT_CL_DW10_A, \
+						   _ICL_PORT_CL_DW10_B)
+#define  PG_SEQ_DELAY_OVERRIDE_MASK	(3 << 25)
+#define  PG_SEQ_DELAY_OVERRIDE_SHIFT	25
+#define  PG_SEQ_DELAY_OVERRIDE_ENABLE	(1 << 24)
+#define  PWR_UP_ALL_LANES		(0x0 << 4)
+#define  PWR_DOWN_LN_3_2_1		(0xe << 4)
+#define  PWR_DOWN_LN_3_2		(0xc << 4)
+#define  PWR_DOWN_LN_3			(0x8 << 4)
+#define  PWR_DOWN_LN_2_1_0		(0x7 << 4)
+#define  PWR_DOWN_LN_1_0		(0x3 << 4)
+#define  PWR_DOWN_LN_1			(0x2 << 4)
+#define  PWR_DOWN_LN_3_1		(0xa << 4)
+#define  PWR_DOWN_LN_3_1_0		(0xb << 4)
+#define  PWR_DOWN_LN_MASK		(0xf << 4)
+#define  PWR_DOWN_LN_SHIFT		4
+
 #define _PORT_CL1CM_DW9_A		0x162024
 #define _PORT_CL1CM_DW9_BC		0x6C024
 #define   IREF0RC_OFFSET_SHIFT		8
@@ -1679,6 +1753,13 @@ enum i915_power_well_id {
 #define   IREF1RC_OFFSET_MASK		(0xFF << IREF1RC_OFFSET_SHIFT)
 #define BXT_PORT_CL1CM_DW10(phy)	_BXT_PHY((phy), _PORT_CL1CM_DW10_BC)
 
+#define _ICL_PORT_CL_DW12_A		0x162030
+#define _ICL_PORT_CL_DW12_B		0x6C030
+#define   ICL_LANE_ENABLE_AUX		(1 << 0)
+#define ICL_PORT_CL_DW12(port)		_MMIO_PORT((port),		\
+						   _ICL_PORT_CL_DW12_A, \
+						   _ICL_PORT_CL_DW12_B)
+
 #define _PORT_CL1CM_DW28_A		0x162070
 #define _PORT_CL1CM_DW28_BC		0x6C070
 #define   OCL1_POWER_DOWN_EN		(1 << 23)
@@ -1716,16 +1797,22 @@ enum i915_power_well_id {
 						    _CNL_PORT_PCS_DW1_LN0_D, \
 						    _CNL_PORT_PCS_DW1_LN0_AE, \
 						    _CNL_PORT_PCS_DW1_LN0_F))
+
 #define _ICL_PORT_PCS_DW1_GRP_A		0x162604
 #define _ICL_PORT_PCS_DW1_GRP_B		0x6C604
 #define _ICL_PORT_PCS_DW1_LN0_A		0x162804
 #define _ICL_PORT_PCS_DW1_LN0_B		0x6C804
+#define _ICL_PORT_PCS_DW1_AUX_A		0x162304
+#define _ICL_PORT_PCS_DW1_AUX_B		0x6c304
 #define ICL_PORT_PCS_DW1_GRP(port)	_MMIO_PORT(port,\
 						   _ICL_PORT_PCS_DW1_GRP_A, \
 						   _ICL_PORT_PCS_DW1_GRP_B)
 #define ICL_PORT_PCS_DW1_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_PCS_DW1_LN0_A, \
 						   _ICL_PORT_PCS_DW1_LN0_B)
+#define ICL_PORT_PCS_DW1_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_PCS_DW1_AUX_A, \
+						   _ICL_PORT_PCS_DW1_AUX_B)
 #define   COMMON_KEEPER_EN		(1 << 26)
 
 /* CNL Port TX registers */
@@ -1762,16 +1849,23 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW2_GRP_B		0x6C688
 #define _ICL_PORT_TX_DW2_LN0_A		0x162888
 #define _ICL_PORT_TX_DW2_LN0_B		0x6C888
+#define _ICL_PORT_TX_DW2_AUX_A		0x162388
+#define _ICL_PORT_TX_DW2_AUX_B		0x6c388
 #define ICL_PORT_TX_DW2_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW2_GRP_A, \
 						   _ICL_PORT_TX_DW2_GRP_B)
 #define ICL_PORT_TX_DW2_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW2_LN0_A, \
 						   _ICL_PORT_TX_DW2_LN0_B)
+#define ICL_PORT_TX_DW2_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW2_AUX_A, \
+						   _ICL_PORT_TX_DW2_AUX_B)
 #define   SWING_SEL_UPPER(x)		(((x) >> 3) << 15)
 #define   SWING_SEL_UPPER_MASK		(1 << 15)
 #define   SWING_SEL_LOWER(x)		(((x) & 0x7) << 11)
 #define   SWING_SEL_LOWER_MASK		(0x7 << 11)
+#define   FRC_LATENCY_OPTIM_MASK	(0x7 << 8)
+#define   FRC_LATENCY_OPTIM_VAL(x)	((x) << 8)
 #define   RCOMP_SCALAR(x)		((x) << 0)
 #define   RCOMP_SCALAR_MASK		(0xFF << 0)
 
@@ -1787,6 +1881,8 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW4_LN0_A		0x162890
 #define _ICL_PORT_TX_DW4_LN1_A		0x162990
 #define _ICL_PORT_TX_DW4_LN0_B		0x6C890
+#define _ICL_PORT_TX_DW4_AUX_A		0x162390
+#define _ICL_PORT_TX_DW4_AUX_B		0x6c390
 #define ICL_PORT_TX_DW4_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW4_GRP_A, \
 						   _ICL_PORT_TX_DW4_GRP_B)
@@ -1795,6 +1891,9 @@ enum i915_power_well_id {
 						   _ICL_PORT_TX_DW4_LN0_B) + \
 					     ((ln) * (_ICL_PORT_TX_DW4_LN1_A - \
 						      _ICL_PORT_TX_DW4_LN0_A)))
+#define ICL_PORT_TX_DW4_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW4_AUX_A, \
+						   _ICL_PORT_TX_DW4_AUX_B)
 #define   LOADGEN_SELECT		(1 << 31)
 #define   POST_CURSOR_1(x)		((x) << 12)
 #define   POST_CURSOR_1_MASK		(0x3F << 12)
@@ -1809,12 +1908,17 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW5_GRP_B		0x6C694
 #define _ICL_PORT_TX_DW5_LN0_A		0x162894
 #define _ICL_PORT_TX_DW5_LN0_B		0x6C894
+#define _ICL_PORT_TX_DW5_AUX_A		0x162394
+#define _ICL_PORT_TX_DW5_AUX_B		0x6c394
 #define ICL_PORT_TX_DW5_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW5_GRP_A, \
 						   _ICL_PORT_TX_DW5_GRP_B)
 #define ICL_PORT_TX_DW5_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW5_LN0_A, \
 						   _ICL_PORT_TX_DW5_LN0_B)
+#define ICL_PORT_TX_DW5_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW5_AUX_A, \
+						   _ICL_PORT_TX_DW5_AUX_B)
 #define   TX_TRAINING_EN		(1 << 31)
 #define   TAP2_DISABLE			(1 << 30)
 #define   TAP3_DISABLE			(1 << 29)
@@ -2811,7 +2915,6 @@ enum i915_power_well_id {
 #define I915_DISPLAY_PORT_INTERRUPT			(1 << 17)
 #define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1 << 16)
 #define I915_MASTER_ERROR_INTERRUPT			(1 << 15)
-#define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1 << 15)
 #define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1 << 14)
 #define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1 << 14) /* p-state */
 #define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1 << 13)
@@ -3020,6 +3123,7 @@ enum i915_power_well_id {
 #define   GMBUS_RATE_400KHZ	(2 << 8) /* reserved on Pineview */
 #define   GMBUS_RATE_1MHZ	(3 << 8) /* reserved on Pineview */
 #define   GMBUS_HOLD_EXT	(1 << 7) /* 300ns hold time, rsvd on Pineview */
+#define   GMBUS_BYTE_CNT_OVERRIDE (1 << 6)
 #define   GMBUS_PIN_DISABLED	0
 #define   GMBUS_PIN_SSC		1
 #define   GMBUS_PIN_VGADDC	2
@@ -3049,6 +3153,7 @@ enum i915_power_well_id {
 #define   GMBUS_CYCLE_STOP	(4 << 25)
 #define   GMBUS_BYTE_COUNT_SHIFT 16
 #define   GMBUS_BYTE_COUNT_MAX   256U
+#define   GEN9_GMBUS_BYTE_COUNT_MAX 511U
 #define   GMBUS_SLAVE_INDEX_SHIFT 8
 #define   GMBUS_SLAVE_ADDR_SHIFT 1
 #define   GMBUS_SLAVE_READ	(1 << 0)
@@ -4044,6 +4149,7 @@ enum {
 #define   EDP_PSR_SKIP_AUX_EXIT			(1 << 12)
 #define   EDP_PSR_TP1_TP2_SEL			(0 << 11)
 #define   EDP_PSR_TP1_TP3_SEL			(1 << 11)
+#define   EDP_PSR_CRC_ENABLE			(1 << 10) /* BDW+ */
 #define   EDP_PSR_TP2_TP3_TIME_500us		(0 << 8)
 #define   EDP_PSR_TP2_TP3_TIME_100us		(1 << 8)
 #define   EDP_PSR_TP2_TP3_TIME_2500us		(2 << 8)
@@ -4072,6 +4178,7 @@ enum {
 
 #define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
 #define   EDP_PSR_STATUS_STATE_MASK		(7 << 29)
+#define   EDP_PSR_STATUS_STATE_SHIFT		29
 #define   EDP_PSR_STATUS_STATE_IDLE		(0 << 29)
 #define   EDP_PSR_STATUS_STATE_SRDONACK		(1 << 29)
 #define   EDP_PSR_STATUS_STATE_SRDENT		(2 << 29)
@@ -4498,6 +4605,16 @@ enum {
 #define   VIDEO_DIP_ENABLE_GMP_HSW	(1 << 4)
 #define   VIDEO_DIP_ENABLE_SPD_HSW	(1 << 0)
 
+#define  DRM_DIP_ENABLE			(1 << 28)
+#define  PSR_VSC_BIT_7_SET		(1 << 27)
+#define  VSC_SELECT_MASK		(0x3 << 26)
+#define  VSC_SELECT_SHIFT		26
+#define  VSC_DIP_HW_HEA_DATA		(0 << 26)
+#define  VSC_DIP_HW_HEA_SW_DATA		(1 << 26)
+#define  VSC_DIP_HW_DATA_SW_HEA		(2 << 26)
+#define  VSC_DIP_SW_HEA_DATA		(3 << 26)
+#define  VDIP_ENABLE_PPS		(1 << 24)
+
 /* Panel power sequencing */
 #define PPS_BASE			0x61200
 #define VLV_PPS_BASE			(VLV_DISPLAY_BASE + PPS_BASE)
@@ -6829,7 +6946,7 @@ enum {
 #define _PS_ECC_STAT_2B     0x68AD0
 #define _PS_ECC_STAT_1C     0x691D0
 
-#define _ID(id, a, b) ((a) + (id) * ((b) - (a)))
+#define _ID(id, a, b) _PICK_EVEN(id, a, b)
 #define SKL_PS_CTRL(pipe, id) _MMIO_PIPE(pipe,        \
 			_ID(id, _PS_1A_CTRL, _PS_2A_CTRL),       \
 			_ID(id, _PS_1B_CTRL, _PS_2B_CTRL))
@@ -7366,6 +7483,14 @@ enum {
 #define BDW_SCRATCH1					_MMIO(0xb11c)
 #define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
 
+/*GEN11 chicken */
+#define _PIPEA_CHICKEN			0x70038
+#define _PIPEB_CHICKEN			0x71038
+#define _PIPEC_CHICKEN			0x72038
+#define  PER_PIXEL_ALPHA_BYPASS_EN	(1 << 7)
+#define PIPE_CHICKEN(pipe)		_MMIO_PIPE(pipe, _PIPEA_CHICKEN,\
+						   _PIPEB_CHICKEN)
+
 /* PCH */
 
 /* south display engine interrupt: IBX */
@@ -7409,7 +7534,7 @@ enum {
 #define SDE_TRANSA_FIFO_UNDER	(1 << 0)
 #define SDE_TRANS_MASK		(0x3f)
 
-/* south display engine interrupt: CPT/PPT */
+/* south display engine interrupt: CPT - CNP */
 #define SDE_AUDIO_POWER_D_CPT	(1 << 31)
 #define SDE_AUDIO_POWER_C_CPT	(1 << 30)
 #define SDE_AUDIO_POWER_B_CPT	(1 << 29)
@@ -7457,6 +7582,21 @@ enum {
 				 SDE_FDI_RXB_CPT | \
 				 SDE_FDI_RXA_CPT)
 
+/* south display engine interrupt: ICP */
+#define SDE_TC4_HOTPLUG_ICP		(1 << 27)
+#define SDE_TC3_HOTPLUG_ICP		(1 << 26)
+#define SDE_TC2_HOTPLUG_ICP		(1 << 25)
+#define SDE_TC1_HOTPLUG_ICP		(1 << 24)
+#define SDE_GMBUS_ICP			(1 << 23)
+#define SDE_DDIB_HOTPLUG_ICP		(1 << 17)
+#define SDE_DDIA_HOTPLUG_ICP		(1 << 16)
+#define SDE_DDI_MASK_ICP		(SDE_DDIB_HOTPLUG_ICP |	\
+					 SDE_DDIA_HOTPLUG_ICP)
+#define SDE_TC_MASK_ICP			(SDE_TC4_HOTPLUG_ICP |	\
+					 SDE_TC3_HOTPLUG_ICP |	\
+					 SDE_TC2_HOTPLUG_ICP |	\
+					 SDE_TC1_HOTPLUG_ICP)
+
 #define SDEISR  _MMIO(0xc4000)
 #define SDEIMR  _MMIO(0xc4004)
 #define SDEIIR  _MMIO(0xc4008)
@@ -7517,6 +7657,134 @@ enum {
 #define  PORTE_HOTPLUG_SHORT_DETECT	(1 << 0)
 #define  PORTE_HOTPLUG_LONG_DETECT	(2 << 0)
 
+/* This register is a reuse of PCH_PORT_HOTPLUG register. The
+ * functionality covered in PCH_PORT_HOTPLUG is split into
+ * SHOTPLUG_CTL_DDI and SHOTPLUG_CTL_TC.
+ */
+
+#define SHOTPLUG_CTL_DDI			_MMIO(0xc4030)
+#define   ICP_DDIB_HPD_ENABLE			(1 << 7)
+#define   ICP_DDIB_HPD_STATUS_MASK		(3 << 4)
+#define   ICP_DDIB_HPD_NO_DETECT		(0 << 4)
+#define   ICP_DDIB_HPD_SHORT_DETECT		(1 << 4)
+#define   ICP_DDIB_HPD_LONG_DETECT		(2 << 4)
+#define   ICP_DDIB_HPD_SHORT_LONG_DETECT	(3 << 4)
+#define   ICP_DDIA_HPD_ENABLE			(1 << 3)
+#define   ICP_DDIA_HPD_STATUS_MASK		(3 << 0)
+#define   ICP_DDIA_HPD_NO_DETECT		(0 << 0)
+#define   ICP_DDIA_HPD_SHORT_DETECT		(1 << 0)
+#define   ICP_DDIA_HPD_LONG_DETECT		(2 << 0)
+#define   ICP_DDIA_HPD_SHORT_LONG_DETECT	(3 << 0)
+
+#define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
+#define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
+/* 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)
+#define DSCC_RC_RANGE_PARAMETERS_0		_MMIO(0x6BA40)
+#define DSCC_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6BA40 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PB	(0x78208)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB	(0x78208 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PB	(0x78308)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB	(0x78308 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PC	(0x78408)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC	(0x78408 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PC	(0x78508)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC	(0x78508 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC)
+#define RC_BPG_OFFSET_SHIFT			10
+#define RC_MAX_QP_SHIFT				5
+#define RC_MIN_QP_SHIFT				0
+
+#define DSCA_RC_RANGE_PARAMETERS_1		_MMIO(0x6B248)
+#define DSCA_RC_RANGE_PARAMETERS_1_UDW		_MMIO(0x6B248 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_1		_MMIO(0x6BA48)
+#define DSCC_RC_RANGE_PARAMETERS_1_UDW		_MMIO(0x6BA48 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PB	(0x78210)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB	(0x78210 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PB	(0x78310)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB	(0x78310 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PC	(0x78410)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC	(0x78410 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PC	(0x78510)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC	(0x78510 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC)
+
+#define DSCA_RC_RANGE_PARAMETERS_2		_MMIO(0x6B250)
+#define DSCA_RC_RANGE_PARAMETERS_2_UDW		_MMIO(0x6B250 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_2		_MMIO(0x6BA50)
+#define DSCC_RC_RANGE_PARAMETERS_2_UDW		_MMIO(0x6BA50 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PB	(0x78218)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB	(0x78218 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PB	(0x78318)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB	(0x78318 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PC	(0x78418)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC	(0x78418 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PC	(0x78518)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC	(0x78518 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_2(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC)
+
+#define DSCA_RC_RANGE_PARAMETERS_3		_MMIO(0x6B258)
+#define DSCA_RC_RANGE_PARAMETERS_3_UDW		_MMIO(0x6B258 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_3		_MMIO(0x6BA58)
+#define DSCC_RC_RANGE_PARAMETERS_3_UDW		_MMIO(0x6BA58 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PB	(0x78220)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB	(0x78220 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PB	(0x78320)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB	(0x78320 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PC	(0x78420)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC	(0x78420 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PC	(0x78520)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC	(0x78520 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_3(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC)
+
+#define   ICP_TC_HPD_LONG_DETECT(tc_port)	(2 << (tc_port) * 4)
+#define   ICP_TC_HPD_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
+
 #define PCH_GPIOA               _MMIO(0xc5010)
 #define PCH_GPIOB               _MMIO(0xc5014)
 #define PCH_GPIOC               _MMIO(0xc5018)
@@ -7689,12 +7957,25 @@ enum {
 #define _HSW_VIDEO_DIP_VSC_ECC_B	0x61344
 #define _HSW_VIDEO_DIP_GCP_B		0x61210
 
+/* Icelake PPS_DATA and _ECC DIP Registers.
+ * These are available for transcoders B,C and eDP.
+ * Adding the _A so as to reuse the _MMIO_TRANS2
+ * definition, with which it offsets to the right location.
+ */
+
+#define _ICL_VIDEO_DIP_PPS_DATA_A	0x60350
+#define _ICL_VIDEO_DIP_PPS_DATA_B	0x61350
+#define _ICL_VIDEO_DIP_PPS_ECC_A	0x603D4
+#define _ICL_VIDEO_DIP_PPS_ECC_B	0x613D4
+
 #define HSW_TVIDEO_DIP_CTL(trans)		_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_CTL_A)
 #define HSW_TVIDEO_DIP_AVI_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_AVI_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_VS_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VS_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_SPD_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_SPD_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_GCP(trans)		_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_GCP_A)
 #define HSW_TVIDEO_DIP_VSC_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VSC_DATA_A + (i) * 4)
+#define ICL_VIDEO_DIP_PPS_DATA(trans, i)	_MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_DATA_A + (i) * 4)
+#define ICL_VIDEO_DIP_PPS_ECC(trans, i)		_MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_ECC_A + (i) * 4)
 
 #define _HSW_STEREO_3D_CTL_A		0x70020
 #define   S3D_ENABLE			(1 << 31)
@@ -8555,6 +8836,14 @@ enum {
 #define _HSW_PWR_WELL_CTL3			0x45408
 #define _HSW_PWR_WELL_CTL4			0x4540C
 
+#define _ICL_PWR_WELL_CTL_AUX1			0x45440
+#define _ICL_PWR_WELL_CTL_AUX2			0x45444
+#define _ICL_PWR_WELL_CTL_AUX4			0x4544C
+
+#define _ICL_PWR_WELL_CTL_DDI1			0x45450
+#define _ICL_PWR_WELL_CTL_DDI2			0x45454
+#define _ICL_PWR_WELL_CTL_DDI4			0x4545C
+
 /*
  * Each power well control register contains up to 16 (request, status) HW
  * flag tuples. The register index and HW flag shift is determined by the
@@ -8564,14 +8853,20 @@ enum {
  */
 #define _HSW_PW_REG_IDX(pw)			((pw) >> 4)
 #define _HSW_PW_SHIFT(pw)			(((pw) & 0xf) * 2)
-/* TODO: Add all PWR_WELL_CTL registers below for new platforms */
 #define HSW_PWR_WELL_CTL_BIOS(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL1))
+						    _HSW_PWR_WELL_CTL1,	       \
+						    _ICL_PWR_WELL_CTL_AUX1,    \
+						    _ICL_PWR_WELL_CTL_DDI1))
 #define HSW_PWR_WELL_CTL_DRIVER(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL2))
+						    _HSW_PWR_WELL_CTL2,	       \
+						    _ICL_PWR_WELL_CTL_AUX2,    \
+						    _ICL_PWR_WELL_CTL_DDI2))
+/* KVMR doesn't have a reg for AUX or DDI power well control */
 #define HSW_PWR_WELL_CTL_KVMR		_MMIO(_HSW_PWR_WELL_CTL3)
 #define HSW_PWR_WELL_CTL_DEBUG(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL4))
+						    _HSW_PWR_WELL_CTL4,	       \
+						    _ICL_PWR_WELL_CTL_AUX4,    \
+						    _ICL_PWR_WELL_CTL_DDI4))
 
 #define   HSW_PWR_WELL_CTL_REQ(pw)		(1 << (_HSW_PW_SHIFT(pw) + 1))
 #define   HSW_PWR_WELL_CTL_STATE(pw)		(1 << _HSW_PW_SHIFT(pw))
@@ -8592,6 +8887,8 @@ enum skl_power_gate {
 #define  SKL_FUSE_DOWNLOAD_STATUS		(1 << 31)
 /* PG0 (HW control->no power well ID), PG1..PG2 (SKL_DISP_PW1..SKL_DISP_PW2) */
 #define  SKL_PW_TO_PG(pw)			((pw) - SKL_DISP_PW_1 + SKL_PG1)
+/* PG0 (HW control->no power well ID), PG1..PG4 (ICL_DISP_PW1..ICL_DISP_PW4) */
+#define  ICL_PW_TO_PG(pw)			((pw) - ICL_DISP_PW_1 + SKL_PG1)
 #define  SKL_FUSE_PG_DIST_STATUS(pg)		(1 << (27 - (pg)))
 
 #define _CNL_AUX_REG_IDX(pw)		((pw) - 9)
@@ -9047,6 +9344,7 @@ enum skl_power_gate {
 #define _MG_REFCLKIN_CTL_PORT3				0x16A92C
 #define _MG_REFCLKIN_CTL_PORT4				0x16B92C
 #define   MG_REFCLKIN_CTL_OD_2_MUX(x)			((x) << 8)
+#define   MG_REFCLKIN_CTL_OD_2_MUX_MASK			(0x7 << 8)
 #define MG_REFCLKIN_CTL(port) _MMIO_PORT((port) - PORT_C, \
 					 _MG_REFCLKIN_CTL_PORT1, \
 					 _MG_REFCLKIN_CTL_PORT2)
@@ -9056,7 +9354,9 @@ enum skl_power_gate {
 #define _MG_CLKTOP2_CORECLKCTL1_PORT3			0x16A8D8
 #define _MG_CLKTOP2_CORECLKCTL1_PORT4			0x16B8D8
 #define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO(x)		((x) << 16)
+#define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO_MASK	(0xff << 16)
 #define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(x)		((x) << 8)
+#define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK	(0xff << 8)
 #define MG_CLKTOP2_CORECLKCTL1(port) _MMIO_PORT((port) - PORT_C, \
 						_MG_CLKTOP2_CORECLKCTL1_PORT1, \
 						_MG_CLKTOP2_CORECLKCTL1_PORT2)
@@ -9066,9 +9366,13 @@ enum skl_power_gate {
 #define _MG_CLKTOP2_HSCLKCTL_PORT3			0x16A8D4
 #define _MG_CLKTOP2_HSCLKCTL_PORT4			0x16B8D4
 #define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(x)		((x) << 16)
+#define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK	(0x1 << 16)
 #define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(x)	((x) << 14)
+#define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK	(0x3 << 14)
 #define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(x)		((x) << 12)
+#define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK		(0x3 << 12)
 #define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(x)		((x) << 8)
+#define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK		(0xf << 8)
 #define MG_CLKTOP2_HSCLKCTL(port) _MMIO_PORT((port) - PORT_C, \
 					     _MG_CLKTOP2_HSCLKCTL_PORT1, \
 					     _MG_CLKTOP2_HSCLKCTL_PORT2)
@@ -9142,12 +9446,18 @@ enum skl_power_gate {
 #define _MG_PLL_BIAS_PORT3				0x16AA14
 #define _MG_PLL_BIAS_PORT4				0x16BA14
 #define   MG_PLL_BIAS_BIAS_GB_SEL(x)			((x) << 30)
+#define   MG_PLL_BIAS_BIAS_GB_SEL_MASK			(0x3 << 30)
 #define   MG_PLL_BIAS_INIT_DCOAMP(x)			((x) << 24)
+#define   MG_PLL_BIAS_INIT_DCOAMP_MASK			(0x3f << 24)
 #define   MG_PLL_BIAS_BIAS_BONUS(x)			((x) << 16)
+#define   MG_PLL_BIAS_BIAS_BONUS_MASK			(0xff << 16)
 #define   MG_PLL_BIAS_BIASCAL_EN			(1 << 15)
 #define   MG_PLL_BIAS_CTRIM(x)				((x) << 8)
+#define   MG_PLL_BIAS_CTRIM_MASK			(0x1f << 8)
 #define   MG_PLL_BIAS_VREF_RDAC(x)			((x) << 5)
+#define   MG_PLL_BIAS_VREF_RDAC_MASK			(0x7 << 5)
 #define   MG_PLL_BIAS_IREFTRIM(x)			((x) << 0)
+#define   MG_PLL_BIAS_IREFTRIM_MASK			(0x1f << 0)
 #define MG_PLL_BIAS(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_BIAS_PORT1, \
 				     _MG_PLL_BIAS_PORT2)
 
@@ -9401,6 +9711,22 @@ enum skl_power_gate {
 #define MIPIO_TXESC_CLK_DIV2			_MMIO(0x160008)
 #define  GLK_TX_ESC_CLK_DIV2_MASK			0x3FF
 
+#define _ICL_DSI_ESC_CLK_DIV0		0x6b090
+#define _ICL_DSI_ESC_CLK_DIV1		0x6b890
+#define ICL_DSI_ESC_CLK_DIV(port)	_MMIO_PORT((port),	\
+							_ICL_DSI_ESC_CLK_DIV0, \
+							_ICL_DSI_ESC_CLK_DIV1)
+#define _ICL_DPHY_ESC_CLK_DIV0		0x162190
+#define _ICL_DPHY_ESC_CLK_DIV1		0x6C190
+#define ICL_DPHY_ESC_CLK_DIV(port)	_MMIO_PORT((port),	\
+						_ICL_DPHY_ESC_CLK_DIV0, \
+						_ICL_DPHY_ESC_CLK_DIV1)
+#define  ICL_BYTE_CLK_PER_ESC_CLK_MASK		(0x1f << 16)
+#define  ICL_BYTE_CLK_PER_ESC_CLK_SHIFT	16
+#define  ICL_ESC_CLK_DIV_MASK			0x1ff
+#define  ICL_ESC_CLK_DIV_SHIFT			0
+#define DSI_MAX_ESC_CLK			20000		/* in KHz */
+
 /* Gen4+ Timestamp and Pipe Frame time stamp registers */
 #define GEN4_TIMESTAMP		_MMIO(0x2358)
 #define ILK_TIMESTAMP_HI	_MMIO(0x70070)
@@ -9535,6 +9861,14 @@ enum skl_power_gate {
 #define _BXT_MIPIC_PORT_CTRL				0x6B8C0
 #define BXT_MIPI_PORT_CTRL(tc)	_MMIO_MIPI(tc, _BXT_MIPIA_PORT_CTRL, _BXT_MIPIC_PORT_CTRL)
 
+/* ICL DSI MODE control */
+#define _ICL_DSI_IO_MODECTL_0				0x6B094
+#define _ICL_DSI_IO_MODECTL_1				0x6B894
+#define ICL_DSI_IO_MODECTL(port)	_MMIO_PORT(port,	\
+						    _ICL_DSI_IO_MODECTL_0, \
+						    _ICL_DSI_IO_MODECTL_1)
+#define  COMBO_PHY_MODE_DSI				(1 << 0)
+
 #define BXT_P_DSI_REGULATOR_CFG			_MMIO(0x160020)
 #define  STAP_SELECT					(1 << 0)
 
@@ -10014,4 +10348,310 @@ enum skl_power_gate {
 						 _ICL_PHY_MISC_B)
 #define  ICL_PHY_MISC_DE_IO_COMP_PWR_DOWN	(1 << 23)
 
+/* Icelake Display Stream Compression Registers */
+#define DSCA_PICTURE_PARAMETER_SET_0		0x6B200
+#define DSCC_PICTURE_PARAMETER_SET_0		0x6BA00
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB	0x78270
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB	0x78370
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC	0x78470
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC	0x78570
+#define ICL_DSC0_PICTURE_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC)
+#define  DSC_VBR_ENABLE			(1 << 19)
+#define  DSC_422_ENABLE			(1 << 18)
+#define  DSC_COLOR_SPACE_CONVERSION	(1 << 17)
+#define  DSC_BLOCK_PREDICTION		(1 << 16)
+#define  DSC_LINE_BUF_DEPTH_SHIFT	12
+#define  DSC_BPC_SHIFT			8
+#define  DSC_VER_MIN_SHIFT		4
+#define  DSC_VER_MAJ			(0x1 << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_1		0x6B204
+#define DSCC_PICTURE_PARAMETER_SET_1		0x6BA04
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB	0x78274
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB	0x78374
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC	0x78474
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC	0x78574
+#define ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_1(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC)
+#define  DSC_BPP(bpp)				((bpp) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_2		0x6B208
+#define DSCC_PICTURE_PARAMETER_SET_2		0x6BA08
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB	0x78278
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB	0x78378
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC	0x78478
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC	0x78578
+#define ICL_DSC0_PICTURE_PARAMETER_SET_2(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_2(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+					    _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB, \
+					    _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC)
+#define  DSC_PIC_WIDTH(pic_width)	((pic_width) << 16)
+#define  DSC_PIC_HEIGHT(pic_height)	((pic_height) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_3		0x6B20C
+#define DSCC_PICTURE_PARAMETER_SET_3		0x6BA0C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB	0x7827C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB	0x7837C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC	0x7847C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC	0x7857C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_3(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_3(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC)
+#define  DSC_SLICE_WIDTH(slice_width)   ((slice_width) << 16)
+#define  DSC_SLICE_HEIGHT(slice_height) ((slice_height) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_4		0x6B210
+#define DSCC_PICTURE_PARAMETER_SET_4		0x6BA10
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB	0x78280
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PB	0x78380
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC	0x78480
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC	0x78580
+#define ICL_DSC0_PICTURE_PARAMETER_SET_4(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC)
+#define  DSC_INITIAL_DEC_DELAY(dec_delay)       ((dec_delay) << 16)
+#define  DSC_INITIAL_XMIT_DELAY(xmit_delay)     ((xmit_delay) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_5		0x6B214
+#define DSCC_PICTURE_PARAMETER_SET_5		0x6BA14
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB	0x78284
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PB	0x78384
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC	0x78484
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC	0x78584
+#define ICL_DSC0_PICTURE_PARAMETER_SET_5(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC)
+#define  DSC_SCALE_DEC_INTINT(scale_dec)	((scale_dec) << 16)
+#define  DSC_SCALE_INC_INT(scale_inc)		((scale_inc) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_6		0x6B218
+#define DSCC_PICTURE_PARAMETER_SET_6		0x6BA18
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB	0x78288
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB	0x78388
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC	0x78488
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC	0x78588
+#define ICL_DSC0_PICTURE_PARAMETER_SET_6(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_6(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC)
+#define  DSC_FLATNESS_MAX_QP(max_qp)		(qp << 24)
+#define  DSC_FLATNESS_MIN_QP(min_qp)		(qp << 16)
+#define  DSC_FIRST_LINE_BPG_OFFSET(offset)	((offset) << 8)
+#define  DSC_INITIAL_SCALE_VALUE(value)		((value) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_7		0x6B21C
+#define DSCC_PICTURE_PARAMETER_SET_7		0x6BA1C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB	0x7828C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB	0x7838C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC	0x7848C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC	0x7858C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_7(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							    _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB, \
+							    _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_7(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							    _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB, \
+							    _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC)
+#define  DSC_NFL_BPG_OFFSET(bpg_offset)		((bpg_offset) << 16)
+#define  DSC_SLICE_BPG_OFFSET(bpg_offset)	((bpg_offset) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_8		0x6B220
+#define DSCC_PICTURE_PARAMETER_SET_8		0x6BA20
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB	0x78290
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB	0x78390
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC	0x78490
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC	0x78590
+#define ICL_DSC0_PICTURE_PARAMETER_SET_8(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_8(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC)
+#define  DSC_INITIAL_OFFSET(initial_offset)		((initial_offset) << 16)
+#define  DSC_FINAL_OFFSET(final_offset)			((final_offset) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_9		0x6B224
+#define DSCC_PICTURE_PARAMETER_SET_9		0x6BA24
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB	0x78294
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB	0x78394
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC	0x78494
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC	0x78594
+#define ICL_DSC0_PICTURE_PARAMETER_SET_9(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_9(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC)
+#define  DSC_RC_EDGE_FACTOR(rc_edge_fact)	((rc_edge_fact) << 16)
+#define  DSC_RC_MODEL_SIZE(rc_model_size)	((rc_model_size) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_10		0x6B228
+#define DSCC_PICTURE_PARAMETER_SET_10		0x6BA28
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB	0x78298
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB	0x78398
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC	0x78498
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC	0x78598
+#define ICL_DSC0_PICTURE_PARAMETER_SET_10(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_10(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC)
+#define  DSC_RC_TARGET_OFF_LOW(rc_tgt_off_low)		((rc_tgt_off_low) << 20)
+#define  DSC_RC_TARGET_OFF_HIGH(rc_tgt_off_high)	((rc_tgt_off_high) << 16)
+#define  DSC_RC_QUANT_INC_LIMIT1(lim)			((lim) << 8)
+#define  DSC_RC_QUANT_INC_LIMIT0(lim)			((lim) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_11		0x6B22C
+#define DSCC_PICTURE_PARAMETER_SET_11		0x6BA2C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB	0x7829C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB	0x7839C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC	0x7849C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC	0x7859C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_11(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_11(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_12		0x6B260
+#define DSCC_PICTURE_PARAMETER_SET_12		0x6BA60
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB	0x782A0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB	0x783A0
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC	0x784A0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC	0x785A0
+#define ICL_DSC0_PICTURE_PARAMETER_SET_12(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_12(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_13		0x6B264
+#define DSCC_PICTURE_PARAMETER_SET_13		0x6BA64
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB	0x782A4
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB	0x783A4
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC	0x784A4
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC	0x785A4
+#define ICL_DSC0_PICTURE_PARAMETER_SET_13(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_13(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_14		0x6B268
+#define DSCC_PICTURE_PARAMETER_SET_14		0x6BA68
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB	0x782A8
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB	0x783A8
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC	0x784A8
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC	0x785A8
+#define ICL_DSC0_PICTURE_PARAMETER_SET_14(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_14(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_15		0x6B26C
+#define DSCC_PICTURE_PARAMETER_SET_15		0x6BA6C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB	0x782AC
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB	0x783AC
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC	0x784AC
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC	0x785AC
+#define ICL_DSC0_PICTURE_PARAMETER_SET_15(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_15(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_16		0x6B270
+#define DSCC_PICTURE_PARAMETER_SET_16		0x6BA70
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB	0x782B0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB	0x783B0
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC	0x784B0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC	0x785B0
+#define ICL_DSC0_PICTURE_PARAMETER_SET_16(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_16(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC)
+#define  DSC_SLICE_PER_LINE(slice_per_line)		((slice_per_line) << 16)
+#define  DSC_SLICE_CHUNK_SIZE(slice_chunk_aize)		(slice_chunk_size << 0)
+
+/* Icelake Rate Control Buffer Threshold Registers */
+#define DSCA_RC_BUF_THRESH_0			_MMIO(0x6B230)
+#define DSCA_RC_BUF_THRESH_0_UDW		_MMIO(0x6B230 + 4)
+#define DSCC_RC_BUF_THRESH_0			_MMIO(0x6BA30)
+#define DSCC_RC_BUF_THRESH_0_UDW		_MMIO(0x6BA30 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_0_PB		(0x78254)
+#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PB	(0x78254 + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_0_PB		(0x78354)
+#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PB	(0x78354 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_0_PC		(0x78454)
+#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PC	(0x78454 + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_0_PC		(0x78554)
+#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PC	(0x78554 + 4)
+#define ICL_DSC0_RC_BUF_THRESH_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_0_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_0_PC)
+#define ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_0_UDW_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_0_UDW_PC)
+#define ICL_DSC1_RC_BUF_THRESH_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_0_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_0_PC)
+#define ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_0_UDW_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_0_UDW_PC)
+
+#define DSCA_RC_BUF_THRESH_1			_MMIO(0x6B238)
+#define DSCA_RC_BUF_THRESH_1_UDW		_MMIO(0x6B238 + 4)
+#define DSCC_RC_BUF_THRESH_1			_MMIO(0x6BA38)
+#define DSCC_RC_BUF_THRESH_1_UDW		_MMIO(0x6BA38 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_1_PB		(0x7825C)
+#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PB	(0x7825C + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_1_PB		(0x7835C)
+#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PB	(0x7835C + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_1_PC		(0x7845C)
+#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PC	(0x7845C + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_1_PC		(0x7855C)
+#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PC	(0x7855C + 4)
+#define ICL_DSC0_RC_BUF_THRESH_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_1_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_1_PC)
+#define ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_1_UDW_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_1_UDW_PC)
+#define ICL_DSC1_RC_BUF_THRESH_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_1_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_1_PC)
+#define ICL_DSC1_RC_BUF_THRESH_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_1_UDW_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_1_UDW_PC)
+
 #endif /* _I915_REG_H_ */
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index e1dbb544046f..5c2c93cbab12 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -206,7 +206,8 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno)
 	/* Carefully retire all requests without writing to the rings */
 	ret = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		return ret;
 
@@ -503,7 +504,7 @@ static void move_to_timeline(struct i915_request *request,
 	GEM_BUG_ON(request->timeline == &request->engine->timeline);
 	lockdep_assert_held(&request->engine->timeline.lock);
 
-	spin_lock_nested(&request->timeline->lock, SINGLE_DEPTH_NESTING);
+	spin_lock(&request->timeline->lock);
 	list_move_tail(&request->link, &timeline->requests);
 	spin_unlock(&request->timeline->lock);
 }
@@ -735,7 +736,8 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		/* Ratelimit ourselves to prevent oom from malicious clients */
 		ret = i915_gem_wait_for_idle(i915,
 					     I915_WAIT_LOCKED |
-					     I915_WAIT_INTERRUPTIBLE);
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			goto err_unreserve;
 
@@ -1013,6 +1015,27 @@ i915_request_await_object(struct i915_request *to,
 	return ret;
 }
 
+void i915_request_skip(struct i915_request *rq, int error)
+{
+	void *vaddr = rq->ring->vaddr;
+	u32 head;
+
+	GEM_BUG_ON(!IS_ERR_VALUE((long)error));
+	dma_fence_set_error(&rq->fence, error);
+
+	/*
+	 * As this request likely depends on state from the lost
+	 * context, clear out all the user operations leaving the
+	 * breadcrumb at the end (so we get the fence notifications).
+	 */
+	head = rq->infix;
+	if (rq->postfix < head) {
+		memset(vaddr + head, 0, rq->ring->size - head);
+		head = 0;
+	}
+	memset(vaddr + head, 0, rq->postfix - head);
+}
+
 /*
  * NB: This function is not allowed to fail. Doing so would mean the the
  * request is not being tracked for completion but the work itself is
@@ -1196,7 +1219,7 @@ static bool __i915_spin_request(const struct i915_request *rq,
 	 * takes to sleep on a request, on the order of a microsecond.
 	 */
 
-	irq = atomic_read(&engine->irq_count);
+	irq = READ_ONCE(engine->breadcrumbs.irq_count);
 	timeout_us += local_clock_us(&cpu);
 	do {
 		if (i915_seqno_passed(intel_engine_get_seqno(engine), seqno))
@@ -1208,7 +1231,7 @@ static bool __i915_spin_request(const struct i915_request *rq,
 		 * assume we won't see one in the near future but require
 		 * the engine->seqno_barrier() to fixup coherency.
 		 */
-		if (atomic_read(&engine->irq_count) != irq)
+		if (READ_ONCE(engine->breadcrumbs.irq_count) != irq)
 			break;
 
 		if (signal_pending_state(state, current))
@@ -1285,7 +1308,7 @@ long i915_request_wait(struct i915_request *rq,
 	if (flags & I915_WAIT_LOCKED)
 		add_wait_queue(errq, &reset);
 
-	intel_wait_init(&wait, rq);
+	intel_wait_init(&wait);
 
 restart:
 	do {
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 7ee220ded9c9..e1c9365dfefb 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -258,6 +258,8 @@ void i915_request_add(struct i915_request *rq);
 void __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
+void i915_request_skip(struct i915_request *request, int error);
+
 void __i915_request_unsubmit(struct i915_request *request);
 void i915_request_unsubmit(struct i915_request *request);
 
@@ -378,6 +380,7 @@ static inline void
 init_request_active(struct i915_gem_active *active,
 		    i915_gem_retire_fn retire)
 {
+	RCU_INIT_POINTER(active->request, NULL);
 	INIT_LIST_HEAD(&active->link);
 	active->retire = retire ?: i915_gem_retire_noop;
 }
diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index 9766e806dce6..a73472dd12fd 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -99,6 +99,6 @@ __printf(2, 3)
 bool __igt_timeout(unsigned long timeout, const char *fmt, ...);
 
 #define igt_timeout(t, fmt, ...) \
-	__igt_timeout((t), KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
+	__igt_timeout((t), KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 
 #endif /* !__I915_SELFTEST_H__ */
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index dc2a4632faa7..a2c2c3ab5fb0 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -37,6 +37,8 @@ struct i915_timeline {
 	u32 seqno;
 
 	spinlock_t lock;
+#define TIMELINE_CLIENT 0 /* default subclass */
+#define TIMELINE_ENGINE 1
 
 	/**
 	 * List of breadcrumbs associated with GPU requests currently
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index e82aa804cdba..11d834f94220 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -21,7 +21,7 @@
  * IN THE SOFTWARE.
  *
  */
- 
+
 #include "i915_vma.h"
 
 #include "i915_drv.h"
@@ -30,18 +30,53 @@
 
 #include <drm/drm_gem.h>
 
+#if IS_ENABLED(CONFIG_DRM_I915_ERRLOG_GEM) && IS_ENABLED(CONFIG_DRM_DEBUG_MM)
+
+#include <linux/stackdepot.h>
+
+static void vma_print_allocator(struct i915_vma *vma, const char *reason)
+{
+	unsigned long entries[12];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+	};
+	char buf[512];
+
+	if (!vma->node.stack) {
+		DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: unknown owner\n",
+				 vma->node.start, vma->node.size, reason);
+		return;
+	}
+
+	depot_fetch_stack(vma->node.stack, &trace);
+	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
+			 vma->node.start, vma->node.size, reason, buf);
+}
+
+#else
+
+static void vma_print_allocator(struct i915_vma *vma, const char *reason)
+{
+}
+
+#endif
+
+struct i915_vma_active {
+	struct i915_gem_active base;
+	struct i915_vma *vma;
+	struct rb_node node;
+	u64 timeline;
+};
+
 static void
-i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
+__i915_vma_retire(struct i915_vma *vma, struct i915_request *rq)
 {
-	const unsigned int idx = rq->engine->id;
-	struct i915_vma *vma =
-		container_of(active, struct i915_vma, last_read[idx]);
 	struct drm_i915_gem_object *obj = vma->obj;
 
-	GEM_BUG_ON(!i915_vma_has_active_engine(vma, idx));
-
-	i915_vma_clear_active(vma, idx);
-	if (i915_vma_is_active(vma))
+	GEM_BUG_ON(!i915_vma_is_active(vma));
+	if (--vma->active_count)
 		return;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
@@ -75,6 +110,21 @@ i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
 	}
 }
 
+static void
+i915_vma_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	struct i915_vma_active *active =
+		container_of(base, typeof(*active), base);
+
+	__i915_vma_retire(active->vma, rq);
+}
+
+static void
+i915_vma_last_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	__i915_vma_retire(container_of(base, struct i915_vma, last_active), rq);
+}
+
 static struct i915_vma *
 vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
@@ -82,7 +132,6 @@ vma_create(struct drm_i915_gem_object *obj,
 {
 	struct i915_vma *vma;
 	struct rb_node *rb, **p;
-	int i;
 
 	/* The aliasing_ppgtt should never be used directly! */
 	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
@@ -91,8 +140,9 @@ vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		init_request_active(&vma->last_read[i], i915_vma_retire);
+	vma->active = RB_ROOT;
+
+	init_request_active(&vma->last_active, i915_vma_last_retire);
 	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
 	vma->ops = &vm->vma_ops;
@@ -110,7 +160,7 @@ vma_create(struct drm_i915_gem_object *obj,
 						     obj->base.size >> PAGE_SHIFT));
 			vma->size = view->partial.size;
 			vma->size <<= PAGE_SHIFT;
-			GEM_BUG_ON(vma->size >= obj->base.size);
+			GEM_BUG_ON(vma->size > obj->base.size);
 		} else if (view->type == I915_GGTT_VIEW_ROTATED) {
 			vma->size = intel_rotation_info_size(&view->rotated);
 			vma->size <<= PAGE_SHIFT;
@@ -745,13 +795,11 @@ void i915_vma_reopen(struct i915_vma *vma)
 static void __i915_vma_destroy(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	int i;
+	struct i915_vma_active *iter, *n;
 
 	GEM_BUG_ON(vma->node.allocated);
 	GEM_BUG_ON(vma->fence);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		GEM_BUG_ON(i915_gem_active_isset(&vma->last_read[i]));
 	GEM_BUG_ON(i915_gem_active_isset(&vma->last_fence));
 
 	list_del(&vma->obj_link);
@@ -762,6 +810,11 @@ static void __i915_vma_destroy(struct i915_vma *vma)
 	if (!i915_vma_is_ggtt(vma))
 		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));
 
+	rbtree_postorder_for_each_entry_safe(iter, n, &vma->active, node) {
+		GEM_BUG_ON(i915_gem_active_isset(&iter->base));
+		kfree(iter);
+	}
+
 	kmem_cache_free(i915->vmas, vma);
 }
 
@@ -826,9 +879,159 @@ void i915_vma_revoke_mmap(struct i915_vma *vma)
 		list_del(&vma->obj->userfault_link);
 }
 
+static void export_fence(struct i915_vma *vma,
+			 struct i915_request *rq,
+			 unsigned int flags)
+{
+	struct reservation_object *resv = vma->resv;
+
+	/*
+	 * Ignore errors from failing to allocate the new fence, we can't
+	 * handle an error right now. Worst case should be missed
+	 * synchronisation leading to rendering corruption.
+	 */
+	reservation_object_lock(resv, NULL);
+	if (flags & EXEC_OBJECT_WRITE)
+		reservation_object_add_excl_fence(resv, &rq->fence);
+	else if (reservation_object_reserve_shared(resv) == 0)
+		reservation_object_add_shared_fence(resv, &rq->fence);
+	reservation_object_unlock(resv);
+}
+
+static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
+{
+	struct i915_vma_active *active;
+	struct rb_node **p, *parent;
+	struct i915_request *old;
+
+	/*
+	 * We track the most recently used timeline to skip a rbtree search
+	 * for the common case, under typical loads we never need the rbtree
+	 * at all. We can reuse the last_active slot if it is empty, that is
+	 * after the previous activity has been retired, or if the active
+	 * matches the current timeline.
+	 *
+	 * Note that we allow the timeline to be active simultaneously in
+	 * the rbtree and the last_active cache. We do this to avoid having
+	 * to search and replace the rbtree element for a new timeline, with
+	 * the cost being that we must be aware that the vma may be retired
+	 * twice for the same timeline (as the older rbtree element will be
+	 * retired before the new request added to last_active).
+	 */
+	old = i915_gem_active_raw(&vma->last_active,
+				  &vma->vm->i915->drm.struct_mutex);
+	if (!old || old->fence.context == idx)
+		goto out;
+
+	/* Move the currently active fence into the rbtree */
+	idx = old->fence.context;
+
+	parent = NULL;
+	p = &vma->active.rb_node;
+	while (*p) {
+		parent = *p;
+
+		active = rb_entry(parent, struct i915_vma_active, node);
+		if (active->timeline == idx)
+			goto replace;
+
+		if (active->timeline < idx)
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+
+	active = kmalloc(sizeof(*active), GFP_KERNEL);
+
+	/* kmalloc may retire the vma->last_active request (thanks shrinker)! */
+	if (unlikely(!i915_gem_active_raw(&vma->last_active,
+					  &vma->vm->i915->drm.struct_mutex))) {
+		kfree(active);
+		goto out;
+	}
+
+	if (unlikely(!active))
+		return ERR_PTR(-ENOMEM);
+
+	init_request_active(&active->base, i915_vma_retire);
+	active->vma = vma;
+	active->timeline = idx;
+
+	rb_link_node(&active->node, parent, p);
+	rb_insert_color(&active->node, &vma->active);
+
+replace:
+	/*
+	 * Overwrite the previous active slot in the rbtree with last_active,
+	 * leaving last_active zeroed. If the previous slot is still active,
+	 * we must be careful as we now only expect to receive one retire
+	 * callback not two, and so much undo the active counting for the
+	 * overwritten slot.
+	 */
+	if (i915_gem_active_isset(&active->base)) {
+		/* Retire ourselves from the old rq->active_list */
+		__list_del_entry(&active->base.link);
+		vma->active_count--;
+		GEM_BUG_ON(!vma->active_count);
+	}
+	GEM_BUG_ON(list_empty(&vma->last_active.link));
+	list_replace_init(&vma->last_active.link, &active->base.link);
+	active->base.request = fetch_and_zero(&vma->last_active.request);
+
+out:
+	return &vma->last_active;
+}
+
+int i915_vma_move_to_active(struct i915_vma *vma,
+			    struct i915_request *rq,
+			    unsigned int flags)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+	struct i915_gem_active *active;
+
+	lockdep_assert_held(&rq->i915->drm.struct_mutex);
+	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+
+	active = active_instance(vma, rq->fence.context);
+	if (IS_ERR(active))
+		return PTR_ERR(active);
+
+	/*
+	 * Add a reference if we're newly entering the active list.
+	 * The order in which we add operations to the retirement queue is
+	 * vital here: mark_active adds to the start of the callback list,
+	 * such that subsequent callbacks are called first. Therefore we
+	 * add the active reference first and queue for it to be dropped
+	 * *last*.
+	 */
+	if (!i915_gem_active_isset(active) && !vma->active_count++) {
+		list_move_tail(&vma->vm_link, &vma->vm->active_list);
+		obj->active_count++;
+	}
+	i915_gem_active_set(active, rq);
+	GEM_BUG_ON(!i915_vma_is_active(vma));
+	GEM_BUG_ON(!obj->active_count);
+
+	obj->write_domain = 0;
+	if (flags & EXEC_OBJECT_WRITE) {
+		obj->write_domain = I915_GEM_DOMAIN_RENDER;
+
+		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
+			i915_gem_active_set(&obj->frontbuffer_write, rq);
+
+		obj->read_domains = 0;
+	}
+	obj->read_domains |= I915_GEM_GPU_DOMAINS;
+
+	if (flags & EXEC_OBJECT_NEEDS_FENCE)
+		i915_gem_active_set(&vma->last_fence, rq);
+
+	export_fence(vma, rq, flags);
+	return 0;
+}
+
 int i915_vma_unbind(struct i915_vma *vma)
 {
-	unsigned long active;
 	int ret;
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
@@ -838,9 +1041,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 	 * have side-effects such as unpinning or even unbinding this vma.
 	 */
 	might_sleep();
-	active = i915_vma_get_active(vma);
-	if (active) {
-		int idx;
+	if (i915_vma_is_active(vma)) {
+		struct i915_vma_active *active, *n;
 
 		/*
 		 * When a closed VMA is retired, it is unbound - eek.
@@ -857,26 +1059,32 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 */
 		__i915_vma_pin(vma);
 
-		for_each_active(active, idx) {
-			ret = i915_gem_active_retire(&vma->last_read[idx],
-						     &vma->vm->i915->drm.struct_mutex);
-			if (ret)
-				break;
-		}
+		ret = i915_gem_active_retire(&vma->last_active,
+					     &vma->vm->i915->drm.struct_mutex);
+		if (ret)
+			goto unpin;
 
-		if (!ret) {
-			ret = i915_gem_active_retire(&vma->last_fence,
+		rbtree_postorder_for_each_entry_safe(active, n,
+						     &vma->active, node) {
+			ret = i915_gem_active_retire(&active->base,
 						     &vma->vm->i915->drm.struct_mutex);
+			if (ret)
+				goto unpin;
 		}
 
+		ret = i915_gem_active_retire(&vma->last_fence,
+					     &vma->vm->i915->drm.struct_mutex);
+unpin:
 		__i915_vma_unpin(vma);
 		if (ret)
 			return ret;
 	}
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
-	if (i915_vma_is_pinned(vma))
+	if (i915_vma_is_pinned(vma)) {
+		vma_print_allocator(vma, "is pinned");
 		return -EBUSY;
+	}
 
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 66a228931517..f06d66377107 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -26,6 +26,7 @@
 #define __I915_VMA_H__
 
 #include <linux/io-mapping.h>
+#include <linux/rbtree.h>
 
 #include <drm/drm_mm.h>
 
@@ -94,8 +95,9 @@ struct i915_vma {
 #define I915_VMA_USERFAULT	BIT(I915_VMA_USERFAULT_BIT)
 #define I915_VMA_GGTT_WRITE	BIT(12)
 
-	unsigned int active;
-	struct i915_gem_active last_read[I915_NUM_ENGINES];
+	unsigned int active_count;
+	struct rb_root active;
+	struct i915_gem_active last_active;
 	struct i915_gem_active last_fence;
 
 	/**
@@ -138,6 +140,15 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 
 void i915_vma_unpin_and_release(struct i915_vma **p_vma);
 
+static inline bool i915_vma_is_active(struct i915_vma *vma)
+{
+	return vma->active_count;
+}
+
+int __must_check i915_vma_move_to_active(struct i915_vma *vma,
+					 struct i915_request *rq,
+					 unsigned int flags);
+
 static inline bool i915_vma_is_ggtt(const struct i915_vma *vma)
 {
 	return vma->flags & I915_VMA_GGTT;
@@ -187,34 +198,6 @@ static inline bool i915_vma_has_userfault(const struct i915_vma *vma)
 	return test_bit(I915_VMA_USERFAULT_BIT, &vma->flags);
 }
 
-static inline unsigned int i915_vma_get_active(const struct i915_vma *vma)
-{
-	return vma->active;
-}
-
-static inline bool i915_vma_is_active(const struct i915_vma *vma)
-{
-	return i915_vma_get_active(vma);
-}
-
-static inline void i915_vma_set_active(struct i915_vma *vma,
-				       unsigned int engine)
-{
-	vma->active |= BIT(engine);
-}
-
-static inline void i915_vma_clear_active(struct i915_vma *vma,
-					 unsigned int engine)
-{
-	vma->active &= ~BIT(engine);
-}
-
-static inline bool i915_vma_has_active_engine(const struct i915_vma *vma,
-					      unsigned int engine)
-{
-	return vma->active & BIT(engine);
-}
-
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
new file mode 100644
index 000000000000..13830e43a4d1
--- /dev/null
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -0,0 +1,127 @@
+/*
+ * Copyright © 2018 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.
+ *
+ * Authors:
+ *   Madhav Chauhan <madhav.chauhan@intel.com>
+ *   Jani Nikula <jani.nikula@intel.com>
+ */
+
+#include "intel_dsi.h"
+
+static void gen11_dsi_program_esc_clk_div(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);
+	enum port port;
+	u32 bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	u32 afe_clk_khz; /* 8X Clock */
+	u32 esc_clk_div_m;
+
+	afe_clk_khz = DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp,
+					intel_dsi->lane_count);
+
+	esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(ICL_DSI_ESC_CLK_DIV(port),
+			   esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
+		POSTING_READ(ICL_DSI_ESC_CLK_DIV(port));
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(ICL_DPHY_ESC_CLK_DIV(port),
+			   esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
+		POSTING_READ(ICL_DPHY_ESC_CLK_DIV(port));
+	}
+}
+
+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);
+	enum port port;
+	u32 tmp;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(ICL_DSI_IO_MODECTL(port));
+		tmp |= COMBO_PHY_MODE_DSI;
+		I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp);
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		intel_display_power_get(dev_priv, port == PORT_A ?
+					POWER_DOMAIN_PORT_DDI_A_IO :
+					POWER_DOMAIN_PORT_DDI_B_IO);
+	}
+}
+
+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);
+	enum port port;
+	u32 tmp;
+	u32 lane_mask;
+
+	switch (intel_dsi->lane_count) {
+	case 1:
+		lane_mask = PWR_DOWN_LN_3_1_0;
+		break;
+	case 2:
+		lane_mask = PWR_DOWN_LN_3_1;
+		break;
+	case 3:
+		lane_mask = PWR_DOWN_LN_3;
+		break;
+	case 4:
+	default:
+		lane_mask = PWR_UP_ALL_LANES;
+		break;
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(ICL_PORT_CL_DW10(port));
+		tmp &= ~PWR_DOWN_LN_MASK;
+		I915_WRITE(ICL_PORT_CL_DW10(port), tmp | lane_mask);
+	}
+}
+
+static void gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder)
+{
+	/* step 4a: power up all lanes of the DDI used by DSI */
+	gen11_dsi_power_up_lanes(encoder);
+}
+
+static void __attribute__((unused))
+gen11_dsi_pre_enable(struct intel_encoder *encoder,
+		     const struct intel_crtc_state *pipe_config,
+		     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);
+
+	/* step4: enable DSI port and DPHY */
+	gen11_dsi_enable_port_and_phy(encoder);
+}
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 86a987b8ac66..1db6ba7d926e 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -98,12 +98,14 @@ static void intel_breadcrumbs_hangcheck(struct timer_list *t)
 	struct intel_engine_cs *engine =
 		from_timer(engine, t, breadcrumbs.hangcheck);
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	unsigned int irq_count;
 
 	if (!b->irq_armed)
 		return;
 
-	if (b->hangcheck_interrupts != atomic_read(&engine->irq_count)) {
-		b->hangcheck_interrupts = atomic_read(&engine->irq_count);
+	irq_count = READ_ONCE(b->irq_count);
+	if (b->hangcheck_interrupts != irq_count) {
+		b->hangcheck_interrupts = irq_count;
 		mod_timer(&b->hangcheck, wait_timeout());
 		return;
 	}
@@ -272,13 +274,14 @@ static bool use_fake_irq(const struct intel_breadcrumbs *b)
 	if (!test_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings))
 		return false;
 
-	/* Only start with the heavy weight fake irq timer if we have not
+	/*
+	 * Only start with the heavy weight fake irq timer if we have not
 	 * seen any interrupts since enabling it the first time. If the
 	 * interrupts are still arriving, it means we made a mistake in our
 	 * engine->seqno_barrier(), a timing error that should be transient
 	 * and unlikely to reoccur.
 	 */
-	return atomic_read(&engine->irq_count) == b->hangcheck_interrupts;
+	return READ_ONCE(b->irq_count) == b->hangcheck_interrupts;
 }
 
 static void enable_fake_irq(struct intel_breadcrumbs *b)
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index bf9433d7964d..29075c763428 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -316,6 +316,7 @@ static void pnv_get_cdclk(struct drm_i915_private *dev_priv,
 		break;
 	default:
 		DRM_ERROR("Unknown pnv display core clock 0x%04x\n", gcfgc);
+		/* fall through */
 	case GC_DISPLAY_CLOCK_133_MHZ_PNV:
 		cdclk_state->cdclk = 133333;
 		break;
@@ -1797,6 +1798,7 @@ static int icl_calc_cdclk(int min_cdclk, unsigned int ref)
 	switch (ref) {
 	default:
 		MISSING_CASE(ref);
+		/* fall through */
 	case 24000:
 		ranges = ranges_24;
 		break;
@@ -1824,6 +1826,7 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 	switch (cdclk) {
 	default:
 		MISSING_CASE(cdclk);
+		/* fall through */
 	case 307200:
 	case 556800:
 	case 652800:
@@ -1896,6 +1899,7 @@ static u8 icl_calc_voltage_level(int cdclk)
 		return 1;
 	default:
 		MISSING_CASE(cdclk);
+		/* fall through */
 	case 652800:
 	case 648000:
 		return 2;
@@ -1913,6 +1917,7 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 	switch (val & ICL_DSSM_CDCLK_PLL_REFCLK_MASK) {
 	default:
 		MISSING_CASE(val);
+		/* fall through */
 	case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz:
 		cdclk_state->ref = 24000;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 044fe1fb9872..39d66f8493fa 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1069,6 +1069,7 @@ static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder,
 	switch (id) {
 	default:
 		MISSING_CASE(id);
+		/* fall through */
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return DDI_CLK_SEL_NONE;
@@ -1807,15 +1808,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder)
+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 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);
 	uint32_t val = I915_READ(reg);
 
 	val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
 	val |= TRANS_DDI_PORT_NONE;
 	I915_WRITE(reg, val);
+
+	if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
+	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+		DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n");
+		/* Quirk time at 100ms for reliable operation */
+		msleep(100);
+	}
 }
 
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
@@ -1983,15 +1993,50 @@ out:
 	return ret;
 }
 
-static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder)
+static inline enum intel_display_power_domain
+intel_ddi_main_link_aux_domain(struct intel_dp *intel_dp)
+{
+	/* CNL HW requires corresponding AUX IOs to be powered up for PSR with
+	 * DC states enabled at the same time, while for driver initiated AUX
+	 * transfers we need the same AUX IOs to be powered but with DC states
+	 * disabled. Accordingly use the AUX power domain here which leaves DC
+	 * states enabled.
+	 * However, for non-A AUX ports the corresponding non-EDP transcoders
+	 * would have already enabled power well 2 and DC_OFF. This means we can
+	 * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a
+	 * specific AUX_IO reference without powering up any extra wells.
+	 * Note that PSR is enabled only on Port A even though this function
+	 * returns the correct domain for other ports too.
+	 */
+	return intel_dp->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A :
+					      intel_dp->aux_power_domain;
+}
+
+static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
+				       struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
-	enum pipe pipe;
+	struct intel_digital_port *dig_port;
+	u64 domains;
 
-	if (intel_ddi_get_hw_state(encoder, &pipe))
-		return BIT_ULL(dig_port->ddi_io_power_domain);
+	/*
+	 * TODO: Add support for MST encoders. Atm, the following should never
+	 * happen since fake-MST encoders don't set their get_power_domains()
+	 * hook.
+	 */
+	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
+		return 0;
 
-	return 0;
+	dig_port = enc_to_dig_port(&encoder->base);
+	domains = BIT_ULL(dig_port->ddi_io_power_domain);
+
+	/* AUX power is only needed for (e)DP mode, not for HDMI. */
+	if (intel_crtc_has_dp_encoder(crtc_state)) {
+		struct intel_dp *intel_dp = &dig_port->dp;
+
+		domains |= BIT_ULL(intel_ddi_main_link_aux_domain(intel_dp));
+	}
+
+	return domains;
 }
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
@@ -2631,6 +2676,9 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
 
+	intel_display_power_get(dev_priv,
+				intel_ddi_main_link_aux_domain(intel_dp));
+
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
@@ -2775,6 +2823,9 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
+
+	intel_display_power_put(dev_priv,
+				intel_ddi_main_link_aux_domain(intel_dp));
 }
 
 static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
@@ -3588,7 +3639,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 			goto err;
 
 		intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
-		dev_priv->hotplug.irq_port[port] = intel_dig_port;
 	}
 
 	/* In theory we don't need the encoder->type check, but leave it just in
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 0fd13df424cf..0ef0c6448d53 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -858,6 +858,8 @@ void intel_device_info_runtime_init(struct intel_device_info *info)
 void intel_driver_caps_print(const struct intel_driver_caps *caps,
 			     struct drm_printer *p)
 {
+	drm_printf(p, "Has logical contexts? %s\n",
+		   yesno(caps->has_logical_contexts));
 	drm_printf(p, "scheduler: %x\n", caps->scheduler);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 933e31669557..633f9fbf72ea 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -186,6 +186,7 @@ struct intel_device_info {
 
 struct intel_driver_caps {
 	unsigned int scheduler;
+	bool has_logical_contexts:1;
 };
 
 static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 694a4703042f..87e4cfbfd096 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3657,7 +3657,7 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(fb->format->format);
 
-	if (intel_format_is_yuv(fb->format->format)) {
+	if (fb->format->is_yuv) {
 		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
@@ -5632,6 +5632,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
 	bool psl_clkgate_wa;
+	u32 pipe_chicken;
 
 	if (WARN_ON(intel_crtc->active))
 		return;
@@ -5691,6 +5692,17 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	 */
 	intel_color_load_luts(&pipe_config->base);
 
+	/*
+	 * Display WA #1153: enable hardware to bypass the alpha math
+	 * and rounding for per-pixel values 00 and 0xff
+	 */
+	if (INTEL_GEN(dev_priv) >= 11) {
+		pipe_chicken = I915_READ(PIPE_CHICKEN(pipe));
+		if (!(pipe_chicken & PER_PIXEL_ALPHA_BYPASS_EN))
+			I915_WRITE_FW(PIPE_CHICKEN(pipe),
+				      pipe_chicken | PER_PIXEL_ALPHA_BYPASS_EN);
+	}
+
 	intel_ddi_set_pipe_settings(pipe_config);
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_enable_transcoder_func(pipe_config);
@@ -5825,7 +5837,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
+		intel_ddi_disable_transcoder_func(old_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		skylake_scaler_disable(intel_crtc);
@@ -9347,6 +9359,7 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 		switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
 		default:
 			WARN(1, "unknown pipe linked to edp transcoder\n");
+			/* fall through */
 		case TRANS_DDI_EDP_INPUT_A_ONOFF:
 		case TRANS_DDI_EDP_INPUT_A_ON:
 			trans_edp_pipe = PIPE_A;
@@ -9402,7 +9415,7 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 		 * registers/MIPI[BXT]. We can break out here early, since we
 		 * need the same DSI PLL to be enabled for both DSI ports.
 		 */
-		if (!intel_dsi_pll_is_enabled(dev_priv))
+		if (!bxt_dsi_pll_is_enabled(dev_priv))
 			break;
 
 		/* XXX: this works for video mode only */
@@ -10724,7 +10737,7 @@ static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 	drm_connector_list_iter_begin(dev, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		if (connector->base.state->crtc)
-			drm_connector_unreference(&connector->base);
+			drm_connector_put(&connector->base);
 
 		if (connector->base.encoder) {
 			connector->base.state->best_encoder =
@@ -10732,7 +10745,7 @@ static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 			connector->base.state->crtc =
 				connector->base.encoder->crtc;
 
-			drm_connector_reference(&connector->base);
+			drm_connector_get(&connector->base);
 		} else {
 			connector->base.state->best_encoder = NULL;
 			connector->base.state->crtc = NULL;
@@ -11011,6 +11024,7 @@ static bool check_digital_port_conflicts(struct drm_atomic_state *state)
 		case INTEL_OUTPUT_DDI:
 			if (WARN_ON(!HAS_DDI(to_i915(dev))))
 				break;
+			/* else: fall through */
 		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_HDMI:
 		case INTEL_OUTPUT_EDP:
@@ -12542,6 +12556,19 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat
 	finish_wait(&dev_priv->gpu_error.wait_queue, &wait_reset);
 }
 
+static void intel_atomic_cleanup_work(struct work_struct *work)
+{
+	struct drm_atomic_state *state =
+		container_of(work, struct drm_atomic_state, commit_work);
+	struct drm_i915_private *i915 = to_i915(state->dev);
+
+	drm_atomic_helper_cleanup_planes(&i915->drm, state);
+	drm_atomic_helper_commit_cleanup_done(state);
+	drm_atomic_state_put(state);
+
+	intel_atomic_helper_free_state(i915);
+}
+
 static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -12702,13 +12729,16 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
 	}
 
-	drm_atomic_helper_cleanup_planes(dev, state);
-
-	drm_atomic_helper_commit_cleanup_done(state);
-
-	drm_atomic_state_put(state);
-
-	intel_atomic_helper_free_state(dev_priv);
+	/*
+	 * Defer the cleanup of the old state to a separate worker to not
+	 * impede the current task (userspace for blocking modesets) that
+	 * are executed inline. For out-of-line asynchronous modesets/flips,
+	 * deferring to a new worker seems overkill, but we would place a
+	 * schedule point (cond_resched()) here anyway to keep latencies
+	 * down.
+	 */
+	INIT_WORK(&state->commit_work, intel_atomic_cleanup_work);
+	schedule_work(&state->commit_work);
 }
 
 static void intel_atomic_commit_work(struct work_struct *work)
@@ -14105,7 +14135,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_C);
 
-		intel_dsi_init(dev_priv);
+		vlv_dsi_init(dev_priv);
 	} else if (HAS_DDI(dev_priv)) {
 		int found;
 
@@ -14211,7 +14241,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 				intel_hdmi_init(dev_priv, CHV_HDMID, PORT_D);
 		}
 
-		intel_dsi_init(dev_priv);
+		vlv_dsi_init(dev_priv);
 	} else if (!IS_GEN2(dev_priv) && !IS_PINEVIEW(dev_priv)) {
 		bool found = false;
 
@@ -14493,11 +14523,6 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 		}
 		break;
 	case DRM_FORMAT_NV12:
-		if (mode_cmd->modifier[0] == I915_FORMAT_MOD_Y_TILED_CCS ||
-		    mode_cmd->modifier[0] == I915_FORMAT_MOD_Yf_TILED_CCS) {
-			DRM_DEBUG_KMS("RC not to be enabled with NV12\n");
-			goto err;
-		}
 		if (INTEL_GEN(dev_priv) < 9 || IS_SKYLAKE(dev_priv) ||
 		    IS_BROXTON(dev_priv)) {
 			DRM_DEBUG_KMS("unsupported pixel format: %s\n",
@@ -14824,6 +14849,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev)
 	DRM_INFO("Applying T12 delay quirk\n");
 }
 
+/*
+ * GeminiLake NUC HDMI outputs require additional off time
+ * this allows the onboard retimer to correctly sync to signal
+ */
+static void quirk_increase_ddi_disabled_time(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME;
+	DRM_INFO("Applying Increase DDI Disabled quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -14910,6 +14947,13 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Toshiba Satellite P50-C-18C */
 	{ 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay },
+
+	/* GeminiLake NUC */
+	{ 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	/* ASRock ITX*/
+	{ 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
@@ -15676,11 +15720,20 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
 		u64 get_domains;
 		enum intel_display_power_domain domain;
+		struct intel_crtc_state *crtc_state;
 
 		if (!encoder->get_power_domains)
 			continue;
 
-		get_domains = encoder->get_power_domains(encoder);
+		/*
+		 * MST-primary and inactive encoders don't have a crtc state
+		 * and neither of these require any power domain references.
+		 */
+		if (!encoder->base.crtc)
+			continue;
+
+		crtc_state = to_intel_crtc_state(encoder->base.crtc->state);
+		get_domains = encoder->get_power_domains(encoder, crtc_state);
 		for_each_power_domain(domain, get_domains)
 			intel_display_power_get(dev_priv, domain);
 	}
@@ -15856,6 +15909,8 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	flush_workqueue(dev_priv->modeset_wq);
+
 	flush_work(&dev_priv->atomic_helper.free_work);
 	WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
 
@@ -15899,8 +15954,7 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder)
 {
 	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
-					  &encoder->base);
+	drm_connector_attach_encoder(&connector->base, &encoder->base);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index dd30cae5eb00..9292001cdd14 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -199,6 +199,10 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_E,
 	POWER_DOMAIN_AUX_F,
 	POWER_DOMAIN_AUX_IO_A,
+	POWER_DOMAIN_AUX_TBT1,
+	POWER_DOMAIN_AUX_TBT2,
+	POWER_DOMAIN_AUX_TBT3,
+	POWER_DOMAIN_AUX_TBT4,
 	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_MODESET,
 	POWER_DOMAIN_GT_IRQ,
@@ -285,6 +289,10 @@ struct intel_link_m_n {
 			    &(dev)->mode_config.encoder_list,	\
 			    base.head)
 
+#define for_each_intel_dp(dev, intel_encoder)			\
+	for_each_intel_encoder(dev, intel_encoder)		\
+		for_each_if(intel_encoder_is_dp(intel_encoder))
+
 #define for_each_intel_connector_iter(intel_connector, iter) \
 	while ((intel_connector = to_intel_connector(drm_connector_list_iter_next(iter))))
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 6ac6c8787dcf..cd0f649b57a5 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -600,14 +600,8 @@ static enum pipe vlv_find_free_pps(struct drm_i915_private *dev_priv)
 	 * We don't have power sequencer currently.
 	 * Pick one that's not used by other ports.
 	 */
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
 		if (encoder->type == INTEL_OUTPUT_EDP) {
 			WARN_ON(intel_dp->active_pipe != INVALID_PIPE &&
@@ -799,19 +793,8 @@ void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
 	 * should use them always.
 	 */
 
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP &&
-		    encoder->type != INTEL_OUTPUT_DDI)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
-
-		/* Skip pure DVI/HDMI DDI encoders */
-		if (!i915_mmio_reg_valid(intel_dp->output_reg))
-			continue;
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
 		WARN_ON(intel_dp->active_pipe != INVALID_PIPE);
 
@@ -953,7 +936,7 @@ intel_dp_check_edp(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
+intel_dp_aux_wait_done(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 	i915_reg_t ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
@@ -961,14 +944,10 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
 	bool done;
 
 #define C (((status = I915_READ_NOTRACE(ch_ctl)) & DP_AUX_CH_CTL_SEND_BUSY) == 0)
-	if (has_aux_irq)
-		done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
-					  msecs_to_jiffies_timeout(10));
-	else
-		done = wait_for(C, 10) == 0;
+	done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
+				  msecs_to_jiffies_timeout(10));
 	if (!done)
-		DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n",
-			  has_aux_irq);
+		DRM_ERROR("dp aux hw did not signal timeout!\n");
 #undef C
 
 	return status;
@@ -1033,7 +1012,6 @@ static uint32_t skl_get_aux_clock_divider(struct intel_dp *intel_dp, int index)
 }
 
 static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
-				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider)
 {
@@ -1054,7 +1032,7 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 
 	return DP_AUX_CH_CTL_SEND_BUSY |
 	       DP_AUX_CH_CTL_DONE |
-	       (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+	       DP_AUX_CH_CTL_INTERRUPT |
 	       DP_AUX_CH_CTL_TIME_OUT_ERROR |
 	       timeout |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
@@ -1064,13 +1042,12 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 }
 
 static uint32_t skl_get_aux_send_ctl(struct intel_dp *intel_dp,
-				      bool has_aux_irq,
 				      int send_bytes,
 				      uint32_t unused)
 {
 	return DP_AUX_CH_CTL_SEND_BUSY |
 	       DP_AUX_CH_CTL_DONE |
-	       (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+	       DP_AUX_CH_CTL_INTERRUPT |
 	       DP_AUX_CH_CTL_TIME_OUT_ERROR |
 	       DP_AUX_CH_CTL_TIME_OUT_MAX |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
@@ -1093,7 +1070,6 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	int i, ret, recv_bytes;
 	uint32_t status;
 	int try, clock = 0;
-	bool has_aux_irq = HAS_AUX_IRQ(dev_priv);
 	bool vdd;
 
 	ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
@@ -1148,7 +1124,6 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 
 	while ((aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, clock++))) {
 		u32 send_ctl = intel_dp->get_aux_send_ctl(intel_dp,
-							  has_aux_irq,
 							  send_bytes,
 							  aux_clock_divider);
 
@@ -1165,7 +1140,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 			/* Send the command and wait for it to complete */
 			I915_WRITE(ch_ctl, send_ctl);
 
-			status = intel_dp_aux_wait_done(intel_dp, has_aux_irq);
+			status = intel_dp_aux_wait_done(intel_dp);
 
 			/* Clear done status and any errors */
 			I915_WRITE(ch_ctl,
@@ -2838,10 +2813,6 @@ static void vlv_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);
-
-	intel_psr_disable(intel_dp, old_crtc_state);
-
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
 }
 
@@ -3054,10 +3025,7 @@ static void vlv_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);
-
 	intel_edp_backlight_on(pipe_config, conn_state);
-	intel_psr_enable(intel_dp, pipe_config);
 }
 
 static void g4x_pre_enable_dp(struct intel_encoder *encoder,
@@ -3112,16 +3080,9 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv,
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-		enum port port;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
-		port = dp_to_dig_port(intel_dp)->base.port;
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		enum port port = encoder->port;
 
 		WARN(intel_dp->active_pipe == pipe,
 		     "stealing pipe %c power sequencer from active (e)DP port %c\n",
@@ -3913,129 +3874,6 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 					intel_dp->is_mst);
 }
 
-static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp,
-				  struct intel_crtc_state *crtc_state, bool disable_wa)
-{
-	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 intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int ret = 0;
-	int count = 0;
-	int attempts = 10;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) {
-		DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
-			       buf & ~DP_TEST_SINK_START) < 0) {
-		DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	do {
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_TEST_SINK_MISC, &buf) < 0) {
-			ret = -EIO;
-			goto out;
-		}
-		count = buf & DP_TEST_COUNT_MASK;
-	} while (--attempts && count);
-
-	if (attempts == 0) {
-		DRM_DEBUG_KMS("TIMEOUT: Sink CRC counter is not zeroed after calculation is stopped\n");
-		ret = -ETIMEDOUT;
-	}
-
- out:
-	if (disable_wa)
-		hsw_enable_ips(crtc_state);
-	return ret;
-}
-
-static int intel_dp_sink_crc_start(struct intel_dp *intel_dp,
-				   struct intel_crtc_state *crtc_state)
-{
-	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 intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int ret;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0)
-		return -EIO;
-
-	if (!(buf & DP_TEST_CRC_SUPPORTED))
-		return -ENOTTY;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0)
-		return -EIO;
-
-	if (buf & DP_TEST_SINK_START) {
-		ret = intel_dp_sink_crc_stop(intel_dp, crtc_state, false);
-		if (ret)
-			return ret;
-	}
-
-	hsw_disable_ips(crtc_state);
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
-			       buf | DP_TEST_SINK_START) < 0) {
-		hsw_enable_ips(crtc_state);
-		return -EIO;
-	}
-
-	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-	return 0;
-}
-
-int intel_dp_sink_crc(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state, u8 *crc)
-{
-	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 intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int count, ret;
-	int attempts = 6;
-
-	ret = intel_dp_sink_crc_start(intel_dp, crtc_state);
-	if (ret)
-		return ret;
-
-	do {
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_TEST_SINK_MISC, &buf) < 0) {
-			ret = -EIO;
-			goto stop;
-		}
-		count = buf & DP_TEST_COUNT_MASK;
-
-	} while (--attempts && count == 0);
-
-	if (attempts == 0) {
-		DRM_ERROR("Panel is unable to calculate any CRC after 6 vblanks\n");
-		ret = -ETIMEDOUT;
-		goto stop;
-	}
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) {
-		ret = -EIO;
-		goto stop;
-	}
-
-stop:
-	intel_dp_sink_crc_stop(intel_dp, crtc_state, true);
-	return ret;
-}
-
 static bool
 intel_dp_get_sink_irq(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 {
@@ -4495,10 +4333,15 @@ intel_dp_short_pulse(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
+	/* Handle CEC interrupts, if any */
+	drm_dp_cec_irq(&intel_dp->aux);
+
 	/* defer to the hotplug work for link retraining if needed */
 	if (intel_dp_needs_link_retrain(intel_dp))
 		return false;
 
+	intel_psr_short_pulse(intel_dp);
+
 	if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) {
 		DRM_DEBUG_KMS("Link Training Compliance Test requested\n");
 		/* Send a Hotplug Uevent to userspace to start modeset */
@@ -4566,14 +4409,7 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 static enum drm_connector_status
 edp_detect(struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum drm_connector_status status;
-
-	status = intel_panel_detect(dev_priv);
-	if (status == connector_status_unknown)
-		status = connector_status_connected;
-
-	return status;
+	return connector_status_connected;
 }
 
 static bool ibx_digital_port_connected(struct intel_encoder *encoder)
@@ -4809,6 +4645,7 @@ intel_dp_set_edid(struct intel_dp *intel_dp)
 	intel_connector->detect_edid = edid;
 
 	intel_dp->has_audio = drm_detect_monitor_audio(edid);
+	drm_dp_cec_set_edid(&intel_dp->aux, edid);
 }
 
 static void
@@ -4816,6 +4653,7 @@ intel_dp_unset_edid(struct intel_dp *intel_dp)
 {
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 
+	drm_dp_cec_unset_edid(&intel_dp->aux);
 	kfree(intel_connector->detect_edid);
 	intel_connector->detect_edid = NULL;
 
@@ -4834,7 +4672,7 @@ intel_dp_long_pulse(struct intel_connector *connector)
 
 	intel_display_power_get(dev_priv, intel_dp->aux_power_domain);
 
-	/* Can't disconnect eDP, but you can close the lid... */
+	/* Can't disconnect eDP */
 	if (intel_dp_is_edp(intel_dp))
 		status = edp_detect(intel_dp);
 	else if (intel_digital_port_connected(&dp_to_dig_port(intel_dp)->base))
@@ -5004,6 +4842,7 @@ static int
 intel_dp_connector_register(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_device *dev = connector->dev;
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -5016,13 +4855,20 @@ intel_dp_connector_register(struct drm_connector *connector)
 		      intel_dp->aux.name, connector->kdev->kobj.name);
 
 	intel_dp->aux.dev = connector->kdev;
-	return drm_dp_aux_register(&intel_dp->aux);
+	ret = drm_dp_aux_register(&intel_dp->aux);
+	if (!ret)
+		drm_dp_cec_register_connector(&intel_dp->aux,
+					      connector->name, dev->dev);
+	return ret;
 }
 
 static void
 intel_dp_connector_unregister(struct drm_connector *connector)
 {
-	drm_dp_aux_unregister(&intel_attached_dp(connector)->aux);
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+
+	drm_dp_cec_unregister_connector(&intel_dp->aux);
+	drm_dp_aux_unregister(&intel_dp->aux);
 	intel_connector_unregister(connector);
 }
 
@@ -6218,7 +6064,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 		} else {
 			kfree(edid);
@@ -6307,8 +6153,8 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work)
 	/* Set connector link status to BAD and send a Uevent to notify
 	 * userspace to do a modeset.
 	 */
-	drm_mode_connector_set_link_status_property(connector,
-						    DRM_MODE_LINK_STATUS_BAD);
+	drm_connector_set_link_status_property(connector,
+					       DRM_MODE_LINK_STATUS_BAD);
 	mutex_unlock(&connector->dev->mode_config.mutex);
 	/* Send Hotplug uevent so userspace can reprobe */
 	drm_kms_helper_hotplug_event(connector->dev);
@@ -6501,7 +6347,6 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 	intel_encoder->port = port;
 
 	intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
-	dev_priv->hotplug.irq_port[port] = intel_dig_port;
 
 	if (port != PORT_A)
 		intel_infoframe_init(intel_dig_port);
@@ -6520,37 +6365,44 @@ err_connector_alloc:
 	return false;
 }
 
-void intel_dp_mst_suspend(struct drm_device *dev)
+void intel_dp_mst_suspend(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
+	struct intel_encoder *encoder;
 
-	/* disable MST */
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp;
+
+		if (encoder->type != INTEL_OUTPUT_DDI)
+			continue;
 
-		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+		intel_dp = enc_to_intel_dp(&encoder->base);
+
+		if (!intel_dp->can_mst)
 			continue;
 
-		if (intel_dig_port->dp.is_mst)
-			drm_dp_mst_topology_mgr_suspend(&intel_dig_port->dp.mst_mgr);
+		if (intel_dp->is_mst)
+			drm_dp_mst_topology_mgr_suspend(&intel_dp->mst_mgr);
 	}
 }
 
-void intel_dp_mst_resume(struct drm_device *dev)
+void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
+	struct intel_encoder *encoder;
 
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp;
 		int ret;
 
-		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+		if (encoder->type != INTEL_OUTPUT_DDI)
+			continue;
+
+		intel_dp = enc_to_intel_dp(&encoder->base);
+
+		if (!intel_dp->can_mst)
 			continue;
 
-		ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
+		ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr);
 		if (ret)
-			intel_dp_check_mst_status(&intel_dig_port->dp);
+			intel_dp_check_mst_status(intel_dp);
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 5890500a3a8b..7e3e01607643 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -403,20 +403,10 @@ static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *c
 	return &intel_dp->mst_encoders[crtc->pipe]->base.base;
 }
 
-static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connector)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_dp *intel_dp = intel_connector->mst_port;
-	if (!intel_dp)
-		return NULL;
-	return &intel_dp->mst_encoders[0]->base.base;
-}
-
 static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_funcs = {
 	.get_modes = intel_dp_mst_get_modes,
 	.mode_valid = intel_dp_mst_mode_valid,
 	.atomic_best_encoder = intel_mst_atomic_best_encoder,
-	.best_encoder = intel_mst_best_encoder,
 	.atomic_check = intel_dp_mst_atomic_check,
 };
 
@@ -476,8 +466,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 		struct drm_encoder *enc =
 			&intel_dp->mst_encoders[pipe]->base.base;
 
-		ret = drm_mode_connector_attach_encoder(&intel_connector->base,
-							enc);
+		ret = drm_connector_attach_encoder(&intel_connector->base, enc);
 		if (ret)
 			goto err;
 	}
@@ -485,7 +474,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
 
-	ret = drm_mode_connector_set_path_property(connector, pathprop);
+	ret = drm_connector_set_path_property(connector, pathprop);
 	if (ret)
 		goto err;
 
@@ -524,7 +513,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	intel_connector->mst_port = NULL;
 	drm_modeset_unlock(&connector->dev->mode_config.connection_mutex);
 
-	drm_connector_unreference(connector);
+	drm_connector_put(connector);
 }
 
 static void intel_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 156f8e4cbe4c..b51ad2917dbe 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -2566,6 +2566,7 @@ int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv,
 	switch (index) {
 	default:
 		MISSING_CASE(index);
+		/* fall through */
 	case 0:
 		link_clock = 540000;
 		break;
@@ -2639,6 +2640,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 			switch (div1) {
 			default:
 				MISSING_CASE(div1);
+				/* fall through */
 			case 2:
 				hsdiv = 0;
 				break;
@@ -2812,25 +2814,31 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 				MG_PLL_SSC_FLLEN |
 				MG_PLL_SSC_STEPSIZE(ssc_stepsize);
 
-	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART;
-
-	if (refclk_khz != 38400) {
-		pll_state->mg_pll_tdc_coldst_bias |=
-			MG_PLL_TDC_COLDST_IREFINT_EN |
-			MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
-			MG_PLL_TDC_COLDST_COLDSTART |
-			MG_PLL_TDC_TDCOVCCORR_EN |
-			MG_PLL_TDC_TDCSEL(3);
-
-		pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
-					 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
-					 MG_PLL_BIAS_BIAS_BONUS(10) |
-					 MG_PLL_BIAS_BIASCAL_EN |
-					 MG_PLL_BIAS_CTRIM(12) |
-					 MG_PLL_BIAS_VREF_RDAC(4) |
-					 MG_PLL_BIAS_IREFTRIM(iref_trim);
+	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART |
+					    MG_PLL_TDC_COLDST_IREFINT_EN |
+					    MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
+					    MG_PLL_TDC_TDCOVCCORR_EN |
+					    MG_PLL_TDC_TDCSEL(3);
+
+	pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
+				 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
+				 MG_PLL_BIAS_BIAS_BONUS(10) |
+				 MG_PLL_BIAS_BIASCAL_EN |
+				 MG_PLL_BIAS_CTRIM(12) |
+				 MG_PLL_BIAS_VREF_RDAC(4) |
+				 MG_PLL_BIAS_IREFTRIM(iref_trim);
+
+	if (refclk_khz == 38400) {
+		pll_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
+		pll_state->mg_pll_bias_mask = 0;
+	} else {
+		pll_state->mg_pll_tdc_coldst_bias_mask = -1U;
+		pll_state->mg_pll_bias_mask = -1U;
 	}
 
+	pll_state->mg_pll_tdc_coldst_bias &= pll_state->mg_pll_tdc_coldst_bias_mask;
+	pll_state->mg_pll_bias &= pll_state->mg_pll_bias_mask;
+
 	return true;
 }
 
@@ -2897,6 +2905,7 @@ static i915_reg_t icl_pll_id_to_enable_reg(enum intel_dpll_id id)
 	switch (id) {
 	default:
 		MISSING_CASE(id);
+		/* fall through */
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return CNL_DPLL_ENABLE(id);
@@ -2939,18 +2948,41 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	case DPLL_ID_ICL_MGPLL4:
 		port = icl_mg_pll_id_to_port(id);
 		hw_state->mg_refclkin_ctl = I915_READ(MG_REFCLKIN_CTL(port));
+		hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+
 		hw_state->mg_clktop2_coreclkctl1 =
 			I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+		hw_state->mg_clktop2_coreclkctl1 &=
+			MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+
 		hw_state->mg_clktop2_hsclkctl =
 			I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+		hw_state->mg_clktop2_hsclkctl &=
+			MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+			MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+			MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+			MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK;
+
 		hw_state->mg_pll_div0 = I915_READ(MG_PLL_DIV0(port));
 		hw_state->mg_pll_div1 = I915_READ(MG_PLL_DIV1(port));
 		hw_state->mg_pll_lf = I915_READ(MG_PLL_LF(port));
 		hw_state->mg_pll_frac_lock = I915_READ(MG_PLL_FRAC_LOCK(port));
 		hw_state->mg_pll_ssc = I915_READ(MG_PLL_SSC(port));
+
 		hw_state->mg_pll_bias = I915_READ(MG_PLL_BIAS(port));
 		hw_state->mg_pll_tdc_coldst_bias =
 			I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+
+		if (dev_priv->cdclk.hw.ref == 38400) {
+			hw_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
+			hw_state->mg_pll_bias_mask = 0;
+		} else {
+			hw_state->mg_pll_tdc_coldst_bias_mask = -1U;
+			hw_state->mg_pll_bias_mask = -1U;
+		}
+
+		hw_state->mg_pll_tdc_coldst_bias &= hw_state->mg_pll_tdc_coldst_bias_mask;
+		hw_state->mg_pll_bias &= hw_state->mg_pll_bias_mask;
 		break;
 	default:
 		MISSING_CASE(id);
@@ -2978,19 +3010,48 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 {
 	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
 	enum port port = icl_mg_pll_id_to_port(pll->info->id);
+	u32 val;
+
+	/*
+	 * Some of the following registers have reserved fields, so program
+	 * these with RMW based on a mask. The mask can be fixed or generated
+	 * during the calc/readout phase if the mask depends on some other HW
+	 * state like refclk, see icl_calc_mg_pll_state().
+	 */
+	val = I915_READ(MG_REFCLKIN_CTL(port));
+	val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+	val |= hw_state->mg_refclkin_ctl;
+	I915_WRITE(MG_REFCLKIN_CTL(port), val);
+
+	val = I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+	val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+	val |= hw_state->mg_clktop2_coreclkctl1;
+	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port), val);
+
+	val = I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+	val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+		 MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK);
+	val |= hw_state->mg_clktop2_hsclkctl;
+	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), val);
 
-	I915_WRITE(MG_REFCLKIN_CTL(port), hw_state->mg_refclkin_ctl);
-	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port),
-		   hw_state->mg_clktop2_coreclkctl1);
-	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), hw_state->mg_clktop2_hsclkctl);
 	I915_WRITE(MG_PLL_DIV0(port), hw_state->mg_pll_div0);
 	I915_WRITE(MG_PLL_DIV1(port), hw_state->mg_pll_div1);
 	I915_WRITE(MG_PLL_LF(port), hw_state->mg_pll_lf);
 	I915_WRITE(MG_PLL_FRAC_LOCK(port), hw_state->mg_pll_frac_lock);
 	I915_WRITE(MG_PLL_SSC(port), hw_state->mg_pll_ssc);
-	I915_WRITE(MG_PLL_BIAS(port), hw_state->mg_pll_bias);
-	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port),
-		   hw_state->mg_pll_tdc_coldst_bias);
+
+	val = I915_READ(MG_PLL_BIAS(port));
+	val &= ~hw_state->mg_pll_bias_mask;
+	val |= hw_state->mg_pll_bias;
+	I915_WRITE(MG_PLL_BIAS(port), val);
+
+	val = I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+	val &= ~hw_state->mg_pll_tdc_coldst_bias_mask;
+	val |= hw_state->mg_pll_tdc_coldst_bias;
+	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port), val);
+
 	POSTING_READ(MG_PLL_TDC_COLDST_BIAS(port));
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h
index ba925c7ee482..7e522cf4f13f 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h
@@ -180,6 +180,8 @@ struct intel_dpll_hw_state {
 	uint32_t mg_pll_ssc;
 	uint32_t mg_pll_bias;
 	uint32_t mg_pll_tdc_coldst_bias;
+	uint32_t mg_pll_bias_mask;
+	uint32_t mg_pll_tdc_coldst_bias_mask;
 };
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0c3ac0eafde0..c275f91244a6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -254,7 +254,8 @@ struct intel_encoder {
 			   struct intel_crtc_state *pipe_config);
 	/* Returns a mask of power domains that need to be referenced as part
 	 * of the hardware state readout code. */
-	u64 (*get_power_domains)(struct intel_encoder *encoder);
+	u64 (*get_power_domains)(struct intel_encoder *encoder,
+				 struct intel_crtc_state *crtc_state);
 	/*
 	 * Called during system suspend after all pending requests for the
 	 * encoder are flushed (for example for DP AUX transactions) and
@@ -303,6 +304,8 @@ struct intel_panel {
 	} backlight;
 };
 
+struct intel_digital_port;
+
 /*
  * This structure serves as a translation layer between the generic HDCP code
  * and the bus-specific code. What that means is that HDCP over HDMI differs
@@ -1133,7 +1136,6 @@ struct intel_dp {
 	 * register with to kick off an AUX transaction.
 	 */
 	uint32_t (*get_aux_send_ctl)(struct intel_dp *dp,
-				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider);
 
@@ -1246,22 +1248,29 @@ intel_attached_encoder(struct drm_connector *connector)
 	return to_intel_connector(connector)->encoder;
 }
 
-static inline struct intel_digital_port *
-enc_to_dig_port(struct drm_encoder *encoder)
+static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
 {
-	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
-
-	switch (intel_encoder->type) {
+	switch (encoder->type) {
 	case INTEL_OUTPUT_DDI:
-		WARN_ON(!HAS_DDI(to_i915(encoder->dev)));
 	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_EDP:
 	case INTEL_OUTPUT_HDMI:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline struct intel_digital_port *
+enc_to_dig_port(struct drm_encoder *encoder)
+{
+	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
+
+	if (intel_encoder_is_dig_port(intel_encoder))
 		return container_of(encoder, struct intel_digital_port,
 				    base.base);
-	default:
+	else
 		return NULL;
-	}
 }
 
 static inline struct intel_dp_mst_encoder *
@@ -1275,6 +1284,20 @@ static inline struct intel_dp *enc_to_intel_dp(struct drm_encoder *encoder)
 	return &enc_to_dig_port(encoder)->dp;
 }
 
+static inline bool intel_encoder_is_dp(struct intel_encoder *encoder)
+{
+	switch (encoder->type) {
+	case INTEL_OUTPUT_DP:
+	case INTEL_OUTPUT_EDP:
+		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);
+	default:
+		return false;
+	}
+}
+
 static inline struct intel_digital_port *
 dp_to_dig_port(struct intel_dp *intel_dp)
 {
@@ -1331,9 +1354,6 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv);
 void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv);
 
 /* i915_irq.c */
-bool gen11_reset_one_iir(struct drm_i915_private * const i915,
-			 const unsigned int bank,
-			 const unsigned int bit);
 void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen6_mask_pm_irq(struct drm_i915_private *dev_priv, u32 mask);
@@ -1384,8 +1404,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc,
 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);
 void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state);
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder);
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
 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);
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state);
@@ -1664,8 +1683,6 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 void intel_dp_encoder_reset(struct drm_encoder *encoder);
 void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder);
 void intel_dp_encoder_destroy(struct drm_encoder *encoder);
-int intel_dp_sink_crc(struct intel_dp *intel_dp,
-		      struct intel_crtc_state *crtc_state, u8 *crc);
 bool intel_dp_compute_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config,
 			     struct drm_connector_state *conn_state);
@@ -1679,8 +1696,8 @@ void intel_edp_backlight_off(const struct drm_connector_state *conn_state);
 void intel_edp_panel_vdd_on(struct intel_dp *intel_dp);
 void intel_edp_panel_on(struct intel_dp *intel_dp);
 void intel_edp_panel_off(struct intel_dp *intel_dp);
-void intel_dp_mst_suspend(struct drm_device *dev);
-void intel_dp_mst_resume(struct drm_device *dev);
+void intel_dp_mst_suspend(struct drm_i915_private *dev_priv);
+void intel_dp_mst_resume(struct drm_i915_private *dev_priv);
 int intel_dp_max_link_rate(struct intel_dp *intel_dp);
 int intel_dp_max_lane_count(struct intel_dp *intel_dp);
 int intel_dp_rate_select(struct intel_dp *intel_dp, int rate);
@@ -1730,8 +1747,8 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector);
 /* intel_dp_mst.c */
 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);
-/* intel_dsi.c */
-void intel_dsi_init(struct drm_i915_private *dev_priv);
+/* vlv_dsi.c */
+void vlv_dsi_init(struct drm_i915_private *dev_priv);
 
 /* intel_dsi_dcs_backlight.c */
 int intel_dsi_dcs_init_backlight_funcs(struct intel_connector *intel_connector);
@@ -1873,7 +1890,6 @@ void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state);
 void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state);
 void intel_panel_destroy_backlight(struct drm_connector *connector);
-enum drm_connector_status intel_panel_detect(struct drm_i915_private *dev_priv);
 extern struct drm_display_mode *intel_find_panel_downclock(
 				struct drm_i915_private *dev_priv,
 				struct drm_display_mode *fixed_mode,
@@ -1921,6 +1937,8 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 			      struct intel_crtc_state *crtc_state);
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
+void intel_psr_short_pulse(struct intel_dp *intel_dp);
+int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state);
 
 /* intel_runtime_pm.c */
 int intel_power_domains_init(struct drm_i915_private *);
@@ -2069,7 +2087,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 
 
 /* intel_sprite.c */
-bool intel_format_is_yuv(u32 format);
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs);
 struct intel_plane *intel_sprite_plane_create(struct drm_i915_private *dev_priv,
@@ -2085,7 +2102,6 @@ void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
 bool skl_plane_get_hw_state(struct intel_plane *plane, enum pipe *pipe);
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, enum plane_id plane_id);
-bool intel_format_is_yuv(uint32_t format);
 bool skl_plane_has_planar(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, enum plane_id plane_id);
 
@@ -2151,7 +2167,6 @@ void lspcon_resume(struct intel_lspcon *lspcon);
 void lspcon_wait_pcon_mode(struct intel_lspcon *lspcon);
 
 /* intel_pipe_crc.c */
-int intel_pipe_crc_create(struct drm_minor *minor);
 #ifdef CONFIG_DEBUG_FS
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
 			      size_t *values_cnt);
@@ -2167,5 +2182,4 @@ static inline void intel_crtc_enable_pipe_crc(struct intel_crtc *crtc)
 {
 }
 #endif
-extern const struct file_operations i915_display_crc_ctl_fops;
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index 7afeb9580f41..ad7c1cb32983 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -129,21 +129,29 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 	return container_of(encoder, struct intel_dsi, base.base);
 }
 
-/* intel_dsi.c */
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
+/* vlv_dsi.c */
+void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
 enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt);
 
-/* intel_dsi_pll.c */
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config);
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config);
-void intel_disable_dsi_pll(struct intel_encoder *encoder);
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config);
-void intel_dsi_reset_clocks(struct intel_encoder *encoder,
-			    enum port port);
+/* vlv_dsi_pll.c */
+int vlv_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config);
+void vlv_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config);
+void vlv_dsi_pll_disable(struct intel_encoder *encoder);
+u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config);
+void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
+
+bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
+int bxt_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config);
+void bxt_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config);
+void bxt_dsi_pll_disable(struct intel_encoder *encoder);
+u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config);
+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);
diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c
index 4d6ffa7b3e7b..ac83d6b89ae0 100644
--- a/drivers/gpu/drm/i915/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c
@@ -181,7 +181,7 @@ static const u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi,
 		break;
 	}
 
-	wait_for_dsi_fifo_empty(intel_dsi, port);
+	vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
 
 out:
 	data += len;
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 32bf3a408d46..2d1952849d69 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -25,7 +25,6 @@
 #include <drm/drm_print.h>
 
 #include "i915_drv.h"
-#include "i915_vgpu.h"
 #include "intel_ringbuffer.h"
 #include "intel_lrc.h"
 
@@ -230,6 +229,7 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		break;
 	default:
 		MISSING_CASE(class);
+		/* fall through */
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
@@ -302,6 +302,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 							   engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
+	if (engine->context_size)
+		DRIVER_CAPS(dev_priv)->has_logical_contexts = true;
 
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
@@ -456,28 +458,16 @@ static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
 	i915_gem_batch_pool_init(&engine->batch_pool, engine);
 }
 
-static bool csb_force_mmio(struct drm_i915_private *i915)
-{
-	/* Older GVT emulation depends upon intercepting CSB mmio */
-	if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915))
-		return true;
-
-	return false;
-}
-
 static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
-	execlists->csb_use_mmio = csb_force_mmio(engine->i915);
-
 	execlists->port_mask = 1;
 	BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists));
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 }
 
 /**
@@ -492,6 +482,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 void intel_engine_setup_common(struct intel_engine_cs *engine)
 {
 	i915_timeline_init(engine->i915, &engine->timeline, engine->name);
+	lockdep_set_subclass(&engine->timeline.lock, TIMELINE_ENGINE);
 
 	intel_engine_init_execlist(engine);
 	intel_engine_init_hangcheck(engine);
@@ -998,19 +989,23 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 
 	/* Waiting to drain ELSP? */
 	if (READ_ONCE(engine->execlists.active)) {
-		struct intel_engine_execlists *execlists = &engine->execlists;
-
-		if (tasklet_trylock(&execlists->tasklet)) {
-			execlists->tasklet.func(execlists->tasklet.data);
-			tasklet_unlock(&execlists->tasklet);
+		struct tasklet_struct *t = &engine->execlists.tasklet;
+
+		local_bh_disable();
+		if (tasklet_trylock(t)) {
+			/* Must wait for any GPU reset in progress. */
+			if (__tasklet_is_enabled(t))
+				t->func(t->data);
+			tasklet_unlock(t);
 		}
+		local_bh_enable();
 
-		if (READ_ONCE(execlists->active))
+		if (READ_ONCE(engine->execlists.active))
 			return false;
 	}
 
 	/* ELSP is empty, but there are ready requests? E.g. after reset */
-	if (READ_ONCE(engine->execlists.first))
+	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
 		return false;
 
 	/* Ring stopped? */
@@ -1363,12 +1358,10 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
 		read = GEN8_CSB_READ_PTR(ptr);
 		write = GEN8_CSB_WRITE_PTR(ptr);
-		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s, tasklet queued? %s (%s)\n",
+		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], tasklet queued? %s (%s)\n",
 			   read, execlists->csb_head,
 			   write,
 			   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
-			   yesno(test_bit(ENGINE_IRQ_EXECLIST,
-					  &engine->irq_posted)),
 			   yesno(test_bit(TASKLET_STATE_SCHED,
 					  &engine->execlists.tasklet.state)),
 			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
@@ -1548,7 +1541,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	last = NULL;
 	count = 0;
 	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
-	for (rb = execlists->first; rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p =
 			rb_entry(rb, typeof(*p), node);
 
@@ -1580,11 +1573,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	spin_unlock(&b->rb_lock);
 	local_irq_restore(flags);
 
-	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
+	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n",
 		   engine->irq_posted,
 		   yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
-				  &engine->irq_posted)),
-		   yesno(test_bit(ENGINE_IRQ_EXECLIST,
 				  &engine->irq_posted)));
 
 	drm_printf(m, "HWSP:\n");
@@ -1633,8 +1624,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	tasklet_disable(&execlists->tasklet);
-	write_seqlock_irqsave(&engine->stats.lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	write_seqlock(&engine->stats.lock);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1658,8 +1649,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-	tasklet_enable(&execlists->tasklet);
+	write_sequnlock(&engine->stats.lock);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index b431b6733cc1..01d1d2088f04 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -399,89 +399,6 @@ bool intel_fbc_is_active(struct drm_i915_private *dev_priv)
 	return dev_priv->fbc.active;
 }
 
-static void intel_fbc_work_fn(struct work_struct *__work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(__work, struct drm_i915_private, fbc.work.work);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_work *work = &fbc->work;
-	struct intel_crtc *crtc = fbc->crtc;
-	struct drm_vblank_crtc *vblank = &dev_priv->drm.vblank[crtc->pipe];
-
-	if (drm_crtc_vblank_get(&crtc->base)) {
-		/* CRTC is now off, leave FBC deactivated */
-		mutex_lock(&fbc->lock);
-		work->scheduled = false;
-		mutex_unlock(&fbc->lock);
-		return;
-	}
-
-retry:
-	/* Delay the actual enabling to let pageflipping cease and the
-	 * display to settle before starting the compression. Note that
-	 * this delay also serves a second purpose: it allows for a
-	 * vblank to pass after disabling the FBC before we attempt
-	 * to modify the control registers.
-	 *
-	 * WaFbcWaitForVBlankBeforeEnable:ilk,snb
-	 *
-	 * It is also worth mentioning that since work->scheduled_vblank can be
-	 * updated multiple times by the other threads, hitting the timeout is
-	 * not an error condition. We'll just end up hitting the "goto retry"
-	 * case below.
-	 */
-	wait_event_timeout(vblank->queue,
-		drm_crtc_vblank_count(&crtc->base) != work->scheduled_vblank,
-		msecs_to_jiffies(50));
-
-	mutex_lock(&fbc->lock);
-
-	/* Were we cancelled? */
-	if (!work->scheduled)
-		goto out;
-
-	/* Were we delayed again while this function was sleeping? */
-	if (drm_crtc_vblank_count(&crtc->base) == work->scheduled_vblank) {
-		mutex_unlock(&fbc->lock);
-		goto retry;
-	}
-
-	intel_fbc_hw_activate(dev_priv);
-
-	work->scheduled = false;
-
-out:
-	mutex_unlock(&fbc->lock);
-	drm_crtc_vblank_put(&crtc->base);
-}
-
-static void intel_fbc_schedule_activation(struct intel_crtc *crtc)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_work *work = &fbc->work;
-
-	WARN_ON(!mutex_is_locked(&fbc->lock));
-	if (WARN_ON(!fbc->enabled))
-		return;
-
-	if (drm_crtc_vblank_get(&crtc->base)) {
-		DRM_ERROR("vblank not available for FBC on pipe %c\n",
-			  pipe_name(crtc->pipe));
-		return;
-	}
-
-	/* It is useless to call intel_fbc_cancel_work() or cancel_work() in
-	 * this function since we're not releasing fbc.lock, so it won't have an
-	 * opportunity to grab it to discover that it was cancelled. So we just
-	 * update the expected jiffy count. */
-	work->scheduled = true;
-	work->scheduled_vblank = drm_crtc_vblank_count(&crtc->base);
-	drm_crtc_vblank_put(&crtc->base);
-
-	schedule_work(&work->work);
-}
-
 static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 				 const char *reason)
 {
@@ -489,11 +406,6 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	/* Calling cancel_work() here won't help due to the fact that the work
-	 * function grabs fbc->lock. Just set scheduled to false so the work
-	 * function can know it was cancelled. */
-	fbc->work.scheduled = false;
-
 	if (fbc->active)
 		intel_fbc_hw_deactivate(dev_priv);
 
@@ -924,13 +836,6 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 						32 * fbc->threshold) * 8;
 }
 
-static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
-				       struct intel_fbc_reg_params *params2)
-{
-	/* We can use this since intel_fbc_get_reg_params() does a memset. */
-	return memcmp(params1, params2, sizeof(*params1)) == 0;
-}
-
 void intel_fbc_pre_update(struct intel_crtc *crtc,
 			  struct intel_crtc_state *crtc_state,
 			  struct intel_plane_state *plane_state)
@@ -953,6 +858,7 @@ void intel_fbc_pre_update(struct intel_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);
@@ -988,13 +894,15 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_reg_params old_params;
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
 	if (!fbc->enabled || 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");
 		__intel_fbc_disable(dev_priv);
@@ -1002,25 +910,16 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 		return;
 	}
 
-	if (!intel_fbc_can_activate(crtc)) {
-		WARN_ON(fbc->active);
-		return;
-	}
-
-	old_params = fbc->params;
 	intel_fbc_get_reg_params(crtc, &fbc->params);
 
-	/* If the scanout has not changed, don't modify the FBC settings.
-	 * Note that we make the fundamental assumption that the fb->obj
-	 * cannot be unpinned (and have its GTT offset and fence revoked)
-	 * without first being decoupled from the scanout and FBC disabled.
-	 */
-	if (fbc->active &&
-	    intel_fbc_reg_params_equal(&old_params, &fbc->params))
+	if (!intel_fbc_can_activate(crtc))
 		return;
 
-	intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
-	intel_fbc_schedule_activation(crtc);
+	if (!fbc->busy_bits) {
+		intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
+		intel_fbc_hw_activate(dev_priv);
+	} else
+		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 }
 
 void intel_fbc_post_update(struct intel_crtc *crtc)
@@ -1085,7 +984,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
 		if (fbc->active)
 			intel_fbc_recompress(dev_priv);
-		else
+		else if (!fbc->flip_pending)
 			__intel_fbc_post_update(fbc->crtc);
 	}
 
@@ -1225,8 +1124,6 @@ void intel_fbc_disable(struct intel_crtc *crtc)
 	if (fbc->crtc == crtc)
 		__intel_fbc_disable(dev_priv);
 	mutex_unlock(&fbc->lock);
-
-	cancel_work_sync(&fbc->work.work);
 }
 
 /**
@@ -1248,8 +1145,6 @@ void intel_fbc_global_disable(struct drm_i915_private *dev_priv)
 		__intel_fbc_disable(dev_priv);
 	}
 	mutex_unlock(&fbc->lock);
-
-	cancel_work_sync(&fbc->work.work);
 }
 
 static void intel_fbc_underrun_work_fn(struct work_struct *work)
@@ -1400,12 +1295,10 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
-	INIT_WORK(&fbc->work.work, intel_fbc_work_fn);
 	INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn);
 	mutex_init(&fbc->lock);
 	fbc->enabled = false;
 	fbc->active = false;
-	fbc->work.scheduled = false;
 
 	if (need_fbc_vtd_wa(dev_priv))
 		mkwrite_device_info(dev_priv)->has_fbc = false;
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 1aff30b0870c..560c7406ae40 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -27,6 +27,8 @@
 #include "intel_guc_submission.h"
 #include "i915_drv.h"
 
+static void guc_init_ggtt_pin_bias(struct intel_guc *guc);
+
 static void gen8_guc_raise_irq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -73,7 +75,7 @@ void intel_guc_init_early(struct intel_guc *guc)
 	guc->notify = gen8_guc_raise_irq;
 }
 
-int intel_guc_init_wq(struct intel_guc *guc)
+static int guc_init_wq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
@@ -124,7 +126,7 @@ int intel_guc_init_wq(struct intel_guc *guc)
 	return 0;
 }
 
-void intel_guc_fini_wq(struct intel_guc *guc)
+static void guc_fini_wq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
@@ -135,6 +137,28 @@ void intel_guc_fini_wq(struct intel_guc *guc)
 	destroy_workqueue(guc->log.relay.flush_wq);
 }
 
+int intel_guc_init_misc(struct intel_guc *guc)
+{
+	struct drm_i915_private *i915 = guc_to_i915(guc);
+	int ret;
+
+	guc_init_ggtt_pin_bias(guc);
+
+	ret = guc_init_wq(guc);
+	if (ret)
+		return ret;
+
+	intel_uc_fw_fetch(i915, &guc->fw);
+
+	return 0;
+}
+
+void intel_guc_fini_misc(struct intel_guc *guc)
+{
+	intel_uc_fw_fini(&guc->fw);
+	guc_fini_wq(guc);
+}
+
 static int guc_shared_data_create(struct intel_guc *guc)
 {
 	struct i915_vma *vma;
@@ -169,7 +193,7 @@ int intel_guc_init(struct intel_guc *guc)
 
 	ret = guc_shared_data_create(guc);
 	if (ret)
-		return ret;
+		goto err_fetch;
 	GEM_BUG_ON(!guc->shared_data);
 
 	ret = intel_guc_log_create(&guc->log);
@@ -190,6 +214,8 @@ err_log:
 	intel_guc_log_destroy(&guc->log);
 err_shared:
 	guc_shared_data_destroy(guc);
+err_fetch:
+	intel_uc_fw_fini(&guc->fw);
 	return ret;
 }
 
@@ -201,12 +227,17 @@ void intel_guc_fini(struct intel_guc *guc)
 	intel_guc_ads_destroy(guc);
 	intel_guc_log_destroy(&guc->log);
 	guc_shared_data_destroy(guc);
+	intel_uc_fw_fini(&guc->fw);
 }
 
 static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
 	u32 level = intel_guc_log_get_level(&guc->log);
-	u32 flags = 0;
+	u32 flags;
+	u32 ads;
+
+	ads = intel_guc_ggtt_offset(guc, guc->ads_vma) >> PAGE_SHIFT;
+	flags = ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
 
 	if (!GUC_LOG_LEVEL_IS_ENABLED(level))
 		flags |= GUC_LOG_DEFAULT_DISABLED;
@@ -217,13 +248,6 @@ static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 		flags |= GUC_LOG_LEVEL_TO_VERBOSITY(level) <<
 			 GUC_LOG_VERBOSITY_SHIFT;
 
-	if (USES_GUC_SUBMISSION(guc_to_i915(guc))) {
-		u32 ads = intel_guc_ggtt_offset(guc, guc->ads_vma)
-			>> PAGE_SHIFT;
-
-		flags |= ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
-	}
-
 	return flags;
 }
 
@@ -327,6 +351,9 @@ void intel_guc_init_params(struct intel_guc *guc)
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
 	params[GUC_CTL_CTXINFO] = guc_ctl_ctxinfo_flags(guc);
 
+	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
+		DRM_DEBUG_DRIVER("param[%2d] = %#x\n", i, params[i]);
+
 	/*
 	 * All SOFT_SCRATCH registers are in FORCEWAKE_BLITTER domain and
 	 * they are power context saved so it's ok to release forcewake
@@ -439,11 +466,13 @@ void intel_guc_to_host_event_handler_mmio(struct intel_guc *guc)
 	 * could happen that GuC sets the bit for 2nd interrupt but Host
 	 * clears out the bit on handling the 1st interrupt.
 	 */
+	disable_rpm_wakeref_asserts(dev_priv);
 	spin_lock(&guc->irq_lock);
 	val = I915_READ(SOFT_SCRATCH(15));
 	msg = val & guc->msg_enabled_mask;
 	I915_WRITE(SOFT_SCRATCH(15), val & ~msg);
 	spin_unlock(&guc->irq_lock);
+	enable_rpm_wakeref_asserts(dev_priv);
 
 	intel_guc_to_host_process_recv_msg(guc, msg);
 }
@@ -585,13 +614,13 @@ int intel_guc_resume(struct intel_guc *guc)
  */
 
 /**
- * intel_guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
+ * guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
  * @guc: intel_guc structure.
  *
  * This function will calculate and initialize the ggtt_pin_bias value based on
  * overall WOPCM size and GuC WOPCM size.
  */
-void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc)
+static void guc_init_ggtt_pin_bias(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_i915(guc);
 
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index f1265e122d30..4121928a495e 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -151,11 +151,10 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 void intel_guc_init_early(struct intel_guc *guc);
 void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_init_params(struct intel_guc *guc);
-void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc);
-int intel_guc_init_wq(struct intel_guc *guc);
-void intel_guc_fini_wq(struct intel_guc *guc);
+int intel_guc_init_misc(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
 void intel_guc_fini(struct intel_guc *guc);
+void intel_guc_fini_misc(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);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index f3945258fe1b..4aa5e6463e7b 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -628,13 +628,14 @@ static void complete_preempt_context(struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
 
+	if (inject_preempt_hang(execlists))
+		return;
+
 	execlists_cancel_port_requests(execlists);
 	execlists_unwind_incomplete_requests(execlists);
 
 	wait_for_guc_preempt_report(engine);
 	intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0);
-
-	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
 /**
@@ -695,9 +696,6 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->timeline.lock);
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (port_isset(port)) {
 		if (intel_engine_has_preemption(engine)) {
 			struct guc_preempt_work *preempt_work =
@@ -719,7 +717,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 	}
 	GEM_BUG_ON(port_isset(port));
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -744,15 +742,13 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
 	}
 done:
 	execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
-	execlists->first = rb;
 	if (submit)
 		port_assign(port, last);
 	if (last)
@@ -761,7 +757,8 @@ done:
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(port_isset(execlists->port) &&
 		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	return submit;
 }
@@ -914,8 +911,12 @@ static void guc_clients_doorbell_fini(struct intel_guc *guc)
 		__update_doorbell_desc(guc->preempt_client,
 				       GUC_DOORBELL_INVALID);
 	}
-	__destroy_doorbell(guc->execbuf_client);
-	__update_doorbell_desc(guc->execbuf_client, GUC_DOORBELL_INVALID);
+
+	if (guc->execbuf_client) {
+		__destroy_doorbell(guc->execbuf_client);
+		__update_doorbell_desc(guc->execbuf_client,
+				       GUC_DOORBELL_INVALID);
+	}
 }
 
 /**
@@ -1128,7 +1129,8 @@ static void guc_clients_destroy(struct intel_guc *guc)
 		guc_client_free(client);
 
 	client = fetch_and_zero(&guc->execbuf_client);
-	guc_client_free(client);
+	if (client)
+		guc_client_free(client);
 }
 
 /*
@@ -1183,7 +1185,8 @@ void intel_guc_submission_fini(struct intel_guc *guc)
 	guc_clients_destroy(guc);
 	WARN_ON(!guc_verify_doorbells(guc));
 
-	guc_stage_desc_pool_destroy(guc);
+	if (guc->stage_desc_pool)
+		guc_stage_desc_pool_destroy(guc);
 }
 
 static void guc_interrupts_capture(struct drm_i915_private *dev_priv)
@@ -1266,6 +1269,31 @@ static void guc_submission_unpark(struct intel_engine_cs *engine)
 	intel_engine_pin_breadcrumbs_irq(engine);
 }
 
+static void guc_set_default_submission(struct intel_engine_cs *engine)
+{
+	/*
+	 * We inherit a bunch of functions from execlists that we'd like
+	 * to keep using:
+	 *
+	 *    engine->submit_request = execlists_submit_request;
+	 *    engine->cancel_requests = execlists_cancel_requests;
+	 *    engine->schedule = execlists_schedule;
+	 *
+	 * But we need to override the actual submission backend in order
+	 * to talk to the GuC.
+	 */
+	intel_execlists_set_default_submission(engine);
+
+	engine->execlists.tasklet.func = guc_submission_tasklet;
+
+	engine->park = guc_submission_park;
+	engine->unpark = guc_submission_unpark;
+
+	engine->reset.prepare = guc_reset_prepare;
+
+	engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
+}
+
 int intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -1304,17 +1332,8 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	guc_interrupts_capture(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		struct intel_engine_execlists * const execlists =
-			&engine->execlists;
-
-		execlists->tasklet.func = guc_submission_tasklet;
-
-		engine->reset.prepare = guc_reset_prepare;
-
-		engine->park = guc_submission_park;
-		engine->unpark = guc_submission_unpark;
-
-		engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
+		engine->set_default_submission = guc_set_default_submission;
+		engine->set_default_submission(engine);
 	}
 
 	return 0;
@@ -1328,9 +1347,6 @@ void intel_guc_submission_disable(struct intel_guc *guc)
 
 	guc_interrupts_release(dev_priv);
 	guc_clients_doorbell_fini(guc);
-
-	/* Revert back to manual ELSP submission */
-	intel_engines_reset_default_submission(dev_priv);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index a6291f60545b..c22b3e18a0f5 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -92,6 +92,9 @@ int intel_gvt_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
 	if (!i915_modparams.enable_gvt) {
 		DRM_DEBUG_DRIVER("GVT-g is disabled by kernel params\n");
 		return 0;
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 43aa92beff2a..648a13c6043c 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -77,37 +77,6 @@
  */
 
 /**
- * intel_hpd_port - return port hard associated with certain pin.
- * @dev_priv: private driver data pointer
- * @pin: the hpd pin to get associated port
- *
- * Return port that is associatade with @pin and PORT_NONE if no port is
- * hard associated with that @pin.
- */
-enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
-				enum hpd_pin pin)
-{
-	switch (pin) {
-	case HPD_PORT_A:
-		return PORT_A;
-	case HPD_PORT_B:
-		return PORT_B;
-	case HPD_PORT_C:
-		return PORT_C;
-	case HPD_PORT_D:
-		return PORT_D;
-	case HPD_PORT_E:
-		if (IS_CNL_WITH_PORT_F(dev_priv))
-			return PORT_F;
-		return PORT_E;
-	case HPD_PORT_F:
-		return PORT_F;
-	default:
-		return PORT_NONE; /* no port for this pin */
-	}
-}
-
-/**
  * intel_hpd_pin_default - return default pin associated with certain port.
  * @dev_priv: private driver data pointer
  * @port: the hpd port to get associated pin
@@ -241,25 +210,25 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		container_of(work, typeof(*dev_priv),
 			     hotplug.reenable_work.work);
 	struct drm_device *dev = &dev_priv->drm;
-	int i;
+	enum hpd_pin pin;
 
 	intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
-	for_each_hpd_pin(i) {
+	for_each_hpd_pin(pin) {
 		struct drm_connector *connector;
 		struct drm_connector_list_iter conn_iter;
 
-		if (dev_priv->hotplug.stats[i].state != HPD_DISABLED)
+		if (dev_priv->hotplug.stats[pin].state != HPD_DISABLED)
 			continue;
 
-		dev_priv->hotplug.stats[i].state = HPD_ENABLED;
+		dev_priv->hotplug.stats[pin].state = HPD_ENABLED;
 
 		drm_connector_list_iter_begin(dev, &conn_iter);
 		drm_for_each_connector_iter(connector, &conn_iter) {
 			struct intel_connector *intel_connector = to_intel_connector(connector);
 
-			if (intel_connector->encoder->hpd_pin == i) {
+			if (intel_connector->encoder->hpd_pin == pin) {
 				if (connector->polled != intel_connector->polled)
 					DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n",
 							 connector->name);
@@ -301,13 +270,18 @@ bool intel_encoder_hotplug(struct intel_encoder *encoder,
 	return true;
 }
 
+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;
+}
+
 static void i915_digport_work_func(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private, hotplug.dig_port_work);
 	u32 long_port_mask, short_port_mask;
-	struct intel_digital_port *intel_dig_port;
-	int i;
+	struct intel_encoder *encoder;
 	u32 old_bits = 0;
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -317,27 +291,27 @@ static void i915_digport_work_func(struct work_struct *work)
 	dev_priv->hotplug.short_port_mask = 0;
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		bool valid = false;
-		bool long_hpd = false;
-		intel_dig_port = dev_priv->hotplug.irq_port[i];
-		if (!intel_dig_port || !intel_dig_port->hpd_pulse)
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_digital_port *dig_port;
+		enum port port = encoder->port;
+		bool long_hpd, short_hpd;
+		enum irqreturn ret;
+
+		if (!intel_encoder_has_hpd_pulse(encoder))
 			continue;
 
-		if (long_port_mask & (1 << i))  {
-			valid = true;
-			long_hpd = true;
-		} else if (short_port_mask & (1 << i))
-			valid = true;
+		long_hpd = long_port_mask & BIT(port);
+		short_hpd = short_port_mask & BIT(port);
 
-		if (valid) {
-			enum irqreturn ret;
+		if (!long_hpd && !short_hpd)
+			continue;
 
-			ret = intel_dig_port->hpd_pulse(intel_dig_port, long_hpd);
-			if (ret == IRQ_NONE) {
-				/* fall back to old school hpd */
-				old_bits |= (1 << intel_dig_port->base.hpd_pin);
-			}
+		dig_port = enc_to_dig_port(&encoder->base);
+
+		ret = dig_port->hpd_pulse(dig_port, long_hpd);
+		if (ret == IRQ_NONE) {
+			/* fall back to old school hpd */
+			old_bits |= BIT(encoder->hpd_pin);
 		}
 	}
 
@@ -418,26 +392,24 @@ static void i915_hotplug_work_func(struct work_struct *work)
 void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask)
 {
-	int i;
-	enum port port;
+	struct intel_encoder *encoder;
 	bool storm_detected = false;
 	bool queue_dig = false, queue_hp = false;
-	bool is_dig_port;
 
 	if (!pin_mask)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	for_each_hpd_pin(i) {
-		if (!(BIT(i) & pin_mask))
-			continue;
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		enum hpd_pin pin = encoder->hpd_pin;
+		bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder);
 
-		port = intel_hpd_pin_to_port(dev_priv, i);
-		is_dig_port = port != PORT_NONE &&
-			dev_priv->hotplug.irq_port[port];
+		if (!(BIT(pin) & pin_mask))
+			continue;
 
-		if (is_dig_port) {
-			bool long_hpd = long_mask & BIT(i);
+		if (has_hpd_pulse) {
+			bool long_hpd = long_mask & BIT(pin);
+			enum port port = encoder->port;
 
 			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
 					 long_hpd ? "long" : "short");
@@ -455,7 +427,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			}
 		}
 
-		if (dev_priv->hotplug.stats[i].state == HPD_DISABLED) {
+		if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) {
 			/*
 			 * On GMCH platforms the interrupt mask bits only
 			 * prevent irq generation, not the setting of the
@@ -463,20 +435,20 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			 * interrupts on saner platforms.
 			 */
 			WARN_ONCE(!HAS_GMCH_DISPLAY(dev_priv),
-				  "Received HPD interrupt on pin %d although disabled\n", i);
+				  "Received HPD interrupt on pin %d although disabled\n", pin);
 			continue;
 		}
 
-		if (dev_priv->hotplug.stats[i].state != HPD_ENABLED)
+		if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED)
 			continue;
 
-		if (!is_dig_port) {
-			dev_priv->hotplug.event_bits |= BIT(i);
+		if (!has_hpd_pulse) {
+			dev_priv->hotplug.event_bits |= BIT(pin);
 			queue_hp = true;
 		}
 
-		if (intel_hpd_irq_storm_detect(dev_priv, i)) {
-			dev_priv->hotplug.event_bits &= ~BIT(i);
+		if (intel_hpd_irq_storm_detect(dev_priv, pin)) {
+			dev_priv->hotplug.event_bits &= ~BIT(pin);
 			storm_detected = true;
 		}
 	}
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 291285277403..ffcad5fad6a7 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -32,6 +32,14 @@ void intel_huc_init_early(struct intel_huc *huc)
 	intel_huc_fw_init_early(huc);
 }
 
+int intel_huc_init_misc(struct intel_huc *huc)
+{
+	struct drm_i915_private *i915 = huc_to_i915(huc);
+
+	intel_uc_fw_fetch(i915, &huc->fw);
+	return 0;
+}
+
 /**
  * intel_huc_auth() - Authenticate HuC uCode
  * @huc: intel_huc structure
diff --git a/drivers/gpu/drm/i915/intel_huc.h b/drivers/gpu/drm/i915/intel_huc.h
index aa854907abac..7e41d870b509 100644
--- a/drivers/gpu/drm/i915/intel_huc.h
+++ b/drivers/gpu/drm/i915/intel_huc.h
@@ -36,9 +36,15 @@ struct intel_huc {
 };
 
 void intel_huc_init_early(struct intel_huc *huc);
+int intel_huc_init_misc(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc);
 int intel_huc_check_status(struct intel_huc *huc);
 
+static inline void intel_huc_fini_misc(struct intel_huc *huc)
+{
+	intel_uc_fw_fini(&huc->fw);
+}
+
 static inline int intel_huc_sanitize(struct intel_huc *huc)
 {
 	intel_uc_fw_sanitize(&huc->fw);
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 97606c1be70d..bef32b7c248e 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -361,15 +361,39 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+static inline
+unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv)
+{
+	return INTEL_GEN(dev_priv) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX :
+	       GMBUS_BYTE_COUNT_MAX;
+}
+
 static int
 gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 		      unsigned short addr, u8 *buf, unsigned int len,
-		      u32 gmbus1_index)
+		      u32 gmbus0_reg, u32 gmbus1_index)
 {
+	unsigned int size = len;
+	bool burst_read = len > gmbus_max_xfer_size(dev_priv);
+	bool extra_byte_added = false;
+
+	if (burst_read) {
+		/*
+		 * As per HW Spec, for 512Bytes need to read extra Byte and
+		 * Ignore the extra byte read.
+		 */
+		if (len == 512) {
+			extra_byte_added = true;
+			len++;
+		}
+		size = len % 256 + 256;
+		I915_WRITE_FW(GMBUS0, gmbus0_reg | GMBUS_BYTE_CNT_OVERRIDE);
+	}
+
 	I915_WRITE_FW(GMBUS1,
 		      gmbus1_index |
 		      GMBUS_CYCLE_WAIT |
-		      (len << GMBUS_BYTE_COUNT_SHIFT) |
+		      (size << GMBUS_BYTE_COUNT_SHIFT) |
 		      (addr << GMBUS_SLAVE_ADDR_SHIFT) |
 		      GMBUS_SLAVE_READ | GMBUS_SW_RDY);
 	while (len) {
@@ -382,17 +406,34 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 
 		val = I915_READ_FW(GMBUS3);
 		do {
+			if (extra_byte_added && len == 1)
+				break;
+
 			*buf++ = val & 0xff;
 			val >>= 8;
 		} while (--len && ++loop < 4);
+
+		if (burst_read && len == size - 4)
+			/* Reset the override bit */
+			I915_WRITE_FW(GMBUS0, gmbus0_reg);
 	}
 
 	return 0;
 }
 
+/*
+ * HW spec says that 512Bytes in Burst read need special treatment.
+ * But it doesn't talk about other multiple of 256Bytes. And couldn't locate
+ * an I2C slave, which supports such a lengthy burst read too for experiments.
+ *
+ * So until things get clarified on HW support, to avoid the burst read length
+ * in fold of 256Bytes except 512, max burst read length is fixed at 767Bytes.
+ */
+#define INTEL_GMBUS_BURST_READ_MAX_LEN		767U
+
 static int
 gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
-		u32 gmbus1_index)
+		u32 gmbus0_reg, u32 gmbus1_index)
 {
 	u8 *buf = msg->buf;
 	unsigned int rx_size = msg->len;
@@ -400,10 +441,13 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(rx_size, GMBUS_BYTE_COUNT_MAX);
+		if (HAS_GMBUS_BURST_READ(dev_priv))
+			len = min(rx_size, INTEL_GMBUS_BURST_READ_MAX_LEN);
+		else
+			len = min(rx_size, gmbus_max_xfer_size(dev_priv));
 
-		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr,
-					    buf, len, gmbus1_index);
+		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, buf, len,
+					    gmbus0_reg, gmbus1_index);
 		if (ret)
 			return ret;
 
@@ -462,7 +506,7 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(tx_size, GMBUS_BYTE_COUNT_MAX);
+		len = min(tx_size, gmbus_max_xfer_size(dev_priv));
 
 		ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len,
 					     gmbus1_index);
@@ -491,7 +535,8 @@ gmbus_is_index_xfer(struct i2c_msg *msgs, int i, int num)
 }
 
 static int
-gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
+gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs,
+		 u32 gmbus0_reg)
 {
 	u32 gmbus1_index = 0;
 	u32 gmbus5 = 0;
@@ -509,7 +554,8 @@ gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 		I915_WRITE_FW(GMBUS5, gmbus5);
 
 	if (msgs[1].flags & I2C_M_RD)
-		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index);
+		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus0_reg,
+				      gmbus1_index);
 	else
 		ret = gmbus_xfer_write(dev_priv, &msgs[1], gmbus1_index);
 
@@ -544,10 +590,12 @@ retry:
 	for (; i < num; i += inc) {
 		inc = 1;
 		if (gmbus_is_index_xfer(msgs, i, num)) {
-			ret = gmbus_index_xfer(dev_priv, &msgs[i]);
+			ret = gmbus_index_xfer(dev_priv, &msgs[i],
+					       gmbus0_source | bus->reg0);
 			inc = 2; /* an index transmission is two msgs */
 		} else if (msgs[i].flags & I2C_M_RD) {
-			ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
+			ret = gmbus_xfer_read(dev_priv, &msgs[i],
+					      gmbus0_source | bus->reg0, 0);
 		} else {
 			ret = gmbus_xfer_write(dev_priv, &msgs[i], 0);
 		}
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 33bc914c2ef5..174479232e94 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -137,6 +137,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_gem_render_state.h"
+#include "i915_vgpu.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 #include "intel_workarounds.h"
@@ -272,7 +273,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 find_priolist:
 	/* most positive priority is scheduled first, equal priorities fifo */
 	rb = NULL;
-	parent = &execlists->queue.rb_node;
+	parent = &execlists->queue.rb_root.rb_node;
 	while (*parent) {
 		rb = *parent;
 		p = to_priolist(rb);
@@ -310,10 +311,7 @@ find_priolist:
 	p->priority = prio;
 	INIT_LIST_HEAD(&p->requests);
 	rb_link_node(&p->node, rb, parent);
-	rb_insert_color(&p->node, &execlists->queue);
-
-	if (first)
-		execlists->first = &p->node;
+	rb_insert_color_cached(&p->node, &execlists->queue, first);
 
 	return p;
 }
@@ -455,6 +453,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 	unsigned int n;
 
 	/*
+	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
+	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
+	 * not be relinquished until the device is idle (see
+	 * i915_gem_idle_work_handler()). As a precaution, we make sure
+	 * that all ELSP are drained i.e. we have processed the CSB,
+	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
+	 */
+	GEM_BUG_ON(!engine->i915->gt.awake);
+
+	/*
 	 * ELSQ note: the submit queue is not cleared after being submitted
 	 * to the HW so we need to make sure we always clean it up. This is
 	 * currently ensured by the fact that we always write the same number
@@ -561,13 +569,16 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists)
 {
 	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
 
-	execlists_cancel_port_requests(execlists);
-	execlists_unwind_incomplete_requests(execlists);
+	if (inject_preempt_hang(execlists))
+		return;
 
-	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
+	execlists_cancel_port_requests(execlists);
+	__unwind_incomplete_requests(container_of(execlists,
+						  struct intel_engine_cs,
+						  execlists));
 }
 
-static bool __execlists_dequeue(struct intel_engine_cs *engine)
+static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -577,9 +588,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 	struct rb_node *rb;
 	bool submit = false;
 
-	lockdep_assert_held(&engine->timeline.lock);
-
-	/* Hardware submission is through 2 ports. Conceptually each port
+	/*
+	 * Hardware submission is through 2 ports. Conceptually each port
 	 * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is
 	 * static for a context, and unique to each, so we only execute
 	 * requests belonging to a single context from each ring. RING_HEAD
@@ -600,9 +610,6 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (last) {
 		/*
 		 * Don't resubmit or switch until all outstanding
@@ -622,11 +629,11 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * the HW to indicate that it has had a chance to respond.
 		 */
 		if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_HWACK))
-			return false;
+			return;
 
 		if (need_preempt(engine, last, execlists->queue_priority)) {
 			inject_preempt_context(engine);
-			return false;
+			return;
 		}
 
 		/*
@@ -651,7 +658,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * priorities of the ports haven't been switch.
 		 */
 		if (port_count(&port[1]))
-			return false;
+			return;
 
 		/*
 		 * WaIdleLiteRestore:bdw,skl
@@ -664,7 +671,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		last->tail = last->wa_tail;
 	}
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -723,8 +730,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -750,35 +756,23 @@ done:
 	execlists->queue_priority =
 		port != execlists->port ? rq_prio(last) : INT_MIN;
 
-	execlists->first = rb;
-	if (submit)
+	if (submit) {
 		port_assign(port, last);
+		execlists_submit_ports(engine);
+	}
 
 	/* We must always keep the beast fed if we have work piled up */
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	/* Re-evaluate the executing context setup after each preemptive kick */
 	if (last)
 		execlists_user_begin(execlists, execlists->port);
 
-	return submit;
-}
-
-static void execlists_dequeue(struct intel_engine_cs *engine)
-{
-	struct intel_engine_execlists * const execlists = &engine->execlists;
-	unsigned long flags;
-	bool submit;
-
-	spin_lock_irqsave(&engine->timeline.lock, flags);
-	submit = __execlists_dequeue(engine);
-	spin_unlock_irqrestore(&engine->timeline.lock, flags);
-
-	if (submit)
-		execlists_submit_ports(engine);
-
-	GEM_BUG_ON(port_isset(execlists->port) &&
-		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
+	/* If the engine is now idle, so should be the flag; and vice versa. */
+	GEM_BUG_ON(execlists_is_active(&engine->execlists,
+				       EXECLISTS_ACTIVE_USER) ==
+		   !port_isset(engine->execlists.port));
 }
 
 void
@@ -809,82 +803,27 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
 		port++;
 	}
 
-	execlists_user_end(execlists);
+	execlists_clear_all_active(execlists);
 }
 
-static void clear_gtiir(struct intel_engine_cs *engine)
+static void reset_csb_pointers(struct intel_engine_execlists *execlists)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-	int i;
-
 	/*
-	 * Clear any pending interrupt state.
-	 *
-	 * We do it twice out of paranoia that some of the IIR are
-	 * double buffered, and so if we only reset it once there may
-	 * still be an interrupt pending.
+	 * After a reset, the HW starts writing into CSB entry [0]. We
+	 * therefore have to set our HEAD pointer back one entry so that
+	 * the *first* entry we check is entry 0. To complicate this further,
+	 * as we don't wait for the first interrupt after reset, we have to
+	 * fake the HW write to point back to the last entry so that our
+	 * inline comparison of our cached head position against the last HW
+	 * write works even before the first interrupt.
 	 */
-	if (INTEL_GEN(dev_priv) >= 11) {
-		static const struct {
-			u8 bank;
-			u8 bit;
-		} gen11_gtiir[] = {
-			[RCS] = {0, GEN11_RCS0},
-			[BCS] = {0, GEN11_BCS},
-			[_VCS(0)] = {1, GEN11_VCS(0)},
-			[_VCS(1)] = {1, GEN11_VCS(1)},
-			[_VCS(2)] = {1, GEN11_VCS(2)},
-			[_VCS(3)] = {1, GEN11_VCS(3)},
-			[_VECS(0)] = {1, GEN11_VECS(0)},
-			[_VECS(1)] = {1, GEN11_VECS(1)},
-		};
-		unsigned long irqflags;
-
-		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gen11_gtiir));
-
-		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-		for (i = 0; i < 2; i++) {
-			gen11_reset_one_iir(dev_priv,
-					    gen11_gtiir[engine->id].bank,
-					    gen11_gtiir[engine->id].bit);
-		}
-		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-	} else {
-		static const u8 gtiir[] = {
-			[RCS]  = 0,
-			[BCS]  = 0,
-			[VCS]  = 1,
-			[VCS2] = 1,
-			[VECS] = 3,
-		};
-
-		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
-
-		for (i = 0; i < 2; i++) {
-			I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
-				   engine->irq_keep_mask);
-			POSTING_READ(GEN8_GT_IIR(gtiir[engine->id]));
-		}
-		GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) &
-			   engine->irq_keep_mask);
-	}
+	execlists->csb_head = execlists->csb_write_reset;
+	WRITE_ONCE(*execlists->csb_write, execlists->csb_write_reset);
 }
 
-static void reset_irq(struct intel_engine_cs *engine)
+static void nop_submission_tasklet(unsigned long data)
 {
-	/* Mark all CS interrupts as complete */
-	smp_store_mb(engine->execlists.active, 0);
-	synchronize_hardirq(engine->i915->drm.irq);
-
-	clear_gtiir(engine);
-
-	/*
-	 * The port is checked prior to scheduling a tasklet, but
-	 * just in case we have suspended the tasklet to do the
-	 * wedging make sure that when it wakes, it decides there
-	 * is no work to do by clearing the irq_posted bit.
-	 */
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+	/* The driver is wedged; don't process any more events. */
 }
 
 static void execlists_cancel_requests(struct intel_engine_cs *engine)
@@ -911,13 +850,11 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	 * submission's irq state, we also wish to remind ourselves that
 	 * it is irq state.)
 	 */
-	local_irq_save(flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/* Cancel the requests on the HW and clear the ELSP tracker. */
 	execlists_cancel_port_requests(execlists);
-	reset_irq(engine);
-
-	spin_lock(&engine->timeline.lock);
+	execlists_user_end(execlists);
 
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->timeline.requests, link) {
@@ -927,8 +864,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	}
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	rb = execlists->first;
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
@@ -938,8 +874,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 			__i915_request_submit(rq);
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -948,183 +883,179 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 	GEM_BUG_ON(port_isset(execlists->port));
 
-	spin_unlock(&engine->timeline.lock);
+	GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
+	execlists->tasklet.func = nop_submission_tasklet;
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+}
+
+static inline bool
+reset_in_progress(const struct intel_engine_execlists *execlists)
+{
+	return unlikely(!__tasklet_is_enabled(&execlists->tasklet));
 }
 
 static void process_csb(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
-	struct drm_i915_private *i915 = engine->i915;
-	bool fw = false;
+	const u32 * const buf = execlists->csb_status;
+	u8 head, tail;
+
+	/*
+	 * Note that csb_write, csb_status may be either in HWSP or mmio.
+	 * When reading from the csb_write mmio register, we have to be
+	 * careful to only use the GEN8_CSB_WRITE_PTR portion, which is
+	 * the low 4bits. As it happens we know the next 4bits are always
+	 * zero and so we can simply masked off the low u8 of the register
+	 * and treat it identically to reading from the HWSP (without having
+	 * to use explicit shifting and masking, and probably bifurcating
+	 * the code to handle the legacy mmio read).
+	 */
+	head = execlists->csb_head;
+	tail = READ_ONCE(*execlists->csb_write);
+	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	if (unlikely(head == tail))
+		return;
+
+	/*
+	 * Hopefully paired with a wmb() in HW!
+	 *
+	 * We must complete the read of the write pointer before any reads
+	 * from the CSB, so that we do not see stale values. Without an rmb
+	 * (lfence) the HW may speculatively perform the CSB[] reads *before*
+	 * we perform the READ_ONCE(*csb_write).
+	 */
+	rmb();
 
 	do {
-		/* The HWSP contains a (cacheable) mirror of the CSB */
-		const u32 *buf =
-			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
-		unsigned int head, tail;
+		struct i915_request *rq;
+		unsigned int status;
+		unsigned int count;
 
-		/* Clear before reading to catch new interrupts */
-		clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-		smp_mb__after_atomic();
+		if (++head == GEN8_CSB_ENTRIES)
+			head = 0;
 
-		if (unlikely(execlists->csb_use_mmio)) {
-			if (!fw) {
-				intel_uncore_forcewake_get(i915, execlists->fw_domains);
-				fw = true;
-			}
+		/*
+		 * We are flying near dragons again.
+		 *
+		 * We hold a reference to the request in execlist_port[]
+		 * but no more than that. We are operating in softirq
+		 * context and so cannot hold any mutex or sleep. That
+		 * prevents us stopping the requests we are processing
+		 * in port[] from being retired simultaneously (the
+		 * breadcrumb will be complete before we see the
+		 * context-switch). As we only hold the reference to the
+		 * request, any pointer chasing underneath the request
+		 * is subject to a potential use-after-free. Thus we
+		 * store all of the bookkeeping within port[] as
+		 * required, and avoid using unguarded pointers beneath
+		 * request itself. The same applies to the atomic
+		 * status notifier.
+		 */
 
-			buf = (u32 * __force)
-				(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
+			  engine->name, head,
+			  buf[2 * head + 0], buf[2 * head + 1],
+			  execlists->active);
+
+		status = buf[2 * head];
+		if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
+			      GEN8_CTX_STATUS_PREEMPTED))
+			execlists_set_active(execlists,
+					     EXECLISTS_ACTIVE_HWACK);
+		if (status & GEN8_CTX_STATUS_ACTIVE_IDLE)
+			execlists_clear_active(execlists,
+					       EXECLISTS_ACTIVE_HWACK);
+
+		if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
+			continue;
 
-			head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-			tail = GEN8_CSB_WRITE_PTR(head);
-			head = GEN8_CSB_READ_PTR(head);
-			execlists->csb_head = head;
-		} else {
-			const int write_idx =
-				intel_hws_csb_write_index(i915) -
-				I915_HWS_CSB_BUF0_INDEX;
+		/* We should never get a COMPLETED | IDLE_ACTIVE! */
+		GEM_BUG_ON(status & GEN8_CTX_STATUS_IDLE_ACTIVE);
 
-			head = execlists->csb_head;
-			tail = READ_ONCE(buf[write_idx]);
-			rmb(); /* Hopefully paired with a wmb() in HW */
+		if (status & GEN8_CTX_STATUS_COMPLETE &&
+		    buf[2*head + 1] == execlists->preempt_complete_status) {
+			GEM_TRACE("%s preempt-idle\n", engine->name);
+			complete_preempt_context(execlists);
+			continue;
 		}
-		GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
-			  engine->name,
-			  head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
-			  tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
 
-		while (head != tail) {
-			struct i915_request *rq;
-			unsigned int status;
-			unsigned int count;
+		if (status & GEN8_CTX_STATUS_PREEMPTED &&
+		    execlists_is_active(execlists,
+					EXECLISTS_ACTIVE_PREEMPT))
+			continue;
 
-			if (++head == GEN8_CSB_ENTRIES)
-				head = 0;
+		GEM_BUG_ON(!execlists_is_active(execlists,
+						EXECLISTS_ACTIVE_USER));
 
+		rq = port_unpack(port, &count);
+		GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
+			  engine->name,
+			  port->context_id, count,
+			  rq ? rq->global_seqno : 0,
+			  rq ? rq->fence.context : 0,
+			  rq ? rq->fence.seqno : 0,
+			  intel_engine_get_seqno(engine),
+			  rq ? rq_prio(rq) : 0);
+
+		/* Check the context/desc id for this event matches */
+		GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
+
+		GEM_BUG_ON(count == 0);
+		if (--count == 0) {
 			/*
-			 * We are flying near dragons again.
-			 *
-			 * We hold a reference to the request in execlist_port[]
-			 * but no more than that. We are operating in softirq
-			 * context and so cannot hold any mutex or sleep. That
-			 * prevents us stopping the requests we are processing
-			 * in port[] from being retired simultaneously (the
-			 * breadcrumb will be complete before we see the
-			 * context-switch). As we only hold the reference to the
-			 * request, any pointer chasing underneath the request
-			 * is subject to a potential use-after-free. Thus we
-			 * store all of the bookkeeping within port[] as
-			 * required, and avoid using unguarded pointers beneath
-			 * request itself. The same applies to the atomic
-			 * status notifier.
+			 * On the final event corresponding to the
+			 * submission of this context, we expect either
+			 * an element-switch event or a completion
+			 * event (and on completion, the active-idle
+			 * marker). No more preemptions, lite-restore
+			 * or otherwise.
 			 */
+			GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
+			GEM_BUG_ON(port_isset(&port[1]) &&
+				   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
+			GEM_BUG_ON(!port_isset(&port[1]) &&
+				   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
 
-			status = READ_ONCE(buf[2 * head]); /* maybe mmio! */
-			GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
-				  engine->name, head,
-				  status, buf[2*head + 1],
-				  execlists->active);
-
-			if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
-				      GEN8_CTX_STATUS_PREEMPTED))
-				execlists_set_active(execlists,
-						     EXECLISTS_ACTIVE_HWACK);
-			if (status & GEN8_CTX_STATUS_ACTIVE_IDLE)
-				execlists_clear_active(execlists,
-						       EXECLISTS_ACTIVE_HWACK);
-
-			if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
-				continue;
-
-			/* We should never get a COMPLETED | IDLE_ACTIVE! */
-			GEM_BUG_ON(status & GEN8_CTX_STATUS_IDLE_ACTIVE);
-
-			if (status & GEN8_CTX_STATUS_COMPLETE &&
-			    buf[2*head + 1] == execlists->preempt_complete_status) {
-				GEM_TRACE("%s preempt-idle\n", engine->name);
-				complete_preempt_context(execlists);
-				continue;
-			}
-
-			if (status & GEN8_CTX_STATUS_PREEMPTED &&
-			    execlists_is_active(execlists,
-						EXECLISTS_ACTIVE_PREEMPT))
-				continue;
-
-			GEM_BUG_ON(!execlists_is_active(execlists,
-							EXECLISTS_ACTIVE_USER));
-
-			rq = port_unpack(port, &count);
-			GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
-				  engine->name,
-				  port->context_id, count,
-				  rq ? rq->global_seqno : 0,
-				  rq ? rq->fence.context : 0,
-				  rq ? rq->fence.seqno : 0,
-				  intel_engine_get_seqno(engine),
-				  rq ? rq_prio(rq) : 0);
+			/*
+			 * We rely on the hardware being strongly
+			 * ordered, that the breadcrumb write is
+			 * coherent (visible from the CPU) before the
+			 * user interrupt and CSB is processed.
+			 */
+			GEM_BUG_ON(!i915_request_completed(rq));
 
-			/* Check the context/desc id for this event matches */
-			GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
+			execlists_context_schedule_out(rq,
+						       INTEL_CONTEXT_SCHEDULE_OUT);
+			i915_request_put(rq);
 
-			GEM_BUG_ON(count == 0);
-			if (--count == 0) {
-				/*
-				 * On the final event corresponding to the
-				 * submission of this context, we expect either
-				 * an element-switch event or a completion
-				 * event (and on completion, the active-idle
-				 * marker). No more preemptions, lite-restore
-				 * or otherwise.
-				 */
-				GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
-				GEM_BUG_ON(port_isset(&port[1]) &&
-					   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
-				GEM_BUG_ON(!port_isset(&port[1]) &&
-					   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
+			GEM_TRACE("%s completed ctx=%d\n",
+				  engine->name, port->context_id);
 
-				/*
-				 * We rely on the hardware being strongly
-				 * ordered, that the breadcrumb write is
-				 * coherent (visible from the CPU) before the
-				 * user interrupt and CSB is processed.
-				 */
-				GEM_BUG_ON(!i915_request_completed(rq));
-
-				execlists_context_schedule_out(rq,
-							       INTEL_CONTEXT_SCHEDULE_OUT);
-				i915_request_put(rq);
-
-				GEM_TRACE("%s completed ctx=%d\n",
-					  engine->name, port->context_id);
-
-				port = execlists_port_complete(execlists, port);
-				if (port_isset(port))
-					execlists_user_begin(execlists, port);
-				else
-					execlists_user_end(execlists);
-			} else {
-				port_set(port, port_pack(rq, count));
-			}
+			port = execlists_port_complete(execlists, port);
+			if (port_isset(port))
+				execlists_user_begin(execlists, port);
+			else
+				execlists_user_end(execlists);
+		} else {
+			port_set(port, port_pack(rq, count));
 		}
+	} while (head != tail);
 
-		if (head != execlists->csb_head) {
-			execlists->csb_head = head;
-			writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-			       i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-		}
-	} while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted));
+	execlists->csb_head = head;
+}
 
-	if (unlikely(fw))
-		intel_uncore_forcewake_put(i915, execlists->fw_domains);
+static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
+{
+	lockdep_assert_held(&engine->timeline.lock);
+
+	process_csb(engine);
+	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
+		execlists_dequeue(engine);
 }
 
 /*
@@ -1134,38 +1065,16 @@ static void process_csb(struct intel_engine_cs *engine)
 static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+	unsigned long flags;
 
-	GEM_TRACE("%s awake?=%d, active=%x, irq-posted?=%d\n",
+	GEM_TRACE("%s awake?=%d, active=%x\n",
 		  engine->name,
 		  engine->i915->gt.awake,
-		  engine->execlists.active,
-		  test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted));
-
-	/*
-	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
-	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
-	 * not be relinquished until the device is idle (see
-	 * i915_gem_idle_work_handler()). As a precaution, we make sure
-	 * that all ELSP are drained i.e. we have processed the CSB,
-	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
-	 */
-	GEM_BUG_ON(!engine->i915->gt.awake);
-
-	/*
-	 * Prefer doing test_and_clear_bit() as a two stage operation to avoid
-	 * imposing the cost of a locked atomic transaction when submitting a
-	 * new request (outside of the context-switch interrupt).
-	 */
-	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
-		process_csb(engine);
+		  engine->execlists.active);
 
-	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
-		execlists_dequeue(engine);
-
-	/* If the engine is now idle, so should be the flag; and vice versa. */
-	GEM_BUG_ON(execlists_is_active(&engine->execlists,
-				       EXECLISTS_ACTIVE_USER) ==
-		   !port_isset(engine->execlists.port));
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	__execlists_submission_tasklet(engine);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 static void queue_request(struct intel_engine_cs *engine,
@@ -1176,16 +1085,30 @@ static void queue_request(struct intel_engine_cs *engine,
 		      &lookup_priolist(engine, prio)->requests);
 }
 
-static void __submit_queue(struct intel_engine_cs *engine, int prio)
+static void __update_queue(struct intel_engine_cs *engine, int prio)
 {
 	engine->execlists.queue_priority = prio;
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+}
+
+static void __submit_queue_imm(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	if (reset_in_progress(execlists))
+		return; /* defer until we restart the engine following reset */
+
+	if (execlists->tasklet.func == execlists_submission_tasklet)
+		__execlists_submission_tasklet(engine);
+	else
+		tasklet_hi_schedule(&execlists->tasklet);
 }
 
 static void submit_queue(struct intel_engine_cs *engine, int prio)
 {
-	if (prio > engine->execlists.queue_priority)
-		__submit_queue(engine, prio);
+	if (prio > engine->execlists.queue_priority) {
+		__update_queue(engine, prio);
+		__submit_queue_imm(engine);
+	}
 }
 
 static void execlists_submit_request(struct i915_request *request)
@@ -1197,11 +1120,12 @@ static void execlists_submit_request(struct i915_request *request)
 	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	queue_request(engine, &request->sched, rq_prio(request));
-	submit_queue(engine, rq_prio(request));
 
-	GEM_BUG_ON(!engine->execlists.first);
+	GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 	GEM_BUG_ON(list_empty(&request->sched.link));
 
+	submit_queue(engine, rq_prio(request));
+
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
@@ -1328,8 +1252,11 @@ static void execlists_schedule(struct i915_request *request,
 		}
 
 		if (prio > engine->execlists.queue_priority &&
-		    i915_sw_fence_done(&sched_to_request(node)->submit))
-			__submit_queue(engine, prio);
+		    i915_sw_fence_done(&sched_to_request(node)->submit)) {
+			/* defer submission until after all of our updates */
+			__update_queue(engine, prio);
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+		}
 	}
 
 	spin_unlock_irq(&engine->timeline.lock);
@@ -1337,11 +1264,15 @@ static void execlists_schedule(struct i915_request *request,
 
 static void execlists_context_destroy(struct intel_context *ce)
 {
-	GEM_BUG_ON(!ce->state);
 	GEM_BUG_ON(ce->pin_count);
 
+	if (!ce->state)
+		return;
+
 	intel_ring_free(ce->ring);
-	__i915_gem_object_release_unless_active(ce->state->obj);
+
+	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
+	i915_gem_object_put(ce->state->obj);
 }
 
 static void execlists_context_unpin(struct intel_context *ce)
@@ -1851,7 +1782,6 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 		return ret;
 
 	intel_engine_reset_breadcrumbs(engine);
-	intel_engine_init_hangcheck(engine);
 
 	if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) {
 		struct drm_printer p = drm_debug_printer(__func__);
@@ -1906,6 +1836,7 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *request, *active;
+	unsigned long flags;
 
 	GEM_TRACE("%s\n", engine->name);
 
@@ -1920,6 +1851,8 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	 */
 	__tasklet_disable_sync_once(&execlists->tasklet);
 
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+
 	/*
 	 * We want to flush the pending context switches, having disabled
 	 * the tasklet above, we can assume exclusive access to the execlists.
@@ -1927,8 +1860,7 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	 * and avoid blaming an innocent request if the stall was due to the
 	 * preemption itself.
 	 */
-	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
-		process_csb(engine);
+	process_csb(engine);
 
 	/*
 	 * The last active request can then be no later than the last request
@@ -1938,15 +1870,12 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	active = NULL;
 	request = port_request(execlists->port);
 	if (request) {
-		unsigned long flags;
-
 		/*
 		 * Prevent the breadcrumb from advancing before we decide
 		 * which request is currently active.
 		 */
 		intel_engine_stop_cs(engine);
 
-		spin_lock_irqsave(&engine->timeline.lock, flags);
 		list_for_each_entry_from_reverse(request,
 						 &engine->timeline.requests,
 						 link) {
@@ -1956,9 +1885,10 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 
 			active = request;
 		}
-		spin_unlock_irqrestore(&engine->timeline.lock, flags);
 	}
 
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+
 	return active;
 }
 
@@ -1973,8 +1903,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 		  engine->name, request ? request->global_seqno : 0,
 		  intel_engine_get_seqno(engine));
 
-	/* See execlists_cancel_requests() for the irq/spinlock split. */
-	local_irq_save(flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/*
 	 * Catch up with any missed context-switch interrupts.
@@ -1986,17 +1915,14 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	 * requests were completed.
 	 */
 	execlists_cancel_port_requests(execlists);
-	reset_irq(engine);
 
 	/* Push back any incomplete requests for replay after the reset. */
-	spin_lock(&engine->timeline.lock);
 	__unwind_incomplete_requests(engine);
-	spin_unlock(&engine->timeline.lock);
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
-	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
+	reset_csb_pointers(&engine->execlists);
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	/*
 	 * If the request was innocent, we leave the request in the ELSP
@@ -2046,7 +1972,7 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
 	/* After a GPU reset, we may have requests to replay */
-	if (execlists->first)
+	if (!RB_EMPTY_ROOT(&execlists->queue.rb_root))
 		tasklet_schedule(&execlists->tasklet);
 
 	/*
@@ -2366,7 +2292,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	kfree(engine);
 }
 
-static void execlists_set_default_submission(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;
@@ -2406,7 +2332,7 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->emit_breadcrumb = gen8_emit_breadcrumb;
 	engine->emit_breadcrumb_sz = gen8_emit_breadcrumb_sz;
 
-	engine->set_default_submission = execlists_set_default_submission;
+	engine->set_default_submission = intel_execlists_set_default_submission;
 
 	if (INTEL_GEN(engine->i915) < 11) {
 		engine->irq_enable = gen8_logical_ring_enable_irq;
@@ -2446,28 +2372,11 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 static void
 logical_ring_setup(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-	enum forcewake_domains fw_domains;
-
 	intel_engine_setup_common(engine);
 
 	/* Intentionally left blank. */
 	engine->buffer = NULL;
 
-	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
-						    RING_ELSP(engine),
-						    FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_PTR(engine),
-						     FW_REG_READ | FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_BUF_BASE(engine),
-						     FW_REG_READ);
-
-	engine->execlists.fw_domains = fw_domains;
-
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 
@@ -2475,34 +2384,60 @@ logical_ring_setup(struct intel_engine_cs *engine)
 	logical_ring_default_irqs(engine);
 }
 
+static bool csb_force_mmio(struct drm_i915_private *i915)
+{
+	/* Older GVT emulation depends upon intercepting CSB mmio */
+	return intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915);
+}
+
 static int logical_ring_init(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	int ret;
 
 	ret = intel_engine_init_common(engine);
 	if (ret)
 		goto error;
 
-	if (HAS_LOGICAL_RING_ELSQ(engine->i915)) {
-		engine->execlists.submit_reg = engine->i915->regs +
+	if (HAS_LOGICAL_RING_ELSQ(i915)) {
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_SQ_CONTENTS(engine));
-		engine->execlists.ctrl_reg = engine->i915->regs +
+		execlists->ctrl_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_CONTROL(engine));
 	} else {
-		engine->execlists.submit_reg = engine->i915->regs +
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_ELSP(engine));
 	}
 
-	engine->execlists.preempt_complete_status = ~0u;
-	if (engine->i915->preempt_context) {
+	execlists->preempt_complete_status = ~0u;
+	if (i915->preempt_context) {
 		struct intel_context *ce =
-			to_intel_context(engine->i915->preempt_context, engine);
+			to_intel_context(i915->preempt_context, engine);
 
-		engine->execlists.preempt_complete_status =
+		execlists->preempt_complete_status =
 			upper_32_bits(ce->lrc_desc);
 	}
 
-	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
+	execlists->csb_read =
+		i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
+	if (csb_force_mmio(i915)) {
+		execlists->csb_status = (u32 __force *)
+			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+
+		execlists->csb_write = (u32 __force *)execlists->csb_read;
+		execlists->csb_write_reset =
+			_MASKED_FIELD(GEN8_CSB_WRITE_PTR_MASK,
+				      GEN8_CSB_ENTRIES - 1);
+	} else {
+		execlists->csb_status =
+			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+
+		execlists->csb_write =
+			&engine->status_page.page_addr[intel_hws_csb_write_index(i915)];
+		execlists->csb_write_reset = GEN8_CSB_ENTRIES - 1;
+	}
+	reset_csb_pointers(execlists);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 1593194e930c..4dfb78e3ec7e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -104,4 +104,6 @@ struct i915_gem_context;
 
 void intel_lr_context_resume(struct drm_i915_private *dev_priv);
 
+void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
+
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bb06744d28a4..f9f3b0885ba5 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -44,8 +44,6 @@
 /* Private structure for the integrated LVDS support */
 struct intel_lvds_connector {
 	struct intel_connector base;
-
-	struct notifier_block lid_notifier;
 };
 
 struct intel_lvds_pps {
@@ -452,26 +450,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	return true;
 }
 
-/*
- * Detect the LVDS connection.
- *
- * Since LVDS doesn't have hotlug, we use the lid as a proxy.  Open means
- * connected and closed means disconnected.  We also send hotplug events as
- * needed, using lid status notification from the input layer.
- */
 static enum drm_connector_status
 intel_lvds_detect(struct drm_connector *connector, bool force)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	enum drm_connector_status status;
-
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, connector->name);
-
-	status = intel_panel_detect(dev_priv);
-	if (status != connector_status_unknown)
-		return status;
-
 	return connector_status_connected;
 }
 
@@ -496,117 +477,6 @@ static int intel_lvds_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int intel_no_modeset_on_lid_dmi_callback(const struct dmi_system_id *id)
-{
-	DRM_INFO("Skipping forced modeset for %s\n", id->ident);
-	return 1;
-}
-
-/* The GPU hangs up on these systems if modeset is performed on LID open */
-static const struct dmi_system_id intel_no_modeset_on_lid[] = {
-	{
-		.callback = intel_no_modeset_on_lid_dmi_callback,
-		.ident = "Toshiba Tecra A11",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TECRA A11"),
-		},
-	},
-
-	{ }	/* terminating entry */
-};
-
-/*
- * Lid events. Note the use of 'modeset':
- *  - we set it to MODESET_ON_LID_OPEN on lid close,
- *    and set it to MODESET_DONE on open
- *  - we use it as a "only once" bit (ie we ignore
- *    duplicate events where it was already properly set)
- *  - the suspend/resume paths will set it to
- *    MODESET_SUSPENDED and ignore the lid open event,
- *    because they restore the mode ("lid open").
- */
-static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
-			    void *unused)
-{
-	struct intel_lvds_connector *lvds_connector =
-		container_of(nb, struct intel_lvds_connector, lid_notifier);
-	struct drm_connector *connector = &lvds_connector->base.base;
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	if (dev->switch_power_state != DRM_SWITCH_POWER_ON)
-		return NOTIFY_OK;
-
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	if (dev_priv->modeset_restore == MODESET_SUSPENDED)
-		goto exit;
-	/*
-	 * check and update the status of LVDS connector after receiving
-	 * the LID nofication event.
-	 */
-	connector->status = connector->funcs->detect(connector, false);
-
-	/* Don't force modeset on machines where it causes a GPU lockup */
-	if (dmi_check_system(intel_no_modeset_on_lid))
-		goto exit;
-	if (!acpi_lid_open()) {
-		/* do modeset on next lid open event */
-		dev_priv->modeset_restore = MODESET_ON_LID_OPEN;
-		goto exit;
-	}
-
-	if (dev_priv->modeset_restore == MODESET_DONE)
-		goto exit;
-
-	/*
-	 * Some old platform's BIOS love to wreak havoc while the lid is closed.
-	 * We try to detect this here and undo any damage. The split for PCH
-	 * platforms is rather conservative and a bit arbitrary expect that on
-	 * those platforms VGA disabling requires actual legacy VGA I/O access,
-	 * and as part of the cleanup in the hw state restore we also redisable
-	 * the vga plane.
-	 */
-	if (!HAS_PCH_SPLIT(dev_priv))
-		intel_display_resume(dev);
-
-	dev_priv->modeset_restore = MODESET_DONE;
-
-exit:
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-	return NOTIFY_OK;
-}
-
-static int
-intel_lvds_connector_register(struct drm_connector *connector)
-{
-	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
-	int ret;
-
-	ret = intel_connector_register(connector);
-	if (ret)
-		return ret;
-
-	lvds->lid_notifier.notifier_call = intel_lid_notify;
-	if (acpi_lid_notifier_register(&lvds->lid_notifier)) {
-		DRM_DEBUG_KMS("lid notifier registration failed\n");
-		lvds->lid_notifier.notifier_call = NULL;
-	}
-
-	return 0;
-}
-
-static void
-intel_lvds_connector_unregister(struct drm_connector *connector)
-{
-	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
-
-	if (lvds->lid_notifier.notifier_call)
-		acpi_lid_notifier_unregister(&lvds->lid_notifier);
-
-	intel_connector_unregister(connector);
-}
-
 /**
  * intel_lvds_destroy - unregister and free LVDS structures
  * @connector: connector to free
@@ -639,8 +509,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_digital_connector_atomic_get_property,
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
-	.late_register = intel_lvds_connector_register,
-	.early_unregister = intel_lvds_connector_unregister,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
@@ -1114,8 +984,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	 * 2) check for VBT data
 	 * 3) check to see if LVDS is already on
 	 *    if none of the above, no panel
-	 * 4) make sure lid is open
-	 *    if closed, act like it's not there for now
 	 */
 
 	/*
@@ -1131,7 +999,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 				    intel_gmbus_get_adapter(dev_priv, pin));
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 		} else {
 			kfree(edid);
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index b39846613e3c..ca44bf368e24 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -40,7 +40,7 @@ int intel_connector_update_modes(struct drm_connector *connector,
 {
 	int ret;
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 14b827ec5427..4a9f139e7b73 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -375,26 +375,6 @@ out:
 	pipe_config->gmch_pfit.lvds_border_bits = border;
 }
 
-enum drm_connector_status
-intel_panel_detect(struct drm_i915_private *dev_priv)
-{
-	/* Assume that the BIOS does not lie through the OpRegion... */
-	if (!i915_modparams.panel_ignore_lid && dev_priv->opregion.lid_state) {
-		return *dev_priv->opregion.lid_state & 0x1 ?
-			connector_status_connected :
-			connector_status_disconnected;
-	}
-
-	switch (i915_modparams.panel_ignore_lid) {
-	case -2:
-		return connector_status_connected;
-	case -1:
-		return connector_status_disconnected;
-	default:
-		return connector_status_unknown;
-	}
-}
-
 /**
  * scale - scale values from one range to another
  * @source_val: value in range [@source_min..@source_max]
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index 39a4e4edda07..849e1b69ba73 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -30,160 +30,6 @@
 #include <linux/debugfs.h>
 #include "intel_drv.h"
 
-struct pipe_crc_info {
-	const char *name;
-	struct drm_i915_private *dev_priv;
-	enum pipe pipe;
-};
-
-static int i915_pipe_crc_open(struct inode *inode, struct file *filep)
-{
-	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-
-	if (info->pipe >= INTEL_INFO(dev_priv)->num_pipes)
-		return -ENODEV;
-
-	spin_lock_irq(&pipe_crc->lock);
-
-	if (pipe_crc->opened) {
-		spin_unlock_irq(&pipe_crc->lock);
-		return -EBUSY; /* already open */
-	}
-
-	pipe_crc->opened = true;
-	filep->private_data = inode->i_private;
-
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return 0;
-}
-
-static int i915_pipe_crc_release(struct inode *inode, struct file *filep)
-{
-	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-
-	spin_lock_irq(&pipe_crc->lock);
-	pipe_crc->opened = false;
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return 0;
-}
-
-/* (6 fields, 8 chars each, space separated (5) + '\n') */
-#define PIPE_CRC_LINE_LEN	(6 * 8 + 5 + 1)
-/* account for \'0' */
-#define PIPE_CRC_BUFFER_LEN	(PIPE_CRC_LINE_LEN + 1)
-
-static int pipe_crc_data_count(struct intel_pipe_crc *pipe_crc)
-{
-	lockdep_assert_held(&pipe_crc->lock);
-	return CIRC_CNT(pipe_crc->head, pipe_crc->tail,
-			INTEL_PIPE_CRC_ENTRIES_NR);
-}
-
-static ssize_t
-i915_pipe_crc_read(struct file *filep, char __user *user_buf, size_t count,
-		   loff_t *pos)
-{
-	struct pipe_crc_info *info = filep->private_data;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-	char buf[PIPE_CRC_BUFFER_LEN];
-	int n_entries;
-	ssize_t bytes_read;
-
-	/*
-	 * Don't allow user space to provide buffers not big enough to hold
-	 * a line of data.
-	 */
-	if (count < PIPE_CRC_LINE_LEN)
-		return -EINVAL;
-
-	if (pipe_crc->source == INTEL_PIPE_CRC_SOURCE_NONE)
-		return 0;
-
-	/* nothing to read */
-	spin_lock_irq(&pipe_crc->lock);
-	while (pipe_crc_data_count(pipe_crc) == 0) {
-		int ret;
-
-		if (filep->f_flags & O_NONBLOCK) {
-			spin_unlock_irq(&pipe_crc->lock);
-			return -EAGAIN;
-		}
-
-		ret = wait_event_interruptible_lock_irq(pipe_crc->wq,
-				pipe_crc_data_count(pipe_crc), pipe_crc->lock);
-		if (ret) {
-			spin_unlock_irq(&pipe_crc->lock);
-			return ret;
-		}
-	}
-
-	/* We now have one or more entries to read */
-	n_entries = count / PIPE_CRC_LINE_LEN;
-
-	bytes_read = 0;
-	while (n_entries > 0) {
-		struct intel_pipe_crc_entry *entry =
-			&pipe_crc->entries[pipe_crc->tail];
-
-		if (CIRC_CNT(pipe_crc->head, pipe_crc->tail,
-			     INTEL_PIPE_CRC_ENTRIES_NR) < 1)
-			break;
-
-		BUILD_BUG_ON_NOT_POWER_OF_2(INTEL_PIPE_CRC_ENTRIES_NR);
-		pipe_crc->tail = (pipe_crc->tail + 1) &
-				 (INTEL_PIPE_CRC_ENTRIES_NR - 1);
-
-		bytes_read += snprintf(buf, PIPE_CRC_BUFFER_LEN,
-				       "%8u %8x %8x %8x %8x %8x\n",
-				       entry->frame, entry->crc[0],
-				       entry->crc[1], entry->crc[2],
-				       entry->crc[3], entry->crc[4]);
-
-		spin_unlock_irq(&pipe_crc->lock);
-
-		if (copy_to_user(user_buf, buf, PIPE_CRC_LINE_LEN))
-			return -EFAULT;
-
-		user_buf += PIPE_CRC_LINE_LEN;
-		n_entries--;
-
-		spin_lock_irq(&pipe_crc->lock);
-	}
-
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return bytes_read;
-}
-
-static const struct file_operations i915_pipe_crc_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_pipe_crc_open,
-	.read = i915_pipe_crc_read,
-	.release = i915_pipe_crc_release,
-};
-
-static struct pipe_crc_info i915_pipe_crc_data[I915_MAX_PIPES] = {
-	{
-		.name = "i915_pipe_A_crc",
-		.pipe = PIPE_A,
-	},
-	{
-		.name = "i915_pipe_B_crc",
-		.pipe = PIPE_B,
-	},
-	{
-		.name = "i915_pipe_C_crc",
-		.pipe = PIPE_C,
-	},
-};
-
 static const char * const pipe_crc_sources[] = {
 	"none",
 	"plane1",
@@ -197,29 +43,6 @@ static const char * const pipe_crc_sources[] = {
 	"auto",
 };
 
-static const char *pipe_crc_source_name(enum intel_pipe_crc_source source)
-{
-	BUILD_BUG_ON(ARRAY_SIZE(pipe_crc_sources) != INTEL_PIPE_CRC_SOURCE_MAX);
-	return pipe_crc_sources[source];
-}
-
-static int display_crc_ctl_show(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = m->private;
-	enum pipe pipe;
-
-	for_each_pipe(dev_priv, pipe)
-		seq_printf(m, "%c %s\n", pipe_name(pipe),
-			   pipe_crc_source_name(dev_priv->pipe_crc[pipe].source));
-
-	return 0;
-}
-
-static int display_crc_ctl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, display_crc_ctl_show, inode->i_private);
-}
-
 static int i8xx_pipe_crc_ctl_reg(enum intel_pipe_crc_source *source,
 				 uint32_t *val)
 {
@@ -616,177 +439,6 @@ static int get_new_crc_ctl_reg(struct drm_i915_private *dev_priv,
 		return ivb_pipe_crc_ctl_reg(dev_priv, pipe, source, val, set_wa);
 }
 
-static int pipe_crc_set_source(struct drm_i915_private *dev_priv,
-			       enum pipe pipe,
-			       enum intel_pipe_crc_source source)
-{
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	enum intel_display_power_domain power_domain;
-	u32 val = 0; /* shut up gcc */
-	int ret;
-
-	if (pipe_crc->source == source)
-		return 0;
-
-	/* forbid changing the source without going back to 'none' */
-	if (pipe_crc->source && source)
-		return -EINVAL;
-
-	power_domain = POWER_DOMAIN_PIPE(pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) {
-		DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n");
-		return -EIO;
-	}
-
-	ret = get_new_crc_ctl_reg(dev_priv, pipe, &source, &val, true);
-	if (ret != 0)
-		goto out;
-
-	/* none -> real source transition */
-	if (source) {
-		struct intel_pipe_crc_entry *entries;
-
-		DRM_DEBUG_DRIVER("collecting CRCs for pipe %c, %s\n",
-				 pipe_name(pipe), pipe_crc_source_name(source));
-
-		entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR,
-				  sizeof(pipe_crc->entries[0]),
-				  GFP_KERNEL);
-		if (!entries) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		spin_lock_irq(&pipe_crc->lock);
-		kfree(pipe_crc->entries);
-		pipe_crc->entries = entries;
-		pipe_crc->head = 0;
-		pipe_crc->tail = 0;
-		spin_unlock_irq(&pipe_crc->lock);
-	}
-
-	pipe_crc->source = source;
-
-	I915_WRITE(PIPE_CRC_CTL(pipe), val);
-	POSTING_READ(PIPE_CRC_CTL(pipe));
-
-	/* real source -> none transition */
-	if (!source) {
-		struct intel_pipe_crc_entry *entries;
-		struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
-								  pipe);
-
-		DRM_DEBUG_DRIVER("stopping CRCs for pipe %c\n",
-				 pipe_name(pipe));
-
-		drm_modeset_lock(&crtc->base.mutex, NULL);
-		if (crtc->base.state->active)
-			intel_wait_for_vblank(dev_priv, pipe);
-		drm_modeset_unlock(&crtc->base.mutex);
-
-		spin_lock_irq(&pipe_crc->lock);
-		entries = pipe_crc->entries;
-		pipe_crc->entries = NULL;
-		pipe_crc->head = 0;
-		pipe_crc->tail = 0;
-		spin_unlock_irq(&pipe_crc->lock);
-
-		kfree(entries);
-
-		if (IS_G4X(dev_priv))
-			g4x_undo_pipe_scramble_reset(dev_priv, pipe);
-		else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-			vlv_undo_pipe_scramble_reset(dev_priv, pipe);
-		else if ((IS_HASWELL(dev_priv) ||
-			  IS_BROADWELL(dev_priv)) && pipe == PIPE_A)
-			hsw_pipe_A_crc_wa(dev_priv, false);
-	}
-
-	ret = 0;
-
-out:
-	intel_display_power_put(dev_priv, power_domain);
-
-	return ret;
-}
-
-/*
- * Parse pipe CRC command strings:
- *   command: wsp* object wsp+ name wsp+ source wsp*
- *   object: 'pipe'
- *   name: (A | B | C)
- *   source: (none | plane1 | plane2 | pf)
- *   wsp: (#0x20 | #0x9 | #0xA)+
- *
- * eg.:
- *  "pipe A plane1"  ->  Start CRC computations on plane1 of pipe A
- *  "pipe A none"    ->  Stop CRC
- */
-static int display_crc_ctl_tokenize(char *buf, char *words[], int max_words)
-{
-	int n_words = 0;
-
-	while (*buf) {
-		char *end;
-
-		/* skip leading white space */
-		buf = skip_spaces(buf);
-		if (!*buf)
-			break;	/* end of buffer */
-
-		/* find end of word */
-		for (end = buf; *end && !isspace(*end); end++)
-			;
-
-		if (n_words == max_words) {
-			DRM_DEBUG_DRIVER("too many words, allowed <= %d\n",
-					 max_words);
-			return -EINVAL;	/* ran out of words[] before bytes */
-		}
-
-		if (*end)
-			*end++ = '\0';
-		words[n_words++] = buf;
-		buf = end;
-	}
-
-	return n_words;
-}
-
-enum intel_pipe_crc_object {
-	PIPE_CRC_OBJECT_PIPE,
-};
-
-static const char * const pipe_crc_objects[] = {
-	"pipe",
-};
-
-static int
-display_crc_ctl_parse_object(const char *buf, enum intel_pipe_crc_object *o)
-{
-	int i;
-
-	i = match_string(pipe_crc_objects, ARRAY_SIZE(pipe_crc_objects), buf);
-	if (i < 0)
-		return i;
-
-	*o = i;
-	return 0;
-}
-
-static int display_crc_ctl_parse_pipe(struct drm_i915_private *dev_priv,
-				      const char *buf, enum pipe *pipe)
-{
-	const char name = buf[0];
-
-	if (name < 'A' || name >= pipe_name(INTEL_INFO(dev_priv)->num_pipes))
-		return -EINVAL;
-
-	*pipe = name - 'A';
-
-	return 0;
-}
-
 static int
 display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 {
@@ -805,81 +457,6 @@ display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 	return 0;
 }
 
-static int display_crc_ctl_parse(struct drm_i915_private *dev_priv,
-				 char *buf, size_t len)
-{
-#define N_WORDS 3
-	int n_words;
-	char *words[N_WORDS];
-	enum pipe pipe;
-	enum intel_pipe_crc_object object;
-	enum intel_pipe_crc_source source;
-
-	n_words = display_crc_ctl_tokenize(buf, words, N_WORDS);
-	if (n_words != N_WORDS) {
-		DRM_DEBUG_DRIVER("tokenize failed, a command is %d words\n",
-				 N_WORDS);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_object(words[0], &object) < 0) {
-		DRM_DEBUG_DRIVER("unknown object %s\n", words[0]);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_pipe(dev_priv, words[1], &pipe) < 0) {
-		DRM_DEBUG_DRIVER("unknown pipe %s\n", words[1]);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_source(words[2], &source) < 0) {
-		DRM_DEBUG_DRIVER("unknown source %s\n", words[2]);
-		return -EINVAL;
-	}
-
-	return pipe_crc_set_source(dev_priv, pipe, source);
-}
-
-static ssize_t display_crc_ctl_write(struct file *file, const char __user *ubuf,
-				     size_t len, loff_t *offp)
-{
-	struct seq_file *m = file->private_data;
-	struct drm_i915_private *dev_priv = m->private;
-	char *tmpbuf;
-	int ret;
-
-	if (len == 0)
-		return 0;
-
-	if (len > PAGE_SIZE - 1) {
-		DRM_DEBUG_DRIVER("expected <%lu bytes into pipe crc control\n",
-				 PAGE_SIZE);
-		return -E2BIG;
-	}
-
-	tmpbuf = memdup_user_nul(ubuf, len);
-	if (IS_ERR(tmpbuf))
-		return PTR_ERR(tmpbuf);
-
-	ret = display_crc_ctl_parse(dev_priv, tmpbuf, len);
-
-	kfree(tmpbuf);
-	if (ret < 0)
-		return ret;
-
-	*offp += len;
-	return len;
-}
-
-const struct file_operations i915_display_crc_ctl_fops = {
-	.owner = THIS_MODULE,
-	.open = display_crc_ctl_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.write = display_crc_ctl_write
-};
-
 void intel_display_crc_init(struct drm_i915_private *dev_priv)
 {
 	enum pipe pipe;
@@ -887,30 +464,8 @@ void intel_display_crc_init(struct drm_i915_private *dev_priv)
 	for_each_pipe(dev_priv, pipe) {
 		struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 
-		pipe_crc->opened = false;
 		spin_lock_init(&pipe_crc->lock);
-		init_waitqueue_head(&pipe_crc->wq);
-	}
-}
-
-int intel_pipe_crc_create(struct drm_minor *minor)
-{
-	struct drm_i915_private *dev_priv = to_i915(minor->dev);
-	struct dentry *ent;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(i915_pipe_crc_data); i++) {
-		struct pipe_crc_info *info = &i915_pipe_crc_data[i];
-
-		info->dev_priv = dev_priv;
-		ent = debugfs_create_file(info->name, S_IRUGO,
-					  minor->debugfs_root, info,
-					  &i915_pipe_crc_fops);
-		if (!ent)
-			return -ENOMEM;
 	}
-
-	return 0;
 }
 
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 53aaaa3e6886..7312ecb73415 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7347,11 +7347,11 @@ out:
 
 static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
 {
-	if (WARN_ON(!dev_priv->vlv_pctx))
-		return;
+	struct drm_i915_gem_object *pctx;
 
-	i915_gem_object_put(dev_priv->vlv_pctx);
-	dev_priv->vlv_pctx = NULL;
+	pctx = fetch_and_zero(&dev_priv->vlv_pctx);
+	if (pctx)
+		i915_gem_object_put(pctx);
 }
 
 static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index d4cd19fea148..4bd5768731ee 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -56,43 +56,6 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
-static inline enum intel_display_power_domain
-psr_aux_domain(struct intel_dp *intel_dp)
-{
-	/* CNL HW requires corresponding AUX IOs to be powered up for PSR.
-	 * However, for non-A AUX ports the corresponding non-EDP transcoders
-	 * would have already enabled power well 2 and DC_OFF. This means we can
-	 * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a
-	 * specific AUX_IO reference without powering up any extra wells.
-	 * Note that PSR is enabled only on Port A even though this function
-	 * returns the correct domain for other ports too.
-	 */
-	return intel_dp->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A :
-					      intel_dp->aux_power_domain;
-}
-
-static void psr_aux_io_power_get(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);
-
-	if (INTEL_GEN(dev_priv) < 10)
-		return;
-
-	intel_display_power_get(dev_priv, psr_aux_domain(intel_dp));
-}
-
-static void psr_aux_io_power_put(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);
-
-	if (INTEL_GEN(dev_priv) < 10)
-		return;
-
-	intel_display_power_put(dev_priv, psr_aux_domain(intel_dp));
-}
-
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug)
 {
 	u32 debug_mask, mask;
@@ -278,8 +241,8 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	}
 }
 
-static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
-			      const struct intel_crtc_state *crtc_state)
+static void intel_psr_setup_vsc(struct intel_dp *intel_dp,
+				const struct intel_crtc_state *crtc_state)
 {
 	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);
@@ -336,7 +299,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 	aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, 0);
 
 	/* Start with bits set for DDI_AUX_CTL register */
-	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, 0, sizeof(aux_msg),
+	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, sizeof(aux_msg),
 					     aux_clock_divider);
 
 	/* Select only valid bits for SRD_AUX_CTL */
@@ -344,7 +307,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR_AUX_CTL, aux_ctl);
 }
 
-static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
+static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
@@ -360,6 +323,8 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 
 	if (dev_priv->psr.link_standby)
 		dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE;
+	if (!dev_priv->psr.psr2_enabled && INTEL_GEN(dev_priv) >= 8)
+		dpcd_val |= DP_PSR_CRC_VERIFICATION;
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val);
 
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
@@ -415,6 +380,9 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	else
 		val |= EDP_PSR_TP1_TP2_SEL;
 
+	if (INTEL_GEN(dev_priv) >= 8)
+		val |= EDP_PSR_CRC_ENABLE;
+
 	val |= I915_READ(EDP_PSR_CTL) & EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK;
 	I915_WRITE(EDP_PSR_CTL, val);
 }
@@ -456,24 +424,6 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR2_CTL, val);
 }
 
-static void hsw_psr_activate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	/* On HSW+ after we enable PSR on source it will activate it
-	 * as soon as it match configure idle_frame count. So
-	 * we just actually enable it here on activation time.
-	 */
-
-	/* psr1 and psr2 are mutually exclusive.*/
-	if (dev_priv->psr.psr2_enabled)
-		hsw_activate_psr2(intel_dp);
-	else
-		hsw_activate_psr1(intel_dp);
-}
-
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -576,27 +526,29 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	if (dev_priv->psr.psr2_enabled)
+	if (INTEL_GEN(dev_priv) >= 9)
 		WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
-	else
-		WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
+	WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	WARN_ON(dev_priv->psr.active);
 	lockdep_assert_held(&dev_priv->psr.lock);
 
-	dev_priv->psr.activate(intel_dp);
+	/* psr1 and psr2 are mutually exclusive.*/
+	if (dev_priv->psr.psr2_enabled)
+		hsw_activate_psr2(intel_dp);
+	else
+		hsw_activate_psr1(intel_dp);
+
 	dev_priv->psr.active = true;
 }
 
-static void hsw_psr_enable_source(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *crtc_state)
+static void intel_psr_enable_source(struct intel_dp *intel_dp,
+				    const struct intel_crtc_state *crtc_state)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
-	psr_aux_io_power_get(intel_dp);
-
 	/* Only HSW and BDW have PSR AUX registers that need to be setup. SKL+
 	 * use hardcoded values PSR AUX transactions
 	 */
@@ -632,7 +584,8 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 			   EDP_PSR_DEBUG_MASK_MEMUP |
 			   EDP_PSR_DEBUG_MASK_HPD |
 			   EDP_PSR_DEBUG_MASK_LPSP |
-			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE);
+			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE |
+			   EDP_PSR_DEBUG_MASK_MAX_SLEEP);
 	}
 }
 
@@ -666,9 +619,9 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 	dev_priv->psr.psr2_enabled = crtc_state->has_psr2;
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 
-	dev_priv->psr.setup_vsc(intel_dp, crtc_state);
-	dev_priv->psr.enable_sink(intel_dp);
-	dev_priv->psr.enable_source(intel_dp, crtc_state);
+	intel_psr_setup_vsc(intel_dp, crtc_state);
+	intel_psr_enable_sink(intel_dp);
+	intel_psr_enable_source(intel_dp, crtc_state);
 	dev_priv->psr.enabled = intel_dp;
 
 	intel_psr_activate(intel_dp);
@@ -677,8 +630,8 @@ unlock:
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
-static void hsw_psr_disable(struct intel_dp *intel_dp,
-			    const struct intel_crtc_state *old_crtc_state)
+static void
+intel_psr_disable_source(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
@@ -717,8 +670,25 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 		else
 			WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	}
+}
+
+static void intel_psr_disable_locked(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	lockdep_assert_held(&dev_priv->psr.lock);
 
-	psr_aux_io_power_put(intel_dp);
+	if (!dev_priv->psr.enabled)
+		return;
+
+	intel_psr_disable_source(intel_dp);
+
+	/* Disable PSR on Sink */
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
+
+	dev_priv->psr.enabled = NULL;
 }
 
 /**
@@ -742,22 +712,49 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
-	if (!dev_priv->psr.enabled) {
-		mutex_unlock(&dev_priv->psr.lock);
-		return;
-	}
+	intel_psr_disable_locked(intel_dp);
+	mutex_unlock(&dev_priv->psr.lock);
+	cancel_work_sync(&dev_priv->psr.work);
+}
 
-	dev_priv->psr.disable_source(intel_dp, old_crtc_state);
+int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	i915_reg_t reg;
+	u32 mask;
 
-	/* Disable PSR on Sink */
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
+	if (!new_crtc_state->has_psr)
+		return 0;
 
-	dev_priv->psr.enabled = NULL;
-	mutex_unlock(&dev_priv->psr.lock);
-	cancel_work_sync(&dev_priv->psr.work);
+	/*
+	 * The sole user right now is intel_pipe_update_start(),
+	 * which won't race with psr_enable/disable, which is
+	 * where psr2_enabled is written to. So, we don't need
+	 * to acquire the psr.lock. More importantly, we want the
+	 * latency inside intel_pipe_update_start() to be as low
+	 * as possible, so no need to acquire psr.lock when it is
+	 * not needed and will induce latencies in the atomic
+	 * update path.
+	 */
+	if (dev_priv->psr.psr2_enabled) {
+		reg = EDP_PSR2_STATUS;
+		mask = EDP_PSR2_STATUS_STATE_MASK;
+	} else {
+		reg = EDP_PSR_STATUS;
+		mask = EDP_PSR_STATUS_STATE_MASK;
+	}
+
+	/*
+	 * Max time for PSR to idle = Inverse of the refresh rate +
+	 * 6 ms of exit training time + 1.5 ms of aux channel
+	 * handshake. 50 msec is defesive enough to cover everything.
+	 */
+	return intel_wait_for_register(dev_priv, reg, mask,
+				       EDP_PSR_STATUS_STATE_IDLE, 50);
 }
 
-static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
+static bool __psr_wait_for_idle_locked(struct drm_i915_private *dev_priv)
 {
 	struct intel_dp *intel_dp;
 	i915_reg_t reg;
@@ -803,7 +800,7 @@ static void intel_psr_work(struct work_struct *work)
 	 * PSR might take some time to get fully disabled
 	 * and be ready for re-enable.
 	 */
-	if (!psr_wait_for_idle(dev_priv))
+	if (!__psr_wait_for_idle_locked(dev_priv))
 		goto unlock;
 
 	/*
@@ -811,7 +808,7 @@ static void intel_psr_work(struct work_struct *work)
 	 * recheck. Since psr_flush first clears this and then reschedules we
 	 * won't ever miss a flush when bailing out here.
 	 */
-	if (dev_priv->psr.busy_frontbuffer_bits)
+	if (dev_priv->psr.busy_frontbuffer_bits || dev_priv->psr.active)
 		goto unlock;
 
 	intel_psr_activate(dev_priv->psr.enabled);
@@ -974,23 +971,60 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 		/* For new platforms let's respect VBT back again */
 		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
 
-	/* Override link_standby x link_off defaults */
-	if (i915_modparams.enable_psr == 2 && !dev_priv->psr.link_standby) {
-		DRM_DEBUG_KMS("PSR: Forcing link standby\n");
-		dev_priv->psr.link_standby = true;
-	}
-	if (i915_modparams.enable_psr == 3 && dev_priv->psr.link_standby) {
-		DRM_DEBUG_KMS("PSR: Forcing main link off\n");
-		dev_priv->psr.link_standby = false;
-	}
-
 	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
+}
 
-	dev_priv->psr.enable_source = hsw_psr_enable_source;
-	dev_priv->psr.disable_source = hsw_psr_disable;
-	dev_priv->psr.enable_sink = hsw_psr_enable_sink;
-	dev_priv->psr.activate = hsw_psr_activate;
-	dev_priv->psr.setup_vsc = hsw_psr_setup_vsc;
+void intel_psr_short_pulse(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 val;
+	const u8 errors = DP_PSR_RFB_STORAGE_ERROR |
+			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR |
+			  DP_PSR_LINK_CRC_ERROR;
+
+	if (!CAN_PSR(dev_priv) || !intel_dp_is_edp(intel_dp))
+		return;
+
+	mutex_lock(&psr->lock);
+
+	if (psr->enabled != 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");
+		goto exit;
+	}
+
+	if ((val & DP_PSR_SINK_STATE_MASK) == DP_PSR_SINK_INTERNAL_ERROR) {
+		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+		intel_psr_disable_locked(intel_dp);
+	}
+
+	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)
+		DRM_DEBUG_KMS("PSR RFB storage error, disabling PSR\n");
+	if (val & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
+		DRM_DEBUG_KMS("PSR VSC SDP uncorrectable error, disabling PSR\n");
+	if (val & DP_PSR_LINK_CRC_ERROR)
+		DRM_ERROR("PSR Link CRC error, disabling PSR\n");
+
+	if (val & ~errors)
+		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
+			  val & ~errors);
+	if (val & errors)
+		intel_psr_disable_locked(intel_dp);
+	/* clear status register */
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, val);
+
+	/* TODO: handle PSR2 errors */
+exit:
+	mutex_unlock(&psr->lock);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index e0448eff12bd..33faad3197fe 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -524,8 +524,6 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		goto out;
 	}
 
-	intel_engine_init_hangcheck(engine);
-
 	if (INTEL_GEN(dev_priv) > 2)
 		I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING));
 
@@ -1089,6 +1087,7 @@ void intel_ring_unpin(struct intel_ring *ring)
 static struct i915_vma *
 intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 {
+	struct i915_address_space *vm = &dev_priv->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 
@@ -1098,10 +1097,14 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	/* mark ring buffers as read-only from GPU side by default */
-	obj->gt_ro = 1;
+	/*
+	 * Mark ring buffers as read-only from GPU side (so no stray overwrites)
+	 * if supported by the platform's GGTT.
+	 */
+	if (vm->has_read_only)
+		i915_gem_object_set_readonly(obj);
 
-	vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL);
+	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
 
@@ -1169,8 +1172,11 @@ static void intel_ring_context_destroy(struct intel_context *ce)
 {
 	GEM_BUG_ON(ce->pin_count);
 
-	if (ce->state)
-		__i915_gem_object_release_unless_active(ce->state->obj);
+	if (!ce->state)
+		return;
+
+	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
+	i915_gem_object_put(ce->state->obj);
 }
 
 static int __context_pin_ppgtt(struct i915_gem_context *ctx)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index a0bc7a8222b4..f5ffa6d31e82 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -193,6 +193,11 @@ struct i915_priolist {
 	int priority;
 };
 
+struct st_preempt_hang {
+	struct completion completion;
+	bool inject_hang;
+};
+
 /**
  * struct intel_engine_execlists - execlist submission queue and port state
  *
@@ -292,32 +297,49 @@ struct intel_engine_execlists {
 	/**
 	 * @queue: queue of requests, in priority lists
 	 */
-	struct rb_root queue;
+	struct rb_root_cached queue;
 
 	/**
-	 * @first: leftmost level in priority @queue
+	 * @csb_read: control register for Context Switch buffer
+	 *
+	 * Note this register is always in mmio.
 	 */
-	struct rb_node *first;
+	u32 __iomem *csb_read;
 
 	/**
-	 * @fw_domains: forcewake domains for irq tasklet
+	 * @csb_write: control register for Context Switch buffer
+	 *
+	 * Note this register may be either mmio or HWSP shadow.
 	 */
-	unsigned int fw_domains;
+	u32 *csb_write;
 
 	/**
-	 * @csb_head: context status buffer head
+	 * @csb_status: status array for Context Switch buffer
+	 *
+	 * Note these register may be either mmio or HWSP shadow.
+	 */
+	u32 *csb_status;
+
+	/**
+	 * @preempt_complete_status: expected CSB upon completing preemption
 	 */
-	unsigned int csb_head;
+	u32 preempt_complete_status;
 
 	/**
-	 * @csb_use_mmio: access csb through mmio, instead of hwsp
+	 * @csb_write_reset: reset value for CSB write pointer
+	 *
+	 * As the CSB write pointer maybe either in HWSP or as a field
+	 * inside an mmio register, we want to reprogram it slightly
+	 * differently to avoid later confusion.
 	 */
-	bool csb_use_mmio;
+	u32 csb_write_reset;
 
 	/**
-	 * @preempt_complete_status: expected CSB upon completing preemption
+	 * @csb_head: context status buffer head
 	 */
-	u32 preempt_complete_status;
+	u8 csb_head;
+
+	I915_SELFTEST_DECLARE(struct st_preempt_hang preempt_hang;)
 };
 
 #define INTEL_ENGINE_CS_MAX_NAME 8
@@ -345,10 +367,8 @@ struct intel_engine_cs {
 	struct drm_i915_gem_object *default_state;
 	void *pinned_default_state;
 
-	atomic_t irq_count;
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
-#define ENGINE_IRQ_EXECLIST 1
 
 	/* Rather than have every client wait upon all user interrupts,
 	 * with the herd waking after every interrupt and each doing the
@@ -380,6 +400,7 @@ struct intel_engine_cs {
 
 		unsigned int hangcheck_interrupts;
 		unsigned int irq_enabled;
+		unsigned int irq_count;
 
 		bool irq_armed : 1;
 		I915_SELFTEST_DECLARE(bool mock : 1);
@@ -669,6 +690,12 @@ execlists_clear_active(struct intel_engine_execlists *execlists,
 	__clear_bit(bit, (unsigned long *)&execlists->active);
 }
 
+static inline void
+execlists_clear_all_active(struct intel_engine_execlists *execlists)
+{
+	execlists->active = 0;
+}
+
 static inline bool
 execlists_is_active(const struct intel_engine_execlists *execlists,
 		    unsigned int bit)
@@ -928,11 +955,10 @@ static inline u32 intel_hws_preempt_done_address(struct intel_engine_cs *engine)
 /* intel_breadcrumbs.c -- user interrupt bottom-half for waiters */
 int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
 
-static inline void intel_wait_init(struct intel_wait *wait,
-				   struct i915_request *rq)
+static inline void intel_wait_init(struct intel_wait *wait)
 {
 	wait->tsk = current;
-	wait->request = rq;
+	wait->request = NULL;
 }
 
 static inline void intel_wait_init_for_seqno(struct intel_wait *wait, u32 seqno)
@@ -1136,4 +1162,24 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine);
 
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+
+static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
+{
+	if (!execlists->preempt_hang.inject_hang)
+		return false;
+
+	complete(&execlists->preempt_hang.completion);
+	return true;
+}
+
+#else
+
+static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
+{
+	return false;
+}
+
+#endif
+
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index de3a81034f77..6b5aa3b074ec 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -134,6 +134,14 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "AUX_F";
 	case POWER_DOMAIN_AUX_IO_A:
 		return "AUX_IO_A";
+	case POWER_DOMAIN_AUX_TBT1:
+		return "AUX_TBT1";
+	case POWER_DOMAIN_AUX_TBT2:
+		return "AUX_TBT2";
+	case POWER_DOMAIN_AUX_TBT3:
+		return "AUX_TBT3";
+	case POWER_DOMAIN_AUX_TBT4:
+		return "AUX_TBT4";
 	case POWER_DOMAIN_GMBUS:
 		return "GMBUS";
 	case POWER_DOMAIN_INIT:
@@ -384,7 +392,8 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 	u32 val;
 
 	if (wait_fuses) {
-		pg = SKL_PW_TO_PG(id);
+		pg = INTEL_GEN(dev_priv) >= 11 ? ICL_PW_TO_PG(id) :
+						 SKL_PW_TO_PG(id);
 		/*
 		 * For PW1 we have to wait both for the PW0/PG0 fuse state
 		 * before enabling the power well and PW1/PG1's own fuse
@@ -430,6 +439,43 @@ static void hsw_power_well_disable(struct drm_i915_private *dev_priv,
 	hsw_wait_for_power_well_disable(dev_priv, power_well);
 }
 
+#define ICL_AUX_PW_TO_PORT(pw)	((pw) - ICL_DISP_PW_AUX_A)
+
+static void
+icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
+				    struct i915_power_well *power_well)
+{
+	enum i915_power_well_id id = power_well->id;
+	enum port port = ICL_AUX_PW_TO_PORT(id);
+	u32 val;
+
+	val = I915_READ(HSW_PWR_WELL_CTL_DRIVER(id));
+	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id), val | HSW_PWR_WELL_CTL_REQ(id));
+
+	val = I915_READ(ICL_PORT_CL_DW12(port));
+	I915_WRITE(ICL_PORT_CL_DW12(port), val | ICL_LANE_ENABLE_AUX);
+
+	hsw_wait_for_power_well_enable(dev_priv, power_well);
+}
+
+static void
+icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
+				     struct i915_power_well *power_well)
+{
+	enum i915_power_well_id id = power_well->id;
+	enum port port = ICL_AUX_PW_TO_PORT(id);
+	u32 val;
+
+	val = I915_READ(ICL_PORT_CL_DW12(port));
+	I915_WRITE(ICL_PORT_CL_DW12(port), val & ~ICL_LANE_ENABLE_AUX);
+
+	val = I915_READ(HSW_PWR_WELL_CTL_DRIVER(id));
+	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id),
+		   val & ~HSW_PWR_WELL_CTL_REQ(id));
+
+	hsw_wait_for_power_well_disable(dev_priv, power_well);
+}
+
 /*
  * We should only use the power well if we explicitly asked the hardware to
  * enable it, so check if it's enabled and also check if we've requested it to
@@ -1824,6 +1870,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_AUX_A_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_A) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_IO_A) |		\
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_AUX_B_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |		\
@@ -1896,6 +1943,105 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
+/*
+ * ICL PW_0/PG_0 domains (HW/DMC control):
+ * - PCI
+ * - clocks except port PLL
+ * - central power except FBC
+ * - shared functions except pipe interrupts, pipe MBUS, DBUF registers
+ * ICL PW_1/PG_1 domains (HW/DMC control):
+ * - DBUF function
+ * - PIPE_A and its planes, except VGA
+ * - transcoder EDP + PSR
+ * - transcoder DSI
+ * - DDI_A
+ * - FBC
+ */
+#define ICL_PW_4_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PIPE_C) |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_C_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/* VDSC/joining */
+#define ICL_PW_3_POWER_DOMAINS (			\
+	ICL_PW_4_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_A) |		\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_C) |		\
+	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_E) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT1) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT2) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT3) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT4) |		\
+	BIT_ULL(POWER_DOMAIN_VGA) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/*
+	 * - transcoder WD
+	 * - KVMR (HW control)
+	 */
+#define ICL_PW_2_POWER_DOMAINS (			\
+	ICL_PW_3_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/*
+	 * - eDP/DSI VDSC
+	 * - KVMR (HW control)
+	 */
+#define ICL_DISPLAY_DC_OFF_POWER_DOMAINS (		\
+	ICL_PW_2_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_MODESET) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+
+#define ICL_DDI_IO_A_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO))
+#define ICL_DDI_IO_B_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO))
+#define ICL_DDI_IO_C_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO))
+#define ICL_DDI_IO_D_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO))
+#define ICL_DDI_IO_E_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO))
+#define ICL_DDI_IO_F_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO))
+
+#define ICL_AUX_A_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_A))
+#define ICL_AUX_B_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_B))
+#define ICL_AUX_C_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_C))
+#define ICL_AUX_D_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_D))
+#define ICL_AUX_E_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_E))
+#define ICL_AUX_F_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_F))
+#define ICL_AUX_TBT1_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT1))
+#define ICL_AUX_TBT2_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT2))
+#define ICL_AUX_TBT3_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT3))
+#define ICL_AUX_TBT4_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT4))
+
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_power_well_sync_hw_noop,
 	.enable = i9xx_always_on_power_well_noop,
@@ -2453,6 +2599,157 @@ static struct i915_power_well cnl_power_wells[] = {
 	},
 };
 
+static const struct i915_power_well_ops icl_combo_phy_aux_power_well_ops = {
+	.sync_hw = hsw_power_well_sync_hw,
+	.enable = icl_combo_phy_aux_power_well_enable,
+	.disable = icl_combo_phy_aux_power_well_disable,
+	.is_enabled = hsw_power_well_enabled,
+};
+
+static struct i915_power_well icl_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = POWER_DOMAIN_MASK,
+		.ops = &i9xx_always_on_power_well_ops,
+		.id = I915_DISP_PW_ALWAYS_ON,
+	},
+	{
+		.name = "power well 1",
+		/* Handled by the DMC firmware */
+		.domains = 0,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_1,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "power well 2",
+		.domains = ICL_PW_2_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_2,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "DC off",
+		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
+		.ops = &gen9_dc_off_power_well_ops,
+		.id = SKL_DISP_PW_DC_OFF,
+	},
+	{
+		.name = "power well 3",
+		.domains = ICL_PW_3_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_3,
+		.hsw.irq_pipe_mask = BIT(PIPE_B),
+		.hsw.has_vga = true,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "DDI A IO",
+		.domains = ICL_DDI_IO_A_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_A,
+	},
+	{
+		.name = "DDI B IO",
+		.domains = ICL_DDI_IO_B_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_B,
+	},
+	{
+		.name = "DDI C IO",
+		.domains = ICL_DDI_IO_C_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_C,
+	},
+	{
+		.name = "DDI D IO",
+		.domains = ICL_DDI_IO_D_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_D,
+	},
+	{
+		.name = "DDI E IO",
+		.domains = ICL_DDI_IO_E_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_E,
+	},
+	{
+		.name = "DDI F IO",
+		.domains = ICL_DDI_IO_F_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_F,
+	},
+	{
+		.name = "AUX A",
+		.domains = ICL_AUX_A_IO_POWER_DOMAINS,
+		.ops = &icl_combo_phy_aux_power_well_ops,
+		.id = ICL_DISP_PW_AUX_A,
+	},
+	{
+		.name = "AUX B",
+		.domains = ICL_AUX_B_IO_POWER_DOMAINS,
+		.ops = &icl_combo_phy_aux_power_well_ops,
+		.id = ICL_DISP_PW_AUX_B,
+	},
+	{
+		.name = "AUX C",
+		.domains = ICL_AUX_C_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_C,
+	},
+	{
+		.name = "AUX D",
+		.domains = ICL_AUX_D_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_D,
+	},
+	{
+		.name = "AUX E",
+		.domains = ICL_AUX_E_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_E,
+	},
+	{
+		.name = "AUX F",
+		.domains = ICL_AUX_F_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_F,
+	},
+	{
+		.name = "AUX TBT1",
+		.domains = ICL_AUX_TBT1_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT1,
+	},
+	{
+		.name = "AUX TBT2",
+		.domains = ICL_AUX_TBT2_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT2,
+	},
+	{
+		.name = "AUX TBT3",
+		.domains = ICL_AUX_TBT3_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT3,
+	},
+	{
+		.name = "AUX TBT4",
+		.domains = ICL_AUX_TBT4_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT4,
+	},
+	{
+		.name = "power well 4",
+		.domains = ICL_PW_4_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_4,
+		.hsw.has_fuses = true,
+		.hsw.irq_pipe_mask = BIT(PIPE_C),
+	},
+};
+
 static int
 sanitize_disable_power_well_option(const struct drm_i915_private *dev_priv,
 				   int disable_power_well)
@@ -2470,7 +2767,7 @@ static uint32_t get_allowed_dc_mask(const struct drm_i915_private *dev_priv,
 	int requested_dc;
 	int max_dc;
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || INTEL_INFO(dev_priv)->gen >= 10) {
 		max_dc = 2;
 		mask = 0;
 	} else if (IS_GEN9_LP(dev_priv)) {
@@ -2558,7 +2855,9 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	 * The enabling order will be from lower to higher indexed wells,
 	 * the disabling order is reversed.
 	 */
-	if (IS_HASWELL(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		set_power_wells(power_domains, icl_power_wells);
+	} else if (IS_HASWELL(dev_priv)) {
 		set_power_wells(power_domains, hsw_power_wells);
 	} else if (IS_BROADWELL(dev_priv)) {
 		set_power_wells(power_domains, bdw_power_wells);
@@ -2913,6 +3212,7 @@ static void cnl_set_procmon_ref_values(struct drm_i915_private *dev_priv,
 	switch (val & (PROCESS_INFO_MASK | VOLTAGE_INFO_MASK)) {
 	default:
 		MISSING_CASE(val);
+		/* fall through */
 	case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0:
 		procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0];
 		break;
@@ -3025,6 +3325,8 @@ static void cnl_display_core_uninit(struct drm_i915_private *dev_priv)
 static void icl_display_core_init(struct drm_i915_private *dev_priv,
 				  bool resume)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *well;
 	enum port port;
 	u32 val;
 
@@ -3053,8 +3355,14 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 		I915_WRITE(ICL_PORT_CL_DW5(port), val);
 	}
 
-	/* 4. Enable power well 1 (PG1) and aux IO power. */
-	/* FIXME: ICL power wells code not here yet. */
+	/*
+	 * 4. Enable Power Well 1 (PG1).
+	 *    The AUX IO power wells will be enabled on demand.
+	 */
+	mutex_lock(&power_domains->lock);
+	well = lookup_power_well(dev_priv, ICL_DISP_PW_1);
+	intel_power_well_enable(dev_priv, well);
+	mutex_unlock(&power_domains->lock);
 
 	/* 5. Enable CDCLK. */
 	icl_init_cdclk(dev_priv);
@@ -3072,6 +3380,8 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 
 static void icl_display_core_uninit(struct drm_i915_private *dev_priv)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *well;
 	enum port port;
 	u32 val;
 
@@ -3085,8 +3395,15 @@ static void icl_display_core_uninit(struct drm_i915_private *dev_priv)
 	/* 3. Disable CD clock */
 	icl_uninit_cdclk(dev_priv);
 
-	/* 4. Disable Power Well 1 (PG1) and Aux IO Power */
-	/* FIXME: ICL power wells code not here yet. */
+	/*
+	 * 4. Disable Power Well 1 (PG1).
+	 *    The AUX IO power wells are toggled on demand, so they are already
+	 *    disabled at this point.
+	 */
+	mutex_lock(&power_domains->lock);
+	well = lookup_power_well(dev_priv, ICL_DISP_PW_1);
+	intel_power_well_disable(dev_priv, well);
+	mutex_unlock(&power_domains->lock);
 
 	/* 5. Disable Comp */
 	for (port = PORT_A; port <= PORT_B; port++) {
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index e6a64b3ecd91..812fe7b06f87 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1340,6 +1340,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder,
 	switch (crtc_state->pixel_multiplier) {
 	default:
 		WARN(1, "unknown pixel multiplier specified\n");
+		/* fall through */
 	case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break;
 	case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break;
 	case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break;
@@ -1400,10 +1401,7 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
-	if (active_outputs & intel_sdvo_connector->output_flag)
-		return true;
-	else
-		return false;
+	return active_outputs & intel_sdvo_connector->output_flag;
 }
 
 bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
@@ -1913,7 +1911,7 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 	if (edid != NULL) {
 		if (intel_sdvo_connector_matches_edid(to_intel_sdvo_connector(connector),
 						      edid)) {
-			drm_mode_connector_update_edid_property(connector, edid);
+			drm_connector_update_edid_property(connector, edid);
 			drm_add_edid_modes(connector, edid);
 		}
 
@@ -2316,14 +2314,19 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo)
 	switch (sdvo->controlled_output) {
 	case SDVO_OUTPUT_LVDS1:
 		mask |= SDVO_OUTPUT_LVDS1;
+		/* fall through */
 	case SDVO_OUTPUT_LVDS0:
 		mask |= SDVO_OUTPUT_LVDS0;
+		/* fall through */
 	case SDVO_OUTPUT_TMDS1:
 		mask |= SDVO_OUTPUT_TMDS1;
+		/* fall through */
 	case SDVO_OUTPUT_TMDS0:
 		mask |= SDVO_OUTPUT_TMDS0;
+		/* fall through */
 	case SDVO_OUTPUT_RGB1:
 		mask |= SDVO_OUTPUT_RGB1;
+		/* fall through */
 	case SDVO_OUTPUT_RGB0:
 		mask |= SDVO_OUTPUT_RGB0;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 344c0e709b19..f7026e887fa9 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -41,20 +41,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-bool intel_format_is_yuv(u32 format)
-{
-	switch (format) {
-	case DRM_FORMAT_YUYV:
-	case DRM_FORMAT_UYVY:
-	case DRM_FORMAT_VYUY:
-	case DRM_FORMAT_YVYU:
-	case DRM_FORMAT_NV12:
-		return true;
-	default:
-		return false;
-	}
-}
-
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs)
 {
@@ -107,13 +93,21 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 						      VBLANK_EVASION_TIME_US);
 	max = vblank_start - 1;
 
-	local_irq_disable();
-
 	if (min <= 0 || max <= 0)
-		return;
+		goto irq_disable;
 
 	if (WARN_ON(drm_crtc_vblank_get(&crtc->base)))
-		return;
+		goto irq_disable;
+
+	/*
+	 * Wait for psr to idle out after enabling the VBL interrupts
+	 * VBL interrupts will start the PSR exit and prevent a PSR
+	 * re-entry as well.
+	 */
+	if (intel_psr_wait_for_idle(new_crtc_state))
+		DRM_ERROR("PSR idle timed out, atomic update may fail\n");
+
+	local_irq_disable();
 
 	crtc->debug.min_vbl = min;
 	crtc->debug.max_vbl = max;
@@ -171,6 +165,10 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
 
 	trace_i915_pipe_update_vblank_evaded(crtc);
+	return;
+
+irq_disable:
+	local_irq_disable();
 }
 
 /**
@@ -404,7 +402,7 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 	const s16 *csc = csc_matrix[plane_state->base.color_encoding];
 
 	/* Seems RGB data bypasses the CSC always */
-	if (!intel_format_is_yuv(fb->format->format))
+	if (!fb->format->is_yuv)
 		return;
 
 	I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0));
@@ -439,7 +437,7 @@ vlv_update_clrc(const struct intel_plane_state *plane_state)
 	enum plane_id plane_id = plane->id;
 	int contrast, brightness, sh_scale, sh_sin, sh_cos;
 
-	if (intel_format_is_yuv(fb->format->format) &&
+	if (fb->format->is_yuv &&
 	    plane_state->base.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
 		/*
 		 * Expand limited range to full range:
@@ -1040,7 +1038,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 		src->y1 = src_y << 16;
 		src->y2 = (src_y + src_h) << 16;
 
-		if (intel_format_is_yuv(fb->format->format) &&
+		if (fb->format->is_yuv &&
     		    fb->format->format != DRM_FORMAT_NV12 &&
 		    (src_x % 2 || src_w % 2)) {
 			DRM_DEBUG_KMS("src x/w (%u, %u) must be a multiple of 2 for YUV planes\n",
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 24dc368fdaa1..b5b04cb892e9 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1347,8 +1347,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 		mode_ptr = drm_mode_create(connector->dev);
 		if (!mode_ptr)
 			continue;
-		strncpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
-		mode_ptr->name[DRM_DISPLAY_MODE_LEN - 1] = '\0';
+		strlcpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
 
 		mode_ptr->hdisplay = hactive_s;
 		mode_ptr->hsync_start = hactive_s + 1;
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 94e8863bd97c..7c95697e1a35 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -171,24 +171,11 @@ void intel_uc_init_early(struct drm_i915_private *i915)
 	intel_huc_init_early(huc);
 
 	sanitize_options_early(i915);
-
-	if (USES_GUC(i915))
-		intel_uc_fw_fetch(i915, &guc->fw);
-
-	if (USES_HUC(i915))
-		intel_uc_fw_fetch(i915, &huc->fw);
 }
 
 void intel_uc_cleanup_early(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
-	struct intel_huc *huc = &i915->huc;
-
-	if (USES_HUC(i915))
-		intel_uc_fw_fini(&huc->fw);
-
-	if (USES_GUC(i915))
-		intel_uc_fw_fini(&guc->fw);
 
 	guc_free_load_err_log(guc);
 }
@@ -252,28 +239,41 @@ static void guc_disable_communication(struct intel_guc *guc)
 int intel_uc_init_misc(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 	int ret;
 
 	if (!USES_GUC(i915))
 		return 0;
 
-	intel_guc_init_ggtt_pin_bias(guc);
-
-	ret = intel_guc_init_wq(guc);
+	ret = intel_guc_init_misc(guc);
 	if (ret)
 		return ret;
 
+	if (USES_HUC(i915)) {
+		ret = intel_huc_init_misc(huc);
+		if (ret)
+			goto err_guc;
+	}
+
 	return 0;
+
+err_guc:
+	intel_guc_fini_misc(guc);
+	return ret;
 }
 
 void intel_uc_fini_misc(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 
 	if (!USES_GUC(i915))
 		return;
 
-	intel_guc_fini_wq(guc);
+	if (USES_HUC(i915))
+		intel_huc_fini_misc(huc);
+
+	intel_guc_fini_misc(guc);
 }
 
 int intel_uc_init(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index fbe4324116d7..7efb326badcd 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -570,6 +570,7 @@ 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(obj);
 	}
 
@@ -597,6 +598,7 @@ 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(obj);
 	}
 }
@@ -866,6 +868,7 @@ 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(obj);
 		}
 	}
@@ -919,12 +922,12 @@ gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val)
 			*cmd++ = val;
 		} else if (gen >= 4) {
 			*cmd++ = MI_STORE_DWORD_IMM_GEN4 |
-				(gen < 6 ? 1 << 22 : 0);
+				(gen < 6 ? MI_USE_GGTT : 0);
 			*cmd++ = 0;
 			*cmd++ = offset;
 			*cmd++ = val;
 		} else {
-			*cmd++ = MI_STORE_DWORD_IMM | 1 << 22;
+			*cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*cmd++ = offset;
 			*cmd++ = val;
 		}
@@ -985,7 +988,10 @@ static int gpu_write(struct i915_vma *vma,
 		goto err_request;
 	}
 
-	i915_vma_move_to_active(batch, rq, 0);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto err_request;
+
 	i915_gem_object_set_active_reference(batch->obj);
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
@@ -996,11 +1002,9 @@ static int gpu_write(struct i915_vma *vma,
 	if (err)
 		goto err_request;
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		i915_request_skip(rq, err);
 
 err_request:
 	i915_request_add(rq);
@@ -1264,6 +1268,7 @@ 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(obj);
 		}
 	}
@@ -1325,6 +1330,7 @@ static int igt_ppgtt_internal_huge(void *arg)
 		}
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -1393,6 +1399,7 @@ static int igt_ppgtt_gemfs_huge(void *arg)
 		}
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -1694,7 +1701,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(39));
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV), "mock");
+	ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV));
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
@@ -1724,7 +1731,7 @@ out_unlock:
 
 	i915_modparams.enable_ppgtt = saved_ppgtt;
 
-	drm_dev_unref(&dev_priv->drm);
+	drm_dev_put(&dev_priv->drm);
 
 	return err;
 }
@@ -1748,6 +1755,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 		return 0;
 	}
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		return 0;
+
 	file = mock_file(dev_priv);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index a4900091ae3d..3a095c37c120 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -42,11 +42,21 @@ static int cpu_set(struct drm_i915_gem_object *obj,
 
 	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
-	if (needs_clflush & CLFLUSH_BEFORE)
+
+	if (needs_clflush & CLFLUSH_BEFORE) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	map[offset_in_page(offset) / sizeof(*map)] = v;
-	if (needs_clflush & CLFLUSH_AFTER)
+
+	if (needs_clflush & CLFLUSH_AFTER) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	kunmap_atomic(map);
 
 	i915_gem_obj_finish_shmem_access(obj);
@@ -68,8 +78,13 @@ static int cpu_get(struct drm_i915_gem_object *obj,
 
 	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
-	if (needs_clflush & CLFLUSH_BEFORE)
+
+	if (needs_clflush & CLFLUSH_BEFORE) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	*v = map[offset_in_page(offset) / sizeof(*map)];
 	kunmap_atomic(map);
 
@@ -210,28 +225,24 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 		*cs++ = upper_32_bits(i915_ggtt_offset(vma) + offset);
 		*cs++ = v;
 	} else if (INTEL_GEN(i915) >= 4) {
-		*cs++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
+		*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*cs++ = 0;
 		*cs++ = i915_ggtt_offset(vma) + offset;
 		*cs++ = v;
 	} else {
-		*cs++ = MI_STORE_DWORD_IMM | 1 << 22;
+		*cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*cs++ = i915_ggtt_offset(vma) + offset;
 		*cs++ = v;
 		*cs++ = MI_NOOP;
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
-	reservation_object_lock(obj->resv, NULL);
-	reservation_object_add_excl_fence(obj->resv, &rq->fence);
-	reservation_object_unlock(obj->resv);
-
 	i915_request_add(rq);
 
-	return 0;
+	return err;
 }
 
 static bool always_valid(struct drm_i915_private *i915)
@@ -239,8 +250,16 @@ static bool always_valid(struct drm_i915_private *i915)
 	return true;
 }
 
+static bool needs_fence_registers(struct drm_i915_private *i915)
+{
+	return !i915_terminally_wedged(&i915->gpu_error);
+}
+
 static bool needs_mi_store_dword(struct drm_i915_private *i915)
 {
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return false;
+
 	return intel_engine_can_store_dword(i915->engine[RCS]);
 }
 
@@ -251,7 +270,7 @@ static const struct igt_coherency_mode {
 	bool (*valid)(struct drm_i915_private *i915);
 } igt_coherency_mode[] = {
 	{ "cpu", cpu_set, cpu_get, always_valid },
-	{ "gtt", gtt_set, gtt_get, always_valid },
+	{ "gtt", gtt_set, gtt_get, needs_fence_registers },
 	{ "wc", wc_set, wc_get, always_valid },
 	{ "gpu", gpu_set, NULL, needs_mi_store_dword },
 	{ },
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 90c3c36173ba..1c92560d35da 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -23,6 +23,7 @@
  */
 
 #include "../i915_selftest.h"
+#include "i915_random.h"
 #include "igt_flush_test.h"
 
 #include "mock_drm.h"
@@ -63,12 +64,12 @@ gpu_fill_dw(struct i915_vma *vma, u64 offset, unsigned long count, u32 value)
 			*cmd++ = value;
 		} else if (gen >= 4) {
 			*cmd++ = MI_STORE_DWORD_IMM_GEN4 |
-				(gen < 6 ? 1 << 22 : 0);
+				(gen < 6 ? MI_USE_GGTT : 0);
 			*cmd++ = 0;
 			*cmd++ = offset;
 			*cmd++ = value;
 		} else {
-			*cmd++ = MI_STORE_DWORD_IMM | 1 << 22;
+			*cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*cmd++ = offset;
 			*cmd++ = value;
 		}
@@ -170,22 +171,26 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	if (err)
 		goto err_request;
 
-	i915_vma_move_to_active(batch, rq, 0);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
+
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
+
 	i915_gem_object_set_active_reference(batch->obj);
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
 
-	i915_vma_move_to_active(vma, rq, 0);
 	i915_vma_unpin(vma);
 
-	reservation_object_lock(obj->resv, NULL);
-	reservation_object_add_excl_fence(obj->resv, &rq->fence);
-	reservation_object_unlock(obj->resv);
-
 	i915_request_add(rq);
 
 	return 0;
 
+skip_request:
+	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_batch:
@@ -248,9 +253,9 @@ static int cpu_check(struct drm_i915_gem_object *obj, unsigned int max)
 		}
 
 		for (; m < DW_PER_PAGE; m++) {
-			if (map[m] != 0xdeadbeef) {
+			if (map[m] != STACK_MAGIC) {
 				pr_err("Invalid value at page %d, offset %d: found %x expected %x\n",
-				       n, m, map[m], 0xdeadbeef);
+				       n, m, map[m], STACK_MAGIC);
 				err = -EINVAL;
 				goto out_unmap;
 			}
@@ -306,7 +311,7 @@ create_test_object(struct i915_gem_context *ctx,
 	if (err)
 		return ERR_PTR(err);
 
-	err = cpu_fill(obj, 0xdeadbeef);
+	err = cpu_fill(obj, STACK_MAGIC);
 	if (err) {
 		pr_err("Failed to fill object with cpu, err=%d\n",
 		       err);
@@ -336,11 +341,15 @@ static int igt_ctx_exec(void *arg)
 	bool first_shared_gtt = true;
 	int err = -ENODEV;
 
-	/* Create a few different contexts (with different mm) and write
+	/*
+	 * Create a few different contexts (with different mm) and write
 	 * through each ctx/mm using the GPU making sure those writes end
 	 * up in the expected pages of our obj.
 	 */
 
+	if (!DRIVER_CAPS(i915)->has_logical_contexts)
+		return 0;
+
 	file = mock_file(i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
@@ -367,6 +376,9 @@ static int igt_ctx_exec(void *arg)
 		}
 
 		for_each_engine(engine, i915, id) {
+			if (!engine->context_size)
+				continue; /* No logical context support in HW */
+
 			if (!intel_engine_can_store_dword(engine))
 				continue;
 
@@ -421,6 +433,111 @@ out_unlock:
 	return err;
 }
 
+static int igt_ctx_readonly(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj = NULL;
+	struct drm_file *file;
+	I915_RND_STATE(prng);
+	IGT_TIMEOUT(end_time);
+	LIST_HEAD(objects);
+	struct i915_gem_context *ctx;
+	struct i915_hw_ppgtt *ppgtt;
+	unsigned long ndwords, dw;
+	int err = -ENODEV;
+
+	/*
+	 * Create a few read-only objects (with the occasional writable object)
+	 * and try to write into these object checking that the GPU discards
+	 * any write to a read-only object.
+	 */
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	ctx = i915_gem_create_context(i915, file->driver_priv);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_unlock;
+	}
+
+	ppgtt = ctx->ppgtt ?: i915->mm.aliasing_ppgtt;
+	if (!ppgtt || !ppgtt->vm.has_read_only) {
+		err = 0;
+		goto out_unlock;
+	}
+
+	ndwords = 0;
+	dw = 0;
+	while (!time_after(jiffies, end_time)) {
+		struct intel_engine_cs *engine;
+		unsigned int id;
+
+		for_each_engine(engine, i915, id) {
+			if (!intel_engine_can_store_dword(engine))
+				continue;
+
+			if (!obj) {
+				obj = create_test_object(ctx, file, &objects);
+				if (IS_ERR(obj)) {
+					err = PTR_ERR(obj);
+					goto out_unlock;
+				}
+
+				if (prandom_u32_state(&prng) & 1)
+					i915_gem_object_set_readonly(obj);
+			}
+
+			intel_runtime_pm_get(i915);
+			err = gpu_fill(obj, ctx, engine, dw);
+			intel_runtime_pm_put(i915);
+			if (err) {
+				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
+				       ndwords, dw, max_dwords(obj),
+				       engine->name, ctx->hw_id,
+				       yesno(!!ctx->ppgtt), err);
+				goto out_unlock;
+			}
+
+			if (++dw == max_dwords(obj)) {
+				obj = NULL;
+				dw = 0;
+			}
+			ndwords++;
+		}
+	}
+	pr_info("Submitted %lu dwords (across %u engines)\n",
+		ndwords, INTEL_INFO(i915)->num_rings);
+
+	dw = 0;
+	list_for_each_entry(obj, &objects, st_link) {
+		unsigned int rem =
+			min_t(unsigned int, ndwords - dw, max_dwords(obj));
+		unsigned int num_writes;
+
+		num_writes = rem;
+		if (i915_gem_object_is_readonly(obj))
+			num_writes = 0;
+
+		err = cpu_check(obj, num_writes);
+		if (err)
+			break;
+
+		dw += rem;
+	}
+
+out_unlock:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	mock_file_free(i915, file);
+	return err;
+}
+
 static __maybe_unused const char *
 __engine_name(struct drm_i915_private *i915, unsigned int engines)
 {
@@ -467,7 +584,9 @@ static int __igt_switch_to_kernel_context(struct drm_i915_private *i915,
 		}
 	}
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
@@ -586,7 +705,7 @@ int i915_gem_context_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
@@ -595,10 +714,14 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_switch_to_kernel_context),
 		SUBTEST(igt_ctx_exec),
+		SUBTEST(igt_ctx_readonly),
 	};
 	bool fake_alias = false;
 	int err;
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		return 0;
+
 	/* Install a fake aliasing gtt for exercise */
 	if (USES_PPGTT(dev_priv) && !dev_priv->mm.aliasing_ppgtt) {
 		mutex_lock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
index 89dc25a5a53b..a7055b12e53c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
@@ -389,7 +389,7 @@ int i915_gem_dmabuf_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	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 2dc72a984d45..128ad1cf0647 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -490,7 +490,7 @@ int i915_gem_evict_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
@@ -500,5 +500,8 @@ int i915_gem_evict_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_evict_contexts),
 	};
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index a4060238bef0..8e2e269db97e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -32,6 +32,20 @@
 #include "mock_drm.h"
 #include "mock_gem_device.h"
 
+static void cleanup_freed_objects(struct drm_i915_private *i915)
+{
+	/*
+	 * As we may hold onto the struct_mutex for inordinate lengths of
+	 * time, the NMI khungtaskd detector may fire for the free objects
+	 * worker.
+	 */
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	i915_gem_drain_freed_objects(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+}
+
 static void fake_free_pages(struct drm_i915_gem_object *obj,
 			    struct sg_table *pages)
 {
@@ -134,7 +148,7 @@ static int igt_ppgtt_alloc(void *arg)
 {
 	struct drm_i915_private *dev_priv = arg;
 	struct i915_hw_ppgtt *ppgtt;
-	u64 size, last;
+	u64 size, last, limit;
 	int err = 0;
 
 	/* Allocate a ppggt and try to fill the entire range */
@@ -142,20 +156,25 @@ static int igt_ppgtt_alloc(void *arg)
 	if (!USES_PPGTT(dev_priv))
 		return 0;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	ppgtt = __hw_ppgtt_create(dev_priv);
-	if (IS_ERR(ppgtt)) {
-		err = PTR_ERR(ppgtt);
-		goto err_unlock;
-	}
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
 	if (!ppgtt->vm.allocate_va_range)
 		goto err_ppgtt_cleanup;
 
+	/*
+	 * While we only allocate the page tables here and so we could
+	 * address a much larger GTT than we could actually fit into
+	 * RAM, a practical limit is the amount of physical pages in the system.
+	 * This should ensure that we do not run into the oomkiller during
+	 * the test and take down the machine wilfully.
+	 */
+	limit = totalram_pages << PAGE_SHIFT;
+	limit = min(ppgtt->vm.total, limit);
+
 	/* Check we can allocate the entire range */
-	for (size = 4096;
-	     size <= ppgtt->vm.total;
-	     size <<= 2) {
+	for (size = 4096; size <= limit; size <<= 2) {
 		err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, size);
 		if (err) {
 			if (err == -ENOMEM) {
@@ -166,13 +185,13 @@ static int igt_ppgtt_alloc(void *arg)
 			goto err_ppgtt_cleanup;
 		}
 
+		cond_resched();
+
 		ppgtt->vm.clear_range(&ppgtt->vm, 0, size);
 	}
 
 	/* Check we can incrementally allocate the entire range */
-	for (last = 0, size = 4096;
-	     size <= ppgtt->vm.total;
-	     last = size, size <<= 2) {
+	for (last = 0, size = 4096; size <= limit; last = size, size <<= 2) {
 		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
 						  last, size - last);
 		if (err) {
@@ -183,12 +202,13 @@ static int igt_ppgtt_alloc(void *arg)
 			}
 			goto err_ppgtt_cleanup;
 		}
+
+		cond_resched();
 	}
 
 err_ppgtt_cleanup:
-	ppgtt->vm.cleanup(&ppgtt->vm);
-	kfree(ppgtt);
-err_unlock:
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_ppgtt_put(ppgtt);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return err;
 }
@@ -291,6 +311,8 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 		i915_gem_object_put(obj);
 
 		kfree(order);
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -519,6 +541,7 @@ static int fill_hole(struct drm_i915_private *i915,
 		}
 
 		close_object_list(&objects, vm);
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -605,6 +628,8 @@ err_put:
 		i915_gem_object_put(obj);
 		if (err)
 			return err;
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -789,6 +814,8 @@ err_obj:
 		kfree(order);
 		if (err)
 			return err;
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -857,6 +884,7 @@ static int __shrink_hole(struct drm_i915_private *i915,
 	}
 
 	close_object_list(&objects, vm);
+	cleanup_freed_objects(i915);
 	return err;
 }
 
@@ -949,6 +977,7 @@ 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);
 	}
 
 	return 0;
@@ -980,7 +1009,7 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 		return PTR_ERR(file);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt = i915_ppgtt_create(dev_priv, file->driver_priv, "mock");
+	ppgtt = i915_ppgtt_create(dev_priv, file->driver_priv);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
@@ -1215,6 +1244,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
+	const u64 limit = totalram_pages << PAGE_SHIFT;
 	struct i915_gem_context *ctx;
 	struct i915_hw_ppgtt *ppgtt;
 	IGT_TIMEOUT(end_time);
@@ -1227,7 +1257,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 	ppgtt = ctx->ppgtt;
 	GEM_BUG_ON(!ppgtt);
 
-	err = func(i915, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
+	err = func(i915, &ppgtt->vm, 0, min(ppgtt->vm.total, limit), end_time);
 
 	mock_context_close(ctx);
 	return err;
@@ -1644,7 +1674,7 @@ int i915_gem_gtt_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 2b2dde94526f..c69cbd5aed52 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -169,9 +169,16 @@ static u64 tiled_offset(const struct tile *tile, u64 v)
 		v += y * tile->width;
 		v += div64_u64_rem(x, tile->width, &x) << tile->size;
 		v += x;
-	} else {
+	} else if (tile->width == 128) {
 		const unsigned int ytile_span = 16;
-		const unsigned int ytile_height = 32 * ytile_span;
+		const unsigned int ytile_height = 512;
+
+		v += y * ytile_span;
+		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
+		v += x;
+	} else {
+		const unsigned int ytile_span = 32;
+		const unsigned int ytile_height = 256;
 
 		v += y * ytile_span;
 		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
@@ -288,6 +295,8 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 		kunmap(p);
 		if (err)
 			return err;
+
+		i915_vma_destroy(vma);
 	}
 
 	return 0;
@@ -347,6 +356,14 @@ static int igt_partial_tiling(void *arg)
 		unsigned int pitch;
 		struct tile tile;
 
+		if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+			/*
+			 * The swizzling pattern is actually unknown as it
+			 * varies based on physical address of each page.
+			 * See i915_gem_detect_bit_6_swizzle().
+			 */
+			break;
+
 		tile.tiling = tiling;
 		switch (tiling) {
 		case I915_TILING_X:
@@ -357,7 +374,8 @@ static int igt_partial_tiling(void *arg)
 			break;
 		}
 
-		if (tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN ||
+		GEM_BUG_ON(tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN);
+		if (tile.swizzle == I915_BIT_6_SWIZZLE_9_17 ||
 		    tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
 			continue;
 
@@ -454,12 +472,14 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		return PTR_ERR(rq);
 	}
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+
 	i915_request_add(rq);
 
-	i915_gem_object_set_active_reference(obj);
+	__i915_gem_object_release_unless_active(obj);
 	i915_vma_unpin(vma);
-	return 0;
+
+	return err;
 }
 
 static bool assert_mmap_offset(struct drm_i915_private *i915,
@@ -488,6 +508,15 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	u64 hole_start, hole_end;
 	int loop, err;
 
+	/* Disable background reaper */
+	mutex_lock(&i915->drm.struct_mutex);
+	if (!i915->gt.active_requests++)
+		i915_gem_unpark(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	cancel_delayed_work_sync(&i915->gt.retire_work);
+	cancel_delayed_work_sync(&i915->gt.idle_work);
+	GEM_BUG_ON(!i915->gt.awake);
+
 	/* 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) {
@@ -496,7 +525,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		err = drm_mm_reserve_node(mm, &resv);
 		if (err) {
 			pr_err("Failed to trim VMA manager, err=%d\n", err);
-			return err;
+			goto out_park;
 		}
 		break;
 	}
@@ -538,6 +567,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 	/* Now fill with busy dead objects that we expect to reap */
 	for (loop = 0; loop < 3; loop++) {
+		if (i915_terminally_wedged(&i915->gpu_error))
+			break;
+
 		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
@@ -554,6 +586,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 			goto err_obj;
 		}
 
+		/* NB we rely on the _active_ reference to access obj now */
 		GEM_BUG_ON(!i915_gem_object_is_active(obj));
 		err = i915_gem_object_create_mmap_offset(obj);
 		if (err) {
@@ -565,6 +598,13 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 out:
 	drm_mm_remove_node(&resv);
+out_park:
+	mutex_lock(&i915->drm.struct_mutex);
+	if (--i915->gt.active_requests)
+		queue_delayed_work(i915->wq, &i915->gt.retire_work, 0);
+	else
+		queue_delayed_work(i915->wq, &i915->gt.idle_work, 0);
+	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 err_obj:
 	i915_gem_object_put(obj);
@@ -586,7 +626,7 @@ int i915_gem_object_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 63cd9486cc13..c4aac6141e04 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -262,7 +262,7 @@ int i915_request_mock_selftests(void)
 		return -ENOMEM;
 
 	err = i915_subtests(tests, i915);
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 
 	return err;
 }
@@ -286,7 +286,9 @@ static int begin_live_test(struct live_test *t,
 	t->func = func;
 	t->name = name;
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
 		       func, name, err);
@@ -594,11 +596,8 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 	} else if (gen >= 6) {
 		*cmd++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*cmd++ = lower_32_bits(vma->node.start);
-	} else if (gen >= 4) {
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
-		*cmd++ = lower_32_bits(vma->node.start);
 	} else {
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT | 1;
+		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
 		*cmd++ = lower_32_bits(vma->node.start);
 	}
 	*cmd++ = MI_BATCH_BUFFER_END; /* terminate early in case of error */
@@ -678,7 +677,9 @@ static int live_all_engines(void *arg)
 			i915_gem_object_set_active_reference(batch->obj);
 		}
 
-		i915_vma_move_to_active(batch, request[id], 0);
+		err = i915_vma_move_to_active(batch, request[id], 0);
+		GEM_BUG_ON(err);
+
 		i915_request_get(request[id]);
 		i915_request_add(request[id]);
 	}
@@ -788,7 +789,9 @@ static int live_sequential_engines(void *arg)
 		GEM_BUG_ON(err);
 		request[id]->batch = batch;
 
-		i915_vma_move_to_active(batch, request[id], 0);
+		err = i915_vma_move_to_active(batch, request[id], 0);
+		GEM_BUG_ON(err);
+
 		i915_gem_object_set_active_reference(batch->obj);
 		i915_vma_get(batch);
 
@@ -862,5 +865,9 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_sequential_engines),
 		SUBTEST(live_empty_request),
 	};
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index addc5a599c4a..86c54ea37f48 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -210,6 +210,8 @@ int __i915_subtests(const char *caller,
 			return -EINTR;
 
 		pr_debug(DRIVER_NAME ": Running %s/%s\n", caller, st->name);
+		GEM_TRACE("Running %s/%s\n", caller, st->name);
+
 		err = st->func(data);
 		if (err && err != -EINTR) {
 			pr_err(DRIVER_NAME "/%s: %s failed with error %d\n",
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 8400a8cc5cf2..ffa74290e054 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -733,7 +733,7 @@ int i915_vma_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 0d06f559243f..af66e3d4e23a 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -9,52 +9,8 @@
 #include "../i915_selftest.h"
 #include "igt_flush_test.h"
 
-struct wedge_me {
-	struct delayed_work work;
-	struct drm_i915_private *i915;
-	const void *symbol;
-};
-
-static void wedge_me(struct work_struct *work)
-{
-	struct wedge_me *w = container_of(work, typeof(*w), work.work);
-
-	pr_err("%pS timed out, cancelling all further testing.\n", w->symbol);
-
-	GEM_TRACE("%pS timed out.\n", w->symbol);
-	GEM_TRACE_DUMP();
-
-	i915_gem_set_wedged(w->i915);
-}
-
-static void __init_wedge(struct wedge_me *w,
-			 struct drm_i915_private *i915,
-			 long timeout,
-			 const void *symbol)
-{
-	w->i915 = i915;
-	w->symbol = symbol;
-
-	INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
-	schedule_delayed_work(&w->work, timeout);
-}
-
-static void __fini_wedge(struct wedge_me *w)
-{
-	cancel_delayed_work_sync(&w->work);
-	destroy_delayed_work_on_stack(&w->work);
-	w->i915 = NULL;
-}
-
-#define wedge_on_timeout(W, DEV, TIMEOUT)				\
-	for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \
-	     (W)->i915;							\
-	     __fini_wedge((W)))
-
 int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 {
-	struct wedge_me w;
-
 	cond_resched();
 
 	if (flags & I915_WAIT_LOCKED &&
@@ -63,8 +19,15 @@ int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 		i915_gem_set_wedged(i915);
 	}
 
-	wedge_on_timeout(&w, i915, HZ)
-		i915_gem_wait_for_idle(i915, flags);
+	if (i915_gem_wait_for_idle(i915, flags, HZ / 5) == -ETIME) {
+		pr_err("%pS timed out, cancelling all further testing.\n",
+		       __builtin_return_address(0));
+
+		GEM_TRACE("%pS timed out.\n", __builtin_return_address(0));
+		GEM_TRACE_DUMP();
+
+		i915_gem_set_wedged(i915);
+	}
 
 	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
 }
diff --git a/drivers/gpu/drm/i915/selftests/igt_wedge_me.h b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
new file mode 100644
index 000000000000..08e5ff11bbd9
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
@@ -0,0 +1,58 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#ifndef IGT_WEDGE_ME_H
+#define IGT_WEDGE_ME_H
+
+#include <linux/workqueue.h>
+
+#include "../i915_gem.h"
+
+struct drm_i915_private;
+
+struct igt_wedge_me {
+	struct delayed_work work;
+	struct drm_i915_private *i915;
+	const char *name;
+};
+
+static void __igt_wedge_me(struct work_struct *work)
+{
+	struct igt_wedge_me *w = container_of(work, typeof(*w), work.work);
+
+	pr_err("%s timed out, cancelling test.\n", w->name);
+
+	GEM_TRACE("%s timed out.\n", w->name);
+	GEM_TRACE_DUMP();
+
+	i915_gem_set_wedged(w->i915);
+}
+
+static void __igt_init_wedge(struct igt_wedge_me *w,
+			     struct drm_i915_private *i915,
+			     long timeout,
+			     const char *name)
+{
+	w->i915 = i915;
+	w->name = name;
+
+	INIT_DELAYED_WORK_ONSTACK(&w->work, __igt_wedge_me);
+	schedule_delayed_work(&w->work, timeout);
+}
+
+static void __igt_fini_wedge(struct igt_wedge_me *w)
+{
+	cancel_delayed_work_sync(&w->work);
+	destroy_delayed_work_on_stack(&w->work);
+	w->i915 = NULL;
+}
+
+#define igt_wedge_on_timeout(W, DEV, TIMEOUT)				\
+	for (__igt_init_wedge((W), (DEV), (TIMEOUT), __func__);		\
+	     (W)->i915;							\
+	     __igt_fini_wedge((W)))
+
+#endif /* IGT_WEDGE_ME_H */
diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
index d6926e7820e5..f03b407fdbe2 100644
--- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
@@ -464,7 +464,7 @@ int intel_breadcrumbs_mock_selftests(void)
 		return -ENOMEM;
 
 	err = i915_subtests(tests, i915->engine[RCS]);
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_guc.c b/drivers/gpu/drm/i915/selftests/intel_guc.c
index fb74e2cf8a0a..407c98fb9170 100644
--- a/drivers/gpu/drm/i915/selftests/intel_guc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_guc.c
@@ -196,19 +196,23 @@ static int igt_guc_clients(void *args)
 	}
 
 	unreserve_doorbell(guc->execbuf_client);
-	err = guc_clients_doorbell_init(guc);
+
+	__create_doorbell(guc->execbuf_client);
+	err = __guc_allocate_doorbell(guc, guc->execbuf_client->stage_id);
 	if (err != -EIO) {
 		pr_err("unexpected (err = %d)", err);
-		goto out;
+		goto out_db;
 	}
 
 	if (!available_dbs(guc, guc->execbuf_client->priority)) {
 		pr_err("doorbell not available when it should\n");
 		err = -EIO;
-		goto out;
+		goto out_db;
 	}
 
+out_db:
 	/* clean after test */
+	__destroy_doorbell(guc->execbuf_client);
 	err = reserve_doorbell(guc->execbuf_client);
 	if (err) {
 		pr_err("failed to reserve back the doorbell back\n");
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index fe7d3190ebfe..65d66cdedd26 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -27,6 +27,7 @@
 #include "../i915_selftest.h"
 #include "i915_random.h"
 #include "igt_flush_test.h"
+#include "igt_wedge_me.h"
 
 #include "mock_context.h"
 #include "mock_drm.h"
@@ -130,13 +131,19 @@ static int emit_recurse_batch(struct hang *h,
 	if (err)
 		goto unpin_vma;
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
 		i915_gem_object_set_active_reference(vma->obj);
 	}
 
-	i915_vma_move_to_active(hws, rq, 0);
+	err = i915_vma_move_to_active(hws, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(hws->obj)) {
 		i915_gem_object_get(hws->obj);
 		i915_gem_object_set_active_reference(hws->obj);
@@ -171,7 +178,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else if (INTEL_GEN(i915) >= 4) {
-		*batch++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
@@ -184,7 +191,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else {
-		*batch++ = MI_STORE_DWORD_IMM;
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
 		*batch++ = MI_ARB_CHECK;
@@ -193,7 +200,7 @@ static int emit_recurse_batch(struct hang *h,
 		batch += 1024 / sizeof(*batch);
 
 		*batch++ = MI_ARB_CHECK;
-		*batch++ = MI_BATCH_BUFFER_START | 2 << 6 | 1;
+		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	}
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
@@ -205,6 +212,7 @@ static int emit_recurse_batch(struct hang *h,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
 
+unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
@@ -914,7 +922,7 @@ static u32 fake_hangcheck(struct i915_request *rq, u32 mask)
 	return reset_count;
 }
 
-static int igt_wait_reset(void *arg)
+static int igt_reset_wait(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_request *rq;
@@ -988,6 +996,170 @@ unlock:
 	return err;
 }
 
+struct evict_vma {
+	struct completion completion;
+	struct i915_vma *vma;
+};
+
+static int evict_vma(void *data)
+{
+	struct evict_vma *arg = data;
+	struct i915_address_space *vm = arg->vma->vm;
+	struct drm_i915_private *i915 = vm->i915;
+	struct drm_mm_node evict = arg->vma->node;
+	int err;
+
+	complete(&arg->completion);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = i915_gem_evict_for_node(vm, &evict, 0);
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	return err;
+}
+
+static int __igt_reset_evict_vma(struct drm_i915_private *i915,
+				 struct i915_address_space *vm)
+{
+	struct drm_i915_gem_object *obj;
+	struct task_struct *tsk = NULL;
+	struct i915_request *rq;
+	struct evict_vma arg;
+	struct hang h;
+	int err;
+
+	if (!intel_engine_can_store_dword(i915->engine[RCS]))
+		return 0;
+
+	/* Check that we can recover an unbind stuck on a hanging request */
+
+	global_reset_lock(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = hang_init(&h, i915);
+	if (err)
+		goto unlock;
+
+	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto fini;
+	}
+
+	arg.vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(arg.vma)) {
+		err = PTR_ERR(arg.vma);
+		goto out_obj;
+	}
+
+	rq = hang_create_request(&h, i915->engine[RCS]);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_obj;
+	}
+
+	err = i915_vma_pin(arg.vma, 0, 0,
+			   i915_vma_is_ggtt(arg.vma) ? PIN_GLOBAL : PIN_USER);
+	if (err)
+		goto out_obj;
+
+	err = i915_vma_move_to_active(arg.vma, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unpin(arg.vma);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (err)
+		goto out_rq;
+
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	if (!wait_until_running(&h, rq)) {
+		struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+		pr_err("%s: Failed to start request %x, at %x\n",
+		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
+
+		i915_gem_set_wedged(i915);
+		goto out_reset;
+	}
+
+	init_completion(&arg.completion);
+
+	tsk = kthread_run(evict_vma, &arg, "igt/evict_vma");
+	if (IS_ERR(tsk)) {
+		err = PTR_ERR(tsk);
+		tsk = NULL;
+		goto out_reset;
+	}
+
+	wait_for_completion(&arg.completion);
+
+	if (wait_for(waitqueue_active(&rq->execute), 10)) {
+		struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+		pr_err("igt/evict_vma kthread did not wait\n");
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
+
+		i915_gem_set_wedged(i915);
+		goto out_reset;
+	}
+
+out_reset:
+	fake_hangcheck(rq, intel_engine_flag(rq->engine));
+
+	if (tsk) {
+		struct igt_wedge_me w;
+
+		/* The reset, even indirectly, should take less than 10ms. */
+		igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/)
+			err = kthread_stop(tsk);
+	}
+
+	mutex_lock(&i915->drm.struct_mutex);
+out_rq:
+	i915_request_put(rq);
+out_obj:
+	i915_gem_object_put(obj);
+fini:
+	hang_fini(&h);
+unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	global_reset_unlock(i915);
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO;
+
+	return err;
+}
+
+static int igt_reset_evict_ggtt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+
+	return __igt_reset_evict_vma(i915, &i915->ggtt.vm);
+}
+
+static int igt_reset_evict_ppgtt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx;
+	int err;
+
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = kernel_context(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	err = 0;
+	if (ctx->ppgtt) /* aliasing == global gtt locking, covered above */
+		err = __igt_reset_evict_vma(i915, &ctx->ppgtt->vm);
+
+	kernel_context_close(ctx);
+	return err;
+}
+
 static int wait_for_others(struct drm_i915_private *i915,
 			   struct intel_engine_cs *exclude)
 {
@@ -1233,8 +1405,10 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_reset_idle_engine),
 		SUBTEST(igt_reset_active_engine),
 		SUBTEST(igt_reset_engines),
-		SUBTEST(igt_wait_reset),
 		SUBTEST(igt_reset_queue),
+		SUBTEST(igt_reset_wait),
+		SUBTEST(igt_reset_evict_ggtt),
+		SUBTEST(igt_reset_evict_ppgtt),
 		SUBTEST(igt_handle_error),
 	};
 	bool saved_hangcheck;
@@ -1243,6 +1417,9 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	if (!intel_has_gpu_reset(i915))
 		return 0;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO; /* we're long past hope of a successful reset */
+
 	intel_runtime_pm_get(i915);
 	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index ea27c7cfbf96..582566faef09 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -104,13 +104,19 @@ static int emit_recurse_batch(struct spinner *spin,
 	if (err)
 		goto unpin_vma;
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
 		i915_gem_object_set_active_reference(vma->obj);
 	}
 
-	i915_vma_move_to_active(hws, rq, 0);
+	err = i915_vma_move_to_active(hws, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(hws->obj)) {
 		i915_gem_object_get(hws->obj);
 		i915_gem_object_set_active_reference(hws->obj);
@@ -134,6 +140,7 @@ static int emit_recurse_batch(struct spinner *spin,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0);
 
+unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
@@ -444,16 +451,134 @@ err_wedged:
 	goto err_ctx_lo;
 }
 
+static int live_preempt_hang(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx_hi, *ctx_lo;
+	struct spinner spin_hi, spin_lo;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+		return 0;
+
+	if (!intel_has_reset_engine(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	if (spinner_init(&spin_hi, i915))
+		goto err_unlock;
+
+	if (spinner_init(&spin_lo, i915))
+		goto err_spin_hi;
+
+	ctx_hi = kernel_context(i915);
+	if (!ctx_hi)
+		goto err_spin_lo;
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+
+	ctx_lo = kernel_context(i915);
+	if (!ctx_lo)
+		goto err_ctx_hi;
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		rq = spinner_create_request(&spin_lo, ctx_lo, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin_lo, rq)) {
+			GEM_TRACE("lo spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		rq = spinner_create_request(&spin_hi, ctx_hi, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			spinner_end(&spin_lo);
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		init_completion(&engine->execlists.preempt_hang.completion);
+		engine->execlists.preempt_hang.inject_hang = true;
+
+		i915_request_add(rq);
+
+		if (!wait_for_completion_timeout(&engine->execlists.preempt_hang.completion,
+						 HZ / 10)) {
+			pr_err("Preemption did not occur within timeout!");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		i915_reset_engine(engine, NULL);
+		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+
+		engine->execlists.preempt_hang.inject_hang = false;
+
+		if (!wait_for_spinner(&spin_hi, rq)) {
+			GEM_TRACE("hi spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		spinner_end(&spin_hi);
+		spinner_end(&spin_lo);
+		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+	}
+
+	err = 0;
+err_ctx_lo:
+	kernel_context_close(ctx_lo);
+err_ctx_hi:
+	kernel_context_close(ctx_hi);
+err_spin_lo:
+	spinner_fini(&spin_lo);
+err_spin_hi:
+	spinner_fini(&spin_hi);
+err_unlock:
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
 int intel_execlists_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_sanitycheck),
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
+		SUBTEST(live_preempt_hang),
 	};
 
 	if (!HAS_EXECLISTS(i915))
 		return 0;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index e1ea2d2bedd2..0d39b3bf0c0d 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -6,6 +6,7 @@
 
 #include "../i915_selftest.h"
 
+#include "igt_wedge_me.h"
 #include "mock_context.h"
 
 static struct drm_i915_gem_object *
@@ -49,6 +50,10 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 		goto err_pin;
 	}
 
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto err_req;
+
 	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
 	if (INTEL_GEN(ctx->i915) >= 8)
 		srm++;
@@ -67,11 +72,6 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
-
 	i915_gem_object_get(result);
 	i915_gem_object_set_active_reference(result);
 
@@ -112,6 +112,7 @@ static int check_whitelist(const struct whitelist *w,
 			   struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_object *results;
+	struct igt_wedge_me wedge;
 	u32 *vaddr;
 	int err;
 	int i;
@@ -120,7 +121,11 @@ static int check_whitelist(const struct whitelist *w,
 	if (IS_ERR(results))
 		return PTR_ERR(results);
 
-	err = i915_gem_object_set_to_cpu_domain(results, false);
+	err = 0;
+	igt_wedge_on_timeout(&wedge, ctx->i915, HZ / 5) /* a safety net! */
+		err = i915_gem_object_set_to_cpu_domain(results, false);
+	if (i915_terminally_wedged(&ctx->i915->gpu_error))
+		err = -EIO;
 	if (err)
 		goto out_put;
 
@@ -283,6 +288,9 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915)
 	};
 	int err;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index c2a0451336cf..22a73da45ad5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -200,6 +200,8 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.submit_request = mock_submit_request;
 
 	i915_timeline_init(i915, &engine->base.timeline, engine->base.name);
+	lockdep_set_subclass(&engine->base.timeline.lock, TIMELINE_ENGINE);
+
 	intel_engine_init_breadcrumbs(&engine->base);
 	engine->base.breadcrumbs.mock = true; /* prevent touching HW for irqs */
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index c97075c5ccaf..43ed8b28aeaa 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -157,7 +157,8 @@ struct drm_i915_private *mock_gem_device(void)
 	dev_pm_domain_set(&pdev->dev, &pm_domain);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	WARN_ON(pm_runtime_get_sync(&pdev->dev));
+	if (pm_runtime_enabled(&pdev->dev))
+		WARN_ON(pm_runtime_get_sync(&pdev->dev));
 
 	i915 = (struct drm_i915_private *)(pdev + 1);
 	pci_set_drvdata(pdev, i915);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 6a7f4da7b523..a140ea5c3a7c 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -70,12 +70,7 @@ mock_ppgtt(struct drm_i915_private *i915,
 	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
 	ppgtt->vm.file = ERR_PTR(-ENODEV);
 
-	INIT_LIST_HEAD(&ppgtt->vm.active_list);
-	INIT_LIST_HEAD(&ppgtt->vm.inactive_list);
-	INIT_LIST_HEAD(&ppgtt->vm.unbound_list);
-
-	INIT_LIST_HEAD(&ppgtt->vm.global_link);
-	drm_mm_init(&ppgtt->vm.mm, 0, ppgtt->vm.total);
+	i915_address_space_init(&ppgtt->vm, i915);
 
 	ppgtt->vm.clear_range = nop_clear_range;
 	ppgtt->vm.insert_page = mock_insert_page;
@@ -106,8 +101,6 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
 
-	INIT_LIST_HEAD(&i915->vm_list);
-
 	ggtt->vm.i915 = i915;
 
 	ggtt->gmadr = (struct resource) DEFINE_RES_MEM(0, 2048 * PAGE_SIZE);
@@ -124,7 +117,7 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
 	ggtt->vm.vma_ops.clear_pages = clear_pages;
 
-	i915_address_space_init(&ggtt->vm, i915, "global");
+	i915_address_space_init(&ggtt->vm, i915);
 }
 
 void mock_fini_ggtt(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index 3b7acb5a70b3..435a2c35ee8c 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -69,7 +69,7 @@ enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt)
 	}
 }
 
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
+void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
 {
 	struct drm_encoder *encoder = &intel_dsi->base.base;
 	struct drm_device *dev = encoder->dev;
@@ -342,11 +342,15 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 			pipe_config->cpu_transcoder = TRANSCODER_DSI_C;
 		else
 			pipe_config->cpu_transcoder = TRANSCODER_DSI_A;
-	}
 
-	ret = intel_compute_dsi_pll(encoder, pipe_config);
-	if (ret)
-		return false;
+		ret = bxt_dsi_pll_compute(encoder, pipe_config);
+		if (ret)
+			return false;
+	} else {
+		ret = vlv_dsi_pll_compute(encoder, pipe_config);
+		if (ret)
+			return false;
+	}
 
 	pipe_config->clock_set = true;
 
@@ -546,12 +550,12 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_device_ready(encoder);
-	else if (IS_BROXTON(dev_priv))
-		bxt_dsi_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
+	if (IS_GEMINILAKE(dev_priv))
 		glk_dsi_device_ready(encoder);
+	else if (IS_GEN9_LP(dev_priv))
+		bxt_dsi_device_ready(encoder);
+	else
+		vlv_dsi_device_ready(encoder);
 }
 
 static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
@@ -810,8 +814,13 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	 * The BIOS may leave the PLL in a wonky state where it doesn't
 	 * lock. It needs to be fully powered down to fix it.
 	 */
-	intel_disable_dsi_pll(encoder);
-	intel_enable_dsi_pll(encoder, pipe_config);
+	if (IS_GEN9_LP(dev_priv)) {
+		bxt_dsi_pll_disable(encoder);
+		bxt_dsi_pll_enable(encoder, pipe_config);
+	} else {
+		vlv_dsi_pll_disable(encoder);
+		vlv_dsi_pll_enable(encoder, pipe_config);
+	}
 
 	if (IS_BROXTON(dev_priv)) {
 		/* Add MIPI IO reset programming for modeset */
@@ -929,11 +938,10 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv) ||
-	    IS_BROXTON(dev_priv))
-		vlv_dsi_clear_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
+	if (IS_GEMINILAKE(dev_priv))
 		glk_dsi_clear_device_ready(encoder);
+	else
+		vlv_dsi_clear_device_ready(encoder);
 }
 
 static void intel_dsi_post_disable(struct intel_encoder *encoder,
@@ -949,7 +957,7 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports)
-			wait_for_dsi_fifo_empty(intel_dsi, port);
+			vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
 
 		intel_dsi_port_disable(encoder);
 		usleep_range(2000, 5000);
@@ -979,11 +987,13 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 				val & ~MIPIO_RST_CTRL);
 	}
 
-	intel_disable_dsi_pll(encoder);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv)) {
+		bxt_dsi_pll_disable(encoder);
+	} else {
 		u32 val;
 
+		vlv_dsi_pll_disable(encoder);
+
 		val = I915_READ(DSPCLK_GATE_D);
 		val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
 		I915_WRITE(DSPCLK_GATE_D, val);
@@ -1024,7 +1034,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	 * configuration, otherwise accessing DSI registers will hang the
 	 * machine. See BSpec North Display Engine registers/MIPI[BXT].
 	 */
-	if (IS_GEN9_LP(dev_priv) && !intel_dsi_pll_is_enabled(dev_priv))
+	if (IS_GEN9_LP(dev_priv) && !bxt_dsi_pll_is_enabled(dev_priv))
 		goto out_put_power;
 
 	/* XXX: this only works for one DSI output */
@@ -1247,16 +1257,19 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
 
-	if (IS_GEN9_LP(dev_priv))
+	if (IS_GEN9_LP(dev_priv)) {
 		bxt_dsi_get_pipe_config(encoder, pipe_config);
+		pclk = bxt_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+					pipe_config);
+	} else {
+		pclk = vlv_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+					pipe_config);
+	}
 
-	pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
-				  pipe_config);
-	if (!pclk)
-		return;
-
-	pipe_config->base.adjusted_mode.crtc_clock = pclk;
-	pipe_config->port_clock = pclk;
+	if (pclk) {
+		pipe_config->base.adjusted_mode.crtc_clock = pclk;
+		pipe_config->port_clock = pclk;
+	}
 }
 
 static enum drm_mode_status
@@ -1585,20 +1598,24 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder)
 	enum port port;
 	u32 val;
 
-	if (!IS_GEMINILAKE(dev_priv)) {
-		for_each_dsi_port(port, intel_dsi->ports) {
-			/* Panel commands can be sent when clock is in LP11 */
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
+	if (IS_GEMINILAKE(dev_priv))
+		return;
 
-			intel_dsi_reset_clocks(encoder, port);
-			I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
+	for_each_dsi_port(port, intel_dsi->ports) {
+		/* Panel commands can be sent when clock is in LP11 */
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
 
-			val = I915_READ(MIPI_DSI_FUNC_PRG(port));
-			val &= ~VID_MODE_FORMAT_MASK;
-			I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+		if (IS_GEN9_LP(dev_priv))
+			bxt_dsi_reset_clocks(encoder, port);
+		else
+			vlv_dsi_reset_clocks(encoder, port);
+		I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
-		}
+		val = I915_READ(MIPI_DSI_FUNC_PRG(port));
+		val &= ~VID_MODE_FORMAT_MASK;
+		I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
 	}
 }
 
@@ -1713,7 +1730,7 @@ static void intel_dsi_add_properties(struct intel_connector *connector)
 	}
 }
 
-void intel_dsi_init(struct drm_i915_private *dev_priv)
+void vlv_dsi_init(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_dsi *intel_dsi;
@@ -1730,14 +1747,10 @@ void intel_dsi_init(struct drm_i915_private *dev_priv)
 	if (!intel_bios_is_dsi_present(dev_priv, &port))
 		return;
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
-	} else if (IS_GEN9_LP(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv))
 		dev_priv->mipi_mmio_base = BXT_MIPI_BASE;
-	} else {
-		DRM_ERROR("Unsupported Mipi device to reg base");
-		return;
-	}
+	else
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
 
 	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
 	if (!intel_dsi)
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/vlv_dsi_pll.c
index 2ff2ee7f3b78..a132a8037ecc 100644
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ b/drivers/gpu/drm/i915/vlv_dsi_pll.c
@@ -111,8 +111,8 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
  * XXX: The muxing and gating is hard coded for now. Need to add support for
  * sharing PLLs with two DSI outputs.
  */
-static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
+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);
@@ -142,8 +142,8 @@ static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
+void vlv_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
@@ -175,7 +175,7 @@ static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("DSI PLL locked\n");
 }
 
-static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
+void vlv_dsi_pll_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 tmp;
@@ -192,7 +192,7 @@ static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
-static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
+bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
 {
 	bool enabled;
 	u32 val;
@@ -229,7 +229,7 @@ static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
 	return enabled;
 }
 
-static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
+void bxt_dsi_pll_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 val;
@@ -261,8 +261,8 @@ static void assert_bpp_mismatch(enum mipi_dsi_pixel_format fmt, int pipe_bpp)
 	     bpp, pipe_bpp);
 }
 
-static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
+u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     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);
@@ -327,8 +327,8 @@ static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	return pclk;
 }
 
-static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
+u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config)
 {
 	u32 pclk;
 	u32 dsi_clk;
@@ -357,16 +357,7 @@ static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	return pclk;
 }
 
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config)
-{
-	if (IS_GEN9_LP(to_i915(encoder->base.dev)))
-		return bxt_dsi_get_pclk(encoder, pipe_bpp, config);
-	else
-		return vlv_dsi_get_pclk(encoder, pipe_bpp, config);
-}
-
-static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+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);
@@ -480,8 +471,8 @@ static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port,
 	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
 }
 
-static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
+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);
@@ -528,8 +519,8 @@ static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
+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);
@@ -568,52 +559,7 @@ static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("DSI PLL locked\n");
 }
 
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
-{
-	if (IS_GEN9_LP(dev_priv))
-		return bxt_dsi_pll_is_enabled(dev_priv);
-
-	MISSING_CASE(INTEL_DEVID(dev_priv));
-
-	return false;
-}
-
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_compute_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		return gen9lp_compute_dsi_pll(encoder, config);
-
-	return -ENODEV;
-}
-
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_enable_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		gen9lp_enable_dsi_pll(encoder, config);
-}
-
-void intel_disable_dsi_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_disable_dsi_pll(encoder);
-	else if (IS_GEN9_LP(dev_priv))
-		bxt_disable_dsi_pll(encoder);
-}
-
-static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
-				    enum port port)
+void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 tmp;
 	struct drm_device *dev = encoder->base.dev;
@@ -638,13 +584,3 @@ static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
 	}
 	I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 }
-
-void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_GEN9_LP(dev_priv))
-		gen9lp_dsi_reset_clocks(encoder, port);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_reset_clocks(encoder, port);
-}
diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 1d053bbefc02..f0122afcf2a8 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -37,7 +37,6 @@
 
 struct imx_drm_device {
 	struct drm_device			*drm;
-	unsigned int				pipes;
 	struct drm_atomic_state			*state;
 };
 
@@ -229,7 +228,7 @@ static int imx_drm_bind(struct device *dev)
 	imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL);
 	if (!imxdrm) {
 		ret = -ENOMEM;
-		goto err_unref;
+		goto err_put;
 	}
 
 	imxdrm->drm = drm;
@@ -306,8 +305,8 @@ err_unbind:
 	component_unbind_all(drm->dev, drm);
 err_kms:
 	drm_mode_config_cleanup(drm);
-err_unref:
-	drm_dev_unref(drm);
+err_put:
+	drm_dev_put(drm);
 
 	return ret;
 }
@@ -327,7 +326,7 @@ static void imx_drm_unbind(struct device *dev)
 	component_unbind_all(drm->dev, drm);
 	dev_set_drvdata(dev, NULL);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops imx_drm_ops = {
diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index 15c2bec47a04..ab9c6f706eb3 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -10,7 +10,6 @@ struct drm_display_mode;
 struct drm_encoder;
 struct drm_framebuffer;
 struct drm_plane;
-struct imx_drm_crtc;
 struct platform_device;
 
 struct imx_crtc_state {
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 56dd7a9a8e25..3bd0f8a18e74 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -143,7 +143,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 		imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc);
 
 	if (imx_ldb_ch->edid) {
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 							imx_ldb_ch->edid);
 		num_modes = drm_add_edid_modes(connector, imx_ldb_ch->edid);
 	}
@@ -471,8 +471,7 @@ static int imx_ldb_register(struct drm_device *drm,
 		drm_connector_init(drm, &imx_ldb_ch->connector,
 				&imx_ldb_connector_funcs,
 				DRM_MODE_CONNECTOR_LVDS);
-		drm_mode_connector_attach_encoder(&imx_ldb_ch->connector,
-				encoder);
+		drm_connector_attach_encoder(&imx_ldb_ch->connector, encoder);
 	}
 
 	if (imx_ldb_ch->panel) {
@@ -612,6 +611,9 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		return PTR_ERR(imx_ldb->regmap);
 	}
 
+	/* disable LDB by resetting the control register to POR default */
+	regmap_write(imx_ldb->regmap, IOMUXC_GPR2, 0);
+
 	imx_ldb->dev = dev;
 
 	if (of_id)
@@ -652,14 +654,14 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data)
 		if (ret || i < 0 || i > 1)
 			return -EINVAL;
 
+		if (!of_device_is_available(child))
+			continue;
+
 		if (dual && i > 0) {
 			dev_warn(dev, "dual-channel mode, ignoring second output\n");
 			continue;
 		}
 
-		if (!of_device_is_available(child))
-			continue;
-
 		channel = &imx_ldb->channel[i];
 		channel->ldb = imx_ldb;
 		channel->chno = i;
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index bc27c2699464..cffd3310240e 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -235,7 +235,7 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, tve->ddc);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
@@ -493,7 +493,7 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve)
 	drm_connector_init(drm, &tve->connector, &imx_tve_connector_funcs,
 			   DRM_MODE_CONNECTOR_VGA);
 
-	drm_mode_connector_attach_encoder(&tve->connector, &tve->encoder);
+	drm_connector_attach_encoder(&tve->connector, &tve->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index 21d002859ae0..7d4b710b837a 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -35,7 +35,6 @@
 struct ipu_crtc {
 	struct device		*dev;
 	struct drm_crtc		base;
-	struct imx_drm_crtc	*imx_crtc;
 
 	/* plane[0] is the full plane, plane[1] is the partial plane */
 	struct ipu_plane	*plane[2];
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index aedecda9728a..aefd04e18f93 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -63,7 +63,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 	}
 
 	if (imxpd->edid) {
-		drm_mode_connector_update_edid_property(connector, imxpd->edid);
+		drm_connector_update_edid_property(connector, imxpd->edid);
 		num_modes = drm_add_edid_modes(connector, imxpd->edid);
 	}
 
@@ -197,7 +197,7 @@ static int imx_pd_register(struct drm_device *drm,
 			return ret;
 		}
 	} else {
-		drm_mode_connector_attach_encoder(&imxpd->connector, encoder);
+		drm_connector_attach_encoder(&imxpd->connector, encoder);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 658b8dd45b83..2d6aa150a9ff 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -539,6 +539,9 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int ret;
 	int i;
 
+	if (!path)
+		return 0;
+
 	for (i = 0; i < path_len; i++) {
 		enum mtk_ddp_comp_id comp_id = path[i];
 		struct device_node *node;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 8130f3dab661..87e4191c250e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -28,8 +28,12 @@
 #define DISP_REG_CONFIG_DISP_UFOE_MOUT_EN	0x050
 #define DISP_REG_CONFIG_DISP_COLOR0_SEL_IN	0x084
 #define DISP_REG_CONFIG_DISP_COLOR1_SEL_IN	0x088
+#define DISP_REG_CONFIG_DSIE_SEL_IN		0x0a4
+#define DISP_REG_CONFIG_DSIO_SEL_IN		0x0a8
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
-#define DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN	0x0c8
+#define DISP_REG_CONFIG_DISP_RDMA2_SOUT		0x0b8
+#define DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN	0x0c4
+#define DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN	0x0c8
 #define DISP_REG_CONFIG_MMSYS_CG_CON0		0x100
 
 #define DISP_REG_CONFIG_DISP_OVL_MOUT_EN	0x030
@@ -41,45 +45,89 @@
 #define DISP_REG_MUTEX_RST(n)	(0x28 + 0x20 * (n))
 #define DISP_REG_MUTEX_MOD(n)	(0x2c + 0x20 * (n))
 #define DISP_REG_MUTEX_SOF(n)	(0x30 + 0x20 * (n))
+#define DISP_REG_MUTEX_MOD2(n)	(0x34 + 0x20 * (n))
 
 #define INT_MUTEX				BIT(1)
 
-#define MT8173_MUTEX_MOD_DISP_OVL0		BIT(11)
-#define MT8173_MUTEX_MOD_DISP_OVL1		BIT(12)
-#define MT8173_MUTEX_MOD_DISP_RDMA0		BIT(13)
-#define MT8173_MUTEX_MOD_DISP_RDMA1		BIT(14)
-#define MT8173_MUTEX_MOD_DISP_RDMA2		BIT(15)
-#define MT8173_MUTEX_MOD_DISP_WDMA0		BIT(16)
-#define MT8173_MUTEX_MOD_DISP_WDMA1		BIT(17)
-#define MT8173_MUTEX_MOD_DISP_COLOR0		BIT(18)
-#define MT8173_MUTEX_MOD_DISP_COLOR1		BIT(19)
-#define MT8173_MUTEX_MOD_DISP_AAL		BIT(20)
-#define MT8173_MUTEX_MOD_DISP_GAMMA		BIT(21)
-#define MT8173_MUTEX_MOD_DISP_UFOE		BIT(22)
-#define MT8173_MUTEX_MOD_DISP_PWM0		BIT(23)
-#define MT8173_MUTEX_MOD_DISP_PWM1		BIT(24)
-#define MT8173_MUTEX_MOD_DISP_OD		BIT(25)
-
-#define MT2701_MUTEX_MOD_DISP_OVL		BIT(3)
-#define MT2701_MUTEX_MOD_DISP_WDMA		BIT(6)
-#define MT2701_MUTEX_MOD_DISP_COLOR		BIT(7)
-#define MT2701_MUTEX_MOD_DISP_BLS		BIT(9)
-#define MT2701_MUTEX_MOD_DISP_RDMA0		BIT(10)
-#define MT2701_MUTEX_MOD_DISP_RDMA1		BIT(12)
+#define MT8173_MUTEX_MOD_DISP_OVL0		11
+#define MT8173_MUTEX_MOD_DISP_OVL1		12
+#define MT8173_MUTEX_MOD_DISP_RDMA0		13
+#define MT8173_MUTEX_MOD_DISP_RDMA1		14
+#define MT8173_MUTEX_MOD_DISP_RDMA2		15
+#define MT8173_MUTEX_MOD_DISP_WDMA0		16
+#define MT8173_MUTEX_MOD_DISP_WDMA1		17
+#define MT8173_MUTEX_MOD_DISP_COLOR0		18
+#define MT8173_MUTEX_MOD_DISP_COLOR1		19
+#define MT8173_MUTEX_MOD_DISP_AAL		20
+#define MT8173_MUTEX_MOD_DISP_GAMMA		21
+#define MT8173_MUTEX_MOD_DISP_UFOE		22
+#define MT8173_MUTEX_MOD_DISP_PWM0		23
+#define MT8173_MUTEX_MOD_DISP_PWM1		24
+#define MT8173_MUTEX_MOD_DISP_OD		25
+
+#define MT2712_MUTEX_MOD_DISP_PWM2		10
+#define MT2712_MUTEX_MOD_DISP_OVL0		11
+#define MT2712_MUTEX_MOD_DISP_OVL1		12
+#define MT2712_MUTEX_MOD_DISP_RDMA0		13
+#define MT2712_MUTEX_MOD_DISP_RDMA1		14
+#define MT2712_MUTEX_MOD_DISP_RDMA2		15
+#define MT2712_MUTEX_MOD_DISP_WDMA0		16
+#define MT2712_MUTEX_MOD_DISP_WDMA1		17
+#define MT2712_MUTEX_MOD_DISP_COLOR0		18
+#define MT2712_MUTEX_MOD_DISP_COLOR1		19
+#define MT2712_MUTEX_MOD_DISP_AAL0		20
+#define MT2712_MUTEX_MOD_DISP_UFOE		22
+#define MT2712_MUTEX_MOD_DISP_PWM0		23
+#define MT2712_MUTEX_MOD_DISP_PWM1		24
+#define MT2712_MUTEX_MOD_DISP_OD0		25
+#define MT2712_MUTEX_MOD2_DISP_AAL1		33
+#define MT2712_MUTEX_MOD2_DISP_OD1		34
+
+#define MT2701_MUTEX_MOD_DISP_OVL		3
+#define MT2701_MUTEX_MOD_DISP_WDMA		6
+#define MT2701_MUTEX_MOD_DISP_COLOR		7
+#define MT2701_MUTEX_MOD_DISP_BLS		9
+#define MT2701_MUTEX_MOD_DISP_RDMA0		10
+#define MT2701_MUTEX_MOD_DISP_RDMA1		12
 
 #define MUTEX_SOF_SINGLE_MODE		0
 #define MUTEX_SOF_DSI0			1
 #define MUTEX_SOF_DSI1			2
 #define MUTEX_SOF_DPI0			3
+#define MUTEX_SOF_DPI1			4
+#define MUTEX_SOF_DSI2			5
+#define MUTEX_SOF_DSI3			6
 
 #define OVL0_MOUT_EN_COLOR0		0x1
 #define OD_MOUT_EN_RDMA0		0x1
+#define OD1_MOUT_EN_RDMA1		BIT(16)
 #define UFOE_MOUT_EN_DSI0		0x1
 #define COLOR0_SEL_IN_OVL0		0x1
 #define OVL1_MOUT_EN_COLOR1		0x1
 #define GAMMA_MOUT_EN_RDMA1		0x1
-#define RDMA1_MOUT_DPI0			0x2
+#define RDMA0_SOUT_DPI0			0x2
+#define RDMA0_SOUT_DSI2			0x4
+#define RDMA0_SOUT_DSI3			0x5
+#define RDMA1_SOUT_DPI0			0x2
+#define RDMA1_SOUT_DPI1			0x3
+#define RDMA1_SOUT_DSI1			0x1
+#define RDMA1_SOUT_DSI2			0x4
+#define RDMA1_SOUT_DSI3			0x5
+#define RDMA2_SOUT_DPI0			0x2
+#define RDMA2_SOUT_DPI1			0x3
+#define RDMA2_SOUT_DSI1			0x1
+#define RDMA2_SOUT_DSI2			0x4
+#define RDMA2_SOUT_DSI3			0x5
 #define DPI0_SEL_IN_RDMA1		0x1
+#define DPI0_SEL_IN_RDMA2		0x3
+#define DPI1_SEL_IN_RDMA1		(0x1 << 8)
+#define DPI1_SEL_IN_RDMA2		(0x3 << 8)
+#define DSI1_SEL_IN_RDMA1		0x1
+#define DSI1_SEL_IN_RDMA2		0x4
+#define DSI2_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI2_SEL_IN_RDMA2		(0x4 << 16)
+#define DSI3_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI3_SEL_IN_RDMA2		(0x4 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -108,12 +156,32 @@ static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_WDMA0] = MT2701_MUTEX_MOD_DISP_WDMA,
 };
 
+static const unsigned int mt2712_mutex_mod[DDP_COMPONENT_ID_MAX] = {
+	[DDP_COMPONENT_AAL0] = MT2712_MUTEX_MOD_DISP_AAL0,
+	[DDP_COMPONENT_AAL1] = MT2712_MUTEX_MOD2_DISP_AAL1,
+	[DDP_COMPONENT_COLOR0] = MT2712_MUTEX_MOD_DISP_COLOR0,
+	[DDP_COMPONENT_COLOR1] = MT2712_MUTEX_MOD_DISP_COLOR1,
+	[DDP_COMPONENT_OD0] = MT2712_MUTEX_MOD_DISP_OD0,
+	[DDP_COMPONENT_OD1] = MT2712_MUTEX_MOD2_DISP_OD1,
+	[DDP_COMPONENT_OVL0] = MT2712_MUTEX_MOD_DISP_OVL0,
+	[DDP_COMPONENT_OVL1] = MT2712_MUTEX_MOD_DISP_OVL1,
+	[DDP_COMPONENT_PWM0] = MT2712_MUTEX_MOD_DISP_PWM0,
+	[DDP_COMPONENT_PWM1] = MT2712_MUTEX_MOD_DISP_PWM1,
+	[DDP_COMPONENT_PWM2] = MT2712_MUTEX_MOD_DISP_PWM2,
+	[DDP_COMPONENT_RDMA0] = MT2712_MUTEX_MOD_DISP_RDMA0,
+	[DDP_COMPONENT_RDMA1] = MT2712_MUTEX_MOD_DISP_RDMA1,
+	[DDP_COMPONENT_RDMA2] = MT2712_MUTEX_MOD_DISP_RDMA2,
+	[DDP_COMPONENT_UFOE] = MT2712_MUTEX_MOD_DISP_UFOE,
+	[DDP_COMPONENT_WDMA0] = MT2712_MUTEX_MOD_DISP_WDMA0,
+	[DDP_COMPONENT_WDMA1] = MT2712_MUTEX_MOD_DISP_WDMA1,
+};
+
 static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
-	[DDP_COMPONENT_AAL] = MT8173_MUTEX_MOD_DISP_AAL,
+	[DDP_COMPONENT_AAL0] = MT8173_MUTEX_MOD_DISP_AAL,
 	[DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0,
 	[DDP_COMPONENT_COLOR1] = MT8173_MUTEX_MOD_DISP_COLOR1,
 	[DDP_COMPONENT_GAMMA] = MT8173_MUTEX_MOD_DISP_GAMMA,
-	[DDP_COMPONENT_OD] = MT8173_MUTEX_MOD_DISP_OD,
+	[DDP_COMPONENT_OD0] = MT8173_MUTEX_MOD_DISP_OD,
 	[DDP_COMPONENT_OVL0] = MT8173_MUTEX_MOD_DISP_OVL0,
 	[DDP_COMPONENT_OVL1] = MT8173_MUTEX_MOD_DISP_OVL1,
 	[DDP_COMPONENT_PWM0] = MT8173_MUTEX_MOD_DISP_PWM0,
@@ -138,7 +206,7 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_OVL0 && next == DDP_COMPONENT_RDMA0) {
 		*addr = DISP_REG_CONFIG_DISP_OVL_MOUT_EN;
 		value = OVL_MOUT_EN_RDMA;
-	} else if (cur == DDP_COMPONENT_OD && next == DDP_COMPONENT_RDMA0) {
+	} else if (cur == DDP_COMPONENT_OD0 && next == DDP_COMPONENT_RDMA0) {
 		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
 		value = OD_MOUT_EN_RDMA0;
 	} else if (cur == DDP_COMPONENT_UFOE && next == DDP_COMPONENT_DSI0) {
@@ -150,9 +218,48 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_GAMMA && next == DDP_COMPONENT_RDMA1) {
 		*addr = DISP_REG_CONFIG_DISP_GAMMA_MOUT_EN;
 		value = GAMMA_MOUT_EN_RDMA1;
+	} else if (cur == DDP_COMPONENT_OD1 && next == DDP_COMPONENT_RDMA1) {
+		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
+		value = OD1_MOUT_EN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DSI3;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI3;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
-		*addr = DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN;
-		value = RDMA1_MOUT_DPI0;
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DPI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DPI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI3;
 	} else {
 		value = 0;
 	}
@@ -172,6 +279,33 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
 		value = DPI0_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI1_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
+		value = DSI1_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI2_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
+		value = DSI3_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI0_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI1_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI1_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI2_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI3_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
@@ -278,6 +412,7 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
@@ -288,13 +423,30 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DSI1:
 		reg = MUTEX_SOF_DSI0;
 		break;
+	case DDP_COMPONENT_DSI2:
+		reg = MUTEX_SOF_DSI2;
+		break;
+	case DDP_COMPONENT_DSI3:
+		reg = MUTEX_SOF_DSI3;
+		break;
 	case DDP_COMPONENT_DPI0:
 		reg = MUTEX_SOF_DPI0;
 		break;
+	case DDP_COMPONENT_DPI1:
+		reg = MUTEX_SOF_DPI1;
+		break;
 	default:
-		reg = readl_relaxed(ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
-		reg |= ddp->mutex_mod[id];
-		writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
+		if (ddp->mutex_mod[id] < 32) {
+			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg |= 1 << ddp->mutex_mod[id];
+			writel_relaxed(reg, ddp->regs + offset);
+		} else {
+			offset = DISP_REG_MUTEX_MOD2(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg |= 1 << (ddp->mutex_mod[id] - 32);
+			writel_relaxed(reg, ddp->regs + offset);
+		}
 		return;
 	}
 
@@ -307,20 +459,32 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
 	switch (id) {
 	case DDP_COMPONENT_DSI0:
 	case DDP_COMPONENT_DSI1:
+	case DDP_COMPONENT_DSI2:
+	case DDP_COMPONENT_DSI3:
 	case DDP_COMPONENT_DPI0:
+	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
 			       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
 		break;
 	default:
-		reg = readl_relaxed(ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
-		reg &= ~(ddp->mutex_mod[id]);
-		writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
+		if (ddp->mutex_mod[id] < 32) {
+			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg &= ~(1 << ddp->mutex_mod[id]);
+			writel_relaxed(reg, ddp->regs + offset);
+		} else {
+			offset = DISP_REG_MUTEX_MOD2(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg &= ~(1 << (ddp->mutex_mod[id] - 32));
+			writel_relaxed(reg, ddp->regs + offset);
+		}
 		break;
 	}
 }
@@ -407,6 +571,7 @@ static int mtk_ddp_remove(struct platform_device *pdev)
 
 static const struct of_device_id ddp_driver_dt_match[] = {
 	{ .compatible = "mediatek,mt2701-disp-mutex", .data = mt2701_mutex_mod},
+	{ .compatible = "mediatek,mt2712-disp-mutex", .data = mt2712_mutex_mod},
 	{ .compatible = "mediatek,mt8173-disp-mutex", .data = mt8173_mutex_mod},
 	{},
 };
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 4672317e3ad1..ff974d82a4a6 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -218,18 +218,25 @@ struct mtk_ddp_comp_match {
 };
 
 static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
-	[DDP_COMPONENT_AAL]	= { MTK_DISP_AAL,	0, &ddp_aal },
+	[DDP_COMPONENT_AAL0]	= { MTK_DISP_AAL,	0, &ddp_aal },
+	[DDP_COMPONENT_AAL1]	= { MTK_DISP_AAL,	1, &ddp_aal },
 	[DDP_COMPONENT_BLS]	= { MTK_DISP_BLS,	0, NULL },
 	[DDP_COMPONENT_COLOR0]	= { MTK_DISP_COLOR,	0, NULL },
 	[DDP_COMPONENT_COLOR1]	= { MTK_DISP_COLOR,	1, NULL },
 	[DDP_COMPONENT_DPI0]	= { MTK_DPI,		0, NULL },
+	[DDP_COMPONENT_DPI1]	= { MTK_DPI,		1, NULL },
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
 	[DDP_COMPONENT_DSI1]	= { MTK_DSI,		1, NULL },
+	[DDP_COMPONENT_DSI2]	= { MTK_DSI,		2, NULL },
+	[DDP_COMPONENT_DSI3]	= { MTK_DSI,		3, NULL },
 	[DDP_COMPONENT_GAMMA]	= { MTK_DISP_GAMMA,	0, &ddp_gamma },
-	[DDP_COMPONENT_OD]	= { MTK_DISP_OD,	0, &ddp_od },
+	[DDP_COMPONENT_OD0]	= { MTK_DISP_OD,	0, &ddp_od },
+	[DDP_COMPONENT_OD1]	= { MTK_DISP_OD,	1, &ddp_od },
 	[DDP_COMPONENT_OVL0]	= { MTK_DISP_OVL,	0, NULL },
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
+	[DDP_COMPONENT_PWM1]	= { MTK_DISP_PWM,	1, NULL },
+	[DDP_COMPONENT_PWM2]	= { MTK_DISP_PWM,	2, NULL },
 	[DDP_COMPONENT_RDMA0]	= { MTK_DISP_RDMA,	0, NULL },
 	[DDP_COMPONENT_RDMA1]	= { MTK_DISP_RDMA,	1, NULL },
 	[DDP_COMPONENT_RDMA2]	= { MTK_DISP_RDMA,	2, NULL },
@@ -271,7 +278,11 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 
 	if (comp_id == DDP_COMPONENT_BLS ||
 	    comp_id == DDP_COMPONENT_DPI0 ||
+	    comp_id == DDP_COMPONENT_DPI1 ||
 	    comp_id == DDP_COMPONENT_DSI0 ||
+	    comp_id == DDP_COMPONENT_DSI1 ||
+	    comp_id == DDP_COMPONENT_DSI2 ||
+	    comp_id == DDP_COMPONENT_DSI3 ||
 	    comp_id == DDP_COMPONENT_PWM0) {
 		comp->regs = NULL;
 		comp->clk = NULL;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 0828cf8bf85c..7413ffeb3c9d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -41,19 +41,25 @@ enum mtk_ddp_comp_type {
 };
 
 enum mtk_ddp_comp_id {
-	DDP_COMPONENT_AAL,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_AAL1,
 	DDP_COMPONENT_BLS,
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
 	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_DPI1,
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
+	DDP_COMPONENT_DSI2,
+	DDP_COMPONENT_DSI3,
 	DDP_COMPONENT_GAMMA,
-	DDP_COMPONENT_OD,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_OD1,
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_OVL1,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
+	DDP_COMPONENT_PWM2,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_RDMA1,
 	DDP_COMPONENT_RDMA2,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index a2ca90fc403c..39721119713b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -146,11 +146,37 @@ static const enum mtk_ddp_comp_id mt2701_mtk_ddp_ext[] = {
 	DDP_COMPONENT_DPI0,
 };
 
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_main[] = {
+	DDP_COMPONENT_OVL0,
+	DDP_COMPONENT_COLOR0,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_RDMA0,
+	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_PWM0,
+};
+
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_ext[] = {
+	DDP_COMPONENT_OVL1,
+	DDP_COMPONENT_COLOR1,
+	DDP_COMPONENT_AAL1,
+	DDP_COMPONENT_OD1,
+	DDP_COMPONENT_RDMA1,
+	DDP_COMPONENT_DPI1,
+	DDP_COMPONENT_PWM1,
+};
+
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_third[] = {
+	DDP_COMPONENT_RDMA2,
+	DDP_COMPONENT_DSI3,
+	DDP_COMPONENT_PWM2,
+};
+
 static const enum mtk_ddp_comp_id mt8173_mtk_ddp_main[] = {
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_COLOR0,
-	DDP_COMPONENT_AAL,
-	DDP_COMPONENT_OD,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_UFOE,
 	DDP_COMPONENT_DSI0,
@@ -173,6 +199,15 @@ static const struct mtk_mmsys_driver_data mt2701_mmsys_driver_data = {
 	.shadow_register = true,
 };
 
+static const struct mtk_mmsys_driver_data mt2712_mmsys_driver_data = {
+	.main_path = mt2712_mtk_ddp_main,
+	.main_len = ARRAY_SIZE(mt2712_mtk_ddp_main),
+	.ext_path = mt2712_mtk_ddp_ext,
+	.ext_len = ARRAY_SIZE(mt2712_mtk_ddp_ext),
+	.third_path = mt2712_mtk_ddp_third,
+	.third_len = ARRAY_SIZE(mt2712_mtk_ddp_third),
+};
+
 static const struct mtk_mmsys_driver_data mt8173_mmsys_driver_data = {
 	.main_path = mt8173_mtk_ddp_main,
 	.main_len = ARRAY_SIZE(mt8173_mtk_ddp_main),
@@ -232,6 +267,11 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	if (ret < 0)
 		goto err_component_unbind;
 
+	ret = mtk_drm_crtc_create(drm, private->data->third_path,
+				  private->data->third_len);
+	if (ret < 0)
+		goto err_component_unbind;
+
 	/* Use OVL device for all DMA memory allocations */
 	np = private->comp_node[private->data->main_path[0]] ?:
 	     private->comp_node[private->data->ext_path[0]];
@@ -360,24 +400,44 @@ static const struct component_master_ops mtk_drm_ops = {
 };
 
 static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
-	{ .compatible = "mediatek,mt2701-disp-ovl",   .data = (void *)MTK_DISP_OVL },
-	{ .compatible = "mediatek,mt8173-disp-ovl",   .data = (void *)MTK_DISP_OVL },
-	{ .compatible = "mediatek,mt2701-disp-rdma",  .data = (void *)MTK_DISP_RDMA },
-	{ .compatible = "mediatek,mt8173-disp-rdma",  .data = (void *)MTK_DISP_RDMA },
-	{ .compatible = "mediatek,mt8173-disp-wdma",  .data = (void *)MTK_DISP_WDMA },
-	{ .compatible = "mediatek,mt2701-disp-color", .data = (void *)MTK_DISP_COLOR },
-	{ .compatible = "mediatek,mt8173-disp-color", .data = (void *)MTK_DISP_COLOR },
-	{ .compatible = "mediatek,mt8173-disp-aal",   .data = (void *)MTK_DISP_AAL},
-	{ .compatible = "mediatek,mt8173-disp-gamma", .data = (void *)MTK_DISP_GAMMA, },
-	{ .compatible = "mediatek,mt8173-disp-ufoe",  .data = (void *)MTK_DISP_UFOE },
-	{ .compatible = "mediatek,mt2701-dsi",	      .data = (void *)MTK_DSI },
-	{ .compatible = "mediatek,mt8173-dsi",        .data = (void *)MTK_DSI },
-	{ .compatible = "mediatek,mt8173-dpi",        .data = (void *)MTK_DPI },
-	{ .compatible = "mediatek,mt2701-disp-mutex", .data = (void *)MTK_DISP_MUTEX },
-	{ .compatible = "mediatek,mt8173-disp-mutex", .data = (void *)MTK_DISP_MUTEX },
-	{ .compatible = "mediatek,mt2701-disp-pwm",   .data = (void *)MTK_DISP_BLS },
-	{ .compatible = "mediatek,mt8173-disp-pwm",   .data = (void *)MTK_DISP_PWM },
-	{ .compatible = "mediatek,mt8173-disp-od",    .data = (void *)MTK_DISP_OD },
+	{ .compatible = "mediatek,mt2701-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt8173-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt2701-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8173-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8173-disp-wdma",
+	  .data = (void *)MTK_DISP_WDMA },
+	{ .compatible = "mediatek,mt2701-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8173-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8173-disp-aal",
+	  .data = (void *)MTK_DISP_AAL},
+	{ .compatible = "mediatek,mt8173-disp-gamma",
+	  .data = (void *)MTK_DISP_GAMMA, },
+	{ .compatible = "mediatek,mt8173-disp-ufoe",
+	  .data = (void *)MTK_DISP_UFOE },
+	{ .compatible = "mediatek,mt2701-dsi",
+	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8173-dsi",
+	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8173-dpi",
+	  .data = (void *)MTK_DPI },
+	{ .compatible = "mediatek,mt2701-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt2712-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt8173-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt2701-disp-pwm",
+	  .data = (void *)MTK_DISP_BLS },
+	{ .compatible = "mediatek,mt8173-disp-pwm",
+	  .data = (void *)MTK_DISP_PWM },
+	{ .compatible = "mediatek,mt8173-disp-od",
+	  .data = (void *)MTK_DISP_OD },
 	{ }
 };
 
@@ -552,6 +612,8 @@ static SIMPLE_DEV_PM_OPS(mtk_drm_pm_ops, mtk_drm_sys_suspend,
 static const struct of_device_id mtk_drm_of_ids[] = {
 	{ .compatible = "mediatek,mt2701-mmsys",
 	  .data = &mt2701_mmsys_driver_data},
+	{ .compatible = "mediatek,mt2712-mmsys",
+	  .data = &mt2712_mmsys_driver_data},
 	{ .compatible = "mediatek,mt8173-mmsys",
 	  .data = &mt8173_mmsys_driver_data},
 	{ }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
index c3378c452c0a..ecc00ca3221d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
@@ -17,7 +17,7 @@
 #include <linux/io.h>
 #include "mtk_drm_ddp_comp.h"
 
-#define MAX_CRTC	2
+#define MAX_CRTC	3
 #define MAX_CONNECTOR	2
 
 struct device;
@@ -33,6 +33,9 @@ struct mtk_mmsys_driver_data {
 	unsigned int main_len;
 	const enum mtk_ddp_comp_id *ext_path;
 	unsigned int ext_len;
+	const enum mtk_ddp_comp_id *third_path;
+	unsigned int third_len;
+
 	bool shadow_register;
 };
 
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index aa0943ec32b0..66df1b177959 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -782,7 +782,7 @@ static int mtk_dsi_create_connector(struct drm_device *drm, struct mtk_dsi *dsi)
 	drm_connector_helper_add(&dsi->conn, &mtk_dsi_connector_helper_funcs);
 
 	dsi->conn.dpms = DRM_MODE_DPMS_OFF;
-	drm_mode_connector_attach_encoder(&dsi->conn, &dsi->encoder);
+	drm_connector_attach_encoder(&dsi->conn, &dsi->encoder);
 
 	if (dsi->panel) {
 		ret = drm_panel_attach(dsi->panel, &dsi->conn);
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 59a11026dceb..2d45d1dd9554 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1220,7 +1220,7 @@ static int mtk_hdmi_conn_get_modes(struct drm_connector *conn)
 
 	hdmi->dvi_mode = !drm_detect_monitor_audio(edid);
 
-	drm_mode_connector_update_edid_property(conn, edid);
+	drm_connector_update_edid_property(conn, edid);
 
 	ret = drm_add_edid_modes(conn, edid);
 	kfree(edid);
@@ -1306,7 +1306,7 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge)
 	hdmi->conn.interlace_allowed = true;
 	hdmi->conn.doublescan_allowed = false;
 
-	ret = drm_mode_connector_attach_encoder(&hdmi->conn,
+	ret = drm_connector_attach_encoder(&hdmi->conn,
 						bridge->encoder);
 	if (ret) {
 		dev_err(hdmi->dev,
diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index c9ad45686e7a..df7247cd93f9 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -329,6 +329,12 @@ static void dw_hdmi_set_vclk(struct meson_dw_hdmi *dw_hdmi,
 
 	vclk_freq = mode->clock;
 
+	if (!vic) {
+		meson_vclk_setup(priv, MESON_VCLK_TARGET_DMT, vclk_freq,
+				 vclk_freq, vclk_freq, false);
+		return;
+	}
+
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		vclk_freq *= 2;
 
@@ -542,10 +548,12 @@ static enum drm_mode_status
 dw_hdmi_mode_valid(struct drm_connector *connector,
 		   const struct drm_display_mode *mode)
 {
+	struct meson_drm *priv = connector->dev->dev_private;
 	unsigned int vclk_freq;
 	unsigned int venc_freq;
 	unsigned int hdmi_freq;
 	int vic = drm_match_cea_mode(mode);
+	enum drm_mode_status status;
 
 	DRM_DEBUG_DRIVER("Modeline %d:\"%s\" %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x\n",
 		mode->base.id, mode->name, mode->vrefresh, mode->clock,
@@ -556,8 +564,11 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 
 	/* Check against non-VIC supported modes */
 	if (!vic) {
-		if (!meson_venc_hdmi_supported_mode(mode))
-			return MODE_BAD;
+		status = meson_venc_hdmi_supported_mode(mode);
+		if (status != MODE_OK)
+			return status;
+
+		return meson_vclk_dmt_supported_freq(priv, mode->clock);
 	/* Check against supported VIC modes */
 	} else if (!meson_venc_hdmi_supported_vic(vic))
 		return MODE_BAD;
@@ -583,16 +594,11 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 	dev_dbg(connector->dev->dev, "%s: vclk:%d venc=%d hdmi=%d\n", __func__,
 		vclk_freq, venc_freq, hdmi_freq);
 
-	/* Finally filter by configurable vclk frequencies */
+	/* Finally filter by configurable vclk frequencies for VIC modes */
 	switch (vclk_freq) {
-	case 25175:
-	case 40000:
 	case 54000:
-	case 65000:
 	case 74250:
-	case 108000:
 	case 148500:
-	case 162000:
 	case 297000:
 	case 594000:
 		return MODE_OK;
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index f0511220317f..ae5473257f72 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -320,32 +320,23 @@ static void meson_venci_cvbs_clock_config(struct meson_drm *priv)
 				CTS_VDAC_EN, CTS_VDAC_EN);
 }
 
-
+enum {
 /* PLL	O1 O2 O3 VP DV     EN TX */
 /* 4320 /4 /4 /1 /5 /1  => /2 /2 */
-#define MESON_VCLK_HDMI_ENCI_54000	1
+	MESON_VCLK_HDMI_ENCI_54000 = 1,
 /* 4320 /4 /4 /1 /5 /1  => /1 /2 */
-#define MESON_VCLK_HDMI_DDR_54000	2
+	MESON_VCLK_HDMI_DDR_54000,
 /* 2970 /4 /1 /1 /5 /1  => /1 /2 */
-#define MESON_VCLK_HDMI_DDR_148500	3
-/* 4028 /4 /4 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_25175		4
-/* 3200 /4 /2 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_40000		5
-/* 5200 /4 /2 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_65000		6
+	MESON_VCLK_HDMI_DDR_148500,
 /* 2970 /2 /2 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_74250		7
-/* 4320 /4 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_108000		8
+	MESON_VCLK_HDMI_74250,
 /* 2970 /1 /2 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_148500		9
-/* 3240 /2 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_162000		10
+	MESON_VCLK_HDMI_148500,
 /* 2970 /1 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_297000		11
+	MESON_VCLK_HDMI_297000,
 /* 5940 /1 /1 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_594000		12
+	MESON_VCLK_HDMI_594000
+};
 
 struct meson_vclk_params {
 	unsigned int pll_base_freq;
@@ -411,46 +402,6 @@ struct meson_vclk_params {
 		.vid_pll_div = VID_PLL_DIV_5,
 		.vclk_div = 1,
 	},
-	[MESON_VCLK_HDMI_25175] = {
-		.pll_base_freq = 4028000,
-		.pll_od1 = 4,
-		.pll_od2 = 4,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_40000] = {
-		.pll_base_freq = 3200000,
-		.pll_od1 = 4,
-		.pll_od2 = 2,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_65000] = {
-		.pll_base_freq = 5200000,
-		.pll_od1 = 4,
-		.pll_od2 = 2,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_108000] = {
-		.pll_base_freq = 4320000,
-		.pll_od1 = 4,
-		.pll_od2 = 1,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_162000] = {
-		.pll_base_freq = 3240000,
-		.pll_od1 = 2,
-		.pll_od2 = 1,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
 };
 
 static inline unsigned int pll_od_to_reg(unsigned int od)
@@ -470,358 +421,217 @@ static inline unsigned int pll_od_to_reg(unsigned int od)
 	return 0;
 }
 
-void meson_hdmi_pll_set(struct meson_drm *priv,
-			unsigned int base,
-			unsigned int od1,
-			unsigned int od2,
-			unsigned int od3)
+void meson_hdmi_pll_set_params(struct meson_drm *priv, unsigned int m,
+			       unsigned int frac, unsigned int od1,
+			       unsigned int od2, unsigned int od3)
 {
 	unsigned int val;
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
-		switch (base) {
-		case 2970000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800023d);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* Enable and unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						0x7 << 28, 0x4 << 28);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4e00);
-			break;
-
-		case 3200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000242);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4aab);
-			break;
-
-		case 3240000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000243);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4800);
-			break;
-
-		case 3865000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000250);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4855);
-			break;
-
-		case 4028000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000253);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4eab);
-			break;
-
-		case 4320000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800025a);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000200 | m);
+		if (frac)
+			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2,
+				     0x00004000 | frac);
+		else
+			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2,
+				     0x00000000);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
 
-		case 5940000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800027b);
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4c00);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x135c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
+		/* Enable and unreset */
+		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
+				   0x7 << 28, 0x4 << 28);
 
-		case 5200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800026c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x135c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
-		};
+		/* Poll for lock bit */
+		regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
+					 val, (val & HDMI_PLL_LOCK), 10, 0);
 	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
 		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
-		switch (base) {
-		case 2970000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x4000027b);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb300);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000285);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb155);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3240000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000287);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3865000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002a1);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb02b);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 4028000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002a7);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb355);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 4320000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002b4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 5940000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002f7);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb200);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 5200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002d8);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb2ab);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		};
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000200 | m);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000 | frac);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
 
 		/* Reset PLL */
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-					HDMI_PLL_RESET, HDMI_PLL_RESET);
+				HDMI_PLL_RESET, HDMI_PLL_RESET);
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-					HDMI_PLL_RESET, 0);
+				HDMI_PLL_RESET, 0);
 
 		/* Poll for lock bit */
 		regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL, val,
 				(val & HDMI_PLL_LOCK), 10, 0);
-	};
+	}
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 16, pll_od_to_reg(od1) << 16);
+				3 << 16, pll_od_to_reg(od1) << 16);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 21, pll_od_to_reg(od1) << 21);
+				3 << 21, pll_od_to_reg(od1) << 21);
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 22, pll_od_to_reg(od2) << 22);
+				3 << 22, pll_od_to_reg(od2) << 22);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 23, pll_od_to_reg(od2) << 23);
+				3 << 23, pll_od_to_reg(od2) << 23);
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 18, pll_od_to_reg(od3) << 18);
+				3 << 18, pll_od_to_reg(od3) << 18);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 19, pll_od_to_reg(od3) << 19);
+				3 << 19, pll_od_to_reg(od3) << 19);
+
 }
 
-void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int vclk_freq, unsigned int venc_freq,
-		      unsigned int dac_freq, bool hdmi_use_enci)
+#define XTAL_FREQ 24000
+
+static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
+					 unsigned int pll_freq)
 {
-	unsigned int freq;
-	unsigned int hdmi_tx_div;
-	unsigned int venc_div;
+	/* The GXBB PLL has a /2 pre-multiplier */
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
+		pll_freq /= 2;
 
-	if (target == MESON_VCLK_TARGET_CVBS) {
-		meson_venci_cvbs_clock_config(priv);
-		return;
+	return pll_freq / XTAL_FREQ;
+}
+
+#define HDMI_FRAC_MAX_GXBB	4096
+#define HDMI_FRAC_MAX_GXL	1024
+
+static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
+					    unsigned int m,
+					    unsigned int pll_freq)
+{
+	unsigned int parent_freq = XTAL_FREQ;
+	unsigned int frac_max = HDMI_FRAC_MAX_GXL;
+	unsigned int frac_m;
+	unsigned int frac;
+
+	/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		frac_max = HDMI_FRAC_MAX_GXBB;
+		parent_freq *= 2;
 	}
 
-	hdmi_tx_div = vclk_freq / dac_freq;
+	/* We can have a perfect match !*/
+	if (pll_freq / m == parent_freq &&
+	    pll_freq % m == 0)
+		return 0;
 
-	if (hdmi_tx_div == 0) {
-		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
-				dac_freq);
-		return;
+	frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+	frac_m = m * frac_max;
+	if (frac_m > frac)
+		return frac_max;
+	frac -= frac_m;
+
+	return min((u16)frac, (u16)(frac_max - 1));
+}
+
+static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
+					   unsigned int m,
+					   unsigned int frac)
+{
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		/* Empiric supported min/max dividers */
+		if (m < 53 || m > 123)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_GXBB)
+			return false;
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
+		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
+		/* Empiric supported min/max dividers */
+		if (m < 106 || m > 247)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_GXL)
+			return false;
 	}
 
-	venc_div = vclk_freq / venc_freq;
+	return true;
+}
 
-	if (venc_div == 0) {
-		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
-				venc_freq);
-		return;
+static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
+				       unsigned int freq,
+				       unsigned int *m,
+				       unsigned int *frac,
+				       unsigned int *od)
+{
+	/* Cycle from /16 to /2 */
+	for (*od = 16 ; *od > 1 ; *od >>= 1) {
+		*m = meson_hdmi_pll_get_m(priv, freq * *od);
+		if (!*m)
+			continue;
+		*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
+
+		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+				 freq, *m, *frac, *od);
+
+		if (meson_hdmi_pll_validate_params(priv, *m, *frac))
+			return true;
 	}
 
-	switch (vclk_freq) {
-	case 54000:
-		if (hdmi_use_enci)
-			freq = MESON_VCLK_HDMI_ENCI_54000;
-		else
-			freq = MESON_VCLK_HDMI_DDR_54000;
-		break;
-	case 25175:
-		freq = MESON_VCLK_HDMI_25175;
-		break;
-	case 40000:
-		freq = MESON_VCLK_HDMI_40000;
-		break;
-	case 65000:
-		freq = MESON_VCLK_HDMI_65000;
-		break;
-	case 74250:
-		freq = MESON_VCLK_HDMI_74250;
-		break;
-	case 108000:
-		freq = MESON_VCLK_HDMI_108000;
-		break;
-	case 148500:
-		if (dac_freq != 148500)
-			freq = MESON_VCLK_HDMI_DDR_148500;
-		else
-			freq = MESON_VCLK_HDMI_148500;
-		break;
-	case 162000:
-		freq = MESON_VCLK_HDMI_162000;
-		break;
-	case 297000:
-		freq = MESON_VCLK_HDMI_297000;
-		break;
-	case 594000:
-		freq = MESON_VCLK_HDMI_594000;
-		break;
-	default:
-		pr_err("Fatal Error, invalid HDMI vclk freq %d\n",
-			vclk_freq);
+	return false;
+}
+
+/* pll_freq is the frequency after the OD dividers */
+enum drm_mode_status
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+{
+	unsigned int od, m, frac;
+
+	/* In DMT mode, path after PLL is always /10 */
+	freq *= 10;
+
+	if (meson_hdmi_pll_find_params(priv, freq, &m, &frac, &od))
+		return MODE_OK;
+
+	return MODE_CLOCK_RANGE;
+}
+EXPORT_SYMBOL_GPL(meson_vclk_dmt_supported_freq);
+
+/* pll_freq is the frequency after the OD dividers */
+static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
+				       unsigned int pll_freq)
+{
+	unsigned int od, m, frac, od1, od2, od3;
+
+	if (meson_hdmi_pll_find_params(priv, pll_freq, &m, &frac, &od)) {
+		od3 = 1;
+		if (od < 4) {
+			od1 = 2;
+			od2 = 1;
+		} else {
+			od2 = od / 4;
+			od1 = od / od2;
+		}
+
+		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+				 pll_freq, m, frac, od1, od2, od3);
+
+		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
+
 		return;
 	}
 
+	DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+		  pll_freq);
+}
+
+static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
+			   unsigned int od1, unsigned int od2, unsigned int od3,
+			   unsigned int vid_pll_div, unsigned int vclk_div,
+			   unsigned int hdmi_tx_div, unsigned int venc_div,
+			   bool hdmi_use_enci)
+{
 	/* Set HDMI-TX sys clock */
 	regmap_update_bits(priv->hhi, HHI_HDMI_CLK_CNTL,
 			   CTS_HDMI_SYS_SEL_MASK, 0);
@@ -831,19 +641,49 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 			   CTS_HDMI_SYS_EN, CTS_HDMI_SYS_EN);
 
 	/* Set HDMI PLL rate */
-	meson_hdmi_pll_set(priv, params[freq].pll_base_freq,
-			   params[freq].pll_od1,
-			   params[freq].pll_od2,
-			   params[freq].pll_od3);
+	if (!od1 && !od2 && !od3) {
+		meson_hdmi_pll_generic_set(priv, pll_base_freq);
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		switch (pll_base_freq) {
+		case 2970000:
+			meson_hdmi_pll_set_params(priv, 0x3d, 0xe00,
+						  od1, od2, od3);
+			break;
+		case 4320000:
+			meson_hdmi_pll_set_params(priv, 0x5a, 0,
+						  od1, od2, od3);
+			break;
+		case 5940000:
+			meson_hdmi_pll_set_params(priv, 0x7b, 0xc00,
+						  od1, od2, od3);
+			break;
+		}
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
+		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
+		switch (pll_base_freq) {
+		case 2970000:
+			meson_hdmi_pll_set_params(priv, 0x7b, 0x300,
+						  od1, od2, od3);
+			break;
+		case 4320000:
+			meson_hdmi_pll_set_params(priv, 0xb4, 0,
+						  od1, od2, od3);
+			break;
+		case 5940000:
+			meson_hdmi_pll_set_params(priv, 0xf7, 0x200,
+						  od1, od2, od3);
+			break;
+		}
+	}
 
 	/* Setup vid_pll divider */
-	meson_vid_pll_set(priv, params[freq].vid_pll_div);
+	meson_vid_pll_set(priv, vid_pll_div);
 
 	/* Set VCLK div */
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_CNTL,
 			   VCLK_SEL_MASK, 0);
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_DIV,
-			   VCLK_DIV_MASK, params[freq].vclk_div - 1);
+			   VCLK_DIV_MASK, vclk_div - 1);
 
 	/* Set HDMI-TX source */
 	switch (hdmi_tx_div) {
@@ -981,4 +821,80 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_CNTL, VCLK_EN, VCLK_EN);
 }
+
+void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
+		      unsigned int vclk_freq, unsigned int venc_freq,
+		      unsigned int dac_freq, bool hdmi_use_enci)
+{
+	unsigned int freq;
+	unsigned int hdmi_tx_div;
+	unsigned int venc_div;
+
+	if (target == MESON_VCLK_TARGET_CVBS) {
+		meson_venci_cvbs_clock_config(priv);
+		return;
+	} else if (target == MESON_VCLK_TARGET_DMT) {
+		/* The DMT clock path is fixed after the PLL:
+		 * - automatic PLL freq + OD management
+		 * - vid_pll_div = VID_PLL_DIV_5
+		 * - vclk_div = 2
+		 * - hdmi_tx_div = 1
+		 * - venc_div = 1
+		 * - encp encoder
+		 */
+		meson_vclk_set(priv, vclk_freq * 10, 0, 0, 0,
+			       VID_PLL_DIV_5, 2, 1, 1, false);
+		return;
+	}
+
+	hdmi_tx_div = vclk_freq / dac_freq;
+
+	if (hdmi_tx_div == 0) {
+		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+		       dac_freq);
+		return;
+	}
+
+	venc_div = vclk_freq / venc_freq;
+
+	if (venc_div == 0) {
+		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+		       venc_freq);
+		return;
+	}
+
+	switch (vclk_freq) {
+	case 54000:
+		if (hdmi_use_enci)
+			freq = MESON_VCLK_HDMI_ENCI_54000;
+		else
+			freq = MESON_VCLK_HDMI_DDR_54000;
+		break;
+	case 74250:
+		freq = MESON_VCLK_HDMI_74250;
+		break;
+	case 148500:
+		if (dac_freq != 148500)
+			freq = MESON_VCLK_HDMI_DDR_148500;
+		else
+			freq = MESON_VCLK_HDMI_148500;
+		break;
+	case 297000:
+		freq = MESON_VCLK_HDMI_297000;
+		break;
+	case 594000:
+		freq = MESON_VCLK_HDMI_594000;
+		break;
+	default:
+		pr_err("Fatal Error, invalid HDMI vclk freq %d\n",
+		       vclk_freq);
+		return;
+	}
+
+	meson_vclk_set(priv, params[freq].pll_base_freq,
+		       params[freq].pll_od1, params[freq].pll_od2,
+		       params[freq].pll_od3, params[freq].vid_pll_div,
+		       params[freq].vclk_div, hdmi_tx_div, venc_div,
+		       hdmi_use_enci);
+}
 EXPORT_SYMBOL_GPL(meson_vclk_setup);
diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h
index 0401b5213471..869fa3a3073e 100644
--- a/drivers/gpu/drm/meson/meson_vclk.h
+++ b/drivers/gpu/drm/meson/meson_vclk.h
@@ -24,11 +24,15 @@
 enum {
 	MESON_VCLK_TARGET_CVBS = 0,
 	MESON_VCLK_TARGET_HDMI = 1,
+	MESON_VCLK_TARGET_DMT = 2,
 };
 
 /* 27MHz is the CVBS Pixel Clock */
 #define MESON_VCLK_CVBS			27000
 
+enum drm_mode_status
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 		      unsigned int vclk_freq, unsigned int venc_freq,
 		      unsigned int dac_freq, bool hdmi_use_enci);
diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c
index 6e2701389801..514245e69b38 100644
--- a/drivers/gpu/drm/meson/meson_venc.c
+++ b/drivers/gpu/drm/meson/meson_venc.c
@@ -697,314 +697,6 @@ union meson_hdmi_venc_mode meson_hdmi_encp_mode_1080p60 = {
 	},
 };
 
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_640x480_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x31f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x90,
-		.havon_end = 0x30f,
-		.vavon_bline = 0x23,
-		.vavon_eline = 0x202,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x60,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 2,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x20c,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_800x600_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x41f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0xD8,
-		.havon_end = 0x3f7,
-		.vavon_bline = 0x1b,
-		.vavon_eline = 0x272,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x80,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 4,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x273,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1024x768_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 1343,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 296,
-		.havon_end = 1319,
-		.vavon_bline = 35,
-		.vavon_eline = 802,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 136,
-		.vso_begin = 30,
-		.vso_end = 50,
-		.vso_bline = 0,
-		.vso_eline = 6,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 805,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1152x864_75 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x63f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x180,
-		.havon_end = 0x5ff,
-		.vavon_bline = 0x23,
-		.vavon_eline = 0x382,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x80,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x383,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1280x1024_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x697,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x168,
-		.havon_end = 0x667,
-		.vavon_bline = 0x29,
-		.vavon_eline = 0x428,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x70,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x429,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1600x1200_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x86f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x1f0,
-		.havon_end = 0x82f,
-		.vavon_bline = 0x31,
-		.vavon_eline = 0x4e0,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0xc0,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x4e1,
-	},
-};
-
-struct meson_hdmi_venc_dmt_mode {
-	struct drm_display_mode drm_mode;
-	union meson_hdmi_venc_mode *mode;
-} meson_hdmi_venc_dmt_modes[] = {
-	/* 640x480@60Hz */
-	{
-		{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
-		  752, 800, 0, 480, 490, 492, 525, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_640x480_60,
-	},
-	/* 800x600@60Hz */
-	{
-		{ DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 40000, 800, 840,
-		  968, 1056, 0, 600, 601, 605, 628, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_800x600_60,
-	},
-	/* 1024x768@60Hz */
-	{
-		{ DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 65000, 1024,
-		  1048, 1184, 1344, 0, 768, 771, 777, 806, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_1024x768_60,
-	},
-	/* 1152x864@75Hz */
-	{
-		{ DRM_MODE("1152x864", DRM_MODE_TYPE_DRIVER, 108000, 1152,
-		  1216, 1344, 1600, 0, 864, 865, 868, 900, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1152x864_75,
-	},
-	/* 1280x1024@60Hz */
-	{
-		{ DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 108000, 1280,
-		  1328, 1440, 1688, 0, 1024, 1025, 1028, 1066, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1280x1024_60,
-	},
-	/* 1600x1200@60Hz */
-	{
-		{ DRM_MODE("1600x1200", DRM_MODE_TYPE_DRIVER, 162000, 1600,
-		  1664, 1856, 2160, 0, 1200, 1201, 1204, 1250, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1600x1200_60,
-	},
-	/* 1920x1080@60Hz */
-	{
-		{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920,
-		  2008, 2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_1080p60
-	},
-	{ }, /* sentinel */
-};
-
 struct meson_hdmi_venc_vic_mode {
 	unsigned int vic;
 	union meson_hdmi_venc_mode *mode;
@@ -1044,17 +736,20 @@ static unsigned long modulo(unsigned long a, unsigned long b)
 		return a;
 }
 
-bool meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode)
+enum drm_mode_status
+meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode)
 {
-	struct meson_hdmi_venc_dmt_mode *vmode = meson_hdmi_venc_dmt_modes;
+	if (mode->flags & ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC |
+			    DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC))
+		return MODE_BAD;
 
-	while (vmode->mode) {
-		if (drm_mode_equal(&vmode->drm_mode, mode))
-			return true;
-		vmode++;
-	}
+	if (mode->hdisplay < 640 || mode->hdisplay > 1920)
+		return MODE_BAD_HVALUE;
 
-	return false;
+	if (mode->vdisplay < 480 || mode->vdisplay > 1200)
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
 }
 EXPORT_SYMBOL_GPL(meson_venc_hdmi_supported_mode);
 
@@ -1072,18 +767,29 @@ bool meson_venc_hdmi_supported_vic(int vic)
 }
 EXPORT_SYMBOL_GPL(meson_venc_hdmi_supported_vic);
 
-static union meson_hdmi_venc_mode
-*meson_venc_hdmi_get_dmt_vmode(const struct drm_display_mode *mode)
+void meson_venc_hdmi_get_dmt_vmode(const struct drm_display_mode *mode,
+				   union meson_hdmi_venc_mode *dmt_mode)
 {
-	struct meson_hdmi_venc_dmt_mode *vmode = meson_hdmi_venc_dmt_modes;
-
-	while (vmode->mode) {
-		if (drm_mode_equal(&vmode->drm_mode, mode))
-			return vmode->mode;
-		vmode++;
-	}
-
-	return NULL;
+	memset(dmt_mode, 0, sizeof(*dmt_mode));
+
+	dmt_mode->encp.dvi_settings = 0x21;
+	dmt_mode->encp.video_mode = 0x4040;
+	dmt_mode->encp.video_mode_adv = 0x18;
+	dmt_mode->encp.max_pxcnt = mode->htotal - 1;
+	dmt_mode->encp.havon_begin = mode->htotal - mode->hsync_start;
+	dmt_mode->encp.havon_end = dmt_mode->encp.havon_begin +
+				   mode->hdisplay - 1;
+	dmt_mode->encp.vavon_bline = mode->vtotal - mode->vsync_start;
+	dmt_mode->encp.vavon_eline = dmt_mode->encp.vavon_bline +
+				     mode->vdisplay - 1;
+	dmt_mode->encp.hso_begin = 0;
+	dmt_mode->encp.hso_end = mode->hsync_end - mode->hsync_start;
+	dmt_mode->encp.vso_begin = 30;
+	dmt_mode->encp.vso_end = 50;
+	dmt_mode->encp.vso_bline = 0;
+	dmt_mode->encp.vso_eline = mode->vsync_end - mode->vsync_start;
+	dmt_mode->encp.vso_eline_present = true;
+	dmt_mode->encp.max_lncnt = mode->vtotal - 1;
 }
 
 static union meson_hdmi_venc_mode *meson_venc_hdmi_get_vic_vmode(int vic)
@@ -1120,6 +826,7 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 			      struct drm_display_mode *mode)
 {
 	union meson_hdmi_venc_mode *vmode = NULL;
+	union meson_hdmi_venc_mode vmode_dmt;
 	bool use_enci = false;
 	bool venc_repeat = false;
 	bool hdmi_repeat = false;
@@ -1147,14 +854,17 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 	unsigned int sof_lines;
 	unsigned int vsync_lines;
 
-	if (meson_venc_hdmi_supported_vic(vic))
+	if (meson_venc_hdmi_supported_vic(vic)) {
 		vmode = meson_venc_hdmi_get_vic_vmode(vic);
-	else
-		vmode = meson_venc_hdmi_get_dmt_vmode(mode);
-	if (!vmode) {
-		dev_err(priv->dev, "%s: Fatal Error, unsupported mode "
-			DRM_MODE_FMT "\n", __func__, DRM_MODE_ARG(mode));
-		return;
+		if (!vmode) {
+			dev_err(priv->dev, "%s: Fatal Error, unsupported mode "
+				DRM_MODE_FMT "\n", __func__,
+				DRM_MODE_ARG(mode));
+			return;
+		}
+	} else {
+		meson_venc_hdmi_get_dmt_vmode(mode, &vmode_dmt);
+		vmode = &vmode_dmt;
 	}
 
 	/* Use VENCI for 480i and 576i and double HDMI pixels */
diff --git a/drivers/gpu/drm/meson/meson_venc.h b/drivers/gpu/drm/meson/meson_venc.h
index 7c18a36a0dd0..97eaebbfa0c4 100644
--- a/drivers/gpu/drm/meson/meson_venc.h
+++ b/drivers/gpu/drm/meson/meson_venc.h
@@ -58,7 +58,8 @@ struct meson_cvbs_enci_mode {
 };
 
 /* HDMI Clock parameters */
-bool meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode);
+enum drm_mode_status
+meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode);
 bool meson_venc_hdmi_supported_vic(int vic);
 bool meson_venc_hdmi_venc_repeat(int vic);
 
diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c
index 79d95ca8a0c0..f7945bae3b4a 100644
--- a/drivers/gpu/drm/meson/meson_venc_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c
@@ -282,7 +282,7 @@ int meson_venc_cvbs_create(struct meson_drm *priv)
 
 	encoder->possible_crtcs = BIT(0);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 8918539a19aa..acf7bfe68454 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1553,7 +1553,7 @@ static int mga_vga_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &mga_connector->i2c->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
@@ -1747,7 +1747,7 @@ int mgag200_modeset_init(struct mga_device *mdev)
 		return -1;
 	}
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ret = mgag200_fbdev_init(mdev);
 	if (ret) {
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 38cbde971b48..843a9d40c05e 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -12,6 +12,7 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
+	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
 	select PM_OPP
diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index cd40c050b2d7..7c773e003663 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 ccflags-y := -Idrivers/gpu/drm/msm
+ccflags-y += -Idrivers/gpu/drm/msm/disp/dpu1
 ccflags-$(CONFIG_DRM_MSM_DSI) += -Idrivers/gpu/drm/msm/dsi
 
 msm-y := \
@@ -45,6 +46,33 @@ msm-y := \
 	disp/mdp5/mdp5_mixer.o \
 	disp/mdp5/mdp5_plane.o \
 	disp/mdp5/mdp5_smp.o \
+	disp/dpu1/dpu_core_irq.o \
+	disp/dpu1/dpu_core_perf.o \
+	disp/dpu1/dpu_crtc.o \
+	disp/dpu1/dpu_encoder.o \
+	disp/dpu1/dpu_encoder_phys_cmd.o \
+	disp/dpu1/dpu_encoder_phys_vid.o \
+	disp/dpu1/dpu_formats.o \
+	disp/dpu1/dpu_hw_blk.o \
+	disp/dpu1/dpu_hw_catalog.o \
+	disp/dpu1/dpu_hw_cdm.o \
+	disp/dpu1/dpu_hw_ctl.o \
+	disp/dpu1/dpu_hw_interrupts.o \
+	disp/dpu1/dpu_hw_intf.o \
+	disp/dpu1/dpu_hw_lm.o \
+	disp/dpu1/dpu_hw_pingpong.o \
+	disp/dpu1/dpu_hw_sspp.o \
+	disp/dpu1/dpu_hw_top.o \
+	disp/dpu1/dpu_hw_util.o \
+	disp/dpu1/dpu_hw_vbif.o \
+	disp/dpu1/dpu_io_util.o \
+	disp/dpu1/dpu_irq.o \
+	disp/dpu1/dpu_kms.o \
+	disp/dpu1/dpu_mdss.o \
+	disp/dpu1/dpu_plane.o \
+	disp/dpu1/dpu_power_handle.o \
+	disp/dpu1/dpu_rm.o \
+	disp/dpu1/dpu_vbif.o \
 	msm_atomic.o \
 	msm_debugfs.o \
 	msm_drv.o \
@@ -62,7 +90,8 @@ msm-y := \
 	msm_ringbuffer.o \
 	msm_submitqueue.o
 
-msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o
+msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \
+			  disp/dpu1/dpu_dbg.o
 
 msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o
 msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 3ebbeb3a9b68..669c2d4b070d 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -411,15 +411,6 @@ static const unsigned int a3xx_registers[] = {
 	~0   /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-	adreno_show(gpu, m);
-}
-#endif
-
 /* would be nice to not have to duplicate the _show() stuff with printk(): */
 static void a3xx_dump(struct msm_gpu *gpu)
 {
@@ -427,6 +418,21 @@ static void a3xx_dump(struct msm_gpu *gpu)
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
 	adreno_dump(gpu);
 }
+
+static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
+
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
+
+	state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
+
+	return state;
+}
+
 /* Register offset defines for A3XX */
 static const unsigned int a3xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE),
@@ -450,9 +456,11 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
-#ifdef CONFIG_DEBUG_FS
-		.show = a3xx_show,
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+		.show = adreno_show,
 #endif
+		.gpu_state_get = a3xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 16d3d596638e..7c4e6dc1ed59 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -455,15 +455,19 @@ static const unsigned int a4xx_registers[] = {
 	~0 /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
+static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A4XX_RBBM_STATUS));
-	adreno_show(gpu, m);
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
+
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
 
+	state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS);
+
+	return state;
 }
-#endif
 
 /* Register offset defines for A4XX, in order of enum adreno_regs */
 static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
@@ -538,9 +542,11 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
-#ifdef CONFIG_DEBUG_FS
-		.show = a4xx_show,
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+		.show = adreno_show,
 #endif
+		.gpu_state_get = a4xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 	.get_timestamp = a4xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index d39400e5bc42..bd84f71d27d8 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -19,6 +19,7 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/pm_opp.h>
 #include <linux/nvmem-consumer.h>
+#include <linux/iopoll.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "a5xx_gpu.h"
@@ -1123,8 +1124,9 @@ static const u32 a5xx_registers[] = {
 	0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB,
 	0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05,
 	0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3,
-	0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F,
-	0xB9A0, 0xB9BF, ~0
+	0xEAA5, 0xEAC2, 0xA800, 0xA800, 0xA820, 0xA828, 0xA840, 0xA87D,
+	0XA880, 0xA88D, 0xA890, 0xA8A3, 0xA8D0, 0xA8D8, 0xA8E0, 0xA8F5,
+	0xAC60, 0xAC60, ~0,
 };
 
 static void a5xx_dump(struct msm_gpu *gpu)
@@ -1195,19 +1197,231 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
+struct a5xx_crashdumper {
+	void *ptr;
+	struct drm_gem_object *bo;
+	u64 iova;
+};
+
+struct a5xx_gpu_state {
+	struct msm_gpu_state base;
+	u32 *hlsqregs;
+};
+
+#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
+	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
+		interval, timeout)
+
+static int a5xx_crashdumper_init(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
 {
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
+	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+		SZ_1M, MSM_BO_UNCACHED, gpu->aspace,
+		&dumper->bo, &dumper->iova);
 
