1575 files changed, 46337 insertions, 18111 deletions

diff --git a/.mailmap b/.mailmap
index edcac87e76c8..fd6219293057 100644
--- a/.mailmap
+++ b/.mailmap
@@ -108,6 +108,10 @@ Jason Gunthorpe <jgg@ziepe.ca> <jgg@mellanox.com>
 Jason Gunthorpe <jgg@ziepe.ca> <jgunthorpe@obsidianresearch.com>
 Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
+Jayachandran C <c.jayachandran@gmail.com> <jayachandranc@netlogicmicro.com>
+Jayachandran C <c.jayachandran@gmail.com> <jchandra@broadcom.com>
+Jayachandran C <c.jayachandran@gmail.com> <jchandra@digeo.com>
+Jayachandran C <c.jayachandran@gmail.com> <jnair@caviumnetworks.com>
 Jean Tourrilhes <jt@hpl.hp.com>
 <jean-philippe@linaro.org> <jean-philippe.brucker@arm.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
@@ -196,7 +200,8 @@ Oleksij Rempel <linux@rempel-privat.de> <o.rempel@pengutronix.de>
 Oleksij Rempel <linux@rempel-privat.de> <ore@pengutronix.de>
 Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
 Patrick Mochel <mochel@digitalimplant.org>
-Paul Burton <paul.burton@mips.com> <paul.burton@imgtec.com>
+Paul Burton <paulburton@kernel.org> <paul.burton@imgtec.com>
+Paul Burton <paulburton@kernel.org> <paul.burton@mips.com>
 Peter A Jonsson <pj@ludd.ltu.se>
 Peter Oruba <peter@oruba.de>
 Peter Oruba <peter.oruba@amd.com>
@@ -229,6 +234,7 @@ Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com>
 Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com>
 Shuah Khan <shuah@kernel.org> <shuahkh@osg.samsung.com>
 Shuah Khan <shuah@kernel.org> <shuah.kh@samsung.com>
+Simon Arlott <simon@octiron.net> <simon@fire.lp0.eu>
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst
index ab7ed2fd072f..5a09661330fc 100644
--- a/Documentation/arm64/silicon-errata.rst
+++ b/Documentation/arm64/silicon-errata.rst
@@ -91,6 +91,11 @@ stable kernels.
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+
+| Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
++----------------+-----------------+-----------------+-----------------------------+
+| Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_843419        |
++----------------+-----------------+-----------------+-----------------------------+
++----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX ITS    | #22375,24313    | CAVIUM_ERRATUM_22375        |
 +----------------+-----------------+-----------------+-----------------------------+
 | Cavium         | ThunderX ITS    | #23144          | CAVIUM_ERRATUM_23144        |
@@ -126,7 +131,7 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | Qualcomm Tech. | Kryo/Falkor v1  | E1003           | QCOM_FALKOR_ERRATUM_1003    |
 +----------------+-----------------+-----------------+-----------------------------+
-| Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
+| Qualcomm Tech. | Kryo/Falkor v1  | E1009           | QCOM_FALKOR_ERRATUM_1009    |
 +----------------+-----------------+-----------------+-----------------------------+
 | Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/Documentation/devicetree/bindings/arm/rockchip.yaml b/Documentation/devicetree/bindings/arm/rockchip.yaml
index c82c5e57d44c..9c7e70335ac0 100644
--- a/Documentation/devicetree/bindings/arm/rockchip.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip.yaml
@@ -496,12 +496,12 @@ properties:
 
       - description: Theobroma Systems RK3368-uQ7 with Haikou baseboard
         items:
-          - const: tsd,rk3368-uq7-haikou
+          - const: tsd,rk3368-lion-haikou
           - const: rockchip,rk3368
 
       - description: Theobroma Systems RK3399-Q7 with Haikou baseboard
         items:
-          - const: tsd,rk3399-q7-haikou
+          - const: tsd,rk3399-puma-haikou
           - const: rockchip,rk3399
 
       - description: Tronsmart Orion R68 Meta
diff --git a/Documentation/devicetree/bindings/display/msm/gmu.txt b/Documentation/devicetree/bindings/display/msm/gmu.txt
index 90af5b0a56a9..bf9c7a2a495c 100644
--- a/Documentation/devicetree/bindings/display/msm/gmu.txt
+++ b/Documentation/devicetree/bindings/display/msm/gmu.txt
@@ -31,6 +31,10 @@ Required properties:
 - iommus: phandle to the adreno iommu
 - operating-points-v2: phandle to the OPP operating points
 
+Optional properties:
+- sram: phandle to the On Chip Memory (OCMEM) that's present on some Snapdragon
+        SoCs. See Documentation/devicetree/bindings/sram/qcom,ocmem.yaml.
+
 Example:
 
 / {
@@ -63,3 +67,50 @@ Example:
 		operating-points-v2 = <&gmu_opp_table>;
 	};
 };
+
+a3xx example with OCMEM support:
+
+/ {
+	...
+
+	gpu: adreno@fdb00000 {
+		compatible = "qcom,adreno-330.2",
+		             "qcom,adreno";
+		reg = <0xfdb00000 0x10000>;
+		reg-names = "kgsl_3d0_reg_memory";
+		interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-names = "kgsl_3d0_irq";
+		clock-names = "core",
+		              "iface",
+		              "mem_iface";
+		clocks = <&mmcc OXILI_GFX3D_CLK>,
+		         <&mmcc OXILICX_AHB_CLK>,
+		         <&mmcc OXILICX_AXI_CLK>;
+		sram = <&gmu_sram>;
+		power-domains = <&mmcc OXILICX_GDSC>;
+		operating-points-v2 = <&gpu_opp_table>;
+		iommus = <&gpu_iommu 0>;
+	};
+
+	ocmem@fdd00000 {
+		compatible = "qcom,msm8974-ocmem";
+
+		reg = <0xfdd00000 0x2000>,
+		      <0xfec00000 0x180000>;
+		reg-names = "ctrl",
+		             "mem";
+
+		clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>,
+		         <&mmcc OCMEMCX_OCMEMNOC_CLK>;
+		clock-names = "core",
+		              "iface";
+
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		gmu_sram: gmu-sram@0 {
+			reg = <0x0 0x100000>;
+			ranges = <0 0 0xfec00000 0x100000>;
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt
index 4e11338548aa..43d11279c925 100644
--- a/Documentation/devicetree/bindings/display/msm/mdp5.txt
+++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt
@@ -76,6 +76,8 @@ Required properties:
 Optional properties:
 - clock-names: the following clocks are optional:
   * "lut"
+  * "tbu"
+  * "tbu_rt"
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
index 27f38eed389e..d3e423fcb6c2 100644
--- a/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
+++ b/Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/arm/allwinner,sun4i-a10-csi.yaml#
+$id: http://devicetree.org/schemas/media/allwinner,sun4i-a10-csi.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Allwinner A10 CMOS Sensor Interface (CSI) Device Tree Bindings
@@ -27,14 +27,12 @@ properties:
   clocks:
     items:
       - description: The CSI interface clock
-      - description: The CSI module clock
       - description: The CSI ISP clock
       - description: The CSI DRAM clock
 
   clock-names:
     items:
       - const: bus
-      - const: mod
       - const: isp
       - const: ram
 
@@ -89,9 +87,8 @@ examples:
         compatible = "allwinner,sun7i-a20-csi0";
         reg = <0x01c09000 0x1000>;
         interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
-        clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>,
-                 <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
-        clock-names = "bus", "mod", "isp", "ram";
+        clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
+        clock-names = "bus", "isp", "ram";
         resets = <&ccu RST_CSI0>;
 
         port {
diff --git a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml
index f83d888176cc..064b7dfc4252 100644
--- a/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml
+++ b/Documentation/devicetree/bindings/pinctrl/aspeed,ast2600-pinctrl.yaml
@@ -33,13 +33,13 @@ patternProperties:
           allOf:
             - $ref: "/schemas/types.yaml#/definitions/string"
             - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15,
-              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI,
-              ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0, GPIT1,
-              GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1, GPIU2,
-              GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11, I2C12,
-              I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7,
-              I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC,
-              LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2,
+              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMC,
+              ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWSPIWP, GPIT0,
+              GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1,
+              GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, I2C1, I2C10, I2C11,
+              I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6,
+              I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ,
+              LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2,
               MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2,
               NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3,
               NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1,
@@ -48,47 +48,45 @@ patternProperties:
               PWM8, PWM9, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3,
               RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10, SALT11, SALT12,
               SALT13, SALT14, SALT15, SALT16, SALT2, SALT3, SALT4, SALT5,
-              SALT6, SALT7, SALT8, SALT9, SD1, SD2, SD3, SD3DAT4, SD3DAT5,
-              SD3DAT6, SD3DAT7, SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO,
-              SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1,
-              SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11,
-              TACH12, TACH13, TACH14, TACH15, TACH2, TACH3, TACH4, TACH5,
-              TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2, THRU3, TXD1,
-              TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13, UART6, UART7,
-              UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3,
-              WDTRST4, ]
+              SALT6, SALT7, SALT8, SALT9, SD1, SD2, SGPM1, SGPS1, SIOONCTRL,
+              SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1,
+              SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1,
+              TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3,
+              TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2,
+              THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12, UART13,
+              UART6, UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2,
+              WDTRST3, WDTRST4, ]
         groups:
           allOf:
             - $ref: "/schemas/types.yaml#/definitions/string"
             - enum: [ ADC0, ADC1, ADC10, ADC11, ADC12, ADC13, ADC14, ADC15,
-              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, ESPI,
-              ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID, FWQSPID, FWSPIWP, GPIT0,
-              GPIT1, GPIT2, GPIT3, GPIT4, GPIT5, GPIT6, GPIT7, GPIU0, GPIU1,
-              GPIU2, GPIU3, GPIU4, GPIU5, GPIU6, GPIU7, HVI3C3, HVI3C4, I2C1,
-              I2C10, I2C11, I2C12, I2C13, I2C14, I2C15, I2C16, I2C2, I2C3,
-              I2C4, I2C5, I2C6, I2C7, I2C8, I2C9, I3C3, I3C4, I3C5, I3C6,
-              JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD, LPCPME, LPCSMI, LSIRQ,
-              MACLINK1, MACLINK2, MACLINK3, MACLINK4, MDIO1, MDIO2, MDIO3,
-              MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1, NDCD2, NDCD3, NDCD4,
-              NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2, NDTR3, NDTR4, NRI1,
-              NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4, OSCCLK, PEWAKE,
-              PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1, PWM12G0, PWM12G1,
-              PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0, PWM15G1, PWM2, PWM3,
-              PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1, PWM9G0, PWM9G1, QSPI1,
-              QSPI2, RGMII1, RGMII2, RGMII3, RGMII4, RMII1, RMII2, RMII3,
-              RMII4, RXD1, RXD2, RXD3, RXD4, SALT1, SALT10G0, SALT10G1,
-              SALT11G0, SALT11G1, SALT12G0, SALT12G1, SALT13G0, SALT13G1,
-              SALT14G0, SALT14G1, SALT15G0, SALT15G1, SALT16G0, SALT16G1,
-              SALT2, SALT3, SALT4, SALT5, SALT6, SALT7, SALT8, SALT9G0,
-              SALT9G1, SD1, SD2, SD3, SD3DAT4, SD3DAT5, SD3DAT6, SD3DAT7,
-              SGPM1, SGPS1, SIOONCTRL, SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD,
-              SIOS3, SIOS5, SIOSCI, SPI1, SPI1ABR, SPI1CS1, SPI1WP, SPI2,
-              SPI2CS1, SPI2CS2, TACH0, TACH1, TACH10, TACH11, TACH12, TACH13,
-              TACH14, TACH15, TACH2, TACH3, TACH4, TACH5, TACH6, TACH7, TACH8,
-              TACH9, THRU0, THRU1, THRU2, THRU3, TXD1, TXD2, TXD3, TXD4,
-              UART10, UART11, UART12G0, UART12G1, UART13G0, UART13G1, UART6,
-              UART7, UART8, UART9, VB, VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3,
-              WDTRST4, ]
+              ADC2, ADC3, ADC4, ADC5, ADC6, ADC7, ADC8, ADC9, BMCINT, EMMCG1,
+              EMMCG4, EMMCG8, ESPI, ESPIALT, FSI1, FSI2, FWSPIABR, FWSPID,
+              FWQSPID, FWSPIWP, GPIT0, GPIT1, GPIT2, GPIT3, GPIT4, GPIT5,
+              GPIT6, GPIT7, GPIU0, GPIU1, GPIU2, GPIU3, GPIU4, GPIU5, GPIU6,
+              GPIU7, HVI3C3, HVI3C4, I2C1, I2C10, I2C11, I2C12, I2C13, I2C14,
+              I2C15, I2C16, I2C2, I2C3, I2C4, I2C5, I2C6, I2C7, I2C8, I2C9,
+              I3C3, I3C4, I3C5, I3C6, JTAGM, LHPD, LHSIRQ, LPC, LPCHC, LPCPD,
+              LPCPME, LPCSMI, LSIRQ, MACLINK1, MACLINK2, MACLINK3, MACLINK4,
+              MDIO1, MDIO2, MDIO3, MDIO4, NCTS1, NCTS2, NCTS3, NCTS4, NDCD1,
+              NDCD2, NDCD3, NDCD4, NDSR1, NDSR2, NDSR3, NDSR4, NDTR1, NDTR2,
+              NDTR3, NDTR4, NRI1, NRI2, NRI3, NRI4, NRTS1, NRTS2, NRTS3, NRTS4,
+              OSCCLK, PEWAKE, PWM0, PWM1, PWM10G0, PWM10G1, PWM11G0, PWM11G1,
+              PWM12G0, PWM12G1, PWM13G0, PWM13G1, PWM14G0, PWM14G1, PWM15G0,
+              PWM15G1, PWM2, PWM3, PWM4, PWM5, PWM6, PWM7, PWM8G0, PWM8G1,
+              PWM9G0, PWM9G1, QSPI1, QSPI2, RGMII1, RGMII2, RGMII3, RGMII4,
+              RMII1, RMII2, RMII3, RMII4, RXD1, RXD2, RXD3, RXD4, SALT1,
+              SALT10G0, SALT10G1, SALT11G0, SALT11G1, SALT12G0, SALT12G1,
+              SALT13G0, SALT13G1, SALT14G0, SALT14G1, SALT15G0, SALT15G1,
+              SALT16G0, SALT16G1, SALT2, SALT3, SALT4, SALT5, SALT6, SALT7,
+              SALT8, SALT9G0, SALT9G1, SD1, SD2, SD3, SGPM1, SGPS1, SIOONCTRL,
+              SIOPBI, SIOPBO, SIOPWREQ, SIOPWRGD, SIOS3, SIOS5, SIOSCI, SPI1,
+              SPI1ABR, SPI1CS1, SPI1WP, SPI2, SPI2CS1, SPI2CS2, TACH0, TACH1,
+              TACH10, TACH11, TACH12, TACH13, TACH14, TACH15, TACH2, TACH3,
+              TACH4, TACH5, TACH6, TACH7, TACH8, TACH9, THRU0, THRU1, THRU2,
+              THRU3, TXD1, TXD2, TXD3, TXD4, UART10, UART11, UART12G0,
+              UART12G1, UART13G0, UART13G1, UART6, UART7, UART8, UART9, VB,
+              VGAHS, VGAVS, WDTRST1, WDTRST2, WDTRST3, WDTRST4, ]
 
 required:
   - compatible
diff --git a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
index a78150c47aa2..f32416968197 100644
--- a/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/fixed-regulator.yaml
@@ -30,8 +30,8 @@ if:
 properties:
   compatible:
     enum:
-      - const: regulator-fixed
-      - const: regulator-fixed-clock
+      - regulator-fixed
+      - regulator-fixed-clock
 
   regulator-name: true
 
diff --git a/Documentation/devicetree/bindings/riscv/cpus.yaml b/Documentation/devicetree/bindings/riscv/cpus.yaml
index b261a3015f84..04819ad379c2 100644
--- a/Documentation/devicetree/bindings/riscv/cpus.yaml
+++ b/Documentation/devicetree/bindings/riscv/cpus.yaml
@@ -24,15 +24,17 @@ description: |
 
 properties:
   compatible:
-    items:
-      - enum:
-          - sifive,rocket0
-          - sifive,e5
-          - sifive,e51
-          - sifive,u54-mc
-          - sifive,u54
-          - sifive,u5
-      - const: riscv
+    oneOf:
+      - items:
+          - enum:
+              - sifive,rocket0
+              - sifive,e5
+              - sifive,e51
+              - sifive,u54-mc
+              - sifive,u54
+              - sifive,u5
+          - const: riscv
+      - const: riscv    # Simulator only
     description:
       Identifies that the hart uses the RISC-V instruction set
       and identifies the type of the hart.
@@ -66,12 +68,8 @@ properties:
       insensitive, letters in the riscv,isa string must be all
       lowercase to simplify parsing.
 
-  timebase-frequency:
-    type: integer
-    minimum: 1
-    description:
-      Specifies the clock frequency of the system timer in Hz.
-      This value is common to all harts on a single system image.
+  # RISC-V requires 'timebase-frequency' in /cpus, so disallow it here
+  timebase-frequency: false
 
   interrupt-controller:
     type: object
@@ -93,7 +91,6 @@ properties:
 
 required:
   - riscv,isa
-  - timebase-frequency
   - interrupt-controller
 
 examples:
diff --git a/Documentation/devicetree/bindings/sram/qcom,ocmem.yaml b/Documentation/devicetree/bindings/sram/qcom,ocmem.yaml
new file mode 100644
index 000000000000..222990f9923c
--- /dev/null
+++ b/Documentation/devicetree/bindings/sram/qcom,ocmem.yaml
@@ -0,0 +1,96 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/sram/qcom,ocmem.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: On Chip Memory (OCMEM) that is present on some Qualcomm Snapdragon SoCs.
+
+maintainers:
+  - Brian Masney <masneyb@onstation.org>
+
+description: |
+  The On Chip Memory (OCMEM) is typically used by the GPU, camera/video, and
+  audio components on some Snapdragon SoCs.
+
+properties:
+  compatible:
+    const: qcom,msm8974-ocmem
+
+  reg:
+    items:
+      - description: Control registers
+      - description: OCMEM address range
+
+  reg-names:
+    items:
+      - const: ctrl
+      - const: mem
+
+  clocks:
+    items:
+      - description: Core clock
+      - description: Interface clock
+
+  clock-names:
+    items:
+      - const: core
+      - const: iface
+
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 1
+
+required:
+  - compatible
+  - reg
+  - reg-names
+  - clocks
+  - clock-names
+  - '#address-cells'
+  - '#size-cells'
+
+patternProperties:
+  "^.+-sram$":
+    type: object
+    description: A region of reserved memory.
+
+    properties:
+      reg:
+        maxItems: 1
+
+      ranges:
+        maxItems: 1
+
+    required:
+      - reg
+      - ranges
+
+examples:
+  - |
+      #include <dt-bindings/clock/qcom,rpmcc.h>
+      #include <dt-bindings/clock/qcom,mmcc-msm8974.h>
+
+      ocmem: ocmem@fdd00000 {
+        compatible = "qcom,msm8974-ocmem";
+
+        reg = <0xfdd00000 0x2000>,
+              <0xfec00000 0x180000>;
+        reg-names = "ctrl",
+                    "mem";
+
+        clocks = <&rpmcc RPM_SMD_OCMEMGX_CLK>,
+                 <&mmcc OCMEMCX_OCMEMNOC_CLK>;
+        clock-names = "core",
+                      "iface";
+
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        gmu-sram@0 {
+                reg = <0x0 0x100000>;
+                ranges = <0 0 0xfec00000 0x100000>;
+        };
+      };
diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index b541e97c7ab1..c78db28519f7 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -118,13 +118,13 @@ Kernel Functions and Structures Reference
 Reservation Objects
 -------------------
 
-.. kernel-doc:: drivers/dma-buf/reservation.c
+.. kernel-doc:: drivers/dma-buf/dma-resv.c
    :doc: Reservation Object Overview
 
-.. kernel-doc:: drivers/dma-buf/reservation.c
+.. kernel-doc:: drivers/dma-buf/dma-resv.c
    :export:
 
-.. kernel-doc:: include/linux/reservation.h
+.. kernel-doc:: include/linux/dma-resv.h
    :internal:
 
 DMA Fences
diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 5acdd1842ea2..0efede580039 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -79,16 +79,71 @@ AMDGPU XGMI Support
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
    :internal:
 
-AMDGPU RAS debugfs control interface
-====================================
+AMDGPU RAS Support
+==================
+
+The AMDGPU RAS interfaces are exposed via sysfs (for informational queries) and
+debugfs (for error injection).
+
+RAS debugfs/sysfs Control and Error Injection Interfaces
+--------------------------------------------------------
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
    :doc: AMDGPU RAS debugfs control interface
 
+RAS Reboot Behavior for Unrecoverable Errors
+--------------------------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+   :doc: AMDGPU RAS Reboot Behavior for Unrecoverable Errors
+
+RAS Error Count sysfs Interface
+-------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+   :doc: AMDGPU RAS sysfs Error Count Interface
+
+RAS EEPROM debugfs Interface
+----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+   :doc: AMDGPU RAS debugfs EEPROM table reset interface
+
+RAS VRAM Bad Pages sysfs Interface
+----------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+   :doc: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
    :internal:
 
+Sample Code
+-----------
+Sample code for testing error injection can be found here:
+https://cgit.freedesktop.org/mesa/drm/tree/tests/amdgpu/ras_tests.c
+
+This is part of the libdrm amdgpu unit tests which cover several areas of the GPU.
+There are four sets of tests:
+
+RAS Basic Test
+
+The test verifies the RAS feature enabled status and makes sure the necessary sysfs and debugfs files
+are present.
+
+RAS Query Test
+
+This test checks the RAS availability and enablement status for each supported IP block as well as
+the error counts.
+
+RAS Inject Test
+
+This test injects errors for each IP.
+
+RAS Disable Test
+
+This test tests disabling of RAS features for each IP block.
+
 
 GPU Power/Thermal Controls and Monitoring
 =========================================
@@ -130,11 +185,11 @@ pp_od_clk_voltage
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
    :doc: pp_od_clk_voltage
 
-pp_dpm_sclk pp_dpm_mclk pp_dpm_pcie
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+pp_dpm_*
+~~~~~~~~
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
-   :doc: pp_dpm_sclk pp_dpm_mclk pp_dpm_pcie
+   :doc: pp_dpm_sclk pp_dpm_mclk pp_dpm_socclk pp_dpm_fclk pp_dpm_dcefclk pp_dpm_pcie
 