-	/*
-	 * Temporarily disable hardware clock gating before going into
-	 * adreno_show to avoid issues while reading the registers
-	 */
+	if (IS_ERR(dumper->ptr))
+		return PTR_ERR(dumper->ptr);
+
+	return 0;
+}
+
+static void a5xx_crashdumper_free(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	msm_gem_put_iova(dumper->bo, gpu->aspace);
+	msm_gem_put_vaddr(dumper->bo);
+
+	drm_gem_object_unreference(dumper->bo);
+}
+
+static int a5xx_crashdumper_run(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	u32 val;
+
+	if (IS_ERR_OR_NULL(dumper->ptr))
+		return -EINVAL;
+
+	gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO,
+		REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1);
+
+	return gpu_poll_timeout(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, val,
+		val & 0x04, 100, 10000);
+}
+
+/*
+ * These are a list of the registers that need to be read through the HLSQ
+ * aperture through the crashdumper.  These are not nominally accessible from
+ * the CPU on a secure platform.
+ */
+static const struct {
+	u32 type;
+	u32 regoffset;
+	u32 count;
+} a5xx_hlsq_aperture_regs[] = {
+	{ 0x35, 0xe00, 0x32 },   /* HSLQ non-context */
+	{ 0x31, 0x2080, 0x1 },   /* HLSQ 2D context 0 */
+	{ 0x33, 0x2480, 0x1 },   /* HLSQ 2D context 1 */
+	{ 0x32, 0xe780, 0x62 },  /* HLSQ 3D context 0 */
+	{ 0x34, 0xef80, 0x62 },  /* HLSQ 3D context 1 */
+	{ 0x3f, 0x0ec0, 0x40 },  /* SP non-context */
+	{ 0x3d, 0x2040, 0x1 },   /* SP 2D context 0 */
+	{ 0x3b, 0x2440, 0x1 },   /* SP 2D context 1 */
+	{ 0x3e, 0xe580, 0x170 }, /* SP 3D context 0 */
+	{ 0x3c, 0xed80, 0x170 }, /* SP 3D context 1 */
+	{ 0x3a, 0x0f00, 0x1c },  /* TP non-context */
+	{ 0x38, 0x2000, 0xa },   /* TP 2D context 0 */
+	{ 0x36, 0x2400, 0xa },   /* TP 2D context 1 */
+	{ 0x39, 0xe700, 0x80 },  /* TP 3D context 0 */
+	{ 0x37, 0xef00, 0x80 },  /* TP 3D context 1 */
+};
+
+static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
+		struct a5xx_gpu_state *a5xx_state)
+{
+	struct a5xx_crashdumper dumper = { 0 };
+	u32 offset, count = 0;
+	u64 *ptr;
+	int i;
+
+	if (a5xx_crashdumper_init(gpu, &dumper))
+		return;
+
+	/* The script will be written at offset 0 */
+	ptr = dumper.ptr;
+
+	/* Start writing the data at offset 256k */
+	offset = dumper.iova + (256 * SZ_1K);
+
+	/* Count how many additional registers to get from the HLSQ aperture */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++)
+		count += a5xx_hlsq_aperture_regs[i].count;
+
+	a5xx_state->hlsqregs = kcalloc(count, sizeof(u32), GFP_KERNEL);
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	/* Build the crashdump script */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 type = a5xx_hlsq_aperture_regs[i].type;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		/* Write the register to select the desired bank */
+		*ptr++ = ((u64) type << 8);
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_READ_SEL) << 44) |
+			(1 << 21) | 1;
+
+		*ptr++ = offset;
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_AHB_READ_APERTURE) << 44)
+			| c;
+
+		offset += c * sizeof(u32);
+	}
+
+	/* Write two zeros to close off the script */
+	*ptr++ = 0;
+	*ptr++ = 0;
+
+	if (a5xx_crashdumper_run(gpu, &dumper)) {
+		kfree(a5xx_state->hlsqregs);
+		a5xx_crashdumper_free(gpu, &dumper);
+		return;
+	}
+
+	/* Copy the data from the crashdumper to the state */
+	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
+		count * sizeof(u32));
+
+	a5xx_crashdumper_free(gpu, &dumper);
+}
+
+static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct a5xx_gpu_state *a5xx_state = kzalloc(sizeof(*a5xx_state),
+			GFP_KERNEL);
+
+	if (!a5xx_state)
+		return ERR_PTR(-ENOMEM);
+
+	/* Temporarily disable hardware clock gating before reading the hw */
 	a5xx_set_hwcg(gpu, false);
-	adreno_show(gpu, m);
+
+	/* First get the generic state from the adreno core */
+	adreno_gpu_state_get(gpu, &(a5xx_state->base));
+
+	a5xx_state->base.rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
+
+	/* Get the HLSQ regs with the help of the crashdumper */
+	a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state);
+
 	a5xx_set_hwcg(gpu, true);
+
+	return &a5xx_state->base;
+}
+
+static void a5xx_gpu_state_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	kfree(a5xx_state->hlsqregs);
+
+	adreno_gpu_state_destroy(state);
+	kfree(a5xx_state);
+}
+
+int a5xx_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, a5xx_gpu_state_destroy);
+}
+
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	int i, j;
+	u32 pos = 0;
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	adreno_show(gpu, state, p);
+
+	/* Dump the additional a5xx HLSQ registers */
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	drm_printf(p, "registers-hlsq:\n");
+
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 o = a5xx_hlsq_aperture_regs[i].regoffset;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		for (j = 0; j < c; j++, pos++, o++) {
+			/*
+			 * To keep the crashdump simple we pull the entire range
+			 * for each register type but not all of the registers
+			 * in the range are valid. Fortunately invalid registers
+			 * stick out like a sore thumb with a value of
+			 * 0xdeadbeef
+			 */
+			if (a5xx_state->hlsqregs[pos] == 0xdeadbeef)
+				continue;
+
+			drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+				o << 2, a5xx_state->hlsqregs[pos]);
+		}
+	}
 }
 #endif
 
@@ -1239,11 +1453,15 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = a5xx_active_ring,
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = a5xx_show,
+#endif
+#if defined(CONFIG_DEBUG_FS)
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
+		.gpu_state_get = a5xx_gpu_state_get,
+		.gpu_state_put = a5xx_gpu_state_put,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 0ae5ace65462..44813624a286 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -35,6 +35,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_256K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 0, 6, 0),
@@ -45,6 +46,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_128K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 2, ANY_ID, ANY_ID),
@@ -55,6 +57,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 3, 0, ANY_ID),
@@ -65,6 +68,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a330_pfp.fw",
 		},
 		.gmem  = SZ_1M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(4, 2, 0, ANY_ID),
@@ -75,6 +79,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a420_pfp.fw",
 		},
 		.gmem  = (SZ_1M + SZ_512K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(4, 3, 0, ANY_ID),
@@ -85,6 +90,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a420_pfp.fw",
 		},
 		.gmem  = (SZ_1M + SZ_512K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
@@ -96,6 +102,11 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_GPMU] = "a530v3_gpmu.fw2",
 		},
 		.gmem = SZ_1M,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
 		.quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI |
 			ADRENO_QUIRK_FAULT_DETECT_MASK,
 		.init = a5xx_gpu_init,
@@ -158,7 +169,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 	ret = msm_gpu_hw_init(gpu);
 	mutex_unlock(&dev->struct_mutex);
-	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
 	if (ret) {
 		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
 		return NULL;
@@ -316,6 +327,7 @@ static int adreno_suspend(struct device *dev)
 #endif
 
 static const struct dev_pm_ops adreno_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL)
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 17d0506d058c..38ac50b73829 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/ascii85.h>
 #include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
@@ -368,40 +369,185 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return false;
 }
 
-#ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i, count = 0;
+
+	kref_init(&state->ref);
+
+	ktime_get_real_ts64(&state->time);
+
+	for (i = 0; i < gpu->nr_rings; i++) {
+		int size = 0, j;
+
+		state->ring[i].fence = gpu->rb[i]->memptrs->fence;
+		state->ring[i].iova = gpu->rb[i]->iova;
+		state->ring[i].seqno = gpu->rb[i]->seqno;
+		state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]);
+		state->ring[i].wptr = get_wptr(gpu->rb[i]);
+
+		/* Copy at least 'wptr' dwords of the data */
+		size = state->ring[i].wptr;
+
+		/* After wptr find the last non zero dword to save space */
+		for (j = state->ring[i].wptr; j < MSM_GPU_RINGBUFFER_SZ >> 2; j++)
+			if (gpu->rb[i]->start[j])
+				size = j + 1;
+
+		if (size) {
+			state->ring[i].data = kmalloc(size << 2, GFP_KERNEL);
+			if (state->ring[i].data) {
+				memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2);
+				state->ring[i].data_size = size << 2;
+			}
+		}
+	}
+
+	/* Count the number of registers */
+	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2)
+		count += adreno_gpu->registers[i + 1] -
+			adreno_gpu->registers[i] + 1;
+
+	state->registers = kcalloc(count * 2, sizeof(u32), GFP_KERNEL);
+	if (state->registers) {
+		int pos = 0;
+
+		for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
+			u32 start = adreno_gpu->registers[i];
+			u32 end   = adreno_gpu->registers[i + 1];
+			u32 addr;
+
+			for (addr = start; addr <= end; addr++) {
+				state->registers[pos++] = addr;
+				state->registers[pos++] = gpu_read(gpu, addr);
+			}
+		}
+
+		state->nr_registers = count;
+	}
+
+	return 0;
+}
+
+void adreno_gpu_state_destroy(struct msm_gpu_state *state)
+{
 	int i;
 
-	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
+	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
+		kfree(state->ring[i].data);
+
+	for (i = 0; state->bos && i < state->nr_bos; i++)
+		kvfree(state->bos[i].data);
+
+	kfree(state->bos);
+	kfree(state->comm);
+	kfree(state->cmd);
+	kfree(state->registers);
+}
+
+static void adreno_gpu_state_kref_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+
+	adreno_gpu_state_destroy(state);
+	kfree(state);
+}
+
+int adreno_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, adreno_gpu_state_kref_destroy);
+}
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+
+static void adreno_show_object(struct drm_printer *p, u32 *ptr, int len)
+{
+	char out[ASCII85_BUFSZ];
+	long l, datalen, i;
+
+	if (!ptr || !len)
+		return;
+
+	/*
+	 * Only dump the non-zero part of the buffer - rarely will any data
+	 * completely fill the entire allocated size of the buffer
+	 */
+	for (datalen = 0, i = 0; i < len >> 2; i++) {
+		if (ptr[i])
+			datalen = (i << 2) + 1;
+	}
+
+	/* Skip printing the object if it is empty */
+	if (datalen == 0)
+		return;
+
+	l = ascii85_encode_len(datalen);
+
+	drm_puts(p, "    data: !!ascii85 |\n");
+	drm_puts(p, "     ");
+
+	for (i = 0; i < l; i++)
+		drm_puts(p, ascii85_encode(ptr[i], out));
+
+	drm_puts(p, "\n");
+}
+
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	int i;
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	drm_printf(p, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
-	for (i = 0; i < gpu->nr_rings; i++) {
-		struct msm_ringbuffer *ring = gpu->rb[i];
+	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
 
-		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
-			ring->memptrs->fence, ring->seqno);
+	drm_puts(p, "ringbuffer:\n");
 
-		seq_printf(m, "      rptr:     %d\n",
-			get_rptr(adreno_gpu, ring));
-		seq_printf(m, "rb wptr:  %d\n", get_wptr(ring));
+	for (i = 0; i < gpu->nr_rings; i++) {
+		drm_printf(p, "  - id: %d\n", i);
+		drm_printf(p, "    iova: 0x%016llx\n", state->ring[i].iova);
+		drm_printf(p, "    last-fence: %d\n", state->ring[i].seqno);
+		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
+		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
+		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
+		drm_printf(p, "    size: %d\n", MSM_GPU_RINGBUFFER_SZ);
+
+		adreno_show_object(p, state->ring[i].data,
+			state->ring[i].data_size);
 	}
 
-	/* dump these out in a form that can be parsed by demsm: */
-	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
-	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
-		uint32_t start = adreno_gpu->registers[i];
-		uint32_t end   = adreno_gpu->registers[i+1];
-		uint32_t addr;
+	if (state->bos) {
+		drm_puts(p, "bos:\n");
 
-		for (addr = start; addr <= end; addr++) {
-			uint32_t val = gpu_read(gpu, addr);
-			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
+		for (i = 0; i < state->nr_bos; i++) {
+			drm_printf(p, "  - iova: 0x%016llx\n",
+				state->bos[i].iova);
+			drm_printf(p, "    size: %zd\n", state->bos[i].size);
+
+			adreno_show_object(p, state->bos[i].data,
+				state->bos[i].size);
 		}
 	}
+
+	drm_puts(p, "registers:\n");
+
+	for (i = 0; i < state->nr_registers; i++) {
+		drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+			state->registers[i * 2] << 2,
+			state->registers[(i * 2) + 1]);
+	}
 }
 #endif
 
@@ -565,7 +711,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_get_pwrlevels(&pdev->dev, gpu);
 
-	pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
+	pm_runtime_set_autosuspend_delay(&pdev->dev,
+		adreno_gpu->info->inactive_period);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index d6b0e7b813f4..4406776597fd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -84,6 +84,7 @@ struct adreno_info {
 	enum adreno_quirks quirks;
 	struct msm_gpu *(*init)(struct drm_device *dev);
 	const char *zapfw;
+	u32 inactive_period;
 };
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);
@@ -214,8 +215,9 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		struct msm_file_private *ctx);
 void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
 bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
-#ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m);
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p);
 #endif
 void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
@@ -228,6 +230,11 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
+void adreno_gpu_state_destroy(struct msm_gpu_state *state);
+
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
+int adreno_gpu_state_put(struct msm_gpu_state *state);
+
 /* ringbuffer helpers (the parts that are adreno specific) */
 
 static inline void
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
new file mode 100644
index 000000000000..879c13fe74e0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -0,0 +1,479 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include "dpu_core_irq.h"
+#include "dpu_trace.h"
+
+/**
+ * dpu_core_irq_callback_handler - dispatch core interrupts
+ * @arg:		private data of callback handler
+ * @irq_idx:		interrupt index
+ */
+static void dpu_core_irq_callback_handler(void *arg, int irq_idx)
+{
+	struct dpu_kms *dpu_kms = arg;
+	struct dpu_irq *irq_obj = &dpu_kms->irq_obj;
+	struct dpu_irq_callback *cb;
+	unsigned long irq_flags;
+
+	pr_debug("irq_idx=%d\n", irq_idx);
+
+	if (list_empty(&irq_obj->irq_cb_tbl[irq_idx])) {
+		DRM_ERROR("no registered cb, idx:%d enable_count:%d\n", irq_idx,
+			atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]));
+	}
+
+	atomic_inc(&irq_obj->irq_counts[irq_idx]);
+
+	/*
+	 * Perform registered function callback
+	 */
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	list_for_each_entry(cb, &irq_obj->irq_cb_tbl[irq_idx], list)
+		if (cb->func)
+			cb->func(cb->arg, irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	/*
+	 * Clear pending interrupt status in HW.
+	 * NOTE: dpu_core_irq_callback_handler is protected by top-level
+	 *       spinlock, so it is safe to clear any interrupt status here.
+	 */
+	dpu_kms->hw_intr->ops.clear_intr_status_nolock(
+			dpu_kms->hw_intr,
+			irq_idx);
+}
+
+int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms,
+		enum dpu_intr_type intr_type, u32 instance_idx)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.irq_idx_lookup)
+		return -EINVAL;
+
+	return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type,
+			instance_idx);
+}
+
+/**
+ * _dpu_core_irq_enable - enable core interrupt given by the index
+ * @dpu_kms:		Pointer to dpu kms context
+ * @irq_idx:		interrupt index
+ */
+static int _dpu_core_irq_enable(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	unsigned long irq_flags;
+	int ret = 0, enable_count;
+
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->irq_obj.enable_counts ||
+			!dpu_kms->irq_obj.irq_counts) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]);
+	DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count);
+	trace_dpu_core_irq_enable_idx(irq_idx, enable_count);
+
+	if (atomic_inc_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 1) {
+		ret = dpu_kms->hw_intr->ops.enable_irq(
+				dpu_kms->hw_intr,
+				irq_idx);
+		if (ret)
+			DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n",
+					irq_idx);
+
+		DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret);
+
+		spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+		/* empty callback list but interrupt is enabled */
+		if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]))
+			DPU_ERROR("irq_idx=%d enabled with no callback\n",
+					irq_idx);
+		spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	}
+
+	return ret;
+}
+
+int dpu_core_irq_enable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
+{
+	int i, ret = 0, counts;
+
+	if (!dpu_kms || !irq_idxs || !irq_count) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]);
+	if (counts)
+		DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts);
+
+	for (i = 0; (i < irq_count) && !ret; i++)
+		ret = _dpu_core_irq_enable(dpu_kms, irq_idxs[i]);
+
+	return ret;
+}
+
+/**
+ * _dpu_core_irq_disable - disable core interrupt given by the index
+ * @dpu_kms:		Pointer to dpu kms context
+ * @irq_idx:		interrupt index
+ */
+static int _dpu_core_irq_disable(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	int ret = 0, enable_count;
+
+	if (!dpu_kms || !dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]);
+	DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count);
+	trace_dpu_core_irq_disable_idx(irq_idx, enable_count);
+
+	if (atomic_dec_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 0) {
+		ret = dpu_kms->hw_intr->ops.disable_irq(
+				dpu_kms->hw_intr,
+				irq_idx);
+		if (ret)
+			DPU_ERROR("Fail to disable IRQ for irq_idx:%d\n",
+					irq_idx);
+		DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret);
+	}
+
+	return ret;
+}
+
+int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
+{
+	int i, ret = 0, counts;
+
+	if (!dpu_kms || !irq_idxs || !irq_count) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]);
+	if (counts == 2)
+		DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts);
+
+	for (i = 0; (i < irq_count) && !ret; i++)
+		ret = _dpu_core_irq_disable(dpu_kms, irq_idxs[i]);
+
+	return ret;
+}
+
+u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.get_interrupt_status)
+		return 0;
+
+	if (irq_idx < 0) {
+		DPU_ERROR("[%pS] invalid irq_idx=%d\n",
+				__builtin_return_address(0), irq_idx);
+		return 0;
+	}
+
+	return dpu_kms->hw_intr->ops.get_interrupt_status(dpu_kms->hw_intr,
+			irq_idx, clear);
+}
+
+int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		struct dpu_irq_callback *register_irq_cb)
+{
+	unsigned long irq_flags;
+
+	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (!register_irq_cb || !register_irq_cb->func) {
+		DPU_ERROR("invalid irq_cb:%d func:%d\n",
+				register_irq_cb != NULL,
+				register_irq_cb ?
+					register_irq_cb->func != NULL : -1);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	trace_dpu_core_irq_register_callback(irq_idx, register_irq_cb);
+	list_del_init(&register_irq_cb->list);
+	list_add_tail(&register_irq_cb->list,
+			&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	return 0;
+}
+
+int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		struct dpu_irq_callback *register_irq_cb)
+{
+	unsigned long irq_flags;
+
+	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (!register_irq_cb || !register_irq_cb->func) {
+		DPU_ERROR("invalid irq_cb:%d func:%d\n",
+				register_irq_cb != NULL,
+				register_irq_cb ?
+					register_irq_cb->func != NULL : -1);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	trace_dpu_core_irq_unregister_callback(irq_idx, register_irq_cb);
+	list_del_init(&register_irq_cb->list);
+	/* empty callback list but interrupt is still enabled */
+	if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]) &&
+			atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]))
+		DPU_ERROR("irq_idx=%d enabled with no callback\n", irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	return 0;
+}
+
+static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.clear_all_irqs)
+		return;
+
+	dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr);
+}
+
+static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.disable_all_irqs)
+		return;
+
+	dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr);
+}
+
+#ifdef CONFIG_DEBUG_FS
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)				\
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
+{
+	struct dpu_irq *irq_obj = s->private;
+	struct dpu_irq_callback *cb;
+	unsigned long irq_flags;
+	int i, irq_count, enable_count, cb_count;
+
+	if (!irq_obj || !irq_obj->enable_counts || !irq_obj->irq_cb_tbl) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	for (i = 0; i < irq_obj->total_irqs; i++) {
+		spin_lock_irqsave(&irq_obj->cb_lock, irq_flags);
+		cb_count = 0;
+		irq_count = atomic_read(&irq_obj->irq_counts[i]);
+		enable_count = atomic_read(&irq_obj->enable_counts[i]);
+		list_for_each_entry(cb, &irq_obj->irq_cb_tbl[i], list)
+			cb_count++;
+		spin_unlock_irqrestore(&irq_obj->cb_lock, irq_flags);
+
+		if (irq_count || enable_count || cb_count)
+			seq_printf(s, "idx:%d irq:%d enable:%d cb:%d\n",
+					i, irq_count, enable_count, cb_count);
+	}
+
+	return 0;
+}
+
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_core_irq);
+
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	dpu_kms->irq_obj.debugfs_file = debugfs_create_file("core_irq", 0600,
+			parent, &dpu_kms->irq_obj,
+			&dpu_debugfs_core_irq_fops);
+
+	return 0;
+}
+
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove(dpu_kms->irq_obj.debugfs_file);
+	dpu_kms->irq_obj.debugfs_file = NULL;
+}
+
+#else
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	return 0;
+}
+
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+
+void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid drm device\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	dpu_clear_all_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	spin_lock_init(&dpu_kms->irq_obj.cb_lock);
+
+	/* Create irq callbacks for all possible irq_idx */
+	dpu_kms->irq_obj.total_irqs = dpu_kms->hw_intr->irq_idx_tbl_size;
+	dpu_kms->irq_obj.irq_cb_tbl = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(struct list_head), GFP_KERNEL);
+	dpu_kms->irq_obj.enable_counts = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(atomic_t), GFP_KERNEL);
+	dpu_kms->irq_obj.irq_counts = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(atomic_t), GFP_KERNEL);
+	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) {
+		INIT_LIST_HEAD(&dpu_kms->irq_obj.irq_cb_tbl[i]);
+		atomic_set(&dpu_kms->irq_obj.enable_counts[i], 0);
+		atomic_set(&dpu_kms->irq_obj.irq_counts[i], 0);
+	}
+}
+
+int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms)
+{
+	return 0;
+}
+
+void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid drm device\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++)
+		if (atomic_read(&dpu_kms->irq_obj.enable_counts[i]) ||
+				!list_empty(&dpu_kms->irq_obj.irq_cb_tbl[i]))
+			DPU_ERROR("irq_idx=%d still enabled/registered\n", i);
+
+	dpu_clear_all_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	kfree(dpu_kms->irq_obj.irq_cb_tbl);
+	kfree(dpu_kms->irq_obj.enable_counts);
+	kfree(dpu_kms->irq_obj.irq_counts);
+	dpu_kms->irq_obj.irq_cb_tbl = NULL;
+	dpu_kms->irq_obj.enable_counts = NULL;
+	dpu_kms->irq_obj.irq_counts = NULL;
+	dpu_kms->irq_obj.total_irqs = 0;
+}
+
+irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms)
+{
+	/*
+	 * Read interrupt status from all sources. Interrupt status are
+	 * stored within hw_intr.
+	 * Function will also clear the interrupt status after reading.
+	 * Individual interrupt status bit will only get stored if it
+	 * is enabled.
+	 */
+	dpu_kms->hw_intr->ops.get_interrupt_statuses(dpu_kms->hw_intr);
+
+	/*
+	 * Dispatch to HW driver to handle interrupt lookup that is being
+	 * fired. When matching interrupt is located, HW driver will call to
+	 * dpu_core_irq_callback_handler with the irq_idx from the lookup table.
+	 * dpu_core_irq_callback_handler will perform the registered function
+	 * callback, and do the interrupt status clearing once the registered
+	 * callback is finished.
+	 */
+	dpu_kms->hw_intr->ops.dispatch_irqs(
+			dpu_kms->hw_intr,
+			dpu_core_irq_callback_handler,
+			dpu_kms);
+
+	return IRQ_HANDLED;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
new file mode 100644
index 000000000000..5e98bba46af5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
@@ -0,0 +1,153 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_CORE_IRQ_H__
+#define __DPU_CORE_IRQ_H__
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+
+/**
+ * dpu_core_irq_preinstall - perform pre-installation of core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		none
+ */
+void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_postinstall - perform post-installation of core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		0 if success; error code otherwise
+ */
+int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_uninstall - uninstall core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		none
+ */
+void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq - core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_idx_lookup - IRQ helper function for lookup irq_idx from HW
+ *                      interrupt mapping table.
+ * @dpu_kms:		DPU handle
+ * @intr_type:		DPU HW interrupt type for lookup
+ * @instance_idx:	DPU HW block instance defined in dpu_hw_mdss.h
+ * @return:		irq_idx or -EINVAL when fail to lookup
+ */
+int dpu_core_irq_idx_lookup(
+		struct dpu_kms *dpu_kms,
+		enum dpu_intr_type intr_type,
+		uint32_t instance_idx);
+
+/**
+ * dpu_core_irq_enable - IRQ helper function for enabling one or more IRQs
+ * @dpu_kms:		DPU handle
+ * @irq_idxs:		Array of irq index
+ * @irq_count:		Number of irq_idx provided in the array
+ * @return:		0 for success enabling IRQ, otherwise failure
+ *
+ * This function increments count on each enable and decrements on each
+ * disable.  Interrupts is enabled if count is 0 before increment.
+ */
+int dpu_core_irq_enable(
+		struct dpu_kms *dpu_kms,
+		int *irq_idxs,
+		uint32_t irq_count);
+
+/**
+ * dpu_core_irq_disable - IRQ helper function for disabling one of more IRQs
+ * @dpu_kms:		DPU handle
+ * @irq_idxs:		Array of irq index
+ * @irq_count:		Number of irq_idx provided in the array
+ * @return:		0 for success disabling IRQ, otherwise failure
+ *
+ * This function increments count on each enable and decrements on each
+ * disable.  Interrupts is disabled if count is 0 after decrement.
+ */
+int dpu_core_irq_disable(
+		struct dpu_kms *dpu_kms,
+		int *irq_idxs,
+		uint32_t irq_count);
+
+/**
+ * dpu_core_irq_read - IRQ helper function for reading IRQ status
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @clear:		True to clear the irq after read
+ * @return:		non-zero if irq detected; otherwise no irq detected
+ */
+u32 dpu_core_irq_read(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		bool clear);
+
+/**
+ * dpu_core_irq_register_callback - For registering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback structure, containing callback function
+ *			and argument. Passing NULL for irq_cb will unregister
+ *			the callback for the given irq_idx
+ *			This must exist until un-registration.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_register_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		struct dpu_irq_callback *irq_cb);
+
+/**
+ * dpu_core_irq_unregister_callback - For unregistering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback structure, containing callback function
+ *			and argument. Passing NULL for irq_cb will unregister
+ *			the callback for the given irq_idx
+ *			This must match with registration.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_unregister_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		struct dpu_irq_callback *irq_cb);
+
+/**
+ * dpu_debugfs_core_irq_init - register core irq debugfs
+ * @dpu_kms: pointer to kms
+ * @parent: debugfs directory root
+ * @Return: 0 on success
+ */
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent);
+
+/**
+ * dpu_debugfs_core_irq_destroy - deregister core irq debugfs
+ * @dpu_kms: pointer to kms
+ */
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms);
+
+#endif /* __DPU_CORE_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
new file mode 100644
index 000000000000..41c5191f9056
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -0,0 +1,637 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/sort.h>
+#include <linux/clk.h>
+#include <linux/bitmap.h>
+
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_core_perf.h"
+
+#define DPU_PERF_MODE_STRING_SIZE	128
+
+/**
+ * enum dpu_perf_mode - performance tuning mode
+ * @DPU_PERF_MODE_NORMAL: performance controlled by user mode client
+ * @DPU_PERF_MODE_MINIMUM: performance bounded by minimum setting
+ * @DPU_PERF_MODE_FIXED: performance bounded by fixed setting
+ */
+enum dpu_perf_mode {
+	DPU_PERF_MODE_NORMAL,
+	DPU_PERF_MODE_MINIMUM,
+	DPU_PERF_MODE_FIXED,
+	DPU_PERF_MODE_MAX
+};
+
+static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+
+	if (!crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid device\n");
+		return NULL;
+	}
+
+	priv = crtc->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return NULL;
+	}
+
+	return to_dpu_kms(priv->kms);
+}
+
+static bool _dpu_core_perf_crtc_is_power_on(struct drm_crtc *crtc)
+{
+	return dpu_crtc_is_enabled(crtc);
+}
+
+static bool _dpu_core_video_mode_intf_connected(struct drm_crtc *crtc)
+{
+	struct drm_crtc *tmp_crtc;
+	bool intf_connected = false;
+
+	if (!crtc)
+		goto end;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if ((dpu_crtc_get_intf_mode(tmp_crtc) == INTF_MODE_VIDEO) &&
+				_dpu_core_perf_crtc_is_power_on(tmp_crtc)) {
+			DPU_DEBUG("video interface connected crtc:%d\n",
+				tmp_crtc->base.id);
+			intf_connected = true;
+			goto end;
+		}
+	}
+
+end:
+	return intf_connected;
+}
+
+static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
+		struct drm_crtc *crtc,
+		struct drm_crtc_state *state,
+		struct dpu_core_perf_params *perf)
+{
+	struct dpu_crtc_state *dpu_cstate;
+	int i;
+
+	if (!kms || !kms->catalog || !crtc || !state || !perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_cstate = to_dpu_crtc_state(state);
+	memset(perf, 0, sizeof(struct dpu_core_perf_params));
+
+	if (!dpu_cstate->bw_control) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = kms->catalog->perf.max_bw_high *
+					1000ULL;
+			perf->max_per_pipe_ib[i] = perf->bw_ctl[i];
+		}
+		perf->core_clk_rate = kms->perf.max_core_clk_rate;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = 0;
+			perf->max_per_pipe_ib[i] = 0;
+		}
+		perf->core_clk_rate = 0;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = kms->perf.fix_core_ab_vote;
+			perf->max_per_pipe_ib[i] = kms->perf.fix_core_ib_vote;
+		}
+		perf->core_clk_rate = kms->perf.fix_core_clk_rate;
+	}
+
+	DPU_DEBUG(
+		"crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu llcc_ib=%llu llcc_ab=%llu mem_ib=%llu mem_ab=%llu\n",
+			crtc->base.id, perf->core_clk_rate,
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_EBI],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI]);
+}
+
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	u32 bw, threshold;
+	u64 bw_sum_of_intfs = 0;
+	enum dpu_crtc_client_type curr_client_type;
+	bool is_video_mode;
+	struct dpu_crtc_state *dpu_cstate;
+	struct drm_crtc *tmp_crtc;
+	struct dpu_kms *kms;
+	int i;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	/* we only need bandwidth check on real-time clients (interfaces) */
+	if (dpu_crtc_get_client_type(crtc) == NRT_CLIENT)
+		return 0;
+
+	dpu_cstate = to_dpu_crtc_state(state);
+
+	/* obtain new values */
+	_dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf);
+
+	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
+			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl[i];
+		curr_client_type = dpu_crtc_get_client_type(crtc);
+
+		drm_for_each_crtc(tmp_crtc, crtc->dev) {
+			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			    (dpu_crtc_get_client_type(tmp_crtc) ==
+					    curr_client_type) &&
+			    (tmp_crtc != crtc)) {
+				struct dpu_crtc_state *tmp_cstate =
+					to_dpu_crtc_state(tmp_crtc->state);
+
+				DPU_DEBUG("crtc:%d bw:%llu ctrl:%d\n",
+					tmp_crtc->base.id,
+					tmp_cstate->new_perf.bw_ctl[i],
+					tmp_cstate->bw_control);
+				/*
+				 * For bw check only use the bw if the
+				 * atomic property has been already set
+				 */
+				if (tmp_cstate->bw_control)
+					bw_sum_of_intfs +=
+						tmp_cstate->new_perf.bw_ctl[i];
+			}
+		}
+
+		/* convert bandwidth to kb */
+		bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000);
+		DPU_DEBUG("calculated bandwidth=%uk\n", bw);
+
+		is_video_mode = dpu_crtc_get_intf_mode(crtc) == INTF_MODE_VIDEO;
+		threshold = (is_video_mode ||
+			_dpu_core_video_mode_intf_connected(crtc)) ?
+			kms->catalog->perf.max_bw_low :
+			kms->catalog->perf.max_bw_high;
+
+		DPU_DEBUG("final threshold bw limit = %d\n", threshold);
+
+		if (!dpu_cstate->bw_control) {
+			DPU_DEBUG("bypass bandwidth check\n");
+		} else if (!threshold) {
+			DPU_ERROR("no bandwidth limits specified\n");
+			return -E2BIG;
+		} else if (bw > threshold) {
+			DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw,
+					threshold);
+			return -E2BIG;
+		}
+	}
+
+	return 0;
+}
+
+static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
+		struct drm_crtc *crtc, u32 bus_id)
+{
+	struct dpu_core_perf_params perf = { { 0 } };
+	enum dpu_crtc_client_type curr_client_type
+					= dpu_crtc_get_client_type(crtc);
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int ret = 0;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			curr_client_type ==
+				dpu_crtc_get_client_type(tmp_crtc)) {
+			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
+
+			perf.max_per_pipe_ib[bus_id] =
+				max(perf.max_per_pipe_ib[bus_id],
+				dpu_cstate->new_perf.max_per_pipe_ib[bus_id]);
+
+			DPU_DEBUG("crtc=%d bus_id=%d bw=%llu\n",
+				tmp_crtc->base.id, bus_id,
+				dpu_cstate->new_perf.bw_ctl[bus_id]);
+		}
+	}
+	return ret;
+}
+
+/**
+ * @dpu_core_perf_crtc_release_bw() - request zero bandwidth
+ * @crtc - pointer to a crtc
+ *
+ * Function checks a state variable for the crtc, if all pending commit
+ * requests are done, meaning no more bandwidth is needed, release
+ * bandwidth request.
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
+{
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	struct dpu_kms *kms;
+	int i;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	/* only do this for command mode rt client */
+	if (dpu_crtc_get_intf_mode(crtc) != INTF_MODE_CMD)
+		return;
+
+	/*
+	 * If video interface present, cmd panel bandwidth cannot be
+	 * released.
+	 */
+	if (dpu_crtc_get_intf_mode(crtc) == INTF_MODE_CMD)
+		drm_for_each_crtc(tmp_crtc, crtc->dev) {
+			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+				dpu_crtc_get_intf_mode(tmp_crtc) ==
+						INTF_MODE_VIDEO)
+				return;
+		}
+
+	/* Release the bandwidth */
+	if (kms->perf.enable_bw_release) {
+		trace_dpu_cmd_release_bw(crtc->base.id);
+		DPU_DEBUG("Release BW crtc=%d\n", crtc->base.id);
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			dpu_crtc->cur_perf.bw_ctl[i] = 0;
+			_dpu_core_perf_crtc_update_bus(kms, crtc, i);
+		}
+	}
+}
+
+static int _dpu_core_perf_set_core_clk_rate(struct dpu_kms *kms, u64 rate)
+{
+	struct dss_clk *core_clk = kms->perf.core_clk;
+
+	if (core_clk->max_rate && (rate > core_clk->max_rate))
+		rate = core_clk->max_rate;
+
+	core_clk->rate = rate;
+	return msm_dss_clk_set_rate(core_clk, 1);
+}
+
+static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
+{
+	u64 clk_rate = kms->perf.perf_tune.min_core_clk;
+	struct drm_crtc *crtc;
+	struct dpu_crtc_state *dpu_cstate;
+
+	drm_for_each_crtc(crtc, kms->dev) {
+		if (_dpu_core_perf_crtc_is_power_on(crtc)) {
+			dpu_cstate = to_dpu_crtc_state(crtc->state);
+			clk_rate = max(dpu_cstate->new_perf.core_clk_rate,
+							clk_rate);
+			clk_rate = clk_round_rate(kms->perf.core_clk->clk,
+					clk_rate);
+		}
+	}
+
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED)
+		clk_rate = kms->perf.fix_core_clk_rate;
+
+	DPU_DEBUG("clk:%llu\n", clk_rate);
+
+	return clk_rate;
+}
+
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req)
+{
+	struct dpu_core_perf_params *new, *old;
+	int update_bus = 0, update_clk = 0;
+	u64 clk_rate = 0;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int i;
+	struct msm_drm_private *priv;
+	struct dpu_kms *kms;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+	priv = kms->dev->dev_private;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	DPU_DEBUG("crtc:%d stop_req:%d core_clk:%llu\n",
+			crtc->base.id, stop_req, kms->perf.core_clk_rate);
+
+	old = &dpu_crtc->cur_perf;
+	new = &dpu_cstate->new_perf;
+
+	if (_dpu_core_perf_crtc_is_power_on(crtc) && !stop_req) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			/*
+			 * cases for bus bandwidth update.
+			 * 1. new bandwidth vote - "ab or ib vote" is higher
+			 *    than current vote for update request.
+			 * 2. new bandwidth vote - "ab or ib vote" is lower
+			 *    than current vote at end of commit or stop.
+			 */
+			if ((params_changed && ((new->bw_ctl[i] >
+						old->bw_ctl[i]) ||
+				  (new->max_per_pipe_ib[i] >
+						old->max_per_pipe_ib[i]))) ||
+			    (!params_changed && ((new->bw_ctl[i] <
+						old->bw_ctl[i]) ||
+				  (new->max_per_pipe_ib[i] <
+						old->max_per_pipe_ib[i])))) {
+				DPU_DEBUG(
+					"crtc=%d p=%d new_bw=%llu,old_bw=%llu\n",
+					crtc->base.id, params_changed,
+					new->bw_ctl[i], old->bw_ctl[i]);
+				old->bw_ctl[i] = new->bw_ctl[i];
+				old->max_per_pipe_ib[i] =
+						new->max_per_pipe_ib[i];
+				update_bus |= BIT(i);
+			}
+		}
+
+		if ((params_changed &&
+				(new->core_clk_rate > old->core_clk_rate)) ||
+				(!params_changed &&
+				(new->core_clk_rate < old->core_clk_rate))) {
+			old->core_clk_rate = new->core_clk_rate;
+			update_clk = 1;
+		}
+	} else {
+		DPU_DEBUG("crtc=%d disable\n", crtc->base.id);
+		memset(old, 0, sizeof(*old));
+		memset(new, 0, sizeof(*new));
+		update_bus = ~0;
+		update_clk = 1;
+	}
+	trace_dpu_perf_crtc_update(crtc->base.id,
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI],
+				new->core_clk_rate, stop_req,
+				update_bus, update_clk);
+
+	for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		if (update_bus & BIT(i)) {
+			ret = _dpu_core_perf_crtc_update_bus(kms, crtc, i);
+			if (ret) {
+				DPU_ERROR("crtc-%d: failed to update bw vote for bus-%d\n",
+					  crtc->base.id, i);
+				return ret;
+			}
+		}
+	}
+
+	/*
+	 * Update the clock after bandwidth vote to ensure
+	 * bandwidth is available before clock rate is increased.
+	 */
+	if (update_clk) {
+		clk_rate = _dpu_core_perf_get_core_clk_rate(kms);
+
+		trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate);
+
+		ret = _dpu_core_perf_set_core_clk_rate(kms, clk_rate);
+		if (ret) {
+			DPU_ERROR("failed to set %s clock rate %llu\n",
+					kms->perf.core_clk->clk_name, clk_rate);
+			return ret;
+		}
+
+		kms->perf.core_clk_rate = clk_rate;
+		DPU_DEBUG("update clk rate = %lld HZ\n", clk_rate);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static ssize_t _dpu_core_perf_mode_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	struct dpu_perf_cfg *cfg = &perf->catalog->perf;
+	u32 perf_mode = 0;
+	char buf[10];
+
+	if (!perf)
+		return -ENODEV;
+
+	if (count >= sizeof(buf))
+		return -EFAULT;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[count] = 0;	/* end of string */
+
+	if (kstrtouint(buf, 0, &perf_mode))
+		return -EFAULT;
+
+	if (perf_mode >= DPU_PERF_MODE_MAX)
+		return -EFAULT;
+
+	if (perf_mode == DPU_PERF_MODE_FIXED) {
+		DRM_INFO("fix performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_MINIMUM) {
+		/* run the driver with max clk and BW vote */
+		perf->perf_tune.min_core_clk = perf->max_core_clk_rate;
+		perf->perf_tune.min_bus_vote =
+				(u64) cfg->max_bw_high * 1000;
+		DRM_INFO("minimum performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_NORMAL) {
+		/* reset the perf tune params to 0 */
+		perf->perf_tune.min_core_clk = 0;
+		perf->perf_tune.min_bus_vote = 0;
+		DRM_INFO("normal performance mode\n");
+	}
+	perf->perf_tune.mode = perf_mode;
+
+	return count;
+}
+
+static ssize_t _dpu_core_perf_mode_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	int len = 0;
+	char buf[DPU_PERF_MODE_STRING_SIZE] = {'\0'};
+
+	if (!perf)
+		return -ENODEV;
+
+	if (*ppos)
+		return 0;	/* the end */
+
+	len = snprintf(buf, sizeof(buf),
+			"mode %d min_mdp_clk %llu min_bus_vote %llu\n",
+			perf->perf_tune.mode,
+			perf->perf_tune.min_core_clk,
+			perf->perf_tune.min_bus_vote);
+	if (len < 0 || len >= sizeof(buf))
+		return 0;
+
+	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
+		return -EFAULT;
+
+	*ppos += len;   /* increase offset */
+
+	return len;
+}
+
+static const struct file_operations dpu_core_perf_mode_fops = {
+	.open = simple_open,
+	.read = _dpu_core_perf_mode_read,
+	.write = _dpu_core_perf_mode_write,
+};
+
+static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
+{
+	debugfs_remove_recursive(perf->debugfs_root);
+	perf->debugfs_root = NULL;
+}
+
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent)
+{
+	struct dpu_mdss_cfg *catalog = perf->catalog;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	priv = perf->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	perf->debugfs_root = debugfs_create_dir("core_perf", parent);
+	if (!perf->debugfs_root) {
+		DPU_ERROR("failed to create core perf debugfs\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_u64("max_core_clk_rate", 0600, perf->debugfs_root,
+			&perf->max_core_clk_rate);
+	debugfs_create_u64("core_clk_rate", 0600, perf->debugfs_root,
+			&perf->core_clk_rate);
+	debugfs_create_u32("enable_bw_release", 0600, perf->debugfs_root,
+			(u32 *)&perf->enable_bw_release);
+	debugfs_create_u32("threshold_low", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.max_bw_low);
+	debugfs_create_u32("threshold_high", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.max_bw_high);
+	debugfs_create_u32("min_core_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_core_ib);
+	debugfs_create_u32("min_llcc_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_llcc_ib);
+	debugfs_create_u32("min_dram_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_dram_ib);
+	debugfs_create_file("perf_mode", 0600, perf->debugfs_root,
+			(u32 *)perf, &dpu_core_perf_mode_fops);
+	debugfs_create_u64("fix_core_clk_rate", 0600, perf->debugfs_root,
+			&perf->fix_core_clk_rate);
+	debugfs_create_u64("fix_core_ib_vote", 0600, perf->debugfs_root,
+			&perf->fix_core_ib_vote);
+	debugfs_create_u64("fix_core_ab_vote", 0600, perf->debugfs_root,
+			&perf->fix_core_ab_vote);
+
+	return 0;
+}
+#else
+static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
+{
+}
+
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent)
+{
+	return 0;
+}
+#endif
+
+void dpu_core_perf_destroy(struct dpu_core_perf *perf)
+{
+	if (!perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_core_perf_debugfs_destroy(perf);
+	perf->max_core_clk_rate = 0;
+	perf->core_clk = NULL;
+	perf->phandle = NULL;
+	perf->catalog = NULL;
+	perf->dev = NULL;
+}
+
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_power_handle *phandle,
+		struct dss_clk *core_clk)
+{
+	perf->dev = dev;
+	perf->catalog = catalog;
+	perf->phandle = phandle;
+	perf->core_clk = core_clk;
+
+	perf->max_core_clk_rate = core_clk->max_rate;
+	if (!perf->max_core_clk_rate) {
+		DPU_DEBUG("optional max core clk rate, use default\n");
+		perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
new file mode 100644
index 000000000000..fbcbe0c7527a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -0,0 +1,133 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_CORE_PERF_H_
+#define _DPU_CORE_PERF_H_
+
+#include <linux/types.h>
+#include <linux/dcache.h>
+#include <linux/mutex.h>
+#include <drm/drm_crtc.h>
+
+#include "dpu_hw_catalog.h"
+#include "dpu_power_handle.h"
+
+#define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
+
+/**
+ * struct dpu_core_perf_params - definition of performance parameters
+ * @max_per_pipe_ib: maximum instantaneous bandwidth request
+ * @bw_ctl: arbitrated bandwidth request
+ * @core_clk_rate: core clock rate request
+ */
+struct dpu_core_perf_params {
+	u64 max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 core_clk_rate;
+};
+
+/**
+ * struct dpu_core_perf_tune - definition of performance tuning control
+ * @mode: performance mode
+ * @min_core_clk: minimum core clock
+ * @min_bus_vote: minimum bus vote
+ */
+struct dpu_core_perf_tune {
+	u32 mode;
+	u64 min_core_clk;
+	u64 min_bus_vote;
+};
+
+/**
+ * struct dpu_core_perf - definition of core performance context
+ * @dev: Pointer to drm device
+ * @debugfs_root: top level debug folder
+ * @catalog: Pointer to catalog configuration
+ * @phandle: Pointer to power handler
+ * @core_clk: Pointer to core clock structure
+ * @core_clk_rate: current core clock rate
+ * @max_core_clk_rate: maximum allowable core clock rate
+ * @perf_tune: debug control for performance tuning
+ * @enable_bw_release: debug control for bandwidth release
+ * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2
+ * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2
+ * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2
+ */
+struct dpu_core_perf {
+	struct drm_device *dev;
+	struct dentry *debugfs_root;
+	struct dpu_mdss_cfg *catalog;
+	struct dpu_power_handle *phandle;
+	struct dss_clk *core_clk;
+	u64 core_clk_rate;
+	u64 max_core_clk_rate;
+	struct dpu_core_perf_tune perf_tune;
+	u32 enable_bw_release;
+	u64 fix_core_clk_rate;
+	u64 fix_core_ib_vote;
+	u64 fix_core_ab_vote;
+};
+
+/**
+ * dpu_core_perf_crtc_check - validate performance of the given crtc state
+ * @crtc: Pointer to crtc
+ * @state: Pointer to new crtc state
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state);
+
+/**
+ * dpu_core_perf_crtc_update - update performance of the given crtc
+ * @crtc: Pointer to crtc
+ * @params_changed: true if crtc parameters are modified
+ * @stop_req: true if this is a stop request
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req);
+
+/**
+ * dpu_core_perf_crtc_release_bw - release bandwidth of the given crtc
+ * @crtc: Pointer to crtc
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc);
+
+/**
+ * dpu_core_perf_destroy - destroy the given core performance context
+ * @perf: Pointer to core performance context
+ */
+void dpu_core_perf_destroy(struct dpu_core_perf *perf);
+
+/**
+ * dpu_core_perf_init - initialize the given core performance context
+ * @perf: Pointer to core performance context
+ * @dev: Pointer to drm device
+ * @catalog: Pointer to catalog
+ * @phandle: Pointer to power handle
+ * @core_clk: pointer to core clock
+ */
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_power_handle *phandle,
+		struct dss_clk *core_clk);
+
+/**
+ * dpu_core_perf_debugfs_init - initialize debugfs for core performance context
+ * @perf: Pointer to core performance context
+ * @debugfs_parent: Pointer to parent debugfs
+ */
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent);
+
+#endif /* _DPU_CORE_PERF_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
new file mode 100644
index 000000000000..80cbf75bc2ff
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -0,0 +1,2138 @@
+/*
+ * Copyright (c) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/sort.h>
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_flip_work.h>
+#include <drm/drm_rect.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_crtc.h"
+#include "dpu_plane.h"
+#include "dpu_encoder.h"
+#include "dpu_vbif.h"
+#include "dpu_power_handle.h"
+#include "dpu_core_perf.h"
+#include "dpu_trace.h"
+
+#define DPU_DRM_BLEND_OP_NOT_DEFINED    0
+#define DPU_DRM_BLEND_OP_OPAQUE         1
+#define DPU_DRM_BLEND_OP_PREMULTIPLIED  2
+#define DPU_DRM_BLEND_OP_COVERAGE       3
+#define DPU_DRM_BLEND_OP_MAX            4
+
+/* layer mixer index on dpu_crtc */
+#define LEFT_MIXER 0
+#define RIGHT_MIXER 1
+
+#define MISR_BUFF_SIZE			256
+
+static inline struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return NULL;
+	}
+	priv = crtc->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return NULL;
+	}
+
+	return to_dpu_kms(priv->kms);
+}
+
+static inline int _dpu_crtc_power_enable(struct dpu_crtc *dpu_crtc, bool enable)
+{
+	struct drm_crtc *crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid dpu crtc\n");
+		return -EINVAL;
+	}
+
+	crtc = &dpu_crtc->base;
+	if (!crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid drm device\n");
+		return -EINVAL;
+	}
+
+	priv = crtc->dev->dev_private;
+	if (!priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	if (enable)
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	else
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+/**
+ * _dpu_crtc_rp_to_crtc - get crtc from resource pool object
+ * @rp: Pointer to resource pool
+ * return: Pointer to drm crtc if success; null otherwise
+ */
+static struct drm_crtc *_dpu_crtc_rp_to_crtc(struct dpu_crtc_respool *rp)
+{
+	if (!rp)
+		return NULL;
+
+	return container_of(rp, struct dpu_crtc_state, rp)->base.crtc;
+}
+
+/**
+ * _dpu_crtc_rp_reclaim - reclaim unused, or all if forced, resources in pool
+ * @rp: Pointer to resource pool
+ * @force: True to reclaim all resources; otherwise, reclaim only unused ones
+ * return: None
+ */
+static void _dpu_crtc_rp_reclaim(struct dpu_crtc_respool *rp, bool force)
+{
+	struct dpu_crtc_res *res, *next;
+	struct drm_crtc *crtc;
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	DPU_DEBUG("crtc%d.%u %s\n", crtc->base.id, rp->sequence_id,
+			force ? "destroy" : "free_unused");
+
+	list_for_each_entry_safe(res, next, &rp->res_list, list) {
+		if (!force && !(res->flags & DPU_CRTC_RES_FLAG_FREE))
+			continue;
+		DPU_DEBUG("crtc%d.%u reclaim res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		list_del(&res->list);
+		if (res->ops.put)
+			res->ops.put(res->val);
+		kfree(res);
+	}
+}
+
+/**
+ * _dpu_crtc_rp_free_unused - free unused resource in pool
+ * @rp: Pointer to resource pool
+ * return: none
+ */
+static void _dpu_crtc_rp_free_unused(struct dpu_crtc_respool *rp)
+{
+	mutex_lock(rp->rp_lock);
+	_dpu_crtc_rp_reclaim(rp, false);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_destroy - destroy resource pool
+ * @rp: Pointer to resource pool
+ * return: None
+ */
+static void _dpu_crtc_rp_destroy(struct dpu_crtc_respool *rp)
+{
+	mutex_lock(rp->rp_lock);
+	list_del_init(&rp->rp_list);
+	_dpu_crtc_rp_reclaim(rp, true);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_hw_blk_get - get callback for hardware block
+ * @val: Resource handle
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * return: Resource handle
+ */
+static void *_dpu_crtc_hw_blk_get(void *val, u32 type, u64 tag)
+{
+	DPU_DEBUG("res:%d/0x%llx/%pK\n", type, tag, val);
+	return dpu_hw_blk_get(val, type, tag);
+}
+
+/**
+ * _dpu_crtc_hw_blk_put - put callback for hardware block
+ * @val: Resource handle
+ * return: None
+ */
+static void _dpu_crtc_hw_blk_put(void *val)
+{
+	DPU_DEBUG("res://%pK\n", val);
+	dpu_hw_blk_put(val);
+}
+
+/**
+ * _dpu_crtc_rp_duplicate - duplicate resource pool and reset reference count
+ * @rp: Pointer to original resource pool
+ * @dup_rp: Pointer to duplicated resource pool
+ * return: None
+ */
+static void _dpu_crtc_rp_duplicate(struct dpu_crtc_respool *rp,
+		struct dpu_crtc_respool *dup_rp)
+{
+	struct dpu_crtc_res *res, *dup_res;
+	struct drm_crtc *crtc;
+
+	if (!rp || !dup_rp || !rp->rp_head) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	DPU_DEBUG("crtc%d.%u duplicate\n", crtc->base.id, rp->sequence_id);
+
+	mutex_lock(rp->rp_lock);
+	dup_rp->sequence_id = rp->sequence_id + 1;
+	INIT_LIST_HEAD(&dup_rp->res_list);
+	dup_rp->ops = rp->ops;
+	list_for_each_entry(res, &rp->res_list, list) {
+		dup_res = kzalloc(sizeof(struct dpu_crtc_res), GFP_KERNEL);
+		if (!dup_res) {
+			mutex_unlock(rp->rp_lock);
+			return;
+		}
+		INIT_LIST_HEAD(&dup_res->list);
+		atomic_set(&dup_res->refcount, 0);
+		dup_res->type = res->type;
+		dup_res->tag = res->tag;
+		dup_res->val = res->val;
+		dup_res->ops = res->ops;
+		dup_res->flags = DPU_CRTC_RES_FLAG_FREE;
+		DPU_DEBUG("crtc%d.%u dup res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, dup_rp->sequence_id,
+				dup_res->type, dup_res->tag, dup_res->val,
+				atomic_read(&dup_res->refcount));
+		list_add_tail(&dup_res->list, &dup_rp->res_list);
+		if (dup_res->ops.get)
+			dup_res->ops.get(dup_res->val, 0, -1);
+	}
+
+	dup_rp->rp_lock = rp->rp_lock;
+	dup_rp->rp_head = rp->rp_head;
+	INIT_LIST_HEAD(&dup_rp->rp_list);
+	list_add_tail(&dup_rp->rp_list, rp->rp_head);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_reset - reset resource pool after allocation
+ * @rp: Pointer to original resource pool
+ * @rp_lock: Pointer to serialization resource pool lock
+ * @rp_head: Pointer to crtc resource pool head
+ * return: None
+ */
+static void _dpu_crtc_rp_reset(struct dpu_crtc_respool *rp,
+		struct mutex *rp_lock, struct list_head *rp_head)
+{
+	if (!rp || !rp_lock || !rp_head) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	mutex_lock(rp_lock);
+	rp->rp_lock = rp_lock;
+	rp->rp_head = rp_head;
+	INIT_LIST_HEAD(&rp->rp_list);
+	rp->sequence_id = 0;
+	INIT_LIST_HEAD(&rp->res_list);
+	rp->ops.get = _dpu_crtc_hw_blk_get;
+	rp->ops.put = _dpu_crtc_hw_blk_put;
+	list_add_tail(&rp->rp_list, rp->rp_head);
+	mutex_unlock(rp_lock);
+}
+
+static void dpu_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	DPU_DEBUG("\n");
+
+	if (!crtc)
+		return;
+
+	dpu_crtc->phandle = NULL;
+
+	drm_crtc_cleanup(crtc);
+	mutex_destroy(&dpu_crtc->crtc_lock);
+	kfree(dpu_crtc);
+}
+
+static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer,
+		struct dpu_plane_state *pstate)
+{
+	struct dpu_hw_mixer *lm = mixer->hw_lm;
+
+	/* default to opaque blending */
+	lm->ops.setup_blend_config(lm, pstate->stage, 0XFF, 0,
+				DPU_BLEND_FG_ALPHA_FG_CONST |
+				DPU_BLEND_BG_ALPHA_BG_CONST);
+}
+
+static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *crtc_state;
+	int lm_idx, lm_horiz_position;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	crtc_state = to_dpu_crtc_state(crtc->state);
+
+	lm_horiz_position = 0;
+	for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) {
+		const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx];
+		struct dpu_hw_mixer *hw_lm = dpu_crtc->mixers[lm_idx].hw_lm;
+		struct dpu_hw_mixer_cfg cfg;
+
+		if (!lm_roi || !drm_rect_visible(lm_roi))
+			continue;
+
+		cfg.out_width = drm_rect_width(lm_roi);
+		cfg.out_height = drm_rect_height(lm_roi);
+		cfg.right_mixer = lm_horiz_position++;
+		cfg.flags = 0;
+		hw_lm->ops.setup_mixer_out(hw_lm, &cfg);
+	}
+}
+
+static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
+	struct dpu_crtc *dpu_crtc, struct dpu_crtc_mixer *mixer)
+{
+	struct drm_plane *plane;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_format *format;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+	struct dpu_hw_stage_cfg *stage_cfg;
+
+	u32 flush_mask;
+	uint32_t stage_idx, lm_idx;
+	int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 };
+	bool bg_alpha_enable = false;
+
+	if (!dpu_crtc || !mixer) {
+		DPU_ERROR("invalid dpu_crtc or mixer\n");
+		return;
+	}
+
+	ctl = mixer->hw_ctl;
+	lm = mixer->hw_lm;
+	stage_cfg = &dpu_crtc->stage_cfg;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		state = plane->state;
+		if (!state)
+			continue;
+
+		pstate = to_dpu_plane_state(state);
+		fb = state->fb;
+
+		dpu_plane_get_ctl_flush(plane, ctl, &flush_mask);
+
+		DPU_DEBUG("crtc %d stage:%d - plane %d sspp %d fb %d\n",
+				crtc->base.id,
+				pstate->stage,
+				plane->base.id,
+				dpu_plane_pipe(plane) - SSPP_VIG0,
+				state->fb ? state->fb->base.id : -1);
+
+		format = to_dpu_format(msm_framebuffer_format(pstate->base.fb));
+		if (!format) {
+			DPU_ERROR("invalid format\n");
+			return;
+		}
+
+		if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable)
+			bg_alpha_enable = true;
+
+		stage_idx = zpos_cnt[pstate->stage]++;
+		stage_cfg->stage[pstate->stage][stage_idx] =
+					dpu_plane_pipe(plane);
+		stage_cfg->multirect_index[pstate->stage][stage_idx] =
+					pstate->multirect_index;
+
+		trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane),
+					   state, pstate, stage_idx,
+					   dpu_plane_pipe(plane) - SSPP_VIG0,
+					   format->base.pixel_format,
+					   fb ? fb->modifier : 0);
+
+		/* blend config update */
+		for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) {
+			_dpu_crtc_setup_blend_cfg(mixer + lm_idx, pstate);
+
+			mixer[lm_idx].flush_mask |= flush_mask;
+
+			if (bg_alpha_enable && !format->alpha_enable)
+				mixer[lm_idx].mixer_op_mode = 0;
+			else
+				mixer[lm_idx].mixer_op_mode |=
+						1 << pstate->stage;
+		}
+	}
+
+	 _dpu_crtc_program_lm_output_roi(crtc);
+}
+
+/**
+ * _dpu_crtc_blend_setup - configure crtc mixers
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_blend_setup(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_crtc_state;
+	struct dpu_crtc_mixer *mixer;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+
+	int i;
+
+	if (!crtc)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_crtc_state = to_dpu_crtc_state(crtc->state);
+	mixer = dpu_crtc->mixers;
+
+	DPU_DEBUG("%s\n", dpu_crtc->name);
+
+	if (dpu_crtc->num_mixers > CRTC_DUAL_MIXERS) {
+		DPU_ERROR("invalid number mixers: %d\n", dpu_crtc->num_mixers);
+		return;
+	}
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		if (!mixer[i].hw_lm || !mixer[i].hw_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].hw_ctl->ops.clear_all_blendstages)
+			mixer[i].hw_ctl->ops.clear_all_blendstages(
+					mixer[i].hw_ctl);
+	}
+
+	/* initialize stage cfg */
+	memset(&dpu_crtc->stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg));
+
+	_dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer);
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		ctl = mixer[i].hw_ctl;
+		lm = mixer[i].hw_lm;
+
+		lm->ops.setup_alpha_out(lm, mixer[i].mixer_op_mode);
+
+		mixer[i].flush_mask |= ctl->ops.get_bitmask_mixer(ctl,
+			mixer[i].hw_lm->idx);
+
+		/* stage config flush mask */
+		ctl->ops.update_pending_flush(ctl, mixer[i].flush_mask);
+
+		DPU_DEBUG("lm %d, op_mode 0x%X, ctl %d, flush mask 0x%x\n",
+			mixer[i].hw_lm->idx - LM_0,
+			mixer[i].mixer_op_mode,
+			ctl->idx - CTL_0,
+			mixer[i].flush_mask);
+
+		ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx,
+			&dpu_crtc->stage_cfg);
+	}
+}
+
+/**
+ *  _dpu_crtc_complete_flip - signal pending page_flip events
+ * Any pending vblank events are added to the vblank_event_list
+ * so that the next vblank interrupt shall signal them.
+ * However PAGE_FLIP events are not handled through the vblank_event_list.
+ * This API signals any pending PAGE_FLIP events requested through
+ * DRM_IOCTL_MODE_PAGE_FLIP and are cached in the dpu_crtc->event.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_complete_flip(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (dpu_crtc->event) {
+		DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name,
+			      dpu_crtc->event);
+		trace_dpu_crtc_complete_flip(DRMID(crtc));
+		drm_crtc_send_vblank_event(crtc, dpu_crtc->event);
+		dpu_crtc->event = NULL;
+	}
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+
+	if (!crtc || !crtc->dev) {
+		DPU_ERROR("invalid crtc\n");
+		return INTF_MODE_NONE;
+	}
+
+	drm_for_each_encoder(encoder, crtc->dev)
+		if (encoder->crtc == crtc)
+			return dpu_encoder_get_intf_mode(encoder);
+
+	return INTF_MODE_NONE;
+}
+
+static void dpu_crtc_vblank_cb(void *data)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	/* keep statistics on vblank callback - with auto reset via debugfs */
+	if (ktime_compare(dpu_crtc->vblank_cb_time, ktime_set(0, 0)) == 0)
+		dpu_crtc->vblank_cb_time = ktime_get();
+	else
+		dpu_crtc->vblank_cb_count++;
+	_dpu_crtc_complete_flip(crtc);
+	drm_crtc_handle_vblank(crtc);
+	trace_dpu_crtc_vblank_cb(DRMID(crtc));
+}
+
+static void dpu_crtc_frame_event_work(struct kthread_work *work)
+{
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	struct drm_crtc *crtc;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *dpu_kms;
+	unsigned long flags;
+	bool frame_done = false;
+
+	if (!work) {
+		DPU_ERROR("invalid work handle\n");
+		return;
+	}
+
+	fevent = container_of(work, struct dpu_crtc_frame_event, work);
+	if (!fevent->crtc || !fevent->crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	crtc = fevent->crtc;
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid kms handle\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+	DPU_ATRACE_BEGIN("crtc_frame_event");
+
+	DRM_DEBUG_KMS("crtc%d event:%u ts:%lld\n", crtc->base.id, fevent->event,
+			ktime_to_ns(fevent->ts));
+
+	if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+				| DPU_ENCODER_FRAME_EVENT_ERROR
+				| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (atomic_read(&dpu_crtc->frame_pending) < 1) {
+			/* this should not happen */
+			DRM_ERROR("crtc%d ev:%u ts:%lld frame_pending:%d\n",
+					crtc->base.id,
+					fevent->event,
+					ktime_to_ns(fevent->ts),
+					atomic_read(&dpu_crtc->frame_pending));
+		} else if (atomic_dec_return(&dpu_crtc->frame_pending) == 0) {
+			/* release bandwidth and other resources */
+			trace_dpu_crtc_frame_event_done(DRMID(crtc),
+							fevent->event);
+			dpu_core_perf_crtc_release_bw(crtc);
+		} else {
+			trace_dpu_crtc_frame_event_more_pending(DRMID(crtc),
+								fevent->event);
+		}
+
+		if (fevent->event & DPU_ENCODER_FRAME_EVENT_DONE)
+			dpu_core_perf_crtc_update(crtc, 0, false);
+
+		if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+					| DPU_ENCODER_FRAME_EVENT_ERROR))
+			frame_done = true;
+	}
+
+	if (fevent->event & DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)
+		DPU_ERROR("crtc%d ts:%lld received panel dead event\n",
+				crtc->base.id, ktime_to_ns(fevent->ts));
+
+	if (frame_done)
+		complete_all(&dpu_crtc->frame_done_comp);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	list_add_tail(&fevent->list, &dpu_crtc->frame_event_list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+	DPU_ATRACE_END("crtc_frame_event");
+}
+
+/*
+ * dpu_crtc_frame_event_cb - crtc frame event callback API. CRTC module
+ * registers this API to encoder for all frame event callbacks like
+ * frame_error, frame_done, idle_timeout, etc. Encoder may call different events
+ * from different context - IRQ, user thread, commit_thread, etc. Each event
+ * should be carefully reviewed and should be processed in proper task context
+ * to avoid schedulin delay or properly manage the irq context's bottom half
+ * processing.
+ */
+static void dpu_crtc_frame_event_cb(void *data, u32 event)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	unsigned long flags;
+	u32 crtc_id;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	/* Nothing to do on idle event */
+	if (event & DPU_ENCODER_FRAME_EVENT_IDLE)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+	crtc_id = drm_crtc_index(crtc);
+
+	trace_dpu_crtc_frame_event_cb(DRMID(crtc), event);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	fevent = list_first_entry_or_null(&dpu_crtc->frame_event_list,
+			struct dpu_crtc_frame_event, list);
+	if (fevent)
+		list_del_init(&fevent->list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+
+	if (!fevent) {
+		DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event);
+		return;
+	}
+
+	fevent->event = event;
+	fevent->crtc = crtc;
+	fevent->ts = ktime_get();
+	kthread_queue_work(&priv->event_thread[crtc_id].worker, &fevent->work);
+}
+
+void dpu_crtc_complete_commit(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state)
+{
+	if (!crtc || !crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	trace_dpu_crtc_complete_commit(DRMID(crtc));
+}
+
+static void _dpu_crtc_setup_mixer_for_encoder(
+		struct drm_crtc *crtc,
+		struct drm_encoder *enc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
+	struct dpu_rm *rm = &dpu_kms->rm;
+	struct dpu_crtc_mixer *mixer;
+	struct dpu_hw_ctl *last_valid_ctl = NULL;
+	int i;
+	struct dpu_rm_hw_iter lm_iter, ctl_iter;
+
+	dpu_rm_init_hw_iter(&lm_iter, enc->base.id, DPU_HW_BLK_LM);
+	dpu_rm_init_hw_iter(&ctl_iter, enc->base.id, DPU_HW_BLK_CTL);
+
+	/* Set up all the mixers and ctls reserved by this encoder */
+	for (i = dpu_crtc->num_mixers; i < ARRAY_SIZE(dpu_crtc->mixers); i++) {
+		mixer = &dpu_crtc->mixers[i];
+
+		if (!dpu_rm_get_hw(rm, &lm_iter))
+			break;
+		mixer->hw_lm = (struct dpu_hw_mixer *)lm_iter.hw;
+
+		/* CTL may be <= LMs, if <, multiple LMs controlled by 1 CTL */
+		if (!dpu_rm_get_hw(rm, &ctl_iter)) {
+			DPU_DEBUG("no ctl assigned to lm %d, using previous\n",
+					mixer->hw_lm->idx - LM_0);
+			mixer->hw_ctl = last_valid_ctl;
+		} else {
+			mixer->hw_ctl = (struct dpu_hw_ctl *)ctl_iter.hw;
+			last_valid_ctl = mixer->hw_ctl;
+		}
+
+		/* Shouldn't happen, mixers are always >= ctls */
+		if (!mixer->hw_ctl) {
+			DPU_ERROR("no valid ctls found for lm %d\n",
+					mixer->hw_lm->idx - LM_0);
+			return;
+		}
+
+		mixer->encoder = enc;
+
+		dpu_crtc->num_mixers++;
+		DPU_DEBUG("setup mixer %d: lm %d\n",
+				i, mixer->hw_lm->idx - LM_0);
+		DPU_DEBUG("setup mixer %d: ctl %d\n",
+				i, mixer->hw_ctl->idx - CTL_0);
+	}
+}
+
+static void _dpu_crtc_setup_mixers(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_encoder *enc;
+
+	dpu_crtc->num_mixers = 0;
+	dpu_crtc->mixers_swapped = false;
+	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	/* Check for mixers on all encoders attached to this crtc */
+	list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) {
+		if (enc->crtc != crtc)
+			continue;
+
+		_dpu_crtc_setup_mixer_for_encoder(crtc, enc);
+	}
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+	struct drm_display_mode *adj_mode;
+	u32 crtc_split_width;
+	int i;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	adj_mode = &state->adjusted_mode;
+	crtc_split_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, adj_mode);
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		struct drm_rect *r = &cstate->lm_bounds[i];
+		r->x1 = crtc_split_width * i;
+		r->y1 = 0;
+		r->x2 = r->x1 + crtc_split_width;
+		r->y2 = dpu_crtc_get_mixer_height(dpu_crtc, cstate, adj_mode);
+
+		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
+	}
+
+	drm_mode_debug_printmodeline(adj_mode);
+}
+
+static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	unsigned long flags;
+	struct dpu_crtc_smmu_state_data *smmu_state;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("crtc%d -> enable %d, skip atomic_begin\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dev = crtc->dev;
+	smmu_state = &dpu_crtc->smmu_state;
+
+	if (!dpu_crtc->num_mixers) {
+		_dpu_crtc_setup_mixers(crtc);
+		_dpu_crtc_setup_lm_bounds(crtc, crtc->state);
+	}
+
+	if (dpu_crtc->event) {
+		WARN_ON(dpu_crtc->event);
+	} else {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		dpu_crtc->event = crtc->state->event;
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		/* encoder will trigger pending mask now */
+		dpu_encoder_trigger_kickoff_pending(encoder);
+	}
+
+	/*
+	 * If no mixers have been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	_dpu_crtc_blend_setup(crtc);
+
+	/*
+	 * PP_DONE irq is only used by command mode for now.
+	 * It is better to request pending before FLUSH and START trigger
+	 * to make sure no pp_done irq missed.
+	 * This is safe because no pp_done will happen before SW trigger
+	 * in command mode.
+	 */
+}
+
+static void dpu_crtc_atomic_flush(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_crtc_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_device *dev;
+	struct drm_plane *plane;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+	unsigned long flags;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("crtc%d -> enable %d, skip atomic_flush\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	dev = crtc->dev;
+	priv = dev->dev_private;
+
+	if (crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index[%d]\n", crtc->index);
+		return;
+	}
+
+	event_thread = &priv->event_thread[crtc->index];
+
+	if (dpu_crtc->event) {
+		DPU_DEBUG("already received dpu_crtc->event\n");
+	} else {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		dpu_crtc->event = crtc->state->event;
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	/*
+	 * For planes without commit update, drm framework will not add
+	 * those planes to current state since hardware update is not
+	 * required. However, if those planes were power collapsed since
+	 * last commit cycle, driver has to restore the hardware state
+	 * of those planes explicitly here prior to plane flush.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc)
+		dpu_plane_restore(plane);
+
+	/* update performance setting before crtc kickoff */
+	dpu_core_perf_crtc_update(crtc, 1, false);
+
+	/*
+	 * Final plane updates: Give each plane a chance to complete all
+	 *                      required writes/flushing before crtc's "flush
+	 *                      everything" call below.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		if (dpu_crtc->smmu_state.transition_error)
+			dpu_plane_set_error(plane, true);
+		dpu_plane_flush(plane);
+	}
+
+	/* Kickoff will be scheduled by outer layer */
+}
+
+/**
+ * dpu_crtc_destroy_state - state destroy hook
+ * @crtc: drm CRTC
+ * @state: CRTC state object to release
+ */
+static void dpu_crtc_destroy_state(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	_dpu_crtc_rp_destroy(&cstate->rp);
+
+	__drm_atomic_helper_crtc_destroy_state(state);
+
+	kfree(cstate);
+}
+
+static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	int ret, rc = 0;
+
+	if (!crtc) {
+		DPU_ERROR("invalid argument\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	if (!atomic_read(&dpu_crtc->frame_pending)) {
+		DPU_DEBUG("no frames pending\n");
+		return 0;
+	}
+
+	DPU_ATRACE_BEGIN("frame done completion wait");
+	ret = wait_for_completion_timeout(&dpu_crtc->frame_done_comp,
+			msecs_to_jiffies(DPU_FRAME_DONE_TIMEOUT));
+	if (!ret) {
+		DRM_ERROR("frame done wait timed out, ret:%d\n", ret);
+		rc = -ETIMEDOUT;
+	}
+	DPU_ATRACE_END("frame done completion wait");
+
+	return rc;
+}
+
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_crtc_state *cstate;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+	dev = crtc->dev;
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	priv = dpu_kms->dev->dev_private;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to start a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	DPU_ATRACE_BEGIN("crtc_commit");
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		struct dpu_encoder_kickoff_params params = { 0 };
+
+		if (encoder->crtc != crtc)
+			continue;
+
+		/*
+		 * Encoder will flush/start now, unless it has a tx pending.
+		 * If so, it may delay and flush at an irq event (e.g. ppdone)
+		 */
+		dpu_encoder_prepare_for_kickoff(encoder, &params);
+	}
+
+	/* wait for frame_event_done completion */
+	DPU_ATRACE_BEGIN("wait_for_frame_done_event");
+	ret = _dpu_crtc_wait_for_frame_done(crtc);
+	DPU_ATRACE_END("wait_for_frame_done_event");
+	if (ret) {
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+		goto end;
+	}
+
+	if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) {
+		/* acquire bandwidth and other resources */
+		DPU_DEBUG("crtc%d first commit\n", crtc->base.id);
+	} else
+		DPU_DEBUG("crtc%d commit\n", crtc->base.id);
+
+	dpu_crtc->play_count++;
+
+	dpu_vbif_clear_errors(dpu_kms);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		dpu_encoder_kickoff(encoder);
+	}
+
+end:
+	reinit_completion(&dpu_crtc->frame_done_comp);
+	DPU_ATRACE_END("crtc_commit");
+}
+
+/**
+ * _dpu_crtc_vblank_enable_no_lock - update power resource and vblank request
+ * @dpu_crtc: Pointer to dpu crtc structure
+ * @enable: Whether to enable/disable vblanks
+ *
+ * @Return: error code
+ */
+static int _dpu_crtc_vblank_enable_no_lock(
+		struct dpu_crtc *dpu_crtc, bool enable)
+{
+	struct drm_device *dev;
+	struct drm_crtc *crtc;
+	struct drm_encoder *enc;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	crtc = &dpu_crtc->base;
+	dev = crtc->dev;
+
+	if (enable) {
+		int ret;
+
+		/* drop lock since power crtc cb may try to re-acquire lock */
+		mutex_unlock(&dpu_crtc->crtc_lock);
+		ret = _dpu_crtc_power_enable(dpu_crtc, true);
+		mutex_lock(&dpu_crtc->crtc_lock);
+		if (ret)
+			return ret;
+
+		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
+			if (enc->crtc != crtc)
+				continue;
+
+			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
+						     DRMID(enc), enable,
+						     dpu_crtc);
+
+			dpu_encoder_register_vblank_callback(enc,
+					dpu_crtc_vblank_cb, (void *)crtc);
+		}
+	} else {
+		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
+			if (enc->crtc != crtc)
+				continue;
+
+			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
+						     DRMID(enc), enable,
+						     dpu_crtc);
+
+			dpu_encoder_register_vblank_callback(enc, NULL, NULL);
+		}
+
+		/* drop lock since power crtc cb may try to re-acquire lock */
+		mutex_unlock(&dpu_crtc->crtc_lock);
+		_dpu_crtc_power_enable(dpu_crtc, false);
+		mutex_lock(&dpu_crtc->crtc_lock);
+	}
+
+	return 0;
+}
+
+/**
+ * _dpu_crtc_set_suspend - notify crtc of suspend enable/disable
+ * @crtc: Pointer to drm crtc object
+ * @enable: true to enable suspend, false to indicate resume
+ */
+static void _dpu_crtc_set_suspend(struct drm_crtc *crtc, bool enable)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int ret = 0;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+
+	if (!priv->kms) {
+		DPU_ERROR("invalid crtc kms\n");
+		return;
+	}
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	DRM_DEBUG_KMS("crtc%d suspend = %d\n", crtc->base.id, enable);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	/*
+	 * If the vblank is enabled, release a power reference on suspend
+	 * and take it back during resume (if it is still enabled).
+	 */
+	trace_dpu_crtc_set_suspend(DRMID(&dpu_crtc->base), enable, dpu_crtc);
+	if (dpu_crtc->suspend == enable)
+		DPU_DEBUG("crtc%d suspend already set to %d, ignoring update\n",
+				crtc->base.id, enable);
+	else if (dpu_crtc->enabled && dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, !enable);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+
+	dpu_crtc->suspend = enable;
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+/**
+ * dpu_crtc_duplicate_state - state duplicate hook
+ * @crtc: Pointer to drm crtc structure
+ * @Returns: Pointer to new drm_crtc_state structure
+ */
+static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate, *old_cstate;
+
+	if (!crtc || !crtc->state) {
+		DPU_ERROR("invalid argument(s)\n");
+		return NULL;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	old_cstate = to_dpu_crtc_state(crtc->state);
+	cstate = kmemdup(old_cstate, sizeof(*old_cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return NULL;
+	}
+
+	/* duplicate base helper */
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &cstate->base);
+
+	_dpu_crtc_rp_duplicate(&old_cstate->rp, &cstate->rp);
+
+	return &cstate->base;
+}
+
+/**
+ * dpu_crtc_reset - reset hook for CRTCs
+ * Resets the atomic state for @crtc by freeing the state pointer (which might
+ * be NULL, e.g. at driver load time) and allocating a new empty state object.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void dpu_crtc_reset(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	/* revert suspend actions, if necessary */
+	if (dpu_kms_is_suspend_state(crtc->dev))
+		_dpu_crtc_set_suspend(crtc, false);
+
+	/* remove previous state, if present */
+	if (crtc->state) {
+		dpu_crtc_destroy_state(crtc, crtc->state);
+		crtc->state = 0;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = kzalloc(sizeof(*cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return;
+	}
+
+	_dpu_crtc_rp_reset(&cstate->rp, &dpu_crtc->rp_lock,
+			&dpu_crtc->rp_head);
+
+	cstate->base.crtc = crtc;
+	crtc->state = &cstate->base;
+}
+
+static void dpu_crtc_handle_power_event(u32 event_type, void *arg)
+{
+	struct drm_crtc *crtc = arg;
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct dpu_crtc_mixer *m;
+	u32 i, misr_status;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	trace_dpu_crtc_handle_power_event(DRMID(crtc), event_type);
+
+	switch (event_type) {
+	case DPU_POWER_EVENT_POST_ENABLE:
+		/* restore encoder; crtc will be programmed during commit */
+		drm_for_each_encoder(encoder, crtc->dev) {
+			if (encoder->crtc != crtc)
+				continue;
+
+			dpu_encoder_virt_restore(encoder);
+		}
+
+		for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+			m = &dpu_crtc->mixers[i];
+			if (!m->hw_lm || !m->hw_lm->ops.setup_misr ||
+					!dpu_crtc->misr_enable)
+				continue;
+
+			m->hw_lm->ops.setup_misr(m->hw_lm, true,
+					dpu_crtc->misr_frame_count);
+		}
+		break;
+	case DPU_POWER_EVENT_PRE_DISABLE:
+		for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+			m = &dpu_crtc->mixers[i];
+			if (!m->hw_lm || !m->hw_lm->ops.collect_misr ||
+					!dpu_crtc->misr_enable)
+				continue;
+
+			misr_status = m->hw_lm->ops.collect_misr(m->hw_lm);
+			dpu_crtc->misr_data[i] = misr_status ? misr_status :
+							dpu_crtc->misr_data[i];
+		}
+		break;
+	case DPU_POWER_EVENT_POST_DISABLE:
+		/**
+		 * Nothing to do. All the planes on the CRTC will be
+		 * programmed for every frame
+		 */
+		break;
+	default:
+		DPU_DEBUG("event:%d not handled\n", event_type);
+		break;
+	}
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void dpu_crtc_disable(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+	struct drm_display_mode *mode;
+	struct drm_encoder *encoder;
+	struct msm_drm_private *priv;
+	int ret;
+	unsigned long flags;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	mode = &cstate->base.adjusted_mode;
+	priv = crtc->dev->dev_private;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+
+	if (dpu_kms_is_suspend_state(crtc->dev))
+		_dpu_crtc_set_suspend(crtc, true);
+
+	/* Disable/save vblank irq handling */
+	drm_crtc_vblank_off(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	/* wait for frame_event_done completion */
+	if (_dpu_crtc_wait_for_frame_done(crtc))
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+
+	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
+	if (dpu_crtc->enabled && !dpu_crtc->suspend &&
+			dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->enabled = false;
+
+	if (atomic_read(&dpu_crtc->frame_pending)) {
+		trace_dpu_crtc_disable_frame_pending(DRMID(crtc),
+				     atomic_read(&dpu_crtc->frame_pending));
+		dpu_core_perf_crtc_release_bw(crtc);
+		atomic_set(&dpu_crtc->frame_pending, 0);
+	}
+
+	dpu_core_perf_crtc_update(crtc, 0, true);
+
+	drm_for_each_encoder(encoder, crtc->dev) {
+		if (encoder->crtc != crtc)
+			continue;
+		dpu_encoder_register_frame_event_callback(encoder, NULL, NULL);
+	}
+
+	if (dpu_crtc->power_event)
+		dpu_power_handle_unregister_event(dpu_crtc->phandle,
+				dpu_crtc->power_event);
+
+	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
+	dpu_crtc->num_mixers = 0;
+	dpu_crtc->mixers_swapped = false;
+
+	/* disable clk & bw control until clk & bw properties are set */
+	cstate->bw_control = false;
+	cstate->bw_split_vote = false;
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+	}
+}
+
+static void dpu_crtc_enable(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_crtc_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct msm_drm_private *priv;
+	int ret;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	priv = crtc->dev->dev_private;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	drm_for_each_encoder(encoder, crtc->dev) {
+		if (encoder->crtc != crtc)
+			continue;
+		dpu_encoder_register_frame_event_callback(encoder,
+				dpu_crtc_frame_event_cb, (void *)crtc);
+	}
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	trace_dpu_crtc_enable(DRMID(crtc), true, dpu_crtc);
+	if (!dpu_crtc->enabled && !dpu_crtc->suspend &&
+			dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, true);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->enabled = true;
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	/* Enable/restore vblank irq handling */
+	drm_crtc_vblank_on(crtc);
+
+	dpu_crtc->power_event = dpu_power_handle_register_event(
+		dpu_crtc->phandle,
+		DPU_POWER_EVENT_POST_ENABLE | DPU_POWER_EVENT_POST_DISABLE |
+		DPU_POWER_EVENT_PRE_DISABLE,
+		dpu_crtc_handle_power_event, crtc, dpu_crtc->name);
+
+}
+
+struct plane_state {
+	struct dpu_plane_state *dpu_pstate;
+	const struct drm_plane_state *drm_pstate;
+	int stage;
+	u32 pipe_id;
+};
+
+static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct plane_state *pstates;
+	struct dpu_crtc_state *cstate;
+
+	const struct drm_plane_state *pstate;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+
+	int cnt = 0, rc = 0, mixer_width, i, z_pos;
+
+	struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2];
+	int multirect_count = 0;
+	const struct drm_plane_state *pipe_staged[SSPP_MAX];
+	int left_zpos_cnt = 0, right_zpos_cnt = 0;
+	struct drm_rect crtc_rect = { 0 };
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	if (!state->enable || !state->active) {
+		DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n",
+				crtc->base.id, state->enable, state->active);
+		goto end;
+	}
+
+	mode = &state->adjusted_mode;
+	DPU_DEBUG("%s: check", dpu_crtc->name);
+
+	/* force a full mode set if active state changed */
+	if (state->active_changed)
+		state->mode_changed = true;
+
+	memset(pipe_staged, 0, sizeof(pipe_staged));
+
+	mixer_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode);
+
+	_dpu_crtc_setup_lm_bounds(crtc, state);
+
+	crtc_rect.x2 = mode->hdisplay;
+	crtc_rect.y2 = mode->vdisplay;
+
+	 /* get plane state for all drm planes associated with crtc state */
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
+		struct drm_rect dst, clip = crtc_rect;
+
+		if (IS_ERR_OR_NULL(pstate)) {
+			rc = PTR_ERR(pstate);
+			DPU_ERROR("%s: failed to get plane%d state, %d\n",
+					dpu_crtc->name, plane->base.id, rc);
+			goto end;
+		}
+		if (cnt >= DPU_STAGE_MAX * 4)
+			continue;
+
+		pstates[cnt].dpu_pstate = to_dpu_plane_state(pstate);
+		pstates[cnt].drm_pstate = pstate;
+		pstates[cnt].stage = pstate->normalized_zpos;
+		pstates[cnt].pipe_id = dpu_plane_pipe(plane);
+
+		if (pipe_staged[pstates[cnt].pipe_id]) {
+			multirect_plane[multirect_count].r0 =
+				pipe_staged[pstates[cnt].pipe_id];
+			multirect_plane[multirect_count].r1 = pstate;
+			multirect_count++;
+
+			pipe_staged[pstates[cnt].pipe_id] = NULL;
+		} else {
+			pipe_staged[pstates[cnt].pipe_id] = pstate;
+		}
+
+		cnt++;
+
+		dst = drm_plane_state_dest(pstate);
+		if (!drm_rect_intersect(&clip, &dst) ||
+		    !drm_rect_equals(&clip, &dst)) {
+			DPU_ERROR("invalid vertical/horizontal destination\n");
+			DPU_ERROR("display: " DRM_RECT_FMT " plane: "
+				  DRM_RECT_FMT "\n", DRM_RECT_ARG(&crtc_rect),
+				  DRM_RECT_ARG(&dst));
+			rc = -E2BIG;
+			goto end;
+		}
+	}
+
+	for (i = 1; i < SSPP_MAX; i++) {
+		if (pipe_staged[i]) {
+			dpu_plane_clear_multirect(pipe_staged[i]);
+
+			if (is_dpu_plane_virtual(pipe_staged[i]->plane)) {
+				DPU_ERROR(
+					"r1 only virt plane:%d not supported\n",
+					pipe_staged[i]->plane->base.id);
+				rc  = -EINVAL;
+				goto end;
+			}
+		}
+	}
+
+	z_pos = -1;
+	for (i = 0; i < cnt; i++) {
+		/* reset counts at every new blend stage */
+		if (pstates[i].stage != z_pos) {
+			left_zpos_cnt = 0;
+			right_zpos_cnt = 0;
+			z_pos = pstates[i].stage;
+		}
+
+		/* verify z_pos setting before using it */
+		if (z_pos >= DPU_STAGE_MAX - DPU_STAGE_0) {
+			DPU_ERROR("> %d plane stages assigned\n",
+					DPU_STAGE_MAX - DPU_STAGE_0);
+			rc = -EINVAL;
+			goto end;
+		} else if (pstates[i].drm_pstate->crtc_x < mixer_width) {
+			if (left_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on left\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			left_zpos_cnt++;
+
+		} else {
+			if (right_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on right\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			right_zpos_cnt++;
+		}
+
+		pstates[i].dpu_pstate->stage = z_pos + DPU_STAGE_0;
+		DPU_DEBUG("%s: zpos %d", dpu_crtc->name, z_pos);
+	}
+
+	for (i = 0; i < multirect_count; i++) {
+		if (dpu_plane_validate_multirect_v2(&multirect_plane[i])) {
+			DPU_ERROR(
+			"multirect validation failed for planes (%d - %d)\n",
+					multirect_plane[i].r0->plane->base.id,
+					multirect_plane[i].r1->plane->base.id);
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+	rc = dpu_core_perf_crtc_check(crtc, state);
+	if (rc) {
+		DPU_ERROR("crtc%d failed performance check %d\n",
+				crtc->base.id, rc);
+		goto end;
+	}
+
+	/* validate source split:
+	 * use pstates sorted by stage to check planes on same stage
+	 * we assume that all pipes are in source split so its valid to compare
+	 * without taking into account left/right mixer placement
+	 */
+	for (i = 1; i < cnt; i++) {
+		struct plane_state *prv_pstate, *cur_pstate;
+		struct drm_rect left_rect, right_rect;
+		int32_t left_pid, right_pid;
+		int32_t stage;
+
+		prv_pstate = &pstates[i - 1];
+		cur_pstate = &pstates[i];
+		if (prv_pstate->stage != cur_pstate->stage)
+			continue;
+
+		stage = cur_pstate->stage;
+
+		left_pid = prv_pstate->dpu_pstate->base.plane->base.id;
+		left_rect = drm_plane_state_dest(prv_pstate->drm_pstate);
+
+		right_pid = cur_pstate->dpu_pstate->base.plane->base.id;
+		right_rect = drm_plane_state_dest(cur_pstate->drm_pstate);
+
+		if (right_rect.x1 < left_rect.x1) {
+			swap(left_pid, right_pid);
+			swap(left_rect, right_rect);
+		}
+
+		/**
+		 * - planes are enumerated in pipe-priority order such that
+		 *   planes with lower drm_id must be left-most in a shared
+		 *   blend-stage when using source split.
+		 * - planes in source split must be contiguous in width
+		 * - planes in source split must have same dest yoff and height
+		 */
+		if (right_pid < left_pid) {
+			DPU_ERROR(
+				"invalid src split cfg. priority mismatch. stage: %d left: %d right: %d\n",
+				stage, left_pid, right_pid);
+			rc = -EINVAL;
+			goto end;
+		} else if (right_rect.x1 != drm_rect_width(&left_rect)) {
+			DPU_ERROR("non-contiguous coordinates for src split. "
+				  "stage: %d left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		} else if (left_rect.y1 != right_rect.y1 ||
+			   drm_rect_height(&left_rect) != drm_rect_height(&right_rect)) {
+			DPU_ERROR("source split at stage: %d. invalid "
+				  "yoff/height: left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+end:
+	_dpu_crtc_rp_free_unused(&cstate->rp);
+	kfree(pstates);
+	return rc;
+}
+
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en)
+{
+	struct dpu_crtc *dpu_crtc;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	trace_dpu_crtc_vblank(DRMID(&dpu_crtc->base), en, dpu_crtc);
+	if (dpu_crtc->enabled && !dpu_crtc->suspend) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, en);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->vblank_requested = en;
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_crtc_mixer *m;
+
+	struct drm_crtc *crtc;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+
+	int i, out_width;
+
+	if (!s || !s->private)
+		return -EINVAL;
+
+	dpu_crtc = s->private;
+	crtc = &dpu_crtc->base;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	mode = &crtc->state->adjusted_mode;
+	out_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode);
+
+	seq_printf(s, "crtc:%d width:%d height:%d\n", crtc->base.id,
+				mode->hdisplay, mode->vdisplay);
+
+	seq_puts(s, "\n");
+
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm)
+			seq_printf(s, "\tmixer[%d] has no lm\n", i);
+		else if (!m->hw_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->hw_ctl->idx - CTL_0,
+				out_width, mode->vdisplay);
+	}
+
+	seq_puts(s, "\n");
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		pstate = to_dpu_plane_state(plane->state);
+		state = plane->state;
+
+		if (!pstate || !state)
+			continue;
+
+		seq_printf(s, "\tplane:%u stage:%d\n", plane->base.id,
+			pstate->stage);
+
+		if (plane->state->fb) {
+			fb = plane->state->fb;
+
+			seq_printf(s, "\tfb:%d image format:%4.4s wxh:%ux%u ",
+				fb->base.id, (char *) &fb->format->format,
+				fb->width, fb->height);
+			for (i = 0; i < ARRAY_SIZE(fb->format->cpp); ++i)
+				seq_printf(s, "cpp[%d]:%u ",
+						i, fb->format->cpp[i]);
+			seq_puts(s, "\n\t");
+
+			seq_printf(s, "modifier:%8llu ", fb->modifier);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->pitches); i++)
+				seq_printf(s, "pitches[%d]:%8u ", i,
+							fb->pitches[i]);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->offsets); i++)
+				seq_printf(s, "offsets[%d]:%8u ", i,
+							fb->offsets[i]);
+			seq_puts(s, "\n");
+		}
+
+		seq_printf(s, "\tsrc_x:%4d src_y:%4d src_w:%4d src_h:%4d\n",
+			state->src_x, state->src_y, state->src_w, state->src_h);
+
+		seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n",
+			state->crtc_x, state->crtc_y, state->crtc_w,
+			state->crtc_h);
+		seq_printf(s, "\tmultirect: mode: %d index: %d\n",
+			pstate->multirect_mode, pstate->multirect_index);
+
+		seq_puts(s, "\n");
+	}
+	if (dpu_crtc->vblank_cb_count) {
+		ktime_t diff = ktime_sub(ktime_get(), dpu_crtc->vblank_cb_time);
+		s64 diff_ms = ktime_to_ms(diff);
+		s64 fps = diff_ms ? div_s64(
+				dpu_crtc->vblank_cb_count * 1000, diff_ms) : 0;
+
+		seq_printf(s,
+			"vblank fps:%lld count:%u total:%llums total_framecount:%llu\n",
+				fps, dpu_crtc->vblank_cb_count,
+				ktime_to_ms(diff), dpu_crtc->play_count);
+
+		/* reset time & count for next measurement */
+		dpu_crtc->vblank_cb_count = 0;
+		dpu_crtc->vblank_cb_time = ktime_set(0, 0);
+	}
+
+	seq_printf(s, "vblank_enable:%d\n", dpu_crtc->vblank_requested);
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	return 0;
+}
+
+static int _dpu_debugfs_status_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, _dpu_debugfs_status_show, inode->i_private);
+}
+
+static ssize_t _dpu_crtc_misr_setup(struct file *file,
+		const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_mixer *m;
+	int i = 0, rc;
+	char buf[MISR_BUFF_SIZE + 1];
+	u32 frame_count, enable;
+	size_t buff_copy;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_crtc = file->private_data;
+	buff_copy = min_t(size_t, count, MISR_BUFF_SIZE);
+	if (copy_from_user(buf, user_buf, buff_copy)) {
+		DPU_ERROR("buffer copy failed\n");
+		return -EINVAL;
+	}
+
+	buf[buff_copy] = 0; /* end of string */
+
+	if (sscanf(buf, "%u %u", &enable, &frame_count) != 2)
+		return -EINVAL;
+
+	rc = _dpu_crtc_power_enable(dpu_crtc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	dpu_crtc->misr_enable = enable;
+	dpu_crtc->misr_frame_count = frame_count;
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		dpu_crtc->misr_data[i] = 0;
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm || !m->hw_lm->ops.setup_misr)
+			continue;
+
+		m->hw_lm->ops.setup_misr(m->hw_lm, enable, frame_count);
+	}
+	mutex_unlock(&dpu_crtc->crtc_lock);
+	_dpu_crtc_power_enable(dpu_crtc, false);
+
+	return count;
+}
+
+static ssize_t _dpu_crtc_misr_read(struct file *file,
+		char __user *user_buff, size_t count, loff_t *ppos)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_mixer *m;
+	int i = 0, rc;
+	u32 misr_status;
+	ssize_t len = 0;
+	char buf[MISR_BUFF_SIZE + 1] = {'\0'};
+
+	if (*ppos)
+		return 0;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_crtc = file->private_data;
+	rc = _dpu_crtc_power_enable(dpu_crtc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	if (!dpu_crtc->misr_enable) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"disabled\n");
+		goto buff_check;
+	}
+
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm || !m->hw_lm->ops.collect_misr)
+			continue;
+
+		misr_status = m->hw_lm->ops.collect_misr(m->hw_lm);
+		dpu_crtc->misr_data[i] = misr_status ? misr_status :
+							dpu_crtc->misr_data[i];
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "lm idx:%d\n",
+					m->hw_lm->idx - LM_0);
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n",
+							dpu_crtc->misr_data[i]);
+	}
+
+buff_check:
+	if (count <= len) {
+		len = 0;
+		goto end;
+	}
+
+	if (copy_to_user(user_buff, buf, len)) {
+		len = -EFAULT;
+		goto end;
+	}
+
+	*ppos += len;   /* increase offset */
+
+end:
+	mutex_unlock(&dpu_crtc->crtc_lock);
+	_dpu_crtc_power_enable(dpu_crtc, false);
+	return len;
+}
+
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)                          \
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *) s->private;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc_res *res;
+	struct dpu_crtc_respool *rp;
+	int i;
+
+	seq_printf(s, "client type: %d\n", dpu_crtc_get_client_type(crtc));
+	seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc));
+	seq_printf(s, "core_clk_rate: %llu\n",
+			dpu_crtc->cur_perf.core_clk_rate);
+	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
+			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		seq_printf(s, "bw_ctl[%s]: %llu\n",
+				dpu_power_handle_get_dbus_name(i),
+				dpu_crtc->cur_perf.bw_ctl[i]);
+		seq_printf(s, "max_per_pipe_ib[%s]: %llu\n",
+				dpu_power_handle_get_dbus_name(i),
+				dpu_crtc->cur_perf.max_per_pipe_ib[i]);
+	}
+
+	mutex_lock(&dpu_crtc->rp_lock);
+	list_for_each_entry(rp, &dpu_crtc->rp_head, rp_list) {
+		seq_printf(s, "rp.%d: ", rp->sequence_id);
+		list_for_each_entry(res, &rp->res_list, list)
+			seq_printf(s, "0x%x/0x%llx/%pK/%d ",
+					res->type, res->tag, res->val,
+					atomic_read(&res->refcount));
+		seq_puts(s, "\n");
+	}
+	mutex_unlock(&dpu_crtc->rp_lock);
+
+	return 0;
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_crtc_debugfs_state);
+
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *dpu_kms;
+
+	static const struct file_operations debugfs_status_fops = {
+		.open =		_dpu_debugfs_status_open,
+		.read =		seq_read,
+		.llseek =	seq_lseek,
+		.release =	single_release,
+	};
+	static const struct file_operations debugfs_misr_fops = {
+		.open =		simple_open,
+		.read =		_dpu_crtc_misr_read,
+		.write =	_dpu_crtc_misr_setup,
+	};
+
+	if (!crtc)
+		return -EINVAL;
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+	if (!dpu_kms)
+		return -EINVAL;
+
+	dpu_crtc->debugfs_root = debugfs_create_dir(dpu_crtc->name,
+			crtc->dev->primary->debugfs_root);
+	if (!dpu_crtc->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_file("status", 0400,
+			dpu_crtc->debugfs_root,
+			dpu_crtc, &debugfs_status_fops);
+	debugfs_create_file("state", 0600,
+			dpu_crtc->debugfs_root,
+			&dpu_crtc->base,
+			&dpu_crtc_debugfs_state_fops);
+	debugfs_create_file("misr_data", 0600, dpu_crtc->debugfs_root,
+					dpu_crtc, &debugfs_misr_fops);
+
+	return 0;
+}
+
+static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+
+	if (!crtc)
+		return;
+	dpu_crtc = to_dpu_crtc(crtc);
+	debugfs_remove_recursive(dpu_crtc->debugfs_root);
+}
+#else
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	return 0;
+}
+
+static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static int dpu_crtc_late_register(struct drm_crtc *crtc)
+{
+	return _dpu_crtc_init_debugfs(crtc);
+}
+
+static void dpu_crtc_early_unregister(struct drm_crtc *crtc)
+{
+	_dpu_crtc_destroy_debugfs(crtc);
+}
+
+static const struct drm_crtc_funcs dpu_crtc_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = dpu_crtc_destroy,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = dpu_crtc_reset,
+	.atomic_duplicate_state = dpu_crtc_duplicate_state,
+	.atomic_destroy_state = dpu_crtc_destroy_state,
+	.late_register = dpu_crtc_late_register,
+	.early_unregister = dpu_crtc_early_unregister,
+};
+
+static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
+	.disable = dpu_crtc_disable,
+	.atomic_enable = dpu_crtc_enable,
+	.atomic_check = dpu_crtc_atomic_check,
+	.atomic_begin = dpu_crtc_atomic_begin,
+	.atomic_flush = dpu_crtc_atomic_flush,
+};
+
+/* initialize crtc */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane)
+{
+	struct drm_crtc *crtc = NULL;
+	struct dpu_crtc *dpu_crtc = NULL;
+	struct msm_drm_private *priv = NULL;
+	struct dpu_kms *kms = NULL;
+	int i;
+
+	priv = dev->dev_private;
+	kms = to_dpu_kms(priv->kms);
+
+	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
+	if (!dpu_crtc)
+		return ERR_PTR(-ENOMEM);
+
+	crtc = &dpu_crtc->base;
+	crtc->dev = dev;
+
+	mutex_init(&dpu_crtc->crtc_lock);
+	spin_lock_init(&dpu_crtc->spin_lock);
+	atomic_set(&dpu_crtc->frame_pending, 0);
+
+	mutex_init(&dpu_crtc->rp_lock);
+	INIT_LIST_HEAD(&dpu_crtc->rp_head);
+
+	init_completion(&dpu_crtc->frame_done_comp);
+
+	INIT_LIST_HEAD(&dpu_crtc->frame_event_list);
+
+	for (i = 0; i < ARRAY_SIZE(dpu_crtc->frame_events); i++) {
+		INIT_LIST_HEAD(&dpu_crtc->frame_events[i].list);
+		list_add(&dpu_crtc->frame_events[i].list,
+				&dpu_crtc->frame_event_list);
+		kthread_init_work(&dpu_crtc->frame_events[i].work,
+				dpu_crtc_frame_event_work);
+	}
+
+	drm_crtc_init_with_planes(dev, crtc, plane, NULL, &dpu_crtc_funcs,
+				NULL);
+
+	drm_crtc_helper_add(crtc, &dpu_crtc_helper_funcs);
+	plane->crtc = crtc;
+
+	/* save user friendly CRTC name for later */
+	snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id);
+
+	/* initialize event handling */
+	spin_lock_init(&dpu_crtc->event_lock);
+
+	dpu_crtc->phandle = &kms->phandle;
+
+	DPU_DEBUG("%s: successfully initialized crtc\n", dpu_crtc->name);
+	return crtc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
new file mode 100644
index 000000000000..e87109e608e9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
@@ -0,0 +1,423 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DPU_CRTC_H_
+#define _DPU_CRTC_H_
+
+#include <linux/kthread.h>
+#include <drm/drm_crtc.h>
+#include "dpu_kms.h"
+#include "dpu_core_perf.h"
+#include "dpu_hw_blk.h"
+
+#define DPU_CRTC_NAME_SIZE	12
+
+/* define the maximum number of in-flight frame events */
+#define DPU_CRTC_FRAME_EVENT_SIZE	4
+
+/**
+ * enum dpu_crtc_client_type: crtc client type
+ * @RT_CLIENT:	RealTime client like video/cmd mode display
+ *              voting through apps rsc
+ * @NRT_CLIENT:	Non-RealTime client like WB display
+ *              voting through apps rsc
+ */
+enum dpu_crtc_client_type {
+	RT_CLIENT,
+	NRT_CLIENT,
+};
+
+/**
+ * enum dpu_crtc_smmu_state:	smmu state
+ * @ATTACHED:	 all the context banks are attached.
+ * @DETACHED:	 all the context banks are detached.
+ * @ATTACH_ALL_REQ:	 transient state of attaching context banks.
+ * @DETACH_ALL_REQ:	 transient state of detaching context banks.
+ */
+enum dpu_crtc_smmu_state {
+	ATTACHED = 0,
+	DETACHED,
+	ATTACH_ALL_REQ,
+	DETACH_ALL_REQ,
+};
+
+/**
+ * enum dpu_crtc_smmu_state_transition_type: state transition type
+ * @NONE: no pending state transitions
+ * @PRE_COMMIT: state transitions should be done before processing the commit
+ * @POST_COMMIT: state transitions to be done after processing the commit.
+ */
+enum dpu_crtc_smmu_state_transition_type {
+	NONE,
+	PRE_COMMIT,
+	POST_COMMIT
+};
+
+/**
+ * struct dpu_crtc_smmu_state_data: stores the smmu state and transition type
+ * @state: current state of smmu context banks
+ * @transition_type: transition request type
+ * @transition_error: whether there is error while transitioning the state
+ */
+struct dpu_crtc_smmu_state_data {
+	uint32_t state;
+	uint32_t transition_type;
+	uint32_t transition_error;
+};
+
+/**
+ * struct dpu_crtc_mixer: stores the map for each virtual pipeline in the CRTC
+ * @hw_lm:	LM HW Driver context
+ * @hw_ctl:	CTL Path HW driver context
+ * @encoder:	Encoder attached to this lm & ctl
+ * @mixer_op_mode:	mixer blending operation mode
+ * @flush_mask:	mixer flush mask for ctl, mixer and pipe
+ */
+struct dpu_crtc_mixer {
+	struct dpu_hw_mixer *hw_lm;
+	struct dpu_hw_ctl *hw_ctl;
+	struct drm_encoder *encoder;
+	u32 mixer_op_mode;
+	u32 flush_mask;
+};
+
+/**
+ * struct dpu_crtc_frame_event: stores crtc frame event for crtc processing
+ * @work:	base work structure
+ * @crtc:	Pointer to crtc handling this event
+ * @list:	event list
+ * @ts:		timestamp at queue entry
+ * @event:	event identifier
+ */
+struct dpu_crtc_frame_event {
+	struct kthread_work work;
+	struct drm_crtc *crtc;
+	struct list_head list;
+	ktime_t ts;
+	u32 event;
+};
+
+/*
+ * Maximum number of free event structures to cache
+ */
+#define DPU_CRTC_MAX_EVENT_COUNT	16
+
+/**
+ * struct dpu_crtc - virtualized CRTC data structure
+ * @base          : Base drm crtc structure
+ * @name          : ASCII description of this crtc
+ * @num_ctls      : Number of ctl paths in use
+ * @num_mixers    : Number of mixers in use
+ * @mixers_swapped: Whether the mixers have been swapped for left/right update
+ *                  especially in the case of DSC Merge.
+ * @mixers        : List of active mixers
+ * @event         : Pointer to last received drm vblank event. If there is a
+ *                  pending vblank event, this will be non-null.
+ * @vsync_count   : Running count of received vsync events
+ * @drm_requested_vblank : Whether vblanks have been enabled in the encoder
+ * @property_info : Opaque structure for generic property support
+ * @property_defaults : Array of default values for generic property support
+ * @stage_cfg     : H/w mixer stage configuration
+ * @debugfs_root  : Parent of debugfs node
+ * @vblank_cb_count : count of vblank callback since last reset
+ * @play_count    : frame count between crtc enable and disable
+ * @vblank_cb_time  : ktime at vblank count reset
+ * @vblank_requested : whether the user has requested vblank events
+ * @suspend         : whether or not a suspend operation is in progress
+ * @enabled       : whether the DPU CRTC is currently enabled. updated in the
+ *                  commit-thread, not state-swap time which is earlier, so
+ *                  safe to make decisions on during VBLANK on/off work
+ * @feature_list  : list of color processing features supported on a crtc
+ * @active_list   : list of color processing features are active
+ * @dirty_list    : list of color processing features are dirty
+ * @ad_dirty: list containing ad properties that are dirty
+ * @ad_active: list containing ad properties that are active
+ * @crtc_lock     : crtc lock around create, destroy and access.
+ * @frame_pending : Whether or not an update is pending
+ * @frame_events  : static allocation of in-flight frame events
+ * @frame_event_list : available frame event list
+ * @spin_lock     : spin lock for frame event, transaction status, etc...
+ * @frame_done_comp    : for frame_event_done synchronization
+ * @event_thread  : Pointer to event handler thread
+ * @event_worker  : Event worker queue
+ * @event_lock    : Spinlock around event handling code
+ * @misr_enable   : boolean entry indicates misr enable/disable status.
+ * @misr_frame_count  : misr frame count provided by client
+ * @misr_data     : store misr data before turning off the clocks.
+ * @phandle: Pointer to power handler
+ * @power_event   : registered power event handle
+ * @cur_perf      : current performance committed to clock/bandwidth driver
+ * @rp_lock       : serialization lock for resource pool
+ * @rp_head       : list of active resource pool
+ * @scl3_cfg_lut  : qseed3 lut config
+ */
+struct dpu_crtc {
+	struct drm_crtc base;
+	char name[DPU_CRTC_NAME_SIZE];
+
+	/* HW Resources reserved for the crtc */
+	u32 num_ctls;
+	u32 num_mixers;
+	bool mixers_swapped;
+	struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS];
+	struct dpu_hw_scaler3_lut_cfg *scl3_lut_cfg;
+
+	struct drm_pending_vblank_event *event;
+	u32 vsync_count;
+
+	struct dpu_hw_stage_cfg stage_cfg;
+	struct dentry *debugfs_root;
+
+	u32 vblank_cb_count;
+	u64 play_count;
+	ktime_t vblank_cb_time;
+	bool vblank_requested;
+	bool suspend;
+	bool enabled;
+
+	struct list_head feature_list;
+	struct list_head active_list;
+	struct list_head dirty_list;
+	struct list_head ad_dirty;
+	struct list_head ad_active;
+
+	struct mutex crtc_lock;
+
+	atomic_t frame_pending;
+	struct dpu_crtc_frame_event frame_events[DPU_CRTC_FRAME_EVENT_SIZE];
+	struct list_head frame_event_list;
+	spinlock_t spin_lock;
+	struct completion frame_done_comp;
+
+	/* for handling internal event thread */
+	spinlock_t event_lock;
+	bool misr_enable;
+	u32 misr_frame_count;
+	u32 misr_data[CRTC_DUAL_MIXERS];
+
+	struct dpu_power_handle *phandle;
+	struct dpu_power_event *power_event;
+
+	struct dpu_core_perf_params cur_perf;
+
+	struct mutex rp_lock;
+	struct list_head rp_head;
+
+	struct dpu_crtc_smmu_state_data smmu_state;
+};
+
+#define to_dpu_crtc(x) container_of(x, struct dpu_crtc, base)
+
+/**
+ * struct dpu_crtc_res_ops - common operations for crtc resources
+ * @get: get given resource
+ * @put: put given resource
+ */
+struct dpu_crtc_res_ops {
+	void *(*get)(void *val, u32 type, u64 tag);
+	void (*put)(void *val);
+};
+
+#define DPU_CRTC_RES_FLAG_FREE		BIT(0)
+
+/**
+ * struct dpu_crtc_res - definition of crtc resources
+ * @list: list of crtc resource
+ * @type: crtc resource type
+ * @tag: unique identifier per type
+ * @refcount: reference/usage count
+ * @ops: callback operations
+ * @val: resource handle associated with type/tag
+ * @flags: customization flags
+ */
+struct dpu_crtc_res {
+	struct list_head list;
+	u32 type;
+	u64 tag;
+	atomic_t refcount;
+	struct dpu_crtc_res_ops ops;
+	void *val;
+	u32 flags;
+};
+
+/**
+ * dpu_crtc_respool - crtc resource pool
+ * @rp_lock: pointer to serialization lock
+ * @rp_head: pointer to head of active resource pools of this crtc
+ * @rp_list: list of crtc resource pool
+ * @sequence_id: sequence identifier, incremented per state duplication
+ * @res_list: list of resource managed by this resource pool
+ * @ops: resource operations for parent resource pool
+ */
+struct dpu_crtc_respool {
+	struct mutex *rp_lock;
+	struct list_head *rp_head;
+	struct list_head rp_list;
+	u32 sequence_id;
+	struct list_head res_list;
+	struct dpu_crtc_res_ops ops;
+};
+
+/**
+ * struct dpu_crtc_state - dpu container for atomic crtc state
+ * @base: Base drm crtc state structure
+ * @is_ppsplit    : Whether current topology requires PPSplit special handling
+ * @bw_control    : true if bw/clk controlled by core bw/clk properties
+ * @bw_split_vote : true if bw controlled by llcc/dram bw properties
+ * @lm_bounds     : LM boundaries based on current mode full resolution, no ROI.
+ *                  Origin top left of CRTC.
+ * @property_state: Local storage for msm_prop properties
+ * @property_values: Current crtc property values
+ * @input_fence_timeout_ns : Cached input fence timeout, in ns
+ * @new_perf: new performance state being requested
+ */
+struct dpu_crtc_state {
+	struct drm_crtc_state base;
+
+	bool bw_control;
+	bool bw_split_vote;
+
+	bool is_ppsplit;
+	struct drm_rect lm_bounds[CRTC_DUAL_MIXERS];
+
+	uint64_t input_fence_timeout_ns;
+
+	struct dpu_core_perf_params new_perf;
+	struct dpu_crtc_respool rp;
+};
+
+#define to_dpu_crtc_state(x) \
+	container_of(x, struct dpu_crtc_state, base)
+
+/**
+ * dpu_crtc_get_mixer_width - get the mixer width
+ * Mixer width will be same as panel width(/2 for split)
+ */
+static inline int dpu_crtc_get_mixer_width(struct dpu_crtc *dpu_crtc,
+	struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
+{
+	u32 mixer_width;
+
+	if (!dpu_crtc || !cstate || !mode)
+		return 0;
+
+	mixer_width = (dpu_crtc->num_mixers == CRTC_DUAL_MIXERS ?
+			mode->hdisplay / CRTC_DUAL_MIXERS : mode->hdisplay);
+
+	return mixer_width;
+}
+
+/**
+ * dpu_crtc_get_mixer_height - get the mixer height
+ * Mixer height will be same as panel height
+ */
+static inline int dpu_crtc_get_mixer_height(struct dpu_crtc *dpu_crtc,
+		struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
+{
+	if (!dpu_crtc || !cstate || !mode)
+		return 0;
+
+	return mode->vdisplay;
+}
+
+/**
+ * dpu_crtc_frame_pending - retun the number of pending frames
+ * @crtc: Pointer to drm crtc object
+ */
+static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+
+	if (!crtc)
+		return -EINVAL;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	return atomic_read(&dpu_crtc->frame_pending);
+}
+
+/**
+ * dpu_crtc_vblank - enable or disable vblanks for this crtc
+ * @crtc: Pointer to drm crtc object
+ * @en: true to enable vblanks, false to disable
+ */
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en);
+
+/**
+ * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_complete_commit - callback signalling completion of current commit
+ * @crtc: Pointer to drm crtc object
+ * @old_state: Pointer to drm crtc old state object
+ */
+void dpu_crtc_complete_commit(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state);
+
+/**
+ * dpu_crtc_init - create a new crtc object
+ * @dev: dpu device
+ * @plane: base plane
+ * @Return: new crtc object or error
+ */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane);
+
+/**
+ * dpu_crtc_register_custom_event - api for enabling/disabling crtc event
+ * @kms: Pointer to dpu_kms
+ * @crtc_drm: Pointer to crtc object
+ * @event: Event that client is interested
+ * @en: Flag to enable/disable the event
+ */
+int dpu_crtc_register_custom_event(struct dpu_kms *kms,
+		struct drm_crtc *crtc_drm, u32 event, bool en);
+
+/**
+ * dpu_crtc_get_intf_mode - get interface mode of the given crtc
+ * @crtc: Pointert to crtc
+ */
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_get_client_type - check the crtc type- rt, nrt etc.
+ * @crtc: Pointer to crtc
+ */
+static inline enum dpu_crtc_client_type dpu_crtc_get_client_type(
+						struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *cstate =
+			crtc ? to_dpu_crtc_state(crtc->state) : NULL;
+
+	if (!cstate)
+		return NRT_CLIENT;
+
+	return RT_CLIENT;
+}
+
+/**
+ * dpu_crtc_is_enabled - check if dpu crtc is enabled or not
+ * @crtc: Pointer to crtc
+ */
+static inline bool dpu_crtc_is_enabled(struct drm_crtc *crtc)
+{
+	return crtc ? crtc->enabled : false;
+}
+
+#endif /* _DPU_CRTC_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
new file mode 100644
index 000000000000..ae2aee7ed9e1
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
@@ -0,0 +1,2393 @@
+/* Copyright (c) 2009-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/dma-buf.h>
+#include <linux/slab.h>
+#include <linux/list_sort.h>
+#include <linux/pm_runtime.h>
+
+#include "dpu_dbg.h"
+#include "disp/dpu1/dpu_hw_catalog.h"
+
+
+#define DEFAULT_DBGBUS_DPU	DPU_DBG_DUMP_IN_MEM
+#define DEFAULT_DBGBUS_VBIFRT	DPU_DBG_DUMP_IN_MEM
+#define REG_BASE_NAME_LEN	80
+
+#define DBGBUS_FLAGS_DSPP	BIT(0)
+#define DBGBUS_DSPP_STATUS	0x34C
+
+#define DBGBUS_NAME_DPU		"dpu"
+#define DBGBUS_NAME_VBIF_RT	"vbif_rt"
+
+/* offsets from dpu top address for the debug buses */
+#define DBGBUS_SSPP0	0x188
+#define DBGBUS_AXI_INTF	0x194
+#define DBGBUS_SSPP1	0x298
+#define DBGBUS_DSPP	0x348
+#define DBGBUS_PERIPH	0x418
+
+#define TEST_MASK(id, tp)	((id << 4) | (tp << 1) | BIT(0))
+
+/* following offsets are with respect to MDP VBIF base for DBG BUS access */
+#define MMSS_VBIF_CLKON			0x4
+#define MMSS_VBIF_TEST_BUS_OUT_CTRL	0x210
+#define MMSS_VBIF_TEST_BUS_OUT		0x230
+
+/* Vbif error info */
+#define MMSS_VBIF_PND_ERR		0x190
+#define MMSS_VBIF_SRC_ERR		0x194
+#define MMSS_VBIF_XIN_HALT_CTRL1	0x204
+#define MMSS_VBIF_ERR_INFO		0X1a0
+#define MMSS_VBIF_ERR_INFO_1		0x1a4
+#define MMSS_VBIF_CLIENT_NUM		14
+
+/**
+ * struct dpu_dbg_reg_base - register region base.
+ *	may sub-ranges: sub-ranges are used for dumping
+ *	or may not have sub-ranges: dumping is base -> max_offset
+ * @reg_base_head: head of this node
+ * @name: register base name
+ * @base: base pointer
+ * @off: cached offset of region for manual register dumping
+ * @cnt: cached range of region for manual register dumping
+ * @max_offset: length of region
+ * @buf: buffer used for manual register dumping
+ * @buf_len:  buffer length used for manual register dumping
+ * @cb: callback for external dump function, null if not defined
+ * @cb_ptr: private pointer to callback function
+ */
+struct dpu_dbg_reg_base {
+	struct list_head reg_base_head;
+	char name[REG_BASE_NAME_LEN];
+	void __iomem *base;
+	size_t off;
+	size_t cnt;
+	size_t max_offset;
+	char *buf;
+	size_t buf_len;
+	void (*cb)(void *ptr);
+	void *cb_ptr;
+};
+
+struct dpu_debug_bus_entry {
+	u32 wr_addr;
+	u32 block_id;
+	u32 test_id;
+	void (*analyzer)(void __iomem *mem_base,
+				struct dpu_debug_bus_entry *entry, u32 val);
+};
+
+struct vbif_debug_bus_entry {
+	u32 disable_bus_addr;
+	u32 block_bus_addr;
+	u32 bit_offset;
+	u32 block_cnt;
+	u32 test_pnt_start;
+	u32 test_pnt_cnt;
+};
+
+struct dpu_dbg_debug_bus_common {
+	char *name;
+	u32 enable_mask;
+	bool include_in_deferred_work;
+	u32 flags;
+	u32 entries_size;
+	u32 *dumped_content;
+};
+
+struct dpu_dbg_dpu_debug_bus {
+	struct dpu_dbg_debug_bus_common cmn;
+	struct dpu_debug_bus_entry *entries;
+	u32 top_blk_off;
+};
+
+struct dpu_dbg_vbif_debug_bus {
+	struct dpu_dbg_debug_bus_common cmn;
+	struct vbif_debug_bus_entry *entries;
+};
+
+/**
+ * struct dpu_dbg_base - global dpu debug base structure
+ * @reg_base_list: list of register dumping regions
+ * @dev: device pointer
+ * @dump_work: work struct for deferring register dump work to separate thread
+ * @dbgbus_dpu: debug bus structure for the dpu
+ * @dbgbus_vbif_rt: debug bus structure for the realtime vbif
+ */
+static struct dpu_dbg_base {
+	struct list_head reg_base_list;
+	struct device *dev;
+
+	struct work_struct dump_work;
+
+	struct dpu_dbg_dpu_debug_bus dbgbus_dpu;
+	struct dpu_dbg_vbif_debug_bus dbgbus_vbif_rt;
+} dpu_dbg_base;
+
+static void _dpu_debug_bus_xbar_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	dev_err(dpu_dbg_base.dev, "xbar 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_lm_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & 0xFFF000))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "lm 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_ppb0_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & BIT(15)))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "ppb0 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_ppb1_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & BIT(15)))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "ppb1 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static struct dpu_debug_bus_entry dbg_bus_dpu_8998[] = {
+
+	/* Unpack 0 sspp 0*/
+	{ DBGBUS_SSPP0, 50, 2 },
+	{ DBGBUS_SSPP0, 60, 2 },
+	{ DBGBUS_SSPP0, 70, 2 },
+	{ DBGBUS_SSPP0, 85, 2 },
+
+	/* Upack 0 sspp 1*/
+	{ DBGBUS_SSPP1, 50, 2 },
+	{ DBGBUS_SSPP1, 60, 2 },
+	{ DBGBUS_SSPP1, 70, 2 },
+	{ DBGBUS_SSPP1, 85, 2 },
+
+	/* scheduler */
+	{ DBGBUS_DSPP, 130, 0 },
+	{ DBGBUS_DSPP, 130, 1 },
+	{ DBGBUS_DSPP, 130, 2 },
+	{ DBGBUS_DSPP, 130, 3 },
+	{ DBGBUS_DSPP, 130, 4 },
+	{ DBGBUS_DSPP, 130, 5 },
+
+	/* qseed */
+	{ DBGBUS_SSPP0, 6, 0},
+	{ DBGBUS_SSPP0, 6, 1},
+	{ DBGBUS_SSPP0, 26, 0},
+	{ DBGBUS_SSPP0, 26, 1},
+	{ DBGBUS_SSPP1, 6, 0},
+	{ DBGBUS_SSPP1, 6, 1},
+	{ DBGBUS_SSPP1, 26, 0},
+	{ DBGBUS_SSPP1, 26, 1},
+
+	/* scale */
+	{ DBGBUS_SSPP0, 16, 0},
+	{ DBGBUS_SSPP0, 16, 1},
+	{ DBGBUS_SSPP0, 36, 0},
+	{ DBGBUS_SSPP0, 36, 1},
+	{ DBGBUS_SSPP1, 16, 0},
+	{ DBGBUS_SSPP1, 16, 1},
+	{ DBGBUS_SSPP1, 36, 0},
+	{ DBGBUS_SSPP1, 36, 1},
+
+	/* fetch sspp0 */
+
+	/* vig 0 */
+	{ DBGBUS_SSPP0, 0, 0 },
+	{ DBGBUS_SSPP0, 0, 1 },
+	{ DBGBUS_SSPP0, 0, 2 },
+	{ DBGBUS_SSPP0, 0, 3 },
+	{ DBGBUS_SSPP0, 0, 4 },
+	{ DBGBUS_SSPP0, 0, 5 },
+	{ DBGBUS_SSPP0, 0, 6 },
+	{ DBGBUS_SSPP0, 0, 7 },
+
+	{ DBGBUS_SSPP0, 1, 0 },
+	{ DBGBUS_SSPP0, 1, 1 },
+	{ DBGBUS_SSPP0, 1, 2 },
+	{ DBGBUS_SSPP0, 1, 3 },
+	{ DBGBUS_SSPP0, 1, 4 },
+	{ DBGBUS_SSPP0, 1, 5 },
+	{ DBGBUS_SSPP0, 1, 6 },
+	{ DBGBUS_SSPP0, 1, 7 },
+
+	{ DBGBUS_SSPP0, 2, 0 },
+	{ DBGBUS_SSPP0, 2, 1 },
+	{ DBGBUS_SSPP0, 2, 2 },
+	{ DBGBUS_SSPP0, 2, 3 },
+	{ DBGBUS_SSPP0, 2, 4 },
+	{ DBGBUS_SSPP0, 2, 5 },
+	{ DBGBUS_SSPP0, 2, 6 },
+	{ DBGBUS_SSPP0, 2, 7 },
+
+	{ DBGBUS_SSPP0, 4, 0 },
+	{ DBGBUS_SSPP0, 4, 1 },
+	{ DBGBUS_SSPP0, 4, 2 },
+	{ DBGBUS_SSPP0, 4, 3 },
+	{ DBGBUS_SSPP0, 4, 4 },
+	{ DBGBUS_SSPP0, 4, 5 },
+	{ DBGBUS_SSPP0, 4, 6 },
+	{ DBGBUS_SSPP0, 4, 7 },
+
+	{ DBGBUS_SSPP0, 5, 0 },
+	{ DBGBUS_SSPP0, 5, 1 },
+	{ DBGBUS_SSPP0, 5, 2 },
+	{ DBGBUS_SSPP0, 5, 3 },
+	{ DBGBUS_SSPP0, 5, 4 },
+	{ DBGBUS_SSPP0, 5, 5 },
+	{ DBGBUS_SSPP0, 5, 6 },
+	{ DBGBUS_SSPP0, 5, 7 },
+
+	/* vig 2 */
+	{ DBGBUS_SSPP0, 20, 0 },
+	{ DBGBUS_SSPP0, 20, 1 },
+	{ DBGBUS_SSPP0, 20, 2 },
+	{ DBGBUS_SSPP0, 20, 3 },
+	{ DBGBUS_SSPP0, 20, 4 },
+	{ DBGBUS_SSPP0, 20, 5 },
+	{ DBGBUS_SSPP0, 20, 6 },
+	{ DBGBUS_SSPP0, 20, 7 },
+
+	{ DBGBUS_SSPP0, 21, 0 },
+	{ DBGBUS_SSPP0, 21, 1 },
+	{ DBGBUS_SSPP0, 21, 2 },
+	{ DBGBUS_SSPP0, 21, 3 },
+	{ DBGBUS_SSPP0, 21, 4 },
+	{ DBGBUS_SSPP0, 21, 5 },
+	{ DBGBUS_SSPP0, 21, 6 },
+	{ DBGBUS_SSPP0, 21, 7 },
+
+	{ DBGBUS_SSPP0, 22, 0 },
+	{ DBGBUS_SSPP0, 22, 1 },
+	{ DBGBUS_SSPP0, 22, 2 },
+	{ DBGBUS_SSPP0, 22, 3 },
+	{ DBGBUS_SSPP0, 22, 4 },
+	{ DBGBUS_SSPP0, 22, 5 },
+	{ DBGBUS_SSPP0, 22, 6 },
+	{ DBGBUS_SSPP0, 22, 7 },
+
+	{ DBGBUS_SSPP0, 24, 0 },
+	{ DBGBUS_SSPP0, 24, 1 },
+	{ DBGBUS_SSPP0, 24, 2 },
+	{ DBGBUS_SSPP0, 24, 3 },
+	{ DBGBUS_SSPP0, 24, 4 },
+	{ DBGBUS_SSPP0, 24, 5 },
+	{ DBGBUS_SSPP0, 24, 6 },
+	{ DBGBUS_SSPP0, 24, 7 },
+
+	{ DBGBUS_SSPP0, 25, 0 },
+	{ DBGBUS_SSPP0, 25, 1 },
+	{ DBGBUS_SSPP0, 25, 2 },
+	{ DBGBUS_SSPP0, 25, 3 },
+	{ DBGBUS_SSPP0, 25, 4 },
+	{ DBGBUS_SSPP0, 25, 5 },
+	{ DBGBUS_SSPP0, 25, 6 },
+	{ DBGBUS_SSPP0, 25, 7 },
+
+	/* dma 2 */
+	{ DBGBUS_SSPP0, 30, 0 },
+	{ DBGBUS_SSPP0, 30, 1 },
+	{ DBGBUS_SSPP0, 30, 2 },
+	{ DBGBUS_SSPP0, 30, 3 },
+	{ DBGBUS_SSPP0, 30, 4 },
+	{ DBGBUS_SSPP0, 30, 5 },
+	{ DBGBUS_SSPP0, 30, 6 },
+	{ DBGBUS_SSPP0, 30, 7 },
+
+	{ DBGBUS_SSPP0, 31, 0 },
+	{ DBGBUS_SSPP0, 31, 1 },
+	{ DBGBUS_SSPP0, 31, 2 },
+	{ DBGBUS_SSPP0, 31, 3 },
+	{ DBGBUS_SSPP0, 31, 4 },
+	{ DBGBUS_SSPP0, 31, 5 },
+	{ DBGBUS_SSPP0, 31, 6 },
+	{ DBGBUS_SSPP0, 31, 7 },
+
+	{ DBGBUS_SSPP0, 32, 0 },
+	{ DBGBUS_SSPP0, 32, 1 },
+	{ DBGBUS_SSPP0, 32, 2 },
+	{ DBGBUS_SSPP0, 32, 3 },
+	{ DBGBUS_SSPP0, 32, 4 },
+	{ DBGBUS_SSPP0, 32, 5 },
+	{ DBGBUS_SSPP0, 32, 6 },
+	{ DBGBUS_SSPP0, 32, 7 },
+
+	{ DBGBUS_SSPP0, 33, 0 },
+	{ DBGBUS_SSPP0, 33, 1 },
+	{ DBGBUS_SSPP0, 33, 2 },
+	{ DBGBUS_SSPP0, 33, 3 },
+	{ DBGBUS_SSPP0, 33, 4 },
+	{ DBGBUS_SSPP0, 33, 5 },
+	{ DBGBUS_SSPP0, 33, 6 },
+	{ DBGBUS_SSPP0, 33, 7 },
+
+	{ DBGBUS_SSPP0, 34, 0 },
+	{ DBGBUS_SSPP0, 34, 1 },
+	{ DBGBUS_SSPP0, 34, 2 },
+	{ DBGBUS_SSPP0, 34, 3 },
+	{ DBGBUS_SSPP0, 34, 4 },
+	{ DBGBUS_SSPP0, 34, 5 },
+	{ DBGBUS_SSPP0, 34, 6 },
+	{ DBGBUS_SSPP0, 34, 7 },
+
+	{ DBGBUS_SSPP0, 35, 0 },
+	{ DBGBUS_SSPP0, 35, 1 },
+	{ DBGBUS_SSPP0, 35, 2 },
+	{ DBGBUS_SSPP0, 35, 3 },
+
+	/* dma 0 */
+	{ DBGBUS_SSPP0, 40, 0 },
+	{ DBGBUS_SSPP0, 40, 1 },
+	{ DBGBUS_SSPP0, 40, 2 },
+	{ DBGBUS_SSPP0, 40, 3 },
+	{ DBGBUS_SSPP0, 40, 4 },
+	{ DBGBUS_SSPP0, 40, 5 },
+	{ DBGBUS_SSPP0, 40, 6 },
+	{ DBGBUS_SSPP0, 40, 7 },
+
+	{ DBGBUS_SSPP0, 41, 0 },
+	{ DBGBUS_SSPP0, 41, 1 },
+	{ DBGBUS_SSPP0, 41, 2 },
+	{ DBGBUS_SSPP0, 41, 3 },
+	{ DBGBUS_SSPP0, 41, 4 },
+	{ DBGBUS_SSPP0, 41, 5 },
+	{ DBGBUS_SSPP0, 41, 6 },
+	{ DBGBUS_SSPP0, 41, 7 },
+
+	{ DBGBUS_SSPP0, 42, 0 },
+	{ DBGBUS_SSPP0, 42, 1 },
+	{ DBGBUS_SSPP0, 42, 2 },
+	{ DBGBUS_SSPP0, 42, 3 },
+	{ DBGBUS_SSPP0, 42, 4 },
+	{ DBGBUS_SSPP0, 42, 5 },
+	{ DBGBUS_SSPP0, 42, 6 },
+	{ DBGBUS_SSPP0, 42, 7 },
+
+	{ DBGBUS_SSPP0, 44, 0 },
+	{ DBGBUS_SSPP0, 44, 1 },
+	{ DBGBUS_SSPP0, 44, 2 },
+	{ DBGBUS_SSPP0, 44, 3 },
+	{ DBGBUS_SSPP0, 44, 4 },
+	{ DBGBUS_SSPP0, 44, 5 },
+	{ DBGBUS_SSPP0, 44, 6 },
+	{ DBGBUS_SSPP0, 44, 7 },
+
+	{ DBGBUS_SSPP0, 45, 0 },
+	{ DBGBUS_SSPP0, 45, 1 },
+	{ DBGBUS_SSPP0, 45, 2 },
+	{ DBGBUS_SSPP0, 45, 3 },
+	{ DBGBUS_SSPP0, 45, 4 },
+	{ DBGBUS_SSPP0, 45, 5 },
+	{ DBGBUS_SSPP0, 45, 6 },
+	{ DBGBUS_SSPP0, 45, 7 },
+
+	/* fetch sspp1 */
+	/* vig 1 */
+	{ DBGBUS_SSPP1, 0, 0 },
+	{ DBGBUS_SSPP1, 0, 1 },
+	{ DBGBUS_SSPP1, 0, 2 },
+	{ DBGBUS_SSPP1, 0, 3 },
+	{ DBGBUS_SSPP1, 0, 4 },
+	{ DBGBUS_SSPP1, 0, 5 },
+	{ DBGBUS_SSPP1, 0, 6 },
+	{ DBGBUS_SSPP1, 0, 7 },
+
+	{ DBGBUS_SSPP1, 1, 0 },
+	{ DBGBUS_SSPP1, 1, 1 },
+	{ DBGBUS_SSPP1, 1, 2 },
+	{ DBGBUS_SSPP1, 1, 3 },
+	{ DBGBUS_SSPP1, 1, 4 },
+	{ DBGBUS_SSPP1, 1, 5 },
+	{ DBGBUS_SSPP1, 1, 6 },
+	{ DBGBUS_SSPP1, 1, 7 },
+
+	{ DBGBUS_SSPP1, 2, 0 },
+	{ DBGBUS_SSPP1, 2, 1 },
+	{ DBGBUS_SSPP1, 2, 2 },
+	{ DBGBUS_SSPP1, 2, 3 },
+	{ DBGBUS_SSPP1, 2, 4 },
+	{ DBGBUS_SSPP1, 2, 5 },
+	{ DBGBUS_SSPP1, 2, 6 },
+	{ DBGBUS_SSPP1, 2, 7 },
+
+	{ DBGBUS_SSPP1, 4, 0 },
+	{ DBGBUS_SSPP1, 4, 1 },
+	{ DBGBUS_SSPP1, 4, 2 },
+	{ DBGBUS_SSPP1, 4, 3 },
+	{ DBGBUS_SSPP1, 4, 4 },
+	{ DBGBUS_SSPP1, 4, 5 },
+	{ DBGBUS_SSPP1, 4, 6 },
+	{ DBGBUS_SSPP1, 4, 7 },
+
+	{ DBGBUS_SSPP1, 5, 0 },
+	{ DBGBUS_SSPP1, 5, 1 },
+	{ DBGBUS_SSPP1, 5, 2 },
+	{ DBGBUS_SSPP1, 5, 3 },
+	{ DBGBUS_SSPP1, 5, 4 },
+	{ DBGBUS_SSPP1, 5, 5 },
+	{ DBGBUS_SSPP1, 5, 6 },
+	{ DBGBUS_SSPP1, 5, 7 },
+
+	/* vig 3 */
+	{ DBGBUS_SSPP1, 20, 0 },
+	{ DBGBUS_SSPP1, 20, 1 },
+	{ DBGBUS_SSPP1, 20, 2 },
+	{ DBGBUS_SSPP1, 20, 3 },
+	{ DBGBUS_SSPP1, 20, 4 },
+	{ DBGBUS_SSPP1, 20, 5 },
+	{ DBGBUS_SSPP1, 20, 6 },
+	{ DBGBUS_SSPP1, 20, 7 },
+
+	{ DBGBUS_SSPP1, 21, 0 },
+	{ DBGBUS_SSPP1, 21, 1 },
+	{ DBGBUS_SSPP1, 21, 2 },
+	{ DBGBUS_SSPP1, 21, 3 },
+	{ DBGBUS_SSPP1, 21, 4 },
+	{ DBGBUS_SSPP1, 21, 5 },
+	{ DBGBUS_SSPP1, 21, 6 },
+	{ DBGBUS_SSPP1, 21, 7 },
+
+	{ DBGBUS_SSPP1, 22, 0 },
+	{ DBGBUS_SSPP1, 22, 1 },
+	{ DBGBUS_SSPP1, 22, 2 },
+	{ DBGBUS_SSPP1, 22, 3 },
+	{ DBGBUS_SSPP1, 22, 4 },
+	{ DBGBUS_SSPP1, 22, 5 },
+	{ DBGBUS_SSPP1, 22, 6 },
+	{ DBGBUS_SSPP1, 22, 7 },
+
+	{ DBGBUS_SSPP1, 24, 0 },
+	{ DBGBUS_SSPP1, 24, 1 },
+	{ DBGBUS_SSPP1, 24, 2 },
+	{ DBGBUS_SSPP1, 24, 3 },
+	{ DBGBUS_SSPP1, 24, 4 },
+	{ DBGBUS_SSPP1, 24, 5 },
+	{ DBGBUS_SSPP1, 24, 6 },
+	{ DBGBUS_SSPP1, 24, 7 },
+
+	{ DBGBUS_SSPP1, 25, 0 },
+	{ DBGBUS_SSPP1, 25, 1 },
+	{ DBGBUS_SSPP1, 25, 2 },
+	{ DBGBUS_SSPP1, 25, 3 },
+	{ DBGBUS_SSPP1, 25, 4 },
+	{ DBGBUS_SSPP1, 25, 5 },
+	{ DBGBUS_SSPP1, 25, 6 },
+	{ DBGBUS_SSPP1, 25, 7 },
+
+	/* dma 3 */
+	{ DBGBUS_SSPP1, 30, 0 },
+	{ DBGBUS_SSPP1, 30, 1 },
+	{ DBGBUS_SSPP1, 30, 2 },
+	{ DBGBUS_SSPP1, 30, 3 },
+	{ DBGBUS_SSPP1, 30, 4 },
+	{ DBGBUS_SSPP1, 30, 5 },
+	{ DBGBUS_SSPP1, 30, 6 },
+	{ DBGBUS_SSPP1, 30, 7 },
+
+	{ DBGBUS_SSPP1, 31, 0 },
+	{ DBGBUS_SSPP1, 31, 1 },
+	{ DBGBUS_SSPP1, 31, 2 },
+	{ DBGBUS_SSPP1, 31, 3 },
+	{ DBGBUS_SSPP1, 31, 4 },
+	{ DBGBUS_SSPP1, 31, 5 },
+	{ DBGBUS_SSPP1, 31, 6 },
+	{ DBGBUS_SSPP1, 31, 7 },
+
+	{ DBGBUS_SSPP1, 32, 0 },
+	{ DBGBUS_SSPP1, 32, 1 },
+	{ DBGBUS_SSPP1, 32, 2 },
+	{ DBGBUS_SSPP1, 32, 3 },
+	{ DBGBUS_SSPP1, 32, 4 },
+	{ DBGBUS_SSPP1, 32, 5 },
+	{ DBGBUS_SSPP1, 32, 6 },
+	{ DBGBUS_SSPP1, 32, 7 },
+
+	{ DBGBUS_SSPP1, 33, 0 },
+	{ DBGBUS_SSPP1, 33, 1 },
+	{ DBGBUS_SSPP1, 33, 2 },
+	{ DBGBUS_SSPP1, 33, 3 },
+	{ DBGBUS_SSPP1, 33, 4 },
+	{ DBGBUS_SSPP1, 33, 5 },
+	{ DBGBUS_SSPP1, 33, 6 },
+	{ DBGBUS_SSPP1, 33, 7 },
+
+	{ DBGBUS_SSPP1, 34, 0 },
+	{ DBGBUS_SSPP1, 34, 1 },
+	{ DBGBUS_SSPP1, 34, 2 },
+	{ DBGBUS_SSPP1, 34, 3 },
+	{ DBGBUS_SSPP1, 34, 4 },
+	{ DBGBUS_SSPP1, 34, 5 },
+	{ DBGBUS_SSPP1, 34, 6 },
+	{ DBGBUS_SSPP1, 34, 7 },
+
+	{ DBGBUS_SSPP1, 35, 0 },
+	{ DBGBUS_SSPP1, 35, 1 },
+	{ DBGBUS_SSPP1, 35, 2 },
+
+	/* dma 1 */
+	{ DBGBUS_SSPP1, 40, 0 },
+	{ DBGBUS_SSPP1, 40, 1 },
+	{ DBGBUS_SSPP1, 40, 2 },
+	{ DBGBUS_SSPP1, 40, 3 },
+	{ DBGBUS_SSPP1, 40, 4 },
+	{ DBGBUS_SSPP1, 40, 5 },
+	{ DBGBUS_SSPP1, 40, 6 },
+	{ DBGBUS_SSPP1, 40, 7 },
+
+	{ DBGBUS_SSPP1, 41, 0 },
+	{ DBGBUS_SSPP1, 41, 1 },
+	{ DBGBUS_SSPP1, 41, 2 },
+	{ DBGBUS_SSPP1, 41, 3 },
+	{ DBGBUS_SSPP1, 41, 4 },
+	{ DBGBUS_SSPP1, 41, 5 },
+	{ DBGBUS_SSPP1, 41, 6 },
+	{ DBGBUS_SSPP1, 41, 7 },
+
+	{ DBGBUS_SSPP1, 42, 0 },
+	{ DBGBUS_SSPP1, 42, 1 },
+	{ DBGBUS_SSPP1, 42, 2 },
+	{ DBGBUS_SSPP1, 42, 3 },
+	{ DBGBUS_SSPP1, 42, 4 },
+	{ DBGBUS_SSPP1, 42, 5 },
+	{ DBGBUS_SSPP1, 42, 6 },
+	{ DBGBUS_SSPP1, 42, 7 },
+
+	{ DBGBUS_SSPP1, 44, 0 },
+	{ DBGBUS_SSPP1, 44, 1 },
+	{ DBGBUS_SSPP1, 44, 2 },
+	{ DBGBUS_SSPP1, 44, 3 },
+	{ DBGBUS_SSPP1, 44, 4 },
+	{ DBGBUS_SSPP1, 44, 5 },
+	{ DBGBUS_SSPP1, 44, 6 },
+	{ DBGBUS_SSPP1, 44, 7 },
+
+	{ DBGBUS_SSPP1, 45, 0 },
+	{ DBGBUS_SSPP1, 45, 1 },
+	{ DBGBUS_SSPP1, 45, 2 },
+	{ DBGBUS_SSPP1, 45, 3 },
+	{ DBGBUS_SSPP1, 45, 4 },
+	{ DBGBUS_SSPP1, 45, 5 },
+	{ DBGBUS_SSPP1, 45, 6 },
+	{ DBGBUS_SSPP1, 45, 7 },
+
+	/* cursor 1 */
+	{ DBGBUS_SSPP1, 80, 0 },
+	{ DBGBUS_SSPP1, 80, 1 },
+	{ DBGBUS_SSPP1, 80, 2 },
+	{ DBGBUS_SSPP1, 80, 3 },
+	{ DBGBUS_SSPP1, 80, 4 },
+	{ DBGBUS_SSPP1, 80, 5 },
+	{ DBGBUS_SSPP1, 80, 6 },
+	{ DBGBUS_SSPP1, 80, 7 },
+
+	{ DBGBUS_SSPP1, 81, 0 },
+	{ DBGBUS_SSPP1, 81, 1 },
+	{ DBGBUS_SSPP1, 81, 2 },
+	{ DBGBUS_SSPP1, 81, 3 },
+	{ DBGBUS_SSPP1, 81, 4 },
+	{ DBGBUS_SSPP1, 81, 5 },
+	{ DBGBUS_SSPP1, 81, 6 },
+	{ DBGBUS_SSPP1, 81, 7 },
+
+	{ DBGBUS_SSPP1, 82, 0 },
+	{ DBGBUS_SSPP1, 82, 1 },
+	{ DBGBUS_SSPP1, 82, 2 },
+	{ DBGBUS_SSPP1, 82, 3 },
+	{ DBGBUS_SSPP1, 82, 4 },
+	{ DBGBUS_SSPP1, 82, 5 },
+	{ DBGBUS_SSPP1, 82, 6 },
+	{ DBGBUS_SSPP1, 82, 7 },
+
+	{ DBGBUS_SSPP1, 83, 0 },
+	{ DBGBUS_SSPP1, 83, 1 },
+	{ DBGBUS_SSPP1, 83, 2 },
+	{ DBGBUS_SSPP1, 83, 3 },
+	{ DBGBUS_SSPP1, 83, 4 },
+	{ DBGBUS_SSPP1, 83, 5 },
+	{ DBGBUS_SSPP1, 83, 6 },
+	{ DBGBUS_SSPP1, 83, 7 },
+
+	{ DBGBUS_SSPP1, 84, 0 },
+	{ DBGBUS_SSPP1, 84, 1 },
+	{ DBGBUS_SSPP1, 84, 2 },
+	{ DBGBUS_SSPP1, 84, 3 },
+	{ DBGBUS_SSPP1, 84, 4 },
+	{ DBGBUS_SSPP1, 84, 5 },
+	{ DBGBUS_SSPP1, 84, 6 },
+	{ DBGBUS_SSPP1, 84, 7 },
+
+	/* dspp */
+	{ DBGBUS_DSPP, 13, 0 },
+	{ DBGBUS_DSPP, 19, 0 },
+	{ DBGBUS_DSPP, 14, 0 },
+	{ DBGBUS_DSPP, 14, 1 },
+	{ DBGBUS_DSPP, 14, 3 },
+	{ DBGBUS_DSPP, 20, 0 },
+	{ DBGBUS_DSPP, 20, 1 },
+	{ DBGBUS_DSPP, 20, 3 },
+
+	/* ppb_0 */
+	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
+
+	/* ppb_1 */
+	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
+
+	/* lm_lut */
+	{ DBGBUS_DSPP, 109, 0 },
+	{ DBGBUS_DSPP, 105, 0 },
+	{ DBGBUS_DSPP, 103, 0 },
+
+	/* tear-check */
+	{ DBGBUS_PERIPH, 63, 0 },
+	{ DBGBUS_PERIPH, 64, 0 },
+	{ DBGBUS_PERIPH, 65, 0 },
+	{ DBGBUS_PERIPH, 73, 0 },
+	{ DBGBUS_PERIPH, 74, 0 },
+
+	/* crossbar */
+	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
+
+	/* rotator */
+	{ DBGBUS_DSPP, 9, 0},
+
+	/* blend */
+	/* LM0 */
+	{ DBGBUS_DSPP, 63, 0},
+	{ DBGBUS_DSPP, 63, 1},
+	{ DBGBUS_DSPP, 63, 2},
+	{ DBGBUS_DSPP, 63, 3},
+	{ DBGBUS_DSPP, 63, 4},
+	{ DBGBUS_DSPP, 63, 5},
+	{ DBGBUS_DSPP, 63, 6},
+	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 64, 0},
+	{ DBGBUS_DSPP, 64, 1},
+	{ DBGBUS_DSPP, 64, 2},
+	{ DBGBUS_DSPP, 64, 3},
+	{ DBGBUS_DSPP, 64, 4},
+	{ DBGBUS_DSPP, 64, 5},
+	{ DBGBUS_DSPP, 64, 6},
+	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 65, 0},
+	{ DBGBUS_DSPP, 65, 1},
+	{ DBGBUS_DSPP, 65, 2},
+	{ DBGBUS_DSPP, 65, 3},
+	{ DBGBUS_DSPP, 65, 4},
+	{ DBGBUS_DSPP, 65, 5},
+	{ DBGBUS_DSPP, 65, 6},
+	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 66, 0},
+	{ DBGBUS_DSPP, 66, 1},
+	{ DBGBUS_DSPP, 66, 2},
+	{ DBGBUS_DSPP, 66, 3},
+	{ DBGBUS_DSPP, 66, 4},
+	{ DBGBUS_DSPP, 66, 5},
+	{ DBGBUS_DSPP, 66, 6},
+	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 67, 0},
+	{ DBGBUS_DSPP, 67, 1},
+	{ DBGBUS_DSPP, 67, 2},
+	{ DBGBUS_DSPP, 67, 3},
+	{ DBGBUS_DSPP, 67, 4},
+	{ DBGBUS_DSPP, 67, 5},
+	{ DBGBUS_DSPP, 67, 6},
+	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 68, 0},
+	{ DBGBUS_DSPP, 68, 1},
+	{ DBGBUS_DSPP, 68, 2},
+	{ DBGBUS_DSPP, 68, 3},
+	{ DBGBUS_DSPP, 68, 4},
+	{ DBGBUS_DSPP, 68, 5},
+	{ DBGBUS_DSPP, 68, 6},
+	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 69, 0},
+	{ DBGBUS_DSPP, 69, 1},
+	{ DBGBUS_DSPP, 69, 2},
+	{ DBGBUS_DSPP, 69, 3},
+	{ DBGBUS_DSPP, 69, 4},
+	{ DBGBUS_DSPP, 69, 5},
+	{ DBGBUS_DSPP, 69, 6},
+	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM1 */
+	{ DBGBUS_DSPP, 70, 0},
+	{ DBGBUS_DSPP, 70, 1},
+	{ DBGBUS_DSPP, 70, 2},
+	{ DBGBUS_DSPP, 70, 3},
+	{ DBGBUS_DSPP, 70, 4},
+	{ DBGBUS_DSPP, 70, 5},
+	{ DBGBUS_DSPP, 70, 6},
+	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 71, 0},
+	{ DBGBUS_DSPP, 71, 1},
+	{ DBGBUS_DSPP, 71, 2},
+	{ DBGBUS_DSPP, 71, 3},
+	{ DBGBUS_DSPP, 71, 4},
+	{ DBGBUS_DSPP, 71, 5},
+	{ DBGBUS_DSPP, 71, 6},
+	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 72, 0},
+	{ DBGBUS_DSPP, 72, 1},
+	{ DBGBUS_DSPP, 72, 2},
+	{ DBGBUS_DSPP, 72, 3},
+	{ DBGBUS_DSPP, 72, 4},
+	{ DBGBUS_DSPP, 72, 5},
+	{ DBGBUS_DSPP, 72, 6},
+	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 73, 0},
+	{ DBGBUS_DSPP, 73, 1},
+	{ DBGBUS_DSPP, 73, 2},
+	{ DBGBUS_DSPP, 73, 3},
+	{ DBGBUS_DSPP, 73, 4},
+	{ DBGBUS_DSPP, 73, 5},
+	{ DBGBUS_DSPP, 73, 6},
+	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 74, 0},
+	{ DBGBUS_DSPP, 74, 1},
+	{ DBGBUS_DSPP, 74, 2},
+	{ DBGBUS_DSPP, 74, 3},
+	{ DBGBUS_DSPP, 74, 4},
+	{ DBGBUS_DSPP, 74, 5},
+	{ DBGBUS_DSPP, 74, 6},
+	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 75, 0},
+	{ DBGBUS_DSPP, 75, 1},
+	{ DBGBUS_DSPP, 75, 2},
+	{ DBGBUS_DSPP, 75, 3},
+	{ DBGBUS_DSPP, 75, 4},
+	{ DBGBUS_DSPP, 75, 5},
+	{ DBGBUS_DSPP, 75, 6},
+	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 76, 0},
+	{ DBGBUS_DSPP, 76, 1},
+	{ DBGBUS_DSPP, 76, 2},
+	{ DBGBUS_DSPP, 76, 3},
+	{ DBGBUS_DSPP, 76, 4},
+	{ DBGBUS_DSPP, 76, 5},
+	{ DBGBUS_DSPP, 76, 6},
+	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM2 */
+	{ DBGBUS_DSPP, 77, 0},
+	{ DBGBUS_DSPP, 77, 1},
+	{ DBGBUS_DSPP, 77, 2},
+	{ DBGBUS_DSPP, 77, 3},
+	{ DBGBUS_DSPP, 77, 4},
+	{ DBGBUS_DSPP, 77, 5},
+	{ DBGBUS_DSPP, 77, 6},
+	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 78, 0},
+	{ DBGBUS_DSPP, 78, 1},
+	{ DBGBUS_DSPP, 78, 2},
+	{ DBGBUS_DSPP, 78, 3},
+	{ DBGBUS_DSPP, 78, 4},
+	{ DBGBUS_DSPP, 78, 5},
+	{ DBGBUS_DSPP, 78, 6},
+	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 79, 0},
+	{ DBGBUS_DSPP, 79, 1},
+	{ DBGBUS_DSPP, 79, 2},
+	{ DBGBUS_DSPP, 79, 3},
+	{ DBGBUS_DSPP, 79, 4},
+	{ DBGBUS_DSPP, 79, 5},
+	{ DBGBUS_DSPP, 79, 6},
+	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 80, 0},
+	{ DBGBUS_DSPP, 80, 1},
+	{ DBGBUS_DSPP, 80, 2},
+	{ DBGBUS_DSPP, 80, 3},
+	{ DBGBUS_DSPP, 80, 4},
+	{ DBGBUS_DSPP, 80, 5},
+	{ DBGBUS_DSPP, 80, 6},
+	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 81, 0},
+	{ DBGBUS_DSPP, 81, 1},
+	{ DBGBUS_DSPP, 81, 2},
+	{ DBGBUS_DSPP, 81, 3},
+	{ DBGBUS_DSPP, 81, 4},
+	{ DBGBUS_DSPP, 81, 5},
+	{ DBGBUS_DSPP, 81, 6},
+	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 82, 0},
+	{ DBGBUS_DSPP, 82, 1},
+	{ DBGBUS_DSPP, 82, 2},
+	{ DBGBUS_DSPP, 82, 3},
+	{ DBGBUS_DSPP, 82, 4},
+	{ DBGBUS_DSPP, 82, 5},
+	{ DBGBUS_DSPP, 82, 6},
+	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 83, 0},
+	{ DBGBUS_DSPP, 83, 1},
+	{ DBGBUS_DSPP, 83, 2},
+	{ DBGBUS_DSPP, 83, 3},
+	{ DBGBUS_DSPP, 83, 4},
+	{ DBGBUS_DSPP, 83, 5},
+	{ DBGBUS_DSPP, 83, 6},
+	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
+
+	/* csc */
+	{ DBGBUS_SSPP0, 7, 0},
+	{ DBGBUS_SSPP0, 7, 1},
+	{ DBGBUS_SSPP0, 27, 0},
+	{ DBGBUS_SSPP0, 27, 1},
+	{ DBGBUS_SSPP1, 7, 0},
+	{ DBGBUS_SSPP1, 7, 1},
+	{ DBGBUS_SSPP1, 27, 0},
+	{ DBGBUS_SSPP1, 27, 1},
+
+	/* pcc */
+	{ DBGBUS_SSPP0, 3,  3},
+	{ DBGBUS_SSPP0, 23, 3},
+	{ DBGBUS_SSPP0, 33, 3},
+	{ DBGBUS_SSPP0, 43, 3},
+	{ DBGBUS_SSPP1, 3,  3},
+	{ DBGBUS_SSPP1, 23, 3},
+	{ DBGBUS_SSPP1, 33, 3},
+	{ DBGBUS_SSPP1, 43, 3},
+
+	/* spa */
+	{ DBGBUS_SSPP0, 8,  0},
+	{ DBGBUS_SSPP0, 28, 0},
+	{ DBGBUS_SSPP1, 8,  0},
+	{ DBGBUS_SSPP1, 28, 0},
+	{ DBGBUS_DSPP, 13, 0},
+	{ DBGBUS_DSPP, 19, 0},
+
+	/* igc */
+	{ DBGBUS_SSPP0, 9,  0},
+	{ DBGBUS_SSPP0, 9,  1},
+	{ DBGBUS_SSPP0, 9,  3},
+	{ DBGBUS_SSPP0, 29, 0},
+	{ DBGBUS_SSPP0, 29, 1},
+	{ DBGBUS_SSPP0, 29, 3},
+	{ DBGBUS_SSPP0, 17, 0},
+	{ DBGBUS_SSPP0, 17, 1},
+	{ DBGBUS_SSPP0, 17, 3},
+	{ DBGBUS_SSPP0, 37, 0},
+	{ DBGBUS_SSPP0, 37, 1},
+	{ DBGBUS_SSPP0, 37, 3},
+	{ DBGBUS_SSPP0, 46, 0},
+	{ DBGBUS_SSPP0, 46, 1},
+	{ DBGBUS_SSPP0, 46, 3},
+
+	{ DBGBUS_SSPP1, 9,  0},
+	{ DBGBUS_SSPP1, 9,  1},
+	{ DBGBUS_SSPP1, 9,  3},
+	{ DBGBUS_SSPP1, 29, 0},
+	{ DBGBUS_SSPP1, 29, 1},
+	{ DBGBUS_SSPP1, 29, 3},
+	{ DBGBUS_SSPP1, 17, 0},
+	{ DBGBUS_SSPP1, 17, 1},
+	{ DBGBUS_SSPP1, 17, 3},
+	{ DBGBUS_SSPP1, 37, 0},
+	{ DBGBUS_SSPP1, 37, 1},
+	{ DBGBUS_SSPP1, 37, 3},
+	{ DBGBUS_SSPP1, 46, 0},
+	{ DBGBUS_SSPP1, 46, 1},
+	{ DBGBUS_SSPP1, 46, 3},
+
+	{ DBGBUS_DSPP, 14, 0},
+	{ DBGBUS_DSPP, 14, 1},
+	{ DBGBUS_DSPP, 14, 3},
+	{ DBGBUS_DSPP, 20, 0},
+	{ DBGBUS_DSPP, 20, 1},
+	{ DBGBUS_DSPP, 20, 3},
+
+	{ DBGBUS_PERIPH, 60, 0},
+};
+
+static struct dpu_debug_bus_entry dbg_bus_dpu_sdm845[] = {
+
+	/* Unpack 0 sspp 0*/
+	{ DBGBUS_SSPP0, 50, 2 },
+	{ DBGBUS_SSPP0, 60, 2 },
+	{ DBGBUS_SSPP0, 70, 2 },
+
+	/* Upack 0 sspp 1*/
+	{ DBGBUS_SSPP1, 50, 2 },
+	{ DBGBUS_SSPP1, 60, 2 },
+	{ DBGBUS_SSPP1, 70, 2 },
+
+	/* scheduler */
+	{ DBGBUS_DSPP, 130, 0 },
+	{ DBGBUS_DSPP, 130, 1 },
+	{ DBGBUS_DSPP, 130, 2 },
+	{ DBGBUS_DSPP, 130, 3 },
+	{ DBGBUS_DSPP, 130, 4 },
+	{ DBGBUS_DSPP, 130, 5 },
+
+	/* qseed */
+	{ DBGBUS_SSPP0, 6, 0},
+	{ DBGBUS_SSPP0, 6, 1},
+	{ DBGBUS_SSPP0, 26, 0},
+	{ DBGBUS_SSPP0, 26, 1},
+	{ DBGBUS_SSPP1, 6, 0},
+	{ DBGBUS_SSPP1, 6, 1},
+	{ DBGBUS_SSPP1, 26, 0},
+	{ DBGBUS_SSPP1, 26, 1},
+
+	/* scale */
+	{ DBGBUS_SSPP0, 16, 0},
+	{ DBGBUS_SSPP0, 16, 1},
+	{ DBGBUS_SSPP0, 36, 0},
+	{ DBGBUS_SSPP0, 36, 1},
+	{ DBGBUS_SSPP1, 16, 0},
+	{ DBGBUS_SSPP1, 16, 1},
+	{ DBGBUS_SSPP1, 36, 0},
+	{ DBGBUS_SSPP1, 36, 1},
+
+	/* fetch sspp0 */
+
+	/* vig 0 */
+	{ DBGBUS_SSPP0, 0, 0 },
+	{ DBGBUS_SSPP0, 0, 1 },
+	{ DBGBUS_SSPP0, 0, 2 },
+	{ DBGBUS_SSPP0, 0, 3 },
+	{ DBGBUS_SSPP0, 0, 4 },
+	{ DBGBUS_SSPP0, 0, 5 },
+	{ DBGBUS_SSPP0, 0, 6 },
+	{ DBGBUS_SSPP0, 0, 7 },
+
+	{ DBGBUS_SSPP0, 1, 0 },
+	{ DBGBUS_SSPP0, 1, 1 },
+	{ DBGBUS_SSPP0, 1, 2 },
+	{ DBGBUS_SSPP0, 1, 3 },
+	{ DBGBUS_SSPP0, 1, 4 },
+	{ DBGBUS_SSPP0, 1, 5 },
+	{ DBGBUS_SSPP0, 1, 6 },
+	{ DBGBUS_SSPP0, 1, 7 },
+
+	{ DBGBUS_SSPP0, 2, 0 },
+	{ DBGBUS_SSPP0, 2, 1 },
+	{ DBGBUS_SSPP0, 2, 2 },
+	{ DBGBUS_SSPP0, 2, 3 },
+	{ DBGBUS_SSPP0, 2, 4 },
+	{ DBGBUS_SSPP0, 2, 5 },
+	{ DBGBUS_SSPP0, 2, 6 },
+	{ DBGBUS_SSPP0, 2, 7 },
+
+	{ DBGBUS_SSPP0, 4, 0 },
+	{ DBGBUS_SSPP0, 4, 1 },
+	{ DBGBUS_SSPP0, 4, 2 },
+	{ DBGBUS_SSPP0, 4, 3 },
+	{ DBGBUS_SSPP0, 4, 4 },
+	{ DBGBUS_SSPP0, 4, 5 },
+	{ DBGBUS_SSPP0, 4, 6 },
+	{ DBGBUS_SSPP0, 4, 7 },
+
+	{ DBGBUS_SSPP0, 5, 0 },
+	{ DBGBUS_SSPP0, 5, 1 },
+	{ DBGBUS_SSPP0, 5, 2 },
+	{ DBGBUS_SSPP0, 5, 3 },
+	{ DBGBUS_SSPP0, 5, 4 },
+	{ DBGBUS_SSPP0, 5, 5 },
+	{ DBGBUS_SSPP0, 5, 6 },
+	{ DBGBUS_SSPP0, 5, 7 },
+
+	/* vig 2 */
+	{ DBGBUS_SSPP0, 20, 0 },
+	{ DBGBUS_SSPP0, 20, 1 },
+	{ DBGBUS_SSPP0, 20, 2 },
+	{ DBGBUS_SSPP0, 20, 3 },
+	{ DBGBUS_SSPP0, 20, 4 },
+	{ DBGBUS_SSPP0, 20, 5 },
+	{ DBGBUS_SSPP0, 20, 6 },
+	{ DBGBUS_SSPP0, 20, 7 },
+
+	{ DBGBUS_SSPP0, 21, 0 },
+	{ DBGBUS_SSPP0, 21, 1 },
+	{ DBGBUS_SSPP0, 21, 2 },
+	{ DBGBUS_SSPP0, 21, 3 },
+	{ DBGBUS_SSPP0, 21, 4 },
+	{ DBGBUS_SSPP0, 21, 5 },
+	{ DBGBUS_SSPP0, 21, 6 },
+	{ DBGBUS_SSPP0, 21, 7 },
+
+	{ DBGBUS_SSPP0, 22, 0 },
+	{ DBGBUS_SSPP0, 22, 1 },
+	{ DBGBUS_SSPP0, 22, 2 },
+	{ DBGBUS_SSPP0, 22, 3 },
+	{ DBGBUS_SSPP0, 22, 4 },
+	{ DBGBUS_SSPP0, 22, 5 },
+	{ DBGBUS_SSPP0, 22, 6 },
+	{ DBGBUS_SSPP0, 22, 7 },
+
+	{ DBGBUS_SSPP0, 24, 0 },
+	{ DBGBUS_SSPP0, 24, 1 },
+	{ DBGBUS_SSPP0, 24, 2 },
+	{ DBGBUS_SSPP0, 24, 3 },
+	{ DBGBUS_SSPP0, 24, 4 },
+	{ DBGBUS_SSPP0, 24, 5 },
+	{ DBGBUS_SSPP0, 24, 6 },
+	{ DBGBUS_SSPP0, 24, 7 },
+
+	{ DBGBUS_SSPP0, 25, 0 },
+	{ DBGBUS_SSPP0, 25, 1 },
+	{ DBGBUS_SSPP0, 25, 2 },
+	{ DBGBUS_SSPP0, 25, 3 },
+	{ DBGBUS_SSPP0, 25, 4 },
+	{ DBGBUS_SSPP0, 25, 5 },
+	{ DBGBUS_SSPP0, 25, 6 },
+	{ DBGBUS_SSPP0, 25, 7 },
+
+	/* dma 2 */
+	{ DBGBUS_SSPP0, 30, 0 },
+	{ DBGBUS_SSPP0, 30, 1 },
+	{ DBGBUS_SSPP0, 30, 2 },
+	{ DBGBUS_SSPP0, 30, 3 },
+	{ DBGBUS_SSPP0, 30, 4 },
+	{ DBGBUS_SSPP0, 30, 5 },
+	{ DBGBUS_SSPP0, 30, 6 },
+	{ DBGBUS_SSPP0, 30, 7 },
+
+	{ DBGBUS_SSPP0, 31, 0 },
+	{ DBGBUS_SSPP0, 31, 1 },
+	{ DBGBUS_SSPP0, 31, 2 },
+	{ DBGBUS_SSPP0, 31, 3 },
+	{ DBGBUS_SSPP0, 31, 4 },
+	{ DBGBUS_SSPP0, 31, 5 },
+	{ DBGBUS_SSPP0, 31, 6 },
+	{ DBGBUS_SSPP0, 31, 7 },
+
+	{ DBGBUS_SSPP0, 32, 0 },
+	{ DBGBUS_SSPP0, 32, 1 },
+	{ DBGBUS_SSPP0, 32, 2 },
+	{ DBGBUS_SSPP0, 32, 3 },
+	{ DBGBUS_SSPP0, 32, 4 },
+	{ DBGBUS_SSPP0, 32, 5 },
+	{ DBGBUS_SSPP0, 32, 6 },
+	{ DBGBUS_SSPP0, 32, 7 },
+
+	{ DBGBUS_SSPP0, 33, 0 },
+	{ DBGBUS_SSPP0, 33, 1 },
+	{ DBGBUS_SSPP0, 33, 2 },
+	{ DBGBUS_SSPP0, 33, 3 },
+	{ DBGBUS_SSPP0, 33, 4 },
+	{ DBGBUS_SSPP0, 33, 5 },
+	{ DBGBUS_SSPP0, 33, 6 },
+	{ DBGBUS_SSPP0, 33, 7 },
+
+	{ DBGBUS_SSPP0, 34, 0 },
+	{ DBGBUS_SSPP0, 34, 1 },
+	{ DBGBUS_SSPP0, 34, 2 },
+	{ DBGBUS_SSPP0, 34, 3 },
+	{ DBGBUS_SSPP0, 34, 4 },
+	{ DBGBUS_SSPP0, 34, 5 },
+	{ DBGBUS_SSPP0, 34, 6 },
+	{ DBGBUS_SSPP0, 34, 7 },
+
+	{ DBGBUS_SSPP0, 35, 0 },
+	{ DBGBUS_SSPP0, 35, 1 },
+	{ DBGBUS_SSPP0, 35, 2 },
+	{ DBGBUS_SSPP0, 35, 3 },
+
+	/* dma 0 */
+	{ DBGBUS_SSPP0, 40, 0 },
+	{ DBGBUS_SSPP0, 40, 1 },
+	{ DBGBUS_SSPP0, 40, 2 },
+	{ DBGBUS_SSPP0, 40, 3 },
+	{ DBGBUS_SSPP0, 40, 4 },
+	{ DBGBUS_SSPP0, 40, 5 },
+	{ DBGBUS_SSPP0, 40, 6 },
+	{ DBGBUS_SSPP0, 40, 7 },
+
+	{ DBGBUS_SSPP0, 41, 0 },
+	{ DBGBUS_SSPP0, 41, 1 },
+	{ DBGBUS_SSPP0, 41, 2 },
+	{ DBGBUS_SSPP0, 41, 3 },
+	{ DBGBUS_SSPP0, 41, 4 },
+	{ DBGBUS_SSPP0, 41, 5 },
+	{ DBGBUS_SSPP0, 41, 6 },
+	{ DBGBUS_SSPP0, 41, 7 },
+
+	{ DBGBUS_SSPP0, 42, 0 },
+	{ DBGBUS_SSPP0, 42, 1 },
+	{ DBGBUS_SSPP0, 42, 2 },
+	{ DBGBUS_SSPP0, 42, 3 },
+	{ DBGBUS_SSPP0, 42, 4 },
+	{ DBGBUS_SSPP0, 42, 5 },
+	{ DBGBUS_SSPP0, 42, 6 },
+	{ DBGBUS_SSPP0, 42, 7 },
+
+	{ DBGBUS_SSPP0, 44, 0 },
+	{ DBGBUS_SSPP0, 44, 1 },
+	{ DBGBUS_SSPP0, 44, 2 },
+	{ DBGBUS_SSPP0, 44, 3 },
+	{ DBGBUS_SSPP0, 44, 4 },
+	{ DBGBUS_SSPP0, 44, 5 },
+	{ DBGBUS_SSPP0, 44, 6 },
+	{ DBGBUS_SSPP0, 44, 7 },
+
+	{ DBGBUS_SSPP0, 45, 0 },
+	{ DBGBUS_SSPP0, 45, 1 },
+	{ DBGBUS_SSPP0, 45, 2 },
+	{ DBGBUS_SSPP0, 45, 3 },
+	{ DBGBUS_SSPP0, 45, 4 },
+	{ DBGBUS_SSPP0, 45, 5 },
+	{ DBGBUS_SSPP0, 45, 6 },
+	{ DBGBUS_SSPP0, 45, 7 },
+
+	/* fetch sspp1 */
+	/* vig 1 */
+	{ DBGBUS_SSPP1, 0, 0 },
+	{ DBGBUS_SSPP1, 0, 1 },
+	{ DBGBUS_SSPP1, 0, 2 },
+	{ DBGBUS_SSPP1, 0, 3 },
+	{ DBGBUS_SSPP1, 0, 4 },
+	{ DBGBUS_SSPP1, 0, 5 },
+	{ DBGBUS_SSPP1, 0, 6 },
+	{ DBGBUS_SSPP1, 0, 7 },
+
+	{ DBGBUS_SSPP1, 1, 0 },
+	{ DBGBUS_SSPP1, 1, 1 },
+	{ DBGBUS_SSPP1, 1, 2 },
+	{ DBGBUS_SSPP1, 1, 3 },
+	{ DBGBUS_SSPP1, 1, 4 },
+	{ DBGBUS_SSPP1, 1, 5 },
+	{ DBGBUS_SSPP1, 1, 6 },
+	{ DBGBUS_SSPP1, 1, 7 },
+
+	{ DBGBUS_SSPP1, 2, 0 },
+	{ DBGBUS_SSPP1, 2, 1 },
+	{ DBGBUS_SSPP1, 2, 2 },
+	{ DBGBUS_SSPP1, 2, 3 },
+	{ DBGBUS_SSPP1, 2, 4 },
+	{ DBGBUS_SSPP1, 2, 5 },
+	{ DBGBUS_SSPP1, 2, 6 },
+	{ DBGBUS_SSPP1, 2, 7 },
+
+	{ DBGBUS_SSPP1, 4, 0 },
+	{ DBGBUS_SSPP1, 4, 1 },
+	{ DBGBUS_SSPP1, 4, 2 },
+	{ DBGBUS_SSPP1, 4, 3 },
+	{ DBGBUS_SSPP1, 4, 4 },
+	{ DBGBUS_SSPP1, 4, 5 },
+	{ DBGBUS_SSPP1, 4, 6 },
+	{ DBGBUS_SSPP1, 4, 7 },
+
+	{ DBGBUS_SSPP1, 5, 0 },
+	{ DBGBUS_SSPP1, 5, 1 },
+	{ DBGBUS_SSPP1, 5, 2 },
+	{ DBGBUS_SSPP1, 5, 3 },
+	{ DBGBUS_SSPP1, 5, 4 },
+	{ DBGBUS_SSPP1, 5, 5 },
+	{ DBGBUS_SSPP1, 5, 6 },
+	{ DBGBUS_SSPP1, 5, 7 },
+
+	/* vig 3 */
+	{ DBGBUS_SSPP1, 20, 0 },
+	{ DBGBUS_SSPP1, 20, 1 },
+	{ DBGBUS_SSPP1, 20, 2 },
+	{ DBGBUS_SSPP1, 20, 3 },
+	{ DBGBUS_SSPP1, 20, 4 },
+	{ DBGBUS_SSPP1, 20, 5 },
+	{ DBGBUS_SSPP1, 20, 6 },
+	{ DBGBUS_SSPP1, 20, 7 },
+
+	{ DBGBUS_SSPP1, 21, 0 },
+	{ DBGBUS_SSPP1, 21, 1 },
+	{ DBGBUS_SSPP1, 21, 2 },
+	{ DBGBUS_SSPP1, 21, 3 },
+	{ DBGBUS_SSPP1, 21, 4 },
+	{ DBGBUS_SSPP1, 21, 5 },
+	{ DBGBUS_SSPP1, 21, 6 },
+	{ DBGBUS_SSPP1, 21, 7 },
+
+	{ DBGBUS_SSPP1, 22, 0 },
+	{ DBGBUS_SSPP1, 22, 1 },
+	{ DBGBUS_SSPP1, 22, 2 },
+	{ DBGBUS_SSPP1, 22, 3 },
+	{ DBGBUS_SSPP1, 22, 4 },
+	{ DBGBUS_SSPP1, 22, 5 },
+	{ DBGBUS_SSPP1, 22, 6 },
+	{ DBGBUS_SSPP1, 22, 7 },
+
+	{ DBGBUS_SSPP1, 24, 0 },
+	{ DBGBUS_SSPP1, 24, 1 },
+	{ DBGBUS_SSPP1, 24, 2 },
+	{ DBGBUS_SSPP1, 24, 3 },
+	{ DBGBUS_SSPP1, 24, 4 },
+	{ DBGBUS_SSPP1, 24, 5 },
+	{ DBGBUS_SSPP1, 24, 6 },
+	{ DBGBUS_SSPP1, 24, 7 },
+
+	{ DBGBUS_SSPP1, 25, 0 },
+	{ DBGBUS_SSPP1, 25, 1 },
+	{ DBGBUS_SSPP1, 25, 2 },
+	{ DBGBUS_SSPP1, 25, 3 },
+	{ DBGBUS_SSPP1, 25, 4 },
+	{ DBGBUS_SSPP1, 25, 5 },
+	{ DBGBUS_SSPP1, 25, 6 },
+	{ DBGBUS_SSPP1, 25, 7 },
+
+	/* dma 3 */
+	{ DBGBUS_SSPP1, 30, 0 },
+	{ DBGBUS_SSPP1, 30, 1 },
+	{ DBGBUS_SSPP1, 30, 2 },
+	{ DBGBUS_SSPP1, 30, 3 },
+	{ DBGBUS_SSPP1, 30, 4 },
+	{ DBGBUS_SSPP1, 30, 5 },
+	{ DBGBUS_SSPP1, 30, 6 },
+	{ DBGBUS_SSPP1, 30, 7 },
+
+	{ DBGBUS_SSPP1, 31, 0 },
+	{ DBGBUS_SSPP1, 31, 1 },
+	{ DBGBUS_SSPP1, 31, 2 },
+	{ DBGBUS_SSPP1, 31, 3 },
+	{ DBGBUS_SSPP1, 31, 4 },
+	{ DBGBUS_SSPP1, 31, 5 },
+	{ DBGBUS_SSPP1, 31, 6 },
+	{ DBGBUS_SSPP1, 31, 7 },
+
+	{ DBGBUS_SSPP1, 32, 0 },
+	{ DBGBUS_SSPP1, 32, 1 },
+	{ DBGBUS_SSPP1, 32, 2 },
+	{ DBGBUS_SSPP1, 32, 3 },
+	{ DBGBUS_SSPP1, 32, 4 },
+	{ DBGBUS_SSPP1, 32, 5 },
+	{ DBGBUS_SSPP1, 32, 6 },
+	{ DBGBUS_SSPP1, 32, 7 },
+
+	{ DBGBUS_SSPP1, 33, 0 },
+	{ DBGBUS_SSPP1, 33, 1 },
+	{ DBGBUS_SSPP1, 33, 2 },
+	{ DBGBUS_SSPP1, 33, 3 },
+	{ DBGBUS_SSPP1, 33, 4 },
+	{ DBGBUS_SSPP1, 33, 5 },
+	{ DBGBUS_SSPP1, 33, 6 },
+	{ DBGBUS_SSPP1, 33, 7 },
+
+	{ DBGBUS_SSPP1, 34, 0 },
+	{ DBGBUS_SSPP1, 34, 1 },
+	{ DBGBUS_SSPP1, 34, 2 },
+	{ DBGBUS_SSPP1, 34, 3 },
+	{ DBGBUS_SSPP1, 34, 4 },
+	{ DBGBUS_SSPP1, 34, 5 },
+	{ DBGBUS_SSPP1, 34, 6 },
+	{ DBGBUS_SSPP1, 34, 7 },
+
+	{ DBGBUS_SSPP1, 35, 0 },
+	{ DBGBUS_SSPP1, 35, 1 },
+	{ DBGBUS_SSPP1, 35, 2 },
+
+	/* dma 1 */
+	{ DBGBUS_SSPP1, 40, 0 },
+	{ DBGBUS_SSPP1, 40, 1 },
+	{ DBGBUS_SSPP1, 40, 2 },
+	{ DBGBUS_SSPP1, 40, 3 },
+	{ DBGBUS_SSPP1, 40, 4 },
+	{ DBGBUS_SSPP1, 40, 5 },
+	{ DBGBUS_SSPP1, 40, 6 },
+	{ DBGBUS_SSPP1, 40, 7 },
+
+	{ DBGBUS_SSPP1, 41, 0 },
+	{ DBGBUS_SSPP1, 41, 1 },
+	{ DBGBUS_SSPP1, 41, 2 },
+	{ DBGBUS_SSPP1, 41, 3 },
+	{ DBGBUS_SSPP1, 41, 4 },
+	{ DBGBUS_SSPP1, 41, 5 },
+	{ DBGBUS_SSPP1, 41, 6 },
+	{ DBGBUS_SSPP1, 41, 7 },
+
+	{ DBGBUS_SSPP1, 42, 0 },
+	{ DBGBUS_SSPP1, 42, 1 },
+	{ DBGBUS_SSPP1, 42, 2 },
+	{ DBGBUS_SSPP1, 42, 3 },
+	{ DBGBUS_SSPP1, 42, 4 },
+	{ DBGBUS_SSPP1, 42, 5 },
+	{ DBGBUS_SSPP1, 42, 6 },
+	{ DBGBUS_SSPP1, 42, 7 },
+
+	{ DBGBUS_SSPP1, 44, 0 },
+	{ DBGBUS_SSPP1, 44, 1 },
+	{ DBGBUS_SSPP1, 44, 2 },
+	{ DBGBUS_SSPP1, 44, 3 },
+	{ DBGBUS_SSPP1, 44, 4 },
+	{ DBGBUS_SSPP1, 44, 5 },
+	{ DBGBUS_SSPP1, 44, 6 },
+	{ DBGBUS_SSPP1, 44, 7 },
+
+	{ DBGBUS_SSPP1, 45, 0 },
+	{ DBGBUS_SSPP1, 45, 1 },
+	{ DBGBUS_SSPP1, 45, 2 },
+	{ DBGBUS_SSPP1, 45, 3 },
+	{ DBGBUS_SSPP1, 45, 4 },
+	{ DBGBUS_SSPP1, 45, 5 },
+	{ DBGBUS_SSPP1, 45, 6 },
+	{ DBGBUS_SSPP1, 45, 7 },
+
+	/* dspp */
+	{ DBGBUS_DSPP, 13, 0 },
+	{ DBGBUS_DSPP, 19, 0 },
+	{ DBGBUS_DSPP, 14, 0 },
+	{ DBGBUS_DSPP, 14, 1 },
+	{ DBGBUS_DSPP, 14, 3 },
+	{ DBGBUS_DSPP, 20, 0 },
+	{ DBGBUS_DSPP, 20, 1 },
+	{ DBGBUS_DSPP, 20, 3 },
+
+	/* ppb_0 */
+	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
+
+	/* ppb_1 */
+	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
+
+	/* lm_lut */
+	{ DBGBUS_DSPP, 109, 0 },
+	{ DBGBUS_DSPP, 105, 0 },
+	{ DBGBUS_DSPP, 103, 0 },
+
+	/* crossbar */
+	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
+
+	/* rotator */
+	{ DBGBUS_DSPP, 9, 0},
+
+	/* blend */
+	/* LM0 */
+	{ DBGBUS_DSPP, 63, 1},
+	{ DBGBUS_DSPP, 63, 2},
+	{ DBGBUS_DSPP, 63, 3},
+	{ DBGBUS_DSPP, 63, 4},
+	{ DBGBUS_DSPP, 63, 5},
+	{ DBGBUS_DSPP, 63, 6},
+	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 64, 1},
+	{ DBGBUS_DSPP, 64, 2},
+	{ DBGBUS_DSPP, 64, 3},
+	{ DBGBUS_DSPP, 64, 4},
+	{ DBGBUS_DSPP, 64, 5},
+	{ DBGBUS_DSPP, 64, 6},
+	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 65, 1},
+	{ DBGBUS_DSPP, 65, 2},
+	{ DBGBUS_DSPP, 65, 3},
+	{ DBGBUS_DSPP, 65, 4},
+	{ DBGBUS_DSPP, 65, 5},
+	{ DBGBUS_DSPP, 65, 6},
+	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 66, 1},
+	{ DBGBUS_DSPP, 66, 2},
+	{ DBGBUS_DSPP, 66, 3},
+	{ DBGBUS_DSPP, 66, 4},
+	{ DBGBUS_DSPP, 66, 5},
+	{ DBGBUS_DSPP, 66, 6},
+	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 67, 1},
+	{ DBGBUS_DSPP, 67, 2},
+	{ DBGBUS_DSPP, 67, 3},
+	{ DBGBUS_DSPP, 67, 4},
+	{ DBGBUS_DSPP, 67, 5},
+	{ DBGBUS_DSPP, 67, 6},
+	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 68, 1},
+	{ DBGBUS_DSPP, 68, 2},
+	{ DBGBUS_DSPP, 68, 3},
+	{ DBGBUS_DSPP, 68, 4},
+	{ DBGBUS_DSPP, 68, 5},
+	{ DBGBUS_DSPP, 68, 6},
+	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 69, 1},
+	{ DBGBUS_DSPP, 69, 2},
+	{ DBGBUS_DSPP, 69, 3},
+	{ DBGBUS_DSPP, 69, 4},
+	{ DBGBUS_DSPP, 69, 5},
+	{ DBGBUS_DSPP, 69, 6},
+	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 84, 1},
+	{ DBGBUS_DSPP, 84, 2},
+	{ DBGBUS_DSPP, 84, 3},
+	{ DBGBUS_DSPP, 84, 4},
+	{ DBGBUS_DSPP, 84, 5},
+	{ DBGBUS_DSPP, 84, 6},
+	{ DBGBUS_DSPP, 84, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 85, 1},
+	{ DBGBUS_DSPP, 85, 2},
+	{ DBGBUS_DSPP, 85, 3},
+	{ DBGBUS_DSPP, 85, 4},
+	{ DBGBUS_DSPP, 85, 5},
+	{ DBGBUS_DSPP, 85, 6},
+	{ DBGBUS_DSPP, 85, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 86, 1},
+	{ DBGBUS_DSPP, 86, 2},
+	{ DBGBUS_DSPP, 86, 3},
+	{ DBGBUS_DSPP, 86, 4},
+	{ DBGBUS_DSPP, 86, 5},
+	{ DBGBUS_DSPP, 86, 6},
+	{ DBGBUS_DSPP, 86, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 87, 1},
+	{ DBGBUS_DSPP, 87, 2},
+	{ DBGBUS_DSPP, 87, 3},
+	{ DBGBUS_DSPP, 87, 4},
+	{ DBGBUS_DSPP, 87, 5},
+	{ DBGBUS_DSPP, 87, 6},
+	{ DBGBUS_DSPP, 87, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM1 */
+	{ DBGBUS_DSPP, 70, 1},
+	{ DBGBUS_DSPP, 70, 2},
+	{ DBGBUS_DSPP, 70, 3},
+	{ DBGBUS_DSPP, 70, 4},
+	{ DBGBUS_DSPP, 70, 5},
+	{ DBGBUS_DSPP, 70, 6},
+	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 71, 1},
+	{ DBGBUS_DSPP, 71, 2},
+	{ DBGBUS_DSPP, 71, 3},
+	{ DBGBUS_DSPP, 71, 4},
+	{ DBGBUS_DSPP, 71, 5},
+	{ DBGBUS_DSPP, 71, 6},
+	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 72, 1},
+	{ DBGBUS_DSPP, 72, 2},
+	{ DBGBUS_DSPP, 72, 3},
+	{ DBGBUS_DSPP, 72, 4},
+	{ DBGBUS_DSPP, 72, 5},
+	{ DBGBUS_DSPP, 72, 6},
+	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 73, 1},
+	{ DBGBUS_DSPP, 73, 2},
+	{ DBGBUS_DSPP, 73, 3},
+	{ DBGBUS_DSPP, 73, 4},
+	{ DBGBUS_DSPP, 73, 5},
+	{ DBGBUS_DSPP, 73, 6},
+	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 74, 1},
+	{ DBGBUS_DSPP, 74, 2},
+	{ DBGBUS_DSPP, 74, 3},
+	{ DBGBUS_DSPP, 74, 4},
+	{ DBGBUS_DSPP, 74, 5},
+	{ DBGBUS_DSPP, 74, 6},
+	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 75, 1},
+	{ DBGBUS_DSPP, 75, 2},
+	{ DBGBUS_DSPP, 75, 3},
+	{ DBGBUS_DSPP, 75, 4},
+	{ DBGBUS_DSPP, 75, 5},
+	{ DBGBUS_DSPP, 75, 6},
+	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 76, 1},
+	{ DBGBUS_DSPP, 76, 2},
+	{ DBGBUS_DSPP, 76, 3},
+	{ DBGBUS_DSPP, 76, 4},
+	{ DBGBUS_DSPP, 76, 5},
+	{ DBGBUS_DSPP, 76, 6},
+	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 88, 1},
+	{ DBGBUS_DSPP, 88, 2},
+	{ DBGBUS_DSPP, 88, 3},
+	{ DBGBUS_DSPP, 88, 4},
+	{ DBGBUS_DSPP, 88, 5},
+	{ DBGBUS_DSPP, 88, 6},
+	{ DBGBUS_DSPP, 88, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 89, 1},
+	{ DBGBUS_DSPP, 89, 2},
+	{ DBGBUS_DSPP, 89, 3},
+	{ DBGBUS_DSPP, 89, 4},
+	{ DBGBUS_DSPP, 89, 5},
+	{ DBGBUS_DSPP, 89, 6},
+	{ DBGBUS_DSPP, 89, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 90, 1},
+	{ DBGBUS_DSPP, 90, 2},
+	{ DBGBUS_DSPP, 90, 3},
+	{ DBGBUS_DSPP, 90, 4},
+	{ DBGBUS_DSPP, 90, 5},
+	{ DBGBUS_DSPP, 90, 6},
+	{ DBGBUS_DSPP, 90, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 91, 1},
+	{ DBGBUS_DSPP, 91, 2},
+	{ DBGBUS_DSPP, 91, 3},
+	{ DBGBUS_DSPP, 91, 4},
+	{ DBGBUS_DSPP, 91, 5},
+	{ DBGBUS_DSPP, 91, 6},
+	{ DBGBUS_DSPP, 91, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM2 */
+	{ DBGBUS_DSPP, 77, 0},
+	{ DBGBUS_DSPP, 77, 1},
+	{ DBGBUS_DSPP, 77, 2},
+	{ DBGBUS_DSPP, 77, 3},
+	{ DBGBUS_DSPP, 77, 4},
+	{ DBGBUS_DSPP, 77, 5},
+	{ DBGBUS_DSPP, 77, 6},
+	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 78, 0},
+	{ DBGBUS_DSPP, 78, 1},
+	{ DBGBUS_DSPP, 78, 2},
+	{ DBGBUS_DSPP, 78, 3},
+	{ DBGBUS_DSPP, 78, 4},
+	{ DBGBUS_DSPP, 78, 5},
+	{ DBGBUS_DSPP, 78, 6},
+	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 79, 0},
+	{ DBGBUS_DSPP, 79, 1},
+	{ DBGBUS_DSPP, 79, 2},
+	{ DBGBUS_DSPP, 79, 3},
+	{ DBGBUS_DSPP, 79, 4},
+	{ DBGBUS_DSPP, 79, 5},
+	{ DBGBUS_DSPP, 79, 6},
+	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 80, 0},
+	{ DBGBUS_DSPP, 80, 1},
+	{ DBGBUS_DSPP, 80, 2},
+	{ DBGBUS_DSPP, 80, 3},
+	{ DBGBUS_DSPP, 80, 4},
+	{ DBGBUS_DSPP, 80, 5},
+	{ DBGBUS_DSPP, 80, 6},
+	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 81, 0},
+	{ DBGBUS_DSPP, 81, 1},
+	{ DBGBUS_DSPP, 81, 2},
+	{ DBGBUS_DSPP, 81, 3},
+	{ DBGBUS_DSPP, 81, 4},
+	{ DBGBUS_DSPP, 81, 5},
+	{ DBGBUS_DSPP, 81, 6},
+	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 82, 0},
+	{ DBGBUS_DSPP, 82, 1},
+	{ DBGBUS_DSPP, 82, 2},
+	{ DBGBUS_DSPP, 82, 3},
+	{ DBGBUS_DSPP, 82, 4},
+	{ DBGBUS_DSPP, 82, 5},
+	{ DBGBUS_DSPP, 82, 6},
+	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 83, 0},
+	{ DBGBUS_DSPP, 83, 1},
+	{ DBGBUS_DSPP, 83, 2},
+	{ DBGBUS_DSPP, 83, 3},
+	{ DBGBUS_DSPP, 83, 4},
+	{ DBGBUS_DSPP, 83, 5},
+	{ DBGBUS_DSPP, 83, 6},
+	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 92, 1},
+	{ DBGBUS_DSPP, 92, 2},
+	{ DBGBUS_DSPP, 92, 3},
+	{ DBGBUS_DSPP, 92, 4},
+	{ DBGBUS_DSPP, 92, 5},
+	{ DBGBUS_DSPP, 92, 6},
+	{ DBGBUS_DSPP, 92, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 93, 1},
+	{ DBGBUS_DSPP, 93, 2},
+	{ DBGBUS_DSPP, 93, 3},
+	{ DBGBUS_DSPP, 93, 4},
+	{ DBGBUS_DSPP, 93, 5},
+	{ DBGBUS_DSPP, 93, 6},
+	{ DBGBUS_DSPP, 93, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 94, 1},
+	{ DBGBUS_DSPP, 94, 2},
+	{ DBGBUS_DSPP, 94, 3},
+	{ DBGBUS_DSPP, 94, 4},
+	{ DBGBUS_DSPP, 94, 5},
+	{ DBGBUS_DSPP, 94, 6},
+	{ DBGBUS_DSPP, 94, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 95, 1},
+	{ DBGBUS_DSPP, 95, 2},
+	{ DBGBUS_DSPP, 95, 3},
+	{ DBGBUS_DSPP, 95, 4},
+	{ DBGBUS_DSPP, 95, 5},
+	{ DBGBUS_DSPP, 95, 6},
+	{ DBGBUS_DSPP, 95, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM5 */
+	{ DBGBUS_DSPP, 110, 1},
+	{ DBGBUS_DSPP, 110, 2},
+	{ DBGBUS_DSPP, 110, 3},
+	{ DBGBUS_DSPP, 110, 4},
+	{ DBGBUS_DSPP, 110, 5},
+	{ DBGBUS_DSPP, 110, 6},
+	{ DBGBUS_DSPP, 110, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 111, 1},
+	{ DBGBUS_DSPP, 111, 2},
+	{ DBGBUS_DSPP, 111, 3},
+	{ DBGBUS_DSPP, 111, 4},
+	{ DBGBUS_DSPP, 111, 5},
+	{ DBGBUS_DSPP, 111, 6},
+	{ DBGBUS_DSPP, 111, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 112, 1},
+	{ DBGBUS_DSPP, 112, 2},
+	{ DBGBUS_DSPP, 112, 3},
+	{ DBGBUS_DSPP, 112, 4},
+	{ DBGBUS_DSPP, 112, 5},
+	{ DBGBUS_DSPP, 112, 6},
+	{ DBGBUS_DSPP, 112, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 113, 1},
+	{ DBGBUS_DSPP, 113, 2},
+	{ DBGBUS_DSPP, 113, 3},
+	{ DBGBUS_DSPP, 113, 4},
+	{ DBGBUS_DSPP, 113, 5},
+	{ DBGBUS_DSPP, 113, 6},
+	{ DBGBUS_DSPP, 113, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 114, 1},
+	{ DBGBUS_DSPP, 114, 2},
+	{ DBGBUS_DSPP, 114, 3},
+	{ DBGBUS_DSPP, 114, 4},
+	{ DBGBUS_DSPP, 114, 5},
+	{ DBGBUS_DSPP, 114, 6},
+	{ DBGBUS_DSPP, 114, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 115, 1},
+	{ DBGBUS_DSPP, 115, 2},
+	{ DBGBUS_DSPP, 115, 3},
+	{ DBGBUS_DSPP, 115, 4},
+	{ DBGBUS_DSPP, 115, 5},
+	{ DBGBUS_DSPP, 115, 6},
+	{ DBGBUS_DSPP, 115, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 116, 1},
+	{ DBGBUS_DSPP, 116, 2},
+	{ DBGBUS_DSPP, 116, 3},
+	{ DBGBUS_DSPP, 116, 4},
+	{ DBGBUS_DSPP, 116, 5},
+	{ DBGBUS_DSPP, 116, 6},
+	{ DBGBUS_DSPP, 116, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 117, 1},
+	{ DBGBUS_DSPP, 117, 2},
+	{ DBGBUS_DSPP, 117, 3},
+	{ DBGBUS_DSPP, 117, 4},
+	{ DBGBUS_DSPP, 117, 5},
+	{ DBGBUS_DSPP, 117, 6},
+	{ DBGBUS_DSPP, 117, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 118, 1},
+	{ DBGBUS_DSPP, 118, 2},
+	{ DBGBUS_DSPP, 118, 3},
+	{ DBGBUS_DSPP, 118, 4},
+	{ DBGBUS_DSPP, 118, 5},
+	{ DBGBUS_DSPP, 118, 6},
+	{ DBGBUS_DSPP, 118, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 119, 1},
+	{ DBGBUS_DSPP, 119, 2},
+	{ DBGBUS_DSPP, 119, 3},
+	{ DBGBUS_DSPP, 119, 4},
+	{ DBGBUS_DSPP, 119, 5},
+	{ DBGBUS_DSPP, 119, 6},
+	{ DBGBUS_DSPP, 119, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 120, 1},
+	{ DBGBUS_DSPP, 120, 2},
+	{ DBGBUS_DSPP, 120, 3},
+	{ DBGBUS_DSPP, 120, 4},
+	{ DBGBUS_DSPP, 120, 5},
+	{ DBGBUS_DSPP, 120, 6},
+	{ DBGBUS_DSPP, 120, 7, _dpu_debug_bus_lm_dump },
+
+	/* csc */
+	{ DBGBUS_SSPP0, 7, 0},
+	{ DBGBUS_SSPP0, 7, 1},
+	{ DBGBUS_SSPP0, 27, 0},
+	{ DBGBUS_SSPP0, 27, 1},
+	{ DBGBUS_SSPP1, 7, 0},
+	{ DBGBUS_SSPP1, 7, 1},
+	{ DBGBUS_SSPP1, 27, 0},
+	{ DBGBUS_SSPP1, 27, 1},
+
+	/* pcc */
+	{ DBGBUS_SSPP0, 3,  3},
+	{ DBGBUS_SSPP0, 23, 3},
+	{ DBGBUS_SSPP0, 33, 3},
+	{ DBGBUS_SSPP0, 43, 3},
+	{ DBGBUS_SSPP1, 3,  3},
+	{ DBGBUS_SSPP1, 23, 3},
+	{ DBGBUS_SSPP1, 33, 3},
+	{ DBGBUS_SSPP1, 43, 3},
+
+	/* spa */
+	{ DBGBUS_SSPP0, 8,  0},
+	{ DBGBUS_SSPP0, 28, 0},
+	{ DBGBUS_SSPP1, 8,  0},
+	{ DBGBUS_SSPP1, 28, 0},
+	{ DBGBUS_DSPP, 13, 0},
+	{ DBGBUS_DSPP, 19, 0},
+
+	/* igc */
+	{ DBGBUS_SSPP0, 17, 0},
+	{ DBGBUS_SSPP0, 17, 1},
+	{ DBGBUS_SSPP0, 17, 3},
+	{ DBGBUS_SSPP0, 37, 0},
+	{ DBGBUS_SSPP0, 37, 1},
+	{ DBGBUS_SSPP0, 37, 3},
+	{ DBGBUS_SSPP0, 46, 0},
+	{ DBGBUS_SSPP0, 46, 1},
+	{ DBGBUS_SSPP0, 46, 3},
+
+	{ DBGBUS_SSPP1, 17, 0},
+	{ DBGBUS_SSPP1, 17, 1},
+	{ DBGBUS_SSPP1, 17, 3},
+	{ DBGBUS_SSPP1, 37, 0},
+	{ DBGBUS_SSPP1, 37, 1},
+	{ DBGBUS_SSPP1, 37, 3},
+	{ DBGBUS_SSPP1, 46, 0},
+	{ DBGBUS_SSPP1, 46, 1},
+	{ DBGBUS_SSPP1, 46, 3},
+
+	{ DBGBUS_DSPP, 14, 0},
+	{ DBGBUS_DSPP, 14, 1},
+	{ DBGBUS_DSPP, 14, 3},
+	{ DBGBUS_DSPP, 20, 0},
+	{ DBGBUS_DSPP, 20, 1},
+	{ DBGBUS_DSPP, 20, 3},
+
+	/* intf0-3 */
+	{ DBGBUS_PERIPH, 0, 0},
+	{ DBGBUS_PERIPH, 1, 0},
+	{ DBGBUS_PERIPH, 2, 0},
+	{ DBGBUS_PERIPH, 3, 0},
+
+	/* te counter wrapper */
+	{ DBGBUS_PERIPH, 60, 0},
+
+	/* dsc0 */
+	{ DBGBUS_PERIPH, 47, 0},
+	{ DBGBUS_PERIPH, 47, 1},
+	{ DBGBUS_PERIPH, 47, 2},
+	{ DBGBUS_PERIPH, 47, 3},
+	{ DBGBUS_PERIPH, 47, 4},
+	{ DBGBUS_PERIPH, 47, 5},
+	{ DBGBUS_PERIPH, 47, 6},
+	{ DBGBUS_PERIPH, 47, 7},
+
+	/* dsc1 */
+	{ DBGBUS_PERIPH, 48, 0},
+	{ DBGBUS_PERIPH, 48, 1},
+	{ DBGBUS_PERIPH, 48, 2},
+	{ DBGBUS_PERIPH, 48, 3},
+	{ DBGBUS_PERIPH, 48, 4},
+	{ DBGBUS_PERIPH, 48, 5},
+	{ DBGBUS_PERIPH, 48, 6},
+	{ DBGBUS_PERIPH, 48, 7},
+
+	/* dsc2 */
+	{ DBGBUS_PERIPH, 51, 0},
+	{ DBGBUS_PERIPH, 51, 1},
+	{ DBGBUS_PERIPH, 51, 2},
+	{ DBGBUS_PERIPH, 51, 3},
+	{ DBGBUS_PERIPH, 51, 4},
+	{ DBGBUS_PERIPH, 51, 5},
+	{ DBGBUS_PERIPH, 51, 6},
+	{ DBGBUS_PERIPH, 51, 7},
+
+	/* dsc3 */
+	{ DBGBUS_PERIPH, 52, 0},
+	{ DBGBUS_PERIPH, 52, 1},
+	{ DBGBUS_PERIPH, 52, 2},
+	{ DBGBUS_PERIPH, 52, 3},
+	{ DBGBUS_PERIPH, 52, 4},
+	{ DBGBUS_PERIPH, 52, 5},
+	{ DBGBUS_PERIPH, 52, 6},
+	{ DBGBUS_PERIPH, 52, 7},
+
+	/* tear-check */
+	{ DBGBUS_PERIPH, 63, 0 },
+	{ DBGBUS_PERIPH, 64, 0 },
+	{ DBGBUS_PERIPH, 65, 0 },
+	{ DBGBUS_PERIPH, 73, 0 },
+	{ DBGBUS_PERIPH, 74, 0 },
+
+	/* cdwn */
+	{ DBGBUS_PERIPH, 80, 0},
+	{ DBGBUS_PERIPH, 80, 1},
+	{ DBGBUS_PERIPH, 80, 2},
+
+	{ DBGBUS_PERIPH, 81, 0},
+	{ DBGBUS_PERIPH, 81, 1},
+	{ DBGBUS_PERIPH, 81, 2},
+
+	{ DBGBUS_PERIPH, 82, 0},
+	{ DBGBUS_PERIPH, 82, 1},
+	{ DBGBUS_PERIPH, 82, 2},
+	{ DBGBUS_PERIPH, 82, 3},
+	{ DBGBUS_PERIPH, 82, 4},
+	{ DBGBUS_PERIPH, 82, 5},
+	{ DBGBUS_PERIPH, 82, 6},
+	{ DBGBUS_PERIPH, 82, 7},
+
+	/* hdmi */
+	{ DBGBUS_PERIPH, 68, 0},
+	{ DBGBUS_PERIPH, 68, 1},
+	{ DBGBUS_PERIPH, 68, 2},
+	{ DBGBUS_PERIPH, 68, 3},
+	{ DBGBUS_PERIPH, 68, 4},
+	{ DBGBUS_PERIPH, 68, 5},
+
+	/* edp */
+	{ DBGBUS_PERIPH, 69, 0},
+	{ DBGBUS_PERIPH, 69, 1},
+	{ DBGBUS_PERIPH, 69, 2},
+	{ DBGBUS_PERIPH, 69, 3},
+	{ DBGBUS_PERIPH, 69, 4},
+	{ DBGBUS_PERIPH, 69, 5},
+
+	/* dsi0 */
+	{ DBGBUS_PERIPH, 70, 0},
+	{ DBGBUS_PERIPH, 70, 1},
+	{ DBGBUS_PERIPH, 70, 2},
+	{ DBGBUS_PERIPH, 70, 3},
+	{ DBGBUS_PERIPH, 70, 4},
+	{ DBGBUS_PERIPH, 70, 5},
+
+	/* dsi1 */
+	{ DBGBUS_PERIPH, 71, 0},
+	{ DBGBUS_PERIPH, 71, 1},
+	{ DBGBUS_PERIPH, 71, 2},
+	{ DBGBUS_PERIPH, 71, 3},
+	{ DBGBUS_PERIPH, 71, 4},
+	{ DBGBUS_PERIPH, 71, 5},
+};
+
+static struct vbif_debug_bus_entry vbif_dbg_bus_msm8998[] = {
+	{0x214, 0x21c, 16, 2, 0x0, 0xd},     /* arb clients */
+	{0x214, 0x21c, 16, 2, 0x80, 0xc0},   /* arb clients */
+	{0x214, 0x21c, 16, 2, 0x100, 0x140}, /* arb clients */
+	{0x214, 0x21c, 0, 16, 0x0, 0xf},     /* xin blocks - axi side */
+	{0x214, 0x21c, 0, 16, 0x80, 0xa4},   /* xin blocks - axi side */
+	{0x214, 0x21c, 0, 15, 0x100, 0x124}, /* xin blocks - axi side */
+	{0x21c, 0x214, 0, 14, 0, 0xc}, /* xin blocks - clock side */
+};
+
+/**
+ * _dpu_dbg_enable_power - use callback to turn power on for hw register access
+ * @enable: whether to turn power on or off
+ */
+static inline void _dpu_dbg_enable_power(int enable)
+{
+	if (enable)
+		pm_runtime_get_sync(dpu_dbg_base.dev);
+	else
+		pm_runtime_put_sync(dpu_dbg_base.dev);
+}
+
+static void _dpu_dbg_dump_dpu_dbg_bus(struct dpu_dbg_dpu_debug_bus *bus)
+{
+	bool in_log, in_mem;
+	u32 **dump_mem = NULL;
+	u32 *dump_addr = NULL;
+	u32 status = 0;
+	struct dpu_debug_bus_entry *head;
+	phys_addr_t phys = 0;
+	int list_size;
+	int i;
+	u32 offset;
+	void __iomem *mem_base = NULL;
+	struct dpu_dbg_reg_base *reg_base;
+
+	if (!bus || !bus->cmn.entries_size)
+		return;
+
+	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
+			reg_base_head)
+		if (strlen(reg_base->name) &&
+			!strcmp(reg_base->name, bus->cmn.name))
+			mem_base = reg_base->base + bus->top_blk_off;
+
+	if (!mem_base) {
+		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
+		return;
+	}
+
+	dump_mem = &bus->cmn.dumped_content;
+
+	/* will keep in memory 4 entries of 4 bytes each */
+	list_size = (bus->cmn.entries_size * 4 * 4);
+
+	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
+	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
+
+	if (!in_log && !in_mem)
+		return;
+
+	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
+			bus->cmn.name);
+
+	if (in_mem) {
+		if (!(*dump_mem))
+			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
+				list_size, &phys, GFP_KERNEL);
+
+		if (*dump_mem) {
+			dump_addr = *dump_mem;
+			dev_info(dpu_dbg_base.dev,
+				"%s: start_addr:0x%pK len:0x%x\n",
+				__func__, dump_addr, list_size);
+		} else {
+			in_mem = false;
+			pr_err("dump_mem: allocation fails\n");
+		}
+	}
+
+	_dpu_dbg_enable_power(true);
+	for (i = 0; i < bus->cmn.entries_size; i++) {
+		head = bus->entries + i;
+		writel_relaxed(TEST_MASK(head->block_id, head->test_id),
+				mem_base + head->wr_addr);
+		wmb(); /* make sure test bits were written */
+
+		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP) {
+			offset = DBGBUS_DSPP_STATUS;
+			/* keep DSPP test point enabled */
+			if (head->wr_addr != DBGBUS_DSPP)
+				writel_relaxed(0xF, mem_base + DBGBUS_DSPP);
+		} else {
+			offset = head->wr_addr + 0x4;
+		}
+
+		status = readl_relaxed(mem_base + offset);
+
+		if (in_log)
+			dev_info(dpu_dbg_base.dev,
+					"waddr=0x%x blk=%d tst=%d val=0x%x\n",
+					head->wr_addr, head->block_id,
+					head->test_id, status);
+
+		if (dump_addr && in_mem) {
+			dump_addr[i*4]     = head->wr_addr;
+			dump_addr[i*4 + 1] = head->block_id;
+			dump_addr[i*4 + 2] = head->test_id;
+			dump_addr[i*4 + 3] = status;
+		}
+
+		if (head->analyzer)
+			head->analyzer(mem_base, head, status);
+
+		/* Disable debug bus once we are done */
+		writel_relaxed(0, mem_base + head->wr_addr);
+		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP &&
+						head->wr_addr != DBGBUS_DSPP)
+			writel_relaxed(0x0, mem_base + DBGBUS_DSPP);
+	}
+	_dpu_dbg_enable_power(false);
+
+	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
+			bus->cmn.name);
+}
+
+static void _dpu_dbg_dump_vbif_debug_bus_entry(
+		struct vbif_debug_bus_entry *head, void __iomem *mem_base,
+		u32 *dump_addr, bool in_log)
+{
+	int i, j;
+	u32 val;
+
+	if (!dump_addr && !in_log)
+		return;
+
+	for (i = 0; i < head->block_cnt; i++) {
+		writel_relaxed(1 << (i + head->bit_offset),
+				mem_base + head->block_bus_addr);
+		/* make sure that current bus blcok enable */
+		wmb();
+		for (j = head->test_pnt_start; j < head->test_pnt_cnt; j++) {
+			writel_relaxed(j, mem_base + head->block_bus_addr + 4);
+			/* make sure that test point is enabled */
+			wmb();
+			val = readl_relaxed(mem_base + MMSS_VBIF_TEST_BUS_OUT);
+			if (dump_addr) {
+				*dump_addr++ = head->block_bus_addr;
+				*dump_addr++ = i;
+				*dump_addr++ = j;
+				*dump_addr++ = val;
+			}
+			if (in_log)
+				dev_info(dpu_dbg_base.dev,
+					"testpoint:%x arb/xin id=%d index=%d val=0x%x\n",
+					head->block_bus_addr, i, j, val);
+		}
+	}
+}
+
+static void _dpu_dbg_dump_vbif_dbg_bus(struct dpu_dbg_vbif_debug_bus *bus)
+{
+	bool in_log, in_mem;
+	u32 **dump_mem = NULL;
+	u32 *dump_addr = NULL;
+	u32 value, d0, d1;
+	unsigned long reg, reg1, reg2;
+	struct vbif_debug_bus_entry *head;
+	phys_addr_t phys = 0;
+	int i, list_size = 0;
+	void __iomem *mem_base = NULL;
+	struct vbif_debug_bus_entry *dbg_bus;
+	u32 bus_size;
+	struct dpu_dbg_reg_base *reg_base;
+
+	if (!bus || !bus->cmn.entries_size)
+		return;
+
+	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
+			reg_base_head)
+		if (strlen(reg_base->name) &&
+			!strcmp(reg_base->name, bus->cmn.name))
+			mem_base = reg_base->base;
+
+	if (!mem_base) {
+		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
+		return;
+	}
+
+	dbg_bus = bus->entries;
+	bus_size = bus->cmn.entries_size;
+	list_size = bus->cmn.entries_size;
+	dump_mem = &bus->cmn.dumped_content;
+
+	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
+			bus->cmn.name);
+
+	if (!dump_mem || !dbg_bus || !bus_size || !list_size)
+		return;
+
+	/* allocate memory for each test point */
+	for (i = 0; i < bus_size; i++) {
+		head = dbg_bus + i;
+		list_size += (head->block_cnt * head->test_pnt_cnt);
+	}
+
+	/* 4 bytes * 4 entries for each test point*/
+	list_size *= 16;
+
+	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
+	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
+
+	if (!in_log && !in_mem)
+		return;
+
+	if (in_mem) {
+		if (!(*dump_mem))
+			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
+				list_size, &phys, GFP_KERNEL);
+
+		if (*dump_mem) {
+			dump_addr = *dump_mem;
+			dev_info(dpu_dbg_base.dev,
+				"%s: start_addr:0x%pK len:0x%x\n",
+				__func__, dump_addr, list_size);
+		} else {
+			in_mem = false;
+			pr_err("dump_mem: allocation fails\n");
+		}
+	}
+
+	_dpu_dbg_enable_power(true);
+
+	value = readl_relaxed(mem_base + MMSS_VBIF_CLKON);
+	writel_relaxed(value | BIT(1), mem_base + MMSS_VBIF_CLKON);
+
+	/* make sure that vbif core is on */
+	wmb();
+
+	/**
+	 * Extract VBIF error info based on XIN halt and error status.
+	 * If the XIN client is not in HALT state, or an error is detected,
+	 * then retrieve the VBIF error info for it.
+	 */
+	reg = readl_relaxed(mem_base + MMSS_VBIF_XIN_HALT_CTRL1);
+	reg1 = readl_relaxed(mem_base + MMSS_VBIF_PND_ERR);
+	reg2 = readl_relaxed(mem_base + MMSS_VBIF_SRC_ERR);
+	dev_err(dpu_dbg_base.dev,
+			"XIN HALT:0x%lX, PND ERR:0x%lX, SRC ERR:0x%lX\n",
+			reg, reg1, reg2);
+	reg >>= 16;
+	reg &= ~(reg1 | reg2);
+	for (i = 0; i < MMSS_VBIF_CLIENT_NUM; i++) {
+		if (!test_bit(0, &reg)) {
+			writel_relaxed(i, mem_base + MMSS_VBIF_ERR_INFO);
+			/* make sure reg write goes through */
+			wmb();
+
+			d0 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO);
+			d1 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO_1);
+
+			dev_err(dpu_dbg_base.dev,
+					"Client:%d, errinfo=0x%X, errinfo1=0x%X\n",
+					i, d0, d1);
+		}
+		reg >>= 1;
+	}
+
+	for (i = 0; i < bus_size; i++) {
+		head = dbg_bus + i;
+
+		writel_relaxed(0, mem_base + head->disable_bus_addr);
+		writel_relaxed(BIT(0), mem_base + MMSS_VBIF_TEST_BUS_OUT_CTRL);
+		/* make sure that other bus is off */
+		wmb();
+
+		_dpu_dbg_dump_vbif_debug_bus_entry(head, mem_base, dump_addr,
+				in_log);
+		if (dump_addr)
+			dump_addr += (head->block_cnt * head->test_pnt_cnt * 4);
+	}
+
+	_dpu_dbg_enable_power(false);
+
+	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
+			bus->cmn.name);
+}
+
+/**
+ * _dpu_dump_array - dump array of register bases
+ * @name: string indicating origin of dump
+ * @dump_dbgbus_dpu: whether to dump the dpu debug bus
+ * @dump_dbgbus_vbif_rt: whether to dump the vbif rt debug bus
+ */
+static void _dpu_dump_array(const char *name, bool dump_dbgbus_dpu,
+			    bool dump_dbgbus_vbif_rt)
+{
+	if (dump_dbgbus_dpu)
+		_dpu_dbg_dump_dpu_dbg_bus(&dpu_dbg_base.dbgbus_dpu);
+
+	if (dump_dbgbus_vbif_rt)
+		_dpu_dbg_dump_vbif_dbg_bus(&dpu_dbg_base.dbgbus_vbif_rt);
+}
+
+/**
+ * _dpu_dump_work - deferred dump work function
+ * @work: work structure
+ */
+static void _dpu_dump_work(struct work_struct *work)
+{
+	_dpu_dump_array("dpudump_workitem",
+		dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work,
+		dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work);
+}
+
+void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
+		  bool dump_dbgbus_vbif_rt)
+{
+	if (queue_work && work_pending(&dpu_dbg_base.dump_work))
+		return;
+
+	if (!queue_work) {
+		_dpu_dump_array(name, dump_dbgbus_dpu, dump_dbgbus_vbif_rt);
+		return;
+	}
+
+	/* schedule work to dump later */
+	dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work = dump_dbgbus_dpu;
+	dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work =
+			dump_dbgbus_vbif_rt;
+	schedule_work(&dpu_dbg_base.dump_work);
+}
+
+/*
+ * dpu_dbg_debugfs_open - debugfs open handler for debug dump
+ * @inode: debugfs inode
+ * @file: file handle
+ */
+static int dpu_dbg_debugfs_open(struct inode *inode, struct file *file)
+{
+	/* non-seekable */
+	file->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+/**
+ * dpu_dbg_dump_write - debugfs write handler for debug dump
+ * @file: file handler
+ * @user_buf: user buffer content from debugfs
+ * @count: size of user buffer
+ * @ppos: position offset of user buffer
+ */
+static ssize_t dpu_dbg_dump_write(struct file *file,
+	const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	_dpu_dump_array("dump_debugfs", true, true);
+	return count;
+}
+
+static const struct file_operations dpu_dbg_dump_fops = {
+	.open = dpu_dbg_debugfs_open,
+	.write = dpu_dbg_dump_write,
+};
+
+int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
+{
+	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
+	char debug_name[80] = "";
+
+	if (!debugfs_root)
+		return -EINVAL;
+
+	debugfs_create_file("dump", 0600, debugfs_root, NULL,
+			&dpu_dbg_dump_fops);
+
+	if (dbg->dbgbus_dpu.entries) {
+		dbg->dbgbus_dpu.cmn.name = DBGBUS_NAME_DPU;
+		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
+				dbg->dbgbus_dpu.cmn.name);
+		dbg->dbgbus_dpu.cmn.enable_mask = DEFAULT_DBGBUS_DPU;
+		debugfs_create_u32(debug_name, 0600, debugfs_root,
+				&dbg->dbgbus_dpu.cmn.enable_mask);
+	}
+
+	if (dbg->dbgbus_vbif_rt.entries) {
+		dbg->dbgbus_vbif_rt.cmn.name = DBGBUS_NAME_VBIF_RT;
+		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
+				dbg->dbgbus_vbif_rt.cmn.name);
+		dbg->dbgbus_vbif_rt.cmn.enable_mask = DEFAULT_DBGBUS_VBIFRT;
+		debugfs_create_u32(debug_name, 0600, debugfs_root,
+				&dbg->dbgbus_vbif_rt.cmn.enable_mask);
+	}
+
+	return 0;
+}
+
+static void _dpu_dbg_debugfs_destroy(void)
+{
+}
+
+void dpu_dbg_init_dbg_buses(u32 hwversion)
+{
+	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
+
+	memset(&dbg->dbgbus_dpu, 0, sizeof(dbg->dbgbus_dpu));
+	memset(&dbg->dbgbus_vbif_rt, 0, sizeof(dbg->dbgbus_vbif_rt));
+
+	if (IS_MSM8998_TARGET(hwversion)) {
+		dbg->dbgbus_dpu.entries = dbg_bus_dpu_8998;
+		dbg->dbgbus_dpu.cmn.entries_size = ARRAY_SIZE(dbg_bus_dpu_8998);
+		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
+
+		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
+		dbg->dbgbus_vbif_rt.cmn.entries_size =
+				ARRAY_SIZE(vbif_dbg_bus_msm8998);
+	} else if (IS_SDM845_TARGET(hwversion) || IS_SDM670_TARGET(hwversion)) {
+		dbg->dbgbus_dpu.entries = dbg_bus_dpu_sdm845;
+		dbg->dbgbus_dpu.cmn.entries_size =
+				ARRAY_SIZE(dbg_bus_dpu_sdm845);
+		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
+
+		/* vbif is unchanged vs 8998 */
+		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
+		dbg->dbgbus_vbif_rt.cmn.entries_size =
+				ARRAY_SIZE(vbif_dbg_bus_msm8998);
+	} else {
+		pr_err("unsupported chipset id %X\n", hwversion);
+	}
+}
+
+int dpu_dbg_init(struct device *dev)
+{
+	if (!dev) {
+		pr_err("invalid params\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&dpu_dbg_base.reg_base_list);
+	dpu_dbg_base.dev = dev;
+
+	INIT_WORK(&dpu_dbg_base.dump_work, _dpu_dump_work);
+
+	return 0;
+}
+
+/**
+ * dpu_dbg_destroy - destroy dpu debug facilities
+ */
+void dpu_dbg_destroy(void)
+{
+	_dpu_dbg_debugfs_destroy();
+}
+
+void dpu_dbg_set_dpu_top_offset(u32 blk_off)
+{
+	dpu_dbg_base.dbgbus_dpu.top_blk_off = blk_off;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
new file mode 100644
index 000000000000..1e6fa945f98b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
@@ -0,0 +1,103 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef DPU_DBG_H_
+#define DPU_DBG_H_
+
+#include <stdarg.h>
+#include <linux/debugfs.h>
+#include <linux/list.h>
+
+enum dpu_dbg_dump_flag {
+	DPU_DBG_DUMP_IN_LOG = BIT(0),
+	DPU_DBG_DUMP_IN_MEM = BIT(1),
+};
+
+#if defined(CONFIG_DEBUG_FS)
+
+/**
+ * dpu_dbg_init_dbg_buses - initialize debug bus dumping support for the chipset
+ * @hwversion:		Chipset revision
+ */
+void dpu_dbg_init_dbg_buses(u32 hwversion);
+
+/**
+ * dpu_dbg_init - initialize global dpu debug facilities: regdump
+ * @dev:		device handle
+ * Returns:		0 or -ERROR
+ */
+int dpu_dbg_init(struct device *dev);
+
+/**
+ * dpu_dbg_debugfs_register - register entries at the given debugfs dir
+ * @debugfs_root:	debugfs root in which to create dpu debug entries
+ * Returns:	0 or -ERROR
+ */
+int dpu_dbg_debugfs_register(struct dentry *debugfs_root);
+
+/**
+ * dpu_dbg_destroy - destroy the global dpu debug facilities
+ * Returns:	none
+ */
+void dpu_dbg_destroy(void);
+
+/**
+ * dpu_dbg_dump - trigger dumping of all dpu_dbg facilities
+ * @queue_work:	  whether to queue the dumping work to the work_struct
+ * @name:	  string indicating origin of dump
+ * @dump_dbgbus:  dump the dpu debug bus
+ * @dump_vbif_rt: dump the vbif rt bus
+ * Returns:	none
+ */
+void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
+		  bool dump_dbgbus_vbif_rt);
+
+/**
+ * dpu_dbg_set_dpu_top_offset - set the target specific offset from mdss base
+ *	address of the top registers. Used for accessing debug bus controls.
+ * @blk_off: offset from mdss base of the top block
+ */
+void dpu_dbg_set_dpu_top_offset(u32 blk_off);
+
+#else
+
+static inline void dpu_dbg_init_dbg_buses(u32 hwversion)
+{
+}
+
+static inline int dpu_dbg_init(struct device *dev)
+{
+	return 0;
+}
+
+static inline int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
+{
+	return 0;
+}
+
+static inline void dpu_dbg_destroy(void)
+{
+}
+
+static inline void dpu_dbg_dump(bool queue_work, const char *name,
+				bool dump_dbgbus_dpu, bool dump_dbgbus_vbif_rt)
+{
+}
+
+static inline void dpu_dbg_set_dpu_top_offset(u32 blk_off)
+{
+}
+
+#endif /* defined(CONFIG_DEBUG_FS) */
+
+
+#endif /* DPU_DBG_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
new file mode 100644
index 000000000000..0bd3eda93e22
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -0,0 +1,2498 @@
+/*
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_formats.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_crtc.h"
+#include "dpu_trace.h"
+#include "dpu_core_irq.h"
+
+#define DPU_DEBUG_ENC(e, fmt, ...) DPU_DEBUG("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_DEBUG_PHYS(p, fmt, ...) DPU_DEBUG("enc%d intf%d pp%d " fmt,\
+		(p) ? (p)->parent->base.id : -1, \
+		(p) ? (p)->intf_idx - INTF_0 : -1, \
+		(p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \
+		##__VA_ARGS__)
+
+#define DPU_ERROR_PHYS(p, fmt, ...) DPU_ERROR("enc%d intf%d pp%d " fmt,\
+		(p) ? (p)->parent->base.id : -1, \
+		(p) ? (p)->intf_idx - INTF_0 : -1, \
+		(p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \
+		##__VA_ARGS__)
+
+/*
+ * Two to anticipate panels that can do cmd/vid dynamic switching
+ * plan is to create all possible physical encoder types, and switch between
+ * them at runtime
+ */
+#define NUM_PHYS_ENCODER_TYPES 2
+
+#define MAX_PHYS_ENCODERS_PER_VIRTUAL \
+	(MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES)
+
+#define MAX_CHANNELS_PER_ENC 2
+
+#define MISR_BUFF_SIZE			256
+
+#define IDLE_SHORT_TIMEOUT	1
+
+#define MAX_VDISPLAY_SPLIT 1080
+
+/**
+ * enum dpu_enc_rc_events - events for resource control state machine
+ * @DPU_ENC_RC_EVENT_KICKOFF:
+ *	This event happens at NORMAL priority.
+ *	Event that signals the start of the transfer. When this event is
+ *	received, enable MDP/DSI core clocks. Regardless of the previous
+ *	state, the resource should be in ON state at the end of this event.
+ * @DPU_ENC_RC_EVENT_FRAME_DONE:
+ *	This event happens at INTERRUPT level.
+ *	Event signals the end of the data transfer after the PP FRAME_DONE
+ *	event. At the end of this event, a delayed work is scheduled to go to
+ *	IDLE_PC state after IDLE_TIMEOUT time.
+ * @DPU_ENC_RC_EVENT_PRE_STOP:
+ *	This event happens at NORMAL priority.
+ *	This event, when received during the ON state, leave the RC STATE
+ *	in the PRE_OFF state. It should be followed by the STOP event as
+ *	part of encoder disable.
+ *	If received during IDLE or OFF states, it will do nothing.
+ * @DPU_ENC_RC_EVENT_STOP:
+ *	This event happens at NORMAL priority.
+ *	When this event is received, disable all the MDP/DSI core clocks, and
+ *	disable IRQs. It should be called from the PRE_OFF or IDLE states.
+ *	IDLE is expected when IDLE_PC has run, and PRE_OFF did nothing.
+ *	PRE_OFF is expected when PRE_STOP was executed during the ON state.
+ *	Resource state should be in OFF at the end of the event.
+ * @DPU_ENC_RC_EVENT_ENTER_IDLE:
+ *	This event happens at NORMAL priority from a work item.
+ *	Event signals that there were no frame updates for IDLE_TIMEOUT time.
+ *	This would disable MDP/DSI core clocks and change the resource state
+ *	to IDLE.
+ */
+enum dpu_enc_rc_events {
+	DPU_ENC_RC_EVENT_KICKOFF = 1,
+	DPU_ENC_RC_EVENT_FRAME_DONE,
+	DPU_ENC_RC_EVENT_PRE_STOP,
+	DPU_ENC_RC_EVENT_STOP,
+	DPU_ENC_RC_EVENT_ENTER_IDLE
+};
+
+/*
+ * enum dpu_enc_rc_states - states that the resource control maintains
+ * @DPU_ENC_RC_STATE_OFF: Resource is in OFF state
+ * @DPU_ENC_RC_STATE_PRE_OFF: Resource is transitioning to OFF state
+ * @DPU_ENC_RC_STATE_ON: Resource is in ON state
+ * @DPU_ENC_RC_STATE_MODESET: Resource is in modeset state
+ * @DPU_ENC_RC_STATE_IDLE: Resource is in IDLE state
+ */
+enum dpu_enc_rc_states {
+	DPU_ENC_RC_STATE_OFF,
+	DPU_ENC_RC_STATE_PRE_OFF,
+	DPU_ENC_RC_STATE_ON,
+	DPU_ENC_RC_STATE_IDLE
+};
+
+/**
+ * struct dpu_encoder_virt - virtual encoder. Container of one or more physical
+ *	encoders. Virtual encoder manages one "logical" display. Physical
+ *	encoders manage one intf block, tied to a specific panel/sub-panel.
+ *	Virtual encoder defers as much as possible to the physical encoders.
+ *	Virtual encoder registers itself with the DRM Framework as the encoder.
+ * @base:		drm_encoder base class for registration with DRM
+ * @enc_spin_lock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @bus_scaling_client:	Client handle to the bus scaling interface
+ * @num_phys_encs:	Actual number of physical encoders contained.
+ * @phys_encs:		Container of physical encoders managed.
+ * @cur_master:		Pointer to the current master in this mode. Optimization
+ *			Only valid after enable. Cleared as disable.
+ * @hw_pp		Handle to the pingpong blocks used for the display. No.
+ *			pingpong blocks can be different than num_phys_encs.
+ * @intfs_swapped	Whether or not the phys_enc interfaces have been swapped
+ *			for partial update right-only cases, such as pingpong
+ *			split where virtual pingpong does not generate IRQs
+ * @crtc_vblank_cb:	Callback into the upper layer / CRTC for
+ *			notification of the VBLANK
+ * @crtc_vblank_cb_data:	Data from upper layer for VBLANK notification
+ * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
+ *				all CTL paths
+ * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
+ * @debugfs_root:		Debug file system root file node
+ * @enc_lock:			Lock around physical encoder create/destroy and
+				access.
+ * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
+ *				busy processing current command.
+ *				Bit0 = phys_encs[0] etc.
+ * @crtc_frame_event_cb:	callback handler for frame event
+ * @crtc_frame_event_cb_data:	callback handler private data
+ * @frame_done_timeout:		frame done timeout in Hz
+ * @frame_done_timer:		watchdog timer for frame done event
+ * @vsync_event_timer:		vsync timer
+ * @disp_info:			local copy of msm_display_info struct
+ * @misr_enable:		misr enable/disable status
+ * @misr_frame_count:		misr frame count before start capturing the data
+ * @idle_pc_supported:		indicate if idle power collaps is supported
+ * @rc_lock:			resource control mutex lock to protect
+ *				virt encoder over various state changes
+ * @rc_state:			resource controller state
+ * @delayed_off_work:		delayed worker to schedule disabling of
+ *				clks and resources after IDLE_TIMEOUT time.
+ * @vsync_event_work:		worker to handle vsync event for autorefresh
+ * @topology:                   topology of the display
+ * @mode_set_complete:          flag to indicate modeset completion
+ * @idle_timeout:		idle timeout duration in milliseconds
+ */
+struct dpu_encoder_virt {
+	struct drm_encoder base;
+	spinlock_t enc_spinlock;
+	uint32_t bus_scaling_client;
+
+	uint32_t display_num_of_h_tiles;
+
+	unsigned int num_phys_encs;
+	struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL];
+	struct dpu_encoder_phys *cur_master;
+	struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC];
+
+	bool intfs_swapped;
+
+	void (*crtc_vblank_cb)(void *);
+	void *crtc_vblank_cb_data;
+
+	struct dentry *debugfs_root;
+	struct mutex enc_lock;
+	DECLARE_BITMAP(frame_busy_mask, MAX_PHYS_ENCODERS_PER_VIRTUAL);
+	void (*crtc_frame_event_cb)(void *, u32 event);
+	void *crtc_frame_event_cb_data;
+
+	atomic_t frame_done_timeout;
+	struct timer_list frame_done_timer;
+	struct timer_list vsync_event_timer;
+
+	struct msm_display_info disp_info;
+	bool misr_enable;
+	u32 misr_frame_count;
+
+	bool idle_pc_supported;
+	struct mutex rc_lock;
+	enum dpu_enc_rc_states rc_state;
+	struct kthread_delayed_work delayed_off_work;
+	struct kthread_work vsync_event_work;
+	struct msm_display_topology topology;
+	bool mode_set_complete;
+
+	u32 idle_timeout;
+};
+
+#define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base)
+static inline int _dpu_encoder_power_enable(struct dpu_encoder_virt *dpu_enc,
+								bool enable)
+{
+	struct drm_encoder *drm_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu enc\n");
+		return -EINVAL;
+	}
+
+	drm_enc = &dpu_enc->base;
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("drm device invalid\n");
+		return -EINVAL;
+	}
+
+	priv = drm_enc->dev->dev_private;
+	if (!priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	if (enable)
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	else
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	DRM_ERROR("irq timeout id=%u, intf=%d, pp=%d, intr=%d\n",
+		  DRMID(phys_enc->parent), phys_enc->intf_idx - INTF_0,
+		  phys_enc->hw_pp->idx - PINGPONG_0, intr_idx);
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_ERROR);
+}
+
+static int dpu_encoder_helper_wait_event_timeout(int32_t drm_id,
+		int32_t hw_id, struct dpu_encoder_wait_info *info);
+
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx,
+		struct dpu_encoder_wait_info *wait_info)
+{
+	struct dpu_encoder_irq *irq;
+	u32 irq_status;
+	int ret;
+
+	if (!phys_enc || !wait_info || intr_idx >= INTR_IDX_MAX) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	/* note: do master / slave checking outside */
+
+	/* return EWOULDBLOCK since we know the wait isn't necessary */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DRM_ERROR("encoder is disabled id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		return -EWOULDBLOCK;
+	}
+
+	if (irq->irq_idx < 0) {
+		DRM_DEBUG_KMS("skip irq wait id=%u, intr=%d, hw=%d, irq=%s",
+			      DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			      irq->name);
+		return 0;
+	}
+
+	DRM_DEBUG_KMS("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, pending_cnt=%d",
+		      DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+		      irq->irq_idx, phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(wait_info->atomic_cnt));
+
+	ret = dpu_encoder_helper_wait_event_timeout(
+			DRMID(phys_enc->parent),
+			irq->hw_idx,
+			wait_info);
+
+	if (ret <= 0) {
+		irq_status = dpu_core_irq_read(phys_enc->dpu_kms,
+				irq->irq_idx, true);
+		if (irq_status) {
+			unsigned long flags;
+
+			DRM_DEBUG_KMS("irq not triggered id=%u, intr=%d, "
+				      "hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+				      DRMID(phys_enc->parent), intr_idx,
+				      irq->hw_idx, irq->irq_idx,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+			local_irq_save(flags);
+			irq->cb.func(phys_enc, irq->irq_idx);
+			local_irq_restore(flags);
+			ret = 0;
+		} else {
+			ret = -ETIMEDOUT;
+			DRM_DEBUG_KMS("irq timeout id=%u, intr=%d, "
+				      "hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+				      DRMID(phys_enc->parent), intr_idx,
+				      irq->hw_idx, irq->irq_idx,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+		}
+	} else {
+		ret = 0;
+		trace_dpu_enc_irq_wait_success(DRMID(phys_enc->parent),
+			intr_idx, irq->hw_idx, irq->irq_idx,
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(wait_info->atomic_cnt));
+	}
+
+	return ret;
+}
+
+int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	struct dpu_encoder_irq *irq;
+	int ret = 0;
+
+	if (!phys_enc || intr_idx >= INTR_IDX_MAX) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	if (irq->irq_idx >= 0) {
+		DPU_DEBUG_PHYS(phys_enc,
+				"skipping already registered irq %s type %d\n",
+				irq->name, irq->intr_type);
+		return 0;
+	}
+
+	irq->irq_idx = dpu_core_irq_idx_lookup(phys_enc->dpu_kms,
+			irq->intr_type, irq->hw_idx);
+	if (irq->irq_idx < 0) {
+		DPU_ERROR_PHYS(phys_enc,
+			"failed to lookup IRQ index for %s type:%d\n",
+			irq->name, irq->intr_type);
+		return -EINVAL;
+	}
+
+	ret = dpu_core_irq_register_callback(phys_enc->dpu_kms, irq->irq_idx,
+			&irq->cb);
+	if (ret) {
+		DPU_ERROR_PHYS(phys_enc,
+			"failed to register IRQ callback for %s\n",
+			irq->name);
+		irq->irq_idx = -EINVAL;
+		return ret;
+	}
+
+	ret = dpu_core_irq_enable(phys_enc->dpu_kms, &irq->irq_idx, 1);
+	if (ret) {
+		DRM_ERROR("enable failed id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				irq->irq_idx, &irq->cb);
+		irq->irq_idx = -EINVAL;
+		return ret;
+	}
+
+	trace_dpu_enc_irq_register_success(DRMID(phys_enc->parent), intr_idx,
+				irq->hw_idx, irq->irq_idx);
+
+	return ret;
+}
+
+int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	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 */
+	if (irq->irq_idx < 0) {
+		DRM_ERROR("duplicate unregister id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		return 0;
+	}
+
+	ret = dpu_core_irq_disable(phys_enc->dpu_kms, &irq->irq_idx, 1);
+	if (ret) {
+		DRM_ERROR("diable failed id=%u, intr=%d, hw=%d, irq=%d ret=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx, ret);
+	}
+
+	ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms, irq->irq_idx,
+			&irq->cb);
+	if (ret) {
+		DRM_ERROR("unreg cb fail id=%u, intr=%d, hw=%d, irq=%d ret=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx, ret);
+	}
+
+	trace_dpu_enc_irq_unregister_success(DRMID(phys_enc->parent), intr_idx,
+					     irq->hw_idx, irq->irq_idx);
+
+	irq->irq_idx = -EINVAL;
+
+	return 0;
+}
+
+void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!hw_res || !drm_enc || !conn_state) {
+		DPU_ERROR("invalid argument(s), drm_enc %d, res %d, state %d\n",
+				drm_enc != 0, hw_res != 0, conn_state != 0);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/* Query resources used by phys encs, expected to be without overlap */
+	memset(hw_res, 0, sizeof(*hw_res));
+	hw_res->display_num_of_h_tiles = dpu_enc->display_num_of_h_tiles;
+
+	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)
+			phys->ops.get_hw_resources(phys, hw_res, conn_state);
+	}
+}
+
+static void dpu_encoder_destroy(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	mutex_lock(&dpu_enc->enc_lock);
+
+	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) {
+			phys->ops.destroy(phys);
+			--dpu_enc->num_phys_encs;
+			dpu_enc->phys_encs[i] = NULL;
+		}
+	}
+
+	if (dpu_enc->num_phys_encs)
+		DPU_ERROR_ENC(dpu_enc, "expected 0 num_phys_encs not %d\n",
+				dpu_enc->num_phys_encs);
+	dpu_enc->num_phys_encs = 0;
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	drm_encoder_cleanup(drm_enc);
+	mutex_destroy(&dpu_enc->enc_lock);
+
+	kfree(dpu_enc);
+}
+
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct split_pipe_cfg cfg = { 0 };
+	struct dpu_hw_mdp *hw_mdptop;
+	struct msm_display_info *disp_info;
+
+	if (!phys_enc || !phys_enc->hw_mdptop || !phys_enc->parent) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	hw_mdptop = phys_enc->hw_mdptop;
+	disp_info = &dpu_enc->disp_info;
+
+	if (disp_info->intf_type != DRM_MODE_CONNECTOR_DSI)
+		return;
+
+	/**
+	 * disable split modes since encoder will be operating in as the only
+	 * encoder, either for the entire use case in the case of, for example,
+	 * single DSI, or for this frame in the case of left/right only partial
+	 * update.
+	 */
+	if (phys_enc->split_role == ENC_ROLE_SOLO) {
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+		return;
+	}
+
+	cfg.en = true;
+	cfg.mode = phys_enc->intf_mode;
+	cfg.intf = interface;
+
+	if (cfg.en && phys_enc->ops.needs_single_flush &&
+			phys_enc->ops.needs_single_flush(phys_enc))
+		cfg.split_flush_en = true;
+
+	if (phys_enc->split_role == ENC_ROLE_MASTER) {
+		DPU_DEBUG_ENC(dpu_enc, "enable %d\n", cfg.en);
+
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+	}
+}
+
+static void _dpu_encoder_adjust_mode(struct drm_connector *connector,
+		struct drm_display_mode *adj_mode)
+{
+	struct drm_display_mode *cur_mode;
+
+	if (!connector || !adj_mode)
+		return;
+
+	list_for_each_entry(cur_mode, &connector->modes, head) {
+		if (cur_mode->vdisplay == adj_mode->vdisplay &&
+			cur_mode->hdisplay == adj_mode->hdisplay &&
+			cur_mode->vrefresh == adj_mode->vrefresh) {
+			adj_mode->private = cur_mode->private;
+			adj_mode->private_flags |= cur_mode->private_flags;
+		}
+	}
+}
+
+static struct msm_display_topology dpu_encoder_get_topology(
+			struct dpu_encoder_virt *dpu_enc,
+			struct dpu_kms *dpu_kms,
+			struct drm_display_mode *mode)
+{
+	struct msm_display_topology topology;
+	int i, intf_count = 0;
+
+	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
+		if (dpu_enc->phys_encs[i])
+			intf_count++;
+
+	/* User split topology for width > 1080 */
+	topology.num_lm = (mode->vdisplay > MAX_VDISPLAY_SPLIT) ? 2 : 1;
+	topology.num_enc = 0;
+	topology.num_intf = intf_count;
+
+	return topology;
+}
+static int dpu_encoder_virt_atomic_check(
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	const struct drm_display_mode *mode;
+	struct drm_display_mode *adj_mode;
+	struct msm_display_topology topology;
+	int i = 0;
+	int ret = 0;
+
+	if (!drm_enc || !crtc_state || !conn_state) {
+		DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n",
+				drm_enc != 0, crtc_state != 0, conn_state != 0);
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	mode = &crtc_state->mode;
+	adj_mode = &crtc_state->adjusted_mode;
+	trace_dpu_enc_atomic_check(DRMID(drm_enc));
+
+	/*
+	 * display drivers may populate private fields of the drm display mode
+	 * structure while registering possible modes of a connector with DRM.
+	 * These private fields are not populated back while DRM invokes
+	 * the mode_set callbacks. This module retrieves and populates the
+	 * private fields of the given mode.
+	 */
+	_dpu_encoder_adjust_mode(conn_state->connector, adj_mode);
+
+	/* perform atomic check on the first physical encoder (master) */
+	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)
+			ret = phys->ops.atomic_check(phys, crtc_state,
+					conn_state);
+		else if (phys && phys->ops.mode_fixup)
+			if (!phys->ops.mode_fixup(phys, mode, adj_mode))
+				ret = -EINVAL;
+
+		if (ret) {
+			DPU_ERROR_ENC(dpu_enc,
+					"mode unsupported, phys idx %d\n", i);
+			break;
+		}
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. Indicating AtomicTest phase */
+	if (!ret) {
+		/*
+		 * Avoid reserving resources when mode set is pending. Topology
+		 * info may not be available to complete reservation.
+		 */
+		if (drm_atomic_crtc_needs_modeset(crtc_state)
+				&& dpu_enc->mode_set_complete) {
+			ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, crtc_state,
+				conn_state, topology, true);
+			dpu_enc->mode_set_complete = false;
+		}
+	}
+
+	if (!ret)
+		drm_mode_set_crtcinfo(adj_mode, 0);
+
+	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags,
+			adj_mode->private_flags);
+
+	return ret;
+}
+
+static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
+			struct msm_display_info *disp_info)
+{
+	struct dpu_vsync_source_cfg vsync_cfg = { 0 };
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct drm_encoder *drm_enc;
+	int i;
+
+	if (!dpu_enc || !disp_info) {
+		DPU_ERROR("invalid param dpu_enc:%d or disp_info:%d\n",
+					dpu_enc != NULL, disp_info != NULL);
+		return;
+	} else if (dpu_enc->num_phys_encs > ARRAY_SIZE(dpu_enc->hw_pp)) {
+		DPU_ERROR("invalid num phys enc %d/%d\n",
+				dpu_enc->num_phys_encs,
+				(int) ARRAY_SIZE(dpu_enc->hw_pp));
+		return;
+	}
+
+	drm_enc = &dpu_enc->base;
+	/* this pointers are checked in virt_enable_helper */
+	priv = drm_enc->dev->dev_private;
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	}
+
+	hw_mdptop = dpu_kms->hw_mdp;
+	if (!hw_mdptop) {
+		DPU_ERROR("invalid mdptop\n");
+		return;
+	}
+
+	if (hw_mdptop->ops.setup_vsync_source &&
+			disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) {
+		for (i = 0; i < dpu_enc->num_phys_encs; i++)
+			vsync_cfg.ppnumber[i] = dpu_enc->hw_pp[i]->idx;
+
+		vsync_cfg.pp_count = dpu_enc->num_phys_encs;
+		if (disp_info->is_te_using_watchdog_timer)
+			vsync_cfg.vsync_source = DPU_VSYNC_SOURCE_WD_TIMER_0;
+		else
+			vsync_cfg.vsync_source = DPU_VSYNC0_SOURCE_GPIO;
+
+		hw_mdptop->ops.setup_vsync_source(hw_mdptop, &vsync_cfg);
+	}
+}
+
+static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	DPU_DEBUG_ENC(dpu_enc, "enable:%d\n", 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)
+			phys->ops.irq_control(phys, enable);
+	}
+
+}
+
+static void _dpu_encoder_resource_control_helper(struct drm_encoder *drm_enc,
+		bool enable)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_encoder_virt *dpu_enc;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_rc_helper(DRMID(drm_enc), enable);
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("encoder master not set\n");
+		return;
+	}
+
+	if (enable) {
+		/* enable DPU core clks */
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+		/* enable all the irq */
+		_dpu_encoder_irq_control(drm_enc, true);
+
+	} else {
+		/* disable all the irq */
+		_dpu_encoder_irq_control(drm_enc, false);
+
+		/* disable DPU core clks */
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+	}
+
+}
+
+static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
+		u32 sw_event)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *disp_thread;
+	bool is_vid_mode = false;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private ||
+			!drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	is_vid_mode = dpu_enc->disp_info.capabilities &
+						MSM_DISPLAY_CAP_VID_MODE;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->disp_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return -EINVAL;
+	}
+	disp_thread = &priv->disp_thread[drm_enc->crtc->index];
+
+	/*
+	 * when idle_pc is not supported, process only KICKOFF, STOP and MODESET
+	 * events and return early for other events (ie wb display).
+	 */
+	if (!dpu_enc->idle_pc_supported &&
+			(sw_event != DPU_ENC_RC_EVENT_KICKOFF &&
+			sw_event != DPU_ENC_RC_EVENT_STOP &&
+			sw_event != DPU_ENC_RC_EVENT_PRE_STOP))
+		return 0;
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event, dpu_enc->idle_pc_supported,
+			 dpu_enc->rc_state, "begin");
+
+	switch (sw_event) {
+	case DPU_ENC_RC_EVENT_KICKOFF:
+		/* cancel delayed off work, if any */
+		if (kthread_cancel_delayed_work_sync(
+				&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in ON state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in ON state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state != DPU_ENC_RC_STATE_OFF &&
+				dpu_enc->rc_state != DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in state %d\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		if (is_vid_mode && dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE)
+			_dpu_encoder_irq_control(drm_enc, true);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, true);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_ON;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "kickoff");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_FRAME_DONE:
+		/*
+		 * mutex lock is not used as this event happens at interrupt
+		 * context. And locking is not required as, the other events
+		 * like KICKOFF and STOP does a wait-for-idle before executing
+		 * the resource_control
+		 */
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id:%d, sw_event:%d,rc:%d-unexpected\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			return -EINVAL;
+		}
+
+		/*
+		 * schedule off work item only when there are no
+		 * frames pending
+		 */
+		if (dpu_crtc_frame_pending(drm_enc->crtc) > 1) {
+			DRM_DEBUG_KMS("id:%d skip schedule work\n",
+				      DRMID(drm_enc));
+			return 0;
+		}
+
+		kthread_queue_delayed_work(
+			&disp_thread->worker,
+			&dpu_enc->delayed_off_work,
+			msecs_to_jiffies(dpu_enc->idle_timeout));
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "frame done");
+		break;
+
+	case DPU_ENC_RC_EVENT_PRE_STOP:
+		/* cancel delayed off work, if any */
+		if (kthread_cancel_delayed_work_sync(
+				&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (is_vid_mode &&
+			  dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			_dpu_encoder_irq_control(drm_enc, true);
+		}
+		/* skip if is already OFF or IDLE, resources are off already */
+		else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF ||
+				dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id:%u, sw_event:%d, rc in %d state\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_PRE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "pre stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_STOP:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in OFF state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF) {
+			DRM_DEBUG_KMS("id: %u, sw_event:%d, rc in OFF state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc in state %d\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		/**
+		 * expect to arrive here only if in either idle state or pre-off
+		 * and in IDLE state the resources are already disabled
+		 */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_PRE_OFF)
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_ENTER_IDLE:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc:%d !ON state\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		/*
+		 * if we are in ON but a frame was just kicked off,
+		 * ignore the IDLE event, it's probably a stale timer event
+		 */
+		if (dpu_enc->frame_busy_mask[0]) {
+			DRM_ERROR("id:%u, sw_event:%d, rc:%d frame pending\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		if (is_vid_mode)
+			_dpu_encoder_irq_control(drm_enc, false);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_IDLE;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "idle");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	default:
+		DRM_ERROR("id:%u, unexpected sw_event: %d\n", DRMID(drm_enc),
+			  sw_event);
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "error");
+		break;
+	}
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+			 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+			 "end");
+	return 0;
+}
+
+static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
+				      struct drm_display_mode *mode,
+				      struct drm_display_mode *adj_mode)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct list_head *connector_list;
+	struct drm_connector *conn = NULL, *conn_iter;
+	struct dpu_rm_hw_iter pp_iter;
+	struct msm_display_topology topology;
+	enum dpu_rm_topology_name topology_name;
+	int i = 0, ret;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	connector_list = &dpu_kms->dev->mode_config.connector_list;
+
+	trace_dpu_enc_mode_set(DRMID(drm_enc));
+
+	list_for_each_entry(conn_iter, connector_list, head)
+		if (conn_iter->encoder == drm_enc)
+			conn = conn_iter;
+
+	if (!conn) {
+		DPU_ERROR_ENC(dpu_enc, "failed to find attached connector\n");
+		return;
+	} else if (!conn->state) {
+		DPU_ERROR_ENC(dpu_enc, "invalid connector state\n");
+		return;
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. Indicating non-AtomicTest phase */
+	ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, drm_enc->crtc->state,
+			conn->state, topology, false);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc,
+				"failed to reserve hw resources, %d\n", ret);
+		return;
+	}
+
+	dpu_rm_init_hw_iter(&pp_iter, drm_enc->base.id, DPU_HW_BLK_PINGPONG);
+	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
+		dpu_enc->hw_pp[i] = NULL;
+		if (!dpu_rm_get_hw(&dpu_kms->rm, &pp_iter))
+			break;
+		dpu_enc->hw_pp[i] = (struct dpu_hw_pingpong *) pp_iter.hw;
+	}
+
+	topology_name = dpu_rm_get_topology_name(topology);
+	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,
+				    "invalid pingpong block for the encoder\n");
+				return;
+			}
+			phys->hw_pp = dpu_enc->hw_pp[i];
+			phys->connector = conn->state->connector;
+			phys->topology_name = topology_name;
+			if (phys->ops.mode_set)
+				phys->ops.mode_set(phys, mode, adj_mode);
+		}
+	}
+
+	dpu_enc->mode_set_complete = true;
+}
+
+static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	if (!dpu_enc || !dpu_enc->cur_master) {
+		DPU_ERROR("invalid dpu encoder/master\n");
+		return;
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DisplayPort &&
+	    dpu_enc->cur_master->hw_mdptop &&
+	    dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select)
+		dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select(
+					dpu_enc->cur_master->hw_mdptop);
+
+	if (dpu_enc->cur_master->hw_mdptop &&
+			dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc)
+		dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc(
+				dpu_enc->cur_master->hw_mdptop,
+				dpu_kms->catalog);
+
+	_dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info);
+}
+
+void dpu_encoder_virt_restore(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(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 != dpu_enc->cur_master) && phys->ops.restore)
+			phys->ops.restore(phys);
+	}
+
+	if (dpu_enc->cur_master && dpu_enc->cur_master->ops.restore)
+		dpu_enc->cur_master->ops.restore(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+}
+
+static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+	struct drm_display_mode *cur_mode = NULL;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
+
+	trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay,
+			     cur_mode->vdisplay);
+
+	dpu_enc->cur_master = NULL;
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.is_master && phys->ops.is_master(phys)) {
+			DPU_DEBUG_ENC(dpu_enc, "master is now idx %d\n", i);
+			dpu_enc->cur_master = phys;
+			break;
+		}
+	}
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("virt encoder has no master! num_phys %d\n", i);
+		return;
+	}
+
+	ret = dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc, "dpu resource control failed: %d\n",
+				ret);
+		return;
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys)
+			continue;
+
+		if (phys != dpu_enc->cur_master) {
+			if (phys->ops.enable)
+				phys->ops.enable(phys);
+		}
+
+		if (dpu_enc->misr_enable && (dpu_enc->disp_info.capabilities &
+		     MSM_DISPLAY_CAP_VID_MODE) && phys->ops.setup_misr)
+			phys->ops.setup_misr(phys, true,
+						dpu_enc->misr_frame_count);
+	}
+
+	if (dpu_enc->cur_master->ops.enable)
+		dpu_enc->cur_master->ops.enable(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+}
+
+static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode *mode;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	} else if (!drm_enc->dev) {
+		DPU_ERROR("invalid dev\n");
+		return;
+	} else if (!drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid dev_private\n");
+		return;
+	}
+
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_disable(DRMID(drm_enc));
+
+	/* wait for idle */
+	dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE);
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP);
+
+	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)
+			phys->ops.disable(phys);
+	}
+
+	/* after phys waits for frame-done, should be no more frames pending */
+	if (atomic_xchg(&dpu_enc->frame_done_timeout, 0)) {
+		DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id);
+		del_timer_sync(&dpu_enc->frame_done_timer);
+	}
+
+	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->cur_master = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
+
+	dpu_rm_release(&dpu_kms->rm, drm_enc);
+}
+
+static enum dpu_intf dpu_encoder_get_intf(struct dpu_mdss_cfg *catalog,
+		enum dpu_intf_type type, u32 controller_id)
+{
+	int i = 0;
+
+	for (i = 0; i < catalog->intf_count; i++) {
+		if (catalog->intf[i].type == type
+		    && catalog->intf[i].controller_id == controller_id) {
+			return catalog->intf[i].id;
+		}
+	}
+
+	return INTF_MAX;
+}
+
+static void dpu_encoder_vblank_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	unsigned long lock_flags;
+
+	if (!drm_enc || !phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_vblank_callback");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	if (dpu_enc->crtc_vblank_cb)
+		dpu_enc->crtc_vblank_cb(dpu_enc->crtc_vblank_cb_data);
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	atomic_inc(&phy_enc->vsync_cnt);
+	DPU_ATRACE_END("encoder_vblank_callback");
+}
+
+static void dpu_encoder_underrun_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	if (!phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_underrun_callback");
+	atomic_inc(&phy_enc->underrun_cnt);
+	trace_dpu_enc_underrun_cb(DRMID(drm_enc),
+				  atomic_read(&phy_enc->underrun_cnt));
+	DPU_ATRACE_END("encoder_underrun_callback");
+}
+
+void dpu_encoder_register_vblank_callback(struct drm_encoder *drm_enc,
+		void (*vbl_cb)(void *), void *vbl_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+	int i;
+
+	enable = vbl_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_vblank_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_vblank_cb = vbl_cb;
+	dpu_enc->crtc_vblank_cb_data = vbl_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	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)
+			phys->ops.control_vblank_irq(phys, enable);
+	}
+}
+
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *drm_enc,
+		void (*frame_event_cb)(void *, u32 event),
+		void *frame_event_cb_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+
+	enable = frame_event_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_frame_event_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_frame_event_cb = frame_event_cb;
+	dpu_enc->crtc_frame_event_cb_data = frame_event_cb_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+static void dpu_encoder_frame_done_callback(
+		struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *ready_phys, u32 event)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned int i;
+
+	if (event & (DPU_ENCODER_FRAME_EVENT_DONE
+			| DPU_ENCODER_FRAME_EVENT_ERROR
+			| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			/**
+			 * suppress frame_done without waiter,
+			 * likely autorefresh
+			 */
+			trace_dpu_enc_frame_done_cb_not_busy(DRMID(drm_enc),
+					event, ready_phys->intf_idx);
+			return;
+		}
+
+		/* One of the physical encoders has become idle */
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			if (dpu_enc->phys_encs[i] == ready_phys) {
+				clear_bit(i, dpu_enc->frame_busy_mask);
+				trace_dpu_enc_frame_done_cb(DRMID(drm_enc), i,
+						dpu_enc->frame_busy_mask[0]);
+			}
+		}
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			atomic_set(&dpu_enc->frame_done_timeout, 0);
+			del_timer(&dpu_enc->frame_done_timer);
+
+			dpu_encoder_resource_control(drm_enc,
+					DPU_ENC_RC_EVENT_FRAME_DONE);
+
+			if (dpu_enc->crtc_frame_event_cb)
+				dpu_enc->crtc_frame_event_cb(
+					dpu_enc->crtc_frame_event_cb_data,
+					event);
+		}
+	} else {
+		if (dpu_enc->crtc_frame_event_cb)
+			dpu_enc->crtc_frame_event_cb(
+				dpu_enc->crtc_frame_event_cb_data, event);
+	}
+}
+
+static void dpu_encoder_off_work(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, delayed_off_work.work);
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu encoder\n");
+		return;
+	}
+
+	dpu_encoder_resource_control(&dpu_enc->base,
+						DPU_ENC_RC_EVENT_ENTER_IDLE);
+
+	dpu_encoder_frame_done_callback(&dpu_enc->base, NULL,
+				DPU_ENCODER_FRAME_EVENT_IDLE);
+}
+
+/**
+ * _dpu_encoder_trigger_flush - trigger flush for a physical encoder
+ * drm_enc: Pointer to drm encoder structure
+ * phys: Pointer to physical encoder structure
+ * extra_flush_bits: Additional bit mask to include in flush trigger
+ */
+static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits)
+{
+	struct dpu_hw_ctl *ctl;
+	int pending_kickoff_cnt;
+	u32 ret = UINT_MAX;
+
+	if (!drm_enc || !phys) {
+		DPU_ERROR("invalid argument(s), drm_enc %d, phys_enc %d\n",
+				drm_enc != 0, phys != 0);
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	ctl = phys->hw_ctl;
+	if (!ctl || !ctl->ops.trigger_flush) {
+		DPU_ERROR("missing trigger cb\n");
+		return;
+	}
+
+	pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
+
+	if (extra_flush_bits && ctl->ops.update_pending_flush)
+		ctl->ops.update_pending_flush(ctl, extra_flush_bits);
+
+	ctl->ops.trigger_flush(ctl);
+
+	if (ctl->ops.get_pending_flush)
+		ret = ctl->ops.get_pending_flush(ctl);
+
+	trace_dpu_enc_trigger_flush(DRMID(drm_enc), phys->intf_idx,
+				    pending_kickoff_cnt, ctl->idx, ret);
+}
+
+/**
+ * _dpu_encoder_trigger_start - trigger start for a physical encoder
+ * phys: Pointer to physical encoder structure
+ */
+static inline void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
+{
+	if (!phys) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED)
+		phys->ops.trigger_start(phys);
+}
+
+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) {
+		ctl->ops.trigger_start(ctl);
+		trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx);
+	}
+}
+
+static int dpu_encoder_helper_wait_event_timeout(
+		int32_t drm_id,
+		int32_t hw_id,
+		struct dpu_encoder_wait_info *info)
+{
+	int rc = 0;
+	s64 expected_time = ktime_to_ms(ktime_get()) + info->timeout_ms;
+	s64 jiffies = msecs_to_jiffies(info->timeout_ms);
+	s64 time;
+
+	do {
+		rc = wait_event_timeout(*(info->wq),
+				atomic_read(info->atomic_cnt) == 0, jiffies);
+		time = ktime_to_ms(ktime_get());
+
+		trace_dpu_enc_wait_event_timeout(drm_id, hw_id, rc, time,
+						 expected_time,
+						 atomic_read(info->atomic_cnt));
+	/* If we timed out, counter is valid and time is less, wait again */
+	} while (atomic_read(info->atomic_cnt) && (rc == 0) &&
+			(time < expected_time));
+
+	return rc;
+}
+
+void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_virt *dpu_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)
+		return;
+
+	DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(phys_enc->parent),
+		      ctl->idx);
+
+	rc = ctl->ops.reset(ctl);
+	if (rc) {
+		DPU_ERROR_ENC(dpu_enc, "ctl %d reset failure\n",  ctl->idx);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+/**
+ * _dpu_encoder_kickoff_phys - handle physical encoder kickoff
+ *	Iterate through the physical encoders and perform consolidated flush
+ *	and/or control start triggering as needed. This is done in the virtual
+ *	encoder rather than the individual physical ones in order to handle
+ *	use cases that require visibility into multiple physical encoders at
+ *	a time.
+ * dpu_enc: Pointer to virtual encoder structure
+ */
+static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	uint32_t i, pending_flush;
+	unsigned long lock_flags;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	pending_flush = 0x0;
+
+	/* update pending counts and trigger kickoff ctl flush atomically */
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+
+	/* don't perform flush/start operations for slave encoders */
+	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)
+			continue;
+
+		ctl = phys->hw_ctl;
+		if (!ctl)
+			continue;
+
+		if (phys->split_role != ENC_ROLE_SLAVE)
+			set_bit(i, dpu_enc->frame_busy_mask);
+		if (!phys->ops.needs_single_flush ||
+				!phys->ops.needs_single_flush(phys))
+			_dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0);
+		else if (ctl->ops.get_pending_flush)
+			pending_flush |= ctl->ops.get_pending_flush(ctl);
+	}
+
+	/* for split flush, combine pending flush masks and send to master */
+	if (pending_flush && dpu_enc->cur_master) {
+		_dpu_encoder_trigger_flush(
+				&dpu_enc->base,
+				dpu_enc->cur_master,
+				pending_flush);
+	}
+
+	_dpu_encoder_trigger_start(dpu_enc->cur_master);
+
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	unsigned int i;
+	struct dpu_hw_ctl *ctl;
+	struct msm_display_info *disp_info;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	disp_info = &dpu_enc->disp_info;
+
+	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);
+
+			/* 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);
+		}
+	}
+}
+
+static u32 _dpu_encoder_calculate_linetime(struct dpu_encoder_virt *dpu_enc,
+		struct drm_display_mode *mode)
+{
+	u64 pclk_rate;
+	u32 pclk_period;
+	u32 line_time;
+
+	/*
+	 * For linetime calculation, only operate on master encoder.
+	 */
+	if (!dpu_enc->cur_master)
+		return 0;
+
+	if (!dpu_enc->cur_master->ops.get_line_count) {
+		DPU_ERROR("get_line_count function not defined\n");
+		return 0;
+	}
+
+	pclk_rate = mode->clock; /* pixel clock in kHz */
+	if (pclk_rate == 0) {
+		DPU_ERROR("pclk is 0, cannot calculate line time\n");
+		return 0;
+	}
+
+	pclk_period = DIV_ROUND_UP_ULL(1000000000ull, pclk_rate);
+	if (pclk_period == 0) {
+		DPU_ERROR("pclk period is 0\n");
+		return 0;
+	}
+
+	/*
+	 * Line time calculation based on Pixel clock and HTOTAL.
+	 * Final unit is in ns.
+	 */
+	line_time = (pclk_period * mode->htotal) / 1000;
+	if (line_time == 0) {
+		DPU_ERROR("line time calculation is 0\n");
+		return 0;
+	}
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"clk_rate=%lldkHz, clk_period=%d, linetime=%dns\n",
+			pclk_rate, pclk_period, line_time);
+
+	return line_time;
+}
+
+static int _dpu_encoder_wakeup_time(struct drm_encoder *drm_enc,
+		ktime_t *wakeup_time)
+{
+	struct drm_display_mode *mode;
+	struct dpu_encoder_virt *dpu_enc;
+	u32 cur_line;
+	u32 line_time;
+	u32 vtotal, time_to_vsync;
+	ktime_t cur_time;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	if (!drm_enc->crtc || !drm_enc->crtc->state) {
+		DPU_ERROR("crtc/crtc state object is NULL\n");
+		return -EINVAL;
+	}
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	line_time = _dpu_encoder_calculate_linetime(dpu_enc, mode);
+	if (!line_time)
+		return -EINVAL;
+
+	cur_line = dpu_enc->cur_master->ops.get_line_count(dpu_enc->cur_master);
+
+	vtotal = mode->vtotal;
+	if (cur_line >= vtotal)
+		time_to_vsync = line_time * vtotal;
+	else
+		time_to_vsync = line_time * (vtotal - cur_line);
+
+	if (time_to_vsync == 0) {
+		DPU_ERROR("time to vsync should not be zero, vtotal=%d\n",
+				vtotal);
+		return -EINVAL;
+	}
+
+	cur_time = ktime_get();
+	*wakeup_time = ktime_add_ns(cur_time, time_to_vsync);
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"cur_line=%u vtotal=%u time_to_vsync=%u, cur_time=%lld, wakeup_time=%lld\n",
+			cur_line, vtotal, time_to_vsync,
+			ktime_to_ms(cur_time),
+			ktime_to_ms(*wakeup_time));
+	return 0;
+}
+
+static void dpu_encoder_vsync_event_handler(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			vsync_event_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+
+	if (!drm_enc->dev || !drm_enc->dev->dev_private ||
+			!drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return;
+	}
+	event_thread = &priv->event_thread[drm_enc->crtc->index];
+	if (!event_thread) {
+		DPU_ERROR("event_thread not found for crtc:%d\n",
+				drm_enc->crtc->index);
+		return;
+	}
+
+	del_timer(&dpu_enc->vsync_event_timer);
+}
+
+static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, vsync_event_work);
+	ktime_t wakeup_time;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu encoder\n");
+		return;
+	}
+
+	if (_dpu_encoder_wakeup_time(&dpu_enc->base, &wakeup_time))
+		return;
+
+	trace_dpu_enc_vsync_event_work(DRMID(&dpu_enc->base), wakeup_time);
+	mod_timer(&dpu_enc->vsync_event_timer,
+			nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+}
+
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	bool needs_hw_reset = false;
+	unsigned int i;
+
+	if (!drm_enc || !params) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_prepare_kickoff(DRMID(drm_enc));
+
+	/* prepare for next kickoff, may include waiting on previous kickoff */
+	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, params);
+			if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
+				needs_hw_reset = true;
+		}
+	}
+	DPU_ATRACE_END("enc_prepare_for_kickoff");
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+
+	/* if any phys needs reset, reset all phys, in-order */
+	if (needs_hw_reset) {
+		trace_dpu_enc_prepare_kickoff_reset(DRMID(drm_enc));
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			phys = dpu_enc->phys_encs[i];
+			if (phys && phys->ops.hw_reset)
+				phys->ops.hw_reset(phys);
+		}
+	}
+}
+
+void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	ktime_t wakeup_time;
+	unsigned int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DPU_ATRACE_BEGIN("encoder_kickoff");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_kickoff(DRMID(drm_enc));
+
+	atomic_set(&dpu_enc->frame_done_timeout,
+			DPU_FRAME_DONE_TIMEOUT * 1000 /
+			drm_enc->crtc->state->adjusted_mode.vrefresh);
+	mod_timer(&dpu_enc->frame_done_timer, jiffies +
+		((atomic_read(&dpu_enc->frame_done_timeout) * HZ) / 1000));
+
+	/* All phys encs are ready to go, trigger the kickoff */
+	_dpu_encoder_kickoff_phys(dpu_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)
+			phys->ops.handle_post_kickoff(phys);
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DSI &&
+			!_dpu_encoder_wakeup_time(drm_enc, &wakeup_time)) {
+		trace_dpu_enc_early_kickoff(DRMID(drm_enc),
+					    ktime_to_ms(wakeup_time));
+		mod_timer(&dpu_enc->vsync_event_timer,
+				nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+	}
+
+	DPU_ATRACE_END("encoder_kickoff");
+}
+
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys && phys->ops.prepare_commit)
+			phys->ops.prepare_commit(phys);
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_encoder_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!s || !s->private)
+		return -EINVAL;
+
+	dpu_enc = s->private;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	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),
+				atomic_read(&phys->underrun_cnt));
+
+		switch (phys->intf_mode) {
+		case INTF_MODE_VIDEO:
+			seq_puts(s, "mode: video\n");
+			break;
+		case INTF_MODE_CMD:
+			seq_puts(s, "mode: command\n");
+			break;
+		default:
+			seq_puts(s, "mode: ???\n");
+			break;
+		}
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return 0;
+}
+
+static int _dpu_encoder_debugfs_status_open(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_encoder_status_show, inode->i_private);
+}
+
+static ssize_t _dpu_encoder_misr_setup(struct file *file,
+		const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i = 0, rc;
+	char buf[MISR_BUFF_SIZE + 1];
+	size_t buff_copy;
+	u32 frame_count, enable;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_enc = file->private_data;
+
+	buff_copy = min_t(size_t, count, MISR_BUFF_SIZE);
+	if (copy_from_user(buf, user_buf, buff_copy))
+		return -EINVAL;
+
+	buf[buff_copy] = 0; /* end of string */
+
+	if (sscanf(buf, "%u %u", &enable, &frame_count) != 2)
+		return -EINVAL;
+
+	rc = _dpu_encoder_power_enable(dpu_enc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	dpu_enc->misr_enable = enable;
+	dpu_enc->misr_frame_count = frame_count;
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || !phys->ops.setup_misr)
+			continue;
+
+		phys->ops.setup_misr(phys, enable, frame_count);
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+	_dpu_encoder_power_enable(dpu_enc, false);
+
+	return count;
+}
+
+static ssize_t _dpu_encoder_misr_read(struct file *file,
+		char __user *user_buff, size_t count, loff_t *ppos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i = 0, len = 0;
+	char buf[MISR_BUFF_SIZE + 1] = {'\0'};
+	int rc;
+
+	if (*ppos)
+		return 0;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_enc = file->private_data;
+
+	rc = _dpu_encoder_power_enable(dpu_enc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	if (!dpu_enc->misr_enable) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"disabled\n");
+		goto buff_check;
+	} else if (dpu_enc->disp_info.capabilities &
+						~MSM_DISPLAY_CAP_VID_MODE) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"unsupported\n");
+		goto buff_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.collect_misr)
+			continue;
+
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"Intf idx:%d\n", phys->intf_idx - INTF_0);
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n",
+					phys->ops.collect_misr(phys));
+	}
+
+buff_check:
+	if (count <= len) {
+		len = 0;
+		goto end;
+	}
+
+	if (copy_to_user(user_buff, buf, len)) {
+		len = -EFAULT;
+		goto end;
+	}
+
+	*ppos += len;   /* increase offset */
+
+end:
+	mutex_unlock(&dpu_enc->enc_lock);
+	_dpu_encoder_power_enable(dpu_enc, false);
+	return len;
+}
+
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int i;
+
+	static const struct file_operations debugfs_status_fops = {
+		.open =		_dpu_encoder_debugfs_status_open,
+		.read =		seq_read,
+		.llseek =	seq_lseek,
+		.release =	single_release,
+	};
+
+	static const struct file_operations debugfs_misr_fops = {
+		.open = simple_open,
+		.read = _dpu_encoder_misr_read,
+		.write = _dpu_encoder_misr_setup,
+	};
+
+	char name[DPU_NAME_SIZE];
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid encoder or kms\n");
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id);
+
+	/* create overall sub-directory for the encoder */
+	dpu_enc->debugfs_root = debugfs_create_dir(name,
+			drm_enc->dev->primary->debugfs_root);
+	if (!dpu_enc->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_file("status", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops);
+
+	debugfs_create_file("misr_data", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &debugfs_misr_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)
+			dpu_enc->phys_encs[i]->ops.late_register(
+					dpu_enc->phys_encs[i],
+					dpu_enc->debugfs_root);
+
+	return 0;
+}
+
+static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+
+	if (!drm_enc)
+		return;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	debugfs_remove_recursive(dpu_enc->debugfs_root);
+}
+#else
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	return 0;
+}
+
+static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
+{
+}
+#endif
+
+static int dpu_encoder_late_register(struct drm_encoder *encoder)
+{
+	return _dpu_encoder_init_debugfs(encoder);
+}
+
+static void dpu_encoder_early_unregister(struct drm_encoder *encoder)
+{
+	_dpu_encoder_destroy_debugfs(encoder);
+}
+
+static int dpu_encoder_virt_add_phys_encs(
+		u32 display_caps,
+		struct dpu_encoder_virt *dpu_enc,
+		struct dpu_enc_phys_init_params *params)
+{
+	struct dpu_encoder_phys *enc = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/*
+	 * We may create up to NUM_PHYS_ENCODER_TYPES physical encoder types
+	 * in this function, check up-front.
+	 */
+	if (dpu_enc->num_phys_encs + NUM_PHYS_ENCODER_TYPES >=
+			ARRAY_SIZE(dpu_enc->phys_encs)) {
+		DPU_ERROR_ENC(dpu_enc, "too many physical encoders %d\n",
+			  dpu_enc->num_phys_encs);
+		return -EINVAL;
+	}
+
+	if (display_caps & MSM_DISPLAY_CAP_VID_MODE) {
+		enc = dpu_encoder_phys_vid_init(params);
+
+		if (IS_ERR_OR_NULL(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n",
+				PTR_ERR(enc));
+			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	if (display_caps & MSM_DISPLAY_CAP_CMD_MODE) {
+		enc = dpu_encoder_phys_cmd_init(params);
+
+		if (IS_ERR_OR_NULL(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n",
+				PTR_ERR(enc));
+			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	return 0;
+}
+
+static const struct dpu_encoder_virt_ops dpu_encoder_parent_ops = {
+	.handle_vblank_virt = dpu_encoder_vblank_callback,
+	.handle_underrun_virt = dpu_encoder_underrun_callback,
+	.handle_frame_done = dpu_encoder_frame_done_callback,
+};
+
+static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
+				 struct dpu_kms *dpu_kms,
+				 struct msm_display_info *disp_info,
+				 int *drm_enc_mode)
+{
+	int ret = 0;
+	int i = 0;
+	enum dpu_intf_type intf_type;
+	struct dpu_enc_phys_init_params phys_params;
+
+	if (!dpu_enc || !dpu_kms) {
+		DPU_ERROR("invalid arg(s), enc %d kms %d\n",
+				dpu_enc != 0, dpu_kms != 0);
+		return -EINVAL;
+	}
+
+	memset(&phys_params, 0, sizeof(phys_params));
+	phys_params.dpu_kms = dpu_kms;
+	phys_params.parent = &dpu_enc->base;
+	phys_params.parent_ops = &dpu_encoder_parent_ops;
+	phys_params.enc_spinlock = &dpu_enc->enc_spinlock;
+
+	DPU_DEBUG("\n");
+
+	if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI) {
+		*drm_enc_mode = DRM_MODE_ENCODER_DSI;
+		intf_type = INTF_DSI;
+	} else if (disp_info->intf_type == DRM_MODE_CONNECTOR_HDMIA) {
+		*drm_enc_mode = DRM_MODE_ENCODER_TMDS;
+		intf_type = INTF_HDMI;
+	} else if (disp_info->intf_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		*drm_enc_mode = DRM_MODE_ENCODER_TMDS;
+		intf_type = INTF_DP;
+	} else {
+		DPU_ERROR_ENC(dpu_enc, "unsupported display interface type\n");
+		return -EINVAL;
+	}
+
+	WARN_ON(disp_info->num_of_h_tiles < 1);
+
+	dpu_enc->display_num_of_h_tiles = disp_info->num_of_h_tiles;
+
+	DPU_DEBUG("dsi_info->num_of_h_tiles %d\n", disp_info->num_of_h_tiles);
+
+	if ((disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) ||
+	    (disp_info->capabilities & MSM_DISPLAY_CAP_VID_MODE))
+		dpu_enc->idle_pc_supported =
+				dpu_kms->catalog->caps->has_idle_pc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < disp_info->num_of_h_tiles && !ret; i++) {
+		/*
+		 * Left-most tile is at index 0, content is controller id
+		 * h_tile_instance_ids[2] = {0, 1}; DSI0 = left, DSI1 = right
+		 * h_tile_instance_ids[2] = {1, 0}; DSI1 = left, DSI0 = right
+		 */
+		u32 controller_id = disp_info->h_tile_instance[i];
+
+		if (disp_info->num_of_h_tiles > 1) {
+			if (i == 0)
+				phys_params.split_role = ENC_ROLE_MASTER;
+			else
+				phys_params.split_role = ENC_ROLE_SLAVE;
+		} else {
+			phys_params.split_role = ENC_ROLE_SOLO;
+		}
+
+		DPU_DEBUG("h_tile_instance %d = %d, split_role %d\n",
+				i, controller_id, phys_params.split_role);
+
+		phys_params.intf_idx = dpu_encoder_get_intf(dpu_kms->catalog,
+													intf_type,
+													controller_id);
+		if (phys_params.intf_idx == INTF_MAX) {
+			DPU_ERROR_ENC(dpu_enc, "could not get intf: type %d, id %d\n",
+						  intf_type, controller_id);
+			ret = -EINVAL;
+		}
+
+		if (!ret) {
+			ret = dpu_encoder_virt_add_phys_encs(disp_info->capabilities,
+												 dpu_enc,
+												 &phys_params);
+			if (ret)
+				DPU_ERROR_ENC(dpu_enc, "failed to add phys encs\n");
+		}
+	}
+
+	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);
+		}
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return ret;
+}
+
+static void dpu_encoder_frame_done_timeout(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			frame_done_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	u32 event;
+
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+	priv = drm_enc->dev->dev_private;
+
+	if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) {
+		DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n",
+			      DRMID(drm_enc), dpu_enc->frame_busy_mask[0]);
+		return;
+	} else if (!atomic_xchg(&dpu_enc->frame_done_timeout, 0)) {
+		DRM_DEBUG_KMS("id:%u invalid timeout\n", DRMID(drm_enc));
+		return;
+	}
+
+	DPU_ERROR_ENC(dpu_enc, "frame done timeout\n");
+
+	event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event);
+	dpu_enc->crtc_frame_event_cb(dpu_enc->crtc_frame_event_cb_data, event);
+}
+
+static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = {
+	.mode_set = dpu_encoder_virt_mode_set,
+	.disable = dpu_encoder_virt_disable,
+	.enable = dpu_kms_encoder_enable,
+	.atomic_check = dpu_encoder_virt_atomic_check,
+
+	/* This is called by dpu_kms_encoder_enable */
+	.commit = dpu_encoder_virt_enable,
+};
+
+static const struct drm_encoder_funcs dpu_encoder_funcs = {
+		.destroy = dpu_encoder_destroy,
+		.late_register = dpu_encoder_late_register,
+		.early_unregister = dpu_encoder_early_unregister,
+};
+
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_encoder *drm_enc = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int drm_enc_mode = DRM_MODE_ENCODER_NONE;
+	int ret = 0;
+
+	dpu_enc = to_dpu_encoder_virt(enc);
+
+	mutex_init(&dpu_enc->enc_lock);
+	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info,
+			&drm_enc_mode);
+	if (ret)
+		goto fail;
+
+	dpu_enc->cur_master = NULL;
+	spin_lock_init(&dpu_enc->enc_spinlock);
+
+	atomic_set(&dpu_enc->frame_done_timeout, 0);
+	timer_setup(&dpu_enc->frame_done_timer,
+			dpu_encoder_frame_done_timeout, 0);
+
+	if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI)
+		timer_setup(&dpu_enc->vsync_event_timer,
+				dpu_encoder_vsync_event_handler,
+				0);
+
+
+	mutex_init(&dpu_enc->rc_lock);
+	kthread_init_delayed_work(&dpu_enc->delayed_off_work,
+			dpu_encoder_off_work);
+	dpu_enc->idle_timeout = IDLE_TIMEOUT;
+
+	kthread_init_work(&dpu_enc->vsync_event_work,
+			dpu_encoder_vsync_event_work_handler);
+
+	memcpy(&dpu_enc->disp_info, disp_info, sizeof(*disp_info));
+
+	DPU_DEBUG_ENC(dpu_enc, "created\n");
+
+	return ret;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (drm_enc)
+		dpu_encoder_destroy(drm_enc);
+
+	return ret;
+
+
+}
+
+struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
+		int drm_enc_mode)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int rc = 0;
+
+	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
+	if (!dpu_enc)
+		return ERR_PTR(ENOMEM);
+
+	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
+			drm_enc_mode, NULL);
+	if (rc) {
+		devm_kfree(dev->dev, dpu_enc);
+		return ERR_PTR(rc);
+	}
+
+	drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs);
+
+	return &dpu_enc->base;
+}
+
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
+	enum msm_event_wait event)
+{
+	int (*fn_wait)(struct dpu_encoder_phys *phys_enc) = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		switch (event) {
+		case MSM_ENC_COMMIT_DONE:
+			fn_wait = phys->ops.wait_for_commit_done;
+			break;
+		case MSM_ENC_TX_COMPLETE:
+			fn_wait = phys->ops.wait_for_tx_complete;
+			break;
+		case MSM_ENC_VBLANK:
+			fn_wait = phys->ops.wait_for_vblank;
+			break;
+		default:
+			DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n",
+					event);
+			return -EINVAL;
+		};
+
+		if (phys && fn_wait) {
+			DPU_ATRACE_BEGIN("wait_for_completion_event");
+			ret = fn_wait(phys);
+			DPU_ATRACE_END("wait_for_completion_event");
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+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");
+		return INTF_MODE_NONE;
+	}
+	dpu_enc = to_dpu_encoder_virt(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;
+	}
+
+	return INTF_MODE_NONE;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
new file mode 100644
index 000000000000..60f809fc7c13
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -0,0 +1,177 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __DPU_ENCODER_H__
+#define __DPU_ENCODER_H__
+
+#include <drm/drm_crtc.h>
+#include "dpu_hw_mdss.h"
+
+#define DPU_ENCODER_FRAME_EVENT_DONE			BIT(0)
+#define DPU_ENCODER_FRAME_EVENT_ERROR			BIT(1)
+#define DPU_ENCODER_FRAME_EVENT_PANEL_DEAD		BIT(2)
+#define DPU_ENCODER_FRAME_EVENT_IDLE			BIT(3)
+
+#define IDLE_TIMEOUT	(66 - 16/2)
+
+/**
+ * Encoder functions and data types
+ * @intfs:	Interfaces this encoder is using, INTF_MODE_NONE if unused
+ * @needs_cdm:	Encoder requests a CDM based on pixel format conversion needs
+ * @display_num_of_h_tiles: Number of horizontal tiles in case of split
+ *                          interface
+ * @topology:   Topology of the display
+ */
+struct dpu_encoder_hw_resources {
+	enum dpu_intf_mode intfs[INTF_MAX];
+	bool needs_cdm;
+	u32 display_num_of_h_tiles;
+};
+
+/**
+ * dpu_encoder_kickoff_params - info encoder requires at kickoff
+ * @affected_displays:  bitmask, bit set means the ROI of the commit lies within
+ *                      the bounds of the physical display at the bit index
+ */
+struct dpu_encoder_kickoff_params {
+	unsigned long affected_displays;
+};
+
+/**
+ * dpu_encoder_get_hw_resources - Populate table of required hardware resources
+ * @encoder:	encoder pointer
+ * @hw_res:	resource table to populate with encoder required resources
+ * @conn_state:	report hw reqs based on this proposed connector state
+ */
+void dpu_encoder_get_hw_resources(struct drm_encoder *encoder,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state);
+
+/**
+ * dpu_encoder_register_vblank_callback - provide callback to encoder that
+ *	will be called on the next vblank.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister and disable IRQs
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_vblank_callback(struct drm_encoder *encoder,
+		void (*cb)(void *), void *data);
+
+/**
+ * dpu_encoder_register_frame_event_callback - provide callback to encoder that
+ *	will be called after the request is complete, or other events.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *encoder,
+		void (*cb)(void *, u32), void *data);
+
+/**
+ * dpu_encoder_prepare_for_kickoff - schedule double buffer flip of the ctl
+ *	path (i.e. ctl flush and start) at next appropriate time.
+ *	Immediately: if no previous commit is outstanding.
+ *	Delayed: Block until next trigger can be issued.
+ * @encoder:	encoder pointer
+ * @params:	kickoff time parameters
+ */
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *encoder,
+		struct dpu_encoder_kickoff_params *params);
+
+/**
+ * dpu_encoder_trigger_kickoff_pending - Clear the flush bits from previous
+ *        kickoff and trigger the ctl prepare progress for command mode display.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path
+ *	(i.e. ctl flush and start) immediately.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_kickoff(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_wait_for_event - Waits for encoder events
+ * @encoder:	encoder pointer
+ * @event:      event to wait for
+ * MSM_ENC_COMMIT_DONE -  Wait for hardware to have flushed the current pending
+ *                        frames to hardware at a vblank or ctl_start
+ *                        Encoders will map this differently depending on the
+ *                        panel type.
+ *	                  vid mode -> vsync_irq
+ *                        cmd mode -> ctl_start
+ * MSM_ENC_TX_COMPLETE -  Wait for the hardware to transfer all the pixels to
+ *                        the panel. Encoders will map this differently
+ *                        depending on the panel type.
+ *                        vid mode -> vsync_irq
+ *                        cmd mode -> pp_done
+ * Returns: 0 on success, -EWOULDBLOCK if already signaled, error otherwise
+ */
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder,
+						enum msm_event_wait event);
+
+/*
+ * dpu_encoder_get_intf_mode - get interface mode of the given encoder
+ * @encoder: Pointer to drm encoder object
+ */
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_virt_restore - restore the encoder configs
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_virt_restore(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_init - initialize virtual encoder object
+ * @dev:        Pointer to drm device structure
+ * @disp_info:  Pointer to display information structure
+ * Returns:     Pointer to newly created drm encoder
+ */
+struct drm_encoder *dpu_encoder_init(
+		struct drm_device *dev,
+		int drm_enc_mode);
+
+/**
+ * dpu_encoder_setup - setup dpu_encoder for the display probed
+ * @dev:		Pointer to drm device structure
+ * @enc:		Pointer to the drm_encoder
+ * @disp_info:	Pointer to the display info
+ */
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info);
+
+/**
+ * dpu_encoder_prepare_commit - prepare encoder at the very beginning of an
+ *	atomic commit, before any registers are written
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_set_idle_timeout - set the idle timeout for video
+ *                    and command mode encoders.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * @idle_timeout:    idle timeout duration in milliseconds
+ */
+void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc,
+							u32 idle_timeout);
+
+#endif /* __DPU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
new file mode 100644
index 000000000000..c7df8aad6613
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -0,0 +1,430 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DPU_ENCODER_PHYS_H__
+#define __DPU_ENCODER_PHYS_H__
+
+#include <linux/jiffies.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_encoder.h"
+
+#define DPU_ENCODER_NAME_MAX	16
+
+/* wait for at most 2 vsync for lowest refresh rate (24hz) */
+#define KICKOFF_TIMEOUT_MS		84
+#define KICKOFF_TIMEOUT_JIFFIES		msecs_to_jiffies(KICKOFF_TIMEOUT_MS)
+
+/**
+ * enum dpu_enc_split_role - Role this physical encoder will play in a
+ *	split-panel configuration, where one panel is master, and others slaves.
+ *	Masters have extra responsibilities, like managing the VBLANK IRQ.
+ * @ENC_ROLE_SOLO:	This is the one and only panel. This encoder is master.
+ * @ENC_ROLE_MASTER:	This encoder is the master of a split panel config.
+ * @ENC_ROLE_SLAVE:	This encoder is not the master of a split panel config.
+ */
+enum dpu_enc_split_role {
+	ENC_ROLE_SOLO,
+	ENC_ROLE_MASTER,
+	ENC_ROLE_SLAVE,
+};
+
+/**
+ * enum dpu_enc_enable_state - current enabled state of the physical encoder
+ * @DPU_ENC_DISABLING:	Encoder transitioning to disable state
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_DISABLED:	Encoder is disabled
+ * @DPU_ENC_ENABLING:	Encoder transitioning to enabled
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_ENABLED:	Encoder is enabled
+ * @DPU_ENC_ERR_NEEDS_HW_RESET:	Encoder is enabled, but requires a hw_reset
+ *				to recover from a previous error
+ */
+enum dpu_enc_enable_state {
+	DPU_ENC_DISABLING,
+	DPU_ENC_DISABLED,
+	DPU_ENC_ENABLING,
+	DPU_ENC_ENABLED,
+	DPU_ENC_ERR_NEEDS_HW_RESET
+};
+
+struct dpu_encoder_phys;
+
+/**
+ * struct dpu_encoder_virt_ops - Interface the containing virtual encoder
+ *	provides for the physical encoders to use to callback.
+ * @handle_vblank_virt:	Notify virtual encoder of vblank IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_underrun_virt: Notify virtual encoder of underrun IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_frame_done:	Notify virtual encoder that this phys encoder
+ *			completes last request frame.
+ */
+struct dpu_encoder_virt_ops {
+	void (*handle_vblank_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_underrun_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_frame_done)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys, u32 event);
+};
+
+/**
+ * struct dpu_encoder_phys_ops - Interface the physical encoders provide to
+ *	the containing virtual encoder.
+ * @late_register:		DRM Call. Add Userspace interfaces, debugfs.
+ * @prepare_commit:		MSM Atomic Call, start of atomic commit sequence
+ * @is_master:			Whether this phys_enc is the current master
+ *				encoder. Can be switched at enable time. Based
+ *				on split_role and current mode (CMD/VID).
+ * @mode_fixup:			DRM Call. Fixup a DRM mode.
+ * @mode_set:			DRM Call. Set a DRM mode.
+ *				This likely caches the mode, for use at enable.
+ * @enable:			DRM Call. Enable a DRM mode.
+ * @disable:			DRM Call. Disable mode.
+ * @atomic_check:		DRM Call. Atomic check new DRM state.
+ * @destroy:			DRM Call. Destroy and release resources.
+ * @get_hw_resources:		Populate the structure with the hardware
+ *				resources that this phys_enc is using.
+ *				Expect no overlap between phys_encs.
+ * @control_vblank_irq		Register/Deregister for VBLANK IRQ
+ * @wait_for_commit_done:	Wait for hardware to have flushed the
+ *				current pending frames to hardware
+ * @wait_for_tx_complete:	Wait for hardware to transfer the pixels
+ *				to the panel
+ * @wait_for_vblank:		Wait for VBLANK, for sub-driver internal use
+ * @prepare_for_kickoff:	Do any work necessary prior to a kickoff
+ *				For CMD encoder, may wait for previous tx done
+ * @handle_post_kickoff:	Do any work necessary post-kickoff work
+ * @trigger_start:		Process start event on physical encoder
+ * @needs_single_flush:		Whether encoder slaves need to be flushed
+ * @setup_misr:		Sets up MISR, enable and disables based on sysfs
+ * @collect_misr:		Collects MISR data on frame update
+ * @hw_reset:			Issue HW recovery such as CTL reset and clear
+ *				DPU_ENC_ERR_NEEDS_HW_RESET state
+ * @irq_control:		Handler to enable/disable all the encoder IRQs
+ * @prepare_idle_pc:		phys encoder can update the vsync_enable status
+ *                              on idle power collapse prepare
+ * @restore:			Restore all the encoder configs.
+ * @get_line_count:		Obtain current vertical line count
+ */
+
+struct dpu_encoder_phys_ops {
+	int (*late_register)(struct dpu_encoder_phys *encoder,
+			struct dentry *debugfs_root);
+	void (*prepare_commit)(struct dpu_encoder_phys *encoder);
+	bool (*is_master)(struct dpu_encoder_phys *encoder);
+	bool (*mode_fixup)(struct dpu_encoder_phys *encoder,
+			const struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+	void (*mode_set)(struct dpu_encoder_phys *encoder,
+			struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+	void (*enable)(struct dpu_encoder_phys *encoder);
+	void (*disable)(struct dpu_encoder_phys *encoder);
+	int (*atomic_check)(struct dpu_encoder_phys *encoder,
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_connector_state *conn_state);
+	void (*destroy)(struct dpu_encoder_phys *encoder);
+	void (*get_hw_resources)(struct dpu_encoder_phys *encoder,
+			struct dpu_encoder_hw_resources *hw_res,
+			struct drm_connector_state *conn_state);
+	int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable);
+	int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_vblank)(struct dpu_encoder_phys *phys_enc);
+	void (*prepare_for_kickoff)(struct dpu_encoder_phys *phys_enc,
+			struct dpu_encoder_kickoff_params *params);
+	void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc);
+	void (*trigger_start)(struct dpu_encoder_phys *phys_enc);
+	bool (*needs_single_flush)(struct dpu_encoder_phys *phys_enc);
+
+	void (*setup_misr)(struct dpu_encoder_phys *phys_encs,
+				bool enable, u32 frame_count);
+	u32 (*collect_misr)(struct dpu_encoder_phys *phys_enc);
+	void (*hw_reset)(struct dpu_encoder_phys *phys_enc);
+	void (*irq_control)(struct dpu_encoder_phys *phys, bool enable);
+	void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc);
+	void (*restore)(struct dpu_encoder_phys *phys);
+	int (*get_line_count)(struct dpu_encoder_phys *phys);
+};
+
+/**
+ * enum dpu_intr_idx - dpu encoder interrupt index
+ * @INTR_IDX_VSYNC:    Vsync interrupt for video mode panel
+ * @INTR_IDX_PINGPONG: Pingpong done unterrupt for cmd mode panel
+ * @INTR_IDX_UNDERRUN: Underrun unterrupt for video and cmd mode panel
+ * @INTR_IDX_RDPTR:    Readpointer done unterrupt for cmd mode panel
+ */
+enum dpu_intr_idx {
+	INTR_IDX_VSYNC,
+	INTR_IDX_PINGPONG,
+	INTR_IDX_UNDERRUN,
+	INTR_IDX_CTL_START,
+	INTR_IDX_RDPTR,
+	INTR_IDX_MAX,
+};
+
+/**
+ * dpu_encoder_irq - tracking structure for interrupts
+ * @name:		string name of interrupt
+ * @intr_type:		Encoder interrupt type
+ * @intr_idx:		Encoder interrupt enumeration
+ * @hw_idx:		HW Block ID
+ * @irq_idx:		IRQ interface lookup index from DPU IRQ framework
+ *			will be -EINVAL if IRQ is not registered
+ * @irq_cb:		interrupt callback
+ */
+struct dpu_encoder_irq {
+	const char *name;
+	enum dpu_intr_type intr_type;
+	enum dpu_intr_idx intr_idx;
+	int hw_idx;
+	int irq_idx;
+	struct dpu_irq_callback cb;
+};
+
+/**
+ * struct dpu_encoder_phys - physical encoder that drives a single INTF block
+ *	tied to a specific panel / sub-panel. Abstract type, sub-classed by
+ *	phys_vid or phys_cmd for video mode or command mode encs respectively.
+ * @parent:		Pointer to the containing virtual encoder
+ * @connector:		If a mode is set, cached pointer to the active connector
+ * @ops:		Operations exposed to the virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @hw_mdptop:		Hardware interface to the top registers
+ * @hw_ctl:		Hardware interface to the ctl registers
+ * @hw_cdm:		Hardware interface to the cdm registers
+ * @cdm_cfg:		Chroma-down hardware configuration
+ * @hw_pp:		Hardware interface to the ping pong registers
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @cached_mode:	DRM mode cached at mode_set time, acted on in enable
+ * @enabled:		Whether the encoder has enabled and running a mode
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_mode:		Interface mode
+ * @intf_idx:		Interface index on dpu hardware
+ * @topology_name:	topology selected for the display
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @enable_state:	Enable state tracking
+ * @vblank_refcount:	Reference count of vblank request
+ * @vsync_cnt:		Vsync count for the physical encoder
+ * @underrun_cnt:	Underrun count for the physical encoder
+ * @pending_kickoff_cnt:	Atomic counter tracking the number of kickoffs
+ *				vs. the number of done/vblank irqs. Should hover
+ *				between 0-2 Incremented when a new kickoff is
+ *				scheduled. Decremented in irq handler
+ * @pending_ctlstart_cnt:	Atomic counter tracking the number of ctl start
+ *                              pending.
+ * @pending_kickoff_wq:		Wait queue for blocking until kickoff completes
+ * @irq:			IRQ tracking structures
+ */
+struct dpu_encoder_phys {
+	struct drm_encoder *parent;
+	struct drm_connector *connector;
+	struct dpu_encoder_phys_ops ops;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct dpu_hw_ctl *hw_ctl;
+	struct dpu_hw_cdm *hw_cdm;
+	struct dpu_hw_cdm_cfg cdm_cfg;
+	struct dpu_hw_pingpong *hw_pp;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode cached_mode;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf_mode intf_mode;
+	enum dpu_intf intf_idx;
+	enum dpu_rm_topology_name topology_name;
+	spinlock_t *enc_spinlock;
+	enum dpu_enc_enable_state enable_state;
+	atomic_t vblank_refcount;
+	atomic_t vsync_cnt;
+	atomic_t underrun_cnt;
+	atomic_t pending_ctlstart_cnt;
+	atomic_t pending_kickoff_cnt;
+	wait_queue_head_t pending_kickoff_wq;
+	struct dpu_encoder_irq irq[INTR_IDX_MAX];
+};
+
+static inline int dpu_encoder_phys_inc_pending(struct dpu_encoder_phys *phys)
+{
+	atomic_inc_return(&phys->pending_ctlstart_cnt);
+	return atomic_inc_return(&phys->pending_kickoff_cnt);
+}
+
+/**
+ * struct dpu_encoder_phys_vid - sub-class of dpu_encoder_phys to handle video
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @hw_intf:	Hardware interface to the intf registers
+ * @timing_params: Current timing parameter
+ */
+struct dpu_encoder_phys_vid {
+	struct dpu_encoder_phys base;
+	struct dpu_hw_intf *hw_intf;
+	struct intf_timing_params timing_params;
+};
+
+/**
+ * struct dpu_encoder_phys_cmd - sub-class of dpu_encoder_phys to handle command
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @intf_idx:	Intf Block index used by this phys encoder
+ * @stream_sel:	Stream selection for multi-stream interfaces
+ * @serialize_wait4pp:	serialize wait4pp feature waits for pp_done interrupt
+ *			after ctl_start instead of before next frame kickoff
+ * @pp_timeout_report_cnt: number of pingpong done irq timeout errors
+ * @pending_vblank_cnt: Atomic counter tracking pending wait for VBLANK
+ * @pending_vblank_wq: Wait queue for blocking until VBLANK received
+ */
+struct dpu_encoder_phys_cmd {
+	struct dpu_encoder_phys base;
+	int stream_sel;
+	bool serialize_wait4pp;
+	int pp_timeout_report_cnt;
+	atomic_t pending_vblank_cnt;
+	wait_queue_head_t pending_vblank_wq;
+};
+
+/**
+ * struct dpu_enc_phys_init_params - initialization parameters for phys encs
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @parent:		Pointer to the containing virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_idx:		Interface index this phys_enc will control
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ */
+struct dpu_enc_phys_init_params {
+	struct dpu_kms *dpu_kms;
+	struct drm_encoder *parent;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf intf_idx;
+	spinlock_t *enc_spinlock;
+};
+
+/**
+ * dpu_encoder_wait_info - container for passing arguments to irq wait functions
+ * @wq: wait queue structure
+ * @atomic_cnt: wait until atomic_cnt equals zero
+ * @timeout_ms: timeout value in milliseconds
+ */
+struct dpu_encoder_wait_info {
+	wait_queue_head_t *wq;
+	atomic_t *atomic_cnt;
+	s64 timeout_ms;
+};
+
+/**
+ * dpu_encoder_phys_vid_init - Construct a new video mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_phys_cmd_init - Construct a new command mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_helper_trigger_start - control start helper function
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl_start triggering.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc);
+
+/**
+ * dpu_encoder_helper_hw_reset - issue ctl hw reset
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl hw reset. If state is currently
+ *	DPU_ENC_ERR_NEEDS_HW_RESET, it is set back to DPU_ENC_ENABLED.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc);
+
+static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc || phys_enc->enable_state == DPU_ENC_DISABLING)
+		return BLEND_3D_NONE;
+
+	if (phys_enc->split_role == ENC_ROLE_SOLO &&
+	    phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE)
+		return BLEND_3D_H_ROW_INT;
+
+	return BLEND_3D_NONE;
+}
+
+/**
+ * dpu_encoder_helper_split_config - split display configuration helper function
+ *	This helper function may be used by physical encoders to configure
+ *	the split display related registers.
+ * @phys_enc: Pointer to physical encoder structure
+ * @interface: enum dpu_intf setting
+ */
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface);
+
+/**
+ * dpu_encoder_helper_report_irq_timeout - utility to report error that irq has
+ *	timed out, including reporting frame error event to crtc and debug dump
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: Failing interrupt index
+ */
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_wait_for_irq - utility to wait on an irq.
+ *	note: will call dpu_encoder_helper_wait_for_irq on timeout
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @wait_info: wait info struct
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx,
+		struct dpu_encoder_wait_info *wait_info);
+
+/**
+ * dpu_encoder_helper_register_irq - register and enable an irq
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_unregister_irq - unregister and disable an irq
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+#endif /* __dpu_encoder_phys_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
new file mode 100644
index 000000000000..3084675ed425
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -0,0 +1,905 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+
+#define DPU_DEBUG_CMDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_CMDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_cmd(x) \
+	container_of(x, struct dpu_encoder_phys_cmd, base)
+
+#define PP_TIMEOUT_MAX_TRIALS	10
+
+/*
+ * Tearcheck sync start and continue thresholds are empirically found
+ * based on common panels In the future, may want to allow panels to override
+ * these default values
+ */
+#define DEFAULT_TEARCHECK_SYNC_THRESH_START	4
+#define DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE	4
+
+#define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000
+
+static inline int _dpu_encoder_phys_cmd_get_idle_timeout(
+		struct dpu_encoder_phys_cmd *cmd_enc)
+{
+	return KICKOFF_TIMEOUT_MS;
+}
+
+static inline bool dpu_encoder_phys_cmd_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false;
+}
+
+static bool dpu_encoder_phys_cmd_mode_fixup(
+		struct dpu_encoder_phys *phys_enc,
+		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");
+	return true;
+}
+
+static void _dpu_encoder_phys_cmd_update_intf_cfg(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	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)
+		return;
+
+	intf_cfg.intf = phys_enc->intf_idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD;
+	intf_cfg.stream_sel = cmd_enc->stream_sel;
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+	ctl->ops.setup_intf_cfg(ctl, &intf_cfg);
+}
+
+static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	unsigned long lock_flags;
+	int new_cnt;
+	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("pp_done_irq");
+	/* notify all synchronous clients first, then asynchronous clients */
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(phys_enc->parent,
+				phys_enc, event);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	trace_dpu_enc_phys_cmd_pp_tx_done(DRMID(phys_enc->parent),
+					  phys_enc->hw_pp->idx - PINGPONG_0,
+					  new_cnt, event);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("pp_done_irq");
+}
+
+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)
+		return;
+
+	DPU_ATRACE_BEGIN("rd_ptr_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+			phys_enc);
+
+	atomic_add_unless(&cmd_enc->pending_vblank_cnt, -1, 0);
+	wake_up_all(&cmd_enc->pending_vblank_wq);
+	DPU_ATRACE_END("rd_ptr_irq");
+}
+
+static void dpu_encoder_phys_cmd_ctl_start_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_ctl)
+		return;
+
+	DPU_ATRACE_BEGIN("ctl_start_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
+
+	/* Signal any waiting ctl start interrupt */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("ctl_start_irq");
+}
+
+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);
+}
+
+static void _dpu_encoder_phys_cmd_setup_irq_hw_idx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_irq *irq;
+
+	irq = &phys_enc->irq[INTR_IDX_CTL_START];
+	irq->hw_idx = phys_enc->hw_ctl->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_PINGPONG];
+	irq->hw_idx = phys_enc->hw_pp->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_RDPTR];
+	irq->hw_idx = phys_enc->hw_pp->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->hw_idx = phys_enc->intf_idx;
+	irq->irq_idx = -EINVAL;
+}
+
+static void dpu_encoder_phys_cmd_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_rm *rm = &phys_enc->dpu_kms->rm;
+	struct dpu_rm_hw_iter iter;
+	int i, instance;
+
+	if (!phys_enc || !mode || !adj_mode) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+	phys_enc->cached_mode = *adj_mode;
+	DPU_DEBUG_CMDENC(cmd_enc, "caching mode:\n");
+	drm_mode_debug_printmodeline(adj_mode);
+
+	instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0;
+
+	/* Retrieve previously allocated HW Resources. Shouldn't fail */
+	dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL);
+	for (i = 0; i <= instance; i++) {
+		if (dpu_rm_get_hw(rm, &iter))
+			phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw;
+	}
+
+	if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) {
+		DPU_ERROR_CMDENC(cmd_enc, "failed to init ctl: %ld\n",
+				PTR_ERR(phys_enc->hw_ctl));
+		phys_enc->hw_ctl = NULL;
+		return;
+	}
+
+	_dpu_encoder_phys_cmd_setup_irq_hw_idx(phys_enc);
+}
+
+static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	bool do_log = false;
+
+	if (!phys_enc || !phys_enc->hw_pp || !phys_enc->hw_ctl)
+		return -EINVAL;
+
+	cmd_enc->pp_timeout_report_cnt++;
+	if (cmd_enc->pp_timeout_report_cnt == PP_TIMEOUT_MAX_TRIALS) {
+		frame_event |= DPU_ENCODER_FRAME_EVENT_PANEL_DEAD;
+		do_log = true;
+	} else if (cmd_enc->pp_timeout_report_cnt == 1) {
+		do_log = true;
+	}
+
+	trace_dpu_enc_phys_cmd_pdone_timeout(DRMID(phys_enc->parent),
+		     phys_enc->hw_pp->idx - PINGPONG_0,
+		     cmd_enc->pp_timeout_report_cnt,
+		     atomic_read(&phys_enc->pending_kickoff_cnt),
+		     frame_event);
+
+	/* to avoid flooding, only log first time, and "dead" time */
+	if (do_log) {
+		DRM_ERROR("id:%d pp:%d kickoff timeout %d cnt %d koff_cnt %d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0,
+			  phys_enc->hw_ctl->idx - CTL_0,
+			  cmd_enc->pp_timeout_report_cnt,
+			  atomic_read(&phys_enc->pending_kickoff_cnt));
+
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_RDPTR);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+
+	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+
+	/* request a ctl reset before the next kickoff */
+	phys_enc->enable_state = DPU_ENC_ERR_NEEDS_HW_RESET;
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc, frame_event);
+
+	return -ETIMEDOUT;
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_idle(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	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;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_PINGPONG,
+			&wait_info);
+	if (ret == -ETIMEDOUT)
+		_dpu_encoder_phys_cmd_handle_ppdone_timeout(phys_enc);
+	else if (!ret)
+		cmd_enc->pp_timeout_report_cnt = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	int refcount;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      enable ? "true" : "false", refcount);
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_RDPTR);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_encoder_helper_unregister_irq(phys_enc,
+				INTR_IDX_RDPTR);
+
+end:
+	if (ret) {
+		DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0, ret,
+			  enable ? "true" : "false", refcount);
+	}
+
+	return ret;
+}
+
+static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	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));
+
+	if (enable) {
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_PINGPONG);
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, true);
+
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_encoder_helper_register_irq(phys_enc,
+					INTR_IDX_CTL_START);
+	} else {
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_encoder_helper_unregister_irq(phys_enc,
+					INTR_IDX_CTL_START);
+
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, false);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_PINGPONG);
+	}
+}
+
+static void dpu_encoder_phys_cmd_tearcheck_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_tear_check tc_cfg = { 0 };
+	struct drm_display_mode *mode;
+	bool tc_enable = true;
+	u32 vsync_hz;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	mode = &phys_enc->cached_mode;
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (!phys_enc->hw_pp->ops.setup_tearcheck ||
+		!phys_enc->hw_pp->ops.enable_tearcheck) {
+		DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
+		return;
+	}
+
+	dpu_kms = phys_enc->dpu_kms;
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	/*
+	 * TE default: dsi byte clock calculated base on 70 fps;
+	 * around 14 ms to complete a kickoff cycle if te disabled;
+	 * vclk_line base on 60 fps; write is faster than read;
+	 * init == start == rdptr;
+	 *
+	 * vsync_count is ratio of MDP VSYNC clock frequency to LCD panel
+	 * frequency divided by the no. of rows (lines) in the LCDpanel.
+	 */
+	vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync");
+	if (vsync_hz <= 0) {
+		DPU_DEBUG_CMDENC(cmd_enc, "invalid - vsync_hz %u\n",
+				 vsync_hz);
+		return;
+	}
+
+	tc_cfg.vsync_count = vsync_hz / (mode->vtotal * mode->vrefresh);
+
+	/* enable external TE after kickoff to avoid premature autorefresh */
+	tc_cfg.hw_vsync_mode = 0;
+
+	/*
+	 * By setting sync_cfg_height to near max register value, we essentially
+	 * disable dpu hw generated TE signal, since hw TE will arrive first.
+	 * Only caveat is if due to error, we hit wrap-around.
+	 */
+	tc_cfg.sync_cfg_height = 0xFFF0;
+	tc_cfg.vsync_init_val = mode->vdisplay;
+	tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START;
+	tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE;
+	tc_cfg.start_pos = mode->vdisplay;
+	tc_cfg.rd_ptr_irq = mode->vdisplay + 1;
+
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d vsync_clk_speed_hz %u vtotal %u vrefresh %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, vsync_hz,
+		mode->vtotal, mode->vrefresh);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d enable %u start_pos %u rd_ptr_irq %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_enable, tc_cfg.start_pos,
+		tc_cfg.rd_ptr_irq);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d hw_vsync_mode %u vsync_count %u vsync_init_val %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.hw_vsync_mode,
+		tc_cfg.vsync_count, tc_cfg.vsync_init_val);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d cfgheight %u thresh_start %u thresh_cont %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.sync_cfg_height,
+		tc_cfg.sync_threshold_start, tc_cfg.sync_threshold_continue);
+
+	phys_enc->hw_pp->ops.setup_tearcheck(phys_enc->hw_pp, &tc_cfg);
+	phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, tc_enable);
+}
+
+static void _dpu_encoder_phys_cmd_pingpong_config(
+		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_ctl || !phys_enc->hw_pp
+			|| !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d, enabling mode:\n",
+			phys_enc->hw_pp->idx - PINGPONG_0);
+	drm_mode_debug_printmodeline(&phys_enc->cached_mode);
+
+	_dpu_encoder_phys_cmd_update_intf_cfg(phys_enc);
+	dpu_encoder_phys_cmd_tearcheck_config(phys_enc);
+}
+
+static bool dpu_encoder_phys_cmd_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	/**
+	 * we do separate flush for each CTL and let
+	 * CTL_START synchronize them
+	 */
+	return false;
+}
+
+static void dpu_encoder_phys_cmd_enable_helper(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	u32 flush_mask = 0;
+
+	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	dpu_encoder_helper_split_config(phys_enc, phys_enc->intf_idx);
+
+	_dpu_encoder_phys_cmd_pingpong_config(phys_enc);
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl = phys_enc->hw_ctl;
+	ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->intf_idx);
+	ctl->ops.update_pending_flush(ctl, flush_mask);
+
+skip_flush:
+	return;
+}
+
+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) {
+		DPU_ERROR("invalid phys encoder\n");
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (phys_enc->enable_state == DPU_ENC_ENABLED) {
+		DPU_ERROR("already enabled\n");
+		return;
+	}
+
+	dpu_encoder_phys_cmd_enable_helper(phys_enc);
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+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)
+		return;
+
+	trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable);
+	phys_enc->hw_pp->ops.connect_external_te(phys_enc->hw_pp, enable);
+}
+
+static void dpu_encoder_phys_cmd_prepare_idle_pc(
+		struct dpu_encoder_phys *phys_enc)
+{
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, false);
+}
+
+static int dpu_encoder_phys_cmd_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_pingpong *hw_pp;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return -EINVAL;
+
+	hw_pp = phys_enc->hw_pp;
+	if (!hw_pp->ops.get_line_count)
+		return -EINVAL;
+
+	return hw_pp->ops.get_line_count(hw_pp);
+}
+
+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) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d state:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      phys_enc->enable_state);
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR_CMDENC(cmd_enc, "already disabled\n");
+		return;
+	}
+
+	if (phys_enc->hw_pp->ops.enable_tearcheck)
+		phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, false);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+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);
+}
+
+static void dpu_encoder_phys_cmd_get_hw_resources(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	if ((phys_enc->intf_idx - INTF_0) >= INTF_MAX) {
+		DPU_ERROR("invalid intf idx:%d\n", phys_enc->intf_idx);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "\n");
+	hw_res->intfs[phys_enc->intf_idx - INTF_0] = INTF_MODE_CMD;
+}
+
+static void dpu_encoder_phys_cmd_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	int ret;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d pending_cnt:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(&phys_enc->pending_kickoff_cnt));
+
+	/*
+	 * Mark kickoff request as outstanding. If there are more than one,
+	 * outstanding, then we have to wait for the previous one to complete
+	 */
+	ret = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (ret) {
+		/* force pending_kickoff_cnt 0 to discard failed kickoff */
+		atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d pp:%d\n",
+			  DRMID(phys_enc->parent), ret,
+			  phys_enc->hw_pp->idx - PINGPONG_0);
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp:%d pending_cnt %d\n",
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(&phys_enc->pending_kickoff_cnt));
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	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;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_CTL_START,
+			&wait_info);
+	if (ret == -ETIMEDOUT) {
+		DPU_ERROR_CMDENC(cmd_enc, "ctl start interrupt wait failed\n");
+		ret = -EINVAL;
+	} else if (!ret)
+		ret = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_tx_complete(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	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",
+			  DRMID(phys_enc->parent), rc,
+			  phys_enc->intf_idx - INTF_0);
+	}
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_commit_done(
+		struct dpu_encoder_phys *phys_enc)
+{
+	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 */
+	if (dpu_encoder_phys_cmd_is_master(phys_enc))
+		rc = _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc);
+
+	/* required for both controllers */
+	if (!rc && cmd_enc->serialize_wait4pp)
+		dpu_encoder_phys_cmd_prepare_for_kickoff(phys_enc, NULL);
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc = 0;
+	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 */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return rc;
+
+	wait_info.wq = &cmd_enc->pending_vblank_wq;
+	wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt;
+	wait_info.timeout_ms = _dpu_encoder_phys_cmd_get_idle_timeout(cmd_enc);
+
+	atomic_inc(&cmd_enc->pending_vblank_cnt);
+
+	rc = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_RDPTR,
+			&wait_info);
+
+	return rc;
+}
+
+static void dpu_encoder_phys_cmd_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return;
+
+	/**
+	 * re-enable external TE, either for the first time after enabling
+	 * or if disabled for Autorefresh
+	 */
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, true);
+}
+
+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);
+}
+
+static void dpu_encoder_phys_cmd_init_ops(
+		struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_cmd_is_master;
+	ops->mode_set = dpu_encoder_phys_cmd_mode_set;
+	ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup;
+	ops->enable = dpu_encoder_phys_cmd_enable;
+	ops->disable = dpu_encoder_phys_cmd_disable;
+	ops->destroy = dpu_encoder_phys_cmd_destroy;
+	ops->get_hw_resources = dpu_encoder_phys_cmd_get_hw_resources;
+	ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done;
+	ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff;
+	ops->wait_for_tx_complete = dpu_encoder_phys_cmd_wait_for_tx_complete;
+	ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank;
+	ops->trigger_start = dpu_encoder_phys_cmd_trigger_start;
+	ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush;
+	ops->hw_reset = dpu_encoder_helper_hw_reset;
+	ops->irq_control = dpu_encoder_phys_cmd_irq_control;
+	ops->restore = dpu_encoder_phys_cmd_enable_helper;
+	ops->prepare_idle_pc = dpu_encoder_phys_cmd_prepare_idle_pc;
+	ops->handle_post_kickoff = dpu_encoder_phys_cmd_handle_post_kickoff;
+	ops->get_line_count = dpu_encoder_phys_cmd_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_cmd *cmd_enc = NULL;
+	struct dpu_hw_mdp *hw_mdp;
+	struct dpu_encoder_irq *irq;
+	int i, ret = 0;
+
+	DPU_DEBUG("intf %d\n", p->intf_idx - INTF_0);
+
+	cmd_enc = kzalloc(sizeof(*cmd_enc), GFP_KERNEL);
+	if (!cmd_enc) {
+		ret = -ENOMEM;
+		DPU_ERROR("failed to allocate\n");
+		goto fail;
+	}
+	phys_enc = &cmd_enc->base;
+
+	hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm);
+	if (IS_ERR_OR_NULL(hw_mdp)) {
+		ret = PTR_ERR(hw_mdp);
+		DPU_ERROR("failed to get mdptop\n");
+		goto fail_mdp_init;
+	}
+	phys_enc->hw_mdptop = hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	dpu_encoder_phys_cmd_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_CMD;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	cmd_enc->stream_sel = 0;
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+	for (i = 0; i < INTR_IDX_MAX; i++) {
+		irq = &phys_enc->irq[i];
+		INIT_LIST_HEAD(&irq->cb.list);
+		irq->irq_idx = -EINVAL;
+		irq->hw_idx = -EINVAL;
+		irq->cb.arg = phys_enc;
+	}
+
+	irq = &phys_enc->irq[INTR_IDX_CTL_START];
+	irq->name = "ctl_start";
+	irq->intr_type = DPU_IRQ_TYPE_CTL_START;
+	irq->intr_idx = INTR_IDX_CTL_START;
+	irq->cb.func = dpu_encoder_phys_cmd_ctl_start_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_PINGPONG];
+	irq->name = "pp_done";
+	irq->intr_type = DPU_IRQ_TYPE_PING_PONG_COMP;
+	irq->intr_idx = INTR_IDX_PINGPONG;
+	irq->cb.func = dpu_encoder_phys_cmd_pp_tx_done_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_RDPTR];
+	irq->name = "pp_rd_ptr";
+	irq->intr_type = DPU_IRQ_TYPE_PING_PONG_RD_PTR;
+	irq->intr_idx = INTR_IDX_RDPTR;
+	irq->cb.func = dpu_encoder_phys_cmd_pp_rd_ptr_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->name = "underrun";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN;
+	irq->intr_idx = INTR_IDX_UNDERRUN;
+	irq->cb.func = dpu_encoder_phys_cmd_underrun_irq;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	atomic_set(&phys_enc->pending_ctlstart_cnt, 0);
+	atomic_set(&cmd_enc->pending_vblank_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	init_waitqueue_head(&cmd_enc->pending_vblank_wq);
+
+	DPU_DEBUG_CMDENC(cmd_enc, "created\n");
+
+	return phys_enc;
+
+fail_mdp_init:
+	kfree(cmd_enc);
+fail:
+	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
new file mode 100644
index 000000000000..14fc7c2a6bb7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -0,0 +1,922 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+
+#define DPU_DEBUG_VIDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_VIDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_vid(x) \
+	container_of(x, struct dpu_encoder_phys_vid, base)
+
+static bool dpu_encoder_phys_vid_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	bool ret = false;
+
+	if (phys_enc->split_role != ENC_ROLE_SLAVE)
+		ret = true;
+
+	return ret;
+}
+
+static void drm_mode_to_intf_timing_params(
+		const struct dpu_encoder_phys_vid *vid_enc,
+		const struct drm_display_mode *mode,
+		struct intf_timing_params *timing)
+{
+	memset(timing, 0, sizeof(*timing));
+
+	if ((mode->htotal < mode->hsync_end)
+			|| (mode->hsync_start < mode->hdisplay)
+			|| (mode->vtotal < mode->vsync_end)
+			|| (mode->vsync_start < mode->vdisplay)
+			|| (mode->hsync_end < mode->hsync_start)
+			|| (mode->vsync_end < mode->vsync_start)) {
+		DPU_ERROR(
+		    "invalid params - hstart:%d,hend:%d,htot:%d,hdisplay:%d\n",
+				mode->hsync_start, mode->hsync_end,
+				mode->htotal, mode->hdisplay);
+		DPU_ERROR("vstart:%d,vend:%d,vtot:%d,vdisplay:%d\n",
+				mode->vsync_start, mode->vsync_end,
+				mode->vtotal, mode->vdisplay);
+		return;
+	}
+
+	/*
+	 * https://www.kernel.org/doc/htmldocs/drm/ch02s05.html
+	 *  Active Region      Front Porch   Sync   Back Porch
+	 * <-----------------><------------><-----><----------->
+	 * <- [hv]display --->
+	 * <--------- [hv]sync_start ------>
+	 * <----------------- [hv]sync_end ------->
+	 * <---------------------------- [hv]total ------------->
+	 */
+	timing->width = mode->hdisplay;	/* active width */
+	timing->height = mode->vdisplay;	/* active height */
+	timing->xres = timing->width;
+	timing->yres = timing->height;
+	timing->h_back_porch = mode->htotal - mode->hsync_end;
+	timing->h_front_porch = mode->hsync_start - mode->hdisplay;
+	timing->v_back_porch = mode->vtotal - mode->vsync_end;
+	timing->v_front_porch = mode->vsync_start - mode->vdisplay;
+	timing->hsync_pulse_width = mode->hsync_end - mode->hsync_start;
+	timing->vsync_pulse_width = mode->vsync_end - mode->vsync_start;
+	timing->hsync_polarity = (mode->flags & DRM_MODE_FLAG_NHSYNC) ? 1 : 0;
+	timing->vsync_polarity = (mode->flags & DRM_MODE_FLAG_NVSYNC) ? 1 : 0;
+	timing->border_clr = 0;
+	timing->underflow_clr = 0xff;
+	timing->hsync_skew = mode->hskew;
+
+	/* DSI controller cannot handle active-low sync signals. */
+	if (vid_enc->hw_intf->cap->type == INTF_DSI) {
+		timing->hsync_polarity = 0;
+		timing->vsync_polarity = 0;
+	}
+
+	/*
+	 * For edp only:
+	 * DISPLAY_V_START = (VBP * HCYCLE) + HBP
+	 * DISPLAY_V_END = (VBP + VACTIVE) * HCYCLE - 1 - HFP
+	 */
+	/*
+	 * if (vid_enc->hw->cap->type == INTF_EDP) {
+	 * display_v_start += mode->htotal - mode->hsync_start;
+	 * display_v_end -= mode->hsync_start - mode->hdisplay;
+	 * }
+	 */
+}
+
+static inline u32 get_horizontal_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->xres;
+	u32 inactive =
+	    timing->h_back_porch + timing->h_front_porch +
+	    timing->hsync_pulse_width;
+	return active + inactive;
+}
+
+static inline u32 get_vertical_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->yres;
+	u32 inactive =
+	    timing->v_back_porch + timing->v_front_porch +
+	    timing->vsync_pulse_width;
+	return active + inactive;
+}
+
+/*
+ * programmable_fetch_get_num_lines:
+ *	Number of fetch lines in vertical front porch
+ * @timing: Pointer to the intf timing information for the requested mode
+ *
+ * Returns the number of fetch lines in vertical front porch at which mdp
+ * can start fetching the next frame.
+ *
+ * Number of needed prefetch lines is anything that cannot be absorbed in the
+ * start of frame time (back porch + vsync pulse width).
+ *
+ * Some panels have very large VFP, however we only need a total number of
+ * lines based on the chip worst case latencies.
+ */
+static u32 programmable_fetch_get_num_lines(
+		struct dpu_encoder_phys_vid *vid_enc,
+		const struct intf_timing_params *timing)
+{
+	u32 worst_case_needed_lines =
+	    vid_enc->hw_intf->cap->prog_fetch_lines_worst_case;
+	u32 start_of_frame_lines =
+	    timing->v_back_porch + timing->vsync_pulse_width;
+	u32 needed_vfp_lines = worst_case_needed_lines - start_of_frame_lines;
+	u32 actual_vfp_lines = 0;
+
+	/* Fetch must be outside active lines, otherwise undefined. */
+	if (start_of_frame_lines >= worst_case_needed_lines) {
+		DPU_DEBUG_VIDENC(vid_enc,
+				"prog fetch is not needed, large vbp+vsw\n");
+		actual_vfp_lines = 0;
+	} else if (timing->v_front_porch < needed_vfp_lines) {
+		/* Warn fetch needed, but not enough porch in panel config */
+		pr_warn_once
+			("low vbp+vfp may lead to perf issues in some cases\n");
+		DPU_DEBUG_VIDENC(vid_enc,
+				"less vfp than fetch req, using entire vfp\n");
+		actual_vfp_lines = timing->v_front_porch;
+	} else {
+		DPU_DEBUG_VIDENC(vid_enc, "room in vfp for needed prefetch\n");
+		actual_vfp_lines = needed_vfp_lines;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc,
+		"v_front_porch %u v_back_porch %u vsync_pulse_width %u\n",
+		timing->v_front_porch, timing->v_back_porch,
+		timing->vsync_pulse_width);
+	DPU_DEBUG_VIDENC(vid_enc,
+		"wc_lines %u needed_vfp_lines %u actual_vfp_lines %u\n",
+		worst_case_needed_lines, needed_vfp_lines, actual_vfp_lines);
+
+	return actual_vfp_lines;
+}
+
+/*
+ * programmable_fetch_config: Programs HW to prefetch lines by offsetting
+ *	the start of fetch into the vertical front porch for cases where the
+ *	vsync pulse width and vertical back porch time is insufficient
+ *
+ *	Gets # of lines to pre-fetch, then calculate VSYNC counter value.
+ *	HW layer requires VSYNC counter of first pixel of tgt VFP line.
+ *
+ * @timing: Pointer to the intf timing information for the requested mode
+ */
+static void programmable_fetch_config(struct dpu_encoder_phys *phys_enc,
+				      const struct intf_timing_params *timing)
+{
+	struct dpu_encoder_phys_vid *vid_enc =
+		to_dpu_encoder_phys_vid(phys_enc);
+	struct intf_prog_fetch f = { 0 };
+	u32 vfp_fetch_lines = 0;
+	u32 horiz_total = 0;
+	u32 vert_total = 0;
+	u32 vfp_fetch_start_vsync_counter = 0;
+	unsigned long lock_flags;
+
+	if (WARN_ON_ONCE(!vid_enc->hw_intf->ops.setup_prg_fetch))
+		return;
+
+	vfp_fetch_lines = programmable_fetch_get_num_lines(vid_enc, timing);
+	if (vfp_fetch_lines) {
+		vert_total = get_vertical_total(timing);
+		horiz_total = get_horizontal_total(timing);
+		vfp_fetch_start_vsync_counter =
+		    (vert_total - vfp_fetch_lines) * horiz_total + 1;
+		f.enable = 1;
+		f.fetch_start = vfp_fetch_start_vsync_counter;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc,
+		"vfp_fetch_lines %u vfp_fetch_start_vsync_counter %u\n",
+		vfp_fetch_lines, vfp_fetch_start_vsync_counter);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.setup_prg_fetch(vid_enc->hw_intf, &f);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+}
+
+static bool dpu_encoder_phys_vid_mode_fixup(
+		struct dpu_encoder_phys *phys_enc,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	if (phys_enc)
+		DPU_DEBUG_VIDENC(to_dpu_encoder_phys_vid(phys_enc), "\n");
+
+	/*
+	 * Modifying mode has consequences when the mode comes back to us
+	 */
+	return true;
+}
+
+static void dpu_encoder_phys_vid_setup_timing_engine(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct drm_display_mode mode;
+	struct intf_timing_params timing_params = { 0 };
+	const struct dpu_format *fmt = NULL;
+	u32 fmt_fourcc = DRM_FORMAT_RGB888;
+	unsigned long lock_flags;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	if (!phys_enc || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	mode = phys_enc->cached_mode;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf->ops.setup_timing_gen) {
+		DPU_ERROR("timing engine setup is not supported\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "enabling mode:\n");
+	drm_mode_debug_printmodeline(&mode);
+
+	if (phys_enc->split_role != ENC_ROLE_SOLO) {
+		mode.hdisplay >>= 1;
+		mode.htotal >>= 1;
+		mode.hsync_start >>= 1;
+		mode.hsync_end >>= 1;
+
+		DPU_DEBUG_VIDENC(vid_enc,
+			"split_role %d, halve horizontal %d %d %d %d\n",
+			phys_enc->split_role,
+			mode.hdisplay, mode.htotal,
+			mode.hsync_start, mode.hsync_end);
+	}
+
+	drm_mode_to_intf_timing_params(vid_enc, &mode, &timing_params);
+
+	fmt = dpu_get_dpu_format(fmt_fourcc);
+	DPU_DEBUG_VIDENC(vid_enc, "fmt_fourcc 0x%X\n", fmt_fourcc);
+
+	intf_cfg.intf = vid_enc->hw_intf->idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID;
+	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.setup_timing_gen(vid_enc->hw_intf,
+			&timing_params, fmt);
+	phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	programmable_fetch_config(phys_enc, &timing_params);
+
+	vid_enc->timing_params = timing_params;
+}
+
+static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_hw_ctl *hw_ctl;
+	unsigned long lock_flags;
+	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");
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+				phys_enc);
+
+	old_cnt  = atomic_read(&phys_enc->pending_kickoff_cnt);
+
+	/*
+	 * only decrement the pending flush count if we've actually flushed
+	 * hardware. due to sw irq latency, vblank may have already happened
+	 * 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)
+		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
+
+	if (flush_register == 0)
+		new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt,
+				-1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("vblank_irq");
+}
+
+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);
+}
+
+static bool _dpu_encoder_phys_is_dual_ctl(struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return false;
+
+	if (phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE)
+		return true;
+
+	return false;
+}
+
+static bool dpu_encoder_phys_vid_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc && _dpu_encoder_phys_is_dual_ctl(phys_enc));
+}
+
+static void _dpu_encoder_phys_vid_setup_irq_hw_idx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_irq *irq;
+
+	/*
+	 * Initialize irq->hw_idx only when irq is not registered.
+	 * Prevent invalidating irq->irq_idx as modeset may be
+	 * called many times during dfps.
+	 */
+
+	irq = &phys_enc->irq[INTR_IDX_VSYNC];
+	if (irq->irq_idx < 0)
+		irq->hw_idx = phys_enc->intf_idx;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	if (irq->irq_idx < 0)
+		irq->hw_idx = phys_enc->intf_idx;
+}
+
+static void dpu_encoder_phys_vid_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	struct dpu_rm *rm;
+	struct dpu_rm_hw_iter iter;
+	int i, instance;
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc || !phys_enc->dpu_kms) {
+		DPU_ERROR("invalid encoder/kms\n");
+		return;
+	}
+
+	rm = &phys_enc->dpu_kms->rm;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	if (adj_mode) {
+		phys_enc->cached_mode = *adj_mode;
+		drm_mode_debug_printmodeline(adj_mode);
+		DPU_DEBUG_VIDENC(vid_enc, "caching mode:\n");
+	}
+
+	instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0;
+
+	/* Retrieve previously allocated HW Resources. Shouldn't fail */
+	dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL);
+	for (i = 0; i <= instance; i++) {
+		if (dpu_rm_get_hw(rm, &iter))
+			phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw;
+	}
+	if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) {
+		DPU_ERROR_VIDENC(vid_enc, "failed to init ctl, %ld\n",
+				PTR_ERR(phys_enc->hw_ctl));
+		phys_enc->hw_ctl = NULL;
+		return;
+	}
+
+	_dpu_encoder_phys_vid_setup_irq_hw_idx(phys_enc);
+}
+
+static int dpu_encoder_phys_vid_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	struct dpu_encoder_phys_vid *vid_enc;
+	int refcount;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u enable=%d/%d\n", DRMID(phys_enc->parent), enable,
+		      atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_VSYNC);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_encoder_helper_unregister_irq(phys_enc,
+				INTR_IDX_VSYNC);
+
+end:
+	if (ret) {
+		DRM_ERROR("failed: id:%u intf:%d ret:%d enable:%d refcnt:%d\n",
+			  DRMID(phys_enc->parent),
+			  vid_enc->hw_intf->idx - INTF_0, ret, enable,
+			  refcount);
+	}
+	return ret;
+}
+
+static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct msm_drm_private *priv;
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct dpu_hw_intf *intf;
+	struct dpu_hw_ctl *ctl;
+	u32 flush_mask = 0;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
+			!phys_enc->parent->dev->dev_private) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+	priv = phys_enc->parent->dev->dev_private;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	intf = vid_enc->hw_intf;
+	ctl = phys_enc->hw_ctl;
+	if (!vid_enc->hw_intf || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing))
+		return;
+
+	dpu_encoder_helper_split_config(phys_enc, vid_enc->hw_intf->idx);
+
+	dpu_encoder_phys_vid_setup_timing_engine(phys_enc);
+
+	/*
+	 * For single flush cases (dual-ctl or pp-split), skip setting the
+	 * flush bit for the slave intf, since both intfs use same ctl
+	 * and HW will only flush the master.
+	 */
+	if (dpu_encoder_phys_vid_needs_single_flush(phys_enc) &&
+		!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl->ops.get_bitmask_intf(ctl, &flush_mask, intf->idx);
+	ctl->ops.update_pending_flush(ctl, flush_mask);
+
+skip_flush:
+	DPU_DEBUG_VIDENC(vid_enc, "update pending flush ctl %d flush_mask %x\n",
+		ctl->idx - CTL_0, flush_mask);
+
+	/* ctl_flush & timing engine enable will be triggered by framework */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED)
+		phys_enc->enable_state = DPU_ENC_ENABLING;
+}
+
+static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+	kfree(vid_enc);
+}
+
+static void dpu_encoder_phys_vid_get_hw_resources(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc || !hw_res) {
+		DPU_ERROR("invalid arg(s), enc %d hw_res %d conn_state %d\n",
+				phys_enc != 0, hw_res != 0, conn_state != 0);
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf) {
+		DPU_ERROR("invalid arg(s), hw_intf\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+	hw_res->intfs[vid_enc->hw_intf->idx - INTF_0] = INTF_MODE_VIDEO;
+}
+
+static int _dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc, bool notify)
+{
+	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;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc)) {
+		if (notify && phys_enc->parent_ops->handle_frame_done)
+			phys_enc->parent_ops->handle_frame_done(
+					phys_enc->parent, phys_enc,
+					DPU_ENCODER_FRAME_EVENT_DONE);
+		return 0;
+	}
+
+	/* Wait for kickoff to complete */
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_VSYNC,
+			&wait_info);
+
+	if (ret == -ETIMEDOUT) {
+		dpu_encoder_helper_report_irq_timeout(phys_enc, INTR_IDX_VSYNC);
+	} else if (!ret && notify && phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_DONE);
+
+	return ret;
+}
+
+static int dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, true);
+}
+
+static void dpu_encoder_phys_vid_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct dpu_hw_ctl *ctl;
+	int rc;
+
+	if (!phys_enc || !params) {
+		DPU_ERROR("invalid encoder/parameters\n");
+		return;
+	}
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl || !ctl->ops.wait_reset_status)
+		return;
+
+	/*
+	 * hw supports hardware initiated ctl reset, so before we kickoff a new
+	 * frame, need to check and wait for hw initiated ctl reset completion
+	 */
+	rc = ctl->ops.wait_reset_status(ctl);
+	if (rc) {
+		DPU_ERROR_VIDENC(vid_enc, "ctl %d reset failure: %d\n",
+				ctl->idx, rc);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_VSYNC);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+}
+
+static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct msm_drm_private *priv;
+	struct dpu_encoder_phys_vid *vid_enc;
+	unsigned long lock_flags;
+	int ret;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
+			!phys_enc->parent->dev->dev_private) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+	priv = phys_enc->parent->dev->dev_private;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing))
+		return;
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR("already disabled\n");
+		return;
+	}
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 0);
+	if (dpu_encoder_phys_vid_is_master(phys_enc))
+		dpu_encoder_phys_inc_pending(phys_enc);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/*
+	 * Wait for a vsync so we know the ENABLE=0 latched before
+	 * the (connector) source of the vsync's gets disabled,
+	 * otherwise we end up in a funny state if we re-enable
+	 * before the disable latches, which results that some of
+	 * the settings changes for the new modeset (like new
+	 * scanout buffer) don't latch properly..
+	 */
+	if (dpu_encoder_phys_vid_is_master(phys_enc)) {
+		ret = _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, false);
+		if (ret) {
+			atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+			DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n",
+				  DRMID(phys_enc->parent),
+				  vid_enc->hw_intf->idx - INTF_0, ret);
+		}
+	}
+
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_vid_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	unsigned long lock_flags;
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	DPU_DEBUG_VIDENC(vid_enc, "enable_state %d\n", phys_enc->enable_state);
+
+	/*
+	 * Video mode must flush CTL before enabling timing engine
+	 * Video encoders need to turn on their interfaces now
+	 */
+	if (phys_enc->enable_state == DPU_ENC_ENABLING) {
+		trace_dpu_enc_phys_vid_post_kickoff(DRMID(phys_enc->parent),
+				    vid_enc->hw_intf->idx - INTF_0);
+		spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+		vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 1);
+		spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+		phys_enc->enable_state = DPU_ENC_ENABLED;
+	}
+}
+
+static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	int ret;
+
+	if (!phys_enc)
+		return;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent),
+			    vid_enc->hw_intf->idx - INTF_0,
+			    enable,
+			    atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		ret = dpu_encoder_phys_vid_control_vblank_irq(phys_enc, true);
+		if (ret)
+			return;
+
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN);
+	} else {
+		dpu_encoder_phys_vid_control_vblank_irq(phys_enc, false);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN);
+	}
+}
+
+static void dpu_encoder_phys_vid_setup_misr(struct dpu_encoder_phys *phys_enc,
+						bool enable, u32 frame_count)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	if (vid_enc->hw_intf && vid_enc->hw_intf->ops.setup_misr)
+		vid_enc->hw_intf->ops.setup_misr(vid_enc->hw_intf,
+							enable, frame_count);
+}
+
+static u32 dpu_encoder_phys_vid_collect_misr(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return 0;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	return vid_enc->hw_intf && vid_enc->hw_intf->ops.collect_misr ?
+		vid_enc->hw_intf->ops.collect_misr(vid_enc->hw_intf) : 0;
+}
+
+static int dpu_encoder_phys_vid_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		return -EINVAL;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf || !vid_enc->hw_intf->ops.get_line_count)
+		return -EINVAL;
+
+	return vid_enc->hw_intf->ops.get_line_count(vid_enc->hw_intf);
+}
+
+static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_vid_is_master;
+	ops->mode_set = dpu_encoder_phys_vid_mode_set;
+	ops->mode_fixup = dpu_encoder_phys_vid_mode_fixup;
+	ops->enable = dpu_encoder_phys_vid_enable;
+	ops->disable = dpu_encoder_phys_vid_disable;
+	ops->destroy = dpu_encoder_phys_vid_destroy;
+	ops->get_hw_resources = dpu_encoder_phys_vid_get_hw_resources;
+	ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->irq_control = dpu_encoder_phys_vid_irq_control;
+	ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff;
+	ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff;
+	ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush;
+	ops->setup_misr = dpu_encoder_phys_vid_setup_misr;
+	ops->collect_misr = dpu_encoder_phys_vid_collect_misr;
+	ops->hw_reset = dpu_encoder_helper_hw_reset;
+	ops->get_line_count = dpu_encoder_phys_vid_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_vid *vid_enc = NULL;
+	struct dpu_rm_hw_iter iter;
+	struct dpu_hw_mdp *hw_mdp;
+	struct dpu_encoder_irq *irq;
+	int i, ret = 0;
+
+	if (!p) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	vid_enc = kzalloc(sizeof(*vid_enc), GFP_KERNEL);
+	if (!vid_enc) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	phys_enc = &vid_enc->base;
+
+	hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm);
+	if (IS_ERR_OR_NULL(hw_mdp)) {
+		ret = PTR_ERR(hw_mdp);
+		DPU_ERROR("failed to get mdptop\n");
+		goto fail;
+	}
+	phys_enc->hw_mdptop = hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	/**
+	 * hw_intf resource permanently assigned to this encoder
+	 * Other resources allocated at atomic commit time by use case
+	 */
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_INTF);
+	while (dpu_rm_get_hw(&p->dpu_kms->rm, &iter)) {
+		struct dpu_hw_intf *hw_intf = (struct dpu_hw_intf *)iter.hw;
+
+		if (hw_intf->idx == p->intf_idx) {
+			vid_enc->hw_intf = hw_intf;
+			break;
+		}
+	}
+
+	if (!vid_enc->hw_intf) {
+		ret = -EINVAL;
+		DPU_ERROR("failed to get hw_intf\n");
+		goto fail;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	dpu_encoder_phys_vid_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_VIDEO;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	for (i = 0; i < INTR_IDX_MAX; i++) {
+		irq = &phys_enc->irq[i];
+		INIT_LIST_HEAD(&irq->cb.list);
+		irq->irq_idx = -EINVAL;
+		irq->hw_idx = -EINVAL;
+		irq->cb.arg = phys_enc;
+	}
+
+	irq = &phys_enc->irq[INTR_IDX_VSYNC];
+	irq->name = "vsync_irq";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_VSYNC;
+	irq->intr_idx = INTR_IDX_VSYNC;
+	irq->cb.func = dpu_encoder_phys_vid_vblank_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->name = "underrun";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN;
+	irq->intr_idx = INTR_IDX_UNDERRUN;
+	irq->cb.func = dpu_encoder_phys_vid_underrun_irq;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+
+	DPU_DEBUG_VIDENC(vid_enc, "created intf idx:%d\n", p->intf_idx);
+
+	return phys_enc;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (vid_enc)
+		dpu_encoder_phys_vid_destroy(phys_enc);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
new file mode 100644
index 000000000000..bfcd165e96df
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -0,0 +1,1173 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <uapi/drm/drm_fourcc.h>
+
+#include "msm_media_info.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+
+#define DPU_UBWC_META_MACRO_W_H		16
+#define DPU_UBWC_META_BLOCK_SIZE	256
+#define DPU_UBWC_PLANE_SIZE_ALIGNMENT	4096
+
+#define DPU_TILE_HEIGHT_DEFAULT	1
+#define DPU_TILE_HEIGHT_TILED	4
+#define DPU_TILE_HEIGHT_UBWC	4
+#define DPU_TILE_HEIGHT_NV12	8
+
+#define DPU_MAX_IMG_WIDTH		0x3FFF
+#define DPU_MAX_IMG_HEIGHT		0x3FFF
+
+/**
+ * DPU supported format packing, bpp, and other format
+ * information.
+ * DPU currently only supports interleaved RGB formats
+ * UBWC support for a pixel format is indicated by the flag,
+ * there is additional meta data plane for such formats
+ */
+
+#define INTERLEAVED_RGB_FMT(fmt, a, r, g, b, e0, e1, e2, e3, uc, alpha,   \
+bp, flg, fm, np)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define INTERLEAVED_RGB_FMT_TILED(fmt, a, r, g, b, e0, e1, e2, e3, uc,    \
+alpha, bp, flg, fm, np, th)                                               \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define INTERLEAVED_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, e3,              \
+alpha, chroma, count, bp, flg, fm, np)                                    \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3)},                             \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = count,                                            \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_TILED(fmt, a, r, g, b, e0, e1, chroma,             \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)\
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE_TILED(fmt, a, r, g, b, e0, e1, chroma,       \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define PLANAR_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, alpha, chroma, bp,    \
+flg, fm, np)                                                      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PLANAR,                                 \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), 0 },                               \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 1,                                                \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+/*
+ * struct dpu_media_color_map - maps drm format to media format
+ * @format: DRM base pixel format
+ * @color: Media API color related to DRM format
+ */
+struct dpu_media_color_map {
+	uint32_t format;
+	uint32_t color;
+};
+
+static const struct dpu_format dpu_format_map[] = {
+	INTERLEAVED_RGB_FMT(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR2101010,
+		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_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR2101010,
+		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_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	PSEUDO_YUV_FMT(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV16,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV61,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(VYUY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(UYVY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YUYV,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C1_B_Cb, C0_G_Y, C2_R_Cr,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YVYU,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C2_R_Cr, C0_G_Y, C1_B_Cb,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PLANAR_YUV_FMT(YUV420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+
+	PLANAR_YUV_FMT(YVU420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+};
+
+/*
+ * A5x tile formats tables:
+ * These tables hold the A5x tile formats supported.
+ */
+static const struct dpu_format dpu_format_map_tile[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	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, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	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,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		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_DX,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12),
+
+	PSEUDO_YUV_FMT_TILED(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12),
+};
+
+/*
+ * UBWC formats table:
+ * This table holds the UBWC formats supported.
+ * If a compression ratio needs to be used for this or any other format,
+ * the data will be passed by user-space.
+ */
+static const struct dpu_format dpu_format_map_ubwc[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		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(ABGR2101010,
+		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_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		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_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV |
+				DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+static const struct dpu_format dpu_format_map_p010[] = {
+	PSEUDO_YUV_FMT_LOOSE(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX),
+		DPU_FETCH_LINEAR, 2),
+};
+
+static const struct dpu_format dpu_format_map_p010_ubwc[] = {
+	PSEUDO_YUV_FMT_LOOSE_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX |
+				DPU_FORMAT_FLAG_COMPRESSED),
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+static const struct dpu_format dpu_format_map_tp10_ubwc[] = {
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX |
+				DPU_FORMAT_FLAG_COMPRESSED),
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+/* _dpu_get_v_h_subsample_rate - Get subsample rates for all formats we support
+ *   Note: Not using the drm_format_*_subsampling since we have formats
+ */
+static void _dpu_get_v_h_subsample_rate(
+	enum dpu_chroma_samp_type chroma_sample,
+	uint32_t *v_sample,
+	uint32_t *h_sample)
+{
+	if (!v_sample || !h_sample)
+		return;
+
+	switch (chroma_sample) {
+	case DPU_CHROMA_H2V1:
+		*v_sample = 1;
+		*h_sample = 2;
+		break;
+	case DPU_CHROMA_H1V2:
+		*v_sample = 2;
+		*h_sample = 1;
+		break;
+	case DPU_CHROMA_420:
+		*v_sample = 2;
+		*h_sample = 2;
+		break;
+	default:
+		*v_sample = 1;
+		*h_sample = 1;
+		break;
+	}
+}
+
+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_XBGR8888, 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},
+	};
+	int color_fmt = -1;
+	int i;
+
+	if (fmt->base.pixel_format == DRM_FORMAT_NV12) {
+		if (DPU_FORMAT_IS_DX(fmt)) {
+			if (fmt->unpack_tight)
+				color_fmt = COLOR_FMT_NV12_BPP10_UBWC;
+			else
+				color_fmt = COLOR_FMT_P010_UBWC;
+		} else
+			color_fmt = COLOR_FMT_NV12_UBWC;
+		return color_fmt;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_media_ubwc_map); ++i)
+		if (fmt->base.pixel_format == dpu_media_ubwc_map[i].format) {
+			color_fmt = dpu_media_ubwc_map[i].color;
+			break;
+		}
+	return color_fmt;
+}
+
+static int _dpu_format_get_plane_sizes_ubwc(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout)
+{
+	int i;
+	int color;
+	bool meta = DPU_FORMAT_IS_UBWC(fmt);
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	color = _dpu_format_get_media_color_ubwc(fmt);
+	if (color < 0) {
+		DRM_ERROR("UBWC format not supported for fmt: %4.4s\n",
+			(char *)&fmt->base.pixel_format);
+		return -EINVAL;
+	}
+
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		uint32_t y_sclines, uv_sclines;
+		uint32_t y_meta_scanlines = 0;
+		uint32_t uv_meta_scanlines = 0;
+
+		layout->num_planes = 2;
+		layout->plane_pitch[0] = VENUS_Y_STRIDE(color, width);
+		y_sclines = VENUS_Y_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[1] = VENUS_UV_STRIDE(color, width);
+		uv_sclines = VENUS_UV_SCANLINES(color, height);
+		layout->plane_size[1] = MSM_MEDIA_ALIGN(layout->plane_pitch[1] *
+			uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_Y_META_STRIDE(color, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			y_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[3] = VENUS_UV_META_STRIDE(color, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color, height);
+		layout->plane_size[3] = MSM_MEDIA_ALIGN(layout->plane_pitch[3] *
+			uv_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+	} else {
+		uint32_t rgb_scanlines, rgb_meta_scanlines;
+
+		layout->num_planes = 1;
+
+		layout->plane_pitch[0] = VENUS_RGB_STRIDE(color, width);
+		rgb_scanlines = VENUS_RGB_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			rgb_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_RGB_META_STRIDE(color, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			rgb_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+	}
+
+done:
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int _dpu_format_get_plane_sizes_linear(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	int i;
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	/* Due to memset above, only need to set planes of interest */
+	if (fmt->fetch_planes == DPU_PLANE_INTERLEAVED) {
+		layout->num_planes = 1;
+		layout->plane_size[0] = width * height * layout->format->bpp;
+		layout->plane_pitch[0] = width * layout->format->bpp;
+	} else {
+		uint32_t v_subsample, h_subsample;
+		uint32_t chroma_samp;
+		uint32_t bpp = 1;
+
+		chroma_samp = fmt->chroma_sample;
+		_dpu_get_v_h_subsample_rate(chroma_samp, &v_subsample,
+				&h_subsample);
+
+		if (width % h_subsample || height % v_subsample) {
+			DRM_ERROR("mismatch in subsample vs dimensions\n");
+			return -EINVAL;
+		}
+
+		if ((fmt->base.pixel_format == DRM_FORMAT_NV12) &&
+			(DPU_FORMAT_IS_DX(fmt)))
+			bpp = 2;
+		layout->plane_pitch[0] = width * bpp;
+		layout->plane_pitch[1] = layout->plane_pitch[0] / h_subsample;
+		layout->plane_size[0] = layout->plane_pitch[0] * height;
+		layout->plane_size[1] = layout->plane_pitch[1] *
+				(height / v_subsample);
+
+		if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+			layout->num_planes = 2;
+			layout->plane_size[1] *= 2;
+			layout->plane_pitch[1] *= 2;
+		} else {
+			/* planar */
+			layout->num_planes = 3;
+			layout->plane_size[2] = layout->plane_size[1];
+			layout->plane_pitch[2] = layout->plane_pitch[1];
+		}
+	}
+
+	/*
+	 * linear format: allow user allocated pitches if they are greater than
+	 * the requirement.
+	 * ubwc format: pitch values are computed uniformly across
+	 * all the components based on ubwc specifications.
+	 */
+	for (i = 0; i < layout->num_planes && i < DPU_MAX_PLANES; ++i) {
+		if (pitches && layout->plane_pitch[i] < pitches[i])
+			layout->plane_pitch[i] = pitches[i];
+	}
+
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int dpu_format_get_plane_sizes(
+		const struct dpu_format *fmt,
+		const uint32_t w,
+		const uint32_t h,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	if (!layout || !fmt) {
+		DRM_ERROR("invalid pointer\n");
+		return -EINVAL;
+	}
+
+	if ((w > DPU_MAX_IMG_WIDTH) || (h > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	if (DPU_FORMAT_IS_UBWC(fmt) || DPU_FORMAT_IS_TILE(fmt))
+		return _dpu_format_get_plane_sizes_ubwc(fmt, w, h, layout);
+
+	return _dpu_format_get_plane_sizes_linear(fmt, w, h, layout, pitches);
+}
+
+static int _dpu_format_populate_addrs_ubwc(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t base_addr = 0;
+	bool meta;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid pointers\n");
+		return -EINVAL;
+	}
+
+	if (aspace)
+		base_addr = msm_framebuffer_iova(fb, aspace, 0);
+	if (!base_addr) {
+		DRM_ERROR("failed to retrieve base addr\n");
+		return -EFAULT;
+	}
+
+	meta = DPU_FORMAT_IS_UBWC(layout->format);
+
+	/* Per-format logic for verifying active planes */
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      Y meta     |  ** |    Y bitstream   | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |    Y bitstream  |  ** |  CbCr bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |   Cbcr metadata |  ** |       Y meta     | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  CbCr bitstream |  ** |     CbCr meta    | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/************************************************/
+
+		/* configure Y bitstream plane */
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+
+		/* configure CbCr bitstream plane */
+		layout->plane_addr[1] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2] + layout->plane_size[3];
+
+		if (!meta)
+			goto done;
+
+		/* configure Y metadata plane */
+		layout->plane_addr[2] = base_addr;
+
+		/* configure CbCr metadata plane */
+		layout->plane_addr[3] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2];
+
+	} else {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      RGB meta   |  ** |   RGB bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  RGB bitstream  |  ** |       NONE       | */
+		/* |       data      |  ** |                  | */
+		/* -------------------  ** -------------------- */
+		/*                      ** |     RGB meta     | */
+		/*                      ** |       plane      | */
+		/*                      ** -------------------- */
+		/************************************************/
+
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+		layout->plane_addr[1] = 0;
+
+		if (!meta)
+			goto done;
+
+		layout->plane_addr[2] = base_addr;
+		layout->plane_addr[3] = 0;
+	}
+done:
+	return 0;
+}
+
+static int _dpu_format_populate_addrs_linear(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	unsigned int i;
+
+	/* Can now check the pitches given vs pitches expected */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (layout->plane_pitch[i] > fb->pitches[i]) {
+			DRM_ERROR("plane %u expected pitch %u, fb %u\n",
+				i, layout->plane_pitch[i], fb->pitches[i]);
+			return -EINVAL;
+		}
+	}
+
+	/* Populate addresses for simple formats here */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (aspace)
+			layout->plane_addr[i] =
+				msm_framebuffer_iova(fb, aspace, i);
+		if (!layout->plane_addr[i]) {
+			DRM_ERROR("failed to retrieve base addr\n");
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	int i, ret;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	if ((fb->width > DPU_MAX_IMG_WIDTH) ||
+			(fb->height > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	layout->format = to_dpu_format(msm_framebuffer_format(fb));
+
+	/* Populate the plane sizes etc via get_format */
+	ret = dpu_format_get_plane_sizes(layout->format, fb->width, fb->height,
+			layout, fb->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < DPU_MAX_PLANES; ++i)
+		plane_addr[i] = layout->plane_addr[i];
+
+	/* Populate the addresses given the fb */
+	if (DPU_FORMAT_IS_UBWC(layout->format) ||
+			DPU_FORMAT_IS_TILE(layout->format))
+		ret = _dpu_format_populate_addrs_ubwc(aspace, fb, layout);
+	else
+		ret = _dpu_format_populate_addrs_linear(aspace, fb, layout);
+
+	/* check if anything changed */
+	if (!ret && !memcmp(plane_addr, layout->plane_addr, sizeof(plane_addr)))
+		ret = -EAGAIN;
+
+	return ret;
+}
+
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos)
+{
+	int ret, i, num_base_fmt_planes;
+	const struct dpu_format *fmt;
+	struct dpu_hw_fmt_layout layout;
+	uint32_t bos_total_size = 0;
+
+	if (!msm_fmt || !cmd || !bos) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	fmt = to_dpu_format(msm_fmt);
+	num_base_fmt_planes = drm_format_num_planes(fmt->base.pixel_format);
+
+	ret = dpu_format_get_plane_sizes(fmt, cmd->width, cmd->height,
+			&layout, cmd->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_base_fmt_planes; i++) {
+		if (!bos[i]) {
+			DRM_ERROR("invalid handle for plane %d\n", i);
+			return -EINVAL;
+		}
+		if ((i == 0) || (bos[i] != bos[0]))
+			bos_total_size += bos[i]->size;
+	}
+
+	if (bos_total_size < layout.total_size) {
+		DRM_ERROR("buffers total size too small %u expected %u\n",
+				bos_total_size, layout.total_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier)
+{
+	uint32_t i = 0;
+	const struct dpu_format *fmt = NULL;
+	const struct dpu_format *map = NULL;
+	ssize_t map_size = 0;
+
+	/*
+	 * Currently only support exactly zero or one modifier.
+	 * All planes use the same modifier.
+	 */
+	DPU_DEBUG("plane format modifier 0x%llX\n", modifier);
+
+	switch (modifier) {
+	case 0:
+		map = dpu_format_map;
+		map_size = ARRAY_SIZE(dpu_format_map);
+		break;
+	case DRM_FORMAT_MOD_QCOM_COMPRESSED:
+		map = dpu_format_map_ubwc;
+		map_size = ARRAY_SIZE(dpu_format_map_ubwc);
+		DPU_DEBUG("found fmt: %4.4s  DRM_FORMAT_MOD_QCOM_COMPRESSED\n",
+				(char *)&format);
+		break;
+	default:
+		DPU_ERROR("unsupported format modifier %llX\n", modifier);
+		return NULL;
+	}
+
+	for (i = 0; i < map_size; i++) {
+		if (format == map[i].base.pixel_format) {
+			fmt = &map[i];
+			break;
+		}
+	}
+
+	if (fmt == NULL)
+		DPU_ERROR("unsupported fmt: %4.4s modifier 0x%llX\n",
+			(char *)&format, modifier);
+	else
+		DPU_DEBUG("fmt %4.4s mod 0x%llX ubwc %d yuv %d\n",
+				(char *)&format, modifier,
+				DPU_FORMAT_IS_UBWC(fmt),
+				DPU_FORMAT_IS_YUV(fmt));
+
+	return fmt;
+}
+
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers)
+{
+	const struct dpu_format *fmt = dpu_get_dpu_format_ext(format,
+			modifiers);
+	if (fmt)
+		return &fmt->base;
+	return NULL;
+}
+
+uint32_t dpu_populate_formats(
+		const struct dpu_format_extended *format_list,
+		uint32_t *pixel_formats,
+		uint64_t *pixel_modifiers,
+		uint32_t pixel_formats_max)
+{
+	uint32_t i, fourcc_format;
+
+	if (!format_list || !pixel_formats)
+		return 0;
+
+	for (i = 0, fourcc_format = 0;
+			format_list->fourcc_format && i < pixel_formats_max;
+			++format_list) {
+		/* verify if listed format is in dpu_format_map? */
+
+		/* optionally return modified formats */
+		if (pixel_modifiers) {
+			/* assume same modifier for all fb planes */
+			pixel_formats[i] = format_list->fourcc_format;
+			pixel_modifiers[i++] = format_list->modifier;
+		} else {
+			/* assume base formats grouped together */
+			if (fourcc_format != format_list->fourcc_format) {
+				fourcc_format = format_list->fourcc_format;
+				pixel_formats[i++] = fourcc_format;
+			}
+		}
+	}
+
+	return i;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
new file mode 100644
index 000000000000..a54451d8d011
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
@@ -0,0 +1,88 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_FORMATS_H
+#define _DPU_FORMATS_H
+
+#include <drm/drm_fourcc.h>
+#include "msm_gem.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * dpu_get_dpu_format_ext() - Returns dpu format structure pointer.
+ * @format:          DRM FourCC Code
+ * @modifiers:       format modifier array from client, one per plane
+ */
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier);
+
+#define dpu_get_dpu_format(f) dpu_get_dpu_format_ext(f, 0)
+
+/**
+ * dpu_get_msm_format - get an dpu_format by its msm_format base
+ *                     callback function registers with the msm_kms layer
+ * @kms:             kms driver
+ * @format:          DRM FourCC Code
+ * @modifiers:       data layout modifier
+ */
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers);
+
+/**
+ * dpu_populate_formats - populate the given array with fourcc codes supported
+ * @format_list:       pointer to list of possible formats
+ * @pixel_formats:     array to populate with fourcc codes
+ * @pixel_modifiers:   array to populate with drm modifiers, can be NULL
+ * @pixel_formats_max: length of pixel formats array
+ * Return: number of elements populated
+ */
+uint32_t dpu_populate_formats(
+		const struct dpu_format_extended *format_list,
+		uint32_t *pixel_formats,
+		uint64_t *pixel_modifiers,
+		uint32_t pixel_formats_max);
+
+/**
+ * dpu_format_check_modified_format - validate format and buffers for
+ *                   dpu non-standard, i.e. modified format
+ * @kms:             kms driver
+ * @msm_fmt:         pointer to the msm_fmt base pointer of an dpu_format
+ * @cmd:             fb_cmd2 structure user request
+ * @bos:             gem buffer object list
+ *
+ * Return: error code on failure, 0 on success
+ */
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos);
+
+/**
+ * dpu_format_populate_layout - populate the given format layout based on
+ *                     mmu, fb, and format found in the fb
+ * @aspace:            address space pointer
+ * @fb:                framebuffer pointer
+ * @fmtl:              format layout structure to populate
+ *
+ * Return: error code on failure, -EAGAIN if success but the addresses
+ *         are the same as before or 0 if new addresses were populated
+ */
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *fmtl);
+
+#endif /*_DPU_FORMATS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
new file mode 100644
index 000000000000..58d29e43faef
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
@@ -0,0 +1,155 @@
+/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/mutex.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_blk.h"
+
+/* Serialization lock for dpu_hw_blk_list */
+static DEFINE_MUTEX(dpu_hw_blk_lock);
+
+/* List of all hw block objects */
+static LIST_HEAD(dpu_hw_blk_list);
+
+/**
+ * dpu_hw_blk_init - initialize hw block object
+ * @type: hw block type - enum dpu_hw_blk_type
+ * @id: instance id of the hw block
+ * @ops: Pointer to block operations
+ * return: 0 if success; error code otherwise
+ */
+int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+		struct dpu_hw_blk_ops *ops)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&hw_blk->list);
+	hw_blk->type = type;
+	hw_blk->id = id;
+	atomic_set(&hw_blk->refcount, 0);
+
+	if (ops)
+		hw_blk->ops = *ops;
+
+	mutex_lock(&dpu_hw_blk_lock);
+	list_add(&hw_blk->list, &dpu_hw_blk_list);
+	mutex_unlock(&dpu_hw_blk_lock);
+
+	return 0;
+}
+
+/**
+ * dpu_hw_blk_destroy - destroy hw block object.
+ * @hw_blk:  pointer to hw block object
+ * return: none
+ */
+void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return;
+	}
+
+	if (atomic_read(&hw_blk->refcount))
+		pr_err("hw_blk:%d.%d invalid refcount\n", hw_blk->type,
+				hw_blk->id);
+
+	mutex_lock(&dpu_hw_blk_lock);
+	list_del(&hw_blk->list);
+	mutex_unlock(&dpu_hw_blk_lock);
+}
+
+/**
+ * dpu_hw_blk_get - get hw_blk from free pool
+ * @hw_blk: if specified, increment reference count only
+ * @type: if hw_blk is not specified, allocate the next available of this type
+ * @id: if specified (>= 0), allocate the given instance of the above type
+ * return: pointer to hw block object
+ */
+struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id)
+{
+	struct dpu_hw_blk *curr;
+	int rc, refcount;
+
+	if (!hw_blk) {
+		mutex_lock(&dpu_hw_blk_lock);
+		list_for_each_entry(curr, &dpu_hw_blk_list, list) {
+			if ((curr->type != type) ||
+					(id >= 0 && curr->id != id) ||
+					(id < 0 &&
+						atomic_read(&curr->refcount)))
+				continue;
+
+			hw_blk = curr;
+			break;
+		}
+		mutex_unlock(&dpu_hw_blk_lock);
+	}
+
+	if (!hw_blk) {
+		pr_debug("no hw_blk:%d\n", type);
+		return NULL;
+	}
+
+	refcount = atomic_inc_return(&hw_blk->refcount);
+
+	if (refcount == 1 && hw_blk->ops.start) {
+		rc = hw_blk->ops.start(hw_blk);
+		if (rc) {
+			pr_err("failed to start  hw_blk:%d rc:%d\n", type, rc);
+			goto error_start;
+		}
+	}
+
+	pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type,
+			hw_blk->id, refcount);
+	return hw_blk;
+
+error_start:
+	dpu_hw_blk_put(hw_blk);
+	return ERR_PTR(rc);
+}
+
+/**
+ * dpu_hw_blk_put - put hw_blk to free pool if decremented refcount is zero
+ * @hw_blk: hw block to be freed
+ * @free_blk: function to be called when reference count goes to zero
+ */
+void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return;
+	}
+
+	pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type, hw_blk->id,
+			atomic_read(&hw_blk->refcount));
+
+	if (!atomic_read(&hw_blk->refcount)) {
+		pr_err("hw_blk:%d.%d invalid put\n", hw_blk->type, hw_blk->id);
+		return;
+	}
+
+	if (atomic_dec_return(&hw_blk->refcount))
+		return;
+
+	if (hw_blk->ops.stop)
+		hw_blk->ops.stop(hw_blk);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
new file mode 100644
index 000000000000..0f4ca8af1ec5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
@@ -0,0 +1,53 @@
+/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_BLK_H
+#define _DPU_HW_BLK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+
+struct dpu_hw_blk;
+
+/**
+ * struct dpu_hw_blk_ops - common hardware block operations
+ * @start: start operation on first get
+ * @stop: stop operation on last put
+ */
+struct dpu_hw_blk_ops {
+	int (*start)(struct dpu_hw_blk *);
+	void (*stop)(struct dpu_hw_blk *);
+};
+
+/**
+ * struct dpu_hw_blk - definition of hardware block object
+ * @list: list of hardware blocks
+ * @type: hardware block type
+ * @id: instance id
+ * @refcount: reference/usage count
+ */
+struct dpu_hw_blk {
+	struct list_head list;
+	u32 type;
+	int id;
+	atomic_t refcount;
+	struct dpu_hw_blk_ops ops;
+};
+
+int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+		struct dpu_hw_blk_ops *ops);
+void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk);
+
+struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id);
+void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk);
+#endif /*_DPU_HW_BLK_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
new file mode 100644
index 000000000000..44ee06398b1d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -0,0 +1,511 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/slab.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_catalog.h"
+#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) |\
+	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 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) |\
+	BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define MIXER_SDM845_MASK \
+	(BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER))
+
+#define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER)
+
+#define PINGPONG_SDM845_SPLIT_MASK \
+	(PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2))
+
+#define DEFAULT_PIXEL_RAM_SIZE		(50 * 1024)
+#define DEFAULT_DPU_LINE_WIDTH		2048
+#define DEFAULT_DPU_OUTPUT_LINE_WIDTH	2560
+
+#define MAX_HORZ_DECIMATION	4
+#define MAX_VERT_DECIMATION	4
+
+#define MAX_UPSCALE_RATIO	20
+#define MAX_DOWNSCALE_RATIO	4
+#define SSPP_UNITY_SCALE	1
+
+#define STRCAT(X, Y) (X Y)
+
+/*************************************************************
+ * DPU sub blocks config
+ *************************************************************/
+/* DPU top level caps */
+static const struct dpu_caps sdm845_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+};
+
+static struct dpu_mdp_cfg sdm845_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x45C,
+	.features = 0,
+	.highest_bank_bit = 0x2,
+	.has_dest_scaler = true,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .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},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	},
+};
+
+/*************************************************************
+ * CTL sub blocks config
+ *************************************************************/
+static struct dpu_ctl_cfg sdm845_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY)
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY)
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0xE4,
+	.features = 0
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x1600, .len = 0xE4,
+	.features = 0
+	},
+	{
+	.name = "ctl_4", .id = CTL_4,
+	.base = 0x1800, .len = 0xE4,
+	.features = 0
+	},
+};
+
+/*************************************************************
+ * SSPP sub blocks config
+ *************************************************************/
+
+/* SSPP common configuration */
+static const struct dpu_sspp_blks_common sdm845_sspp_common = {
+	.maxlinewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.maxhdeciexp = MAX_HORZ_DECIMATION,
+	.maxvdeciexp = MAX_VERT_DECIMATION,
+};
+
+#define _VIG_SBLK(num, sdma_pri) \
+	{ \
+	.common = &sdm845_sspp_common, \
+	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
+	.maxupscale = MAX_UPSCALE_RATIO, \
+	.smart_dma_priority = sdma_pri, \
+	.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, \
+		.base = 0xa00, .len = 0xa0,}, \
+	.csc_blk = {.name = STRCAT("sspp_csc", num), \
+		.id = DPU_SSPP_CSC_10BIT, \
+		.base = 0x1a00, .len = 0x100,}, \
+	.format_list = plane_formats_yuv, \
+	.virt_format_list = plane_formats, \
+	}
+
+#define _DMA_SBLK(num, sdma_pri) \
+	{ \
+	.common = &sdm845_sspp_common, \
+	.maxdwnscale = SSPP_UNITY_SCALE, \
+	.maxupscale = SSPP_UNITY_SCALE, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.format_list = plane_formats, \
+	.virt_format_list = 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_dma_sblk_0 = _DMA_SBLK("8", 1);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK("10", 3);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4);
+
+#define SSPP_VIG_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = VIG_SDM845_MASK, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = SSPP_TYPE_VIG, \
+	.clk_ctrl = _clkctrl \
+	}
+
+#define SSPP_DMA_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = DMA_SDM845_MASK, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = SSPP_TYPE_DMA, \
+	.clk_ctrl = _clkctrl \
+	}
+
+static struct dpu_sspp_cfg sdm845_sspp[] = {
+	SSPP_VIG_BLK("sspp_0", SSPP_VIG0, 0x4000,
+		sdm845_vig_sblk_0, 0, DPU_CLK_CTRL_VIG0),
+	SSPP_VIG_BLK("sspp_1", SSPP_VIG1, 0x6000,
+		sdm845_vig_sblk_1, 4, DPU_CLK_CTRL_VIG1),
+	SSPP_VIG_BLK("sspp_2", SSPP_VIG2, 0x8000,
+		sdm845_vig_sblk_2, 8, DPU_CLK_CTRL_VIG2),
+	SSPP_VIG_BLK("sspp_3", SSPP_VIG3, 0xa000,
+		sdm845_vig_sblk_3, 12, DPU_CLK_CTRL_VIG3),
+	SSPP_DMA_BLK("sspp_8", SSPP_DMA0, 0x24000,
+		sdm845_dma_sblk_0, 1, DPU_CLK_CTRL_DMA0),
+	SSPP_DMA_BLK("sspp_9", SSPP_DMA1, 0x26000,
+		sdm845_dma_sblk_1, 5, DPU_CLK_CTRL_DMA1),
+	SSPP_DMA_BLK("sspp_10", SSPP_DMA2, 0x28000,
+		sdm845_dma_sblk_2, 9, DPU_CLK_CTRL_CURSOR0),
+	SSPP_DMA_BLK("sspp_11", SSPP_DMA3, 0x2a000,
+		sdm845_dma_sblk_3, 13, DPU_CLK_CTRL_CURSOR1),
+};
+
+/*************************************************************
+ * MIXER sub blocks config
+ *************************************************************/
+static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 11, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98,
+		0xb0, 0xc8, 0xe0, 0xf8, 0x110
+	},
+};
+
+#define LM_BLK(_name, _id, _base, _ds, _pp, _lmpair) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x320, \
+	.features = MIXER_SDM845_MASK, \
+	.sblk = &sdm845_lm_sblk, \
+	.ds = _ds, \
+	.pingpong = _pp, \
+	.lm_pair_mask = (1 << _lmpair) \
+	}
+
+static struct dpu_lm_cfg sdm845_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, DS_0, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, DS_1, PINGPONG_1, LM_0),
+	LM_BLK("lm_2", LM_2, 0x46000, DS_MAX, PINGPONG_2, LM_5),
+	LM_BLK("lm_3", LM_3, 0x0, DS_MAX, PINGPONG_MAX, 0),
+	LM_BLK("lm_4", LM_4, 0x0, DS_MAX, PINGPONG_MAX, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, DS_MAX, PINGPONG_3, LM_2),
+};
+
+/*************************************************************
+ * DS sub blocks config
+ *************************************************************/
+static const struct dpu_ds_top_cfg sdm845_ds_top = {
+	.name = "ds_top_0", .id = DS_TOP,
+	.base = 0x60000, .len = 0xc,
+	.maxinputwidth = DEFAULT_DPU_LINE_WIDTH,
+	.maxoutputwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxupscale = MAX_UPSCALE_RATIO,
+};
+
+#define DS_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x800, \
+	.features = DPU_SSPP_SCALER_QSEED3, \
+	.top = &sdm845_ds_top \
+	}
+
+static struct dpu_ds_cfg sdm845_ds[] = {
+	DS_BLK("ds_0", DS_0, 0x800),
+	DS_BLK("ds_1", DS_1, 0x1000),
+};
+
+/*************************************************************
+ * PINGPONG sub blocks config
+ *************************************************************/
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk_te = {
+	.te2 = {.id = DPU_PINGPONG_TE2, .base = 0x2000, .len = 0x0,
+		.version = 0x1},
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = {
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+#define PP_BLK_TE(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_SPLIT_MASK, \
+	.sblk = &sdm845_pp_sblk_te \
+	}
+#define PP_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_MASK, \
+	.sblk = &sdm845_pp_sblk \
+	}
+
+static 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),
+};
+
+/*************************************************************
+ * INTF sub blocks config
+ *************************************************************/
+#define INTF_BLK(_name, _id, _base, _type, _ctrl_id) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x280, \
+	.type = _type, \
+	.controller_id = _ctrl_id, \
+	.prog_fetch_lines_worst_case = 24 \
+	}
+
+static 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),
+};
+
+/*************************************************************
+ * CDM sub blocks config
+ *************************************************************/
+static struct dpu_cdm_cfg sdm845_cdm[] = {
+	{
+	.name = "cdm_0", .id = CDM_0,
+	.base = 0x79200, .len = 0x224,
+	.features = 0,
+	.intf_connect = BIT(INTF_3),
+	},
+};
+
+/*************************************************************
+ * 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 struct dpu_vbif_cfg sdm845_vbif[] = {
+	{
+	.name = "vbif_0", .id = VBIF_0,
+	.base = 0, .len = 0x1040,
+	.features = BIT(DPU_VBIF_QOS_REMAP),
+	.xin_halt_timeout = 0x4000,
+	.qos_rt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_rt_pri_lvl),
+		.priority_lvl = sdm845_rt_pri_lvl,
+		},
+	.qos_nrt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_nrt_pri_lvl),
+		.priority_lvl = sdm845_nrt_pri_lvl,
+		},
+	.memtype_count = 14,
+	.memtype = {3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3},
+	},
+};
+
+static struct dpu_reg_dma_cfg sdm845_regdma = {
+	.base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c
+};
+
+/*************************************************************
+ * PERF data config
+ *************************************************************/
+
+/* SSPP QOS LUTs */
+static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
+	{.fl = 4, .lut = 0x357},
+	{.fl = 5, .lut = 0x3357},
+	{.fl = 6, .lut = 0x23357},
+	{.fl = 7, .lut = 0x223357},
+	{.fl = 8, .lut = 0x2223357},
+	{.fl = 9, .lut = 0x22223357},
+	{.fl = 10, .lut = 0x222223357},
+	{.fl = 11, .lut = 0x2222223357},
+	{.fl = 12, .lut = 0x22222223357},
+	{.fl = 13, .lut = 0x222222223357},
+	{.fl = 14, .lut = 0x1222222223357},
+	{.fl = 0, .lut = 0x11222222223357}
+};
+
+static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
+	{.fl = 10, .lut = 0x344556677},
+	{.fl = 11, .lut = 0x3344556677},
+	{.fl = 12, .lut = 0x23344556677},
+	{.fl = 13, .lut = 0x223344556677},
+	{.fl = 14, .lut = 0x1223344556677},
+	{.fl = 0, .lut = 0x112233344556677},
+};
+
+static struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static struct dpu_perf_cfg sdm845_perf_data = {
+	.max_bw_low = 6800000,
+	.max_bw_high = 6800000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.core_ib_ff = "6.0",
+	.core_clk_ff = "1.0",
+	.comp_ratio_rt =
+	"NV12/5/1/1.23 AB24/5/1/1.23 XB24/5/1/1.23",
+	.comp_ratio_nrt =
+	"NV12/5/1/1.25 AB24/5/1/1.25 XB24/5/1/1.25",
+	.undersized_prefill_lines = 2,
+	.xtra_prefill_lines = 2,
+	.dest_scale_prefill_lines = 3,
+	.macrotile_prefill_lines = 4,
+	.yuv_nv12_prefill_lines = 8,
+	.linear_prefill_lines = 1,
+	.downscaling_prefill_lines = 1,
+	.amortizable_threshold = 25,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sdm845_qos_linear),
+		.entries = sdm845_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_macrotile),
+		.entries = sdm845_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_nrt),
+		.entries = sdm845_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+};
+
+/*************************************************************
+ * Hardware catalog init
+ *************************************************************/
+
+/*
+ * sdm845_cfg_init(): populate sdm845 dpu sub-blocks reg offsets
+ * and instance counts.
+ */
+static void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
+{
+	*dpu_cfg = (struct dpu_mdss_cfg){
+		.caps = &sdm845_dpu_caps,
+		.mdp_count = ARRAY_SIZE(sdm845_mdp),
+		.mdp = sdm845_mdp,
+		.ctl_count = ARRAY_SIZE(sdm845_ctl),
+		.ctl = sdm845_ctl,
+		.sspp_count = ARRAY_SIZE(sdm845_sspp),
+		.sspp = sdm845_sspp,
+		.mixer_count = ARRAY_SIZE(sdm845_lm),
+		.mixer = sdm845_lm,
+		.ds_count = ARRAY_SIZE(sdm845_ds),
+		.ds = sdm845_ds,
+		.pingpong_count = ARRAY_SIZE(sdm845_pp),
+		.pingpong = sdm845_pp,
+		.cdm_count = ARRAY_SIZE(sdm845_cdm),
+		.cdm = sdm845_cdm,
+		.intf_count = ARRAY_SIZE(sdm845_intf),
+		.intf = sdm845_intf,
+		.vbif_count = ARRAY_SIZE(sdm845_vbif),
+		.vbif = sdm845_vbif,
+		.reg_dma_count = 1,
+		.dma_cfg = sdm845_regdma,
+		.perf = sdm845_perf_data,
+	};
+}
+
+static 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},
+};
+
+void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg)
+{
+	kfree(dpu_cfg);
+}
+
+struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev)
+{
+	int i;
+	struct dpu_mdss_cfg *dpu_cfg;
+
+	dpu_cfg = kzalloc(sizeof(*dpu_cfg), GFP_KERNEL);
+	if (!dpu_cfg)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev) {
+			cfg_handler[i].cfg_init(dpu_cfg);
+			dpu_cfg->hwversion = hw_rev;
+			return dpu_cfg;
+		}
+	}
+
+	DPU_ERROR("unsupported chipset id:%X\n", hw_rev);
+	dpu_hw_catalog_deinit(dpu_cfg);
+	return ERR_PTR(-ENODEV);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
new file mode 100644
index 000000000000..f0cb0d4fc80e
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -0,0 +1,804 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CATALOG_H
+#define _DPU_HW_CATALOG_H
+
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/bitmap.h>
+#include <linux/err.h>
+#include <drm/drmP.h>
+
+/**
+ * Max hardware block count: For ex: max 12 SSPP pipes or
+ * 5 ctl paths. In all cases, it can have max 12 hardware blocks
+ * based on current design
+ */
+#define MAX_BLOCKS    12
+
+#define DPU_HW_VER(MAJOR, MINOR, STEP) (((MAJOR & 0xF) << 28)    |\
+		((MINOR & 0xFFF) << 16)  |\
+		(STEP & 0xFFFF))
+
+#define DPU_HW_MAJOR(rev)		((rev) >> 28)
+#define DPU_HW_MINOR(rev)		(((rev) >> 16) & 0xFFF)
+#define DPU_HW_STEP(rev)		((rev) & 0xFFFF)
+#define DPU_HW_MAJOR_MINOR(rev)		((rev) >> 16)
+
+#define IS_DPU_MAJOR_MINOR_SAME(rev1, rev2)   \
+	(DPU_HW_MAJOR_MINOR((rev1)) == DPU_HW_MAJOR_MINOR((rev2)))
+
+#define DPU_HW_VER_170	DPU_HW_VER(1, 7, 0) /* 8996 v1.0 */
+#define DPU_HW_VER_171	DPU_HW_VER(1, 7, 1) /* 8996 v2.0 */
+#define DPU_HW_VER_172	DPU_HW_VER(1, 7, 2) /* 8996 v3.0 */
+#define DPU_HW_VER_300	DPU_HW_VER(3, 0, 0) /* 8998 v1.0 */
+#define DPU_HW_VER_301	DPU_HW_VER(3, 0, 1) /* 8998 v1.1 */
+#define DPU_HW_VER_400	DPU_HW_VER(4, 0, 0) /* sdm845 v1.0 */
+#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 IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170)
+#define IS_MSM8998_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_300)
+#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 DPU_HW_BLK_NAME_LEN	16
+
+#define MAX_IMG_WIDTH 0x3fff
+#define MAX_IMG_HEIGHT 0x3fff
+
+#define CRTC_DUAL_MIXERS	2
+
+#define MAX_XIN_COUNT 16
+
+/**
+ * Supported UBWC feature versions
+ */
+enum {
+	DPU_HW_UBWC_VER_10 = 0x100,
+	DPU_HW_UBWC_VER_20 = 0x200,
+	DPU_HW_UBWC_VER_30 = 0x300,
+};
+
+#define IS_UBWC_20_SUPPORTED(rev)       ((rev) >= DPU_HW_UBWC_VER_20)
+
+/**
+ * MDP TOP BLOCK features
+ * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be be done per pipe
+ * @DPU_MDP_10BIT_SUPPORT, Chipset supports 10 bit pixel formats
+ * @DPU_MDP_BWC,           MDSS HW supports Bandwidth compression.
+ * @DPU_MDP_UBWC_1_0,      This chipsets supports Universal Bandwidth
+ *                         compression initial revision
+ * @DPU_MDP_UBWC_1_5,      Universal Bandwidth compression version 1.5
+ * @DPU_MDP_MAX            Maximum value
+
+ */
+enum {
+	DPU_MDP_PANIC_PER_PIPE = 0x1,
+	DPU_MDP_10BIT_SUPPORT,
+	DPU_MDP_BWC,
+	DPU_MDP_UBWC_1_0,
+	DPU_MDP_UBWC_1_5,
+	DPU_MDP_MAX
+};
+
+/**
+ * SSPP sub-blocks/features
+ * @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_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
+ * @DPU_SSPP_CURSOR,         SSPP can be used as a cursor layer
+ * @DPU_SSPP_QOS,            SSPP support QoS control, danger/safe/creq
+ * @DPU_SSPP_QOS_8LVL,       SSPP support 8-level QoS control
+ * @DPU_SSPP_EXCL_RECT,      SSPP supports exclusion rect
+ * @DPU_SSPP_SMART_DMA_V1,   SmartDMA 1.0 support
+ * @DPU_SSPP_SMART_DMA_V2,   SmartDMA 2.0 support
+ * @DPU_SSPP_TS_PREFILL      Supports prefill with traffic shaper
+ * @DPU_SSPP_TS_PREFILL_REC1 Supports prefill with traffic shaper multirec
+ * @DPU_SSPP_CDP             Supports client driven prefetch
+ * @DPU_SSPP_MAX             maximum value
+ */
+enum {
+	DPU_SSPP_SRC = 0x1,
+	DPU_SSPP_SCALER_QSEED2,
+	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_RGB,
+	DPU_SSPP_CSC,
+	DPU_SSPP_CSC_10BIT,
+	DPU_SSPP_CURSOR,
+	DPU_SSPP_QOS,
+	DPU_SSPP_QOS_8LVL,
+	DPU_SSPP_EXCL_RECT,
+	DPU_SSPP_SMART_DMA_V1,
+	DPU_SSPP_SMART_DMA_V2,
+	DPU_SSPP_TS_PREFILL,
+	DPU_SSPP_TS_PREFILL_REC1,
+	DPU_SSPP_CDP,
+	DPU_SSPP_MAX
+};
+
+/*
+ * MIXER sub-blocks/features
+ * @DPU_MIXER_LAYER           Layer mixer layer blend configuration,
+ * @DPU_MIXER_SOURCESPLIT     Layer mixer supports source-split configuration
+ * @DPU_MIXER_GC              Gamma correction block
+ * @DPU_DIM_LAYER             Layer mixer supports dim layer
+ * @DPU_MIXER_MAX             maximum value
+ */
+enum {
+	DPU_MIXER_LAYER = 0x1,
+	DPU_MIXER_SOURCESPLIT,
+	DPU_MIXER_GC,
+	DPU_DIM_LAYER,
+	DPU_MIXER_MAX
+};
+
+/**
+ * PINGPONG sub-blocks
+ * @DPU_PINGPONG_TE         Tear check block
+ * @DPU_PINGPONG_TE2        Additional tear check block for split pipes
+ * @DPU_PINGPONG_SPLIT      PP block supports split fifo
+ * @DPU_PINGPONG_SLAVE      PP block is a suitable slave for split fifo
+ * @DPU_PINGPONG_DITHER,    Dither blocks
+ * @DPU_PINGPONG_MAX
+ */
+enum {
+	DPU_PINGPONG_TE = 0x1,
+	DPU_PINGPONG_TE2,
+	DPU_PINGPONG_SPLIT,
+	DPU_PINGPONG_SLAVE,
+	DPU_PINGPONG_DITHER,
+	DPU_PINGPONG_MAX
+};
+
+/**
+ * CTL sub-blocks
+ * @DPU_CTL_SPLIT_DISPLAY       CTL supports video mode split display
+ * @DPU_CTL_MAX
+ */
+enum {
+	DPU_CTL_SPLIT_DISPLAY = 0x1,
+	DPU_CTL_MAX
+};
+
+/**
+ * VBIF sub-blocks and features
+ * @DPU_VBIF_QOS_OTLIM        VBIF supports OT Limit
+ * @DPU_VBIF_QOS_REMAP        VBIF supports QoS priority remap
+ * @DPU_VBIF_MAX              maximum value
+ */
+enum {
+	DPU_VBIF_QOS_OTLIM = 0x1,
+	DPU_VBIF_QOS_REMAP,
+	DPU_VBIF_MAX
+};
+
+/**
+ * MACRO DPU_HW_BLK_INFO - information of HW blocks inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this block
+ * @base:              register base offset to mdss
+ * @len:               length of hardware block
+ * @features           bit mask identifying sub-blocks/features
+ */
+#define DPU_HW_BLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len; \
+	unsigned long features
+
+/**
+ * MACRO DPU_HW_SUBBLK_INFO - information of HW sub-block inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this sub-block
+ * @base:              offset of this sub-block relative to the block
+ *                     offset
+ * @len                register block length of this sub-block
+ */
+#define DPU_HW_SUBBLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len
+
+/**
+ * struct dpu_src_blk: SSPP part of the source pipes
+ * @info:   HW register and features supported by this sub-blk
+ */
+struct dpu_src_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_scaler_blk: Scaler information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: qseed block revision
+ */
+struct dpu_scaler_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+struct dpu_csc_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_pp_blk : Pixel processing sub-blk information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: HW Algorithm version
+ */
+struct dpu_pp_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+/**
+ * struct dpu_format_extended - define dpu specific pixel format+modifier
+ * @fourcc_format: Base FOURCC pixel format code
+ * @modifier: 64-bit drm format modifier, same modifier must be applied to all
+ *            framebuffer planes
+ */
+struct dpu_format_extended {
+	uint32_t fourcc_format;
+	uint64_t modifier;
+};
+
+/**
+ * enum dpu_qos_lut_usage - define QoS LUT use cases
+ */
+enum dpu_qos_lut_usage {
+	DPU_QOS_LUT_USAGE_LINEAR,
+	DPU_QOS_LUT_USAGE_MACROTILE,
+	DPU_QOS_LUT_USAGE_NRT,
+	DPU_QOS_LUT_USAGE_MAX,
+};
+
+/**
+ * struct dpu_qos_lut_entry - define QoS LUT table entry
+ * @fl: fill level, or zero on last entry to indicate default lut
+ * @lut: lut to use if equal to or less than fill level
+ */
+struct dpu_qos_lut_entry {
+	u32 fl;
+	u64 lut;
+};
+
+/**
+ * struct dpu_qos_lut_tbl - define QoS LUT table
+ * @nentry: number of entry in this table
+ * @entries: Pointer to table entries
+ */
+struct dpu_qos_lut_tbl {
+	u32 nentry;
+	struct dpu_qos_lut_entry *entries;
+};
+
+/**
+ * struct dpu_caps - define DPU capabilities
+ * @max_mixer_width    max layer mixer line width support.
+ * @max_mixer_blendstages max layer mixer blend stages or
+ *                       supported z order
+ * @qseed_type         qseed2 or qseed3 support.
+ * @smart_dma_rev      Supported version of SmartDMA feature.
+ * @ubwc_version       UBWC feature version (0x0 for not supported)
+ * @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
+ */
+struct dpu_caps {
+	u32 max_mixer_width;
+	u32 max_mixer_blendstages;
+	u32 qseed_type;
+	u32 smart_dma_rev;
+	u32 ubwc_version;
+	bool has_src_split;
+	bool has_dim_layer;
+	bool has_idle_pc;
+};
+
+/**
+ * struct dpu_sspp_blks_common : SSPP sub-blocks common configuration
+ * @maxwidth: max pixelwidth supported by this pipe
+ * @pixel_ram_size: size of latency hiding and de-tiling buffer in bytes
+ * @maxhdeciexp: max horizontal decimation supported by this pipe
+ *				(max is 2^value)
+ * @maxvdeciexp: max vertical decimation supported by this pipe
+ *				(max is 2^value)
+ */
+struct dpu_sspp_blks_common {
+	u32 maxlinewidth;
+	u32 pixel_ram_size;
+	u32 maxhdeciexp;
+	u32 maxvdeciexp;
+};
+
+/**
+ * struct dpu_sspp_sub_blks : SSPP sub-blocks
+ * common: Pointer to common configurations shared by sub blocks
+ * @creq_vblank: creq priority during vertical blanking
+ * @danger_vblank: danger priority during vertical blanking
+ * @maxdwnscale: max downscale ratio supported(without DECIMATION)
+ * @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
+ * @src_blk:
+ * @scaler_blk:
+ * @csc_blk:
+ * @hsic:
+ * @memcolor:
+ * @pcc_blk:
+ * @igc_blk:
+ * @format_list: Pointer to list of supported formats
+ * @virt_format_list: Pointer to list of supported formats for virtual planes
+ */
+struct dpu_sspp_sub_blks {
+	const struct dpu_sspp_blks_common *common;
+	u32 creq_vblank;
+	u32 danger_vblank;
+	u32 maxdwnscale;
+	u32 maxupscale;
+	u32 smart_dma_priority;
+	u32 max_per_pipe_bw;
+	struct dpu_src_blk src_blk;
+	struct dpu_scaler_blk scaler_blk;
+	struct dpu_pp_blk csc_blk;
+	struct dpu_pp_blk hsic_blk;
+	struct dpu_pp_blk memcolor_blk;
+	struct dpu_pp_blk pcc_blk;
+	struct dpu_pp_blk igc_blk;
+
+	const struct dpu_format_extended *format_list;
+	const struct dpu_format_extended *virt_format_list;
+};
+
+/**
+ * struct dpu_lm_sub_blks:      information of mixer block
+ * @maxwidth:               Max pixel width supported by this mixer
+ * @maxblendstages:         Max number of blend-stages supported
+ * @blendstage_base:        Blend-stage register base offset
+ * @gc: gamma correction block
+ */
+struct dpu_lm_sub_blks {
+	u32 maxwidth;
+	u32 maxblendstages;
+	u32 blendstage_base[MAX_BLOCKS];
+	struct dpu_pp_blk gc;
+};
+
+struct dpu_pingpong_sub_blks {
+	struct dpu_pp_blk te;
+	struct dpu_pp_blk te2;
+	struct dpu_pp_blk dither;
+};
+
+/**
+ * dpu_clk_ctrl_type - Defines top level clock control signals
+ */
+enum dpu_clk_ctrl_type {
+	DPU_CLK_CTRL_NONE,
+	DPU_CLK_CTRL_VIG0,
+	DPU_CLK_CTRL_VIG1,
+	DPU_CLK_CTRL_VIG2,
+	DPU_CLK_CTRL_VIG3,
+	DPU_CLK_CTRL_VIG4,
+	DPU_CLK_CTRL_RGB0,
+	DPU_CLK_CTRL_RGB1,
+	DPU_CLK_CTRL_RGB2,
+	DPU_CLK_CTRL_RGB3,
+	DPU_CLK_CTRL_DMA0,
+	DPU_CLK_CTRL_DMA1,
+	DPU_CLK_CTRL_CURSOR0,
+	DPU_CLK_CTRL_CURSOR1,
+	DPU_CLK_CTRL_INLINE_ROT0_SSPP,
+	DPU_CLK_CTRL_MAX,
+};
+
+/* struct dpu_clk_ctrl_reg : Clock control register
+ * @reg_off:           register offset
+ * @bit_off:           bit offset
+ */
+struct dpu_clk_ctrl_reg {
+	u32 reg_off;
+	u32 bit_off;
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ * @highest_bank_bit:  UBWC parameter
+ * @ubwc_static:       ubwc static configuration
+ * @ubwc_swizzle:      ubwc default swizzle setting
+ * @has_dest_scaler:   indicates support of destination scaler
+ * @clk_ctrls          clock control register definition
+ */
+struct dpu_mdp_cfg {
+	DPU_HW_BLK_INFO;
+	u32 highest_bank_bit;
+	u32 ubwc_static;
+	u32 ubwc_swizzle;
+	bool has_dest_scaler;
+	struct dpu_clk_ctrl_reg clk_ctrls[DPU_CLK_CTRL_MAX];
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ */
+struct dpu_ctl_cfg {
+	DPU_HW_BLK_INFO;
+};
+
+/**
+ * struct dpu_sspp_cfg - information of source pipes
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              SSPP sub-blocks information
+ * @xin_id:            bus client identifier
+ * @clk_ctrl           clock control identifier
+ * @type               sspp type identifier
+ */
+struct dpu_sspp_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_sspp_sub_blks *sblk;
+	u32 xin_id;
+	enum dpu_clk_ctrl_type clk_ctrl;
+	u32 type;
+};
+
+/**
+ * struct dpu_lm_cfg - information of layer mixer blocks
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              LM Sub-blocks information
+ * @pingpong:          ID of connected PingPong, PINGPONG_MAX if unsupported
+ * @ds:                ID of connected DS, DS_MAX if unsupported
+ * @lm_pair_mask:      Bitmask of LMs that can be controlled by same CTL
+ */
+struct dpu_lm_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_lm_sub_blks *sblk;
+	u32 pingpong;
+	u32 ds;
+	unsigned long lm_pair_mask;
+};
+
+/**
+ * struct dpu_ds_top_cfg - information of dest scaler top
+ * @id               enum identifying this block
+ * @base             register offset of this block
+ * @features         bit mask identifying features
+ * @version          hw version of dest scaler
+ * @maxinputwidth    maximum input line width
+ * @maxoutputwidth   maximum output line width
+ * @maxupscale       maximum upscale ratio
+ */
+struct dpu_ds_top_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 maxinputwidth;
+	u32 maxoutputwidth;
+	u32 maxupscale;
+};
+
+/**
+ * struct dpu_ds_cfg - information of dest scaler blocks
+ * @id          enum identifying this block
+ * @base        register offset wrt DS top offset
+ * @features    bit mask identifying features
+ * @version     hw version of the qseed block
+ * @top         DS top information
+ */
+struct dpu_ds_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	const struct dpu_ds_top_cfg *top;
+};
+
+/**
+ * struct dpu_pingpong_cfg - information of PING-PONG blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk               sub-blocks information
+ */
+struct dpu_pingpong_cfg  {
+	DPU_HW_BLK_INFO;
+	const struct dpu_pingpong_sub_blks *sblk;
+};
+
+/**
+ * struct dpu_cdm_cfg - information of chroma down blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @intf_connect       Bitmask of INTF IDs this CDM can connect to
+ */
+struct dpu_cdm_cfg   {
+	DPU_HW_BLK_INFO;
+	unsigned long intf_connect;
+};
+
+/**
+ * struct dpu_intf_cfg - information of timing engine blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @type:              Interface type(DSI, DP, HDMI)
+ * @controller_id:     Controller Instance ID in case of multiple of intf type
+ * @prog_fetch_lines_worst_case	Worst case latency num lines needed to prefetch
+ */
+struct dpu_intf_cfg  {
+	DPU_HW_BLK_INFO;
+	u32 type;   /* interface type*/
+	u32 controller_id;
+	u32 prog_fetch_lines_worst_case;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting
+ * @pps                pixel per seconds
+ * @ot_limit           OT limit to use up to specified pixel per second
+ */
+struct dpu_vbif_dynamic_ot_cfg {
+	u64 pps;
+	u32 ot_limit;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_tbl - dynamic OT setting table
+ * @count              length of cfg
+ * @cfg                pointer to array of configuration settings with
+ *                     ascending requirements
+ */
+struct dpu_vbif_dynamic_ot_tbl {
+	u32 count;
+	struct dpu_vbif_dynamic_ot_cfg *cfg;
+};
+
+/**
+ * struct dpu_vbif_qos_tbl - QoS priority table
+ * @npriority_lvl      num of priority level
+ * @priority_lvl       pointer to array of priority level in ascending order
+ */
+struct dpu_vbif_qos_tbl {
+	u32 npriority_lvl;
+	u32 *priority_lvl;
+};
+
+/**
+ * struct dpu_vbif_cfg - information of VBIF blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @ot_rd_limit        default OT read limit
+ * @ot_wr_limit        default OT write limit
+ * @xin_halt_timeout   maximum time (in usec) for xin to halt
+ * @dynamic_ot_rd_tbl  dynamic OT read configuration table
+ * @dynamic_ot_wr_tbl  dynamic OT write configuration table
+ * @qos_rt_tbl         real-time QoS priority table
+ * @qos_nrt_tbl        non-real-time QoS priority table
+ * @memtype_count      number of defined memtypes
+ * @memtype            array of xin memtype definitions
+ */
+struct dpu_vbif_cfg {
+	DPU_HW_BLK_INFO;
+	u32 default_ot_rd_limit;
+	u32 default_ot_wr_limit;
+	u32 xin_halt_timeout;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_rd_tbl;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_wr_tbl;
+	struct dpu_vbif_qos_tbl qos_rt_tbl;
+	struct dpu_vbif_qos_tbl qos_nrt_tbl;
+	u32 memtype_count;
+	u32 memtype[MAX_XIN_COUNT];
+};
+/**
+ * struct dpu_reg_dma_cfg - information of lut dma blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @version            version of lutdma hw block
+ * @trigger_sel_off    offset to trigger select registers of lutdma
+ */
+struct dpu_reg_dma_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 trigger_sel_off;
+};
+
+/**
+ * Define CDP use cases
+ * @DPU_PERF_CDP_UDAGE_RT: real-time use cases
+ * @DPU_PERF_CDP_USAGE_NRT: non real-time use cases such as WFD
+ */
+enum {
+	DPU_PERF_CDP_USAGE_RT,
+	DPU_PERF_CDP_USAGE_NRT,
+	DPU_PERF_CDP_USAGE_MAX
+};
+
+/**
+ * struct dpu_perf_cdp_cfg - define CDP use case configuration
+ * @rd_enable: true if read pipe CDP is enabled
+ * @wr_enable: true if write pipe CDP is enabled
+ */
+struct dpu_perf_cdp_cfg {
+	bool rd_enable;
+	bool wr_enable;
+};
+
+/**
+ * struct dpu_perf_cfg - performance control settings
+ * @max_bw_low         low threshold of maximum bandwidth (kbps)
+ * @max_bw_high        high threshold of maximum bandwidth (kbps)
+ * @min_core_ib        minimum bandwidth for core (kbps)
+ * @min_core_ib        minimum mnoc ib vote in kbps
+ * @min_llcc_ib        minimum llcc ib vote in kbps
+ * @min_dram_ib        minimum dram ib vote in kbps
+ * @core_ib_ff         core instantaneous bandwidth fudge factor
+ * @core_clk_ff        core clock fudge factor
+ * @comp_ratio_rt      string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio>
+ * @comp_ratio_nrt     string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio>
+ * @undersized_prefill_lines   undersized prefill in lines
+ * @xtra_prefill_lines         extra prefill latency in lines
+ * @dest_scale_prefill_lines   destination scaler latency in lines
+ * @macrotile_perfill_lines    macrotile latency in lines
+ * @yuv_nv12_prefill_lines     yuv_nv12 latency in lines
+ * @linear_prefill_lines       linear latency in lines
+ * @downscaling_prefill_lines  downscaling latency in lines
+ * @amortizable_theshold minimum y position for traffic shaping prefill
+ * @min_prefill_lines  minimum pipeline latency in lines
+ * @safe_lut_tbl: LUT tables for safe signals
+ * @danger_lut_tbl: LUT tables for danger signals
+ * @qos_lut_tbl: LUT tables for QoS signals
+ * @cdp_cfg            cdp use case configurations
+ */
+struct dpu_perf_cfg {
+	u32 max_bw_low;
+	u32 max_bw_high;
+	u32 min_core_ib;
+	u32 min_llcc_ib;
+	u32 min_dram_ib;
+	const char *core_ib_ff;
+	const char *core_clk_ff;
+	const char *comp_ratio_rt;
+	const char *comp_ratio_nrt;
+	u32 undersized_prefill_lines;
+	u32 xtra_prefill_lines;
+	u32 dest_scale_prefill_lines;
+	u32 macrotile_prefill_lines;
+	u32 yuv_nv12_prefill_lines;
+	u32 linear_prefill_lines;
+	u32 downscaling_prefill_lines;
+	u32 amortizable_threshold;
+	u32 min_prefill_lines;
+	u32 safe_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	u32 danger_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_qos_lut_tbl qos_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_perf_cdp_cfg cdp_cfg[DPU_PERF_CDP_USAGE_MAX];
+};
+
+/**
+ * struct dpu_mdss_cfg - information of MDSS HW
+ * This is the main catalog data structure representing
+ * this HW version. Contains number of instances,
+ * register offsets, capabilities of the all MDSS HW sub-blocks.
+ *
+ * @dma_formats        Supported formats for dma pipe
+ * @cursor_formats     Supported formats for cursor pipe
+ * @vig_formats        Supported formats for vig pipe
+ */
+struct dpu_mdss_cfg {
+	u32 hwversion;
+
+	const struct dpu_caps *caps;
+
+	u32 mdp_count;
+	struct dpu_mdp_cfg *mdp;
+
+	u32 ctl_count;
+	struct dpu_ctl_cfg *ctl;
+
+	u32 sspp_count;
+	struct dpu_sspp_cfg *sspp;
+
+	u32 mixer_count;
+	struct dpu_lm_cfg *mixer;
+
+	u32 ds_count;
+	struct dpu_ds_cfg *ds;
+
+	u32 pingpong_count;
+	struct dpu_pingpong_cfg *pingpong;
+
+	u32 cdm_count;
+	struct dpu_cdm_cfg *cdm;
+
+	u32 intf_count;
+	struct dpu_intf_cfg *intf;
+
+	u32 vbif_count;
+	struct dpu_vbif_cfg *vbif;
+
+	u32 reg_dma_count;
+	struct dpu_reg_dma_cfg dma_cfg;
+
+	u32 ad_count;
+
+	/* 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;
+};
+
+struct dpu_mdss_hw_cfg_handler {
+	u32 hw_rev;
+	void (*cfg_init)(struct dpu_mdss_cfg *dpu_cfg);
+};
+
+/*
+ * Access Macros
+ */
+#define BLK_MDP(s) ((s)->mdp)
+#define BLK_CTL(s) ((s)->ctl)
+#define BLK_VIG(s) ((s)->vig)
+#define BLK_RGB(s) ((s)->rgb)
+#define BLK_DMA(s) ((s)->dma)
+#define BLK_CURSOR(s) ((s)->cursor)
+#define BLK_MIXER(s) ((s)->mixer)
+#define BLK_DS(s) ((s)->ds)
+#define BLK_PINGPONG(s) ((s)->pingpong)
+#define BLK_CDM(s) ((s)->cdm)
+#define BLK_INTF(s) ((s)->intf)
+#define BLK_AD(s) ((s)->ad)
+
+/**
+ * dpu_hw_catalog_init - dpu hardware catalog init API retrieves
+ * hardcoded target specific catalog information in config structure
+ * @hw_rev:       caller needs provide the hardware revision.
+ *
+ * Return: dpu config structure
+ */
+struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev);
+
+/**
+ * dpu_hw_catalog_deinit - dpu hardware catalog cleanup
+ * @dpu_cfg:      pointer returned from init function
+ */
+void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg);
+
+/**
+ * dpu_hw_sspp_multirect_enabled - check multirect enabled for the sspp
+ * @cfg:          pointer to sspp cfg
+ */
+static inline bool dpu_hw_sspp_multirect_enabled(const struct dpu_sspp_cfg *cfg)
+{
+	return test_bit(DPU_SSPP_SMART_DMA_V1, &cfg->features) ||
+			 test_bit(DPU_SSPP_SMART_DMA_V2, &cfg->features);
+}
+#endif /* _DPU_HW_CATALOG_H */
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
new file mode 100644
index 000000000000..3c9f028628ef
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
@@ -0,0 +1,168 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hw_mdss.h"
+
+static const struct dpu_format_extended plane_formats[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended plane_formats_yuv[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+
+	{DRM_FORMAT_NV12, 0},
+	{DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_NV21, 0},
+	{DRM_FORMAT_NV16, 0},
+	{DRM_FORMAT_NV61, 0},
+	{DRM_FORMAT_VYUY, 0},
+	{DRM_FORMAT_UYVY, 0},
+	{DRM_FORMAT_YUYV, 0},
+	{DRM_FORMAT_YVYU, 0},
+	{DRM_FORMAT_YUV420, 0},
+	{DRM_FORMAT_YVU420, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended cursor_formats[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended wb2_formats[] = {
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+
+	{DRM_FORMAT_YUV420, 0},
+	{DRM_FORMAT_NV12, 0},
+	{DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_NV16, 0},
+	{DRM_FORMAT_YUYV, 0},
+
+	{0, 0},
+};
+
+static const struct dpu_format_extended rgb_10bit_formats[] = {
+	{DRM_FORMAT_BGRA1010102, 0},
+	{DRM_FORMAT_BGRX1010102, 0},
+	{DRM_FORMAT_RGBA1010102, 0},
+	{DRM_FORMAT_RGBX1010102, 0},
+	{DRM_FORMAT_ABGR2101010, 0},
+	{DRM_FORMAT_ABGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_XBGR2101010, 0},
+	{DRM_FORMAT_XBGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_ARGB2101010, 0},
+	{DRM_FORMAT_XRGB2101010, 0},
+};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
new file mode 100644
index 000000000000..554874ba0c3b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
@@ -0,0 +1,323 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define CDM_CSC_10_OPMODE                  0x000
+#define CDM_CSC_10_BASE                    0x004
+
+#define CDM_CDWN2_OP_MODE                  0x100
+#define CDM_CDWN2_CLAMP_OUT                0x104
+#define CDM_CDWN2_PARAMS_3D_0              0x108
+#define CDM_CDWN2_PARAMS_3D_1              0x10C
+#define CDM_CDWN2_COEFF_COSITE_H_0         0x110
+#define CDM_CDWN2_COEFF_COSITE_H_1         0x114
+#define CDM_CDWN2_COEFF_COSITE_H_2         0x118
+#define CDM_CDWN2_COEFF_OFFSITE_H_0        0x11C
+#define CDM_CDWN2_COEFF_OFFSITE_H_1        0x120
+#define CDM_CDWN2_COEFF_OFFSITE_H_2        0x124
+#define CDM_CDWN2_COEFF_COSITE_V           0x128
+#define CDM_CDWN2_COEFF_OFFSITE_V          0x12C
+#define CDM_CDWN2_OUT_SIZE                 0x130
+
+#define CDM_HDMI_PACK_OP_MODE              0x200
+#define CDM_CSC_10_MATRIX_COEFF_0          0x004
+
+/**
+ * Horizontal coefficients for cosite chroma downscale
+ * s13 representation of coefficients
+ */
+static u32 cosite_h_coeff[] = {0x00000016, 0x000001cc, 0x0100009e};
+
+/**
+ * Horizontal coefficients for offsite chroma downscale
+ */
+static u32 offsite_h_coeff[] = {0x000b0005, 0x01db01eb, 0x00e40046};
+
+/**
+ * Vertical coefficients for cosite chroma downscale
+ */
+static u32 cosite_v_coeff[] = {0x00080004};
+/**
+ * Vertical coefficients for offsite chroma downscale
+ */
+static u32 offsite_v_coeff[] = {0x00060002};
+
+/* Limited Range rgb2yuv coeff with clamp and bias values for CSC 10 module */
+static struct dpu_csc_cfg rgb2yuv_cfg = {
+	{
+		0x0083, 0x0102, 0x0032,
+		0x1fb5, 0x1f6c, 0x00e1,
+		0x00e1, 0x1f45, 0x1fdc
+	},
+	{ 0x00, 0x00, 0x00 },
+	{ 0x0040, 0x0200, 0x0200 },
+	{ 0x000, 0x3ff, 0x000, 0x3ff, 0x000, 0x3ff },
+	{ 0x040, 0x3ac, 0x040, 0x3c0, 0x040, 0x3c0 },
+};
+
+static struct dpu_cdm_cfg *_cdm_offset(enum dpu_cdm cdm,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->cdm_count; i++) {
+		if (cdm == m->cdm[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->cdm[i].base;
+			b->length = m->cdm[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_CDM;
+			return &m->cdm[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int dpu_hw_cdm_setup_csc_10bit(struct dpu_hw_cdm *ctx,
+		struct dpu_csc_cfg *data)
+{
+	dpu_hw_csc_setup(&ctx->hw, CDM_CSC_10_MATRIX_COEFF_0, data, true);
+
+	return 0;
+}
+
+static int dpu_hw_cdm_setup_cdwn(struct dpu_hw_cdm *ctx,
+		struct dpu_hw_cdm_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 opmode = 0;
+	u32 out_size = 0;
+
+	if (cfg->output_bit_depth == CDM_CDWN_OUTPUT_10BIT)
+		opmode &= ~BIT(7);
+	else
+		opmode |= BIT(7);
+
+	/* ENABLE DWNS_H bit */
+	opmode |= BIT(1);
+
+	switch (cfg->h_cdwn_type) {
+	case CDM_CDWN_DISABLE:
+		/* CLEAR METHOD_H field */
+		opmode &= ~(0x18);
+		/* CLEAR DWNS_H bit */
+		opmode &= ~BIT(1);
+		break;
+	case CDM_CDWN_PIXEL_DROP:
+		/* Clear METHOD_H field (pixel drop is 0) */
+		opmode &= ~(0x18);
+		break;
+	case CDM_CDWN_AVG:
+		/* Clear METHOD_H field (Average is 0x1) */
+		opmode &= ~(0x18);
+		opmode |= (0x1 << 0x3);
+		break;
+	case CDM_CDWN_COSITE:
+		/* Clear METHOD_H field (Average is 0x2) */
+		opmode &= ~(0x18);
+		opmode |= (0x2 << 0x3);
+		/* Co-site horizontal coefficients */
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_0,
+				cosite_h_coeff[0]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_1,
+				cosite_h_coeff[1]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_2,
+				cosite_h_coeff[2]);
+		break;
+	case CDM_CDWN_OFFSITE:
+		/* Clear METHOD_H field (Average is 0x3) */
+		opmode &= ~(0x18);
+		opmode |= (0x3 << 0x3);
+
+		/* Off-site horizontal coefficients */
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_0,
+				offsite_h_coeff[0]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_1,
+				offsite_h_coeff[1]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_2,
+				offsite_h_coeff[2]);
+		break;
+	default:
+		pr_err("%s invalid horz down sampling type\n", __func__);
+		return -EINVAL;
+	}
+
+	/* ENABLE DWNS_V bit */
+	opmode |= BIT(2);
+
+	switch (cfg->v_cdwn_type) {
+	case CDM_CDWN_DISABLE:
+		/* CLEAR METHOD_V field */
+		opmode &= ~(0x60);
+		/* CLEAR DWNS_V bit */
+		opmode &= ~BIT(2);
+		break;
+	case CDM_CDWN_PIXEL_DROP:
+		/* Clear METHOD_V field (pixel drop is 0) */
+		opmode &= ~(0x60);
+		break;
+	case CDM_CDWN_AVG:
+		/* Clear METHOD_V field (Average is 0x1) */
+		opmode &= ~(0x60);
+		opmode |= (0x1 << 0x5);
+		break;
+	case CDM_CDWN_COSITE:
+		/* Clear METHOD_V field (Average is 0x2) */
+		opmode &= ~(0x60);
+		opmode |= (0x2 << 0x5);
+		/* Co-site vertical coefficients */
+		DPU_REG_WRITE(c,
+				CDM_CDWN2_COEFF_COSITE_V,
+				cosite_v_coeff[0]);
+		break;
+	case CDM_CDWN_OFFSITE:
+		/* Clear METHOD_V field (Average is 0x3) */
+		opmode &= ~(0x60);
+		opmode |= (0x3 << 0x5);
+
+		/* Off-site vertical coefficients */
+		DPU_REG_WRITE(c,
+				CDM_CDWN2_COEFF_OFFSITE_V,
+				offsite_v_coeff[0]);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (cfg->v_cdwn_type || cfg->h_cdwn_type)
+		opmode |= BIT(0); /* EN CDWN module */
+	else
+		opmode &= ~BIT(0);
+
+	out_size = (cfg->output_width & 0xFFFF) |
+		((cfg->output_height & 0xFFFF) << 16);
+	DPU_REG_WRITE(c, CDM_CDWN2_OUT_SIZE, out_size);
+	DPU_REG_WRITE(c, CDM_CDWN2_OP_MODE, opmode);
+	DPU_REG_WRITE(c, CDM_CDWN2_CLAMP_OUT,
+			((0x3FF << 16) | 0x0));
+
+	return 0;
+}
+
+static int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx,
+		struct dpu_hw_cdm_cfg *cdm)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	const struct dpu_format *fmt = cdm->output_fmt;
+	struct cdm_output_cfg cdm_cfg = { 0 };
+	u32 opmode = 0;
+	u32 csc = 0;
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		return -EINVAL;
+
+	if (cdm->output_type == CDM_CDWN_OUTPUT_HDMI) {
+		if (fmt->chroma_sample != DPU_CHROMA_H1V2)
+			return -EINVAL; /*unsupported format */
+		opmode = BIT(0);
+		opmode |= (fmt->chroma_sample << 1);
+		cdm_cfg.intf_en = true;
+	}
+
+	csc |= BIT(2);
+	csc &= ~BIT(1);
+	csc |= BIT(0);
+
+	if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output)
+		ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg);
+
+	DPU_REG_WRITE(c, CDM_CSC_10_OPMODE, csc);
+	DPU_REG_WRITE(c, CDM_HDMI_PACK_OP_MODE, opmode);
+	return 0;
+}
+
+static void dpu_hw_cdm_disable(struct dpu_hw_cdm *ctx)
+{
+	struct cdm_output_cfg cdm_cfg = { 0 };
+
+	if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output)
+		ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg);
+}
+
+static void _setup_cdm_ops(struct dpu_hw_cdm_ops *ops,
+	unsigned long features)
+{
+	ops->setup_csc_data = dpu_hw_cdm_setup_csc_10bit;
+	ops->setup_cdwn = dpu_hw_cdm_setup_cdwn;
+	ops->enable = dpu_hw_cdm_enable;
+	ops->disable = dpu_hw_cdm_disable;
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m,
+		struct dpu_hw_mdp *hw_mdp)
+{
+	struct dpu_hw_cdm *c;
+	struct dpu_cdm_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _cdm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_cdm_ops(&c->ops, c->caps->features);
+	c->hw_mdp = hw_mdp;
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CDM, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	/*
+	 * Perform any default initialization for the chroma down module
+	 * @setup default csc coefficients
+	 */
+	dpu_hw_cdm_setup_csc_10bit(c, &rgb2yuv_cfg);
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm)
+{
+	if (cdm)
+		dpu_hw_blk_destroy(&cdm->base);
+	kfree(cdm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
new file mode 100644
index 000000000000..5cceb1ecb8e0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
@@ -0,0 +1,139 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CDM_H
+#define _DPU_HW_CDM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_cdm;
+
+struct dpu_hw_cdm_cfg {
+	u32 output_width;
+	u32 output_height;
+	u32 output_bit_depth;
+	u32 h_cdwn_type;
+	u32 v_cdwn_type;
+	const struct dpu_format *output_fmt;
+	u32 output_type;
+	int flags;
+};
+
+enum dpu_hw_cdwn_type {
+	CDM_CDWN_DISABLE,
+	CDM_CDWN_PIXEL_DROP,
+	CDM_CDWN_AVG,
+	CDM_CDWN_COSITE,
+	CDM_CDWN_OFFSITE,
+};
+
+enum dpu_hw_cdwn_output_type {
+	CDM_CDWN_OUTPUT_HDMI,
+	CDM_CDWN_OUTPUT_WB,
+};
+
+enum dpu_hw_cdwn_output_bit_depth {
+	CDM_CDWN_OUTPUT_8BIT,
+	CDM_CDWN_OUTPUT_10BIT,
+};
+
+/**
+ * struct dpu_hw_cdm_ops : Interface to the chroma down Hw driver functions
+ *                         Assumption is these functions will be called after
+ *                         clocks are enabled
+ *  @setup_csc:            Programs the csc matrix
+ *  @setup_cdwn:           Sets up the chroma down sub module
+ *  @enable:               Enables the output to interface and programs the
+ *                         output packer
+ *  @disable:              Puts the cdm in bypass mode
+ */
+struct dpu_hw_cdm_ops {
+	/**
+	 * Programs the CSC matrix for conversion from RGB space to YUV space,
+	 * it is optional to call this function as this matrix is automatically
+	 * set during initialization, user should call this if it wants
+	 * to program a different matrix than default matrix.
+	 * @cdm:          Pointer to the chroma down context structure
+	 * @data          Pointer to CSC configuration data
+	 * return:        0 if success; error code otherwise
+	 */
+	int (*setup_csc_data)(struct dpu_hw_cdm *cdm,
+			struct dpu_csc_cfg *data);
+
+	/**
+	 * Programs the Chroma downsample part.
+	 * @cdm         Pointer to chroma down context
+	 */
+	int (*setup_cdwn)(struct dpu_hw_cdm *cdm,
+	struct dpu_hw_cdm_cfg *cfg);
+
+	/**
+	 * Enable the CDM module
+	 * @cdm         Pointer to chroma down context
+	 */
+	int (*enable)(struct dpu_hw_cdm *cdm,
+	struct dpu_hw_cdm_cfg *cfg);
+
+	/**
+	 * Disable the CDM module
+	 * @cdm         Pointer to chroma down context
+	 */
+	void (*disable)(struct dpu_hw_cdm *cdm);
+};
+
+struct dpu_hw_cdm {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* chroma down */
+	const struct dpu_cdm_cfg *caps;
+	enum  dpu_cdm  idx;
+
+	/* mdp top hw driver */
+	struct dpu_hw_mdp *hw_mdp;
+
+	/* ops */
+	struct dpu_hw_cdm_ops ops;
+};
+
+/**
+ * dpu_hw_cdm - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_cdm *to_dpu_hw_cdm(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_cdm, base);
+}
+
+/**
+ * dpu_hw_cdm_init - initializes the cdm hw driver object.
+ * should be called once before accessing every cdm.
+ * @idx:  cdm index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ * @hw_mdp:  pointer to mdp top hw driver object
+ */
+struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m,
+		struct dpu_hw_mdp *hw_mdp);
+
+/**
+ * dpu_hw_cdm_destroy - destroys CDM driver context
+ * @cdm:   pointer to CDM driver context
+ */
+void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm);
+
+#endif /*_DPU_HW_CDM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
new file mode 100644
index 000000000000..06be7cf7ce50
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -0,0 +1,540 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define   CTL_LAYER(lm)                 \
+	(((lm) == LM_5) ? (0x024) : (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT(lm)             \
+	(0x40 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT2(lm)             \
+	(0x70 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT3(lm)             \
+	(0xA0 + (((lm) - LM_0) * 0x004))
+#define   CTL_TOP                       0x014
+#define   CTL_FLUSH                     0x018
+#define   CTL_START                     0x01C
+#define   CTL_PREPARE                   0x0d0
+#define   CTL_SW_RESET                  0x030
+#define   CTL_LAYER_EXTN_OFFSET         0x40
+
+#define CTL_MIXER_BORDER_OUT            BIT(24)
+#define CTL_FLUSH_MASK_CTL              BIT(17)
+
+#define DPU_REG_RESET_TIMEOUT_US        2000
+
+static struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->ctl_count; i++) {
+		if (ctl == m->ctl[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->ctl[i].base;
+			b->length = m->ctl[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_CTL;
+			return &m->ctl[i];
+		}
+	}
+	return ERR_PTR(-ENOMEM);
+}
+
+static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
+		enum dpu_lm lm)
+{
+	int i;
+	int stages = -EINVAL;
+
+	for (i = 0; i < count; i++) {
+		if (lm == mixer[i].id) {
+			stages = mixer[i].sblk->maxblendstages;
+			break;
+		}
+	}
+
+	return stages;
+}
+
+static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx)
+{
+	DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1);
+}
+
+static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx)
+{
+	DPU_REG_WRITE(&ctx->hw, CTL_PREPARE, 0x1);
+}
+
+static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	ctx->pending_flush_mask = 0x0;
+}
+
+static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
+		u32 flushbits)
+{
+	ctx->pending_flush_mask |= flushbits;
+}
+
+static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	if (!ctx)
+		return 0x0;
+
+	return ctx->pending_flush_mask;
+}
+
+static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
+{
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
+static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, CTL_FLUSH);
+}
+
+static inline uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx,
+	enum dpu_sspp sspp)
+{
+	uint32_t flushbits = 0;
+
+	switch (sspp) {
+	case SSPP_VIG0:
+		flushbits =  BIT(0);
+		break;
+	case SSPP_VIG1:
+		flushbits = BIT(1);
+		break;
+	case SSPP_VIG2:
+		flushbits = BIT(2);
+		break;
+	case SSPP_VIG3:
+		flushbits = BIT(18);
+		break;
+	case SSPP_RGB0:
+		flushbits = BIT(3);
+		break;
+	case SSPP_RGB1:
+		flushbits = BIT(4);
+		break;
+	case SSPP_RGB2:
+		flushbits = BIT(5);
+		break;
+	case SSPP_RGB3:
+		flushbits = BIT(19);
+		break;
+	case SSPP_DMA0:
+		flushbits = BIT(11);
+		break;
+	case SSPP_DMA1:
+		flushbits = BIT(12);
+		break;
+	case SSPP_DMA2:
+		flushbits = BIT(24);
+		break;
+	case SSPP_DMA3:
+		flushbits = BIT(25);
+		break;
+	case SSPP_CURSOR0:
+		flushbits = BIT(22);
+		break;
+	case SSPP_CURSOR1:
+		flushbits = BIT(23);
+		break;
+	default:
+		break;
+	}
+
+	return flushbits;
+}
+
+static inline uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm)
+{
+	uint32_t flushbits = 0;
+
+	switch (lm) {
+	case LM_0:
+		flushbits = BIT(6);
+		break;
+	case LM_1:
+		flushbits = BIT(7);
+		break;
+	case LM_2:
+		flushbits = BIT(8);
+		break;
+	case LM_3:
+		flushbits = BIT(9);
+		break;
+	case LM_4:
+		flushbits = BIT(10);
+		break;
+	case LM_5:
+		flushbits = BIT(20);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	flushbits |= CTL_FLUSH_MASK_CTL;
+
+	return flushbits;
+}
+
+static inline int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+		*flushbits |= BIT(31);
+		break;
+	case INTF_1:
+		*flushbits |= BIT(30);
+		break;
+	case INTF_2:
+		*flushbits |= BIT(29);
+		break;
+	case INTF_3:
+		*flushbits |= BIT(28);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static inline int dpu_hw_ctl_get_bitmask_cdm(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_cdm cdm)
+{
+	switch (cdm) {
+	case CDM_0:
+		*flushbits |= BIT(26);
+		break;
+	default:
+		return -EINVAL;
+	}
+	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;
+	ktime_t timeout;
+	u32 status;
+
+	timeout = ktime_add_us(ktime_get(), timeout_us);
+
+	/*
+	 * it takes around 30us to have mdp finish resetting its ctl path
+	 * poll every 50us so that reset should be completed at 1st poll
+	 */
+	do {
+		status = DPU_REG_READ(c, CTL_SW_RESET);
+		status &= 0x1;
+		if (status)
+			usleep_range(20, 50);
+	} while (status && ktime_compare_safe(ktime_get(), timeout) < 0);
+
+	return status;
+}
+
+static int dpu_hw_ctl_reset_control(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	pr_debug("issuing hw ctl reset for ctl:%d\n", ctx->idx);
+	DPU_REG_WRITE(c, CTL_SW_RESET, 0x1);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int dpu_hw_ctl_wait_reset_status(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 status;
+
+	status = DPU_REG_READ(c, CTL_SW_RESET);
+	status &= 0x01;
+	if (!status)
+		return 0;
+
+	pr_debug("hw ctl reset is set for ctl:%d\n", ctx->idx);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US)) {
+		pr_err("hw recovery is not complete for ctl:%d\n", ctx->idx);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int i;
+
+	for (i = 0; i < ctx->mixer_count; i++) {
+		DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0);
+	}
+}
+
+static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm, struct dpu_hw_stage_cfg *stage_cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 mixercfg = 0, mixercfg_ext = 0, mix, ext;
+	u32 mixercfg_ext2 = 0, mixercfg_ext3 = 0;
+	int i, j;
+	u8 stages;
+	int pipes_per_stage;
+
+	stages = _mixer_stages(ctx->mixer_hw_caps, ctx->mixer_count, lm);
+	if (stages < 0)
+		return;
+
+	if (test_bit(DPU_MIXER_SOURCESPLIT,
+		&ctx->mixer_hw_caps->features))
+		pipes_per_stage = PIPES_PER_STAGE;
+	else
+		pipes_per_stage = 1;
+
+	mixercfg = CTL_MIXER_BORDER_OUT; /* always set BORDER_OUT */
+
+	if (!stage_cfg)
+		goto exit;
+
+	for (i = 0; i <= stages; i++) {
+		/* overflow to ext register if 'i + 1 > 7' */
+		mix = (i + 1) & 0x7;
+		ext = i >= 7;
+
+		for (j = 0 ; j < pipes_per_stage; j++) {
+			enum dpu_sspp_multirect_index rect_index =
+				stage_cfg->multirect_index[i][j];
+
+			switch (stage_cfg->stage[i][j]) {
+			case SSPP_VIG0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 0;
+				} else {
+					mixercfg |= mix << 0;
+					mixercfg_ext |= ext << 0;
+				}
+				break;
+			case SSPP_VIG1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 4;
+				} else {
+					mixercfg |= mix << 3;
+					mixercfg_ext |= ext << 2;
+				}
+				break;
+			case SSPP_VIG2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 6;
+					mixercfg_ext |= ext << 4;
+				}
+				break;
+			case SSPP_VIG3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 26;
+					mixercfg_ext |= ext << 6;
+				}
+				break;
+			case SSPP_RGB0:
+				mixercfg |= mix << 9;
+				mixercfg_ext |= ext << 8;
+				break;
+			case SSPP_RGB1:
+				mixercfg |= mix << 12;
+				mixercfg_ext |= ext << 10;
+				break;
+			case SSPP_RGB2:
+				mixercfg |= mix << 15;
+				mixercfg_ext |= ext << 12;
+				break;
+			case SSPP_RGB3:
+				mixercfg |= mix << 29;
+				mixercfg_ext |= ext << 14;
+				break;
+			case SSPP_DMA0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 18;
+					mixercfg_ext |= ext << 16;
+				}
+				break;
+			case SSPP_DMA1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 21;
+					mixercfg_ext |= ext << 18;
+				}
+				break;
+			case SSPP_DMA2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 16;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 0;
+				}
+				break;
+			case SSPP_DMA3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 20;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 4;
+				}
+				break;
+			case SSPP_CURSOR0:
+				mixercfg_ext |= ((i + 1) & 0xF) << 20;
+				break;
+			case SSPP_CURSOR1:
+				mixercfg_ext |= ((i + 1) & 0xF) << 26;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+exit:
+	DPU_REG_WRITE(c, CTL_LAYER(lm), mixercfg);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT(lm), mixercfg_ext);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT2(lm), mixercfg_ext2);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3);
+}
+
+static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_cfg = 0;
+
+	intf_cfg |= (cfg->intf & 0xF) << 4;
+
+	if (cfg->mode_3d) {
+		intf_cfg |= BIT(19);
+		intf_cfg |= (cfg->mode_3d - 0x1) << 20;
+	}
+
+	switch (cfg->intf_mode_sel) {
+	case DPU_CTL_MODE_SEL_VID:
+		intf_cfg &= ~BIT(17);
+		intf_cfg &= ~(0x3 << 15);
+		break;
+	case DPU_CTL_MODE_SEL_CMD:
+		intf_cfg |= BIT(17);
+		intf_cfg |= ((cfg->stream_sel & 0x3) << 15);
+		break;
+	default:
+		pr_err("unknown interface type %d\n", cfg->intf_mode_sel);
+		return;
+	}
+
+	DPU_REG_WRITE(c, CTL_TOP, intf_cfg);
+}
+
+static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
+		unsigned long cap)
+{
+	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;
+	ops->get_bitmask_cdm = dpu_hw_ctl_get_bitmask_cdm;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_ctl *c;
+	struct dpu_ctl_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _ctl_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_ctl %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->caps = cfg;
+	_setup_ctl_ops(&c->ops, c->caps->features);
+	c->idx = idx;
+	c->mixer_count = m->mixer_count;
+	c->mixer_hw_caps = m->mixer;
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CTL, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx)
+{
+	if (ctx)
+		dpu_hw_blk_destroy(&ctx->base);
+	kfree(ctx);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
new file mode 100644
index 000000000000..c66a71f8b839
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
@@ -0,0 +1,218 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CTL_H
+#define _DPU_HW_CTL_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_hw_blk.h"
+
+/**
+ * dpu_ctl_mode_sel: Interface mode selection
+ * DPU_CTL_MODE_SEL_VID:    Video mode interface
+ * DPU_CTL_MODE_SEL_CMD:    Command mode interface
+ */
+enum dpu_ctl_mode_sel {
+	DPU_CTL_MODE_SEL_VID = 0,
+	DPU_CTL_MODE_SEL_CMD
+};
+
+struct dpu_hw_ctl;
+/**
+ * struct dpu_hw_stage_cfg - blending stage cfg
+ * @stage : SSPP_ID at each stage
+ * @multirect_index: index of the rectangle of SSPP.
+ */
+struct dpu_hw_stage_cfg {
+	enum dpu_sspp stage[DPU_STAGE_MAX][PIPES_PER_STAGE];
+	enum dpu_sspp_multirect_index multirect_index
+					[DPU_STAGE_MAX][PIPES_PER_STAGE];
+};
+
+/**
+ * struct dpu_hw_intf_cfg :Describes how the DPU writes data to output interface
+ * @intf :                 Interface id
+ * @mode_3d:               3d mux configuration
+ * @intf_mode_sel:         Interface mode, cmd / vid
+ * @stream_sel:            Stream selection for multi-stream interfaces
+ */
+struct dpu_hw_intf_cfg {
+	enum dpu_intf intf;
+	enum dpu_3d_blend_mode mode_3d;
+	enum dpu_ctl_mode_sel intf_mode_sel;
+	int stream_sel;
+};
+
+/**
+ * struct dpu_hw_ctl_ops - Interface to the wb Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_ctl_ops {
+	/**
+	 * kickoff hw operation for Sw controlled interfaces
+	 * DSI cmd mode and WB interface are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_start)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * kickoff prepare is in progress hw operation for sw
+	 * controlled interfaces: DSI cmd mode and WB interface
+	 * are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_pending)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Clear the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Query the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	u32 (*get_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @flushbits : module flushmask
+	 */
+	void (*update_pending_flush)(struct dpu_hw_ctl *ctx,
+		u32 flushbits);
+
+	/**
+	 * Write the value of the pending_flush_mask to hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Read the value of the flush register
+	 * @ctx       : ctl path ctx pointer
+	 * @Return: value of the ctl flush register.
+	 */
+	u32 (*get_flush_register)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Setup ctl_path interface config
+	 * @ctx
+	 * @cfg    : interface config structure pointer
+	 */
+	void (*setup_intf_cfg)(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg);
+
+	int (*reset)(struct dpu_hw_ctl *c);
+
+	/*
+	 * wait_reset_status - checks ctl reset status
+	 * @ctx       : ctl path ctx pointer
+	 *
+	 * This function checks the ctl reset status bit.
+	 * If the reset bit is set, it keeps polling the status till the hw
+	 * reset is complete.
+	 * Returns: 0 on success or -error if reset incomplete within interval
+	 */
+	int (*wait_reset_status)(struct dpu_hw_ctl *ctx);
+
+	uint32_t (*get_bitmask_sspp)(struct dpu_hw_ctl *ctx,
+		enum dpu_sspp blk);
+
+	uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm blk);
+
+	int (*get_bitmask_intf)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits,
+		enum dpu_intf blk);
+
+	int (*get_bitmask_cdm)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits,
+		enum dpu_cdm blk);
+
+	/**
+	 * Set all blend stages to disabled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_all_blendstages)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Configure layer mixer to pipe configuration
+	 * @ctx       : ctl path ctx pointer
+	 * @lm        : layer mixer enumeration
+	 * @cfg       : blend stage configuration
+	 */
+	void (*setup_blendstage)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg);
+};
+
+/**
+ * struct dpu_hw_ctl : CTL PATH driver object
+ * @base: hardware block base structure
+ * @hw: block register map object
+ * @idx: control path index
+ * @caps: control path capabilities
+ * @mixer_count: number of mixers
+ * @mixer_hw_caps: mixer hardware capabilities
+ * @pending_flush_mask: storage for pending ctl_flush managed via ops
+ * @ops: operation list
+ */
+struct dpu_hw_ctl {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* ctl path */
+	int idx;
+	const struct dpu_ctl_cfg *caps;
+	int mixer_count;
+	const struct dpu_lm_cfg *mixer_hw_caps;
+	u32 pending_flush_mask;
+
+	/* ops */
+	struct dpu_hw_ctl_ops ops;
+};
+
+/**
+ * dpu_hw_ctl - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_ctl, base);
+}
+
+/**
+ * dpu_hw_ctl_init(): Initializes the ctl_path hw driver object.
+ * should be called before accessing every ctl path registers.
+ * @idx:  ctl_path index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_ctl_destroy(): Destroys ctl driver context
+ * should be called to free the context
+ */
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx);
+
+#endif /*_DPU_HW_CTL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
new file mode 100644
index 000000000000..c0b7f0049365
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -0,0 +1,1183 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/slab.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * Register offsets in MDSS register file for the interrupt registers
+ * w.r.t. to the MDP base
+ */
+#define MDP_SSPP_TOP0_OFF		0x0
+#define MDP_INTF_0_OFF			0x6A000
+#define MDP_INTF_1_OFF			0x6A800
+#define MDP_INTF_2_OFF			0x6B000
+#define MDP_INTF_3_OFF			0x6B800
+#define MDP_INTF_4_OFF			0x6C000
+#define MDP_AD4_0_OFF			0x7C000
+#define MDP_AD4_1_OFF			0x7D000
+#define MDP_AD4_INTR_EN_OFF		0x41c
+#define MDP_AD4_INTR_CLEAR_OFF		0x424
+#define MDP_AD4_INTR_STATUS_OFF		0x420
+
+/**
+ * WB interrupt status bit definitions
+ */
+#define DPU_INTR_WB_0_DONE BIT(0)
+#define DPU_INTR_WB_1_DONE BIT(1)
+#define DPU_INTR_WB_2_DONE BIT(4)
+
+/**
+ * WDOG timer interrupt status bit definitions
+ */
+#define DPU_INTR_WD_TIMER_0_DONE BIT(2)
+#define DPU_INTR_WD_TIMER_1_DONE BIT(3)
+#define DPU_INTR_WD_TIMER_2_DONE BIT(5)
+#define DPU_INTR_WD_TIMER_3_DONE BIT(6)
+#define DPU_INTR_WD_TIMER_4_DONE BIT(7)
+
+/**
+ * Pingpong interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_DONE BIT(8)
+#define DPU_INTR_PING_PONG_1_DONE BIT(9)
+#define DPU_INTR_PING_PONG_2_DONE BIT(10)
+#define DPU_INTR_PING_PONG_3_DONE BIT(11)
+#define DPU_INTR_PING_PONG_0_RD_PTR BIT(12)
+#define DPU_INTR_PING_PONG_1_RD_PTR BIT(13)
+#define DPU_INTR_PING_PONG_2_RD_PTR BIT(14)
+#define DPU_INTR_PING_PONG_3_RD_PTR BIT(15)
+#define DPU_INTR_PING_PONG_0_WR_PTR BIT(16)
+#define DPU_INTR_PING_PONG_1_WR_PTR BIT(17)
+#define DPU_INTR_PING_PONG_2_WR_PTR BIT(18)
+#define DPU_INTR_PING_PONG_3_WR_PTR BIT(19)
+#define DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE BIT(20)
+#define DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE BIT(21)
+#define DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE BIT(22)
+#define DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE BIT(23)
+
+/**
+ * Interface interrupt status bit definitions
+ */
+#define DPU_INTR_INTF_0_UNDERRUN BIT(24)
+#define DPU_INTR_INTF_1_UNDERRUN BIT(26)
+#define DPU_INTR_INTF_2_UNDERRUN BIT(28)
+#define DPU_INTR_INTF_3_UNDERRUN BIT(30)
+#define DPU_INTR_INTF_0_VSYNC BIT(25)
+#define DPU_INTR_INTF_1_VSYNC BIT(27)
+#define DPU_INTR_INTF_2_VSYNC BIT(29)
+#define DPU_INTR_INTF_3_VSYNC BIT(31)
+
+/**
+ * Pingpong Secondary interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE BIT(0)
+#define DPU_INTR_PING_PONG_S0_WR_PTR BIT(4)
+#define DPU_INTR_PING_PONG_S0_RD_PTR BIT(8)
+#define DPU_INTR_PING_PONG_S0_TEAR_DETECTED BIT(22)
+#define DPU_INTR_PING_PONG_S0_TE_DETECTED BIT(28)
+
+/**
+ * Pingpong TEAR detection interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_TEAR_DETECTED BIT(16)
+#define DPU_INTR_PING_PONG_1_TEAR_DETECTED BIT(17)
+#define DPU_INTR_PING_PONG_2_TEAR_DETECTED BIT(18)
+#define DPU_INTR_PING_PONG_3_TEAR_DETECTED BIT(19)
+
+/**
+ * Pingpong TE detection interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_TE_DETECTED BIT(24)
+#define DPU_INTR_PING_PONG_1_TE_DETECTED BIT(25)
+#define DPU_INTR_PING_PONG_2_TE_DETECTED BIT(26)
+#define DPU_INTR_PING_PONG_3_TE_DETECTED BIT(27)
+
+/**
+ * Ctl start interrupt status bit definitions
+ */
+#define DPU_INTR_CTL_0_START BIT(9)
+#define DPU_INTR_CTL_1_START BIT(10)
+#define DPU_INTR_CTL_2_START BIT(11)
+#define DPU_INTR_CTL_3_START BIT(12)
+#define DPU_INTR_CTL_4_START BIT(13)
+
+/**
+ * Concurrent WB overflow interrupt status bit definitions
+ */
+#define DPU_INTR_CWB_2_OVERFLOW BIT(14)
+#define DPU_INTR_CWB_3_OVERFLOW BIT(15)
+
+/**
+ * Histogram VIG done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_VIG_0_DONE BIT(0)
+#define DPU_INTR_HIST_VIG_1_DONE BIT(4)
+#define DPU_INTR_HIST_VIG_2_DONE BIT(8)
+#define DPU_INTR_HIST_VIG_3_DONE BIT(10)
+
+/**
+ * Histogram VIG reset Sequence done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_VIG_0_RSTSEQ_DONE BIT(1)
+#define DPU_INTR_HIST_VIG_1_RSTSEQ_DONE BIT(5)
+#define DPU_INTR_HIST_VIG_2_RSTSEQ_DONE BIT(9)
+#define DPU_INTR_HIST_VIG_3_RSTSEQ_DONE BIT(11)
+
+/**
+ * Histogram DSPP done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_DSPP_0_DONE BIT(12)
+#define DPU_INTR_HIST_DSPP_1_DONE BIT(16)
+#define DPU_INTR_HIST_DSPP_2_DONE BIT(20)
+#define DPU_INTR_HIST_DSPP_3_DONE BIT(22)
+
+/**
+ * Histogram DSPP reset Sequence done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE BIT(13)
+#define DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE BIT(17)
+#define DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE BIT(21)
+#define DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE BIT(23)
+
+/**
+ * INTF interrupt status bit definitions
+ */
+#define DPU_INTR_VIDEO_INTO_STATIC BIT(0)
+#define DPU_INTR_VIDEO_OUTOF_STATIC BIT(1)
+#define DPU_INTR_DSICMD_0_INTO_STATIC BIT(2)
+#define DPU_INTR_DSICMD_0_OUTOF_STATIC BIT(3)
+#define DPU_INTR_DSICMD_1_INTO_STATIC BIT(4)
+#define DPU_INTR_DSICMD_1_OUTOF_STATIC BIT(5)
+#define DPU_INTR_DSICMD_2_INTO_STATIC BIT(6)
+#define DPU_INTR_DSICMD_2_OUTOF_STATIC BIT(7)
+#define DPU_INTR_PROG_LINE BIT(8)
+
+/**
+ * AD4 interrupt status bit definitions
+ */
+#define DPU_INTR_BRIGHTPR_UPDATED BIT(4)
+#define DPU_INTR_DARKENH_UPDATED BIT(3)
+#define DPU_INTR_STREN_OUTROI_UPDATED BIT(2)
+#define DPU_INTR_STREN_INROI_UPDATED BIT(1)
+#define DPU_INTR_BACKLIGHT_UPDATED BIT(0)
+/**
+ * struct dpu_intr_reg - array of DPU register sets
+ * @clr_off:	offset to CLEAR reg
+ * @en_off:	offset to ENABLE reg
+ * @status_off:	offset to STATUS reg
+ */
+struct dpu_intr_reg {
+	u32 clr_off;
+	u32 en_off;
+	u32 status_off;
+};
+
+/**
+ * struct dpu_irq_type - maps each irq with i/f
+ * @intr_type:		type of interrupt listed in dpu_intr_type
+ * @instance_idx:	instance index of the associated HW block in DPU
+ * @irq_mask:		corresponding bit in the interrupt status reg
+ * @reg_idx:		which reg set to use
+ */
+struct dpu_irq_type {
+	u32 intr_type;
+	u32 instance_idx;
+	u32 irq_mask;
+	u32 reg_idx;
+};
+
+/**
+ * List of DPU interrupt registers
+ */
+static const struct dpu_intr_reg dpu_intr_set[] = {
+	{
+		MDP_SSPP_TOP0_OFF+INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR_EN,
+		MDP_SSPP_TOP0_OFF+INTR_STATUS
+	},
+	{
+		MDP_SSPP_TOP0_OFF+INTR2_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR2_EN,
+		MDP_SSPP_TOP0_OFF+INTR2_STATUS
+	},
+	{
+		MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_EN,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS
+	},
+	{
+		MDP_INTF_0_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_0_OFF+INTF_INTR_EN,
+		MDP_INTF_0_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_1_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_1_OFF+INTF_INTR_EN,
+		MDP_INTF_1_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_2_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_2_OFF+INTF_INTR_EN,
+		MDP_INTF_2_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_3_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_3_OFF+INTF_INTR_EN,
+		MDP_INTF_3_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_4_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_4_OFF+INTF_INTR_EN,
+		MDP_INTF_4_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF,
+	},
+	{
+		MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF,
+	}
+};
+
+/**
+ * IRQ mapping table - use for lookup an irq_idx in this table that have
+ *                     a matching interface type and instance index.
+ */
+static const struct dpu_irq_type dpu_irq_map[] = {
+	/* BEGIN MAP_RANGE: 0-31, INTR */
+	/* irq_idx: 0-3 */
+	{ DPU_IRQ_TYPE_WB_ROT_COMP, WB_0, DPU_INTR_WB_0_DONE, 0},
+	{ DPU_IRQ_TYPE_WB_ROT_COMP, WB_1, DPU_INTR_WB_1_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_0, DPU_INTR_WD_TIMER_0_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_1, DPU_INTR_WD_TIMER_1_DONE, 0},
+	/* irq_idx: 4-7 */
+	{ DPU_IRQ_TYPE_WB_WFD_COMP, WB_2, DPU_INTR_WB_2_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_2, DPU_INTR_WD_TIMER_2_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_3, DPU_INTR_WD_TIMER_3_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_4, DPU_INTR_WD_TIMER_4_DONE, 0},
+	/* irq_idx: 8-11 */
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_DONE, 0},
+	/* irq_idx: 12-15 */
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_RD_PTR, 0},
+	/* irq_idx: 16-19 */
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_WR_PTR, 0},
+	/* irq_idx: 20-23 */
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE, 0},
+	/* irq_idx: 24-27 */
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_0, DPU_INTR_INTF_0_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_0, DPU_INTR_INTF_0_VSYNC, 0},
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_1, DPU_INTR_INTF_1_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_1, DPU_INTR_INTF_1_VSYNC, 0},
+	/* irq_idx: 28-31 */
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_2, DPU_INTR_INTF_2_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_2, DPU_INTR_INTF_2_VSYNC, 0},
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_3, DPU_INTR_INTF_3_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_3, DPU_INTR_INTF_3_VSYNC, 0},
+
+	/* BEGIN MAP_RANGE: 32-64, INTR2 */
+	/* irq_idx: 32-35 */
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 36-39 */
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_WR_PTR, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 40 */
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_RD_PTR, 1},
+	/* irq_idx: 41-45 */
+	{ DPU_IRQ_TYPE_CTL_START, CTL_0,
+		DPU_INTR_CTL_0_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_1,
+		DPU_INTR_CTL_1_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_2,
+		DPU_INTR_CTL_2_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_3,
+		DPU_INTR_CTL_3_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_4,
+		DPU_INTR_CTL_4_START, 1},
+	/* irq_idx: 46-47 */
+	{ DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_2, DPU_INTR_CWB_2_OVERFLOW, 1},
+	{ DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_3, DPU_INTR_CWB_3_OVERFLOW, 1},
+	/* irq_idx: 48-51 */
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_TEAR_DETECTED, 1},
+	/* irq_idx: 52-55 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 56-59 */
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_TE_DETECTED, 1},
+	/* irq_idx: 60-63 */
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+
+	/* BEGIN MAP_RANGE: 64-95 HIST */
+	/* irq_idx: 64-67 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG0, DPU_INTR_HIST_VIG_0_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG0,
+		DPU_INTR_HIST_VIG_0_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 68-71 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG1, DPU_INTR_HIST_VIG_1_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG1,
+		DPU_INTR_HIST_VIG_1_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 72-75 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG2, DPU_INTR_HIST_VIG_2_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG2,
+		DPU_INTR_HIST_VIG_2_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG3, DPU_INTR_HIST_VIG_3_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG3,
+		DPU_INTR_HIST_VIG_3_RSTSEQ_DONE, 2},
+	/* irq_idx: 76-79 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_0, DPU_INTR_HIST_DSPP_0_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_0,
+		DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 80-83 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_1, DPU_INTR_HIST_DSPP_1_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_1,
+		DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 84-87 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_2, DPU_INTR_HIST_DSPP_2_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_2,
+		DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_3, DPU_INTR_HIST_DSPP_3_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_3,
+		DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE, 2},
+	/* irq_idx: 88-91 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 92-95 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+
+	/* BEGIN MAP_RANGE: 96-127 INTF_0_INTR */
+	/* irq_idx: 96-99 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_0,
+		DPU_INTR_VIDEO_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_0,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_0,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_0,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 3},
+	/* irq_idx: 100-103 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_0,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_0,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_0,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_0,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 3},
+	/* irq_idx: 104-107 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_0, DPU_INTR_PROG_LINE, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 108-111 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 112-115 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 116-119 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 120-123 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 124-127 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+
+	/* BEGIN MAP_RANGE: 128-159 INTF_1_INTR */
+	/* irq_idx: 128-131 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_1,
+		DPU_INTR_VIDEO_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_1,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_1,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_1,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 4},
+	/* irq_idx: 132-135 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_1,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_1,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_1,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_1,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 4},
+	/* irq_idx: 136-139 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_1, DPU_INTR_PROG_LINE, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 140-143 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 144-147 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 148-151 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 152-155 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 156-159 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+
+	/* BEGIN MAP_RANGE: 160-191 INTF_2_INTR */
+	/* irq_idx: 160-163 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_2,
+		DPU_INTR_VIDEO_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_2,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_2,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_2,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 5},
+	/* irq_idx: 164-167 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_2,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_2,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_2,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_2,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 5},
+	/* irq_idx: 168-171 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_2, DPU_INTR_PROG_LINE, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 172-175 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 176-179 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 180-183 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 184-187 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 188-191 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+
+	/* BEGIN MAP_RANGE: 192-223 INTF_3_INTR */
+	/* irq_idx: 192-195 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_3,
+		DPU_INTR_VIDEO_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_3,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_3,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_3,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 6},
+	/* irq_idx: 196-199 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_3,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_3,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_3,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_3,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 6},
+	/* irq_idx: 200-203 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_3, DPU_INTR_PROG_LINE, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 204-207 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 208-211 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 212-215 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 216-219 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 220-223 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+
+	/* BEGIN MAP_RANGE: 224-255 INTF_4_INTR */
+	/* irq_idx: 224-227 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_4,
+		DPU_INTR_VIDEO_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_4,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_4,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_4,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 7},
+	/* irq_idx: 228-231 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_4,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_4,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_4,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_4,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 7},
+	/* irq_idx: 232-235 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_4, DPU_INTR_PROG_LINE, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 236-239 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 240-243 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 244-247 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 248-251 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 252-255 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+
+	/* BEGIN MAP_RANGE: 256-287 AD4_0_INTR */
+	/* irq_idx: 256-259 */
+	{ DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_0, DPU_INTR_BACKLIGHT_UPDATED, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 260-263 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 264-267 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 268-271 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 272-275 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 276-279 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 280-283 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 284-287 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+
+	/* BEGIN MAP_RANGE: 288-319 AD4_1_INTR */
+	/* irq_idx: 288-291 */
+	{ DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_1, DPU_INTR_BACKLIGHT_UPDATED, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 292-295 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 296-299 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 300-303 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 304-307 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 308-311 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 312-315 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 315-319 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+};
+
+static int dpu_hw_intr_irqidx_lookup(enum dpu_intr_type intr_type,
+		u32 instance_idx)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_irq_map); i++) {
+		if (intr_type == dpu_irq_map[i].intr_type &&
+			instance_idx == dpu_irq_map[i].instance_idx)
+			return i;
+	}
+
+	pr_debug("IRQ lookup fail!! intr_type=%d, instance_idx=%d\n",
+			intr_type, instance_idx);
+	return -EINVAL;
+}
+
+static void dpu_hw_intr_set_mask(struct dpu_hw_intr *intr, uint32_t reg_off,
+		uint32_t mask)
+{
+	if (!intr)
+		return;
+
+	DPU_REG_WRITE(&intr->hw, reg_off, mask);
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr,
+		void (*cbfunc)(void *, int),
+		void *arg)
+{
+	int reg_idx;
+	int irq_idx;
+	int start_idx;
+	int end_idx;
+	u32 irq_status;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	/*
+	 * The dispatcher will save the IRQ status before calling here.
+	 * Now need to go through each IRQ status and find matching
+	 * irq lookup index.
+	 */
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (reg_idx = 0; reg_idx < ARRAY_SIZE(dpu_intr_set); reg_idx++) {
+		irq_status = intr->save_irq_status[reg_idx];
+
+		/*
+		 * Each Interrupt register has a range of 32 indexes, and
+		 * that is static for dpu_irq_map.
+		 */
+		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))
+			continue;
+
+		/*
+		 * Search through matching intr status from irq map.
+		 * start_idx and end_idx defined the search range in
+		 * the dpu_irq_map.
+		 */
+		for (irq_idx = start_idx;
+				(irq_idx < end_idx) && irq_status;
+				irq_idx++)
+			if ((irq_status & dpu_irq_map[irq_idx].irq_mask) &&
+				(dpu_irq_map[irq_idx].reg_idx == reg_idx)) {
+				/*
+				 * Once a match on irq mask, perform a callback
+				 * to the given cbfunc. cbfunc will take care
+				 * the interrupt status clearing. If cbfunc is
+				 * not provided, then the interrupt clearing
+				 * is here.
+				 */
+				if (cbfunc)
+					cbfunc(arg, irq_idx);
+				else
+					intr->ops.clear_intr_status_nolock(
+							intr, irq_idx);
+
+				/*
+				 * When callback finish, clear the irq_status
+				 * with the matching mask. Once irq_status
+				 * is all cleared, the search can be stopped.
+				 */
+				irq_status &= ~dpu_irq_map[irq_idx].irq_mask;
+			}
+	}
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static int dpu_hw_intr_enable_irq(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	unsigned long irq_flags;
+	const struct dpu_intr_reg *reg;
+	const struct dpu_irq_type *irq;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	irq = &dpu_irq_map[irq_idx];
+	reg_idx = irq->reg_idx;
+	reg = &dpu_intr_set[reg_idx];
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if (cache_irq_mask & irq->irq_mask) {
+		dbgstr = "DPU IRQ already set:";
+	} else {
+		dbgstr = "DPU IRQ enabled:";
+
+		cache_irq_mask |= irq->irq_mask;
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask);
+		/* Enabling interrupts with the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr,
+			irq->irq_mask, cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq_nolock(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	const struct dpu_intr_reg *reg;
+	const struct dpu_irq_type *irq;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	irq = &dpu_irq_map[irq_idx];
+	reg_idx = irq->reg_idx;
+	reg = &dpu_intr_set[reg_idx];
+
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if ((cache_irq_mask & irq->irq_mask) == 0) {
+		dbgstr = "DPU IRQ is already cleared:";
+	} else {
+		dbgstr = "DPU IRQ mask disable:";
+
+		cache_irq_mask &= ~irq->irq_mask;
+		/* Disable interrupts based on the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+
+	pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr,
+			irq->irq_mask, cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq(struct dpu_hw_intr *intr, int irq_idx)
+{
+	unsigned long irq_flags;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	dpu_hw_intr_disable_irq_nolock(intr, irq_idx);
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return 0;
+}
+
+static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr)
+{
+	int i;
+
+	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);
+
+	/* ensure register writes go through */
+	wmb();
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr)
+{
+	int i;
+
+	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);
+
+	/* ensure register writes go through */
+	wmb();
+
+	return 0;
+}
+
+static int dpu_hw_intr_get_valid_interrupts(struct dpu_hw_intr *intr,
+		uint32_t *mask)
+{
+	if (!intr || !mask)
+		return -EINVAL;
+
+	*mask = IRQ_SOURCE_MDP | IRQ_SOURCE_DSI0 | IRQ_SOURCE_DSI1
+		| IRQ_SOURCE_HDMI | IRQ_SOURCE_EDP;
+
+	return 0;
+}
+
+static void dpu_hw_intr_get_interrupt_statuses(struct dpu_hw_intr *intr)
+{
+	int i;
+	u32 enable_mask;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		/* Read interrupt status */
+		intr->save_irq_status[i] = DPU_REG_READ(&intr->hw,
+				dpu_intr_set[i].status_off);
+
+		/* Read enable mask */
+		enable_mask = DPU_REG_READ(&intr->hw, dpu_intr_set[i].en_off);
+
+		/* and clear the interrupt */
+		if (intr->save_irq_status[i])
+			DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off,
+					intr->save_irq_status[i]);
+
+		/* Finally update IRQ status based on enable mask */
+		intr->save_irq_status[i] &= enable_mask;
+	}
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static void dpu_hw_intr_clear_intr_status_nolock(struct dpu_hw_intr *intr,
+		int irq_idx)
+{
+	int reg_idx;
+
+	if (!intr)
+		return;
+
+	reg_idx = dpu_irq_map[irq_idx].reg_idx;
+	DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+			dpu_irq_map[irq_idx].irq_mask);
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_hw_intr_clear_interrupt_status(struct dpu_hw_intr *intr,
+		int irq_idx)
+{
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	dpu_hw_intr_clear_intr_status_nolock(intr, irq_idx);
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr,
+		int irq_idx, bool clear)
+{
+	int reg_idx;
+	unsigned long irq_flags;
+	u32 intr_status;
+
+	if (!intr)
+		return 0;
+
+	if (irq_idx >= ARRAY_SIZE(dpu_irq_map) || irq_idx < 0) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return 0;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+
+	reg_idx = dpu_irq_map[irq_idx].reg_idx;
+	intr_status = DPU_REG_READ(&intr->hw,
+			dpu_intr_set[reg_idx].status_off) &
+					dpu_irq_map[irq_idx].irq_mask;
+	if (intr_status && clear)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+				intr_status);
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return intr_status;
+}
+
+static void __setup_intr_ops(struct dpu_hw_intr_ops *ops)
+{
+	ops->set_mask = dpu_hw_intr_set_mask;
+	ops->irq_idx_lookup = dpu_hw_intr_irqidx_lookup;
+	ops->enable_irq = dpu_hw_intr_enable_irq;
+	ops->disable_irq = dpu_hw_intr_disable_irq;
+	ops->dispatch_irqs = dpu_hw_intr_dispatch_irq;
+	ops->clear_all_irqs = dpu_hw_intr_clear_irqs;
+	ops->disable_all_irqs = dpu_hw_intr_disable_irqs;
+	ops->get_valid_interrupts = dpu_hw_intr_get_valid_interrupts;
+	ops->get_interrupt_statuses = dpu_hw_intr_get_interrupt_statuses;
+	ops->clear_interrupt_status = dpu_hw_intr_clear_interrupt_status;
+	ops->clear_intr_status_nolock = dpu_hw_intr_clear_intr_status_nolock;
+	ops->get_interrupt_status = dpu_hw_intr_get_interrupt_status;
+}
+
+static void __intr_offset(struct dpu_mdss_cfg *m,
+		void __iomem *addr, struct dpu_hw_blk_reg_map *hw)
+{
+	hw->base_off = addr;
+	hw->blk_off = m->mdp[0].base;
+	hw->hwversion = m->hwversion;
+}
+
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intr *intr;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	intr = kzalloc(sizeof(*intr), GFP_KERNEL);
+	if (!intr)
+		return ERR_PTR(-ENOMEM);
+
+	__intr_offset(m, addr, &intr->hw);
+	__setup_intr_ops(&intr->ops);
+
+	intr->irq_idx_tbl_size = ARRAY_SIZE(dpu_irq_map);
+
+	intr->cache_irq_mask = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32),
+			GFP_KERNEL);
+	if (intr->cache_irq_mask == NULL) {
+		kfree(intr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	intr->save_irq_status = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32),
+			GFP_KERNEL);
+	if (intr->save_irq_status == NULL) {
+		kfree(intr->cache_irq_mask);
+		kfree(intr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spin_lock_init(&intr->irq_lock);
+
+	return intr;
+}
+
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr)
+{
+	if (intr) {
+		kfree(intr->cache_irq_mask);
+		kfree(intr->save_irq_status);
+		kfree(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
new file mode 100644
index 000000000000..61e4cba36562
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -0,0 +1,257 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_INTERRUPTS_H
+#define _DPU_HW_INTERRUPTS_H
+
+#include <linux/types.h>
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+#define IRQ_SOURCE_MDP		BIT(0)
+#define IRQ_SOURCE_DSI0		BIT(4)
+#define IRQ_SOURCE_DSI1		BIT(5)
+#define IRQ_SOURCE_HDMI		BIT(8)
+#define IRQ_SOURCE_EDP		BIT(12)
+#define IRQ_SOURCE_MHL		BIT(16)
+
+/**
+ * dpu_intr_type - HW Interrupt Type
+ * @DPU_IRQ_TYPE_WB_ROT_COMP:		WB rotator done
+ * @DPU_IRQ_TYPE_WB_WFD_COMP:		WB WFD done
+ * @DPU_IRQ_TYPE_PING_PONG_COMP:	PingPong done
+ * @DPU_IRQ_TYPE_PING_PONG_RD_PTR:	PingPong read pointer
+ * @DPU_IRQ_TYPE_PING_PONG_WR_PTR:	PingPong write pointer
+ * @DPU_IRQ_TYPE_PING_PONG_AUTO_REF:	PingPong auto refresh
+ * @DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK:	PingPong Tear check
+ * @DPU_IRQ_TYPE_PING_PONG_TE_CHECK:	PingPong TE detection
+ * @DPU_IRQ_TYPE_INTF_UNDER_RUN:	INTF underrun
+ * @DPU_IRQ_TYPE_INTF_VSYNC:		INTF VSYNC
+ * @DPU_IRQ_TYPE_CWB_OVERFLOW:		Concurrent WB overflow
+ * @DPU_IRQ_TYPE_HIST_VIG_DONE:		VIG Histogram done
+ * @DPU_IRQ_TYPE_HIST_VIG_RSTSEQ:	VIG Histogram reset
+ * @DPU_IRQ_TYPE_HIST_DSPP_DONE:	DSPP Histogram done
+ * @DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ:	DSPP Histogram reset
+ * @DPU_IRQ_TYPE_WD_TIMER:		Watchdog timer
+ * @DPU_IRQ_TYPE_SFI_VIDEO_IN:		Video static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_VIDEO_OUT:		Video static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_0_IN:		DSI CMD0 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_0_OUT:		DSI CMD0 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_1_IN:		DSI CMD1 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_1_OUT:		DSI CMD1 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_2_IN:		DSI CMD2 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_2_OUT:		DSI CMD2 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_PROG_LINE:		Programmable Line interrupt
+ * @DPU_IRQ_TYPE_AD4_BL_DONE:		AD4 backlight
+ * @DPU_IRQ_TYPE_CTL_START:		Control start
+ * @DPU_IRQ_TYPE_RESERVED:		Reserved for expansion
+ */
+enum dpu_intr_type {
+	DPU_IRQ_TYPE_WB_ROT_COMP,
+	DPU_IRQ_TYPE_WB_WFD_COMP,
+	DPU_IRQ_TYPE_PING_PONG_COMP,
+	DPU_IRQ_TYPE_PING_PONG_RD_PTR,
+	DPU_IRQ_TYPE_PING_PONG_WR_PTR,
+	DPU_IRQ_TYPE_PING_PONG_AUTO_REF,
+	DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK,
+	DPU_IRQ_TYPE_PING_PONG_TE_CHECK,
+	DPU_IRQ_TYPE_INTF_UNDER_RUN,
+	DPU_IRQ_TYPE_INTF_VSYNC,
+	DPU_IRQ_TYPE_CWB_OVERFLOW,
+	DPU_IRQ_TYPE_HIST_VIG_DONE,
+	DPU_IRQ_TYPE_HIST_VIG_RSTSEQ,
+	DPU_IRQ_TYPE_HIST_DSPP_DONE,
+	DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ,
+	DPU_IRQ_TYPE_WD_TIMER,
+	DPU_IRQ_TYPE_SFI_VIDEO_IN,
+	DPU_IRQ_TYPE_SFI_VIDEO_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_0_IN,
+	DPU_IRQ_TYPE_SFI_CMD_0_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_1_IN,
+	DPU_IRQ_TYPE_SFI_CMD_1_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_2_IN,
+	DPU_IRQ_TYPE_SFI_CMD_2_OUT,
+	DPU_IRQ_TYPE_PROG_LINE,
+	DPU_IRQ_TYPE_AD4_BL_DONE,
+	DPU_IRQ_TYPE_CTL_START,
+	DPU_IRQ_TYPE_RESERVED,
+};
+
+struct dpu_hw_intr;
+
+/**
+ * Interrupt operations.
+ */
+struct dpu_hw_intr_ops {
+	/**
+	 * set_mask - Programs the given interrupt register with the
+	 *            given interrupt mask. Register value will get overwritten.
+	 * @intr:	HW interrupt handle
+	 * @reg_off:	MDSS HW register offset
+	 * @irqmask:	IRQ mask value
+	 */
+	void (*set_mask)(
+			struct dpu_hw_intr *intr,
+			uint32_t reg,
+			uint32_t irqmask);
+
+	/**
+	 * irq_idx_lookup - Lookup IRQ index on the HW interrupt type
+	 *                 Used for all irq related ops
+	 * @intr_type:		Interrupt type defined in dpu_intr_type
+	 * @instance_idx:	HW interrupt block instance
+	 * @return:		irq_idx or -EINVAL for lookup fail
+	 */
+	int (*irq_idx_lookup)(
+			enum dpu_intr_type intr_type,
+			u32 instance_idx);
+
+	/**
+	 * enable_irq - Enable IRQ based on lookup IRQ index
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*enable_irq)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * disable_irq - Disable IRQ based on lookup IRQ index
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*disable_irq)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * clear_all_irqs - Clears all the interrupts (i.e. acknowledges
+	 *                  any asserted IRQs). Useful during reset.
+	 * @intr:	HW interrupt handle
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*clear_all_irqs)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * disable_all_irqs - Disables all the interrupts. Useful during reset.
+	 * @intr:	HW interrupt handle
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*disable_all_irqs)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * dispatch_irqs - IRQ dispatcher will call the given callback
+	 *                 function when a matching interrupt status bit is
+	 *                 found in the irq mapping table.
+	 * @intr:	HW interrupt handle
+	 * @cbfunc:	Callback function pointer
+	 * @arg:	Argument to pass back during callback
+	 */
+	void (*dispatch_irqs)(
+			struct dpu_hw_intr *intr,
+			void (*cbfunc)(void *arg, int irq_idx),
+			void *arg);
+
+	/**
+	 * get_interrupt_statuses - Gets and store value from all interrupt
+	 *                          status registers that are currently fired.
+	 * @intr:	HW interrupt handle
+	 */
+	void (*get_interrupt_statuses)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * clear_interrupt_status - Clears HW interrupt status based on given
+	 *                          lookup IRQ index.
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 */
+	void (*clear_interrupt_status)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * clear_intr_status_nolock() - clears the HW interrupts without lock
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 */
+	void (*clear_intr_status_nolock)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * get_interrupt_status - Gets HW interrupt status, and clear if set,
+	 *                        based on given lookup IRQ index.
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @clear:	True to clear irq after read
+	 */
+	u32 (*get_interrupt_status)(
+			struct dpu_hw_intr *intr,
+			int irq_idx,
+			bool clear);
+
+	/**
+	 * get_valid_interrupts - Gets a mask of all valid interrupt sources
+	 *                        within DPU. These are actually status bits
+	 *                        within interrupt registers that specify the
+	 *                        source of the interrupt in IRQs. For example,
+	 *                        valid interrupt sources can be MDP, DSI,
+	 *                        HDMI etc.
+	 * @intr:	HW interrupt handle
+	 * @mask:	Returning the interrupt source MASK
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*get_valid_interrupts)(
+			struct dpu_hw_intr *intr,
+			uint32_t *mask);
+};
+
+/**
+ * struct dpu_hw_intr: hw interrupts handling data structure
+ * @hw:               virtual address mapping
+ * @ops:              function pointer mapping for IRQ handling
+ * @cache_irq_mask:   array of IRQ enable masks reg storage created during init
+ * @save_irq_status:  array of IRQ status reg storage created during init
+ * @irq_idx_tbl_size: total number of irq_idx mapped in the hw_interrupts
+ * @irq_lock:         spinlock for accessing IRQ resources
+ */
+struct dpu_hw_intr {
+	struct dpu_hw_blk_reg_map hw;
+	struct dpu_hw_intr_ops ops;
+	u32 *cache_irq_mask;
+	u32 *save_irq_status;
+	u32 irq_idx_tbl_size;
+	spinlock_t irq_lock;
+};
+
+/**
+ * dpu_hw_intr_init(): Initializes the interrupts hw object
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intr_destroy(): Cleanup interrutps hw object
+ * @intr: pointer to interrupts hw object
+ */
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr);
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
new file mode 100644
index 000000000000..d280df5613c9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -0,0 +1,349 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define INTF_TIMING_ENGINE_EN           0x000
+#define INTF_CONFIG                     0x004
+#define INTF_HSYNC_CTL                  0x008
+#define INTF_VSYNC_PERIOD_F0            0x00C
+#define INTF_VSYNC_PERIOD_F1            0x010
+#define INTF_VSYNC_PULSE_WIDTH_F0       0x014
+#define INTF_VSYNC_PULSE_WIDTH_F1       0x018
+#define INTF_DISPLAY_V_START_F0         0x01C
+#define INTF_DISPLAY_V_START_F1         0x020
+#define INTF_DISPLAY_V_END_F0           0x024
+#define INTF_DISPLAY_V_END_F1           0x028
+#define INTF_ACTIVE_V_START_F0          0x02C
+#define INTF_ACTIVE_V_START_F1          0x030
+#define INTF_ACTIVE_V_END_F0            0x034
+#define INTF_ACTIVE_V_END_F1            0x038
+#define INTF_DISPLAY_HCTL               0x03C
+#define INTF_ACTIVE_HCTL                0x040
+#define INTF_BORDER_COLOR               0x044
+#define INTF_UNDERFLOW_COLOR            0x048
+#define INTF_HSYNC_SKEW                 0x04C
+#define INTF_POLARITY_CTL               0x050
+#define INTF_TEST_CTL                   0x054
+#define INTF_TP_COLOR0                  0x058
+#define INTF_TP_COLOR1                  0x05C
+#define INTF_FRAME_LINE_COUNT_EN        0x0A8
+#define INTF_FRAME_COUNT                0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define   INTF_DEFLICKER_CONFIG         0x0F0
+#define   INTF_DEFLICKER_STRNG_COEFF    0x0F4
+#define   INTF_DEFLICKER_WEAK_COEFF     0x0F8
+
+#define   INTF_DSI_CMD_MODE_TRIGGER_EN  0x084
+#define   INTF_PANEL_FORMAT             0x090
+#define   INTF_TPG_ENABLE               0x100
+#define   INTF_TPG_MAIN_CONTROL         0x104
+#define   INTF_TPG_VIDEO_CONFIG         0x108
+#define   INTF_TPG_COMPONENT_LIMITS     0x10C
+#define   INTF_TPG_RECTANGLE            0x110
+#define   INTF_TPG_INITIAL_VALUE        0x114
+#define   INTF_TPG_BLK_WHITE_PATTERN_FRAMES   0x118
+#define   INTF_TPG_RGB_MAPPING          0x11C
+#define   INTF_PROG_FETCH_START         0x170
+#define   INTF_PROG_ROT_START           0x174
+
+#define   INTF_FRAME_LINE_COUNT_EN      0x0A8
+#define   INTF_FRAME_COUNT              0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define INTF_MISR_CTRL			0x180
+#define INTF_MISR_SIGNATURE		0x184
+
+static struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->intf_count; i++) {
+		if ((intf == m->intf[i].id) &&
+		(m->intf[i].type != INTF_NONE)) {
+			b->base_off = addr;
+			b->blk_off = m->intf[i].base;
+			b->length = m->intf[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_INTF;
+			return &m->intf[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx,
+		const struct intf_timing_params *p,
+		const struct dpu_format *fmt)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 hsync_period, vsync_period;
+	u32 display_v_start, display_v_end;
+	u32 hsync_start_x, hsync_end_x;
+	u32 active_h_start, active_h_end;
+	u32 active_v_start, active_v_end;
+	u32 active_hctl, display_hctl, hsync_ctl;
+	u32 polarity_ctl, den_polarity, hsync_polarity, vsync_polarity;
+	u32 panel_format;
+	u32 intf_cfg;
+
+	/* read interface_cfg */
+	intf_cfg = DPU_REG_READ(c, INTF_CONFIG);
+	hsync_period = p->hsync_pulse_width + p->h_back_porch + p->width +
+	p->h_front_porch;
+	vsync_period = p->vsync_pulse_width + p->v_back_porch + p->height +
+	p->v_front_porch;
+
+	display_v_start = ((p->vsync_pulse_width + p->v_back_porch) *
+	hsync_period) + p->hsync_skew;
+	display_v_end = ((vsync_period - p->v_front_porch) * hsync_period) +
+	p->hsync_skew - 1;
+
+	if (ctx->cap->type == INTF_EDP || ctx->cap->type == INTF_DP) {
+		display_v_start += p->hsync_pulse_width + p->h_back_porch;
+		display_v_end -= p->h_front_porch;
+	}
+
+	hsync_start_x = p->h_back_porch + p->hsync_pulse_width;
+	hsync_end_x = hsync_period - p->h_front_porch - 1;
+
+	if (p->width != p->xres) {
+		active_h_start = hsync_start_x;
+		active_h_end = active_h_start + p->xres - 1;
+	} else {
+		active_h_start = 0;
+		active_h_end = 0;
+	}
+
+	if (p->height != p->yres) {
+		active_v_start = display_v_start;
+		active_v_end = active_v_start + (p->yres * hsync_period) - 1;
+	} else {
+		active_v_start = 0;
+		active_v_end = 0;
+	}
+
+	if (active_h_end) {
+		active_hctl = (active_h_end << 16) | active_h_start;
+		intf_cfg |= BIT(29);	/* ACTIVE_H_ENABLE */
+	} else {
+		active_hctl = 0;
+	}
+
+	if (active_v_end)
+		intf_cfg |= BIT(30); /* ACTIVE_V_ENABLE */
+
+	hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width;
+	display_hctl = (hsync_end_x << 16) | hsync_start_x;
+
+	den_polarity = 0;
+	if (ctx->cap->type == INTF_HDMI) {
+		hsync_polarity = p->yres >= 720 ? 0 : 1;
+		vsync_polarity = p->yres >= 720 ? 0 : 1;
+	} else {
+		hsync_polarity = 0;
+		vsync_polarity = 0;
+	}
+	polarity_ctl = (den_polarity << 2) | /*  DEN Polarity  */
+		(vsync_polarity << 1) | /* VSYNC Polarity */
+		(hsync_polarity << 0);  /* HSYNC Polarity */
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		panel_format = (fmt->bits[C0_G_Y] |
+				(fmt->bits[C1_B_Cb] << 2) |
+				(fmt->bits[C2_R_Cr] << 4) |
+				(0x21 << 8));
+	else
+		/* Interface treats all the pixel data in RGB888 format */
+		panel_format = (COLOR_8BIT |
+				(COLOR_8BIT << 2) |
+				(COLOR_8BIT << 4) |
+				(0x21 << 8));
+
+	DPU_REG_WRITE(c, INTF_HSYNC_CTL, hsync_ctl);
+	DPU_REG_WRITE(c, INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period);
+	DPU_REG_WRITE(c, INTF_VSYNC_PULSE_WIDTH_F0,
+			p->vsync_pulse_width * hsync_period);
+	DPU_REG_WRITE(c, INTF_DISPLAY_HCTL, display_hctl);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_START_F0, display_v_start);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_END_F0, display_v_end);
+	DPU_REG_WRITE(c, INTF_ACTIVE_HCTL,  active_hctl);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_START_F0, active_v_start);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_END_F0, active_v_end);
+	DPU_REG_WRITE(c, INTF_BORDER_COLOR, p->border_clr);
+	DPU_REG_WRITE(c, INTF_UNDERFLOW_COLOR, p->underflow_clr);
+	DPU_REG_WRITE(c, INTF_HSYNC_SKEW, p->hsync_skew);
+	DPU_REG_WRITE(c, INTF_POLARITY_CTL, polarity_ctl);
+	DPU_REG_WRITE(c, INTF_FRAME_LINE_COUNT_EN, 0x3);
+	DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg);
+	DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format);
+}
+
+static void dpu_hw_intf_enable_timing_engine(
+		struct dpu_hw_intf *intf,
+		u8 enable)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	/* Note: Display interface select is handled in top block hw layer */
+	DPU_REG_WRITE(c, INTF_TIMING_ENGINE_EN, enable != 0);
+}
+
+static void dpu_hw_intf_setup_prg_fetch(
+		struct dpu_hw_intf *intf,
+		const struct intf_prog_fetch *fetch)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	int fetch_enable;
+
+	/*
+	 * Fetch should always be outside the active lines. If the fetching
+	 * is programmed within active region, hardware behavior is unknown.
+	 */
+
+	fetch_enable = DPU_REG_READ(c, INTF_CONFIG);
+	if (fetch->enable) {
+		fetch_enable |= BIT(31);
+		DPU_REG_WRITE(c, INTF_PROG_FETCH_START,
+				fetch->fetch_start);
+	} else {
+		fetch_enable &= ~BIT(31);
+	}
+
+	DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable);
+}
+
+static void dpu_hw_intf_get_status(
+		struct dpu_hw_intf *intf,
+		struct intf_status *s)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+
+	s->is_en = DPU_REG_READ(c, INTF_TIMING_ENGINE_EN);
+	if (s->is_en) {
+		s->frame_count = DPU_REG_READ(c, INTF_FRAME_COUNT);
+		s->line_count = DPU_REG_READ(c, INTF_LINE_COUNT);
+	} else {
+		s->line_count = 0;
+		s->frame_count = 0;
+	}
+}
+
+static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf,
+						bool enable, u32 frame_count)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, INTF_MISR_CTRL, MISR_CTRL_STATUS_CLEAR);
+	/* clear misr data */
+	wmb();
+
+	if (enable)
+		config = (frame_count & MISR_FRAME_COUNT_MASK) |
+			MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK;
+
+	DPU_REG_WRITE(c, INTF_MISR_CTRL, config);
+}
+
+static u32 dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_MISR_SIGNATURE);
+}
+
+static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!intf)
+		return 0;
+
+	c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_LINE_COUNT);
+}
+
+static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_timing_gen = dpu_hw_intf_setup_timing_engine;
+	ops->setup_prg_fetch  = dpu_hw_intf_setup_prg_fetch;
+	ops->get_status = dpu_hw_intf_get_status;
+	ops->enable_timing = dpu_hw_intf_enable_timing_engine;
+	ops->setup_misr = dpu_hw_intf_setup_misr;
+	ops->collect_misr = dpu_hw_intf_collect_misr;
+	ops->get_line_count = dpu_hw_intf_get_line_count;
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intf *c;
+	struct dpu_intf_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _intf_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_intf %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	c->mdss = m;
+	_setup_intf_ops(&c->ops, c->cap->features);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_INTF, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf)
+{
+	if (intf)
+		dpu_hw_blk_destroy(&intf->base);
+	kfree(intf);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
new file mode 100644
index 000000000000..a79d735da68d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -0,0 +1,128 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_INTF_H
+#define _DPU_HW_INTF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_intf;
+
+/* intf timing settings */
+struct intf_timing_params {
+	u32 width;		/* active width */
+	u32 height;		/* active height */
+	u32 xres;		/* Display panel width */
+	u32 yres;		/* Display panel height */
+
+	u32 h_back_porch;
+	u32 h_front_porch;
+	u32 v_back_porch;
+	u32 v_front_porch;
+	u32 hsync_pulse_width;
+	u32 vsync_pulse_width;
+	u32 hsync_polarity;
+	u32 vsync_polarity;
+	u32 border_clr;
+	u32 underflow_clr;
+	u32 hsync_skew;
+};
+
+struct intf_prog_fetch {
+	u8 enable;
+	/* vsync counter for the front porch pixel line */
+	u32 fetch_start;
+};
+
+struct intf_status {
+	u8 is_en;		/* interface timing engine is enabled or not */
+	u32 frame_count;	/* frame count since timing engine enabled */
+	u32 line_count;		/* current line count including blanking */
+};
+
+/**
+ * struct dpu_hw_intf_ops : Interface to the interface Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ * @ setup_timing_gen : programs the timing engine
+ * @ setup_prog_fetch : enables/disables the programmable fetch logic
+ * @ enable_timing: enable/disable timing engine
+ * @ get_status: returns if timing engine is enabled or not
+ * @ setup_misr: enables/disables MISR in HW register
+ * @ collect_misr: reads and stores MISR data from HW register
+ * @ get_line_count: reads current vertical line counter
+ */
+struct dpu_hw_intf_ops {
+	void (*setup_timing_gen)(struct dpu_hw_intf *intf,
+			const struct intf_timing_params *p,
+			const struct dpu_format *fmt);
+
+	void (*setup_prg_fetch)(struct dpu_hw_intf *intf,
+			const struct intf_prog_fetch *fetch);
+
+	void (*enable_timing)(struct dpu_hw_intf *intf,
+			u8 enable);
+
+	void (*get_status)(struct dpu_hw_intf *intf,
+			struct intf_status *status);
+
+	void (*setup_misr)(struct dpu_hw_intf *intf,
+			bool enable, u32 frame_count);
+
+	u32 (*collect_misr)(struct dpu_hw_intf *intf);
+
+	u32 (*get_line_count)(struct dpu_hw_intf *intf);
+};
+
+struct dpu_hw_intf {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* intf */
+	enum dpu_intf idx;
+	const struct dpu_intf_cfg *cap;
+	const struct dpu_mdss_cfg *mdss;
+
+	/* ops */
+	struct dpu_hw_intf_ops ops;
+};
+
+/**
+ * to_dpu_hw_intf - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_intf, base);
+}
+
+/**
+ * dpu_hw_intf_init(): Initializes the intf driver for the passed
+ * interface idx.
+ * @idx:  interface index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intf_destroy(): Destroys INTF driver context
+ * @intf:   Pointer to INTF driver context
+ */
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf);
+
+#endif /*_DPU_HW_INTF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
new file mode 100644
index 000000000000..4ab72b0f07a5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -0,0 +1,261 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_kms.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define LM_OP_MODE                        0x00
+#define LM_OUT_SIZE                       0x04
+#define LM_BORDER_COLOR_0                 0x08
+#define LM_BORDER_COLOR_1                 0x010
+
+/* These register are offset to mixer base + stage base */
+#define LM_BLEND0_OP                     0x00
+#define LM_BLEND0_CONST_ALPHA            0x04
+#define LM_FG_COLOR_FILL_COLOR_0         0x08
+#define LM_FG_COLOR_FILL_COLOR_1         0x0C
+#define LM_FG_COLOR_FILL_SIZE            0x10
+#define LM_FG_COLOR_FILL_XY              0x14
+
+#define LM_BLEND0_FG_ALPHA               0x04
+#define LM_BLEND0_BG_ALPHA               0x08
+
+#define LM_MISR_CTRL			0x310
+#define LM_MISR_SIGNATURE		0x314
+
+static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->mixer_count; i++) {
+		if (mixer == m->mixer[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->mixer[i].base;
+			b->length = m->mixer[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_LM;
+			return &m->mixer[i];
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * _stage_offset(): returns the relative offset of the blend registers
+ * for the stage to be setup
+ * @c:     mixer ctx contains the mixer to be programmed
+ * @stage: stage index to setup
+ */
+static inline int _stage_offset(struct dpu_hw_mixer *ctx, enum dpu_stage stage)
+{
+	const struct dpu_lm_sub_blks *sblk = ctx->cap->sblk;
+	int rc;
+
+	if (stage == DPU_STAGE_BASE)
+		rc = -EINVAL;
+	else if (stage <= sblk->maxblendstages)
+		rc = sblk->blendstage_base[stage - DPU_STAGE_0];
+	else
+		rc = -EINVAL;
+
+	return rc;
+}
+
+static void dpu_hw_lm_setup_out(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *mixer)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 outsize;
+	u32 op_mode;
+
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	outsize = mixer->out_height << 16 | mixer->out_width;
+	DPU_REG_WRITE(c, LM_OUT_SIZE, outsize);
+
+	/* SPLIT_LEFT_RIGHT */
+	if (mixer->right_mixer)
+		op_mode |= BIT(31);
+	else
+		op_mode &= ~BIT(31);
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	if (border_en) {
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_0,
+			(color->color_0 & 0xFFF) |
+			((color->color_1 & 0xFFF) << 0x10));
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_1,
+			(color->color_2 & 0xFFF) |
+			((color->color_3 & 0xFFF) << 0x10));
+	}
+}
+
+static void dpu_hw_lm_setup_blend_config_sdm845(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+	u32 const_alpha;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	const_alpha = (bg_alpha & 0xFF) | ((fg_alpha & 0xFF) << 16);
+	DPU_REG_WRITE(c, LM_BLEND0_CONST_ALPHA + stage_off, const_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_blend_config(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	DPU_REG_WRITE(c, LM_BLEND0_FG_ALPHA + stage_off, fg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_BG_ALPHA + stage_off, bg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
+	uint32_t mixer_op_mode)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int op_mode;
+
+	/* read the existing op_mode configuration */
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	op_mode = (op_mode & (BIT(31) | BIT(30))) | mixer_op_mode;
+
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_gc(struct dpu_hw_mixer *mixer,
+			void *cfg)
+{
+}
+
+static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx,
+				bool enable, u32 frame_count)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, LM_MISR_CTRL, MISR_CTRL_STATUS_CLEAR);
+	/* clear misr data */
+	wmb();
+
+	if (enable)
+		config = (frame_count & MISR_FRAME_COUNT_MASK) |
+			MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK;
+
+	DPU_REG_WRITE(c, LM_MISR_CTRL, config);
+}
+
+static u32 dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, LM_MISR_SIGNATURE);
+}
+
+static void _setup_mixer_ops(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))
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config_sdm845;
+	else
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
+	ops->setup_alpha_out = dpu_hw_lm_setup_color3;
+	ops->setup_border_color = dpu_hw_lm_setup_border_color;
+	ops->setup_gc = dpu_hw_lm_gc;
+	ops->setup_misr = dpu_hw_lm_setup_misr;
+	ops->collect_misr = dpu_hw_lm_collect_misr;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mixer *c;
+	struct dpu_lm_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _lm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_mixer_ops(m, &c->ops, c->cap->features);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_LM, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm)
+{
+	if (lm)
+		dpu_hw_blk_destroy(&lm->base);
+	kfree(lm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
new file mode 100644
index 000000000000..e29e5dab31bf
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -0,0 +1,122 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_LM_H
+#define _DPU_HW_LM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_mixer;
+
+struct dpu_hw_mixer_cfg {
+	u32 out_width;
+	u32 out_height;
+	bool right_mixer;
+	int flags;
+};
+
+struct dpu_hw_color3_cfg {
+	u8 keep_fg[DPU_STAGE_MAX];
+};
+
+/**
+ *
+ * struct dpu_hw_lm_ops : Interface to the mixer Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_lm_ops {
+	/*
+	 * Sets up mixer output width and height
+	 * and border color if enabled
+	 */
+	void (*setup_mixer_out)(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *cfg);
+
+	/*
+	 * Alpha blending configuration
+	 * for the specified stage
+	 */
+	void (*setup_blend_config)(struct dpu_hw_mixer *ctx, uint32_t stage,
+		uint32_t fg_alpha, uint32_t bg_alpha, uint32_t blend_op);
+
+	/*
+	 * Alpha color component selection from either fg or bg
+	 */
+	void (*setup_alpha_out)(struct dpu_hw_mixer *ctx, uint32_t mixer_op);
+
+	/**
+	 * setup_border_color : enable/disable border color
+	 */
+	void (*setup_border_color)(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en);
+	/**
+	 * setup_gc : enable/disable gamma correction feature
+	 */
+	void (*setup_gc)(struct dpu_hw_mixer *mixer,
+			void *cfg);
+
+	/* setup_misr: enables/disables MISR in HW register */
+	void (*setup_misr)(struct dpu_hw_mixer *ctx,
+			bool enable, u32 frame_count);
+
+	/* collect_misr: reads and stores MISR data from HW register */
+	u32 (*collect_misr)(struct dpu_hw_mixer *ctx);
+};
+
+struct dpu_hw_mixer {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* lm */
+	enum dpu_lm  idx;
+	const struct dpu_lm_cfg   *cap;
+	const struct dpu_mdp_cfg  *mdp;
+	const struct dpu_ctl_cfg  *ctl;
+
+	/* ops */
+	struct dpu_hw_lm_ops ops;
+
+	/* store mixer info specific to display */
+	struct dpu_hw_mixer_cfg cfg;
+};
+
+/**
+ * to_dpu_hw_mixer - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mixer, base);
+}
+
+/**
+ * dpu_hw_lm_init(): Initializes the mixer hw driver object.
+ * should be called once before accessing every mixer.
+ * @idx:  mixer index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_lm_destroy(): Destroys layer mixer driver context
+ * @lm:   Pointer to LM driver context
+ */
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm);
+
+#endif /*_DPU_HW_LM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
new file mode 100644
index 000000000000..35e6bf930924
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
@@ -0,0 +1,465 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_MDSS_H
+#define _DPU_HW_MDSS_H
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include "msm_drv.h"
+
+#define DPU_DBG_NAME			"dpu"
+
+#define DPU_NONE                        0
+
+#ifndef DPU_CSC_MATRIX_COEFF_SIZE
+#define DPU_CSC_MATRIX_COEFF_SIZE	9
+#endif
+
+#ifndef DPU_CSC_CLAMP_SIZE
+#define DPU_CSC_CLAMP_SIZE		6
+#endif
+
+#ifndef DPU_CSC_BIAS_SIZE
+#define DPU_CSC_BIAS_SIZE		3
+#endif
+
+#ifndef DPU_MAX_PLANES
+#define DPU_MAX_PLANES			4
+#endif
+
+#define PIPES_PER_STAGE			2
+#ifndef DPU_MAX_DE_CURVES
+#define DPU_MAX_DE_CURVES		3
+#endif
+
+enum dpu_format_flags {
+	DPU_FORMAT_FLAG_YUV_BIT,
+	DPU_FORMAT_FLAG_DX_BIT,
+	DPU_FORMAT_FLAG_COMPRESSED_BIT,
+	DPU_FORMAT_FLAG_BIT_MAX,
+};
+
+#define DPU_FORMAT_FLAG_YUV		BIT(DPU_FORMAT_FLAG_YUV_BIT)
+#define DPU_FORMAT_FLAG_DX		BIT(DPU_FORMAT_FLAG_DX_BIT)
+#define DPU_FORMAT_FLAG_COMPRESSED	BIT(DPU_FORMAT_FLAG_COMPRESSED_BIT)
+#define DPU_FORMAT_IS_YUV(X)		\
+	(test_bit(DPU_FORMAT_FLAG_YUV_BIT, (X)->flag))
+#define DPU_FORMAT_IS_DX(X)		\
+	(test_bit(DPU_FORMAT_FLAG_DX_BIT, (X)->flag))
+#define DPU_FORMAT_IS_LINEAR(X)		((X)->fetch_mode == DPU_FETCH_LINEAR)
+#define DPU_FORMAT_IS_TILE(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			!test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+#define DPU_FORMAT_IS_UBWC(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+
+#define DPU_BLEND_FG_ALPHA_FG_CONST	(0 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_CONST	(1 << 0)
+#define DPU_BLEND_FG_ALPHA_FG_PIXEL	(2 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_PIXEL	(3 << 0)
+#define DPU_BLEND_FG_INV_ALPHA		(1 << 2)
+#define DPU_BLEND_FG_MOD_ALPHA		(1 << 3)
+#define DPU_BLEND_FG_INV_MOD_ALPHA	(1 << 4)
+#define DPU_BLEND_FG_TRANSP_EN		(1 << 5)
+#define DPU_BLEND_BG_ALPHA_FG_CONST	(0 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_CONST	(1 << 8)
+#define DPU_BLEND_BG_ALPHA_FG_PIXEL	(2 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_PIXEL	(3 << 8)
+#define DPU_BLEND_BG_INV_ALPHA		(1 << 10)
+#define DPU_BLEND_BG_MOD_ALPHA		(1 << 11)
+#define DPU_BLEND_BG_INV_MOD_ALPHA	(1 << 12)
+#define DPU_BLEND_BG_TRANSP_EN		(1 << 13)
+
+#define DPU_VSYNC0_SOURCE_GPIO		0
+#define DPU_VSYNC1_SOURCE_GPIO		1
+#define DPU_VSYNC2_SOURCE_GPIO		2
+#define DPU_VSYNC_SOURCE_INTF_0		3
+#define DPU_VSYNC_SOURCE_INTF_1		4
+#define DPU_VSYNC_SOURCE_INTF_2		5
+#define DPU_VSYNC_SOURCE_INTF_3		6
+#define DPU_VSYNC_SOURCE_WD_TIMER_4	11
+#define DPU_VSYNC_SOURCE_WD_TIMER_3	12
+#define DPU_VSYNC_SOURCE_WD_TIMER_2	13
+#define DPU_VSYNC_SOURCE_WD_TIMER_1	14
+#define DPU_VSYNC_SOURCE_WD_TIMER_0	15
+
+enum dpu_hw_blk_type {
+	DPU_HW_BLK_TOP = 0,
+	DPU_HW_BLK_SSPP,
+	DPU_HW_BLK_LM,
+	DPU_HW_BLK_CTL,
+	DPU_HW_BLK_CDM,
+	DPU_HW_BLK_PINGPONG,
+	DPU_HW_BLK_INTF,
+	DPU_HW_BLK_WB,
+	DPU_HW_BLK_MAX,
+};
+
+enum dpu_mdp {
+	MDP_TOP = 0x1,
+	MDP_MAX,
+};
+
+enum dpu_sspp {
+	SSPP_NONE,
+	SSPP_VIG0,
+	SSPP_VIG1,
+	SSPP_VIG2,
+	SSPP_VIG3,
+	SSPP_RGB0,
+	SSPP_RGB1,
+	SSPP_RGB2,
+	SSPP_RGB3,
+	SSPP_DMA0,
+	SSPP_DMA1,
+	SSPP_DMA2,
+	SSPP_DMA3,
+	SSPP_CURSOR0,
+	SSPP_CURSOR1,
+	SSPP_MAX
+};
+
+enum dpu_sspp_type {
+	SSPP_TYPE_VIG,
+	SSPP_TYPE_RGB,
+	SSPP_TYPE_DMA,
+	SSPP_TYPE_CURSOR,
+	SSPP_TYPE_MAX
+};
+
+enum dpu_lm {
+	LM_0 = 1,
+	LM_1,
+	LM_2,
+	LM_3,
+	LM_4,
+	LM_5,
+	LM_6,
+	LM_MAX
+};
+
+enum dpu_stage {
+	DPU_STAGE_BASE = 0,
+	DPU_STAGE_0,
+	DPU_STAGE_1,
+	DPU_STAGE_2,
+	DPU_STAGE_3,
+	DPU_STAGE_4,
+	DPU_STAGE_5,
+	DPU_STAGE_6,
+	DPU_STAGE_7,
+	DPU_STAGE_8,
+	DPU_STAGE_9,
+	DPU_STAGE_10,
+	DPU_STAGE_MAX
+};
+enum dpu_dspp {
+	DSPP_0 = 1,
+	DSPP_1,
+	DSPP_2,
+	DSPP_3,
+	DSPP_MAX
+};
+
+enum dpu_ds {
+	DS_TOP,
+	DS_0,
+	DS_1,
+	DS_MAX
+};
+
+enum dpu_ctl {
+	CTL_0 = 1,
+	CTL_1,
+	CTL_2,
+	CTL_3,
+	CTL_4,
+	CTL_MAX
+};
+
+enum dpu_cdm {
+	CDM_0 = 1,
+	CDM_1,
+	CDM_MAX
+};
+
+enum dpu_pingpong {
+	PINGPONG_0 = 1,
+	PINGPONG_1,
+	PINGPONG_2,
+	PINGPONG_3,
+	PINGPONG_4,
+	PINGPONG_S0,
+	PINGPONG_MAX
+};
+
+enum dpu_intf {
+	INTF_0 = 1,
+	INTF_1,
+	INTF_2,
+	INTF_3,
+	INTF_4,
+	INTF_5,
+	INTF_6,
+	INTF_MAX
+};
+
+enum dpu_intf_type {
+	INTF_NONE = 0x0,
+	INTF_DSI = 0x1,
+	INTF_HDMI = 0x3,
+	INTF_LCDC = 0x5,
+	INTF_EDP = 0x9,
+	INTF_DP = 0xa,
+	INTF_TYPE_MAX,
+
+	/* virtual interfaces */
+	INTF_WB = 0x100,
+};
+
+enum dpu_intf_mode {
+	INTF_MODE_NONE = 0,
+	INTF_MODE_CMD,
+	INTF_MODE_VIDEO,
+	INTF_MODE_WB_BLOCK,
+	INTF_MODE_WB_LINE,
+	INTF_MODE_MAX
+};
+
+enum dpu_wb {
+	WB_0 = 1,
+	WB_1,
+	WB_2,
+	WB_3,
+	WB_MAX
+};
+
+enum dpu_ad {
+	AD_0 = 0x1,
+	AD_1,
+	AD_MAX
+};
+
+enum dpu_cwb {
+	CWB_0 = 0x1,
+	CWB_1,
+	CWB_2,
+	CWB_3,
+	CWB_MAX
+};
+
+enum dpu_wd_timer {
+	WD_TIMER_0 = 0x1,
+	WD_TIMER_1,
+	WD_TIMER_2,
+	WD_TIMER_3,
+	WD_TIMER_4,
+	WD_TIMER_5,
+	WD_TIMER_MAX
+};
+
+enum dpu_vbif {
+	VBIF_0,
+	VBIF_1,
+	VBIF_MAX,
+	VBIF_RT = VBIF_0,
+	VBIF_NRT = VBIF_1
+};
+
+enum dpu_iommu_domain {
+	DPU_IOMMU_DOMAIN_UNSECURE,
+	DPU_IOMMU_DOMAIN_SECURE,
+	DPU_IOMMU_DOMAIN_MAX
+};
+
+/**
+ * DPU HW,Component order color map
+ */
+enum {
+	C0_G_Y = 0,
+	C1_B_Cb = 1,
+	C2_R_Cr = 2,
+	C3_ALPHA = 3
+};
+
+/**
+ * enum dpu_plane_type - defines how the color component pixel packing
+ * @DPU_PLANE_INTERLEAVED   : Color components in single plane
+ * @DPU_PLANE_PLANAR        : Color component in separate planes
+ * @DPU_PLANE_PSEUDO_PLANAR : Chroma components interleaved in separate plane
+ */
+enum dpu_plane_type {
+	DPU_PLANE_INTERLEAVED,
+	DPU_PLANE_PLANAR,
+	DPU_PLANE_PSEUDO_PLANAR,
+};
+
+/**
+ * enum dpu_chroma_samp_type - chroma sub-samplng type
+ * @DPU_CHROMA_RGB   : No chroma subsampling
+ * @DPU_CHROMA_H2V1  : Chroma pixels are horizontally subsampled
+ * @DPU_CHROMA_H1V2  : Chroma pixels are vertically subsampled
+ * @DPU_CHROMA_420   : 420 subsampling
+ */
+enum dpu_chroma_samp_type {
+	DPU_CHROMA_RGB,
+	DPU_CHROMA_H2V1,
+	DPU_CHROMA_H1V2,
+	DPU_CHROMA_420
+};
+
+/**
+ * dpu_fetch_type - Defines How DPU HW fetches data
+ * @DPU_FETCH_LINEAR   : fetch is line by line
+ * @DPU_FETCH_TILE     : fetches data in Z order from a tile
+ * @DPU_FETCH_UBWC     : fetch and decompress data
+ */
+enum dpu_fetch_type {
+	DPU_FETCH_LINEAR,
+	DPU_FETCH_TILE,
+	DPU_FETCH_UBWC
+};
+
+/**
+ * Value of enum chosen to fit the number of bits
+ * expected by the HW programming.
+ */
+enum {
+	COLOR_ALPHA_1BIT = 0,
+	COLOR_ALPHA_4BIT = 1,
+	COLOR_4BIT = 0,
+	COLOR_5BIT = 1, /* No 5-bit Alpha */
+	COLOR_6BIT = 2, /* 6-Bit Alpha also = 2 */
+	COLOR_8BIT = 3, /* 8-Bit Alpha also = 3 */
+};
+
+/**
+ * enum dpu_3d_blend_mode
+ * Desribes how the 3d data is blended
+ * @BLEND_3D_NONE      : 3d blending not enabled
+ * @BLEND_3D_FRAME_INT : Frame interleaving
+ * @BLEND_3D_H_ROW_INT : Horizontal row interleaving
+ * @BLEND_3D_V_ROW_INT : vertical row interleaving
+ * @BLEND_3D_COL_INT   : column interleaving
+ * @BLEND_3D_MAX       :
+ */
+enum dpu_3d_blend_mode {
+	BLEND_3D_NONE = 0,
+	BLEND_3D_FRAME_INT,
+	BLEND_3D_H_ROW_INT,
+	BLEND_3D_V_ROW_INT,
+	BLEND_3D_COL_INT,
+	BLEND_3D_MAX
+};
+
+/** struct dpu_format - defines the format configuration which
+ * allows DPU HW to correctly fetch and decode the format
+ * @base: base msm_format struture containing fourcc code
+ * @fetch_planes: how the color components are packed in pixel format
+ * @element: element color ordering
+ * @bits: element bit widths
+ * @chroma_sample: chroma sub-samplng type
+ * @unpack_align_msb: unpack aligned, 0 to LSB, 1 to MSB
+ * @unpack_tight: 0 for loose, 1 for tight
+ * @unpack_count: 0 = 1 component, 1 = 2 component
+ * @bpp: bytes per pixel
+ * @alpha_enable: whether the format has an alpha channel
+ * @num_planes: number of planes (including meta data planes)
+ * @fetch_mode: linear, tiled, or ubwc hw fetch behavior
+ * @is_yuv: is format a yuv variant
+ * @flag: usage bit flags
+ * @tile_width: format tile width
+ * @tile_height: format tile height
+ */
+struct dpu_format {
+	struct msm_format base;
+	enum dpu_plane_type fetch_planes;
+	u8 element[DPU_MAX_PLANES];
+	u8 bits[DPU_MAX_PLANES];
+	enum dpu_chroma_samp_type chroma_sample;
+	u8 unpack_align_msb;
+	u8 unpack_tight;
+	u8 unpack_count;
+	u8 bpp;
+	u8 alpha_enable;
+	u8 num_planes;
+	enum dpu_fetch_type fetch_mode;
+	DECLARE_BITMAP(flag, DPU_FORMAT_FLAG_BIT_MAX);
+	u16 tile_width;
+	u16 tile_height;
+};
+#define to_dpu_format(x) container_of(x, struct dpu_format, base)
+
+/**
+ * struct dpu_hw_fmt_layout - format information of the source pixel data
+ * @format: pixel format parameters
+ * @num_planes: number of planes (including meta data planes)
+ * @width: image width
+ * @height: image height
+ * @total_size: total size in bytes
+ * @plane_addr: address of each plane
+ * @plane_size: length of each plane
+ * @plane_pitch: pitch of each plane
+ */
+struct dpu_hw_fmt_layout {
+	const struct dpu_format *format;
+	uint32_t num_planes;
+	uint32_t width;
+	uint32_t height;
+	uint32_t total_size;
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	uint32_t plane_size[DPU_MAX_PLANES];
+	uint32_t plane_pitch[DPU_MAX_PLANES];
+};
+
+struct dpu_csc_cfg {
+	/* matrix coefficients in S15.16 format */
+	uint32_t csc_mv[DPU_CSC_MATRIX_COEFF_SIZE];
+	uint32_t csc_pre_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_post_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_pre_lv[DPU_CSC_CLAMP_SIZE];
+	uint32_t csc_post_lv[DPU_CSC_CLAMP_SIZE];
+};
+
+/**
+ * struct dpu_mdss_color - mdss color description
+ * color 0 : green
+ * color 1 : blue
+ * color 2 : red
+ * color 3 : alpha
+ */
+struct dpu_mdss_color {
+	u32 color_0;
+	u32 color_1;
+	u32 color_2;
+	u32 color_3;
+};
+
+/*
+ * Define bit masks for h/w logging.
+ */
+#define DPU_DBG_MASK_NONE     (1 << 0)
+#define DPU_DBG_MASK_CDM      (1 << 1)
+#define DPU_DBG_MASK_INTF     (1 << 2)
+#define DPU_DBG_MASK_LM       (1 << 3)
+#define DPU_DBG_MASK_CTL      (1 << 4)
+#define DPU_DBG_MASK_PINGPONG (1 << 5)
+#define DPU_DBG_MASK_SSPP     (1 << 6)
+#define DPU_DBG_MASK_WB       (1 << 7)
+#define DPU_DBG_MASK_TOP      (1 << 8)
+#define DPU_DBG_MASK_VBIF     (1 << 9)
+#define DPU_DBG_MASK_ROT      (1 << 10)
+
+#endif  /* _DPU_HW_MDSS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
new file mode 100644
index 000000000000..cc3a623903f4
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -0,0 +1,250 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/iopoll.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+
+#define PP_TEAR_CHECK_EN                0x000
+#define PP_SYNC_CONFIG_VSYNC            0x004
+#define PP_SYNC_CONFIG_HEIGHT           0x008
+#define PP_SYNC_WRCOUNT                 0x00C
+#define PP_VSYNC_INIT_VAL               0x010
+#define PP_INT_COUNT_VAL                0x014
+#define PP_SYNC_THRESH                  0x018
+#define PP_START_POS                    0x01C
+#define PP_RD_PTR_IRQ                   0x020
+#define PP_WR_PTR_IRQ                   0x024
+#define PP_OUT_LINE_COUNT               0x028
+#define PP_LINE_COUNT                   0x02C
+
+#define PP_FBC_MODE                     0x034
+#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,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->pingpong_count; i++) {
+		if (pp == m->pingpong[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->pingpong[i].base;
+			b->length = m->pingpong[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_PINGPONG;
+			return &m->pingpong[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_tear_check *te)
+{
+	struct dpu_hw_blk_reg_map *c;
+	int cfg;
+
+	if (!pp || !te)
+		return -EINVAL;
+	c = &pp->hw;
+
+	cfg = BIT(19); /*VSYNC_COUNTER_EN */
+	if (te->hw_vsync_mode)
+		cfg |= BIT(20);
+
+	cfg |= te->vsync_count;
+
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_HEIGHT, te->sync_cfg_height);
+	DPU_REG_WRITE(c, PP_VSYNC_INIT_VAL, te->vsync_init_val);
+	DPU_REG_WRITE(c, PP_RD_PTR_IRQ, te->rd_ptr_irq);
+	DPU_REG_WRITE(c, PP_START_POS, te->start_pos);
+	DPU_REG_WRITE(c, PP_SYNC_THRESH,
+			((te->sync_threshold_continue << 16) |
+			 te->sync_threshold_start));
+	DPU_REG_WRITE(c, PP_SYNC_WRCOUNT,
+			(te->start_pos + te->sync_threshold_start + 1));
+
+	return 0;
+}
+
+static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp,
+		u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+	int rc;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	rc = readl_poll_timeout(c->base_off + c->blk_off + PP_LINE_COUNT,
+			val, (val & 0xffff) >= 1, 10, timeout_us);
+
+	return rc;
+}
+
+static int dpu_hw_pp_enable_te(struct dpu_hw_pingpong *pp, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!pp)
+		return -EINVAL;
+	c = &pp->hw;
+
+	DPU_REG_WRITE(c, PP_TEAR_CHECK_EN, enable);
+	return 0;
+}
+
+static int dpu_hw_pp_connect_external_te(struct dpu_hw_pingpong *pp,
+		bool enable_external_te)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 cfg;
+	int orig;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	cfg = DPU_REG_READ(c, PP_SYNC_CONFIG_VSYNC);
+	orig = (bool)(cfg & BIT(20));
+	if (enable_external_te)
+		cfg |= BIT(20);
+	else
+		cfg &= ~BIT(20);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	trace_dpu_pp_connect_ext_te(pp->idx - PINGPONG_0, cfg);
+
+	return orig;
+}
+
+static int dpu_hw_pp_get_vsync_info(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_pp_vsync_info *info)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+
+	if (!pp || !info)
+		return -EINVAL;
+	c = &pp->hw;
+
+	val = DPU_REG_READ(c, PP_VSYNC_INIT_VAL);
+	info->rd_ptr_init_val = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_INT_COUNT_VAL);
+	info->rd_ptr_frame_count = (val & 0xffff0000) >> 16;
+	info->rd_ptr_line_count = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_LINE_COUNT);
+	info->wr_ptr_line_count = val & 0xffff;
+
+	return 0;
+}
+
+static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 height, init;
+	u32 line = 0xFFFF;
+
+	if (!pp)
+		return 0;
+	c = &pp->hw;
+
+	init = DPU_REG_READ(c, PP_VSYNC_INIT_VAL) & 0xFFFF;
+	height = DPU_REG_READ(c, PP_SYNC_CONFIG_HEIGHT) & 0xFFFF;
+
+	if (height < init)
+		goto line_count_exit;
+
+	line = DPU_REG_READ(c, PP_INT_COUNT_VAL) & 0xFFFF;
+
+	if (line < init)
+		line += (0xFFFF - init);
+	else
+		line -= init;
+
+line_count_exit:
+	return line;
+}
+
+static void _setup_pingpong_ops(struct dpu_hw_pingpong_ops *ops,
+	const struct dpu_pingpong_cfg *hw_cap)
+{
+	ops->setup_tearcheck = dpu_hw_pp_setup_te_config;
+	ops->enable_tearcheck = dpu_hw_pp_enable_te;
+	ops->connect_external_te = dpu_hw_pp_connect_external_te;
+	ops->get_vsync_info = dpu_hw_pp_get_vsync_info;
+	ops->poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr;
+	ops->get_line_count = dpu_hw_pp_get_line_count;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_pingpong *c;
+	struct dpu_pingpong_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _pingpong_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_pingpong_ops(&c->ops, c->caps);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_PINGPONG, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp)
+{
+	if (pp)
+		dpu_hw_blk_destroy(&pp->base);
+	kfree(pp);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
new file mode 100644
index 000000000000..3caccd7d6a3e
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -0,0 +1,136 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_PINGPONG_H
+#define _DPU_HW_PINGPONG_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_pingpong;
+
+struct dpu_hw_tear_check {
+	/*
+	 * This is ratio of MDP VSYNC clk freq(Hz) to
+	 * refresh rate divided by no of lines
+	 */
+	u32 vsync_count;
+	u32 sync_cfg_height;
+	u32 vsync_init_val;
+	u32 sync_threshold_start;
+	u32 sync_threshold_continue;
+	u32 start_pos;
+	u32 rd_ptr_irq;
+	u8 hw_vsync_mode;
+};
+
+struct dpu_hw_pp_vsync_info {
+	u32 rd_ptr_init_val;	/* value of rd pointer at vsync edge */
+	u32 rd_ptr_frame_count;	/* num frames sent since enabling interface */
+	u32 rd_ptr_line_count;	/* current line on panel (rd ptr) */
+	u32 wr_ptr_line_count;	/* current line within pp fifo (wr ptr) */
+};
+
+/**
+ *
+ * struct dpu_hw_pingpong_ops : Interface to the pingpong Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ *  @setup_tearcheck : program tear check values
+ *  @enable_tearcheck : enables tear check
+ *  @get_vsync_info : retries timing info of the panel
+ *  @setup_dither : function to program the dither hw block
+ *  @get_line_count: obtain current vertical line counter
+ */
+struct dpu_hw_pingpong_ops {
+	/**
+	 * enables vysnc generation and sets up init value of
+	 * read pointer and programs the tear check cofiguration
+	 */
+	int (*setup_tearcheck)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_tear_check *cfg);
+
+	/**
+	 * enables tear check block
+	 */
+	int (*enable_tearcheck)(struct dpu_hw_pingpong *pp,
+			bool enable);
+
+	/**
+	 * read, modify, write to either set or clear listening to external TE
+	 * @Return: 1 if TE was originally connected, 0 if not, or -ERROR
+	 */
+	int (*connect_external_te)(struct dpu_hw_pingpong *pp,
+			bool enable_external_te);
+
+	/**
+	 * provides the programmed and current
+	 * line_count
+	 */
+	int (*get_vsync_info)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_pp_vsync_info  *info);
+
+	/**
+	 * poll until write pointer transmission starts
+	 * @Return: 0 on success, -ETIMEDOUT on timeout
+	 */
+	int (*poll_timeout_wr_ptr)(struct dpu_hw_pingpong *pp, u32 timeout_us);
+
+	/**
+	 * Obtain current vertical line counter
+	 */
+	u32 (*get_line_count)(struct dpu_hw_pingpong *pp);
+};
+
+struct dpu_hw_pingpong {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* pingpong */
+	enum dpu_pingpong idx;
+	const struct dpu_pingpong_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_pingpong_ops ops;
+};
+
+/**
+ * dpu_hw_pingpong - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pingpong, base);
+}
+
+/**
+ * dpu_hw_pingpong_init - initializes the pingpong driver for the passed
+ *	pingpong idx.
+ * @idx:  Pingpong index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ * Returns: Error code or allocated dpu_hw_pingpong context
+ */
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_pingpong_destroy - destroys pingpong driver context
+ *	should be called to free the context
+ * @pp:   Pointer to PP driver context returned by dpu_hw_pingpong_init
+ */
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp);
+
+#endif /*_DPU_HW_PINGPONG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
new file mode 100644
index 000000000000..c25b52a6b219
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -0,0 +1,753 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define DPU_FETCH_CONFIG_RESET_VALUE   0x00000087
+
+/* DPU_SSPP_SRC */
+#define SSPP_SRC_SIZE                      0x00
+#define SSPP_SRC_XY                        0x08
+#define SSPP_OUT_SIZE                      0x0c
+#define SSPP_OUT_XY                        0x10
+#define SSPP_SRC0_ADDR                     0x14
+#define SSPP_SRC1_ADDR                     0x18
+#define SSPP_SRC2_ADDR                     0x1C
+#define SSPP_SRC3_ADDR                     0x20
+#define SSPP_SRC_YSTRIDE0                  0x24
+#define SSPP_SRC_YSTRIDE1                  0x28
+#define SSPP_SRC_FORMAT                    0x30
+#define SSPP_SRC_UNPACK_PATTERN            0x34
+#define SSPP_SRC_OP_MODE                   0x38
+
+/* SSPP_MULTIRECT*/
+#define SSPP_SRC_SIZE_REC1                 0x16C
+#define SSPP_SRC_XY_REC1                   0x168
+#define SSPP_OUT_SIZE_REC1                 0x160
+#define SSPP_OUT_XY_REC1                   0x164
+#define SSPP_SRC_FORMAT_REC1               0x174
+#define SSPP_SRC_UNPACK_PATTERN_REC1       0x178
+#define SSPP_SRC_OP_MODE_REC1              0x17C
+#define SSPP_MULTIRECT_OPMODE              0x170
+#define SSPP_SRC_CONSTANT_COLOR_REC1       0x180
+#define SSPP_EXCL_REC_SIZE_REC1            0x184
+#define SSPP_EXCL_REC_XY_REC1              0x188
+
+#define MDSS_MDP_OP_DEINTERLACE            BIT(22)
+#define MDSS_MDP_OP_DEINTERLACE_ODD        BIT(23)
+#define MDSS_MDP_OP_IGC_ROM_1              BIT(18)
+#define MDSS_MDP_OP_IGC_ROM_0              BIT(17)
+#define MDSS_MDP_OP_IGC_EN                 BIT(16)
+#define MDSS_MDP_OP_FLIP_UD                BIT(14)
+#define MDSS_MDP_OP_FLIP_LR                BIT(13)
+#define MDSS_MDP_OP_BWC_EN                 BIT(0)
+#define MDSS_MDP_OP_PE_OVERRIDE            BIT(31)
+#define MDSS_MDP_OP_BWC_LOSSLESS           (0 << 1)
+#define MDSS_MDP_OP_BWC_Q_HIGH             (1 << 1)
+#define MDSS_MDP_OP_BWC_Q_MED              (2 << 1)
+
+#define SSPP_SRC_CONSTANT_COLOR            0x3c
+#define SSPP_EXCL_REC_CTL                  0x40
+#define SSPP_UBWC_STATIC_CTRL              0x44
+#define SSPP_FETCH_CONFIG                  0x048
+#define SSPP_DANGER_LUT                    0x60
+#define SSPP_SAFE_LUT                      0x64
+#define SSPP_CREQ_LUT                      0x68
+#define SSPP_QOS_CTRL                      0x6C
+#define SSPP_DECIMATION_CONFIG             0xB4
+#define SSPP_SRC_ADDR_SW_STATUS            0x70
+#define SSPP_CREQ_LUT_0                    0x74
+#define SSPP_CREQ_LUT_1                    0x78
+#define SSPP_SW_PIX_EXT_C0_LR              0x100
+#define SSPP_SW_PIX_EXT_C0_TB              0x104
+#define SSPP_SW_PIX_EXT_C0_REQ_PIXELS      0x108
+#define SSPP_SW_PIX_EXT_C1C2_LR            0x110
+#define SSPP_SW_PIX_EXT_C1C2_TB            0x114
+#define SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS    0x118
+#define SSPP_SW_PIX_EXT_C3_LR              0x120
+#define SSPP_SW_PIX_EXT_C3_TB              0x124
+#define SSPP_SW_PIX_EXT_C3_REQ_PIXELS      0x128
+#define SSPP_TRAFFIC_SHAPER                0x130
+#define SSPP_CDP_CNTL                      0x134
+#define SSPP_UBWC_ERROR_STATUS             0x138
+#define SSPP_TRAFFIC_SHAPER_PREFILL        0x150
+#define SSPP_TRAFFIC_SHAPER_REC1_PREFILL   0x154
+#define SSPP_TRAFFIC_SHAPER_REC1           0x158
+#define SSPP_EXCL_REC_SIZE                 0x1B4
+#define SSPP_EXCL_REC_XY                   0x1B8
+#define SSPP_VIG_OP_MODE                   0x0
+#define SSPP_VIG_CSC_10_OP_MODE            0x0
+#define SSPP_TRAFFIC_SHAPER_BPC_MAX        0xFF
+
+/* SSPP_QOS_CTRL */
+#define SSPP_QOS_CTRL_VBLANK_EN            BIT(16)
+#define SSPP_QOS_CTRL_DANGER_SAFE_EN       BIT(0)
+#define SSPP_QOS_CTRL_DANGER_VBLANK_MASK   0x3
+#define SSPP_QOS_CTRL_DANGER_VBLANK_OFF    4
+#define SSPP_QOS_CTRL_CREQ_VBLANK_MASK     0x3
+#define SSPP_QOS_CTRL_CREQ_VBLANK_OFF      20
+
+/* DPU_SSPP_SCALER_QSEED2 */
+#define SCALE_CONFIG                       0x04
+#define COMP0_3_PHASE_STEP_X               0x10
+#define COMP0_3_PHASE_STEP_Y               0x14
+#define COMP1_2_PHASE_STEP_X               0x18
+#define COMP1_2_PHASE_STEP_Y               0x1c
+#define COMP0_3_INIT_PHASE_X               0x20
+#define COMP0_3_INIT_PHASE_Y               0x24
+#define COMP1_2_INIT_PHASE_X               0x28
+#define COMP1_2_INIT_PHASE_Y               0x2C
+#define VIG_0_QSEED2_SHARP                 0x30
+
+/*
+ * Definitions for ViG op modes
+ */
+#define VIG_OP_CSC_DST_DATAFMT BIT(19)
+#define VIG_OP_CSC_SRC_DATAFMT BIT(18)
+#define VIG_OP_CSC_EN          BIT(17)
+#define VIG_OP_MEM_PROT_CONT   BIT(15)
+#define VIG_OP_MEM_PROT_VAL    BIT(14)
+#define VIG_OP_MEM_PROT_SAT    BIT(13)
+#define VIG_OP_MEM_PROT_HUE    BIT(12)
+#define VIG_OP_HIST            BIT(8)
+#define VIG_OP_SKY_COL         BIT(7)
+#define VIG_OP_FOIL            BIT(6)
+#define VIG_OP_SKIN_COL        BIT(5)
+#define VIG_OP_PA_EN           BIT(4)
+#define VIG_OP_PA_SAT_ZERO_EXP BIT(2)
+#define VIG_OP_MEM_PROT_BLEND  BIT(1)
+
+/*
+ * Definitions for CSC 10 op modes
+ */
+#define VIG_CSC_10_SRC_DATAFMT BIT(1)
+#define VIG_CSC_10_EN          BIT(0)
+#define CSC_10BIT_OFFSET       4
+
+/* traffic shaper clock in Hz */
+#define TS_CLK			19200000
+
+static inline int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
+		int s_id,
+		u32 *idx)
+{
+	int rc = 0;
+	const struct dpu_sspp_sub_blks *sblk = ctx->cap->sblk;
+
+	if (!ctx)
+		return -EINVAL;
+
+	switch (s_id) {
+	case DPU_SSPP_SRC:
+		*idx = sblk->src_blk.base;
+		break;
+	case DPU_SSPP_SCALER_QSEED2:
+	case DPU_SSPP_SCALER_QSEED3:
+	case DPU_SSPP_SCALER_RGB:
+		*idx = sblk->scaler_blk.base;
+		break;
+	case DPU_SSPP_CSC:
+	case DPU_SSPP_CSC_10BIT:
+		*idx = sblk->csc_blk.base;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void dpu_hw_sspp_setup_multirect(struct dpu_hw_pipe *ctx,
+		enum dpu_sspp_multirect_index index,
+		enum dpu_sspp_multirect_mode mode)
+{
+	u32 mode_mask;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (index == DPU_SSPP_RECT_SOLO) {
+		/**
+		 * if rect index is RECT_SOLO, we cannot expect a
+		 * virtual plane sharing the same SSPP id. So we go
+		 * and disable multirect
+		 */
+		mode_mask = 0;
+	} else {
+		mode_mask = DPU_REG_READ(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx);
+		mode_mask |= index;
+		if (mode == DPU_SSPP_MULTIRECT_TIME_MX)
+			mode_mask |= BIT(2);
+		else
+			mode_mask &= ~BIT(2);
+	}
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx, mode_mask);
+}
+
+static void _sspp_setup_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (!test_bit(DPU_SSPP_SCALER_QSEED2, &ctx->cap->features) ||
+		_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED2, &idx) ||
+		!test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_OP_MODE + idx);
+
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_OP_MODE + idx, opmode);
+}
+
+static void _sspp_setup_csc10_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC_10BIT, &idx))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx);
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx, opmode);
+}
+
+/**
+ * Setup source pixel format, flip,
+ */
+static void dpu_hw_sspp_setup_format(struct dpu_hw_pipe *ctx,
+		const struct dpu_format *fmt, u32 flags,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 chroma_samp, unpack, src_format;
+	u32 opmode = 0;
+	u32 fast_clear = 0;
+	u32 op_mode_off, unpack_pat_off, format_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !fmt)
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO || rect_mode == DPU_SSPP_RECT_0) {
+		op_mode_off = SSPP_SRC_OP_MODE;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN;
+		format_off = SSPP_SRC_FORMAT;
+	} else {
+		op_mode_off = SSPP_SRC_OP_MODE_REC1;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN_REC1;
+		format_off = SSPP_SRC_FORMAT_REC1;
+	}
+
+	c = &ctx->hw;
+	opmode = DPU_REG_READ(c, op_mode_off + idx);
+	opmode &= ~(MDSS_MDP_OP_FLIP_LR | MDSS_MDP_OP_FLIP_UD |
+			MDSS_MDP_OP_BWC_EN | MDSS_MDP_OP_PE_OVERRIDE);
+
+	if (flags & DPU_SSPP_FLIP_LR)
+		opmode |= MDSS_MDP_OP_FLIP_LR;
+	if (flags & DPU_SSPP_FLIP_UD)
+		opmode |= MDSS_MDP_OP_FLIP_UD;
+
+	chroma_samp = fmt->chroma_sample;
+	if (flags & DPU_SSPP_SOURCE_ROTATED_90) {
+		if (chroma_samp == DPU_CHROMA_H2V1)
+			chroma_samp = DPU_CHROMA_H1V2;
+		else if (chroma_samp == DPU_CHROMA_H1V2)
+			chroma_samp = DPU_CHROMA_H2V1;
+	}
+
+	src_format = (chroma_samp << 23) | (fmt->fetch_planes << 19) |
+		(fmt->bits[C3_ALPHA] << 6) | (fmt->bits[C2_R_Cr] << 4) |
+		(fmt->bits[C1_B_Cb] << 2) | (fmt->bits[C0_G_Y] << 0);
+
+	if (flags & DPU_SSPP_ROT_90)
+		src_format |= BIT(11); /* ROT90 */
+
+	if (fmt->alpha_enable && fmt->fetch_planes == DPU_PLANE_INTERLEAVED)
+		src_format |= BIT(8); /* SRCC3_EN */
+
+	if (flags & DPU_SSPP_SOLID_FILL)
+		src_format |= BIT(22);
+
+	unpack = (fmt->element[3] << 24) | (fmt->element[2] << 16) |
+		(fmt->element[1] << 8) | (fmt->element[0] << 0);
+	src_format |= ((fmt->unpack_count - 1) << 12) |
+		(fmt->unpack_tight << 17) |
+		(fmt->unpack_align_msb << 18) |
+		((fmt->bpp - 1) << 9);
+
+	if (fmt->fetch_mode != DPU_FETCH_LINEAR) {
+		if (DPU_FORMAT_IS_UBWC(fmt))
+			opmode |= MDSS_MDP_OP_BWC_EN;
+		src_format |= (fmt->fetch_mode & 3) << 30; /*FRAME_FORMAT */
+		DPU_REG_WRITE(c, SSPP_FETCH_CONFIG,
+			DPU_FETCH_CONFIG_RESET_VALUE |
+			ctx->mdp->highest_bank_bit << 18);
+		if (IS_UBWC_20_SUPPORTED(ctx->catalog->caps->ubwc_version)) {
+			fast_clear = fmt->alpha_enable ? BIT(31) : 0;
+			DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL,
+					fast_clear | (ctx->mdp->ubwc_swizzle) |
+					(ctx->mdp->highest_bank_bit << 4));
+		}
+	}
+
+	opmode |= MDSS_MDP_OP_PE_OVERRIDE;
+
+	/* if this is YUV pixel format, enable CSC */
+	if (DPU_FORMAT_IS_YUV(fmt))
+		src_format |= BIT(15);
+
+	if (DPU_FORMAT_IS_DX(fmt))
+		src_format |= BIT(14);
+
+	/* update scaler opmode, if appropriate */
+	if (test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		_sspp_setup_opmode(ctx, VIG_OP_CSC_EN | VIG_OP_CSC_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+	else if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features))
+		_sspp_setup_csc10_opmode(ctx,
+			VIG_CSC_10_EN | VIG_CSC_10_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+
+	DPU_REG_WRITE(c, format_off + idx, src_format);
+	DPU_REG_WRITE(c, unpack_pat_off + idx, unpack);
+	DPU_REG_WRITE(c, op_mode_off + idx, opmode);
+
+	/* clear previous UBWC error */
+	DPU_REG_WRITE(c, SSPP_UBWC_ERROR_STATUS + idx, BIT(31));
+}
+
+static void dpu_hw_sspp_setup_pe_config(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pixel_ext *pe_ext)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u8 color;
+	u32 lr_pe[4], tb_pe[4], tot_req_pixels[4];
+	const u32 bytemask = 0xff;
+	const u32 shortmask = 0xffff;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !pe_ext)
+		return;
+
+	c = &ctx->hw;
+
+	/* program SW pixel extension override for all pipes*/
+	for (color = 0; color < DPU_MAX_PLANES; color++) {
+		/* color 2 has the same set of registers as color 1 */
+		if (color == 2)
+			continue;
+
+		lr_pe[color] = ((pe_ext->right_ftch[color] & bytemask) << 24)|
+			((pe_ext->right_rpt[color] & bytemask) << 16)|
+			((pe_ext->left_ftch[color] & bytemask) << 8)|
+			(pe_ext->left_rpt[color] & bytemask);
+
+		tb_pe[color] = ((pe_ext->btm_ftch[color] & bytemask) << 24)|
+			((pe_ext->btm_rpt[color] & bytemask) << 16)|
+			((pe_ext->top_ftch[color] & bytemask) << 8)|
+			(pe_ext->top_rpt[color] & bytemask);
+
+		tot_req_pixels[color] = (((pe_ext->roi_h[color] +
+			pe_ext->num_ext_pxls_top[color] +
+			pe_ext->num_ext_pxls_btm[color]) & shortmask) << 16) |
+			((pe_ext->roi_w[color] +
+			pe_ext->num_ext_pxls_left[color] +
+			pe_ext->num_ext_pxls_right[color]) & shortmask);
+	}
+
+	/* color 0 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_LR + idx, lr_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_TB + idx, tb_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_REQ_PIXELS + idx,
+			tot_req_pixels[0]);
+
+	/* color 1 and color 2 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_LR + idx, lr_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_TB + idx, tb_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS + idx,
+			tot_req_pixels[1]);
+
+	/* color 3 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_LR + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_TB + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_REQ_PIXELS + idx,
+			tot_req_pixels[3]);
+}
+
+static void _dpu_hw_sspp_setup_scaler3(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *sspp,
+		struct dpu_hw_pixel_ext *pe,
+		void *scaler_cfg)
+{
+	u32 idx;
+	struct dpu_hw_scaler3_cfg *scaler3_cfg = scaler_cfg;
+
+	(void)pe;
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx) || !sspp
+		|| !scaler3_cfg || !ctx || !ctx->cap || !ctx->cap->sblk)
+		return;
+
+	dpu_hw_setup_scaler3(&ctx->hw, scaler3_cfg, idx,
+			ctx->cap->sblk->scaler_blk.version,
+			sspp->layout.format);
+}
+
+static u32 _dpu_hw_sspp_get_scaler3_ver(struct dpu_hw_pipe *ctx)
+{
+	u32 idx;
+
+	if (!ctx || _sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx))
+		return 0;
+
+	return dpu_hw_get_scaler3_ver(&ctx->hw, idx);
+}
+
+/**
+ * dpu_hw_sspp_setup_rects()
+ */
+static void dpu_hw_sspp_setup_rects(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_index)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 src_size, src_xy, dst_size, dst_xy, ystride0, ystride1;
+	u32 src_size_off, src_xy_off, out_size_off, out_xy_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !cfg)
+		return;
+
+	c = &ctx->hw;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0) {
+		src_size_off = SSPP_SRC_SIZE;
+		src_xy_off = SSPP_SRC_XY;
+		out_size_off = SSPP_OUT_SIZE;
+		out_xy_off = SSPP_OUT_XY;
+	} else {
+		src_size_off = SSPP_SRC_SIZE_REC1;
+		src_xy_off = SSPP_SRC_XY_REC1;
+		out_size_off = SSPP_OUT_SIZE_REC1;
+		out_xy_off = SSPP_OUT_XY_REC1;
+	}
+
+
+	/* src and dest rect programming */
+	src_xy = (cfg->src_rect.y1 << 16) | cfg->src_rect.x1;
+	src_size = (drm_rect_height(&cfg->src_rect) << 16) |
+		   drm_rect_width(&cfg->src_rect);
+	dst_xy = (cfg->dst_rect.y1 << 16) | cfg->dst_rect.x1;
+	dst_size = (drm_rect_height(&cfg->dst_rect) << 16) |
+		drm_rect_width(&cfg->dst_rect);
+
+	if (rect_index == DPU_SSPP_RECT_SOLO) {
+		ystride0 = (cfg->layout.plane_pitch[0]) |
+			(cfg->layout.plane_pitch[1] << 16);
+		ystride1 = (cfg->layout.plane_pitch[2]) |
+			(cfg->layout.plane_pitch[3] << 16);
+	} else {
+		ystride0 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE0 + idx);
+		ystride1 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE1 + idx);
+
+		if (rect_index == DPU_SSPP_RECT_0) {
+			ystride0 = (ystride0 & 0xFFFF0000) |
+				(cfg->layout.plane_pitch[0] & 0x0000FFFF);
+			ystride1 = (ystride1 & 0xFFFF0000)|
+				(cfg->layout.plane_pitch[2] & 0x0000FFFF);
+		} else {
+			ystride0 = (ystride0 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[0] << 16) &
+				 0xFFFF0000);
+			ystride1 = (ystride1 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[2] << 16) &
+				 0xFFFF0000);
+		}
+	}
+
+	/* rectangle register programming */
+	DPU_REG_WRITE(c, src_size_off + idx, src_size);
+	DPU_REG_WRITE(c, src_xy_off + idx, src_xy);
+	DPU_REG_WRITE(c, out_size_off + idx, dst_size);
+	DPU_REG_WRITE(c, out_xy_off + idx, dst_xy);
+
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE0 + idx, ystride0);
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE1 + idx, ystride1);
+}
+
+static void dpu_hw_sspp_setup_sourceaddress(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	int i;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO) {
+		for (i = 0; i < ARRAY_SIZE(cfg->layout.plane_addr); i++)
+			DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx + i * 0x4,
+					cfg->layout.plane_addr[i]);
+	} else if (rect_mode == DPU_SSPP_RECT_0) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC2_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC1_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC3_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	}
+}
+
+static void dpu_hw_sspp_setup_csc(struct dpu_hw_pipe *ctx,
+		struct dpu_csc_cfg *data)
+{
+	u32 idx;
+	bool csc10 = false;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC, &idx) || !data)
+		return;
+
+	if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features)) {
+		idx += CSC_10BIT_OFFSET;
+		csc10 = true;
+	}
+
+	dpu_hw_csc_setup(&ctx->hw, idx, data, csc10);
+}
+
+static void dpu_hw_sspp_setup_solidfill(struct dpu_hw_pipe *ctx, u32 color, enum
+		dpu_sspp_multirect_index rect_index)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0)
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR + idx, color);
+	else
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR_REC1 + idx,
+				color);
+}
+
+static void dpu_hw_sspp_setup_danger_safe_lut(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_DANGER_LUT + idx, cfg->danger_lut);
+	DPU_REG_WRITE(&ctx->hw, SSPP_SAFE_LUT + idx, cfg->safe_lut);
+}
+
+static void dpu_hw_sspp_setup_creq_lut(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (ctx->cap && test_bit(DPU_SSPP_QOS_8LVL, &ctx->cap->features)) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_0 + idx, cfg->creq_lut);
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_1 + idx,
+				cfg->creq_lut >> 32);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT + idx, cfg->creq_lut);
+	}
+}
+
+static void dpu_hw_sspp_setup_qos_ctrl(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+	u32 qos_ctrl = 0;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->vblank_en) {
+		qos_ctrl |= ((cfg->creq_vblank &
+				SSPP_QOS_CTRL_CREQ_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_CREQ_VBLANK_OFF);
+		qos_ctrl |= ((cfg->danger_vblank &
+				SSPP_QOS_CTRL_DANGER_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_DANGER_VBLANK_OFF);
+		qos_ctrl |= SSPP_QOS_CTRL_VBLANK_EN;
+	}
+
+	if (cfg->danger_safe_en)
+		qos_ctrl |= SSPP_QOS_CTRL_DANGER_SAFE_EN;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_QOS_CTRL + idx, qos_ctrl);
+}
+
+static void dpu_hw_sspp_setup_cdp(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cdp_cfg *cfg)
+{
+	u32 idx;
+	u32 cdp_cntl = 0;
+
+	if (!ctx || !cfg)
+		return;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->enable)
+		cdp_cntl |= BIT(0);
+	if (cfg->ubwc_meta_enable)
+		cdp_cntl |= BIT(1);
+	if (cfg->tile_amortize_enable)
+		cdp_cntl |= BIT(2);
+	if (cfg->preload_ahead == DPU_SSPP_CDP_PRELOAD_AHEAD_64)
+		cdp_cntl |= BIT(3);
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_CDP_CNTL, cdp_cntl);
+}
+
+static void _setup_layer_ops(struct dpu_hw_pipe *c,
+		unsigned long features)
+{
+	if (test_bit(DPU_SSPP_SRC, &features)) {
+		c->ops.setup_format = dpu_hw_sspp_setup_format;
+		c->ops.setup_rects = dpu_hw_sspp_setup_rects;
+		c->ops.setup_sourceaddress = dpu_hw_sspp_setup_sourceaddress;
+		c->ops.setup_solidfill = dpu_hw_sspp_setup_solidfill;
+		c->ops.setup_pe = dpu_hw_sspp_setup_pe_config;
+	}
+
+	if (test_bit(DPU_SSPP_QOS, &features)) {
+		c->ops.setup_danger_safe_lut =
+			dpu_hw_sspp_setup_danger_safe_lut;
+		c->ops.setup_creq_lut = dpu_hw_sspp_setup_creq_lut;
+		c->ops.setup_qos_ctrl = dpu_hw_sspp_setup_qos_ctrl;
+	}
+
+	if (test_bit(DPU_SSPP_CSC, &features) ||
+		test_bit(DPU_SSPP_CSC_10BIT, &features))
+		c->ops.setup_csc = dpu_hw_sspp_setup_csc;
+
+	if (dpu_hw_sspp_multirect_enabled(c->cap))
+		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
+
+	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) {
+		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
+		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
+	}
+
+	if (test_bit(DPU_SSPP_CDP, &features))
+		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
+}
+
+static 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)
+{
+	int i;
+
+	if ((sspp < SSPP_MAX) && catalog && addr && b) {
+		for (i = 0; i < catalog->sspp_count; i++) {
+			if (sspp == catalog->sspp[i].id) {
+				b->base_off = addr;
+				b->blk_off = catalog->sspp[i].base;
+				b->length = catalog->sspp[i].len;
+				b->hwversion = catalog->hwversion;
+				b->log_mask = DPU_DBG_MASK_SSPP;
+				return &catalog->sspp[i];
+			}
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, struct dpu_mdss_cfg *catalog,
+		bool is_virtual_pipe)
+{
+	struct dpu_hw_pipe *hw_pipe;
+	struct dpu_sspp_cfg *cfg;
+	int rc;
+
+	if (!addr || !catalog)
+		return ERR_PTR(-EINVAL);
+
+	hw_pipe = kzalloc(sizeof(*hw_pipe), GFP_KERNEL);
+	if (!hw_pipe)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _sspp_offset(idx, addr, catalog, &hw_pipe->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(hw_pipe);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	hw_pipe->catalog = catalog;
+	hw_pipe->mdp = &catalog->mdp[0];
+	hw_pipe->idx = idx;
+	hw_pipe->cap = cfg;
+	_setup_layer_ops(hw_pipe, hw_pipe->cap->features);
+
+	rc = dpu_hw_blk_init(&hw_pipe->base, DPU_HW_BLK_SSPP, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return hw_pipe;
+
+blk_init_error:
+	kzfree(hw_pipe);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx)
+{
+	if (ctx)
+		dpu_hw_blk_destroy(&ctx->base);
+	kfree(ctx);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
new file mode 100644
index 000000000000..4d81e5f5ce1b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -0,0 +1,424 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_SSPP_H
+#define _DPU_HW_SSPP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+#include "dpu_formats.h"
+
+struct dpu_hw_pipe;
+
+/**
+ * Flags
+ */
+#define DPU_SSPP_FLIP_LR		BIT(0)
+#define DPU_SSPP_FLIP_UD		BIT(1)
+#define DPU_SSPP_SOURCE_ROTATED_90	BIT(2)
+#define DPU_SSPP_ROT_90			BIT(3)
+#define DPU_SSPP_SOLID_FILL		BIT(4)
+
+/**
+ * Define all scaler feature bits in catalog
+ */
+#define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \
+	(1UL << DPU_SSPP_SCALER_QSEED2) | \
+	(1UL << DPU_SSPP_SCALER_QSEED3))
+
+/**
+ * Component indices
+ */
+enum {
+	DPU_SSPP_COMP_0,
+	DPU_SSPP_COMP_1_2,
+	DPU_SSPP_COMP_2,
+	DPU_SSPP_COMP_3,
+
+	DPU_SSPP_COMP_MAX
+};
+
+/**
+ * DPU_SSPP_RECT_SOLO - multirect disabled
+ * DPU_SSPP_RECT_0 - rect0 of a multirect pipe
+ * DPU_SSPP_RECT_1 - rect1 of a multirect pipe
+ *
+ * Note: HW supports multirect with either RECT0 or
+ * RECT1. Considering no benefit of such configs over
+ * SOLO mode and to keep the plane management simple,
+ * we dont support single rect multirect configs.
+ */
+enum dpu_sspp_multirect_index {
+	DPU_SSPP_RECT_SOLO = 0,
+	DPU_SSPP_RECT_0,
+	DPU_SSPP_RECT_1,
+};
+
+enum dpu_sspp_multirect_mode {
+	DPU_SSPP_MULTIRECT_NONE = 0,
+	DPU_SSPP_MULTIRECT_PARALLEL,
+	DPU_SSPP_MULTIRECT_TIME_MX,
+};
+
+enum {
+	DPU_FRAME_LINEAR,
+	DPU_FRAME_TILE_A4X,
+	DPU_FRAME_TILE_A5X,
+};
+
+enum dpu_hw_filter {
+	DPU_SCALE_FILTER_NEAREST = 0,
+	DPU_SCALE_FILTER_BIL,
+	DPU_SCALE_FILTER_PCMN,
+	DPU_SCALE_FILTER_CA,
+	DPU_SCALE_FILTER_MAX
+};
+
+enum dpu_hw_filter_alpa {
+	DPU_SCALE_ALPHA_PIXEL_REP,
+	DPU_SCALE_ALPHA_BIL
+};
+
+enum dpu_hw_filter_yuv {
+	DPU_SCALE_2D_4X4,
+	DPU_SCALE_2D_CIR,
+	DPU_SCALE_1D_SEP,
+	DPU_SCALE_BIL
+};
+
+struct dpu_hw_sharp_cfg {
+	u32 strength;
+	u32 edge_thr;
+	u32 smooth_thr;
+	u32 noise_thr;
+};
+
+struct dpu_hw_pixel_ext {
+	/* scaling factors are enabled for this input layer */
+	uint8_t enable_pxl_ext;
+
+	int init_phase_x[DPU_MAX_PLANES];
+	int phase_step_x[DPU_MAX_PLANES];
+	int init_phase_y[DPU_MAX_PLANES];
+	int phase_step_y[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels extension in left, right, top and bottom direction
+	 * for all color components. This pixel value for each color component
+	 * should be sum of fetch + repeat pixels.
+	 */
+	int num_ext_pxls_left[DPU_MAX_PLANES];
+	int num_ext_pxls_right[DPU_MAX_PLANES];
+	int num_ext_pxls_top[DPU_MAX_PLANES];
+	int num_ext_pxls_btm[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top and
+	 * bottom directions from source image for scaling.
+	 */
+	int left_ftch[DPU_MAX_PLANES];
+	int right_ftch[DPU_MAX_PLANES];
+	int top_ftch[DPU_MAX_PLANES];
+	int btm_ftch[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int left_rpt[DPU_MAX_PLANES];
+	int right_rpt[DPU_MAX_PLANES];
+	int top_rpt[DPU_MAX_PLANES];
+	int btm_rpt[DPU_MAX_PLANES];
+
+	uint32_t roi_w[DPU_MAX_PLANES];
+	uint32_t roi_h[DPU_MAX_PLANES];
+
+	/*
+	 * Filter type to be used for scaling in horizontal and vertical
+	 * directions
+	 */
+	enum dpu_hw_filter horz_filter[DPU_MAX_PLANES];
+	enum dpu_hw_filter vert_filter[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_hw_pipe_cfg : Pipe description
+ * @layout:    format layout information for programming buffer to hardware
+ * @src_rect:  src ROI, caller takes into account the different operations
+ *             such as decimation, flip etc to program this field
+ * @dest_rect: destination ROI.
+ * @index:     index of the rectangle of SSPP
+ * @mode:      parallel or time multiplex multirect mode
+ */
+struct dpu_hw_pipe_cfg {
+	struct dpu_hw_fmt_layout layout;
+	struct drm_rect src_rect;
+	struct drm_rect dst_rect;
+	enum dpu_sspp_multirect_index index;
+	enum dpu_sspp_multirect_mode mode;
+};
+
+/**
+ * struct dpu_hw_pipe_qos_cfg : Source pipe QoS configuration
+ * @danger_lut: LUT for generate danger level based on fill level
+ * @safe_lut: LUT for generate safe level based on fill level
+ * @creq_lut: LUT for generate creq level based on fill level
+ * @creq_vblank: creq value generated to vbif during vertical blanking
+ * @danger_vblank: danger value generated during vertical blanking
+ * @vblank_en: enable creq_vblank and danger_vblank during vblank
+ * @danger_safe_en: enable danger safe generation
+ */
+struct dpu_hw_pipe_qos_cfg {
+	u32 danger_lut;
+	u32 safe_lut;
+	u64 creq_lut;
+	u32 creq_vblank;
+	u32 danger_vblank;
+	bool vblank_en;
+	bool danger_safe_en;
+};
+
+/**
+ * enum CDP preload ahead address size
+ */
+enum {
+	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+};
+
+/**
+ * struct dpu_hw_pipe_cdp_cfg : CDP configuration
+ * @enable: true to enable CDP
+ * @ubwc_meta_enable: true to enable ubwc metadata preload
+ * @tile_amortize_enable: true to enable amortization control for tile format
+ * @preload_ahead: number of request to preload ahead
+ *	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+ *	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+ */
+struct dpu_hw_pipe_cdp_cfg {
+	bool enable;
+	bool ubwc_meta_enable;
+	bool tile_amortize_enable;
+	u32 preload_ahead;
+};
+
+/**
+ * struct dpu_hw_pipe_ts_cfg - traffic shaper configuration
+ * @size: size to prefill in bytes, or zero to disable
+ * @time: time to prefill in usec, or zero to disable
+ */
+struct dpu_hw_pipe_ts_cfg {
+	u64 size;
+	u64 time;
+};
+
+/**
+ * struct dpu_hw_sspp_ops - interface to the SSPP Hw driver functions
+ * Caller must call the init function to get the pipe context for each pipe
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_sspp_ops {
+	/**
+	 * setup_format - setup pixel format cropping rectangle, flip
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @flags: Extra flags for format config
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_format)(struct dpu_hw_pipe *ctx,
+			const struct dpu_format *fmt, u32 flags,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_rects - setup pipe ROI rectangles
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_rects)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_pe - setup pipe pixel extension
+	 * @ctx: Pointer to pipe context
+	 * @pe_ext: Pointer to pixel ext settings
+	 */
+	void (*setup_pe)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pixel_ext *pe_ext);
+
+	/**
+	 * setup_sourceaddress - setup pipe source addresses
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_sourceaddress)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_csc - setup color space coversion
+	 * @ctx: Pointer to pipe context
+	 * @data: Pointer to config structure
+	 */
+	void (*setup_csc)(struct dpu_hw_pipe *ctx, struct dpu_csc_cfg *data);
+
+	/**
+	 * setup_solidfill - enable/disable colorfill
+	 * @ctx: Pointer to pipe context
+	 * @const_color: Fill color value
+	 * @flags: Pipe flags
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_solidfill)(struct dpu_hw_pipe *ctx, u32 color,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_multirect - setup multirect configuration
+	 * @ctx: Pointer to pipe context
+	 * @index: rectangle index in multirect
+	 * @mode: parallel fetch / time multiplex multirect mode
+	 */
+
+	void (*setup_multirect)(struct dpu_hw_pipe *ctx,
+			enum dpu_sspp_multirect_index index,
+			enum dpu_sspp_multirect_mode mode);
+
+	/**
+	 * setup_sharpening - setup sharpening
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to config structure
+	 */
+	void (*setup_sharpening)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_sharp_cfg *cfg);
+
+	/**
+	 * setup_danger_safe_lut - setup danger safe LUTs
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_danger_safe_lut)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_creq_lut - setup CREQ LUT
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_creq_lut)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_qos_ctrl - setup QoS control
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_qos_ctrl)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_histogram - setup histograms
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to histogram configuration
+	 */
+	void (*setup_histogram)(struct dpu_hw_pipe *ctx,
+			void *cfg);
+
+	/**
+	 * setup_scaler - setup scaler
+	 * @ctx: Pointer to pipe context
+	 * @pipe_cfg: Pointer to pipe configuration
+	 * @pe_cfg: Pointer to pixel extension configuration
+	 * @scaler_cfg: Pointer to scaler configuration
+	 */
+	void (*setup_scaler)(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct dpu_hw_pixel_ext *pe_cfg,
+		void *scaler_cfg);
+
+	/**
+	 * get_scaler_ver - get scaler h/w version
+	 * @ctx: Pointer to pipe context
+	 */
+	u32 (*get_scaler_ver)(struct dpu_hw_pipe *ctx);
+
+	/**
+	 * setup_cdp - setup client driven prefetch
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to cdp configuration
+	 */
+	void (*setup_cdp)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cdp_cfg *cfg);
+};
+
+/**
+ * struct dpu_hw_pipe - pipe description
+ * @base: hardware block base structure
+ * @hw: block hardware details
+ * @catalog: back pointer to catalog
+ * @mdp: pointer to associated mdp portion of the catalog
+ * @idx: pipe index
+ * @cap: pointer to layer_cfg
+ * @ops: pointer to operations possible for this pipe
+ */
+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;
+
+	/* Pipe */
+	enum dpu_sspp idx;
+	const struct dpu_sspp_cfg *cap;
+
+	/* Ops */
+	struct dpu_hw_sspp_ops ops;
+};
+
+/**
+ * dpu_hw_pipe - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pipe *to_dpu_hw_pipe(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pipe, base);
+}
+
+/**
+ * dpu_hw_sspp_init - initializes the sspp hw driver object.
+ * Should be called once before accessing every pipe.
+ * @idx:  Pipe index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @catalog : Pointer to mdss catalog data
+ * @is_virtual_pipe: is this pipe virtual pipe
+ */
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, struct dpu_mdss_cfg *catalog,
+		bool is_virtual_pipe);
+
+/**
+ * dpu_hw_sspp_destroy(): Destroys SSPP driver context
+ * should be called during Hw pipe cleanup.
+ * @ctx:  Pointer to SSPP driver context returned by dpu_hw_sspp_init
+ */
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx);
+
+#endif /*_DPU_HW_SSPP_H */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
new file mode 100644
index 000000000000..db2798e862fc
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -0,0 +1,398 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_top.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define SSPP_SPARE                        0x28
+#define UBWC_STATIC                       0x144
+
+#define FLD_SPLIT_DISPLAY_CMD             BIT(1)
+#define FLD_SMART_PANEL_FREE_RUN          BIT(2)
+#define FLD_INTF_1_SW_TRG_MUX             BIT(4)
+#define FLD_INTF_2_SW_TRG_MUX             BIT(8)
+#define FLD_TE_LINE_INTER_WATERLEVEL_MASK 0xFFFF
+
+#define DANGER_STATUS                     0x360
+#define SAFE_STATUS                       0x364
+
+#define TE_LINE_INTERVAL                  0x3F4
+
+#define TRAFFIC_SHAPER_EN                 BIT(31)
+#define TRAFFIC_SHAPER_RD_CLIENT(num)     (0x030 + (num * 4))
+#define TRAFFIC_SHAPER_WR_CLIENT(num)     (0x060 + (num * 4))
+#define TRAFFIC_SHAPER_FIXPOINT_FACTOR    4
+
+#define MDP_WD_TIMER_0_CTL                0x380
+#define MDP_WD_TIMER_0_CTL2               0x384
+#define MDP_WD_TIMER_0_LOAD_VALUE         0x388
+#define MDP_WD_TIMER_1_CTL                0x390
+#define MDP_WD_TIMER_1_CTL2               0x394
+#define MDP_WD_TIMER_1_LOAD_VALUE         0x398
+#define MDP_WD_TIMER_2_CTL                0x420
+#define MDP_WD_TIMER_2_CTL2               0x424
+#define MDP_WD_TIMER_2_LOAD_VALUE         0x428
+#define MDP_WD_TIMER_3_CTL                0x430
+#define MDP_WD_TIMER_3_CTL2               0x434
+#define MDP_WD_TIMER_3_LOAD_VALUE         0x438
+#define MDP_WD_TIMER_4_CTL                0x440
+#define MDP_WD_TIMER_4_CTL2               0x444
+#define MDP_WD_TIMER_4_LOAD_VALUE         0x448
+
+#define MDP_TICK_COUNT                    16
+#define XO_CLK_RATE                       19200
+#define MS_TICKS_IN_SEC                   1000
+
+#define CALCULATE_WD_LOAD_VALUE(fps) \
+	((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps)))
+
+#define DCE_SEL                           0x450
+
+static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp,
+		struct split_pipe_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 upper_pipe = 0;
+	u32 lower_pipe = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->en) {
+		if (cfg->mode == INTF_MODE_CMD) {
+			lower_pipe = FLD_SPLIT_DISPLAY_CMD;
+			/* interface controlling sw trigger */
+			if (cfg->intf == INTF_2)
+				lower_pipe |= FLD_INTF_1_SW_TRG_MUX;
+			else
+				lower_pipe |= FLD_INTF_2_SW_TRG_MUX;
+			upper_pipe = lower_pipe;
+		} else {
+			if (cfg->intf == INTF_2) {
+				lower_pipe = FLD_INTF_1_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_2_SW_TRG_MUX;
+			} else {
+				lower_pipe = FLD_INTF_2_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_1_SW_TRG_MUX;
+			}
+		}
+	}
+
+	DPU_REG_WRITE(c, SSPP_SPARE, cfg->split_flush_en ? 0x1 : 0x0);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_LOWER_PIPE_CTRL, lower_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_UPPER_PIPE_CTRL, upper_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_EN, cfg->en & 0x1);
+}
+
+static void dpu_hw_setup_cdm_output(struct dpu_hw_mdp *mdp,
+		struct cdm_output_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 out_ctl = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->intf_en)
+		out_ctl |= BIT(19);
+
+	DPU_REG_WRITE(c, MDP_OUT_CTL_0, out_ctl);
+}
+
+static bool dpu_hw_setup_clk_force_ctrl(struct dpu_hw_mdp *mdp,
+		enum dpu_clk_ctrl_type clk_ctrl, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off, bit_off;
+	u32 reg_val, new_val;
+	bool clk_forced_on;
+
+	if (!mdp)
+		return false;
+
+	c = &mdp->hw;
+
+	if (clk_ctrl <= DPU_CLK_CTRL_NONE || clk_ctrl >= DPU_CLK_CTRL_MAX)
+		return false;
+
+	reg_off = mdp->caps->clk_ctrls[clk_ctrl].reg_off;
+	bit_off = mdp->caps->clk_ctrls[clk_ctrl].bit_off;
+
+	reg_val = DPU_REG_READ(c, reg_off);
+
+	if (enable)
+		new_val = reg_val | BIT(bit_off);
+	else
+		new_val = reg_val & ~BIT(bit_off);
+
+	DPU_REG_WRITE(c, reg_off, new_val);
+
+	clk_forced_on = !(reg_val & BIT(bit_off));
+
+	return clk_forced_on;
+}
+
+
+static void dpu_hw_get_danger_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, DANGER_STATUS);
+	status->mdp = (value >> 0) & 0x3;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x3;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x3;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x3;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x3;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x3;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x3;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x3;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x3;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x3;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x3;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x3;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x3;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x3;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x3;
+}
+
+static void dpu_hw_setup_vsync_source(struct dpu_hw_mdp *mdp,
+		struct dpu_vsync_source_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg, wd_load_value, wd_ctl, wd_ctl2, i;
+	static const u32 pp_offset[PINGPONG_MAX] = {0xC, 0x8, 0x4, 0x13, 0x18};
+
+	if (!mdp || !cfg || (cfg->pp_count > ARRAY_SIZE(cfg->ppnumber)))
+		return;
+
+	c = &mdp->hw;
+	reg = DPU_REG_READ(c, MDP_VSYNC_SEL);
+	for (i = 0; i < cfg->pp_count; i++) {
+		int pp_idx = cfg->ppnumber[i] - PINGPONG_0;
+
+		if (pp_idx >= ARRAY_SIZE(pp_offset))
+			continue;
+
+		reg &= ~(0xf << pp_offset[pp_idx]);
+		reg |= (cfg->vsync_source & 0xf) << pp_offset[pp_idx];
+	}
+	DPU_REG_WRITE(c, MDP_VSYNC_SEL, reg);
+
+	if (cfg->vsync_source >= DPU_VSYNC_SOURCE_WD_TIMER_4 &&
+			cfg->vsync_source <= DPU_VSYNC_SOURCE_WD_TIMER_0) {
+		switch (cfg->vsync_source) {
+		case DPU_VSYNC_SOURCE_WD_TIMER_4:
+			wd_load_value = MDP_WD_TIMER_4_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_4_CTL;
+			wd_ctl2 = MDP_WD_TIMER_4_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_3:
+			wd_load_value = MDP_WD_TIMER_3_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_3_CTL;
+			wd_ctl2 = MDP_WD_TIMER_3_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_2:
+			wd_load_value = MDP_WD_TIMER_2_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_2_CTL;
+			wd_ctl2 = MDP_WD_TIMER_2_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_1:
+			wd_load_value = MDP_WD_TIMER_1_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_1_CTL;
+			wd_ctl2 = MDP_WD_TIMER_1_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_0:
+		default:
+			wd_load_value = MDP_WD_TIMER_0_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_0_CTL;
+			wd_ctl2 = MDP_WD_TIMER_0_CTL2;
+			break;
+		}
+
+		DPU_REG_WRITE(c, wd_load_value,
+			CALCULATE_WD_LOAD_VALUE(cfg->frame_rate));
+
+		DPU_REG_WRITE(c, wd_ctl, BIT(0)); /* clear timer */
+		reg = DPU_REG_READ(c, wd_ctl2);
+		reg |= BIT(8);		/* enable heartbeat timer */
+		reg |= BIT(0);		/* enable WD timer */
+		DPU_REG_WRITE(c, wd_ctl2, reg);
+
+		/* make sure that timers are enabled/disabled for vsync state */
+		wmb();
+	}
+}
+
+static void dpu_hw_get_safe_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, SAFE_STATUS);
+	status->mdp = (value >> 0) & 0x1;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x1;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x1;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x1;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x1;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x1;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x1;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x1;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x1;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x1;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x1;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x1;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x1;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x1;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x1;
+}
+
+static void dpu_hw_reset_ubwc(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_blk_reg_map c;
+
+	if (!mdp || !m)
+		return;
+
+	if (!IS_UBWC_20_SUPPORTED(m->caps->ubwc_version))
+		return;
+
+	/* force blk offset to zero to access beginning of register region */
+	c = mdp->hw;
+	c.blk_off = 0x0;
+	DPU_REG_WRITE(&c, UBWC_STATIC, m->mdp[0].ubwc_static);
+}
+
+static void dpu_hw_intf_audio_select(struct dpu_hw_mdp *mdp)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!mdp)
+		return;
+
+	c = &mdp->hw;
+
+	DPU_REG_WRITE(c, HDMI_DP_CORE_SELECT, 0x1);
+}
+
+static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_split_pipe = dpu_hw_setup_split_pipe;
+	ops->setup_cdm_output = dpu_hw_setup_cdm_output;
+	ops->setup_clk_force_ctrl = dpu_hw_setup_clk_force_ctrl;
+	ops->get_danger_status = dpu_hw_get_danger_status;
+	ops->setup_vsync_source = dpu_hw_setup_vsync_source;
+	ops->get_safe_status = dpu_hw_get_safe_status;
+	ops->reset_ubwc = dpu_hw_reset_ubwc;
+	ops->intf_audio_select = dpu_hw_intf_audio_select;
+}
+
+static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if (!m || !addr || !b)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < m->mdp_count; i++) {
+		if (mdp == m->mdp[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->mdp[i].base;
+			b->length = m->mdp[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_TOP;
+			return &m->mdp[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mdp *mdp;
+	const struct dpu_mdp_cfg *cfg;
+	int rc;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	mdp = kzalloc(sizeof(*mdp), GFP_KERNEL);
+	if (!mdp)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &mdp->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(mdp);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	mdp->idx = idx;
+	mdp->caps = cfg;
+	_setup_mdp_ops(&mdp->ops, mdp->caps->features);
+
+	rc = dpu_hw_blk_init(&mdp->base, DPU_HW_BLK_TOP, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	dpu_dbg_set_dpu_top_offset(mdp->hw.blk_off);
+
+	return mdp;
+
+blk_init_error:
+	kzfree(mdp);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp)
+{
+	if (mdp)
+		dpu_hw_blk_destroy(&mdp->base);
+	kfree(mdp);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
new file mode 100644
index 000000000000..899925aaa6d7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
@@ -0,0 +1,202 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_TOP_H
+#define _DPU_HW_TOP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_mdp;
+
+/**
+ * struct traffic_shaper_cfg: traffic shaper configuration
+ * @en        : enable/disable traffic shaper
+ * @rd_client : true if read client; false if write client
+ * @client_id : client identifier
+ * @bpc_denom : denominator of byte per clk
+ * @bpc_numer : numerator of byte per clk
+ */
+struct traffic_shaper_cfg {
+	bool en;
+	bool rd_client;
+	u32 client_id;
+	u32 bpc_denom;
+	u64 bpc_numer;
+};
+
+/**
+ * struct split_pipe_cfg - pipe configuration for dual display panels
+ * @en        : Enable/disable dual pipe confguration
+ * @mode      : Panel interface mode
+ * @intf      : Interface id for main control path
+ * @split_flush_en: Allows both the paths to be flushed when master path is
+ *              flushed
+ */
+struct split_pipe_cfg {
+	bool en;
+	enum dpu_intf_mode mode;
+	enum dpu_intf intf;
+	bool split_flush_en;
+};
+
+/**
+ * struct cdm_output_cfg: output configuration for cdm
+ * @intf_en   : enable/disable interface output
+ */
+struct cdm_output_cfg {
+	bool intf_en;
+};
+
+/**
+ * struct dpu_danger_safe_status: danger and safe status signals
+ * @mdp: top level status
+ * @sspp: source pipe status
+ */
+struct dpu_danger_safe_status {
+	u8 mdp;
+	u8 sspp[SSPP_MAX];
+};
+
+/**
+ * struct dpu_vsync_source_cfg - configure vsync source and configure the
+ *                                    watchdog timers if required.
+ * @pp_count: number of ping pongs active
+ * @frame_rate: Display frame rate
+ * @ppnumber: ping pong index array
+ * @vsync_source: vsync source selection
+ */
+struct dpu_vsync_source_cfg {
+	u32 pp_count;
+	u32 frame_rate;
+	u32 ppnumber[PINGPONG_MAX];
+	u32 vsync_source;
+};
+
+/**
+ * struct dpu_hw_mdp_ops - interface to the MDP TOP Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled.
+ * @setup_split_pipe : Programs the pipe control registers
+ * @setup_pp_split : Programs the pp split control registers
+ * @setup_cdm_output : programs cdm control
+ * @setup_traffic_shaper : programs traffic shaper control
+ */
+struct dpu_hw_mdp_ops {
+	/** setup_split_pipe() : Regsiters are not double buffered, thisk
+	 * function should be called before timing control enable
+	 * @mdp  : mdp top context driver
+	 * @cfg  : upper and lower part of pipe configuration
+	 */
+	void (*setup_split_pipe)(struct dpu_hw_mdp *mdp,
+			struct split_pipe_cfg *p);
+
+	/**
+	 * setup_cdm_output() : Setup selection control of the cdm data path
+	 * @mdp  : mdp top context driver
+	 * @cfg  : cdm output configuration
+	 */
+	void (*setup_cdm_output)(struct dpu_hw_mdp *mdp,
+			struct cdm_output_cfg *cfg);
+
+	/**
+	 * setup_traffic_shaper() : Setup traffic shaper control
+	 * @mdp  : mdp top context driver
+	 * @cfg  : traffic shaper configuration
+	 */
+	void (*setup_traffic_shaper)(struct dpu_hw_mdp *mdp,
+			struct traffic_shaper_cfg *cfg);
+
+	/**
+	 * setup_clk_force_ctrl - set clock force control
+	 * @mdp: mdp top context driver
+	 * @clk_ctrl: clock to be controlled
+	 * @enable: force on enable
+	 * @return: if the clock is forced-on by this function
+	 */
+	bool (*setup_clk_force_ctrl)(struct dpu_hw_mdp *mdp,
+			enum dpu_clk_ctrl_type clk_ctrl, bool enable);
+
+	/**
+	 * get_danger_status - get danger status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_danger_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * setup_vsync_source - setup vsync source configuration details
+	 * @mdp: mdp top context driver
+	 * @cfg: vsync source selection configuration
+	 */
+	void (*setup_vsync_source)(struct dpu_hw_mdp *mdp,
+				struct dpu_vsync_source_cfg *cfg);
+
+	/**
+	 * get_safe_status - get safe status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_safe_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * reset_ubwc - reset top level UBWC configuration
+	 * @mdp: mdp top context driver
+	 * @m: pointer to mdss catalog data
+	 */
+	void (*reset_ubwc)(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m);
+
+	/**
+	 * intf_audio_select - select the external interface for audio
+	 * @mdp: mdp top context driver
+	 */
+	void (*intf_audio_select)(struct dpu_hw_mdp *mdp);
+};
+
+struct dpu_hw_mdp {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* top */
+	enum dpu_mdp idx;
+	const struct dpu_mdp_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_mdp_ops ops;
+};
+
+/**
+ * to_dpu_hw_mdp - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mdp *to_dpu_hw_mdp(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mdp, base);
+}
+
+/**
+ * dpu_hw_mdptop_init - initializes the top driver for the passed idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp);
+
+#endif /*_DPU_HW_TOP_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
new file mode 100644
index 000000000000..4cabae480a7b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -0,0 +1,368 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+/* using a file static variables for debugfs access */
+static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE;
+
+/* DPU_SCALER_QSEED3 */
+#define QSEED3_HW_VERSION                  0x00
+#define QSEED3_OP_MODE                     0x04
+#define QSEED3_RGB2Y_COEFF                 0x08
+#define QSEED3_PHASE_INIT                  0x0C
+#define QSEED3_PHASE_STEP_Y_H              0x10
+#define QSEED3_PHASE_STEP_Y_V              0x14
+#define QSEED3_PHASE_STEP_UV_H             0x18
+#define QSEED3_PHASE_STEP_UV_V             0x1C
+#define QSEED3_PRELOAD                     0x20
+#define QSEED3_DE_SHARPEN                  0x24
+#define QSEED3_DE_SHARPEN_CTL              0x28
+#define QSEED3_DE_SHAPE_CTL                0x2C
+#define QSEED3_DE_THRESHOLD                0x30
+#define QSEED3_DE_ADJUST_DATA_0            0x34
+#define QSEED3_DE_ADJUST_DATA_1            0x38
+#define QSEED3_DE_ADJUST_DATA_2            0x3C
+#define QSEED3_SRC_SIZE_Y_RGB_A            0x40
+#define QSEED3_SRC_SIZE_UV                 0x44
+#define QSEED3_DST_SIZE                    0x48
+#define QSEED3_COEF_LUT_CTRL               0x4C
+#define QSEED3_COEF_LUT_SWAP_BIT           0
+#define QSEED3_COEF_LUT_DIR_BIT            1
+#define QSEED3_COEF_LUT_Y_CIR_BIT          2
+#define QSEED3_COEF_LUT_UV_CIR_BIT         3
+#define QSEED3_COEF_LUT_Y_SEP_BIT          4
+#define QSEED3_COEF_LUT_UV_SEP_BIT         5
+#define QSEED3_BUFFER_CTRL                 0x50
+#define QSEED3_CLK_CTRL0                   0x54
+#define QSEED3_CLK_CTRL1                   0x58
+#define QSEED3_CLK_STATUS                  0x5C
+#define QSEED3_MISR_CTRL                   0x70
+#define QSEED3_MISR_SIGNATURE_0            0x74
+#define QSEED3_MISR_SIGNATURE_1            0x78
+#define QSEED3_PHASE_INIT_Y_H              0x90
+#define QSEED3_PHASE_INIT_Y_V              0x94
+#define QSEED3_PHASE_INIT_UV_H             0x98
+#define QSEED3_PHASE_INIT_UV_V             0x9C
+#define QSEED3_COEF_LUT                    0x100
+#define QSEED3_FILTERS                     5
+#define QSEED3_LUT_REGIONS                 4
+#define QSEED3_CIRCULAR_LUTS               9
+#define QSEED3_SEPARABLE_LUTS              10
+#define QSEED3_LUT_SIZE                    60
+#define QSEED3_ENABLE                      2
+#define QSEED3_DIR_LUT_SIZE                (200 * sizeof(u32))
+#define QSEED3_CIR_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_CIRCULAR_LUTS * sizeof(u32))
+#define QSEED3_SEP_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32))
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name)
+{
+	/* don't need to mutex protect this */
+	if (c->log_mask & dpu_hw_util_log_mask)
+		DPU_DEBUG_DRIVER("[%s:0x%X] <= 0x%X\n",
+				name, c->blk_off + reg_off, val);
+	writel_relaxed(val, c->base_off + c->blk_off + reg_off);
+}
+
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off)
+{
+	return readl_relaxed(c->base_off + c->blk_off + reg_off);
+}
+
+u32 *dpu_hw_util_get_log_mask_ptr(void)
+{
+	return &dpu_hw_util_log_mask;
+}
+
+static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
+{
+	int i, j, filter;
+	int config_lut = 0x0;
+	unsigned long lut_flags;
+	u32 lut_addr, lut_offset, lut_len;
+	u32 *lut[QSEED3_FILTERS] = {NULL, NULL, NULL, NULL, NULL};
+	static const uint32_t off_tbl[QSEED3_FILTERS][QSEED3_LUT_REGIONS][2] = {
+		{{18, 0x000}, {12, 0x120}, {12, 0x1E0}, {8, 0x2A0} },
+		{{6, 0x320}, {3, 0x3E0}, {3, 0x440}, {3, 0x4A0} },
+		{{6, 0x500}, {3, 0x5c0}, {3, 0x620}, {3, 0x680} },
+		{{6, 0x380}, {3, 0x410}, {3, 0x470}, {3, 0x4d0} },
+		{{6, 0x560}, {3, 0x5f0}, {3, 0x650}, {3, 0x6b0} },
+	};
+
+	lut_flags = (unsigned long) scaler3_cfg->lut_flag;
+	if (test_bit(QSEED3_COEF_LUT_DIR_BIT, &lut_flags) &&
+		(scaler3_cfg->dir_len == QSEED3_DIR_LUT_SIZE)) {
+		lut[0] = scaler3_cfg->dir_lut;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[1] = scaler3_cfg->cir_lut +
+			scaler3_cfg->y_rgb_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[2] = scaler3_cfg->cir_lut +
+			scaler3_cfg->uv_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[3] = scaler3_cfg->sep_lut +
+			scaler3_cfg->y_rgb_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[4] = scaler3_cfg->sep_lut +
+			scaler3_cfg->uv_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+
+	if (config_lut) {
+		for (filter = 0; filter < QSEED3_FILTERS; filter++) {
+			if (!lut[filter])
+				continue;
+			lut_offset = 0;
+			for (i = 0; i < QSEED3_LUT_REGIONS; i++) {
+				lut_addr = QSEED3_COEF_LUT + offset
+					+ off_tbl[filter][i][1];
+				lut_len = off_tbl[filter][i][0] << 2;
+				for (j = 0; j < lut_len; j++) {
+					DPU_REG_WRITE(c,
+						lut_addr,
+						(lut[filter])[lut_offset++]);
+					lut_addr += 4;
+				}
+			}
+		}
+	}
+
+	if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags))
+		DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0));
+
+}
+
+static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset)
+{
+	u32 sharp_lvl, sharp_ctl, shape_ctl, de_thr;
+	u32 adjust_a, adjust_b, adjust_c;
+
+	if (!de_cfg->enable)
+		return;
+
+	sharp_lvl = (de_cfg->sharpen_level1 & 0x1FF) |
+		((de_cfg->sharpen_level2 & 0x1FF) << 16);
+
+	sharp_ctl = ((de_cfg->limit & 0xF) << 9) |
+		((de_cfg->prec_shift & 0x7) << 13) |
+		((de_cfg->clip & 0x7) << 16);
+
+	shape_ctl = (de_cfg->thr_quiet & 0xFF) |
+		((de_cfg->thr_dieout & 0x3FF) << 16);
+
+	de_thr = (de_cfg->thr_low & 0x3FF) |
+		((de_cfg->thr_high & 0x3FF) << 16);
+
+	adjust_a = (de_cfg->adjust_a[0] & 0x3FF) |
+		((de_cfg->adjust_a[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_a[2] & 0x3FF) << 20);
+
+	adjust_b = (de_cfg->adjust_b[0] & 0x3FF) |
+		((de_cfg->adjust_b[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_b[2] & 0x3FF) << 20);
+
+	adjust_c = (de_cfg->adjust_c[0] & 0x3FF) |
+		((de_cfg->adjust_c[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_c[2] & 0x3FF) << 20);
+
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN + offset, sharp_lvl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN_CTL + offset, sharp_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHAPE_CTL + offset, shape_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_THRESHOLD + offset, de_thr);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_0 + offset, adjust_a);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_1 + offset, adjust_b);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_2 + offset, adjust_c);
+
+}
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format)
+{
+	u32 op_mode = 0;
+	u32 phase_init, preload, src_y_rgb, src_uv, dst;
+
+	if (!scaler3_cfg->enable)
+		goto end;
+
+	op_mode |= BIT(0);
+	op_mode |= (scaler3_cfg->y_rgb_filter_cfg & 0x3) << 16;
+
+	if (format && DPU_FORMAT_IS_YUV(format)) {
+		op_mode |= BIT(12);
+		op_mode |= (scaler3_cfg->uv_filter_cfg & 0x3) << 24;
+	}
+
+	op_mode |= (scaler3_cfg->blend_cfg & 1) << 31;
+	op_mode |= (scaler3_cfg->dir_en) ? BIT(4) : 0;
+
+	preload =
+		((scaler3_cfg->preload_x[0] & 0x7F) << 0) |
+		((scaler3_cfg->preload_y[0] & 0x7F) << 8) |
+		((scaler3_cfg->preload_x[1] & 0x7F) << 16) |
+		((scaler3_cfg->preload_y[1] & 0x7F) << 24);
+
+	src_y_rgb = (scaler3_cfg->src_width[0] & 0x1FFFF) |
+		((scaler3_cfg->src_height[0] & 0x1FFFF) << 16);
+
+	src_uv = (scaler3_cfg->src_width[1] & 0x1FFFF) |
+		((scaler3_cfg->src_height[1] & 0x1FFFF) << 16);
+
+	dst = (scaler3_cfg->dst_width & 0x1FFFF) |
+		((scaler3_cfg->dst_height & 0x1FFFF) << 16);
+
+	if (scaler3_cfg->de.enable) {
+		_dpu_hw_setup_scaler3_de(c, &scaler3_cfg->de, scaler_offset);
+		op_mode |= BIT(8);
+	}
+
+	if (scaler3_cfg->lut_flag)
+		_dpu_hw_setup_scaler3_lut(c, scaler3_cfg,
+								scaler_offset);
+
+	if (scaler_version == 0x1002) {
+		phase_init =
+			((scaler3_cfg->init_phase_x[0] & 0x3F) << 0) |
+			((scaler3_cfg->init_phase_y[0] & 0x3F) << 8) |
+			((scaler3_cfg->init_phase_x[1] & 0x3F) << 16) |
+			((scaler3_cfg->init_phase_y[1] & 0x3F) << 24);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT + scaler_offset, phase_init);
+	} else {
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_H + scaler_offset,
+			scaler3_cfg->init_phase_x[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_V + scaler_offset,
+			scaler3_cfg->init_phase_y[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_H + scaler_offset,
+			scaler3_cfg->init_phase_x[1] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_V + scaler_offset,
+			scaler3_cfg->init_phase_y[1] & 0x1FFFFF);
+	}
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_H + scaler_offset,
+		scaler3_cfg->phase_step_x[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_V + scaler_offset,
+		scaler3_cfg->phase_step_y[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_H + scaler_offset,
+		scaler3_cfg->phase_step_x[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_V + scaler_offset,
+		scaler3_cfg->phase_step_y[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PRELOAD + scaler_offset, preload);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_Y_RGB_A + scaler_offset, src_y_rgb);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_UV + scaler_offset, src_uv);
+
+	DPU_REG_WRITE(c, QSEED3_DST_SIZE + scaler_offset, dst);
+
+end:
+	if (format && !DPU_FORMAT_IS_DX(format))
+		op_mode |= BIT(14);
+
+	if (format && format->alpha_enable) {
+		op_mode |= BIT(10);
+		if (scaler_version == 0x1002)
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x1) << 30;
+		else
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x3) << 29;
+	}
+
+	DPU_REG_WRITE(c, QSEED3_OP_MODE + scaler_offset, op_mode);
+}
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+			u32 scaler_offset)
+{
+	return DPU_REG_READ(c, QSEED3_HW_VERSION + scaler_offset);
+}
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c,
+		u32 csc_reg_off,
+		struct dpu_csc_cfg *data, bool csc10)
+{
+	static const u32 matrix_shift = 7;
+	u32 clamp_shift = csc10 ? 16 : 8;
+	u32 val;
+
+	/* matrix coeff - convert S15.16 to S4.9 */
+	val = ((data->csc_mv[0] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[1] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off, val);
+	val = ((data->csc_mv[2] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[3] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x4, val);
+	val = ((data->csc_mv[4] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[5] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x8, val);
+	val = ((data->csc_mv[6] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[7] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0xc, val);
+	val = (data->csc_mv[8] >> matrix_shift) & 0x1FFF;
+	DPU_REG_WRITE(c, csc_reg_off + 0x10, val);
+
+	/* Pre clamp */
+	val = (data->csc_pre_lv[0] << clamp_shift) | data->csc_pre_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x14, val);
+	val = (data->csc_pre_lv[2] << clamp_shift) | data->csc_pre_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x18, val);
+	val = (data->csc_pre_lv[4] << clamp_shift) | data->csc_pre_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x1c, val);
+
+	/* Post clamp */
+	val = (data->csc_post_lv[0] << clamp_shift) | data->csc_post_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x20, val);
+	val = (data->csc_post_lv[2] << clamp_shift) | data->csc_post_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x24, val);
+	val = (data->csc_post_lv[4] << clamp_shift) | data->csc_post_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x28, val);
+
+	/* Pre-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x2c, data->csc_pre_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x30, data->csc_pre_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x34, data->csc_pre_bv[2]);
+
+	/* Post-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x38, data->csc_post_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x3c, data->csc_post_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x40, data->csc_post_bv[2]);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
new file mode 100644
index 000000000000..1240f505ca53
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -0,0 +1,348 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_UTIL_H
+#define _DPU_HW_UTIL_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include "dpu_hw_mdss.h"
+
+#define REG_MASK(n)                     ((BIT(n)) - 1)
+struct dpu_format_extended;
+
+/*
+ * This is the common struct maintained by each sub block
+ * for mapping the register offsets in this block to the
+ * absoulute IO address
+ * @base_off:     mdp register mapped offset
+ * @blk_off:      pipe offset relative to mdss offset
+ * @length        length of register block offset
+ * @xin_id        xin id
+ * @hwversion     mdss hw version number
+ */
+struct dpu_hw_blk_reg_map {
+	void __iomem *base_off;
+	u32 blk_off;
+	u32 length;
+	u32 xin_id;
+	u32 hwversion;
+	u32 log_mask;
+};
+
+/**
+ * struct dpu_hw_scaler3_de_cfg : QSEEDv3 detail enhancer configuration
+ * @enable:         detail enhancer enable/disable
+ * @sharpen_level1: sharpening strength for noise
+ * @sharpen_level2: sharpening strength for signal
+ * @ clip:          clip shift
+ * @ limit:         limit value
+ * @ thr_quiet:     quiet threshold
+ * @ thr_dieout:    dieout threshold
+ * @ thr_high:      low threshold
+ * @ thr_high:      high threshold
+ * @ prec_shift:    precision shift
+ * @ adjust_a:      A-coefficients for mapping curve
+ * @ adjust_b:      B-coefficients for mapping curve
+ * @ adjust_c:      C-coefficients for mapping curve
+ */
+struct dpu_hw_scaler3_de_cfg {
+	u32 enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+
+/**
+ * struct dpu_hw_scaler3_cfg : QSEEDv3 configuration
+ * @enable:        scaler enable
+ * @dir_en:        direction detection block enable
+ * @ init_phase_x: horizontal initial phase
+ * @ phase_step_x: horizontal phase step
+ * @ init_phase_y: vertical initial phase
+ * @ phase_step_y: vertical phase step
+ * @ preload_x:    horizontal preload value
+ * @ preload_y:    vertical preload value
+ * @ src_width:    source width
+ * @ src_height:   source height
+ * @ dst_width:    destination width
+ * @ dst_height:   destination height
+ * @ y_rgb_filter_cfg: y/rgb plane filter configuration
+ * @ uv_filter_cfg: uv plane filter configuration
+ * @ alpha_filter_cfg: alpha filter configuration
+ * @ blend_cfg:    blend coefficients configuration
+ * @ lut_flag:     scaler LUT update flags
+ *                 0x1 swap LUT bank
+ *                 0x2 update 2D filter LUT
+ *                 0x4 update y circular filter LUT
+ *                 0x8 update uv circular filter LUT
+ *                 0x10 update y separable filter LUT
+ *                 0x20 update uv separable filter LUT
+ * @ dir_lut_idx:  2D filter LUT index
+ * @ y_rgb_cir_lut_idx: y circular filter LUT index
+ * @ uv_cir_lut_idx: uv circular filter LUT index
+ * @ y_rgb_sep_lut_idx: y circular filter LUT index
+ * @ uv_sep_lut_idx: uv separable filter LUT index
+ * @ dir_lut:      pointer to 2D LUT
+ * @ cir_lut:      pointer to circular filter LUT
+ * @ sep_lut:      pointer to separable filter LUT
+ * @ de: detail enhancer configuration
+ */
+struct dpu_hw_scaler3_cfg {
+	u32 enable;
+	u32 dir_en;
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	u32 preload_x[DPU_MAX_PLANES];
+	u32 preload_y[DPU_MAX_PLANES];
+	u32 src_width[DPU_MAX_PLANES];
+	u32 src_height[DPU_MAX_PLANES];
+
+	u32 dst_width;
+	u32 dst_height;
+
+	u32 y_rgb_filter_cfg;
+	u32 uv_filter_cfg;
+	u32 alpha_filter_cfg;
+	u32 blend_cfg;
+
+	u32 lut_flag;
+	u32 dir_lut_idx;
+
+	u32 y_rgb_cir_lut_idx;
+	u32 uv_cir_lut_idx;
+	u32 y_rgb_sep_lut_idx;
+	u32 uv_sep_lut_idx;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_hw_scaler3_de_cfg de;
+};
+
+struct dpu_hw_scaler3_lut_cfg {
+	bool is_configured;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+};
+
+/**
+ * struct dpu_drm_pix_ext_v1 - version 1 of pixel ext structure
+ * @num_ext_pxls_lr: Number of total horizontal pixels
+ * @num_ext_pxls_tb: Number of total vertical lines
+ * @left_ftch:       Number of extra pixels to overfetch from left
+ * @right_ftch:      Number of extra pixels to overfetch from right
+ * @top_ftch:        Number of extra lines to overfetch from top
+ * @btm_ftch:        Number of extra lines to overfetch from bottom
+ * @left_rpt:        Number of extra pixels to repeat from left
+ * @right_rpt:       Number of extra pixels to repeat from right
+ * @top_rpt:         Number of extra lines to repeat from top
+ * @btm_rpt:         Number of extra lines to repeat from bottom
+ */
+struct dpu_drm_pix_ext_v1 {
+	/*
+	 * Number of pixels ext in left, right, top and bottom direction
+	 * for all color components.
+	 */
+	int32_t num_ext_pxls_lr[DPU_MAX_PLANES];
+	int32_t num_ext_pxls_tb[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top
+	 * and bottom directions from source image for scaling.
+	 */
+	int32_t left_ftch[DPU_MAX_PLANES];
+	int32_t right_ftch[DPU_MAX_PLANES];
+	int32_t top_ftch[DPU_MAX_PLANES];
+	int32_t btm_ftch[DPU_MAX_PLANES];
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int32_t left_rpt[DPU_MAX_PLANES];
+	int32_t right_rpt[DPU_MAX_PLANES];
+	int32_t top_rpt[DPU_MAX_PLANES];
+	int32_t btm_rpt[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_drm_de_v1 - version 1 of detail enhancer structure
+ * @enable:         Enables/disables detail enhancer
+ * @sharpen_level1: Sharpening strength for noise
+ * @sharpen_level2: Sharpening strength for context
+ * @clip:           Clip coefficient
+ * @limit:          Detail enhancer limit factor
+ * @thr_quiet:      Quite zone threshold
+ * @thr_dieout:     Die-out zone threshold
+ * @thr_low:        Linear zone left threshold
+ * @thr_high:       Linear zone right threshold
+ * @prec_shift:     Detail enhancer precision
+ * @adjust_a:       Mapping curves A coefficients
+ * @adjust_b:       Mapping curves B coefficients
+ * @adjust_c:       Mapping curves C coefficients
+ */
+struct dpu_drm_de_v1 {
+	uint32_t enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+/**
+ * struct dpu_drm_scaler_v2 - version 2 of struct dpu_drm_scaler
+ * @enable:            Scaler enable
+ * @dir_en:            Detail enhancer enable
+ * @pe:                Pixel extension settings
+ * @horz_decimate:     Horizontal decimation factor
+ * @vert_decimate:     Vertical decimation factor
+ * @init_phase_x:      Initial scaler phase values for x
+ * @phase_step_x:      Phase step values for x
+ * @init_phase_y:      Initial scaler phase values for y
+ * @phase_step_y:      Phase step values for y
+ * @preload_x:         Horizontal preload value
+ * @preload_y:         Vertical preload value
+ * @src_width:         Source width
+ * @src_height:        Source height
+ * @dst_width:         Destination width
+ * @dst_height:        Destination height
+ * @y_rgb_filter_cfg:  Y/RGB plane filter configuration
+ * @uv_filter_cfg:     UV plane filter configuration
+ * @alpha_filter_cfg:  Alpha filter configuration
+ * @blend_cfg:         Selection of blend coefficients
+ * @lut_flag:          LUT configuration flags
+ * @dir_lut_idx:       2d 4x4 LUT index
+ * @y_rgb_cir_lut_idx: Y/RGB circular LUT index
+ * @uv_cir_lut_idx:    UV circular LUT index
+ * @y_rgb_sep_lut_idx: Y/RGB separable LUT index
+ * @uv_sep_lut_idx:    UV separable LUT index
+ * @de:                Detail enhancer settings
+ */
+struct dpu_drm_scaler_v2 {
+	/*
+	 * General definitions
+	 */
+	uint32_t enable;
+	uint32_t dir_en;
+
+	/*
+	 * Pix ext settings
+	 */
+	struct dpu_drm_pix_ext_v1 pe;
+
+	/*
+	 * Decimation settings
+	 */
+	uint32_t horz_decimate;
+	uint32_t vert_decimate;
+
+	/*
+	 * Phase settings
+	 */
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	uint32_t preload_x[DPU_MAX_PLANES];
+	uint32_t preload_y[DPU_MAX_PLANES];
+	uint32_t src_width[DPU_MAX_PLANES];
+	uint32_t src_height[DPU_MAX_PLANES];
+
+	uint32_t dst_width;
+	uint32_t dst_height;
+
+	uint32_t y_rgb_filter_cfg;
+	uint32_t uv_filter_cfg;
+	uint32_t alpha_filter_cfg;
+	uint32_t blend_cfg;
+
+	uint32_t lut_flag;
+	uint32_t dir_lut_idx;
+
+	/* for Y(RGB) and UV planes*/
+	uint32_t y_rgb_cir_lut_idx;
+	uint32_t uv_cir_lut_idx;
+	uint32_t y_rgb_sep_lut_idx;
+	uint32_t uv_sep_lut_idx;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_drm_de_v1 de;
+};
+
+
+u32 *dpu_hw_util_get_log_mask_ptr(void);
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name);
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off);
+
+#define DPU_REG_WRITE(c, off, val) dpu_reg_write(c, off, val, #off)
+#define DPU_REG_READ(c, off) dpu_reg_read(c, off)
+
+#define MISR_FRAME_COUNT_MASK		0xFF
+#define MISR_CTRL_ENABLE		BIT(8)
+#define MISR_CTRL_STATUS		BIT(9)
+#define MISR_CTRL_STATUS_CLEAR		BIT(10)
+#define INTF_MISR_CTRL_FREE_RUN_MASK	BIT(31)
+
+void *dpu_hw_util_get_dir(void);
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format);
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+		u32 scaler_offset);
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map  *c,
+		u32 csc_reg_off,
+		struct dpu_csc_cfg *data, bool csc10);
+
+#endif /* _DPU_HW_UTIL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
new file mode 100644
index 000000000000..d43905525f92
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
@@ -0,0 +1,275 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_dbg.h"
+
+#define VBIF_VERSION			0x0000
+#define VBIF_CLK_FORCE_CTRL0		0x0008
+#define VBIF_CLK_FORCE_CTRL1		0x000C
+#define VBIF_QOS_REMAP_00		0x0020
+#define VBIF_QOS_REMAP_01		0x0024
+#define VBIF_QOS_REMAP_10		0x0028
+#define VBIF_QOS_REMAP_11		0x002C
+#define VBIF_WRITE_GATHER_EN		0x00AC
+#define VBIF_IN_RD_LIM_CONF0		0x00B0
+#define VBIF_IN_RD_LIM_CONF1		0x00B4
+#define VBIF_IN_RD_LIM_CONF2		0x00B8
+#define VBIF_IN_WR_LIM_CONF0		0x00C0
+#define VBIF_IN_WR_LIM_CONF1		0x00C4
+#define VBIF_IN_WR_LIM_CONF2		0x00C8
+#define VBIF_OUT_RD_LIM_CONF0		0x00D0
+#define VBIF_OUT_WR_LIM_CONF0		0x00D4
+#define VBIF_OUT_AXI_AMEMTYPE_CONF0	0x0160
+#define VBIF_OUT_AXI_AMEMTYPE_CONF1	0x0164
+#define VBIF_XIN_PND_ERR		0x0190
+#define VBIF_XIN_SRC_ERR		0x0194
+#define VBIF_XIN_CLR_ERR		0x019C
+#define VBIF_XIN_HALT_CTRL0		0x0200
+#define VBIF_XIN_HALT_CTRL1		0x0204
+#define VBIF_XINL_QOS_RP_REMAP_000	0x0550
+#define VBIF_XINL_QOS_LVL_REMAP_000	0x0590
+
+static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 pnd, src;
+
+	if (!vbif)
+		return;
+	c = &vbif->hw;
+	pnd = DPU_REG_READ(c, VBIF_XIN_PND_ERR);
+	src = DPU_REG_READ(c, VBIF_XIN_SRC_ERR);
+
+	if (pnd_errors)
+		*pnd_errors = pnd;
+	if (src_errors)
+		*src_errors = src;
+
+	DPU_REG_WRITE(c, VBIF_XIN_CLR_ERR, pnd | src);
+}
+
+static void dpu_hw_set_mem_type(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 value)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off;
+	u32 bit_off;
+	u32 reg_val;
+
+	/*
+	 * Assume 4 bits per bit field, 8 fields per 32-bit register so
+	 * 16 bit fields maximum across two registers
+	 */
+	if (!vbif || xin_id >= MAX_XIN_COUNT || xin_id >= 16)
+		return;
+
+	c = &vbif->hw;
+
+	if (xin_id >= 8) {
+		xin_id -= 8;
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF1;
+	} else {
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF0;
+	}
+	bit_off = (xin_id & 0x7) * 4;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0x7 << bit_off);
+	reg_val |= (value & 0x7) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static void dpu_hw_set_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd, u32 limit)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0xFF << bit_off);
+	reg_val |= (limit) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static u32 dpu_hw_get_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+	u32 limit;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	limit = (reg_val >> bit_off) & 0xFF;
+
+	return limit;
+}
+
+static void dpu_hw_set_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL0);
+
+	if (enable)
+		reg_val |= BIT(xin_id);
+	else
+		reg_val &= ~BIT(xin_id);
+
+	DPU_REG_WRITE(c, VBIF_XIN_HALT_CTRL0, reg_val);
+}
+
+static bool dpu_hw_get_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL1);
+
+	return (reg_val & BIT(xin_id)) ? true : false;
+}
+
+static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 level, u32 remap_level)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val, reg_val_lvl, mask, reg_high, reg_shift;
+
+	if (!vbif)
+		return;
+
+	c = &vbif->hw;
+
+	reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8);
+	reg_shift = (xin_id & 0x7) * 4;
+
+	reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high);
+	reg_val_lvl = DPU_REG_READ(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high);
+
+	mask = 0x7 << reg_shift;
+
+	reg_val &= ~mask;
+	reg_val |= (remap_level << reg_shift) & mask;
+
+	reg_val_lvl &= ~mask;
+	reg_val_lvl |= (remap_level << reg_shift) & mask;
+
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val);
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high, reg_val_lvl);
+}
+
+static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val;
+
+	if (!vbif || xin_id >= MAX_XIN_COUNT)
+		return;
+
+	c = &vbif->hw;
+
+	reg_val = DPU_REG_READ(c, VBIF_WRITE_GATHER_EN);
+	reg_val |= BIT(xin_id);
+	DPU_REG_WRITE(c, VBIF_WRITE_GATHER_EN, reg_val);
+}
+
+static void _setup_vbif_ops(struct dpu_hw_vbif_ops *ops,
+		unsigned long cap)
+{
+	ops->set_limit_conf = dpu_hw_set_limit_conf;
+	ops->get_limit_conf = dpu_hw_get_limit_conf;
+	ops->set_halt_ctrl = dpu_hw_set_halt_ctrl;
+	ops->get_halt_ctrl = dpu_hw_get_halt_ctrl;
+	if (test_bit(DPU_VBIF_QOS_REMAP, &cap))
+		ops->set_qos_remap = dpu_hw_set_qos_remap;
+	ops->set_mem_type = dpu_hw_set_mem_type;
+	ops->clear_errors = dpu_hw_clear_errors;
+	ops->set_write_gather_en = dpu_hw_set_write_gather_en;
+}
+
+static const struct dpu_vbif_cfg *_top_offset(enum dpu_vbif vbif,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->vbif_count; i++) {
+		if (vbif == m->vbif[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->vbif[i].base;
+			b->length = m->vbif[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_VBIF;
+			return &m->vbif[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_vbif *c;
+	const struct dpu_vbif_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_vbif_ops(&c->ops, c->cap->features);
+
+	/* no need to register sub-range in dpu dbg, dump entire vbif io base */
+
+	return c;
+}
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif)
+{
+	kfree(vbif);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
new file mode 100644
index 000000000000..471ff673c045
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
@@ -0,0 +1,128 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_VBIF_H
+#define _DPU_HW_VBIF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_vbif;
+
+/**
+ * struct dpu_hw_vbif_ops : Interface to the VBIF hardware driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_vbif_ops {
+	/**
+	 * set_limit_conf - set transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @limit: outstanding transaction limit
+	 */
+	void (*set_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd, u32 limit);
+
+	/**
+	 * get_limit_conf - get transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @return: outstanding transaction limit
+	 */
+	u32 (*get_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd);
+
+	/**
+	 * set_halt_ctrl - set halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @enable: halt control enable
+	 */
+	void (*set_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool enable);
+
+	/**
+	 * get_halt_ctrl - get halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @return: halt control enable
+	 */
+	bool (*get_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id);
+
+	/**
+	 * set_qos_remap - set QoS priority remap
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @level: priority level
+	 * @remap_level: remapped level
+	 */
+	void (*set_qos_remap)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 level, u32 remap_level);
+
+	/**
+	 * set_mem_type - set memory type
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @value: memory type value
+	 */
+	void (*set_mem_type)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 value);
+
+	/**
+	 * clear_errors - clear any vbif errors
+	 *	This function clears any detected pending/source errors
+	 *	on the VBIF interface, and optionally returns the detected
+	 *	error mask(s).
+	 * @vbif: vbif context driver
+	 * @pnd_errors: pointer to pending error reporting variable
+	 * @src_errors: pointer to source error reporting variable
+	 */
+	void (*clear_errors)(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors);
+
+	/**
+	 * set_write_gather_en - set write_gather enable
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 */
+	void (*set_write_gather_en)(struct dpu_hw_vbif *vbif, u32 xin_id);
+};
+
+struct dpu_hw_vbif {
+	/* base */
+	struct dpu_hw_blk_reg_map hw;
+
+	/* vbif */
+	enum dpu_vbif idx;
+	const struct dpu_vbif_cfg *cap;
+
+	/* ops */
+	struct dpu_hw_vbif_ops ops;
+};
+
+/**
+ * dpu_hw_vbif_init - initializes the vbif driver for the passed interface idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDSS
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif);
+
+#endif /*_DPU_HW_VBIF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
new file mode 100644
index 000000000000..5b2bc9b65b15
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
@@ -0,0 +1,56 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HWIO_H
+#define _DPU_HWIO_H
+
+#include "dpu_hw_util.h"
+
+/**
+ * MDP TOP block Register and bit fields and defines
+ */
+#define DISP_INTF_SEL                   0x004
+#define INTR_EN                         0x010
+#define INTR_STATUS                     0x014
+#define INTR_CLEAR                      0x018
+#define INTR2_EN                        0x008
+#define INTR2_STATUS                    0x00c
+#define INTR2_CLEAR                     0x02c
+#define HIST_INTR_EN                    0x01c
+#define HIST_INTR_STATUS                0x020
+#define HIST_INTR_CLEAR                 0x024
+#define INTF_INTR_EN                    0x1C0
+#define INTF_INTR_STATUS                0x1C4
+#define INTF_INTR_CLEAR                 0x1C8
+#define SPLIT_DISPLAY_EN                0x2F4
+#define SPLIT_DISPLAY_UPPER_PIPE_CTRL   0x2F8
+#define DSPP_IGC_COLOR0_RAM_LUTN        0x300
+#define DSPP_IGC_COLOR1_RAM_LUTN        0x304
+#define DSPP_IGC_COLOR2_RAM_LUTN        0x308
+#define HW_EVENTS_CTL                   0x37C
+#define CLK_CTRL3                       0x3A8
+#define CLK_STATUS3                     0x3AC
+#define CLK_CTRL4                       0x3B0
+#define CLK_STATUS4                     0x3B4
+#define CLK_CTRL5                       0x3B8
+#define CLK_STATUS5                     0x3BC
+#define CLK_CTRL7                       0x3D0
+#define CLK_STATUS7                     0x3D4
+#define SPLIT_DISPLAY_LOWER_PIPE_CTRL   0x3F0
+#define SPLIT_DISPLAY_TE_LINE_INTERVAL  0x3F4
+#define INTF_SW_RESET_MASK              0x3FC
+#define HDMI_DP_CORE_SELECT             0x408
+#define MDP_OUT_CTL_0                   0x410
+#define MDP_VSYNC_SEL                   0x414
+#define DCE_SEL                         0x450
+
+#endif /*_DPU_HWIO_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
new file mode 100644
index 000000000000..790d39f816dc
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -0,0 +1,203 @@
+/* Copyright (c) 2012-2015, 2017-2018, The Linux Foundation.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk/clk-conf.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+
+#include "dpu_io_util.h"
+
+void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk)
+{
+	int i;
+
+	for (i = num_clk - 1; i >= 0; i--) {
+		if (clk_arry[i].clk)
+			clk_put(clk_arry[i].clk);
+		clk_arry[i].clk = NULL;
+	}
+}
+
+int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < num_clk; i++) {
+		clk_arry[i].clk = clk_get(dev, clk_arry[i].clk_name);
+		rc = PTR_ERR_OR_ZERO(clk_arry[i].clk);
+		if (rc) {
+			DEV_ERR("%pS->%s: '%s' get failed. rc=%d\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name, rc);
+			goto error;
+		}
+	}
+
+	return rc;
+
+error:
+	for (i--; i >= 0; i--) {
+		if (clk_arry[i].clk)
+			clk_put(clk_arry[i].clk);
+		clk_arry[i].clk = NULL;
+	}
+
+	return rc;
+}
+
+int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < num_clk; i++) {
+		if (clk_arry[i].clk) {
+			if (clk_arry[i].type != DSS_CLK_AHB) {
+				DEV_DBG("%pS->%s: '%s' rate %ld\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name,
+					clk_arry[i].rate);
+				rc = clk_set_rate(clk_arry[i].clk,
+					clk_arry[i].rate);
+				if (rc) {
+					DEV_ERR("%pS->%s: %s failed. rc=%d\n",
+						__builtin_return_address(0),
+						__func__,
+						clk_arry[i].clk_name, rc);
+					break;
+				}
+			}
+		} else {
+			DEV_ERR("%pS->%s: '%s' is not available\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+			rc = -EPERM;
+			break;
+		}
+	}
+
+	return rc;
+}
+
+int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
+{
+	int i, rc = 0;
+
+	if (enable) {
+		for (i = 0; i < num_clk; i++) {
+			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;
+			}
+
+			if (rc) {
+				msm_dss_enable_clk(&clk_arry[i],
+					i, false);
+				break;
+			}
+		}
+	} else {
+		for (i = num_clk - 1; i >= 0; i--) {
+			DEV_DBG("%pS->%s: disable '%s'\n",
+				__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);
+		}
+	}
+
+	return rc;
+}
+
+int msm_dss_parse_clock(struct platform_device *pdev,
+			struct dss_module_power *mp)
+{
+	u32 i, rc = 0;
+	const char *clock_name;
+	int num_clk = 0;
+
+	if (!pdev || !mp)
+		return -EINVAL;
+
+	mp->num_clk = 0;
+	num_clk = of_property_count_strings(pdev->dev.of_node, "clock-names");
+	if (num_clk <= 0) {
+		pr_debug("clocks are not defined\n");
+		return 0;
+	}
+
+	mp->clk_config = devm_kzalloc(&pdev->dev,
+				      sizeof(struct dss_clk) * num_clk,
+				      GFP_KERNEL);
+	if (!mp->clk_config)
+		return -ENOMEM;
+
+	for (i = 0; i < num_clk; i++) {
+		rc = of_property_read_string_index(pdev->dev.of_node,
+						   "clock-names", i,
+						   &clock_name);
+		if (rc) {
+			dev_err(&pdev->dev, "Failed to get clock name for %d\n",
+				i);
+			break;
+		}
+		strlcpy(mp->clk_config[i].clk_name, clock_name,
+			sizeof(mp->clk_config[i].clk_name));
+
+		mp->clk_config[i].type = DSS_CLK_AHB;
+	}
+
+	rc = msm_dss_get_clk(&pdev->dev, mp->clk_config, num_clk);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to get clock refs %d\n", rc);
+		goto err;
+	}
+
+	rc = of_clk_set_defaults(pdev->dev.of_node, false);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to set clock defaults %d\n", rc);
+		goto err;
+	}
+
+	for (i = 0; i < num_clk; i++) {
+		u32 rate = clk_get_rate(mp->clk_config[i].clk);
+		if (!rate)
+			continue;
+		mp->clk_config[i].rate = rate;
+		mp->clk_config[i].type = DSS_CLK_PCLK;
+	}
+
+	mp->num_clk = num_clk;
+	return 0;
+
+err:
+	msm_dss_put_clk(mp->clk_config, num_clk);
+	return rc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
new file mode 100644
index 000000000000..bc07381d7429
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
@@ -0,0 +1,57 @@
+/* Copyright (c) 2012, 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_IO_UTIL_H__
+#define __DPU_IO_UTIL_H__
+
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#define DEV_DBG(fmt, args...)   pr_debug(fmt, ##args)
+#define DEV_INFO(fmt, args...)  pr_info(fmt, ##args)
+#define DEV_WARN(fmt, args...)  pr_warn(fmt, ##args)
+#define DEV_ERR(fmt, args...)   pr_err(fmt, ##args)
+
+struct dss_gpio {
+	unsigned int gpio;
+	unsigned int value;
+	char gpio_name[32];
+};
+
+enum dss_clk_type {
+	DSS_CLK_AHB, /* no set rate. rate controlled through rpm */
+	DSS_CLK_PCLK,
+};
+
+struct dss_clk {
+	struct clk *clk; /* clk handle */
+	char clk_name[32];
+	enum dss_clk_type type;
+	unsigned long rate;
+	unsigned long max_rate;
+};
+
+struct dss_module_power {
+	unsigned int num_gpio;
+	struct dss_gpio *gpio_config;
+	unsigned int num_clk;
+	struct dss_clk *clk_config;
+};
+
+int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk);
+void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk);
+int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk);
+int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable);
+int msm_dss_parse_clock(struct platform_device *pdev,
+		struct dss_module_power *mp);
+#endif /* __DPU_IO_UTIL_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
new file mode 100644
index 000000000000..d5e6ce0140cf
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
@@ -0,0 +1,66 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include "dpu_irq.h"
+#include "dpu_core_irq.h"
+
+irqreturn_t dpu_irq(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	return dpu_core_irq(dpu_kms);
+}
+
+void dpu_irq_preinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	if (!dpu_kms->dev || !dpu_kms->dev->dev) {
+		pr_err("invalid device handles\n");
+		return;
+	}
+
+	dpu_core_irq_preinstall(dpu_kms);
+}
+
+int dpu_irq_postinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	int rc;
+
+	if (!kms) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	rc = dpu_core_irq_postinstall(dpu_kms);
+
+	return rc;
+}
+
+void dpu_irq_uninstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	if (!kms) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_core_irq_uninstall(dpu_kms);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
new file mode 100644
index 000000000000..3e147f7176e2
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
@@ -0,0 +1,59 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_IRQ_H__
+#define __DPU_IRQ_H__
+
+#include <linux/kernel.h>
+#include <linux/irqdomain.h>
+
+#include "msm_kms.h"
+
+/**
+ * dpu_irq_controller - define MDSS level interrupt controller context
+ * @enabled_mask:	enable status of MDSS level interrupt
+ * @domain:		interrupt domain of this controller
+ */
+struct dpu_irq_controller {
+	unsigned long enabled_mask;
+	struct irq_domain *domain;
+};
+
+/**
+ * dpu_irq_preinstall - perform pre-installation of MDSS IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		none
+ */
+void dpu_irq_preinstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq_postinstall - perform post-installation of MDSS IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		0 if success; error code otherwise
+ */
+int dpu_irq_postinstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq_uninstall - uninstall MDSS IRQ handler
+ * @drm_dev:		pointer to kms context
+ * @return:		none
+ */
+void dpu_irq_uninstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq - MDSS level IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_irq(struct msm_kms *kms);
+
+#endif /* __DPU_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
new file mode 100644
index 000000000000..7dd6bd2d6d37
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -0,0 +1,1345 @@
+/*
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <drm/drm_crtc.h>
+#include <linux/debugfs.h>
+#include <linux/of_irq.h>
+#include <linux/dma-buf.h>
+
+#include "msm_drv.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+
+#include "dpu_kms.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_vbif.h"
+#include "dpu_encoder.h"
+#include "dpu_plane.h"
+#include "dpu_crtc.h"
+
+#define CREATE_TRACE_POINTS
+#include "dpu_trace.h"
+
+static const char * const iommu_ports[] = {
+		"mdp_0",
+};
+
+/*
+ * To enable overall DRM driver logging
+ * # echo 0x2 > /sys/module/drm/parameters/debug
+ *
+ * To enable DRM driver h/w logging
+ * # echo <mask> > /sys/kernel/debug/dri/0/debug/hw_log_mask
+ *
+ * See dpu_hw_mdss.h for h/w logging mask definitions (search for DPU_DBG_MASK_)
+ */
+#define DPU_DEBUGFS_DIR "msm_dpu"
+#define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
+
+static int dpu_kms_hw_init(struct msm_kms *kms);
+static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
+
+static unsigned long dpu_iomap_size(struct platform_device *pdev,
+				    const char *name)
+{
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+	if (!res) {
+		DRM_ERROR("failed to get memory resource: %s\n", name);
+		return 0;
+	}
+
+	return resource_size(res);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_danger_signal_status(struct seq_file *s,
+		bool danger_status)
+{
+	struct dpu_kms *kms = (struct dpu_kms *)s->private;
+	struct msm_drm_private *priv;
+	struct dpu_danger_safe_status status;
+	int i;
+
+	if (!kms || !kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+		DPU_ERROR("invalid arg(s)\n");
+		return 0;
+	}
+
+	priv = kms->dev->dev_private;
+	memset(&status, 0, sizeof(struct dpu_danger_safe_status));
+
+	pm_runtime_get_sync(&kms->pdev->dev);
+	if (danger_status) {
+		seq_puts(s, "\nDanger signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	} else {
+		seq_puts(s, "\nSafe signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	}
+	pm_runtime_put_sync(&kms->pdev->dev);
+
+	seq_printf(s, "MDP     :  0x%x\n", status.mdp);
+
+	for (i = SSPP_VIG0; i < SSPP_MAX; i++)
+		seq_printf(s, "SSPP%d   :  0x%x  \t", i - SSPP_VIG0,
+				status.sspp[i]);
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)				\
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_debugfs_danger_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, true);
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_danger_stats);
+
+static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, false);
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_safe_stats);
+
+static void dpu_debugfs_danger_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove_recursive(dpu_kms->debugfs_danger);
+	dpu_kms->debugfs_danger = NULL;
+}
+
+static int dpu_debugfs_danger_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	dpu_kms->debugfs_danger = debugfs_create_dir("danger",
+			parent);
+	if (!dpu_kms->debugfs_danger) {
+		DPU_ERROR("failed to create danger debugfs\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_file("danger_status", 0600, dpu_kms->debugfs_danger,
+			dpu_kms, &dpu_debugfs_danger_stats_fops);
+	debugfs_create_file("safe_status", 0600, dpu_kms->debugfs_danger,
+			dpu_kms, &dpu_debugfs_safe_stats_fops);
+
+	return 0;
+}
+
+static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
+{
+	struct dpu_debugfs_regset32 *regset;
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	void __iomem *base;
+	uint32_t i, addr;
+
+	if (!s || !s->private)
+		return 0;
+
+	regset = s->private;
+
+	dpu_kms = regset->dpu_kms;
+	if (!dpu_kms || !dpu_kms->mmio)
+		return 0;
+
+	dev = dpu_kms->dev;
+	if (!dev)
+		return 0;
+
+	priv = dev->dev_private;
+	if (!priv)
+		return 0;
+
+	base = dpu_kms->mmio + regset->offset;
+
+	/* insert padding spaces, if needed */
+	if (regset->offset & 0xF) {
+		seq_printf(s, "[%x]", regset->offset & ~0xF);
+		for (i = 0; i < (regset->offset & 0xF); i += 4)
+			seq_puts(s, "         ");
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	/* main register output */
+	for (i = 0; i < regset->blk_len; i += 4) {
+		addr = regset->offset + i;
+		if ((addr & 0xF) == 0x0)
+			seq_printf(s, i ? "\n[%x]" : "[%x]", addr);
+		seq_printf(s, " %08x", readl_relaxed(base + i));
+	}
+	seq_puts(s, "\n");
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+static int dpu_debugfs_open_regset32(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_debugfs_show_regset32, inode->i_private);
+}
+
+static const struct file_operations dpu_fops_regset32 = {
+	.open =		dpu_debugfs_open_regset32,
+	.read =		seq_read,
+	.llseek =	seq_lseek,
+	.release =	single_release,
+};
+
+void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms)
+{
+	if (regset) {
+		regset->offset = offset;
+		regset->blk_len = length;
+		regset->dpu_kms = dpu_kms;
+	}
+}
+
+void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent, struct dpu_debugfs_regset32 *regset)
+{
+	if (!name || !regset || !regset->dpu_kms || !regset->blk_len)
+		return NULL;
+
+	/* make sure offset is a multiple of 4 */
+	regset->offset = round_down(regset->offset, 4);
+
+	return debugfs_create_file(name, mode, parent,
+			regset, &dpu_fops_regset32);
+}
+
+static int _dpu_debugfs_init(struct dpu_kms *dpu_kms)
+{
+	void *p;
+	int rc;
+
+	p = dpu_hw_util_get_log_mask_ptr();
+
+	if (!dpu_kms || !p)
+		return -EINVAL;
+
+	dpu_kms->debugfs_root = debugfs_create_dir("debug",
+					   dpu_kms->dev->primary->debugfs_root);
+	if (IS_ERR_OR_NULL(dpu_kms->debugfs_root)) {
+		DRM_ERROR("debugfs create_dir failed %ld\n",
+			  PTR_ERR(dpu_kms->debugfs_root));
+		return PTR_ERR(dpu_kms->debugfs_root);
+	}
+
+	rc = dpu_dbg_debugfs_register(dpu_kms->debugfs_root);
+	if (rc) {
+		DRM_ERROR("failed to reg dpu dbg debugfs: %d\n", rc);
+		return rc;
+	}
+
+	/* allow root to be NULL */
+	debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, dpu_kms->debugfs_root, p);
+
+	(void) dpu_debugfs_danger_init(dpu_kms, dpu_kms->debugfs_root);
+	(void) dpu_debugfs_vbif_init(dpu_kms, dpu_kms->debugfs_root);
+	(void) dpu_debugfs_core_irq_init(dpu_kms, dpu_kms->debugfs_root);
+
+	rc = dpu_core_perf_debugfs_init(&dpu_kms->perf, dpu_kms->debugfs_root);
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
+{
+	/* don't need to NULL check debugfs_root */
+	if (dpu_kms) {
+		dpu_debugfs_vbif_destroy(dpu_kms);
+		dpu_debugfs_danger_destroy(dpu_kms);
+		dpu_debugfs_core_irq_destroy(dpu_kms);
+		debugfs_remove_recursive(dpu_kms->debugfs_root);
+	}
+}
+#else
+static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+
+static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	return dpu_crtc_vblank(crtc, true);
+}
+
+static void dpu_kms_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	dpu_crtc_vblank(crtc, false);
+}
+
+static void dpu_kms_prepare_commit(struct msm_kms *kms,
+		struct drm_atomic_state *state)
+{
+	struct dpu_kms *dpu_kms;
+	struct msm_drm_private *priv;
+	struct drm_device *dev;
+	struct drm_encoder *encoder;
+
+	if (!kms)
+		return;
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+
+	if (!dev || !dev->dev_private)
+		return;
+	priv = dev->dev_private;
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
+		if (encoder->crtc != NULL)
+			dpu_encoder_prepare_commit(encoder);
+}
+
+/*
+ * Override the encoder enable since we need to setup the inline rotator and do
+ * some crtc magic before enabling any bridge that might be present.
+ */
+void dpu_kms_encoder_enable(struct drm_encoder *encoder)
+{
+	const struct drm_encoder_helper_funcs *funcs = encoder->helper_private;
+	struct drm_crtc *crtc = encoder->crtc;
+
+	/* Forward this enable call to the commit hook */
+	if (funcs && funcs->commit)
+		funcs->commit(encoder);
+
+	if (crtc && crtc->state->active) {
+		trace_dpu_kms_enc_enable(DRMID(crtc));
+		dpu_crtc_commit_kickoff(crtc);
+	}
+}
+
+static void dpu_kms_commit(struct msm_kms *kms, struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	int i;
+
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		/* If modeset is required, kickoff is run in encoder_enable */
+		if (drm_atomic_crtc_needs_modeset(crtc_state))
+			continue;
+
+		if (crtc->state->active) {
+			trace_dpu_kms_commit(DRMID(crtc));
+			dpu_crtc_commit_kickoff(crtc);
+		}
+	}
+}
+
+static void dpu_kms_complete_commit(struct msm_kms *kms,
+		struct drm_atomic_state *old_state)
+{
+	struct dpu_kms *dpu_kms;
+	struct msm_drm_private *priv;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state;
+	int i;
+
+	if (!kms || !old_state)
+		return;
+	dpu_kms = to_dpu_kms(kms);
+
+	if (!dpu_kms->dev || !dpu_kms->dev->dev_private)
+		return;
+	priv = dpu_kms->dev->dev_private;
+
+	DPU_ATRACE_BEGIN("kms_complete_commit");
+
+	for_each_old_crtc_in_state(old_state, crtc, old_crtc_state, i)
+		dpu_crtc_complete_commit(crtc, old_crtc_state);
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	DPU_ATRACE_END("kms_complete_commit");
+}
+
+static void dpu_kms_wait_for_commit_done(struct msm_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	int ret;
+
+	if (!kms || !crtc || !crtc->state) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	dev = crtc->dev;
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("[crtc:%d] not enable\n", crtc->base.id);
+		return;
+	}
+
+	if (!crtc->state->active) {
+		DPU_DEBUG("[crtc:%d] not active\n", crtc->base.id);
+		return;
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+		/*
+		 * Wait for post-flush if necessary to delay before
+		 * plane_cleanup. For example, wait for vsync in case of video
+		 * mode panels. This may be a no-op for command mode panels.
+		 */
+		trace_dpu_kms_wait_for_commit_done(DRMID(crtc));
+		ret = dpu_encoder_wait_for_event(encoder, MSM_ENC_COMMIT_DONE);
+		if (ret && ret != -EWOULDBLOCK) {
+			DPU_ERROR("wait for commit done returned %d\n", ret);
+			break;
+		}
+	}
+}
+
+static void _dpu_kms_initialize_dsi(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	struct drm_encoder *encoder = NULL;
+	int i, rc;
+
+	/*TODO: Support two independent DSI connectors */
+	encoder = dpu_encoder_init(dev, DRM_MODE_CONNECTOR_DSI);
+	if (IS_ERR_OR_NULL(encoder)) {
+		DPU_ERROR("encoder init failed for dsi display\n");
+		return;
+	}
+
+	priv->encoders[priv->num_encoders++] = encoder;
+
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		if (!priv->dsi[i]) {
+			DPU_DEBUG("invalid msm_dsi for ctrl %d\n", i);
+			return;
+		}
+
+		rc = msm_dsi_modeset_init(priv->dsi[i], dev, encoder);
+		if (rc) {
+			DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
+				i, rc);
+			continue;
+		}
+	}
+}
+
+/**
+ * _dpu_kms_setup_displays - create encoders, bridges and connectors
+ *                           for underlying displays
+ * @dev:        Pointer to drm device structure
+ * @priv:       Pointer to private drm device data
+ * @dpu_kms:    Pointer to dpu kms structure
+ * Returns:     Zero on success
+ */
+static void _dpu_kms_setup_displays(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	_dpu_kms_initialize_dsi(dev, priv, dpu_kms);
+
+	/**
+	 * Extend this function to initialize other
+	 * types of displays
+	 */
+}
+
+static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid dev\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid dev_private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	for (i = 0; i < priv->num_crtcs; i++)
+		priv->crtcs[i]->funcs->destroy(priv->crtcs[i]);
+	priv->num_crtcs = 0;
+
+	for (i = 0; i < priv->num_planes; i++)
+		priv->planes[i]->funcs->destroy(priv->planes[i]);
+	priv->num_planes = 0;
+
+	for (i = 0; i < priv->num_connectors; i++)
+		priv->connectors[i]->funcs->destroy(priv->connectors[i]);
+	priv->num_connectors = 0;
+
+	for (i = 0; i < priv->num_encoders; i++)
+		priv->encoders[i]->funcs->destroy(priv->encoders[i]);
+	priv->num_encoders = 0;
+}
+
+static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	struct drm_plane *primary_planes[MAX_PLANES], *plane;
+	struct drm_crtc *crtc;
+
+	struct msm_drm_private *priv;
+	struct dpu_mdss_cfg *catalog;
+
+	int primary_planes_idx = 0, i, ret;
+	int max_crtc_count;
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return -EINVAL;
+	}
+
+	dev = dpu_kms->dev;
+	priv = dev->dev_private;
+	catalog = dpu_kms->catalog;
+
+	/*
+	 * Create encoder and query display drivers to create
+	 * bridges and connectors
+	 */
+	_dpu_kms_setup_displays(dev, priv, dpu_kms);
+
+	max_crtc_count = min(catalog->mixer_count, priv->num_encoders);
+
+	/* Create the planes */
+	for (i = 0; i < catalog->sspp_count; i++) {
+		bool primary = true;
+
+		if (catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR)
+			|| primary_planes_idx >= max_crtc_count)
+			primary = false;
+
+		plane = dpu_plane_init(dev, catalog->sspp[i].id, primary,
+				(1UL << max_crtc_count) - 1, 0);
+		if (IS_ERR(plane)) {
+			DPU_ERROR("dpu_plane_init failed\n");
+			ret = PTR_ERR(plane);
+			goto fail;
+		}
+		priv->planes[priv->num_planes++] = plane;
+
+		if (primary)
+			primary_planes[primary_planes_idx++] = plane;
+	}
+
+	max_crtc_count = min(max_crtc_count, primary_planes_idx);
+
+	/* Create one CRTC per encoder */
+	for (i = 0; i < max_crtc_count; i++) {
+		crtc = dpu_crtc_init(dev, primary_planes[i]);
+		if (IS_ERR(crtc)) {
+			ret = PTR_ERR(crtc);
+			goto fail;
+		}
+		priv->crtcs[priv->num_crtcs++] = crtc;
+	}
+
+	/* All CRTCs are compatible with all encoders */
+	for (i = 0; i < priv->num_encoders; i++)
+		priv->encoders[i]->possible_crtcs = (1 << priv->num_crtcs) - 1;
+
+	return 0;
+fail:
+	_dpu_kms_drm_obj_destroy(dpu_kms);
+	return ret;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct drm_device *dev;
+	int rc;
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return -EINVAL;
+	}
+
+	dev = dpu_kms->dev;
+
+	rc = _dpu_debugfs_init(dpu_kms);
+	if (rc)
+		DPU_ERROR("dpu_debugfs init failed: %d\n", rc);
+
+	return rc;
+}
+#endif
+
+static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate,
+		struct drm_encoder *encoder)
+{
+	return rate;
+}
+
+static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	int i;
+
+	dev = dpu_kms->dev;
+	if (!dev)
+		return;
+
+	if (dpu_kms->hw_intr)
+		dpu_hw_intr_destroy(dpu_kms->hw_intr);
+	dpu_kms->hw_intr = NULL;
+
+	if (dpu_kms->power_event)
+		dpu_power_handle_unregister_event(
+				&dpu_kms->phandle, dpu_kms->power_event);
+
+	/* safe to call these more than once during shutdown */
+	_dpu_debugfs_destroy(dpu_kms);
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	if (dpu_kms->catalog) {
+		for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+			u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+			if ((vbif_idx < VBIF_MAX) && dpu_kms->hw_vbif[vbif_idx])
+				dpu_hw_vbif_destroy(dpu_kms->hw_vbif[vbif_idx]);
+		}
+	}
+
+	if (dpu_kms->rm_init)
+		dpu_rm_destroy(&dpu_kms->rm);
+	dpu_kms->rm_init = false;
+
+	if (dpu_kms->catalog)
+		dpu_hw_catalog_deinit(dpu_kms->catalog);
+	dpu_kms->catalog = NULL;
+
+	if (dpu_kms->core_client)
+		dpu_power_client_destroy(&dpu_kms->phandle,
+			dpu_kms->core_client);
+	dpu_kms->core_client = NULL;
+
+	if (dpu_kms->vbif[VBIF_NRT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_NRT]);
+	dpu_kms->vbif[VBIF_NRT] = NULL;
+
+	if (dpu_kms->vbif[VBIF_RT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_RT]);
+	dpu_kms->vbif[VBIF_RT] = NULL;
+
+	if (dpu_kms->mmio)
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->mmio);
+	dpu_kms->mmio = NULL;
+}
+
+static void dpu_kms_destroy(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+
+	dpu_dbg_destroy();
+	_dpu_kms_hw_destroy(dpu_kms);
+}
+
+static int dpu_kms_pm_suspend(struct device *dev)
+{
+	struct drm_device *ddev;
+	struct drm_modeset_acquire_ctx ctx;
+	struct drm_atomic_state *state;
+	struct dpu_kms *dpu_kms;
+	int ret = 0, num_crtcs = 0;
+
+	if (!dev)
+		return -EINVAL;
+
+	ddev = dev_get_drvdata(dev);
+	if (!ddev || !ddev_to_msm_kms(ddev))
+		return -EINVAL;
+
+	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
+
+	/* disable hot-plug polling */
+	drm_kms_helper_poll_disable(ddev);
+
+	/* acquire modeset lock(s) */
+	drm_modeset_acquire_init(&ctx, 0);
+
+retry:
+	DPU_ATRACE_BEGIN("kms_pm_suspend");
+
+	ret = drm_modeset_lock_all_ctx(ddev, &ctx);
+	if (ret)
+		goto unlock;
+
+	/* save current state for resume */
+	if (dpu_kms->suspend_state)
+		drm_atomic_state_put(dpu_kms->suspend_state);
+	dpu_kms->suspend_state = drm_atomic_helper_duplicate_state(ddev, &ctx);
+	if (IS_ERR_OR_NULL(dpu_kms->suspend_state)) {
+		DRM_ERROR("failed to back up suspend state\n");
+		dpu_kms->suspend_state = NULL;
+		goto unlock;
+	}
+
+	/* create atomic state to disable all CRTCs */
+	state = drm_atomic_state_alloc(ddev);
+	if (IS_ERR_OR_NULL(state)) {
+		DRM_ERROR("failed to allocate crtc disable state\n");
+		goto unlock;
+	}
+
+	state->acquire_ctx = &ctx;
+
+	/* check for nothing to do */
+	if (num_crtcs == 0) {
+		DRM_DEBUG("all crtcs are already in the off state\n");
+		drm_atomic_state_put(state);
+		goto suspended;
+	}
+
+	/* commit the "disable all" state */
+	ret = drm_atomic_commit(state);
+	if (ret < 0) {
+		DRM_ERROR("failed to disable crtcs, %d\n", ret);
+		drm_atomic_state_put(state);
+		goto unlock;
+	}
+
+suspended:
+	dpu_kms->suspend_block = true;
+
+unlock:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(&ctx);
+		goto retry;
+	}
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+
+	DPU_ATRACE_END("kms_pm_suspend");
+	return 0;
+}
+
+static int dpu_kms_pm_resume(struct device *dev)
+{
+	struct drm_device *ddev;
+	struct dpu_kms *dpu_kms;
+	int ret;
+
+	if (!dev)
+		return -EINVAL;
+
+	ddev = dev_get_drvdata(dev);
+	if (!ddev || !ddev_to_msm_kms(ddev))
+		return -EINVAL;
+
+	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
+
+	DPU_ATRACE_BEGIN("kms_pm_resume");
+
+	drm_mode_config_reset(ddev);
+
+	drm_modeset_lock_all(ddev);
+
+	dpu_kms->suspend_block = false;
+
+	if (dpu_kms->suspend_state) {
+		dpu_kms->suspend_state->acquire_ctx =
+			ddev->mode_config.acquire_ctx;
+		ret = drm_atomic_commit(dpu_kms->suspend_state);
+		if (ret < 0) {
+			DRM_ERROR("failed to restore state, %d\n", ret);
+			drm_atomic_state_put(dpu_kms->suspend_state);
+		}
+		dpu_kms->suspend_state = NULL;
+	}
+	drm_modeset_unlock_all(ddev);
+
+	/* enable hot-plug polling */
+	drm_kms_helper_poll_enable(ddev);
+
+	DPU_ATRACE_END("kms_pm_resume");
+	return 0;
+}
+
+static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
+				 struct drm_encoder *encoder,
+				 bool cmd_mode)
+{
+	struct msm_display_info info;
+	struct msm_drm_private *priv = encoder->dev->dev_private;
+	int i, rc = 0;
+
+	memset(&info, 0, sizeof(info));
+
+	info.intf_type = encoder->encoder_type;
+	info.capabilities = cmd_mode ? MSM_DISPLAY_CAP_CMD_MODE :
+			MSM_DISPLAY_CAP_VID_MODE;
+
+	/* TODO: No support for DSI swap */
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		if (priv->dsi[i]) {
+			info.h_tile_instance[info.num_of_h_tiles] = i;
+			info.num_of_h_tiles++;
+		}
+	}
+
+	rc = dpu_encoder_setup(encoder->dev, encoder, &info);
+	if (rc)
+		DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+			encoder->base.id, rc);
+}
+
+static const struct msm_kms_funcs kms_funcs = {
+	.hw_init         = dpu_kms_hw_init,
+	.irq_preinstall  = dpu_irq_preinstall,
+	.irq_postinstall = dpu_irq_postinstall,
+	.irq_uninstall   = dpu_irq_uninstall,
+	.irq             = dpu_irq,
+	.prepare_commit  = dpu_kms_prepare_commit,
+	.commit          = dpu_kms_commit,
+	.complete_commit = dpu_kms_complete_commit,
+	.wait_for_crtc_commit_done = dpu_kms_wait_for_commit_done,
+	.enable_vblank   = dpu_kms_enable_vblank,
+	.disable_vblank  = dpu_kms_disable_vblank,
+	.check_modified_format = dpu_format_check_modified_format,
+	.get_format      = dpu_get_msm_format,
+	.round_pixclk    = dpu_kms_round_pixclk,
+	.pm_suspend      = dpu_kms_pm_suspend,
+	.pm_resume       = dpu_kms_pm_resume,
+	.destroy         = dpu_kms_destroy,
+	.set_encoder_mode = _dpu_kms_set_encoder_mode,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init    = dpu_kms_debugfs_init,
+#endif
+};
+
+/* the caller api needs to turn on clock before calling it */
+static inline void _dpu_kms_core_hw_rev_init(struct dpu_kms *dpu_kms)
+{
+	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
+}
+
+static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_mmu *mmu;
+
+	mmu = dpu_kms->base.aspace->mmu;
+
+	mmu->funcs->detach(mmu, (const char **)iommu_ports,
+			ARRAY_SIZE(iommu_ports));
+	msm_gem_address_space_put(dpu_kms->base.aspace);
+
+	return 0;
+}
+
+static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
+{
+	struct iommu_domain *domain;
+	struct msm_gem_address_space *aspace;
+	int ret;
+
+	domain = iommu_domain_alloc(&platform_bus_type);
+	if (!domain)
+		return 0;
+
+	aspace = msm_gem_address_space_create(dpu_kms->dev->dev,
+			domain, "dpu1");
+	if (IS_ERR(aspace)) {
+		ret = PTR_ERR(aspace);
+		goto fail;
+	}
+
+	dpu_kms->base.aspace = aspace;
+
+	ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
+			ARRAY_SIZE(iommu_ports));
+	if (ret) {
+		DPU_ERROR("failed to attach iommu %d\n", ret);
+		msm_gem_address_space_put(aspace);
+		goto fail;
+	}
+
+	return 0;
+fail:
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	return ret;
+}
+
+static struct dss_clk *_dpu_kms_get_clk(struct dpu_kms *dpu_kms,
+		char *clock_name)
+{
+	struct dss_module_power *mp = &dpu_kms->mp;
+	int i;
+
+	for (i = 0; i < mp->num_clk; i++) {
+		if (!strcmp(mp->clk_config[i].clk_name, clock_name))
+			return &mp->clk_config[i];
+	}
+
+	return NULL;
+}
+
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name)
+{
+	struct dss_clk *clk;
+
+	clk = _dpu_kms_get_clk(dpu_kms, clock_name);
+	if (!clk)
+		return -EINVAL;
+
+	return clk_get_rate(clk->clk);
+}
+
+static void dpu_kms_handle_power_event(u32 event_type, void *usr)
+{
+	struct dpu_kms *dpu_kms = usr;
+
+	if (!dpu_kms)
+		return;
+
+	if (event_type == DPU_POWER_EVENT_POST_ENABLE)
+		dpu_vbif_init_memtypes(dpu_kms);
+}
+
+static int dpu_kms_hw_init(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	int i, rc = -EINVAL;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		goto end;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+	if (!dev) {
+		DPU_ERROR("invalid device\n");
+		goto end;
+	}
+
+	rc = dpu_dbg_init(&dpu_kms->pdev->dev);
+	if (rc) {
+		DRM_ERROR("failed to init dpu dbg: %d\n", rc);
+		goto end;
+	}
+
+	priv = dev->dev_private;
+	if (!priv) {
+		DPU_ERROR("invalid private data\n");
+		goto dbg_destroy;
+	}
+
+	dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp", "mdp");
+	if (IS_ERR(dpu_kms->mmio)) {
+		rc = PTR_ERR(dpu_kms->mmio);
+		DPU_ERROR("mdp register memory map failed: %d\n", rc);
+		dpu_kms->mmio = NULL;
+		goto error;
+	}
+	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	dpu_kms->mmio_len = dpu_iomap_size(dpu_kms->pdev, "mdp");
+
+	dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif", "vbif");
+	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
+		rc = PTR_ERR(dpu_kms->vbif[VBIF_RT]);
+		DPU_ERROR("vbif register memory map failed: %d\n", rc);
+		dpu_kms->vbif[VBIF_RT] = NULL;
+		goto error;
+	}
+	dpu_kms->vbif_len[VBIF_RT] = dpu_iomap_size(dpu_kms->pdev, "vbif");
+	dpu_kms->vbif[VBIF_NRT] = msm_ioremap(dpu_kms->pdev, "vbif_nrt", "vbif_nrt");
+	if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) {
+		dpu_kms->vbif[VBIF_NRT] = NULL;
+		DPU_DEBUG("VBIF NRT is not defined");
+	} else {
+		dpu_kms->vbif_len[VBIF_NRT] = dpu_iomap_size(dpu_kms->pdev,
+							     "vbif_nrt");
+	}
+
+	dpu_kms->reg_dma = msm_ioremap(dpu_kms->pdev, "regdma", "regdma");
+	if (IS_ERR(dpu_kms->reg_dma)) {
+		dpu_kms->reg_dma = NULL;
+		DPU_DEBUG("REG_DMA is not defined");
+	} else {
+		dpu_kms->reg_dma_len = dpu_iomap_size(dpu_kms->pdev, "regdma");
+	}
+
+	dpu_kms->core_client = dpu_power_client_create(&dpu_kms->phandle,
+					"core");
+	if (IS_ERR_OR_NULL(dpu_kms->core_client)) {
+		rc = PTR_ERR(dpu_kms->core_client);
+		if (!dpu_kms->core_client)
+			rc = -EINVAL;
+		DPU_ERROR("dpu power client create failed: %d\n", rc);
+		dpu_kms->core_client = NULL;
+		goto error;
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	_dpu_kms_core_hw_rev_init(dpu_kms);
+
+	pr_info("dpu hardware revision:0x%x\n", dpu_kms->core_rev);
+
+	dpu_kms->catalog = dpu_hw_catalog_init(dpu_kms->core_rev);
+	if (IS_ERR_OR_NULL(dpu_kms->catalog)) {
+		rc = PTR_ERR(dpu_kms->catalog);
+		if (!dpu_kms->catalog)
+			rc = -EINVAL;
+		DPU_ERROR("catalog init failed: %d\n", rc);
+		dpu_kms->catalog = NULL;
+		goto power_error;
+	}
+
+	dpu_dbg_init_dbg_buses(dpu_kms->core_rev);
+
+	/*
+	 * Now we need to read the HW catalog and initialize resources such as
+	 * clocks, regulators, GDSC/MMAGIC, ioremap the register ranges etc
+	 */
+	rc = _dpu_kms_mmu_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("dpu_kms_mmu_init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	rc = dpu_rm_init(&dpu_kms->rm, dpu_kms->catalog, dpu_kms->mmio,
+			dpu_kms->dev);
+	if (rc) {
+		DPU_ERROR("rm init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	dpu_kms->rm_init = true;
+
+	dpu_kms->hw_mdp = dpu_rm_get_mdp(&dpu_kms->rm);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_mdp)) {
+		rc = PTR_ERR(dpu_kms->hw_mdp);
+		if (!dpu_kms->hw_mdp)
+			rc = -EINVAL;
+		DPU_ERROR("failed to get hw_mdp: %d\n", rc);
+		dpu_kms->hw_mdp = NULL;
+		goto power_error;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+		dpu_kms->hw_vbif[i] = dpu_hw_vbif_init(vbif_idx,
+				dpu_kms->vbif[vbif_idx], dpu_kms->catalog);
+		if (IS_ERR_OR_NULL(dpu_kms->hw_vbif[vbif_idx])) {
+			rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]);
+			if (!dpu_kms->hw_vbif[vbif_idx])
+				rc = -EINVAL;
+			DPU_ERROR("failed to init vbif %d: %d\n", vbif_idx, rc);
+			dpu_kms->hw_vbif[vbif_idx] = NULL;
+			goto power_error;
+		}
+	}
+
+	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog,
+			&dpu_kms->phandle,
+			_dpu_kms_get_clk(dpu_kms, "core"));
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		goto perf_err;
+	}
+
+	dpu_kms->hw_intr = dpu_hw_intr_init(dpu_kms->mmio, dpu_kms->catalog);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_intr)) {
+		rc = PTR_ERR(dpu_kms->hw_intr);
+		DPU_ERROR("hw_intr init failed: %d\n", rc);
+		dpu_kms->hw_intr = NULL;
+		goto hw_intr_init_err;
+	}
+
+	/*
+	 * _dpu_kms_drm_obj_init should create the DRM related objects
+	 * i.e. CRTCs, planes, encoders, connectors and so forth
+	 */
+	rc = _dpu_kms_drm_obj_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("modeset init failed: %d\n", rc);
+		goto drm_obj_init_err;
+	}
+
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+
+	/*
+	 * max crtc width is equal to the max mixer width * 2 and max height is
+	 * is 4K
+	 */
+	dev->mode_config.max_width =
+			dpu_kms->catalog->caps->max_mixer_width * 2;
+	dev->mode_config.max_height = 4096;
+
+	/*
+	 * Support format modifiers for compression etc.
+	 */
+	dev->mode_config.allow_fb_modifiers = true;
+
+	/*
+	 * Handle (re)initializations during power enable
+	 */
+	dpu_kms_handle_power_event(DPU_POWER_EVENT_POST_ENABLE, dpu_kms);
+	dpu_kms->power_event = dpu_power_handle_register_event(
+			&dpu_kms->phandle,
+			DPU_POWER_EVENT_POST_ENABLE,
+			dpu_kms_handle_power_event, dpu_kms, "kms");
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+
+drm_obj_init_err:
+	dpu_core_perf_destroy(&dpu_kms->perf);
+hw_intr_init_err:
+perf_err:
+power_error:
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+error:
+	_dpu_kms_hw_destroy(dpu_kms);
+dbg_destroy:
+	dpu_dbg_destroy();
+end:
+	return rc;
+}
+
+struct msm_kms *dpu_kms_init(struct drm_device *dev)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int irq;
+
+	if (!dev || !dev->dev_private) {
+		DPU_ERROR("drm device node invalid\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	priv = dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	irq = irq_of_parse_and_map(dpu_kms->pdev->dev.of_node, 0);
+	if (irq < 0) {
+		DPU_ERROR("failed to get irq: %d\n", irq);
+		return ERR_PTR(irq);
+	}
+	dpu_kms->base.irq = irq;
+
+	return &dpu_kms->base;
+}
+
+static int dpu_bind(struct device *dev, struct device *master, void *data)
+{
+	struct drm_device *ddev = dev_get_drvdata(master);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct dpu_kms *dpu_kms;
+	struct dss_module_power *mp;
+	int ret = 0;
+
+	dpu_kms = devm_kzalloc(&pdev->dev, sizeof(*dpu_kms), GFP_KERNEL);
+	if (!dpu_kms)
+		return -ENOMEM;
+
+	mp = &dpu_kms->mp;
+	ret = msm_dss_parse_clock(pdev, mp);
+	if (ret) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		return ret;
+	}
+
+	dpu_power_resource_init(pdev, &dpu_kms->phandle);
+
+	platform_set_drvdata(pdev, dpu_kms);
+
+	msm_kms_init(&dpu_kms->base, &kms_funcs);
+	dpu_kms->dev = ddev;
+	dpu_kms->pdev = pdev;
+
+	pm_runtime_enable(&pdev->dev);
+	dpu_kms->rpm_enabled = true;
+
+	priv->kms = &dpu_kms->base;
+	return ret;
+}
+
+static void dpu_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	dpu_power_resource_deinit(pdev, &dpu_kms->phandle);
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+	devm_kfree(&pdev->dev, mp->clk_config);
+	mp->num_clk = 0;
+
+	if (dpu_kms->rpm_enabled)
+		pm_runtime_disable(&pdev->dev);
+}
+
+static const struct component_ops dpu_ops = {
+	.bind   = dpu_bind,
+	.unbind = dpu_unbind,
+};
+
+static int dpu_dev_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &dpu_ops);
+}
+
+static int dpu_dev_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &dpu_ops);
+	return 0;
+}
+
+static int __maybe_unused dpu_runtime_suspend(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct drm_device *ddev;
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	ddev = dpu_kms->dev;
+	if (!ddev) {
+		DPU_ERROR("invalid drm_device\n");
+		goto exit;
+	}
+
+	rc = dpu_power_resource_enable(&dpu_kms->phandle,
+			dpu_kms->core_client, false);
+	if (rc)
+		DPU_ERROR("resource disable failed: %d\n", rc);
+
+	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
+	if (rc)
+		DPU_ERROR("clock disable failed rc:%d\n", rc);
+
+exit:
+	return rc;
+}
+
+static int __maybe_unused dpu_runtime_resume(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct drm_device *ddev;
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	ddev = dpu_kms->dev;
+	if (!ddev) {
+		DPU_ERROR("invalid drm_device\n");
+		goto exit;
+	}
+
+	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
+	if (rc) {
+		DPU_ERROR("clock enable failed rc:%d\n", rc);
+		goto exit;
+	}
+
+	rc = dpu_power_resource_enable(&dpu_kms->phandle,
+			dpu_kms->core_client, true);
+	if (rc)
+		DPU_ERROR("resource enable failed: %d\n", rc);
+
+exit:
+	return rc;
+}
+
+static const struct dev_pm_ops dpu_pm_ops = {
+	SET_RUNTIME_PM_OPS(dpu_runtime_suspend, dpu_runtime_resume, NULL)
+};
+
+static const struct of_device_id dpu_dt_match[] = {
+	{ .compatible = "qcom,sdm845-dpu", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dpu_dt_match);
+
+static struct platform_driver dpu_driver = {
+	.probe = dpu_dev_probe,
+	.remove = dpu_dev_remove,
+	.driver = {
+		.name = "msm_dpu",
+		.of_match_table = dpu_dt_match,
+		.pm = &dpu_pm_ops,
+	},
+};
+
+void __init msm_dpu_register(void)
+{
+	platform_driver_register(&dpu_driver);
+}
+
+void __exit msm_dpu_unregister(void)
+{
+	platform_driver_unregister(&dpu_driver);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
new file mode 100644
index 000000000000..66d466628e2b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -0,0 +1,290 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __DPU_KMS_H__
+#define __DPU_KMS_H__
+
+#include "msm_drv.h"
+#include "msm_kms.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+#include "dpu_dbg.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_top.h"
+#include "dpu_rm.h"
+#include "dpu_power_handle.h"
+#include "dpu_irq.h"
+#include "dpu_core_perf.h"
+
+#define DRMID(x) ((x) ? (x)->base.id : -1)
+
+/**
+ * DPU_DEBUG - macro for kms/plane/crtc/encoder/connector logs
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG(fmt, ...)                                                \
+	do {                                                               \
+		if (unlikely(drm_debug & DRM_UT_KMS))                      \
+			DRM_DEBUG(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+/**
+ * DPU_DEBUG_DRIVER - macro for hardware driver logging
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG_DRIVER(fmt, ...)                                         \
+	do {                                                               \
+		if (unlikely(drm_debug & DRM_UT_DRIVER))                   \
+			DRM_ERROR(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
+
+/**
+ * ktime_compare_safe - compare two ktime structures
+ *	This macro is similar to the standard ktime_compare() function, but
+ *	attempts to also handle ktime overflows.
+ * @A: First ktime value
+ * @B: Second ktime value
+ * Returns: -1 if A < B, 0 if A == B, 1 if A > B
+ */
+#define ktime_compare_safe(A, B) \
+	ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0))
+
+#define DPU_NAME_SIZE  12
+
+/* timeout in frames waiting for frame done */
+#define DPU_FRAME_DONE_TIMEOUT	60
+
+/*
+ * struct dpu_irq_callback - IRQ callback handlers
+ * @list: list to callback
+ * @func: intr handler
+ * @arg: argument for the handler
+ */
+struct dpu_irq_callback {
+	struct list_head list;
+	void (*func)(void *arg, int irq_idx);
+	void *arg;
+};
+
+/**
+ * struct dpu_irq: IRQ structure contains callback registration info
+ * @total_irq:    total number of irq_idx obtained from HW interrupts mapping
+ * @irq_cb_tbl:   array of IRQ callbacks setting
+ * @enable_counts array of IRQ enable counts
+ * @cb_lock:      callback lock
+ * @debugfs_file: debugfs file for irq statistics
+ */
+struct dpu_irq {
+	u32 total_irqs;
+	struct list_head *irq_cb_tbl;
+	atomic_t *enable_counts;
+	atomic_t *irq_counts;
+	spinlock_t cb_lock;
+	struct dentry *debugfs_file;
+};
+
+struct dpu_kms {
+	struct msm_kms base;
+	struct drm_device *dev;
+	int core_rev;
+	struct dpu_mdss_cfg *catalog;
+
+	struct dpu_power_handle phandle;
+	struct dpu_power_client *core_client;
+	struct dpu_power_event *power_event;
+
+	/* directory entry for debugfs */
+	struct dentry *debugfs_root;
+	struct dentry *debugfs_danger;
+	struct dentry *debugfs_vbif;
+
+	/* io/register spaces: */
+	void __iomem *mmio, *vbif[VBIF_MAX], *reg_dma;
+	unsigned long mmio_len, vbif_len[VBIF_MAX], reg_dma_len;
+
+	struct regulator *vdd;
+	struct regulator *mmagic;
+	struct regulator *venus;
+
+	struct dpu_hw_intr *hw_intr;
+	struct dpu_irq irq_obj;
+
+	struct dpu_core_perf perf;
+
+	/* saved atomic state during system suspend */
+	struct drm_atomic_state *suspend_state;
+	bool suspend_block;
+
+	struct dpu_rm rm;
+	bool rm_init;
+
+	struct dpu_hw_vbif *hw_vbif[VBIF_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+
+	bool has_danger_ctrl;
+
+	struct platform_device *pdev;
+	bool rpm_enabled;
+	struct dss_module_power mp;
+};
+
+struct vsync_info {
+	u32 frame_count;
+	u32 line_count;
+};
+
+#define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
+
+/* get struct msm_kms * from drm_device * */
+#define ddev_to_msm_kms(D) ((D) && (D)->dev_private ? \
+		((struct msm_drm_private *)((D)->dev_private))->kms : NULL)
+
+/**
+ * dpu_kms_is_suspend_state - whether or not the system is pm suspended
+ * @dev: Pointer to drm device
+ * Return: Suspend status
+ */
+static inline bool dpu_kms_is_suspend_state(struct drm_device *dev)
+{
+	if (!ddev_to_msm_kms(dev))
+		return false;
+
+	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_state != NULL;
+}
+
+/**
+ * dpu_kms_is_suspend_blocked - whether or not commits are blocked due to pm
+ *				suspend status
+ * @dev: Pointer to drm device
+ * Return: True if commits should be rejected due to pm suspend
+ */
+static inline bool dpu_kms_is_suspend_blocked(struct drm_device *dev)
+{
+	if (!dpu_kms_is_suspend_state(dev))
+		return false;
+
+	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_block;
+}
+
+/**
+ * Debugfs functions - extra helper functions for debugfs support
+ *
+ * Main debugfs documentation is located at,
+ *
+ * Documentation/filesystems/debugfs.txt
+ *
+ * @dpu_debugfs_setup_regset32: Initialize data for dpu_debugfs_create_regset32
+ * @dpu_debugfs_create_regset32: Create 32-bit register dump file
+ * @dpu_debugfs_get_root: Get root dentry for DPU_KMS's debugfs node
+ */
+
+/**
+ * Companion structure for dpu_debugfs_create_regset32. Do not initialize the
+ * members of this structure explicitly; use dpu_debugfs_setup_regset32 instead.
+ */
+struct dpu_debugfs_regset32 {
+	uint32_t offset;
+	uint32_t blk_len;
+	struct dpu_kms *dpu_kms;
+};
+
+/**
+ * dpu_debugfs_setup_regset32 - Initialize register block definition for debugfs
+ * This function is meant to initialize dpu_debugfs_regset32 structures for use
+ * with dpu_debugfs_create_regset32.
+ * @regset: opaque register definition structure
+ * @offset: sub-block offset
+ * @length: sub-block length, in bytes
+ * @dpu_kms: pointer to dpu kms structure
+ */
+void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_debugfs_create_regset32 - Create register read back file for debugfs
+ *
+ * This function is almost identical to the standard debugfs_create_regset32()
+ * function, with the main difference being that a list of register
+ * names/offsets do not need to be provided. The 'read' function simply outputs
+ * sequential register values over a specified range.
+ *
+ * Similar to the related debugfs_create_regset32 API, the structure pointed to
+ * by regset needs to persist for the lifetime of the created file. The calling
+ * code is responsible for initialization/management of this structure.
+ *
+ * The structure pointed to by regset is meant to be opaque. Please use
+ * dpu_debugfs_setup_regset32 to initialize it.
+ *
+ * @name:   File name within debugfs
+ * @mode:   File mode within debugfs
+ * @parent: Parent directory entry within debugfs, can be NULL
+ * @regset: Pointer to persistent register block definition
+ *
+ * Return: dentry pointer for newly created file, use either debugfs_remove()
+ *         or debugfs_remove_recursive() (on a parent directory) to remove the
+ *         file
+ */
+void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent, struct dpu_debugfs_regset32 *regset);
+
+/**
+ * dpu_debugfs_get_root - Return root directory entry for KMS's debugfs
+ *
+ * The return value should be passed as the 'parent' argument to subsequent
+ * debugfs create calls.
+ *
+ * @dpu_kms: Pointer to DPU's KMS structure
+ *
+ * Return: dentry pointer for DPU's debugfs location
+ */
+void *dpu_debugfs_get_root(struct dpu_kms *dpu_kms);
+
+/**
+ * DPU info management functions
+ * These functions/definitions allow for building up a 'dpu_info' structure
+ * containing one or more "key=value\n" entries.
+ */
+#define DPU_KMS_INFO_MAX_SIZE	4096
+
+/**
+ * Vblank enable/disable functions
+ */
+int dpu_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+void dpu_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+
+void dpu_kms_encoder_enable(struct drm_encoder *encoder);
+
+/**
+ * dpu_kms_get_clk_rate() - get the clock rate
+ * @dpu_kms:  poiner to dpu_kms structure
+ * @clock_name: clock name to get the rate
+ *
+ * Return: current clock rate
+ */
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name);
+
+#endif /* __dpu_kms_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
new file mode 100644
index 000000000000..9e533b86682c
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -0,0 +1,245 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018, The Linux Foundation
+ */
+
+#include "dpu_kms.h"
+
+#define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
+
+#define HW_INTR_STATUS			0x0010
+
+struct dpu_mdss {
+	struct msm_mdss base;
+	void __iomem *mmio;
+	unsigned long mmio_len;
+	u32 hwversion;
+	struct dss_module_power mp;
+	struct dpu_irq_controller irq_controller;
+};
+
+static irqreturn_t dpu_mdss_irq(int irq, void *arg)
+{
+	struct dpu_mdss *dpu_mdss = arg;
+	u32 interrupts;
+
+	interrupts = readl_relaxed(dpu_mdss->mmio + HW_INTR_STATUS);
+
+	while (interrupts) {
+		irq_hw_number_t hwirq = fls(interrupts) - 1;
+		unsigned int mapping;
+		int rc;
+
+		mapping = irq_find_mapping(dpu_mdss->irq_controller.domain,
+					   hwirq);
+		if (mapping == 0) {
+			DRM_ERROR("couldn't find irq mapping for %lu\n", hwirq);
+			return IRQ_NONE;
+		}
+
+		rc = generic_handle_irq(mapping);
+		if (rc < 0) {
+			DRM_ERROR("handle irq fail: irq=%lu mapping=%u rc=%d\n",
+				  hwirq, mapping, rc);
+			return IRQ_NONE;
+		}
+
+		interrupts &= ~(1 << hwirq);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void dpu_mdss_irq_mask(struct irq_data *irqd)
+{
+	struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd);
+
+	/* memory barrier */
+	smp_mb__before_atomic();
+	clear_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask);
+	/* memory barrier */
+	smp_mb__after_atomic();
+}
+
+static void dpu_mdss_irq_unmask(struct irq_data *irqd)
+{
+	struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd);
+
+	/* memory barrier */
+	smp_mb__before_atomic();
+	set_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask);
+	/* memory barrier */
+	smp_mb__after_atomic();
+}
+
+static struct irq_chip dpu_mdss_irq_chip = {
+	.name = "dpu_mdss",
+	.irq_mask = dpu_mdss_irq_mask,
+	.irq_unmask = dpu_mdss_irq_unmask,
+};
+
+static int dpu_mdss_irqdomain_map(struct irq_domain *domain,
+		unsigned int irq, irq_hw_number_t hwirq)
+{
+	struct dpu_mdss *dpu_mdss = domain->host_data;
+	int ret;
+
+	irq_set_chip_and_handler(irq, &dpu_mdss_irq_chip, handle_level_irq);
+	ret = irq_set_chip_data(irq, dpu_mdss);
+
+	return ret;
+}
+
+static const struct irq_domain_ops dpu_mdss_irqdomain_ops = {
+	.map = dpu_mdss_irqdomain_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int _dpu_mdss_irq_domain_add(struct dpu_mdss *dpu_mdss)
+{
+	struct device *dev;
+	struct irq_domain *domain;
+
+	dev = dpu_mdss->base.dev->dev;
+
+	domain = irq_domain_add_linear(dev->of_node, 32,
+			&dpu_mdss_irqdomain_ops, dpu_mdss);
+	if (!domain) {
+		DPU_ERROR("failed to add irq_domain\n");
+		return -EINVAL;
+	}
+
+	dpu_mdss->irq_controller.enabled_mask = 0;
+	dpu_mdss->irq_controller.domain = domain;
+
+	return 0;
+}
+
+static int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
+{
+	if (dpu_mdss->irq_controller.domain) {
+		irq_domain_remove(dpu_mdss->irq_controller.domain);
+		dpu_mdss->irq_controller.domain = NULL;
+	}
+	return 0;
+}
+static int dpu_mdss_enable(struct msm_mdss *mdss)
+{
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+	int ret;
+
+	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
+	if (ret)
+		DPU_ERROR("clock enable failed, ret:%d\n", ret);
+
+	return ret;
+}
+
+static int dpu_mdss_disable(struct msm_mdss *mdss)
+{
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+	int ret;
+
+	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
+	if (ret)
+		DPU_ERROR("clock disable failed, ret:%d\n", ret);
+
+	return ret;
+}
+
+static void dpu_mdss_destroy(struct drm_device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+
+	_dpu_mdss_irq_domain_fini(dpu_mdss);
+
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+	devm_kfree(&pdev->dev, mp->clk_config);
+
+	if (dpu_mdss->mmio)
+		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
+	dpu_mdss->mmio = NULL;
+
+	pm_runtime_disable(dev->dev);
+	priv->mdss = NULL;
+}
+
+static const struct msm_mdss_funcs mdss_funcs = {
+	.enable	= dpu_mdss_enable,
+	.disable = dpu_mdss_disable,
+	.destroy = dpu_mdss_destroy,
+};
+
+int dpu_mdss_init(struct drm_device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct msm_drm_private *priv = dev->dev_private;
+	struct resource *res;
+	struct dpu_mdss *dpu_mdss;
+	struct dss_module_power *mp;
+	int ret = 0;
+
+	dpu_mdss = devm_kzalloc(dev->dev, sizeof(*dpu_mdss), GFP_KERNEL);
+	if (!dpu_mdss)
+		return -ENOMEM;
+
+	dpu_mdss->mmio = msm_ioremap(pdev, "mdss", "mdss");
+	if (IS_ERR(dpu_mdss->mmio))
+		return PTR_ERR(dpu_mdss->mmio);
+
+	DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mdss");
+	if (!res) {
+		DRM_ERROR("failed to get memory resource for mdss\n");
+		return -ENOMEM;
+	}
+	dpu_mdss->mmio_len = resource_size(res);
+
+	mp = &dpu_mdss->mp;
+	ret = msm_dss_parse_clock(pdev, mp);
+	if (ret) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		goto clk_parse_err;
+	}
+
+	dpu_mdss->base.dev = dev;
+	dpu_mdss->base.funcs = &mdss_funcs;
+
+	ret = _dpu_mdss_irq_domain_add(dpu_mdss);
+	if (ret)
+		goto irq_domain_error;
+
+	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
+			dpu_mdss_irq, 0, "dpu_mdss_isr", dpu_mdss);
+	if (ret) {
+		DPU_ERROR("failed to init irq: %d\n", ret);
+		goto irq_error;
+	}
+
+	pm_runtime_enable(dev->dev);
+
+	pm_runtime_get_sync(dev->dev);
+	dpu_mdss->hwversion = readl_relaxed(dpu_mdss->mmio);
+	pm_runtime_put_sync(dev->dev);
+
+	priv->mdss = &dpu_mdss->base;
+
+	return ret;
+
+irq_error:
+	_dpu_mdss_irq_domain_fini(dpu_mdss);
+irq_domain_error:
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+clk_parse_err:
+	devm_kfree(&pdev->dev, mp->clk_config);
+	if (dpu_mdss->mmio)
+		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
+	dpu_mdss->mmio = NULL;
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
new file mode 100644
index 000000000000..b640e39ebaca
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -0,0 +1,1963 @@
+/*
+ * Copyright (C) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_hw_catalog_format.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_vbif.h"
+#include "dpu_plane.h"
+
+#define DPU_DEBUG_PLANE(pl, fmt, ...) DPU_DEBUG("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_PLANE(pl, fmt, ...) DPU_ERROR("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DECIMATED_DIMENSION(dim, deci) (((dim) + ((1 << (deci)) - 1)) >> (deci))
+#define PHASE_STEP_SHIFT	21
+#define PHASE_STEP_UNIT_SCALE   ((int) (1 << PHASE_STEP_SHIFT))
+#define PHASE_RESIDUAL		15
+
+#define SHARP_STRENGTH_DEFAULT	32
+#define SHARP_EDGE_THR_DEFAULT	112
+#define SHARP_SMOOTH_THR_DEFAULT	8
+#define SHARP_NOISE_THR_DEFAULT	2
+
+#define DPU_NAME_SIZE  12
+
+#define DPU_PLANE_COLOR_FILL_FLAG	BIT(31)
+#define DPU_ZPOS_MAX 255
+
+/* multirect rect index */
+enum {
+	R0,
+	R1,
+	R_MAX
+};
+
+#define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4
+#define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3
+
+#define DEFAULT_REFRESH_RATE	60
+
+/**
+ * enum dpu_plane_qos - Different qos configurations for each pipe
+ *
+ * @DPU_PLANE_QOS_VBLANK_CTRL: Setup VBLANK qos for the pipe.
+ * @DPU_PLANE_QOS_VBLANK_AMORTIZE: Enables Amortization within pipe.
+ *	this configuration is mutually exclusive from VBLANK_CTRL.
+ * @DPU_PLANE_QOS_PANIC_CTRL: Setup panic for the pipe.
+ */
+enum dpu_plane_qos {
+	DPU_PLANE_QOS_VBLANK_CTRL = BIT(0),
+	DPU_PLANE_QOS_VBLANK_AMORTIZE = BIT(1),
+	DPU_PLANE_QOS_PANIC_CTRL = BIT(2),
+};
+
+/*
+ * struct dpu_plane - local dpu plane structure
+ * @aspace: address space pointer
+ * @csc_ptr: Points to dpu_csc_cfg structure to use for current
+ * @mplane_list: List of multirect planes of the same pipe
+ * @catalog: Points to dpu catalog structure
+ * @revalidate: force revalidation of all the plane properties
+ */
+struct dpu_plane {
+	struct drm_plane base;
+
+	struct mutex lock;
+
+	enum dpu_sspp pipe;
+	uint32_t features;      /* capabilities from catalog */
+	uint32_t nformats;
+	uint32_t formats[64];
+
+	struct dpu_hw_pipe *pipe_hw;
+	struct dpu_hw_pipe_cfg pipe_cfg;
+	struct dpu_hw_pipe_qos_cfg pipe_qos_cfg;
+	uint32_t color_fill;
+	bool is_error;
+	bool is_rt_pipe;
+	bool is_virtual;
+	struct list_head mplane_list;
+	struct dpu_mdss_cfg *catalog;
+
+	struct dpu_csc_cfg *csc_ptr;
+
+	const struct dpu_sspp_sub_blks *pipe_sblk;
+	char pipe_name[DPU_NAME_SIZE];
+
+	/* debugfs related stuff */
+	struct dentry *debugfs_root;
+	struct dpu_debugfs_regset32 debugfs_src;
+	struct dpu_debugfs_regset32 debugfs_scaler;
+	struct dpu_debugfs_regset32 debugfs_csc;
+	bool debugfs_default_scale;
+};
+
+#define to_dpu_plane(x) container_of(x, struct dpu_plane, base)
+
+static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane)
+{
+	struct msm_drm_private *priv;
+
+	if (!plane || !plane->dev)
+		return NULL;
+	priv = plane->dev->dev_private;
+	if (!priv)
+		return NULL;
+	return to_dpu_kms(priv->kms);
+}
+
+static bool dpu_plane_enabled(struct drm_plane_state *state)
+{
+	return state && state->fb && state->crtc;
+}
+
+static bool dpu_plane_sspp_enabled(struct drm_plane_state *state)
+{
+	return state && state->crtc;
+}
+
+/**
+ * _dpu_plane_calc_fill_level - calculate fill level of the given source format
+ * @plane:		Pointer to drm plane
+ * @fmt:		Pointer to source buffer format
+ * @src_wdith:		width of source buffer
+ * Return: fill level corresponding to the source buffer/format or 0 if error
+ */
+static inline int _dpu_plane_calc_fill_level(struct drm_plane *plane,
+		const struct dpu_format *fmt, u32 src_width)
+{
+	struct dpu_plane *pdpu, *tmp;
+	struct dpu_plane_state *pstate;
+	u32 fixed_buff_size;
+	u32 total_fl;
+
+	if (!plane || !fmt || !plane->state || !src_width || !fmt->bpp) {
+		DPU_ERROR("invalid arguments\n");
+		return 0;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+	fixed_buff_size = pdpu->pipe_sblk->common->pixel_ram_size;
+
+	list_for_each_entry(tmp, &pdpu->mplane_list, mplane_list) {
+		if (!dpu_plane_enabled(tmp->base.state))
+			continue;
+		DPU_DEBUG("plane%d/%d src_width:%d/%d\n",
+				pdpu->base.base.id, tmp->base.base.id,
+				src_width,
+				drm_rect_width(&tmp->pipe_cfg.src_rect));
+		src_width = max_t(u32, src_width,
+				  drm_rect_width(&tmp->pipe_cfg.src_rect));
+	}
+
+	if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+		if (fmt->chroma_sample == DPU_CHROMA_420) {
+			/* NV12 */
+			total_fl = (fixed_buff_size / 2) /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			/* non NV12 */
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	} else {
+		if (pstate->multirect_mode == DPU_SSPP_MULTIRECT_PARALLEL) {
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			total_fl = (fixed_buff_size) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	}
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s w:%u fl:%u\n",
+			plane->base.id, pdpu->pipe - SSPP_VIG0,
+			(char *)&fmt->base.pixel_format,
+			src_width, total_fl);
+
+	return total_fl;
+}
+
+/**
+ * _dpu_plane_get_qos_lut - get LUT mapping based on fill level
+ * @tbl:		Pointer to LUT table
+ * @total_fl:		fill level
+ * Return: LUT setting corresponding to the fill level
+ */
+static u64 _dpu_plane_get_qos_lut(const struct dpu_qos_lut_tbl *tbl,
+		u32 total_fl)
+{
+	int i;
+
+	if (!tbl || !tbl->nentry || !tbl->entries)
+		return 0;
+
+	for (i = 0; i < tbl->nentry; i++)
+		if (total_fl <= tbl->entries[i].fl)
+			return tbl->entries[i].lut;
+
+	/* if last fl is zero, use as default */
+	if (!tbl->entries[i-1].fl)
+		return tbl->entries[i-1].lut;
+
+	return 0;
+}
+
+/**
+ * _dpu_plane_set_qos_lut - set QoS LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_qos_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	const struct dpu_format *fmt = NULL;
+	u64 qos_lut;
+	u32 total_fl = 0, lut_usage;
+
+	if (!plane || !fb) {
+		DPU_ERROR("invalid arguments plane %d fb %d\n",
+				plane != 0, fb != 0);
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_creq_lut) {
+		return;
+	}
+
+	if (!pdpu->is_rt_pipe) {
+		lut_usage = DPU_QOS_LUT_USAGE_NRT;
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+		total_fl = _dpu_plane_calc_fill_level(plane, fmt,
+				drm_rect_width(&pdpu->pipe_cfg.src_rect));
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt))
+			lut_usage = DPU_QOS_LUT_USAGE_LINEAR;
+		else
+			lut_usage = DPU_QOS_LUT_USAGE_MACROTILE;
+	}
+
+	qos_lut = _dpu_plane_get_qos_lut(
+			&pdpu->catalog->perf.qos_lut_tbl[lut_usage], total_fl);
+
+	pdpu->pipe_qos_cfg.creq_lut = qos_lut;
+
+	trace_dpu_perf_set_qos_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			pdpu->is_rt_pipe, total_fl, qos_lut, lut_usage);
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s rt:%d fl:%u lut:0x%llx\n",
+			plane->base.id,
+			pdpu->pipe - SSPP_VIG0,
+			fmt ? (char *)&fmt->base.pixel_format : NULL,
+			pdpu->is_rt_pipe, total_fl, qos_lut);
+
+	pdpu->pipe_hw->ops.setup_creq_lut(pdpu->pipe_hw, &pdpu->pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_panic_lut - set danger/safe LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_danger_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	const struct dpu_format *fmt = NULL;
+	u32 danger_lut, safe_lut;
+
+	if (!plane || !fb) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_danger_safe_lut) {
+		return;
+	}
+
+	if (!pdpu->is_rt_pipe) {
+		danger_lut = pdpu->catalog->perf.danger_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+		safe_lut = pdpu->catalog->perf.safe_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt)) {
+			danger_lut = pdpu->catalog->perf.danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+			safe_lut = pdpu->catalog->perf.safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+		} else {
+			danger_lut = pdpu->catalog->perf.danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+			safe_lut = pdpu->catalog->perf.safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+		}
+	}
+
+	pdpu->pipe_qos_cfg.danger_lut = danger_lut;
+	pdpu->pipe_qos_cfg.safe_lut = safe_lut;
+
+	trace_dpu_perf_set_danger_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			(fmt) ? fmt->fetch_mode : 0,
+			pdpu->pipe_qos_cfg.danger_lut,
+			pdpu->pipe_qos_cfg.safe_lut);
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s mode:%d luts[0x%x, 0x%x]\n",
+		plane->base.id,
+		pdpu->pipe - SSPP_VIG0,
+		fmt ? (char *)&fmt->base.pixel_format : NULL,
+		fmt ? fmt->fetch_mode : -1,
+		pdpu->pipe_qos_cfg.danger_lut,
+		pdpu->pipe_qos_cfg.safe_lut);
+
+	pdpu->pipe_hw->ops.setup_danger_safe_lut(pdpu->pipe_hw,
+			&pdpu->pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_qos_ctrl - set QoS control of the given plane
+ * @plane:		Pointer to drm plane
+ * @enable:		true to enable QoS control
+ * @flags:		QoS control mode (enum dpu_plane_qos)
+ */
+static void _dpu_plane_set_qos_ctrl(struct drm_plane *plane,
+	bool enable, u32 flags)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_qos_ctrl) {
+		return;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_CTRL) {
+		pdpu->pipe_qos_cfg.creq_vblank = pdpu->pipe_sblk->creq_vblank;
+		pdpu->pipe_qos_cfg.danger_vblank =
+				pdpu->pipe_sblk->danger_vblank;
+		pdpu->pipe_qos_cfg.vblank_en = enable;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_AMORTIZE) {
+		/* this feature overrules previous VBLANK_CTRL */
+		pdpu->pipe_qos_cfg.vblank_en = false;
+		pdpu->pipe_qos_cfg.creq_vblank = 0; /* clear vblank bits */
+	}
+
+	if (flags & DPU_PLANE_QOS_PANIC_CTRL)
+		pdpu->pipe_qos_cfg.danger_safe_en = enable;
+
+	if (!pdpu->is_rt_pipe) {
+		pdpu->pipe_qos_cfg.vblank_en = false;
+		pdpu->pipe_qos_cfg.danger_safe_en = false;
+	}
+
+	DPU_DEBUG("plane%u: pnum:%d ds:%d vb:%d pri[0x%x, 0x%x] is_rt:%d\n",
+		plane->base.id,
+		pdpu->pipe - SSPP_VIG0,
+		pdpu->pipe_qos_cfg.danger_safe_en,
+		pdpu->pipe_qos_cfg.vblank_en,
+		pdpu->pipe_qos_cfg.creq_vblank,
+		pdpu->pipe_qos_cfg.danger_vblank,
+		pdpu->is_rt_pipe);
+
+	pdpu->pipe_hw->ops.setup_qos_ctrl(pdpu->pipe_hw,
+			&pdpu->pipe_qos_cfg);
+}
+
+int dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable)
+{
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->is_rt_pipe)
+		goto end;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	_dpu_plane_set_qos_ctrl(plane, enable, DPU_PLANE_QOS_PANIC_CTRL);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+end:
+	return 0;
+}
+
+/**
+ * _dpu_plane_set_ot_limit - set OT limit for the given plane
+ * @plane:		Pointer to drm plane
+ * @crtc:		Pointer to drm crtc
+ */
+static void _dpu_plane_set_ot_limit(struct drm_plane *plane,
+		struct drm_crtc *crtc)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_vbif_set_ot_params ot_params;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev || !crtc) {
+		DPU_ERROR("invalid arguments plane %d crtc %d\n",
+				plane != 0, crtc != 0);
+		return;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR("invalid pipe reference\n");
+		return;
+	}
+
+	memset(&ot_params, 0, sizeof(ot_params));
+	ot_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	ot_params.num = pdpu->pipe_hw->idx - SSPP_NONE;
+	ot_params.width = drm_rect_width(&pdpu->pipe_cfg.src_rect);
+	ot_params.height = drm_rect_height(&pdpu->pipe_cfg.src_rect);
+	ot_params.is_wfd = !pdpu->is_rt_pipe;
+	ot_params.frame_rate = crtc->mode.vrefresh;
+	ot_params.vbif_idx = VBIF_RT;
+	ot_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	ot_params.rd = true;
+
+	dpu_vbif_set_ot_limit(dpu_kms, &ot_params);
+}
+
+/**
+ * _dpu_plane_set_vbif_qos - set vbif QoS for the given plane
+ * @plane:		Pointer to drm plane
+ */
+static void _dpu_plane_set_qos_remap(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_vbif_set_qos_params qos_params;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR("invalid pipe reference\n");
+		return;
+	}
+
+	memset(&qos_params, 0, sizeof(qos_params));
+	qos_params.vbif_idx = VBIF_RT;
+	qos_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	qos_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	qos_params.num = pdpu->pipe_hw->idx - SSPP_VIG0;
+	qos_params.is_rt = pdpu->is_rt_pipe;
+
+	DPU_DEBUG("plane%d pipe:%d vbif:%d xin:%d rt:%d, clk_ctrl:%d\n",
+			plane->base.id, qos_params.num,
+			qos_params.vbif_idx,
+			qos_params.xin_id, qos_params.is_rt,
+			qos_params.clk_ctrl);
+
+	dpu_vbif_set_qos_remap(dpu_kms, &qos_params);
+}
+
+/**
+ * _dpu_plane_get_aspace: gets the address space
+ */
+static int _dpu_plane_get_aspace(
+		struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		struct msm_gem_address_space **aspace)
+{
+	struct dpu_kms *kms;
+
+	if (!pdpu || !pstate || !aspace) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_plane_get_kms(&pdpu->base);
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	*aspace = kms->base.aspace;
+
+	return 0;
+}
+
+static inline void _dpu_plane_set_scanout(struct drm_plane *plane,
+		struct dpu_plane_state *pstate,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	struct msm_gem_address_space *aspace = NULL;
+	int ret;
+
+	if (!plane || !pstate || !pipe_cfg || !fb) {
+		DPU_ERROR(
+			"invalid arg(s), plane %d state %d cfg %d fb %d\n",
+			plane != 0, pstate != 0, pipe_cfg != 0, fb != 0);
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR_PLANE(pdpu, "invalid pipe_hw\n");
+		return;
+	}
+
+	ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "Failed to get aspace %d\n", ret);
+		return;
+	}
+
+	ret = dpu_format_populate_layout(aspace, fb, &pipe_cfg->layout);
+	if (ret == -EAGAIN)
+		DPU_DEBUG_PLANE(pdpu, "not updating same src addrs\n");
+	else if (ret)
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+	else if (pdpu->pipe_hw->ops.setup_sourceaddress) {
+		trace_dpu_plane_set_scanout(pdpu->pipe_hw->idx,
+					    &pipe_cfg->layout,
+					    pstate->multirect_index);
+		pdpu->pipe_hw->ops.setup_sourceaddress(pdpu->pipe_hw, pipe_cfg,
+						pstate->multirect_index);
+	}
+}
+
+static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		uint32_t src_w, uint32_t src_h, uint32_t dst_w, uint32_t dst_h,
+		struct dpu_hw_scaler3_cfg *scale_cfg,
+		const struct dpu_format *fmt,
+		uint32_t chroma_subsmpl_h, uint32_t chroma_subsmpl_v)
+{
+	uint32_t i;
+
+	if (!pdpu || !pstate || !scale_cfg || !fmt || !chroma_subsmpl_h ||
+			!chroma_subsmpl_v) {
+		DPU_ERROR(
+			"pdpu %d pstate %d scale_cfg %d fmt %d smp_h %d smp_v %d\n",
+			!!pdpu, !!pstate, !!scale_cfg, !!fmt, chroma_subsmpl_h,
+			chroma_subsmpl_v);
+		return;
+	}
+
+	memset(scale_cfg, 0, sizeof(*scale_cfg));
+	memset(&pstate->pixel_ext, 0, sizeof(struct dpu_hw_pixel_ext));
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_w, dst_w);
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_h, dst_h);
+
+
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0] / chroma_subsmpl_v;
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0] / chroma_subsmpl_h;
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2];
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0];
+
+	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		scale_cfg->src_width[i] = src_w;
+		scale_cfg->src_height[i] = src_h;
+		if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) {
+			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;
+		pstate->pixel_ext.num_ext_pxls_top[i] =
+			scale_cfg->src_height[i];
+		pstate->pixel_ext.num_ext_pxls_left[i] =
+			scale_cfg->src_width[i];
+	}
+	if (!(DPU_FORMAT_IS_YUV(fmt)) && (src_h == dst_h)
+		&& (src_w == dst_w))
+		return;
+
+	scale_cfg->dst_width = dst_w;
+	scale_cfg->dst_height = dst_h;
+	scale_cfg->y_rgb_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->uv_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->alpha_filter_cfg = DPU_SCALE_ALPHA_BIL;
+	scale_cfg->lut_flag = 0;
+	scale_cfg->blend_cfg = 1;
+	scale_cfg->enable = 1;
+}
+
+static inline void _dpu_plane_setup_csc(struct dpu_plane *pdpu)
+{
+	static const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L = {
+		{
+			/* S15.16 format */
+			0x00012A00, 0x00000000, 0x00019880,
+			0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+			0x00012A00, 0x00020480, 0x00000000,
+		},
+		/* signed bias */
+		{ 0xfff0, 0xff80, 0xff80,},
+		{ 0x0, 0x0, 0x0,},
+		/* unsigned clamp */
+		{ 0x10, 0xeb, 0x10, 0xf0, 0x10, 0xf0,},
+		{ 0x00, 0xff, 0x00, 0xff, 0x00, 0xff,},
+	};
+	static const struct dpu_csc_cfg dpu_csc10_YUV2RGB_601L = {
+		{
+			/* S15.16 format */
+			0x00012A00, 0x00000000, 0x00019880,
+			0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+			0x00012A00, 0x00020480, 0x00000000,
+			},
+		/* signed bias */
+		{ 0xffc0, 0xfe00, 0xfe00,},
+		{ 0x0, 0x0, 0x0,},
+		/* unsigned clamp */
+		{ 0x40, 0x3ac, 0x40, 0x3c0, 0x40, 0x3c0,},
+		{ 0x00, 0x3ff, 0x00, 0x3ff, 0x00, 0x3ff,},
+	};
+
+	if (!pdpu) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	if (BIT(DPU_SSPP_CSC_10BIT) & pdpu->features)
+		pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc10_YUV2RGB_601L;
+	else
+		pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc_YUV2RGB_601L;
+
+	DPU_DEBUG_PLANE(pdpu, "using 0x%X 0x%X 0x%X...\n",
+			pdpu->csc_ptr->csc_mv[0],
+			pdpu->csc_ptr->csc_mv[1],
+			pdpu->csc_ptr->csc_mv[2]);
+}
+
+static void _dpu_plane_setup_scaler(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		const struct dpu_format *fmt, bool color_fill)
+{
+	struct dpu_hw_pixel_ext *pe;
+	uint32_t chroma_subsmpl_h, chroma_subsmpl_v;
+
+	if (!pdpu || !fmt || !pstate) {
+		DPU_ERROR("invalid arg(s), plane %d fmt %d state %d\n",
+				pdpu != 0, fmt != 0, pstate != 0);
+		return;
+	}
+
+	pe = &pstate->pixel_ext;
+
+	/* don't chroma subsample if decimating */
+	chroma_subsmpl_h =
+		drm_format_horz_chroma_subsampling(fmt->base.pixel_format);
+	chroma_subsmpl_v =
+		drm_format_vert_chroma_subsampling(fmt->base.pixel_format);
+
+	/* update scaler. calculate default config for QSEED3 */
+	_dpu_plane_setup_scaler3(pdpu, pstate,
+			drm_rect_width(&pdpu->pipe_cfg.src_rect),
+			drm_rect_height(&pdpu->pipe_cfg.src_rect),
+			drm_rect_width(&pdpu->pipe_cfg.dst_rect),
+			drm_rect_height(&pdpu->pipe_cfg.dst_rect),
+			&pstate->scaler3_cfg, fmt,
+			chroma_subsmpl_h, chroma_subsmpl_v);
+}
+
+/**
+ * _dpu_plane_color_fill - enables color fill on plane
+ * @pdpu:   Pointer to DPU plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+static int _dpu_plane_color_fill(struct dpu_plane *pdpu,
+		uint32_t color, uint32_t alpha)
+{
+	const struct dpu_format *fmt;
+	const struct drm_plane *plane;
+	struct dpu_plane_state *pstate;
+
+	if (!pdpu || !pdpu->base.state) {
+		DPU_ERROR("invalid plane\n");
+		return -EINVAL;
+	}
+
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR_PLANE(pdpu, "invalid plane h/w pointer\n");
+		return -EINVAL;
+	}
+
+	plane = &pdpu->base;
+	pstate = to_dpu_plane_state(plane->state);
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/*
+	 * select fill format to match user property expectation,
+	 * h/w only supports RGB variants
+	 */
+	fmt = dpu_get_dpu_format(DRM_FORMAT_ABGR8888);
+
+	/* update sspp */
+	if (fmt && pdpu->pipe_hw->ops.setup_solidfill) {
+		pdpu->pipe_hw->ops.setup_solidfill(pdpu->pipe_hw,
+				(color & 0xFFFFFF) | ((alpha & 0xFF) << 24),
+				pstate->multirect_index);
+
+		/* override scaler/decimation if solid fill */
+		pdpu->pipe_cfg.src_rect.x1 = 0;
+		pdpu->pipe_cfg.src_rect.y1 = 0;
+		pdpu->pipe_cfg.src_rect.x2 =
+			drm_rect_width(&pdpu->pipe_cfg.dst_rect);
+		pdpu->pipe_cfg.src_rect.y2 =
+			drm_rect_height(&pdpu->pipe_cfg.dst_rect);
+		_dpu_plane_setup_scaler(pdpu, pstate, fmt, true);
+
+		if (pdpu->pipe_hw->ops.setup_format)
+			pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw,
+					fmt, DPU_SSPP_SOLID_FILL,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_rects)
+			pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+					&pdpu->pipe_cfg,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_pe)
+			pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+					&pstate->pixel_ext);
+
+		if (pdpu->pipe_hw->ops.setup_scaler &&
+				pstate->multirect_index != DPU_SSPP_RECT_1)
+			pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+					&pdpu->pipe_cfg, &pstate->pixel_ext,
+					&pstate->scaler3_cfg);
+	}
+
+	return 0;
+}
+
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!drm_state)
+		return;
+
+	pstate = to_dpu_plane_state(drm_state);
+
+	pstate->multirect_index = DPU_SSPP_RECT_SOLO;
+	pstate->multirect_mode = DPU_SSPP_MULTIRECT_NONE;
+}
+
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane)
+{
+	struct dpu_plane_state *pstate[R_MAX];
+	const struct drm_plane_state *drm_state[R_MAX];
+	struct drm_rect src[R_MAX], dst[R_MAX];
+	struct dpu_plane *dpu_plane[R_MAX];
+	const struct dpu_format *fmt[R_MAX];
+	int i, buffer_lines;
+	unsigned int max_tile_height = 1;
+	bool parallel_fetch_qualified = true;
+	bool has_tiled_rect = false;
+
+	for (i = 0; i < R_MAX; i++) {
+		const struct msm_format *msm_fmt;
+
+		drm_state[i] = i ? plane->r1 : plane->r0;
+		msm_fmt = msm_framebuffer_format(drm_state[i]->fb);
+		fmt[i] = to_dpu_format(msm_fmt);
+
+		if (DPU_FORMAT_IS_UBWC(fmt[i])) {
+			has_tiled_rect = true;
+			if (fmt[i]->tile_height > max_tile_height)
+				max_tile_height = fmt[i]->tile_height;
+		}
+	}
+
+	for (i = 0; i < R_MAX; i++) {
+		int width_threshold;
+
+		pstate[i] = to_dpu_plane_state(drm_state[i]);
+		dpu_plane[i] = to_dpu_plane(drm_state[i]->plane);
+
+		if (pstate[i] == NULL) {
+			DPU_ERROR("DPU plane state of plane id %d is NULL\n",
+				drm_state[i]->plane->base.id);
+			return -EINVAL;
+		}
+
+		src[i].x1 = drm_state[i]->src_x >> 16;
+		src[i].y1 = drm_state[i]->src_y >> 16;
+		src[i].x2 = src[i].x1 + (drm_state[i]->src_w >> 16);
+		src[i].y2 = src[i].y1 + (drm_state[i]->src_h >> 16);
+
+		dst[i] = drm_plane_state_dest(drm_state[i]);
+
+		if (drm_rect_calc_hscale(&src[i], &dst[i], 1, 1) != 1 ||
+		    drm_rect_calc_vscale(&src[i], &dst[i], 1, 1) != 1) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"scaling is not supported in multirect mode\n");
+			return -EINVAL;
+		}
+
+		if (DPU_FORMAT_IS_YUV(fmt[i])) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"Unsupported format for multirect mode\n");
+			return -EINVAL;
+		}
+
+		/**
+		 * SSPP PD_MEM is split half - one for each RECT.
+		 * Tiled formats need 5 lines of buffering while fetching
+		 * whereas linear formats need only 2 lines.
+		 * So we cannot support more than half of the supported SSPP
+		 * width for tiled formats.
+		 */
+		width_threshold = dpu_plane[i]->pipe_sblk->common->maxlinewidth;
+		if (has_tiled_rect)
+			width_threshold /= 2;
+
+		if (parallel_fetch_qualified &&
+		    drm_rect_width(&src[i]) > width_threshold)
+			parallel_fetch_qualified = false;
+
+	}
+
+	/* Validate RECT's and set the mode */
+
+	/* Prefer PARALLEL FETCH Mode over TIME_MX Mode */
+	if (parallel_fetch_qualified) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+
+		goto done;
+	}
+
+	/* TIME_MX Mode */
+	buffer_lines = 2 * max_tile_height;
+
+	if (dst[R1].y1 >= dst[R0].y2 + buffer_lines ||
+	    dst[R0].y1 >= dst[R1].y2 + buffer_lines) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+	} else {
+		DPU_ERROR(
+			"No multirect mode possible for the planes (%d - %d)\n",
+			drm_state[R0]->plane->base.id,
+			drm_state[R1]->plane->base.id);
+		return -EINVAL;
+	}
+
+done:
+	if (dpu_plane[R0]->is_virtual) {
+		pstate[R0]->multirect_index = DPU_SSPP_RECT_1;
+		pstate[R1]->multirect_index = DPU_SSPP_RECT_0;
+	} 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);
+	DPU_DEBUG_PLANE(dpu_plane[R1], "R1: %d - %d\n",
+		pstate[R1]->multirect_mode, pstate[R1]->multirect_index);
+	return 0;
+}
+
+/**
+ * dpu_plane_get_ctl_flush - get control flush for the given plane
+ * @plane: Pointer to drm plane structure
+ * @ctl: Pointer to hardware control driver
+ * @flush_sspp: Pointer to sspp flush control word
+ */
+void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl,
+		u32 *flush_sspp)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !flush_sspp) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	pstate = to_dpu_plane_state(plane->state);
+
+	*flush_sspp = ctl->ops.get_bitmask_sspp(ctl, dpu_plane_pipe(plane));
+}
+
+static int dpu_plane_prepare_fb(struct drm_plane *plane,
+		struct drm_plane_state *new_state)
+{
+	struct drm_framebuffer *fb = new_state->fb;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *pstate = to_dpu_plane_state(new_state);
+	struct dpu_hw_fmt_layout layout;
+	struct drm_gem_object *obj;
+	struct msm_gem_object *msm_obj;
+	struct dma_fence *fence;
+	struct msm_gem_address_space *aspace;
+	int ret;
+
+	if (!new_state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", fb->base.id);
+
+	ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "Failed to get aspace\n");
+		return ret;
+	}
+
+	/* cache aspace */
+	pstate->aspace = aspace;
+
+	/*
+	 * TODO: Need to sort out the msm_framebuffer_prepare() call below so
+	 *       we can use msm_atomic_prepare_fb() instead of doing the
+	 *       implicit fence and fb prepare by hand here.
+	 */
+	obj = msm_framebuffer_bo(new_state->fb, 0);
+	msm_obj = to_msm_bo(obj);
+	fence = reservation_object_get_excl_rcu(msm_obj->resv);
+	if (fence)
+		drm_atomic_set_fence_for_plane(new_state, fence);
+
+	if (pstate->aspace) {
+		ret = msm_framebuffer_prepare(new_state->fb,
+				pstate->aspace);
+		if (ret) {
+			DPU_ERROR("failed to prepare framebuffer\n");
+			return ret;
+		}
+	}
+
+	/* validate framebuffer layout before commit */
+	ret = dpu_format_populate_layout(pstate->aspace,
+			new_state->fb, &layout);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dpu_plane_cleanup_fb(struct drm_plane *plane,
+		struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *old_pstate;
+
+	if (!old_state || !old_state->fb)
+		return;
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id);
+
+	msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace);
+}
+
+static bool dpu_plane_validate_src(struct drm_rect *src,
+				   struct drm_rect *fb_rect,
+				   uint32_t min_src_size)
+{
+	/* Ensure fb size is supported */
+	if (drm_rect_width(fb_rect) > MAX_IMG_WIDTH ||
+	    drm_rect_height(fb_rect) > MAX_IMG_HEIGHT)
+		return false;
+
+	/* Ensure src rect is above the minimum size */
+	if (drm_rect_width(src) < min_src_size ||
+	    drm_rect_height(src) < min_src_size)
+		return false;
+
+	/* Ensure src is fully encapsulated in fb */
+	return drm_rect_intersect(fb_rect, src) &&
+		drm_rect_equals(fb_rect, src);
+}
+
+static int dpu_plane_sspp_atomic_check(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	int ret = 0;
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	const struct dpu_format *fmt;
+	struct drm_rect src, dst, fb_rect = { 0 };
+	uint32_t max_upscale = 1, max_downscale = 1;
+	uint32_t min_src_size, max_linewidth;
+	int hscale = 1, vscale = 1;
+
+	if (!plane || !state) {
+		DPU_ERROR("invalid arg(s), plane %d state %d\n",
+				plane != 0, state != 0);
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(state);
+
+	if (!pdpu->pipe_sblk) {
+		DPU_ERROR_PLANE(pdpu, "invalid catalog\n");
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	src.x1 = state->src_x >> 16;
+	src.y1 = state->src_y >> 16;
+	src.x2 = src.x1 + (state->src_w >> 16);
+	src.y2 = src.y1 + (state->src_h >> 16);
+
+	dst = drm_plane_state_dest(state);
+
+	fb_rect.x2 = state->fb->width;
+	fb_rect.y2 = state->fb->height;
+
+	max_linewidth = pdpu->pipe_sblk->common->maxlinewidth;
+
+	if (pdpu->features & DPU_SSPP_SCALER) {
+		max_downscale = pdpu->pipe_sblk->maxdwnscale;
+		max_upscale = pdpu->pipe_sblk->maxupscale;
+	}
+	if (drm_rect_width(&src) < drm_rect_width(&dst))
+		hscale = drm_rect_calc_hscale(&src, &dst, 1, max_upscale);
+	else
+		hscale = drm_rect_calc_hscale(&dst, &src, 1, max_downscale);
+	if (drm_rect_height(&src) < drm_rect_height(&dst))
+		vscale = drm_rect_calc_vscale(&src, &dst, 1, max_upscale);
+	else
+		vscale = drm_rect_calc_vscale(&dst, &src, 1, max_downscale);
+
+	DPU_DEBUG_PLANE(pdpu, "check %d -> %d\n",
+		dpu_plane_enabled(plane->state), dpu_plane_enabled(state));
+
+	if (!dpu_plane_enabled(state))
+		goto exit;
+
+	fmt = to_dpu_format(msm_framebuffer_format(state->fb));
+
+	min_src_size = DPU_FORMAT_IS_YUV(fmt) ? 2 : 1;
+
+	if (DPU_FORMAT_IS_YUV(fmt) &&
+		(!(pdpu->features & DPU_SSPP_SCALER) ||
+		 !(pdpu->features & (BIT(DPU_SSPP_CSC)
+		 | BIT(DPU_SSPP_CSC_10BIT))))) {
+		DPU_ERROR_PLANE(pdpu,
+				"plane doesn't have scaler/csc for yuv\n");
+		ret = -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",
+				DRM_RECT_ARG(&src));
+		ret = -E2BIG;
+
+	/* valid yuv image */
+	} else if (DPU_FORMAT_IS_YUV(fmt) &&
+		   (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",
+				DRM_RECT_ARG(&src));
+		ret = -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",
+				DRM_RECT_ARG(&dst));
+		ret = -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",
+				DRM_RECT_ARG(&src), max_linewidth);
+		ret = -E2BIG;
+
+	/* check scaler capability */
+	} else if (hscale < 0 || vscale < 0) {
+		DPU_ERROR_PLANE(pdpu, "invalid scaling requested src="
+				DRM_RECT_FMT " dst=" DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src), DRM_RECT_ARG(&dst));
+		ret = -E2BIG;
+	}
+
+exit:
+	return ret;
+}
+
+static int dpu_plane_atomic_check(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	if (!state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(to_dpu_plane(plane), "\n");
+
+	return dpu_plane_sspp_atomic_check(plane, state);
+}
+
+void dpu_plane_flush(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+
+	/*
+	 * These updates have to be done immediately before the plane flush
+	 * timing, and may not be moved to the atomic_update/mode_set functions.
+	 */
+	if (pdpu->is_error)
+		/* force white frame with 100% alpha pipe output on error */
+		_dpu_plane_color_fill(pdpu, 0xFFFFFF, 0xFF);
+	else if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG)
+		/* force 100% alpha */
+		_dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF);
+	else if (pdpu->pipe_hw && pdpu->csc_ptr && pdpu->pipe_hw->ops.setup_csc)
+		pdpu->pipe_hw->ops.setup_csc(pdpu->pipe_hw, pdpu->csc_ptr);
+
+	/* flag h/w flush complete */
+	if (plane->state)
+		pstate->pending = false;
+}
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = error;
+}
+
+static int dpu_plane_sspp_atomic_update(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	uint32_t nplanes, src_flags;
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_pstate;
+	const struct dpu_format *fmt;
+	struct drm_crtc *crtc;
+	struct drm_framebuffer *fb;
+	struct drm_rect src, dst;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return -EINVAL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return -EINVAL;
+	} else if (!old_state) {
+		DPU_ERROR("invalid old state\n");
+		return -EINVAL;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	state = plane->state;
+
+	pstate = to_dpu_plane_state(state);
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	crtc = state->crtc;
+	fb = state->fb;
+	if (!crtc || !fb) {
+		DPU_ERROR_PLANE(pdpu, "invalid crtc %d or fb %d\n",
+				crtc != 0, fb != 0);
+		return -EINVAL;
+	}
+	fmt = to_dpu_format(msm_framebuffer_format(fb));
+	nplanes = fmt->num_planes;
+
+	memset(&(pdpu->pipe_cfg), 0, sizeof(struct dpu_hw_pipe_cfg));
+
+	_dpu_plane_set_scanout(plane, pstate, &pdpu->pipe_cfg, fb);
+
+	pstate->pending = true;
+
+	pdpu->is_rt_pipe = (dpu_crtc_get_client_type(crtc) != NRT_CLIENT);
+	_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+	src.x1 = state->src_x >> 16;
+	src.y1 = state->src_y >> 16;
+	src.x2 = src.x1 + (state->src_w >> 16);
+	src.y2 = src.y1 + (state->src_h >> 16);
+
+	dst = drm_plane_state_dest(state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u] " DRM_RECT_FMT "->crtc%u " DRM_RECT_FMT
+			", %4.4s ubwc %d\n", fb->base.id, DRM_RECT_ARG(&src),
+			crtc->base.id, DRM_RECT_ARG(&dst),
+			(char *)&fmt->base.pixel_format,
+			DPU_FORMAT_IS_UBWC(fmt));
+
+	pdpu->pipe_cfg.src_rect = src;
+	pdpu->pipe_cfg.dst_rect = dst;
+
+	_dpu_plane_setup_scaler(pdpu, pstate, fmt, false);
+
+	/* override for color fill */
+	if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG) {
+		/* skip remaining processing on color fill */
+		return 0;
+	}
+
+	if (pdpu->pipe_hw->ops.setup_rects) {
+		pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+				&pdpu->pipe_cfg,
+				pstate->multirect_index);
+	}
+
+	if (pdpu->pipe_hw->ops.setup_pe &&
+			(pstate->multirect_index != DPU_SSPP_RECT_1))
+		pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+				&pstate->pixel_ext);
+
+	/**
+	 * when programmed in multirect mode, scalar block will be
+	 * bypassed. Still we need to update alpha and bitwidth
+	 * ONLY for RECT0
+	 */
+	if (pdpu->pipe_hw->ops.setup_scaler &&
+			pstate->multirect_index != DPU_SSPP_RECT_1)
+		pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+				&pdpu->pipe_cfg, &pstate->pixel_ext,
+				&pstate->scaler3_cfg);
+
+	if (pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(
+				pdpu->pipe_hw,
+				pstate->multirect_index,
+				pstate->multirect_mode);
+
+	if (pdpu->pipe_hw->ops.setup_format) {
+		src_flags = 0x0;
+
+		/* update format */
+		pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw, fmt, src_flags,
+				pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_cdp) {
+			struct dpu_hw_pipe_cdp_cfg *cdp_cfg = &pstate->cdp_cfg;
+
+			memset(cdp_cfg, 0, sizeof(struct dpu_hw_pipe_cdp_cfg));
+
+			cdp_cfg->enable = pdpu->catalog->perf.cdp_cfg
+					[DPU_PERF_CDP_USAGE_RT].rd_enable;
+			cdp_cfg->ubwc_meta_enable =
+					DPU_FORMAT_IS_UBWC(fmt);
+			cdp_cfg->tile_amortize_enable =
+					DPU_FORMAT_IS_UBWC(fmt) ||
+					DPU_FORMAT_IS_TILE(fmt);
+			cdp_cfg->preload_ahead = DPU_SSPP_CDP_PRELOAD_AHEAD_64;
+
+			pdpu->pipe_hw->ops.setup_cdp(pdpu->pipe_hw, cdp_cfg);
+		}
+
+		/* update csc */
+		if (DPU_FORMAT_IS_YUV(fmt))
+			_dpu_plane_setup_csc(pdpu);
+		else
+			pdpu->csc_ptr = 0;
+	}
+
+	_dpu_plane_set_qos_lut(plane, fb);
+	_dpu_plane_set_danger_lut(plane, fb);
+
+	if (plane->type != DRM_PLANE_TYPE_CURSOR) {
+		_dpu_plane_set_qos_ctrl(plane, true, DPU_PLANE_QOS_PANIC_CTRL);
+		_dpu_plane_set_ot_limit(plane, crtc);
+	}
+
+	_dpu_plane_set_qos_remap(plane);
+	return 0;
+}
+
+static void _dpu_plane_atomic_disable(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return;
+	} else if (!old_state) {
+		DPU_ERROR("invalid old state\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	state = plane->state;
+	pstate = to_dpu_plane_state(state);
+
+	trace_dpu_plane_disable(DRMID(plane), is_dpu_plane_virtual(plane),
+				pstate->multirect_mode);
+
+	pstate->pending = true;
+
+	if (is_dpu_plane_virtual(plane) &&
+			pdpu->pipe_hw && pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(pdpu->pipe_hw,
+				DPU_SSPP_RECT_SOLO, DPU_SSPP_MULTIRECT_NONE);
+}
+
+static void dpu_plane_atomic_update(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = false;
+	state = plane->state;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (!dpu_plane_sspp_enabled(state)) {
+		_dpu_plane_atomic_disable(plane, old_state);
+	} else {
+		int ret;
+
+		ret = dpu_plane_sspp_atomic_update(plane, old_state);
+		/* atomic_check should have ensured that this doesn't fail */
+		WARN_ON(ret < 0);
+	}
+}
+
+void dpu_plane_restore(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* last plane state is same as current state */
+	dpu_plane_atomic_update(plane, plane->state);
+}
+
+static void dpu_plane_destroy(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu = plane ? to_dpu_plane(plane) : NULL;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (pdpu) {
+		_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+		mutex_destroy(&pdpu->lock);
+
+		drm_plane_helper_disable(plane, NULL);
+
+		/* this will destroy the states as well */
+		drm_plane_cleanup(plane);
+
+		if (pdpu->pipe_hw)
+			dpu_hw_sspp_destroy(pdpu->pipe_hw);
+
+		kfree(pdpu);
+	}
+}
+
+static void dpu_plane_destroy_state(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !state) {
+		DPU_ERROR("invalid arg(s), plane %d state %d\n",
+				plane != 0, state != 0);
+		return;
+	}
+
+	pstate = to_dpu_plane_state(state);
+
+	/* remove ref count for frame buffers */
+	if (state->fb)
+		drm_framebuffer_put(state->fb);
+
+	kfree(pstate);
+}
+
+static struct drm_plane_state *
+dpu_plane_duplicate_state(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return NULL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return NULL;
+	}
+
+	old_state = to_dpu_plane_state(plane->state);
+	pdpu = to_dpu_plane(plane);
+	pstate = kmemdup(old_state, sizeof(*old_state), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return NULL;
+	}
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	pstate->pending = false;
+
+	__drm_atomic_helper_plane_duplicate_state(plane, &pstate->base);
+
+	return &pstate->base;
+}
+
+static void dpu_plane_reset(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* remove previous state, if present */
+	if (plane->state) {
+		dpu_plane_destroy_state(plane, plane->state);
+		plane->state = 0;
+	}
+
+	pstate = kzalloc(sizeof(*pstate), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return;
+	}
+
+	pstate->base.plane = plane;
+
+	plane->state = &pstate->base;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static ssize_t _dpu_plane_danger_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	struct dpu_mdss_cfg *cfg = kms->catalog;
+	int len = 0;
+	char buf[40] = {'\0'};
+
+	if (!cfg)
+		return -ENODEV;
+
+	if (*ppos)
+		return 0; /* the end */
+
+	len = snprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl);
+	if (len < 0 || len >= sizeof(buf))
+		return 0;
+
+	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
+		return -EFAULT;
+
+	*ppos += len;   /* increase offset */
+
+	return len;
+}
+
+static void _dpu_plane_set_danger_state(struct dpu_kms *kms, bool enable)
+{
+	struct drm_plane *plane;
+
+	drm_for_each_plane(plane, kms->dev) {
+		if (plane->fb && plane->state) {
+			dpu_plane_danger_signal_ctrl(plane, enable);
+			DPU_DEBUG("plane:%d img:%dx%d ",
+				plane->base.id, plane->fb->width,
+				plane->fb->height);
+			DPU_DEBUG("src[%d,%d,%d,%d] dst[%d,%d,%d,%d]\n",
+				plane->state->src_x >> 16,
+				plane->state->src_y >> 16,
+				plane->state->src_w >> 16,
+				plane->state->src_h >> 16,
+				plane->state->crtc_x, plane->state->crtc_y,
+				plane->state->crtc_w, plane->state->crtc_h);
+		} else {
+			DPU_DEBUG("Inactive plane:%d\n", plane->base.id);
+		}
+	}
+}
+
+static ssize_t _dpu_plane_danger_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	struct dpu_mdss_cfg *cfg = kms->catalog;
+	int disable_panic;
+	char buf[10];
+
+	if (!cfg)
+		return -EFAULT;
+
+	if (count >= sizeof(buf))
+		return -EFAULT;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[count] = 0;	/* end of string */
+
+	if (kstrtoint(buf, 0, &disable_panic))
+		return -EFAULT;
+
+	if (disable_panic) {
+		/* Disable panic signal for all active pipes */
+		DPU_DEBUG("Disabling danger:\n");
+		_dpu_plane_set_danger_state(kms, false);
+		kms->has_danger_ctrl = false;
+	} else {
+		/* Enable panic signal for all active pipes */
+		DPU_DEBUG("Enabling danger:\n");
+		kms->has_danger_ctrl = true;
+		_dpu_plane_set_danger_state(kms, true);
+	}
+
+	return count;
+}
+
+static const struct file_operations dpu_plane_danger_enable = {
+	.open = simple_open,
+	.read = _dpu_plane_danger_read,
+	.write = _dpu_plane_danger_write,
+};
+
+static int _dpu_plane_init_debugfs(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_kms *kms;
+	struct msm_drm_private *priv;
+	const struct dpu_sspp_sub_blks *sblk = 0;
+	const struct dpu_sspp_cfg *cfg = 0;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+
+	if (pdpu && pdpu->pipe_hw)
+		cfg = pdpu->pipe_hw->cap;
+	if (cfg)
+		sblk = cfg->sblk;
+
+	if (!sblk)
+		return 0;
+
+	/* create overall sub-directory for the pipe */
+	pdpu->debugfs_root =
+		debugfs_create_dir(pdpu->pipe_name,
+				plane->dev->primary->debugfs_root);
+
+	if (!pdpu->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_x32("features", 0600,
+			pdpu->debugfs_root, &pdpu->features);
+
+	/* add register dump support */
+	dpu_debugfs_setup_regset32(&pdpu->debugfs_src,
+			sblk->src_blk.base + cfg->base,
+			sblk->src_blk.len,
+			kms);
+	dpu_debugfs_create_regset32("src_blk", 0400,
+			pdpu->debugfs_root, &pdpu->debugfs_src);
+
+	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2)) {
+		dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler,
+				sblk->scaler_blk.base + cfg->base,
+				sblk->scaler_blk.len,
+				kms);
+		dpu_debugfs_create_regset32("scaler_blk", 0400,
+				pdpu->debugfs_root,
+				&pdpu->debugfs_scaler);
+		debugfs_create_bool("default_scaling",
+				0600,
+				pdpu->debugfs_root,
+				&pdpu->debugfs_default_scale);
+	}
+
+	if (cfg->features & BIT(DPU_SSPP_CSC) ||
+			cfg->features & BIT(DPU_SSPP_CSC_10BIT)) {
+		dpu_debugfs_setup_regset32(&pdpu->debugfs_csc,
+				sblk->csc_blk.base + cfg->base,
+				sblk->csc_blk.len,
+				kms);
+		dpu_debugfs_create_regset32("csc_blk", 0400,
+				pdpu->debugfs_root, &pdpu->debugfs_csc);
+	}
+
+	debugfs_create_u32("xin_id",
+			0400,
+			pdpu->debugfs_root,
+			(u32 *) &cfg->xin_id);
+	debugfs_create_u32("clk_ctrl",
+			0400,
+			pdpu->debugfs_root,
+			(u32 *) &cfg->clk_ctrl);
+	debugfs_create_x32("creq_vblank",
+			0600,
+			pdpu->debugfs_root,
+			(u32 *) &sblk->creq_vblank);
+	debugfs_create_x32("danger_vblank",
+			0600,
+			pdpu->debugfs_root,
+			(u32 *) &sblk->danger_vblank);
+
+	debugfs_create_file("disable_danger",
+			0600,
+			pdpu->debugfs_root,
+			kms, &dpu_plane_danger_enable);
+
+	return 0;
+}
+
+static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+	pdpu = to_dpu_plane(plane);
+
+	debugfs_remove_recursive(pdpu->debugfs_root);
+}
+#else
+static int _dpu_plane_init_debugfs(struct drm_plane *plane)
+{
+	return 0;
+}
+static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
+{
+}
+#endif
+
+static int dpu_plane_late_register(struct drm_plane *plane)
+{
+	return _dpu_plane_init_debugfs(plane);
+}
+
+static void dpu_plane_early_unregister(struct drm_plane *plane)
+{
+	_dpu_plane_destroy_debugfs(plane);
+}
+
+static const struct drm_plane_funcs dpu_plane_funcs = {
+		.update_plane = drm_atomic_helper_update_plane,
+		.disable_plane = drm_atomic_helper_disable_plane,
+		.destroy = dpu_plane_destroy,
+		.reset = dpu_plane_reset,
+		.atomic_duplicate_state = dpu_plane_duplicate_state,
+		.atomic_destroy_state = dpu_plane_destroy_state,
+		.late_register = dpu_plane_late_register,
+		.early_unregister = dpu_plane_early_unregister,
+};
+
+static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = {
+		.prepare_fb = dpu_plane_prepare_fb,
+		.cleanup_fb = dpu_plane_cleanup_fb,
+		.atomic_check = dpu_plane_atomic_check,
+		.atomic_update = dpu_plane_atomic_update,
+};
+
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->pipe : SSPP_NONE;
+}
+
+bool is_dpu_plane_virtual(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->is_virtual : false;
+}
+
+/* initialize plane */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, bool primary_plane,
+		unsigned long possible_crtcs, u32 master_plane_id)
+{
+	struct drm_plane *plane = NULL, *master_plane = NULL;
+	const struct dpu_format_extended *format_list;
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv;
+	struct dpu_kms *kms;
+	enum drm_plane_type type;
+	int zpos_max = DPU_ZPOS_MAX;
+	int ret = -EINVAL;
+
+	if (!dev) {
+		DPU_ERROR("[%u]device is NULL\n", pipe);
+		goto exit;
+	}
+
+	priv = dev->dev_private;
+	if (!priv) {
+		DPU_ERROR("[%u]private data is NULL\n", pipe);
+		goto exit;
+	}
+
+	if (!priv->kms) {
+		DPU_ERROR("[%u]invalid KMS reference\n", pipe);
+		goto exit;
+	}
+	kms = to_dpu_kms(priv->kms);
+
+	if (!kms->catalog) {
+		DPU_ERROR("[%u]invalid catalog reference\n", pipe);
+		goto exit;
+	}
+
+	/* create and zero local structure */
+	pdpu = kzalloc(sizeof(*pdpu), GFP_KERNEL);
+	if (!pdpu) {
+		DPU_ERROR("[%u]failed to allocate local plane struct\n", pipe);
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	/* cache local stuff for later */
+	plane = &pdpu->base;
+	pdpu->pipe = pipe;
+	pdpu->is_virtual = (master_plane_id != 0);
+	INIT_LIST_HEAD(&pdpu->mplane_list);
+	master_plane = drm_plane_find(dev, NULL, master_plane_id);
+	if (master_plane) {
+		struct dpu_plane *mpdpu = to_dpu_plane(master_plane);
+
+		list_add_tail(&pdpu->mplane_list, &mpdpu->mplane_list);
+	}
+
+	/* initialize underlying h/w driver */
+	pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog,
+							master_plane_id != 0);
+	if (IS_ERR(pdpu->pipe_hw)) {
+		DPU_ERROR("[%u]SSPP init failed\n", pipe);
+		ret = PTR_ERR(pdpu->pipe_hw);
+		goto clean_plane;
+	} else if (!pdpu->pipe_hw->cap || !pdpu->pipe_hw->cap->sblk) {
+		DPU_ERROR("[%u]SSPP init returned invalid cfg\n", pipe);
+		goto clean_sspp;
+	}
+
+	/* cache features mask for later */
+	pdpu->features = pdpu->pipe_hw->cap->features;
+	pdpu->pipe_sblk = pdpu->pipe_hw->cap->sblk;
+	if (!pdpu->pipe_sblk) {
+		DPU_ERROR("[%u]invalid sblk\n", pipe);
+		goto clean_sspp;
+	}
+
+	if (!master_plane_id)
+		format_list = pdpu->pipe_sblk->format_list;
+	else
+		format_list = pdpu->pipe_sblk->virt_format_list;
+
+	pdpu->nformats = dpu_populate_formats(format_list,
+				pdpu->formats,
+				0,
+				ARRAY_SIZE(pdpu->formats));
+
+	if (!pdpu->nformats) {
+		DPU_ERROR("[%u]no valid formats for plane\n", pipe);
+		goto clean_sspp;
+	}
+
+	if (pdpu->features & BIT(DPU_SSPP_CURSOR))
+		type = DRM_PLANE_TYPE_CURSOR;
+	else if (primary_plane)
+		type = DRM_PLANE_TYPE_PRIMARY;
+	else
+		type = DRM_PLANE_TYPE_OVERLAY;
+	ret = drm_universal_plane_init(dev, plane, 0xff, &dpu_plane_funcs,
+				pdpu->formats, pdpu->nformats,
+				NULL, type, NULL);
+	if (ret)
+		goto clean_sspp;
+
+	pdpu->catalog = kms->catalog;
+
+	if (kms->catalog->mixer_count &&
+		kms->catalog->mixer[0].sblk->maxblendstages) {
+		zpos_max = kms->catalog->mixer[0].sblk->maxblendstages - 1;
+		if (zpos_max > DPU_STAGE_MAX - DPU_STAGE_0 - 1)
+			zpos_max = DPU_STAGE_MAX - DPU_STAGE_0 - 1;
+	}
+
+	ret = drm_plane_create_zpos_property(plane, 0, 0, zpos_max);
+	if (ret)
+		DPU_ERROR("failed to install zpos property, rc = %d\n", ret);
+
+	/* success! finalize initialization */
+	drm_plane_helper_add(plane, &dpu_plane_helper_funcs);
+
+	/* save user friendly pipe name for later */
+	snprintf(pdpu->pipe_name, DPU_NAME_SIZE, "plane%u", plane->base.id);
+
+	mutex_init(&pdpu->lock);
+
+	DPU_DEBUG("%s created for pipe:%u id:%u virtual:%u\n", pdpu->pipe_name,
+					pipe, plane->base.id, master_plane_id);
+	return plane;
+
+clean_sspp:
+	if (pdpu && pdpu->pipe_hw)
+		dpu_hw_sspp_destroy(pdpu->pipe_hw);
+clean_plane:
+	kfree(pdpu);
+exit:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
new file mode 100644
index 000000000000..f6fe6ddc7a3a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DPU_PLANE_H_
+#define _DPU_PLANE_H_
+
+#include <drm/drm_crtc.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_sspp.h"
+
+/**
+ * struct dpu_plane_state: Define dpu extension of drm plane state object
+ * @base:	base drm plane state object
+ * @property_state: Local storage for msm_prop properties
+ * @property_values:	cached plane property values
+ * @aspace:	pointer to address space for input/output buffers
+ * @input_fence:	dereferenced input fence pointer
+ * @stage:	assigned by crtc blender
+ * @multirect_index: index of the rectangle of SSPP
+ * @multirect_mode: parallel or time multiplex multirect mode
+ * @pending:	whether the current update is still pending
+ * @scaler3_cfg: configuration data for scaler3
+ * @pixel_ext: configuration data for pixel extensions
+ * @scaler_check_state: indicates status of user provided pixel extension data
+ * @cdp_cfg:	CDP configuration
+ */
+struct dpu_plane_state {
+	struct drm_plane_state base;
+	struct msm_gem_address_space *aspace;
+	void *input_fence;
+	enum dpu_stage stage;
+	uint32_t multirect_index;
+	uint32_t multirect_mode;
+	bool pending;
+
+	/* scaler configuration */
+	struct dpu_hw_scaler3_cfg scaler3_cfg;
+	struct dpu_hw_pixel_ext pixel_ext;
+
+	struct dpu_hw_pipe_cdp_cfg cdp_cfg;
+};
+
+/**
+ * struct dpu_multirect_plane_states: Defines multirect pair of drm plane states
+ * @r0: drm plane configured on rect 0
+ * @r1: drm plane configured on rect 1
+ */
+struct dpu_multirect_plane_states {
+	const struct drm_plane_state *r0;
+	const struct drm_plane_state *r1;
+};
+
+#define to_dpu_plane_state(x) \
+	container_of(x, struct dpu_plane_state, base)
+
+/**
+ * dpu_plane_pipe - return sspp identifier for the given plane
+ * @plane:   Pointer to DRM plane object
+ * Returns: sspp identifier of the given plane
+ */
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane);
+
+/**
+ * is_dpu_plane_virtual - check for virtual plane
+ * @plane: Pointer to DRM plane object
+ * returns: true - if the plane is virtual
+ *          false - if the plane is primary
+ */
+bool is_dpu_plane_virtual(struct drm_plane *plane);
+
+/**
+ * dpu_plane_get_ctl_flush - get control flush mask
+ * @plane:   Pointer to DRM plane object
+ * @ctl: Pointer to control hardware
+ * @flush_sspp: Pointer to sspp flush control word
+ */
+void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl,
+		u32 *flush_sspp);
+
+/**
+ * dpu_plane_restore - restore hw state if previously power collapsed
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_restore(struct drm_plane *plane);
+
+/**
+ * dpu_plane_flush - final plane operations before commit flush
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_flush(struct drm_plane *plane);
+
+/**
+ * dpu_plane_kickoff - final plane operations before commit kickoff
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_kickoff(struct drm_plane *plane);
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error);
+
+/**
+ * dpu_plane_init - create new dpu plane for the given pipe
+ * @dev:   Pointer to DRM device
+ * @pipe:  dpu hardware pipe identifier
+ * @primary_plane: true if this pipe is primary plane for crtc
+ * @possible_crtcs: bitmask of crtc that can be attached to the given pipe
+ * @master_plane_id: primary plane id of a multirect pipe. 0 value passed for
+ *                   a regular plane initialization. A non-zero primary plane
+ *                   id will be passed for a virtual pipe initialization.
+ *
+ */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, bool primary_plane,
+		unsigned long possible_crtcs, u32 master_plane_id);
+
+/**
+ * dpu_plane_validate_multirecti_v2 - validate the multirect planes
+ *				      against hw limitations
+ * @plane: drm plate states of the multirect pair
+ */
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane);
+
+/**
+ * dpu_plane_clear_multirect - clear multirect bits for the given pipe
+ * @drm_state: Pointer to DRM plane state
+ */
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state);
+
+/**
+ * dpu_plane_wait_input_fence - wait for input fence object
+ * @plane:   Pointer to DRM plane object
+ * @wait_ms: Wait timeout value
+ * Returns: Zero on success
+ */
+int dpu_plane_wait_input_fence(struct drm_plane *plane, uint32_t wait_ms);
+
+/**
+ * dpu_plane_color_fill - enables color fill on plane
+ * @plane:  Pointer to DRM plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+int dpu_plane_color_fill(struct drm_plane *plane,
+		uint32_t color, uint32_t alpha);
+
+/**
+ * dpu_plane_set_revalidate - sets revalidate flag which forces a full
+ *	validation of the plane properties in the next atomic check
+ * @plane: Pointer to DRM plane object
+ * @enable: Boolean to set/unset the flag
+ */
+void dpu_plane_set_revalidate(struct drm_plane *plane, bool enable);
+
+#endif /* _DPU_PLANE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
new file mode 100644
index 000000000000..a68f1249388c
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
@@ -0,0 +1,249 @@
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d]: " fmt, __func__, __LINE__
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/of_platform.h>
+
+#include "dpu_power_handle.h"
+#include "dpu_trace.h"
+
+static const char *data_bus_name[DPU_POWER_HANDLE_DBUS_ID_MAX] = {
+	[DPU_POWER_HANDLE_DBUS_ID_MNOC] = "qcom,dpu-data-bus",
+	[DPU_POWER_HANDLE_DBUS_ID_LLCC] = "qcom,dpu-llcc-bus",
+	[DPU_POWER_HANDLE_DBUS_ID_EBI] = "qcom,dpu-ebi-bus",
+};
+
+const char *dpu_power_handle_get_dbus_name(u32 bus_id)
+{
+	if (bus_id < DPU_POWER_HANDLE_DBUS_ID_MAX)
+		return data_bus_name[bus_id];
+
+	return NULL;
+}
+
+static void dpu_power_event_trigger_locked(struct dpu_power_handle *phandle,
+		u32 event_type)
+{
+	struct dpu_power_event *event;
+
+	list_for_each_entry(event, &phandle->event_list, list) {
+		if (event->event_type & event_type)
+			event->cb_fnc(event_type, event->usr);
+	}
+}
+
+struct dpu_power_client *dpu_power_client_create(
+	struct dpu_power_handle *phandle, char *client_name)
+{
+	struct dpu_power_client *client;
+	static u32 id;
+
+	if (!client_name || !phandle) {
+		pr_err("client name is null or invalid power data\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	client = kzalloc(sizeof(struct dpu_power_client), GFP_KERNEL);
+	if (!client)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_lock(&phandle->phandle_lock);
+	strlcpy(client->name, client_name, MAX_CLIENT_NAME_LEN);
+	client->usecase_ndx = VOTE_INDEX_DISABLE;
+	client->id = id;
+	client->active = true;
+	pr_debug("client %s created:%pK id :%d\n", client_name,
+		client, id);
+	id++;
+	list_add(&client->list, &phandle->power_client_clist);
+	mutex_unlock(&phandle->phandle_lock);
+
+	return client;
+}
+
+void dpu_power_client_destroy(struct dpu_power_handle *phandle,
+	struct dpu_power_client *client)
+{
+	if (!client  || !phandle) {
+		pr_err("reg bus vote: invalid client handle\n");
+	} else if (!client->active) {
+		pr_err("dpu power deinit already done\n");
+		kfree(client);
+	} else {
+		pr_debug("bus vote client %s destroyed:%pK id:%u\n",
+			client->name, client, client->id);
+		mutex_lock(&phandle->phandle_lock);
+		list_del_init(&client->list);
+		mutex_unlock(&phandle->phandle_lock);
+		kfree(client);
+	}
+}
+
+void dpu_power_resource_init(struct platform_device *pdev,
+	struct dpu_power_handle *phandle)
+{
+	phandle->dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&phandle->power_client_clist);
+	INIT_LIST_HEAD(&phandle->event_list);
+
+	mutex_init(&phandle->phandle_lock);
+}
+
+void dpu_power_resource_deinit(struct platform_device *pdev,
+	struct dpu_power_handle *phandle)
+{
+	struct dpu_power_client *curr_client, *next_client;
+	struct dpu_power_event *curr_event, *next_event;
+
+	if (!phandle || !pdev) {
+		pr_err("invalid input param\n");
+		return;
+	}
+
+	mutex_lock(&phandle->phandle_lock);
+	list_for_each_entry_safe(curr_client, next_client,
+			&phandle->power_client_clist, list) {
+		pr_err("cliend:%s-%d still registered with refcount:%d\n",
+				curr_client->name, curr_client->id,
+				curr_client->refcount);
+		curr_client->active = false;
+		list_del(&curr_client->list);
+	}
+
+	list_for_each_entry_safe(curr_event, next_event,
+			&phandle->event_list, list) {
+		pr_err("event:%d, client:%s still registered\n",
+				curr_event->event_type,
+				curr_event->client_name);
+		curr_event->active = false;
+		list_del(&curr_event->list);
+	}
+	mutex_unlock(&phandle->phandle_lock);
+}
+
+int dpu_power_resource_enable(struct dpu_power_handle *phandle,
+	struct dpu_power_client *pclient, bool enable)
+{
+	bool changed = false;
+	u32 max_usecase_ndx = VOTE_INDEX_DISABLE, prev_usecase_ndx;
+	struct dpu_power_client *client;
+
+	if (!phandle || !pclient) {
+		pr_err("invalid input argument\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&phandle->phandle_lock);
+	if (enable)
+		pclient->refcount++;
+	else if (pclient->refcount)
+		pclient->refcount--;
+
+	if (pclient->refcount)
+		pclient->usecase_ndx = VOTE_INDEX_LOW;
+	else
+		pclient->usecase_ndx = VOTE_INDEX_DISABLE;
+
+	list_for_each_entry(client, &phandle->power_client_clist, list) {
+		if (client->usecase_ndx < VOTE_INDEX_MAX &&
+		    client->usecase_ndx > max_usecase_ndx)
+			max_usecase_ndx = client->usecase_ndx;
+	}
+
+	if (phandle->current_usecase_ndx != max_usecase_ndx) {
+		changed = true;
+		prev_usecase_ndx = phandle->current_usecase_ndx;
+		phandle->current_usecase_ndx = max_usecase_ndx;
+	}
+
+	pr_debug("%pS: changed=%d current idx=%d request client %s id:%u enable:%d refcount:%d\n",
+		__builtin_return_address(0), changed, max_usecase_ndx,
+		pclient->name, pclient->id, enable, pclient->refcount);
+
+	if (!changed)
+		goto end;
+
+	if (enable) {
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_PRE_ENABLE);
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_POST_ENABLE);
+
+	} else {
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_PRE_DISABLE);
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_POST_DISABLE);
+	}
+
+end:
+	mutex_unlock(&phandle->phandle_lock);
+	return 0;
+}
+
+struct dpu_power_event *dpu_power_handle_register_event(
+		struct dpu_power_handle *phandle,
+		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
+		void *usr, char *client_name)
+{
+	struct dpu_power_event *event;
+
+	if (!phandle) {
+		pr_err("invalid power handle\n");
+		return ERR_PTR(-EINVAL);
+	} else if (!cb_fnc || !event_type) {
+		pr_err("no callback fnc or event type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	event = kzalloc(sizeof(struct dpu_power_event), GFP_KERNEL);
+	if (!event)
+		return ERR_PTR(-ENOMEM);
+
+	event->event_type = event_type;
+	event->cb_fnc = cb_fnc;
+	event->usr = usr;
+	strlcpy(event->client_name, client_name, MAX_CLIENT_NAME_LEN);
+	event->active = true;
+
+	mutex_lock(&phandle->phandle_lock);
+	list_add(&event->list, &phandle->event_list);
+	mutex_unlock(&phandle->phandle_lock);
+
+	return event;
+}
+
+void dpu_power_handle_unregister_event(
+		struct dpu_power_handle *phandle,
+		struct dpu_power_event *event)
+{
+	if (!phandle || !event) {
+		pr_err("invalid phandle or event\n");
+	} else if (!event->active) {
+		pr_err("power handle deinit already done\n");
+		kfree(event);
+	} else {
+		mutex_lock(&phandle->phandle_lock);
+		list_del_init(&event->list);
+		mutex_unlock(&phandle->phandle_lock);
+		kfree(event);
+	}
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
new file mode 100644
index 000000000000..344f74464eca
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
@@ -0,0 +1,225 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _DPU_POWER_HANDLE_H_
+#define _DPU_POWER_HANDLE_H_
+
+#define MAX_CLIENT_NAME_LEN 128
+
+#define DPU_POWER_HANDLE_ENABLE_BUS_AB_QUOTA	0
+#define DPU_POWER_HANDLE_DISABLE_BUS_AB_QUOTA	0
+#define DPU_POWER_HANDLE_ENABLE_BUS_IB_QUOTA	1600000000
+#define DPU_POWER_HANDLE_DISABLE_BUS_IB_QUOTA	0
+
+#include "dpu_io_util.h"
+
+/* event will be triggered before power handler disable */
+#define DPU_POWER_EVENT_PRE_DISABLE	0x1
+
+/* event will be triggered after power handler disable */
+#define DPU_POWER_EVENT_POST_DISABLE	0x2
+
+/* event will be triggered before power handler enable */
+#define DPU_POWER_EVENT_PRE_ENABLE	0x4
+
+/* event will be triggered after power handler enable */
+#define DPU_POWER_EVENT_POST_ENABLE	0x8
+
+/**
+ * mdss_bus_vote_type: register bus vote type
+ * VOTE_INDEX_DISABLE: removes the client vote
+ * VOTE_INDEX_LOW: keeps the lowest vote for register bus
+ * VOTE_INDEX_MAX: invalid
+ */
+enum mdss_bus_vote_type {
+	VOTE_INDEX_DISABLE,
+	VOTE_INDEX_LOW,
+	VOTE_INDEX_MAX,
+};
+
+/**
+ * enum dpu_power_handle_data_bus_client - type of axi bus clients
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT: core real-time bus client
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT: core non-real-time bus client
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX: maximum number of bus client type
+ */
+enum dpu_power_handle_data_bus_client {
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT,
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT,
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX
+};
+
+/**
+ * enum DPU_POWER_HANDLE_DBUS_ID - data bus identifier
+ * @DPU_POWER_HANDLE_DBUS_ID_MNOC: DPU/MNOC data bus
+ * @DPU_POWER_HANDLE_DBUS_ID_LLCC: MNOC/LLCC data bus
+ * @DPU_POWER_HANDLE_DBUS_ID_EBI: LLCC/EBI data bus
+ */
+enum DPU_POWER_HANDLE_DBUS_ID {
+	DPU_POWER_HANDLE_DBUS_ID_MNOC,
+	DPU_POWER_HANDLE_DBUS_ID_LLCC,
+	DPU_POWER_HANDLE_DBUS_ID_EBI,
+	DPU_POWER_HANDLE_DBUS_ID_MAX,
+};
+
+/**
+ * struct dpu_power_client: stores the power client for dpu driver
+ * @name:	name of the client
+ * @usecase_ndx: current regs bus vote type
+ * @refcount:	current refcount if multiple modules are using same
+ *              same client for enable/disable. Power module will
+ *              aggregate the refcount and vote accordingly for this
+ *              client.
+ * @id:		assigned during create. helps for debugging.
+ * @list:	list to attach power handle master list
+ * @ab:         arbitrated bandwidth for each bus client
+ * @ib:         instantaneous bandwidth for each bus client
+ * @active:	inidcates the state of dpu power handle
+ */
+struct dpu_power_client {
+	char name[MAX_CLIENT_NAME_LEN];
+	short usecase_ndx;
+	short refcount;
+	u32 id;
+	struct list_head list;
+	u64 ab[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
+	u64 ib[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
+	bool active;
+};
+
+/*
+ * struct dpu_power_event - local event registration structure
+ * @client_name: name of the client registering
+ * @cb_fnc: pointer to desired callback function
+ * @usr: user pointer to pass to callback event trigger
+ * @event: refer to DPU_POWER_HANDLE_EVENT_*
+ * @list: list to attach event master list
+ * @active: indicates the state of dpu power handle
+ */
+struct dpu_power_event {
+	char client_name[MAX_CLIENT_NAME_LEN];
+	void (*cb_fnc)(u32 event_type, void *usr);
+	void *usr;
+	u32 event_type;
+	struct list_head list;
+	bool active;
+};
+
+/**
+ * struct dpu_power_handle: power handle main struct
+ * @client_clist: master list to store all clients
+ * @phandle_lock: lock to synchronize the enable/disable
+ * @dev: pointer to device structure
+ * @usecase_ndx: current usecase index
+ * @event_list: current power handle event list
+ */
+struct dpu_power_handle {
+	struct list_head power_client_clist;
+	struct mutex phandle_lock;
+	struct device *dev;
+	u32 current_usecase_ndx;
+	struct list_head event_list;
+};
+
+/**
+ * dpu_power_resource_init() - initializes the dpu power handle
+ * @pdev:   platform device to search the power resources
+ * @pdata:  power handle to store the power resources
+ */
+void dpu_power_resource_init(struct platform_device *pdev,
+	struct dpu_power_handle *pdata);
+
+/**
+ * dpu_power_resource_deinit() - release the dpu power handle
+ * @pdev:   platform device for power resources
+ * @pdata:  power handle containing the resources
+ *
+ * Return: error code.
+ */
+void dpu_power_resource_deinit(struct platform_device *pdev,
+	struct dpu_power_handle *pdata);
+
+/**
+ * dpu_power_client_create() - create the client on power handle
+ * @pdata:  power handle containing the resources
+ * @client_name: new client name for registration
+ *
+ * Return: error code.
+ */
+struct dpu_power_client *dpu_power_client_create(struct dpu_power_handle *pdata,
+	char *client_name);
+
+/**
+ * dpu_power_client_destroy() - destroy the client on power handle
+ * @pdata:  power handle containing the resources
+ * @client_name: new client name for registration
+ *
+ * Return: none
+ */
+void dpu_power_client_destroy(struct dpu_power_handle *phandle,
+	struct dpu_power_client *client);
+
+/**
+ * dpu_power_resource_enable() - enable/disable the power resources
+ * @pdata:  power handle containing the resources
+ * @client: client information to enable/disable its vote
+ * @enable: boolean request for enable/disable
+ *
+ * Return: error code.
+ */
+int dpu_power_resource_enable(struct dpu_power_handle *pdata,
+	struct dpu_power_client *pclient, bool enable);
+
+/**
+ * dpu_power_data_bus_bandwidth_ctrl() - control data bus bandwidth enable
+ * @phandle:  power handle containing the resources
+ * @client: client information to bandwidth control
+ * @enable: true to enable bandwidth for data base
+ *
+ * Return: none
+ */
+void dpu_power_data_bus_bandwidth_ctrl(struct dpu_power_handle *phandle,
+		struct dpu_power_client *pclient, int enable);
+
+/**
+ * dpu_power_handle_register_event - register a callback function for an event.
+ *	Clients can register for multiple events with a single register.
+ *	Any block with access to phandle can register for the event
+ *	notification.
+ * @phandle:	power handle containing the resources
+ * @event_type:	event type to register; refer DPU_POWER_HANDLE_EVENT_*
+ * @cb_fnc:	pointer to desired callback function
+ * @usr:	user pointer to pass to callback on event trigger
+ *
+ * Return:	event pointer if success, or error code otherwise
+ */
+struct dpu_power_event *dpu_power_handle_register_event(
+		struct dpu_power_handle *phandle,
+		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
+		void *usr, char *client_name);
+/**
+ * dpu_power_handle_unregister_event - unregister callback for event(s)
+ * @phandle:	power handle containing the resources
+ * @event:	event pointer returned after power handle register
+ */
+void dpu_power_handle_unregister_event(struct dpu_power_handle *phandle,
+		struct dpu_power_event *event);
+
+/**
+ * dpu_power_handle_get_dbus_name - get name of given data bus identifier
+ * @bus_id:	data bus identifier
+ * Return:	Pointer to name string if success; NULL otherwise
+ */
+const char *dpu_power_handle_get_dbus_name(u32 bus_id);
+
+#endif /* _DPU_POWER_HANDLE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
new file mode 100644
index 000000000000..13c0a36d4ef9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -0,0 +1,1079 @@
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s] " fmt, __func__
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_intf.h"
+#include "dpu_encoder.h"
+#include "dpu_trace.h"
+
+#define RESERVED_BY_OTHER(h, r) \
+	((h)->rsvp && ((h)->rsvp->enc_id != (r)->enc_id))
+
+#define RM_RQ_LOCK(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_LOCK))
+#define RM_RQ_CLEAR(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_CLEAR))
+#define RM_RQ_DS(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_DS))
+#define RM_IS_TOPOLOGY_MATCH(t, r) ((t).num_lm == (r).num_lm && \
+				(t).num_comp_enc == (r).num_enc && \
+				(t).num_intf == (r).num_intf)
+
+struct dpu_rm_topology_def {
+	enum dpu_rm_topology_name top_name;
+	int num_lm;
+	int num_comp_enc;
+	int num_intf;
+	int num_ctl;
+	int needs_split_display;
+};
+
+static const struct dpu_rm_topology_def g_top_table[] = {
+	{   DPU_RM_TOPOLOGY_NONE,                 0, 0, 0, 0, false },
+	{   DPU_RM_TOPOLOGY_SINGLEPIPE,           1, 0, 1, 1, false },
+	{   DPU_RM_TOPOLOGY_DUALPIPE,             2, 0, 2, 2, true  },
+	{   DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE,     2, 0, 1, 1, false },
+};
+
+/**
+ * struct dpu_rm_requirements - Reservation requirements parameter bundle
+ * @top_ctrl:  topology control preference from kernel client
+ * @top:       selected topology for the display
+ * @hw_res:	   Hardware resources required as reported by the encoders
+ */
+struct dpu_rm_requirements {
+	uint64_t top_ctrl;
+	const struct dpu_rm_topology_def *topology;
+	struct dpu_encoder_hw_resources hw_res;
+};
+
+/**
+ * struct dpu_rm_rsvp - Use Case Reservation tagging structure
+ *	Used to tag HW blocks as reserved by a CRTC->Encoder->Connector chain
+ *	By using as a tag, rather than lists of pointers to HW blocks used
+ *	we can avoid some list management since we don't know how many blocks
+ *	of each type a given use case may require.
+ * @list:	List head for list of all reservations
+ * @seq:	Global RSVP sequence number for debugging, especially for
+ *		differentiating differenct allocations for same encoder.
+ * @enc_id:	Reservations are tracked by Encoder DRM object ID.
+ *		CRTCs may be connected to multiple Encoders.
+ *		An encoder or connector id identifies the display path.
+ * @topology	DRM<->HW topology use case
+ */
+struct dpu_rm_rsvp {
+	struct list_head list;
+	uint32_t seq;
+	uint32_t enc_id;
+	enum dpu_rm_topology_name topology;
+};
+
+/**
+ * struct dpu_rm_hw_blk - hardware block tracking list member
+ * @list:	List head for list of all hardware blocks tracking items
+ * @rsvp:	Pointer to use case reservation if reserved by a client
+ * @rsvp_nxt:	Temporary pointer used during reservation to the incoming
+ *		request. Will be swapped into rsvp if proposal is accepted
+ * @type:	Type of hardware block this structure tracks
+ * @id:		Hardware ID number, within it's own space, ie. LM_X
+ * @catalog:	Pointer to the hardware catalog entry for this block
+ * @hw:		Pointer to the hardware register access object for this block
+ */
+struct dpu_rm_hw_blk {
+	struct list_head list;
+	struct dpu_rm_rsvp *rsvp;
+	struct dpu_rm_rsvp *rsvp_nxt;
+	enum dpu_hw_blk_type type;
+	uint32_t id;
+	struct dpu_hw_blk *hw;
+};
+
+/**
+ * dpu_rm_dbg_rsvp_stage - enum of steps in making reservation for event logging
+ */
+enum dpu_rm_dbg_rsvp_stage {
+	DPU_RM_STAGE_BEGIN,
+	DPU_RM_STAGE_AFTER_CLEAR,
+	DPU_RM_STAGE_AFTER_RSVPNEXT,
+	DPU_RM_STAGE_FINAL
+};
+
+static void _dpu_rm_print_rsvps(
+		struct dpu_rm *rm,
+		enum dpu_rm_dbg_rsvp_stage stage)
+{
+	struct dpu_rm_rsvp *rsvp;
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+
+	DPU_DEBUG("%d\n", stage);
+
+	list_for_each_entry(rsvp, &rm->rsvps, list) {
+		DRM_DEBUG_KMS("%d rsvp[s%ue%u] topology %d\n", stage, rsvp->seq,
+			      rsvp->enc_id, rsvp->topology);
+	}
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (!blk->rsvp && !blk->rsvp_nxt)
+				continue;
+
+			DRM_DEBUG_KMS("%d rsvp[s%ue%u->s%ue%u] %d %d\n", stage,
+				(blk->rsvp) ? blk->rsvp->seq : 0,
+				(blk->rsvp) ? blk->rsvp->enc_id : 0,
+				(blk->rsvp_nxt) ? blk->rsvp_nxt->seq : 0,
+				(blk->rsvp_nxt) ? blk->rsvp_nxt->enc_id : 0,
+				blk->type, blk->id);
+		}
+	}
+}
+
+struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm)
+{
+	return rm->hw_mdp;
+}
+
+enum dpu_rm_topology_name
+dpu_rm_get_topology_name(struct msm_display_topology topology)
+{
+	int i;
+
+	for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++)
+		if (RM_IS_TOPOLOGY_MATCH(g_top_table[i], topology))
+			return g_top_table[i].top_name;
+
+	return DPU_RM_TOPOLOGY_NONE;
+}
+
+void dpu_rm_init_hw_iter(
+		struct dpu_rm_hw_iter *iter,
+		uint32_t enc_id,
+		enum dpu_hw_blk_type type)
+{
+	memset(iter, 0, sizeof(*iter));
+	iter->enc_id = enc_id;
+	iter->type = type;
+}
+
+static bool _dpu_rm_get_hw_locked(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+{
+	struct list_head *blk_list;
+
+	if (!rm || !i || i->type >= DPU_HW_BLK_MAX) {
+		DPU_ERROR("invalid rm\n");
+		return false;
+	}
+
+	i->hw = NULL;
+	blk_list = &rm->hw_blks[i->type];
+
+	if (i->blk && (&i->blk->list == blk_list)) {
+		DPU_DEBUG("attempt resume iteration past last\n");
+		return false;
+	}
+
+	i->blk = list_prepare_entry(i->blk, blk_list, list);
+
+	list_for_each_entry_continue(i->blk, blk_list, list) {
+		struct dpu_rm_rsvp *rsvp = i->blk->rsvp;
+
+		if (i->blk->type != i->type) {
+			DPU_ERROR("found incorrect block type %d on %d list\n",
+					i->blk->type, i->type);
+			return false;
+		}
+
+		if ((i->enc_id == 0) || (rsvp && rsvp->enc_id == i->enc_id)) {
+			i->hw = i->blk->hw;
+			DPU_DEBUG("found type %d id %d for enc %d\n",
+					i->type, i->blk->id, i->enc_id);
+			return true;
+		}
+	}
+
+	DPU_DEBUG("no match, type %d for enc %d\n", i->type, i->enc_id);
+
+	return false;
+}
+
+bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+{
+	bool ret;
+
+	mutex_lock(&rm->rm_lock);
+	ret = _dpu_rm_get_hw_locked(rm, i);
+	mutex_unlock(&rm->rm_lock);
+
+	return ret;
+}
+
+static void _dpu_rm_hw_destroy(enum dpu_hw_blk_type type, void *hw)
+{
+	switch (type) {
+	case DPU_HW_BLK_LM:
+		dpu_hw_lm_destroy(hw);
+		break;
+	case DPU_HW_BLK_CTL:
+		dpu_hw_ctl_destroy(hw);
+		break;
+	case DPU_HW_BLK_CDM:
+		dpu_hw_cdm_destroy(hw);
+		break;
+	case DPU_HW_BLK_PINGPONG:
+		dpu_hw_pingpong_destroy(hw);
+		break;
+	case DPU_HW_BLK_INTF:
+		dpu_hw_intf_destroy(hw);
+		break;
+	case DPU_HW_BLK_SSPP:
+		/* SSPPs are not managed by the resource manager */
+	case DPU_HW_BLK_TOP:
+		/* Top is a singleton, not managed in hw_blks list */
+	case DPU_HW_BLK_MAX:
+	default:
+		DPU_ERROR("unsupported block type %d\n", type);
+		break;
+	}
+}
+
+int dpu_rm_destroy(struct dpu_rm *rm)
+{
+
+	struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt;
+	struct dpu_rm_hw_blk *hw_cur, *hw_nxt;
+	enum dpu_hw_blk_type type;
+
+	if (!rm) {
+		DPU_ERROR("invalid rm\n");
+		return -EINVAL;
+	}
+
+	list_for_each_entry_safe(rsvp_cur, rsvp_nxt, &rm->rsvps, list) {
+		list_del(&rsvp_cur->list);
+		kfree(rsvp_cur);
+	}
+
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry_safe(hw_cur, hw_nxt, &rm->hw_blks[type],
+				list) {
+			list_del(&hw_cur->list);
+			_dpu_rm_hw_destroy(hw_cur->type, hw_cur->hw);
+			kfree(hw_cur);
+		}
+	}
+
+	dpu_hw_mdp_destroy(rm->hw_mdp);
+	rm->hw_mdp = NULL;
+
+	mutex_destroy(&rm->rm_lock);
+
+	return 0;
+}
+
+static int _dpu_rm_hw_blk_create(
+		struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		enum dpu_hw_blk_type type,
+		uint32_t id,
+		void *hw_catalog_info)
+{
+	struct dpu_rm_hw_blk *blk;
+	struct dpu_hw_mdp *hw_mdp;
+	void *hw;
+
+	hw_mdp = rm->hw_mdp;
+
+	switch (type) {
+	case DPU_HW_BLK_LM:
+		hw = dpu_hw_lm_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_CTL:
+		hw = dpu_hw_ctl_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_CDM:
+		hw = dpu_hw_cdm_init(id, mmio, cat, hw_mdp);
+		break;
+	case DPU_HW_BLK_PINGPONG:
+		hw = dpu_hw_pingpong_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_INTF:
+		hw = dpu_hw_intf_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_SSPP:
+		/* SSPPs are not managed by the resource manager */
+	case DPU_HW_BLK_TOP:
+		/* Top is a singleton, not managed in hw_blks list */
+	case DPU_HW_BLK_MAX:
+	default:
+		DPU_ERROR("unsupported block type %d\n", type);
+		return -EINVAL;
+	}
+
+	if (IS_ERR_OR_NULL(hw)) {
+		DPU_ERROR("failed hw object creation: type %d, err %ld\n",
+				type, PTR_ERR(hw));
+		return -EFAULT;
+	}
+
+	blk = kzalloc(sizeof(*blk), GFP_KERNEL);
+	if (!blk) {
+		_dpu_rm_hw_destroy(type, hw);
+		return -ENOMEM;
+	}
+
+	blk->type = type;
+	blk->id = id;
+	blk->hw = hw;
+	list_add_tail(&blk->list, &rm->hw_blks[type]);
+
+	return 0;
+}
+
+int dpu_rm_init(struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		struct drm_device *dev)
+{
+	int rc, i;
+	enum dpu_hw_blk_type type;
+
+	if (!rm || !cat || !mmio || !dev) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	/* Clear, setup lists */
+	memset(rm, 0, sizeof(*rm));
+
+	mutex_init(&rm->rm_lock);
+
+	INIT_LIST_HEAD(&rm->rsvps);
+	for (type = 0; type < DPU_HW_BLK_MAX; type++)
+		INIT_LIST_HEAD(&rm->hw_blks[type]);
+
+	rm->dev = dev;
+
+	/* Some of the sub-blocks require an mdptop to be created */
+	rm->hw_mdp = dpu_hw_mdptop_init(MDP_TOP, mmio, cat);
+	if (IS_ERR_OR_NULL(rm->hw_mdp)) {
+		rc = PTR_ERR(rm->hw_mdp);
+		rm->hw_mdp = NULL;
+		DPU_ERROR("failed: mdp hw not available\n");
+		goto fail;
+	}
+
+	/* 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];
+
+		if (lm->pingpong == PINGPONG_MAX) {
+			DPU_DEBUG("skip mixer %d without pingpong\n", lm->id);
+			continue;
+		}
+
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_LM,
+				cat->mixer[i].id, &cat->mixer[i]);
+		if (rc) {
+			DPU_ERROR("failed: lm hw not available\n");
+			goto fail;
+		}
+
+		if (!rm->lm_max_width) {
+			rm->lm_max_width = lm->sblk->maxwidth;
+		} else if (rm->lm_max_width != lm->sblk->maxwidth) {
+			/*
+			 * Don't expect to have hw where lm max widths differ.
+			 * If found, take the min.
+			 */
+			DPU_ERROR("unsupported: lm maxwidth differs\n");
+			if (rm->lm_max_width > lm->sblk->maxwidth)
+				rm->lm_max_width = lm->sblk->maxwidth;
+		}
+	}
+
+	for (i = 0; i < cat->pingpong_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_PINGPONG,
+				cat->pingpong[i].id, &cat->pingpong[i]);
+		if (rc) {
+			DPU_ERROR("failed: pp hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->intf_count; i++) {
+		if (cat->intf[i].type == INTF_NONE) {
+			DPU_DEBUG("skip intf %d with type none\n", i);
+			continue;
+		}
+
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_INTF,
+				cat->intf[i].id, &cat->intf[i]);
+		if (rc) {
+			DPU_ERROR("failed: intf hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->ctl_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CTL,
+				cat->ctl[i].id, &cat->ctl[i]);
+		if (rc) {
+			DPU_ERROR("failed: ctl hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->cdm_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CDM,
+				cat->cdm[i].id, &cat->cdm[i]);
+		if (rc) {
+			DPU_ERROR("failed: cdm hw not available\n");
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	dpu_rm_destroy(rm);
+
+	return rc;
+}
+
+/**
+ * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets
+ *	proposed use case requirements, incl. hardwired dependent blocks like
+ *	pingpong
+ * @rm: dpu resource manager handle
+ * @rsvp: reservation currently being created
+ * @reqs: proposed use case requirements
+ * @lm: proposed layer mixer, function checks if lm, and all other hardwired
+ *      blocks connected to the lm (pp) is available and appropriate
+ * @pp: output parameter, pingpong block attached to the layer mixer.
+ *      NULL if pp was not available, or not matching requirements.
+ * @primary_lm: if non-null, this function check if lm is compatible primary_lm
+ *              as well as satisfying all other requirements
+ * @Return: true if lm matches all requirements, false otherwise
+ */
+static bool _dpu_rm_check_lm_and_get_connected_blks(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs,
+		struct dpu_rm_hw_blk *lm,
+		struct dpu_rm_hw_blk **pp,
+		struct dpu_rm_hw_blk *primary_lm)
+{
+	const struct dpu_lm_cfg *lm_cfg = to_dpu_hw_mixer(lm->hw)->cap;
+	struct dpu_rm_hw_iter iter;
+
+	*pp = NULL;
+
+	DPU_DEBUG("check lm %d pp %d\n",
+			   lm_cfg->id, lm_cfg->pingpong);
+
+	/* Check if this layer mixer is a peer of the proposed primary LM */
+	if (primary_lm) {
+		const struct dpu_lm_cfg *prim_lm_cfg =
+				to_dpu_hw_mixer(primary_lm->hw)->cap;
+
+		if (!test_bit(lm_cfg->id, &prim_lm_cfg->lm_pair_mask)) {
+			DPU_DEBUG("lm %d not peer of lm %d\n", lm_cfg->id,
+					prim_lm_cfg->id);
+			return false;
+		}
+	}
+
+	/* Already reserved? */
+	if (RESERVED_BY_OTHER(lm, rsvp)) {
+		DPU_DEBUG("lm %d already reserved\n", lm_cfg->id);
+		return false;
+	}
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_PINGPONG);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		if (iter.blk->id == lm_cfg->pingpong) {
+			*pp = iter.blk;
+			break;
+		}
+	}
+
+	if (!*pp) {
+		DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong);
+		return false;
+	}
+
+	if (RESERVED_BY_OTHER(*pp, rsvp)) {
+		DPU_DEBUG("lm %d pp %d already reserved\n", lm->id,
+				(*pp)->id);
+		return false;
+	}
+
+	return true;
+}
+
+static int _dpu_rm_reserve_lms(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs)
+
+{
+	struct dpu_rm_hw_blk *lm[MAX_BLOCKS];
+	struct dpu_rm_hw_blk *pp[MAX_BLOCKS];
+	struct dpu_rm_hw_iter iter_i, iter_j;
+	int lm_count = 0;
+	int i, rc = 0;
+
+	if (!reqs->topology->num_lm) {
+		DPU_ERROR("invalid number of lm: %d\n", reqs->topology->num_lm);
+		return -EINVAL;
+	}
+
+	/* Find a primary mixer */
+	dpu_rm_init_hw_iter(&iter_i, 0, DPU_HW_BLK_LM);
+	while (lm_count != reqs->topology->num_lm &&
+			_dpu_rm_get_hw_locked(rm, &iter_i)) {
+		memset(&lm, 0, sizeof(lm));
+		memset(&pp, 0, sizeof(pp));
+
+		lm_count = 0;
+		lm[lm_count] = iter_i.blk;
+
+		if (!_dpu_rm_check_lm_and_get_connected_blks(
+				rm, rsvp, reqs, lm[lm_count],
+				&pp[lm_count], NULL))
+			continue;
+
+		++lm_count;
+
+		/* Valid primary mixer found, find matching peers */
+		dpu_rm_init_hw_iter(&iter_j, 0, DPU_HW_BLK_LM);
+
+		while (lm_count != reqs->topology->num_lm &&
+				_dpu_rm_get_hw_locked(rm, &iter_j)) {
+			if (iter_i.blk == iter_j.blk)
+				continue;
+
+			if (!_dpu_rm_check_lm_and_get_connected_blks(
+					rm, rsvp, reqs, iter_j.blk,
+					&pp[lm_count], iter_i.blk))
+				continue;
+
+			lm[lm_count] = iter_j.blk;
+			++lm_count;
+		}
+	}
+
+	if (lm_count != reqs->topology->num_lm) {
+		DPU_DEBUG("unable to find appropriate mixers\n");
+		return -ENAVAIL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(lm); i++) {
+		if (!lm[i])
+			break;
+
+		lm[i]->rsvp_nxt = rsvp;
+		pp[i]->rsvp_nxt = rsvp;
+
+		trace_dpu_rm_reserve_lms(lm[i]->id, lm[i]->type, rsvp->enc_id,
+					 pp[i]->id);
+	}
+
+	return rc;
+}
+
+static int _dpu_rm_reserve_ctls(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		const struct dpu_rm_topology_def *top)
+{
+	struct dpu_rm_hw_blk *ctls[MAX_BLOCKS];
+	struct dpu_rm_hw_iter iter;
+	int i = 0;
+
+	memset(&ctls, 0, sizeof(ctls));
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CTL);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		const struct dpu_hw_ctl *ctl = to_dpu_hw_ctl(iter.blk->hw);
+		unsigned long features = ctl->caps->features;
+		bool has_split_display;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp))
+			continue;
+
+		has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features;
+
+		DPU_DEBUG("ctl %d caps 0x%lX\n", iter.blk->id, features);
+
+		if (top->needs_split_display != has_split_display)
+			continue;
+
+		ctls[i] = iter.blk;
+		DPU_DEBUG("ctl %d match\n", iter.blk->id);
+
+		if (++i == top->num_ctl)
+			break;
+	}
+
+	if (i != top->num_ctl)
+		return -ENAVAIL;
+
+	for (i = 0; i < ARRAY_SIZE(ctls) && i < top->num_ctl; i++) {
+		ctls[i]->rsvp_nxt = rsvp;
+		trace_dpu_rm_reserve_ctls(ctls[i]->id, ctls[i]->type,
+					  rsvp->enc_id);
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_cdm(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		uint32_t id,
+		enum dpu_hw_blk_type type)
+{
+	struct dpu_rm_hw_iter iter;
+
+	DRM_DEBUG_KMS("type %d id %d\n", type, id);
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CDM);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		const struct dpu_hw_cdm *cdm = to_dpu_hw_cdm(iter.blk->hw);
+		const struct dpu_cdm_cfg *caps = cdm->caps;
+		bool match = false;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp))
+			continue;
+
+		if (type == DPU_HW_BLK_INTF && id != INTF_MAX)
+			match = test_bit(id, &caps->intf_connect);
+
+		DRM_DEBUG_KMS("iter: type:%d id:%d enc:%d cdm:%lu match:%d\n",
+			      iter.blk->type, iter.blk->id, rsvp->enc_id,
+			      caps->intf_connect, match);
+
+		if (!match)
+			continue;
+
+		trace_dpu_rm_reserve_cdm(iter.blk->id, iter.blk->type,
+					 rsvp->enc_id);
+		iter.blk->rsvp_nxt = rsvp;
+		break;
+	}
+
+	if (!iter.hw) {
+		DPU_ERROR("couldn't reserve cdm for type %d id %d\n", type, id);
+		return -ENAVAIL;
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_intf(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		uint32_t id,
+		enum dpu_hw_blk_type type,
+		bool needs_cdm)
+{
+	struct dpu_rm_hw_iter iter;
+	int ret = 0;
+
+	/* Find the block entry in the rm, and note the reservation */
+	dpu_rm_init_hw_iter(&iter, 0, type);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		if (iter.blk->id != id)
+			continue;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp)) {
+			DPU_ERROR("type %d id %d already reserved\n", type, id);
+			return -ENAVAIL;
+		}
+
+		iter.blk->rsvp_nxt = rsvp;
+		trace_dpu_rm_reserve_intf(iter.blk->id, iter.blk->type,
+					  rsvp->enc_id);
+		break;
+	}
+
+	/* Shouldn't happen since intfs are fixed at probe */
+	if (!iter.hw) {
+		DPU_ERROR("couldn't find type %d id %d\n", type, id);
+		return -EINVAL;
+	}
+
+	if (needs_cdm)
+		ret = _dpu_rm_reserve_cdm(rm, rsvp, id, type);
+
+	return ret;
+}
+
+static int _dpu_rm_reserve_intf_related_hw(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_encoder_hw_resources *hw_res)
+{
+	int i, ret = 0;
+	u32 id;
+
+	for (i = 0; i < ARRAY_SIZE(hw_res->intfs); i++) {
+		if (hw_res->intfs[i] == INTF_MODE_NONE)
+			continue;
+		id = i + INTF_0;
+		ret = _dpu_rm_reserve_intf(rm, rsvp, id,
+				DPU_HW_BLK_INTF, hw_res->needs_cdm);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int _dpu_rm_make_next_rsvp(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs)
+{
+	int ret;
+	struct dpu_rm_topology_def topology;
+
+	/* Create reservation info, tag reserved blocks with it as we go */
+	rsvp->seq = ++rm->rsvp_next_seq;
+	rsvp->enc_id = enc->base.id;
+	rsvp->topology = reqs->topology->top_name;
+	list_add_tail(&rsvp->list, &rm->rsvps);
+
+	ret = _dpu_rm_reserve_lms(rm, rsvp, reqs);
+	if (ret) {
+		DPU_ERROR("unable to find appropriate mixers\n");
+		return ret;
+	}
+
+	/*
+	 * Do assignment preferring to give away low-resource CTLs first:
+	 * - Check mixers without Split Display
+	 * - Only then allow to grab from CTLs with split display capability
+	 */
+	_dpu_rm_reserve_ctls(rm, rsvp, reqs->topology);
+	if (ret && !reqs->topology->needs_split_display) {
+		memcpy(&topology, reqs->topology, sizeof(topology));
+		topology.needs_split_display = true;
+		_dpu_rm_reserve_ctls(rm, rsvp, &topology);
+	}
+	if (ret) {
+		DPU_ERROR("unable to find appropriate CTL\n");
+		return ret;
+	}
+
+	/* Assign INTFs and blks whose usage is tied to them: CTL & CDM */
+	ret = _dpu_rm_reserve_intf_related_hw(rm, rsvp, &reqs->hw_res);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int _dpu_rm_populate_requirements(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct dpu_rm_requirements *reqs,
+		struct msm_display_topology req_topology)
+{
+	int i;
+
+	memset(reqs, 0, sizeof(*reqs));
+
+	dpu_encoder_get_hw_resources(enc, &reqs->hw_res, conn_state);
+
+	for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++) {
+		if (RM_IS_TOPOLOGY_MATCH(g_top_table[i],
+					req_topology)) {
+			reqs->topology = &g_top_table[i];
+			break;
+		}
+	}
+
+	if (!reqs->topology) {
+		DPU_ERROR("invalid topology for the display\n");
+		return -EINVAL;
+	}
+
+	/**
+	 * Set the requirement based on caps if not set from user space
+	 * This will ensure to select LM tied with DS blocks
+	 * Currently, DS blocks are tied with LM 0 and LM 1 (primary display)
+	 */
+	if (!RM_RQ_DS(reqs) && rm->hw_mdp->caps->has_dest_scaler &&
+		conn_state->connector->connector_type == DRM_MODE_CONNECTOR_DSI)
+		reqs->top_ctrl |= BIT(DPU_RM_TOPCTL_DS);
+
+	DRM_DEBUG_KMS("top_ctrl: 0x%llX num_h_tiles: %d\n", reqs->top_ctrl,
+		      reqs->hw_res.display_num_of_h_tiles);
+	DRM_DEBUG_KMS("num_lm: %d num_ctl: %d topology: %d split_display: %d\n",
+		      reqs->topology->num_lm, reqs->topology->num_ctl,
+		      reqs->topology->top_name,
+		      reqs->topology->needs_split_display);
+
+	return 0;
+}
+
+static struct dpu_rm_rsvp *_dpu_rm_get_rsvp(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc)
+{
+	struct dpu_rm_rsvp *i;
+
+	if (!rm || !enc) {
+		DPU_ERROR("invalid params\n");
+		return NULL;
+	}
+
+	if (list_empty(&rm->rsvps))
+		return NULL;
+
+	list_for_each_entry(i, &rm->rsvps, list)
+		if (i->enc_id == enc->base.id)
+			return i;
+
+	return NULL;
+}
+
+static struct drm_connector *_dpu_rm_get_connector(
+		struct drm_encoder *enc)
+{
+	struct drm_connector *conn = NULL;
+	struct list_head *connector_list =
+			&enc->dev->mode_config.connector_list;
+
+	list_for_each_entry(conn, connector_list, head)
+		if (conn->encoder == enc)
+			return conn;
+
+	return NULL;
+}
+
+/**
+ * _dpu_rm_release_rsvp - release resources and release a reservation
+ * @rm:	KMS handle
+ * @rsvp:	RSVP pointer to release and release resources for
+ */
+static void _dpu_rm_release_rsvp(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct drm_connector *conn)
+{
+	struct dpu_rm_rsvp *rsvp_c, *rsvp_n;
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+
+	if (!rsvp)
+		return;
+
+	DPU_DEBUG("rel rsvp %d enc %d\n", rsvp->seq, rsvp->enc_id);
+
+	list_for_each_entry_safe(rsvp_c, rsvp_n, &rm->rsvps, list) {
+		if (rsvp == rsvp_c) {
+			list_del(&rsvp_c->list);
+			break;
+		}
+	}
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (blk->rsvp == rsvp) {
+				blk->rsvp = NULL;
+				DPU_DEBUG("rel rsvp %d enc %d %d %d\n",
+						rsvp->seq, rsvp->enc_id,
+						blk->type, blk->id);
+			}
+			if (blk->rsvp_nxt == rsvp) {
+				blk->rsvp_nxt = NULL;
+				DPU_DEBUG("rel rsvp_nxt %d enc %d %d %d\n",
+						rsvp->seq, rsvp->enc_id,
+						blk->type, blk->id);
+			}
+		}
+	}
+
+	kfree(rsvp);
+}
+
+void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc)
+{
+	struct dpu_rm_rsvp *rsvp;
+	struct drm_connector *conn;
+
+	if (!rm || !enc) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	mutex_lock(&rm->rm_lock);
+
+	rsvp = _dpu_rm_get_rsvp(rm, enc);
+	if (!rsvp) {
+		DPU_ERROR("failed to find rsvp for enc %d\n", enc->base.id);
+		goto end;
+	}
+
+	conn = _dpu_rm_get_connector(enc);
+	if (!conn) {
+		DPU_ERROR("failed to get connector for enc %d\n", enc->base.id);
+		goto end;
+	}
+
+	_dpu_rm_release_rsvp(rm, rsvp, conn);
+end:
+	mutex_unlock(&rm->rm_lock);
+}
+
+static int _dpu_rm_commit_rsvp(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+	int ret = 0;
+
+	/* Swap next rsvp to be the active */
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (blk->rsvp_nxt) {
+				blk->rsvp = blk->rsvp_nxt;
+				blk->rsvp_nxt = NULL;
+			}
+		}
+	}
+
+	if (!ret)
+		DRM_DEBUG_KMS("rsrv enc %d topology %d\n", rsvp->enc_id,
+			      rsvp->topology);
+
+	return ret;
+}
+
+int dpu_rm_reserve(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct msm_display_topology topology,
+		bool test_only)
+{
+	struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt;
+	struct dpu_rm_requirements reqs;
+	int ret;
+
+	if (!rm || !enc || !crtc_state || !conn_state) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	/* Check if this is just a page-flip */
+	if (!drm_atomic_crtc_needs_modeset(crtc_state))
+		return 0;
+
+	DRM_DEBUG_KMS("reserving hw for conn %d enc %d crtc %d test_only %d\n",
+		      conn_state->connector->base.id, enc->base.id,
+		      crtc_state->crtc->base.id, test_only);
+
+	mutex_lock(&rm->rm_lock);
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_BEGIN);
+
+	ret = _dpu_rm_populate_requirements(rm, enc, crtc_state,
+			conn_state, &reqs, topology);
+	if (ret) {
+		DPU_ERROR("failed to populate hw requirements\n");
+		goto end;
+	}
+
+	/*
+	 * We only support one active reservation per-hw-block. But to implement
+	 * transactional semantics for test-only, and for allowing failure while
+	 * modifying your existing reservation, over the course of this
+	 * function we can have two reservations:
+	 * Current: Existing reservation
+	 * Next: Proposed reservation. The proposed reservation may fail, or may
+	 *       be discarded if in test-only mode.
+	 * If reservation is successful, and we're not in test-only, then we
+	 * replace the current with the next.
+	 */
+	rsvp_nxt = kzalloc(sizeof(*rsvp_nxt), GFP_KERNEL);
+	if (!rsvp_nxt) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	rsvp_cur = _dpu_rm_get_rsvp(rm, enc);
+
+	/*
+	 * User can request that we clear out any reservation during the
+	 * atomic_check phase by using this CLEAR bit
+	 */
+	if (rsvp_cur && test_only && RM_RQ_CLEAR(&reqs)) {
+		DPU_DEBUG("test_only & CLEAR: clear rsvp[s%de%d]\n",
+				rsvp_cur->seq, rsvp_cur->enc_id);
+		_dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector);
+		rsvp_cur = NULL;
+		_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_CLEAR);
+	}
+
+	/* Check the proposed reservation, store it in hw's "next" field */
+	ret = _dpu_rm_make_next_rsvp(rm, enc, crtc_state, conn_state,
+			rsvp_nxt, &reqs);
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_RSVPNEXT);
+
+	if (ret) {
+		DPU_ERROR("failed to reserve hw resources: %d\n", ret);
+		_dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector);
+	} else if (test_only && !RM_RQ_LOCK(&reqs)) {
+		/*
+		 * Normally, if test_only, test the reservation and then undo
+		 * However, if the user requests LOCK, then keep the reservation
+		 * made during the atomic_check phase.
+		 */
+		DPU_DEBUG("test_only: discard test rsvp[s%de%d]\n",
+				rsvp_nxt->seq, rsvp_nxt->enc_id);
+		_dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector);
+	} else {
+		if (test_only && RM_RQ_LOCK(&reqs))
+			DPU_DEBUG("test_only & LOCK: lock rsvp[s%de%d]\n",
+					rsvp_nxt->seq, rsvp_nxt->enc_id);
+
+		_dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector);
+
+		ret = _dpu_rm_commit_rsvp(rm, rsvp_nxt, conn_state);
+	}
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_FINAL);
+
+end:
+	mutex_unlock(&rm->rm_lock);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
new file mode 100644
index 000000000000..ffd1841a6067
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DPU_RM_H__
+#define __DPU_RM_H__
+
+#include <linux/list.h>
+
+#include "msm_kms.h"
+#include "dpu_hw_top.h"
+
+/**
+ * enum dpu_rm_topology_name - HW resource use case in use by connector
+ * @DPU_RM_TOPOLOGY_NONE:                 No topology in use currently
+ * @DPU_RM_TOPOLOGY_SINGLEPIPE:           1 LM, 1 PP, 1 INTF/WB
+ * @DPU_RM_TOPOLOGY_DUALPIPE:             2 LM, 2 PP, 2 INTF/WB
+ * @DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE:     2 LM, 2 PP, 3DMux, 1 INTF/WB
+ */
+enum dpu_rm_topology_name {
+	DPU_RM_TOPOLOGY_NONE = 0,
+	DPU_RM_TOPOLOGY_SINGLEPIPE,
+	DPU_RM_TOPOLOGY_DUALPIPE,
+	DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE,
+	DPU_RM_TOPOLOGY_MAX,
+};
+
+/**
+ * enum dpu_rm_topology_control - HW resource use case in use by connector
+ * @DPU_RM_TOPCTL_RESERVE_LOCK: If set, in AtomicTest phase, after a successful
+ *                              test, reserve the resources for this display.
+ *                              Normal behavior would not impact the reservation
+ *                              list during the AtomicTest phase.
+ * @DPU_RM_TOPCTL_RESERVE_CLEAR: If set, in AtomicTest phase, before testing,
+ *                               release any reservation held by this display.
+ *                               Normal behavior would not impact the
+ *                               reservation list during the AtomicTest phase.
+ * @DPU_RM_TOPCTL_DS  : Require layer mixers with DS capabilities
+ */
+enum dpu_rm_topology_control {
+	DPU_RM_TOPCTL_RESERVE_LOCK,
+	DPU_RM_TOPCTL_RESERVE_CLEAR,
+	DPU_RM_TOPCTL_DS,
+};
+
+/**
+ * struct dpu_rm - DPU dynamic hardware resource manager
+ * @dev: device handle for event logging purposes
+ * @rsvps: list of hardware reservations by each crtc->encoder->connector
+ * @hw_blks: array of lists of hardware resources present in the system, one
+ *	list per type of hardware block
+ * @hw_mdp: hardware object for mdp_top
+ * @lm_max_width: cached layer mixer maximum width
+ * @rsvp_next_seq: sequence number for next reservation for debugging purposes
+ * @rm_lock: resource manager mutex
+ */
+struct dpu_rm {
+	struct drm_device *dev;
+	struct list_head rsvps;
+	struct list_head hw_blks[DPU_HW_BLK_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+	uint32_t lm_max_width;
+	uint32_t rsvp_next_seq;
+	struct mutex rm_lock;
+};
+
+/**
+ *  struct dpu_rm_hw_blk - resource manager internal structure
+ *	forward declaration for single iterator definition without void pointer
+ */
+struct dpu_rm_hw_blk;
+
+/**
+ * struct dpu_rm_hw_iter - iterator for use with dpu_rm
+ * @hw: dpu_hw object requested, or NULL on failure
+ * @blk: dpu_rm internal block representation. Clients ignore. Used as iterator.
+ * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
+ * @type: Hardware Block Type client wishes to search for.
+ */
+struct dpu_rm_hw_iter {
+	void *hw;
+	struct dpu_rm_hw_blk *blk;
+	uint32_t enc_id;
+	enum dpu_hw_blk_type type;
+};
+
+/**
+ * dpu_rm_init - Read hardware catalog and create reservation tracking objects
+ *	for all HW blocks.
+ * @rm: DPU Resource Manager handle
+ * @cat: Pointer to hardware catalog
+ * @mmio: mapped register io address of MDP
+ * @dev: device handle for event logging purposes
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_init(struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		struct drm_device *dev);
+
+/**
+ * dpu_rm_destroy - Free all memory allocated by dpu_rm_init
+ * @rm: DPU Resource Manager handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_destroy(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_reserve - Given a CRTC->Encoder->Connector display chain, analyze
+ *	the use connections and user requirements, specified through related
+ *	topology control properties, and reserve hardware blocks to that
+ *	display chain.
+ *	HW blocks can then be accessed through dpu_rm_get_* functions.
+ *	HW Reservations should be released via dpu_rm_release_hw.
+ * @rm: DPU Resource Manager handle
+ * @drm_enc: DRM Encoder handle
+ * @crtc_state: Proposed Atomic DRM CRTC State handle
+ * @conn_state: Proposed Atomic DRM Connector State handle
+ * @topology: Pointer to topology info for the display
+ * @test_only: Atomic-Test phase, discard results (unless property overrides)
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_reserve(struct dpu_rm *rm,
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct msm_display_topology topology,
+		bool test_only);
+
+/**
+ * dpu_rm_reserve - Given the encoder for the display chain, release any
+ *	HW blocks previously reserved for that use case.
+ * @rm: DPU Resource Manager handle
+ * @enc: DRM Encoder handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc);
+
+/**
+ * dpu_rm_get_mdp - Retrieve HW block for MDP TOP.
+ *	This is never reserved, and is usable by any display.
+ * @rm: DPU Resource Manager handle
+ * @Return: Pointer to hw block or NULL
+ */
+struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_init_hw_iter - setup given iterator for new iteration over hw list
+ *	using dpu_rm_get_hw
+ * @iter: iter object to initialize
+ * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
+ * @type: Hardware Block Type client wishes to search for.
+ */
+void dpu_rm_init_hw_iter(
+		struct dpu_rm_hw_iter *iter,
+		uint32_t enc_id,
+		enum dpu_hw_blk_type type);
+/**
+ * dpu_rm_get_hw - retrieve reserved hw object given encoder and hw type
+ *	Meant to do a single pass through the hardware list to iteratively
+ *	retrieve hardware blocks of a given type for a given encoder.
+ *	Initialize an iterator object.
+ *	Set hw block type of interest. Set encoder id of interest, 0 for any.
+ *	Function returns first hw of type for that encoder.
+ *	Subsequent calls will return the next reserved hw of that type in-order.
+ *	Iterator HW pointer will be null on failure to find hw.
+ * @rm: DPU Resource Manager handle
+ * @iter: iterator object
+ * @Return: true on match found, false on no match found
+ */
+bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *iter);
+
+/**
+ * dpu_rm_check_property_topctl - validate property bitmask before it is set
+ * @val: user's proposed topology control bitmask
+ * @Return: 0 on success or error
+ */
+int dpu_rm_check_property_topctl(uint64_t val);
+
+/**
+ * dpu_rm_get_topology_name - returns the name of the the given topology
+ *                            definition
+ * @topology: topology definition
+ * @Return: name of the topology
+ */
+enum dpu_rm_topology_name
+dpu_rm_get_topology_name(struct msm_display_topology topology);
+
+#endif /* __DPU_RM_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
new file mode 100644
index 000000000000..ae0ca5076238
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
@@ -0,0 +1,1007 @@
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#if !defined(_DPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _DPU_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#include <drm/drm_rect.h>
+#include "dpu_crtc.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_plane.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM dpu
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dpu_trace
+
+TRACE_EVENT(dpu_perf_set_qos_luts,
+	TP_PROTO(u32 pnum, u32 fmt, bool rt, u32 fl,
+		u32 lut, u32 lut_usage),
+	TP_ARGS(pnum, fmt, rt, fl, lut, lut_usage),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(bool, rt)
+			__field(u32, fl)
+			__field(u64, lut)
+			__field(u32, lut_usage)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->rt = rt;
+			__entry->fl = fl;
+			__entry->lut = lut;
+			__entry->lut_usage = lut_usage;
+	),
+	TP_printk("pnum=%d fmt=%x rt=%d fl=%d lut=0x%llx lut_usage=%d",
+			__entry->pnum, __entry->fmt,
+			__entry->rt, __entry->fl,
+			__entry->lut, __entry->lut_usage)
+);
+
+TRACE_EVENT(dpu_perf_set_danger_luts,
+	TP_PROTO(u32 pnum, u32 fmt, u32 mode, u32 danger_lut,
+		u32 safe_lut),
+	TP_ARGS(pnum, fmt, mode, danger_lut, safe_lut),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(u32, mode)
+			__field(u32, danger_lut)
+			__field(u32, safe_lut)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->mode = mode;
+			__entry->danger_lut = danger_lut;
+			__entry->safe_lut = safe_lut;
+	),
+	TP_printk("pnum=%d fmt=%x mode=%d luts[0x%x, 0x%x]",
+			__entry->pnum, __entry->fmt,
+			__entry->mode, __entry->danger_lut,
+			__entry->safe_lut)
+);
+
+TRACE_EVENT(dpu_perf_set_ot,
+	TP_PROTO(u32 pnum, u32 xin_id, u32 rd_lim, u32 vbif_idx),
+	TP_ARGS(pnum, xin_id, rd_lim, vbif_idx),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, xin_id)
+			__field(u32, rd_lim)
+			__field(u32, vbif_idx)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->xin_id = xin_id;
+			__entry->rd_lim = rd_lim;
+			__entry->vbif_idx = vbif_idx;
+	),
+	TP_printk("pnum:%d xin_id:%d ot:%d vbif:%d",
+			__entry->pnum, __entry->xin_id, __entry->rd_lim,
+			__entry->vbif_idx)
+)
+
+TRACE_EVENT(dpu_perf_update_bus,
+	TP_PROTO(int client, unsigned long long ab_quota,
+	unsigned long long ib_quota),
+	TP_ARGS(client, ab_quota, ib_quota),
+	TP_STRUCT__entry(
+			__field(int, client)
+			__field(u64, ab_quota)
+			__field(u64, ib_quota)
+	),
+	TP_fast_assign(
+			__entry->client = client;
+			__entry->ab_quota = ab_quota;
+			__entry->ib_quota = ib_quota;
+	),
+	TP_printk("Request client:%d ab=%llu ib=%llu",
+			__entry->client,
+			__entry->ab_quota,
+			__entry->ib_quota)
+)
+
+
+TRACE_EVENT(dpu_cmd_release_bw,
+	TP_PROTO(u32 crtc_id),
+	TP_ARGS(crtc_id),
+	TP_STRUCT__entry(
+			__field(u32, crtc_id)
+	),
+	TP_fast_assign(
+			__entry->crtc_id = crtc_id;
+	),
+	TP_printk("crtc:%d", __entry->crtc_id)
+);
+
+TRACE_EVENT(tracing_mark_write,
+	TP_PROTO(int pid, const char *name, bool trace_begin),
+	TP_ARGS(pid, name, trace_begin),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(trace_name, name)
+			__field(bool, trace_begin)
+	),
+	TP_fast_assign(
+			__entry->pid = pid;
+			__assign_str(trace_name, name);
+			__entry->trace_begin = trace_begin;
+	),
+	TP_printk("%s|%d|%s", __entry->trace_begin ? "B" : "E",
+		__entry->pid, __get_str(trace_name))
+)
+
+TRACE_EVENT(dpu_trace_counter,
+	TP_PROTO(int pid, char *name, int value),
+	TP_ARGS(pid, name, value),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(counter_name, name)
+			__field(int, value)
+	),
+	TP_fast_assign(
+			__entry->pid = current->tgid;
+			__assign_str(counter_name, name);
+			__entry->value = value;
+	),
+	TP_printk("%d|%s|%d", __entry->pid,
+			__get_str(counter_name), __entry->value)
+)
+
+TRACE_EVENT(dpu_perf_crtc_update,
+	TP_PROTO(u32 crtc, u64 bw_ctl_mnoc, u64 bw_ctl_llcc,
+			u64 bw_ctl_ebi, u32 core_clk_rate,
+			bool stop_req, u32 update_bus, u32 update_clk),
+	TP_ARGS(crtc, bw_ctl_mnoc, bw_ctl_llcc, bw_ctl_ebi, core_clk_rate,
+		stop_req, update_bus, update_clk),
+	TP_STRUCT__entry(
+			__field(u32, crtc)
+			__field(u64, bw_ctl_mnoc)
+			__field(u64, bw_ctl_llcc)
+			__field(u64, bw_ctl_ebi)
+			__field(u32, core_clk_rate)
+			__field(bool, stop_req)
+			__field(u32, update_bus)
+			__field(u32, update_clk)
+	),
+	TP_fast_assign(
+			__entry->crtc = crtc;
+			__entry->bw_ctl_mnoc = bw_ctl_mnoc;
+			__entry->bw_ctl_llcc = bw_ctl_llcc;
+			__entry->bw_ctl_ebi = bw_ctl_ebi;
+			__entry->core_clk_rate = core_clk_rate;
+			__entry->stop_req = stop_req;
+			__entry->update_bus = update_bus;
+			__entry->update_clk = update_clk;
+	),
+	 TP_printk(
+		"crtc=%d bw_mnoc=%llu bw_llcc=%llu bw_ebi=%llu clk_rate=%u stop_req=%d u_bus=%d u_clk=%d",
+			__entry->crtc,
+			__entry->bw_ctl_mnoc,
+			__entry->bw_ctl_llcc,
+			__entry->bw_ctl_ebi,
+			__entry->core_clk_rate,
+			__entry->stop_req,
+			__entry->update_bus,
+			__entry->update_clk)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_irq_template,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_intr_idx,	intr_idx	)
+		__field(	int,			hw_idx		)
+		__field(	int,			irq_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intr_idx = intr_idx;
+		__entry->hw_idx = hw_idx;
+		__entry->irq_idx = irq_idx;
+	),
+	TP_printk("id=%u, intr=%d, hw=%d, irq=%d",
+		  __entry->drm_id, __entry->intr_idx, __entry->hw_idx,
+		  __entry->irq_idx)
+);
+DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_register_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx)
+);
+DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_unregister_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx)
+);
+
+TRACE_EVENT(dpu_enc_irq_wait_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx, enum dpu_pingpong pp_idx, int atomic_cnt),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx, pp_idx, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_intr_idx,	intr_idx	)
+		__field(	int,			hw_idx		)
+		__field(	int,			irq_idx		)
+		__field(	enum dpu_pingpong,	pp_idx		)
+		__field(	int,			atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intr_idx = intr_idx;
+		__entry->hw_idx = hw_idx;
+		__entry->irq_idx = irq_idx;
+		__entry->pp_idx = pp_idx;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+		  __entry->drm_id, __entry->intr_idx, __entry->hw_idx,
+		  __entry->irq_idx, __entry->pp_idx, __entry->atomic_cnt)
+);
+
+DECLARE_EVENT_CLASS(dpu_drm_obj_template,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+	),
+	TP_printk("id=%u", __entry->drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_atomic_check,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_mode_set,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_disable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff_reset,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_flip,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_vblank_cb,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_enc_enable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_wait_for_commit_done,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+
+TRACE_EVENT(dpu_enc_enable,
+	TP_PROTO(uint32_t drm_id, int hdisplay, int vdisplay),
+	TP_ARGS(drm_id, hdisplay, vdisplay),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			hdisplay	)
+		__field(	int,			vdisplay	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hdisplay = hdisplay;
+		__entry->vdisplay = vdisplay;
+	),
+	TP_printk("id=%u, mode=%dx%d",
+		  __entry->drm_id, __entry->hdisplay, __entry->vdisplay)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_keyval_template,
+	TP_PROTO(uint32_t drm_id, int val),
+	TP_ARGS(drm_id, val),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	int,		val	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->val = val;
+	),
+	TP_printk("id=%u, val=%d", __entry->drm_id, __entry->val)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_underrun_cb,
+	TP_PROTO(uint32_t drm_id, int count),
+	TP_ARGS(drm_id, count)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_trigger_start,
+	TP_PROTO(uint32_t drm_id, int ctl_idx),
+	TP_ARGS(drm_id, ctl_idx)
+);
+
+TRACE_EVENT(dpu_enc_atomic_check_flags,
+	TP_PROTO(uint32_t drm_id, unsigned int flags, int private_flags),
+	TP_ARGS(drm_id, flags, private_flags),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		flags		)
+		__field(	int,			private_flags	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->flags = flags;
+		__entry->private_flags = private_flags;
+	),
+	TP_printk("id=%u, flags=%u, private_flags=%d",
+		  __entry->drm_id, __entry->flags, __entry->private_flags)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_id_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			enable		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+	),
+	TP_printk("id=%u, enable=%s",
+		  __entry->drm_id, __entry->enable ? "true" : "false")
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_rc_helper,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_vblank_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_phys_cmd_connect_te,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+
+TRACE_EVENT(dpu_enc_rc,
+	TP_PROTO(uint32_t drm_id, u32 sw_event, bool idle_pc_supported,
+		 int rc_state, const char *stage),
+	TP_ARGS(drm_id, sw_event, idle_pc_supported, rc_state, stage),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	u32,		sw_event		)
+		__field(	bool,		idle_pc_supported	)
+		__field(	int,		rc_state		)
+		__string(	stage_str,	stage			)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->sw_event = sw_event;
+		__entry->idle_pc_supported = idle_pc_supported;
+		__entry->rc_state = rc_state;
+		__assign_str(stage_str, stage);
+	),
+	TP_printk("%s: id:%u, sw_event:%d, idle_pc_supported:%s, rc_state:%d\n",
+		  __get_str(stage_str), __entry->drm_id, __entry->sw_event,
+		  __entry->idle_pc_supported ? "true" : "false",
+		  __entry->rc_state)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb_not_busy,
+	TP_PROTO(uint32_t drm_id, u32 event, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, event, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	u32,		event		)
+		__field(	enum dpu_intf,	intf_idx	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, event=%u, intf=%d", __entry->drm_id, __entry->event,
+		  __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb,
+	TP_PROTO(uint32_t drm_id, unsigned int idx,
+		 unsigned long frame_busy_mask),
+	TP_ARGS(drm_id, idx, frame_busy_mask),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		idx		)
+		__field(	unsigned long,		frame_busy_mask	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->idx = idx;
+		__entry->frame_busy_mask = frame_busy_mask;
+	),
+	TP_printk("id=%u, idx=%u, frame_busy_mask=%lx", __entry->drm_id,
+		  __entry->idx, __entry->frame_busy_mask)
+);
+
+TRACE_EVENT(dpu_enc_trigger_flush,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx,
+		 int pending_kickoff_cnt, int ctl_idx, u32 pending_flush_ret),
+	TP_ARGS(drm_id, intf_idx, pending_kickoff_cnt, ctl_idx,
+		pending_flush_ret),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+		__field(	int,		pending_kickoff_cnt	)
+		__field(	int,		ctl_idx			)
+		__field(	u32,		pending_flush_ret	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->pending_kickoff_cnt = pending_kickoff_cnt;
+		__entry->ctl_idx = ctl_idx;
+		__entry->pending_flush_ret = pending_flush_ret;
+	),
+	TP_printk("id=%u, intf_idx=%d, pending_kickoff_cnt=%d ctl_idx=%d "
+		  "pending_flush_ret=%u", __entry->drm_id,
+		  __entry->intf_idx, __entry->pending_kickoff_cnt,
+		  __entry->ctl_idx, __entry->pending_flush_ret)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_ktime_template,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	ktime_t,	time	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->time = time;
+	),
+	TP_printk("id=%u, time=%lld", __entry->drm_id,
+		  ktime_to_ms(__entry->time))
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_vsync_event_work,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_early_kickoff,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+
+DECLARE_EVENT_CLASS(dpu_id_event_template,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	u32,		event	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, event=%u", __entry->drm_id, __entry->event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_enc_frame_done_timeout,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_handle_power_event,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_done,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_more_pending,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+
+TRACE_EVENT(dpu_enc_wait_event_timeout,
+	TP_PROTO(uint32_t drm_id, int32_t hw_id, int rc, s64 time,
+		 s64 expected_time, int atomic_cnt),
+	TP_ARGS(drm_id, hw_id, rc, time, expected_time, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	int32_t,	hw_id		)
+		__field(	int,		rc		)
+		__field(	s64,		time		)
+		__field(	s64,		expected_time	)
+		__field(	int,		atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hw_id = hw_id;
+		__entry->rc = rc;
+		__entry->time = time;
+		__entry->expected_time = expected_time;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, hw_id=%d, rc=%d, time=%lld, expected=%lld cnt=%d",
+		  __entry->drm_id, __entry->hw_id, __entry->rc, __entry->time,
+		  __entry->expected_time, __entry->atomic_cnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, pp, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	bool,			enable	)
+		__field(	int,			refcnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, pp=%d, enable=%s, refcnt=%d", __entry->drm_id,
+		  __entry->pp, __entry->enable ? "true" : "false",
+		  __entry->refcnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pp_tx_done,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int new_count,
+		 u32 event),
+	TP_ARGS(drm_id, pp, new_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			new_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->new_count = new_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, new_count=%d, event=%u", __entry->drm_id,
+		  __entry->pp, __entry->new_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pdone_timeout,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int timeout_count,
+		 int kickoff_count, u32 event),
+	TP_ARGS(drm_id, pp, timeout_count, kickoff_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			timeout_count	)
+		__field(	int,			kickoff_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->timeout_count = timeout_count;
+		__entry->kickoff_count = kickoff_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, timeout_count=%d, kickoff_count=%d, event=%u",
+		  __entry->drm_id, __entry->pp, __entry->timeout_count,
+		  __entry->kickoff_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_post_kickoff,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, intf_idx=%d", __entry->drm_id, __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, intf_idx, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	enum dpu_intf,	intf_idx	)
+		__field(	bool,		enable		)
+		__field(	int,		refcnt		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, intf_idx=%d enable=%s refcnt=%d", __entry->drm_id,
+		  __entry->intf_idx, __entry->enable ? "true" : "false",
+		  __entry->drm_id)
+);
+
+TRACE_EVENT(dpu_crtc_setup_mixer,
+	TP_PROTO(uint32_t crtc_id, uint32_t plane_id,
+		 struct drm_plane_state *state, struct dpu_plane_state *pstate,
+		 uint32_t stage_idx, enum dpu_sspp sspp, uint32_t pixel_format,
+		 uint64_t modifier),
+	TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, sspp,
+		pixel_format, modifier),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		crtc_id		)
+		__field(	uint32_t,		plane_id	)
+		__field(	struct drm_plane_state*,state		)
+		__field(	struct dpu_plane_state*,pstate		)
+		__field(	uint32_t,		stage_idx	)
+		__field(	enum dpu_sspp,		sspp		)
+		__field(	uint32_t,		pixel_format	)
+		__field(	uint64_t,		modifier	)
+	),
+	TP_fast_assign(
+		__entry->crtc_id = crtc_id;
+		__entry->plane_id = plane_id;
+		__entry->state = state;
+		__entry->pstate = pstate;
+		__entry->stage_idx = stage_idx;
+		__entry->sspp = sspp;
+		__entry->pixel_format = pixel_format;
+		__entry->modifier = modifier;
+	),
+	TP_printk("crtc_id:%u plane_id:%u fb_id:%u src:{%ux%u+%ux%u} "
+		  "dst:{%ux%u+%ux%u} stage_idx:%u stage:%d, sspp:%d "
+		  "multirect_index:%d multirect_mode:%u pix_format:%u "
+		  "modifier:%llu",
+		  __entry->crtc_id, __entry->plane_id,
+		  __entry->state->fb ? __entry->state->fb->base.id : -1,
+		  __entry->state->src_w >> 16,  __entry->state->src_h >> 16,
+		  __entry->state->src_x >> 16,  __entry->state->src_y >> 16,
+		  __entry->state->crtc_w,  __entry->state->crtc_h,
+		  __entry->state->crtc_x,  __entry->state->crtc_y,
+		  __entry->stage_idx, __entry->pstate->stage, __entry->sspp,
+		  __entry->pstate->multirect_index,
+		  __entry->pstate->multirect_mode, __entry->pixel_format,
+		  __entry->modifier)
+);
+
+TRACE_EVENT(dpu_crtc_setup_lm_bounds,
+	TP_PROTO(uint32_t drm_id, int mixer, struct drm_rect *bounds),
+	TP_ARGS(drm_id, mixer, bounds),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	int,			mixer	)
+		__field(	struct drm_rect *,	bounds	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->mixer = mixer;
+		__entry->bounds = bounds;
+	),
+	TP_printk("id:%u mixer:%d bounds:" DRM_RECT_FMT, __entry->drm_id,
+		  __entry->mixer, DRM_RECT_ARG(__entry->bounds))
+);
+
+TRACE_EVENT(dpu_crtc_vblank_enable,
+	TP_PROTO(uint32_t drm_id, uint32_t enc_id, bool enable,
+		 struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enc_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	uint32_t,		enc_id	)
+		__field(	bool,			enable	)
+		__field(	struct dpu_crtc *,	crtc	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enc_id = enc_id;
+		__entry->enable = enable;
+		__entry->crtc = crtc;
+	),
+	TP_printk("id:%u encoder:%u enable:%s state{enabled:%s suspend:%s "
+		  "vblank_req:%s}",
+		  __entry->drm_id, __entry->enc_id,
+		  __entry->enable ? "true" : "false",
+		  __entry->crtc->enabled ? "true" : "false",
+		  __entry->crtc->suspend ? "true" : "false",
+		  __entry->crtc->vblank_requested ? "true" : "false")
+);
+
+DECLARE_EVENT_CLASS(dpu_crtc_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	bool,			enable	)
+		__field(	struct dpu_crtc *,	crtc	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+		__entry->crtc = crtc;
+	),
+	TP_printk("id:%u enable:%s state{enabled:%s suspend:%s vblank_req:%s}",
+		  __entry->drm_id, __entry->enable ? "true" : "false",
+		  __entry->crtc->enabled ? "true" : "false",
+		  __entry->crtc->suspend ? "true" : "false",
+		  __entry->crtc->vblank_requested ? "true" : "false")
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_set_suspend,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_enable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_disable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_vblank,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+
+TRACE_EVENT(dpu_crtc_disable_frame_pending,
+	TP_PROTO(uint32_t drm_id, int frame_pending),
+	TP_ARGS(drm_id, frame_pending),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			frame_pending	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->frame_pending = frame_pending;
+	),
+	TP_printk("id:%u frame_pending:%d", __entry->drm_id,
+		  __entry->frame_pending)
+);
+
+TRACE_EVENT(dpu_plane_set_scanout,
+	TP_PROTO(enum dpu_sspp index, struct dpu_hw_fmt_layout *layout,
+		 enum dpu_sspp_multirect_index multirect_index),
+	TP_ARGS(index, layout, multirect_index),
+	TP_STRUCT__entry(
+		__field(	enum dpu_sspp,			index	)
+		__field(	struct dpu_hw_fmt_layout*,	layout	)
+		__field(	enum dpu_sspp_multirect_index,	multirect_index)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->layout = layout;
+		__entry->multirect_index = multirect_index;
+	),
+	TP_printk("index:%d layout:{%ux%u @ [%u/%u, %u/%u, %u/%u, %u/%u]} "
+		  "multirect_index:%d", __entry->index, __entry->layout->width,
+		  __entry->layout->height, __entry->layout->plane_addr[0],
+		  __entry->layout->plane_size[0],
+		  __entry->layout->plane_addr[1],
+		  __entry->layout->plane_size[1],
+		  __entry->layout->plane_addr[2],
+		  __entry->layout->plane_size[2],
+		  __entry->layout->plane_addr[3],
+		  __entry->layout->plane_size[3], __entry->multirect_index)
+);
+
+TRACE_EVENT(dpu_plane_disable,
+	TP_PROTO(uint32_t drm_id, bool is_virtual, uint32_t multirect_mode),
+	TP_ARGS(drm_id, is_virtual, multirect_mode),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			is_virtual	)
+		__field(	uint32_t,		multirect_mode	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->is_virtual = is_virtual;
+		__entry->multirect_mode = multirect_mode;
+	),
+	TP_printk("id:%u is_virtual:%s multirect_mode:%u", __entry->drm_id,
+		  __entry->is_virtual ? "true" : "false",
+		  __entry->multirect_mode)
+);
+
+DECLARE_EVENT_CLASS(dpu_rm_iter_template,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	enum dpu_hw_blk_type,	type	)
+		__field(	uint32_t,		enc_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->type = type;
+		__entry->enc_id = enc_id;
+	),
+	TP_printk("id:%d type:%d enc_id:%u", __entry->id, __entry->type,
+		  __entry->enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_cdm,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_intf,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_ctls,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+
+TRACE_EVENT(dpu_rm_reserve_lms,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id,
+		 uint32_t pp_id),
+	TP_ARGS(id, type, enc_id, pp_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	enum dpu_hw_blk_type,	type	)
+		__field(	uint32_t,		enc_id	)
+		__field(	uint32_t,		pp_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->type = type;
+		__entry->enc_id = enc_id;
+		__entry->pp_id = pp_id;
+	),
+	TP_printk("id:%d type:%d enc_id:%u pp_id:%u", __entry->id,
+		  __entry->type, __entry->enc_id, __entry->pp_id)
+);
+
+TRACE_EVENT(dpu_vbif_wait_xin_halt_fail,
+	TP_PROTO(enum dpu_vbif index, u32 xin_id),
+	TP_ARGS(index, xin_id),
+	TP_STRUCT__entry(
+		__field(	enum dpu_vbif,	index	)
+		__field(	u32,		xin_id	)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->xin_id = xin_id;
+	),
+	TP_printk("index:%d xin_id:%u", __entry->index, __entry->xin_id)
+);
+
+TRACE_EVENT(dpu_pp_connect_ext_te,
+	TP_PROTO(enum dpu_pingpong pp, u32 cfg),
+	TP_ARGS(pp, cfg),
+	TP_STRUCT__entry(
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	u32,			cfg	)
+	),
+	TP_fast_assign(
+		__entry->pp = pp;
+		__entry->cfg = cfg;
+	),
+	TP_printk("pp:%d cfg:%u", __entry->pp, __entry->cfg)
+);
+
+DECLARE_EVENT_CLASS(dpu_core_irq_idx_cnt_template,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count),
+	TP_STRUCT__entry(
+		__field(	int,	irq_idx		)
+		__field(	int,	enable_count	)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->enable_count = enable_count;
+	),
+	TP_printk("irq_idx:%d enable_count:%u", __entry->irq_idx,
+		  __entry->enable_count)
+);
+DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_enable_idx,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count)
+);
+DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_disable_idx,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count)
+);
+
+DECLARE_EVENT_CLASS(dpu_core_irq_callback_template,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback),
+	TP_STRUCT__entry(
+		__field(	int,				irq_idx	)
+		__field(	struct dpu_irq_callback *,	callback)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->callback = callback;
+	),
+	TP_printk("irq_idx:%d callback:%pK", __entry->irq_idx,
+		  __entry->callback)
+);
+DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_register_callback,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback)
+);
+DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_unregister_callback,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback)
+);
+
+TRACE_EVENT(dpu_core_perf_update_clk,
+	TP_PROTO(struct drm_device *dev, bool stop_req, u64 clk_rate),
+	TP_ARGS(dev, stop_req, clk_rate),
+	TP_STRUCT__entry(
+		__field(	struct drm_device *,	dev		)
+		__field(	bool,			stop_req	)
+		__field(	u64,			clk_rate	)
+	),
+	TP_fast_assign(
+		__entry->dev = dev;
+		__entry->stop_req = stop_req;
+		__entry->clk_rate = clk_rate;
+	),
+	TP_printk("dev:%s stop_req:%s clk_rate:%llu", __entry->dev->unique,
+		  __entry->stop_req ? "true" : "false", __entry->clk_rate)
+);
+
+#define DPU_ATRACE_END(name) trace_tracing_mark_write(current->tgid, name, 0)
+#define DPU_ATRACE_BEGIN(name) trace_tracing_mark_write(current->tgid, name, 1)
+#define DPU_ATRACE_FUNC() DPU_ATRACE_BEGIN(__func__)
+
+#define DPU_ATRACE_INT(name, value) \
+	trace_dpu_trace_counter(current->tgid, name, value)
+
+#endif /* _DPU_TRACE_H_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
new file mode 100644
index 000000000000..295528292296
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -0,0 +1,384 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+
+#include "dpu_vbif.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_trace.h"
+
+/**
+ * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt
+ * @vbif:	Pointer to hardware vbif driver
+ * @xin_id:	Client interface identifier
+ * @return:	0 if success; error code otherwise
+ */
+static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	ktime_t timeout;
+	bool status;
+	int rc;
+
+	if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		return -EINVAL;
+	}
+
+	timeout = ktime_add_us(ktime_get(), vbif->cap->xin_halt_timeout);
+	for (;;) {
+		status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+		if (status)
+			break;
+		if (ktime_compare_safe(ktime_get(), timeout) > 0) {
+			status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+			break;
+		}
+		usleep_range(501, 1000);
+	}
+
+	if (!status) {
+		rc = -ETIMEDOUT;
+		DPU_ERROR("VBIF %d client %d not halting. TIMEDOUT.\n",
+				vbif->idx - VBIF_0, xin_id);
+	} else {
+		rc = 0;
+		DPU_DEBUG("VBIF %d client %d is halted\n",
+				vbif->idx - VBIF_0, xin_id);
+	}
+
+	return rc;
+}
+
+/**
+ * _dpu_vbif_apply_dynamic_ot_limit - determine OT based on usecase parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @ot_lim:	Pointer to OT limit to be modified
+ * @params:	Pointer to usecase parameters
+ */
+static void _dpu_vbif_apply_dynamic_ot_limit(struct dpu_hw_vbif *vbif,
+		u32 *ot_lim, struct dpu_vbif_set_ot_params *params)
+{
+	u64 pps;
+	const struct dpu_vbif_dynamic_ot_tbl *tbl;
+	u32 i;
+
+	if (!vbif || !(vbif->cap->features & BIT(DPU_VBIF_QOS_OTLIM)))
+		return;
+
+	/* Dynamic OT setting done only for WFD */
+	if (!params->is_wfd)
+		return;
+
+	pps = params->frame_rate;
+	pps *= params->width;
+	pps *= params->height;
+
+	tbl = params->rd ? &vbif->cap->dynamic_ot_rd_tbl :
+			&vbif->cap->dynamic_ot_wr_tbl;
+
+	for (i = 0; i < tbl->count; i++) {
+		if (pps <= tbl->cfg[i].pps) {
+			*ot_lim = tbl->cfg[i].ot_limit;
+			break;
+		}
+	}
+
+	DPU_DEBUG("vbif:%d xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n",
+			vbif->idx - VBIF_0, params->xin_id,
+			params->width, params->height, params->frame_rate,
+			pps, *ot_lim);
+}
+
+/**
+ * _dpu_vbif_get_ot_limit - get OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ * @return:	OT limit
+ */
+static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif,
+	struct dpu_vbif_set_ot_params *params)
+{
+	u32 ot_lim = 0;
+	u32 val;
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		return -EINVAL;
+	}
+
+	if (vbif->cap->default_ot_wr_limit && !params->rd)
+		ot_lim = vbif->cap->default_ot_wr_limit;
+	else if (vbif->cap->default_ot_rd_limit && params->rd)
+		ot_lim = vbif->cap->default_ot_rd_limit;
+
+	/*
+	 * If default ot is not set from dt/catalog,
+	 * then do not configure it.
+	 */
+	if (ot_lim == 0)
+		goto exit;
+
+	/* Modify the limits if the target and the use case requires it */
+	_dpu_vbif_apply_dynamic_ot_limit(vbif, &ot_lim, params);
+
+	if (vbif && vbif->ops.get_limit_conf) {
+		val = vbif->ops.get_limit_conf(vbif,
+				params->xin_id, params->rd);
+		if (val == ot_lim)
+			ot_lim = 0;
+	}
+
+exit:
+	DPU_DEBUG("vbif:%d xin:%d ot_lim:%d\n",
+			vbif->idx - VBIF_0, params->xin_id, ot_lim);
+	return ot_lim;
+}
+
+/**
+ * dpu_vbif_set_ot_limit - set OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ *
+ * Note this function would block waiting for bus halt.
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params)
+{
+	struct dpu_hw_vbif *vbif = NULL;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	u32 ot_lim;
+	int ret, i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		if (dpu_kms->hw_vbif[i] &&
+				dpu_kms->hw_vbif[i]->idx == params->vbif_idx)
+			vbif = dpu_kms->hw_vbif[i];
+	}
+
+	if (!vbif || !mdp) {
+		DPU_DEBUG("invalid arguments vbif %d mdp %d\n",
+				vbif != 0, mdp != 0);
+		return;
+	}
+
+	if (!mdp->ops.setup_clk_force_ctrl ||
+			!vbif->ops.set_limit_conf ||
+			!vbif->ops.set_halt_ctrl)
+		return;
+
+	/* set write_gather_en for all write clients */
+	if (vbif->ops.set_write_gather_en && !params->rd)
+		vbif->ops.set_write_gather_en(vbif, params->xin_id);
+
+	ot_lim = _dpu_vbif_get_ot_limit(vbif, params) & 0xFF;
+
+	if (ot_lim == 0)
+		goto exit;
+
+	trace_dpu_perf_set_ot(params->num, params->xin_id, ot_lim,
+		params->vbif_idx);
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	vbif->ops.set_limit_conf(vbif, params->xin_id, params->rd, ot_lim);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, true);
+
+	ret = _dpu_vbif_wait_for_xin_halt(vbif, params->xin_id);
+	if (ret)
+		trace_dpu_vbif_wait_xin_halt_fail(vbif->idx, params->xin_id);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, false);
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+exit:
+	return;
+}
+
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params)
+{
+	struct dpu_hw_vbif *vbif = NULL;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	const struct dpu_vbif_qos_tbl *qos_tbl;
+	int i;
+
+	if (!dpu_kms || !params || !dpu_kms->hw_mdp) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		if (dpu_kms->hw_vbif[i] &&
+				dpu_kms->hw_vbif[i]->idx == params->vbif_idx) {
+			vbif = dpu_kms->hw_vbif[i];
+			break;
+		}
+	}
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid vbif %d\n", params->vbif_idx);
+		return;
+	}
+
+	if (!vbif->ops.set_qos_remap || !mdp->ops.setup_clk_force_ctrl) {
+		DPU_DEBUG("qos remap not supported\n");
+		return;
+	}
+
+	qos_tbl = params->is_rt ? &vbif->cap->qos_rt_tbl :
+			&vbif->cap->qos_nrt_tbl;
+
+	if (!qos_tbl->npriority_lvl || !qos_tbl->priority_lvl) {
+		DPU_DEBUG("qos tbl not defined\n");
+		return;
+	}
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	for (i = 0; i < qos_tbl->npriority_lvl; i++) {
+		DPU_DEBUG("vbif:%d xin:%d lvl:%d/%d\n",
+				params->vbif_idx, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+		vbif->ops.set_qos_remap(vbif, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+	}
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+}
+
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	u32 i, pnd, src;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->ops.clear_errors) {
+			vbif->ops.clear_errors(vbif, &pnd, &src);
+			if (pnd || src) {
+				DRM_DEBUG_KMS("VBIF %d: pnd 0x%X, src 0x%X\n",
+					      vbif->idx - VBIF_0, pnd, src);
+			}
+		}
+	}
+}
+
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	int i, j;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->cap && vbif->ops.set_mem_type) {
+			for (j = 0; j < vbif->cap->memtype_count; j++)
+				vbif->ops.set_mem_type(
+						vbif, j, vbif->cap->memtype[j]);
+		}
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove_recursive(dpu_kms->debugfs_vbif);
+	dpu_kms->debugfs_vbif = NULL;
+}
+
+int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
+{
+	char vbif_name[32];
+	struct dentry *debugfs_vbif;
+	int i, j;
+
+	dpu_kms->debugfs_vbif = debugfs_create_dir("vbif", debugfs_root);
+	if (!dpu_kms->debugfs_vbif) {
+		DPU_ERROR("failed to create vbif debugfs\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
+
+		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
+
+		debugfs_vbif = debugfs_create_dir(vbif_name,
+				dpu_kms->debugfs_vbif);
+
+		debugfs_create_u32("features", 0600, debugfs_vbif,
+			(u32 *)&vbif->features);
+
+		debugfs_create_u32("xin_halt_timeout", 0400, debugfs_vbif,
+			(u32 *)&vbif->xin_halt_timeout);
+
+		debugfs_create_u32("default_rd_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_rd_limit);
+
+		debugfs_create_u32("default_wr_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_wr_limit);
+
+		for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) {
+			struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_rd_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+
+		for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) {
+			struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_wr_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+	}
+
+	return 0;
+}
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
new file mode 100644
index 000000000000..f17af52dbbd5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
@@ -0,0 +1,94 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_VBIF_H__
+#define __DPU_VBIF_H__
+
+#include "dpu_kms.h"
+
+struct dpu_vbif_set_ot_params {
+	u32 xin_id;
+	u32 num;
+	u32 width;
+	u32 height;
+	u32 frame_rate;
+	bool rd;
+	bool is_wfd;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+};
+
+struct dpu_vbif_set_memtype_params {
+	u32 xin_id;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+	bool is_cacheable;
+};
+
+/**
+ * struct dpu_vbif_set_qos_params - QoS remapper parameter
+ * @vbif_idx: vbif identifier
+ * @xin_id: client interface identifier
+ * @clk_ctrl: clock control identifier of the xin
+ * @num: pipe identifier (debug only)
+ * @is_rt: true if pipe is used in real-time use case
+ */
+struct dpu_vbif_set_qos_params {
+	u32 vbif_idx;
+	u32 xin_id;
+	u32 clk_ctrl;
+	u32 num;
+	bool is_rt;
+};
+
+/**
+ * dpu_vbif_set_ot_limit - set OT limit for vbif client
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to OT configuration parameters
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params);
+
+/**
+ * dpu_vbif_set_qos_remap - set QoS priority level remap
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to QoS configuration parameters
+ */
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params);
+
+/**
+ * dpu_vbif_clear_errors - clear any vbif errors
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_vbif_init_memtypes - initialize xin memory types for vbif
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms);
+
+#ifdef CONFIG_DEBUG_FS
+int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
+void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms);
+#else
+static inline int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms,
+		struct dentry *debugfs_root)
+{
+	return 0;
+}
+static inline void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+#endif /* __DPU_VBIF_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
new file mode 100644
index 000000000000..4f12e5c534c8
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
@@ -0,0 +1,1376 @@
+#ifndef __MEDIA_INFO_H__
+#define __MEDIA_INFO_H__
+
+#ifndef MSM_MEDIA_ALIGN
+#define MSM_MEDIA_ALIGN(__sz, __align) (((__align) & ((__align) - 1)) ?\
+	((((__sz) + (__align) - 1) / (__align)) * (__align)) :\
+	(((__sz) + (__align) - 1) & (~((__align) - 1))))
+#endif
+
+#ifndef MSM_MEDIA_ROUNDUP
+#define MSM_MEDIA_ROUNDUP(__sz, __r) (((__sz) + ((__r) - 1)) / (__r))
+#endif
+
+#ifndef MSM_MEDIA_MAX
+#define MSM_MEDIA_MAX(__a, __b) ((__a) > (__b)?(__a):(__b))
+#endif
+
+enum color_fmts {
+	/* Venus NV12:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV12,
+
+	/* Venus NV21:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved V/U plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * V U V U V U V U V U V U . . . .  ^
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Padding & Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV21,
+	/* Venus NV12_MVTB:
+	 * Two YUV 4:2:0 images/views one after the other
+	 * in a top-bottom layout, same as NV12
+	 * with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_1
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_2
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * View_1 begin at: 0 (zero)
+	 * View_2 begin at: Y_Stride * Y_Scanlines + UV_Stride * UV_Scanlines
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((2*(Y_Stride * Y_Scanlines)
+	 *          + 2*(UV_Stride * UV_Scanlines) + Extradata), 4096)
+	 */
+	COLOR_FMT_NV12_MVTB,
+	/*
+	 * The buffer can be of 2 types:
+	 * (1) Venus NV12 UBWC Progressive
+	 * (2) Venus NV12 UBWC Interlaced
+	 *
+	 * (1) Venus NV12 UBWC Progressive Buffer Format:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 8 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 8 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Y_Stride = align(Width, 128)
+	 * UV_Stride = align(Width, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 *
+	 *
+	 * (2) Venus NV12 UBWC Interlaced Buffer Format:
+	 * Compressed Macro-tile format for NV12 interlaced.
+	 * Contains 8 planes in the following order -
+	 * (A) Y_Meta_Top_Field_Plane
+	 * (B) Y_UBWC_Top_Field_Plane
+	 * (C) UV_Meta_Top_Field_Plane
+	 * (D) UV_UBWC_Top_Field_Plane
+	 * (E) Y_Meta_Bottom_Field_Plane
+	 * (F) Y_UBWC_Bottom_Field_Plane
+	 * (G) UV_Meta_Bottom_Field_Plane
+	 * (H) UV_UBWC_Bottom_Field_Plane
+	 * Y_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Top_Field_Plane.
+	 * Y_UBWC_Top_Field_Plane consists of Y data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Top_Field_Plane data together
+	 * with Y_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit Y samples for top field of an interlaced frame.
+	 *
+	 * UV_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Top_Field_Plane.
+	 * UV_UBWC_Top_Field_Plane consists of UV data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Top_Field_Plane data together
+	 * with UV_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit subsampled color difference samples for top field of an
+	 * interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Top_Field_Plane/UV_UBWC_Top_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * Y_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Bottom_Field_Plane.
+	 * Y_UBWC_Bottom_Field_Plane consists of Y data in compressed macro-tile
+	 * format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Bottom_Field_Plane data
+	 * together with Y_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit Y samples for bottom field of an interlaced frame.
+	 *
+	 * UV_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Bottom_Field_Plane.
+	 * UV_UBWC_Bottom_Field_Plane consists of UV data in compressed
+	 * macro-tile format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Bottom_Field_Plane data together
+	 * with UV_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit subsampled color difference samples for bottom
+	 * field of an interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Bottom_Field_Plane/UV_UBWC_Bottom_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * <-----Y_TF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_TF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_TF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_TF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_TF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_TF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_TF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_TF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * <-----Y_BF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_BF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_BF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_BF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_BF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_BF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_BF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_BF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Half_height = (Height+1)>>1
+	 * Y_TF_Stride = align(Width, 128)
+	 * UV_TF_Stride = align(Width, 128)
+	 * Y_TF_Scanlines = align(Half_height, 32)
+	 * UV_TF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_TF_Plane_size = align(Y_TF_Stride * Y_TF_Scanlines, 4096)
+	 * UV_UBWC_TF_Plane_size = align(UV_TF_Stride * UV_TF_Scanlines, 4096)
+	 * Y_TF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_TF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_TF_Meta_Plane_size =
+	 *     align(Y_TF_Meta_Stride * Y_TF_Meta_Scanlines, 4096)
+	 * UV_TF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_TF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_TF_Meta_Plane_size =
+	 *     align(UV_TF_Meta_Stride * UV_TF_Meta_Scanlines, 4096)
+	 * Y_BF_Stride = align(Width, 128)
+	 * UV_BF_Stride = align(Width, 128)
+	 * Y_BF_Scanlines = align(Half_height, 32)
+	 * UV_BF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_BF_Plane_size = align(Y_BF_Stride * Y_BF_Scanlines, 4096)
+	 * UV_UBWC_BF_Plane_size = align(UV_BF_Stride * UV_BF_Scanlines, 4096)
+	 * Y_BF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_BF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_BF_Meta_Plane_size =
+	 *     align(Y_BF_Meta_Stride * Y_BF_Meta_Scanlines, 4096)
+	 * UV_BF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_BF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_BF_Meta_Plane_size =
+	 *     align(UV_BF_Meta_Stride * UV_BF_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_TF_Plane_size + UV_UBWC_TF_Plane_size +
+	 *           Y_TF_Meta_Plane_size + UV_TF_Meta_Plane_size +
+	 *			 Y_UBWC_BF_Plane_size + UV_UBWC_BF_Plane_size +
+	 *           Y_BF_Meta_Plane_size + UV_BF_Meta_Plane_size +
+	 *           + max(Extradata, Y_TF_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_UBWC,
+	/* Venus NV12 10-bit UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 4/3, 128)
+	 * UV_Stride = align(Width * 4/3, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_BPP10_UBWC,
+	/* Venus RGBA8888 format:
+	 * Contains 1 plane in the following order -
+	 * (A) RGBA plane
+	 *
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Plane_size + Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888,
+	/* Venus RGBA8888 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888_UBWC,
+	/* Venus RGBA1010102 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 256)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA1010102_UBWC,
+	/* Venus RGB565 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGB plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 2, 128)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGB565_UBWC,
+	/* P010 UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 2, 256)
+	 * UV_Stride = align(Width * 2, 256)
+	 * Y_Scanlines = align(Height, 16)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_P010_UBWC,
+	/* Venus P010:
+	 * YUV 4:2:0 image with a plane of 10 bit Y samples followed
+	 * by an interleaved U/V plane containing 10 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width * 2 aligned to 128
+	 * UV_Stride : Width * 2 aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_P010,
+};
+
+#define COLOR_FMT_RGBA1010102_UBWC	COLOR_FMT_RGBA1010102_UBWC
+#define COLOR_FMT_RGB565_UBWC		COLOR_FMT_RGB565_UBWC
+#define COLOR_FMT_P010_UBWC		COLOR_FMT_P010_UBWC
+#define COLOR_FMT_P010		COLOR_FMT_P010
+
+static inline unsigned int VENUS_EXTRADATA_SIZE(int width, int height)
+{
+	(void)height;
+	(void)width;
+
+	/*
+	 * In the future, calculate the size based on the w/h but just
+	 * hardcode it for now since 16K satisfies all current usecases.
+	 */
+	return 16 * 1024;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_Y_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment, stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width, alignment);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		break;
+	case COLOR_FMT_P010:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width*2, alignment);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_UV_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment, stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width, alignment);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		break;
+	case COLOR_FMT_P010:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width*2, alignment);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment, sclines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010:
+		alignment = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		alignment = 16;
+		break;
+	default:
+		return 0;
+	}
+	sclines = MSM_MEDIA_ALIGN(height, alignment);
+invalid_input:
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment, sclines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+	case COLOR_FMT_P010:
+		alignment = 16;
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 32;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	sclines = MSM_MEDIA_ALIGN((height+1)>>1, alignment);
+
+invalid_input:
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
+{
+	int y_tile_width = 0, y_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_width = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_tile_width = 48;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	y_meta_stride = MSM_MEDIA_ROUNDUP(width, y_tile_width);
+	y_meta_stride = MSM_MEDIA_ALIGN(y_meta_stride, 64);
+
+invalid_input:
+	return y_meta_stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
+{
+	int y_tile_height = 0, y_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		y_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	y_meta_scanlines = MSM_MEDIA_ROUNDUP(height, y_tile_height);
+	y_meta_scanlines = MSM_MEDIA_ALIGN(y_meta_scanlines, 16);
+
+invalid_input:
+	return y_meta_scanlines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
+{
+	int uv_tile_width = 0, uv_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_width = 16;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		uv_tile_width = 24;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	uv_meta_stride = MSM_MEDIA_ROUNDUP((width+1)>>1, uv_tile_width);
+	uv_meta_stride = MSM_MEDIA_ALIGN(uv_meta_stride, 64);
+
+invalid_input:
+	return uv_meta_stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
+{
+	int uv_tile_height = 0, uv_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		uv_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	uv_meta_scanlines = MSM_MEDIA_ROUNDUP((height+1)>>1, uv_tile_height);
+	uv_meta_scanlines = MSM_MEDIA_ALIGN(uv_meta_scanlines, 16);
+
+invalid_input:
+	return uv_meta_scanlines;
+}
+
+static inline unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment = 0, stride = 0, bpp = 4;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 128;
+		break;
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 256;
+		bpp = 2;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+		alignment = 256;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	stride = MSM_MEDIA_ALIGN(width * bpp, alignment);
+
+invalid_input:
+	return stride;
+}
+
+static inline unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment = 0, scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 32;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 16;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	scanlines = MSM_MEDIA_ALIGN(height, alignment);
+
+invalid_input:
+	return scanlines;
+}
+
+static inline unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width)
+{
+	int rgb_tile_width = 0, rgb_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_tile_width = 16;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, rgb_tile_width);
+	rgb_meta_stride = MSM_MEDIA_ALIGN(rgb_meta_stride, 64);
+
+invalid_input:
+	return rgb_meta_stride;
+}
+
+static inline unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height)
+{
+	int rgb_tile_height = 0, rgb_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, rgb_tile_height);
+	rgb_meta_scanlines = MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16);
+
+invalid_input:
+	return rgb_meta_scanlines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ * @height
+ * Progressive: height
+ * Interlaced: height
+ */
+static inline unsigned int VENUS_BUFFER_SIZE(
+	int color_fmt, int width, int height)
+{
+	const unsigned int extra_size = VENUS_EXTRADATA_SIZE(width, height);
+	unsigned int uv_alignment = 0, size = 0;
+	unsigned int y_plane, uv_plane, y_stride,
+		uv_stride, y_sclines, uv_sclines;
+	unsigned int y_ubwc_plane = 0, uv_ubwc_plane = 0;
+	unsigned int y_meta_stride = 0, y_meta_scanlines = 0;
+	unsigned int uv_meta_stride = 0, uv_meta_scanlines = 0;
+	unsigned int y_meta_plane = 0, uv_meta_plane = 0;
+	unsigned int rgb_stride = 0, rgb_scanlines = 0;
+	unsigned int rgb_plane = 0, rgb_ubwc_plane = 0, rgb_meta_plane = 0;
+	unsigned int rgb_meta_stride = 0, rgb_meta_scanlines = 0;
+
+	if (!width || !height)
+		goto invalid_input;
+
+	y_stride = VENUS_Y_STRIDE(color_fmt, width);
+	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
+	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
+	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
+	rgb_stride = VENUS_RGB_STRIDE(color_fmt, width);
+	rgb_scanlines = VENUS_RGB_SCANLINES(color_fmt, height);
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_P010:
+		uv_alignment = 4096;
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines + uv_alignment;
+		size = y_plane + uv_plane +
+				MSM_MEDIA_MAX(extra_size, 8 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_MVTB:
+		uv_alignment = 4096;
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines + uv_alignment;
+		size = y_plane + uv_plane;
+		size = 2 * size + extra_size;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		y_sclines = VENUS_Y_SCANLINES(color_fmt, (height+1)>>1);
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_sclines = VENUS_UV_SCANLINES(color_fmt, (height+1)>>1);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines =
+			VENUS_Y_META_SCANLINES(color_fmt, (height+1)>>1);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+			y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines =
+			VENUS_UV_META_SCANLINES(color_fmt, (height+1)>>1);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+			uv_meta_scanlines, 4096);
+
+		size = (y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane)*2 +
+			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+				y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+					uv_meta_scanlines, 4096);
+
+		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane +
+			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+				y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+					uv_meta_scanlines, 4096);
+
+		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_RGBA8888:
+		rgb_plane = MSM_MEDIA_ALIGN(rgb_stride  * rgb_scanlines, 4096);
+		size = rgb_plane;
+		size =  MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_ubwc_plane = MSM_MEDIA_ALIGN(rgb_stride * rgb_scanlines,
+							4096);
+		rgb_meta_stride = VENUS_RGB_META_STRIDE(color_fmt, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color_fmt,
+					height);
+		rgb_meta_plane = MSM_MEDIA_ALIGN(rgb_meta_stride *
+					rgb_meta_scanlines, 4096);
+		size = rgb_ubwc_plane + rgb_meta_plane;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return size;
+}
+
+static inline unsigned int VENUS_VIEW2_OFFSET(
+	int color_fmt, int width, int height)
+{
+	unsigned int offset = 0;
+	unsigned int y_plane, uv_plane, y_stride,
+		uv_stride, y_sclines, uv_sclines;
+	if (!width || !height)
+		goto invalid_input;
+
+	y_stride = VENUS_Y_STRIDE(color_fmt, width);
+	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
+	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
+	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_MVTB:
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines;
+		offset = y_plane + uv_plane;
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return offset;
+}
+
+#endif
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 4b646bf9c214..44d1cda56974 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -125,6 +125,8 @@ static void mdp4_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 
+	drm_atomic_helper_wait_for_vblanks(mdp4_kms->dev, state);
+
 	/* see 119ecb7fd */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i)
 		drm_crtc_vblank_put(crtc);
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
index 4a645926edb7..2bfb39082f54 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
@@ -341,7 +341,7 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder)
 	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		drm_panel_disable(panel);
 		drm_panel_unprepare(panel);
 	}
@@ -410,7 +410,7 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder)
 		dev_err(dev->dev, "failed to enable lcdc_clk: %d\n", ret);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		drm_panel_prepare(panel);
 		drm_panel_enable(panel);
 	}
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 e3b1c86b7aae..5368e621999c 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -34,9 +34,12 @@ static enum drm_connector_status mdp4_lvds_connector_detect(
 	struct mdp4_lvds_connector *mdp4_lvds_connector =
 			to_mdp4_lvds_connector(connector);
 