 pp_power_profile_mode
 ~~~~~~~~~~~~~~~~~~~~~
diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 60bd6e6403da..d0947c5c4ab8 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -550,9 +550,9 @@ i915 Perf Stream
 This section covers the stream-semantics-agnostic structures and functions
 for representing an i915 perf stream FD and associated file operations.
 
-.. kernel-doc:: drivers/gpu/drm/i915/i915_drv.h
+.. kernel-doc:: drivers/gpu/drm/i915/i915_perf_types.h
    :functions: i915_perf_stream
-.. kernel-doc:: drivers/gpu/drm/i915/i915_drv.h
+.. kernel-doc:: drivers/gpu/drm/i915/i915_perf_types.h
    :functions: i915_perf_stream_ops
 
 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
@@ -577,7 +577,7 @@ for representing an i915 perf stream FD and associated file operations.
 i915 Perf Observation Architecture Stream
 -----------------------------------------
 
-.. kernel-doc:: drivers/gpu/drm/i915/i915_drv.h
+.. kernel-doc:: drivers/gpu/drm/i915/i915_perf_types.h
    :functions: i915_oa_ops
 
 .. kernel-doc:: drivers/gpu/drm/i915/i915_perf.c
diff --git a/Documentation/gpu/todo.rst b/Documentation/gpu/todo.rst
index 73c51b5a0997..6792fa9b6b6b 100644
--- a/Documentation/gpu/todo.rst
+++ b/Documentation/gpu/todo.rst
@@ -206,10 +206,10 @@ Generic fbdev defio support
 ---------------------------
 
 The defio support code in the fbdev core has some very specific requirements,
-which means drivers need to have a special framebuffer for fbdev. Which prevents
-us from using the generic fbdev emulation code everywhere. The main issue is
-that it uses some fields in struct page itself, which breaks shmem gem objects
-(and other things).
+which means drivers need to have a special framebuffer for fbdev. The main
+issue is that it uses some fields in struct page itself, which breaks shmem
+gem objects (and other things). To support defio, affected drivers require
+the use of a shadow buffer, which may add CPU and memory overhead.
 
 Possible solution would be to write our own defio mmap code in the drm fbdev
 emulation. It would need to fully wrap the existing mmap ops, forwarding
diff --git a/Documentation/networking/device_drivers/intel/e100.rst b/Documentation/networking/device_drivers/intel/e100.rst
index 2b9f4887beda..caf023cc88de 100644
--- a/Documentation/networking/device_drivers/intel/e100.rst
+++ b/Documentation/networking/device_drivers/intel/e100.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==============================================================
-Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters
-==============================================================
+=============================================================
+Linux Base Driver for the Intel(R) PRO/100 Family of Adapters
+=============================================================
 
 June 1, 2018
 
@@ -21,7 +21,7 @@ Contents
 In This Release
 ===============
 
-This file describes the Linux* Base Driver for the Intel(R) PRO/100 Family of
+This file describes the Linux Base Driver for the Intel(R) PRO/100 Family of
 Adapters. This driver includes support for Itanium(R)2-based systems.
 
 For questions related to hardware requirements, refer to the documentation
@@ -138,9 +138,9 @@ 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 provided through the ethtool* utility.  For instructions on
+Enabling Wake on LAN (WoL)
+--------------------------
+WoL is provided through the ethtool utility.  For instructions on
 enabling WoL with ethtool, refer to the ethtool man page.  WoL will be
 enabled on the system during the next shut down or reboot.  For this
 driver version, in order to enable WoL, the e100 driver must be loaded
diff --git a/Documentation/networking/device_drivers/intel/e1000.rst b/Documentation/networking/device_drivers/intel/e1000.rst
index 956560b6e745..4aaae0f7d6ba 100644
--- a/Documentation/networking/device_drivers/intel/e1000.rst
+++ b/Documentation/networking/device_drivers/intel/e1000.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-===========================================================
-Linux* Base Driver for Intel(R) Ethernet Network Connection
-===========================================================
+==========================================================
+Linux Base Driver for Intel(R) Ethernet Network Connection
+==========================================================
 
 Intel Gigabit Linux driver.
 Copyright(c) 1999 - 2013 Intel Corporation.
@@ -438,10 +438,10 @@ ethtool
   The latest release of ethtool can be found from
   https://www.kernel.org/pub/software/network/ethtool/
 
-Enabling Wake on LAN* (WoL)
----------------------------
+Enabling Wake on LAN (WoL)
+--------------------------
 
-  WoL is configured through the ethtool* utility.
+  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
diff --git a/Documentation/networking/device_drivers/intel/e1000e.rst b/Documentation/networking/device_drivers/intel/e1000e.rst
index 01999f05509c..f49cd370e7bf 100644
--- a/Documentation/networking/device_drivers/intel/e1000e.rst
+++ b/Documentation/networking/device_drivers/intel/e1000e.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-======================================================
-Linux* Driver for Intel(R) Ethernet Network Connection
-======================================================
+=====================================================
+Linux Driver for Intel(R) Ethernet Network Connection
+=====================================================
 
 Intel Gigabit Linux driver.
 Copyright(c) 2008-2018 Intel Corporation.
@@ -338,7 +338,7 @@ and higher cannot be forced. Use the autonegotiation advertising setting to
 manually set devices for 1 Gbps and higher.
 
 Speed, duplex, and autonegotiation advertising are configured through the
-ethtool* utility.
+ethtool utility.
 
 Caution: Only experienced network administrators should force speed and duplex
 or change autonegotiation advertising manually. The settings at the switch must
@@ -351,9 +351,9 @@ will not attempt to auto-negotiate with its link partner since those adapters
 operate only in full duplex and only at their native speed.
 
 
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is configured through the ethtool* utility.
+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 e1000e driver must be loaded
diff --git a/Documentation/networking/device_drivers/intel/fm10k.rst b/Documentation/networking/device_drivers/intel/fm10k.rst
index ac3269e34f55..4d279e64e221 100644
--- a/Documentation/networking/device_drivers/intel/fm10k.rst
+++ b/Documentation/networking/device_drivers/intel/fm10k.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==============================================================
-Linux* Base Driver for Intel(R) Ethernet Multi-host Controller
-==============================================================
+=============================================================
+Linux Base Driver for Intel(R) Ethernet Multi-host Controller
+=============================================================
 
 August 20, 2018
 Copyright(c) 2015-2018 Intel Corporation.
@@ -120,8 +120,8 @@ rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 m|v|t|s|d|f|n|r
 Known Issues/Troubleshooting
 ============================
 
-Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS under Linux KVM
----------------------------------------------------------------------------------------
+Enabling SR-IOV in a 64-bit Microsoft Windows Server 2012/R2 guest OS under Linux KVM
+-------------------------------------------------------------------------------------
 KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM. This
 includes traditional PCIe devices, as well as SR-IOV-capable devices based on
 the Intel Ethernet Controller XL710.
diff --git a/Documentation/networking/device_drivers/intel/i40e.rst b/Documentation/networking/device_drivers/intel/i40e.rst
index 848fd388fa6e..8a9b18573688 100644
--- a/Documentation/networking/device_drivers/intel/i40e.rst
+++ b/Documentation/networking/device_drivers/intel/i40e.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==================================================================
-Linux* Base Driver for the Intel(R) Ethernet Controller 700 Series
-==================================================================
+=================================================================
+Linux Base Driver for the Intel(R) Ethernet Controller 700 Series
+=================================================================
 
 Intel 40 Gigabit Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
@@ -384,7 +384,7 @@ NOTE: You cannot set the speed for devices based on the Intel(R) Ethernet
 Network Adapter XXV710 based devices.
 
 Speed, duplex, and autonegotiation advertising are configured through the
-ethtool* utility.
+ethtool utility.
 
 Caution: Only experienced network administrators should force speed and duplex
 or change autonegotiation advertising manually. The settings at the switch must
diff --git a/Documentation/networking/device_drivers/intel/iavf.rst b/Documentation/networking/device_drivers/intel/iavf.rst
index cfc08842e32c..84ac7e75f363 100644
--- a/Documentation/networking/device_drivers/intel/iavf.rst
+++ b/Documentation/networking/device_drivers/intel/iavf.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==================================================================
-Linux* Base Driver for Intel(R) Ethernet Adaptive Virtual Function
-==================================================================
+=================================================================
+Linux Base Driver for Intel(R) Ethernet Adaptive Virtual Function
+=================================================================
 
 Intel Ethernet Adaptive Virtual Function Linux driver.
 Copyright(c) 2013-2018 Intel Corporation.
@@ -19,7 +19,7 @@ Contents
 Overview
 ========
 
-This file describes the iavf Linux* Base Driver. This driver was formerly
+This file describes the iavf Linux Base Driver. This driver was formerly
 called i40evf.
 
 The iavf driver supports the below mentioned virtual function devices and
diff --git a/Documentation/networking/device_drivers/intel/ice.rst b/Documentation/networking/device_drivers/intel/ice.rst
index c220aa2711c6..ee43ea57d443 100644
--- a/Documentation/networking/device_drivers/intel/ice.rst
+++ b/Documentation/networking/device_drivers/intel/ice.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-===================================================================
-Linux* Base Driver for the Intel(R) Ethernet Connection E800 Series
-===================================================================
+==================================================================
+Linux Base Driver for the Intel(R) Ethernet Connection E800 Series
+==================================================================
 
 Intel ice Linux driver.
 Copyright(c) 2018 Intel Corporation.
diff --git a/Documentation/networking/device_drivers/intel/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst
index fc8cfaa5dcfa..87e560fe5eaa 100644
--- a/Documentation/networking/device_drivers/intel/igb.rst
+++ b/Documentation/networking/device_drivers/intel/igb.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-===========================================================
-Linux* Base Driver for Intel(R) Ethernet Network Connection
-===========================================================
+==========================================================
+Linux Base Driver for Intel(R) Ethernet Network Connection
+==========================================================
 
 Intel Gigabit Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
@@ -129,9 +129,9 @@ version is required for this functionality. Download it at:
 https://www.kernel.org/pub/software/network/ethtool/
 
 
-Enabling Wake on LAN* (WoL)
----------------------------
-WoL is configured through the ethtool* utility.
+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 igb driver must be loaded
diff --git a/Documentation/networking/device_drivers/intel/igbvf.rst b/Documentation/networking/device_drivers/intel/igbvf.rst
index 9cddabe8108e..557fc020ef31 100644
--- a/Documentation/networking/device_drivers/intel/igbvf.rst
+++ b/Documentation/networking/device_drivers/intel/igbvf.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-============================================================
-Linux* Base Virtual Function Driver for Intel(R) 1G Ethernet
-============================================================
+===========================================================
+Linux Base Virtual Function Driver for Intel(R) 1G Ethernet
+===========================================================
 
 Intel Gigabit Virtual Function Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
diff --git a/Documentation/networking/device_drivers/intel/ixgbe.rst b/Documentation/networking/device_drivers/intel/ixgbe.rst
index c7d25483fedb..f1d5233e5e51 100644
--- a/Documentation/networking/device_drivers/intel/ixgbe.rst
+++ b/Documentation/networking/device_drivers/intel/ixgbe.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-=============================================================================
-Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters
-=============================================================================
+===========================================================================
+Linux Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters
+===========================================================================
 
 Intel 10 Gigabit Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
@@ -519,8 +519,8 @@ The offload is also supported for ixgbe's VFs, but the VF must be set as
 Known Issues/Troubleshooting
 ============================
 
-Enabling SR-IOV in a 64-bit Microsoft* Windows Server* 2012/R2 guest OS
------------------------------------------------------------------------
+Enabling SR-IOV in a 64-bit Microsoft Windows Server 2012/R2 guest OS
+---------------------------------------------------------------------
 Linux KVM Hypervisor/VMM supports direct assignment of a PCIe device to a VM.
 This includes traditional PCIe devices, as well as SR-IOV-capable devices based
 on the Intel Ethernet Controller XL710.
diff --git a/Documentation/networking/device_drivers/intel/ixgbevf.rst b/Documentation/networking/device_drivers/intel/ixgbevf.rst
index 5d4977360157..76bbde736f21 100644
--- a/Documentation/networking/device_drivers/intel/ixgbevf.rst
+++ b/Documentation/networking/device_drivers/intel/ixgbevf.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-=============================================================
-Linux* Base Virtual Function Driver for Intel(R) 10G Ethernet
-=============================================================
+============================================================
+Linux Base Virtual Function Driver for Intel(R) 10G Ethernet
+============================================================
 
 Intel 10 Gigabit Virtual Function Linux driver.
 Copyright(c) 1999-2018 Intel Corporation.
diff --git a/Documentation/networking/device_drivers/pensando/ionic.rst b/Documentation/networking/device_drivers/pensando/ionic.rst
index 13935896bee6..c17d680cf334 100644
--- a/Documentation/networking/device_drivers/pensando/ionic.rst
+++ b/Documentation/networking/device_drivers/pensando/ionic.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0+
 
-==========================================================
-Linux* Driver for the Pensando(R) Ethernet adapter family
-==========================================================
+========================================================
+Linux Driver for the Pensando(R) Ethernet adapter family
+========================================================
 
 Pensando Linux Ethernet driver.
 Copyright(c) 2019 Pensando Systems, Inc
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 49e95f438ed7..8d4ad1d1ae26 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -207,8 +207,8 @@ TCP variables:
 
 somaxconn - INTEGER
 	Limit of socket listen() backlog, known in userspace as SOMAXCONN.
-	Defaults to 128.  See also tcp_max_syn_backlog for additional tuning
-	for TCP sockets.
+	Defaults to 4096. (Was 128 before linux-5.4)
+	See also tcp_max_syn_backlog for additional tuning for TCP sockets.
 
 tcp_abort_on_overflow - BOOLEAN
 	If listening service is too slow to accept new connections,
@@ -408,11 +408,14 @@ tcp_max_orphans - INTEGER
 	up to ~64K of unswappable memory.
 
 tcp_max_syn_backlog - INTEGER
-	Maximal number of remembered connection requests, which have not
-	received an acknowledgment from connecting client.
+	Maximal number of remembered connection requests (SYN_RECV),
+	which have not received an acknowledgment from connecting client.
+	This is a per-listener limit.
 	The minimal value is 128 for low memory machines, and it will
 	increase in proportion to the memory of machine.
 	If server suffers from overload, try increasing this number.
+	Remember to also check /proc/sys/net/core/somaxconn
+	A SYN_RECV request socket consumes about 304 bytes of memory.
 
 tcp_max_tw_buckets - INTEGER
 	Maximal number of timewait sockets held by system simultaneously.
diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index 0dd3f748239f..f914e81fd3a6 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -436,6 +436,10 @@ by the driver:
    encryption.
  * ``tx_tls_ooo`` - number of TX packets which were part of a TLS stream
    but did not arrive in the expected order.
+ * ``tx_tls_skip_no_sync_data`` - number of TX packets which were part of
+   a TLS stream and arrived out-of-order, but skipped the HW offload routine
+   and went to the regular transmit flow as they were retransmissions of the
+   connection handshake.
  * ``tx_tls_drop_no_sync_data`` - number of TX packets which were part of
    a TLS stream dropped, because they arrived out of order and associated
    record could not be found.
diff --git a/MAINTAINERS b/MAINTAINERS
index b63c291ad029..71c4ca8b278f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -856,7 +856,6 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-amd-mp2*
 
 AMD POWERPLAY
-M:	Rex Zhu <rex.zhu@amd.com>
 M:	Evan Quan <evan.quan@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
@@ -2326,11 +2325,13 @@ F:	drivers/edac/altera_edac.
 
 ARM/SPREADTRUM SoC SUPPORT
 M:	Orson Zhai <orsonzhai@gmail.com>
-M:	Baolin Wang <baolin.wang@linaro.org>
+M:	Baolin Wang <baolin.wang7@gmail.com>
 M:	Chunyan Zhang <zhang.lyra@gmail.com>
 S:	Maintained
 F:	arch/arm64/boot/dts/sprd
 N:	sprd
+N:	sc27xx
+N:	sc2731
 
 ARM/STI ARCHITECTURE
 M:	Patrice Chotard <patrice.chotard@st.com>
@@ -3054,6 +3055,7 @@ M:	Daniel Borkmann <daniel@iogearbox.net>
 R:	Martin KaFai Lau <kafai@fb.com>
 R:	Song Liu <songliubraving@fb.com>
 R:	Yonghong Song <yhs@fb.com>
+R:	Andrii Nakryiko <andriin@fb.com>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git
@@ -3099,7 +3101,7 @@ S:	Supported
 F:	arch/arm64/net/
 
 BPF JIT for MIPS (32-BIT AND 64-BIT)
-M:	Paul Burton <paul.burton@mips.com>
+M:	Paul Burton <paulburton@kernel.org>
 L:	netdev@vger.kernel.org
 L:	bpf@vger.kernel.org
 S:	Maintained
@@ -3186,7 +3188,7 @@ N:	bcm216*
 N:	kona
 F:	arch/arm/mach-bcm/
 
-BROADCOM BCM2835 ARM ARCHITECTURE
+BROADCOM BCM2711/BCM2835 ARM ARCHITECTURE
 M:	Eric Anholt <eric@anholt.net>
 M:	Stefan Wahren <wahrenst@gmx.net>
 L:	bcm-kernel-feedback-list@broadcom.com
@@ -3194,6 +3196,7 @@ L:	linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://github.com/anholt/linux
 S:	Maintained
+N:	bcm2711
 N:	bcm2835
 F:	drivers/staging/vc04_services
 
@@ -3240,8 +3243,6 @@ S:	Maintained
 F:	drivers/usb/gadget/udc/bcm63xx_udc.*
 
 BROADCOM BCM7XXX ARM ARCHITECTURE
-M:	Brian Norris <computersforpeace@gmail.com>
-M:	Gregory Fong <gregory.0xf0@gmail.com>
 M:	Florian Fainelli <f.fainelli@gmail.com>
 M:	bcm-kernel-feedback-list@broadcom.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -3739,7 +3740,6 @@ F:	drivers/crypto/cavium/cpt/
 
 CAVIUM THUNDERX2 ARM64 SOC
 M:	Robert Richter <rrichter@cavium.com>
-M:	Jayachandran C <jnair@caviumnetworks.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm64/boot/dts/cavium/thunder2-99xx*
@@ -8014,7 +8014,7 @@ S:	Maintained
 F:	drivers/usb/atm/ueagle-atm.c
 
 IMGTEC ASCII LCD DRIVER
-M:	Paul Burton <paul.burton@mips.com>
+M:	Paul Burton <paulburton@kernel.org>
 S:	Maintained
 F:	Documentation/devicetree/bindings/auxdisplay/img-ascii-lcd.txt
 F:	drivers/auxdisplay/img-ascii-lcd.c
@@ -10531,8 +10531,12 @@ F:	mm/memblock.c
 F:	Documentation/core-api/boot-time-mm.rst
 
 MEMORY MANAGEMENT
+M:	Andrew Morton <akpm@linux-foundation.org>
 L:	linux-mm@kvack.org
 W:	http://www.linux-mm.org
+T:	quilt https://ozlabs.org/~akpm/mmotm/
+T:	quilt https://ozlabs.org/~akpm/mmots/
+T:	git git://github.com/hnaz/linux-mm.git
 S:	Maintained
 F:	include/linux/mm.h
 F:	include/linux/gfp.h
@@ -10841,7 +10845,7 @@ F:	drivers/usb/image/microtek.*
 
 MIPS
 M:	Ralf Baechle <ralf@linux-mips.org>
-M:	Paul Burton <paul.burton@mips.com>
+M:	Paul Burton <paulburton@kernel.org>
 M:	James Hogan <jhogan@kernel.org>
 L:	linux-mips@vger.kernel.org
 W:	http://www.linux-mips.org/
@@ -10855,7 +10859,7 @@ F:	arch/mips/
 F:	drivers/platform/mips/
 
 MIPS BOSTON DEVELOPMENT BOARD
-M:	Paul Burton <paul.burton@mips.com>
+M:	Paul Burton <paulburton@kernel.org>
 L:	linux-mips@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/clock/img,boston-clock.txt
@@ -10865,7 +10869,7 @@ F:	drivers/clk/imgtec/clk-boston.c
 F:	include/dt-bindings/clock/boston-clock.h
 
 MIPS GENERIC PLATFORM
-M:	Paul Burton <paul.burton@mips.com>
+M:	Paul Burton <paulburton@kernel.org>
 L:	linux-mips@vger.kernel.org
 S:	Supported
 F:	Documentation/devicetree/bindings/power/mti,mips-cpc.txt
@@ -11420,7 +11424,6 @@ F:	include/trace/events/tcp.h
 NETWORKING [TLS]
 M:	Boris Pismenny <borisp@mellanox.com>
 M:	Aviad Yehezkel <aviadye@mellanox.com>
-M:	Dave Watson <davejwatson@fb.com>
 M:	John Fastabend <john.fastabend@gmail.com>
 M:	Daniel Borkmann <daniel@iogearbox.net>
 M:	Jakub Kicinski <jakub.kicinski@netronome.com>
@@ -13918,7 +13921,7 @@ F:	drivers/mtd/nand/raw/r852.h
 
 RISC-V ARCHITECTURE
 M:	Paul Walmsley <paul.walmsley@sifive.com>
-M:	Palmer Dabbelt <palmer@sifive.com>
+M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Albert Ou <aou@eecs.berkeley.edu>
 L:	linux-riscv@lists.infradead.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git
@@ -14795,7 +14798,7 @@ F:	drivers/media/usb/siano/
 F:	drivers/media/mmc/siano/
 
 SIFIVE DRIVERS
-M:	Palmer Dabbelt <palmer@sifive.com>
+M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 L:	linux-riscv@lists.infradead.org
 T:	git git://github.com/sifive/riscv-linux.git
@@ -14805,7 +14808,7 @@ N:	sifive
 
 SIFIVE FU540 SYSTEM-ON-CHIP
 M:	Paul Walmsley <paul.walmsley@sifive.com>
-M:	Palmer Dabbelt <palmer@sifive.com>
+M:	Palmer Dabbelt <palmer@dabbelt.com>
 L:	linux-riscv@lists.infradead.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/pjw/sifive.git
 S:	Supported
@@ -17347,6 +17350,12 @@ F:	include/linux/vbox_utils.h
 F:	include/uapi/linux/vbox*.h
 F:	drivers/virt/vboxguest/
 
+VIRTUAL BOX SHARED FOLDER VFS DRIVER:
+M:	Hans de Goede <hdegoede@redhat.com>
+L:	linux-fsdevel@vger.kernel.org
+S:	Maintained
+F:	drivers/staging/vboxsf/*
+
 VIRTUAL SERIO DEVICE DRIVER
 M:	Stephen Chandler Paul <thatslyude@gmail.com>
 S:	Maintained
@@ -18047,6 +18056,7 @@ F:	Documentation/vm/zsmalloc.rst
 ZSWAP COMPRESSED SWAP CACHING
 M:	Seth Jennings <sjenning@redhat.com>
 M:	Dan Streetman <ddstreet@ieee.org>
+M:	Vitaly Wool <vitaly.wool@konsulko.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/zswap.c
diff --git a/Makefile b/Makefile
index 5475cdb6d57d..1d5298356ea8 100644
--- a/Makefile
+++ b/Makefile
@@ -2,8 +2,8 @@
 VERSION = 5
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
-NAME = Nesting Opossum
+EXTRAVERSION = -rc7
+NAME = Kleptomaniac Octopus
 
 # *DOCUMENTATION*
 # To see a list of typical targets execute "make help"
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index bfc7f5f5d6f2..9acbeba832c0 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -65,6 +65,14 @@
 		clock-frequency = <33333333>;
 	};
 
+	reg_5v0: regulator-5v0 {
+		compatible = "regulator-fixed";
+
+		regulator-name = "5v0-supply";
+		regulator-min-microvolt = <5000000>;
+		regulator-max-microvolt = <5000000>;
+	};
+
 	cpu_intc: cpu-interrupt-controller {
 		compatible = "snps,archs-intc";
 		interrupt-controller;
@@ -264,6 +272,21 @@
 			clocks = <&input_clk>;
 			cs-gpios = <&creg_gpio 0 GPIO_ACTIVE_LOW>,
 				   <&creg_gpio 1 GPIO_ACTIVE_LOW>;
+
+			spi-flash@0 {
+				compatible = "sst26wf016b", "jedec,spi-nor";
+				reg = <0>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+				spi-max-frequency = <4000000>;
+			};
+
+			adc@1 {
+				compatible = "ti,adc108s102";
+				reg = <1>;
+				vref-supply = <&reg_5v0>;
+				spi-max-frequency = <1000000>;
+			};
 		};
 
 		creg_gpio: gpio@14b0 {
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 9b9a74444ce2..0974226fab55 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -32,6 +32,8 @@ CONFIG_INET=y
 CONFIG_DEVTMPFS=y
 # CONFIG_STANDALONE is not set
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
+CONFIG_MTD=y
+CONFIG_MTD_SPI_NOR=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_NETDEVICES=y
@@ -55,6 +57,8 @@ CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_DWAPB=y
 CONFIG_GPIO_SNPS_CREG=y
 # CONFIG_HWMON is not set
+CONFIG_REGULATOR=y
+CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_DRM=y
 # CONFIG_DRM_FBDEV_EMULATION is not set
 CONFIG_DRM_UDL=y
@@ -72,6 +76,8 @@ CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 CONFIG_DMADEVICES=y
 CONFIG_DW_AXI_DMAC=y
+CONFIG_IIO=y
+CONFIG_TI_ADC108S102=y
 CONFIG_EXT3_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 861a8aea51f9..661fd842ea97 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -614,8 +614,8 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	/* loop thru all available h/w condition indexes */
 	for (i = 0; i < cc_bcr.c; i++) {
 		write_aux_reg(ARC_REG_CC_INDEX, i);
-		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
-		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
+		cc_name.indiv.word0 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME0));
+		cc_name.indiv.word1 = le32_to_cpu(read_aux_reg(ARC_REG_CC_NAME1));
 
 		arc_pmu_map_hw_event(i, cc_name.str);
 		arc_pmu_add_raw_event_attr(i, cc_name.str);
diff --git a/arch/arm/boot/dts/am3874-iceboard.dts b/arch/arm/boot/dts/am3874-iceboard.dts
index 883fb85135d4..1b4b2b0500e4 100644
--- a/arch/arm/boot/dts/am3874-iceboard.dts
+++ b/arch/arm/boot/dts/am3874-iceboard.dts
@@ -111,13 +111,13 @@
 		reg = <0x70>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		i2c-mux-idle-disconnect;
 
 		i2c@0 {
 			/* FMC A */
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <0>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@1 {
@@ -125,7 +125,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <1>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@2 {
@@ -133,7 +132,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <2>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@3 {
@@ -141,7 +139,6 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <3>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@4 {
@@ -149,14 +146,12 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <4>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@5 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <5>;
-			i2c-mux-idle-disconnect;
 
 			ina230@40 { compatible = "ti,ina230"; reg = <0x40>; shunt-resistor = <5000>; };
 			ina230@41 { compatible = "ti,ina230"; reg = <0x41>; shunt-resistor = <5000>; };
@@ -182,14 +177,12 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <6>;
-			i2c-mux-idle-disconnect;
 		};
 
 		i2c@7 {
 			#address-cells = <1>;
 			#size-cells = <0>;
 			reg = <7>;
-			i2c-mux-idle-disconnect;
 
 			u41: pca9575@20 {
 				compatible = "nxp,pca9575";
diff --git a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
index 09a088f98566..b75af21069f9 100644
--- a/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
+++ b/arch/arm/boot/dts/bcm2835-rpi-zero-w.dts
@@ -113,6 +113,7 @@
 	#address-cells = <1>;
 	#size-cells = <0>;
 	pinctrl-0 = <&emmc_gpio34 &gpclk2_gpio43>;
+	bus-width = <4>;
 	mmc-pwrseq = <&wifi_pwrseq>;
 	non-removable;
 	status = "okay";
diff --git a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi
index 7c3cb7ece6cb..925cb37c22f0 100644
--- a/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi
+++ b/arch/arm/boot/dts/bcm2837-rpi-cm3.dtsi
@@ -9,6 +9,14 @@
 		reg = <0 0x40000000>;
 	};
 
+	leds {
+		/*
+		 * Since there is no upstream GPIO driver yet,
+		 * remove the incomplete node.
+		 */
+		/delete-node/ act;
+	};
+
 	reg_3v3: fixed-regulator {
 		compatible = "regulator-fixed";
 		regulator-name = "3V3";
diff --git a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi
index 2a6ce87071f9..9e027b9a5f91 100644
--- a/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi
+++ b/arch/arm/boot/dts/imx6-logicpd-baseboard.dtsi
@@ -328,6 +328,10 @@
 	pinctrl-0 = <&pinctrl_pwm3>;
 };
 
+&snvs_pwrkey {
+	status = "okay";
+};
+
 &ssi2 {
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6-logicpd-som.dtsi b/arch/arm/boot/dts/imx6-logicpd-som.dtsi
index 7ceae3573248..547fb141ec0c 100644
--- a/arch/arm/boot/dts/imx6-logicpd-som.dtsi
+++ b/arch/arm/boot/dts/imx6-logicpd-som.dtsi
@@ -207,6 +207,10 @@
 	vin-supply = <&sw1c_reg>;
 };
 
+&snvs_poweroff {
+	status = "okay";
+};
+
 &iomuxc {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_hog>;
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index f3404dd10537..cf628465cd0a 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -230,6 +230,8 @@
 			accelerometer@1c {
 				compatible = "fsl,mma8451";
 				reg = <0x1c>;
+				pinctrl-names = "default";
+				pinctrl-0 = <&pinctrl_mma8451_int>;
 				interrupt-parent = <&gpio6>;
 				interrupts = <31 IRQ_TYPE_LEVEL_LOW>;
 			};
@@ -628,6 +630,12 @@
 			>;
 		};
 
+		pinctrl_mma8451_int: mma8451intgrp {
+			fsl,pins = <
+				MX6QDL_PAD_EIM_BCLK__GPIO6_IO31		0xb0b1
+			>;
+		};
+
 		pinctrl_pwm3: pwm1grp {
 			fsl,pins = <
 				MX6QDL_PAD_SD4_DAT1__PWM3_OUT		0x1b0b1
diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi
index 710f850e785c..e2e604d6ba0b 100644
--- a/arch/arm/boot/dts/imx7s.dtsi
+++ b/arch/arm/boot/dts/imx7s.dtsi
@@ -448,7 +448,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302d0000 0x10000>;
 				interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT1_ROOT_CLK>,
 					 <&clks IMX7D_GPT1_ROOT_CLK>;
 				clock-names = "ipg", "per";
 			};
@@ -457,7 +457,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302e0000 0x10000>;
 				interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT2_ROOT_CLK>,
 					 <&clks IMX7D_GPT2_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
@@ -467,7 +467,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x302f0000 0x10000>;
 				interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT3_ROOT_CLK>,
 					 <&clks IMX7D_GPT3_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
@@ -477,7 +477,7 @@
 				compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt";
 				reg = <0x30300000 0x10000>;
 				interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks IMX7D_CLK_DUMMY>,
+				clocks = <&clks IMX7D_GPT4_ROOT_CLK>,
 					 <&clks IMX7D_GPT4_ROOT_CLK>;
 				clock-names = "ipg", "per";
 				status = "disabled";
diff --git a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
index 3fdd0a72f87f..506b118e511a 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-som.dtsi
@@ -192,3 +192,7 @@
 &twl_gpio {
 	ti,use-leds;
 };
+
+&twl_keypad {
+	status = "disabled";
+};
diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts
index 4454449de00c..a40fe8d49da6 100644
--- a/arch/arm/boot/dts/omap4-droid4-xt894.dts
+++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts
@@ -369,7 +369,7 @@
 		compatible = "ti,wl1285", "ti,wl1283";
 		reg = <2>;
 		/* gpio_100 with gpmc_wait2 pad as wakeirq */
-		interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>,
+		interrupts-extended = <&gpio4 4 IRQ_TYPE_LEVEL_HIGH>,
 				      <&omap4_pmx_core 0x4e>;
 		interrupt-names = "irq", "wakeup";
 		ref-clock-frequency = <26000000>;
diff --git a/arch/arm/boot/dts/omap4-panda-common.dtsi b/arch/arm/boot/dts/omap4-panda-common.dtsi
index 14be2ecb62b1..55ea8b6189af 100644
--- a/arch/arm/boot/dts/omap4-panda-common.dtsi
+++ b/arch/arm/boot/dts/omap4-panda-common.dtsi
@@ -474,7 +474,7 @@
 		compatible = "ti,wl1271";
 		reg = <2>;
 		/* gpio_53 with gpmc_ncs3 pad as wakeup */
-		interrupts-extended = <&gpio2 21 IRQ_TYPE_EDGE_RISING>,
+		interrupts-extended = <&gpio2 21 IRQ_TYPE_LEVEL_HIGH>,
 				      <&omap4_pmx_core 0x3a>;
 		interrupt-names = "irq", "wakeup";
 		ref-clock-frequency = <38400000>;
diff --git a/arch/arm/boot/dts/omap4-sdp.dts b/arch/arm/boot/dts/omap4-sdp.dts
index 3c274965ff40..91480ac1f328 100644
--- a/arch/arm/boot/dts/omap4-sdp.dts
+++ b/arch/arm/boot/dts/omap4-sdp.dts
@@ -512,7 +512,7 @@
 		compatible = "ti,wl1281";
 		reg = <2>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <21 IRQ_TYPE_EDGE_RISING>; /* gpio 53 */
+		interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; /* gpio 53 */
 		ref-clock-frequency = <26000000>;
 		tcxo-clock-frequency = <26000000>;
 	};
diff --git a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi
index 6dbbc9b3229c..d0032213101e 100644
--- a/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi
+++ b/arch/arm/boot/dts/omap4-var-som-om44-wlan.dtsi
@@ -69,7 +69,7 @@
 		compatible = "ti,wl1271";
 		reg = <2>;
 		interrupt-parent = <&gpio2>;
-		interrupts = <9 IRQ_TYPE_EDGE_RISING>; /* gpio 41 */
+		interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; /* gpio 41 */
 		ref-clock-frequency = <38400000>;
 	};
 };
diff --git a/arch/arm/boot/dts/omap5-board-common.dtsi b/arch/arm/boot/dts/omap5-board-common.dtsi
index 7fff555ee394..68ac04641bdb 100644
--- a/arch/arm/boot/dts/omap5-board-common.dtsi
+++ b/arch/arm/boot/dts/omap5-board-common.dtsi
@@ -362,7 +362,7 @@
 		pinctrl-names = "default";
 		pinctrl-0 = <&wlcore_irq_pin>;
 		interrupt-parent = <&gpio1>;
-		interrupts = <14 IRQ_TYPE_EDGE_RISING>;	/* gpio 14 */
+		interrupts = <14 IRQ_TYPE_LEVEL_HIGH>;	/* gpio 14 */
 		ref-clock-frequency = <26000000>;
 	};
 };
diff --git a/arch/arm/boot/dts/omap54xx-clocks.dtsi b/arch/arm/boot/dts/omap54xx-clocks.dtsi
index fac2e57dcca9..4791834dacb2 100644
--- a/arch/arm/boot/dts/omap54xx-clocks.dtsi
+++ b/arch/arm/boot/dts/omap54xx-clocks.dtsi
@@ -1146,7 +1146,7 @@
 		};
 	};
 
-	gpu_cm: clock-controller@1500 {
+	gpu_cm: gpu_cm@1500 {
 		compatible = "ti,omap4-cm";
 		reg = <0x1500 0x100>;
 		#address-cells = <1>;
diff --git a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
index e4a0d51ec3a8..0a3a7d66737b 100644
--- a/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stm32mp157-pinctrl.dtsi
@@ -609,13 +609,13 @@
 						 <STM32_PINMUX('F', 6, AF9)>; /* QSPI_BK1_IO3 */
 					bias-disable;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 				pins2 {
 					pinmux = <STM32_PINMUX('B', 6, AF10)>; /* QSPI_BK1_NCS */
 					bias-pull-up;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 			};
 
@@ -637,13 +637,13 @@
 						 <STM32_PINMUX('G', 7, AF11)>; /* QSPI_BK2_IO3 */
 					bias-disable;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 				pins2 {
 					pinmux = <STM32_PINMUX('C', 0, AF10)>; /* QSPI_BK2_NCS */
 					bias-pull-up;
 					drive-push-pull;
-					slew-rate = <3>;
+					slew-rate = <1>;
 				};
 			};
 
diff --git a/arch/arm/boot/dts/stm32mp157c-ev1.dts b/arch/arm/boot/dts/stm32mp157c-ev1.dts
index 89d29b50c3f4..91fc0a315c49 100644
--- a/arch/arm/boot/dts/stm32mp157c-ev1.dts
+++ b/arch/arm/boot/dts/stm32mp157c-ev1.dts
@@ -183,14 +183,12 @@
 
 	ov5640: camera@3c {
 		compatible = "ovti,ov5640";
-		pinctrl-names = "default";
-		pinctrl-0 = <&ov5640_pins>;
 		reg = <0x3c>;
 		clocks = <&clk_ext_camera>;
 		clock-names = "xclk";
 		DOVDD-supply = <&v2v8>;
-		powerdown-gpios = <&stmfx_pinctrl 18 GPIO_ACTIVE_HIGH>;
-		reset-gpios = <&stmfx_pinctrl 19 GPIO_ACTIVE_LOW>;
+		powerdown-gpios = <&stmfx_pinctrl 18 (GPIO_ACTIVE_HIGH | GPIO_PUSH_PULL)>;
+		reset-gpios = <&stmfx_pinctrl 19 (GPIO_ACTIVE_LOW | GPIO_PUSH_PULL)>;
 		rotation = <180>;
 		status = "okay";
 
@@ -223,15 +221,8 @@
 
 			joystick_pins: joystick {
 				pins = "gpio0", "gpio1", "gpio2", "gpio3", "gpio4";
-				drive-push-pull;
 				bias-pull-down;
 			};
-
-			ov5640_pins: camera {
-				pins = "agpio2", "agpio3"; /* stmfx pins 18 & 19 */
-				drive-push-pull;
-				output-low;
-			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 9b11654a0a39..f98e0370c0bc 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -932,7 +932,7 @@
 			interrupt-names = "int0", "int1";
 			clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>;
 			clock-names = "hclk", "cclk";
-			bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>;
+			bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>;
 			status = "disabled";
 		};
 
@@ -945,7 +945,7 @@
 			interrupt-names = "int0", "int1";
 			clocks = <&rcc CK_HSE>, <&rcc FDCAN_K>;
 			clock-names = "hclk", "cclk";
-			bosch,mram-cfg = <0x0 0 0 32 0 0 2 2>;
+			bosch,mram-cfg = <0x1400 0 0 32 0 0 2 2>;
 			status = "disabled";
 		};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 874231be04e4..8aebefd6accf 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -380,9 +380,8 @@
 			compatible = "allwinner,sun7i-a20-csi0";
 			reg = <0x01c09000 0x1000>;
 			interrupts = <GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI0>,
-				 <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
-			clock-names = "bus", "mod", "isp", "ram";
+			clocks = <&ccu CLK_AHB_CSI0>, <&ccu CLK_CSI_SCLK>, <&ccu CLK_DRAM_CSI0>;
+			clock-names = "bus", "isp", "ram";
 			resets = <&ccu RST_CSI0>;
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
index 568b90ece342..3bec3e0a81b2 100644
--- a/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
+++ b/arch/arm/boot/dts/sun8i-a83t-tbs-a711.dts
@@ -192,6 +192,7 @@
 	vqmmc-supply = <&reg_dldo1>;
 	non-removable;
 	wakeup-source;
+	keep-power-in-suspend;
 	status = "okay";
 
 	brcmf: wifi@1 {
diff --git a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts
index dc8a5f37a1ef..c8ebb23c4e02 100644
--- a/arch/arm/boot/dts/vf610-zii-scu4-aib.dts
+++ b/arch/arm/boot/dts/vf610-zii-scu4-aib.dts
@@ -602,6 +602,7 @@
 		#address-cells = <1>;
 		#size-cells = <0>;
 		reg = <0x70>;
+		i2c-mux-idle-disconnect;
 
 		sff0_i2c: i2c@1 {
 			#address-cells = <1>;
@@ -640,6 +641,7 @@
 		reg = <0x71>;
 		#address-cells = <1>;
 		#size-cells = <0>;
+		i2c-mux-idle-disconnect;
 
 		sff5_i2c: i2c@1 {
 			#address-cells = <1>;
diff --git a/arch/arm/configs/davinci_all_defconfig b/arch/arm/configs/davinci_all_defconfig
index 01e3c0f4be92..231f8973bbb2 100644
--- a/arch/arm/configs/davinci_all_defconfig
+++ b/arch/arm/configs/davinci_all_defconfig
@@ -167,6 +167,7 @@ CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_DA8XX=y
 CONFIG_BACKLIGHT_PWM=m
+CONFIG_BACKLIGHT_GPIO=m
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig
index 9bfffbe22d53..0f7381ee0c37 100644
--- a/arch/arm/configs/imx_v6_v7_defconfig
+++ b/arch/arm/configs/imx_v6_v7_defconfig
@@ -276,6 +276,7 @@ CONFIG_VIDEO_OV5640=m
 CONFIG_VIDEO_OV5645=m
 CONFIG_IMX_IPUV3_CORE=y
 CONFIG_DRM=y
+CONFIG_DRM_MSM=y
 CONFIG_DRM_PANEL_LVDS=y
 CONFIG_DRM_PANEL_SIMPLE=y
 CONFIG_DRM_PANEL_SEIKO_43WVF1G=y
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index d3f50971e451..40d7f1a4fc45 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -356,15 +356,15 @@ CONFIG_DRM_OMAP_CONNECTOR_HDMI=m
 CONFIG_DRM_OMAP_CONNECTOR_ANALOG_TV=m
 CONFIG_DRM_OMAP_PANEL_DPI=m
 CONFIG_DRM_OMAP_PANEL_DSI_CM=m
-CONFIG_DRM_OMAP_PANEL_SONY_ACX565AKM=m
-CONFIG_DRM_OMAP_PANEL_LGPHILIPS_LB035Q02=m
-CONFIG_DRM_OMAP_PANEL_SHARP_LS037V7DW01=m
-CONFIG_DRM_OMAP_PANEL_TPO_TD028TTEC1=m
-CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m
-CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m
 CONFIG_DRM_TILCDC=m
 CONFIG_DRM_PANEL_SIMPLE=m
 CONFIG_DRM_TI_TFP410=m
+CONFIG_DRM_PANEL_LG_LB035Q02=m
+CONFIG_DRM_PANEL_NEC_NL8048HL11=m
+CONFIG_DRM_PANEL_SHARP_LS037V7DW01=m
+CONFIG_DRM_PANEL_SONY_ACX565AKM=m
+CONFIG_DRM_PANEL_TPO_TD028TTEC1=m
+CONFIG_DRM_PANEL_TPO_TD043MTEA1=m
 CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index 567dbede4785..f1d0a7807cd0 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -82,7 +82,7 @@
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_CPU_CP15_MMU
-static inline unsigned int get_domain(void)
+static __always_inline unsigned int get_domain(void)
 {
 	unsigned int domain;
 
@@ -94,7 +94,7 @@ static inline unsigned int get_domain(void)
 	return domain;
 }
 
-static inline void set_domain(unsigned val)
+static __always_inline void set_domain(unsigned int val)
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
@@ -102,12 +102,12 @@ static inline void set_domain(unsigned val)
 	isb();
 }
 #else
-static inline unsigned int get_domain(void)
+static __always_inline unsigned int get_domain(void)
 {
 	return 0;
 }
 
-static inline void set_domain(unsigned val)
+static __always_inline void set_domain(unsigned int val)
 {
 }
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 303248e5b990..98c6b91be4a8 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -22,7 +22,7 @@
  * perform such accesses (eg, via list poison values) which could then
  * be exploited for priviledge escalation.
  */
-static inline unsigned int uaccess_save_and_enable(void)
+static __always_inline unsigned int uaccess_save_and_enable(void)
 {
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	unsigned int old_domain = get_domain();
@@ -37,7 +37,7 @@ static inline unsigned int uaccess_save_and_enable(void)
 #endif
 }
 
-static inline void uaccess_restore(unsigned int flags)
+static __always_inline void uaccess_restore(unsigned int flags)
 {
 #ifdef CONFIG_CPU_SW_DOMAIN_PAN
 	/* Restore the user access mask */
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index a7810be07da1..4a3982812a40 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -68,7 +68,7 @@ ENDPROC(__vet_atags)
  * The following fragment of code is executed with the MMU on in MMU mode,
  * and uses absolute addresses; this is not position independent.
  *
- *  r0  = cp#15 control register
+ *  r0  = cp#15 control register (exc_ret for M-class)
  *  r1  = machine ID
  *  r2  = atags/dtb pointer
  *  r9  = processor ID
@@ -137,7 +137,8 @@ __mmap_switched_data:
 #ifdef CONFIG_CPU_CP15
 	.long	cr_alignment			@ r3
 #else
-	.long	0				@ r3
+M_CLASS(.long	exc_ret)			@ r3
+AR_CLASS(.long	0)				@ r3
 #endif
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index afa350f44dea..0fc814bbc34b 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -201,6 +201,8 @@ M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
 	bic	r0, r0, #V7M_SCB_CCR_IC
 #endif
 	str	r0, [r12, V7M_SCB_CCR]
+	/* Pass exc_ret to __mmap_switched */
+	mov	r0, r10
 #endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */
 	ret	lr
 ENDPROC(__after_proc_init)
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 8062412be70f..9fc5c73cc0be 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -462,8 +462,8 @@ static s8 dm365_queue_priority_mapping[][2] = {
 };
 
 static const struct dma_slave_map dm365_edma_map[] = {
-	{ "davinci-mcbsp.0", "tx", EDMA_FILTER_PARAM(0, 2) },
-	{ "davinci-mcbsp.0", "rx", EDMA_FILTER_PARAM(0, 3) },
+	{ "davinci-mcbsp", "tx", EDMA_FILTER_PARAM(0, 2) },
+	{ "davinci-mcbsp", "rx", EDMA_FILTER_PARAM(0, 3) },
 	{ "davinci_voicecodec", "tx", EDMA_FILTER_PARAM(0, 2) },
 	{ "davinci_voicecodec", "rx", EDMA_FILTER_PARAM(0, 3) },
 	{ "spi_davinci.2", "tx", EDMA_FILTER_PARAM(0, 10) },
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index d942a3357090..2efd18e8824c 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -89,6 +89,13 @@ static struct iommu_platform_data omap3_iommu_pdata = {
 	.reset_name = "mmu",
 	.assert_reset = omap_device_assert_hardreset,
 	.deassert_reset = omap_device_deassert_hardreset,
+	.device_enable = omap_device_enable,
+	.device_idle = omap_device_idle,
+};
+