-	if (!mdp4_lvds_connector->panel)
+	if (!mdp4_lvds_connector->panel) {
 		mdp4_lvds_connector->panel =
 			of_drm_find_panel(mdp4_lvds_connector->panel_node);
+		if (IS_ERR(mdp4_lvds_connector->panel))
+			mdp4_lvds_connector->panel = NULL;
+	}
 
 	return mdp4_lvds_connector->panel ?
 			connector_status_connected :
@@ -129,7 +132,7 @@ struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 24e00274844b..b1da9ce54379 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -65,7 +65,7 @@ struct mdp5_crtc {
 		struct drm_gem_object *scanout_bo;
 		uint64_t iova;
 		uint32_t width, height;
-		uint32_t x, y;
+		int x, y;
 	} cursor;
 };
 #define to_mdp5_crtc(x) container_of(x, struct mdp5_crtc, base)
@@ -760,20 +760,31 @@ static void get_roi(struct drm_crtc *crtc, uint32_t *roi_w, uint32_t *roi_h)
 	 * Cursor Region Of Interest (ROI) is a plane read from cursor
 	 * buffer to render. The ROI region is determined by the visibility of
 	 * the cursor point. In the default Cursor image the cursor point will
-	 * be at the top left of the cursor image, unless it is specified
-	 * otherwise using hotspot feature.
+	 * be at the top left of the cursor image.
 	 *
+	 * Without rotation:
 	 * If the cursor point reaches the right (xres - x < cursor.width) or
 	 * bottom (yres - y < cursor.height) boundary of the screen, then ROI
 	 * width and ROI height need to be evaluated to crop the cursor image
 	 * accordingly.
 	 * (xres-x) will be new cursor width when x > (xres - cursor.width)
 	 * (yres-y) will be new cursor height when y > (yres - cursor.height)
+	 *
+	 * With rotation:
+	 * We get negative x and/or y coordinates.
+	 * (cursor.width - abs(x)) will be new cursor width when x < 0
+	 * (cursor.height - abs(y)) will be new cursor width when y < 0
 	 */
-	*roi_w = min(mdp5_crtc->cursor.width, xres -
+	if (mdp5_crtc->cursor.x >= 0)
+		*roi_w = min(mdp5_crtc->cursor.width, xres -
 			mdp5_crtc->cursor.x);
-	*roi_h = min(mdp5_crtc->cursor.height, yres -
+	else
+		*roi_w = mdp5_crtc->cursor.width - abs(mdp5_crtc->cursor.x);
+	if (mdp5_crtc->cursor.y >= 0)
+		*roi_h = min(mdp5_crtc->cursor.height, yres -
 			mdp5_crtc->cursor.y);
+	else
+		*roi_h = mdp5_crtc->cursor.height - abs(mdp5_crtc->cursor.y);
 }
 
 static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
@@ -783,7 +794,7 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	const enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL;
 	uint32_t blendcfg, stride;
-	uint32_t x, y, width, height;
+	uint32_t x, y, src_x, src_y, width, height;
 	uint32_t roi_w, roi_h;
 	int lm;
 
@@ -800,6 +811,26 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 
 	get_roi(crtc, &roi_w, &roi_h);
 
+	/* If cusror buffer overlaps due to rotation on the
+	 * upper or left screen border the pixel offset inside
+	 * the cursor buffer of the ROI is the positive overlap
+	 * distance.
+	 */
+	if (mdp5_crtc->cursor.x < 0) {
+		src_x = abs(mdp5_crtc->cursor.x);
+		x = 0;
+	} else {
+		src_x = 0;
+	}
+	if (mdp5_crtc->cursor.y < 0) {
+		src_y = abs(mdp5_crtc->cursor.y);
+		y = 0;
+	} else {
+		src_y = 0;
+	}
+	DBG("%s: x=%d, y=%d roi_w=%d roi_h=%d src_x=%d src_y=%d",
+		crtc->name, x, y, roi_w, roi_h, src_x, src_y);
+
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm),
 			MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888));
@@ -812,6 +843,9 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_START_XY(lm),
 			MDP5_LM_CURSOR_START_XY_Y_START(y) |
 			MDP5_LM_CURSOR_START_XY_X_START(x));
+	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_XY(lm),
+			MDP5_LM_CURSOR_XY_SRC_Y(src_y) |
+			MDP5_LM_CURSOR_XY_SRC_X(src_x));
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BASE_ADDR(lm),
 			mdp5_crtc->cursor.iova);
 
@@ -932,8 +966,9 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	if (unlikely(!crtc->state->enable))
 		return 0;
 
-	mdp5_crtc->cursor.x = x = max(x, 0);
-	mdp5_crtc->cursor.y = y = max(y, 0);
+	/* accept negative x/y coordinates up to maximum cursor overlap */
+	mdp5_crtc->cursor.x = x = max(x, -(int)mdp5_crtc->cursor.width);
+	mdp5_crtc->cursor.y = y = max(y, -(int)mdp5_crtc->cursor.height);
 
 	get_roi(crtc, &roi_w, &roi_h);
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
index 9af94e35f678..fcd44d1d1068 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
@@ -319,7 +319,17 @@ static int mdp5_encoder_atomic_check(struct drm_encoder *encoder,
 
 	mdp5_cstate->ctl = ctl;
 	mdp5_cstate->pipeline.intf = intf;
-	mdp5_cstate->defer_start = true;
+
+	/*
+	 * This is a bit awkward, but we want to flush the CTL and hit the
+	 * START bit at most once for an atomic update.  In the non-full-
+	 * modeset case, this is done from crtc->atomic_flush(), but that
+	 * is too early in the case of full modeset, in which case we
+	 * defer to encoder->enable().  But we need to *know* whether
+	 * encoder->enable() will be called to do this:
+	 */
+	if (drm_atomic_crtc_needs_modeset(crtc_state))
+		mdp5_cstate->defer_start = true;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 6e12e275deba..bddd625ab91b 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -170,6 +170,8 @@ static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 	struct device *dev = &mdp5_kms->pdev->dev;
 	struct mdp5_global_state *global_state;
 
+	drm_atomic_helper_wait_for_vblanks(mdp5_kms->dev, state);
+
 	global_state = mdp5_get_existing_global_state(mdp5_kms);
 
 	if (mdp5_kms->smp)
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
index f2a0db7a8a03..1cc4e57f0226 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
@@ -20,12 +20,10 @@
 #include "msm_drv.h"
 #include "mdp5_kms.h"
 
-/*
- * If needed, this can become more specific: something like struct mdp5_mdss,
- * which contains a 'struct msm_mdss base' member.
- */
-struct msm_mdss {
-	struct drm_device *dev;
+#define to_mdp5_mdss(x) container_of(x, struct mdp5_mdss, base)
+
+struct mdp5_mdss {
+	struct msm_mdss base;
 
 	void __iomem *mmio, *vbif;
 
@@ -41,22 +39,22 @@ struct msm_mdss {
 	} irqcontroller;
 };
 
-static inline void mdss_write(struct msm_mdss *mdss, u32 reg, u32 data)
+static inline void mdss_write(struct mdp5_mdss *mdp5_mdss, u32 reg, u32 data)
 {
-	msm_writel(data, mdss->mmio + reg);
+	msm_writel(data, mdp5_mdss->mmio + reg);
 }
 
-static inline u32 mdss_read(struct msm_mdss *mdss, u32 reg)
+static inline u32 mdss_read(struct mdp5_mdss *mdp5_mdss, u32 reg)
 {
-	return msm_readl(mdss->mmio + reg);
+	return msm_readl(mdp5_mdss->mmio + reg);
 }
 
 static irqreturn_t mdss_irq(int irq, void *arg)
 {
-	struct msm_mdss *mdss = arg;
+	struct mdp5_mdss *mdp5_mdss = arg;
 	u32 intr;
 
-	intr = mdss_read(mdss, REG_MDSS_HW_INTR_STATUS);
+	intr = mdss_read(mdp5_mdss, REG_MDSS_HW_INTR_STATUS);
 
 	VERB("intr=%08x", intr);
 
@@ -64,7 +62,7 @@ static irqreturn_t mdss_irq(int irq, void *arg)
 		irq_hw_number_t hwirq = fls(intr) - 1;
 
 		generic_handle_irq(irq_find_mapping(
-				mdss->irqcontroller.domain, hwirq));
+				mdp5_mdss->irqcontroller.domain, hwirq));
 		intr &= ~(1 << hwirq);
 	}
 
@@ -84,19 +82,19 @@ static irqreturn_t mdss_irq(int irq, void *arg)
 
 static void mdss_hw_mask_irq(struct irq_data *irqd)
 {
-	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+	struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd);
 
 	smp_mb__before_atomic();
-	clear_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	clear_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask);
 	smp_mb__after_atomic();
 }
 
 static void mdss_hw_unmask_irq(struct irq_data *irqd)
 {
-	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+	struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd);
 
 	smp_mb__before_atomic();
-	set_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	set_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask);
 	smp_mb__after_atomic();
 }
 
@@ -109,13 +107,13 @@ static struct irq_chip mdss_hw_irq_chip = {
 static int mdss_hw_irqdomain_map(struct irq_domain *d, unsigned int irq,
 				 irq_hw_number_t hwirq)
 {
-	struct msm_mdss *mdss = d->host_data;
+	struct mdp5_mdss *mdp5_mdss = d->host_data;
 
 	if (!(VALID_IRQS & (1 << hwirq)))
 		return -EPERM;
 
 	irq_set_chip_and_handler(irq, &mdss_hw_irq_chip, handle_level_irq);
-	irq_set_chip_data(irq, mdss);
+	irq_set_chip_data(irq, mdp5_mdss);
 
 	return 0;
 }
@@ -126,90 +124,99 @@ static const struct irq_domain_ops mdss_hw_irqdomain_ops = {
 };
 
 
-static int mdss_irq_domain_init(struct msm_mdss *mdss)
+static int mdss_irq_domain_init(struct mdp5_mdss *mdp5_mdss)
 {
-	struct device *dev = mdss->dev->dev;
+	struct device *dev = mdp5_mdss->base.dev->dev;
 	struct irq_domain *d;
 
 	d = irq_domain_add_linear(dev->of_node, 32, &mdss_hw_irqdomain_ops,
-				  mdss);
+				  mdp5_mdss);
 	if (!d) {
 		dev_err(dev, "mdss irq domain add failed\n");
 		return -ENXIO;
 	}
 
-	mdss->irqcontroller.enabled_mask = 0;
-	mdss->irqcontroller.domain = d;
+	mdp5_mdss->irqcontroller.enabled_mask = 0;
+	mdp5_mdss->irqcontroller.domain = d;
 
 	return 0;
 }
 
-int msm_mdss_enable(struct msm_mdss *mdss)
+static int mdp5_mdss_enable(struct msm_mdss *mdss)
 {
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss);
 	DBG("");
 
-	clk_prepare_enable(mdss->ahb_clk);
-	if (mdss->axi_clk)
-		clk_prepare_enable(mdss->axi_clk);
-	if (mdss->vsync_clk)
-		clk_prepare_enable(mdss->vsync_clk);
+	clk_prepare_enable(mdp5_mdss->ahb_clk);
+	if (mdp5_mdss->axi_clk)
+		clk_prepare_enable(mdp5_mdss->axi_clk);
+	if (mdp5_mdss->vsync_clk)
+		clk_prepare_enable(mdp5_mdss->vsync_clk);
 
 	return 0;
 }
 
-int msm_mdss_disable(struct msm_mdss *mdss)
+static int mdp5_mdss_disable(struct msm_mdss *mdss)
 {
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss);
 	DBG("");
 
-	if (mdss->vsync_clk)
-		clk_disable_unprepare(mdss->vsync_clk);
-	if (mdss->axi_clk)
-		clk_disable_unprepare(mdss->axi_clk);
-	clk_disable_unprepare(mdss->ahb_clk);
+	if (mdp5_mdss->vsync_clk)
+		clk_disable_unprepare(mdp5_mdss->vsync_clk);
+	if (mdp5_mdss->axi_clk)
+		clk_disable_unprepare(mdp5_mdss->axi_clk);
+	clk_disable_unprepare(mdp5_mdss->ahb_clk);
 
 	return 0;
 }
 
-static int msm_mdss_get_clocks(struct msm_mdss *mdss)
+static int msm_mdss_get_clocks(struct mdp5_mdss *mdp5_mdss)
 {
-	struct platform_device *pdev = to_platform_device(mdss->dev->dev);
+	struct platform_device *pdev =
+			to_platform_device(mdp5_mdss->base.dev->dev);
 
-	mdss->ahb_clk = msm_clk_get(pdev, "iface");
-	if (IS_ERR(mdss->ahb_clk))
-		mdss->ahb_clk = NULL;
+	mdp5_mdss->ahb_clk = msm_clk_get(pdev, "iface");
+	if (IS_ERR(mdp5_mdss->ahb_clk))
+		mdp5_mdss->ahb_clk = NULL;
 
-	mdss->axi_clk = msm_clk_get(pdev, "bus");
-	if (IS_ERR(mdss->axi_clk))
-		mdss->axi_clk = NULL;
+	mdp5_mdss->axi_clk = msm_clk_get(pdev, "bus");
+	if (IS_ERR(mdp5_mdss->axi_clk))
+		mdp5_mdss->axi_clk = NULL;
 
-	mdss->vsync_clk = msm_clk_get(pdev, "vsync");
-	if (IS_ERR(mdss->vsync_clk))
-		mdss->vsync_clk = NULL;
+	mdp5_mdss->vsync_clk = msm_clk_get(pdev, "vsync");
+	if (IS_ERR(mdp5_mdss->vsync_clk))
+		mdp5_mdss->vsync_clk = NULL;
 
 	return 0;
 }
 
-void msm_mdss_destroy(struct drm_device *dev)
+static void mdp5_mdss_destroy(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_mdss *mdss = priv->mdss;
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(priv->mdss);
 
-	if (!mdss)
+	if (!mdp5_mdss)
 		return;
 
-	irq_domain_remove(mdss->irqcontroller.domain);
-	mdss->irqcontroller.domain = NULL;
+	irq_domain_remove(mdp5_mdss->irqcontroller.domain);
+	mdp5_mdss->irqcontroller.domain = NULL;
 
-	regulator_disable(mdss->vdd);
+	regulator_disable(mdp5_mdss->vdd);
 
 	pm_runtime_disable(dev->dev);
 }
 
-int msm_mdss_init(struct drm_device *dev)
+static const struct msm_mdss_funcs mdss_funcs = {
+	.enable	= mdp5_mdss_enable,
+	.disable = mdp5_mdss_disable,
+	.destroy = mdp5_mdss_destroy,
+};
+
+int mdp5_mdss_init(struct drm_device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_mdss *mdss;
+	struct mdp5_mdss *mdp5_mdss;
 	int ret;
 
 	DBG("");
@@ -217,40 +224,40 @@ int msm_mdss_init(struct drm_device *dev)
 	if (!of_device_is_compatible(dev->dev->of_node, "qcom,mdss"))
 		return 0;
 
-	mdss = devm_kzalloc(dev->dev, sizeof(*mdss), GFP_KERNEL);
-	if (!mdss) {
+	mdp5_mdss = devm_kzalloc(dev->dev, sizeof(*mdp5_mdss), GFP_KERNEL);
+	if (!mdp5_mdss) {
 		ret = -ENOMEM;
 		goto fail;
 	}
 
-	mdss->dev = dev;
+	mdp5_mdss->base.dev = dev;
 
-	mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
-	if (IS_ERR(mdss->mmio)) {
-		ret = PTR_ERR(mdss->mmio);
+	mdp5_mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
+	if (IS_ERR(mdp5_mdss->mmio)) {
+		ret = PTR_ERR(mdp5_mdss->mmio);
 		goto fail;
 	}
 
-	mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
-	if (IS_ERR(mdss->vbif)) {
-		ret = PTR_ERR(mdss->vbif);
+	mdp5_mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
+	if (IS_ERR(mdp5_mdss->vbif)) {
+		ret = PTR_ERR(mdp5_mdss->vbif);
 		goto fail;
 	}
 
-	ret = msm_mdss_get_clocks(mdss);
+	ret = msm_mdss_get_clocks(mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to get clocks: %d\n", ret);
 		goto fail;
 	}
 
 	/* Regulator to enable GDSCs in downstream kernels */
-	mdss->vdd = devm_regulator_get(dev->dev, "vdd");
-	if (IS_ERR(mdss->vdd)) {
-		ret = PTR_ERR(mdss->vdd);
+	mdp5_mdss->vdd = devm_regulator_get(dev->dev, "vdd");
+	if (IS_ERR(mdp5_mdss->vdd)) {
+		ret = PTR_ERR(mdp5_mdss->vdd);
 		goto fail;
 	}
 
-	ret = regulator_enable(mdss->vdd);
+	ret = regulator_enable(mdp5_mdss->vdd);
 	if (ret) {
 		dev_err(dev->dev, "failed to enable regulator vdd: %d\n",
 			ret);
@@ -258,25 +265,26 @@ int msm_mdss_init(struct drm_device *dev)
 	}
 
 	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
-			       mdss_irq, 0, "mdss_isr", mdss);
+			       mdss_irq, 0, "mdss_isr", mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to init irq: %d\n", ret);
 		goto fail_irq;
 	}
 
-	ret = mdss_irq_domain_init(mdss);
+	ret = mdss_irq_domain_init(mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to init sub-block irqs: %d\n", ret);
 		goto fail_irq;
 	}
 
-	priv->mdss = mdss;
+	mdp5_mdss->base.funcs = &mdss_funcs;
+	priv->mdss = &mdp5_mdss->base;
 
 	pm_runtime_enable(dev->dev);
 
 	return 0;
 fail_irq:
-	regulator_disable(mdss->vdd);
+	regulator_disable(mdp5_mdss->vdd);
 fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index b744bcc7d8ad..ff8164cc6738 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -208,6 +208,9 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
+	if (!msm_dsi_manager_validate_current_config(msm_dsi->id))
+		goto fail;
+
 	msm_dsi->encoder = encoder;
 
 	msm_dsi->bridge = msm_dsi_manager_bridge_init(msm_dsi->id);
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 70d9a9a47acd..08f3fc6771b7 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -100,6 +100,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len);
 void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags);
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi);
 void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi);
+bool msm_dsi_manager_validate_current_config(u8 id);
 
 /* msm dsi */
 static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi)
@@ -149,6 +150,7 @@ static inline int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll,
 #endif
 
 /* dsi host */
+struct msm_dsi_host;
 int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 					const struct mipi_dsi_msg *msg);
 void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
@@ -162,7 +164,8 @@ void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host,
 int msm_dsi_host_enable(struct mipi_dsi_host *host);
 int msm_dsi_host_disable(struct mipi_dsi_host *host);
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings);
+			struct msm_dsi_phy_shared_timings *phy_shared_timings,
+			bool is_dual_dsi);
 int msm_dsi_host_power_off(struct mipi_dsi_host *host);
 int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 					struct drm_display_mode *mode);
@@ -175,13 +178,29 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 			struct msm_dsi_pll *src_pll);
 void msm_dsi_host_reset_phy(struct mipi_dsi_host *host);
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
-	struct msm_dsi_phy_clk_request *clk_req);
+	struct msm_dsi_phy_clk_request *clk_req,
+	bool is_dual_dsi);
 void msm_dsi_host_destroy(struct mipi_dsi_host *host);
 int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev);
 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_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);
+void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host);
+int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size);
+int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size);
+void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host);
+void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host);
+void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host);
+int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova);
+int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova);
+int dsi_clk_init_v2(struct msm_dsi_host *msm_host);
+int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host);
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi);
 
 /* dsi phy */
 struct msm_dsi_phy;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 0327bb54b01b..dcdfb1bb54f9 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -136,20 +136,58 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
+const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_v2,
+	.link_clk_disable = dsi_link_clk_disable_v2,
+	.clk_init_ver = dsi_clk_init_v2,
+	.tx_buf_alloc = dsi_tx_buf_alloc_v2,
+	.tx_buf_get = dsi_tx_buf_get_v2,
+	.tx_buf_put = NULL,
+	.dma_base_get = dsi_dma_base_get_v2,
+	.calc_clk_rate = dsi_calc_clk_rate_v2,
+};
+
+const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_6g,
+	.link_clk_disable = dsi_link_clk_disable_6g,
+	.clk_init_ver = NULL,
+	.tx_buf_alloc = dsi_tx_buf_alloc_6g,
+	.tx_buf_get = dsi_tx_buf_get_6g,
+	.tx_buf_put = dsi_tx_buf_put_6g,
+	.dma_base_get = dsi_dma_base_get_6g,
+	.calc_clk_rate = dsi_calc_clk_rate_6g,
+};
+
+const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_6g,
+	.link_clk_disable = dsi_link_clk_disable_6g,
+	.clk_init_ver = dsi_clk_init_6g_v2,
+	.tx_buf_alloc = dsi_tx_buf_alloc_6g,
+	.tx_buf_get = dsi_tx_buf_get_6g,
+	.tx_buf_put = dsi_tx_buf_put_6g,
+	.dma_base_get = dsi_dma_base_get_6g,
+	.calc_clk_rate = dsi_calc_clk_rate_6g,
+};
+
 static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
-	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064, &apq8064_dsi_cfg},
+	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064,
+		&apq8064_dsi_cfg, &msm_dsi_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_0,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1_1,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_2,
-						&msm8974_apq8084_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3, &msm8994_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1, &msm8916_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1, &msm8996_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, &sdm845_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3,
+		&msm8994_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1,
+		&msm8916_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1,
+		&msm8996_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
+		&sdm845_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 9cfdcf1c95d5..16c507911110 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -40,10 +40,22 @@ struct msm_dsi_config {
 	const int num_dsi;
 };
 
+struct msm_dsi_host_cfg_ops {
+	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);
+	int (*tx_buf_alloc)(struct msm_dsi_host *msm_host, int size);
+	void* (*tx_buf_get)(struct msm_dsi_host *msm_host);
+	void (*tx_buf_put)(struct msm_dsi_host *msm_host);
+	int (*dma_base_get)(struct msm_dsi_host *msm_host, uint64_t *iova);
+	int (*calc_clk_rate)(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+};
+
 struct msm_dsi_cfg_handler {
 	u32 major;
 	u32 minor;
 	const struct msm_dsi_config *cfg;
+	const struct msm_dsi_host_cfg_ops *ops;
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 2f1a2780658a..96fb5f635314 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -118,6 +118,7 @@ struct msm_dsi_host {
 	struct clk *byte_intf_clk;
 
 	u32 byte_clk_rate;
+	u32 pixel_clk_rate;
 	u32 esc_clk_rate;
 
 	/* DSI v2 specific clocks */
@@ -332,6 +333,54 @@ static int dsi_regulator_init(struct msm_dsi_host *msm_host)
 	return 0;
 }
 
+int dsi_clk_init_v2(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	int ret = 0;
+
+	msm_host->src_clk = msm_clk_get(pdev, "src");
+
+	if (IS_ERR(msm_host->src_clk)) {
+		ret = PTR_ERR(msm_host->src_clk);
+		pr_err("%s: can't find src clock. ret=%d\n",
+			__func__, ret);
+		msm_host->src_clk = NULL;
+		return ret;
+	}
+
+	msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
+	if (!msm_host->esc_clk_src) {
+		ret = -ENODEV;
+		pr_err("%s: can't get esc clock parent. ret=%d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
+	if (!msm_host->dsi_clk_src) {
+		ret = -ENODEV;
+		pr_err("%s: can't get src clock parent. ret=%d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	int ret = 0;
+
+	msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf");
+	if (IS_ERR(msm_host->byte_intf_clk)) {
+		ret = PTR_ERR(msm_host->byte_intf_clk);
+		pr_err("%s: can't find byte_intf clock. ret=%d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
 static int dsi_clk_init(struct msm_dsi_host *msm_host)
 {
 	struct platform_device *pdev = msm_host->pdev;
@@ -379,19 +428,6 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G &&
-	    cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V2_2_1) {
-		msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf");
-		if (IS_ERR(msm_host->byte_intf_clk)) {
-			ret = PTR_ERR(msm_host->byte_intf_clk);
-			pr_err("%s: can't find byte_intf clock. ret=%d\n",
-			        __func__, ret);
-			goto exit;
-		}
-	} else {
-		msm_host->byte_intf_clk = NULL;
-	}
-
 	msm_host->byte_clk_src = clk_get_parent(msm_host->byte_clk);
 	if (!msm_host->byte_clk_src) {
 		ret = -ENODEV;
@@ -406,31 +442,8 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
-		msm_host->src_clk = msm_clk_get(pdev, "src");
-		if (IS_ERR(msm_host->src_clk)) {
-			ret = PTR_ERR(msm_host->src_clk);
-			pr_err("%s: can't find src clock. ret=%d\n",
-				__func__, ret);
-			msm_host->src_clk = NULL;
-			goto exit;
-		}
-
-		msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
-		if (!msm_host->esc_clk_src) {
-			ret = -ENODEV;
-			pr_err("%s: can't get esc clock parent. ret=%d\n",
-				__func__, ret);
-			goto exit;
-		}
-
-		msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
-		if (!msm_host->dsi_clk_src) {
-			ret = -ENODEV;
-			pr_err("%s: can't get src clock parent. ret=%d\n",
-				__func__, ret);
-		}
-	}
+	if (cfg_hnd->ops->clk_init_ver)
+		ret = cfg_hnd->ops->clk_init_ver(msm_host);
 exit:
 	return ret;
 }
@@ -498,7 +511,7 @@ int msm_dsi_runtime_resume(struct device *dev)
 	return dsi_bus_clk_enable(msm_host);
 }
 
-static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -511,7 +524,7 @@ static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 		goto error;
 	}
 
-	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	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;
@@ -566,7 +579,7 @@ error:
 	return ret;
 }
 
-static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -592,7 +605,7 @@ static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 		goto error;
 	}
 
-	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	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;
@@ -634,98 +647,121 @@ error:
 	return ret;
 }
 
-static int dsi_link_clk_enable(struct msm_dsi_host *msm_host)
+void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host)
 {
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+	clk_disable_unprepare(msm_host->esc_clk);
+	clk_disable_unprepare(msm_host->pixel_clk);
+	if (msm_host->byte_intf_clk)
+		clk_disable_unprepare(msm_host->byte_intf_clk);
+	clk_disable_unprepare(msm_host->byte_clk);
+}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
-		return dsi_link_clk_enable_6g(msm_host);
-	else
-		return dsi_link_clk_enable_v2(msm_host);
+void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
+{
+	clk_disable_unprepare(msm_host->pixel_clk);
+	clk_disable_unprepare(msm_host->src_clk);
+	clk_disable_unprepare(msm_host->esc_clk);
+	clk_disable_unprepare(msm_host->byte_clk);
 }
 
-static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
+static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
+	struct drm_display_mode *mode = msm_host->mode;
+	u32 pclk_rate;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		clk_disable_unprepare(msm_host->esc_clk);
-		clk_disable_unprepare(msm_host->pixel_clk);
-		if (msm_host->byte_intf_clk)
-			clk_disable_unprepare(msm_host->byte_intf_clk);
-		clk_disable_unprepare(msm_host->byte_clk);
-	} else {
-		clk_disable_unprepare(msm_host->pixel_clk);
-		clk_disable_unprepare(msm_host->src_clk);
-		clk_disable_unprepare(msm_host->esc_clk);
-		clk_disable_unprepare(msm_host->byte_clk);
-	}
+	pclk_rate = mode->clock * 1000;
+
+	/*
+	 * For dual DSI mode, the current DRM mode has the complete width of the
+	 * panel. Since, the complete panel is driven by two DSI controllers,
+	 * the clock rates have to be split between the two dsi controllers.
+	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
+	 */
+	if (is_dual_dsi)
+		pclk_rate /= 2;
+
+	return pclk_rate;
 }
 
-static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host)
+static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
-	struct drm_display_mode *mode = msm_host->mode;
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	u8 lanes = msm_host->lanes;
 	u32 bpp = dsi_get_bpp(msm_host->format);
-	u32 pclk_rate;
+	u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_dual_dsi);
+	u64 pclk_bpp = (u64)pclk_rate * bpp;
 
-	if (!mode) {
-		pr_err("%s: mode not set\n", __func__);
-		return -EINVAL;
-	}
-
-	pclk_rate = mode->clock * 1000;
-	if (lanes > 0) {
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
-	} else {
+	if (lanes == 0) {
 		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
+		lanes = 1;
 	}
 
-	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
+	do_div(pclk_bpp, (8 * lanes));
 
-	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+	msm_host->pixel_clk_rate = pclk_rate;
+	msm_host->byte_clk_rate = pclk_bpp;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
-		unsigned int esc_mhz, esc_div;
-		unsigned long byte_mhz;
+	DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate,
+				msm_host->byte_clk_rate);
 
-		msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
+}
 
-		/*
-		 * esc clock is byte clock followed by a 4 bit divider,
-		 * we need to find an escape clock frequency within the
-		 * mipi DSI spec range within the maximum divider limit
-		 * We iterate here between an escape clock frequencey
-		 * between 20 Mhz to 5 Mhz and pick up the first one
-		 * that can be supported by our divider
-		 */
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+{
+	if (!msm_host->mode) {
+		pr_err("%s: mode not set\n", __func__);
+		return -EINVAL;
+	}
+
+	dsi_calc_pclk(msm_host, is_dual_dsi);
+	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+	return 0;
+}
 
-		byte_mhz = msm_host->byte_clk_rate / 1000000;
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+{
+	u32 bpp = dsi_get_bpp(msm_host->format);
+	u64 pclk_bpp;
+	unsigned int esc_mhz, esc_div;
+	unsigned long byte_mhz;
 
-		for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
-			esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
+	dsi_calc_pclk(msm_host, is_dual_dsi);
 
-			/*
-			 * TODO: Ideally, we shouldn't know what sort of divider
-			 * is available in mmss_cc, we're just assuming that
-			 * it'll always be a 4 bit divider. Need to come up with
-			 * a better way here.
-			 */
-			if (esc_div >= 1 && esc_div <= 16)
-				break;
-		}
+	pclk_bpp = (u64)dsi_get_pclk_rate(msm_host, is_dual_dsi) * bpp;
+	do_div(pclk_bpp, 8);
+	msm_host->src_clk_rate = pclk_bpp;
 
-		if (esc_mhz < 5)
-			return -EINVAL;
+	/*
+	 * esc clock is byte clock followed by a 4 bit divider,
+	 * we need to find an escape clock frequency within the
+	 * mipi DSI spec range within the maximum divider limit
+	 * We iterate here between an escape clock frequencey
+	 * between 20 Mhz to 5 Mhz and pick up the first one
+	 * that can be supported by our divider
+	 */
+
+	byte_mhz = msm_host->byte_clk_rate / 1000000;
 
-		msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
+	for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
+		esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
 
-		DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
-			msm_host->src_clk_rate);
+		/*
+		 * TODO: Ideally, we shouldn't know what sort of divider
+		 * is available in mmss_cc, we're just assuming that
+		 * it'll always be a 4 bit divider. Need to come up with
+		 * a better way here.
+		 */
+		if (esc_div >= 1 && esc_div <= 16)
+			break;
 	}
 
+	if (esc_mhz < 5)
+		return -EINVAL;
+
+	msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
+
+	DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
+		msm_host->src_clk_rate);
+
 	return 0;
 }
 
@@ -885,7 +921,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	dsi_write(msm_host, REG_DSI_CTRL, data);
 }
 
-static void dsi_timing_setup(struct msm_dsi_host *msm_host)
+static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u32 hs_start = 0, vs_start = 0; /* take sync start as 0 */
@@ -897,10 +933,26 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 	u32 ha_end = ha_start + mode->hdisplay;
 	u32 va_start = v_total - mode->vsync_start;
 	u32 va_end = va_start + mode->vdisplay;
+	u32 hdisplay = mode->hdisplay;
 	u32 wc;
 
 	DBG("");
 
+	/*
+	 * For dual DSI mode, the current DRM mode has
+	 * the complete width of the panel. Since, the complete
+	 * panel is driven by two DSI controllers, the horizontal
+	 * timings have to be split between the two dsi controllers.
+	 * Adjust the DSI host timing values accordingly.
+	 */
+	if (is_dual_dsi) {
+		h_total /= 2;
+		hs_end /= 2;
+		ha_start /= 2;
+		ha_end /= 2;
+		hdisplay /= 2;
+	}
+
 	if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) {
 		dsi_write(msm_host, REG_DSI_ACTIVE_H,
 			DSI_ACTIVE_H_START(ha_start) |
@@ -921,7 +973,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 			DSI_ACTIVE_VSYNC_VPOS_END(vs_end));
 	} else {		/* command mode */
 		/* image data and 1 byte write_memory_start cmd */
-		wc = mode->hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1;
+		wc = hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1;
 
 		dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_CTRL,
 			DSI_CMD_MDP_STREAM_CTRL_WORD_COUNT(wc) |
@@ -931,7 +983,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 					MIPI_DSI_DCS_LONG_WRITE));
 
 		dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_TOTAL,
-			DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(mode->hdisplay) |
+			DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(hdisplay) |
 			DSI_CMD_MDP_STREAM_TOTAL_V_TOTAL(mode->vdisplay));
 	}
 }
@@ -1015,50 +1067,37 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
 	}
 }
 
-/* dsi_cmd */
-static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
+int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size)
 {
 	struct drm_device *dev = msm_host->dev;
 	struct msm_drm_private *priv = dev->dev_private;
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	int ret;
 	uint64_t iova;
+	u8 *data;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED);
-		if (IS_ERR(msm_host->tx_gem_obj)) {
-			ret = PTR_ERR(msm_host->tx_gem_obj);
-			pr_err("%s: failed to allocate gem, %d\n",
-				__func__, ret);
-			msm_host->tx_gem_obj = NULL;
-			return ret;
-		}
+	data = msm_gem_kernel_new(dev, size, MSM_BO_UNCACHED,
+					priv->kms->aspace,
+					&msm_host->tx_gem_obj, &iova);
 
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
-				priv->kms->aspace, &iova);
-		if (ret) {
-			pr_err("%s: failed to get iova, %d\n", __func__, ret);
-			return ret;
-		}
+	if (IS_ERR(data)) {
+		msm_host->tx_gem_obj = NULL;
+		return PTR_ERR(data);
+	}
 
-		if (iova & 0x07) {
-			pr_err("%s: buf NOT 8 bytes aligned\n", __func__);
-			return -EINVAL;
-		}
+	msm_host->tx_size = msm_host->tx_gem_obj->size;
 
-		msm_host->tx_size = msm_host->tx_gem_obj->size;
-	} else {
-		msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
+	return 0;
+}
+
+int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size)
+{
+	struct drm_device *dev = msm_host->dev;
+
+	msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
 					&msm_host->tx_buf_paddr, GFP_KERNEL);
-		if (!msm_host->tx_buf) {
-			ret = -ENOMEM;
-			pr_err("%s: failed to allocate tx buf, %d\n",
-				__func__, ret);
-			return ret;
-		}
+	if (!msm_host->tx_buf)
+		return -ENOMEM;
 
-		msm_host->tx_size = size;
-	}
+	msm_host->tx_size = size;
 
 	return 0;
 }
@@ -1089,6 +1128,21 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 			msm_host->tx_buf_paddr);
 }
 
+void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host)
+{
+	return msm_gem_get_vaddr(msm_host->tx_gem_obj);
+}
+
+void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host)
+{
+	return msm_host->tx_buf;
+}
+
+void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host)
+{
+	msm_gem_put_vaddr(msm_host->tx_gem_obj);
+}
+
 /*
  * prepare cmd buffer to be txed
  */
@@ -1113,15 +1167,11 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 		return -EINVAL;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		data = msm_gem_get_vaddr(msm_host->tx_gem_obj);
-		if (IS_ERR(data)) {
-			ret = PTR_ERR(data);
-			pr_err("%s: get vaddr failed, %d\n", __func__, ret);
-			return ret;
-		}
-	} else {
-		data = msm_host->tx_buf;
+	data = cfg_hnd->ops->tx_buf_get(msm_host);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		pr_err("%s: get vaddr failed, %d\n", __func__, ret);
+		return ret;
 	}
 
 	/* MSM specific command format in memory */
@@ -1142,8 +1192,8 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 	if (packet.size < len)
 		memset(data + packet.size, 0xff, len - packet.size);
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
-		msm_gem_put_vaddr(msm_host->tx_gem_obj);
+	if (cfg_hnd->ops->tx_buf_put)
+		cfg_hnd->ops->tx_buf_put(msm_host);
 
 	return len;
 }
@@ -1190,24 +1240,38 @@ static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 	return msg->rx_len;
 }
 
-static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
+int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *dma_base)
 {
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct drm_device *dev = msm_host->dev;
 	struct msm_drm_private *priv = dev->dev_private;
+
+	if (!dma_base)
+		return -EINVAL;
+
+	return msm_gem_get_iova(msm_host->tx_gem_obj,
+				priv->kms->aspace, dma_base);
+}
+
+int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *dma_base)
+{
+	if (!dma_base)
+		return -EINVAL;
+
+	*dma_base = msm_host->tx_buf_paddr;
+	return 0;
+}
+
+static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
+{
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 	uint64_t dma_base;
 	bool triggered;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
-				priv->kms->aspace, &dma_base);
-		if (ret) {
-			pr_err("%s: failed to get iova: %d\n", __func__, ret);
-			return ret;
-		}
-	} else {
-		dma_base = msm_host->tx_buf_paddr;
+	ret = cfg_hnd->ops->dma_base_get(msm_host, &dma_base);
+	if (ret) {
+		pr_err("%s: failed to get iova: %d\n", __func__, ret);
+		return ret;
 	}
 
 	reinit_completion(&msm_host->dma_comp);
@@ -1845,6 +1909,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct platform_device *pdev = msm_host->pdev;
 	int ret;
 
@@ -1865,7 +1930,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 	}
 
 	msm_host->dev = dev;
-	ret = dsi_tx_buf_alloc(msm_host, SZ_4K);
+	ret = cfg_hnd->ops->tx_buf_alloc(msm_host, SZ_4K);
 	if (ret) {
 		pr_err("%s: alloc tx gem obj failed, %d\n", __func__, ret);
 		return ret;
@@ -1898,7 +1963,7 @@ int msm_dsi_host_register(struct mipi_dsi_host *host, bool check_defer)
 		 * output
 		 */
 		if (check_defer && msm_host->device_node) {
-			if (!of_drm_find_panel(msm_host->device_node))
+			if (IS_ERR(of_drm_find_panel(msm_host->device_node)))
 				if (!of_drm_find_bridge(msm_host->device_node))
 					return -EPROBE_DEFER;
 		}
@@ -1923,6 +1988,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 				const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	/* TODO: make sure dsi_cmd_mdp is idle.
 	 * Since DSI6G v1.2.0, we can set DSI_TRIG_CTRL.BLOCK_DMA_WITHIN_FRAME
@@ -1935,7 +2001,7 @@ 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);
-	dsi_link_clk_enable(msm_host);
+	cfg_hnd->ops->link_clk_enable(msm_host);
 
 	/* TODO: vote for bus bandwidth */
 
@@ -1956,6 +2022,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
 				const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_CMD_DMA_DONE, 0);
 	dsi_write(msm_host, REG_DSI_CTRL, msm_host->dma_cmd_ctrl_restore);
@@ -1965,7 +2032,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
 
 	/* TODO: unvote for bus bandwidth */
 
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 }
 
@@ -2129,7 +2196,6 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 	struct msm_dsi_pll *src_pll)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct clk *byte_clk_provider, *pixel_clk_provider;
 	int ret;
 
@@ -2155,14 +2221,16 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
+	if (msm_host->dsi_clk_src) {
 		ret = clk_set_parent(msm_host->dsi_clk_src, pixel_clk_provider);
 		if (ret) {
 			pr_err("%s: can't set parent to dsi_clk_src. ret=%d\n",
 				__func__, ret);
 			goto exit;
 		}
+	}
 
+	if (msm_host->esc_clk_src) {
 		ret = clk_set_parent(msm_host->esc_clk_src, byte_clk_provider);
 		if (ret) {
 			pr_err("%s: can't set parent to esc_clk_src. ret=%d\n",
@@ -2189,12 +2257,14 @@ void msm_dsi_host_reset_phy(struct mipi_dsi_host *host)
 }
 
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
-	struct msm_dsi_phy_clk_request *clk_req)
+			struct msm_dsi_phy_clk_request *clk_req,
+			bool is_dual_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 
-	ret = dsi_calc_clk_rate(msm_host);
+	ret = cfg_hnd->ops->calc_clk_rate(msm_host, is_dual_dsi);
 	if (ret) {
 		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
 		return;
@@ -2256,9 +2326,11 @@ static void msm_dsi_sfpb_config(struct msm_dsi_host *msm_host, bool enable)
 }
 
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings)
+			struct msm_dsi_phy_shared_timings *phy_shared_timings,
+			bool is_dual_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret = 0;
 
 	mutex_lock(&msm_host->dev_mutex);
@@ -2277,7 +2349,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	}
 
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	ret = dsi_link_clk_enable(msm_host);
+	ret = cfg_hnd->ops->link_clk_enable(msm_host);
 	if (ret) {
 		pr_err("%s: failed to enable link clocks. ret=%d\n",
 		       __func__, ret);
@@ -2291,7 +2363,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 		goto fail_disable_clk;
 	}
 
-	dsi_timing_setup(msm_host);
+	dsi_timing_setup(msm_host, is_dual_dsi);
 	dsi_sw_reset(msm_host);
 	dsi_ctrl_config(msm_host, true, phy_shared_timings);
 
@@ -2304,7 +2376,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	return 0;
 
 fail_disable_clk:
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 fail_disable_reg:
 	dsi_host_regulator_disable(msm_host);
@@ -2316,6 +2388,7 @@ unlock_ret:
 int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	mutex_lock(&msm_host->dev_mutex);
 	if (!msm_host->power_on) {
@@ -2330,7 +2403,7 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 
 	pinctrl_pm_select_sleep_state(&msm_host->pdev->dev);
 
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 
 	dsi_host_regulator_disable(msm_host);
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 4cb1cb68878b..5224010d90e4 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -134,8 +134,9 @@ static int enable_phy(struct msm_dsi *msm_dsi, int src_pll_id,
 {
 	struct msm_dsi_phy_clk_request clk_req;
 	int ret;
+	bool is_dual_dsi = IS_DUAL_DSI();
 
-	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req);
+	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_dual_dsi);
 
 	ret = msm_dsi_phy_enable(msm_dsi->phy, src_pll_id, &clk_req);
 	msm_dsi_phy_get_shared_timings(msm_dsi->phy, shared_timings);
@@ -305,102 +306,25 @@ static void dsi_mgr_connector_destroy(struct drm_connector *connector)
 	kfree(dsi_connector);
 }
 
-static void dsi_dual_connector_fix_modes(struct drm_connector *connector)
-{
-	struct drm_display_mode *mode, *m;
-
-	/* Only support left-right mode */
-	list_for_each_entry_safe(mode, m, &connector->probed_modes, head) {
-		mode->clock >>= 1;
-		mode->hdisplay >>= 1;
-		mode->hsync_start >>= 1;
-		mode->hsync_end >>= 1;
-		mode->htotal >>= 1;
-		drm_mode_set_name(mode);
-	}
-}
-
-static int dsi_dual_connector_tile_init(
-			struct drm_connector *connector, int id)
-{
-	struct drm_display_mode *mode;
-	/* Fake topology id */
-	char topo_id[8] = {'M', 'S', 'M', 'D', 'U', 'D', 'S', 'I'};
-
-	if (connector->tile_group) {
-		DBG("Tile property has been initialized");
-		return 0;
-	}
-
-	/* Use the first mode only for now */
-	mode = list_first_entry(&connector->probed_modes,
-				struct drm_display_mode,
-				head);
-	if (!mode)
-		return -EINVAL;
-
-	connector->tile_group = drm_mode_get_tile_group(
-					connector->dev, topo_id);
-	if (!connector->tile_group)
-		connector->tile_group = drm_mode_create_tile_group(
-					connector->dev, topo_id);
-	if (!connector->tile_group) {
-		pr_err("%s: failed to create tile group\n", __func__);
-		return -ENOMEM;
-	}
-
-	connector->has_tile = true;
-	connector->tile_is_single_monitor = true;
-
-	/* mode has been fixed */
-	connector->tile_h_size = mode->hdisplay;
-	connector->tile_v_size = mode->vdisplay;
-
-	/* Only support left-right mode */
-	connector->num_h_tile = 2;
-	connector->num_v_tile = 1;
-
-	connector->tile_v_loc = 0;
-	connector->tile_h_loc = (id == DSI_RIGHT) ? 1 : 0;
-
-	return 0;
-}
-
 static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 {
 	int id = dsi_mgr_connector_get_id(connector);
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_panel *panel = msm_dsi->panel;
-	int ret, num;
+	int num;
 
 	if (!panel)
 		return 0;
 
-	/* Since we have 2 connectors, but only 1 drm_panel in dual DSI mode,
-	 * panel should not attach to any connector.
-	 * Only temporarily attach panel to the current connector here,
-	 * to let panel set mode to this connector.
+	/*
+	 * In dual DSI mode, we have one connector that can be
+	 * attached to the drm_panel.
 	 */
 	drm_panel_attach(panel, connector);
 	num = drm_panel_get_modes(panel);
-	drm_panel_detach(panel);
 	if (!num)
 		return 0;
 
-	if (IS_DUAL_DSI()) {
-		/* report half resolution to user */
-		dsi_dual_connector_fix_modes(connector);
-		ret = dsi_dual_connector_tile_init(connector, id);
-		if (ret)
-			return ret;
-		ret = drm_mode_connector_set_tile_property(connector);
-		if (ret) {
-			pr_err("%s: set tile property failed, %d\n",
-					__func__, ret);
-			return ret;
-		}
-	}
-
 	return num;
 }
 
@@ -454,11 +378,11 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 	if (ret)
 		goto phy_en_fail;
 
-	/* Do nothing with the host if it is DSI 1 in case of dual DSI */
-	if (is_dual_dsi && (DSI_1 == id))
+	/* 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;
 
-	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id]);
+	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_dual_dsi);
 	if (ret) {
 		pr_err("%s: power on host %d failed, %d\n", __func__, id, ret);
 		goto host_on_fail;
@@ -466,7 +390,7 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 
 	if (is_dual_dsi && msm_dsi1) {
 		ret = msm_dsi_host_power_on(msm_dsi1->host,
-					    &phy_shared_timings[DSI_1]);
+				&phy_shared_timings[DSI_1], is_dual_dsi);
 		if (ret) {
 			pr_err("%s: power on host1 failed, %d\n",
 							__func__, ret);
@@ -556,11 +480,11 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 		return;
 
 	/*
-	 * Do nothing with the host if it is DSI 1 in case of dual DSI.
+	 * Do nothing with the host if it is slave-DSI in case of dual DSI.
 	 * It is safe to call dsi_mgr_phy_disable() here because a single PHY
 	 * won't be diabled until both PHYs request disable.
 	 */
-	if (is_dual_dsi && (DSI_1 == id))
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		goto disable_phy;
 
 	if (panel) {
@@ -621,7 +545,7 @@ static void dsi_mgr_bridge_mode_set(struct drm_bridge *bridge,
 			mode->vsync_end, mode->vtotal,
 			mode->type, mode->flags);
 
-	if (is_dual_dsi && (DSI_1 == id))
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	msm_dsi_host_set_display_mode(host, adjusted_mode);
@@ -684,11 +608,28 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id)
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, msm_dsi->encoder);
+	drm_connector_attach_encoder(connector, msm_dsi->encoder);
 
 	return connector;
 }
 
+bool msm_dsi_manager_validate_current_config(u8 id)
+{
+	bool is_dual_dsi = IS_DUAL_DSI();
+
+	/*
+	 * For dual DSI, we only have one drm panel. For this
+	 * use case, we register only one bridge/connector.
+	 * Skip bridge/connector initialisation if it is
+	 * slave-DSI for dual DSI configuration.
+	 */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) {
+		DBG("Skip bridge registration for slave DSI->id: %d\n", id);
+		return false;
+	}
+	return true;
+}
+
 /* initialize bridge */
 struct drm_bridge *msm_dsi_manager_bridge_init(u8 id)
 {
@@ -751,12 +692,8 @@ struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id)
 	connector_list = &dev->mode_config.connector_list;
 
 	list_for_each_entry(connector, connector_list, head) {
-		int i;
-
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == encoder->base.id)
-				return connector;
-		}
+		if (drm_connector_has_possible_encoder(connector, encoder))
+			return connector;
 	}
 
 	return ERR_PTR(-ENODEV);
@@ -836,6 +773,7 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
 	struct drm_encoder *encoder;
+	bool cmd_mode;
 
 	/*
 	 * drm_device pointer is assigned to msm_dsi only in the modeset_init
@@ -850,10 +788,11 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 	priv = dev->dev_private;
 	kms = priv->kms;
 	encoder = msm_dsi_get_encoder(msm_dsi);
+	cmd_mode = !(device_flags &
+				 MIPI_DSI_MODE_VIDEO);
 
 	if (encoder && kms->funcs->set_encoder_mode)
-		if (!(device_flags & MIPI_DSI_MODE_VIDEO))
-			kms->funcs->set_encoder_mode(kms, encoder, true);
+		kms->funcs->set_encoder_mode(kms, encoder, cmd_mode);
 }
 
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi)
diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index c4c37a7df637..4c03f0b7343e 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -798,6 +798,8 @@ struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	spin_lock_init(&pll_10nm->postdiv_lock);
+
 	pll = &pll_10nm->base;
 	pll->min_rate = 1000000000UL;
 	pll->max_rate = 3500000000UL;
diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c
index 6f3fc6b0f0a3..058ff92a0207 100644
--- a/drivers/gpu/drm/msm/edp/edp_connector.c
+++ b/drivers/gpu/drm/msm/edp/edp_connector.c
@@ -56,7 +56,7 @@ static int edp_connector_get_modes(struct drm_connector *connector)
 	if (ret)
 		return ret;
 
-	drm_mode_connector_update_edid_property(connector, drm_edid);
+	drm_connector_update_edid_property(connector, drm_edid);
 	if (drm_edid)
 		ret = drm_add_edid_modes(connector, drm_edid);
 
@@ -134,7 +134,7 @@ struct drm_connector *msm_edp_connector_init(struct msm_edp *edp)
 	connector->interlace_allowed = false;
 	connector->doublescan_allowed = false;
 
-	drm_mode_connector_attach_encoder(connector, edp->encoder);
+	drm_connector_attach_encoder(connector, edp->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index c0848dfedd50..e9c9a0af508e 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -392,7 +392,7 @@ static int msm_hdmi_connector_get_modes(struct drm_connector *connector)
 	hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl);
 
 	hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		ret = drm_add_edid_modes(connector, edid);
@@ -477,7 +477,7 @@ struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi)
 		return ERR_PTR(ret);
 	}
 
-	drm_mode_connector_attach_encoder(connector, hdmi->encoder);
+	drm_connector_attach_encoder(connector, hdmi->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index f0635c3da7f4..c1f1779c980f 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -71,12 +71,15 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
+	if (kms->funcs->commit) {
+		DRM_DEBUG_ATOMIC("triggering commit\n");
+		kms->funcs->commit(kms, state);
+	}
+
 	msm_atomic_wait_for_commit_done(dev, state);
 
 	kms->funcs->complete_commit(kms, state);
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
-
 	drm_atomic_helper_commit_hw_done(state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 1ff3fda245d1..f0da0d3c8a80 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -16,26 +16,101 @@
  */
 
 #ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
 #include "msm_drv.h"
 #include "msm_gpu.h"
 #include "msm_kms.h"
 #include "msm_debugfs.h"
 
-static int msm_gpu_show(struct drm_device *dev, struct seq_file *m)
+struct msm_gpu_show_priv {
+	struct msm_gpu_state *state;
+	struct drm_device *dev;
+};
+
+static int msm_gpu_show(struct seq_file *m, void *arg)
+{
+	struct drm_printer p = drm_seq_file_printer(m);
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	drm_printf(&p, "%s Status:\n", gpu->name);
+	gpu->funcs->show(gpu, show_priv->state, &p);
+
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	return 0;
+}
+
+static int msm_gpu_release(struct inode *inode, struct file *file)
 {
+	struct seq_file *m = file->private_data;
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	gpu->funcs->gpu_state_put(show_priv->state);
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	kfree(show_priv);
+
+	return single_release(inode, file);
+}
+
+static int msm_gpu_open(struct inode *inode, struct file *file)
+{
+	struct drm_device *dev = inode->i_private;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
+	struct msm_gpu_show_priv *show_priv;
+	int ret;
 
-	if (gpu) {
-		seq_printf(m, "%s Status:\n", gpu->name);
-		pm_runtime_get_sync(&gpu->pdev->dev);
-		gpu->funcs->show(gpu, m);
-		pm_runtime_put_sync(&gpu->pdev->dev);
+	if (!gpu)
+		return -ENODEV;
+
+	show_priv = kmalloc(sizeof(*show_priv), GFP_KERNEL);
+	if (!show_priv)
+		return -ENOMEM;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	show_priv->state = gpu->funcs->gpu_state_get(gpu);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	if (IS_ERR(show_priv->state)) {
+		ret = PTR_ERR(show_priv->state);
+		kfree(show_priv);
+		return ret;
 	}
 
-	return 0;
+	show_priv->dev = dev;
+
+	return single_open(file, msm_gpu_show, show_priv);
 }
 
+static const struct file_operations msm_gpu_fops = {
+	.owner = THIS_MODULE,
+	.open = msm_gpu_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = msm_gpu_release,
+};
+
 static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -105,7 +180,6 @@ static int show_locked(struct seq_file *m, void *arg)
 }
 
 static struct drm_info_list msm_debugfs_list[] = {
-		{"gpu", show_locked, 0, msm_gpu_show},
 		{"gem", show_locked, 0, msm_gem_show},
 		{ "mm", show_locked, 0, msm_mm_show },
 		{ "fb", show_locked, 0, msm_fb_show },
@@ -158,6 +232,9 @@ int msm_debugfs_init(struct drm_minor *minor)
 		return ret;
 	}
 
+	debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root,
+		dev, &msm_gpu_fops);
+
 	if (priv->kms->funcs->debugfs_init) {
 		ret = priv->kms->funcs->debugfs_init(priv->kms, minor);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 021a0b6f9a59..46876bc8b707 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -15,6 +16,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <drm/drm_of.h>
 
 #include "msm_drv.h"
@@ -149,7 +152,7 @@ struct vblank_event {
 	bool enable;
 };
 
-static void vblank_ctrl_worker(struct work_struct *work)
+static void vblank_ctrl_worker(struct kthread_work *work)
 {
 	struct msm_vblank_ctrl *vbl_ctrl = container_of(work,
 						struct msm_vblank_ctrl, work);
@@ -197,7 +200,8 @@ static int vblank_ctrl_queue_work(struct msm_drm_private *priv,
 	list_add_tail(&vbl_ev->node, &vbl_ctrl->event_list);
 	spin_unlock_irqrestore(&vbl_ctrl->lock, flags);
 
-	queue_work(priv->wq, &vbl_ctrl->work);
+	kthread_queue_work(&priv->disp_thread[crtc_id].worker,
+			&vbl_ctrl->work);
 
 	return 0;
 }
@@ -208,19 +212,36 @@ static int msm_drm_uninit(struct device *dev)
 	struct drm_device *ddev = platform_get_drvdata(pdev);
 	struct msm_drm_private *priv = ddev->dev_private;
 	struct msm_kms *kms = priv->kms;
+	struct msm_mdss *mdss = priv->mdss;
 	struct msm_vblank_ctrl *vbl_ctrl = &priv->vblank_ctrl;
 	struct vblank_event *vbl_ev, *tmp;
+	int i;
 
 	/* We must cancel and cleanup any pending vblank enable/disable
 	 * work before drm_irq_uninstall() to avoid work re-enabling an
 	 * irq after uninstall has disabled it.
 	 */
-	cancel_work_sync(&vbl_ctrl->work);
+	kthread_flush_work(&vbl_ctrl->work);
 	list_for_each_entry_safe(vbl_ev, tmp, &vbl_ctrl->event_list, node) {
 		list_del(&vbl_ev->node);
 		kfree(vbl_ev);
 	}
 
+	/* clean up display commit/event worker threads */
+	for (i = 0; i < priv->num_crtcs; i++) {
+		if (priv->disp_thread[i].thread) {
+			kthread_flush_worker(&priv->disp_thread[i].worker);
+			kthread_stop(priv->disp_thread[i].thread);
+			priv->disp_thread[i].thread = NULL;
+		}
+
+		if (priv->event_thread[i].thread) {
+			kthread_flush_worker(&priv->event_thread[i].worker);
+			kthread_stop(priv->event_thread[i].thread);
+			priv->event_thread[i].thread = NULL;
+		}
+	}
+
 	msm_gem_shrinker_cleanup(ddev);
 
 	drm_kms_helper_poll_fini(ddev);
@@ -243,9 +264,6 @@ static int msm_drm_uninit(struct device *dev)
 	flush_workqueue(priv->wq);
 	destroy_workqueue(priv->wq);
 
-	flush_workqueue(priv->atomic_wq);
-	destroy_workqueue(priv->atomic_wq);
-
 	if (kms && kms->funcs)
 		kms->funcs->destroy(kms);
 
@@ -258,7 +276,8 @@ static int msm_drm_uninit(struct device *dev)
 
 	component_unbind_all(dev, ddev);
 
-	msm_mdss_destroy(ddev);
+	if (mdss && mdss->funcs)
+		mdss->funcs->destroy(ddev);
 
 	ddev->dev_private = NULL;
 	drm_dev_unref(ddev);
@@ -268,6 +287,10 @@ static int msm_drm_uninit(struct device *dev)
 	return 0;
 }
 
+#define KMS_MDP4 4
+#define KMS_MDP5 5
+#define KMS_DPU  3
+
 static int get_mdp_ver(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -357,7 +380,9 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	struct drm_device *ddev;
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
-	int ret;
+	struct msm_mdss *mdss;
+	int ret, i;
+	struct sched_param param;
 
 	ddev = drm_dev_alloc(drv, dev);
 	if (IS_ERR(ddev)) {
@@ -369,53 +394,61 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
-		drm_dev_unref(ddev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_unref_drm_dev;
 	}
 
 	ddev->dev_private = priv;
 	priv->dev = ddev;
 
-	ret = msm_mdss_init(ddev);
-	if (ret) {
-		kfree(priv);
-		drm_dev_unref(ddev);
-		return ret;
+	switch (get_mdp_ver(pdev)) {
+	case KMS_MDP5:
+		ret = mdp5_mdss_init(ddev);
+		break;
+	case KMS_DPU:
+		ret = dpu_mdss_init(ddev);
+		break;
+	default:
+		ret = 0;
+		break;
 	}
+	if (ret)
+		goto err_free_priv;
+
+	mdss = priv->mdss;
 
 	priv->wq = alloc_ordered_workqueue("msm", 0);
-	priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0);
 
 	INIT_LIST_HEAD(&priv->inactive_list);
 	INIT_LIST_HEAD(&priv->vblank_ctrl.event_list);
-	INIT_WORK(&priv->vblank_ctrl.work, vblank_ctrl_worker);
+	kthread_init_work(&priv->vblank_ctrl.work, vblank_ctrl_worker);
 	spin_lock_init(&priv->vblank_ctrl.lock);
 
 	drm_mode_config_init(ddev);
 
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
-	if (ret) {
-		msm_mdss_destroy(ddev);
-		kfree(priv);
-		drm_dev_unref(ddev);
-		return ret;
-	}
+	if (ret)
+		goto err_destroy_mdss;
 
 	ret = msm_init_vram(ddev);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	msm_gem_shrinker_init(ddev);
 
 	switch (get_mdp_ver(pdev)) {
-	case 4:
+	case KMS_MDP4:
 		kms = mdp4_kms_init(ddev);
 		priv->kms = kms;
 		break;
-	case 5:
+	case KMS_MDP5:
 		kms = mdp5_kms_init(ddev);
 		break;
+	case KMS_DPU:
+		kms = dpu_kms_init(ddev);
+		priv->kms = kms;
+		break;
 	default:
 		kms = ERR_PTR(-ENODEV);
 		break;
@@ -430,24 +463,100 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		 */
 		dev_err(dev, "failed to load kms\n");
 		ret = PTR_ERR(kms);
-		goto fail;
+		goto err_msm_uninit;
 	}
 
+	/* Enable normalization of plane zpos */
+	ddev->mode_config.normalize_zpos = true;
+
 	if (kms) {
 		ret = kms->funcs->hw_init(kms);
 		if (ret) {
 			dev_err(dev, "kms hw init failed: %d\n", ret);
-			goto fail;
+			goto err_msm_uninit;
 		}
 	}
 
 	ddev->mode_config.funcs = &mode_config_funcs;
 	ddev->mode_config.helper_private = &mode_config_helper_funcs;
 
+	/**
+	 * this priority was found during empiric testing to have appropriate
+	 * realtime scheduling to process display updates and interact with
+	 * other real time and normal priority task
+	 */
+	param.sched_priority = 16;
+	for (i = 0; i < priv->num_crtcs; i++) {
+
+		/* initialize display thread */
+		priv->disp_thread[i].crtc_id = priv->crtcs[i]->base.id;
+		kthread_init_worker(&priv->disp_thread[i].worker);
+		priv->disp_thread[i].dev = ddev;
+		priv->disp_thread[i].thread =
+			kthread_run(kthread_worker_fn,
+				&priv->disp_thread[i].worker,
+				"crtc_commit:%d", priv->disp_thread[i].crtc_id);
+		ret = sched_setscheduler(priv->disp_thread[i].thread,
+							SCHED_FIFO, &param);
+		if (ret)
+			pr_warn("display thread priority update failed: %d\n",
+									ret);
+
+		if (IS_ERR(priv->disp_thread[i].thread)) {
+			dev_err(dev, "failed to create crtc_commit kthread\n");
+			priv->disp_thread[i].thread = NULL;
+		}
+
+		/* initialize event thread */
+		priv->event_thread[i].crtc_id = priv->crtcs[i]->base.id;
+		kthread_init_worker(&priv->event_thread[i].worker);
+		priv->event_thread[i].dev = ddev;
+		priv->event_thread[i].thread =
+			kthread_run(kthread_worker_fn,
+				&priv->event_thread[i].worker,
+				"crtc_event:%d", priv->event_thread[i].crtc_id);
+		/**
+		 * event thread should also run at same priority as disp_thread
+		 * because it is handling frame_done events. A lower priority
+		 * event thread and higher priority disp_thread can causes
+		 * frame_pending counters beyond 2. This can lead to commit
+		 * failure at crtc commit level.
+		 */
+		ret = sched_setscheduler(priv->event_thread[i].thread,
+							SCHED_FIFO, &param);
+		if (ret)
+			pr_warn("display event thread priority update failed: %d\n",
+									ret);
+
+		if (IS_ERR(priv->event_thread[i].thread)) {
+			dev_err(dev, "failed to create crtc_event kthread\n");
+			priv->event_thread[i].thread = NULL;
+		}
+
+		if ((!priv->disp_thread[i].thread) ||
+				!priv->event_thread[i].thread) {
+			/* clean up previously created threads if any */
+			for ( ; i >= 0; i--) {
+				if (priv->disp_thread[i].thread) {
+					kthread_stop(
+						priv->disp_thread[i].thread);
+					priv->disp_thread[i].thread = NULL;
+				}
+
+				if (priv->event_thread[i].thread) {
+					kthread_stop(
+						priv->event_thread[i].thread);
+					priv->event_thread[i].thread = NULL;
+				}
+			}
+			goto err_msm_uninit;
+		}
+	}
+
 	ret = drm_vblank_init(ddev, priv->num_crtcs);
 	if (ret < 0) {
 		dev_err(dev, "failed to initialize vblank\n");
-		goto fail;
+		goto err_msm_uninit;
 	}
 
 	if (kms) {
@@ -456,13 +565,13 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		pm_runtime_put_sync(dev);
 		if (ret < 0) {
 			dev_err(dev, "failed to install IRQ handler\n");
-			goto fail;
+			goto err_msm_uninit;
 		}
 	}
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	drm_mode_config_reset(ddev);
 
@@ -473,15 +582,23 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	ret = msm_debugfs_late_init(ddev);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	drm_kms_helper_poll_init(ddev);
 
 	return 0;
 
-fail:
+err_msm_uninit:
 	msm_drm_uninit(dev);
 	return ret;
+err_destroy_mdss:
+	if (mdss && mdss->funcs)
+		mdss->funcs->destroy(ddev);
+err_free_priv:
+	kfree(priv);
+err_unref_drm_dev:
+	drm_dev_unref(ddev);
+	return ret;
 }
 
 /*
@@ -894,16 +1011,35 @@ static struct drm_driver msm_driver = {
 static int msm_pm_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	/* TODO: Use atomic helper suspend/resume */
+	if (kms && kms->funcs && kms->funcs->pm_suspend)
+		return kms->funcs->pm_suspend(dev);
 
 	drm_kms_helper_poll_disable(ddev);
 
+	priv->pm_state = drm_atomic_helper_suspend(ddev);
+	if (IS_ERR(priv->pm_state)) {
+		drm_kms_helper_poll_enable(ddev);
+		return PTR_ERR(priv->pm_state);
+	}
+
 	return 0;
 }
 
 static int msm_pm_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	/* TODO: Use atomic helper suspend/resume */
+	if (kms && kms->funcs && kms->funcs->pm_resume)
+		return kms->funcs->pm_resume(dev);
 
+	drm_atomic_helper_resume(ddev, priv->pm_state);
 	drm_kms_helper_poll_enable(ddev);
 
 	return 0;
@@ -915,11 +1051,12 @@ static int msm_runtime_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
 
 	DBG("");
 
-	if (priv->mdss)
-		return msm_mdss_disable(priv->mdss);
+	if (mdss && mdss->funcs)
+		return mdss->funcs->disable(mdss);
 
 	return 0;
 }
@@ -928,11 +1065,12 @@ static int msm_runtime_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
 
 	DBG("");
 
-	if (priv->mdss)
-		return msm_mdss_enable(priv->mdss);
+	if (mdss && mdss->funcs)
+		return mdss->funcs->enable(mdss);
 
 	return 0;
 }
@@ -1031,12 +1169,13 @@ static int add_display_components(struct device *dev,
 	int ret;
 
 	/*
-	 * MDP5 based devices don't have a flat hierarchy. There is a top level
-	 * parent: MDSS, and children: MDP5, DSI, HDMI, eDP etc. Populate the
-	 * children devices, find the MDP5 node, and then add the interfaces
-	 * to our components list.
+	 * MDP5/DPU based devices don't have a flat hierarchy. There is a top
+	 * level parent: MDSS, and children: MDP5/DPU, DSI, HDMI, eDP etc.
+	 * Populate the children devices, find the MDP5/DPU node, and then add
+	 * the interfaces to our components list.
 	 */
-	if (of_device_is_compatible(dev->of_node, "qcom,mdss")) {
+	if (of_device_is_compatible(dev->of_node, "qcom,mdss") ||
+	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) {
 		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to populate children devices\n");
@@ -1146,8 +1285,9 @@ static int msm_pdev_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id dt_match[] = {
-	{ .compatible = "qcom,mdp4", .data = (void *)4 },	/* MDP4 */
-	{ .compatible = "qcom,mdss", .data = (void *)5 },	/* MDP5 MDSS */
+	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
+	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
+	{ .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
@@ -1169,6 +1309,7 @@ static int __init msm_drm_register(void)
 
 	DBG("init");
 	msm_mdp_register();
+	msm_dpu_register();
 	msm_dsi_register();
 	msm_edp_register();
 	msm_hdmi_register();
@@ -1185,6 +1326,7 @@ static void __exit msm_drm_unregister(void)
 	msm_edp_unregister();
 	msm_dsi_unregister();
 	msm_mdp_unregister();
+	msm_dpu_unregister();
 }
 
 module_init(msm_drm_register);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index b2da1fbf81e0..0cba86ed3f54 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -33,6 +34,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_device.h>
 #include <asm/sizes.h>
+#include <linux/kthread.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
@@ -54,6 +56,12 @@ struct msm_fence_context;
 struct msm_gem_address_space;
 struct msm_gem_vma;
 
+#define MAX_CRTCS      8
+#define MAX_PLANES     20
+#define MAX_ENCODERS   8
+#define MAX_BRIDGES    8
+#define MAX_CONNECTORS 8
+
 struct msm_file_private {
 	rwlock_t queuelock;
 	struct list_head submitqueues;
@@ -68,12 +76,77 @@ enum msm_mdp_plane_property {
 };
 
 struct msm_vblank_ctrl {
-	struct work_struct work;
+	struct kthread_work work;
 	struct list_head event_list;
 	spinlock_t lock;
 };
 
 #define MSM_GPU_MAX_RINGS 4
+#define MAX_H_TILES_PER_DISPLAY 2
+
+/**
+ * enum msm_display_caps - features/capabilities supported by displays
+ * @MSM_DISPLAY_CAP_VID_MODE:           Video or "active" mode supported
+ * @MSM_DISPLAY_CAP_CMD_MODE:           Command mode supported
+ * @MSM_DISPLAY_CAP_HOT_PLUG:           Hot plug detection supported
+ * @MSM_DISPLAY_CAP_EDID:               EDID supported
+ */
+enum msm_display_caps {
+	MSM_DISPLAY_CAP_VID_MODE	= BIT(0),
+	MSM_DISPLAY_CAP_CMD_MODE	= BIT(1),
+	MSM_DISPLAY_CAP_HOT_PLUG	= BIT(2),
+	MSM_DISPLAY_CAP_EDID		= BIT(3),
+};
+
+/**
+ * enum msm_event_wait - type of HW events to wait for
+ * @MSM_ENC_COMMIT_DONE - wait for the driver to flush the registers to HW
+ * @MSM_ENC_TX_COMPLETE - wait for the HW to transfer the frame to panel
+ * @MSM_ENC_VBLANK - wait for the HW VBLANK event (for driver-internal waiters)
+ */
+enum msm_event_wait {
+	MSM_ENC_COMMIT_DONE = 0,
+	MSM_ENC_TX_COMPLETE,
+	MSM_ENC_VBLANK,
+};
+
+/**
+ * struct msm_display_topology - defines a display topology pipeline
+ * @num_lm:       number of layer mixers used
+ * @num_enc:      number of compression encoder blocks used
+ * @num_intf:     number of interfaces the panel is mounted on
+ */
+struct msm_display_topology {
+	u32 num_lm;
+	u32 num_enc;
+	u32 num_intf;
+};
+
+/**
+ * struct msm_display_info - defines display properties
+ * @intf_type:          DRM_MODE_CONNECTOR_ display type
+ * @capabilities:       Bitmask of display flags
+ * @num_of_h_tiles:     Number of horizontal tiles in case of split interface
+ * @h_tile_instance:    Controller instance used per tile. Number of elements is
+ *                      based on num_of_h_tiles
+ * @is_te_using_watchdog_timer:  Boolean to indicate watchdog TE is
+ *				 used instead of panel TE in cmd mode panels
+ */
+struct msm_display_info {
+	int intf_type;
+	uint32_t capabilities;
+	uint32_t num_of_h_tiles;
+	uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY];
+	bool is_te_using_watchdog_timer;
+};
+
+/* Commit/Event thread specific structure */
+struct msm_drm_thread {
+	struct drm_device *dev;
+	struct task_struct *thread;
+	unsigned int crtc_id;
+	struct kthread_worker worker;
+};
 
 struct msm_drm_private {
 
@@ -84,7 +157,7 @@ struct msm_drm_private {
 	/* subordinate devices, if present: */
 	struct platform_device *gpu_pdev;
 
-	/* top level MDSS wrapper device (for MDP5 only) */
+	/* top level MDSS wrapper device (for MDP5/DPU only) */
 	struct msm_mdss *mdss;
 
 	/* possibly this should be in the kms component, but it is
@@ -115,22 +188,24 @@ struct msm_drm_private {
 	struct list_head inactive_list;
 
 	struct workqueue_struct *wq;
-	struct workqueue_struct *atomic_wq;
 
 	unsigned int num_planes;
-	struct drm_plane *planes[16];
+	struct drm_plane *planes[MAX_PLANES];
 
 	unsigned int num_crtcs;
-	struct drm_crtc *crtcs[8];
+	struct drm_crtc *crtcs[MAX_CRTCS];
+
+	struct msm_drm_thread disp_thread[MAX_CRTCS];
+	struct msm_drm_thread event_thread[MAX_CRTCS];
 
 	unsigned int num_encoders;
-	struct drm_encoder *encoders[8];
+	struct drm_encoder *encoders[MAX_ENCODERS];
 
 	unsigned int num_bridges;
-	struct drm_bridge *bridges[8];
+	struct drm_bridge *bridges[MAX_BRIDGES];
 
 	unsigned int num_connectors;
-	struct drm_connector *connectors[8];
+	struct drm_connector *connectors[MAX_CONNECTORS];
 
 	/* Properties */
 	struct drm_property *plane_property[PLANE_PROP_MAX_NUM];
@@ -150,6 +225,7 @@ struct msm_drm_private {
 	struct shrinker shrinker;
 
 	struct msm_vblank_ctrl vblank_ctrl;
+	struct drm_atomic_state *pm_state;
 };
 
 struct msm_format {
@@ -174,6 +250,9 @@ struct msm_gem_address_space *
 msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 		const char *name);
 
+int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
+void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu);
+
 void msm_gem_submit_free(struct msm_gem_submit *submit);
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
@@ -285,6 +364,8 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi,
 
 void __init msm_mdp_register(void);
 void __exit msm_mdp_unregister(void);
+void __init msm_dpu_register(void);
+void __exit msm_dpu_unregister(void);
 
 #ifdef CONFIG_DEBUG_FS
 void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 1c09acfb4028..f388944c93e2 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -20,10 +20,11 @@
 #include "msm_mmu.h"
 #include "msm_fence.h"
 
+#include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
-
+#include <linux/devcoredump.h>
 
 /*
  * Power Management:
@@ -273,6 +274,123 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
+#ifdef CONFIG_DEV_COREDUMP
+static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
+		size_t count, void *data, size_t datalen)
+{
+	struct msm_gpu *gpu = data;
+	struct drm_print_iterator iter;
+	struct drm_printer p;
+	struct msm_gpu_state *state;
+
+	state = msm_gpu_crashstate_get(gpu);
+	if (!state)
+		return 0;
+
+	iter.data = buffer;
+	iter.offset = 0;
+	iter.start = offset;
+	iter.remain = count;
+
+	p = drm_coredump_printer(&iter);
+
+	drm_printf(&p, "---\n");
+	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
+	drm_printf(&p, "time: %lld.%09ld\n",
+		state->time.tv_sec, state->time.tv_nsec);
+	if (state->comm)
+		drm_printf(&p, "comm: %s\n", state->comm);
+	if (state->cmd)
+		drm_printf(&p, "cmdline: %s\n", state->cmd);
+
+	gpu->funcs->show(gpu, state, &p);
+
+	msm_gpu_crashstate_put(gpu);
+
+	return count - iter.remain;
+}
+
+static void msm_gpu_devcoredump_free(void *data)
+{
+	struct msm_gpu *gpu = data;
+
+	msm_gpu_crashstate_put(gpu);
+}
+
+static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
+		struct msm_gem_object *obj, u64 iova, u32 flags)
+{
+	struct msm_gpu_state_bo *state_bo = &state->bos[state->nr_bos];
+
+	/* Don't record write only objects */
+
+	state_bo->size = obj->base.size;
+	state_bo->iova = iova;
+
+	/* Only store the data for buffer objects marked for read */
+	if ((flags & MSM_SUBMIT_BO_READ)) {
+		void *ptr;
+
+		state_bo->data = kvmalloc(obj->base.size, GFP_KERNEL);
+		if (!state_bo->data)
+			return;
+
+		ptr = msm_gem_get_vaddr_active(&obj->base);
+		if (IS_ERR(ptr)) {
+			kvfree(state_bo->data);
+			return;
+		}
+
+		memcpy(state_bo->data, ptr, obj->base.size);
+		msm_gem_put_vaddr(&obj->base);
+	}
+
+	state->nr_bos++;
+}
+
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
+		struct msm_gem_submit *submit, char *comm, char *cmd)
+{
+	struct msm_gpu_state *state;
+
+	/* Only save one crash state at a time */
+	if (gpu->crashstate)
+		return;
+
+	state = gpu->funcs->gpu_state_get(gpu);
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	/* Fill in the additional crash state information */
+	state->comm = kstrdup(comm, GFP_KERNEL);
+	state->cmd = kstrdup(cmd, GFP_KERNEL);
+
+	if (submit) {
+		int i;
+
+		state->bos = kcalloc(submit->nr_bos,
+			sizeof(struct msm_gpu_state_bo), GFP_KERNEL);
+
+		for (i = 0; state->bos && i < submit->nr_bos; i++)
+			msm_gpu_crashstate_get_bo(state, submit->bos[i].obj,
+				submit->bos[i].iova, submit->bos[i].flags);
+	}
+
+	/* Set the active crash state to be dumped on failure */
+	gpu->crashstate = state;
+
+	/* FIXME: Release the crashstate if this errors out? */
+	dev_coredumpm(gpu->dev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL,
+		msm_gpu_devcoredump_read, msm_gpu_devcoredump_free);
+}
+#else
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
+		char *cmd)
+{
+}
+#endif
+
 /*
  * Hangcheck detection for locked gpu:
  */
@@ -314,6 +432,7 @@ static void recover_worker(struct work_struct *work)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
+	char *comm = NULL, *cmd = NULL;
 	int i;
 
 	mutex_lock(&dev->struct_mutex);
@@ -327,7 +446,7 @@ static void recover_worker(struct work_struct *work)
 		rcu_read_lock();
 		task = pid_task(submit->pid, PIDTYPE_PID);
 		if (task) {
-			char *cmd;
+			comm = kstrdup(task->comm, GFP_ATOMIC);
 
 			/*
 			 * So slightly annoying, in other paths like
@@ -340,22 +459,28 @@ static void recover_worker(struct work_struct *work)
 			 * about the submit going away.
 			 */
 			mutex_unlock(&dev->struct_mutex);
-			cmd = kstrdup_quotable_cmdline(task, GFP_KERNEL);
+			cmd = kstrdup_quotable_cmdline(task, GFP_ATOMIC);
 			mutex_lock(&dev->struct_mutex);
+		}
+		rcu_read_unlock();
 
+		if (comm && cmd) {
 			dev_err(dev->dev, "%s: offending task: %s (%s)\n",
-				gpu->name, task->comm, cmd);
+				gpu->name, comm, cmd);
 
 			msm_rd_dump_submit(priv->hangrd, submit,
-				"offending task: %s (%s)", task->comm, cmd);
-
-			kfree(cmd);
-		} else {
+				"offending task: %s (%s)", comm, cmd);
+		} else
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
-		}
-		rcu_read_unlock();
 	}
 
+	/* Record the crash state */
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	kfree(cmd);
+	kfree(comm);
 
 	/*
 	 * Update all the rings with the latest and greatest fence.. this
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b8241179175a..1c6105bc55c7 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -27,6 +27,7 @@
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
+struct msm_gpu_state;
 
 struct msm_gpu_config {
 	const char *ioname;
@@ -64,11 +65,14 @@ struct msm_gpu_funcs {
 	void (*destroy)(struct msm_gpu *gpu);
 #ifdef CONFIG_DEBUG_FS
 	/* show GPU status in debugfs: */
-	void (*show)(struct msm_gpu *gpu, struct seq_file *m);
+	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
+			struct drm_printer *p);
 	/* for generation specific debugfs: */
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
 	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
+	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
+	int (*gpu_state_put)(struct msm_gpu_state *state);
 };
 
 struct msm_gpu {
@@ -129,6 +133,8 @@ struct msm_gpu {
 		u64 busy_cycles;
 		ktime_t time;
 	} devfreq;
+
+	struct msm_gpu_state *crashstate;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -175,6 +181,38 @@ struct msm_gpu_submitqueue {
 	struct kref ref;
 };
 
+struct msm_gpu_state_bo {
+	u64 iova;
+	size_t size;
+	void *data;
+};
+
+struct msm_gpu_state {
+	struct kref ref;
+	struct timespec64 time;
+
+	struct {
+		u64 iova;
+		u32 fence;
+		u32 seqno;
+		u32 rptr;
+		u32 wptr;
+		void *data;
+		int data_size;
+	} ring[MSM_GPU_MAX_RINGS];
+
+	int nr_registers;
+	u32 *registers;
+
+	u32 rbbm_status;
+
+	char *comm;
+	char *cmd;
+
+	int nr_bos;
+	struct msm_gpu_state_bo *bos;
+};
+
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
 {
 	msm_writel(data, gpu->mmio + (reg << 2));
@@ -254,4 +292,32 @@ static inline void msm_submitqueue_put(struct msm_gpu_submitqueue *queue)
 		kref_put(&queue->ref, msm_submitqueue_destroy);
 }
 
+static inline struct msm_gpu_state *msm_gpu_crashstate_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = NULL;
+
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		kref_get(&gpu->crashstate->ref);
+		state = gpu->crashstate;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+
+	return state;
+}
+
+static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
+{
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		if (gpu->funcs->gpu_state_put(gpu->crashstate))
+			gpu->crashstate = NULL;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+}
+
 #endif /* __MSM_GPU_H__ */
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index dfd92947de2c..fd88cebb6adb 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -42,6 +43,7 @@ struct msm_kms_funcs {
 	void (*disable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
 	/* modeset, bracketing atomic_commit(): */
 	void (*prepare_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
+	void (*commit)(struct msm_kms *kms, struct drm_atomic_state *state);
 	void (*complete_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
 	/* functions to wait for atomic commit completed on each CRTC */
 	void (*wait_for_crtc_commit_done)(struct msm_kms *kms,
@@ -50,6 +52,11 @@ struct msm_kms_funcs {
 	const struct msm_format *(*get_format)(struct msm_kms *kms,
 					const uint32_t format,
 					const uint64_t modifiers);
+	/* do format checking on format modified through fb_cmd2 modifiers */
+	int (*check_modified_format)(const struct msm_kms *kms,
+			const struct msm_format *msm_fmt,
+			const struct drm_mode_fb_cmd2 *cmd,
+			struct drm_gem_object **bos);
 	/* misc: */
 	long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
 			struct drm_encoder *encoder);
@@ -60,6 +67,9 @@ struct msm_kms_funcs {
 	void (*set_encoder_mode)(struct msm_kms *kms,
 				 struct drm_encoder *encoder,
 				 bool cmd_mode);
+	/* pm suspend/resume hooks */
+	int (*pm_suspend)(struct device *dev);
+	int (*pm_resume)(struct device *dev);
 	/* cleanup: */
 	void (*destroy)(struct msm_kms *kms);
 #ifdef CONFIG_DEBUG_FS
@@ -86,9 +96,20 @@ static inline void msm_kms_init(struct msm_kms *kms,
 
 struct msm_kms *mdp4_kms_init(struct drm_device *dev);
 struct msm_kms *mdp5_kms_init(struct drm_device *dev);
-int msm_mdss_init(struct drm_device *dev);
-void msm_mdss_destroy(struct drm_device *dev);
-int msm_mdss_enable(struct msm_mdss *mdss);
-int msm_mdss_disable(struct msm_mdss *mdss);
+struct msm_kms *dpu_kms_init(struct drm_device *dev);
+
+struct msm_mdss_funcs {
+	int (*enable)(struct msm_mdss *mdss);
+	int (*disable)(struct msm_mdss *mdss);
+	void (*destroy)(struct drm_device *dev);
+};
+
+struct msm_mdss {
+	struct drm_device *dev;
+	const struct msm_mdss_funcs *funcs;
+};
+
+int mdp5_mdss_init(struct drm_device *dev);
+int dpu_mdss_init(struct drm_device *dev);
 
 #endif /* __MSM_KMS_H__ */
diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index 6aa6ee16dcbd..2c569e264df3 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -1017,7 +1017,7 @@ nv04_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
 	nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.offset);
 	nv_crtc->cursor.show(nv_crtc, true);
 out:
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c
index 4feab0a5419d..e7af95d37ddb 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dac.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c
@@ -556,6 +556,6 @@ nv04_dac_create(struct drm_connector *connector, struct dcb_output *entry)
 	encoder->possible_crtcs = entry->heads;
 	encoder->possible_clones = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index 9805d2cdc1a1..73d41abbb510 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -716,6 +716,6 @@ nv04_dfp_create(struct drm_connector *connector, struct dcb_output *entry)
 	    entry->location != DCB_LOC_ON_CHIP)
 		nv04_tmds_slave_init(encoder);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/disp.c b/drivers/gpu/drm/nouveau/dispnv04/disp.c
index 501d2d290e9c..70dce544984e 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/disp.c
@@ -55,6 +55,9 @@ nv04_display_create(struct drm_device *dev)
 	nouveau_display(dev)->init = nv04_display_init;
 	nouveau_display(dev)->fini = nv04_display_fini;
 
+	/* Pre-nv50 doesn't support atomic, so don't expose the ioctls */
+	dev->driver->driver_features &= ~DRIVER_ATOMIC;
+
 	nouveau_hw_save_vga_fonts(dev, 1);
 
 	nv04_crtc_create(dev, 0);
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
index 01664357d3e1..de4490b4ed30 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
@@ -244,7 +244,7 @@ nv04_tv_create(struct drm_connector *connector, struct dcb_output *entry)
 
 	/* Attach it to the specified connector. */
 	get_slave_funcs(encoder)->create_resources(encoder, connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 6d99f11fee4e..6a4ca139cf5d 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -821,6 +821,6 @@ nv17_tv_create(struct drm_connector *connector, struct dcb_output *entry)
 	encoder->possible_clones = 0;
 
 	nv17_tv_create_resources(encoder, connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b83465ae7c1b..8412119bd940 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -136,12 +136,24 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
 	struct nv50_disp_core_channel_dma_v0 *args = data;
+	u8 type = NVIF_MEM_COHERENT;
 	int ret;
 
 	mutex_init(&dmac->lock);
 
-	ret = nvif_mem_init_map(&cli->mmu, NVIF_MEM_COHERENT, 0x1000,
-				&dmac->push);
+	/* Pascal added support for 47-bit physical addresses, but some
+	 * parts of EVO still only accept 40-bit PAs.
+	 *
+	 * To avoid issues on systems with large amounts of RAM, and on
+	 * systems where an IOMMU maps pages at a high address, we need
+	 * to allocate push buffers in VRAM instead.
+	 *
+	 * This appears to match NVIDIA's behaviour on Pascal.
+	 */
+	if (device->info.family == NV_DEVICE_INFO_V0_PASCAL)
+		type |= NVIF_MEM_VRAM;
+
+	ret = nvif_mem_init_map(&cli->mmu, type, 0x1000, &dmac->push);
 	if (ret)
 		return ret;
 
@@ -216,6 +228,19 @@ void
 evo_kick(u32 *push, struct nv50_dmac *evoc)
 {
 	struct nv50_dmac *dmac = evoc;
+
+	/* Push buffer fetches are not coherent with BAR1, we need to ensure
+	 * writes have been flushed right through to VRAM before writing PUT.
+	 */
+	if (dmac->push.type & NVIF_MEM_VRAM) {
+		struct nvif_device *device = dmac->base.device;
+		nvif_wr32(&device->object, 0x070000, 0x00000001);
+		nvif_msec(device, 2000,
+			if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002))
+				break;
+		);
+	}
+
 	nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2);
 	mutex_unlock(&dmac->lock);
 }
@@ -424,7 +449,7 @@ nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "dac-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_dac_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
 
@@ -850,7 +875,7 @@ nv50_mstc_get_modes(struct drm_connector *connector)
 	int ret = 0;
 
 	mstc->edid = drm_dp_mst_get_edid(&mstc->connector, mstc->port->mgr, mstc->port);
-	drm_mode_connector_update_edid_property(&mstc->connector, mstc->edid);
+	drm_connector_update_edid_property(&mstc->connector, mstc->edid);
 	if (mstc->edid)
 		ret = drm_add_edid_modes(&mstc->connector, mstc->edid);
 
@@ -927,11 +952,11 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	nouveau_conn_attach_properties(&mstc->connector);
 
 	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
-		drm_mode_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
+		drm_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->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);
-	drm_mode_connector_set_path_property(&mstc->connector, path);
+	drm_connector_set_path_property(&mstc->connector, path);
 	return 0;
 }
 
@@ -1007,7 +1032,7 @@ nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr,
 	mstc->port = NULL;
 	drm_modeset_unlock(&drm->dev->mode_config.connection_mutex);
 
-	drm_connector_unreference(&mstc->connector);
+	drm_connector_put(&mstc->connector);
 }
 
 static void
@@ -1418,7 +1443,7 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "sor-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_sor_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	if (dcbe->type == DCB_OUTPUT_DP) {
 		struct nv50_disp *disp = nv50_disp(encoder->dev);
@@ -1576,7 +1601,7 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "pior-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_pior_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
 
@@ -1585,8 +1610,9 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
  *****************************************************************************/
 
 static void
-nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock)
+nv50_disp_atomic_commit_core(struct drm_atomic_state *state, u32 *interlock)
 {
+	struct nouveau_drm *drm = nouveau_drm(state->dev);
 	struct nv50_disp *disp = nv50_disp(drm->dev);
 	struct nv50_core *core = disp->core;
 	struct nv50_mstm *mstm;
@@ -1618,6 +1644,22 @@ nv50_disp_atomic_commit_core(struct nouveau_drm *drm, u32 *interlock)
 }
 
 static void
+nv50_disp_atomic_commit_wndw(struct drm_atomic_state *state, u32 *interlock)
+{
+	struct drm_plane_state *new_plane_state;
+	struct drm_plane *plane;
+	int i;
+
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		struct nv50_wndw *wndw = nv50_wndw(plane);
+		if (interlock[wndw->interlock.type] & wndw->interlock.data) {
+			if (wndw->func->update)
+				wndw->func->update(wndw, interlock);
+		}
+	}
+}
+
+static void
 nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -1684,7 +1726,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 			help->disable(encoder);
 			interlock[NV50_DISP_INTERLOCK_CORE] |= 1;
 			if (outp->flush_disable) {
-				nv50_disp_atomic_commit_core(drm, interlock);
+				nv50_disp_atomic_commit_wndw(state, interlock);
+				nv50_disp_atomic_commit_core(state, interlock);
 				memset(interlock, 0x00, sizeof(interlock));
 			}
 		}
@@ -1693,15 +1736,8 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 	/* Flush disable. */
 	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
 		if (atom->flush_disable) {
-			for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-				struct nv50_wndw *wndw = nv50_wndw(plane);
-				if (interlock[wndw->interlock.type] & wndw->interlock.data) {
-					if (wndw->func->update)
-						wndw->func->update(wndw, interlock);
-				}
-			}
-
-			nv50_disp_atomic_commit_core(drm, interlock);
+			nv50_disp_atomic_commit_wndw(state, interlock);
+			nv50_disp_atomic_commit_core(state, interlock);
 			memset(interlock, 0x00, sizeof(interlock));
 		}
 	}
@@ -1762,18 +1798,14 @@ nv50_disp_atomic_commit_tail(struct drm_atomic_state *state)
 	}
 
 	/* Flush update. */
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		struct nv50_wndw *wndw = nv50_wndw(plane);
-		if (interlock[wndw->interlock.type] & wndw->interlock.data) {
-			if (wndw->func->update)
-				wndw->func->update(wndw, interlock);
-		}
-	}
+	nv50_disp_atomic_commit_wndw(state, interlock);
 
 	if (interlock[NV50_DISP_INTERLOCK_CORE]) {
 		if (interlock[NV50_DISP_INTERLOCK_BASE] ||
+		    interlock[NV50_DISP_INTERLOCK_OVLY] ||
+		    interlock[NV50_DISP_INTERLOCK_WNDW] ||
 		    !atom->state.legacy_cursor_update)
-			nv50_disp_atomic_commit_core(drm, interlock);
+			nv50_disp_atomic_commit_core(state, interlock);
 		else
 			disp->core->func->update(disp->core, interlock, false);
 	}
@@ -1871,7 +1903,7 @@ nv50_disp_atomic_commit(struct drm_device *dev,
 		nv50_disp_atomic_commit_tail(state);
 
 	drm_for_each_crtc(crtc, dev) {
-		if (crtc->state->enable) {
+		if (crtc->state->active) {
 			if (!drm->have_disp_power_ref) {
 				drm->have_disp_power_ref = true;
 				return 0;
@@ -2119,10 +2151,6 @@ nv50_display_destroy(struct drm_device *dev)
 	kfree(disp);
 }
 
-MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
-static int nouveau_atomic = 0;
-module_param_named(atomic, nouveau_atomic, int, 0400);
-
 int
 nv50_display_create(struct drm_device *dev)
 {
@@ -2147,8 +2175,6 @@ nv50_display_create(struct drm_device *dev)
 	disp->disp = &nouveau_display(dev)->disp;
 	dev->mode_config.funcs = &nv50_disp_func;
 	dev->driver->driver_features |= DRIVER_PREFER_XBGR_30BPP;
-	if (nouveau_atomic)
-		dev->driver->driver_features |= DRIVER_ATOMIC;
 
 	/* small shared memory area we use for notifiers and semaphores */
 	ret = nouveau_bo_new(&drm->client, 4096, 0x1000, TTM_PL_FLAG_VRAM,
@@ -2231,6 +2257,9 @@ nv50_display_create(struct drm_device *dev)
 		connector->funcs->destroy(connector);
 	}
 
+	/* Disable vblank irqs aggressively for power-saving, safe on nv50+ */
+	dev->vblank_disable_immediate = true;
+
 out:
 	if (ret)
 		nv50_display_destroy(dev);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index c5a9bc1af5af..2187922e8dc2 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -586,7 +586,6 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	wndw->id = index;
 	wndw->interlock.type = interlock_type;
 	wndw->interlock.data = interlock_data;
-	wndw->ctxdma.parent = &wndw->wndw.base.user;
 
 	wndw->ctxdma.parent = &wndw->wndw.base.user;
 	INIT_LIST_HEAD(&wndw->ctxdma.list);
diff --git a/drivers/gpu/drm/nouveau/include/nvif/object.h b/drivers/gpu/drm/nouveau/include/nvif/object.h
index 20754d9e6883..8407651f6ac6 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/object.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/object.h
@@ -78,7 +78,7 @@ struct nvif_mclass {
 #define nvif_mclass(o,m) ({                                                    \
 	struct nvif_object *object = (o);                                      \
 	struct nvif_sclass *sclass;                                            \
-	const typeof(m[0]) *mclass = (m);                                      \
+	typeof(m[0]) *mclass = (m);                                            \
 	int ret = -ENODEV;                                                     \
 	int cnt, i, j;                                                         \
                                                                                \
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index e2211bb2cf79..e67a471331b5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -139,7 +139,7 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 	if (chan->ntfy) {
 		nouveau_vma_del(&chan->ntfy_vma);
 		nouveau_bo_unpin(chan->ntfy);
-		drm_gem_object_unreference_unlocked(&chan->ntfy->gem);
+		drm_gem_object_put_unlocked(&chan->ntfy->gem);
 	}
 
 	if (chan->heap.block_size)
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index debbbf0fd4bd..408b955e5c39 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -267,6 +267,7 @@ nouveau_backlight_init(struct drm_device *dev)
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvif_device *device = &drm->client.device;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 
 	INIT_LIST_HEAD(&drm->bl_connectors);
 
@@ -275,7 +276,8 @@ nouveau_backlight_init(struct drm_device *dev)
 		return 0;
 	}
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(connector, &conn_iter) {
 		if (connector->connector_type != DRM_MODE_CONNECTOR_LVDS &&
 		    connector->connector_type != DRM_MODE_CONNECTOR_eDP)
 			continue;
@@ -292,7 +294,7 @@ nouveau_backlight_init(struct drm_device *dev)
 			break;
 		}
 	}
-
+	drm_connector_list_iter_end(&conn_iter);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 7b557c354307..51932c72334e 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -363,19 +363,11 @@ module_param_named(hdmimhz, nouveau_hdmimhz, int, 0400);
 struct nouveau_encoder *
 find_encoder(struct drm_connector *connector, int type)
 {
-	struct drm_device *dev = connector->dev;
 	struct nouveau_encoder *nv_encoder;
 	struct drm_encoder *enc;
-	int i, id;
-
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		id = connector->encoder_ids[i];
-		if (!id)
-			break;
+	int i;
 
-		enc = drm_encoder_find(dev, NULL, id);
-		if (!enc)
-			continue;
+	drm_connector_for_each_possible_encoder(connector, enc, i) {
 		nv_encoder = nouveau_encoder(enc);
 
 		if (type == DCB_OUTPUT_ANY ||
@@ -420,7 +412,7 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvkm_gpio *gpio = nvxx_gpio(&drm->client.device);
-	struct nouveau_encoder *nv_encoder;
+	struct nouveau_encoder *nv_encoder = NULL;
 	struct drm_encoder *encoder;
 	int i, panel = -ENODEV;
 
@@ -436,14 +428,7 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 		}
 	}
 
-	for (i = 0; nv_encoder = NULL, i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		int id = connector->encoder_ids[i];
-		if (id == 0)
-			break;
-
-		encoder = drm_encoder_find(dev, NULL, id);
-		if (!encoder)
-			continue;
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		nv_encoder = nouveau_encoder(encoder);
 
 		if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
@@ -565,7 +550,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		kfree(nv_connector->edid);
 		nv_connector->edid = NULL;
 	}
@@ -590,7 +575,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		else
 			nv_connector->edid = drm_get_edid(connector, i2c);
 
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 							nv_connector->edid);
 		if (!nv_connector->edid) {
 			NV_ERROR(drm, "DDC responded, but no EDID for %s\n",
@@ -672,7 +657,7 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force)
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		kfree(nv_connector->edid);
 		nv_connector->edid = NULL;
 	}
@@ -736,7 +721,7 @@ out:
 		status = connector_status_unknown;
 #endif
 
-	drm_mode_connector_update_edid_property(connector, nv_connector->edid);
+	drm_connector_update_edid_property(connector, nv_connector->edid);
 	nouveau_connector_set_encoder(connector, nv_encoder);
 	return status;
 }
@@ -1208,14 +1193,19 @@ nouveau_connector_create(struct drm_device *dev, int index)
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_connector *nv_connector = NULL;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 	int type, ret = 0;
 	bool dummy;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
 		nv_connector = nouveau_connector(connector);
-		if (nv_connector->index == index)
+		if (nv_connector->index == index) {
+			drm_connector_list_iter_end(&conn_iter);
 			return connector;
+		}
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
 	nv_connector = kzalloc(sizeof(*nv_connector), GFP_KERNEL);
 	if (!nv_connector)
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.h b/drivers/gpu/drm/nouveau/nouveau_connector.h
index a4d1a059bd3d..dc7454e7f19a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.h
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.h
@@ -33,6 +33,7 @@
 #include <drm/drm_encoder.h>
 #include <drm/drm_dp_helper.h>
 #include "nouveau_crtc.h"
+#include "nouveau_encoder.h"
 
 struct nvkm_i2c_port;
 
@@ -60,19 +61,46 @@ static inline struct nouveau_connector *nouveau_connector(
 	return container_of(con, struct nouveau_connector, base);
 }
 
+static inline bool
+nouveau_connector_is_mst(struct drm_connector *connector)
+{
+	const struct nouveau_encoder *nv_encoder;
+	const struct drm_encoder *encoder;
+
+	if (connector->connector_type != DRM_MODE_CONNECTOR_DisplayPort)
+		return false;
+
+	nv_encoder = find_encoder(connector, DCB_OUTPUT_ANY);
+	if (!nv_encoder)
+		return false;
+
+	encoder = &nv_encoder->base.base;
+	return encoder->encoder_type == DRM_MODE_ENCODER_DPMST;
+}
+
+#define nouveau_for_each_non_mst_connector_iter(connector, iter) \
+	drm_for_each_connector_iter(connector, iter) \
+		for_each_if(!nouveau_connector_is_mst(connector))
+
 static inline struct nouveau_connector *
 nouveau_crtc_connector_get(struct nouveau_crtc *nv_crtc)
 {
 	struct drm_device *dev = nv_crtc->base.dev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
+	struct nouveau_connector *nv_connector = NULL;
 	struct drm_crtc *crtc = to_drm_crtc(nv_crtc);
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		if (connector->encoder && connector->encoder->crtc == crtc)
-			return nouveau_connector(connector);
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
+		if (connector->encoder && connector->encoder->crtc == crtc) {
+			nv_connector = nouveau_connector(connector);
+			break;
+		}
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
-	return NULL;
+	return nv_connector;
 }
 
 struct drm_connector *
diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 963a4dba8213..9109b69cd052 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -160,7 +160,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf,
 		args.ustate = value;
 	}
 
+	ret = pm_runtime_get_sync(drm->dev);
+	if (IS_ERR_VALUE(ret) && ret != -EACCES)
+		return ret;
 	ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
+	pm_runtime_put_autosuspend(drm->dev);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 774b429142bc..139368b31916 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -205,7 +205,7 @@ nouveau_user_framebuffer_destroy(struct drm_framebuffer *drm_fb)
 	struct nouveau_framebuffer *fb = nouveau_framebuffer(drm_fb);
 
 	if (fb->nvbo)
-		drm_gem_object_unreference_unlocked(&fb->nvbo->gem);
+		drm_gem_object_put_unlocked(&fb->nvbo->gem);
 
 	drm_framebuffer_cleanup(drm_fb);
 	kfree(fb);
@@ -287,7 +287,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev,
 	if (ret == 0)
 		return &fb->base;
 
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ERR_PTR(ret);
 }
 
@@ -404,6 +404,7 @@ nouveau_display_init(struct drm_device *dev)
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 	int ret;
 
 	ret = disp->init(dev);
@@ -411,10 +412,12 @@ nouveau_display_init(struct drm_device *dev)
 		return ret;
 
 	/* enable hotplug interrupts */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
 		struct nouveau_connector *conn = nouveau_connector(connector);
 		nvif_notify_get(&conn->hpd);
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
 	/* enable flip completion events */
 	nvif_notify_get(&drm->flip);
@@ -427,6 +430,7 @@ nouveau_display_fini(struct drm_device *dev, bool suspend)
 	struct nouveau_display *disp = nouveau_display(dev);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct drm_connector *connector;
+	struct drm_connector_list_iter conn_iter;
 
 	if (!suspend) {
 		if (drm_drv_uses_atomic_modeset(dev))
@@ -439,10 +443,12 @@ nouveau_display_fini(struct drm_device *dev, bool suspend)
 	nvif_notify_put(&drm->flip);
 
 	/* disable hotplug interrupts */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) {
 		struct nouveau_connector *conn = nouveau_connector(connector);
 		nvif_notify_put(&conn->hpd);
 	}
+	drm_connector_list_iter_end(&conn_iter);
 
 	drm_kms_helper_poll_disable(dev);
 	disp->fini(dev);
@@ -939,7 +945,7 @@ nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
 		return ret;
 
 	ret = drm_gem_handle_create(file_priv, &bo->gem, &args->handle);
-	drm_gem_object_unreference_unlocked(&bo->gem);
+	drm_gem_object_put_unlocked(&bo->gem);
 	return ret;
 }
 
@@ -954,7 +960,7 @@ nouveau_display_dumb_map_offset(struct drm_file *file_priv,
 	if (gem) {
 		struct nouveau_bo *bo = nouveau_gem_object(gem);
 		*poffset = drm_vma_node_offset_addr(&bo->bo.vma_node);
-		drm_gem_object_unreference_unlocked(gem);
+		drm_gem_object_put_unlocked(gem);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 775443c9af94..c7ec86d6c3c9 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -81,6 +81,10 @@ MODULE_PARM_DESC(modeset, "enable driver (default: auto, "
 int nouveau_modeset = -1;
 module_param_named(modeset, nouveau_modeset, int, 0400);
 
+MODULE_PARM_DESC(atomic, "Expose atomic ioctl (default: disabled)");
+static int nouveau_atomic = 0;
+module_param_named(atomic, nouveau_atomic, int, 0400);
+
 MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
 static int nouveau_runtime_pm = -1;
 module_param_named(runpm, nouveau_runtime_pm, int, 0400);
@@ -509,6 +513,9 @@ static int nouveau_drm_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
+	if (nouveau_atomic)
+		driver_pci.driver_features |= DRIVER_ATOMIC;
+
 	ret = drm_get_pci_dev(pdev, pent, &driver_pci);
 	if (ret) {
 		nvkm_device_del(&device);
@@ -874,22 +881,11 @@ nouveau_pmops_runtime_resume(struct device *dev)
 static int
 nouveau_pmops_runtime_idle(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct drm_device *drm_dev = pci_get_drvdata(pdev);
-	struct nouveau_drm *drm = nouveau_drm(drm_dev);
-	struct drm_crtc *crtc;
-
 	if (!nouveau_pmops_runtime()) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
 
-	list_for_each_entry(crtc, &drm->dev->mode_config.crtc_list, head) {
-		if (crtc->enabled) {
-			DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
-			return -EBUSY;
-		}
-	}
 	pm_runtime_mark_last_busy(dev);
 	pm_runtime_autosuspend(dev);
 	/* we don't want the main rpm_idle to call suspend - we want to autosuspend */
@@ -912,8 +908,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
 
-	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL)))
-		return ret;
+	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto done;
+	}
 
 	ret = nouveau_cli_init(drm, name, cli);
 	if (ret)
diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 85c1f10bc2b6..844498c4267c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -429,7 +429,7 @@ nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
 		nouveau_vma_del(&nouveau_fb->vma);
 		nouveau_bo_unmap(nouveau_fb->nvbo);
 		nouveau_bo_unpin(nouveau_fb->nvbo);
-		drm_framebuffer_unreference(&nouveau_fb->base);
+		drm_framebuffer_put(&nouveau_fb->base);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 300daee74209..b56524d343c3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -274,7 +274,7 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data,
 	}
 
 	/* drop reference from allocate - handle holds it now */
-	drm_gem_object_unreference_unlocked(&nvbo->gem);
+	drm_gem_object_put_unlocked(&nvbo->gem);
 	return ret;
 }
 
@@ -354,7 +354,7 @@ validate_fini_no_ticket(struct validate_op *op, struct nouveau_fence *fence,
 		list_del(&nvbo->entry);
 		nvbo->reserved_by = NULL;
 		ttm_bo_unreserve(&nvbo->bo);
-		drm_gem_object_unreference_unlocked(&nvbo->gem);
+		drm_gem_object_put_unlocked(&nvbo->gem);
 	}
 }
 
@@ -400,14 +400,14 @@ retry:
 		nvbo = nouveau_gem_object(gem);
 		if (nvbo == res_bo) {
 			res_bo = NULL;
-			drm_gem_object_unreference_unlocked(gem);
+			drm_gem_object_put_unlocked(gem);
 			continue;
 		}
 
 		if (nvbo->reserved_by && nvbo->reserved_by == file_priv) {
 			NV_PRINTK(err, cli, "multiple instances of buffer %d on "
 				      "validation list\n", b->handle);
-			drm_gem_object_unreference_unlocked(gem);
+			drm_gem_object_put_unlocked(gem);
 			ret = -EINVAL;
 			break;
 		}
@@ -616,7 +616,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		struct nouveau_bo *nvbo;
 		uint32_t data;
 
-		if (unlikely(r->bo_index > req->nr_buffers)) {
+		if (unlikely(r->bo_index >= req->nr_buffers)) {
 			NV_PRINTK(err, cli, "reloc bo index invalid\n");
 			ret = -EINVAL;
 			break;
@@ -626,7 +626,7 @@ nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli,
 		if (b->presumed.valid)
 			continue;
 
-		if (unlikely(r->reloc_bo_index > req->nr_buffers)) {
+		if (unlikely(r->reloc_bo_index >= req->nr_buffers)) {
 			NV_PRINTK(err, cli, "reloc container bo index invalid\n");
 			ret = -EINVAL;
 			break;
@@ -894,7 +894,7 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 		ret = lret;
 
 	nouveau_bo_sync_for_cpu(nvbo);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 
 	return ret;
 }
@@ -913,7 +913,7 @@ nouveau_gem_ioctl_cpu_fini(struct drm_device *dev, void *data,
 	nvbo = nouveau_gem_object(gem);
 
 	nouveau_bo_sync_for_device(nvbo);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return 0;
 }
 
@@ -930,7 +930,7 @@ nouveau_gem_ioctl_info(struct drm_device *dev, void *data,
 		return -ENOENT;
 
 	ret = nouveau_gem_info(file_priv, gem, req);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index 44178b4c3599..08a1ab6b150d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -69,8 +69,8 @@ nouveau_hwmon_set_temp1_auto_point1_temp(struct device *d,
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 	long value;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
-		return count;
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
 
 	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST,
 			value / 1000);
@@ -102,8 +102,8 @@ nouveau_hwmon_set_temp1_auto_point1_temp_hyst(struct device *d,
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 	long value;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
-		return count;
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
 
 	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST_HYST,
 			value / 1000);
@@ -156,7 +156,7 @@ nouveau_hwmon_set_pwm1_min(struct device *d, struct device_attribute *a,
 	long value;
 	int ret;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
+	if (kstrtol(buf, 10, &value))
 		return -EINVAL;
 
 	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MIN_DUTY, value);
@@ -179,7 +179,7 @@ nouveau_hwmon_set_pwm1_max(struct device *d, struct device_attribute *a,
 	long value;
 	int ret;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
+	if (kstrtol(buf, 10, &value))
 		return -EINVAL;
 
 	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MAX_DUTY, value);
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 1ada186fab77..039e23548e08 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -36,7 +36,7 @@ static int nouveau_platform_probe(struct platform_device *pdev)
 
 	ret = drm_dev_register(drm, 0);
 	if (ret < 0) {
-		drm_dev_unref(drm);
+		drm_dev_put(drm);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/core/engine.c b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
index d0322ce85172..1a47c40e171b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/engine.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
@@ -87,11 +87,12 @@ nvkm_engine_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data)
 {
 	struct nvkm_engine *engine = nvkm_engine(subdev);
 	if (engine->func->info) {
-		if ((engine = nvkm_engine_ref(engine))) {
+		if (!IS_ERR((engine = nvkm_engine_ref(engine)))) {
 			int ret = engine->func->info(engine, mthd, data);
 			nvkm_engine_unref(&engine);
 			return ret;
 		}
+		return PTR_ERR(engine);
 	}
 	return -ENOSYS;
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 78597da6313a..0e372a190d3f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -23,6 +23,10 @@
 #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER
 #include "priv.h"
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+#include <asm/dma-iommu.h>
+#endif
+
 static int
 nvkm_device_tegra_power_up(struct nvkm_device_tegra *tdev)
 {
@@ -105,6 +109,15 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
 	unsigned long pgsize_bitmap;
 	int ret;
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+	if (dev->archdata.mapping) {
+		struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+
+		arm_iommu_detach_device(dev);
+		arm_iommu_release_mapping(mapping);
+	}
+#endif
+
 	if (!tdev->func->iommu_bit)
 		return;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
index 29e6dd58ac48..525f95d06429 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
@@ -52,7 +52,7 @@ void
 gf119_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
 {
 	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
-	const u64 mask = 0x00000001 << chan->chid.user;
+	const u32 mask = 0x00000001 << chan->chid.user;
 	if (!en) {
 		nvkm_mask(device, 0x610090, mask, 0x00000000);
 		nvkm_mask(device, 0x6100a0, mask, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index 57719f675eec..bcf32d92ee5a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -166,8 +166,8 @@ void
 nv50_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
 {
 	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
-	const u64 mask = 0x00010001 << chan->chid.user;
-	const u64 data = en ? 0x00010000 : 0x00000000;
+	const u32 mask = 0x00010001 << chan->chid.user;
+	const u32 data = en ? 0x00010000 << chan->chid.user : 0x00000000;
 	nvkm_mask(device, 0x610028, mask, data);
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
index 19173ea19096..3b3327789ae7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
@@ -25,24 +25,31 @@
 #include <nvif/class.h>
 
 static void
-gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+gv100_gr_trap_sm(struct gf100_gr *gr, int gpc, int tpc, int sm)
 {
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730));
-	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734));
+	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730 + (sm * 0x80)));
+	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734 + (sm * 0x80)));
 	const struct nvkm_enum *warp;
 	char glob[128];
 
 	nvkm_snprintbf(glob, sizeof(glob), gf100_mp_global_error, gerr);
 	warp = nvkm_enum_find(gf100_mp_warp_error, werr & 0xffff);
 
-	nvkm_error(subdev, "GPC%i/TPC%i/MP trap: "
+	nvkm_error(subdev, "GPC%i/TPC%i/SM%d trap: "
 			   "global %08x [%s] warp %04x [%s]\n",
-		   gpc, tpc, gerr, glob, werr, warp ? warp->name : "");
+		   gpc, tpc, sm, gerr, glob, werr, warp ? warp->name : "");
+
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730 + sm * 0x80), 0x00000000);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734 + sm * 0x80), gerr);
+}
 
-	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730), 0x00000000);
-	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734), gerr);
+static void
+gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+{
+	gv100_gr_trap_sm(gr, gpc, tpc, 0);
+	gv100_gr_trap_sm(gr, gpc, tpc, 1);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
index 20b6fc8243e0..71524548de32 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
@@ -58,8 +58,14 @@ nvbios_vpstate_parse(struct nvkm_bios *b, struct nvbios_vpstate_header *h)
 		h->ecount   = nvbios_rd08(b, h->offset + 0x5);
 
 		h->base_id  = nvbios_rd08(b, h->offset + 0x0f);
-		h->boost_id = nvbios_rd08(b, h->offset + 0x10);
-		h->tdp_id   = nvbios_rd08(b, h->offset + 0x11);
+		if (h->hlen > 0x10)
+			h->boost_id = nvbios_rd08(b, h->offset + 0x10);
+		else
+			h->boost_id = 0xff;
+		if (h->hlen > 0x11)
+			h->tdp_id = nvbios_rd08(b, h->offset + 0x11);
+		else
+			h->tdp_id = 0xff;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
index 007bf4af33b9..16ad91c91a7b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -133,8 +133,14 @@ nvkm_fault_oneinit(struct nvkm_subdev *subdev)
 		}
 	}
 
-	return nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
-			       &fault->event);
+	ret = nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
+			      &fault->event);
+	if (ret)
+		return ret;
+
+	if (fault->func->oneinit)
+		ret = fault->func->oneinit(fault);
+	return ret;
 }
 
 static void *
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
index 73c7728b5969..3cd610d7deb5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
@@ -176,8 +176,17 @@ gv100_fault_init(struct nvkm_fault *fault)
 	nvkm_notify_get(&fault->nrpfb);
 }
 
+static int
+gv100_fault_oneinit(struct nvkm_fault *fault)
+{
+	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
+				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
+				&fault->nrpfb);
+}
+
 static const struct nvkm_fault_func
 gv100_fault = {
+	.oneinit = gv100_fault_oneinit,
 	.init = gv100_fault_init,
 	.fini = gv100_fault_fini,
 	.intr = gv100_fault_intr,
@@ -192,15 +201,5 @@ int
 gv100_fault_new(struct nvkm_device *device, int index,
 		struct nvkm_fault **pfault)
 {
-	struct nvkm_fault *fault;
-	int ret;
-
-	ret = nvkm_fault_new_(&gv100_fault, device, index, &fault);
-	*pfault = fault;
-	if (ret)
-		return ret;
-
-	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
-				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
-				&fault->nrpfb);
+	return nvkm_fault_new_(&gv100_fault, device, index, pfault);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
index 44843ecf12b0..e4d2f5234fd1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
@@ -20,6 +20,7 @@ int nvkm_fault_new_(const struct nvkm_fault_func *, struct nvkm_device *,
 		    int index, struct nvkm_fault **);
 
 struct nvkm_fault_func {
+	int (*oneinit)(struct nvkm_fault *);
 	void (*init)(struct nvkm_fault *);
 	void (*fini)(struct nvkm_fault *);
 	void (*intr)(struct nvkm_fault *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
index 73b5d46104bd..434d2fc5bb1c 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/base.c
@@ -140,6 +140,9 @@ nvkm_fb_init(struct nvkm_subdev *subdev)
 	if (fb->func->init)
 		fb->func->init(fb);
 
+	if (fb->func->init_remapper)
+		fb->func->init_remapper(fb);
+
 	if (fb->func->init_page) {
 		ret = fb->func->init_page(fb);
 		if (WARN_ON(ret))
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
index dffe1f5e1071..8205ce436b3e 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp100.c
@@ -37,6 +37,14 @@ gp100_fb_init_unkn(struct nvkm_fb *base)
 }
 
 void
+gp100_fb_init_remapper(struct nvkm_fb *fb)
+{
+	struct nvkm_device *device = fb->subdev.device;
+	/* Disable address remapper. */
+	nvkm_mask(device, 0x100c14, 0x00040000, 0x00000000);
+}
+
+void
 gp100_fb_init(struct nvkm_fb *base)
 {
 	struct gf100_fb *fb = gf100_fb(base);
@@ -56,6 +64,7 @@ gp100_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gp100_fb_init,
+	.init_remapper = gp100_fb_init_remapper,
 	.init_page = gm200_fb_init_page,
 	.init_unkn = gp100_fb_init_unkn,
 	.ram_new = gp100_ram_new,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
index b84b9861ef26..b4d74e815674 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gp102.c
@@ -31,6 +31,7 @@ gp102_fb = {
 	.dtor = gf100_fb_dtor,
 	.oneinit = gf100_fb_oneinit,
 	.init = gp100_fb_init,
+	.init_remapper = gp100_fb_init_remapper,
 	.init_page = gm200_fb_init_page,
 	.ram_new = gp100_ram_new,
 };
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 2857f31466bf..1e4ad61c19e1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -11,6 +11,7 @@ struct nvkm_fb_func {
 	u32 (*tags)(struct nvkm_fb *);
 	int (*oneinit)(struct nvkm_fb *);
 	void (*init)(struct nvkm_fb *);
+	void (*init_remapper)(struct nvkm_fb *);
 	int (*init_page)(struct nvkm_fb *);
 	void (*init_unkn)(struct nvkm_fb *);
 	void (*intr)(struct nvkm_fb *);
@@ -69,5 +70,6 @@ int gf100_fb_init_page(struct nvkm_fb *);
 
 int gm200_fb_init_page(struct nvkm_fb *);
 
+void gp100_fb_init_remapper(struct nvkm_fb *);
 void gp100_fb_init_unkn(struct nvkm_fb *);
 #endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b. b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.
+++ /dev/null
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
index a721354249ce..d02e183717dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
@@ -414,6 +414,20 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 {
 	struct ls_ucode_img *_img;
 	u32 pos = 0;
+	u32 max_desc_size = 0;
+	u8 *gdesc;
+
+	/* Figure out how large we need gdesc to be. */
+	list_for_each_entry(_img, imgs, node) {
+		const struct acr_r352_ls_func *ls_func =
+					    acr->func->ls_func[_img->falcon_id];
+
+		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
+	}
+
+	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
+	if (!gdesc)
+		return -ENOMEM;
 
 	nvkm_kmap(wpr_blob);
 
@@ -421,7 +435,6 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 		struct ls_ucode_img_r352 *img = ls_ucode_img_r352(_img);
 		const struct acr_r352_ls_func *ls_func =
 					    acr->func->ls_func[_img->falcon_id];
-		u8 gdesc[ls_func->bl_desc_size];
 
 		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
 				      sizeof(img->wpr_header));
@@ -447,6 +460,8 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 
 	nvkm_done(wpr_blob);
 
+	kfree(gdesc);
+
 	return 0;
 }
 
@@ -771,7 +786,11 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 	struct fw_bl_desc *hsbl_desc;
 	void *bl, *blob_data, *hsbl_code, *hsbl_data;
 	u32 code_size;
-	u8 bl_desc[bl_desc_size];
+	u8 *bl_desc;
+
+	bl_desc = kzalloc(bl_desc_size, GFP_KERNEL);
+	if (!bl_desc)
+		return -ENOMEM;
 
 	/* Find the bootloader descriptor for our blob and copy it */
 	if (blob == acr->load_blob) {
@@ -802,7 +821,6 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 			      code_size, hsbl_desc->start_tag, 0, false);
 
 	/* Generate the BL header */
-	memset(bl_desc, 0, bl_desc_size);
 	acr->func->generate_hs_bl_desc(load_hdr, bl_desc, offset);
 
 	/*
@@ -811,6 +829,7 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 	nvkm_falcon_load_dmem(falcon, bl_desc, hsbl_desc->dmem_load_off,
 			      bl_desc_size, 0);
 
+	kfree(bl_desc);
 	return hsbl_desc->start_tag << 8;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
index 866877b88797..978ad0790367 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
@@ -265,6 +265,19 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 {
 	struct ls_ucode_img *_img;
 	u32 pos = 0;
+	u32 max_desc_size = 0;
+	u8 *gdesc;
+
+	list_for_each_entry(_img, imgs, node) {
+		const struct acr_r352_ls_func *ls_func =
+					    acr->func->ls_func[_img->falcon_id];
+
+		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
+	}
+
+	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
+	if (!gdesc)
+		return -ENOMEM;
 
 	nvkm_kmap(wpr_blob);
 
@@ -272,7 +285,6 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 		struct ls_ucode_img_r367 *img = ls_ucode_img_r367(_img);
 		const struct acr_r352_ls_func *ls_func =
 					    acr->func->ls_func[_img->falcon_id];
-		u8 gdesc[ls_func->bl_desc_size];
 
 		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
 				      sizeof(img->wpr_header));
@@ -298,6 +310,8 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 
 	nvkm_done(wpr_blob);
 
+	kfree(gdesc);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
index 30491d132d59..df8b919dcf09 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
@@ -129,6 +129,7 @@ gm20b_secboot_new(struct nvkm_device *device, int index,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
 MODULE_FIRMWARE("nvidia/gm20b/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/gm20b/acr/ucode_load.bin");
 MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_bl.bin");
@@ -144,3 +145,4 @@ MODULE_FIRMWARE("nvidia/gm20b/gr/sw_method_init.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/sig.bin");
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
index 632e9545e292..28ca29d0eeee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
@@ -74,6 +74,7 @@ gp10b_secboot_new(struct nvkm_device *device, int index,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
 MODULE_FIRMWARE("nvidia/gp10b/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/gp10b/acr/ucode_load.bin");
 MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_bl.bin");
@@ -91,3 +92,4 @@ MODULE_FIRMWARE("nvidia/gp10b/gr/sw_method_init.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");
+#endif
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index 5cde26ac937b..2ddb856666c4 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -126,14 +126,14 @@ static int omap_connector_get_modes(struct drm_connector *connector)
 
 		if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) &&
 				drm_edid_is_valid(edid)) {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 					connector, edid);
 			n = drm_add_edid_modes(connector, edid);
 
 			omap_connector->hdmi_mode =
 				drm_detect_hdmi_monitor(edid);
 		} else {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 					connector, NULL);
 		}
 
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 5005ecc284d2..1b6601e9b107 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -274,7 +274,7 @@ static int omap_modeset_init(struct drm_device *dev)
 		if (IS_ERR(crtc))
 			return PTR_ERR(crtc);
 
-		drm_mode_connector_attach_encoder(connector, encoder);
+		drm_connector_attach_encoder(connector, encoder);
 		encoder->possible_crtcs = (1 << crtc_idx);
 
 		priv->crtcs[priv->num_crtcs++] = crtc;
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
index e848af235df5..3ad4a46c4e94 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -334,7 +334,7 @@ static int ili9881c_prepare(struct drm_panel *panel)
 	if (ret)
 		return ret;
 
-	mipi_dsi_dcs_exit_sleep_mode(ctx->dsi);
+	ret = mipi_dsi_dcs_exit_sleep_mode(ctx->dsi);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index bb53e0850764..72edb334d997 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -11,6 +11,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/regulator/consumer.h>
 
 #include <drm/drmP.h>
@@ -20,12 +21,41 @@
 
 #include <video/mipi_display.h>
 
+struct panel_init_cmd {
+	size_t len;
+	const char *data;
+};
+
+#define _INIT_CMD(...) { \
+	.len = sizeof((char[]){__VA_ARGS__}), \
+	.data = (char[]){__VA_ARGS__} }
+
+struct panel_desc {
+	const struct drm_display_mode *mode;
+	unsigned int bpc;
+	struct {
+		unsigned int width;
+		unsigned int height;
+	} size;
+
+	unsigned long flags;
+	enum mipi_dsi_pixel_format format;
+	const struct panel_init_cmd *init_cmds;
+	unsigned int lanes;
+	const char * const *supply_names;
+	unsigned int num_supplies;
+	unsigned int sleep_mode_delay;
+	unsigned int power_down_delay;
+};
+
 struct innolux_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *link;
+	const struct panel_desc *desc;
 
 	struct backlight_device *backlight;
-	struct regulator *supply;
+	struct regulator_bulk_data *supplies;
+	unsigned int num_supplies;
 	struct gpio_desc *enable_gpio;
 
 	bool prepared;
@@ -72,12 +102,16 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 		return err;
 	}
 
+	if (innolux->desc->sleep_mode_delay)
+		msleep(innolux->desc->sleep_mode_delay);
+
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
 
-	/* T8: 80ms - 1000ms */
-	msleep(80);
+	if (innolux->desc->power_down_delay)
+		msleep(innolux->desc->power_down_delay);
 
-	err = regulator_disable(innolux->supply);
+	err = regulator_bulk_disable(innolux->desc->num_supplies,
+				     innolux->supplies);
 	if (err < 0)
 		return err;
 
@@ -89,24 +123,55 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 static int innolux_panel_prepare(struct drm_panel *panel)
 {
 	struct innolux_panel *innolux = to_innolux_panel(panel);
-	int err, regulator_err;
+	int err;
 
 	if (innolux->prepared)
 		return 0;
 
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
 
-	err = regulator_enable(innolux->supply);
+	err = regulator_bulk_enable(innolux->desc->num_supplies,
+				    innolux->supplies);
 	if (err < 0)
 		return err;
 
-	/* T2: 15ms - 1000ms */
-	usleep_range(15000, 16000);
+	/* p079zca: t2 (20ms), p097pfg: t4 (15ms) */
+	usleep_range(20000, 21000);
 
 	gpiod_set_value_cansleep(innolux->enable_gpio, 1);
 
-	/* T4: 15ms - 1000ms */
-	usleep_range(15000, 16000);
+	/* p079zca: t4, p097pfg: t5 */
+	usleep_range(20000, 21000);
+
+	if (innolux->desc->init_cmds) {
+		const struct panel_init_cmd *cmds =
+					innolux->desc->init_cmds;
+		unsigned int i;
+
+		for (i = 0; cmds[i].len != 0; i++) {
+			const struct panel_init_cmd *cmd = &cmds[i];
+
+			err = mipi_dsi_generic_write(innolux->link, cmd->data,
+						     cmd->len);
+			if (err < 0) {
+				dev_err(panel->dev,
+					"failed to write command %u\n", i);
+				goto poweroff;
+			}
+
+			/*
+			 * Included by random guessing, because without this
+			 * (or at least, some delay), the panel sometimes
+			 * didn't appear to pick up the command sequence.
+			 */
+			err = mipi_dsi_dcs_nop(innolux->link);
+			if (err < 0) {
+				dev_err(panel->dev,
+					"failed to send DCS nop: %d\n", err);
+				goto poweroff;
+			}
+		}
+	}
 
 	err = mipi_dsi_dcs_exit_sleep_mode(innolux->link);
 	if (err < 0) {
@@ -133,12 +198,9 @@ static int innolux_panel_prepare(struct drm_panel *panel)
 	return 0;
 
 poweroff:
-	regulator_err = regulator_disable(innolux->supply);
-	if (regulator_err)
-		DRM_DEV_ERROR(panel->dev, "failed to disable regulator: %d\n",
-			      regulator_err);
-
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
+	regulator_bulk_disable(innolux->desc->num_supplies, innolux->supplies);
+
 	return err;
 }
 
@@ -162,7 +224,11 @@ static int innolux_panel_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static const struct drm_display_mode default_mode = {
+static const char * const innolux_p079zca_supply_names[] = {
+	"power",
+};
+
+static const struct drm_display_mode innolux_p079zca_mode = {
 	.clock = 56900,
 	.hdisplay = 768,
 	.hsync_start = 768 + 40,
@@ -175,15 +241,181 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
+static const struct panel_desc innolux_p079zca_panel_desc = {
+	.mode = &innolux_p079zca_mode,
+	.bpc = 8,
+	.size = {
+		.width = 120,
+		.height = 160,
+	},
+	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+		 MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.lanes = 4,
+	.supply_names = innolux_p079zca_supply_names,
+	.num_supplies = ARRAY_SIZE(innolux_p079zca_supply_names),
+	.power_down_delay = 80, /* T8: 80ms - 1000ms */
+};
+
+static const char * const innolux_p097pfg_supply_names[] = {
+	"avdd",
+	"avee",
+};
+
+static const struct drm_display_mode innolux_p097pfg_mode = {
+	.clock = 229000,
+	.hdisplay = 1536,
+	.hsync_start = 1536 + 100,
+	.hsync_end = 1536 + 100 + 24,
+	.htotal = 1536 + 100 + 24 + 100,
+	.vdisplay = 2048,
+	.vsync_start = 2048 + 100,
+	.vsync_end = 2048 + 100 + 2,
+	.vtotal = 2048 + 100 + 2 + 18,
+	.vrefresh = 60,
+};
+
+/*
+ * Display manufacturer failed to provide init sequencing according to
+ * https://chromium-review.googlesource.com/c/chromiumos/third_party/coreboot/+/892065/
+ * so the init sequence stems from a register dump of a working panel.
+ */
+static const struct panel_init_cmd innolux_p097pfg_init_cmds[] = {
+	/* page 0 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x00),
+	_INIT_CMD(0xB1, 0xE8, 0x11),
+	_INIT_CMD(0xB2, 0x25, 0x02),
+	_INIT_CMD(0xB5, 0x08, 0x00),
+	_INIT_CMD(0xBC, 0x0F, 0x00),
+	_INIT_CMD(0xB8, 0x03, 0x06, 0x00, 0x00),
+	_INIT_CMD(0xBD, 0x01, 0x90, 0x14, 0x14),
+	_INIT_CMD(0x6F, 0x01),
+	_INIT_CMD(0xC0, 0x03),
+	_INIT_CMD(0x6F, 0x02),
+	_INIT_CMD(0xC1, 0x0D),
+	_INIT_CMD(0xD9, 0x01, 0x09, 0x70),
+	_INIT_CMD(0xC5, 0x12, 0x21, 0x00),
+	_INIT_CMD(0xBB, 0x93, 0x93),
+
+	/* page 1 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x01),
+	_INIT_CMD(0xB3, 0x3C, 0x3C),
+	_INIT_CMD(0xB4, 0x0F, 0x0F),
+	_INIT_CMD(0xB9, 0x45, 0x45),
+	_INIT_CMD(0xBA, 0x14, 0x14),
+	_INIT_CMD(0xCA, 0x02),
+	_INIT_CMD(0xCE, 0x04),
+	_INIT_CMD(0xC3, 0x9B, 0x9B),
+	_INIT_CMD(0xD8, 0xC0, 0x03),
+	_INIT_CMD(0xBC, 0x82, 0x01),
+	_INIT_CMD(0xBD, 0x9E, 0x01),
+
+	/* page 2 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x02),
+	_INIT_CMD(0xB0, 0x82),
+	_INIT_CMD(0xD1, 0x00, 0x00, 0x00, 0x3E, 0x00, 0x82, 0x00, 0xA5,
+		  0x00, 0xC1, 0x00, 0xEA, 0x01, 0x0D, 0x01, 0x40),
+	_INIT_CMD(0xD2, 0x01, 0x6A, 0x01, 0xA8, 0x01, 0xDC, 0x02, 0x29,
+		  0x02, 0x67, 0x02, 0x68, 0x02, 0xA8, 0x02, 0xF0),
+	_INIT_CMD(0xD3, 0x03, 0x19, 0x03, 0x49, 0x03, 0x67, 0x03, 0x8C,
+		  0x03, 0xA6, 0x03, 0xC7, 0x03, 0xDE, 0x03, 0xEC),
+	_INIT_CMD(0xD4, 0x03, 0xFF, 0x03, 0xFF),
+	_INIT_CMD(0xE0, 0x00, 0x00, 0x00, 0x86, 0x00, 0xC5, 0x00, 0xE5,
+		  0x00, 0xFF, 0x01, 0x26, 0x01, 0x45, 0x01, 0x75),
+	_INIT_CMD(0xE1, 0x01, 0x9C, 0x01, 0xD5, 0x02, 0x05, 0x02, 0x4D,
+		  0x02, 0x86, 0x02, 0x87, 0x02, 0xC3, 0x03, 0x03),
+	_INIT_CMD(0xE2, 0x03, 0x2A, 0x03, 0x56, 0x03, 0x72, 0x03, 0x94,
+		  0x03, 0xAC, 0x03, 0xCB, 0x03, 0xE0, 0x03, 0xED),
+	_INIT_CMD(0xE3, 0x03, 0xFF, 0x03, 0xFF),
+
+	/* page 3 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x03),
+	_INIT_CMD(0xB0, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xB1, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xB2, 0x00, 0x00, 0x06, 0x04, 0x01, 0x40, 0x85),
+	_INIT_CMD(0xB3, 0x10, 0x07, 0xFC, 0x04, 0x01, 0x40, 0x80),
+	_INIT_CMD(0xB6, 0xF0, 0x08, 0x00, 0x04, 0x00, 0x00, 0x00, 0x01,
+		  0x40, 0x80),
+	_INIT_CMD(0xBA, 0xC5, 0x07, 0x00, 0x04, 0x11, 0x25, 0x8C),
+	_INIT_CMD(0xBB, 0xC5, 0x07, 0x00, 0x03, 0x11, 0x25, 0x8C),
+	_INIT_CMD(0xC0, 0x00, 0x3C, 0x00, 0x00, 0x00, 0x80, 0x80),
+	_INIT_CMD(0xC1, 0x00, 0x3C, 0x00, 0x00, 0x00, 0x80, 0x80),
+	_INIT_CMD(0xC4, 0x00, 0x00),
+	_INIT_CMD(0xEF, 0x41),
+
+	/* page 4 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x04),
+	_INIT_CMD(0xEC, 0x4C),
+
+	/* page 5 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x05),
+	_INIT_CMD(0xB0, 0x13, 0x03, 0x03, 0x01),
+	_INIT_CMD(0xB1, 0x30, 0x00),
+	_INIT_CMD(0xB2, 0x02, 0x02, 0x00),
+	_INIT_CMD(0xB3, 0x82, 0x23, 0x82, 0x9D),
+	_INIT_CMD(0xB4, 0xC5, 0x75, 0x24, 0x57),
+	_INIT_CMD(0xB5, 0x00, 0xD4, 0x72, 0x11, 0x11, 0xAB, 0x0A),
+	_INIT_CMD(0xB6, 0x00, 0x00, 0xD5, 0x72, 0x24, 0x56),
+	_INIT_CMD(0xB7, 0x5C, 0xDC, 0x5C, 0x5C),
+	_INIT_CMD(0xB9, 0x0C, 0x00, 0x00, 0x01, 0x00),
+	_INIT_CMD(0xC0, 0x75, 0x11, 0x11, 0x54, 0x05),
+	_INIT_CMD(0xC6, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xD0, 0x00, 0x48, 0x08, 0x00, 0x00),
+	_INIT_CMD(0xD1, 0x00, 0x48, 0x09, 0x00, 0x00),
+
+	/* page 6 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x06),
+	_INIT_CMD(0xB0, 0x02, 0x32, 0x32, 0x08, 0x2F),
+	_INIT_CMD(0xB1, 0x2E, 0x15, 0x14, 0x13, 0x12),
+	_INIT_CMD(0xB2, 0x11, 0x10, 0x00, 0x3D, 0x3D),
+	_INIT_CMD(0xB3, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xB4, 0x3D, 0x32),
+	_INIT_CMD(0xB5, 0x03, 0x32, 0x32, 0x09, 0x2F),
+	_INIT_CMD(0xB6, 0x2E, 0x1B, 0x1A, 0x19, 0x18),
+	_INIT_CMD(0xB7, 0x17, 0x16, 0x01, 0x3D, 0x3D),
+	_INIT_CMD(0xB8, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xB9, 0x3D, 0x32),
+	_INIT_CMD(0xC0, 0x01, 0x32, 0x32, 0x09, 0x2F),
+	_INIT_CMD(0xC1, 0x2E, 0x1A, 0x1B, 0x16, 0x17),
+	_INIT_CMD(0xC2, 0x18, 0x19, 0x03, 0x3D, 0x3D),
+	_INIT_CMD(0xC3, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xC4, 0x3D, 0x32),
+	_INIT_CMD(0xC5, 0x00, 0x32, 0x32, 0x08, 0x2F),
+	_INIT_CMD(0xC6, 0x2E, 0x14, 0x15, 0x10, 0x11),
+	_INIT_CMD(0xC7, 0x12, 0x13, 0x02, 0x3D, 0x3D),
+	_INIT_CMD(0xC8, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xC9, 0x3D, 0x32),
+
+	{},
+};
+
+static const struct panel_desc innolux_p097pfg_panel_desc = {
+	.mode = &innolux_p097pfg_mode,
+	.bpc = 8,
+	.size = {
+		.width = 147,
+		.height = 196,
+	},
+	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+		 MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.init_cmds = innolux_p097pfg_init_cmds,
+	.lanes = 4,
+	.supply_names = innolux_p097pfg_supply_names,
+	.num_supplies = ARRAY_SIZE(innolux_p097pfg_supply_names),
+	.sleep_mode_delay = 100, /* T15 */
+};
+
 static int innolux_panel_get_modes(struct drm_panel *panel)
 {
+	struct innolux_panel *innolux = to_innolux_panel(panel);
+	const struct drm_display_mode *m = innolux->desc->mode;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(panel->drm, m);
 	if (!mode) {
 		DRM_DEV_ERROR(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
-			      default_mode.hdisplay, default_mode.vdisplay,
-			      default_mode.vrefresh);
+			      m->hdisplay, m->vdisplay, m->vrefresh);
 		return -ENOMEM;
 	}
 
@@ -191,9 +423,11 @@ static int innolux_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_probed_add(panel->connector, mode);
 
-	panel->connector->display_info.width_mm = 120;
-	panel->connector->display_info.height_mm = 160;
-	panel->connector->display_info.bpc = 8;
+	panel->connector->display_info.width_mm =
+			innolux->desc->size.width;
+	panel->connector->display_info.height_mm =
+			innolux->desc->size.height;
+	panel->connector->display_info.bpc = innolux->desc->bpc;
 
 	return 1;
 }
@@ -207,19 +441,42 @@ static const struct drm_panel_funcs innolux_panel_funcs = {
 };
 
 static const struct of_device_id innolux_of_match[] = {
-	{ .compatible = "innolux,p079zca", },
+	{ .compatible = "innolux,p079zca",
+	  .data = &innolux_p079zca_panel_desc
+	},
+	{ .compatible = "innolux,p097pfg",
+	  .data = &innolux_p097pfg_panel_desc
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, innolux_of_match);
 
-static int innolux_panel_add(struct innolux_panel *innolux)
+static int innolux_panel_add(struct mipi_dsi_device *dsi,
+			     const struct panel_desc *desc)
 {
-	struct device *dev = &innolux->link->dev;
-	int err;
+	struct innolux_panel *innolux;
+	struct device *dev = &dsi->dev;
+	int err, i;
+
+	innolux = devm_kzalloc(dev, sizeof(*innolux), GFP_KERNEL);
+	if (!innolux)
+		return -ENOMEM;
+
+	innolux->desc = desc;
+
+	innolux->supplies = devm_kcalloc(dev, desc->num_supplies,
+					 sizeof(*innolux->supplies),
+					 GFP_KERNEL);
+	if (!innolux->supplies)
+		return -ENOMEM;
+
+	for (i = 0; i < desc->num_supplies; i++)
+		innolux->supplies[i].supply = desc->supply_names[i];
 
-	innolux->supply = devm_regulator_get(dev, "power");
-	if (IS_ERR(innolux->supply))
-		return PTR_ERR(innolux->supply);
+	err = devm_regulator_bulk_get(dev, desc->num_supplies,
+				      innolux->supplies);
+	if (err < 0)
+		return err;
 
 	innolux->enable_gpio = devm_gpiod_get_optional(dev, "enable",
 						       GPIOD_OUT_HIGH);
@@ -230,15 +487,21 @@ static int innolux_panel_add(struct innolux_panel *innolux)
 	}
 
 	innolux->backlight = devm_of_find_backlight(dev);
-
 	if (IS_ERR(innolux->backlight))
 		return PTR_ERR(innolux->backlight);
 
 	drm_panel_init(&innolux->base);
 	innolux->base.funcs = &innolux_panel_funcs;
-	innolux->base.dev = &innolux->link->dev;
+	innolux->base.dev = dev;
+
+	err = drm_panel_add(&innolux->base);
+	if (err < 0)
+		return err;
+
+	mipi_dsi_set_drvdata(dsi, innolux);
+	innolux->link = dsi;
 
-	return drm_panel_add(&innolux->base);
+	return 0;
 }
 
 static void innolux_panel_del(struct innolux_panel *innolux)
@@ -249,28 +512,19 @@ static void innolux_panel_del(struct innolux_panel *innolux)
 
 static int innolux_panel_probe(struct mipi_dsi_device *dsi)
 {
-	struct innolux_panel *innolux;
+	const struct panel_desc *desc;
 	int err;
 
-	dsi->lanes = 4;
-	dsi->format = MIPI_DSI_FMT_RGB888;
-	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
-			  MIPI_DSI_MODE_LPM;
-
-	innolux = devm_kzalloc(&dsi->dev, sizeof(*innolux), GFP_KERNEL);
-	if (!innolux)
-		return -ENOMEM;
-
-	mipi_dsi_set_drvdata(dsi, innolux);
+	desc = of_device_get_match_data(&dsi->dev);
+	dsi->mode_flags = desc->flags;
+	dsi->format = desc->format;
+	dsi->lanes = desc->lanes;
 
-	innolux->link = dsi;
-
-	err = innolux_panel_add(innolux);
+	err = innolux_panel_add(dsi, desc);
 	if (err < 0)
 		return err;
 
-	err = mipi_dsi_attach(dsi);
-	return err;
+	return mipi_dsi_attach(dsi);
 }
 
 static int innolux_panel_remove(struct mipi_dsi_device *dsi)
@@ -317,5 +571,6 @@ static struct mipi_dsi_driver innolux_panel_driver = {
 module_mipi_dsi_driver(innolux_panel_driver);
 
 MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_AUTHOR("Lin Huang <hl@rock-chips.com>");
 MODULE_DESCRIPTION("Innolux P079ZCA panel driver");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
index a188a3959f1a..6ad827b93ae1 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
@@ -823,7 +823,7 @@ static void s6e8aa0_read_mtp_id(struct s6e8aa0 *ctx)
 	int ret, i;
 
 	ret = s6e8aa0_dcs_read(ctx, 0xd1, id, ARRAY_SIZE(id));
-	if (ret < ARRAY_SIZE(id) || id[0] == 0x00) {
+	if (ret < 0 || ret < ARRAY_SIZE(id) || id[0] == 0x00) {
 		dev_err(ctx->dev, "read id failed\n");
 		ctx->error = -EIO;
 		return;
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index ac6aaa174c0b..5b5d0a24e713 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -252,7 +252,7 @@ static int panel_simple_get_modes(struct drm_panel *panel)
 	/* probe EDID if a DDC bus is available */
 	if (p->ddc) {
 		struct edid *edid = drm_get_edid(panel->connector, p->ddc);
-		drm_mode_connector_update_edid_property(panel->connector, edid);
+		drm_connector_update_edid_property(panel->connector, edid);
 		if (edid) {
 			num += drm_add_edid_modes(panel->connector, edid);
 			kfree(edid);
@@ -772,6 +772,28 @@ static const struct panel_desc avic_tm070ddh03 = {
 	},
 };
 
+static const struct drm_display_mode boe_hv070wsa_mode = {
+	.clock = 40800,
+	.hdisplay = 1024,
+	.hsync_start = 1024 + 90,
+	.hsync_end = 1024 + 90 + 90,
+	.htotal = 1024 + 90 + 90 + 90,
+	.vdisplay = 600,
+	.vsync_start = 600 + 3,
+	.vsync_end = 600 + 3 + 4,
+	.vtotal = 600 + 3 + 4 + 3,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc boe_hv070wsa = {
+	.modes = &boe_hv070wsa_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 154,
+		.height = 90,
+	},
+};
+
 static const struct drm_display_mode boe_nv101wxmn51_modes[] = {
 	{
 		.clock = 71900,
@@ -884,6 +906,61 @@ static const struct panel_desc chunghwa_claa101wb01 = {
 	},
 };
 
+static const struct drm_display_mode dataimage_scf0700c48ggu18_mode = {
+	.clock = 33260,
+	.hdisplay = 800,
+	.hsync_start = 800 + 40,
+	.hsync_end = 800 + 40 + 128,
+	.htotal = 800 + 40 + 128 + 88,
+	.vdisplay = 480,
+	.vsync_start = 480 + 10,
+	.vsync_end = 480 + 10 + 2,
+	.vtotal = 480 + 10 + 2 + 33,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc dataimage_scf0700c48ggu18 = {
+	.modes = &dataimage_scf0700c48ggu18_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE,
+};
+
+static const struct display_timing dlc_dlc0700yzg_1_timing = {
+	.pixelclock = { 45000000, 51200000, 57000000 },
+	.hactive = { 1024, 1024, 1024 },
+	.hfront_porch = { 100, 106, 113 },
+	.hback_porch = { 100, 106, 113 },
+	.hsync_len = { 100, 108, 114 },
+	.vactive = { 600, 600, 600 },
+	.vfront_porch = { 8, 11, 15 },
+	.vback_porch = { 8, 11, 15 },
+	.vsync_len = { 9, 13, 15 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc dlc_dlc0700yzg_1 = {
+	.timings = &dlc_dlc0700yzg_1_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 30,
+		.enable = 200,
+		.disable = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
+};
+
 static const struct drm_display_mode edt_et057090dhu_mode = {
 	.clock = 25175,
 	.hdisplay = 640,
@@ -936,6 +1013,18 @@ static const struct panel_desc edt_etm0700g0dh6 = {
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_NEGEDGE,
 };
 
+static const struct panel_desc edt_etm0700g0bdh6 = {
+	.modes = &edt_etm0700g0dh6_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE,
+};
+
 static const struct drm_display_mode foxlink_fl500wvr00_a0t_mode = {
 	.clock = 32260,
 	.hdisplay = 800,
@@ -1113,6 +1202,36 @@ static const struct panel_desc innolux_at070tn92 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct display_timing innolux_g070y2_l01_timing = {
+	.pixelclock = { 28000000, 29500000, 32000000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 61, 91, 141 },
+	.hback_porch = { 60, 90, 140 },
+	.hsync_len = { 12, 12, 12 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 4, 9, 30 },
+	.vback_porch = { 4, 8, 28 },
+	.vsync_len = { 2, 2, 2 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc innolux_g070y2_l01 = {
+	.timings = &innolux_g070y2_l01_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.delay = {
+		.prepare = 10,
+		.enable = 100,
+		.disable = 100,
+		.unprepare = 800,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+};
+
 static const struct display_timing innolux_g101ice_l01_timing = {
 	.pixelclock = { 60400000, 71100000, 74700000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -1562,6 +1681,33 @@ static const struct panel_desc netron_dy_e231732 = {
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
 };
 
+static const struct drm_display_mode newhaven_nhd_43_480272ef_atxl_mode = {
+	.clock = 9000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 2,
+	.hsync_end = 480 + 2 + 41,
+	.htotal = 480 + 2 + 41 + 2,
+	.vdisplay = 272,
+	.vsync_start = 272 + 2,
+	.vsync_end = 272 + 2 + 10,
+	.vtotal = 272 + 2 + 10 + 2,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc newhaven_nhd_43_480272ef_atxl = {
+	.modes = &newhaven_nhd_43_480272ef_atxl_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 95,
+		.height = 54,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE |
+		     DRM_BUS_FLAG_SYNC_POSEDGE,
+};
+
 static const struct display_timing nlt_nl192108ac18_02d_timing = {
 	.pixelclock = { 130000000, 148350000, 163000000 },
 	.hactive = { 1920, 1920, 1920 },
@@ -1747,6 +1893,36 @@ static const struct panel_desc qd43003c0_40 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct display_timing rocktech_rk070er9427_timing = {
+	.pixelclock = { 26400000, 33300000, 46800000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 16, 210, 354 },
+	.hback_porch = { 46, 46, 46 },
+	.hsync_len = { 1, 1, 1 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 7, 22, 147 },
+	.vback_porch = { 23, 23, 23 },
+	.vsync_len = { 1, 1, 1 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc rocktech_rk070er9427 = {
+	.timings = &rocktech_rk070er9427_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 41,
+		.enable = 50,
+		.unprepare = 41,
+		.disable = 50,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+};
+
 static const struct drm_display_mode samsung_lsn122dl01_c01_mode = {
 	.clock = 271560,
 	.hdisplay = 2560,
@@ -1815,6 +1991,30 @@ static const struct panel_desc samsung_ltn140at29_301 = {
 	},
 };
 
+static const struct drm_display_mode sharp_lq035q7db03_mode = {
+	.clock = 5500,
+	.hdisplay = 240,
+	.hsync_start = 240 + 16,
+	.hsync_end = 240 + 16 + 7,
+	.htotal = 240 + 16 + 7 + 5,
+	.vdisplay = 320,
+	.vsync_start = 320 + 9,
+	.vsync_end = 320 + 9 + 1,
+	.vtotal = 320 + 9 + 1 + 7,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc sharp_lq035q7db03 = {
+	.modes = &sharp_lq035q7db03_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 54,
+		.height = 72,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+};
+
 static const struct display_timing sharp_lq101k1ly04_timing = {
 	.pixelclock = { 60000000, 65000000, 80000000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -2167,6 +2367,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "avic,tm070ddh03",
 		.data = &avic_tm070ddh03,
 	}, {
+		.compatible = "boe,hv070wsa-100",
+		.data = &boe_hv070wsa
+	}, {
 		.compatible = "boe,nv101wxmn51",
 		.data = &boe_nv101wxmn51,
 	}, {
@@ -2179,6 +2382,12 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "chunghwa,claa101wb01",
 		.data = &chunghwa_claa101wb01
 	}, {
+		.compatible = "dataimage,scf0700c48ggu18",
+		.data = &dataimage_scf0700c48ggu18,
+	}, {
+		.compatible = "dlc,dlc0700yzg-1",
+		.data = &dlc_dlc0700yzg_1,
+	}, {
 		.compatible = "edt,et057090dhu",
 		.data = &edt_et057090dhu,
 	}, {
@@ -2188,6 +2397,12 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "edt,etm0700g0dh6",
 		.data = &edt_etm0700g0dh6,
 	}, {
+		.compatible = "edt,etm0700g0bdh6",
+		.data = &edt_etm0700g0bdh6,
+	}, {
+		.compatible = "edt,etm0700g0edh6",
+		.data = &edt_etm0700g0bdh6,
+	}, {
 		.compatible = "foxlink,fl500wvr00-a0t",
 		.data = &foxlink_fl500wvr00_a0t,
 	}, {
@@ -2209,10 +2424,13 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "innolux,at070tn92",
 		.data = &innolux_at070tn92,
 	}, {
-		.compatible ="innolux,g101ice-l01",
+		.compatible = "innolux,g070y2-l01",
+		.data = &innolux_g070y2_l01,
+	}, {
+		.compatible = "innolux,g101ice-l01",
 		.data = &innolux_g101ice_l01
 	}, {
-		.compatible ="innolux,g121i1-l01",
+		.compatible = "innolux,g121i1-l01",
 		.data = &innolux_g121i1_l01
 	}, {
 		.compatible = "innolux,g121x1-l03",
@@ -2263,6 +2481,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "netron-dy,e231732",
 		.data = &netron_dy_e231732,
 	}, {
+		.compatible = "newhaven,nhd-4.3-480272ef-atxl",
+		.data = &newhaven_nhd_43_480272ef_atxl,
+	}, {
 		.compatible = "nlt,nl192108ac18-02d",
 		.data = &nlt_nl192108ac18_02d,
 	}, {
@@ -2284,6 +2505,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "qiaodian,qd43003c0-40",
 		.data = &qd43003c0_40,
 	}, {
+		.compatible = "rocktech,rk070er9427",
+		.data = &rocktech_rk070er9427,
+	}, {
 		.compatible = "samsung,lsn122dl01-c01",
 		.data = &samsung_lsn122dl01_c01,
 	}, {
@@ -2293,6 +2517,9 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "samsung,ltn140at29-301",
 		.data = &samsung_ltn140at29_301,
 	}, {
+		.compatible = "sharp,lq035q7db03",
+		.data = &sharp_lq035q7db03,
+	}, {
 		.compatible = "sharp,lq101k1ly04",
 		.data = &sharp_lq101k1ly04,
 	}, {
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index a432eb7ad445..754f6b25f265 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -63,7 +63,7 @@ pl111_mode_valid(struct drm_crtc *crtc,
 	 * We use the pixelclock to also account for interlaced modes, the
 	 * resulting bandwidth is in bytes per second.
 	 */
-	bw = mode->clock * 1000; /* In Hz */
+	bw = mode->clock * 1000ULL; /* In Hz */
 	bw = bw * mode->hdisplay * mode->vdisplay * cpp;
 	bw = div_u64(bw, mode->htotal * mode->vtotal);
 
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 054b93689d94..47fe30223444 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -250,6 +250,8 @@ static struct drm_driver pl111_drm_driver = {
 	.gem_prime_import_sg_table = pl111_gem_import_sg_table,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
+	.gem_prime_mmap = drm_gem_cma_prime_mmap,
+	.gem_prime_vmap = drm_gem_cma_prime_vmap,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = pl111_debugfs_init,
@@ -302,13 +304,14 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	if (IS_ERR(priv->regs)) {
 		dev_err(dev, "%s failed mmio\n", __func__);
 		ret = PTR_ERR(priv->regs);
-		goto dev_unref;
+		goto dev_put;
 	}
 
 	/* This may override some variant settings */
 	ret = pl111_versatile_init(dev, priv);
 	if (ret)
-		goto dev_unref;
+		goto dev_put;
+
 	pl111_nomadik_init(dev);
 
 	/* turn off interrupts before requesting the irq */
@@ -323,16 +326,16 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 
 	ret = pl111_modeset_init(drm);
 	if (ret != 0)
-		goto dev_unref;
+		goto dev_put;
 
 	ret = drm_dev_register(drm, 0);
 	if (ret < 0)
-		goto dev_unref;
+		goto dev_put;
 
 	return 0;
 
-dev_unref:
-	drm_dev_unref(drm);
+dev_put:
+	drm_dev_put(drm);
 	of_reserved_mem_device_release(dev);
 
 	return ret;
@@ -349,7 +352,7 @@ static int pl111_amba_remove(struct amba_device *amba_dev)
 	if (priv->panel)
 		drm_panel_bridge_remove(priv->bridge);
 	drm_mode_config_cleanup(drm);
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 	of_reserved_mem_device_release(dev);
 
 	return 0;
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 768207fbbae3..0570c6826bff 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -1086,7 +1086,7 @@ static int qdev_output_init(struct drm_device *dev, int num_output)
 	/* we get HPD via client monitors config */
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 	encoder->possible_crtcs = 1 << num_output;
-	drm_mode_connector_attach_encoder(&qxl_output->base,
+	drm_connector_attach_encoder(&qxl_output->base,
 					  &qxl_output->enc);
 	drm_encoder_helper_add(encoder, &qxl_enc_helper_funcs);
 	drm_connector_helper_add(connector, &qxl_connector_helper_funcs);
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index b9302c918271..d587779a80b4 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5676,19 +5676,29 @@ int ci_dpm_init(struct radeon_device *rdev)
 	u16 data_offset, size;
 	u8 frev, crev;
 	struct ci_power_info *pi;
+	enum pci_bus_speed speed_cap;
+	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	rdev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	} else {
+		if (speed_cap == PCIE_SPEED_8_0GT)
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50 |
+				RADEON_PCIE_SPEED_80;
+		else if (speed_cap == PCIE_SPEED_5_0GT)
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50;
+		else
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25;
+	}
 	pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = RADEON_PCIE_GEN1;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 7c73bc7e2f85..ebce4601a305 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -9499,9 +9499,10 @@ int cik_set_vce_clocks(struct radeon_device *rdev, u32 evclk, u32 ecclk)
 static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 {
 	struct pci_dev *root = rdev->pdev->bus->self;
+	enum pci_bus_speed speed_cap;
 	int bridge_pos, gpu_pos;
-	u32 speed_cntl, mask, current_data_rate;
-	int ret, i;
+	u32 speed_cntl, current_data_rate;
+	int i;
 	u16 tmp16;
 
 	if (pci_is_root_bus(rdev->pdev->bus))
@@ -9516,23 +9517,24 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret != 0)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN)
 		return;
 
-	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+	if ((speed_cap != PCIE_SPEED_8_0GT) &&
+	    (speed_cap != PCIE_SPEED_5_0GT))
 		return;
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
 		LC_CURRENT_DATA_RATE_SHIFT;
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		if (current_data_rate == 2) {
 			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
 			return;
 		}
 		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
-	} else if (mask & DRM_PCIE_SPEED_50) {
+	} else if (speed_cap == PCIE_SPEED_5_0GT) {
 		if (current_data_rate == 1) {
 			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
 			return;
@@ -9548,7 +9550,7 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!gpu_pos)
 		return;
 
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		/* re-try equalization if gen3 is not already enabled */
 		if (current_data_rate != 2) {
 			u16 bridge_cfg, gpu_cfg;
@@ -9636,9 +9638,9 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 
 	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
 	tmp16 &= ~0xf;
-	if (mask & DRM_PCIE_SPEED_80)
+	if (speed_cap == PCIE_SPEED_8_0GT)
 		tmp16 |= 3; /* gen3 */
-	else if (mask & DRM_PCIE_SPEED_50)
+	else if (speed_cap == PCIE_SPEED_5_0GT)
 		tmp16 |= 2; /* gen2 */
 	else
 		tmp16 |= 1; /* gen1 */
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index 73d4c5348116..5e044c98fca2 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -1327,9 +1327,9 @@ enum radeon_pcie_gen r600_get_pcie_gen_support(struct radeon_device *rdev,
 	case RADEON_PCIE_GEN3:
 		return RADEON_PCIE_GEN3;
 	default:
-		if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == RADEON_PCIE_GEN3))
+		if ((sys_mask & RADEON_PCIE_SPEED_80) && (default_gen == RADEON_PCIE_GEN3))
 			return RADEON_PCIE_GEN3;
-		else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == RADEON_PCIE_GEN2))
+		else if ((sys_mask & RADEON_PCIE_SPEED_50) && (default_gen == RADEON_PCIE_GEN2))
 			return RADEON_PCIE_GEN2;
 		else
 			return RADEON_PCIE_GEN1;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4a2eb409aacc..1a6f6edb3515 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1653,6 +1653,10 @@ struct radeon_pm {
 	struct radeon_dpm       dpm;
 };
 
+#define RADEON_PCIE_SPEED_25 1
+#define RADEON_PCIE_SPEED_50 2
+#define RADEON_PCIE_SPEED_80 4
+
 int radeon_pm_get_type_index(struct radeon_device *rdev,
 			     enum radeon_pm_state_type ps_type,
 			     int instance);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2aea2bdff99b..414642e5b7a3 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -244,23 +244,15 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 {
 	struct drm_device *dev = connector->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *best_encoder = NULL;
-	struct drm_encoder *encoder = NULL;
+	struct drm_encoder *best_encoder;
+	struct drm_encoder *encoder;
 	const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private;
 	bool connected;
 	int i;
 
 	best_encoder = connector_funcs->best_encoder(connector);
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					   connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if ((encoder == best_encoder) && (status == connector_status_connected))
 			connected = true;
 		else
@@ -270,7 +262,6 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 			radeon_atombios_connected_scratch_regs(connector, encoder, connected);
 		else
 			radeon_combios_connected_scratch_regs(connector, encoder, connected);
-
 	}
 }
 
@@ -279,17 +270,11 @@ static struct drm_encoder *radeon_find_encoder(struct drm_connector *connector,
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == encoder_type)
 			return encoder;
 	}
+
 	return NULL;
 }
 
@@ -383,20 +368,23 @@ static int radeon_ddc_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (radeon_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, radeon_connector->edid);
+		drm_connector_update_edid_property(connector, radeon_connector->edid);
 		ret = drm_add_edid_modes(connector, radeon_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(connector, NULL);
+	drm_connector_update_edid_property(connector, NULL);
 	return 0;
 }
 
 static struct drm_encoder *radeon_best_single_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
-	/* pick the encoder ids */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	struct drm_encoder *encoder;
+	int i;
+
+	/* pick the first one */
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -436,19 +424,19 @@ radeon_connector_analog_encoder_conflict_solve(struct drm_connector *connector,
 	struct drm_device *dev = connector->dev;
 	struct drm_connector *conflict;
 	struct radeon_connector *radeon_conflict;
-	int i;
 
 	list_for_each_entry(conflict, &dev->mode_config.connector_list, head) {
+		struct drm_encoder *enc;
+		int i;
+
 		if (conflict == connector)
 			continue;
 
 		radeon_conflict = to_radeon_connector(conflict);
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (conflict->encoder_ids[i] == 0)
-				break;
 
+		drm_connector_for_each_possible_encoder(conflict, enc, i) {
 			/* if the IDs match */
-			if (conflict->encoder_ids[i] == encoder->base.id) {
+			if (enc == encoder) {
 				if (conflict->status != connector_status_connected)
 					continue;
 
@@ -1256,7 +1244,7 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder = NULL;
 	const struct drm_encoder_helper_funcs *encoder_funcs;
-	int i, r;
+	int r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
@@ -1374,15 +1362,9 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 
 	/* find analog encoder */
 	if (radeon_connector->dac_load_detect) {
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == 0)
-				break;
-
-			encoder = drm_encoder_find(connector->dev, NULL,
-						   connector->encoder_ids[i]);
-			if (!encoder)
-				continue;
+		int i;
 
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
 			if (encoder->encoder_type != DRM_MODE_ENCODER_DAC &&
 			    encoder->encoder_type != DRM_MODE_ENCODER_TVDAC)
 				continue;
@@ -1458,18 +1440,11 @@ exit:
 /* okay need to be smart in here about which encoder to pick */
 static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder;
 	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
 
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (radeon_connector->use_digital == true) {
 			if (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)
 				return encoder;
@@ -1484,8 +1459,9 @@ static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 
 	/* then check use digitial */
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -1628,14 +1604,7 @@ u16 radeon_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
 	struct radeon_encoder *radeon_encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		radeon_encoder = to_radeon_encoder(encoder);
 
 		switch (radeon_encoder->encoder_id) {
@@ -1657,14 +1626,7 @@ static bool radeon_connector_encoder_is_hbr2(struct drm_connector *connector)
 	int i;
 	bool found = false;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		radeon_encoder = to_radeon_encoder(encoder);
 		if (radeon_encoder->caps & ATOM_ENCODER_CAP_RECORD_HBR2)
 			found = true;
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index cd8a3ee16649..f920be236cc9 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -195,11 +195,11 @@ static int radeon_dp_mst_get_ddc_modes(struct drm_connector *connector)
 	radeon_connector->edid = edid;
 	DRM_DEBUG_KMS("edid retrieved %p\n", edid);
 	if (radeon_connector->edid) {
-		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
+		drm_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);
+	drm_connector_update_edid_property(&radeon_connector->base, NULL);
 
 	return ret;
 }
@@ -290,7 +290,7 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol
 
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
-	drm_mode_connector_set_path_property(connector, pathprop);
+	drm_connector_set_path_property(connector, pathprop);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index c6ee80216cf4..c341fb2a5b56 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -211,7 +211,7 @@ radeon_link_encoder_connector(struct drm_device *dev)
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			radeon_encoder = to_radeon_encoder(encoder);
 			if (radeon_encoder->devices & radeon_connector->devices) {
-				drm_mode_connector_attach_encoder(connector, encoder);
+				drm_connector_attach_encoder(connector, encoder);
 				if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
 					radeon_encoder_add_backlight(radeon_encoder, connector);
 			}
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 48f4b273e316..0c7f228db6e3 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright 2009 VMware, Inc.
  *
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1907c950d76f..85c604d29235 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -7082,9 +7082,10 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 static void si_pcie_gen3_enable(struct radeon_device *rdev)
 {
 	struct pci_dev *root = rdev->pdev->bus->self;
+	enum pci_bus_speed speed_cap;
 	int bridge_pos, gpu_pos;
-	u32 speed_cntl, mask, current_data_rate;
-	int ret, i;
+	u32 speed_cntl, current_data_rate;
+	int i;
 	u16 tmp16;
 
 	if (pci_is_root_bus(rdev->pdev->bus))
@@ -7099,23 +7100,24 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret != 0)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN)
 		return;
 
-	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+	if ((speed_cap != PCIE_SPEED_8_0GT) &&
+	    (speed_cap != PCIE_SPEED_5_0GT))
 		return;
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
 		LC_CURRENT_DATA_RATE_SHIFT;
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		if (current_data_rate == 2) {
 			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
 			return;
 		}
 		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
-	} else if (mask & DRM_PCIE_SPEED_50) {
+	} else if (speed_cap == PCIE_SPEED_5_0GT) {
 		if (current_data_rate == 1) {
 			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
 			return;
@@ -7131,7 +7133,7 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!gpu_pos)
 		return;
 
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		/* re-try equalization if gen3 is not already enabled */
 		if (current_data_rate != 2) {
 			u16 bridge_cfg, gpu_cfg;
@@ -7219,9 +7221,9 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 
 	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
 	tmp16 &= ~0xf;
-	if (mask & DRM_PCIE_SPEED_80)
+	if (speed_cap == PCIE_SPEED_8_0GT)
 		tmp16 |= 3; /* gen3 */
-	else if (mask & DRM_PCIE_SPEED_50)
+	else if (speed_cap == PCIE_SPEED_5_0GT)
 		tmp16 |= 2; /* gen2 */
 	else
 		tmp16 |= 1; /* gen1 */
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index fea88078cf8e..8fb60b3af015 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -6899,8 +6899,9 @@ int si_dpm_init(struct radeon_device *rdev)
 	struct ni_power_info *ni_pi;
 	struct si_power_info *si_pi;
 	struct atom_clock_dividers dividers;
+	enum pci_bus_speed speed_cap;
+	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
-	u32 mask;
 
 	si_pi = kzalloc(sizeof(struct si_power_info), GFP_KERNEL);
 	if (si_pi == NULL)
@@ -6910,11 +6911,20 @@ int si_dpm_init(struct radeon_device *rdev)
 	eg_pi = &ni_pi->eg;
 	pi = &eg_pi->rv7xx;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		si_pi->sys_pcie_mask = 0;
-	else
-		si_pi->sys_pcie_mask = mask;
+	} else {
+		if (speed_cap == PCIE_SPEED_8_0GT)
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50 |
+				RADEON_PCIE_SPEED_80;
+		else if (speed_cap == PCIE_SPEED_5_0GT)
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50;
+		else
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25;
+	}
 	si_pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
 	si_pi->boot_pcie_gen = si_get_current_pcie_speed(rdev);
 
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 155ad840f3c5..4c39de3f4f0f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -353,7 +353,7 @@ static int rcar_lvds_attach(struct drm_bridge *bridge)
 
 	drm_connector_helper_add(connector, &rcar_lvds_conn_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		return ret;
 
@@ -434,8 +434,8 @@ static int rcar_lvds_parse_dt(struct rcar_lvds *lvds)
 			ret = -EPROBE_DEFER;
 	} else {
 		lvds->panel = of_drm_find_panel(remote);
-		if (!lvds->panel)
-			ret = -EPROBE_DEFER;
+		if (IS_ERR(lvds->panel))
+			ret = PTR_ERR(lvds->panel);
 	}
 
 done:
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index c6fbdcd87c16..8ad0d773dc33 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -275,7 +275,7 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector)
 		dp->sink_has_audio = drm_detect_monitor_audio(edid);
 		ret = drm_add_edid_modes(connector, edid);
 		if (ret)
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 	}
 	mutex_unlock(&dp->lock);
@@ -1062,7 +1062,7 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 
 	drm_connector_helper_add(connector, &cdn_dp_connector_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_ERROR("failed to attach connector and encoder\n");
 		goto err_free_connector;
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
index d53d5a09547f..662b6cb5d3f0 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
@@ -595,7 +595,7 @@ static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
-	if (dsi->panel)
+	if (!IS_ERR(dsi->panel))
 		return drm_panel_attach(dsi->panel, &dsi->connector);
 
 	return -EINVAL;
@@ -1129,7 +1129,7 @@ static int dw_mipi_dsi_register(struct drm_device *drm,
 			   &dw_mipi_dsi_atomic_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 88d0774c97bd..1c02b3e61299 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -565,7 +565,7 @@ static int inno_hdmi_connector_get_modes(struct drm_connector *connector)
 	if (edid) {
 		hdmi->hdmi_data.sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 		hdmi->hdmi_data.sink_has_audio = drm_detect_monitor_audio(edid);
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
@@ -634,7 +634,7 @@ static int inno_hdmi_register(struct drm_device *drm, struct inno_hdmi *hdmi)
 	drm_connector_init(drm, &hdmi->connector, &inno_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 
-	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
+	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index effecbed2d11..1359e5c773e4 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -243,18 +243,6 @@ static enum vop_data_format vop_convert_format(uint32_t format)
 	}
 }
 
-static bool is_yuv_support(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV16:
-	case DRM_FORMAT_NV24:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static uint16_t scl_vop_cal_scale(enum scale_mode mode, uint32_t src,
 				  uint32_t dst, bool is_horizontal,
 				  int vsu_mode, int *vskiplines)
@@ -298,7 +286,8 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 	uint16_t cbcr_ver_scl_mode = SCALE_NONE;
 	int hsub = drm_format_horz_chroma_subsampling(pixel_format);
 	int vsub = drm_format_vert_chroma_subsampling(pixel_format);
-	bool is_yuv = is_yuv_support(pixel_format);
+	const struct drm_format_info *info;
+	bool is_yuv = false;
 	uint16_t cbcr_src_w = src_w / hsub;
 	uint16_t cbcr_src_h = src_h / vsub;
 	uint16_t vsu_mode;
@@ -306,6 +295,11 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 	uint32_t val;
 	int vskiplines;
 
+	info = drm_format_info(pixel_format);
+
+	if (info->is_yuv)
+		is_yuv = true;
+
 	if (dst_w > 3840) {
 		DRM_DEV_ERROR(vop->dev, "Maximum dst width (3840) exceeded\n");
 		return;
@@ -680,7 +674,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 	 * Src.x1 can be odd when do clip, but yuv plane start point
 	 * need align with 2 pixel.
 	 */
-	if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2)) {
+	if (fb->format->is_yuv && ((state->src.x1 >> 16) % 2)) {
 		DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n");
 		return -EINVAL;
 	}
@@ -767,7 +761,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	VOP_WIN_SET(vop, win, format, format);
 	VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4));
 	VOP_WIN_SET(vop, win, yrgb_mst, dma_addr);
-	if (is_yuv_support(fb->format->format)) {
+	if (fb->format->is_yuv) {
 		int hsub = drm_format_horz_chroma_subsampling(fb->format->format);
 		int vsub = drm_format_vert_chroma_subsampling(fb->format->format);
 		int bpp = fb->format->cpp[1];
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index b3f6f524b402..456bd9f13bae 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -434,7 +434,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		drm_connector_helper_add(connector,
 					 &rockchip_lvds_connector_helper_funcs);
 
-		ret = drm_mode_connector_attach_encoder(connector, encoder);
+		ret = drm_connector_attach_encoder(connector, encoder);
 		if (ret < 0) {
 			DRM_DEV_ERROR(drm_dev->dev,
 				      "failed to attach encoder: %d\n", ret);
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 6a316701da73..3f2fc5e8242a 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -69,11 +69,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
  *
  * Initializes a scheduler runqueue.
  */
-static void drm_sched_rq_init(struct drm_sched_rq *rq)
+static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
+			      struct drm_sched_rq *rq)
 {
 	spin_lock_init(&rq->lock);
 	INIT_LIST_HEAD(&rq->entities);
 	rq->current_entity = NULL;
+	rq->sched = sched;
 }
 
 /**
@@ -160,26 +162,29 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
  * drm_sched_entity_init - Init a context entity used by scheduler when
  * submit to HW ring.
  *
- * @sched: scheduler instance
  * @entity: scheduler entity to init
- * @rq: the run queue this entity belongs
+ * @rq_list: the list of run queue on which jobs from this
+ *           entity can be submitted
+ * @num_rq_list: number of run queue in rq_list
  * @guilty: atomic_t set to 1 when a job on this queue
  *          is found to be guilty causing a timeout
  *
+ * Note: the rq_list should have atleast one element to schedule
+ *       the entity
+ *
  * Returns 0 on success or a negative error code on failure.
 */
-int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
-			  struct drm_sched_entity *entity,
-			  struct drm_sched_rq *rq,
+int drm_sched_entity_init(struct drm_sched_entity *entity,
+			  struct drm_sched_rq **rq_list,
+			  unsigned int num_rq_list,
 			  atomic_t *guilty)
 {
-	if (!(sched && entity && rq))
+	if (!(entity && rq_list && num_rq_list > 0 && rq_list[0]))
 		return -EINVAL;
 
 	memset(entity, 0, sizeof(struct drm_sched_entity));
 	INIT_LIST_HEAD(&entity->list);
-	entity->rq = rq;
-	entity->sched = sched;
+	entity->rq = rq_list[0];
 	entity->guilty = guilty;
 	entity->last_scheduled = NULL;
 
@@ -204,8 +209,8 @@ EXPORT_SYMBOL(drm_sched_entity_init);
 static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched,
 					    struct drm_sched_entity *entity)
 {
-	return entity->sched == sched &&
-		entity->rq != NULL;
+	return entity->rq != NULL &&
+		entity->rq->sched == sched;
 }
 
 /**
@@ -256,7 +261,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 
 
 /**
- * drm_sched_entity_do_release - Destroy a context entity
+ * drm_sched_entity_flush - Flush a context entity
  *
  * @sched: scheduler instance
  * @entity: scheduler entity
@@ -267,11 +272,12 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
  *
  * Returns the remaining time in jiffies left from the input timeout
  */
-long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity, long timeout)
+long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 {
+	struct drm_gpu_scheduler *sched;
 	long ret = timeout;
 
+	sched = entity->rq->sched;
 	if (!drm_sched_entity_is_initialized(sched, entity))
 		return ret;
 	/**
@@ -294,7 +300,7 @@ long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_sched_entity_do_release);
+EXPORT_SYMBOL(drm_sched_entity_flush);
 
 /**
  * drm_sched_entity_cleanup - Destroy a context entity
@@ -306,10 +312,11 @@ EXPORT_SYMBOL(drm_sched_entity_do_release);
  * entity and signals all jobs with an error code if the process was killed.
  *
  */
-void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity)
+void drm_sched_entity_fini(struct drm_sched_entity *entity)
 {
+	struct drm_gpu_scheduler *sched;
 
+	sched = entity->rq->sched;
 	drm_sched_entity_set_rq(entity, NULL);
 
 	/* Consumption of existing IBs wasn't completed. Forcefully
@@ -357,7 +364,7 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 	dma_fence_put(entity->last_scheduled);
 	entity->last_scheduled = NULL;
 }
-EXPORT_SYMBOL(drm_sched_entity_cleanup);
+EXPORT_SYMBOL(drm_sched_entity_fini);
 
 /**
  * drm_sched_entity_fini - Destroy a context entity
@@ -367,13 +374,12 @@ EXPORT_SYMBOL(drm_sched_entity_cleanup);
  *
  * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup()
  */
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
-				struct drm_sched_entity *entity)
+void drm_sched_entity_destroy(struct drm_sched_entity *entity)
 {
-	drm_sched_entity_do_release(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
-	drm_sched_entity_cleanup(sched, entity);
+	drm_sched_entity_flush(entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
+	drm_sched_entity_fini(entity);
 }
-EXPORT_SYMBOL(drm_sched_entity_fini);
+EXPORT_SYMBOL(drm_sched_entity_destroy);
 
 static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb)
 {
@@ -381,7 +387,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb
 		container_of(cb, struct drm_sched_entity, cb);
 	entity->dependency = NULL;
 	dma_fence_put(f);
-	drm_sched_wakeup(entity->sched);
+	drm_sched_wakeup(entity->rq->sched);
 }
 
 static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb *cb)
@@ -431,7 +437,7 @@ EXPORT_SYMBOL(drm_sched_entity_set_rq);
 bool drm_sched_dependency_optimized(struct dma_fence* fence,
 				    struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_fence *s_fence;
 
 	if (!fence || dma_fence_is_signaled(fence))
@@ -448,7 +454,7 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized);
 
 static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct dma_fence * fence = entity->dependency;
 	struct drm_sched_fence *s_fence;
 
@@ -493,7 +499,7 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 static struct drm_sched_job *
 drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_job *sched_job = to_drm_sched_job(
 						spsc_queue_peek(&entity->job_queue));
 
@@ -541,6 +547,11 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 	if (first) {
 		/* Add the entity to the run queue */
 		spin_lock(&entity->rq_lock);
+		if (!entity->rq) {
+			DRM_ERROR("Trying to push to a killed entity\n");
+			spin_unlock(&entity->rq_lock);
+			return;
+		}
 		drm_sched_rq_add_entity(entity->rq, entity);
 		spin_unlock(&entity->rq_lock);
 		drm_sched_wakeup(sched);
@@ -729,10 +740,11 @@ EXPORT_SYMBOL(drm_sched_job_recovery);
  * Returns 0 for success, negative error code otherwise.
  */
 int drm_sched_job_init(struct drm_sched_job *job,
-		       struct drm_gpu_scheduler *sched,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
+
 	job->sched = sched;
 	job->entity = entity;
 	job->s_priority = entity->rq - sched->sched_rq;
@@ -926,7 +938,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->timeout = timeout;
 	sched->hang_limit = hang_limit;
 	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
-		drm_sched_rq_init(&sched->sched_rq[i]);
+		drm_sched_rq_init(sched, &sched->sched_rq[i]);
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index 45d9c3affbea..d8d2dff9ea2f 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -161,7 +161,7 @@ struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity,
 		return NULL;
 
 	fence->owner = owner;
-	fence->sched = entity->sched;
+	fence->sched = entity->rq->sched;
 	spin_lock_init(&fence->lock);
 
 	seq = atomic_inc_return(&entity->fence_seq);
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index 40df8887fc17..fc66167b0641 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -675,7 +675,7 @@ int shmob_drm_connector_create(struct shmob_drm_device *sdev,
 	if (ret < 0)
 		goto err_cleanup;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		goto err_backlight;
 
diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 90c46b49c931..832fc43960ee 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -224,7 +224,7 @@ static int sti_bind(struct device *dev)
 
 	ret = sti_init(ddev);
 	if (ret)
-		goto err_drm_dev_unref;
+		goto err_drm_dev_put;
 
 	ret = component_bind_all(ddev->dev, ddev);
 	if (ret)
@@ -248,8 +248,8 @@ err_register:
 	drm_mode_config_cleanup(ddev);
 err_cleanup:
 	sti_cleanup(ddev);
-err_drm_dev_unref:
-	drm_dev_unref(ddev);
+err_drm_dev_put:
+	drm_dev_put(ddev);
 	return ret;
 }
 
@@ -259,7 +259,7 @@ static void sti_unbind(struct device *dev)
 
 	drm_dev_unregister(ddev);
 	sti_cleanup(ddev);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 }
 
 static const struct component_master_ops sti_ops = {
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index a5979cd25cc7..b08376b7611b 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -387,7 +387,9 @@ sti_dvo_connector_detect(struct drm_connector *connector, bool force)
 
 	if (!dvo->panel) {
 		dvo->panel = of_drm_find_panel(dvo->panel_node);
-		if (dvo->panel)
+		if (IS_ERR(dvo->panel))
+			dvo->panel = NULL;
+		else
 			drm_panel_attach(dvo->panel, connector);
 	}
 
@@ -484,7 +486,7 @@ static int sti_dvo_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 				 &sti_dvo_connector_helper_funcs);
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index 67bbdb49fffc..49438337f70d 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -709,7 +709,7 @@ static int sti_hda_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 			&sti_hda_connector_helper_funcs);
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 58f431102512..34cdc4644435 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -977,7 +977,7 @@ static int sti_hdmi_connector_get_modes(struct drm_connector *connector)
 	cec_notifier_set_phys_addr_from_edid(hdmi->notifier, edid);
 
 	count = drm_add_edid_modes(connector, edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	kfree(edid);
 	return count;
@@ -1290,7 +1290,7 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data)
 
 	hdmi->drm_connector = drm_connector;
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c
index 8698e08313e1..f2021b23554d 100644
--- a/drivers/gpu/drm/stm/drv.c
+++ b/drivers/gpu/drm/stm/drv.c
@@ -148,16 +148,16 @@ static int stm_drm_platform_probe(struct platform_device *pdev)
 
 	ret = drv_load(ddev);
 	if (ret)
-		goto err_unref;
+		goto err_put;
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
-		goto err_unref;
+		goto err_put;
 
 	return 0;
 
-err_unref:
-	drm_dev_unref(ddev);
+err_put:
+	drm_dev_put(ddev);
 
 	return ret;
 }
@@ -170,7 +170,7 @@ static int stm_drm_platform_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(ddev);
 	drv_unload(ddev);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index d997a6014d6c..808d9fb627e9 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -457,6 +457,14 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc,
 	int target_max = target + CLK_TOLERANCE_HZ;
 	int result;
 
+	result = clk_round_rate(ldev->pixel_clk, target);
+
+	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
+
+	/* Filter modes according to the max frequency supported by the pads */
+	if (result > ldev->caps.pad_max_freq_hz)
+		return MODE_CLOCK_HIGH;
+
 	/*
 	 * Accept all "preferred" modes:
 	 * - this is important for panels because panel clock tolerances are
@@ -468,10 +476,6 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc,
 	if (mode->type & DRM_MODE_TYPE_PREFERRED)
 		return MODE_OK;
 
-	result = clk_round_rate(ldev->pixel_clk, target);
-
-	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
-
 	/*
 	 * Filter modes according to the clock value, particularly useful for
 	 * hdmi modes that require precise pixel clocks.
@@ -991,11 +995,15 @@ static int ltdc_get_caps(struct drm_device *ddev)
 		 * does not work on 2nd layer.
 		 */
 		ldev->caps.non_alpha_only_l1 = true;
+		ldev->caps.pad_max_freq_hz = 90000000;
+		if (ldev->caps.hw_version == HWVER_10200)
+			ldev->caps.pad_max_freq_hz = 65000000;
 		break;
 	case HWVER_20101:
 		ldev->caps.reg_ofs = REG_OFS_4;
 		ldev->caps.pix_fmt_hw = ltdc_pix_fmt_a1;
 		ldev->caps.non_alpha_only_l1 = false;
+		ldev->caps.pad_max_freq_hz = 150000000;
 		break;
 	default:
 		return -ENODEV;
@@ -1074,8 +1082,11 @@ int ltdc_load(struct drm_device *ddev)
 		}
 	}
 
-	if (!IS_ERR(rstc))
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		usleep_range(10, 20);
 		reset_control_deassert(rstc);
+	}
 
 	/* Disable interrupts */
 	reg_clear(ldev->regs, LTDC_IER,
diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h
index 1e16d6afb0d2..d5afb8960867 100644
--- a/drivers/gpu/drm/stm/ltdc.h
+++ b/drivers/gpu/drm/stm/ltdc.h
@@ -18,6 +18,7 @@ struct ltdc_caps {
 	u32 bus_width;		/* bus width (32 or 64 bits) */
 	const u32 *pix_fmt_hw;	/* supported pixel formats */
 	bool non_alpha_only_l1; /* non-native no-alpha formats on layer 1 */
+	int pad_max_freq_hz;	/* max frequency supported by pad */
 };
 
 #define LTDC_MAX_LAYER	4
diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 156a865c3e6d..c2c042287c19 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -68,4 +68,11 @@ config DRM_SUN8I_MIXER
 	  graphics mixture and feed graphics to TCON, If M is
 	  selected the module will be called sun8i-mixer.
 