+static struct iommu_platform_data omap3_iommu_isp_pdata = {
+	.device_enable = omap_device_enable,
+	.device_idle = omap_device_idle,
 };
 
 static int omap3_sbc_t3730_twl_callback(struct device *dev,
@@ -424,6 +431,8 @@ static struct iommu_platform_data omap4_iommu_pdata = {
 	.reset_name = "mmu_cache",
 	.assert_reset = omap_device_assert_hardreset,
 	.deassert_reset = omap_device_deassert_hardreset,
+	.device_enable = omap_device_enable,
+	.device_idle = omap_device_idle,
 };
 #endif
 
@@ -617,6 +626,8 @@ static struct of_dev_auxdata omap_auxdata_lookup[] = {
 #ifdef CONFIG_ARCH_OMAP3
 	OF_DEV_AUXDATA("ti,omap2-iommu", 0x5d000000, "5d000000.mmu",
 		       &omap3_iommu_pdata),
+	OF_DEV_AUXDATA("ti,omap2-iommu", 0x480bd400, "480bd400.mmu",
+		       &omap3_iommu_isp_pdata),
 	OF_DEV_AUXDATA("ti,omap3-smartreflex-core", 0x480cb000,
 		       "480cb000.smartreflex", &omap_sr_pdata[OMAP_SR_CORE]),
 	OF_DEV_AUXDATA("ti,omap3-smartreflex-mpu-iva", 0x480c9000,
diff --git a/arch/arm/mach-sunxi/mc_smp.c b/arch/arm/mach-sunxi/mc_smp.c
index 239084cf8192..26cbce135338 100644
--- a/arch/arm/mach-sunxi/mc_smp.c
+++ b/arch/arm/mach-sunxi/mc_smp.c
@@ -481,14 +481,18 @@ static void sunxi_mc_smp_cpu_die(unsigned int l_cpu)
 static int sunxi_cpu_powerdown(unsigned int cpu, unsigned int cluster)
 {
 	u32 reg;
+	int gating_bit = cpu;
 
 	pr_debug("%s: cluster %u cpu %u\n", __func__, cluster, cpu);
 	if (cpu >= SUNXI_CPUS_PER_CLUSTER || cluster >= SUNXI_NR_CLUSTERS)
 		return -EINVAL;
 
+	if (is_a83t && cpu == 0)
+		gating_bit = 4;
+
 	/* gate processor power */
 	reg = readl(prcm_base + PRCM_PWROFF_GATING_REG(cluster));
-	reg |= PRCM_PWROFF_GATING_REG_CORE(cpu);
+	reg |= PRCM_PWROFF_GATING_REG_CORE(gating_bit);
 	writel(reg, prcm_base + PRCM_PWROFF_GATING_REG(cluster));
 	udelay(20);
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 04b36436cbc0..788c5cf46de5 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -324,7 +324,7 @@ union offset_union {
 	__put32_unaligned_check("strbt", val, addr)
 
 static void
-do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset)
+do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset)
 {
 	if (!LDST_U_BIT(instr))
 		offset.un = -offset.un;
@@ -337,7 +337,7 @@ do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs
 }
 
 static int
-do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -386,8 +386,7 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r
 }
 
 static int
-do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
-		      struct pt_regs *regs)
+do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 	unsigned int rd2;
@@ -449,7 +448,7 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
 }
 
 static int
-do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -498,7 +497,7 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg
  * PU = 10             A                    B
  */
 static int
-do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd, rn, correction, nr_regs, regbits;
 	unsigned long eaddr, newaddr;
@@ -539,7 +538,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 	 * processor for us.
 	 */
 	if (addr != eaddr) {
-		pr_err("LDMSTM: PC = %08lx, instr = %08lx, "
+		pr_err("LDMSTM: PC = %08lx, instr = %08x, "
 			"addr = %08lx, eaddr = %08lx\n",
 			 instruction_pointer(regs), instr, addr, eaddr);
 		show_regs(regs);
@@ -716,10 +715,10 @@ thumb2arm(u16 tinstr)
  * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt)
  */
 static void *
-do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
+do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
 			    union offset_union *poffset)
 {
-	unsigned long instr = *pinstr;
+	u32 instr = *pinstr;
 	u16 tinst1 = (instr >> 16) & 0xffff;
 	u16 tinst2 = instr & 0xffff;
 
@@ -767,17 +766,48 @@ do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
 	return NULL;
 }
 
+static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
+{
+	u32 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_arm(instr);
+
+	return fault;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
+{
+	u16 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_thumb16(instr);
+
+	return fault;
+}
+
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	union offset_union uninitialized_var(offset);
-	unsigned long instr = 0, instrptr;
-	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
+	unsigned long instrptr;
+	int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
 	unsigned int type;
-	unsigned int fault;
+	u32 instr = 0;
 	u16 tinstr = 0;
 	int isize = 4;
 	int thumb2_32b = 0;
+	int fault;
 
 	if (interrupts_enabled(regs))
 		local_irq_enable();
@@ -786,15 +816,14 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
-		fault = probe_kernel_address(ptr, tinstr);
-		tinstr = __mem_to_opcode_thumb16(tinstr);
+
+		fault = alignment_get_thumb(regs, ptr, &tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
-				u16 tinst2 = 0;
-				fault = probe_kernel_address(ptr + 1, tinst2);
-				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				u16 tinst2;
+				fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
 				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
@@ -803,8 +832,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 			}
 		}
 	} else {
-		fault = probe_kernel_address((void *)instrptr, instr);
-		instr = __mem_to_opcode_arm(instr);
+		fault = alignment_get_arm(regs, (void *)instrptr, &instr);
 	}
 
 	if (fault) {
@@ -926,7 +954,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	 * Oops, we didn't handle the instruction.
 	 */
 	pr_err("Alignment trap: not handling instruction "
-		"%0*lx at [<%08lx>]\n",
+		"%0*x at [<%08lx>]\n",
 		isize << 1,
 		isize == 2 ? tinstr : instr, instrptr);
 	ai_skipped += 1;
@@ -936,7 +964,7 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	ai_user += 1;
 
 	if (ai_usermode & UM_WARN)
-		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
+		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x "
 		       "Address=0x%08lx FSR 0x%03x\n", current->comm,
 			task_pid_nr(current), instrptr,
 			isize << 1,
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 1448f144e7fb..1a49d503eafc 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -132,13 +132,11 @@ __v7m_setup_cont:
 	dsb
 	mov	r6, lr			@ save LR
 	ldr	sp, =init_thread_union + THREAD_START_SP
-	stmia	sp, {r0-r3, r12}
 	cpsie	i
 	svc	#0
 1:	cpsid	i
-	ldr	r0, =exc_ret
-	orr	lr, lr, #EXC_RET_THREADMODE_PROCESSSTACK
-	str	lr, [r0]
+	/* Calculate exc_ret */
+	orr	r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK
 	ldmia	sp, {r0-r3, r12}
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
index 24f1aac366d6..d5b6e8159a33 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-pine64-plus.dts
@@ -63,3 +63,12 @@
 		reg = <1>;
 	};
 };
+
+&reg_dc1sw {
+	/*
+	 * Ethernet PHY needs 30ms to properly power up and some more
+	 * to initialize. 100ms should be plenty of time to finish
+	 * whole process.
+	 */
+	regulator-enable-ramp-delay = <100000>;
+};
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
index e6fb9683f213..25099202c52c 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-sopine-baseboard.dts
@@ -159,6 +159,12 @@
 };
 
 &reg_dc1sw {
+	/*
+	 * Ethernet PHY needs 30ms to properly power up and some more
+	 * to initialize. 100ms should be plenty of time to finish
+	 * whole process.
+	 */
+	regulator-enable-ramp-delay = <100000>;
 	regulator-name = "vcc-phy";
 };
 
diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
index 3eccbdba7154..70f4cce6be43 100644
--- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
+++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi
@@ -142,15 +142,6 @@
 		clock-output-names = "ext-osc32k";
 	};
 
-	pmu {
-		compatible = "arm,cortex-a53-pmu";
-		interrupts = <GIC_SPI 152 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 153 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 154 IRQ_TYPE_LEVEL_HIGH>,
-			     <GIC_SPI 155 IRQ_TYPE_LEVEL_HIGH>;
-		interrupt-affinity = <&cpu0>, <&cpu1>, <&cpu2>, <&cpu3>;
-	};
-
 	psci {
 		compatible = "arm,psci-0.2";
 		method = "smc";
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
index 8a3a770e8f2c..56789ccf9454 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-pinctrl.dtsi
@@ -42,13 +42,14 @@
 
 		pinmux: pinmux@14029c {
 			compatible = "pinctrl-single";
-			reg = <0x0014029c 0x250>;
+			reg = <0x0014029c 0x26c>;
 			#address-cells = <1>;
 			#size-cells = <1>;
 			pinctrl-single,register-width = <32>;
 			pinctrl-single,function-mask = <0xf>;
 			pinctrl-single,gpio-range = <
-				&range 0 154 MODE_GPIO
+				&range 0  91 MODE_GPIO
+				&range 95 60 MODE_GPIO
 				>;
 			range: gpio-range {
 				#pinctrl-single,gpio-range-cells = <3>;
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index 71e2e34400d4..0098dfdef96c 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -464,8 +464,7 @@
 					<&pinmux 108 16 27>,
 					<&pinmux 135 77 6>,
 					<&pinmux 141 67 4>,
-					<&pinmux 145 149 6>,
-					<&pinmux 151 91 4>;
+					<&pinmux 145 149 6>;
 		};
 
 		i2c1: i2c@e0000 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts
index d98346da01df..078a5010228c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-qds.dts
@@ -127,7 +127,7 @@
 	status = "okay";
 
 	i2c-mux@77 {
-		compatible = "nxp,pca9847";
+		compatible = "nxp,pca9547";
 		reg = <0x77>;
 		#address-cells = <1>;
 		#size-cells = <0>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
index 408e0ecdce6a..b032f3890c8c 100644
--- a/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-lx2160a.dtsi
@@ -33,7 +33,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster0_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@1 {
@@ -49,7 +49,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster0_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@100 {
@@ -65,7 +65,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster1_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@101 {
@@ -81,7 +81,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster1_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@200 {
@@ -97,7 +97,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster2_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@201 {
@@ -113,7 +113,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster2_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@300 {
@@ -129,7 +129,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster3_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@301 {
@@ -145,7 +145,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster3_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@400 {
@@ -161,7 +161,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster4_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@401 {
@@ -177,7 +177,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster4_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@500 {
@@ -193,7 +193,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster5_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@501 {
@@ -209,7 +209,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster5_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@600 {
@@ -225,7 +225,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster6_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@601 {
@@ -241,7 +241,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster6_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@700 {
@@ -257,7 +257,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster7_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cpu@701 {
@@ -273,7 +273,7 @@
 			i-cache-line-size = <64>;
 			i-cache-sets = <192>;
 			next-level-cache = <&cluster7_l2>;
-			cpu-idle-states = <&cpu_pw20>;
+			cpu-idle-states = <&cpu_pw15>;
 		};
 
 		cluster0_l2: l2-cache0 {
@@ -340,9 +340,9 @@
 			cache-level = <2>;
 		};
 
-		cpu_pw20: cpu-pw20 {
+		cpu_pw15: cpu-pw15 {
 			compatible = "arm,idle-state";
-			idle-state-name = "PW20";
+			idle-state-name = "PW15";
 			arm,psci-suspend-param = <0x0>;
 			entry-latency-us = <2000>;
 			exit-latency-us = <2000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mm.dtsi b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
index 5f9d0da196e1..23c8fad7932b 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm.dtsi
@@ -394,7 +394,7 @@
 			};
 
 			sdma2: dma-controller@302c0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302c0000 0x10000>;
 				interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA2_ROOT>,
@@ -405,7 +405,7 @@
 			};
 
 			sdma3: dma-controller@302b0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302b0000 0x10000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA3_ROOT>,
@@ -694,7 +694,7 @@
 				compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b40000 0x10000>;
 				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MM_CLK_DUMMY>,
+				clocks = <&clk IMX8MM_CLK_IPG_ROOT>,
 					 <&clk IMX8MM_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MM_CLK_USDHC1_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -710,7 +710,7 @@
 				compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b50000 0x10000>;
 				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MM_CLK_DUMMY>,
+				clocks = <&clk IMX8MM_CLK_IPG_ROOT>,
 					 <&clk IMX8MM_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MM_CLK_USDHC2_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -724,7 +724,7 @@
 				compatible = "fsl,imx8mm-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b60000 0x10000>;
 				interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MM_CLK_DUMMY>,
+				clocks = <&clk IMX8MM_CLK_IPG_ROOT>,
 					 <&clk IMX8MM_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MM_CLK_USDHC3_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -737,7 +737,7 @@
 			};
 
 			sdma1: dma-controller@30bd0000 {
-				compatible = "fsl,imx8mm-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mm-sdma", "fsl,imx8mq-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MM_CLK_SDMA1_ROOT>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index 785f4c420fa4..43c4db312146 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -288,7 +288,7 @@
 			};
 
 			sdma3: dma-controller@302b0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302b0000 0x10000>;
 				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA3_ROOT>,
@@ -299,7 +299,7 @@
 			};
 
 			sdma2: dma-controller@302c0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x302c0000 0x10000>;
 				interrupts = <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA2_ROOT>,
@@ -569,7 +569,7 @@
 				compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b40000 0x10000>;
 				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_DUMMY>,
+				clocks = <&clk IMX8MN_CLK_IPG_ROOT>,
 					 <&clk IMX8MN_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MN_CLK_USDHC1_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -585,7 +585,7 @@
 				compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b50000 0x10000>;
 				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_DUMMY>,
+				clocks = <&clk IMX8MN_CLK_IPG_ROOT>,
 					 <&clk IMX8MN_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MN_CLK_USDHC2_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -599,7 +599,7 @@
 				compatible = "fsl,imx8mn-usdhc", "fsl,imx7d-usdhc";
 				reg = <0x30b60000 0x10000>;
 				interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MN_CLK_DUMMY>,
+				clocks = <&clk IMX8MN_CLK_IPG_ROOT>,
 					 <&clk IMX8MN_CLK_NAND_USDHC_BUS>,
 					 <&clk IMX8MN_CLK_USDHC3_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -612,7 +612,7 @@
 			};
 
 			sdma1: dma-controller@30bd0000 {
-				compatible = "fsl,imx8mn-sdma", "fsl,imx7d-sdma";
+				compatible = "fsl,imx8mn-sdma", "fsl,imx8mq-sdma";
 				reg = <0x30bd0000 0x10000>;
 				interrupts = <GIC_SPI 2 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MN_CLK_SDMA1_ROOT>,
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi
index af99473ada04..32ce14936b01 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq-zii-ultra.dtsi
@@ -88,9 +88,9 @@
 		regulator-name = "0V9_ARM";
 		regulator-min-microvolt = <900000>;
 		regulator-max-microvolt = <1000000>;
-		gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
-		states = <1000000 0x0
-		           900000 0x1>;
+		gpios = <&gpio3 16 GPIO_ACTIVE_HIGH>;
+		states = <1000000 0x1
+		           900000 0x0>;
 		regulator-always-on;
 	};
 };
diff --git a/arch/arm64/boot/dts/freescale/imx8mq.dtsi b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
index 04115ca6bfb5..55a3d1c4bdf0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mq.dtsi
@@ -850,7 +850,7 @@
 				             "fsl,imx7d-usdhc";
 				reg = <0x30b40000 0x10000>;
 				interrupts = <GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MQ_CLK_DUMMY>,
+				clocks = <&clk IMX8MQ_CLK_IPG_ROOT>,
 				         <&clk IMX8MQ_CLK_NAND_USDHC_BUS>,
 				         <&clk IMX8MQ_CLK_USDHC1_ROOT>;
 				clock-names = "ipg", "ahb", "per";
@@ -867,7 +867,7 @@
 				             "fsl,imx7d-usdhc";
 				reg = <0x30b50000 0x10000>;
 				interrupts = <GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clk IMX8MQ_CLK_DUMMY>,
+				clocks = <&clk IMX8MQ_CLK_IPG_ROOT>,
 				         <&clk IMX8MQ_CLK_NAND_USDHC_BUS>,
 				         <&clk IMX8MQ_CLK_USDHC2_ROOT>;
 				clock-names = "ipg", "ahb", "per";
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index d105986c6be1..5f350cc71a2f 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -60,11 +60,6 @@
 		gpio = <&gpiosb 0 GPIO_ACTIVE_HIGH>;
 	};
 
-	usb3_phy: usb3-phy {
-		compatible = "usb-nop-xceiv";
-		vcc-supply = <&exp_usb3_vbus>;
-	};
-
 	vsdc_reg: vsdc-reg {
 		compatible = "regulator-gpio";
 		regulator-name = "vsdc";
@@ -255,10 +250,16 @@
 	status = "okay";
 };
 
+&comphy2 {
+	connector {
+		compatible = "usb-a-connector";
+		phy-supply = <&exp_usb3_vbus>;
+	};
+};
+
 &usb3 {
 	status = "okay";
 	phys = <&comphy2 0>;
-	usb-phy = <&usb3_phy>;
 };
 
 &mdio {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
index e152b0ca0290..b8066868a3fe 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-kevin.dts
@@ -44,7 +44,7 @@
 		power-supply = <&pp3300_disp>;
 
 		panel-timing {
-			clock-frequency = <266604720>;
+			clock-frequency = <266666667>;
 			hactive = <2400>;
 			hfront-porch = <48>;
 			hback-porch = <84>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
index 0d1f5f9a0de9..c133e8d64b2a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-hugsun-x99.dts
@@ -644,7 +644,7 @@
 	status = "okay";
 
 	u2phy0_host: host-port {
-		phy-supply = <&vcc5v0_host>;
+		phy-supply = <&vcc5v0_typec>;
 		status = "okay";
 	};
 
@@ -712,7 +712,7 @@
 
 &usbdrd_dwc3_0 {
 	status = "okay";
-	dr_mode = "otg";
+	dr_mode = "host";
 };
 
 &usbdrd3_1 {
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
index 0401d4ec1f45..e544deb61d28 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dts
@@ -173,7 +173,7 @@
 		regulator-always-on;
 		regulator-boot-on;
 		regulator-min-microvolt = <800000>;
-		regulator-max-microvolt = <1400000>;
+		regulator-max-microvolt = <1700000>;
 		vin-supply = <&vcc5v0_sys>;
 	};
 };
@@ -247,8 +247,8 @@
 	rk808: pmic@1b {
 		compatible = "rockchip,rk808";
 		reg = <0x1b>;
-		interrupt-parent = <&gpio1>;
-		interrupts = <21 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-parent = <&gpio3>;
+		interrupts = <10 IRQ_TYPE_LEVEL_LOW>;
 		#clock-cells = <1>;
 		clock-output-names = "xin32k", "rk808-clkout2";
 		pinctrl-names = "default";
@@ -574,7 +574,7 @@
 
 	pmic {
 		pmic_int_l: pmic-int-l {
-			rockchip,pins = <1 RK_PC5 RK_FUNC_GPIO &pcfg_pull_up>;
+			rockchip,pins = <3 RK_PB2 RK_FUNC_GPIO &pcfg_pull_up>;
 		};
 
 		vsel1_gpio: vsel1-gpio {
@@ -624,7 +624,6 @@
 
 &sdmmc {
 	bus-width = <4>;
-	cap-mmc-highspeed;
 	cap-sd-highspeed;
 	cd-gpios = <&gpio0 7 GPIO_ACTIVE_LOW>;
 	disable-wp;
@@ -636,8 +635,7 @@
 
 &sdhci {
 	bus-width = <8>;
-	mmc-hs400-1_8v;
-	mmc-hs400-enhanced-strobe;
+	mmc-hs200-1_8v;
 	non-removable;
 	status = "okay";
 };
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index b1454d117cd2..aca07c2f6e6e 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -79,6 +79,7 @@
 #define CAVIUM_CPU_PART_THUNDERX_83XX	0x0A3
 #define CAVIUM_CPU_PART_THUNDERX2	0x0AF
 
+#define BRCM_CPU_PART_BRAHMA_B53	0x100
 #define BRCM_CPU_PART_VULCAN		0x516
 
 #define QCOM_CPU_PART_FALKOR_V1		0x800
@@ -105,6 +106,7 @@
 #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
 #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
 #define MIDR_CAVIUM_THUNDERX2 MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX2)
+#define MIDR_BRAHMA_B53 MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_BRAHMA_B53)
 #define MIDR_BRCM_VULCAN MIDR_CPU_MODEL(ARM_CPU_IMP_BRCM, BRCM_CPU_PART_VULCAN)
 #define MIDR_QCOM_FALKOR_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR_V1)
 #define MIDR_QCOM_FALKOR MIDR_CPU_MODEL(ARM_CPU_IMP_QCOM, QCOM_CPU_PART_FALKOR)
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 9a21b84536f2..8dc6c5cdabe6 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -32,11 +32,11 @@
 #define PROT_DEFAULT		(_PROT_DEFAULT | PTE_MAYBE_NG)
 #define PROT_SECT_DEFAULT	(_PROT_SECT_DEFAULT | PMD_MAYBE_NG)
 
-#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
-#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
-#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
-#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
-#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
+#define PROT_DEVICE_nGnRnE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+#define PROT_DEVICE_nGnRE	(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE))
+#define PROT_NORMAL_NC		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC))
+#define PROT_NORMAL_WT		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_WT))
+#define PROT_NORMAL		(PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL))
 
 #define PROT_SECT_DEVICE_nGnRE	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE))
 #define PROT_SECT_NORMAL	(PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL))
@@ -80,8 +80,9 @@
 #define PAGE_S2_DEVICE		__pgprot(_PROT_DEFAULT | PAGE_S2_MEMATTR(DEVICE_nGnRE) | PTE_S2_RDONLY | PTE_S2_XN)
 
 #define PAGE_NONE		__pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PROT_NONE | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
-#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
-#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_WRITE)
+/* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */
+#define PAGE_SHARED		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE)
+#define PAGE_SHARED_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN)
 #define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 8330810f699e..565aa45ef134 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -283,23 +283,6 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	set_pte(ptep, pte);
 }
 
-#define __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t pte_a, pte_t pte_b)
-{
-	pteval_t lhs, rhs;
-
-	lhs = pte_val(pte_a);
-	rhs = pte_val(pte_b);
-
-	if (pte_present(pte_a))
-		lhs &= ~PTE_RDONLY;
-
-	if (pte_present(pte_b))
-		rhs &= ~PTE_RDONLY;
-
-	return (lhs == rhs);
-}
-
 /*
  * Huge pte definitions.
  */
diff --git a/arch/arm64/include/asm/vdso/vsyscall.h b/arch/arm64/include/asm/vdso/vsyscall.h
index 0c731bfc7c8c..0c20a7c1bee5 100644
--- a/arch/arm64/include/asm/vdso/vsyscall.h
+++ b/arch/arm64/include/asm/vdso/vsyscall.h
@@ -31,13 +31,6 @@ int __arm64_get_clock_mode(struct timekeeper *tk)
 #define __arch_get_clock_mode __arm64_get_clock_mode
 
 static __always_inline
-int __arm64_use_vsyscall(struct vdso_data *vdata)
-{
-	return !vdata[CS_HRES_COARSE].clock_mode;
-}
-#define __arch_use_vsyscall __arm64_use_vsyscall
-
-static __always_inline
 void __arm64_update_vsyscall(struct vdso_data *vdata, struct timekeeper *tk)
 {
 	vdata[CS_HRES_COARSE].mask	= VDSO_PRECISION_MASK;
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 6c3b10a41bd8..93f34b4eca25 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -489,6 +489,7 @@ static const struct midr_range arm64_ssb_cpus[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
 	{},
 };
 
@@ -573,6 +574,7 @@ static const struct midr_range spectre_v2_safe_list[] = {
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
 	MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+	MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53),
 	{ /* sentinel */ }
 };
 
@@ -659,17 +661,23 @@ static const struct midr_range arm64_harden_el2_vectors[] = {
 #endif
 
 #ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
-
-static const struct midr_range arm64_repeat_tlbi_cpus[] = {
+static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
-	MIDR_RANGE(MIDR_QCOM_FALKOR_V1, 0, 0, 0, 0),
+	{
+		ERRATA_MIDR_REV(MIDR_QCOM_FALKOR_V1, 0, 0)
+	},
+	{
+		.midr_range.model = MIDR_QCOM_KRYO,
+		.matches = is_kryo_midr,
+	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_1286807
-	MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	{
+		ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 3, 0),
+	},
 #endif
 	{},
 };
-
 #endif
 
 #ifdef CONFIG_CAVIUM_ERRATUM_27456
@@ -737,6 +745,33 @@ static const struct midr_range erratum_1418040_list[] = {
 };
 #endif
 
+#ifdef CONFIG_ARM64_ERRATUM_845719
+static const struct midr_range erratum_845719_list[] = {
+	/* Cortex-A53 r0p[01234] */
+	MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+	/* Brahma-B53 r0p[0] */
+	MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	{},
+};
+#endif
+
+#ifdef CONFIG_ARM64_ERRATUM_843419
+static const struct arm64_cpu_capabilities erratum_843419_list[] = {
+	{
+		/* Cortex-A53 r0p[01234] */
+		.matches = is_affected_midr_range,
+		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+		MIDR_FIXED(0x4, BIT(8)),
+	},
+	{
+		/* Brahma-B53 r0p[0] */
+		.matches = is_affected_midr_range,
+		ERRATA_MIDR_REV(MIDR_BRAHMA_B53, 0, 0),
+	},
+	{},
+};
+#endif
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -768,19 +803,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_843419
 	{
-	/* Cortex-A53 r0p[01234] */
 		.desc = "ARM erratum 843419",
 		.capability = ARM64_WORKAROUND_843419,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
-		MIDR_FIXED(0x4, BIT(8)),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = erratum_843419_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_845719
 	{
-	/* Cortex-A53 r0p[01234] */
 		.desc = "ARM erratum 845719",
 		.capability = ARM64_WORKAROUND_845719,
-		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A53, 0, 0, 4),
+		ERRATA_MIDR_RANGE_LIST(erratum_845719_list),
 	},
 #endif
 #ifdef CONFIG_CAVIUM_ERRATUM_23154
@@ -816,6 +850,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "Qualcomm Technologies Falkor/Kryo erratum 1003",
 		.capability = ARM64_WORKAROUND_QCOM_FALKOR_E1003,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = cpucap_multi_entry_cap_matches,
 		.match_list = qcom_erratum_1003_list,
 	},
@@ -824,7 +859,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "Qualcomm erratum 1009, ARM erratum 1286807",
 		.capability = ARM64_WORKAROUND_REPEAT_TLBI,
-		ERRATA_MIDR_RANGE_LIST(arm64_repeat_tlbi_cpus),
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.matches = cpucap_multi_entry_cap_matches,
+		.match_list = arm64_repeat_tlbi_list,
 	},
 #endif
 #ifdef CONFIG_ARM64_ERRATUM_858921
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 2071260a275b..46822afc57e0 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	if (!system_supports_32bit_el0())
+		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
 
@@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
+		if (!system_supports_32bit_el0())
+			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
 		kvm_vcpu_pmu_restore_guest(vcpu);
diff --git a/arch/ia64/include/asm/agp.h b/arch/ia64/include/asm/agp.h
index 2b451c4496da..0261507dc264 100644
--- a/arch/ia64/include/asm/agp.h
+++ b/arch/ia64/include/asm/agp.h
@@ -14,8 +14,8 @@
  * in coherent mode, which lets us map the AGP memory as normal (write-back) memory
  * (unlike x86, where it gets mapped "write-coalescing").
  */
-#define map_page_into_agp(page)		/* nothing */
-#define unmap_page_from_agp(page)	/* nothing */
+#define map_page_into_agp(page)		do { } while (0)
+#define unmap_page_from_agp(page)	do { } while (0)
 #define flush_agp_cache()		mb()
 
 /* GATT allocation. Returns/accepts GATT kernel virtual address. */
diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c
index 77a836e661c9..df69eaa453a1 100644
--- a/arch/mips/bcm63xx/prom.c
+++ b/arch/mips/bcm63xx/prom.c
@@ -84,7 +84,7 @@ void __init prom_init(void)
 		 * Here we will start up CPU1 in the background and ask it to
 		 * reconfigure itself then go back to sleep.
 		 */
-		memcpy((void *)0xa0000200, &bmips_smp_movevec, 0x20);
+		memcpy((void *)0xa0000200, bmips_smp_movevec, 0x20);
 		__sync();
 		set_c0_cause(C_SW0);
 		cpumask_set_cpu(1, &bmips_booted_mask);
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index bf6a8afd7ad2..581a6a3c66e4 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -75,11 +75,11 @@ static inline int register_bmips_smp_ops(void)
 #endif
 }
 
-extern char bmips_reset_nmi_vec;
-extern char bmips_reset_nmi_vec_end;
-extern char bmips_smp_movevec;
-extern char bmips_smp_int_vec;
-extern char bmips_smp_int_vec_end;
+extern char bmips_reset_nmi_vec[];
+extern char bmips_reset_nmi_vec_end[];
+extern char bmips_smp_movevec[];
+extern char bmips_smp_int_vec[];
+extern char bmips_smp_int_vec_end[];
 
 extern int bmips_smp_enabled;
 extern int bmips_cpu_offset;
diff --git a/arch/mips/include/asm/vdso/gettimeofday.h b/arch/mips/include/asm/vdso/gettimeofday.h
index e78462e8ca2e..b08825531e9f 100644
--- a/arch/mips/include/asm/vdso/gettimeofday.h
+++ b/arch/mips/include/asm/vdso/gettimeofday.h
@@ -24,6 +24,8 @@
 
 #define VDSO_HAS_CLOCK_GETRES		1
 
+#define __VDSO_USE_SYSCALL		ULLONG_MAX
+
 #ifdef CONFIG_MIPS_CLOCK_VSYSCALL
 
 static __always_inline long gettimeofday_fallback(
@@ -205,7 +207,7 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode)
 		break;
 #endif
 	default:
-		cycle_now = 0;
+		cycle_now = __VDSO_USE_SYSCALL;
 		break;
 	}
 
diff --git a/arch/mips/include/asm/vdso/vsyscall.h b/arch/mips/include/asm/vdso/vsyscall.h
index 195314732233..00d41b94ba31 100644
--- a/arch/mips/include/asm/vdso/vsyscall.h
+++ b/arch/mips/include/asm/vdso/vsyscall.h
@@ -28,13 +28,6 @@ int __mips_get_clock_mode(struct timekeeper *tk)
 }
 #define __arch_get_clock_mode __mips_get_clock_mode
 
-static __always_inline
-int __mips_use_vsyscall(struct vdso_data *vdata)
-{
-	return (vdata[CS_HRES_COARSE].clock_mode != VDSO_CLOCK_NONE);
-}
-#define __arch_use_vsyscall __mips_use_vsyscall
-
 /* The asm-generic header needs to be included after the definitions above */
 #include <asm-generic/vdso/vsyscall.h>
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 76fae9b79f13..712c15de6ab9 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -464,10 +464,10 @@ static void bmips_wr_vec(unsigned long dst, char *start, char *end)
 
 static inline void bmips_nmi_handler_setup(void)
 {
-	bmips_wr_vec(BMIPS_NMI_RESET_VEC, &bmips_reset_nmi_vec,
-		&bmips_reset_nmi_vec_end);
-	bmips_wr_vec(BMIPS_WARM_RESTART_VEC, &bmips_smp_int_vec,
-		&bmips_smp_int_vec_end);
+	bmips_wr_vec(BMIPS_NMI_RESET_VEC, bmips_reset_nmi_vec,
+		bmips_reset_nmi_vec_end);
+	bmips_wr_vec(BMIPS_WARM_RESTART_VEC, bmips_smp_int_vec,
+		bmips_smp_int_vec_end);
 }
 
 struct reset_vec_info {
diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index e01cb33bfa1a..41bb91f05688 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -653,6 +653,13 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r,
 				   int restore_scratch)
 {
 	if (restore_scratch) {
+		/*
+		 * Ensure the MFC0 below observes the value written to the
+		 * KScratch register by the prior MTC0.
+		 */
+		if (scratch_reg >= 0)
+			uasm_i_ehb(p);
+
 		/* Reset default page size */
 		if (PM_DEFAULT_MASK >> 16) {
 			uasm_i_lui(p, tmp, PM_DEFAULT_MASK >> 16);
@@ -667,12 +674,10 @@ static void build_restore_pagemask(u32 **p, struct uasm_reloc **r,
 			uasm_i_mtc0(p, 0, C0_PAGEMASK);
 			uasm_il_b(p, r, lid);
 		}
-		if (scratch_reg >= 0) {
-			uasm_i_ehb(p);
+		if (scratch_reg >= 0)
 			UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
-		} else {
+		else
 			UASM_i_LW(p, 1, scratchpad_offset(0), 0);
-		}
 	} else {
 		/* Reset default page size */
 		if (PM_DEFAULT_MASK >> 16) {
@@ -921,6 +926,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 	}
 	if (mode != not_refill && check_for_high_segbits) {
 		uasm_l_large_segbits_fault(l, *p);
+
+		if (mode == refill_scratch && scratch_reg >= 0)
+			uasm_i_ehb(p);
+
 		/*
 		 * We get here if we are an xsseg address, or if we are
 		 * an xuseg address above (PGDIR_SHIFT+PGDIR_BITS) boundary.
@@ -939,12 +948,10 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r,
 		uasm_i_jr(p, ptr);
 
 		if (mode == refill_scratch) {
-			if (scratch_reg >= 0) {
-				uasm_i_ehb(p);
+			if (scratch_reg >= 0)
 				UASM_i_MFC0(p, 1, c0_kscratch(), scratch_reg);
-			} else {
+			else
 				UASM_i_LW(p, 1, scratchpad_offset(0), 0);
-			}
 		} else {
 			uasm_i_nop(p);
 		}
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 1d1d748c227f..b96d74496977 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -2125,7 +2125,7 @@ ftrace_regs_caller:
 	copy	%rp, %r26
 	LDREG	-FTRACE_FRAME_SIZE-PT_SZ_ALGN(%sp), %r25
 	ldo	-8(%r25), %r25
-	copy	%r3, %arg2
+	ldo	-FTRACE_FRAME_SIZE(%r1), %arg2
 	b,l	ftrace_function_trampoline, %rp
 	copy	%r1, %arg3 /* struct pt_regs */
 
diff --git a/arch/powerpc/include/asm/book3s/32/kup.h b/arch/powerpc/include/asm/book3s/32/kup.h
index 677e9babef80..f9dc597b0b86 100644
--- a/arch/powerpc/include/asm/book3s/32/kup.h
+++ b/arch/powerpc/include/asm/book3s/32/kup.h
@@ -91,6 +91,7 @@
 
 static inline void kuap_update_sr(u32 sr, u32 addr, u32 end)
 {
+	addr &= 0xf0000000;	/* align addr to start of segment */
 	barrier();	/* make sure thread.kuap is updated before playing with SRs */
 	while (addr < end) {
 		mtsrin(sr, addr);
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 409c9bfb43d9..57c229a86f08 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -175,4 +175,7 @@ do {									\
 	ARCH_DLINFO_CACHE_GEOMETRY;					\
 } while (0)
 
+/* Relocate the kernel image to @final_address */
+void relocate(unsigned long final_address);
+
 #endif /* _ASM_POWERPC_ELF_H */
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a4e7762dd286..100f1b57ec2f 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -3249,7 +3249,20 @@ static void setup_secure_guest(unsigned long kbase, unsigned long fdt)
 	/* Switch to secure mode. */
 	prom_printf("Switching to secure mode.\n");
 
+	/*
+	 * The ultravisor will do an integrity check of the kernel image but we
+	 * relocated it so the check will fail. Restore the original image by
+	 * relocating it back to the kernel virtual base address.
+	 */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(KERNELBASE);
+
 	ret = enter_secure_mode(kbase, fdt);
+
+	/* Relocate the kernel again. */
+	if (IS_ENABLED(CONFIG_RELOCATABLE))
+		relocate(kbase);
+
 	if (ret != U_SUCCESS) {
 		prom_printf("Returned %d from switching to secure mode.\n", ret);
 		prom_rtas_os_term("Switch to secure mode failed.\n");
diff --git a/arch/powerpc/kernel/prom_init_check.sh b/arch/powerpc/kernel/prom_init_check.sh
index 78bab17b1396..b183ab9c5107 100644
--- a/arch/powerpc/kernel/prom_init_check.sh
+++ b/arch/powerpc/kernel/prom_init_check.sh
@@ -26,7 +26,8 @@ _end enter_prom $MEM_FUNCS reloc_offset __secondary_hold
 __secondary_hold_acknowledge __secondary_hold_spinloop __start
 logo_linux_clut224 btext_prepare_BAT
 reloc_got2 kernstart_addr memstart_addr linux_banner _stext
-__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC."
+__prom_init_toc_start __prom_init_toc_end btext_setup_display TOC.
+relocate"
 
 NM="$1"
 OBJ="$2"
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 591bfb4bfd0f..a3f9c665bb5b 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -1217,6 +1217,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc;
 	int i, r = -EBUSY;
+	u32 vp_id;
 
 	pr_devel("connect_vcpu(cpu=%d)\n", cpu);
 
@@ -1228,25 +1229,32 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		return -EPERM;
 	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
-		pr_devel("Duplicate !\n");
-		return -EEXIST;
-	}
 	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
 		pr_devel("Out of bounds !\n");
 		return -EINVAL;
 	}
-	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
-	if (!xc)
-		return -ENOMEM;
 
 	/* We need to synchronize with queue provisioning */
 	mutex_lock(&xive->lock);
+
+	vp_id = kvmppc_xive_vp(xive, cpu);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
+		pr_devel("Duplicate !\n");
+		r = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		r = -ENOMEM;
+		goto bail;
+	}
+
 	vcpu->arch.xive_vcpu = xc;
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = kvmppc_xive_vp(xive, cpu);
+	xc->vp_id = vp_id;
 	xc->mfrr = 0xff;
 	xc->valid = true;
 
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 955b820ffd6d..fe3ed50e0818 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -220,6 +220,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
 	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
 }
 
+static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id)
+			return true;
+	}
+	return false;
+}
+
 /*
  * Mapping between guest priorities and host priorities
  * is as follow.
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index 248c1ea9e788..78b906ffa0d2 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -106,6 +106,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc = NULL;
 	int rc;
+	u32 vp_id;
 
 	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
 
@@ -124,7 +125,8 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 
 	mutex_lock(&xive->lock);
 
-	if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
+	vp_id = kvmppc_xive_vp(xive, server_num);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
 		pr_devel("Duplicate !\n");
 		rc = -EEXIST;
 		goto bail;
@@ -141,7 +143,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	xc->vcpu = vcpu;
 	xc->server_num = server_num;
 
-	xc->vp_id = kvmppc_xive_vp(xive, server_num);
+	xc->vp_id = vp_id;
 	xc->valid = true;
 	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
 
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 02a59946a78a..be3517ef0574 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -1142,6 +1142,19 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	}
 
 	/*
+	 * If we have seen a tail call, we need a second pass.
+	 * This is because bpf_jit_emit_common_epilogue() is called
+	 * from bpf_jit_emit_tail_call() with a not yet stable ctx->seen.
+	 */
+	if (cgctx.seen & SEEN_TAILCALL) {
+		cgctx.idx = 0;
+		if (bpf_jit_build_body(fp, 0, &cgctx, addrs, false)) {
+			fp = org_fp;
+			goto out_addrs;
+		}
+	}
+
+	/*
 	 * Pretend to build prologue, given the features we've seen.  This will
 	 * update ctgtx.idx as it pretends to output instructions, then we can
 	 * calculate total size from idx.
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 6bc24a47e9ef..6f300ab7f0e9 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -42,7 +42,7 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	struct pci_dn *pdn = pci_get_pdn(pdev);
 
-	if (eeh_has_flag(EEH_FORCE_DISABLED))
+	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
 		return;
 
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index fbd6e6b7bbf2..13e251699346 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -146,20 +146,25 @@ static int pnv_smp_cpu_disable(void)
 	return 0;
 }
 
+static void pnv_flush_interrupts(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
+		if (xive_enabled())
+			xive_flush_interrupt();
+		else
+			icp_opal_flush_interrupt();
+	} else {
+		icp_native_flush_interrupt();
+	}
+}
+
 static void pnv_smp_cpu_kill_self(void)
 {
+	unsigned long srr1, unexpected_mask, wmask;
 	unsigned int cpu;
-	unsigned long srr1, wmask;
 	u64 lpcr_val;
 
 	/* Standard hot unplug procedure */
-	/*
-	 * This hard disables local interurpts, ensuring we have no lazy
-	 * irqs pending.
-	 */
-	WARN_ON(irqs_disabled());
-	hard_irq_disable();
-	WARN_ON(lazy_irq_pending());
 
 	idle_task_exit();
 	current->active_mm = NULL; /* for sanity */
@@ -173,6 +178,27 @@ static void pnv_smp_cpu_kill_self(void)
 		wmask = SRR1_WAKEMASK_P8;
 
 	/*
+	 * This turns the irq soft-disabled state we're called with, into a
+	 * hard-disabled state with pending irq_happened interrupts cleared.
+	 *
+	 * PACA_IRQ_DEC   - Decrementer should be ignored.
+	 * PACA_IRQ_HMI   - Can be ignored, processing is done in real mode.
+	 * PACA_IRQ_DBELL, EE, PMI - Unexpected.
+	 */
+	hard_irq_disable();
+	if (generic_check_cpu_restart(cpu))
+		goto out;
+
+	unexpected_mask = ~(PACA_IRQ_DEC | PACA_IRQ_HMI | PACA_IRQ_HARD_DIS);
+	if (local_paca->irq_happened & unexpected_mask) {
+		if (local_paca->irq_happened & PACA_IRQ_EE)
+			pnv_flush_interrupts();
+		DBG("CPU%d Unexpected exit while offline irq_happened=%lx!\n",
+				cpu, local_paca->irq_happened);
+	}
+	local_paca->irq_happened = PACA_IRQ_HARD_DIS;
+
+	/*
 	 * We don't want to take decrementer interrupts while we are
 	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
 	 * LPCR_PECE_HVEE on P9) enabled so as to let IPIs in.
@@ -197,6 +223,7 @@ static void pnv_smp_cpu_kill_self(void)
 
 		srr1 = pnv_cpu_offline(cpu);
 
+		WARN_ON_ONCE(!irqs_disabled());
 		WARN_ON(lazy_irq_pending());
 
 		/*
@@ -212,13 +239,7 @@ static void pnv_smp_cpu_kill_self(void)
 		 */
 		if (((srr1 & wmask) == SRR1_WAKEEE) ||
 		    ((srr1 & wmask) == SRR1_WAKEHVI)) {
-			if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-				if (xive_enabled())
-					xive_flush_interrupt();
-				else
-					icp_opal_flush_interrupt();
-			} else
-				icp_native_flush_interrupt();
+			pnv_flush_interrupts();
 		} else if ((srr1 & wmask) == SRR1_WAKEHDBELL) {
 			unsigned long msg = PPC_DBELL_TYPE(PPC_DBELL_SERVER);
 			asm volatile(PPC_MSGCLR(%0) : : "r" (msg));
@@ -266,7 +287,7 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
 	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
-
+out:
 	DBG("CPU%d coming online...\n", cpu);
 }
 
diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h
index 07ceee8b1747..75604fec1b1b 100644
--- a/arch/riscv/include/asm/bug.h
+++ b/arch/riscv/include/asm/bug.h
@@ -12,7 +12,6 @@
 
 #include <asm/asm.h>
 
-#ifdef CONFIG_GENERIC_BUG
 #define __INSN_LENGTH_MASK  _UL(0x3)
 #define __INSN_LENGTH_32    _UL(0x3)
 #define __COMPRESSED_INSN_MASK	_UL(0xffff)
@@ -20,7 +19,6 @@
 #define __BUG_INSN_32	_UL(0x00100073) /* ebreak */
 #define __BUG_INSN_16	_UL(0x9002) /* c.ebreak */
 
-#ifndef __ASSEMBLY__
 typedef u32 bug_insn_t;
 
 #ifdef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
@@ -43,6 +41,7 @@ typedef u32 bug_insn_t;
 	RISCV_SHORT " %2"
 #endif
 
+#ifdef CONFIG_GENERIC_BUG
 #define __BUG_FLAGS(flags)					\
 do {								\
 	__asm__ __volatile__ (					\
@@ -58,14 +57,10 @@ do {								\
 		  "i" (flags),					\
 		  "i" (sizeof(struct bug_entry)));              \
 } while (0)
-
-#endif /* !__ASSEMBLY__ */
 #else /* CONFIG_GENERIC_BUG */
-#ifndef __ASSEMBLY__
 #define __BUG_FLAGS(flags) do {					\
 	__asm__ __volatile__ ("ebreak\n");			\
 } while (0)
-#endif /* !__ASSEMBLY__ */
 #endif /* CONFIG_GENERIC_BUG */
 
 #define BUG() do {						\
@@ -79,15 +74,10 @@ do {								\
 
 #include <asm-generic/bug.h>
 
-#ifndef __ASSEMBLY__
-
 struct pt_regs;
 struct task_struct;
 
-extern void die(struct pt_regs *regs, const char *str);
-extern void do_trap(struct pt_regs *regs, int signo, int code,
-	unsigned long addr);
-
-#endif /* !__ASSEMBLY__ */
+void die(struct pt_regs *regs, const char *str);
+void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr);
 
 #endif /* _ASM_RISCV_BUG_H */
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index fc1189ad3777..3ba4d93721d3 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -13,6 +13,7 @@
 
 #include <linux/types.h>
 #include <asm/mmiowb.h>
+#include <asm/pgtable.h>
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
@@ -162,6 +163,12 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
+ *  I/O port access constants.
+ */
+#define IO_SPACE_LIMIT		(PCI_IO_SIZE - 1)
+#define PCI_IOBASE		((void __iomem *)PCI_IO_START)
+
+/*
  * Emulation routines for the port-mapped IO space used by some PCI drivers.
  * These are defined as being "fully synchronous", but also "not guaranteed to
  * be fully ordered with respect to other memory and I/O operations".  We're
diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h
index 75576424c0f7..6e1b0e0325eb 100644
--- a/arch/riscv/include/asm/irq.h
+++ b/arch/riscv/include/asm/irq.h
@@ -7,6 +7,9 @@
 #ifndef _ASM_RISCV_IRQ_H
 #define _ASM_RISCV_IRQ_H
 
+#include <linux/interrupt.h>
+#include <linux/linkage.h>
+
 #define NR_IRQS         0
 
 void riscv_timer_interrupt(void);
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 42292d99cc74..d3221017194d 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -7,6 +7,7 @@
 #define _ASM_RISCV_PGTABLE_H
 
 #include <linux/mmzone.h>
+#include <linux/sizes.h>
 
 #include <asm/pgtable-bits.h>
 
@@ -86,6 +87,7 @@ extern pgd_t swapper_pg_dir[];
 #define VMALLOC_SIZE     (KERN_VIRT_SIZE >> 1)
 #define VMALLOC_END      (PAGE_OFFSET - 1)
 #define VMALLOC_START    (PAGE_OFFSET - VMALLOC_SIZE)
+#define PCI_IO_SIZE      SZ_16M
 
 /*
  * Roughly size the vmemmap space to be large enough to fit enough
@@ -100,7 +102,10 @@ extern pgd_t swapper_pg_dir[];
 
 #define vmemmap		((struct page *)VMEMMAP_START)
 
-#define FIXADDR_TOP      (VMEMMAP_START)
+#define PCI_IO_END       VMEMMAP_START
+#define PCI_IO_START     (PCI_IO_END - PCI_IO_SIZE)
+#define FIXADDR_TOP      PCI_IO_START
+
 #ifdef CONFIG_64BIT
 #define FIXADDR_SIZE     PMD_SIZE
 #else
@@ -184,10 +189,7 @@ static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot)
 	return __pte((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot));
 }
 
-static inline pte_t mk_pte(struct page *page, pgprot_t prot)
-{
-	return pfn_pte(page_to_pfn(page), prot);
-}
+#define mk_pte(page, prot)       pfn_pte(page_to_pfn(page), prot)
 
 #define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
@@ -428,9 +430,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-#ifdef CONFIG_FLATMEM
 #define kern_addr_valid(addr)   (1) /* FIXME */
-#endif
 
 extern void *dtb_early_va;
 extern void setup_bootmem(void);
diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h
index f0227bdce0f0..ee4f0ac62c9d 100644
--- a/arch/riscv/include/asm/switch_to.h
+++ b/arch/riscv/include/asm/switch_to.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_RISCV_SWITCH_TO_H
 #define _ASM_RISCV_SWITCH_TO_H
 
+#include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/ptrace.h>
 #include <asm/csr.h>
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index b1ade9a49347..a5ad00043104 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -10,6 +10,7 @@
 #include <asm/processor.h>
 #include <asm/hwcap.h>
 #include <asm/smp.h>
+#include <asm/switch_to.h>
 
 unsigned long elf_hwcap __read_mostly;
 #ifdef CONFIG_FPU
diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h
new file mode 100644
index 000000000000..105fb0496b24
--- /dev/null
+++ b/arch/riscv/kernel/head.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 SiFive, Inc.
+ */
+#ifndef __ASM_HEAD_H
+#define __ASM_HEAD_H
+
+#include <linux/linkage.h>
+#include <linux/init.h>
+
+extern atomic_t hart_lottery;
+
+asmlinkage void do_page_fault(struct pt_regs *regs);
+asmlinkage void __init setup_vm(uintptr_t dtb_pa);
+
+extern void *__cpu_up_stack_pointer[];
+extern void *__cpu_up_task_pointer[];
+
+void __init parse_dtb(void);
+
+#endif /* __ASM_HEAD_H */
diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c
index 6d8659388c49..fffac6ddb0e0 100644
--- a/arch/riscv/kernel/irq.c
+++ b/arch/riscv/kernel/irq.c
@@ -24,7 +24,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-asmlinkage void __irq_entry do_IRQ(struct pt_regs *regs)
+asmlinkage __visible void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c
index c9ae48333114..e264e59e596e 100644
--- a/arch/riscv/kernel/module-sections.c
+++ b/arch/riscv/kernel/module-sections.c
@@ -8,6 +8,7 @@
 #include <linux/elf.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/moduleloader.h>
 
 unsigned long module_emit_got_entry(struct module *mod, unsigned long val)
 {
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index fb3a082362eb..85e3c39bb60b 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
@@ -19,6 +20,7 @@
 #include <asm/csr.h>
 #include <asm/string.h>
 #include <asm/switch_to.h>
+#include <asm/thread_info.h>
 
 extern asmlinkage void ret_from_fork(void);
 extern asmlinkage void ret_from_kernel_thread(void);
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 368751438366..1252113ef8b2 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -148,7 +148,7 @@ long arch_ptrace(struct task_struct *child, long request,
  * Allows PTRACE_SYSCALL to work.  These are called from entry.S in
  * {handle,ret_from}_syscall.
  */
-void do_syscall_trace_enter(struct pt_regs *regs)
+__visible void do_syscall_trace_enter(struct pt_regs *regs)
 {
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		if (tracehook_report_syscall_entry(regs))
@@ -162,7 +162,7 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 	audit_syscall_entry(regs->a7, regs->a0, regs->a1, regs->a2, regs->a3);
 }
 
-void do_syscall_trace_exit(struct pt_regs *regs)
+__visible void do_syscall_trace_exit(struct pt_regs *regs)
 {
 	audit_syscall_exit(regs);
 
diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c
index d0fe623bfb8f..aa56bb135ec4 100644
--- a/arch/riscv/kernel/reset.c
+++ b/arch/riscv/kernel/reset.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/reboot.h>
+#include <linux/pm.h>
 #include <asm/sbi.h>
 
 static void default_power_off(void)
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index a990a6cb184f..845ae0e12115 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -24,6 +24,8 @@
 #include <asm/tlbflush.h>
 #include <asm/thread_info.h>
 
+#include "head.h"
+
 #ifdef CONFIG_DUMMY_CONSOLE
 struct screen_info screen_info = {
 	.orig_video_lines	= 30,
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index b14d7647d800..d0f6f212f5df 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -26,7 +26,7 @@ struct rt_sigframe {
 
 #ifdef CONFIG_FPU
 static long restore_fp_state(struct pt_regs *regs,
-			     union __riscv_fp_state *sc_fpregs)
+			     union __riscv_fp_state __user *sc_fpregs)
 {
 	long err;
 	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
@@ -53,7 +53,7 @@ static long restore_fp_state(struct pt_regs *regs,
 }
 
 static long save_fp_state(struct pt_regs *regs,
-			  union __riscv_fp_state *sc_fpregs)
+			  union __riscv_fp_state __user *sc_fpregs)
 {
 	long err;
 	struct __riscv_d_ext_state __user *state = &sc_fpregs->d;
@@ -292,8 +292,8 @@ static void do_signal(struct pt_regs *regs)
  * notification of userspace execution resumption
  * - triggered by the _TIF_WORK_MASK flags
  */
-asmlinkage void do_notify_resume(struct pt_regs *regs,
-	unsigned long thread_info_flags)
+asmlinkage __visible void do_notify_resume(struct pt_regs *regs,
+					   unsigned long thread_info_flags)
 {
 	/* Handle pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index b18cd6c8e8fb..5c9ec78422c2 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -8,7 +8,9 @@
  * Copyright (C) 2017 SiFive
  */
 
+#include <linux/cpu.h>
 #include <linux/interrupt.h>
+#include <linux/profile.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 18ae6da5115e..261f4087cc39 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -29,6 +29,9 @@
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
 #include <asm/sbi.h>
+#include <asm/smp.h>
+
+#include "head.h"
 
 void *__cpu_up_stack_pointer[NR_CPUS];
 void *__cpu_up_task_pointer[NR_CPUS];
@@ -130,7 +133,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 /*
  * C entry point for a secondary processor.
  */
-asmlinkage void __init smp_callin(void)
+asmlinkage __visible void __init smp_callin(void)
 {
 	struct mm_struct *mm = &init_mm;
 
diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c
index e5dd52d8f633..f1ead9df96ca 100644
--- a/arch/riscv/kernel/syscall_table.c
+++ b/arch/riscv/kernel/syscall_table.c
@@ -8,6 +8,7 @@
 #include <linux/syscalls.h>
 #include <asm-generic/syscalls.h>
 #include <asm/vdso.h>
+#include <asm/syscall.h>
 
 #undef __SYSCALL
 #define __SYSCALL(nr, call)	[nr] = (call),
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 9dd1f2e64db1..6a53c02e9c73 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -7,6 +7,7 @@
 #include <linux/clocksource.h>
 #include <linux/delay.h>
 #include <asm/sbi.h>
+#include <asm/processor.h>
 
 unsigned long riscv_timebase;
 EXPORT_SYMBOL_GPL(riscv_timebase);
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 1ac75f7d0bff..473de3ae8bb7 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2012 Regents of the University of California
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sched.h>
@@ -83,7 +84,7 @@ static void do_trap_error(struct pt_regs *regs, int signo, int code,
 }
 
 #define DO_ERROR_INFO(name, signo, code, str)				\
-asmlinkage void name(struct pt_regs *regs)				\
+asmlinkage __visible void name(struct pt_regs *regs)			\
 {									\
 	do_trap_error(regs, signo, code, regs->sepc, "Oops - " str);	\
 }
@@ -111,7 +112,6 @@ DO_ERROR_INFO(do_trap_ecall_s,
 DO_ERROR_INFO(do_trap_ecall_m,
 	SIGILL, ILL_ILLTRP, "environment call from M-mode");
 
-#ifdef CONFIG_GENERIC_BUG
 static inline unsigned long get_break_insn_length(unsigned long pc)
 {
 	bug_insn_t insn;
@@ -120,28 +120,15 @@ static inline unsigned long get_break_insn_length(unsigned long pc)
 		return 0;
 	return (((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? 4UL : 2UL);
 }
-#endif /* CONFIG_GENERIC_BUG */
 
-asmlinkage void do_trap_break(struct pt_regs *regs)
+asmlinkage __visible void do_trap_break(struct pt_regs *regs)
 {
-	if (user_mode(regs)) {
-		force_sig_fault(SIGTRAP, TRAP_BRKPT,
-				(void __user *)(regs->sepc));
-		return;
-	}
-#ifdef CONFIG_GENERIC_BUG
-	{
-		enum bug_trap_type type;
-
-		type = report_bug(regs->sepc, regs);
-		if (type == BUG_TRAP_TYPE_WARN) {
-			regs->sepc += get_break_insn_length(regs->sepc);
-			return;
-		}
-	}
-#endif /* CONFIG_GENERIC_BUG */
-
-	die(regs, "Kernel BUG");
+	if (user_mode(regs))
+		force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->sepc);
+	else if (report_bug(regs->sepc, regs) == BUG_TRAP_TYPE_WARN)
+		regs->sepc += get_break_insn_length(regs->sepc);
+	else
+		die(regs, "Kernel BUG");
 }
 
 #ifdef CONFIG_GENERIC_BUG
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index c9c21e0d5641..484d95a70907 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2015 Regents of the University of California
  */
 
+#include <linux/elf.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/binfmts.h>
@@ -25,7 +26,7 @@ static union {
 	struct vdso_data	data;
 	u8			page[PAGE_SIZE];
 } vdso_data_store __page_aligned_data;
-struct vdso_data *vdso_data = &vdso_data_store.data;
+static struct vdso_data *vdso_data = &vdso_data_store.data;
 
 static int __init vdso_init(void)
 {
diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c
index beeb5d7f92ea..ca66d44156b6 100644
--- a/arch/riscv/mm/context.c
+++ b/arch/riscv/mm/context.c
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
 
 /*
  * When necessary, performs a deferred icache flush for the given MM context,
diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
index 96add1427a75..247b8c859c44 100644
--- a/arch/riscv/mm/fault.c
+++ b/arch/riscv/mm/fault.c
@@ -18,6 +18,8 @@
 #include <asm/ptrace.h>
 #include <asm/tlbflush.h>
 
+#include "../kernel/head.h"
+
 /*
  * This routine handles page faults.  It determines the address and the
  * problem, and then passes it off to one of the appropriate routines.
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 83f7d12042fb..573463d1c799 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -19,6 +19,8 @@
 #include <asm/pgtable.h>
 #include <asm/io.h>
 
+#include "../kernel/head.h"
+
 unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
 							__page_aligned_bss;
 EXPORT_SYMBOL(empty_zero_page);
@@ -337,8 +339,7 @@ static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
  */
 
 #ifndef __riscv_cmodel_medany
-#error "setup_vm() is called from head.S before relocate so it should "
-	"not use absolute addressing."
+#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
 #endif
 
 asmlinkage void __init setup_vm(uintptr_t dtb_pa)
@@ -458,7 +459,7 @@ void __init paging_init(void)
 	zone_sizes_init();
 }
 
-#ifdef CONFIG_SPARSEMEM
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 			       struct vmem_altmap *altmap)
 {
diff --git a/arch/riscv/mm/sifive_l2_cache.c b/arch/riscv/mm/sifive_l2_cache.c
index 2e637ad71c05..a9ffff3277c7 100644
--- a/arch/riscv/mm/sifive_l2_cache.c
+++ b/arch/riscv/mm/sifive_l2_cache.c
@@ -142,7 +142,7 @@ static irqreturn_t l2_int_handler(int irq, void *device)
 	return IRQ_HANDLED;
 }
 
-int __init sifive_l2_init(void)
+static int __init sifive_l2_init(void)
 {
 	struct device_node *np;
 	struct resource res;
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 596ca7cc4d7b..5367950510f6 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -101,10 +101,18 @@ static void handle_relocs(unsigned long offset)
 	dynsym = (Elf64_Sym *) vmlinux.dynsym_start;
 	for (rela = rela_start; rela < rela_end; rela++) {
 		loc = rela->r_offset + offset;
-		val = rela->r_addend + offset;
+		val = rela->r_addend;
 		r_sym = ELF64_R_SYM(rela->r_info);
-		if (r_sym)
-			val += dynsym[r_sym].st_value;
+		if (r_sym) {
+			if (dynsym[r_sym].st_shndx != SHN_UNDEF)
+				val += dynsym[r_sym].st_value + offset;
+		} else {
+			/*
+			 * 0 == undefined symbol table index (STN_UNDEF),
+			 * used for R_390_RELATIVE, only add KASLR offset
+			 */
+			val += offset;
+		}
 		r_type = ELF64_R_TYPE(rela->r_info);
 		rc = arch_kexec_do_relocs(r_type, (void *) loc, val, 0);
 		if (rc)
diff --git a/arch/s390/include/asm/unwind.h b/arch/s390/include/asm/unwind.h
index d827b5b9a32c..eaaefeceef6f 100644
--- a/arch/s390/include/asm/unwind.h
+++ b/arch/s390/include/asm/unwind.h
@@ -35,6 +35,7 @@ struct unwind_state {
 	struct task_struct *task;
 	struct pt_regs *regs;
 	unsigned long sp, ip;
+	bool reuse_sp;
 	int graph_idx;
 	bool reliable;
 	bool error;
diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index b9d8fe45737a..8f8456816d83 100644
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -69,18 +69,26 @@ DEVICE_ATTR(idle_count, 0444, show_idle_count, NULL);
 static ssize_t show_idle_time(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
+	unsigned long long now, idle_time, idle_enter, idle_exit, in_idle;
 	struct s390_idle_data *idle = &per_cpu(s390_idle, dev->id);
-	unsigned long long now, idle_time, idle_enter, idle_exit;
 	unsigned int seq;
 
 	do {
-		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
 		idle_time = READ_ONCE(idle->idle_time);
 		idle_enter = READ_ONCE(idle->clock_idle_enter);
 		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-	idle_time += idle_enter ? ((idle_exit ? : now) - idle_enter) : 0;
+	in_idle = 0;
+	now = get_tod_clock();
+	if (idle_enter) {
+		if (idle_exit) {
+			in_idle = idle_exit - idle_enter;
+		} else if (now > idle_enter) {
+			in_idle = now - idle_enter;
+		}
+	}
+	idle_time += in_idle;
 	return sprintf(buf, "%llu\n", idle_time >> 12);
 }
 DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
@@ -88,17 +96,24 @@ DEVICE_ATTR(idle_time_us, 0444, show_idle_time, NULL);
 u64 arch_cpu_idle_time(int cpu)
 {
 	struct s390_idle_data *idle = &per_cpu(s390_idle, cpu);
-	unsigned long long now, idle_enter, idle_exit;
+	unsigned long long now, idle_enter, idle_exit, in_idle;
 	unsigned int seq;
 
 	do {
-		now = get_tod_clock();
 		seq = read_seqcount_begin(&idle->seqcount);
 		idle_enter = READ_ONCE(idle->clock_idle_enter);
 		idle_exit = READ_ONCE(idle->clock_idle_exit);
 	} while (read_seqcount_retry(&idle->seqcount, seq));
-
-	return cputime_to_nsecs(idle_enter ? ((idle_exit ?: now) - idle_enter) : 0);
+	in_idle = 0;
+	now = get_tod_clock();
+	if (idle_enter) {
+		if (idle_exit) {
+			in_idle = idle_exit - idle_enter;
+		} else if (now > idle_enter) {
+			in_idle = now - idle_enter;
+		}
+	}
+	return cputime_to_nsecs(in_idle);
 }
 
 void arch_cpu_idle_enter(void)
diff --git a/arch/s390/kernel/machine_kexec_reloc.c b/arch/s390/kernel/machine_kexec_reloc.c
index 3b664cb3ec4d..d5035de9020e 100644
--- a/arch/s390/kernel/machine_kexec_reloc.c
+++ b/arch/s390/kernel/machine_kexec_reloc.c
@@ -27,6 +27,7 @@ int arch_kexec_do_relocs(int r_type, void *loc, unsigned long val,
 		*(u32 *)loc = val;
 		break;
 	case R_390_64:		/* Direct 64 bit.  */
+	case R_390_GLOB_DAT:
 		*(u64 *)loc = val;
 		break;
 	case R_390_PC16:	/* PC relative 16 bit.	*/
diff --git a/arch/s390/kernel/unwind_bc.c b/arch/s390/kernel/unwind_bc.c
index 8fc9daae47a2..a8204f952315 100644
--- a/arch/s390/kernel/unwind_bc.c
+++ b/arch/s390/kernel/unwind_bc.c
@@ -46,10 +46,15 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	regs = state->regs;
 	if (unlikely(regs)) {
-		sp = READ_ONCE_NOCHECK(regs->gprs[15]);
-		if (unlikely(outside_of_stack(state, sp))) {
-			if (!update_stack_info(state, sp))
-				goto out_err;
+		if (state->reuse_sp) {
+			sp = state->sp;
+			state->reuse_sp = false;
+		} else {
+			sp = READ_ONCE_NOCHECK(regs->gprs[15]);
+			if (unlikely(outside_of_stack(state, sp))) {
+				if (!update_stack_info(state, sp))
+					goto out_err;
+			}
 		}
 		sf = (struct stack_frame *) sp;
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
@@ -107,9 +112,9 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 {
 	struct stack_info *info = &state->stack_info;
 	unsigned long *mask = &state->stack_mask;
+	bool reliable, reuse_sp;
 	struct stack_frame *sf;
 	unsigned long ip;
-	bool reliable;
 
 	memset(state, 0, sizeof(*state));
 	state->task = task;
@@ -134,10 +139,12 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	if (regs) {
 		ip = READ_ONCE_NOCHECK(regs->psw.addr);
 		reliable = true;
+		reuse_sp = true;
 	} else {
 		sf = (struct stack_frame *) sp;
 		ip = READ_ONCE_NOCHECK(sf->gprs[8]);
 		reliable = false;
+		reuse_sp = false;
 	}
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -151,5 +158,6 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	state->sp = sp;
 	state->ip = ip;
 	state->reliable = reliable;
+	state->reuse_sp = reuse_sp;
 }
 EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 510a18299196..a51c892f14f3 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -298,16 +298,16 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write,
 	}
 
 	if (write) {
-		len = *lenp;
-		if (copy_from_user(buf, buffer,
-				   len > sizeof(buf) ? sizeof(buf) : len))
+		len = min(*lenp, sizeof(buf));
+		if (copy_from_user(buf, buffer, len))
 			return -EFAULT;
-		buf[sizeof(buf) - 1] = '\0';
+		buf[len - 1] = '\0';
 		cmm_skip_blanks(buf, &p);
 		nr = simple_strtoul(p, &p, 0);
 		cmm_skip_blanks(p, &p);
 		seconds = simple_strtoul(p, &p, 0);
 		cmm_set_timeout(nr, seconds);
+		*ppos += *lenp;
 	} else {
 		len = sprintf(buf, "%ld %ld\n",
 			      cmm_timeout_pages, cmm_timeout_seconds);
@@ -315,9 +315,9 @@ static int cmm_timeout_handler(struct ctl_table *ctl, int write,
 			len = *lenp;
 		if (copy_to_user(buffer, buf, len))
 			return -EFAULT;
+		*lenp = len;
+		*ppos += len;
 	}
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 612535cd9706..6627d7c30f37 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -1403,8 +1403,12 @@ static blk_status_t ubd_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	spin_unlock_irq(&ubd_dev->lock);
 
-	if (ret < 0)
-		blk_mq_requeue_request(req, true);
+	if (ret < 0) {
+		if (ret == -ENOMEM)
+			res = BLK_STS_RESOURCE;
+		else
+			res = BLK_STS_DEV_RESOURCE;
+	}
 
 	return res;
 }
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index d6662fdef300..82bc60c8acb2 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -13,6 +13,7 @@
 #include <asm/e820/types.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
+#include <asm/boot.h>
 
 #include "../string.h"
 #include "eboot.h"
@@ -813,7 +814,8 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
 		status = efi_relocate_kernel(sys_table, &bzimage_addr,
 					     hdr->init_size, hdr->init_size,
 					     hdr->pref_address,
-					     hdr->kernel_alignment);
+					     hdr->kernel_alignment,
+					     LOAD_PHYSICAL_ADDR);
 		if (status != EFI_SUCCESS) {
 			efi_printk(sys_table, "efi_relocate_kernel() failed!\n");
 			goto fail;
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 5b35b7ea5d72..26c36357c4c9 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -377,7 +377,8 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
 					  struct hw_perf_event *hwc, u64 config)
 {
 	config &= ~perf_ibs->cnt_mask;
-	wrmsrl(hwc->config_base, config);
+	if (boot_cpu_data.x86 == 0x10)
+		wrmsrl(hwc->config_base, config);
 	config &= ~perf_ibs->enable_mask;
 	wrmsrl(hwc->config_base, config);
 }
@@ -553,7 +554,8 @@ static struct perf_ibs perf_ibs_op = {
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
-	.cnt_mask		= IBS_OP_MAX_CNT,
+	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
+				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
 	.max_period		= IBS_OP_MAX_CNT << 4,
@@ -614,7 +616,7 @@ fail:
 	if (event->attr.sample_type & PERF_SAMPLE_RAW)
 		offset_max = perf_ibs->offset_max;
 	else if (check_rip)
-		offset_max = 2;
+		offset_max = 3;
 	else
 		offset_max = 1;
 	do {
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 74e80ed9c6c4..05e43d0f430b 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -627,7 +627,7 @@ static struct topa *topa_alloc(int cpu, gfp_t gfp)
 	 * link as the 2nd entry in the table
 	 */
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) {
-		TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p);
+		TOPA_ENTRY(&tp->topa, 1)->base = page_to_phys(p) >> TOPA_SHIFT;
 		TOPA_ENTRY(&tp->topa, 1)->end = 1;
 	}
 
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 6fc2e06ab4c6..86467f85c383 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -502,10 +502,8 @@ void uncore_pmu_event_start(struct perf_event *event, int flags)
 	local64_set(&event->hw.prev_count, uncore_read_counter(box, event));
 	uncore_enable_event(box, event);
 
-	if (box->n_active == 1) {
-		uncore_enable_box(box);
+	if (box->n_active == 1)
 		uncore_pmu_start_hrtimer(box);
-	}
 }
 
 void uncore_pmu_event_stop(struct perf_event *event, int flags)
@@ -529,10 +527,8 @@ void uncore_pmu_event_stop(struct perf_event *event, int flags)
 		WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 		hwc->state |= PERF_HES_STOPPED;
 
-		if (box->n_active == 0) {
-			uncore_disable_box(box);
+		if (box->n_active == 0)
 			uncore_pmu_cancel_hrtimer(box);
-		}
 	}
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
@@ -778,6 +774,40 @@ static int uncore_pmu_event_init(struct perf_event *event)
 	return ret;
 }
 
+static void uncore_pmu_enable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->enable_box)
+		uncore_pmu->type->ops->enable_box(box);
+}
+
+static void uncore_pmu_disable(struct pmu *pmu)
+{
+	struct intel_uncore_pmu *uncore_pmu;
+	struct intel_uncore_box *box;
+
+	uncore_pmu = container_of(pmu, struct intel_uncore_pmu, pmu);
+	if (!uncore_pmu)
+		return;
+
+	box = uncore_pmu_to_box(uncore_pmu, smp_processor_id());
+	if (!box)
+		return;
+
+	if (uncore_pmu->type->ops->disable_box)
+		uncore_pmu->type->ops->disable_box(box);
+}
+
 static ssize_t uncore_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
@@ -803,6 +833,8 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 		pmu->pmu = (struct pmu) {
 			.attr_groups	= pmu->type->attr_groups,
 			.task_ctx_nr	= perf_invalid_context,
+			.pmu_enable	= uncore_pmu_enable,
+			.pmu_disable	= uncore_pmu_disable,
 			.event_init	= uncore_pmu_event_init,
 			.add		= uncore_pmu_event_add,
 			.del		= uncore_pmu_event_del,
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index f36f7bebbc1b..bbfdaa720b45 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -441,18 +441,6 @@ static inline int uncore_freerunning_hw_config(struct intel_uncore_box *box,
 	return -EINVAL;
 }
 
-static inline void uncore_disable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->disable_box)
-		box->pmu->type->ops->disable_box(box);
-}
-
-static inline void uncore_enable_box(struct intel_uncore_box *box)
-{
-	if (box->pmu->type->ops->enable_box)
-		box->pmu->type->ops->enable_box(box);
-}
-
 static inline void uncore_disable_event(struct intel_uncore_box *box,
 				struct perf_event *event)
 {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 50eb430b0ad8..24d6598dea29 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1189,7 +1189,7 @@ struct kvm_x86_ops {
 	int (*set_nested_state)(struct kvm_vcpu *vcpu,
 				struct kvm_nested_state __user *user_kvm_nested_state,
 				struct kvm_nested_state *kvm_state);
-	void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
 
 	int (*smi_allowed)(struct kvm_vcpu *vcpu);
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
index e00c9e875933..ac9fc51e2b18 100644
--- a/arch/x86/include/asm/vmware.h
+++ b/arch/x86/include/asm/vmware.h
@@ -4,6 +4,7 @@
 
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
+#include <linux/stringify.h>
 
 /*
  * The hypercall definitions differ in the low word of the %edx argument
@@ -20,8 +21,8 @@
  */
 
 /* Old port-based version */
-#define VMWARE_HYPERVISOR_PORT    "0x5658"
-#define VMWARE_HYPERVISOR_PORT_HB "0x5659"
+#define VMWARE_HYPERVISOR_PORT    0x5658
+#define VMWARE_HYPERVISOR_PORT_HB 0x5659
 
 /* Current vmcall / vmmcall version */
 #define VMWARE_HYPERVISOR_HB   BIT(0)
@@ -29,7 +30,8 @@
 
 /* The low bandwidth call. The low word of edx is presumed clear. */
 #define VMWARE_HYPERCALL						\
-	ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT ", %%dx; inl (%%dx)", \
+	ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT) ", %%dx; " \
+		      "inl (%%dx), %%eax",				\
 		      "vmcall", X86_FEATURE_VMCALL,			\
 		      "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
@@ -38,7 +40,8 @@
  * HB and OUT bits set.
  */
 #define VMWARE_HYPERCALL_HB_OUT						\
-	ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep outsb", \
+	ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \
+		      "rep outsb",					\
 		      "vmcall", X86_FEATURE_VMCALL,			\
 		      "vmmcall", X86_FEATURE_VMW_VMMCALL)
 
@@ -47,7 +50,8 @@
  * HB bit set.
  */
 #define VMWARE_HYPERCALL_HB_IN						\
-	ALTERNATIVE_2("movw $" VMWARE_HYPERVISOR_PORT_HB ", %%dx; rep insb", \
+	ALTERNATIVE_2("movw $" __stringify(VMWARE_HYPERVISOR_PORT_HB) ", %%dx; " \
+		      "rep insb",					\
 		      "vmcall", X86_FEATURE_VMCALL,			\
 		      "vmmcall", X86_FEATURE_VMW_VMMCALL)
 #endif
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 9e2dd2b296cd..2b0faf86da1b 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1586,9 +1586,6 @@ static void setup_local_APIC(void)
 {
 	int cpu = smp_processor_id();
 	unsigned int value;
-#ifdef CONFIG_X86_32
-	int logical_apicid, ldr_apicid;
-#endif
 
 	if (disable_apic) {
 		disable_ioapic_support();
@@ -1626,16 +1623,21 @@ static void setup_local_APIC(void)
 	apic->init_apic_ldr();
 
 #ifdef CONFIG_X86_32
-	/*
-	 * APIC LDR is initialized.  If logical_apicid mapping was
-	 * initialized during get_smp_config(), make sure it matches the
-	 * actual value.
-	 */
-	logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
-	ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
-	WARN_ON(logical_apicid != BAD_APICID && logical_apicid != ldr_apicid);
-	/* always use the value from LDR */
-	early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+	if (apic->dest_logical) {
+		int logical_apicid, ldr_apicid;
+
+		/*
+		 * APIC LDR is initialized.  If logical_apicid mapping was
+		 * initialized during get_smp_config(), make sure it matches
+		 * the actual value.
+		 */
+		logical_apicid = early_per_cpu(x86_cpu_to_logical_apicid, cpu);
+		ldr_apicid = GET_APIC_LOGICAL_ID(apic_read(APIC_LDR));
+		if (logical_apicid != BAD_APICID)
+			WARN_ON(logical_apicid != ldr_apicid);
+		/* Always use the value from LDR. */
+		early_per_cpu(x86_cpu_to_logical_apicid, cpu) = ldr_apicid;
+	}
 #endif
 
 	/*
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index efbd54cc4e69..055c8613b531 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -522,6 +522,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	int ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		ret = -ENOENT;
+		goto out;
+	}
 
 	md.priv = of->kn->priv;
 	resid = md.u.rid;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 753b8cfe8b8a..87b97897a881 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -94,6 +94,13 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 	BUILD_BUG_ON(N_EXCEPTION_STACKS != 6);
 
 	begin = (unsigned long)__this_cpu_read(cea_exception_stacks);
+	/*
+	 * Handle the case where stack trace is collected _before_
+	 * cea_exception_stacks had been initialized.
+	 */
+	if (!begin)
+		return false;
+
 	end = begin + sizeof(struct cea_exception_stacks);
 	/* Bail if @stack is outside the exception stack area. */
 	if (stk < begin || stk >= end)
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c59454c382fd..7e322e2daaf5 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1505,6 +1505,9 @@ void __init tsc_init(void)
 		return;
 	}
 
+	if (tsc_clocksource_reliable || no_tsc_watchdog)
+		clocksource_tsc_early.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
+
 	clocksource_register_khz(&clocksource_tsc_early, tsc_khz);
 	detect_art();
 }
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 9c5029cf6f3f..f68c0c753c38 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -363,7 +363,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
+		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 87b0fcc23ef8..b29d00b661ff 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -111,11 +111,6 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
-{
-	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
-}
-
 static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
 {
 	return apic->vcpu->vcpu_id;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 2aad7e226fc0..1f5014852e20 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -242,4 +242,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
 	return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
 }
 
+static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
+{
+	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
+}
+
 #endif
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index f8ecb6df5106..c5673bda4b66 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -734,8 +734,14 @@ static int get_npt_level(struct kvm_vcpu *vcpu)
 static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	vcpu->arch.efer = efer;
-	if (!npt_enabled && !(efer & EFER_LMA))
-		efer &= ~EFER_LME;
+
+	if (!npt_enabled) {
+		/* Shadow paging assumes NX to be available.  */
+		efer |= EFER_NX;
+
+		if (!(efer & EFER_LMA))
+			efer &= ~EFER_LME;
+	}
 
 	to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME;
 	mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR);
@@ -4591,6 +4597,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	int ret = 0;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (ldr == svm->ldr_reg)
 		return 0;
@@ -4598,7 +4605,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	avic_invalidate_logical_id_entry(vcpu);
 
 	if (ldr)
-		ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr);
+		ret = avic_ldr_write(vcpu, id, ldr);
 
 	if (!ret)
 		svm->ldr_reg = ldr;
@@ -4610,8 +4617,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
 {
 	u64 *old, *new;
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID);
-	u32 id = (apic_id_reg >> 24) & 0xff;
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (vcpu->vcpu_id == id)
 		return 0;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index e76eb4f07f6c..0e7c9301fe86 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2917,7 +2917,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 						 struct vmcs12 *vmcs12);
 
-static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2937,19 +2937,18 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 			vmx->nested.apic_access_page = NULL;
 		}
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
-		/*
-		 * If translation failed, no matter: This feature asks
-		 * to exit when accessing the given address, and if it
-		 * can never be accessed, this feature won't do
-		 * anything anyway.
-		 */
 		if (!is_error_page(page)) {
 			vmx->nested.apic_access_page = page;
 			hpa = page_to_phys(vmx->nested.apic_access_page);
 			vmcs_write64(APIC_ACCESS_ADDR, hpa);
 		} else {
-			secondary_exec_controls_clearbit(vmx,
-				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+			pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n",
+					     __func__);
+			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			vcpu->run->internal.suberror =
+				KVM_INTERNAL_ERROR_EMULATION;
+			vcpu->run->internal.ndata = 0;
+			return false;
 		}
 	}
 
@@ -2994,6 +2993,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
 	else
 		exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+	return true;
 }
 
 /*
@@ -3032,13 +3032,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 /*
  * If from_vmentry is false, this is being called from state restore (either RSM
  * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
-+ *
-+ * Returns:
-+ *   0 - success, i.e. proceed with actual VMEnter
-+ *   1 - consistency check VMExit
-+ *  -1 - consistency check VMFail
+ *
+ * Returns:
+ *	NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
+ *	NVMX_ENTRY_VMFAIL:  Consistency check VMFail
+ *	NVMX_ENTRY_VMEXIT:  Consistency check VMExit
+ *	NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
  */
-int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+							bool from_vmentry)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -3081,11 +3083,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	prepare_vmcs02_early(vmx, vmcs12);
 
 	if (from_vmentry) {
-		nested_get_vmcs12_pages(vcpu);
+		if (unlikely(!nested_get_vmcs12_pages(vcpu)))
+			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
 
 		if (nested_vmx_check_vmentry_hw(vcpu)) {
 			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-			return -1;
+			return NVMX_VMENTRY_VMFAIL;
 		}
 
 		if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
@@ -3149,7 +3152,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * returned as far as L1 is concerned. It will only return (and set
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
-	return 0;
+	return NVMX_VMENTRY_SUCCESS;
 
 	/*
 	 * A failed consistency check that leads to a VMExit during L1's
@@ -3165,14 +3168,14 @@ vmentry_fail_vmexit:
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
 	if (!from_vmentry)
-		return 1;
+		return NVMX_VMENTRY_VMEXIT;
 
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
 	vmcs12->exit_qualification = exit_qual;
 	if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
-	return 1;
+	return NVMX_VMENTRY_VMEXIT;
 }
 
 /*
@@ -3182,9 +3185,9 @@ vmentry_fail_vmexit:
 static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 {
 	struct vmcs12 *vmcs12;
+	enum nvmx_vmentry_status status;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
-	int ret;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -3244,13 +3247,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the nested entry.
 	 */
 	vmx->nested.nested_run_pending = 1;
-	ret = nested_vmx_enter_non_root_mode(vcpu, true);
-	vmx->nested.nested_run_pending = !ret;
-	if (ret > 0)
-		return 1;
-	else if (ret)
-		return nested_vmx_failValid(vcpu,
-			VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+	status = nested_vmx_enter_non_root_mode(vcpu, true);
+	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
+		goto vmentry_failed;
 
 	/* Hide L1D cache contents from the nested guest.  */
 	vmx->vcpu.arch.l1tf_flush_l1d = true;
@@ -3281,6 +3280,15 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return kvm_vcpu_halt(vcpu);
 	}
 	return 1;
+
+vmentry_failed:
+	vmx->nested.nested_run_pending = 0;
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+		return 0;
+	if (status == NVMX_VMENTRY_VMEXIT)
+		return 1;
+	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
+	return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 }
 
 /*
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 187d39bf0bf1..6280f33e5fa6 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -6,6 +6,16 @@
 #include "vmcs12.h"
 #include "vmx.h"
 
+/*
+ * Status returned by nested_vmx_enter_non_root_mode():
+ */
+enum nvmx_vmentry_status {
+	NVMX_VMENTRY_SUCCESS,		/* Entered VMX non-root mode */
+	NVMX_VMENTRY_VMFAIL,		/* Consistency check VMFail */
+	NVMX_VMENTRY_VMEXIT,		/* Consistency check VMExit */
+	NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */
+};
+
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
 void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 				bool apicv);
@@ -13,7 +23,8 @@ void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_vcpu_setup(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
-int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry);
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+						     bool from_vmentry);
 bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason);
 void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		       u32 exit_intr_info, unsigned long exit_qualification);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e7970a2e8eae..5d21a4ab28cf 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -969,17 +969,9 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	u64 guest_efer = vmx->vcpu.arch.efer;
 	u64 ignore_bits = 0;
 
-	if (!enable_ept) {
-		/*
-		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
-		 * host CPUID is more efficient than testing guest CPUID
-		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
-		 */
-		if (boot_cpu_has(X86_FEATURE_SMEP))
-			guest_efer |= EFER_NX;
-		else if (!(guest_efer & EFER_NX))
-			ignore_bits |= EFER_NX;
-	}
+	/* Shadow paging assumes NX to be available.  */
+	if (!enable_ept)
+		guest_efer |= EFER_NX;
 
 	/*
 	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
@@ -5543,14 +5535,6 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x",
-		vmcs_read32(VM_EXIT_REASON));
-	return 1;
-}
-
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -5602,15 +5586,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_INVVPID]                 = handle_vmx_instruction,
 	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
 	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
-	[EXIT_REASON_XSAVES]                  = handle_unexpected_vmexit,
-	[EXIT_REASON_XRSTORS]                 = handle_unexpected_vmexit,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
 	[EXIT_REASON_INVPCID]                 = handle_invpcid,
 	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
 	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
 	[EXIT_REASON_ENCLS]		      = handle_encls,
-	[EXIT_REASON_UMWAIT]                  = handle_unexpected_vmexit,
-	[EXIT_REASON_TPAUSE]                  = handle_unexpected_vmexit,
 };
 
 static const int kvm_vmx_max_exit_handlers =
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 661e2bf38526..ff395f812719 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -360,8 +360,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
-	if (!kvm_rebooting)
-		BUG();
+	BUG_ON(!kvm_rebooting);
 }
 EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
@@ -2537,6 +2536,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pv_time_enabled = false;
+	vcpu->arch.time = 0;
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
@@ -2702,8 +2702,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KVM_SYSTEM_TIME: {
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
-		kvmclock_reset(vcpu);
-
 		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
 			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
 
@@ -2717,14 +2715,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
+		vcpu->arch.pv_time_enabled = false;
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
-			vcpu->arch.pv_time_enabled = false;
-		else
 			vcpu->arch.pv_time_enabled = true;
 
 		break;
@@ -7941,8 +7938,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu))
-			kvm_x86_ops->get_vmcs12_pages(vcpu);
+		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) {
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 58f79ab32358..5bfea374a160 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -117,6 +117,14 @@ static void __init xen_banner(void)
 	printk(KERN_INFO "Xen version: %d.%d%s%s\n",
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
+
+#ifdef CONFIG_X86_32
+	pr_warn("WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n"
+		"Support for running as 32-bit PV-guest under Xen will soon be removed\n"
+		"from the Linux kernel!\n"
+		"Please use either a 64-bit kernel or switch to HVM or PVH mode!\n"
+		"WARNING! WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!\n");
+#endif
 }
 
 static void __init xen_pv_init_platform(void)
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 5d21027b1faf..1eb8895be4c6 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -934,9 +934,14 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		int i;
 		bool has_stats = false;
 
+		spin_lock_irq(&blkg->q->queue_lock);
+
+		if (!blkg->online)
+			goto skip;
+
 		dname = blkg_dev_name(blkg);
 		if (!dname)
-			continue;
+			goto skip;
 
 		/*
 		 * Hooray string manipulation, count is the size written NOT
@@ -946,8 +951,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		 */
 		off += scnprintf(buf+off, size-off, "%s ", dname);
 
-		spin_lock_irq(&blkg->q->queue_lock);
-
 		blkg_rwstat_recursive_sum(blkg, NULL,
 				offsetof(struct blkcg_gq, stat_bytes), &rwstat);
 		rbytes = rwstat.cnt[BLKG_RWSTAT_READ];
@@ -960,8 +963,6 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		wios = rwstat.cnt[BLKG_RWSTAT_WRITE];
 		dios = rwstat.cnt[BLKG_RWSTAT_DISCARD];
 
-		spin_unlock_irq(&blkg->q->queue_lock);
-
 		if (rbytes || wbytes || rios || wios) {
 			has_stats = true;
 			off += scnprintf(buf+off, size-off,
@@ -999,6 +1000,8 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 				seq_commit(sf, -1);
 			}
 		}
+	skip:
+		spin_unlock_irq(&blkg->q->queue_lock);
 	}
 
 	rcu_read_unlock();
diff --git a/block/blk-iocost.c b/block/blk-iocost.c
index 2a3db80c1dce..a7ed434eae03 100644
--- a/block/blk-iocost.c
+++ b/block/blk-iocost.c
@@ -2110,10 +2110,10 @@ static ssize_t ioc_weight_write(struct kernfs_open_file *of, char *buf,
 			goto einval;
 	}
 
-	spin_lock_irq(&iocg->ioc->lock);
+	spin_lock(&iocg->ioc->lock);
 	iocg->cfg_weight = v;
 	weight_updated(iocg);
-	spin_unlock_irq(&iocg->ioc->lock);
+	spin_unlock(&iocg->ioc->lock);
 
 	blkg_conf_finish(&ctx);
 	return nbytes;
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 1413324982f0..14e68f202f81 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -1322,7 +1322,7 @@ static ssize_t scrub_show(struct device *dev,
 	nfit_device_lock(dev);
 	nd_desc = dev_get_drvdata(dev);
 	if (!nd_desc) {
-		device_unlock(dev);
+		nfit_device_unlock(dev);
 		return rc;
 	}
 	acpi_desc = to_acpi_desc(nd_desc);
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 08da9c29f1e9..62114a03a51a 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -290,14 +290,13 @@ static int acpi_processor_notifier(struct notifier_block *nb,
 				   unsigned long event, void *data)
 {
 	struct cpufreq_policy *policy = data;
-	int cpu = policy->cpu;
 
 	if (event == CPUFREQ_CREATE_POLICY) {
-		acpi_thermal_cpufreq_init(cpu);
-		acpi_processor_ppc_init(cpu);
+		acpi_thermal_cpufreq_init(policy);
+		acpi_processor_ppc_init(policy);
 	} else if (event == CPUFREQ_REMOVE_POLICY) {
-		acpi_processor_ppc_exit(cpu);
-		acpi_thermal_cpufreq_exit(cpu);
+		acpi_processor_ppc_exit(policy);
+		acpi_thermal_cpufreq_exit(policy);
 	}
 
 	return 0;
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 930a49fa4dfc..5909e8fa4013 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -81,10 +81,10 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 	pr->performance_platform_limit = (int)ppc;
 