+config DRM_SUN8I_TCON_TOP
+	tristate
+	default DRM_SUN4I if DRM_SUN8I_MIXER!=n
+	help
+	  TCON TOP is responsible for configuring display pipeline for
+	  HTMI, TVE and LCD.
+
 endif
diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 14f420f1d4ae..0eb38ac8e86e 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -32,8 +32,12 @@ obj-$(CONFIG_DRM_SUN4I)		+= sun4i-tcon.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun4i_tv.o
 obj-$(CONFIG_DRM_SUN4I)		+= sun6i_drc.o
 
-obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o sun4i-frontend.o
+obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o
+ifdef CONFIG_DRM_SUN4I_BACKEND
+obj-$(CONFIG_DRM_SUN4I)		+= sun4i-frontend.o
+endif
 obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN6I_DSI)	+= sun6i-dsi.o
 obj-$(CONFIG_DRM_SUN8I_DW_HDMI)	+= sun8i-drm-hdmi.o
-obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o sun8i_tcon_top.o
+obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o
+obj-$(CONFIG_DRM_SUN8I_TCON_TOP) += sun8i_tcon_top.o
diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index de0a76dfa1a2..d7950b52a1fd 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -86,12 +86,6 @@ static inline bool sun4i_backend_format_is_packed_yuv422(uint32_t format)
 	}
 }
 
-static inline bool sun4i_backend_format_is_yuv(uint32_t format)
-{
-	return sun4i_backend_format_is_planar_yuv(format) ||
-		sun4i_backend_format_is_packed_yuv422(format);
-}
-
 static void sun4i_backend_apply_color_correction(struct sunxi_engine *engine)
 {
 	int i;
@@ -304,7 +298,7 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend,
 			   SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN,
 			   val);
 
-	if (sun4i_backend_format_is_yuv(fb->format->format))
+	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_format(backend, layer, plane);
 
 	ret = sun4i_backend_drm_format_to_layer(fb->format->format, &val);
@@ -384,7 +378,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	 */
 	paddr -= PHYS_OFFSET;
 
-	if (sun4i_backend_format_is_yuv(fb->format->format))
+	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_buffer(backend, fb, paddr);
 
 	/* Write the 32 lower bits of the address (in bits) */
@@ -502,7 +496,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 		if (fb->format->has_alpha || (plane_state->alpha != DRM_BLEND_ALPHA_OPAQUE))
 			num_alpha_planes++;
 
-		if (sun4i_backend_format_is_yuv(fb->format->format)) {
+		if (fb->format->is_yuv) {
 			DRM_DEBUG_DRIVER("Plane FB format is YUV\n");
 			num_yuv_planes++;
 		}
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 6ddf4eaccb40..dd19d674055c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -144,7 +144,7 @@ cleanup_mode_config:
 	drm_mode_config_cleanup(drm);
 	of_reserved_mem_device_release(dev);
 free_drm:
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 	return ret;
 }
 
@@ -157,7 +157,7 @@ static void sun4i_drv_unbind(struct device *dev)
 	sun4i_framebuffer_free(drm);
 	drm_mode_config_cleanup(drm);
 	of_reserved_mem_device_release(dev);
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops sun4i_drv_master_ops = {
@@ -216,7 +216,8 @@ static bool sun4i_drv_node_is_tcon_with_ch0(struct device_node *node)
 
 static bool sun4i_drv_node_is_tcon_top(struct device_node *node)
 {
-	return !!of_match_node(sun8i_tcon_top_of_table, node);
+	return IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
+		!!of_match_node(sun8i_tcon_top_of_table, node);
 }
 
 static int compare_of(struct device *dev, void *data)
@@ -417,6 +418,7 @@ static const struct of_device_id sun4i_drv_of_table[] = {
 	{ .compatible = "allwinner,sun8i-a33-display-engine" },
 	{ .compatible = "allwinner,sun8i-a83t-display-engine" },
 	{ .compatible = "allwinner,sun8i-h3-display-engine" },
+	{ .compatible = "allwinner,sun8i-r40-display-engine" },
 	{ .compatible = "allwinner,sun8i-v3s-display-engine" },
 	{ .compatible = "allwinner,sun9i-a80-display-engine" },
 	{ }
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index fa4bcd092eaf..061d2e0d9011 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -220,7 +220,7 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector)
 	DRM_DEBUG_DRIVER("Monitor is %s monitor\n",
 			 hdmi->hdmi_monitor ? "an HDMI" : "a DVI");
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_s_phys_addr_from_edid(hdmi->cec_adap, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
@@ -623,7 +623,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 	ret = cec_register_adapter(hdmi->cec_adap, dev);
 	if (ret < 0)
 		goto err_cleanup_connector;
-	drm_mode_connector_attach_encoder(&hdmi->connector, &hdmi->encoder);
+	drm_connector_attach_encoder(&hdmi->connector, &hdmi->encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index a69fe2e1f9d1..af7dcb6da351 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -149,7 +149,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 			goto err_cleanup_connector;
 		}
 
-		drm_mode_connector_attach_encoder(&lvds->connector,
+		drm_connector_attach_encoder(&lvds->connector,
 						  &lvds->encoder);
 
 		ret = drm_panel_attach(tcon->panel, &lvds->connector);
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index 96d21b07f8fc..bf068da6b12e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -215,7 +215,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 			goto err_cleanup_connector;
 		}
 
-		drm_mode_connector_attach_encoder(&rgb->connector,
+		drm_connector_attach_encoder(&rgb->connector,
 						  &rgb->encoder);
 
 		ret = drm_panel_attach(tcon->panel, &rgb->connector);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index aacc841d3dc6..3fb084f802e2 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -811,6 +811,7 @@ sun4i_tcon_find_engine_traverse(struct sun4i_drv *drv,
 	 * remote output id. If this for some reason can't be done, 0
 	 * is used as input port id.
 	 */
+	of_node_put(port);
 	port = of_graph_get_remote_port(ep);
 	if (!of_property_read_u32(port, "reg", &reg) && reg > 0)
 		reg -= 1;
diff --git a/drivers/gpu/drm/sun4i/sun4i_tv.c b/drivers/gpu/drm/sun4i/sun4i_tv.c
index b070d522ed8d..1a838d208211 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tv.c
@@ -623,7 +623,7 @@ static int sun4i_tv_bind(struct device *dev, struct device *master,
 	}
 	tv->connector.interlace_allowed = true;
 
-	drm_mode_connector_attach_encoder(&tv->connector, &tv->encoder);
+	drm_connector_attach_encoder(&tv->connector, &tv->encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index d4e7d16a2514..e3b34a345546 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -13,6 +13,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
+#include <linux/slab.h>
 
 #include <linux/phy/phy.h>
 
@@ -247,10 +248,8 @@ static u16 sun6i_dsi_crc_compute(u8 const *buffer, size_t len)
 	return crc_ccitt(0xffff, buffer, len);
 }
 
-static u16 sun6i_dsi_crc_repeat_compute(u8 pd, size_t len)
+static u16 sun6i_dsi_crc_repeat(u8 pd, u8 *buffer, size_t len)
 {
-	u8 buffer[len];
-
 	memset(buffer, pd, len);
 
 	return sun6i_dsi_crc_compute(buffer, len);
@@ -274,11 +273,11 @@ static u32 sun6i_dsi_build_blk0_pkt(u8 vc, u16 wc)
 					wc & 0xff, wc >> 8);
 }
 
-static u32 sun6i_dsi_build_blk1_pkt(u16 pd, size_t len)
+static u32 sun6i_dsi_build_blk1_pkt(u16 pd, u8 *buffer, size_t len)
 {
 	u32 val = SUN6I_DSI_BLK_PD(pd);
 
-	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat_compute(pd, len));
+	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat(pd, buffer, len));
 }
 
 static void sun6i_dsi_inst_abort(struct sun6i_dsi *dsi)
@@ -452,6 +451,54 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 	struct mipi_dsi_device *device = dsi->device;
 	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
 	u16 hbp, hfp, hsa, hblk, vblk;
+	size_t bytes;
+	u8 *buffer;
+
+	/* Do all timing calculations up front to allocate buffer space */
+
+	/*
+	 * A sync period is composed of a blanking packet (4 bytes +
+	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
+	 * minimal size is therefore 10 bytes
+	 */
+#define HSA_PACKET_OVERHEAD	10
+	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+
+	/*
+	 * The backporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HBP_PACKET_OVERHEAD	6
+	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+
+	/*
+	 * The frontporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HFP_PACKET_OVERHEAD	6
+	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+
+	/*
+	 * hblk seems to be the line + porches length.
+	 */
+	hblk = mode->htotal * Bpp - hsa;
+
+	/*
+	 * And I'm not entirely sure what vblk is about. The driver in
+	 * Allwinner BSP is using a rather convoluted calculation
+	 * there only for 4 lanes. However, using 0 (the !4 lanes
+	 * case) even with a 4 lanes screen seems to work...
+	 */
+	vblk = 0;
+
+	/* How many bytes do we need to send all payloads? */
+	bytes = max_t(size_t, max(max(hfp, hblk), max(hsa, hbp)), vblk);
+	buffer = kmalloc(bytes, GFP_KERNEL);
+	if (WARN_ON(!buffer))
+		return;
 
 	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, 0);
 
@@ -485,63 +532,37 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		     SUN6I_DSI_BASIC_SIZE1_VACT(mode->vdisplay) |
 		     SUN6I_DSI_BASIC_SIZE1_VT(mode->vtotal));
 
-	/*
-	 * A sync period is composed of a blanking packet (4 bytes +
-	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
-	 * minimal size is therefore 10 bytes
-	 */
-#define HSA_PACKET_OVERHEAD	10
-	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
-		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+	/* sync */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hsa));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hsa));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hsa));
 
-	/*
-	 * The backporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
-#define HBP_PACKET_OVERHEAD	6
-	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
-		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+	/* backporch */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hbp));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hbp));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hbp));
 
-	/*
-	 * The frontporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
-#define HFP_PACKET_OVERHEAD	6
-	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
-		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+	/* frontporch */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hfp));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hfp));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hfp));
 
-	/*
-	 * hblk seems to be the line + porches length.
-	 */
-	hblk = mode->htotal * Bpp - hsa;
+	/* hblk */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hblk));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hblk));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hblk));
 
-	/*
-	 * And I'm not entirely sure what vblk is about. The driver in
-	 * Allwinner BSP is using a rather convoluted calculation
-	 * there only for 4 lanes. However, using 0 (the !4 lanes
-	 * case) even with a 4 lanes screen seems to work...
-	 */
-	vblk = 0;
+	/* vblk */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, vblk));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, vblk));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, vblk));
+
+	kfree(buffer);
 }
 
 static int sun6i_dsi_start(struct sun6i_dsi *dsi,
@@ -812,8 +833,8 @@ static int sun6i_dsi_attach(struct mipi_dsi_host *host,
 
 	dsi->device = device;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
-	if (!dsi->panel)
-		return -EINVAL;
+	if (IS_ERR(dsi->panel))
+		return PTR_ERR(dsi->panel);
 
 	dev_info(host->dev, "Attached device %s\n", device->name);
 
@@ -920,7 +941,7 @@ static int sun6i_dsi_bind(struct device *dev, struct device *master,
 		goto err_cleanup_connector;
 	}
 
-	drm_mode_connector_attach_encoder(&dsi->connector, &dsi->encoder);
+	drm_connector_attach_encoder(&dsi->connector, &dsi->encoder);
 	drm_panel_attach(dsi->panel, &dsi->connector);
 
 	return 0;
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index 3459b9ec56c9..31875b636434 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -44,7 +44,8 @@ sun8i_dw_hdmi_mode_valid(struct drm_connector *connector,
 
 static bool sun8i_dw_hdmi_node_is_tcon_top(struct device_node *node)
 {
-	return !!of_match_node(sun8i_tcon_top_of_table, node);
+	return IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
+		!!of_match_node(sun8i_tcon_top_of_table, node);
 }
 
 static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
@@ -53,22 +54,14 @@ static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
 	struct device_node *port, *ep, *remote, *remote_port;
 	u32 crtcs = 0;
 
-	port = of_graph_get_port_by_id(node, 0);
-	if (!port)
-		return 0;
-
-	ep = of_get_next_available_child(port, NULL);
-	if (!ep)
-		return 0;
-
-	remote = of_graph_get_remote_port_parent(ep);
+	remote = of_graph_get_remote_node(node, 0, -1);
 	if (!remote)
 		return 0;
 
 	if (sun8i_dw_hdmi_node_is_tcon_top(remote)) {
 		port = of_graph_get_port_by_id(remote, 4);
 		if (!port)
-			return 0;
+			goto crtcs_exit;
 
 		for_each_child_of_node(port, ep) {
 			remote_port = of_graph_get_remote_port(ep);
@@ -81,6 +74,9 @@ static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
 		crtcs = drm_of_find_possible_crtcs(drm, node);
 	}
 
+crtcs_exit:
+	of_node_put(remote);
+
 	return crtcs;
 }
 
@@ -225,7 +221,7 @@ static const struct of_device_id sun8i_dw_hdmi_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, sun8i_dw_hdmi_dt_ids);
 
-struct platform_driver sun8i_dw_hdmi_pltfm_driver = {
+static struct platform_driver sun8i_dw_hdmi_pltfm_driver = {
 	.probe  = sun8i_dw_hdmi_probe,
 	.remove = sun8i_dw_hdmi_remove,
 	.driver = {
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index ee8febb25903..fc3713608f78 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -21,8 +21,9 @@
 
 #include <linux/component.h>
 #include <linux/dma-mapping.h>
-#include <linux/reset.h>
 #include <linux/of_device.h>
+#include <linux/of_graph.h>
+#include <linux/reset.h>
 
 #include "sun4i_drv.h"
 #include "sun8i_mixer.h"
@@ -322,6 +323,42 @@ static struct regmap_config sun8i_mixer_regmap_config = {
 	.max_register	= 0xbfffc, /* guessed */
 };
 
+static int sun8i_mixer_of_get_id(struct device_node *node)
+{
+	struct device_node *port, *ep;
+	int ret = -EINVAL;
+
+	/* output is port 1 */
+	port = of_graph_get_port_by_id(node, 1);
+	if (!port)
+		return -EINVAL;
+
+	/* try to find downstream endpoint */
+	for_each_available_child_of_node(port, ep) {
+		struct device_node *remote;
+		u32 reg;
+
+		remote = of_graph_get_remote_endpoint(ep);
+		if (!remote)
+			continue;
+
+		ret = of_property_read_u32(remote, "reg", &reg);
+		if (!ret) {
+			of_node_put(remote);
+			of_node_put(ep);
+			of_node_put(port);
+
+			return reg;
+		}
+
+		of_node_put(remote);
+	}
+
+	of_node_put(port);
+
+	return ret;
+}
+
 static int sun8i_mixer_bind(struct device *dev, struct device *master,
 			      void *data)
 {
@@ -353,8 +390,16 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	dev_set_drvdata(dev, mixer);
 	mixer->engine.ops = &sun8i_engine_ops;
 	mixer->engine.node = dev->of_node;
-	/* The ID of the mixer currently doesn't matter */
-	mixer->engine.id = -1;
+
+	/*
+	 * While this function can fail, we shouldn't do anything
+	 * if this happens. Some early DE2 DT entries don't provide
+	 * mixer id but work nevertheless because matching between
+	 * TCON and mixer is done by comparing node pointers (old
+	 * way) instead comparing ids. If this function fails and
+	 * id is needed, it will fail during id matching anyway.
+	 */
+	mixer->engine.id = sun8i_mixer_of_get_id(dev->of_node);
 
 	mixer->cfg = of_device_get_match_data(dev);
 	if (!mixer->cfg)
@@ -432,14 +477,14 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_ATTR_FCOLOR(0),
 		     SUN8I_MIXER_BLEND_COLOR_BLACK);
 
-	/* Fixed zpos for now */
-	regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_ROUTE, 0x43210);
-
 	plane_cnt = mixer->cfg->vi_num + mixer->cfg->ui_num;
 	for (i = 0; i < plane_cnt; i++)
 		regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_MODE(i),
 			     SUN8I_MIXER_BLEND_MODE_DEF);
 
+	regmap_update_bits(mixer->engine.regs, SUN8I_MIXER_BLEND_PIPE_CTL,
+			   SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK, 0);
+
 	return 0;
 
 err_disable_bus_clk:
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index f34e70c42adf..406c42e752d7 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -44,6 +44,7 @@
 #define SUN8I_MIXER_BLEND_CK_MIN(x)		(0x10e0 + 0x04 * (x))
 #define SUN8I_MIXER_BLEND_OUTCTL		0x10fc
 
+#define SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK	GENMASK(12, 8)
 #define SUN8I_MIXER_BLEND_PIPE_CTL_EN(pipe)	BIT(8 + pipe)
 #define SUN8I_MIXER_BLEND_PIPE_CTL_FC_EN(pipe)	BIT(pipe)
 /* colors are always in AARRGGBB format */
@@ -51,6 +52,9 @@
 /* The following numbers are some still unknown magic numbers */
 #define SUN8I_MIXER_BLEND_MODE_DEF		0x03010301
 
+#define SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(n)	(0xf << ((n) << 2))
+#define SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(n)	((n) << 2)
+
 #define SUN8I_MIXER_BLEND_OUTCTL_INTERLACED	BIT(1)
 
 #define SUN8I_MIXER_FBFMT_ARGB8888	0
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index 8da0460e0028..55fe398d8290 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -14,45 +14,95 @@
 
 #include "sun8i_tcon_top.h"
 
-static int sun8i_tcon_top_get_connected_ep_id(struct device_node *node,
-					      int port_id)
+static bool sun8i_tcon_top_node_is_tcon_top(struct device_node *node)
 {
-	struct device_node *ep, *remote, *port;
-	struct of_endpoint endpoint;
+	return !!of_match_node(sun8i_tcon_top_of_table, node);
+}
 
-	port = of_graph_get_port_by_id(node, port_id);
-	if (!port)
-		return -ENOENT;
+int sun8i_tcon_top_set_hdmi_src(struct device *dev, int tcon)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 val;
 
-	for_each_available_child_of_node(port, ep) {
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote)
-			continue;
+	if (!sun8i_tcon_top_node_is_tcon_top(dev->of_node)) {
+		dev_err(dev, "Device is not TCON TOP!\n");
+		return -EINVAL;
+	}
 
-		if (of_device_is_available(remote)) {
-			of_graph_parse_endpoint(ep, &endpoint);
+	if (tcon < 2 || tcon > 3) {
+		dev_err(dev, "TCON index must be 2 or 3!\n");
+		return -EINVAL;
+	}
 
-			of_node_put(remote);
+	spin_lock_irqsave(&tcon_top->reg_lock, flags);
 
-			return endpoint.id;
-		}
+	val = readl(tcon_top->regs + TCON_TOP_GATE_SRC_REG);
+	val &= ~TCON_TOP_HDMI_SRC_MSK;
+	val |= FIELD_PREP(TCON_TOP_HDMI_SRC_MSK, tcon - 1);
+	writel(val, tcon_top->regs + TCON_TOP_GATE_SRC_REG);
+
+	spin_unlock_irqrestore(&tcon_top->reg_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(sun8i_tcon_top_set_hdmi_src);
+
+int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 reg;
+
+	if (!sun8i_tcon_top_node_is_tcon_top(dev->of_node)) {
+		dev_err(dev, "Device is not TCON TOP!\n");
+		return -EINVAL;
+	}
 
-		of_node_put(remote);
+	if (mixer > 1) {
+		dev_err(dev, "Mixer index is too high!\n");
+		return -EINVAL;
 	}
 
-	return -ENOENT;
+	if (tcon > 3) {
+		dev_err(dev, "TCON index is too high!\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&tcon_top->reg_lock, flags);
+
+	reg = readl(tcon_top->regs + TCON_TOP_PORT_SEL_REG);
+	if (mixer == 0) {
+		reg &= ~TCON_TOP_PORT_DE0_MSK;
+		reg |= FIELD_PREP(TCON_TOP_PORT_DE0_MSK, tcon);
+	} else {
+		reg &= ~TCON_TOP_PORT_DE1_MSK;
+		reg |= FIELD_PREP(TCON_TOP_PORT_DE1_MSK, tcon);
+	}
+	writel(reg, tcon_top->regs + TCON_TOP_PORT_SEL_REG);
+
+	spin_unlock_irqrestore(&tcon_top->reg_lock, flags);
+
+	return 0;
 }
+EXPORT_SYMBOL(sun8i_tcon_top_de_config);
+
 
 static struct clk_hw *sun8i_tcon_top_register_gate(struct device *dev,
-						   struct clk *parent,
+						   const char *parent,
 						   void __iomem *regs,
 						   spinlock_t *lock,
 						   u8 bit, int name_index)
 {
 	const char *clk_name, *parent_name;
-	int ret;
+	int ret, index;
+
+	index = of_property_match_string(dev->of_node, "clock-names", parent);
+	if (index < 0)
+		return ERR_PTR(index);
+
+	parent_name = of_clk_get_parent_name(dev->of_node, index);
 
-	parent_name = __clk_get_name(parent);
 	ret = of_property_read_string_index(dev->of_node,
 					    "clock-output-names", name_index,
 					    &clk_name);
@@ -69,14 +119,11 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 			       void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	struct clk *dsi, *tcon_tv0, *tcon_tv1, *tve0, *tve1;
 	struct clk_hw_onecell_data *clk_data;
 	struct sun8i_tcon_top *tcon_top;
-	bool mixer0_unused = false;
 	struct resource *res;
 	void __iomem *regs;
-	int ret, i, id;
-	u32 val;
+	int ret, i;
 
 	tcon_top = devm_kzalloc(dev, sizeof(*tcon_top), GFP_KERNEL);
 	if (!tcon_top)
@@ -103,38 +150,9 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 		return PTR_ERR(tcon_top->bus);
 	}
 
-	dsi = devm_clk_get(dev, "dsi");
-	if (IS_ERR(dsi)) {
-		dev_err(dev, "Couldn't get the dsi clock\n");
-		return PTR_ERR(dsi);
-	}
-
-	tcon_tv0 = devm_clk_get(dev, "tcon-tv0");
-	if (IS_ERR(tcon_tv0)) {
-		dev_err(dev, "Couldn't get the tcon-tv0 clock\n");
-		return PTR_ERR(tcon_tv0);
-	}
-
-	tcon_tv1 = devm_clk_get(dev, "tcon-tv1");
-	if (IS_ERR(tcon_tv1)) {
-		dev_err(dev, "Couldn't get the tcon-tv1 clock\n");
-		return PTR_ERR(tcon_tv1);
-	}
-
-	tve0 = devm_clk_get(dev, "tve0");
-	if (IS_ERR(tve0)) {
-		dev_err(dev, "Couldn't get the tve0 clock\n");
-		return PTR_ERR(tve0);
-	}
-
-	tve1 = devm_clk_get(dev, "tve1");
-	if (IS_ERR(tve1)) {
-		dev_err(dev, "Couldn't get the tve1 clock\n");
-		return PTR_ERR(tve1);
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(dev, res);
+	tcon_top->regs = regs;
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
@@ -150,50 +168,6 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 		goto err_assert_reset;
 	}
 
-	val = 0;
-
-	/* check if HDMI mux output is connected */
-	if (sun8i_tcon_top_get_connected_ep_id(dev->of_node, 5) >= 0) {
-		/* find HDMI input endpoint id, if it is connected at all*/
-		id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 4);
-		if (id >= 0)
-			val = FIELD_PREP(TCON_TOP_HDMI_SRC_MSK, id + 1);
-		else
-			DRM_DEBUG_DRIVER("TCON TOP HDMI input is not connected\n");
-	} else {
-		DRM_DEBUG_DRIVER("TCON TOP HDMI output is not connected\n");
-	}
-
-	writel(val, regs + TCON_TOP_GATE_SRC_REG);
-
-	val = 0;
-
-	/* process mixer0 mux output */
-	id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 1);
-	if (id >= 0) {
-		val = FIELD_PREP(TCON_TOP_PORT_DE0_MSK, id);
-	} else {
-		DRM_DEBUG_DRIVER("TCON TOP mixer0 output is not connected\n");
-		mixer0_unused = true;
-	}
-
-	/* process mixer1 mux output */
-	id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 3);
-	if (id >= 0) {
-		val |= FIELD_PREP(TCON_TOP_PORT_DE1_MSK, id);
-
-		/*
-		 * mixer0 mux has priority over mixer1 mux. We have to
-		 * make sure mixer0 doesn't overtake TCON from mixer1.
-		 */
-		if (mixer0_unused && id == 0)
-			val |= FIELD_PREP(TCON_TOP_PORT_DE0_MSK, 1);
-	} else {
-		DRM_DEBUG_DRIVER("TCON TOP mixer1 output is not connected\n");
-	}
-
-	writel(val, regs + TCON_TOP_PORT_SEL_REG);
-
 	/*
 	 * TCON TOP has two muxes, which select parent clock for each TCON TV
 	 * channel clock. Parent could be either TCON TV or TVE clock. For now
@@ -203,17 +177,17 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 	 * to TVE clock parent.
 	 */
 	clk_data->hws[CLK_TCON_TOP_TV0] =
-		sun8i_tcon_top_register_gate(dev, tcon_tv0, regs,
+		sun8i_tcon_top_register_gate(dev, "tcon-tv0", regs,
 					     &tcon_top->reg_lock,
 					     TCON_TOP_TCON_TV0_GATE, 0);
 
 	clk_data->hws[CLK_TCON_TOP_TV1] =
-		sun8i_tcon_top_register_gate(dev, tcon_tv1, regs,
+		sun8i_tcon_top_register_gate(dev, "tcon-tv1", regs,
 					     &tcon_top->reg_lock,
 					     TCON_TOP_TCON_TV1_GATE, 1);
 
 	clk_data->hws[CLK_TCON_TOP_DSI] =
-		sun8i_tcon_top_register_gate(dev, dsi, regs,
+		sun8i_tcon_top_register_gate(dev, "dsi", regs,
 					     &tcon_top->reg_lock,
 					     TCON_TOP_TCON_DSI_GATE, 2);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.h b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
index 39838bbfeaee..0390584a330e 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
@@ -26,6 +26,7 @@
 struct sun8i_tcon_top {
 	struct clk			*bus;
 	struct clk_hw_onecell_data	*clk_data;
+	void __iomem			*regs;
 	struct reset_control		*rst;
 
 	/*
@@ -37,4 +38,7 @@ struct sun8i_tcon_top {
 
 extern const struct of_device_id sun8i_tcon_top_of_table[];
 
+int sun8i_tcon_top_set_hdmi_src(struct device *dev, int tcon);
+int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon);
+
 #endif /* _SUN8I_TCON_TOP_H_ */
diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
index 9a540330cb79..28c15c6ef1ef 100644
--- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
@@ -27,7 +27,8 @@
 #include "sun8i_ui_scaler.h"
 
 static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable)
+				  int overlay, bool enable, unsigned int zpos,
+				  unsigned int old_zpos)
 {
 	u32 val;
 
@@ -43,18 +44,36 @@ static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR_EN, val);
 
-	if (enable)
-		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel);
-	else
-		val = 0;
+	if (!enable || zpos != old_zpos) {
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL,
+				   SUN8I_MIXER_BLEND_PIPE_CTL_EN(old_zpos),
+				   0);
 
-	regmap_update_bits(mixer->engine.regs,
-			   SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel), val);
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(old_zpos),
+				   0);
+	}
+
+	if (enable) {
+		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL, val, val);
+
+		val = channel << SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(zpos),
+				   val);
+	}
 }
 
 static int sun8i_ui_layer_update_coord(struct sun8i_mixer *mixer, int channel,
-				       int overlay, struct drm_plane *plane)
+				       int overlay, struct drm_plane *plane,
+				       unsigned int zpos)
 {
 	struct drm_plane_state *state = plane->state;
 	u32 src_w, src_h, dst_w, dst_h;
@@ -137,10 +156,10 @@ static int sun8i_ui_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 			 state->dst.x1, state->dst.y1);
 	DRM_DEBUG_DRIVER("Layer destination size W: %d H: %d\n", dst_w, dst_h);
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_COORD(channel),
+		     SUN8I_MIXER_BLEND_ATTR_COORD(zpos),
 		     SUN8I_MIXER_COORD(state->dst.x1, state->dst.y1));
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_INSIZE(channel),
+		     SUN8I_MIXER_BLEND_ATTR_INSIZE(zpos),
 		     outsize);
 
 	return 0;
@@ -236,30 +255,35 @@ static void sun8i_ui_layer_atomic_disable(struct drm_plane *plane,
 					  struct drm_plane_state *old_state)
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false, 0,
+			      old_zpos);
 }
 
 static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
 					 struct drm_plane_state *old_state)
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
+	unsigned int zpos = plane->state->normalized_zpos;
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_ui_layer_enable(mixer, layer->channel,
-				      layer->overlay, false);
+				      layer->overlay, false, 0, old_zpos);
 		return;
 	}
 
 	sun8i_ui_layer_update_coord(mixer, layer->channel,
-				    layer->overlay, plane);
+				    layer->overlay, plane, zpos);
 	sun8i_ui_layer_update_formats(mixer, layer->channel,
 				      layer->overlay, plane);
 	sun8i_ui_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, true);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay,
+			      true, zpos, old_zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_ui_layer_helper_funcs = {
@@ -307,6 +331,7 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm,
 	enum drm_plane_type type = DRM_PLANE_TYPE_OVERLAY;
 	int channel = mixer->cfg->vi_num + index;
 	struct sun8i_ui_layer *layer;
+	unsigned int plane_cnt;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
@@ -327,8 +352,10 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm,
 		return ERR_PTR(ret);
 	}
 
-	/* fixed zpos for now */
-	ret = drm_plane_create_zpos_immutable_property(&layer->plane, channel);
+	plane_cnt = mixer->cfg->ui_num + mixer->cfg->vi_num;
+
+	ret = drm_plane_create_zpos_property(&layer->plane, channel,
+					     0, plane_cnt - 1);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't add zpos property\n");
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 5877f8ef5895..f4fe97813f94 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -21,7 +21,8 @@
 #include "sun8i_vi_scaler.h"
 
 static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable)
+				  int overlay, bool enable, unsigned int zpos,
+				  unsigned int old_zpos)
 {
 	u32 val;
 
@@ -37,18 +38,36 @@ static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR_EN, val);
 
-	if (enable)
-		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel);
-	else
-		val = 0;
+	if (!enable || zpos != old_zpos) {
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL,
+				   SUN8I_MIXER_BLEND_PIPE_CTL_EN(old_zpos),
+				   0);
 
-	regmap_update_bits(mixer->engine.regs,
-			   SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel), val);
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(old_zpos),
+				   0);
+	}
+
+	if (enable) {
+		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL, val, val);
+
+		val = channel << SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(zpos),
+				   val);
+	}
 }
 
 static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
-				       int overlay, struct drm_plane *plane)
+				       int overlay, struct drm_plane *plane,
+				       unsigned int zpos)
 {
 	struct drm_plane_state *state = plane->state;
 	const struct drm_format_info *format = state->fb->format;
@@ -130,10 +149,10 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 			 state->dst.x1, state->dst.y1);
 	DRM_DEBUG_DRIVER("Layer destination size W: %d H: %d\n", dst_w, dst_h);
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_COORD(channel),
+		     SUN8I_MIXER_BLEND_ATTR_COORD(zpos),
 		     SUN8I_MIXER_COORD(state->dst.x1, state->dst.y1));
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_INSIZE(channel),
+		     SUN8I_MIXER_BLEND_ATTR_INSIZE(zpos),
 		     outsize);
 
 	return 0;
@@ -264,30 +283,35 @@ static void sun8i_vi_layer_atomic_disable(struct drm_plane *plane,
 					  struct drm_plane_state *old_state)
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false, 0,
+			      old_zpos);
 }
 
 static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
 					 struct drm_plane_state *old_state)
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
+	unsigned int zpos = plane->state->normalized_zpos;
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_vi_layer_enable(mixer, layer->channel,
-				      layer->overlay, false);
+				      layer->overlay, false, 0, old_zpos);
 		return;
 	}
 
 	sun8i_vi_layer_update_coord(mixer, layer->channel,
-				    layer->overlay, plane);
+				    layer->overlay, plane, zpos);
 	sun8i_vi_layer_update_formats(mixer, layer->channel,
 				      layer->overlay, plane);
 	sun8i_vi_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, true);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay,
+			      true, zpos, old_zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_vi_layer_helper_funcs = {
@@ -351,6 +375,7 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 					       int index)
 {
 	struct sun8i_vi_layer *layer;
+	unsigned int plane_cnt;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
@@ -368,8 +393,10 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 		return ERR_PTR(ret);
 	}
 
-	/* fixed zpos for now */
-	ret = drm_plane_create_zpos_immutable_property(&layer->plane, index);
+	plane_cnt = mixer->cfg->ui_num + mixer->cfg->vi_num;
+
+	ret = drm_plane_create_zpos_property(&layer->plane, index,
+					     0, plane_cnt - 1);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't add zpos property\n");
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 776c1513e582..a2bd5876c633 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -398,7 +398,7 @@ int tegra_drm_submit(struct tegra_drm_context *context,
 		 * unaligned offset is malformed and cause commands stream
 		 * corruption on the buffer address relocation.
 		 */
-		if (offset & 3 || offset >= obj->gem.size) {
+		if (offset & 3 || offset > obj->gem.size) {
 			err = -EINVAL;
 			goto fail;
 		}
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 87c5d89bc9ba..ee6ca8fa1c65 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -1052,7 +1052,7 @@ static int tegra_dsi_init(struct host1x_client *client)
 		drm_encoder_helper_add(&dsi->output.encoder,
 				       &tegra_dsi_encoder_helper_funcs);
 
-		drm_mode_connector_attach_encoder(&dsi->output.connector,
+		drm_connector_attach_encoder(&dsi->output.connector,
 						  &dsi->output.encoder);
 		drm_connector_register(&dsi->output.connector);
 
@@ -1411,6 +1411,9 @@ static int tegra_dsi_host_attach(struct mipi_dsi_host *host,
 		struct tegra_output *output = &dsi->output;
 
 		output->panel = of_drm_find_panel(device->dev.of_node);
+		if (IS_ERR(output->panel))
+			output->panel = NULL;
+
 		if (output->panel && output->connector.dev) {
 			drm_panel_attach(output->panel, &output->connector);
 			drm_helper_hpd_irq_event(output->connector.dev);
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 784739a9f497..0082468f703c 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1488,7 +1488,7 @@ static int tegra_hdmi_init(struct host1x_client *client)
 	drm_encoder_helper_add(&hdmi->output.encoder,
 			       &tegra_hdmi_encoder_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&hdmi->output.connector,
+	drm_connector_attach_encoder(&hdmi->output.connector,
 					  &hdmi->output.encoder);
 	drm_connector_register(&hdmi->output.connector);
 
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index ffe34bd0bb9d..c662efc7e413 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -37,7 +37,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector)
 		edid = drm_get_edid(connector, output->ddc);
 
 	cec_notifier_set_phys_addr_from_edid(output->notifier, edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		err = drm_add_edid_modes(connector, edid);
@@ -110,8 +110,8 @@ int tegra_output_probe(struct tegra_output *output)
 	panel = of_parse_phandle(output->of_node, "nvidia,panel", 0);
 	if (panel) {
 		output->panel = of_drm_find_panel(panel);
-		if (!output->panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(output->panel))
+			return PTR_ERR(output->panel);
 
 		of_node_put(panel);
 	}
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 78ec5193741d..28a78d3120bc 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -289,7 +289,7 @@ int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc)
 	drm_encoder_helper_add(&output->encoder,
 			       &tegra_rgb_encoder_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&output->connector,
+	drm_connector_attach_encoder(&output->connector,
 					  &output->encoder);
 	drm_connector_register(&output->connector);
 
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index 7d2a955fc515..d7fe9f15def1 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -2622,7 +2622,7 @@ static int tegra_sor_init(struct host1x_client *client)
 			 encoder, NULL);
 	drm_encoder_helper_add(&sor->output.encoder, helpers);
 
-	drm_mode_connector_attach_encoder(&sor->output.connector,
+	drm_connector_attach_encoder(&sor->output.connector,
 					  &sor->output.encoder);
 	drm_connector_register(&sor->output.connector);
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index b8a5e4ed22e6..0fb300d41a09 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -378,7 +378,7 @@ static int tilcdc_init(struct drm_driver *ddrv, struct device *dev)
 	if (!priv->external_connector &&
 	    ((priv->num_encoders == 0) || (priv->num_connectors == 0))) {
 		dev_err(dev, "no encoders/connectors found\n");
-		ret = -ENXIO;
+		ret = -EPROBE_DEFER;
 		goto init_failed;
 	}
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_external.c b/drivers/gpu/drm/tilcdc/tilcdc_external.c
index d651bdd6597e..b4eaf9bc87f8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_external.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_external.c
@@ -103,12 +103,11 @@ struct drm_connector *tilcdc_encoder_find_connector(struct drm_device *ddev,
 						    struct drm_encoder *encoder)
 {
 	struct drm_connector *connector;
-	int i;
 
-	list_for_each_entry(connector, &ddev->mode_config.connector_list, head)
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++)
-			if (connector->encoder_ids[i] == encoder->base.id)
-				return connector;
+	list_for_each_entry(connector, &ddev->mode_config.connector_list, head) {
+		if (drm_connector_has_possible_encoder(connector, encoder))
+			return connector;
+	}
 
 	dev_err(ddev->dev, "No connector found for %s encoder (id %d)\n",
 		encoder->name, encoder->base.id);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index d616d64a6725..a1acab39d87f 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -223,7 +223,7 @@ static struct drm_connector *panel_connector_create(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index c45cabb38db0..daebf1aa6b0a 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -173,7 +173,7 @@ static int tfp410_connector_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, tfp410_connector->mod->i2c);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		ret = drm_add_edid_modes(connector, edid);
@@ -240,7 +240,7 @@ static struct drm_connector *tfp410_connector_create(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/tinydrm/Kconfig b/drivers/gpu/drm/tinydrm/Kconfig
index 7a8008b0783f..16f4b5c91f1b 100644
--- a/drivers/gpu/drm/tinydrm/Kconfig
+++ b/drivers/gpu/drm/tinydrm/Kconfig
@@ -23,6 +23,7 @@ config TINYDRM_ILI9225
 config TINYDRM_ILI9341
 	tristate "DRM support for ILI9341 display panels"
 	depends on DRM_TINYDRM && SPI
+	depends on BACKLIGHT_CLASS_DEVICE
 	select TINYDRM_MIPI_DBI
 	help
 	  DRM driver for the following Ilitek ILI9341 panels:
diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
index 24a33bf862fa..19c7f70adfa5 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
@@ -204,7 +204,7 @@ static int tinydrm_register(struct tinydrm_device *tdev)
 	if (ret)
 		return ret;
 
-	ret = drm_fb_cma_fbdev_init_with_funcs(drm, 0, 0, tdev->fb_funcs);
+	ret = drm_fbdev_generic_setup(drm, 0);
 	if (ret)
 		DRM_ERROR("Failed to initialize fbdev: %d\n", ret);
 
@@ -214,7 +214,6 @@ static int tinydrm_register(struct tinydrm_device *tdev)
 static void tinydrm_unregister(struct tinydrm_device *tdev)
 {
 	drm_atomic_helper_shutdown(tdev->drm);
-	drm_fb_cma_fbdev_fini(tdev->drm);
 	drm_dev_unregister(tdev->drm);
 }
 
diff --git a/drivers/gpu/drm/tinydrm/ili9225.c b/drivers/gpu/drm/tinydrm/ili9225.c
index 841c69aba059..455fefe012f5 100644
--- a/drivers/gpu/drm/tinydrm/ili9225.c
+++ b/drivers/gpu/drm/tinydrm/ili9225.c
@@ -368,7 +368,6 @@ static struct drm_driver ili9225_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &ili9225_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.name			= "ili9225",
 	.desc			= "Ilitek ILI9225",
 	.date			= "20171106",
diff --git a/drivers/gpu/drm/tinydrm/ili9341.c b/drivers/gpu/drm/tinydrm/ili9341.c
index 8864dcde6edc..6701037749a7 100644
--- a/drivers/gpu/drm/tinydrm/ili9341.c
+++ b/drivers/gpu/drm/tinydrm/ili9341.c
@@ -145,7 +145,6 @@ static struct drm_driver ili9341_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC,
 	.fops			= &ili9341_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "ili9341",
 	.desc			= "Ilitek ILI9341",
diff --git a/drivers/gpu/drm/tinydrm/mi0283qt.c b/drivers/gpu/drm/tinydrm/mi0283qt.c
index 015d03f2acba..d7bb4c5e6657 100644
--- a/drivers/gpu/drm/tinydrm/mi0283qt.c
+++ b/drivers/gpu/drm/tinydrm/mi0283qt.c
@@ -154,7 +154,6 @@ static struct drm_driver mi0283qt_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &mi0283qt_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "mi0283qt",
 	.desc			= "Multi-Inno MI0283QT",
diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c
index 4d1fb31a781f..cb3441e51d5f 100644
--- a/drivers/gpu/drm/tinydrm/mipi-dbi.c
+++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c
@@ -260,6 +260,8 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = {
 /**
  * mipi_dbi_enable_flush - MIPI DBI enable helper
  * @mipi: MIPI DBI structure
+ * @crtc_state: CRTC state
+ * @plane_state: Plane state
  *
  * This function sets &mipi_dbi->enabled, flushes the whole framebuffer and
  * enables the backlight. Drivers can use this in their
diff --git a/drivers/gpu/drm/tinydrm/st7586.c b/drivers/gpu/drm/tinydrm/st7586.c
index 5c29e3803ecb..2fcbc3067d71 100644
--- a/drivers/gpu/drm/tinydrm/st7586.c
+++ b/drivers/gpu/drm/tinydrm/st7586.c
@@ -304,7 +304,6 @@ static struct drm_driver st7586_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &st7586_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "st7586",
 	.desc			= "Sitronix ST7586",
diff --git a/drivers/gpu/drm/tinydrm/st7735r.c b/drivers/gpu/drm/tinydrm/st7735r.c
index 6c7b15c9da4f..3081bc57c116 100644
--- a/drivers/gpu/drm/tinydrm/st7735r.c
+++ b/drivers/gpu/drm/tinydrm/st7735r.c
@@ -120,7 +120,6 @@ static struct drm_driver st7735r_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &st7735r_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "st7735r",
 	.desc			= "Sitronix ST7735R",
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 5d8688e522d1..7c484729f9b2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -287,12 +287,9 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	if (ret) {
 		if (bdev->driver->move_notify) {
-			struct ttm_mem_reg tmp_mem = *mem;
-			*mem = bo->mem;
-			bo->mem = tmp_mem;
+			swap(*mem, bo->mem);
 			bdev->driver->move_notify(bo, false, mem);
-			bo->mem = *mem;
-			*mem = tmp_mem;
+			swap(*mem, bo->mem);
 		}
 
 		goto out_err;
@@ -590,12 +587,18 @@ static void ttm_bo_release(struct kref *kref)
 	kref_put(&bo->list_kref, ttm_bo_release_list);
 }
 
+void ttm_bo_put(struct ttm_buffer_object *bo)
+{
+	kref_put(&bo->kref, ttm_bo_release);
+}
+EXPORT_SYMBOL(ttm_bo_put);
+
 void ttm_bo_unref(struct ttm_buffer_object **p_bo)
 {
 	struct ttm_buffer_object *bo = *p_bo;
 
 	*p_bo = NULL;
-	kref_put(&bo->kref, ttm_bo_release);
+	ttm_bo_put(bo);
 }
 EXPORT_SYMBOL(ttm_bo_unref);
 
@@ -1201,7 +1204,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		if (!resv)
 			ttm_bo_unreserve(bo);
 
-		ttm_bo_unref(&bo);
+		ttm_bo_put(bo);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index f2c167702eef..046a6dda690a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -463,7 +463,7 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
 	struct ttm_transfer_obj *fbo;
 
 	fbo = container_of(bo, struct ttm_transfer_obj, base);
-	ttm_bo_unref(&fbo->bo);
+	ttm_bo_put(fbo->bo);
 	kfree(fbo);
 }
 
@@ -492,8 +492,9 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	if (!fbo)
 		return -ENOMEM;
 
+	ttm_bo_get(bo);
 	fbo->base = *bo;
-	fbo->bo = ttm_bo_reference(bo);
+	fbo->bo = bo;
 
 	/**
 	 * Fix up members that we shouldn't copy directly:
@@ -730,7 +731,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			bo->ttm = NULL;
 
 		ttm_bo_unreserve(ghost_obj);
-		ttm_bo_unref(&ghost_obj);
+		ttm_bo_put(ghost_obj);
 	}
 
 	*old_mem = *new_mem;
@@ -786,7 +787,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			bo->ttm = NULL;
 
 		ttm_bo_unreserve(ghost_obj);
-		ttm_bo_unref(&ghost_obj);
+		ttm_bo_put(ghost_obj);
 
 	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
 
@@ -851,7 +852,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	bo->ttm = NULL;
 
 	ttm_bo_unreserve(ghost);
-	ttm_bo_unref(&ghost);
+	ttm_bo_put(ghost);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0ca0ec47334e..6fe91c1b692d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -68,11 +68,11 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_unlock;
 
-		ttm_bo_reference(bo);
+		ttm_bo_get(bo);
 		up_read(&vmf->vma->vm_mm->mmap_sem);
 		(void) dma_fence_wait(bo->moving, true);
 		ttm_bo_unreserve(bo);
-		ttm_bo_unref(&bo);
+		ttm_bo_put(bo);
 		goto out_unlock;
 	}
 
@@ -138,10 +138,10 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 
 		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
-				ttm_bo_reference(bo);
+				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
 				(void) ttm_bo_wait_unreserved(bo);
-				ttm_bo_unref(&bo);
+				ttm_bo_put(bo);
 			}
 
 			return VM_FAULT_RETRY;
@@ -302,14 +302,14 @@ static void ttm_bo_vm_open(struct vm_area_struct *vma)
 
 	WARN_ON(bo->bdev->dev_mapping != vma->vm_file->f_mapping);
 
-	(void)ttm_bo_reference(bo);
+	ttm_bo_get(bo);
 }
 
 static void ttm_bo_vm_close(struct vm_area_struct *vma)
 {
 	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)vma->vm_private_data;
 
-	ttm_bo_unref(&bo);
+	ttm_bo_put(bo);
 	vma->vm_private_data = NULL;
 }
 
@@ -461,7 +461,7 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 out_unref:
-	ttm_bo_unref(&bo);
+	ttm_bo_put(bo);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_mmap);
@@ -471,8 +471,10 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 	if (vma->vm_pgoff != 0)
 		return -EACCES;
 
+	ttm_bo_get(bo);
+
 	vma->vm_ops = &ttm_bo_vm_ops;
-	vma->vm_private_data = ttm_bo_reference(bo);
+	vma->vm_private_data = bo;
 	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND;
 	return 0;
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index 09dc585aa46f..68e88bed77ca 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -99,7 +99,7 @@ static int udl_get_modes(struct drm_connector *connector)
 					struct udl_drm_connector,
 					connector);
 
-	drm_mode_connector_update_edid_property(connector, udl_connector->edid);
+	drm_connector_update_edid_property(connector, udl_connector->edid);
 	if (udl_connector->edid)
 		return drm_add_edid_modes(connector, udl_connector->edid);
 	return 0;
@@ -200,7 +200,7 @@ int udl_connector_init(struct drm_device *dev, struct drm_encoder *encoder)
 	drm_connector_helper_add(connector, &udl_connector_helper_funcs);
 
 	drm_connector_register(connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	connector->polled = DRM_CONNECTOR_POLL_HPD |
 		DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 
diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 072582570a4f..e9e9b1ff678e 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -113,7 +113,7 @@ udl_fb_user_fb_create(struct drm_device *dev,
 		      struct drm_file *file,
 		      const struct drm_mode_fb_cmd2 *mode_cmd);
 
-int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
+int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset, u32 byte_width,
 		     int *ident_ptr, int *sent_ptr);
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 2ebdc6d5a76e..dbb62f6eb48a 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -90,7 +90,10 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 	int bytes_identical = 0;
 	struct urb *urb;
 	int aligned_x;
-	int bpp = fb->base.format->cpp[0];
+	int log_bpp;
+
+	BUG_ON(!is_power_of_2(fb->base.format->cpp[0]));
+	log_bpp = __ffs(fb->base.format->cpp[0]);
 
 	if (!fb->active_16)
 		return 0;
@@ -125,19 +128,22 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 
 	for (i = y; i < y + height ; i++) {
 		const int line_offset = fb->base.pitches[0] * i;
-		const int byte_offset = line_offset + (x * bpp);
-		const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp);
-		if (udl_render_hline(dev, bpp, &urb,
+		const int byte_offset = line_offset + (x << log_bpp);
+		const int dev_byte_offset = (fb->base.width * i + x) << log_bpp;
+		if (udl_render_hline(dev, log_bpp, &urb,
 				     (char *) fb->obj->vmapping,
 				     &cmd, byte_offset, dev_byte_offset,
-				     width * bpp,
+				     width << log_bpp,
 				     &bytes_identical, &bytes_sent))
 			goto error;
 	}
 
 	if (cmd > (char *) urb->transfer_buffer) {
 		/* Send partial buffer remaining before exiting */
-		int len = cmd - (char *) urb->transfer_buffer;
+		int len;
+		if (cmd < (char *) urb->transfer_buffer + urb->transfer_buffer_length)
+			*cmd++ = 0xAF;
+		len = cmd - (char *) urb->transfer_buffer;
 		ret = udl_submit_urb(dev, urb, len);
 		bytes_sent += len;
 	} else
@@ -146,7 +152,7 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 error:
 	atomic_add(bytes_sent, &udl->bytes_sent);
 	atomic_add(bytes_identical, &udl->bytes_identical);
-	atomic_add(width*height*bpp, &udl->bytes_rendered);
+	atomic_add((width * height) << log_bpp, &udl->bytes_rendered);
 	end_cycles = get_cycles();
 	atomic_add(((unsigned int) ((end_cycles - start_cycles)
 		    >> 10)), /* Kcycles */
@@ -172,7 +178,7 @@ static int udl_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
 	pos = (unsigned long)info->fix.smem_start + offset;
 
-	pr_notice("mmap() framebuffer addr:%lu size:%lu\n",
+	pr_debug("mmap() framebuffer addr:%lu size:%lu\n",
 		  pos, size);
 
 	/* We don't want the framebuffer to be mapped encrypted */
@@ -218,7 +224,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 
 		struct fb_deferred_io *fbdefio;
 
-		fbdefio = kmalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
+		fbdefio = kzalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
 
 		if (fbdefio) {
 			fbdefio->delay = DL_DEFIO_WRITE_DELAY;
@@ -230,7 +236,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 	}
 #endif
 
-	pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n",
+	pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d\n",
 		  info->node, user, info, ufbdev->fb_count);
 
 	return 0;
@@ -255,7 +261,7 @@ static int udl_fb_release(struct fb_info *info, int user)
 	}
 #endif
 
-	pr_warn("released /dev/fb%d user=%d count=%d\n",
+	pr_debug("released /dev/fb%d user=%d count=%d\n",
 		info->node, user, ufbdev->fb_count);
 
 	return 0;
diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index d518de8f496b..f455f095a146 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -170,25 +170,19 @@ static void udl_free_urb_list(struct drm_device *dev)
 	struct list_head *node;
 	struct urb_node *unode;
 	struct urb *urb;
-	int ret;
-	unsigned long flags;
 
 	DRM_DEBUG("Waiting for completes and freeing all render urbs\n");
 
 	/* keep waiting and freeing, until we've got 'em all */
 	while (count--) {
+		down(&udl->urbs.limit_sem);
 
-		/* Getting interrupted means a leak, but ok at shutdown*/
-		ret = down_interruptible(&udl->urbs.limit_sem);
-		if (ret)
-			break;
-
-		spin_lock_irqsave(&udl->urbs.lock, flags);
+		spin_lock_irq(&udl->urbs.lock);
 
 		node = udl->urbs.list.next; /* have reserved one with sem */
 		list_del_init(node);
 
-		spin_unlock_irqrestore(&udl->urbs.lock, flags);
+		spin_unlock_irq(&udl->urbs.lock);
 
 		unode = list_entry(node, struct urb_node, entry);
 		urb = unode->urb;
@@ -205,17 +199,22 @@ static void udl_free_urb_list(struct drm_device *dev)
 static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 {
 	struct udl_device *udl = dev->dev_private;
-	int i = 0;
 	struct urb *urb;
 	struct urb_node *unode;
 	char *buf;
+	size_t wanted_size = count * size;
 
 	spin_lock_init(&udl->urbs.lock);
 
+retry:
 	udl->urbs.size = size;
 	INIT_LIST_HEAD(&udl->urbs.list);
 
-	while (i < count) {
+	sema_init(&udl->urbs.limit_sem, 0);
+	udl->urbs.count = 0;
+	udl->urbs.available = 0;
+
+	while (udl->urbs.count * size < wanted_size) {
 		unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL);
 		if (!unode)
 			break;
@@ -231,11 +230,16 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 		unode->urb = urb;
 
-		buf = usb_alloc_coherent(udl->udev, MAX_TRANSFER, GFP_KERNEL,
+		buf = usb_alloc_coherent(udl->udev, size, GFP_KERNEL,
 					 &urb->transfer_dma);
 		if (!buf) {
 			kfree(unode);
 			usb_free_urb(urb);
+			if (size > PAGE_SIZE) {
+				size /= 2;
+				udl_free_urb_list(dev);
+				goto retry;
+			}
 			break;
 		}
 
@@ -246,16 +250,14 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 
 		list_add_tail(&unode->entry, &udl->urbs.list);
 
-		i++;
+		up(&udl->urbs.limit_sem);
+		udl->urbs.count++;
+		udl->urbs.available++;
 	}
 
-	sema_init(&udl->urbs.limit_sem, i);
-	udl->urbs.count = i;
-	udl->urbs.available = i;
-
-	DRM_DEBUG("allocated %d %d byte urbs\n", i, (int) size);
+	DRM_DEBUG("allocated %d %d byte urbs\n", udl->urbs.count, (int) size);
 
-	return i;
+	return udl->urbs.count;
 }
 
 struct urb *udl_get_urb(struct drm_device *dev)
@@ -265,7 +267,6 @@ struct urb *udl_get_urb(struct drm_device *dev)
 	struct list_head *entry;
 	struct urb_node *unode;
 	struct urb *urb = NULL;
-	unsigned long flags;
 
 	/* Wait for an in-flight buffer to complete and get re-queued */
 	ret = down_timeout(&udl->urbs.limit_sem, GET_URB_TIMEOUT);
@@ -276,14 +277,14 @@ struct urb *udl_get_urb(struct drm_device *dev)
 		goto error;
 	}
 
-	spin_lock_irqsave(&udl->urbs.lock, flags);
+	spin_lock_irq(&udl->urbs.lock);
 
 	BUG_ON(list_empty(&udl->urbs.list)); /* reserved one with limit_sem */
 	entry = udl->urbs.list.next;
 	list_del_init(entry);
 	udl->urbs.available--;
 
-	spin_unlock_irqrestore(&udl->urbs.lock, flags);
+	spin_unlock_irq(&udl->urbs.lock);
 
 	unode = list_entry(entry, struct urb_node, entry);
 	urb = unode->urb;
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index 5bcae7649795..7e37765cf5ac 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -243,7 +243,7 @@ static int udl_crtc_write_mode_to_hw(struct drm_crtc *crtc)
 
 	memcpy(buf, udl->mode_buf, udl->mode_buf_len);
 	retval = udl_submit_urb(dev, urb, udl->mode_buf_len);
-	DRM_INFO("write mode info %d\n", udl->mode_buf_len);
+	DRM_DEBUG("write mode info %d\n", udl->mode_buf_len);
 	return retval;
 }
 
@@ -366,7 +366,6 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 {
 	struct udl_framebuffer *ufb = to_udl_fb(fb);
 	struct drm_device *dev = crtc->dev;
-	unsigned long flags;
 
 	struct drm_framebuffer *old_fb = crtc->primary->fb;
 	if (old_fb) {
@@ -377,10 +376,10 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 
 	udl_handle_damage(ufb, 0, 0, fb->width, fb->height);
 
-	spin_lock_irqsave(&dev->event_lock, flags);
+	spin_lock_irq(&dev->event_lock);
 	if (event)
 		drm_crtc_send_vblank_event(crtc, event);
-	spin_unlock_irqrestore(&dev->event_lock, flags);
+	spin_unlock_irq(&dev->event_lock);
 	crtc->primary->fb = fb;
 
 	return 0;
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index 0c87b1ac6b68..ce87661e544f 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fb.h>
-#include <linux/prefetch.h>
 #include <asm/unaligned.h>
 
 #include <drm/drmP.h>
@@ -51,9 +50,6 @@ static int udl_trim_hline(const u8 *bback, const u8 **bfront, int *width_bytes)
 	int start = width;
 	int end = width;
 
-	prefetch((void *) front);
-	prefetch((void *) back);
-
 	for (j = 0; j < width; j++) {
 		if (back[j] != front[j]) {
 			start = j;
@@ -83,12 +79,12 @@ static inline u16 pixel32_to_be16(const uint32_t pixel)
 		((pixel >> 8) & 0xf800));
 }
 
-static inline u16 get_pixel_val16(const uint8_t *pixel, int bpp)
+static inline u16 get_pixel_val16(const uint8_t *pixel, int log_bpp)
 {
-	u16 pixel_val16 = 0;
-	if (bpp == 2)
+	u16 pixel_val16;
+	if (log_bpp == 1)
 		pixel_val16 = *(const uint16_t *)pixel;
-	else if (bpp == 4)
+	else
 		pixel_val16 = pixel32_to_be16(*(const uint32_t *)pixel);
 	return pixel_val16;
 }
@@ -125,8 +121,9 @@ static void udl_compress_hline16(
 	const u8 *const pixel_end,
 	uint32_t *device_address_ptr,
 	uint8_t **command_buffer_ptr,
-	const uint8_t *const cmd_buffer_end, int bpp)
+	const uint8_t *const cmd_buffer_end, int log_bpp)
 {
+	const int bpp = 1 << log_bpp;
 	const u8 *pixel = *pixel_start_ptr;
 	uint32_t dev_addr  = *device_address_ptr;
 	uint8_t *cmd = *command_buffer_ptr;
@@ -139,8 +136,6 @@ static void udl_compress_hline16(
 		const u8 *cmd_pixel_start, *cmd_pixel_end = NULL;
 		uint16_t pixel_val16;
 
-		prefetchw((void *) cmd); /* pull in one cache line at least */
-
 		*cmd++ = 0xaf;
 		*cmd++ = 0x6b;
 		*cmd++ = (uint8_t) ((dev_addr >> 16) & 0xFF);
@@ -153,12 +148,11 @@ static void udl_compress_hline16(
 		raw_pixels_count_byte = cmd++; /*  we'll know this later */
 		raw_pixel_start = pixel;
 
-		cmd_pixel_end = pixel + (min(MAX_CMD_PIXELS + 1,
-			min((int)(pixel_end - pixel) / bpp,
-			    (int)(cmd_buffer_end - cmd) / 2))) * bpp;
+		cmd_pixel_end = pixel + (min3(MAX_CMD_PIXELS + 1UL,
+					(unsigned long)(pixel_end - pixel) >> log_bpp,
+					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) << log_bpp);
 
-		prefetch_range((void *) pixel, (cmd_pixel_end - pixel) * bpp);
-		pixel_val16 = get_pixel_val16(pixel, bpp);
+		pixel_val16 = get_pixel_val16(pixel, log_bpp);
 
 		while (pixel < cmd_pixel_end) {
 			const u8 *const start = pixel;
@@ -170,7 +164,7 @@ static void udl_compress_hline16(
 			pixel += bpp;
 
 			while (pixel < cmd_pixel_end) {
-				pixel_val16 = get_pixel_val16(pixel, bpp);
+				pixel_val16 = get_pixel_val16(pixel, log_bpp);
 				if (pixel_val16 != repeating_pixel_val16)
 					break;
 				pixel += bpp;
@@ -179,10 +173,10 @@ static void udl_compress_hline16(
 			if (unlikely(pixel > start + bpp)) {
 				/* go back and fill in raw pixel count */
 				*raw_pixels_count_byte = (((start -
-						raw_pixel_start) / bpp) + 1) & 0xFF;
+						raw_pixel_start) >> log_bpp) + 1) & 0xFF;
 
 				/* immediately after raw data is repeat byte */
-				*cmd++ = (((pixel - start) / bpp) - 1) & 0xFF;
+				*cmd++ = (((pixel - start) >> log_bpp) - 1) & 0xFF;
 
 				/* Then start another raw pixel span */
 				raw_pixel_start = pixel;
@@ -192,11 +186,14 @@ static void udl_compress_hline16(
 
 		if (pixel > raw_pixel_start) {
 			/* finalize last RAW span */
-			*raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF;
+			*raw_pixels_count_byte = ((pixel - raw_pixel_start) >> log_bpp) & 0xFF;
+		} else {
+			/* undo unused byte */
+			cmd--;
 		}
 
-		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF;
-		dev_addr += ((pixel - cmd_pixel_start) / bpp) * 2;
+		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) >> log_bpp) & 0xFF;
+		dev_addr += ((pixel - cmd_pixel_start) >> log_bpp) * 2;
 	}
 
 	if (cmd_buffer_end <= MIN_RLX_CMD_BYTES + cmd) {
@@ -219,19 +216,19 @@ static void udl_compress_hline16(
  * (that we can only write to, slowly, and can never read), and (optionally)
  * our shadow copy that tracks what's been sent to that hardware buffer.
  */
-int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
+int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset,
 		     u32 byte_width,
 		     int *ident_ptr, int *sent_ptr)
 {
 	const u8 *line_start, *line_end, *next_pixel;
-	u32 base16 = 0 + (device_byte_offset / bpp) * 2;
+	u32 base16 = 0 + (device_byte_offset >> log_bpp) * 2;
 	struct urb *urb = *urb_ptr;
 	u8 *cmd = *urb_buf_ptr;
 	u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length;
 
-	BUG_ON(!(bpp == 2 || bpp == 4));
+	BUG_ON(!(log_bpp == 1 || log_bpp == 2));
 
 	line_start = (u8 *) (front + byte_offset);
 	next_pixel = line_start;
@@ -241,7 +238,7 @@ int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
 
 		udl_compress_hline16(&next_pixel,
 			     line_end, &base16,
-			     (u8 **) &cmd, (u8 *) cmd_end, bpp);
+			     (u8 **) &cmd, (u8 *) cmd_end, log_bpp);
 
 		if (cmd >= cmd_end) {
 			int len = cmd - (u8 *) urb->transfer_buffer;
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index 7b1e2a549a71..54d96518a131 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -227,37 +227,19 @@ v3d_set_mmap_vma_flags(struct vm_area_struct *vma)
 	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 }
 
-int v3d_gem_fault(struct vm_fault *vmf)
+vm_fault_t v3d_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct v3d_bo *bo = to_v3d_bo(obj);
-	unsigned long pfn;
+	pfn_t pfn;
 	pgoff_t pgoff;
-	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
 	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
-	pfn = page_to_pfn(bo->pages[pgoff]);
-
-	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
-
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	pfn = __pfn_to_pfn_t(page_to_pfn(bo->pages[pgoff]), PFN_DEV);
+
+	return vmf_insert_mixed(vma, vmf->address, pfn);
 }
 
 int v3d_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index cdb582043b4f..2a85fa68ffea 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -123,6 +123,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv;
+	struct drm_sched_rq *rq;
 	int i;
 
 	v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL);
@@ -132,10 +133,8 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 	v3d_priv->v3d = v3d;
 
 	for (i = 0; i < V3D_MAX_QUEUES; i++) {
-		drm_sched_entity_init(&v3d->queue[i].sched,
-				      &v3d_priv->sched_entity[i],
-				      &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				      NULL);
+		rq = &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+		drm_sched_entity_init(&v3d_priv->sched_entity[i], &rq, 1, NULL);
 	}
 
 	file->driver_priv = v3d_priv;
@@ -146,13 +145,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 static void
 v3d_postclose(struct drm_device *dev, struct drm_file *file)
 {
-	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file->driver_priv;
 	enum v3d_queue q;
 
 	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		drm_sched_entity_fini(&v3d->queue[q].sched,
-				      &v3d_priv->sched_entity[q]);
+		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
 	}
 
 	kfree(v3d_priv);
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index f32ac8c98f37..e6fed696ad86 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -2,6 +2,7 @@
 /* Copyright (C) 2015-2018 Broadcom */
 
 #include <linux/reservation.h>
+#include <linux/mm_types.h>
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem.h>
@@ -183,6 +184,8 @@ struct v3d_job {
 
 	/* GPU virtual addresses of the start/end of the CL job. */
 	u32 start, end;
+
+	u32 timedout_ctca, timedout_ctra;
 };
 
 struct v3d_exec_info {
@@ -252,7 +255,7 @@ int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
 int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv);
-int v3d_gem_fault(struct vm_fault *vmf);
+vm_fault_t v3d_gem_fault(struct vm_fault *vmf);
 int v3d_mmap(struct file *filp, struct vm_area_struct *vma);
 struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj);
 int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index bfe31a89668b..50bfcf9a8a1a 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -35,19 +35,7 @@ static const char *v3d_fence_get_timeline_name(struct dma_fence *fence)
 		return "v3d-render";
 }
 
-static bool v3d_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 const struct dma_fence_ops v3d_fence_ops = {
 	.get_driver_name = v3d_fence_get_driver_name,
 	.get_timeline_name = v3d_fence_get_timeline_name,
-	.enable_signaling = v3d_fence_enable_signaling,
-	/* Each of our fences gets signaled as complete by the IRQ
-	 * handler, so we rely on the core's tracking of signaling.
-	 */
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
-	.release = dma_fence_free,
 };
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index e1fcbb4cd0ae..5ce24098a5fd 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -553,7 +553,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&v3d->sched_lock);
 	if (exec->bin.start != exec->bin.end) {
 		ret = drm_sched_job_init(&exec->bin.base,
-					 &v3d->queue[V3D_BIN].sched,
 					 &v3d_priv->sched_entity[V3D_BIN],
 					 v3d_priv);
 		if (ret)
@@ -568,7 +567,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	}
 
 	ret = drm_sched_job_init(&exec->render.base,
-				 &v3d->queue[V3D_RENDER].sched,
 				 &v3d_priv->sched_entity[V3D_RENDER],
 				 v3d_priv);
 	if (ret)
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
index fc13282dfc2f..854046565989 100644
--- a/drivers/gpu/drm/v3d/v3d_regs.h
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -222,6 +222,7 @@
 #define V3D_CLE_CTNCA(n) (V3D_CLE_CT0CA + 4 * n)
 #define V3D_CLE_CT0RA                                  0x00118
 #define V3D_CLE_CT1RA                                  0x0011c
+#define V3D_CLE_CTNRA(n) (V3D_CLE_CT0RA + 4 * n)
 #define V3D_CLE_CT0LC                                  0x00120
 #define V3D_CLE_CT1LC                                  0x00124
 #define V3D_CLE_CT0PC                                  0x00128
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 808bc901f567..a5501581d96b 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -14,8 +14,8 @@
  * to the HW only when it has completed the last one, instead of
  * filling up the CT[01]Q FIFOs with jobs.  Similarly, we use
  * v3d_job_dependency() to manage the dependency between bin and
- * render, instead of having the clients submit jobs with using the
- * HW's semaphores to interlock between them.
+ * render, instead of having the clients submit jobs using the HW's
+ * semaphores to interlock between them.
  */
 
 #include <linux/kthread.h>
@@ -153,7 +153,25 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
 	struct v3d_job *job = to_v3d_job(sched_job);
 	struct v3d_exec_info *exec = job->exec;
 	struct v3d_dev *v3d = exec->v3d;
+	enum v3d_queue job_q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
 	enum v3d_queue q;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(job_q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(job_q));
+
+	/* If the current address or return address have changed, then
+	 * the GPU has probably made progress and we should delay the
+	 * reset.  This could fail if the GPU got in an infinite loop
+	 * in the CL, but that is pretty unlikely outside of an i-g-t
+	 * testcase.
+	 */
+	if (job->timedout_ctca != ctca || job->timedout_ctra != ctra) {
+		job->timedout_ctca = ctca;
+		job->timedout_ctra = ctra;
+
+		schedule_delayed_work(&job->base.work_tdr,
+				      job->base.sched->timeout);
+		return;
+	}
 
 	mutex_lock(&v3d->reset_lock);
 
diff --git a/drivers/gpu/drm/vc4/Makefile b/drivers/gpu/drm/vc4/Makefile
index 4a3a868235f8..b303703bc7f3 100644
--- a/drivers/gpu/drm/vc4/Makefile
+++ b/drivers/gpu/drm/vc4/Makefile
@@ -19,6 +19,7 @@ vc4-y := \
 	vc4_plane.o \
 	vc4_render_cl.o \
 	vc4_trace_points.o \
+	vc4_txp.o \
 	vc4_v3d.o \
 	vc4_validate.o \
 	vc4_validate_shaders.o
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index d222358fa8a7..0e6a121858d1 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -46,6 +46,8 @@ struct vc4_crtc_state {
 	struct drm_crtc_state base;
 	/* Dlist area for this CRTC configuration. */
 	struct drm_mm_node mm;
+	bool feed_txp;
+	bool txp_armed;
 };
 
 static inline struct vc4_crtc_state *
@@ -324,10 +326,8 @@ static struct drm_encoder *vc4_get_crtc_encoder(struct drm_crtc *crtc)
 	return NULL;
 }
 
-static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
+static void vc4_crtc_config_pv(struct drm_crtc *crtc)
 {
-	struct drm_device *dev = crtc->dev;
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_encoder *encoder = vc4_get_crtc_encoder(crtc);
 	struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
@@ -338,12 +338,6 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	bool is_dsi = (vc4_encoder->type == VC4_ENCODER_TYPE_DSI0 ||
 		       vc4_encoder->type == VC4_ENCODER_TYPE_DSI1);
 	u32 format = is_dsi ? PV_CONTROL_FORMAT_DSIV_24 : PV_CONTROL_FORMAT_24;
-	bool debug_dump_regs = false;
-
-	if (debug_dump_regs) {
-		DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc));
-		vc4_crtc_dump_regs(vc4_crtc);
-	}
 
 	/* Reset the PV fifo. */
 	CRTC_WRITE(PV_CONTROL, 0);
@@ -419,6 +413,49 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
 				 PV_CONTROL_CLK_SELECT) |
 		   PV_CONTROL_FIFO_CLR |
 		   PV_CONTROL_EN);
+}
+
+static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
+	bool interlace = mode->flags & DRM_MODE_FLAG_INTERLACE;
+	bool debug_dump_regs = false;
+
+	if (debug_dump_regs) {
+		DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc));
+		vc4_crtc_dump_regs(vc4_crtc);
+	}
+
+	if (vc4_crtc->channel == 2) {
+		u32 dispctrl;
+		u32 dsp3_mux;
+
+		/*
+		 * SCALER_DISPCTRL_DSP3 = X, where X < 2 means 'connect DSP3 to
+		 * FIFO X'.
+		 * SCALER_DISPCTRL_DSP3 = 3 means 'disable DSP 3'.
+		 *
+		 * DSP3 is connected to FIFO2 unless the transposer is
+		 * enabled. In this case, FIFO 2 is directly accessed by the
+		 * TXP IP, and we need to disable the FIFO2 -> pixelvalve1
+		 * route.
+		 */
+		if (vc4_state->feed_txp)
+			dsp3_mux = VC4_SET_FIELD(3, SCALER_DISPCTRL_DSP3_MUX);
+		else
+			dsp3_mux = VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX);
+
+		dispctrl = HVS_READ(SCALER_DISPCTRL) &
+			   ~SCALER_DISPCTRL_DSP3_MUX_MASK;
+		HVS_WRITE(SCALER_DISPCTRL, dispctrl | dsp3_mux);
+	}
+
+	if (!vc4_state->feed_txp)
+		vc4_crtc_config_pv(crtc);
 
 	HVS_WRITE(SCALER_DISPBKGNDX(vc4_crtc->channel),
 		  SCALER_DISPBKGND_AUTOHS |
@@ -499,6 +536,13 @@ static void vc4_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 }
 
+void vc4_crtc_txp_armed(struct drm_crtc_state *state)
+{
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(state);
+
+	vc4_state->txp_armed = true;
+}
+
 static void vc4_crtc_update_dlist(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -514,8 +558,11 @@ static void vc4_crtc_update_dlist(struct drm_crtc *crtc)
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
 		spin_lock_irqsave(&dev->event_lock, flags);
-		vc4_crtc->event = crtc->state->event;
-		crtc->state->event = NULL;
+
+		if (!vc4_state->feed_txp || vc4_state->txp_armed) {
+			vc4_crtc->event = crtc->state->event;
+			crtc->state->event = NULL;
+		}
 
 		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
 			  vc4_state->mm.start);
@@ -533,8 +580,8 @@ static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
-	struct drm_crtc_state *state = crtc->state;
-	struct drm_display_mode *mode = &state->adjusted_mode;
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 
 	require_hvs_enabled(dev);
 
@@ -546,15 +593,21 @@ static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	/* Turn on the scaler, which will wait for vstart to start
 	 * compositing.
+	 * When feeding the transposer, we should operate in oneshot
+	 * mode.
 	 */
 	HVS_WRITE(SCALER_DISPCTRLX(vc4_crtc->channel),
 		  VC4_SET_FIELD(mode->hdisplay, SCALER_DISPCTRLX_WIDTH) |
 		  VC4_SET_FIELD(mode->vdisplay, SCALER_DISPCTRLX_HEIGHT) |
-		  SCALER_DISPCTRLX_ENABLE);
+		  SCALER_DISPCTRLX_ENABLE |
+		  (vc4_state->feed_txp ? SCALER_DISPCTRLX_ONESHOT : 0));
 
-	/* Turn on the pixel valve, which will emit the vstart signal. */
-	CRTC_WRITE(PV_V_CONTROL,
-		   CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN);
+	/* When feeding the transposer block the pixelvalve is unneeded and
+	 * should not be enabled.
+	 */
+	if (!vc4_state->feed_txp)
+		CRTC_WRITE(PV_V_CONTROL,
+			   CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN);
 }
 
 static enum drm_mode_status vc4_crtc_mode_valid(struct drm_crtc *crtc,
@@ -579,8 +632,10 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	struct drm_plane *plane;
 	unsigned long flags;
 	const struct drm_plane_state *plane_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	u32 dlist_count = 0;
-	int ret;
+	int ret, i;
 
 	/* The pixelvalve can only feed one encoder (and encoders are
 	 * 1:1 with connectors.)
@@ -600,6 +655,24 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	if (ret)
 		return ret;
 
+	for_each_new_connector_in_state(state->state, conn, conn_state, i) {
+		if (conn_state->crtc != crtc)
+			continue;
+
+		/* The writeback connector is implemented using the transposer
+		 * block which is directly taking its data from the HVS FIFO.
+		 */
+		if (conn->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) {
+			state->no_vblank = true;
+			vc4_state->feed_txp = true;
+		} else {
+			state->no_vblank = false;
+			vc4_state->feed_txp = false;
+		}
+
+		break;
+	}
+
 	return 0;
 }
 
@@ -713,7 +786,8 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (vc4_crtc->event &&
-	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)))) {
+	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)) ||
+	     vc4_state->feed_txp)) {
 		drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
 		vc4_crtc->event = NULL;
 		drm_crtc_vblank_put(crtc);
@@ -721,6 +795,13 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
+void vc4_crtc_handle_vblank(struct vc4_crtc *crtc)
+{
+	crtc->t_vblank = ktime_get();
+	drm_crtc_handle_vblank(&crtc->base);
+	vc4_crtc_handle_page_flip(crtc);
+}
+
 static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 {
 	struct vc4_crtc *vc4_crtc = data;
@@ -728,10 +809,8 @@ static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 	irqreturn_t ret = IRQ_NONE;
 
 	if (stat & PV_INT_VFP_START) {
-		vc4_crtc->t_vblank = ktime_get();
 		CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
-		drm_crtc_handle_vblank(&vc4_crtc->base);
-		vc4_crtc_handle_page_flip(vc4_crtc);
+		vc4_crtc_handle_vblank(vc4_crtc);
 		ret = IRQ_HANDLED;
 	}
 
@@ -884,12 +963,15 @@ static int vc4_page_flip(struct drm_crtc *crtc,
 
 static struct drm_crtc_state *vc4_crtc_duplicate_state(struct drm_crtc *crtc)
 {
-	struct vc4_crtc_state *vc4_state;
+	struct vc4_crtc_state *vc4_state, *old_vc4_state;
 
 	vc4_state = kzalloc(sizeof(*vc4_state), GFP_KERNEL);
 	if (!vc4_state)
 		return NULL;
 
+	old_vc4_state = to_vc4_crtc_state(crtc->state);
+	vc4_state->feed_txp = old_vc4_state->feed_txp;
+
 	__drm_atomic_helper_crtc_duplicate_state(crtc, &vc4_state->base);
 	return &vc4_state->base;
 }
@@ -987,9 +1069,17 @@ static void vc4_set_crtc_possible_masks(struct drm_device *drm,
 	struct drm_encoder *encoder;
 
 	drm_for_each_encoder(encoder, drm) {
-		struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
+		struct vc4_encoder *vc4_encoder;
 		int i;
 
+		/* HVS FIFO2 can feed the TXP IP. */
+		if (crtc_data->hvs_channel == 2 &&
+		    encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL) {
+			encoder->possible_crtcs |= drm_crtc_mask(crtc);
+			continue;
+		}
+
+		vc4_encoder = to_vc4_encoder(encoder);
 		for (i = 0; i < ARRAY_SIZE(crtc_data->encoder_types); i++) {
 			if (vc4_encoder->type == encoder_types[i]) {
 				vc4_encoder->clock_select = i;
diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c
index 5db06bdb5f27..7a0003de71ab 100644
--- a/drivers/gpu/drm/vc4/vc4_debugfs.c
+++ b/drivers/gpu/drm/vc4/vc4_debugfs.c
@@ -21,6 +21,7 @@ static const struct drm_info_list vc4_debugfs_list[] = {
 	{"dsi1_regs", vc4_dsi_debugfs_regs, 0, (void *)(uintptr_t)1},
 	{"hdmi_regs", vc4_hdmi_debugfs_regs, 0},
 	{"vec_regs", vc4_vec_debugfs_regs, 0},
+	{"txp_regs", vc4_txp_debugfs_regs, 0},
 	{"hvs_regs", vc4_hvs_debugfs_regs, 0},
 	{"crtc0_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)0},
 	{"crtc1_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)1},
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 466d0a27b415..04270a14fcaa 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -288,7 +288,7 @@ static int vc4_drm_bind(struct device *dev)
 
 	ret = vc4_bo_cache_init(drm);
 	if (ret)
-		goto dev_unref;
+		goto dev_put;
 
 	drm_mode_config_init(drm);
 
@@ -313,8 +313,8 @@ unbind_all:
 gem_destroy:
 	vc4_gem_destroy(drm);
 	vc4_bo_cache_destroy(drm);
-dev_unref:
-	drm_dev_unref(drm);
+dev_put:
+	drm_dev_put(drm);
 	return ret;
 }
 
@@ -331,7 +331,7 @@ static void vc4_drm_unbind(struct device *dev)
 
 	drm_atomic_private_obj_fini(&vc4->ctm_manager);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops vc4_drm_ops = {
@@ -344,6 +344,7 @@ static struct platform_driver *const component_drivers[] = {
 	&vc4_vec_driver,
 	&vc4_dpi_driver,
 	&vc4_dsi_driver,
+	&vc4_txp_driver,
 	&vc4_hvs_driver,
 	&vc4_crtc_driver,
 	&vc4_v3d_driver,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index eace76c621a1..bd6ef1f31822 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -73,6 +73,7 @@ struct vc4_dev {
 	struct vc4_dpi *dpi;
 	struct vc4_dsi *dsi1;
 	struct vc4_vec *vec;
+	struct vc4_txp *txp;
 
 	struct vc4_hang_state *hang_state;
 
@@ -698,6 +699,8 @@ bool vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
 			     bool in_vblank_irq, int *vpos, int *hpos,
 			     ktime_t *stime, ktime_t *etime,
 			     const struct drm_display_mode *mode);
+void vc4_crtc_handle_vblank(struct vc4_crtc *crtc);
+void vc4_crtc_txp_armed(struct drm_crtc_state *state);
 
 /* vc4_debugfs.c */
 int vc4_debugfs_init(struct drm_minor *minor);
@@ -745,6 +748,10 @@ int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused);
 extern struct platform_driver vc4_vec_driver;
 int vc4_vec_debugfs_regs(struct seq_file *m, void *unused);
 
+/* vc4_txp.c */
+extern struct platform_driver vc4_txp_driver;
+int vc4_txp_debugfs_regs(struct seq_file *m, void *unused);
+
 /* vc4_irq.c */
 irqreturn_t vc4_irq(int irq, void *arg);
 void vc4_irq_preinstall(struct drm_device *dev);
diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 9c8e89372d1c..0c607eb33d7e 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -1612,8 +1612,18 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0,
 					  &panel, &dsi->bridge);
-	if (ret)
+	if (ret) {
+		/* If the bridge or panel pointed by dev->of_node is not
+		 * enabled, just return 0 here so that we don't prevent the DRM
+		 * dev from being registered. Of course that means the DSI
+		 * encoder won't be exposed, but that's not a problem since
+		 * nothing is connected to it.
+		 */
+		if (ret == -ENODEV)
+			return 0;
+
 		return ret;
+	}
 
 	if (panel) {
 		dsi->bridge = devm_drm_panel_bridge_add(dev, panel,
@@ -1664,7 +1674,8 @@ static void vc4_dsi_unbind(struct device *dev, struct device *master,
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
 
-	pm_runtime_disable(dev);
+	if (dsi->bridge)
+		pm_runtime_disable(dev);
 
 	vc4_dsi_encoder_destroy(dsi->encoder);
 
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index b8d50533e2bb..fd5522fd179e 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -285,7 +285,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 			drm_rgb_quant_range_selectable(edid);
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
@@ -329,7 +329,7 @@ static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev,
 	connector->interlace_allowed = 1;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 8a411e5f8776..ca5aa7fba769 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -153,18 +153,11 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
-	/* Make sure that drm_atomic_helper_wait_for_vblanks()
-	 * actually waits for vblank.  If we're doing a full atomic
-	 * modeset (as opposed to a vc4_update_plane() short circuit),
-	 * then we need to wait for scanout to be done with our
-	 * display lists before we free it and potentially reallocate
-	 * and overwrite the dlist memory with a new modeset.
-	 */
-	state->legacy_cursor_update = false;
+	drm_atomic_helper_fake_vblank(state);
 
 	drm_atomic_helper_commit_hw_done(state);
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
+	drm_atomic_helper_wait_for_flip_done(dev, state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
 
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
new file mode 100644
index 000000000000..6e23c50168f9
--- /dev/null
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2018 Broadcom
+ *
+ * Authors:
+ *	Eric Anholt <eric@anholt.net>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_writeback.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/pm_runtime.h>
+
+#include "vc4_drv.h"
+#include "vc4_regs.h"
+
+/* Base address of the output.  Raster formats must be 4-byte aligned,
+ * T and LT must be 16-byte aligned or maybe utile-aligned (docs are
+ * inconsistent, but probably utile).
+ */
+#define TXP_DST_PTR		0x00
+
+/* Pitch in bytes for raster images, 16-byte aligned.  For tiled, it's
+ * the width in tiles.
+ */
+#define TXP_DST_PITCH		0x04
+/* For T-tiled imgaes, DST_PITCH should be the number of tiles wide,
+ * shifted up.
+ */
+# define TXP_T_TILE_WIDTH_SHIFT		7
+/* For LT-tiled images, DST_PITCH should be the number of utiles wide,
+ * shifted up.
+ */
+# define TXP_LT_TILE_WIDTH_SHIFT	4
+
+/* Pre-rotation width/height of the image.  Must match HVS config.
+ *
+ * If TFORMAT and 32-bit, limit is 1920 for 32-bit and 3840 to 16-bit
+ * and width/height must be tile or utile-aligned as appropriate.  If
+ * transposing (rotating), width is limited to 1920.
+ *
+ * Height is limited to various numbers between 4088 and 4095.  I'd
+ * just use 4088 to be safe.
+ */
+#define TXP_DIM			0x08
+# define TXP_HEIGHT_SHIFT		16
+# define TXP_HEIGHT_MASK		GENMASK(31, 16)
+# define TXP_WIDTH_SHIFT		0
+# define TXP_WIDTH_MASK			GENMASK(15, 0)
+
+#define TXP_DST_CTRL		0x0c
+/* These bits are set to 0x54 */
+#define TXP_PILOT_SHIFT			24
+#define TXP_PILOT_MASK			GENMASK(31, 24)
+/* Bits 22-23 are set to 0x01 */
+#define TXP_VERSION_SHIFT		22
+#define TXP_VERSION_MASK		GENMASK(23, 22)
+
+/* Powers down the internal memory. */
+# define TXP_POWERDOWN			BIT(21)
+
+/* Enables storing the alpha component in 8888/4444, instead of
+ * filling with ~ALPHA_INVERT.
+ */
+# define TXP_ALPHA_ENABLE		BIT(20)
+
+/* 4 bits, each enables stores for a channel in each set of 4 bytes.
+ * Set to 0xf for normal operation.
+ */
+# define TXP_BYTE_ENABLE_SHIFT		16
+# define TXP_BYTE_ENABLE_MASK		GENMASK(19, 16)
+
+/* Debug: Generate VSTART again at EOF. */
+# define TXP_VSTART_AT_EOF		BIT(15)
+
+/* Debug: Terminate the current frame immediately.  Stops AXI
+ * writes.
+ */
+# define TXP_ABORT			BIT(14)
+
+# define TXP_DITHER			BIT(13)
+
+/* Inverts alpha if TXP_ALPHA_ENABLE, chooses fill value for
+ * !TXP_ALPHA_ENABLE.
+ */
+# define TXP_ALPHA_INVERT		BIT(12)
+
+/* Note: I've listed the channels here in high bit (in byte 3/2/1) to
+ * low bit (in byte 0) order.
+ */
+# define TXP_FORMAT_SHIFT		8
+# define TXP_FORMAT_MASK		GENMASK(11, 8)
+# define TXP_FORMAT_ABGR4444		0
+# define TXP_FORMAT_ARGB4444		1
+# define TXP_FORMAT_BGRA4444		2
+# define TXP_FORMAT_RGBA4444		3
+# define TXP_FORMAT_BGR565		6
+# define TXP_FORMAT_RGB565		7
+/* 888s are non-rotated, raster-only */
+# define TXP_FORMAT_BGR888		8
+# define TXP_FORMAT_RGB888		9
+# define TXP_FORMAT_ABGR8888		12
+# define TXP_FORMAT_ARGB8888		13
+# define TXP_FORMAT_BGRA8888		14
+# define TXP_FORMAT_RGBA8888		15
+
+/* If TFORMAT is set, generates LT instead of T format. */
+# define TXP_LINEAR_UTILE		BIT(7)
+
+/* Rotate output by 90 degrees. */
+# define TXP_TRANSPOSE			BIT(6)
+
+/* Generate a tiled format for V3D. */
+# define TXP_TFORMAT			BIT(5)
+
+/* Generates some undefined test mode output. */
+# define TXP_TEST_MODE			BIT(4)
+
+/* Request odd field from HVS. */
+# define TXP_FIELD			BIT(3)
+
+/* Raise interrupt when idle. */
+# define TXP_EI				BIT(2)
+
+/* Set when generating a frame, clears when idle. */
+# define TXP_BUSY			BIT(1)
+
+/* Starts a frame.  Self-clearing. */
+# define TXP_GO				BIT(0)
+
+/* Number of lines received and committed to memory. */
+#define TXP_PROGRESS		0x10
+
+#define TXP_READ(offset) readl(txp->regs + (offset))
+#define TXP_WRITE(offset, val) writel(val, txp->regs + (offset))
+
+struct vc4_txp {
+	struct platform_device *pdev;
+
+	struct drm_writeback_connector connector;
+
+	void __iomem *regs;
+};
+
+static inline struct vc4_txp *encoder_to_vc4_txp(struct drm_encoder *encoder)
+{
+	return container_of(encoder, struct vc4_txp, connector.encoder);
+}
+
+static inline struct vc4_txp *connector_to_vc4_txp(struct drm_connector *conn)
+{
+	return container_of(conn, struct vc4_txp, connector.base);
+}
+
+#define TXP_REG(reg) { reg, #reg }
+static const struct {
+	u32 reg;
+	const char *name;
+} txp_regs[] = {
+	TXP_REG(TXP_DST_PTR),
+	TXP_REG(TXP_DST_PITCH),
+	TXP_REG(TXP_DIM),
+	TXP_REG(TXP_DST_CTRL),
+	TXP_REG(TXP_PROGRESS),
+};
+
+#ifdef CONFIG_DEBUG_FS
+int vc4_txp_debugfs_regs(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_txp *txp = vc4->txp;
+	int i;
+
+	if (!txp)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(txp_regs); i++) {
+		seq_printf(m, "%s (0x%04x): 0x%08x\n",
+			   txp_regs[i].name, txp_regs[i].reg,
+			   TXP_READ(txp_regs[i].reg));
+	}
+
+	return 0;
+}
+#endif
+
+static int vc4_txp_connector_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+
+	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
+				    dev->mode_config.max_height);
+}
+
+static enum drm_mode_status
+vc4_txp_connector_mode_valid(struct drm_connector *connector,
+			     struct drm_display_mode *mode)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	int w = mode->hdisplay, h = mode->vdisplay;
+
+	if (w < mode_config->min_width || w > mode_config->max_width)
+		return MODE_BAD_HVALUE;
+
+	if (h < mode_config->min_height || h > mode_config->max_height)
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
+}
+
+static const u32 drm_fmts[] = {
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_BGRA8888,
+};
+
+static const u32 txp_fmts[] = {
+	TXP_FORMAT_RGB888,
+	TXP_FORMAT_BGR888,
+	TXP_FORMAT_ARGB8888,
+	TXP_FORMAT_ABGR8888,
+	TXP_FORMAT_ARGB8888,
+	TXP_FORMAT_ABGR8888,
+	TXP_FORMAT_RGBA8888,
+	TXP_FORMAT_BGRA8888,
+	TXP_FORMAT_RGBA8888,
+	TXP_FORMAT_BGRA8888,
+};
+
+static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
+					struct drm_connector_state *conn_state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct drm_gem_cma_object *gem;
+	struct drm_framebuffer *fb;
+	int i;
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(conn_state->state,
+						   conn_state->crtc);
+
+	fb = conn_state->writeback_job->fb;
+	if (fb->width != crtc_state->mode.hdisplay ||
+	    fb->height != crtc_state->mode.vdisplay) {
+		DRM_DEBUG_KMS("Invalid framebuffer size %ux%u\n",
+			      fb->width, fb->height);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(drm_fmts); i++) {
+		if (fb->format->format == drm_fmts[i])
+			break;
+	}
+
+	if (i == ARRAY_SIZE(drm_fmts))
+		return -EINVAL;
+
+	gem = drm_fb_cma_get_gem_obj(fb, 0);
+
+	/* Pitch must be aligned on 16 bytes. */
+	if (fb->pitches[0] & GENMASK(3, 0))
+		return -EINVAL;
+
+	vc4_crtc_txp_armed(crtc_state);
+
+	return 0;
+}
+
+static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
+					struct drm_connector_state *conn_state)
+{
+	struct vc4_txp *txp = connector_to_vc4_txp(conn);
+	struct drm_gem_cma_object *gem;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	u32 ctrl;
+	int i;
+
+	if (WARN_ON(!conn_state->writeback_job ||
+		    !conn_state->writeback_job->fb))
+		return;
+
+	mode = &conn_state->crtc->state->adjusted_mode;
+	fb = conn_state->writeback_job->fb;
+
+	for (i = 0; i < ARRAY_SIZE(drm_fmts); i++) {
+		if (fb->format->format == drm_fmts[i])
+			break;
+	}
+
+	if (WARN_ON(i == ARRAY_SIZE(drm_fmts)))
+		return;
+
+	ctrl = TXP_GO | TXP_VSTART_AT_EOF | TXP_EI |
+	       VC4_SET_FIELD(0xf, TXP_BYTE_ENABLE) |
+	       VC4_SET_FIELD(txp_fmts[i], TXP_FORMAT);
+
+	if (fb->format->has_alpha)
+		ctrl |= TXP_ALPHA_ENABLE;
+
+	gem = drm_fb_cma_get_gem_obj(fb, 0);
+	TXP_WRITE(TXP_DST_PTR, gem->paddr + fb->offsets[0]);
+	TXP_WRITE(TXP_DST_PITCH, fb->pitches[0]);
+	TXP_WRITE(TXP_DIM,
+		  VC4_SET_FIELD(mode->hdisplay, TXP_WIDTH) |
+		  VC4_SET_FIELD(mode->vdisplay, TXP_HEIGHT));
+
+	TXP_WRITE(TXP_DST_CTRL, ctrl);
+
+	drm_writeback_queue_job(&txp->connector, conn_state->writeback_job);
+}
+
+static const struct drm_connector_helper_funcs vc4_txp_connector_helper_funcs = {
+	.get_modes = vc4_txp_connector_get_modes,
+	.mode_valid = vc4_txp_connector_mode_valid,
+	.atomic_check = vc4_txp_connector_atomic_check,
+	.atomic_commit = vc4_txp_connector_atomic_commit,
+};
+
+static enum drm_connector_status
+vc4_txp_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static void vc4_txp_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vc4_txp_connector_funcs = {
+	.detect = vc4_txp_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vc4_txp_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 void vc4_txp_encoder_disable(struct drm_encoder *encoder)
+{
+	struct vc4_txp *txp = encoder_to_vc4_txp(encoder);
+
+	if (TXP_READ(TXP_DST_CTRL) & TXP_BUSY) {
+		unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+
+		TXP_WRITE(TXP_DST_CTRL, TXP_ABORT);
+
+		while (TXP_READ(TXP_DST_CTRL) & TXP_BUSY &&
+		       time_before(jiffies, timeout))
+			;
+
+		WARN_ON(TXP_READ(TXP_DST_CTRL) & TXP_BUSY);
+	}
+
+	TXP_WRITE(TXP_DST_CTRL, TXP_POWERDOWN);
+}
+
+static const struct drm_encoder_helper_funcs vc4_txp_encoder_helper_funcs = {
+	.disable = vc4_txp_encoder_disable,
+};
+
+static irqreturn_t vc4_txp_interrupt(int irq, void *data)
+{
+	struct vc4_txp *txp = data;
+
+	TXP_WRITE(TXP_DST_CTRL, TXP_READ(TXP_DST_CTRL) & ~TXP_EI);
+	vc4_crtc_handle_vblank(to_vc4_crtc(txp->connector.base.state->crtc));
+	drm_writeback_signal_completion(&txp->connector, 0);
+
+	return IRQ_HANDLED;
+}
+
+static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct drm_device *drm = dev_get_drvdata(master);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_txp *txp;
+	int ret, irq;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	txp = devm_kzalloc(dev, sizeof(*txp), GFP_KERNEL);
+	if (!txp)
+		return -ENOMEM;
+
+	txp->pdev = pdev;
+
+	txp->regs = vc4_ioremap_regs(pdev, 0);
+	if (IS_ERR(txp->regs))
+		return PTR_ERR(txp->regs);
+
+	drm_connector_helper_add(&txp->connector.base,
+				 &vc4_txp_connector_helper_funcs);
+	ret = drm_writeback_connector_init(drm, &txp->connector,
+					   &vc4_txp_connector_funcs,
+					   &vc4_txp_encoder_helper_funcs,
+					   drm_fmts, ARRAY_SIZE(drm_fmts));
+	if (ret)
+		return ret;
+
+	ret = devm_request_irq(dev, irq, vc4_txp_interrupt, 0,
+			       dev_name(dev), txp);
+	if (ret)
+		return ret;
+
+	dev_set_drvdata(dev, txp);
+	vc4->txp = txp;
+
+	return 0;
+}
+
+static void vc4_txp_unbind(struct device *dev, struct device *master,
+			   void *data)
+{
+	struct drm_device *drm = dev_get_drvdata(master);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_txp *txp = dev_get_drvdata(dev);
+
+	vc4_txp_connector_destroy(&txp->connector.base);
+
+	vc4->txp = NULL;
+}
+
+static const struct component_ops vc4_txp_ops = {
+	.bind   = vc4_txp_bind,
+	.unbind = vc4_txp_unbind,
+};
+
+static int vc4_txp_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &vc4_txp_ops);
+}
+
+static int vc4_txp_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &vc4_txp_ops);
+	return 0;
+}
+
+static const struct of_device_id vc4_txp_dt_match[] = {
+	{ .compatible = "brcm,bcm2835-txp" },
+	{ /* sentinel */ },
+};
+
+struct platform_driver vc4_txp_driver = {
+	.probe = vc4_txp_probe,
+	.remove = vc4_txp_remove,
+	.driver = {
+		.name = "vc4_txp",
+		.of_match_table = vc4_txp_dt_match,
+	},
+};
diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c
index 3a9a302247a2..8e7facb6514e 100644
--- a/drivers/gpu/drm/vc4/vc4_vec.c
+++ b/drivers/gpu/drm/vc4/vc4_vec.c
@@ -404,7 +404,7 @@ static struct drm_connector *vc4_vec_connector_init(struct drm_device *dev,
 				   VC4_VEC_TV_MODE_NTSC);
 	vec->tv_mode = &vc4_vec_tv_modes[VC4_VEC_TV_MODE_NTSC];
 
-	drm_mode_connector_attach_encoder(connector, vec->encoder);
+	drm_connector_attach_encoder(connector, vec->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index ff9933e79416..25503b933599 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -292,7 +292,7 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 	drm_encoder_helper_add(encoder, &virtio_gpu_enc_helper_funcs);
 	encoder->possible_crtcs = 1 << index;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	drm_connector_register(connector);
 	return 0;
 }
diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
new file mode 100644
index 000000000000..986297da51bf
--- /dev/null
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -0,0 +1,3 @@
+vkms-y := vkms_drv.o vkms_plane.o vkms_output.o vkms_crtc.o vkms_gem.o
+
+obj-$(CONFIG_DRM_VKMS) += vkms.o
diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
new file mode 100644
index 000000000000..875fca662ac0
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+
+static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer)
+{
+	struct vkms_output *output = container_of(timer, struct vkms_output,
+						  vblank_hrtimer);
+	struct drm_crtc *crtc = &output->crtc;
+	int ret_overrun;
+	bool ret;
+
+	ret = drm_crtc_handle_vblank(crtc);
+	if (!ret)
+		DRM_ERROR("vkms failure on handling vblank");
+
+	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
+					  output->period_ns);
+
+	return HRTIMER_RESTART;
+}
+
+static int vkms_enable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
+
+	drm_calc_timestamping_constants(crtc, &crtc->mode);
+
+	hrtimer_init(&out->vblank_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	out->vblank_hrtimer.function = &vkms_vblank_simulate;
+	out->period_ns = ktime_set(0, vblank->framedur_ns);
+	hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+static void vkms_disable_vblank(struct drm_crtc *crtc)
+{
+	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
+
+	hrtimer_cancel(&out->vblank_hrtimer);
+}
+
+bool vkms_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
+			       int *max_error, ktime_t *vblank_time,
+			       bool in_vblank_irq)
+{
+	struct vkms_device *vkmsdev = drm_device_to_vkms_device(dev);
+	struct vkms_output *output = &vkmsdev->output;
+
+	*vblank_time = output->vblank_hrtimer.node.expires;
+
+	return true;
+}
+
+static const struct drm_crtc_funcs vkms_crtc_funcs = {
+	.set_config             = drm_atomic_helper_set_config,
+	.destroy                = drm_crtc_cleanup,
+	.page_flip              = drm_atomic_helper_page_flip,
+	.reset                  = drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank		= vkms_enable_vblank,
+	.disable_vblank		= vkms_disable_vblank,
+};
+
+static void vkms_crtc_atomic_enable(struct drm_crtc *crtc,
+				    struct drm_crtc_state *old_state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void vkms_crtc_atomic_disable(struct drm_crtc *crtc,
+				     struct drm_crtc_state *old_state)
+{
+	drm_crtc_vblank_off(crtc);
+}
+
+static void vkms_crtc_atomic_flush(struct drm_crtc *crtc,
+				   struct drm_crtc_state *old_crtc_state)
+{
+	unsigned long flags;
+
+	if (crtc->state->event) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+		if (drm_crtc_vblank_get(crtc) != 0)
+			drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		else
+			drm_crtc_arm_vblank_event(crtc, crtc->state->event);
+
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
+		crtc->state->event = NULL;
+	}
+}
+
+static const struct drm_crtc_helper_funcs vkms_crtc_helper_funcs = {
+	.atomic_flush	= vkms_crtc_atomic_flush,
+	.atomic_enable	= vkms_crtc_atomic_enable,
+	.atomic_disable	= vkms_crtc_atomic_disable,
+};
+
+int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+		   struct drm_plane *primary, struct drm_plane *cursor)
+{
+	int ret;
+
+	ret = drm_crtc_init_with_planes(dev, crtc, primary, cursor,
+					&vkms_crtc_funcs, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init CRTC\n");
+		return ret;
+	}
+
+	drm_crtc_helper_add(crtc, &vkms_crtc_helper_funcs);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
new file mode 100644
index 000000000000..37aa2ef33b21
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -0,0 +1,155 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_fb_helper.h>
+#include "vkms_drv.h"
+
+#define DRIVER_NAME	"vkms"
+#define DRIVER_DESC	"Virtual Kernel Mode Setting"
+#define DRIVER_DATE	"20180514"
+#define DRIVER_MAJOR	1
+#define DRIVER_MINOR	0
+
+static struct vkms_device *vkms_device;
+
+static const struct file_operations vkms_driver_fops = {
+	.owner		= THIS_MODULE,
+	.open		= drm_open,
+	.mmap		= drm_gem_mmap,
+	.unlocked_ioctl	= drm_ioctl,
+	.compat_ioctl	= drm_compat_ioctl,
+	.poll		= drm_poll,
+	.read		= drm_read,
+	.llseek		= no_llseek,
+	.release	= drm_release,
+};
+
+static const struct vm_operations_struct vkms_gem_vm_ops = {
+	.fault = vkms_gem_fault,
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+};
+
+static void vkms_release(struct drm_device *dev)
+{
+	struct vkms_device *vkms = container_of(dev, struct vkms_device, drm);
+
+	platform_device_unregister(vkms->platform);
+	drm_mode_config_cleanup(&vkms->drm);
+	drm_dev_fini(&vkms->drm);
+}
+
+static struct drm_driver vkms_driver = {
+	.driver_features	= DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM,
+	.release		= vkms_release,
+	.fops			= &vkms_driver_fops,
+	.dumb_create		= vkms_dumb_create,
+	.dumb_map_offset	= vkms_dumb_map,
+	.gem_vm_ops		= &vkms_gem_vm_ops,
+	.gem_free_object_unlocked = vkms_gem_free_object,
+	.get_vblank_timestamp	= vkms_get_vblank_timestamp,
+
+	.name			= DRIVER_NAME,
+	.desc			= DRIVER_DESC,
+	.date			= DRIVER_DATE,
+	.major			= DRIVER_MAJOR,
+	.minor			= DRIVER_MINOR,
+};
+
+static const struct drm_mode_config_funcs vkms_mode_funcs = {
+	.fb_create = drm_gem_fb_create,
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
+static int vkms_modeset_init(struct vkms_device *vkmsdev)
+{
+	struct drm_device *dev = &vkmsdev->drm;
+
+	drm_mode_config_init(dev);
+	dev->mode_config.funcs = &vkms_mode_funcs;
+	dev->mode_config.min_width = XRES_MIN;
+	dev->mode_config.min_height = YRES_MIN;
+	dev->mode_config.max_width = XRES_MAX;
+	dev->mode_config.max_height = YRES_MAX;
+
+	return vkms_output_init(vkmsdev);
+}
+
+static int __init vkms_init(void)
+{
+	int ret;
+
+	vkms_device = kzalloc(sizeof(*vkms_device), GFP_KERNEL);
+	if (!vkms_device)
+		return -ENOMEM;
+
+	ret = drm_dev_init(&vkms_device->drm, &vkms_driver, NULL);
+	if (ret)
+		goto out_free;
+
+	vkms_device->platform =
+		platform_device_register_simple(DRIVER_NAME, -1, NULL, 0);
+	if (IS_ERR(vkms_device->platform)) {
+		ret = PTR_ERR(vkms_device->platform);
+		goto out_fini;
+	}
+
+	vkms_device->drm.irq_enabled = true;
+
+	ret = drm_vblank_init(&vkms_device->drm, 1);
+	if (ret) {
+		DRM_ERROR("Failed to vblank\n");
+		goto out_fini;
+	}
+
+	ret = vkms_modeset_init(vkms_device);
+	if (ret)
+		goto out_unregister;
+
+	ret = drm_dev_register(&vkms_device->drm, 0);
+	if (ret)
+		goto out_unregister;
+
+	return 0;
+
+out_unregister:
+	platform_device_unregister(vkms_device->platform);
+
+out_fini:
+	drm_dev_fini(&vkms_device->drm);
+
+out_free:
+	kfree(vkms_device);
+	return ret;
+}
+
+static void __exit vkms_exit(void)
+{
+	if (!vkms_device) {
+		DRM_INFO("vkms_device is NULL.\n");
+		return;
+	}
+
+	drm_dev_unregister(&vkms_device->drm);
+	drm_dev_put(&vkms_device->drm);
+
+	kfree(vkms_device);
+}
+
+module_init(vkms_init);
+module_exit(vkms_exit);
+
+MODULE_AUTHOR("Haneen Mohammed <hamohammed.sa@gmail.com>");
+MODULE_AUTHOR("Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>");
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
new file mode 100644
index 000000000000..07be29f2dc44
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -0,0 +1,78 @@
+#ifndef _VKMS_DRV_H_
+#define _VKMS_DRV_H_
+
+#include <drm/drmP.h>
+#include <drm/drm.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_encoder.h>
+#include <linux/hrtimer.h>
+
+#define XRES_MIN    32
+#define YRES_MIN    32
+
+#define XRES_DEF  1024
+#define YRES_DEF   768
+
+#define XRES_MAX  8192
+#define YRES_MAX  8192
+
+static const u32 vkms_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+struct vkms_output {
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+	struct drm_connector connector;
+	struct hrtimer vblank_hrtimer;
+	ktime_t period_ns;
+	struct drm_pending_vblank_event *event;
+};
+
+struct vkms_device {
+	struct drm_device drm;
+	struct platform_device *platform;
+	struct vkms_output output;
+};
+
+struct vkms_gem_object {
+	struct drm_gem_object gem;
+	struct mutex pages_lock; /* Page lock used in page fault handler */
+	struct page **pages;
+};
+
+#define drm_crtc_to_vkms_output(target) \
+	container_of(target, struct vkms_output, crtc)
+
+#define drm_device_to_vkms_device(target) \
+	container_of(target, struct vkms_device, drm)
+
+/* CRTC */
+int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+		   struct drm_plane *primary, struct drm_plane *cursor);
+
+bool vkms_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
+			       int *max_error, ktime_t *vblank_time,
+			       bool in_vblank_irq);
+
+int vkms_output_init(struct vkms_device *vkmsdev);
+
+struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev);
+
+/* Gem stuff */
+struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+				       struct drm_file *file,
+				       u32 *handle,
+				       u64 size);
+
+int vkms_gem_fault(struct vm_fault *vmf);
+
+int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
+		     struct drm_mode_create_dumb *args);
+
+int vkms_dumb_map(struct drm_file *file, struct drm_device *dev,
+		  u32 handle, u64 *offset);
+
+void vkms_gem_free_object(struct drm_gem_object *obj);
+
+#endif /* _VKMS_DRV_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c
new file mode 100644
index 000000000000..c7e38368602b
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_gem.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/shmem_fs.h>
+
+#include "vkms_drv.h"
+
+static struct vkms_gem_object *__vkms_gem_create(struct drm_device *dev,
+						 u64 size)
+{
+	struct vkms_gem_object *obj;
+	int ret;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	size = roundup(size, PAGE_SIZE);
+	ret = drm_gem_object_init(dev, &obj->gem, size);
+	if (ret) {
+		kfree(obj);
+		return ERR_PTR(ret);
+	}
+
+	mutex_init(&obj->pages_lock);
+
+	return obj;
+}
+
+void vkms_gem_free_object(struct drm_gem_object *obj)
+{
+	struct vkms_gem_object *gem = container_of(obj, struct vkms_gem_object,
+						   gem);
+
+	kvfree(gem->pages);
+	mutex_destroy(&gem->pages_lock);
+	drm_gem_object_release(obj);
+	kfree(gem);
+}
+
+int vkms_gem_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vkms_gem_object *obj = vma->vm_private_data;
+	unsigned long vaddr = vmf->address;
+	pgoff_t page_offset;
+	loff_t num_pages;
+	int ret;
+
+	page_offset = (vaddr - vma->vm_start) >> PAGE_SHIFT;
+	num_pages = DIV_ROUND_UP(obj->gem.size, PAGE_SIZE);
+
+	if (page_offset > num_pages)
+		return VM_FAULT_SIGBUS;
+
+	ret = -ENOENT;
+	mutex_lock(&obj->pages_lock);
+	if (obj->pages) {
+		get_page(obj->pages[page_offset]);
+		vmf->page = obj->pages[page_offset];
+		ret = 0;
+	}
+	mutex_unlock(&obj->pages_lock);
+	if (ret) {
+		struct page *page;
+		struct address_space *mapping;
+
+		mapping = file_inode(obj->gem.filp)->i_mapping;
+		page = shmem_read_mapping_page(mapping, page_offset);
+
+		if (!IS_ERR(page)) {
+			vmf->page = page;
+			ret = 0;
+		} else {
+			switch (PTR_ERR(page)) {
+			case -ENOSPC:
+			case -ENOMEM:
+				ret = VM_FAULT_OOM;
+				break;
+			case -EBUSY:
+				ret = VM_FAULT_RETRY;
+				break;
+			case -EFAULT:
+			case -EINVAL:
+				ret = VM_FAULT_SIGBUS;
+				break;
+			default:
+				WARN_ON(PTR_ERR(page));
+				ret = VM_FAULT_SIGBUS;
+				break;
+			}
+		}
+	}
+	return ret;
+}
+
+struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+				       struct drm_file *file,
+				       u32 *handle,
+				       u64 size)
+{
+	struct vkms_gem_object *obj;
+	int ret;
+
+	if (!file || !dev || !handle)
+		return ERR_PTR(-EINVAL);
+
+	obj = __vkms_gem_create(dev, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	ret = drm_gem_handle_create(file, &obj->gem, handle);
+	drm_gem_object_put_unlocked(&obj->gem);
+	if (ret) {
+		drm_gem_object_release(&obj->gem);
+		kfree(obj);
+		return ERR_PTR(ret);
+	}
+
+	return &obj->gem;
+}
+
+int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
+		     struct drm_mode_create_dumb *args)
+{
+	struct drm_gem_object *gem_obj;
+	u64 pitch, size;
+
+	if (!args || !dev || !file)
+		return -EINVAL;
+
+	pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
+	size = pitch * args->height;
+
+	if (!size)
+		return -EINVAL;
+
+	gem_obj = vkms_gem_create(dev, file, &args->handle, size);
+	if (IS_ERR(gem_obj))
+		return PTR_ERR(gem_obj);
+
+	args->size = gem_obj->size;
+	args->pitch = pitch;
+
+	DRM_DEBUG_DRIVER("Created object of size %lld\n", size);
+
+	return 0;
+}
+
+int vkms_dumb_map(struct drm_file *file, struct drm_device *dev,
+		  u32 handle, u64 *offset)
+{
+	struct drm_gem_object *obj;
+	int ret;
+
+	obj = drm_gem_object_lookup(file, handle);
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->filp) {
+		ret = -EINVAL;
+		goto unref;
+	}
+
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto unref;
+
+	*offset = drm_vma_node_offset_addr(&obj->vma_node);
+unref:
+	drm_gem_object_put_unlocked(obj);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c
new file mode 100644
index 000000000000..901012cb1af1
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_output.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic_helper.h>
+
+static void vkms_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vkms_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vkms_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 const struct drm_encoder_funcs vkms_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+static int vkms_conn_get_modes(struct drm_connector *connector)
+{
+	int count;
+
+	count = drm_add_modes_noedid(connector, XRES_MAX, YRES_MAX);
+	drm_set_preferred_mode(connector, XRES_DEF, YRES_DEF);
+
+	return count;
+}
+
+static const struct drm_connector_helper_funcs vkms_conn_helper_funcs = {
+	.get_modes    = vkms_conn_get_modes,
+};
+
+int vkms_output_init(struct vkms_device *vkmsdev)
+{
+	struct vkms_output *output = &vkmsdev->output;
+	struct drm_device *dev = &vkmsdev->drm;
+	struct drm_connector *connector = &output->connector;
+	struct drm_encoder *encoder = &output->encoder;
+	struct drm_crtc *crtc = &output->crtc;
+	struct drm_plane *primary;
+	int ret;
+
+	primary = vkms_plane_init(vkmsdev);
+	if (IS_ERR(primary))
+		return PTR_ERR(primary);
+
+	ret = vkms_crtc_init(dev, crtc, primary, NULL);
+	if (ret)
+		goto err_crtc;
+
+	ret = drm_connector_init(dev, connector, &vkms_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init connector\n");
+		goto err_connector;
+	}
+
+	drm_connector_helper_add(connector, &vkms_conn_helper_funcs);
+
+	ret = drm_connector_register(connector);
+	if (ret) {
+		DRM_ERROR("Failed to register connector\n");
+		goto err_connector_register;
+	}
+
+	ret = drm_encoder_init(dev, encoder, &vkms_encoder_funcs,
+			       DRM_MODE_ENCODER_VIRTUAL, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init encoder\n");
+		goto err_encoder;
+	}
+	encoder->possible_crtcs = 1;
+
+	ret = drm_connector_attach_encoder(connector, encoder);
+	if (ret) {
+		DRM_ERROR("Failed to attach connector to encoder\n");
+		goto err_attach;
+	}
+
+	drm_mode_config_reset(dev);
+
+	return 0;
+
+err_attach:
+	drm_encoder_cleanup(encoder);
+
+err_encoder:
+	drm_connector_unregister(connector);
+
+err_connector_register:
+	drm_connector_cleanup(connector);
+
+err_connector:
+	drm_crtc_cleanup(crtc);
+
+err_crtc:
+	drm_plane_cleanup(primary);
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
new file mode 100644
index 000000000000..9f75b1e2c1c4
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -0,0 +1,57 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_atomic_helper.h>
+
+static const struct drm_plane_funcs vkms_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,
+};
+
+static void vkms_primary_plane_update(struct drm_plane *plane,
+				      struct drm_plane_state *old_state)
+{
+}
+
+static const struct drm_plane_helper_funcs vkms_primary_helper_funcs = {
+	.atomic_update		= vkms_primary_plane_update,
+};
+
+struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev)
+{
+	struct drm_device *dev = &vkmsdev->drm;
+	struct drm_plane *plane;
+	const u32 *formats;
+	int ret, nformats;
+
+	plane = kzalloc(sizeof(*plane), GFP_KERNEL);
+	if (!plane)
+		return ERR_PTR(-ENOMEM);
+
+	formats = vkms_formats;
+	nformats = ARRAY_SIZE(vkms_formats);
+
+	ret = drm_universal_plane_init(dev, plane, 0,
+				       &vkms_plane_funcs,
+				       formats, nformats,
+				       NULL, DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret) {
+		kfree(plane);
+		return ERR_PTR(ret);
+	}
+
+	drm_plane_helper_add(plane, &vkms_primary_helper_funcs);
+
+	return plane;
+}
diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile
index 794cc9d5c9b0..09b2aa08363e 100644
--- a/drivers/gpu/drm/vmwgfx/Makefile
+++ b/drivers/gpu/drm/vmwgfx/Makefile
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \
-	    vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_buffer.o \
+	    vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_ttm_buffer.o \
 	    vmwgfx_fifo.o vmwgfx_irq.o vmwgfx_ldu.o vmwgfx_ttm_glue.o \
 	    vmwgfx_overlay.o vmwgfx_marker.o vmwgfx_gmrid_manager.o \
-	    vmwgfx_fence.o vmwgfx_dmabuf.o vmwgfx_scrn.o vmwgfx_context.o \
+	    vmwgfx_fence.o vmwgfx_bo.o vmwgfx_scrn.o vmwgfx_context.o \
 	    vmwgfx_surface.o vmwgfx_prime.o vmwgfx_mob.o vmwgfx_shader.o \
 	    vmwgfx_cmdbuf_res.o vmwgfx_cmdbuf.o vmwgfx_stdu.o \
 	    vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
index 3bf75978e155..9cbba0e8ce6a 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
@@ -47,10 +47,10 @@
  * the SVGA3D protocol and remain reserved; they should not be used in the
  * future.
  *
- * IDs between 1040 and 1999 (inclusive) are available for use by the
+ * IDs between 1040 and 2999 (inclusive) are available for use by the
  * current SVGA3D protocol.
  *
- * FIFO clients other than SVGA3D should stay below 1000, or at 2000
+ * FIFO clients other than SVGA3D should stay below 1000, or at 3000
  * and up.
  */
 
@@ -90,19 +90,19 @@ typedef enum {
    SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN                     = 1069,
    SVGA_3D_CMD_SURFACE_DEFINE_V2                          = 1070,
    SVGA_3D_CMD_GENERATE_MIPMAPS                           = 1071,
-   SVGA_3D_CMD_VIDEO_CREATE_DECODER                       = 1072,
-   SVGA_3D_CMD_VIDEO_DESTROY_DECODER                      = 1073,
-   SVGA_3D_CMD_VIDEO_CREATE_PROCESSOR                     = 1074,
-   SVGA_3D_CMD_VIDEO_DESTROY_PROCESSOR                    = 1075,
-   SVGA_3D_CMD_VIDEO_DECODE_START_FRAME                   = 1076,
-   SVGA_3D_CMD_VIDEO_DECODE_RENDER                        = 1077,
-   SVGA_3D_CMD_VIDEO_DECODE_END_FRAME                     = 1078,
-   SVGA_3D_CMD_VIDEO_PROCESS_FRAME                        = 1079,
+   SVGA_3D_CMD_DEAD4                                      = 1072,
+   SVGA_3D_CMD_DEAD5                                      = 1073,
+   SVGA_3D_CMD_DEAD6                                      = 1074,
+   SVGA_3D_CMD_DEAD7                                      = 1075,
+   SVGA_3D_CMD_DEAD8                                      = 1076,
+   SVGA_3D_CMD_DEAD9                                      = 1077,
+   SVGA_3D_CMD_DEAD10                                     = 1078,
+   SVGA_3D_CMD_DEAD11                                     = 1079,
    SVGA_3D_CMD_ACTIVATE_SURFACE                           = 1080,
    SVGA_3D_CMD_DEACTIVATE_SURFACE                         = 1081,
    SVGA_3D_CMD_SCREEN_DMA                                 = 1082,
-   SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE                   = 1083,
-   SVGA_3D_CMD_OPEN_CONTEXT_SURFACE                       = 1084,
+   SVGA_3D_CMD_DEAD1                                      = 1083,
+   SVGA_3D_CMD_DEAD2                                      = 1084,
 
    SVGA_3D_CMD_LOGICOPS_BITBLT                            = 1085,
    SVGA_3D_CMD_LOGICOPS_TRANSBLT                          = 1086,
@@ -218,7 +218,7 @@ typedef enum {
    SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW                 = 1177,
    SVGA_3D_CMD_DX_PRED_COPY_REGION                        = 1178,
    SVGA_3D_CMD_DX_PRED_COPY                               = 1179,
-   SVGA_3D_CMD_DX_STRETCHBLT                              = 1180,
+   SVGA_3D_CMD_DX_PRESENTBLT                              = 1180,
    SVGA_3D_CMD_DX_GENMIPS                                 = 1181,
    SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE                      = 1182,
    SVGA_3D_CMD_DX_READBACK_SUBRESOURCE                    = 1183,
@@ -255,7 +255,7 @@ typedef enum {
    SVGA_3D_CMD_DX_READBACK_ALL_QUERY                      = 1214,
    SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER               = 1215,
    SVGA_3D_CMD_DX_MOB_FENCE_64                            = 1216,
-   SVGA_3D_CMD_DX_BIND_SHADER_ON_CONTEXT                  = 1217,
+   SVGA_3D_CMD_DX_BIND_ALL_SHADER                         = 1217,
    SVGA_3D_CMD_DX_HINT                                    = 1218,
    SVGA_3D_CMD_DX_BUFFER_UPDATE                           = 1219,
    SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET           = 1220,
@@ -263,17 +263,47 @@ typedef enum {
    SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET           = 1222,
 
    /*
-    * Reserve some IDs to be used for the DX11 shader types.
+    * Reserve some IDs to be used for the SM5 shader types.
     */
    SVGA_3D_CMD_DX_RESERVED1                               = 1223,
    SVGA_3D_CMD_DX_RESERVED2                               = 1224,
    SVGA_3D_CMD_DX_RESERVED3                               = 1225,
 
-   SVGA_3D_CMD_DX_MAX                                     = 1226,
-   SVGA_3D_CMD_MAX                                        = 1226,
+   SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER                    = 1226,
+   SVGA_3D_CMD_DX_MAX                                     = 1227,
+
+   SVGA_3D_CMD_SCREEN_COPY                                = 1227,
+
+   /*
+    * Reserve some IDs to be used for video.
+    */
+   SVGA_3D_CMD_VIDEO_RESERVED1                            = 1228,
+   SVGA_3D_CMD_VIDEO_RESERVED2                            = 1229,
+   SVGA_3D_CMD_VIDEO_RESERVED3                            = 1230,
+   SVGA_3D_CMD_VIDEO_RESERVED4                            = 1231,
+   SVGA_3D_CMD_VIDEO_RESERVED5                            = 1232,
+   SVGA_3D_CMD_VIDEO_RESERVED6                            = 1233,
+   SVGA_3D_CMD_VIDEO_RESERVED7                            = 1234,
+   SVGA_3D_CMD_VIDEO_RESERVED8                            = 1235,
+
+   SVGA_3D_CMD_GROW_OTABLE                                = 1236,
+   SVGA_3D_CMD_DX_GROW_COTABLE                            = 1237,
+   SVGA_3D_CMD_INTRA_SURFACE_COPY                         = 1238,
+
+   SVGA_3D_CMD_DEFINE_GB_SURFACE_V3                       = 1239,
+
+   SVGA_3D_CMD_DX_RESOLVE_COPY                            = 1240,
+   SVGA_3D_CMD_DX_PRED_RESOLVE_COPY                       = 1241,
+   SVGA_3D_CMD_DX_PRED_CONVERT_REGION                     = 1242,
+   SVGA_3D_CMD_DX_PRED_CONVERT                            = 1243,
+   SVGA_3D_CMD_WHOLE_SURFACE_COPY                         = 1244,
+
+   SVGA_3D_CMD_MAX                                        = 1245,
    SVGA_3D_CMD_FUTURE_MAX                                 = 3000
 } SVGAFifo3dCmdId;
 
+#define SVGA_NUM_3D_CMD (SVGA_3D_CMD_MAX - SVGA_3D_CMD_BASE)
+
 /*
  * FIFO command format definitions:
  */
@@ -302,7 +332,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    uint32                      sid;
-   SVGA3dSurfaceFlags          surfaceFlags;
+   SVGA3dSurface1Flags         surfaceFlags;
    SVGA3dSurfaceFormat         format;
    /*
     * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
@@ -328,7 +358,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    uint32                      sid;
-   SVGA3dSurfaceFlags          surfaceFlags;
+   SVGA3dSurface1Flags         surfaceFlags;
    SVGA3dSurfaceFormat         format;
    /*
     * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
@@ -460,6 +490,28 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdSurfaceCopy;               /* SVGA_3D_CMD_SURFACE_COPY */
 
+/*
+ * Perform a surface copy within the same image.
+ * The src/dest boxes are allowed to overlap.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceImageId  surface;
+   SVGA3dCopyBox box;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdIntraSurfaceCopy;               /* SVGA_3D_CMD_INTRA_SURFACE_COPY */
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 srcSid;
+   uint32 destSid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdWholeSurfaceCopy;               /* SVGA_3D_CMD_WHOLE_SURFACE_COPY */
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -773,6 +825,17 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dVertexElement;
 
+/*
+ * Should the vertex element respect the stream value?  The high bit of the
+ * stream should be set to indicate that the stream should be respected.  If
+ * the high bit is not set, the stream will be ignored and replaced by the index
+ * of the position of the currently considered vertex element.
+ *
+ * All guests should set this bit and correctly specify the stream going
+ * forward.
+ */
+#define SVGA3D_VERTEX_ELEMENT_RESPECT_STREAM (1 << 7)
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1103,8 +1166,6 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdGenerateMipmaps;             /* SVGA_3D_CMD_GENERATE_MIPMAPS */
 
-
-
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1148,38 +1209,6 @@ struct SVGA3dCmdScreenDMA {
 SVGA3dCmdScreenDMA;        /* SVGA_3D_CMD_SCREEN_DMA */
 
 /*
- * Set Unity Surface Cookie
- *
- * Associates the supplied cookie with the surface id for use with
- * Unity.  This cookie is a hint from guest to host, there is no way
- * for the guest to readback the cookie and the host is free to drop
- * the cookie association at will.  The default value for the cookie
- * on all surfaces is 0.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdSetUnitySurfaceCookie {
-   uint32 sid;
-   uint64 cookie;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetUnitySurfaceCookie;   /* SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE */
-
-/*
- * Open a context-specific surface in a non-context-specific manner.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdOpenContextSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdOpenContextSurface;   /* SVGA_3D_CMD_OPEN_CONTEXT_SURFACE */
-
-
-/*
  * Logic ops
  */
 
@@ -1325,7 +1354,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    SVGA3dSurfaceFormat format;
-   SVGA3dSurfaceFlags surfaceFlags;
+   SVGA3dSurface1Flags surface1Flags;
    uint32 numMipLevels;
    uint32 multisampleCount;
    SVGA3dTextureFilter autogenFilter;
@@ -1333,7 +1362,11 @@ struct {
    SVGAMobId mobid;
    uint32 arraySize;
    uint32 mobPitch;
-   uint32 pad[5];
+   SVGA3dSurface2Flags surface2Flags;
+   uint8 multisamplePattern;
+   uint8 qualityLevel;
+   uint8  pad0[2];
+   uint32 pad1[3];
 }
 #include "vmware_pack_end.h"
 SVGAOTableSurfaceEntry;
@@ -1361,7 +1394,8 @@ struct {
 SVGAOTableShaderEntry;
 #define SVGA3D_OTABLE_SHADER_ENTRY_SIZE (sizeof(SVGAOTableShaderEntry))
 
-#define SVGA_STFLAG_PRIMARY (1 << 0)
+#define SVGA_STFLAG_PRIMARY  (1 << 0)
+#define SVGA_STFLAG_RESERVED (1 << 1) /* Added with cap SVGA_CAP_HP_CMD_QUEUE */
 typedef uint32 SVGAScreenTargetFlags;
 
 typedef
@@ -1529,6 +1563,25 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdSetOTableBase64;  /* SVGA_3D_CMD_SET_OTABLE_BASE64 */
 
+/*
+ * Guests using SVGA_3D_CMD_GROW_OTABLE are promising that
+ * the new OTable contains the same contents as the old one, except possibly
+ * for some new invalid entries at the end.
+ *
+ * (Otherwise, guests should use one of the SetOTableBase commands.)
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGAOTableType type;
+   PPN64 baseAddress;
+   uint32 sizeInBytes;
+   uint32 validSizeInBytes;
+   SVGAMobFormat ptDepth;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdGrowOTable;  /* SVGA_3D_CMD_GROW_OTABLE */
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1616,7 +1669,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDefineGBSurface {
    uint32 sid;
-   SVGA3dSurfaceFlags surfaceFlags;
+   SVGA3dSurface1Flags surfaceFlags;
    SVGA3dSurfaceFormat format;
    uint32 numMipLevels;
    uint32 multisampleCount;
@@ -1627,6 +1680,45 @@ struct SVGA3dCmdDefineGBSurface {
 SVGA3dCmdDefineGBSurface;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
 
 /*
+ * Defines a guest-backed surface, adding the arraySize field.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDefineGBSurface_v2 {
+   uint32 sid;
+   SVGA3dSurface1Flags surfaceFlags;
+   SVGA3dSurfaceFormat format;
+   uint32 numMipLevels;
+   uint32 multisampleCount;
+   SVGA3dTextureFilter autogenFilter;
+   SVGA3dSize size;
+   uint32 arraySize;
+   uint32 pad;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
+
+/*
+ * Defines a guest-backed surface, adding the larger flags.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDefineGBSurface_v3 {
+   uint32 sid;
+   SVGA3dSurfaceAllFlags surfaceFlags;
+   SVGA3dSurfaceFormat format;
+   uint32 numMipLevels;
+   uint32 multisampleCount;
+   SVGA3dMSPattern multisamplePattern;
+   SVGA3dMSQualityLevel qualityLevel;
+   SVGA3dTextureFilter autogenFilter;
+   SVGA3dSize size;
+   uint32 arraySize;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDefineGBSurface_v3;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 */
+
+/*
  * Destroy a guest-backed surface.
  */
 
@@ -1673,7 +1765,7 @@ SVGA3dCmdBindGBSurfaceWithPitch;   /* SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH */
 
 typedef
 #include "vmware_pack_begin.h"
-struct{
+struct SVGA3dCmdCondBindGBSurface {
    uint32 sid;
    SVGAMobId testMobid;
    SVGAMobId mobid;
@@ -2067,6 +2159,26 @@ struct {
    uint32 mobOffset;
 }
 #include "vmware_pack_end.h"
-SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE*/
+SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE */
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 stid;
+   SVGA3dSurfaceImageId dest;
+
+   uint32 statusMobId;
+   uint32 statusMobOffset;
+
+   /* Reserved fields */
+   uint32 mustBeInvalidId;
+   uint32 mustBeZero;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdScreenCopy;  /* SVGA_3D_CMD_SCREEN_COPY */
+
+#define SVGA_SCREEN_COPY_STATUS_FAILURE 0x00
+#define SVGA_SCREEN_COPY_STATUS_SUCCESS 0x01
+#define SVGA_SCREEN_COPY_STATUS_INVALID 0xFFFFFFFF
 
 #endif /* _SVGA3D_CMD_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
index e1c0d94cc1e9..f256560049bf 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
@@ -230,9 +230,9 @@ typedef enum {
    SVGA3D_DEVCAP_DEAD2                             = 94,
 
    /*
-    * Does the device support the DX commands?
+    * Does the device support DXContexts?
     */
-   SVGA3D_DEVCAP_DX                                = 95,
+   SVGA3D_DEVCAP_DXCONTEXT                         = 95,
 
    /*
     * What is the maximum size of a texture array?
@@ -242,21 +242,47 @@ typedef enum {
    SVGA3D_DEVCAP_MAX_TEXTURE_ARRAY_SIZE            = 96,
 
    /*
-    * What is the maximum number of vertex buffers that can
-    * be used in the DXContext inputAssembly?
+    * What is the maximum number of vertex buffers or vertex input registers
+    * that can be expected to work correctly with a DXContext?
+    *
+    * The guest is allowed to set up to SVGA3D_DX_MAX_VERTEXBUFFERS, but
+    * anything in excess of this cap is not guaranteed to render correctly.
+    *
+    * Similarly, the guest can set up to SVGA3D_DX_MAX_VERTEXINPUTREGISTERS
+    * input registers without the SVGA3D_DEVCAP_SM4_1 cap, or
+    * SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS with the SVGA3D_DEVCAP_SM4_1,
+    * but only the registers up to this cap value are guaranteed to render
+    * correctly.
+    *
+    * If guest-drivers are able to expose a lower-limit, it's recommended
+    * that they clamp to this value.  Otherwise, the host will make a
+    * best-effort on case-by-case basis if guests exceed this.
     */
    SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS              = 97,
 
    /*
-    * What is the maximum number of constant buffers
-    * that can be expected to work correctly with a
-    * DX context?
+    * What is the maximum number of constant buffers that can be expected to
+    * work correctly with a DX context?
+    *
+    * The guest is allowed to set up to SVGA3D_DX_MAX_CONSTBUFFERS, but
+    * anything in excess of this cap is not guaranteed to render correctly.
+    *
+    * If guest-drivers are able to expose a lower-limit, it's recommended
+    * that they clamp to this value.  Otherwise, the host will make a
+    * best-effort on case-by-case basis if guests exceed this.
     */
    SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS           = 98,
 
    /*
     * Does the device support provoking vertex control?
-    * If zero, the first vertex will always be the provoking vertex.
+    *
+    * If this cap is present, the provokingVertexLast field in the
+    * rasterizer state is enabled.  (Guests can then set it to FALSE,
+    * meaning that the first vertex is the provoking vertex, or TRUE,
+    * meaning that the last verteix is the provoking vertex.)
+    *
+    * If this cap is FALSE, then guests should set the provokingVertexLast
+    * to FALSE, otherwise rendering behavior is undefined.
     */
    SVGA3D_DEVCAP_DX_PROVOKING_VERTEX               = 99,
 
@@ -282,7 +308,7 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_BUMPU8V8                    = 119,
    SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5                  = 120,
    SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8                = 121,
-   SVGA3D_DEVCAP_DXFMT_BUMPL8V8U8                  = 122,
+   SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1                = 122,
    SVGA3D_DEVCAP_DXFMT_ARGB_S10E5                  = 123,
    SVGA3D_DEVCAP_DXFMT_ARGB_S23E8                  = 124,
    SVGA3D_DEVCAP_DXFMT_A2R10G10B10                 = 125,
@@ -321,8 +347,8 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_R32G32_SINT                 = 158,
    SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS           = 159,
    SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT        = 160,
-   SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24_TYPELESS    = 161,
-   SVGA3D_DEVCAP_DXFMT_X32_TYPELESS_G8X24_UINT     = 162,
+   SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24             = 161,
+   SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT              = 162,
    SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS        = 163,
    SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT            = 164,
    SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT             = 165,
@@ -340,8 +366,8 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_R32_SINT                    = 177,
    SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS              = 178,
    SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT           = 179,
-   SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8_TYPELESS       = 180,
-   SVGA3D_DEVCAP_DXFMT_X24_TYPELESS_G8_UINT        = 181,
+   SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8                = 180,
+   SVGA3D_DEVCAP_DXFMT_X24_G8_UINT                 = 181,
    SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS               = 182,
    SVGA3D_DEVCAP_DXFMT_R8G8_UNORM                  = 183,
    SVGA3D_DEVCAP_DXFMT_R8G8_UINT                   = 184,
@@ -405,6 +431,17 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_BC4_UNORM                   = 242,
    SVGA3D_DEVCAP_DXFMT_BC5_UNORM                   = 243,
 
+   /*
+    * Advertises shaderModel 4.1 support, independent blend-states,
+    * cube-map arrays, and a higher vertex input registers limit.
+    *
+    * (See documentation on SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS.)
+    */
+   SVGA3D_DEVCAP_SM41                              = 244,
+
+   SVGA3D_DEVCAP_MULTISAMPLE_2X                    = 245,
+   SVGA3D_DEVCAP_MULTISAMPLE_4X                    = 246,
+
    SVGA3D_DEVCAP_MAX                       /* This must be the last index. */
 } SVGA3dDevCapIndex;
 
@@ -420,9 +457,7 @@ typedef enum {
  * MIPS: Does the format support mip levels?
  * ARRAY: Does the format support texture arrays?
  * VOLUME: Does the format support having volume?
- * MULTISAMPLE_2: Does the format support 2x multisample?
- * MULTISAMPLE_4: Does the format support 4x multisample?
- * MULTISAMPLE_8: Does the format support 8x multisample?
+ * MULTISAMPLE: Does the format support multisample?
  */
 #define SVGA3D_DXFMT_SUPPORTED                (1 <<  0)
 #define SVGA3D_DXFMT_SHADER_SAMPLE            (1 <<  1)
@@ -433,20 +468,8 @@ typedef enum {
 #define SVGA3D_DXFMT_ARRAY                    (1 <<  6)
 #define SVGA3D_DXFMT_VOLUME                   (1 <<  7)
 #define SVGA3D_DXFMT_DX_VERTEX_BUFFER         (1 <<  8)
-#define SVGADX_DXFMT_MULTISAMPLE_2            (1 <<  9)
-#define SVGADX_DXFMT_MULTISAMPLE_4            (1 << 10)
-#define SVGADX_DXFMT_MULTISAMPLE_8            (1 << 11)
-#define SVGADX_DXFMT_MAX                      (1 << 12)
-
-/*
- * Convenience mask for any multisample capability.
- *
- * The multisample bits imply both load and render capability.
- */
-#define SVGA3D_DXFMT_MULTISAMPLE ( \
-           SVGADX_DXFMT_MULTISAMPLE_2 | \
-           SVGADX_DXFMT_MULTISAMPLE_4 | \
-           SVGADX_DXFMT_MULTISAMPLE_8 )
+#define SVGA3D_DXFMT_MULTISAMPLE              (1 <<  9)
+#define SVGA3D_DXFMT_MAX                      (1 << 10)
 
 typedef union {
    Bool   b;
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
index f4606d04556b..7a49c94df221 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
@@ -57,6 +57,16 @@ typedef uint32 SVGA3dInputClassification;
 #define SVGA3D_RESOURCE_TYPE_MAX      7
 typedef uint32 SVGA3dResourceType;
 
+#define SVGA3D_COLOR_WRITE_ENABLE_RED     (1 << 0)
+#define SVGA3D_COLOR_WRITE_ENABLE_GREEN   (1 << 1)
+#define SVGA3D_COLOR_WRITE_ENABLE_BLUE    (1 << 2)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA   (1 << 3)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALL     (SVGA3D_COLOR_WRITE_ENABLE_RED |   \
+                                           SVGA3D_COLOR_WRITE_ENABLE_GREEN | \
+                                           SVGA3D_COLOR_WRITE_ENABLE_BLUE |  \
+                                           SVGA3D_COLOR_WRITE_ENABLE_ALPHA)
+typedef uint8 SVGA3dColorWriteEnable;
+
 #define SVGA3D_DEPTH_WRITE_MASK_ZERO   0
 #define SVGA3D_DEPTH_WRITE_MASK_ALL    1
 typedef uint8 SVGA3dDepthWriteMask;
@@ -89,17 +99,28 @@ typedef uint8 SVGA3dCullMode;
 #define SVGA3D_COMPARISON_MAX             9
 typedef uint8 SVGA3dComparisonFunc;
 
+/*
+ * SVGA3D_MULTISAMPLE_RAST_DISABLE disables MSAA for all primitives.
+ * SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE, which is supported in SM41,
+ * disables MSAA for lines only.
+ */
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE        0
+#define SVGA3D_MULTISAMPLE_RAST_ENABLE         1
+#define SVGA3D_MULTISAMPLE_RAST_DX_MAX         1
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE   2
+#define SVGA3D_MULTISAMPLE_RAST_MAX            2
+typedef uint8 SVGA3dMultisampleRastEnable;
+
 #define SVGA3D_DX_MAX_VERTEXBUFFERS 32
+#define SVGA3D_DX_MAX_VERTEXINPUTREGISTERS 16
+#define SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS 32
 #define SVGA3D_DX_MAX_SOTARGETS 4
 #define SVGA3D_DX_MAX_SRVIEWS 128
 #define SVGA3D_DX_MAX_CONSTBUFFERS 16
 #define SVGA3D_DX_MAX_SAMPLERS 16
 
-/* Id limits */
-static const uint32 SVGA3dBlendObjectCountPerContext = 4096;
-static const uint32 SVGA3dDepthStencilObjectCountPerContext = 4096;
+#define SVGA3D_DX_MAX_CONSTBUF_BINDING_SIZE (4096 * 4 * (uint32)sizeof(uint32))
 
-typedef uint32 SVGA3dSurfaceId;
 typedef uint32 SVGA3dShaderResourceViewId;
 typedef uint32 SVGA3dRenderTargetViewId;
 typedef uint32 SVGA3dDepthStencilViewId;
@@ -195,20 +216,6 @@ SVGA3dCmdDXInvalidateContext;   /* SVGA_3D_CMD_DX_INVALIDATE_CONTEXT */
 
 typedef
 #include "vmware_pack_begin.h"
-struct SVGA3dReplyFormatData {
-   uint32 formatSupport;
-   uint32 msaa2xQualityLevels:5;
-   uint32 msaa4xQualityLevels:5;
-   uint32 msaa8xQualityLevels:5;
-   uint32 msaa16xQualityLevels:5;
-   uint32 msaa32xQualityLevels:5;
-   uint32 pad:7;
-}
-#include "vmware_pack_end.h"
-SVGA3dReplyFormatData;
-
-typedef
-#include "vmware_pack_begin.h"
 struct SVGA3dCmdDXSetSingleConstantBuffer {
    uint32 slot;
    SVGA3dShaderType type;
@@ -625,6 +632,28 @@ SVGA3dCmdDXPredCopy; /* SVGA_3D_CMD_DX_PRED_COPY */
 
 typedef
 #include "vmware_pack_begin.h"
+struct SVGA3dCmdDXPredConvertRegion {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dBox destBox;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dBox srcBox;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredConvertRegion; /* SVGA_3D_CMD_DX_PRED_CONVERT_REGION */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXPredConvert {
+   SVGA3dSurfaceId dstSid;
+   SVGA3dSurfaceId srcSid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredConvert; /* SVGA_3D_CMD_DX_PRED_CONVERT */
+
+typedef
+#include "vmware_pack_begin.h"
 struct SVGA3dCmdDXBufferCopy {
    SVGA3dSurfaceId dest;
    SVGA3dSurfaceId src;
@@ -636,23 +665,57 @@ struct SVGA3dCmdDXBufferCopy {
 SVGA3dCmdDXBufferCopy;
 /* SVGA_3D_CMD_DX_BUFFER_COPY */
 
-typedef uint32 SVGA3dDXStretchBltMode;
-#define SVGADX_STRETCHBLT_LINEAR         (1 << 0)
-#define SVGADX_STRETCHBLT_FORCE_SRC_SRGB (1 << 1)
+/*
+ * Perform a surface copy between a multisample, and a non-multisampled
+ * surface.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dSurfaceFormat copyFormat;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXResolveCopy;               /* SVGA_3D_CMD_DX_RESOLVE_COPY */
+
+/*
+ * Perform a predicated surface copy between a multisample, and a
+ * non-multisampled surface.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dSurfaceFormat copyFormat;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredResolveCopy;           /* SVGA_3D_CMD_DX_PRED_RESOLVE_COPY */
+
+typedef uint32 SVGA3dDXPresentBltMode;
+#define SVGADX_PRESENTBLT_LINEAR           (1 << 0)
+#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB   (1 << 1)
+#define SVGADX_PRESENTBLT_FORCE_SRC_XRBIAS (1 << 2)
+#define SVGADX_PRESENTBLT_MODE_MAX         (1 << 3)
 
 typedef
 #include "vmware_pack_begin.h"
-struct SVGA3dCmdDXStretchBlt {
+struct SVGA3dCmdDXPresentBlt {
    SVGA3dSurfaceId srcSid;
    uint32 srcSubResource;
    SVGA3dSurfaceId dstSid;
    uint32 destSubResource;
    SVGA3dBox boxSrc;
    SVGA3dBox boxDest;
-   SVGA3dDXStretchBltMode mode;
+   SVGA3dDXPresentBltMode mode;
 }
 #include "vmware_pack_end.h"
-SVGA3dCmdDXStretchBlt; /* SVGA_3D_CMD_DX_STRETCHBLT */
+SVGA3dCmdDXPresentBlt; /* SVGA_3D_CMD_DX_PRESENTBLT*/
 
 typedef
 #include "vmware_pack_begin.h"
@@ -663,26 +726,6 @@ struct SVGA3dCmdDXGenMips {
 SVGA3dCmdDXGenMips; /* SVGA_3D_CMD_DX_GENMIPS */
 
 /*
- * Defines a resource/DX surface.  Resources share the surfaceId namespace.
- *
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface_v2 {
-   uint32 sid;
-   SVGA3dSurfaceFlags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   uint32 arraySize;
-   uint32 pad;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
-
-/*
  * Update a sub-resource in a guest-backed resource.
  * (Inform the device that the guest-contents have been updated.)
  */
@@ -725,7 +768,8 @@ SVGA3dCmdDXInvalidateSubResource;   /* SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE */
 
 /*
  * Raw byte wise transfer from a buffer surface into another surface
- * of the requested box.
+ * of the requested box.  Supported if 3d is enabled and SVGA_CAP_DX
+ * is set.  This command does not take a context.
  */
 typedef
 #include "vmware_pack_begin.h"
@@ -774,6 +818,93 @@ struct SVGA3dCmdDXSurfaceCopyAndReadback {
 SVGA3dCmdDXSurfaceCopyAndReadback;
 /* SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK */
 
+/*
+ * SVGA_DX_HINT_NONE: Does nothing.
+ *
+ * SVGA_DX_HINT_PREFETCH_OBJECT:
+ * SVGA_DX_HINT_PREEVICT_OBJECT:
+ *      Consumes a SVGAObjectRef, and hints that the host should consider
+ *      fetching/evicting the specified object.
+ *
+ *      An id of SVGA3D_INVALID_ID can be used if the guest isn't sure
+ *      what object was affected.  (For instance, if the guest knows that
+ *      it is about to evict a DXShader, but doesn't know precisely which one,
+ *      the device can still use this to help limit it's search, or track
+ *      how many page-outs have happened.)
+ *
+ * SVGA_DX_HINT_PREFETCH_COBJECT:
+ * SVGA_DX_HINT_PREEVICT_COBJECT:
+ *      Same as the above, except they consume an SVGACObjectRef.
+ */
+typedef uint32 SVGADXHintId;
+#define SVGA_DX_HINT_NONE              0
+#define SVGA_DX_HINT_PREFETCH_OBJECT   1
+#define SVGA_DX_HINT_PREEVICT_OBJECT   2
+#define SVGA_DX_HINT_PREFETCH_COBJECT  3
+#define SVGA_DX_HINT_PREEVICT_COBJECT  4
+#define SVGA_DX_HINT_MAX               5
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGAObjectRef {
+   SVGAOTableType type;
+   uint32 id;
+}
+#include "vmware_pack_end.h"
+SVGAObjectRef;
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGACObjectRef {
+   SVGACOTableType type;
+   uint32 cid;
+   uint32 id;
+}
+#include "vmware_pack_end.h"
+SVGACObjectRef;
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXHint {
+   SVGADXHintId hintId;
+
+   /*
+    * Followed by variable sized data depending on the hintId.
+    */
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXHint;
+/* SVGA_3D_CMD_DX_HINT */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXBufferUpdate {
+   SVGA3dSurfaceId sid;
+   uint32 x;
+   uint32 width;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXBufferUpdate;
+/* SVGA_3D_CMD_DX_BUFFER_UPDATE */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXSetConstantBufferOffset {
+   uint32 slot;
+   uint32 offsetInBytes;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXSetConstantBufferOffset;
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetVSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET */
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetPSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET */
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetGSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET */
+
 
 typedef
 #include "vmware_pack_begin.h"
@@ -790,7 +921,7 @@ struct {
          uint32 firstArraySlice;
          uint32 mipLevels;
          uint32 arraySize;
-      } tex;
+      } tex; /* 1d, 2d, 3d, cube */
       struct {
          uint32 firstElement;
          uint32 numElements;
@@ -845,6 +976,7 @@ struct SVGA3dRenderTargetViewDesc {
       struct {
          uint32 firstElement;
          uint32 numElements;
+         uint32 padding0;
       } buffer;
       struct {
          uint32 mipSlice;
@@ -965,9 +1097,6 @@ SVGA3dInputElementDesc;
 typedef
 #include "vmware_pack_begin.h"
 struct {
-   /*
-    * XXX: How many of these can there be?
-    */
    uint32 elid;
    uint32 numDescs;
    SVGA3dInputElementDesc desc[32];
@@ -1008,7 +1137,7 @@ struct SVGA3dDXBlendStatePerRT {
       uint8 srcBlendAlpha;
       uint8 destBlendAlpha;
       uint8 blendOpAlpha;
-      uint8 renderTargetWriteMask;
+      SVGA3dColorWriteEnable renderTargetWriteMask;
       uint8 logicOpEnable;
       uint8 logicOp;
       uint16 pad0;
@@ -1126,7 +1255,7 @@ struct {
    float slopeScaledDepthBias;
    uint8 depthClipEnable;
    uint8 scissorEnable;
-   uint8 multisampleEnable;
+   SVGA3dMultisampleRastEnable multisampleEnable;
    uint8 antialiasedLineEnable;
    float lineWidth;
    uint8 lineStippleEnable;
@@ -1153,7 +1282,7 @@ struct SVGA3dCmdDXDefineRasterizerState {
    float slopeScaledDepthBias;
    uint8 depthClipEnable;
    uint8 scissorEnable;
-   uint8 multisampleEnable;
+   SVGA3dMultisampleRastEnable multisampleEnable;
    uint8 antialiasedLineEnable;
    float lineWidth;
    uint8 lineStippleEnable;
@@ -1223,21 +1352,6 @@ struct SVGA3dCmdDXDestroySamplerState {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXDestroySamplerState; /* SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE */
 
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dSignatureEntry {
-   uint8 systemValue;
-   uint8 reg;                 /* register is a reserved word */
-   uint16 mask;
-   uint8 registerComponentType;
-   uint8 minPrecision;
-   uint16 pad0;
-}
-#include "vmware_pack_end.h"
-SVGA3dSignatureEntry;
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXDefineShader {
@@ -1255,12 +1369,7 @@ struct SVGACOTableDXShaderEntry {
    uint32 sizeInBytes;
    uint32 offsetInBytes;
    SVGAMobId mobid;
-   uint32 numInputSignatureEntries;
-   uint32 numOutputSignatureEntries;
-
-   uint32 numPatchConstantSignatureEntries;
-
-   uint32 pad;
+   uint32 pad[4];
 }
 #include "vmware_pack_end.h"
 SVGACOTableDXShaderEntry;
@@ -1284,6 +1393,25 @@ struct SVGA3dCmdDXBindShader {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXBindShader;   /* SVGA_3D_CMD_DX_BIND_SHADER */
 
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXBindAllShader {
+   uint32 cid;
+   SVGAMobId mobid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXBindAllShader;   /* SVGA_3D_CMD_DX_BIND_ALL_SHADER */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXCondBindAllShader {
+   uint32 cid;
+   SVGAMobId testMobid;
+   SVGAMobId mobid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXCondBindAllShader;   /* SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER */
+
 /*
  * The maximum number of streamout decl's in each streamout entry.
  */
@@ -1357,7 +1485,6 @@ SVGA3dCmdDXMobFence64;  /* SVGA_3D_CMD_DX_MOB_FENCE_64 */
  *
  * This command allows the guest to bind a mob to a context-object table.
  */
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXSetCOTable {
@@ -1369,6 +1496,26 @@ struct SVGA3dCmdDXSetCOTable {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXSetCOTable; /* SVGA_3D_CMD_DX_SET_COTABLE */
 
+/*
+ * Guests using SVGA_3D_CMD_DX_GROW_COTABLE are promising that
+ * the new COTable contains the same contents as the old one, except possibly
+ * for some new invalid entries at the end.
+ *
+ * If there is an old cotable mob bound, it also has to still be valid.
+ *
+ * (Otherwise, guests should use the DXSetCOTableBase command.)
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXGrowCOTable {
+   uint32 cid;
+   uint32 mobid;
+   SVGACOTableType type;
+   uint32 validSizeInBytes;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXGrowCOTable; /* SVGA_3D_CMD_DX_GROW_COTABLE */
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXReadbackCOTable {
@@ -1472,7 +1619,7 @@ struct SVGADXContextMobFormat {
    SVGA3dQueryId queryID[SVGA3D_MAX_QUERY];
 
    SVGA3dCOTableData cotables[SVGA_COTABLE_MAX];
-   uint32 pad7[381];
+   uint32 pad7[380];
 }
 #include "vmware_pack_end.h"
 SVGADXContextMobFormat;
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
index 8732490d45d5..b22a67f15660 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
@@ -63,7 +63,9 @@
  * Maximum size in dwords of shader text the SVGA device will allow.
  * Currently 8 MB.
  */
-#define SVGA3D_MAX_SHADER_MEMORY  (8 * 1024 * 1024 / sizeof(uint32))
+#define SVGA3D_MAX_SHADER_MEMORY_BYTES (8 * 1024 * 1024)
+#define SVGA3D_MAX_SHADER_MEMORY  (SVGA3D_MAX_SHADER_MEMORY_BYTES / \
+                                   sizeof(uint32))
 
 #define SVGA3D_MAX_CLIP_PLANES    6
 
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
index b45e96309233..f2bfd3d80598 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
@@ -25,189 +25,355 @@
  *
  **************************************************************************/
 
-#include <linux/kernel.h>
-
-#ifdef __KERNEL__
-
-#include <drm/vmwgfx_drm.h>
-#define surf_size_struct struct drm_vmw_size
-
-#else /* __KERNEL__ */
+/*
+ * svga3d_surfacedefs.h --
+ *
+ *      Surface definitions and inlineable utilities for SVGA3d.
+ */
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(_A) (sizeof(_A) / sizeof((_A)[0]))
-#endif /* ARRAY_SIZE */
+#ifndef _SVGA3D_SURFACEDEFS_H_
+#define _SVGA3D_SURFACEDEFS_H_
 
-#define max_t(type, x, y)  ((x) > (y) ? (x) : (y))
-#define surf_size_struct SVGA3dSize
-#define u32 uint32
+#define INCLUDE_ALLOW_USERLEVEL
+#define INCLUDE_ALLOW_MODULE
+#include "includeCheck.h"
 
-#endif /* __KERNEL__ */
+#include <linux/kernel.h>
+#include <drm/vmwgfx_drm.h>
 
 #include "svga3d_reg.h"
 
+#define surf_size_struct struct drm_vmw_size
+
 /*
- * enum svga3d_block_desc describes the active data channels in a block.
- *
- * There can be at-most four active channels in a block:
- *    1. Red, bump W, luminance and depth are stored in the first channel.
- *    2. Green, bump V and stencil are stored in the second channel.
- *    3. Blue and bump U are stored in the third channel.
- *    4. Alpha and bump Q are stored in the fourth channel.
- *
- * Block channels can be used to store compressed and buffer data:
- *    1. For compressed formats, only the data channel is used and its size
- *       is equal to that of a singular block in the compression scheme.
- *    2. For buffer formats, only the data channel is used and its size is
- *       exactly one byte in length.
- *    3. In each case the bit depth represent the size of a singular block.
- *
- * Note: Compressed and IEEE formats do not use the bitMask structure.
+ * enum svga3d_block_desc - describes generic properties about formats.
  */
-
 enum svga3d_block_desc {
-	SVGA3DBLOCKDESC_NONE        = 0,         /* No channels are active */
-	SVGA3DBLOCKDESC_BLUE        = 1 << 0,    /* Block with red channel
-						    data */
-	SVGA3DBLOCKDESC_U           = 1 << 0,    /* Block with bump U channel
-						    data */
-	SVGA3DBLOCKDESC_UV_VIDEO    = 1 << 7,    /* Block with alternating video
-						    U and V */
-	SVGA3DBLOCKDESC_GREEN       = 1 << 1,    /* Block with green channel
-						    data */
-	SVGA3DBLOCKDESC_V           = 1 << 1,    /* Block with bump V channel
-						    data */
-	SVGA3DBLOCKDESC_STENCIL     = 1 << 1,    /* Block with a stencil
-						    channel */
-	SVGA3DBLOCKDESC_RED         = 1 << 2,    /* Block with blue channel
-						    data */
-	SVGA3DBLOCKDESC_W           = 1 << 2,    /* Block with bump W channel
-						    data */
-	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,    /* Block with luminance channel
-						    data */
-	SVGA3DBLOCKDESC_Y           = 1 << 2,    /* Block with video luminance
-						    data */
-	SVGA3DBLOCKDESC_DEPTH       = 1 << 2,    /* Block with depth channel */
-	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,    /* Block with an alpha
-						    channel */
-	SVGA3DBLOCKDESC_Q           = 1 << 3,    /* Block with bump Q channel
-						    data */
-	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,    /* Block stores 1 byte of
-						    data */
-	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,    /* Block stores n bytes of
-						    data depending on the
-						    compression method used */
-	SVGA3DBLOCKDESC_IEEE_FP     = 1 << 6,    /* Block stores data in an IEEE
-						    floating point
-						    representation in
-						    all channels */
-	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 8,    /* Three separate blocks store
-						    data. */
-	SVGA3DBLOCKDESC_U_VIDEO     = 1 << 9,    /* Block with U video data */
-	SVGA3DBLOCKDESC_V_VIDEO     = 1 << 10,   /* Block with V video data */
-	SVGA3DBLOCKDESC_EXP         = 1 << 11,   /* Shared exponent */
-	SVGA3DBLOCKDESC_SRGB        = 1 << 12,   /* Data is in sRGB format */
-	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 13,   /* 2 planes of Y, UV,
-						    e.g., NV12. */
-	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 14,   /* 3 planes of separate
-						    Y, U, V, e.g., YV12. */
-
-	SVGA3DBLOCKDESC_RG         = SVGA3DBLOCKDESC_RED |
-	SVGA3DBLOCKDESC_GREEN,
-	SVGA3DBLOCKDESC_RGB        = SVGA3DBLOCKDESC_RG |
-	SVGA3DBLOCKDESC_BLUE,
-	SVGA3DBLOCKDESC_RGB_SRGB   = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_RGBA       = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_ALPHA,
-	SVGA3DBLOCKDESC_RGBA_SRGB  = SVGA3DBLOCKDESC_RGBA |
-	SVGA3DBLOCKDESC_SRGB,
+	/* Nothing special can be said about this format. */
+	SVGA3DBLOCKDESC_NONE        = 0,
+
+	/* Format contains Blue/U data */
+	SVGA3DBLOCKDESC_BLUE        = 1 << 0,
+	SVGA3DBLOCKDESC_W           = 1 << 0,
+	SVGA3DBLOCKDESC_BUMP_L      = 1 << 0,
+
+	/* Format contains Green/V data */
+	SVGA3DBLOCKDESC_GREEN       = 1 << 1,
+	SVGA3DBLOCKDESC_V           = 1 << 1,
+
+	/* Format contains Red/W/Luminance data */
+	SVGA3DBLOCKDESC_RED         = 1 << 2,
+	SVGA3DBLOCKDESC_U           = 1 << 2,
+	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,
+
+	/* Format contains Alpha/Q data */
+	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,
+	SVGA3DBLOCKDESC_Q           = 1 << 3,
+
+	/* Format is a buffer */
+	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,
+
+	/* Format is compressed */
+	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,
+
+	/* Format uses IEEE floating point */
+	SVGA3DBLOCKDESC_FP          = 1 << 6,
+
+	/* Three separate blocks store data. */
+	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 7,
+
+	/* 2 planes of Y, UV, e.g., NV12. */
+	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 8,
+
+	/* 3 planes of separate Y, U, V, e.g., YV12. */
+	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 9,
+
+	/* Block with a stencil channel */
+	SVGA3DBLOCKDESC_STENCIL     = 1 << 11,
+
+	/* Typeless format */
+	SVGA3DBLOCKDESC_TYPELESS    = 1 << 12,
+
+	/* Channels are signed integers */
+	SVGA3DBLOCKDESC_SINT        = 1 << 13,
+
+	/* Channels are unsigned integers */
+	SVGA3DBLOCKDESC_UINT        = 1 << 14,
+
+	/* Channels are normalized (when sampling) */
+	SVGA3DBLOCKDESC_NORM        = 1 << 15,
+
+	/* Channels are in SRGB */
+	SVGA3DBLOCKDESC_SRGB        = 1 << 16,
+
+	/* Shared exponent */
+	SVGA3DBLOCKDESC_EXP         = 1 << 17,
+
+	/* Format contains color data. */
+	SVGA3DBLOCKDESC_COLOR       = 1 << 18,
+	/* Format contains depth data. */
+	SVGA3DBLOCKDESC_DEPTH       = 1 << 19,
+	/* Format contains bump data. */
+	SVGA3DBLOCKDESC_BUMP        = 1 << 20,
+
+	/* Format contains YUV video data. */
+	SVGA3DBLOCKDESC_YUV_VIDEO   = 1 << 21,
+
+	/* For mixed unsigned/signed formats. */
+	SVGA3DBLOCKDESC_MIXED       = 1 << 22,
+
+	/* For distingushing CxV8U8. */
+	SVGA3DBLOCKDESC_CX          = 1 << 23,
+
+	/* Different compressed format groups. */
+	SVGA3DBLOCKDESC_BC1         = 1 << 24,
+	SVGA3DBLOCKDESC_BC2         = 1 << 25,
+	SVGA3DBLOCKDESC_BC3         = 1 << 26,
+	SVGA3DBLOCKDESC_BC4         = 1 << 27,
+	SVGA3DBLOCKDESC_BC5         = 1 << 28,
+
+	SVGA3DBLOCKDESC_A_UINT    = SVGA3DBLOCKDESC_ALPHA |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_A_UNORM   = SVGA3DBLOCKDESC_A_UINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_UINT    = SVGA3DBLOCKDESC_RED |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_UNORM   = SVGA3DBLOCKDESC_R_UINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_SINT    = SVGA3DBLOCKDESC_RED |
+				    SVGA3DBLOCKDESC_SINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_SNORM   = SVGA3DBLOCKDESC_R_SINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_G_UINT    = SVGA3DBLOCKDESC_GREEN |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UINT    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UNORM   = SVGA3DBLOCKDESC_RG_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RG_SINT    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_SNORM   = SVGA3DBLOCKDESC_RG_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UINT   = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_SINT   = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_UNORM   = SVGA3DBLOCKDESC_RGB_UINT |
+				      SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UNORM_SRGB = SVGA3DBLOCKDESC_RGB_UNORM |
+					 SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_UINT  = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_UNORM = SVGA3DBLOCKDESC_RGBA_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_UNORM_SRGB = SVGA3DBLOCKDESC_RGBA_UNORM |
+					  SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_SINT  = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_SNORM = SVGA3DBLOCKDESC_RGBA_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_FP |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_UV         = SVGA3DBLOCKDESC_U |
-	SVGA3DBLOCKDESC_V,
+				     SVGA3DBLOCKDESC_V |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVL        = SVGA3DBLOCKDESC_UV |
-	SVGA3DBLOCKDESC_LUMINANCE,
+				     SVGA3DBLOCKDESC_BUMP_L |
+				     SVGA3DBLOCKDESC_MIXED |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVW        = SVGA3DBLOCKDESC_UV |
-	SVGA3DBLOCKDESC_W,
+				     SVGA3DBLOCKDESC_W |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVWA       = SVGA3DBLOCKDESC_UVW |
-	SVGA3DBLOCKDESC_ALPHA,
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_MIXED |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVWQ       = SVGA3DBLOCKDESC_U |
-	SVGA3DBLOCKDESC_V |
-	SVGA3DBLOCKDESC_W |
-	SVGA3DBLOCKDESC_Q,
-	SVGA3DBLOCKDESC_LA         = SVGA3DBLOCKDESC_LUMINANCE |
-	SVGA3DBLOCKDESC_ALPHA,
+				     SVGA3DBLOCKDESC_V |
+				     SVGA3DBLOCKDESC_W |
+				     SVGA3DBLOCKDESC_Q |
+				     SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_L_UNORM    = SVGA3DBLOCKDESC_LUMINANCE |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_LA_UNORM   = SVGA3DBLOCKDESC_LUMINANCE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_R_FP       = SVGA3DBLOCKDESC_RED |
-	SVGA3DBLOCKDESC_IEEE_FP,
+				     SVGA3DBLOCKDESC_FP |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_RG_FP      = SVGA3DBLOCKDESC_R_FP |
-	SVGA3DBLOCKDESC_GREEN,
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_RGB_FP     = SVGA3DBLOCKDESC_RG_FP |
-	SVGA3DBLOCKDESC_BLUE,
-	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RGB_FP |
-	SVGA3DBLOCKDESC_ALPHA,
-	SVGA3DBLOCKDESC_DS         = SVGA3DBLOCKDESC_DEPTH |
-	SVGA3DBLOCKDESC_STENCIL,
-	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_UV_VIDEO |
-	SVGA3DBLOCKDESC_Y,
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_AYUV       = SVGA3DBLOCKDESC_ALPHA |
-	SVGA3DBLOCKDESC_Y |
-	SVGA3DBLOCKDESC_U_VIDEO |
-	SVGA3DBLOCKDESC_V_VIDEO,
-	SVGA3DBLOCKDESC_RGBE       = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_EXP,
-	SVGA3DBLOCKDESC_COMPRESSED_SRGB = SVGA3DBLOCKDESC_COMPRESSED |
-	SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_PLANAR_YUV |
-	SVGA3DBLOCKDESC_2PLANAR_YUV,
-	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_PLANAR_YUV |
-	SVGA3DBLOCKDESC_3PLANAR_YUV,
+				     SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_EXP       = SVGA3DBLOCKDESC_RED |
+					SVGA3DBLOCKDESC_GREEN |
+					SVGA3DBLOCKDESC_BLUE |
+					SVGA3DBLOCKDESC_EXP |
+					SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_COMP_TYPELESS = SVGA3DBLOCKDESC_COMPRESSED |
+					SVGA3DBLOCKDESC_TYPELESS,
+	SVGA3DBLOCKDESC_COMP_UNORM = SVGA3DBLOCKDESC_COMPRESSED |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_SNORM = SVGA3DBLOCKDESC_COMPRESSED |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_COMP_UNORM |
+					  SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC1_COMP_TYPELESS = SVGA3DBLOCKDESC_BC1 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM = SVGA3DBLOCKDESC_BC1 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC1_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC2_COMP_TYPELESS = SVGA3DBLOCKDESC_BC2 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM = SVGA3DBLOCKDESC_BC2 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC2_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC3_COMP_TYPELESS = SVGA3DBLOCKDESC_BC3 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM = SVGA3DBLOCKDESC_BC3 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC3_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC4_COMP_TYPELESS = SVGA3DBLOCKDESC_BC4 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC4_COMP_UNORM = SVGA3DBLOCKDESC_BC4 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC4_COMP_SNORM = SVGA3DBLOCKDESC_BC4 |
+					 SVGA3DBLOCKDESC_COMP_SNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_TYPELESS = SVGA3DBLOCKDESC_BC5 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC5_COMP_UNORM = SVGA3DBLOCKDESC_BC5 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_SNORM = SVGA3DBLOCKDESC_BC5 |
+					 SVGA3DBLOCKDESC_COMP_SNORM,
+
+	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_PLANAR_YUV |
+				     SVGA3DBLOCKDESC_2PLANAR_YUV |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_PLANAR_YUV |
+				     SVGA3DBLOCKDESC_3PLANAR_YUV |
+				     SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_DEPTH_UINT = SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DEPTH_UNORM = SVGA3DBLOCKDESC_DEPTH_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DS      =    SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_STENCIL,
+	SVGA3DBLOCKDESC_DS_UINT =    SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_STENCIL |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DS_UNORM =   SVGA3DBLOCKDESC_DS_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DEPTH_FP   = SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_FP,
+
+	SVGA3DBLOCKDESC_UV_UINT    = SVGA3DBLOCKDESC_UV |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_UV_SNORM   = SVGA3DBLOCKDESC_UV |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_UVCX_SNORM = SVGA3DBLOCKDESC_UV_SNORM |
+				     SVGA3DBLOCKDESC_CX,
+	SVGA3DBLOCKDESC_UVWQ_SNORM = SVGA3DBLOCKDESC_UVWQ |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM,
 };
 
-/*
- * SVGA3dSurfaceDesc describes the actual pixel data.
- *
- * This structure provides the following information:
- *    1. Block description.
- *    2. Dimensions of a block in the surface.
- *    3. Size of block in bytes.
- *    4. Bit depth of the pixel data.
- *    5. Channel bit depths and masks (if applicable).
- */
 struct svga3d_channel_def {
 	union {
 		u8 blue;
-		u8 u;
+		u8 w_bump;
+		u8 l_bump;
 		u8 uv_video;
 		u8 u_video;
 	};
 	union {
 		u8 green;
-		u8 v;
 		u8 stencil;
+		u8 v_bump;
 		u8 v_video;
 	};
 	union {
 		u8 red;
-		u8 w;
+		u8 u_bump;
 		u8 luminance;
-		u8 y;
+		u8 y_video;
 		u8 depth;
 		u8 data;
 	};
 	union {
 		u8 alpha;
-		u8 q;
+		u8 q_bump;
 		u8 exp;
 	};
 };
 
+/*
+ * struct svga3d_surface_desc - describes the actual pixel data.
+ *
+ * @format: Format
+ * @block_desc: Block description
+ * @block_size: Dimensions in pixels of a block
+ * @bytes_per_block: Size of block in bytes
+ * @pitch_bytes_per_block: Size of a block in bytes for purposes of pitch
+ * @bit_depth: Channel bit depths
+ * @bit_offset: Channel bit masks (in bits offset from the start of the pointer)
+ */
 struct svga3d_surface_desc {
 	SVGA3dSurfaceFormat format;
 	enum svga3d_block_desc block_desc;
+
 	surf_size_struct block_size;
 	u32 bytes_per_block;
 	u32 pitch_bytes_per_block;
 
-	u32 total_bit_depth;
 	struct svga3d_channel_def bit_depth;
 	struct svga3d_channel_def bit_offset;
 };
@@ -215,729 +381,728 @@ struct svga3d_surface_desc {
 static const struct svga3d_surface_desc svga3d_surface_descs[] = {
    {SVGA3D_FORMAT_INVALID, SVGA3DBLOCKDESC_NONE,
       {1, 1, 1},  0, 0,
-      0, {{0}, {0}, {0}, {0}},
+      {{0}, {0}, {0}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {6}, {5}, {0}},
+      {{5}, {6}, {5}, {0}},
       {{0}, {5}, {11}, {0}}},
 
-   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      15, {{5}, {5}, {5}, {0}},
+      {{5}, {5}, {5}, {0}},
       {{0}, {5}, {10}, {0}}},
 
-   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {5}, {1}},
+      {{5}, {5}, {5}, {1}},
       {{0}, {5}, {10}, {15}}},
 
-   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{4}, {4}, {4}, {4}},
+      {{4}, {4}, {4}, {4}},
       {{0}, {4}, {8}, {12}}},
 
-   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {8}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {1}, {15}, {0}},
-      {{0}, {15}, {0}, {0}}},
+      {{0}, {1}, {15}, {0}},
+      {{0}, {0}, {1}, {0}}},
 
-   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_LUMINANCE,
+   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_L_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA,
-    {1  , 1, 1},  1, 1,
-      8, {{0}, {0}, {4}, {4}},
+   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA_UNORM,
+      {1, 1, 1},  1, 1,
+      {{0}, {0}, {4}, {4}},
       {{0}, {0}, {0}, {4}}},
 
-   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_LUMINANCE,
+   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_L_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA,
+   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {8}, {8}},
+      {{0}, {0}, {8}, {8}},
       {{0}, {0}, {0}, {8}}},
 
-   {SVGA3D_DXT1, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT1, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT2, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT2, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT3, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT3, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT4, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT4, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT5, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT5, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {8}, {8}},
-      {{0}, {0}, {0}, {8}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_BUMPL6V5U5, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {6}, {0}},
-      {{11}, {6}, {0}, {0}}},
+      {{6}, {5}, {5}, {0}},
+      {{10}, {5}, {0}, {0}}},
 
    {SVGA3D_BUMPX8L8V8U8, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
-   {SVGA3D_BUMPL8V8U8, SVGA3DBLOCKDESC_UVL,
+   {SVGA3D_FORMAT_DEAD1, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  3, 3,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
    {SVGA3D_ARGB_S10E5, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_ARGB_S23E8, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
+      {{10}, {10}, {10}, {2}},
       {{0}, {10}, {20}, {30}}},
 
-   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
-      {{24}, {16}, {8}, {0}}},
+      {{8}, {8}, {8}, {8}},
+      {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UVCX_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_X8L8V8U8, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
    {SVGA3D_A2W10V10U10, SVGA3DBLOCKDESC_UVWA,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_ALPHA,
+   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_A_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {0}, {8}},
+      {{0}, {0}, {0}, {8}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R_S10E5, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R_S23E8, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_RG_S10E5, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
    {SVGA3D_RG_S23E8, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
    {SVGA3D_BUFFER, SVGA3DBLOCKDESC_BUFFER,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{16}, {16}, {0}, {0}},
-      {{16}, {0}, {0}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
-      {{0}, {0}, {16}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_UYVY, SVGA3DBLOCKDESC_YUV,
-      {1, 1, 1},  2, 2,
-      16, {{8}, {0}, {8}, {0}},
+      {2, 1, 1},  4, 4,
+      {{8}, {0}, {8}, {0}},
       {{0}, {0}, {8}, {0}}},
 
    {SVGA3D_YUY2, SVGA3DBLOCKDESC_YUV,
-      {1, 1, 1},  2, 2,
-      16, {{8}, {0}, {8}, {0}},
+      {2, 1, 1},  4, 4,
+      {{8}, {0}, {8}, {0}},
       {{8}, {0}, {0}, {0}}},
 
    {SVGA3D_NV12, SVGA3DBLOCKDESC_NV12,
       {2, 2, 1},  6, 2,
-      48, {{0}, {0}, {48}, {0}},
+      {{0}, {0}, {48}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_AYUV, SVGA3DBLOCKDESC_AYUV,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
    {SVGA3D_R32G32B32_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB_UINT,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_UVW,
+   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_RGB_SINT,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {32}, {0}},
+      {{0}, {8}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
    {SVGA3D_D32_FLOAT_S8X24_UINT, SVGA3DBLOCKDESC_DS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {32}, {0}},
+      {{0}, {8}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32_FLOAT_X8X24_TYPELESS, SVGA3DBLOCKDESC_R_FP,
+   {SVGA3D_R32_FLOAT_X8X24, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X32_TYPELESS_G8X24_UINT, SVGA3DBLOCKDESC_GREEN,
+   {SVGA3D_X32_G8X24_UINT, SVGA3DBLOCKDESC_G_UINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {0}, {0}},
+      {{0}, {8}, {0}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
    {SVGA3D_R11G11B10_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
       {1, 1, 1},  4, 4,
-      32, {{10}, {11}, {11}, {0}},
-      {{0}, {10}, {21}, {0}}},
+      {{10}, {11}, {11}, {0}},
+      {{22}, {11}, {0}, {0}}},
 
-   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_SRGB,
+   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_FP,
+   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
+      {{0}, {8}, {24}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
+      {{0}, {8}, {24}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_R24_UNORM_X8_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R24_UNORM_X8, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {24}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X24_TYPELESS_G8_UINT, SVGA3DBLOCKDESC_GREEN,
+   {SVGA3D_X24_G8_UINT, SVGA3DBLOCKDESC_G_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {0}, {0}},
+      {{0}, {8}, {0}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_R_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_R_SNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_P8, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_P8, SVGA3DBLOCKDESC_NONE,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGBE,
+   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGB_EXP,
       {1, 1, 1},  4, 4,
-      32, {{9}, {9}, {9}, {5}},
+      {{9}, {9}, {9}, {5}},
       {{18}, {9}, {0}, {27}}},
 
-   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_RG,
-      {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
+   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_NONE,
+      {2, 1, 1},  4, 4,
+      {{0}, {8}, {8}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_RG,
-      {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_NONE,
+      {2, 1, 1},  4, 4,
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_BC1_COMP_TYPELESS,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_BC2_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_BC3_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_BC4_COMP_TYPELESS,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_ATI1, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_ATI1, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_BC4_COMP_SNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_BC5_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_ATI2, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_ATI2, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_BC5_COMP_SNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+     {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_SRGB,
+   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_SRGB,
+   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {8}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
    {SVGA3D_YV12, SVGA3DBLOCKDESC_YV12,
       {2, 2, 1},  6, 2,
-      48, {{0}, {0}, {48}, {0}},
+      {{0}, {0}, {48}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R32G32B32A32_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
    {SVGA3D_R16G16B16A16_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_R32G32_FLOAT, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
-      {{24}, {16}, {8}, {0}}},
+      {{8}, {8}, {8}, {8}},
+      {{16}, {8}, {0}, {24}}},
 
    {SVGA3D_R16G16_FLOAT, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
-      {{0}, {0}, {16}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{16}, {16}, {0}, {0}},
-      {{16}, {0}, {0}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
    {SVGA3D_R32_FLOAT, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_R16_FLOAT, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_ALPHA,
+   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_A_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {0}, {8}},
+      {{0}, {0}, {0}, {8}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {6}, {5}, {0}},
+      {{5}, {6}, {5}, {0}},
       {{0}, {5}, {11}, {0}}},
 
-   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {5}, {1}},
+      {{5}, {5}, {5}, {1}},
       {{0}, {5}, {10}, {15}}},
 
-   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
-
 };
 
 static inline u32 clamped_umul32(u32 a, u32 b)
@@ -946,6 +1111,10 @@ static inline u32 clamped_umul32(u32 a, u32 b)
 	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
 }
 
+/**
+ * svga3dsurface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the
+ * given format.
+ */
 static inline const struct svga3d_surface_desc *
 svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
 {
@@ -955,23 +1124,10 @@ svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
 	return &svga3d_surface_descs[SVGA3D_FORMAT_INVALID];
 }
 
-/*
- *----------------------------------------------------------------------
- *
- * svga3dsurface_get_mip_size --
- *
- *      Given a base level size and the mip level, compute the size of
- *      the mip level.
- *
- * Results:
- *      See above.
- *
- * Side effects:
- *      None.
- *
- *----------------------------------------------------------------------
+/**
+ * svga3dsurface_get_mip_size -  Given a base level size and the mip level,
+ * compute the size of the mip level.
  */
-
 static inline surf_size_struct
 svga3dsurface_get_mip_size(surf_size_struct base_level, u32 mip_level)
 {
@@ -1018,28 +1174,17 @@ svga3dsurface_calculate_pitch(const struct svga3d_surface_desc *desc,
 	return pitch;
 }
 
-/*
- *-----------------------------------------------------------------------------
- *
- * svga3dsurface_get_image_buffer_size --
- *
- *      Return the number of bytes of buffer space required to store
- *      one image of a surface, optionally using the specified pitch.
- *
- *      If pitch is zero, it is assumed that rows are tightly packed.
+/**
+ * svga3dsurface_get_image_buffer_size - Calculates image buffer size.
  *
- *      This function is overflow-safe. If the result would have
- *      overflowed, instead we return MAX_UINT32.
+ * Return the number of bytes of buffer space required to store one image of a
+ * surface, optionally using the specified pitch.
  *
- * Results:
- *      Byte count.
+ * If pitch is zero, it is assumed that rows are tightly packed.
  *
- * Side effects:
- *      None.
- *
- *-----------------------------------------------------------------------------
+ * This function is overflow-safe. If the result would have overflowed, instead
+ * we return MAX_UINT32.
  */
-
 static inline u32
 svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
 				    const surf_size_struct *size,
@@ -1067,6 +1212,9 @@ svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
 	return total_size;
 }
 
+/**
+ * svga3dsurface_get_serialized_size - Get the serialized size for the image.
+ */
 static inline u32
 svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
 				  surf_size_struct base_level_size,
@@ -1087,6 +1235,26 @@ svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
 	return total_size * num_layers;
 }
 
+/**
+ * svga3dsurface_get_serialized_size_extended - Returns the number of bytes
+ * required for a surface with given parameters. Support for sample count.
+ */
+static inline u32
+svga3dsurface_get_serialized_size_extended(SVGA3dSurfaceFormat format,
+					   surf_size_struct base_level_size,
+					   u32 num_mip_levels,
+					   u32 num_layers,
+					   u32 num_samples)
+{
+	uint64_t total_size =
+		svga3dsurface_get_serialized_size(format,
+						  base_level_size,
+						  num_mip_levels,
+						  num_layers);
+	total_size *= max_t(u32, 1, num_samples);
+
+	return min_t(uint64_t, total_size, (uint64_t)U32_MAX);
+}
 
 /**
  * svga3dsurface_get_pixel_offset - Compute the offset (in bytes) to a pixel
@@ -1206,3 +1374,5 @@ svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format)
 	}
 	return svga3dsurface_is_dx_screen_target_format(format);
 }
+
+#endif /* _SVGA3D_SURFACEDEFS_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
index df63f24c2e10..308370665a8e 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
@@ -45,9 +45,21 @@
 
 #define SVGA3D_INVALID_ID         ((uint32)-1)
 
+typedef uint8 SVGABool8;   /* 8-bit Bool definition */
 typedef uint32 SVGA3dBool; /* 32-bit Bool definition */
 typedef uint32 SVGA3dColor; /* a, r, g, b */
 
+typedef uint32 SVGA3dSurfaceId;
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 numerator;
+   uint32 denominator;
+}
+#include "vmware_pack_end.h"
+SVGA3dFraction64;
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCopyRect {
@@ -146,7 +158,7 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_BUMPU8V8                     = 20,
    SVGA3D_BUMPL6V5U5                   = 21,
    SVGA3D_BUMPX8L8V8U8                 = 22,
-   SVGA3D_BUMPL8V8U8                   = 23,
+   SVGA3D_FORMAT_DEAD1                 = 23,
 
    SVGA3D_ARGB_S10E5                   = 24,   /* 16-bit floating-point ARGB */
    SVGA3D_ARGB_S23E8                   = 25,   /* 32-bit floating-point ARGB */
@@ -205,8 +217,8 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_R32G32_SINT                  = 59,
    SVGA3D_R32G8X24_TYPELESS            = 60,
    SVGA3D_D32_FLOAT_S8X24_UINT         = 61,
-   SVGA3D_R32_FLOAT_X8X24_TYPELESS     = 62,
-   SVGA3D_X32_TYPELESS_G8X24_UINT      = 63,
+   SVGA3D_R32_FLOAT_X8X24              = 62,
+   SVGA3D_X32_G8X24_UINT               = 63,
    SVGA3D_R10G10B10A2_TYPELESS         = 64,
    SVGA3D_R10G10B10A2_UINT             = 65,
    SVGA3D_R11G11B10_FLOAT              = 66,
@@ -224,8 +236,8 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_R32_SINT                     = 78,
    SVGA3D_R24G8_TYPELESS               = 79,
    SVGA3D_D24_UNORM_S8_UINT            = 80,
-   SVGA3D_R24_UNORM_X8_TYPELESS        = 81,
-   SVGA3D_X24_TYPELESS_G8_UINT         = 82,
+   SVGA3D_R24_UNORM_X8                 = 81,
+   SVGA3D_X24_G8_UINT                  = 82,
    SVGA3D_R8G8_TYPELESS                = 83,
    SVGA3D_R8G8_UNORM                   = 84,
    SVGA3D_R8G8_UINT                    = 85,
@@ -297,92 +309,114 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_FORMAT_MAX
 } SVGA3dSurfaceFormat;
 
-typedef enum SVGA3dSurfaceFlags {
-   SVGA3D_SURFACE_CUBEMAP               = (1 << 0),
+/*
+ * SVGA3d Surface Flags --
+ */
+#define SVGA3D_SURFACE_CUBEMAP                (1 << 0)
 
-   /*
-    * HINT flags are not enforced by the device but are useful for
-    * performance.
-    */
-   SVGA3D_SURFACE_HINT_STATIC           = (1 << 1),
-   SVGA3D_SURFACE_HINT_DYNAMIC          = (1 << 2),
-   SVGA3D_SURFACE_HINT_INDEXBUFFER      = (1 << 3),
-   SVGA3D_SURFACE_HINT_VERTEXBUFFER     = (1 << 4),
-   SVGA3D_SURFACE_HINT_TEXTURE          = (1 << 5),
-   SVGA3D_SURFACE_HINT_RENDERTARGET     = (1 << 6),
-   SVGA3D_SURFACE_HINT_DEPTHSTENCIL     = (1 << 7),
-   SVGA3D_SURFACE_HINT_WRITEONLY        = (1 << 8),
-   SVGA3D_SURFACE_MASKABLE_ANTIALIAS    = (1 << 9),
-   SVGA3D_SURFACE_AUTOGENMIPMAPS        = (1 << 10),
-   SVGA3D_SURFACE_DECODE_RENDERTARGET   = (1 << 11),
+/*
+ * HINT flags are not enforced by the device but are useful for
+ * performance.
+ */
+#define SVGA3D_SURFACE_HINT_STATIC            (CONST64U(1) << 1)
+#define SVGA3D_SURFACE_HINT_DYNAMIC           (CONST64U(1) << 2)
+#define SVGA3D_SURFACE_HINT_INDEXBUFFER       (CONST64U(1) << 3)
+#define SVGA3D_SURFACE_HINT_VERTEXBUFFER      (CONST64U(1) << 4)
+#define SVGA3D_SURFACE_HINT_TEXTURE           (CONST64U(1) << 5)
+#define SVGA3D_SURFACE_HINT_RENDERTARGET      (CONST64U(1) << 6)
+#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL      (CONST64U(1) << 7)
+#define SVGA3D_SURFACE_HINT_WRITEONLY         (CONST64U(1) << 8)
+#define SVGA3D_SURFACE_MASKABLE_ANTIALIAS     (CONST64U(1) << 9)
+#define SVGA3D_SURFACE_AUTOGENMIPMAPS         (CONST64U(1) << 10)
+
+#define SVGA3D_SURFACE_DECODE_RENDERTARGET    (CONST64U(1) << 11)
 
-   /*
-    * Is this surface using a base-level pitch for it's mob backing?
-    *
-    * This flag is not intended to be set by guest-drivers, but is instead
-    * set by the device when the surface is bound to a mob with a specified
-    * pitch.
-    */
-   SVGA3D_SURFACE_MOB_PITCH             = (1 << 12),
+/*
+ * Is this surface using a base-level pitch for it's mob backing?
+ *
+ * This flag is not intended to be set by guest-drivers, but is instead
+ * set by the device when the surface is bound to a mob with a specified
+ * pitch.
+ */
+#define SVGA3D_SURFACE_MOB_PITCH              (CONST64U(1) << 12)
 
-   SVGA3D_SURFACE_INACTIVE              = (1 << 13),
-   SVGA3D_SURFACE_HINT_RT_LOCKABLE      = (1 << 14),
-   SVGA3D_SURFACE_VOLUME                = (1 << 15),
+#define SVGA3D_SURFACE_INACTIVE               (CONST64U(1) << 13)
+#define SVGA3D_SURFACE_HINT_RT_LOCKABLE       (CONST64U(1) << 14)
+#define SVGA3D_SURFACE_VOLUME                 (CONST64U(1) << 15)
 
-   /*
-    * Required to be set on a surface to bind it to a screen target.
-    */
-   SVGA3D_SURFACE_SCREENTARGET          = (1 << 16),
+/*
+ * Required to be set on a surface to bind it to a screen target.
+ */
+#define SVGA3D_SURFACE_SCREENTARGET           (CONST64U(1) << 16)
 
-   /*
-    * Align images in the guest-backing mob to 16-bytes.
-    */
-   SVGA3D_SURFACE_ALIGN16               = (1 << 17),
+/*
+ * Align images in the guest-backing mob to 16-bytes.
+ */
+#define SVGA3D_SURFACE_ALIGN16                (CONST64U(1) << 17)
 
-   SVGA3D_SURFACE_1D                    = (1 << 18),
-   SVGA3D_SURFACE_ARRAY                 = (1 << 19),
+#define SVGA3D_SURFACE_1D                     (CONST64U(1) << 18)
+#define SVGA3D_SURFACE_ARRAY                  (CONST64U(1) << 19)
 
-   /*
-    * Bind flags.
-    * These are enforced for any surface defined with DefineGBSurface_v2.
-    */
-   SVGA3D_SURFACE_BIND_VERTEX_BUFFER    = (1 << 20),
-   SVGA3D_SURFACE_BIND_INDEX_BUFFER     = (1 << 21),
-   SVGA3D_SURFACE_BIND_CONSTANT_BUFFER  = (1 << 22),
-   SVGA3D_SURFACE_BIND_SHADER_RESOURCE  = (1 << 23),
-   SVGA3D_SURFACE_BIND_RENDER_TARGET    = (1 << 24),
-   SVGA3D_SURFACE_BIND_DEPTH_STENCIL    = (1 << 25),
-   SVGA3D_SURFACE_BIND_STREAM_OUTPUT    = (1 << 26),
+/*
+ * Bind flags.
+ * These are enforced for any surface defined with DefineGBSurface_v2.
+ */
+#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER     (CONST64U(1) << 20)
+#define SVGA3D_SURFACE_BIND_INDEX_BUFFER      (CONST64U(1) << 21)
+#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER   (CONST64U(1) << 22)
+#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE   (CONST64U(1) << 23)
+#define SVGA3D_SURFACE_BIND_RENDER_TARGET     (CONST64U(1) << 24)
+#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL     (CONST64U(1) << 25)
+#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT     (CONST64U(1) << 26)
 
-   /*
-    * A note on staging flags:
-    *
-    * The STAGING flags notes that the surface will not be used directly by the
-    * drawing pipeline, i.e. that it will not be bound to any bind point.
-    * Staging surfaces may be used by copy operations to move data in and out
-    * of other surfaces.
-    *
-    * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
-    * updates indirectly, i.e. the surface will not be updated directly, but
-    * will receive copies from staging surfaces.
-    */
-   SVGA3D_SURFACE_STAGING_UPLOAD        = (1 << 27),
-   SVGA3D_SURFACE_STAGING_DOWNLOAD      = (1 << 28),
-   SVGA3D_SURFACE_HINT_INDIRECT_UPDATE  = (1 << 29),
+/*
+ * The STAGING flags notes that the surface will not be used directly by the
+ * drawing pipeline, i.e. that it will not be bound to any bind point.
+ * Staging surfaces may be used by copy operations to move data in and out
+ * of other surfaces.  No bind flags may be set on surfaces with this flag.
+ *
+ * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
+ * updates indirectly, i.e. the surface will not be updated directly, but
+ * will receive copies from staging surfaces.
+ */
+#define SVGA3D_SURFACE_STAGING_UPLOAD         (CONST64U(1) << 27)
+#define SVGA3D_SURFACE_STAGING_DOWNLOAD       (CONST64U(1) << 28)
+#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE   (CONST64U(1) << 29)
 
-   /*
-    * Setting this flag allow this surface to be used with the
-    * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
-    * buffer surfaces, an no bind flags are allowed to be set on surfaces
-    * with this flag.
-    */
-   SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  = (1 << 30),
+/*
+ * Setting this flag allow this surface to be used with the
+ * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
+ * buffer surfaces, and no bind flags are allowed to be set on surfaces
+ * with this flag.
+ */
+#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   (CONST64U(1) << 30)
 
-   /*
-    * Marker for the last defined bit.
-    */
-   SVGA3D_SURFACE_FLAG_MAX              = (1 << 31),
-} SVGA3dSurfaceFlags;
+/*
+ * Reserved for video operations.
+ */
+#define SVGA3D_SURFACE_RESERVED1              (CONST64U(1) << 31)
+
+/*
+ * Specifies that a surface is multisample, and therefore requires the full
+ * mob-backing to store all the samples.
+ */
+#define SVGA3D_SURFACE_MULTISAMPLE            (CONST64U(1) << 32)
+
+#define SVGA3D_SURFACE_FLAG_MAX               (CONST64U(1) << 33)
+
+/*
+ * Surface flags types:
+ *
+ * SVGA3dSurface1Flags:  Lower 32-bits of flags.
+ * SVGA3dSurface2Flags:  Upper 32-bits of flags.
+ * SVGA3dSurfaceAllFlags: Full 64-bits of flags.
+ */
+typedef uint32 SVGA3dSurface1Flags;
+typedef uint32 SVGA3dSurface2Flags;
+typedef uint64 SVGA3dSurfaceAllFlags;
+
+#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64_t)MAX_UINT32)
+#define SVGA3D_SURFACE_FLAGS2_MASK (MAX_UINT64 & ~SVGA3D_SURFACE_FLAGS1_MASK)
 
 #define SVGA3D_SURFACE_HB_DISALLOWED_MASK        \
         (  SVGA3D_SURFACE_MOB_PITCH    |         \
@@ -393,29 +427,41 @@ typedef enum SVGA3dSurfaceFlags {
            SVGA3D_SURFACE_STAGING_UPLOAD |       \
            SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
            SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \
+           SVGA3D_SURFACE_MULTISAMPLE            \
+        )
+
+#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK   \
+       (   SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MULTISAMPLE               \
         )
 
 #define SVGA3D_SURFACE_2D_DISALLOWED_MASK           \
         (  SVGA3D_SURFACE_CUBEMAP |                 \
            SVGA3D_SURFACE_MASKABLE_ANTIALIAS |      \
            SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_DECODE_RENDERTARGET |     \
            SVGA3D_SURFACE_VOLUME |                  \
            SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_ARRAY |                   \
            SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
            SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
            SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
            SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
            SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER      \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
+           SVGA3D_SURFACE_MULTISAMPLE               \
+        )
+
+#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK     \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MULTISAMPLE               \
         )
 
 #define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK \
         (  SVGA3D_SURFACE_CUBEMAP |                 \
            SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_DECODE_RENDERTARGET |     \
            SVGA3D_SURFACE_VOLUME |                  \
            SVGA3D_SURFACE_1D |                      \
            SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
@@ -427,12 +473,36 @@ typedef enum SVGA3dSurfaceFlags {
            SVGA3D_SURFACE_STAGING_UPLOAD |          \
            SVGA3D_SURFACE_STAGING_DOWNLOAD |        \
            SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |    \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER      \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
+           SVGA3D_SURFACE_MULTISAMPLE               \
+        )
+
+#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK       \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MASKABLE_ANTIALIAS |      \
+           SVGA3D_SURFACE_ARRAY |                   \
+           SVGA3D_SURFACE_MULTISAMPLE |             \
+           SVGA3D_SURFACE_MOB_PITCH                 \
+        )
+
+#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK  \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_SCREENTARGET |            \
+           SVGA3D_SURFACE_MOB_PITCH                 \
         )
 
 #define SVGA3D_SURFACE_DX_ONLY_MASK             \
         (  SVGA3D_SURFACE_BIND_STREAM_OUTPUT |  \
+           SVGA3D_SURFACE_STAGING_UPLOAD |      \
+           SVGA3D_SURFACE_STAGING_DOWNLOAD |    \
            SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  \
+        )
 
 #define SVGA3D_SURFACE_STAGING_MASK             \
         (  SVGA3D_SURFACE_STAGING_UPLOAD |      \
@@ -488,7 +558,7 @@ typedef enum {
 
 /*
  * Indicates that this format can be converted to any RGB format for which
- * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified
+ * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified.
  */
    SVGA3DFORMAT_OP_CONVERT_TO_ARGB                       = 0x00002000,
 
@@ -499,22 +569,22 @@ typedef enum {
 
 /*
  * Indicated that this format can be read as an SRGB texture (meaning that the
- * sampler will linearize the looked up data)
+ * sampler will linearize the looked up data).
  */
    SVGA3DFORMAT_OP_SRGBREAD                              = 0x00008000,
 
 /*
- * Indicates that this format can be used in the bumpmap instructions
+ * Indicates that this format can be used in the bumpmap instructions.
  */
    SVGA3DFORMAT_OP_BUMPMAP                               = 0x00010000,
 
 /*
- * Indicates that this format can be sampled by the displacement map sampler
+ * Indicates that this format can be sampled by the displacement map sampler.
  */
    SVGA3DFORMAT_OP_DMAP                                  = 0x00020000,
 
 /*
- * Indicates that this format cannot be used with texture filtering
+ * Indicates that this format cannot be used with texture filtering.
  */
    SVGA3DFORMAT_OP_NOFILTER                              = 0x00040000,
 
@@ -531,18 +601,18 @@ typedef enum {
    SVGA3DFORMAT_OP_SRGBWRITE                             = 0x00100000,
 
 /*
- * Indicates that this format cannot be used with alpha blending
+ * Indicates that this format cannot be used with alpha blending.
  */
    SVGA3DFORMAT_OP_NOALPHABLEND                          = 0x00200000,
 
 /*
  * Indicates that the device can auto-generated sublevels for resources
- * of this format
+ * of this format.
  */
    SVGA3DFORMAT_OP_AUTOGENMIPMAP                         = 0x00400000,
 
 /*
- * Indicates that this format can be used by vertex texture sampler
+ * Indicates that this format can be used by vertex texture sampler.
  */
    SVGA3DFORMAT_OP_VERTEXTEXTURE                         = 0x00800000,
 
@@ -1502,7 +1572,6 @@ union SVGADXQueryResultUnion {
 #include "vmware_pack_end.h"
 SVGADXQueryResultUnion;
 
-
 typedef enum {
    SVGA3D_QUERYSTATE_PENDING     = 0,      /* Query is not finished yet */
    SVGA3D_QUERYSTATE_SUCCEEDED   = 1,      /* Completed successfully */
@@ -1534,9 +1603,9 @@ typedef
 struct {
    union {
       struct {
-	 uint16  function;       /* SVGA3dFogFunction */
-	 uint8   type;           /* SVGA3dFogType */
-	 uint8   base;           /* SVGA3dFogBase */
+         uint16  function;       /* SVGA3dFogFunction */
+         uint8   type;           /* SVGA3dFogType */
+         uint8   base;           /* SVGA3dFogBase */
       };
       uint32     uintValue;
    };
@@ -1548,19 +1617,27 @@ SVGA3dFogMode;
  * Uniquely identify one image (a 1D/2D/3D array) from a surface. This
  * is a surface ID as well as face/mipmap indices.
  */
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dSurfaceImageId {
-   uint32               sid;
-   uint32               face;
-   uint32               mipmap;
+   uint32 sid;
+   uint32 face;
+   uint32 mipmap;
 }
 #include "vmware_pack_end.h"
 SVGA3dSurfaceImageId;
 
 typedef
 #include "vmware_pack_begin.h"
+struct SVGA3dSubSurfaceId {
+   uint32 sid;
+   uint32 subResourceId;
+}
+#include "vmware_pack_end.h"
+SVGA3dSubSurfaceId;
+
+typedef
+#include "vmware_pack_begin.h"
 struct {
    uint32               width;
    uint32               height;
@@ -1583,13 +1660,18 @@ typedef enum {
    SVGA_OTABLE_DX9_MAX         = 5,
 
    SVGA_OTABLE_DXCONTEXT       = 5,
-   SVGA_OTABLE_MAX             = 6
-} SVGAOTableType;
+   SVGA_OTABLE_DX_MAX          = 6,
 
-/*
- * Deprecated.
- */
-#define SVGA_OTABLE_COUNT 4
+   SVGA_OTABLE_RESERVED1       = 6,
+   SVGA_OTABLE_RESERVED2       = 7,
+
+   /*
+    * Additions to this table need to be tied to HW-version features and
+    * checkpointed accordingly.
+    */
+   SVGA_OTABLE_DEVEL_MAX       = 8,
+   SVGA_OTABLE_MAX             = 8
+} SVGAOTableType;
 
 typedef enum {
    SVGA_COTABLE_MIN             = 0,
@@ -1606,7 +1688,7 @@ typedef enum {
    SVGA_COTABLE_DXSHADER        = 10,
    SVGA_COTABLE_DX10_MAX        = 11,
    SVGA_COTABLE_UAVIEW          = 11,
-   SVGA_COTABLE_MAX
+   SVGA_COTABLE_MAX             = 12,
 } SVGACOTableType;
 
 /*
@@ -1627,8 +1709,37 @@ typedef enum SVGAMobFormat {
    SVGA3D_MOBFMT_PREDX_MAX   = 7,
    SVGA3D_MOBFMT_EMPTY       = 7,
    SVGA3D_MOBFMT_MAX,
+
+   /*
+    * This isn't actually used by the guest, but is a mob-format used
+    * internally by the SVGA device (and is therefore not binary compatible).
+    */
+   SVGA3D_MOBFMT_HB,
 } SVGAMobFormat;
 
 #define SVGA3D_MOB_EMPTY_BASE 1
 
+/*
+ * Multisample pattern types.
+ */
+
+typedef enum SVGA3dMSPattern {
+   SVGA3D_MS_PATTERN_NONE     = 0,
+   SVGA3D_MS_PATTERN_MIN      = 0,
+   SVGA3D_MS_PATTERN_STANDARD = 1,
+   SVGA3D_MS_PATTERN_CENTER   = 2,
+   SVGA3D_MS_PATTERN_MAX      = 3,
+} SVGA3dMSPattern;
+
+/*
+ * Precision settings for each sample.
+ */
+
+typedef enum SVGA3dMSQualityLevel {
+   SVGA3D_MS_QUALITY_NONE = 0,
+   SVGA3D_MS_QUALITY_MIN  = 0,
+   SVGA3D_MS_QUALITY_FULL = 1,
+   SVGA3D_MS_QUALITY_MAX  = 2,
+} SVGA3dMSQualityLevel;
+
 #endif /* _SVGA3D_TYPES_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
index 847e3301c478..056f54b35d73 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
@@ -64,16 +64,26 @@ typedef uint32 SVGAMobId;
 #define SVGA_MAX_BITS_PER_PIXEL         32
 #define SVGA_MAX_DEPTH                  24
 #define SVGA_MAX_DISPLAYS               10
+#define SVGA_MAX_SCREEN_SIZE            8192
+#define SVGA_SCREEN_ROOT_LIMIT (SVGA_MAX_SCREEN_SIZE * SVGA_MAX_DISPLAYS)
+
 
 /*
  * Legal values for the SVGA_REG_CURSOR_ON register in old-fashioned
  * cursor bypass mode. This is still supported, but no new guest
  * drivers should use it.
  */
-#define SVGA_CURSOR_ON_HIDE            0x0   /* Must be 0 to maintain backward compatibility */
-#define SVGA_CURSOR_ON_SHOW            0x1   /* Must be 1 to maintain backward compatibility */
-#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2   /* Remove the cursor from the framebuffer because we need to see what's under it */
-#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3   /* Put the cursor back in the framebuffer so the user can see it */
+#define SVGA_CURSOR_ON_HIDE            0x0
+#define SVGA_CURSOR_ON_SHOW            0x1
+
+/*
+ * Remove the cursor from the framebuffer
+ * because we need to see what's under it
+ */
+#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2
+
+/* Put the cursor back in the framebuffer so the user can see it */
+#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3
 
 /*
  * The maximum framebuffer size that can traced for guests unless the
@@ -102,7 +112,10 @@ typedef uint32 SVGAMobId;
 #define SVGA_VERSION_0     0
 #define SVGA_ID_0          SVGA_MAKE_ID(SVGA_VERSION_0)
 
-/* "Invalid" value for all SVGA IDs. (Version ID, screen object ID, surface ID...) */
+/*
+ * "Invalid" value for all SVGA IDs.
+ * (Version ID, screen object ID, surface ID...)
+ */
 #define SVGA_ID_INVALID    0xFFFFFFFF
 
 /* Port offsets, relative to BAR0 */
@@ -155,7 +168,7 @@ enum {
    SVGA_REG_CONFIG_DONE = 20,         /* Set when memory area configured */
    SVGA_REG_SYNC = 21,                /* See "FIFO Synchronization Registers" */
    SVGA_REG_BUSY = 22,                /* See "FIFO Synchronization Registers" */
-   SVGA_REG_GUEST_ID = 23,            /* Set guest OS identifier */
+   SVGA_REG_GUEST_ID = 23,            /* (Deprecated) */
    SVGA_REG_CURSOR_ID = 24,           /* (Deprecated) */
    SVGA_REG_CURSOR_X = 25,            /* (Deprecated) */
    SVGA_REG_CURSOR_Y = 26,            /* (Deprecated) */
@@ -187,7 +200,14 @@ enum {
    SVGA_REG_MEMORY_SIZE = 47,       /* Total dedicated device memory excluding FIFO */
    SVGA_REG_COMMAND_LOW = 48,       /* Lower 32 bits and submits commands */
    SVGA_REG_COMMAND_HIGH = 49,      /* Upper 32 bits of command buffer PA */
-   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,   /* Max primary memory */
+
+   /*
+    * Max primary memory.
+    * See SVGA_CAP_NO_BB_RESTRICTION.
+    */
+   SVGA_REG_MAX_PRIMARY_MEM = 50,
+   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,
+
    SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Sugested limit on mob mem */
    SVGA_REG_DEV_CAP = 52,           /* Write dev cap index, read value */
    SVGA_REG_CMD_PREPEND_LOW = 53,
@@ -195,7 +215,10 @@ enum {
    SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
    SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
    SVGA_REG_MOB_MAX_SIZE = 57,
-   SVGA_REG_TOP = 58,               /* Must be 1 more than the last register */
+   SVGA_REG_BLANK_SCREEN_TARGETS = 58,
+   SVGA_REG_CAP2 = 59,
+   SVGA_REG_DEVEL_CAP = 60,
+   SVGA_REG_TOP = 61,               /* Must be 1 more than the last register */
 
    SVGA_PALETTE_BASE = 1024,        /* Base of SVGA color map */
    /* Next 768 (== 256*3) registers exist for colormap */
@@ -393,6 +416,7 @@ typedef enum {
    SVGA_CB_CONTEXT_0      = 0x0,
    SVGA_CB_CONTEXT_1      = 0x1, /* Supported with SVGA_CAP_HP_CMD_QUEUE */
    SVGA_CB_CONTEXT_MAX    = 0x2,
+   SVGA_CB_CONTEXT_HP_MAX = 0x2,
 } SVGACBContext;
 
 
@@ -449,6 +473,18 @@ typedef enum {
     * due to an error.  No IRQ is raised.
     */
    SVGA_CB_STATUS_SUBMISSION_ERROR = 6,
+
+   /*
+    * Written by the host when the host finished a
+    * SVGA_DC_CMD_ASYNC_STOP_QUEUE request for this command buffer
+    * queue.  The offset of the first byte not processed is stored in
+    * the errorOffset field of the command buffer header.  All guest
+    * visible side effects of commands till that point are guaranteed
+    * to be finished before this is written.  The
+    * SVGA_IRQFLAG_COMMAND_BUFFER IRQ is raised as long as the
+    * SVGA_CB_FLAG_NO_IRQ is not set.
+    */
+   SVGA_CB_STATUS_PARTIAL_COMPLETE = 7,
 } SVGACBStatus;
 
 typedef enum {
@@ -461,8 +497,8 @@ typedef enum {
 typedef
 #include "vmware_pack_begin.h"
 struct {
-   volatile SVGACBStatus status;
-   volatile uint32 errorOffset;
+   volatile SVGACBStatus status; /* Modified by device. */
+   volatile uint32 errorOffset;  /* Modified by device. */
    uint64 id;
    SVGACBFlags flags;
    uint32 length;
@@ -473,7 +509,9 @@ struct {
          uint32 mobOffset;
       } mob;
    } ptr;
-   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise */
+   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise,
+                   * modified by device.
+                   */
    uint32 dxContext; /* Valid if DX_CONTEXT flag set, must be zero otherwise */
    uint32 mustBeZero[6];
 }
@@ -484,20 +522,26 @@ typedef enum {
    SVGA_DC_CMD_NOP                   = 0,
    SVGA_DC_CMD_START_STOP_CONTEXT    = 1,
    SVGA_DC_CMD_PREEMPT               = 2,
-   SVGA_DC_CMD_MAX                   = 3,
-   SVGA_DC_CMD_FORCE_UINT            = MAX_UINT32,
+   SVGA_DC_CMD_START_QUEUE           = 3, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_ASYNC_STOP_QUEUE      = 4, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE   = 5, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_MAX                   = 6,
 } SVGADeviceContextCmdId;
 
-typedef struct {
+/*
+ * Starts or stops both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1.
+ */
+
+typedef struct SVGADCCmdStartStop {
    uint32 enable;
-   SVGACBContext context;
+   SVGACBContext context; /* Must be zero */
 } SVGADCCmdStartStop;
 
 /*
  * SVGADCCmdPreempt --
  *
  * This command allows the guest to request that all command buffers
- * on the specified context be preempted that can be.  After execution
+ * on SVGA_CB_CONTEXT_0 be preempted that can be.  After execution
  * of this command all command buffers that were preempted will
  * already have SVGA_CB_STATUS_PREEMPTED written into the status
  * field.  The device might still be processing a command buffer,
@@ -507,12 +551,69 @@ typedef struct {
  * command buffer header set to zero.
  */
 
-typedef struct {
-   SVGACBContext context;
+typedef struct SVGADCCmdPreempt {
+   SVGACBContext context; /* Must be zero */
    uint32 ignoreIDZero;
 } SVGADCCmdPreempt;
 
 /*
+ * Starts the requested command buffer processing queue.  Valid only
+ * if the SVGA_CAP_HP_CMD_QUEUE cap is set.
+ *
+ * For a command queue to be considered runnable it must be enabled
+ * and any corresponding higher priority queues must also be enabled.
+ * For example in order for command buffers to be processed on
+ * SVGA_CB_CONTEXT_0 both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1 must
+ * be enabled.  But for commands to be runnable on SVGA_CB_CONTEXT_1
+ * only that queue must be enabled.
+ */
+
+typedef struct SVGADCCmdStartQueue {
+   SVGACBContext context;
+} SVGADCCmdStartQueue;
+
+/*
+ * Requests the SVGA device to stop processing the requested command
+ * buffer queue as soon as possible.  The guest knows the stop has
+ * completed when one of the following happens.
+ *
+ * 1) A command buffer status of SVGA_CB_STATUS_PARTIAL_COMPLETE is returned
+ * 2) A command buffer error is encountered with would stop the queue
+ *    regardless of the async stop request.
+ * 3) All command buffers that have been submitted complete successfully.
+ * 4) The stop completes synchronously if no command buffers are
+ *    active on the queue when it is issued.
+ *
+ * If the command queue is not in a runnable state there is no
+ * guarentee this async stop will finish.  For instance if the high
+ * priority queue is not enabled and a stop is requested on the low
+ * priority queue, the high priority queue must be reenabled to
+ * guarantee that the async stop will finish.
+ *
+ * This command along with SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE can be used
+ * to implement mid command buffer preemption.
+ *
+ * Valid only if the SVGA_CAP_HP_CMD_QUEUE cap is set.
+ */
+
+typedef struct SVGADCCmdAsyncStopQueue {
+   SVGACBContext context;
+} SVGADCCmdAsyncStopQueue;
+
+/*
+ * Requests the SVGA device to throw away any full command buffers on
+ * the requested command queue that have not been started.  For a
+ * driver to know which command buffers were thrown away a driver
+ * should only issue this command when the queue is stopped, for
+ * whatever reason.
+ */
+
+typedef struct SVGADCCmdEmptyQueue {
+   SVGACBContext context;
+} SVGADCCmdEmptyQueue;
+
+
+/*
  * SVGAGMRImageFormat --
  *
  *    This is a packed representation of the source 2D image format
@@ -537,7 +638,7 @@ typedef struct SVGAGMRImageFormat {
       struct {
          uint32 bitsPerPixel : 8;
          uint32 colorDepth   : 8;
-	 uint32 reserved     : 16;  /* Must be zero */
+         uint32 reserved     : 16;  /* Must be zero */
       };
 
       uint32 value;
@@ -673,8 +774,36 @@ SVGASignedPoint;
  * SVGA_CAP_GBOBJECTS --
  *    Enable guest-backed objects and surfaces.
  *
- * SVGA_CAP_CMD_BUFFERS_3 --
- *    Enable support for command buffers in a mob.
+ * SVGA_CAP_DX --
+ *    Enable support for DX commands, and command buffers in a mob.
+ *
+ * SVGA_CAP_HP_CMD_QUEUE --
+ *    Enable support for the high priority command queue, and the
+ *    ScreenCopy command.
+ *
+ * SVGA_CAP_NO_BB_RESTRICTION --
+ *    Allow ScreenTargets to be defined without regard to the 32-bpp
+ *    bounding-box memory restrictions. ie:
+ *
+ *    The summed memory usage of all screens (assuming they were defined as
+ *    32-bpp) must always be less than the value of the
+ *    SVGA_REG_MAX_PRIMARY_MEM register.
+ *
+ *    If this cap is not present, the 32-bpp bounding box around all screens
+ *    must additionally be under the value of the SVGA_REG_MAX_PRIMARY_MEM
+ *    register.
+ *
+ *    If the cap is present, the bounding box restriction is lifted (and only
+ *    the screen-sum limit applies).
+ *
+ *    (Note that this is a slight lie... there is still a sanity limit on any
+ *     dimension of the topology to be less than SVGA_SCREEN_ROOT_LIMIT, even
+ *     when SVGA_CAP_NO_BB_RESTRICTION is present, but that should be
+ *     large enough to express any possible topology without holes between
+ *     monitors.)
+ *
+ * SVGA_CAP_CAP2_REGISTER --
+ *    If this cap is present, the SVGA_REG_CAP2 register is supported.
  */
 
 #define SVGA_CAP_NONE               0x00000000
@@ -700,8 +829,30 @@ SVGASignedPoint;
 #define SVGA_CAP_GBOBJECTS          0x08000000
 #define SVGA_CAP_DX                 0x10000000
 #define SVGA_CAP_HP_CMD_QUEUE       0x20000000
+#define SVGA_CAP_NO_BB_RESTRICTION  0x40000000
+#define SVGA_CAP_CAP2_REGISTER      0x80000000
 
-#define SVGA_CAP_CMD_RESERVED       0x80000000
+/*
+ * The SVGA_REG_CAP2 register is an additional set of SVGA capability bits.
+ *
+ * SVGA_CAP2_GROW_OTABLE --
+ *      Allow the GrowOTable/DXGrowCOTable commands.
+ *
+ * SVGA_CAP2_INTRA_SURFACE_COPY --
+ *      Allow the IntraSurfaceCopy command.
+ *
+ * SVGA_CAP2_DX2 --
+ *      Allow the DefineGBSurface_v3, WholeSurfaceCopy.
+ *
+ * SVGA_CAP2_RESERVED --
+ *      Reserve the last bit for extending the SVGA capabilities to some
+ *      future mechanisms.
+ */
+#define SVGA_CAP2_NONE               0x00000000
+#define SVGA_CAP2_GROW_OTABLE        0x00000001
+#define SVGA_CAP2_INTRA_SURFACE_COPY 0x00000002
+#define SVGA_CAP2_DX2                0x00000004
+#define SVGA_CAP2_RESERVED           0x80000000
 
 
 /*
@@ -723,7 +874,8 @@ typedef enum {
    SVGABackdoorCapDeviceCaps = 0,
    SVGABackdoorCapFifoCaps = 1,
    SVGABackdoorCap3dHWVersion = 2,
-   SVGABackdoorCapMax = 3,
+   SVGABackdoorCapDeviceCaps2 = 3,
+   SVGABackdoorCapMax = 4,
 } SVGABackdoorCapType;
 
 
@@ -1915,16 +2067,6 @@ SVGAFifoCmdRemapGMR2;
 
 #define SVGA_VRAM_SIZE_W2K          (64 * 1024 * 1024) /* 64 MB */
 
-/*
- * To simplify autoDetect display configuration, support a minimum of
- * two 1920x1200 monitors, 32bpp, side-by-side, optionally rotated:
- *   numDisplays = 2
- *   maxWidth = numDisplay * 1920 = 3840
- *   maxHeight = rotated width of single monitor = 1920
- *   vramSize = maxWidth * maxHeight * 4 = 29491200
- */
-#define SVGA_VRAM_SIZE_AUTODETECT   (32 * 1024 * 1024)
-
 #if defined(VMX86_SERVER)
 #define SVGA_VRAM_SIZE               (4 * 1024 * 1024)
 #define SVGA_VRAM_SIZE_3D           (64 * 1024 * 1024)
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
index 53602a4e7957..350bbc6fab02 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
@@ -41,7 +41,10 @@ typedef uint64 PPN64;
 
 typedef bool Bool;
 
+#define MAX_UINT64 U64_MAX
 #define MAX_UINT32 U32_MAX
 #define MAX_UINT16 U16_MAX
 
+#define CONST64U(x) x##ULL
+
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
new file mode 100644
index 000000000000..2dda03345761
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -0,0 +1,1123 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
+/**************************************************************************
+ *
+ * Copyright © 2011-2018 VMware, Inc., Palo Alto, CA., USA
+ * 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 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 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.
+ *
+ **************************************************************************/
+
+#include <drm/ttm/ttm_placement.h>
+
+#include <drm/drmP.h>
+#include "vmwgfx_drv.h"
+#include "drm/ttm/ttm_object.h"
+
+
+/**
+ * struct vmw_user_buffer_object - User-space-visible buffer object
+ *
+ * @prime: The prime object providing user visibility.
+ * @vbo: The struct vmw_buffer_object
+ */
+struct vmw_user_buffer_object {
+	struct ttm_prime_object prime;
+	struct vmw_buffer_object vbo;
+};
+
+
+/**
+ * vmw_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the
+ * TTM buffer object.
+ */
+static struct vmw_buffer_object *
+vmw_buffer_object(struct ttm_buffer_object *bo)
+{
+	return container_of(bo, struct vmw_buffer_object, base);
+}
+
+
+/**
+ * vmw_user_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_user_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the TTM buffer
+ * object.
+ */
+static struct vmw_user_buffer_object *
+vmw_user_buffer_object(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	return container_of(vmw_bo, struct vmw_user_buffer_object, vbo);
+}
+
+
+/**
+ * vmw_bo_pin_in_placement - Validate a buffer to placement.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @placement:  The placement to pin it.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_placement(struct vmw_private *dev_priv,
+			    struct vmw_buffer_object *buf,
+			    struct ttm_placement *placement,
+			    bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+	uint32_t new_flags;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, placement, &ctx);
+
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_bo_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @pin:  Pin buffer if true.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+	uint32_t new_flags;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->pin_count > 0) {
+		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+		goto out_unreserve;
+	}
+
+	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
+	if (likely(ret == 0) || ret == -ERESTARTSYS)
+		goto out_unreserve;
+
+	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
+
+out_unreserve:
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_bo_pin_in_vram - Move a buffer to vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *buf,
+		       bool interruptible)
+{
+	return vmw_bo_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
+				       interruptible);
+}
+
+
+/**
+ * vmw_bo_pin_in_start_of_vram - Move a buffer to start of vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to pin.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *buf,
+				bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	struct ttm_placement placement;
+	struct ttm_place place;
+	int ret = 0;
+	uint32_t new_flags;
+
+	place = vmw_vram_placement.placement[0];
+	place.lpfn = bo->num_pages;
+	placement.num_placement = 1;
+	placement.placement = &place;
+	placement.num_busy_placement = 1;
+	placement.busy_placement = &place;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err_unlock;
+
+	/*
+	 * Is this buffer already in vram but not at the start of it?
+	 * In that case, evict it first because TTM isn't good at handling
+	 * that situation.
+	 */
+	if (bo->mem.mem_type == TTM_PL_VRAM &&
+	    bo->mem.start < bo->num_pages &&
+	    bo->mem.start > 0 &&
+	    buf->pin_count == 0) {
+		ctx.interruptible = false;
+		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
+	}
+
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(&placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	/* For some reason we didn't end up at the start of vram */
+	WARN_ON(ret == 0 && bo->offset != 0);
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err_unlock:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+
+	return ret;
+}
+
+
+/**
+ * vmw_bo_unpin - Unpin the buffer given buffer, does not move the buffer.
+ *
+ * This function takes the reservation_sem in write mode.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to unpin.
+ * @interruptible:  Use interruptible wait.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
+ */
+int vmw_bo_unpin(struct vmw_private *dev_priv,
+		 struct vmw_buffer_object *buf,
+		 bool interruptible)
+{
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	vmw_bo_pin_reserved(buf, false);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
+ * of a buffer.
+ *
+ * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
+ * @ptr: SVGAGuestPtr returning the result.
+ */
+void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
+			  SVGAGuestPtr *ptr)
+{
+	if (bo->mem.mem_type == TTM_PL_VRAM) {
+		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
+		ptr->offset = bo->offset;
+	} else {
+		ptr->gmrId = bo->mem.start;
+		ptr->offset = 0;
+	}
+}
+
+
+/**
+ * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
+ *
+ * @vbo: The buffer object. Must be reserved.
+ * @pin: Whether to pin or unpin.
+ *
+ */
+void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin)
+{
+	struct ttm_operation_ctx ctx = { false, true };
+	struct ttm_place pl;
+	struct ttm_placement placement;
+	struct ttm_buffer_object *bo = &vbo->base;
+	uint32_t old_mem_type = bo->mem.mem_type;
+	int ret;
+
+	lockdep_assert_held(&bo->resv->lock.base);
+
+	if (pin) {
+		if (vbo->pin_count++ > 0)
+			return;
+	} else {
+		WARN_ON(vbo->pin_count <= 0);
+		if (--vbo->pin_count > 0)
+			return;
+	}
+
+	pl.fpfn = 0;
+	pl.lpfn = 0;
+	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
+		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
+	if (pin)
+		pl.flags |= TTM_PL_FLAG_NO_EVICT;
+
+	memset(&placement, 0, sizeof(placement));
+	placement.num_placement = 1;
+	placement.placement = &pl;
+
+	ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
+}
+
+
+/**
+ * vmw_bo_map_and_cache - Map a buffer object and cache the map
+ *
+ * @vbo: The buffer object to map
+ * Return: A kernel virtual address or NULL if mapping failed.
+ *
+ * This function maps a buffer object into the kernel address space, or
+ * returns the virtual kernel address of an already existing map. The virtual
+ * address remains valid as long as the buffer object is pinned or reserved.
+ * The cached map is torn down on either
+ * 1) Buffer object move
+ * 2) Buffer object swapout
+ * 3) Buffer object destruction
+ *
+ */
+void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo)
+{
+	struct ttm_buffer_object *bo = &vbo->base;
+	bool not_used;
+	void *virtual;
+	int ret;
+
+	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
+	if (virtual)
+		return virtual;
+
+	ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map);
+	if (ret)
+		DRM_ERROR("Buffer object map failed: %d.\n", ret);
+
+	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
+}
+
+
+/**
+ * vmw_bo_unmap - Tear down a cached buffer object map.
+ *
+ * @vbo: The buffer object whose map we are tearing down.
+ *
+ * This function tears down a cached map set up using
+ * vmw_buffer_object_map_and_cache().
+ */
+void vmw_bo_unmap(struct vmw_buffer_object *vbo)
+{
+	if (vbo->map.bo == NULL)
+		return;
+
+	ttm_bo_kunmap(&vbo->map);
+}
+
+
+/**
+ * vmw_bo_acc_size - Calculate the pinned memory usage of buffers
+ *
+ * @dev_priv: Pointer to a struct vmw_private identifying the device.
+ * @size: The requested buffer size.
+ * @user: Whether this is an ordinary dma buffer or a user dma buffer.
+ */
+static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size,
+			      bool user)
+{
+	static size_t struct_size, user_struct_size;
+	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
+
+	if (unlikely(struct_size == 0)) {
+		size_t backend_size = ttm_round_pot(vmw_tt_size);
+
+		struct_size = backend_size +
+			ttm_round_pot(sizeof(struct vmw_buffer_object));
+		user_struct_size = backend_size +
+			ttm_round_pot(sizeof(struct vmw_user_buffer_object));
+	}
+
+	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
+		page_array_size +=
+			ttm_round_pot(num_pages * sizeof(dma_addr_t));
+
+	return ((user) ? user_struct_size : struct_size) +
+		page_array_size;
+}
+
+
+/**
+ * vmw_bo_bo_free - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+void vmw_bo_bo_free(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	vmw_bo_unmap(vmw_bo);
+	kfree(vmw_bo);
+}
+
+
+/**
+ * vmw_user_bo_destroy - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+static void vmw_user_bo_destroy(struct ttm_buffer_object *bo)
+{
+	struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo);
+
+	vmw_bo_unmap(&vmw_user_bo->vbo);
+	ttm_prime_object_kfree(vmw_user_bo, prime);
+}
+
+
+/**
+ * vmw_bo_init - Initialize a vmw buffer object
+ *
+ * @dev_priv: Pointer to the device private struct
+ * @vmw_bo: Pointer to the struct vmw_buffer_object to initialize.
+ * @size: Buffer object size in bytes.
+ * @placement: Initial placement.
+ * @interruptible: Whether waits should be performed interruptible.
+ * @bo_free: The buffer object destructor.
+ * Returns: Zero on success, negative error code on error.
+ *
+ * Note that on error, the code will free the buffer object.
+ */
+int vmw_bo_init(struct vmw_private *dev_priv,
+		struct vmw_buffer_object *vmw_bo,
+		size_t size, struct ttm_placement *placement,
+		bool interruptible,
+		void (*bo_free)(struct ttm_buffer_object *bo))
+{
+	struct ttm_bo_device *bdev = &dev_priv->bdev;
+	size_t acc_size;
+	int ret;
+	bool user = (bo_free == &vmw_user_bo_destroy);
+
+	WARN_ON_ONCE(!bo_free && (!user && (bo_free != vmw_bo_bo_free)));
+
+	acc_size = vmw_bo_acc_size(dev_priv, size, user);
+	memset(vmw_bo, 0, sizeof(*vmw_bo));
+
+	INIT_LIST_HEAD(&vmw_bo->res_list);
+
+	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
+			  ttm_bo_type_device, placement,
+			  0, interruptible, acc_size,
+			  NULL, NULL, bo_free);
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_release - TTM reference base object release callback for
+ * vmw user buffer objects
+ *
+ * @p_base: The TTM base object pointer about to be unreferenced.
+ *
+ * Clears the TTM base object pointer and drops the reference the
+ * base object has on the underlying struct vmw_buffer_object.
+ */
+static void vmw_user_bo_release(struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+	struct ttm_base_object *base = *p_base;
+	struct ttm_buffer_object *bo;
+
+	*p_base = NULL;
+
+	if (unlikely(base == NULL))
+		return;
+
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
+				   prime.base);
+	bo = &vmw_user_bo->vbo.base;
+	ttm_bo_unref(&bo);
+}
+
+
+/**
+ * vmw_user_bo_ref_obj-release - TTM synccpu reference object release callback
+ * for vmw user buffer objects
+ *
+ * @base: Pointer to the TTM base object
+ * @ref_type: Reference type of the reference reaching zero.
+ *
+ * Called when user-space drops its last synccpu reference on the buffer
+ * object, Either explicitly or as part of a cleanup file close.
+ */
+static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base,
+					enum ttm_ref_type ref_type)
+{
+	struct vmw_user_buffer_object *user_bo;
+
+	user_bo = container_of(base, struct vmw_user_buffer_object, prime.base);
+
+	switch (ref_type) {
+	case TTM_REF_SYNCCPU_WRITE:
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+		break;
+	default:
+		WARN_ONCE(true, "Undefined buffer object reference release.\n");
+	}
+}
+
+
+/**
+ * vmw_user_bo_alloc - Allocate a user buffer object
+ *
+ * @dev_priv: Pointer to a struct device private.
+ * @tfile: Pointer to a struct ttm_object_file on which to register the user
+ * object.
+ * @size: Size of the buffer object.
+ * @shareable: Boolean whether the buffer is shareable with other open files.
+ * @handle: Pointer to where the handle value should be assigned.
+ * @p_vbo: Pointer to where the refcounted struct vmw_buffer_object pointer
+ * should be assigned.
+ * Return: Zero on success, negative error code on error.
+ */
+int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+		      struct ttm_object_file *tfile,
+		      uint32_t size,
+		      bool shareable,
+		      uint32_t *handle,
+		      struct vmw_buffer_object **p_vbo,
+		      struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *user_bo;
+	struct ttm_buffer_object *tmp;
+	int ret;
+
+	user_bo = kzalloc(sizeof(*user_bo), GFP_KERNEL);
+	if (unlikely(!user_bo)) {
+		DRM_ERROR("Failed to allocate a buffer.\n");
+		return -ENOMEM;
+	}
+
+	ret = vmw_bo_init(dev_priv, &user_bo->vbo, size,
+			  (dev_priv->has_mob) ?
+			  &vmw_sys_placement :
+			  &vmw_vram_sys_placement, true,
+			  &vmw_user_bo_destroy);
+	if (unlikely(ret != 0))
+		return ret;
+
+	tmp = ttm_bo_reference(&user_bo->vbo.base);
+	ret = ttm_prime_object_init(tfile,
+				    size,
+				    &user_bo->prime,
+				    shareable,
+				    ttm_buffer_type,
+				    &vmw_user_bo_release,
+				    &vmw_user_bo_ref_obj_release);
+	if (unlikely(ret != 0)) {
+		ttm_bo_unref(&tmp);
+		goto out_no_base_object;
+	}
+
+	*p_vbo = &user_bo->vbo;
+	if (p_base) {
+		*p_base = &user_bo->prime.base;
+		kref_get(&(*p_base)->refcount);
+	}
+	*handle = user_bo->prime.base.hash.key;
+
+out_no_base_object:
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_verify_access - verify access permissions on this
+ * buffer object.
+ *
+ * @bo: Pointer to the buffer object being accessed
+ * @tfile: Identifying the caller.
+ */
+int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+			      struct ttm_object_file *tfile)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+
+	if (unlikely(bo->destroy != vmw_user_bo_destroy))
+		return -EPERM;
+
+	vmw_user_bo = vmw_user_buffer_object(bo);
+
+	/* Check that the caller has opened the object. */
+	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
+		return 0;
+
+	DRM_ERROR("Could not grant buffer access.\n");
+	return -EPERM;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_grab - Grab a struct vmw_user_buffer_object for cpu
+ * access, idling previous GPU operations on the buffer and optionally
+ * blocking it for further command submissions.
+ *
+ * @user_bo: Pointer to the buffer object being grabbed for CPU access
+ * @tfile: Identifying the caller.
+ * @flags: Flags indicating how the grab should be performed.
+ * Return: Zero on success, Negative error code on error. In particular,
+ * -EBUSY will be returned if a dontblock operation is requested and the
+ * buffer object is busy, and -ERESTARTSYS will be returned if a wait is
+ * interrupted by a signal.
+ *
+ * A blocking grab will be automatically released when @tfile is closed.
+ */
+static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
+				    struct ttm_object_file *tfile,
+				    uint32_t flags)
+{
+	struct ttm_buffer_object *bo = &user_bo->vbo.base;
+	bool existed;
+	int ret;
+
+	if (flags & drm_vmw_synccpu_allow_cs) {
+		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
+		long lret;
+
+		lret = reservation_object_wait_timeout_rcu
+			(bo->resv, true, true,
+			 nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
+		if (!lret)
+			return -EBUSY;
+		else if (lret < 0)
+			return lret;
+		return 0;
+	}
+
+	ret = ttm_bo_synccpu_write_grab
+		(bo, !!(flags & drm_vmw_synccpu_dontblock));
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
+				 TTM_REF_SYNCCPU_WRITE, &existed, false);
+	if (ret != 0 || existed)
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+
+	return ret;
+}
+
+/**
+ * vmw_user_bo_synccpu_release - Release a previous grab for CPU access,
+ * and unblock command submission on the buffer if blocked.
+ *
+ * @handle: Handle identifying the buffer object.
+ * @tfile: Identifying the caller.
+ * @flags: Flags indicating the type of release.
+ */
+static int vmw_user_bo_synccpu_release(uint32_t handle,
+					   struct ttm_object_file *tfile,
+					   uint32_t flags)
+{
+	if (!(flags & drm_vmw_synccpu_allow_cs))
+		return ttm_ref_object_base_unref(tfile, handle,
+						 TTM_REF_SYNCCPU_WRITE);
+
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_ioctl - ioctl function implementing the synccpu
+ * functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and calls the
+ * relevant synccpu functions.
+ */
+int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct drm_vmw_synccpu_arg *arg =
+		(struct drm_vmw_synccpu_arg *) data;
+	struct vmw_buffer_object *vbo;
+	struct vmw_user_buffer_object *user_bo;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct ttm_base_object *buffer_base;
+	int ret;
+
+	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
+	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
+			       drm_vmw_synccpu_dontblock |
+			       drm_vmw_synccpu_allow_cs)) != 0) {
+		DRM_ERROR("Illegal synccpu flags.\n");
+		return -EINVAL;
+	}
+
+	switch (arg->op) {
+	case drm_vmw_synccpu_grab:
+		ret = vmw_user_bo_lookup(tfile, arg->handle, &vbo,
+					     &buffer_base);
+		if (unlikely(ret != 0))
+			return ret;
+
+		user_bo = container_of(vbo, struct vmw_user_buffer_object,
+				       vbo);
+		ret = vmw_user_bo_synccpu_grab(user_bo, tfile, arg->flags);
+		vmw_bo_unreference(&vbo);
+		ttm_base_object_unref(&buffer_base);
+		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
+			     ret != -EBUSY)) {
+			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	case drm_vmw_synccpu_release:
+		ret = vmw_user_bo_synccpu_release(arg->handle, tfile,
+						  arg->flags);
+		if (unlikely(ret != 0)) {
+			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	default:
+		DRM_ERROR("Invalid synccpu operation.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+/**
+ * vmw_bo_alloc_ioctl - ioctl function implementing the buffer object
+ * allocation functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and allocates a
+ * struct vmw_user_buffer_object bo.
+ */
+int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	union drm_vmw_alloc_dmabuf_arg *arg =
+	    (union drm_vmw_alloc_dmabuf_arg *)data;
+	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
+	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
+	struct vmw_buffer_object *vbo;
+	uint32_t handle;
+	int ret;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				req->size, false, &handle, &vbo,
+				NULL);
+	if (unlikely(ret != 0))
+		goto out_no_bo;
+
+	rep->handle = handle;
+	rep->map_handle = drm_vma_node_offset_addr(&vbo->base.vma_node);
+	rep->cur_gmr_id = handle;
+	rep->cur_gmr_offset = 0;
+
+	vmw_bo_unreference(&vbo);
+
+out_no_bo:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+
+	return ret;
+}
+
+
+/**
+ * vmw_bo_unref_ioctl - Generic handle close ioctl.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and closes a
+ * handle to a TTM base object, optionally freeing the object.
+ */
+int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct drm_vmw_unref_dmabuf_arg *arg =
+	    (struct drm_vmw_unref_dmabuf_arg *)data;
+
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 arg->handle,
+					 TTM_REF_USAGE);
+}
+
+
+/**
+ * vmw_user_bo_lookup - Look up a vmw user buffer object from a handle.
+ *
+ * @tfile: The TTM object file the handle is registered with.
+ * @handle: The user buffer object handle
+ * @out: Pointer to a where a pointer to the embedded
+ * struct vmw_buffer_object should be placed.
+ * @p_base: Pointer to where a pointer to the TTM base object should be
+ * placed, or NULL if no such pointer is required.
+ * Return: Zero on success, Negative error code on error.
+ *
+ * Both the output base object pointer and the vmw buffer object pointer
+ * will be refcounted.
+ */
+int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+		       uint32_t handle, struct vmw_buffer_object **out,
+		       struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+	struct ttm_base_object *base;
+
+	base = ttm_base_object_lookup(tfile, handle);
+	if (unlikely(base == NULL)) {
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -ESRCH;
+	}
+
+	if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
+		ttm_base_object_unref(&base);
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -EINVAL;
+	}
+
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
+				   prime.base);
+	(void)ttm_bo_reference(&vmw_user_bo->vbo.base);
+	if (p_base)
+		*p_base = base;
+	else
+		ttm_base_object_unref(&base);
+	*out = &vmw_user_bo->vbo;
+
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_reference - Open a handle to a vmw user buffer object.
+ *
+ * @tfile: The TTM object file to register the handle with.
+ * @vbo: The embedded vmw buffer object.
+ * @handle: Pointer to where the new handle should be placed.
+ * Return: Zero on success, Negative error code on error.
+ */
+int vmw_user_bo_reference(struct ttm_object_file *tfile,
+			  struct vmw_buffer_object *vbo,
+			  uint32_t *handle)
+{
+	struct vmw_user_buffer_object *user_bo;
+
+	if (vbo->base.destroy != vmw_user_bo_destroy)
+		return -EINVAL;
+
+	user_bo = container_of(vbo, struct vmw_user_buffer_object, vbo);
+
+	*handle = user_bo->prime.base.hash.key;
+	return ttm_ref_object_add(tfile, &user_bo->prime.base,
+				  TTM_REF_USAGE, NULL, false);
+}
+
+
+/**
+ * vmw_bo_fence_single - Utility function to fence a single TTM buffer
+ *                       object without unreserving it.
+ *
+ * @bo:             Pointer to the struct ttm_buffer_object to fence.
+ * @fence:          Pointer to the fence. If NULL, this function will
+ *                  insert a fence into the command stream..
+ *
+ * Contrary to the ttm_eu version of this function, it takes only
+ * a single buffer object instead of a list, and it also doesn't
+ * unreserve the buffer object, which needs to be done separately.
+ */
+void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+			 struct vmw_fence_obj *fence)
+{
+	struct ttm_bo_device *bdev = bo->bdev;
+
+	struct vmw_private *dev_priv =
+		container_of(bdev, struct vmw_private, bdev);
+
+	if (fence == NULL) {
+		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+		dma_fence_put(&fence->base);
+	} else
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+}
+
+
+/**
+ * vmw_dumb_create - Create a dumb kms buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @args: Pointer to a struct drm_mode_create_dumb structure
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm create_dumb functionality.
+ * Note that this is very similar to the vmw_bo_alloc ioctl, except
+ * that the arguments have a different format.
+ */
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_buffer_object *vbo;
+	int ret;
+
+	args->pitch = args->width * ((args->bpp + 7) / 8);
+	args->size = args->pitch * args->height;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				    args->size, false, &args->handle,
+				    &vbo, NULL);
+	if (unlikely(ret != 0))
+		goto out_no_bo;
+
+	vmw_bo_unreference(&vbo);
+out_no_bo:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_dumb_map_offset - Return the address space offset of a dumb buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @handle: Handle identifying the dumb buffer.
+ * @offset: The address space offset returned.
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm dumb_map_offset functionality.
+ */
+int vmw_dumb_map_offset(struct drm_file *file_priv,
+			struct drm_device *dev, uint32_t handle,
+			uint64_t *offset)
+{
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_buffer_object *out_buf;
+	int ret;
+
+	ret = vmw_user_bo_lookup(tfile, handle, &out_buf, NULL);
+	if (ret != 0)
+		return -EINVAL;
+
+	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
+	vmw_bo_unreference(&out_buf);
+	return 0;
+}
+
+
+/**
+ * vmw_dumb_destroy - Destroy a dumb boffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @handle: Handle identifying the dumb buffer.
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm dumb_destroy functionality.
+ */
+int vmw_dumb_destroy(struct drm_file *file_priv,
+		     struct drm_device *dev,
+		     uint32_t handle)
+{
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 handle, TTM_REF_USAGE);
+}
+
+
+/**
+ * vmw_bo_swap_notify - swapout notify callback.
+ *
+ * @bo: The buffer object to be swapped out.
+ */
+void vmw_bo_swap_notify(struct ttm_buffer_object *bo)
+{
+	/* Is @bo embedded in a struct vmw_buffer_object? */
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
+		return;
+
+	/* Kill any cached kernel maps before swapout */
+	vmw_bo_unmap(vmw_buffer_object(bo));
+}
+
+
+/**
+ * vmw_bo_move_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to move.
+ * @mem: The struct ttm_mem_reg indicating to what memory
+ *       region the move is taking place.
+ *
+ * Detaches cached maps and device bindings that require that the
+ * buffer doesn't move.
+ */
+void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			struct ttm_mem_reg *mem)
+{
+	struct vmw_buffer_object *vbo;
+
+	if (mem == NULL)
+		return;
+
+	/* Make sure @bo is embedded in a struct vmw_buffer_object? */
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
+		return;
+
+	vbo = container_of(bo, struct vmw_buffer_object, base);
+
+	/*
+	 * Kill any cached kernel maps before move to or from VRAM.
+	 * With other types of moves, the underlying pages stay the same,
+	 * and the map can be kept.
+	 */
+	if (mem->mem_type == TTM_PL_VRAM || bo->mem.mem_type == TTM_PL_VRAM)
+		vmw_bo_unmap(vbo);
+
+	/*
+	 * If we're moving a backup MOB out of MOB placement, then make sure we
+	 * read back all resource content first, and unbind the MOB from
+	 * the resource.
+	 */
+	if (mem->mem_type != VMW_PL_MOB && bo->mem.mem_type == VMW_PL_MOB)
+		vmw_resource_unbind_list(vbo);
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 750319d95458..7c3cb8efd11a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -38,7 +38,7 @@ struct vmw_user_context {
 	struct vmw_cmdbuf_res_manager *man;
 	struct vmw_resource *cotables[SVGA_COTABLE_DX10_MAX];
 	spinlock_t cotable_lock;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 };
 
 static void vmw_user_context_free(struct vmw_resource *res);
@@ -424,7 +424,7 @@ static int vmw_gb_context_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -648,7 +648,7 @@ static int vmw_dx_context_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -900,7 +900,7 @@ vmw_context_binding_state(struct vmw_resource *ctx)
  * specified in the parameter.  0 otherwise.
  */
 int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
-			      struct vmw_dma_buffer *mob)
+			      struct vmw_buffer_object *mob)
 {
 	struct vmw_user_context *uctx =
 		container_of(ctx_res, struct vmw_user_context, res);
@@ -908,7 +908,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
 	if (mob == NULL) {
 		if (uctx->dx_query_mob) {
 			uctx->dx_query_mob->dx_query_ctx = NULL;
-			vmw_dmabuf_unreference(&uctx->dx_query_mob);
+			vmw_bo_unreference(&uctx->dx_query_mob);
 			uctx->dx_query_mob = NULL;
 		}
 
@@ -922,7 +922,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
 	mob->dx_query_ctx  = ctx_res;
 
 	if (!uctx->dx_query_mob)
-		uctx->dx_query_mob = vmw_dmabuf_reference(mob);
+		uctx->dx_query_mob = vmw_bo_reference(mob);
 
 	return 0;
 }
@@ -932,7 +932,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
  *
  * @ctx_res: The context resource
  */
-struct vmw_dma_buffer *
+struct vmw_buffer_object *
 vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res)
 {
 	struct vmw_user_context *uctx =
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index df55e7d8b4cf..1d45714e1d5a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -324,7 +324,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 		vmw_dx_context_scrub_cotables(vcotbl->ctx, readback);
 	mutex_unlock(&dev_priv->binding_mutex);
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
 
@@ -367,7 +367,7 @@ static int vmw_cotable_readback(struct vmw_resource *res)
 	}
 
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	vmw_fence_single_bo(&res->backup->base, fence);
+	vmw_bo_fence_single(&res->backup->base, fence);
 	vmw_fence_obj_unreference(&fence);
 
 	return 0;
@@ -390,7 +390,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	struct ttm_operation_ctx ctx = { false, false };
 	struct vmw_private *dev_priv = res->dev_priv;
 	struct vmw_cotable *vcotbl = vmw_cotable(res);
-	struct vmw_dma_buffer *buf, *old_buf = res->backup;
+	struct vmw_buffer_object *buf, *old_buf = res->backup;
 	struct ttm_buffer_object *bo, *old_bo = &res->backup->base;
 	size_t old_size = res->backup_size;
 	size_t old_size_read_back = vcotbl->size_read_back;
@@ -415,8 +415,8 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	if (!buf)
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, buf, new_size, &vmw_mob_ne_placement,
-			      true, vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, buf, new_size, &vmw_mob_ne_placement,
+			  true, vmw_bo_bo_free);
 	if (ret) {
 		DRM_ERROR("Failed initializing new cotable MOB.\n");
 		return ret;
@@ -482,7 +482,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	/* Let go of the old mob. */
 	list_del(&res->mob_head);
 	list_add_tail(&res->mob_head, &buf->res_list);
-	vmw_dmabuf_unreference(&old_buf);
+	vmw_bo_unreference(&old_buf);
 	res->id = vcotbl->type;
 
 	return 0;
@@ -491,7 +491,7 @@ out_map_new:
 	ttm_bo_kunmap(&old_map);
 out_wait:
 	ttm_bo_unreserve(bo);
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
deleted file mode 100644
index df7d1c97eb82..000000000000
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ /dev/null
@@ -1,376 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/**************************************************************************
- *
- * Copyright 2011-2015 VMware, Inc., Palo Alto, CA., USA
- *
- * 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 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 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.
- *
- **************************************************************************/
-
-#include <drm/ttm/ttm_placement.h>
-
-#include <drm/drmP.h>
-#include "vmwgfx_drv.h"
-
-
-/**
- * vmw_dmabuf_pin_in_placement - Validate a buffer to placement.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @placement:  The placement to pin it.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- *  -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv,
-				struct vmw_dma_buffer *buf,
-				struct ttm_placement *placement,
-				bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-	uint32_t new_flags;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	if (buf->pin_count > 0)
-		ret = ttm_bo_mem_compat(placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-	else
-		ret = ttm_bo_validate(bo, placement, &ctx);
-
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-
-err:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dmabuf_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @pin:  Pin buffer if true.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
-				  bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-	uint32_t new_flags;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	if (buf->pin_count > 0) {
-		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-		goto out_unreserve;
-	}
-
-	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
-	if (likely(ret == 0) || ret == -ERESTARTSYS)
-		goto out_unreserve;
-
-	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
-
-out_unreserve:
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-err:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dmabuf_pin_in_vram - Move a buffer to vram.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv,
-			   struct vmw_dma_buffer *buf,
-			   bool interruptible)
-{
-	return vmw_dmabuf_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
-					   interruptible);
-}
-
-/**
- * vmw_dmabuf_pin_in_start_of_vram - Move a buffer to start of vram.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to pin.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv,
-				    struct vmw_dma_buffer *buf,
-				    bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	struct ttm_placement placement;
-	struct ttm_place place;
-	int ret = 0;
-	uint32_t new_flags;
-
-	place = vmw_vram_placement.placement[0];
-	place.lpfn = bo->num_pages;
-	placement.num_placement = 1;
-	placement.placement = &place;
-	placement.num_busy_placement = 1;
-	placement.busy_placement = &place;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err_unlock;
-
-	/*
-	 * Is this buffer already in vram but not at the start of it?
-	 * In that case, evict it first because TTM isn't good at handling
-	 * that situation.
-	 */
-	if (bo->mem.mem_type == TTM_PL_VRAM &&
-	    bo->mem.start < bo->num_pages &&
-	    bo->mem.start > 0 &&
-	    buf->pin_count == 0) {
-		ctx.interruptible = false;
-		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
-	}
-
-	if (buf->pin_count > 0)
-		ret = ttm_bo_mem_compat(&placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-	else
-		ret = ttm_bo_validate(bo, &placement, &ctx);
-
-	/* For some reason we didn't end up at the start of vram */
-	WARN_ON(ret == 0 && bo->offset != 0);
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-err_unlock:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-
-	return ret;
-}
-
-/**
- * vmw_dmabuf_unpin - Unpin the buffer given buffer, does not move the buffer.
- *
- * This function takes the reservation_sem in write mode.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to unpin.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_unpin(struct vmw_private *dev_priv,
-		     struct vmw_dma_buffer *buf,
-		     bool interruptible)
-{
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	vmw_bo_pin_reserved(buf, false);
-
-	ttm_bo_unreserve(bo);
-
-err:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
- * of a buffer.
- *
- * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
- * @ptr: SVGAGuestPtr returning the result.
- */
-void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
-			  SVGAGuestPtr *ptr)
-{
-	if (bo->mem.mem_type == TTM_PL_VRAM) {
-		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
-		ptr->offset = bo->offset;
-	} else {
-		ptr->gmrId = bo->mem.start;
-		ptr->offset = 0;
-	}
-}
-
-
-/**
- * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
- *
- * @vbo: The buffer object. Must be reserved.
- * @pin: Whether to pin or unpin.
- *
- */
-void vmw_bo_pin_reserved(struct vmw_dma_buffer *vbo, bool pin)
-{
-	struct ttm_operation_ctx ctx = { false, true };
-	struct ttm_place pl;
-	struct ttm_placement placement;
-	struct ttm_buffer_object *bo = &vbo->base;
-	uint32_t old_mem_type = bo->mem.mem_type;
-	int ret;
-
-	lockdep_assert_held(&bo->resv->lock.base);
-
-	if (pin) {
-		if (vbo->pin_count++ > 0)
-			return;
-	} else {
-		WARN_ON(vbo->pin_count <= 0);
-		if (--vbo->pin_count > 0)
-			return;
-	}
-
-	pl.fpfn = 0;
-	pl.lpfn = 0;
-	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
-		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
-	if (pin)
-		pl.flags |= TTM_PL_FLAG_NO_EVICT;
-
-	memset(&placement, 0, sizeof(placement));
-	placement.num_placement = 1;
-	placement.placement = &pl;
-
-	ret = ttm_bo_validate(bo, &placement, &ctx);
-
-	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
-}
-
-
-/*
- * vmw_dma_buffer_unmap - Tear down a cached buffer object map.
- *
- * @vbo: The buffer object whose map we are tearing down.
- *
- * This function tears down a cached map set up using
- * vmw_dma_buffer_map_and_cache().
- */
-void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo)
-{
-	if (vbo->map.bo == NULL)
-		return;
-
-	ttm_bo_kunmap(&vbo->map);
-}
-
-
-/*
- * vmw_dma_buffer_map_and_cache - Map a buffer object and cache the map
- *
- * @vbo: The buffer object to map
- * Return: A kernel virtual address or NULL if mapping failed.
- *
- * This function maps a buffer object into the kernel address space, or
- * returns the virtual kernel address of an already existing map. The virtual
- * address remains valid as long as the buffer object is pinned or reserved.
- * The cached map is torn down on either
- * 1) Buffer object move
- * 2) Buffer object swapout
- * 3) Buffer object destruction
- *
- */
-void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo)
-{
-	struct ttm_buffer_object *bo = &vbo->base;
-	bool not_used;
-	void *virtual;
-	int ret;
-
-	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
-	if (virtual)
-		return virtual;
-
-	ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map);
-	if (ret)
-		DRM_ERROR("Buffer object map failed: %d.\n", ret);
-
-	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
-}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index af88cb737be3..bb6dbbe18835 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -137,6 +137,12 @@
 #define DRM_IOCTL_VMW_CREATE_EXTENDED_CONTEXT			\
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_CREATE_EXTENDED_CONTEXT,	\
 		struct drm_vmw_context_arg)
+#define DRM_IOCTL_VMW_GB_SURFACE_CREATE_EXT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_CREATE_EXT,	\
+		union drm_vmw_gb_surface_create_ext_arg)
+#define DRM_IOCTL_VMW_GB_SURFACE_REF_EXT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_REF_EXT,		\
+		union drm_vmw_gb_surface_reference_ext_arg)
 
 /**
  * The core DRM version of this macro doesn't account for
@@ -153,9 +159,9 @@
 static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_dmabuf_alloc_ioctl,
+	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_dmabuf_unref_ioctl,
+	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CURSOR_BYPASS,
 		      vmw_kms_cursor_bypass_ioctl,
@@ -219,11 +225,17 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 		      vmw_gb_surface_reference_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_SYNCCPU,
-		      vmw_user_dmabuf_synccpu_ioctl,
+		      vmw_user_bo_synccpu_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT,
 		      vmw_extended_context_define_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE_EXT,
+		      vmw_gb_surface_define_ext_ioctl,
+		      DRM_AUTH | DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF_EXT,
+		      vmw_gb_surface_reference_ext_ioctl,
+		      DRM_AUTH | DRM_RENDER_ALLOW),
 };
 
 static const struct pci_device_id vmw_pci_id_list[] = {
@@ -258,6 +270,15 @@ MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
 module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
 
+static void vmw_print_capabilities2(uint32_t capabilities2)
+{
+	DRM_INFO("Capabilities2:\n");
+	if (capabilities2 & SVGA_CAP2_GROW_OTABLE)
+		DRM_INFO("  Grow oTable.\n");
+	if (capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY)
+		DRM_INFO("  IntraSurface copy.\n");
+}
+
 static void vmw_print_capabilities(uint32_t capabilities)
 {
 	DRM_INFO("Capabilities:\n");
@@ -321,7 +342,7 @@ static void vmw_print_capabilities(uint32_t capabilities)
 static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 {
 	int ret;
-	struct vmw_dma_buffer *vbo;
+	struct vmw_buffer_object *vbo;
 	struct ttm_bo_kmap_obj map;
 	volatile SVGA3dQueryResult *result;
 	bool dummy;
@@ -335,9 +356,9 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 	if (!vbo)
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, vbo, PAGE_SIZE,
-			      &vmw_sys_ne_placement, false,
-			      &vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, vbo, PAGE_SIZE,
+			  &vmw_sys_ne_placement, false,
+			  &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -358,7 +379,7 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Dummy query buffer map failed.\n");
-		vmw_dmabuf_unreference(&vbo);
+		vmw_bo_unreference(&vbo);
 	} else
 		dev_priv->dummy_query_bo = vbo;
 
@@ -460,7 +481,7 @@ static void vmw_release_device_early(struct vmw_private *dev_priv)
 
 	BUG_ON(dev_priv->pinned_bo != NULL);
 
-	vmw_dmabuf_unreference(&dev_priv->dummy_query_bo);
+	vmw_bo_unreference(&dev_priv->dummy_query_bo);
 	if (dev_priv->cman)
 		vmw_cmdbuf_remove_pool(dev_priv->cman);
 
@@ -644,6 +665,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	mutex_init(&dev_priv->cmdbuf_mutex);
 	mutex_init(&dev_priv->release_mutex);
 	mutex_init(&dev_priv->binding_mutex);
+	mutex_init(&dev_priv->requested_layout_mutex);
 	mutex_init(&dev_priv->global_kms_state_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	ttm_lock_init(&dev_priv->reservation_sem);
@@ -683,6 +705,12 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	dev_priv->capabilities = vmw_read(dev_priv, SVGA_REG_CAPABILITIES);
+
+	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) {
+		dev_priv->capabilities2 = vmw_read(dev_priv, SVGA_REG_CAP2);
+	}
+
+
 	ret = vmw_dma_select_mode(dev_priv);
 	if (unlikely(ret != 0)) {
 		DRM_INFO("Restricting capabilities due to IOMMU setup.\n");
@@ -751,6 +779,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	vmw_print_capabilities(dev_priv->capabilities);
+	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER)
+		vmw_print_capabilities2(dev_priv->capabilities2);
 
 	ret = vmw_dma_masks(dev_priv);
 	if (unlikely(ret != 0))
@@ -883,7 +913,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	if (dev_priv->has_mob) {
 		spin_lock(&dev_priv->cap_lock);
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DX);
+		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DXCONTEXT);
 		dev_priv->has_dx = !!vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 		spin_unlock(&dev_priv->cap_lock);
 	}
@@ -898,9 +928,23 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	if (ret)
 		goto out_no_fifo;
 
+	if (dev_priv->has_dx) {
+		/*
+		 * SVGA_CAP2_DX2 (DefineGBSurface_v3) is needed for SM4_1
+		 * support
+		 */
+		if ((dev_priv->capabilities2 & SVGA_CAP2_DX2) != 0) {
+			vmw_write(dev_priv, SVGA_REG_DEV_CAP,
+					SVGA3D_DEVCAP_SM41);
+			dev_priv->has_sm4_1 = vmw_read(dev_priv,
+							SVGA_REG_DEV_CAP);
+		}
+	}
+
 	DRM_INFO("DX: %s\n", dev_priv->has_dx ? "yes." : "no.");
-	DRM_INFO("Atomic: %s\n",
-		 (dev->driver->driver_features & DRIVER_ATOMIC) ? "yes" : "no");
+	DRM_INFO("Atomic: %s\n", (dev->driver->driver_features & DRIVER_ATOMIC)
+		 ? "yes." : "no.");
+	DRM_INFO("SM4_1: %s\n", dev_priv->has_sm4_1 ? "yes." : "no.");
 
 	snprintf(host_log, sizeof(host_log), "vmwgfx: %s-%s",
 		VMWGFX_REPO, VMWGFX_GIT_VERSION);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 422eef114b98..1abe21758b0d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -43,10 +43,10 @@
 #include <linux/sync_file.h>
 
 #define VMWGFX_DRIVER_NAME "vmwgfx"
-#define VMWGFX_DRIVER_DATE "20180322"
+#define VMWGFX_DRIVER_DATE "20180704"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 14
-#define VMWGFX_DRIVER_PATCHLEVEL 1
+#define VMWGFX_DRIVER_MINOR 15
+#define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
 #define VMWGFX_MAX_RELOCATIONS 2048
@@ -83,10 +83,10 @@
 struct vmw_fpriv {
 	struct drm_master *locked_master;
 	struct ttm_object_file *tfile;
-	bool gb_aware;
+	bool gb_aware; /* user-space is guest-backed aware */
 };
 
-struct vmw_dma_buffer {
+struct vmw_buffer_object {
 	struct ttm_buffer_object base;
 	struct list_head res_list;
 	s32 pin_count;
@@ -120,7 +120,7 @@ struct vmw_resource {
 	unsigned long backup_size;
 	bool res_dirty; /* Protected by backup buffer reserved */
 	bool backup_dirty; /* Protected by backup buffer reserved */
-	struct vmw_dma_buffer *backup;
+	struct vmw_buffer_object *backup;
 	unsigned long backup_offset;
 	unsigned long pin_count; /* Protected by resource reserved */
 	const struct vmw_res_func *func;
@@ -166,7 +166,7 @@ struct vmw_surface_offset;
 
 struct vmw_surface {
 	struct vmw_resource res;
-	uint32_t flags;
+	SVGA3dSurfaceAllFlags flags;
 	uint32_t format;
 	uint32_t mip_levels[DRM_VMW_MAX_SURFACE_FACES];
 	struct drm_vmw_size base_size;
@@ -180,6 +180,8 @@ struct vmw_surface {
 	SVGA3dTextureFilter autogen_filter;
 	uint32_t multisample_count;
 	struct list_head view_list;
+	SVGA3dMSPattern multisample_pattern;
+	SVGA3dMSQualityLevel quality_level;
 };
 
 struct vmw_marker_queue {
@@ -304,7 +306,7 @@ struct vmw_sw_context{
 	uint32_t cmd_bounce_size;
 	struct list_head resource_list;
 	struct list_head ctx_resource_list; /* For contexts and cotables */
-	struct vmw_dma_buffer *cur_query_bo;
+	struct vmw_buffer_object *cur_query_bo;
 	struct list_head res_relocations;
 	uint32_t *buf_start;
 	struct vmw_res_cache_entry res_cache[vmw_res_max];
@@ -315,7 +317,7 @@ struct vmw_sw_context{
 	bool staged_bindings_inuse;
 	struct list_head staged_cmd_res;
 	struct vmw_resource_val_node *dx_ctx_node;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_cmdbuf_res_manager *man;
 };
@@ -386,6 +388,7 @@ struct vmw_private {
 	uint32_t initial_height;
 	u32 *mmio_virt;
 	uint32_t capabilities;
+	uint32_t capabilities2;
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
 	uint32_t max_mob_pages;
@@ -397,6 +400,7 @@ struct vmw_private {
 	spinlock_t cap_lock;
 	bool has_dx;
 	bool assume_16bpp;
+	bool has_sm4_1;
 
 	/*
 	 * VGA registers.
@@ -412,6 +416,15 @@ struct vmw_private {
 	uint32_t num_displays;
 
 	/*
+	 * Currently requested_layout_mutex is used to protect the gui
+	 * positionig state in display unit. With that use case currently this
+	 * mutex is only taken during layout ioctl and atomic check_modeset.
+	 * Other display unit state can be protected with this mutex but that
+	 * needs careful consideration.
+	 */
+	struct mutex requested_layout_mutex;
+
+	/*
 	 * Framebuffer info.
 	 */
 
@@ -513,8 +526,8 @@ struct vmw_private {
 	 * are protected by the cmdbuf mutex.
 	 */
 
-	struct vmw_dma_buffer *dummy_query_bo;
-	struct vmw_dma_buffer *pinned_bo;
+	struct vmw_buffer_object *dummy_query_bo;
+	struct vmw_buffer_object *pinned_bo;
 	uint32_t query_cid;
 	uint32_t query_cid_valid;
 	bool dummy_query_bo_pinned;
@@ -623,43 +636,13 @@ extern int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 				  struct ttm_object_file *tfile,
 				  uint32_t handle,
 				  struct vmw_surface **out_surf,
-				  struct vmw_dma_buffer **out_buf);
+				  struct vmw_buffer_object **out_buf);
 extern int vmw_user_resource_lookup_handle(
 	struct vmw_private *dev_priv,
 	struct ttm_object_file *tfile,
 	uint32_t handle,
 	const struct vmw_user_resource_conv *converter,
 	struct vmw_resource **p_res);
-extern void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo);
-extern int vmw_dmabuf_init(struct vmw_private *dev_priv,
-			   struct vmw_dma_buffer *vmw_bo,
-			   size_t size, struct ttm_placement *placement,
-			   bool interuptable,
-			   void (*bo_free) (struct ttm_buffer_object *bo));
-extern int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
-				  struct ttm_object_file *tfile);
-extern int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
-				 struct ttm_object_file *tfile,
-				 uint32_t size,
-				 bool shareable,
-				 uint32_t *handle,
-				 struct vmw_dma_buffer **p_dma_buf,
-				 struct ttm_base_object **p_base);
-extern int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
-				     struct vmw_dma_buffer *dma_buf,
-				     uint32_t *handle);
-extern int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv);
-extern int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv);
-extern int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
-					 struct drm_file *file_priv);
-extern uint32_t vmw_dmabuf_validate_node(struct ttm_buffer_object *bo,
-					 uint32_t cur_validate_node);
-extern void vmw_dmabuf_validate_clear(struct ttm_buffer_object *bo);
-extern int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-				  uint32_t id, struct vmw_dma_buffer **out,
-				  struct ttm_base_object **base);
 extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
@@ -670,43 +653,70 @@ extern int vmw_user_stream_lookup(struct vmw_private *dev_priv,
 				  struct vmw_resource **out);
 extern void vmw_resource_unreserve(struct vmw_resource *res,
 				   bool switch_backup,
-				   struct vmw_dma_buffer *new_backup,
+				   struct vmw_buffer_object *new_backup,
 				   unsigned long new_backup_offset);
-extern void vmw_resource_move_notify(struct ttm_buffer_object *bo,
-				     struct ttm_mem_reg *mem);
 extern void vmw_query_move_notify(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem);
-extern void vmw_resource_swap_notify(struct ttm_buffer_object *bo);
-extern int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob);
-extern void vmw_fence_single_bo(struct ttm_buffer_object *bo,
-				struct vmw_fence_obj *fence);
+extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob);
 extern void vmw_resource_evict_all(struct vmw_private *dev_priv);
-
+extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo);
 
 /**
- * DMA buffer helper routines - vmwgfx_dmabuf.c
+ * Buffer object helper functions - vmwgfx_bo.c
  */
-extern int vmw_dmabuf_pin_in_placement(struct vmw_private *vmw_priv,
-				       struct vmw_dma_buffer *bo,
-				       struct ttm_placement *placement,
+extern int vmw_bo_pin_in_placement(struct vmw_private *vmw_priv,
+				   struct vmw_buffer_object *bo,
+				   struct ttm_placement *placement,
+				   bool interruptible);
+extern int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible);
+extern int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+				     struct vmw_buffer_object *buf,
+				     bool interruptible);
+extern int vmw_bo_pin_in_start_of_vram(struct vmw_private *vmw_priv,
+				       struct vmw_buffer_object *bo,
 				       bool interruptible);
-extern int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
-				  bool interruptible);
-extern int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
-					 struct vmw_dma_buffer *buf,
-					 bool interruptible);
-extern int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *vmw_priv,
-					   struct vmw_dma_buffer *bo,
-					   bool interruptible);
-extern int vmw_dmabuf_unpin(struct vmw_private *vmw_priv,
-			    struct vmw_dma_buffer *bo,
-			    bool interruptible);
+extern int vmw_bo_unpin(struct vmw_private *vmw_priv,
+			struct vmw_buffer_object *bo,
+			bool interruptible);
 extern void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *buf,
 				 SVGAGuestPtr *ptr);
-extern void vmw_bo_pin_reserved(struct vmw_dma_buffer *bo, bool pin);
-extern void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo);
-extern void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo);
+extern void vmw_bo_pin_reserved(struct vmw_buffer_object *bo, bool pin);
+extern void vmw_bo_bo_free(struct ttm_buffer_object *bo);
+extern int vmw_bo_init(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *vmw_bo,
+		       size_t size, struct ttm_placement *placement,
+		       bool interuptable,
+		       void (*bo_free)(struct ttm_buffer_object *bo));
+extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+				     struct ttm_object_file *tfile);
+extern int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+			     struct ttm_object_file *tfile,
+			     uint32_t size,
+			     bool shareable,
+			     uint32_t *handle,
+			     struct vmw_buffer_object **p_dma_buf,
+			     struct ttm_base_object **p_base);
+extern int vmw_user_bo_reference(struct ttm_object_file *tfile,
+				 struct vmw_buffer_object *dma_buf,
+				 uint32_t *handle);
+extern int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+				     struct drm_file *file_priv);
+extern int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+			      uint32_t id, struct vmw_buffer_object **out,
+			      struct ttm_base_object **base);
+extern void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+				struct vmw_fence_obj *fence);
+extern void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo);
+extern void vmw_bo_unmap(struct vmw_buffer_object *vbo);
+extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			       struct ttm_mem_reg *mem);
+extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
 
 /**
  * Misc Ioctl functionality - vmwgfx_ioctl.c
@@ -758,7 +768,7 @@ extern void vmw_ttm_global_release(struct vmw_private *dev_priv);
 extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /**
- * TTM buffer object driver - vmwgfx_buffer.c
+ * TTM buffer object driver - vmwgfx_ttm_buffer.c
  */
 
 extern const size_t vmw_tt_size;
@@ -1041,8 +1051,8 @@ vmw_context_binding_state(struct vmw_resource *ctx);
 extern void vmw_dx_context_scrub_cotables(struct vmw_resource *ctx,
 					  bool readback);
 extern int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
-				     struct vmw_dma_buffer *mob);
-extern struct vmw_dma_buffer *
+				     struct vmw_buffer_object *mob);
+extern struct vmw_buffer_object *
 vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res);
 
 
@@ -1070,14 +1080,22 @@ extern int vmw_surface_validate(struct vmw_private *dev_priv,
 				struct vmw_surface *srf);
 int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t user_accounting_size,
-			       uint32_t svga3d_flags,
+			       SVGA3dSurfaceAllFlags svga3d_flags,
 			       SVGA3dSurfaceFormat format,
 			       bool for_scanout,
 			       uint32_t num_mip_levels,
 			       uint32_t multisample_count,
 			       uint32_t array_size,
 			       struct drm_vmw_size size,
+			       SVGA3dMSPattern multisample_pattern,
+			       SVGA3dMSQualityLevel quality_level,
 			       struct vmw_surface **srf_out);
+extern int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev,
+					   void *data,
+					   struct drm_file *file_priv);
+extern int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev,
+					      void *data,
+					      struct drm_file *file_priv);
 
 /*
  * Shader management - vmwgfx_shader.c
@@ -1224,6 +1242,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 		    u32 w, u32 h,
 		    struct vmw_diff_cpy *diff);
 
+/* Host messaging -vmwgfx_msg.c: */
+int vmw_host_get_guestinfo(const char *guest_info_param,
+			   char *buffer, size_t *length);
+int vmw_host_log(const char *log);
+
 /**
  * Inline helper functions
  */
@@ -1243,9 +1266,9 @@ static inline struct vmw_surface *vmw_surface_reference(struct vmw_surface *srf)
 	return srf;
 }
 
-static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf)
+static inline void vmw_bo_unreference(struct vmw_buffer_object **buf)
 {
-	struct vmw_dma_buffer *tmp_buf = *buf;
+	struct vmw_buffer_object *tmp_buf = *buf;
 
 	*buf = NULL;
 	if (tmp_buf != NULL) {
@@ -1255,7 +1278,8 @@ static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf)
 	}
 }
 
-static inline struct vmw_dma_buffer *vmw_dmabuf_reference(struct vmw_dma_buffer *buf)
+static inline struct vmw_buffer_object *
+vmw_bo_reference(struct vmw_buffer_object *buf)
 {
 	if (ttm_bo_reference(&buf->base))
 		return buf;
@@ -1302,10 +1326,4 @@ static inline void vmw_mmio_write(u32 value, u32 *addr)
 {
 	WRITE_ONCE(*addr, value);
 }
-
-/**
- * Add vmw_msg module function
- */
-extern int vmw_host_log(const char *log);
-
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 47bb7e58a368..1f134570b759 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -92,7 +92,7 @@ struct vmw_resource_val_node {
 	struct list_head head;
 	struct drm_hash_item hash;
 	struct vmw_resource *res;
-	struct vmw_dma_buffer *new_backup;
+	struct vmw_buffer_object *new_backup;
 	struct vmw_ctx_binding_state *staged_bindings;
 	unsigned long new_backup_offset;
 	u32 first_usage : 1;
@@ -126,9 +126,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
 static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGAMobId *id,
-				 struct vmw_dma_buffer **vmw_bo_p);
+				 struct vmw_buffer_object **vmw_bo_p);
 static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
-				   struct vmw_dma_buffer *vbo,
+				   struct vmw_buffer_object *vbo,
 				   bool validate_as_mob,
 				   uint32_t *p_val_node);
 /**
@@ -185,7 +185,7 @@ static void vmw_resources_unreserve(struct vmw_sw_context *sw_context,
 		}
 		vmw_resource_unreserve(res, switch_backup, val->new_backup,
 				       val->new_backup_offset);
-		vmw_dmabuf_unreference(&val->new_backup);
+		vmw_bo_unreference(&val->new_backup);
 	}
 }
 
@@ -423,7 +423,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
 	}
 
 	if (dev_priv->has_dx && vmw_res_type(ctx) == vmw_res_dx_context) {
-		struct vmw_dma_buffer *dx_query_mob;
+		struct vmw_buffer_object *dx_query_mob;
 
 		dx_query_mob = vmw_context_get_dx_query_mob(ctx);
 		if (dx_query_mob)
@@ -544,7 +544,7 @@ static int vmw_cmd_ok(struct vmw_private *dev_priv,
  * submission is reached.
  */
 static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
-				   struct vmw_dma_buffer *vbo,
+				   struct vmw_buffer_object *vbo,
 				   bool validate_as_mob,
 				   uint32_t *p_val_node)
 {
@@ -616,7 +616,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context)
 			return ret;
 
 		if (res->backup) {
-			struct vmw_dma_buffer *vbo = res->backup;
+			struct vmw_buffer_object *vbo = res->backup;
 
 			ret = vmw_bo_to_validate_list
 				(sw_context, vbo,
@@ -628,7 +628,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context)
 	}
 
 	if (sw_context->dx_query_mob) {
-		struct vmw_dma_buffer *expected_dx_query_mob;
+		struct vmw_buffer_object *expected_dx_query_mob;
 
 		expected_dx_query_mob =
 			vmw_context_get_dx_query_mob(sw_context->dx_query_ctx);
@@ -657,7 +657,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context)
 
 	list_for_each_entry(val, &sw_context->resource_list, head) {
 		struct vmw_resource *res = val->res;
-		struct vmw_dma_buffer *backup = res->backup;
+		struct vmw_buffer_object *backup = res->backup;
 
 		ret = vmw_resource_validate(res);
 		if (unlikely(ret != 0)) {
@@ -668,7 +668,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context)
 
 		/* Check if the resource switched backup buffer */
 		if (backup && res->backup && (backup != res->backup)) {
-			struct vmw_dma_buffer *vbo = res->backup;
+			struct vmw_buffer_object *vbo = res->backup;
 
 			ret = vmw_bo_to_validate_list
 				(sw_context, vbo,
@@ -821,7 +821,7 @@ out_no_reloc:
 static int vmw_rebind_all_dx_query(struct vmw_resource *ctx_res)
 {
 	struct vmw_private *dev_priv = ctx_res->dev_priv;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXBindAllQuery body;
@@ -1152,7 +1152,7 @@ static int vmw_cmd_present_check(struct vmw_private *dev_priv,
  * command batch.
  */
 static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv,
-				       struct vmw_dma_buffer *new_query_bo,
+				       struct vmw_buffer_object *new_query_bo,
 				       struct vmw_sw_context *sw_context)
 {
 	struct vmw_res_cache_entry *ctx_entry =
@@ -1234,7 +1234,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 	if (dev_priv->pinned_bo != sw_context->cur_query_bo) {
 		if (dev_priv->pinned_bo) {
 			vmw_bo_pin_reserved(dev_priv->pinned_bo, false);
-			vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+			vmw_bo_unreference(&dev_priv->pinned_bo);
 		}
 
 		if (!sw_context->needs_post_query_barrier) {
@@ -1256,7 +1256,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 			dev_priv->query_cid = sw_context->last_query_ctx->id;
 			dev_priv->query_cid_valid = true;
 			dev_priv->pinned_bo =
-				vmw_dmabuf_reference(sw_context->cur_query_bo);
+				vmw_bo_reference(sw_context->cur_query_bo);
 		}
 	}
 }
@@ -1282,15 +1282,14 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGAMobId *id,
-				 struct vmw_dma_buffer **vmw_bo_p)
+				 struct vmw_buffer_object **vmw_bo_p)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	uint32_t handle = *id;
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
-				     NULL);
+	ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use MOB buffer.\n");
 		ret = -EINVAL;
@@ -1316,7 +1315,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 	return 0;
 
 out_no_reloc:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	*vmw_bo_p = NULL;
 	return ret;
 }
@@ -1343,15 +1342,14 @@ out_no_reloc:
 static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 				   struct vmw_sw_context *sw_context,
 				   SVGAGuestPtr *ptr,
-				   struct vmw_dma_buffer **vmw_bo_p)
+				   struct vmw_buffer_object **vmw_bo_p)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	uint32_t handle = ptr->gmrId;
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
-				     NULL);
+	ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
 		ret = -EINVAL;
@@ -1376,7 +1374,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 	return 0;
 
 out_no_reloc:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	*vmw_bo_p = NULL;
 	return ret;
 }
@@ -1447,7 +1445,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 		SVGA3dCmdDXBindQuery q;
 	} *cmd;
 
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int    ret;
 
 
@@ -1466,7 +1464,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 	sw_context->dx_query_mob = vmw_bo;
 	sw_context->dx_query_ctx = sw_context->dx_ctx_node->res;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 
 	return ret;
 }
@@ -1549,7 +1547,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv,
 				struct vmw_sw_context *sw_context,
 				SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdEndGBQuery q;
@@ -1569,7 +1567,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv,
 
 	ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context);
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1584,7 +1582,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv,
 			     struct vmw_sw_context *sw_context,
 			     SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdEndQuery q;
@@ -1623,7 +1621,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv,
 
 	ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context);
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1638,7 +1636,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdWaitForGBQuery q;
@@ -1656,7 +1654,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return 0;
 }
 
@@ -1671,7 +1669,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
 			      struct vmw_sw_context *sw_context,
 			      SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdWaitForQuery q;
@@ -1708,7 +1706,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return 0;
 }
 
@@ -1716,7 +1714,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		       struct vmw_sw_context *sw_context,
 		       SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	struct vmw_surface *srf = NULL;
 	struct vmw_dma_cmd {
 		SVGA3dCmdHeader header;
@@ -1768,7 +1766,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 			     header);
 
 out_no_surface:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1887,7 +1885,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv,
 				      struct vmw_sw_context *sw_context,
 				      void *buf)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int ret;
 
 	struct {
@@ -1901,7 +1899,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 
 	return ret;
 }
@@ -1928,7 +1926,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv,
 				     uint32_t *buf_id,
 				     unsigned long backup_offset)
 {
-	struct vmw_dma_buffer *dma_buf;
+	struct vmw_buffer_object *dma_buf;
 	int ret;
 
 	ret = vmw_translate_mob_ptr(dev_priv, sw_context, buf_id, &dma_buf);
@@ -1939,7 +1937,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv,
 	if (val_node->first_usage)
 		val_node->no_buffer_needed = true;
 
-	vmw_dmabuf_unreference(&val_node->new_backup);
+	vmw_bo_unreference(&val_node->new_backup);
 	val_node->new_backup = dma_buf;
 	val_node->new_backup_offset = backup_offset;
 
@@ -3118,6 +3116,32 @@ static int vmw_cmd_dx_transfer_from_buffer(struct vmw_private *dev_priv,
 				 &cmd->body.destSid, NULL);
 }
 
+/**
+ * vmw_cmd_intra_surface_copy -
+ * Validate an SVGA_3D_CMD_INTRA_SURFACE_COPY command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_intra_surface_copy(struct vmw_private *dev_priv,
+					   struct vmw_sw_context *sw_context,
+					   SVGA3dCmdHeader *header)
+{
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdIntraSurfaceCopy body;
+	} *cmd = container_of(header, typeof(*cmd), header);
+
+	if (!(dev_priv->capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY))
+		return -EINVAL;
+
+	return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+				user_surface_converter,
+				&cmd->body.surface.sid, NULL);
+}
+
+
 static int vmw_cmd_check_not_3d(struct vmw_private *dev_priv,
 				struct vmw_sw_context *sw_context,
 				void *buf, uint32_t *size)
@@ -3232,9 +3256,9 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_SCREEN_DMA, &vmw_cmd_invalid,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DEAD1, &vmw_cmd_invalid,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_OPEN_CONTEXT_SURFACE, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DEAD2, &vmw_cmd_invalid,
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_LOGICOPS_BITBLT, &vmw_cmd_invalid,
 		    false, false, false),
@@ -3473,6 +3497,8 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER,
 		    &vmw_cmd_dx_transfer_from_buffer,
 		    true, false, true),
+	VMW_CMD_DEF(SVGA_3D_CMD_INTRA_SURFACE_COPY, &vmw_cmd_intra_surface_copy,
+		    true, false, true),
 };
 
 bool vmw_cmd_describe(const void *buf, u32 *size, char const **cmd)
@@ -3701,8 +3727,8 @@ int vmw_validate_single_buffer(struct vmw_private *dev_priv,
 			       bool interruptible,
 			       bool validate_as_mob)
 {
-	struct vmw_dma_buffer *vbo = container_of(bo, struct vmw_dma_buffer,
-						  base);
+	struct vmw_buffer_object *vbo =
+		container_of(bo, struct vmw_buffer_object, base);
 	struct ttm_operation_ctx ctx = { interruptible, true };
 	int ret;
 
@@ -4423,7 +4449,7 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 
 	ttm_bo_unref(&query_val.bo);
 	ttm_bo_unref(&pinned_val.bo);
-	vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+	vmw_bo_unreference(&dev_priv->pinned_bo);
 out_unlock:
 	return;
 
@@ -4432,7 +4458,7 @@ out_no_emit:
 out_no_reserve:
 	ttm_bo_unref(&query_val.bo);
 	ttm_bo_unref(&pinned_val.bo);
-	vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+	vmw_bo_unreference(&dev_priv->pinned_bo);
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 9b7e0aca5f84..b913a56f3426 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -42,7 +42,7 @@ struct vmw_fb_par {
 	void *vmalloc;
 
 	struct mutex bo_mutex;
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	unsigned bo_size;
 	struct drm_framebuffer *set_fb;
 	struct drm_display_mode *set_mode;
@@ -184,7 +184,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 	struct drm_clip_rect clip;
 	struct drm_framebuffer *cur_fb;
 	u8 *src_ptr, *dst_ptr;
-	struct vmw_dma_buffer *vbo = par->vmw_bo;
+	struct vmw_buffer_object *vbo = par->vmw_bo;
 	void *virtual;
 
 	if (!READ_ONCE(par->dirty.active))
@@ -197,7 +197,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 
 	(void) ttm_read_lock(&vmw_priv->reservation_sem, false);
 	(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
-	virtual = vmw_dma_buffer_map_and_cache(vbo);
+	virtual = vmw_bo_map_and_cache(vbo);
 	if (!virtual)
 		goto out_unreserve;
 
@@ -391,9 +391,9 @@ static void vmw_fb_imageblit(struct fb_info *info, const struct fb_image *image)
  */
 
 static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
-			    size_t size, struct vmw_dma_buffer **out)
+			    size_t size, struct vmw_buffer_object **out)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int ret;
 
 	(void) ttm_write_lock(&vmw_priv->reservation_sem, false);
@@ -404,10 +404,10 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
 		goto err_unlock;
 	}
 
-	ret = vmw_dmabuf_init(vmw_priv, vmw_bo, size,
+	ret = vmw_bo_init(vmw_priv, vmw_bo, size,
 			      &vmw_sys_placement,
 			      false,
-			      &vmw_dmabuf_bo_free);
+			      &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		goto err_unlock; /* init frees the buffer on failure */
 
@@ -491,7 +491,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par,
 	}
 
 	if (par->vmw_bo && detach_bo && unref_bo)
-		vmw_dmabuf_unreference(&par->vmw_bo);
+		vmw_bo_unreference(&par->vmw_bo);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index c2eeb677cdfc..3d546d409334 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -175,7 +175,6 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	struct vmw_private *dev_priv = fman->dev_priv;
 	struct vmwgfx_wait_cb cb;
 	long ret = timeout;
-	unsigned long irq_flags;
 
 	if (likely(vmw_fence_obj_signaled(fence)))
 		return timeout;
@@ -183,7 +182,7 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 	vmw_seqno_waiter_add(dev_priv);
 
-	spin_lock_irqsave(f->lock, irq_flags);
+	spin_lock(f->lock);
 
 	if (intr && signal_pending(current)) {
 		ret = -ERESTARTSYS;
@@ -194,30 +193,45 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	cb.task = current;
 	list_add(&cb.base.node, &f->cb_list);
 
-	while (ret > 0) {
+	for (;;) {
 		__vmw_fences_update(fman);
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags))
-			break;
 
+		/*
+		 * We can use the barrier free __set_current_state() since
+		 * DMA_FENCE_FLAG_SIGNALED_BIT + wakeup is protected by the
+		 * fence spinlock.
+		 */
 		if (intr)
 			__set_current_state(TASK_INTERRUPTIBLE);
 		else
 			__set_current_state(TASK_UNINTERRUPTIBLE);
-		spin_unlock_irqrestore(f->lock, irq_flags);
 
-		ret = schedule_timeout(ret);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags)) {
+			if (ret == 0 && timeout > 0)
+				ret = 1;
+			break;
+		}
 
-		spin_lock_irqsave(f->lock, irq_flags);
-		if (ret > 0 && intr && signal_pending(current))
+		if (intr && signal_pending(current)) {
 			ret = -ERESTARTSYS;
-	}
+			break;
+		}
 
+		if (ret == 0)
+			break;
+
+		spin_unlock(f->lock);
+
+		ret = schedule_timeout(ret);
+
+		spin_lock(f->lock);
+	}
+	__set_current_state(TASK_RUNNING);
 	if (!list_empty(&cb.base.node))
 		list_del(&cb.base.node);
-	__set_current_state(TASK_RUNNING);
 
 out:
-	spin_unlock_irqrestore(f->lock, irq_flags);
+	spin_unlock(f->lock);
 
 	vmw_seqno_waiter_remove(dev_priv);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 78fce406e1d4..172a6ba6539c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -56,6 +56,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	case DRM_VMW_PARAM_HW_CAPS:
 		param->value = dev_priv->capabilities;
 		break;
+	case DRM_VMW_PARAM_HW_CAPS2:
+		param->value = dev_priv->capabilities2;
+		break;
 	case DRM_VMW_PARAM_FIFO_CAPS:
 		param->value = dev_priv->fifo.capabilities;
 		break;
@@ -113,6 +116,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	case DRM_VMW_PARAM_DX:
 		param->value = dev_priv->has_dx;
 		break;
+	case DRM_VMW_PARAM_SM4_1:
+		param->value = dev_priv->has_sm4_1;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -122,15 +128,12 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 
 static u32 vmw_mask_multisample(unsigned int cap, u32 fmt_value)
 {
-	/* If the header is updated, update the format test as well! */
-	BUILD_BUG_ON(SVGA3D_DEVCAP_DXFMT_BC5_UNORM + 1 != SVGA3D_DEVCAP_MAX);
-
-	if (cap >= SVGA3D_DEVCAP_DXFMT_X8R8G8B8 &&
-	    cap <= SVGA3D_DEVCAP_DXFMT_BC5_UNORM)
-		fmt_value &= ~(SVGADX_DXFMT_MULTISAMPLE_2 |
-			       SVGADX_DXFMT_MULTISAMPLE_4 |
-			       SVGADX_DXFMT_MULTISAMPLE_8);
-	else if (cap == SVGA3D_DEVCAP_MULTISAMPLE_MASKABLESAMPLES)
+	/*
+	 * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES
+	 * to check the sample count supported by virtual device. Since there
+	 * never was support for multisample count for backing MOB return 0.
+	 */
+	if (cap == SVGA3D_DEVCAP_MULTISAMPLE_MASKABLESAMPLES)
 		return 0;
 
 	return fmt_value;
@@ -377,8 +380,8 @@ int vmw_present_readback_ioctl(struct drm_device *dev, void *data,
 	}
 
 	vfb = vmw_framebuffer_to_vfb(fb);
-	if (!vfb->dmabuf) {
-		DRM_ERROR("Framebuffer not dmabuf backed.\n");
+	if (!vfb->bo) {
+		DRM_ERROR("Framebuffer not buffer backed.\n");
 		ret = -EINVAL;
 		goto out_no_ttm_lock;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index bc5fbd39cf9a..23beff5d8e3c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -85,10 +85,10 @@ static int vmw_cursor_update_image(struct vmw_private *dev_priv,
 	return 0;
 }
 
-static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
-				    struct vmw_dma_buffer *dmabuf,
-				    u32 width, u32 height,
-				    u32 hotspotX, u32 hotspotY)
+static int vmw_cursor_update_bo(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *bo,
+				u32 width, u32 height,
+				u32 hotspotX, u32 hotspotY)
 {
 	struct ttm_bo_kmap_obj map;
 	unsigned long kmap_offset;
@@ -100,13 +100,13 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
 	kmap_offset = 0;
 	kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	ret = ttm_bo_reserve(&dmabuf->base, true, false, NULL);
+	ret = ttm_bo_reserve(&bo->base, true, false, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("reserve failed\n");
 		return -EINVAL;
 	}
 
-	ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map);
+	ret = ttm_bo_kmap(&bo->base, kmap_offset, kmap_num, &map);
 	if (unlikely(ret != 0))
 		goto err_unreserve;
 
@@ -116,7 +116,7 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
 
 	ttm_bo_kunmap(&map);
 err_unreserve:
-	ttm_bo_unreserve(&dmabuf->base);
+	ttm_bo_unreserve(&bo->base);
 
 	return ret;
 }
@@ -352,13 +352,13 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 	if (vps->surf)
 		vmw_surface_unreference(&vps->surf);
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unreference(&vps->dmabuf);
+	if (vps->bo)
+		vmw_bo_unreference(&vps->bo);
 
 	if (fb) {
-		if (vmw_framebuffer_to_vfb(fb)->dmabuf) {
-			vps->dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer;
-			vmw_dmabuf_reference(vps->dmabuf);
+		if (vmw_framebuffer_to_vfb(fb)->bo) {
+			vps->bo = vmw_framebuffer_to_vfbd(fb)->buffer;
+			vmw_bo_reference(vps->bo);
 		} else {
 			vps->surf = vmw_framebuffer_to_vfbs(fb)->surface;
 			vmw_surface_reference(vps->surf);
@@ -390,7 +390,7 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 	}
 
 	du->cursor_surface = vps->surf;
-	du->cursor_dmabuf = vps->dmabuf;
+	du->cursor_bo = vps->bo;
 
 	if (vps->surf) {
 		du->cursor_age = du->cursor_surface->snooper.age;
@@ -399,11 +399,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 					      vps->surf->snooper.image,
 					      64, 64, hotspot_x,
 					      hotspot_y);
-	} else if (vps->dmabuf) {
-		ret = vmw_cursor_update_dmabuf(dev_priv, vps->dmabuf,
-					       plane->state->crtc_w,
-					       plane->state->crtc_h,
-					       hotspot_x, hotspot_y);
+	} else if (vps->bo) {
+		ret = vmw_cursor_update_bo(dev_priv, vps->bo,
+					   plane->state->crtc_w,
+					   plane->state->crtc_h,
+					   hotspot_x, hotspot_y);
 	} else {
 		vmw_cursor_update_position(dev_priv, false, 0, 0);
 		return;
@@ -519,7 +519,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
 		ret = -EINVAL;
 	}
 
-	if (!vmw_framebuffer_to_vfb(fb)->dmabuf)
+	if (!vmw_framebuffer_to_vfb(fb)->bo)
 		surface = vmw_framebuffer_to_vfbs(fb)->surface;
 
 	if (surface && !surface->snooper.image) {
@@ -687,8 +687,8 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane)
 	if (vps->surf)
 		(void) vmw_surface_reference(vps->surf);
 
-	if (vps->dmabuf)
-		(void) vmw_dmabuf_reference(vps->dmabuf);
+	if (vps->bo)
+		(void) vmw_bo_reference(vps->bo);
 
 	state = &vps->base;
 
@@ -745,8 +745,8 @@ vmw_du_plane_destroy_state(struct drm_plane *plane,
 	if (vps->surf)
 		vmw_surface_unreference(&vps->surf);
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unreference(&vps->dmabuf);
+	if (vps->bo)
+		vmw_bo_unreference(&vps->bo);
 
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
@@ -902,12 +902,12 @@ static int vmw_framebuffer_surface_dirty(struct drm_framebuffer *framebuffer,
 
 /**
  * vmw_kms_readback - Perform a readback from the screen system to
- * a dma-buffer backed framebuffer.
+ * a buffer-object backed framebuffer.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm_file identifying the caller.
  * Must be set to NULL if @user_fence_rep is NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @user_fence_rep: User-space provided structure for fence information.
  * Must be set to non-NULL if @file_priv is non-NULL.
  * @vclips: Array of clip rects.
@@ -951,7 +951,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 					   struct vmw_framebuffer **out,
 					   const struct drm_mode_fb_cmd2
 					   *mode_cmd,
-					   bool is_dmabuf_proxy)
+					   bool is_bo_proxy)
 
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -1019,7 +1019,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 	drm_helper_mode_fill_fb_struct(dev, &vfbs->base.base, mode_cmd);
 	vfbs->surface = vmw_surface_reference(surface);
 	vfbs->base.user_handle = mode_cmd->handles[0];
-	vfbs->is_dmabuf_proxy = is_dmabuf_proxy;
+	vfbs->is_bo_proxy = is_bo_proxy;
 
 	*out = &vfbs->base;
 
@@ -1038,30 +1038,30 @@ out_err1:
 }
 
 /*
- * Dmabuf framebuffer code
+ * Buffer-object framebuffer code
  */
 
-static void vmw_framebuffer_dmabuf_destroy(struct drm_framebuffer *framebuffer)
+static void vmw_framebuffer_bo_destroy(struct drm_framebuffer *framebuffer)
 {
-	struct vmw_framebuffer_dmabuf *vfbd =
+	struct vmw_framebuffer_bo *vfbd =
 		vmw_framebuffer_to_vfbd(framebuffer);
 
 	drm_framebuffer_cleanup(framebuffer);
-	vmw_dmabuf_unreference(&vfbd->buffer);
+	vmw_bo_unreference(&vfbd->buffer);
 	if (vfbd->base.user_obj)
 		ttm_base_object_unref(&vfbd->base.user_obj);
 
 	kfree(vfbd);
 }
 
-static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
-				 struct drm_file *file_priv,
-				 unsigned flags, unsigned color,
-				 struct drm_clip_rect *clips,
-				 unsigned num_clips)
+static int vmw_framebuffer_bo_dirty(struct drm_framebuffer *framebuffer,
+				    struct drm_file *file_priv,
+				    unsigned int flags, unsigned int color,
+				    struct drm_clip_rect *clips,
+				    unsigned int num_clips)
 {
 	struct vmw_private *dev_priv = vmw_priv(framebuffer->dev);
-	struct vmw_framebuffer_dmabuf *vfbd =
+	struct vmw_framebuffer_bo *vfbd =
 		vmw_framebuffer_to_vfbd(framebuffer);
 	struct drm_clip_rect norect;
 	int ret, increment = 1;
@@ -1092,13 +1092,13 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
 				       true, true, NULL);
 		break;
 	case vmw_du_screen_object:
-		ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, &vfbd->base,
-						  clips, NULL, num_clips,
-						  increment, true, NULL, NULL);
+		ret = vmw_kms_sou_do_bo_dirty(dev_priv, &vfbd->base,
+					      clips, NULL, num_clips,
+					      increment, true, NULL, NULL);
 		break;
 	case vmw_du_legacy:
-		ret = vmw_kms_ldu_do_dmabuf_dirty(dev_priv, &vfbd->base, 0, 0,
-						  clips, num_clips, increment);
+		ret = vmw_kms_ldu_do_bo_dirty(dev_priv, &vfbd->base, 0, 0,
+					      clips, num_clips, increment);
 		break;
 	default:
 		ret = -EINVAL;
@@ -1114,23 +1114,23 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
 	return ret;
 }
 
-static const struct drm_framebuffer_funcs vmw_framebuffer_dmabuf_funcs = {
-	.destroy = vmw_framebuffer_dmabuf_destroy,
-	.dirty = vmw_framebuffer_dmabuf_dirty,
+static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = {
+	.destroy = vmw_framebuffer_bo_destroy,
+	.dirty = vmw_framebuffer_bo_dirty,
 };
 
 /**
- * Pin the dmabuffer in a location suitable for access by the
+ * Pin the bofer in a location suitable for access by the
  * display system.
  */
 static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 {
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct ttm_placement *placement;
 	int ret;
 
-	buf = vfb->dmabuf ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
 		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup;
 
 	if (!buf)
@@ -1139,12 +1139,12 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 	switch (dev_priv->active_display_unit) {
 	case vmw_du_legacy:
 		vmw_overlay_pause_all(dev_priv);
-		ret = vmw_dmabuf_pin_in_start_of_vram(dev_priv, buf, false);
+		ret = vmw_bo_pin_in_start_of_vram(dev_priv, buf, false);
 		vmw_overlay_resume_all(dev_priv);
 		break;
 	case vmw_du_screen_object:
 	case vmw_du_screen_target:
-		if (vfb->dmabuf) {
+		if (vfb->bo) {
 			if (dev_priv->capabilities & SVGA_CAP_3D) {
 				/*
 				 * Use surface DMA to get content to
@@ -1160,8 +1160,7 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 			placement = &vmw_mob_placement;
 		}
 
-		return vmw_dmabuf_pin_in_placement(dev_priv, buf, placement,
-						   false);
+		return vmw_bo_pin_in_placement(dev_priv, buf, placement, false);
 	default:
 		return -EINVAL;
 	}
@@ -1172,36 +1171,36 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 static int vmw_framebuffer_unpin(struct vmw_framebuffer *vfb)
 {
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 
-	buf = vfb->dmabuf ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
 		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup;
 
 	if (WARN_ON(!buf))
 		return 0;
 
-	return vmw_dmabuf_unpin(dev_priv, buf, false);
+	return vmw_bo_unpin(dev_priv, buf, false);
 }
 
 /**
- * vmw_create_dmabuf_proxy - create a proxy surface for the DMA buf
+ * vmw_create_bo_proxy - create a proxy surface for the buffer object
  *
  * @dev: DRM device
  * @mode_cmd: parameters for the new surface
- * @dmabuf_mob: MOB backing the DMA buf
+ * @bo_mob: MOB backing the buffer object
  * @srf_out: newly created surface
  *
- * When the content FB is a DMA buf, we create a surface as a proxy to the
+ * When the content FB is a buffer object, we create a surface as a proxy to the
  * same buffer.  This way we can do a surface copy rather than a surface DMA.
  * This is a more efficient approach
  *
  * RETURNS:
  * 0 on success, error code otherwise
  */
-static int vmw_create_dmabuf_proxy(struct drm_device *dev,
-				   const struct drm_mode_fb_cmd2 *mode_cmd,
-				   struct vmw_dma_buffer *dmabuf_mob,
-				   struct vmw_surface **srf_out)
+static int vmw_create_bo_proxy(struct drm_device *dev,
+			       const struct drm_mode_fb_cmd2 *mode_cmd,
+			       struct vmw_buffer_object *bo_mob,
+			       struct vmw_surface **srf_out)
 {
 	uint32_t format;
 	struct drm_vmw_size content_base_size = {0};
@@ -1239,15 +1238,17 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 	content_base_size.depth  = 1;
 
 	ret = vmw_surface_gb_priv_define(dev,
-			0, /* kernel visible only */
-			0, /* flags */
-			format,
-			true, /* can be a scanout buffer */
-			1, /* num of mip levels */
-			0,
-			0,
-			content_base_size,
-			srf_out);
+					 0, /* kernel visible only */
+					 0, /* flags */
+					 format,
+					 true, /* can be a scanout buffer */
+					 1, /* num of mip levels */
+					 0,
+					 0,
+					 content_base_size,
+					 SVGA3D_MS_PATTERN_NONE,
+					 SVGA3D_MS_QUALITY_NONE,
+					 srf_out);
 	if (ret) {
 		DRM_ERROR("Failed to allocate proxy content buffer\n");
 		return ret;
@@ -1258,8 +1259,8 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 	/* Reserve and switch the backing mob. */
 	mutex_lock(&res->dev_priv->cmdbuf_mutex);
 	(void) vmw_resource_reserve(res, false, true);
-	vmw_dmabuf_unreference(&res->backup);
-	res->backup = vmw_dmabuf_reference(dmabuf_mob);
+	vmw_bo_unreference(&res->backup);
+	res->backup = vmw_bo_reference(bo_mob);
 	res->backup_offset = 0;
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
@@ -1269,21 +1270,21 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 
 
 
-static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv,
-					  struct vmw_dma_buffer *dmabuf,
-					  struct vmw_framebuffer **out,
-					  const struct drm_mode_fb_cmd2
-					  *mode_cmd)
+static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv,
+				      struct vmw_buffer_object *bo,
+				      struct vmw_framebuffer **out,
+				      const struct drm_mode_fb_cmd2
+				      *mode_cmd)
 
 {
 	struct drm_device *dev = dev_priv->dev;
-	struct vmw_framebuffer_dmabuf *vfbd;
+	struct vmw_framebuffer_bo *vfbd;
 	unsigned int requested_size;
 	struct drm_format_name_buf format_name;
 	int ret;
 
 	requested_size = mode_cmd->height * mode_cmd->pitches[0];
-	if (unlikely(requested_size > dmabuf->base.num_pages * PAGE_SIZE)) {
+	if (unlikely(requested_size > bo->base.num_pages * PAGE_SIZE)) {
 		DRM_ERROR("Screen buffer object size is too small "
 			  "for requested mode.\n");
 		return -EINVAL;
@@ -1312,20 +1313,20 @@ static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv,
 	}
 
 	drm_helper_mode_fill_fb_struct(dev, &vfbd->base.base, mode_cmd);
-	vfbd->base.dmabuf = true;
-	vfbd->buffer = vmw_dmabuf_reference(dmabuf);
+	vfbd->base.bo = true;
+	vfbd->buffer = vmw_bo_reference(bo);
 	vfbd->base.user_handle = mode_cmd->handles[0];
 	*out = &vfbd->base;
 
 	ret = drm_framebuffer_init(dev, &vfbd->base.base,
-				   &vmw_framebuffer_dmabuf_funcs);
+				   &vmw_framebuffer_bo_funcs);
 	if (ret)
 		goto out_err2;
 
 	return 0;
 
 out_err2:
-	vmw_dmabuf_unreference(&dmabuf);
+	vmw_bo_unreference(&bo);
 	kfree(vfbd);
 out_err1:
 	return ret;
@@ -1354,57 +1355,57 @@ vmw_kms_srf_ok(struct vmw_private *dev_priv, uint32_t width, uint32_t height)
  * vmw_kms_new_framebuffer - Create a new framebuffer.
  *
  * @dev_priv: Pointer to device private struct.
- * @dmabuf: Pointer to dma buffer to wrap the kms framebuffer around.
- * Either @dmabuf or @surface must be NULL.
+ * @bo: Pointer to buffer object to wrap the kms framebuffer around.
+ * Either @bo or @surface must be NULL.
  * @surface: Pointer to a surface to wrap the kms framebuffer around.
- * Either @dmabuf or @surface must be NULL.
- * @only_2d: No presents will occur to this dma buffer based framebuffer. This
- * Helps the code to do some important optimizations.
+ * Either @bo or @surface must be NULL.
+ * @only_2d: No presents will occur to this buffer object based framebuffer.
+ * This helps the code to do some important optimizations.
  * @mode_cmd: Frame-buffer metadata.
  */
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_dma_buffer *dmabuf,
+			struct vmw_buffer_object *bo,
 			struct vmw_surface *surface,
 			bool only_2d,
 			const struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct vmw_framebuffer *vfb = NULL;
-	bool is_dmabuf_proxy = false;
+	bool is_bo_proxy = false;
 	int ret;
 
 	/*
 	 * We cannot use the SurfaceDMA command in an non-accelerated VM,
-	 * therefore, wrap the DMA buf in a surface so we can use the
+	 * therefore, wrap the buffer object in a surface so we can use the
 	 * SurfaceCopy command.
 	 */
 	if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)  &&
-	    dmabuf && only_2d &&
+	    bo && only_2d &&
 	    mode_cmd->width > 64 &&  /* Don't create a proxy for cursor */
 	    dev_priv->active_display_unit == vmw_du_screen_target) {
-		ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd,
-					      dmabuf, &surface);
+		ret = vmw_create_bo_proxy(dev_priv->dev, mode_cmd,
+					  bo, &surface);
 		if (ret)
 			return ERR_PTR(ret);
 
-		is_dmabuf_proxy = true;
+		is_bo_proxy = true;
 	}
 
 	/* Create the new framebuffer depending one what we have */
 	if (surface) {
 		ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb,
 						      mode_cmd,
-						      is_dmabuf_proxy);
+						      is_bo_proxy);
 
 		/*
-		 * vmw_create_dmabuf_proxy() adds a reference that is no longer
+		 * vmw_create_bo_proxy() adds a reference that is no longer
 		 * needed
 		 */
-		if (is_dmabuf_proxy)
+		if (is_bo_proxy)
 			vmw_surface_unreference(&surface);
-	} else if (dmabuf) {
-		ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, dmabuf, &vfb,
-						     mode_cmd);
+	} else if (bo) {
+		ret = vmw_kms_new_framebuffer_bo(dev_priv, bo, &vfb,
+						 mode_cmd);
 	} else {
 		BUG();
 	}
@@ -1430,23 +1431,10 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	struct vmw_framebuffer *vfb = NULL;
 	struct vmw_surface *surface = NULL;
-	struct vmw_dma_buffer *bo = NULL;
+	struct vmw_buffer_object *bo = NULL;
 	struct ttm_base_object *user_obj;
 	int ret;
 
-	/**
-	 * This code should be conditioned on Screen Objects not being used.
-	 * If screen objects are used, we can allocate a GMR to hold the
-	 * requested framebuffer.
-	 */
-
-	if (!vmw_kms_validate_mode_vram(dev_priv,
-					mode_cmd->pitches[0],
-					mode_cmd->height)) {
-		DRM_ERROR("Requested mode exceed bounding box limit.\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
 	/*
 	 * Take a reference on the user object of the resource
 	 * backing the kms fb. This ensures that user-space handle
@@ -1466,7 +1454,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	 * End conditioned code.
 	 */
 
-	/* returns either a dmabuf or surface */
+	/* returns either a bo or surface */
 	ret = vmw_user_lookup_handle(dev_priv, tfile,
 				     mode_cmd->handles[0],
 				     &surface, &bo);
@@ -1494,7 +1482,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 err_out:
 	/* vmw_user_lookup_handle takes one ref so does new_fb */
 	if (bo)
-		vmw_dmabuf_unreference(&bo);
+		vmw_bo_unreference(&bo);
 	if (surface)
 		vmw_surface_unreference(&surface);
 
@@ -1508,7 +1496,168 @@ err_out:
 	return &vfb->base;
 }
 
+/**
+ * vmw_kms_check_display_memory - Validates display memory required for a
+ * topology
+ * @dev: DRM device
+ * @num_rects: number of drm_rect in rects
+ * @rects: array of drm_rect representing the topology to validate indexed by
+ * crtc index.
+ *
+ * Returns:
+ * 0 on success otherwise negative error code
+ */
+static int vmw_kms_check_display_memory(struct drm_device *dev,
+					uint32_t num_rects,
+					struct drm_rect *rects)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct drm_rect bounding_box = {0};
+	u64 total_pixels = 0, pixel_mem, bb_mem;
+	int i;
+
+	for (i = 0; i < num_rects; i++) {
+		/*
+		 * Currently this check is limiting the topology within max
+		 * texture/screentarget size. This should change in future when
+		 * user-space support multiple fb with topology.
+		 */
+		if (rects[i].x1 < 0 ||  rects[i].y1 < 0 ||
+		    rects[i].x2 > mode_config->max_width ||
+		    rects[i].y2 > mode_config->max_height) {
+			DRM_ERROR("Invalid GUI layout.\n");
+			return -EINVAL;
+		}
+
+		/* Bounding box upper left is at (0,0). */
+		if (rects[i].x2 > bounding_box.x2)
+			bounding_box.x2 = rects[i].x2;
+
+		if (rects[i].y2 > bounding_box.y2)
+			bounding_box.y2 = rects[i].y2;
+
+		total_pixels += (u64) drm_rect_width(&rects[i]) *
+			(u64) drm_rect_height(&rects[i]);
+	}
+
+	/* Virtual svga device primary limits are always in 32-bpp. */
+	pixel_mem = total_pixels * 4;
+
+	/*
+	 * For HV10 and below prim_bb_mem is vram size. When
+	 * SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM is not present vram size is
+	 * limit on primary bounding box
+	 */
+	if (pixel_mem > dev_priv->prim_bb_mem) {
+		DRM_ERROR("Combined output size too large.\n");
+		return -EINVAL;
+	}
+
+	/* SVGA_CAP_NO_BB_RESTRICTION is available for STDU only. */
+	if (dev_priv->active_display_unit != vmw_du_screen_target ||
+	    !(dev_priv->capabilities & SVGA_CAP_NO_BB_RESTRICTION)) {
+		bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4;
+
+		if (bb_mem > dev_priv->prim_bb_mem) {
+			DRM_ERROR("Topology is beyond supported limits.\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * vmw_kms_check_topology - Validates topology in drm_atomic_state
+ * @dev: DRM device
+ * @state: the driver state object
+ *
+ * Returns:
+ * 0 on success otherwise negative error code
+ */
+static int vmw_kms_check_topology(struct drm_device *dev,
+				  struct drm_atomic_state *state)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_rect *rects;
+	struct drm_crtc *crtc;
+	uint32_t i;
+	int ret = 0;
+
+	rects = kcalloc(dev->mode_config.num_crtc, sizeof(struct drm_rect),
+			GFP_KERNEL);
+	if (!rects)
+		return -ENOMEM;
+
+	mutex_lock(&dev_priv->requested_layout_mutex);
+
+	drm_for_each_crtc(crtc, dev) {
+		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+		struct drm_crtc_state *crtc_state = crtc->state;
+
+		i = drm_crtc_index(crtc);
+
+		if (crtc_state && crtc_state->enable) {
+			rects[i].x1 = du->gui_x;
+			rects[i].y1 = du->gui_y;
+			rects[i].x2 = du->gui_x + crtc_state->mode.hdisplay;
+			rects[i].y2 = du->gui_y + crtc_state->mode.vdisplay;
+		}
+	}
+
+	/* Determine change to topology due to new atomic state */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
+				      new_crtc_state, i) {
+		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+		struct drm_connector *connector;
+		struct drm_connector_state *conn_state;
+		struct vmw_connector_state *vmw_conn_state;
+
+		if (!new_crtc_state->enable && old_crtc_state->enable) {
+			rects[i].x1 = 0;
+			rects[i].y1 = 0;
+			rects[i].x2 = 0;
+			rects[i].y2 = 0;
+			continue;
+		}
+
+		if (!du->pref_active) {
+			ret = -EINVAL;
+			goto clean;
+		}
+
+		/*
+		 * For vmwgfx each crtc has only one connector attached and it
+		 * is not changed so don't really need to check the
+		 * crtc->connector_mask and iterate over it.
+		 */
+		connector = &du->connector;
+		conn_state = drm_atomic_get_connector_state(state, connector);
+		if (IS_ERR(conn_state)) {
+			ret = PTR_ERR(conn_state);
+			goto clean;
+		}
+
+		vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+		vmw_conn_state->gui_x = du->gui_x;
+		vmw_conn_state->gui_y = du->gui_y;
+
+		rects[i].x1 = du->gui_x;
+		rects[i].y1 = du->gui_y;
+		rects[i].x2 = du->gui_x + new_crtc_state->mode.hdisplay;
+		rects[i].y2 = du->gui_y + new_crtc_state->mode.vdisplay;
+	}
+
+	ret = vmw_kms_check_display_memory(dev, dev->mode_config.num_crtc,
+					   rects);
 
+clean:
+	mutex_unlock(&dev_priv->requested_layout_mutex);
+	kfree(rects);
+	return ret;
+}
 
 /**
  * vmw_kms_atomic_check_modeset- validate state object for modeset changes
@@ -1520,40 +1669,39 @@ err_out:
  * us to assign a value to mode->crtc_clock so that
  * drm_calc_timestamping_constants() won't throw an error message
  *
- * RETURNS
+ * Returns:
  * Zero for success or -errno
  */
 static int
 vmw_kms_atomic_check_modeset(struct drm_device *dev,
 			     struct drm_atomic_state *state)
 {
-	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	int i;
-
-	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
-		unsigned long requested_bb_mem = 0;
-
-		if (dev_priv->active_display_unit == vmw_du_screen_target) {
-			struct drm_plane *plane = crtc->primary;
-			struct drm_plane_state *plane_state;
-
-			plane_state = drm_atomic_get_new_plane_state(state, plane);
+	struct drm_crtc_state *crtc_state;
+	bool need_modeset = false;
+	int i, ret;
 
-			if (plane_state && plane_state->fb) {
-				int cpp = plane_state->fb->format->cpp[0];
+	ret = drm_atomic_helper_check(dev, state);
+	if (ret)
+		return ret;
 
-				requested_bb_mem += crtc->mode.hdisplay * cpp *
-						    crtc->mode.vdisplay;
-			}
+	if (!state->allow_modeset)
+		return ret;
 
-			if (requested_bb_mem > dev_priv->prim_bb_mem)
-				return -EINVAL;
-		}
+	/*
+	 * Legacy path do not set allow_modeset properly like
+	 * @drm_atomic_helper_update_plane, This will result in unnecessary call
+	 * to vmw_kms_check_topology. So extra set of check.
+	 */
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		if (drm_atomic_crtc_needs_modeset(crtc_state))
+			need_modeset = true;
 	}
 
-	return drm_atomic_helper_check(dev, state);
+	if (need_modeset)
+		return vmw_kms_check_topology(dev, state);
+
+	return ret;
 }
 
 static const struct drm_mode_config_funcs vmw_kms_funcs = {
@@ -1845,40 +1993,49 @@ void vmw_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
 }
 
-
-/*
- * Small shared kms functions.
+/**
+ * vmw_du_update_layout - Update the display unit with topology from resolution
+ * plugin and generate DRM uevent
+ * @dev_priv: device private
+ * @num_rects: number of drm_rect in rects
+ * @rects: toplogy to update
  */
-
-static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
-			 struct drm_vmw_rect *rects)
+static int vmw_du_update_layout(struct vmw_private *dev_priv,
+				unsigned int num_rects, struct drm_rect *rects)
 {
 	struct drm_device *dev = dev_priv->dev;
 	struct vmw_display_unit *du;
 	struct drm_connector *con;
+	struct drm_connector_list_iter conn_iter;
 
-	mutex_lock(&dev->mode_config.mutex);
-
-#if 0
-	{
-		unsigned int i;
-
-		DRM_INFO("%s: new layout ", __func__);
-		for (i = 0; i < num; i++)
-			DRM_INFO("(%i, %i %ux%u) ", rects[i].x, rects[i].y,
-				 rects[i].w, rects[i].h);
-		DRM_INFO("\n");
+	/*
+	 * Currently only gui_x/y is protected with requested_layout_mutex.
+	 */
+	mutex_lock(&dev_priv->requested_layout_mutex);
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(con, &conn_iter) {
+		du = vmw_connector_to_du(con);
+		if (num_rects > du->unit) {
+			du->pref_width = drm_rect_width(&rects[du->unit]);
+			du->pref_height = drm_rect_height(&rects[du->unit]);
+			du->pref_active = true;
+			du->gui_x = rects[du->unit].x1;
+			du->gui_y = rects[du->unit].y1;
+		} else {
+			du->pref_width = 800;
+			du->pref_height = 600;
+			du->pref_active = false;
+			du->gui_x = 0;
+			du->gui_y = 0;
+		}
 	}
-#endif
+	drm_connector_list_iter_end(&conn_iter);
+	mutex_unlock(&dev_priv->requested_layout_mutex);
 
+	mutex_lock(&dev->mode_config.mutex);
 	list_for_each_entry(con, &dev->mode_config.connector_list, head) {
 		du = vmw_connector_to_du(con);
-		if (num > du->unit) {
-			du->pref_width = rects[du->unit].w;
-			du->pref_height = rects[du->unit].h;
-			du->pref_active = true;
-			du->gui_x = rects[du->unit].x;
-			du->gui_y = rects[du->unit].y;
+		if (num_rects > du->unit) {
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   du->gui_x);
@@ -1886,9 +2043,6 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 			  (&con->base, dev->mode_config.suggested_y_property,
 			   du->gui_y);
 		} else {
-			du->pref_width = 800;
-			du->pref_height = 600;
-			du->pref_active = false;
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   0);
@@ -1898,8 +2052,8 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 		}
 		con->status = vmw_du_connector_detect(con, true);
 	}
-
 	mutex_unlock(&dev->mode_config.mutex);
+
 	drm_sysfs_hotplug_event(dev);
 
 	return 0;
@@ -2114,7 +2268,7 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		drm_mode_probed_add(connector, mode);
 	}
 
-	drm_mode_connector_list_update(connector);
+	drm_connector_list_update(connector);
 	/* Move the prefered mode first, help apps pick the right mode. */
 	drm_mode_sort(&connector->modes);
 
@@ -2199,7 +2353,25 @@ vmw_du_connector_atomic_get_property(struct drm_connector *connector,
 	return 0;
 }
 
-
+/**
+ * vmw_kms_update_layout_ioctl - Handler for DRM_VMW_UPDATE_LAYOUT ioctl
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Update preferred topology of display unit as per ioctl request. The topology
+ * is expressed as array of drm_vmw_rect.
+ * e.g.
+ * [0 0 640 480] [640 0 800 600] [0 480 640 480]
+ *
+ * NOTE:
+ * The x and y offset (upper left) in drm_vmw_rect cannot be less than 0. Beside
+ * device limit on topology, x + w and y + h (lower right) cannot be greater
+ * than INT_MAX. So topology beyond these limits will return with error.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
 int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
@@ -2208,15 +2380,12 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		(struct drm_vmw_update_layout_arg *)data;
 	void __user *user_rects;
 	struct drm_vmw_rect *rects;
+	struct drm_rect *drm_rects;
 	unsigned rects_size;
-	int ret;
-	int i;
-	u64 total_pixels = 0;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct drm_vmw_rect bounding_box = {0};
+	int ret, i;
 
 	if (!arg->num_outputs) {
-		struct drm_vmw_rect def_rect = {0, 0, 800, 600};
+		struct drm_rect def_rect = {0, 0, 800, 600};
 		vmw_du_update_layout(dev_priv, 1, &def_rect);
 		return 0;
 	}
@@ -2235,52 +2404,29 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		goto out_free;
 	}
 
-	for (i = 0; i < arg->num_outputs; ++i) {
-		if (rects[i].x < 0 ||
-		    rects[i].y < 0 ||
-		    rects[i].x + rects[i].w > mode_config->max_width ||
-		    rects[i].y + rects[i].h > mode_config->max_height) {
-			DRM_ERROR("Invalid GUI layout.\n");
-			ret = -EINVAL;
-			goto out_free;
-		}
-
-		/*
-		 * bounding_box.w and bunding_box.h are used as
-		 * lower-right coordinates
-		 */
-		if (rects[i].x + rects[i].w > bounding_box.w)
-			bounding_box.w = rects[i].x + rects[i].w;
-
-		if (rects[i].y + rects[i].h > bounding_box.h)
-			bounding_box.h = rects[i].y + rects[i].h;
+	drm_rects = (struct drm_rect *)rects;
 
-		total_pixels += (u64) rects[i].w * (u64) rects[i].h;
-	}
+	for (i = 0; i < arg->num_outputs; i++) {
+		struct drm_vmw_rect curr_rect;
 
-	if (dev_priv->active_display_unit == vmw_du_screen_target) {
-		/*
-		 * For Screen Targets, the limits for a toplogy are:
-		 *	1. Bounding box (assuming 32bpp) must be < prim_bb_mem
-		 *      2. Total pixels (assuming 32bpp) must be < prim_bb_mem
-		 */
-		u64 bb_mem    = (u64) bounding_box.w * bounding_box.h * 4;
-		u64 pixel_mem = total_pixels * 4;
-
-		if (bb_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Topology is beyond supported limits.\n");
-			ret = -EINVAL;
+		/* Verify user-space for overflow as kernel use drm_rect */
+		if ((rects[i].x + rects[i].w > INT_MAX) ||
+		    (rects[i].y + rects[i].h > INT_MAX)) {
+			ret = -ERANGE;
 			goto out_free;
 		}
 
-		if (pixel_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Combined output size too large\n");
-			ret = -EINVAL;
-			goto out_free;
-		}
+		curr_rect = rects[i];
+		drm_rects[i].x1 = curr_rect.x;
+		drm_rects[i].y1 = curr_rect.y;
+		drm_rects[i].x2 = curr_rect.x + curr_rect.w;
+		drm_rects[i].y2 = curr_rect.y + curr_rect.h;
 	}
 
-	vmw_du_update_layout(dev_priv, arg->num_outputs, rects);
+	ret = vmw_kms_check_display_memory(dev, arg->num_outputs, drm_rects);
+
+	if (ret == 0)
+		vmw_du_update_layout(dev_priv, arg->num_outputs, drm_rects);
 
 out_free:
 	kfree(rects);
@@ -2427,7 +2573,7 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
  * interrupted by a signal.
  */
 int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  bool interruptible,
 				  bool validate_as_mob,
 				  bool for_cpu_blit)
@@ -2459,7 +2605,7 @@ int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
  * Helper to be used if an error forces the caller to undo the actions of
  * vmw_kms_helper_buffer_prepare.
  */
-void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf)
+void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf)
 {
 	if (buf)
 		ttm_bo_unreserve(&buf->base);
@@ -2482,7 +2628,7 @@ void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf)
  */
 void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 				  struct drm_file *file_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  struct vmw_fence_obj **out_fence,
 				  struct drm_vmw_fence_rep __user *
 				  user_fence_rep)
@@ -2494,7 +2640,7 @@ void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 	ret = vmw_execbuf_fence_commands(file_priv, dev_priv, &fence,
 					 file_priv ? &handle : NULL);
 	if (buf)
-		vmw_fence_single_bo(&buf->base, fence);
+		vmw_bo_fence_single(&buf->base, fence);
 	if (file_priv)
 		vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv),
 					    ret, user_fence_rep, fence,
@@ -2522,7 +2668,7 @@ void vmw_kms_helper_resource_revert(struct vmw_validation_ctx *ctx)
 	struct vmw_resource *res = ctx->res;
 
 	vmw_kms_helper_buffer_revert(ctx->buf);
-	vmw_dmabuf_unreference(&ctx->buf);
+	vmw_bo_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
@@ -2567,7 +2713,7 @@ int vmw_kms_helper_resource_prepare(struct vmw_resource *res,
 		if (ret)
 			goto out_unreserve;
 
-		ctx->buf = vmw_dmabuf_reference(res->backup);
+		ctx->buf = vmw_bo_reference(res->backup);
 	}
 	ret = vmw_resource_validate(res);
 	if (ret)
@@ -2600,7 +2746,7 @@ void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx,
 		vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf,
 					     out_fence, NULL);
 
-	vmw_dmabuf_unreference(&ctx->buf);
+	vmw_bo_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 27c41c227120..31311298ec0b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -90,7 +90,7 @@ struct vmw_kms_dirty {
 #define vmw_framebuffer_to_vfbs(x) \
 	container_of(x, struct vmw_framebuffer_surface, base.base)
 #define vmw_framebuffer_to_vfbd(x) \
-	container_of(x, struct vmw_framebuffer_dmabuf, base.base)
+	container_of(x, struct vmw_framebuffer_bo, base.base)
 
 /**
  * Base class for framebuffers
@@ -102,7 +102,7 @@ struct vmw_framebuffer {
 	struct drm_framebuffer base;
 	int (*pin)(struct vmw_framebuffer *fb);
 	int (*unpin)(struct vmw_framebuffer *fb);
-	bool dmabuf;
+	bool bo;
 	struct ttm_base_object *user_obj;
 	uint32_t user_handle;
 };
@@ -117,15 +117,15 @@ struct vmw_clip_rect {
 struct vmw_framebuffer_surface {
 	struct vmw_framebuffer base;
 	struct vmw_surface *surface;
-	struct vmw_dma_buffer *buffer;
+	struct vmw_buffer_object *buffer;
 	struct list_head head;
-	bool is_dmabuf_proxy;  /* true if this is proxy surface for DMA buf */
+	bool is_bo_proxy;  /* true if this is proxy surface for DMA buf */
 };
 
 
-struct vmw_framebuffer_dmabuf {
+struct vmw_framebuffer_bo {
 	struct vmw_framebuffer base;
-	struct vmw_dma_buffer *buffer;
+	struct vmw_buffer_object *buffer;
 };
 
 
@@ -161,18 +161,18 @@ struct vmw_crtc_state {
  *
  * @base DRM plane object
  * @surf Display surface for STDU
- * @dmabuf display dmabuf for SOU
+ * @bo display bo for SOU
  * @content_fb_type Used by STDU.
- * @dmabuf_size Size of the dmabuf, used by Screen Object Display Unit
+ * @bo_size Size of the bo, used by Screen Object Display Unit
  * @pinned pin count for STDU display surface
  */
 struct vmw_plane_state {
 	struct drm_plane_state base;
 	struct vmw_surface *surf;
-	struct vmw_dma_buffer *dmabuf;
+	struct vmw_buffer_object *bo;
 
 	int content_fb_type;
-	unsigned long dmabuf_size;
+	unsigned long bo_size;
 
 	int pinned;
 
@@ -192,6 +192,24 @@ struct vmw_connector_state {
 	struct drm_connector_state base;
 
 	bool is_implicit;
+
+	/**
+	 * @gui_x:
+	 *
+	 * vmwgfx connector property representing the x position of this display
+	 * unit (connector is synonymous to display unit) in overall topology.
+	 * This is what the device expect as xRoot while creating screen.
+	 */
+	int gui_x;
+
+	/**
+	 * @gui_y:
+	 *
+	 * vmwgfx connector property representing the y position of this display
+	 * unit (connector is synonymous to display unit) in overall topology.
+	 * This is what the device expect as yRoot while creating screen.
+	 */
+	int gui_y;
 };
 
 /**
@@ -209,7 +227,7 @@ struct vmw_display_unit {
 	struct drm_plane cursor;
 
 	struct vmw_surface *cursor_surface;
-	struct vmw_dma_buffer *cursor_dmabuf;
+	struct vmw_buffer_object *cursor_bo;
 	size_t cursor_age;
 
 	int cursor_x;
@@ -243,7 +261,7 @@ struct vmw_display_unit {
 
 struct vmw_validation_ctx {
 	struct vmw_resource *res;
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 };
 