 	if (ppc >= pr->performance->state_count ||
-	    unlikely(!dev_pm_qos_request_active(&pr->perflib_req)))
+	    unlikely(!freq_qos_request_active(&pr->perflib_req)))
 		return 0;
 
-	ret = dev_pm_qos_update_request(&pr->perflib_req,
+	ret = freq_qos_update_request(&pr->perflib_req,
 			pr->performance->states[ppc].core_frequency * 1000);
 	if (ret < 0) {
 		pr_warn("Failed to update perflib freq constraint: CPU%d (%d)\n",
@@ -157,28 +157,36 @@ void acpi_processor_ignore_ppc_init(void)
 		ignore_ppc = 0;
 }
 
-void acpi_processor_ppc_init(int cpu)
+void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
-	int ret;
+	unsigned int cpu;
 
-	if (!pr)
-		return;
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+		int ret;
+
+		if (!pr)
+			continue;
 
-	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
-				     &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY,
-				     INT_MAX);
-	if (ret < 0)
-		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
-		       ret);
+		ret = freq_qos_add_request(&policy->constraints,
+					   &pr->perflib_req,
+					   FREQ_QOS_MAX, INT_MAX);
+		if (ret < 0)
+			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
+	}
 }
 
-void acpi_processor_ppc_exit(int cpu)
+void acpi_processor_ppc_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
+	unsigned int cpu;
 
-	if (pr)
-		dev_pm_qos_remove_request(&pr->perflib_req);
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+
+		if (pr)
+			freq_qos_remove_request(&pr->perflib_req);
+	}
 }
 
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 8227c7dd75b1..41feb88ee92d 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -105,7 +105,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 
 		pr = per_cpu(processors, i);
 
-		if (unlikely(!dev_pm_qos_request_active(&pr->thermal_req)))
+		if (unlikely(!freq_qos_request_active(&pr->thermal_req)))
 			continue;
 
 		policy = cpufreq_cpu_get(i);
@@ -116,7 +116,7 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 
 		cpufreq_cpu_put(policy);
 
-		ret = dev_pm_qos_update_request(&pr->thermal_req, max_freq);
+		ret = freq_qos_update_request(&pr->thermal_req, max_freq);
 		if (ret < 0) {
 			pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
 				pr->id, ret);
@@ -125,28 +125,36 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	return 0;
 }
 
-void acpi_thermal_cpufreq_init(int cpu)
+void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
-	int ret;
+	unsigned int cpu;
 
-	if (!pr)
-		return;
-
-	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
-				     &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY,
-				     INT_MAX);
-	if (ret < 0)
-		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
-		       ret);
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+		int ret;
+
+		if (!pr)
+			continue;
+
+		ret = freq_qos_add_request(&policy->constraints,
+					   &pr->thermal_req,
+					   FREQ_QOS_MAX, INT_MAX);
+		if (ret < 0)
+			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
+	}
 }
 
-void acpi_thermal_cpufreq_exit(int cpu)
+void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_processor *pr = per_cpu(processors, cpu);
+	unsigned int cpu;
+
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, policy->cpu);
 
-	if (pr)
-		dev_pm_qos_remove_request(&pr->thermal_req);
+		if (pr)
+			freq_qos_remove_request(&pr->thermal_req);
+	}
 }
 #else				/* ! CONFIG_CPU_FREQ */
 static int cpufreq_get_max_state(unsigned int cpu)
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index f39f075abff9..fe1523664816 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -409,9 +409,11 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 		 */
 		rstc = of_reset_control_array_get_optional_shared(dev->dev.of_node);
 		if (IS_ERR(rstc)) {
-			if (PTR_ERR(rstc) != -EPROBE_DEFER)
-				dev_err(&dev->dev, "Can't get amba reset!\n");
-			return PTR_ERR(rstc);
+			ret = PTR_ERR(rstc);
+			if (ret != -EPROBE_DEFER)
+				dev_err(&dev->dev, "can't get reset: %d\n",
+					ret);
+			goto err_reset;
 		}
 		reset_control_deassert(rstc);
 		reset_control_put(rstc);
@@ -472,6 +474,12 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 	release_resource(&dev->res);
  err_out:
 	return ret;
+
+ err_reset:
+	amba_put_disable_pclk(dev);
+	iounmap(tmp);
+	dev_pm_domain_detach(&dev->dev, true);
+	goto err_release;
 }
 
 /*
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 5b9ac2122e89..265d9dd46a5e 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -97,10 +97,6 @@ DEFINE_SHOW_ATTRIBUTE(proc);
 #define SZ_1K                               0x400
 #endif
 
-#ifndef SZ_4M
-#define SZ_4M                               0x400000
-#endif
-
 #define FORBIDDEN_MMAP_FLAGS                (VM_WRITE)
 
 enum {
@@ -5177,9 +5173,6 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
 	if (proc->tsk != current->group_leader)
 		return -EINVAL;
 
-	if ((vma->vm_end - vma->vm_start) > SZ_4M)
-		vma->vm_end = vma->vm_start + SZ_4M;
-
 	binder_debug(BINDER_DEBUG_OPEN_CLOSE,
 		     "%s: %d %lx-%lx (%ld K) vma %lx pagep %lx\n",
 		     __func__, proc->pid, vma->vm_start, vma->vm_end,
diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c
index d42a8b2f636a..eb76a823fbb2 100644
--- a/drivers/android/binder_alloc.c
+++ b/drivers/android/binder_alloc.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <linux/uaccess.h>
 #include <linux/highmem.h>
+#include <linux/sizes.h>
 #include "binder_alloc.h"
 #include "binder_trace.h"
 
@@ -689,7 +690,9 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 	alloc->buffer = (void __user *)vma->vm_start;
 	mutex_unlock(&binder_alloc_mmap_lock);
 
-	alloc->pages = kcalloc((vma->vm_end - vma->vm_start) / PAGE_SIZE,
+	alloc->buffer_size = min_t(unsigned long, vma->vm_end - vma->vm_start,
+				   SZ_4M);
+	alloc->pages = kcalloc(alloc->buffer_size / PAGE_SIZE,
 			       sizeof(alloc->pages[0]),
 			       GFP_KERNEL);
 	if (alloc->pages == NULL) {
@@ -697,7 +700,6 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc,
 		failure_string = "alloc page array";
 		goto err_alloc_pages_failed;
 	}
-	alloc->buffer_size = vma->vm_end - vma->vm_start;
 
 	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
 	if (!buffer) {
diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index e742780950de..8befce036af8 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -153,17 +153,13 @@ int ahci_platform_enable_regulators(struct ahci_host_priv *hpriv)
 {
 	int rc, i;
 
-	if (hpriv->ahci_regulator) {
-		rc = regulator_enable(hpriv->ahci_regulator);
-		if (rc)
-			return rc;
-	}
+	rc = regulator_enable(hpriv->ahci_regulator);
+	if (rc)
+		return rc;
 
-	if (hpriv->phy_regulator) {
-		rc = regulator_enable(hpriv->phy_regulator);
-		if (rc)
-			goto disable_ahci_pwrs;
-	}
+	rc = regulator_enable(hpriv->phy_regulator);
+	if (rc)
+		goto disable_ahci_pwrs;
 
 	for (i = 0; i < hpriv->nports; i++) {
 		if (!hpriv->target_pwrs[i])
@@ -181,11 +177,9 @@ disable_target_pwrs:
 		if (hpriv->target_pwrs[i])
 			regulator_disable(hpriv->target_pwrs[i]);
 
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->phy_regulator);
 disable_ahci_pwrs:
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->ahci_regulator);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(ahci_platform_enable_regulators);
@@ -207,10 +201,8 @@ void ahci_platform_disable_regulators(struct ahci_host_priv *hpriv)
 		regulator_disable(hpriv->target_pwrs[i]);
 	}
 
-	if (hpriv->ahci_regulator)
-		regulator_disable(hpriv->ahci_regulator);
-	if (hpriv->phy_regulator)
-		regulator_disable(hpriv->phy_regulator);
+	regulator_disable(hpriv->ahci_regulator);
+	regulator_disable(hpriv->phy_regulator);
 }
 EXPORT_SYMBOL_GPL(ahci_platform_disable_regulators);
 /**
@@ -359,7 +351,7 @@ static int ahci_platform_get_regulator(struct ahci_host_priv *hpriv, u32 port,
 	struct regulator *target_pwr;
 	int rc = 0;
 
-	target_pwr = regulator_get_optional(dev, "target");
+	target_pwr = regulator_get(dev, "target");
 
 	if (!IS_ERR(target_pwr))
 		hpriv->target_pwrs[port] = target_pwr;
@@ -436,16 +428,14 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		hpriv->clks[i] = clk;
 	}
 
-	hpriv->ahci_regulator = devm_regulator_get_optional(dev, "ahci");
+	hpriv->ahci_regulator = devm_regulator_get(dev, "ahci");
 	if (IS_ERR(hpriv->ahci_regulator)) {
 		rc = PTR_ERR(hpriv->ahci_regulator);
-		if (rc == -EPROBE_DEFER)
+		if (rc != 0)
 			goto err_out;
-		rc = 0;
-		hpriv->ahci_regulator = NULL;
 	}
 
-	hpriv->phy_regulator = devm_regulator_get_optional(dev, "phy");
+	hpriv->phy_regulator = devm_regulator_get(dev, "phy");
 	if (IS_ERR(hpriv->phy_regulator)) {
 		rc = PTR_ERR(hpriv->phy_regulator);
 		if (rc == -EPROBE_DEFER)
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 6c90fd7e2ff8..350dcafd751f 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -115,20 +115,10 @@ s32 dev_pm_qos_read_value(struct device *dev, enum dev_pm_qos_req_type type)
 
 	spin_lock_irqsave(&dev->power.lock, flags);
 
-	switch (type) {
-	case DEV_PM_QOS_RESUME_LATENCY:
+	if (type == DEV_PM_QOS_RESUME_LATENCY) {
 		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_RESUME_LATENCY_NO_CONSTRAINT
 			: pm_qos_read_value(&qos->resume_latency);
-		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE
-			: pm_qos_read_value(&qos->min_frequency);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = IS_ERR_OR_NULL(qos) ? PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE
-			: pm_qos_read_value(&qos->max_frequency);
-		break;
-	default:
+	} else {
 		WARN_ON(1);
 		ret = 0;
 	}
@@ -169,14 +159,6 @@ static int apply_constraint(struct dev_pm_qos_request *req,
 			req->dev->power.set_latency_tolerance(req->dev, value);
 		}
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = pm_qos_update_target(&qos->min_frequency,
-					   &req->data.pnode, action, value);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = pm_qos_update_target(&qos->max_frequency,
-					   &req->data.pnode, action, value);
-		break;
 	case DEV_PM_QOS_FLAGS:
 		ret = pm_qos_update_flags(&qos->flags, &req->data.flr,
 					  action, value);
@@ -227,24 +209,6 @@ static int dev_pm_qos_constraints_allocate(struct device *dev)
 	c->no_constraint_value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 
-	c = &qos->min_frequency;
-	plist_head_init(&c->list);
-	c->target_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->default_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	c->type = PM_QOS_MAX;
-	c->notifiers = ++n;
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
-
-	c = &qos->max_frequency;
-	plist_head_init(&c->list);
-	c->target_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->default_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
-	c->type = PM_QOS_MIN;
-	c->notifiers = ++n;
-	BLOCKING_INIT_NOTIFIER_HEAD(n);
-
 	INIT_LIST_HEAD(&qos->flags.list);
 
 	spin_lock_irq(&dev->power.lock);
@@ -305,18 +269,6 @@ void dev_pm_qos_constraints_destroy(struct device *dev)
 		memset(req, 0, sizeof(*req));
 	}
 
-	c = &qos->min_frequency;
-	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
-		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE);
-		memset(req, 0, sizeof(*req));
-	}
-
-	c = &qos->max_frequency;
-	plist_for_each_entry_safe(req, tmp, &c->list, data.pnode) {
-		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
-		memset(req, 0, sizeof(*req));
-	}
-
 	f = &qos->flags;
 	list_for_each_entry_safe(req, tmp, &f->list, data.flr.node) {
 		apply_constraint(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
@@ -428,8 +380,6 @@ static int __dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 	switch(req->type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
 	case DEV_PM_QOS_LATENCY_TOLERANCE:
-	case DEV_PM_QOS_MIN_FREQUENCY:
-	case DEV_PM_QOS_MAX_FREQUENCY:
 		curr_value = req->data.pnode.prio;
 		break;
 	case DEV_PM_QOS_FLAGS:
@@ -557,14 +507,6 @@ int dev_pm_qos_add_notifier(struct device *dev, struct notifier_block *notifier,
 		ret = blocking_notifier_chain_register(dev->power.qos->resume_latency.notifiers,
 						       notifier);
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = blocking_notifier_chain_register(dev->power.qos->min_frequency.notifiers,
-						       notifier);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = blocking_notifier_chain_register(dev->power.qos->max_frequency.notifiers,
-						       notifier);
-		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
@@ -604,14 +546,6 @@ int dev_pm_qos_remove_notifier(struct device *dev,
 		ret = blocking_notifier_chain_unregister(dev->power.qos->resume_latency.notifiers,
 							 notifier);
 		break;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		ret = blocking_notifier_chain_unregister(dev->power.qos->min_frequency.notifiers,
-							 notifier);
-		break;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		ret = blocking_notifier_chain_unregister(dev->power.qos->max_frequency.notifiers,
-							 notifier);
-		break;
 	default:
 		WARN_ON(1);
 		ret = -EINVAL;
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 5b248763a672..a18155cdce41 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -786,7 +786,6 @@ int __drbd_send_protocol(struct drbd_connection *connection, enum drbd_packet cm
 
 	if (nc->tentative && connection->agreed_pro_version < 92) {
 		rcu_read_unlock();
-		mutex_unlock(&sock->mutex);
 		drbd_err(connection, "--dry-run is not supported by peer");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 478aa86fc1f2..a94ee45440b3 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -385,17 +385,16 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 	struct nbd_device *nbd = cmd->nbd;
 	struct nbd_config *config;
 
+	if (!mutex_trylock(&cmd->lock))
+		return BLK_EH_RESET_TIMER;
+
 	if (!refcount_inc_not_zero(&nbd->config_refs)) {
 		cmd->status = BLK_STS_TIMEOUT;
+		mutex_unlock(&cmd->lock);
 		goto done;
 	}
 	config = nbd->config;
 
-	if (!mutex_trylock(&cmd->lock)) {
-		nbd_config_put(nbd);
-		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",
@@ -711,6 +710,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
 		ret = -ENOENT;
 		goto out;
 	}
+	if (cmd->status != BLK_STS_OK) {
+		dev_err(disk_to_dev(nbd->disk), "Command already handled %p\n",
+			req);
+		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);
@@ -792,7 +797,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved)
 {
 	struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
 
+	mutex_lock(&cmd->lock);
 	cmd->status = BLK_STS_IOERR;
+	mutex_unlock(&cmd->lock);
+
 	blk_mq_complete_request(req);
 	return true;
 }
@@ -972,6 +980,25 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return ret;
 }
 
+static struct socket *nbd_get_socket(struct nbd_device *nbd, unsigned long fd,
+				     int *err)
+{
+	struct socket *sock;
+
+	*err = 0;
+	sock = sockfd_lookup(fd, err);
+	if (!sock)
+		return NULL;
+
+	if (sock->ops->shutdown == sock_no_shutdown) {
+		dev_err(disk_to_dev(nbd->disk), "Unsupported socket: shutdown callout must be supported.\n");
+		*err = -EINVAL;
+		return NULL;
+	}
+
+	return sock;
+}
+
 static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 			  bool netlink)
 {
@@ -981,7 +1008,7 @@ static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
 	struct nbd_sock *nsock;
 	int err;
 
-	sock = sockfd_lookup(arg, &err);
+	sock = nbd_get_socket(nbd, arg, &err);
 	if (!sock)
 		return err;
 
@@ -1033,7 +1060,7 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
 	int i;
 	int err;
 
-	sock = sockfd_lookup(arg, &err);
+	sock = nbd_get_socket(nbd, arg, &err);
 	if (!sock)
 		return err;
 
diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c
index ad50efb470aa..2b6670daf7fc 100644
--- a/drivers/bus/ti-sysc.c
+++ b/drivers/bus/ti-sysc.c
@@ -74,6 +74,7 @@ static const char * const clock_names[SYSC_MAX_CLOCKS] = {
  * @clk_disable_quirk: module specific clock disable quirk
  * @reset_done_quirk: module specific reset done quirk
  * @module_enable_quirk: module specific enable quirk
+ * @module_disable_quirk: module specific disable quirk
  */
 struct sysc {
 	struct device *dev;
@@ -100,6 +101,7 @@ struct sysc {
 	void (*clk_disable_quirk)(struct sysc *sysc);
 	void (*reset_done_quirk)(struct sysc *sysc);
 	void (*module_enable_quirk)(struct sysc *sysc);
+	void (*module_disable_quirk)(struct sysc *sysc);
 };
 
 static void sysc_parse_dts_quirks(struct sysc *ddata, struct device_node *np,
@@ -959,6 +961,9 @@ static int sysc_disable_module(struct device *dev)
 	if (ddata->offsets[SYSC_SYSCONFIG] == -ENODEV)
 		return 0;
 
+	if (ddata->module_disable_quirk)
+		ddata->module_disable_quirk(ddata);
+
 	regbits = ddata->cap->regbits;
 	reg = sysc_read(ddata, ddata->offsets[SYSC_SYSCONFIG]);
 
@@ -1248,6 +1253,9 @@ static const struct sysc_revision_quirk sysc_revision_quirks[] = {
 		   SYSC_MODULE_QUIRK_SGX),
 	SYSC_QUIRK("wdt", 0, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0,
 		   SYSC_MODULE_QUIRK_WDT),
+	/* Watchdog on am3 and am4 */
+	SYSC_QUIRK("wdt", 0x44e35000, 0, 0x10, 0x14, 0x502a0500, 0xfffff0f0,
+		   SYSC_MODULE_QUIRK_WDT | SYSC_QUIRK_SWSUP_SIDLE),
 
 #ifdef DEBUG
 	SYSC_QUIRK("adc", 0, 0, 0x10, -1, 0x47300001, 0xffffffff, 0),
@@ -1440,14 +1448,14 @@ static void sysc_reset_done_quirk_wdt(struct sysc *ddata)
 				   !(val & 0x10), 100,
 				   MAX_MODULE_SOFTRESET_WAIT);
 	if (error)
-		dev_warn(ddata->dev, "wdt disable spr failed\n");
+		dev_warn(ddata->dev, "wdt disable step1 failed\n");
 
-	sysc_write(ddata, wps, 0x5555);
+	sysc_write(ddata, spr, 0x5555);
 	error = readl_poll_timeout(ddata->module_va + wps, val,
 				   !(val & 0x10), 100,
 				   MAX_MODULE_SOFTRESET_WAIT);
 	if (error)
-		dev_warn(ddata->dev, "wdt disable wps failed\n");
+		dev_warn(ddata->dev, "wdt disable step2 failed\n");
 }
 
 static void sysc_init_module_quirks(struct sysc *ddata)
@@ -1471,8 +1479,10 @@ static void sysc_init_module_quirks(struct sysc *ddata)
 	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_SGX)
 		ddata->module_enable_quirk = sysc_module_enable_quirk_sgx;
 
-	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_WDT)
+	if (ddata->cfg.quirks & SYSC_MODULE_QUIRK_WDT) {
 		ddata->reset_done_quirk = sysc_reset_done_quirk_wdt;
+		ddata->module_disable_quirk = sysc_reset_done_quirk_wdt;
+	}
 }
 
 static int sysc_clockdomain_init(struct sysc *ddata)
diff --git a/drivers/char/agp/frontend.c b/drivers/char/agp/frontend.c
index f6955888e676..47098648502d 100644
--- a/drivers/char/agp/frontend.c
+++ b/drivers/char/agp/frontend.c
@@ -102,14 +102,13 @@ agp_segment_priv *agp_find_seg_in_client(const struct agp_client *client,
 					    int size, pgprot_t page_prot)
 {
 	struct agp_segment_priv *seg;
-	int num_segments, i;
+	int i;
 	off_t pg_start;
 	size_t pg_count;
 
 	pg_start = offset / 4096;
 	pg_count = size / 4096;
 	seg = *(client->segments);
-	num_segments = client->num_segments;
 
 	for (i = 0; i < client->num_segments; i++) {
 		if ((seg[i].pg_start == pg_start) &&
diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c
index df1edb5ec0ad..ab154a75acf0 100644
--- a/drivers/char/agp/generic.c
+++ b/drivers/char/agp/generic.c
@@ -207,6 +207,7 @@ EXPORT_SYMBOL(agp_free_memory);
 /**
  *	agp_allocate_memory  -  allocate a group of pages of a certain type.
  *
+ *	@bridge: an agp_bridge_data struct allocated for the AGP host bridge.
  *	@page_count:	size_t argument of the number of pages
  *	@type:	u32 argument of the type of memory to be allocated.
  *
@@ -355,6 +356,7 @@ EXPORT_SYMBOL_GPL(agp_num_entries);
 /**
  *	agp_copy_info  -  copy bridge state information
  *
+ *	@bridge: an agp_bridge_data struct allocated for the AGP host bridge.
  *	@info:		agp_kern_info pointer.  The caller should insure that this pointer is valid.
  *
  *	This function copies information about the agp bridge device and the state of
@@ -850,7 +852,6 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 {
 	char *table;
 	char *table_end;
-	int size;
 	int page_order;
 	int num_entries;
 	int i;
@@ -864,25 +865,22 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 	table = NULL;
 	i = bridge->aperture_size_idx;
 	temp = bridge->current_size;
-	size = page_order = num_entries = 0;
+	page_order = num_entries = 0;
 
 	if (bridge->driver->size_type != FIXED_APER_SIZE) {
 		do {
 			switch (bridge->driver->size_type) {
 			case U8_APER_SIZE:
-				size = A_SIZE_8(temp)->size;
 				page_order =
 				    A_SIZE_8(temp)->page_order;
 				num_entries =
 				    A_SIZE_8(temp)->num_entries;
 				break;
 			case U16_APER_SIZE:
-				size = A_SIZE_16(temp)->size;
 				page_order = A_SIZE_16(temp)->page_order;
 				num_entries = A_SIZE_16(temp)->num_entries;
 				break;
 			case U32_APER_SIZE:
-				size = A_SIZE_32(temp)->size;
 				page_order = A_SIZE_32(temp)->page_order;
 				num_entries = A_SIZE_32(temp)->num_entries;
 				break;
@@ -890,7 +888,7 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 			case FIXED_APER_SIZE:
 			case LVL2_APER_SIZE:
 			default:
-				size = page_order = num_entries = 0;
+				page_order = num_entries = 0;
 				break;
 			}
 
@@ -920,7 +918,6 @@ int agp_generic_create_gatt_table(struct agp_bridge_data *bridge)
 			}
 		} while (!table && (i < bridge->driver->num_aperture_sizes));
 	} else {
-		size = ((struct aper_size_info_fixed *) temp)->size;
 		page_order = ((struct aper_size_info_fixed *) temp)->page_order;
 		num_entries = ((struct aper_size_info_fixed *) temp)->num_entries;
 		table = alloc_gatt_pages(page_order);
@@ -1282,6 +1279,7 @@ EXPORT_SYMBOL(agp_generic_destroy_page);
 /**
  * agp_enable  -  initialise the agp point-to-point connection.
  *
+ * @bridge: an agp_bridge_data struct allocated for the AGP host bridge.
  * @mode:	agp mode register value to configure with.
  */
 void agp_enable(struct agp_bridge_data *bridge, u32 mode)
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index 87083b3a2769..37c22667e831 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -297,7 +297,10 @@ static int clk_main_probe_frequency(struct regmap *regmap)
 		regmap_read(regmap, AT91_CKGR_MCFR, &mcfr);
 		if (mcfr & AT91_PMC_MAINRDY)
 			return 0;
-		usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT);
+		if (system_state < SYSTEM_RUNNING)
+			udelay(MAINF_LOOP_MIN_WAIT);
+		else
+			usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT);
 	} while (time_before(prep_time, timeout));
 
 	return -ETIMEDOUT;
diff --git a/drivers/clk/at91/sam9x60.c b/drivers/clk/at91/sam9x60.c
index 9790ddfa5b3c..86238d5ecb4d 100644
--- a/drivers/clk/at91/sam9x60.c
+++ b/drivers/clk/at91/sam9x60.c
@@ -43,6 +43,7 @@ static const struct clk_pll_characteristics upll_characteristics = {
 };
 
 static const struct clk_programmable_layout sam9x60_programmable_layout = {
+	.pres_mask = 0xff,
 	.pres_shift = 8,
 	.css_mask = 0x1f,
 	.have_slck_mck = 0,
diff --git a/drivers/clk/at91/sckc.c b/drivers/clk/at91/sckc.c
index 9bfe9a28294a..fac0ca56d42d 100644
--- a/drivers/clk/at91/sckc.c
+++ b/drivers/clk/at91/sckc.c
@@ -76,7 +76,10 @@ static int clk_slow_osc_prepare(struct clk_hw *hw)
 
 	writel(tmp | osc->bits->cr_osc32en, sckcr);
 
-	usleep_range(osc->startup_usec, osc->startup_usec + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(osc->startup_usec);
+	else
+		usleep_range(osc->startup_usec, osc->startup_usec + 1);
 
 	return 0;
 }
@@ -187,7 +190,10 @@ static int clk_slow_rc_osc_prepare(struct clk_hw *hw)
 
 	writel(readl(sckcr) | osc->bits->cr_rcen, sckcr);
 
-	usleep_range(osc->startup_usec, osc->startup_usec + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(osc->startup_usec);
+	else
+		usleep_range(osc->startup_usec, osc->startup_usec + 1);
 
 	return 0;
 }
@@ -288,7 +294,10 @@ static int clk_sam9x5_slow_set_parent(struct clk_hw *hw, u8 index)
 
 	writel(tmp, sckcr);
 
-	usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(SLOWCK_SW_TIME_USEC);
+	else
+		usleep_range(SLOWCK_SW_TIME_USEC, SLOWCK_SW_TIME_USEC + 1);
 
 	return 0;
 }
@@ -533,7 +542,10 @@ static int clk_sama5d4_slow_osc_prepare(struct clk_hw *hw)
 		return 0;
 	}
 
-	usleep_range(osc->startup_usec, osc->startup_usec + 1);
+	if (system_state < SYSTEM_RUNNING)
+		udelay(osc->startup_usec);
+	else
+		usleep_range(osc->startup_usec, osc->startup_usec + 1);
 	osc->prepared = true;
 
 	return 0;
diff --git a/drivers/clk/clk-ast2600.c b/drivers/clk/clk-ast2600.c
index 1c1bb39bb04e..b1318e6b655b 100644
--- a/drivers/clk/clk-ast2600.c
+++ b/drivers/clk/clk-ast2600.c
@@ -266,10 +266,11 @@ static int aspeed_g6_clk_enable(struct clk_hw *hw)
 
 	/* Enable clock */
 	if (gate->flags & CLK_GATE_SET_TO_DISABLE) {
-		regmap_write(gate->map, get_clock_reg(gate), clk);
-	} else {
-		/* Use set to clear register */
+		/* Clock is clear to enable, so use set to clear register */
 		regmap_write(gate->map, get_clock_reg(gate) + 0x04, clk);
+	} else {
+		/* Clock is set to enable, so use write to set register */
+		regmap_write(gate->map, get_clock_reg(gate), clk);
 	}
 
 	if (gate->reset_idx >= 0) {
diff --git a/drivers/clk/imx/clk-imx8mm.c b/drivers/clk/imx/clk-imx8mm.c
index 067ab876911d..172589e94f60 100644
--- a/drivers/clk/imx/clk-imx8mm.c
+++ b/drivers/clk/imx/clk-imx8mm.c
@@ -638,7 +638,7 @@ static int imx8mm_clocks_probe(struct platform_device *pdev)
 					   clks[IMX8MM_CLK_A53_DIV],
 					   clks[IMX8MM_CLK_A53_SRC],
 					   clks[IMX8MM_ARM_PLL_OUT],
-					   clks[IMX8MM_CLK_24M]);
+					   clks[IMX8MM_SYS_PLL1_800M]);
 
 	imx_check_clocks(clks, ARRAY_SIZE(clks));
 
diff --git a/drivers/clk/imx/clk-imx8mn.c b/drivers/clk/imx/clk-imx8mn.c
index 47a4b44ba3cb..58b5acee3830 100644
--- a/drivers/clk/imx/clk-imx8mn.c
+++ b/drivers/clk/imx/clk-imx8mn.c
@@ -610,7 +610,7 @@ static int imx8mn_clocks_probe(struct platform_device *pdev)
 					   clks[IMX8MN_CLK_A53_DIV],
 					   clks[IMX8MN_CLK_A53_SRC],
 					   clks[IMX8MN_ARM_PLL_OUT],
-					   clks[IMX8MN_CLK_24M]);
+					   clks[IMX8MN_SYS_PLL1_800M]);
 
 	imx_check_clocks(clks, ARRAY_SIZE(clks));
 
diff --git a/drivers/clk/meson/g12a.c b/drivers/clk/meson/g12a.c
index ea4c791f106d..b3af61cc6fb9 100644
--- a/drivers/clk/meson/g12a.c
+++ b/drivers/clk/meson/g12a.c
@@ -343,6 +343,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x3,
 		.shift = 0,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_dyn0_sel",
@@ -353,8 +354,7 @@ static struct clk_regmap g12a_cpu_clk_premux0 = {
 			{ .hw = &g12a_fclk_div3.hw },
 		},
 		.num_parents = 3,
-		/* This sub-tree is used a parking clock */
-		.flags = CLK_SET_RATE_NO_REPARENT,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -410,6 +410,7 @@ static struct clk_regmap g12a_cpu_clk_postmux0 = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 2,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_dyn0",
@@ -466,6 +467,7 @@ static struct clk_regmap g12a_cpu_clk_dyn = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 10,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk_dyn",
@@ -485,6 +487,7 @@ static struct clk_regmap g12a_cpu_clk = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 11,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk",
@@ -504,6 +507,7 @@ static struct clk_regmap g12b_cpu_clk = {
 		.offset = HHI_SYS_CPU_CLK_CNTL0,
 		.mask = 0x1,
 		.shift = 11,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpu_clk",
@@ -523,6 +527,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x3,
 		.shift = 0,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk_dyn0_sel",
@@ -533,6 +538,7 @@ static struct clk_regmap g12b_cpub_clk_premux0 = {
 			{ .hw = &g12a_fclk_div3.hw },
 		},
 		.num_parents = 3,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
@@ -567,6 +573,7 @@ static struct clk_regmap g12b_cpub_clk_postmux0 = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x1,
 		.shift = 2,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk_dyn0",
@@ -644,6 +651,7 @@ static struct clk_regmap g12b_cpub_clk_dyn = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x1,
 		.shift = 10,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk_dyn",
@@ -663,6 +671,7 @@ static struct clk_regmap g12b_cpub_clk = {
 		.offset = HHI_SYS_CPUB_CLK_CNTL,
 		.mask = 0x1,
 		.shift = 11,
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cpub_clk",
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 7cfb998eeb3e..1f9c056e684c 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -935,6 +935,7 @@ static struct clk_regmap gxbb_sar_adc_clk_div = {
 			&gxbb_sar_adc_clk_sel.hw
 		},
 		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
diff --git a/drivers/clk/samsung/clk-exynos5420.c b/drivers/clk/samsung/clk-exynos5420.c
index 7670cc596c74..31466cd1842f 100644
--- a/drivers/clk/samsung/clk-exynos5420.c
+++ b/drivers/clk/samsung/clk-exynos5420.c
@@ -165,12 +165,18 @@ static const unsigned long exynos5x_clk_regs[] __initconst = {
 	GATE_BUS_CPU,
 	GATE_SCLK_CPU,
 	CLKOUT_CMU_CPU,
+	CPLL_CON0,
+	DPLL_CON0,
 	EPLL_CON0,
 	EPLL_CON1,
 	EPLL_CON2,
 	RPLL_CON0,
 	RPLL_CON1,
 	RPLL_CON2,
+	IPLL_CON0,
+	SPLL_CON0,
+	VPLL_CON0,
+	MPLL_CON0,
 	SRC_TOP0,
 	SRC_TOP1,
 	SRC_TOP2,
@@ -1172,8 +1178,6 @@ static const struct samsung_gate_clock exynos5x_gate_clks[] __initconst = {
 	GATE(CLK_SCLK_ISP_SENSOR2, "sclk_isp_sensor2", "dout_isp_sensor2",
 			GATE_TOP_SCLK_ISP, 12, CLK_SET_RATE_PARENT, 0),
 
-	GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0),
-
 	/* CDREX */
 	GATE(CLK_CLKM_PHY0, "clkm_phy0", "dout_sclk_cdrex",
 			GATE_BUS_CDREX0, 0, 0, 0),
@@ -1248,6 +1252,15 @@ static struct exynos5_subcmu_reg_dump exynos5x_gsc_suspend_regs[] = {
 	{ DIV2_RATIO0, 0, 0x30 },	/* DIV dout_gscl_blk_300 */
 };
 
+static const struct samsung_gate_clock exynos5x_g3d_gate_clks[] __initconst = {
+	GATE(CLK_G3D, "g3d", "mout_user_aclk_g3d", GATE_IP_G3D, 9, 0, 0),
+};
+
+static struct exynos5_subcmu_reg_dump exynos5x_g3d_suspend_regs[] = {
+	{ GATE_IP_G3D, 0x3ff, 0x3ff },	/* G3D gates */
+	{ SRC_TOP5, 0, BIT(16) },	/* MUX mout_user_aclk_g3d */
+};
+
 static const struct samsung_div_clock exynos5x_mfc_div_clks[] __initconst = {
 	DIV(0, "dout_mfc_blk", "mout_user_aclk333", DIV4_RATIO, 0, 2),
 };
@@ -1320,6 +1333,14 @@ static const struct exynos5_subcmu_info exynos5x_gsc_subcmu = {
 	.pd_name	= "GSC",
 };
 
+static const struct exynos5_subcmu_info exynos5x_g3d_subcmu = {
+	.gate_clks	= exynos5x_g3d_gate_clks,
+	.nr_gate_clks	= ARRAY_SIZE(exynos5x_g3d_gate_clks),
+	.suspend_regs	= exynos5x_g3d_suspend_regs,
+	.nr_suspend_regs = ARRAY_SIZE(exynos5x_g3d_suspend_regs),
+	.pd_name	= "G3D",
+};
+
 static const struct exynos5_subcmu_info exynos5x_mfc_subcmu = {
 	.div_clks	= exynos5x_mfc_div_clks,
 	.nr_div_clks	= ARRAY_SIZE(exynos5x_mfc_div_clks),
@@ -1351,6 +1372,7 @@ static const struct exynos5_subcmu_info exynos5800_mau_subcmu = {
 static const struct exynos5_subcmu_info *exynos5x_subcmus[] = {
 	&exynos5x_disp_subcmu,
 	&exynos5x_gsc_subcmu,
+	&exynos5x_g3d_subcmu,
 	&exynos5x_mfc_subcmu,
 	&exynos5x_mscl_subcmu,
 };
@@ -1358,6 +1380,7 @@ static const struct exynos5_subcmu_info *exynos5x_subcmus[] = {
 static const struct exynos5_subcmu_info *exynos5800_subcmus[] = {
 	&exynos5x_disp_subcmu,
 	&exynos5x_gsc_subcmu,
+	&exynos5x_g3d_subcmu,
 	&exynos5x_mfc_subcmu,
 	&exynos5x_mscl_subcmu,
 	&exynos5800_mau_subcmu,
diff --git a/drivers/clk/samsung/clk-exynos5433.c b/drivers/clk/samsung/clk-exynos5433.c
index 7824c2ba3d8e..4b1aa9382ad2 100644
--- a/drivers/clk/samsung/clk-exynos5433.c
+++ b/drivers/clk/samsung/clk-exynos5433.c
@@ -13,6 +13,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/slab.h>
 
 #include <dt-bindings/clock/exynos5433.h>
 
@@ -5584,6 +5585,8 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev)
 
 	data->clk_save = samsung_clk_alloc_reg_dump(info->clk_regs,
 						    info->nr_clk_regs);
+	if (!data->clk_save)
+		return -ENOMEM;
 	data->nr_clk_save = info->nr_clk_regs;
 	data->clk_suspend = info->suspend_regs;
 	data->nr_clk_suspend = info->nr_suspend_regs;
@@ -5592,12 +5595,19 @@ static int __init exynos5433_cmu_probe(struct platform_device *pdev)
 	if (data->nr_pclks > 0) {
 		data->pclks = devm_kcalloc(dev, sizeof(struct clk *),
 					   data->nr_pclks, GFP_KERNEL);
-
+		if (!data->pclks) {
+			kfree(data->clk_save);
+			return -ENOMEM;
+		}
 		for (i = 0; i < data->nr_pclks; i++) {
 			struct clk *clk = of_clk_get(dev->of_node, i);
 
-			if (IS_ERR(clk))
+			if (IS_ERR(clk)) {
+				kfree(data->clk_save);
+				while (--i >= 0)
+					clk_put(data->pclks[i]);
 				return PTR_ERR(clk);
+			}
 			data->pclks[i] = clk;
 		}
 	}
diff --git a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c
index dcac1391767f..ef29582676f6 100644
--- a/drivers/clk/sunxi-ng/ccu-sun9i-a80.c
+++ b/drivers/clk/sunxi-ng/ccu-sun9i-a80.c
@@ -1224,7 +1224,7 @@ static int sun9i_a80_ccu_probe(struct platform_device *pdev)
 
 	/* Enforce d1 = 0, d2 = 0 for Audio PLL */
 	val = readl(reg + SUN9I_A80_PLL_AUDIO_REG);
-	val &= (BIT(16) & BIT(18));
+	val &= ~(BIT(16) | BIT(18));
 	writel(val, reg + SUN9I_A80_PLL_AUDIO_REG);
 
 	/* Enforce P = 1 for both CPU cluster PLLs */
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index d3a43381a792..27201fd26e44 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -1080,8 +1080,8 @@ static struct clk ** __init sunxi_divs_clk_setup(struct device_node *node,
 						 rate_hw, rate_ops,
 						 gate_hw, &clk_gate_ops,
 						 clkflags |
-						 data->div[i].critical ?
-							CLK_IS_CRITICAL : 0);
+						 (data->div[i].critical ?
+							CLK_IS_CRITICAL : 0));
 
 		WARN_ON(IS_ERR(clk_data->clks[i]));
 	}
diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
index a01ca9395179..f65e16c4f3c4 100644
--- a/drivers/clk/ti/clk-dra7-atl.c
+++ b/drivers/clk/ti/clk-dra7-atl.c
@@ -174,7 +174,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node)
 	struct clk_init_data init = { NULL };
 	const char **parent_names = NULL;
 	struct clk *clk;
-	int ret;
 
 	clk_hw = kzalloc(sizeof(*clk_hw), GFP_KERNEL);
 	if (!clk_hw) {
@@ -207,11 +206,6 @@ static void __init of_dra7_atl_clock_setup(struct device_node *node)
 	clk = ti_clk_register(NULL, &clk_hw->hw, node->name);
 
 	if (!IS_ERR(clk)) {
-		ret = ti_clk_add_alias(NULL, clk, node->name);
-		if (ret) {
-			clk_unregister(clk);
-			goto cleanup;
-		}
 		of_clk_add_provider(node, of_clk_src_simple_get, clk);
 		kfree(parent_names);
 		return;
diff --git a/drivers/clk/ti/clkctrl.c b/drivers/clk/ti/clkctrl.c
index 975995eea15c..b0c0690a5a12 100644
--- a/drivers/clk/ti/clkctrl.c
+++ b/drivers/clk/ti/clkctrl.c
@@ -100,11 +100,12 @@ static bool _omap4_is_timeout(union omap4_timeout *time, u32 timeout)
 	 * can be from a timer that requires pm_runtime access, which
 	 * will eventually bring us here with timekeeping_suspended,
 	 * during both suspend entry and resume paths. This happens
-	 * at least on am43xx platform.
+	 * at least on am43xx platform. Account for flakeyness
+	 * with udelay() by multiplying the timeout value by 2.
 	 */
 	if (unlikely(_early_timeout || timekeeping_suspended)) {
 		if (time->cycles++ < timeout) {
-			udelay(1);
+			udelay(1 * 2);
 			return false;
 		}
 	} else {
diff --git a/drivers/clocksource/sh_mtu2.c b/drivers/clocksource/sh_mtu2.c
index 354b27d14a19..62812f80b5cc 100644
--- a/drivers/clocksource/sh_mtu2.c
+++ b/drivers/clocksource/sh_mtu2.c
@@ -328,12 +328,13 @@ static int sh_mtu2_register(struct sh_mtu2_channel *ch, const char *name)
 	return 0;
 }
 
+static const unsigned int sh_mtu2_channel_offsets[] = {
+	0x300, 0x380, 0x000,
+};
+
 static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 				 struct sh_mtu2_device *mtu)
 {
-	static const unsigned int channel_offsets[] = {
-		0x300, 0x380, 0x000,
-	};
 	char name[6];
 	int irq;
 	int ret;
@@ -356,7 +357,7 @@ static int sh_mtu2_setup_channel(struct sh_mtu2_channel *ch, unsigned int index,
 		return ret;
 	}
 
-	ch->base = mtu->mapbase + channel_offsets[index];
+	ch->base = mtu->mapbase + sh_mtu2_channel_offsets[index];
 	ch->index = index;
 
 	return sh_mtu2_register(ch, dev_name(&mtu->pdev->dev));
@@ -408,7 +409,12 @@ static int sh_mtu2_setup(struct sh_mtu2_device *mtu,
 	}
 
 	/* Allocate and setup the channels. */
-	mtu->num_channels = 3;
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_unmap;
+
+	mtu->num_channels = min_t(unsigned int, ret,
+				  ARRAY_SIZE(sh_mtu2_channel_offsets));
 
 	mtu->channels = kcalloc(mtu->num_channels, sizeof(*mtu->channels),
 				GFP_KERNEL);
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
index a562f491b0f8..9318edcd8963 100644
--- a/drivers/clocksource/timer-mediatek.c
+++ b/drivers/clocksource/timer-mediatek.c
@@ -268,15 +268,12 @@ static int __init mtk_syst_init(struct device_node *node)
 
 	ret = timer_of_init(node, &to);
 	if (ret)
-		goto err;
+		return ret;
 
 	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
 					TIMER_SYNC_TICKS, 0xffffffff);
 
 	return 0;
-err:
-	timer_of_cleanup(&to);
-	return ret;
 }
 
 static int __init mtk_gpt_init(struct device_node *node)
@@ -293,7 +290,7 @@ static int __init mtk_gpt_init(struct device_node *node)
 
 	ret = timer_of_init(node, &to);
 	if (ret)
-		goto err;
+		return ret;
 
 	/* Configure clock source */
 	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
@@ -311,9 +308,6 @@ static int __init mtk_gpt_init(struct device_node *node)
 	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
 
 	return 0;
-err:
-	timer_of_cleanup(&to);
-	return ret;
 }
 TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
 TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index bffc11b87247..48a224a6b178 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -720,7 +720,7 @@ static ssize_t store_##file_name					\
 	if (ret != 1)							\
 		return -EINVAL;						\
 									\
-	ret = dev_pm_qos_update_request(policy->object##_freq_req, val);\
+	ret = freq_qos_update_request(policy->object##_freq_req, val);\
 	return ret >= 0 ? count : ret;					\
 }
 
@@ -1202,19 +1202,21 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 		goto err_free_real_cpus;
 	}
 
+	freq_constraints_init(&policy->constraints);
+
 	policy->nb_min.notifier_call = cpufreq_notifier_min;
 	policy->nb_max.notifier_call = cpufreq_notifier_max;
 
-	ret = dev_pm_qos_add_notifier(dev, &policy->nb_min,
-				      DEV_PM_QOS_MIN_FREQUENCY);
+	ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MIN,
+				    &policy->nb_min);
 	if (ret) {
 		dev_err(dev, "Failed to register MIN QoS notifier: %d (%*pbl)\n",
 			ret, cpumask_pr_args(policy->cpus));
 		goto err_kobj_remove;
 	}
 
-	ret = dev_pm_qos_add_notifier(dev, &policy->nb_max,
-				      DEV_PM_QOS_MAX_FREQUENCY);
+	ret = freq_qos_add_notifier(&policy->constraints, FREQ_QOS_MAX,
+				    &policy->nb_max);
 	if (ret) {
 		dev_err(dev, "Failed to register MAX QoS notifier: %d (%*pbl)\n",
 			ret, cpumask_pr_args(policy->cpus));
@@ -1232,8 +1234,8 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	return policy;
 
 err_min_qos_notifier:
-	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
-				   DEV_PM_QOS_MIN_FREQUENCY);
+	freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN,
+				 &policy->nb_min);
 err_kobj_remove:
 	cpufreq_policy_put_kobj(policy);
 err_free_real_cpus:
@@ -1250,7 +1252,6 @@ err_free_policy:
 
 static void cpufreq_policy_free(struct cpufreq_policy *policy)
 {
-	struct device *dev = get_cpu_device(policy->cpu);
 	unsigned long flags;
 	int cpu;
 
@@ -1262,10 +1263,13 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 		per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	dev_pm_qos_remove_notifier(dev, &policy->nb_max,
-				   DEV_PM_QOS_MAX_FREQUENCY);
-	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
-				   DEV_PM_QOS_MIN_FREQUENCY);
+	freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MAX,
+				 &policy->nb_max);
+	freq_qos_remove_notifier(&policy->constraints, FREQ_QOS_MIN,
+				 &policy->nb_min);
+
+	/* Cancel any pending policy->update work before freeing the policy. */
+	cancel_work_sync(&policy->update);
 
 	if (policy->max_freq_req) {
 		/*
@@ -1274,10 +1278,10 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 		 */
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 					     CPUFREQ_REMOVE_POLICY, policy);
-		dev_pm_qos_remove_request(policy->max_freq_req);
+		freq_qos_remove_request(policy->max_freq_req);
 	}
 
-	dev_pm_qos_remove_request(policy->min_freq_req);
+	freq_qos_remove_request(policy->min_freq_req);
 	kfree(policy->min_freq_req);
 
 	cpufreq_policy_put_kobj(policy);
@@ -1357,8 +1361,6 @@ static int cpufreq_online(unsigned int cpu)
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
 	if (new_policy) {
-		struct device *dev = get_cpu_device(cpu);
-
 		for_each_cpu(j, policy->related_cpus) {
 			per_cpu(cpufreq_cpu_data, j) = policy;
 			add_cpu_dev_symlink(policy, j);
@@ -1369,36 +1371,31 @@ static int cpufreq_online(unsigned int cpu)
 		if (!policy->min_freq_req)
 			goto out_destroy_policy;
 
-		ret = dev_pm_qos_add_request(dev, policy->min_freq_req,
-					     DEV_PM_QOS_MIN_FREQUENCY,
-					     policy->min);
+		ret = freq_qos_add_request(&policy->constraints,
+					   policy->min_freq_req, FREQ_QOS_MIN,
+					   policy->min);
 		if (ret < 0) {
 			/*
-			 * So we don't call dev_pm_qos_remove_request() for an
+			 * So we don't call freq_qos_remove_request() for an
 			 * uninitialized request.
 			 */
 			kfree(policy->min_freq_req);
 			policy->min_freq_req = NULL;
-
-			dev_err(dev, "Failed to add min-freq constraint (%d)\n",
-				ret);
 			goto out_destroy_policy;
 		}
 
 		/*
 		 * This must be initialized right here to avoid calling
-		 * dev_pm_qos_remove_request() on uninitialized request in case
+		 * freq_qos_remove_request() on uninitialized request in case
 		 * of errors.
 		 */
 		policy->max_freq_req = policy->min_freq_req + 1;
 
-		ret = dev_pm_qos_add_request(dev, policy->max_freq_req,
-					     DEV_PM_QOS_MAX_FREQUENCY,
-					     policy->max);
+		ret = freq_qos_add_request(&policy->constraints,
+					   policy->max_freq_req, FREQ_QOS_MAX,
+					   policy->max);
 		if (ret < 0) {
 			policy->max_freq_req = NULL;
-			dev_err(dev, "Failed to add max-freq constraint (%d)\n",
-				ret);
 			goto out_destroy_policy;
 		}
 
@@ -2374,7 +2371,6 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 		       struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
-	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	int ret;
 
 	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
@@ -2386,8 +2382,8 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	 * PM QoS framework collects all the requests from users and provide us
 	 * the final aggregated value here.
 	 */
-	new_policy->min = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MIN_FREQUENCY);
-	new_policy->max = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MAX_FREQUENCY);
+	new_policy->min = freq_qos_read_value(&policy->constraints, FREQ_QOS_MIN);
+	new_policy->max = freq_qos_read_value(&policy->constraints, FREQ_QOS_MAX);
 
 	/* verify the cpu speed can be set within this limit */
 	ret = cpufreq_driver->verify(new_policy);
@@ -2518,7 +2514,7 @@ static int cpufreq_boost_set_sw(int state)
 			break;
 		}
 
-		ret = dev_pm_qos_update_request(policy->max_freq_req, policy->max);
+		ret = freq_qos_update_request(policy->max_freq_req, policy->max);
 		if (ret < 0)
 			break;
 	}
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 9f02de9a1b47..8ab31702cf6a 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -847,11 +847,9 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	value |= HWP_MAX_PERF(min_perf);
 	value |= HWP_MIN_PERF(min_perf);
 
-	/* Set EPP/EPB to min */
+	/* Set EPP to min */
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
-	else
-		intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE);
 
 	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 }
@@ -1088,10 +1086,10 @@ static ssize_t store_no_turbo(struct kobject *a, struct kobj_attribute *b,
 
 static struct cpufreq_driver intel_pstate;
 
-static void update_qos_request(enum dev_pm_qos_req_type type)
+static void update_qos_request(enum freq_qos_req_type type)
 {
 	int max_state, turbo_max, freq, i, perf_pct;
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	struct cpufreq_policy *policy;
 
 	for_each_possible_cpu(i) {
@@ -1112,7 +1110,7 @@ static void update_qos_request(enum dev_pm_qos_req_type type)
 		else
 			turbo_max = cpu->pstate.turbo_pstate;
 
-		if (type == DEV_PM_QOS_MIN_FREQUENCY) {
+		if (type == FREQ_QOS_MIN) {
 			perf_pct = global.min_perf_pct;
 		} else {
 			req++;
@@ -1122,7 +1120,7 @@ static void update_qos_request(enum dev_pm_qos_req_type type)
 		freq = DIV_ROUND_UP(turbo_max * perf_pct, 100);
 		freq *= cpu->pstate.scaling;
 
-		if (dev_pm_qos_update_request(req, freq) < 0)
+		if (freq_qos_update_request(req, freq) < 0)
 			pr_warn("Failed to update freq constraint: CPU%d\n", i);
 	}
 }
@@ -1153,7 +1151,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct kobj_attribute *b,
 	if (intel_pstate_driver == &intel_pstate)
 		intel_pstate_update_policies();
 	else
-		update_qos_request(DEV_PM_QOS_MAX_FREQUENCY);
+		update_qos_request(FREQ_QOS_MAX);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -1187,7 +1185,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct kobj_attribute *b,
 	if (intel_pstate_driver == &intel_pstate)
 		intel_pstate_update_policies();
 	else
-		update_qos_request(DEV_PM_QOS_MIN_FREQUENCY);
+		update_qos_request(FREQ_QOS_MIN);
 
 	mutex_unlock(&intel_pstate_driver_lock);
 
@@ -2381,7 +2379,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
 	int max_state, turbo_max, min_freq, max_freq, ret;
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	struct cpudata *cpu;
 	struct device *dev;
 
@@ -2416,15 +2414,15 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	max_freq = DIV_ROUND_UP(turbo_max * global.max_perf_pct, 100);
 	max_freq *= cpu->pstate.scaling;
 
-	ret = dev_pm_qos_add_request(dev, req, DEV_PM_QOS_MIN_FREQUENCY,
-				     min_freq);
+	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MIN,
+				   min_freq);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add min-freq constraint (%d)\n", ret);
 		goto free_req;
 	}
 
-	ret = dev_pm_qos_add_request(dev, req + 1, DEV_PM_QOS_MAX_FREQUENCY,
-				     max_freq);
+	ret = freq_qos_add_request(&policy->constraints, req + 1, FREQ_QOS_MAX,
+				   max_freq);
 	if (ret < 0) {
 		dev_err(dev, "Failed to add max-freq constraint (%d)\n", ret);
 		goto remove_min_req;
@@ -2435,7 +2433,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return 0;
 
 remove_min_req:
-	dev_pm_qos_remove_request(req);
+	freq_qos_remove_request(req);
 free_req:
 	kfree(req);
 pstate_exit:
@@ -2446,12 +2444,12 @@ pstate_exit:
 
 static int intel_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 
 	req = policy->driver_data;
 
-	dev_pm_qos_remove_request(req + 1);
-	dev_pm_qos_remove_request(req);
+	freq_qos_remove_request(req + 1);
+	freq_qos_remove_request(req);
 	kfree(req);
 
 	return intel_pstate_cpu_exit(policy);
diff --git a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index bc9dd30395c4..037fe23bc6ed 100644
--- a/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -65,7 +65,7 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_set_pmode_pmi);
 static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg)
 {
 	struct cpufreq_policy *policy;
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	u8 node, slow_mode;
 	int cpu, ret;
 
@@ -86,7 +86,7 @@ static void cbe_cpufreq_handle_pmi(pmi_message_t pmi_msg)
 
 	req = policy->driver_data;
 
-	ret = dev_pm_qos_update_request(req,
+	ret = freq_qos_update_request(req,
 			policy->freq_table[slow_mode].frequency);
 	if (ret < 0)
 		pr_warn("Failed to update freq constraint: %d\n", ret);
@@ -103,7 +103,7 @@ static struct pmi_handler cbe_pmi_handler = {
 
 void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy)
 {
-	struct dev_pm_qos_request *req;
+	struct freq_qos_request *req;
 	int ret;
 
 	if (!cbe_cpufreq_has_pmi)
@@ -113,9 +113,8 @@ void cbe_cpufreq_pmi_policy_init(struct cpufreq_policy *policy)
 	if (!req)
 		return;
 
-	ret = dev_pm_qos_add_request(get_cpu_device(policy->cpu), req,
-				     DEV_PM_QOS_MAX_FREQUENCY,
-				     policy->freq_table[0].frequency);
+	ret = freq_qos_add_request(&policy->constraints, req, FREQ_QOS_MAX,
+				   policy->freq_table[0].frequency);
 	if (ret < 0) {
 		pr_err("Failed to add freq constraint (%d)\n", ret);
 		kfree(req);
@@ -128,10 +127,10 @@ EXPORT_SYMBOL_GPL(cbe_cpufreq_pmi_policy_init);
 
 void cbe_cpufreq_pmi_policy_exit(struct cpufreq_policy *policy)
 {
-	struct dev_pm_qos_request *req = policy->driver_data;
+	struct freq_qos_request *req = policy->driver_data;
 
 	if (cbe_cpufreq_has_pmi) {
-		dev_pm_qos_remove_request(req);
+		freq_qos_remove_request(req);
 		kfree(req);
 	}
 }
diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c
index 932390b028f1..b0ce9bc78113 100644
--- a/drivers/cpuidle/cpuidle-haltpoll.c
+++ b/drivers/cpuidle/cpuidle-haltpoll.c
@@ -95,6 +95,10 @@ static int __init haltpoll_init(void)
 	int ret;
 	struct cpuidle_driver *drv = &haltpoll_driver;
 
+	/* Do not load haltpoll if idle= is passed */
+	if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+		return -ENODEV;
+
 	cpuidle_poll_state_init(drv);
 
 	if (!kvm_para_available() ||
diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 774d991d7cca..aca75237bbcf 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1297,7 +1297,7 @@ static void make_established(struct sock *sk, u32 snd_isn, unsigned int opt)
 	tp->write_seq = snd_isn;
 	tp->snd_nxt = snd_isn;
 	tp->snd_una = snd_isn;
-	inet_sk(sk)->inet_id = tp->write_seq ^ jiffies;
+	inet_sk(sk)->inet_id = prandom_u32();
 	assign_rxopt(sk, opt);
 
 	if (tp->rcv_wnd > (RCV_BUFSIZ_M << 10))
diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c
index 0891ab829b1b..98bc5a4cd5e7 100644
--- a/drivers/crypto/chelsio/chtls/chtls_io.c
+++ b/drivers/crypto/chelsio/chtls/chtls_io.c
@@ -1702,7 +1702,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		return peekmsg(sk, msg, len, nonblock, flags);
 
 	if (sk_can_busy_loop(sk) &&
-	    skb_queue_empty(&sk->sk_receive_queue) &&
+	    skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    sk->sk_state == TCP_ESTABLISHED)
 		sk_busy_loop(sk, nonblock);
 
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 433d91d710e4..d377b4ca66bf 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -45,10 +45,10 @@ static char *dmabuffs_dname(struct dentry *dentry, char *buffer, int buflen)
 	size_t ret = 0;
 
 	dmabuf = dentry->d_fsdata;
-	mutex_lock(&dmabuf->lock);
+	dma_resv_lock(dmabuf->resv, NULL);
 	if (dmabuf->name)
 		ret = strlcpy(name, dmabuf->name, DMA_BUF_NAME_LEN);
-	mutex_unlock(&dmabuf->lock);
+	dma_resv_unlock(dmabuf->resv);
 
 	return dynamic_dname(dentry, buffer, buflen, "/%s:%s",
 			     dentry->d_name.name, ret > 0 ? name : "");
@@ -334,7 +334,7 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf)
 	if (IS_ERR(name))
 		return PTR_ERR(name);
 
-	mutex_lock(&dmabuf->lock);
+	dma_resv_lock(dmabuf->resv, NULL);
 	if (!list_empty(&dmabuf->attachments)) {
 		ret = -EBUSY;
 		kfree(name);
@@ -344,7 +344,7 @@ static long dma_buf_set_name(struct dma_buf *dmabuf, const char __user *buf)
 	dmabuf->name = name;
 
 out_unlock:
-	mutex_unlock(&dmabuf->lock);
+	dma_resv_unlock(dmabuf->resv);
 	return ret;
 }
 
@@ -403,10 +403,10 @@ static void dma_buf_show_fdinfo(struct seq_file *m, struct file *file)
 	/* Don't count the temporary reference taken inside procfs seq_show */
 	seq_printf(m, "count:\t%ld\n", file_count(dmabuf->file) - 1);
 	seq_printf(m, "exp_name:\t%s\n", dmabuf->exp_name);
-	mutex_lock(&dmabuf->lock);
+	dma_resv_lock(dmabuf->resv, NULL);
 	if (dmabuf->name)
 		seq_printf(m, "name:\t%s\n", dmabuf->name);
-	mutex_unlock(&dmabuf->lock);
+	dma_resv_unlock(dmabuf->resv);
 }
 
 static const struct file_operations dma_buf_fops = {
@@ -525,6 +525,10 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (WARN_ON(exp_info->ops->cache_sgt_mapping &&
+		    exp_info->ops->dynamic_mapping))
+		return ERR_PTR(-EINVAL);
+
 	if (!try_module_get(exp_info->owner))
 		return ERR_PTR(-ENOENT);
 
@@ -645,10 +649,11 @@ void dma_buf_put(struct dma_buf *dmabuf)
 EXPORT_SYMBOL_GPL(dma_buf_put);
 
 /**
- * dma_buf_attach - Add the device to dma_buf's attachments list; optionally,
+ * dma_buf_dynamic_attach - Add the device to dma_buf's attachments list; optionally,
  * calls attach() of dma_buf_ops to allow device-specific attach functionality
- * @dmabuf:	[in]	buffer to attach device to.
- * @dev:	[in]	device to be attached.
+ * @dmabuf:		[in]	buffer to attach device to.
+ * @dev:		[in]	device to be attached.
+ * @dynamic_mapping:	[in]	calling convention for map/unmap
  *
  * Returns struct dma_buf_attachment pointer for this attachment. Attachments
  * must be cleaned up by calling dma_buf_detach().
@@ -662,8 +667,9 @@ EXPORT_SYMBOL_GPL(dma_buf_put);
  * accessible to @dev, and cannot be moved to a more suitable place. This is
  * indicated with the error code -EBUSY.
  */
-struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
-					  struct device *dev)
+struct dma_buf_attachment *
+dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
+		       bool dynamic_mapping)
 {
 	struct dma_buf_attachment *attach;
 	int ret;
@@ -677,25 +683,69 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 
 	attach->dev = dev;
 	attach->dmabuf = dmabuf;
-
-	mutex_lock(&dmabuf->lock);
+	attach->dynamic_mapping = dynamic_mapping;
 
 	if (dmabuf->ops->attach) {
 		ret = dmabuf->ops->attach(dmabuf, attach);
 		if (ret)
 			goto err_attach;
 	}
+	dma_resv_lock(dmabuf->resv, NULL);
 	list_add(&attach->node, &dmabuf->attachments);
+	dma_resv_unlock(dmabuf->resv);
 
-	mutex_unlock(&dmabuf->lock);
+	/* When either the importer or the exporter can't handle dynamic
+	 * mappings we cache the mapping here to avoid issues with the
+	 * reservation object lock.
+	 */
+	if (dma_buf_attachment_is_dynamic(attach) !=
+	    dma_buf_is_dynamic(dmabuf)) {
+		struct sg_table *sgt;
+
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			dma_resv_lock(attach->dmabuf->resv, NULL);
+
+		sgt = dmabuf->ops->map_dma_buf(attach, DMA_BIDIRECTIONAL);
+		if (!sgt)
+			sgt = ERR_PTR(-ENOMEM);
+		if (IS_ERR(sgt)) {
+			ret = PTR_ERR(sgt);
+			goto err_unlock;
+		}
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			dma_resv_unlock(attach->dmabuf->resv);
+		attach->sgt = sgt;
+		attach->dir = DMA_BIDIRECTIONAL;
+	}
 
 	return attach;
 
 err_attach:
 	kfree(attach);
-	mutex_unlock(&dmabuf->lock);
+	return ERR_PTR(ret);
+
+err_unlock:
+	if (dma_buf_is_dynamic(attach->dmabuf))
+		dma_resv_unlock(attach->dmabuf->resv);
+
+	dma_buf_detach(dmabuf, attach);
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_GPL(dma_buf_dynamic_attach);
+
+/**
+ * dma_buf_attach - Wrapper for dma_buf_dynamic_attach
+ * @dmabuf:	[in]	buffer to attach device to.
+ * @dev:	[in]	device to be attached.
+ *
+ * Wrapper to call dma_buf_dynamic_attach() for drivers which still use a static
+ * mapping.
+ */
+struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
+					  struct device *dev)
+{
+	return dma_buf_dynamic_attach(dmabuf, dev, false);
+}
 EXPORT_SYMBOL_GPL(dma_buf_attach);
 
 /**
@@ -711,15 +761,22 @@ void dma_buf_detach(struct dma_buf *dmabuf, struct dma_buf_attachment *attach)
 	if (WARN_ON(!dmabuf || !attach))
 		return;
 
-	if (attach->sgt)
+	if (attach->sgt) {
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			dma_resv_lock(attach->dmabuf->resv, NULL);
+
 		dmabuf->ops->unmap_dma_buf(attach, attach->sgt, attach->dir);
 
-	mutex_lock(&dmabuf->lock);
+		if (dma_buf_is_dynamic(attach->dmabuf))
+			dma_resv_unlock(attach->dmabuf->resv);
+	}
+
+	dma_resv_lock(dmabuf->resv, NULL);
 	list_del(&attach->node);
+	dma_resv_unlock(dmabuf->resv);
 	if (dmabuf->ops->detach)
 		dmabuf->ops->detach(dmabuf, attach);
 
-	mutex_unlock(&dmabuf->lock);
 	kfree(attach);
 }
 EXPORT_SYMBOL_GPL(dma_buf_detach);
@@ -749,6 +806,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 	if (WARN_ON(!attach || !attach->dmabuf))
 		return ERR_PTR(-EINVAL);
 
+	if (dma_buf_attachment_is_dynamic(attach))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	if (attach->sgt) {
 		/*
 		 * Two mappings with different directions for the same
@@ -761,6 +821,9 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *attach,
 		return attach->sgt;
 	}
 
+	if (dma_buf_is_dynamic(attach->dmabuf))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	sg_table = attach->dmabuf->ops->map_dma_buf(attach, direction);
 	if (!sg_table)
 		sg_table = ERR_PTR(-ENOMEM);
@@ -793,9 +856,15 @@ void dma_buf_unmap_attachment(struct dma_buf_attachment *attach,
 	if (WARN_ON(!attach || !attach->dmabuf || !sg_table))
 		return;
 
+	if (dma_buf_attachment_is_dynamic(attach))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	if (attach->sgt == sg_table)
 		return;
 
+	if (dma_buf_is_dynamic(attach->dmabuf))
+		dma_resv_assert_held(attach->dmabuf->resv);
+
 	attach->dmabuf->ops->unmap_dma_buf(attach, sg_table, direction);
 }
 EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
@@ -1171,13 +1240,10 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 		   "size", "flags", "mode", "count", "ino");
 
 	list_for_each_entry(buf_obj, &db_list.head, list_node) {
-		ret = mutex_lock_interruptible(&buf_obj->lock);
 
-		if (ret) {
-			seq_puts(s,
-				 "\tERROR locking buffer object: skipping\n");
-			continue;
-		}
+		ret = dma_resv_lock_interruptible(buf_obj->resv, NULL);
+		if (ret)
+			goto error_unlock;
 
 		seq_printf(s, "%08zu\t%08x\t%08x\t%08ld\t%s\t%08lu\t%s\n",
 				buf_obj->size,
@@ -1223,19 +1289,23 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 			seq_printf(s, "\t%s\n", dev_name(attach_obj->dev));
 			attach_count++;
 		}
+		dma_resv_unlock(buf_obj->resv);
 
 		seq_printf(s, "Total %d devices attached\n\n",
 				attach_count);
 
 		count++;
 		size += buf_obj->size;
-		mutex_unlock(&buf_obj->lock);
 	}
 
 	seq_printf(s, "\nTotal %d objects, %zu bytes\n", count, size);
 
 	mutex_unlock(&db_list.lock);
 	return 0;
+
+error_unlock:
+	mutex_unlock(&db_list.lock);
+	return ret;
 }
 
 DEFINE_SHOW_ATTRIBUTE(dma_buf_debug);
diff --git a/drivers/dma/imx-sdma.c b/drivers/dma/imx-sdma.c
index 9ba74ab7e912..c27e206a764c 100644
--- a/drivers/dma/imx-sdma.c
+++ b/drivers/dma/imx-sdma.c
@@ -1707,6 +1707,14 @@ static void sdma_add_scripts(struct sdma_engine *sdma,
 	if (!sdma->script_number)
 		sdma->script_number = SDMA_SCRIPT_ADDRS_ARRAY_SIZE_V1;
 
+	if (sdma->script_number > sizeof(struct sdma_script_start_addrs)
+				  / sizeof(s32)) {
+		dev_err(sdma->dev,
+			"SDMA script number %d not match with firmware.\n",
+			sdma->script_number);
+		return;
+	}
+
 	for (i = 0; i < sdma->script_number; i++)
 		if (addr_arr[i] > 0)
 			saddr_arr[i] = addr_arr[i];
diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index 8e90a405939d..ef73f65224b1 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -694,6 +694,25 @@ static int bam_dma_terminate_all(struct dma_chan *chan)
 
 	/* remove all transactions, including active transaction */
 	spin_lock_irqsave(&bchan->vc.lock, flag);
+	/*
+	 * If we have transactions queued, then some might be committed to the
+	 * hardware in the desc fifo.  The only way to reset the desc fifo is
+	 * to do a hardware reset (either by pipe or the entire block).
+	 * bam_chan_init_hw() will trigger a pipe reset, and also reinit the
+	 * pipe.  If the pipe is left disabled (default state after pipe reset)
+	 * and is accessed by a connected hardware engine, a fatal error in
+	 * the BAM will occur.  There is a small window where this could happen
+	 * with bam_chan_init_hw(), but it is assumed that the caller has
+	 * stopped activity on any attached hardware engine.  Make sure to do
+	 * this first so that the BAM hardware doesn't cause memory corruption
+	 * by accessing freed resources.
+	 */
+	if (!list_empty(&bchan->desc_list)) {
+		async_desc = list_first_entry(&bchan->desc_list,
+					      struct bam_async_desc, desc_node);
+		bam_chan_init_hw(bchan, async_desc->dir);
+	}
+
 	list_for_each_entry_safe(async_desc, tmp,
 				 &bchan->desc_list, desc_node) {
 		list_add(&async_desc->vd.node, &bchan->vc.desc_issued);
diff --git a/drivers/dma/sprd-dma.c b/drivers/dma/sprd-dma.c
index 525dc7338fe3..8546ad034720 100644
--- a/drivers/dma/sprd-dma.c
+++ b/drivers/dma/sprd-dma.c
@@ -134,6 +134,10 @@
 #define SPRD_DMA_SRC_TRSF_STEP_OFFSET	0
 #define SPRD_DMA_TRSF_STEP_MASK		GENMASK(15, 0)
 
+/* SPRD DMA_SRC_BLK_STEP register definition */
+#define SPRD_DMA_LLIST_HIGH_MASK	GENMASK(31, 28)
+#define SPRD_DMA_LLIST_HIGH_SHIFT	28
+
 /* define DMA channel mode & trigger mode mask */
 #define SPRD_DMA_CHN_MODE_MASK		GENMASK(7, 0)
 #define SPRD_DMA_TRG_MODE_MASK		GENMASK(7, 0)
@@ -208,6 +212,7 @@ struct sprd_dma_dev {
 	struct sprd_dma_chn	channels[0];
 };
 
+static void sprd_dma_free_desc(struct virt_dma_desc *vd);
 static bool sprd_dma_filter_fn(struct dma_chan *chan, void *param);
 static struct of_dma_filter_info sprd_dma_info = {
 	.filter_fn = sprd_dma_filter_fn,
@@ -609,12 +614,19 @@ static int sprd_dma_alloc_chan_resources(struct dma_chan *chan)
 static void sprd_dma_free_chan_resources(struct dma_chan *chan)
 {
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	struct virt_dma_desc *cur_vd = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&schan->vc.lock, flags);
+	if (schan->cur_desc)
+		cur_vd = &schan->cur_desc->vd;
+
 	sprd_dma_stop(schan);
 	spin_unlock_irqrestore(&schan->vc.lock, flags);
 
+	if (cur_vd)
+		sprd_dma_free_desc(cur_vd);
+
 	vchan_free_chan_resources(&schan->vc);
 	pm_runtime_put(chan->device->dev);
 }
@@ -717,6 +729,7 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 	u32 int_mode = flags & SPRD_DMA_INT_MASK;
 	int src_datawidth, dst_datawidth, src_step, dst_step;
 	u32 temp, fix_mode = 0, fix_en = 0;
+	phys_addr_t llist_ptr;
 
 	if (dir == DMA_MEM_TO_DEV) {
 		src_step = sprd_dma_get_step(slave_cfg->src_addr_width);
@@ -814,13 +827,16 @@ static int sprd_dma_fill_desc(struct dma_chan *chan,
 		 * Set the link-list pointer point to next link-list
 		 * configuration's physical address.
 		 */
-		hw->llist_ptr = schan->linklist.phy_addr + temp;
+		llist_ptr = schan->linklist.phy_addr + temp;
+		hw->llist_ptr = lower_32_bits(llist_ptr);
+		hw->src_blk_step = (upper_32_bits(llist_ptr) << SPRD_DMA_LLIST_HIGH_SHIFT) &
+			SPRD_DMA_LLIST_HIGH_MASK;
 	} else {
 		hw->llist_ptr = 0;
+		hw->src_blk_step = 0;
 	}
 
 	hw->frg_step = 0;
-	hw->src_blk_step = 0;
 	hw->des_blk_step = 0;
 	return 0;
 }
@@ -1023,15 +1039,22 @@ static int sprd_dma_resume(struct dma_chan *chan)
 static int sprd_dma_terminate_all(struct dma_chan *chan)
 {
 	struct sprd_dma_chn *schan = to_sprd_dma_chan(chan);
+	struct virt_dma_desc *cur_vd = NULL;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&schan->vc.lock, flags);
+	if (schan->cur_desc)
+		cur_vd = &schan->cur_desc->vd;
+
 	sprd_dma_stop(schan);
 
 	vchan_get_all_descriptors(&schan->vc, &head);
 	spin_unlock_irqrestore(&schan->vc.lock, flags);
 
+	if (cur_vd)
+		sprd_dma_free_desc(cur_vd);
+
 	vchan_dma_desc_free_list(&schan->vc, &head);
 	return 0;
 }
diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 5f8adf5c1f20..6e1268552f74 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -40,6 +40,7 @@
 #define ADMA_CH_CONFIG_MAX_BURST_SIZE                   16
 #define ADMA_CH_CONFIG_WEIGHT_FOR_WRR(val)		((val) & 0xf)
 #define ADMA_CH_CONFIG_MAX_BUFS				8
+#define TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(reqs)	(reqs << 4)
 
 #define ADMA_CH_FIFO_CTRL				0x2c
 #define TEGRA210_ADMA_CH_FIFO_CTRL_TXSIZE(val)		(((val) & 0xf) << 8)
@@ -77,6 +78,7 @@ struct tegra_adma;
  * @ch_req_tx_shift: Register offset for AHUB transmit channel select.
  * @ch_req_rx_shift: Register offset for AHUB receive channel select.
  * @ch_base_offset: Register offset of DMA channel registers.
+ * @has_outstanding_reqs: If DMA channel can have outstanding requests.
  * @ch_fifo_ctrl: Default value for channel FIFO CTRL register.
  * @ch_req_mask: Mask for Tx or Rx channel select.
  * @ch_req_max: Maximum number of Tx or Rx channels available.
@@ -95,6 +97,7 @@ struct tegra_adma_chip_data {
 	unsigned int ch_req_max;
 	unsigned int ch_reg_size;
 	unsigned int nr_channels;
+	bool has_outstanding_reqs;
 };
 
 /*
@@ -594,6 +597,8 @@ static int tegra_adma_set_xfer_params(struct tegra_adma_chan *tdc,
 			 ADMA_CH_CTRL_FLOWCTRL_EN;
 	ch_regs->config |= cdata->adma_get_burst_config(burst_size);
 	ch_regs->config |= ADMA_CH_CONFIG_WEIGHT_FOR_WRR(1);
+	if (cdata->has_outstanding_reqs)
+		ch_regs->config |= TEGRA186_ADMA_CH_CONFIG_OUTSTANDING_REQS(8);
 	ch_regs->fifo_ctrl = cdata->ch_fifo_ctrl;
 	ch_regs->tc = desc->period_len & ADMA_CH_TC_COUNT_MASK;
 
@@ -778,6 +783,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.ch_req_tx_shift	= 28,
 	.ch_req_rx_shift	= 24,
 	.ch_base_offset		= 0,
+	.has_outstanding_reqs	= false,
 	.ch_fifo_ctrl		= TEGRA210_FIFO_CTRL_DEFAULT,
 	.ch_req_mask		= 0xf,
 	.ch_req_max		= 10,
@@ -792,6 +798,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.ch_req_tx_shift	= 27,
 	.ch_req_rx_shift	= 22,
 	.ch_base_offset		= 0x10000,
+	.has_outstanding_reqs	= true,
 	.ch_fifo_ctrl		= TEGRA186_FIFO_CTRL_DEFAULT,
 	.ch_req_mask		= 0x1f,
 	.ch_req_max		= 20,
diff --git a/drivers/dma/ti/cppi41.c b/drivers/dma/ti/cppi41.c
index 2f946f55076c..8c2f7ebe998c 100644
--- a/drivers/dma/ti/cppi41.c
+++ b/drivers/dma/ti/cppi41.c
@@ -586,9 +586,22 @@ static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg(
 	enum dma_transfer_direction dir, unsigned long tx_flags, void *context)
 {
 	struct cppi41_channel *c = to_cpp41_chan(chan);
+	struct dma_async_tx_descriptor *txd = NULL;
+	struct cppi41_dd *cdd = c->cdd;
 	struct cppi41_desc *d;
 	struct scatterlist *sg;
 	unsigned int i;
+	int error;
+
+	error = pm_runtime_get(cdd->ddev.dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(cdd->ddev.dev);
+
+		return NULL;
+	}
+
+	if (cdd->is_suspended)
+		goto err_out_not_ready;
 
 	d = c->desc;
 	for_each_sg(sgl, sg, sg_len, i) {
@@ -611,7 +624,13 @@ static struct dma_async_tx_descriptor *cppi41_dma_prep_slave_sg(
 		d++;
 	}
 
-	return &c->txd;
+	txd = &c->txd;
+
+err_out_not_ready:
+	pm_runtime_mark_last_busy(cdd->ddev.dev);
+	pm_runtime_put_autosuspend(cdd->ddev.dev);
+
+	return txd;
 }
 
 static void cppi41_compute_td_desc(struct cppi41_desc *d)
diff --git a/drivers/dma/xilinx/xilinx_dma.c b/drivers/dma/xilinx/xilinx_dma.c
index e7dc3c4dc8e0..5d56f1e4d332 100644
--- a/drivers/dma/xilinx/xilinx_dma.c
+++ b/drivers/dma/xilinx/xilinx_dma.c
@@ -68,6 +68,9 @@
 #define XILINX_DMA_DMACR_CIRC_EN		BIT(1)
 #define XILINX_DMA_DMACR_RUNSTOP		BIT(0)
 #define XILINX_DMA_DMACR_FSYNCSRC_MASK		GENMASK(6, 5)
+#define XILINX_DMA_DMACR_DELAY_MASK		GENMASK(31, 24)
+#define XILINX_DMA_DMACR_FRAME_COUNT_MASK	GENMASK(23, 16)
+#define XILINX_DMA_DMACR_MASTER_MASK		GENMASK(11, 8)
 
 #define XILINX_DMA_REG_DMASR			0x0004
 #define XILINX_DMA_DMASR_EOL_LATE_ERR		BIT(15)
@@ -1354,7 +1357,8 @@ static void xilinx_dma_start_transfer(struct xilinx_dma_chan *chan)
 					   node);
 		hw = &segment->hw;
 
-		xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR, hw->buf_addr);
+		xilinx_write(chan, XILINX_DMA_REG_SRCDSTADDR,
+			     xilinx_prep_dma_addr_t(hw->buf_addr));
 
 		/* Start the transfer */
 		dma_ctrl_write(chan, XILINX_DMA_REG_BTT,
@@ -2117,8 +2121,10 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
 	chan->config.gen_lock = cfg->gen_lock;
 	chan->config.master = cfg->master;
 
+	dmacr &= ~XILINX_DMA_DMACR_GENLOCK_EN;
 	if (cfg->gen_lock && chan->genlock) {
 		dmacr |= XILINX_DMA_DMACR_GENLOCK_EN;
+		dmacr &= ~XILINX_DMA_DMACR_MASTER_MASK;
 		dmacr |= cfg->master << XILINX_DMA_DMACR_MASTER_SHIFT;
 	}
 
@@ -2134,11 +2140,13 @@ int xilinx_vdma_channel_set_config(struct dma_chan *dchan,
 	chan->config.delay = cfg->delay;
 
 	if (cfg->coalesc <= XILINX_DMA_DMACR_FRAME_COUNT_MAX) {
+		dmacr &= ~XILINX_DMA_DMACR_FRAME_COUNT_MASK;
 		dmacr |= cfg->coalesc << XILINX_DMA_DMACR_FRAME_COUNT_SHIFT;
 		chan->config.coalesc = cfg->coalesc;
 	}
 
 	if (cfg->delay <= XILINX_DMA_DMACR_DELAY_MAX) {
+		dmacr &= ~XILINX_DMA_DMACR_DELAY_MASK;
 		dmacr |= cfg->delay << XILINX_DMA_DMACR_DELAY_SHIFT;
 		chan->config.delay = cfg->delay;
 	}
diff --git a/drivers/edac/ghes_edac.c b/drivers/edac/ghes_edac.c
index d413a0bdc9ad..0bb62857ffb2 100644
--- a/drivers/edac/ghes_edac.c
+++ b/drivers/edac/ghes_edac.c
@@ -553,7 +553,11 @@ void ghes_edac_unregister(struct ghes *ghes)
 	if (!ghes_pvt)
 		return;
 
+	if (atomic_dec_return(&ghes_init))
+		return;
+
 	mci = ghes_pvt->mci;
+	ghes_pvt = NULL;
 	edac_mc_del_mc(mci->pdev);
 	edac_mc_free(mci);
 }
diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 178ee8106828..b248870a9806 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -182,6 +182,7 @@ config RESET_ATTACK_MITIGATION
 
 config EFI_RCI2_TABLE
 	bool "EFI Runtime Configuration Interface Table Version 2 Support"
+	depends on X86 || COMPILE_TEST
 	help
 	  Displays the content of the Runtime Configuration Interface
 	  Table version 2 on Dell EMC PowerEdge systems as a binary
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 69f00f7453a3..e98bbf8e56d9 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -554,7 +554,7 @@ int __init efi_config_parse_tables(void *config_tables, int count, int sz,
 					      sizeof(*seed) + size);
 			if (seed != NULL) {
 				pr_notice("seeding entropy pool\n");
-				add_device_randomness(seed->bits, seed->size);
+				add_bootloader_randomness(seed->bits, seed->size);
 				early_memunmap(seed, sizeof(*seed) + size);
 			} else {
 				pr_err("Could not map UEFI random seed!\n");
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 0460c7581220..ee0661ddb25b 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -52,6 +52,7 @@ lib-$(CONFIG_EFI_ARMSTUB)	+= arm-stub.o fdt.o string.o random.o \
 
 lib-$(CONFIG_ARM)		+= arm32-stub.o
 lib-$(CONFIG_ARM64)		+= arm64-stub.o
+CFLAGS_arm32-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 CFLAGS_arm64-stub.o		:= -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 #
diff --git a/drivers/firmware/efi/libstub/arm32-stub.c b/drivers/firmware/efi/libstub/arm32-stub.c
index e8f7aefb6813..41213bf5fcf5 100644
--- a/drivers/firmware/efi/libstub/arm32-stub.c
+++ b/drivers/firmware/efi/libstub/arm32-stub.c
@@ -195,6 +195,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 				 unsigned long dram_base,
 				 efi_loaded_image_t *image)
 {
+	unsigned long kernel_base;
 	efi_status_t status;
 
 	/*
@@ -204,9 +205,18 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	 * loaded. These assumptions are made by the decompressor,
 	 * before any memory map is available.
 	 */
-	dram_base = round_up(dram_base, SZ_128M);
+	kernel_base = round_up(dram_base, SZ_128M);
 
-	status = reserve_kernel_base(sys_table, dram_base, reserve_addr,
+	/*
+	 * Note that some platforms (notably, the Raspberry Pi 2) put
+	 * spin-tables and other pieces of firmware at the base of RAM,
+	 * abusing the fact that the window of TEXT_OFFSET bytes at the
+	 * base of the kernel image is only partially used at the moment.
+	 * (Up to 5 pages are used for the swapper page tables)
+	 */
+	kernel_base += TEXT_OFFSET - 5 * PAGE_SIZE;
+
+	status = reserve_kernel_base(sys_table, kernel_base, reserve_addr,
 				     reserve_size);
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table, "Unable to allocate memory for uncompressed kernel.\n");
@@ -220,7 +230,7 @@ efi_status_t handle_kernel_image(efi_system_table_t *sys_table,
 	*image_size = image->image_size;
 	status = efi_relocate_kernel(sys_table, image_addr, *image_size,
 				     *image_size,
-				     dram_base + MAX_UNCOMP_KERNEL_SIZE, 0);
+				     kernel_base + MAX_UNCOMP_KERNEL_SIZE, 0, 0);
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table, "Failed to relocate kernel.\n");
 		efi_free(sys_table, *reserve_size, *reserve_addr);
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 3caae7f2cf56..35dbc2791c97 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -260,11 +260,11 @@ fail:
 }
 
 /*
- * Allocate at the lowest possible address.
+ * Allocate at the lowest possible address that is not below 'min'.
  */
-efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
-			   unsigned long size, unsigned long align,
-			   unsigned long *addr)
+efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg,
+				 unsigned long size, unsigned long align,
+				 unsigned long *addr, unsigned long min)
 {
 	unsigned long map_size, desc_size, buff_size;
 	efi_memory_desc_t *map;
@@ -311,13 +311,8 @@ efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 		start = desc->phys_addr;
 		end = start + desc->num_pages * EFI_PAGE_SIZE;
 
-		/*
-		 * Don't allocate at 0x0. It will confuse code that
-		 * checks pointers against NULL. Skip the first 8
-		 * bytes so we start at a nice even number.
-		 */
-		if (start == 0x0)
-			start += 8;
+		if (start < min)
+			start = min;
 
 		start = round_up(start, align);
 		if ((start + size) > end)
@@ -698,7 +693,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
 				 unsigned long image_size,
 				 unsigned long alloc_size,
 				 unsigned long preferred_addr,
-				 unsigned long alignment)
+				 unsigned long alignment,
+				 unsigned long min_addr)
 {
 	unsigned long cur_image_addr;
 	unsigned long new_addr = 0;
@@ -731,8 +727,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
 	 * possible.
 	 */
 	if (status != EFI_SUCCESS) {
-		status = efi_low_alloc(sys_table_arg, alloc_size, alignment,
-				       &new_addr);
+		status = efi_low_alloc_above(sys_table_arg, alloc_size,
+					     alignment, &new_addr, min_addr);
 	}
 	if (status != EFI_SUCCESS) {
 		pr_efi_err(sys_table_arg, "Failed to allocate usable memory for kernel.\n");
diff --git a/drivers/firmware/efi/test/efi_test.c b/drivers/firmware/efi/test/efi_test.c
index 877745c3aaf2..7baf48c01e72 100644
--- a/drivers/firmware/efi/test/efi_test.c
+++ b/drivers/firmware/efi/test/efi_test.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/proc_fs.h>
 #include <linux/efi.h>
+#include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
@@ -717,6 +718,13 @@ static long efi_test_ioctl(struct file *file, unsigned int cmd,
 
 static int efi_test_open(struct inode *inode, struct file *file)
 {
+	int ret = security_locked_down(LOCKDOWN_EFI_TEST);
+
+	if (ret)
+		return ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
 	/*
 	 * nothing special to do here
 	 * We do accept multiple open files at the same time as we
diff --git a/drivers/firmware/efi/tpm.c b/drivers/firmware/efi/tpm.c
index ebd7977653a8..31f9f0e369b9 100644
--- a/drivers/firmware/efi/tpm.c
+++ b/drivers/firmware/efi/tpm.c
@@ -88,6 +88,7 @@ int __init efi_tpm_eventlog_init(void)
 
 	if (tbl_size < 0) {
 		pr_err(FW_BUG "Failed to parse event in TPM Final Events Log\n");
+		ret = -EINVAL;
 		goto out_calc;
 	}
 
diff --git a/drivers/firmware/qcom_scm-32.c b/drivers/firmware/qcom_scm-32.c
index 215061c581e1..5d90b7f5ab5a 100644
--- a/drivers/firmware/qcom_scm-32.c
+++ b/drivers/firmware/qcom_scm-32.c
@@ -442,6 +442,41 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
 		req, req_cnt * sizeof(*req), resp, sizeof(*resp));
 }
 
+int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset, u32 size,
+			  u32 mode)
+{
+	struct ocmem_tz_lock {
+		__le32 id;
+		__le32 offset;
+		__le32 size;
+		__le32 mode;
+	} request;
+
+	request.id = cpu_to_le32(id);
+	request.offset = cpu_to_le32(offset);
+	request.size = cpu_to_le32(size);
+	request.mode = cpu_to_le32(mode);
+
+	return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_LOCK_CMD,
+			     &request, sizeof(request), NULL, 0);
+}
+
+int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset, u32 size)
+{
+	struct ocmem_tz_unlock {
+		__le32 id;
+		__le32 offset;
+		__le32 size;
+	} request;
+
+	request.id = cpu_to_le32(id);
+	request.offset = cpu_to_le32(offset);
+	request.size = cpu_to_le32(size);
+
+	return qcom_scm_call(dev, QCOM_SCM_OCMEM_SVC, QCOM_SCM_OCMEM_UNLOCK_CMD,
+			     &request, sizeof(request), NULL, 0);
+}
+
 void __qcom_scm_init(void)
 {
 }
@@ -582,7 +617,22 @@ int __qcom_scm_assign_mem(struct device *dev, phys_addr_t mem_region,
 int __qcom_scm_restore_sec_cfg(struct device *dev, u32 device_id,
 			       u32 spare)
 {
-	return -ENODEV;
+	struct msm_scm_sec_cfg {
+		__le32 id;
+		__le32 ctx_bank_num;
+	} cfg;
+	int ret, scm_ret = 0;
+
+	cfg.id = cpu_to_le32(device_id);
+	cfg.ctx_bank_num = cpu_to_le32(spare);
+
+	ret = qcom_scm_call(dev, QCOM_SCM_SVC_MP, QCOM_SCM_RESTORE_SEC_CFG,
+			    &cfg, sizeof(cfg), &scm_ret, sizeof(scm_ret));
+
+	if (ret || scm_ret)
+		return ret ? ret : -EINVAL;
+
+	return 0;
 }
 
 int __qcom_scm_iommu_secure_ptbl_size(struct device *dev, u32 spare,
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
index 91d5ad7cf58b..c3a3d9874def 100644
--- a/drivers/firmware/qcom_scm-64.c
+++ b/drivers/firmware/qcom_scm-64.c
@@ -241,6 +241,18 @@ int __qcom_scm_hdcp_req(struct device *dev, struct qcom_scm_hdcp_req *req,
 	return ret;
 }
 
+int __qcom_scm_ocmem_lock(struct device *dev, uint32_t id, uint32_t offset,
+			  uint32_t size, uint32_t mode)
+{
+	return -ENOTSUPP;
+}
+
+int __qcom_scm_ocmem_unlock(struct device *dev, uint32_t id, uint32_t offset,
+			    uint32_t size)
+{
+	return -ENOTSUPP;
+}
+
 void __qcom_scm_init(void)
 {
 	u64 cmd;
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index 4802ab170fe5..27c1d98a34e6 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -192,6 +192,46 @@ bool qcom_scm_pas_supported(u32 peripheral)
 EXPORT_SYMBOL(qcom_scm_pas_supported);
 
 /**
+ * qcom_scm_ocmem_lock_available() - is OCMEM lock/unlock interface available
+ */
+bool qcom_scm_ocmem_lock_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_OCMEM_SVC,
+					    QCOM_SCM_OCMEM_LOCK_CMD);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_lock_available);
+
+/**
+ * qcom_scm_ocmem_lock() - call OCMEM lock interface to assign an OCMEM
+ * region to the specified initiator
+ *
+ * @id:     tz initiator id
+ * @offset: OCMEM offset
+ * @size:   OCMEM size
+ * @mode:   access mode (WIDE/NARROW)
+ */
+int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, u32 size,
+			u32 mode)
+{
+	return __qcom_scm_ocmem_lock(__scm->dev, id, offset, size, mode);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_lock);
+
+/**
+ * qcom_scm_ocmem_unlock() - call OCMEM unlock interface to release an OCMEM
+ * region from the specified initiator
+ *
+ * @id:     tz initiator id
+ * @offset: OCMEM offset
+ * @size:   OCMEM size
+ */
+int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size)
+{
+	return __qcom_scm_ocmem_unlock(__scm->dev, id, offset, size);
+}
+EXPORT_SYMBOL(qcom_scm_ocmem_unlock);
+
+/**
  * qcom_scm_pas_init_image() - Initialize peripheral authentication service
  *			       state machine for a given peripheral, using the
  *			       metadata
@@ -327,6 +367,19 @@ static const struct reset_control_ops qcom_scm_pas_reset_ops = {
 	.deassert = qcom_scm_pas_reset_deassert,
 };
 
+/**
+ * qcom_scm_restore_sec_cfg_available() - Check if secure environment
+ * supports restore security config interface.
+ *
+ * Return true if restore-cfg interface is supported, false if not.
+ */
+bool qcom_scm_restore_sec_cfg_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_MP,
+					    QCOM_SCM_RESTORE_SEC_CFG);
+}
+EXPORT_SYMBOL(qcom_scm_restore_sec_cfg_available);
+
 int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare)
 {
 	return __qcom_scm_restore_sec_cfg(__scm->dev, device_id, spare);
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 99506bd873c0..ef293ee67ec1 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -42,6 +42,15 @@ extern int __qcom_scm_hdcp_req(struct device *dev,
 
 extern void __qcom_scm_init(void);
 
+#define QCOM_SCM_OCMEM_SVC			0xf
+#define QCOM_SCM_OCMEM_LOCK_CMD		0x1
+#define QCOM_SCM_OCMEM_UNLOCK_CMD		0x2
+
+extern int __qcom_scm_ocmem_lock(struct device *dev, u32 id, u32 offset,
+				 u32 size, u32 mode);
+extern int __qcom_scm_ocmem_unlock(struct device *dev, u32 id, u32 offset,
+				   u32 size);
+
 #define QCOM_SCM_SVC_PIL		0x2
 #define QCOM_SCM_PAS_INIT_IMAGE_CMD	0x1
 #define QCOM_SCM_PAS_MEM_SETUP_CMD	0x2
diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c
index 2f1e9da81c1e..3302125e5265 100644
--- a/drivers/gpio/gpio-merrifield.c
+++ b/drivers/gpio/gpio-merrifield.c
@@ -362,9 +362,8 @@ static void mrfld_irq_handler(struct irq_desc *desc)
 	chained_irq_exit(irqchip, desc);
 }
 
-static int mrfld_irq_init_hw(struct gpio_chip *chip)
+static void mrfld_irq_init_hw(struct mrfld_gpio *priv)
 {
-	struct mrfld_gpio *priv = gpiochip_get_data(chip);
 	void __iomem *reg;
 	unsigned int base;
 
@@ -376,8 +375,6 @@ static int mrfld_irq_init_hw(struct gpio_chip *chip)
 		reg = gpio_reg(&priv->chip, base, GFER);
 		writel(0, reg);
 	}
-
-	return 0;
 }
 
 static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv)
@@ -400,7 +397,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 {
 	const struct mrfld_gpio_pinrange *range;
 	const char *pinctrl_dev_name;
-	struct gpio_irq_chip *girq;
 	struct mrfld_gpio *priv;
 	u32 gpio_base, irq_base;
 	void __iomem *base;
@@ -448,21 +444,6 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 
 	raw_spin_lock_init(&priv->lock);
 
-	girq = &priv->chip.irq;
-	girq->chip = &mrfld_irqchip;
-	girq->init_hw = mrfld_irq_init_hw;
-	girq->parent_handler = mrfld_irq_handler;
-	girq->num_parents = 1;
-	girq->parents = devm_kcalloc(&pdev->dev, girq->num_parents,
-				     sizeof(*girq->parents),
-				     GFP_KERNEL);
-	if (!girq->parents)
-		return -ENOMEM;
-	girq->parents[0] = pdev->irq;
-	girq->first = irq_base;
-	girq->default_type = IRQ_TYPE_NONE;
-	girq->handler = handle_bad_irq;
-
 	pci_set_drvdata(pdev, priv);
 	retval = devm_gpiochip_add_data(&pdev->dev, &priv->chip, priv);
 	if (retval) {
@@ -484,6 +465,18 @@ static int mrfld_gpio_probe(struct pci_dev *pdev, const struct pci_device_id *id
 		}
 	}
 
+	retval = gpiochip_irqchip_add(&priv->chip, &mrfld_irqchip, irq_base,
+				      handle_bad_irq, IRQ_TYPE_NONE);
+	if (retval) {
+		dev_err(&pdev->dev, "could not connect irqchip to gpiochip\n");
+		return retval;
+	}
+
+	mrfld_irq_init_hw(priv);
+
+	gpiochip_set_chained_irqchip(&priv->chip, &mrfld_irqchip, pdev->irq,
+				     mrfld_irq_handler);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 36357a36a281..1168351267fd 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -93,6 +93,20 @@ config DRM_KMS_FB_HELPER
 	help
 	  FBDEV helpers for KMS drivers.
 
+config DRM_DEBUG_DP_MST_TOPOLOGY_REFS
+        bool "Enable refcount backtrace history in the DP MST helpers"
+        select STACKDEPOT
+        depends on DRM_KMS_HELPER
+        depends on DEBUG_KERNEL
+        depends on EXPERT
+        help
+          Enables debug tracing for topology refs in DRM's DP MST helpers. A
+          history of each topology reference/dereference will be printed to the
+          kernel log once a port or branch device's topology refcount reaches 0.
+
+          This has the potential to use a lot of memory and print some very
+          large kernel messages. If in doubt, say "N".
+
 config DRM_FBDEV_EMULATION
 	bool "Enable legacy fbdev support for your modesetting driver"
 	depends on DRM
@@ -165,6 +179,13 @@ config DRM_TTM
 	  GPU memory types. Will be enabled automatically if a device driver
 	  uses it.
 
+config DRM_TTM_DMA_PAGE_POOL
+	bool
+	depends on DRM_TTM && (SWIOTLB || INTEL_IOMMU)
+	default y
+	help
+	  Choose this if you need the TTM dma page pool
+
 config DRM_VRAM_HELPER
 	tristate
 	depends on DRM
@@ -232,9 +253,9 @@ config DRM_AMDGPU
 	tristate "AMD GPU"
 	depends on DRM && PCI && MMU
 	select FW_LOADER
-        select DRM_KMS_HELPER
+	select DRM_KMS_HELPER
 	select DRM_SCHED
-        select DRM_TTM
+	select DRM_TTM
 	select POWER_SUPPLY
 	select HWMON
 	select BACKLIGHT_CLASS_DEVICE
diff --git a/drivers/gpu/drm/amd/amdgpu/Makefile b/drivers/gpu/drm/amd/amdgpu/Makefile
index 00962a659009..ca0e435559d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/Makefile
+++ b/drivers/gpu/drm/amd/amdgpu/Makefile
@@ -53,8 +53,9 @@ amdgpu-y += amdgpu_device.o amdgpu_kms.o \
 	amdgpu_ucode.o amdgpu_bo_list.o amdgpu_ctx.o amdgpu_sync.o \
 	amdgpu_gtt_mgr.o amdgpu_vram_mgr.o amdgpu_virt.o amdgpu_atomfirmware.o \
 	amdgpu_vf_error.o amdgpu_sched.o amdgpu_debugfs.o amdgpu_ids.o \
-	amdgpu_gmc.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
-	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o smu_v11_0_i2c.o
+	amdgpu_gmc.o amdgpu_mmhub.o amdgpu_xgmi.o amdgpu_csa.o amdgpu_ras.o amdgpu_vm_cpu.o \
+	amdgpu_vm_sdma.o amdgpu_discovery.o amdgpu_ras_eeprom.o amdgpu_nbio.o \
+	amdgpu_umc.o smu_v11_0_i2c.o
 
 amdgpu-$(CONFIG_PERF_EVENTS) += amdgpu_pmu.o
 
@@ -67,7 +68,7 @@ amdgpu-$(CONFIG_DRM_AMDGPU_SI)+= si.o gmc_v6_0.o gfx_v6_0.o si_ih.o si_dma.o dce
 amdgpu-y += \
 	vi.o mxgpu_vi.o nbio_v6_1.o soc15.o emu_soc.o mxgpu_ai.o nbio_v7_0.o vega10_reg_init.o \
 	vega20_reg_init.o nbio_v7_4.o nbio_v2_3.o nv.o navi10_reg_init.o navi14_reg_init.o \
-	arct_reg_init.o navi12_reg_init.o
+	arct_reg_init.o navi12_reg_init.o mxgpu_nv.o
 
 # add DF block
 amdgpu-y += \
@@ -83,7 +84,7 @@ amdgpu-y += \
 
 # add UMC block
 amdgpu-y += \
-	umc_v6_1.o
+	umc_v6_1.o umc_v6_0.o
 
 # add IH block
 amdgpu-y += \
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index bd37df5dd6d0..bcc5d40a8d5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -73,6 +73,7 @@
 #include "amdgpu_gmc.h"
 #include "amdgpu_gfx.h"
 #include "amdgpu_sdma.h"
+#include "amdgpu_nbio.h"
 #include "amdgpu_dm.h"
 #include "amdgpu_virt.h"
 #include "amdgpu_csa.h"
@@ -106,6 +107,8 @@ struct amdgpu_mgpu_info
 	uint32_t			num_apu;
 };
 
+#define AMDGPU_MAX_TIMEOUT_PARAM_LENGTH	256
+
 /*
  * Modules parameters.
  */
@@ -122,6 +125,7 @@ extern int amdgpu_disp_priority;
 extern int amdgpu_hw_i2c;
 extern int amdgpu_pcie_gen2;
 extern int amdgpu_msi;
+extern char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
 extern int amdgpu_dpm;
 extern int amdgpu_fw_load_type;
 extern int amdgpu_aspm;
@@ -135,6 +139,7 @@ extern int amdgpu_vm_fragment_size;
 extern int amdgpu_vm_fault_stop;
 extern int amdgpu_vm_debug;
 extern int amdgpu_vm_update_mode;
+extern int amdgpu_exp_hw_support;
 extern int amdgpu_dc;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
@@ -146,11 +151,7 @@ extern uint amdgpu_sdma_phase_quantum;
 extern char *amdgpu_disable_cu;
 extern char *amdgpu_virtual_display;
 extern uint amdgpu_pp_feature_mask;
-extern int amdgpu_ngg;
-extern int amdgpu_prim_buf_per_se;
-extern int amdgpu_pos_buf_per_se;
-extern int amdgpu_cntl_sb_buf_per_se;
-extern int amdgpu_param_buf_per_se;
+extern uint amdgpu_force_long_training;
 extern int amdgpu_job_hang_limit;
 extern int amdgpu_lbpw;
 extern int amdgpu_compute_multipipe;
@@ -167,6 +168,12 @@ extern int amdgpu_mcbp;
 extern int amdgpu_discovery;
 extern int amdgpu_mes;
 extern int amdgpu_noretry;
+extern int amdgpu_force_asic_type;
+#ifdef CONFIG_HSA_AMD
+extern int sched_policy;
+#else
+static const int sched_policy = KFD_SCHED_POLICY_HWS;
+#endif
 
 #ifdef CONFIG_DRM_AMDGPU_SI
 extern int amdgpu_si_support;
@@ -283,6 +290,9 @@ struct amdgpu_ip_block_version {
 	const struct amd_ip_funcs *funcs;
 };
 
+#define HW_REV(_Major, _Minor, _Rev) \
+	((((uint32_t) (_Major)) << 16) | ((uint32_t) (_Minor) << 8) | ((uint32_t) (_Rev)))
+
 struct amdgpu_ip_block {
 	struct amdgpu_ip_block_status status;
 	const struct amdgpu_ip_block_version *version;
@@ -425,7 +435,6 @@ struct amdgpu_fpriv {
 };
 
 int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv);
-int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev);
 
 int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		  unsigned size, struct amdgpu_ib *ib);
@@ -477,7 +486,6 @@ struct amdgpu_cs_parser {
 	uint64_t			bytes_moved_vis_threshold;
 	uint64_t			bytes_moved;
 	uint64_t			bytes_moved_vis;
-	struct amdgpu_bo_list_entry	*evictable;
 
 	/* user fence */
 	struct amdgpu_bo_list_entry	uf_entry;
@@ -624,6 +632,11 @@ struct amdgpu_fw_vram_usage {
 	u64 size;
 	struct amdgpu_bo *reserved_bo;
 	void *va;
+
+	/* Offset on the top of VRAM, used as c2p write buffer.
+	*/
+	u64 mem_train_fb_loc;
+	bool mem_train_support;
 };
 
 /*
@@ -644,71 +657,14 @@ typedef void (*amdgpu_wreg64_t)(struct amdgpu_device*, uint32_t, uint64_t);
 typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
 
-
-/*
- * amdgpu nbio functions
- *
- */
-struct nbio_hdp_flush_reg {
-	u32 ref_and_mask_cp0;
-	u32 ref_and_mask_cp1;
-	u32 ref_and_mask_cp2;
-	u32 ref_and_mask_cp3;
-	u32 ref_and_mask_cp4;
-	u32 ref_and_mask_cp5;
-	u32 ref_and_mask_cp6;
-	u32 ref_and_mask_cp7;
-	u32 ref_and_mask_cp8;
-	u32 ref_and_mask_cp9;