 #define vmw_crtc_to_du(x) \
@@ -291,14 +309,14 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 			 struct vmw_kms_dirty *dirty);
 
 int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  bool interruptible,
 				  bool validate_as_mob,
 				  bool for_cpu_blit);
-void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf);
+void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf);
 void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 				  struct drm_file *file_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  struct vmw_fence_obj **out_fence,
 				  struct drm_vmw_fence_rep __user *
 				  user_fence_rep);
@@ -316,7 +334,7 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
 		     uint32_t num_clips);
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_dma_buffer *dmabuf,
+			struct vmw_buffer_object *bo,
 			struct vmw_surface *surface,
 			bool only_2d,
 			const struct drm_mode_fb_cmd2 *mode_cmd);
@@ -384,11 +402,11 @@ void vmw_du_connector_destroy_state(struct drm_connector *connector,
  */
 int vmw_kms_ldu_init_display(struct vmw_private *dev_priv);
 int vmw_kms_ldu_close_display(struct vmw_private *dev_priv);
-int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				unsigned flags, unsigned color,
-				struct drm_clip_rect *clips,
-				unsigned num_clips, int increment);
+int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    unsigned int flags, unsigned int color,
+			    struct drm_clip_rect *clips,
+			    unsigned int num_clips, int increment);
 int vmw_kms_update_proxy(struct vmw_resource *res,
 			 const struct drm_clip_rect *clips,
 			 unsigned num_clips,
@@ -408,14 +426,14 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 				 unsigned num_clips, int inc,
 				 struct vmw_fence_obj **out_fence,
 				 struct drm_crtc *crtc);
-int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				struct drm_clip_rect *clips,
-				struct drm_vmw_rect *vclips,
-				unsigned num_clips, int increment,
-				bool interruptible,
-				struct vmw_fence_obj **out_fence,
-				struct drm_crtc *crtc);
+int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    struct drm_clip_rect *clips,
+			    struct drm_vmw_rect *vclips,
+			    unsigned int num_clips, int increment,
+			    bool interruptible,
+			    struct vmw_fence_obj **out_fence,
+			    struct drm_crtc *crtc);
 int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 			 struct drm_file *file_priv,
 			 struct vmw_framebuffer *vfb,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index dc0cfda26b1b..723578117191 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -438,7 +438,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
@@ -547,11 +547,11 @@ int vmw_kms_ldu_close_display(struct vmw_private *dev_priv)
 }
 
 
-int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				unsigned flags, unsigned color,
-				struct drm_clip_rect *clips,
-				unsigned num_clips, int increment)
+int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    unsigned int flags, unsigned int color,
+			    struct drm_clip_rect *clips,
+			    unsigned int num_clips, int increment)
 {
 	size_t fifo_size;
 	int i;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index 0963d0438190..7ed179d30ec5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -225,7 +225,7 @@ static void vmw_takedown_otable_base(struct vmw_private *dev_priv,
 		ret = ttm_bo_reserve(bo, false, true, NULL);
 		BUG_ON(ret != 0);
 
-		vmw_fence_single_bo(bo, NULL);
+		vmw_bo_fence_single(bo, NULL);
 		ttm_bo_unreserve(bo);
 	}
 
@@ -362,7 +362,7 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv,
 	ret = ttm_bo_reserve(bo, false, true, NULL);
 	BUG_ON(ret != 0);
 
-	vmw_fence_single_bo(bo, NULL);
+	vmw_bo_fence_single(bo, NULL);
 	ttm_bo_unreserve(bo);
 
 	ttm_bo_unref(&batch->otable_bo);
@@ -620,7 +620,7 @@ void vmw_mob_unbind(struct vmw_private *dev_priv,
 		vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	}
 	if (bo) {
-		vmw_fence_single_bo(bo, NULL);
+		vmw_bo_fence_single(bo, NULL);
 		ttm_bo_unreserve(bo);
 	}
 	vmw_fifo_resource_dec(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 4437c41c585a..8b9270f31409 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -31,6 +31,7 @@
 #include <linux/frame.h>
 #include <asm/hypervisor.h>
 #include <drm/drmP.h>
+#include "vmwgfx_drv.h"
 #include "vmwgfx_msg.h"
 
 
@@ -234,7 +235,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 
 		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0 ||
 		    (HIGH_WORD(ecx) & MESSAGE_STATUS_HB) == 0) {
-			DRM_ERROR("Failed to get reply size\n");
+			DRM_ERROR("Failed to get reply size for host message.\n");
 			return -EINVAL;
 		}
 
@@ -245,7 +246,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 		reply_len = ebx;
 		reply     = kzalloc(reply_len + 1, GFP_KERNEL);
 		if (!reply) {
-			DRM_ERROR("Cannot allocate memory for reply\n");
+			DRM_ERROR("Cannot allocate memory for host message reply.\n");
 			return -ENOMEM;
 		}
 
@@ -338,7 +339,8 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
 
 	msg = kasprintf(GFP_KERNEL, "info-get %s", guest_info_param);
 	if (!msg) {
-		DRM_ERROR("Cannot allocate memory to get %s", guest_info_param);
+		DRM_ERROR("Cannot allocate memory to get guest info \"%s\".",
+			  guest_info_param);
 		return -ENOMEM;
 	}
 
@@ -374,7 +376,7 @@ out_msg:
 out_open:
 	*length = 0;
 	kfree(msg);
-	DRM_ERROR("Failed to get %s", guest_info_param);
+	DRM_ERROR("Failed to get guest info \"%s\".", guest_info_param);
 
 	return -EINVAL;
 }
@@ -403,7 +405,7 @@ int vmw_host_log(const char *log)
 
 	msg = kasprintf(GFP_KERNEL, "log %s", log);
 	if (!msg) {
-		DRM_ERROR("Cannot allocate memory for log message\n");
+		DRM_ERROR("Cannot allocate memory for host log message.\n");
 		return -ENOMEM;
 	}
 
@@ -422,7 +424,7 @@ out_msg:
 	vmw_close_channel(&channel);
 out_open:
 	kfree(msg);
-	DRM_ERROR("Failed to send log\n");
+	DRM_ERROR("Failed to send host log message.\n");
 
 	return -EINVAL;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index 3ced89e70a64..9f1b9d289bec 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -38,7 +38,7 @@
 #define VMW_OVERLAY_CAP_MASK (SVGA_FIFO_CAP_VIDEO | SVGA_FIFO_CAP_ESCAPE)
 
 struct vmw_stream {
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	bool claimed;
 	bool paused;
 	struct drm_vmw_control_stream_arg saved;
@@ -94,7 +94,7 @@ static inline void fill_flush(struct vmw_escape_video_flush *cmd,
  * -ERESTARTSYS if interrupted by a signal.
  */
 static int vmw_overlay_send_put(struct vmw_private *dev_priv,
-				struct vmw_dma_buffer *buf,
+				struct vmw_buffer_object *buf,
 				struct drm_vmw_control_stream_arg *arg,
 				bool interruptible)
 {
@@ -225,16 +225,16 @@ static int vmw_overlay_send_stop(struct vmw_private *dev_priv,
  * used with GMRs instead of being locked to vram.
  */
 static int vmw_overlay_move_buffer(struct vmw_private *dev_priv,
-				   struct vmw_dma_buffer *buf,
+				   struct vmw_buffer_object *buf,
 				   bool pin, bool inter)
 {
 	if (!pin)
-		return vmw_dmabuf_unpin(dev_priv, buf, inter);
+		return vmw_bo_unpin(dev_priv, buf, inter);
 
 	if (dev_priv->active_display_unit == vmw_du_legacy)
-		return vmw_dmabuf_pin_in_vram(dev_priv, buf, inter);
+		return vmw_bo_pin_in_vram(dev_priv, buf, inter);
 
-	return vmw_dmabuf_pin_in_vram_or_gmr(dev_priv, buf, inter);
+	return vmw_bo_pin_in_vram_or_gmr(dev_priv, buf, inter);
 }
 
 /**
@@ -278,7 +278,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv,
 	}
 
 	if (!pause) {
-		vmw_dmabuf_unreference(&stream->buf);
+		vmw_bo_unreference(&stream->buf);
 		stream->paused = false;
 	} else {
 		stream->paused = true;
@@ -297,7 +297,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv,
  * -ERESTARTSYS if interrupted.
  */
 static int vmw_overlay_update_stream(struct vmw_private *dev_priv,
-				     struct vmw_dma_buffer *buf,
+				     struct vmw_buffer_object *buf,
 				     struct drm_vmw_control_stream_arg *arg,
 				     bool interruptible)
 {
@@ -347,7 +347,7 @@ static int vmw_overlay_update_stream(struct vmw_private *dev_priv,
 	}
 
 	if (stream->buf != buf)
-		stream->buf = vmw_dmabuf_reference(buf);
+		stream->buf = vmw_bo_reference(buf);
 	stream->saved = *arg;
 	/* stream is no longer stopped/paused */
 	stream->paused = false;
@@ -466,7 +466,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 	struct vmw_overlay *overlay = dev_priv->overlay_priv;
 	struct drm_vmw_control_stream_arg *arg =
 	    (struct drm_vmw_control_stream_arg *)data;
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct vmw_resource *res;
 	int ret;
 
@@ -484,13 +484,13 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
-	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, arg->handle, &buf, NULL);
 	if (ret)
 		goto out_unlock;
 
 	ret = vmw_overlay_update_stream(dev_priv, buf, arg, true);
 
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 
 out_unlock:
 	mutex_unlock(&overlay->mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 3063a3e4bd40..92003ea5a219 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -27,7 +27,6 @@
 
 #include "vmwgfx_drv.h"
 #include <drm/vmwgfx_drm.h>
-#include <drm/ttm/ttm_object.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/drmP.h>
 #include "vmwgfx_resource_priv.h"
@@ -35,29 +34,6 @@
 
 #define VMW_RES_EVICT_ERR_COUNT 10
 
-struct vmw_user_dma_buffer {
-	struct ttm_prime_object prime;
-	struct vmw_dma_buffer dma;
-};
-
-struct vmw_bo_user_rep {
-	uint32_t handle;
-	uint64_t map_handle;
-};
-
-static inline struct vmw_dma_buffer *
-vmw_dma_buffer(struct ttm_buffer_object *bo)
-{
-	return container_of(bo, struct vmw_dma_buffer, base);
-}
-
-static inline struct vmw_user_dma_buffer *
-vmw_user_dma_buffer(struct ttm_buffer_object *bo)
-{
-	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
-	return container_of(vmw_bo, struct vmw_user_dma_buffer, dma);
-}
-
 struct vmw_resource *vmw_resource_reference(struct vmw_resource *res)
 {
 	kref_get(&res->kref);
@@ -116,7 +92,7 @@ static void vmw_resource_release(struct kref *kref)
 		res->backup_dirty = false;
 		list_del_init(&res->mob_head);
 		ttm_bo_unreserve(bo);
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 	}
 
 	if (likely(res->hw_destroy != NULL)) {
@@ -287,7 +263,7 @@ out_bad_resource:
 }
 
 /**
- * Helper function that looks either a surface or dmabuf.
+ * Helper function that looks either a surface or bo.
  *
  * The pointer this pointed at by out_surf and out_buf needs to be null.
  */
@@ -295,7 +271,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 			   struct ttm_object_file *tfile,
 			   uint32_t handle,
 			   struct vmw_surface **out_surf,
-			   struct vmw_dma_buffer **out_buf)
+			   struct vmw_buffer_object **out_buf)
 {
 	struct vmw_resource *res;
 	int ret;
@@ -311,513 +287,11 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 	}
 
 	*out_surf = NULL;
-	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, handle, out_buf, NULL);
 	return ret;
 }
 
 /**
- * Buffer management.
- */
-
-/**
- * vmw_dmabuf_acc_size - Calculate the pinned memory usage of buffers
- *
- * @dev_priv: Pointer to a struct vmw_private identifying the device.
- * @size: The requested buffer size.
- * @user: Whether this is an ordinary dma buffer or a user dma buffer.
- */
-static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size,
-				  bool user)
-{
-	static size_t struct_size, user_struct_size;
-	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
-
-	if (unlikely(struct_size == 0)) {
-		size_t backend_size = ttm_round_pot(vmw_tt_size);
-
-		struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_dma_buffer));
-		user_struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_user_dma_buffer));
-	}
-
-	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
-		page_array_size +=
-			ttm_round_pot(num_pages * sizeof(dma_addr_t));
-
-	return ((user) ? user_struct_size : struct_size) +
-		page_array_size;
-}
-
-void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo)
-{
-	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
-
-	vmw_dma_buffer_unmap(vmw_bo);
-	kfree(vmw_bo);
-}
-
-static void vmw_user_dmabuf_destroy(struct ttm_buffer_object *bo)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo);
-
-	vmw_dma_buffer_unmap(&vmw_user_bo->dma);
-	ttm_prime_object_kfree(vmw_user_bo, prime);
-}
-
-int vmw_dmabuf_init(struct vmw_private *dev_priv,
-		    struct vmw_dma_buffer *vmw_bo,
-		    size_t size, struct ttm_placement *placement,
-		    bool interruptible,
-		    void (*bo_free) (struct ttm_buffer_object *bo))
-{
-	struct ttm_bo_device *bdev = &dev_priv->bdev;
-	size_t acc_size;
-	int ret;
-	bool user = (bo_free == &vmw_user_dmabuf_destroy);
-
-	BUG_ON(!bo_free && (!user && (bo_free != vmw_dmabuf_bo_free)));
-
-	acc_size = vmw_dmabuf_acc_size(dev_priv, size, user);
-	memset(vmw_bo, 0, sizeof(*vmw_bo));
-
-	INIT_LIST_HEAD(&vmw_bo->res_list);
-
-	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
-			  ttm_bo_type_device, placement,
-			  0, interruptible, acc_size,
-			  NULL, NULL, bo_free);
-	return ret;
-}
-
-static void vmw_user_dmabuf_release(struct ttm_base_object **p_base)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo;
-	struct ttm_base_object *base = *p_base;
-	struct ttm_buffer_object *bo;
-
-	*p_base = NULL;
-
-	if (unlikely(base == NULL))
-		return;
-
-	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
-				   prime.base);
-	bo = &vmw_user_bo->dma.base;
-	ttm_bo_unref(&bo);
-}
-
-static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base,
-					    enum ttm_ref_type ref_type)
-{
-	struct vmw_user_dma_buffer *user_bo;
-	user_bo = container_of(base, struct vmw_user_dma_buffer, prime.base);
-
-	switch (ref_type) {
-	case TTM_REF_SYNCCPU_WRITE:
-		ttm_bo_synccpu_write_release(&user_bo->dma.base);
-		break;
-	default:
-		BUG();
-	}
-}
-
-/**
- * vmw_user_dmabuf_alloc - Allocate a user dma buffer
- *
- * @dev_priv: Pointer to a struct device private.
- * @tfile: Pointer to a struct ttm_object_file on which to register the user
- * object.
- * @size: Size of the dma buffer.
- * @shareable: Boolean whether the buffer is shareable with other open files.
- * @handle: Pointer to where the handle value should be assigned.
- * @p_dma_buf: Pointer to where the refcounted struct vmw_dma_buffer pointer
- * should be assigned.
- */
-int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
-			  struct ttm_object_file *tfile,
-			  uint32_t size,
-			  bool shareable,
-			  uint32_t *handle,
-			  struct vmw_dma_buffer **p_dma_buf,
-			  struct ttm_base_object **p_base)
-{
-	struct vmw_user_dma_buffer *user_bo;
-	struct ttm_buffer_object *tmp;
-	int ret;
-
-	user_bo = kzalloc(sizeof(*user_bo), GFP_KERNEL);
-	if (unlikely(!user_bo)) {
-		DRM_ERROR("Failed to allocate a buffer.\n");
-		return -ENOMEM;
-	}
-
-	ret = vmw_dmabuf_init(dev_priv, &user_bo->dma, size,
-			      (dev_priv->has_mob) ?
-			      &vmw_sys_placement :
-			      &vmw_vram_sys_placement, true,
-			      &vmw_user_dmabuf_destroy);
-	if (unlikely(ret != 0))
-		return ret;
-
-	tmp = ttm_bo_reference(&user_bo->dma.base);
-	ret = ttm_prime_object_init(tfile,
-				    size,
-				    &user_bo->prime,
-				    shareable,
-				    ttm_buffer_type,
-				    &vmw_user_dmabuf_release,
-				    &vmw_user_dmabuf_ref_obj_release);
-	if (unlikely(ret != 0)) {
-		ttm_bo_unref(&tmp);
-		goto out_no_base_object;
-	}
-
-	*p_dma_buf = &user_bo->dma;
-	if (p_base) {
-		*p_base = &user_bo->prime.base;
-		kref_get(&(*p_base)->refcount);
-	}
-	*handle = user_bo->prime.base.hash.key;
-
-out_no_base_object:
-	return ret;
-}
-
-/**
- * vmw_user_dmabuf_verify_access - verify access permissions on this
- * buffer object.
- *
- * @bo: Pointer to the buffer object being accessed
- * @tfile: Identifying the caller.
- */
-int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
-				  struct ttm_object_file *tfile)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo;
-
-	if (unlikely(bo->destroy != vmw_user_dmabuf_destroy))
-		return -EPERM;
-
-	vmw_user_bo = vmw_user_dma_buffer(bo);
-
-	/* Check that the caller has opened the object. */
-	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
-		return 0;
-
-	DRM_ERROR("Could not grant buffer access.\n");
-	return -EPERM;
-}
-
-/**
- * vmw_user_dmabuf_synccpu_grab - Grab a struct vmw_user_dma_buffer for cpu
- * access, idling previous GPU operations on the buffer and optionally
- * blocking it for further command submissions.
- *
- * @user_bo: Pointer to the buffer object being grabbed for CPU access
- * @tfile: Identifying the caller.
- * @flags: Flags indicating how the grab should be performed.
- *
- * A blocking grab will be automatically released when @tfile is closed.
- */
-static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
-					struct ttm_object_file *tfile,
-					uint32_t flags)
-{
-	struct ttm_buffer_object *bo = &user_bo->dma.base;
-	bool existed;
-	int ret;
-
-	if (flags & drm_vmw_synccpu_allow_cs) {
-		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
-		long lret;
-
-		lret = reservation_object_wait_timeout_rcu(bo->resv, true, true,
-							   nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
-		if (!lret)
-			return -EBUSY;
-		else if (lret < 0)
-			return lret;
-		return 0;
-	}
-
-	ret = ttm_bo_synccpu_write_grab
-		(bo, !!(flags & drm_vmw_synccpu_dontblock));
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
-				 TTM_REF_SYNCCPU_WRITE, &existed, false);
-	if (ret != 0 || existed)
-		ttm_bo_synccpu_write_release(&user_bo->dma.base);
-
-	return ret;
-}
-
-/**
- * vmw_user_dmabuf_synccpu_release - Release a previous grab for CPU access,
- * and unblock command submission on the buffer if blocked.
- *
- * @handle: Handle identifying the buffer object.
- * @tfile: Identifying the caller.
- * @flags: Flags indicating the type of release.
- */
-static int vmw_user_dmabuf_synccpu_release(uint32_t handle,
-					   struct ttm_object_file *tfile,
-					   uint32_t flags)
-{
-	if (!(flags & drm_vmw_synccpu_allow_cs))
-		return ttm_ref_object_base_unref(tfile, handle,
-						 TTM_REF_SYNCCPU_WRITE);
-
-	return 0;
-}
-
-/**
- * vmw_user_dmabuf_synccpu_release - ioctl function implementing the synccpu
- * functionality.
- *
- * @dev: Identifies the drm device.
- * @data: Pointer to the ioctl argument.
- * @file_priv: Identifies the caller.
- *
- * This function checks the ioctl arguments for validity and calls the
- * relevant synccpu functions.
- */
-int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv)
-{
-	struct drm_vmw_synccpu_arg *arg =
-		(struct drm_vmw_synccpu_arg *) data;
-	struct vmw_dma_buffer *dma_buf;
-	struct vmw_user_dma_buffer *user_bo;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct ttm_base_object *buffer_base;
-	int ret;
-
-	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
-	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
-			       drm_vmw_synccpu_dontblock |
-			       drm_vmw_synccpu_allow_cs)) != 0) {
-		DRM_ERROR("Illegal synccpu flags.\n");
-		return -EINVAL;
-	}
-
-	switch (arg->op) {
-	case drm_vmw_synccpu_grab:
-		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf,
-					     &buffer_base);
-		if (unlikely(ret != 0))
-			return ret;
-
-		user_bo = container_of(dma_buf, struct vmw_user_dma_buffer,
-				       dma);
-		ret = vmw_user_dmabuf_synccpu_grab(user_bo, tfile, arg->flags);
-		vmw_dmabuf_unreference(&dma_buf);
-		ttm_base_object_unref(&buffer_base);
-		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
-			     ret != -EBUSY)) {
-			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
-				  (unsigned int) arg->handle);
-			return ret;
-		}
-		break;
-	case drm_vmw_synccpu_release:
-		ret = vmw_user_dmabuf_synccpu_release(arg->handle, tfile,
-						      arg->flags);
-		if (unlikely(ret != 0)) {
-			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
-				  (unsigned int) arg->handle);
-			return ret;
-		}
-		break;
-	default:
-		DRM_ERROR("Invalid synccpu operation.\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	union drm_vmw_alloc_dmabuf_arg *arg =
-	    (union drm_vmw_alloc_dmabuf_arg *)data;
-	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
-	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
-	struct vmw_dma_buffer *dma_buf;
-	uint32_t handle;
-	int ret;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    req->size, false, &handle, &dma_buf,
-				    NULL);
-	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
-
-	rep->handle = handle;
-	rep->map_handle = drm_vma_node_offset_addr(&dma_buf->base.vma_node);
-	rep->cur_gmr_id = handle;
-	rep->cur_gmr_offset = 0;
-
-	vmw_dmabuf_unreference(&dma_buf);
-
-out_no_dmabuf:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-
-	return ret;
-}
-
-int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv)
-{
-	struct drm_vmw_unref_dmabuf_arg *arg =
-	    (struct drm_vmw_unref_dmabuf_arg *)data;
-
-	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					 arg->handle,
-					 TTM_REF_USAGE);
-}
-
-int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-			   uint32_t handle, struct vmw_dma_buffer **out,
-			   struct ttm_base_object **p_base)
-{
-	struct vmw_user_dma_buffer *vmw_user_bo;
-	struct ttm_base_object *base;
-
-	base = ttm_base_object_lookup(tfile, handle);
-	if (unlikely(base == NULL)) {
-		pr_err("Invalid buffer object handle 0x%08lx\n",
-		       (unsigned long)handle);
-		return -ESRCH;
-	}
-
-	if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
-		ttm_base_object_unref(&base);
-		pr_err("Invalid buffer object handle 0x%08lx\n",
-		       (unsigned long)handle);
-		return -EINVAL;
-	}
-
-	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
-				   prime.base);
-	(void)ttm_bo_reference(&vmw_user_bo->dma.base);
-	if (p_base)
-		*p_base = base;
-	else
-		ttm_base_object_unref(&base);
-	*out = &vmw_user_bo->dma;
-
-	return 0;
-}
-
-int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
-			      struct vmw_dma_buffer *dma_buf,
-			      uint32_t *handle)
-{
-	struct vmw_user_dma_buffer *user_bo;
-
-	if (dma_buf->base.destroy != vmw_user_dmabuf_destroy)
-		return -EINVAL;
-
-	user_bo = container_of(dma_buf, struct vmw_user_dma_buffer, dma);
-
-	*handle = user_bo->prime.base.hash.key;
-	return ttm_ref_object_add(tfile, &user_bo->prime.base,
-				  TTM_REF_USAGE, NULL, false);
-}
-
-/**
- * vmw_dumb_create - Create a dumb kms buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @args: Pointer to a struct drm_mode_create_dumb structure
- *
- * This is a driver callback for the core drm create_dumb functionality.
- * Note that this is very similar to the vmw_dmabuf_alloc ioctl, except
- * that the arguments have a different format.
- */
-int vmw_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_dma_buffer *dma_buf;
-	int ret;
-
-	args->pitch = args->width * ((args->bpp + 7) / 8);
-	args->size = args->pitch * args->height;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    args->size, false, &args->handle,
-				    &dma_buf, NULL);
-	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
-
-	vmw_dmabuf_unreference(&dma_buf);
-out_no_dmabuf:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dumb_map_offset - Return the address space offset of a dumb buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @handle: Handle identifying the dumb buffer.
- * @offset: The address space offset returned.
- *
- * This is a driver callback for the core drm dumb_map_offset functionality.
- */
-int vmw_dumb_map_offset(struct drm_file *file_priv,
-			struct drm_device *dev, uint32_t handle,
-			uint64_t *offset)
-{
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_dma_buffer *out_buf;
-	int ret;
-
-	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf, NULL);
-	if (ret != 0)
-		return -EINVAL;
-
-	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
-	vmw_dmabuf_unreference(&out_buf);
-	return 0;
-}
-
-/**
- * vmw_dumb_destroy - Destroy a dumb boffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @handle: Handle identifying the dumb buffer.
- *
- * This is a driver callback for the core drm dumb_destroy functionality.
- */
-int vmw_dumb_destroy(struct drm_file *file_priv,
-		     struct drm_device *dev,
-		     uint32_t handle)
-{
-	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					 handle, TTM_REF_USAGE);
-}
-
-/**
  * vmw_resource_buf_alloc - Allocate a backup buffer for a resource.
  *
  * @res:            The resource for which to allocate a backup buffer.
@@ -829,7 +303,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res,
 {
 	unsigned long size =
 		(res->backup_size + PAGE_SIZE - 1) & PAGE_MASK;
-	struct vmw_dma_buffer *backup;
+	struct vmw_buffer_object *backup;
 	int ret;
 
 	if (likely(res->backup)) {
@@ -841,16 +315,16 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res,
 	if (unlikely(!backup))
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(res->dev_priv, backup, res->backup_size,
+	ret = vmw_bo_init(res->dev_priv, backup, res->backup_size,
 			      res->func->backup_placement,
 			      interruptible,
-			      &vmw_dmabuf_bo_free);
+			      &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
+		goto out_no_bo;
 
 	res->backup = backup;
 
-out_no_dmabuf:
+out_no_bo:
 	return ret;
 }
 
@@ -919,7 +393,7 @@ out_bind_failed:
  */
 void vmw_resource_unreserve(struct vmw_resource *res,
 			    bool switch_backup,
-			    struct vmw_dma_buffer *new_backup,
+			    struct vmw_buffer_object *new_backup,
 			    unsigned long new_backup_offset)
 {
 	struct vmw_private *dev_priv = res->dev_priv;
@@ -931,11 +405,11 @@ void vmw_resource_unreserve(struct vmw_resource *res,
 		if (res->backup) {
 			lockdep_assert_held(&res->backup->base.resv->lock.base);
 			list_del_init(&res->mob_head);
-			vmw_dmabuf_unreference(&res->backup);
+			vmw_bo_unreference(&res->backup);
 		}
 
 		if (new_backup) {
-			res->backup = vmw_dmabuf_reference(new_backup);
+			res->backup = vmw_bo_reference(new_backup);
 			lockdep_assert_held(&new_backup->base.resv->lock.base);
 			list_add_tail(&res->mob_head, &new_backup->res_list);
 		} else {
@@ -959,6 +433,7 @@ void vmw_resource_unreserve(struct vmw_resource *res,
  *                             for a resource and in that case, allocate
  *                             one, reserve and validate it.
  *
+ * @ticket:         The ww aqcquire context to use, or NULL if trylocking.
  * @res:            The resource for which to allocate a backup buffer.
  * @interruptible:  Whether any sleeps during allocation should be
  *                  performed while interruptible.
@@ -966,7 +441,8 @@ void vmw_resource_unreserve(struct vmw_resource *res,
  *                  reserved and validated backup buffer.
  */
 static int
-vmw_resource_check_buffer(struct vmw_resource *res,
+vmw_resource_check_buffer(struct ww_acquire_ctx *ticket,
+			  struct vmw_resource *res,
 			  bool interruptible,
 			  struct ttm_validate_buffer *val_buf)
 {
@@ -985,7 +461,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
 	val_buf->shared = false;
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible, NULL);
+	ret = ttm_eu_reserve_buffers(ticket, &val_list, interruptible, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
@@ -1003,11 +479,11 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	return 0;
 
 out_no_validate:
-	ttm_eu_backoff_reservation(NULL, &val_list);
+	ttm_eu_backoff_reservation(ticket, &val_list);
 out_no_reserve:
 	ttm_bo_unref(&val_buf->bo);
 	if (backup_dirty)
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 
 	return ret;
 }
@@ -1050,10 +526,12 @@ int vmw_resource_reserve(struct vmw_resource *res, bool interruptible,
  * vmw_resource_backoff_reservation - Unreserve and unreference a
  *                                    backup buffer
  *.
+ * @ticket:         The ww acquire ctx used for reservation.
  * @val_buf:        Backup buffer information.
  */
 static void
-vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
+vmw_resource_backoff_reservation(struct ww_acquire_ctx *ticket,
+				 struct ttm_validate_buffer *val_buf)
 {
 	struct list_head val_list;
 
@@ -1062,7 +540,7 @@ vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
 
 	INIT_LIST_HEAD(&val_list);
 	list_add_tail(&val_buf->head, &val_list);
-	ttm_eu_backoff_reservation(NULL, &val_list);
+	ttm_eu_backoff_reservation(ticket, &val_list);
 	ttm_bo_unref(&val_buf->bo);
 }
 
@@ -1070,10 +548,12 @@ vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
  * vmw_resource_do_evict - Evict a resource, and transfer its data
  *                         to a backup buffer.
  *
+ * @ticket:         The ww acquire ticket to use, or NULL if trylocking.
  * @res:            The resource to evict.
  * @interruptible:  Whether to wait interruptible.
  */
-static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
+static int vmw_resource_do_evict(struct ww_acquire_ctx *ticket,
+				 struct vmw_resource *res, bool interruptible)
 {
 	struct ttm_validate_buffer val_buf;
 	const struct vmw_res_func *func = res->func;
@@ -1083,7 +563,7 @@ static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 
 	val_buf.bo = NULL;
 	val_buf.shared = false;
-	ret = vmw_resource_check_buffer(res, interruptible, &val_buf);
+	ret = vmw_resource_check_buffer(ticket, res, interruptible, &val_buf);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -1098,7 +578,7 @@ static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 	res->backup_dirty = true;
 	res->res_dirty = false;
 out_no_unbind:
-	vmw_resource_backoff_reservation(&val_buf);
+	vmw_resource_backoff_reservation(ticket, &val_buf);
 
 	return ret;
 }
@@ -1152,7 +632,8 @@ int vmw_resource_validate(struct vmw_resource *res)
 
 		write_unlock(&dev_priv->resource_lock);
 
-		ret = vmw_resource_do_evict(evict_res, true);
+		/* Trylock backup buffers with a NULL ticket. */
+		ret = vmw_resource_do_evict(NULL, evict_res, true);
 		if (unlikely(ret != 0)) {
 			write_lock(&dev_priv->resource_lock);
 			list_add_tail(&evict_res->lru_head, lru_list);
@@ -1171,7 +652,7 @@ int vmw_resource_validate(struct vmw_resource *res)
 		goto out_no_validate;
 	else if (!res->func->needs_backup && res->backup) {
 		list_del_init(&res->mob_head);
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 	}
 
 	return 0;
@@ -1180,109 +661,39 @@ out_no_validate:
 	return ret;
 }
 
-/**
- * vmw_fence_single_bo - Utility function to fence a single TTM buffer
- *                       object without unreserving it.
- *
- * @bo:             Pointer to the struct ttm_buffer_object to fence.
- * @fence:          Pointer to the fence. If NULL, this function will
- *                  insert a fence into the command stream..
- *
- * Contrary to the ttm_eu version of this function, it takes only
- * a single buffer object instead of a list, and it also doesn't
- * unreserve the buffer object, which needs to be done separately.
- */
-void vmw_fence_single_bo(struct ttm_buffer_object *bo,
-			 struct vmw_fence_obj *fence)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-
-	struct vmw_private *dev_priv =
-		container_of(bdev, struct vmw_private, bdev);
-
-	if (fence == NULL) {
-		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-		reservation_object_add_excl_fence(bo->resv, &fence->base);
-		dma_fence_put(&fence->base);
-	} else
-		reservation_object_add_excl_fence(bo->resv, &fence->base);
-}
 
 /**
- * vmw_resource_move_notify - TTM move_notify_callback
+ * vmw_resource_unbind_list
  *
- * @bo: The TTM buffer object about to move.
- * @mem: The struct ttm_mem_reg indicating to what memory
- *       region the move is taking place.
+ * @vbo: Pointer to the current backing MOB.
  *
  * Evicts the Guest Backed hardware resource if the backup
  * buffer is being moved out of MOB memory.
- * Note that this function should not race with the resource
- * validation code as long as it accesses only members of struct
- * resource that remain static while bo::res is !NULL and
- * while we have @bo reserved. struct resource::backup is *not* a
- * static member. The resource validation code will take care
- * to set @bo::res to NULL, while having @bo reserved when the
- * buffer is no longer bound to the resource, so @bo:res can be
- * used to determine whether there is a need to unbind and whether
- * it is safe to unbind.
+ * Note that this function will not race with the resource
+ * validation code, since resource validation and eviction
+ * both require the backup buffer to be reserved.
  */
-void vmw_resource_move_notify(struct ttm_buffer_object *bo,
-			      struct ttm_mem_reg *mem)
+void vmw_resource_unbind_list(struct vmw_buffer_object *vbo)
 {
-	struct vmw_dma_buffer *dma_buf;
-
-	if (mem == NULL)
-		return;
-
-	if (bo->destroy != vmw_dmabuf_bo_free &&
-	    bo->destroy != vmw_user_dmabuf_destroy)
-		return;
-
-	dma_buf = container_of(bo, struct vmw_dma_buffer, base);
-
-	/*
-	 * Kill any cached kernel maps before move. An optimization could
-	 * be to do this iff source or destination memory type is VRAM.
-	 */
-	vmw_dma_buffer_unmap(dma_buf);
 
-	if (mem->mem_type != VMW_PL_MOB) {
-		struct vmw_resource *res, *n;
-		struct ttm_validate_buffer val_buf;
+	struct vmw_resource *res, *next;
+	struct ttm_validate_buffer val_buf = {
+		.bo = &vbo->base,
+		.shared = false
+	};
 
-		val_buf.bo = bo;
-		val_buf.shared = false;
+	lockdep_assert_held(&vbo->base.resv->lock.base);
+	list_for_each_entry_safe(res, next, &vbo->res_list, mob_head) {
+		if (!res->func->unbind)
+			continue;
 
-		list_for_each_entry_safe(res, n, &dma_buf->res_list, mob_head) {
-
-			if (unlikely(res->func->unbind == NULL))
-				continue;
-
-			(void) res->func->unbind(res, true, &val_buf);
-			res->backup_dirty = true;
-			res->res_dirty = false;
-			list_del_init(&res->mob_head);
-		}
-
-		(void) ttm_bo_wait(bo, false, false);
+		(void) res->func->unbind(res, true, &val_buf);
+		res->backup_dirty = true;
+		res->res_dirty = false;
+		list_del_init(&res->mob_head);
 	}
-}
-
-
-/**
- * vmw_resource_swap_notify - swapout notify callback.
- *
- * @bo: The buffer object to be swapped out.
- */
-void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
-{
-	if (bo->destroy != vmw_dmabuf_bo_free &&
-	    bo->destroy != vmw_user_dmabuf_destroy)
-		return;
 
-	/* Kill any cached kernel maps before swapout */
-	vmw_dma_buffer_unmap(vmw_dma_buffer(bo));
+	(void) ttm_bo_wait(&vbo->base, false, false);
 }
 
 
@@ -1294,7 +705,7 @@ void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
  * Read back cached states from the device if they exist.  This function
  * assumings binding_mutex is held.
  */
-int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob)
+int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob)
 {
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_private *dev_priv;
@@ -1344,7 +755,7 @@ int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob)
 void vmw_query_move_notify(struct ttm_buffer_object *bo,
 			   struct ttm_mem_reg *mem)
 {
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct vmw_private *dev_priv;
 
@@ -1353,7 +764,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo,
 
 	mutex_lock(&dev_priv->binding_mutex);
 
-	dx_query_mob = container_of(bo, struct vmw_dma_buffer, base);
+	dx_query_mob = container_of(bo, struct vmw_buffer_object, base);
 	if (mem == NULL || !dx_query_mob || !dx_query_mob->dx_query_ctx) {
 		mutex_unlock(&dev_priv->binding_mutex);
 		return;
@@ -1368,7 +779,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo,
 
 		/* Create a fence and attach the BO to it */
 		(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-		vmw_fence_single_bo(bo, fence);
+		vmw_bo_fence_single(bo, fence);
 
 		if (fence != NULL)
 			vmw_fence_obj_unreference(&fence);
@@ -1405,6 +816,7 @@ static void vmw_resource_evict_type(struct vmw_private *dev_priv,
 	struct vmw_resource *evict_res;
 	unsigned err_count = 0;
 	int ret;
+	struct ww_acquire_ctx ticket;
 
 	do {
 		write_lock(&dev_priv->resource_lock);
@@ -1418,7 +830,8 @@ static void vmw_resource_evict_type(struct vmw_private *dev_priv,
 		list_del_init(&evict_res->lru_head);
 		write_unlock(&dev_priv->resource_lock);
 
-		ret = vmw_resource_do_evict(evict_res, false);
+		/* Wait lock backup buffers with a ticket. */
+		ret = vmw_resource_do_evict(&ticket, evict_res, false);
 		if (unlikely(ret != 0)) {
 			write_lock(&dev_priv->resource_lock);
 			list_add_tail(&evict_res->lru_head, lru_list);
@@ -1481,7 +894,7 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible)
 		goto out_no_reserve;
 
 	if (res->pin_count == 0) {
-		struct vmw_dma_buffer *vbo = NULL;
+		struct vmw_buffer_object *vbo = NULL;
 
 		if (res->backup) {
 			vbo = res->backup;
@@ -1539,7 +952,7 @@ void vmw_resource_unpin(struct vmw_resource *res)
 
 	WARN_ON(res->pin_count == 0);
 	if (--res->pin_count == 0 && res->backup) {
-		struct vmw_dma_buffer *vbo = res->backup;
+		struct vmw_buffer_object *vbo = res->backup;
 
 		(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
 		vmw_bo_pin_reserved(vbo, false);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 73cf3c6e1591..ad0de7f0cd60 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -66,7 +66,7 @@ struct vmw_kms_sou_readback_blit {
 	SVGAFifoCmdBlitScreenToGMRFB body;
 };
 
-struct vmw_kms_sou_dmabuf_blit {
+struct vmw_kms_sou_bo_blit {
 	uint32 header;
 	SVGAFifoCmdBlitGMRFBToScreen body;
 };
@@ -83,7 +83,7 @@ struct vmw_screen_object_unit {
 	struct vmw_display_unit base;
 
 	unsigned long buffer_size; /**< Size of allocated buffer */
-	struct vmw_dma_buffer *buffer; /**< Backing store buffer */
+	struct vmw_buffer_object *buffer; /**< Backing store buffer */
 
 	bool defined;
 };
@@ -109,7 +109,7 @@ static void vmw_sou_crtc_destroy(struct drm_crtc *crtc)
  */
 static int vmw_sou_fifo_create(struct vmw_private *dev_priv,
 			       struct vmw_screen_object_unit *sou,
-			       uint32_t x, uint32_t y,
+			       int x, int y,
 			       struct drm_display_mode *mode)
 {
 	size_t fifo_size;
@@ -139,13 +139,8 @@ static int vmw_sou_fifo_create(struct vmw_private *dev_priv,
 		(sou->base.unit == 0 ? SVGA_SCREEN_IS_PRIMARY : 0);
 	cmd->obj.size.width = mode->hdisplay;
 	cmd->obj.size.height = mode->vdisplay;
-	if (sou->base.is_implicit) {
-		cmd->obj.root.x = x;
-		cmd->obj.root.y = y;
-	} else {
-		cmd->obj.root.x = sou->base.gui_x;
-		cmd->obj.root.y = sou->base.gui_y;
-	}
+	cmd->obj.root.x = x;
+	cmd->obj.root.y = y;
 	sou->base.set_gui_x = cmd->obj.root.x;
 	sou->base.set_gui_y = cmd->obj.root.y;
 
@@ -222,12 +217,11 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	struct vmw_plane_state *vps;
 	int ret;
 
-
-	sou      = vmw_crtc_to_sou(crtc);
+	sou = vmw_crtc_to_sou(crtc);
 	dev_priv = vmw_priv(crtc->dev);
-	ps       = crtc->primary->state;
-	fb       = ps->fb;
-	vps      = vmw_plane_state_to_vps(ps);
+	ps = crtc->primary->state;
+	fb = ps->fb;
+	vps = vmw_plane_state_to_vps(ps);
 
 	vfb = (fb) ? vmw_framebuffer_to_vfb(fb) : NULL;
 
@@ -240,11 +234,25 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	}
 
 	if (vfb) {
-		sou->buffer = vps->dmabuf;
-		sou->buffer_size = vps->dmabuf_size;
+		struct drm_connector_state *conn_state;
+		struct vmw_connector_state *vmw_conn_state;
+		int x, y;
+
+		sou->buffer = vps->bo;
+		sou->buffer_size = vps->bo_size;
+
+		if (sou->base.is_implicit) {
+			x = crtc->x;
+			y = crtc->y;
+		} else {
+			conn_state = sou->base.connector.state;
+			vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+
+			x = vmw_conn_state->gui_x;
+			y = vmw_conn_state->gui_y;
+		}
 
-		ret = vmw_sou_fifo_create(dev_priv, sou, crtc->x, crtc->y,
-					  &crtc->mode);
+		ret = vmw_sou_fifo_create(dev_priv, sou, x, y, &crtc->mode);
 		if (ret)
 			DRM_ERROR("Failed to define Screen Object %dx%d\n",
 				  crtc->x, crtc->y);
@@ -408,10 +416,10 @@ vmw_sou_primary_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_crtc *crtc = plane->state->crtc ?
 		plane->state->crtc : old_state->crtc;
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unpin(vmw_priv(crtc->dev), vps->dmabuf, false);
-	vmw_dmabuf_unreference(&vps->dmabuf);
-	vps->dmabuf_size = 0;
+	if (vps->bo)
+		vmw_bo_unpin(vmw_priv(crtc->dev), vps->bo, false);
+	vmw_bo_unreference(&vps->bo);
+	vps->bo_size = 0;
 
 	vmw_du_plane_cleanup_fb(plane, old_state);
 }
@@ -440,8 +448,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 
 
 	if (!new_fb) {
-		vmw_dmabuf_unreference(&vps->dmabuf);
-		vps->dmabuf_size = 0;
+		vmw_bo_unreference(&vps->bo);
+		vps->bo_size = 0;
 
 		return 0;
 	}
@@ -449,22 +457,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	size = new_state->crtc_w * new_state->crtc_h * 4;
 	dev_priv = vmw_priv(crtc->dev);
 
-	if (vps->dmabuf) {
-		if (vps->dmabuf_size == size) {
+	if (vps->bo) {
+		if (vps->bo_size == size) {
 			/*
 			 * Note that this might temporarily up the pin-count
 			 * to 2, until cleanup_fb() is called.
 			 */
-			return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf,
+			return vmw_bo_pin_in_vram(dev_priv, vps->bo,
 						      true);
 		}
 
-		vmw_dmabuf_unreference(&vps->dmabuf);
-		vps->dmabuf_size = 0;
+		vmw_bo_unreference(&vps->bo);
+		vps->bo_size = 0;
 	}
 
-	vps->dmabuf = kzalloc(sizeof(*vps->dmabuf), GFP_KERNEL);
-	if (!vps->dmabuf)
+	vps->bo = kzalloc(sizeof(*vps->bo), GFP_KERNEL);
+	if (!vps->bo)
 		return -ENOMEM;
 
 	vmw_svga_enable(dev_priv);
@@ -473,22 +481,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	 * resume the overlays, this is preferred to failing to alloc.
 	 */
 	vmw_overlay_pause_all(dev_priv);
-	ret = vmw_dmabuf_init(dev_priv, vps->dmabuf, size,
+	ret = vmw_bo_init(dev_priv, vps->bo, size,
 			      &vmw_vram_ne_placement,
-			      false, &vmw_dmabuf_bo_free);
+			      false, &vmw_bo_bo_free);
 	vmw_overlay_resume_all(dev_priv);
 	if (ret) {
-		vps->dmabuf = NULL; /* vmw_dmabuf_init frees on error */
+		vps->bo = NULL; /* vmw_bo_init frees on error */
 		return ret;
 	}
 
-	vps->dmabuf_size = size;
+	vps->bo_size = size;
 
 	/*
 	 * TTM already thinks the buffer is pinned, but make sure the
 	 * pin_count is upped.
 	 */
-	return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf, true);
+	return vmw_bo_pin_in_vram(dev_priv, vps->bo, true);
 }
 
 
@@ -512,10 +520,10 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane,
 		vclips.w = crtc->mode.hdisplay;
 		vclips.h = crtc->mode.vdisplay;
 
-		if (vfb->dmabuf)
-			ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, vfb, NULL,
-							  &vclips, 1, 1, true,
-							  &fence, crtc);
+		if (vfb->bo)
+			ret = vmw_kms_sou_do_bo_dirty(dev_priv, vfb, NULL,
+						      &vclips, 1, 1, true,
+						      &fence, crtc);
 		else
 			ret = vmw_kms_sou_do_surface_dirty(dev_priv, vfb, NULL,
 							   &vclips, NULL, 0, 0,
@@ -695,7 +703,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
@@ -775,11 +783,11 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv)
 	return 0;
 }
 
-static int do_dmabuf_define_gmrfb(struct vmw_private *dev_priv,
+static int do_bo_define_gmrfb(struct vmw_private *dev_priv,
 				  struct vmw_framebuffer *framebuffer)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(framebuffer, struct vmw_framebuffer_dmabuf,
+	struct vmw_buffer_object *buf =
+		container_of(framebuffer, struct vmw_framebuffer_bo,
 			     base)->buffer;
 	int depth = framebuffer->base.format->depth;
 	struct {
@@ -970,13 +978,13 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 }
 
 /**
- * vmw_sou_dmabuf_fifo_commit - Callback to submit a set of readback clips.
+ * vmw_sou_bo_fifo_commit - Callback to submit a set of readback clips.
  *
  * @dirty: The closure structure.
  *
  * Commits a previously built command buffer of readback clips.
  */
-static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
+static void vmw_sou_bo_fifo_commit(struct vmw_kms_dirty *dirty)
 {
 	if (!dirty->num_hits) {
 		vmw_fifo_commit(dirty->dev_priv, 0);
@@ -984,20 +992,20 @@ static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
 	}
 
 	vmw_fifo_commit(dirty->dev_priv,
-			sizeof(struct vmw_kms_sou_dmabuf_blit) *
+			sizeof(struct vmw_kms_sou_bo_blit) *
 			dirty->num_hits);
 }
 
 /**
- * vmw_sou_dmabuf_clip - Callback to encode a readback cliprect.
+ * vmw_sou_bo_clip - Callback to encode a readback cliprect.
  *
  * @dirty: The closure structure
  *
  * Encodes a BLIT_GMRFB_TO_SCREEN cliprect.
  */
-static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
+static void vmw_sou_bo_clip(struct vmw_kms_dirty *dirty)
 {
-	struct vmw_kms_sou_dmabuf_blit *blit = dirty->cmd;
+	struct vmw_kms_sou_bo_blit *blit = dirty->cmd;
 
 	blit += dirty->num_hits;
 	blit->header = SVGA_CMD_BLIT_GMRFB_TO_SCREEN;
@@ -1012,10 +1020,10 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
 }
 
 /**
- * vmw_kms_do_dmabuf_dirty - Dirty part of a dma-buffer backed framebuffer
+ * vmw_kms_do_bo_dirty - Dirty part of a buffer-object backed framebuffer
  *
  * @dev_priv: Pointer to the device private structure.
- * @framebuffer: Pointer to the dma-buffer backed framebuffer.
+ * @framebuffer: Pointer to the buffer-object backed framebuffer.
  * @clips: Array of clip rects.
  * @vclips: Alternate array of clip rects. Either @clips or @vclips must
  * be NULL.
@@ -1025,12 +1033,12 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
  * @out_fence: If non-NULL, will return a ref-counted pointer to a
  * struct vmw_fence_obj. The returned fence pointer may be NULL in which
  * case the device has already synchronized.
- * @crtc: If crtc is passed, perform dmabuf dirty on that crtc only.
+ * @crtc: If crtc is passed, perform bo dirty on that crtc only.
  *
  * Returns 0 on success, negative error code on failure. -ERESTARTSYS if
  * interrupted.
  */
-int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
+int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv,
 				struct vmw_framebuffer *framebuffer,
 				struct drm_clip_rect *clips,
 				struct drm_vmw_rect *vclips,
@@ -1039,8 +1047,8 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
 				struct vmw_fence_obj **out_fence,
 				struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(framebuffer, struct vmw_framebuffer_dmabuf,
+	struct vmw_buffer_object *buf =
+		container_of(framebuffer, struct vmw_framebuffer_bo,
 			     base)->buffer;
 	struct vmw_kms_dirty dirty;
 	int ret;
@@ -1050,14 +1058,14 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	ret = do_dmabuf_define_gmrfb(dev_priv, framebuffer);
+	ret = do_bo_define_gmrfb(dev_priv, framebuffer);
 	if (unlikely(ret != 0))
 		goto out_revert;
 
 	dirty.crtc = crtc;
-	dirty.fifo_commit = vmw_sou_dmabuf_fifo_commit;
-	dirty.clip = vmw_sou_dmabuf_clip;
-	dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_dmabuf_blit) *
+	dirty.fifo_commit = vmw_sou_bo_fifo_commit;
+	dirty.clip = vmw_sou_bo_clip;
+	dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_bo_blit) *
 		num_clips;
 	ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips,
 				   0, 0, num_clips, increment, &dirty);
@@ -1116,12 +1124,12 @@ static void vmw_sou_readback_clip(struct vmw_kms_dirty *dirty)
 
 /**
  * vmw_kms_sou_readback - Perform a readback from the screen object system to
- * a dma-buffer backed framebuffer.
+ * a buffer-object backed framebuffer.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm_file identifying the caller.
  * Must be set to NULL if @user_fence_rep is NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @user_fence_rep: User-space provided structure for fence information.
  * Must be set to non-NULL if @file_priv is non-NULL.
  * @vclips: Array of clip rects.
@@ -1139,8 +1147,8 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 			 uint32_t num_clips,
 			 struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer;
+	struct vmw_buffer_object *buf =
+		container_of(vfb, struct vmw_framebuffer_bo, base)->buffer;
 	struct vmw_kms_dirty dirty;
 	int ret;
 
@@ -1149,7 +1157,7 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	ret = do_dmabuf_define_gmrfb(dev_priv, vfb);
+	ret = do_bo_define_gmrfb(dev_priv, vfb);
 	if (unlikely(ret != 0))
 		goto out_revert;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index e3ba63da396d..fe4842ca3b6e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -159,7 +159,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv,
 			      SVGA3dShaderType type,
 			      uint8_t num_input_sig,
 			      uint8_t num_output_sig,
-			      struct vmw_dma_buffer *byte_code,
+			      struct vmw_buffer_object *byte_code,
 			      void (*res_free) (struct vmw_resource *res))
 {
 	struct vmw_shader *shader = vmw_res_to_shader(res);
@@ -178,7 +178,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv,
 
 	res->backup_size = size;
 	if (byte_code) {
-		res->backup = vmw_dmabuf_reference(byte_code);
+		res->backup = vmw_bo_reference(byte_code);
 		res->backup_offset = offset;
 	}
 	shader->size = size;
@@ -306,7 +306,7 @@ static int vmw_gb_shader_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -537,7 +537,7 @@ static int vmw_dx_shader_unbind(struct vmw_resource *res,
 
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -723,7 +723,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data,
 }
 
 static int vmw_user_shader_alloc(struct vmw_private *dev_priv,
-				 struct vmw_dma_buffer *buffer,
+				 struct vmw_buffer_object *buffer,
 				 size_t shader_size,
 				 size_t offset,
 				 SVGA3dShaderType shader_type,
@@ -801,7 +801,7 @@ out:
 
 
 static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv,
-					     struct vmw_dma_buffer *buffer,
+					     struct vmw_buffer_object *buffer,
 					     size_t shader_size,
 					     size_t offset,
 					     SVGA3dShaderType shader_type)
@@ -862,12 +862,12 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_dma_buffer *buffer = NULL;
+	struct vmw_buffer_object *buffer = NULL;
 	SVGA3dShaderType shader_type;
 	int ret;
 
 	if (buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_dmabuf_lookup(tfile, buffer_handle,
+		ret = vmw_user_bo_lookup(tfile, buffer_handle,
 					     &buffer, NULL);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not find buffer for shader "
@@ -906,7 +906,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 
 	ttm_read_unlock(&dev_priv->reservation_sem);
 out_bad_arg:
-	vmw_dmabuf_unreference(&buffer);
+	vmw_bo_unreference(&buffer);
 	return ret;
 }
 
@@ -983,7 +983,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 			  struct list_head *list)
 {
 	struct ttm_operation_ctx ctx = { false, true };
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct ttm_bo_kmap_obj map;
 	bool is_iomem;
 	int ret;
@@ -997,8 +997,8 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, buf, size, &vmw_sys_ne_placement,
-			      true, vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, buf, size, &vmw_sys_ne_placement,
+			      true, vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -1031,7 +1031,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 				 res, list);
 	vmw_resource_unreference(&res);
 no_reserve:
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index a474d87b1af3..93f6b96ca7bb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -44,7 +44,7 @@
 enum stdu_content_type {
 	SAME_AS_DISPLAY = 0,
 	SEPARATE_SURFACE,
-	SEPARATE_DMA
+	SEPARATE_BO
 };
 
 /**
@@ -58,7 +58,7 @@ enum stdu_content_type {
  * @bottom: Bottom side of bounding box.
  * @fb_left: Left side of the framebuffer/content bounding box
  * @fb_top: Top of the framebuffer/content bounding box
- * @buf: DMA buffer when DMA-ing between buffer and screen targets.
+ * @buf: buffer object when DMA-ing between buffer and screen targets.
  * @sid: Surface ID when copying between surface and screen targets.
  */
 struct vmw_stdu_dirty {
@@ -68,7 +68,7 @@ struct vmw_stdu_dirty {
 	s32 fb_left, fb_top;
 	u32 pitch;
 	union {
-		struct vmw_dma_buffer *buf;
+		struct vmw_buffer_object *buf;
 		u32 sid;
 	};
 };
@@ -178,13 +178,9 @@ static int vmw_stdu_define_st(struct vmw_private *dev_priv,
 	cmd->body.height = mode->vdisplay;
 	cmd->body.flags  = (0 == cmd->body.stid) ? SVGA_STFLAG_PRIMARY : 0;
 	cmd->body.dpi    = 0;
-	if (stdu->base.is_implicit) {
-		cmd->body.xRoot  = crtc_x;
-		cmd->body.yRoot  = crtc_y;
-	} else {
-		cmd->body.xRoot  = stdu->base.gui_x;
-		cmd->body.yRoot  = stdu->base.gui_y;
-	}
+	cmd->body.xRoot  = crtc_x;
+	cmd->body.yRoot  = crtc_y;
+
 	stdu->base.set_gui_x = cmd->body.xRoot;
 	stdu->base.set_gui_y = cmd->body.yRoot;
 
@@ -374,11 +370,14 @@ static void vmw_stdu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
-	int ret;
-
+	struct drm_connector_state *conn_state;
+	struct vmw_connector_state *vmw_conn_state;
+	int x, y, ret;
 
-	stdu     = vmw_crtc_to_stdu(crtc);
+	stdu = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
+	conn_state = stdu->base.connector.state;
+	vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
 
 	if (stdu->defined) {
 		ret = vmw_stdu_bind_st(dev_priv, stdu, NULL);
@@ -397,8 +396,16 @@ static void vmw_stdu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	if (!crtc->state->enable)
 		return;
 
+	if (stdu->base.is_implicit) {
+		x = crtc->x;
+		y = crtc->y;
+	} else {
+		x = vmw_conn_state->gui_x;
+		y = vmw_conn_state->gui_y;
+	}
+
 	vmw_svga_enable(dev_priv);
-	ret = vmw_stdu_define_st(dev_priv, stdu, &crtc->mode, crtc->x, crtc->y);
+	ret = vmw_stdu_define_st(dev_priv, stdu, &crtc->mode, x, y);
 
 	if (ret)
 		DRM_ERROR("Failed to define Screen Target of size %dx%d\n",
@@ -508,14 +515,14 @@ static int vmw_stdu_crtc_page_flip(struct drm_crtc *crtc,
 
 
 /**
- * vmw_stdu_dmabuf_clip - Callback to encode a suface DMA command cliprect
+ * vmw_stdu_bo_clip - Callback to encode a suface DMA command cliprect
  *
  * @dirty: The closure structure.
  *
  * Encodes a surface DMA command cliprect and updates the bounding box
  * for the DMA.
  */
-static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_clip(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -543,14 +550,14 @@ static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty)
 }
 
 /**
- * vmw_stdu_dmabuf_fifo_commit - Callback to fill in and submit a DMA command.
+ * vmw_stdu_bo_fifo_commit - Callback to fill in and submit a DMA command.
  *
  * @dirty: The closure structure.
  *
  * Fills in the missing fields in a DMA command, and optionally encodes
  * a screen target update command, depending on transfer direction.
  */
-static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_fifo_commit(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -594,13 +601,13 @@ static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
 
 
 /**
- * vmw_stdu_dmabuf_cpu_clip - Callback to encode a CPU blit
+ * vmw_stdu_bo_cpu_clip - Callback to encode a CPU blit
  *
  * @dirty: The closure structure.
  *
  * This function calculates the bounding box for all the incoming clips.
  */
-static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_cpu_clip(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -624,14 +631,14 @@ static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
 
 
 /**
- * vmw_stdu_dmabuf_cpu_commit - Callback to do a CPU blit from DMAbuf
+ * vmw_stdu_bo_cpu_commit - Callback to do a CPU blit from buffer object
  *
  * @dirty: The closure structure.
  *
  * For the special case when we cannot create a proxy surface in a
  * 2D VM, we have to do a CPU blit ourselves.
  */
-static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -652,7 +659,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
 	if (width == 0 || height == 0)
 		return;
 
-	/* Assume we are blitting from Guest (dmabuf) to Host (display_srf) */
+	/* Assume we are blitting from Guest (bo) to Host (display_srf) */
 	dst_pitch = stdu->display_srf->base_size.width * stdu->cpp;
 	dst_bo = &stdu->display_srf->res.backup->base;
 	dst_offset = ddirty->top * dst_pitch + ddirty->left * stdu->cpp;
@@ -712,13 +719,13 @@ out_cleanup:
 }
 
 /**
- * vmw_kms_stdu_dma - Perform a DMA transfer between a dma-buffer backed
+ * vmw_kms_stdu_dma - Perform a DMA transfer between a buffer-object backed
  * framebuffer and the screen target system.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm-file identifying the caller. May be
  * set to NULL, but then @user_fence_rep must also be set to NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @clips: Array of clip rects. Either @clips or @vclips must be NULL.
  * @vclips: Alternate array of clip rects. Either @clips or @vclips must
  * be NULL.
@@ -747,8 +754,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 		     bool interruptible,
 		     struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer;
+	struct vmw_buffer_object *buf =
+		container_of(vfb, struct vmw_framebuffer_bo, base)->buffer;
 	struct vmw_stdu_dirty ddirty;
 	int ret;
 	bool cpu_blit = !(dev_priv->capabilities & SVGA_CAP_3D);
@@ -770,8 +777,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 	ddirty.fb_left = ddirty.fb_top = S32_MAX;
 	ddirty.pitch = vfb->base.pitches[0];
 	ddirty.buf = buf;
-	ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit;
-	ddirty.base.clip = vmw_stdu_dmabuf_clip;
+	ddirty.base.fifo_commit = vmw_stdu_bo_fifo_commit;
+	ddirty.base.clip = vmw_stdu_bo_clip;
 	ddirty.base.fifo_reserve_size = sizeof(struct vmw_stdu_dma) +
 		num_clips * sizeof(SVGA3dCopyBox) +
 		sizeof(SVGA3dCmdSurfaceDMASuffix);
@@ -780,8 +787,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 
 
 	if (cpu_blit) {
-		ddirty.base.fifo_commit = vmw_stdu_dmabuf_cpu_commit;
-		ddirty.base.clip = vmw_stdu_dmabuf_cpu_clip;
+		ddirty.base.fifo_commit = vmw_stdu_bo_cpu_commit;
+		ddirty.base.clip = vmw_stdu_bo_cpu_clip;
 		ddirty.base.fifo_reserve_size = 0;
 	}
 
@@ -927,7 +934,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	if (vfbs->is_dmabuf_proxy) {
+	if (vfbs->is_bo_proxy) {
 		ret = vmw_kms_update_proxy(srf, clips, num_clips, inc);
 		if (ret)
 			goto out_finish;
@@ -1075,7 +1082,7 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
  * @new_state: info on the new plane state, including the FB
  *
  * This function allocates a new display surface if the content is
- * backed by a DMA.  The display surface is pinned here, and it'll
+ * backed by a buffer object.  The display surface is pinned here, and it'll
  * be unpinned in .cleanup_fb()
  *
  * Returns 0 on success
@@ -1105,13 +1112,13 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	}
 
 	vfb = vmw_framebuffer_to_vfb(new_fb);
-	new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
+	new_vfbs = (vfb->bo) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
 
 	if (new_vfbs && new_vfbs->surface->base_size.width == hdisplay &&
 	    new_vfbs->surface->base_size.height == vdisplay)
 		new_content_type = SAME_AS_DISPLAY;
-	else if (vfb->dmabuf)
-		new_content_type = SEPARATE_DMA;
+	else if (vfb->bo)
+		new_content_type = SEPARATE_BO;
 	else
 		new_content_type = SEPARATE_SURFACE;
 
@@ -1124,10 +1131,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 		display_base_size.depth  = 1;
 
 		/*
-		 * If content buffer is a DMA buf, then we have to construct
-		 * surface info
+		 * If content buffer is a buffer object, then we have to
+		 * construct surface info
 		 */
-		if (new_content_type == SEPARATE_DMA) {
+		if (new_content_type == SEPARATE_BO) {
 
 			switch (new_fb->format->cpp[0]*8) {
 			case 32:
@@ -1150,6 +1157,9 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 			content_srf.flags             = 0;
 			content_srf.mip_levels[0]     = 1;
 			content_srf.multisample_count = 0;
+			content_srf.multisample_pattern =
+				SVGA3D_MS_PATTERN_NONE;
+			content_srf.quality_level = SVGA3D_MS_QUALITY_NONE;
 		} else {
 			content_srf = *new_vfbs->surface;
 		}
@@ -1178,6 +1188,8 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 				 content_srf.multisample_count,
 				 0,
 				 display_base_size,
+				 content_srf.multisample_pattern,
+				 content_srf.quality_level,
 				 &vps->surf);
 			if (ret != 0) {
 				DRM_ERROR("Couldn't allocate STDU surface.\n");
@@ -1212,12 +1224,12 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	vps->content_fb_type = new_content_type;
 
 	/*
-	 * This should only happen if the DMA buf is too large to create a
+	 * This should only happen if the buffer object is too large to create a
 	 * proxy surface for.
-	 * If we are a 2D VM with a DMA buffer then we have to use CPU blit
+	 * If we are a 2D VM with a buffer object then we have to use CPU blit
 	 * so cache these mappings
 	 */
-	if (vps->content_fb_type == SEPARATE_DMA &&
+	if (vps->content_fb_type == SEPARATE_BO &&
 	    !(dev_priv->capabilities & SVGA_CAP_3D))
 		vps->cpp = new_fb->pitches[0] / new_fb->width;
 
@@ -1276,7 +1288,7 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 		if (ret)
 			DRM_ERROR("Failed to bind surface to STDU.\n");
 
-		if (vfb->dmabuf)
+		if (vfb->bo)
 			ret = vmw_kms_stdu_dma(dev_priv, NULL, vfb, NULL, NULL,
 					       &vclips, 1, 1, true, false,
 					       crtc);
@@ -1486,7 +1498,7 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 40a439797ae2..e125233e074b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -33,6 +33,10 @@
 #include "vmwgfx_binding.h"
 #include "device_include/svga3d_surfacedefs.h"
 
+#define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32)
+#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) (svga3d_flags >> 32)
+#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
+	(svga3d_flags & ((uint64_t)U32_MAX))
 
 /**
  * struct vmw_user_surface - User-space visible surface resource
@@ -81,7 +85,16 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 				 bool readback,
 				 struct ttm_validate_buffer *val_buf);
 static int vmw_gb_surface_destroy(struct vmw_resource *res);
-
+static int
+vmw_gb_surface_define_internal(struct drm_device *dev,
+			       struct drm_vmw_gb_surface_create_ext_req *req,
+			       struct drm_vmw_gb_surface_create_rep *rep,
+			       struct drm_file *file_priv);
+static int
+vmw_gb_surface_reference_internal(struct drm_device *dev,
+				  struct drm_vmw_surface_arg *req,
+				  struct drm_vmw_gb_surface_ref_ext_rep *rep,
+				  struct drm_file *file_priv);
 
 static const struct vmw_user_resource_conv user_surface_conv = {
 	.object_type = VMW_RES_SURFACE,
@@ -224,7 +237,12 @@ static void vmw_surface_define_encode(const struct vmw_surface *srf,
 	cmd->header.id = SVGA_3D_CMD_SURFACE_DEFINE;
 	cmd->header.size = cmd_len;
 	cmd->body.sid = srf->res.id;
-	cmd->body.surfaceFlags = srf->flags;
+	/*
+	 * Downcast of surfaceFlags, was upcasted when received from user-space,
+	 * since driver internally stores as 64 bit.
+	 * For legacy surface define only 32 bit flag is supported.
+	 */
+	cmd->body.surfaceFlags = (SVGA3dSurface1Flags)srf->flags;
 	cmd->body.format = srf->format;
 	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i)
 		cmd->body.face[i].numMipLevels = srf->mip_levels[i];
@@ -468,7 +486,7 @@ static int vmw_legacy_srf_dma(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -760,7 +778,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	srf = &user_srf->srf;
 	res = &srf->res;
 
-	srf->flags = req->flags;
+	/* Driver internally stores as 64-bit flags */
+	srf->flags = (SVGA3dSurfaceAllFlags)req->flags;
 	srf->format = req->format;
 	srf->scanout = req->scanout;
 
@@ -785,6 +804,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	srf->base_size = *srf->sizes;
 	srf->autogen_filter = SVGA3D_TEX_FILTER_NONE;
 	srf->multisample_count = 0;
+	srf->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	srf->quality_level = SVGA3D_MS_QUALITY_NONE;
 
 	cur_bo_offset = 0;
 	cur_offset = srf->offsets;
@@ -842,12 +863,12 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	if (dev_priv->has_mob && req->shareable) {
 		uint32_t backup_handle;
 
-		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
-					    res->backup_size,
-					    true,
-					    &backup_handle,
-					    &res->backup,
-					    &user_srf->backup_base);
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					true,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
 		if (unlikely(ret != 0)) {
 			vmw_resource_unreference(&res);
 			goto out_unlock;
@@ -990,7 +1011,8 @@ int vmw_surface_reference_ioctl(struct drm_device *dev, void *data,
 	user_srf = container_of(base, struct vmw_user_surface, prime.base);
 	srf = &user_srf->srf;
 
-	rep->flags = srf->flags;
+	/* Downcast of flags when sending back to user space */
+	rep->flags = (uint32_t)srf->flags;
 	rep->format = srf->format;
 	memcpy(rep->mip_levels, srf->mip_levels, sizeof(srf->mip_levels));
 	user_sizes = (struct drm_vmw_size __user *)(unsigned long)
@@ -1031,6 +1053,10 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDefineGBSurface_v2 body;
 	} *cmd2;
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdDefineGBSurface_v3 body;
+	} *cmd3;
 
 	if (likely(res->id != -1))
 		return 0;
@@ -1047,7 +1073,11 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		goto out_no_fifo;
 	}
 
-	if (srf->array_size > 0) {
+	if (dev_priv->has_sm4_1 && srf->array_size > 0) {
+		cmd_id = SVGA_3D_CMD_DEFINE_GB_SURFACE_V3;
+		cmd_len = sizeof(cmd3->body);
+		submit_len = sizeof(*cmd3);
+	} else if (srf->array_size > 0) {
 		/* has_dx checked on creation time. */
 		cmd_id = SVGA_3D_CMD_DEFINE_GB_SURFACE_V2;
 		cmd_len = sizeof(cmd2->body);
@@ -1060,6 +1090,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 
 	cmd = vmw_fifo_reserve(dev_priv, submit_len);
 	cmd2 = (typeof(cmd2))cmd;
+	cmd3 = (typeof(cmd3))cmd;
 	if (unlikely(!cmd)) {
 		DRM_ERROR("Failed reserving FIFO space for surface "
 			  "creation.\n");
@@ -1067,12 +1098,27 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		goto out_no_fifo;
 	}
 
-	if (srf->array_size > 0) {
+	if (dev_priv->has_sm4_1 && srf->array_size > 0) {
+		cmd3->header.id = cmd_id;
+		cmd3->header.size = cmd_len;
+		cmd3->body.sid = srf->res.id;
+		cmd3->body.surfaceFlags = srf->flags;
+		cmd3->body.format = srf->format;
+		cmd3->body.numMipLevels = srf->mip_levels[0];
+		cmd3->body.multisampleCount = srf->multisample_count;
+		cmd3->body.multisamplePattern = srf->multisample_pattern;
+		cmd3->body.qualityLevel = srf->quality_level;
+		cmd3->body.autogenFilter = srf->autogen_filter;
+		cmd3->body.size.width = srf->base_size.width;
+		cmd3->body.size.height = srf->base_size.height;
+		cmd3->body.size.depth = srf->base_size.depth;
+		cmd3->body.arraySize = srf->array_size;
+	} else if (srf->array_size > 0) {
 		cmd2->header.id = cmd_id;
 		cmd2->header.size = cmd_len;
 		cmd2->body.sid = srf->res.id;
 		cmd2->body.surfaceFlags = srf->flags;
-		cmd2->body.format = cpu_to_le32(srf->format);
+		cmd2->body.format = srf->format;
 		cmd2->body.numMipLevels = srf->mip_levels[0];
 		cmd2->body.multisampleCount = srf->multisample_count;
 		cmd2->body.autogenFilter = srf->autogen_filter;
@@ -1085,7 +1131,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		cmd->header.size = cmd_len;
 		cmd->body.sid = srf->res.id;
 		cmd->body.surfaceFlags = srf->flags;
-		cmd->body.format = cpu_to_le32(srf->format);
+		cmd->body.format = srf->format;
 		cmd->body.numMipLevels = srf->mip_levels[0];
 		cmd->body.multisampleCount = srf->multisample_count;
 		cmd->body.autogenFilter = srf->autogen_filter;
@@ -1210,7 +1256,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -1256,194 +1302,55 @@ static int vmw_gb_surface_destroy(struct vmw_resource *res)
 
 /**
  * vmw_gb_surface_define_ioctl - Ioctl function implementing
- *                               the user surface define functionality.
+ * the user surface define functionality.
  *
- * @dev:            Pointer to a struct drm_device.
- * @data:           Pointer to data copied from / to user-space.
- * @file_priv:      Pointer to a drm file private structure.
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
  */
 int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_user_surface *user_srf;
-	struct vmw_surface *srf;
-	struct vmw_resource *res;
-	struct vmw_resource *tmp;
 	union drm_vmw_gb_surface_create_arg *arg =
 	    (union drm_vmw_gb_surface_create_arg *)data;
-	struct drm_vmw_gb_surface_create_req *req = &arg->req;
 	struct drm_vmw_gb_surface_create_rep *rep = &arg->rep;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	int ret;
-	uint32_t size;
-	uint32_t backup_handle = 0;
-
-	if (req->multisample_count != 0)
-		return -EINVAL;
-
-	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
-		return -EINVAL;
+	struct drm_vmw_gb_surface_create_ext_req req_ext;
 
-	if (unlikely(vmw_user_surface_size == 0))
-		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
-			128;
-
-	size = vmw_user_surface_size + 128;
-
-	/* Define a surface based on the parameters. */
-	ret = vmw_surface_gb_priv_define(dev,
-			size,
-			req->svga3d_flags,
-			req->format,
-			req->drm_surface_flags & drm_vmw_surface_flag_scanout,
-			req->mip_levels,
-			req->multisample_count,
-			req->array_size,
-			req->base_size,
-			&srf);
-	if (unlikely(ret != 0))
-		return ret;
-
-	user_srf = container_of(srf, struct vmw_user_surface, srf);
-	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
+	req_ext.base = arg->req;
+	req_ext.version = drm_vmw_gb_surface_v1;
+	req_ext.svga3d_flags_upper_32_bits = 0;
+	req_ext.multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	req_ext.quality_level = SVGA3D_MS_QUALITY_NONE;
+	req_ext.must_be_zero = 0;
 
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	res = &user_srf->srf.res;
-
-
-	if (req->buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
-					     &res->backup,
-					     &user_srf->backup_base);
-		if (ret == 0) {
-			if (res->backup->base.num_pages * PAGE_SIZE <
-			    res->backup_size) {
-				DRM_ERROR("Surface backup buffer is too small.\n");
-				vmw_dmabuf_unreference(&res->backup);
-				ret = -EINVAL;
-				goto out_unlock;
-			} else {
-				backup_handle = req->buffer_handle;
-			}
-		}
-	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
-		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
-					    res->backup_size,
-					    req->drm_surface_flags &
-					    drm_vmw_surface_flag_shareable,
-					    &backup_handle,
-					    &res->backup,
-					    &user_srf->backup_base);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&res);
-		goto out_unlock;
-	}
-
-	tmp = vmw_resource_reference(res);
-	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
-				    req->drm_surface_flags &
-				    drm_vmw_surface_flag_shareable,
-				    VMW_RES_SURFACE,
-				    &vmw_user_surface_base_release, NULL);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&tmp);
-		vmw_resource_unreference(&res);
-		goto out_unlock;
-	}
-
-	rep->handle      = user_srf->prime.base.hash.key;
-	rep->backup_size = res->backup_size;
-	if (res->backup) {
-		rep->buffer_map_handle =
-			drm_vma_node_offset_addr(&res->backup->base.vma_node);
-		rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE;
-		rep->buffer_handle = backup_handle;
-	} else {
-		rep->buffer_map_handle = 0;
-		rep->buffer_size = 0;
-		rep->buffer_handle = SVGA3D_INVALID_ID;
-	}
-
-	vmw_resource_unreference(&res);
-
-out_unlock:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
+	return vmw_gb_surface_define_internal(dev, &req_ext, rep, file_priv);
 }
 
 /**
  * vmw_gb_surface_reference_ioctl - Ioctl function implementing
- *                                  the user surface reference functionality.
+ * the user surface reference functionality.
  *
- * @dev:            Pointer to a struct drm_device.
- * @data:           Pointer to data copied from / to user-space.
- * @file_priv:      Pointer to a drm file private structure.
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
  */
 int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
 				   struct drm_file *file_priv)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
 	union drm_vmw_gb_surface_reference_arg *arg =
 	    (union drm_vmw_gb_surface_reference_arg *)data;
 	struct drm_vmw_surface_arg *req = &arg->req;
 	struct drm_vmw_gb_surface_ref_rep *rep = &arg->rep;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_surface *srf;
-	struct vmw_user_surface *user_srf;
-	struct ttm_base_object *base;
-	uint32_t backup_handle;
-	int ret = -EINVAL;
+	struct drm_vmw_gb_surface_ref_ext_rep rep_ext;
+	int ret;
+
+	ret = vmw_gb_surface_reference_internal(dev, req, &rep_ext, file_priv);
 
-	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
-					   req->handle_type, &base);
 	if (unlikely(ret != 0))
 		return ret;
 
-	user_srf = container_of(base, struct vmw_user_surface, prime.base);
-	srf = &user_srf->srf;
-	if (!srf->res.backup) {
-		DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
-		goto out_bad_resource;
-	}
-
-	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
-	ret = vmw_user_dmabuf_reference(tfile, srf->res.backup,
-					&backup_handle);
-	mutex_unlock(&dev_priv->cmdbuf_mutex);
-
-	if (unlikely(ret != 0)) {
-		DRM_ERROR("Could not add a reference to a GB surface "
-			  "backup buffer.\n");
-		(void) ttm_ref_object_base_unref(tfile, base->hash.key,
-						 TTM_REF_USAGE);
-		goto out_bad_resource;
-	}
-
-	rep->creq.svga3d_flags = srf->flags;
-	rep->creq.format = srf->format;
-	rep->creq.mip_levels = srf->mip_levels[0];
-	rep->creq.drm_surface_flags = 0;
-	rep->creq.multisample_count = srf->multisample_count;
-	rep->creq.autogen_filter = srf->autogen_filter;
-	rep->creq.array_size = srf->array_size;
-	rep->creq.buffer_handle = backup_handle;
-	rep->creq.base_size = srf->base_size;
-	rep->crep.handle = user_srf->prime.base.hash.key;
-	rep->crep.backup_size = srf->res.backup_size;
-	rep->crep.buffer_handle = backup_handle;
-	rep->crep.buffer_map_handle =
-		drm_vma_node_offset_addr(&srf->res.backup->base.vma_node);
-	rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE;
-
-out_bad_resource:
-	ttm_base_object_unref(&base);
+	rep->creq = rep_ext.creq.base;
+	rep->crep = rep_ext.crep;
 
 	return ret;
 }
@@ -1461,6 +1368,8 @@ out_bad_resource:
  * @multisample_count:
  * @array_size: Surface array size.
  * @size: width, heigh, depth of the surface requested
+ * @multisample_pattern: Multisampling pattern when msaa is supported
+ * @quality_level: Precision settings
  * @user_srf_out: allocated user_srf.  Set to NULL on failure.
  *
  * GB surfaces allocated by this function will not have a user mode handle, and
@@ -1470,13 +1379,15 @@ out_bad_resource:
  */
 int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t user_accounting_size,
-			       uint32_t svga3d_flags,
+			       SVGA3dSurfaceAllFlags svga3d_flags,
 			       SVGA3dSurfaceFormat format,
 			       bool for_scanout,
 			       uint32_t num_mip_levels,
 			       uint32_t multisample_count,
 			       uint32_t array_size,
 			       struct drm_vmw_size size,
+			       SVGA3dMSPattern multisample_pattern,
+			       SVGA3dMSQualityLevel quality_level,
 			       struct vmw_surface **srf_out)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
@@ -1487,7 +1398,8 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	};
 	struct vmw_surface *srf;
 	int ret;
-	u32 num_layers;
+	u32 num_layers = 1;
+	u32 sample_count = 1;
 
 	*srf_out = NULL;
 
@@ -1562,19 +1474,23 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	srf->autogen_filter    = SVGA3D_TEX_FILTER_NONE;
 	srf->array_size        = array_size;
 	srf->multisample_count = multisample_count;
+	srf->multisample_pattern = multisample_pattern;
+	srf->quality_level = quality_level;
 
 	if (array_size)
 		num_layers = array_size;
 	else if (svga3d_flags & SVGA3D_SURFACE_CUBEMAP)
 		num_layers = SVGA3D_MAX_SURFACE_FACES;
-	else
-		num_layers = 1;
+
+	if (srf->flags & SVGA3D_SURFACE_MULTISAMPLE)
+		sample_count = srf->multisample_count;
 
 	srf->res.backup_size   =
-		svga3dsurface_get_serialized_size(srf->format,
-						  srf->base_size,
-						  srf->mip_levels[0],
-						  num_layers);
+		svga3dsurface_get_serialized_size_extended(srf->format,
+							   srf->base_size,
+							   srf->mip_levels[0],
+							   num_layers,
+							   sample_count);
 
 	if (srf->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT)
 		srf->res.backup_size += sizeof(SVGA3dDXSOState);
@@ -1599,3 +1515,266 @@ out_unlock:
 	ttm_read_unlock(&dev_priv->reservation_sem);
 	return ret;
 }
+
+/**
+ * vmw_gb_surface_define_ext_ioctl - Ioctl function implementing
+ * the user surface define functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	union drm_vmw_gb_surface_create_ext_arg *arg =
+	    (union drm_vmw_gb_surface_create_ext_arg *)data;
+	struct drm_vmw_gb_surface_create_ext_req *req = &arg->req;
+	struct drm_vmw_gb_surface_create_rep *rep = &arg->rep;
+
+	return vmw_gb_surface_define_internal(dev, req, rep, file_priv);
+}
+
+/**
+ * vmw_gb_surface_reference_ext_ioctl - Ioctl function implementing
+ * the user surface reference functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev, void *data,
+				   struct drm_file *file_priv)
+{
+	union drm_vmw_gb_surface_reference_ext_arg *arg =
+	    (union drm_vmw_gb_surface_reference_ext_arg *)data;
+	struct drm_vmw_surface_arg *req = &arg->req;
+	struct drm_vmw_gb_surface_ref_ext_rep *rep = &arg->rep;
+
+	return vmw_gb_surface_reference_internal(dev, req, rep, file_priv);
+}
+
+/**
+ * vmw_gb_surface_define_internal - Ioctl function implementing
+ * the user surface define functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @req: Request argument from user-space.
+ * @rep: Response argument to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+static int
+vmw_gb_surface_define_internal(struct drm_device *dev,
+			       struct drm_vmw_gb_surface_create_ext_req *req,
+			       struct drm_vmw_gb_surface_create_rep *rep,
+			       struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_user_surface *user_srf;
+	struct vmw_surface *srf;
+	struct vmw_resource *res;
+	struct vmw_resource *tmp;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	int ret;
+	uint32_t size;
+	uint32_t backup_handle = 0;
+	SVGA3dSurfaceAllFlags svga3d_flags_64 =
+		SVGA3D_FLAGS_64(req->svga3d_flags_upper_32_bits,
+				req->base.svga3d_flags);
+
+	if (!dev_priv->has_sm4_1) {
+		/*
+		 * If SM4_1 is not support then cannot send 64-bit flag to
+		 * device.
+		 */
+		if (req->svga3d_flags_upper_32_bits != 0)
+			return -EINVAL;
+
+		if (req->base.multisample_count != 0)
+			return -EINVAL;
+
+		if (req->multisample_pattern != SVGA3D_MS_PATTERN_NONE)
+			return -EINVAL;
+
+		if (req->quality_level != SVGA3D_MS_QUALITY_NONE)
+			return -EINVAL;
+	}
+
+	if ((svga3d_flags_64 & SVGA3D_SURFACE_MULTISAMPLE) &&
+	    req->base.multisample_count == 0)
+		return -EINVAL;
+
+	if (req->base.mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
+	if (unlikely(vmw_user_surface_size == 0))
+		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
+			128;
+
+	size = vmw_user_surface_size + 128;
+
+	/* Define a surface based on the parameters. */
+	ret = vmw_surface_gb_priv_define(dev,
+					 size,
+					 svga3d_flags_64,
+					 req->base.format,
+					 req->base.drm_surface_flags &
+					 drm_vmw_surface_flag_scanout,
+					 req->base.mip_levels,
+					 req->base.multisample_count,
+					 req->base.array_size,
+					 req->base.base_size,
+					 req->multisample_pattern,
+					 req->quality_level,
+					 &srf);
+	if (unlikely(ret != 0))
+		return ret;
+
+	user_srf = container_of(srf, struct vmw_user_surface, srf);
+	if (drm_is_primary_client(file_priv))
+		user_srf->master = drm_master_get(file_priv->master);
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	res = &user_srf->srf.res;
+
+	if (req->base.buffer_handle != SVGA3D_INVALID_ID) {
+		ret = vmw_user_bo_lookup(tfile, req->base.buffer_handle,
+					 &res->backup,
+					 &user_srf->backup_base);
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer too small.\n");
+				vmw_bo_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->base.buffer_handle;
+			}
+		}
+	} else if (req->base.drm_surface_flags &
+		   drm_vmw_surface_flag_create_buffer)
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					req->base.drm_surface_flags &
+					drm_vmw_surface_flag_shareable,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&res);
+		goto out_unlock;
+	}
+
+	tmp = vmw_resource_reference(res);
+	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
+				    req->base.drm_surface_flags &
+				    drm_vmw_surface_flag_shareable,
+				    VMW_RES_SURFACE,
+				    &vmw_user_surface_base_release, NULL);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&tmp);
+		vmw_resource_unreference(&res);
+		goto out_unlock;
+	}
+
+	rep->handle      = user_srf->prime.base.hash.key;
+	rep->backup_size = res->backup_size;
+	if (res->backup) {
+		rep->buffer_map_handle =
+			drm_vma_node_offset_addr(&res->backup->base.vma_node);
+		rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE;
+		rep->buffer_handle = backup_handle;
+	} else {
+		rep->buffer_map_handle = 0;
+		rep->buffer_size = 0;
+		rep->buffer_handle = SVGA3D_INVALID_ID;
+	}
+
+	vmw_resource_unreference(&res);
+
+out_unlock:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_gb_surface_reference_internal - Ioctl function implementing
+ * the user surface reference functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @req: Pointer to user-space request surface arg.
+ * @rep: Pointer to response to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+static int
+vmw_gb_surface_reference_internal(struct drm_device *dev,
+				  struct drm_vmw_surface_arg *req,
+				  struct drm_vmw_gb_surface_ref_ext_rep *rep,
+				  struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_surface *srf;
+	struct vmw_user_surface *user_srf;
+	struct ttm_base_object *base;
+	uint32_t backup_handle;
+	int ret = -EINVAL;
+
+	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
+					   req->handle_type, &base);
+	if (unlikely(ret != 0))
+		return ret;
+
+	user_srf = container_of(base, struct vmw_user_surface, prime.base);
+	srf = &user_srf->srf;
+	if (!srf->res.backup) {
+		DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
+		goto out_bad_resource;
+	}
+
+	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
+	ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle);
+	mutex_unlock(&dev_priv->cmdbuf_mutex);
+
+	if (unlikely(ret != 0)) {
+		DRM_ERROR("Could not add a reference to a GB surface "
+			  "backup buffer.\n");
+		(void) ttm_ref_object_base_unref(tfile, base->hash.key,
+						 TTM_REF_USAGE);
+		goto out_bad_resource;
+	}
+
+	rep->creq.base.svga3d_flags = SVGA3D_FLAGS_LOWER_32(srf->flags);
+	rep->creq.base.format = srf->format;
+	rep->creq.base.mip_levels = srf->mip_levels[0];
+	rep->creq.base.drm_surface_flags = 0;
+	rep->creq.base.multisample_count = srf->multisample_count;
+	rep->creq.base.autogen_filter = srf->autogen_filter;
+	rep->creq.base.array_size = srf->array_size;
+	rep->creq.base.buffer_handle = backup_handle;
+	rep->creq.base.base_size = srf->base_size;
+	rep->crep.handle = user_srf->prime.base.hash.key;
+	rep->crep.backup_size = srf->res.backup_size;
+	rep->crep.buffer_handle = backup_handle;
+	rep->crep.buffer_map_handle =
+		drm_vma_node_offset_addr(&srf->res.backup->base.vma_node);
+	rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE;
+
+	rep->creq.version = drm_vmw_gb_surface_v1;
+	rep->creq.svga3d_flags_upper_32_bits =
+		SVGA3D_FLAGS_UPPER_32(srf->flags);
+	rep->creq.multisample_pattern = srf->multisample_pattern;
+	rep->creq.quality_level = srf->quality_level;
+	rep->creq.must_be_zero = 0;
+
+out_bad_resource:
+	ttm_base_object_unref(&base);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 02de216d55a1..31786b200afc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -798,7 +798,7 @@ static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 	struct ttm_object_file *tfile =
 		vmw_fpriv((struct drm_file *)filp->private_data)->tfile;
 
-	return vmw_user_dmabuf_verify_access(bo, tfile);
+	return vmw_user_bo_verify_access(bo, tfile);
 }
 
 static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
@@ -852,7 +852,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
 			    bool evict,
 			    struct ttm_mem_reg *mem)
 {
-	vmw_resource_move_notify(bo, mem);
+	vmw_bo_move_notify(bo, mem);
 	vmw_query_move_notify(bo, mem);
 }
 
@@ -864,7 +864,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
  */
 static void vmw_swap_notify(struct ttm_buffer_object *bo)
 {
-	vmw_resource_swap_notify(bo);
+	vmw_bo_swap_notify(bo);
 	(void) ttm_bo_wait(bo, false, false);
 }
 
diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c
index 13ea90f7a185..78655269d843 100644
--- a/drivers/gpu/drm/zte/zx_hdmi.c
+++ b/drivers/gpu/drm/zte/zx_hdmi.c
@@ -272,7 +272,7 @@ static int zx_hdmi_connector_get_modes(struct drm_connector *connector)
 
 	hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 	hdmi->sink_has_audio = drm_detect_monitor_audio(edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
@@ -326,7 +326,7 @@ static int zx_hdmi_register(struct drm_device *drm, struct zx_hdmi *hdmi)
 	drm_connector_helper_add(&hdmi->connector,
 				 &zx_hdmi_connector_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
+	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/zte/zx_tvenc.c b/drivers/gpu/drm/zte/zx_tvenc.c
index 0de1a71ca4e0..b73afb212fb2 100644
--- a/drivers/gpu/drm/zte/zx_tvenc.c
+++ b/drivers/gpu/drm/zte/zx_tvenc.c
@@ -297,7 +297,7 @@ static int zx_tvenc_register(struct drm_device *drm, struct zx_tvenc *tvenc)
 			   DRM_MODE_CONNECTOR_Composite);
 	drm_connector_helper_add(connector, &zx_tvenc_connector_helper_funcs);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c
index 3e7e33cd3dfa..23d1ff4355a0 100644
--- a/drivers/gpu/drm/zte/zx_vga.c
+++ b/drivers/gpu/drm/zte/zx_vga.c
@@ -109,7 +109,7 @@ static int zx_vga_connector_get_modes(struct drm_connector *connector)
 	 */
 	zx_writel(vga->mmio + VGA_AUTO_DETECT_SEL, VGA_DETECT_SEL_HAS_DEVICE);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
@@ -175,7 +175,7 @@ static int zx_vga_register(struct drm_device *drm, struct zx_vga *vga)
 
 	drm_connector_helper_add(connector, &zx_vga_connector_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to attach encoder: %d\n", ret);
 		goto clean_connector;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index f1d5f76e9c33..d88073e7d22d 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -218,6 +218,9 @@ static int host1x_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	if (IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL))
+		goto skip_iommu;
+
 	host->group = iommu_group_get(&pdev->dev);
 	if (host->group) {
 		struct iommu_domain_geometry *geometry;
diff --git a/drivers/gpu/host1x/job.c b/drivers/gpu/host1x/job.c
index e2f4a4d93d20..527a1cddb14f 100644
--- a/drivers/gpu/host1x/job.c
+++ b/drivers/gpu/host1x/job.c
@@ -569,7 +569,8 @@ void host1x_job_unpin(struct host1x_job *job)
 	for (i = 0; i < job->num_unpins; i++) {
 		struct host1x_job_unpin_data *unpin = &job->unpins[i];
 
-		if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) && host->domain) {
+		if (!IS_ENABLED(CONFIG_TEGRA_HOST1X_FIREWALL) &&
+		    unpin->size && host->domain) {
 			iommu_unmap(host->domain, job->addr_phys[i],
 				    unpin->size);
 			free_iova(&host->iova,
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 9f2d9ec42add..125721a7f8b6 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -269,9 +269,20 @@ EXPORT_SYMBOL_GPL(ipu_cpmem_set_uv_offset);
 
 void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride)
 {
+	u32 ilo, sly;
+
+	if (stride < 0) {
+		stride = -stride;
+		ilo = 0x100000 - (stride / 8);
+	} else {
+		ilo = stride / 8;
+	}
+
+	sly = (stride * 2) - 1;
+
 	ipu_ch_param_write_field(ch, IPU_FIELD_SO, 1);
-	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, stride / 8);
-	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, (stride * 2) - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, ilo);
+	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, sly);
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan);
 
diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
index caa05b0702e1..954eefe144e2 100644
--- a/drivers/gpu/ipu-v3/ipu-csi.c
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -224,14 +224,18 @@ static int ipu_csi_set_testgen_mclk(struct ipu_csi *csi, u32 pixel_clk,
  * Find the CSI data format and data width for the given V4L2 media
  * bus pixel format code.
  */
-static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
+static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code,
+				enum v4l2_mbus_type mbus_type)
 {
 	switch (mbus_code) {
 	case MEDIA_BUS_FMT_BGR565_2X8_BE:
 	case MEDIA_BUS_FMT_BGR565_2X8_LE:
 	case MEDIA_BUS_FMT_RGB565_2X8_BE:
 	case MEDIA_BUS_FMT_RGB565_2X8_LE:
-		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		if (mbus_type == V4L2_MBUS_CSI2)
+			cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		else
+			cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
 		cfg->mipi_dt = MIPI_DT_RGB565;
 		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
 		break;
@@ -247,6 +251,12 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
 		cfg->mipi_dt = MIPI_DT_RGB555;
 		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
 		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+	case MEDIA_BUS_FMT_BGR888_1X24:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB_YUV444;
+		cfg->mipi_dt = MIPI_DT_RGB888;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
 	case MEDIA_BUS_FMT_UYVY8_2X8:
 		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
 		cfg->mipi_dt = MIPI_DT_YUV422;
@@ -318,13 +328,17 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
 /*
  * Fill a CSI bus config struct from mbus_config and mbus_framefmt.
  */
-static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
+static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 				 struct v4l2_mbus_config *mbus_cfg,
 				 struct v4l2_mbus_framefmt *mbus_fmt)
 {
+	int ret;
+
 	memset(csicfg, 0, sizeof(*csicfg));
 
-	mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(csicfg, mbus_fmt->code, mbus_cfg->type);
+	if (ret < 0)
+		return ret;
 
 	switch (mbus_cfg->type) {
 	case V4L2_MBUS_PARALLEL:
@@ -339,7 +353,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 		break;
 	case V4L2_MBUS_BT656:
 		csicfg->ext_vsync = 0;
-		if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field))
+		if (V4L2_FIELD_HAS_BOTH(mbus_fmt->field) ||
+		    mbus_fmt->field == V4L2_FIELD_ALTERNATE)
 			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_INTERLACED;
 		else
 			csicfg->clk_mode = IPU_CSI_CLK_MODE_CCIR656_PROGRESSIVE;
@@ -355,6 +370,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 		/* will never get here, keep compiler quiet */
 		break;
 	}
+
+	return 0;
 }
 
 int ipu_csi_init_interface(struct ipu_csi *csi,
@@ -364,8 +381,11 @@ int ipu_csi_init_interface(struct ipu_csi *csi,
 	struct ipu_csi_bus_config cfg;
 	unsigned long flags;
 	u32 width, height, data = 0;
+	int ret;
 
-	fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+	ret = fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+	if (ret < 0)
+		return ret;
 
 	/* set default sensor frame width and height */
 	width = mbus_fmt->width;
@@ -586,11 +606,14 @@ int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
 	struct ipu_csi_bus_config cfg;
 	unsigned long flags;
 	u32 temp;
+	int ret;
 
 	if (vc > 3)
 		return -EINVAL;
 
-	mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(&cfg, mbus_fmt->code, V4L2_MBUS_CSI2);
+	if (ret < 0)
+		return ret;
 
 	spin_lock_irqsave(&csi->lock, flags);
 
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index f858cc72011d..3942ee61bd1c 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1952,6 +1952,8 @@ static int hid_device_probe(struct device *dev)
 	}
 	hdev->io_started = false;
 
+	clear_bit(ffs(HID_STAT_REPROBED), &hdev->status);
+
 	if (!hdev->driver) {
 		id = hid_match_device(hdev, hdrv);
 		if (id == NULL) {
@@ -2215,7 +2217,8 @@ static int __hid_bus_reprobe_drivers(struct device *dev, void *data)
 	struct hid_device *hdev = to_hid_device(dev);
 
 	if (hdev->driver == hdrv &&
-	    !hdrv->match(hdev, hid_ignore_special_drivers))
+	    !hdrv->match(hdev, hid_ignore_special_drivers) &&
+	    !test_and_set_bit(ffs(HID_STAT_REPROBED), &hdev->status))
 		return device_reprobe(dev);
 
 	return 0;
diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 8469b6964ff6..b48100236df8 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -1154,6 +1154,8 @@ copy_rest:
 			goto out;
 		if (list->tail > list->head) {
 			len = list->tail - list->head;
+			if (len > count)
+				len = count;
 
 			if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) {
 				ret = -EFAULT;
@@ -1163,6 +1165,8 @@ copy_rest:
 			list->head += len;
 		} else {
 			len = HID_DEBUG_BUFSIZE - list->head;
+			if (len > count)
+				len = count;
 
 			if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) {
 				ret = -EFAULT;
@@ -1170,7 +1174,9 @@ copy_rest:
 			}
 			list->head = 0;
 			ret += len;
-			goto copy_rest;
+			count -= len;
+			if (count > 0)
+				goto copy_rest;
 		}
 
 	}
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index c1652bb7bd15..eae0cb3ddec6 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -484,7 +484,7 @@ static void i2c_hid_get_input(struct i2c_hid *ihid)
 		return;
 	}
 
-	if ((ret_size > size) || (ret_size <= 2)) {
+	if ((ret_size > size) || (ret_size < 2)) {
 		dev_err(&ihid->client->dev, "%s: incomplete report (%d/%d)\n",
 			__func__, size, ret_size);
 		return;
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index e3ce233f8bdc..23872d08308c 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -36,6 +36,7 @@
 #include <linux/hiddev.h>
 #include <linux/compat.h>
 #include <linux/vmalloc.h>
+#include <linux/nospec.h>
 #include "usbhid.h"
 
 #ifdef CONFIG_USB_DYNAMIC_MINORS
@@ -469,10 +470,14 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 
 		if (uref->field_index >= report->maxfield)
 			goto inval;
+		uref->field_index = array_index_nospec(uref->field_index,
+						       report->maxfield);
 
 		field = report->field[uref->field_index];
 		if (uref->usage_index >= field->maxusage)
 			goto inval;
+		uref->usage_index = array_index_nospec(uref->usage_index,
+						       field->maxusage);
 
 		uref->usage_code = field->usage[uref->usage_index].hid;
 
@@ -499,6 +504,8 @@ static noinline int hiddev_ioctl_usage(struct hiddev *hiddev, unsigned int cmd,
 
 			if (uref->field_index >= report->maxfield)
 				goto inval;
+			uref->field_index = array_index_nospec(uref->field_index,
+							       report->maxfield);
 
 			field = report->field[uref->field_index];
 
@@ -753,6 +760,8 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		if (finfo.field_index >= report->maxfield)
 			break;
+		finfo.field_index = array_index_nospec(finfo.field_index,
+						       report->maxfield);
 
 		field = report->field[finfo.field_index];
 		memset(&finfo, 0, sizeof(finfo));
@@ -797,6 +806,8 @@ static long hiddev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 		if (cinfo.index >= hid->maxcollection)
 			break;
+		cinfo.index = array_index_nospec(cinfo.index,
+						 hid->maxcollection);
 
 		cinfo.type = hid->collection[cinfo.index].type;
 		cinfo.usage = hid->collection[cinfo.index].usage;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 0bb44d0088ed..ad7afa74d365 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -3365,8 +3365,14 @@ void wacom_setup_device_quirks(struct wacom *wacom)
 			if (features->type >= INTUOSHT && features->type <= BAMBOO_PT)
 				features->device_type |= WACOM_DEVICETYPE_PAD;
 
-			features->x_max = 4096;
-			features->y_max = 4096;
+			if (features->type == INTUOSHT2) {
+				features->x_max = features->x_max / 10;
+				features->y_max = features->y_max / 10;
+			}
+			else {
+				features->x_max = 4096;
+				features->y_max = 4096;
+			}
 		}
 		else if (features->pktlen == WACOM_PKGLEN_BBTOUCH) {
 			features->device_type |= WACOM_DEVICETYPE_PAD;
diff --git a/drivers/i2c/busses/i2c-cht-wc.c b/drivers/i2c/busses/i2c-cht-wc.c
index 44cffad43701..c4d176f5ed79 100644
--- a/drivers/i2c/busses/i2c-cht-wc.c
+++ b/drivers/i2c/busses/i2c-cht-wc.c
@@ -234,7 +234,8 @@ static const struct irq_chip cht_wc_i2c_irq_chip = {
 	.name			= "cht_wc_ext_chrg_irq_chip",
 };
 
-static const char * const bq24190_suppliers[] = { "fusb302-typec-source" };
+static const char * const bq24190_suppliers[] = {
+	"tcpm-source-psy-i2c-fusb302" };
 
 static const struct property_entry bq24190_props[] = {
 	PROPERTY_ENTRY_STRING_ARRAY("supplied-from", bq24190_suppliers),
diff --git a/drivers/i2c/busses/i2c-davinci.c b/drivers/i2c/busses/i2c-davinci.c
index 75d6ab177055..7379043711df 100644
--- a/drivers/i2c/busses/i2c-davinci.c
+++ b/drivers/i2c/busses/i2c-davinci.c
@@ -237,12 +237,16 @@ static void i2c_davinci_calc_clk_dividers(struct davinci_i2c_dev *dev)
 	/*
 	 * It's not always possible to have 1 to 2 ratio when d=7, so fall back
 	 * to minimal possible clkh in this case.
+	 *
+	 * Note:
+	 * CLKH is not allowed to be 0, in this case I2C clock is not generated
+	 * at all
 	 */
-	if (clk >= clkl + d) {
+	if (clk > clkl + d) {
 		clkh = clk - clkl - d;
 		clkl -= d;
 	} else {
-		clkh = 0;
+		clkh = 1;
 		clkl = clk - (d << 1);
 	}
 
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index 0207e194f84b..498c5e891649 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -368,6 +368,7 @@ static int i2c_imx_dma_xfer(struct imx_i2c_struct *i2c_imx,
 		goto err_desc;
 	}
 
+	reinit_completion(&dma->cmd_complete);
 	txdesc->callback = i2c_imx_dma_callback;
 	txdesc->callback_param = i2c_imx;
 	if (dma_submit_error(dmaengine_submit(txdesc))) {
@@ -622,7 +623,6 @@ static int i2c_imx_dma_write(struct imx_i2c_struct *i2c_imx,
 	 * The first byte must be transmitted by the CPU.
 	 */
 	imx_i2c_write_reg(i2c_8bit_addr_from_msg(msgs), i2c_imx, IMX_I2C_I2DR);
-	reinit_completion(&i2c_imx->dma->cmd_complete);
 	time_left = wait_for_completion_timeout(
 				&i2c_imx->dma->cmd_complete,
 				msecs_to_jiffies(DMA_TIMEOUT));
@@ -681,7 +681,6 @@ static int i2c_imx_dma_read(struct imx_i2c_struct *i2c_imx,
 	if (result)
 		return result;
 
-	reinit_completion(&i2c_imx->dma->cmd_complete);
 	time_left = wait_for_completion_timeout(
 				&i2c_imx->dma->cmd_complete,
 				msecs_to_jiffies(DMA_TIMEOUT));
@@ -1010,7 +1009,7 @@ static int i2c_imx_init_recovery_info(struct imx_i2c_struct *i2c_imx,
 	i2c_imx->pinctrl_pins_gpio = pinctrl_lookup_state(i2c_imx->pinctrl,
 			"gpio");
 	rinfo->sda_gpiod = devm_gpiod_get(&pdev->dev, "sda", GPIOD_IN);
-	rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH);
+	rinfo->scl_gpiod = devm_gpiod_get(&pdev->dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN);
 
 	if (PTR_ERR(rinfo->sda_gpiod) == -EPROBE_DEFER ||
 	    PTR_ERR(rinfo->scl_gpiod) == -EPROBE_DEFER) {
diff --git a/drivers/i2c/busses/i2c-rcar.c b/drivers/i2c/busses/i2c-rcar.c
index 5e310efd9446..3c1c817f6968 100644
--- a/drivers/i2c/busses/i2c-rcar.c
+++ b/drivers/i2c/busses/i2c-rcar.c
@@ -32,6 +32,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/reset.h>
 #include <linux/slab.h>
 
 /* register offsets */
@@ -111,8 +112,9 @@
 #define ID_ARBLOST	(1 << 3)
 #define ID_NACK		(1 << 4)
 /* persistent flags */
+#define ID_P_NO_RXDMA	(1 << 30) /* HW forbids RXDMA sometimes */
 #define ID_P_PM_BLOCKED	(1 << 31)
-#define ID_P_MASK	ID_P_PM_BLOCKED
+#define ID_P_MASK	(ID_P_PM_BLOCKED | ID_P_NO_RXDMA)
 
 enum rcar_i2c_type {
 	I2C_RCAR_GEN1,
@@ -141,6 +143,8 @@ struct rcar_i2c_priv {
 	struct dma_chan *dma_rx;
 	struct scatterlist sg;
 	enum dma_data_direction dma_direction;
+
+	struct reset_control *rstc;
 };
 
 #define rcar_i2c_priv_to_dev(p)		((p)->adap.dev.parent)
@@ -370,6 +374,11 @@ static void rcar_i2c_dma_unmap(struct rcar_i2c_priv *priv)
 	dma_unmap_single(chan->device->dev, sg_dma_address(&priv->sg),
 			 sg_dma_len(&priv->sg), priv->dma_direction);
 
+	/* Gen3 can only do one RXDMA per transfer and we just completed it */
+	if (priv->devtype == I2C_RCAR_GEN3 &&
+	    priv->dma_direction == DMA_FROM_DEVICE)
+		priv->flags |= ID_P_NO_RXDMA;
+
 	priv->dma_direction = DMA_NONE;
 }
 
@@ -407,8 +416,9 @@ static void rcar_i2c_dma(struct rcar_i2c_priv *priv)
 	unsigned char *buf;
 	int len;
 
-	/* Do not use DMA if it's not available or for messages < 8 bytes */
-	if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE))
+	/* Do various checks to see if DMA is feasible at all */
+	if (IS_ERR(chan) || msg->len < 8 || !(msg->flags & I2C_M_DMA_SAFE) ||
+	    (read && priv->flags & ID_P_NO_RXDMA))
 		return;
 
 	if (read) {
@@ -739,6 +749,25 @@ static void rcar_i2c_release_dma(struct rcar_i2c_priv *priv)
 	}
 }
 
+/* I2C is a special case, we need to poll the status of a reset */
+static int rcar_i2c_do_reset(struct rcar_i2c_priv *priv)
+{
+	int i, ret;
+
+	ret = reset_control_reset(priv->rstc);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < LOOP_TIMEOUT; i++) {
+		ret = reset_control_status(priv->rstc);
+		if (ret == 0)
+			return 0;
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
 static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 				struct i2c_msg *msgs,
 				int num)
@@ -750,6 +779,16 @@ static int rcar_i2c_master_xfer(struct i2c_adapter *adap,
 
 	pm_runtime_get_sync(dev);
 
+	/* Gen3 needs a reset before allowing RXDMA once */
+	if (priv->devtype == I2C_RCAR_GEN3) {
+		priv->flags |= ID_P_NO_RXDMA;
+		if (!IS_ERR(priv->rstc)) {
+			ret = rcar_i2c_do_reset(priv);
+			if (ret == 0)
+				priv->flags &= ~ID_P_NO_RXDMA;
+		}
+	}
+
 	rcar_i2c_init(priv);
 
 	ret = rcar_i2c_bus_barrier(priv);
@@ -920,6 +959,15 @@ static int rcar_i2c_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto out_pm_put;
 
+	if (priv->devtype == I2C_RCAR_GEN3) {
+		priv->rstc = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+		if (!IS_ERR(priv->rstc)) {
+			ret = reset_control_status(priv->rstc);
+			if (ret < 0)
+				priv->rstc = ERR_PTR(-ENOTSUPP);
+		}
+	}
+
 	/* Stay always active when multi-master to keep arbitration working */
 	if (of_property_read_bool(dev->of_node, "multi-master"))
 		priv->flags |= ID_P_PM_BLOCKED;
diff --git a/drivers/i2c/busses/i2c-stu300.c b/drivers/i2c/busses/i2c-stu300.c
index e866c481bfc3..fce52bdab2b7 100644
--- a/drivers/i2c/busses/i2c-stu300.c
+++ b/drivers/i2c/busses/i2c-stu300.c
@@ -127,7 +127,7 @@ enum stu300_error {
 
 /*
  * The number of address send athemps tried before giving up.
- * If the first one failes it seems like 5 to 8 attempts are required.
+ * If the first one fails it seems like 5 to 8 attempts are required.
  */
 #define NUM_ADDR_RESEND_ATTEMPTS 12
 
diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
index 5fccd1f1bca8..797def5319f1 100644
--- a/drivers/i2c/busses/i2c-tegra.c
+++ b/drivers/i2c/busses/i2c-tegra.c
@@ -545,6 +545,14 @@ static int tegra_i2c_disable_packet_mode(struct tegra_i2c_dev *i2c_dev)
 {
 	u32 cnfg;
 
+	/*
+	 * NACK interrupt is generated before the I2C controller generates
+	 * the STOP condition on the bus. So wait for 2 clock periods
+	 * before disabling the controller so that the STOP condition has
+	 * been delivered properly.
+	 */
+	udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
+
 	cnfg = i2c_readl(i2c_dev, I2C_CNFG);
 	if (cnfg & I2C_CNFG_PACKET_MODE_EN)
 		i2c_writel(i2c_dev, cnfg & ~I2C_CNFG_PACKET_MODE_EN, I2C_CNFG);
@@ -706,15 +714,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev *i2c_dev,
 	if (likely(i2c_dev->msg_err == I2C_ERR_NONE))
 		return 0;
 
-	/*
-	 * NACK interrupt is generated before the I2C controller generates
-	 * the STOP condition on the bus. So wait for 2 clock periods
-	 * before resetting the controller so that the STOP condition has
-	 * been delivered properly.
-	 */
-	if (i2c_dev->msg_err == I2C_ERR_NO_ACK)
-		udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
-
 	tegra_i2c_init(i2c_dev);
 	if (i2c_dev->msg_err == I2C_ERR_NO_ACK) {
 		if (msg->flags & I2C_M_IGNORE_NAK)
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 31d16ada6e7d..301285c54603 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -198,7 +198,16 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 
 		val = !val;
 		bri->set_scl(adap, val);
-		ndelay(RECOVERY_NDELAY);
+
+		/*
+		 * If we can set SDA, we will always create STOP here to ensure
+		 * the additional pulses will do no harm. This is achieved by
+		 * letting SDA follow SCL half a cycle later.
+		 */
+		ndelay(RECOVERY_NDELAY / 2);
+		if (bri->set_sda)
+			bri->set_sda(adap, val);
+		ndelay(RECOVERY_NDELAY / 2);
 	}
 
 	/* check if recovery actually succeeded */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 3e90b6a1d9d2..cc06e8404e9b 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -3488,8 +3488,8 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 	struct ib_flow_attr		  *flow_attr;
 	struct ib_qp			  *qp;
 	struct ib_uflow_resources	  *uflow_res;
+	struct ib_uverbs_flow_spec_hdr	  *kern_spec;
 	int err = 0;
-	void *kern_spec;
 	void *ib_spec;
 	int i;
 
@@ -3538,8 +3538,8 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		if (!kern_flow_attr)
 			return -ENOMEM;
 
-		memcpy(kern_flow_attr, &cmd.flow_attr, sizeof(*kern_flow_attr));
-		err = ib_copy_from_udata(kern_flow_attr + 1, ucore,
+		*kern_flow_attr = cmd.flow_attr;
+		err = ib_copy_from_udata(&kern_flow_attr->flow_specs, ucore,
 					 cmd.flow_attr.size);
 		if (err)
 			goto err_free_attr;
@@ -3559,6 +3559,11 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 		goto err_uobj;
 	}
 
+	if (qp->qp_type != IB_QPT_UD && qp->qp_type != IB_QPT_RAW_PACKET) {
+		err = -EINVAL;
+		goto err_put;
+	}
+
 	flow_attr = kzalloc(struct_size(flow_attr, flows,
 				cmd.flow_attr.num_of_specs), GFP_KERNEL);
 	if (!flow_attr) {
@@ -3578,21 +3583,22 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file,
 	flow_attr->flags = kern_flow_attr->flags;
 	flow_attr->size = sizeof(*flow_attr);
 
-	kern_spec = kern_flow_attr + 1;
+	kern_spec = kern_flow_attr->flow_specs;
 	ib_spec = flow_attr + 1;
 	for (i = 0; i < flow_attr->num_of_specs &&
-	     cmd.flow_attr.size > offsetof(struct ib_uverbs_flow_spec, reserved) &&
-	     cmd.flow_attr.size >=
-	     ((struct ib_uverbs_flow_spec *)kern_spec)->size; i++) {
-		err = kern_spec_to_ib_spec(file->ucontext, kern_spec, ib_spec,
-					   uflow_res);
+			cmd.flow_attr.size >= sizeof(*kern_spec) &&
+			cmd.flow_attr.size >= kern_spec->size;
+	     i++) {
+		err = kern_spec_to_ib_spec(
+				file->ucontext, (struct ib_uverbs_flow_spec *)kern_spec,
+				ib_spec, uflow_res);
 		if (err)
 			goto err_free;
 
 		flow_attr->size +=
 			((union ib_flow_spec *) ib_spec)->size;
-		cmd.flow_attr.size -= ((struct ib_uverbs_flow_spec *)kern_spec)->size;
-		kern_spec += ((struct ib_uverbs_flow_spec *) kern_spec)->size;
+		cmd.flow_attr.size -= kern_spec->size;
+		kern_spec = ((void *)kern_spec) + kern_spec->size;
 		ib_spec += ((union ib_flow_spec *) ib_spec)->size;
 	}
 	if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) {
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 1445918e3239..7b76e6f81aeb 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -774,7 +774,7 @@ static int c4iw_set_page(struct ib_mr *ibmr, u64 addr)
 {
 	struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
 
-	if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
+	if (unlikely(mhp->mpl_len == mhp->attr.pbl_size))
 		return -ENOMEM;
 
 	mhp->mpl[mhp->mpl_len++] = addr;
diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
index 1a1a47ac53c6..f15c93102081 100644
--- a/drivers/infiniband/hw/hfi1/rc.c
+++ b/drivers/infiniband/hw/hfi1/rc.c
@@ -271,7 +271,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 
 	lockdep_assert_held(&qp->s_lock);
 	ps->s_txreq = get_txreq(ps->dev, qp);
-	if (IS_ERR(ps->s_txreq))
+	if (!ps->s_txreq)
 		goto bail_no_tx;
 
 	if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
index b7b671017e59..e254dcec6f64 100644
--- a/drivers/infiniband/hw/hfi1/uc.c
+++ b/drivers/infiniband/hw/hfi1/uc.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -72,7 +72,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	int middle = 0;
 
 	ps->s_txreq = get_txreq(ps->dev, qp);
-	if (IS_ERR(ps->s_txreq))
+	if (!ps->s_txreq)
 		goto bail_no_tx;
 
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
index 1ab332f1866e..70d39fc450a1 100644
--- a/drivers/infiniband/hw/hfi1/ud.c
+++ b/drivers/infiniband/hw/hfi1/ud.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2015, 2016 Intel Corporation.
+ * Copyright(c) 2015 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -503,7 +503,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct hfi1_pkt_state *ps)
 	u32 lid;
 
 	ps->s_txreq = get_txreq(ps->dev, qp);
-	if (IS_ERR(ps->s_txreq))
+	if (!ps->s_txreq)
 		goto bail_no_tx;
 
 	if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c b/drivers/infiniband/hw/hfi1/verbs_txreq.c
index 873e48ea923f..c4ab2d5b4502 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.c
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 - 2017 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -94,7 +94,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
 				struct rvt_qp *qp)
 	__must_hold(&qp->s_lock)
 {
-	struct verbs_txreq *tx = ERR_PTR(-EBUSY);
+	struct verbs_txreq *tx = NULL;
 
 	write_seqlock(&dev->txwait_lock);
 	if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h b/drivers/infiniband/hw/hfi1/verbs_txreq.h
index 729244c3086c..1c19bbc764b2 100644
--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
+++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation.
+ * Copyright(c) 2016 - 2018 Intel Corporation.
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
@@ -83,7 +83,7 @@ static inline struct verbs_txreq *get_txreq(struct hfi1_ibdev *dev,
 	if (unlikely(!tx)) {
 		/* call slow path to get the lock */
 		tx = __get_txreq(dev, qp);
-		if (IS_ERR(tx))
+		if (!tx)
 			return tx;
 	}
 	tx->qp = qp;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index e3e330f59c2c..b3ba9a222550 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -6113,7 +6113,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
 			     MLX5_CAP_GEN(mdev, num_vhca_ports));
 
-	if (MLX5_VPORT_MANAGER(mdev) &&
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
 	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
 		dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0);
 
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index 0af7b7905550..f5de5adc9b1a 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -266,18 +266,24 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 
 	desc_size = sizeof(struct mlx5_wqe_srq_next_seg) +
 		    srq->msrq.max_gs * sizeof(struct mlx5_wqe_data_seg);
-	if (desc_size == 0 || srq->msrq.max_gs > desc_size)
-		return ERR_PTR(-EINVAL);
+	if (desc_size == 0 || srq->msrq.max_gs > desc_size) {
+		err = -EINVAL;
+		goto err_srq;
+	}
 	desc_size = roundup_pow_of_two(desc_size);
 	desc_size = max_t(size_t, 32, desc_size);
-	if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg))
-		return ERR_PTR(-EINVAL);
+	if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg)) {
+		err = -EINVAL;
+		goto err_srq;
+	}
 	srq->msrq.max_avail_gather = (desc_size - sizeof(struct mlx5_wqe_srq_next_seg)) /
 		sizeof(struct mlx5_wqe_data_seg);
 	srq->msrq.wqe_shift = ilog2(desc_size);
 	buf_size = srq->msrq.max * desc_size;
-	if (buf_size < desc_size)
-		return ERR_PTR(-EINVAL);
+	if (buf_size < desc_size) {
+		err = -EINVAL;
+		goto err_srq;
+	}
 	in.type = init_attr->srq_type;
 
 	if (pd->uobject)
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 1f9cd7d8b7ad..f5ae24865355 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -1346,6 +1346,8 @@ static const struct acpi_device_id elan_acpi_id[] = {
 	{ "ELAN0611", 0 },
 	{ "ELAN0612", 0 },
 	{ "ELAN0618", 0 },
+	{ "ELAN061D", 0 },
+	{ "ELAN0622", 0 },
 	{ "ELAN1000", 0 },
 	{ }
 };
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index b353d494ad40..136f6e7bf797 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -527,6 +527,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "N24_25BU"),
 		},
 	},
+	{
+		/* Lenovo LaVie Z */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "Lenovo LaVie Z"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index e055d228bfb9..689ffe538370 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -142,7 +142,6 @@ config DMAR_TABLE
 config INTEL_IOMMU
 	bool "Support for Intel IOMMU using DMA Remapping Devices"
 	depends on PCI_MSI && ACPI && (X86 || IA64_GENERIC)
-	select DMA_DIRECT_OPS
 	select IOMMU_API
 	select IOMMU_IOVA
 	select NEED_DMA_MAP_STATE
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 14e4b3722428..115ff26e9ced 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -31,7 +31,6 @@
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma-direct.h>
 #include <linux/mempool.h>
 #include <linux/memory.h>
 #include <linux/cpu.h>
@@ -485,14 +484,37 @@ static int dmar_forcedac;
 static int intel_iommu_strict;
 static int intel_iommu_superpage = 1;
 static int intel_iommu_ecs = 1;
+static int intel_iommu_pasid28;
 static int iommu_identity_mapping;
 
 #define IDENTMAP_ALL		1
 #define IDENTMAP_GFX		2
 #define IDENTMAP_AZALIA		4
 
-#define ecs_enabled(iommu)	(intel_iommu_ecs && ecap_ecs(iommu->ecap))
-#define pasid_enabled(iommu)	(ecs_enabled(iommu) && ecap_pasid(iommu->ecap))
+/* Broadwell and Skylake have broken ECS support — normal so-called "second
+ * level" translation of DMA requests-without-PASID doesn't actually happen
+ * unless you also set the NESTE bit in an extended context-entry. Which of
+ * course means that SVM doesn't work because it's trying to do nested
+ * translation of the physical addresses it finds in the process page tables,
+ * through the IOVA->phys mapping found in the "second level" page tables.
+ *
+ * The VT-d specification was retroactively changed to change the definition
+ * of the capability bits and pretend that Broadwell/Skylake never happened...
+ * but unfortunately the wrong bit was changed. It's ECS which is broken, but
+ * for some reason it was the PASID capability bit which was redefined (from
+ * bit 28 on BDW/SKL to bit 40 in future).
+ *
+ * So our test for ECS needs to eschew those implementations which set the old
+ * PASID capabiity bit 28, since those are the ones on which ECS is broken.
+ * Unless we are working around the 'pasid28' limitations, that is, by putting
+ * the device into passthrough mode for normal DMA and thus masking the bug.
+ */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+			    (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap)))
+/* PASID support is thus enabled if ECS is enabled and *either* of the old
+ * or new capability bits are set. */
+#define pasid_enabled(iommu) (ecs_enabled(iommu) &&			\
+			      (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap)))
 
 int intel_iommu_gfx_mapped;
 EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
@@ -555,6 +577,11 @@ static int __init intel_iommu_setup(char *str)
 			printk(KERN_INFO
 				"Intel-IOMMU: disable extended context table support\n");
 			intel_iommu_ecs = 0;
+		} else if (!strncmp(str, "pasid28", 7)) {
+			printk(KERN_INFO
+				"Intel-IOMMU: enable pre-production PASID support\n");
+			intel_iommu_pasid28 = 1;
+			iommu_identity_mapping |= IDENTMAP_GFX;
 		} else if (!strncmp(str, "tboot_noforce", 13)) {
 			printk(KERN_INFO
 				"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
@@ -3713,30 +3740,61 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
 				  dma_addr_t *dma_handle, gfp_t flags,
 				  unsigned long attrs)
 {
-	void *vaddr;
+	struct page *page = NULL;
+	int order;
 
-	vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs);
-	if (iommu_no_mapping(dev) || !vaddr)
-		return vaddr;
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
 
-	*dma_handle = __intel_map_single(dev, virt_to_phys(vaddr),
-			PAGE_ALIGN(size), DMA_BIDIRECTIONAL,
-			dev->coherent_dma_mask);
-	if (!*dma_handle)
-		goto out_free_pages;
-	return vaddr;
+	if (!iommu_no_mapping(dev))
+		flags &= ~(GFP_DMA | GFP_DMA32);
+	else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
+		if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
+			flags |= GFP_DMA;
+		else
+			flags |= GFP_DMA32;
+	}
+
+	if (gfpflags_allow_blocking(flags)) {
+		unsigned int count = size >> PAGE_SHIFT;
+
+		page = dma_alloc_from_contiguous(dev, count, order, flags);
+		if (page && iommu_no_mapping(dev) &&
+		    page_to_phys(page) + size > dev->coherent_dma_mask) {
+			dma_release_from_contiguous(dev, page, count);
+			page = NULL;
+		}
+	}
+
+	if (!page)
+		page = alloc_pages(flags, order);
+	if (!page)
+		return NULL;
+	memset(page_address(page), 0, size);
+
+	*dma_handle = __intel_map_single(dev, page_to_phys(page), size,
+					 DMA_BIDIRECTIONAL,
+					 dev->coherent_dma_mask);
+	if (*dma_handle)
+		return page_address(page);
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, order);
 
-out_free_pages:
-	dma_direct_free(dev, size, vaddr, *dma_handle, attrs);
 	return NULL;
 }
 
 static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
 				dma_addr_t dma_handle, unsigned long attrs)
 {
-	if (!iommu_no_mapping(dev))
-		intel_unmap(dev, dma_handle, PAGE_ALIGN(size));
-	dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+	int order;
+	struct page *page = virt_to_page(vaddr);
+
+	size = PAGE_ALIGN(size);
+	order = get_order(size);
+
+	intel_unmap(dev, dma_handle, size);
+	if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+		__free_pages(page, order);
 }
 
 static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index 07ea6a48aac6..87107c995cb5 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -136,6 +136,7 @@ struct dm_writecache {
 	struct dm_target *ti;
 	struct dm_dev *dev;
 	struct dm_dev *ssd_dev;
+	sector_t start_sector;
 	void *memory_map;
 	uint64_t memory_map_size;
 	size_t metadata_sectors;
@@ -293,6 +294,10 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 	}
 
 	dax_read_unlock(id);
+
+	wc->memory_map += (size_t)wc->start_sector << SECTOR_SHIFT;
+	wc->memory_map_size -= (size_t)wc->start_sector << SECTOR_SHIFT;
+
 	return 0;
 err3:
 	kvfree(pages);
@@ -311,7 +316,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 static void persistent_memory_release(struct dm_writecache *wc)
 {
 	if (wc->memory_vmapped)
-		vunmap(wc->memory_map);
+		vunmap(wc->memory_map - ((size_t)wc->start_sector << SECTOR_SHIFT));
 }
 
 static struct page *persistent_memory_page(void *addr)
@@ -359,7 +364,7 @@ static void *memory_data(struct dm_writecache *wc, struct wc_entry *e)
 
 static sector_t cache_sector(struct dm_writecache *wc, struct wc_entry *e)
 {
-	return wc->metadata_sectors +
+	return wc->start_sector + wc->metadata_sectors +
 		((sector_t)e->index << (wc->block_size_bits - SECTOR_SHIFT));
 }
 
@@ -471,6 +476,7 @@ static void ssd_commit_flushed(struct dm_writecache *wc)
 		if (unlikely(region.sector + region.count > wc->metadata_sectors))
 			region.count = wc->metadata_sectors - region.sector;
 
+		region.sector += wc->start_sector;
 		atomic_inc(&endio.count);
 		req.bi_op = REQ_OP_WRITE;
 		req.bi_op_flags = REQ_SYNC;
@@ -1946,14 +1952,6 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	}
 	wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode);
 
-	if (WC_MODE_PMEM(wc)) {
-		r = persistent_memory_claim(wc);
-		if (r) {
-			ti->error = "Unable to map persistent memory for cache";
-			goto bad;
-		}
-	}
-
 	/*
 	 * Parse the cache block size
 	 */
@@ -1982,7 +1980,16 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	while (opt_params) {
 		string = dm_shift_arg(&as), opt_params--;
-		if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
+		if (!strcasecmp(string, "start_sector") && opt_params >= 1) {
+			unsigned long long start_sector;
+			string = dm_shift_arg(&as), opt_params--;
+			if (sscanf(string, "%llu%c", &start_sector, &dummy) != 1)
+				goto invalid_optional;
+			wc->start_sector = start_sector;
+			if (wc->start_sector != start_sector ||
+			    wc->start_sector >= wc->memory_map_size >> SECTOR_SHIFT)
+				goto invalid_optional;
+		} else if (!strcasecmp(string, "high_watermark") && opt_params >= 1) {
 			string = dm_shift_arg(&as), opt_params--;
 			if (sscanf(string, "%d%c", &high_wm_percent, &dummy) != 1)
 				goto invalid_optional;
@@ -2039,12 +2046,20 @@ invalid_optional:
 		goto bad;
 	}
 
-	if (!WC_MODE_PMEM(wc)) {
+	if (WC_MODE_PMEM(wc)) {
+		r = persistent_memory_claim(wc);
+		if (r) {
+			ti->error = "Unable to map persistent memory for cache";
+			goto bad;
+		}
+	} else {
 		struct dm_io_region region;
 		struct dm_io_request req;
 		size_t n_blocks, n_metadata_blocks;
 		uint64_t n_bitmap_bits;
 
+		wc->memory_map_size -= (uint64_t)wc->start_sector << SECTOR_SHIFT;
+
 		bio_list_init(&wc->flush_list);
 		wc->flush_thread = kthread_create(writecache_flush_thread, wc, "dm_writecache_flush");
 		if (IS_ERR(wc->flush_thread)) {
@@ -2097,7 +2112,7 @@ invalid_optional:
 		}
 
 		region.bdev = wc->ssd_dev->bdev;
-		region.sector = 0;
+		region.sector = wc->start_sector;
 		region.count = wc->metadata_sectors;
 		req.bi_op = REQ_OP_READ;
 		req.bi_op_flags = REQ_SYNC;
@@ -2265,7 +2280,7 @@ static void writecache_status(struct dm_target *ti, status_type_t type,
 
 static struct target_type writecache_target = {
 	.name			= "writecache",
-	.version		= {1, 0, 0},
+	.version		= {1, 1, 0},
 	.module			= THIS_MODULE,
 	.ctr			= writecache_ctr,
 	.dtr			= writecache_dtr,
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 29b0cd9ec951..994aed2f9dff 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5547,7 +5547,8 @@ int md_run(struct mddev *mddev)
 		else
 			pr_warn("md: personality for level %s is not loaded!\n",
 				mddev->clevel);
-		return -EINVAL;
+		err = -EINVAL;
+		goto abort;
 	}
 	spin_unlock(&pers_lock);
 	if (mddev->level != pers->level) {
@@ -5560,7 +5561,8 @@ int md_run(struct mddev *mddev)
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
 		module_put(pers->owner);
-		return -EINVAL;
+		err = -EINVAL;
+		goto abort;
 	}
 
 	if (pers->sync_request) {
@@ -5629,7 +5631,7 @@ int md_run(struct mddev *mddev)
 		mddev->private = NULL;
 		module_put(pers->owner);
 		bitmap_destroy(mddev);
-		return err;
+		goto abort;
 	}
 	if (mddev->queue) {
 		bool nonrot = true;
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 478cf446827f..35bd3a62451b 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3893,6 +3893,13 @@ static int raid10_run(struct mddev *mddev)
 			    disk->rdev->saved_raid_disk < 0)
 				conf->fullsync = 1;
 		}
+
+		if (disk->replacement &&
+		    !test_bit(In_sync, &disk->replacement->flags) &&
+		    disk->replacement->saved_raid_disk < 0) {
+			conf->fullsync = 1;
+		}
+
 		disk->recovery_disabled = mddev->recovery_disabled - 1;
 	}
 
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 40826bba06b6..fcfab6635f9c 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -207,29 +207,19 @@ void lirc_bpf_free(struct rc_dev *rcdev)
 	bpf_prog_array_free(rcdev->raw->progs);
 }
 
-int lirc_prog_attach(const union bpf_attr *attr)
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
-	struct bpf_prog *prog;
 	struct rc_dev *rcdev;
 	int ret;
 
 	if (attr->attach_flags)
 		return -EINVAL;
 
-	prog = bpf_prog_get_type(attr->attach_bpf_fd,
-				 BPF_PROG_TYPE_LIRC_MODE2);
-	if (IS_ERR(prog))
-		return PTR_ERR(prog);
-
 	rcdev = rc_dev_get_from_fd(attr->target_fd);
-	if (IS_ERR(rcdev)) {
-		bpf_prog_put(prog);
+	if (IS_ERR(rcdev))
 		return PTR_ERR(rcdev);
-	}
 
 	ret = lirc_bpf_attach(rcdev, prog);
-	if (ret)
-		bpf_prog_put(prog);
 
 	put_device(&rcdev->dev);
 
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 753b1a698fc4..6b16946f9b05 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -103,15 +103,15 @@ static struct file *cxl_getfile(const char *name,
 	d_instantiate(path.dentry, inode);
 
 	file = alloc_file(&path, OPEN_FMODE(flags), fops);
-	if (IS_ERR(file))
-		goto err_dput;
+	if (IS_ERR(file)) {
+		path_put(&path);
+		goto err_fs;
+	}
 	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
 err_inode:
 	iput(inode);
 err_fs:
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index e05c3245930a..fa840666bdd1 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -507,35 +507,14 @@ static int remote_settings_file_close(struct inode *inode, struct file *file)
 static ssize_t remote_settings_file_read(struct file *file, char __user *buf, size_t count, loff_t *offset)
 {
 	void __iomem *address = (void __iomem *)file->private_data;
-	unsigned char *page;
-	int retval;
 	int len = 0;
 	unsigned int value;
-
-	if (*offset < 0)
-		return -EINVAL;
-	if (count == 0 || count > 1024)
-		return 0;
-	if (*offset != 0)
-		return 0;
-
-	page = (unsigned char *)__get_free_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
+	char lbuf[20];
 
 	value = readl(address);
-	len = sprintf(page, "%d\n", value);
-
-	if (copy_to_user(buf, page, len)) {
-		retval = -EFAULT;
-		goto exit;
-	}
-	*offset += len;
-	retval = len;
+	len = snprintf(lbuf, sizeof(lbuf), "%d\n", value);
 
-exit:
-	free_page((unsigned long)page);
-	return retval;
+	return simple_read_from_buffer(buf, count, offset, lbuf, len);
 }
 
 static ssize_t remote_settings_file_write(struct file *file, const char __user *ubuff, size_t count, loff_t *offset)
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index b0b8f18a85e3..6649f0d56d2f 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -310,8 +310,11 @@ int mei_irq_read_handler(struct mei_device *dev,
 	if (&cl->link == &dev->file_list) {
 		/* A message for not connected fixed address clients
 		 * should be silently discarded
+		 * On power down client may be force cleaned,
+		 * silently discard such messages
 		 */
-		if (hdr_is_fixed(mei_hdr)) {
+		if (hdr_is_fixed(mei_hdr) ||
+		    dev->dev_state == MEI_DEV_POWER_DOWN) {
 			mei_irq_discard_msg(dev, mei_hdr);
 			ret = 0;
 			goto reset_slots;
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index efd733472a35..56c6f79a5c5a 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -467,7 +467,7 @@ static int vmballoon_send_batched_lock(struct vmballoon *b,
 		unsigned int num_pages, bool is_2m_pages, unsigned int *target)
 {
 	unsigned long status;
-	unsigned long pfn = page_to_pfn(b->page);
+	unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
 
 	STATS_INC(b->stats.lock[is_2m_pages]);
 
@@ -515,7 +515,7 @@ static bool vmballoon_send_batched_unlock(struct vmballoon *b,
 		unsigned int num_pages, bool is_2m_pages, unsigned int *target)
 {
 	unsigned long status;
-	unsigned long pfn = page_to_pfn(b->page);
+	unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
 
 	STATS_INC(b->stats.unlock[is_2m_pages]);
 
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index ef05e0039378..2a833686784b 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -27,8 +27,8 @@ struct mmc_gpio {
 	bool override_cd_active_level;
 	irqreturn_t (*cd_gpio_isr)(int irq, void *dev_id);
 	char *ro_label;
-	char cd_label[0];
 	u32 cd_debounce_delay_ms;
+	char cd_label[];
 };
 
 static irqreturn_t mmc_gpio_cd_irqt(int irq, void *dev_id)
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 623f4d27fa01..80dc2fd6576c 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -1065,8 +1065,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data)
 	 * It's used when HS400 mode is enabled.
 	 */
 	if (data->flags & MMC_DATA_WRITE &&
-		!(host->timing != MMC_TIMING_MMC_HS400))
-		return;
+		host->timing != MMC_TIMING_MMC_HS400)
+		goto disable;
 
 	if (data->flags & MMC_DATA_WRITE)
 		enable = SDMMC_CARD_WR_THR_EN;
@@ -1074,7 +1074,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct mmc_data *data)
 		enable = SDMMC_CARD_RD_THR_EN;
 
 	if (host->timing != MMC_TIMING_MMC_HS200 &&
-	    host->timing != MMC_TIMING_UHS_SDR104)
+	    host->timing != MMC_TIMING_UHS_SDR104 &&
+	    host->timing != MMC_TIMING_MMC_HS400)
 		goto disable;
 
 	blksz_depth = blksz / (1 << host->data_shift);
diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
index f7f9773d161f..d032bd63444d 100644
--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
@@ -139,8 +139,7 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host *host) {
 	renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
 					    RST_RESERVED_BITS | val);
 
-	if (host->data && host->data->flags & MMC_DATA_READ)
-		clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+	clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
 
 	renesas_sdhi_internal_dmac_enable_dma(host, true);
 }
@@ -164,17 +163,14 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 		goto force_pio;
 
 	/* This DMAC cannot handle if buffer is not 8-bytes alignment */
-	if (!IS_ALIGNED(sg_dma_address(sg), 8)) {
-		dma_unmap_sg(&host->pdev->dev, sg, host->sg_len,
-			     mmc_get_dma_dir(data));
-		goto force_pio;
-	}
+	if (!IS_ALIGNED(sg_dma_address(sg), 8))
+		goto force_pio_with_unmap;
 
 	if (data->flags & MMC_DATA_READ) {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH1;
 		if (test_bit(SDHI_INTERNAL_DMAC_ONE_RX_ONLY, &global_flags) &&
 		    test_and_set_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags))
-			goto force_pio;
+			goto force_pio_with_unmap;
 	} else {
 		dtran_mode |= DTRAN_MODE_CH_NUM_CH0;
 	}
@@ -189,6 +185,9 @@ renesas_sdhi_internal_dmac_start_dma(struct tmio_mmc_host *host,
 
 	return;
 
+force_pio_with_unmap:
+	dma_unmap_sg(&host->pdev->dev, sg, host->sg_len, mmc_get_dma_dir(data));
+
 force_pio:
 	host->force_pio = true;
 	renesas_sdhi_internal_dmac_enable_dma(host, false);
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index d6aef70d34fa..4eb3d29ecde1 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -312,6 +312,15 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int reg)
 
 			if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
 				val |= SDHCI_SUPPORT_HS400;
+
+			/*
+			 * Do not advertise faster UHS modes if there are no
+			 * pinctrl states for 100MHz/200MHz.
+			 */
+			if (IS_ERR_OR_NULL(imx_data->pins_100mhz) ||
+			    IS_ERR_OR_NULL(imx_data->pins_200mhz))
+				val &= ~(SDHCI_SUPPORT_SDR50 | SDHCI_SUPPORT_DDR50
+					 | SDHCI_SUPPORT_SDR104 | SDHCI_SUPPORT_HS400);
 		}
 	}
 
@@ -1158,18 +1167,6 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 						ESDHC_PINCTRL_STATE_100MHZ);
 		imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
 						ESDHC_PINCTRL_STATE_200MHZ);
-		if (IS_ERR(imx_data->pins_100mhz) ||
-				IS_ERR(imx_data->pins_200mhz)) {
-			dev_warn(mmc_dev(host->mmc),
-				"could not get ultra high speed state, work on normal mode\n");
-			/*
-			 * fall back to not supporting uhs by specifying no
-			 * 1.8v quirk
-			 */
-			host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
-		}
-	} else {
-		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
 	}
 
 	/* call to generic mmc_of_parse to support additional capabilities */
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index e7472590f2ed..8e7f3e35ee3d 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -1446,6 +1446,7 @@ static int sunxi_mmc_runtime_resume(struct device *dev)
 	sunxi_mmc_init_host(host);
 	sunxi_mmc_set_bus_width(host, mmc->ios.bus_width);
 	sunxi_mmc_set_clk(host, &mmc->ios);
+	enable_irq(host->irq);
 
 	return 0;
 }
@@ -1455,6 +1456,12 @@ static int sunxi_mmc_runtime_suspend(struct device *dev)
 	struct mmc_host	*mmc = dev_get_drvdata(dev);
 	struct sunxi_mmc_host *host = mmc_priv(mmc);
 
+	/*
+	 * When clocks are off, it's possible receiving
+	 * fake interrupts, which will stall the system.
+	 * Disabling the irq  will prevent this.
+	 */
+	disable_irq(host->irq);
 	sunxi_mmc_reset_host(host);
 	sunxi_mmc_disable(host);
 
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index c3f7aaa5d18f..d7e10b36a0b9 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -926,10 +926,12 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t to,
 	if (ret)
 		return ret;
 
-	if (f_pdata->use_direct_mode)
+	if (f_pdata->use_direct_mode) {
 		memcpy_toio(cqspi->ahb_base + to, buf, len);
-	else
+		ret = cqspi_wait_idle(cqspi);
+	} else {
 		ret = cqspi_indirect_write_execute(nor, to, buf, len);
+	}
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 98663c50ded0..4d5d01cb8141 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -743,15 +743,20 @@ const struct bond_option *bond_opt_get(unsigned int option)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
-	if (!bond_mode_uses_arp(newval->value) && bond->params.arp_interval) {
-		netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
-			   newval->string);
-		/* disable arp monitoring */
-		bond->params.arp_interval = 0;
-		/* set miimon to default value */
-		bond->params.miimon = BOND_DEFAULT_MIIMON;
-		netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
-			   bond->params.miimon);
+	if (!bond_mode_uses_arp(newval->value)) {
+		if (bond->params.arp_interval) {
+			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
+				   newval->string);
+			/* disable arp monitoring */
+			bond->params.arp_interval = 0;
+		}
+
+		if (!bond->params.miimon) {
+			/* set miimon to default value */
+			bond->params.miimon = BOND_DEFAULT_MIIMON;
+			netdev_dbg(bond->dev, "Setting MII monitoring interval to %d\n",
+				   bond->params.miimon);
+		}
 	}
 
 	if (newval->value == BOND_MODE_ALB)
diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
index b397a33f3d32..9b449400376b 100644
--- a/drivers/net/can/m_can/m_can.c
+++ b/drivers/net/can/m_can/m_can.c
@@ -634,10 +634,12 @@ static int m_can_clk_start(struct m_can_priv *priv)
 	int err;
 
 	err = pm_runtime_get_sync(priv->device);
-	if (err)
+	if (err < 0) {
 		pm_runtime_put_noidle(priv->device);
+		return err;
+	}
 
-	return err;
+	return 0;
 }
 
 static void m_can_clk_stop(struct m_can_priv *priv)
@@ -1109,7 +1111,8 @@ static void m_can_chip_config(struct net_device *dev)
 
 	} else {
 	/* Version 3.1.x or 3.2.x */
-		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE);
+		cccr &= ~(CCCR_TEST | CCCR_MON | CCCR_BRSE | CCCR_FDOE |
+			  CCCR_NISO);
 
 		/* Only 3.2.x has NISO Bit implemented */
 		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
@@ -1642,8 +1645,6 @@ static int m_can_plat_probe(struct platform_device *pdev)
 	priv->can.clock.freq = clk_get_rate(cclk);
 	priv->mram_base = mram_addr;
 
-	m_can_of_parse_mram(priv, mram_config_vals);
-
 	platform_set_drvdata(pdev, dev);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
@@ -1666,6 +1667,8 @@ static int m_can_plat_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
+	m_can_of_parse_mram(priv, mram_config_vals);
+
 	devm_can_led_init(dev);
 
 	of_can_transceiver(dev);
@@ -1687,8 +1690,6 @@ failed_ret:
 	return ret;
 }
 
-/* TODO: runtime PM with power down or sleep mode  */
-
 static __maybe_unused int m_can_suspend(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
@@ -1715,8 +1716,6 @@ static __maybe_unused int m_can_resume(struct device *dev)
 
 	pinctrl_pm_select_default_state(dev);
 
-	m_can_init_ram(priv);
-
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
 	if (netif_running(ndev)) {
@@ -1726,6 +1725,7 @@ static __maybe_unused int m_can_resume(struct device *dev)
 		if (ret)
 			return ret;
 
+		m_can_init_ram(priv);
 		m_can_start(ndev);
 		netif_device_attach(ndev);
 		netif_start_queue(ndev);
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index c7427bdd3a4b..2949a381a94d 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -86,6 +86,11 @@ static u32 mpc52xx_can_get_clock(struct platform_device *ofdev,
 		return 0;
 	}
 	cdm = of_iomap(np_cdm, 0);
+	if (!cdm) {
+		of_node_put(np_cdm);
+		dev_err(&ofdev->dev, "can't map clock node!\n");
+		return 0;
+	}
 
 	if (in_8(&cdm->ipb_clk_sel) & 0x1)
 		freq *= 2;
diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index b9e28578bc7b..455a3797a200 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -58,6 +58,10 @@ MODULE_LICENSE("GPL v2");
 #define PCIEFD_REG_SYS_VER1		0x0040	/* version reg #1 */
 #define PCIEFD_REG_SYS_VER2		0x0044	/* version reg #2 */
 
+#define PCIEFD_FW_VERSION(x, y, z)	(((u32)(x) << 24) | \
+					 ((u32)(y) << 16) | \
+					 ((u32)(z) << 8))
+
 /* System Control Registers Bits */
 #define PCIEFD_SYS_CTL_TS_RST		0x00000001	/* timestamp clock */
 #define PCIEFD_SYS_CTL_CLK_EN		0x00000002	/* system clock */
@@ -782,6 +786,21 @@ static int peak_pciefd_probe(struct pci_dev *pdev,
 		 "%ux CAN-FD PCAN-PCIe FPGA v%u.%u.%u:\n", can_count,
 		 hw_ver_major, hw_ver_minor, hw_ver_sub);
 
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+	/* FW < v3.3.0 DMA logic doesn't handle correctly the mix of 32-bit and
+	 * 64-bit logical addresses: this workaround forces usage of 32-bit
+	 * DMA addresses only when such a fw is detected.
+	 */
+	if (PCIEFD_FW_VERSION(hw_ver_major, hw_ver_minor, hw_ver_sub) <
+	    PCIEFD_FW_VERSION(3, 3, 0)) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err)
+			dev_warn(&pdev->dev,
+				 "warning: can't set DMA mask %llxh (err %d)\n",
+				 DMA_BIT_MASK(32), err);
+	}
+#endif
+
 	/* stop system clock */
 	pciefd_sys_writereg(pciefd, PCIEFD_SYS_CTL_CLK_EN,
 			    PCIEFD_REG_SYS_CTL_CLR);
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 89aec07c225f..5a24039733ef 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -2,6 +2,7 @@
  *
  * Copyright (C) 2012 - 2014 Xilinx, Inc.
  * Copyright (C) 2009 PetaLogix. All rights reserved.
+ * Copyright (C) 2017 Sandvik Mining and Construction Oy
  *
  * Description:
  * This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
@@ -25,8 +26,10 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/skbuff.h>
+#include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/can/dev.h>
@@ -101,7 +104,7 @@ enum xcan_reg {
 #define XCAN_INTR_ALL		(XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
 				 XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
 				 XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
-				 XCAN_IXR_ARBLST_MASK | XCAN_IXR_RXOK_MASK)
+				 XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)
 
 /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
 #define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
@@ -118,6 +121,7 @@ enum xcan_reg {
 /**
  * struct xcan_priv - This definition define CAN driver instance
  * @can:			CAN private data structure.
+ * @tx_lock:			Lock for synchronizing TX interrupt handling
  * @tx_head:			Tx CAN packets ready to send on the queue
  * @tx_tail:			Tx CAN packets successfully sended on the queue
  * @tx_max:			Maximum number packets the driver can send
@@ -132,6 +136,7 @@ enum xcan_reg {
  */
 struct xcan_priv {
 	struct can_priv can;
+	spinlock_t tx_lock;
 	unsigned int tx_head;
 	unsigned int tx_tail;
 	unsigned int tx_max;
@@ -159,6 +164,11 @@ static const struct can_bittiming_const xcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
+#define XCAN_CAP_WATERMARK	0x0001
+struct xcan_devtype_data {
+	unsigned int caps;
+};
+
 /**
  * xcan_write_reg_le - Write a value to the device register little endian
  * @priv:	Driver private data structure
@@ -238,6 +248,10 @@ static int set_reset_mode(struct net_device *ndev)
 		usleep_range(500, 10000);
 	}
 
+	/* reset clears FIFOs */
+	priv->tx_head = 0;
+	priv->tx_tail = 0;
+
 	return 0;
 }
 
@@ -392,6 +406,7 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 id, dlc, data[2] = {0, 0};
+	unsigned long flags;
 
 	if (can_dropped_invalid_skb(ndev, skb))
 		return NETDEV_TX_OK;
@@ -439,6 +454,9 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
 
 	can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
 	priv->tx_head++;
 
 	/* Write the Frame to Xilinx CAN TX FIFO */
@@ -454,10 +472,16 @@ static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		stats->tx_bytes += cf->can_dlc;
 	}
 
+	/* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
+	if (priv->tx_max > 1)
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXFEMP_MASK);
+
 	/* Check if the TX buffer is full */
 	if ((priv->tx_head - priv->tx_tail) == priv->tx_max)
 		netif_stop_queue(ndev);
 
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
 	return NETDEV_TX_OK;
 }
 
@@ -530,6 +554,123 @@ static int xcan_rx(struct net_device *ndev)
 }
 
 /**
+ * xcan_current_error_state - Get current error state from HW
+ * @ndev:	Pointer to net_device structure
+ *
+ * Checks the current CAN error state from the HW. Note that this
+ * only checks for ERROR_PASSIVE and ERROR_WARNING.
+ *
+ * Return:
+ * ERROR_PASSIVE or ERROR_WARNING if either is active, ERROR_ACTIVE
+ * otherwise.
+ */
+static enum can_state xcan_current_error_state(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 status = priv->read_reg(priv, XCAN_SR_OFFSET);
+
+	if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK)
+		return CAN_STATE_ERROR_PASSIVE;
+	else if (status & XCAN_SR_ERRWRN_MASK)
+		return CAN_STATE_ERROR_WARNING;
+	else
+		return CAN_STATE_ERROR_ACTIVE;
+}
+
+/**
+ * xcan_set_error_state - Set new CAN error state
+ * @ndev:	Pointer to net_device structure
+ * @new_state:	The new CAN state to be set
+ * @cf:		Error frame to be populated or NULL
+ *
+ * Set new CAN error state for the device, updating statistics and
+ * populating the error frame if given.
+ */
+static void xcan_set_error_state(struct net_device *ndev,
+				 enum can_state new_state,
+				 struct can_frame *cf)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
+	u32 txerr = ecr & XCAN_ECR_TEC_MASK;
+	u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+
+	priv->can.state = new_state;
+
+	if (cf) {
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[6] = txerr;
+		cf->data[7] = rxerr;
+	}
+
+	switch (new_state) {
+	case CAN_STATE_ERROR_PASSIVE:
+		priv->can.can_stats.error_passive++;
+		if (cf)
+			cf->data[1] = (rxerr > 127) ?
+					CAN_ERR_CRTL_RX_PASSIVE :
+					CAN_ERR_CRTL_TX_PASSIVE;
+		break;
+	case CAN_STATE_ERROR_WARNING:
+		priv->can.can_stats.error_warning++;
+		if (cf)
+			cf->data[1] |= (txerr > rxerr) ?
+					CAN_ERR_CRTL_TX_WARNING :
+					CAN_ERR_CRTL_RX_WARNING;
+		break;
+	case CAN_STATE_ERROR_ACTIVE:
+		if (cf)
+			cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
+		break;
+	default:
+		/* non-ERROR states are handled elsewhere */
+		WARN_ON(1);
+		break;
+	}
+}
+
+/**
+ * xcan_update_error_state_after_rxtx - Update CAN error state after RX/TX
+ * @ndev:	Pointer to net_device structure
+ *
+ * If the device is in a ERROR-WARNING or ERROR-PASSIVE state, check if
+ * the performed RX/TX has caused it to drop to a lesser state and set
+ * the interface state accordingly.
+ */
+static void xcan_update_error_state_after_rxtx(struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	enum can_state old_state = priv->can.state;
+	enum can_state new_state;
+
+	/* changing error state due to successful frame RX/TX can only
+	 * occur from these states
+	 */
+	if (old_state != CAN_STATE_ERROR_WARNING &&
+	    old_state != CAN_STATE_ERROR_PASSIVE)
+		return;
+
+	new_state = xcan_current_error_state(ndev);
+
+	if (new_state != old_state) {
+		struct sk_buff *skb;
+		struct can_frame *cf;
+
+		skb = alloc_can_err_skb(ndev, &cf);
+
+		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+
+		if (skb) {
+			struct net_device_stats *stats = &ndev->stats;
+
+			stats->rx_packets++;
+			stats->rx_bytes += cf->can_dlc;
+			netif_rx(skb);
+		}
+	}
+}
+
+/**
  * xcan_err_interrupt - error frame Isr
  * @ndev:	net_device pointer
  * @isr:	interrupt status register value
@@ -544,16 +685,12 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf;
 	struct sk_buff *skb;
-	u32 err_status, status, txerr = 0, rxerr = 0;
+	u32 err_status;
 
 	skb = alloc_can_err_skb(ndev, &cf);
 
 	err_status = priv->read_reg(priv, XCAN_ESR_OFFSET);
 	priv->write_reg(priv, XCAN_ESR_OFFSET, err_status);
-	txerr = priv->read_reg(priv, XCAN_ECR_OFFSET) & XCAN_ECR_TEC_MASK;
-	rxerr = ((priv->read_reg(priv, XCAN_ECR_OFFSET) &
-			XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT);
-	status = priv->read_reg(priv, XCAN_SR_OFFSET);
 
 	if (isr & XCAN_IXR_BSOFF_MASK) {
 		priv->can.state = CAN_STATE_BUS_OFF;
@@ -563,28 +700,10 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 		can_bus_off(ndev);
 		if (skb)
 			cf->can_id |= CAN_ERR_BUSOFF;
-	} else if ((status & XCAN_SR_ESTAT_MASK) == XCAN_SR_ESTAT_MASK) {
-		priv->can.state = CAN_STATE_ERROR_PASSIVE;
-		priv->can.can_stats.error_passive++;
-		if (skb) {
-			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[1] = (rxerr > 127) ?
-					CAN_ERR_CRTL_RX_PASSIVE :
-					CAN_ERR_CRTL_TX_PASSIVE;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
-	} else if (status & XCAN_SR_ERRWRN_MASK) {
-		priv->can.state = CAN_STATE_ERROR_WARNING;
-		priv->can.can_stats.error_warning++;
-		if (skb) {
-			cf->can_id |= CAN_ERR_CRTL;
-			cf->data[1] |= (txerr > rxerr) ?
-					CAN_ERR_CRTL_TX_WARNING :
-					CAN_ERR_CRTL_RX_WARNING;
-			cf->data[6] = txerr;
-			cf->data[7] = rxerr;
-		}
+	} else {
+		enum can_state new_state = xcan_current_error_state(ndev);
+
+		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
 	}
 
 	/* Check for Arbitration lost interrupt */
@@ -600,7 +719,6 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	if (isr & XCAN_IXR_RXOFLW_MASK) {
 		stats->rx_over_errors++;
 		stats->rx_errors++;
-		priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
 		if (skb) {
 			cf->can_id |= CAN_ERR_CRTL;
 			cf->data[1] |= CAN_ERR_CRTL_RX_OVERFLOW;
@@ -709,26 +827,20 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
-		if (isr & XCAN_IXR_RXOK_MASK) {
-			priv->write_reg(priv, XCAN_ICR_OFFSET,
-				XCAN_IXR_RXOK_MASK);
-			work_done += xcan_rx(ndev);
-		} else {
-			priv->write_reg(priv, XCAN_ICR_OFFSET,
-				XCAN_IXR_RXNEMP_MASK);
-			break;
-		}
+		work_done += xcan_rx(ndev);
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
 		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
 
-	if (work_done)
+	if (work_done) {
 		can_led_event(ndev, CAN_LED_EVENT_RX);
+		xcan_update_error_state_after_rxtx(ndev);
+	}
 
 	if (work_done < quota) {
 		napi_complete_done(napi, work_done);
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier |= (XCAN_IXR_RXOK_MASK | XCAN_IXR_RXNEMP_MASK);
+		ier |= XCAN_IXR_RXNEMP_MASK;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 	}
 	return work_done;
@@ -743,18 +855,71 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
+	unsigned int frames_in_fifo;
+	int frames_sent = 1; /* TXOK => at least 1 frame was sent */
+	unsigned long flags;
+	int retries = 0;
+
+	/* Synchronize with xmit as we need to know the exact number
+	 * of frames in the FIFO to stay in sync due to the TXFEMP
+	 * handling.
+	 * This also prevents a race between netif_wake_queue() and
+	 * netif_stop_queue().
+	 */
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	frames_in_fifo = priv->tx_head - priv->tx_tail;
+
+	if (WARN_ON_ONCE(frames_in_fifo == 0)) {
+		/* clear TXOK anyway to avoid getting back here */
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+		spin_unlock_irqrestore(&priv->tx_lock, flags);
+		return;
+	}
+
+	/* Check if 2 frames were sent (TXOK only means that at least 1
+	 * frame was sent).
+	 */
+	if (frames_in_fifo > 1) {
+		WARN_ON(frames_in_fifo > priv->tx_max);
+
+		/* Synchronize TXOK and isr so that after the loop:
+		 * (1) isr variable is up-to-date at least up to TXOK clear
+		 *     time. This avoids us clearing a TXOK of a second frame
+		 *     but not noticing that the FIFO is now empty and thus
+		 *     marking only a single frame as sent.
+		 * (2) No TXOK is left. Having one could mean leaving a
+		 *     stray TXOK as we might process the associated frame
+		 *     via TXFEMP handling as we read TXFEMP *after* TXOK
+		 *     clear to satisfy (1).
+		 */
+		while ((isr & XCAN_IXR_TXOK_MASK) && !WARN_ON(++retries == 100)) {
+			priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+			isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+		}
 
-	while ((priv->tx_head - priv->tx_tail > 0) &&
-			(isr & XCAN_IXR_TXOK_MASK)) {
+		if (isr & XCAN_IXR_TXFEMP_MASK) {
+			/* nothing in FIFO anymore */
+			frames_sent = frames_in_fifo;
+		}
+	} else {
+		/* single frame in fifo, just clear TXOK */
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_TXOK_MASK);
+	}
+
+	while (frames_sent--) {
 		can_get_echo_skb(ndev, priv->tx_tail %
 					priv->tx_max);
 		priv->tx_tail++;
 		stats->tx_packets++;
-		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
-	can_led_event(ndev, CAN_LED_EVENT_TX);
+
 	netif_wake_queue(ndev);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	can_led_event(ndev, CAN_LED_EVENT_TX);
+	xcan_update_error_state_after_rxtx(ndev);
 }
 
 /**
@@ -773,6 +938,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 	struct net_device *ndev = (struct net_device *)dev_id;
 	struct xcan_priv *priv = netdev_priv(ndev);
 	u32 isr, ier;
+	u32 isr_errors;
 
 	/* Get the interrupt status from Xilinx CAN */
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
@@ -791,18 +957,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 		xcan_tx_interrupt(ndev, isr);
 
 	/* Check for the type of error interrupt and Processing it */
-	if (isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
-			XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK)) {
-		priv->write_reg(priv, XCAN_ICR_OFFSET, (XCAN_IXR_ERROR_MASK |
-				XCAN_IXR_RXOFLW_MASK | XCAN_IXR_BSOFF_MASK |
-				XCAN_IXR_ARBLST_MASK));
+	isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
+	if (isr_errors) {
+		priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
 		xcan_err_interrupt(ndev, isr);
 	}
 
 	/* Check for the type of receive interrupt and Processing it */
-	if (isr & (XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK)) {
+	if (isr & XCAN_IXR_RXNEMP_MASK) {
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier &= ~(XCAN_IXR_RXNEMP_MASK | XCAN_IXR_RXOK_MASK);
+		ier &= ~XCAN_IXR_RXNEMP_MASK;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 		napi_schedule(&priv->napi);
 	}
@@ -819,13 +984,9 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 static void xcan_chip_stop(struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
-	u32 ier;
 
 	/* Disable interrupts and leave the can in configuration mode */
-	ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-	ier &= ~XCAN_INTR_ALL;
-	priv->write_reg(priv, XCAN_IER_OFFSET, ier);
-	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
+	set_reset_mode(ndev);
 	priv->can.state = CAN_STATE_STOPPED;
 }
 
@@ -958,10 +1119,15 @@ static const struct net_device_ops xcan_netdev_ops = {
  */
 static int __maybe_unused xcan_suspend(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
-		return pm_runtime_force_suspend(dev);
+	struct net_device *ndev = dev_get_drvdata(dev);
 
-	return 0;
+	if (netif_running(ndev)) {
+		netif_stop_queue(ndev);
+		netif_device_detach(ndev);
+		xcan_chip_stop(ndev);
+	}
+
+	return pm_runtime_force_suspend(dev);
 }
 
 /**
@@ -973,11 +1139,27 @@ static int __maybe_unused xcan_suspend(struct device *dev)
  */
 static int __maybe_unused xcan_resume(struct device *dev)
 {
-	if (!device_may_wakeup(dev))
-		return pm_runtime_force_resume(dev);
+	struct net_device *ndev = dev_get_drvdata(dev);
+	int ret;
 
-	return 0;
+	ret = pm_runtime_force_resume(dev);
+	if (ret) {
+		dev_err(dev, "pm_runtime_force_resume failed on resume\n");
+		return ret;
+	}
+
+	if (netif_running(ndev)) {
+		ret = xcan_chip_start(ndev);
+		if (ret) {
+			dev_err(dev, "xcan_chip_start failed on resume\n");
+			return ret;
+		}
+
+		netif_device_attach(ndev);
+		netif_start_queue(ndev);
+	}
 
+	return 0;
 }
 
 /**
@@ -992,14 +1174,6 @@ static int __maybe_unused xcan_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xcan_priv *priv = netdev_priv(ndev);
 
-	if (netif_running(ndev)) {
-		netif_stop_queue(ndev);
-		netif_device_detach(ndev);
-	}
-
-	priv->write_reg(priv, XCAN_MSR_OFFSET, XCAN_MSR_SLEEP_MASK);
-	priv->can.state = CAN_STATE_SLEEPING;
-
 	clk_disable_unprepare(priv->bus_clk);
 	clk_disable_unprepare(priv->can_clk);
 
@@ -1018,7 +1192,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct xcan_priv *priv = netdev_priv(ndev);
 	int ret;
-	u32 isr, status;
 
 	ret = clk_prepare_enable(priv->bus_clk);
 	if (ret) {
@@ -1032,27 +1205,6 @@ static int __maybe_unused xcan_runtime_resume(struct device *dev)
 		return ret;
 	}
 
-	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_RESET_MASK);
-	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
-	status = priv->read_reg(priv, XCAN_SR_OFFSET);
-
-	if (netif_running(ndev)) {
-		if (isr & XCAN_IXR_BSOFF_MASK) {
-			priv->can.state = CAN_STATE_BUS_OFF;
-			priv->write_reg(priv, XCAN_SRR_OFFSET,
-					XCAN_SRR_RESET_MASK);
-		} else if ((status & XCAN_SR_ESTAT_MASK) ==
-					XCAN_SR_ESTAT_MASK) {
-			priv->can.state = CAN_STATE_ERROR_PASSIVE;
-		} else if (status & XCAN_SR_ERRWRN_MASK) {
-			priv->can.state = CAN_STATE_ERROR_WARNING;
-		} else {
-			priv->can.state = CAN_STATE_ERROR_ACTIVE;
-		}
-		netif_device_attach(ndev);
-		netif_start_queue(ndev);
-	}
-
 	return 0;
 }
 
@@ -1061,6 +1213,18 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
 	SET_RUNTIME_PM_OPS(xcan_runtime_suspend, xcan_runtime_resume, NULL)
 };
 
+static const struct xcan_devtype_data xcan_zynq_data = {
+	.caps = XCAN_CAP_WATERMARK,
+};
+
+/* Match table for OF platform binding */
+static const struct of_device_id xcan_of_match[] = {
+	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
+	{ .compatible = "xlnx,axi-can-1.00.a", },
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(of, xcan_of_match);
+
 /**
  * xcan_probe - Platform registration call
  * @pdev:	Handle to the platform device structure
@@ -1075,8 +1239,10 @@ static int xcan_probe(struct platform_device *pdev)
 	struct resource *res; /* IO mem resources */
 	struct net_device *ndev;
 	struct xcan_priv *priv;
+	const struct of_device_id *of_id;
+	int caps = 0;
 	void __iomem *addr;
-	int ret, rx_max, tx_max;
+	int ret, rx_max, tx_max, tx_fifo_depth;
 
 	/* Get the virtual base address for the device */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1086,7 +1252,8 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth", &tx_max);
+	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
+				   &tx_fifo_depth);
 	if (ret < 0)
 		goto err;
 
@@ -1094,6 +1261,30 @@ static int xcan_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err;
 
+	of_id = of_match_device(xcan_of_match, &pdev->dev);
+	if (of_id) {
+		const struct xcan_devtype_data *devtype_data = of_id->data;
+
+		if (devtype_data)
+			caps = devtype_data->caps;
+	}
+
+	/* There is no way to directly figure out how many frames have been
+	 * sent when the TXOK interrupt is processed. If watermark programming
+	 * is supported, we can have 2 frames in the FIFO and use TXFEMP
+	 * to determine if 1 or 2 frames have been sent.
+	 * Theoretically we should be able to use TXFWMEMP to determine up
+	 * to 3 frames, but it seems that after putting a second frame in the
+	 * FIFO, with watermark at 2 frames, it can happen that TXFWMEMP (less
+	 * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
+	 * sent), which is not a sensible state - possibly TXFWMEMP is not
+	 * completely synchronized with the rest of the bits?
+	 */
+	if (caps & XCAN_CAP_WATERMARK)
+		tx_max = min(tx_fifo_depth, 2);
+	else
+		tx_max = 1;
+
 	/* Create a CAN device instance */
 	ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
 	if (!ndev)
@@ -1108,6 +1299,7 @@ static int xcan_probe(struct platform_device *pdev)
 					CAN_CTRLMODE_BERR_REPORTING;
 	priv->reg_base = addr;
 	priv->tx_max = tx_max;
+	spin_lock_init(&priv->tx_lock);
 
 	/* Get IRQ for the device */
 	ndev->irq = platform_get_irq(pdev, 0);
@@ -1172,9 +1364,9 @@ static int xcan_probe(struct platform_device *pdev)
 
 	pm_runtime_put(&pdev->dev);
 
-	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth:%d\n",
+	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
 			priv->reg_base, ndev->irq, priv->can.clock.freq,
-			priv->tx_max);
+			tx_fifo_depth, priv->tx_max);
 
 	return 0;
 
@@ -1208,14 +1400,6 @@ static int xcan_remove(struct platform_device *pdev)
 	return 0;
 }
 
-/* Match table for OF platform binding */
-static const struct of_device_id xcan_of_match[] = {
-	{ .compatible = "xlnx,zynq-can-1.0", },
-	{ .compatible = "xlnx,axi-can-1.00.a", },
-	{ /* end of list */ },
-};
-MODULE_DEVICE_TABLE(of, xcan_of_match);
-
 static struct platform_driver xcan_driver = {
 	.probe = xcan_probe,
 	.remove	= xcan_remove,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 437cd6eb4faa..9ef07a06aceb 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -343,6 +343,7 @@ static const struct irq_domain_ops mv88e6xxx_g1_irq_domain_ops = {
 	.xlate	= irq_domain_xlate_twocell,
 };
 
+/* To be called with reg_lock held */
 static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 {
 	int irq, virq;
@@ -362,9 +363,15 @@ static void mv88e6xxx_g1_irq_free_common(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_g1_irq_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
+	/*
+	 * free_irq must be called without reg_lock taken because the irq
+	 * handler takes this lock, too.
+	 */
 	free_irq(chip->irq, chip);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip)
@@ -469,10 +476,12 @@ static int mv88e6xxx_irq_poll_setup(struct mv88e6xxx_chip *chip)
 
 static void mv88e6xxx_irq_poll_free(struct mv88e6xxx_chip *chip)
 {
-	mv88e6xxx_g1_irq_free_common(chip);
-
 	kthread_cancel_delayed_work_sync(&chip->irq_poll_work);
 	kthread_destroy_worker(chip->kworker);
+
+	mutex_lock(&chip->reg_lock);
+	mv88e6xxx_g1_irq_free_common(chip);
+	mutex_unlock(&chip->reg_lock);
 }
 
 int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask)
@@ -4506,12 +4515,10 @@ out_g2_irq:
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 out_g1_irq:
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 out:
 	if (pdata)
 		dev_put(pdata->netdev);
@@ -4539,12 +4546,10 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev)
 	if (chip->info->g2_irqs > 0)
 		mv88e6xxx_g2_irq_free(chip);
 
-	mutex_lock(&chip->reg_lock);
 	if (chip->irq > 0)
 		mv88e6xxx_g1_irq_free(chip);
 	else
 		mv88e6xxx_irq_poll_free(chip);
-	mutex_unlock(&chip->reg_lock);
 }
 
 static const struct of_device_id mv88e6xxx_of_match[] = {
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 5b7658bcf020..5c3ef9fc8207 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -32,7 +32,7 @@ config EL3
 
 config 3C515
 	tristate "3c515 ISA \"Fast EtherLink\""
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !PPC32
 	---help---
 	  If you have a 3Com ISA EtherLink XL "Corkscrew" 3c515 Fast Ethernet
 	  network card, say Y here.
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index f273af136fc7..9e5cf5583c87 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -44,7 +44,7 @@ config AMD8111_ETH
 
 config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
-	depends on ISA && ISA_DMA_API && !ARM
+	depends on ISA && ISA_DMA_API && !ARM && !PPC32
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y here.
 	  Some LinkSys cards are of this type.
@@ -138,7 +138,7 @@ config PCMCIA_NMCLAN
 
 config NI65
 	tristate "NI6510 support"
-	depends on ISA && ISA_DMA_API && !ARM
+	depends on ISA && ISA_DMA_API && !ARM && !PPC32
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y here.
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index fc7383106946..91eb8910b1c9 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -63,8 +63,6 @@
 
 #define AQ_CFG_NAPI_WEIGHT     64U
 
-#define AQ_CFG_MULTICAST_ADDRESS_MAX     32U
-
 /*#define AQ_CFG_MAC_ADDR_PERMANENT {0x30, 0x0E, 0xE3, 0x12, 0x34, 0x56}*/
 
 #define AQ_NIC_FC_OFF    0U
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index a2d416b24ffc..2c6ebd91a9f2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -98,6 +98,8 @@ struct aq_stats_s {
 #define AQ_HW_MEDIA_TYPE_TP    1U
 #define AQ_HW_MEDIA_TYPE_FIBRE 2U
 
+#define AQ_HW_MULTICAST_ADDRESS_MAX     32U
+
 struct aq_hw_s {
 	atomic_t flags;
 	u8 rbl_enabled:1;
@@ -177,7 +179,7 @@ struct aq_hw_ops {
 				    unsigned int packet_filter);
 
 	int (*hw_multicast_list_set)(struct aq_hw_s *self,
-				     u8 ar_mac[AQ_CFG_MULTICAST_ADDRESS_MAX]
+				     u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
 				     [ETH_ALEN],
 				     u32 count);
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index ba5fe8c4125d..e3ae29e523f0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -135,17 +135,10 @@ err_exit:
 static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 {
 	struct aq_nic_s *aq_nic = netdev_priv(ndev);
-	int err = 0;
 
-	err = aq_nic_set_packet_filter(aq_nic, ndev->flags);
-	if (err < 0)
-		return;
+	aq_nic_set_packet_filter(aq_nic, ndev->flags);
 
-	if (netdev_mc_count(ndev)) {
-		err = aq_nic_set_multicast_list(aq_nic, ndev);
-		if (err < 0)
-			return;
-	}
+	aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
 static const struct net_device_ops aq_ndev_ops = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 1a1a6380c128..7a22d0257e04 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -563,34 +563,41 @@ err_exit:
 
 int aq_nic_set_multicast_list(struct aq_nic_s *self, struct net_device *ndev)
 {
+	unsigned int packet_filter = self->packet_filter;
 	struct netdev_hw_addr *ha = NULL;
 	unsigned int i = 0U;
 
-	self->mc_list.count = 0U;
-
-	netdev_for_each_mc_addr(ha, ndev) {
-		ether_addr_copy(self->mc_list.ar[i++], ha->addr);
-		++self->mc_list.count;
+	self->mc_list.count = 0;
+	if (netdev_uc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_PROMISC;
+	} else {
+		netdev_for_each_uc_addr(ha, ndev) {
+			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
 
-		if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX)
-			break;
+			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+				break;
+		}
 	}
 
-	if (i >= AQ_CFG_MULTICAST_ADDRESS_MAX) {
-		/* Number of filters is too big: atlantic does not support this.
-		 * Force all multi filter to support this.
-		 * With this we disable all UC filters and setup "all pass"
-		 * multicast mask
-		 */
-		self->packet_filter |= IFF_ALLMULTI;
-		self->aq_nic_cfg.mc_list_count = 0;
-		return self->aq_hw_ops->hw_packet_filter_set(self->aq_hw,
-							     self->packet_filter);
+	if (i + netdev_mc_count(ndev) > AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_ALLMULTI;
 	} else {
-		return self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
-						    self->mc_list.ar,
-						    self->mc_list.count);
+		netdev_for_each_mc_addr(ha, ndev) {
+			ether_addr_copy(self->mc_list.ar[i++], ha->addr);
+
+			if (i >= AQ_HW_MULTICAST_ADDRESS_MAX)
+				break;
+		}
+	}
+
+	if (i > 0 && i < AQ_HW_MULTICAST_ADDRESS_MAX) {
+		packet_filter |= IFF_MULTICAST;
+		self->mc_list.count = i;
+		self->aq_hw_ops->hw_multicast_list_set(self->aq_hw,
+						       self->mc_list.ar,
+						       self->mc_list.count);
 	}
+	return aq_nic_set_packet_filter(self, packet_filter);
 }
 
 int aq_nic_set_mtu(struct aq_nic_s *self, int new_mtu)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index faa533a0ec47..fecfc401f95d 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -75,7 +75,7 @@ struct aq_nic_s {
 	struct aq_hw_link_status_s link_status;
 	struct {
 		u32 count;
-		u8 ar[AQ_CFG_MULTICAST_ADDRESS_MAX][ETH_ALEN];
+		u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN];
 	} mc_list;
 
 	struct pci_dev *pdev;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 67e2f9fb9402..8cc6abadc03b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -765,7 +765,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self,
 
 static int hw_atl_a0_hw_multicast_list_set(struct aq_hw_s *self,
 					   u8 ar_mac
-					   [AQ_CFG_MULTICAST_ADDRESS_MAX]
+					   [AQ_HW_MULTICAST_ADDRESS_MAX]
 					   [ETH_ALEN],
 					   u32 count)
 {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 819f6bcf9b4e..956860a69797 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -784,7 +784,7 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self,
 
 static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
 					   u8 ar_mac
-					   [AQ_CFG_MULTICAST_ADDRESS_MAX]
+					   [AQ_HW_MULTICAST_ADDRESS_MAX]
 					   [ETH_ALEN],
 					   u32 count)
 {
@@ -812,7 +812,7 @@ static int hw_atl_b0_hw_multicast_list_set(struct aq_hw_s *self,
 
 		hw_atl_rpfl2_uc_flr_en_set(self,
 					   (self->aq_nic_cfg->is_mc_list_enabled),
-				    HW_ATL_B0_MAC_MIN + i);
+					   HW_ATL_B0_MAC_MIN + i);
 	}
 
 	err = aq_hw_err_from_flags(self);
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 567ee54504bc..5e5022fa1d04 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1897,13 +1897,19 @@ static int alx_resume(struct device *dev)
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct alx_priv *alx = pci_get_drvdata(pdev);
 	struct alx_hw *hw = &alx->hw;
+	int err;
 
 	alx_reset_phy(hw);
 
 	if (!netif_running(alx->dev))
 		return 0;
 	netif_device_attach(alx->dev);
-	return __alx_open(alx, true);
+
+	rtnl_lock();
+	err = __alx_open(alx, true);
+	rtnl_unlock();
+
+	return err;
 }
 
 static SIMPLE_DEV_PM_OPS(alx_pm_ops, alx_suspend, alx_resume);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 94270f654b3b..7087b88550db 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1686,6 +1686,7 @@ static struct sk_buff *atl1c_alloc_skb(struct atl1c_adapter *adapter)
 	skb = build_skb(page_address(page) + adapter->rx_page_offset,
 			adapter->rx_frag_size);
 	if (likely(skb)) {
+		skb_reserve(skb, NET_SKB_PAD);
 		adapter->rx_page_offset += adapter->rx_frag_size;
 		if (adapter->rx_page_offset >= PAGE_SIZE)
 			adapter->rx_page = NULL;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index d5fca2e5a9bc..a1f60f89e059 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1946,8 +1946,8 @@ static int bcm_sysport_open(struct net_device *dev)
 	if (!priv->is_lite)
 		priv->crc_fwd = !!(umac_readl(priv, UMAC_CMD) & CMD_CRC_FWD);
 	else
-		priv->crc_fwd = !!(gib_readl(priv, GIB_CONTROL) &
-				   GIB_FCS_STRIP);
+		priv->crc_fwd = !((gib_readl(priv, GIB_CONTROL) &
+				  GIB_FCS_STRIP) >> GIB_FCS_STRIP_SHIFT);
 
 	phydev = of_phy_connect(dev, priv->phy_dn, bcm_sysport_adj_link,
 				0, priv->phy_interface);
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index d6e5d0cbf3a3..cf440b91fd04 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -278,7 +278,8 @@ struct bcm_rsb {
 #define  GIB_GTX_CLK_EXT_CLK		(0 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_125MHZ		(1 << GIB_GTX_CLK_SEL_SHIFT)
 #define  GIB_GTX_CLK_250MHZ		(2 << GIB_GTX_CLK_SEL_SHIFT)
-#define  GIB_FCS_STRIP			(1 << 6)
+#define  GIB_FCS_STRIP_SHIFT		6
+#define  GIB_FCS_STRIP			(1 << GIB_FCS_STRIP_SHIFT)
 #define  GIB_LCL_LOOP_EN		(1 << 7)
 #define  GIB_LCL_LOOP_TXEN		(1 << 8)
 #define  GIB_RMT_LOOP_EN		(1 << 9)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index d847e1b9c37b..be1506169076 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1533,6 +1533,7 @@ struct bnx2x {
 	struct link_vars	link_vars;
 	u32			link_cnt;
 	struct bnx2x_link_report_data last_reported_link;
+	bool			force_link_down;
 
 	struct mdio_if_info	mdio;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 8cd73ff5debc..af7b5a4d8ba0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1261,6 +1261,11 @@ void __bnx2x_link_report(struct bnx2x *bp)
 {
 	struct bnx2x_link_report_data cur_data;
 
+	if (bp->force_link_down) {
+		bp->link_vars.link_up = 0;
+		return;
+	}
+
 	/* reread mf_cfg */
 	if (IS_PF(bp) && !CHIP_IS_E1(bp))
 		bnx2x_read_mf_cfg(bp);
@@ -2817,6 +2822,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 		bp->pending_max = 0;
 	}
 
+	bp->force_link_down = false;
 	if (bp->port.pmf) {
 		rc = bnx2x_initial_phy_init(bp, load_mode);
 		if (rc)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index da18aa239acb..a4a90b6cdb46 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -3388,14 +3388,18 @@ static int bnx2x_set_rss_flags(struct bnx2x *bp, struct ethtool_rxnfc *info)
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+			if (bp->state == BNX2X_STATE_OPEN)
+				return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+						 true);
 		} else if ((info->flow_type == UDP_V6_FLOW) &&
 			   (bp->rss_conf_obj.udp_rss_v6 != udp_rss_requested)) {
 			bp->rss_conf_obj.udp_rss_v6 = udp_rss_requested;
 			DP(BNX2X_MSG_ETHTOOL,
 			   "rss re-configured, UDP 4-tupple %s\n",
 			   udp_rss_requested ? "enabled" : "disabled");
-			return bnx2x_rss(bp, &bp->rss_conf_obj, false, true);
+			if (bp->state == BNX2X_STATE_OPEN)
+				return bnx2x_rss(bp, &bp->rss_conf_obj, false,
+						 true);
 		}
 		return 0;
 
@@ -3509,7 +3513,10 @@ static int bnx2x_set_rxfh(struct net_device *dev, const u32 *indir,
 		bp->rss_conf_obj.ind_table[i] = indir[i] + bp->fp->cl_id;
 	}
 
-	return bnx2x_config_rss_eth(bp, false);
+	if (bp->state == BNX2X_STATE_OPEN)
+		return bnx2x_config_rss_eth(bp, false);
+
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 5b1ed240bf18..57348f2b49a3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -10279,6 +10279,12 @@ static void bnx2x_sp_rtnl_task(struct work_struct *work)
 		bp->sp_rtnl_state = 0;
 		smp_mb();
 
+		/* Immediately indicate link as down */
+		bp->link_vars.link_up = 0;
+		bp->force_link_down = true;
+		netif_carrier_off(bp->dev);
+		BNX2X_ERR("Indicating link is down due to Tx-timeout\n");
+
 		bnx2x_nic_unload(bp, UNLOAD_NORMAL, true);
 		/* When ret value shows failure of allocation failure,
 		 * the nic is rebooted again. If open still fails, a error
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 176fc9f4d7de..4394c1162be4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5712,7 +5712,9 @@ static int bnxt_init_chip(struct bnxt *bp, bool irq_re_init)
 	}
 	vnic->uc_filter_count = 1;
 
-	vnic->rx_mask = CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
+	vnic->rx_mask = 0;
+	if (bp->dev->flags & IFF_BROADCAST)
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
 
 	if ((bp->dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
 		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
@@ -5917,7 +5919,7 @@ unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 	return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
 }
 
-void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
+static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 {
 	bp->hw_resc.max_irqs = max_irqs;
 }
@@ -6888,7 +6890,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		rc = bnxt_request_irq(bp);
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_request_irq err: %x\n", rc);
-			goto open_err;
+			goto open_err_irq;
 		}
 	}
 
@@ -6928,6 +6930,8 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 open_err:
 	bnxt_debug_dev_exit(bp);
 	bnxt_disable_napi(bp);
+
+open_err_irq:
 	bnxt_del_napi(bp);
 
 open_err_free_mem:
@@ -7214,13 +7218,16 @@ static void bnxt_set_rx_mode(struct net_device *dev)
 
 	mask &= ~(CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS |
 		  CFA_L2_SET_RX_MASK_REQ_MASK_MCAST |
-		  CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST);
+		  CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST |
+		  CFA_L2_SET_RX_MASK_REQ_MASK_BCAST);
 
 	if ((dev->flags & IFF_PROMISC) && bnxt_promisc_ok(bp))
 		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS;
 
 	uc_update = bnxt_uc_list_updated(bp);
 
+	if (dev->flags & IFF_BROADCAST)
+		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_BCAST;
 	if (dev->flags & IFF_ALLMULTI) {
 		mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
 		vnic->mc_list_count = 0;
@@ -8502,11 +8509,11 @@ int bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, bool shared)
 	int rx, tx, cp;
 
 	_bnxt_get_max_rings(bp, &rx, &tx, &cp);
+	*max_rx = rx;
+	*max_tx = tx;
 	if (!rx || !tx || !cp)
 		return -ENOMEM;
 
-	*max_rx = rx;
-	*max_tx = tx;
 	return bnxt_trim_rings(bp, max_rx, max_tx, cp, shared);
 }
 
@@ -8520,8 +8527,11 @@ static int bnxt_get_dflt_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 		/* Not enough rings, try disabling agg rings. */
 		bp->flags &= ~BNXT_FLAG_AGG_RINGS;
 		rc = bnxt_get_max_rings(bp, max_rx, max_tx, shared);
-		if (rc)
+		if (rc) {
+			/* set BNXT_FLAG_AGG_RINGS back for consistency */
+			bp->flags |= BNXT_FLAG_AGG_RINGS;
 			return rc;
+		}
 		bp->flags |= BNXT_FLAG_NO_AGG_RINGS;
 		bp->dev->hw_features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
 		bp->dev->features &= ~(NETIF_F_LRO | NETIF_F_GRO_HW);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 9b14eb610b9f..91575ef97c8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1470,7 +1470,6 @@ void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
 void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max);
 unsigned int bnxt_get_max_func_irqs(struct bnxt *bp);
-void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 795f45024c20..491bd40a254d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -27,6 +27,15 @@
 #define BNXT_FID_INVALID			0xffff
 #define VLAN_TCI(vid, prio)	((vid) | ((prio) << VLAN_PRIO_SHIFT))
 
+#define is_vlan_pcp_wildcarded(vlan_tci_mask)	\
+	((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == 0x0000)
+#define is_vlan_pcp_exactmatch(vlan_tci_mask)	\
+	((ntohs(vlan_tci_mask) & VLAN_PRIO_MASK) == VLAN_PRIO_MASK)
+#define is_vlan_pcp_zero(vlan_tci)	\
+	((ntohs(vlan_tci) & VLAN_PRIO_MASK) == 0x0000)
+#define is_vid_exactmatch(vlan_tci_mask)	\
+	((ntohs(vlan_tci_mask) & VLAN_VID_MASK) == VLAN_VID_MASK)
+
 /* Return the dst fid of the func for flow forwarding
  * For PFs: src_fid is the fid of the PF
  * For VF-reps: src_fid the fid of the VF
@@ -389,6 +398,21 @@ static bool is_exactmatch(void *mask, int len)
 	return true;
 }
 
+static bool is_vlan_tci_allowed(__be16  vlan_tci_mask,
+				__be16  vlan_tci)
+{
+	/* VLAN priority must be either exactly zero or fully wildcarded and
+	 * VLAN id must be exact match.
+	 */
+	if (is_vid_exactmatch(vlan_tci_mask) &&
+	    ((is_vlan_pcp_exactmatch(vlan_tci_mask) &&
+	      is_vlan_pcp_zero(vlan_tci)) ||
+	     is_vlan_pcp_wildcarded(vlan_tci_mask)))
+		return true;
+
+	return false;
+}
+
 static bool bits_set(void *key, int len)
 {
 	const u8 *p = key;
@@ -803,9 +827,9 @@ static bool bnxt_tc_can_offload(struct bnxt *bp, struct bnxt_tc_flow *flow)
 	/* Currently VLAN fields cannot be partial wildcard */
 	if (bits_set(&flow->l2_key.inner_vlan_tci,
 		     sizeof(flow->l2_key.inner_vlan_tci)) &&
-	    !is_exactmatch(&flow->l2_mask.inner_vlan_tci,
-			   sizeof(flow->l2_mask.inner_vlan_tci))) {
-		netdev_info(bp->dev, "Wildcard match unsupported for VLAN TCI\n");
+	    !is_vlan_tci_allowed(flow->l2_mask.inner_vlan_tci,
+				 flow->l2_key.inner_vlan_tci)) {
+		netdev_info(bp->dev, "Unsupported VLAN TCI\n");
 		return false;
 	}
 	if (bits_set(&flow->l2_key.inner_vlan_tpid,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 347e4f946eb2..840f6e505f73 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 		edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
 	}
 	bnxt_fill_msix_vecs(bp, ent);
-	bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) - avail_msix);
 	bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix);
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 	return avail_msix;
@@ -192,7 +191,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id)
 	msix_requested = edev->ulp_tbl[ulp_id].msix_requested;
 	bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested);
 	edev->ulp_tbl[ulp_id].msix_requested = 0;
-	bnxt_set_max_func_irqs(bp, bnxt_get_max_func_irqs(bp) + msix_requested);
 	edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
 	if (netif_running(dev)) {
 		bnxt_close_nic(bp, true, false);
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 30273a7717e2..4fd829b5e65d 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -660,7 +660,7 @@ static int cnic_init_id_tbl(struct cnic_id_tbl *id_tbl, u32 size, u32 start_id,
 	id_tbl->max = size;
 	id_tbl->next = next;
 	spin_lock_init(&id_tbl->lock);
-	id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+	id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
 	if (!id_tbl->table)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3be87efdc93d..aa1374d0af93 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -6,11 +6,15 @@
  * Copyright (C) 2004 Sun Microsystems Inc.
  * Copyright (C) 2005-2016 Broadcom Corporation.
  * Copyright (C) 2016-2017 Broadcom Limited.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
  *
  * Firmware is:
  *	Derived from proprietary unpublished source code,
  *	Copyright (C) 2000-2016 Broadcom Corporation.
  *	Copyright (C) 2016-2017 Broadcom Ltd.
+ *	Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ *	refers to Broadcom Inc. and/or its subsidiaries.
  *
  *	Permission is hereby granted for the distribution of this firmware
  *	data in hexadecimal or equivalent format, provided this copyright
@@ -9290,6 +9294,15 @@ static int tg3_chip_reset(struct tg3 *tp)
 
 	tg3_restore_clk(tp);
 
+	/* Increase the core clock speed to fix tx timeout issue for 5762
+	 * with 100Mbps link speed.
+	 */
+	if (tg3_asic_rev(tp) == ASIC_REV_5762) {
+		val = tr32(TG3_CPMU_CLCK_ORIDE_ENABLE);
+		tw32(TG3_CPMU_CLCK_ORIDE_ENABLE, val |
+		     TG3_CPMU_MAC_ORIDE_ENABLE);
+	}
+
 	/* Reprobe ASF enable state.  */
 	tg3_flag_clear(tp, ENABLE_ASF);
 	tp->phy_flags &= ~(TG3_PHYFLG_1G_ON_VAUX_OK |
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 1d61aa3efda1..a772a33b685c 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -7,6 +7,8 @@
  * Copyright (C) 2004 Sun Microsystems Inc.
  * Copyright (C) 2007-2016 Broadcom Corporation.
  * Copyright (C) 2016-2017 Broadcom Limited.
+ * Copyright (C) 2018 Broadcom. All Rights Reserved. The term "Broadcom"
+ * refers to Broadcom Inc. and/or its subsidiaries.
  */
 
 #ifndef _T3_H
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 86659823b259..3d45f4c92cf6 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -166,6 +166,7 @@
 #define GEM_DCFG6		0x0294 /* Design Config 6 */
 #define GEM_DCFG7		0x0298 /* Design Config 7 */
 #define GEM_DCFG8		0x029C /* Design Config 8 */
+#define GEM_DCFG10		0x02A4 /* Design Config 10 */
 
 #define GEM_TXBDCTRL	0x04cc /* TX Buffer Descriptor control register */
 #define GEM_RXBDCTRL	0x04d0 /* RX Buffer Descriptor control register */
@@ -490,6 +491,12 @@
 #define GEM_SCR2CMP_OFFSET			0
 #define GEM_SCR2CMP_SIZE			8
 
+/* Bitfields in DCFG10 */
+#define GEM_TXBD_RDBUFF_OFFSET			12
+#define GEM_TXBD_RDBUFF_SIZE			4
+#define GEM_RXBD_RDBUFF_OFFSET			8
+#define GEM_RXBD_RDBUFF_SIZE			4
+
 /* Bitfields in TISUBN */
 #define GEM_SUBNSINCR_OFFSET			0
 #define GEM_SUBNSINCR_SIZE			16
@@ -635,6 +642,7 @@
 #define MACB_CAPS_USRIO_DISABLED		0x00000010
 #define MACB_CAPS_JUMBO				0x00000020
 #define MACB_CAPS_GEM_HAS_PTP			0x00000040
+#define MACB_CAPS_BD_RD_PREFETCH		0x00000080
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000
@@ -1203,6 +1211,9 @@ struct macb {
 	unsigned int max_tuples;
 
 	struct tasklet_struct	hresp_err_tasklet;
+
+	int	rx_bd_rd_prefetch;
+	int	tx_bd_rd_prefetch;
 };
 
 #ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 3e93df5d4e3b..a6c911bb5ce2 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1811,23 +1811,25 @@ static void macb_free_consistent(struct macb *bp)
 {
 	struct macb_queue *queue;
 	unsigned int q;
+	int size;
 
-	queue = &bp->queues[0];
 	bp->macbgem_ops.mog_free_rx_buffers(bp);
-	if (queue->rx_ring) {
-		dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp),
-				queue->rx_ring, queue->rx_ring_dma);
-		queue->rx_ring = NULL;
-	}
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		kfree(queue->tx_skb);
 		queue->tx_skb = NULL;
 		if (queue->tx_ring) {
-			dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp),
+			size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
+			dma_free_coherent(&bp->pdev->dev, size,
 					  queue->tx_ring, queue->tx_ring_dma);
 			queue->tx_ring = NULL;
 		}
+		if (queue->rx_ring) {
+			size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
+			dma_free_coherent(&bp->pdev->dev, size,
+					  queue->rx_ring, queue->rx_ring_dma);
+			queue->rx_ring = NULL;
+		}
 	}
 }
 
@@ -1874,7 +1876,7 @@ static int macb_alloc_consistent(struct macb *bp)
 	int size;
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		size = TX_RING_BYTES(bp);
+		size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
 		queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
 						    &queue->tx_ring_dma,
 						    GFP_KERNEL);
@@ -1890,7 +1892,7 @@ static int macb_alloc_consistent(struct macb *bp)
 		if (!queue->tx_skb)
 			goto out_err;
 
-		size = RX_RING_BYTES(bp);
+		size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
 		queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
 						 &queue->rx_ring_dma, GFP_KERNEL);
 		if (!queue->rx_ring)
@@ -3726,6 +3728,8 @@ static int at91ether_init(struct platform_device *pdev)
 	int err;
 	u32 reg;
 
+	bp->queues[0].bp = bp;
+
 	dev->netdev_ops = &at91ether_netdev_ops;
 	dev->ethtool_ops = &macb_ethtool_ops;
 
@@ -3795,7 +3799,7 @@ static const struct macb_config np4_config = {
 static const struct macb_config zynqmp_config = {
 	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE |
 			MACB_CAPS_JUMBO |
-			MACB_CAPS_GEM_HAS_PTP,
+			MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_BD_RD_PREFETCH,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
@@ -3856,7 +3860,7 @@ static int macb_probe(struct platform_device *pdev)
 	void __iomem *mem;
 	const char *mac;
 	struct macb *bp;
-	int err;
+	int err, val;
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	mem = devm_ioremap_resource(&pdev->dev, regs);
@@ -3945,6 +3949,18 @@ static int macb_probe(struct platform_device *pdev)
 	else
 		dev->max_mtu = ETH_DATA_LEN;
 
+	if (bp->caps & MACB_CAPS_BD_RD_PREFETCH) {
+		val = GEM_BFEXT(RXBD_RDBUFF, gem_readl(bp, DCFG10));
+		if (val)
+			bp->rx_bd_rd_prefetch = (2 << (val - 1)) *
+						macb_dma_desc_get_size(bp);
+
+		val = GEM_BFEXT(TXBD_RDBUFF, gem_readl(bp, DCFG10));
+		if (val)
+			bp->tx_bd_rd_prefetch = (2 << (val - 1)) *
+						macb_dma_desc_get_size(bp);
+	}
+
 	mac = of_get_mac_address(np);
 	if (mac) {
 		ether_addr_copy(bp->dev->dev_addr, mac);
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 043e3c11c42b..92d88c5f76fb 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -15,7 +15,7 @@ if NET_VENDOR_CAVIUM
 
 config THUNDER_NIC_PF
 	tristate "Thunder Physical function driver"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select THUNDER_NIC_BGX
 	---help---
 	  This driver supports Thunder's NIC physical function.
@@ -28,13 +28,13 @@ config THUNDER_NIC_PF
 config THUNDER_NIC_VF
 	tristate "Thunder Virtual function driver"
 	imply CAVIUM_PTP
-	depends on 64BIT
+	depends on 64BIT && PCI
 	---help---
 	  This driver supports Thunder's NIC virtual function
 
 config	THUNDER_NIC_BGX
 	tristate "Thunder MAC interface driver (BGX)"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select PHYLIB
 	select MDIO_THUNDER
 	select THUNDER_NIC_RGX
@@ -44,7 +44,7 @@ config	THUNDER_NIC_BGX
 
 config	THUNDER_NIC_RGX
 	tristate "Thunder MAC interface driver (RGX)"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select PHYLIB
 	select MDIO_THUNDER
 	---help---
@@ -53,7 +53,7 @@ config	THUNDER_NIC_RGX
 
 config CAVIUM_PTP
 	tristate "Cavium PTP coprocessor as PTP clock"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	imply PTP_1588_CLOCK
 	default y
 	---help---
@@ -65,7 +65,7 @@ config CAVIUM_PTP
 
 config LIQUIDIO
 	tristate "Cavium LiquidIO support"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	depends on MAY_USE_DEVLINK
 	imply PTP_1588_CLOCK
 	select FW_LOADER
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8a815bb57177..7e8454d3b1ad 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -91,6 +91,9 @@ static int octeon_console_debug_enabled(u32 console)
  */
 #define LIO_SYNC_OCTEON_TIME_INTERVAL_MS 60000
 
+/* time to wait for possible in-flight requests in milliseconds */
+#define WAIT_INFLIGHT_REQUEST	msecs_to_jiffies(1000)
+
 struct lio_trusted_vf_ctx {
 	struct completion complete;
 	int status;
@@ -259,7 +262,7 @@ static inline void pcierror_quiesce_device(struct octeon_device *oct)
 	force_io_queues_off(oct);
 
 	/* To allow for in-flight requests */
-	schedule_timeout_uninterruptible(100);
+	schedule_timeout_uninterruptible(WAIT_INFLIGHT_REQUEST);
 
 	if (wait_for_pending_requests(oct))
 		dev_err(&oct->pci_dev->dev, "There were pending requests\n");
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 3f6afb54a5eb..bb43ddb7539e 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -643,13 +643,21 @@ static int octeon_mgmt_set_mac_address(struct net_device *netdev, void *addr)
 static int octeon_mgmt_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct octeon_mgmt *p = netdev_priv(netdev);
-	int size_without_fcs = new_mtu + OCTEON_MGMT_RX_HEADROOM;
+	int max_packet = new_mtu + ETH_HLEN + ETH_FCS_LEN;
 
 	netdev->mtu = new_mtu;
 
-	cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, size_without_fcs);
+	/* HW lifts the limit if the frame is VLAN tagged
+	 * (+4 bytes per each tag, up to two tags)
+	 */
+	cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_MAX, max_packet);
+	/* Set the hardware to truncate packets larger than the MTU. The jabber
+	 * register must be set to a multiple of 8 bytes, so round up. JABBER is
+	 * an unconditional limit, so we need to account for two possible VLAN
+	 * tags.
+	 */
 	cvmx_write_csr(p->agl + AGL_GMX_RX_JABBER,
-		       (size_without_fcs + 7) & 0xfff8);
+		       (max_packet + 7 + VLAN_HLEN * 2) & 0xfff8);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 7b795edd9d3a..a19172dbe6be 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -51,6 +51,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/nospec.h>
 
 #include "common.h"
 #include "cxgb3_ioctl.h"
@@ -2268,6 +2269,7 @@ static int cxgb_extension_ioctl(struct net_device *dev, void __user *useraddr)
 
 		if (t.qset_idx >= nqsets)
 			return -EINVAL;
+		t.qset_idx = array_index_nospec(t.qset_idx, nqsets);
 
 		q = &adapter->params.sge.qset[q1 + t.qset_idx];
 		t.rspq_size = q->rspq_size;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 974a868a4824..3720c3e11ebb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -8702,7 +8702,7 @@ static int t4_get_flash_params(struct adapter *adap)
 	};
 
 	unsigned int part, manufacturer;
-	unsigned int density, size;
+	unsigned int density, size = 0;
 	u32 flashid = 0;
 	int ret;
 
@@ -8772,11 +8772,6 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x22: /* 256MB */
 			size = 1 << 28;
 			break;
-
-		default:
-			dev_err(adap->pdev_dev, "Micron Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
@@ -8792,10 +8787,6 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x17: /* 64MB */
 			size = 1 << 26;
 			break;
-		default:
-			dev_err(adap->pdev_dev, "ISSI Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
@@ -8811,10 +8802,6 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x18: /* 16MB */
 			size = 1 << 24;
 			break;
-		default:
-			dev_err(adap->pdev_dev, "Macronix Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
@@ -8830,17 +8817,21 @@ static int t4_get_flash_params(struct adapter *adap)
 		case 0x18: /* 16MB */
 			size = 1 << 24;
 			break;
-		default:
-			dev_err(adap->pdev_dev, "Winbond Flash Part has bad size, ID = %#x, Density code = %#x\n",
-				flashid, density);
-			return -EINVAL;
 		}
 		break;
 	}
-	default:
-		dev_err(adap->pdev_dev, "Unsupported Flash Part, ID = %#x\n",
-			flashid);
-		return -EINVAL;
+	}
+
+	/* If we didn't recognize the FLASH part, that's no real issue: the
+	 * Hardware/Software contract says that Hardware will _*ALWAYS*_
+	 * use a FLASH part which is at least 4MB in size and has 64KB
+	 * sectors.  The unrecognized FLASH part is likely to be much larger
+	 * than 4MB, but that's all we really need.
+	 */
+	if (size == 0) {
+		dev_warn(adap->pdev_dev, "Unknown Flash Part, ID = %#x, assuming 4MB\n",
+			 flashid);
+		size = 1 << 22;
 	}
 
 	/* Store decoded Flash size and fall through into vetting code. */
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 5ab912937aff..ec0b545197e2 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -19,6 +19,7 @@ if NET_VENDOR_CIRRUS
 config CS89x0
 	tristate "CS89x0 support"
 	depends on ISA || EISA || ARM
+	depends on !PPC32
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 5f4e1ffa7b95..ab02057ac730 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -125,6 +125,9 @@ MODULE_PARM_DESC(tx_timeout, "The Tx timeout in ms");
 /* Default alignment for start of data in an Rx FD */
 #define DPAA_FD_DATA_ALIGNMENT  16
 
+/* The DPAA requires 256 bytes reserved and mapped for the SGT */
+#define DPAA_SGT_SIZE 256
+
 /* Values for the L3R field of the FM Parse Results
  */
 /* L3 Type field: First IP Present IPv4 */
@@ -1617,8 +1620,8 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 
 	if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
 		nr_frags = skb_shinfo(skb)->nr_frags;
-		dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
-				 sizeof(struct qm_sg_entry) * (1 + nr_frags),
+		dma_unmap_single(dev, addr,
+				 qm_fd_get_offset(fd) + DPAA_SGT_SIZE,
 				 dma_dir);
 
 		/* The sgt buffer has been allocated with netdev_alloc_frag(),
@@ -1903,8 +1906,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 	void *sgt_buf;
 
 	/* get a page frag to store the SGTable */
-	sz = SKB_DATA_ALIGN(priv->tx_headroom +
-		sizeof(struct qm_sg_entry) * (1 + nr_frags));
+	sz = SKB_DATA_ALIGN(priv->tx_headroom + DPAA_SGT_SIZE);
 	sgt_buf = netdev_alloc_frag(sz);
 	if (unlikely(!sgt_buf)) {
 		netdev_err(net_dev, "netdev_alloc_frag() failed for size %d\n",
@@ -1972,9 +1974,8 @@ static int skb_to_sg_fd(struct dpaa_priv *priv,
 	skbh = (struct sk_buff **)buffer_start;
 	*skbh = skb;
 
-	addr = dma_map_single(dev, buffer_start, priv->tx_headroom +
-			      sizeof(struct qm_sg_entry) * (1 + nr_frags),
-			      dma_dir);
+	addr = dma_map_single(dev, buffer_start,
+			      priv->tx_headroom + DPAA_SGT_SIZE, dma_dir);
 	if (unlikely(dma_mapping_error(dev, addr))) {
 		dev_err(dev, "DMA mapping failed");
 		err = -EINVAL;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index ce6e24c74978..ecbf6187e13a 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -324,6 +324,10 @@ struct fman_port_qmi_regs {
 #define HWP_HXS_PHE_REPORT 0x00000800
 #define HWP_HXS_PCAC_PSTAT 0x00000100
 #define HWP_HXS_PCAC_PSTOP 0x00000001
+#define HWP_HXS_TCP_OFFSET 0xA
+#define HWP_HXS_UDP_OFFSET 0xB
+#define HWP_HXS_SH_PAD_REM 0x80000000
+
 struct fman_port_hwp_regs {
 	struct {
 		u32 ssa; /* Soft Sequence Attachment */
@@ -728,6 +732,10 @@ static void init_hwp(struct fman_port *port)
 		iowrite32be(0xffffffff, &regs->pmda[i].lcv);
 	}
 
+	/* Short packet padding removal from checksum calculation */
+	iowrite32be(HWP_HXS_SH_PAD_REM, &regs->pmda[HWP_HXS_TCP_OFFSET].ssa);
+	iowrite32be(HWP_HXS_SH_PAD_REM, &regs->pmda[HWP_HXS_UDP_OFFSET].ssa);
+
 	start_port_hwp(port);
 }
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index e2e5cdc7119c..4c0f7eda1166 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -439,6 +439,7 @@ static void rx_free_irq(struct hinic_rxq *rxq)
 {
 	struct hinic_rq *rq = rxq->rq;
 
+	irq_set_affinity_hint(rq->irq, NULL);
 	free_irq(rq->irq, rxq);
 	rx_del_napi(rxq);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 9128858479c4..2353ec829c04 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -229,6 +229,7 @@ netdev_tx_t hinic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 		txq->txq_stats.tx_busy++;
 		u64_stats_update_end(&txq->txq_stats.syncp);
 		err = NETDEV_TX_BUSY;
+		wqe_size = 0;
 		goto flush_skbs;
 	}
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index d0e196bff081..ffe7acbeaa22 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -329,7 +329,8 @@ static void replenish_rx_pool(struct ibmvnic_adapter *adapter,
 	return;
 
 failure:
-	dev_info(dev, "replenish pools failure\n");
+	if (lpar_rc != H_PARAMETER && lpar_rc != H_CLOSED)
+		dev_err_ratelimited(dev, "rx: replenish packet buffer failed\n");
 	pool->free_map[pool->next_free] = index;
 	pool->rx_buff[index].skb = NULL;
 
@@ -1617,7 +1618,8 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev)
 				      &tx_crq);
 	}
 	if (lpar_rc != H_SUCCESS) {
-		dev_err(dev, "tx failed with code %ld\n", lpar_rc);
+		if (lpar_rc != H_CLOSED && lpar_rc != H_PARAMETER)
+			dev_err_ratelimited(dev, "tx: send failed\n");
 		dev_kfree_skb_any(skb);
 		tx_buff->skb = NULL;
 
@@ -1825,8 +1827,8 @@ static int do_reset(struct ibmvnic_adapter *adapter,
 
 		rc = ibmvnic_login(netdev);
 		if (rc) {
-			adapter->state = VNIC_PROBED;
-			return 0;
+			adapter->state = reset_state;
+			return rc;
 		}
 
 		if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
@@ -3204,6 +3206,25 @@ static union ibmvnic_crq *ibmvnic_next_crq(struct ibmvnic_adapter *adapter)
 	return crq;
 }
 
+static void print_subcrq_error(struct device *dev, int rc, const char *func)
+{
+	switch (rc) {
+	case H_PARAMETER:
+		dev_warn_ratelimited(dev,
+				     "%s failed: Send request is malformed or adapter failover pending. (rc=%d)\n",
+				     func, rc);
+		break;
+	case H_CLOSED:
+		dev_warn_ratelimited(dev,
+				     "%s failed: Backing queue closed. Adapter is down or failover pending. (rc=%d)\n",
+				     func, rc);
+		break;
+	default:
+		dev_err_ratelimited(dev, "%s failed: (rc=%d)\n", func, rc);
+		break;
+	}
+}
+
 static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
 		       union sub_crq *sub_crq)
 {
@@ -3230,11 +3251,8 @@ static int send_subcrq(struct ibmvnic_adapter *adapter, u64 remote_handle,
 				cpu_to_be64(u64_crq[2]),
 				cpu_to_be64(u64_crq[3]));
 
-	if (rc) {
-		if (rc == H_CLOSED)
-			dev_warn(dev, "CRQ Queue closed\n");
-		dev_err(dev, "Send error (rc=%d)\n", rc);
-	}
+	if (rc)
+		print_subcrq_error(dev, rc, __func__);
 
 	return rc;
 }
@@ -3252,11 +3270,8 @@ static int send_subcrq_indirect(struct ibmvnic_adapter *adapter,
 				cpu_to_be64(remote_handle),
 				ioba, num_entries);
 
-	if (rc) {
-		if (rc == H_CLOSED)
-			dev_warn(dev, "CRQ Queue closed\n");
-		dev_err(dev, "Send (indirect) error (rc=%d)\n", rc);
-	}
+	if (rc)
+		print_subcrq_error(dev, rc, __func__);
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index ed6dbcfd4e96..b151ae316546 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2199,9 +2199,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring,
 	return true;
 }
 
-#define I40E_XDP_PASS 0
-#define I40E_XDP_CONSUMED 1
-#define I40E_XDP_TX 2
+#define I40E_XDP_PASS		0
+#define I40E_XDP_CONSUMED	BIT(0)
+#define I40E_XDP_TX		BIT(1)
+#define I40E_XDP_REDIR		BIT(2)
 
 static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 			      struct i40e_ring *xdp_ring);
@@ -2248,7 +2249,7 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 		break;
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
-		result = !err ? I40E_XDP_TX : I40E_XDP_CONSUMED;
+		result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED;
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
@@ -2311,7 +2312,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = I40E_DESC_UNUSED(rx_ring);
-	bool failure = false, xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
+	bool failure = false;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
@@ -2372,8 +2374,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -I40E_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				i40e_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2427,12 +2431,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget)
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & I40E_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & I40E_XDP_TX) {
 		struct i40e_ring *xdp_ring =
 			rx_ring->vsi->xdp_rings[rx_ring->queue_index];
 
 		i40e_xdp_ring_update_tail(xdp_ring);
-		xdp_do_flush_map();
 	}
 
 	rx_ring->skb = skb;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
index 3f5c350716bb..0bd1294ba517 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c
@@ -1871,7 +1871,12 @@ s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq,
 	if (enable_addr != 0)
 		rar_high |= IXGBE_RAH_AV;
 
+	/* Record lower 32 bits of MAC address and then make
+	 * sure that write is flushed to hardware before writing
+	 * the upper 16 bits and setting the valid bit.
+	 */
 	IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low);
+	IXGBE_WRITE_FLUSH(hw);
 	IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high);
 
 	return 0;
@@ -1903,8 +1908,13 @@ s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index)
 	rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index));
 	rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV);
 
-	IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0);
+	/* Clear the address valid bit and upper 16 bits of the address
+	 * before clearing the lower bits. This way we aren't updating
+	 * a live filter.
+	 */
 	IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high);
+	IXGBE_WRITE_FLUSH(hw);
+	IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0);
 
 	/* clear VMDq pool/queue selection for this RAR */
 	hw->mac.ops.clear_vmdq(hw, index, IXGBE_CLEAR_VMDQ_ALL);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index c116f459945d..da4322e4daed 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -839,7 +839,7 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 	}
 
 	itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX;
-	if (unlikely(itd->sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) {
+	if (unlikely(itd->sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) {
 		netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n",
 			   __func__, itd->sa_idx, xs->xso.offload_handle);
 		return 0;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 3e87dbbc9024..62e57b05a0ae 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -2186,9 +2186,10 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring,
 	return skb;
 }
 
-#define IXGBE_XDP_PASS 0
-#define IXGBE_XDP_CONSUMED 1
-#define IXGBE_XDP_TX 2
+#define IXGBE_XDP_PASS		0
+#define IXGBE_XDP_CONSUMED	BIT(0)
+#define IXGBE_XDP_TX		BIT(1)
+#define IXGBE_XDP_REDIR		BIT(2)
 
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_frame *xdpf);
@@ -2225,7 +2226,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter,
 	case XDP_REDIRECT:
 		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);
 		if (!err)
-			result = IXGBE_XDP_TX;
+			result = IXGBE_XDP_REDIR;
 		else
 			result = IXGBE_XDP_CONSUMED;
 		break;
@@ -2285,7 +2286,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 	unsigned int mss = 0;
 #endif /* IXGBE_FCOE */
 	u16 cleaned_count = ixgbe_desc_unused(rx_ring);
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 	struct xdp_buff xdp;
 
 	xdp.rxq = &rx_ring->xdp_rxq;
@@ -2328,8 +2329,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		}
 
 		if (IS_ERR(skb)) {
-			if (PTR_ERR(skb) == -IXGBE_XDP_TX) {
-				xdp_xmit = true;
+			unsigned int xdp_res = -PTR_ERR(skb);
+
+			if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) {
+				xdp_xmit |= xdp_res;
 				ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size);
 			} else {
 				rx_buffer->pagecnt_bias++;
@@ -2401,7 +2404,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		total_rx_packets++;
 	}
 
-	if (xdp_xmit) {
+	if (xdp_xmit & IXGBE_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & IXGBE_XDP_TX) {
 		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
 
 		/* Force memory writes to complete before letting h/w
@@ -2409,8 +2415,6 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
 		 */
 		wmb();
 		writel(ring->next_to_use, ring->tail);
-
-		xdp_do_flush_map();
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 9f54ccbddea7..3360f7b9ee73 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -474,10 +474,10 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 {
 	const struct mlx4_en_frag_info *frag_info = priv->frag_info;
 	unsigned int truesize = 0;
+	bool release = true;
 	int nr, frag_size;
 	struct page *page;
 	dma_addr_t dma;
-	bool release;
 
 	/* Collect used fragments while replacing them in the HW descriptors */
 	for (nr = 0;; frags++) {
@@ -500,7 +500,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = page_count(page) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
-		} else {
+		} else if (!priv->rx_headroom) {
+			/* rx_headroom for non XDP setup is always 0.
+			 * When XDP is set, the above condition will
+			 * guarantee page is always released.
+			 */
 			u32 sz_align = ALIGN(frag_size, SMP_CACHE_BYTES);
 
 			frags->page_offset += sz_align;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 7b1b5ac986d0..31bd56727022 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2958,7 +2958,7 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	u32 srqn = qp_get_srqn(qpc) & 0xffffff;
 	int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
 	struct res_srq *srq;
-	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+	int local_qpn = vhcr->in_modifier & 0xffffff;
 
 	err = adjust_qp_sched_queue(dev, slave, qpc, inbox);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 323ffe8bf7e4..456f30007ad6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -123,7 +123,7 @@ int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 	int i;
 
 	buf->size = size;
-	buf->npages = 1 << get_order(size);
+	buf->npages = DIV_ROUND_UP(size, PAGE_SIZE);
 	buf->page_shift = PAGE_SHIFT;
 	buf->frags = kcalloc(buf->npages, sizeof(struct mlx5_buf_list),
 			     GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 487388aed98f..384c1fa49081 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -807,6 +807,7 @@ static void cmd_work_handler(struct work_struct *work)
 	unsigned long flags;
 	bool poll_cmd = ent->polling;
 	int alloc_ret;
+	int cmd_mode;
 
 	sem = ent->page_queue ? &cmd->pages_sem : &cmd->sem;
 	down(sem);
@@ -853,6 +854,7 @@ static void cmd_work_handler(struct work_struct *work)
 	set_signature(ent, !cmd->checksum_disabled);
 	dump_command(dev, ent, 1);
 	ent->ts1 = ktime_get_ns();
+	cmd_mode = cmd->mode;
 
 	if (ent->callback)
 		schedule_delayed_work(&ent->cb_timeout_work, cb_timeout);
@@ -877,7 +879,7 @@ static void cmd_work_handler(struct work_struct *work)
 	iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell);
 	mmiowb();
 	/* if not in polling don't use ent after this point */
-	if (cmd->mode == CMD_MODE_POLLING || poll_cmd) {
+	if (cmd_mode == CMD_MODE_POLLING || poll_cmd) {
 		poll_timeout(ent);
 		/* make sure we read the descriptor after ownership is SW */
 		rmb();
@@ -1276,7 +1278,7 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 {
 	struct mlx5_core_dev *dev = filp->private_data;
 	struct mlx5_cmd_debug *dbg = &dev->cmd.dbg;
-	char outlen_str[8];
+	char outlen_str[8] = {0};
 	int outlen;
 	void *ptr;
 	int err;
@@ -1291,8 +1293,6 @@ static ssize_t outlen_write(struct file *filp, const char __user *buf,
 	if (copy_from_user(outlen_str, buf, count))
 		return -EFAULT;
 
-	outlen_str[7] = 0;
-
 	err = sscanf(outlen_str, "%d", &outlen);
 	if (err < 0)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index 75e4308ba786..d258bb679271 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -381,14 +381,14 @@ static void arfs_may_expire_flow(struct mlx5e_priv *priv)
 	HLIST_HEAD(del_list);
 	spin_lock_bh(&priv->fs.arfs.arfs_lock);
 	mlx5e_for_each_arfs_rule(arfs_rule, htmp, priv->fs.arfs.arfs_tables, i, j) {
-		if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
-			break;
 		if (!work_pending(&arfs_rule->arfs_work) &&
 		    rps_may_expire_flow(priv->netdev,
 					arfs_rule->rxq, arfs_rule->flow_id,
 					arfs_rule->filter_id)) {
 			hlist_del_init(&arfs_rule->hlist);
 			hlist_add_head(&arfs_rule->hlist, &del_list);
+			if (quota++ > MLX5E_ARFS_EXPIRY_QUOTA)
+				break;
 		}
 	}
 	spin_unlock_bh(&priv->fs.arfs.arfs_lock);
@@ -711,6 +711,9 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	    skb->protocol != htons(ETH_P_IPV6))
 		return -EPROTONOSUPPORT;
 
+	if (skb->encapsulation)
+		return -EPROTONOSUPPORT;
+
 	arfs_t = arfs_get_table(arfs, arfs_get_ip_proto(skb), skb->protocol);
 	if (!arfs_t)
 		return -EPROTONOSUPPORT;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 0a52f31fef37..86bc9ac99586 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -275,7 +275,8 @@ int mlx5e_dcbnl_ieee_setets_core(struct mlx5e_priv *priv, struct ieee_ets *ets)
 }
 
 static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
-				    struct ieee_ets *ets)
+				    struct ieee_ets *ets,
+				    bool zero_sum_allowed)
 {
 	bool have_ets_tc = false;
 	int bw_sum = 0;
@@ -300,8 +301,9 @@ static int mlx5e_dbcnl_validate_ets(struct net_device *netdev,
 	}
 
 	if (have_ets_tc && bw_sum != 100) {
-		netdev_err(netdev,
-			   "Failed to validate ETS: BW sum is illegal\n");
+		if (bw_sum || (!bw_sum && !zero_sum_allowed))
+			netdev_err(netdev,
+				   "Failed to validate ETS: BW sum is illegal\n");
 		return -EINVAL;
 	}
 	return 0;
@@ -316,7 +318,7 @@ static int mlx5e_dcbnl_ieee_setets(struct net_device *netdev,
 	if (!MLX5_CAP_GEN(priv->mdev, ets))
 		return -EOPNOTSUPP;
 
-	err = mlx5e_dbcnl_validate_ets(netdev, ets);
+	err = mlx5e_dbcnl_validate_ets(netdev, ets, false);
 	if (err)
 		return err;
 
@@ -642,12 +644,9 @@ static u8 mlx5e_dcbnl_setall(struct net_device *netdev)
 			  ets.prio_tc[i]);
 	}
 
-	err = mlx5e_dbcnl_validate_ets(netdev, &ets);
-	if (err) {
-		netdev_err(netdev,
-			   "%s, Failed to validate ETS: %d\n", __func__, err);
+	err = mlx5e_dbcnl_validate_ets(netdev, &ets, true);
+	if (err)
 		goto out;
-	}
 
 	err = mlx5e_dcbnl_ieee_setets_core(priv, &ets);
 	if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 56c1b6f5593e..dae4156a710d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2846,7 +2846,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 	mlx5e_activate_channels(&priv->channels);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
@@ -2857,7 +2857,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -4597,7 +4597,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	mlx5e_set_netdev_dev_addr(netdev);
 
 #if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_VPORT_MANAGER(mdev))
+	if (MLX5_ESWITCH_MANAGER(mdev))
 		netdev->switchdev_ops = &mlx5e_switchdev_ops;
 #endif
 
@@ -4753,7 +4753,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 
 	mlx5e_enable_async_events(priv);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_register_vport_reps(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
@@ -4788,7 +4788,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_VPORT_MANAGER(priv->mdev))
+	if (MLX5_ESWITCH_MANAGER(priv->mdev))
 		mlx5e_unregister_vport_reps(priv);
 
 	mlx5e_disable_async_events(priv);
@@ -4972,7 +4972,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		return NULL;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_VPORT_MANAGER(mdev)) {
+	if (MLX5_ESWITCH_MANAGER(mdev)) {
 		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
 		if (!rpriv) {
 			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 57987f6546e8..2b8040a3cdbd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -823,7 +823,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
-	if (!MLX5_CAP_GEN(priv->mdev, vport_group_manager))
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
 	rep = rpriv->rep;
@@ -837,8 +837,12 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
 {
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct mlx5_eswitch_rep *rep;
 
+	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
+		return false;
+
+	rep = rpriv->rep;
 	if (rep && rep->vport != FDB_UPLINK_VPORT)
 		return true;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0edf4751a8ba..3a2c4e548226 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1957,6 +1957,10 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	else
 		actions = flow->nic_attr->action;
 
+	if (flow->flags & MLX5E_TC_FLOW_EGRESS &&
+	    !(actions & MLX5_FLOW_CONTEXT_ACTION_DECAP))
+		return false;
+
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec, exts);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index f63dfbcd29fe..dd01ad4c0b54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1594,17 +1594,15 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 }
 
 /* Public E-Switch API */
-#define ESW_ALLOWED(esw) ((esw) && MLX5_VPORT_MANAGER((esw)->dev))
+#define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
+
 
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
 	int err;
 	int i, enabled_events;
 
-	if (!ESW_ALLOWED(esw))
-		return 0;
-
-	if (!MLX5_CAP_GEN(esw->dev, eswitch_flow_table) ||
+	if (!ESW_ALLOWED(esw) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
 		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
 		return -EOPNOTSUPP;
@@ -1806,7 +1804,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	u64 node_guid;
 	int err = 0;
 
-	if (!ESW_ALLOWED(esw))
+	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
 		return -EINVAL;
@@ -1883,7 +1881,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 {
 	struct mlx5_vport *evport;
 
-	if (!ESW_ALLOWED(esw))
+	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport))
 		return -EINVAL;
@@ -2218,6 +2216,6 @@ free_out:
 
 u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return esw->mode;
+	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index cecd201f0b73..91f1209886ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -1079,8 +1079,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
 		return -EOPNOTSUPP;
 
-	if (!MLX5_CAP_GEN(dev, vport_group_manager))
-		return -EOPNOTSUPP;
+	if(!MLX5_ESWITCH_MANAGER(dev))
+		return -EPERM;
 
 	if (dev->priv.eswitch->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 49a75d31185e..6ddb2565884d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -32,6 +32,7 @@
 
 #include <linux/mutex.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eswitch.h>
 
 #include "mlx5_core.h"
 #include "fs_core.h"
@@ -1886,7 +1887,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!fwd_next_prio_supported(ft))
 			return ERR_PTR(-EOPNOTSUPP);
-		if (dest)
+		if (dest_num)
 			return ERR_PTR(-EINVAL);
 		mutex_lock(&root->chain_lock);
 		next_ft = find_next_chained_ft(prio);
@@ -2652,7 +2653,7 @@ int mlx5_init_fs(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ft_support)) {
 			err = init_fdb_root_ns(steering);
 			if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index afd9f4fa22f4..41ad24f0de2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -32,6 +32,7 @@
 
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
+#include <linux/mlx5/eswitch.h>
 #include <linux/module.h>
 #include "mlx5_core.h"
 #include "../../mlxfw/mlxfw.h"
@@ -159,13 +160,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_CAP_GEN(dev, vport_group_manager) &&
-	    MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	    MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH_FLOW_TABLE);
 		if (err)
 			return err;
 	}
 
-	if (MLX5_CAP_GEN(dev, eswitch_flow_table)) {
+	if (MLX5_ESWITCH_MANAGER(dev)) {
 		err = mlx5_core_get_caps(dev, MLX5_CAP_ESWITCH);
 		if (err)
 			return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 1e062e6b2587..3f767cde4c1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -488,6 +488,7 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 void mlx5_init_clock(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
+	u64 overflow_cycles;
 	u64 ns;
 	u64 frac = 0;
 	u32 dev_freq;
@@ -511,10 +512,17 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
 	 * sure counter is checked at least once every wrap around.
+	 * The period is calculated as the minimum between max HW cycles count
+	 * (The clock source mask) and max amount of cycles that can be
+	 * multiplied by clock multiplier where the result doesn't exceed
+	 * 64bits.
 	 */
-	ns = cyclecounter_cyc2ns(&clock->cycles, clock->cycles.mask,
+	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
+	overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+
+	ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
 				 frac, &frac);
-	do_div(ns, NSEC_PER_SEC / 2 / HZ);
+	do_div(ns, NSEC_PER_SEC / HZ);
 	clock->overflow_period = ns;
 
 	mdev->clock_info_page = alloc_page(GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 7cb67122e8b5..98359559c77e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -33,6 +33,7 @@
 #include <linux/etherdevice.h>
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/mlx5_ifc.h>
+#include <linux/mlx5/eswitch.h>
 #include "mlx5_core.h"
 #include "lib/mpfs.h"
 
@@ -98,7 +99,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 	int l2table_size = 1 << MLX5_CAP_GEN(dev, log_max_l2_table);
 	struct mlx5_mpfs *mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mpfs = kzalloc(sizeof(*mpfs), GFP_KERNEL);
@@ -122,7 +123,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
 {
 	struct mlx5_mpfs *mpfs = dev->priv.mpfs;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return;
 
 	WARN_ON(!hlist_empty(mpfs->hash));
@@ -137,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac)
 	u32 index;
 	int err;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
@@ -179,7 +180,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac)
 	int err = 0;
 	u32 index;
 
-	if (!MLX5_VPORT_MANAGER(dev))
+	if (!MLX5_ESWITCH_MANAGER(dev))
 		return 0;
 
 	mutex_lock(&mpfs->lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index fa9d0760dd36..31a9cbd85689 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -701,7 +701,7 @@ EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
 {
-	u32 out[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 out[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
@@ -713,7 +713,7 @@ static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 static int mlx5_query_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *out,
 				     int outlen)
 {
-	u32 in[MLX5_ST_SZ_DW(qtct_reg)];
+	u32 in[MLX5_ST_SZ_DW(qetc_reg)];
 
 	if (!MLX5_CAP_GEN(mdev, ets))
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 2a8b529ce6dd..a0674962f02c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -88,6 +88,9 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return -EBUSY;
 	}
 
+	if (!MLX5_ESWITCH_MANAGER(dev))
+		goto enable_vfs_hca;
+
 	err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
 	if (err) {
 		mlx5_core_warn(dev,
@@ -95,6 +98,7 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 		return err;
 	}
 
+enable_vfs_hca:
 	for (vf = 0; vf < num_vfs; vf++) {
 		err = mlx5_core_enable_hca(dev, vf + 1);
 		if (err) {
@@ -140,7 +144,8 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 	}
 
 out:
-	mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+	if (MLX5_ESWITCH_MANAGER(dev))
+		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
 
 	if (mlx5_wait_for_vf_pages(dev))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 719cecb182c6..7eecd5b07bb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -549,8 +549,6 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 		return -EINVAL;
 	if (!MLX5_CAP_GEN(mdev, vport_group_manager))
 		return -EACCES;
-	if (!MLX5_CAP_ESW(mdev, nic_vport_node_guid_modify))
-		return -EOPNOTSUPP;
 
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index b97bb72b4db4..86478a6b99c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -113,35 +113,45 @@ err_db_free:
 	return err;
 }
 
-static void mlx5e_qp_set_frag_buf(struct mlx5_frag_buf *buf,
-				  struct mlx5_wq_qp *qp)
+static void mlx5_qp_set_frag_buf(struct mlx5_frag_buf *buf,
+				 struct mlx5_wq_qp *qp)
 {
+	struct mlx5_frag_buf_ctrl *sq_fbc;
 	struct mlx5_frag_buf *rqb, *sqb;
 
-	rqb = &qp->rq.fbc.frag_buf;
+	rqb  = &qp->rq.fbc.frag_buf;
 	*rqb = *buf;
 	rqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
-	rqb->npages = 1 << get_order(rqb->size);
+	rqb->npages = DIV_ROUND_UP(rqb->size, PAGE_SIZE);
 
-	sqb = &qp->sq.fbc.frag_buf;
-	*sqb = *buf;
-	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->rq);
-	sqb->npages = 1 << get_order(sqb->size);
+	sq_fbc = &qp->sq.fbc;
+	sqb    = &sq_fbc->frag_buf;
+	*sqb   = *buf;
+	sqb->size   = mlx5_wq_cyc_get_byte_size(&qp->sq);
+	sqb->npages = DIV_ROUND_UP(sqb->size, PAGE_SIZE);
 	sqb->frags += rqb->npages; /* first part is for the rq */
+	if (sq_fbc->strides_offset)
+		sqb->frags--;
 }
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
 {
+	u32 sq_strides_offset;
 	int err;
 
 	mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4,
 		      MLX5_GET(qpc, qpc, log_rq_size),
 		      &wq->rq.fbc);
-	mlx5_fill_fbc(ilog2(MLX5_SEND_WQE_BB),
-		      MLX5_GET(qpc, qpc, log_sq_size),
-		      &wq->sq.fbc);
+
+	sq_strides_offset =
+		((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB;
+
+	mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB),
+			     MLX5_GET(qpc, qpc, log_sq_size),
+			     sq_strides_offset,
+			     &wq->sq.fbc);
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {
@@ -156,7 +166,7 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		goto err_db_free;
 	}
 
-	mlx5e_qp_set_frag_buf(&wq_ctrl->buf, wq);
+	mlx5_qp_set_frag_buf(&wq_ctrl->buf, wq);
 
 	wq->rq.db  = &wq_ctrl->db.db[MLX5_RCV_DBR];
 	wq->sq.db  = &wq_ctrl->db.db[MLX5_SND_DBR];
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 6aaaf3d9ba31..77b2adb29341 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -4756,6 +4756,12 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
 	kfree(mlxsw_sp_rt6);
 }
 
+static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
+{
+	/* RTF_CACHE routes are ignored */
+	return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
+}
+
 static struct fib6_info *
 mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
 {
@@ -4765,11 +4771,11 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
 
 static struct mlxsw_sp_fib6_entry *
 mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
-				 const struct fib6_info *nrt, bool append)
+				 const struct fib6_info *nrt, bool replace)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 
-	if (!append)
+	if (!mlxsw_sp_fib6_rt_can_mp(nrt) || replace)
 		return NULL;
 
 	list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
@@ -4784,7 +4790,8 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 			break;
 		if (rt->fib6_metric < nrt->fib6_metric)
 			continue;
-		if (rt->fib6_metric == nrt->fib6_metric)
+		if (rt->fib6_metric == nrt->fib6_metric &&
+		    mlxsw_sp_fib6_rt_can_mp(rt))
 			return fib6_entry;
 		if (rt->fib6_metric > nrt->fib6_metric)
 			break;
@@ -5163,7 +5170,7 @@ static struct mlxsw_sp_fib6_entry *
 mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 			      const struct fib6_info *nrt, bool replace)
 {
-	struct mlxsw_sp_fib6_entry *fib6_entry;
+	struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL;
 
 	list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
 		struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
@@ -5172,13 +5179,18 @@ mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
 			continue;
 		if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id)
 			break;
-		if (replace && rt->fib6_metric == nrt->fib6_metric)
-			return fib6_entry;
+		if (replace && rt->fib6_metric == nrt->fib6_metric) {
+			if (mlxsw_sp_fib6_rt_can_mp(rt) ==
+			    mlxsw_sp_fib6_rt_can_mp(nrt))
+				return fib6_entry;
+			if (mlxsw_sp_fib6_rt_can_mp(nrt))
+				fallback = fallback ?: fib6_entry;
+		}
 		if (rt->fib6_metric > nrt->fib6_metric)
-			return fib6_entry;
+			return fallback ?: fib6_entry;
 	}
 
-	return NULL;
+	return fallback;
 }
 
 static int
@@ -5304,8 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
-				    struct fib6_info *rt, bool replace,
-				    bool append)
+				    struct fib6_info *rt, bool replace)
 {
 	struct mlxsw_sp_fib6_entry *fib6_entry;
 	struct mlxsw_sp_fib_node *fib_node;
@@ -5331,7 +5342,7 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 	/* Before creating a new entry, try to append route to an existing
 	 * multipath entry.
 	 */
-	fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, append);
+	fib6_entry = mlxsw_sp_fib6_node_mp_entry_find(fib_node, rt, replace);
 	if (fib6_entry) {
 		err = mlxsw_sp_fib6_entry_nexthop_add(mlxsw_sp, fib6_entry, rt);
 		if (err)
@@ -5339,14 +5350,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 	}
 
-	/* We received an append event, yet did not find any route to
-	 * append to.
-	 */
-	if (WARN_ON(append)) {
-		err = -EINVAL;
-		goto err_fib6_entry_append;
-	}
-
 	fib6_entry = mlxsw_sp_fib6_entry_create(mlxsw_sp, fib_node, rt);
 	if (IS_ERR(fib6_entry)) {
 		err = PTR_ERR(fib6_entry);
@@ -5364,7 +5367,6 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
 err_fib6_node_entry_link:
 	mlxsw_sp_fib6_entry_destroy(mlxsw_sp, fib6_entry);
 err_fib6_entry_create:
-err_fib6_entry_append:
 err_fib6_entry_nexthop_add:
 	mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
 	return err;
@@ -5715,7 +5717,7 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 	struct mlxsw_sp_fib_event_work *fib_work =
 		container_of(work, struct mlxsw_sp_fib_event_work, work);
 	struct mlxsw_sp *mlxsw_sp = fib_work->mlxsw_sp;
-	bool replace, append;
+	bool replace;
 	int err;
 
 	rtnl_lock();
@@ -5726,10 +5728,8 @@ static void mlxsw_sp_router_fib6_event_work(struct work_struct *work)
 	case FIB_EVENT_ENTRY_APPEND: /* fall through */
 	case FIB_EVENT_ENTRY_ADD:
 		replace = fib_work->event == FIB_EVENT_ENTRY_REPLACE;
-		append = fib_work->event == FIB_EVENT_ENTRY_APPEND;
 		err = mlxsw_sp_router_fib6_add(mlxsw_sp,
-					       fib_work->fen6_info.rt, replace,
-					       append);
+					       fib_work->fen6_info.rt, replace);
 		if (err)
 			mlxsw_sp_router_fib_abort(mlxsw_sp);
 		mlxsw_sp_rt6_release(fib_work->fen6_info.rt);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index fcdfb8e7fdea..40216d56dddc 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -81,10 +81,10 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 
 	ret = nfp_net_bpf_offload(nn, prog, running, extack);
 	/* Stop offload if replace not possible */
-	if (ret && prog)
-		nfp_bpf_xdp_offload(app, nn, NULL, extack);
+	if (ret)
+		return ret;
 
-	nn->dp.bpf_offload_xdp = prog && !ret;
+	nn->dp.bpf_offload_xdp = !!prog;
 	return ret;
 }
 
@@ -202,6 +202,9 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	if (tcf_block_shared(f->block))
+		return -EOPNOTSUPP;
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 91935405f586..84f7a5dbea9d 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -123,6 +123,20 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame,
 			 NFP_FLOWER_MASK_MPLS_Q;
 
 		frame->mpls_lse = cpu_to_be32(t_mpls);
+	} else if (dissector_uses_key(flow->dissector,
+				      FLOW_DISSECTOR_KEY_BASIC)) {
+		/* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
+		 * bit, which indicates an mpls ether type but without any
+		 * mpls fields.
+		 */
+		struct flow_dissector_key_basic *key_basic;
+
+		key_basic = skb_flow_dissector_target(flow->dissector,
+						      FLOW_DISSECTOR_KEY_BASIC,
+						      flow->key);
+		if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+		    key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
+			frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
 	}
 }
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index c42e64f32333..525057bee0ed 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -264,6 +264,14 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		case cpu_to_be16(ETH_P_ARP):
 			return -EOPNOTSUPP;
 
+		case cpu_to_be16(ETH_P_MPLS_UC):
+		case cpu_to_be16(ETH_P_MPLS_MC):
+			if (!(key_layer & NFP_FLOWER_LAYER_MAC)) {
+				key_layer |= NFP_FLOWER_LAYER_MAC;
+				key_size += sizeof(struct nfp_flower_mac_mpls);
+			}
+			break;
+
 		/* Will be included in layer 2. */
 		case cpu_to_be16(ETH_P_8021Q):
 			break;
@@ -623,6 +631,9 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	if (tcf_block_shared(f->block))
+		return -EOPNOTSUPP;
+
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 78afe75129ab..382bb93cb090 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -317,7 +317,7 @@ nfp_tun_write_neigh(struct net_device *netdev, struct nfp_app *app,
 	payload.dst_ipv4 = flow->daddr;
 
 	/* If entry has expired send dst IP with all other fields 0. */
-	if (!(neigh->nud_state & NUD_VALID)) {
+	if (!(neigh->nud_state & NUD_VALID) || neigh->dead) {
 		nfp_tun_del_route_from_cache(app, payload.dst_ipv4);
 		/* Trigger ARP to verify invalid neighbour state. */
 		neigh_event_send(neigh, NULL);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 46b76d5a726c..152283d7e59c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -240,7 +240,6 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 		return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
 
 	pf->limit_vfs = ~0;
-	pci_sriov_set_totalvfs(pf->pdev, 0); /* 0 is unset */
 	/* Allow any setting for backwards compatibility if symbol not found */
 	if (err == -ENOENT)
 		return 0;
@@ -668,7 +667,7 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 
 	err = nfp_net_pci_probe(pf);
 	if (err)
-		goto err_sriov_unlimit;
+		goto err_fw_unload;
 
 	err = nfp_hwmon_register(pf);
 	if (err) {
@@ -680,8 +679,6 @@ static int nfp_pci_probe(struct pci_dev *pdev,
 
 err_net_remove:
 	nfp_net_pci_remove(pf);
-err_sriov_unlimit:
-	pci_sriov_set_totalvfs(pf->pdev, 0);
 err_fw_unload:
 	kfree(pf->rtbl);
 	nfp_mip_close(pf->mip);
@@ -715,7 +712,6 @@ static void nfp_pci_remove(struct pci_dev *pdev)
 	nfp_hwmon_unregister(pf);
 
 	nfp_pcie_sriov_disable(pdev);
-	pci_sriov_set_totalvfs(pf->pdev, 0);
 
 	nfp_net_pci_remove(pf);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
index cd34097b79f1..37a6d7822a38 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
@@ -232,7 +232,7 @@ struct nfp_nffw_info *nfp_nffw_info_open(struct nfp_cpp *cpp)
 	err = nfp_cpp_read(cpp, nfp_resource_cpp_id(state->res),
 			   nfp_resource_address(state->res),
 			   fwinf, sizeof(*fwinf));
-	if (err < sizeof(*fwinf))
+	if (err < (int)sizeof(*fwinf))
 		goto err_release;
 
 	if (!nffw_res_flg_init_get(fwinf))
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 00db3401b898..1dfaccd151f0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -502,6 +502,7 @@ enum BAR_ID {
 struct qed_nvm_image_info {
 	u32 num_images;
 	struct bist_nvm_image_att *image_att;
+	bool valid;
 };
 
 #define DRV_MODULE_VERSION		      \
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index f0b01385d5cb..e0680ce91328 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -709,9 +709,9 @@ qed_dcbx_get_local_lldp_params(struct qed_hwfn *p_hwfn,
 	p_local = &p_hwfn->p_dcbx_info->lldp_local[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_local.local_chassis_id, p_local->local_chassis_id,
-	       ARRAY_SIZE(p_local->local_chassis_id));
+	       sizeof(p_local->local_chassis_id));
 	memcpy(params->lldp_local.local_port_id, p_local->local_port_id,
-	       ARRAY_SIZE(p_local->local_port_id));
+	       sizeof(p_local->local_port_id));
 }
 
 static void
@@ -723,9 +723,9 @@ qed_dcbx_get_remote_lldp_params(struct qed_hwfn *p_hwfn,
 	p_remote = &p_hwfn->p_dcbx_info->lldp_remote[LLDP_NEAREST_BRIDGE];
 
 	memcpy(params->lldp_remote.peer_chassis_id, p_remote->peer_chassis_id,
-	       ARRAY_SIZE(p_remote->peer_chassis_id));
+	       sizeof(p_remote->peer_chassis_id));
 	memcpy(params->lldp_remote.peer_port_id, p_remote->peer_port_id,
-	       ARRAY_SIZE(p_remote->peer_port_id));
+	       sizeof(p_remote->peer_port_id));
 }
 
 static int
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index a14e48489029..4340c4c90bcb 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -6723,7 +6723,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf,
 		format_idx = header & MFW_TRACE_EVENTID_MASK;
 
 		/* Skip message if its index doesn't exist in the meta data */
-		if (format_idx > s_mcp_trace_meta.formats_num) {
+		if (format_idx >= s_mcp_trace_meta.formats_num) {
 			u8 format_size =
 				(u8)((header & MFW_TRACE_PRM_SIZE_MASK) >>
 				     MFW_TRACE_PRM_SIZE_SHIFT);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 329781cda77f..e5249b4741d0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1804,7 +1804,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			DP_INFO(p_hwfn, "Failed to update driver state\n");
 
 		rc = qed_mcp_ov_update_eswitch(p_hwfn, p_hwfn->p_main_ptt,
-					       QED_OV_ESWITCH_VEB);
+					       QED_OV_ESWITCH_NONE);
 		if (rc)
 			DP_INFO(p_hwfn, "Failed to update eswitch mode\n");
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 99973e10b179..5ede6408649d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -665,7 +665,7 @@ qed_sp_update_mcast_bin(struct qed_hwfn *p_hwfn,
 
 	p_ramrod->common.update_approx_mcast_flg = 1;
 	for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
-		u32 *p_bins = (u32 *)p_params->bins;
+		u32 *p_bins = p_params->bins;
 
 		p_ramrod->approx_mcast.bins[i] = cpu_to_le32(p_bins[i]);
 	}
@@ -1476,8 +1476,8 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn,
 			enum spq_mode comp_mode,
 			struct qed_spq_comp_cb *p_comp_data)
 {
-	unsigned long bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
 	struct vport_update_ramrod_data *p_ramrod = NULL;
+	u32 bins[ETH_MULTICAST_MAC_BINS_IN_REGS];
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	u8 abs_vport_id = 0;
@@ -1513,26 +1513,25 @@ qed_sp_eth_filter_mcast(struct qed_hwfn *p_hwfn,
 	/* explicitly clear out the entire vector */
 	memset(&p_ramrod->approx_mcast.bins, 0,
 	       sizeof(p_ramrod->approx_mcast.bins));
-	memset(bins, 0, sizeof(unsigned long) *
-	       ETH_MULTICAST_MAC_BINS_IN_REGS);
+	memset(bins, 0, sizeof(bins));
 	/* filter ADD op is explicit set op and it removes
 	 *  any existing filters for the vport
 	 */
 	if (p_filter_cmd->opcode == QED_FILTER_ADD) {
 		for (i = 0; i < p_filter_cmd->num_mc_addrs; i++) {
-			u32 bit;
+			u32 bit, nbits;
 
 			bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
-			__set_bit(bit, bins);
+			nbits = sizeof(u32) * BITS_PER_BYTE;
+			bins[bit / nbits] |= 1 << (bit % nbits);
 		}
 
 		/* Convert to correct endianity */
 		for (i = 0; i < ETH_MULTICAST_MAC_BINS_IN_REGS; i++) {
 			struct vport_update_ramrod_mcast *p_ramrod_bins;
-			u32 *p_bins = (u32 *)bins;
 
 			p_ramrod_bins = &p_ramrod->approx_mcast;
-			p_ramrod_bins->bins[i] = cpu_to_le32(p_bins[i]);
+			p_ramrod_bins->bins[i] = cpu_to_le32(bins[i]);
 		}
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index 806a8da257e9..8d80f1095d17 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -215,7 +215,7 @@ struct qed_sp_vport_update_params {
 	u8				anti_spoofing_en;
 	u8				update_accept_any_vlan_flg;
 	u8				accept_any_vlan;
-	unsigned long			bins[8];
+	u32				bins[8];
 	struct qed_rss_params		*rss_params;
 	struct qed_filter_accept_flags	accept_flags;
 	struct qed_sge_tpa_params	*sge_tpa_params;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 5c10fd7210c3..758a9a5127fa 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -371,7 +371,7 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 		goto err2;
 	}
 
-	DP_INFO(cdev, "qed_probe completed successffuly\n");
+	DP_INFO(cdev, "qed_probe completed successfully\n");
 
 	return cdev;
 
@@ -789,6 +789,14 @@ static int qed_slowpath_setup_int(struct qed_dev *cdev,
 	/* We want a minimum of one slowpath and one fastpath vector per hwfn */
 	cdev->int_params.in.min_msix_cnt = cdev->num_hwfns * 2;
 
+	if (is_kdump_kernel()) {
+		DP_INFO(cdev,
+			"Kdump kernel: Limit the max number of requested MSI-X vectors to %hd\n",
+			cdev->int_params.in.min_msix_cnt);
+		cdev->int_params.in.num_vectors =
+			cdev->int_params.in.min_msix_cnt;
+	}
+
 	rc = qed_set_int_mode(cdev, false);
 	if (rc)  {
 		DP_ERR(cdev, "qed_slowpath_setup_int ERR\n");
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 4e0b443c9519..cdd645024a32 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -592,6 +592,9 @@ int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
 	*o_mcp_resp = mb_params.mcp_resp;
 	*o_mcp_param = mb_params.mcp_param;
 
+	/* nvm_info needs to be updated */
+	p_hwfn->nvm_info.valid = false;
+
 	return 0;
 }
 
@@ -1208,6 +1211,7 @@ static void qed_mcp_handle_link_change(struct qed_hwfn *p_hwfn,
 		break;
 	default:
 		p_link->speed = 0;
+		p_link->link_up = 0;
 	}
 
 	if (p_link->link_up && p_link->speed)
@@ -1305,9 +1309,15 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	phy_cfg.pause |= (params->pause.forced_tx) ? ETH_PAUSE_TX : 0;
 	phy_cfg.adv_speed = params->speed.advertised_speeds;
 	phy_cfg.loopback_mode = params->loopback_mode;
-	if (p_hwfn->mcp_info->capabilities & FW_MB_PARAM_FEATURE_SUPPORT_EEE) {
-		if (params->eee.enable)
-			phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
+
+	/* There are MFWs that share this capability regardless of whether
+	 * this is feasible or not. And given that at the very least adv_caps
+	 * would be set internally by qed, we want to make sure LFA would
+	 * still work.
+	 */
+	if ((p_hwfn->mcp_info->capabilities &
+	     FW_MB_PARAM_FEATURE_SUPPORT_EEE) && params->eee.enable) {
+		phy_cfg.eee_cfg |= EEE_CFG_EEE_ENABLED;
 		if (params->eee.tx_lpi_enable)
 			phy_cfg.eee_cfg |= EEE_CFG_TX_LPI;
 		if (params->eee.adv_caps & QED_EEE_1G_ADV)
@@ -2555,11 +2565,14 @@ int qed_mcp_bist_nvm_get_image_att(struct qed_hwfn *p_hwfn,
 
 int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 {
-	struct qed_nvm_image_info *nvm_info = &p_hwfn->nvm_info;
+	struct qed_nvm_image_info nvm_info;
 	struct qed_ptt *p_ptt;
 	int rc;
 	u32 i;
 
+	if (p_hwfn->nvm_info.valid)
+		return 0;
+
 	p_ptt = qed_ptt_acquire(p_hwfn);
 	if (!p_ptt) {
 		DP_ERR(p_hwfn, "failed to acquire ptt\n");
@@ -2567,29 +2580,29 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 	}
 
 	/* Acquire from MFW the amount of available images */
-	nvm_info->num_images = 0;
+	nvm_info.num_images = 0;
 	rc = qed_mcp_bist_nvm_get_num_images(p_hwfn,
-					     p_ptt, &nvm_info->num_images);
+					     p_ptt, &nvm_info.num_images);
 	if (rc == -EOPNOTSUPP) {
 		DP_INFO(p_hwfn, "DRV_MSG_CODE_BIST_TEST is not supported\n");
 		goto out;
-	} else if (rc || !nvm_info->num_images) {
+	} else if (rc || !nvm_info.num_images) {
 		DP_ERR(p_hwfn, "Failed getting number of images\n");
 		goto err0;
 	}
 
-	nvm_info->image_att = kmalloc_array(nvm_info->num_images,
-					    sizeof(struct bist_nvm_image_att),
-					    GFP_KERNEL);
-	if (!nvm_info->image_att) {
+	nvm_info.image_att = kmalloc_array(nvm_info.num_images,
+					   sizeof(struct bist_nvm_image_att),
+					   GFP_KERNEL);
+	if (!nvm_info.image_att) {
 		rc = -ENOMEM;
 		goto err0;
 	}
 
 	/* Iterate over images and get their attributes */
-	for (i = 0; i < nvm_info->num_images; i++) {
+	for (i = 0; i < nvm_info.num_images; i++) {
 		rc = qed_mcp_bist_nvm_get_image_att(p_hwfn, p_ptt,
-						    &nvm_info->image_att[i], i);
+						    &nvm_info.image_att[i], i);
 		if (rc) {
 			DP_ERR(p_hwfn,
 			       "Failed getting image index %d attributes\n", i);
@@ -2597,14 +2610,22 @@ int qed_mcp_nvm_info_populate(struct qed_hwfn *p_hwfn)
 		}
 
 		DP_VERBOSE(p_hwfn, QED_MSG_SP, "image index %d, size %x\n", i,
-			   nvm_info->image_att[i].len);
+			   nvm_info.image_att[i].len);
 	}
 out:
+	/* Update hwfn's nvm_info */
+	if (nvm_info.num_images) {
+		p_hwfn->nvm_info.num_images = nvm_info.num_images;
+		kfree(p_hwfn->nvm_info.image_att);
+		p_hwfn->nvm_info.image_att = nvm_info.image_att;
+		p_hwfn->nvm_info.valid = true;
+	}
+
 	qed_ptt_release(p_hwfn, p_ptt);
 	return 0;
 
 err1:
-	kfree(nvm_info->image_att);
+	kfree(nvm_info.image_att);
 err0:
 	qed_ptt_release(p_hwfn, p_ptt);
 	return rc;
@@ -2641,6 +2662,7 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn,
 		return -EINVAL;
 	}
 
+	qed_mcp_nvm_info_populate(p_hwfn);
 	for (i = 0; i < p_hwfn->nvm_info.num_images; i++)
 		if (type == p_hwfn->nvm_info.image_att[i].image_type)
 			break;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index f01bf52bc381..26e918d7f2f9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -2831,7 +2831,7 @@ qed_iov_vp_update_mcast_bin_param(struct qed_hwfn *p_hwfn,
 
 	p_data->update_approx_mcast_flg = 1;
 	memcpy(p_data->bins, p_mcast_tlv->bins,
-	       sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+	       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
 	*tlvs_mask |= 1 << QED_IOV_VP_UPDATE_MCAST;
 }
 
@@ -4513,6 +4513,8 @@ static void qed_sriov_enable_qid_config(struct qed_hwfn *hwfn,
 static int qed_sriov_enable(struct qed_dev *cdev, int num)
 {
 	struct qed_iov_vf_init_params params;
+	struct qed_hwfn *hwfn;
+	struct qed_ptt *ptt;
 	int i, j, rc;
 
 	if (num >= RESC_NUM(&cdev->hwfns[0], QED_VPORT)) {
@@ -4525,8 +4527,8 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 
 	/* Initialize HW for VF access */
 	for_each_hwfn(cdev, j) {
-		struct qed_hwfn *hwfn = &cdev->hwfns[j];
-		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
+		hwfn = &cdev->hwfns[j];
+		ptt = qed_ptt_acquire(hwfn);
 
 		/* Make sure not to use more than 16 queues per VF */
 		params.num_queues = min_t(int,
@@ -4562,6 +4564,19 @@ static int qed_sriov_enable(struct qed_dev *cdev, int num)
 		goto err;
 	}
 
+	hwfn = QED_LEADING_HWFN(cdev);
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt) {
+		DP_ERR(hwfn, "Failed to acquire ptt\n");
+		rc = -EBUSY;
+		goto err;
+	}
+
+	rc = qed_mcp_ov_update_eswitch(hwfn, ptt, QED_OV_ESWITCH_VEB);
+	if (rc)
+		DP_INFO(cdev, "Failed to update eswitch mode\n");
+	qed_ptt_release(hwfn, ptt);
+
 	return num;
 
 err:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 2d7fcd6a0777..be6ddde1a104 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -1126,7 +1126,7 @@ int qed_vf_pf_vport_update(struct qed_hwfn *p_hwfn,
 		resp_size += sizeof(struct pfvf_def_resp_tlv);
 
 		memcpy(p_mcast_tlv->bins, p_params->bins,
-		       sizeof(unsigned long) * ETH_MULTICAST_MAC_BINS_IN_REGS);
+		       sizeof(u32) * ETH_MULTICAST_MAC_BINS_IN_REGS);
 	}
 
 	update_rx = p_params->accept_flags.update_rx_mode_config;
@@ -1272,7 +1272,7 @@ void qed_vf_pf_filter_mcast(struct qed_hwfn *p_hwfn,
 			u32 bit;
 
 			bit = qed_mcast_bin_from_mac(p_filter_cmd->mac[i]);
-			__set_bit(bit, sp_params.bins);
+			sp_params.bins[bit / 32] |= 1 << (bit % 32);
 		}
 	}
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h
index 4f05d5eb3cf5..033409db86ae 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h
@@ -392,7 +392,12 @@ struct vfpf_vport_update_mcast_bin_tlv {
 	struct channel_tlv tl;
 	u8 padding[4];
 
-	u64 bins[8];
+	/* There are only 256 approx bins, and in HSI they're divided into
+	 * 32-bit values. As old VFs used to set-bit to the values on its side,
+	 * the upper half of the array is never expected to contain any data.
+	 */
+	u64 bins[4];
+	u64 obsolete_bins[4];
 };
 
 struct vfpf_vport_update_accept_param_tlv {
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 02adb513f475..013ff567283c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -337,8 +337,14 @@ int qede_ptp_get_ts_info(struct qede_dev *edev, struct ethtool_ts_info *info)
 {
 	struct qede_ptp *ptp = edev->ptp;
 
-	if (!ptp)
-		return -EIO;
+	if (!ptp) {
+		info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+					SOF_TIMESTAMPING_RX_SOFTWARE |
+					SOF_TIMESTAMPING_SOFTWARE;
+		info->phc_index = -1;
+
+		return 0;
+	}
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
 				SOF_TIMESTAMPING_RX_SOFTWARE |
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
index 891f03a7a33d..8d7b9bb910f2 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sysfs.c
@@ -1128,6 +1128,8 @@ static ssize_t qlcnic_83xx_sysfs_flash_write_handler(struct file *filp,
 	struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
 
 	ret = kstrtoul(buf, 16, &data);
+	if (ret)
+		return ret;
 
 	switch (data) {
 	case QLC_83XX_FLASH_SECTOR_ERASE_CMD:
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index 5803cd6db406..206f0266463e 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -658,7 +658,7 @@ qcaspi_netdev_open(struct net_device *dev)
 		return ret;
 	}
 
-	netif_start_queue(qca->net_dev);
+	/* SPI thread takes care of TX queue */
 
 	return 0;
 }
@@ -760,6 +760,9 @@ qcaspi_netdev_tx_timeout(struct net_device *dev)
 	qca->net_dev->stats.tx_errors++;
 	/* Trigger tx queue flush and QCA7000 reset */
 	qca->sync = QCASPI_SYNC_UNKNOWN;
+
+	if (qca->spi_thread)
+		wake_up_process(qca->spi_thread);
 }
 
 static int
@@ -878,22 +881,22 @@ qca_spi_probe(struct spi_device *spi)
 
 	if ((qcaspi_clkspeed < QCASPI_CLK_SPEED_MIN) ||
 	    (qcaspi_clkspeed > QCASPI_CLK_SPEED_MAX)) {
-		dev_info(&spi->dev, "Invalid clkspeed: %d\n",
-			 qcaspi_clkspeed);
+		dev_err(&spi->dev, "Invalid clkspeed: %d\n",
+			qcaspi_clkspeed);
 		return -EINVAL;
 	}
 
 	if ((qcaspi_burst_len < QCASPI_BURST_LEN_MIN) ||
 	    (qcaspi_burst_len > QCASPI_BURST_LEN_MAX)) {
-		dev_info(&spi->dev, "Invalid burst len: %d\n",
-			 qcaspi_burst_len);
+		dev_err(&spi->dev, "Invalid burst len: %d\n",
+			qcaspi_burst_len);
 		return -EINVAL;
 	}
 
 	if ((qcaspi_pluggable < QCASPI_PLUGGABLE_MIN) ||
 	    (qcaspi_pluggable > QCASPI_PLUGGABLE_MAX)) {
-		dev_info(&spi->dev, "Invalid pluggable: %d\n",
-			 qcaspi_pluggable);
+		dev_err(&spi->dev, "Invalid pluggable: %d\n",
+			qcaspi_pluggable);
 		return -EINVAL;
 	}
 
@@ -955,8 +958,8 @@ qca_spi_probe(struct spi_device *spi)
 	}
 
 	if (register_netdev(qcaspi_devs)) {
-		dev_info(&spi->dev, "Unable to register net device %s\n",
-			 qcaspi_devs->name);
+		dev_err(&spi->dev, "Unable to register net device %s\n",
+			qcaspi_devs->name);
 		free_netdev(qcaspi_devs);
 		return -EFAULT;
 	}
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f4cae2be0fda..eaedc11ed686 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7734,8 +7734,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
-	/* override BIOS settings, use userspace tools to enable WOL */
-	__rtl8169_set_wol(tp, 0);
+	tp->saved_wolopts = __rtl8169_get_wol(tp);
 
 	if (rtl_tbi_enabled(tp)) {
 		tp->set_speed = rtl8169_set_speed_tbi;
@@ -7789,6 +7788,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		NETIF_F_HW_VLAN_CTAG_RX;
 	dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO |
 		NETIF_F_HIGHDMA;
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	tp->cp_cmd |= RxChkSum | RxVlan;
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 68f122140966..0d811c02ff34 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -980,6 +980,13 @@ static void ravb_adjust_link(struct net_device *ndev)
 	struct ravb_private *priv = netdev_priv(ndev);
 	struct phy_device *phydev = ndev->phydev;
 	bool new_state = false;
+	unsigned long flags;
+
+	spin_lock_irqsave(&priv->lock, flags);
+
+	/* Disable TX and RX right over here, if E-MAC change is ignored */
+	if (priv->no_avb_link)
+		ravb_rcv_snd_disable(ndev);
 
 	if (phydev->link) {
 		if (phydev->duplex != priv->duplex) {
@@ -997,18 +1004,21 @@ static void ravb_adjust_link(struct net_device *ndev)
 			ravb_modify(ndev, ECMR, ECMR_TXF, 0);
 			new_state = true;
 			priv->link = phydev->link;
-			if (priv->no_avb_link)
-				ravb_rcv_snd_enable(ndev);
 		}
 	} else if (priv->link) {
 		new_state = true;
 		priv->link = 0;
 		priv->speed = 0;
 		priv->duplex = -1;
-		if (priv->no_avb_link)
-			ravb_rcv_snd_disable(ndev);
 	}
 
+	/* Enable TX and RX right over here, if E-MAC change is ignored */
+	if (priv->no_avb_link && phydev->link)
+		ravb_rcv_snd_enable(ndev);
+
+	mmiowb();
+	spin_unlock_irqrestore(&priv->lock, flags);
+
 	if (new_state && netif_msg_link(priv))
 		phy_print_status(phydev);
 }
@@ -1096,75 +1106,6 @@ static int ravb_phy_start(struct net_device *ndev)
 	return 0;
 }
 
-static int ravb_get_link_ksettings(struct net_device *ndev,
-				   struct ethtool_link_ksettings *cmd)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	unsigned long flags;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&priv->lock, flags);
-	phy_ethtool_ksettings_get(ndev->phydev, cmd);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	return 0;
-}
-
-static int ravb_set_link_ksettings(struct net_device *ndev,
-				   const struct ethtool_link_ksettings *cmd)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	unsigned long flags;
-	int error;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&priv->lock, flags);
-
-	/* Disable TX and RX */
-	ravb_rcv_snd_disable(ndev);
-
-	error = phy_ethtool_ksettings_set(ndev->phydev, cmd);
-	if (error)
-		goto error_exit;
-
-	if (cmd->base.duplex == DUPLEX_FULL)
-		priv->duplex = 1;
-	else
-		priv->duplex = 0;
-
-	ravb_set_duplex(ndev);
-
-error_exit:
-	mdelay(1);
-
-	/* Enable TX and RX */
-	ravb_rcv_snd_enable(ndev);
-
-	mmiowb();
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	return error;
-}
-
-static int ravb_nway_reset(struct net_device *ndev)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-	int error = -ENODEV;
-	unsigned long flags;
-
-	if (ndev->phydev) {
-		spin_lock_irqsave(&priv->lock, flags);
-		error = phy_start_aneg(ndev->phydev);
-		spin_unlock_irqrestore(&priv->lock, flags);
-	}
-
-	return error;
-}
-
 static u32 ravb_get_msglevel(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -1377,7 +1318,7 @@ static int ravb_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 }
 
 static const struct ethtool_ops ravb_ethtool_ops = {
-	.nway_reset		= ravb_nway_reset,
+	.nway_reset		= phy_ethtool_nway_reset,
 	.get_msglevel		= ravb_get_msglevel,
 	.set_msglevel		= ravb_set_msglevel,
 	.get_link		= ethtool_op_get_link,
@@ -1387,8 +1328,8 @@ static const struct ethtool_ops ravb_ethtool_ops = {
 	.get_ringparam		= ravb_get_ringparam,
 	.set_ringparam		= ravb_set_ringparam,
 	.get_ts_info		= ravb_get_ts_info,
-	.get_link_ksettings	= ravb_get_link_ksettings,
-	.set_link_ksettings	= ravb_set_link_ksettings,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 	.get_wol		= ravb_get_wol,
 	.set_wol		= ravb_set_wol,
 };
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index e9007b613f17..5614fd231bbe 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1927,8 +1927,15 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
 	struct phy_device *phydev = ndev->phydev;
+	unsigned long flags;
 	int new_state = 0;
 
+	spin_lock_irqsave(&mdp->lock, flags);
+
+	/* Disable TX and RX right over here, if E-MAC change is ignored */
+	if (mdp->cd->no_psr || mdp->no_ether_link)
+		sh_eth_rcv_snd_disable(ndev);
+
 	if (phydev->link) {
 		if (phydev->duplex != mdp->duplex) {
 			new_state = 1;
@@ -1947,18 +1954,21 @@ static void sh_eth_adjust_link(struct net_device *ndev)
 			sh_eth_modify(ndev, ECMR, ECMR_TXF, 0);
 			new_state = 1;
 			mdp->link = phydev->link;
-			if (mdp->cd->no_psr || mdp->no_ether_link)
-				sh_eth_rcv_snd_enable(ndev);
 		}
 	} else if (mdp->link) {
 		new_state = 1;
 		mdp->link = 0;
 		mdp->speed = 0;
 		mdp->duplex = -1;
-		if (mdp->cd->no_psr || mdp->no_ether_link)
-			sh_eth_rcv_snd_disable(ndev);
 	}
 
+	/* Enable TX and RX right over here, if E-MAC change is ignored */
+	if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link)
+		sh_eth_rcv_snd_enable(ndev);
+
+	mmiowb();
+	spin_unlock_irqrestore(&mdp->lock, flags);
+
 	if (new_state && netif_msg_link(mdp))
 		phy_print_status(phydev);
 }
@@ -2030,60 +2040,6 @@ static int sh_eth_phy_start(struct net_device *ndev)
 	return 0;
 }
 
-static int sh_eth_get_link_ksettings(struct net_device *ndev,
-				     struct ethtool_link_ksettings *cmd)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	unsigned long flags;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&mdp->lock, flags);
-	phy_ethtool_ksettings_get(ndev->phydev, cmd);
-	spin_unlock_irqrestore(&mdp->lock, flags);
-
-	return 0;
-}
-
-static int sh_eth_set_link_ksettings(struct net_device *ndev,
-				     const struct ethtool_link_ksettings *cmd)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	unsigned long flags;
-	int ret;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&mdp->lock, flags);
-
-	/* disable tx and rx */
-	sh_eth_rcv_snd_disable(ndev);
-
-	ret = phy_ethtool_ksettings_set(ndev->phydev, cmd);
-	if (ret)
-		goto error_exit;
-
-	if (cmd->base.duplex == DUPLEX_FULL)
-		mdp->duplex = 1;
-	else
-		mdp->duplex = 0;
-
-	if (mdp->cd->set_duplex)
-		mdp->cd->set_duplex(ndev);
-
-error_exit:
-	mdelay(1);
-
-	/* enable tx and rx */
-	sh_eth_rcv_snd_enable(ndev);
-
-	spin_unlock_irqrestore(&mdp->lock, flags);
-
-	return ret;
-}
-
 /* If it is ever necessary to increase SH_ETH_REG_DUMP_MAX_REGS, the
  * version must be bumped as well.  Just adding registers up to that
  * limit is fine, as long as the existing register indices don't
@@ -2263,22 +2219,6 @@ static void sh_eth_get_regs(struct net_device *ndev, struct ethtool_regs *regs,
 	pm_runtime_put_sync(&mdp->pdev->dev);
 }
 
-static int sh_eth_nway_reset(struct net_device *ndev)
-{
-	struct sh_eth_private *mdp = netdev_priv(ndev);
-	unsigned long flags;
-	int ret;
-
-	if (!ndev->phydev)
-		return -ENODEV;
-
-	spin_lock_irqsave(&mdp->lock, flags);
-	ret = phy_start_aneg(ndev->phydev);
-	spin_unlock_irqrestore(&mdp->lock, flags);
-
-	return ret;
-}
-
 static u32 sh_eth_get_msglevel(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
@@ -2429,7 +2369,7 @@ static int sh_eth_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
 static const struct ethtool_ops sh_eth_ethtool_ops = {
 	.get_regs_len	= sh_eth_get_regs_len,
 	.get_regs	= sh_eth_get_regs,
-	.nway_reset	= sh_eth_nway_reset,
+	.nway_reset	= phy_ethtool_nway_reset,
 	.get_msglevel	= sh_eth_get_msglevel,
 	.set_msglevel	= sh_eth_set_msglevel,
 	.get_link	= ethtool_op_get_link,
@@ -2438,8 +2378,8 @@ static const struct ethtool_ops sh_eth_ethtool_ops = {
 	.get_sset_count     = sh_eth_get_sset_count,
 	.get_ringparam	= sh_eth_get_ringparam,
 	.set_ringparam	= sh_eth_set_ringparam,
-	.get_link_ksettings = sh_eth_get_link_ksettings,
-	.set_link_ksettings = sh_eth_set_link_ksettings,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 	.get_wol	= sh_eth_get_wol,
 	.set_wol	= sh_eth_set_wol,
 };
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 23f0785c0573..7eeac3d6cfe8 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4288,9 +4288,9 @@ static int efx_ef10_filter_pri(struct efx_ef10_filter_table *table,
 	return -EPROTONOSUPPORT;
 }
 
-static s32 efx_ef10_filter_insert(struct efx_nic *efx,
-				  struct efx_filter_spec *spec,
-				  bool replace_equal)
+static s32 efx_ef10_filter_insert_locked(struct efx_nic *efx,
+					 struct efx_filter_spec *spec,
+					 bool replace_equal)
 {
 	DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
@@ -4307,7 +4307,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx,
 	bool is_mc_recip;
 	s32 rc;
 
-	down_read(&efx->filter_sem);
+	WARN_ON(!rwsem_is_locked(&efx->filter_sem));
 	table = efx->filter_state;
 	down_write(&table->lock);
 
@@ -4498,10 +4498,22 @@ out_unlock:
 	if (rss_locked)
 		mutex_unlock(&efx->rss_lock);
 	up_write(&table->lock);
-	up_read(&efx->filter_sem);
 	return rc;
 }
 
+static s32 efx_ef10_filter_insert(struct efx_nic *efx,
+				  struct efx_filter_spec *spec,
+				  bool replace_equal)
+{
+	s32 ret;
+
+	down_read(&efx->filter_sem);
+	ret = efx_ef10_filter_insert_locked(efx, spec, replace_equal);
+	up_read(&efx->filter_sem);
+
+	return ret;
+}
+
 static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx)
 {
 	/* no need to do anything here on EF10 */
@@ -5285,7 +5297,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 		EFX_WARN_ON_PARANOID(ids[i] != EFX_EF10_FILTER_ID_INVALID);
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 		efx_filter_set_eth_local(&spec, vlan->vid, addr_list[i].addr);
-		rc = efx_ef10_filter_insert(efx, &spec, true);
+		rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 		if (rc < 0) {
 			if (rollback) {
 				netif_info(efx, drv, efx->net_dev,
@@ -5314,7 +5326,7 @@ static int efx_ef10_filter_insert_addr_list(struct efx_nic *efx,
 		efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, filter_flags, 0);
 		eth_broadcast_addr(baddr);
 		efx_filter_set_eth_local(&spec, vlan->vid, baddr);
-		rc = efx_ef10_filter_insert(efx, &spec, true);
+		rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 		if (rc < 0) {
 			netif_warn(efx, drv, efx->net_dev,
 				   "Broadcast filter insert failed rc=%d\n", rc);
@@ -5370,7 +5382,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx,
 	if (vlan->vid != EFX_FILTER_VID_UNSPEC)
 		efx_filter_set_eth_local(&spec, vlan->vid, NULL);
 
-	rc = efx_ef10_filter_insert(efx, &spec, true);
+	rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 	if (rc < 0) {
 		const char *um = multicast ? "Multicast" : "Unicast";
 		const char *encap_name = "";
@@ -5430,7 +5442,7 @@ static int efx_ef10_filter_insert_def(struct efx_nic *efx,
 					   filter_flags, 0);
 			eth_broadcast_addr(baddr);
 			efx_filter_set_eth_local(&spec, vlan->vid, baddr);
-			rc = efx_ef10_filter_insert(efx, &spec, true);
+			rc = efx_ef10_filter_insert_locked(efx, &spec, true);
 			if (rc < 0) {
 				netif_warn(efx, drv, efx->net_dev,
 					   "Broadcast filter insert failed rc=%d\n",
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 570ec72266f3..ce3a177081a8 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1871,12 +1871,6 @@ static void efx_remove_filters(struct efx_nic *efx)
 	up_write(&efx->filter_sem);
 }
 
-static void efx_restore_filters(struct efx_nic *efx)
-{
-	down_read(&efx->filter_sem);
-	efx->type->filter_table_restore(efx);
-	up_read(&efx->filter_sem);
-}
 
 /**************************************************************************
  *
@@ -2688,6 +2682,7 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method)
 	efx_disable_interrupts(efx);
 
 	mutex_lock(&efx->mac_lock);
+	down_write(&efx->filter_sem);
 	mutex_lock(&efx->rss_lock);
 	if (efx->port_initialized && method != RESET_TYPE_INVISIBLE &&
 	    method != RESET_TYPE_DATAPATH)
@@ -2745,9 +2740,8 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
 	if (efx->type->rx_restore_rss_contexts)
 		efx->type->rx_restore_rss_contexts(efx);
 	mutex_unlock(&efx->rss_lock);
-	down_read(&efx->filter_sem);
-	efx_restore_filters(efx);
-	up_read(&efx->filter_sem);
+	efx->type->filter_table_restore(efx);
+	up_write(&efx->filter_sem);
 	if (efx->type->sriov_reset)
 		efx->type->sriov_reset(efx);
 
@@ -2764,6 +2758,7 @@ fail:
 	efx->port_initialized = false;
 
 	mutex_unlock(&efx->rss_lock);
+	up_write(&efx->filter_sem);
 	mutex_unlock(&efx->mac_lock);
 
 	return rc;
@@ -3473,7 +3468,9 @@ static int efx_pci_probe_main(struct efx_nic *efx)
 
 	efx_init_napi(efx);
 
+	down_write(&efx->filter_sem);
 	rc = efx->type->init(efx);
+	up_write(&efx->filter_sem);
 	if (rc) {
 		netif_err(efx, probe, efx->net_dev,
 			  "failed to initialise NIC\n");
@@ -3765,7 +3762,9 @@ static int efx_pm_resume(struct device *dev)
 	rc = efx->type->reset(efx, RESET_TYPE_ALL);
 	if (rc)
 		return rc;
+	down_write(&efx->filter_sem);
 	rc = efx->type->init(efx);
+	up_write(&efx->filter_sem);
 	if (rc)
 		return rc;
 	rc = efx_pm_thaw(dev);
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
index 8edf20967c82..e045a5d6b938 100644
--- a/drivers/net/ethernet/sfc/farch.c
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -2794,6 +2794,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx)
 	if (!state)
 		return -ENOMEM;
 	efx->filter_state = state;
+	init_rwsem(&state->lock);
 
 	table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
 	table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 2e6e2a96b4f2..f9a61f90cfbc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -37,7 +37,7 @@
  *		is done in the "stmmac files"
  */
 
-/* struct emac_variant - Descrive dwmac-sun8i hardware variant
+/* struct emac_variant - Describe dwmac-sun8i hardware variant
  * @default_syscon_value:	The default value of the EMAC register in syscon
  *				This value is used for disabling properly EMAC
  *				and used as a good starting value in case of the
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index d37f17ca62fe..65bc3556bd8f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -407,6 +407,16 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 	}
 }
 
+static void dwmac4_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+	value &= ~DMA_RBSZ_MASK;
+	value |= (bfsize << DMA_RBSZ_SHIFT) & DMA_RBSZ_MASK;
+
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+}
+
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
@@ -431,6 +441,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.set_bfsize = dwmac4_set_bfsize,
 };
 
 const struct stmmac_dma_ops dwmac410_dma_ops = {
@@ -457,4 +468,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.set_bfsize = dwmac4_set_bfsize,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
index c63c1fe3f26b..22a4a6dbb1a4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -120,6 +120,8 @@
 
 /* DMA Rx Channel X Control register defines */
 #define DMA_CONTROL_SR			BIT(0)
+#define DMA_RBSZ_MASK			GENMASK(14, 1)
+#define DMA_RBSZ_SHIFT			1
 
 /* Interrupt status per channel */
 #define DMA_CHAN_STATUS_REB		GENMASK(21, 19)
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index e44e7b26ce82..fe8b536b13f8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -183,6 +183,7 @@ struct stmmac_dma_ops {
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+	void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan);
 };
 
 #define stmmac_reset(__priv, __args...) \
@@ -235,6 +236,8 @@ struct stmmac_dma_ops {
 	stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
 #define stmmac_enable_tso(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_set_dma_bfsize(__priv, __args...) \
+	stmmac_do_void_callback(__priv, dma, set_bfsize, __args)
 
 struct mac_device_info;
 struct net_device;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cba46b62a1cd..60f59abab009 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1804,6 +1804,8 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 
 		stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan,
 				rxfifosz, qmode);
+		stmmac_set_dma_bfsize(priv, priv->ioaddr, priv->dma_buf_sz,
+				chan);
 	}
 
 	for (chan = 0; chan < tx_channels_count; chan++) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 6d141f3931eb..72da77b94ecd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -94,7 +94,6 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries)
 /**
  * stmmac_axi_setup - parse DT parameters for programming the AXI register
  * @pdev: platform device
- * @priv: driver private struct.
  * Description:
  * if required, from device-tree the AXI internal register can be tuned
  * by using platform parameters.
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
index 16c3bfbe1992..757a3b37ae8a 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c
@@ -218,6 +218,7 @@ issue:
 	ret = of_mdiobus_register(bus, np1);
 	if (ret) {
 		mdiobus_free(bus);
+		lp->mii_bus = NULL;
 		return ret;
 	}
 	return 0;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 750eaa53bf0c..ada33c2d9ac2 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -476,7 +476,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 1a924b867b07..4b6e308199d2 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -210,7 +210,7 @@ int netvsc_recv_callback(struct net_device *net,
 void netvsc_channel_cb(void *context);
 int netvsc_poll(struct napi_struct *napi, int budget);
 
-void rndis_set_subchannel(struct work_struct *w);
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev);
 int rndis_filter_open(struct netvsc_device *nvdev);
 int rndis_filter_close(struct netvsc_device *nvdev);
 struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 5d5bd513847f..31c3d77b4733 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -65,6 +65,41 @@ void netvsc_switch_datapath(struct net_device *ndev, bool vf)
 			       VM_PKT_DATA_INBAND, 0);
 }
 
+/* Worker to setup sub channels on initial setup
+ * Initial hotplug event occurs in softirq context
+ * and can't wait for channels.
+ */
+static void netvsc_subchan_work(struct work_struct *w)
+{
+	struct netvsc_device *nvdev =
+		container_of(w, struct netvsc_device, subchan_work);
+	struct rndis_device *rdev;
+	int i, ret;
+
+	/* Avoid deadlock with device removal already under RTNL */
+	if (!rtnl_trylock()) {
+		schedule_work(w);
+		return;
+	}
+
+	rdev = nvdev->extension;
+	if (rdev) {
+		ret = rndis_set_subchannel(rdev->ndev, nvdev);
+		if (ret == 0) {
+			netif_device_attach(rdev->ndev);
+		} else {
+			/* fallback to only primary channel */
+			for (i = 1; i < nvdev->num_chn; i++)
+				netif_napi_del(&nvdev->chan_table[i].napi);
+
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	rtnl_unlock();
+}
+
 static struct netvsc_device *alloc_net_device(void)
 {
 	struct netvsc_device *net_device;
@@ -81,7 +116,7 @@ static struct netvsc_device *alloc_net_device(void)
 
 	init_completion(&net_device->channel_init_wait);
 	init_waitqueue_head(&net_device->subchan_open);
-	INIT_WORK(&net_device->subchan_work, rndis_set_subchannel);
+	INIT_WORK(&net_device->subchan_work, netvsc_subchan_work);
 
 	return net_device;
 }
@@ -1239,6 +1274,7 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 	struct hv_device *device = netvsc_channel_to_device(channel);
 	struct net_device *ndev = hv_get_drvdata(device);
 	int work_done = 0;
+	int ret;
 
 	/* If starting a new interval */
 	if (!nvchan->desc)
@@ -1250,16 +1286,18 @@ int netvsc_poll(struct napi_struct *napi, int budget)
 		nvchan->desc = hv_pkt_iter_next(channel, nvchan->desc);
 	}
 
-	/* If send of pending receive completions suceeded
-	 *   and did not exhaust NAPI budget this time
-	 *   and not doing busy poll
+	/* Send any pending receive completions */
+	ret = send_recv_completions(ndev, net_device, nvchan);
+
+	/* If it did not exhaust NAPI budget this time
+	 *  and not doing busy poll
 	 * then re-enable host interrupts
-	 *     and reschedule if ring is not empty.
+	 *  and reschedule if ring is not empty
+	 *   or sending receive completion failed.
 	 */
-	if (send_recv_completions(ndev, net_device, nvchan) == 0 &&
-	    work_done < budget &&
+	if (work_done < budget &&
 	    napi_complete_done(napi, work_done) &&
-	    hv_end_read(&channel->inbound) &&
+	    (ret || hv_end_read(&channel->inbound)) &&
 	    napi_schedule_prep(napi)) {
 		hv_begin_read(&channel->inbound);
 		__napi_schedule(napi);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index fe2256bf1d13..dd1d6e115145 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -905,8 +905,20 @@ static int netvsc_attach(struct net_device *ndev,
 	if (IS_ERR(nvdev))
 		return PTR_ERR(nvdev);
 
-	/* Note: enable and attach happen when sub-channels setup */
+	if (nvdev->num_chn > 1) {
+		ret = rndis_set_subchannel(ndev, nvdev);
+
+		/* if unavailable, just proceed with one queue */
+		if (ret) {
+			nvdev->max_chn = 1;
+			nvdev->num_chn = 1;
+		}
+	}
+
+	/* In any case device is now ready */
+	netif_device_attach(ndev);
 
+	/* Note: enable and attach happen when sub-channels setup */
 	netif_carrier_off(ndev);
 
 	if (netif_running(ndev)) {
@@ -2089,6 +2101,9 @@ static int netvsc_probe(struct hv_device *dev,
 
 	memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN);
 
+	if (nvdev->num_chn > 1)
+		schedule_work(&nvdev->subchan_work);
+
 	/* hw_features computed in rndis_netdev_set_hwcaps() */
 	net->features = net->hw_features |
 		NETIF_F_HIGHDMA | NETIF_F_SG |
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 5428bb261102..408ece27131c 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1062,29 +1062,15 @@ static void netvsc_sc_open(struct vmbus_channel *new_sc)
  * This breaks overlap of processing the host message for the
  * new primary channel with the initialization of sub-channels.
  */
-void rndis_set_subchannel(struct work_struct *w)
+int rndis_set_subchannel(struct net_device *ndev, struct netvsc_device *nvdev)
 {
-	struct netvsc_device *nvdev
-		= container_of(w, struct netvsc_device, subchan_work);
 	struct nvsp_message *init_packet = &nvdev->channel_init_pkt;
-	struct net_device_context *ndev_ctx;
-	struct rndis_device *rdev;
-	struct net_device *ndev;
-	struct hv_device *hv_dev;
+	struct net_device_context *ndev_ctx = netdev_priv(ndev);
+	struct hv_device *hv_dev = ndev_ctx->device_ctx;
+	struct rndis_device *rdev = nvdev->extension;
 	int i, ret;
 
-	if (!rtnl_trylock()) {
-		schedule_work(w);
-		return;
-	}
-
-	rdev = nvdev->extension;
-	if (!rdev)
-		goto unlock;	/* device was removed */
-
-	ndev = rdev->ndev;
-	ndev_ctx = netdev_priv(ndev);
-	hv_dev = ndev_ctx->device_ctx;
+	ASSERT_RTNL();
 
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG5_TYPE_SUBCHANNEL;
@@ -1100,13 +1086,13 @@ void rndis_set_subchannel(struct work_struct *w)
 			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret) {
 		netdev_err(ndev, "sub channel allocate send failed: %d\n", ret);
-		goto failed;
+		return ret;
 	}
 
 	wait_for_completion(&nvdev->channel_init_wait);
 	if (init_packet->msg.v5_msg.subchn_comp.status != NVSP_STAT_SUCCESS) {
 		netdev_err(ndev, "sub channel request failed\n");
-		goto failed;
+		return -EIO;
 	}
 
 	nvdev->num_chn = 1 +
@@ -1125,21 +1111,7 @@ void rndis_set_subchannel(struct work_struct *w)
 	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
 		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
 
-	netif_device_attach(ndev);
-	rtnl_unlock();
-	return;
-
-failed:
-	/* fallback to only primary channel */
-	for (i = 1; i < nvdev->num_chn; i++)
-		netif_napi_del(&nvdev->chan_table[i].napi);
-
-	nvdev->max_chn = 1;
-	nvdev->num_chn = 1;
-
-	netif_device_attach(ndev);
-unlock:
-	rtnl_unlock();
+	return 0;
 }
 
 static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
@@ -1360,21 +1332,13 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev,
 		netif_napi_add(net, &net_device->chan_table[i].napi,
 			       netvsc_poll, NAPI_POLL_WEIGHT);
 
-	if (net_device->num_chn > 1)
-		schedule_work(&net_device->subchan_work);
+	return net_device;
 
 out:
-	/* if unavailable, just proceed with one queue */
-	if (ret) {
-		net_device->max_chn = 1;
-		net_device->num_chn = 1;
-	}
-
-	/* No sub channels, device is ready */
-	if (net_device->num_chn == 1)
-		netif_device_attach(net);
-
-	return net_device;
+	/* setting up multiple channels failed */
+	net_device->max_chn = 1;
+	net_device->num_chn = 1;
+	return 0;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index 64f1b1e77bc0..23a52b9293f3 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -275,6 +275,8 @@ struct adf7242_local {
 	struct spi_message stat_msg;
 	struct spi_transfer stat_xfer;
 	struct dentry *debugfs_root;
+	struct delayed_work work;
+	struct workqueue_struct *wqueue;
 	unsigned long flags;
 	int tx_stat;
 	bool promiscuous;
@@ -575,10 +577,26 @@ static int adf7242_cmd_rx(struct adf7242_local *lp)
 	/* Wait until the ACK is sent */
 	adf7242_wait_status(lp, RC_STATUS_PHY_RDY, RC_STATUS_MASK, __LINE__);
 	adf7242_clear_irqstat(lp);
+	mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400));
 
 	return adf7242_cmd(lp, CMD_RC_RX);
 }
 
+static void adf7242_rx_cal_work(struct work_struct *work)
+{
+	struct adf7242_local *lp =
+	container_of(work, struct adf7242_local, work.work);
+
+	/* Reissuing RC_RX every 400ms - to adjust for offset
+	 * drift in receiver (datasheet page 61, OCL section)
+	 */
+
+	if (!test_bit(FLAG_XMIT, &lp->flags)) {
+		adf7242_cmd(lp, CMD_RC_PHY_RDY);
+		adf7242_cmd_rx(lp);
+	}
+}
+
 static int adf7242_set_txpower(struct ieee802154_hw *hw, int mbm)
 {
 	struct adf7242_local *lp = hw->priv;
@@ -686,7 +704,7 @@ static int adf7242_start(struct ieee802154_hw *hw)
 	enable_irq(lp->spi->irq);
 	set_bit(FLAG_START, &lp->flags);
 
-	return adf7242_cmd(lp, CMD_RC_RX);
+	return adf7242_cmd_rx(lp);
 }
 
 static void adf7242_stop(struct ieee802154_hw *hw)
@@ -694,6 +712,7 @@ static void adf7242_stop(struct ieee802154_hw *hw)
 	struct adf7242_local *lp = hw->priv;
 
 	disable_irq(lp->spi->irq);
+	cancel_delayed_work_sync(&lp->work);
 	adf7242_cmd(lp, CMD_RC_IDLE);
 	clear_bit(FLAG_START, &lp->flags);
 	adf7242_clear_irqstat(lp);
@@ -719,7 +738,10 @@ static int adf7242_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 	adf7242_write_reg(lp, REG_CH_FREQ1, freq >> 8);
 	adf7242_write_reg(lp, REG_CH_FREQ2, freq >> 16);
 
-	return adf7242_cmd(lp, CMD_RC_RX);
+	if (test_bit(FLAG_START, &lp->flags))
+		return adf7242_cmd_rx(lp);
+	else
+		return adf7242_cmd(lp, CMD_RC_PHY_RDY);
 }
 
 static int adf7242_set_hw_addr_filt(struct ieee802154_hw *hw,
@@ -814,6 +836,7 @@ static int adf7242_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 	/* ensure existing instances of the IRQ handler have completed */
 	disable_irq(lp->spi->irq);
 	set_bit(FLAG_XMIT, &lp->flags);
+	cancel_delayed_work_sync(&lp->work);
 	reinit_completion(&lp->tx_complete);
 	adf7242_cmd(lp, CMD_RC_PHY_RDY);
 	adf7242_clear_irqstat(lp);
@@ -952,6 +975,7 @@ static irqreturn_t adf7242_isr(int irq, void *data)
 	unsigned int xmit;
 	u8 irq1;
 
+	mod_delayed_work(lp->wqueue, &lp->work, msecs_to_jiffies(400));
 	adf7242_read_reg(lp, REG_IRQ1_SRC1, &irq1);
 
 	if (!(irq1 & (IRQ_RX_PKT_RCVD | IRQ_CSMA_CA)))
@@ -1241,6 +1265,9 @@ static int adf7242_probe(struct spi_device *spi)
 	spi_message_add_tail(&lp->stat_xfer, &lp->stat_msg);
 
 	spi_set_drvdata(spi, lp);
+	INIT_DELAYED_WORK(&lp->work, adf7242_rx_cal_work);
+	lp->wqueue = alloc_ordered_workqueue(dev_name(&spi->dev),
+					     WQ_MEM_RECLAIM);
 
 	ret = adf7242_hw_init(lp);
 	if (ret)
@@ -1284,6 +1311,9 @@ static int adf7242_remove(struct spi_device *spi)
 	if (!IS_ERR_OR_NULL(lp->debugfs_root))
 		debugfs_remove_recursive(lp->debugfs_root);
 
+	cancel_delayed_work_sync(&lp->work);
+	destroy_workqueue(lp->wqueue);
+
 	ieee802154_unregister_hw(lp->hw);
 	mutex_destroy(&lp->bmux);
 	ieee802154_free_hw(lp->hw);
diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c
index 77abedf0b524..3d9e91579866 100644
--- a/drivers/net/ieee802154/at86rf230.c
+++ b/drivers/net/ieee802154/at86rf230.c
@@ -940,7 +940,7 @@ at86rf230_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
 static int
 at86rf230_ed(struct ieee802154_hw *hw, u8 *level)
 {
-	BUG_ON(!level);
+	WARN_ON(!level);
 	*level = 0xbe;
 	return 0;
 }
@@ -1121,8 +1121,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 	if (changed & IEEE802154_AFILT_SADDR_CHANGED) {
 		u16 addr = le16_to_cpu(filt->short_addr);
 
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for saddr\n");
+		dev_vdbg(&lp->spi->dev, "%s called for saddr\n", __func__);
 		__at86rf230_write(lp, RG_SHORT_ADDR_0, addr);
 		__at86rf230_write(lp, RG_SHORT_ADDR_1, addr >> 8);
 	}
@@ -1130,8 +1129,7 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 	if (changed & IEEE802154_AFILT_PANID_CHANGED) {
 		u16 pan = le16_to_cpu(filt->pan_id);
 
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for pan id\n");
+		dev_vdbg(&lp->spi->dev, "%s called for pan id\n", __func__);
 		__at86rf230_write(lp, RG_PAN_ID_0, pan);
 		__at86rf230_write(lp, RG_PAN_ID_1, pan >> 8);
 	}
@@ -1140,15 +1138,13 @@ at86rf230_set_hw_addr_filt(struct ieee802154_hw *hw,
 		u8 i, addr[8];
 
 		memcpy(addr, &filt->ieee_addr, 8);
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for IEEE addr\n");
+		dev_vdbg(&lp->spi->dev, "%s called for IEEE addr\n", __func__);
 		for (i = 0; i < 8; i++)
 			__at86rf230_write(lp, RG_IEEE_ADDR_0 + i, addr[i]);
 	}
 
 	if (changed & IEEE802154_AFILT_PANC_CHANGED) {
-		dev_vdbg(&lp->spi->dev,
-			 "at86rf230_set_hw_addr_filt called for panc change\n");
+		dev_vdbg(&lp->spi->dev, "%s called for panc change\n", __func__);
 		if (filt->pan_coord)
 			at86rf230_write_subreg(lp, SR_AACK_I_AM_COORD, 1);
 		else
@@ -1252,7 +1248,6 @@ at86rf230_set_cca_mode(struct ieee802154_hw *hw,
 	return at86rf230_write_subreg(lp, SR_CCA_MODE, val);
 }
 
-
 static int
 at86rf230_set_cca_ed_level(struct ieee802154_hw *hw, s32 mbm)
 {
diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 0d673f7682ee..176395e4b7bb 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -49,7 +49,7 @@ struct fakelb_phy {
 
 static int fakelb_hw_ed(struct ieee802154_hw *hw, u8 *level)
 {
-	BUG_ON(!level);
+	WARN_ON(!level);
 	*level = 0xbe;
 
 	return 0;
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index de0d7f28a181..e428277781ac 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -15,10 +15,11 @@
  */
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/spi/spi.h>
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/skbuff.h>
 #include <linux/of_gpio.h>
 #include <linux/regmap.h>
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 23c1d6600241..4a949569ec4c 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -75,10 +75,23 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 {
 	struct ipvl_dev *ipvlan;
 	struct net_device *mdev = port->dev;
-	int err = 0;
+	unsigned int flags;
+	int err;
 
 	ASSERT_RTNL();
 	if (port->mode != nval) {
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			flags = ipvlan->dev->flags;
+			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+				err = dev_change_flags(ipvlan->dev,
+						       flags | IFF_NOARP);
+			} else {
+				err = dev_change_flags(ipvlan->dev,
+						       flags & ~IFF_NOARP);
+			}
+			if (unlikely(err))
+				goto fail;
+		}
 		if (nval == IPVLAN_MODE_L3S) {
 			/* New mode is L3S */
 			err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
@@ -86,21 +99,28 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
 				mdev->priv_flags |= IFF_L3MDEV_MASTER;
 			} else
-				return err;
+				goto fail;
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
 			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
 			ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
 			mdev->l3mdev_ops = NULL;
 		}
-		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
-				ipvlan->dev->flags |= IFF_NOARP;
-			else
-				ipvlan->dev->flags &= ~IFF_NOARP;
-		}
 		port->mode = nval;
 	}
+	return 0;
+
+fail:
+	/* Undo the flags changes that have been done so far. */
+	list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+		flags = ipvlan->dev->flags;
+		if (port->mode == IPVLAN_MODE_L3 ||
+		    port->mode == IPVLAN_MODE_L3S)
+			dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+		else
+			dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+	}
+
 	return err;
 }
 
diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 081d99aa3985..49ac678eb2dc 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -222,7 +222,7 @@ static int dp83811_config_intr(struct phy_device *phydev)
 		if (err < 0)
 			return err;
 
-		err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
+		err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
 	}
 
 	return err;
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index b8f57e9b9379..1cd439bdf608 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -130,8 +130,9 @@
 #define MII_88E1318S_PHY_WOL_CTRL_CLEAR_WOL_STATUS		BIT(12)
 #define MII_88E1318S_PHY_WOL_CTRL_MAGIC_PACKET_MATCH_ENABLE	BIT(14)
 
-#define MII_88E1121_PHY_LED_CTRL	16
+#define MII_PHY_LED_CTRL	        16
 #define MII_88E1121_PHY_LED_DEF		0x0030
+#define MII_88E1510_PHY_LED_DEF		0x1177
 
 #define MII_M1011_PHY_STATUS		0x11
 #define MII_M1011_PHY_STATUS_1000	0x8000
@@ -632,8 +633,40 @@ error:
 	return err;
 }
 
+static void marvell_config_led(struct phy_device *phydev)
+{
+	u16 def_config;
+	int err;
+
+	switch (MARVELL_PHY_FAMILY_ID(phydev->phy_id)) {
+	/* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
+	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1121R):
+	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1318S):
+		def_config = MII_88E1121_PHY_LED_DEF;
+		break;
+	/* Default PHY LED config:
+	 * LED[0] .. 1000Mbps Link
+	 * LED[1] .. 100Mbps Link
+	 * LED[2] .. Blink, Activity
+	 */
+	case MARVELL_PHY_FAMILY_ID(MARVELL_PHY_ID_88E1510):
+		def_config = MII_88E1510_PHY_LED_DEF;
+		break;
+	default:
+		return;
+	}
+
+	err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE, MII_PHY_LED_CTRL,
+			      def_config);
+	if (err < 0)
+		pr_warn("Fail to config marvell phy LED.\n");
+}
+
 static int marvell_config_init(struct phy_device *phydev)
 {
+	/* Set defalut LED */
+	marvell_config_led(phydev);
+
 	/* Set registers from marvell,reg-init DT property */
 	return marvell_of_reg_init(phydev);
 }
@@ -813,21 +846,6 @@ static int m88e1111_config_init(struct phy_device *phydev)
 	return genphy_soft_reset(phydev);
 }
 
-static int m88e1121_config_init(struct phy_device *phydev)
-{
-	int err;
-
-	/* Default PHY LED config: LED[0] .. Link, LED[1] .. Activity */
-	err = phy_write_paged(phydev, MII_MARVELL_LED_PAGE,
-			      MII_88E1121_PHY_LED_CTRL,
-			      MII_88E1121_PHY_LED_DEF);
-	if (err < 0)
-		return err;
-
-	/* Set marvell,reg-init configuration from device tree */
-	return marvell_config_init(phydev);
-}
-
 static int m88e1318_config_init(struct phy_device *phydev)
 {
 	if (phy_interrupt_is_valid(phydev)) {
@@ -841,7 +859,7 @@ static int m88e1318_config_init(struct phy_device *phydev)
 			return err;
 	}
 
-	return m88e1121_config_init(phydev);
+	return marvell_config_init(phydev);
 }
 
 static int m88e1510_config_init(struct phy_device *phydev)
@@ -2087,7 +2105,7 @@ static struct phy_driver marvell_drivers[] = {
 		.features = PHY_GBIT_FEATURES,
 		.flags = PHY_HAS_INTERRUPT,
 		.probe = &m88e1121_probe,
-		.config_init = &m88e1121_config_init,
+		.config_init = &marvell_config_init,
 		.config_aneg = &m88e1121_config_aneg,
 		.read_status = &marvell_read_status,
 		.ack_interrupt = &marvell_ack_interrupt,
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 537297d2b4b4..6c9b24fe3148 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -514,7 +514,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phy_interrupt_is_valid(phydev) && (phydev->state == PHY_AN)) {
+	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index bd0f339f69fd..b9f5f40a7ac1 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1724,11 +1724,8 @@ EXPORT_SYMBOL(genphy_loopback);
 
 static int __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	/* The default values for phydev->supported are provided by the PHY
-	 * driver "features" member, we want to reset to sane defaults first
-	 * before supporting higher speeds.
-	 */
-	phydev->supported &= PHY_DEFAULT_FEATURES;
+	phydev->supported &= ~(PHY_1000BT_FEATURES | PHY_100BT_FEATURES |
+			       PHY_10BT_FEATURES);
 
 	switch (max_speed) {
 	default:
diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c
index d437f4f5ed52..740655261e5b 100644
--- a/drivers/net/phy/sfp-bus.c
+++ b/drivers/net/phy/sfp-bus.c
@@ -349,7 +349,6 @@ static int sfp_register_bus(struct sfp_bus *bus)
 	}
 	if (bus->started)
 		bus->socket_ops->start(bus->sfp);
-	bus->netdev->sfp_bus = bus;
 	bus->registered = true;
 	return 0;
 }
@@ -364,7 +363,6 @@ static void sfp_unregister_bus(struct sfp_bus *bus)
 		if (bus->phydev && ops && ops->disconnect_phy)
 			ops->disconnect_phy(bus->upstream);
 	}
-	bus->netdev->sfp_bus = NULL;
 	bus->registered = false;
 }
 
@@ -436,6 +434,14 @@ void sfp_upstream_stop(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_upstream_stop);
 
+static void sfp_upstream_clear(struct sfp_bus *bus)
+{
+	bus->upstream_ops = NULL;
+	bus->upstream = NULL;
+	bus->netdev->sfp_bus = NULL;
+	bus->netdev = NULL;
+}
+
 /**
  * sfp_register_upstream() - Register the neighbouring device
  * @fwnode: firmware node for the SFP bus
@@ -461,9 +467,13 @@ struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode,
 		bus->upstream_ops = ops;
 		bus->upstream = upstream;
 		bus->netdev = ndev;
+		ndev->sfp_bus = bus;
 
-		if (bus->sfp)
+		if (bus->sfp) {
 			ret = sfp_register_bus(bus);
+			if (ret)
+				sfp_upstream_clear(bus);
+		}
 		rtnl_unlock();
 	}
 
@@ -488,8 +498,7 @@ void sfp_unregister_upstream(struct sfp_bus *bus)
 	rtnl_lock();
 	if (bus->sfp)
 		sfp_unregister_bus(bus);
-	bus->upstream = NULL;
-	bus->netdev = NULL;
+	sfp_upstream_clear(bus);
 	rtnl_unlock();
 
 	sfp_bus_put(bus);
@@ -561,6 +570,13 @@ void sfp_module_remove(struct sfp_bus *bus)
 }
 EXPORT_SYMBOL_GPL(sfp_module_remove);
 
+static void sfp_socket_clear(struct sfp_bus *bus)
+{
+	bus->sfp_dev = NULL;
+	bus->sfp = NULL;
+	bus->socket_ops = NULL;
+}
+
 struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
 				    const struct sfp_socket_ops *ops)
 {
@@ -573,8 +589,11 @@ struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
 		bus->sfp = sfp;
 		bus->socket_ops = ops;
 
-		if (bus->netdev)
+		if (bus->netdev) {
 			ret = sfp_register_bus(bus);
+			if (ret)
+				sfp_socket_clear(bus);
+		}
 		rtnl_unlock();
 	}
 
@@ -592,9 +611,7 @@ void sfp_unregister_socket(struct sfp_bus *bus)
 	rtnl_lock();
 	if (bus->netdev)
 		sfp_unregister_bus(bus);
-	bus->sfp_dev = NULL;
-	bus->sfp = NULL;
-	bus->socket_ops = NULL;
+	sfp_socket_clear(bus);
 	rtnl_unlock();
 
 	sfp_bus_put(bus);
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a192a017cc68..f5727baac84a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1688,7 +1688,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		case XDP_TX:
 			get_page(alloc_frag->page);
 			alloc_frag->offset += buflen;
-			if (tun_xdp_tx(tun->dev, &xdp))
+			if (tun_xdp_tx(tun->dev, &xdp) < 0)
 				goto err_redirect;
 			rcu_read_unlock();
 			local_bh_enable();
diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 3d4f7959dabb..b1b3d8f7e67d 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -642,10 +642,12 @@ static void ax88772_restore_phy(struct usbnet *dev)
 				     priv->presvd_phy_advertise);
 
 		/* Restore BMCR */
+		if (priv->presvd_phy_bmcr & BMCR_ANENABLE)
+			priv->presvd_phy_bmcr |= BMCR_ANRESTART;
+
 		asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR,
 				     priv->presvd_phy_bmcr);
 
-		mii_nway_restart(&dev->mii);
 		priv->presvd_phy_advertise = 0;
 		priv->presvd_phy_bmcr = 0;
 	}
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 8dff87ec6d99..ed10d49eb5e0 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -64,6 +64,7 @@
 #define DEFAULT_RX_CSUM_ENABLE		(true)
 #define DEFAULT_TSO_CSUM_ENABLE		(true)
 #define DEFAULT_VLAN_FILTER_ENABLE	(true)
+#define DEFAULT_VLAN_RX_OFFLOAD		(true)
 #define TX_OVERHEAD			(8)
 #define RXW_PADDING			2
 
@@ -2298,7 +2299,7 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu)
 	if ((ll_mtu % dev->maxpacket) == 0)
 		return -EDOM;
 
-	ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + ETH_HLEN);
+	ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN);
 
 	netdev->mtu = new_mtu;
 
@@ -2364,6 +2365,11 @@ static int lan78xx_set_features(struct net_device *netdev,
 	}
 
 	if (features & NETIF_F_HW_VLAN_CTAG_RX)
+		pdata->rfe_ctl |= RFE_CTL_VLAN_STRIP_;
+	else
+		pdata->rfe_ctl &= ~RFE_CTL_VLAN_STRIP_;
+
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
 		pdata->rfe_ctl |= RFE_CTL_VLAN_FILTER_;
 	else
 		pdata->rfe_ctl &= ~RFE_CTL_VLAN_FILTER_;
@@ -2587,7 +2593,8 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	buf |= FCT_TX_CTL_EN_;
 	ret = lan78xx_write_reg(dev, FCT_TX_CTL, buf);
 
-	ret = lan78xx_set_rx_max_frame_length(dev, dev->net->mtu + ETH_HLEN);
+	ret = lan78xx_set_rx_max_frame_length(dev,
+					      dev->net->mtu + VLAN_ETH_HLEN);
 
 	ret = lan78xx_read_reg(dev, MAC_RX, &buf);
 	buf |= MAC_RX_RXEN_;
@@ -2975,6 +2982,12 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf)
 	if (DEFAULT_TSO_CSUM_ENABLE)
 		dev->net->features |= NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_SG;
 
+	if (DEFAULT_VLAN_RX_OFFLOAD)
+		dev->net->features |= NETIF_F_HW_VLAN_CTAG_RX;
+
+	if (DEFAULT_VLAN_FILTER_ENABLE)
+		dev->net->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
 	dev->net->hw_features = dev->net->features;
 
 	ret = lan78xx_setup_irq_domain(dev);
@@ -3039,8 +3052,13 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev,
 				    struct sk_buff *skb,
 				    u32 rx_cmd_a, u32 rx_cmd_b)
 {
+	/* HW Checksum offload appears to be flawed if used when not stripping
+	 * VLAN headers. Drop back to S/W checksums under these conditions.
+	 */
 	if (!(dev->net->features & NETIF_F_RXCSUM) ||
-	    unlikely(rx_cmd_a & RX_CMD_A_ICSM_)) {
+	    unlikely(rx_cmd_a & RX_CMD_A_ICSM_) ||
+	    ((rx_cmd_a & RX_CMD_A_FVTG_) &&
+	     !(dev->net->features & NETIF_F_HW_VLAN_CTAG_RX))) {
 		skb->ip_summed = CHECKSUM_NONE;
 	} else {
 		skb->csum = ntohs((u16)(rx_cmd_b >> RX_CMD_B_CSUM_SHIFT_));
@@ -3048,6 +3066,16 @@ static void lan78xx_rx_csum_offload(struct lan78xx_net *dev,
 	}
 }
 
+static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev,
+				    struct sk_buff *skb,
+				    u32 rx_cmd_a, u32 rx_cmd_b)
+{
+	if ((dev->net->features & NETIF_F_HW_VLAN_CTAG_RX) &&
+	    (rx_cmd_a & RX_CMD_A_FVTG_))
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       (rx_cmd_b & 0xffff));
+}
+
 static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb)
 {
 	int		status;
@@ -3112,6 +3140,8 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb)
 			if (skb->len == size) {
 				lan78xx_rx_csum_offload(dev, skb,
 							rx_cmd_a, rx_cmd_b);
+				lan78xx_rx_vlan_offload(dev, skb,
+							rx_cmd_a, rx_cmd_b);
 
 				skb_trim(skb, skb->len - 4); /* remove fcs */
 				skb->truesize = size + sizeof(struct sk_buff);
@@ -3130,6 +3160,7 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb)
 			skb_set_tail_pointer(skb2, size);
 
 			lan78xx_rx_csum_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
+			lan78xx_rx_vlan_offload(dev, skb2, rx_cmd_a, rx_cmd_b);
 
 			skb_trim(skb2, skb2->len - 4); /* remove fcs */
 			skb2->truesize = size + sizeof(struct sk_buff);
@@ -3313,6 +3344,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev)
 	pkt_cnt = 0;
 	count = 0;
 	length = 0;
+	spin_lock_irqsave(&tqp->lock, flags);
 	for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) {
 		if (skb_is_gso(skb)) {
 			if (pkt_cnt) {
@@ -3321,7 +3353,8 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev)
 			}
 			count = 1;
 			length = skb->len - TX_OVERHEAD;
-			skb2 = skb_dequeue(tqp);
+			__skb_unlink(skb, tqp);
+			spin_unlock_irqrestore(&tqp->lock, flags);
 			goto gso_skb;
 		}
 
@@ -3330,6 +3363,7 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev)
 		skb_totallen = skb->len + roundup(skb_totallen, sizeof(u32));
 		pkt_cnt++;
 	}
+	spin_unlock_irqrestore(&tqp->lock, flags);
 
 	/* copy to a single skb */
 	skb = alloc_skb(skb_totallen, GFP_ATOMIC);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 8fac8e132c5b..cb0cc30c3d6a 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1246,13 +1246,14 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b3, 8)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card (rev3) */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
-	{QMI_FIXED_INTF(0x413c, 0x81d7, 1)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
 	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x9d1d, 1)},	/* HP lt4120 Snapdragon X5 LTE */
 	{QMI_FIXED_INTF(0x22de, 0x9061, 3)},	/* WeTelecom WPD-600N */
 	{QMI_QUIRK_SET_DTR(0x1e0e, 0x9001, 5)},	/* SIMCom 7100E, 7230E, 7600E ++ */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0125, 4)},	/* Quectel EC25, EC20 R2.0  Mini PCIe */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)},	/* Quectel EC21 Mini PCIe */
+	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)},	/* Quectel EG91 */
 	{QMI_FIXED_INTF(0x2c7c, 0x0296, 4)},	/* Quectel BG96 */
 	{QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)},	/* Quectel EP06 Mini PCIe */
 
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 86f7196f9d91..2a58607a6aea 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -3962,7 +3962,8 @@ static int rtl8152_close(struct net_device *netdev)
 #ifdef CONFIG_PM_SLEEP
 	unregister_pm_notifier(&tp->pm_notifier);
 #endif
-	napi_disable(&tp->napi);
+	if (!test_bit(RTL8152_UNPLUG, &tp->flags))
+		napi_disable(&tp->napi);
 	clear_bit(WORK_ENABLE, &tp->flags);
 	usb_kill_urb(tp->intr_urb);
 	cancel_delayed_work_sync(&tp->schedule);
diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 5f565bd574da..48ba80a8ca5c 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -681,7 +681,7 @@ static void rtl8150_set_multicast(struct net_device *netdev)
 		   (netdev->flags & IFF_ALLMULTI)) {
 		rx_creg &= 0xfffe;
 		rx_creg |= 0x0002;
-		dev_info(&netdev->dev, "%s: allmulti set\n", netdev->name);
+		dev_dbg(&netdev->dev, "%s: allmulti set\n", netdev->name);
 	} else {
 		/* ~RX_MULTICAST, ~RX_PROMISCUOUS */
 		rx_creg &= 0x00fc;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 7a6a1fe79309..05553d252446 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -82,6 +82,9 @@ static bool turbo_mode = true;
 module_param(turbo_mode, bool, 0644);
 MODULE_PARM_DESC(turbo_mode, "Enable multiple frames per Rx transaction");
 
+static int smsc75xx_link_ok_nopm(struct usbnet *dev);
+static int smsc75xx_phy_gig_workaround(struct usbnet *dev);
+
 static int __must_check __smsc75xx_read_reg(struct usbnet *dev, u32 index,
 					    u32 *data, int in_pm)
 {
@@ -852,6 +855,9 @@ static int smsc75xx_phy_initialize(struct usbnet *dev)
 		return -EIO;
 	}
 
+	/* phy workaround for gig link */
+	smsc75xx_phy_gig_workaround(dev);
+
 	smsc75xx_mdio_write(dev->net, dev->mii.phy_id, MII_ADVERTISE,
 		ADVERTISE_ALL | ADVERTISE_CSMA | ADVERTISE_PAUSE_CAP |
 		ADVERTISE_PAUSE_ASYM);
@@ -987,6 +993,62 @@ static int smsc75xx_wait_ready(struct usbnet *dev, int in_pm)
 	return -EIO;
 }
 
+static int smsc75xx_phy_gig_workaround(struct usbnet *dev)
+{
+	struct mii_if_info *mii = &dev->mii;
+	int ret = 0, timeout = 0;
+	u32 buf, link_up = 0;
+
+	/* Set the phy in Gig loopback */
+	smsc75xx_mdio_write(dev->net, mii->phy_id, MII_BMCR, 0x4040);
+
+	/* Wait for the link up */
+	do {
+		link_up = smsc75xx_link_ok_nopm(dev);
+		usleep_range(10000, 20000);
+		timeout++;
+	} while ((!link_up) && (timeout < 1000));
+
+	if (timeout >= 1000) {
+		netdev_warn(dev->net, "Timeout waiting for PHY link up\n");
+		return -EIO;
+	}
+
+	/* phy reset */
+	ret = smsc75xx_read_reg(dev, PMT_CTL, &buf);
+	if (ret < 0) {
+		netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n", ret);
+		return ret;
+	}
+
+	buf |= PMT_CTL_PHY_RST;
+
+	ret = smsc75xx_write_reg(dev, PMT_CTL, buf);
+	if (ret < 0) {
+		netdev_warn(dev->net, "Failed to write PMT_CTL: %d\n", ret);
+		return ret;
+	}
+
+	timeout = 0;
+	do {
+		usleep_range(10000, 20000);
+		ret = smsc75xx_read_reg(dev, PMT_CTL, &buf);
+		if (ret < 0) {
+			netdev_warn(dev->net, "Failed to read PMT_CTL: %d\n",
+				    ret);
+			return ret;
+		}
+		timeout++;
+	} while ((buf & PMT_CTL_PHY_RST) && (timeout < 100));
+
+	if (timeout >= 100) {
+		netdev_warn(dev->net, "timeout waiting for PHY Reset\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int smsc75xx_reset(struct usbnet *dev)
 {
 	struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]);
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index b6c9a2af3732..53085c63277b 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -53,6 +53,10 @@ module_param(napi_tx, bool, 0644);
 /* Amount of XDP headroom to prepend to packets for use by xdp_adjust_head */
 #define VIRTIO_XDP_HEADROOM 256
 
+/* Separating two types of XDP xmit */
+#define VIRTIO_XDP_TX		BIT(0)
+#define VIRTIO_XDP_REDIR	BIT(1)
+
 /* RX packet size EWMA. The average packet size is used to determine the packet
  * buffer size when refilling RX rings. As the entire RX ring may be refilled
  * at once, the weight is chosen so that the EWMA will be insensitive to short-
@@ -582,7 +586,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
 				     unsigned int len,
-				     bool *xdp_xmit)
+				     unsigned int *xdp_xmit)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -654,14 +658,14 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_TX;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err)
 				goto err_xdp;
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			rcu_read_unlock();
 			goto xdp_xmit;
 		default:
@@ -723,7 +727,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *buf,
 					 void *ctx,
 					 unsigned int len,
-					 bool *xdp_xmit)
+					 unsigned int *xdp_xmit)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -818,7 +822,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					put_page(xdp_page);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_TX;
 			if (unlikely(xdp_page != page))
 				put_page(page);
 			rcu_read_unlock();
@@ -830,7 +834,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					put_page(xdp_page);
 				goto err_xdp;
 			}
-			*xdp_xmit = true;
+			*xdp_xmit |= VIRTIO_XDP_REDIR;
 			if (unlikely(xdp_page != page))
 				put_page(page);
 			rcu_read_unlock();
@@ -939,7 +943,8 @@ xdp_xmit:
 }
 
 static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx, bool *xdp_xmit)
+		       void *buf, unsigned int len, void **ctx,
+		       unsigned int *xdp_xmit)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -1232,7 +1237,8 @@ static void refill_work(struct work_struct *work)
 	}
 }
 
-static int virtnet_receive(struct receive_queue *rq, int budget, bool *xdp_xmit)
+static int virtnet_receive(struct receive_queue *rq, int budget,
+			   unsigned int *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	unsigned int len, received = 0, bytes = 0;
@@ -1321,7 +1327,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct send_queue *sq;
 	unsigned int received, qp;
-	bool xdp_xmit = false;
+	unsigned int xdp_xmit = 0;
 
 	virtnet_poll_cleantx(rq);
 
@@ -1331,12 +1337,14 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 	if (received < budget)
 		virtqueue_napi_complete(napi, rq->vq, received);
 
-	if (xdp_xmit) {
+	if (xdp_xmit & VIRTIO_XDP_REDIR)
+		xdp_do_flush_map();
+
+	if (xdp_xmit & VIRTIO_XDP_TX) {
 		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
 		     smp_processor_id();
 		sq = &vi->sq[qp];
 		virtqueue_kick(sq->vq);
-		xdp_do_flush_map();
 	}
 
 	return received;
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index aee0e60471f1..e857cb3335f6 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -623,9 +623,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 	flush = 0;
 
 out:
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
@@ -638,9 +636,62 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+					 const u8 *mac, __u16 state,
+					 __be32 src_vni, __u8 ndm_flags)
+{
+	struct vxlan_fdb *f;
+
+	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return NULL;
+	f->state = state;
+	f->flags = ndm_flags;
+	f->updated = f->used = jiffies;
+	f->vni = src_vni;
+	INIT_LIST_HEAD(&f->remotes);
+	memcpy(f->eth_addr, mac, ETH_ALEN);
+
+	return f;
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
+			    __u16 state, __be16 port, __be32 src_vni,
+			    __be32 vni, __u32 ifindex, __u8 ndm_flags,
+			    struct vxlan_fdb **fdb)
+{
+	struct vxlan_rdst *rd = NULL;
+	struct vxlan_fdb *f;
+	int rc;
+
+	if (vxlan->cfg.addrmax &&
+	    vxlan->addrcnt >= vxlan->cfg.addrmax)
+		return -ENOSPC;
+
+	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+	if (!f)
+		return -ENOMEM;
+
+	rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+	if (rc < 0) {
+		kfree(f);
+		return rc;
+	}
+
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+
+	*fdb = f;
+
+	return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
+			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
 			    __u32 ifindex, __u8 ndm_flags)
@@ -689,37 +740,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
-		if (vxlan->cfg.addrmax &&
-		    vxlan->addrcnt >= vxlan->cfg.addrmax)
-			return -ENOSPC;
-
 		/* Disallow replace to add a multicast entry */
 		if ((flags & NLM_F_REPLACE) &&
 		    (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
 			return -EOPNOTSUPP;
 
 		netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
-		f = kmalloc(sizeof(*f), GFP_ATOMIC);
-		if (!f)
-			return -ENOMEM;
-
-		notify = 1;
-		f->state = state;
-		f->flags = ndm_flags;
-		f->updated = f->used = jiffies;
-		f->vni = src_vni;
-		INIT_LIST_HEAD(&f->remotes);
-		memcpy(f->eth_addr, mac, ETH_ALEN);
-
-		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
-		if (rc < 0) {
-			kfree(f);
+		rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+				      vni, ifindex, ndm_flags, &f);
+		if (rc < 0)
 			return rc;
-		}
-
-		++vxlan->addrcnt;
-		hlist_add_head_rcu(&f->hlist,
-				   vxlan_fdb_head(vxlan, mac, src_vni));
+		notify = 1;
 	}
 
 	if (notify) {
@@ -743,13 +774,15 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+			      bool do_notify)
 {
 	netdev_dbg(vxlan->dev,
 		    "delete %pM\n", f->eth_addr);
 
 	--vxlan->addrcnt;
-	vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+	if (do_notify)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
 
 	hlist_del_rcu(&f->hlist);
 	call_rcu(&f->rcu, vxlan_fdb_free);
@@ -865,7 +898,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EAFNOSUPPORT;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex, ndm->ndm_flags);
 	spin_unlock_bh(&vxlan->hash_lock);
 
@@ -899,7 +932,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 		goto out;
 	}
 
-	vxlan_fdb_destroy(vxlan, f);
+	vxlan_fdb_destroy(vxlan, f, true);
 
 out:
 	return 0;
@@ -1008,7 +1041,7 @@ static bool vxlan_snoop(struct net_device *dev,
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
-			vxlan_fdb_create(vxlan, src_mac, src_ip,
+			vxlan_fdb_update(vxlan, src_mac, src_ip,
 					 NUD_REACHABLE,
 					 NLM_F_EXCL|NLM_F_CREATE,
 					 vxlan->cfg.dst_port,
@@ -2366,7 +2399,7 @@ static void vxlan_cleanup(struct timer_list *t)
 					   "garbage collect %pM\n",
 					   f->eth_addr);
 				f->state = NUD_STALE;
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
@@ -2417,7 +2450,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 	spin_lock_bh(&vxlan->hash_lock);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
-		vxlan_fdb_destroy(vxlan, f);
+		vxlan_fdb_destroy(vxlan, f, true);
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
@@ -2471,7 +2504,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
@@ -3162,6 +3195,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
@@ -3175,24 +3209,35 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 		err = vxlan_fdb_create(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
 				       vxlan->cfg.dst_port,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
+				       NTF_SELF, &f);
 		if (err)
 			return err;
 	}
 
 	err = register_netdevice(dev);
+	if (err)
+		goto errout;
+
+	err = rtnl_configure_link(dev, NULL);
 	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
+		unregister_netdevice(dev);
+		goto errout;
 	}
 
+	/* notify default fdb entry */
+	if (f)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
+errout:
+	if (f)
+		vxlan_fdb_destroy(vxlan, f, false);
+	return err;
 }
 
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
@@ -3427,6 +3472,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct vxlan_rdst old_dst;
 	struct vxlan_config conf;
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_nl2conf(tb, data,
@@ -3455,16 +3501,16 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 			err = vxlan_fdb_create(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
-					       NLM_F_CREATE | NLM_F_APPEND,
 					       vxlan->cfg.dst_port,
 					       dst->remote_vni,
 					       dst->remote_vni,
 					       dst->remote_ifindex,
-					       NTF_SELF);
+					       NTF_SELF, &f);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
 			}
+			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
 		}
 		spin_unlock_bh(&vxlan->hash_lock);
 	}
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index e9c2fb318c03..836e0a47b94a 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -6058,8 +6058,19 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 			   ath10k_mac_max_vht_nss(vht_mcs_mask)));
 
 	if (changed & IEEE80211_RC_BW_CHANGED) {
-		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d\n",
-			   sta->addr, bw);
+		enum wmi_phy_mode mode;
+
+		mode = chan_to_phymode(&def);
+		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n",
+				sta->addr, bw, mode);
+
+		err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
+				WMI_PEER_PHYMODE, mode);
+		if (err) {
+			ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n",
+					sta->addr, mode, err);
+			goto exit;
+		}
 
 		err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
 						WMI_PEER_CHAN_WIDTH, bw);
@@ -6100,6 +6111,7 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 				    sta->addr);
 	}
 
+exit:
 	mutex_unlock(&ar->conf_mutex);
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index b48db54e9865..d68afb65402a 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -6144,6 +6144,7 @@ enum wmi_peer_param {
 	WMI_PEER_NSS        = 0x5,
 	WMI_PEER_USE_4ADDR  = 0x6,
 	WMI_PEER_DEBUG      = 0xa,
+	WMI_PEER_PHYMODE    = 0xd,
 	WMI_PEER_DUMMY_VAR  = 0xff, /* dummy parameter for STA PS workaround */
 };
 
diff --git a/drivers/net/wireless/ath/wcn36xx/testmode.c b/drivers/net/wireless/ath/wcn36xx/testmode.c
index 1279064a3b71..51a038022c8b 100644
--- a/drivers/net/wireless/ath/wcn36xx/testmode.c
+++ b/drivers/net/wireless/ath/wcn36xx/testmode.c
@@ -1,4 +1,4 @@
-/*
+/*
  * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index c99a191e8d69..a907d7b065fa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -4296,6 +4296,13 @@ void brcmf_sdio_remove(struct brcmf_sdio *bus)
 	brcmf_dbg(TRACE, "Enter\n");
 
 	if (bus) {
+		/* Stop watchdog task */
+		if (bus->watchdog_tsk) {
+			send_sig(SIGTERM, bus->watchdog_tsk, 1);
+			kthread_stop(bus->watchdog_tsk);
+			bus->watchdog_tsk = NULL;
+		}
+
 		/* De-register interrupt handler */
 		brcmf_sdiod_intr_unregister(bus->sdiodev);
 
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 6e3cf9817730..88f4c89f89ba 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -644,11 +644,6 @@ static void mwifiex_usb_disconnect(struct usb_interface *intf)
 					 MWIFIEX_FUNC_SHUTDOWN);
 	}
 
-	if (adapter->workqueue)
-		flush_workqueue(adapter->workqueue);
-
-	mwifiex_usb_free(card);
-
 	mwifiex_dbg(adapter, FATAL,
 		    "%s: removing card\n", __func__);
 	mwifiex_remove_card(adapter);
@@ -1356,6 +1351,8 @@ static void mwifiex_unregister_dev(struct mwifiex_adapter *adapter)
 {
 	struct usb_card_rec *card = (struct usb_card_rec *)adapter->card;
 
+	mwifiex_usb_free(card);
+
 	mwifiex_usb_cleanup_tx_aggr(adapter);
 
 	card->adapter = NULL;
diff --git a/drivers/net/wireless/mediatek/mt7601u/phy.c b/drivers/net/wireless/mediatek/mt7601u/phy.c
index 9d2f9a776ef1..b804abd464ae 100644
--- a/drivers/net/wireless/mediatek/mt7601u/phy.c
+++ b/drivers/net/wireless/mediatek/mt7601u/phy.c
@@ -986,13 +986,15 @@ static void mt7601u_agc_tune(struct mt7601u_dev *dev)
 	 */
 	spin_lock_bh(&dev->con_mon_lock);
 	avg_rssi = ewma_rssi_read(&dev->avg_rssi);
-	WARN_ON_ONCE(avg_rssi == 0);
+	spin_unlock_bh(&dev->con_mon_lock);
+	if (avg_rssi == 0)
+		return;
+
 	avg_rssi = -avg_rssi;
 	if (avg_rssi <= -70)
 		val -= 0x20;
 	else if (avg_rssi <= -60)
 		val -= 0x10;
-	spin_unlock_bh(&dev->con_mon_lock);
 
 	if (val != mt7601u_bbp_rr(dev, 66))
 		mt7601u_bbp_wr(dev, 66, val);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 220e2b710208..ae0ca8006849 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -654,8 +654,7 @@ qtnf_disconnect(struct wiphy *wiphy, struct net_device *dev,
 	vif = qtnf_mac_get_base_vif(mac);
 	if (!vif) {
 		pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
-		ret = -EFAULT;
-		goto out;
+		return -EFAULT;
 	}
 
 	if (vif->wdev.iftype != NL80211_IFTYPE_STATION) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 39c817eddd78..54c9f6ab0c8c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -484,18 +484,21 @@ static void _rtl_init_deferred_work(struct ieee80211_hw *hw)
 
 }
 
-void rtl_deinit_deferred_work(struct ieee80211_hw *hw)
+void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq)
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	del_timer_sync(&rtlpriv->works.watchdog_timer);
 
-	cancel_delayed_work(&rtlpriv->works.watchdog_wq);
-	cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
-	cancel_delayed_work(&rtlpriv->works.ps_work);
-	cancel_delayed_work(&rtlpriv->works.ps_rfon_wq);
-	cancel_delayed_work(&rtlpriv->works.fwevt_wq);
-	cancel_delayed_work(&rtlpriv->works.c2hcmd_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.watchdog_wq);
+	if (ips_wq)
+		cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
+	else
+		cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.ps_work);
+	cancel_delayed_work_sync(&rtlpriv->works.ps_rfon_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.fwevt_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.c2hcmd_wq);
 }
 EXPORT_SYMBOL_GPL(rtl_deinit_deferred_work);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/base.h b/drivers/net/wireless/realtek/rtlwifi/base.h
index 912f205779c3..a7ae40eaa3cd 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.h
+++ b/drivers/net/wireless/realtek/rtlwifi/base.h
@@ -121,7 +121,7 @@ void rtl_init_rfkill(struct ieee80211_hw *hw);
 void rtl_deinit_rfkill(struct ieee80211_hw *hw);
 
 void rtl_watch_dog_timer_callback(struct timer_list *t);
-void rtl_deinit_deferred_work(struct ieee80211_hw *hw);
+void rtl_deinit_deferred_work(struct ieee80211_hw *hw, bool ips_wq);
 
 bool rtl_action_proc(struct ieee80211_hw *hw, struct sk_buff *skb, u8 is_tx);
 int rtlwifi_rate_mapping(struct ieee80211_hw *hw, bool isht,
diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c
index cfea57efa7f4..4bf7967590ca 100644
--- a/drivers/net/wireless/realtek/rtlwifi/core.c
+++ b/drivers/net/wireless/realtek/rtlwifi/core.c
@@ -130,7 +130,6 @@ found_alt:
 		       firmware->size);
 		rtlpriv->rtlhal.wowlan_fwsize = firmware->size;
 	}
-	rtlpriv->rtlhal.fwsize = firmware->size;
 	release_firmware(firmware);
 }
 
@@ -196,7 +195,7 @@ static void rtl_op_stop(struct ieee80211_hw *hw)
 		/* reset sec info */
 		rtl_cam_reset_sec_info(hw);
 
-		rtl_deinit_deferred_work(hw);
+		rtl_deinit_deferred_work(hw, false);
 	}
 	rtlpriv->intf_ops->adapter_stop(hw);
 
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index ae13bcfb3bf0..5d1fda16fc8c 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -2377,7 +2377,7 @@ void rtl_pci_disconnect(struct pci_dev *pdev)
 		ieee80211_unregister_hw(hw);
 		rtlmac->mac80211_registered = 0;
 	} else {
-		rtl_deinit_deferred_work(hw);
+		rtl_deinit_deferred_work(hw, false);
 		rtlpriv->intf_ops->adapter_stop(hw);
 	}
 	rtlpriv->cfg->ops->disable_interrupt(hw);
diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c
index 71af24e2e051..479a4cfc245d 100644
--- a/drivers/net/wireless/realtek/rtlwifi/ps.c
+++ b/drivers/net/wireless/realtek/rtlwifi/ps.c
@@ -71,7 +71,7 @@ bool rtl_ps_disable_nic(struct ieee80211_hw *hw)
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 
 	/*<1> Stop all timer */
-	rtl_deinit_deferred_work(hw);
+	rtl_deinit_deferred_work(hw, true);
 
 	/*<2> Disable Interrupt */
 	rtlpriv->cfg->ops->disable_interrupt(hw);
@@ -292,7 +292,7 @@ void rtl_ips_nic_on(struct ieee80211_hw *hw)
 	struct rtl_ps_ctl *ppsc = rtl_psc(rtl_priv(hw));
 	enum rf_pwrstate rtstate;
 
-	cancel_delayed_work(&rtlpriv->works.ips_nic_off_wq);
+	cancel_delayed_work_sync(&rtlpriv->works.ips_nic_off_wq);
 
 	mutex_lock(&rtlpriv->locks.ips_mutex);
 	if (ppsc->inactiveps) {
diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
index f9faffc498bc..2ac5004d7a40 100644
--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
+++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
@@ -1132,7 +1132,7 @@ void rtl_usb_disconnect(struct usb_interface *intf)
 		ieee80211_unregister_hw(hw);
 		rtlmac->mac80211_registered = 0;
 	} else {
-		rtl_deinit_deferred_work(hw);
+		rtl_deinit_deferred_work(hw, false);
 		rtlpriv->intf_ops->adapter_stop(hw);
 	}
 	/*deinit rfkill */
diff --git a/drivers/nvdimm/claim.c b/drivers/nvdimm/claim.c
index 2e96b34bc936..fb667bf469c7 100644
--- a/drivers/nvdimm/claim.c
+++ b/drivers/nvdimm/claim.c
@@ -278,6 +278,7 @@ static int nsio_rw_bytes(struct nd_namespace_common *ndns,
 			return -EIO;
 		if (memcpy_mcsafe(buf, nsio->addr + offset, size) != 0)
 			return -EIO;
+		return 0;
 	}
 
 	if (unlikely(is_bad_pmem(&nsio->bb, sector, sz_align))) {
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 46df030b2c3f..bf65501e6ed6 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -100,6 +100,22 @@ static struct class *nvme_subsys_class;
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					   unsigned nsid);
+
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+	/*
+	 * Revalidating a dead namespace sets capacity to 0. This will end
+	 * buffered writers dirtying pages that can't be synced.
+	 */
+	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+		return;
+	revalidate_disk(ns->disk);
+	blk_set_queue_dying(ns->queue);
+	/* Forcibly unquiesce queues to avoid blocking dispatch */
+	blk_mq_unquiesce_queue(ns->queue);
+}
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 {
@@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
-	u32 result;
+	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
 	int status;
 
-	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
-			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	if (!supported_aens)
+		return;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
+			NULL, 0, &result);
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
-			 ctrl->oaes & NVME_AEN_SUPPORTED);
+			 supported_aens);
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns, *next;
-	LIST_HEAD(rm_list);
+	struct nvme_ns *ns;
 