-	u32 ref_and_mask_sdma0;
-	u32 ref_and_mask_sdma1;
-	u32 ref_and_mask_sdma2;
-	u32 ref_and_mask_sdma3;
-	u32 ref_and_mask_sdma4;
-	u32 ref_and_mask_sdma5;
-	u32 ref_and_mask_sdma6;
-	u32 ref_and_mask_sdma7;
-};
-
 struct amdgpu_mmio_remap {
 	u32 reg_offset;
 	resource_size_t bus_addr;
 };
 
-struct amdgpu_nbio_funcs {
-	const struct nbio_hdp_flush_reg *hdp_flush_reg;
-	u32 (*get_hdp_flush_req_offset)(struct amdgpu_device *adev);
-	u32 (*get_hdp_flush_done_offset)(struct amdgpu_device *adev);
-	u32 (*get_pcie_index_offset)(struct amdgpu_device *adev);
-	u32 (*get_pcie_data_offset)(struct amdgpu_device *adev);
-	u32 (*get_rev_id)(struct amdgpu_device *adev);
-	void (*mc_access_enable)(struct amdgpu_device *adev, bool enable);
-	void (*hdp_flush)(struct amdgpu_device *adev, struct amdgpu_ring *ring);
-	u32 (*get_memsize)(struct amdgpu_device *adev);
-	void (*sdma_doorbell_range)(struct amdgpu_device *adev, int instance,
-			bool use_doorbell, int doorbell_index, int doorbell_size);
-	void (*vcn_doorbell_range)(struct amdgpu_device *adev, bool use_doorbell,
-				   int doorbell_index, int instance);
-	void (*enable_doorbell_aperture)(struct amdgpu_device *adev,
-					 bool enable);
-	void (*enable_doorbell_selfring_aperture)(struct amdgpu_device *adev,
-						  bool enable);
-	void (*ih_doorbell_range)(struct amdgpu_device *adev,
-				  bool use_doorbell, int doorbell_index);
-	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
-						 bool enable);
-	void (*update_medium_grain_light_sleep)(struct amdgpu_device *adev,
-						bool enable);
-	void (*get_clockgating_state)(struct amdgpu_device *adev,
-				      u32 *flags);
-	void (*ih_control)(struct amdgpu_device *adev);
-	void (*init_registers)(struct amdgpu_device *adev);
-	void (*detect_hw_virt)(struct amdgpu_device *adev);
-	void (*remap_hdp_registers)(struct amdgpu_device *adev);
-};
-
 struct amdgpu_df_funcs {
 	void (*sw_init)(struct amdgpu_device *adev);
+	void (*sw_fini)(struct amdgpu_device *adev);
 	void (*enable_broadcast_mode)(struct amdgpu_device *adev,
 				      bool enable);
 	u32 (*get_fb_channel_number)(struct amdgpu_device *adev);
@@ -813,6 +769,7 @@ struct amdgpu_device {
 	uint8_t				*bios;
 	uint32_t			bios_size;
 	struct amdgpu_bo		*stolen_vga_memory;
+	struct amdgpu_bo		*discovery_memory;
 	uint32_t			bios_scratch_reg_offset;
 	uint32_t			bios_scratch[AMDGPU_BIOS_NUM_SCRATCH];
 
@@ -921,6 +878,12 @@ struct amdgpu_device {
 	u32				cg_flags;
 	u32				pg_flags;
 
+	/* nbio */
+	struct amdgpu_nbio		nbio;
+
+	/* mmhub */
+	struct amdgpu_mmhub		mmhub;
+
 	/* gfx */
 	struct amdgpu_gfx		gfx;
 
@@ -974,9 +937,7 @@ struct amdgpu_device {
 	/* soc15 register offset based on ip, instance and  segment */
 	uint32_t 		*reg_offset[MAX_HWIP][HWIP_MAX_INSTANCE];
 
-	const struct amdgpu_nbio_funcs	*nbio_funcs;
 	const struct amdgpu_df_funcs	*df_funcs;
-	const struct amdgpu_mmhub_funcs	*mmhub_funcs;
 
 	/* delayed work_func for deferring clockgating during resume */
 	struct delayed_work     delayed_init_work;
@@ -1009,8 +970,6 @@ struct amdgpu_device {
 	int asic_reset_res;
 	struct work_struct		xgmi_reset_work;
 
-	bool                            in_baco_reset;
-
 	long				gfx_timeout;
 	long				sdma_timeout;
 	long				video_timeout;
@@ -1018,6 +977,9 @@ struct amdgpu_device {
 
 	uint64_t			unique_id;
 	uint64_t	df_perfmon_config_assign_mask[AMDGPU_MAX_DF_PERFMONS];
+
+	/* device pstate */
+	int				pstate;
 };
 
 static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev)
@@ -1032,6 +994,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 void amdgpu_device_fini(struct amdgpu_device *adev);
 int amdgpu_gpu_wait_for_idle(struct amdgpu_device *adev);
 
+void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
+			       uint32_t *buf, size_t size, bool write);
 uint32_t amdgpu_mm_rreg(struct amdgpu_device *adev, uint32_t reg,
 			uint32_t acc_flags);
 void amdgpu_mm_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 07eb29885372..d3da9dde4ee1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -63,45 +63,10 @@ void amdgpu_amdkfd_fini(void)
 
 void amdgpu_amdkfd_device_probe(struct amdgpu_device *adev)
 {
-	const struct kfd2kgd_calls *kfd2kgd;
-
-	switch (adev->asic_type) {
-#ifdef CONFIG_DRM_AMDGPU_CIK
-	case CHIP_KAVERI:
-	case CHIP_HAWAII:
-		kfd2kgd = amdgpu_amdkfd_gfx_7_get_functions();
-		break;
-#endif
-	case CHIP_CARRIZO:
-	case CHIP_TONGA:
-	case CHIP_FIJI:
-	case CHIP_POLARIS10:
-	case CHIP_POLARIS11:
-	case CHIP_POLARIS12:
-	case CHIP_VEGAM:
-		kfd2kgd = amdgpu_amdkfd_gfx_8_0_get_functions();
-		break;
-	case CHIP_VEGA10:
-	case CHIP_VEGA12:
-	case CHIP_VEGA20:
-	case CHIP_RAVEN:
-		kfd2kgd = amdgpu_amdkfd_gfx_9_0_get_functions();
-		break;
-	case CHIP_ARCTURUS:
-		kfd2kgd = amdgpu_amdkfd_arcturus_get_functions();
-		break;
-	case CHIP_NAVI10:
-	case CHIP_NAVI14:
-	case CHIP_NAVI12:
-		kfd2kgd = amdgpu_amdkfd_gfx_10_0_get_functions();
-		break;
-	default:
-		dev_info(adev->dev, "kfd not supported on this ASIC\n");
-		return;
-	}
+	bool vf = amdgpu_sriov_vf(adev);
 
 	adev->kfd.dev = kgd2kfd_probe((struct kgd_dev *)adev,
-				      adev->pdev, kfd2kgd);
+				      adev->pdev, adev->asic_type, vf);
 
 	if (adev->kfd.dev)
 		amdgpu_amdkfd_total_mem_size += adev->gmc.real_vram_size;
@@ -165,14 +130,6 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 				  adev->gfx.mec.queue_bitmap,
 				  KGD_MAX_QUEUES);
 
-		/* remove the KIQ bit as well */
-		if (adev->gfx.kiq.ring.sched.ready)
-			clear_bit(amdgpu_gfx_mec_queue_to_bit(adev,
-							  adev->gfx.kiq.ring.me - 1,
-							  adev->gfx.kiq.ring.pipe,
-							  adev->gfx.kiq.ring.queue),
-				  gpu_resources.queue_bitmap);
-
 		/* According to linux/bitmap.h we shouldn't use bitmap_clear if
 		 * nbits is not compile time constant
 		 */
@@ -202,7 +159,7 @@ void amdgpu_amdkfd_device_init(struct amdgpu_device *adev)
 					adev->doorbell_index.last_non_cp;
 		}
 
-		kgd2kfd_device_init(adev->kfd.dev, &gpu_resources);
+		kgd2kfd_device_init(adev->kfd.dev, adev->ddev, &gpu_resources);
 	}
 }
 
@@ -709,38 +666,14 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm)
 	return 0;
 }
 
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
-{
-	return NULL;
-}
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
-{
-	return NULL;
-}
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
-{
-	return NULL;
-}
-
-struct kfd2kgd_calls *amdgpu_amdkfd_arcturus_get_functions(void)
-{
-	return NULL;
-}
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_10_0_get_functions(void)
-{
-	return NULL;
-}
-
 struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
-			      const struct kfd2kgd_calls *f2g)
+			      unsigned int asic_type, bool vf)
 {
 	return NULL;
 }
 
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
+			 struct drm_device *ddev,
 			 const struct kgd2kfd_shared_resources *gpu_resources)
 {
 	return false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index e519df3fd2b6..069d5d230810 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -57,7 +57,7 @@ struct kgd_mem {
 	unsigned int mapped_to_gpu_memory;
 	uint64_t va;
 
-	uint32_t mapping_flags;
+	uint32_t alloc_flags;
 
 	atomic_t invalid;
 	struct amdkfd_process_info *process_info;
@@ -137,12 +137,6 @@ int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 bool amdgpu_amdkfd_have_atomics_support(struct kgd_dev *kgd);
 
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void);
-struct kfd2kgd_calls *amdgpu_amdkfd_arcturus_get_functions(void);
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_10_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);
@@ -179,10 +173,17 @@ uint64_t amdgpu_amdkfd_get_mmio_remap_phys_addr(struct kgd_dev *kgd);
 uint32_t amdgpu_amdkfd_get_num_gws(struct kgd_dev *kgd);
 uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *src);
 
+/* Read user wptr from a specified user address space with page fault
+ * disabled. The memory must be pinned and mapped to the hardware when
+ * this is called in hqd_load functions, so it should never fault in
+ * the first place. This resolves a circular lock dependency involving
+ * four locks, including the DQM lock and mmap_sem.
+ */
 #define read_user_wptr(mmptr, wptr, dst)				\
 	({								\
 		bool valid = false;					\
 		if ((mmptr) && (wptr)) {				\
+			pagefault_disable();				\
 			if ((mmptr) == current->mm) {			\
 				valid = !get_user((dst), (wptr));	\
 			} else if (current->mm == NULL) {		\
@@ -190,6 +191,7 @@ uint8_t amdgpu_amdkfd_get_xgmi_hops_count(struct kgd_dev *dst, struct kgd_dev *s
 				valid = !get_user((dst), (wptr));	\
 				unuse_mm(mmptr);			\
 			}						\
+			pagefault_enable();				\
 		}							\
 		valid;							\
 	})
@@ -240,8 +242,9 @@ void amdgpu_amdkfd_unreserve_memory_limit(struct amdgpu_bo *bo);
 int kgd2kfd_init(void);
 void kgd2kfd_exit(void);
 struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd, struct pci_dev *pdev,
-			      const struct kfd2kgd_calls *f2g);
+			      unsigned int asic_type, bool vf);
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
+			 struct drm_device *ddev,
 			 const struct kgd2kfd_shared_resources *gpu_resources);
 void kgd2kfd_device_exit(struct kfd_dev *kfd);
 void kgd2kfd_suspend(struct kfd_dev *kfd);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
index c79aaebeeaf0..b6713e0ed1b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c
@@ -19,10 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#undef pr_fmt
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/module.h>
 #include <linux/fdtable.h>
 #include <linux/uaccess.h>
@@ -69,11 +65,11 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct v9_sdma_mqd *)mqd;
 }
 
-static uint32_t get_sdma_base_addr(struct amdgpu_device *adev,
+static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t base[8] = {
+	uint32_t sdma_engine_reg_base[8] = {
 		SOC15_REG_OFFSET(SDMA0, 0,
 				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
 		SOC15_REG_OFFSET(SDMA1, 0,
@@ -91,111 +87,82 @@ static uint32_t get_sdma_base_addr(struct amdgpu_device *adev,
 		SOC15_REG_OFFSET(SDMA7, 0,
 				 mmSDMA7_RLC0_RB_CNTL) - mmSDMA7_RLC0_RB_CNTL
 	};
-	uint32_t retval;
 
-	retval = base[engine_id] + queue_id * (mmSDMA0_RLC1_RB_CNTL -
-					       mmSDMA0_RLC0_RB_CNTL);
+	uint32_t retval = sdma_engine_reg_base[engine_id]
+		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
-	pr_debug("sdma base address: 0x%x\n", retval);
+	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
+			queue_id, retval);
 
 	return retval;
 }
 
-static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
-		u32 instance, u32 offset)
-{
-	switch (instance) {
-	case 0:
-		return (adev->reg_offset[SDMA0_HWIP][0][0] + offset);
-	case 1:
-		return (adev->reg_offset[SDMA1_HWIP][0][1] + offset);
-	case 2:
-		return (adev->reg_offset[SDMA2_HWIP][0][1] + offset);
-	case 3:
-		return (adev->reg_offset[SDMA3_HWIP][0][1] + offset);
-	case 4:
-		return (adev->reg_offset[SDMA4_HWIP][0][1] + offset);
-	case 5:
-		return (adev->reg_offset[SDMA5_HWIP][0][1] + offset);
-	case 6:
-		return (adev->reg_offset[SDMA6_HWIP][0][1] + offset);
-	case 7:
-		return (adev->reg_offset[SDMA7_HWIP][0][1] + offset);
-	default:
-		break;
-	}
-	return 0;
-}
-
 static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
 			     uint32_t __user *wptr, struct mm_struct *mm)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v9_sdma_mqd *m;
-	uint32_t sdma_base_addr, sdmax_gfx_context_cntl;
+	uint32_t sdma_rlc_reg_offset;
 	unsigned long end_jiffies;
 	uint32_t data;
 	uint64_t data64;
 	uint64_t __user *wptr64 = (uint64_t __user *)wptr;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
-	sdmax_gfx_context_cntl = sdma_v4_0_get_reg_offset(adev,
-			m->sdma_engine_id, mmSDMA0_GFX_CONTEXT_CNTL);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
 		m->sdmax_rlcx_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
 	end_jiffies = msecs_to_jiffies(2000) + jiffies;
 	while (true) {
-		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		data = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
-	data = RREG32(sdmax_gfx_context_cntl);
-	data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
-			     RESUME_CTX, 0);
-	WREG32(sdmax_gfx_context_cntl, data);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL_OFFSET,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL_OFFSET,
 	       m->sdmax_rlcx_doorbell_offset);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_doorbell, SDMA0_RLC0_DOORBELL,
 			     ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdmax_rlcx_rb_rptr);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR,
+				m->sdmax_rlcx_rb_rptr);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_HI,
 				m->sdmax_rlcx_rb_rptr_hi);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
 	if (read_user_wptr(mm, wptr64, data64)) {
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       lower_32_bits(data64));
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR_HI,
 		       upper_32_bits(data64));
 	} else {
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       m->sdmax_rlcx_rb_rptr);
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR_HI,
 		       m->sdmax_rlcx_rb_rptr_hi);
 	}
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdmax_rlcx_rb_base_hi);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdmax_rlcx_rb_rptr_addr_lo);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdmax_rlcx_rb_rptr_addr_hi);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_rb_cntl, SDMA0_RLC0_RB_CNTL,
 			     RB_ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, data);
 
 	return 0;
 }
@@ -205,7 +172,8 @@ static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
 			     uint32_t (**dump)[2], uint32_t *n_regs)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-	uint32_t sdma_base_addr = get_sdma_base_addr(adev, engine_id, queue_id);
+	uint32_t sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev,
+			engine_id, queue_id);
 	uint32_t i = 0, reg;
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+10)
@@ -215,15 +183,15 @@ static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
 		return -ENOMEM;
 
 	for (reg = mmSDMA0_RLC0_RB_CNTL; reg <= mmSDMA0_RLC0_DOORBELL; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_STATUS; reg <= mmSDMA0_RLC0_CSA_ADDR_HI; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_IB_SUB_REMAIN;
 	     reg <= mmSDMA0_RLC0_MINOR_PTR_UPDATE; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_MIDCMD_DATA0;
 	     reg <= mmSDMA0_RLC0_MIDCMD_CNTL; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 
 	WARN_ON_ONCE(i != HQD_N_REGS);
 	*n_regs = i;
@@ -235,14 +203,14 @@ static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v9_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t sdma_rlc_rb_cntl;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
 
-	sdma_rlc_rb_cntl = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	sdma_rlc_rb_cntl = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 
 	if (sdma_rlc_rb_cntl & SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK)
 		return true;
@@ -255,40 +223,42 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v9_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t temp;
 	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
 
-	temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 	temp = temp & ~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK;
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, temp);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, temp);
 
 	while (true) {
-		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL) |
 		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
-	m->sdmax_rlcx_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
+	m->sdmax_rlcx_rb_rptr = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR);
 	m->sdmax_rlcx_rb_rptr_hi =
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI);
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_HI);
 
 	return 0;
 }
 
-static const struct kfd2kgd_calls kfd2kgd = {
+const struct kfd2kgd_calls arcturus_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_gfx_v9_init_interrupts,
@@ -304,20 +274,11 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.address_watch_execute = kgd_gfx_v9_address_watch_execute,
 	.wave_control_execute = kgd_gfx_v9_wave_control_execute,
 	.address_watch_get_offset = kgd_gfx_v9_address_watch_get_offset,
-	.get_atc_vmid_pasid_mapping_pasid =
-			kgd_gfx_v9_get_atc_vmid_pasid_mapping_pasid,
-	.get_atc_vmid_pasid_mapping_valid =
-			kgd_gfx_v9_get_atc_vmid_pasid_mapping_valid,
-	.set_scratch_backing_va = kgd_gfx_v9_set_scratch_backing_va,
+	.get_atc_vmid_pasid_mapping_info =
+			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = kgd_gfx_v9_get_tile_config,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
 	.invalidate_tlbs = kgd_gfx_v9_invalidate_tlbs,
 	.invalidate_tlbs_vmid = kgd_gfx_v9_invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
-
-struct kfd2kgd_calls *amdgpu_amdkfd_arcturus_get_functions(void)
-{
-	return (struct kfd2kgd_calls *)&kfd2kgd;
-}
-
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
index d10f483f5e27..61cd707158e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v10.c
@@ -19,18 +19,9 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-#undef pr_fmt
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
-#include <linux/module.h>
-#include <linux/fdtable.h>
-#include <linux/uaccess.h>
-#include <linux/firmware.h>
 #include <linux/mmu_context.h>
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
-#include "amdgpu_ucode.h"
-#include "soc15_hw_ip.h"
 #include "gc/gc_10_1_0_offset.h"
 #include "gc/gc_10_1_0_sh_mask.h"
 #include "navi10_enum.h"
@@ -42,6 +33,7 @@
 #include "v10_structs.h"
 #include "nv.h"
 #include "nvd.h"
+#include "gfxhub_v2_0.h"
 
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
@@ -50,63 +42,6 @@ enum hqd_dequeue_request_type {
 	SAVE_WAVES
 };
 
-/*
- * Register access functions
- */
-
-static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
-		uint32_t sh_mem_config,
-		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
-		uint32_t sh_mem_bases);
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
-		unsigned int vmid);
-static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
-static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
-			uint32_t queue_id, uint32_t __user *wptr,
-			uint32_t wptr_shift, uint32_t wptr_mask,
-			struct mm_struct *mm);
-static int kgd_hqd_dump(struct kgd_dev *kgd,
-			uint32_t pipe_id, uint32_t queue_id,
-			uint32_t (**dump)[2], uint32_t *n_regs);
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
-			     uint32_t __user *wptr, struct mm_struct *mm);
-static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
-			     uint32_t engine_id, uint32_t queue_id,
-			     uint32_t (**dump)[2], uint32_t *n_regs);
-static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
-		uint32_t pipe_id, uint32_t queue_id);
-static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd);
-static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
-				enum kfd_preempt_type reset_type,
-				unsigned int utimeout, uint32_t pipe_id,
-				uint32_t queue_id);
-static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
-				unsigned int utimeout);
-#if 0
-static uint32_t get_watch_base_addr(struct amdgpu_device *adev);
-#endif
-static int kgd_address_watch_disable(struct kgd_dev *kgd);
-static int kgd_address_watch_execute(struct kgd_dev *kgd,
-					unsigned int watch_point_id,
-					uint32_t cntl_val,
-					uint32_t addr_hi,
-					uint32_t addr_lo);
-static int kgd_wave_control_execute(struct kgd_dev *kgd,
-					uint32_t gfx_index_val,
-					uint32_t sq_cmd);
-static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
-					unsigned int watch_point_id,
-					unsigned int reg_offset);
-
-static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-		uint8_t vmid);
-static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-		uint8_t vmid);
-static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_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);
-
 /* Because of REG_GET_FIELD() being used, we put this function in the
  * asic specific file.
  */
@@ -139,37 +74,6 @@ static int amdgpu_amdkfd_get_tile_config(struct kgd_dev *kgd,
 	return 0;
 }
 
-static const struct kfd2kgd_calls kfd2kgd = {
-	.program_sh_mem_settings = kgd_program_sh_mem_settings,
-	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
-	.init_interrupts = kgd_init_interrupts,
-	.hqd_load = kgd_hqd_load,
-	.hqd_sdma_load = kgd_hqd_sdma_load,
-	.hqd_dump = kgd_hqd_dump,
-	.hqd_sdma_dump = kgd_hqd_sdma_dump,
-	.hqd_is_occupied = kgd_hqd_is_occupied,
-	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
-	.hqd_destroy = kgd_hqd_destroy,
-	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
-	.address_watch_disable = kgd_address_watch_disable,
-	.address_watch_execute = kgd_address_watch_execute,
-	.wave_control_execute = kgd_wave_control_execute,
-	.address_watch_get_offset = kgd_address_watch_get_offset,
-	.get_atc_vmid_pasid_mapping_pasid =
-			get_atc_vmid_pasid_mapping_pasid,
-	.get_atc_vmid_pasid_mapping_valid =
-			get_atc_vmid_pasid_mapping_valid,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
-	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.get_tile_config = amdgpu_amdkfd_get_tile_config,
-};
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_10_0_get_functions()
-{
-	return (struct kfd2kgd_calls *)&kfd2kgd;
-}
-
 static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
 	return (struct amdgpu_device *)kgd;
@@ -250,11 +154,6 @@ static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
 			ATC_VMID0_PASID_MAPPING__VALID_MASK;
 
 	pr_debug("pasid 0x%x vmid %d, reg value %x\n", pasid, vmid, pasid_mapping);
-	/*
-	 * need to do this twice, once for gfx and once for mmhub
-	 * for ATC add 16 to VMID for mmhub, for IH different registers.
-	 * ATC_VMID0..15 registers are separate from ATC_VMID16..31.
-	 */
 
 	pr_debug("ATHUB, reg %x\n", SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING) + vmid);
 	WREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING) + vmid,
@@ -306,11 +205,11 @@ static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 	return 0;
 }
 
-static uint32_t get_sdma_base_addr(struct amdgpu_device *adev,
+static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t base[2] = {
+	uint32_t sdma_engine_reg_base[2] = {
 		SOC15_REG_OFFSET(SDMA0, 0,
 				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
 		/* On gfx10, mmSDMA1_xxx registers are defined NOT based
@@ -322,12 +221,12 @@ static uint32_t get_sdma_base_addr(struct amdgpu_device *adev,
 		SOC15_REG_OFFSET(SDMA1, 0,
 				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL
 	};
-	uint32_t retval;
 
-	retval = base[engine_id] + queue_id * (mmSDMA0_RLC1_RB_CNTL -
-					       mmSDMA0_RLC0_RB_CNTL);
+	uint32_t retval = sdma_engine_reg_base[engine_id]
+		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
-	pr_debug("sdma base address: 0x%x\n", retval);
+	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
+			queue_id, retval);
 
 	return retval;
 }
@@ -488,72 +387,67 @@ static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v10_sdma_mqd *m;
-	uint32_t sdma_base_addr, sdmax_gfx_context_cntl;
+	uint32_t sdma_rlc_reg_offset;
 	unsigned long end_jiffies;
 	uint32_t data;
 	uint64_t data64;
 	uint64_t __user *wptr64 = (uint64_t __user *)wptr;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
-	pr_debug("sdma load base addr %x for engine %d, queue %d\n", sdma_base_addr, m->sdma_engine_id, m->sdma_queue_id);
-	sdmax_gfx_context_cntl = m->sdma_engine_id ?
-		SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GFX_CONTEXT_CNTL) :
-		SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_CONTEXT_CNTL);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
 		m->sdmax_rlcx_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
 	end_jiffies = msecs_to_jiffies(2000) + jiffies;
 	while (true) {
-		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		data = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
-	data = RREG32(sdmax_gfx_context_cntl);
-	data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
-			     RESUME_CTX, 0);
-	WREG32(sdmax_gfx_context_cntl, data);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL_OFFSET,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL_OFFSET,
 	       m->sdmax_rlcx_doorbell_offset);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_doorbell, SDMA0_RLC0_DOORBELL,
 			     ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdmax_rlcx_rb_rptr);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR,
+				m->sdmax_rlcx_rb_rptr);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_HI,
 				m->sdmax_rlcx_rb_rptr_hi);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
 	if (read_user_wptr(mm, wptr64, data64)) {
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       lower_32_bits(data64));
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR_HI,
 		       upper_32_bits(data64));
 	} else {
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       m->sdmax_rlcx_rb_rptr);
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR_HI,
 		       m->sdmax_rlcx_rb_rptr_hi);
 	}
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdmax_rlcx_rb_base_hi);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdmax_rlcx_rb_rptr_addr_lo);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdmax_rlcx_rb_rptr_addr_hi);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_rb_cntl, SDMA0_RLC0_RB_CNTL,
 			     RB_ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, data);
 
 	return 0;
 }
@@ -563,28 +457,26 @@ static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
 			     uint32_t (**dump)[2], uint32_t *n_regs)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-	uint32_t sdma_base_addr = get_sdma_base_addr(adev, engine_id, queue_id);
+	uint32_t sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev,
+			engine_id, queue_id);
 	uint32_t i = 0, reg;
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+10)
 
-	pr_debug("sdma dump engine id %d queue_id %d\n", engine_id, queue_id);
-	pr_debug("sdma base addr %x\n", sdma_base_addr);
-
 	*dump = kmalloc(HQD_N_REGS*2*sizeof(uint32_t), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
 	for (reg = mmSDMA0_RLC0_RB_CNTL; reg <= mmSDMA0_RLC0_DOORBELL; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_STATUS; reg <= mmSDMA0_RLC0_CSA_ADDR_HI; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_IB_SUB_REMAIN;
 	     reg <= mmSDMA0_RLC0_MINOR_PTR_UPDATE; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_MIDCMD_DATA0;
 	     reg <= mmSDMA0_RLC0_MIDCMD_CNTL; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 
 	WARN_ON_ONCE(i != HQD_N_REGS);
 	*n_regs = i;
@@ -618,14 +510,14 @@ static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v10_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t sdma_rlc_rb_cntl;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
 
-	sdma_rlc_rb_cntl = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	sdma_rlc_rb_cntl = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 
 	if (sdma_rlc_rb_cntl & SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK)
 		return true;
@@ -746,59 +638,52 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v10_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t temp;
 	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
 
-	temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 	temp = temp & ~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK;
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, temp);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, temp);
 
 	while (true) {
-		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL) |
 		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
-	m->sdmax_rlcx_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
+	m->sdmax_rlcx_rb_rptr = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR);
 	m->sdmax_rlcx_rb_rptr_hi =
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI);
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_HI);
 
 	return 0;
 }
 
-static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-							uint8_t vmid)
+static bool get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
+					uint8_t vmid, uint16_t *p_pasid)
 {
-	uint32_t reg;
+	uint32_t value;
 	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
 
-	reg = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+	value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
 		     + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__VALID_MASK;
-}
-
-static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-								uint8_t vmid)
-{
-	uint32_t reg;
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
 
-	reg = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
-		     + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
 static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid)
@@ -830,6 +715,8 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
 	int vmid;
+	uint16_t queried_pasid;
+	bool ret;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 
 	if (amdgpu_emu_mode == 0 && ring->sched.ready)
@@ -838,13 +725,13 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
-		if (get_atc_vmid_pasid_mapping_valid(kgd, vmid)) {
-			if (get_atc_vmid_pasid_mapping_pasid(kgd, vmid)
-				== pasid) {
-				amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-						AMDGPU_GFXHUB_0, 0);
-				break;
-			}
+
+		ret = get_atc_vmid_pasid_mapping_info(kgd, vmid,
+				&queried_pasid);
+		if (ret	&& queried_pasid == pasid) {
+			amdgpu_gmc_flush_gpu_tlb(adev, vmid,
+					AMDGPU_GFXHUB_0, 0);
+			break;
 		}
 	}
 
@@ -914,7 +801,6 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint64_t page_table_base)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-	uint64_t base = page_table_base | AMDGPU_PTE_VALID;
 
 	if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid)) {
 		pr_err("trying to set page table base for wrong VMID %u\n",
@@ -922,18 +808,31 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		return;
 	}
 
-	/* TODO: take advantage of per-process address space size. For
-	 * now, all processes share the same address space size, like
-	 * on GFX8 and older.
-	 */
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32) + (vmid*2), 0);
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_START_ADDR_HI32) + (vmid*2), 0);
-
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_END_ADDR_LO32) + (vmid*2),
-			lower_32_bits(adev->vm_manager.max_pfn - 1));
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_END_ADDR_HI32) + (vmid*2),
-			upper_32_bits(adev->vm_manager.max_pfn - 1));
-
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32) + (vmid*2), lower_32_bits(base));
-	WREG32(SOC15_REG_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) + (vmid*2), upper_32_bits(base));
+	/* SDMA is on gfxhub as well for Navi1* series */
+	gfxhub_v2_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 }
+
+const struct kfd2kgd_calls gfx_v10_kfd2kgd = {
+	.program_sh_mem_settings = kgd_program_sh_mem_settings,
+	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
+	.init_interrupts = kgd_init_interrupts,
+	.hqd_load = kgd_hqd_load,
+	.hqd_sdma_load = kgd_hqd_sdma_load,
+	.hqd_dump = kgd_hqd_dump,
+	.hqd_sdma_dump = kgd_hqd_sdma_dump,
+	.hqd_is_occupied = kgd_hqd_is_occupied,
+	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
+	.hqd_destroy = kgd_hqd_destroy,
+	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
+	.address_watch_disable = kgd_address_watch_disable,
+	.address_watch_execute = kgd_address_watch_execute,
+	.wave_control_execute = kgd_wave_control_execute,
+	.address_watch_get_offset = kgd_address_watch_get_offset,
+	.get_atc_vmid_pasid_mapping_info =
+			get_atc_vmid_pasid_mapping_info,
+	.get_tile_config = amdgpu_amdkfd_get_tile_config,
+	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.invalidate_tlbs = invalidate_tlbs,
+	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
+	.get_hive_id = amdgpu_amdkfd_get_hive_id,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 5f459bf5f622..6e6f0a99ec06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -20,8 +20,6 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#include <linux/fdtable.h>
-#include <linux/uaccess.h>
 #include <linux/mmu_context.h>
 
 #include "amdgpu.h"
@@ -86,65 +84,6 @@ union TCP_WATCH_CNTL_BITS {
 	float f32All;
 };
 
-/*
- * Register access functions
- */
-
-static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
-		uint32_t sh_mem_config,	uint32_t sh_mem_ape1_base,
-		uint32_t sh_mem_ape1_limit, uint32_t sh_mem_bases);
-
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
-					unsigned int vmid);
-
-static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
-static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
-			uint32_t queue_id, uint32_t __user *wptr,
-			uint32_t wptr_shift, uint32_t wptr_mask,
-			struct mm_struct *mm);
-static int kgd_hqd_dump(struct kgd_dev *kgd,
-			uint32_t pipe_id, uint32_t queue_id,
-			uint32_t (**dump)[2], uint32_t *n_regs);
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
-			     uint32_t __user *wptr, struct mm_struct *mm);
-static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
-			     uint32_t engine_id, uint32_t queue_id,
-			     uint32_t (**dump)[2], uint32_t *n_regs);
-static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
-				uint32_t pipe_id, uint32_t queue_id);
-
-static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
-				enum kfd_preempt_type reset_type,
-				unsigned int utimeout, uint32_t pipe_id,
-				uint32_t queue_id);
-static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd);
-static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
-				unsigned int utimeout);
-static int kgd_address_watch_disable(struct kgd_dev *kgd);
-static int kgd_address_watch_execute(struct kgd_dev *kgd,
-					unsigned int watch_point_id,
-					uint32_t cntl_val,
-					uint32_t addr_hi,
-					uint32_t addr_lo);
-static int kgd_wave_control_execute(struct kgd_dev *kgd,
-					uint32_t gfx_index_val,
-					uint32_t sq_cmd);
-static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
-					unsigned int watch_point_id,
-					unsigned int reg_offset);
-
-static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd, uint8_t vmid);
-static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-							uint8_t vmid);
-
-static void set_scratch_backing_va(struct kgd_dev *kgd,
-					uint64_t va, uint32_t vmid);
-static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_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.
  */
@@ -170,37 +109,6 @@ static int get_tile_config(struct kgd_dev *kgd,
 	return 0;
 }
 
-static const struct kfd2kgd_calls kfd2kgd = {
-	.program_sh_mem_settings = kgd_program_sh_mem_settings,
-	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
-	.init_interrupts = kgd_init_interrupts,
-	.hqd_load = kgd_hqd_load,
-	.hqd_sdma_load = kgd_hqd_sdma_load,
-	.hqd_dump = kgd_hqd_dump,
-	.hqd_sdma_dump = kgd_hqd_sdma_dump,
-	.hqd_is_occupied = kgd_hqd_is_occupied,
-	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
-	.hqd_destroy = kgd_hqd_destroy,
-	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
-	.address_watch_disable = kgd_address_watch_disable,
-	.address_watch_execute = kgd_address_watch_execute,
-	.wave_control_execute = kgd_wave_control_execute,
-	.address_watch_get_offset = kgd_address_watch_get_offset,
-	.get_atc_vmid_pasid_mapping_pasid = get_atc_vmid_pasid_mapping_pasid,
-	.get_atc_vmid_pasid_mapping_valid = get_atc_vmid_pasid_mapping_valid,
-	.set_scratch_backing_va = set_scratch_backing_va,
-	.get_tile_config = get_tile_config,
-	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
-	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
-};
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
-{
-	return (struct kfd2kgd_calls *)&kfd2kgd;
-}
-
 static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
 	return (struct amdgpu_device *)kgd;
@@ -303,14 +211,15 @@ static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 	return 0;
 }
 
-static inline uint32_t get_sdma_base_addr(struct cik_sdma_rlc_registers *m)
+static inline uint32_t get_sdma_rlc_reg_offset(struct cik_sdma_rlc_registers *m)
 {
 	uint32_t retval;
 
 	retval = m->sdma_engine_id * SDMA1_REGISTER_OFFSET +
 			m->sdma_queue_id * KFD_CIK_SDMA_QUEUE_OFFSET;
 
-	pr_debug("sdma base address: 0x%x\n", retval);
+	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n",
+			m->sdma_engine_id, m->sdma_queue_id, retval);
 
 	return retval;
 }
@@ -413,60 +322,52 @@ static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
 	unsigned long end_jiffies;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t data;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(m);
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(m);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
 		m->sdma_rlc_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
 	end_jiffies = msecs_to_jiffies(2000) + jiffies;
 	while (true) {
-		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		data = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
-	if (m->sdma_engine_id) {
-		data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
-		data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
-				RESUME_CTX, 0);
-		WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
-	} else {
-		data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
-		data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
-				RESUME_CTX, 0);
-		WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
-	}
 
 	data = REG_SET_FIELD(m->sdma_rlc_doorbell, SDMA0_RLC0_DOORBELL,
 			     ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdma_rlc_rb_rptr);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR,
+				m->sdma_rlc_rb_rptr);
 
 	if (read_user_wptr(mm, wptr, data))
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, data);
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR, data);
 	else
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       m->sdma_rlc_rb_rptr);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_VIRTUAL_ADDR,
 				m->sdma_rlc_virtual_addr);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdma_rlc_rb_base);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE, m->sdma_rlc_rb_base);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdma_rlc_rb_base_hi);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdma_rlc_rb_rptr_addr_lo);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdma_rlc_rb_rptr_addr_hi);
 
 	data = REG_SET_FIELD(m->sdma_rlc_rb_cntl, SDMA0_RLC0_RB_CNTL,
 			     RB_ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, data);
 
 	return 0;
 }
@@ -524,13 +425,13 @@ static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t sdma_rlc_rb_cntl;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(m);
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(m);
 
-	sdma_rlc_rb_cntl = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	sdma_rlc_rb_cntl = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 
 	if (sdma_rlc_rb_cntl & SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK)
 		return true;
@@ -645,32 +546,34 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct cik_sdma_rlc_registers *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t temp;
 	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(m);
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(m);
 
-	temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 	temp = temp & ~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK;
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, temp);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, temp);
 
 	while (true) {
-		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL) |
 		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
-	m->sdma_rlc_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
+	m->sdma_rlc_rb_rptr = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR);
 
 	return 0;
 }
@@ -758,24 +661,16 @@ static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
 	return watchRegs[watch_point_id * ADDRESS_WATCH_REG_MAX + reg_offset];
 }
 
-static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-							uint8_t vmid)
+static bool get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
+					uint8_t vmid, uint16_t *p_pasid)
 {
-	uint32_t reg;
+	uint32_t value;
 	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
 
-	reg = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__VALID_MASK;
-}
-
-static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-								uint8_t vmid)
-{
-	uint32_t reg;
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+	value = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
 
-	reg = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
 static void set_scratch_backing_va(struct kgd_dev *kgd,
@@ -855,3 +750,28 @@ static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd)
 
 	return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID);
 }
+
+const struct kfd2kgd_calls gfx_v7_kfd2kgd = {
+	.program_sh_mem_settings = kgd_program_sh_mem_settings,
+	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
+	.init_interrupts = kgd_init_interrupts,
+	.hqd_load = kgd_hqd_load,
+	.hqd_sdma_load = kgd_hqd_sdma_load,
+	.hqd_dump = kgd_hqd_dump,
+	.hqd_sdma_dump = kgd_hqd_sdma_dump,
+	.hqd_is_occupied = kgd_hqd_is_occupied,
+	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
+	.hqd_destroy = kgd_hqd_destroy,
+	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
+	.address_watch_disable = kgd_address_watch_disable,
+	.address_watch_execute = kgd_address_watch_execute,
+	.wave_control_execute = kgd_wave_control_execute,
+	.address_watch_get_offset = kgd_address_watch_get_offset,
+	.get_atc_vmid_pasid_mapping_info = get_atc_vmid_pasid_mapping_info,
+	.set_scratch_backing_va = set_scratch_backing_va,
+	.get_tile_config = get_tile_config,
+	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.invalidate_tlbs = invalidate_tlbs,
+	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
+	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 6d2f61449606..bfbddedb2380 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -20,9 +20,6 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#include <linux/module.h>
-#include <linux/fdtable.h>
-#include <linux/uaccess.h>
 #include <linux/mmu_context.h>
 
 #include "amdgpu.h"
@@ -44,62 +41,6 @@ enum hqd_dequeue_request_type {
 	RESET_WAVES
 };
 
-/*
- * Register access functions
- */
-
-static void kgd_program_sh_mem_settings(struct kgd_dev *kgd, uint32_t vmid,
-		uint32_t sh_mem_config,
-		uint32_t sh_mem_ape1_base, uint32_t sh_mem_ape1_limit,
-		uint32_t sh_mem_bases);
-static int kgd_set_pasid_vmid_mapping(struct kgd_dev *kgd, unsigned int pasid,
-		unsigned int vmid);
-static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id);
-static int kgd_hqd_load(struct kgd_dev *kgd, void *mqd, uint32_t pipe_id,
-			uint32_t queue_id, uint32_t __user *wptr,
-			uint32_t wptr_shift, uint32_t wptr_mask,
-			struct mm_struct *mm);
-static int kgd_hqd_dump(struct kgd_dev *kgd,
-			uint32_t pipe_id, uint32_t queue_id,
-			uint32_t (**dump)[2], uint32_t *n_regs);
-static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
-			     uint32_t __user *wptr, struct mm_struct *mm);
-static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
-			     uint32_t engine_id, uint32_t queue_id,
-			     uint32_t (**dump)[2], uint32_t *n_regs);
-static bool kgd_hqd_is_occupied(struct kgd_dev *kgd, uint64_t queue_address,
-		uint32_t pipe_id, uint32_t queue_id);
-static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd);
-static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
-				enum kfd_preempt_type reset_type,
-				unsigned int utimeout, uint32_t pipe_id,
-				uint32_t queue_id);
-static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
-				unsigned int utimeout);
-static int kgd_address_watch_disable(struct kgd_dev *kgd);
-static int kgd_address_watch_execute(struct kgd_dev *kgd,
-					unsigned int watch_point_id,
-					uint32_t cntl_val,
-					uint32_t addr_hi,
-					uint32_t addr_lo);
-static int kgd_wave_control_execute(struct kgd_dev *kgd,
-					uint32_t gfx_index_val,
-					uint32_t sq_cmd);
-static uint32_t kgd_address_watch_get_offset(struct kgd_dev *kgd,
-					unsigned int watch_point_id,
-					unsigned int reg_offset);
-
-static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-		uint8_t vmid);
-static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-		uint8_t vmid);
-static void set_scratch_backing_va(struct kgd_dev *kgd,
-					uint64_t va, uint32_t vmid);
-static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
-		uint64_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);
-
 /* Because of REG_GET_FIELD() being used, we put this function in the
  * asic specific file.
  */
@@ -125,38 +66,6 @@ static int get_tile_config(struct kgd_dev *kgd,
 	return 0;
 }
 
-static const struct kfd2kgd_calls kfd2kgd = {
-	.program_sh_mem_settings = kgd_program_sh_mem_settings,
-	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
-	.init_interrupts = kgd_init_interrupts,
-	.hqd_load = kgd_hqd_load,
-	.hqd_sdma_load = kgd_hqd_sdma_load,
-	.hqd_dump = kgd_hqd_dump,
-	.hqd_sdma_dump = kgd_hqd_sdma_dump,
-	.hqd_is_occupied = kgd_hqd_is_occupied,
-	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
-	.hqd_destroy = kgd_hqd_destroy,
-	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
-	.address_watch_disable = kgd_address_watch_disable,
-	.address_watch_execute = kgd_address_watch_execute,
-	.wave_control_execute = kgd_wave_control_execute,
-	.address_watch_get_offset = kgd_address_watch_get_offset,
-	.get_atc_vmid_pasid_mapping_pasid =
-			get_atc_vmid_pasid_mapping_pasid,
-	.get_atc_vmid_pasid_mapping_valid =
-			get_atc_vmid_pasid_mapping_valid,
-	.set_scratch_backing_va = set_scratch_backing_va,
-	.get_tile_config = get_tile_config,
-	.set_vm_context_page_table_base = set_vm_context_page_table_base,
-	.invalidate_tlbs = invalidate_tlbs,
-	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
-};
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
-{
-	return (struct kfd2kgd_calls *)&kfd2kgd;
-}
-
 static inline struct amdgpu_device *get_amdgpu_device(struct kgd_dev *kgd)
 {
 	return (struct amdgpu_device *)kgd;
@@ -260,13 +169,15 @@ static int kgd_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 	return 0;
 }
 
-static inline uint32_t get_sdma_base_addr(struct vi_sdma_mqd *m)
+static inline uint32_t get_sdma_rlc_reg_offset(struct vi_sdma_mqd *m)
 {
 	uint32_t retval;
 
 	retval = m->sdma_engine_id * SDMA1_REGISTER_OFFSET +
 		m->sdma_queue_id * KFD_VI_SDMA_QUEUE_OFFSET;
-	pr_debug("sdma base address: 0x%x\n", retval);
+
+	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n",
+			m->sdma_engine_id, m->sdma_queue_id, retval);
 
 	return retval;
 }
@@ -398,59 +309,51 @@ static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct vi_sdma_mqd *m;
 	unsigned long end_jiffies;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t data;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(m);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(m);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
 		m->sdmax_rlcx_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
 	end_jiffies = msecs_to_jiffies(2000) + jiffies;
 	while (true) {
-		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		data = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
-	if (m->sdma_engine_id) {
-		data = RREG32(mmSDMA1_GFX_CONTEXT_CNTL);
-		data = REG_SET_FIELD(data, SDMA1_GFX_CONTEXT_CNTL,
-				RESUME_CTX, 0);
-		WREG32(mmSDMA1_GFX_CONTEXT_CNTL, data);
-	} else {
-		data = RREG32(mmSDMA0_GFX_CONTEXT_CNTL);
-		data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
-				RESUME_CTX, 0);
-		WREG32(mmSDMA0_GFX_CONTEXT_CNTL, data);
-	}
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_doorbell, SDMA0_RLC0_DOORBELL,
 			     ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdmax_rlcx_rb_rptr);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR,
+				m->sdmax_rlcx_rb_rptr);
 
 	if (read_user_wptr(mm, wptr, data))
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR, data);
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR, data);
 	else
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       m->sdmax_rlcx_rb_rptr);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_VIRTUAL_ADDR,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_VIRTUAL_ADDR,
 				m->sdmax_rlcx_virtual_addr);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdmax_rlcx_rb_base_hi);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdmax_rlcx_rb_rptr_addr_lo);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdmax_rlcx_rb_rptr_addr_hi);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_rb_cntl, SDMA0_RLC0_RB_CNTL,
 			     RB_ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, data);
 
 	return 0;
 }
@@ -517,13 +420,13 @@ static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct vi_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t sdma_rlc_rb_cntl;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(m);
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(m);
 
-	sdma_rlc_rb_cntl = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	sdma_rlc_rb_cntl = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 
 	if (sdma_rlc_rb_cntl & SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK)
 		return true;
@@ -641,54 +544,48 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct vi_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t temp;
 	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(m);
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(m);
 
-	temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 	temp = temp & ~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK;
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, temp);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, temp);
 
 	while (true) {
-		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL) |
 		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
-	m->sdmax_rlcx_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
+	m->sdmax_rlcx_rb_rptr = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR);
 
 	return 0;
 }
 
-static bool get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-							uint8_t vmid)
+static bool get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
+					uint8_t vmid, uint16_t *p_pasid)
 {
-	uint32_t reg;
+	uint32_t value;
 	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
 
-	reg = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__VALID_MASK;
-}
+	value = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
 
-static uint16_t get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-								uint8_t vmid)
-{
-	uint32_t reg;
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
-
-	reg = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
 static int kgd_address_watch_disable(struct kgd_dev *kgd)
@@ -798,3 +695,28 @@ static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
 	RREG32(mmVM_INVALIDATE_RESPONSE);
 	return 0;
 }
+
+const struct kfd2kgd_calls gfx_v8_kfd2kgd = {
+	.program_sh_mem_settings = kgd_program_sh_mem_settings,
+	.set_pasid_vmid_mapping = kgd_set_pasid_vmid_mapping,
+	.init_interrupts = kgd_init_interrupts,
+	.hqd_load = kgd_hqd_load,
+	.hqd_sdma_load = kgd_hqd_sdma_load,
+	.hqd_dump = kgd_hqd_dump,
+	.hqd_sdma_dump = kgd_hqd_sdma_dump,
+	.hqd_is_occupied = kgd_hqd_is_occupied,
+	.hqd_sdma_is_occupied = kgd_hqd_sdma_is_occupied,
+	.hqd_destroy = kgd_hqd_destroy,
+	.hqd_sdma_destroy = kgd_hqd_sdma_destroy,
+	.address_watch_disable = kgd_address_watch_disable,
+	.address_watch_execute = kgd_address_watch_execute,
+	.wave_control_execute = kgd_wave_control_execute,
+	.address_watch_get_offset = kgd_address_watch_get_offset,
+	.get_atc_vmid_pasid_mapping_info =
+			get_atc_vmid_pasid_mapping_info,
+	.set_scratch_backing_va = set_scratch_backing_va,
+	.get_tile_config = get_tile_config,
+	.set_vm_context_page_table_base = set_vm_context_page_table_base,
+	.invalidate_tlbs = invalidate_tlbs,
+	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index e262f2ac07a3..47c853ef1051 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -19,17 +19,10 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
-#include <linux/module.h>
-#include <linux/fdtable.h>
-#include <linux/uaccess.h>
 #include <linux/mmu_context.h>
 
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
-#include "soc15_hw_ip.h"
 #include "gc/gc_9_0_offset.h"
 #include "gc/gc_9_0_sh_mask.h"
 #include "vega10_enum.h"
@@ -50,9 +43,6 @@
 #include "gmc_v9_0.h"
 
 
-#define V9_PIPE_PER_MEC		(4)
-#define V9_QUEUES_PER_PIPE_MEC	(8)
-
 enum hqd_dequeue_request_type {
 	NO_ACTION = 0,
 	DRAIN_PIPE,
@@ -226,22 +216,21 @@ int kgd_gfx_v9_init_interrupts(struct kgd_dev *kgd, uint32_t pipe_id)
 	return 0;
 }
 
-static uint32_t get_sdma_base_addr(struct amdgpu_device *adev,
+static uint32_t get_sdma_rlc_reg_offset(struct amdgpu_device *adev,
 				unsigned int engine_id,
 				unsigned int queue_id)
 {
-	uint32_t base[2] = {
+	uint32_t sdma_engine_reg_base[2] = {
 		SOC15_REG_OFFSET(SDMA0, 0,
 				 mmSDMA0_RLC0_RB_CNTL) - mmSDMA0_RLC0_RB_CNTL,
 		SOC15_REG_OFFSET(SDMA1, 0,
 				 mmSDMA1_RLC0_RB_CNTL) - mmSDMA1_RLC0_RB_CNTL
 	};
-	uint32_t retval;
+	uint32_t retval = sdma_engine_reg_base[engine_id]
+		+ queue_id * (mmSDMA0_RLC1_RB_CNTL - mmSDMA0_RLC0_RB_CNTL);
 
-	retval = base[engine_id] + queue_id * (mmSDMA0_RLC1_RB_CNTL -
-					       mmSDMA0_RLC0_RB_CNTL);
-
-	pr_debug("sdma base address: 0x%x\n", retval);
+	pr_debug("RLC register offset for SDMA%d RLC%d: 0x%x\n", engine_id,
+			queue_id, retval);
 
 	return retval;
 }
@@ -388,71 +377,67 @@ static int kgd_hqd_sdma_load(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v9_sdma_mqd *m;
-	uint32_t sdma_base_addr, sdmax_gfx_context_cntl;
+	uint32_t sdma_rlc_reg_offset;
 	unsigned long end_jiffies;
 	uint32_t data;
 	uint64_t data64;
 	uint64_t __user *wptr64 = (uint64_t __user *)wptr;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
-	sdmax_gfx_context_cntl = m->sdma_engine_id ?
-		SOC15_REG_OFFSET(SDMA1, 0, mmSDMA1_GFX_CONTEXT_CNTL) :
-		SOC15_REG_OFFSET(SDMA0, 0, mmSDMA0_GFX_CONTEXT_CNTL);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
 		m->sdmax_rlcx_rb_cntl & (~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK));
 
 	end_jiffies = msecs_to_jiffies(2000) + jiffies;
 	while (true) {
-		data = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		data = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (data & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
-	data = RREG32(sdmax_gfx_context_cntl);
-	data = REG_SET_FIELD(data, SDMA0_GFX_CONTEXT_CNTL,
-			     RESUME_CTX, 0);
-	WREG32(sdmax_gfx_context_cntl, data);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL_OFFSET,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL_OFFSET,
 	       m->sdmax_rlcx_doorbell_offset);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_doorbell, SDMA0_RLC0_DOORBELL,
 			     ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, data);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR, m->sdmax_rlcx_rb_rptr);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR,
+				m->sdmax_rlcx_rb_rptr);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_HI,
 				m->sdmax_rlcx_rb_rptr_hi);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 1);
 	if (read_user_wptr(mm, wptr64, data64)) {
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       lower_32_bits(data64));
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR_HI,
 		       upper_32_bits(data64));
 	} else {
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR,
 		       m->sdmax_rlcx_rb_rptr);
-		WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_WPTR_HI,
+		WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_WPTR_HI,
 		       m->sdmax_rlcx_rb_rptr_hi);
 	}
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_MINOR_PTR_UPDATE, 0);
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_BASE_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE, m->sdmax_rlcx_rb_base);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_BASE_HI,
 			m->sdmax_rlcx_rb_base_hi);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_LO,
 			m->sdmax_rlcx_rb_rptr_addr_lo);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_ADDR_HI,
 			m->sdmax_rlcx_rb_rptr_addr_hi);
 
 	data = REG_SET_FIELD(m->sdmax_rlcx_rb_cntl, SDMA0_RLC0_RB_CNTL,
 			     RB_ENABLE, 1);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, data);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, data);
 
 	return 0;
 }
@@ -462,7 +447,8 @@ static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
 			     uint32_t (**dump)[2], uint32_t *n_regs)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
-	uint32_t sdma_base_addr = get_sdma_base_addr(adev, engine_id, queue_id);
+	uint32_t sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev,
+			engine_id, queue_id);
 	uint32_t i = 0, reg;
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+10)
@@ -472,15 +458,15 @@ static int kgd_hqd_sdma_dump(struct kgd_dev *kgd,
 		return -ENOMEM;
 
 	for (reg = mmSDMA0_RLC0_RB_CNTL; reg <= mmSDMA0_RLC0_DOORBELL; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_STATUS; reg <= mmSDMA0_RLC0_CSA_ADDR_HI; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_IB_SUB_REMAIN;
 	     reg <= mmSDMA0_RLC0_MINOR_PTR_UPDATE; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 	for (reg = mmSDMA0_RLC0_MIDCMD_DATA0;
 	     reg <= mmSDMA0_RLC0_MIDCMD_CNTL; reg++)
-		DUMP_REG(sdma_base_addr + reg);
+		DUMP_REG(sdma_rlc_reg_offset + reg);
 
 	WARN_ON_ONCE(i != HQD_N_REGS);
 	*n_regs = i;
@@ -514,14 +500,14 @@ static bool kgd_hqd_sdma_is_occupied(struct kgd_dev *kgd, void *mqd)
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v9_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t sdma_rlc_rb_cntl;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
 
-	sdma_rlc_rb_cntl = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	sdma_rlc_rb_cntl = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 
 	if (sdma_rlc_rb_cntl & SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK)
 		return true;
@@ -584,59 +570,52 @@ static int kgd_hqd_sdma_destroy(struct kgd_dev *kgd, void *mqd,
 {
 	struct amdgpu_device *adev = get_amdgpu_device(kgd);
 	struct v9_sdma_mqd *m;
-	uint32_t sdma_base_addr;
+	uint32_t sdma_rlc_reg_offset;
 	uint32_t temp;
 	unsigned long end_jiffies = (utimeout * HZ / 1000) + jiffies;
 
 	m = get_sdma_mqd(mqd);
-	sdma_base_addr = get_sdma_base_addr(adev, m->sdma_engine_id,
+	sdma_rlc_reg_offset = get_sdma_rlc_reg_offset(adev, m->sdma_engine_id,
 					    m->sdma_queue_id);
 
-	temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL);
+	temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL);
 	temp = temp & ~SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK;
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL, temp);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL, temp);
 
 	while (true) {
-		temp = RREG32(sdma_base_addr + mmSDMA0_RLC0_CONTEXT_STATUS);
+		temp = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_CONTEXT_STATUS);
 		if (temp & SDMA0_RLC0_CONTEXT_STATUS__IDLE_MASK)
 			break;
-		if (time_after(jiffies, end_jiffies))
+		if (time_after(jiffies, end_jiffies)) {
+			pr_err("SDMA RLC not idle in %s\n", __func__);
 			return -ETIME;
+		}
 		usleep_range(500, 1000);
 	}
 
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_DOORBELL, 0);
-	WREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL,
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_CNTL) |
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_DOORBELL, 0);
+	WREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL,
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_CNTL) |
 		SDMA0_RLC0_RB_CNTL__RB_ENABLE_MASK);
 
-	m->sdmax_rlcx_rb_rptr = RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR);
+	m->sdmax_rlcx_rb_rptr = RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR);
 	m->sdmax_rlcx_rb_rptr_hi =
-		RREG32(sdma_base_addr + mmSDMA0_RLC0_RB_RPTR_HI);
+		RREG32(sdma_rlc_reg_offset + mmSDMA0_RLC0_RB_RPTR_HI);
 
 	return 0;
 }
 
-bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-							uint8_t vmid)
+bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
+					uint8_t vmid, uint16_t *p_pasid)
 {
-	uint32_t reg;
+	uint32_t value;
 	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
 
-	reg = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
+	value = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
 		     + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__VALID_MASK;
-}
-
-uint16_t kgd_gfx_v9_get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-								uint8_t vmid)
-{
-	uint32_t reg;
-	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
+	*p_pasid = value & ATC_VMID0_PASID_MAPPING__PASID_MASK;
 
-	reg = RREG32(SOC15_REG_OFFSET(ATHUB, 0, mmATC_VMID0_PASID_MAPPING)
-		     + vmid);
-	return reg & ATC_VMID0_PASID_MAPPING__PASID_MASK;
+	return !!(value & ATC_VMID0_PASID_MAPPING__VALID_MASK);
 }
 
 static int invalidate_tlbs_with_kiq(struct amdgpu_device *adev, uint16_t pasid,
@@ -671,6 +650,8 @@ int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *) kgd;
 	int vmid, i;
+	uint16_t queried_pasid;
+	bool ret;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 	uint32_t flush_type = 0;
 
@@ -686,14 +667,14 @@ int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
-		if (kgd_gfx_v9_get_atc_vmid_pasid_mapping_valid(kgd, vmid)) {
-			if (kgd_gfx_v9_get_atc_vmid_pasid_mapping_pasid(kgd, vmid)
-				== pasid) {
-				for (i = 0; i < adev->num_vmhubs; i++)
-					amdgpu_gmc_flush_gpu_tlb(adev, vmid,
-								i, flush_type);
-				break;
-			}
+
+		ret = kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(kgd, vmid,
+				&queried_pasid);
+		if (ret && queried_pasid == pasid) {
+			for (i = 0; i < adev->num_vmhubs; i++)
+				amdgpu_gmc_flush_gpu_tlb(adev, vmid,
+							i, flush_type);
+			break;
 		}
 	}
 
@@ -777,15 +758,6 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 	return 0;
 }
 
-void kgd_gfx_v9_set_scratch_backing_va(struct kgd_dev *kgd,
-					uint64_t va, uint32_t vmid)
-{
-	/* No longer needed on GFXv9. The scratch base address is
-	 * passed to the shader by the CP. It's the user mode driver's
-	 * responsibility.
-	 */
-}
-
 void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint64_t page_table_base)
 {
@@ -811,7 +783,7 @@ void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmi
 	gfxhub_v1_0_setup_vm_pt_regs(adev, vmid, page_table_base);
 }
 
-static const struct kfd2kgd_calls kfd2kgd = {
+const struct kfd2kgd_calls gfx_v9_kfd2kgd = {
 	.program_sh_mem_settings = kgd_gfx_v9_program_sh_mem_settings,
 	.set_pasid_vmid_mapping = kgd_gfx_v9_set_pasid_vmid_mapping,
 	.init_interrupts = kgd_gfx_v9_init_interrupts,
@@ -827,19 +799,11 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.address_watch_execute = kgd_gfx_v9_address_watch_execute,
 	.wave_control_execute = kgd_gfx_v9_wave_control_execute,
 	.address_watch_get_offset = kgd_gfx_v9_address_watch_get_offset,
-	.get_atc_vmid_pasid_mapping_pasid =
-			kgd_gfx_v9_get_atc_vmid_pasid_mapping_pasid,
-	.get_atc_vmid_pasid_mapping_valid =
-			kgd_gfx_v9_get_atc_vmid_pasid_mapping_valid,
-	.set_scratch_backing_va = kgd_gfx_v9_set_scratch_backing_va,
+	.get_atc_vmid_pasid_mapping_info =
+			kgd_gfx_v9_get_atc_vmid_pasid_mapping_info,
 	.get_tile_config = kgd_gfx_v9_get_tile_config,
 	.set_vm_context_page_table_base = kgd_gfx_v9_set_vm_context_page_table_base,
 	.invalidate_tlbs = kgd_gfx_v9_invalidate_tlbs,
 	.invalidate_tlbs_vmid = kgd_gfx_v9_invalidate_tlbs_vmid,
 	.get_hive_id = amdgpu_amdkfd_get_hive_id,
 };
-
-struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
-{
-	return (struct kfd2kgd_calls *)&kfd2kgd;
-}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
index 26d8879bff9d..d9e9ad22b2bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h
@@ -55,14 +55,10 @@ uint32_t kgd_gfx_v9_address_watch_get_offset(struct kgd_dev *kgd,
 					unsigned int watch_point_id,
 					unsigned int reg_offset);
 
-bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_valid(struct kgd_dev *kgd,
-		uint8_t vmid);
-uint16_t kgd_gfx_v9_get_atc_vmid_pasid_mapping_pasid(struct kgd_dev *kgd,
-		uint8_t vmid);
+bool kgd_gfx_v9_get_atc_vmid_pasid_mapping_info(struct kgd_dev *kgd,
+					uint8_t vmid, uint16_t *p_pasid);
 void kgd_gfx_v9_set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint64_t page_table_base);
-void kgd_gfx_v9_set_scratch_backing_va(struct kgd_dev *kgd,
-					uint64_t va, uint32_t vmid);
 int kgd_gfx_v9_invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
 int kgd_gfx_v9_invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
 int kgd_gfx_v9_get_tile_config(struct kgd_dev *kgd,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6d021ecc8d59..12dbcfaa34b8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -19,9 +19,6 @@
  * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
  * OTHER DEALINGS IN THE SOFTWARE.
  */
-
-#define pr_fmt(fmt) "kfd2kgd: " fmt
-
 #include <linux/dma-buf.h>
 #include <linux/list.h>
 #include <linux/pagemap.h>
@@ -33,11 +30,6 @@
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_dma_buf.h"
 
-/* Special VM and GART address alignment needed for VI pre-Fiji due to
- * a HW bug.
- */
-#define VI_BO_SIZE_ALIGN (0x8000)
-
 /* BO flag to indicate a KFD userptr BO */
 #define AMDGPU_AMDKFD_USERPTR_BO (1ULL << 63)
 
@@ -113,11 +105,24 @@ void amdgpu_amdkfd_gpuvm_init_mem_limits(void)
 		(kfd_mem_limit.max_ttm_mem_limit >> 20));
 }
 
+/* Estimate page table size needed to represent a given memory size
+ *
+ * With 4KB pages, we need one 8 byte PTE for each 4KB of memory
+ * (factor 512, >> 9). With 2MB pages, we need one 8 byte PTE for 2MB
+ * of memory (factor 256K, >> 18). ROCm user mode tries to optimize
+ * for 2MB pages for TLB efficiency. However, small allocations and
+ * fragmented system memory still need some 4KB pages. We choose a
+ * compromise that should work in most cases without reserving too
+ * much memory for page tables unnecessarily (factor 16K, >> 14).
+ */
+#define ESTIMATE_PT_SIZE(mem_size) ((mem_size) >> 14)
+
 static int amdgpu_amdkfd_reserve_mem_limit(struct amdgpu_device *adev,
 		uint64_t size, u32 domain, bool sg)
 {
+	uint64_t reserved_for_pt =
+		ESTIMATE_PT_SIZE(amdgpu_amdkfd_total_mem_size);
 	size_t acc_size, system_mem_needed, ttm_mem_needed, vram_needed;
-	uint64_t reserved_for_pt = amdgpu_amdkfd_total_mem_size >> 9;
 	int ret = 0;
 
 	acc_size = ttm_bo_dma_acc_size(&adev->mman.bdev, size,
@@ -349,13 +354,46 @@ static int vm_update_pds(struct amdgpu_vm *vm, struct amdgpu_sync *sync)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(pd->tbo.bdev);
 	int ret;
 
-	ret = amdgpu_vm_update_directories(adev, vm);
+	ret = amdgpu_vm_update_pdes(adev, vm, false);
 	if (ret)
 		return ret;
 
 	return amdgpu_sync_fence(NULL, sync, vm->last_update, false);
 }
 
+static uint64_t get_pte_flags(struct amdgpu_device *adev, struct kgd_mem *mem)
+{
+	struct amdgpu_device *bo_adev = amdgpu_ttm_adev(mem->bo->tbo.bdev);
+	bool coherent = mem->alloc_flags & ALLOC_MEM_FLAGS_COHERENT;
+	uint32_t mapping_flags;
+
+	mapping_flags = AMDGPU_VM_PAGE_READABLE;
+	if (mem->alloc_flags & ALLOC_MEM_FLAGS_WRITABLE)
+		mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE;
+	if (mem->alloc_flags & ALLOC_MEM_FLAGS_EXECUTABLE)
+		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
+
+	switch (adev->asic_type) {
+	case CHIP_ARCTURUS:
+		if (mem->alloc_flags & ALLOC_MEM_FLAGS_VRAM) {
+			if (bo_adev == adev)
+				mapping_flags |= coherent ?
+					AMDGPU_VM_MTYPE_CC : AMDGPU_VM_MTYPE_RW;
+			else
+				mapping_flags |= AMDGPU_VM_MTYPE_UC;
+		} else {
+			mapping_flags |= coherent ?
+				AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
+		}
+		break;
+	default:
+		mapping_flags |= coherent ?
+			AMDGPU_VM_MTYPE_UC : AMDGPU_VM_MTYPE_NC;
+	}
+
+	return amdgpu_gem_va_map_flags(adev, mapping_flags);
+}
+
 /* add_bo_to_vm - Add a BO to a VM
  *
  * Everything that needs to bo done only once when a BO is first added
@@ -404,8 +442,7 @@ static int add_bo_to_vm(struct amdgpu_device *adev, struct kgd_mem *mem,
 	}
 
 	bo_va_entry->va = va;
-	bo_va_entry->pte_flags = amdgpu_gmc_get_pte_flags(adev,
-							 mem->mapping_flags);
+	bo_va_entry->pte_flags = get_pte_flags(adev, mem);
 	bo_va_entry->kgd_dev = (void *)adev;
 	list_add(&bo_va_entry->bo_list, list_bo_va);
 
@@ -586,7 +623,7 @@ static int reserve_bo_and_vm(struct kgd_mem *mem,
 	amdgpu_vm_get_pd_bo(vm, &ctx->list, &ctx->vm_pd[0]);
 
 	ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list,
-				     false, &ctx->duplicates, true);
+				     false, &ctx->duplicates);
 	if (!ret)
 		ctx->reserved = true;
 	else {
@@ -659,7 +696,7 @@ static int reserve_bo_and_cond_vms(struct kgd_mem *mem,
 	}
 
 	ret = ttm_eu_reserve_buffers(&ctx->ticket, &ctx->list,
-				     false, &ctx->duplicates, true);
+				     false, &ctx->duplicates);
 	if (!ret)
 		ctx->reserved = true;
 	else
@@ -1079,10 +1116,8 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	uint64_t user_addr = 0;
 	struct amdgpu_bo *bo;
 	struct amdgpu_bo_param bp;
-	int byte_align;
 	u32 domain, alloc_domain;
 	u64 alloc_flags;
-	uint32_t mapping_flags;
 	int ret;
 
 	/*
@@ -1135,25 +1170,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 	if ((*mem)->aql_queue)
 		size = size >> 1;
 
-	/* Workaround for TLB bug on older VI chips */
-	byte_align = (adev->family == AMDGPU_FAMILY_VI &&
-			adev->asic_type != CHIP_FIJI &&
-			adev->asic_type != CHIP_POLARIS10 &&
-			adev->asic_type != CHIP_POLARIS11 &&
-			adev->asic_type != CHIP_POLARIS12 &&
-			adev->asic_type != CHIP_VEGAM) ?
-			VI_BO_SIZE_ALIGN : 1;
-
-	mapping_flags = AMDGPU_VM_PAGE_READABLE;
-	if (flags & ALLOC_MEM_FLAGS_WRITABLE)
-		mapping_flags |= AMDGPU_VM_PAGE_WRITEABLE;
-	if (flags & ALLOC_MEM_FLAGS_EXECUTABLE)
-		mapping_flags |= AMDGPU_VM_PAGE_EXECUTABLE;
-	if (flags & ALLOC_MEM_FLAGS_COHERENT)
-		mapping_flags |= AMDGPU_VM_MTYPE_UC;
-	else
-		mapping_flags |= AMDGPU_VM_MTYPE_NC;
-	(*mem)->mapping_flags = mapping_flags;
+	(*mem)->alloc_flags = flags;
 
 	amdgpu_sync_create(&(*mem)->sync);
 
@@ -1168,7 +1185,7 @@ int amdgpu_amdkfd_gpuvm_alloc_memory_of_gpu(
 
 	memset(&bp, 0, sizeof(bp));
 	bp.size = size;
-	bp.byte_align = byte_align;
+	bp.byte_align = 1;
 	bp.domain = alloc_domain;
 	bp.flags = alloc_flags;
 	bp.type = bo_type;
@@ -1626,9 +1643,10 @@ int amdgpu_amdkfd_gpuvm_import_dmabuf(struct kgd_dev *kgd,
 
 	INIT_LIST_HEAD(&(*mem)->bo_va_list);
 	mutex_init(&(*mem)->lock);
-	(*mem)->mapping_flags =
-		AMDGPU_VM_PAGE_READABLE | AMDGPU_VM_PAGE_WRITEABLE |
-		AMDGPU_VM_PAGE_EXECUTABLE | AMDGPU_VM_MTYPE_NC;
+	(*mem)->alloc_flags =
+		((bo->preferred_domains & AMDGPU_GEM_DOMAIN_VRAM) ?
+		 ALLOC_MEM_FLAGS_VRAM : ALLOC_MEM_FLAGS_GTT) |
+		ALLOC_MEM_FLAGS_WRITABLE | ALLOC_MEM_FLAGS_EXECUTABLE;
 
 	(*mem)->bo = amdgpu_bo_ref(bo);
 	(*mem)->va = va;
@@ -1797,8 +1815,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 	}
 
 	/* Reserve all BOs and page tables for validation */
-	ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates,
-				     true);
+	ret = ttm_eu_reserve_buffers(&ticket, &resv_list, false, &duplicates);
 	WARN(!list_empty(&duplicates), "Duplicates should be empty");
 	if (ret)
 		goto out_free;
@@ -1996,7 +2013,7 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
 	}
 
 	ret = ttm_eu_reserve_buffers(&ctx.ticket, &ctx.list,
-				     false, &duplicate_save, true);
+				     false, &duplicate_save);
 	if (ret) {
 		pr_debug("Memory eviction: TTM Reserve Failed. Try again\n");
 		goto ttm_reserve_fail;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
index 1c9d40f97a9b..72232fccf61a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
@@ -2038,6 +2038,11 @@ int amdgpu_atombios_init(struct amdgpu_device *adev)
 	if (adev->is_atom_fw) {
 		amdgpu_atomfirmware_scratch_regs_init(adev);
 		amdgpu_atomfirmware_allocate_fb_scratch(adev);
+		ret = amdgpu_atomfirmware_get_mem_train_fb_loc(adev);
+		if (ret) {
+			DRM_ERROR("Failed to get mem train fb location.\n");
+			return ret;
+		}
 	} else {
 		amdgpu_atombios_scratch_regs_init(adev);
 		amdgpu_atombios_allocate_fb_scratch(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index daf687428cdb..ff4eb96bdfb5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -27,6 +27,7 @@
 #include "amdgpu_atomfirmware.h"
 #include "atom.h"
 #include "atombios.h"
+#include "soc15_hw_ip.h"
 
 bool amdgpu_atomfirmware_gpu_supports_virtualization(struct amdgpu_device *adev)
 {
@@ -120,65 +121,14 @@ union vram_info {
 	struct atom_vram_info_header_v2_3 v23;
 	struct atom_vram_info_header_v2_4 v24;
 };
-/*
- * Return vram width from integrated system info table, if available,
- * or 0 if not.
- */
-int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev)
-{
-	struct amdgpu_mode_info *mode_info = &adev->mode_info;
-	int index;
-	u16 data_offset, size;
-	union igp_info *igp_info;
-	union vram_info *vram_info;
-	u32 mem_channel_number;
-	u32 mem_channel_width;
-	u8 frev, crev;
-
-	if (adev->flags & AMD_IS_APU)
-		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
-						    integratedsysteminfo);
-	else
-		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
-						    vram_info);
 
-	/* get any igp specific overrides */
-	if (amdgpu_atom_parse_data_header(mode_info->atom_context, index, &size,
-				   &frev, &crev, &data_offset)) {
-		if (adev->flags & AMD_IS_APU) {
-			igp_info = (union igp_info *)
-				(mode_info->atom_context->bios + data_offset);
-			switch (crev) {
-			case 11:
-				mem_channel_number = igp_info->v11.umachannelnumber;
-				/* channel width is 64 */
-				return mem_channel_number * 64;
-			default:
-				return 0;
-			}
-		} else {
-			vram_info = (union vram_info *)
-				(mode_info->atom_context->bios + data_offset);
-			switch (crev) {
-			case 3:
-				mem_channel_number = vram_info->v23.vram_module[0].channel_num;
-				mem_channel_width = vram_info->v23.vram_module[0].channel_width;
-				return mem_channel_number * (1 << mem_channel_width);
-			case 4:
-				mem_channel_number = vram_info->v24.vram_module[0].channel_num;
-				mem_channel_width = vram_info->v24.vram_module[0].channel_width;
-				return mem_channel_number * (1 << mem_channel_width);
-			default:
-				return 0;
-			}
-		}
-	}
-
-	return 0;
-}
+union vram_module {
+	struct atom_vram_module_v9 v9;
+	struct atom_vram_module_v10 v10;
+};
 
-static int convert_atom_mem_type_to_vram_type (struct amdgpu_device *adev,
-					       int atom_mem_type)
+static int convert_atom_mem_type_to_vram_type(struct amdgpu_device *adev,
+					      int atom_mem_type)
 {
 	int vram_type;
 
@@ -219,19 +169,25 @@ static int convert_atom_mem_type_to_vram_type (struct amdgpu_device *adev,
 
 	return vram_type;
 }
-/*
- * Return vram type from either integrated system info table
- * or umc info table, if available, or 0 (TYPE_UNKNOWN) if not
- */
-int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev)
+
+
+int
+amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
+				  int *vram_width, int *vram_type,
+				  int *vram_vendor)
 {
 	struct amdgpu_mode_info *mode_info = &adev->mode_info;
-	int index;
+	int index, i = 0;
 	u16 data_offset, size;
 	union igp_info *igp_info;
 	union vram_info *vram_info;
+	union vram_module *vram_module;
 	u8 frev, crev;
 	u8 mem_type;
+	u8 mem_vendor;
+	u32 mem_channel_number;
+	u32 mem_channel_width;
+	u32 module_id;
 
 	if (adev->flags & AMD_IS_APU)
 		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
@@ -239,6 +195,7 @@ int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev)
 	else
 		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
 						    vram_info);
+
 	if (amdgpu_atom_parse_data_header(mode_info->atom_context,
 					  index, &size,
 					  &frev, &crev, &data_offset)) {
@@ -247,25 +204,67 @@ int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev)
 				(mode_info->atom_context->bios + data_offset);
 			switch (crev) {
 			case 11:
+				mem_channel_number = igp_info->v11.umachannelnumber;
+				/* channel width is 64 */
+				if (vram_width)
+					*vram_width = mem_channel_number * 64;
 				mem_type = igp_info->v11.memorytype;
-				return convert_atom_mem_type_to_vram_type(adev, mem_type);
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				break;
 			default:
-				return 0;
+				return -EINVAL;
 			}
 		} else {
 			vram_info = (union vram_info *)
 				(mode_info->atom_context->bios + data_offset);
+			module_id = (RREG32(adev->bios_scratch_reg_offset + 4) & 0x00ff0000) >> 16;
 			switch (crev) {
 			case 3:
-				mem_type = vram_info->v23.vram_module[0].memory_type;
-				return convert_atom_mem_type_to_vram_type(adev, mem_type);
+				if (module_id > vram_info->v23.vram_module_num)
+					module_id = 0;
+				vram_module = (union vram_module *)vram_info->v23.vram_module;
+				while (i < module_id) {
+					vram_module = (union vram_module *)
+						((u8 *)vram_module + vram_module->v9.vram_module_size);
+					i++;
+				}
+				mem_type = vram_module->v9.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_module->v9.channel_num;
+				mem_channel_width = vram_module->v9.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
+				mem_vendor = (vram_module->v9.vender_rev_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				break;
 			case 4:
-				mem_type = vram_info->v24.vram_module[0].memory_type;
-				return convert_atom_mem_type_to_vram_type(adev, mem_type);
+				if (module_id > vram_info->v24.vram_module_num)
+					module_id = 0;
+				vram_module = (union vram_module *)vram_info->v24.vram_module;
+				while (i < module_id) {
+					vram_module = (union vram_module *)
+						((u8 *)vram_module + vram_module->v10.vram_module_size);
+					i++;
+				}
+				mem_type = vram_module->v10.memory_type;
+				if (vram_type)
+					*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+				mem_channel_number = vram_module->v10.channel_num;
+				mem_channel_width = vram_module->v10.channel_width;
+				if (vram_width)
+					*vram_width = mem_channel_number * (1 << mem_channel_width);
+				mem_vendor = (vram_module->v10.vender_rev_id) & 0xF;
+				if (vram_vendor)
+					*vram_vendor = mem_vendor;
+				break;
 			default:
-				return 0;
+				return -EINVAL;
 			}
 		}
+
 	}
 
 	return 0;
@@ -464,3 +463,138 @@ int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev)
 	}
 	return -EINVAL;
 }
+
+/*
+ * Check if VBIOS supports GDDR6 training data save/restore
+ */
+static bool gddr6_mem_train_vbios_support(struct amdgpu_device *adev)
+{
+	uint16_t data_offset;
+	int index;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+					    firmwareinfo);
+	if (amdgpu_atom_parse_data_header(adev->mode_info.atom_context, index, NULL,
+					  NULL, NULL, &data_offset)) {
+		struct atom_firmware_info_v3_1 *firmware_info =
+			(struct atom_firmware_info_v3_1 *)(adev->mode_info.atom_context->bios +
+							   data_offset);
+
+		DRM_DEBUG("atom firmware capability:0x%08x.\n",
+			  le32_to_cpu(firmware_info->firmware_capability));
+
+		if (le32_to_cpu(firmware_info->firmware_capability) &
+		    ATOM_FIRMWARE_CAP_ENABLE_2STAGE_BIST_TRAINING)
+			return true;
+	}
+
+	return false;
+}
+
+static int gddr6_mem_train_support(struct amdgpu_device *adev)
+{
+	int ret;
+	uint32_t major, minor, revision, hw_v;
+
+	if (gddr6_mem_train_vbios_support(adev)) {
+		amdgpu_discovery_get_ip_version(adev, MP0_HWID, &major, &minor, &revision);
+		hw_v = HW_REV(major, minor, revision);
+		/*
+		 * treat 0 revision as a special case since register for MP0 and MMHUB is missing
+		 * for some Navi10 A0, preventing driver from discovering the hwip information since
+		 * none of the functions will be initialized, it should not cause any problems
+		 */
+		switch (hw_v) {
+		case HW_REV(11, 0, 0):
+		case HW_REV(11, 0, 5):
+			ret = 1;
+			break;
+		default:
+			DRM_ERROR("memory training vbios supports but psp hw(%08x)"
+				  " doesn't support!\n", hw_v);
+			ret = -1;
+			break;
+		}
+	} else {
+		ret = 0;
+		hw_v = -1;
+	}
+
+
+	DRM_DEBUG("mp0 hw_v %08x, ret:%d.\n", hw_v, ret);
+	return ret;
+}
+
+int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev)
+{
+	struct atom_context *ctx = adev->mode_info.atom_context;
+	unsigned char *bios = ctx->bios;
+	struct vram_reserve_block *reserved_block;
+	int index, block_number;
+	uint8_t frev, crev;
+	uint16_t data_offset, size;
+	uint32_t start_address_in_kb;
+	uint64_t offset;
+	int ret;
+
+	adev->fw_vram_usage.mem_train_support = false;
+
+	if (adev->asic_type != CHIP_NAVI10 &&
+	    adev->asic_type != CHIP_NAVI14)
+		return 0;
+
+	if (amdgpu_sriov_vf(adev))
+		return 0;
+
+	ret = gddr6_mem_train_support(adev);
+	if (ret == -1)
+		return -EINVAL;
+	else if (ret == 0)
+		return 0;
+
+	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
+					    vram_usagebyfirmware);
+	ret = amdgpu_atom_parse_data_header(ctx, index, &size, &frev, &crev,
+					    &data_offset);
+	if (ret == 0) {
+		DRM_ERROR("parse data header failed.\n");
+		return -EINVAL;
+	}
+
+	DRM_DEBUG("atom firmware common table header size:0x%04x, frev:0x%02x,"
+		  " crev:0x%02x, data_offset:0x%04x.\n", size, frev, crev, data_offset);
+	/* only support 2.1+ */
+	if (((uint16_t)frev << 8 | crev) < 0x0201) {
+		DRM_ERROR("frev:0x%02x, crev:0x%02x < 2.1 !\n", frev, crev);
+		return -EINVAL;
+	}
+
+	reserved_block = (struct vram_reserve_block *)
+		(bios + data_offset + sizeof(struct atom_common_table_header));
+	block_number = ((unsigned int)size - sizeof(struct atom_common_table_header))
+		/ sizeof(struct vram_reserve_block);
+	reserved_block += (block_number > 0) ? block_number-1 : 0;
+	DRM_DEBUG("block_number:0x%04x, last block: 0x%08xkb sz, %dkb fw, %dkb drv.\n",
+		  block_number,
+		  le32_to_cpu(reserved_block->start_address_in_kb),
+		  le16_to_cpu(reserved_block->used_by_firmware_in_kb),
+		  le16_to_cpu(reserved_block->used_by_driver_in_kb));
+	if (reserved_block->used_by_firmware_in_kb > 0) {
+		start_address_in_kb = le32_to_cpu(reserved_block->start_address_in_kb);
+		offset = (uint64_t)start_address_in_kb * ONE_KiB;
+		if ((offset & (ONE_MiB - 1)) < (4 * ONE_KiB + 1) ) {
+			offset -= ONE_MiB;
+		}
+
+		offset &= ~(ONE_MiB - 1);
+		adev->fw_vram_usage.mem_train_fb_loc = offset;
+		adev->fw_vram_usage.mem_train_support = true;
+		DRM_DEBUG("mem_train_fb_loc:0x%09llx.\n", offset);
+		ret = 0;
+	} else {
+		DRM_ERROR("used_by_firmware_in_kb is 0!\n");
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
index 5ec6f92f353c..f871af5ea6f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.h
@@ -29,8 +29,9 @@
 bool amdgpu_atomfirmware_gpu_supports_virtualization(struct amdgpu_device *adev);
 void amdgpu_atomfirmware_scratch_regs_init(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev);
-int amdgpu_atomfirmware_get_vram_width(struct amdgpu_device *adev);
-int amdgpu_atomfirmware_get_vram_type(struct amdgpu_device *adev);
+int amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
+	int *vram_width, int *vram_type, int *vram_vendor);
+int amdgpu_atomfirmware_get_mem_train_fb_loc(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_clock_info(struct amdgpu_device *adev);
 int amdgpu_atomfirmware_get_gfx_info(struct amdgpu_device *adev);
 bool amdgpu_atomfirmware_mem_ecc_supported(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index 3e35a8f2c5e5..a97fb759e2f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -613,17 +613,7 @@ static bool amdgpu_atpx_detect(void)
 	bool d3_supported = false;
 	struct pci_dev *parent_pdev;
 
-	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
-		vga_count++;
-
-		has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
-
-		parent_pdev = pci_upstream_bridge(pdev);
-		d3_supported |= parent_pdev && parent_pdev->bridge_d3;
-		amdgpu_atpx_get_quirks(pdev);
-	}
-
-	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) {
+	while ((pdev = pci_get_class(PCI_BASE_CLASS_DISPLAY << 16, pdev)) != NULL) {
 		vga_count++;
 
 		has_atpx |= (amdgpu_atpx_pci_probe_handle(pdev) == true);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 649e68c4479b..d1495e1c9289 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -33,7 +33,7 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
 {
 	unsigned long start_jiffies;
 	unsigned long end_jiffies;
-	struct dma_fence *fence = NULL;
+	struct dma_fence *fence;
 	int i, r;
 
 	start_jiffies = jiffies;
@@ -44,16 +44,14 @@ static int amdgpu_benchmark_do_move(struct amdgpu_device *adev, unsigned size,
 		if (r)
 			goto exit_do_move;
 		r = dma_fence_wait(fence, false);
+		dma_fence_put(fence);
 		if (r)
 			goto exit_do_move;
-		dma_fence_put(fence);
 	}
 	end_jiffies = jiffies;
 	r = jiffies_to_msecs(end_jiffies - start_jiffies);
 
 exit_do_move:
-	if (fence)
-		dma_fence_put(fence);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 61e38e43ad1d..85b0515c0fdc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -140,7 +140,12 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
 	return 0;
 
 error_free:
-	while (i--) {
+	for (i = 0; i < last_entry; ++i) {
+		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
+
+		amdgpu_bo_unref(&bo);
+	}
+	for (i = first_userptr; i < num_entries; ++i) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(array[i].tv.bo);
 
 		amdgpu_bo_unref(&bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index d8729285f731..a62cbc8199de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -1019,8 +1019,12 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 			 */
 			if (amdgpu_connector->shared_ddc && (ret == connector_status_connected)) {
 				struct drm_connector *list_connector;
+				struct drm_connector_list_iter iter;
 				struct amdgpu_connector *list_amdgpu_connector;
-				list_for_each_entry(list_connector, &dev->mode_config.connector_list, head) {
+
+				drm_connector_list_iter_begin(dev, &iter);
+				drm_for_each_connector_iter(list_connector,
+							    &iter) {
 					if (connector == list_connector)
 						continue;
 					list_amdgpu_connector = to_amdgpu_connector(list_connector);
@@ -1037,6 +1041,7 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 						}
 					}
 				}
+				drm_connector_list_iter_end(&iter);
 			}
 		}
 	}
@@ -1494,6 +1499,7 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector;
 	struct amdgpu_connector_atom_dig *amdgpu_dig_connector;
 	struct drm_encoder *encoder;
@@ -1508,10 +1514,12 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 		return;
 
 	/* see if we already added it */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		amdgpu_connector = to_amdgpu_connector(connector);
 		if (amdgpu_connector->connector_id == connector_id) {
 			amdgpu_connector->devices |= supported_device;
+			drm_connector_list_iter_end(&iter);
 			return;
 		}
 		if (amdgpu_connector->ddc_bus && i2c_bus->valid) {
@@ -1526,6 +1534,7 @@ amdgpu_connector_add(struct amdgpu_device *adev,
 			}
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	/* check if it's a dp bridge */
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 2e53feed40e2..a169ff16277f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -35,6 +35,7 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_gmc.h"
 #include "amdgpu_gem.h"
+#include "amdgpu_ras.h"
 
 static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 				      struct drm_amdgpu_cs_chunk_fence *data,
@@ -449,75 +450,12 @@ retry:
 	return r;
 }
 
-/* Last resort, try to evict something from the current working set */
-static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
-				struct amdgpu_bo *validated)
-{
-	uint32_t domain = validated->allowed_domains;
-	struct ttm_operation_ctx ctx = { true, false };
-	int r;
-
-	if (!p->evictable)
-		return false;
-
-	for (;&p->evictable->tv.head != &p->validated;
-	     p->evictable = list_prev_entry(p->evictable, tv.head)) {
-
-		struct amdgpu_bo_list_entry *candidate = p->evictable;
-		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(candidate->tv.bo);
-		struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-		bool update_bytes_moved_vis;
-		uint32_t other;
-
-		/* If we reached our current BO we can forget it */
-		if (bo == validated)
-			break;
-
-		/* We can't move pinned BOs here */
-		if (bo->pin_count)
-			continue;
-
-		other = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
-
-		/* Check if this BO is in one of the domains we need space for