-	down_write(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
-			list_move_tail(&ns->list, &rm_list);
-		}
-	}
-	up_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		if (ns->disk && nvme_revalidate_disk(ns->disk))
+			nvme_set_queue_dying(ns);
+	up_read(&ctrl->namespaces_rwsem);
 
-	list_for_each_entry_safe(ns, next, &rm_list, list)
-		nvme_ns_remove(ns);
+	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
+			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -3138,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
+		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
 			list_move_tail(&ns->list, &rm_list);
 	}
 	up_write(&ctrl->namespaces_rwsem);
@@ -3542,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 	if (ctrl->admin_q)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		/*
-		 * Revalidating a dead namespace sets capacity to 0. This will
-		 * end buffered writers dirtying pages that can't be synced.
-		 */
-		if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-			continue;
-		revalidate_disk(ns->disk);
-		blk_set_queue_dying(ns->queue);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		nvme_set_queue_dying(ns);
 
-		/* Forcibly unquiesce queues to avoid blocking dispatch */
-		blk_mq_unquiesce_queue(ns->queue);
-	}
 	up_read(&ctrl->namespaces_rwsem);
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 903eb4545e26..f7efe5a58cc7 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -539,14 +539,18 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 /*
  * For something we're not in a state to send to the device the default action
  * is to busy it and retry it after the controller state is recovered.  However,
- * anything marked for failfast or nvme multipath is immediately failed.
+ * if the controller is deleting or if anything is marked for failfast or
+ * nvme multipath it is immediately failed.
  *
  * Note: commands used to initialize the controller will be marked for failfast.
  * Note: nvme cli/ioctl commands are marked for failfast.
  */
-blk_status_t nvmf_fail_nonready_command(struct request *rq)
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq)
 {
-	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+	if (ctrl->state != NVME_CTRL_DELETING &&
+	    ctrl->state != NVME_CTRL_DEAD &&
+	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 	return BLK_STS_IOERR;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index e1818a27aa2d..aa2fdb2a2e8f 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -162,7 +162,8 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_fail_nonready_command(struct request *rq);
+blk_status_t nvmf_fail_nonready_command(struct nvme_ctrl *ctrl,
+		struct request *rq);
 bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		bool queue_live);
 
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 41d45a1b5c62..9bac912173ba 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -2272,7 +2272,7 @@ nvme_fc_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	if (ctrl->rport->remoteport.port_state != FC_OBJSTATE_ONLINE ||
 	    !nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	ret = nvme_setup_cmd(ns, rq, sqe);
 	if (ret)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ba943f211687..ddd441b1516a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2556,11 +2556,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	quirks |= check_vendor_combination_bug(pdev);
 
-	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
-			quirks);
-	if (result)
-		goto release_pools;
-
 	/*
 	 * Double check that our mempool alloc size will cover the biggest
 	 * command we support.
@@ -2578,6 +2573,11 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto release_pools;
 	}
 
+	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
+			quirks);
+	if (result)
+		goto release_mempool;
+
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	nvme_get_ctrl(&dev->ctrl);
@@ -2585,6 +2585,8 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+ release_mempool:
+	mempool_destroy(dev->iod_mempool);
  release_pools:
 	nvme_release_prp_pools(dev);
  unmap:
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 518c5b09038c..66ec5985c9f3 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1639,7 +1639,7 @@ static blk_status_t nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
 	WARN_ON_ONCE(rq->tag < 0);
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, rq, queue_ready))
-		return nvmf_fail_nonready_command(rq);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, rq);
 
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index d3f3b3ec4d1a..ebea1373d1b7 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -282,6 +282,7 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 {
 	struct nvmet_ns *ns = to_nvmet_ns(item);
 	struct nvmet_subsys *subsys = ns->subsys;
+	size_t len;
 	int ret;
 
 	mutex_lock(&subsys->lock);
@@ -289,10 +290,14 @@ static ssize_t nvmet_ns_device_path_store(struct config_item *item,
 	if (ns->enabled)
 		goto out_unlock;
 
-	kfree(ns->device_path);
+	ret = -EINVAL;
+	len = strcspn(page, "\n");
+	if (!len)
+		goto out_unlock;
 
+	kfree(ns->device_path);
 	ret = -ENOMEM;
-	ns->device_path = kstrndup(page, strcspn(page, "\n"), GFP_KERNEL);
+	ns->device_path = kstrndup(page, len, GFP_KERNEL);
 	if (!ns->device_path)
 		goto out_unlock;
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 74d4b785d2da..9838103f2d62 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -339,7 +339,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 		goto out_unlock;
 
 	ret = nvmet_bdev_ns_enable(ns);
-	if (ret)
+	if (ret == -ENOTBLK)
 		ret = nvmet_file_ns_enable(ns);
 	if (ret)
 		goto out_unlock;
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 408279cb6f2c..29b4b236afd8 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -58,8 +58,8 @@ struct nvmet_fc_ls_iod {
 	struct work_struct		work;
 } __aligned(sizeof(unsigned long long));
 
+/* desired maximum for a single sequence - if sg list allows it */
 #define NVMET_FC_MAX_SEQ_LENGTH		(256 * 1024)
-#define NVMET_FC_MAX_XFR_SGENTS		(NVMET_FC_MAX_SEQ_LENGTH / PAGE_SIZE)
 
 enum nvmet_fcp_datadir {
 	NVMET_FCP_NODATA,
@@ -74,6 +74,7 @@ struct nvmet_fc_fcp_iod {
 	struct nvme_fc_cmd_iu		cmdiubuf;
 	struct nvme_fc_ersp_iu		rspiubuf;
 	dma_addr_t			rspdma;
+	struct scatterlist		*next_sg;
 	struct scatterlist		*data_sg;
 	int				data_sg_cnt;
 	u32				offset;
@@ -1025,8 +1026,7 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
 	INIT_LIST_HEAD(&newrec->assoc_list);
 	kref_init(&newrec->ref);
 	ida_init(&newrec->assoc_cnt);
-	newrec->max_sg_cnt = min_t(u32, NVMET_FC_MAX_XFR_SGENTS,
-					template->max_sgl_segments);
+	newrec->max_sg_cnt = template->max_sgl_segments;
 
 	ret = nvmet_fc_alloc_ls_iodlist(newrec);
 	if (ret) {
@@ -1722,6 +1722,7 @@ nvmet_fc_alloc_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
 				((fod->io_dir == NVMET_FCP_WRITE) ?
 					DMA_FROM_DEVICE : DMA_TO_DEVICE));
 				/* note: write from initiator perspective */
+	fod->next_sg = fod->data_sg;
 
 	return 0;
 
@@ -1866,24 +1867,49 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
 				struct nvmet_fc_fcp_iod *fod, u8 op)
 {
 	struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+	struct scatterlist *sg = fod->next_sg;
 	unsigned long flags;
-	u32 tlen;
+	u32 remaininglen = fod->req.transfer_len - fod->offset;
+	u32 tlen = 0;
 	int ret;
 
 	fcpreq->op = op;
 	fcpreq->offset = fod->offset;
 	fcpreq->timeout = NVME_FC_TGTOP_TIMEOUT_SEC;
 
-	tlen = min_t(u32, tgtport->max_sg_cnt * PAGE_SIZE,
-			(fod->req.transfer_len - fod->offset));
+	/*
+	 * for next sequence:
+	 *  break at a sg element boundary
+	 *  attempt to keep sequence length capped at
+	 *    NVMET_FC_MAX_SEQ_LENGTH but allow sequence to
+	 *    be longer if a single sg element is larger
+	 *    than that amount. This is done to avoid creating
+	 *    a new sg list to use for the tgtport api.
+	 */
+	fcpreq->sg = sg;
+	fcpreq->sg_cnt = 0;
+	while (tlen < remaininglen &&
+	       fcpreq->sg_cnt < tgtport->max_sg_cnt &&
+	       tlen + sg_dma_len(sg) < NVMET_FC_MAX_SEQ_LENGTH) {
+		fcpreq->sg_cnt++;
+		tlen += sg_dma_len(sg);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen && fcpreq->sg_cnt == 0) {
+		fcpreq->sg_cnt++;
+		tlen += min_t(u32, sg_dma_len(sg), remaininglen);
+		sg = sg_next(sg);
+	}
+	if (tlen < remaininglen)
+		fod->next_sg = sg;
+	else
+		fod->next_sg = NULL;
+
 	fcpreq->transfer_length = tlen;
 	fcpreq->transferred_length = 0;
 	fcpreq->fcp_error = 0;
 	fcpreq->rsplen = 0;
 
-	fcpreq->sg = &fod->data_sg[fod->offset / PAGE_SIZE];
-	fcpreq->sg_cnt = DIV_ROUND_UP(tlen, PAGE_SIZE);
-
 	/*
 	 * If the last READDATA request: check if LLDD supports
 	 * combined xfr with response.
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d8d91f04bd7e..ae7586b8be07 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -162,7 +162,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 	blk_status_t ret;
 
 	if (!nvmf_check_ready(&queue->ctrl->ctrl, req, queue_ready))
-		return nvmf_fail_nonready_command(req);
+		return nvmf_fail_nonready_command(&queue->ctrl->ctrl, req);
 
 	ret = nvme_setup_cmd(ns, req, &iod->cmd);
 	if (ret)
diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
index b5b0cdc21d01..514d1dfc5630 100644
--- a/drivers/nvmem/core.c
+++ b/drivers/nvmem/core.c
@@ -936,6 +936,10 @@ struct nvmem_cell *nvmem_cell_get(struct device *dev, const char *cell_id)
 			return cell;
 	}
 
+	/* NULL cell_id only allowed for device tree; invalid otherwise */
+	if (!cell_id)
+		return ERR_PTR(-EINVAL);
+
 	return nvmem_cell_get_from_list(cell_id);
 }
 EXPORT_SYMBOL_GPL(nvmem_cell_get);
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 848f549164cd..466e3c8582f0 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -102,7 +102,7 @@ static u32 phandle_cache_mask;
  *   - the phandle lookup overhead reduction provided by the cache
  *     will likely be less
  */
-static void of_populate_phandle_cache(void)
+void of_populate_phandle_cache(void)
 {
 	unsigned long flags;
 	u32 cache_entries;
@@ -134,8 +134,7 @@ out:
 	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 }
 
-#ifndef CONFIG_MODULES
-static int __init of_free_phandle_cache(void)
+int of_free_phandle_cache(void)
 {
 	unsigned long flags;
 
@@ -148,6 +147,7 @@ static int __init of_free_phandle_cache(void)
 
 	return 0;
 }
+#if !defined(CONFIG_MODULES)
 late_initcall_sync(of_free_phandle_cache);
 #endif
 
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 891d780c076a..216175d11d3d 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -79,6 +79,8 @@ int of_resolve_phandles(struct device_node *tree);
 #if defined(CONFIG_OF_OVERLAY)
 void of_overlay_mutex_lock(void);
 void of_overlay_mutex_unlock(void);
+int of_free_phandle_cache(void);
+void of_populate_phandle_cache(void);
 #else
 static inline void of_overlay_mutex_lock(void) {};
 static inline void of_overlay_mutex_unlock(void) {};
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index 7baa53e5b1d7..eda57ef12fd0 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -804,6 +804,8 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree,
 		goto err_free_overlay_changeset;
 	}
 
+	of_populate_phandle_cache();
+
 	ret = __of_changeset_apply_notify(&ovcs->cset);
 	if (ret)
 		pr_err("overlay changeset entry notify error %d\n", ret);
@@ -1046,8 +1048,17 @@ int of_overlay_remove(int *ovcs_id)
 
 	list_del(&ovcs->ovcs_list);
 
+	/*
+	 * Disable phandle cache.  Avoids race condition that would arise
+	 * from removing cache entry when the associated node is deleted.
+	 */
+	of_free_phandle_cache();
+
 	ret_apply = 0;
 	ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
+
+	of_populate_phandle_cache();
+
 	if (ret) {
 		if (ret_apply)
 			devicetree_state_flags |= DTSF_REVERT_FAIL;
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 16f52c626b4b..91b0194240a5 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -58,7 +58,6 @@ config PCIE_DW_PLAT_HOST
 	depends on PCI && PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
 	select PCIE_DW_PLAT
-	default y
 	help
 	  Enables support for the PCIe controller in the Designware IP to
 	  work in host mode. There are two instances of PCIe controller in
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 781aa03aeede..29a05759a294 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -363,7 +363,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	resource_list_for_each_entry_safe(win, tmp, &bridge->windows) {
 		switch (resource_type(win->res)) {
 		case IORESOURCE_IO:
-			ret = pci_remap_iospace(win->res, pp->io_base);
+			ret = devm_pci_remap_iospace(dev, win->res,
+						     pp->io_base);
 			if (ret) {
 				dev_warn(dev, "Error %d: failed to map resource %pR\n",
 					 ret, win->res);
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index d3172d5d3d35..0fae816fba39 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -849,7 +849,7 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
 					     0,	0xF8000000, 0,
 					     lower_32_bits(res->start),
 					     OB_PCIE_IO);
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c
index a1ebe9ed441f..bf5ece5d9291 100644
--- a/drivers/pci/controller/pci-ftpci100.c
+++ b/drivers/pci/controller/pci-ftpci100.c
@@ -355,11 +355,13 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p)
 	irq = of_irq_get(intc, 0);
 	if (irq <= 0) {
 		dev_err(p->dev, "failed to get parent IRQ\n");
+		of_node_put(intc);
 		return irq ?: -EINVAL;
 	}
 
 	p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX,
 					     &faraday_pci_irqdomain_ops, p);
+	of_node_put(intc);
 	if (!p->irqdomain) {
 		dev_err(p->dev, "failed to create Gemini PCI IRQ domain\n");
 		return -EINVAL;
@@ -501,7 +503,7 @@ static int faraday_pci_probe(struct platform_device *pdev)
 				dev_err(dev, "illegal IO mem size\n");
 				return -EINVAL;
 			}
-			ret = pci_remap_iospace(io, io_base);
+			ret = devm_pci_remap_iospace(dev, io, io_base);
 			if (ret) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 ret, io);
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6cc5036ac83c..f6325f1a89e8 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1073,6 +1073,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	struct pci_bus *pbus;
 	struct pci_dev *pdev;
 	struct cpumask *dest;
+	unsigned long flags;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
 	struct {
@@ -1164,14 +1165,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		 * the channel callback directly when channel->target_cpu is
 		 * the current CPU. When the higher level interrupt code
 		 * calls us with interrupt enabled, let's add the
-		 * local_bh_disable()/enable() to avoid race.
+		 * local_irq_save()/restore() to avoid race:
+		 * hv_pci_onchannelcallback() can also run in tasklet.
 		 */
-		local_bh_disable();
+		local_irq_save(flags);
 
 		if (hbus->hdev->channel->target_cpu == smp_processor_id())
 			hv_pci_onchannelcallback(hbus);
 
-		local_bh_enable();
+		local_irq_restore(flags);
 
 		if (hpdev->state == hv_pcichild_ejecting) {
 			dev_err_once(&hbus->hdev->device,
diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c
index 68b8bfbdb867..d219404bad92 100644
--- a/drivers/pci/controller/pci-v3-semi.c
+++ b/drivers/pci/controller/pci-v3-semi.c
@@ -537,7 +537,7 @@ static int v3_pci_setup_resource(struct v3_pci *v3,
 		v3->io_bus_addr = io->start - win->offset;
 		dev_dbg(dev, "I/O window %pR, bus addr %pap\n",
 			io, &v3->io_bus_addr);
-		ret = pci_remap_iospace(io, io_base);
+		ret = devm_pci_remap_iospace(dev, io, io_base);
 		if (ret) {
 			dev_warn(dev,
 				 "error %d: failed to map resource %pR\n",
diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c
index 994f32061b32..f59ad2728c0b 100644
--- a/drivers/pci/controller/pci-versatile.c
+++ b/drivers/pci/controller/pci-versatile.c
@@ -82,7 +82,7 @@ static int versatile_pci_parse_request_of_pci_ranges(struct device *dev,
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c
index d854d67e873c..ffda3e8b4742 100644
--- a/drivers/pci/controller/pci-xgene.c
+++ b/drivers/pci/controller/pci-xgene.c
@@ -423,7 +423,7 @@ static int xgene_pcie_map_ranges(struct xgene_pcie_port *port,
 		case IORESOURCE_IO:
 			xgene_pcie_setup_ob_reg(port, res, OMR3BARL, io_base,
 						res->start - window->offset);
-			ret = pci_remap_iospace(res, io_base);
+			ret = devm_pci_remap_iospace(dev, res, io_base);
 			if (ret < 0)
 				return ret;
 			break;
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index 0baabe30858f..861dda69f366 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -1109,7 +1109,7 @@ static int mtk_pcie_request_resources(struct mtk_pcie *pcie)
 	if (err < 0)
 		return err;
 
-	pci_remap_iospace(&pcie->pio, pcie->io.start);
+	devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start);
 
 	return 0;
 }
diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c
index 874d75c9ee4a..c8febb009454 100644
--- a/drivers/pci/controller/pcie-rcar.c
+++ b/drivers/pci/controller/pcie-rcar.c
@@ -680,7 +680,11 @@ static int rcar_pcie_phy_init_gen3(struct rcar_pcie *pcie)
 	if (err)
 		return err;
 
-	return phy_power_on(pcie->phy);
+	err = phy_power_on(pcie->phy);
+	if (err)
+		phy_exit(pcie->phy);
+
+	return err;
 }
 
 static int rcar_msi_alloc(struct rcar_msi *chip)
@@ -1165,7 +1169,7 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 	if (rcar_pcie_hw_init(pcie)) {
 		dev_info(dev, "PCIe link down\n");
 		err = -ENODEV;
-		goto err_clk_disable;
+		goto err_phy_shutdown;
 	}
 
 	data = rcar_pci_read_reg(pcie, MACSR);
@@ -1177,7 +1181,7 @@ static int rcar_pcie_probe(struct platform_device *pdev)
 			dev_err(dev,
 				"failed to enable MSI support: %d\n",
 				err);
-			goto err_clk_disable;
+			goto err_phy_shutdown;
 		}
 	}
 
@@ -1191,6 +1195,12 @@ err_msi_teardown:
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		rcar_pcie_teardown_msi(pcie);
 
+err_phy_shutdown:
+	if (pcie->phy) {
+		phy_power_off(pcie->phy);
+		phy_exit(pcie->phy);
+	}
+
 err_clk_disable:
 	clk_disable_unprepare(pcie->bus_clk);
 
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index 6a4bbb5b3de0..fb32840ce8e6 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -559,7 +559,7 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie)
 							PCI_NUM_INTX,
 							&legacy_domain_ops,
 							pcie);
-
+	of_node_put(legacy_intc_node);
 	if (!pcie->legacy_irq_domain) {
 		dev_err(dev, "failed to create IRQ domain\n");
 		return -ENOMEM;
diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index b110a3a814e3..7b1389d8e2a5 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -509,6 +509,7 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 	port->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
 						 &intx_domain_ops,
 						 port);
+	of_node_put(pcie_intc_node);
 	if (!port->leg_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
 		return -ENODEV;
diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
index 523a8cab3bfb..825fa24427a3 100644
--- a/drivers/pci/endpoint/pci-epf-core.c
+++ b/drivers/pci/endpoint/pci-epf-core.c
@@ -137,6 +137,20 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar)
 }
 EXPORT_SYMBOL_GPL(pci_epf_alloc_space);
 
+static void pci_epf_remove_cfs(struct pci_epf_driver *driver)
+{
+	struct config_group *group, *tmp;
+
+	if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS))
+		return;
+
+	mutex_lock(&pci_epf_mutex);
+	list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry)
+		pci_ep_cfs_remove_epf_group(group);
+	list_del(&driver->epf_group);
+	mutex_unlock(&pci_epf_mutex);
+}
+
 /**
  * pci_epf_unregister_driver() - unregister the PCI EPF driver
  * @driver: the PCI EPF driver that has to be unregistered
@@ -145,17 +159,38 @@ EXPORT_SYMBOL_GPL(pci_epf_alloc_space);
  */
 void pci_epf_unregister_driver(struct pci_epf_driver *driver)
 {
-	struct config_group *group;
-
-	mutex_lock(&pci_epf_mutex);
-	list_for_each_entry(group, &driver->epf_group, group_entry)
-		pci_ep_cfs_remove_epf_group(group);
-	list_del(&driver->epf_group);
-	mutex_unlock(&pci_epf_mutex);
+	pci_epf_remove_cfs(driver);
 	driver_unregister(&driver->driver);
 }
 EXPORT_SYMBOL_GPL(pci_epf_unregister_driver);
 
+static int pci_epf_add_cfs(struct pci_epf_driver *driver)
+{
+	struct config_group *group;
+	const struct pci_epf_device_id *id;
+
+	if (!IS_ENABLED(CONFIG_PCI_ENDPOINT_CONFIGFS))
+		return 0;
+
+	INIT_LIST_HEAD(&driver->epf_group);
+
+	id = driver->id_table;
+	while (id->name[0]) {
+		group = pci_ep_cfs_add_epf_group(id->name);
+		if (IS_ERR(group)) {
+			pci_epf_remove_cfs(driver);
+			return PTR_ERR(group);
+		}
+
+		mutex_lock(&pci_epf_mutex);
+		list_add_tail(&group->group_entry, &driver->epf_group);
+		mutex_unlock(&pci_epf_mutex);
+		id++;
+	}
+
+	return 0;
+}
+
 /**
  * __pci_epf_register_driver() - register a new PCI EPF driver
  * @driver: structure representing PCI EPF driver
@@ -167,8 +202,6 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver,
 			      struct module *owner)
 {
 	int ret;
-	struct config_group *group;
-	const struct pci_epf_device_id *id;
 
 	if (!driver->ops)
 		return -EINVAL;
@@ -183,16 +216,7 @@ int __pci_epf_register_driver(struct pci_epf_driver *driver,
 	if (ret)
 		return ret;
 
-	INIT_LIST_HEAD(&driver->epf_group);
-
-	id = driver->id_table;
-	while (id->name[0]) {
-		group = pci_ep_cfs_add_epf_group(id->name);
-		mutex_lock(&pci_epf_mutex);
-		list_add_tail(&group->group_entry, &driver->epf_group);
-		mutex_unlock(&pci_epf_mutex);
-		id++;
-	}
+	pci_epf_add_cfs(driver);
 
 	return 0;
 }
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index d0d73dbbd5ca..0f04ae648cf1 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -575,6 +575,22 @@ void pci_iov_release(struct pci_dev *dev)
 }
 
 /**
+ * pci_iov_remove - clean up SR-IOV state after PF driver is detached
+ * @dev: the PCI device
+ */
+void pci_iov_remove(struct pci_dev *dev)
+{
+	struct pci_sriov *iov = dev->sriov;
+
+	if (!dev->is_physfn)
+		return;
+
+	iov->driver_max_VFs = iov->total_VFs;
+	if (iov->num_VFs)
+		pci_warn(dev, "driver left SR-IOV enabled after remove\n");
+}
+
+/**
  * pci_iov_update_resource - update a VF BAR
  * @dev: the PCI device
  * @resno: the resource number
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index d088c9147f10..69a60d6ebd73 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -612,7 +612,7 @@ int pci_parse_request_of_pci_ranges(struct device *dev,
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			err = pci_remap_iospace(res, iobase);
+			err = devm_pci_remap_iospace(dev, res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
 					 err, res);
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 65113b6eed14..89ee6a2b6eb8 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -629,6 +629,18 @@ static bool acpi_pci_need_resume(struct pci_dev *dev)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&dev->dev);
 
+	/*
+	 * In some cases (eg. Samsung 305V4A) leaving a bridge in suspend over
+	 * system-wide suspend/resume confuses the platform firmware, so avoid
+	 * doing that, unless the bridge has a driver that should take care of
+	 * the PM handling.  According to Section 16.1.6 of ACPI 6.2, endpoint
+	 * devices are expected to be in D3 before invoking the S3 entry path
+	 * from the firmware, so they should not be affected by this issue.
+	 */
+	if (pci_is_bridge(dev) && !dev->driver &&
+	    acpi_target_system_state() != ACPI_STATE_S0)
+		return true;
+
 	if (!adev || !acpi_device_power_manageable(adev))
 		return false;
 
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index c125d53033c6..6792292b5fc7 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -445,6 +445,7 @@ static int pci_device_remove(struct device *dev)
 		}
 		pcibios_free_irq(pci_dev);
 		pci_dev->driver = NULL;
+		pci_iov_remove(pci_dev);
 	}
 
 	/* Undo the runtime PM settings in local_pci_probe() */
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..aa1684d99b70 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3579,6 +3579,44 @@ void pci_unmap_iospace(struct resource *res)
 }
 EXPORT_SYMBOL(pci_unmap_iospace);
 
+static void devm_pci_unmap_iospace(struct device *dev, void *ptr)
+{
+	struct resource **res = ptr;
+
+	pci_unmap_iospace(*res);
+}
+
+/**
+ * devm_pci_remap_iospace - Managed pci_remap_iospace()
+ * @dev: Generic device to remap IO address for
+ * @res: Resource describing the I/O space
+ * @phys_addr: physical address of range to be mapped
+ *
+ * Managed pci_remap_iospace().  Map is automatically unmapped on driver
+ * detach.
+ */
+int devm_pci_remap_iospace(struct device *dev, const struct resource *res,
+			   phys_addr_t phys_addr)
+{
+	const struct resource **ptr;
+	int error;
+
+	ptr = devres_alloc(devm_pci_unmap_iospace, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	error = pci_remap_iospace(res, phys_addr);
+	if (error) {
+		devres_free(ptr);
+	} else	{
+		*ptr = res;
+		devres_add(dev, ptr);
+	}
+
+	return error;
+}
+EXPORT_SYMBOL(devm_pci_remap_iospace);
+
 /**
  * devm_pci_remap_cfgspace - Managed pci_remap_cfgspace()
  * @dev: Generic device to remap IO address for
@@ -5222,6 +5260,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
 
 	return PCI_SPEED_UNKNOWN;
 }
+EXPORT_SYMBOL(pcie_get_speed_cap);
 
 /**
  * pcie_get_width_cap - query for the PCI device's link width capability
@@ -5240,6 +5279,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev)
 
 	return PCIE_LNK_WIDTH_UNKNOWN;
 }
+EXPORT_SYMBOL(pcie_get_width_cap);
 
 /**
  * pcie_bandwidth_capable - calculate a PCI device's link bandwidth capability
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..882f1f9596df 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -311,6 +311,7 @@ static inline void pci_restore_ats_state(struct pci_dev *dev)
 #ifdef CONFIG_PCI_IOV
 int pci_iov_init(struct pci_dev *dev);
 void pci_iov_release(struct pci_dev *dev);
+void pci_iov_remove(struct pci_dev *dev);
 void pci_iov_update_resource(struct pci_dev *dev, int resno);
 resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
 void pci_restore_iov_state(struct pci_dev *dev);
@@ -325,6 +326,9 @@ static inline void pci_iov_release(struct pci_dev *dev)
 
 {
 }
+static inline void pci_iov_remove(struct pci_dev *dev)
+{
+}
 static inline void pci_restore_iov_state(struct pci_dev *dev)
 {
 }
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index f7ce0cb0b0b7..f02e334beb45 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -295,6 +295,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 
 	parent = udev->subordinate;
 	pci_lock_rescan_remove();
+	pci_dev_get(dev);
 	list_for_each_entry_safe_reverse(pdev, temp, &parent->devices,
 					 bus_list) {
 		pci_dev_get(pdev);
@@ -328,6 +329,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 		pci_info(dev, "Device recovery from fatal error failed\n");
 	}
 
+	pci_dev_put(dev);
 	pci_unlock_rescan_remove();
 }
 
diff --git a/drivers/phy/broadcom/phy-brcm-usb-init.c b/drivers/phy/broadcom/phy-brcm-usb-init.c
index 1b7febc43da9..29d2c3b1913a 100644
--- a/drivers/phy/broadcom/phy-brcm-usb-init.c
+++ b/drivers/phy/broadcom/phy-brcm-usb-init.c
@@ -962,6 +962,10 @@ void brcm_usb_init_xhci(struct brcm_usb_init_params *params)
 {
 	void __iomem *ctrl = params->ctrl_regs;
 
+	USB_CTRL_UNSET(ctrl, USB30_PCTL, PHY3_IDDQ_OVERRIDE);
+	/* 1 millisecond - for USB clocks to settle down */
+	usleep_range(1000, 2000);
+
 	if (BRCM_ID(params->family_id) == 0x7366) {
 		/*
 		 * The PHY3_SOFT_RESETB bits default to the wrong state.
diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c
index 23705e1a0023..0075fb0bef8c 100644
--- a/drivers/phy/motorola/phy-mapphone-mdm6600.c
+++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c
@@ -182,13 +182,13 @@ static void phy_mdm6600_status(struct work_struct *work)
 	ddata = container_of(work, struct phy_mdm6600, status_work.work);
 	dev = ddata->dev;
 
-	error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_CMD_LINES,
+	error = gpiod_get_array_value_cansleep(PHY_MDM6600_NR_STATUS_LINES,
 					       ddata->status_gpios->desc,
 					       values);
 	if (error)
 		return;
 
-	for (i = 0; i < PHY_MDM6600_NR_CMD_LINES; i++) {
+	for (i = 0; i < PHY_MDM6600_NR_STATUS_LINES; i++) {
 		val |= values[i] << i;
 		dev_dbg(ddata->dev, "XXX %s: i: %i values[i]: %i val: %i\n",
 			__func__, i, values[i], val);
diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c
index 35c17653c694..87618a4e90e4 100644
--- a/drivers/pinctrl/bcm/pinctrl-nsp-mux.c
+++ b/drivers/pinctrl/bcm/pinctrl-nsp-mux.c
@@ -460,8 +460,8 @@ static int nsp_pinmux_enable(struct pinctrl_dev *pctrl_dev,
 	const struct nsp_pin_function *func;
 	const struct nsp_pin_group *grp;
 
-	if (grp_select > pinctrl->num_groups ||
-		func_select > pinctrl->num_functions)
+	if (grp_select >= pinctrl->num_groups ||
+	    func_select >= pinctrl->num_functions)
 		return -EINVAL;
 
 	func = &pinctrl->functions[func_select];
@@ -577,6 +577,8 @@ static int nsp_pinmux_probe(struct platform_device *pdev)
 		return PTR_ERR(pinctrl->base0);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res)
+		return -EINVAL;
 	pinctrl->base1 = devm_ioremap_nocache(&pdev->dev, res->start,
 					      resource_size(res));
 	if (!pinctrl->base1) {
diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
index e3f1ab2290fc..4c4740ffeb9c 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
@@ -1424,7 +1424,7 @@ static struct pinctrl_desc mtk_desc = {
 
 static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio)
 {
-	struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent);
+	struct mtk_pinctrl *hw = gpiochip_get_data(chip);
 	int value, err;
 
 	err = mtk_hw_get_value(hw, gpio, PINCTRL_PIN_REG_DI, &value);
@@ -1436,7 +1436,7 @@ static int mtk_gpio_get(struct gpio_chip *chip, unsigned int gpio)
 
 static void mtk_gpio_set(struct gpio_chip *chip, unsigned int gpio, int value)
 {
-	struct mtk_pinctrl *hw = dev_get_drvdata(chip->parent);
+	struct mtk_pinctrl *hw = gpiochip_get_data(chip);
 
 	mtk_hw_set_value(hw, gpio, PINCTRL_PIN_REG_DO, !!value);
 }
@@ -1508,11 +1508,20 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw, struct device_node *np)
 	if (ret < 0)
 		return ret;
 
-	ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0,
-				     chip->ngpio);
-	if (ret < 0) {
-		gpiochip_remove(chip);
-		return ret;
+	/* Just for backward compatible for these old pinctrl nodes without
+	 * "gpio-ranges" property. Otherwise, called directly from a
+	 * DeviceTree-supported pinctrl driver is DEPRECATED.
+	 * Please see Section 2.1 of
+	 * Documentation/devicetree/bindings/gpio/gpio.txt on how to
+	 * bind pinctrl and gpio drivers via the "gpio-ranges" property.
+	 */
+	if (!of_find_property(np, "gpio-ranges", NULL)) {
+		ret = gpiochip_add_pin_range(chip, dev_name(hw->dev), 0, 0,
+					     chip->ngpio);
+		if (ret < 0) {
+			gpiochip_remove(chip);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -1695,15 +1704,16 @@ static int mtk_pinctrl_probe(struct platform_device *pdev)
 	mtk_desc.custom_conf_items = mtk_conf_items;
 #endif
 
-	hw->pctrl = devm_pinctrl_register(&pdev->dev, &mtk_desc, hw);
-	if (IS_ERR(hw->pctrl))
-		return PTR_ERR(hw->pctrl);
+	err = devm_pinctrl_register_and_init(&pdev->dev, &mtk_desc, hw,
+					     &hw->pctrl);
+	if (err)
+		return err;
 
 	/* Setup groups descriptions per SoC types */
 	err = mtk_build_groups(hw);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to build groups\n");
-		return 0;
+		return err;
 	}
 
 	/* Setup functions descriptions per SoC types */
@@ -1713,17 +1723,25 @@ static int mtk_pinctrl_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	err = mtk_build_gpiochip(hw, pdev->dev.of_node);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to add gpio_chip\n");
+	/* For able to make pinctrl_claim_hogs, we must not enable pinctrl
+	 * until all groups and functions are being added one.
+	 */
+	err = pinctrl_enable(hw->pctrl);
+	if (err)
 		return err;
-	}
 
 	err = mtk_build_eint(hw, pdev);
 	if (err)
 		dev_warn(&pdev->dev,
 			 "Failed to add EINT, but pinctrl still can work\n");
 
+	/* Build gpiochip should be after pinctrl_enable is done */
+	err = mtk_build_gpiochip(hw, pdev->dev.of_node);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to add gpio_chip\n");
+		return err;
+	}
+
 	platform_set_drvdata(pdev, hw);
 
 	return 0;
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index a1d7156d0a43..6a1b6058b991 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -536,7 +536,7 @@ static int ingenic_pinmux_gpio_set_direction(struct pinctrl_dev *pctldev,
 		ingenic_config_pin(jzpc, pin, JZ4770_GPIO_PAT1, input);
 	} else {
 		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_SELECT, false);
-		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, input);
+		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_DIR, !input);
 		ingenic_config_pin(jzpc, pin, JZ4740_GPIO_FUNC, false);
 	}
 
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c
index b02caf316711..eeb58b3bbc9a 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77970.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77970.c
@@ -21,15 +21,13 @@
 #include "core.h"
 #include "sh_pfc.h"
 
-#define CFG_FLAGS SH_PFC_PIN_CFG_DRIVE_STRENGTH
-
 #define CPU_ALL_PORT(fn, sfx)						\
-	PORT_GP_CFG_22(0, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
-	PORT_GP_CFG_28(1, fn, sfx, CFG_FLAGS),				\
-	PORT_GP_CFG_17(2, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
-	PORT_GP_CFG_17(3, fn, sfx, CFG_FLAGS | SH_PFC_PIN_CFG_IO_VOLTAGE), \
-	PORT_GP_CFG_6(4,  fn, sfx, CFG_FLAGS),				\
-	PORT_GP_CFG_15(5, fn, sfx, CFG_FLAGS)
+	PORT_GP_CFG_22(0, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE),		\
+	PORT_GP_28(1, fn, sfx),						\
+	PORT_GP_CFG_17(2, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE),		\
+	PORT_GP_CFG_17(3, fn, sfx, SH_PFC_PIN_CFG_IO_VOLTAGE),		\
+	PORT_GP_6(4,  fn, sfx),						\
+	PORT_GP_15(5, fn, sfx)
 /*
  * F_() : just information
  * FM() : macro for FN_xxx / xxx_MARK
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index f1fa8612db40..06978c14c83b 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -2185,7 +2185,7 @@ static int __init dell_init(void)
 		dell_fill_request(&buffer, token->location, 0, 0, 0);
 		ret = dell_send_request(&buffer,
 					CLASS_TOKEN_READ, SELECT_TOKEN_AC);
-		if (ret)
+		if (ret == 0)
 			max_intensity = buffer.output[3];
 	}
 
diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index 547dbdac9d54..01b0e2bb3319 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -89,6 +89,7 @@ int ptp_set_pinfunc(struct ptp_clock *ptp, unsigned int pin,
 	case PTP_PF_PHYSYNC:
 		if (chan != 0)
 			return -EINVAL;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 6d4012dd6922..bac1eeb3d312 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -265,8 +265,10 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 			return err;
 
 		/* full-function RTCs won't have such missing fields */
-		if (rtc_valid_tm(&alarm->time) == 0)
+		if (rtc_valid_tm(&alarm->time) == 0) {
+			rtc_add_offset(rtc, &alarm->time);
 			return 0;
+		}
 
 		/* get the "after" timestamp, to detect wrapped fields */
 		err = rtc_read_time(rtc, &now);
@@ -409,7 +411,6 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	if (err)
 		return err;
 
-	rtc_subtract_offset(rtc, &alarm->time);
 	scheduled = rtc_tm_to_time64(&alarm->time);
 
 	/* Make sure we're not setting alarms in the past */
@@ -426,6 +427,8 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	 * over right here, before we set the alarm.
 	 */
 
+	rtc_subtract_offset(rtc, &alarm->time);
+
 	if (!rtc->ops)
 		err = -ENODEV;
 	else if (!rtc->ops->set_alarm)
@@ -467,7 +470,6 @@ int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 
 	mutex_unlock(&rtc->ops_lock);
 
-	rtc_add_offset(rtc, &alarm->time);
 	return err;
 }
 EXPORT_SYMBOL_GPL(rtc_set_alarm);
diff --git a/drivers/rtc/rtc-mrst.c b/drivers/rtc/rtc-mrst.c
index 097a4d4e2aba..1925aaf09093 100644
--- a/drivers/rtc/rtc-mrst.c
+++ b/drivers/rtc/rtc-mrst.c
@@ -367,10 +367,8 @@ static int vrtc_mrst_do_probe(struct device *dev, struct resource *iomem,
 	}
 
 	retval = rtc_register_device(mrst_rtc.rtc);
-	if (retval) {
-		retval = PTR_ERR(mrst_rtc.rtc);
+	if (retval)
 		goto cleanup0;
-	}
 
 	dev_dbg(dev, "initialised\n");
 	return 0;
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d3a38c421503..a9f60d0ee02e 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -41,6 +41,15 @@
 
 #define DASD_DIAG_MOD		"dasd_diag_mod"
 
+static unsigned int queue_depth = 32;
+static unsigned int nr_hw_queues = 4;
+
+module_param(queue_depth, uint, 0444);
+MODULE_PARM_DESC(queue_depth, "Default queue depth for new DASD devices");
+
+module_param(nr_hw_queues, uint, 0444);
+MODULE_PARM_DESC(nr_hw_queues, "Default number of hardware queues for new DASD devices");
+
 /*
  * SECTION: exported variables of dasd.c
  */
@@ -3115,8 +3124,8 @@ static int dasd_alloc_queue(struct dasd_block *block)
 
 	block->tag_set.ops = &dasd_mq_ops;
 	block->tag_set.cmd_size = sizeof(struct dasd_ccw_req);
-	block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
-	block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
+	block->tag_set.nr_hw_queues = nr_hw_queues;
+	block->tag_set.queue_depth = queue_depth;
 	block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
 
 	rc = blk_mq_alloc_tag_set(&block->tag_set);
diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
index 976b6bd4fb05..de6b96036aa4 100644
--- a/drivers/s390/block/dasd_int.h
+++ b/drivers/s390/block/dasd_int.h
@@ -228,14 +228,6 @@ struct dasd_ccw_req {
 #define DASD_CQR_SUPPRESS_IL	6	/* Suppress 'Incorrect Length' error */
 #define DASD_CQR_SUPPRESS_CR	7	/* Suppress 'Command Reject' error */
 
-/*
- * There is no reliable way to determine the number of available CPUs on
- * LPAR but there is no big performance difference between 1 and the
- * maximum CPU number.
- * 64 is a good trade off performance wise.
- */
-#define DASD_NR_HW_QUEUES 64
-#define DASD_MAX_LCU_DEV 256
 #define DASD_REQ_PER_DEV 4
 
 /* Signature for error recovery functions. */
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 2a5fec55bf60..a246a618f9a4 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -829,6 +829,17 @@ struct qeth_trap_id {
 /*some helper functions*/
 #define QETH_CARD_IFNAME(card) (((card)->dev)? (card)->dev->name : "")
 
+static inline void qeth_scrub_qdio_buffer(struct qdio_buffer *buf,
+					  unsigned int elements)
+{
+	unsigned int i;
+
+	for (i = 0; i < elements; i++)
+		memset(&buf->element[i], 0, sizeof(struct qdio_buffer_element));
+	buf->element[14].sflags = 0;
+	buf->element[15].sflags = 0;
+}
+
 /**
  * qeth_get_elements_for_range() -	find number of SBALEs to cover range.
  * @start:				Start of the address range.
@@ -1029,7 +1040,7 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *,
 						 __u16, __u16,
 						 enum qeth_prot_versions);
 int qeth_set_features(struct net_device *, netdev_features_t);
-void qeth_recover_features(struct net_device *dev);
+void qeth_enable_hw_features(struct net_device *dev);
 netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t);
 netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 8e1474f1ffac..d01ac29fd986 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -73,9 +73,6 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue,
 		struct qeth_qdio_out_buffer *buf,
 		enum iucv_tx_notify notification);
 static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf);
-static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
-		struct qeth_qdio_out_buffer *buf,
-		enum qeth_qdio_buffer_states newbufstate);
 static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int);
 
 struct workqueue_struct *qeth_wq;
@@ -489,6 +486,7 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	struct qaob *aob;
 	struct qeth_qdio_out_buffer *buffer;
 	enum iucv_tx_notify notification;
+	unsigned int i;
 
 	aob = (struct qaob *) phys_to_virt(phys_aob_addr);
 	QETH_CARD_TEXT(card, 5, "haob");
@@ -513,10 +511,18 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	qeth_notify_skbs(buffer->q, buffer, notification);
 
 	buffer->aob = NULL;
-	qeth_clear_output_buffer(buffer->q, buffer,
-				 QETH_QDIO_BUF_HANDLED_DELAYED);
+	/* Free dangling allocations. The attached skbs are handled by
+	 * qeth_cleanup_handled_pending().
+	 */
+	for (i = 0;
+	     i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card);
+	     i++) {
+		if (aob->sba[i] && buffer->is_header[i])
+			kmem_cache_free(qeth_core_header_cache,
+					(void *) aob->sba[i]);
+	}
+	atomic_set(&buffer->state, QETH_QDIO_BUF_HANDLED_DELAYED);
 
-	/* from here on: do not touch buffer anymore */
 	qdio_release_aob(aob);
 }
 
@@ -3759,6 +3765,10 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 			QETH_CARD_TEXT(queue->card, 5, "aob");
 			QETH_CARD_TEXT_(queue->card, 5, "%lx",
 					virt_to_phys(buffer->aob));
+
+			/* prepare the queue slot for re-use: */
+			qeth_scrub_qdio_buffer(buffer->buffer,
+					       QETH_MAX_BUFFER_ELEMENTS(card));
 			if (qeth_init_qdio_out_buf(queue, bidx)) {
 				QETH_CARD_TEXT(card, 2, "outofbuf");
 				qeth_schedule_recovery(card);
@@ -4834,7 +4844,7 @@ int qeth_vm_request_mac(struct qeth_card *card)
 		goto out;
 	}
 
-	ccw_device_get_id(CARD_RDEV(card), &id);
+	ccw_device_get_id(CARD_DDEV(card), &id);
 	request->resp_buf_len = sizeof(*response);
 	request->resp_version = DIAG26C_VERSION2;
 	request->op_code = DIAG26C_GET_MAC;
@@ -6459,28 +6469,27 @@ static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on)
 #define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \
 			  NETIF_F_IPV6_CSUM)
 /**
- * qeth_recover_features() - Restore device features after recovery
- * @dev:	the recovering net_device
- *
- * Caller must hold rtnl lock.
+ * qeth_enable_hw_features() - (Re-)Enable HW functions for device features
+ * @dev:	a net_device
  */
-void qeth_recover_features(struct net_device *dev)
+void qeth_enable_hw_features(struct net_device *dev)
 {
-	netdev_features_t features = dev->features;
 	struct qeth_card *card = dev->ml_priv;
+	netdev_features_t features;
 
+	rtnl_lock();
+	features = dev->features;
 	/* force-off any feature that needs an IPA sequence.
 	 * netdev_update_features() will restart them.
 	 */
 	dev->features &= ~QETH_HW_FEATURES;
 	netdev_update_features(dev);
-
-	if (features == dev->features)
-		return;
-	dev_warn(&card->gdev->dev,
-		 "Device recovery failed to restore all offload features\n");
+	if (features != dev->features)
+		dev_warn(&card->gdev->dev,
+			 "Device recovery failed to restore all offload features\n");
+	rtnl_unlock();
 }
-EXPORT_SYMBOL_GPL(qeth_recover_features);
+EXPORT_SYMBOL_GPL(qeth_enable_hw_features);
 
 int qeth_set_features(struct net_device *dev, netdev_features_t features)
 {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index a7cb37da6a21..2487f0aeb165 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -140,7 +140,7 @@ static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac)
 
 static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 {
-	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+	enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
 					IPA_CMD_SETGMAC : IPA_CMD_SETVMAC;
 	int rc;
 
@@ -157,7 +157,7 @@ static int qeth_l2_write_mac(struct qeth_card *card, u8 *mac)
 
 static int qeth_l2_remove_mac(struct qeth_card *card, u8 *mac)
 {
-	enum qeth_ipa_cmds cmd = is_multicast_ether_addr_64bits(mac) ?
+	enum qeth_ipa_cmds cmd = is_multicast_ether_addr(mac) ?
 					IPA_CMD_DELGMAC : IPA_CMD_DELVMAC;
 	int rc;
 
@@ -501,27 +501,34 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p)
 		return -ERESTARTSYS;
 	}
 
+	/* avoid racing against concurrent state change: */
+	if (!mutex_trylock(&card->conf_mutex))
+		return -EAGAIN;
+
 	if (!qeth_card_hw_is_reachable(card)) {
 		ether_addr_copy(dev->dev_addr, addr->sa_data);
-		return 0;
+		goto out_unlock;
 	}
 
 	/* don't register the same address twice */
 	if (ether_addr_equal_64bits(dev->dev_addr, addr->sa_data) &&
 	    (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED))
-		return 0;
+		goto out_unlock;
 
 	/* add the new address, switch over, drop the old */
 	rc = qeth_l2_send_setmac(card, addr->sa_data);
 	if (rc)
-		return rc;
+		goto out_unlock;
 	ether_addr_copy(old_addr, dev->dev_addr);
 	ether_addr_copy(dev->dev_addr, addr->sa_data);
 
 	if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)
 		qeth_l2_remove_mac(card, old_addr);
 	card->info.mac_bits |= QETH_LAYER2_MAC_REGISTERED;
-	return 0;
+
+out_unlock:
+	mutex_unlock(&card->conf_mutex);
+	return rc;
 }
 
 static void qeth_promisc_to_bridge(struct qeth_card *card)
@@ -1112,6 +1119,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		netif_carrier_off(card->dev);
 
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
+
+	qeth_enable_hw_features(card->dev);
 	if (recover_flag == CARD_STATE_RECOVER) {
 		if (recovery_mode &&
 		    card->info.type != QETH_CARD_TYPE_OSN) {
@@ -1123,9 +1132,6 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		}
 		/* this also sets saved unicast addresses */
 		qeth_l2_set_rx_mode(card->dev);
-		rtnl_lock();
-		qeth_recover_features(card->dev);
-		rtnl_unlock();
 	}
 	/* let user_space know that device is online */
 	kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index e7fa479adf47..5905dc63e256 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2662,6 +2662,8 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		netif_carrier_on(card->dev);
 	else
 		netif_carrier_off(card->dev);
+
+	qeth_enable_hw_features(card->dev);
 	if (recover_flag == CARD_STATE_RECOVER) {
 		rtnl_lock();
 		if (recovery_mode)
@@ -2669,7 +2671,6 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		else
 			dev_open(card->dev);
 		qeth_l3_set_rx_mode(card->dev);
-		qeth_recover_features(card->dev);
 		rtnl_unlock();
 	}
 	qeth_trace_features(card);
diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index a9831bd37a73..a57f3a7d4748 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -1974,7 +1974,6 @@ static void aac_set_safw_attr_all_targets(struct aac_dev *dev)
 	u32 lun_count, nexus;
 	u32 i, bus, target;
 	u8 expose_flag, attribs;
-	u8 devtype;
 
 	lun_count = aac_get_safw_phys_lun_count(dev);
 
@@ -1992,23 +1991,23 @@ static void aac_set_safw_attr_all_targets(struct aac_dev *dev)
 			continue;
 
 		if (expose_flag != 0) {
-			devtype = AAC_DEVTYPE_RAID_MEMBER;
-			goto update_devtype;
+			dev->hba_map[bus][target].devtype =
+				AAC_DEVTYPE_RAID_MEMBER;
+			continue;
 		}
 
 		if (nexus != 0 && (attribs & 8)) {
-			devtype = AAC_DEVTYPE_NATIVE_RAW;
+			dev->hba_map[bus][target].devtype =
+				AAC_DEVTYPE_NATIVE_RAW;
 			dev->hba_map[bus][target].rmw_nexus =
 					nexus;
 		} else
-			devtype = AAC_DEVTYPE_ARC_RAW;
+			dev->hba_map[bus][target].devtype =
+				AAC_DEVTYPE_ARC_RAW;
 
 		dev->hba_map[bus][target].scan_counter = dev->scan_counter;
 
 		aac_set_safw_target_qd(dev, bus, target);
-
-update_devtype:
-		dev->hba_map[bus][target].devtype = devtype;
 	}
 }
 
diff --git a/drivers/scsi/cxlflash/main.h b/drivers/scsi/cxlflash/main.h
index 2a3977823812..a39be94d110c 100644
--- a/drivers/scsi/cxlflash/main.h
+++ b/drivers/scsi/cxlflash/main.h
@@ -107,12 +107,12 @@ cxlflash_assign_ops(struct dev_dependent_vals *ddv)
 {
 	const struct cxlflash_backend_ops *ops = NULL;
 
-#ifdef CONFIG_OCXL
+#ifdef CONFIG_OCXL_BASE
 	if (ddv->flags & CXLFLASH_OCXL_DEV)
 		ops = &cxlflash_ocxl_ops;
 #endif
 
-#ifdef CONFIG_CXL
+#ifdef CONFIG_CXL_BASE
 	if (!(ddv->flags & CXLFLASH_OCXL_DEV))
 		ops = &cxlflash_cxl_ops;
 #endif
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 0a95b5f25380..497a68389461 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -134,15 +134,14 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		goto err5;
+		path_put(&path);
+		goto err3;
 	}
 
 	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;
-err5:
-	path_put(&path);
 err4:
 	iput(inode);
 err3:
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 15c7f3b6f35e..58bb70b886d7 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3440,11 +3440,11 @@ static void hpsa_get_enclosure_info(struct ctlr_info *h,
 	struct ext_report_lun_entry *rle = &rlep->LUN[rle_index];
 	u16 bmic_device_index = 0;
 
-	bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
-
-	encl_dev->sas_address =
+	encl_dev->eli =
 		hpsa_get_enclosure_logical_identifier(h, scsi3addr);
 
+	bmic_device_index = GET_BMIC_DRIVE_NUMBER(&rle->lunid[0]);
+
 	if (encl_dev->target == -1 || encl_dev->lun == -1) {
 		rc = IO_OK;
 		goto out;
@@ -9697,7 +9697,24 @@ hpsa_sas_get_linkerrors(struct sas_phy *phy)
 static int
 hpsa_sas_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
 {
-	*identifier = rphy->identify.sas_address;
+	struct Scsi_Host *shost = phy_to_shost(rphy);
+	struct ctlr_info *h;
+	struct hpsa_scsi_dev_t *sd;
+
+	if (!shost)
+		return -ENXIO;
+
+	h = shost_to_hba(shost);
+
+	if (!h)
+		return -ENXIO;
+
+	sd = hpsa_find_device_by_sas_rphy(h, rphy);
+	if (!sd)
+		return -ENXIO;
+
+	*identifier = sd->eli;
+
 	return 0;
 }
 
diff --git a/drivers/scsi/hpsa.h b/drivers/scsi/hpsa.h
index fb9f5e7f8209..59e023696fff 100644
--- a/drivers/scsi/hpsa.h
+++ b/drivers/scsi/hpsa.h
@@ -68,6 +68,7 @@ struct hpsa_scsi_dev_t {
 #define RAID_CTLR_LUNID "\0\0\0\0\0\0\0\0"
 	unsigned char device_id[16];    /* from inquiry pg. 0x83 */
 	u64 sas_address;
+	u64 eli;			/* from report diags. */
 	unsigned char vendor[8];        /* bytes 8-15 of inquiry data */
 	unsigned char model[16];        /* bytes 16-31 of inquiry data */
 	unsigned char rev;		/* byte 2 of inquiry data */
diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c
index 90394cef0f41..0a5dd5595dd3 100644
--- a/drivers/scsi/qedf/qedf_main.c
+++ b/drivers/scsi/qedf/qedf_main.c
@@ -3295,6 +3295,11 @@ static int __qedf_probe(struct pci_dev *pdev, int mode)
 
 	init_completion(&qedf->flogi_compl);
 
+	status = qed_ops->common->update_drv_state(qedf->cdev, true);
+	if (status)
+		QEDF_ERR(&(qedf->dbg_ctx),
+			"Failed to send drv state to MFW.\n");
+
 	memset(&link_params, 0, sizeof(struct qed_link_params));
 	link_params.link_up = true;
 	status = qed_ops->common->set_link(qedf->cdev, &link_params);
@@ -3343,6 +3348,7 @@ static int qedf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 static void __qedf_remove(struct pci_dev *pdev, int mode)
 {
 	struct qedf_ctx *qedf;
+	int rc;
 
 	if (!pdev) {
 		QEDF_ERR(NULL, "pdev is NULL.\n");
@@ -3437,6 +3443,12 @@ static void __qedf_remove(struct pci_dev *pdev, int mode)
 		qed_ops->common->set_power_state(qedf->cdev, PCI_D0);
 		pci_set_drvdata(pdev, NULL);
 	}
+
+	rc = qed_ops->common->update_drv_state(qedf->cdev, false);
+	if (rc)
+		QEDF_ERR(&(qedf->dbg_ctx),
+			"Failed to send drv state to MFW.\n");
+
 	qed_ops->common->slowpath_stop(qedf->cdev);
 	qed_ops->common->remove(qedf->cdev);
 
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index cf274a79e77a..091ec1207bea 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -2273,6 +2273,7 @@ kset_free:
 static void __qedi_remove(struct pci_dev *pdev, int mode)
 {
 	struct qedi_ctx *qedi = pci_get_drvdata(pdev);
+	int rval;
 
 	if (qedi->tmf_thread) {
 		flush_workqueue(qedi->tmf_thread);
@@ -2302,6 +2303,10 @@ static void __qedi_remove(struct pci_dev *pdev, int mode)
 	if (mode == QEDI_MODE_NORMAL)
 		qedi_free_iscsi_pf_param(qedi);
 
+	rval = qedi_ops->common->update_drv_state(qedi->cdev, false);
+	if (rval)
+		QEDI_ERR(&qedi->dbg_ctx, "Failed to send drv state to MFW\n");
+
 	if (!test_bit(QEDI_IN_OFFLINE, &qedi->flags)) {
 		qedi_ops->common->slowpath_stop(qedi->cdev);
 		qedi_ops->common->remove(qedi->cdev);
@@ -2576,6 +2581,12 @@ static int __qedi_probe(struct pci_dev *pdev, int mode)
 		if (qedi_setup_boot_info(qedi))
 			QEDI_ERR(&qedi->dbg_ctx,
 				 "No iSCSI boot target configured\n");
+
+		rc = qedi_ops->common->update_drv_state(qedi->cdev, true);
+		if (rc)
+			QEDI_ERR(&qedi->dbg_ctx,
+				 "Failed to send drv state to MFW\n");
+
 	}
 
 	return 0;
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 9442e18aef6f..0f94b1d62d3f 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -361,6 +361,8 @@ struct ct_arg {
 	dma_addr_t	rsp_dma;
 	u32		req_size;
 	u32		rsp_size;
+	u32		req_allocated_size;
+	u32		rsp_allocated_size;
 	void		*req;
 	void		*rsp;
 	port_id_t	id;
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 4bc2b66b299f..2c35b0b2baa0 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -556,7 +556,7 @@ err2:
 		/* please ignore kernel warning. otherwise, we have mem leak. */
 		if (sp->u.iocb_cmd.u.ctarg.req) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.req,
 			    sp->u.iocb_cmd.u.ctarg.req_dma);
 			sp->u.iocb_cmd.u.ctarg.req = NULL;
@@ -564,7 +564,7 @@ err2:
 
 		if (sp->u.iocb_cmd.u.ctarg.rsp) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.rsp,
 			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -617,6 +617,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id)
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -627,6 +628,7 @@ static int qla_async_rftid(scsi_qla_host_t *vha, port_id_t *d_id)
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -712,6 +714,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -722,6 +725,7 @@ static int qla_async_rffid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -802,6 +806,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -812,6 +817,7 @@ static int qla_async_rnnid(scsi_qla_host_t *vha, port_id_t *d_id,
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -909,6 +915,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha)
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -919,6 +926,7 @@ static int qla_async_rsnn_nn(scsi_qla_host_t *vha)
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 	    sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 	    GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "%s: Failed to allocate ct_sns request.\n",
@@ -3388,14 +3396,14 @@ void qla24xx_sp_unmap(scsi_qla_host_t *vha, srb_t *sp)
 {
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 			sp->u.iocb_cmd.u.ctarg.req,
 			sp->u.iocb_cmd.u.ctarg.req_dma);
 		sp->u.iocb_cmd.u.ctarg.req = NULL;
 	}
 	if (sp->u.iocb_cmd.u.ctarg.rsp) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-			sizeof(struct ct_sns_pkt),
+			sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 			sp->u.iocb_cmd.u.ctarg.rsp,
 			sp->u.iocb_cmd.u.ctarg.rsp_dma);
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -3596,14 +3604,14 @@ static void qla2x00_async_gpnid_sp_done(void *s, int res)
 		/* please ignore kernel warning. otherwise, we have mem leak. */
 		if (sp->u.iocb_cmd.u.ctarg.req) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-				sizeof(struct ct_sns_pkt),
+				sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 				sp->u.iocb_cmd.u.ctarg.req,
 				sp->u.iocb_cmd.u.ctarg.req_dma);
 			sp->u.iocb_cmd.u.ctarg.req = NULL;
 		}
 		if (sp->u.iocb_cmd.u.ctarg.rsp) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-				sizeof(struct ct_sns_pkt),
+				sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 				sp->u.iocb_cmd.u.ctarg.rsp,
 				sp->u.iocb_cmd.u.ctarg.rsp_dma);
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -3654,6 +3662,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
 	sp->u.iocb_cmd.u.ctarg.req = dma_alloc_coherent(&vha->hw->pdev->dev,
 		sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.req_dma,
 		GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.req) {
 		ql_log(ql_log_warn, vha, 0xd041,
 		    "Failed to allocate ct_sns request.\n");
@@ -3663,6 +3672,7 @@ int qla24xx_async_gpnid(scsi_qla_host_t *vha, port_id_t *id)
 	sp->u.iocb_cmd.u.ctarg.rsp = dma_alloc_coherent(&vha->hw->pdev->dev,
 		sizeof(struct ct_sns_pkt), &sp->u.iocb_cmd.u.ctarg.rsp_dma,
 		GFP_KERNEL);
+	sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 	if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 		ql_log(ql_log_warn, vha, 0xd042,
 		    "Failed to allocate ct_sns request.\n");
@@ -4142,14 +4152,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res)
 			 */
 			if (sp->u.iocb_cmd.u.ctarg.req) {
 				dma_free_coherent(&vha->hw->pdev->dev,
-				    sizeof(struct ct_sns_pkt),
+				    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 				    sp->u.iocb_cmd.u.ctarg.req,
 				    sp->u.iocb_cmd.u.ctarg.req_dma);
 				sp->u.iocb_cmd.u.ctarg.req = NULL;
 			}
 			if (sp->u.iocb_cmd.u.ctarg.rsp) {
 				dma_free_coherent(&vha->hw->pdev->dev,
-				    sizeof(struct ct_sns_pkt),
+				    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 				    sp->u.iocb_cmd.u.ctarg.rsp,
 				    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 				sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -4179,14 +4189,14 @@ static void qla2x00_async_gpnft_gnnft_sp_done(void *s, int res)
 		/* please ignore kernel warning. Otherwise, we have mem leak. */
 		if (sp->u.iocb_cmd.u.ctarg.req) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.req,
 			    sp->u.iocb_cmd.u.ctarg.req_dma);
 			sp->u.iocb_cmd.u.ctarg.req = NULL;
 		}
 		if (sp->u.iocb_cmd.u.ctarg.rsp) {
 			dma_free_coherent(&vha->hw->pdev->dev,
-			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 			    sp->u.iocb_cmd.u.ctarg.rsp,
 			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -4281,14 +4291,14 @@ static int qla24xx_async_gnnft(scsi_qla_host_t *vha, struct srb *sp,
 done_free_sp:
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.req,
 		    sp->u.iocb_cmd.u.ctarg.req_dma);
 		sp->u.iocb_cmd.u.ctarg.req = NULL;
 	}
 	if (sp->u.iocb_cmd.u.ctarg.rsp) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.rsp,
 		    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
@@ -4349,6 +4359,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 		sp->u.iocb_cmd.u.ctarg.req = dma_zalloc_coherent(
 			&vha->hw->pdev->dev, sizeof(struct ct_sns_pkt),
 			&sp->u.iocb_cmd.u.ctarg.req_dma, GFP_KERNEL);
+		sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
 		if (!sp->u.iocb_cmd.u.ctarg.req) {
 			ql_log(ql_log_warn, vha, 0xffff,
 			    "Failed to allocate ct_sns request.\n");
@@ -4366,6 +4377,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 		sp->u.iocb_cmd.u.ctarg.rsp = dma_zalloc_coherent(
 			&vha->hw->pdev->dev, rspsz,
 			&sp->u.iocb_cmd.u.ctarg.rsp_dma, GFP_KERNEL);
+		sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = sizeof(struct ct_sns_pkt);
 		if (!sp->u.iocb_cmd.u.ctarg.rsp) {
 			ql_log(ql_log_warn, vha, 0xffff,
 			    "Failed to allocate ct_sns request.\n");
@@ -4425,14 +4437,14 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
 done_free_sp:
 	if (sp->u.iocb_cmd.u.ctarg.req) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.req,
 		    sp->u.iocb_cmd.u.ctarg.req_dma);
 		sp->u.iocb_cmd.u.ctarg.req = NULL;
 	}
 	if (sp->u.iocb_cmd.u.ctarg.rsp) {
 		dma_free_coherent(&vha->hw->pdev->dev,
-		    sizeof(struct ct_sns_pkt),
+		    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
 		    sp->u.iocb_cmd.u.ctarg.rsp,
 		    sp->u.iocb_cmd.u.ctarg.rsp_dma);
 		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 7b675243bd16..db0e3279e07a 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -591,12 +591,14 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 				conflict_fcport =
 					qla2x00_find_fcport_by_wwpn(vha,
 					    e->port_name, 0);
-				ql_dbg(ql_dbg_disc, vha, 0x20e6,
-				    "%s %d %8phC post del sess\n",
-				    __func__, __LINE__,
-				    conflict_fcport->port_name);
-				qlt_schedule_sess_for_deletion
-					(conflict_fcport);
+				if (conflict_fcport) {
+					qlt_schedule_sess_for_deletion
+						(conflict_fcport);
+					ql_dbg(ql_dbg_disc, vha, 0x20e6,
+					    "%s %d %8phC post del sess\n",
+					    __func__, __LINE__,
+					    conflict_fcport->port_name);
+				}
 			}
 
 			/* FW already picked this loop id for another fcport */
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index e881fce7477a..9f309e572be4 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3180,6 +3180,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    "req->req_q_in=%p req->req_q_out=%p rsp->rsp_q_in=%p rsp->rsp_q_out=%p.\n",
 	    req->req_q_in, req->req_q_out, rsp->rsp_q_in, rsp->rsp_q_out);
 
+	ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0);
+
 	if (ha->isp_ops->initialize_adapter(base_vha)) {
 		ql_log(ql_log_fatal, base_vha, 0x00d6,
 		    "Failed to initialize adapter - Adapter flags %x.\n",
@@ -3216,8 +3218,6 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    host->can_queue, base_vha->req,
 	    base_vha->mgmt_svr_loop_id, host->sg_tablesize);
 
-	ha->wq = alloc_workqueue("qla2xxx_wq", 0, 0);
-
 	if (ha->mqenable) {
 		bool mq = false;
 		bool startit = false;
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 8932ae81a15a..2715cdaa669c 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -296,6 +296,20 @@ enum blk_eh_timer_return scsi_times_out(struct request *req)
 		rtn = host->hostt->eh_timed_out(scmd);
 
 	if (rtn == BLK_EH_DONE) {
+		/*
+		 * For blk-mq, we must set the request state to complete now
+		 * before sending the request to the scsi error handler. This
+		 * will prevent a use-after-free in the event the LLD manages
+		 * to complete the request before the error handler finishes
+		 * processing this timed out request.
+		 *
+		 * If the request was already completed, then the LLD beat the
+		 * time out handler from transferring the request to the scsi
+		 * error handler. In that case we can return immediately as no
+		 * further action is required.
+		 */
+		if (req->q->mq_ops && !blk_mq_mark_complete(req))
+			return rtn;
 		if (scsi_abort_command(scmd) != SUCCESS) {
 			set_host_byte(scmd, DID_TIME_OUT);
 			scsi_eh_scmd_add(scmd);
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index a14fef11776e..2bf3bf73886e 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -391,7 +391,8 @@ static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf)
  * Check that all zones of the device are equal. The last zone can however
  * be smaller. The zone size must also be a power of two number of LBAs.
  *
- * Returns the zone size in bytes upon success or an error code upon failure.
+ * Returns the zone size in number of blocks upon success or an error code
+ * upon failure.
  */
 static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 {
@@ -401,7 +402,7 @@ static s64 sd_zbc_check_zone_size(struct scsi_disk *sdkp)
 	unsigned char *rec;
 	unsigned int buf_len;
 	unsigned int list_length;
-	int ret;
+	s64 ret;
 	u8 same;
 
 	/* Get a buffer */
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 53ae52dbff84..cd2fdac000c9 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -51,6 +51,7 @@ static int sg_version_num = 30536;	/* 2 digits for each component */
 #include <linux/atomic.h>
 #include <linux/ratelimit.h>
 #include <linux/uio.h>
+#include <linux/cred.h> /* for sg_check_file_access() */
 
 #include "scsi.h"
 #include <scsi/scsi_dbg.h>
@@ -209,6 +210,33 @@ static void sg_device_destroy(struct kref *kref);
 	sdev_prefix_printk(prefix, (sdp)->device,		\
 			   (sdp)->disk->disk_name, fmt, ##a)
 
+/*
+ * The SCSI interfaces that use read() and write() as an asynchronous variant of
+ * ioctl(..., SG_IO, ...) are fundamentally unsafe, since there are lots of ways
+ * to trigger read() and write() calls from various contexts with elevated
+ * privileges. This can lead to kernel memory corruption (e.g. if these
+ * interfaces are called through splice()) and privilege escalation inside
+ * userspace (e.g. if a process with access to such a device passes a file
+ * descriptor to a SUID binary as stdin/stdout/stderr).
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static int sg_check_file_access(struct file *filp, const char *caller)
+{
+	if (filp->f_cred != current_real_cred()) {
+		pr_err_once("%s: process %d (%s) changed security contexts after opening file descriptor, this is not allowed.\n",
+			caller, task_tgid_vnr(current), current->comm);
+		return -EPERM;
+	}
+	if (uaccess_kernel()) {
+		pr_err_once("%s: process %d (%s) called from kernel context, this is not allowed.\n",
+			caller, task_tgid_vnr(current), current->comm);
+		return -EACCES;
+	}
+	return 0;
+}
+
 static int sg_allow_access(struct file *filp, unsigned char *cmd)
 {
 	struct sg_fd *sfp = filp->private_data;
@@ -393,6 +421,14 @@ sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos)
 	struct sg_header *old_hdr = NULL;
 	int retval = 0;
 
+	/*
+	 * This could cause a response to be stranded. Close the associated
+	 * file descriptor to free up any resources being held.
+	 */
+	retval = sg_check_file_access(filp, __func__);
+	if (retval)
+		return retval;
+
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
 	SCSI_LOG_TIMEOUT(3, sg_printk(KERN_INFO, sdp,
@@ -580,9 +616,11 @@ sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos)
 	struct sg_header old_hdr;
 	sg_io_hdr_t *hp;
 	unsigned char cmnd[SG_MAX_CDB_SIZE];
+	int retval;
 
-	if (unlikely(uaccess_kernel()))
-		return -EINVAL;
+	retval = sg_check_file_access(filp, __func__);
+	if (retval)
+		return retval;
 
 	if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)))
 		return -ENXIO;
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 32f0748fd067..0097a939487f 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -27,9 +27,16 @@
 #define GPC_PGC_SW2ISO_SHIFT	0x8
 #define GPC_PGC_SW_SHIFT	0x0
 
+#define GPC_PGC_PCI_PDN		0x200
+#define GPC_PGC_PCI_SR		0x20c
+
 #define GPC_PGC_GPU_PDN		0x260
 #define GPC_PGC_GPU_PUPSCR	0x264
 #define GPC_PGC_GPU_PDNSCR	0x268
+#define GPC_PGC_GPU_SR		0x26c
+
+#define GPC_PGC_DISP_PDN	0x240
+#define GPC_PGC_DISP_SR		0x24c
 
 #define GPU_VPU_PUP_REQ		BIT(1)
 #define GPU_VPU_PDN_REQ		BIT(0)
@@ -318,10 +325,24 @@ static const struct of_device_id imx_gpc_dt_ids[] = {
 	{ }
 };
 
+static const struct regmap_range yes_ranges[] = {
+	regmap_reg_range(GPC_CNTR, GPC_CNTR),
+	regmap_reg_range(GPC_PGC_PCI_PDN, GPC_PGC_PCI_SR),
+	regmap_reg_range(GPC_PGC_GPU_PDN, GPC_PGC_GPU_SR),
+	regmap_reg_range(GPC_PGC_DISP_PDN, GPC_PGC_DISP_SR),
+};
+
+static const struct regmap_access_table access_table = {
+	.yes_ranges	= yes_ranges,
+	.n_yes_ranges	= ARRAY_SIZE(yes_ranges),
+};
+
 static const struct regmap_config imx_gpc_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
+	.rd_table = &access_table,
+	.wr_table = &access_table,
 	.max_register = 0x2ac,
 };
 
diff --git a/drivers/staging/ks7010/ks_hostif.c b/drivers/staging/ks7010/ks_hostif.c
index 0ecffab52ec2..abdaf7cf8162 100644
--- a/drivers/staging/ks7010/ks_hostif.c
+++ b/drivers/staging/ks7010/ks_hostif.c
@@ -1842,15 +1842,15 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv)
 	memset(set_address, 0, NIC_MAX_MCAST_LIST * ETH_ALEN);
 
 	if (dev->flags & IFF_PROMISC) {
-		hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
-					    MCAST_FILTER_PROMISC);
+		hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+					   MCAST_FILTER_PROMISC);
 		goto spin_unlock;
 	}
 
 	if ((netdev_mc_count(dev) > NIC_MAX_MCAST_LIST) ||
 	    (dev->flags & IFF_ALLMULTI)) {
-		hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
-					    MCAST_FILTER_MCASTALL);
+		hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+					   MCAST_FILTER_MCASTALL);
 		goto spin_unlock;
 	}
 
@@ -1866,8 +1866,8 @@ void hostif_sme_multicast_set(struct ks_wlan_private *priv)
 					       ETH_ALEN * mc_count);
 	} else {
 		priv->sme_i.sme_flag |= SME_MULTICAST;
-		hostif_mib_set_request_bool(priv, LOCAL_MULTICAST_FILTER,
-					    MCAST_FILTER_MCAST);
+		hostif_mib_set_request_int(priv, LOCAL_MULTICAST_FILTER,
+					   MCAST_FILTER_MCAST);
 	}
 
 spin_unlock:
diff --git a/drivers/staging/media/omap4iss/iss_video.c b/drivers/staging/media/omap4iss/iss_video.c
index a3a83424a926..16478fe9e3f8 100644
--- a/drivers/staging/media/omap4iss/iss_video.c
+++ b/drivers/staging/media/omap4iss/iss_video.c
@@ -11,7 +11,6 @@
  * (at your option) any later version.
  */
 
-#include <asm/cacheflush.h>
 #include <linux/clk.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -24,6 +23,8 @@
 #include <media/v4l2-ioctl.h>
 #include <media/v4l2-mc.h>
 
+#include <asm/cacheflush.h>
+
 #include "iss_video.h"
 #include "iss.h"
 
diff --git a/drivers/staging/rtl8188eu/Kconfig b/drivers/staging/rtl8188eu/Kconfig
index 673fdce25530..ff7832798a77 100644
--- a/drivers/staging/rtl8188eu/Kconfig
+++ b/drivers/staging/rtl8188eu/Kconfig
@@ -7,7 +7,6 @@ config R8188EU
 	select LIB80211
 	select LIB80211_CRYPT_WEP
 	select LIB80211_CRYPT_CCMP
-	select LIB80211_CRYPT_TKIP
 	---help---
 	This option adds the Realtek RTL8188EU USB device such as TP-Link TL-WN725N.
 	If built as a module, it will be called r8188eu.
diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c
index 05936a45eb93..c6857a5be12a 100644
--- a/drivers/staging/rtl8188eu/core/rtw_recv.c
+++ b/drivers/staging/rtl8188eu/core/rtw_recv.c
@@ -23,7 +23,6 @@
 #include <mon.h>
 #include <wifi.h>
 #include <linux/vmalloc.h>
-#include <net/lib80211.h>
 
 #define ETHERNET_HEADER_SIZE	14	/*  Ethernet Header Length */
 #define LLC_HEADER_SIZE			6	/*  LLC Header Length */
@@ -221,20 +220,31 @@ u32 rtw_free_uc_swdec_pending_queue(struct adapter *adapter)
 static int recvframe_chkmic(struct adapter *adapter,
 			    struct recv_frame *precvframe)
 {
-	int res = _SUCCESS;
-	struct rx_pkt_attrib *prxattrib = &precvframe->attrib;
-	struct sta_info *stainfo = rtw_get_stainfo(&adapter->stapriv, prxattrib->ta);
+	int	i, res = _SUCCESS;
+	u32	datalen;
+	u8	miccode[8];
+	u8	bmic_err = false, brpt_micerror = true;
+	u8	*pframe, *payload, *pframemic;
+	u8	*mickey;
+	struct	sta_info		*stainfo;
+	struct	rx_pkt_attrib	*prxattrib = &precvframe->attrib;
+	struct	security_priv	*psecuritypriv = &adapter->securitypriv;
+
+	struct mlme_ext_priv	*pmlmeext = &adapter->mlmeextpriv;
+	struct mlme_ext_info	*pmlmeinfo = &(pmlmeext->mlmext_info);
+
+	stainfo = rtw_get_stainfo(&adapter->stapriv, &prxattrib->ta[0]);
 
 	if (prxattrib->encrypt == _TKIP_) {
+		RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+			 ("\n %s: prxattrib->encrypt==_TKIP_\n", __func__));
+		RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+			 ("\n %s: da=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+			  __func__, prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2],
+			  prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5]));
+
+		/* calculate mic code */
 		if (stainfo) {
-			int key_idx;
-			const int iv_len = 8, icv_len = 4, key_length = 32;
-			struct sk_buff *skb = precvframe->pkt;
-			u8 key[32], iv[8], icv[4], *pframe = skb->data;
-			void *crypto_private = NULL;
-			struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip");
-			struct security_priv *psecuritypriv = &adapter->securitypriv;
-
 			if (IS_MCAST(prxattrib->ra)) {
 				if (!psecuritypriv) {
 					res = _FAIL;
@@ -243,58 +253,115 @@ static int recvframe_chkmic(struct adapter *adapter,
 					DBG_88E("\n %s: didn't install group key!!!!!!!!!!\n", __func__);
 					goto exit;
 				}
-				key_idx = prxattrib->key_index;
-				memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16);
-				memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16);
+				mickey = &psecuritypriv->dot118021XGrprxmickey[prxattrib->key_index].skey[0];
+
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_info_,
+					 ("\n %s: bcmc key\n", __func__));
 			} else {
-				key_idx = 0;
-				memcpy(key, stainfo->dot118021x_UncstKey.skey, 16);
-				memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16);
+				mickey = &stainfo->dot11tkiprxmickey.skey[0];
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("\n %s: unicast key\n", __func__));
 			}
 
-			if (!crypto_ops) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
+			/* icv_len included the mic code */
+			datalen = precvframe->pkt->len-prxattrib->hdrlen -
+				  prxattrib->iv_len-prxattrib->icv_len-8;
+			pframe = precvframe->pkt->data;
+			payload = pframe+prxattrib->hdrlen+prxattrib->iv_len;
 
-			memcpy(iv, pframe + prxattrib->hdrlen, iv_len);
-			memcpy(icv, pframe + skb->len - icv_len, icv_len);
-			memmove(pframe + iv_len, pframe, prxattrib->hdrlen);
+			RT_TRACE(_module_rtl871x_recv_c_, _drv_info_, ("\n prxattrib->iv_len=%d prxattrib->icv_len=%d\n", prxattrib->iv_len, prxattrib->icv_len));
+			rtw_seccalctkipmic(mickey, pframe, payload, datalen, &miccode[0],
+					   (unsigned char)prxattrib->priority); /* care the length of the data */
 
-			skb_pull(skb, iv_len);
-			skb_trim(skb, skb->len - icv_len);
+			pframemic = payload+datalen;
 
-			crypto_private = crypto_ops->init(key_idx);
-			if (!crypto_private) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->decrypt_msdu(skb, key_idx, prxattrib->hdrlen, crypto_private)) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
+			bmic_err = false;
+
+			for (i = 0; i < 8; i++) {
+				if (miccode[i] != *(pframemic+i)) {
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+						 ("%s: miccode[%d](%02x)!=*(pframemic+%d)(%02x) ",
+						  __func__, i, miccode[i], i, *(pframemic + i)));
+					bmic_err = true;
+				}
 			}
 
-			memmove(pframe, pframe + iv_len, prxattrib->hdrlen);
-			skb_push(skb, iv_len);
-			skb_put(skb, icv_len);
+			if (bmic_err) {
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("\n *(pframemic-8)-*(pframemic-1)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+					 *(pframemic-8), *(pframemic-7), *(pframemic-6),
+					 *(pframemic-5), *(pframemic-4), *(pframemic-3),
+					 *(pframemic-2), *(pframemic-1)));
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("\n *(pframemic-16)-*(pframemic-9)=0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x\n",
+					 *(pframemic-16), *(pframemic-15), *(pframemic-14),
+					 *(pframemic-13), *(pframemic-12), *(pframemic-11),
+					 *(pframemic-10), *(pframemic-9)));
+				{
+					uint i;
 
-			memcpy(pframe + prxattrib->hdrlen, iv, iv_len);
-			memcpy(pframe + skb->len - icv_len, icv, icv_len);
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+						 ("\n ======demp packet (len=%d)======\n",
+						 precvframe->pkt->len));
+					for (i = 0; i < precvframe->pkt->len; i += 8) {
+						RT_TRACE(_module_rtl871x_recv_c_,
+							 _drv_err_,
+							 ("0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x:0x%02x",
+							 *(precvframe->pkt->data+i),
+							 *(precvframe->pkt->data+i+1),
+							 *(precvframe->pkt->data+i+2),
+							 *(precvframe->pkt->data+i+3),
+							 *(precvframe->pkt->data+i+4),
+							 *(precvframe->pkt->data+i+5),
+							 *(precvframe->pkt->data+i+6),
+							 *(precvframe->pkt->data+i+7)));
+					}
+					RT_TRACE(_module_rtl871x_recv_c_,
+						 _drv_err_,
+						 ("\n ====== demp packet end [len=%d]======\n",
+						 precvframe->pkt->len));
+					RT_TRACE(_module_rtl871x_recv_c_,
+						 _drv_err_,
+						 ("\n hrdlen=%d,\n",
+						 prxattrib->hdrlen));
+				}
 
-exit_lib80211_tkip:
-			if (crypto_ops && crypto_private)
-				crypto_ops->deinit(crypto_private);
+				RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
+					 ("ra=0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x 0x%.2x psecuritypriv->binstallGrpkey=%d ",
+					 prxattrib->ra[0], prxattrib->ra[1], prxattrib->ra[2],
+					 prxattrib->ra[3], prxattrib->ra[4], prxattrib->ra[5], psecuritypriv->binstallGrpkey));
+
+				/*  double check key_index for some timing issue , */
+				/*  cannot compare with psecuritypriv->dot118021XGrpKeyid also cause timing issue */
+				if ((IS_MCAST(prxattrib->ra) == true)  && (prxattrib->key_index != pmlmeinfo->key_index))
+					brpt_micerror = false;
+
+				if ((prxattrib->bdecrypted) && (brpt_micerror)) {
+					rtw_handle_tkip_mic_err(adapter, (u8)IS_MCAST(prxattrib->ra));
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted));
+					DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted);
+				} else {
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, (" mic error :prxattrib->bdecrypted=%d ", prxattrib->bdecrypted));
+					DBG_88E(" mic error :prxattrib->bdecrypted=%d\n", prxattrib->bdecrypted);
+				}
+				res = _FAIL;
+			} else {
+				/* mic checked ok */
+				if ((!psecuritypriv->bcheck_grpkey) && (IS_MCAST(prxattrib->ra))) {
+					psecuritypriv->bcheck_grpkey = true;
+					RT_TRACE(_module_rtl871x_recv_c_, _drv_err_, ("psecuritypriv->bcheck_grpkey = true"));
+				}
+			}
 		} else {
 			RT_TRACE(_module_rtl871x_recv_c_, _drv_err_,
 				 ("%s: rtw_get_stainfo==NULL!!!\n", __func__));
 		}
+
+		skb_trim(precvframe->pkt, precvframe->pkt->len - 8);
 	}
 
 exit:
+
 	return res;
 }
 
diff --git a/drivers/staging/rtl8188eu/core/rtw_security.c b/drivers/staging/rtl8188eu/core/rtw_security.c
index bfe0b217e679..67a2490f055e 100644
--- a/drivers/staging/rtl8188eu/core/rtw_security.c
+++ b/drivers/staging/rtl8188eu/core/rtw_security.c
@@ -650,71 +650,71 @@ u32	rtw_tkip_encrypt(struct adapter *padapter, u8 *pxmitframe)
 	return res;
 }
 
+/* The hlen isn't include the IV */
 u32 rtw_tkip_decrypt(struct adapter *padapter, u8 *precvframe)
-{
-	struct rx_pkt_attrib *prxattrib = &((struct recv_frame *)precvframe)->attrib;
-	u32 res = _SUCCESS;
+{																	/*  exclude ICV */
+	u16 pnl;
+	u32 pnh;
+	u8   rc4key[16];
+	u8   ttkey[16];
+	u8	crc[4];
+	struct arc4context mycontext;
+	int			length;
+
+	u8	*pframe, *payload, *iv, *prwskey;
+	union pn48 dot11txpn;
+	struct	sta_info		*stainfo;
+	struct	rx_pkt_attrib	 *prxattrib = &((struct recv_frame *)precvframe)->attrib;
+	struct	security_priv	*psecuritypriv = &padapter->securitypriv;
+	u32		res = _SUCCESS;
+
+
+	pframe = (unsigned char *)((struct recv_frame *)precvframe)->pkt->data;
 
 	/* 4 start to decrypt recvframe */
 	if (prxattrib->encrypt == _TKIP_) {
-		struct sta_info *stainfo = rtw_get_stainfo(&padapter->stapriv, prxattrib->ta);
-
+		stainfo = rtw_get_stainfo(&padapter->stapriv, &prxattrib->ta[0]);
 		if (stainfo) {
-			int key_idx;
-			const int iv_len = 8, icv_len = 4, key_length = 32;
-			void *crypto_private = NULL;
-			struct sk_buff *skb = ((struct recv_frame *)precvframe)->pkt;
-			u8 key[32], iv[8], icv[4], *pframe = skb->data;
-			struct lib80211_crypto_ops *crypto_ops = try_then_request_module(lib80211_get_crypto_ops("TKIP"), "lib80211_crypt_tkip");
-			struct security_priv *psecuritypriv = &padapter->securitypriv;
-
 			if (IS_MCAST(prxattrib->ra)) {
 				if (!psecuritypriv->binstallGrpkey) {
 					res = _FAIL;
 					DBG_88E("%s:rx bc/mc packets, but didn't install group key!!!!!!!!!!\n", __func__);
 					goto exit;
 				}
-				key_idx = prxattrib->key_index;
-				memcpy(key, psecuritypriv->dot118021XGrpKey[key_idx].skey, 16);
-				memcpy(key + 16, psecuritypriv->dot118021XGrprxmickey[key_idx].skey, 16);
+				prwskey = psecuritypriv->dot118021XGrpKey[prxattrib->key_index].skey;
 			} else {
-				key_idx = 0;
-				memcpy(key, stainfo->dot118021x_UncstKey.skey, 16);
-				memcpy(key + 16, stainfo->dot11tkiprxmickey.skey, 16);
+				RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("%s: stainfo!= NULL!!!\n", __func__));
+				prwskey = &stainfo->dot118021x_UncstKey.skey[0];
 			}
 
-			if (!crypto_ops) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
+			iv = pframe+prxattrib->hdrlen;
+			payload = pframe+prxattrib->iv_len+prxattrib->hdrlen;
+			length = ((struct recv_frame *)precvframe)->pkt->len-prxattrib->hdrlen-prxattrib->iv_len;
 
-			memcpy(iv, pframe + prxattrib->hdrlen, iv_len);
-			memcpy(icv, pframe + skb->len - icv_len, icv_len);
+			GET_TKIP_PN(iv, dot11txpn);
 
-			crypto_private = crypto_ops->init(key_idx);
-			if (!crypto_private) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->set_key(key, key_length, NULL, crypto_private) < 0) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
-			if (crypto_ops->decrypt_mpdu(skb, prxattrib->hdrlen, crypto_private)) {
-				res = _FAIL;
-				goto exit_lib80211_tkip;
-			}
+			pnl = (u16)(dot11txpn.val);
+			pnh = (u32)(dot11txpn.val>>16);
 
-			memmove(pframe, pframe + iv_len, prxattrib->hdrlen);
-			skb_push(skb, iv_len);
-			skb_put(skb, icv_len);
+			phase1((u16 *)&ttkey[0], prwskey, &prxattrib->ta[0], pnh);
+			phase2(&rc4key[0], prwskey, (unsigned short *)&ttkey[0], pnl);
 
-			memcpy(pframe + prxattrib->hdrlen, iv, iv_len);
-			memcpy(pframe + skb->len - icv_len, icv, icv_len);
+			/* 4 decrypt payload include icv */
 
-exit_lib80211_tkip:
-			if (crypto_ops && crypto_private)
-				crypto_ops->deinit(crypto_private);
+			arcfour_init(&mycontext, rc4key, 16);
+			arcfour_encrypt(&mycontext, payload, payload, length);
+
+			*((__le32 *)crc) = getcrc32(payload, length-4);
+
+			if (crc[3] != payload[length-1] ||
+			    crc[2] != payload[length-2] ||
+			    crc[1] != payload[length-3] ||
+			    crc[0] != payload[length-4]) {
+				RT_TRACE(_module_rtl871x_security_c_, _drv_err_,
+					 ("rtw_wep_decrypt:icv error crc (%4ph)!=payload (%4ph)\n",
+					 &crc, &payload[length-4]));
+				res = _FAIL;
+			}
 		} else {
 			RT_TRACE(_module_rtl871x_security_c_, _drv_err_, ("rtw_tkip_decrypt: stainfo==NULL!!!\n"));
 			res = _FAIL;
diff --git a/drivers/staging/rtl8723bs/core/rtw_ap.c b/drivers/staging/rtl8723bs/core/rtw_ap.c
index 45c05527a57a..faf4b4158cfa 100644
--- a/drivers/staging/rtl8723bs/core/rtw_ap.c
+++ b/drivers/staging/rtl8723bs/core/rtw_ap.c
@@ -1051,7 +1051,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 *pbuf,  int len)
 		return _FAIL;
 
 
-	if (len > MAX_IE_SZ)
+	if (len < 0 || len > MAX_IE_SZ)
 		return _FAIL;
 
 	pbss_network->IELength = len;
diff --git a/drivers/staging/rtlwifi/rtl8822be/hw.c b/drivers/staging/rtlwifi/rtl8822be/hw.c
index 7947edb239a1..88ba5b2fea6a 100644
--- a/drivers/staging/rtlwifi/rtl8822be/hw.c
+++ b/drivers/staging/rtlwifi/rtl8822be/hw.c
@@ -803,7 +803,7 @@ static void _rtl8822be_enable_aspm_back_door(struct ieee80211_hw *hw)
 		return;
 
 	pci_read_config_byte(rtlpci->pdev, 0x70f, &tmp);
-	pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | BIT(7));
+	pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | ASPM_L1_LATENCY << 3);
 
 	pci_read_config_byte(rtlpci->pdev, 0x719, &tmp);
 	pci_write_config_byte(rtlpci->pdev, 0x719, tmp | BIT(3) | BIT(4));
diff --git a/drivers/staging/rtlwifi/wifi.h b/drivers/staging/rtlwifi/wifi.h
index 012fb618840b..a45f0eb69d3f 100644
--- a/drivers/staging/rtlwifi/wifi.h
+++ b/drivers/staging/rtlwifi/wifi.h
@@ -88,6 +88,7 @@
 #define RTL_USB_MAX_RX_COUNT			100
 #define QBSS_LOAD_SIZE				5
 #define MAX_WMMELE_LENGTH			64
+#define ASPM_L1_LATENCY				7
 
 #define TOTAL_CAM_ENTRY				32
 
diff --git a/drivers/staging/speakup/speakup_soft.c b/drivers/staging/speakup/speakup_soft.c
index a61bc41b82d7..947c79532e10 100644
--- a/drivers/staging/speakup/speakup_soft.c
+++ b/drivers/staging/speakup/speakup_soft.c
@@ -198,11 +198,15 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count,
 	int chars_sent = 0;
 	char __user *cp;
 	char *init;
+	size_t bytes_per_ch = unicode ? 3 : 1;
 	u16 ch;
 	int empty;
 	unsigned long flags;
 	DEFINE_WAIT(wait);
 
+	if (count < bytes_per_ch)
+		return -EINVAL;
+
 	spin_lock_irqsave(&speakup_info.spinlock, flags);
 	while (1) {
 		prepare_to_wait(&speakup_event, &wait, TASK_INTERRUPTIBLE);
@@ -228,7 +232,7 @@ static ssize_t softsynthx_read(struct file *fp, char __user *buf, size_t count,
 	init = get_initstring();
 
 	/* Keep 3 bytes available for a 16bit UTF-8-encoded character */
-	while (chars_sent <= count - 3) {
+	while (chars_sent <= count - bytes_per_ch) {
 		if (speakup_info.flushing) {
 			speakup_info.flushing = 0;
 			ch = '\x18';
diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c
index 5c7ea237893e..da4a93df8d75 100644
--- a/drivers/staging/vboxvideo/vbox_mode.c
+++ b/drivers/staging/vboxvideo/vbox_mode.c
@@ -504,7 +504,7 @@ static void vbox_set_edid(struct drm_connector *connector, int width,
 	for (i = 0; i < EDID_SIZE - 1; ++i)
 		sum += edid[i];
 	edid[EDID_SIZE - 1] = (0x100 - (sum & 0xFF)) & 0xFF;
-	drm_mode_connector_update_edid_property(connector, (struct edid *)edid);
+	drm_connector_update_edid_property(connector, (struct edid *)edid);
 }
 
 static int vbox_get_modes(struct drm_connector *connector)
@@ -655,7 +655,7 @@ static int vbox_connector_init(struct drm_device *dev,
 				   dev->mode_config.suggested_y_property, 0);
 	drm_connector_register(connector);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 01ac306131c1..10db5656fd5d 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -3727,11 +3727,16 @@ core_scsi3_pri_read_keys(struct se_cmd *cmd)
 		 * Check for overflow of 8byte PRI READ_KEYS payload and
 		 * next reservation key list descriptor.
 		 */
-		if ((add_len + 8) > (cmd->data_length - 8))
-			break;
-
-		put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
-		off += 8;
+		if (off + 8 <= cmd->data_length) {
+			put_unaligned_be64(pr_reg->pr_res_key, &buf[off]);
+			off += 8;
+		}
+		/*
+		 * SPC5r17: 6.16.2 READ KEYS service action
+		 * The ADDITIONAL LENGTH field indicates the number of bytes in
+		 * the Reservation key list. The contents of the ADDITIONAL
+		 * LENGTH field are not altered based on the allocation length
+		 */
 		add_len += 8;
 	}
 	spin_unlock(&dev->t10_pr.registration_lock);
diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
index 6281266b8ec0..a923ebdeb73c 100644
--- a/drivers/thunderbolt/domain.c
+++ b/drivers/thunderbolt/domain.c
@@ -213,6 +213,10 @@ static ssize_t boot_acl_store(struct device *dev, struct device_attribute *attr,
 		goto err_free_acl;
 	}
 	ret = tb->cm_ops->set_boot_acl(tb, acl, tb->nboot_acl);
+	if (!ret) {
+		/* Notify userspace about the change */
+		kobject_uevent(&tb->dev.kobj, KOBJ_CHANGE);
+	}
 	mutex_unlock(&tb->lock);
 
 err_free_acl:
diff --git a/drivers/uio/uio.c b/drivers/uio/uio.c
index e8f4ac9400ea..5d421d7e8904 100644
--- a/drivers/uio/uio.c
+++ b/drivers/uio/uio.c
@@ -215,7 +215,20 @@ static ssize_t name_show(struct device *dev,
 			 struct device_attribute *attr, char *buf)
 {
 	struct uio_device *idev = dev_get_drvdata(dev);
-	return sprintf(buf, "%s\n", idev->info->name);
+	int ret;
+
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = -EINVAL;
+		dev_err(dev, "the device has been unregistered\n");
+		goto out;
+	}
+
+	ret = sprintf(buf, "%s\n", idev->info->name);
+
+out:
+	mutex_unlock(&idev->info_lock);
+	return ret;
 }
 static DEVICE_ATTR_RO(name);
 
@@ -223,7 +236,20 @@ static ssize_t version_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct uio_device *idev = dev_get_drvdata(dev);
-	return sprintf(buf, "%s\n", idev->info->version);
+	int ret;
+
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = -EINVAL;
+		dev_err(dev, "the device has been unregistered\n");
+		goto out;
+	}
+
+	ret = sprintf(buf, "%s\n", idev->info->version);
+
+out:
+	mutex_unlock(&idev->info_lock);
+	return ret;
 }
 static DEVICE_ATTR_RO(version);
 
@@ -415,11 +441,15 @@ EXPORT_SYMBOL_GPL(uio_event_notify);
 static irqreturn_t uio_interrupt(int irq, void *dev_id)
 {
 	struct uio_device *idev = (struct uio_device *)dev_id;
-	irqreturn_t ret = idev->info->handler(irq, idev->info);
+	irqreturn_t ret;
 
+	mutex_lock(&idev->info_lock);
+
+	ret = idev->info->handler(irq, idev->info);
 	if (ret == IRQ_HANDLED)
 		uio_event_notify(idev->info);
 
+	mutex_unlock(&idev->info_lock);
 	return ret;
 }
 
@@ -433,7 +463,6 @@ static int uio_open(struct inode *inode, struct file *filep)
 	struct uio_device *idev;
 	struct uio_listener *listener;
 	int ret = 0;
-	unsigned long flags;
 
 	mutex_lock(&minor_lock);
 	idev = idr_find(&uio_idr, iminor(inode));
@@ -460,10 +489,16 @@ static int uio_open(struct inode *inode, struct file *filep)
 	listener->event_count = atomic_read(&idev->event);
 	filep->private_data = listener;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		mutex_unlock(&idev->info_lock);
+		ret = -EINVAL;
+		goto err_alloc_listener;
+	}
+
 	if (idev->info && idev->info->open)
 		ret = idev->info->open(idev->info, inode);
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 	if (ret)
 		goto err_infoopen;
 
@@ -495,12 +530,11 @@ static int uio_release(struct inode *inode, struct file *filep)
 	int ret = 0;
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
 	if (idev->info && idev->info->release)
 		ret = idev->info->release(idev->info, inode);
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	module_put(idev->owner);
 	kfree(listener);
@@ -513,12 +547,11 @@ static __poll_t uio_poll(struct file *filep, poll_table *wait)
 	struct uio_listener *listener = filep->private_data;
 	struct uio_device *idev = listener->dev;
 	__poll_t ret = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
 	if (!idev->info || !idev->info->irq)
 		ret = -EIO;
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	if (ret)
 		return ret;
@@ -537,12 +570,11 @@ static ssize_t uio_read(struct file *filep, char __user *buf,
 	DECLARE_WAITQUEUE(wait, current);
 	ssize_t retval = 0;
 	s32 event_count;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
 	if (!idev->info || !idev->info->irq)
 		retval = -EIO;
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	if (retval)
 		return retval;
@@ -592,9 +624,13 @@ static ssize_t uio_write(struct file *filep, const char __user *buf,
 	struct uio_device *idev = listener->dev;
 	ssize_t retval;
 	s32 irq_on;
-	unsigned long flags;
 
-	spin_lock_irqsave(&idev->info_lock, flags);
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		retval = -EINVAL;
+		goto out;
+	}
+
 	if (!idev->info || !idev->info->irq) {
 		retval = -EIO;
 		goto out;
@@ -618,7 +654,7 @@ static ssize_t uio_write(struct file *filep, const char __user *buf,
 	retval = idev->info->irqcontrol(idev->info, irq_on);
 
 out:
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 	return retval ? retval : sizeof(s32);
 }
 
@@ -640,10 +676,20 @@ static vm_fault_t uio_vma_fault(struct vm_fault *vmf)
 	struct page *page;
 	unsigned long offset;
 	void *addr;
+	int ret = 0;
+	int mi;
 
-	int mi = uio_find_mem_index(vmf->vma);
-	if (mi < 0)
-		return VM_FAULT_SIGBUS;
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
+
+	mi = uio_find_mem_index(vmf->vma);
+	if (mi < 0) {
+		ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
 
 	/*
 	 * We need to subtract mi because userspace uses offset = N*PAGE_SIZE
@@ -658,7 +704,11 @@ static vm_fault_t uio_vma_fault(struct vm_fault *vmf)
 		page = vmalloc_to_page(addr);
 	get_page(page);
 	vmf->page = page;
-	return 0;
+
+out:
+	mutex_unlock(&idev->info_lock);
+
+	return ret;
 }
 
 static const struct vm_operations_struct uio_logical_vm_ops = {
@@ -683,6 +733,7 @@ static int uio_mmap_physical(struct vm_area_struct *vma)
 	struct uio_device *idev = vma->vm_private_data;
 	int mi = uio_find_mem_index(vma);
 	struct uio_mem *mem;
+
 	if (mi < 0)
 		return -EINVAL;
 	mem = idev->info->mem + mi;
@@ -724,30 +775,46 @@ static int uio_mmap(struct file *filep, struct vm_area_struct *vma)
 
 	vma->vm_private_data = idev;
 
+	mutex_lock(&idev->info_lock);
+	if (!idev->info) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	mi = uio_find_mem_index(vma);
-	if (mi < 0)
-		return -EINVAL;
+	if (mi < 0) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	requested_pages = vma_pages(vma);
 	actual_pages = ((idev->info->mem[mi].addr & ~PAGE_MASK)
 			+ idev->info->mem[mi].size + PAGE_SIZE -1) >> PAGE_SHIFT;
-	if (requested_pages > actual_pages)
-		return -EINVAL;
+	if (requested_pages > actual_pages) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	if (idev->info->mmap) {
 		ret = idev->info->mmap(idev->info, vma);
-		return ret;
+		goto out;
 	}
 
 	switch (idev->info->mem[mi].memtype) {
 		case UIO_MEM_PHYS:
-			return uio_mmap_physical(vma);
+			ret = uio_mmap_physical(vma);
+			break;
 		case UIO_MEM_LOGICAL:
 		case UIO_MEM_VIRTUAL:
-			return uio_mmap_logical(vma);
+			ret = uio_mmap_logical(vma);
+			break;
 		default:
-			return -EINVAL;
+			ret = -EINVAL;
 	}
+
+out:
+	mutex_unlock(&idev->info_lock);
+	return 0;
 }
 
 static const struct file_operations uio_fops = {
@@ -865,7 +932,7 @@ int __uio_register_device(struct module *owner,
 
 	idev->owner = owner;
 	idev->info = info;
-	spin_lock_init(&idev->info_lock);
+	mutex_init(&idev->info_lock);
 	init_waitqueue_head(&idev->wait);
 	atomic_set(&idev->event, 0);
 
@@ -902,8 +969,9 @@ int __uio_register_device(struct module *owner,
 		 * FDs at the time of unregister and therefore may not be
 		 * freed until they are released.
 		 */
-		ret = request_irq(info->irq, uio_interrupt,
-				  info->irq_flags, info->name, idev);
+		ret = request_threaded_irq(info->irq, NULL, uio_interrupt,
+					   info->irq_flags, info->name, idev);
+
 		if (ret)
 			goto err_request_irq;
 	}
@@ -928,7 +996,6 @@ EXPORT_SYMBOL_GPL(__uio_register_device);
 void uio_unregister_device(struct uio_info *info)
 {
 	struct uio_device *idev;
-	unsigned long flags;
 
 	if (!info || !info->uio_dev)
 		return;
@@ -937,14 +1004,14 @@ void uio_unregister_device(struct uio_info *info)
 
 	uio_free_minor(idev);
 
+	mutex_lock(&idev->info_lock);
 	uio_dev_del_attributes(idev);
 
 	if (info->irq && info->irq != UIO_IRQ_CUSTOM)
 		free_irq(info->irq, idev);
 
-	spin_lock_irqsave(&idev->info_lock, flags);
 	idev->info = NULL;
-	spin_unlock_irqrestore(&idev->info_lock, flags);
+	mutex_unlock(&idev->info_lock);
 
 	device_unregister(&idev->dev);
 
diff --git a/drivers/usb/chipidea/Kconfig b/drivers/usb/chipidea/Kconfig
index 785f0ed037f7..ee34e9046f7e 100644
--- a/drivers/usb/chipidea/Kconfig
+++ b/drivers/usb/chipidea/Kconfig
@@ -3,6 +3,7 @@ config USB_CHIPIDEA
 	depends on ((USB_EHCI_HCD && USB_GADGET) || (USB_EHCI_HCD && !USB_GADGET) || (!USB_EHCI_HCD && USB_GADGET)) && HAS_DMA
 	select EXTCON
 	select RESET_CONTROLLER
+	select USB_ULPI_BUS
 	help
 	  Say Y here if your system has a dual role high speed USB
 	  controller based on ChipIdea silicon IP. It supports:
@@ -38,12 +39,4 @@ config USB_CHIPIDEA_HOST
 	help
 	  Say Y here to enable host controller functionality of the
 	  ChipIdea driver.
-
-config USB_CHIPIDEA_ULPI
-	bool "ChipIdea ULPI PHY support"
-	depends on USB_ULPI_BUS=y || USB_ULPI_BUS=USB_CHIPIDEA
-	help
-	  Say Y here if you have a ULPI PHY attached to your ChipIdea
-	  controller.
-
 endif
diff --git a/drivers/usb/chipidea/Makefile b/drivers/usb/chipidea/Makefile
index e3d5e728fa53..12df94f78f72 100644
--- a/drivers/usb/chipidea/Makefile
+++ b/drivers/usb/chipidea/Makefile
@@ -1,11 +1,10 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_USB_CHIPIDEA)		+= ci_hdrc.o
 
-ci_hdrc-y				:= core.o otg.o debug.o
+ci_hdrc-y				:= core.o otg.o debug.o ulpi.o
 ci_hdrc-$(CONFIG_USB_CHIPIDEA_UDC)	+= udc.o
 ci_hdrc-$(CONFIG_USB_CHIPIDEA_HOST)	+= host.o
 ci_hdrc-$(CONFIG_USB_OTG_FSM)		+= otg_fsm.o
-ci_hdrc-$(CONFIG_USB_CHIPIDEA_ULPI)	+= ulpi.o
 
 # Glue/Bridge layers go here
 
diff --git a/drivers/usb/chipidea/ci.h b/drivers/usb/chipidea/ci.h
index 0bf244d50544..6a2cc5cd0281 100644
--- a/drivers/usb/chipidea/ci.h
+++ b/drivers/usb/chipidea/ci.h
@@ -240,10 +240,8 @@ struct ci_hdrc {
 
 	struct ci_hdrc_platform_data	*platdata;
 	int				vbus_active;
-#ifdef CONFIG_USB_CHIPIDEA_ULPI
 	struct ulpi			*ulpi;
 	struct ulpi_ops 		ulpi_ops;
-#endif
 	struct phy			*phy;
 	/* old usb_phy interface */
 	struct usb_phy			*usb_phy;
@@ -426,15 +424,9 @@ static inline bool ci_otg_is_fsm_mode(struct ci_hdrc *ci)
 #endif
 }
 
-#if IS_ENABLED(CONFIG_USB_CHIPIDEA_ULPI)
 int ci_ulpi_init(struct ci_hdrc *ci);
 void ci_ulpi_exit(struct ci_hdrc *ci);
 int ci_ulpi_resume(struct ci_hdrc *ci);
-#else
-static inline int ci_ulpi_init(struct ci_hdrc *ci) { return 0; }
-static inline void ci_ulpi_exit(struct ci_hdrc *ci) { }
-static inline int ci_ulpi_resume(struct ci_hdrc *ci) { return 0; }
-#endif
 
 u32 hw_read_intr_enable(struct ci_hdrc *ci);
 
diff --git a/drivers/usb/chipidea/ulpi.c b/drivers/usb/chipidea/ulpi.c
index 6da42dcd2888..dfec07e8ae1d 100644
--- a/drivers/usb/chipidea/ulpi.c
+++ b/drivers/usb/chipidea/ulpi.c
@@ -95,6 +95,9 @@ int ci_ulpi_resume(struct ci_hdrc *ci)
 {
 	int cnt = 100000;
 
+	if (ci->platdata->phy_mode != USBPHY_INTERFACE_MODE_ULPI)
+		return 0;
+
 	while (cnt-- > 0) {
 		if (hw_read(ci, OP_ULPI_VIEWPORT, ULPI_SYNC_STATE))
 			return 0;
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 998b32d0167e..75c4623ad779 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1831,6 +1831,9 @@ static const struct usb_device_id acm_ids[] = {
 	{ USB_DEVICE(0x09d8, 0x0320), /* Elatec GmbH TWN3 */
 	.driver_info = NO_UNION_NORMAL, /* has misplaced union descriptor */
 	},
+	{ USB_DEVICE(0x0ca6, 0xa050), /* Castles VEGA3000 */
+	.driver_info = NO_UNION_NORMAL, /* reports zero length descriptor */
+	},
 
 	{ USB_DEVICE(0x2912, 0x0001), /* ATOL FPrint */
 	.driver_info = CLEAR_HALT_CONDITIONS,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index fcae521df29b..1fb266809966 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -1142,10 +1142,14 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 
 		if (!udev || udev->state == USB_STATE_NOTATTACHED) {
 			/* Tell hub_wq to disconnect the device or
-			 * check for a new connection
+			 * check for a new connection or over current condition.
+			 * Based on USB2.0 Spec Section 11.12.5,
+			 * C_PORT_OVER_CURRENT could be set while
+			 * PORT_OVER_CURRENT is not. So check for any of them.
 			 */
 			if (udev || (portstatus & USB_PORT_STAT_CONNECTION) ||
-			    (portstatus & USB_PORT_STAT_OVERCURRENT))
+			    (portstatus & USB_PORT_STAT_OVERCURRENT) ||
+			    (portchange & USB_PORT_STAT_C_OVERCURRENT))
 				set_bit(port1, hub->change_bits);
 
 		} else if (portstatus & USB_PORT_STAT_ENABLE) {
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index c55def2f1320..097057d2eacf 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -378,6 +378,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Corsair K70 RGB */
 	{ USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Corsair Strafe */
+	{ USB_DEVICE(0x1b1c, 0x1b15), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_DELAY_CTRL_MSG },
+
 	/* Corsair Strafe RGB */
 	{ USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT |
 	  USB_QUIRK_DELAY_CTRL_MSG },
diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c
index a0f82cca2d9a..cefc99ae69b2 100644
--- a/drivers/usb/dwc2/gadget.c
+++ b/drivers/usb/dwc2/gadget.c
@@ -3430,7 +3430,7 @@ static void dwc2_gadget_handle_incomplete_isoc_in(struct dwc2_hsotg *hsotg)
 	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_in[idx];
 		/* Proceed only unmasked ISOC EPs */
-		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+		if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 			continue;
 
 		epctrl = dwc2_readl(hsotg->regs + DIEPCTL(idx));
@@ -3476,7 +3476,7 @@ static void dwc2_gadget_handle_incomplete_isoc_out(struct dwc2_hsotg *hsotg)
 	for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 		hs_ep = hsotg->eps_out[idx];
 		/* Proceed only unmasked ISOC EPs */
-		if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+		if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 			continue;
 
 		epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
@@ -3650,7 +3650,7 @@ irq_retry:
 		for (idx = 1; idx < hsotg->num_of_eps; idx++) {
 			hs_ep = hsotg->eps_out[idx];
 			/* Proceed only unmasked ISOC EPs */
-			if (!hs_ep->isochronous || (BIT(idx) & ~daintmsk))
+			if ((BIT(idx) & ~daintmsk) || !hs_ep->isochronous)
 				continue;
 
 			epctrl = dwc2_readl(hsotg->regs + DOEPCTL(idx));
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index b1104be3429c..6e2cdd7b93d4 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -2665,34 +2665,35 @@ static int dwc2_alloc_split_dma_aligned_buf(struct dwc2_hsotg *hsotg,
 
 #define DWC2_USB_DMA_ALIGN 4
 
-struct dma_aligned_buffer {
-	void *kmalloc_ptr;
-	void *old_xfer_buffer;
-	u8 data[0];
-};
-
 static void dwc2_free_dma_aligned_buffer(struct urb *urb)
 {
-	struct dma_aligned_buffer *temp;
+	void *stored_xfer_buffer;
+	size_t length;
 
 	if (!(urb->transfer_flags & URB_ALIGNED_TEMP_BUFFER))
 		return;
 
-	temp = container_of(urb->transfer_buffer,
-			    struct dma_aligned_buffer, data);
+	/* Restore urb->transfer_buffer from the end of the allocated area */
+	memcpy(&stored_xfer_buffer, urb->transfer_buffer +
+	       urb->transfer_buffer_length, sizeof(urb->transfer_buffer));
 
-	if (usb_urb_dir_in(urb))
-		memcpy(temp->old_xfer_buffer, temp->data,
-		       urb->transfer_buffer_length);
-	urb->transfer_buffer = temp->old_xfer_buffer;
-	kfree(temp->kmalloc_ptr);
+	if (usb_urb_dir_in(urb)) {
+		if (usb_pipeisoc(urb->pipe))
+			length = urb->transfer_buffer_length;
+		else
+			length = urb->actual_length;
+
+		memcpy(stored_xfer_buffer, urb->transfer_buffer, length);
+	}
+	kfree(urb->transfer_buffer);
+	urb->transfer_buffer = stored_xfer_buffer;
 
 	urb->transfer_flags &= ~URB_ALIGNED_TEMP_BUFFER;
 }
 
 static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 {
-	struct dma_aligned_buffer *temp, *kmalloc_ptr;
+	void *kmalloc_ptr;
 	size_t kmalloc_size;
 
 	if (urb->num_sgs || urb->sg ||
@@ -2700,22 +2701,29 @@ static int dwc2_alloc_dma_aligned_buffer(struct urb *urb, gfp_t mem_flags)
 	    !((uintptr_t)urb->transfer_buffer & (DWC2_USB_DMA_ALIGN - 1)))
 		return 0;
 
-	/* Allocate a buffer with enough padding for alignment */
+	/*
+	 * Allocate a buffer with enough padding for original transfer_buffer
+	 * pointer. This allocation is guaranteed to be aligned properly for
+	 * DMA
+	 */
 	kmalloc_size = urb->transfer_buffer_length +
-		sizeof(struct dma_aligned_buffer) + DWC2_USB_DMA_ALIGN - 1;
+		sizeof(urb->transfer_buffer);
 
 	kmalloc_ptr = kmalloc(kmalloc_size, mem_flags);
 	if (!kmalloc_ptr)
 		return -ENOMEM;
 
-	/* Position our struct dma_aligned_buffer such that data is aligned */
-	temp = PTR_ALIGN(kmalloc_ptr + 1, DWC2_USB_DMA_ALIGN) - 1;
-	temp->kmalloc_ptr = kmalloc_ptr;
-	temp->old_xfer_buffer = urb->transfer_buffer;
+	/*
+	 * Position value of original urb->transfer_buffer pointer to the end
+	 * of allocation for later referencing
+	 */
+	memcpy(kmalloc_ptr + urb->transfer_buffer_length,
+	       &urb->transfer_buffer, sizeof(urb->transfer_buffer));
+
 	if (usb_urb_dir_out(urb))
-		memcpy(temp->data, urb->transfer_buffer,
+		memcpy(kmalloc_ptr, urb->transfer_buffer,
 		       urb->transfer_buffer_length);
-	urb->transfer_buffer = temp->data;
+	urb->transfer_buffer = kmalloc_ptr;
 
 	urb->transfer_flags |= URB_ALIGNED_TEMP_BUFFER;
 
diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c
index ed7f05cf4906..8ce10caf3e19 100644
--- a/drivers/usb/dwc2/hcd_intr.c
+++ b/drivers/usb/dwc2/hcd_intr.c
@@ -1231,7 +1231,10 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg,
 	 * avoid interrupt storms we'll wait before retrying if we've got
 	 * several NAKs. If we didn't do this we'd retry directly from the
 	 * interrupt handler and could end up quickly getting another
-	 * interrupt (another NAK), which we'd retry.
+	 * interrupt (another NAK), which we'd retry. Note that we do not
+	 * delay retries for IN parts of control requests, as those are expected
+	 * to complete fairly quickly, and if we delay them we risk confusing
+	 * the device and cause it issue STALL.
 	 *
 	 * Note that in DMA mode software only gets involved to re-send NAKed
 	 * transfers for split transactions, so we only need to apply this
@@ -1244,7 +1247,9 @@ static void dwc2_hc_nak_intr(struct dwc2_hsotg *hsotg,
 			qtd->error_count = 0;
 		qtd->complete_split = 0;
 		qtd->num_naks++;
-		qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY;
+		qtd->qh->want_wait = qtd->num_naks >= DWC2_NAKS_BEFORE_DELAY &&
+				!(chan->ep_type == USB_ENDPOINT_XFER_CONTROL &&
+				  chan->ep_is_in);
 		dwc2_halt_channel(hsotg, chan, qtd, DWC2_HC_XFER_NAK);
 		goto handle_nak_done;
 	}
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index c77ff50a88a2..8efde178eef4 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -973,15 +973,12 @@ static void __dwc3_ep0_do_control_data(struct dwc3 *dwc,
 		ret = dwc3_ep0_start_trans(dep);
 	} else if (IS_ALIGNED(req->request.length, dep->endpoint.maxpacket) &&
 		   req->request.length && req->request.zero) {
-		u32	maxpacket;
 
 		ret = usb_gadget_map_request_by_dev(dwc->sysdev,
 				&req->request, dep->number);
 		if (ret)
 			return;
 
-		maxpacket = dep->endpoint.maxpacket;
-
 		/* prepare normal TRB */
 		dwc3_ep0_prepare_one_trb(dep, req->request.dma,
 					 req->request.length,
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index d2fa071c21b1..b8a15840b4ff 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1819,7 +1819,6 @@ unknown:
 		if (cdev->use_os_string && cdev->os_desc_config &&
 		    (ctrl->bRequestType & USB_TYPE_VENDOR) &&
 		    ctrl->bRequest == cdev->b_vendor_code) {
-			struct usb_request		*req;
 			struct usb_configuration	*os_desc_cfg;
 			u8				*buf;
 			int				interface;
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 33e2030503fa..3ada83d81bda 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -3263,7 +3263,7 @@ static int ffs_func_setup(struct usb_function *f,
 	__ffs_event_add(ffs, FUNCTIONFS_SETUP);
 	spin_unlock_irqrestore(&ffs->ev.waitq.lock, flags);
 
-	return USB_GADGET_DELAYED_STATUS;
+	return creq->wLength == 0 ? USB_GADGET_DELAYED_STATUS : 0;
 }
 
 static bool ffs_func_req_match(struct usb_function *f,
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index d2dc1f00180b..d582921f7257 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -438,14 +438,14 @@ static struct usb_descriptor_header *hs_audio_desc[] = {
 };
 
 struct cntrl_cur_lay3 {
-	__u32	dCUR;
+	__le32	dCUR;
 };
 
 struct cntrl_range_lay3 {
-	__u16	wNumSubRanges;
-	__u32	dMIN;
-	__u32	dMAX;
-	__u32	dRES;
+	__le16	wNumSubRanges;
+	__le32	dMIN;
+	__le32	dMAX;
+	__le32	dRES;
 } __packed;
 
 static void set_ep_max_packet_size(const struct f_uac2_opts *uac2_opts,
@@ -559,13 +559,13 @@ afunc_bind(struct usb_configuration *cfg, struct usb_function *fn)
 	agdev->out_ep = usb_ep_autoconfig(gadget, &fs_epout_desc);
 	if (!agdev->out_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		return ret;
+		return -ENODEV;
 	}
 
 	agdev->in_ep = usb_ep_autoconfig(gadget, &fs_epin_desc);
 	if (!agdev->in_ep) {
 		dev_err(dev, "%s:%d Error!\n", __func__, __LINE__);
-		return ret;
+		return -ENODEV;
 	}
 
 	agdev->in_ep_maxpsize = max_t(u16,
@@ -703,9 +703,9 @@ in_rq_cur(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 		memset(&c, 0, sizeof(struct cntrl_cur_lay3));
 
 		if (entity_id == USB_IN_CLK_ID)
-			c.dCUR = p_srate;
+			c.dCUR = cpu_to_le32(p_srate);
 		else if (entity_id == USB_OUT_CLK_ID)
-			c.dCUR = c_srate;
+			c.dCUR = cpu_to_le32(c_srate);
 
 		value = min_t(unsigned, w_length, sizeof c);
 		memcpy(req->buf, &c, value);
@@ -742,15 +742,15 @@ in_rq_range(struct usb_function *fn, const struct usb_ctrlrequest *cr)
 
 	if (control_selector == UAC2_CS_CONTROL_SAM_FREQ) {
 		if (entity_id == USB_IN_CLK_ID)
-			r.dMIN = p_srate;
+			r.dMIN = cpu_to_le32(p_srate);
 		else if (entity_id == USB_OUT_CLK_ID)
-			r.dMIN = c_srate;
+			r.dMIN = cpu_to_le32(c_srate);
 		else
 			return -EOPNOTSUPP;
 
 		r.dMAX = r.dMIN;
 		r.dRES = 0;
-		r.wNumSubRanges = 1;
+		r.wNumSubRanges = cpu_to_le16(1);
 
 		value = min_t(unsigned, w_length, sizeof r);
 		memcpy(req->buf, &r, value);
diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c
index a72295c953bb..fb5ed97572e5 100644
--- a/drivers/usb/gadget/function/u_audio.c
+++ b/drivers/usb/gadget/function/u_audio.c
@@ -32,9 +32,6 @@ struct uac_req {
 struct uac_rtd_params {
 	struct snd_uac_chip *uac; /* parent chip */
 	bool ep_enabled; /* if the ep is enabled */
-	/* Size of the ring buffer */
-	size_t dma_bytes;
-	unsigned char *dma_area;
 
 	struct snd_pcm_substream *ss;
 
@@ -43,8 +40,6 @@ struct uac_rtd_params {
 
 	void *rbuf;
 
-	size_t period_size;
-
 	unsigned max_psize;	/* MaxPacketSize of endpoint */
 	struct uac_req *ureq;
 
@@ -84,12 +79,12 @@ static const struct snd_pcm_hardware uac_pcm_hardware = {
 static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 {
 	unsigned pending;
-	unsigned long flags;
+	unsigned long flags, flags2;
 	unsigned int hw_ptr;
-	bool update_alsa = false;
 	int status = req->status;
 	struct uac_req *ur = req->context;
 	struct snd_pcm_substream *substream;
+	struct snd_pcm_runtime *runtime;
 	struct uac_rtd_params *prm = ur->pp;
 	struct snd_uac_chip *uac = prm->uac;
 
@@ -111,6 +106,14 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 	if (!substream)
 		goto exit;
 
+	snd_pcm_stream_lock_irqsave(substream, flags2);
+
+	runtime = substream->runtime;
+	if (!runtime || !snd_pcm_running(substream)) {
+		snd_pcm_stream_unlock_irqrestore(substream, flags2);
+		goto exit;
+	}
+
 	spin_lock_irqsave(&prm->lock, flags);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
@@ -137,43 +140,46 @@ static void u_audio_iso_complete(struct usb_ep *ep, struct usb_request *req)
 		req->actual = req->length;
 	}
 
-	pending = prm->hw_ptr % prm->period_size;
-	pending += req->actual;
-	if (pending >= prm->period_size)
-		update_alsa = true;
-
 	hw_ptr = prm->hw_ptr;
-	prm->hw_ptr = (prm->hw_ptr + req->actual) % prm->dma_bytes;
 
 	spin_unlock_irqrestore(&prm->lock, flags);
 
 	/* Pack USB load in ALSA ring buffer */
-	pending = prm->dma_bytes - hw_ptr;
+	pending = runtime->dma_bytes - hw_ptr;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		if (unlikely(pending < req->actual)) {
-			memcpy(req->buf, prm->dma_area + hw_ptr, pending);
-			memcpy(req->buf + pending, prm->dma_area,
+			memcpy(req->buf, runtime->dma_area + hw_ptr, pending);
+			memcpy(req->buf + pending, runtime->dma_area,
 			       req->actual - pending);
 		} else {
-			memcpy(req->buf, prm->dma_area + hw_ptr, req->actual);
+			memcpy(req->buf, runtime->dma_area + hw_ptr,
+			       req->actual);
 		}
 	} else {
 		if (unlikely(pending < req->actual)) {
-			memcpy(prm->dma_area + hw_ptr, req->buf, pending);
-			memcpy(prm->dma_area, req->buf + pending,
+			memcpy(runtime->dma_area + hw_ptr, req->buf, pending);
+			memcpy(runtime->dma_area, req->buf + pending,
 			       req->actual - pending);
 		} else {
-			memcpy(prm->dma_area + hw_ptr, req->buf, req->actual);
+			memcpy(runtime->dma_area + hw_ptr, req->buf,
+			       req->actual);
 		}
 	}
 
+	spin_lock_irqsave(&prm->lock, flags);
+	/* update hw_ptr after data is copied to memory */
+	prm->hw_ptr = (hw_ptr + req->actual) % runtime->dma_bytes;
+	hw_ptr = prm->hw_ptr;
+	spin_unlock_irqrestore(&prm->lock, flags);
+	snd_pcm_stream_unlock_irqrestore(substream, flags2);
+
+	if ((hw_ptr % snd_pcm_lib_period_bytes(substream)) < req->actual)
+		snd_pcm_period_elapsed(substream);
+
 exit:
 	if (usb_ep_queue(ep, req, GFP_ATOMIC))
 		dev_err(uac->card->dev, "%d Error!\n", __LINE__);
-
-	if (update_alsa)
-		snd_pcm_period_elapsed(substream);
 }
 
 static int uac_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
@@ -236,40 +242,12 @@ static snd_pcm_uframes_t uac_pcm_pointer(struct snd_pcm_substream *substream)
 static int uac_pcm_hw_params(struct snd_pcm_substream *substream,
 			       struct snd_pcm_hw_params *hw_params)
 {
-	struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
-	struct uac_rtd_params *prm;
-	int err;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		prm = &uac->p_prm;
-	else
-		prm = &uac->c_prm;
-
-	err = snd_pcm_lib_malloc_pages(substream,
+	return snd_pcm_lib_malloc_pages(substream,
 					params_buffer_bytes(hw_params));
-	if (err >= 0) {
-		prm->dma_bytes = substream->runtime->dma_bytes;
-		prm->dma_area = substream->runtime->dma_area;
-		prm->period_size = params_period_bytes(hw_params);
-	}
-
-	return err;
 }
 
 static int uac_pcm_hw_free(struct snd_pcm_substream *substream)
 {
-	struct snd_uac_chip *uac = snd_pcm_substream_chip(substream);
-	struct uac_rtd_params *prm;
-
-	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		prm = &uac->p_prm;
-	else
-		prm = &uac->c_prm;
-
-	prm->dma_area = NULL;
-	prm->dma_bytes = 0;
-	prm->period_size = 0;
-
 	return snd_pcm_lib_free_pages(substream);
 }
 
@@ -595,15 +573,15 @@ int g_audio_setup(struct g_audio *g_audio, const char *pcm_name,
 	if (err < 0)
 		goto snd_fail;
 
-	strcpy(pcm->name, pcm_name);
+	strlcpy(pcm->name, pcm_name, sizeof(pcm->name));
 	pcm->private_data = uac;
 	uac->pcm = pcm;
 
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &uac_pcm_ops);
 	snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_CAPTURE, &uac_pcm_ops);
 
-	strcpy(card->driver, card_name);
-	strcpy(card->shortname, card_name);
+	strlcpy(card->driver, card_name, sizeof(card->driver));
+	strlcpy(card->shortname, card_name, sizeof(card->shortname));
 	sprintf(card->longname, "%s %i", card_name, card->dev->id);
 
 	snd_pcm_lib_preallocate_pages_for_all(pcm, SNDRV_DMA_TYPE_CONTINUOUS,
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
index f0cdf89b8503..83ba8a2eb6af 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
+++ b/drivers/usb/gadget/udc/aspeed-vhub/Kconfig
@@ -2,6 +2,7 @@
 config USB_ASPEED_VHUB
 	tristate "Aspeed vHub UDC driver"
 	depends on ARCH_ASPEED || COMPILE_TEST
+	depends on USB_LIBCOMPOSITE
 	help
 	  USB peripheral controller for the Aspeed AST2500 family
 	  SoCs supporting the "vHub" functionality and USB2.0
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
index 20ffb03ff6ac..e2927fb083cf 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/ep0.c
@@ -108,6 +108,13 @@ void ast_vhub_ep0_handle_setup(struct ast_vhub_ep *ep)
 	/* Check our state, cancel pending requests if needed */
 	if (ep->ep0.state != ep0_state_token) {
 		EPDBG(ep, "wrong state\n");
+		ast_vhub_nuke(ep, -EIO);
+
+		/*
+		 * Accept the packet regardless, this seems to happen
+		 * when stalling a SETUP packet that has an OUT data
+		 * phase.
+		 */
 		ast_vhub_nuke(ep, 0);
 		goto stall;
 	}
@@ -212,6 +219,8 @@ static void ast_vhub_ep0_do_send(struct ast_vhub_ep *ep,
 	if (chunk && req->req.buf)
 		memcpy(ep->buf, req->req.buf + req->req.actual, chunk);
 
+	vhub_dma_workaround(ep->buf);
+
 	/* Remember chunk size and trigger send */
 	reg = VHUB_EP0_SET_TX_LEN(chunk);
 	writel(reg, ep->ep0.ctlstat);
@@ -224,7 +233,7 @@ static void ast_vhub_ep0_rx_prime(struct ast_vhub_ep *ep)
 	EPVDBG(ep, "rx prime\n");
 
 	/* Prime endpoint for receiving data */
-	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat + AST_VHUB_EP0_CTRL);
+	writel(VHUB_EP0_RX_BUFF_RDY, ep->ep0.ctlstat);
 }
 
 static void ast_vhub_ep0_do_receive(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/epn.c b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
index 80c9feac5147..5939eb1e97f2 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/epn.c
+++ b/drivers/usb/gadget/udc/aspeed-vhub/epn.c
@@ -66,11 +66,16 @@ static void ast_vhub_epn_kick(struct ast_vhub_ep *ep, struct ast_vhub_req *req)
 	if (!req->req.dma) {
 
 		/* For IN transfers, copy data over first */
-		if (ep->epn.is_in)
+		if (ep->epn.is_in) {
 			memcpy(ep->buf, req->req.buf + act, chunk);
+			vhub_dma_workaround(ep->buf);
+		}
 		writel(ep->buf_dma, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
-	} else
+	} else {
+		if (ep->epn.is_in)
+			vhub_dma_workaround(req->req.buf);
 		writel(req->req.dma + act, ep->epn.regs + AST_VHUB_EP_DESC_BASE);
+	}
 
 	/* Start DMA */
 	req->active = true;
@@ -161,6 +166,7 @@ static inline unsigned int ast_vhub_count_free_descs(struct ast_vhub_ep *ep)
 static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 				   struct ast_vhub_req *req)
 {
+	struct ast_vhub_desc *desc = NULL;
 	unsigned int act = req->act_count;
 	unsigned int len = req->req.length;
 	unsigned int chunk;
@@ -177,7 +183,6 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 
 	/* While we can create descriptors */
 	while (ast_vhub_count_free_descs(ep) && req->last_desc < 0) {
-		struct ast_vhub_desc *desc;
 		unsigned int d_num;
 
 		/* Grab next free descriptor */
@@ -227,6 +232,9 @@ static void ast_vhub_epn_kick_desc(struct ast_vhub_ep *ep,
 		req->act_count = act = act + chunk;
 	}
 
+	if (likely(desc))
+		vhub_dma_workaround(desc);
+
 	/* Tell HW about new descriptors */
 	writel(VHUB_EP_DMA_SET_CPU_WPTR(ep->epn.d_next),
 	       ep->epn.regs + AST_VHUB_EP_DESC_STATUS);
diff --git a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
index 2b040257bc1f..4ed03d33a5a9 100644
--- a/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
+++ b/drivers/usb/gadget/udc/aspeed-vhub/vhub.h
@@ -462,6 +462,39 @@ enum std_req_rc {
 #define DDBG(d, fmt, ...)	do { } while(0)
 #endif
 
+static inline void vhub_dma_workaround(void *addr)
+{
+	/*
+	 * This works around a confirmed HW issue with the Aspeed chip.
+	 *
+	 * The core uses a different bus to memory than the AHB going to
+	 * the USB device controller. Due to the latter having a higher
+	 * priority than the core for arbitration on that bus, it's
+	 * possible for an MMIO to the device, followed by a DMA by the
+	 * device from memory to all be performed and services before
+	 * a previous store to memory gets completed.
+	 *
+	 * This the following scenario can happen:
+	 *
+	 *    - Driver writes to a DMA descriptor (Mbus)
+	 *    - Driver writes to the MMIO register to start the DMA (AHB)
+	 *    - The gadget sees the second write and sends a read of the
+	 *      descriptor to the memory controller (Mbus)
+	 *    - The gadget hits memory before the descriptor write
+	 *      causing it to read an obsolete value.
+	 *
+	 * Thankfully the problem is limited to the USB gadget device, other
+	 * masters in the SoC all have a lower priority than the core, thus
+	 * ensuring that the store by the core arrives first.
+	 *
+	 * The workaround consists of using a dummy read of the memory before
+	 * doing the MMIO writes. This will ensure that the previous writes
+	 * have been "pushed out".
+	 */
+	mb();
+	(void)__raw_readl((void __iomem *)addr);
+}
+
 /* core.c */
 void ast_vhub_done(struct ast_vhub_ep *ep, struct ast_vhub_req *req,
 		   int status);
diff --git a/drivers/usb/gadget/udc/r8a66597-udc.c b/drivers/usb/gadget/udc/r8a66597-udc.c
index a3ecce62662b..11e25a3f4f1f 100644
--- a/drivers/usb/gadget/udc/r8a66597-udc.c
+++ b/drivers/usb/gadget/udc/r8a66597-udc.c
@@ -832,11 +832,11 @@ static void init_controller(struct r8a66597 *r8a66597)
 
 		r8a66597_bset(r8a66597, XCKE, SYSCFG0);
 
-		msleep(3);
+		mdelay(3);
 
 		r8a66597_bset(r8a66597, PLLC, SYSCFG0);
 
-		msleep(1);
+		mdelay(1);
 
 		r8a66597_bset(r8a66597, SCKE, SYSCFG0);
 
@@ -1190,7 +1190,7 @@ __acquires(r8a66597->lock)
 	r8a66597->ep0_req->length = 2;
 	/* AV: what happens if we get called again before that gets through? */
 	spin_unlock(&r8a66597->lock);
-	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_KERNEL);
+	r8a66597_queue(r8a66597->gadget.ep0, r8a66597->ep0_req, GFP_ATOMIC);
 	spin_lock(&r8a66597->lock);
 }
 
diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c
index 1fbfd89d0a0f..387f124a8334 100644
--- a/drivers/usb/host/xhci-dbgcap.c
+++ b/drivers/usb/host/xhci-dbgcap.c
@@ -508,16 +508,18 @@ static int xhci_do_dbc_start(struct xhci_hcd *xhci)
 	return 0;
 }
 
-static void xhci_do_dbc_stop(struct xhci_hcd *xhci)
+static int xhci_do_dbc_stop(struct xhci_hcd *xhci)
 {
 	struct xhci_dbc		*dbc = xhci->dbc;
 
 	if (dbc->state == DS_DISABLED)
-		return;
+		return -1;
 
 	writel(0, &dbc->regs->control);
 	xhci_dbc_mem_cleanup(xhci);
 	dbc->state = DS_DISABLED;
+
+	return 0;
 }
 
 static int xhci_dbc_start(struct xhci_hcd *xhci)
@@ -544,6 +546,7 @@ static int xhci_dbc_start(struct xhci_hcd *xhci)
 
 static void xhci_dbc_stop(struct xhci_hcd *xhci)
 {
+	int ret;
 	unsigned long		flags;
 	struct xhci_dbc		*dbc = xhci->dbc;
 	struct dbc_port		*port = &dbc->port;
@@ -556,10 +559,11 @@ static void xhci_dbc_stop(struct xhci_hcd *xhci)
 		xhci_dbc_tty_unregister_device(xhci);
 
 	spin_lock_irqsave(&dbc->lock, flags);
-	xhci_do_dbc_stop(xhci);
+	ret = xhci_do_dbc_stop(xhci);
 	spin_unlock_irqrestore(&dbc->lock, flags);
 
-	pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
+	if (!ret)
+		pm_runtime_put_sync(xhci_to_hcd(xhci)->self.controller);
 }
 
 static void
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 8a62eee9eee1..ef350c33dc4a 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -595,7 +595,7 @@ struct xhci_ring *xhci_stream_id_to_ring(
 	if (!ep->stream_info)
 		return NULL;
 
-	if (stream_id > ep->stream_info->num_streams)
+	if (stream_id >= ep->stream_info->num_streams)
 		return NULL;
 	return ep->stream_info->stream_rings[stream_id];
 }
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 2f4850f25e82..68e6132aa8b2 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3051,6 +3051,7 @@ static void xhci_endpoint_reset(struct usb_hcd *hcd,
 	if (!list_empty(&ep->ring->td_list)) {
 		dev_err(&udev->dev, "EP not empty, refuse reset\n");
 		spin_unlock_irqrestore(&xhci->lock, flags);
+		xhci_free_command(xhci, cfg_cmd);
 		goto cleanup;
 	}
 	xhci_queue_stop_endpoint(xhci, stop_cmd, udev->slot_id, ep_index, 0);
diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
index 8abb6cbbd98a..3be40eaa1ac9 100644
--- a/drivers/usb/misc/yurex.c
+++ b/drivers/usb/misc/yurex.c
@@ -396,8 +396,7 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 			  loff_t *ppos)
 {
 	struct usb_yurex *dev;
-	int retval = 0;
-	int bytes_read = 0;
+	int len = 0;
 	char in_buffer[20];
 	unsigned long flags;
 
@@ -405,26 +404,16 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
 
 	mutex_lock(&dev->io_mutex);
 	if (!dev->interface) {		/* already disconnected */
-		retval = -ENODEV;
-		goto exit;
+		mutex_unlock(&dev->io_mutex);
+		return -ENODEV;
 	}
 
 	spin_lock_irqsave(&dev->lock, flags);
-	bytes_read = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
+	len = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
 	spin_unlock_irqrestore(&dev->lock, flags);
-
-	if (*ppos < bytes_read) {
-		if (copy_to_user(buffer, in_buffer + *ppos, bytes_read - *ppos))
-			retval = -EFAULT;
-		else {
-			retval = bytes_read - *ppos;
-			*ppos += bytes_read;
-		}
-	}
-
-exit:
 	mutex_unlock(&dev->io_mutex);
-	return retval;
+
+	return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
 }
 
 static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
diff --git a/drivers/usb/phy/phy-fsl-usb.c b/drivers/usb/phy/phy-fsl-usb.c
index 900875f326d7..f7c96d209eda 100644
--- a/drivers/usb/phy/phy-fsl-usb.c
+++ b/drivers/usb/phy/phy-fsl-usb.c
@@ -861,6 +861,7 @@ int usb_otg_start(struct platform_device *pdev)
 	if (pdata->init && pdata->init(pdev) != 0)
 		return -EINVAL;
 
+#ifdef CONFIG_PPC32
 	if (pdata->big_endian_mmio) {
 		_fsl_readl = _fsl_readl_be;
 		_fsl_writel = _fsl_writel_be;
@@ -868,6 +869,7 @@ int usb_otg_start(struct platform_device *pdev)
 		_fsl_readl = _fsl_readl_le;
 		_fsl_writel = _fsl_writel_le;
 	}
+#endif
 
 	/* request irq */
 	p_otg->irq = platform_get_irq(pdev, 0);
@@ -958,7 +960,7 @@ int usb_otg_start(struct platform_device *pdev)
 /*
  * state file in sysfs
  */
-static int show_fsl_usb2_otg_state(struct device *dev,
+static ssize_t show_fsl_usb2_otg_state(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct otg_fsm *fsm = &fsl_otg_dev->fsm;
diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
index bdd7a5ad3bf1..3bb1fff02bed 100644
--- a/drivers/usb/serial/ch341.c
+++ b/drivers/usb/serial/ch341.c
@@ -128,7 +128,7 @@ static int ch341_control_in(struct usb_device *dev,
 	r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request,
 			    USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
 			    value, index, buf, bufsize, DEFAULT_TIMEOUT);
-	if (r < bufsize) {
+	if (r < (int)bufsize) {
 		if (r >= 0) {
 			dev_err(&dev->dev,
 				"short control message received (%d < %u)\n",
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index ee0cc1d90b51..626a29d9aa58 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -149,6 +149,7 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(0x10C4, 0x8977) },	/* CEL MeshWorks DevKit Device */
 	{ USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
 	{ USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor Bridge Controller */
+	{ USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */
 	{ USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
 	{ USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long Range */
 	{ USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
diff --git a/drivers/usb/serial/keyspan_pda.c b/drivers/usb/serial/keyspan_pda.c
index 5169624d8b11..38d43c4b7ce5 100644
--- a/drivers/usb/serial/keyspan_pda.c
+++ b/drivers/usb/serial/keyspan_pda.c
@@ -369,8 +369,10 @@ static int keyspan_pda_get_modem_info(struct usb_serial *serial,
 			     3, /* get pins */
 			     USB_TYPE_VENDOR|USB_RECIP_INTERFACE|USB_DIR_IN,
 			     0, 0, data, 1, 2000);
-	if (rc >= 0)
+	if (rc == 1)
 		*value = *data;
+	else if (rc >= 0)
+		rc = -EIO;
 
 	kfree(data);
 	return rc;
diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
index fdceb46d9fc6..b580b4c7fa48 100644
--- a/drivers/usb/serial/mos7840.c
+++ b/drivers/usb/serial/mos7840.c
@@ -468,6 +468,9 @@ static void mos7840_control_callback(struct urb *urb)
 	}
 
 	dev_dbg(dev, "%s urb buffer size is %d\n", __func__, urb->actual_length);
+	if (urb->actual_length < 1)
+		goto out;
+
 	dev_dbg(dev, "%s mos7840_port->MsrLsr is %d port %d\n", __func__,
 		mos7840_port->MsrLsr, mos7840_port->port_num);
 	data = urb->transfer_buffer;
diff --git a/drivers/usb/typec/tcpm.c b/drivers/usb/typec/tcpm.c
index d961f1ec0e08..d1d20252bad8 100644
--- a/drivers/usb/typec/tcpm.c
+++ b/drivers/usb/typec/tcpm.c
@@ -725,6 +725,9 @@ static int tcpm_set_current_limit(struct tcpm_port *port, u32 max_ma, u32 mv)
 
 	tcpm_log(port, "Setting voltage/current limit %u mV %u mA", mv, max_ma);
 
+	port->supply_voltage = mv;
+	port->current_limit = max_ma;
+
 	if (port->tcpc->set_current_limit)
 		ret = port->tcpc->set_current_limit(port->tcpc, max_ma, mv);
 
@@ -2137,7 +2140,7 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port)
 			 * PPS APDO. Again skip the first sink PDO as this will
 			 * always be 5V 3A.
 			 */
-			for (j = i; j < port->nr_snk_pdo; j++) {
+			for (j = 1; j < port->nr_snk_pdo; j++) {
 				pdo = port->snk_pdo[j];
 
 				switch (pdo_type(pdo)) {
@@ -2595,8 +2598,6 @@ static void tcpm_reset_port(struct tcpm_port *port)
 	tcpm_set_attached_state(port, false);
 	port->try_src_count = 0;
 	port->try_snk_count = 0;
-	port->supply_voltage = 0;
-	port->current_limit = 0;
 	port->usb_type = POWER_SUPPLY_USB_TYPE_C;
 
 	power_supply_changed(port->psy);
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index 24ee2605b9f0..42dc1d3d71cf 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -28,5 +28,13 @@ config VFIO_PCI_INTX
 	def_bool y if !S390
 
 config VFIO_PCI_IGD
-	depends on VFIO_PCI
-	def_bool y if X86
+	bool "VFIO PCI extensions for Intel graphics (GVT-d)"
+	depends on VFIO_PCI && X86
+	default y
+	help
+	  Support for Intel IGD specific extensions to enable direct
+	  assignment to virtual machines.  This includes exposing an IGD
+	  specific firmware table and read-only copies of the host bridge
+	  and LPC bridge config space.
+
+	  To enable Intel IGD assignment through vfio-pci, say Y.
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b423a309a6e0..125b58eff936 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -28,6 +28,7 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/vgaarb.h>
+#include <linux/nospec.h>
 
 #include "vfio_pci_private.h"
 
@@ -727,6 +728,9 @@ static long vfio_pci_ioctl(void *device_data,
 			if (info.index >=
 			    VFIO_PCI_NUM_REGIONS + vdev->num_regions)
 				return -EINVAL;
+			info.index = array_index_nospec(info.index,
+							VFIO_PCI_NUM_REGIONS +
+							vdev->num_regions);
 
 			i = info.index - VFIO_PCI_NUM_REGIONS;
 
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 759a5bdd40e1..7cd63b0c1a46 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -457,17 +457,17 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 }
 
 static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
-		unsigned long tce, unsigned long size,
+		unsigned long tce, unsigned long shift,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(container->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
 	if (!mem)
 		return -EINVAL;
 
-	ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+	ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
 	if (ret)
 		return -EINVAL;
 
@@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container,
 	if (!pua)
 		return;
 
-	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
+	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift,
 			&hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
@@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 				entry + i);
 
 		ret = tce_iommu_prereg_ua_to_hpa(container,
-				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+				tce, tbl->it_page_shift, &hpa, &mem);
 		if (ret)
 			break;
 
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 2c75b33db4ac..3e5b17710a4f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -343,18 +343,16 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 	struct page *page[1];
 	struct vm_area_struct *vma;
 	struct vm_area_struct *vmas[1];
+	unsigned int flags = 0;
 	int ret;
 
+	if (prot & IOMMU_WRITE)
+		flags |= FOLL_WRITE;
+
+	down_read(&mm->mmap_sem);
 	if (mm == current->mm) {
-		ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE),
-					      page, vmas);
+		ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas);
 	} else {
-		unsigned int flags = 0;
-
-		if (prot & IOMMU_WRITE)
-			flags |= FOLL_WRITE;
-
-		down_read(&mm->mmap_sem);
 		ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
 					    vmas, NULL);
 		/*
@@ -368,8 +366,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
 			ret = -EOPNOTSUPP;
 			put_page(page[0]);
 		}
-		up_read(&mm->mmap_sem);
 	}
+	up_read(&mm->mmap_sem);
 
 	if (ret == 1) {
 		*pfn = page_to_pfn(page[0]);
diff --git a/fs/aio.c b/fs/aio.c
index 210df9da1283..27454594e37a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1896,6 +1896,11 @@ SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id,
 	return ret;
 }
 
+struct __aio_sigset {
+	const sigset_t __user	*sigmask;
+	size_t		sigsetsize;
+};
+
 SYSCALL_DEFINE6(io_pgetevents,
 		aio_context_t, ctx_id,
 		long, min_nr,
diff --git a/fs/autofs/Makefile b/fs/autofs/Makefile
index 43fedde15c26..1f85d35ec8b7 100644
--- a/fs/autofs/Makefile
+++ b/fs/autofs/Makefile
@@ -2,6 +2,6 @@
 # Makefile for the linux autofs-filesystem routines.
 #
 
-obj-$(CONFIG_AUTOFS_FS) += autofs.o
+obj-$(CONFIG_AUTOFS_FS) += autofs4.o
 
-autofs-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
+autofs4-objs := init.o inode.o root.o symlink.o waitq.o expire.o dev-ioctl.o
diff --git a/fs/autofs/dev-ioctl.c b/fs/autofs/dev-ioctl.c
index ea4ca1445ab7..86eafda4a652 100644
--- a/fs/autofs/dev-ioctl.c
+++ b/fs/autofs/dev-ioctl.c
@@ -135,6 +135,15 @@ static int validate_dev_ioctl(int cmd, struct autofs_dev_ioctl *param)
 				cmd);
 			goto out;
 		}
+	} else {
+		unsigned int inr = _IOC_NR(cmd);
+
+		if (inr == AUTOFS_DEV_IOCTL_OPENMOUNT_CMD ||
+		    inr == AUTOFS_DEV_IOCTL_REQUESTER_CMD ||
+		    inr == AUTOFS_DEV_IOCTL_ISMOUNTPOINT_CMD) {
+			err = -EINVAL;
+			goto out;
+		}
 	}
 
 	err = 0;
@@ -271,7 +280,8 @@ static int autofs_dev_ioctl_openmount(struct file *fp,
 	dev_t devid;
 	int err, fd;
 
-	/* param->path has already been checked */
+	/* param->path has been checked in validate_dev_ioctl() */
+
 	if (!param->openmount.devid)
 		return -EINVAL;
 
@@ -433,10 +443,7 @@ static int autofs_dev_ioctl_requester(struct file *fp,
 	dev_t devid;
 	int err = -ENOENT;
 
-	if (param->size <= AUTOFS_DEV_IOCTL_SIZE) {
-		err = -EINVAL;
-		goto out;
-	}
+	/* param->path has been checked in validate_dev_ioctl() */
 
 	devid = sbi->sb->s_dev;
 
@@ -521,10 +528,7 @@ static int autofs_dev_ioctl_ismountpoint(struct file *fp,
 	unsigned int devid, magic;
 	int err = -ENOENT;
 
-	if (param->size <= AUTOFS_DEV_IOCTL_SIZE) {
-		err = -EINVAL;
-		goto out;
-	}
+	/* param->path has been checked in validate_dev_ioctl() */
 
 	name = param->path;
 	type = param->ismountpoint.in.type;
diff --git a/fs/autofs/init.c b/fs/autofs/init.c
index cc9447e1903f..79ae07d9592f 100644
--- a/fs/autofs/init.c
+++ b/fs/autofs/init.c
@@ -23,7 +23,7 @@ static struct file_system_type autofs_fs_type = {
 	.kill_sb	= autofs_kill_sb,
 };
 MODULE_ALIAS_FS("autofs");
-MODULE_ALIAS("autofs4");
+MODULE_ALIAS("autofs");
 
 static int __init init_autofs_fs(void)
 {
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0ac456b52bdd..816cc921cf36 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1259,9 +1259,8 @@ static int load_elf_library(struct file *file)
 		goto out_free_ph;
 	}
 
-	len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
-			    ELF_MIN_ALIGN - 1);
-	bss = eppnt->p_memsz + eppnt->p_vaddr;
+	len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr);
+	bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr);
 	if (bss > len) {
 		error = vm_brk(len, bss - len);
 		if (error)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0dd87aaeb39a..aba25414231a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -221,7 +221,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
 	if (unlikely(ret))
-		return ret;
+		goto out;
 	ret = bio.bi_iter.bi_size;
 
 	if (iov_iter_rw(iter) == READ) {
@@ -250,12 +250,13 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 		put_page(bvec->bv_page);
 	}
 
-	if (vecs != inline_vecs)
-		kfree(vecs);
-
 	if (unlikely(bio.bi_status))
 		ret = blk_status_to_errno(bio.bi_status);
 
+out:
+	if (vecs != inline_vecs)
+		kfree(vecs);
+
 	bio_uninit(&bio);
 
 	return ret;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e55843f536bc..b3e45714d28f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4238,8 +4238,9 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 	struct extent_map *em;
 	u64 start = page_offset(page);
 	u64 end = start + PAGE_SIZE - 1;
-	struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree;
-	struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree;
+	struct btrfs_inode *btrfs_inode = BTRFS_I(page->mapping->host);
+	struct extent_io_tree *tree = &btrfs_inode->io_tree;
+	struct extent_map_tree *map = &btrfs_inode->extent_tree;
 
 	if (gfpflags_allow_blocking(mask) &&
 	    page->mapping->host->i_size > SZ_16M) {
@@ -4262,6 +4263,8 @@ int try_release_extent_mapping(struct page *page, gfp_t mask)
 					    extent_map_end(em) - 1,
 					    EXTENT_LOCKED | EXTENT_WRITEBACK,
 					    0, NULL)) {
+				set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+					&btrfs_inode->runtime_flags);
 				remove_extent_mapping(map, em);
 				/* once for the rb tree */
 				free_extent_map(em);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 43ecbe620dea..b077544b5232 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3327,11 +3327,13 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
 		if (pg) {
 			unlock_page(pg);
 			put_page(pg);
+			cmp->src_pages[i] = NULL;
 		}
 		pg = cmp->dst_pages[i];
 		if (pg) {
 			unlock_page(pg);
 			put_page(pg);
+			cmp->dst_pages[i] = NULL;
 		}
 	}
 }
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 572306036477..6702896cdb8f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1151,11 +1151,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 		return ret;
 	}
 
-	if (sctx->is_dev_replace && !is_metadata && !have_csum) {
-		sblocks_for_recheck = NULL;
-		goto nodatasum_case;
-	}
-
 	/*
 	 * read all mirrors one after the other. This includes to
 	 * re-read the extent or metadata block that failed (that was
@@ -1268,13 +1263,19 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 		goto out;
 	}
 
-	if (!is_metadata && !have_csum) {
+	/*
+	 * NOTE: Even for nodatasum case, it's still possible that it's a
+	 * compressed data extent, thus scrub_fixup_nodatasum(), which write
+	 * inode page cache onto disk, could cause serious data corruption.
+	 *
+	 * So here we could only read from disk, and hope our recovery could
+	 * reach disk before the newer write.
+	 */
+	if (0 && !is_metadata && !have_csum) {
 		struct scrub_fixup_nodatasum *fixup_nodatasum;
 
 		WARN_ON(sctx->is_dev_replace);
 
-nodatasum_case:
-
 		/*
 		 * !is_metadata and !have_csum, this means that the data
 		 * might not be COWed, that it might be modified
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e034ad9e23b4..1da162928d1a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1146,6 +1146,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 {
 	int ret;
 
+	mutex_lock(&uuid_mutex);
 	mutex_lock(&fs_devices->device_list_mutex);
 	if (fs_devices->opened) {
 		fs_devices->opened++;
@@ -1155,6 +1156,7 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		ret = open_fs_devices(fs_devices, flags, holder);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
+	mutex_unlock(&uuid_mutex);
 
 	return ret;
 }
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
index d9f001078e08..4a717d400807 100644
--- a/fs/cachefiles/bind.c
+++ b/fs/cachefiles/bind.c
@@ -218,7 +218,8 @@ static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
 			   "%s",
 			   fsdef->dentry->d_sb->s_id);
 
-	fscache_object_init(&fsdef->fscache, NULL, &cache->cache);
+	fscache_object_init(&fsdef->fscache, &fscache_fsdef_index,
+			    &cache->cache);
 
 	ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag);
 	if (ret < 0)
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index ab0bbe93b398..af2b17b21b94 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -186,12 +186,12 @@ try_again:
 	 * need to wait for it to be destroyed */
 wait_for_old_object:
 	trace_cachefiles_wait_active(object, dentry, xobject);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
 
 	if (fscache_object_is_live(&xobject->fscache)) {
 		pr_err("\n");
 		pr_err("Error: Unexpected object collision\n");
 		cachefiles_printk_object(object, xobject);
-		BUG();
 	}
 	atomic_inc(&xobject->usage);
 	write_unlock(&cache->active_lock);
@@ -248,7 +248,6 @@ wait_for_old_object:
 	goto try_again;
 
 requeue:
-	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
 	cache->cache.ops->put_object(&xobject->fscache, cachefiles_obj_put_wait_timeo);
 	_leave(" = -ETIMEDOUT");
 	return -ETIMEDOUT;
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 5082c8a49686..40f7595aad10 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -27,6 +27,7 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	struct cachefiles_one_read *monitor =
 		container_of(wait, struct cachefiles_one_read, monitor);
 	struct cachefiles_object *object;
+	struct fscache_retrieval *op = monitor->op;
 	struct wait_bit_key *key = _key;
 	struct page *page = wait->private;
 
@@ -51,16 +52,22 @@ static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 	list_del(&wait->entry);
 
 	/* move onto the action list and queue for FS-Cache thread pool */
-	ASSERT(monitor->op);
+	ASSERT(op);
 
-	object = container_of(monitor->op->op.object,
-			      struct cachefiles_object, fscache);
+	/* We need to temporarily bump the usage count as we don't own a ref
+	 * here otherwise cachefiles_read_copier() may free the op between the
+	 * monitor being enqueued on the op->to_do list and the op getting
+	 * enqueued on the work queue.
+	 */
+	fscache_get_retrieval(op);
 
+	object = container_of(op->op.object, struct cachefiles_object, fscache);
 	spin_lock(&object->work_lock);
-	list_add_tail(&monitor->op_link, &monitor->op->to_do);
+	list_add_tail(&monitor->op_link, &op->to_do);
 	spin_unlock(&object->work_lock);
 
-	fscache_enqueue_retrieval(monitor->op);
+	fscache_enqueue_retrieval(op);
+	fscache_put_retrieval(op);
 	return 0;
 }
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index bd78da59a4fd..c923c7854027 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -423,7 +423,7 @@ struct smb_version_operations {
 	void (*set_oplock_level)(struct cifsInodeInfo *, __u32, unsigned int,
 				 bool *);
 	/* create lease context buffer for CREATE request */
-	char * (*create_lease_buf)(u8 *, u8);
+	char * (*create_lease_buf)(u8 *lease_key, u8 oplock);
 	/* parse lease context buffer and return oplock/epoch info */
 	__u8 (*parse_lease_buf)(void *buf, unsigned int *epoch, char *lkey);
 	ssize_t (*copychunk_range)(const unsigned int,
@@ -1416,6 +1416,7 @@ typedef int (mid_handle_t)(struct TCP_Server_Info *server,
 /* one of these for every pending CIFS request to the server */
 struct mid_q_entry {
 	struct list_head qhead;	/* mids waiting on reply from this server */
+	struct kref refcount;
 	struct TCP_Server_Info *server;	/* server corresponding to this mid */
 	__u64 mid;		/* multiplex id */
 	__u32 pid;		/* process id */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 03018be17283..1890f534c88b 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -82,6 +82,7 @@ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
 					struct TCP_Server_Info *server);
 extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
 extern void cifs_delete_mid(struct mid_q_entry *mid);
+extern void cifs_mid_q_entry_release(struct mid_q_entry *midEntry);
 extern void cifs_wake_up_task(struct mid_q_entry *mid);
 extern int cifs_handle_standard(struct TCP_Server_Info *server,
 				struct mid_q_entry *mid);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index d352da325de3..93408eab92e7 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -157,8 +157,14 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command)
 	 * greater than cifs socket timeout which is 7 seconds
 	 */
 	while (server->tcpStatus == CifsNeedReconnect) {
-		wait_event_interruptible_timeout(server->response_q,
-			(server->tcpStatus != CifsNeedReconnect), 10 * HZ);
+		rc = wait_event_interruptible_timeout(server->response_q,
+						      (server->tcpStatus != CifsNeedReconnect),
+						      10 * HZ);
+		if (rc < 0) {
+			cifs_dbg(FYI, "%s: aborting reconnect due to a received"
+				 " signal by the process\n", __func__);
+			return -ERESTARTSYS;
+		}
 
 		/* are we still trying to reconnect? */
 		if (server->tcpStatus != CifsNeedReconnect)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a57da1b88bdf..5df2c0698cda 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -924,6 +924,7 @@ next_pdu:
 				server->pdu_size = next_offset;
 		}
 
+		mid_entry = NULL;
 		if (server->ops->is_transform_hdr &&
 		    server->ops->receive_transform &&
 		    server->ops->is_transform_hdr(buf)) {
@@ -938,8 +939,11 @@ next_pdu:
 				length = mid_entry->receive(server, mid_entry);
 		}
 
-		if (length < 0)
+		if (length < 0) {
+			if (mid_entry)
+				cifs_mid_q_entry_release(mid_entry);
 			continue;
+		}
 
 		if (server->large_buf)
 			buf = server->bigbuf;
@@ -956,6 +960,8 @@ next_pdu:
 
 			if (!mid_entry->multiRsp || mid_entry->multiEnd)
 				mid_entry->callback(mid_entry);
+
+			cifs_mid_q_entry_release(mid_entry);
 		} else if (server->ops->is_oplock_break &&
 			   server->ops->is_oplock_break(buf, server)) {
 			cifs_dbg(FYI, "Received oplock break\n");
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index aff8ce8ba34d..646dcd149de1 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -107,6 +107,7 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer)
 		if (compare_mid(mid->mid, buf) &&
 		    mid->mid_state == MID_REQUEST_SUBMITTED &&
 		    le16_to_cpu(mid->command) == buf->Command) {
+			kref_get(&mid->refcount);
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index 788412675723..4ed10dd086e6 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -41,7 +41,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 	int rc;
 	__le16 *smb2_path;
 	struct smb2_file_all_info *smb2_data = NULL;
-	__u8 smb2_oplock[17];
+	__u8 smb2_oplock;
 	struct cifs_fid *fid = oparms->fid;
 	struct network_resiliency_req nr_ioctl_req;
 
@@ -59,12 +59,9 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 	}
 
 	oparms->desired_access |= FILE_READ_ATTRIBUTES;
-	*smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH;
+	smb2_oplock = SMB2_OPLOCK_LEVEL_BATCH;
 
-	if (oparms->tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LEASING)
-		memcpy(smb2_oplock + 1, fid->lease_key, SMB2_LEASE_KEY_SIZE);
-
-	rc = SMB2_open(xid, oparms, smb2_path, smb2_oplock, smb2_data, NULL,
+	rc = SMB2_open(xid, oparms, smb2_path, &smb2_oplock, smb2_data, NULL,
 		       NULL);
 	if (rc)
 		goto out;
@@ -101,7 +98,7 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		move_smb2_info_to_cifs(buf, smb2_data);
 	}
 
-	*oplock = *smb2_oplock;
+	*oplock = smb2_oplock;
 out:
 	kfree(smb2_data);
 	kfree(smb2_path);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 0356b5559c71..ea92a38b2f08 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -203,6 +203,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 		if ((mid->mid == wire_mid) &&
 		    (mid->mid_state == MID_REQUEST_SUBMITTED) &&
 		    (mid->command == shdr->Command)) {
+			kref_get(&mid->refcount);
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
@@ -855,6 +856,8 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_set_ea(xid, tcon, fid.persistent_fid, fid.volatile_fid, ea,
 			 len);
+	kfree(ea);
+
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 
 	return rc;
@@ -2219,8 +2222,7 @@ smb2_create_lease_buf(u8 *lease_key, u8 oplock)
 	if (!buf)
 		return NULL;
 
-	buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
-	buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+	memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
 	buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
 
 	buf->ccontext.DataOffset = cpu_to_le16(offsetof
@@ -2246,8 +2248,7 @@ smb3_create_lease_buf(u8 *lease_key, u8 oplock)
 	if (!buf)
 		return NULL;
 
-	buf->lcontext.LeaseKeyLow = cpu_to_le64(*((u64 *)lease_key));
-	buf->lcontext.LeaseKeyHigh = cpu_to_le64(*((u64 *)(lease_key + 8)));
+	memcpy(&buf->lcontext.LeaseKey, lease_key, SMB2_LEASE_KEY_SIZE);
 	buf->lcontext.LeaseState = map_oplock_to_lease(oplock);
 
 	buf->ccontext.DataOffset = cpu_to_le16(offsetof
@@ -2284,8 +2285,7 @@ smb3_parse_lease_buf(void *buf, unsigned int *epoch, char *lease_key)
 	if (lc->lcontext.LeaseFlags & SMB2_LEASE_FLAG_BREAK_IN_PROGRESS)
 		return SMB2_OPLOCK_LEVEL_NOCHANGE;
 	if (lease_key)
-		memcpy(lease_key, &lc->lcontext.LeaseKeyLow,
-		       SMB2_LEASE_KEY_SIZE);
+		memcpy(lease_key, &lc->lcontext.LeaseKey, SMB2_LEASE_KEY_SIZE);
 	return le32_to_cpu(lc->lcontext.LeaseState);
 }
 
@@ -2521,7 +2521,7 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
 	if (!tr_hdr)
 		goto err_free_iov;
 
-	orig_len = smb2_rqst_len(old_rq, false);
+	orig_len = smb_rqst_len(server, old_rq);
 
 	/* fill the 2nd iov with a transform header */
 	fill_transform_hdr(tr_hdr, orig_len, old_rq);
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 810b85787c91..3c92678cb45b 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -155,7 +155,7 @@ out:
 static int
 smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 {
-	int rc = 0;
+	int rc;
 	struct nls_table *nls_codepage;
 	struct cifs_ses *ses;
 	struct TCP_Server_Info *server;
@@ -166,10 +166,10 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	 * for those three - in the calling routine.
 	 */
 	if (tcon == NULL)
-		return rc;
+		return 0;
 
 	if (smb2_command == SMB2_TREE_CONNECT)
-		return rc;
+		return 0;
 
 	if (tcon->tidStatus == CifsExiting) {
 		/*
@@ -212,8 +212,14 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 			return -EAGAIN;
 		}
 
-		wait_event_interruptible_timeout(server->response_q,
-			(server->tcpStatus != CifsNeedReconnect), 10 * HZ);
+		rc = wait_event_interruptible_timeout(server->response_q,
+						      (server->tcpStatus != CifsNeedReconnect),
+						      10 * HZ);
+		if (rc < 0) {
+			cifs_dbg(FYI, "%s: aborting reconnect due to a received"
+				 " signal by the process\n", __func__);
+			return -ERESTARTSYS;
+		}
 
 		/* are we still trying to reconnect? */
 		if (server->tcpStatus != CifsNeedReconnect)
@@ -231,7 +237,7 @@ smb2_reconnect(__le16 smb2_command, struct cifs_tcon *tcon)
 	}
 
 	if (!tcon->ses->need_reconnect && !tcon->need_reconnect)
-		return rc;
+		return 0;
 
 	nls_codepage = load_nls_default();
 
@@ -340,7 +346,10 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		return rc;
 
 	/* BB eventually switch this to SMB2 specific small buf size */
-	*request_buf = cifs_small_buf_get();
+	if (smb2_command == SMB2_SET_INFO)
+		*request_buf = cifs_buf_get();
+	else
+		*request_buf = cifs_small_buf_get();
 	if (*request_buf == NULL) {
 		/* BB should we add a retry in here if not a writepage? */
 		return -ENOMEM;
@@ -1707,12 +1716,12 @@ parse_lease_state(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp,
 
 static int
 add_lease_context(struct TCP_Server_Info *server, struct kvec *iov,
-		  unsigned int *num_iovec, __u8 *oplock)
+		  unsigned int *num_iovec, u8 *lease_key, __u8 *oplock)
 {
 	struct smb2_create_req *req = iov[0].iov_base;
 	unsigned int num = *num_iovec;
 
-	iov[num].iov_base = server->ops->create_lease_buf(oplock+1, *oplock);
+	iov[num].iov_base = server->ops->create_lease_buf(lease_key, *oplock);
 	if (iov[num].iov_base == NULL)
 		return -ENOMEM;
 	iov[num].iov_len = server->vals->create_lease_size;
@@ -2172,7 +2181,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	    *oplock == SMB2_OPLOCK_LEVEL_NONE)
 		req->RequestedOplockLevel = *oplock;
 	else {
-		rc = add_lease_context(server, iov, &n_iov, oplock);
+		rc = add_lease_context(server, iov, &n_iov,
+				       oparms->fid->lease_key, oplock);
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
@@ -3720,7 +3730,7 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
 			    &rsp_iov);
-	cifs_small_buf_release(req);
+	cifs_buf_release(req);
 	rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 824dddeee3f2..a671adcc44a6 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -678,16 +678,14 @@ struct create_context {
 #define SMB2_LEASE_KEY_SIZE 16
 
 struct lease_context {
-	__le64 LeaseKeyLow;
-	__le64 LeaseKeyHigh;
+	u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le32 LeaseState;
 	__le32 LeaseFlags;
 	__le64 LeaseDuration;
 } __packed;
 
 struct lease_context_v2 {
-	__le64 LeaseKeyLow;
-	__le64 LeaseKeyHigh;
+	u8 LeaseKey[SMB2_LEASE_KEY_SIZE];
 	__le32 LeaseState;
 	__le32 LeaseFlags;
 	__le64 LeaseDuration;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 3ae208ac2a77..6e6a4f2ec890 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -113,8 +113,8 @@ extern int smb2_unlock_range(struct cifsFileInfo *cfile,
 extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
 extern void smb2_reconnect_server(struct work_struct *work);
 extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
-extern unsigned long
-smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker);
+extern unsigned long smb_rqst_len(struct TCP_Server_Info *server,
+				  struct smb_rqst *rqst);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 51b9437c3c7b..719d55e63d88 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -173,6 +173,8 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	struct kvec *iov = rqst->rq_iov;
 	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
+	struct shash_desc *shash = &server->secmech.sdeschmacsha256->shash;
+	struct smb_rqst drqst;
 
 	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
@@ -190,21 +192,39 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	}
 
 	rc = crypto_shash_setkey(server->secmech.hmacsha256,
-		ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
+				 ses->auth_key.response, SMB2_NTLMV2_SESSKEY_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not update with response\n", __func__);
 		return rc;
 	}
 
-	rc = crypto_shash_init(&server->secmech.sdeschmacsha256->shash);
+	rc = crypto_shash_init(shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init sha256", __func__);
 		return rc;
 	}
 
-	rc = __cifs_calc_signature(rqst, server, sigptr,
-		&server->secmech.sdeschmacsha256->shash);
+	/*
+	 * For SMB2+, __cifs_calc_signature() expects to sign only the actual
+	 * data, that is, iov[0] should not contain a rfc1002 length.
+	 *
+	 * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to
+	 * __cifs_calc_signature().
+	 */
+	drqst = *rqst;
+	if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) {
+		rc = crypto_shash_update(shash, iov[0].iov_base,
+					 iov[0].iov_len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			return rc;
+		}
+		drqst.rq_iov++;
+		drqst.rq_nvec--;
+	}
 
+	rc = __cifs_calc_signature(&drqst, server, sigptr, shash);
 	if (!rc)
 		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
@@ -408,12 +428,14 @@ generate_smb311signingkey(struct cifs_ses *ses)
 int
 smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
-	int rc = 0;
+	int rc;
 	unsigned char smb3_signature[SMB2_CMACAES_SIZE];
 	unsigned char *sigptr = smb3_signature;
 	struct kvec *iov = rqst->rq_iov;
 	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
+	struct shash_desc *shash = &server->secmech.sdesccmacaes->shash;
+	struct smb_rqst drqst;
 
 	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
@@ -425,8 +447,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
 
 	rc = crypto_shash_setkey(server->secmech.cmacaes,
-		ses->smb3signingkey, SMB2_CMACAES_SIZE);
-
+				 ses->smb3signingkey, SMB2_CMACAES_SIZE);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not set key for cmac aes\n", __func__);
 		return rc;
@@ -437,15 +458,33 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	 * so unlike smb2 case we do not have to check here if secmech are
 	 * initialized
 	 */
-	rc = crypto_shash_init(&server->secmech.sdesccmacaes->shash);
+	rc = crypto_shash_init(shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init cmac aes\n", __func__);
 		return rc;
 	}
 
-	rc = __cifs_calc_signature(rqst, server, sigptr,
-				   &server->secmech.sdesccmacaes->shash);
+	/*
+	 * For SMB2+, __cifs_calc_signature() expects to sign only the actual
+	 * data, that is, iov[0] should not contain a rfc1002 length.
+	 *
+	 * Sign the rfc1002 length prior to passing the data (iov[1-N]) down to
+	 * __cifs_calc_signature().
+	 */
+	drqst = *rqst;
+	if (drqst.rq_nvec >= 2 && iov[0].iov_len == 4) {
+		rc = crypto_shash_update(shash, iov[0].iov_base,
+					 iov[0].iov_len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			return rc;
+		}
+		drqst.rq_iov++;
+		drqst.rq_nvec--;
+	}
 
+	rc = __cifs_calc_signature(&drqst, server, sigptr, shash);
 	if (!rc)
 		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
@@ -548,6 +587,7 @@ smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
 	memset(temp, 0, sizeof(struct mid_q_entry));
+	kref_init(&temp->refcount);
 	temp->mid = le64_to_cpu(shdr->MessageId);
 	temp->pid = current->pid;
 	temp->command = shdr->Command; /* Always LE */
diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c
index 6fd94d9ffac2..c55ea4e6201b 100644
--- a/fs/cifs/smbdirect.c
+++ b/fs/cifs/smbdirect.c
@@ -2083,8 +2083,9 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg)
  * rqst: the data to write
  * return value: 0 if successfully write, otherwise error code
  */
-int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
+int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
+	struct smbd_connection *info = server->smbd_conn;
 	struct kvec vec;
 	int nvecs;
 	int size;
@@ -2118,7 +2119,7 @@ int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst)
 	 * rq_tailsz to PAGE_SIZE when the buffer has multiple pages and
 	 * ends at page boundary
 	 */
-	buflen = smb2_rqst_len(rqst, true);
+	buflen = smb_rqst_len(server, rqst);
 
 	if (buflen + sizeof(struct smbd_data_transfer) >
 		info->max_fragmented_send_size) {
diff --git a/fs/cifs/smbdirect.h b/fs/cifs/smbdirect.h
index 1e419c21dc60..a11096254f29 100644
--- a/fs/cifs/smbdirect.h
+++ b/fs/cifs/smbdirect.h
@@ -292,7 +292,7 @@ void smbd_destroy(struct smbd_connection *info);
 
 /* Interface for carrying upper layer I/O through send/recv */
 int smbd_recv(struct smbd_connection *info, struct msghdr *msg);
-int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst);
+int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst);
 
 enum mr_state {
 	MR_READY,
@@ -332,7 +332,7 @@ static inline void *smbd_get_connection(
 static inline int smbd_reconnect(struct TCP_Server_Info *server) {return -1; }
 static inline void smbd_destroy(struct smbd_connection *info) {}
 static inline int smbd_recv(struct smbd_connection *info, struct msghdr *msg) {return -1; }
-static inline int smbd_send(struct smbd_connection *info, struct smb_rqst *rqst) {return -1; }
+static inline int smbd_send(struct TCP_Server_Info *server, struct smb_rqst *rqst) {return -1; }
 #endif
 
 #endif
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index fb57dfbfb749..a341ec839c83 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -61,6 +61,7 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
 	memset(temp, 0, sizeof(struct mid_q_entry));
+	kref_init(&temp->refcount);
 	temp->mid = get_mid(smb_buffer);
 	temp->pid = current->pid;
 	temp->command = cpu_to_le16(smb_buffer->Command);
@@ -82,6 +83,21 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	return temp;
 }
 
+static void _cifs_mid_q_entry_release(struct kref *refcount)
+{
+	struct mid_q_entry *mid = container_of(refcount, struct mid_q_entry,
+					       refcount);
+
+	mempool_free(mid, cifs_mid_poolp);
+}
+
+void cifs_mid_q_entry_release(struct mid_q_entry *midEntry)
+{
+	spin_lock(&GlobalMid_Lock);
+	kref_put(&midEntry->refcount, _cifs_mid_q_entry_release);
+	spin_unlock(&GlobalMid_Lock);
+}
+
 void
 DeleteMidQEntry(struct mid_q_entry *midEntry)
 {
@@ -110,7 +126,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 		}
 	}
 #endif
-	mempool_free(midEntry, cifs_mid_poolp);
+	cifs_mid_q_entry_release(midEntry);
 }
 
 void
@@ -202,14 +218,15 @@ smb_send_kvec(struct TCP_Server_Info *server, struct msghdr *smb_msg,
 }
 
 unsigned long
-smb2_rqst_len(struct smb_rqst *rqst, bool skip_rfc1002_marker)
+smb_rqst_len(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
 	unsigned int i;
 	struct kvec *iov;
 	int nvec;
 	unsigned long buflen = 0;
 
-	if (skip_rfc1002_marker && rqst->rq_iov[0].iov_len == 4) {
+	if (server->vals->header_preamble_size == 0 &&
+	    rqst->rq_nvec >= 2 && rqst->rq_iov[0].iov_len == 4) {
 		iov = &rqst->rq_iov[1];
 		nvec = rqst->rq_nvec - 1;
 	} else {
@@ -260,7 +277,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	__be32 rfc1002_marker;
 
 	if (cifs_rdma_enabled(server) && server->smbd_conn) {
-		rc = smbd_send(server->smbd_conn, rqst);
+		rc = smbd_send(server, rqst);
 		goto smbd_done;
 	}
 	if (ssocket == NULL)
@@ -271,7 +288,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 				(char *)&val, sizeof(val));
 
 	for (j = 0; j < num_rqst; j++)
-		send_length += smb2_rqst_len(&rqst[j], true);
+		send_length += smb_rqst_len(server, &rqst[j]);
 	rfc1002_marker = cpu_to_be32(send_length);
 
 	/* Generate a rfc1002 marker for SMB2+ */
diff --git a/fs/exec.c b/fs/exec.c
index 2d4e0075bd24..bdd0eacefdf5 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -290,15 +290,15 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	struct vm_area_struct *vma = NULL;
 	struct mm_struct *mm = bprm->mm;
 
-	bprm->vma = vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	bprm->vma = vma = vm_area_alloc(mm);
 	if (!vma)
 		return -ENOMEM;
+	vma_set_anonymous(vma);
 
 	if (down_write_killable(&mm->mmap_sem)) {
 		err = -EINTR;
 		goto err_free;
 	}
-	vma->vm_mm = mm;
 
 	/*
 	 * Place the stack at the largest stack address the architecture
@@ -311,7 +311,6 @@ static int __bprm_mm_init(struct linux_binprm *bprm)
 	vma->vm_start = vma->vm_end - PAGE_SIZE;
 	vma->vm_flags = VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP;
 	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	err = insert_vm_struct(mm, vma);
 	if (err)
@@ -326,7 +325,7 @@ err:
 	up_write(&mm->mmap_sem);
 err_free:
 	bprm->vma = NULL;
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return err;
 }
 
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index b00481c475cb..aa52d87985aa 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -184,7 +184,6 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 	unsigned int bit, bit_max;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t start, tmp;
-	int flex_bg = 0;
 
 	J_ASSERT_BH(bh, buffer_locked(bh));
 
@@ -207,22 +206,19 @@ static int ext4_init_block_bitmap(struct super_block *sb,
 
 	start = ext4_group_first_block_no(sb, block_group);
 
-	if (ext4_has_feature_flex_bg(sb))
-		flex_bg = 1;
-
 	/* Set bits for block and inode bitmaps, and inode table */
 	tmp = ext4_block_bitmap(sb, gdp);
-	if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+	if (ext4_block_in_group(sb, tmp, block_group))
 		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 
 	tmp = ext4_inode_bitmap(sb, gdp);
-	if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+	if (ext4_block_in_group(sb, tmp, block_group))
 		ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 
 	tmp = ext4_inode_table(sb, gdp);
 	for (; tmp < ext4_inode_table(sb, gdp) +
 		     sbi->s_itb_per_group; tmp++) {
-		if (!flex_bg || ext4_block_in_group(sb, tmp, block_group))
+		if (ext4_block_in_group(sb, tmp, block_group))
 			ext4_set_bit(EXT4_B2C(sbi, tmp - start), bh->b_data);
 	}
 
@@ -372,6 +368,8 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
+	if (buffer_verified(bh))
+		goto verified;
 	if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group,
 			desc, bh))) {
 		ext4_unlock_group(sb, block_group);
@@ -390,6 +388,7 @@ static int ext4_validate_block_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 	}
 	set_buffer_verified(bh);
+verified:
 	ext4_unlock_group(sb, block_group);
 	return 0;
 }
@@ -442,7 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 		goto verify;
 	}
 	ext4_lock_group(sb, block_group);
-	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
+		if (block_group == 0) {
+			ext4_unlock_group(sb, block_group);
+			unlock_buffer(bh);
+			ext4_error(sb, "Block bitmap for bg 0 marked "
+				   "uninitialized");
+			err = -EFSCORRUPTED;
+			goto out;
+		}
 		err = ext4_init_block_bitmap(sb, bh, block_group, desc);
 		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0b127853c584..7c7123f265c2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1114,6 +1114,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DIOREAD_NOLOCK	0x400000 /* Enable support for dio read nolocking */
 #define EXT4_MOUNT_JOURNAL_CHECKSUM	0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT	0x1000000 /* Journal Async Commit */
+#define EXT4_MOUNT_WARN_ON_ERROR	0x2000000 /* Trigger WARN_ON on error */
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
@@ -1507,11 +1508,6 @@ static inline struct ext4_inode_info *EXT4_I(struct inode *inode)
 static inline int ext4_valid_inum(struct super_block *sb, unsigned long ino)
 {
 	return ino == EXT4_ROOT_INO ||
-		ino == EXT4_USR_QUOTA_INO ||
-		ino == EXT4_GRP_QUOTA_INO ||
-		ino == EXT4_BOOT_LOADER_INO ||
-		ino == EXT4_JOURNAL_INO ||
-		ino == EXT4_RESIZE_INO ||
 		(ino >= EXT4_FIRST_INO(sb) &&
 		 ino <= le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count));
 }
@@ -3018,9 +3014,6 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
 struct iomap;
 extern int ext4_inline_data_iomap(struct inode *inode, struct iomap *iomap);
 
-extern int ext4_try_to_evict_inline_data(handle_t *handle,
-					 struct inode *inode,
-					 int needed);
 extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
 
 extern int ext4_convert_inline_data(struct inode *inode);
diff --git a/fs/ext4/ext4_extents.h b/fs/ext4/ext4_extents.h
index 98fb0c119c68..adf6668b596f 100644
--- a/fs/ext4/ext4_extents.h
+++ b/fs/ext4/ext4_extents.h
@@ -91,6 +91,7 @@ struct ext4_extent_header {
 };
 
 #define EXT4_EXT_MAGIC		cpu_to_le16(0xf30a)
+#define EXT4_MAX_EXTENT_DEPTH 5
 
 #define EXT4_EXTENT_TAIL_OFFSET(hdr) \
 	(sizeof(struct ext4_extent_header) + \
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 0057fe3f248d..8ce6fd5b10dd 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -869,6 +869,12 @@ ext4_find_extent(struct inode *inode, ext4_lblk_t block,
 
 	eh = ext_inode_hdr(inode);
 	depth = ext_depth(inode);
+	if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) {
+		EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d",
+				 depth);
+		ret = -EFSCORRUPTED;
+		goto err;
+	}
 
 	if (path) {
 		ext4_ext_drop_refs(path);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f525f909b559..f336cbc6e932 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -90,6 +90,8 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		return -EFSCORRUPTED;
 
 	ext4_lock_group(sb, block_group);
+	if (buffer_verified(bh))
+		goto verified;
 	blk = ext4_inode_bitmap(sb, desc);
 	if (!ext4_inode_bitmap_csum_verify(sb, block_group, desc, bh,
 					   EXT4_INODES_PER_GROUP(sb) / 8)) {
@@ -101,6 +103,7 @@ static int ext4_validate_inode_bitmap(struct super_block *sb,
 		return -EFSBADCRC;
 	}
 	set_buffer_verified(bh);
+verified:
 	ext4_unlock_group(sb, block_group);
 	return 0;
 }
@@ -150,7 +153,16 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	}
 
 	ext4_lock_group(sb, block_group);
-	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT))) {
+		if (block_group == 0) {
+			ext4_unlock_group(sb, block_group);
+			unlock_buffer(bh);
+			ext4_error(sb, "Inode bitmap for bg 0 marked "
+				   "uninitialized");
+			err = -EFSCORRUPTED;
+			goto out;
+		}
 		memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
 		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
 				     sb->s_blocksize * 8, bh->b_data);
@@ -994,7 +1006,8 @@ got:
 
 		/* recheck and clear flag under lock if we still need to */
 		ext4_lock_group(sb, group);
-		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+		if (ext4_has_group_desc_csum(sb) &&
+		    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 			ext4_free_group_clusters_set(sb, gdp,
 				ext4_free_clusters_after_init(sb, group, gdp));
@@ -1375,7 +1388,10 @@ int ext4_init_inode_table(struct super_block *sb, ext4_group_t group,
 			    ext4_itable_unused_count(sb, gdp)),
 			    sbi->s_inodes_per_block);
 
-	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group)) {
+	if ((used_blks < 0) || (used_blks > sbi->s_itb_per_group) ||
+	    ((group == 0) && ((EXT4_INODES_PER_GROUP(sb) -
+			       ext4_itable_unused_count(sb, gdp)) <
+			      EXT4_FIRST_INO(sb)))) {
 		ext4_error(sb, "Something is wrong with group %u: "
 			   "used itable blocks: %d; "
 			   "itable unused count: %u",
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 285ed1588730..3543fe80a3c4 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -437,6 +437,7 @@ static int ext4_destroy_inline_data_nolock(handle_t *handle,
 
 	memset((void *)ext4_raw_inode(&is.iloc)->i_block,
 		0, EXT4_MIN_INLINE_DATA_SIZE);
+	memset(ei->i_data, 0, EXT4_MIN_INLINE_DATA_SIZE);
 
 	if (ext4_has_feature_extents(inode->i_sb)) {
 		if (S_ISDIR(inode->i_mode) ||
@@ -681,6 +682,10 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 		goto convert;
 	}
 
+	ret = ext4_journal_get_write_access(handle, iloc.bh);
+	if (ret)
+		goto out;
+
 	flags |= AOP_FLAG_NOFS;
 
 	page = grab_cache_page_write_begin(mapping, 0, flags);
@@ -709,7 +714,7 @@ int ext4_try_to_write_inline_data(struct address_space *mapping,
 out_up_read:
 	up_read(&EXT4_I(inode)->xattr_sem);
 out:
-	if (handle)
+	if (handle && (ret != 1))
 		ext4_journal_stop(handle);
 	brelse(iloc.bh);
 	return ret;
@@ -751,6 +756,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 
 	ext4_write_unlock_xattr(inode, &no_expand);
 	brelse(iloc.bh);
+	mark_inode_dirty(inode);
 out:
 	return copied;
 }
@@ -886,18 +892,17 @@ retry_journal:
 	flags |= AOP_FLAG_NOFS;
 
 	if (ret == -ENOSPC) {
+		ext4_journal_stop(handle);
 		ret = ext4_da_convert_inline_data_to_extent(mapping,
 							    inode,
 							    flags,
 							    fsdata);
-		ext4_journal_stop(handle);
 		if (ret == -ENOSPC &&
 		    ext4_should_retry_alloc(inode->i_sb, &retries))
 			goto retry_journal;
 		goto out;
 	}
 
-
 	page = grab_cache_page_write_begin(mapping, 0, flags);
 	if (!page) {
 		ret = -ENOMEM;
@@ -915,6 +920,9 @@ retry_journal:
 		if (ret < 0)
 			goto out_release_page;
 	}
+	ret = ext4_journal_get_write_access(handle, iloc.bh);
+	if (ret)
+		goto out_release_page;
 
 	up_read(&EXT4_I(inode)->xattr_sem);
 	*pagep = page;
@@ -935,7 +943,6 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  unsigned len, unsigned copied,
 				  struct page *page)
 {
-	int i_size_changed = 0;
 	int ret;
 
 	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
@@ -953,10 +960,8 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 	 * But it's important to update i_size while still holding page lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
 	 */
-	if (pos+copied > inode->i_size) {
+	if (pos+copied > inode->i_size)
 		i_size_write(inode, pos+copied);
-		i_size_changed = 1;
-	}
 	unlock_page(page);
 	put_page(page);
 
@@ -966,8 +971,7 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed)
-		mark_inode_dirty(inode);
+	mark_inode_dirty(inode);
 
 	return copied;
 }
@@ -1890,42 +1894,6 @@ out:
 	return (error < 0 ? error : 0);
 }
 
-/*
- * Called during xattr set, and if we can sparse space 'needed',
- * just create the extent tree evict the data to the outer block.
- *
- * We use jbd2 instead of page cache to move data to the 1st block
- * so that the whole transaction can be committed as a whole and
- * the data isn't lost because of the delayed page cache write.
- */
-int ext4_try_to_evict_inline_data(handle_t *handle,
-				  struct inode *inode,
-				  int needed)
-{
-	int error;
-	struct ext4_xattr_entry *entry;
-	struct ext4_inode *raw_inode;
-	struct ext4_iloc iloc;
-
-	error = ext4_get_inode_loc(inode, &iloc);
-	if (error)
-		return error;
-
-	raw_inode = ext4_raw_inode(&iloc);
-	entry = (struct ext4_xattr_entry *)((void *)raw_inode +
-					    EXT4_I(inode)->i_inline_off);
-	if (EXT4_XATTR_LEN(entry->e_name_len) +
-	    EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
-		error = -ENOSPC;
-		goto out;
-	}
-
-	error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-out:
-	brelse(iloc.bh);
-	return error;
-}
-
 int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 {
 	handle_t *handle;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 2ea07efbe016..4efe77286ecd 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -402,9 +402,9 @@ static int __check_block_validity(struct inode *inode, const char *func,
 	if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), map->m_pblk,
 				   map->m_len)) {
 		ext4_error_inode(inode, func, line, map->m_pblk,
-				 "lblock %lu mapped to illegal pblock "
+				 "lblock %lu mapped to illegal pblock %llu "
 				 "(length %d)", (unsigned long) map->m_lblk,
-				 map->m_len);
+				 map->m_pblk, map->m_len);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -1389,9 +1389,10 @@ static int ext4_write_end(struct file *file,
 	loff_t old_size = inode->i_size;
 	int ret = 0, ret2;
 	int i_size_changed = 0;
+	int inline_data = ext4_has_inline_data(inode);
 
 	trace_ext4_write_end(inode, pos, len, copied);
-	if (ext4_has_inline_data(inode)) {
+	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
 		if (ret < 0) {
@@ -1419,7 +1420,7 @@ static int ext4_write_end(struct file *file,
 	 * ordering of page lock and transaction start for journaling
 	 * filesystems.
 	 */
-	if (i_size_changed)
+	if (i_size_changed || inline_data)
 		ext4_mark_inode_dirty(handle, inode);
 
 	if (pos + len > inode->i_size && ext4_can_truncate(inode))
@@ -1493,6 +1494,7 @@ static int ext4_journalled_write_end(struct file *file,
 	int partial = 0;
 	unsigned from, to;
 	int size_changed = 0;
+	int inline_data = ext4_has_inline_data(inode);
 
 	trace_ext4_journalled_write_end(inode, pos, len, copied);
 	from = pos & (PAGE_SIZE - 1);
@@ -1500,7 +1502,7 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode)) {
+	if (inline_data) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
 		if (ret < 0) {
@@ -1531,7 +1533,7 @@ static int ext4_journalled_write_end(struct file *file,
 	if (old_size < pos)
 		pagecache_isize_extended(inode, old_size, pos);
 
-	if (size_changed) {
+	if (size_changed || inline_data) {
 		ret2 = ext4_mark_inode_dirty(handle, inode);
 		if (!ret)
 			ret = ret2;
@@ -2028,11 +2030,7 @@ static int __ext4_journalled_writepage(struct page *page,
 	}
 
 	if (inline_data) {
-		BUFFER_TRACE(inode_bh, "get write access");
-		ret = ext4_journal_get_write_access(handle, inode_bh);
-
-		err = ext4_handle_dirty_metadata(handle, inode, inode_bh);
-
+		ret = ext4_mark_inode_dirty(handle, inode);
 	} else {
 		ret = ext4_walk_page_buffers(handle, page_bufs, 0, len, NULL,
 					     do_journal_get_write_access);
@@ -4506,7 +4504,8 @@ static int __ext4_get_inode_loc(struct inode *inode,
 	int			inodes_per_block, inode_offset;
 
 	iloc->bh = NULL;
-	if (!ext4_valid_inum(sb, inode->i_ino))
+	if (inode->i_ino < EXT4_ROOT_INO ||
+	    inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
 		return -EFSCORRUPTED;
 
 	iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 6eae2b91aafa..f7ab34088162 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2423,7 +2423,8 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 	 * initialize bb_free to be able to skip
 	 * empty groups without initialization
 	 */
-	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 		meta_group_info[i]->bb_free =
 			ext4_free_clusters_after_init(sb, group, desc);
 	} else {
@@ -2989,7 +2990,8 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
 #endif
 	ext4_set_bits(bitmap_bh->b_data, ac->ac_b_ex.fe_start,
 		      ac->ac_b_ex.fe_len);
-	if (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
+	if (ext4_has_group_desc_csum(sb) &&
+	    (gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))) {
 		gdp->bg_flags &= cpu_to_le16(~EXT4_BG_BLOCK_UNINIT);
 		ext4_free_group_clusters_set(sb, gdp,
 					     ext4_free_clusters_after_init(sb,
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 27b9a76a0dfa..638ad4743477 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -186,11 +186,8 @@ static int kmmpd(void *data)
 			goto exit_thread;
 		}
 
-		if (sb_rdonly(sb)) {
-			ext4_warning(sb, "kmmpd being stopped since filesystem "
-				     "has been remounted as readonly.");
-			goto exit_thread;
-		}
+		if (sb_rdonly(sb))
+			break;
 
 		diff = jiffies - last_update_time;
 		if (diff < mmp_update_interval * HZ)
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0c4c2201b3aa..b7f7922061be 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -405,6 +405,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 
 static void ext4_handle_error(struct super_block *sb)
 {
+	if (test_opt(sb, WARN_ON_ERROR))
+		WARN_ON_ONCE(1);
+
 	if (sb_rdonly(sb))
 		return;
 
@@ -740,6 +743,9 @@ __acquires(bitlock)
 		va_end(args);
 	}
 
+	if (test_opt(sb, WARN_ON_ERROR))
+		WARN_ON_ONCE(1);
+
 	if (test_opt(sb, ERRORS_CONT)) {
 		ext4_commit_super(sb, 0);
 		return;
@@ -1371,7 +1377,8 @@ enum {
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
-	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
+	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
+	Opt_nowarn_on_error, Opt_mblk_io_submit,
 	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
@@ -1438,6 +1445,8 @@ static const match_table_t tokens = {
 	{Opt_dax, "dax"},
 	{Opt_stripe, "stripe=%u"},
 	{Opt_delalloc, "delalloc"},
+	{Opt_warn_on_error, "warn_on_error"},
+	{Opt_nowarn_on_error, "nowarn_on_error"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
 	{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
@@ -1602,6 +1611,8 @@ static const struct mount_opts {
 	 MOPT_EXT4_ONLY | MOPT_SET | MOPT_EXPLICIT},
 	{Opt_nodelalloc, EXT4_MOUNT_DELALLOC,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
+	{Opt_warn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_SET},
+	{Opt_nowarn_on_error, EXT4_MOUNT_WARN_ON_ERROR, MOPT_CLEAR},
 	{Opt_nojournal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
 	 MOPT_EXT4_ONLY | MOPT_CLEAR},
 	{Opt_journal_checksum, EXT4_MOUNT_JOURNAL_CHECKSUM,
@@ -2331,6 +2342,7 @@ static int ext4_check_descriptors(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	ext4_fsblk_t first_block = le32_to_cpu(sbi->s_es->s_first_data_block);
 	ext4_fsblk_t last_block;
+	ext4_fsblk_t last_bg_block = sb_block + ext4_bg_num_gdb(sb, 0);
 	ext4_fsblk_t block_bitmap;
 	ext4_fsblk_t inode_bitmap;
 	ext4_fsblk_t inode_table;
@@ -2363,6 +2375,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (block_bitmap >= sb_block + 1 &&
+		    block_bitmap <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Block bitmap for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (block_bitmap < first_block || block_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Block bitmap for group %u not in group "
@@ -2377,6 +2397,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (inode_bitmap >= sb_block + 1 &&
+		    inode_bitmap <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode bitmap for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (inode_bitmap < first_block || inode_bitmap > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
 			       "Inode bitmap for group %u not in group "
@@ -2391,6 +2419,14 @@ static int ext4_check_descriptors(struct super_block *sb,
 			if (!sb_rdonly(sb))
 				return 0;
 		}
+		if (inode_table >= sb_block + 1 &&
+		    inode_table <= last_bg_block) {
+			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
+				 "Inode table for group %u overlaps "
+				 "block group descriptors", i);
+			if (!sb_rdonly(sb))
+				return 0;
+		}
 		if (inode_table < first_block ||
 		    inode_table + sbi->s_itb_per_group - 1 > last_block) {
 			ext4_msg(sb, KERN_ERR, "ext4_check_descriptors: "
@@ -3097,6 +3133,9 @@ static ext4_group_t ext4_has_uninit_itable(struct super_block *sb)
 	ext4_group_t group, ngroups = EXT4_SB(sb)->s_groups_count;
 	struct ext4_group_desc *gdp = NULL;
 
+	if (!ext4_has_group_desc_csum(sb))
+		return ngroups;
+
 	for (group = 0; group < ngroups; group++) {
 		gdp = ext4_get_group_desc(sb, group, NULL);
 		if (!gdp)
@@ -3742,6 +3781,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 le32_to_cpu(es->s_log_block_size));
 		goto failed_mount;
 	}
+	if (le32_to_cpu(es->s_log_cluster_size) >
+	    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
+		ext4_msg(sb, KERN_ERR,
+			 "Invalid log cluster size: %u",
+			 le32_to_cpu(es->s_log_cluster_size));
+		goto failed_mount;
+	}
 
 	if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
 		ext4_msg(sb, KERN_ERR,
@@ -3806,6 +3852,11 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	} else {
 		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
 		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
+		if (sbi->s_first_ino < EXT4_GOOD_OLD_FIRST_INO) {
+			ext4_msg(sb, KERN_ERR, "invalid first ino: %u",
+				 sbi->s_first_ino);
+			goto failed_mount;
+		}
 		if ((sbi->s_inode_size < EXT4_GOOD_OLD_INODE_SIZE) ||
 		    (!is_power_of_2(sbi->s_inode_size)) ||
 		    (sbi->s_inode_size > blocksize)) {
@@ -3882,13 +3933,6 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "block size (%d)", clustersize, blocksize);
 			goto failed_mount;
 		}
-		if (le32_to_cpu(es->s_log_cluster_size) >
-		    (EXT4_MAX_CLUSTER_LOG_SIZE - EXT4_MIN_BLOCK_LOG_SIZE)) {
-			ext4_msg(sb, KERN_ERR,
-				 "Invalid log cluster size: %u",
-				 le32_to_cpu(es->s_log_cluster_size));
-			goto failed_mount;
-		}
 		sbi->s_cluster_bits = le32_to_cpu(es->s_log_cluster_size) -
 			le32_to_cpu(es->s_log_block_size);
 		sbi->s_clusters_per_group =
@@ -3909,10 +3953,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		}
 	} else {
 		if (clustersize != blocksize) {
-			ext4_warning(sb, "fragment/cluster size (%d) != "
-				     "block size (%d)", clustersize,
-				     blocksize);
-			clustersize = blocksize;
+			ext4_msg(sb, KERN_ERR,
+				 "fragment/cluster size (%d) != "
+				 "block size (%d)", clustersize, blocksize);
+			goto failed_mount;
 		}
 		if (sbi->s_blocks_per_group > blocksize * 8) {
 			ext4_msg(sb, KERN_ERR,
@@ -3966,6 +4010,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			 ext4_blocks_count(es));
 		goto failed_mount;
 	}
+	if ((es->s_first_data_block == 0) && (es->s_log_block_size == 0) &&
+	    (sbi->s_cluster_ratio == 1)) {
+		ext4_msg(sb, KERN_WARNING, "bad geometry: first data "
+			 "block is 0 with a 1k block and cluster size");
+		goto failed_mount;
+	}
+
 	blocks_count = (ext4_blocks_count(es) -
 			le32_to_cpu(es->s_first_data_block) +
 			EXT4_BLOCKS_PER_GROUP(sb) - 1);
@@ -4001,6 +4052,14 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		ret = -ENOMEM;
 		goto failed_mount;
 	}
+	if (((u64)sbi->s_groups_count * sbi->s_inodes_per_group) !=
+	    le32_to_cpu(es->s_inodes_count)) {
+		ext4_msg(sb, KERN_ERR, "inodes count not valid: %u vs %llu",
+			 le32_to_cpu(es->s_inodes_count),
+			 ((u64)sbi->s_groups_count * sbi->s_inodes_per_group));
+		ret = -EINVAL;
+		goto failed_mount;
+	}
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
@@ -4020,14 +4079,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount2;
 		}
 	}
+	sbi->s_gdb_count = db_count;
 	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {
 		ext4_msg(sb, KERN_ERR, "group descriptors corrupted!");
 		ret = -EFSCORRUPTED;
 		goto failed_mount2;
 	}
 
-	sbi->s_gdb_count = db_count;
-
 	timer_setup(&sbi->s_err_report, print_daily_error_info, 0);
 
 	/* Register extent status tree shrinker */
@@ -4736,6 +4794,14 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 
 	if (!sbh || block_device_ejected(sb))
 		return error;
+
+	/*
+	 * The superblock bh should be mapped, but it might not be if the
+	 * device was hot-removed. Not much we can do but fail the I/O.
+	 */
+	if (!buffer_mapped(sbh))
+		return error;
+
 	/*
 	 * If the file system is mounted read-only, don't update the
 	 * superblock write time.  This avoids updating the superblock
@@ -5140,6 +5206,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 
 			if (sbi->s_journal)
 				ext4_mark_recovery_complete(sb, es);
+			if (sbi->s_mmp_tsk)
+				kthread_stop(sbi->s_mmp_tsk);
 		} else {
 			/* Make sure we can mount this feature set readwrite */
 			if (ext4_has_feature_readonly(sb) ||
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index fc4ced59c565..723df14f4084 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -230,12 +230,12 @@ __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh,
 {
 	int error = -EFSCORRUPTED;
 
-	if (buffer_verified(bh))
-		return 0;
-
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1))
 		goto errout;
+	if (buffer_verified(bh))
+		return 0;
+
 	error = -EFSBADCRC;
 	if (!ext4_xattr_block_csum_verify(inode, bh))
 		goto errout;
@@ -1560,7 +1560,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 				handle_t *handle, struct inode *inode,
 				bool is_block)
 {
-	struct ext4_xattr_entry *last;
+	struct ext4_xattr_entry *last, *next;
 	struct ext4_xattr_entry *here = s->here;
 	size_t min_offs = s->end - s->base, name_len = strlen(i->name);
 	int in_inode = i->in_inode;
@@ -1595,7 +1595,13 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 
 	/* Compute min_offs and last. */
 	last = s->first;
-	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+	for (; !IS_LAST_ENTRY(last); last = next) {
+		next = EXT4_XATTR_NEXT(last);
+		if ((void *)next >= s->end) {
+			EXT4_ERROR_INODE(inode, "corrupted xattr entries");
+			ret = -EFSCORRUPTED;
+			goto out;
+		}
 		if (!last->e_value_inum && last->e_value_size) {
 			size_t offs = le16_to_cpu(last->e_value_offs);
 			if (offs < min_offs)
@@ -2206,23 +2212,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 	if (EXT4_I(inode)->i_extra_isize == 0)
 		return -ENOSPC;
 	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
-	if (error) {
-		if (error == -ENOSPC &&
-		    ext4_has_inline_data(inode)) {
-			error = ext4_try_to_evict_inline_data(handle, inode,
-					EXT4_XATTR_LEN(strlen(i->name) +
-					EXT4_XATTR_SIZE(i->value_len)));
-			if (error)
-				return error;
-			error = ext4_xattr_ibody_find(inode, i, is);
-			if (error)
-				return error;
-			error = ext4_xattr_set_entry(i, s, handle, inode,
-						     false /* is_block */);
-		}
-		if (error)
-			return error;
-	}
+	if (error)
+		return error;
 	header = IHDR(inode, ext4_raw_inode(&is->iloc));
 	if (!IS_LAST_ENTRY(s->first)) {
 		header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC);
@@ -2651,6 +2642,11 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
 		last = IFIRST(header);
 		/* Find the entry best suited to be pushed into EA block */
 		for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
+			/* never move system.data out of the inode */
+			if ((last->e_name_len == 4) &&
+			    (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) &&
+			    !memcmp(last->e_name, "data", 4))
+				continue;
 			total_size = EXT4_XATTR_LEN(last->e_name_len);
 			if (!last->e_value_inum)
 				total_size += EXT4_XATTR_SIZE(
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 065dc919a0ce..bfd589ea74c0 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -707,13 +707,21 @@ static void fat_set_state(struct super_block *sb,
 	brelse(bh);
 }
 
+static void fat_reset_iocharset(struct fat_mount_options *opts)
+{
+	if (opts->iocharset != fat_default_iocharset) {
+		/* Note: opts->iocharset can be NULL here */
+		kfree(opts->iocharset);
+		opts->iocharset = fat_default_iocharset;
+	}
+}
+
 static void delayed_free(struct rcu_head *p)
 {
 	struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu);
 	unload_nls(sbi->nls_disk);
 	unload_nls(sbi->nls_io);
-	if (sbi->options.iocharset != fat_default_iocharset)
-		kfree(sbi->options.iocharset);
+	fat_reset_iocharset(&sbi->options);
 	kfree(sbi);
 }
 
@@ -1132,7 +1140,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 	opts->fs_fmask = opts->fs_dmask = current_umask();
 	opts->allow_utime = -1;
 	opts->codepage = fat_default_codepage;
-	opts->iocharset = fat_default_iocharset;
+	fat_reset_iocharset(opts);
 	if (is_vfat) {
 		opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95;
 		opts->rodir = 0;
@@ -1289,8 +1297,7 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat,
 
 		/* vfat specific */
 		case Opt_charset:
-			if (opts->iocharset != fat_default_iocharset)
-				kfree(opts->iocharset);
+			fat_reset_iocharset(opts);
 			iocharset = match_strdup(&args[0]);
 			if (!iocharset)
 				return -ENOMEM;
@@ -1881,8 +1888,7 @@ out_fail:
 		iput(fat_inode);
 	unload_nls(sbi->nls_io);
 	unload_nls(sbi->nls_disk);
-	if (sbi->options.iocharset != fat_default_iocharset)
-		kfree(sbi->options.iocharset);
+	fat_reset_iocharset(&sbi->options);
 	sb->s_fs_info = NULL;
 	kfree(sbi);
 	return error;
diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
index c184c5a356ff..cdcb376ef8df 100644
--- a/fs/fscache/cache.c
+++ b/fs/fscache/cache.c
@@ -220,6 +220,7 @@ int fscache_add_cache(struct fscache_cache *cache,
 {
 	struct fscache_cache_tag *tag;
 
+	ASSERTCMP(ifsdef->cookie, ==, &fscache_fsdef_index);
 	BUG_ON(!cache->ops);
 	BUG_ON(!ifsdef);
 
@@ -248,7 +249,6 @@ int fscache_add_cache(struct fscache_cache *cache,
 	if (!cache->kobj)
 		goto error;
 
-	ifsdef->cookie = &fscache_fsdef_index;
 	ifsdef->cache = cache;
 	cache->fsdef = ifsdef;
 
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 97137d7ec5ee..83bfe04456b6 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -516,6 +516,7 @@ static int fscache_alloc_object(struct fscache_cache *cache,
 		goto error;
 	}
 
+	ASSERTCMP(object->cookie, ==, cookie);
 	fscache_stat(&fscache_n_object_alloc);
 
 	object->debug_id = atomic_inc_return(&fscache_object_debug_id);
@@ -571,6 +572,8 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
 
 	_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
 
+	ASSERTCMP(object->cookie, ==, cookie);
+
 	spin_lock(&cookie->lock);
 
 	/* there may be multiple initial creations of this object, but we only
@@ -610,9 +613,7 @@ static int fscache_attach_object(struct fscache_cookie *cookie,
 		spin_unlock(&cache->object_list_lock);
 	}
 
-	/* attach to the cookie */
-	object->cookie = cookie;
-	fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
+	/* Attach to the cookie.  The object already has a ref on it. */
 	hlist_add_head(&object->cookie_link, &cookie->backing_objects);
 
 	fscache_objlist_add(object);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
index 20e0d0a4dc8c..9edc920f651f 100644
--- a/fs/fscache/object.c
+++ b/fs/fscache/object.c
@@ -327,6 +327,7 @@ void fscache_object_init(struct fscache_object *object,
 	object->store_limit_l = 0;
 	object->cache = cache;
 	object->cookie = cookie;
+	fscache_cookie_get(cookie, fscache_cookie_get_attach_object);
 	object->parent = NULL;
 #ifdef CONFIG_FSCACHE_OBJECT_LIST
 	RB_CLEAR_NODE(&object->objlist_link);
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index e30c5975ea58..8d265790374c 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -70,7 +70,8 @@ void fscache_enqueue_operation(struct fscache_operation *op)
 	ASSERT(op->processor != NULL);
 	ASSERT(fscache_object_is_available(op->object));
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
-	ASSERTCMP(op->state, ==, FSCACHE_OP_ST_IN_PROGRESS);
+	ASSERTIFCMP(op->state != FSCACHE_OP_ST_IN_PROGRESS,
+		    op->state, ==,  FSCACHE_OP_ST_CANCELLED);
 
 	fscache_stat(&fscache_n_op_enqueue);
 	switch (op->flags & FSCACHE_OP_TYPE) {
@@ -499,7 +500,8 @@ void fscache_put_operation(struct fscache_operation *op)
 	struct fscache_cache *cache;
 
 	_enter("{OBJ%x OP%x,%d}",
-	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+	       op->object ? op->object->debug_id : 0,
+	       op->debug_id, atomic_read(&op->usage));
 
 	ASSERTCMP(atomic_read(&op->usage), >, 0);
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d508c7844681..40d4c66c7751 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -411,6 +411,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	bool truncate_op = (lend == LLONG_MAX);
 
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	vma_init(&pseudo_vma, current->mm);
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pagevec_init(&pvec);
 	next = start;
@@ -595,6 +596,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	 * as input to create an allocation policy.
 	 */
 	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	vma_init(&pseudo_vma, mm);
 	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pseudo_vma.vm_file = file;
 
diff --git a/fs/inode.c b/fs/inode.c
index 2c300e981796..8c86c809ca17 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1999,8 +1999,14 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
 	inode->i_uid = current_fsuid();
 	if (dir && dir->i_mode & S_ISGID) {
 		inode->i_gid = dir->i_gid;
+
+		/* Directories are special, and always inherit S_ISGID */
 		if (S_ISDIR(mode))
 			mode |= S_ISGID;
+		else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
+			 !in_group_p(inode->i_gid) &&
+			 !capable_wrt_inode_uidgid(dir, CAP_FSETID))
+			mode &= ~S_ISGID;
 	} else
 		inode->i_gid = current_fsgid();
 	inode->i_mode = mode;
diff --git a/fs/internal.h b/fs/internal.h
index 980d005b21b4..5645b4ebf494 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -127,7 +127,6 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 
 extern int open_check_o_direct(struct file *f);
 extern int vfs_open(const struct path *, struct file *, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
 
 /*
  * inode.c
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 51dd68e67b0f..c0b66a7a795b 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1361,6 +1361,13 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		if (jh->b_transaction == transaction &&
 		    jh->b_jlist != BJ_Metadata) {
 			jbd_lock_bh_state(bh);
+			if (jh->b_transaction == transaction &&
+			    jh->b_jlist != BJ_Metadata)
+				pr_err("JBD2: assertion failure: h_type=%u "
+				       "h_line_no=%u block_no=%llu jlist=%u\n",
+				       handle->h_type, handle->h_line_no,
+				       (unsigned long long) bh->b_blocknr,
+				       jh->b_jlist);
 			J_ASSERT_JH(jh, jh->b_transaction != transaction ||
 					jh->b_jlist == BJ_Metadata);
 			jbd_unlock_bh_state(bh);
@@ -1380,11 +1387,11 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 		 * of the transaction. This needs to be done
 		 * once a transaction -bzzz
 		 */
-		jh->b_modified = 1;
 		if (handle->h_buffer_credits <= 0) {
 			ret = -ENOSPC;
 			goto out_unlock_bh;
 		}
+		jh->b_modified = 1;
 		handle->h_buffer_credits--;
 	}
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e9679016271f..dfd73a4616ce 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -831,7 +831,8 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		SEQ_PUT_DEC(" kB\nSwap:           ", mss->swap);
 		SEQ_PUT_DEC(" kB\nSwapPss:        ",
 						mss->swap_pss >> PSS_SHIFT);
-		SEQ_PUT_DEC(" kB\nLocked:         ", mss->pss >> PSS_SHIFT);
+		SEQ_PUT_DEC(" kB\nLocked:         ",
+						mss->pss_locked >> PSS_SHIFT);
 		seq_puts(m, " kB\n");
 	}
 	if (!rollup_mode) {
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index 7e288d97adcb..9fed1c05f1f4 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -76,83 +76,99 @@ static char *le_type(struct reiserfs_key *key)
 }
 
 /* %k */
-static void sprintf_le_key(char *buf, struct reiserfs_key *key)
+static int scnprintf_le_key(char *buf, size_t size, struct reiserfs_key *key)
 {
 	if (key)
-		sprintf(buf, "[%d %d %s %s]", le32_to_cpu(key->k_dir_id),
-			le32_to_cpu(key->k_objectid), le_offset(key),
-			le_type(key));
+		return scnprintf(buf, size, "[%d %d %s %s]",
+				 le32_to_cpu(key->k_dir_id),
+				 le32_to_cpu(key->k_objectid), le_offset(key),
+				 le_type(key));
 	else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 }
 
 /* %K */
-static void sprintf_cpu_key(char *buf, struct cpu_key *key)
+static int scnprintf_cpu_key(char *buf, size_t size, struct cpu_key *key)
 {
 	if (key)
-		sprintf(buf, "[%d %d %s %s]", key->on_disk_key.k_dir_id,
-			key->on_disk_key.k_objectid, reiserfs_cpu_offset(key),
-			cpu_type(key));
+		return scnprintf(buf, size, "[%d %d %s %s]",
+				 key->on_disk_key.k_dir_id,
+				 key->on_disk_key.k_objectid,
+				 reiserfs_cpu_offset(key), cpu_type(key));
 	else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 }
 
-static void sprintf_de_head(char *buf, struct reiserfs_de_head *deh)
+static int scnprintf_de_head(char *buf, size_t size,
+			     struct reiserfs_de_head *deh)
 {
 	if (deh)
-		sprintf(buf,
-			"[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
-			deh_offset(deh), deh_dir_id(deh), deh_objectid(deh),
-			deh_location(deh), deh_state(deh));
+		return scnprintf(buf, size,
+				 "[offset=%d dir_id=%d objectid=%d location=%d state=%04x]",
+				 deh_offset(deh), deh_dir_id(deh),
+				 deh_objectid(deh), deh_location(deh),
+				 deh_state(deh));
 	else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 
 }
 
-static void sprintf_item_head(char *buf, struct item_head *ih)
+static int scnprintf_item_head(char *buf, size_t size, struct item_head *ih)
 {
 	if (ih) {
-		strcpy(buf,
-		       (ih_version(ih) == KEY_FORMAT_3_6) ? "*3.6* " : "*3.5*");
-		sprintf_le_key(buf + strlen(buf), &(ih->ih_key));
-		sprintf(buf + strlen(buf), ", item_len %d, item_location %d, "
-			"free_space(entry_count) %d",
-			ih_item_len(ih), ih_location(ih), ih_free_space(ih));
+		char *p = buf;
+		char * const end = buf + size;
+
+		p += scnprintf(p, end - p, "%s",
+			       (ih_version(ih) == KEY_FORMAT_3_6) ?
+			       "*3.6* " : "*3.5*");
+
+		p += scnprintf_le_key(p, end - p, &ih->ih_key);
+
+		p += scnprintf(p, end - p,
+			       ", item_len %d, item_location %d, free_space(entry_count) %d",
+			       ih_item_len(ih), ih_location(ih),
+			       ih_free_space(ih));
+		return p - buf;
 	} else
-		sprintf(buf, "[NULL]");
+		return scnprintf(buf, size, "[NULL]");
 }
 
-static void sprintf_direntry(char *buf, struct reiserfs_dir_entry *de)
+static int scnprintf_direntry(char *buf, size_t size,
+			      struct reiserfs_dir_entry *de)
 {
 	char name[20];
 
 	memcpy(name, de->de_name, de->de_namelen > 19 ? 19 : de->de_namelen);
 	name[de->de_namelen > 19 ? 19 : de->de_namelen] = 0;
-	sprintf(buf, "\"%s\"==>[%d %d]", name, de->de_dir_id, de->de_objectid);
+	return scnprintf(buf, size, "\"%s\"==>[%d %d]",
+			 name, de->de_dir_id, de->de_objectid);
 }
 
-static void sprintf_block_head(char *buf, struct buffer_head *bh)
+static int scnprintf_block_head(char *buf, size_t size, struct buffer_head *bh)
 {
-	sprintf(buf, "level=%d, nr_items=%d, free_space=%d rdkey ",
-		B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
+	return scnprintf(buf, size,
+			 "level=%d, nr_items=%d, free_space=%d rdkey ",
+			 B_LEVEL(bh), B_NR_ITEMS(bh), B_FREE_SPACE(bh));
 }
 
-static void sprintf_buffer_head(char *buf, struct buffer_head *bh)
+static int scnprintf_buffer_head(char *buf, size_t size, struct buffer_head *bh)
 {
-	sprintf(buf,
-		"dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
-		bh->b_bdev, bh->b_size,
-		(unsigned long long)bh->b_blocknr, atomic_read(&(bh->b_count)),
-		bh->b_state, bh->b_page,
-		buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
-		buffer_dirty(bh) ? "DIRTY" : "CLEAN",
-		buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
+	return scnprintf(buf, size,
+			 "dev %pg, size %zd, blocknr %llu, count %d, state 0x%lx, page %p, (%s, %s, %s)",
+			 bh->b_bdev, bh->b_size,
+			 (unsigned long long)bh->b_blocknr,
+			 atomic_read(&(bh->b_count)),
+			 bh->b_state, bh->b_page,
+			 buffer_uptodate(bh) ? "UPTODATE" : "!UPTODATE",
+			 buffer_dirty(bh) ? "DIRTY" : "CLEAN",
+			 buffer_locked(bh) ? "LOCKED" : "UNLOCKED");
 }
 
-static void sprintf_disk_child(char *buf, struct disk_child *dc)
+static int scnprintf_disk_child(char *buf, size_t size, struct disk_child *dc)
 {
-	sprintf(buf, "[dc_number=%d, dc_size=%u]", dc_block_number(dc),
-		dc_size(dc));
+	return scnprintf(buf, size, "[dc_number=%d, dc_size=%u]",
+			 dc_block_number(dc), dc_size(dc));
 }
 
 static char *is_there_reiserfs_struct(char *fmt, int *what)
@@ -189,55 +205,60 @@ static void prepare_error_buf(const char *fmt, va_list args)
 	char *fmt1 = fmt_buf;
 	char *k;
 	char *p = error_buf;
+	char * const end = &error_buf[sizeof(error_buf)];
 	int what;
 
 	spin_lock(&error_lock);
 
-	strcpy(fmt1, fmt);
+	if (WARN_ON(strscpy(fmt_buf, fmt, sizeof(fmt_buf)) < 0)) {
+		strscpy(error_buf, "format string too long", end - error_buf);
+		goto out_unlock;
+	}
 
 	while ((k = is_there_reiserfs_struct(fmt1, &what)) != NULL) {
 		*k = 0;
 
-		p += vsprintf(p, fmt1, args);
+		p += vscnprintf(p, end - p, fmt1, args);
 
 		switch (what) {
 		case 'k':
-			sprintf_le_key(p, va_arg(args, struct reiserfs_key *));
+			p += scnprintf_le_key(p, end - p,
+					      va_arg(args, struct reiserfs_key *));
 			break;
 		case 'K':
-			sprintf_cpu_key(p, va_arg(args, struct cpu_key *));
+			p += scnprintf_cpu_key(p, end - p,
+					       va_arg(args, struct cpu_key *));
 			break;
 		case 'h':
-			sprintf_item_head(p, va_arg(args, struct item_head *));
+			p += scnprintf_item_head(p, end - p,
+						 va_arg(args, struct item_head *));
 			break;
 		case 't':
-			sprintf_direntry(p,
-					 va_arg(args,
-						struct reiserfs_dir_entry *));
+			p += scnprintf_direntry(p, end - p,
+						va_arg(args, struct reiserfs_dir_entry *));
 			break;
 		case 'y':
-			sprintf_disk_child(p,
-					   va_arg(args, struct disk_child *));
+			p += scnprintf_disk_child(p, end - p,
+						  va_arg(args, struct disk_child *));
 			break;
 		case 'z':
-			sprintf_block_head(p,
-					   va_arg(args, struct buffer_head *));
+			p += scnprintf_block_head(p, end - p,
+						  va_arg(args, struct buffer_head *));
 			break;
 		case 'b':
-			sprintf_buffer_head(p,
-					    va_arg(args, struct buffer_head *));
+			p += scnprintf_buffer_head(p, end - p,
+						   va_arg(args, struct buffer_head *));
 			break;
 		case 'a':
-			sprintf_de_head(p,
-					va_arg(args,
-					       struct reiserfs_de_head *));
+			p += scnprintf_de_head(p, end - p,
+					       va_arg(args, struct reiserfs_de_head *));
 			break;
 		}
 
-		p += strlen(p);
 		fmt1 = k + 2;
 	}
-	vsprintf(p, fmt1, args);
+	p += vscnprintf(p, end - p, fmt1, args);
+out_unlock:
 	spin_unlock(&error_lock);
 
 }
diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 23813c078cc9..0839efa720b3 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -350,6 +350,9 @@ int squashfs_read_metadata(struct super_block *sb, void *buffer,
 
 	TRACE("Entered squashfs_read_metadata [%llx:%x]\n", *block, *offset);
 
+	if (unlikely(length < 0))
+		return -EIO;
+
 	while (length) {
 		entry = squashfs_cache_get(sb, msblk->block_cache, *block, 0);
 		if (entry->error) {
diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index 13d80947bf9e..fcff2e0487fe 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -194,7 +194,11 @@ static long long read_indexes(struct super_block *sb, int n,
 		}
 
 		for (i = 0; i < blocks; i++) {
-			int size = le32_to_cpu(blist[i]);
+			int size = squashfs_block_size(blist[i]);
+			if (size < 0) {
+				err = size;
+				goto failure;
+			}
 			block += SQUASHFS_COMPRESSED_SIZE_BLOCK(size);
 		}
 		n -= blocks;
@@ -367,7 +371,7 @@ static int read_blocklist(struct inode *inode, int index, u64 *block)
 			sizeof(size));
 	if (res < 0)
 		return res;
-	return le32_to_cpu(size);
+	return squashfs_block_size(size);
 }
 
 /* Copy data into page cache  */
diff --git a/fs/squashfs/fragment.c b/fs/squashfs/fragment.c
index 0ed6edbc5c71..86ad9a4b8c36 100644
--- a/fs/squashfs/fragment.c
+++ b/fs/squashfs/fragment.c
@@ -61,9 +61,7 @@ int squashfs_frag_lookup(struct super_block *sb, unsigned int fragment,
 		return size;
 
 	*fragment_block = le64_to_cpu(fragment_entry.start_block);
-	size = le32_to_cpu(fragment_entry.size);
-
-	return size;
+	return squashfs_block_size(fragment_entry.size);
 }
 
 
diff --git a/fs/squashfs/squashfs_fs.h b/fs/squashfs/squashfs_fs.h
index 24d12fd14177..4e6853f084d0 100644
--- a/fs/squashfs/squashfs_fs.h
+++ b/fs/squashfs/squashfs_fs.h
@@ -129,6 +129,12 @@
 
 #define SQUASHFS_COMPRESSED_BLOCK(B)	(!((B) & SQUASHFS_COMPRESSED_BIT_BLOCK))
 
+static inline int squashfs_block_size(__le32 raw)
+{
+	u32 size = le32_to_cpu(raw);
+	return (size >> 25) ? -EIO : size;
+}
+
 /*
  * Inode number ops.  Inodes consist of a compressed block number, and an
  * uncompressed offset within that block
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 123bf7d516fc..594d192b2331 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -222,24 +222,26 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 					 unsigned long reason)
 {
 	struct mm_struct *mm = ctx->mm;
-	pte_t *pte;
+	pte_t *ptep, pte;
 	bool ret = true;
 
 	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
-	pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
-	if (!pte)
+	ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+
+	if (!ptep)
 		goto out;
 
 	ret = false;
+	pte = huge_ptep_get(ptep);
 
 	/*
 	 * Lockless access: we're in a wait_event so it's ok if it
 	 * changes under us.
 	 */
-	if (huge_pte_none(*pte))
+	if (huge_pte_none(pte))
 		ret = true;
-	if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
+	if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
 		ret = true;
 out:
 	return ret;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index eef466260d43..75dbdc14c45f 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -223,12 +223,13 @@ xfs_alloc_get_rec(
 	error = xfs_btree_get_rec(cur, &rec, stat);
 	if (error || !(*stat))
 		return error;
-	if (rec->alloc.ar_blockcount == 0)
-		goto out_bad_rec;
 
 	*bno = be32_to_cpu(rec->alloc.ar_startblock);
 	*len = be32_to_cpu(rec->alloc.ar_blockcount);
 
+	if (*len == 0)
+		goto out_bad_rec;
+
 	/* check for valid extent range, including overflow */
 	if (!xfs_verify_agbno(mp, agno, *bno))
 		goto out_bad_rec;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 33dc34655ac3..30d1d60f1d46 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -731,7 +731,8 @@ xfs_inode_validate_extsize(
 	if ((hint_flag || inherit_flag) && extsize == 0)
 		return __this_address;
 
-	if (!(hint_flag || inherit_flag) && extsize != 0)
+	/* free inodes get flags set to zero but extsize remains */
+	if (mode && !(hint_flag || inherit_flag) && extsize != 0)
 		return __this_address;
 
 	if (extsize_bytes % blocksize_bytes)
@@ -777,7 +778,8 @@ xfs_inode_validate_cowextsize(
 	if (hint_flag && cowextsize == 0)
 		return __this_address;
 
-	if (!hint_flag && cowextsize != 0)
+	/* free inodes get flags set to zero but cowextsize remains */
+	if (mode && !hint_flag && cowextsize != 0)
 		return __this_address;
 
 	if (hint_flag && rt_flag)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index faddde44de8c..3063125197ad 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -265,33 +265,41 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
  * For now w.r.t page table cache, mark the range_size as PAGE_SIZE
  */
 
+#ifndef pte_free_tlb
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
+#endif
 
+#ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
+#endif
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
+#ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
+#endif
 
 #ifndef __ARCH_HAS_5LEVEL_HACK
+#ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
 		__tlb_adjust_range(tlb, address, PAGE_SIZE);		\
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
+#endif
 
 #define tlb_migrate_finish(mm) do {} while (0)
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index c5dfbdb7271d..f7a19c2a7a80 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -102,25 +102,6 @@ struct pci_controller;
 #define DRM_SWITCH_POWER_CHANGING 2
 #define DRM_SWITCH_POWER_DYNAMIC_OFF 3
 
-static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
-{
-	return dev->driver->driver_features & feature;
-}
-
-/**
- * drm_drv_uses_atomic_modeset - check if the driver implements
- * atomic_commit()
- * @dev: DRM device
- *
- * This check is useful if drivers do not have DRIVER_ATOMIC set but
- * have atomic modesetting internally implemented.
- */
-static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev)
-{
-	return drm_core_check_feature(dev, DRIVER_ATOMIC) ||
-		dev->mode_config.funcs->atomic_commit != NULL;
-}
-
 /* returns true if currently okay to sleep */
 static inline bool drm_can_sleep(void)
 {
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 26aaba58d6ce..99e2a5297c69 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -100,6 +100,7 @@ int __must_check drm_atomic_helper_swap_state(struct drm_atomic_state *state,
 int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
 				   bool nonblock);
 void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *state);
+void drm_atomic_helper_fake_vblank(struct drm_atomic_state *state);
 void drm_atomic_helper_commit_hw_done(struct drm_atomic_state *state);
 void drm_atomic_helper_commit_cleanup_done(struct drm_atomic_state *state);
 
diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h
new file mode 100644
index 000000000000..989f8e52864d
--- /dev/null
+++ b/include/drm/drm_client.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _DRM_CLIENT_H_
+#define _DRM_CLIENT_H_
+
+#include <linux/types.h>
+
+struct drm_client_dev;
+struct drm_device;
+struct drm_file;
+struct drm_framebuffer;
+struct drm_gem_object;
+struct drm_minor;
+struct module;
+
+/**
+ * struct drm_client_funcs - DRM client callbacks
+ */
+struct drm_client_funcs {
+	/**
+	 * @owner: The module owner
+	 */
+	struct module *owner;
+
+	/**
+	 * @unregister:
+	 *
+	 * Called when &drm_device is unregistered. The client should respond by
+	 * releasing it's resources using drm_client_release().
+	 *
+	 * This callback is optional.
+	 */
+	void (*unregister)(struct drm_client_dev *client);
+
+	/**
+	 * @restore:
+	 *
+	 * Called on drm_lastclose(). The first client instance in the list that
+	 * returns zero gets the privilege to restore and no more clients are
+	 * called. This callback is not called after @unregister has been called.
+	 *
+	 * This callback is optional.
+	 */
+	int (*restore)(struct drm_client_dev *client);
+
+	/**
+	 * @hotplug:
+	 *
+	 * Called on drm_kms_helper_hotplug_event().
+	 * This callback is not called after @unregister has been called.
+	 *
+	 * This callback is optional.
+	 */
+	int (*hotplug)(struct drm_client_dev *client);
+};
+
+/**
+ * struct drm_client_dev - DRM client instance
+ */
+struct drm_client_dev {
+	/**
+	 * @dev: DRM device
+	 */
+	struct drm_device *dev;
+
+	/**
+	 * @name: Name of the client.
+	 */
+	const char *name;
+
+	/**
+	 * @list:
+	 *
+	 * List of all clients of a DRM device, linked into
+	 * &drm_device.clientlist. Protected by &drm_device.clientlist_mutex.
+	 */
+	struct list_head list;
+
+	/**
+	 * @funcs: DRM client functions (optional)
+	 */
+	const struct drm_client_funcs *funcs;
+
+	/**
+	 * @file: DRM file
+	 */
+	struct drm_file *file;
+};
+
+int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
+		   const char *name, const struct drm_client_funcs *funcs);
+void drm_client_release(struct drm_client_dev *client);
+
+void drm_client_dev_unregister(struct drm_device *dev);
+void drm_client_dev_hotplug(struct drm_device *dev);
+void drm_client_dev_restore(struct drm_device *dev);
+
+/**
+ * struct drm_client_buffer - DRM client buffer
+ */
+struct drm_client_buffer {
+	/**
+	 * @client: DRM client
+	 */
+	struct drm_client_dev *client;
+
+	/**
+	 * @handle: Buffer handle
+	 */
+	u32 handle;
+
+	/**
+	 * @pitch: Buffer pitch
+	 */
+	u32 pitch;
+
+	/**
+	 * @gem: GEM object backing this buffer
+	 */
+	struct drm_gem_object *gem;
+
+	/**
+	 * @vaddr: Virtual address for the buffer
+	 */
+	void *vaddr;
+
+	/**
+	 * @fb: DRM framebuffer
+	 */
+	struct drm_framebuffer *fb;
+};
+
+struct drm_client_buffer *
+drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format);
+void drm_client_framebuffer_delete(struct drm_client_buffer *buffer);
+
+int drm_client_debugfs_init(struct drm_minor *minor);
+
+#endif
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index bf0f0f0786d3..97ea41dc678f 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -290,6 +290,10 @@ struct drm_display_info {
 #define DRM_BUS_FLAG_DATA_MSB_TO_LSB	(1<<4)
 /* data is transmitted LSB to MSB on the bus */
 #define DRM_BUS_FLAG_DATA_LSB_TO_MSB	(1<<5)
+/* drive sync on pos. edge */
+#define DRM_BUS_FLAG_SYNC_POSEDGE	(1<<6)
+/* drive sync on neg. edge */
+#define DRM_BUS_FLAG_SYNC_NEGEDGE	(1<<7)
 
 	/**
 	 * @bus_flags: Additional information (like pixel signal polarity) for
@@ -374,12 +378,9 @@ struct drm_tv_connector_state {
 
 /**
  * struct drm_connector_state - mutable connector state
- * @connector: backpointer to the connector
- * @best_encoder: can be used by helpers and drivers to select the encoder
- * @state: backpointer to global drm_atomic_state
- * @tv: TV connector state
  */
 struct drm_connector_state {
+	/** @connector: backpointer to the connector */
 	struct drm_connector *connector;
 
 	/**
@@ -390,6 +391,13 @@ struct drm_connector_state {
 	 */
 	struct drm_crtc *crtc;
 
+	/**
+	 * @best_encoder:
+	 *
+	 * Used by the atomic helpers to select the encoder, through the
+	 * &drm_connector_helper_funcs.atomic_best_encoder or
+	 * &drm_connector_helper_funcs.best_encoder callbacks.
+	 */
 	struct drm_encoder *best_encoder;
 
 	/**
@@ -398,6 +406,7 @@ struct drm_connector_state {
 	 */
 	enum drm_link_status link_status;
 
+	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
 
 	/**
@@ -407,6 +416,7 @@ struct drm_connector_state {
 	 */
 	struct drm_crtc_commit *commit;
 
+	/** @tv: TV connector state */
 	struct drm_tv_connector_state tv;
 
 	/**
@@ -551,8 +561,7 @@ struct drm_connector_funcs {
 	 * received for this output connector->edid must be NULL.
 	 *
 	 * Drivers using the probe helpers should use
-	 * drm_helper_probe_single_connector_modes() or
-	 * drm_helper_probe_single_connector_modes_nomerge() to implement this
+	 * drm_helper_probe_single_connector_modes() to implement this
 	 * function.
 	 *
 	 * RETURNS:
@@ -763,45 +772,6 @@ struct drm_cmdline_mode {
 
 /**
  * struct drm_connector - central DRM connector control structure
- * @dev: parent DRM device
- * @kdev: kernel device for sysfs attributes
- * @attr: sysfs attributes
- * @head: list management
- * @base: base KMS object
- * @name: human readable name, can be overwritten by the driver
- * @connector_type: one of the DRM_MODE_CONNECTOR_<foo> types from drm_mode.h
- * @connector_type_id: index into connector type enum
- * @interlace_allowed: can this connector handle interlaced modes?
- * @doublescan_allowed: can this connector handle doublescan?
- * @stereo_allowed: can this connector handle stereo modes?
- * @funcs: connector control functions
- * @edid_blob_ptr: DRM property containing EDID if present
- * @properties: property tracking for this connector
- * @dpms: current dpms state
- * @helper_private: mid-layer private data
- * @cmdline_mode: mode line parsed from the kernel cmdline for this connector
- * @force: a DRM_FORCE_<foo> state for forced mode sets
- * @override_edid: has the EDID been overwritten through debugfs for testing?
- * @encoder_ids: valid encoders for this connector
- * @eld: EDID-like data, if present
- * @latency_present: AV delay info from ELD, if found
- * @video_latency: video latency info from ELD, if found
- * @audio_latency: audio latency info from ELD, if found
- * @null_edid_counter: track sinks that give us all zeros for the EDID
- * @bad_edid_counter: track sinks that give us an EDID with invalid checksum
- * @edid_corrupt: indicates whether the last read EDID was corrupt
- * @debugfs_entry: debugfs directory for this connector
- * @has_tile: is this connector connected to a tiled monitor
- * @tile_group: tile group for the connected monitor
- * @tile_is_single_monitor: whether the tile is one monitor housing
- * @num_h_tile: number of horizontal tiles in the tile group
- * @num_v_tile: number of vertical tiles in the tile group
- * @tile_h_loc: horizontal location of this tile
- * @tile_v_loc: vertical location of this tile
- * @tile_h_size: horizontal size of this tile.
- * @tile_v_size: vertical size of this tile.
- * @scaling_mode_property:  Optional atomic property to control the upscaling.
- * @content_protection_property: Optional property to control content protection
  *
  * Each connector may be connected to one or more CRTCs, or may be clonable by
  * another connector if they can share a CRTC.  Each connector also has a specific
@@ -809,13 +779,27 @@ struct drm_cmdline_mode {
  * span multiple monitors).
  */
 struct drm_connector {
+	/** @dev: parent DRM device */
 	struct drm_device *dev;
+	/** @kdev: kernel device for sysfs attributes */
 	struct device *kdev;
+	/** @attr: sysfs attributes */
 	struct device_attribute *attr;
+
+	/**
+	 * @head:
+	 *
+	 * List of all connectors on a @dev, linked from
+	 * &drm_mode_config.connector_list. Protected by
+	 * &drm_mode_config.connector_list_lock, but please only use
+	 * &drm_connector_list_iter to walk this list.
+	 */
 	struct list_head head;
 
+	/** @base: base KMS object */
 	struct drm_mode_object base;
 
+	/** @name: human readable name, can be overwritten by the driver */
 	char *name;
 
 	/**
@@ -833,10 +817,30 @@ struct drm_connector {
 	 */
 	unsigned index;
 
+	/**
+	 * @connector_type:
+	 * one of the DRM_MODE_CONNECTOR_<foo> types from drm_mode.h
+	 */
 	int connector_type;
+	/** @connector_type_id: index into connector type enum */
 	int connector_type_id;
+	/**
+	 * @interlace_allowed:
+	 * Can this connector handle interlaced modes? Only used by
+	 * drm_helper_probe_single_connector_modes() for mode filtering.
+	 */
 	bool interlace_allowed;
+	/**
+	 * @doublescan_allowed:
+	 * Can this connector handle doublescan? Only used by
+	 * drm_helper_probe_single_connector_modes() for mode filtering.
+	 */
 	bool doublescan_allowed;
+	/**
+	 * @stereo_allowed:
+	 * Can this connector handle stereo modes? Only used by
+	 * drm_helper_probe_single_connector_modes() for mode filtering.
+	 */
 	bool stereo_allowed;
 
 	/**
@@ -885,45 +889,42 @@ struct drm_connector {
 	 * Protected by &drm_mode_config.mutex.
 	 */
 	struct drm_display_info display_info;
+
+	/** @funcs: connector control functions */
 	const struct drm_connector_funcs *funcs;
 
+	/**
+	 * @edid_blob_ptr: DRM property containing EDID if present. Protected by
+	 * &drm_mode_config.mutex. This should be updated only by calling
+	 * drm_connector_update_edid_property().
+	 */
 	struct drm_property_blob *edid_blob_ptr;
+
+	/** @properties: property tracking for this connector */
 	struct drm_object_properties properties;
 
+	/**
+	 * @scaling_mode_property: Optional atomic property to control the
+	 * upscaling. See drm_connector_attach_content_protection_property().
+	 */
 	struct drm_property *scaling_mode_property;
 
 	/**
 	 * @content_protection_property: DRM ENUM property for content
-	 * protection
+	 * protection. See drm_connector_attach_content_protection_property().
 	 */
 	struct drm_property *content_protection_property;
 
 	/**
 	 * @path_blob_ptr:
 	 *
-	 * DRM blob property data for the DP MST path property.
+	 * DRM blob property data for the DP MST path property. This should only
+	 * be updated by calling drm_connector_set_path_property().
 	 */
 	struct drm_property_blob *path_blob_ptr;
 
-	/**
-	 * @tile_blob_ptr:
-	 *
-	 * DRM blob property data for the tile property (used mostly by DP MST).
-	 * This is meant for screens which are driven through separate display
-	 * pipelines represented by &drm_crtc, which might not be running with
-	 * genlocked clocks. For tiled panels which are genlocked, like
-	 * dual-link LVDS or dual-link DSI, the driver should try to not expose
-	 * the tiling and virtualize both &drm_crtc and &drm_plane if needed.
-	 */
-	struct drm_property_blob *tile_blob_ptr;
-
-/* should we poll this connector for connects and disconnects */
-/* hot plug detectable */
 #define DRM_CONNECTOR_POLL_HPD (1 << 0)
-/* poll for connections */
 #define DRM_CONNECTOR_POLL_CONNECT (1 << 1)
-/* can cleanly poll for disconnections without flickering the screen */
-/* DACs should rarely do this without a lot of testing */
 #define DRM_CONNECTOR_POLL_DISCONNECT (1 << 2)
 
 	/**
@@ -940,25 +941,40 @@ struct drm_connector {
 	 *     Periodically poll the connector for connection.
 	 *
 	 * DRM_CONNECTOR_POLL_DISCONNECT
-	 *     Periodically poll the connector for disconnection.
+	 *     Periodically poll the connector for disconnection, without
+	 *     causing flickering even when the connector is in use. DACs should
+	 *     rarely do this without a lot of testing.
 	 *
 	 * Set to 0 for connectors that don't support connection status
 	 * discovery.
 	 */
 	uint8_t polled;
 
-	/* requested DPMS state */
+	/**
+	 * @dpms: Current dpms state. For legacy drivers the
+	 * &drm_connector_funcs.dpms callback must update this. For atomic
+	 * drivers, this is handled by the core atomic code, and drivers must
+	 * only take &drm_crtc_state.active into account.
+	 */
 	int dpms;
 
+	/** @helper_private: mid-layer private data */
 	const struct drm_connector_helper_funcs *helper_private;
 
-	/* forced on connector */
+	/** @cmdline_mode: mode line parsed from the kernel cmdline for this connector */
 	struct drm_cmdline_mode cmdline_mode;
+	/** @force: a DRM_FORCE_<foo> state for forced mode sets */
 	enum drm_connector_force force;
+	/** @override_edid: has the EDID been overwritten through debugfs for testing? */
 	bool override_edid;
 
 #define DRM_CONNECTOR_MAX_ENCODER 3
+	/**
+	 * @encoder_ids: Valid encoders for this connector. Please only use
+	 * drm_connector_for_each_possible_encoder() to enumerate these.
+	 */
 	uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER];
+
 	/**
 	 * @encoder: Currently bound encoder driving this connector, if any.
 	 * Only really meaningful for non-atomic drivers. Atomic drivers should
@@ -968,19 +984,37 @@ struct drm_connector {
 	struct drm_encoder *encoder;
 
 #define MAX_ELD_BYTES	128
-	/* EDID bits */
+	/** @eld: EDID-like data, if present */
 	uint8_t eld[MAX_ELD_BYTES];
+	/** @latency_present: AV delay info from ELD, if found */
 	bool latency_present[2];
-	int video_latency[2];	/* [0]: progressive, [1]: interlaced */
+	/**
+	 * @video_latency: Video latency info from ELD, if found.
+	 * [0]: progressive, [1]: interlaced
+	 */
+	int video_latency[2];
+	/**
+	 * @audio_latency: audio latency info from ELD, if found
+	 * [0]: progressive, [1]: interlaced
+	 */
 	int audio_latency[2];
-	int null_edid_counter; /* needed to workaround some HW bugs where we get all 0s */
+	/**
+	 * @null_edid_counter: track sinks that give us all zeros for the EDID.
+	 * Needed to workaround some HW bugs where we get all 0s
+	 */
+	int null_edid_counter;
+
+	/** @bad_edid_counter: track sinks that give us an EDID with invalid checksum */
 	unsigned bad_edid_counter;
 
-	/* Flag for raw EDID header corruption - used in Displayport
-	 * compliance testing - * Displayport Link CTS Core 1.2 rev1.1 4.2.2.6
+	/**
+	 * @edid_corrupt: Indicates whether the last read EDID was corrupt. Used
+	 * in Displayport compliance testing - Displayport Link CTS Core 1.2
+	 * rev1.1 4.2.2.6
 	 */
 	bool edid_corrupt;
 
+	/** @debugfs_entry: debugfs directory for this connector */
 	struct dentry *debugfs_entry;
 
 	/**
@@ -988,7 +1022,7 @@ struct drm_connector {
 	 *
 	 * Current atomic state for this connector.
 	 *
-	 * This is protected by @drm_mode_config.connection_mutex. Note that
+	 * This is protected by &drm_mode_config.connection_mutex. Note that
 	 * nonblocking atomic commits access the current connector state without
 	 * taking locks. Either by going through the &struct drm_atomic_state
 	 * pointers, see for_each_oldnew_connector_in_state(),
@@ -999,19 +1033,44 @@ struct drm_connector {
 	 */
 	struct drm_connector_state *state;
 
-	/* DisplayID bits */
+	/* DisplayID bits. FIXME: Extract into a substruct? */
+
+	/**
+	 * @tile_blob_ptr:
+	 *
+	 * DRM blob property data for the tile property (used mostly by DP MST).
+	 * This is meant for screens which are driven through separate display
+	 * pipelines represented by &drm_crtc, which might not be running with
+	 * genlocked clocks. For tiled panels which are genlocked, like
+	 * dual-link LVDS or dual-link DSI, the driver should try to not expose
+	 * the tiling and virtualize both &drm_crtc and &drm_plane if needed.
+	 *
+	 * This should only be updated by calling
+	 * drm_connector_set_tile_property().
+	 */
+	struct drm_property_blob *tile_blob_ptr;
+
+	/** @has_tile: is this connector connected to a tiled monitor */
 	bool has_tile;
+	/** @tile_group: tile group for the connected monitor */
 	struct drm_tile_group *tile_group;
+	/** @tile_is_single_monitor: whether the tile is one monitor housing */
 	bool tile_is_single_monitor;
 
+	/** @num_h_tile: number of horizontal tiles in the tile group */
+	/** @num_v_tile: number of vertical tiles in the tile group */
 	uint8_t num_h_tile, num_v_tile;
+	/** @tile_h_loc: horizontal location of this tile */
+	/** @tile_v_loc: vertical location of this tile */
 	uint8_t tile_h_loc, tile_v_loc;
+	/** @tile_h_size: horizontal size of this tile. */
+	/** @tile_v_size: vertical size of this tile. */
 	uint16_t tile_h_size, tile_v_size;
 
 	/**
 	 * @free_node:
 	 *
-	 * List used only by &drm_connector_iter to be able to clean up a
+	 * List used only by &drm_connector_list_iter to be able to clean up a
 	 * connector from any context, in conjunction with
 	 * &drm_mode_config.connector_free_work.
 	 */
@@ -1026,7 +1085,7 @@ int drm_connector_init(struct drm_device *dev,
 		       int connector_type);
 int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
-int drm_mode_connector_attach_encoder(struct drm_connector *connector,
+int drm_connector_attach_encoder(struct drm_connector *connector,
 				      struct drm_encoder *encoder);
 
 void drm_connector_cleanup(struct drm_connector *connector);
@@ -1132,13 +1191,13 @@ void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame,
 
 int drm_mode_create_suggested_offset_properties(struct drm_device *dev);
 
-int drm_mode_connector_set_path_property(struct drm_connector *connector,
-					 const char *path);
-int drm_mode_connector_set_tile_property(struct drm_connector *connector);
-int drm_mode_connector_update_edid_property(struct drm_connector *connector,
-					    const struct edid *edid);
-void drm_mode_connector_set_link_status_property(struct drm_connector *connector,
-						 uint64_t link_status);
+int drm_connector_set_path_property(struct drm_connector *connector,
+				    const char *path);
+int drm_connector_set_tile_property(struct drm_connector *connector);
+int drm_connector_update_edid_property(struct drm_connector *connector,
+				       const struct edid *edid);
+void drm_connector_set_link_status_property(struct drm_connector *connector,
+					    uint64_t link_status);
 int drm_connector_init_panel_orientation_property(
 	struct drm_connector *connector, int width, int height);
 
@@ -1187,6 +1246,9 @@ struct drm_connector *
 drm_connector_list_iter_next(struct drm_connector_list_iter *iter);
 void drm_connector_list_iter_end(struct drm_connector_list_iter *iter);
 
+bool drm_connector_has_possible_encoder(struct drm_connector *connector,
+					struct drm_encoder *encoder);
+
 /**
  * drm_for_each_connector_iter - connector_list iterator macro
  * @connector: &struct drm_connector pointer used as cursor
@@ -1199,4 +1261,17 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter);
 #define drm_for_each_connector_iter(connector, iter) \
 	while ((connector = drm_connector_list_iter_next(iter)))
 
+/**
+ * drm_connector_for_each_possible_encoder - iterate connector's possible encoders
+ * @connector: &struct drm_connector pointer
+ * @encoder: &struct drm_encoder pointer used as cursor
+ * @__i: int iteration cursor, for macro-internal use
+ */
+#define drm_connector_for_each_possible_encoder(connector, encoder, __i) \
+	for ((__i) = 0; (__i) < ARRAY_SIZE((connector)->encoder_ids) && \
+		     (connector)->encoder_ids[(__i)] != 0; (__i)++) \
+		for_each_if((encoder) = \
+			    drm_encoder_find((connector)->dev, NULL, \
+					     (connector)->encoder_ids[(__i)])) \
+
 #endif
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 23eddbccab10..92e7fc7f05a4 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -77,21 +77,6 @@ struct drm_plane_helper_funcs;
 
 /**
  * struct drm_crtc_state - mutable CRTC state
- * @crtc: backpointer to the CRTC
- * @enable: whether the CRTC should be enabled, gates all other state
- * @active: whether the CRTC is actively displaying (used for DPMS)
- * @planes_changed: planes on this crtc are updated
- * @mode_changed: @mode or @enable has been changed
- * @active_changed: @active has been toggled.
- * @connectors_changed: connectors to this crtc have been updated
- * @zpos_changed: zpos values of planes on this crtc have been updated
- * @color_mgmt_changed: color management properties have changed (degamma or
- *	gamma LUT or CSC matrix)
- * @plane_mask: bitmask of (1 << drm_plane_index(plane)) of attached planes
- * @connector_mask: bitmask of (1 << drm_connector_index(connector)) of attached connectors
- * @encoder_mask: bitmask of (1 << drm_encoder_index(encoder)) of attached encoders
- * @mode_blob: &drm_property_blob for @mode
- * @state: backpointer to global drm_atomic_state
  *
  * Note that the distinction between @enable and @active is rather subtile:
  * Flipping @active while @enable is set without changing anything else may
@@ -102,31 +87,127 @@ struct drm_plane_helper_funcs;
  *
  * The three booleans active_changed, connectors_changed and mode_changed are
  * intended to indicate whether a full modeset is needed, rather than strictly
- * describing what has changed in a commit.
- * See also: drm_atomic_crtc_needs_modeset()
+ * describing what has changed in a commit. See also:
+ * drm_atomic_crtc_needs_modeset()
+ *
+ * WARNING: Transitional helpers (like drm_helper_crtc_mode_set() or
+ * drm_helper_crtc_mode_set_base()) do not maintain many of the derived control
+ * state like @plane_mask so drivers not converted over to atomic helpers should
+ * not rely on these being accurate!
  */
 struct drm_crtc_state {
+	/** @crtc: backpointer to the CRTC */
 	struct drm_crtc *crtc;
 
+	/**
+	 * @enable: Whether the CRTC should be enabled, gates all other state.
+	 * This controls reservations of shared resources. Actual hardware state
+	 * is controlled by @active.
+	 */
 	bool enable;
+
+	/**
+	 * @active: Whether the CRTC is actively displaying (used for DPMS).
+	 * Implies that @enable is set. The driver must not release any shared
+	 * resources if @active is set to false but @enable still true, because
+	 * userspace expects that a DPMS ON always succeeds.
+	 *
+	 * Hence drivers must not consult @active in their various
+	 * &drm_mode_config_funcs.atomic_check callback to reject an atomic
+	 * commit. They can consult it to aid in the computation of derived
+	 * hardware state, since even in the DPMS OFF state the display hardware
+	 * should be as much powered down as when the CRTC is completely
+	 * disabled through setting @enable to false.
+	 */
 	bool active;
 
-	/* computed state bits used by helpers and drivers */
+	/**
+	 * @planes_changed: Planes on this crtc are updated. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow.
+	 */
 	bool planes_changed : 1;
+
+	/**
+	 * @mode_changed: @mode or @enable has been changed. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow. See also
+	 * drm_atomic_crtc_needs_modeset().
+	 *
+	 * Drivers are supposed to set this for any CRTC state changes that
+	 * require a full modeset. They can also reset it to false if e.g. a
+	 * @mode change can be done without a full modeset by only changing
+	 * scaler settings.
+	 */
 	bool mode_changed : 1;
+
+	/**
+	 * @active_changed: @active has been toggled. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow. See also
+	 * drm_atomic_crtc_needs_modeset().
+	 */
 	bool active_changed : 1;
+
+	/**
+	 * @connectors_changed: Connectors to this crtc have been updated,
+	 * either in their state or routing. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow. See also
+	 * drm_atomic_crtc_needs_modeset().
+	 *
+	 * Drivers are supposed to set this as-needed from their own atomic
+	 * check code, e.g. from &drm_encoder_helper_funcs.atomic_check
+	 */
 	bool connectors_changed : 1;
+	/**
+	 * @zpos_changed: zpos values of planes on this crtc have been updated.
+	 * Used by the atomic helpers and drivers to steer the atomic commit
+	 * control flow.
+	 */
 	bool zpos_changed : 1;
+	/**
+	 * @color_mgmt_changed: Color management properties have changed
+	 * (@gamma_lut, @degamma_lut or @ctm). Used by the atomic helpers and
+	 * drivers to steer the atomic commit control flow.
+	 */
 	bool color_mgmt_changed : 1;
 
-	/* attached planes bitmask:
-	 * WARNING: transitional helpers do not maintain plane_mask so
-	 * drivers not converted over to atomic helpers should not rely
-	 * on plane_mask being accurate!
+	/**
+	 * @no_vblank:
+	 *
+	 * Reflects the ability of a CRTC to send VBLANK events. This state
+	 * usually depends on the pipeline configuration, and the main usuage
+	 * is CRTCs feeding a writeback connector operating in oneshot mode.
+	 * In this case the VBLANK event is only generated when a job is queued
+	 * to the writeback connector, and we want the core to fake VBLANK
+	 * events when this part of the pipeline hasn't changed but others had
+	 * or when the CRTC and connectors are being disabled.
+	 *
+	 * __drm_atomic_helper_crtc_duplicate_state() will not reset the value
+	 * from the current state, the CRTC driver is then responsible for
+	 * updating this field when needed.
+	 *
+	 * Note that the combination of &drm_crtc_state.event == NULL and
+	 * &drm_crtc_state.no_blank == true is valid and usually used when the
+	 * writeback connector attached to the CRTC has a new job queued. In
+	 * this case the driver will send the VBLANK event on its own when the
+	 * writeback job is complete.
+	 */
+	bool no_vblank : 1;
+
+	/**
+	 * @plane_mask: Bitmask of drm_plane_mask(plane) of planes attached to
+	 * this CRTC.
 	 */
 	u32 plane_mask;
 
+	/**
+	 * @connector_mask: Bitmask of drm_connector_mask(connector) of
+	 * connectors attached to this CRTC.
+	 */
 	u32 connector_mask;
+
+	/**
+	 * @encoder_mask: Bitmask of drm_encoder_mask(encoder) of encoders
+	 * attached to this CRTC.
+	 */
 	u32 encoder_mask;
 
 	/**
@@ -136,7 +217,7 @@ struct drm_crtc_state {
 	 * differences between the mode requested by userspace in @mode and what
 	 * is actually programmed into the hardware.
 	 *
-	 * For drivers using drm_bridge, this stores hardware display timings
+	 * For drivers using &drm_bridge, this stores hardware display timings
 	 * used between the CRTC and the first bridge. For other drivers, the
 	 * meaning of the adjusted_mode field is purely driver implementation
 	 * defined information, and will usually be used to store the hardware
@@ -161,7 +242,10 @@ struct drm_crtc_state {
 	 */
 	struct drm_display_mode mode;
 
-	/* blob property to expose current mode to atomic userspace */
+	/**
+	 * @mode_blob: &drm_property_blob for @mode, for exposing the mode to
+	 * atomic userspace.
+	 */
 	struct drm_property_blob *mode_blob;
 
 	/**
@@ -265,6 +349,7 @@ struct drm_crtc_state {
 	 */
 	struct drm_crtc_commit *commit;
 
+	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
 };
 
@@ -724,35 +809,25 @@ struct drm_crtc_funcs {
 
 /**
  * struct drm_crtc - central CRTC control structure
- * @dev: parent DRM device
- * @port: OF node used by drm_of_find_possible_crtcs()
- * @head: list management
- * @name: human readable name, can be overwritten by the driver
- * @mutex: per-CRTC locking
- * @base: base KMS object for ID tracking etc.
- * @primary: primary plane for this CRTC
- * @cursor: cursor plane for this CRTC
- * @cursor_x: current x position of the cursor, used for universal cursor planes
- * @cursor_y: current y position of the cursor, used for universal cursor planes
- * @enabled: is this CRTC enabled?
- * @mode: current mode timings
- * @hwmode: mode timings as programmed to hw regs
- * @x: x position on screen
- * @y: y position on screen
- * @funcs: CRTC control functions
- * @gamma_size: size of gamma ramp
- * @gamma_store: gamma ramp values
- * @helper_private: mid-layer private data
- * @properties: property tracking for this CRTC
  *
  * Each CRTC may have one or more connectors associated with it.  This structure
  * allows the CRTC to be controlled.
  */
 struct drm_crtc {
+	/** @dev: parent DRM device */
 	struct drm_device *dev;
+	/** @port: OF node used by drm_of_find_possible_crtcs(). */
 	struct device_node *port;
+	/**
+	 * @head:
+	 *
+	 * List of all CRTCs on @dev, linked from &drm_mode_config.crtc_list.
+	 * Invariant over the lifetime of @dev and therefore does not need
+	 * locking.
+	 */
 	struct list_head head;
 
+	/** @name: human readable name, can be overwritten by the driver */
 	char *name;
 
 	/**
@@ -767,10 +842,25 @@ struct drm_crtc {
 	 */
 	struct drm_modeset_lock mutex;
 
+	/** @base: base KMS object for ID tracking etc. */
 	struct drm_mode_object base;
 
-	/* primary and cursor planes for CRTC */
+	/**
+	 * @primary:
+	 * Primary plane for this CRTC. Note that this is only
+	 * relevant for legacy IOCTL, it specifies the plane implicitly used by
+	 * the SETCRTC and PAGE_FLIP IOCTLs. It does not have any significance
+	 * beyond that.
+	 */
 	struct drm_plane *primary;
+
+	/**
+	 * @cursor:
+	 * Cursor plane for this CRTC. Note that this is only relevant for
+	 * legacy IOCTL, it specifies the plane implicitly used by the SETCURSOR
+	 * and SETCURSOR2 IOCTLs. It does not have any significance
+	 * beyond that.
+	 */
 	struct drm_plane *cursor;
 
 	/**
@@ -779,30 +869,94 @@ struct drm_crtc {
 	 */
 	unsigned index;
 
-	/* position of cursor plane on crtc */
+	/**
+	 * @cursor_x: Current x position of the cursor, used for universal
+	 * cursor planes because the SETCURSOR IOCTL only can update the
+	 * framebuffer without supplying the coordinates. Drivers should not use
+	 * this directly, atomic drivers should look at &drm_plane_state.crtc_x
+	 * of the cursor plane instead.
+	 */
 	int cursor_x;
+	/**
+	 * @cursor_y: Current y position of the cursor, used for universal
+	 * cursor planes because the SETCURSOR IOCTL only can update the
+	 * framebuffer without supplying the coordinates. Drivers should not use
+	 * this directly, atomic drivers should look at &drm_plane_state.crtc_y
+	 * of the cursor plane instead.
+	 */
 	int cursor_y;
 
+	/**
+	 * @enabled:
+	 *
+	 * Is this CRTC enabled? Should only be used by legacy drivers, atomic
+	 * drivers should instead consult &drm_crtc_state.enable and
+	 * &drm_crtc_state.active. Atomic drivers can update this by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
 	bool enabled;
 
-	/* Requested mode from modesetting. */
+	/**
+	 * @mode:
+	 *
+	 * Current mode timings. Should only be used by legacy drivers, atomic
+	 * drivers should instead consult &drm_crtc_state.mode. Atomic drivers
+	 * can update this by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
 	struct drm_display_mode mode;
 
-	/* Programmed mode in hw, after adjustments for encoders,
-	 * crtc, panel scaling etc. Needed for timestamping etc.
+	/**
+	 * @hwmode:
+	 *
+	 * Programmed mode in hw, after adjustments for encoders, crtc, panel
+	 * scaling etc. Should only be used by legacy drivers, for high
+	 * precision vblank timestamps in
+	 * drm_calc_vbltimestamp_from_scanoutpos().
+	 *
+	 * Note that atomic drivers should not use this, but instead use
+	 * &drm_crtc_state.adjusted_mode. And for high-precision timestamps
+	 * drm_calc_vbltimestamp_from_scanoutpos() used &drm_vblank_crtc.hwmode,
+	 * which is filled out by calling drm_calc_timestamping_constants().
 	 */
 	struct drm_display_mode hwmode;
 
-	int x, y;
+	/**
+	 * @x:
+	 * x position on screen. Should only be used by legacy drivers, atomic
+	 * drivers should look at &drm_plane_state.crtc_x of the primary plane
+	 * instead. Updated by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
+	int x;
+	/**
+	 * @y:
+	 * y position on screen. Should only be used by legacy drivers, atomic
+	 * drivers should look at &drm_plane_state.crtc_y of the primary plane
+	 * instead. Updated by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
+	int y;
+
+	/** @funcs: CRTC control functions */
 	const struct drm_crtc_funcs *funcs;
 
-	/* Legacy FB CRTC gamma size for reporting to userspace */
+	/**
+	 * @gamma_size: Size of legacy gamma ramp reported to userspace. Set up
+	 * by calling drm_mode_crtc_set_gamma_size().
+	 */
 	uint32_t gamma_size;
+
+	/**
+	 * @gamma_store: Gamma ramp values used by the legacy SETGAMMA and
+	 * GETGAMMA IOCTls. Set up by calling drm_mode_crtc_set_gamma_size().
+	 */
 	uint16_t *gamma_store;
 
-	/* if you are using the helper */
+	/** @helper_private: mid-layer private data */
 	const struct drm_crtc_helper_funcs *helper_private;
 
+	/** @properties: property tracking for this CRTC */
 	struct drm_object_properties properties;
 
 	/**
@@ -872,7 +1026,6 @@ struct drm_crtc {
 	 *
 	 * spinlock to protect the fences in the fence_context.
 	 */
-
 	spinlock_t fence_lock;
 	/**
 	 * @fence_seqno:
@@ -942,8 +1095,8 @@ static inline unsigned int drm_crtc_index(const struct drm_crtc *crtc)
  * drm_crtc_mask - find the mask of a registered CRTC
  * @crtc: CRTC to find mask for
  *
- * Given a registered CRTC, return the mask bit of that CRTC for an
- * encoder's possible_crtcs field.
+ * Given a registered CRTC, return the mask bit of that CRTC for the
+ * &drm_encoder.possible_crtcs and &drm_plane.possible_crtcs fields.
  */
 static inline uint32_t drm_crtc_mask(const struct drm_crtc *crtc)
 {
diff --git a/include/drm/drm_debugfs_crc.h b/include/drm/drm_debugfs_crc.h
index 7d63b1d4adb9..b225eeb30d05 100644
--- a/include/drm/drm_debugfs_crc.h
+++ b/include/drm/drm_debugfs_crc.h
@@ -43,6 +43,7 @@ struct drm_crtc_crc_entry {
  * @lock: protects the fields in this struct
  * @source: name of the currently configured source of CRCs
  * @opened: whether userspace has opened the data file for reading
+ * @overflow: whether an overflow occured.
  * @entries: array of entries, with size of %DRM_CRC_ENTRIES_NR
  * @head: head of circular queue
  * @tail: tail of circular queue
@@ -52,7 +53,7 @@ struct drm_crtc_crc_entry {
 struct drm_crtc_crc {
 	spinlock_t lock;
 	const char *source;
-	bool opened;
+	bool opened, overflow;
 	struct drm_crtc_crc_entry *entries;
 	int head, tail;
 	size_t values_cnt;
diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index 858ba19a3e29..f9c6e0e3aec7 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -74,6 +74,27 @@ struct drm_device {
 	struct mutex filelist_mutex;
 	struct list_head filelist;
 
+	/**
+	 * @filelist_internal:
+	 *
+	 * List of open DRM files for in-kernel clients. Protected by @filelist_mutex.
+	 */
+	struct list_head filelist_internal;
+
+	/**
+	 * @clientlist_mutex:
+	 *
+	 * Protects @clientlist access.
+	 */
+	struct mutex clientlist_mutex;
+
+	/**
+	 * @clientlist:
+	 *
+	 * List of in-kernel clients. Protected by @clientlist_mutex.
+	 */
+	struct list_head clientlist;
+
 	/** \name Memory management */
 	/*@{ */
 	struct list_head maplist;	/**< Linked list of regions */
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index c01564991a9f..05cc31b5db16 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1078,6 +1078,25 @@ struct drm_dp_aux_msg {
 	size_t size;
 };
 
+struct cec_adapter;
+struct edid;
+
+/**
+ * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX
+ * @lock: mutex protecting this struct
+ * @adap: the CEC adapter for CEC-Tunneling-over-AUX support.
+ * @name: name of the CEC adapter
+ * @parent: parent device of the CEC adapter
+ * @unregister_work: unregister the CEC adapter
+ */
+struct drm_dp_aux_cec {
+	struct mutex lock;
+	struct cec_adapter *adap;
+	const char *name;
+	struct device *parent;
+	struct delayed_work unregister_work;
+};
+
 /**
  * struct drm_dp_aux - DisplayPort AUX channel
  * @name: user-visible name of this AUX channel and the I2C-over-AUX adapter
@@ -1136,6 +1155,10 @@ struct drm_dp_aux {
 	 * @i2c_defer_count: Counts I2C DEFERs, used for DP validation.
 	 */
 	unsigned i2c_defer_count;
+	/**
+	 * @cec: struct containing fields used for CEC-Tunneling-over-AUX.
+	 */
+	struct drm_dp_aux_cec cec;
 };
 
 ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
@@ -1258,4 +1281,37 @@ drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk)
 	return desc->quirks & BIT(quirk);
 }
 
+#ifdef CONFIG_DRM_DP_CEC
+void drm_dp_cec_irq(struct drm_dp_aux *aux);
+void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name,
+				   struct device *parent);
+void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux);
+void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid);
+void drm_dp_cec_unset_edid(struct drm_dp_aux *aux);
+#else
+static inline void drm_dp_cec_irq(struct drm_dp_aux *aux)
+{
+}
+
+static inline void drm_dp_cec_register_connector(struct drm_dp_aux *aux,
+						 const char *name,
+						 struct device *parent)
+{
+}
+
+static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux)
+{
+}
+
+static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux,
+				       const struct edid *edid)
+{
+}
+
+static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux)
+{
+}
+
+#endif
+
 #endif /* _DRM_DP_HELPER_H_ */
diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index 7e545f5f94d3..46a8009784df 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -649,6 +649,35 @@ static inline bool drm_dev_is_unplugged(struct drm_device *dev)
 	return true;
 }
 
+/**
+ * drm_core_check_feature - check driver feature flags
+ * @dev: DRM device to check
+ * @feature: feature flag
+ *
+ * This checks @dev for driver features, see &drm_driver.driver_features and the
+ * various DRIVER_\* flags.
+ *
+ * Returns true if the @feature is supported, false otherwise.
+ */
+static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
+{
+	return dev->driver->driver_features & feature;
+}
+
+/**
+ * drm_drv_uses_atomic_modeset - check if the driver implements
+ * atomic_commit()
+ * @dev: DRM device
+ *
+ * This check is useful if drivers do not have DRIVER_ATOMIC set but
+ * have atomic modesetting internally implemented.
+ */
+static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev)
+{
+	return drm_core_check_feature(dev, DRIVER_ATOMIC) ||
+		dev->mode_config.funcs->atomic_commit != NULL;
+}
+
 
 int drm_dev_set_unique(struct drm_device *dev, const char *name);
 
diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h
index d532f88a8d55..96e26e3b9a0c 100644
--- a/include/drm/drm_fb_cma_helper.h
+++ b/include/drm/drm_fb_cma_helper.h
@@ -16,16 +16,10 @@ struct drm_mode_fb_cmd2;
 struct drm_plane;
 struct drm_plane_state;
 
-int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs);
 int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
 			  unsigned int max_conn_count);
 void drm_fb_cma_fbdev_fini(struct drm_device *dev);
 
-struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs);
 struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
 	unsigned int preferred_bpp, unsigned int max_conn_count);
 void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma);
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index b069433e7fc1..5db08c8f1d25 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -32,6 +32,7 @@
 
 struct drm_fb_helper;
 
+#include <drm/drm_client.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_device.h>
 #include <linux/kgdb.h>
@@ -154,6 +155,20 @@ struct drm_fb_helper_connector {
  * operations.
  */
 struct drm_fb_helper {
+	/**
+	 * @client:
+	 *
+	 * DRM client used by the generic fbdev emulation.
+	 */
+	struct drm_client_dev client;
+
+	/**
+	 * @buffer:
+	 *
+	 * Framebuffer used by the generic fbdev emulation.
+	 */
+	struct drm_client_buffer *buffer;
+
 	struct drm_framebuffer *fb;
 	struct drm_device *dev;
 	int crtc_count;
@@ -234,6 +249,12 @@ struct drm_fb_helper {
 	int preferred_bpp;
 };
 
+static inline struct drm_fb_helper *
+drm_fb_helper_from_client(struct drm_client_dev *client)
+{
+	return container_of(client, struct drm_fb_helper, client);
+}
+
 /**
  * define DRM_FB_HELPER_DEFAULT_OPS - helper define for drm drivers
  *
@@ -330,6 +351,10 @@ void drm_fb_helper_fbdev_teardown(struct drm_device *dev);
 
 void drm_fb_helper_lastclose(struct drm_device *dev);
 void drm_fb_helper_output_poll_changed(struct drm_device *dev);
+
+int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+				struct drm_fb_helper_surface_size *sizes);
+int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp);
 #else
 static inline void drm_fb_helper_prepare(struct drm_device *dev,
 					struct drm_fb_helper *helper,
@@ -564,6 +589,19 @@ static inline void drm_fb_helper_output_poll_changed(struct drm_device *dev)
 {
 }
 
+static inline int
+drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+			    struct drm_fb_helper_surface_size *sizes)
+{
+	return 0;
+}
+
+static inline int
+drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
+{
+	return 0;
+}
+
 #endif
 
 static inline int
diff --git a/include/drm/drm_fourcc.h b/include/drm/drm_fourcc.h
index 3e86408dac9f..f9c15845f465 100644
--- a/include/drm/drm_fourcc.h
+++ b/include/drm/drm_fourcc.h
@@ -39,6 +39,7 @@ struct drm_mode_fb_cmd2;
  * @hsub: Horizontal chroma subsampling factor
  * @vsub: Vertical chroma subsampling factor
  * @has_alpha: Does the format embeds an alpha component?
+ * @is_yuv: Is it a YUV format?
  */
 struct drm_format_info {
 	u32 format;
@@ -48,6 +49,7 @@ struct drm_format_info {
 	u8 hsub;
 	u8 vsub;
 	bool has_alpha;
+	bool is_yuv;
 };
 
 /**
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index b159fe07fcf9..baded6514456 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -530,7 +530,7 @@ drm_mode_validate_ycbcr420(const struct drm_display_mode *mode,
 void drm_mode_prune_invalid(struct drm_device *dev,
 			    struct list_head *mode_list, bool verbose);
 void drm_mode_sort(struct list_head *mode_list);
-void drm_mode_connector_list_update(struct drm_connector *connector);
+void drm_connector_list_update(struct drm_connector *connector);
 
 /* parsing cmdline modes */
 bool
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index 3b289773297c..61142aa0ab23 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -785,7 +785,7 @@ struct drm_connector_helper_funcs {
 	 *
 	 * This function should fill in all modes currently valid for the sink
 	 * into the &drm_connector.probed_modes list. It should also update the
-	 * EDID property by calling drm_mode_connector_update_edid_property().
+	 * EDID property by calling drm_connector_update_edid_property().
 	 *
 	 * The usual way to implement this is to cache the EDID retrieved in the
 	 * probe callback somewhere in the driver-private connector structure.
@@ -980,11 +980,15 @@ struct drm_connector_helper_funcs {
 	 *
 	 * This hook is to be used by drivers implementing writeback connectors
 	 * that need a point when to commit the writeback job to the hardware.
+	 * The writeback_job to commit is available in
+	 * &drm_connector_state.writeback_job.
+	 *
+	 * This hook is optional.
 	 *
 	 * This callback is used by the atomic modeset helpers.
 	 */
 	void (*atomic_commit)(struct drm_connector *connector,
-			      struct drm_writeback_job *writeback_job);
+			      struct drm_connector_state *state);
 };
 
 /**
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index 26a1b5fd8796..582a0ec0aa70 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -200,7 +200,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np);
 #else
 static inline struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 #endif
 
diff --git a/include/drm/drm_pci.h b/include/drm/drm_pci.h
index 674599025d7d..8181e9e7cf1d 100644
--- a/include/drm/drm_pci.h
+++ b/include/drm/drm_pci.h
@@ -58,11 +58,4 @@ static inline int drm_get_pci_dev(struct pci_dev *pdev,
 }
 #endif
 
-#define DRM_PCIE_SPEED_25 1
-#define DRM_PCIE_SPEED_50 2
-#define DRM_PCIE_SPEED_80 4
-
-int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *speed_mask);
-int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw);
-
 #endif /* _DRM_PCI_H_ */
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index cee9dfaaa740..8a152dc16ea5 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -34,31 +34,15 @@ struct drm_modeset_acquire_ctx;
 
 /**
  * struct drm_plane_state - mutable plane state
- * @plane: backpointer to the plane
- * @crtc_w: width of visible portion of plane on crtc
- * @crtc_h: height of visible portion of plane on crtc
- * @src_x: left position of visible portion of plane within
- *	plane (in 16.16)
- * @src_y: upper position of visible portion of plane within
- *	plane (in 16.16)
- * @src_w: width of visible portion of plane (in 16.16)
- * @src_h: height of visible portion of plane (in 16.16)
- * @alpha: opacity of the plane
- * @rotation: rotation of the plane
- * @zpos: priority of the given plane on crtc (optional)
- *	Note that multiple active planes on the same crtc can have an identical
- *	zpos value. The rule to solving the conflict is to compare the plane
- *	object IDs; the plane with a higher ID must be stacked on top of a
- *	plane with a lower ID.
- * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1
- *	where N is the number of active planes for given crtc. Note that
- *	the driver must set drm_mode_config.normalize_zpos or call
- *	drm_atomic_normalize_zpos() to update this before it can be trusted.
- * @src: clipped source coordinates of the plane (in 16.16)
- * @dst: clipped destination coordinates of the plane
- * @state: backpointer to global drm_atomic_state
+ *
+ * Please not that the destination coordinates @crtc_x, @crtc_y, @crtc_h and
+ * @crtc_w and the source coordinates @src_x, @src_y, @src_h and @src_w are the
+ * raw coordinates provided by userspace. Drivers should use
+ * drm_atomic_helper_check_plane_state() and only use the derived rectangles in
+ * @src and @dst to program the hardware.
  */
 struct drm_plane_state {
+	/** @plane: backpointer to the plane */
 	struct drm_plane *plane;
 
 	/**
@@ -87,7 +71,7 @@ struct drm_plane_state {
 	 * preserved.
 	 *
 	 * Drivers should store any implicit fence in this from their
-	 * &drm_plane_helper.prepare_fb callback. See drm_gem_fb_prepare_fb()
+	 * &drm_plane_helper_funcs.prepare_fb callback. See drm_gem_fb_prepare_fb()
 	 * and drm_gem_fb_simple_display_pipe_prepare_fb() for suitable helpers.
 	 */
 	struct dma_fence *fence;
@@ -108,20 +92,60 @@ struct drm_plane_state {
 	 */
 	int32_t crtc_y;
 
+	/** @crtc_w: width of visible portion of plane on crtc */
+	/** @crtc_h: height of visible portion of plane on crtc */
 	uint32_t crtc_w, crtc_h;
 
-	/* Source values are 16.16 fixed point */
-	uint32_t src_x, src_y;
+	/**
+	 * @src_x: left position of visible portion of plane within plane (in
+	 * 16.16 fixed point).
+	 */
+	uint32_t src_x;
+	/**
+	 * @src_y: upper position of visible portion of plane within plane (in
+	 * 16.16 fixed point).
+	 */
+	uint32_t src_y;
+	/** @src_w: width of visible portion of plane (in 16.16) */
+	/** @src_h: height of visible portion of plane (in 16.16) */
 	uint32_t src_h, src_w;
 
-	/* Plane opacity */
+	/**
+	 * @alpha:
+	 * Opacity of the plane with 0 as completely transparent and 0xffff as
+	 * completely opaque. See drm_plane_create_alpha_property() for more
+	 * details.
+	 */
 	u16 alpha;
 
-	/* Plane rotation */
+	/**
+	 * @rotation:
+	 * Rotation of the plane. See drm_plane_create_rotation_property() for
+	 * more details.
+	 */
 	unsigned int rotation;
 
-	/* Plane zpos */
+	/**
+	 * @zpos:
+	 * Priority of the given plane on crtc (optional).
+	 *
+	 * Note that multiple active planes on the same crtc can have an
+	 * identical zpos value. The rule to solving the conflict is to compare
+	 * the plane object IDs; the plane with a higher ID must be stacked on
+	 * top of a plane with a lower ID.
+	 *
+	 * See drm_plane_create_zpos_property() and
+	 * drm_plane_create_zpos_immutable_property() for more details.
+	 */
 	unsigned int zpos;
+
+	/**
+	 * @normalized_zpos:
+	 * Normalized value of zpos: unique, range from 0 to N-1 where N is the
+	 * number of active planes for given crtc. Note that the driver must set
+	 * &drm_mode_config.normalize_zpos or call drm_atomic_normalize_zpos() to
+	 * update this before it can be trusted.
+	 */
 	unsigned int normalized_zpos;
 
 	/**
@@ -138,7 +162,8 @@ struct drm_plane_state {
 	 */
 	enum drm_color_range color_range;
 
-	/* Clipped coordinates */
+	/** @src: clipped source coordinates of the plane (in 16.16) */
+	/** @dst: clipped destination coordinates of the plane */
 	struct drm_rect src, dst;
 
 	/**
@@ -157,6 +182,7 @@ struct drm_plane_state {
 	 */
 	struct drm_crtc_commit *commit;
 
+	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
 };
 
@@ -499,30 +525,27 @@ enum drm_plane_type {
 
 /**
  * struct drm_plane - central DRM plane control structure
- * @dev: DRM device this plane belongs to
- * @head: for list management
- * @name: human readable name, can be overwritten by the driver
- * @base: base mode object
- * @possible_crtcs: pipes this plane can be bound to
- * @format_types: array of formats supported by this plane
- * @format_count: number of formats supported
- * @format_default: driver hasn't supplied supported formats for the plane
- * @modifiers: array of modifiers supported by this plane
- * @modifier_count: number of modifiers supported
- * @old_fb: Temporary tracking of the old fb while a modeset is ongoing. Used by
- * 	drm_mode_set_config_internal() to implement correct refcounting.
- * @funcs: helper functions
- * @properties: property tracking for this plane
- * @type: type of plane (overlay, primary, cursor)
- * @alpha_property: alpha property for this plane
- * @zpos_property: zpos property for this plane
- * @rotation_property: rotation property for this plane
- * @helper_private: mid-layer private data
+ *
+ * Planes represent the scanout hardware of a display block. They receive their
+ * input data from a &drm_framebuffer and feed it to a &drm_crtc. Planes control
+ * the color conversion, see `Plane Composition Properties`_ for more details,
+ * and are also involved in the color conversion of input pixels, see `Color
+ * Management Properties`_ for details on that.
  */
 struct drm_plane {
+	/** @dev: DRM device this plane belongs to */
 	struct drm_device *dev;
+
+	/**
+	 * @head:
+	 *
+	 * List of all planes on @dev, linked from &drm_mode_config.plane_list.
+	 * Invariant over the lifetime of @dev and therefore does not need
+	 * locking.
+	 */
 	struct list_head head;
 
+	/** @name: human readable name, can be overwritten by the driver */
 	char *name;
 
 	/**
@@ -536,35 +559,62 @@ struct drm_plane {
 	 */
 	struct drm_modeset_lock mutex;
 
+	/** @base: base mode object */
 	struct drm_mode_object base;
 
+	/**
+	 * @possible_crtcs: pipes this plane can be bound to constructed from
+	 * drm_crtc_mask()
+	 */
 	uint32_t possible_crtcs;
+	/** @format_types: array of formats supported by this plane */
 	uint32_t *format_types;
+	/** @format_count: Size of the array pointed at by @format_types. */
 	unsigned int format_count;
+	/**
+	 * @format_default: driver hasn't supplied supported formats for the
+	 * plane. Used by the drm_plane_init compatibility wrapper only.
+	 */
 	bool format_default;
 
+	/** @modifiers: array of modifiers supported by this plane */
 	uint64_t *modifiers;
+	/** @modifier_count: Size of the array pointed at by @modifier_count. */
 	unsigned int modifier_count;
 
 	/**
-	 * @crtc: Currently bound CRTC, only really meaningful for non-atomic
-	 * drivers.  Atomic drivers should instead check &drm_plane_state.crtc.
+	 * @crtc:
+	 *
+	 * Currently bound CRTC, only meaningful for non-atomic drivers. For
+	 * atomic drivers this is forced to be NULL, atomic drivers should
+	 * instead check &drm_plane_state.crtc.
 	 */
 	struct drm_crtc *crtc;
 
 	/**
-	 * @fb: Currently bound framebuffer, only really meaningful for
-	 * non-atomic drivers.  Atomic drivers should instead check
-	 * &drm_plane_state.fb.
+	 * @fb:
+	 *
+	 * Currently bound framebuffer, only meaningful for non-atomic drivers.
+	 * For atomic drivers this is forced to be NULL, atomic drivers should
+	 * instead check &drm_plane_state.fb.
 	 */
 	struct drm_framebuffer *fb;
 
+	/**
+	 * @old_fb:
+	 *
+	 * Temporary tracking of the old fb while a modeset is ongoing. Only
+	 * used by non-atomic drivers, forced to be NULL for atomic drivers.
+	 */
 	struct drm_framebuffer *old_fb;
 
+	/** @funcs: plane control functions */
 	const struct drm_plane_funcs *funcs;
 
+	/** @properties: property tracking for this plane */
 	struct drm_object_properties properties;
 
+	/** @type: Type of plane, see &enum drm_plane_type for details. */
 	enum drm_plane_type type;
 
 	/**
@@ -573,6 +623,7 @@ struct drm_plane {
 	 */
 	unsigned index;
 
+	/** @helper_private: mid-layer private data */
 	const struct drm_plane_helper_funcs *helper_private;
 
 	/**
@@ -590,8 +641,23 @@ struct drm_plane {
 	 */
 	struct drm_plane_state *state;
 
+	/**
+	 * @alpha_property:
+	 * Optional alpha property for this plane. See
+	 * drm_plane_create_alpha_property().
+	 */
 	struct drm_property *alpha_property;
+	/**
+	 * @zpos_property:
+	 * Optional zpos property for this plane. See
+	 * drm_plane_create_zpos_property().
+	 */
 	struct drm_property *zpos_property;
+	/**
+	 * @rotation_property:
+	 * Optional rotation property for this plane. See
+	 * drm_plane_create_rotation_property().
+	 */
 	struct drm_property *rotation_property;
 
 	/**
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index e1a46e9991cc..f3e6eed3e79c 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -69,16 +69,21 @@
 struct drm_printer {
 	/* private: */
 	void (*printfn)(struct drm_printer *p, struct va_format *vaf);
+	void (*puts)(struct drm_printer *p, const char *str);
 	void *arg;
 	const char *prefix;
 };
 
+void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf);
+void __drm_puts_coredump(struct drm_printer *p, const char *str);
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf);
+void __drm_puts_seq_file(struct drm_printer *p, const char *str);
 void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf);
 void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf);
 
 __printf(2, 3)
 void drm_printf(struct drm_printer *p, const char *f, ...);
+void drm_puts(struct drm_printer *p, const char *str);
 
 __printf(2, 0)
 /**
@@ -105,6 +110,71 @@ drm_vprintf(struct drm_printer *p, const char *fmt, va_list *va)
 	drm_printf((printer), "%.*s" fmt, (indent), "\t\t\t\t\tX", ##__VA_ARGS__)
 
 /**
+ * struct drm_print_iterator - local struct used with drm_printer_coredump
+ * @data: Pointer to the devcoredump output buffer
+ * @start: The offset within the buffer to start writing
+ * @remain: The number of bytes to write for this iteration
+ */
+struct drm_print_iterator {
+	void *data;
+	ssize_t start;
+	ssize_t remain;
+	/* private: */
+	ssize_t offset;
+};
+
+/**
+ * drm_coredump_printer - construct a &drm_printer that can output to a buffer
+ * from the read function for devcoredump
+ * @iter: A pointer to a struct drm_print_iterator for the read instance
+ *
+ * This wrapper extends drm_printf() to work with a dev_coredumpm() callback
+ * function. The passed in drm_print_iterator struct contains the buffer
+ * pointer, size and offset as passed in from devcoredump.
+ *
+ * For example::
+ *
+ *	void coredump_read(char *buffer, loff_t offset, size_t count,
+ *		void *data, size_t datalen)
+ *	{
+ *		struct drm_print_iterator iter;
+ *		struct drm_printer p;
+ *
+ *		iter.data = buffer;
+ *		iter.start = offset;
+ *		iter.remain = count;
+ *
+ *		p = drm_coredump_printer(&iter);
+ *
+ *		drm_printf(p, "foo=%d\n", foo);
+ *	}
+ *
+ *	void makecoredump(...)
+ *	{
+ *		...
+ *		dev_coredumpm(dev, THIS_MODULE, data, 0, GFP_KERNEL,
+ *			coredump_read, ...)
+ *	}
+ *
+ * RETURNS:
+ * The &drm_printer object
+ */
+static inline struct drm_printer
+drm_coredump_printer(struct drm_print_iterator *iter)
+{
+	struct drm_printer p = {
+		.printfn = __drm_printfn_coredump,
+		.puts = __drm_puts_coredump,
+		.arg = iter,
+	};
+
+	/* Set the internal offset of the iterator to zero */
+	iter->offset = 0;
+
+	return p;
+}
+
+/**
  * drm_seq_file_printer - construct a &drm_printer that outputs to &seq_file
  * @f:  the &struct seq_file to output to
  *
@@ -115,6 +185,7 @@ static inline struct drm_printer drm_seq_file_printer(struct seq_file *f)
 {
 	struct drm_printer p = {
 		.printfn = __drm_printfn_seq_file,
+		.puts = __drm_puts_seq_file,
 		.arg = f,
 	};
 	return p;
@@ -195,6 +266,7 @@ static inline struct drm_printer drm_debug_printer(const char *prefix)
 #define DRM_UT_VBL		0x20
 #define DRM_UT_STATE		0x40
 #define DRM_UT_LEASE		0x80
+#define DRM_UT_DP		0x100
 
 __printf(3, 4)
 void drm_dev_printk(const struct device *dev, const char *level,
@@ -307,6 +379,11 @@ void drm_err(const char *format, ...);
 #define DRM_DEBUG_LEASE(fmt, ...)					\
 	drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
 
+#define	DRM_DEV_DEBUG_DP(dev, fmt, ...)					\
+	drm_dev_dbg(dev, DRM_UT_DP, fmt, ## __VA_ARGS__)
+#define DRM_DEBUG_DP(dev, fmt, ...)					\
+	drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__)
+
 #define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, category, fmt, ...)	\
 ({									\
 	static DEFINE_RATELIMIT_STATE(_rs,				\
diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h
index 1d5c0b2a8956..c030f6ccab99 100644
--- a/include/drm/drm_property.h
+++ b/include/drm/drm_property.h
@@ -147,10 +147,10 @@ struct drm_property {
 	 *     properties are not exposed to legacy userspace.
 	 *
 	 * DRM_MODE_PROP_IMMUTABLE
-	 *     Set for properties where userspace cannot be changed by
+	 *     Set for properties whose values cannot be changed by
 	 *     userspace. The kernel is allowed to update the value of these
 	 *     properties. This is generally used to expose probe state to
-	 *     usersapce, e.g. the EDID, or the connector path property on DP
+	 *     userspace, e.g. the EDID, or the connector path property on DP
 	 *     MST sinks.
 	 */
 	uint32_t flags;
diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h
index 8758df94e9a0..c7987daeaed0 100644
--- a/include/drm/drm_vma_manager.h
+++ b/include/drm/drm_vma_manager.h
@@ -41,6 +41,7 @@ struct drm_vma_offset_node {
 	rwlock_t vm_lock;
 	struct drm_mm_node vm_node;
 	struct rb_root vm_files;
+	bool readonly:1;
 };
 
 struct drm_vma_offset_manager {
diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h
index a10fe556dfd4..23df9d463003 100644
--- a/include/drm/drm_writeback.h
+++ b/include/drm/drm_writeback.h
@@ -110,6 +110,12 @@ struct drm_writeback_job {
 	struct dma_fence *out_fence;
 };
 
+static inline struct drm_writeback_connector *
+drm_connector_to_writeback(struct drm_connector *connector)
+{
+	return container_of(connector, struct drm_writeback_connector, base);
+}
+
 int drm_writeback_connector_init(struct drm_device *dev,
 				 struct drm_writeback_connector *wb_connector,
 				 const struct drm_connector_funcs *con_funcs,
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 7c2dfd6cc1af..091b9afcd184 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -52,7 +52,6 @@ enum drm_sched_priority {
  *        runqueue.
  * @rq: runqueue to which this entity belongs.
  * @rq_lock: lock to modify the runqueue to which this entity belongs.
- * @sched: the scheduler instance to which this entity is enqueued.
  * @job_queue: the list of jobs of this entity.
  * @fence_seq: a linearly increasing seqno incremented with each
  *             new &drm_sched_fence which is part of the entity.
@@ -76,7 +75,6 @@ struct drm_sched_entity {
 	struct list_head		list;
 	struct drm_sched_rq		*rq;
 	spinlock_t			rq_lock;
-	struct drm_gpu_scheduler	*sched;
 
 	struct spsc_queue		job_queue;
 
@@ -93,6 +91,7 @@ struct drm_sched_entity {
  * struct drm_sched_rq - queue of entities to be scheduled.
  *
  * @lock: to modify the entities list.
+ * @sched: the scheduler to which this rq belongs to.
  * @entities: list of the entities to be scheduled.
  * @current_entity: the entity which is to be scheduled.
  *
@@ -102,6 +101,7 @@ struct drm_sched_entity {
  */
 struct drm_sched_rq {
 	spinlock_t			lock;
+	struct drm_gpu_scheduler	*sched;
 	struct list_head		entities;
 	struct drm_sched_entity		*current_entity;
 };
@@ -280,16 +280,13 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const char *name);
 void drm_sched_fini(struct drm_gpu_scheduler *sched);
 
-int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
-			  struct drm_sched_entity *entity,
-			  struct drm_sched_rq *rq,
+int drm_sched_entity_init(struct drm_sched_entity *entity,
+			  struct drm_sched_rq **rq_list,
+			  unsigned int num_rq_list,
 			  atomic_t *guilty);
-long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity, long timeout);
-void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
+long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout);
+void drm_sched_entity_fini(struct drm_sched_entity *entity);
+void drm_sched_entity_destroy(struct drm_sched_entity *entity);
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 			       struct drm_sched_entity *entity);
 void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
@@ -300,7 +297,6 @@ struct drm_sched_fence *drm_sched_fence_create(
 void drm_sched_fence_scheduled(struct drm_sched_fence *fence);
 void drm_sched_fence_finished(struct drm_sched_fence *fence);
 int drm_sched_job_init(struct drm_sched_job *job,
-		       struct drm_gpu_scheduler *sched,
 		       struct drm_sched_entity *entity,
 		       void *owner);
 void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched,
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index c9e5a6621b95..c44703f471b3 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -95,7 +95,9 @@ extern struct resource intel_graphics_stolen_res;
 #define    I845_TSEG_SIZE_512K	(2 << 1)
 #define    I845_TSEG_SIZE_1M	(3 << 1)
 
-#define INTEL_BSM 0x5c
+#define INTEL_BSM		0x5c
+#define INTEL_GEN11_BSM_DW0	0xc0
+#define INTEL_GEN11_BSM_DW1	0xc4
 #define   INTEL_BSM_MASK	(-(1u << 20))
 
 #endif				/* _I915_DRM_H_ */
diff --git a/include/drm/tinydrm/tinydrm.h b/include/drm/tinydrm/tinydrm.h
index 56e4a916b5e8..fe9827d0ca8a 100644
--- a/include/drm/tinydrm/tinydrm.h
+++ b/include/drm/tinydrm/tinydrm.h
@@ -16,16 +16,31 @@
 
 /**
  * struct tinydrm_device - tinydrm device
- * @drm: DRM device
- * @pipe: Display pipe structure
- * @dirty_lock: Serializes framebuffer flushing
- * @fb_funcs: Framebuffer functions used when creating framebuffers
  */
 struct tinydrm_device {
+	/**
+	 * @drm: DRM device
+	 */
 	struct drm_device *drm;
+
+	/**
+	 * @pipe: Display pipe structure
+	 */
 	struct drm_simple_display_pipe pipe;
+
+	/**
+	 * @dirty_lock: Serializes framebuffer flushing
+	 */
 	struct mutex dirty_lock;
+
+	/**
+	 * @fb_funcs: Framebuffer functions used when creating framebuffers
+	 */
 	const struct drm_framebuffer_funcs *fb_funcs;
+
+	/**
+	 * @fb_dirty: Framebuffer dirty callback
+	 */
 	int (*fb_dirty)(struct drm_framebuffer *framebuffer,
 			struct drm_file *file_priv, unsigned flags,
 			unsigned color, struct drm_clip_rect *clips,
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index c67977aa1a0e..a01ba2032f0e 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -284,17 +284,29 @@ struct ttm_operation_ctx {
 #define TTM_OPT_FLAG_FORCE_ALLOC		0x2
 
 /**
+ * ttm_bo_get - reference a struct ttm_buffer_object
+ *
+ * @bo: The buffer object.
+ */
+static inline void ttm_bo_get(struct ttm_buffer_object *bo)
+{
+	kref_get(&bo->kref);
+}
+
+/**
  * ttm_bo_reference - reference a struct ttm_buffer_object
  *
  * @bo: The buffer object.
  *
  * Returns a refcounted pointer to a buffer object.
+ *
+ * This function is deprecated. Use @ttm_bo_get instead.
  */
 
 static inline struct ttm_buffer_object *
 ttm_bo_reference(struct ttm_buffer_object *bo)
 {
-	kref_get(&bo->kref);
+	ttm_bo_get(bo);
 	return bo;
 }
 
@@ -346,11 +358,22 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 		    struct ttm_operation_ctx *ctx);
 
 /**
+ * ttm_bo_put
+ *
+ * @bo: The buffer object.
+ *
+ * Unreference a buffer object.
+ */
+void ttm_bo_put(struct ttm_buffer_object *bo);
+
+/**
  * ttm_bo_unref
  *
  * @bo: The buffer object.
  *
  * Unreference and clear a pointer to a buffer object.
+ *
+ * This function is deprecated. Use @ttm_bo_put instead.
  */
 void ttm_bo_unref(struct ttm_buffer_object **bo);
 
diff --git a/include/dt-bindings/clock/imx6ul-clock.h b/include/dt-bindings/clock/imx6ul-clock.h
index 9564597cbfac..0aa1d9c3e0b9 100644
--- a/include/dt-bindings/clock/imx6ul-clock.h
+++ b/include/dt-bindings/clock/imx6ul-clock.h
@@ -235,27 +235,25 @@
 #define IMX6UL_CLK_CSI_PODF		222
 #define IMX6UL_CLK_PLL3_120M		223
 #define IMX6UL_CLK_KPP			224
-#define IMX6UL_CLK_CKO1_SEL		225
-#define IMX6UL_CLK_CKO1_PODF		226
-#define IMX6UL_CLK_CKO1			227
-#define IMX6UL_CLK_CKO2_SEL		228
-#define IMX6UL_CLK_CKO2_PODF		229
-#define IMX6UL_CLK_CKO2			230
-#define IMX6UL_CLK_CKO			231
-
-/* For i.MX6ULL */
-#define IMX6ULL_CLK_ESAI_PRED		232
-#define IMX6ULL_CLK_ESAI_PODF		233
-#define IMX6ULL_CLK_ESAI_EXTAL		234
-#define IMX6ULL_CLK_ESAI_MEM		235
-#define IMX6ULL_CLK_ESAI_IPG		236
-#define IMX6ULL_CLK_DCP_CLK		237
-#define IMX6ULL_CLK_EPDC_PRE_SEL	238
-#define IMX6ULL_CLK_EPDC_SEL		239
-#define IMX6ULL_CLK_EPDC_PODF		240
-#define IMX6ULL_CLK_EPDC_ACLK		241
-#define IMX6ULL_CLK_EPDC_PIX		242
-#define IMX6ULL_CLK_ESAI_SEL		243
+#define IMX6ULL_CLK_ESAI_PRED		225
+#define IMX6ULL_CLK_ESAI_PODF		226
+#define IMX6ULL_CLK_ESAI_EXTAL		227
+#define IMX6ULL_CLK_ESAI_MEM		228
+#define IMX6ULL_CLK_ESAI_IPG		229
+#define IMX6ULL_CLK_DCP_CLK		230
+#define IMX6ULL_CLK_EPDC_PRE_SEL	231
+#define IMX6ULL_CLK_EPDC_SEL		232
+#define IMX6ULL_CLK_EPDC_PODF		233
+#define IMX6ULL_CLK_EPDC_ACLK		234
+#define IMX6ULL_CLK_EPDC_PIX		235
+#define IMX6ULL_CLK_ESAI_SEL		236
+#define IMX6UL_CLK_CKO1_SEL		237
+#define IMX6UL_CLK_CKO1_PODF		238
+#define IMX6UL_CLK_CKO1			239
+#define IMX6UL_CLK_CKO2_SEL		240
+#define IMX6UL_CLK_CKO2_PODF		241
+#define IMX6UL_CLK_CKO2			242
+#define IMX6UL_CLK_CKO			243
 #define IMX6UL_CLK_END			244
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */
diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h
new file mode 100644
index 000000000000..4cc40201273e
--- /dev/null
+++ b/include/linux/ascii85.h
@@ -0,0 +1,38 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (c) 2008 Intel Corporation
+ * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _ASCII85_H_
+#define _ASCII85_H_
+
+#include <linux/kernel.h>
+
+#define ASCII85_BUFSZ 6
+
+static inline long
+ascii85_encode_len(long len)
+{
+	return DIV_ROUND_UP(len, 4);
+}
+
+static inline const char *
+ascii85_encode(u32 in, char *out)
+{
+	int i;
+
+	if (in == 0)
+		return "z";
+
+	out[5] = '\0';
+	for (i = 5; i--; ) {
+		out[i] = '!' + in % 85;
+		in /= 85;
+	}
+
+	return out;
+}
+
+#endif
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e3147eb74222..ca3f2c2edd85 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -287,6 +287,20 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
 
+/**
+ * blk_mq_mark_complete() - Set request state to complete
+ * @rq: request to set to complete state
+ *
+ * Returns true if request state was successfully set to complete. If
+ * successful, the caller is responsibile for seeing this request is ended, as
+ * blk_mq_complete_request will not work again.
+ */
+static inline bool blk_mq_mark_complete(struct request *rq)
+{
+	return cmpxchg(&rq->state, MQ_RQ_IN_FLIGHT, MQ_RQ_COMPLETE) ==
+			MQ_RQ_IN_FLIGHT;
+}
+
 /*
  * Driver command data is immediately after the request. So subtract request
  * size to get back to the original request, add request size to get the PDU.
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 975fb4cf1bb7..d50c2f0a655a 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -2,6 +2,7 @@
 #ifndef _BPF_CGROUP_H
 #define _BPF_CGROUP_H
 
+#include <linux/errno.h>
 #include <linux/jump_label.h>
 #include <uapi/linux/bpf.h>
 
@@ -188,12 +189,38 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 									      \
 	__ret;								      \
 })
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype, struct bpf_prog *prog);
+int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype);
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr);
 #else
 
+struct bpf_prog;
 struct cgroup_bpf {};
 static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
 
+static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+					 enum bpf_prog_type ptype,
+					 struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_detach(const union bpf_attr *attr,
+					 enum bpf_prog_type ptype)
+{
+	return -EINVAL;
+}
+
+static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
+					union bpf_attr __user *uattr)
+{
+	return -EINVAL;
+}
+
 #define cgroup_bpf_enabled (0)
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7df32a3200f7..8827e797ff97 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -696,6 +696,8 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map)
 struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key);
 struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key);
 int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type);
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+			struct bpf_prog *prog);
 #else
 static inline struct sock  *__sock_map_lookup_elem(struct bpf_map *map, u32 key)
 {
@@ -714,6 +716,12 @@ static inline int sock_map_prog(struct bpf_map *map,
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+				      struct bpf_prog *prog)
+{
+	return -EINVAL;
+}
 #endif
 
 #if defined(CONFIG_XDP_SOCKETS)
diff --git a/include/linux/bpf_lirc.h b/include/linux/bpf_lirc.h
index 5f8a4283092d..9d9ff755ec29 100644
--- a/include/linux/bpf_lirc.h
+++ b/include/linux/bpf_lirc.h
@@ -5,11 +5,12 @@
 #include <uapi/linux/bpf.h>
 
 #ifdef CONFIG_BPF_LIRC_MODE2
-int lirc_prog_attach(const union bpf_attr *attr);
+int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 int lirc_prog_detach(const union bpf_attr *attr);
 int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr);
 #else
-static inline int lirc_prog_attach(const union bpf_attr *attr)
+static inline int lirc_prog_attach(const union bpf_attr *attr,
+				   struct bpf_prog *prog)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
index 687b1760bb9f..f02cee0225d4 100644
--- a/include/linux/bpfilter.h
+++ b/include/linux/bpfilter.h
@@ -5,10 +5,10 @@
 #include <uapi/linux/bpfilter.h>
 
 struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char *optval,
+int bpfilter_ip_set_sockopt(struct sock *sk, int optname, char __user *optval,
 			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char *optval,
-			    int *optlen);
+int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
+			    int __user *optlen);
 extern int (*bpfilter_process_sockopt)(struct sock *sk, int optname,
 				       char __user *optval,
 				       unsigned int optlen, bool is_set);
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index fd282c7d3e5e..573f5a7d42d4 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -66,25 +66,40 @@
 #endif
 
 /*
+ * Feature detection for gnu_inline (gnu89 extern inline semantics). Either
+ * __GNUC_STDC_INLINE__ is defined (not using gnu89 extern inline semantics,
+ * and we opt in to the gnu89 semantics), or __GNUC_STDC_INLINE__ is not
+ * defined so the gnu89 semantics are the default.
+ */
+#ifdef __GNUC_STDC_INLINE__
+# define __gnu_inline	__attribute__((gnu_inline))
+#else
+# define __gnu_inline
+#endif
+
+/*
  * Force always-inline if the user requests it so via the .config,
  * or if gcc is too old.
  * GCC does not warn about unused static inline functions for
  * -Wunused-function.  This turns out to avoid the need for complex #ifdef
  * directives.  Suppress the warning in clang as well by using "unused"
  * function attribute, which is redundant but not harmful for gcc.
+ * Prefer gnu_inline, so that extern inline functions do not emit an
+ * externally visible function. This makes extern inline behave as per gnu89
+ * semantics rather than c99. This prevents multiple symbol definition errors
+ * of extern inline functions at link time.
+ * A lot of inline functions can cause havoc with function tracing.
  */
 #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) ||		\
     !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-#define inline inline		__attribute__((always_inline,unused)) notrace
-#define __inline__ __inline__	__attribute__((always_inline,unused)) notrace
-#define __inline __inline	__attribute__((always_inline,unused)) notrace
+#define inline \
+	inline __attribute__((always_inline, unused)) notrace __gnu_inline
 #else
-/* A lot of inline functions can cause havoc with function tracing */
-#define inline inline		__attribute__((unused)) notrace
-#define __inline__ __inline__	__attribute__((unused)) notrace
-#define __inline __inline	__attribute__((unused)) notrace
+#define inline inline		__attribute__((unused)) notrace __gnu_inline
 #endif
 
+#define __inline__ inline
+#define __inline inline
 #define __always_inline	inline __attribute__((always_inline))
 #define  noinline	__attribute__((noinline))
 
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index e6c0448ebcc7..31c865d1842e 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -124,7 +124,7 @@ static inline void delayacct_blkio_start(void)
 
 static inline void delayacct_blkio_end(struct task_struct *p)
 {
-	if (current->delays)
+	if (p->delays)
 		__delayacct_blkio_end(p);
 	delayacct_clear_flag(DELAYACCT_PF_BLKIO);
 }
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 7094718b653b..ffcc7724ca21 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -11,6 +11,7 @@
 
 #include <linux/fcntl.h>
 #include <linux/wait.h>
+#include <linux/err.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 20f2659dd829..c73dd7396886 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -470,9 +470,7 @@ struct sock_fprog_kern {
 };
 
 struct bpf_binary_header {
-	u16 pages;
-	u16 locked:1;
-
+	u32 pages;
 	/* Some arches need word alignment for their instructions */
 	u8 image[] __aligned(4);
 };
@@ -481,7 +479,7 @@ struct bpf_prog {
 	u16			pages;		/* Number of allocated pages */
 	u16			jited:1,	/* Is our filter JIT'ed? */
 				jit_requested:1,/* archs need to JIT the prog */
-				locked:1,	/* Program image locked? */
+				undo_set_mem:1,	/* Passed set_memory_ro() checkpoint */
 				gpl_compatible:1, /* Is filter GPL compatible? */
 				cb_access:1,	/* Is control block accessed? */
 				dst_needed:1,	/* Do we need dst entry? */
@@ -677,46 +675,24 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	fp->locked = 1;
-	if (set_memory_ro((unsigned long)fp, fp->pages))
-		fp->locked = 0;
-#endif
+	fp->undo_set_mem = 1;
+	set_memory_ro((unsigned long)fp, fp->pages);
 }
 
 static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	if (fp->locked) {
-		WARN_ON_ONCE(set_memory_rw((unsigned long)fp, fp->pages));
-		/* In case set_memory_rw() fails, we want to be the first
-		 * to crash here instead of some random place later on.
-		 */
-		fp->locked = 0;
-	}
-#endif
+	if (fp->undo_set_mem)
+		set_memory_rw((unsigned long)fp, fp->pages);
 }
 
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	hdr->locked = 1;
-	if (set_memory_ro((unsigned long)hdr, hdr->pages))
-		hdr->locked = 0;
-#endif
+	set_memory_ro((unsigned long)hdr, hdr->pages);
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
 {
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	if (hdr->locked) {
-		WARN_ON_ONCE(set_memory_rw((unsigned long)hdr, hdr->pages));
-		/* In case set_memory_rw() fails, we want to be the first
-		 * to crash here instead of some random place later on.
-		 */
-		hdr->locked = 0;
-	}
-#endif
+	set_memory_rw((unsigned long)hdr, hdr->pages);
 }
 
 static inline struct bpf_binary_header *
@@ -728,22 +704,6 @@ bpf_jit_binary_hdr(const struct bpf_prog *fp)
 	return (void *)addr;
 }
 
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-static inline int bpf_prog_check_pages_ro_single(const struct bpf_prog *fp)
-{
-	if (!fp->locked)
-		return -ENOLCK;
-	if (fp->jited) {
-		const struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp);
-
-		if (!hdr->locked)
-			return -ENOLCK;
-	}
-
-	return 0;
-}
-#endif
-
 int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
@@ -805,8 +765,8 @@ static inline bool bpf_dump_raw_ok(void)
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 
-static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
-					   struct net_device *fwd)
+static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
+				 unsigned int pktlen)
 {
 	unsigned int len;
 
@@ -814,7 +774,7 @@ static inline int __xdp_generic_ok_fwd_dev(struct sk_buff *skb,
 		return -ENETDOWN;
 
 	len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN;
-	if (skb->len > len)
+	if (pktlen > len)
 		return -EMSGSIZE;
 
 	return 0;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d78d146a98da..805bf22898cf 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2420,6 +2420,7 @@ extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
+extern struct file *filp_clone_open(struct file *);
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);
diff --git a/include/linux/fsl/guts.h b/include/linux/fsl/guts.h
index 3efa3b861d44..941b11811f85 100644
--- a/include/linux/fsl/guts.h
+++ b/include/linux/fsl/guts.h
@@ -16,6 +16,7 @@
 #define __FSL_GUTS_H__
 
 #include <linux/types.h>
+#include <linux/io.h>
 
 /**
  * Global Utility Registers.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8154f4920fcb..ebb77674be90 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -223,7 +223,6 @@ extern enum ftrace_tracing_type_t ftrace_tracing_type;
  */
 int register_ftrace_function(struct ftrace_ops *ops);
 int unregister_ftrace_function(struct ftrace_ops *ops);
-void clear_ftrace_function(void);
 
 extern void ftrace_stub(unsigned long a0, unsigned long a1,
 			struct ftrace_ops *op, struct pt_regs *regs);
@@ -239,7 +238,6 @@ static inline int ftrace_nr_registered_ops(void)
 {
 	return 0;
 }
-static inline void clear_ftrace_function(void) { }
 static inline void ftrace_kill(void) { }
 static inline void ftrace_free_init_mem(void) { }
 static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { }
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 41a3d5775394..773bcb1d4044 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -511,6 +511,7 @@ struct hid_output_fifo {
 #define HID_STAT_ADDED		BIT(0)
 #define HID_STAT_PARSED		BIT(1)
 #define HID_STAT_DUP_DETECTED	BIT(2)
+#define HID_STAT_REPROBED	BIT(3)
 
 struct hid_input {
 	struct list_head list;
@@ -579,7 +580,7 @@ struct hid_device {							/* device report descriptor */
 	bool battery_avoid_query;
 #endif
 
-	unsigned int status;						/* see STAT flags above */
+	unsigned long status;						/* see STAT flags above */
 	unsigned claimed;						/* Claimed by hidinput, hiddev? */
 	unsigned quirks;						/* Various quirks the device can pull on us */
 	bool io_started;						/* If IO has started */
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 7843b98e1c6e..c20c7e197d07 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -105,13 +105,13 @@ static inline bool br_vlan_enabled(const struct net_device *dev)
 
 static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid)
 {
-	return -1;
+	return -EINVAL;
 }
 
 static inline int br_vlan_get_info(const struct net_device *dev, u16 vid,
 				   struct bridge_vlan_info *p_vinfo)
 {
-	return -1;
+	return -EINVAL;
 }
 #endif
 
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index f8231854b5d6..119f53941c12 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -109,6 +109,8 @@ struct ip_mc_list {
 extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto);
 extern int igmp_rcv(struct sk_buff *);
 extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr);
+extern int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+				unsigned int mode);
 extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr);
 extern void ip_mc_drop_socket(struct sock *sk);
 extern int ip_mc_source(int add, int omode, struct sock *sk,
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 1df940196ab2..ef169d67df92 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -121,6 +121,7 @@
 #define ecap_srs(e)		((e >> 31) & 0x1)
 #define ecap_ers(e)		((e >> 30) & 0x1)
 #define ecap_prs(e)		((e >> 29) & 0x1)
+#define ecap_broken_pasid(e)	((e >> 28) & 0x1)
 #define ecap_dis(e)		((e >> 27) & 0x1)
 #define ecap_nest(e)		((e >> 26) & 0x1)
 #define ecap_mts(e)		((e >> 25) & 0x1)
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 2803264c512f..c1961761311d 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -62,7 +62,6 @@ void *kthread_probe_data(struct task_struct *k);
 int kthread_park(struct task_struct *k);
 void kthread_unpark(struct task_struct *k);
 void kthread_parkme(void);
-void kthread_park_complete(struct task_struct *k);
 
 int kthreadd(void *unused);
 extern struct task_struct *kthreadd_task;
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 8b8946dd63b9..32f247cb5e9e 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -210,6 +210,7 @@ enum {
 	ATA_FLAG_SLAVE_POSS	= (1 << 0), /* host supports slave dev */
 					    /* (doesn't imply presence) */
 	ATA_FLAG_SATA		= (1 << 1),
+	ATA_FLAG_NO_LPM		= (1 << 2), /* host not happy with LPM */
 	ATA_FLAG_NO_LOG_PAGE	= (1 << 5), /* do not issue log page read */
 	ATA_FLAG_NO_ATAPI	= (1 << 6), /* No ATAPI support */
 	ATA_FLAG_PIO_DMA	= (1 << 7), /* PIO cmds via DMA */
@@ -1495,6 +1496,29 @@ static inline bool ata_tag_valid(unsigned int tag)
 	return tag < ATA_MAX_QUEUE || ata_tag_internal(tag);
 }
 
+#define __ata_qc_for_each(ap, qc, tag, max_tag, fn)		\
+	for ((tag) = 0; (tag) < (max_tag) &&			\
+	     ({ qc = fn((ap), (tag)); 1; }); (tag)++)		\
+
+/*
+ * Internal use only, iterate commands ignoring error handling and
+ * status of 'qc'.
+ */
+#define ata_qc_for_each_raw(ap, qc, tag)					\
+	__ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, __ata_qc_from_tag)
+
+/*
+ * Iterate all potential commands that can be queued
+ */
+#define ata_qc_for_each(ap, qc, tag)					\
+	__ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE, ata_qc_from_tag)
+
+/*
+ * Like ata_qc_for_each, but with the internal tag included
+ */
+#define ata_qc_for_each_with_internal(ap, qc, tag)			\
+	__ata_qc_for_each(ap, qc, tag, ATA_MAX_QUEUE + 1, ata_qc_from_tag)
+
 /*
  * device helpers
  */
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 4f5f8c21e283..1eb6f244588d 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -27,6 +27,8 @@
  */
 #define MARVELL_PHY_ID_88E6390		0x01410f90
 
+#define MARVELL_PHY_FAMILY_ID(id)	((id) >> 4)
+
 /* struct phy_device dev_flags definitions */
 #define MARVELL_PHY_M1145_FLAGS_RESISTANCE	0x00000001
 #define MARVELL_PHY_M1118_DNS323_LEDS		0x00000002
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 80cbb7fdce4a..83957920653a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -358,6 +358,7 @@ struct mlx5_frag_buf_ctrl {
 	struct mlx5_frag_buf	frag_buf;
 	u32			sz_m1;
 	u32			frag_sz_m1;
+	u32			strides_offset;
 	u8			log_sz;
 	u8			log_stride;
 	u8			log_frag_strides;
@@ -983,14 +984,22 @@ static inline u32 mlx5_base_mkey(const u32 key)
 	return key & 0xffffff00u;
 }
 
-static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
-				 struct mlx5_frag_buf_ctrl *fbc)
+static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz,
+					u32 strides_offset,
+					struct mlx5_frag_buf_ctrl *fbc)
 {
 	fbc->log_stride = log_stride;
 	fbc->log_sz     = log_sz;
 	fbc->sz_m1	= (1 << fbc->log_sz) - 1;
 	fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
 	fbc->frag_sz_m1	= (1 << fbc->log_frag_strides) - 1;
+	fbc->strides_offset = strides_offset;
+}
+
+static inline void mlx5_fill_fbc(u8 log_stride, u8 log_sz,
+				 struct mlx5_frag_buf_ctrl *fbc)
+{
+	mlx5_fill_fbc_offset(log_stride, log_sz, 0, fbc);
 }
 
 static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
@@ -1004,7 +1013,10 @@ static inline void mlx5_core_init_cq_frag_buf(struct mlx5_frag_buf_ctrl *fbc,
 static inline void *mlx5_frag_buf_get_wqe(struct mlx5_frag_buf_ctrl *fbc,
 					  u32 ix)
 {
-	unsigned int frag = (ix >> fbc->log_frag_strides);
+	unsigned int frag;
+
+	ix  += fbc->strides_offset;
+	frag = ix >> fbc->log_frag_strides;
 
 	return fbc->frag_buf.frags[frag].buf +
 		((fbc->frag_sz_m1 & ix) << fbc->log_stride);
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index d3c9db492b30..fab5121ffb8f 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -8,6 +8,8 @@
 
 #include <linux/mlx5/driver.h>
 
+#define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
+
 enum {
 	SRIOV_NONE,
 	SRIOV_LEGACY,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 27134c4fcb76..ac281f5ec9b8 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -922,7 +922,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         vnic_env_queue_counters[0x1];
 	u8         ets[0x1];
 	u8         nic_flow_table[0x1];
-	u8         eswitch_flow_table[0x1];
+	u8         eswitch_manager[0x1];
 	u8         device_memory[0x1];
 	u8         mcam_reg[0x1];
 	u8         pcam_reg[0x1];
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a0fbb9ffe380..7ba6d356d18f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -155,7 +155,9 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
  * mmap() functions).
  */
 
-extern struct kmem_cache *vm_area_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *);
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
+void vm_area_free(struct vm_area_struct *);
 
 #ifndef CONFIG_MMU
 extern struct rb_root nommu_region_tree;
@@ -450,6 +452,20 @@ struct vm_operations_struct {
 					  unsigned long addr);
 };
 
+static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
+{
+	static const struct vm_operations_struct dummy_vm_ops = {};
+
+	vma->vm_mm = mm;
+	vma->vm_ops = &dummy_vm_ops;
+	INIT_LIST_HEAD(&vma->anon_vma_chain);
+}
+
+static inline void vma_set_anonymous(struct vm_area_struct *vma)
+{
+	vma->vm_ops = NULL;
+}
+
 struct mmu_gather;
 struct inode;
 
@@ -2132,7 +2148,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn,
 					struct mminit_pfnnid_cache *state);
 #endif
 
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
 void zero_resv_unavail(void);
 #else
 static inline void zero_resv_unavail(void) {}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec9850c7936..3d0cc0b5cec2 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2789,11 +2789,31 @@ static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp,
 	if (PTR_ERR(pp) != -EINPROGRESS)
 		NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS) {
+		NAPI_GRO_CB(skb)->flush |= flush;
+		skb_gro_remcsum_cleanup(skb, grc);
+		skb->remcsum_offload = 0;
+	}
+}
 #else
 static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
 {
 	NAPI_GRO_CB(skb)->flush |= flush;
 }
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff **pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, grc);
+	skb->remcsum_offload = 0;
+}
 #endif
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..e04ab6265566 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -261,6 +261,9 @@ enum pci_bus_speed {
 	PCI_SPEED_UNKNOWN		= 0xff,
 };
 
+enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
+enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
+
 struct pci_cap_saved_data {
 	u16		cap_nr;
 	bool		cap_extended;
@@ -1240,6 +1243,8 @@ int pci_register_io_range(struct fwnode_handle *fwnode, phys_addr_t addr,
 unsigned long pci_address_to_pio(phys_addr_t addr);
 phys_addr_t pci_pio_to_address(unsigned long pio);
 int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr);
+int devm_pci_remap_iospace(struct device *dev, const struct resource *res,
+			   phys_addr_t phys_addr);
 void pci_unmap_iospace(struct resource *res);
 void __iomem *devm_pci_remap_cfgspace(struct device *dev,
 				      resource_size_t offset,
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index b72ebdff0b77..003d09ab308d 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -165,6 +165,7 @@ void ring_buffer_record_enable(struct ring_buffer *buffer);
 void ring_buffer_record_off(struct ring_buffer *buffer);
 void ring_buffer_record_on(struct ring_buffer *buffer);
 int ring_buffer_record_is_on(struct ring_buffer *buffer);
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer);
 void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9256118bd40c..43731fe51c97 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -118,7 +118,7 @@ struct task_group;
  * the comment with set_special_state().
  */
 #define is_special_task_state(state)				\
-	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_PARKED | TASK_DEAD))
 
 #define __set_current_state(state_value)			\
 	do {							\
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 5be31eb7b266..108ede99e533 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -75,7 +75,7 @@ extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *,
 extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *);
 struct task_struct *fork_idle(int);
 extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-extern long kernel_wait4(pid_t, int *, int, struct rusage *);
+extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
 
 extern void free_task(struct task_struct *tsk);
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 164cdedf6012..610a201126ee 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
+ *	@pfmemalloc: skbuff was allocated from PFMEMALLOC reserves
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -735,7 +736,7 @@ struct sk_buff {
 				peeked:1,
 				head_frag:1,
 				xmit_more:1,
-				__unused:1; /* one bit hole */
+				pfmemalloc:1;
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
@@ -754,31 +755,30 @@ struct sk_buff {
 
 	__u8			__pkt_type_offset[0];
 	__u8			pkt_type:3;
-	__u8			pfmemalloc:1;
 	__u8			ignore_df:1;
-
 	__u8			nf_trace:1;
 	__u8			ip_summed:2;
 	__u8			ooo_okay:1;
+
 	__u8			l4_hash:1;
 	__u8			sw_hash:1;
 	__u8			wifi_acked_valid:1;
 	__u8			wifi_acked:1;
-
 	__u8			no_fcs:1;
 	/* Indicates the inner headers are valid in the skbuff. */
 	__u8			encapsulation:1;
 	__u8			encap_hdr_csum:1;
 	__u8			csum_valid:1;
+
 	__u8			csum_complete_sw:1;
 	__u8			csum_level:2;
 	__u8			csum_not_inet:1;
-
 	__u8			dst_pending_confirm:1;
 #ifdef CONFIG_IPV6_NDISC_NODETYPE
 	__u8			ndisc_nodetype:2;
 #endif
 	__u8			ipvs_property:1;
+
 	__u8			inner_protocol_type:1;
 	__u8			remcsum_offload:1;
 #ifdef CONFIG_NET_SWITCHDEV
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a368a68cb667..5c1a0933768e 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -11,6 +11,7 @@
 #ifndef _LINUX_SYSCALLS_H
 #define _LINUX_SYSCALLS_H
 
+struct __aio_sigset;
 struct epoll_event;
 struct iattr;
 struct inode;
diff --git a/include/linux/uio_driver.h b/include/linux/uio_driver.h
index 6c5f2074e14f..6f8b68cd460f 100644
--- a/include/linux/uio_driver.h
+++ b/include/linux/uio_driver.h
@@ -75,7 +75,7 @@ struct uio_device {
         struct fasync_struct    *async_queue;
         wait_queue_head_t       wait;
         struct uio_info         *info;
-	spinlock_t		info_lock;
+	struct mutex		info_lock;
         struct kobject          *map_dir;
         struct kobject          *portio_dir;
 };
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5fbfe61f41c6..1beb3ead0385 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -5835,10 +5835,11 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 /**
  * cfg80211_rx_control_port - notification about a received control port frame
  * @dev: The device the frame matched to
- * @buf: control port frame
- * @len: length of the frame data
- * @addr: The peer from which the frame was received
- * @proto: frame protocol, typically PAE or Pre-authentication
+ * @skb: The skbuf with the control port frame.  It is assumed that the skbuf
+ *	is 802.3 formatted (with 802.3 header).  The skb can be non-linear.
+ *	This function does not take ownership of the skb, so the caller is
+ *	responsible for any cleanup.  The caller must also ensure that
+ *	skb->protocol is set appropriately.
  * @unencrypted: Whether the frame was received unencrypted
  *
  * This function is used to inform userspace about a received control port
@@ -5851,8 +5852,7 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
  * Return: %true if the frame was passed to userspace
  */
 bool cfg80211_rx_control_port(struct net_device *dev,
-			      const u8 *buf, size_t len,
-			      const u8 *addr, u16 proto, bool unencrypted);
+			      struct sk_buff *skb, bool unencrypted);
 
 /**
  * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 71b9043aa0e7..3d4930528db0 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -281,6 +281,11 @@ static inline void fib6_info_hold(struct fib6_info *f6i)
 	atomic_inc(&f6i->fib6_ref);
 }
 
+static inline bool fib6_info_hold_safe(struct fib6_info *f6i)
+{
+	return atomic_inc_not_zero(&f6i->fib6_ref);
+}
+
 static inline void fib6_info_release(struct fib6_info *f6i)
 {
 	if (f6i && atomic_dec_and_test(&f6i->fib6_ref))
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 59656fc580df..7b9c82de11cc 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -66,6 +66,12 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
 		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
 }
 
+static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i)
+{
+	return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
+	       RTF_GATEWAY;
+}
+
 void ip6_route_input(struct sk_buff *skb);
 struct dst_entry *ip6_route_input_lookup(struct net *net,
 					 struct net_device *dev,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 16475c269749..8f73be494503 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -355,14 +355,7 @@ struct ipv6_txoptions *ipv6_dup_options(struct sock *sk,
 struct ipv6_txoptions *ipv6_renew_options(struct sock *sk,
 					  struct ipv6_txoptions *opt,
 					  int newtype,
-					  struct ipv6_opt_hdr __user *newopt,
-					  int newoptlen);
-struct ipv6_txoptions *
-ipv6_renew_options_kern(struct sock *sk,
-			struct ipv6_txoptions *opt,
-			int newtype,
-			struct ipv6_opt_hdr *newopt,
-			int newoptlen);
+					  struct ipv6_opt_hdr *newopt);
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
 					  struct ipv6_txoptions *opt);
 
@@ -830,7 +823,7 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 	 * to minimize possbility that any useful information to an
 	 * attacker is leaked. Only lower 20 bits are relevant.
 	 */
-	rol32(hash, 16);
+	hash = rol32(hash, 16);
 
 	flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 
@@ -1107,6 +1100,8 @@ void ipv6_sysctl_unregister(void);
 
 int ipv6_sock_mc_join(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+			  const struct in6_addr *addr, unsigned int mode);
 int ipv6_sock_mc_drop(struct sock *sk, int ifindex,
 		      const struct in6_addr *addr);
 #endif /* _NET_IPV6_H */
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 47e35cce3b64..a71264d75d7f 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -128,6 +128,7 @@ struct net {
 #endif
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 	struct netns_nf_frag	nf_frag;
+	struct ctl_table_header *nf_frag_frags_hdr;
 #endif
 	struct sock		*nfnl;
 	struct sock		*nfnl_stash;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 08c005ce56e9..dc417ef0a0c5 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -150,6 +150,7 @@ static inline void nft_data_debug(const struct nft_data *data)
  *	@portid: netlink portID of the original message
  *	@seq: netlink sequence number
  *	@family: protocol family
+ *	@level: depth of the chains
  *	@report: notify via unicast netlink message
  */
 struct nft_ctx {
@@ -160,6 +161,7 @@ struct nft_ctx {
 	u32				portid;
 	u32				seq;
 	u8				family;
+	u8				level;
 	bool				report;
 };
 
@@ -865,7 +867,6 @@ enum nft_chain_flags {
  *	@table: table that this chain belongs to
  *	@handle: chain handle
  *	@use: number of jump references to this chain
- *	@level: length of longest path to this chain
  *	@flags: bitmask of enum nft_chain_flags
  *	@name: name of the chain
  */
@@ -878,7 +879,6 @@ struct nft_chain {
 	struct nft_table		*table;
 	u64				handle;
 	u32				use;
-	u16				level;
 	u8				flags:6,
 					genmask:2;
 	char				*name;
@@ -1124,7 +1124,6 @@ struct nft_flowtable {
 	u32				genmask:2,
 					use:30;
 	u64				handle;
-	char				*dev_name[NFT_FLOWTABLE_DEVICE_MAX];
 	/* runtime data below here */
 	struct nf_hook_ops		*ops ____cacheline_aligned;
 	struct nf_flowtable		data;
diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index e0c0c2558ec4..a05134507e7b 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -65,4 +65,10 @@ extern const struct nft_expr_ops nft_payload_fast_ops;
 extern struct static_key_false nft_counters_enabled;
 extern struct static_key_false nft_trace_enabled;
 
+extern struct nft_set_type nft_set_rhash_type;
+extern struct nft_set_type nft_set_hash_type;
+extern struct nft_set_type nft_set_hash_fast_type;
+extern struct nft_set_type nft_set_rbtree_type;
+extern struct nft_set_type nft_set_bitmap_type;
+
 #endif /* _NET_NF_TABLES_CORE_H */
diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h
index 9754a50ecde9..4cc64c8446eb 100644
--- a/include/net/netfilter/nf_tproxy.h
+++ b/include/net/netfilter/nf_tproxy.h
@@ -64,7 +64,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
  * belonging to established connections going through that one.
  */
 struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 		      const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
@@ -103,7 +103,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 			    struct sock *sk);
 
 struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff,
 		      const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
 		      const __be16 sport, const __be16 dport,
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index c978a31b0f84..762ac9931b62 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -109,7 +109,6 @@ struct netns_ipv6 {
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 struct netns_nf_frag {
-	struct netns_sysctl_ipv6 sysctl;
 	struct netns_frags	frags;
 };
 #endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a3c1a2c47cd4..20b059574e60 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -111,6 +111,11 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 {
 }
 
+static inline bool tcf_block_shared(struct tcf_block *block)
+{
+	return false;
+}
+
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	return NULL;
diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h
index 9470fd7e4350..32d2454c0479 100644
--- a/include/net/tc_act/tc_csum.h
+++ b/include/net/tc_act/tc_csum.h
@@ -7,7 +7,6 @@
 #include <linux/tc_act/tc_csum.h>
 
 struct tcf_csum_params {
-	int action;
 	u32 update_flags;
 	struct rcu_head rcu;
 };
diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h
index efef0b4b1b2b..46b8c7f1c8d5 100644
--- a/include/net/tc_act/tc_tunnel_key.h
+++ b/include/net/tc_act/tc_tunnel_key.h
@@ -18,7 +18,6 @@
 struct tcf_tunnel_key_params {
 	struct rcu_head		rcu;
 	int			tcft_action;
-	int			action;
 	struct metadata_dst     *tcft_enc_metadata;
 };
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 800582b5dd54..cd3ecda9386a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -342,6 +342,7 @@ ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
 			struct pipe_inode_info *pipe, size_t len,
 			unsigned int flags);
 
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks);
 static inline void tcp_dec_quickack_mode(struct sock *sk,
 					 const unsigned int pkts)
 {
@@ -539,6 +540,7 @@ void tcp_send_fin(struct sock *sk);
 void tcp_send_active_reset(struct sock *sk, gfp_t priority);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
@@ -828,6 +830,10 @@ struct tcp_skb_cb {
 
 #define TCP_SKB_CB(__skb)	((struct tcp_skb_cb *)&((__skb)->cb[0]))
 
+static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb)
+{
+	TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb);
+}
 
 #if IS_ENABLED(CONFIG_IPV6)
 /* This is the variant of inet6_iif() that must be used by TCP,
@@ -835,6 +841,11 @@ struct tcp_skb_cb {
  */
 static inline int tcp_v6_iif(const struct sk_buff *skb)
 {
+	return TCP_SKB_CB(skb)->header.h6.iif;
+}
+
+static inline int tcp_v6_iif_l3_slave(const struct sk_buff *skb)
+{
 	bool l3_slave = ipv6_l3mdev_skb(TCP_SKB_CB(skb)->header.h6.flags);
 
 	return l3_slave ? skb->skb_iif : TCP_SKB_CB(skb)->header.h6.iif;
@@ -908,8 +919,6 @@ enum tcp_ca_event {
 	CA_EVENT_LOSS,		/* loss timeout */
 	CA_EVENT_ECN_NO_CE,	/* ECT set, but not CE marked */
 	CA_EVENT_ECN_IS_CE,	/* received CE marked IP packet */
-	CA_EVENT_DELAYED_ACK,	/* Delayed ack is sent */
-	CA_EVENT_NON_DELAYED_ACK,
 };
 
 /* Information about inbound ACK, passed to cong_ops->in_ack_event() */
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 9fe472f2ac95..7161856bcf9c 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -60,6 +60,10 @@ struct xdp_sock {
 	bool zc;
 	/* Protects multiple processes in the control path */
 	struct mutex mutex;
+	/* Mutual exclusion of NAPI TX thread and sendmsg error paths
+	 * in the SKB destructor callback.
+	 */
+	spinlock_t tx_completion_lock;
 	u64 rx_dropped;
 };
 
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 784b0fe470ee..1ceec56de015 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -516,6 +516,7 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
+#define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index d5e52350a3aa..721ab7e54d96 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -183,6 +183,7 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_QCOM    0x05
 #define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
+#define DRM_FORMAT_MOD_VENDOR_ARM     0x08
 /* add more to the end as needed */
 
 #define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
@@ -298,6 +299,19 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE	fourcc_mod_code(SAMSUNG, 1)
 
+/*
+ * Qualcomm Compressed Format
+ *
+ * Refers to a compressed variant of the base format that is compressed.
+ * Implementation may be platform and base-format specific.
+ *
+ * Each macrotile consists of m x n (mostly 4 x 4) tiles.
+ * Pixel data pitch/stride is aligned with macrotile width.
+ * Pixel data height is aligned with macrotile height.
+ * Entire pixel data buffer is aligned with 4k(bytes).
+ */
+#define DRM_FORMAT_MOD_QCOM_COMPRESSED	fourcc_mod_code(QCOM, 1)
+
 /* Vivante framebuffer modifiers */
 
 /*
@@ -485,6 +499,88 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6)
 
+/*
+ * Arm Framebuffer Compression (AFBC) modifiers
+ *
+ * AFBC is a proprietary lossless image compression protocol and format.
+ * It provides fine-grained random access and minimizes the amount of data
+ * transferred between IP blocks.
+ *
+ * AFBC has several features which may be supported and/or used, which are
+ * represented using bits in the modifier. Not all combinations are valid,
+ * and different devices or use-cases may support different combinations.
+ */
+#define DRM_FORMAT_MOD_ARM_AFBC(__afbc_mode)	fourcc_mod_code(ARM, __afbc_mode)
+
+/*
+ * AFBC superblock size
+ *
+ * Indicates the superblock size(s) used for the AFBC buffer. The buffer
+ * size (in pixels) must be aligned to a multiple of the superblock size.
+ * Four lowest significant bits(LSBs) are reserved for block size.
+ */
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_MASK      0xf
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_16x16     (1ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8      (2ULL)
+
+/*
+ * AFBC lossless colorspace transform
+ *
+ * Indicates that the buffer makes use of the AFBC lossless colorspace
+ * transform.
+ */
+#define AFBC_FORMAT_MOD_YTR     (1ULL <<  4)
+
+/*
+ * AFBC block-split
+ *
+ * Indicates that the payload of each superblock is split. The second
+ * half of the payload is positioned at a predefined offset from the start
+ * of the superblock payload.
+ */
+#define AFBC_FORMAT_MOD_SPLIT   (1ULL <<  5)
+
+/*
+ * AFBC sparse layout
+ *
+ * This flag indicates that the payload of each superblock must be stored at a
+ * predefined position relative to the other superblocks in the same AFBC
+ * buffer. This order is the same order used by the header buffer. In this mode
+ * each superblock is given the same amount of space as an uncompressed
+ * superblock of the particular format would require, rounding up to the next
+ * multiple of 128 bytes in size.
+ */
+#define AFBC_FORMAT_MOD_SPARSE  (1ULL <<  6)
+
+/*
+ * AFBC copy-block restrict
+ *
+ * Buffers with this flag must obey the copy-block restriction. The restriction
+ * is such that there are no copy-blocks referring across the border of 8x8
+ * blocks. For the subsampled data the 8x8 limitation is also subsampled.
+ */
+#define AFBC_FORMAT_MOD_CBR     (1ULL <<  7)
+
+/*
+ * AFBC tiled layout
+ *
+ * The tiled layout groups superblocks in 8x8 or 4x4 tiles, where all
+ * superblocks inside a tile are stored together in memory. 8x8 tiles are used
+ * for pixel formats up to and including 32 bpp while 4x4 tiles are used for
+ * larger bpp formats. The order between the tiles is scan line.
+ * When the tiled layout is used, the buffer size (in pixels) must be aligned
+ * to the tile size.
+ */
+#define AFBC_FORMAT_MOD_TILED   (1ULL <<  8)
+
+/*
+ * AFBC solid color blocks
+ *
+ * Indicates that the buffer makes use of solid-color blocks, whereby bandwidth
+ * can be reduced if a whole superblock is a single color.
+ */
+#define AFBC_FORMAT_MOD_SC      (1ULL <<  9)
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 0bc784f5e0db..399f58317cff 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -40,6 +40,7 @@ extern "C" {
 
 #define DRM_VMW_GET_PARAM            0
 #define DRM_VMW_ALLOC_DMABUF         1
+#define DRM_VMW_ALLOC_BO             1
 #define DRM_VMW_UNREF_DMABUF         2
 #define DRM_VMW_HANDLE_CLOSE         2
 #define DRM_VMW_CURSOR_BYPASS        3
@@ -68,6 +69,8 @@ extern "C" {
 #define DRM_VMW_GB_SURFACE_REF       24
 #define DRM_VMW_SYNCCPU              25
 #define DRM_VMW_CREATE_EXTENDED_CONTEXT 26
+#define DRM_VMW_GB_SURFACE_CREATE_EXT   27
+#define DRM_VMW_GB_SURFACE_REF_EXT      28
 
 /*************************************************************************/
 /**
@@ -79,6 +82,9 @@ extern "C" {
  *
  * DRM_VMW_PARAM_OVERLAY_IOCTL:
  * Does the driver support the overlay ioctl.
+ *
+ * DRM_VMW_PARAM_SM4_1
+ * SM4_1 support is enabled.
  */
 
 #define DRM_VMW_PARAM_NUM_STREAMS      0
@@ -94,6 +100,8 @@ extern "C" {
 #define DRM_VMW_PARAM_MAX_MOB_SIZE     10
 #define DRM_VMW_PARAM_SCREEN_TARGET    11
 #define DRM_VMW_PARAM_DX               12
+#define DRM_VMW_PARAM_HW_CAPS2         13
+#define DRM_VMW_PARAM_SM4_1            14
 
 /**
  * enum drm_vmw_handle_type - handle type for ref ioctls
@@ -356,9 +364,9 @@ struct drm_vmw_fence_rep {
 
 /*************************************************************************/
 /**
- * DRM_VMW_ALLOC_DMABUF
+ * DRM_VMW_ALLOC_BO
  *
- * Allocate a DMA buffer that is visible also to the host.
+ * Allocate a buffer object that is visible also to the host.
  * NOTE: The buffer is
  * identified by a handle and an offset, which are private to the guest, but
  * useable in the command stream. The guest kernel may translate these
@@ -366,27 +374,28 @@ struct drm_vmw_fence_rep {
  * be zero at all times, or it may disappear from the interface before it is
  * fixed.
  *
- * The DMA buffer may stay user-space mapped in the guest at all times,
+ * The buffer object may stay user-space mapped in the guest at all times,
  * and is thus suitable for sub-allocation.
  *
- * DMA buffers are mapped using the mmap() syscall on the drm device.
+ * Buffer objects are mapped using the mmap() syscall on the drm device.
  */
 
 /**
- * struct drm_vmw_alloc_dmabuf_req
+ * struct drm_vmw_alloc_bo_req
  *
  * @size: Required minimum size of the buffer.
  *
- * Input data to the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Input data to the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-struct drm_vmw_alloc_dmabuf_req {
+struct drm_vmw_alloc_bo_req {
 	__u32 size;
 	__u32 pad64;
 };
+#define drm_vmw_alloc_dmabuf_req drm_vmw_alloc_bo_req
 
 /**
- * struct drm_vmw_dmabuf_rep
+ * struct drm_vmw_bo_rep
  *
  * @map_handle: Offset to use in the mmap() call used to map the buffer.
  * @handle: Handle unique to this buffer. Used for unreferencing.
@@ -395,50 +404,32 @@ struct drm_vmw_alloc_dmabuf_req {
  * @cur_gmr_offset: Offset to use in the command stream when this buffer is
  * referenced. See note above.
  *
- * Output data from the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Output data from the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-struct drm_vmw_dmabuf_rep {
+struct drm_vmw_bo_rep {
 	__u64 map_handle;
 	__u32 handle;
 	__u32 cur_gmr_id;
 	__u32 cur_gmr_offset;
 	__u32 pad64;
 };
+#define drm_vmw_dmabuf_rep drm_vmw_bo_rep
 
 /**
- * union drm_vmw_dmabuf_arg
+ * union drm_vmw_alloc_bo_arg
  *
  * @req: Input data as described above.
  * @rep: Output data as described above.
  *
- * Argument to the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Argument to the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-union drm_vmw_alloc_dmabuf_arg {
-	struct drm_vmw_alloc_dmabuf_req req;
-	struct drm_vmw_dmabuf_rep rep;
-};
-
-/*************************************************************************/
-/**
- * DRM_VMW_UNREF_DMABUF - Free a DMA buffer.
- *
- */
-
-/**
- * struct drm_vmw_unref_dmabuf_arg
- *
- * @handle: Handle indicating what buffer to free. Obtained from the
- * DRM_VMW_ALLOC_DMABUF Ioctl.
- *
- * Argument to the DRM_VMW_UNREF_DMABUF Ioctl.
- */
-
-struct drm_vmw_unref_dmabuf_arg {
-	__u32 handle;
-	__u32 pad64;
+union drm_vmw_alloc_bo_arg {
+	struct drm_vmw_alloc_bo_req req;
+	struct drm_vmw_bo_rep rep;
 };
+#define drm_vmw_alloc_dmabuf_arg drm_vmw_alloc_bo_arg
 
 /*************************************************************************/
 /**
@@ -1103,9 +1094,8 @@ union drm_vmw_extended_context_arg {
  * DRM_VMW_HANDLE_CLOSE - Close a user-space handle and release its
  * underlying resource.
  *
- * Note that this ioctl is overlaid on the DRM_VMW_UNREF_DMABUF Ioctl.
- * The ioctl arguments therefore need to be identical in layout.
- *
+ * Note that this ioctl is overlaid on the deprecated DRM_VMW_UNREF_DMABUF
+ * Ioctl.
  */
 
 /**
@@ -1119,7 +1109,107 @@ struct drm_vmw_handle_close_arg {
 	__u32 handle;
 	__u32 pad64;
 };
+#define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_CREATE_EXT - Create a host guest-backed surface.
+ *
+ * Allocates a surface handle and queues a create surface command
+ * for the host on the first use of the surface. The surface ID can
+ * be used as the surface ID in commands referencing the surface.
+ *
+ * This new command extends DRM_VMW_GB_SURFACE_CREATE by adding version
+ * parameter and 64 bit svga flag.
+ */
+
+/**
+ * enum drm_vmw_surface_version
+ *
+ * @drm_vmw_surface_gb_v1: Corresponds to current gb surface format with
+ * svga3d surface flags split into 2, upper half and lower half.
+ */
+enum drm_vmw_surface_version {
+	drm_vmw_gb_surface_v1
+};
+
+/**
+ * struct drm_vmw_gb_surface_create_ext_req
+ *
+ * @base: Surface create parameters.
+ * @version: Version of surface create ioctl.
+ * @svga3d_flags_upper_32_bits: Upper 32 bits of svga3d flags.
+ * @multisample_pattern: Multisampling pattern when msaa is supported.
+ * @quality_level: Precision settings for each sample.
+ * @must_be_zero: Reserved for future usage.
+ *
+ * Input argument to the  DRM_VMW_GB_SURFACE_CREATE_EXT Ioctl.
+ * Part of output argument for the DRM_VMW_GB_SURFACE_REF_EXT Ioctl.
+ */
+struct drm_vmw_gb_surface_create_ext_req {
+	struct drm_vmw_gb_surface_create_req base;
+	enum drm_vmw_surface_version version;
+	uint32_t svga3d_flags_upper_32_bits;
+	SVGA3dMSPattern multisample_pattern;
+	SVGA3dMSQualityLevel quality_level;
+	uint64_t must_be_zero;
+};
+
+/**
+ * union drm_vmw_gb_surface_create_ext_arg
+ *
+ * @req: Input argument as described above.
+ * @rep: Output argument as described above.
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
+union drm_vmw_gb_surface_create_ext_arg {
+	struct drm_vmw_gb_surface_create_rep rep;
+	struct drm_vmw_gb_surface_create_ext_req req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_REF_EXT - Reference a host surface.
+ *
+ * Puts a reference on a host surface with a given handle, as previously
+ * returned by the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ * A reference will make sure the surface isn't destroyed while we hold
+ * it and will allow the calling client to use the surface handle in
+ * the command stream.
+ *
+ * On successful return, the Ioctl returns the surface information given
+ * to and returned from the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
 
+/**
+ * struct drm_vmw_gb_surface_ref_ext_rep
+ *
+ * @creq: The data used as input when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_ext_req"
+ * @crep: Additional data output when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_rep"
+ *
+ * Output Argument to the DRM_VMW_GB_SURFACE_REF_EXT ioctl.
+ */
+struct drm_vmw_gb_surface_ref_ext_rep {
+	struct drm_vmw_gb_surface_create_ext_req creq;
+	struct drm_vmw_gb_surface_create_rep crep;
+};
+
+/**
+ * union drm_vmw_gb_surface_reference_ext_arg
+ *
+ * @req: Input data as described above at "struct drm_vmw_surface_arg"
+ * @rep: Output data as described above at
+ *       "struct drm_vmw_gb_surface_ref_ext_rep"
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_REF Ioctl.
+ */
+union drm_vmw_gb_surface_reference_ext_arg {
+	struct drm_vmw_gb_surface_ref_ext_rep rep;
+	struct drm_vmw_surface_arg req;
+};
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index 3c5038b587ba..d4593a6062ef 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,7 +29,6 @@
 
 #include <linux/types.h>
 #include <linux/fs.h>
-#include <linux/signal.h>
 #include <asm/byteorder.h>
 
 typedef __kernel_ulong_t aio_context_t;
@@ -110,10 +109,5 @@ struct iocb {
 #undef IFBIG
 #undef IFLITTLE
 
-struct __aio_sigset {
-	const sigset_t __user	*sigmask;
-	size_t		sigsetsize;
-};
-
 #endif /* __LINUX__AIO_ABI_H */
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 59b19b6a40d7..b7db3261c62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1857,7 +1857,8 @@ union bpf_attr {
  *		is resolved), the nexthop address is returned in ipv4_dst
  *		or ipv6_dst based on family, smac is set to mac address of
  *		egress device, dmac is set to nexthop mac address, rt_metric
- *		is set to metric from route (IPv4/IPv6 only).
+ *		is set to metric from route (IPv4/IPv6 only), and ifindex
+ *		is set to the device index of the nexthop from the FIB lookup.
  *
  *             *plen* argument is the size of the passed in struct.
  *             *flags* argument can be a combination of one or more of the
@@ -1873,9 +1874,10 @@ union bpf_attr {
  *             *ctx* is either **struct xdp_md** for XDP programs or
  *             **struct sk_buff** tc cls_act programs.
  *     Return
- *             Egress device index on success, 0 if packet needs to continue
- *             up the stack for further processing or a negative error in case
- *             of failure.
+ *		* < 0 if any input argument is invalid
+ *		*   0 on success (packet is forwarded, nexthop neighbor exists)
+ *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ *		*     packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2612,6 +2614,18 @@ struct bpf_raw_tracepoint_args {
 #define BPF_FIB_LOOKUP_DIRECT  BIT(0)
 #define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
 
+enum {
+	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
+	BPF_FIB_LKUP_RET_BLACKHOLE,    /* dest is blackholed; can be dropped */
+	BPF_FIB_LKUP_RET_UNREACHABLE,  /* dest is unreachable; can be dropped */
+	BPF_FIB_LKUP_RET_PROHIBIT,     /* dest not allowed; can be dropped */
+	BPF_FIB_LKUP_RET_NOT_FWDED,    /* packet is not forwarded */
+	BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
+	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
+	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+};
+
 struct bpf_fib_lookup {
 	/* input:  network family for lookup (AF_INET, AF_INET6)
 	 * output: network family of egress nexthop
@@ -2625,7 +2639,11 @@ struct bpf_fib_lookup {
 
 	/* total length of packet from network header - used for MTU check */
 	__u16	tot_len;
-	__u32	ifindex;  /* L3 device index for lookup */
+
+	/* input: L3 device index for lookup
+	 * output: device index from FIB lookup
+	 */
+	__u32	ifindex;
 
 	union {
 		/* inputs to lookup */
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 0b5ddbe135a4..972265f32871 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -76,7 +76,7 @@ struct btf_type {
  */
 #define BTF_INT_ENCODING(VAL)	(((VAL) & 0x0f000000) >> 24)
 #define BTF_INT_OFFSET(VAL)	(((VAL  & 0x00ff0000)) >> 16)
-#define BTF_INT_BITS(VAL)	((VAL)  & 0x0000ffff)
+#define BTF_INT_BITS(VAL)	((VAL)  & 0x000000ff)
 
 /* Attributes stored in the BTF_INT_ENCODING */
 #define BTF_INT_SIGNED	(1 << 0)
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 4ca65b56084f..7363f18e65a5 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -226,7 +226,7 @@ enum tunable_id {
 	ETHTOOL_TX_COPYBREAK,
 	ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */
 	/*
-	 * Add your fresh new tubale attribute above and remember to update
+	 * Add your fresh new tunable attribute above and remember to update
 	 * tunable_strings[] in net/core/ethtool.c
 	 */
 	__ETHTOOL_TUNABLE_COUNT,
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index b4f5073dbac2..01674b56e14f 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args {
 	__u32 queue_priority;	/* to KFD */
 };
 
+struct kfd_ioctl_set_cu_mask_args {
+	__u32 queue_id;		/* to KFD */
+	__u32 num_cu_mask;		/* to KFD */
+	__u64 cu_mask_ptr;		/* to KFD */
+};
+
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
 #define KFD_IOC_CACHE_POLICY_COHERENT 0
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
@@ -189,6 +195,15 @@ struct kfd_ioctl_dbg_wave_control_args {
 
 #define KFD_SIGNAL_EVENT_LIMIT			4096
 
+/* For kfd_event_data.hw_exception_data.reset_type. */
+#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET	0
+#define KFD_HW_EXCEPTION_PER_ENGINE_RESET	1
+
+/* For kfd_event_data.hw_exception_data.reset_cause. */
+#define KFD_HW_EXCEPTION_GPU_HANG	0
+#define KFD_HW_EXCEPTION_ECC		1
+
+
 struct kfd_ioctl_create_event_args {
 	__u64 event_page_offset;	/* from KFD */
 	__u32 event_trigger_data;	/* from KFD - signal events only */
@@ -219,7 +234,7 @@ struct kfd_memory_exception_failure {
 	__u32 NotPresent;	/* Page not present or supervisor privilege */
 	__u32 ReadOnly;	/* Write access to a read-only page */
 	__u32 NoExecute;	/* Execute access to a page marked NX */
-	__u32 pad;
+	__u32 imprecise;	/* Can't determine the	exact fault address */
 };
 
 /* memory exception data*/
@@ -230,10 +245,19 @@ struct kfd_hsa_memory_exception_data {
 	__u32 pad;
 };
 
-/* Event data*/
+/* hw exception data */
+struct kfd_hsa_hw_exception_data {
+	uint32_t reset_type;
+	uint32_t reset_cause;
+	uint32_t memory_lost;
+	uint32_t gpu_id;
+};
+
+/* Event data */
 struct kfd_event_data {
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};				/* From KFD */
 	__u64 kfd_event_data_ext;	/* pointer to an extension structure
 					   for future exception types */
@@ -448,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU	\
 		AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)
 
+#define AMDKFD_IOC_SET_CU_MASK		\
+		AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1A
+#define AMDKFD_COMMAND_END		0x1B
 
 #endif
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index d620fa43756c..9a402fdb60e9 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -10,13 +10,8 @@
  * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
  */
 
-#ifdef __KERNEL__
-# include <linux/types.h>
-#else
-# include <stdint.h>
-#endif
-
-#include <linux/types_32_64.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
 
 enum rseq_cpu_id_state {
 	RSEQ_CPU_ID_UNINITIALIZED		= -1,
@@ -52,10 +47,10 @@ struct rseq_cs {
 	__u32 version;
 	/* enum rseq_cs_flags */
 	__u32 flags;
-	LINUX_FIELD_u32_u64(start_ip);
+	__u64 start_ip;
 	/* Offset from start_ip. */
-	LINUX_FIELD_u32_u64(post_commit_offset);
-	LINUX_FIELD_u32_u64(abort_ip);
+	__u64 post_commit_offset;
+	__u64 abort_ip;
 } __attribute__((aligned(4 * sizeof(__u64))));
 
 /*
@@ -67,28 +62,30 @@ struct rseq_cs {
 struct rseq {
 	/*
 	 * Restartable sequences cpu_id_start field. Updated by the
-	 * kernel, and read by user-space with single-copy atomicity
-	 * semantics. Aligned on 32-bit. Always contains a value in the
-	 * range of possible CPUs, although the value may not be the
-	 * actual current CPU (e.g. if rseq is not initialized). This
-	 * CPU number value should always be compared against the value
-	 * of the cpu_id field before performing a rseq commit or
-	 * returning a value read from a data structure indexed using
-	 * the cpu_id_start value.
+	 * kernel. Read by user-space with single-copy atomicity
+	 * semantics. This field should only be read by the thread which
+	 * registered this data structure. Aligned on 32-bit. Always
+	 * contains a value in the range of possible CPUs, although the
+	 * value may not be the actual current CPU (e.g. if rseq is not
+	 * initialized). This CPU number value should always be compared
+	 * against the value of the cpu_id field before performing a rseq
+	 * commit or returning a value read from a data structure indexed
+	 * using the cpu_id_start value.
 	 */
 	__u32 cpu_id_start;
 	/*
-	 * Restartable sequences cpu_id field. Updated by the kernel,
-	 * and read by user-space with single-copy atomicity semantics.
-	 * Aligned on 32-bit. Values RSEQ_CPU_ID_UNINITIALIZED and
-	 * RSEQ_CPU_ID_REGISTRATION_FAILED have a special semantic: the
-	 * former means "rseq uninitialized", and latter means "rseq
-	 * initialization failed". This value is meant to be read within
-	 * rseq critical sections and compared with the cpu_id_start
-	 * value previously read, before performing the commit instruction,
-	 * or read and compared with the cpu_id_start value before returning
-	 * a value loaded from a data structure indexed using the
-	 * cpu_id_start value.
+	 * Restartable sequences cpu_id field. Updated by the kernel.
+	 * Read by user-space with single-copy atomicity semantics. This
+	 * field should only be read by the thread which registered this
+	 * data structure. Aligned on 32-bit. Values
+	 * RSEQ_CPU_ID_UNINITIALIZED and RSEQ_CPU_ID_REGISTRATION_FAILED
+	 * have a special semantic: the former means "rseq uninitialized",
+	 * and latter means "rseq initialization failed". This value is
+	 * meant to be read within rseq critical sections and compared
+	 * with the cpu_id_start value previously read, before performing
+	 * the commit instruction, or read and compared with the
+	 * cpu_id_start value before returning a value loaded from a data
+	 * structure indexed using the cpu_id_start value.
 	 */
 	__u32 cpu_id;
 	/*
@@ -105,27 +102,44 @@ struct rseq {
 	 * targeted by the rseq_cs. Also needs to be set to NULL by user-space
 	 * before reclaiming memory that contains the targeted struct rseq_cs.
 	 *
-	 * Read and set by the kernel with single-copy atomicity semantics.
-	 * Set by user-space with single-copy atomicity semantics. Aligned
-	 * on 64-bit.
+	 * Read and set by the kernel. Set by user-space with single-copy
+	 * atomicity semantics. This field should only be updated by the
+	 * thread which registered this data structure. Aligned on 64-bit.
 	 */
-	LINUX_FIELD_u32_u64(rseq_cs);
+	union {
+		__u64 ptr64;
+#ifdef __LP64__
+		__u64 ptr;
+#else
+		struct {
+#if (defined(__BYTE_ORDER) && (__BYTE_ORDER == __BIG_ENDIAN)) || defined(__BIG_ENDIAN)
+			__u32 padding;		/* Initialized to zero. */
+			__u32 ptr32;
+#else /* LITTLE */
+			__u32 ptr32;
+			__u32 padding;		/* Initialized to zero. */
+#endif /* ENDIAN */
+		} ptr;
+#endif
+	} rseq_cs;
+
 	/*
-	 * - RSEQ_DISABLE flag:
+	 * Restartable sequences flags field.
+	 *
+	 * This field should only be updated by the thread which
+	 * registered this data structure. Read by the kernel.
+	 * Mainly used for single-stepping through rseq critical sections
+	 * with debuggers.
 	 *
-	 * Fallback fast-track flag for single-stepping.
-	 * Set by user-space if lack of progress is detected.
-	 * Cleared by user-space after rseq finish.
-	 * Read by the kernel.
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
-	 *     Inhibit instruction sequence block restart and event
-	 *     counter increment on preemption for this thread.
+	 *     Inhibit instruction sequence block restart on preemption
+	 *     for this thread.
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
-	 *     Inhibit instruction sequence block restart and event
-	 *     counter increment on signal delivery for this thread.
+	 *     Inhibit instruction sequence block restart on signal
+	 *     delivery for this thread.
 	 * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
-	 *     Inhibit instruction sequence block restart and event
-	 *     counter increment on migration for this thread.
+	 *     Inhibit instruction sequence block restart on migration for
+	 *     this thread.
 	 */
 	__u32 flags;
 } __attribute__((aligned(4 * sizeof(__u64))));
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 29eb659aa77a..e3f6ed8a7064 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -127,6 +127,10 @@ enum {
 
 #define TCP_CM_INQ		TCP_INQ
 
+#define TCP_REPAIR_ON		1
+#define TCP_REPAIR_OFF		0
+#define TCP_REPAIR_OFF_NO_WP	-1	/* Turn off without window probes */
+
 struct tcp_repair_opt {
 	__u32	opt_code;
 	__u32	opt_val;
diff --git a/include/uapi/linux/types_32_64.h b/include/uapi/linux/types_32_64.h
deleted file mode 100644
index 0a87ace34a57..000000000000
--- a/include/uapi/linux/types_32_64.h
+++ /dev/null
@@ -1,50 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_TYPES_32_64_H
-#define _UAPI_LINUX_TYPES_32_64_H
-
-/*
- * linux/types_32_64.h
- *
- * Integer type declaration for pointers across 32-bit and 64-bit systems.
- *
- * Copyright (c) 2015-2018 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
- */
-
-#ifdef __KERNEL__
-# include <linux/types.h>
-#else
-# include <stdint.h>
-#endif
-
-#include <asm/byteorder.h>
-
-#ifdef __BYTE_ORDER
-# if (__BYTE_ORDER == __BIG_ENDIAN)
-#  define LINUX_BYTE_ORDER_BIG_ENDIAN
-# else
-#  define LINUX_BYTE_ORDER_LITTLE_ENDIAN
-# endif
-#else
-# ifdef __BIG_ENDIAN
-#  define LINUX_BYTE_ORDER_BIG_ENDIAN
-# else
-#  define LINUX_BYTE_ORDER_LITTLE_ENDIAN
-# endif
-#endif
-
-#ifdef __LP64__
-# define LINUX_FIELD_u32_u64(field)			__u64 field
-# define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	field = (intptr_t)v
-#else
-# ifdef LINUX_BYTE_ORDER_BIG_ENDIAN
-#  define LINUX_FIELD_u32_u64(field)	__u32 field ## _padding, field
-#  define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	\
-	field ## _padding = 0, field = (intptr_t)v
-# else
-#  define LINUX_FIELD_u32_u64(field)	__u32 field, field ## _padding
-#  define LINUX_FIELD_u32_u64_INIT_ONSTACK(field, v)	\
-	field = (intptr_t)v, field ## _padding = 0
-# endif
-#endif
-
-#endif /* _UAPI_LINUX_TYPES_32_64_H */
diff --git a/include/video/mipi_display.h b/include/video/mipi_display.h
index 19aa65a35546..49a53ef8da96 100644
--- a/include/video/mipi_display.h
+++ b/include/video/mipi_display.h
@@ -38,6 +38,9 @@ enum {
 
 	MIPI_DSI_DCS_READ				= 0x06,
 
+	MIPI_DSI_DCS_COMPRESSION_MODE                   = 0x07,
+	MIPI_DSI_PPS_LONG_WRITE                         = 0x0A,
+
 	MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE		= 0x37,
 
 	MIPI_DSI_END_OF_TRANSMISSION			= 0x08,
diff --git a/ipc/sem.c b/ipc/sem.c
index 5af1943ad782..76e95e4f3aa2 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -2118,7 +2118,7 @@ static long do_semtimedop(int semid, struct sembuf __user *tsops,
 	}
 
 	do {
-		queue.status = -EINTR;
+		WRITE_ONCE(queue.status, -EINTR);
 		queue.sleeper = current;
 
 		__set_current_state(TASK_INTERRUPTIBLE);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..9704934252b3 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
  */
 static bool btf_type_int_is_regular(const struct btf_type *t)
 {
-	u16 nr_bits, nr_bytes;
+	u8 nr_bits, nr_bytes;
 	u32 int_data;
 
 	int_data = btf_type_int(t);
@@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf,
 				  void *data, u8 bits_offset,
 				  struct seq_file *m)
 {
+	u16 left_shift_bits, right_shift_bits;
 	u32 int_data = btf_type_int(t);
-	u16 nr_bits = BTF_INT_BITS(int_data);
-	u16 total_bits_offset;
-	u16 nr_copy_bytes;
-	u16 nr_copy_bits;
-	u8 nr_upper_bits;
-	union {
-		u64 u64_num;
-		u8  u8_nums[8];
-	} print_num;
+	u8 nr_bits = BTF_INT_BITS(int_data);
+	u8 total_bits_offset;
+	u8 nr_copy_bytes;
+	u8 nr_copy_bits;
+	u64 print_num;
 
+	/*
+	 * bits_offset is at most 7.
+	 * BTF_INT_OFFSET() cannot exceed 64 bits.
+	 */
 	total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
 	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
 	bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
 	nr_copy_bits = nr_bits + bits_offset;
 	nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
 
-	print_num.u64_num = 0;
-	memcpy(&print_num.u64_num, data, nr_copy_bytes);
+	print_num = 0;
+	memcpy(&print_num, data, nr_copy_bytes);
 
-	/* Ditch the higher order bits */
-	nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
-	if (nr_upper_bits) {
-		/* We need to mask out some bits of the upper byte. */
-		u8 mask = (1 << nr_upper_bits) - 1;
-
-		print_num.u8_nums[nr_copy_bytes - 1] &= mask;
-	}
+#ifdef __BIG_ENDIAN_BITFIELD
+	left_shift_bits = bits_offset;
+#else
+	left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+	right_shift_bits = BITS_PER_U64 - nr_bits;
 
-	print_num.u64_num >>= bits_offset;
+	print_num <<= left_shift_bits;
+	print_num >>= right_shift_bits;
 
-	seq_printf(m, "0x%llx", print_num.u64_num);
+	seq_printf(m, "0x%llx", print_num);
 }
 
 static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
@@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
 	u32 int_data = btf_type_int(t);
 	u8 encoding = BTF_INT_ENCODING(int_data);
 	bool sign = encoding & BTF_INT_SIGNED;
-	u32 nr_bits = BTF_INT_BITS(int_data);
+	u8 nr_bits = BTF_INT_BITS(int_data);
 
 	if (bits_offset || BTF_INT_OFFSET(int_data) ||
 	    BITS_PER_BYTE_MASKED(nr_bits)) {
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f7c00bd6f8e4..3d83ee7df381 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
 	return ret;
 }
 
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+			   enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+				attr->attach_flags);
+	cgroup_put(cgrp);
+	return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+	struct bpf_prog *prog;
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+	if (IS_ERR(prog))
+		prog = NULL;
+
+	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+	if (prog)
+		bpf_prog_put(prog);
+
+	cgroup_put(cgrp);
+	return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+			  union bpf_attr __user *uattr)
+{
+	struct cgroup *cgrp;
+	int ret;
+
+	cgrp = cgroup_get_from_fd(attr->query.target_fd);
+	if (IS_ERR(cgrp))
+		return PTR_ERR(cgrp);
+
+	ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+	cgroup_put(cgrp);
+	return ret;
+}
+
 /**
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socket sending or receiving traffic
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a9e6c04d0f4a..1e5625d46414 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -598,8 +598,6 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
 	bpf_fill_ill_insns(hdr, size);
 
 	hdr->pages = size / PAGE_SIZE;
-	hdr->locked = 0;
-
 	hole = min_t(unsigned int, size - (proglen + sizeof(*hdr)),
 		     PAGE_SIZE - sizeof(*hdr));
 	start = (get_random_int() % hole) & ~(alignment - 1);
@@ -1450,22 +1448,6 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
 	return 0;
 }
 
-static int bpf_prog_check_pages_ro_locked(const struct bpf_prog *fp)
-{
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-	int i, err;
-
-	for (i = 0; i < fp->aux->func_cnt; i++) {
-		err = bpf_prog_check_pages_ro_single(fp->aux->func[i]);
-		if (err)
-			return err;
-	}
-
-	return bpf_prog_check_pages_ro_single(fp);
-#endif
-	return 0;
-}
-
 static void bpf_prog_select_func(struct bpf_prog *fp)
 {
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
@@ -1524,17 +1506,7 @@ finalize:
 	 * all eBPF JITs might immediately support all features.
 	 */
 	*err = bpf_check_tail_call(fp);
-	if (*err)
-		return fp;
-
-	/* Checkpoint: at this point onwards any cBPF -> eBPF or
-	 * native eBPF program is read-only. If we failed to change
-	 * the page attributes (e.g. allocation failure from
-	 * splitting large pages), then reject the whole program
-	 * in order to guarantee not ending up with any W+X pages
-	 * from BPF side in kernel.
-	 */
-	*err = bpf_prog_check_pages_ro_locked(fp);
+
 	return fp;
 }
 EXPORT_SYMBOL_GPL(bpf_prog_select_runtime);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 642c97f6d1b8..d361fc1e3bf3 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -334,10 +334,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 {
 	struct net_device *dev = dst->dev;
 	struct xdp_frame *xdpf;
+	int err;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit)
 		return -EOPNOTSUPP;
 
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
 	xdpf = convert_to_xdp_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -350,7 +355,7 @@ int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
 {
 	int err;
 
-	err = __xdp_generic_ok_fwd_dev(skb, dst->dev);
+	err = xdp_ok_fwd_dev(dst->dev, skb->len);
 	if (unlikely(err))
 		return err;
 	skb->dev = dst->dev;
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..513d9dfcf4ee 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 				 * old element will be freed immediately.
 				 * Otherwise return an error
 				 */
-				atomic_dec(&htab->count);
-				return ERR_PTR(-E2BIG);
+				l_new = ERR_PTR(-E2BIG);
+				goto dec_count;
 			}
 		l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
 				     htab->map.numa_node);
-		if (!l_new)
-			return ERR_PTR(-ENOMEM);
+		if (!l_new) {
+			l_new = ERR_PTR(-ENOMEM);
+			goto dec_count;
+		}
 	}
 
 	memcpy(l_new->key, key, key_size);
@@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 						  GFP_ATOMIC | __GFP_NOWARN);
 			if (!pptr) {
 				kfree(l_new);
-				return ERR_PTR(-ENOMEM);
+				l_new = ERR_PTR(-ENOMEM);
+				goto dec_count;
 			}
 		}
 
@@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 
 	l_new->hash = hash;
 	return l_new;
+dec_count:
+	atomic_dec(&htab->count);
+	return l_new;
 }
 
 static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 52a91d816c0e..98fb7938beea 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -72,6 +72,7 @@ struct bpf_htab {
 	u32 n_buckets;
 	u32 elem_size;
 	struct bpf_sock_progs progs;
+	struct rcu_head rcu;
 };
 
 struct htab_elem {
@@ -89,8 +90,8 @@ enum smap_psock_state {
 struct smap_psock_map_entry {
 	struct list_head list;
 	struct sock **entry;
-	struct htab_elem *hash_link;
-	struct bpf_htab *htab;
+	struct htab_elem __rcu *hash_link;
+	struct bpf_htab __rcu *htab;
 };
 
 struct smap_psock {
@@ -120,6 +121,7 @@ struct smap_psock {
 	struct bpf_prog *bpf_parse;
 	struct bpf_prog *bpf_verdict;
 	struct list_head maps;
+	spinlock_t maps_lock;
 
 	/* Back reference used when sock callback trigger sockmap operations */
 	struct sock *sock;
@@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
 			    int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
 
 static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
 {
@@ -161,7 +164,42 @@ out:
 	return !empty;
 }
 
-static struct proto tcp_bpf_proto;
+enum {
+	SOCKMAP_IPV4,
+	SOCKMAP_IPV6,
+	SOCKMAP_NUM_PROTS,
+};
+
+enum {
+	SOCKMAP_BASE,
+	SOCKMAP_TX,
+	SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+			 struct proto *base)
+{
+	prot[SOCKMAP_BASE]			= *base;
+	prot[SOCKMAP_BASE].close		= bpf_tcp_close;
+	prot[SOCKMAP_BASE].recvmsg		= bpf_tcp_recvmsg;
+	prot[SOCKMAP_BASE].stream_memory_read	= bpf_tcp_stream_read;
+
+	prot[SOCKMAP_TX]			= prot[SOCKMAP_BASE];
+	prot[SOCKMAP_TX].sendmsg		= bpf_tcp_sendmsg;
+	prot[SOCKMAP_TX].sendpage		= bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+	int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+	int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+	sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
 static int bpf_tcp_init(struct sock *sk)
 {
 	struct smap_psock *psock;
@@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk)
 	psock->save_close = sk->sk_prot->close;
 	psock->sk_proto = sk->sk_prot;
 
-	if (psock->bpf_tx_msg) {
-		tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
-		tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
-		tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
-		tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+	/* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+	if (sk->sk_family == AF_INET6 &&
+	    unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+		spin_lock_bh(&tcpv6_prot_lock);
+		if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+			build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+			smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+		}
+		spin_unlock_bh(&tcpv6_prot_lock);
 	}
-
-	sk->sk_prot = &tcp_bpf_proto;
+	update_sk_prot(sk, psock);
 	rcu_read_unlock();
 	return 0;
 }
@@ -219,24 +260,64 @@ out:
 	rcu_read_unlock();
 }
 
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+					 u32 hash, void *key, u32 key_size)
+{
+	struct htab_elem *l;
+
+	hlist_for_each_entry_rcu(l, head, hash_node) {
+		if (l->hash == hash && !memcmp(&l->key, key, key_size))
+			return l;
+	}
+
+	return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+	return &__select_bucket(htab, hash)->head;
+}
+
 static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
 {
 	atomic_dec(&htab->count);
 	kfree_rcu(l, rcu);
 }
 
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+						  struct smap_psock *psock)
+{
+	struct smap_psock_map_entry *e;
+
+	spin_lock_bh(&psock->maps_lock);
+	e = list_first_entry_or_null(&psock->maps,
+				     struct smap_psock_map_entry,
+				     list);
+	if (e)
+		list_del(&e->list);
+	spin_unlock_bh(&psock->maps_lock);
+	return e;
+}
+
 static void bpf_tcp_close(struct sock *sk, long timeout)
 {
 	void (*close_fun)(struct sock *sk, long timeout);
-	struct smap_psock_map_entry *e, *tmp;
+	struct smap_psock_map_entry *e;
 	struct sk_msg_buff *md, *mtmp;
 	struct smap_psock *psock;
 	struct sock *osk;
 
+	lock_sock(sk);
 	rcu_read_lock();
 	psock = smap_psock_sk(sk);
 	if (unlikely(!psock)) {
 		rcu_read_unlock();
+		release_sock(sk);
 		return sk->sk_prot->close(sk, timeout);
 	}
 
@@ -247,7 +328,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 	 */
 	close_fun = psock->save_close;
 
-	write_lock_bh(&sk->sk_callback_lock);
 	if (psock->cork) {
 		free_start_sg(psock->sock, psock->cork);
 		kfree(psock->cork);
@@ -260,21 +340,40 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
 		kfree(md);
 	}
 
-	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+	e = psock_map_pop(sk, psock);
+	while (e) {
 		if (e->entry) {
 			osk = cmpxchg(e->entry, sk, NULL);
 			if (osk == sk) {
-				list_del(&e->list);
 				smap_release_sock(psock, sk);
 			}
 		} else {
-			hlist_del_rcu(&e->hash_link->hash_node);
-			smap_release_sock(psock, e->hash_link->sk);
-			free_htab_elem(e->htab, e->hash_link);
+			struct htab_elem *link = rcu_dereference(e->hash_link);
+			struct bpf_htab *htab = rcu_dereference(e->htab);
+			struct hlist_head *head;
+			struct htab_elem *l;
+			struct bucket *b;
+
+			b = __select_bucket(htab, link->hash);
+			head = &b->head;
+			raw_spin_lock_bh(&b->lock);
+			l = lookup_elem_raw(head,
+					    link->hash, link->key,
+					    htab->map.key_size);
+			/* If another thread deleted this object skip deletion.
+			 * The refcnt on psock may or may not be zero.
+			 */
+			if (l) {
+				hlist_del_rcu(&link->hash_node);
+				smap_release_sock(psock, link->sk);
+				free_htab_elem(htab, link);
+			}
+			raw_spin_unlock_bh(&b->lock);
 		}
+		e = psock_map_pop(sk, psock);
 	}
-	write_unlock_bh(&sk->sk_callback_lock);
 	rcu_read_unlock();
+	release_sock(sk);
 	close_fun(sk, timeout);
 }
 
@@ -472,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
 	while (sg[i].length) {
 		free += sg[i].length;
 		sk_mem_uncharge(sk, sg[i].length);
-		put_page(sg_page(&sg[i]));
+		if (!md->skb)
+			put_page(sg_page(&sg[i]));
 		sg[i].length = 0;
 		sg[i].page_link = 0;
 		sg[i].offset = 0;
@@ -481,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
 		if (i == MAX_SKB_FRAGS)
 			i = 0;
 	}
+	if (md->skb)
+		consume_skb(md->skb);
 
 	return free;
 }
@@ -1111,8 +1213,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock,
 
 static int bpf_tcp_ulp_register(void)
 {
-	tcp_bpf_proto = tcp_prot;
-	tcp_bpf_proto.close = bpf_tcp_close;
+	build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
 	/* Once BPF TX ULP is registered it is never unregistered. It
 	 * will be in the ULP list for the lifetime of the system. Doing
 	 * duplicate registers is not a problem.
@@ -1135,7 +1236,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
 	skb->sk = psock->sock;
-	bpf_compute_data_pointers(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	preempt_disable();
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	preempt_enable();
@@ -1357,7 +1458,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
 {
 	if (refcount_dec_and_test(&psock->refcnt)) {
 		tcp_cleanup_ulp(sock);
+		write_lock_bh(&sock->sk_callback_lock);
 		smap_stop_sock(psock, sock);
+		write_unlock_bh(&sock->sk_callback_lock);
 		clear_bit(SMAP_TX_RUNNING, &psock->state);
 		rcu_assign_sk_user_data(sock, NULL);
 		call_rcu_sched(&psock->rcu, smap_destroy_psock);
@@ -1388,7 +1491,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
 	 * any socket yet.
 	 */
 	skb->sk = psock->sock;
-	bpf_compute_data_pointers(skb);
+	bpf_compute_data_end_sk_skb(skb);
 	rc = (*prog->bpf_func)(skb, prog->insnsi);
 	skb->sk = NULL;
 	rcu_read_unlock();
@@ -1508,6 +1611,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node)
 	INIT_LIST_HEAD(&psock->maps);
 	INIT_LIST_HEAD(&psock->ingress);
 	refcount_set(&psock->refcnt, 1);
+	spin_lock_init(&psock->maps_lock);
 
 	rcu_assign_sk_user_data(sock, psock);
 	sock_hold(sock);
@@ -1564,18 +1668,32 @@ free_stab:
 	return ERR_PTR(err);
 }
 
-static void smap_list_remove(struct smap_psock *psock,
-			     struct sock **entry,
-			     struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+				 struct sock **entry)
 {
 	struct smap_psock_map_entry *e, *tmp;
 
+	spin_lock_bh(&psock->maps_lock);
 	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
-		if (e->entry == entry || e->hash_link == hash_link) {
+		if (e->entry == entry)
+			list_del(&e->list);
+	}
+	spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+				  struct htab_elem *hash_link)
+{
+	struct smap_psock_map_entry *e, *tmp;
+
+	spin_lock_bh(&psock->maps_lock);
+	list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+		struct htab_elem *c = rcu_dereference(e->hash_link);
+
+		if (c == hash_link)
 			list_del(&e->list);
-			break;
-		}
 	}
+	spin_unlock_bh(&psock->maps_lock);
 }
 
 static void sock_map_free(struct bpf_map *map)
@@ -1601,7 +1719,6 @@ static void sock_map_free(struct bpf_map *map)
 		if (!sock)
 			continue;
 
-		write_lock_bh(&sock->sk_callback_lock);
 		psock = smap_psock_sk(sock);
 		/* This check handles a racing sock event that can get the
 		 * sk_callback_lock before this case but after xchg happens
@@ -1609,10 +1726,9 @@ static void sock_map_free(struct bpf_map *map)
 		 * to be null and queued for garbage collection.
 		 */
 		if (likely(psock)) {
-			smap_list_remove(psock, &stab->sock_map[i], NULL);
+			smap_list_map_remove(psock, &stab->sock_map[i]);
 			smap_release_sock(psock, sock);
 		}
-		write_unlock_bh(&sock->sk_callback_lock);
 	}
 	rcu_read_unlock();
 
@@ -1661,17 +1777,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
 	if (!sock)
 		return -EINVAL;
 
-	write_lock_bh(&sock->sk_callback_lock);
 	psock = smap_psock_sk(sock);
 	if (!psock)
 		goto out;
 
 	if (psock->bpf_parse)
 		smap_stop_sock(psock, sock);
-	smap_list_remove(psock, &stab->sock_map[k], NULL);
+	smap_list_map_remove(psock, &stab->sock_map[k]);
 	smap_release_sock(psock, sock);
 out:
-	write_unlock_bh(&sock->sk_callback_lock);
 	return 0;
 }
 
@@ -1752,7 +1866,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		}
 	}
 
-	write_lock_bh(&sock->sk_callback_lock);
 	psock = smap_psock_sk(sock);
 
 	/* 2. Do not allow inheriting programs if psock exists and has
@@ -1789,7 +1902,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
 		if (!e) {
 			err = -ENOMEM;
-			goto out_progs;
+			goto out_free;
 		}
 	}
 
@@ -1809,7 +1922,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 		if (err)
 			goto out_free;
 		smap_init_progs(psock, verdict, parse);
+		write_lock_bh(&sock->sk_callback_lock);
 		smap_start_sock(psock, sock);
+		write_unlock_bh(&sock->sk_callback_lock);
 	}
 
 	/* 4. Place psock in sockmap for use and stop any programs on
@@ -1819,9 +1934,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
 	 */
 	if (map_link) {
 		e->entry = map_link;
+		spin_lock_bh(&psock->maps_lock);
 		list_add_tail(&e->list, &psock->maps);
+		spin_unlock_bh(&psock->maps_lock);
 	}
-	write_unlock_bh(&sock->sk_callback_lock);
 	return err;
 out_free:
 	smap_release_sock(psock, sock);
@@ -1832,7 +1948,6 @@ out_progs:
 	}
 	if (tx_msg)
 		bpf_prog_put(tx_msg);
-	write_unlock_bh(&sock->sk_callback_lock);
 	kfree(e);
 	return err;
 }
@@ -1869,10 +1984,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	if (osock) {
 		struct smap_psock *opsock = smap_psock_sk(osock);
 
-		write_lock_bh(&osock->sk_callback_lock);
-		smap_list_remove(opsock, &stab->sock_map[i], NULL);
+		smap_list_map_remove(opsock, &stab->sock_map[i]);
 		smap_release_sock(opsock, osock);
-		write_unlock_bh(&osock->sk_callback_lock);
 	}
 out:
 	return err;
@@ -1915,6 +2028,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
 	return 0;
 }
 
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+			struct bpf_prog *prog)
+{
+	int ufd = attr->target_fd;
+	struct bpf_map *map;
+	struct fd f;
+	int err;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	err = sock_map_prog(map, prog, attr->attach_type);
+	fdput(f);
+	return err;
+}
+
 static void *sock_map_lookup(struct bpf_map *map, void *key)
 {
 	return NULL;
@@ -1944,7 +2075,13 @@ static int sock_map_update_elem(struct bpf_map *map,
 		return -EOPNOTSUPP;
 	}
 
+	lock_sock(skops.sk);
+	preempt_disable();
+	rcu_read_lock();
 	err = sock_map_ctx_update_elem(&skops, map, key, flags);
+	rcu_read_unlock();
+	preempt_enable();
+	release_sock(skops.sk);
 	fput(socket->file);
 	return err;
 }
@@ -2043,14 +2180,13 @@ free_htab:
 	return ERR_PTR(err);
 }
 
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
 {
-	return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+	struct bpf_htab *htab;
 
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
-	return &__select_bucket(htab, hash)->head;
+	htab = container_of(rcu, struct bpf_htab, rcu);
+	bpf_map_area_free(htab->buckets);
+	kfree(htab);
 }
 
 static void sock_hash_free(struct bpf_map *map)
@@ -2069,16 +2205,18 @@ static void sock_hash_free(struct bpf_map *map)
 	 */
 	rcu_read_lock();
 	for (i = 0; i < htab->n_buckets; i++) {
-		struct hlist_head *head = select_bucket(htab, i);
+		struct bucket *b = __select_bucket(htab, i);
+		struct hlist_head *head;
 		struct hlist_node *n;
 		struct htab_elem *l;
 
+		raw_spin_lock_bh(&b->lock);
+		head = &b->head;
 		hlist_for_each_entry_safe(l, n, head, hash_node) {
 			struct sock *sock = l->sk;
 			struct smap_psock *psock;
 
 			hlist_del_rcu(&l->hash_node);
-			write_lock_bh(&sock->sk_callback_lock);
 			psock = smap_psock_sk(sock);
 			/* This check handles a racing sock event that can get
 			 * the sk_callback_lock before this case but after xchg
@@ -2086,16 +2224,15 @@ static void sock_hash_free(struct bpf_map *map)
 			 * (psock) to be null and queued for garbage collection.
 			 */
 			if (likely(psock)) {
-				smap_list_remove(psock, NULL, l);
+				smap_list_hash_remove(psock, l);
 				smap_release_sock(psock, sock);
 			}
-			write_unlock_bh(&sock->sk_callback_lock);
-			kfree(l);
+			free_htab_elem(htab, l);
 		}
+		raw_spin_unlock_bh(&b->lock);
 	}
 	rcu_read_unlock();
-	bpf_map_area_free(htab->buckets);
-	kfree(htab);
+	call_rcu(&htab->rcu, __bpf_htab_free);
 }
 
 static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
@@ -2122,19 +2259,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
 	return l_new;
 }
 
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
-					 u32 hash, void *key, u32 key_size)
-{
-	struct htab_elem *l;
-
-	hlist_for_each_entry_rcu(l, head, hash_node) {
-		if (l->hash == hash && !memcmp(&l->key, key, key_size))
-			return l;
-	}
-
-	return NULL;
-}
-
 static inline u32 htab_map_hash(const void *key, u32 key_len)
 {
 	return jhash(key, key_len, 0);
@@ -2230,7 +2354,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 	if (err)
 		goto err;
 
-	/* bpf_map_update_elem() can be called in_irq() */
+	/* psock is valid here because otherwise above *ctx_update_elem would
+	 * have thrown an error. It is safe to skip error check.
+	 */
+	psock = smap_psock_sk(sock);
 	raw_spin_lock_bh(&b->lock);
 	l_old = lookup_elem_raw(head, hash, key, key_size);
 	if (l_old && map_flags == BPF_NOEXIST) {
@@ -2248,15 +2375,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		goto bucket_err;
 	}
 
-	psock = smap_psock_sk(sock);
-	if (unlikely(!psock)) {
-		err = -EINVAL;
-		goto bucket_err;
-	}
-
-	e->hash_link = l_new;
-	e->htab = container_of(map, struct bpf_htab, map);
+	rcu_assign_pointer(e->hash_link, l_new);
+	rcu_assign_pointer(e->htab,
+			   container_of(map, struct bpf_htab, map));
+	spin_lock_bh(&psock->maps_lock);
 	list_add_tail(&e->list, &psock->maps);
+	spin_unlock_bh(&psock->maps_lock);
 
 	/* add new element to the head of the list, so that
 	 * concurrent search will find it before old elem
@@ -2266,19 +2390,17 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
 		psock = smap_psock_sk(l_old->sk);
 
 		hlist_del_rcu(&l_old->hash_node);
-		smap_list_remove(psock, NULL, l_old);
+		smap_list_hash_remove(psock, l_old);
 		smap_release_sock(psock, l_old->sk);
 		free_htab_elem(htab, l_old);
 	}
 	raw_spin_unlock_bh(&b->lock);
 	return 0;
 bucket_err:
+	smap_release_sock(psock, sock);
 	raw_spin_unlock_bh(&b->lock);
 err:
 	kfree(e);
-	psock = smap_psock_sk(sock);
-	if (psock)
-		smap_release_sock(psock, sock);
 	return err;
 }
 
@@ -2300,7 +2422,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
 		return -EINVAL;
 	}
 
+	lock_sock(skops.sk);
+	preempt_disable();
+	rcu_read_lock();
 	err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+	rcu_read_unlock();
+	preempt_enable();
+	release_sock(skops.sk);
 	fput(socket->file);
 	return err;
 }
@@ -2326,7 +2454,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
 		struct smap_psock *psock;
 
 		hlist_del_rcu(&l->hash_node);
-		write_lock_bh(&sock->sk_callback_lock);
 		psock = smap_psock_sk(sock);
 		/* This check handles a racing sock event that can get the
 		 * sk_callback_lock before this case but after xchg happens
@@ -2334,10 +2461,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
 		 * to be null and queued for garbage collection.
 		 */
 		if (likely(psock)) {
-			smap_list_remove(psock, NULL, l);
+			smap_list_hash_remove(psock, l);
 			smap_release_sock(psock, sock);
 		}
-		write_unlock_bh(&sock->sk_callback_lock);
 		free_htab_elem(htab, l);
 		ret = 0;
 	}
@@ -2359,10 +2485,8 @@ struct sock  *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
 	b = __select_bucket(htab, hash);
 	head = &b->head;
 
-	raw_spin_lock_bh(&b->lock);
 	l = lookup_elem_raw(head, hash, key, key_size);
 	sk = l ? l->sk : NULL;
-	raw_spin_unlock_bh(&b->lock);
 	return sk;
 }
 
@@ -2383,6 +2507,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_get_next_key = sock_hash_get_next_key,
 	.map_update_elem = sock_hash_update_elem,
 	.map_delete_elem = sock_hash_delete_elem,
+	.map_release_uref = sock_map_release,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 35dc466641f2..a31a1ba0f8ea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr)
 	if (bpf_map_is_dev_bound(map)) {
 		err = bpf_map_offload_update_elem(map, key, value, attr->flags);
 		goto out;
-	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+		   map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+		   map->map_type == BPF_MAP_TYPE_SOCKMAP) {
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
 		goto out;
 	}
@@ -1483,8 +1485,6 @@ out_free_tp:
 	return err;
 }
 
-#ifdef CONFIG_CGROUP_BPF
-
 static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 					     enum bpf_attach_type attach_type)
 {
@@ -1499,40 +1499,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
 
 #define BPF_PROG_ATTACH_LAST_FIELD attach_flags
 
-static int sockmap_get_from_fd(const union bpf_attr *attr,
-			       int type, bool attach)
-{
-	struct bpf_prog *prog = NULL;
-	int ufd = attr->target_fd;
-	struct bpf_map *map;
-	struct fd f;
-	int err;
-
-	f = fdget(ufd);
-	map = __bpf_map_get(f);
-	if (IS_ERR(map))
-		return PTR_ERR(map);
-
-	if (attach) {
-		prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
-		if (IS_ERR(prog)) {
-			fdput(f);
-			return PTR_ERR(prog);
-		}
-	}
-
-	err = sock_map_prog(map, prog, attr->attach_type);
-	if (err) {
-		fdput(f);
-		if (prog)
-			bpf_prog_put(prog);
-		return err;
-	}
-
-	fdput(f);
-	return 0;
-}
-
 #define BPF_F_ATTACH_MASK \
 	(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
 
@@ -1540,7 +1506,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
 	struct bpf_prog *prog;
-	struct cgroup *cgrp;
 	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
@@ -1577,12 +1542,15 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
 		break;
 	case BPF_SK_MSG_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+		ptype = BPF_PROG_TYPE_SK_MSG;
+		break;
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+		ptype = BPF_PROG_TYPE_SK_SKB;
+		break;
 	case BPF_LIRC_MODE2:
-		return lirc_prog_attach(attr);
+		ptype = BPF_PROG_TYPE_LIRC_MODE2;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1596,18 +1564,20 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 		return -EINVAL;
 	}
 
-	cgrp = cgroup_get_from_fd(attr->target_fd);
-	if (IS_ERR(cgrp)) {
-		bpf_prog_put(prog);
-		return PTR_ERR(cgrp);
+	switch (ptype) {
+	case BPF_PROG_TYPE_SK_SKB:
+	case BPF_PROG_TYPE_SK_MSG:
+		ret = sockmap_get_from_fd(attr, ptype, prog);
+		break;
+	case BPF_PROG_TYPE_LIRC_MODE2:
+		ret = lirc_prog_attach(attr, prog);
+		break;
+	default:
+		ret = cgroup_bpf_prog_attach(attr, ptype, prog);
 	}
 
-	ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
-				attr->attach_flags);
 	if (ret)
 		bpf_prog_put(prog);
-	cgroup_put(cgrp);
-
 	return ret;
 }
 
@@ -1616,9 +1586,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
 static int bpf_prog_detach(const union bpf_attr *attr)
 {
 	enum bpf_prog_type ptype;
-	struct bpf_prog *prog;
-	struct cgroup *cgrp;
-	int ret;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -1651,29 +1618,17 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 		ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
 		break;
 	case BPF_SK_MSG_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
 	case BPF_SK_SKB_STREAM_PARSER:
 	case BPF_SK_SKB_STREAM_VERDICT:
-		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+		return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
 	case BPF_LIRC_MODE2:
 		return lirc_prog_detach(attr);
 	default:
 		return -EINVAL;
 	}
 
-	cgrp = cgroup_get_from_fd(attr->target_fd);
-	if (IS_ERR(cgrp))
-		return PTR_ERR(cgrp);
-
-	prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
-	if (IS_ERR(prog))
-		prog = NULL;
-
-	ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
-	if (prog)
-		bpf_prog_put(prog);
-	cgroup_put(cgrp);
-	return ret;
+	return cgroup_bpf_prog_detach(attr, ptype);
 }
 
 #define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -1681,9 +1636,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
 static int bpf_prog_query(const union bpf_attr *attr,
 			  union bpf_attr __user *uattr)
 {
-	struct cgroup *cgrp;
-	int ret;
-
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 	if (CHECK_ATTR(BPF_PROG_QUERY))
@@ -1711,14 +1663,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	default:
 		return -EINVAL;
 	}
-	cgrp = cgroup_get_from_fd(attr->query.target_fd);
-	if (IS_ERR(cgrp))
-		return PTR_ERR(cgrp);
-	ret = cgroup_bpf_query(cgrp, attr, uattr);
-	cgroup_put(cgrp);
-	return ret;
+
+	return cgroup_bpf_prog_query(attr, uattr);
 }
-#endif /* CONFIG_CGROUP_BPF */
 
 #define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
 
@@ -2365,7 +2312,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_OBJ_GET:
 		err = bpf_obj_get(&attr);
 		break;
-#ifdef CONFIG_CGROUP_BPF
 	case BPF_PROG_ATTACH:
 		err = bpf_prog_attach(&attr);
 		break;
@@ -2375,7 +2321,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_PROG_QUERY:
 		err = bpf_prog_query(&attr, uattr);
 		break;
-#endif
 	case BPF_PROG_TEST_RUN:
 		err = bpf_prog_test_run(&attr, uattr);
 		break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..63aaac52a265 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		if (insn->code != (BPF_JMP | BPF_CALL) ||
 		    insn->src_reg != BPF_PSEUDO_CALL)
 			continue;
+		/* Upon error here we cannot fall back to interpreter but
+		 * need a hard reject of the program. Thus -EFAULT is
+		 * propagated in any case.
+		 */
 		subprog = find_subprog(env, i + insn->imm + 1);
 		if (subprog < 0) {
 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 
 	func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
 	if (!func)
-		return -ENOMEM;
+		goto out_undo_insn;
 
 	for (i = 0; i < env->subprog_cnt; i++) {
 		subprog_start = subprog_end;
@@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		tmp = bpf_int_jit_compile(func[i]);
 		if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
 			verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
-			err = -EFAULT;
+			err = -ENOTSUPP;
 			goto out_free;
 		}
 		cond_resched();
@@ -5552,6 +5556,7 @@ out_free:
 		if (func[i])
 			bpf_jit_free(func[i]);
 	kfree(func);
+out_undo_insn:
 	/* cleanup main prog to be interpreted */
 	prog->jit_requested = 0;
 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
 		err = jit_subprogs(env);
 		if (err == 0)
 			return 0;
+		if (err == -EFAULT)
+			return err;
 	}
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	for (i = 0; i < prog->len; i++, insn++) {
diff --git a/kernel/fork.c b/kernel/fork.c
index 9440d61b925c..1b27babc4c78 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -303,11 +303,36 @@ struct kmem_cache *files_cachep;
 struct kmem_cache *fs_cachep;
 
 /* SLAB cache for vm_area_struct structures */
-struct kmem_cache *vm_area_cachep;
+static struct kmem_cache *vm_area_cachep;
 
 /* SLAB cache for mm_struct structures (tsk->mm) */
 static struct kmem_cache *mm_cachep;
 
+struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
+{
+	struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+
+	if (vma)
+		vma_init(vma, mm);
+	return vma;
+}
+
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
+{
+	struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+
+	if (new) {
+		*new = *orig;
+		INIT_LIST_HEAD(&new->anon_vma_chain);
+	}
+	return new;
+}
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+	kmem_cache_free(vm_area_cachep, vma);
+}
+
 static void account_kernel_stack(struct task_struct *tsk, int account)
 {
 	void *stack = task_stack_page(tsk);
@@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 				goto fail_nomem;
 			charge = len;
 		}
-		tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		tmp = vm_area_dup(mpnt);
 		if (!tmp)
 			goto fail_nomem;
-		*tmp = *mpnt;
-		INIT_LIST_HEAD(&tmp->anon_vma_chain);
 		retval = vma_dup_policy(mpnt, tmp);
 		if (retval)
 			goto fail_nomem_policy;
@@ -539,7 +562,7 @@ fail_uprobe_end:
 fail_nomem_anon_vma_fork:
 	mpol_put(vma_policy(tmp));
 fail_nomem_policy:
-	kmem_cache_free(vm_area_cachep, tmp);
+	vm_area_free(tmp);
 fail_nomem:
 	retval = -ENOMEM;
 	vm_unacct_memory(charge);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 481951bf091d..486dedbd9af5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task)
 static void __kthread_parkme(struct kthread *self)
 {
 	for (;;) {
-		set_current_state(TASK_PARKED);
+		/*
+		 * TASK_PARKED is a special state; we must serialize against
+		 * possible pending wakeups to avoid store-store collisions on
+		 * task->state.
+		 *
+		 * Such a collision might possibly result in the task state
+		 * changin from TASK_PARKED and us failing the
+		 * wait_task_inactive() in kthread_park().
+		 */
+		set_special_state(TASK_PARKED);
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
+
+		complete_all(&self->parked);
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -191,11 +202,6 @@ void kthread_parkme(void)
 }
 EXPORT_SYMBOL_GPL(kthread_parkme);
 
-void kthread_park_complete(struct task_struct *k)
-{
-	complete_all(&to_kthread(k)->parked);
-}
-
 static int kthread(void *_create)
 {
 	/* Copy data: it's on kthread's stack */
@@ -319,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
 	task = create->result;
 	if (!IS_ERR(task)) {
 		static const struct sched_param param = { .sched_priority = 0 };
+		char name[TASK_COMM_LEN];
 
-		vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+		/*
+		 * task is already visible to other tasks, so updating
+		 * COMM must be protected.
+		 */
+		vsnprintf(name, sizeof(name), namefmt, args);
+		set_task_comm(task, name);
 		/*
 		 * root may have changed our (kthreadd's) priority or CPU mask.
 		 * The kernel thread should not inherit these properties.
@@ -461,6 +473,9 @@ void kthread_unpark(struct task_struct *k)
 
 	reinit_completion(&kthread->parked);
 	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+	/*
+	 * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
+	 */
 	wake_up_state(k, TASK_PARKED);
 }
 EXPORT_SYMBOL_GPL(kthread_unpark);
@@ -487,7 +502,16 @@ int kthread_park(struct task_struct *k)
 	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	if (k != current) {
 		wake_up_process(k);
+		/*
+		 * Wait for __kthread_parkme() to complete(), this means we
+		 * _will_ have TASK_PARKED and are about to call schedule().
+		 */
 		wait_for_completion(&kthread->parked);
+		/*
+		 * Now wait for that schedule() to complete and the task to
+		 * get scheduled out.
+		 */
+		WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
 	}
 
 	return 0;
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..38283363da06 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	unsigned long pfn, pgoff, order;
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
+	struct dev_pagemap *conflict_pgmap;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
+	align_end = align_start + align_size - 1;
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+	if (conflict_pgmap) {
+		dev_WARN(dev, "Conflicting mapping in same section\n");
+		put_dev_pagemap(conflict_pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
 	is_ram = region_intersects(align_start, align_size,
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
@@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	mutex_lock(&pgmap_lock);
 	error = 0;
-	align_end = align_start + align_size - 1;
 
 	foreach_order_pgoff(res, order, pgoff) {
 		error = __radix_tree_insert(&pgmap_radix,
@@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
 DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
 static atomic_t devmap_enable;
 
 /*
@@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page)
 	} else if (!count)
 		__put_page(page);
 }
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index 22b6acf1ad63..c6242d8594dc 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -85,9 +85,9 @@ static int rseq_update_cpu_id(struct task_struct *t)
 {
 	u32 cpu_id = raw_smp_processor_id();
 
-	if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+	if (put_user(cpu_id, &t->rseq->cpu_id_start))
 		return -EFAULT;
-	if (__put_user(cpu_id, &t->rseq->cpu_id))
+	if (put_user(cpu_id, &t->rseq->cpu_id))
 		return -EFAULT;
 	trace_rseq_update(t);
 	return 0;
@@ -100,14 +100,14 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 	/*
 	 * Reset cpu_id_start to its initial state (0).
 	 */
-	if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+	if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
 		return -EFAULT;
 	/*
 	 * Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
 	 * in after unregistration can figure out that rseq needs to be
 	 * registered again.
 	 */
-	if (__put_user(cpu_id, &t->rseq->cpu_id))
+	if (put_user(cpu_id, &t->rseq->cpu_id))
 		return -EFAULT;
 	return 0;
 }
@@ -115,29 +115,36 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
 static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 {
 	struct rseq_cs __user *urseq_cs;
-	unsigned long ptr;
+	u64 ptr;
 	u32 __user *usig;
 	u32 sig;
 	int ret;
 
-	ret = __get_user(ptr, &t->rseq->rseq_cs);
-	if (ret)
-		return ret;
+	if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+		return -EFAULT;
 	if (!ptr) {
 		memset(rseq_cs, 0, sizeof(*rseq_cs));
 		return 0;
 	}
-	urseq_cs = (struct rseq_cs __user *)ptr;
+	if (ptr >= TASK_SIZE)
+		return -EINVAL;
+	urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
 	if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
 		return -EFAULT;
-	if (rseq_cs->version > 0)
-		return -EINVAL;
 
+	if (rseq_cs->start_ip >= TASK_SIZE ||
+	    rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+	    rseq_cs->abort_ip >= TASK_SIZE ||
+	    rseq_cs->version > 0)
+		return -EINVAL;
+	/* Check for overflow. */
+	if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+		return -EINVAL;
 	/* Ensure that abort_ip is not in the critical section. */
 	if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
 		return -EINVAL;
 
-	usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+	usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
 	ret = get_user(sig, usig);
 	if (ret)
 		return ret;
@@ -146,7 +153,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
 		printk_ratelimited(KERN_WARNING
 			"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
 			sig, current->rseq_sig, current->pid, usig);
-		return -EPERM;
+		return -EINVAL;
 	}
 	return 0;
 }
@@ -157,7 +164,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
 	int ret;
 
 	/* Get thread flags. */
-	ret = __get_user(flags, &t->rseq->flags);
+	ret = get_user(flags, &t->rseq->flags);
 	if (ret)
 		return ret;
 
@@ -195,9 +202,11 @@ static int clear_rseq_cs(struct task_struct *t)
 	 * of code outside of the rseq assembly block. This performs
 	 * a lazy clear of the rseq_cs field.
 	 *
-	 * Set rseq_cs to NULL with single-copy atomicity.
+	 * Set rseq_cs to NULL.
 	 */
-	return __put_user(0UL, &t->rseq->rseq_cs);
+	if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+		return -EFAULT;
+	return 0;
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78d8facba456..fe365c9a08e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,7 +7,6 @@
  */
 #include "sched.h"
 
-#include <linux/kthread.h>
 #include <linux/nospec.h>
 
 #include <linux/kcov.h>
@@ -2724,28 +2723,20 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		membarrier_mm_sync_core_before_usermode(mm);
 		mmdrop(mm);
 	}
-	if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
-		switch (prev_state) {
-		case TASK_DEAD:
-			if (prev->sched_class->task_dead)
-				prev->sched_class->task_dead(prev);
+	if (unlikely(prev_state == TASK_DEAD)) {
+		if (prev->sched_class->task_dead)
+			prev->sched_class->task_dead(prev);
 
-			/*
-			 * Remove function-return probe instances associated with this
-			 * task and put them back on the free list.
-			 */
-			kprobe_flush_task(prev);
-
-			/* Task is done with its stack. */
-			put_task_stack(prev);
+		/*
+		 * Remove function-return probe instances associated with this
+		 * task and put them back on the free list.
+		 */
+		kprobe_flush_task(prev);
 
-			put_task_struct(prev);
-			break;
+		/* Task is done with its stack. */
+		put_task_stack(prev);
 
-		case TASK_PARKED:
-			kthread_park_complete(prev);
-			break;
-		}
+		put_task_struct(prev);
 	}
 
 	tick_nohz_task_switch();
@@ -3113,7 +3104,9 @@ static void sched_tick_remote(struct work_struct *work)
 	struct tick_work *twork = container_of(dwork, struct tick_work, work);
 	int cpu = twork->cpu;
 	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *curr;
 	struct rq_flags rf;
+	u64 delta;
 
 	/*
 	 * Handle the tick only if it appears the remote CPU is running in full
@@ -3122,24 +3115,28 @@ static void sched_tick_remote(struct work_struct *work)
 	 * statistics and checks timeslices in a time-independent way, regardless
 	 * of when exactly it is running.
 	 */
-	if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
-		struct task_struct *curr;
-		u64 delta;
+	if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+		goto out_requeue;
 
-		rq_lock_irq(rq, &rf);
-		update_rq_clock(rq);
-		curr = rq->curr;
-		delta = rq_clock_task(rq) - curr->se.exec_start;
+	rq_lock_irq(rq, &rf);
+	curr = rq->curr;
+	if (is_idle_task(curr))
+		goto out_unlock;
 
-		/*
-		 * Make sure the next tick runs within a reasonable
-		 * amount of time.
-		 */
-		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
-		curr->sched_class->task_tick(rq, curr, 0);
-		rq_unlock_irq(rq, &rf);
-	}
+	update_rq_clock(rq);
+	delta = rq_clock_task(rq) - curr->se.exec_start;
+
+	/*
+	 * Make sure the next tick runs within a reasonable
+	 * amount of time.
+	 */
+	WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+	curr->sched_class->task_tick(rq, curr, 0);
+
+out_unlock:
+	rq_unlock_irq(rq, &rf);
 
+out_requeue:
 	/*
 	 * Run the remote tick once per second (1Hz). This arbitrary
 	 * frequency is large enough to avoid overload but short enough
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3cde46483f0a..c907fde01eaa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -192,7 +192,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
 
-	if (rq->rt.rt_nr_running)
+	if (rt_rq_is_runnable(&rq->rt))
 		return sg_cpu->max;
 
 	/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fbfc3f1d368a..10c7b51c0d1f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2290,8 +2290,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (task_on_rq_queued(p) && p->dl.dl_runtime)
 		task_non_contending(p);
 
-	if (!task_on_rq_queued(p))
+	if (!task_on_rq_queued(p)) {
+		/*
+		 * Inactive timer is armed. However, p is leaving DEADLINE and
+		 * might migrate away from this rq while continuing to run on
+		 * some other class. We need to remove its contribution from
+		 * this rq running_bw now, or sub_rq_bw (below) will complain.
+		 */
+		if (p->dl.dl_non_contending)
+			sub_running_bw(&p->dl, &rq->dl);
 		sub_rq_bw(&p->dl, &rq->dl);
+	}
 
 	/*
 	 * We cannot use inactive_task_timer() to invoke sub_running_bw()
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1866e64792a7..2f0a0be4d344 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3982,18 +3982,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/*
-	 * Update root cfs_rq's estimated utilization
-	 *
-	 * If *p is the last task then the root cfs_rq's estimated utilization
-	 * of a CPU is 0 by definition.
-	 */
-	ue.enqueued = 0;
-	if (cfs_rq->nr_running) {
-		ue.enqueued  = cfs_rq->avg.util_est.enqueued;
-		ue.enqueued -= min_t(unsigned int, ue.enqueued,
-				     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
-	}
+	/* Update root cfs_rq's estimated utilization */
+	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
+	ue.enqueued -= min_t(unsigned int, ue.enqueued,
+			     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
 
 	/*
@@ -4590,6 +4582,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 	now = sched_clock_cpu(smp_processor_id());
 	cfs_b->runtime = cfs_b->quota;
 	cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+	cfs_b->expires_seq++;
 }
 
 static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4612,6 +4605,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	struct task_group *tg = cfs_rq->tg;
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
 	u64 amount = 0, min_amount, expires;
+	int expires_seq;
 
 	/* note: this is a positive sum as runtime_remaining <= 0 */
 	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4628,6 +4622,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 			cfs_b->idle = 0;
 		}
 	}
+	expires_seq = cfs_b->expires_seq;
 	expires = cfs_b->runtime_expires;
 	raw_spin_unlock(&cfs_b->lock);
 
@@ -4637,8 +4632,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * spread between our sched_clock and the one on which runtime was
 	 * issued.
 	 */
-	if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+	if (cfs_rq->expires_seq != expires_seq) {
+		cfs_rq->expires_seq = expires_seq;
 		cfs_rq->runtime_expires = expires;
+	}
 
 	return cfs_rq->runtime_remaining > 0;
 }
@@ -4664,12 +4661,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * has not truly expired.
 	 *
 	 * Fortunately we can check determine whether this the case by checking
-	 * whether the global deadline has advanced. It is valid to compare
-	 * cfs_b->runtime_expires without any locks since we only care about
-	 * exact equality, so a partial write will still work.
+	 * whether the global deadline(cfs_b->expires_seq) has advanced.
 	 */
-
-	if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+	if (cfs_rq->expires_seq == cfs_b->expires_seq) {
 		/* extend local deadline, drift is bounded above by 2 ticks */
 		cfs_rq->runtime_expires += TICK_NSEC;
 	} else {
@@ -5202,13 +5196,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 
 void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
+	u64 overrun;
+
 	lockdep_assert_held(&cfs_b->lock);
 
-	if (!cfs_b->period_active) {
-		cfs_b->period_active = 1;
-		hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
-		hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
-	}
+	if (cfs_b->period_active)
+		return;
+
+	cfs_b->period_active = 1;
+	overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+	cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
+	cfs_b->expires_seq++;
+	hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 47556b0c9a95..572567078b60 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -508,8 +508,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 
 	rt_se = rt_rq->tg->rt_se[cpu];
 
-	if (!rt_se)
+	if (!rt_se) {
 		dequeue_top_rt_rq(rt_rq);
+		/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+		cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
+	}
 	else if (on_rt_rq(rt_se))
 		dequeue_rt_entity(rt_se, 0);
 }
@@ -1001,8 +1004,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
 	sub_nr_running(rq, rt_rq->rt_nr_running);
 	rt_rq->rt_queued = 0;
 
-	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
-	cpufreq_update_util(rq, 0);
 }
 
 static void
@@ -1014,11 +1015,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq)
 
 	if (rt_rq->rt_queued)
 		return;
-	if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+
+	if (rt_rq_throttled(rt_rq))
 		return;
 
-	add_nr_running(rq, rt_rq->rt_nr_running);
-	rt_rq->rt_queued = 1;
+	if (rt_rq->rt_nr_running) {
+		add_nr_running(rq, rt_rq->rt_nr_running);
+		rt_rq->rt_queued = 1;
+	}
 
 	/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
 	cpufreq_update_util(rq, 0);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6601baf2361c..c7742dcc136c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -334,9 +334,10 @@ struct cfs_bandwidth {
 	u64			runtime;
 	s64			hierarchical_quota;
 	u64			runtime_expires;
+	int			expires_seq;
 
-	int			idle;
-	int			period_active;
+	short			idle;
+	short			period_active;
 	struct hrtimer		period_timer;
 	struct hrtimer		slack_timer;
 	struct list_head	throttled_cfs_rq;
@@ -551,6 +552,7 @@ struct cfs_rq {
 
 #ifdef CONFIG_CFS_BANDWIDTH
 	int			runtime_enabled;
+	int			expires_seq;
 	u64			runtime_expires;
 	s64			runtime_remaining;
 
@@ -609,6 +611,11 @@ struct rt_rq {
 #endif
 };
 
+static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
+{
+	return rt_rq->rt_queued && rt_rq->rt_nr_running;
+}
+
 /* Deadline class' related fields in a runqueue */
 struct dl_rq {
 	/* runqueue is an rbtree, ordered by deadline */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 900dcfee542c..75ffc1d1a2e0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -79,12 +79,16 @@ static void wakeup_softirqd(void)
 
 /*
  * If ksoftirqd is scheduled, we do not want to process pending softirqs
- * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness,
+ * unless we're doing some of the synchronous softirqs.
  */
-static bool ksoftirqd_running(void)
+#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ))
+static bool ksoftirqd_running(unsigned long pending)
 {
 	struct task_struct *tsk = __this_cpu_read(ksoftirqd);
 
+	if (pending & SOFTIRQ_NOW_MASK)
+		return false;
 	return tsk && (tsk->state == TASK_RUNNING);
 }
 
@@ -328,7 +332,7 @@ asmlinkage __visible void do_softirq(void)
 
 	pending = local_softirq_pending();
 
-	if (pending && !ksoftirqd_running())
+	if (pending && !ksoftirqd_running(pending))
 		do_softirq_own_stack();
 
 	local_irq_restore(flags);
@@ -355,7 +359,7 @@ void irq_enter(void)
 
 static inline void invoke_softirq(void)
 {
-	if (ksoftirqd_running())
+	if (ksoftirqd_running(local_softirq_pending()))
 		return;
 
 	if (!force_irqthreads) {
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index f89014a2c238..1ff523dae6e2 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -270,7 +270,11 @@ unlock:
 		goto retry;
 	}
 
-	wake_up_q(&wakeq);
+	if (!err) {
+		preempt_disable();
+		wake_up_q(&wakeq);
+		preempt_enable();
+	}
 
 	return err;
 }
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b7005dd21ec1..14de3727b18e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
 	 */
 	return !curdev ||
 		newdev->rating > curdev->rating ||
-	       (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
-	        !tick_check_percpu(curdev, newdev, smp_processor_id()));
+	       !cpumask_equal(curdev->cpumask, newdev->cpumask);
 }
 
 /*
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index efed9c1cfb7e..caf9cbf35816 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -192,17 +192,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
 	op->saved_func(ip, parent_ip, op, regs);
 }
 
-/**
- * clear_ftrace_function - reset the ftrace function
- *
- * This NULLs the ftrace function and in essence stops
- * tracing.  There may be lag
- */
-void clear_ftrace_function(void)
-{
-	ftrace_trace_function = ftrace_stub;
-}
-
 static void ftrace_sync(struct work_struct *work)
 {
 	/*
@@ -6689,7 +6678,7 @@ void ftrace_kill(void)
 {
 	ftrace_disabled = 1;
 	ftrace_enabled = 0;
-	clear_ftrace_function();
+	ftrace_trace_function = ftrace_stub;
 }
 
 /**
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
 }
 
 /**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+	return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
+/**
  * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
  * @buffer: The ring buffer to stop writes to.
  * @cpu: The CPU buffer to stop
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a0079b4c7a49..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1373,6 +1373,12 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 
 	arch_spin_lock(&tr->max_lock);
 
+	/* Inherit the recordable setting from trace_buffer */
+	if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+		ring_buffer_record_on(tr->max_buffer.buffer);
+	else
+		ring_buffer_record_off(tr->max_buffer.buffer);
+
 	swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
 
 	__update_max_tr(tr, tsk, cpu);
@@ -2953,6 +2959,7 @@ out_nobuffer:
 }
 EXPORT_SYMBOL_GPL(trace_vbprintk);
 
+__printf(3, 0)
 static int
 __trace_array_vprintk(struct ring_buffer *buffer,
 		      unsigned long ip, const char *fmt, va_list args)
@@ -3007,12 +3014,14 @@ out_nobuffer:
 	return len;
 }
 
+__printf(3, 0)
 int trace_array_vprintk(struct trace_array *tr,
 			unsigned long ip, const char *fmt, va_list args)
 {
 	return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
 }
 
+__printf(3, 0)
 int trace_array_printk(struct trace_array *tr,
 		       unsigned long ip, const char *fmt, ...)
 {
@@ -3028,6 +3037,7 @@ int trace_array_printk(struct trace_array *tr,
 	return ret;
 }
 
+__printf(3, 4)
 int trace_array_printk_buf(struct ring_buffer *buffer,
 			   unsigned long ip, const char *fmt, ...)
 {
@@ -3043,6 +3053,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
 	return ret;
 }
 
+__printf(2, 0)
 int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
 {
 	return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -3360,8 +3371,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m,
 
 	print_event_info(buf, m);
 
-	seq_printf(m, "#           TASK-PID   CPU#   %s  TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
-	seq_printf(m, "#              | |       |    %s     |         |\n",	 tgid ? "  |      " : "");
+	seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  FUNCTION\n", tgid ? "TGID     " : "");
+	seq_printf(m, "#              | |     %s    |       |         |\n",	 tgid ? "  |      " : "");
 }
 
 static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
@@ -3381,9 +3392,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
 		   tgid ? tgid_space : space);
 	seq_printf(m, "#                          %s||| /     delay\n",
 		   tgid ? tgid_space : space);
-	seq_printf(m, "#           TASK-PID   CPU#%s||||    TIMESTAMP  FUNCTION\n",
+	seq_printf(m, "#           TASK-PID %sCPU#  ||||    TIMESTAMP  FUNCTION\n",
 		   tgid ? "   TGID   " : space);
-	seq_printf(m, "#              | |       | %s||||       |         |\n",
+	seq_printf(m, "#              | |   %s  |   ||||       |         |\n",
 		   tgid ? "     |    " : space);
 }
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 630c5a24b2b2..f8f86231ad90 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -583,9 +583,7 @@ static __always_inline void trace_clear_recursion(int bit)
 static inline struct ring_buffer_iter *
 trace_buffer_iter(struct trace_iterator *iter, int cpu)
 {
-	if (iter->buffer_iter && iter->buffer_iter[cpu])
-		return iter->buffer_iter[cpu];
-	return NULL;
+	return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL;
 }
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0dceb77d1d42..893a206bcba4 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1701,6 +1701,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
  * @filter_str: filter string
  * @set_str: remember @filter_str and enable detailed error in filter
  * @filterp: out param for created filter (always updated on return)
+ *           Must be a pointer that references a NULL pointer.
  *
  * Creates a filter for @call with @filter_str.  If @set_str is %true,
  * @filter_str is copied and recorded in the new filter.
@@ -1718,6 +1719,10 @@ static int create_filter(struct trace_event_call *call,
 	struct filter_parse_error *pe = NULL;
 	int err;
 
+	/* filterp must point to NULL */
+	if (WARN_ON(*filterp))
+		*filterp = NULL;
+
 	err = create_filter_start(filter_string, set_str, &pe, filterp);
 	if (err)
 		return err;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 046c716a6536..aae18af94c94 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -393,7 +393,7 @@ static void hist_err_event(char *str, char *system, char *event, char *var)
 	else if (system)
 		snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
 	else
-		strncpy(err, var, MAX_FILTER_STR_VAL);
+		strscpy(err, var, MAX_FILTER_STR_VAL);
 
 	hist_err(str, err);
 }
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d18249683682..5dea177cef53 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops,
 		goto out_free;
 
  out_reg:
+	/* Up the trigger_data count to make sure reg doesn't free it on failure */
+	event_trigger_init(trigger_ops, trigger_data);
 	ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
 	/*
 	 * The above returns on success the # of functions enabled,
@@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops,
 	 * Consider no functions a failure too.
 	 */
 	if (!ret) {
+		cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
 		ret = -ENOENT;
-		goto out_free;
-	} else if (ret < 0)
-		goto out_free;
-	ret = 0;
+	} else if (ret > 0)
+		ret = 0;
+
+	/* Down the counter of trigger_data or free it if not used anymore */
+	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
 
@@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 		goto out;
 	}
 
+	/* Up the trigger_data count to make sure nothing frees it on failure */
+	event_trigger_init(trigger_ops, trigger_data);
+
 	if (trigger) {
 		number = strsep(&trigger, ":");
 
@@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
 		goto out_disable;
 	/* Just return zero, not the number of enabled functions */
 	ret = 0;
+	event_trigger_free(trigger_ops, trigger_data);
  out:
 	return ret;
 
@@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
  out_free:
 	if (cmd_ops->set_filter)
 		cmd_ops->set_filter(NULL, trigger_data, NULL);
-	kfree(trigger_data);
+	event_trigger_free(trigger_ops, trigger_data);
 	kfree(enable_data);
 	goto out;
 }
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 23c0b0cb5fb9..169b3c44ee97 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -831,6 +831,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 	struct ftrace_graph_ret *graph_ret;
 	struct ftrace_graph_ent *call;
 	unsigned long long duration;
+	int cpu = iter->cpu;
 	int i;
 
 	graph_ret = &ret_entry->ret;
@@ -839,7 +840,6 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 	if (data) {
 		struct fgraph_cpu_data *cpu_data;
-		int cpu = iter->cpu;
 
 		cpu_data = per_cpu_ptr(data->cpu_data, cpu);
 
@@ -869,6 +869,9 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 	trace_seq_printf(s, "%ps();\n", (void *)call->func);
 
+	print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
+			cpu, iter->ent->pid, flags);
+
 	return trace_handle_return(s);
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index daa81571b22a..6b71860f3998 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
 static int
 enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 {
+	struct event_file_link *link = NULL;
 	int ret = 0;
 
 	if (file) {
-		struct event_file_link *link;
-
 		link = kmalloc(sizeof(*link), GFP_KERNEL);
 		if (!link) {
 			ret = -ENOMEM;
@@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
 		else
 			ret = enable_kprobe(&tk->rp.kp);
 	}
+
+	if (ret) {
+		if (file) {
+			/* Notice the if is true on not WARN() */
+			if (!WARN_ON_ONCE(!link))
+				list_del_rcu(&link->list);
+			kfree(link);
+			tk->tp.flags &= ~TP_FLAG_TRACE;
+		} else {
+			tk->tp.flags &= ~TP_FLAG_PROFILE;
+		}
+	}
  out:
 	return ret;
 }
@@ -1480,8 +1491,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 	}
 
 	ret = __register_trace_kprobe(tk);
-	if (ret < 0)
+	if (ret < 0) {
+		kfree(tk->tp.call.print_fmt);
 		goto error;
+	}
 
 	return &tk->tp.call;
 error:
@@ -1501,6 +1514,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
 	}
 
 	__unregister_trace_kprobe(tk);
+
+	kfree(tk->tp.call.print_fmt);
 	free_trace_kprobe(tk);
 }
 #endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 90db994ac900..1c8e30fda46a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter)
 
 	trace_find_cmdline(entry->pid, comm);
 
-	trace_seq_printf(s, "%16s-%-5d [%03d] ",
-			       comm, entry->pid, iter->cpu);
+	trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
 
 	if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
 		unsigned int tgid = trace_find_tgid(entry->pid);
@@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter)
 			trace_seq_printf(s, "(%5d) ", tgid);
 	}
 
+	trace_seq_printf(s, "[%03d] ", iter->cpu);
+
 	if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
 		trace_print_lat_fmt(s, entry);
 
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index c253c1b46c6b..befb127507c0 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -5,7 +5,7 @@ if HAVE_ARCH_KASAN
 
 config KASAN
 	bool "KASan: runtime memory debugger"
-	depends on SLUB || (SLAB && !DEBUG_SLAB)
+	depends on (SLUB && SYSFS) || (SLAB && !DEBUG_SLAB)
 	select SLUB_DEBUG if SLUB
 	select CONSTRUCTORS
 	select STACKDEPOT
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 7e43cd54c84c..8be175df3075 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -596,15 +596,70 @@ static unsigned long memcpy_mcsafe_to_page(struct page *page, size_t offset,
 	return ret;
 }
 
+static size_t copy_pipe_to_iter_mcsafe(const void *addr, size_t bytes,
+				struct iov_iter *i)
+{
+	struct pipe_inode_info *pipe = i->pipe;
+	size_t n, off, xfer = 0;
+	int idx;
+
+	if (!sanity(i))
+		return 0;
+
+	bytes = n = push_pipe(i, bytes, &idx, &off);
+	if (unlikely(!n))
+		return 0;
+	for ( ; n; idx = next_idx(idx, pipe), off = 0) {
+		size_t chunk = min_t(size_t, n, PAGE_SIZE - off);
+		unsigned long rem;
+
+		rem = memcpy_mcsafe_to_page(pipe->bufs[idx].page, off, addr,
+				chunk);
+		i->idx = idx;
+		i->iov_offset = off + chunk - rem;
+		xfer += chunk - rem;
+		if (rem)
+			break;
+		n -= chunk;
+		addr += chunk;
+	}
+	i->count -= xfer;
+	return xfer;
+}
+
+/**
+ * _copy_to_iter_mcsafe - copy to user with source-read error exception handling
+ * @addr: source kernel address
+ * @bytes: total transfer length
+ * @iter: destination iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_to_iter() for protecting read/write to persistent memory.
+ * Unless / until an architecture can guarantee identical performance
+ * between _copy_to_iter_mcsafe() and _copy_to_iter() it would be a
+ * performance regression to switch more users to the mcsafe version.
+ *
+ * Otherwise, the main differences between this and typical _copy_to_iter().
+ *
+ * * Typical tail/residue handling after a fault retries the copy
+ *   byte-by-byte until the fault happens again. Re-triggering machine
+ *   checks is potentially fatal so the implementation uses source
+ *   alignment and poison alignment assumptions to avoid re-triggering
+ *   hardware exceptions.
+ *
+ * * ITER_KVEC, ITER_PIPE, and ITER_BVEC can return short copies.
+ *   Compare to copy_to_iter() where only ITER_IOVEC attempts might return
+ *   a short copy.
+ *
+ * See MCSAFE_TEST for self-test.
+ */
 size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i)
 {
 	const char *from = addr;
 	unsigned long rem, curr_addr, s_addr = (unsigned long) addr;
 
-	if (unlikely(i->type & ITER_PIPE)) {
-		WARN_ON(1);
-		return 0;
-	}
+	if (unlikely(i->type & ITER_PIPE))
+		return copy_pipe_to_iter_mcsafe(addr, bytes, i);
 	if (iter_is_iovec(i))
 		might_fault();
 	iterate_and_advance(i, bytes, v,
@@ -701,6 +756,20 @@ size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i)
 EXPORT_SYMBOL(_copy_from_iter_nocache);
 
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
+/**
+ * _copy_from_iter_flushcache - write destination through cpu cache
+ * @addr: destination kernel address
+ * @bytes: total transfer length
+ * @iter: source iterator
+ *
+ * The pmem driver arranges for filesystem-dax to use this facility via
+ * dax_copy_from_iter() for ensuring that writes to persistent memory
+ * are flushed through the CPU cache. It is differentiated from
+ * _copy_from_iter_nocache() in that guarantees all data is flushed for
+ * all iterator types. The _copy_from_iter_nocache() only attempts to
+ * bypass the cache for the ITER_IOVEC case, and on some archs may use
+ * instructions that strand dirty-data in the cache.
+ */
 size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
 {
 	char *to = addr;
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9427b5766134..e5c8586cf717 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -774,7 +774,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter)
 				skip++;
 				if (list == iter->list) {
 					iter->p = p;
-					skip = skip;
+					iter->skip = skip;
 					goto found;
 				}
 			}
@@ -964,8 +964,16 @@ EXPORT_SYMBOL_GPL(rhashtable_walk_stop);
 
 static size_t rounded_hashtable_size(const struct rhashtable_params *params)
 {
-	return max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
-		   (unsigned long)params->min_size);
+	size_t retsize;
+
+	if (params->nelem_hint)
+		retsize = max(roundup_pow_of_two(params->nelem_hint * 4 / 3),
+			      (unsigned long)params->min_size);
+	else
+		retsize = max(HASH_DEFAULT_SIZE,
+			      (unsigned long)params->min_size);
+
+	return retsize;
 }
 
 static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
@@ -1022,8 +1030,6 @@ int rhashtable_init(struct rhashtable *ht,
 	struct bucket_table *tbl;
 	size_t size;
 
-	size = HASH_DEFAULT_SIZE;
-
 	if ((!params->key_len && !params->obj_hashfn) ||
 	    (params->obj_hashfn && !params->obj_cmpfn))
 		return -EINVAL;
@@ -1050,8 +1056,7 @@ int rhashtable_init(struct rhashtable *ht,
 
 	ht->p.min_size = max_t(u16, ht->p.min_size, HASH_MIN_SIZE);
 
-	if (params->nelem_hint)
-		size = rounded_hashtable_size(&ht->p);
+	size = rounded_hashtable_size(&ht->p);
 
 	if (params->locks_mul)
 		ht->p.locks_mul = roundup_pow_of_two(params->locks_mul);
@@ -1143,13 +1148,14 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 				 void (*free_fn)(void *ptr, void *arg),
 				 void *arg)
 {
-	struct bucket_table *tbl;
+	struct bucket_table *tbl, *next_tbl;
 	unsigned int i;
 
 	cancel_work_sync(&ht->run_work);
 
 	mutex_lock(&ht->mutex);
 	tbl = rht_dereference(ht->tbl, ht);
+restart:
 	if (free_fn) {
 		for (i = 0; i < tbl->size; i++) {
 			struct rhash_head *pos, *next;
@@ -1166,7 +1172,12 @@ void rhashtable_free_and_destroy(struct rhashtable *ht,
 		}
 	}
 
+	next_tbl = rht_dereference(tbl->future_tbl, ht);
 	bucket_table_free(tbl);
+	if (next_tbl) {
+		tbl = next_tbl;
+		goto restart;
+	}
 	mutex_unlock(&ht->mutex);
 }
 EXPORT_SYMBOL_GPL(rhashtable_free_and_destroy);
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index 60aedc879361..08d3d59dca17 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -5282,21 +5282,31 @@ static struct bpf_test tests[] = {
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Ctx heavy transformations",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ },
 		{
 			{  1, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) },
 			{ 10, !!(SKB_VLAN_TCI & VLAN_TAG_PRESENT) }
 		},
 		.fill_helper = bpf_fill_maxinsns6,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Call heavy transformations",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_NO_DATA | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC | FLAG_NO_DATA,
+#endif
 		{ },
 		{ { 1, 0 }, { 10, 0 } },
 		.fill_helper = bpf_fill_maxinsns7,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{	/* Mainly checking JIT here. */
 		"BPF_MAXINSNS: Jump heavy test",
@@ -5347,18 +5357,28 @@ static struct bpf_test tests[] = {
 	{
 		"BPF_MAXINSNS: exec all MSH",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ 0xfa, 0xfb, 0xfc, 0xfd, },
 		{ { 4, 0xababab83 } },
 		.fill_helper = bpf_fill_maxinsns13,
+		.expected_errcode = -ENOTSUPP,
 	},
 	{
 		"BPF_MAXINSNS: ld_abs+get_processor_id",
 		{ },
+#if defined(CONFIG_BPF_JIT_ALWAYS_ON) && defined(CONFIG_S390)
+		CLASSIC | FLAG_EXPECTED_FAIL,
+#else
 		CLASSIC,
+#endif
 		{ },
 		{ { 1, 0xbee } },
 		.fill_helper = bpf_fill_ld_abs_get_processor_id,
+		.expected_errcode = -ENOTSUPP,
 	},
 	/*
 	 * LD_IND / LD_ABS on fragmented SKBs
diff --git a/mm/debug.c b/mm/debug.c
index 56e2d9125ea5..38c926520c97 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -43,12 +43,25 @@ const struct trace_print_flags vmaflag_names[] = {
 
 void __dump_page(struct page *page, const char *reason)
 {
+	bool page_poisoned = PagePoisoned(page);
+	int mapcount;
+
+	/*
+	 * If struct page is poisoned don't access Page*() functions as that
+	 * leads to recursive loop. Page*() check for poisoned pages, and calls
+	 * dump_page() when detected.
+	 */
+	if (page_poisoned) {
+		pr_emerg("page:%px is uninitialized and poisoned", page);
+		goto hex_only;
+	}
+
 	/*
 	 * Avoid VM_BUG_ON() in page_mapcount().
 	 * page->_mapcount space in struct page is used by sl[aou]b pages to
 	 * encode own info.
 	 */
-	int mapcount = PageSlab(page) ? 0 : page_mapcount(page);
+	mapcount = PageSlab(page) ? 0 : page_mapcount(page);
 
 	pr_emerg("page:%px count:%d mapcount:%d mapping:%px index:%#lx",
 		  page, page_ref_count(page), mapcount,
@@ -60,6 +73,7 @@ void __dump_page(struct page *page, const char *reason)
 
 	pr_emerg("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 
+hex_only:
 	print_hex_dump(KERN_ALERT, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
 			sizeof(struct page), false);
@@ -68,7 +82,7 @@ void __dump_page(struct page *page, const char *reason)
 		pr_alert("page dumped because: %s\n", reason);
 
 #ifdef CONFIG_MEMCG
-	if (page->mem_cgroup)
+	if (!page_poisoned && page->mem_cgroup)
 		pr_alert("page->mem_cgroup:%px\n", page->mem_cgroup);
 #endif
 }
diff --git a/mm/gup.c b/mm/gup.c
index b70d7ba7cc13..fc5f98069f4e 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1238,8 +1238,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	int locked = 0;
 	long ret = 0;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 
 	for (nstart = start; nstart < end; nstart = nend) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1cd7c1a57a14..25346bd99364 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2084,6 +2084,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		if (vma_is_dax(vma))
 			return;
 		page = pmd_page(_pmd);
+		if (!PageDirty(page) && pmd_dirty(_pmd))
+			set_page_dirty(page);
 		if (!PageReferenced(page) && pmd_young(_pmd))
 			SetPageReferenced(page);
 		page_remove_rmap(page, true);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3612fbb32e9d..039ddbc574e9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2163,6 +2163,7 @@ static void __init gather_bootmem_prealloc(void)
 		 */
 		if (hstate_is_gigantic(h))
 			adjust_managed_page_count(page, 1 << h->order);
+		cond_resched();
 	}
 }
 
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index f185455b3406..c3bd5209da38 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -619,12 +619,13 @@ void kasan_kfree_large(void *ptr, unsigned long ip)
 int kasan_module_alloc(void *addr, size_t size)
 {
 	void *ret;
+	size_t scaled_size;
 	size_t shadow_size;
 	unsigned long shadow_start;
 
 	shadow_start = (unsigned long)kasan_mem_to_shadow(addr);
-	shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT,
-			PAGE_SIZE);
+	scaled_size = (size + KASAN_SHADOW_MASK) >> KASAN_SHADOW_SCALE_SHIFT;
+	shadow_size = round_up(scaled_size, PAGE_SIZE);
 
 	if (WARN_ON(!PAGE_ALIGNED(shadow_start)))
 		return -EINVAL;
diff --git a/mm/memblock.c b/mm/memblock.c
index 03d48d8835ba..4b5d245fafc1 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -20,6 +20,7 @@
 #include <linux/kmemleak.h>
 #include <linux/seq_file.h>
 #include <linux/memblock.h>
+#include <linux/bootmem.h>
 
 #include <asm/sections.h>
 #include <linux/io.h>
@@ -227,7 +228,8 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 		 * so we use WARN_ONCE() here to see the stack trace if
 		 * fail happens.
 		 */
-		WARN_ONCE(1, "memblock: bottom-up allocation failed, memory hotunplug may be affected\n");
+		WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE),
+			  "memblock: bottom-up allocation failed, memory hotremove may be affected\n");
 	}
 
 	return __memblock_find_range_top_down(start, end, size, align, nid,
@@ -1224,6 +1226,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
 	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
+#if defined(CONFIG_NO_BOOTMEM)
 /**
  * memblock_virt_alloc_internal - allocate boot memory block
  * @size: size of memory block to be allocated in bytes
@@ -1431,6 +1434,7 @@ void * __init memblock_virt_alloc_try_nid(
 	      (u64)max_addr);
 	return NULL;
 }
+#endif
 
 /**
  * __memblock_free_early - free boot memory block
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6f0d5ef320a..8c0280b3143e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -850,7 +850,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	int nid;
 	int i;
 
-	while ((memcg = parent_mem_cgroup(memcg))) {
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
 		for_each_node(nid) {
 			mz = mem_cgroup_nodeinfo(memcg, nid);
 			for (i = 0; i <= DEF_PRIORITY; i++) {
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 9ac49ef17b4e..01f1a14facc4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2505,6 +2505,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 
 		/* Create pseudo-vma that contains just the policy */
 		memset(&pvma, 0, sizeof(struct vm_area_struct));
+		vma_init(&pvma, NULL);
 		pvma.vm_end = TASK_SIZE;	/* policy covers entire file */
 		mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
 
diff --git a/mm/mmap.c b/mm/mmap.c
index d1eb87ef4b1a..17bbf4d3e24f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -182,12 +182,12 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	mpol_put(vma_policy(vma));
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return next;
 }
 
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf);
-
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags,
+		struct list_head *uf);
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long retval;
@@ -245,7 +245,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 		goto out;
 
 	/* Ok, looks good - let it rip. */
-	if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
+	if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
 		goto out;
 
 set_brk:
@@ -911,7 +911,7 @@ again:
 			anon_vma_merge(vma, next);
 		mm->map_count--;
 		mpol_put(vma_policy(next));
-		kmem_cache_free(vm_area_cachep, next);
+		vm_area_free(next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
 		 * we must remove another next too. It would clutter
@@ -1729,19 +1729,17 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 	 * specific mapper. the address has already been validated, but
 	 * not unmapped, but the maps are removed from the list.
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		error = -ENOMEM;
 		goto unacct_error;
 	}
 
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_flags = vm_flags;
 	vma->vm_page_prot = vm_get_page_prot(vm_flags);
 	vma->vm_pgoff = pgoff;
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 
 	if (file) {
 		if (vm_flags & VM_DENYWRITE) {
@@ -1780,6 +1778,8 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		error = shmem_zero_setup(vma);
 		if (error)
 			goto free_vma;
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	vma_link(mm, vma, prev, rb_link, rb_parent);
@@ -1832,7 +1832,7 @@ allow_write_and_free_vma:
 	if (vm_flags & VM_DENYWRITE)
 		allow_write_access(file);
 free_vma:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 unacct_error:
 	if (charged)
 		vm_unacct_memory(charged);
@@ -2620,15 +2620,10 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 			return err;
 	}
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new)
 		return -ENOMEM;
 
-	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
-
-	INIT_LIST_HEAD(&new->anon_vma_chain);
-
 	if (new_below)
 		new->vm_end = addr;
 	else {
@@ -2669,7 +2664,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  out_free_mpol:
 	mpol_put(vma_policy(new));
  out_free_vma:
-	kmem_cache_free(vm_area_cachep, new);
+	vm_area_free(new);
 	return err;
 }
 
@@ -2929,21 +2924,14 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf)
+static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long flags, struct list_head *uf)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(request);
-	if (len < request)
-		return -ENOMEM;
-	if (!len)
-		return 0;
-
 	/* Until we need other flags, refuse anything except VM_EXEC. */
 	if ((flags & (~VM_EXEC)) != 0)
 		return -EINVAL;
@@ -2991,14 +2979,13 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
 	/*
 	 * create a vma struct for an anonymous mapping
 	 */
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (!vma) {
 		vm_unacct_memory(len >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
+	vma_set_anonymous(vma);
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 	vma->vm_pgoff = pgoff;
@@ -3015,18 +3002,20 @@ out:
 	return 0;
 }
 
-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
-{
-	return do_brk_flags(addr, len, 0, uf);
-}
-
-int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
+int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
+	unsigned long len;
 	int ret;
 	bool populate;
 	LIST_HEAD(uf);
 
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
+	if (!len)
+		return 0;
+
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
@@ -3207,16 +3196,14 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 		}
 		*need_rmap_locks = (new_vma->vm_pgoff <= vma->vm_pgoff);
 	} else {
-		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+		new_vma = vm_area_dup(vma);
 		if (!new_vma)
 			goto out;
-		*new_vma = *vma;
 		new_vma->vm_start = addr;
 		new_vma->vm_end = addr + len;
 		new_vma->vm_pgoff = pgoff;
 		if (vma_dup_policy(vma, new_vma))
 			goto out_free_vma;
-		INIT_LIST_HEAD(&new_vma->anon_vma_chain);
 		if (anon_vma_clone(new_vma, vma))
 			goto out_free_mempol;
 		if (new_vma->vm_file)
@@ -3231,7 +3218,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
 out_free_mempol:
 	mpol_put(vma_policy(new_vma));
 out_free_vma:
-	kmem_cache_free(vm_area_cachep, new_vma);
+	vm_area_free(new_vma);
 out:
 	return NULL;
 }
@@ -3355,12 +3342,10 @@ static struct vm_area_struct *__install_special_mapping(
 	int ret;
 	struct vm_area_struct *vma;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(mm);
 	if (unlikely(vma == NULL))
 		return ERR_PTR(-ENOMEM);
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma->vm_mm = mm;
 	vma->vm_start = addr;
 	vma->vm_end = addr + len;
 
@@ -3381,7 +3366,7 @@ static struct vm_area_struct *__install_special_mapping(
 	return vma;
 
 out:
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ERR_PTR(ret);
 }
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 4452d8bd9ae4..9fc9e43335b6 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -769,7 +769,7 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	put_nommu_region(vma->vm_region);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 }
 
 /*
@@ -1145,6 +1145,8 @@ static int do_mmap_private(struct vm_area_struct *vma,
 		if (ret < len)
 			memset(base + ret, 0, len - ret);
 
+	} else {
+		vma_set_anonymous(vma);
 	}
 
 	return 0;
@@ -1204,7 +1206,7 @@ unsigned long do_mmap(struct file *file,
 	if (!region)
 		goto error_getting_region;
 
-	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	vma = vm_area_alloc(current->mm);
 	if (!vma)
 		goto error_getting_vma;
 
@@ -1212,7 +1214,6 @@ unsigned long do_mmap(struct file *file,
 	region->vm_flags = vm_flags;
 	region->vm_pgoff = pgoff;
 
-	INIT_LIST_HEAD(&vma->anon_vma_chain);
 	vma->vm_flags = vm_flags;
 	vma->vm_pgoff = pgoff;
 
@@ -1368,7 +1369,7 @@ error:
 	kmem_cache_free(vm_region_jar, region);
 	if (vma->vm_file)
 		fput(vma->vm_file);
-	kmem_cache_free(vm_area_cachep, vma);
+	vm_area_free(vma);
 	return ret;
 
 sharing_violation:
@@ -1469,14 +1470,13 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!region)
 		return -ENOMEM;
 
-	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	new = vm_area_dup(vma);
 	if (!new) {
 		kmem_cache_free(vm_region_jar, region);
 		return -ENOMEM;
 	}
 
 	/* most fields are the same, copy all, and then fixup */
-	*new = *vma;
 	*region = *vma->vm_region;
 	new->vm_region = region;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..a790ef4be74e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6383,7 +6383,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
 	free_area_init_core(pgdat);
 }
 
-#ifdef CONFIG_HAVE_MEMBLOCK
+#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP)
 /*
  * Only struct pages that are backed by physical memory are zeroed and
  * initialized by going through __init_single_page(). But, there are some
@@ -6421,7 +6421,7 @@ void __paginginit zero_resv_unavail(void)
 	if (pgcnt)
 		pr_info("Reserved but unavailable: %lld pages", pgcnt);
 }
-#endif /* CONFIG_HAVE_MEMBLOCK */
+#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 
@@ -6847,6 +6847,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
+	zero_resv_unavail();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid, NULL,
@@ -6857,7 +6858,6 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
 			node_set_state(nid, N_MEMORY);
 		check_for_memory(pgdat, nid);
 	}
-	zero_resv_unavail();
 }
 
 static int __init cmdline_parse_core(char *p, unsigned long *core,
@@ -7033,9 +7033,9 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
 
 void __init free_area_init(unsigned long *zones_size)
 {
+	zero_resv_unavail();
 	free_area_init_node(0, zones_size,
 			__pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
-	zero_resv_unavail();
 }
 
 static int page_alloc_cpu_dead(unsigned int cpu)
diff --git a/mm/rmap.c b/mm/rmap.c
index 6db729dc4c50..eb477809a5c0 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -64,6 +64,7 @@
 #include <linux/backing-dev.h>
 #include <linux/page_idle.h>
 #include <linux/memremap.h>
+#include <linux/userfaultfd_k.h>
 
 #include <asm/tlbflush.h>
 
@@ -1481,11 +1482,16 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				set_pte_at(mm, address, pvmw.pte, pteval);
 			}
 
-		} else if (pte_unused(pteval)) {
+		} else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
 			/*
 			 * The guest indicated that the page content is of no
 			 * interest anymore. Simply discard the pte, vmscan
 			 * will take care of the rest.
+			 * A future reference will then fault in a new zero
+			 * page. When userfaultfd is active, we must not drop
+			 * this page though, as its main user (postcopy
+			 * migration) will not expect userfaults on already
+			 * copied pages.
 			 */
 			dec_mm_counter(mm, mm_counter(page));
 			/* We have to invalidate as we cleared the pte */
diff --git a/mm/shmem.c b/mm/shmem.c
index 2cab84403055..41b9bbf24e16 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1421,6 +1421,7 @@ static void shmem_pseudo_vma_init(struct vm_area_struct *vma,
 {
 	/* Create a pseudo vma that just contains the policy */
 	memset(vma, 0, sizeof(*vma));
+	vma_init(vma, NULL);
 	/* Bias interleave by inode number to distribute better across nodes */
 	vma->vm_pgoff = index + info->vfs_inode.i_ino;
 	vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index);
diff --git a/mm/zswap.c b/mm/zswap.c
index 7d34e69507e3..cd91fd9d96b8 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1026,6 +1026,15 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
 			ret = -ENOMEM;
 			goto reject;
 		}
+
+		/* A second zswap_is_full() check after
+		 * zswap_shrink() to make sure it's now
+		 * under the max_pool_percent
+		 */
+		if (zswap_is_full()) {
+			ret = -ENOMEM;
+			goto reject;
+		}
 	}
 
 	/* allocate entry */
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 73a65789271b..8ccee3d01822 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -693,7 +693,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/9p/client.c b/net/9p/client.c
index 18c5271910dc..5c1343195292 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -225,7 +225,8 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 	}
 
 free_and_return:
-	v9fs_put_trans(clnt->trans_mod);
+	if (ret)
+		v9fs_put_trans(clnt->trans_mod);
 	kfree(tmp_options);
 	return ret;
 }
diff --git a/net/Makefile b/net/Makefile
index 13ec0d5415c7..bdaf53925acd 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -20,11 +20,7 @@ obj-$(CONFIG_TLS)		+= tls/
 obj-$(CONFIG_XFRM)		+= xfrm/
 obj-$(CONFIG_UNIX)		+= unix/
 obj-$(CONFIG_NET)		+= ipv6/
-ifneq ($(CC_CAN_LINK),y)
-$(warning CC cannot link executables. Skipping bpfilter.)
-else
 obj-$(CONFIG_BPFILTER)		+= bpfilter/
-endif
 obj-$(CONFIG_PACKET)		+= packet/
 obj-$(CONFIG_NET_KEY)		+= key/
 obj-$(CONFIG_BRIDGE)		+= bridge/
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index be09a9883825..73bf6a93a3cf 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -2732,7 +2732,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 {
 	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	struct batadv_neigh_node *router;
-	struct batadv_gw_node *curr_gw;
+	struct batadv_gw_node *curr_gw = NULL;
 	int ret = 0;
 	void *hdr;
 
@@ -2780,6 +2780,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 	ret = 0;
 
 out:
+	if (curr_gw)
+		batadv_gw_node_put(curr_gw);
 	if (router_ifinfo)
 		batadv_neigh_ifinfo_put(router_ifinfo);
 	if (router)
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index ec93337ee259..6baec4e68898 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -927,7 +927,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 {
 	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
 	struct batadv_neigh_node *router;
-	struct batadv_gw_node *curr_gw;
+	struct batadv_gw_node *curr_gw = NULL;
 	int ret = 0;
 	void *hdr;
 
@@ -995,6 +995,8 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
 	ret = 0;
 
 out:
+	if (curr_gw)
+		batadv_gw_node_put(curr_gw);
 	if (router_ifinfo)
 		batadv_neigh_ifinfo_put(router_ifinfo);
 	if (router)
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 4229b01ac7b5..87479c60670e 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -19,6 +19,7 @@
 #include "debugfs.h"
 #include "main.h"
 
+#include <linux/dcache.h>
 #include <linux/debugfs.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -344,6 +345,25 @@ out:
 }
 
 /**
+ * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif
+ * @hard_iface: hard interface which was renamed
+ */
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
+{
+	const char *name = hard_iface->net_dev->name;
+	struct dentry *dir;
+	struct dentry *d;
+
+	dir = hard_iface->debug_dir;
+	if (!dir)
+		return;
+
+	d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
+	if (!d)
+		pr_err("Can't rename debugfs dir to %s\n", name);
+}
+
+/**
  * batadv_debugfs_del_hardif() - delete the base directory for a hard interface
  *  in debugfs.
  * @hard_iface: hard interface which is deleted.
@@ -414,6 +434,26 @@ out:
 }
 
 /**
+ * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif
+ * @dev: net_device which was renamed
+ */
+void batadv_debugfs_rename_meshif(struct net_device *dev)
+{
+	struct batadv_priv *bat_priv = netdev_priv(dev);
+	const char *name = dev->name;
+	struct dentry *dir;
+	struct dentry *d;
+
+	dir = bat_priv->debug_dir;
+	if (!dir)
+		return;
+
+	d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
+	if (!d)
+		pr_err("Can't rename debugfs dir to %s\n", name);
+}
+
+/**
  * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries
  * @dev: netdev struct of the soft interface
  */
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
index 37b069698b04..08a592ffbee5 100644
--- a/net/batman-adv/debugfs.h
+++ b/net/batman-adv/debugfs.h
@@ -30,8 +30,10 @@ struct net_device;
 void batadv_debugfs_init(void);
 void batadv_debugfs_destroy(void);
 int batadv_debugfs_add_meshif(struct net_device *dev);
+void batadv_debugfs_rename_meshif(struct net_device *dev);
 void batadv_debugfs_del_meshif(struct net_device *dev);
 int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface);
 void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
 
 #else
@@ -49,6 +51,10 @@ static inline int batadv_debugfs_add_meshif(struct net_device *dev)
 	return 0;
 }
 
+static inline void batadv_debugfs_rename_meshif(struct net_device *dev)
+{
+}
+
 static inline void batadv_debugfs_del_meshif(struct net_device *dev)
 {
 }
@@ -60,6 +66,11 @@ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
 }
 
 static inline
+void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
+{
+}
+
+static inline
 void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
 {
 }
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index c405d15befd6..2f0d42f2f913 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -989,6 +989,32 @@ void batadv_hardif_remove_interfaces(void)
 	rtnl_unlock();
 }
 
+/**
+ * batadv_hard_if_event_softif() - Handle events for soft interfaces
+ * @event: NETDEV_* event to handle
+ * @net_dev: net_device which generated an event
+ *
+ * Return: NOTIFY_* result
+ */
+static int batadv_hard_if_event_softif(unsigned long event,
+				       struct net_device *net_dev)
+{
+	struct batadv_priv *bat_priv;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		batadv_sysfs_add_meshif(net_dev);
+		bat_priv = netdev_priv(net_dev);
+		batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
+		break;
+	case NETDEV_CHANGENAME:
+		batadv_debugfs_rename_meshif(net_dev);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
 static int batadv_hard_if_event(struct notifier_block *this,
 				unsigned long event, void *ptr)
 {
@@ -997,12 +1023,8 @@ static int batadv_hard_if_event(struct notifier_block *this,
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_priv *bat_priv;
 
-	if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) {
-		batadv_sysfs_add_meshif(net_dev);
-		bat_priv = netdev_priv(net_dev);
-		batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
-		return NOTIFY_DONE;
-	}
+	if (batadv_softif_is_valid(net_dev))
+		return batadv_hard_if_event_softif(event, net_dev);
 
 	hard_iface = batadv_hardif_get_by_netdev(net_dev);
 	if (!hard_iface && (event == NETDEV_REGISTER ||
@@ -1051,6 +1073,9 @@ static int batadv_hard_if_event(struct notifier_block *this,
 		if (batadv_is_wifi_hardif(hard_iface))
 			hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
 		break;
+	case NETDEV_CHANGENAME:
+		batadv_debugfs_rename_hardif(hard_iface);
+		break;
 	default:
 		break;
 	}
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 3986551397ca..12a2b7d21376 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -1705,7 +1705,9 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 		ether_addr_copy(common->addr, tt_addr);
 		common->vid = vid;
 
-		common->flags = flags;
+		if (!is_multicast_ether_addr(common->addr))
+			common->flags = flags & (~BATADV_TT_SYNC_MASK);
+
 		tt_global_entry->roam_at = 0;
 		/* node must store current time in case of roaming. This is
 		 * needed to purge this entry out on timeout (if nobody claims
@@ -1768,7 +1770,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 		 * TT_CLIENT_TEMP, therefore they have to be copied in the
 		 * client entry
 		 */
-		common->flags |= flags & (~BATADV_TT_SYNC_MASK);
+		if (!is_multicast_ether_addr(common->addr))
+			common->flags |= flags & (~BATADV_TT_SYNC_MASK);
 
 		/* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only
 		 * one originator left in the list and we previously received a
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 68c3578343b4..22a78eedf4b1 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -96,6 +96,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
 	u32 retval, duration;
+	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
 	void *data;
 	int ret;
@@ -131,12 +132,22 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	skb_reset_network_header(skb);
 
 	if (is_l2)
-		__skb_push(skb, ETH_HLEN);
+		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
 	retval = bpf_test_run(prog, skb, repeat, &duration);
-	if (!is_l2)
-		__skb_push(skb, ETH_HLEN);
+	if (!is_l2) {
+		if (skb_headroom(skb) < hh_len) {
+			int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
+
+			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
+				kfree_skb(skb);
+				return -ENOMEM;
+			}
+		}
+		memset(__skb_push(skb, hh_len), 0, hh_len);
+	}
+
 	size = skb->len;
 	/* bpf program can never convert linear skb to non-linear */
 	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index a948b072c28f..76deb6615883 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -1,6 +1,5 @@
 menuconfig BPFILTER
 	bool "BPF based packet filtering framework (BPFILTER)"
-	default n
 	depends on NET && BPF && INET
 	help
 	  This builds experimental bpfilter framework that is aiming to
@@ -9,6 +8,7 @@ menuconfig BPFILTER
 if BPFILTER
 config BPFILTER_UMH
 	tristate "bpfilter kernel module with user mode helper"
+	depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC))
 	default m
 	help
 	  This builds bpfilter kernel module with embedded user mode helper
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
index 051dc18b8ccb..39c6980b5d99 100644
--- a/net/bpfilter/Makefile
+++ b/net/bpfilter/Makefile
@@ -15,20 +15,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y)
 HOSTLDFLAGS += -static
 endif
 
-# a bit of elf magic to convert bpfilter_umh binary into a binary blob
-# inside bpfilter_umh.o elf file referenced by
-# _binary_net_bpfilter_bpfilter_umh_start symbol
-# which bpfilter_kern.c passes further into umh blob loader at run-time
-quiet_cmd_copy_umh = GEN $@
-      cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \
-      $(OBJCOPY) -I binary \
-          `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \
-          |awk -F' |,' '/file format/{print "-O",$$NF} \
-          /^architecture:/{print "-B",$$2}'` \
-      --rename-section .data=.init.rodata $< $@
-
-$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh
-	$(call cmd,copy_umh)
+$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
 
 obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o
-bpfilter-objs += bpfilter_kern.o bpfilter_umh.o
+bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o
diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c
index 09522573f611..f0fc182d3db7 100644
--- a/net/bpfilter/bpfilter_kern.c
+++ b/net/bpfilter/bpfilter_kern.c
@@ -10,11 +10,8 @@
 #include <linux/file.h>
 #include "msgfmt.h"
 
-#define UMH_start _binary_net_bpfilter_bpfilter_umh_start
-#define UMH_end _binary_net_bpfilter_bpfilter_umh_end
-
-extern char UMH_start;
-extern char UMH_end;
+extern char bpfilter_umh_start;
+extern char bpfilter_umh_end;
 
 static struct umh_info info;
 /* since ip_getsockopt() can run in parallel, serialize access to umh */
@@ -93,7 +90,9 @@ static int __init load_umh(void)
 	int err;
 
 	/* fork usermode process */
-	err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info);
+	err = fork_usermode_blob(&bpfilter_umh_start,
+				 &bpfilter_umh_end - &bpfilter_umh_start,
+				 &info);
 	if (err)
 		return err;
 	pr_info("Loaded bpfilter_umh pid %d\n", info.pid);
diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S
new file mode 100644
index 000000000000..40311d10d2f2
--- /dev/null
+++ b/net/bpfilter/bpfilter_umh_blob.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+	.section .init.rodata, "a"
+	.global bpfilter_umh_start
+bpfilter_umh_start:
+	.incbin "net/bpfilter/bpfilter_umh"
+	.global bpfilter_umh_end
+bpfilter_umh_end:
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index e0adcd123f48..711d7156efd8 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb)
 	caifd = caif_get(skb->dev);
 
 	WARN_ON(caifd == NULL);
-	if (caifd == NULL)
+	if (!caifd) {
+		rcu_read_unlock();
 		return;
+	}
 
 	caifd_hold(caifd);
 	rcu_read_unlock();
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index a04e1e88bf3a..50537ff961a7 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 		if (ifr->ifr_qlen < 0)
 			return -EINVAL;
 		if (dev->tx_queue_len ^ ifr->ifr_qlen) {
-			unsigned int orig_len = dev->tx_queue_len;
-
-			dev->tx_queue_len = ifr->ifr_qlen;
-			err = call_netdevice_notifiers(
-					NETDEV_CHANGE_TX_QUEUE_LEN, dev);
-			err = notifier_to_errno(err);
-			if (err) {
-				dev->tx_queue_len = orig_len;
+			err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
+			if (err)
 				return err;
-			}
 		}
 		return 0;
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 126ffc5bc630..f64aa13811ea 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->mark && r->mark != rule->mark)
 			continue;
 
+		if (rule->suppress_ifgroup != -1 &&
+		    r->suppress_ifgroup != rule->suppress_ifgroup)
+			continue;
+
+		if (rule->suppress_prefixlen != -1 &&
+		    r->suppress_prefixlen != rule->suppress_prefixlen)
+			continue;
+
 		if (rule->mark_mask && r->mark_mask != rule->mark_mask)
 			continue;
 
@@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->ip_proto && r->ip_proto != rule->ip_proto)
 			continue;
 
+		if (rule->proto && r->proto != rule->proto)
+			continue;
+
 		if (fib_rule_port_range_set(&rule->sport_range) &&
 		    !fib_rule_port_range_compare(&r->sport_range,
 						 &rule->sport_range))
@@ -645,6 +656,73 @@ errout:
 	return err;
 }
 
+static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
+		       struct nlattr **tb, struct fib_rule *rule)
+{
+	struct fib_rule *r;
+
+	list_for_each_entry(r, &ops->rules_list, list) {
+		if (r->action != rule->action)
+			continue;
+
+		if (r->table != rule->table)
+			continue;
+
+		if (r->pref != rule->pref)
+			continue;
+
+		if (memcmp(r->iifname, rule->iifname, IFNAMSIZ))
+			continue;
+
+		if (memcmp(r->oifname, rule->oifname, IFNAMSIZ))
+			continue;
+
+		if (r->mark != rule->mark)
+			continue;
+
+		if (r->suppress_ifgroup != rule->suppress_ifgroup)
+			continue;
+
+		if (r->suppress_prefixlen != rule->suppress_prefixlen)
+			continue;
+
+		if (r->mark_mask != rule->mark_mask)
+			continue;
+
+		if (r->tun_id != rule->tun_id)
+			continue;
+
+		if (r->fr_net != rule->fr_net)
+			continue;
+
+		if (r->l3mdev != rule->l3mdev)
+			continue;
+
+		if (!uid_eq(r->uid_range.start, rule->uid_range.start) ||
+		    !uid_eq(r->uid_range.end, rule->uid_range.end))
+			continue;
+
+		if (r->ip_proto != rule->ip_proto)
+			continue;
+
+		if (r->proto != rule->proto)
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->sport_range,
+						 &rule->sport_range))
+			continue;
+
+		if (!fib_rule_port_range_compare(&r->dport_range,
+						 &rule->dport_range))
+			continue;
+
+		if (!ops->compare(r, frh, tb))
+			continue;
+		return 1;
+	}
+	return 0;
+}
+
 int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		   struct netlink_ext_ack *extack)
 {
@@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
-	    rule_find(ops, frh, tb, rule, user_priority)) {
+	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
 		goto errout_free;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index e7f12e9f598c..06da770f543f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp)
 	     (!unaligned_ok && offset >= 0 &&
 	      offset + ip_align >= 0 &&
 	      offset + ip_align % size == 0))) {
+		bool ldx_off_ok = offset <= S16_MAX;
+
 		*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H);
 		*insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset);
-		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian);
-		*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D,
-				      offset);
+		*insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP,
+				      size, 2 + endian + (!ldx_off_ok * 2));
+		if (ldx_off_ok) {
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+					      BPF_REG_D, offset);
+		} else {
+			*insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D);
+			*insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset);
+			*insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A,
+					      BPF_REG_TMP, 0);
+		}
 		if (endian)
 			*insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8);
 		*insn++ = BPF_JMP_A(8);
@@ -1762,6 +1772,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static inline int sk_skb_try_make_writable(struct sk_buff *skb,
+					   unsigned int write_len)
+{
+	int err = __bpf_try_make_writable(skb, write_len);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return err;
+}
+
+BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len)
+{
+	/* Idea is the following: should the needed direct read/write
+	 * test fail during runtime, we can pull in more data and redo
+	 * again, since implicitly, we invalidate previous checks here.
+	 *
+	 * Or, since we know how much we need to make read/writeable,
+	 * this can be done once at the program beginning for direct
+	 * access case. By this we overcome limitations of only current
+	 * headroom being accessible.
+	 */
+	return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb));
+}
+
+static const struct bpf_func_proto sk_skb_pull_data_proto = {
+	.func		= sk_skb_pull_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset,
 	   u64, from, u64, to, u64, flags)
 {
@@ -2779,7 +2820,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff)
 
 static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 {
-	return skb->dev->mtu + skb->dev->hard_header_len;
+	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
+			  SKB_MAX_ALLOC;
 }
 
 static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff)
@@ -2863,8 +2905,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
 	return __skb_trim_rcsum(skb, new_len);
 }
 
-BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
-	   u64, flags)
+static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
+					u64 flags)
 {
 	u32 max_len = __bpf_skb_max_len(skb);
 	u32 min_len = __bpf_skb_min_len(skb);
@@ -2900,6 +2942,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 		if (!ret && skb_is_gso(skb))
 			skb_gso_reset(skb);
 	}
+	return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_tail(skb, new_len, flags);
 
 	bpf_compute_data_pointers(skb);
 	return ret;
@@ -2914,9 +2963,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
-BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len,
 	   u64, flags)
 {
+	int ret = __bpf_skb_change_tail(skb, new_len, flags);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_tail_proto = {
+	.func		= sk_skb_change_tail,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
+					u64 flags)
+{
 	u32 max_len = __bpf_skb_max_len(skb);
 	u32 new_len = skb->len + head_room;
 	int ret;
@@ -2941,8 +3008,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
 		skb_reset_mac_header(skb);
 	}
 
+	return ret;
+}
+
+BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_head(skb, head_room, flags);
+
 	bpf_compute_data_pointers(skb);
-	return 0;
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_skb_change_head_proto = {
@@ -2954,6 +3029,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room,
+	   u64, flags)
+{
+	int ret = __bpf_skb_change_head(skb, head_room, flags);
+
+	bpf_compute_data_end_sk_skb(skb);
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_change_head_proto = {
+	.func		= sk_skb_change_head,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+};
 static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
 {
 	return xdp_data_meta_unsupported(xdp) ? 0 :
@@ -3046,12 +3138,16 @@ static int __bpf_tx_xdp(struct net_device *dev,
 			u32 index)
 {
 	struct xdp_frame *xdpf;
-	int sent;
+	int err, sent;
 
 	if (!dev->netdev_ops->ndo_xdp_xmit) {
 		return -EOPNOTSUPP;
 	}
 
+	err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+	if (unlikely(err))
+		return err;
+
 	xdpf = convert_to_xdp_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -3285,7 +3381,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 		goto err;
 	}
 
-	if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd))))
+	err = xdp_ok_fwd_dev(fwd, skb->len);
+	if (unlikely(err))
 		goto err;
 
 	skb->dev = fwd;
@@ -4073,8 +4170,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
+	params->ifindex = dev->ifindex;
 
-	return dev->ifindex;
+	return 0;
 }
 #endif
 
@@ -4098,7 +4196,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	/* verify forwarding is enabled on this interface */
 	in_dev = __in_dev_get_rcu(dev);
 	if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev)))
-		return 0;
+		return BPF_FIB_LKUP_RET_FWD_DISABLED;
 
 	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
 		fl4.flowi4_iif = 1;
@@ -4123,7 +4221,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		tb = fib_get_table(net, tbid);
 		if (unlikely(!tb))
-			return 0;
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 		err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);
 	} else {
@@ -4135,8 +4233,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 		err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF);
 	}
 
-	if (err || res.type != RTN_UNICAST)
-		return 0;
+	if (err) {
+		/* map fib lookup errors to RTN_ type */
+		if (err == -EINVAL)
+			return BPF_FIB_LKUP_RET_BLACKHOLE;
+		if (err == -EHOSTUNREACH)
+			return BPF_FIB_LKUP_RET_UNREACHABLE;
+		if (err == -EACCES)
+			return BPF_FIB_LKUP_RET_PROHIBIT;
+
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
+	}
+
+	if (res.type != RTN_UNICAST)
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	if (res.fi->fib_nhs > 1)
 		fib_select_path(net, &res, &fl4, NULL);
@@ -4144,19 +4254,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (check_mtu) {
 		mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst);
 		if (params->tot_len > mtu)
-			return 0;
+			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
 	nh = &res.fi->fib_nh[res.nh_sel];
 
 	/* do not handle lwt encaps right now */
 	if (nh->nh_lwtstate)
-		return 0;
+		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	dev = nh->nh_dev;
-	if (unlikely(!dev))
-		return 0;
-
 	if (nh->nh_gw)
 		params->ipv4_dst = nh->nh_gw;
 
@@ -4166,10 +4273,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	 * rcu_read_lock_bh is not needed here
 	 */
 	neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst);
-	if (neigh)
-		return bpf_fib_set_fwd_params(params, neigh, dev);
+	if (!neigh)
+		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return 0;
+	return bpf_fib_set_fwd_params(params, neigh, dev);
 }
 #endif
 
@@ -4190,7 +4297,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	/* link local addresses are never forwarded */
 	if (rt6_need_strict(dst) || rt6_need_strict(src))
-		return 0;
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	dev = dev_get_by_index_rcu(net, params->ifindex);
 	if (unlikely(!dev))
@@ -4198,7 +4305,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	idev = __in6_dev_get_safely(dev);
 	if (unlikely(!idev || !net->ipv6.devconf_all->forwarding))
-		return 0;
+		return BPF_FIB_LKUP_RET_FWD_DISABLED;
 
 	if (flags & BPF_FIB_LOOKUP_OUTPUT) {
 		fl6.flowi6_iif = 1;
@@ -4225,7 +4332,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 		tb = ipv6_stub->fib6_get_table(net, tbid);
 		if (unlikely(!tb))
-			return 0;
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 		f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict);
 	} else {
@@ -4238,11 +4345,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	}
 
 	if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry))
-		return 0;
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
+
+	if (unlikely(f6i->fib6_flags & RTF_REJECT)) {
+		switch (f6i->fib6_type) {
+		case RTN_BLACKHOLE:
+			return BPF_FIB_LKUP_RET_BLACKHOLE;
+		case RTN_UNREACHABLE:
+			return BPF_FIB_LKUP_RET_UNREACHABLE;
+		case RTN_PROHIBIT:
+			return BPF_FIB_LKUP_RET_PROHIBIT;
+		default:
+			return BPF_FIB_LKUP_RET_NOT_FWDED;
+		}
+	}
 
-	if (unlikely(f6i->fib6_flags & RTF_REJECT ||
-	    f6i->fib6_type != RTN_UNICAST))
-		return 0;
+	if (f6i->fib6_type != RTN_UNICAST)
+		return BPF_FIB_LKUP_RET_NOT_FWDED;
 
 	if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0)
 		f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6,
@@ -4252,11 +4371,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	if (check_mtu) {
 		mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src);
 		if (params->tot_len > mtu)
-			return 0;
+			return BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
 	if (f6i->fib6_nh.nh_lwtstate)
-		return 0;
+		return BPF_FIB_LKUP_RET_UNSUPP_LWT;
 
 	if (f6i->fib6_flags & RTF_GATEWAY)
 		*dst = f6i->fib6_nh.nh_gw;
@@ -4270,10 +4389,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	 */
 	neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128,
 				      ndisc_hashfn, dst, dev);
-	if (neigh)
-		return bpf_fib_set_fwd_params(params, neigh, dev);
+	if (!neigh)
+		return BPF_FIB_LKUP_RET_NO_NEIGH;
 
-	return 0;
+	return bpf_fib_set_fwd_params(params, neigh, dev);
 }
 #endif
 
@@ -4315,7 +4434,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	   struct bpf_fib_lookup *, params, int, plen, u32, flags)
 {
 	struct net *net = dev_net(skb->dev);
-	int index = -EAFNOSUPPORT;
+	int rc = -EAFNOSUPPORT;
 
 	if (plen < sizeof(*params))
 		return -EINVAL;
@@ -4326,25 +4445,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb,
 	switch (params->family) {
 #if IS_ENABLED(CONFIG_INET)
 	case AF_INET:
-		index = bpf_ipv4_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv4_fib_lookup(net, params, flags, false);
 		break;
 #endif
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
-		index = bpf_ipv6_fib_lookup(net, params, flags, false);
+		rc = bpf_ipv6_fib_lookup(net, params, flags, false);
 		break;
 #endif
 	}
 
-	if (index > 0) {
+	if (!rc) {
 		struct net_device *dev;
 
-		dev = dev_get_by_index_rcu(net, index);
+		dev = dev_get_by_index_rcu(net, params->ifindex);
 		if (!is_skb_forwardable(dev, skb))
-			index = 0;
+			rc = BPF_FIB_LKUP_RET_FRAG_NEEDED;
 	}
 
-	return index;
+	return rc;
 }
 
 static const struct bpf_func_proto bpf_skb_fib_lookup_proto = {
@@ -4417,10 +4536,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = {
 	.arg4_type	= ARG_CONST_SIZE
 };
 
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 	   const void *, from, u32, len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	void *srh_tlvs, *srh_end, *ptr;
@@ -4446,9 +4565,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 
 	memcpy(skb->data + offset, from, len);
 	return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
@@ -4464,7 +4580,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
 BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	   u32, action, void *, param, u32, param_len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	struct ipv6_sr_hdr *srh;
@@ -4512,9 +4627,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	default:
 		return -EINVAL;
 	}
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
@@ -4530,7 +4642,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = {
 BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	   s32, len)
 {
-#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	void *srh_end, *srh_tlvs, *ptr;
@@ -4574,9 +4685,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	srh_state->hdrlen += len;
 	srh_state->valid = 0;
 	return 0;
-#else /* CONFIG_IPV6_SEG6_BPF */
-	return -EOPNOTSUPP;
-#endif
 }
 
 static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
@@ -4587,6 +4695,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
 	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
 };
+#endif /* CONFIG_IPV6_SEG6_BPF */
 
 bool bpf_helper_changes_pkt_data(void *func)
 {
@@ -4595,9 +4704,12 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_store_bytes ||
 	    func == bpf_skb_change_proto ||
 	    func == bpf_skb_change_head ||
+	    func == sk_skb_change_head ||
 	    func == bpf_skb_change_tail ||
+	    func == sk_skb_change_tail ||
 	    func == bpf_skb_adjust_room ||
 	    func == bpf_skb_pull_data ||
+	    func == sk_skb_pull_data ||
 	    func == bpf_clone_redirect ||
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
@@ -4605,11 +4717,12 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_xdp_adjust_meta ||
 	    func == bpf_msg_pull_data ||
 	    func == bpf_xdp_adjust_tail ||
-	    func == bpf_lwt_push_encap ||
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	    func == bpf_lwt_seg6_store_bytes ||
 	    func == bpf_lwt_seg6_adjust_srh ||
-	    func == bpf_lwt_seg6_action
-	    )
+	    func == bpf_lwt_seg6_action ||
+#endif
+	    func == bpf_lwt_push_encap)
 		return true;
 
 	return false;
@@ -4849,11 +4962,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_skb_load_bytes_proto;
 	case BPF_FUNC_skb_pull_data:
-		return &bpf_skb_pull_data_proto;
+		return &sk_skb_pull_data_proto;
 	case BPF_FUNC_skb_change_tail:
-		return &bpf_skb_change_tail_proto;
+		return &sk_skb_change_tail_proto;
 	case BPF_FUNC_skb_change_head:
-		return &bpf_skb_change_head_proto;
+		return &sk_skb_change_head_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
@@ -4944,12 +5057,14 @@ static const struct bpf_func_proto *
 lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	switch (func_id) {
+#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF)
 	case BPF_FUNC_lwt_seg6_store_bytes:
 		return &bpf_lwt_seg6_store_bytes_proto;
 	case BPF_FUNC_lwt_seg6_action:
 		return &bpf_lwt_seg6_action_proto;
 	case BPF_FUNC_lwt_seg6_adjust_srh:
 		return &bpf_lwt_seg6_adjust_srh_proto;
+#endif
 	default:
 		return lwt_out_func_proto(func_id, prog);
 	}
diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c
index b2b2323bdc84..188d693cb251 100644
--- a/net/core/gen_stats.c
+++ b/net/core/gen_stats.c
@@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
 		d->lock = lock;
 		spin_lock_bh(lock);
 	}
-	if (d->tail)
-		return gnet_stats_copy(d, type, NULL, 0, padattr);
+	if (d->tail) {
+		int ret = gnet_stats_copy(d, type, NULL, 0, padattr);
+
+		/* The initial attribute added in gnet_stats_copy() may be
+		 * preceded by a padding attribute, in which case d->tail will
+		 * end up pointing at the padding instead of the real attribute.
+		 * Fix this so gnet_stats_finish_copy() adjusts the length of
+		 * the right attribute.
+		 */
+		if (ret == 0 && d->tail->nla_type == padattr)
+			d->tail = (struct nlattr *)((char *)d->tail +
+						    NLA_ALIGN(d->tail->nla_len));
+		return ret;
+	}
 
 	return 0;
 }
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 68bf07206744..43a932cb609b 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool)
 	struct page *page;
 
 	/* Empty recycle ring */
-	while ((page = ptr_ring_consume(&pool->ring))) {
+	while ((page = ptr_ring_consume_bh(&pool->ring))) {
 		/* Verify the refcnt invariant of cached pages */
 		if (!(page_ref_count(page) == 1))
 			pr_crit("%s() page_pool refcnt %d violation\n",
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ef61222fdef..e3f743c141b3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 			return err;
 	}
 
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
-	__dev_notify_flags(dev, old_flags, ~0U);
+	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+		__dev_notify_flags(dev, old_flags, 0U);
+	} else {
+		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+		__dev_notify_flags(dev, old_flags, ~0U);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..fb35b62af272 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	n->cloned = 1;
 	n->nohdr = 0;
 	n->peeked = 0;
+	C(pfmemalloc);
 	n->destructor = NULL;
 	C(tail);
 	C(end);
@@ -3719,6 +3720,7 @@ normal:
 				net_warn_ratelimited(
 					"skb_segment: too many frags: %u %u\n",
 					pos, mss);
+				err = -EINVAL;
 				goto err;
 			}
 
@@ -3752,11 +3754,10 @@ skip_fraglist:
 
 perform_csum_check:
 		if (!csum) {
-			if (skb_has_shared_frag(nskb)) {
-				err = __skb_linearize(nskb);
-				if (err)
-					goto err;
-			}
+			if (skb_has_shared_frag(nskb) &&
+			    __skb_linearize(nskb))
+				goto err;
+
 			if (!nskb->remcsum_offload)
 				nskb->ip_summed = CHECKSUM_NONE;
 			SKB_GSO_CB(nskb)->csum =
@@ -5276,8 +5277,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len,
 			if (npages >= 1 << order) {
 				page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) |
 						   __GFP_COMP |
-						   __GFP_NOWARN |
-						   __GFP_NORETRY,
+						   __GFP_NOWARN,
 						   order);
 				if (page)
 					goto fill_page;
diff --git a/net/core/sock.c b/net/core/sock.c
index bcc41829a16d..bc2d7a37297f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
 		pfrag->offset += use;
 
 		sge = sg + sg_curr - 1;
-		if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
-			sg->length += use;
+		if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page &&
+		    sge->offset + sge->length == orig_offset) {
+			sge->length += use;
 		} else {
 			sge = sg + sg_curr;
 			sg_unmark_end(sge);
@@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot)
 
 	rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name,
 					   rsk_prot->obj_size, 0,
-					   prot->slab_flags, NULL);
+					   SLAB_ACCOUNT | prot->slab_flags,
+					   NULL);
 
 	if (!rsk_prot->slab) {
 		pr_crit("%s: Can't create request sock SLAB cache!\n",
@@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab)
 	if (alloc_slab) {
 		prot->slab = kmem_cache_create_usercopy(prot->name,
 					prot->obj_size, 0,
-					SLAB_HWCACHE_ALIGN | prot->slab_flags,
+					SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT |
+					prot->slab_flags,
 					prot->useroffset, prot->usersize,
 					NULL);
 
@@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab)
 				kmem_cache_create(prot->twsk_prot->twsk_slab_name,
 						  prot->twsk_prot->twsk_obj_size,
 						  0,
+						  SLAB_ACCOUNT |
 						  prot->slab_flags,
 						  NULL);
 			if (prot->twsk_prot->twsk_slab == NULL)
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 40c851693f77..0c9478b91fa5 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -86,35 +86,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep)
 		opt++;
 		kdebug("options: '%s'", opt);
 		do {
+			int opt_len, opt_nlen;
 			const char *eq;
-			int opt_len, opt_nlen, opt_vlen, tmp;
+			char optval[128];
 
 			next_opt = memchr(opt, '#', end - opt) ?: end;
 			opt_len = next_opt - opt;
-			if (opt_len <= 0 || opt_len > 128) {
+			if (opt_len <= 0 || opt_len > sizeof(optval)) {
 				pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n",
 						    opt_len);
 				return -EINVAL;
 			}
 
-			eq = memchr(opt, '=', opt_len) ?: end;
-			opt_nlen = eq - opt;
-			eq++;
-			opt_vlen = next_opt - eq; /* will be -1 if no value */
+			eq = memchr(opt, '=', opt_len);
+			if (eq) {
+				opt_nlen = eq - opt;
+				eq++;
+				memcpy(optval, eq, next_opt - eq);
+				optval[next_opt - eq] = '\0';
+			} else {
+				opt_nlen = opt_len;
+				optval[0] = '\0';
+			}
 
-			tmp = opt_vlen >= 0 ? opt_vlen : 0;
-			kdebug("option '%*.*s' val '%*.*s'",
-			       opt_nlen, opt_nlen, opt, tmp, tmp, eq);
+			kdebug("option '%*.*s' val '%s'",
+			       opt_nlen, opt_nlen, opt, optval);
 
 			/* see if it's an error number representing a DNS error
 			 * that's to be recorded as the result in this key */
 			if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 &&
 			    memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) {
 				kdebug("dns error number option");
-				if (opt_vlen <= 0)
-					goto bad_option_value;
 
-				ret = kstrtoul(eq, 10, &derrno);
+				ret = kstrtoul(optval, 10, &derrno);
 				if (ret < 0)
 					goto bad_option_value;
 
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 275449b0d633..3297e7fa9945 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -90,12 +90,18 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n)
 	return 0;
 }
 
+static int lowpan_get_iflink(const struct net_device *dev)
+{
+	return lowpan_802154_dev(dev)->wdev->ifindex;
+}
+
 static const struct net_device_ops lowpan_netdev_ops = {
 	.ndo_init		= lowpan_dev_init,
 	.ndo_start_xmit		= lowpan_xmit,
 	.ndo_open		= lowpan_open,
 	.ndo_stop		= lowpan_stop,
 	.ndo_neigh_construct    = lowpan_neigh_construct,
+	.ndo_get_iflink         = lowpan_get_iflink,
 };
 
 static void lowpan_setup(struct net_device *ldev)
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index b21833651394..e46cdd310e5f 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -300,6 +300,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
 		struct flowi4 fl4 = {
 			.flowi4_iif = LOOPBACK_IFINDEX,
+			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
 			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
 			.flowi4_scope = scope,
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..c9ec1603666b 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -448,9 +448,7 @@ next_proto:
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
-	skb_gro_remcsum_cleanup(skb, &grc);
-	skb->remcsum_offload = 0;
+	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);
 
 	return pp;
 }
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..6a7d980105f6 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 
 	return pp;
 }
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 85b617b655bc..28fef7d15959 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1200,13 +1200,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
 	spin_lock_bh(&im->lock);
 	if (pmc) {
 		im->interface = pmc->interface;
-		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
-		im->sfmode = pmc->sfmode;
-		if (pmc->sfmode == MCAST_INCLUDE) {
+		if (im->sfmode == MCAST_INCLUDE) {
 			im->tomb = pmc->tomb;
 			im->sources = pmc->sources;
 			for (psf = im->sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = im->crcount;
+				psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+		} else {
+			im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
 		}
 		in_dev_put(pmc->interface);
 		kfree(pmc);
@@ -1288,7 +1288,7 @@ static void igmp_group_dropped(struct ip_mc_list *im)
 #endif
 }
 
-static void igmp_group_added(struct ip_mc_list *im)
+static void igmp_group_added(struct ip_mc_list *im, unsigned int mode)
 {
 	struct in_device *in_dev = im->interface;
 #ifdef CONFIG_IP_MULTICAST
@@ -1316,7 +1316,13 @@ static void igmp_group_added(struct ip_mc_list *im)
 	}
 	/* else, v3 */
 
-	im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+	/* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should
+	 * not send filter-mode change record as the mode should be from
+	 * IN() to IN(A).
+	 */
+	if (mode == MCAST_EXCLUDE)
+		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+
 	igmp_ifc_event(in_dev);
 #endif
 }
@@ -1381,8 +1387,7 @@ static void ip_mc_hash_remove(struct in_device *in_dev,
 /*
  *	A socket has joined a multicast group on device dev.
  */
-
-void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode)
 {
 	struct ip_mc_list *im;
 #ifdef CONFIG_IP_MULTICAST
@@ -1394,7 +1399,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	for_each_pmc_rtnl(in_dev, im) {
 		if (im->multiaddr == addr) {
 			im->users++;
-			ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0);
+			ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0);
 			goto out;
 		}
 	}
@@ -1408,8 +1413,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 	in_dev_hold(in_dev);
 	im->multiaddr = addr;
 	/* initial mode is (EX, empty) */
-	im->sfmode = MCAST_EXCLUDE;
-	im->sfcount[MCAST_EXCLUDE] = 1;
+	im->sfmode = mode;
+	im->sfcount[mode] = 1;
 	refcount_set(&im->refcnt, 1);
 	spin_lock_init(&im->lock);
 #ifdef CONFIG_IP_MULTICAST
@@ -1426,12 +1431,17 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
 #ifdef CONFIG_IP_MULTICAST
 	igmpv3_del_delrec(in_dev, im);
 #endif
-	igmp_group_added(im);
+	igmp_group_added(im, mode);
 	if (!in_dev->dead)
 		ip_rt_multicast_event(in_dev);
 out:
 	return;
 }
+
+void ip_mc_inc_group(struct in_device *in_dev, __be32 addr)
+{
+	__ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ip_mc_inc_group);
 
 static int ip_mc_check_iphdr(struct sk_buff *skb)
@@ -1688,7 +1698,7 @@ void ip_mc_remap(struct in_device *in_dev)
 #ifdef CONFIG_IP_MULTICAST
 		igmpv3_del_delrec(in_dev, pmc);
 #endif
-		igmp_group_added(pmc);
+		igmp_group_added(pmc, pmc->sfmode);
 	}
 }
 
@@ -1751,7 +1761,7 @@ void ip_mc_up(struct in_device *in_dev)
 #ifdef CONFIG_IP_MULTICAST
 		igmpv3_del_delrec(in_dev, pmc);
 #endif
-		igmp_group_added(pmc);
+		igmp_group_added(pmc, pmc->sfmode);
 	}
 }
 
@@ -2130,8 +2140,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc)
 
 /* Join a multicast group
  */
-
-int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
+			      unsigned int mode)
 {
 	__be32 addr = imr->imr_multiaddr.s_addr;
 	struct ip_mc_socklist *iml, *i;
@@ -2172,15 +2182,30 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
 	memcpy(&iml->multi, imr, sizeof(*imr));
 	iml->next_rcu = inet->mc_list;
 	iml->sflist = NULL;
-	iml->sfmode = MCAST_EXCLUDE;
+	iml->sfmode = mode;
 	rcu_assign_pointer(inet->mc_list, iml);
-	ip_mc_inc_group(in_dev, addr);
+	__ip_mc_inc_group(in_dev, addr, mode);
 	err = 0;
 done:
 	return err;
 }
+
+/* Join ASM (Any-Source Multicast) group
+ */
+int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr)
+{
+	return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ip_mc_join_group);
 
+/* Join SSM (Source-Specific Multicast) group
+ */
+int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr,
+			 unsigned int mode)
+{
+	return __ip_mc_join_group(sk, imr, mode);
+}
+
 static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml,
 			   struct in_device *in_dev)
 {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c9e35b81d093..1e4cf3ab560f 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr, void *arg)
 
 void inet_frags_exit_net(struct netns_frags *nf)
 {
-	nf->low_thresh = 0; /* prevent creation of new frags */
+	nf->high_thresh = 0; /* prevent creation of new frags */
 
 	rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL);
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..0e3edd25f881 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index fc32fdbeefa6..c0fe5ad996f2 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
 {
 	struct sockaddr_in sin;
 	const struct iphdr *iph = ip_hdr(skb);
-	__be16 *ports = (__be16 *)skb_transport_header(skb);
+	__be16 *ports;
+	int end;
 
-	if (skb_transport_offset(skb) + 4 > (int)skb->len)
+	end = skb_transport_offset(skb) + 4;
+	if (end > 0 && !pskb_may_pull(skb, end))
 		return;
 
 	/* All current transport protocols have the port numbers in the
 	 * first four bytes of the transport header and this function is
 	 * written with this assumption in mind.
 	 */
+	ports = (__be16 *)skb_transport_header(skb);
 
 	sin.sin_family = AF_INET;
 	sin.sin_addr.s_addr = iph->daddr;
@@ -984,7 +987,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr;
 			mreq.imr_address.s_addr = mreqs.imr_interface;
 			mreq.imr_ifindex = 0;
-			err = ip_mc_join_group(sk, &mreq);
+			err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
 			if (err && err != -EADDRINUSE)
 				break;
 			omode = MCAST_INCLUDE;
@@ -1061,7 +1064,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 			mreq.imr_multiaddr = psin->sin_addr;
 			mreq.imr_address.s_addr = 0;
 			mreq.imr_ifindex = greqs.gsr_interface;
-			err = ip_mc_join_group(sk, &mreq);
+			err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE);
 			if (err && err != -EADDRINUSE)
 				break;
 			greqs.gsr_interface = mreq.imr_ifindex;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index ca0dad90803a..e77872c93c20 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1898,6 +1898,7 @@ static struct xt_match ipt_builtin_mt[] __read_mostly = {
 		.checkentry = icmp_checkentry,
 		.proto      = IPPROTO_ICMP,
 		.family     = NFPROTO_IPV4,
+		.me	    = THIS_MODULE,
 	},
 };
 
diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c
index 805e83ec3ad9..164714104965 100644
--- a/net/ipv4/netfilter/nf_tproxy_ipv4.c
+++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c
@@ -37,7 +37,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb,
 		 * to a listener socket if there's one */
 		struct sock *sk2;
 
-		sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+		sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
 					    iph->saddr, laddr ? laddr : iph->daddr,
 					    hp->source, lport ? lport : hp->dest,
 					    skb->dev, NF_TPROXY_LOOKUP_LISTENER);
@@ -71,7 +71,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 EXPORT_SYMBOL_GPL(nf_tproxy_laddr4);
 
 struct sock *
-nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
+nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb,
 		      const u8 protocol,
 		      const __be32 saddr, const __be32 daddr,
 		      const __be16 sport, const __be16 dport,
@@ -79,16 +79,21 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
 	struct sock *sk;
-	struct tcphdr *tcph;
 
 	switch (protocol) {
-	case IPPROTO_TCP:
+	case IPPROTO_TCP: {
+		struct tcphdr _hdr, *hp;
+
+		hp = skb_header_pointer(skb, ip_hdrlen(skb),
+					sizeof(struct tcphdr), &_hdr);
+		if (hp == NULL)
+			return NULL;
+
 		switch (lookup_type) {
 		case NF_TPROXY_LOOKUP_LISTENER:
-			tcph = hp;
 			sk = inet_lookup_listener(net, &tcp_hashinfo, skb,
 						    ip_hdrlen(skb) +
-						      __tcp_hdrlen(tcph),
+						      __tcp_hdrlen(hp),
 						    saddr, sport,
 						    daddr, dport,
 						    in->ifindex, 0);
@@ -110,6 +115,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
 			BUG();
 		}
 		break;
+		}
 	case IPPROTO_UDP:
 		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
 				     in->ifindex);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index d06247ba08b2..5fa335fd3852 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -189,8 +189,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	if (write && ret == 0) {
 		low = make_kgid(user_ns, urange[0]);
 		high = make_kgid(user_ns, urange[1]);
-		if (!gid_valid(low) || !gid_valid(high) ||
-		    (urange[1] < urange[0]) || gid_lt(high, low)) {
+		if (!gid_valid(low) || !gid_valid(high))
+			return -EINVAL;
+		if (urange[1] < urange[0] || gid_lt(high, low)) {
 			low = make_kgid(&init_user_ns, 1);
 			high = make_kgid(&init_user_ns, 0);
 		}
@@ -265,8 +266,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	    ipv4.sysctl_tcp_fastopen);
 	struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
 	struct tcp_fastopen_context *ctxt;
-	int ret;
 	u32  user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+	__le32 key[4];
+	int ret, i;
 
 	tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
 	if (!tbl.data)
@@ -275,11 +277,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 	rcu_read_lock();
 	ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
 	if (ctxt)
-		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+		memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
 	else
-		memset(user_key, 0, sizeof(user_key));
+		memset(key, 0, sizeof(key));
 	rcu_read_unlock();
 
+	for (i = 0; i < ARRAY_SIZE(key); i++)
+		user_key[i] = le32_to_cpu(key[i]);
+
 	snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
 		user_key[0], user_key[1], user_key[2], user_key[3]);
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
@@ -290,13 +295,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write,
 			ret = -EINVAL;
 			goto bad_key;
 		}
-		tcp_fastopen_reset_cipher(net, NULL, user_key,
+
+		for (i = 0; i < ARRAY_SIZE(user_key); i++)
+			key[i] = cpu_to_le32(user_key[i]);
+
+		tcp_fastopen_reset_cipher(net, NULL, key,
 					  TCP_FASTOPEN_KEY_LENGTH);
 	}
 
 bad_key:
 	pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
-	       user_key[0], user_key[1], user_key[2], user_key[3],
+		user_key[0], user_key[1], user_key[2], user_key[3],
 	       (char *)tbl.data, ret);
 	kfree(tbl.data);
 	return ret;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e7b53d2a971f..4491faf83f4f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1998,7 +1998,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			 * shouldn't happen.
 			 */
 			if (WARN(before(*seq, TCP_SKB_CB(skb)->seq),
-				 "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n",
+				 "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n",
 				 *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt,
 				 flags))
 				break;
@@ -2013,7 +2013,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 			if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
 				goto found_fin_ok;
 			WARN(!(flags & MSG_PEEK),
-			     "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n",
+			     "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n",
 			     *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags);
 		}
 
@@ -2562,6 +2562,8 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	tcp_clear_xmit_timers(sk);
 	__skb_queue_purge(&sk->sk_receive_queue);
+	tp->copied_seq = tp->rcv_nxt;
+	tp->urg_data = 0;
 	tcp_write_queue_purge(sk);
 	tcp_fastopen_active_disable_ofo_check(sk);
 	skb_rbtree_purge(&tp->out_of_order_queue);
@@ -2821,14 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 	case TCP_REPAIR:
 		if (!tcp_can_repair_sock(sk))
 			err = -EPERM;
-		else if (val == 1) {
+		else if (val == TCP_REPAIR_ON) {
 			tp->repair = 1;
 			sk->sk_reuse = SK_FORCE_REUSE;
 			tp->repair_queue = TCP_NO_QUEUE;
-		} else if (val == 0) {
+		} else if (val == TCP_REPAIR_OFF) {
 			tp->repair = 0;
 			sk->sk_reuse = SK_NO_REUSE;
 			tcp_send_window_probe(sk);
+		} else if (val == TCP_REPAIR_OFF_NO_WP) {
+			tp->repair = 0;
+			sk->sk_reuse = SK_NO_REUSE;
 		} else
 			err = -EINVAL;
 
@@ -3720,8 +3725,7 @@ int tcp_abort(struct sock *sk, int err)
 			struct request_sock *req = inet_reqsk(sk);
 
 			local_bh_disable();
-			inet_csk_reqsk_queue_drop_and_put(req->rsk_listener,
-							  req);
+			inet_csk_reqsk_queue_drop(req->rsk_listener, req);
 			local_bh_enable();
 			return 0;
 		}
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 5f5e5936760e..8b637f9f23a2 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -55,7 +55,6 @@ struct dctcp {
 	u32 dctcp_alpha;
 	u32 next_seq;
 	u32 ce_state;
-	u32 delayed_ack_reserved;
 	u32 loss_cwnd;
 };
 
@@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk)
 
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
 
-		ca->delayed_ack_reserved = 0;
 		ca->loss_cwnd = 0;
 		ca->ce_state = 0;
 
@@ -131,23 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=0 to CE=1 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (!ca->ce_state && ca->delayed_ack_reserved) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=0. */
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
+	if (!ca->ce_state) {
+		/* State has changed from CE=0 to CE=1, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -161,23 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 	struct dctcp *ca = inet_csk_ca(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* State has changed from CE=1 to CE=0 and delayed
-	 * ACK has not sent yet.
-	 */
-	if (ca->ce_state && ca->delayed_ack_reserved) {
-		u32 tmp_rcv_nxt;
-
-		/* Save current rcv_nxt. */
-		tmp_rcv_nxt = tp->rcv_nxt;
-
-		/* Generate previous ack with CE=1. */
-		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
-		tp->rcv_nxt = ca->prior_rcv_nxt;
-
-		tcp_send_ack(sk);
-
-		/* Recover current rcv_nxt. */
-		tp->rcv_nxt = tmp_rcv_nxt;
+	if (ca->ce_state) {
+		/* State has changed from CE=1 to CE=0, force an immediate
+		 * ACK to reflect the new CE state. If an ACK was delayed,
+		 * send that first to reflect the prior CE state.
+		 */
+		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
+			__tcp_send_ack(sk, ca->prior_rcv_nxt);
+		tcp_enter_quickack_mode(sk, 1);
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -248,25 +228,6 @@ static void dctcp_state(struct sock *sk, u8 new_state)
 	}
 }
 
-static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
-{
-	struct dctcp *ca = inet_csk_ca(sk);
-
-	switch (ev) {
-	case CA_EVENT_DELAYED_ACK:
-		if (!ca->delayed_ack_reserved)
-			ca->delayed_ack_reserved = 1;
-		break;
-	case CA_EVENT_NON_DELAYED_ACK:
-		if (ca->delayed_ack_reserved)
-			ca->delayed_ack_reserved = 0;
-		break;
-	default:
-		/* Don't care for the rest. */
-		break;
-	}
-}
-
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 {
 	switch (ev) {
@@ -276,10 +237,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ce_state_1_to_0(sk);
 		break;
-	case CA_EVENT_DELAYED_ACK:
-	case CA_EVENT_NON_DELAYED_ACK:
-		dctcp_update_ack_reserved(sk, ev);
-		break;
 	default:
 		/* Don't care for the rest. */
 		break;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 355d3dffd021..3bcd30a2ba06 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks)
 		icsk->icsk_ack.quick = quickacks;
 }
 
-static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
+void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
@@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 	icsk->icsk_ack.pingpong = 0;
 	icsk->icsk_ack.ato = TCP_ATO_MIN;
 }
+EXPORT_SYMBOL(tcp_enter_quickack_mode);
 
 /* Send ACKs quickly, if "quick" count is not exhausted
  * and the session is not interactive.
@@ -265,7 +266,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 		 * it is probably a retransmit.
 		 */
 		if (tp->ecn_flags & TCP_ECN_SEEN)
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 		break;
 	case INET_ECN_CE:
 		if (tcp_ca_needs_ecn(sk))
@@ -273,7 +274,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 
 		if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) {
 			/* Better not delay acks, sender can have a very low cwnd */
-			tcp_enter_quickack_mode(sk, 1);
+			tcp_enter_quickack_mode(sk, 2);
 			tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
 		}
 		tp->ecn_flags |= TCP_ECN_SEEN;
@@ -3181,6 +3182,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack,
 
 		if (tcp_is_reno(tp)) {
 			tcp_remove_reno_sacks(sk, pkts_acked);
+
+			/* If any of the cumulatively ACKed segments was
+			 * retransmitted, non-SACK case cannot confirm that
+			 * progress was due to original transmission due to
+			 * lack of TCPCB_SACKED_ACKED bits even if some of
+			 * the packets may have been never retransmitted.
+			 */
+			if (flag & FLAG_RETRANS_DATA_ACKED)
+				flag &= ~FLAG_ORIG_SACK_ACKED;
 		} else {
 			int delta;
 
@@ -4348,6 +4358,23 @@ static bool tcp_try_coalesce(struct sock *sk,
 	return true;
 }
 
+static bool tcp_ooo_try_coalesce(struct sock *sk,
+			     struct sk_buff *to,
+			     struct sk_buff *from,
+			     bool *fragstolen)
+{
+	bool res = tcp_try_coalesce(sk, to, from, fragstolen);
+
+	/* In case tcp_drop() is called later, update to->gso_segs */
+	if (res) {
+		u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) +
+			       max_t(u16, 1, skb_shinfo(from)->gso_segs);
+
+		skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+	}
+	return res;
+}
+
 static void tcp_drop(struct sock *sk, struct sk_buff *skb)
 {
 	sk_drops_add(sk, skb);
@@ -4471,8 +4498,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	/* In the typical case, we are adding an skb to the end of the list.
 	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
 	 */
-	if (tcp_try_coalesce(sk, tp->ooo_last_skb,
-			     skb, &fragstolen)) {
+	if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
+				 skb, &fragstolen)) {
 coalesce_done:
 		tcp_grow_window(sk, skb);
 		kfree_skb_partial(skb, fragstolen);
@@ -4500,7 +4527,7 @@ coalesce_done:
 				/* All the bits are present. Drop. */
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb);
+				tcp_drop(sk, skb);
 				skb = NULL;
 				tcp_dsack_set(sk, seq, end_seq);
 				goto add_sack;
@@ -4519,11 +4546,11 @@ coalesce_done:
 						 TCP_SKB_CB(skb1)->end_seq);
 				NET_INC_STATS(sock_net(sk),
 					      LINUX_MIB_TCPOFOMERGE);
-				__kfree_skb(skb1);
+				tcp_drop(sk, skb1);
 				goto merge_right;
 			}
-		} else if (tcp_try_coalesce(sk, skb1,
-					    skb, &fragstolen)) {
+		} else if (tcp_ooo_try_coalesce(sk, skb1,
+						skb, &fragstolen)) {
 			goto coalesce_done;
 		}
 		p = &parent->rb_right;
@@ -4892,6 +4919,7 @@ end:
 static void tcp_collapse_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	u32 range_truesize, sum_tiny = 0;
 	struct sk_buff *skb, *head;
 	u32 start, end;
 
@@ -4903,6 +4931,7 @@ new_range:
 	}
 	start = TCP_SKB_CB(skb)->seq;
 	end = TCP_SKB_CB(skb)->end_seq;
+	range_truesize = skb->truesize;
 
 	for (head = skb;;) {
 		skb = skb_rb_next(skb);
@@ -4913,11 +4942,20 @@ new_range:
 		if (!skb ||
 		    after(TCP_SKB_CB(skb)->seq, end) ||
 		    before(TCP_SKB_CB(skb)->end_seq, start)) {
-			tcp_collapse(sk, NULL, &tp->out_of_order_queue,
-				     head, skb, start, end);
+			/* Do not attempt collapsing tiny skbs */
+			if (range_truesize != head->truesize ||
+			    end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) {
+				tcp_collapse(sk, NULL, &tp->out_of_order_queue,
+					     head, skb, start, end);
+			} else {
+				sum_tiny += range_truesize;
+				if (sum_tiny > sk->sk_rcvbuf >> 3)
+					return;
+			}
 			goto new_range;
 		}
 
+		range_truesize += skb->truesize;
 		if (unlikely(before(TCP_SKB_CB(skb)->seq, start)))
 			start = TCP_SKB_CB(skb)->seq;
 		if (after(TCP_SKB_CB(skb)->end_seq, end))
@@ -4932,6 +4970,7 @@ new_range:
  * 2) not add too big latencies if thousands of packets sit there.
  *    (But if application shrinks SO_RCVBUF, we could still end up
  *     freeing whole queue here)
+ * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks.
  *
  * Return true if queue has shrunk.
  */
@@ -4939,20 +4978,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct rb_node *node, *prev;
+	int goal;
 
 	if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
 		return false;
 
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED);
+	goal = sk->sk_rcvbuf >> 3;
 	node = &tp->ooo_last_skb->rbnode;
 	do {
 		prev = rb_prev(node);
 		rb_erase(node, &tp->out_of_order_queue);
+		goal -= rb_to_skb(node)->truesize;
 		tcp_drop(sk, rb_to_skb(node));
-		sk_mem_reclaim(sk);
-		if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
-		    !tcp_under_memory_pressure(sk))
-			break;
+		if (!prev || goal <= 0) {
+			sk_mem_reclaim(sk);
+			if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf &&
+			    !tcp_under_memory_pressure(sk))
+				break;
+			goal = sk->sk_rcvbuf >> 3;
+		}
 		node = prev;
 	} while (node);
 	tp->ooo_last_skb = rb_to_skb(prev);
@@ -4987,6 +5032,9 @@ static int tcp_prune_queue(struct sock *sk)
 	else if (tcp_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
+	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
+		return 0;
+
 	tcp_collapse_ofo_queue(sk);
 	if (!skb_queue_empty(&sk->sk_receive_queue))
 		tcp_collapse(sk, &sk->sk_receive_queue, NULL,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bea17f1e8302..3b2711e33e4c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
 	    (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
-		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
-		if (tp->write_seq == 0)
-			tp->write_seq = 1;
-		tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
-		tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+		/* In case of repair and re-using TIME-WAIT sockets we still
+		 * want to be sure that it is safe as above but honor the
+		 * sequence numbers and time stamps set as part of the repair
+		 * process.
+		 *
+		 * Without this check re-using a TIME-WAIT socket with TCP
+		 * repair would accumulate a -1 on the repair assigned
+		 * sequence number. The first time it is reused the sequence
+		 * is -1, the second time -2, etc. This fixes that issue
+		 * without appearing to create any others.
+		 */
+		if (likely(!tp->repair)) {
+			tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
+			if (tp->write_seq == 0)
+				tp->write_seq = 1;
+			tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
+			tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
+		}
 		sock_hold(sktw);
 		return 1;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..c4172c1fb198 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp,
 }
 
 /* Account for an ACK we sent. */
-static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
+static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
+				      u32 rcv_nxt)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts)
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
+
+	if (unlikely(rcv_nxt != tp->rcv_nxt))
+		return;  /* Special ACK sent by DCTCP to reflect ECN */
 	tcp_dec_quickack_mode(sk, pkts);
 	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
 }
@@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
  * We are working here with either a clone of the original
  * SKB, or a fresh unique copy made by the retransmit engine.
  */
-static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
-			    gfp_t gfp_mask)
+static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
+			      int clone_it, gfp_t gfp_mask, u32 rcv_nxt)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_sock *inet;
@@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	th->source		= inet->inet_sport;
 	th->dest		= inet->inet_dport;
 	th->seq			= htonl(tcb->seq);
-	th->ack_seq		= htonl(tp->rcv_nxt);
+	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
 					tcb->tcp_flags);
 
@@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	icsk->icsk_af_ops->send_check(sk, skb);
 
 	if (likely(tcb->tcp_flags & TCPHDR_ACK))
-		tcp_event_ack_sent(sk, tcp_skb_pcount(skb));
+		tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt);
 
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
@@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
 	return err;
 }
 
+static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
+			    gfp_t gfp_mask)
+{
+	return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask,
+				  tcp_sk(sk)->rcv_nxt);
+}
+
 /* This routine just queues the buffer for sending.
  *
  * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames,
@@ -3523,8 +3534,6 @@ void tcp_send_delayed_ack(struct sock *sk)
 	int ato = icsk->icsk_ack.ato;
 	unsigned long timeout;
 
-	tcp_ca_event(sk, CA_EVENT_DELAYED_ACK);
-
 	if (ato > TCP_DELACK_MIN) {
 		const struct tcp_sock *tp = tcp_sk(sk);
 		int max_ato = HZ / 2;
@@ -3573,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void tcp_send_ack(struct sock *sk)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 {
 	struct sk_buff *buff;
 
@@ -3581,8 +3590,6 @@ void tcp_send_ack(struct sock *sk)
 	if (sk->sk_state == TCP_CLOSE)
 		return;
 
-	tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK);
-
 	/* We are not putting this on the write queue, so
 	 * tcp_transmit_skb() will set the ownership to this
 	 * sock.
@@ -3608,9 +3615,14 @@ void tcp_send_ack(struct sock *sk)
 	skb_set_tcp_pure_ack(buff);
 
 	/* Send it off, this clears delayed acks for us. */
-	tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0);
+	__tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt);
+}
+EXPORT_SYMBOL_GPL(__tcp_send_ack);
+
+void tcp_send_ack(struct sock *sk)
+{
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
 }
-EXPORT_SYMBOL_GPL(tcp_send_ack);
 
 /* This routine sends a packet with an out of date sequence
  * number. It assumes the other end will try to ack it.
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 92dc9e5a7ff3..69c54540d5b4 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -394,7 +394,7 @@ unflush:
 out_unlock:
 	rcu_read_unlock();
 out:
-	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_flush_final(skb, pp, flush);
 	return pp;
 }
 EXPORT_SYMBOL(udp_gro_receive);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 0eff75525da1..b3885ca22d6f 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -108,6 +108,7 @@ config IPV6_MIP6
 config IPV6_ILA
 	tristate "IPv6: Identifier Locator Addressing (ILA)"
 	depends on NETFILTER
+	select DST_CACHE
 	select LWTUNNEL
 	---help---
 	  Support for IPv6 Identifier Locator Addressing (ILA).
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c134286d6a41..f66a1cae3366 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 			continue;
 		if ((rt->fib6_flags & noflags) != 0)
 			continue;
-		fib6_info_hold(rt);
+		if (!fib6_info_hold_safe(rt))
+			continue;
 		break;
 	}
 out:
@@ -4528,6 +4529,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 			       unsigned long expires, u32 flags)
 {
 	struct fib6_info *f6i;
+	u32 prio;
 
 	f6i = addrconf_get_prefix_route(&ifp->addr,
 					ifp->prefix_len,
@@ -4536,13 +4538,15 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp,
 	if (!f6i)
 		return -ENOENT;
 
-	if (f6i->fib6_metric != ifp->rt_priority) {
+	prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF;
+	if (f6i->fib6_metric != prio) {
+		/* delete old one */
+		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
+
 		/* add new one */
 		addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
 				      ifp->rt_priority, ifp->idev->dev,
 				      expires, flags, GFP_KERNEL);
-		/* delete old one */
-		ip6_del_rt(dev_net(ifp->idev->dev), f6i);
 	} else {
 		if (!expires)
 			fib6_clean_expires(f6i);
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 1323b9679cf7..1c0bb9fb76e6 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -799,8 +799,7 @@ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop)
 {
 	struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts;
 
-	txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS,
-					 hop, hop ? ipv6_optlen(hop) : 0);
+	txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop);
 	txopt_put(old);
 	if (IS_ERR(txopts))
 		return PTR_ERR(txopts);
@@ -1222,8 +1221,7 @@ static int calipso_req_setattr(struct request_sock *req,
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
-	txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
-					 new, new ? ipv6_optlen(new) : 0);
+	txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
 
 	kfree(new);
 
@@ -1260,8 +1258,7 @@ static void calipso_req_delattr(struct request_sock *req)
 	if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new))
 		return; /* Nothing to do */
 
-	txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS,
-					 new, new ? ipv6_optlen(new) : 0);
+	txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new);
 
 	if (!IS_ERR(txopts)) {
 		txopts = xchg(&req_inet->ipv6_opt, txopts);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2ee08b6a86a4..1a1f876f8e28 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 	}
 	if (np->rxopt.bits.rxorigdstaddr) {
 		struct sockaddr_in6 sin6;
-		__be16 *ports = (__be16 *) skb_transport_header(skb);
+		__be16 *ports;
+		int end;
 
-		if (skb_transport_offset(skb) + 4 <= (int)skb->len) {
+		end = skb_transport_offset(skb) + 4;
+		if (end <= 0 || pskb_may_pull(skb, end)) {
 			/* All current transport protocols have the port numbers in the
 			 * first four bytes of the transport header and this function is
 			 * written with this assumption in mind.
 			 */
+			ports = (__be16 *)skb_transport_header(skb);
 
 			sin6.sin6_family = AF_INET6;
 			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 5bc2bf3733ab..20291c2036fc 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -1015,29 +1015,21 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 }
 EXPORT_SYMBOL_GPL(ipv6_dup_options);
 
-static int ipv6_renew_option(void *ohdr,
-			     struct ipv6_opt_hdr __user *newopt, int newoptlen,
-			     int inherit,
-			     struct ipv6_opt_hdr **hdr,
-			     char **p)
+static void ipv6_renew_option(int renewtype,
+			      struct ipv6_opt_hdr **dest,
+			      struct ipv6_opt_hdr *old,
+			      struct ipv6_opt_hdr *new,
+			      int newtype, char **p)
 {
-	if (inherit) {
-		if (ohdr) {
-			memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr));
-			*hdr = (struct ipv6_opt_hdr *)*p;
-			*p += CMSG_ALIGN(ipv6_optlen(*hdr));
-		}
-	} else {
-		if (newopt) {
-			if (copy_from_user(*p, newopt, newoptlen))
-				return -EFAULT;
-			*hdr = (struct ipv6_opt_hdr *)*p;
-			if (ipv6_optlen(*hdr) > newoptlen)
-				return -EINVAL;
-			*p += CMSG_ALIGN(newoptlen);
-		}
-	}
-	return 0;
+	struct ipv6_opt_hdr *src;
+
+	src = (renewtype == newtype ? new : old);
+	if (!src)
+		return;
+
+	memcpy(*p, src, ipv6_optlen(src));
+	*dest = (struct ipv6_opt_hdr *)*p;
+	*p += CMSG_ALIGN(ipv6_optlen(*dest));
 }
 
 /**
@@ -1063,13 +1055,11 @@ static int ipv6_renew_option(void *ohdr,
  */
 struct ipv6_txoptions *
 ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
-		   int newtype,
-		   struct ipv6_opt_hdr __user *newopt, int newoptlen)
+		   int newtype, struct ipv6_opt_hdr *newopt)
 {
 	int tot_len = 0;
 	char *p;
 	struct ipv6_txoptions *opt2;
-	int err;
 
 	if (opt) {
 		if (newtype != IPV6_HOPOPTS && opt->hopopt)
@@ -1082,8 +1072,8 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 			tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt));
 	}
 
-	if (newopt && newoptlen)
-		tot_len += CMSG_ALIGN(newoptlen);
+	if (newopt)
+		tot_len += CMSG_ALIGN(ipv6_optlen(newopt));
 
 	if (!tot_len)
 		return NULL;
@@ -1098,29 +1088,19 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 	opt2->tot_len = tot_len;
 	p = (char *)(opt2 + 1);
 
-	err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen,
-				newtype != IPV6_HOPOPTS,
-				&opt2->hopopt, &p);
-	if (err)
-		goto out;
-
-	err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen,
-				newtype != IPV6_RTHDRDSTOPTS,
-				&opt2->dst0opt, &p);
-	if (err)
-		goto out;
-
-	err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen,
-				newtype != IPV6_RTHDR,
-				(struct ipv6_opt_hdr **)&opt2->srcrt, &p);
-	if (err)
-		goto out;
-
-	err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen,
-				newtype != IPV6_DSTOPTS,
-				&opt2->dst1opt, &p);
-	if (err)
-		goto out;
+	ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt,
+			  (opt ? opt->hopopt : NULL),
+			  newopt, newtype, &p);
+	ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt,
+			  (opt ? opt->dst0opt : NULL),
+			  newopt, newtype, &p);
+	ipv6_renew_option(IPV6_RTHDR,
+			  (struct ipv6_opt_hdr **)&opt2->srcrt,
+			  (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL),
+			  newopt, newtype, &p);
+	ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt,
+			  (opt ? opt->dst1opt : NULL),
+			  newopt, newtype, &p);
 
 	opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) +
 			  (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) +
@@ -1128,37 +1108,6 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt,
 	opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0);
 
 	return opt2;
-out:
-	sock_kfree_s(sk, opt2, opt2->tot_len);
-	return ERR_PTR(err);
-}
-
-/**
- * ipv6_renew_options_kern - replace a specific ext hdr with a new one.
- *
- * @sk: sock from which to allocate memory
- * @opt: original options
- * @newtype: option type to replace in @opt
- * @newopt: new option of type @newtype to replace (kernel-mem)
- * @newoptlen: length of @newopt
- *
- * See ipv6_renew_options().  The difference is that @newopt is
- * kernel memory, rather than user memory.
- */
-struct ipv6_txoptions *
-ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt,
-			int newtype, struct ipv6_opt_hdr *newopt,
-			int newoptlen)
-{
-	struct ipv6_txoptions *ret_val;
-	const mm_segment_t old_fs = get_fs();
-
-	set_fs(KERNEL_DS);
-	ret_val = ipv6_renew_options(sk, opt, newtype,
-				     (struct ipv6_opt_hdr __user *)newopt,
-				     newoptlen);
-	set_fs(old_fs);
-	return ret_val;
 }
 
 struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space,
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index be491bf6ab6e..ef2505aefc15 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb)
 
 	/* for local traffic to local address, skb dev is the loopback
 	 * device. Check if there is a dst attached to the skb and if so
-	 * get the real device index.
+	 * get the real device index. Same is needed for replies to a link
+	 * local address on a device enslaved to an L3 master device
 	 */
-	if (unlikely(iif == LOOPBACK_IFINDEX)) {
+	if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
 		const struct rt6_info *rt6 = skb_rt6_info(skb);
 
 		if (rt6)
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1fb2f3118d60..d212738e9d10 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -935,20 +935,19 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 {
 	struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
 				    lockdep_is_held(&rt->fib6_table->tb6_lock));
-	enum fib_event_type event = FIB_EVENT_ENTRY_ADD;
-	struct fib6_info *iter = NULL, *match = NULL;
+	struct fib6_info *iter = NULL;
 	struct fib6_info __rcu **ins;
+	struct fib6_info __rcu **fallback_ins = NULL;
 	int replace = (info->nlh &&
 		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
-	int append = (info->nlh &&
-		       (info->nlh->nlmsg_flags & NLM_F_APPEND));
 	int add = (!info->nlh ||
 		   (info->nlh->nlmsg_flags & NLM_F_CREATE));
 	int found = 0;
+	bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
 	u16 nlflags = NLM_F_EXCL;
 	int err;
 
-	if (append)
+	if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
 		nlflags |= NLM_F_APPEND;
 
 	ins = &fn->leaf;
@@ -970,8 +969,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 
 			nlflags &= ~NLM_F_EXCL;
 			if (replace) {
-				found++;
-				break;
+				if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+					found++;
+					break;
+				}
+				if (rt_can_ecmp)
+					fallback_ins = fallback_ins ?: ins;
+				goto next_iter;
 			}
 
 			if (rt6_duplicate_nexthop(iter, rt)) {
@@ -986,51 +990,71 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 				fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
 				return -EEXIST;
 			}
-
-			/* first route that matches */
-			if (!match)
-				match = iter;
+			/* If we have the same destination and the same metric,
+			 * but not the same gateway, then the route we try to
+			 * add is sibling to this route, increment our counter
+			 * of siblings, and later we will add our route to the
+			 * list.
+			 * Only static routes (which don't have flag
+			 * RTF_EXPIRES) are used for ECMPv6.
+			 *
+			 * To avoid long list, we only had siblings if the
+			 * route have a gateway.
+			 */
+			if (rt_can_ecmp &&
+			    rt6_qualify_for_ecmp(iter))
+				rt->fib6_nsiblings++;
 		}
 
 		if (iter->fib6_metric > rt->fib6_metric)
 			break;
 
+next_iter:
 		ins = &iter->fib6_next;
 	}
 
+	if (fallback_ins && !found) {
+		/* No ECMP-able route found, replace first non-ECMP one */
+		ins = fallback_ins;
+		iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
+		found++;
+	}
+
 	/* Reset round-robin state, if necessary */
 	if (ins == &fn->leaf)
 		fn->rr_ptr = NULL;
 
 	/* Link this route to others same route. */
-	if (append && match) {
+	if (rt->fib6_nsiblings) {
+		unsigned int fib6_nsiblings;
 		struct fib6_info *sibling, *temp_sibling;
 
-		if (rt->fib6_flags & RTF_REJECT) {
-			NL_SET_ERR_MSG(extack,
-				       "Can not append a REJECT route");
-			return -EINVAL;
-		} else if (match->fib6_flags & RTF_REJECT) {
-			NL_SET_ERR_MSG(extack,
-				       "Can not append to a REJECT route");
-			return -EINVAL;
+		/* Find the first route that have the same metric */
+		sibling = leaf;
+		while (sibling) {
+			if (sibling->fib6_metric == rt->fib6_metric &&
+			    rt6_qualify_for_ecmp(sibling)) {
+				list_add_tail(&rt->fib6_siblings,
+					      &sibling->fib6_siblings);
+				break;
+			}
+			sibling = rcu_dereference_protected(sibling->fib6_next,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
 		}
-		event = FIB_EVENT_ENTRY_APPEND;
-		rt->fib6_nsiblings = match->fib6_nsiblings;
-		list_add_tail(&rt->fib6_siblings, &match->fib6_siblings);
-		match->fib6_nsiblings++;
-
 		/* For each sibling in the list, increment the counter of
 		 * siblings. BUG() if counters does not match, list of siblings
 		 * is broken!
 		 */
+		fib6_nsiblings = 0;
 		list_for_each_entry_safe(sibling, temp_sibling,
-					 &match->fib6_siblings, fib6_siblings) {
+					 &rt->fib6_siblings, fib6_siblings) {
 			sibling->fib6_nsiblings++;
-			BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings);
+			BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings);
+			fib6_nsiblings++;
 		}
-
-		rt6_multipath_rebalance(match);
+		BUG_ON(fib6_nsiblings != rt->fib6_nsiblings);
+		rt6_multipath_rebalance(temp_sibling);
 	}
 
 	/*
@@ -1043,8 +1067,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
 add:
 		nlflags |= NLM_F_CREATE;
 
-		err = call_fib6_entry_notifiers(info->nl_net, event, rt,
-						extack);
+		err = call_fib6_entry_notifiers(info->nl_net,
+						FIB_EVENT_ENTRY_ADD,
+						rt, extack);
 		if (err)
 			return err;
 
@@ -1062,7 +1087,7 @@ add:
 		}
 
 	} else {
-		struct fib6_info *tmp;
+		int nsiblings;
 
 		if (!found) {
 			if (add)
@@ -1077,57 +1102,48 @@ add:
 		if (err)
 			return err;
 
-		/* if route being replaced has siblings, set tmp to
-		 * last one, otherwise tmp is current route. this is
-		 * used to set fib6_next for new route
-		 */
-		if (iter->fib6_nsiblings)
-			tmp = list_last_entry(&iter->fib6_siblings,
-					      struct fib6_info,
-					      fib6_siblings);
-		else
-			tmp = iter;
-
-		/* insert new route */
 		atomic_inc(&rt->fib6_ref);
 		rcu_assign_pointer(rt->fib6_node, fn);
-		rt->fib6_next = tmp->fib6_next;
+		rt->fib6_next = iter->fib6_next;
 		rcu_assign_pointer(*ins, rt);
-
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
 		}
+		nsiblings = iter->fib6_nsiblings;
+		iter->fib6_node = NULL;
+		fib6_purge_rt(iter, fn, info->nl_net);
+		if (rcu_access_pointer(fn->rr_ptr) == iter)
+			fn->rr_ptr = NULL;
+		fib6_info_release(iter);
 
-		/* delete old route */
-		rt = iter;
-
-		if (rt->fib6_nsiblings) {
-			struct fib6_info *tmp;
-
+		if (nsiblings) {
 			/* Replacing an ECMP route, remove all siblings */
-			list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings,
-						 fib6_siblings) {
-				iter->fib6_node = NULL;
-				fib6_purge_rt(iter, fn, info->nl_net);
-				if (rcu_access_pointer(fn->rr_ptr) == iter)
-					fn->rr_ptr = NULL;
-				fib6_info_release(iter);
-
-				rt->fib6_nsiblings--;
-				info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+			ins = &rt->fib6_next;
+			iter = rcu_dereference_protected(*ins,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
+			while (iter) {
+				if (iter->fib6_metric > rt->fib6_metric)
+					break;
+				if (rt6_qualify_for_ecmp(iter)) {
+					*ins = iter->fib6_next;
+					iter->fib6_node = NULL;
+					fib6_purge_rt(iter, fn, info->nl_net);
+					if (rcu_access_pointer(fn->rr_ptr) == iter)
+						fn->rr_ptr = NULL;
+					fib6_info_release(iter);
+					nsiblings--;
+					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
+				} else {
+					ins = &iter->fib6_next;
+				}
+				iter = rcu_dereference_protected(*ins,
+					lockdep_is_held(&rt->fib6_table->tb6_lock));
 			}
+			WARN_ON(nsiblings != 0);
 		}
-
-		WARN_ON(rt->fib6_nsiblings != 0);
-
-		rt->fib6_node = NULL;
-		fib6_purge_rt(rt, fn, info->nl_net);
-		if (rcu_access_pointer(fn->rr_ptr) == rt)
-			fn->rr_ptr = NULL;
-		fib6_info_release(rt);
 	}
 
 	return 0;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c8cf2fdbb13b..cd2cfb04e5d8 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -927,7 +927,6 @@ tx_err:
 static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
-	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device_stats *stats;
@@ -1010,6 +1009,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 			goto tx_err;
 		}
 	} else {
+		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+
 		switch (skb->protocol) {
 		case htons(ETH_P_IP):
 			memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a14fb4fcdf18..3168847c30d1 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 	to->dev = from->dev;
 	to->mark = from->mark;
 
+	skb_copy_hash(to, from);
+
 #ifdef CONFIG_NET_SCHED
 	to->tc_index = from->tc_index;
 #endif
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4d780c7f0130..568ca4187cd1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -398,6 +398,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 	case IPV6_DSTOPTS:
 	{
 		struct ipv6_txoptions *opt;
+		struct ipv6_opt_hdr *new = NULL;
+
+		/* hop-by-hop / destination options are privileged option */
+		retv = -EPERM;
+		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
+			break;
 
 		/* remove any sticky options header with a zero option
 		 * length, per RFC3542.
@@ -409,17 +415,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
 		else if (optlen < sizeof(struct ipv6_opt_hdr) ||
 			 optlen & 0x7 || optlen > 8 * 255)
 			goto e_inval;
-
-		/* hop-by-hop / destination options are privileged option */
-		retv = -EPERM;
-		if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW))
-			break;
+		else {
+			new = memdup_user(optval, optlen);
+			if (IS_ERR(new)) {
+				retv = PTR_ERR(new);
+				break;
+			}
+			if (unlikely(ipv6_optlen(new) > optlen)) {
+				kfree(new);
+				goto e_inval;
+			}
+		}
 
 		opt = rcu_dereference_protected(np->opt,
 						lockdep_sock_is_held(sk));
-		opt = ipv6_renew_options(sk, opt, optname,
-					 (struct ipv6_opt_hdr __user *)optval,
-					 optlen);
+		opt = ipv6_renew_options(sk, opt, optname, new);
+		kfree(new);
 		if (IS_ERR(opt)) {
 			retv = PTR_ERR(opt);
 			break;
@@ -718,8 +729,9 @@ done:
 			struct sockaddr_in6 *psin6;
 
 			psin6 = (struct sockaddr_in6 *)&greqs.gsr_group;
-			retv = ipv6_sock_mc_join(sk, greqs.gsr_interface,
-						 &psin6->sin6_addr);
+			retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface,
+						     &psin6->sin6_addr,
+						     MCAST_INCLUDE);
 			/* prior join w/ different source is ok */
 			if (retv && retv != -EADDRINUSE)
 				break;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index c0c74088f2af..f60f310785fd 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -95,6 +95,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 			  int delta);
 static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml,
 			    struct inet6_dev *idev);
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+			     const struct in6_addr *addr, unsigned int mode);
 
 #define MLD_QRV_DEFAULT		2
 /* RFC3810, 9.2. Query Interval */
@@ -132,7 +134,8 @@ static int unsolicited_report_interval(struct inet6_dev *idev)
 	return iv > 0 ? iv : 1;
 }
 
-int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+static int __ipv6_sock_mc_join(struct sock *sk, int ifindex,
+			       const struct in6_addr *addr, unsigned int mode)
 {
 	struct net_device *dev = NULL;
 	struct ipv6_mc_socklist *mc_lst;
@@ -179,7 +182,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	}
 
 	mc_lst->ifindex = dev->ifindex;
-	mc_lst->sfmode = MCAST_EXCLUDE;
+	mc_lst->sfmode = mode;
 	rwlock_init(&mc_lst->sflock);
 	mc_lst->sflist = NULL;
 
@@ -187,7 +190,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	 *	now add/increase the group membership on the device
 	 */
 
-	err = ipv6_dev_mc_inc(dev, addr);
+	err = __ipv6_dev_mc_inc(dev, addr, mode);
 
 	if (err) {
 		sock_kfree_s(sk, mc_lst, sizeof(*mc_lst));
@@ -199,8 +202,19 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 
 	return 0;
 }
+
+int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
+{
+	return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE);
+}
 EXPORT_SYMBOL(ipv6_sock_mc_join);
 
+int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex,
+			  const struct in6_addr *addr, unsigned int mode)
+{
+	return __ipv6_sock_mc_join(sk, ifindex, addr, mode);
+}
+
 /*
  *	socket leave on multicast group
  */
@@ -646,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 	return rv;
 }
 
-static void igmp6_group_added(struct ifmcaddr6 *mc)
+static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode)
 {
 	struct net_device *dev = mc->idev->dev;
 	char buf[MAX_ADDR_LEN];
@@ -672,7 +686,13 @@ static void igmp6_group_added(struct ifmcaddr6 *mc)
 	}
 	/* else v2 */
 
-	mc->mca_crcount = mc->idev->mc_qrv;
+	/* Based on RFC3810 6.1, for newly added INCLUDE SSM, we
+	 * should not send filter-mode change record as the mode
+	 * should be from IN() to IN(A).
+	 */
+	if (mode == MCAST_EXCLUDE)
+		mc->mca_crcount = mc->idev->mc_qrv;
+
 	mld_ifc_event(mc->idev);
 }
 
@@ -770,13 +790,13 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im)
 	spin_lock_bh(&im->mca_lock);
 	if (pmc) {
 		im->idev = pmc->idev;
-		im->mca_crcount = idev->mc_qrv;
-		im->mca_sfmode = pmc->mca_sfmode;
-		if (pmc->mca_sfmode == MCAST_INCLUDE) {
+		if (im->mca_sfmode == MCAST_INCLUDE) {
 			im->mca_tomb = pmc->mca_tomb;
 			im->mca_sources = pmc->mca_sources;
 			for (psf = im->mca_sources; psf; psf = psf->sf_next)
-				psf->sf_crcount = im->mca_crcount;
+				psf->sf_crcount = idev->mc_qrv;
+		} else {
+			im->mca_crcount = idev->mc_qrv;
 		}
 		in6_dev_put(pmc->idev);
 		kfree(pmc);
@@ -831,7 +851,8 @@ static void ma_put(struct ifmcaddr6 *mc)
 }
 
 static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
-				   const struct in6_addr *addr)
+				   const struct in6_addr *addr,
+				   unsigned int mode)
 {
 	struct ifmcaddr6 *mc;
 
@@ -849,9 +870,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 	refcount_set(&mc->mca_refcnt, 1);
 	spin_lock_init(&mc->mca_lock);
 
-	/* initial mode is (EX, empty) */
-	mc->mca_sfmode = MCAST_EXCLUDE;
-	mc->mca_sfcount[MCAST_EXCLUDE] = 1;
+	mc->mca_sfmode = mode;
+	mc->mca_sfcount[mode] = 1;
 
 	if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) ||
 	    IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL)
@@ -863,7 +883,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev,
 /*
  *	device multicast group inc (add if not found)
  */
-int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+static int __ipv6_dev_mc_inc(struct net_device *dev,
+			     const struct in6_addr *addr, unsigned int mode)
 {
 	struct ifmcaddr6 *mc;
 	struct inet6_dev *idev;
@@ -887,14 +908,13 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 		if (ipv6_addr_equal(&mc->mca_addr, addr)) {
 			mc->mca_users++;
 			write_unlock_bh(&idev->lock);
-			ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0,
-				NULL, 0);
+			ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0);
 			in6_dev_put(idev);
 			return 0;
 		}
 	}
 
-	mc = mca_alloc(idev, addr);
+	mc = mca_alloc(idev, addr, mode);
 	if (!mc) {
 		write_unlock_bh(&idev->lock);
 		in6_dev_put(idev);
@@ -911,11 +931,16 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 	write_unlock_bh(&idev->lock);
 
 	mld_del_delrec(idev, mc);
-	igmp6_group_added(mc);
+	igmp6_group_added(mc, mode);
 	ma_put(mc);
 	return 0;
 }
 
+int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
+{
+	return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE);
+}
+
 /*
  *	device multicast group del
  */
@@ -1751,7 +1776,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
 
 		psf_next = psf->sf_next;
 
-		if (!is_in(pmc, psf, type, gdeleted, sdeleted)) {
+		if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) {
 			psf_prev = psf;
 			continue;
 		}
@@ -2066,7 +2091,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev)
 		if (pmc->mca_sfcount[MCAST_EXCLUDE])
 			type = MLD2_CHANGE_TO_EXCLUDE;
 		else
-			type = MLD2_CHANGE_TO_INCLUDE;
+			type = MLD2_ALLOW_NEW_SOURCES;
 		skb = add_grec(skb, pmc, type, 0, 0, 1);
 		spin_unlock_bh(&pmc->mca_lock);
 	}
@@ -2546,7 +2571,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	ipv6_mc_reset(idev);
 	for (i = idev->mc_list; i; i = i->next) {
 		mld_del_delrec(idev, i);
-		igmp6_group_added(i);
+		igmp6_group_added(i, i->mca_sfmode);
 	}
 	read_unlock_bh(&idev->lock);
 }
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index e640d2f3c55c..0ec273997d1d 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -811,7 +811,7 @@ static void ndisc_recv_ns(struct sk_buff *skb)
 			return;
 		}
 	}
-	if (ndopts.nd_opts_nonce)
+	if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
 		memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
 
 	inc = ipv6_addr_is_multicast(daddr);
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 7eab959734bc..daf2e9e9193d 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -1909,6 +1909,7 @@ static struct xt_match ip6t_builtin_mt[] __read_mostly = {
 		.checkentry = icmp6_checkentry,
 		.proto      = IPPROTO_ICMPV6,
 		.family     = NFPROTO_IPV6,
+		.me	    = THIS_MODULE,
 	},
 };
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 5e0332014c17..e4d9e6976d3c 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net)
 	if (hdr == NULL)
 		goto err_reg;
 
-	net->nf_frag.sysctl.frags_hdr = hdr;
+	net->nf_frag_frags_hdr = hdr;
 	return 0;
 
 err_reg:
@@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
 {
 	struct ctl_table *table;
 
-	table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
-	unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+	table = net->nf_frag_frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->nf_frag_frags_hdr);
 	if (!net_eq(net, &init_net))
 		kfree(table);
 }
@@ -585,6 +585,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	    fq->q.meat == fq->q.len &&
 	    nf_ct_frag6_reasm(fq, skb, dev))
 		ret = 0;
+	else
+		skb_dst_drop(skb);
 
 out_unlock:
 	spin_unlock_bh(&fq->q.lock);
diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c
index bf1d6c421e3b..5dfd33af6451 100644
--- a/net/ipv6/netfilter/nf_tproxy_ipv6.c
+++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c
@@ -55,7 +55,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 		 * to a listener socket if there's one */
 		struct sock *sk2;
 
-		sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto,
+		sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto,
 					    &iph->saddr,
 					    nf_tproxy_laddr6(skb, laddr, &iph->daddr),
 					    hp->source,
@@ -72,7 +72,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff,
 EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6);
 
 struct sock *
-nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
+nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff,
 		      const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
 		      const __be16 sport, const __be16 dport,
@@ -80,15 +80,20 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
 		      const enum nf_tproxy_lookup_t lookup_type)
 {
 	struct sock *sk;
-	struct tcphdr *tcph;
 
 	switch (protocol) {
-	case IPPROTO_TCP:
+	case IPPROTO_TCP: {
+		struct tcphdr _hdr, *hp;
+
+		hp = skb_header_pointer(skb, thoff,
+					sizeof(struct tcphdr), &_hdr);
+		if (hp == NULL)
+			return NULL;
+
 		switch (lookup_type) {
 		case NF_TPROXY_LOOKUP_LISTENER:
-			tcph = hp;
 			sk = inet6_lookup_listener(net, &tcp_hashinfo, skb,
-						   thoff + __tcp_hdrlen(tcph),
+						   thoff + __tcp_hdrlen(hp),
 						   saddr, sport,
 						   daddr, ntohs(dport),
 						   in->ifindex, 0);
@@ -110,6 +115,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
 			BUG();
 		}
 		break;
+		}
 	case IPPROTO_UDP:
 		sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
 				     in->ifindex);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 86a0e4333d42..ec18b3ce8b6d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -972,10 +972,10 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
 	rt->dst.lastuse = jiffies;
 }
 
+/* Caller must already hold reference to @from */
 static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
 {
 	rt->rt6i_flags &= ~RTF_EXPIRES;
-	fib6_info_hold(from);
 	rcu_assign_pointer(rt->from, from);
 	dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
 	if (from->fib6_metrics != &dst_default_metrics) {
@@ -984,6 +984,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
 	}
 }
 
+/* Caller must already hold reference to @ort */
 static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
 {
 	struct net_device *dev = fib6_info_nh_dev(ort);
@@ -1044,9 +1045,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
 	struct net_device *dev = rt->fib6_nh.nh_dev;
 	struct rt6_info *nrt;
 
+	if (!fib6_info_hold_safe(rt))
+		return NULL;
+
 	nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
 	if (nrt)
 		ip6_rt_copy_init(nrt, rt);
+	else
+		fib6_info_release(rt);
 
 	return nrt;
 }
@@ -1178,10 +1184,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
 	 *	Clone the route.
 	 */
 
+	if (!fib6_info_hold_safe(ort))
+		return NULL;
+
 	dev = ip6_rt_get_dev_rcu(ort);
 	rt = ip6_dst_alloc(dev_net(dev), dev, 0);
-	if (!rt)
+	if (!rt) {
+		fib6_info_release(ort);
 		return NULL;
+	}
 
 	ip6_rt_copy_init(rt, ort);
 	rt->rt6i_flags |= RTF_CACHE;
@@ -1210,12 +1221,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
 	struct net_device *dev;
 	struct rt6_info *pcpu_rt;
 
+	if (!fib6_info_hold_safe(rt))
+		return NULL;
+
 	rcu_read_lock();
 	dev = ip6_rt_get_dev_rcu(rt);
 	pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
 	rcu_read_unlock();
-	if (!pcpu_rt)
+	if (!pcpu_rt) {
+		fib6_info_release(rt);
 		return NULL;
+	}
 	ip6_rt_copy_init(pcpu_rt, rt);
 	pcpu_rt->rt6i_flags |= RTF_PCPU;
 	return pcpu_rt;
@@ -2486,7 +2502,7 @@ restart:
 
 out:
 	if (ret)
-		dst_hold(&ret->dst);
+		ip6_hold_safe(net, &ret, true);
 	else
 		ret = ip6_create_rt_rcu(rt);
 
@@ -3303,7 +3319,8 @@ static int ip6_route_del(struct fib6_config *cfg,
 				continue;
 			if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
 				continue;
-			fib6_info_hold(rt);
+			if (!fib6_info_hold_safe(rt))
+				continue;
 			rcu_read_unlock();
 
 			/* if gateway was specified only delete the one hop */
@@ -3409,6 +3426,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 
 	rcu_read_lock();
 	from = rcu_dereference(rt->from);
+	/* This fib6_info_hold() is safe here because we hold reference to rt
+	 * and rt already holds reference to fib6_info.
+	 */
 	fib6_info_hold(from);
 	rcu_read_unlock();
 
@@ -3470,7 +3490,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 			continue;
 		if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
 			continue;
-		fib6_info_hold(rt);
+		if (!fib6_info_hold_safe(rt))
+			continue;
 		break;
 	}
 out:
@@ -3530,8 +3551,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
 		    ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
 			break;
 	}
-	if (rt)
-		fib6_info_hold(rt);
+	if (rt && !fib6_info_hold_safe(rt))
+		rt = NULL;
 	rcu_read_unlock();
 	return rt;
 }
@@ -3579,8 +3600,8 @@ restart:
 		struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL;
 
 		if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
-		    (!idev || idev->cnf.accept_ra != 2)) {
-			fib6_info_hold(rt);
+		    (!idev || idev->cnf.accept_ra != 2) &&
+		    fib6_info_hold_safe(rt)) {
 			rcu_read_unlock();
 			ip6_del_rt(net, rt);
 			goto restart;
@@ -3842,7 +3863,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 			lockdep_is_held(&rt->fib6_table->tb6_lock));
 	while (iter) {
 		if (iter->fib6_metric == rt->fib6_metric &&
-		    iter->fib6_nsiblings)
+		    rt6_qualify_for_ecmp(iter))
 			return iter;
 		iter = rcu_dereference_protected(iter->fib6_next,
 				lockdep_is_held(&rt->fib6_table->tb6_lock));
@@ -4388,6 +4409,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			rt = NULL;
 			goto cleanup;
 		}
+		if (!rt6_qualify_for_ecmp(rt)) {
+			err = -EINVAL;
+			NL_SET_ERR_MSG(extack,
+				       "Device only routes can not be added for IPv6 using the multipath API.");
+			fib6_info_release(rt);
+			goto cleanup;
+		}
 
 		rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
 
@@ -4439,7 +4467,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		 */
 		cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
 						     NLM_F_REPLACE);
-		cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND;
 		nhn++;
 	}
 
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 33fb35cbfac1..558fe8cc6d43 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void)
 			return -ENOMEM;
 
 		for_each_possible_cpu(cpu) {
-			tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL);
+			tfm = crypto_alloc_shash(algo->name, 0, 0);
 			if (IS_ERR(tfm))
 				return PTR_ERR(tfm);
 			p_tfm = per_cpu_ptr(algo->tfms, cpu);
diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 19ccf0dc996c..a8854dd3e9c5 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -101,7 +101,7 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
 
 	if (do_flowlabel > 0) {
 		hash = skb_get_hash(skb);
-		rol32(hash, 16);
+		hash = rol32(hash, 16);
 		flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 	} else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) {
 		flowlabel = ip6_flowlabel(inner_hdr);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 7efa9fd7e109..03e6b7a2bc53 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 					   &tcp_hashinfo, NULL, 0,
 					   &ipv6h->saddr,
 					   th->source, &ipv6h->daddr,
-					   ntohs(th->source), tcp_v6_iif(skb),
+					   ntohs(th->source),
+					   tcp_v6_iif_l3_slave(skb),
 					   tcp_v6_sdif(skb));
 		if (!sk1)
 			goto out;
@@ -1609,7 +1610,8 @@ do_time_wait:
 					    skb, __tcp_hdrlen(th),
 					    &ipv6_hdr(skb)->saddr, th->source,
 					    &ipv6_hdr(skb)->daddr,
-					    ntohs(th->dest), tcp_v6_iif(skb),
+					    ntohs(th->dest),
+					    tcp_v6_iif_l3_slave(skb),
 					    sdif);
 		if (sk2) {
 			struct inet_timewait_sock *tw = inet_twsk(sk);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 0a38cc1cbebc..932985ca4e66 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb,
 		     sdata->control_port_over_nl80211)) {
 		struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 		bool noencrypt = status->flag & RX_FLAG_DECRYPTED;
-		struct ethhdr *ehdr = eth_hdr(skb);
 
-		cfg80211_rx_control_port(dev, skb->data, skb->len,
-					 ehdr->h_source,
-					 be16_to_cpu(skb->protocol), noencrypt);
+		cfg80211_rx_control_port(dev, skb, noencrypt);
 		dev_kfree_skb(skb);
 	} else {
 		/* deliver to local stack */
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 44b5dfe8727d..fa1f1e63a264 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -4845,7 +4845,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev,
 	skb_reset_network_header(skb);
 	skb_reset_mac_header(skb);
 
+	local_bh_disable();
 	__ieee80211_subif_start_xmit(skb, skb->dev, flags);
+	local_bh_enable();
 
 	return 0;
 }
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 5e2e511c4a6f..d02fbfec3783 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		if (!sta->uploaded)
 			continue;
 
-		if (sta->sdata->vif.type != NL80211_IFTYPE_AP)
+		if (sta->sdata->vif.type != NL80211_IFTYPE_AP &&
+		    sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN)
 			continue;
 
 		for (state = IEEE80211_STA_NOTEXIST;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index dbd7d1fad277..f0a1c536ef15 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -460,6 +460,13 @@ config NF_TABLES
 
 if NF_TABLES
 
+config NF_TABLES_SET
+	tristate "Netfilter nf_tables set infrastructure"
+	help
+	  This option enables the nf_tables set infrastructure that allows to
+	  look up for elements in a set and to build one-way mappings between
+	  matchings and actions.
+
 config NF_TABLES_INET
 	depends on IPV6
 	select NF_TABLES_IPV4
@@ -493,24 +500,6 @@ config NFT_FLOW_OFFLOAD
 	  This option adds the "flow_offload" expression that you can use to
 	  choose what flows are placed into the hardware.
 
-config NFT_SET_RBTREE
-	tristate "Netfilter nf_tables rbtree set module"
-	help
-	  This option adds the "rbtree" set type (Red Black tree) that is used
-	  to build interval-based sets.
-
-config NFT_SET_HASH
-	tristate "Netfilter nf_tables hash set module"
-	help
-	  This option adds the "hash" set type that is used to build one-way
-	  mappings between matchings and actions.
-
-config NFT_SET_BITMAP
-	tristate "Netfilter nf_tables bitmap set module"
-	help
-	  This option adds the "bitmap" set type that is used to build sets
-	  whose keys are smaller or equal to 16 bits.
-
 config NFT_COUNTER
 	tristate "Netfilter nf_tables counter module"
 	help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 44449389e527..8a76dced974d 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -78,7 +78,11 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
 		  nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
 		  nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o
 
+nf_tables_set-objs := nf_tables_set_core.o \
+		      nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
+
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
+obj-$(CONFIG_NF_TABLES_SET)	+= nf_tables_set.o
 obj-$(CONFIG_NFT_COMPAT)	+= nft_compat.o
 obj-$(CONFIG_NFT_CONNLIMIT)	+= nft_connlimit.o
 obj-$(CONFIG_NFT_NUMGEN)	+= nft_numgen.o
@@ -91,9 +95,6 @@ obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 obj-$(CONFIG_NFT_QUOTA)		+= nft_quota.o
 obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
 obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
-obj-$(CONFIG_NFT_SET_RBTREE)	+= nft_set_rbtree.o
-obj-$(CONFIG_NFT_SET_HASH)	+= nft_set_hash.o
-obj-$(CONFIG_NFT_SET_BITMAP)	+= nft_set_bitmap.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
 obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index d8383609fe28..510039862aa9 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -47,6 +47,8 @@ struct nf_conncount_tuple {
 	struct hlist_node		node;
 	struct nf_conntrack_tuple	tuple;
 	struct nf_conntrack_zone	zone;
+	int				cpu;
+	u32				jiffies32;
 };
 
 struct nf_conncount_rb {
@@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head,
 		return false;
 	conn->tuple = *tuple;
 	conn->zone = *zone;
+	conn->cpu = raw_smp_processor_id();
+	conn->jiffies32 = (u32)jiffies;
 	hlist_add_head(&conn->node, head);
 	return true;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
 
+static const struct nf_conntrack_tuple_hash *
+find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+{
+	const struct nf_conntrack_tuple_hash *found;
+	unsigned long a, b;
+	int cpu = raw_smp_processor_id();
+	__s32 age;
+
+	found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
+	if (found)
+		return found;
+	b = conn->jiffies32;
+	a = (u32)jiffies;
+
+	/* conn might have been added just before by another cpu and
+	 * might still be unconfirmed.  In this case, nf_conntrack_find()
+	 * returns no result.  Thus only evict if this cpu added the
+	 * stale entry or if the entry is older than two jiffies.
+	 */
+	age = a - b;
+	if (conn->cpu == cpu || age >= 2) {
+		hlist_del(&conn->node);
+		kmem_cache_free(conncount_conn_cachep, conn);
+		return ERR_PTR(-ENOENT);
+	}
+
+	return ERR_PTR(-EAGAIN);
+}
+
 unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 				 const struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_zone *zone,
@@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn;
-	struct hlist_node *n;
 	struct nf_conn *found_ct;
+	struct hlist_node *n;
 	unsigned int length = 0;
 
 	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	hlist_for_each_entry_safe(conn, n, head, node) {
-		found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple);
-		if (found == NULL) {
-			hlist_del(&conn->node);
-			kmem_cache_free(conncount_conn_cachep, conn);
+		found = find_or_evict(net, conn);
+		if (IS_ERR(found)) {
+			/* Not found, but might be about to be confirmed */
+			if (PTR_ERR(found) == -EAGAIN) {
+				length++;
+				if (!tuple)
+					continue;
+
+				if (nf_ct_tuple_equal(&conn->tuple, tuple) &&
+				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
+				    nf_ct_zone_id(zone, zone->dir))
+					*addit = false;
+			}
 			continue;
 		}
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3465da2a98bd..3d5280425027 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2043,7 +2043,7 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
 		return -EOPNOTSUPP;
 
 	/* On boot, we can set this without any fancy locking. */
-	if (!nf_conntrack_htable_size)
+	if (!nf_conntrack_hash)
 		return param_set_uint(val, kp);
 
 	rc = kstrtouint(val, 0, &hashsize);
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index 551a1eddf0fa..a75b11c39312 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me)
 
 	nf_ct_expect_iterate_destroy(expect_iter_me, NULL);
 	nf_ct_iterate_destroy(unhelp, me);
+
+	/* Maybe someone has gotten the helper already when unhelp above.
+	 * So need to wait it.
+	 */
+	synchronize_rcu();
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister);
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index abe647d5b8c6..9ce6336d1e55 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 		 * We currently ignore Sync packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 		[DCCP_PKT_SYNCACK] = {
 		/*
 		 * We currently ignore SyncAck packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 	},
 	[CT_DCCP_ROLE_SERVER] = {
@@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 		 * We currently ignore Sync packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 		[DCCP_PKT_SYNCACK] = {
 		/*
 		 * We currently ignore SyncAck packets
 		 *
 		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
+			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
 		},
 	},
 };
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 426457047578..a61d6df6e5f6 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 	if (write) {
 		struct ctl_table tmp = *table;
 
+		/* proc_dostring() can append to existing strings, so we need to
+		 * initialize it as an empty string.
+		 */
+		buf[0] = '\0';
 		tmp.data = buf;
 		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
 		if (r)
@@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write,
 		rcu_assign_pointer(net->nf.nf_loggers[tindex], logger);
 		mutex_unlock(&nf_log_mutex);
 	} else {
+		struct ctl_table tmp = *table;
+
+		tmp.data = buf;
 		mutex_lock(&nf_log_mutex);
 		logger = nft_log_dereference(net->nf.nf_loggers[tindex]);
 		if (!logger)
-			table->data = "NONE";
+			strlcpy(buf, "NONE", sizeof(buf));
 		else
-			table->data = logger->name;
-		r = proc_dostring(table, write, buffer, lenp, ppos);
+			strlcpy(buf, logger->name, sizeof(buf));
 		mutex_unlock(&nf_log_mutex);
+		r = proc_dostring(&tmp, write, buffer, lenp, ppos);
 	}
 
 	return r;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 896d4a36081d..f5745e4c6513 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 {
 	ctx->net	= net;
 	ctx->family	= family;
+	ctx->level	= 0;
 	ctx->table	= table;
 	ctx->chain	= chain;
 	ctx->nla   	= nla;
@@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	struct nft_base_chain *basechain;
 	struct nft_stats *stats = NULL;
 	struct nft_chain_hook hook;
-	const struct nlattr *name;
 	struct nf_hook_ops *ops;
 	struct nft_trans *trans;
 	int err;
@@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			return PTR_ERR(stats);
 	}
 
+	err = -ENOMEM;
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN,
 				sizeof(struct nft_trans_chain));
-	if (trans == NULL) {
-		free_percpu(stats);
-		return -ENOMEM;
-	}
+	if (trans == NULL)
+		goto err;
 
 	nft_trans_chain_stats(trans) = stats;
 	nft_trans_chain_update(trans) = true;
@@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	else
 		nft_trans_chain_policy(trans) = -1;
 
-	name = nla[NFTA_CHAIN_NAME];
-	if (nla[NFTA_CHAIN_HANDLE] && name) {
-		nft_trans_chain_name(trans) =
-			nla_strdup(name, GFP_KERNEL);
-		if (!nft_trans_chain_name(trans)) {
-			kfree(trans);
-			free_percpu(stats);
-			return -ENOMEM;
+	if (nla[NFTA_CHAIN_HANDLE] &&
+	    nla[NFTA_CHAIN_NAME]) {
+		struct nft_trans *tmp;
+		char *name;
+
+		err = -ENOMEM;
+		name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL);
+		if (!name)
+			goto err;
+
+		err = -EEXIST;
+		list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) {
+			if (tmp->msg_type == NFT_MSG_NEWCHAIN &&
+			    tmp->ctx.table == table &&
+			    nft_trans_chain_update(tmp) &&
+			    nft_trans_chain_name(tmp) &&
+			    strcmp(name, nft_trans_chain_name(tmp)) == 0) {
+				kfree(name);
+				goto err;
+			}
 		}
+
+		nft_trans_chain_name(trans) = name;
 	}
 	list_add_tail(&trans->list, &ctx->net->nft.commit_list);
 
 	return 0;
+err:
+	free_percpu(stats);
+	kfree(trans);
+	return err;
 }
 
 static int nf_tables_newchain(struct net *net, struct sock *nlsk,
@@ -2254,6 +2271,39 @@ done:
 	return skb->len;
 }
 
+static int nf_tables_dump_rules_start(struct netlink_callback *cb)
+{
+	const struct nlattr * const *nla = cb->data;
+	struct nft_rule_dump_ctx *ctx = NULL;
+
+	if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
+		ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
+		if (!ctx)
+			return -ENOMEM;
+
+		if (nla[NFTA_RULE_TABLE]) {
+			ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
+							GFP_ATOMIC);
+			if (!ctx->table) {
+				kfree(ctx);
+				return -ENOMEM;
+			}
+		}
+		if (nla[NFTA_RULE_CHAIN]) {
+			ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
+						GFP_ATOMIC);
+			if (!ctx->chain) {
+				kfree(ctx->table);
+				kfree(ctx);
+				return -ENOMEM;
+			}
+		}
+	}
+
+	cb->data = ctx;
+	return 0;
+}
+
 static int nf_tables_dump_rules_done(struct netlink_callback *cb)
 {
 	struct nft_rule_dump_ctx *ctx = cb->data;
@@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start= nf_tables_dump_rules_start,
 			.dump = nf_tables_dump_rules,
 			.done = nf_tables_dump_rules_done,
 			.module = THIS_MODULE,
+			.data = (void *)nla,
 		};
 
-		if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) {
-			struct nft_rule_dump_ctx *ctx;
-
-			ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC);
-			if (!ctx)
-				return -ENOMEM;
-
-			if (nla[NFTA_RULE_TABLE]) {
-				ctx->table = nla_strdup(nla[NFTA_RULE_TABLE],
-							GFP_ATOMIC);
-				if (!ctx->table) {
-					kfree(ctx);
-					return -ENOMEM;
-				}
-			}
-			if (nla[NFTA_RULE_CHAIN]) {
-				ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN],
-							GFP_ATOMIC);
-				if (!ctx->chain) {
-					kfree(ctx->table);
-					kfree(ctx);
-					return -ENOMEM;
-				}
-			}
-			c.data = ctx;
-		}
-
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain)
 	struct nft_rule *rule;
 	int err;
 
+	if (ctx->level == NFT_JUMP_STACK_SIZE)
+		return -EMLINK;
+
 	list_for_each_entry(rule, &chain->rules, list) {
 		if (!nft_is_active_next(ctx->net, rule))
 			continue;
@@ -3161,6 +3189,18 @@ done:
 	return skb->len;
 }
 
+static int nf_tables_dump_sets_start(struct netlink_callback *cb)
+{
+	struct nft_ctx *ctx_dump = NULL;
+
+	ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC);
+	if (ctx_dump == NULL)
+		return -ENOMEM;
+
+	cb->data = ctx_dump;
+	return 0;
+}
+
 static int nf_tables_dump_sets_done(struct netlink_callback *cb)
 {
 	kfree(cb->data);
@@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_sets_start,
 			.dump = nf_tables_dump_sets,
 			.done = nf_tables_dump_sets_done,
+			.data = &ctx,
 			.module = THIS_MODULE,
 		};
-		struct nft_ctx *ctx_dump;
-
-		ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC);
-		if (ctx_dump == NULL)
-			return -ENOMEM;
-
-		*ctx_dump = ctx;
-		c.data = ctx_dump;
 
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
@@ -3849,6 +3883,15 @@ nla_put_failure:
 	return -ENOSPC;
 }
 
+static int nf_tables_dump_set_start(struct netlink_callback *cb)
+{
+	struct nft_set_dump_ctx *dump_ctx = cb->data;
+
+	cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC);
+
+	return cb->data ? 0 : -ENOMEM;
+}
+
 static int nf_tables_dump_set_done(struct netlink_callback *cb)
 {
 	kfree(cb->data);
@@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_set_start,
 			.dump = nf_tables_dump_set,
 			.done = nf_tables_dump_set_done,
 			.module = THIS_MODULE,
 		};
-		struct nft_set_dump_ctx *dump_ctx;
-
-		dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC);
-		if (!dump_ctx)
-			return -ENOMEM;
-
-		dump_ctx->set = set;
-		dump_ctx->ctx = ctx;
+		struct nft_set_dump_ctx dump_ctx = {
+			.set = set,
+			.ctx = ctx,
+		};
 
-		c.data = dump_ctx;
+		c.data = &dump_ctx;
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -4975,38 +5015,42 @@ done:
 	return skb->len;
 }
 
-static int nf_tables_dump_obj_done(struct netlink_callback *cb)
+static int nf_tables_dump_obj_start(struct netlink_callback *cb)
 {
-	struct nft_obj_filter *filter = cb->data;
+	const struct nlattr * const *nla = cb->data;
+	struct nft_obj_filter *filter = NULL;
 
-	if (filter) {
-		kfree(filter->table);
-		kfree(filter);
+	if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) {
+		filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+		if (!filter)
+			return -ENOMEM;
+
+		if (nla[NFTA_OBJ_TABLE]) {
+			filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
+			if (!filter->table) {
+				kfree(filter);
+				return -ENOMEM;
+			}
+		}
+
+		if (nla[NFTA_OBJ_TYPE])
+			filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 	}
 
+	cb->data = filter;
 	return 0;
 }
 
-static struct nft_obj_filter *
-nft_obj_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_obj_done(struct netlink_callback *cb)
 {
-	struct nft_obj_filter *filter;
-
-	filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
-	if (!filter)
-		return ERR_PTR(-ENOMEM);
+	struct nft_obj_filter *filter = cb->data;
 
-	if (nla[NFTA_OBJ_TABLE]) {
-		filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC);
-		if (!filter->table) {
-			kfree(filter);
-			return ERR_PTR(-ENOMEM);
-		}
+	if (filter) {
+		kfree(filter->table);
+		kfree(filter);
 	}
-	if (nla[NFTA_OBJ_TYPE])
-		filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
 
-	return filter;
+	return 0;
 }
 
 /* called with rcu_read_lock held */
@@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_obj_start,
 			.dump = nf_tables_dump_obj,
 			.done = nf_tables_dump_obj_done,
 			.module = THIS_MODULE,
+			.data = (void *)nla,
 		};
 
-		if (nla[NFTA_OBJ_TABLE] ||
-		    nla[NFTA_OBJ_TYPE]) {
-			struct nft_obj_filter *filter;
-
-			filter = nft_obj_filter_alloc(nla);
-			if (IS_ERR(filter))
-				return -ENOMEM;
-
-			c.data = filter;
-		}
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx,
 		flowtable->ops[i].priv		= &flowtable->data;
 		flowtable->ops[i].hook		= flowtable->data.type->hook;
 		flowtable->ops[i].dev		= dev_array[i];
-		flowtable->dev_name[i]		= kstrdup(dev_array[i]->name,
-							  GFP_KERNEL);
 	}
 
 	return err;
@@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 err6:
 	i = flowtable->ops_len;
 err5:
-	for (k = i - 1; k >= 0; k--) {
-		kfree(flowtable->dev_name[k]);
+	for (k = i - 1; k >= 0; k--)
 		nf_unregister_net_hook(net, &flowtable->ops[k]);
-	}
 
 	kfree(flowtable->ops);
 err4:
@@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net,
 		goto nla_put_failure;
 
 	for (i = 0; i < flowtable->ops_len; i++) {
-		if (flowtable->dev_name[i][0] &&
-		    nla_put_string(skb, NFTA_DEVICE_NAME,
-				   flowtable->dev_name[i]))
+		const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev);
+
+		if (dev &&
+		    nla_put_string(skb, NFTA_DEVICE_NAME, dev->name))
 			goto nla_put_failure;
 	}
 	nla_nest_end(skb, nest_devs);
@@ -5650,37 +5683,39 @@ done:
 	return skb->len;
 }
 
-static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
+static int nf_tables_dump_flowtable_start(struct netlink_callback *cb)
 {
-	struct nft_flowtable_filter *filter = cb->data;
+	const struct nlattr * const *nla = cb->data;
+	struct nft_flowtable_filter *filter = NULL;
 
-	if (!filter)
-		return 0;
+	if (nla[NFTA_FLOWTABLE_TABLE]) {
+		filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
+		if (!filter)
+			return -ENOMEM;
 
-	kfree(filter->table);
-	kfree(filter);
+		filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
+					   GFP_ATOMIC);
+		if (!filter->table) {
+			kfree(filter);
+			return -ENOMEM;
+		}
+	}
 
+	cb->data = filter;
 	return 0;
 }
 
-static struct nft_flowtable_filter *
-nft_flowtable_filter_alloc(const struct nlattr * const nla[])
+static int nf_tables_dump_flowtable_done(struct netlink_callback *cb)
 {
-	struct nft_flowtable_filter *filter;
+	struct nft_flowtable_filter *filter = cb->data;
 
-	filter = kzalloc(sizeof(*filter), GFP_ATOMIC);
 	if (!filter)
-		return ERR_PTR(-ENOMEM);
+		return 0;
 
-	if (nla[NFTA_FLOWTABLE_TABLE]) {
-		filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE],
-					   GFP_ATOMIC);
-		if (!filter->table) {
-			kfree(filter);
-			return ERR_PTR(-ENOMEM);
-		}
-	}
-	return filter;
+	kfree(filter->table);
+	kfree(filter);
+
+	return 0;
 }
 
 /* called with rcu_read_lock held */
@@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk,
 
 	if (nlh->nlmsg_flags & NLM_F_DUMP) {
 		struct netlink_dump_control c = {
+			.start = nf_tables_dump_flowtable_start,
 			.dump = nf_tables_dump_flowtable,
 			.done = nf_tables_dump_flowtable_done,
 			.module = THIS_MODULE,
+			.data = (void *)nla,
 		};
 
-		if (nla[NFTA_FLOWTABLE_TABLE]) {
-			struct nft_flowtable_filter *filter;
-
-			filter = nft_flowtable_filter_alloc(nla);
-			if (IS_ERR(filter))
-				return -ENOMEM;
-
-			c.data = filter;
-		}
 		return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c);
 	}
 
@@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
 	kfree(flowtable->name);
 	flowtable->data.type->free(&flowtable->data);
 	module_put(flowtable->data.type->owner);
+	kfree(flowtable);
 }
 
 static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net,
@@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev,
 			continue;
 
 		nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]);
-		flowtable->dev_name[i][0] = '\0';
 		flowtable->ops[i].dev = NULL;
 		break;
 	}
@@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans)
 	case NFT_MSG_DELTABLE:
 		nf_tables_table_destroy(&trans->ctx);
 		break;
+	case NFT_MSG_NEWCHAIN:
+		kfree(nft_trans_chain_name(trans));
+		break;
 	case NFT_MSG_DELCHAIN:
 		nf_tables_chain_destroy(&trans->ctx);
 		break;
@@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 			nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE);
 			break;
 		case NFT_MSG_NEWCHAIN:
-			if (nft_trans_chain_update(trans))
+			if (nft_trans_chain_update(trans)) {
 				nft_chain_commit_update(trans);
-			else
+				nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+				/* trans destroyed after rcu grace period */
+			} else {
 				nft_clear(net, trans->ctx.chain);
-
-			nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
-			nft_trans_destroy(trans);
+				nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN);
+				nft_trans_destroy(trans);
+			}
 			break;
 		case NFT_MSG_DELCHAIN:
 			nft_chain_del(trans->ctx.chain);
@@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net)
 		case NFT_MSG_NEWCHAIN:
 			if (nft_trans_chain_update(trans)) {
 				free_percpu(nft_trans_chain_stats(trans));
-
+				kfree(nft_trans_chain_name(trans));
 				nft_trans_destroy(trans);
 			} else {
 				trans->ctx.table->use--;
@@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx,
 			err = nf_tables_check_loops(ctx, data->verdict.chain);
 			if (err < 0)
 				return err;
-
-			if (ctx->chain->level + 1 >
-			    data->verdict.chain->level) {
-				if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE)
-					return -EMLINK;
-				data->verdict.chain->level = ctx->chain->level + 1;
-			}
 		}
 
 		return 0;
diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c
new file mode 100644
index 000000000000..814789644bd3
--- /dev/null
+++ b/net/netfilter/nf_tables_set_core.c
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <net/netfilter/nf_tables_core.h>
+
+static int __init nf_tables_set_module_init(void)
+{
+	nft_register_set(&nft_set_hash_fast_type);
+	nft_register_set(&nft_set_hash_type);
+	nft_register_set(&nft_set_rhash_type);
+	nft_register_set(&nft_set_bitmap_type);
+	nft_register_set(&nft_set_rbtree_type);
+
+	return 0;
+}
+
+static void __exit nf_tables_set_module_exit(void)
+{
+	nft_unregister_set(&nft_set_rbtree_type);
+	nft_unregister_set(&nft_set_bitmap_type);
+	nft_unregister_set(&nft_set_rhash_type);
+	nft_unregister_set(&nft_set_hash_type);
+	nft_unregister_set(&nft_set_hash_fast_type);
+}
+
+module_init(nf_tables_set_module_init);
+module_exit(nf_tables_set_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
index 4ccd2988f9db..ea4ba551abb2 100644
--- a/net/netfilter/nfnetlink_queue.c
+++ b/net/netfilter/nfnetlink_queue.c
@@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl,
 static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
 	[NFQA_CFG_CMD]		= { .len = sizeof(struct nfqnl_msg_config_cmd) },
 	[NFQA_CFG_PARAMS]	= { .len = sizeof(struct nfqnl_msg_config_params) },
+	[NFQA_CFG_QUEUE_MAXLEN]	= { .type = NLA_U32 },
+	[NFQA_CFG_MASK]		= { .type = NLA_U32 },
+	[NFQA_CFG_FLAGS]	= { .type = NLA_U32 },
 };
 
 static const struct nf_queue_handler nfqh = {
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 8d1ff654e5af..32535eea51b2 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -832,10 +832,18 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV]));
 	family = ctx->family;
 
+	if (strcmp(tg_name, XT_ERROR_TARGET) == 0 ||
+	    strcmp(tg_name, XT_STANDARD_TARGET) == 0 ||
+	    strcmp(tg_name, "standard") == 0)
+		return ERR_PTR(-EINVAL);
+
 	/* Re-use the existing target if it's already loaded. */
 	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
+		if (!target->target)
+			continue;
+
 		if (nft_target_cmp(target, tg_name, rev, family))
 			return &nft_target->ops;
 	}
@@ -844,6 +852,11 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	if (IS_ERR(target))
 		return ERR_PTR(-ENOENT);
 
+	if (!target->target) {
+		err = -EINVAL;
+		goto err;
+	}
+
 	if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) {
 		err = -EINVAL;
 		goto err;
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index 15adf8ca82c3..0777a93211e2 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
 				  const struct nft_data **d)
 {
 	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	struct nft_ctx *pctx = (struct nft_ctx *)ctx;
 	const struct nft_data *data;
 	int err;
 
@@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
 	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
+		pctx->level++;
 		err = nft_chain_validate(ctx, data->verdict.chain);
 		if (err < 0)
 			return err;
+		pctx->level--;
 		break;
 	default:
 		break;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index 42e6fadf1417..c2a1d84cdfc4 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx,
 				       struct nft_set_elem *elem)
 {
 	const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
+	struct nft_ctx *pctx = (struct nft_ctx *)ctx;
 	const struct nft_data *data;
+	int err;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) &&
 	    *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END)
@@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx,
 	switch (data->verdict.code) {
 	case NFT_JUMP:
 	case NFT_GOTO:
-		return nft_chain_validate(ctx, data->verdict.chain);
+		pctx->level++;
+		err = nft_chain_validate(ctx, data->verdict.chain);
+		if (err < 0)
+			return err;
+		pctx->level--;
+		break;
 	default:
-		return 0;
+		break;
 	}
+
+	return 0;
 }
 
 static int nft_lookup_validate(const struct nft_ctx *ctx,
diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c
index d6626e01c7ee..128bc16f52dd 100644
--- a/net/netfilter/nft_set_bitmap.c
+++ b/net/netfilter/nft_set_bitmap.c
@@ -296,7 +296,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features,
 	return true;
 }
 
-static struct nft_set_type nft_bitmap_type __read_mostly = {
+struct nft_set_type nft_set_bitmap_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.ops		= {
 		.privsize	= nft_bitmap_privsize,
@@ -314,20 +314,3 @@ static struct nft_set_type nft_bitmap_type __read_mostly = {
 		.get		= nft_bitmap_get,
 	},
 };
-
-static int __init nft_bitmap_module_init(void)
-{
-	return nft_register_set(&nft_bitmap_type);
-}
-
-static void __exit nft_bitmap_module_exit(void)
-{
-	nft_unregister_set(&nft_bitmap_type);
-}
-
-module_init(nft_bitmap_module_init);
-module_exit(nft_bitmap_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
-MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6f9a1365a09f..90c3e7e6cacb 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set)
 	struct nft_rhash *priv = nft_set_priv(set);
 
 	cancel_delayed_work_sync(&priv->gc_work);
+	rcu_barrier();
 	rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy,
 				    (void *)set);
 }
@@ -654,7 +655,7 @@ static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features
 	return true;
 }
 
-static struct nft_set_type nft_rhash_type __read_mostly = {
+struct nft_set_type nft_set_rhash_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_MAP | NFT_SET_OBJECT |
 			  NFT_SET_TIMEOUT | NFT_SET_EVAL,
@@ -677,7 +678,7 @@ static struct nft_set_type nft_rhash_type __read_mostly = {
 	},
 };
 
-static struct nft_set_type nft_hash_type __read_mostly = {
+struct nft_set_type nft_set_hash_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_MAP | NFT_SET_OBJECT,
 	.ops		= {
@@ -697,7 +698,7 @@ static struct nft_set_type nft_hash_type __read_mostly = {
 	},
 };
 
-static struct nft_set_type nft_hash_fast_type __read_mostly = {
+struct nft_set_type nft_set_hash_fast_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_MAP | NFT_SET_OBJECT,
 	.ops		= {
@@ -716,26 +717,3 @@ static struct nft_set_type nft_hash_fast_type __read_mostly = {
 		.get		= nft_hash_get,
 	},
 };
-
-static int __init nft_hash_module_init(void)
-{
-	if (nft_register_set(&nft_hash_fast_type) ||
-	    nft_register_set(&nft_hash_type) ||
-	    nft_register_set(&nft_rhash_type))
-		return 1;
-	return 0;
-}
-
-static void __exit nft_hash_module_exit(void)
-{
-	nft_unregister_set(&nft_rhash_type);
-	nft_unregister_set(&nft_hash_type);
-	nft_unregister_set(&nft_hash_fast_type);
-}
-
-module_init(nft_hash_module_init);
-module_exit(nft_hash_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 7f3a9a211034..9873d734b494 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work)
 
 		gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
 		if (!gcb)
-			goto out;
+			break;
 
 		atomic_dec(&set->nelems);
 		nft_set_gc_batch_add(gcb, rbe);
@@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work)
 			rbe = rb_entry(prev, struct nft_rbtree_elem, node);
 			atomic_dec(&set->nelems);
 			nft_set_gc_batch_add(gcb, rbe);
+			prev = NULL;
 		}
 		node = rb_next(node);
+		if (!node)
+			break;
 	}
-out:
 	if (gcb) {
 		for (i = 0; i < gcb->head.cnt; i++) {
 			rbe = gcb->elems[i];
@@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set)
 	struct rb_node *node;
 
 	cancel_delayed_work_sync(&priv->gc_work);
+	rcu_barrier();
 	while ((node = priv->root.rb_node) != NULL) {
 		rb_erase(node, &priv->root);
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
@@ -462,7 +465,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features,
 	return true;
 }
 
-static struct nft_set_type nft_rbtree_type __read_mostly = {
+struct nft_set_type nft_set_rbtree_type __read_mostly = {
 	.owner		= THIS_MODULE,
 	.features	= NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT,
 	.ops		= {
@@ -481,20 +484,3 @@ static struct nft_set_type nft_rbtree_type __read_mostly = {
 		.get		= nft_rbtree_get,
 	},
 };
-
-static int __init nft_rbtree_module_init(void)
-{
-	return nft_register_set(&nft_rbtree_type);
-}
-
-static void __exit nft_rbtree_module_exit(void)
-{
-	nft_unregister_set(&nft_rbtree_type);
-}
-
-module_init(nft_rbtree_module_init);
-module_exit(nft_rbtree_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_SET();
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 58fce4e749a9..d76550a8b642 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -61,7 +61,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	 * addresses, this happens if the redirect already happened
 	 * and the current packet belongs to an already established
 	 * connection */
-	sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+	sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
 				   iph->saddr, iph->daddr,
 				   hp->source, hp->dest,
 				   skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED);
@@ -77,7 +77,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	else if (!sk)
 		/* no, there's no established connection, check if
 		 * there's a listener on the redirected addr/port */
-		sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol,
+		sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol,
 					   iph->saddr, laddr,
 					   hp->source, lport,
 					   skb->dev, NF_TPROXY_LOOKUP_LISTENER);
@@ -150,7 +150,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	 * addresses, this happens if the redirect already happened
 	 * and the current packet belongs to an already established
 	 * connection */
-	sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto,
+	sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto,
 				   &iph->saddr, &iph->daddr,
 				   hp->source, hp->dest,
 				   xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED);
@@ -171,7 +171,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par)
 	else if (!sk)
 		/* no there's no established connection, check if
 		 * there's a listener on the redirected addr/port */
-		sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp,
+		sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff,
 					   tproto, &iph->saddr, laddr,
 					   hp->source, lport,
 					   xt_in(par), NF_TPROXY_LOOKUP_LISTENER);
diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c
index 2ceefa183cee..6a196e438b6c 100644
--- a/net/nfc/llcp_commands.c
+++ b/net/nfc/llcp_commands.c
@@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap,
 		pr_debug("Fragment %zd bytes remaining %zd",
 			 frag_len, remaining_len);
 
-		pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT,
+		pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0,
 					 frag_len + LLCP_HEADER_SIZE, &err);
 		if (pdu == NULL) {
-			pr_err("Could not allocate PDU\n");
-			continue;
+			pr_err("Could not allocate PDU (error=%d)\n", err);
+			len -= remaining_len;
+			if (len == 0)
+				len = err;
+			break;
 		}
 
 		pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI);
diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c
index 9696ef96b719..1a30e165eeb4 100644
--- a/net/nsh/nsh.c
+++ b/net/nsh/nsh.c
@@ -104,7 +104,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb,
 	__skb_pull(skb, nsh_len);
 
 	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0;
 	skb->protocol = proto;
 
 	features &= NETIF_F_SG;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 57634bc3da74..9b27d0cd766d 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2878,6 +2878,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 			goto out_free;
 	} else if (reserve) {
 		skb_reserve(skb, -reserve);
+		if (len < reserve)
+			skb_reset_network_header(skb);
 	}
 
 	/* Returns -EFAULT on error */
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 2aa07b547b16..86e1e37eb4e8 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -191,8 +191,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->type = cpu_to_le32(type);
 	hdr->src_node_id = cpu_to_le32(from->sq_node);
 	hdr->src_port_id = cpu_to_le32(from->sq_port);
-	hdr->dst_node_id = cpu_to_le32(to->sq_node);
-	hdr->dst_port_id = cpu_to_le32(to->sq_port);
+	if (to->sq_port == QRTR_PORT_CTRL) {
+		hdr->dst_node_id = cpu_to_le32(node->nid);
+		hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST);
+	} else {
+		hdr->dst_node_id = cpu_to_le32(to->sq_node);
+		hdr->dst_port_id = cpu_to_le32(to->sq_port);
+	}
 
 	hdr->size = cpu_to_le32(len);
 	hdr->confirm_rx = 0;
@@ -764,6 +769,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	node = NULL;
 	if (addr->sq_node == QRTR_NODE_BCAST) {
 		enqueue_fn = qrtr_bcast_enqueue;
+		if (addr->sq_port != QRTR_PORT_CTRL) {
+			release_sock(sk);
+			return -ENOTCONN;
+		}
 	} else if (addr->sq_node == ipc->us.sq_node) {
 		enqueue_fn = qrtr_local_enqueue;
 	} else {
diff --git a/net/rds/connection.c b/net/rds/connection.c
index abef75da89a7..cfb05953b0e5 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -659,11 +659,19 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
 
 int rds_conn_init(void)
 {
+	int ret;
+
+	ret = rds_loop_net_init(); /* register pernet callback */
+	if (ret)
+		return ret;
+
 	rds_conn_slab = kmem_cache_create("rds_connection",
 					  sizeof(struct rds_connection),
 					  0, 0, NULL);
-	if (!rds_conn_slab)
+	if (!rds_conn_slab) {
+		rds_loop_net_exit();
 		return -ENOMEM;
+	}
 
 	rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info);
 	rds_info_register_func(RDS_INFO_SEND_MESSAGES,
@@ -676,6 +684,7 @@ int rds_conn_init(void)
 
 void rds_conn_exit(void)
 {
+	rds_loop_net_exit(); /* unregister pernet callback */
 	rds_loop_exit();
 
 	WARN_ON(!hlist_empty(rds_conn_hash));
diff --git a/net/rds/loop.c b/net/rds/loop.c
index dac6218a460e..feea1f96ee2a 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -33,6 +33,8 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/in.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include "rds_single_path.h"
 #include "rds.h"
@@ -40,6 +42,17 @@
 
 static DEFINE_SPINLOCK(loop_conns_lock);
 static LIST_HEAD(loop_conns);
+static atomic_t rds_loop_unloading = ATOMIC_INIT(0);
+
+static void rds_loop_set_unloading(void)
+{
+	atomic_set(&rds_loop_unloading, 1);
+}
+
+static bool rds_loop_is_unloading(struct rds_connection *conn)
+{
+	return atomic_read(&rds_loop_unloading) != 0;
+}
 
 /*
  * This 'loopback' transport is a special case for flows that originate
@@ -165,6 +178,8 @@ void rds_loop_exit(void)
 	struct rds_loop_connection *lc, *_lc;
 	LIST_HEAD(tmp_list);
 
+	rds_loop_set_unloading();
+	synchronize_rcu();
 	/* avoid calling conn_destroy with irqs off */
 	spin_lock_irq(&loop_conns_lock);
 	list_splice(&loop_conns, &tmp_list);
@@ -177,6 +192,46 @@ void rds_loop_exit(void)
 	}
 }
 
+static void rds_loop_kill_conns(struct net *net)
+{
+	struct rds_loop_connection *lc, *_lc;
+	LIST_HEAD(tmp_list);
+
+	spin_lock_irq(&loop_conns_lock);
+	list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node)  {
+		struct net *c_net = read_pnet(&lc->conn->c_net);
+
+		if (net != c_net)
+			continue;
+		list_move_tail(&lc->loop_node, &tmp_list);
+	}
+	spin_unlock_irq(&loop_conns_lock);
+
+	list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) {
+		WARN_ON(lc->conn->c_passive);
+		rds_conn_destroy(lc->conn);
+	}
+}
+
+static void __net_exit rds_loop_exit_net(struct net *net)
+{
+	rds_loop_kill_conns(net);
+}
+
+static struct pernet_operations rds_loop_net_ops = {
+	.exit = rds_loop_exit_net,
+};
+
+int rds_loop_net_init(void)
+{
+	return register_pernet_device(&rds_loop_net_ops);
+}
+
+void rds_loop_net_exit(void)
+{
+	unregister_pernet_device(&rds_loop_net_ops);
+}
+
 /*
  * This is missing .xmit_* because loop doesn't go through generic
  * rds_send_xmit() and doesn't call rds_recv_incoming().  .listen_stop and
@@ -194,4 +249,5 @@ struct rds_transport rds_loop_transport = {
 	.inc_free		= rds_loop_inc_free,
 	.t_name			= "loopback",
 	.t_type			= RDS_TRANS_LOOP,
+	.t_unloading		= rds_loop_is_unloading,
 };
diff --git a/net/rds/loop.h b/net/rds/loop.h
index 469fa4b2da4f..bbc8cdd030df 100644
--- a/net/rds/loop.h
+++ b/net/rds/loop.h
@@ -5,6 +5,8 @@
 /* loop.c */
 extern struct rds_transport rds_loop_transport;
 
+int rds_loop_net_init(void);
+void rds_loop_net_exit(void);
 void rds_loop_exit(void);
 
 #endif
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 526a8e491626..6e7124e57918 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -91,7 +91,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	}
 	params_old = rtnl_dereference(p->params);
 
-	params_new->action = parm->action;
+	p->tcf_action = parm->action;
 	params_new->update_flags = parm->update_flags;
 	rcu_assign_pointer(p->params, params_new);
 	if (params_old)
@@ -561,7 +561,7 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&p->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
 
-	action = params->action;
+	action = READ_ONCE(p->tcf_action);
 	if (unlikely(action == TC_ACT_SHOT))
 		goto drop_stats;
 
@@ -599,11 +599,11 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 		.index   = p->tcf_index,
 		.refcnt  = p->tcf_refcnt - ref,
 		.bindcnt = p->tcf_bindcnt - bind,
+		.action  = p->tcf_action,
 	};
 	struct tcf_t t;
 
 	params = rtnl_dereference(p->params);
-	opt.action = params->action;
 	opt.update_flags = params->update_flags;
 
 	if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 626dac81a48a..9bc6c2ae98a5 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -36,7 +36,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 
 	tcf_lastuse_update(&t->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
-	action = params->action;
+	action = READ_ONCE(t->tcf_action);
 
 	switch (params->tcft_action) {
 	case TCA_TUNNEL_KEY_ACT_RELEASE:
@@ -182,7 +182,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 	params_old = rtnl_dereference(t->params);
 
-	params_new->action = parm->action;
+	t->tcf_action = parm->action;
 	params_new->tcft_action = parm->t_action;
 	params_new->tcft_enc_metadata = metadata;
 
@@ -254,13 +254,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 		.index    = t->tcf_index,
 		.refcnt   = t->tcf_refcnt - ref,
 		.bindcnt  = t->tcf_bindcnt - bind,
+		.action   = t->tcf_action,
 	};
 	struct tcf_t tm;
 
 	params = rtnl_dereference(t->params);
 
 	opt.t_action = params->tcft_action;
-	opt.action = params->action;
 
 	if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index cdc3c87c53e6..f74513a7c7a8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1053,7 +1053,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 	for (tp = rtnl_dereference(chain->filter_chain);
 	     tp; tp = rtnl_dereference(tp->next))
 		tfilter_notify(net, oskb, n, tp, block,
-			       q, parent, 0, event, false);
+			       q, parent, NULL, event, false);
 }
 
 static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
@@ -1444,7 +1444,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
 			memset(&cb->args[1], 0,
 			       sizeof(cb->args) - sizeof(cb->args[0]));
 		if (cb->args[1] == 0) {
-			if (tcf_fill_node(net, skb, tp, block, q, parent, 0,
+			if (tcf_fill_node(net, skb, tp, block, q, parent, NULL,
 					  NETLINK_CB(cb->skb).portid,
 					  cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					  RTM_NEWTFILTER) <= 0)
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index cd2e0e342fb6..6c0a9d5dbf94 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -479,24 +479,28 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 	q->cparams.mtu = psched_mtu(qdisc_dev(sch));
 
 	if (opt) {
-		int err = fq_codel_change(sch, opt, extack);
+		err = fq_codel_change(sch, opt, extack);
 		if (err)
-			return err;
+			goto init_failure;
 	}
 
 	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
 	if (err)
-		return err;
+		goto init_failure;
 
 	if (!q->flows) {
 		q->flows = kvcalloc(q->flows_cnt,
 				    sizeof(struct fq_codel_flow),
 				    GFP_KERNEL);
-		if (!q->flows)
-			return -ENOMEM;
+		if (!q->flows) {
+			err = -ENOMEM;
+			goto init_failure;
+		}
 		q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL);
-		if (!q->backlogs)
-			return -ENOMEM;
+		if (!q->backlogs) {
+			err = -ENOMEM;
+			goto alloc_failure;
+		}
 		for (i = 0; i < q->flows_cnt; i++) {
 			struct fq_codel_flow *flow = q->flows + i;
 
@@ -509,6 +513,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt,
 	else
 		sch->flags &= ~TCQ_F_CAN_BYPASS;
 	return 0;
+
+alloc_failure:
+	kvfree(q->flows);
+	q->flows = NULL;
+init_failure:
+	q->flows_cnt = 0;
+	return err;
 }
 
 static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb)
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 445b7ef61677..12cac85da994 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -282,7 +282,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu)
 
 	if (dst) {
 		/* Re-fetch, as under layers may have a higher minimum size */
-		pmtu = SCTP_TRUNC4(dst_mtu(dst));
+		pmtu = sctp_dst_mtu(dst);
 		change = t->pathmtu != pmtu;
 	}
 	t->pathmtu = pmtu;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 973b4471b532..05e4ffe5aabd 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending);	/* serialize link group
 						 */
 
 static void smc_tcp_listen_work(struct work_struct *);
+static void smc_connect_work(struct work_struct *);
 
 static void smc_set_keepalive(struct sock *sk, int val)
 {
@@ -122,6 +123,12 @@ static int smc_release(struct socket *sock)
 		goto out;
 
 	smc = smc_sk(sk);
+
+	/* cleanup for a dangling non-blocking connect */
+	flush_work(&smc->connect_work);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+
 	if (sk->sk_state == SMC_LISTEN)
 		/* smc_close_non_accepted() is called and acquires
 		 * sock lock for child sockets again
@@ -140,7 +147,8 @@ static int smc_release(struct socket *sock)
 		smc->clcsock = NULL;
 	}
 	if (smc->use_fallback) {
-		sock_put(sk); /* passive closing */
+		if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT)
+			sock_put(sk); /* passive closing */
 		sk->sk_state = SMC_CLOSED;
 		sk->sk_state_change(sk);
 	}
@@ -186,6 +194,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock,
 	sk->sk_protocol = protocol;
 	smc = smc_sk(sk);
 	INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work);
+	INIT_WORK(&smc->connect_work, smc_connect_work);
 	INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work);
 	INIT_LIST_HEAD(&smc->accept_q);
 	spin_lock_init(&smc->accept_q_lock);
@@ -409,12 +418,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 {
 	int rc;
 
-	if (reason_code < 0) /* error, fallback is not possible */
+	if (reason_code < 0) { /* error, fallback is not possible */
+		if (smc->sk.sk_state == SMC_INIT)
+			sock_put(&smc->sk); /* passive closing */
 		return reason_code;
+	}
 	if (reason_code != SMC_CLC_DECL_REPLY) {
 		rc = smc_clc_send_decline(smc, reason_code);
-		if (rc < 0)
+		if (rc < 0) {
+			if (smc->sk.sk_state == SMC_INIT)
+				sock_put(&smc->sk); /* passive closing */
 			return rc;
+		}
 	}
 	return smc_connect_fallback(smc);
 }
@@ -427,8 +442,6 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
 		smc_lgr_forget(smc->conn.lgr);
 	mutex_unlock(&smc_create_lgr_pending);
 	smc_conn_free(&smc->conn);
-	if (reason_code < 0 && smc->sk.sk_state == SMC_INIT)
-		sock_put(&smc->sk); /* passive closing */
 	return reason_code;
 }
 
@@ -576,6 +589,35 @@ static int __smc_connect(struct smc_sock *smc)
 	return 0;
 }
 
+static void smc_connect_work(struct work_struct *work)
+{
+	struct smc_sock *smc = container_of(work, struct smc_sock,
+					    connect_work);
+	int rc;
+
+	lock_sock(&smc->sk);
+	rc = kernel_connect(smc->clcsock, &smc->connect_info->addr,
+			    smc->connect_info->alen, smc->connect_info->flags);
+	if (smc->clcsock->sk->sk_err) {
+		smc->sk.sk_err = smc->clcsock->sk->sk_err;
+		goto out;
+	}
+	if (rc < 0) {
+		smc->sk.sk_err = -rc;
+		goto out;
+	}
+
+	rc = __smc_connect(smc);
+	if (rc < 0)
+		smc->sk.sk_err = -rc;
+
+out:
+	smc->sk.sk_state_change(&smc->sk);
+	kfree(smc->connect_info);
+	smc->connect_info = NULL;
+	release_sock(&smc->sk);
+}
+
 static int smc_connect(struct socket *sock, struct sockaddr *addr,
 		       int alen, int flags)
 {
@@ -605,15 +647,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 
 	smc_copy_sock_settings_to_clc(smc);
 	tcp_sk(smc->clcsock->sk)->syn_smc = 1;
-	rc = kernel_connect(smc->clcsock, addr, alen, flags);
-	if (rc)
-		goto out;
+	if (flags & O_NONBLOCK) {
+		if (smc->connect_info) {
+			rc = -EALREADY;
+			goto out;
+		}
+		smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL);
+		if (!smc->connect_info) {
+			rc = -ENOMEM;
+			goto out;
+		}
+		smc->connect_info->alen = alen;
+		smc->connect_info->flags = flags ^ O_NONBLOCK;
+		memcpy(&smc->connect_info->addr, addr, alen);
+		schedule_work(&smc->connect_work);
+		rc = -EINPROGRESS;
+	} else {
+		rc = kernel_connect(smc->clcsock, addr, alen, flags);
+		if (rc)
+			goto out;
 
-	rc = __smc_connect(smc);
-	if (rc < 0)
-		goto out;
-	else
-		rc = 0; /* success cases including fallback */
+		rc = __smc_connect(smc);
+		if (rc < 0)
+			goto out;
+		else
+			rc = 0; /* success cases including fallback */
+	}
 
 out:
 	release_sock(sk);
@@ -1279,40 +1338,20 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 	struct smc_sock *smc;
-	int rc;
 
 	if (!sk)
 		return EPOLLNVAL;
 
 	smc = smc_sk(sock->sk);
-	sock_hold(sk);
-	lock_sock(sk);
 	if ((sk->sk_state == SMC_INIT) || smc->use_fallback) {
 		/* delegate to CLC child sock */
-		release_sock(sk);
 		mask = smc->clcsock->ops->poll(file, smc->clcsock, wait);
-		lock_sock(sk);
 		sk->sk_err = smc->clcsock->sk->sk_err;
-		if (sk->sk_err) {
+		if (sk->sk_err)
 			mask |= EPOLLERR;
-		} else {
-			/* if non-blocking connect finished ... */
-			if (sk->sk_state == SMC_INIT &&
-			    mask & EPOLLOUT &&
-			    smc->clcsock->sk->sk_state != TCP_CLOSE) {
-				rc = __smc_connect(smc);
-				if (rc < 0)
-					mask |= EPOLLERR;
-				/* success cases including fallback */
-				mask |= EPOLLOUT | EPOLLWRNORM;
-			}
-		}
 	} else {
-		if (sk->sk_state != SMC_CLOSED) {
-			release_sock(sk);
+		if (sk->sk_state != SMC_CLOSED)
 			sock_poll_wait(file, sk_sleep(sk), wait);
-			lock_sock(sk);
-		}
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
@@ -1338,10 +1377,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 		}
 		if (smc->conn.urg_state == SMC_URG_VALID)
 			mask |= EPOLLPRI;
-
 	}
-	release_sock(sk);
-	sock_put(sk);
 
 	return mask;
 }
@@ -1421,7 +1457,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 
 	if (optlen < sizeof(int))
 		return -EINVAL;
-	get_user(val, (int __user *)optval);
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
 
 	lock_sock(sk);
 	switch (optname) {
@@ -1489,10 +1526,13 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 			return -EBADF;
 		return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg);
 	}
+	lock_sock(&smc->sk);
 	switch (cmd) {
 	case SIOCINQ: /* same as FIONREAD */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1501,8 +1541,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 	case SIOCOUTQ:
 		/* output queue size (not send + not acked) */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1512,8 +1554,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 	case SIOCOUTQNSD:
 		/* output queue size (not send only) */
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED)
 			answ = 0;
@@ -1521,8 +1565,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 			answ = smc_tx_prepared_sends(&smc->conn);
 		break;
 	case SIOCATMARK:
-		if (smc->sk.sk_state == SMC_LISTEN)
+		if (smc->sk.sk_state == SMC_LISTEN) {
+			release_sock(&smc->sk);
 			return -EINVAL;
+		}
 		if (smc->sk.sk_state == SMC_INIT ||
 		    smc->sk.sk_state == SMC_CLOSED) {
 			answ = 0;
@@ -1538,8 +1584,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		}
 		break;
 	default:
+		release_sock(&smc->sk);
 		return -ENOIOCTLCMD;
 	}
+	release_sock(&smc->sk);
 
 	return put_user(answ, (int __user *)arg);
 }
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 51ae1f10d81a..d7ca26570482 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -187,11 +187,19 @@ struct smc_connection {
 	struct work_struct	close_work;	/* peer sent some closing */
 };
 
+struct smc_connect_info {
+	int			flags;
+	int			alen;
+	struct sockaddr		addr;
+};
+
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
 	struct smc_connection	conn;		/* smc connection */
 	struct smc_sock		*listen_smc;	/* listen parent */
+	struct smc_connect_info *connect_info;	/* connect address & flags */
+	struct work_struct	connect_work;	/* handle non-blocking connect*/
 	struct work_struct	tcp_listen_work;/* handle tcp socket accepts */
 	struct work_struct	smc_listen_work;/* prepare new accept socket */
 	struct list_head	accept_q;	/* sockets to be accepted */
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 717449b1da0b..ae5d168653ce 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -250,6 +250,7 @@ out:
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type)
 {
+	long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo;
 	struct sock *clc_sk = smc->clcsock->sk;
 	struct smc_clc_msg_hdr *clcm = buf;
 	struct msghdr msg = {NULL, 0};
@@ -306,7 +307,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	memset(&msg, 0, sizeof(struct msghdr));
 	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
 	krflags = MSG_WAITALL;
-	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
 		smc->sk.sk_err = EPROTO;
@@ -322,6 +322,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 
 out:
+	smc->clcsock->sk->sk_rcvtimeo = rcvtimeo;
 	return reason_code;
 }
 
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index fa41d9881741..ac961dfb1ea1 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc)
 	}
 	switch (sk->sk_state) {
 	case SMC_INIT:
+		sk->sk_state = SMC_PEERABORTWAIT;
+		break;
 	case SMC_ACTIVE:
 		sk->sk_state = SMC_PEERABORTWAIT;
 		release_sock(sk);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index cee666400752..f82886b7d1d8 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -495,7 +495,8 @@ out:
 
 void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 {
-	union smc_host_cursor cfed, cons;
+	union smc_host_cursor cfed, cons, prod;
+	int sender_free = conn->rmb_desc->len;
 	int to_confirm;
 
 	smc_curs_write(&cons,
@@ -505,11 +506,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 		       smc_curs_read(&conn->rx_curs_confirmed, conn),
 		       conn);
 	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+	if (to_confirm > conn->rmbe_update_limit) {
+		smc_curs_write(&prod,
+			       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
+			       conn);
+		sender_free = conn->rmb_desc->len -
+			      smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+	}
 
 	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
 	    force ||
 	    ((to_confirm > conn->rmbe_update_limit) &&
-	     ((to_confirm > (conn->rmb_desc->len / 2)) ||
+	     ((sender_free <= (conn->rmb_desc->len / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
 		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
 		    conn->alert_token_local) { /* connection healthy */
diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 373836615c57..625acb27efcc 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -35,7 +35,6 @@ struct _strp_msg {
 	 */
 	struct strp_msg strp;
 	int accum_len;
-	int early_eaten;
 };
 
 static inline struct _strp_msg *_strp_msg(struct sk_buff *skb)
@@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 	head = strp->skb_head;
 	if (head) {
 		/* Message already in progress */
-
-		stm = _strp_msg(head);
-		if (unlikely(stm->early_eaten)) {
-			/* Already some number of bytes on the receive sock
-			 * data saved in skb_head, just indicate they
-			 * are consumed.
-			 */
-			eaten = orig_len <= stm->early_eaten ?
-				orig_len : stm->early_eaten;
-			stm->early_eaten -= eaten;
-
-			return eaten;
-		}
-
 		if (unlikely(orig_offset)) {
 			/* Getting data with a non-zero offset when a message is
 			 * in progress is not expected. If it does happen, we
@@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 				}
 
 				stm->accum_len += cand_len;
+				eaten += cand_len;
 				strp->need_bytes = stm->strp.full_len -
 						       stm->accum_len;
-				stm->early_eaten = cand_len;
 				STRP_STATS_ADD(strp->stats.bytes, cand_len);
 				desc->count = 0; /* Stop reading socket */
 				break;
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 9f666e0650e2..2830709957bd 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -133,6 +133,8 @@ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr,
 }
 
 /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer
+ * Returns true if message should be dropped by caller, i.e., if it is a
+ * trial message or we are inside trial period. Otherwise false.
  */
 static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 				     struct tipc_media_addr *maddr,
@@ -168,8 +170,9 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 
+	/* Accept regular link requests/responses only after trial period */
 	if (mtyp != DSC_TRIAL_MSG)
-		return false;
+		return trial;
 
 	sugg_addr = tipc_node_try_addr(net, peer_id, src);
 	if (sugg_addr)
@@ -284,7 +287,6 @@ static void tipc_disc_timeout(struct timer_list *t)
 {
 	struct tipc_discoverer *d = from_timer(d, t, timer);
 	struct tipc_net *tn = tipc_net(d->net);
-	u32 self = tipc_own_addr(d->net);
 	struct tipc_media_addr maddr;
 	struct sk_buff *skb = NULL;
 	struct net *net = d->net;
@@ -298,12 +300,14 @@ static void tipc_disc_timeout(struct timer_list *t)
 		goto exit;
 	}
 
-	/* Did we just leave the address trial period ? */
-	if (!self && !time_before(jiffies, tn->addr_trial_end)) {
-		self = tn->trial_addr;
-		tipc_net_finalize(net, self);
-		msg_set_prevnode(buf_msg(d->skb), self);
+	/* Trial period over ? */
+	if (!time_before(jiffies, tn->addr_trial_end)) {
+		/* Did we just leave it ? */
+		if (!tipc_own_addr(net))
+			tipc_net_finalize(net, tn->trial_addr);
+
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
 	}
 
 	/* Adjust timeout interval according to discovery phase */
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 4fbaa0464405..a7f6964c3a4b 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -121,12 +121,17 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 
 void tipc_net_finalize(struct net *net, u32 addr)
 {
-	tipc_set_node_addr(net, addr);
-	smp_mb();
-	tipc_named_reinit(net);
-	tipc_sk_reinit(net);
-	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
-			     TIPC_CLUSTER_SCOPE, 0, addr);
+	struct tipc_net *tn = tipc_net(net);
+
+	spin_lock_bh(&tn->node_list_lock);
+	if (!tipc_own_addr(net)) {
+		tipc_set_node_addr(net, addr);
+		tipc_named_reinit(net);
+		tipc_sk_reinit(net);
+		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+				     TIPC_CLUSTER_SCOPE, 0, addr);
+	}
+	spin_unlock_bh(&tn->node_list_lock);
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6a44eb812baf..0453bd451ce8 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -797,6 +797,7 @@ static u32 tipc_node_suggest_addr(struct net *net, u32 addr)
 }
 
 /* tipc_node_try_addr(): Check if addr can be used by peer, suggest other if not
+ * Returns suggested address if any, otherwise 0
  */
 u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
 {
@@ -819,12 +820,14 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr)
 	if (n) {
 		addr = n->addr;
 		tipc_node_put(n);
+		return addr;
 	}
-	/* Even this node may be in trial phase */
+
+	/* Even this node may be in conflict */
 	if (tn->trial_addr == addr)
 		return tipc_node_suggest_addr(net, addr);
 
-	return addr;
+	return 0;
 }
 
 void tipc_node_check_dest(struct net *net, u32 addr,
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d2380548f8f6..1f3d9789af30 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -440,7 +440,7 @@ alloc_encrypted:
 			ret = tls_push_record(sk, msg->msg_flags, record_type);
 			if (!ret)
 				continue;
-			if (ret == -EAGAIN)
+			if (ret < 0)
 				goto send_end;
 
 			copied -= try_to_copy;
@@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
 			return NULL;
 		}
 
+		if (sk->sk_shutdown & RCV_SHUTDOWN)
+			return NULL;
+
 		if (sock_flag(sk, SOCK_DONE))
 			return NULL;
 
@@ -701,6 +704,10 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 	nsg = skb_to_sgvec(skb, &sgin[1],
 			   rxm->offset + tls_ctx->rx.prepend_size,
 			   rxm->full_len - tls_ctx->rx.prepend_size);
+	if (nsg < 0) {
+		ret = nsg;
+		goto out;
+	}
 
 	tls_make_aad(ctx->rx_aad_ciphertext,
 		     rxm->full_len - tls_ctx->rx.overhead_size,
@@ -712,6 +719,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 				rxm->full_len - tls_ctx->rx.overhead_size,
 				skb, sk->sk_allocation);
 
+out:
 	if (sgin != &sgin_arr[0])
 		kfree(sgin);
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c7bbe5f0aae8..80bc986c79e5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info,
 		params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) |
 					 BIT(NL80211_STA_FLAG_MFP) |
 					 BIT(NL80211_STA_FLAG_AUTHORIZED);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -6231,7 +6232,7 @@ do {									    \
 				  nl80211_check_s32);
 	/*
 	 * Check HT operation mode based on
-	 * IEEE 802.11 2012 8.4.2.59 HT Operation element.
+	 * IEEE 802.11-2016 9.4.2.57 HT Operation element.
 	 */
 	if (tb[NL80211_MESHCONF_HT_OPMODE]) {
 		ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]);
@@ -6241,22 +6242,9 @@ do {									    \
 				  IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
 			return -EINVAL;
 
-		if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) &&
-		    (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
-			return -EINVAL;
+		/* NON_HT_STA bit is reserved, but some programs set it */
+		ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT;
 
-		switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) {
-		case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
-		case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
-			if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)
-				return -EINVAL;
-			break;
-		case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
-		case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
-			if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT))
-				return -EINVAL;
-			break;
-		}
 		cfg->ht_opmode = ht_opmode;
 		mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1));
 	}
@@ -10962,9 +10950,12 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info)
 				    rem) {
 			u8 *mask_pat;
 
-			nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-					 nl80211_packet_pattern_policy,
-					 info->extack);
+			err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+					       nl80211_packet_pattern_policy,
+					       info->extack);
+			if (err)
+				goto error;
+
 			err = -EINVAL;
 			if (!pat_tb[NL80211_PKTPAT_MASK] ||
 			    !pat_tb[NL80211_PKTPAT_PATTERN])
@@ -11213,8 +11204,11 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev,
 			    rem) {
 		u8 *mask_pat;
 
-		nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
-				 nl80211_packet_pattern_policy, NULL);
+		err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat,
+				       nl80211_packet_pattern_policy, NULL);
+		if (err)
+			return err;
+
 		if (!pat_tb[NL80211_PKTPAT_MASK] ||
 		    !pat_tb[NL80211_PKTPAT_PATTERN])
 			return -EINVAL;
@@ -14930,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie,
 EXPORT_SYMBOL(cfg80211_mgmt_tx_status);
 
 static int __nl80211_rx_control_port(struct net_device *dev,
-				     const u8 *buf, size_t len,
-				     const u8 *addr, u16 proto,
+				     struct sk_buff *skb,
 				     bool unencrypted, gfp_t gfp)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
+	struct ethhdr *ehdr = eth_hdr(skb);
+	const u8 *addr = ehdr->h_source;
+	u16 proto = be16_to_cpu(skb->protocol);
 	struct sk_buff *msg;
 	void *hdr;
+	struct nlattr *frame;
+
 	u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid);
 
 	if (!nlportid)
 		return -ENOENT;
 
-	msg = nlmsg_new(100 + len, gfp);
+	msg = nlmsg_new(100 + skb->len, gfp);
 	if (!msg)
 		return -ENOMEM;
 
@@ -14957,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev,
 	    nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) ||
 	    nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev),
 			      NL80211_ATTR_PAD) ||
-	    nla_put(msg, NL80211_ATTR_FRAME, len, buf) ||
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) ||
 	    nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) ||
 	    (unencrypted && nla_put_flag(msg,
 					 NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT)))
 		goto nla_put_failure;
 
+	frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len);
+	if (!frame)
+		goto nla_put_failure;
+
+	skb_copy_bits(skb, 0, nla_data(frame), skb->len);
 	genlmsg_end(msg, hdr);
 
 	return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid);
@@ -14974,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev,
 }
 
 bool cfg80211_rx_control_port(struct net_device *dev,
-			      const u8 *buf, size_t len,
-			      const u8 *addr, u16 proto, bool unencrypted)
+			      struct sk_buff *skb, bool unencrypted)
 {
 	int ret;
 
-	trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted);
-	ret = __nl80211_rx_control_port(dev, buf, len, addr, proto,
-					unencrypted, GFP_ATOMIC);
+	trace_cfg80211_rx_control_port(dev, skb, unencrypted);
+	ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC);
 	trace_cfg80211_return_bool(ret == 0);
 	return ret == 0;
 }
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index bbe6298e4bb9..4fc66a117b7d 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy,
 		 * as some drivers used this to restore its orig_* reg domain.
 		 */
 		if (initiator == NL80211_REGDOM_SET_BY_CORE &&
-		    wiphy->regulatory_flags & REGULATORY_CUSTOM_REG)
+		    wiphy->regulatory_flags & REGULATORY_CUSTOM_REG &&
+		    !(wiphy->regulatory_flags &
+		      REGULATORY_WIPHY_SELF_MANAGED))
 			reg_call_notifier(wiphy, lr);
 		return;
 	}
@@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request)
 	}
 }
 
-static bool reg_only_self_managed_wiphys(void)
-{
-	struct cfg80211_registered_device *rdev;
-	struct wiphy *wiphy;
-	bool self_managed_found = false;
-
-	ASSERT_RTNL();
-
-	list_for_each_entry(rdev, &cfg80211_rdev_list, list) {
-		wiphy = &rdev->wiphy;
-		if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED)
-			self_managed_found = true;
-		else
-			return false;
-	}
-
-	/* make sure at least one self-managed wiphy exists */
-	return self_managed_found;
-}
-
 /*
  * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_*
  * Regulatory hints come on a first come first serve basis and we
@@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void)
 	spin_unlock(&reg_requests_lock);
 
 	notify_self_managed_wiphys(reg_request);
-	if (reg_only_self_managed_wiphys()) {
-		reg_free_request(reg_request);
-		return;
-	}
 
 	reg_process_hint(reg_request);
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 2b417a2fe63f..7c73510b161f 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status,
 );
 
 TRACE_EVENT(cfg80211_rx_control_port,
-	TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len,
-		 const u8 *addr, u16 proto, bool unencrypted),
-	TP_ARGS(netdev, buf, len, addr, proto, unencrypted),
+	TP_PROTO(struct net_device *netdev, struct sk_buff *skb,
+		 bool unencrypted),
+	TP_ARGS(netdev, skb, unencrypted),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
-		MAC_ENTRY(addr)
+		__field(int, len)
+		MAC_ENTRY(from)
 		__field(u16, proto)
 		__field(bool, unencrypted)
 	),
 	TP_fast_assign(
 		NETDEV_ASSIGN;
-		MAC_ASSIGN(addr, addr);
-		__entry->proto = proto;
+		__entry->len = skb->len;
+		MAC_ASSIGN(from, eth_hdr(skb)->h_source);
+		__entry->proto = be16_to_cpu(skb->protocol);
 		__entry->unencrypted = unencrypted;
 	),
-	TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s",
-		  NETDEV_PR_ARG, MAC_PR_ARG(addr),
+	TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s",
+		  NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from),
 		  __entry->proto, BOOL_TO_STR(__entry->unencrypted))
 );
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 59fb7d3c36a3..72335c2e8108 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -199,8 +199,11 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 {
 	u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg;
 	struct xdp_sock *xs = xdp_sk(skb->sk);
+	unsigned long flags;
 
+	spin_lock_irqsave(&xs->tx_completion_lock, flags);
 	WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr));
+	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
 
 	sock_wfree(skb);
 }
@@ -215,9 +218,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 	struct sk_buff *skb;
 	int err = 0;
 
-	if (unlikely(!xs->tx))
-		return -ENOBUFS;
-
 	mutex_lock(&xs->mutex);
 
 	while (xskq_peek_desc(xs->tx, &desc)) {
@@ -230,22 +230,13 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 			goto out;
 		}
 
-		if (xskq_reserve_addr(xs->umem->cq)) {
-			err = -EAGAIN;
-			goto out;
-		}
-
-		len = desc.len;
-		if (unlikely(len > xs->dev->mtu)) {
-			err = -EMSGSIZE;
+		if (xskq_reserve_addr(xs->umem->cq))
 			goto out;
-		}
 
-		if (xs->queue_id >= xs->dev->real_num_tx_queues) {
-			err = -ENXIO;
+		if (xs->queue_id >= xs->dev->real_num_tx_queues)
 			goto out;
-		}
 
+		len = desc.len;
 		skb = sock_alloc_send_skb(sk, len, 1, &err);
 		if (unlikely(!skb)) {
 			err = -EAGAIN;
@@ -268,15 +259,15 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m,
 		skb->destructor = xsk_destruct_skb;
 
 		err = dev_direct_xmit(skb, xs->queue_id);
+		xskq_discard_desc(xs->tx);
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) {
-			err = -EAGAIN;
-			/* SKB consumed by dev_direct_xmit() */
+			/* SKB completed but not sent */
+			err = -EBUSY;
 			goto out;
 		}
 
 		sent_frame = true;
-		xskq_discard_desc(xs->tx);
 	}
 
 out:
@@ -297,6 +288,8 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 		return -ENXIO;
 	if (unlikely(!(xs->dev->flags & IFF_UP)))
 		return -ENETDOWN;
+	if (unlikely(!xs->tx))
+		return -ENOBUFS;
 	if (need_wait)
 		return -EOPNOTSUPP;
 
@@ -755,6 +748,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 
 	xs = xdp_sk(sk);
 	mutex_init(&xs->mutex);
+	spin_lock_init(&xs->tx_completion_lock);
 
 	local_bh_disable();
 	sock_prot_inuse_add(net, &xsk_proto, 1);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index ef6a6f0ec949..52ecaf770642 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -62,14 +62,9 @@ static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt)
 	return (entries > dcnt) ? dcnt : entries;
 }
 
-static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer)
-{
-	return q->nentries - (producer - q->cons_tail);
-}
-
 static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt)
 {
-	u32 free_entries = xskq_nb_free_lazy(q, producer);
+	u32 free_entries = q->nentries - (producer - q->cons_tail);
 
 	if (free_entries >= dcnt)
 		return free_entries;
@@ -129,7 +124,7 @@ static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr)
 {
 	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
 
-	if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0)
+	if (xskq_nb_free(q, q->prod_tail, 1) == 0)
 		return -ENOSPC;
 
 	ring->desc[q->prod_tail++ & q->ring_mask] = addr;
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore
new file mode 100644
index 000000000000..8ae4940025f8
--- /dev/null
+++ b/samples/bpf/.gitignore
@@ -0,0 +1,49 @@
+cpustat
+fds_example
+lathist
+load_sock_ops
+lwt_len_hist
+map_perf_test
+offwaketime
+per_socket_stats_example
+sampleip
+sock_example
+sockex1
+sockex2
+sockex3
+spintest
+syscall_nrs.h
+syscall_tp
+task_fd_query
+tc_l2_redirect
+test_cgrp2_array_pin
+test_cgrp2_attach
+test_cgrp2_attach2
+test_cgrp2_sock
+test_cgrp2_sock2
+test_current_task_under_cgroup
+test_lru_dist
+test_map_in_map
+test_overhead
+test_probe_write_user
+trace_event
+trace_output
+tracex1
+tracex2
+tracex3
+tracex4
+tracex5
+tracex6
+tracex7
+xdp1
+xdp2
+xdp_adjust_tail
+xdp_fwd
+xdp_monitor
+xdp_redirect
+xdp_redirect_cpu
+xdp_redirect_map
+xdp_router_ipv4
+xdp_rxq_info
+xdp_tx_iptunnel
+xdpsock
diff --git a/samples/bpf/parse_varlen.c b/samples/bpf/parse_varlen.c
index 95c16324760c..0b6f22feb2c9 100644
--- a/samples/bpf/parse_varlen.c
+++ b/samples/bpf/parse_varlen.c
@@ -6,6 +6,7 @@
  */
 #define KBUILD_MODNAME "foo"
 #include <linux/if_ether.h>
+#include <linux/if_vlan.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/in.h>
@@ -108,11 +109,6 @@ static int parse_ipv6(void *data, uint64_t nh_off, void *data_end)
 	return 0;
 }
 
-struct vlan_hdr {
-	uint16_t h_vlan_TCI;
-	uint16_t h_vlan_encapsulated_proto;
-};
-
 SEC("varlen")
 int handle_ingress(struct __sk_buff *skb)
 {
diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c
index 6caf47afa635..9d6dcaa9db92 100644
--- a/samples/bpf/test_overhead_user.c
+++ b/samples/bpf/test_overhead_user.c
@@ -6,6 +6,7 @@
  */
 #define _GNU_SOURCE
 #include <sched.h>
+#include <errno.h>
 #include <stdio.h>
 #include <sys/types.h>
 #include <asm/unistd.h>
@@ -44,8 +45,13 @@ static void test_task_rename(int cpu)
 		exit(1);
 	}
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		write(fd, buf, sizeof(buf));
+	for (i = 0; i < MAX_CNT; i++) {
+		if (write(fd, buf, sizeof(buf)) < 0) {
+			printf("task rename failed: %s\n", strerror(errno));
+			close(fd);
+			return;
+		}
+	}
 	printf("task_rename:%d: %lld events per sec\n",
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 	close(fd);
@@ -63,8 +69,13 @@ static void test_urandom_read(int cpu)
 		exit(1);
 	}
 	start_time = time_get_ns();
-	for (i = 0; i < MAX_CNT; i++)
-		read(fd, buf, sizeof(buf));
+	for (i = 0; i < MAX_CNT; i++) {
+		if (read(fd, buf, sizeof(buf)) < 0) {
+			printf("failed to read from /dev/urandom: %s\n", strerror(errno));
+			close(fd);
+			return;
+		}
+	}
 	printf("urandom_read:%d: %lld events per sec\n",
 	       cpu, MAX_CNT * 1000000000ll / (time_get_ns() - start_time));
 	close(fd);
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index 1fa1becfa641..d08046ab81f0 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -122,6 +122,16 @@ static void print_stacks(void)
 	}
 }
 
+static inline int generate_load(void)
+{
+	if (system("dd if=/dev/zero of=/dev/null count=5000k status=none") < 0) {
+		printf("failed to generate some load with dd: %s\n", strerror(errno));
+		return -1;
+	}
+
+	return 0;
+}
+
 static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 {
 	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
@@ -142,7 +152,11 @@ static void test_perf_event_all_cpu(struct perf_event_attr *attr)
 		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
 		assert(ioctl(pmu_fd[i], PERF_EVENT_IOC_ENABLE) == 0);
 	}
-	system("dd if=/dev/zero of=/dev/null count=5000k status=none");
+
+	if (generate_load() < 0) {
+		error = 1;
+		goto all_cpu_err;
+	}
 	print_stacks();
 all_cpu_err:
 	for (i--; i >= 0; i--) {
@@ -156,7 +170,7 @@ all_cpu_err:
 
 static void test_perf_event_task(struct perf_event_attr *attr)
 {
-	int pmu_fd;
+	int pmu_fd, error = 0;
 
 	/* per task perf event, enable inherit so the "dd ..." command can be traced properly.
 	 * Enabling inherit will cause bpf_perf_prog_read_time helper failure.
@@ -171,10 +185,17 @@ static void test_perf_event_task(struct perf_event_attr *attr)
 	}
 	assert(ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) == 0);
 	assert(ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE) == 0);
-	system("dd if=/dev/zero of=/dev/null count=5000k status=none");
+
+	if (generate_load() < 0) {
+		error = 1;
+		goto err;
+	}
 	print_stacks();
+err:
 	ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
 	close(pmu_fd);
+	if (error)
+		int_exit(0);
 }
 
 static void test_bpf_perf_event(void)
diff --git a/samples/bpf/xdp2skb_meta.sh b/samples/bpf/xdp2skb_meta.sh
index b9c9549c4c27..4bde9d066c46 100755
--- a/samples/bpf/xdp2skb_meta.sh
+++ b/samples/bpf/xdp2skb_meta.sh
@@ -16,8 +16,8 @@
 BPF_FILE=xdp2skb_meta_kern.o
 DIR=$(dirname $0)
 
-export TC=/usr/sbin/tc
-export IP=/usr/sbin/ip
+[ -z "$TC" ] && TC=tc
+[ -z "$IP" ] && IP=ip
 
 function usage() {
     echo ""
@@ -53,7 +53,7 @@ function _call_cmd() {
     local allow_fail="$2"
     shift 2
     if [[ -n "$VERBOSE" ]]; then
-	echo "$(basename $cmd) $@"
+	echo "$cmd $@"
     fi
     if [[ -n "$DRYRUN" ]]; then
 	return
diff --git a/samples/bpf/xdp_fwd_kern.c b/samples/bpf/xdp_fwd_kern.c
index 6673cdb9f55c..a7e94e7ff87d 100644
--- a/samples/bpf/xdp_fwd_kern.c
+++ b/samples/bpf/xdp_fwd_kern.c
@@ -48,9 +48,9 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 	struct ethhdr *eth = data;
 	struct ipv6hdr *ip6h;
 	struct iphdr *iph;
-	int out_index;
 	u16 h_proto;
 	u64 nh_off;
+	int rc;
 
 	nh_off = sizeof(*eth);
 	if (data + nh_off > data_end)
@@ -101,7 +101,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 
 	fib_params.ifindex = ctx->ingress_ifindex;
 
-	out_index = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
+	rc = bpf_fib_lookup(ctx, &fib_params, sizeof(fib_params), flags);
 
 	/* verify egress index has xdp support
 	 * TO-DO bpf_map_lookup_elem(&tx_port, &key) fails with
@@ -109,7 +109,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 	 * NOTE: without verification that egress index supports XDP
 	 *       forwarding packets are dropped.
 	 */
-	if (out_index > 0) {
+	if (rc == 0) {
 		if (h_proto == htons(ETH_P_IP))
 			ip_decrease_ttl(iph);
 		else if (h_proto == htons(ETH_P_IPV6))
@@ -117,7 +117,7 @@ static __always_inline int xdp_fwd_flags(struct xdp_md *ctx, u32 flags)
 
 		memcpy(eth->h_dest, fib_params.dmac, ETH_ALEN);
 		memcpy(eth->h_source, fib_params.smac, ETH_ALEN);
-		return bpf_redirect_map(&tx_port, out_index, 0);
+		return bpf_redirect_map(&tx_port, fib_params.ifindex, 0);
 	}
 
 	return XDP_PASS;
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index d69c8d78d3fd..5904b1543831 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -729,7 +729,7 @@ static void kick_tx(int fd)
 	int ret;
 
 	ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0);
-	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN)
+	if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY)
 		return;
 	lassert(0);
 }
diff --git a/samples/vfio-mdev/mbochs.c b/samples/vfio-mdev/mbochs.c
index 2960e26c6ea4..2535c3677c7b 100644
--- a/samples/vfio-mdev/mbochs.c
+++ b/samples/vfio-mdev/mbochs.c
@@ -178,6 +178,8 @@ static const char *vbe_name(u32 index)
 	return "(invalid)";
 }
 
+static struct page *__mbochs_get_page(struct mdev_state *mdev_state,
+				      pgoff_t pgoff);
 static struct page *mbochs_get_page(struct mdev_state *mdev_state,
 				    pgoff_t pgoff);
 
@@ -394,7 +396,7 @@ static ssize_t mdev_access(struct mdev_device *mdev, char *buf, size_t count,
 		   MBOCHS_MEMORY_BAR_OFFSET + mdev_state->memsize) {
 		pos -= MBOCHS_MMIO_BAR_OFFSET;
 		poff = pos & ~PAGE_MASK;
-		pg = mbochs_get_page(mdev_state, pos >> PAGE_SHIFT);
+		pg = __mbochs_get_page(mdev_state, pos >> PAGE_SHIFT);
 		map = kmap(pg);
 		if (is_write)
 			memcpy(map + poff, buf, count);
@@ -657,7 +659,7 @@ static void mbochs_put_pages(struct mdev_state *mdev_state)
 	dev_dbg(dev, "%s: %d pages released\n", __func__, count);
 }
 
-static int mbochs_region_vm_fault(struct vm_fault *vmf)
+static vm_fault_t mbochs_region_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct mdev_state *mdev_state = vma->vm_private_data;
@@ -695,7 +697,7 @@ static int mbochs_mmap(struct mdev_device *mdev, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int mbochs_dmabuf_vm_fault(struct vm_fault *vmf)
+static vm_fault_t mbochs_dmabuf_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct mbochs_dmabuf *dmabuf = vma->vm_private_data;
@@ -803,29 +805,26 @@ static void mbochs_release_dmabuf(struct dma_buf *buf)
 	mutex_unlock(&mdev_state->ops_lock);
 }
 
-static void *mbochs_kmap_atomic_dmabuf(struct dma_buf *buf,
-				       unsigned long page_num)
+static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
 {
 	struct mbochs_dmabuf *dmabuf = buf->priv;
 	struct page *page = dmabuf->pages[page_num];
 
-	return kmap_atomic(page);
+	return kmap(page);
 }
 
-static void *mbochs_kmap_dmabuf(struct dma_buf *buf, unsigned long page_num)
+static void mbochs_kunmap_dmabuf(struct dma_buf *buf, unsigned long page_num,
+				 void *vaddr)
 {
-	struct mbochs_dmabuf *dmabuf = buf->priv;
-	struct page *page = dmabuf->pages[page_num];
-
-	return kmap(page);
+	kunmap(vaddr);
 }
 
 static struct dma_buf_ops mbochs_dmabuf_ops = {
 	.map_dma_buf	  = mbochs_map_dmabuf,
 	.unmap_dma_buf	  = mbochs_unmap_dmabuf,
 	.release	  = mbochs_release_dmabuf,
-	.map_atomic	  = mbochs_kmap_atomic_dmabuf,
 	.map		  = mbochs_kmap_dmabuf,
+	.unmap		  = mbochs_kunmap_dmabuf,
 	.mmap		  = mbochs_mmap_dmabuf,
 };
 
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index c8156d61678c..86321f06461e 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -214,7 +214,7 @@ hdr-inst := -f $(srctree)/scripts/Makefile.headersinst obj
 # Prefix -I with $(srctree) if it is not an absolute path.
 # skip if -I has no parameter
 addtree = $(if $(patsubst -I%,%,$(1)), \
-$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)))
+$(if $(filter-out -I/% -I./% -I../%,$(1)),$(patsubst -I%,-I$(srctree)/%,$(1)),$(1)),$(1))
 
 # Find all -I options and call addtree
 flags = $(foreach o,$($(1)),$(if $(filter -I%,$(o)),$(call addtree,$(o)),$(o)))
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index e7889f486ca1..514ed63ff571 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -590,7 +590,4 @@ endif
 # We never want them to be removed automatically.
 .SECONDARY: $(targets)
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index 808d09f27ad4..17ef94c635cd 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -88,7 +88,4 @@ PHONY += $(subdir-ymn)
 $(subdir-ymn):
 	$(Q)$(MAKE) $(clean)=$@
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modbuiltin b/scripts/Makefile.modbuiltin
index a763b4775d06..40867a41615b 100644
--- a/scripts/Makefile.modbuiltin
+++ b/scripts/Makefile.modbuiltin
@@ -54,8 +54,4 @@ PHONY += $(subdir-ym)
 $(subdir-ym):
 	$(Q)$(MAKE) $(modbuiltin)=$@
 
-
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
index 51ca0244fc8a..ff5ca9817a85 100644
--- a/scripts/Makefile.modinst
+++ b/scripts/Makefile.modinst
@@ -35,8 +35,4 @@ modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
 $(modules):
 	$(call cmd,modules_install,$(MODLIB)/$(modinst_dir))
 
-
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable so we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost
index df4174405feb..dd92dbbbaa68 100644
--- a/scripts/Makefile.modpost
+++ b/scripts/Makefile.modpost
@@ -149,8 +149,4 @@ ifneq ($(cmd_files),)
   include $(cmd_files)
 endif
 
-
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/Makefile.modsign b/scripts/Makefile.modsign
index 171483bc0538..da56aa78d245 100644
--- a/scripts/Makefile.modsign
+++ b/scripts/Makefile.modsign
@@ -27,7 +27,4 @@ modinst_dir = $(if $(KBUILD_EXTMOD),$(ext-mod-dir),kernel/$(@D))
 $(modules):
 	$(call cmd,sign_ko,$(MODLIB)/$(modinst_dir))
 
-# Declare the contents of the .PHONY variable as phony.  We keep that
-# information in a variable se we can use it in if_changed and friends.
-
 .PHONY: $(PHONY)
diff --git a/scripts/cc-can-link.sh b/scripts/cc-can-link.sh
index 208eb2825dab..6efcead31989 100755
--- a/scripts/cc-can-link.sh
+++ b/scripts/cc-can-link.sh
@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1 && echo "y"
+cat << "END" | $@ -x c - -o /dev/null >/dev/null 2>&1
 #include <stdio.h>
 int main(void)
 {
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index a9c05506e325..447857ffaf6b 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -5813,14 +5813,14 @@ sub process {
 		    defined $stat &&
 		    $stat =~ /^\+(?![^\{]*\{\s*).*\b(\w+)\s*\(.*$String\s*,/s &&
 		    $1 !~ /^_*volatile_*$/) {
-			my $specifier;
-			my $extension;
-			my $bad_specifier = "";
 			my $stat_real;
 
 			my $lc = $stat =~ tr@\n@@;
 			$lc = $lc + $linenr;
 		        for (my $count = $linenr; $count <= $lc; $count++) {
+				my $specifier;
+				my $extension;
+				my $bad_specifier = "";
 				my $fmt = get_quoted_string($lines[$count - 1], raw_line($count, 0));
 				$fmt =~ s/%%//g;
 
diff --git a/scripts/extract-vmlinux b/scripts/extract-vmlinux
index 5061abcc2540..e6239f39abad 100755
--- a/scripts/extract-vmlinux
+++ b/scripts/extract-vmlinux
@@ -57,6 +57,8 @@ try_decompress '\3757zXZ\000' abcde unxz
 try_decompress 'BZh'          xy    bunzip2
 try_decompress '\135\0\0\0'   xxx   unlzma
 try_decompress '\211\114\132' xy    'lzop -d'
+try_decompress '\002!L\030'   xxx   'lz4 -d'
+try_decompress '(\265/\375'   xxx   unzstd
 
 # Bail out:
 echo "$me: Cannot find vmlinux." >&2
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 66f08bb1cce9..26de7d5aa5c8 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -152,6 +152,7 @@ regex_asm=(
 )
 regex_c=(
 	'/^SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/sys_\1/'
+	'/^BPF_CALL_[0-9](\([[:alnum:]_]*\).*/\1/'
 	'/^COMPAT_SYSCALL_DEFINE[0-9](\([[:alnum:]_]*\).*/compat_sys_\1/'
 	'/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1/'
 	'/^TRACE_EVENT(\([[:alnum:]_]*\).*/trace_\1_rcuidle/'
@@ -245,7 +246,7 @@ exuberant()
 {
 	setup_regex exuberant asm c
 	all_target_sources | xargs $1 -a                        \
-	-I __initdata,__exitdata,__initconst,			\
+	-I __initdata,__exitdata,__initconst,__ro_after_init	\
 	-I __initdata_memblock					\
 	-I __refdata,__attribute,__maybe_unused,__always_unused \
 	-I __acquires,__releases,__deprecated			\
diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 69616d00481c..b53026a72e73 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -635,7 +635,7 @@ static int snd_rawmidi_info_select_user(struct snd_card *card,
 int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
 			      struct snd_rawmidi_params * params)
 {
-	char *newbuf;
+	char *newbuf, *oldbuf;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 	
 	if (substream->append && substream->use_count > 1)
@@ -648,13 +648,17 @@ int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
 		return -EINVAL;
 	}
 	if (params->buffer_size != runtime->buffer_size) {
-		newbuf = krealloc(runtime->buffer, params->buffer_size,
-				  GFP_KERNEL);
+		newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
 		if (!newbuf)
 			return -ENOMEM;
+		spin_lock_irq(&runtime->lock);
+		oldbuf = runtime->buffer;
 		runtime->buffer = newbuf;
 		runtime->buffer_size = params->buffer_size;
 		runtime->avail = runtime->buffer_size;
+		runtime->appl_ptr = runtime->hw_ptr = 0;
+		spin_unlock_irq(&runtime->lock);
+		kfree(oldbuf);
 	}
 	runtime->avail_min = params->avail_min;
 	substream->active_sensing = !params->no_active_sensing;
@@ -665,7 +669,7 @@ EXPORT_SYMBOL(snd_rawmidi_output_params);
 int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
 			     struct snd_rawmidi_params * params)
 {
-	char *newbuf;
+	char *newbuf, *oldbuf;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
 	snd_rawmidi_drain_input(substream);
@@ -676,12 +680,16 @@ int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
 		return -EINVAL;
 	}
 	if (params->buffer_size != runtime->buffer_size) {
-		newbuf = krealloc(runtime->buffer, params->buffer_size,
-				  GFP_KERNEL);
+		newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
 		if (!newbuf)
 			return -ENOMEM;
+		spin_lock_irq(&runtime->lock);
+		oldbuf = runtime->buffer;
 		runtime->buffer = newbuf;
 		runtime->buffer_size = params->buffer_size;
+		runtime->appl_ptr = runtime->hw_ptr = 0;
+		spin_unlock_irq(&runtime->lock);
+		kfree(oldbuf);
 	}
 	runtime->avail_min = params->avail_min;
 	return 0;
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 4ff5320378e2..321e95c409c1 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -1048,7 +1048,8 @@ static const struct snd_pci_quirk ca0132_quirks[] = {
 	SND_PCI_QUIRK(0x1102, 0x0010, "Sound Blaster Z", QUIRK_SBZ),
 	SND_PCI_QUIRK(0x1102, 0x0023, "Sound Blaster Z", QUIRK_SBZ),
 	SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
-	SND_PCI_QUIRK(0x1458, 0xA036, "Recon3Di", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI),
 	{}
 };
 
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e7fcfc3b8885..f641c20095f7 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -964,6 +964,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
 	SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
 	SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
+	SND_PCI_QUIRK(0x103c, 0x836e, "HP ProBook 455 G5", CXT_FIXUP_MUTE_LED_GPIO),
 	SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x8455, "HP Z2 G4", CXT_FIXUP_HP_MIC_NO_PRESENCE),
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 98e1c411c56a..8a49415aebac 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -33,6 +33,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <sound/core.h>
 #include <sound/jack.h>
 #include <sound/asoundef.h>
@@ -764,8 +765,10 @@ static void check_presence_and_report(struct hda_codec *codec, hda_nid_t nid,
 
 	if (pin_idx < 0)
 		return;
+	mutex_lock(&spec->pcm_lock);
 	if (hdmi_present_sense(get_pin(spec, pin_idx), 1))
 		snd_hda_jack_report_sync(codec);
+	mutex_unlock(&spec->pcm_lock);
 }
 
 static void jack_callback(struct hda_codec *codec,
@@ -1628,21 +1631,23 @@ static void sync_eld_via_acomp(struct hda_codec *codec,
 static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
 {
 	struct hda_codec *codec = per_pin->codec;
-	struct hdmi_spec *spec = codec->spec;
 	int ret;
 
 	/* no temporary power up/down needed for component notifier */
-	if (!codec_has_acomp(codec))
-		snd_hda_power_up_pm(codec);
+	if (!codec_has_acomp(codec)) {
+		ret = snd_hda_power_up_pm(codec);
+		if (ret < 0 && pm_runtime_suspended(hda_codec_dev(codec))) {
+			snd_hda_power_down_pm(codec);
+			return false;
+		}
+	}
 
-	mutex_lock(&spec->pcm_lock);
 	if (codec_has_acomp(codec)) {
 		sync_eld_via_acomp(codec, per_pin);
 		ret = false; /* don't call snd_hda_jack_report_sync() */
 	} else {
 		ret = hdmi_present_sense_via_verbs(per_pin, repoll);
 	}
-	mutex_unlock(&spec->pcm_lock);
 
 	if (!codec_has_acomp(codec))
 		snd_hda_power_down_pm(codec);
@@ -1654,12 +1659,16 @@ static void hdmi_repoll_eld(struct work_struct *work)
 {
 	struct hdmi_spec_per_pin *per_pin =
 	container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work);
+	struct hda_codec *codec = per_pin->codec;
+	struct hdmi_spec *spec = codec->spec;
 
 	if (per_pin->repoll_count++ > 6)
 		per_pin->repoll_count = 0;
 
+	mutex_lock(&spec->pcm_lock);
 	if (hdmi_present_sense(per_pin, per_pin->repoll_count))
 		snd_hda_jack_report_sync(per_pin->codec);
+	mutex_unlock(&spec->pcm_lock);
 }
 
 static void intel_haswell_fixup_connect_list(struct hda_codec *codec,
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 5ad6c7e5f92e..f6af3e1c2b93 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2366,6 +2366,7 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),
 	SND_PCI_QUIRK(0x147b, 0x107a, "Abit AW9D-MAX", ALC882_FIXUP_ABIT_AW9D_MAX),
 	SND_PCI_QUIRK(0x1558, 0x9501, "Clevo P950HR", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1558, 0x95e1, "Clevo P95xER", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1558, 0x95e2, "Clevo P950ER", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK_VENDOR(0x1558, "Clevo laptop", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x161f, 0x2054, "Medion laptop", ALC883_FIXUP_EAPD),
@@ -6569,6 +6570,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x10cf, 0x1629, "Lifebook U7x7", ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC),
 	SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
 	SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
+	SND_PCI_QUIRK(0x10f7, 0x8338, "Panasonic CF-SZ6", ALC269_FIXUP_HEADSET_MODE),
 	SND_PCI_QUIRK(0x144d, 0xc109, "Samsung Ativ book 9 (NP900X3G)", ALC269_FIXUP_INV_DMIC),
 	SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
 	SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC),
@@ -6612,7 +6614,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
-	SND_PCI_QUIRK(0x17aa, 0x3136, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
@@ -6796,6 +6797,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x1a, 0x02a11040},
 		{0x1b, 0x01014020},
 		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", ALC294_FIXUP_LENOVO_MIC_LOCATION,
+		{0x14, 0x90170110},
+		{0x19, 0x02a11020},
+		{0x1a, 0x02a11030},
+		{0x21, 0x0221101f}),
 	SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60140},
 		{0x14, 0x90170110},
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 32f9e397a6c0..3f140eff039f 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -217,6 +217,14 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	int err;
 	int fd;
 
+	if (argc < 3) {
+		p_err("too few arguments, id ID and FILE path is required");
+		return -1;
+	} else if (argc > 3) {
+		p_err("too many arguments");
+		return -1;
+	}
+
 	if (!is_prefix(*argv, "id")) {
 		p_err("expected 'id' got %s", *argv);
 		return -1;
@@ -230,9 +238,6 @@ int do_pin_any(int argc, char **argv, int (*get_fd_by_id)(__u32))
 	}
 	NEXT_ARG();
 
-	if (argc != 1)
-		usage();
-
 	fd = get_fd_by_id(id);
 	if (fd < 0) {
 		p_err("can't get prog by id (%u): %s", id, strerror(errno));
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 05f42a46d6ed..959aa53ab678 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -694,15 +694,19 @@ static int do_load(int argc, char **argv)
 		return -1;
 	}
 
-	if (do_pin_fd(prog_fd, argv[1])) {
-		p_err("failed to pin program");
-		return -1;
-	}
+	if (do_pin_fd(prog_fd, argv[1]))
+		goto err_close_obj;
 
 	if (json_output)
 		jsonw_null(json_wtr);
 
+	bpf_object__close(obj);
+
 	return 0;
+
+err_close_obj:
+	bpf_object__close(obj);
+	return -1;
 }
 
 static int do_help(int argc, char **argv)
diff --git a/tools/build/Build.include b/tools/build/Build.include
index a4bbb984941d..950c1504ca37 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -63,8 +63,8 @@ dep-cmd = $(if $(wildcard $(fixdep)),
            $(fixdep) $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp;           \
            rm -f $(depfile);                                                    \
            mv -f $(dot-target).tmp $(dot-target).cmd,                           \
-           printf '\# cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
-           printf '\# using basic dep data\n\n' >> $(dot-target).cmd;           \
+           printf '$(pound) cannot find fixdep (%s)\n' $(fixdep) > $(dot-target).cmd; \
+           printf '$(pound) using basic dep data\n\n' >> $(dot-target).cmd;           \
            cat $(depfile) >> $(dot-target).cmd;                                 \
            printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
 
@@ -98,4 +98,4 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CHOSTFLAGS) -D"BUILD_STR(s)=\#s" $(CHOSTFLAGS_$(basetarget).o) $(CHOSTFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 5eb4b5ad79cb..5edf65e684ab 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -43,7 +43,7 @@ $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
 
 $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
-	$(QUIET_LINK)$(HOSTCC) $(LDFLAGS) -o $@ $<
+	$(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $<
 
 FORCE:
 
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 4e60e105583e..7ec85d567598 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -302,19 +302,34 @@ static int read_symbols(struct elf *elf)
 				continue;
 			sym->pfunc = sym->cfunc = sym;
 			coldstr = strstr(sym->name, ".cold.");
-			if (coldstr) {
-				coldstr[0] = '\0';
-				pfunc = find_symbol_by_name(elf, sym->name);
-				coldstr[0] = '.';
-
-				if (!pfunc) {
-					WARN("%s(): can't find parent function",
-					     sym->name);
-					goto err;
-				}
-
-				sym->pfunc = pfunc;
-				pfunc->cfunc = sym;
+			if (!coldstr)
+				continue;
+
+			coldstr[0] = '\0';
+			pfunc = find_symbol_by_name(elf, sym->name);
+			coldstr[0] = '.';
+
+			if (!pfunc) {
+				WARN("%s(): can't find parent function",
+				     sym->name);
+				goto err;
+			}
+
+			sym->pfunc = pfunc;
+			pfunc->cfunc = sym;
+
+			/*
+			 * Unfortunately, -fnoreorder-functions puts the child
+			 * inside the parent.  Remove the overlap so we can
+			 * have sane assumptions.
+			 *
+			 * Note that pfunc->len now no longer matches
+			 * pfunc->sym.st_size.
+			 */
+			if (sym->sec == pfunc->sec &&
+			    sym->offset >= pfunc->offset &&
+			    sym->offset + sym->len == pfunc->offset + pfunc->len) {
+				pfunc->len -= sym->len;
 			}
 		}
 	}
@@ -504,10 +519,12 @@ struct section *elf_create_section(struct elf *elf, const char *name,
 	sec->sh.sh_flags = SHF_ALLOC;
 
 
-	/* Add section name to .shstrtab */
+	/* Add section name to .shstrtab (or .strtab for Clang) */
 	shstrtab = find_section_by_name(elf, ".shstrtab");
+	if (!shstrtab)
+		shstrtab = find_section_by_name(elf, ".strtab");
 	if (!shstrtab) {
-		WARN("can't find .shstrtab section");
+		WARN("can't find .shstrtab or .strtab section");
 		return NULL;
 	}
 
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index b5ac356ba323..f5a3b402589e 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -207,8 +207,7 @@ ifdef PYTHON_CONFIG
   PYTHON_EMBED_LDOPTS := $(shell $(PYTHON_CONFIG_SQ) --ldflags 2>/dev/null)
   PYTHON_EMBED_LDFLAGS := $(call strip-libs,$(PYTHON_EMBED_LDOPTS))
   PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
-  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --cflags 2>/dev/null)
-  PYTHON_EMBED_CCOPTS := $(filter-out -specs=%,$(PYTHON_EMBED_CCOPTS))
+  PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
   FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
 endif
 
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 4b2caf6d48e7..fead6b3b4206 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -226,7 +226,7 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 		else if (rm[2].rm_so != rm[2].rm_eo)
 			prefix[0] = '+';
 		else
-			strncpy(prefix, "+0", 2);
+			scnprintf(prefix, sizeof(prefix), "+0");
 	}
 
 	/* Rename register */
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 22547a490e1f..05be023c3f0e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1742,7 +1742,7 @@ static void print_interval(char *prefix, struct timespec *ts)
 		}
 	}
 
-	if ((num_print_interval == 0 && metric_only) || interval_clear)
+	if ((num_print_interval == 0 || interval_clear) && metric_only)
 		print_metric_headers(" ", true);
 	if (++num_print_interval == 25)
 		num_print_interval = 0;
diff --git a/tools/perf/jvmti/jvmti_agent.c b/tools/perf/jvmti/jvmti_agent.c
index 0c6d1002b524..ac1bcdc17dae 100644
--- a/tools/perf/jvmti/jvmti_agent.c
+++ b/tools/perf/jvmti/jvmti_agent.c
@@ -35,6 +35,7 @@
 #include <sys/mman.h>
 #include <syscall.h> /* for gettid() */
 #include <err.h>
+#include <linux/kernel.h>
 
 #include "jvmti_agent.h"
 #include "../util/jitdump.h"
@@ -249,7 +250,7 @@ void *jvmti_open(void)
 	/*
 	 * jitdump file name
 	 */
-	snprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
+	scnprintf(dump_path, PATH_MAX, "%s/jit-%i.dump", jit_path, getpid());
 
 	fd = open(dump_path, O_CREAT|O_TRUNC|O_RDWR, 0666);
 	if (fd == -1)
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 17783913d330..215ba30b8534 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -1,7 +1,7 @@
 hostprogs := jevents
 
 jevents-y	+= json.o jsmn.o jevents.o
-CHOSTFLAGS_jevents.o	= -I$(srctree)/tools/include
+HOSTCFLAGS_jevents.o	= -I$(srctree)/tools/include
 pmu-events-y	+= pmu-events.o
 JDIR		=  pmu-events/arch/$(SRCARCH)
 JSON		=  $(shell [ -d $(JDIR) ] &&				\
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
index 38dfb720fb6f..54ace2f6bc36 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Core.py
@@ -31,10 +31,8 @@ def flag_str(event_name, field_name, value):
     string = ""
 
     if flag_fields[event_name][field_name]:
-	print_delim = 0
-        keys = flag_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        print_delim = 0
+        for idx in sorted(flag_fields[event_name][field_name]['values']):
             if not value and not idx:
                 string += flag_fields[event_name][field_name]['values'][idx]
                 break
@@ -51,14 +49,12 @@ def symbol_str(event_name, field_name, value):
     string = ""
 
     if symbolic_fields[event_name][field_name]:
-        keys = symbolic_fields[event_name][field_name]['values'].keys()
-        keys.sort()
-        for idx in keys:
+        for idx in sorted(symbolic_fields[event_name][field_name]['values']):
             if not value and not idx:
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
-	    if (value == idx):
-		string = symbolic_fields[event_name][field_name]['values'][idx]
+            if (value == idx):
+                string = symbolic_fields[event_name][field_name]['values'][idx]
                 break
 
     return string
@@ -74,19 +70,17 @@ def trace_flag_str(value):
     string = ""
     print_delim = 0
 
-    keys = trace_flags.keys()
-
-    for idx in keys:
-	if not value and not idx:
-	    string += "NONE"
-	    break
-
-	if idx and (value & idx) == idx:
-	    if print_delim:
-		string += " | ";
-	    string += trace_flags[idx]
-	    print_delim = 1
-	    value &= ~idx
+    for idx in trace_flags:
+        if not value and not idx:
+            string += "NONE"
+            break
+
+        if idx and (value & idx) == idx:
+            if print_delim:
+                string += " | ";
+            string += trace_flags[idx]
+            print_delim = 1
+            value &= ~idx
 
     return string
 
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
index 81a56cd2b3c1..21a7a1298094 100755
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/EventClass.py
@@ -8,6 +8,7 @@
 # PerfEvent is the base class for all perf event sample, PebsEvent
 # is a HW base Intel x86 PEBS event, and user could add more SW/HW
 # event classes based on requirements.
+from __future__ import print_function
 
 import struct
 
@@ -44,7 +45,8 @@ class PerfEvent(object):
                 PerfEvent.event_num += 1
 
         def show(self):
-                print "PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" % (self.name, self.symbol, self.comm, self.dso)
+                print("PMU event: name=%12s, symbol=%24s, comm=%8s, dso=%12s" %
+                      (self.name, self.symbol, self.comm, self.dso))
 
 #
 # Basic Intel PEBS (Precise Event-based Sampling) event, whose raw buffer
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
index fdd92f699055..cac7b2542ee8 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/SchedGui.py
@@ -11,7 +11,7 @@
 try:
 	import wx
 except ImportError:
-	raise ImportError, "You need to install the wxpython lib for this script"
+	raise ImportError("You need to install the wxpython lib for this script")
 
 
 class RootFrame(wx.Frame):
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
index f6c84966e4f8..7384dcb628c4 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
+++ b/tools/perf/scripts/python/Perf-Trace-Util/lib/Perf/Trace/Util.py
@@ -5,6 +5,7 @@
 # This software may be distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
+from __future__ import print_function
 
 import errno, os
 
@@ -33,7 +34,7 @@ def nsecs_str(nsecs):
     return str
 
 def add_stats(dict, key, value):
-	if not dict.has_key(key):
+	if key not in dict:
 		dict[key] = (value, value, value, 1)
 	else:
 		min, max, avg, count = dict[key]
@@ -72,10 +73,10 @@ try:
 except:
 	if not audit_package_warned:
 		audit_package_warned = True
-		print "Install the audit-libs-python package to get syscall names.\n" \
-                    "For example:\n  # apt-get install python-audit (Ubuntu)" \
-                    "\n  # yum install audit-libs-python (Fedora)" \
-                    "\n  etc.\n"
+		print("Install the audit-libs-python package to get syscall names.\n"
+                    "For example:\n  # apt-get install python-audit (Ubuntu)"
+                    "\n  # yum install audit-libs-python (Fedora)"
+                    "\n  etc.\n")
 
 def syscall_name(id):
 	try:
diff --git a/tools/perf/scripts/python/sched-migration.py b/tools/perf/scripts/python/sched-migration.py
index de66cb3b72c9..3473e7f66081 100644
--- a/tools/perf/scripts/python/sched-migration.py
+++ b/tools/perf/scripts/python/sched-migration.py
@@ -9,13 +9,17 @@
 # This software is distributed under the terms of the GNU General
 # Public License ("GPL") version 2 as published by the Free Software
 # Foundation.
-
+from __future__ import print_function
 
 import os
 import sys
 
 from collections import defaultdict
-from UserList import UserList
+try:
+    from UserList import UserList
+except ImportError:
+    # Python 3: UserList moved to the collections package
+    from collections import UserList
 
 sys.path.append(os.environ['PERF_EXEC_PATH'] + \
 	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
@@ -300,7 +304,7 @@ class TimeSliceList(UserList):
 		if i == -1:
 			return
 
-		for i in xrange(i, len(self.data)):
+		for i in range(i, len(self.data)):
 			timeslice = self.data[i]
 			if timeslice.start > end:
 				return
@@ -336,8 +340,8 @@ class SchedEventProxy:
 		on_cpu_task = self.current_tsk[headers.cpu]
 
 		if on_cpu_task != -1 and on_cpu_task != prev_pid:
-			print "Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
-				(headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
+			print("Sched switch event rejected ts: %s cpu: %d prev: %s(%d) next: %s(%d)" % \
+				headers.ts_format(), headers.cpu, prev_comm, prev_pid, next_comm, next_pid)
 
 		threads[prev_pid] = prev_comm
 		threads[next_pid] = next_comm
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 2bde505e2e7e..dd850a26d579 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -422,7 +422,7 @@ static const char *shell_test__description(char *description, size_t size,
 
 #define for_each_shell_test(dir, base, ent)	\
 	while ((ent = readdir(dir)) != NULL)	\
-		if (!is_directory(base, ent))
+		if (!is_directory(base, ent) && ent->d_name[0] != '.')
 
 static const char *shell_tests__dir(char *path, size_t size)
 {
diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 263057039693..94e513e62b34 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -14,35 +14,40 @@ libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
-	idx=0
-	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
-	expected[1]=".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
+
+	expected=`mktemp -u /tmp/expected.XXX`
+
+	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf,max-stack=4'
-		expected[2]="gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[3]="(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$"
-		expected[4]="main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
+		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[2]="getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$"
-		expected[3]=".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$"
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
 	esac
 
-	file=`mktemp -u /tmp/perf.data.XXX`
+	perf_data=`mktemp -u /tmp/perf.data.XXX`
+	perf_script=`mktemp -u /tmp/perf.script.XXX`
+	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $perf_data > $perf_script
 
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
-	perf script -i $file | while read line ; do
+	exec 3<$perf_script
+	exec 4<$expected
+	while read line <&3 && read -r pattern <&4; do
+		[ -z "$pattern" ] && break
 		echo $line
-		echo "$line" | egrep -q "${expected[$idx]}"
+		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
-			printf "FAIL: expected backtrace entry %d \"%s\" got \"%s\"\n" $idx "${expected[$idx]}" "$line"
+			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
 			exit 1
 		fi
-		let idx+=1
-		[ -z "${expected[$idx]}" ] && break
 	done
 
 	# If any statements are executed from this point onwards,
@@ -58,6 +63,6 @@ skip_if_no_perf_probe && \
 perf probe -q $libc inet_pton && \
 trace_libc_inet_pton_backtrace
 err=$?
-rm -f ${file}
+rm -f ${perf_data} ${perf_script} ${expected}
 perf probe -q -d probe_libc:inet_pton
 exit $err
diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
index 55ad9793d544..4ce276efe6b4 100755
--- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh
@@ -17,7 +17,7 @@ skip_if_no_perf_probe || exit 2
 file=$(mktemp /tmp/temporary_file.XXXXX)
 
 trace_open_vfs_getname() {
-	evts=$(echo $(perf list syscalls:sys_enter_open* |& egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
+	evts=$(echo $(perf list syscalls:sys_enter_open* 2>&1 | egrep 'open(at)? ' | sed -r 's/.*sys_enter_([a-z]+) +\[.*$/\1/') | sed 's/ /,/')
 	perf trace -e $evts touch $file 2>&1 | \
 	egrep " +[0-9]+\.[0-9]+ +\( +[0-9]+\.[0-9]+ ms\): +touch\/[0-9]+ open(at)?\((dfd: +CWD, +)?filename: +${file}, +flags: CREAT\|NOCTTY\|NONBLOCK\|WRONLY, +mode: +IRUGO\|IWUGO\) += +[0-9]+$"
 }
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 976e658e38dc..5e94857dfca2 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -266,16 +266,16 @@ static const char *kinc_fetch_script =
 "#!/usr/bin/env sh\n"
 "if ! test -d \"$KBUILD_DIR\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "if ! test -f \"$KBUILD_DIR/include/generated/autoconf.h\"\n"
 "then\n"
-"	exit -1\n"
+"	exit 1\n"
 "fi\n"
 "TMPDIR=`mktemp -d`\n"
 "if test -z \"$TMPDIR\"\n"
 "then\n"
-"    exit -1\n"
+"    exit 1\n"
 "fi\n"
 "cat << EOF > $TMPDIR/Makefile\n"
 "obj-y := dummy.o\n"
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 46e9e19ab1ac..bc32e57d17be 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -908,14 +908,11 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (_PyTuple_Resize(&t, n) == -1)
 		Py_FatalError("error resizing Python tuple");
 
-	if (!dict) {
+	if (!dict)
 		call_object(handler, t, handler_name);
-	} else {
+	else
 		call_object(handler, t, default_handler_name);
-		Py_DECREF(dict);
-	}
 
-	Py_XDECREF(all_entries_dict);
 	Py_DECREF(t);
 }
 
@@ -1235,7 +1232,6 @@ static void python_process_general_event(struct perf_sample *sample,
 
 	call_object(handler, t, handler_name);
 
-	Py_DECREF(dict);
 	Py_DECREF(t);
 }
 
@@ -1627,6 +1623,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
+	fprintf(ofp, "from __future__ import print_function\n\n");
 	fprintf(ofp, "import os\n");
 	fprintf(ofp, "import sys\n\n");
 
@@ -1636,10 +1633,10 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 	fprintf(ofp, "from Core import *\n\n\n");
 
 	fprintf(ofp, "def trace_begin():\n");
-	fprintf(ofp, "\tprint \"in trace_begin\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_begin\")\n\n");
 
 	fprintf(ofp, "def trace_end():\n");
-	fprintf(ofp, "\tprint \"in trace_end\"\n\n");
+	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
 	while ((event = trace_find_next_event(pevent, event))) {
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
@@ -1675,7 +1672,7 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 			"common_secs, common_nsecs,\n\t\t\t"
 			"common_pid, common_comm)\n\n");
 
-		fprintf(ofp, "\t\tprint \"");
+		fprintf(ofp, "\t\tprint(\"");
 
 		not_first = 0;
 		count = 0;
@@ -1736,31 +1733,31 @@ static int python_generate_script(struct pevent *pevent, const char *outfile)
 				fprintf(ofp, "%s", f->name);
 		}
 
-		fprintf(ofp, ")\n\n");
+		fprintf(ofp, "))\n\n");
 
-		fprintf(ofp, "\t\tprint 'Sample: {'+"
-			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+		fprintf(ofp, "\t\tprint('Sample: {'+"
+			"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 		fprintf(ofp, "\t\tfor node in common_callchain:");
 		fprintf(ofp, "\n\t\t\tif 'sym' in node:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name'])");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\\t[%%x] %%s\" %% (node['ip'], node['sym']['name']))");
 		fprintf(ofp, "\n\t\t\telse:");
-		fprintf(ofp, "\n\t\t\t\tprint \"\t[%%x]\" %% (node['ip'])\n\n");
-		fprintf(ofp, "\t\tprint \"\\n\"\n\n");
+		fprintf(ofp, "\n\t\t\t\tprint(\"\t[%%x]\" %% (node['ip']))\n\n");
+		fprintf(ofp, "\t\tprint()\n\n");
 
 	}
 
 	fprintf(ofp, "def trace_unhandled(event_name, context, "
 		"event_fields_dict, perf_sample_dict):\n");
 
-	fprintf(ofp, "\t\tprint get_dict_as_string(event_fields_dict)\n");
-	fprintf(ofp, "\t\tprint 'Sample: {'+"
-		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}'\n\n");
+	fprintf(ofp, "\t\tprint(get_dict_as_string(event_fields_dict))\n");
+	fprintf(ofp, "\t\tprint('Sample: {'+"
+		"get_dict_as_string(perf_sample_dict['sample'], ', ')+'}')\n\n");
 
 	fprintf(ofp, "def print_header("
 		"event_name, cpu, secs, nsecs, pid, comm):\n"
-		"\tprint \"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
-		"(event_name, cpu, secs, nsecs, pid, comm),\n\n");
+		"\tprint(\"%%-20s %%5u %%05u.%%09u %%8u %%-20s \" %% \\\n\t"
+		"(event_name, cpu, secs, nsecs, pid, comm), end=\"\")\n\n");
 
 	fprintf(ofp, "def get_dict_as_string(a_dict, delimiter=' '):\n"
 		"\treturn delimiter.join"
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index a8fb63edcf89..e2926f72a821 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1991,8 +1991,7 @@ static void nfit_test0_setup(struct nfit_test *t)
 	pcap->header.type = ACPI_NFIT_TYPE_CAPABILITIES;
 	pcap->header.length = sizeof(*pcap);
 	pcap->highest_capability = 1;
-	pcap->capabilities = ACPI_NFIT_CAPABILITY_CACHE_FLUSH |
-		ACPI_NFIT_CAPABILITY_MEM_FLUSH;
+	pcap->capabilities = ACPI_NFIT_CAPABILITY_MEM_FLUSH;
 	offset += pcap->header.length;
 
 	if (t->setup_hotplug) {
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7a6214e9ae58..a362e3d7abc6 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -105,7 +105,7 @@ $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
 
 BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
 BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
-BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
 
 ifneq ($(BTF_LLC_PROBE),)
 ifneq ($(BTF_PAHOLE_PROBE),)
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 7eb613ffef55..b4994a94968b 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -6,6 +6,7 @@ CONFIG_TEST_BPF=m
 CONFIG_CGROUP_BPF=y
 CONFIG_NETDEVSIM=m
 CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCHED=y
 CONFIG_NET_SCH_INGRESS=y
 CONFIG_NET_IPIP=y
 CONFIG_IPV6=y
diff --git a/tools/testing/selftests/bpf/test_kmod.sh b/tools/testing/selftests/bpf/test_kmod.sh
index 35669ccd4d23..9df0d2ac45f8 100755
--- a/tools/testing/selftests/bpf/test_kmod.sh
+++ b/tools/testing/selftests/bpf/test_kmod.sh
@@ -1,6 +1,15 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ "$(id -u)" != "0" ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 SRC_TREE=../../../../
 
 test_run()
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
index ce2e15e4f976..677686198df3 100755
--- a/tools/testing/selftests/bpf/test_lirc_mode2.sh
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -1,6 +1,15 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 GREEN='\033[0;92m'
 RED='\033[0;31m'
 NC='\033[0m' # No Color
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
index 1c77994b5e71..270fa8f49573 100755
--- a/tools/testing/selftests/bpf/test_lwt_seg6local.sh
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -21,6 +21,15 @@
 # An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
 # datagram can be read on NS6 when binding to fb00::6.
 
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+msg="skip all tests:"
+if [ $UID != 0 ]; then
+	echo $msg please run this as root >&2
+	exit $ksft_skip
+fi
+
 TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
 
 cleanup()
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 05c8cb71724a..9e78df207919 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1413,18 +1413,12 @@ out:
 
 int main(int argc, char **argv)
 {
-	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
 	int iov_count = 1, length = 1024, rate = 1;
 	struct sockmap_options options = {0};
 	int opt, longindex, err, cg_fd = 0;
 	char *bpf_file = BPF_SOCKMAP_FILENAME;
 	int test = PING_PONG;
 
-	if (setrlimit(RLIMIT_MEMLOCK, &r)) {
-		perror("setrlimit(RLIMIT_MEMLOCK)");
-		return 1;
-	}
-
 	if (argc < 2)
 		return test_suite();
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 2ecd27b670d7..41106d9d5cc7 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -4975,6 +4975,24 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
 	},
 	{
+		"make headroom for LWT_XMIT",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+			BPF_MOV64_IMM(BPF_REG_2, 34),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+			/* split for s390 to succeed */
+			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+			BPF_MOV64_IMM(BPF_REG_2, 42),
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_EMIT_CALL(BPF_FUNC_skb_change_head),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_LWT_XMIT,
+	},
+	{
 		"invalid access of tc_classid for LWT_IN",
 		.insns = {
 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
@@ -11987,6 +12005,46 @@ static struct bpf_test tests[] = {
 		.prog_type = BPF_PROG_TYPE_XDP,
 	},
 	{
+		"xadd/w check whether src/dst got mangled, 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 3,
+	},
+	{
+		"xadd/w check whether src/dst got mangled, 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_0, 1),
+			BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
+			BPF_MOV64_REG(BPF_REG_7, BPF_REG_10),
+			BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -8),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_6, BPF_REG_0, 3),
+			BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_10, 2),
+			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -8),
+			BPF_EXIT_INSN(),
+			BPF_MOV64_IMM(BPF_REG_0, 42),
+			BPF_EXIT_INSN(),
+		},
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.retval = 3,
+	},
+	{
 		"bpf_get_stack return R0 within range",
 		.insns = {
 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
@@ -12554,8 +12612,11 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	}
 
 	if (fd_prog >= 0) {
+		__u8 tmp[TEST_DATA_LEN << 2];
+		__u32 size_tmp = sizeof(tmp);
+
 		err = bpf_prog_test_run(fd_prog, 1, test->data,
-					sizeof(test->data), NULL, NULL,
+					sizeof(test->data), tmp, &size_tmp,
 					&retval, NULL);
 		if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
 			printf("Unexpected bpf_prog_test_run error\n");
diff --git a/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc
new file mode 100644
index 000000000000..3b1f45e13a2e
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/00basic/snapshot.tc
@@ -0,0 +1,28 @@
+#!/bin/sh
+# description: Snapshot and tracing setting
+# flags: instance
+
+[ ! -f snapshot ] && exit_unsupported
+
+echo "Set tracing off"
+echo 0 > tracing_on
+
+echo "Allocate and take a snapshot"
+echo 1 > snapshot
+
+# Since trace buffer is empty, snapshot is also empty, but allocated
+grep -q "Snapshot is allocated" snapshot
+
+echo "Ensure keep tracing off"
+test `cat tracing_on` -eq 0
+
+echo "Set tracing on"
+echo 1 > tracing_on
+
+echo "Take a snapshot again"
+echo 1 > snapshot
+
+echo "Ensure keep tracing on"
+test `cat tracing_on` -eq 1
+
+exit 0
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 78245d60d8bc..0f45633bd634 100644..100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -740,13 +740,6 @@ ipv6_rt_add()
 	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
 	log_test $? 2 "Attempt to add duplicate route - reject route"
 
-	# iproute2 prepend only sets NLM_F_CREATE
-	# - adds a new route; does NOT convert existing route to ECMP
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
-	check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
-	log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
-
 	# route append with same prefix adds a new route
 	# - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
 	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
@@ -754,27 +747,6 @@ ipv6_rt_add()
 	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
 	log_test $? 0 "Append nexthop to existing route - gw"
 
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
-	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
-	log_test $? 0 "Append nexthop to existing route - dev only"
-
-	# multipath route can not have a nexthop that is a reject route
-	add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
-	run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
-	log_test $? 2 "Append nexthop to existing route - reject route"
-
-	# reject route can not be converted to multipath route
-	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
-	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
-	log_test $? 2 "Append nexthop to existing reject route - gw"
-
-	run_cmd "$IP -6 ro flush 2001:db8:104::/64"
-	run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
-	run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
-	log_test $? 2 "Append nexthop to existing reject route - dev only"
-
 	# insert mpath directly
 	add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	check_route6  "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
@@ -819,13 +791,6 @@ ipv6_rt_replace_single()
 	check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
 	log_test $? 0 "Single path with multipath"
 
-	# single path with reject
-	#
-	add_initial_route6 "nexthop via 2001:db8:101::2"
-	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
-	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
-	log_test $? 0 "Single path with reject route"
-
 	# single path with single path using MULTIPATH attribute
 	#
 	add_initial_route6 "via 2001:db8:101::2"
@@ -873,12 +838,6 @@ ipv6_rt_replace_mpath()
 	check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
 	log_test $? 0 "Multipath with single path via multipath attribute"
 
-	# multipath with reject
-	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
-	run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
-	check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
-	log_test $? 0 "Multipath with reject route"
-
 	# route replace fails - invalid nexthop 1
 	add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
 	run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
index 792fa4d0285e..850767befa47 100755
--- a/tools/testing/selftests/net/udpgso_bench.sh
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -35,9 +35,6 @@ run_udp() {
 
 	echo "udp gso"
 	run_in_netns ${args} -S
-
-	echo "udp gso zerocopy"
-	run_in_netns ${args} -S -z
 }
 
 run_tcp() {
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index a4684112676c..86ce22417e0d 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -133,17 +133,27 @@ static inline uint32_t rseq_current_cpu(void)
 	return cpu;
 }
 
+static inline void rseq_clear_rseq_cs(void)
+{
+#ifdef __LP64__
+	__rseq_abi.rseq_cs.ptr = 0;
+#else
+	__rseq_abi.rseq_cs.ptr.ptr32 = 0;
+#endif
+}
+
 /*
- * rseq_prepare_unload() should be invoked by each thread using rseq_finish*()
- * at least once between their last rseq_finish*() and library unload of the
- * library defining the rseq critical section (struct rseq_cs). This also
- * applies to use of rseq in code generated by JIT: rseq_prepare_unload()
- * should be invoked at least once by each thread using rseq_finish*() before
- * reclaim of the memory holding the struct rseq_cs.
+ * rseq_prepare_unload() should be invoked by each thread executing a rseq
+ * critical section at least once between their last critical section and
+ * library unload of the library defining the rseq critical section
+ * (struct rseq_cs). This also applies to use of rseq in code generated by
+ * JIT: rseq_prepare_unload() should be invoked at least once by each
+ * thread executing a rseq critical section before reclaim of the memory
+ * holding the struct rseq_cs.
  */
 static inline void rseq_prepare_unload(void)
 {
-	__rseq_abi.rseq_cs = 0;
+	rseq_clear_rseq_cs();
 }
 
 #endif  /* RSEQ_H_ */
diff --git a/tools/usb/ffs-test.c b/tools/usb/ffs-test.c
index 95dd14648ba5..0f395dfb7774 100644
--- a/tools/usb/ffs-test.c
+++ b/tools/usb/ffs-test.c
@@ -44,12 +44,25 @@
 
 /******************** Little Endian Handling ********************************/
 
-#define cpu_to_le16(x)  htole16(x)
-#define cpu_to_le32(x)  htole32(x)
+/*
+ * cpu_to_le16/32 are used when initializing structures, a context where a
+ * function call is not allowed. To solve this, we code cpu_to_le16/32 in a way
+ * that allows them to be used when initializing structures.
+ */
+
+#if __BYTE_ORDER == __LITTLE_ENDIAN
+#define cpu_to_le16(x)  (x)
+#define cpu_to_le32(x)  (x)
+#else
+#define cpu_to_le16(x)  ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))
+#define cpu_to_le32(x)  \
+	((((x) & 0xff000000u) >> 24) | (((x) & 0x00ff0000u) >>  8) | \
+	(((x) & 0x0000ff00u) <<  8) | (((x) & 0x000000ffu) << 24))
+#endif
+
 #define le32_to_cpu(x)  le32toh(x)
 #define le16_to_cpu(x)  le16toh(x)
 
-
 /******************** Messages and Errors ***********************************/
 
 static const char argv0[] = "ffs-test";
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 90d30fbe95ae..b20b751286fc 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -119,8 +119,12 @@ irqfd_shutdown(struct work_struct *work)
 {
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(work, struct kvm_kernel_irqfd, shutdown);
+	struct kvm *kvm = irqfd->kvm;
 	u64 cnt;
 
+	/* Make sure irqfd has been initalized in assign path. */
+	synchronize_srcu(&kvm->irq_srcu);
+
 	/*
 	 * Synchronize with the wait-queue and unhook ourselves to prevent
 	 * further events.
@@ -387,7 +391,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	irqfd_update(kvm, irqfd);
-	srcu_read_unlock(&kvm->irq_srcu, idx);
 
 	list_add_tail(&irqfd->list, &kvm->irqfds.items);
 
@@ -402,11 +405,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	if (events & EPOLLIN)
 		schedule_work(&irqfd->inject);
 
-	/*
-	 * do not drop the file until the irqfd is fully initialized, otherwise
-	 * we might race against the EPOLLHUP
-	 */
-	fdput(f);
 #ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
 	if (kvm_arch_has_irq_bypass()) {
 		irqfd->consumer.token = (void *)irqfd->eventfd;
@@ -421,6 +419,13 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	}
 #endif
 
+	srcu_read_unlock(&kvm->irq_srcu, idx);
+
+	/*
+	 * do not drop the file until the irqfd is fully initialized, otherwise
+	 * we might race against the EPOLLHUP
+	 */
+	fdput(f);
 	return 0;
 
 fail: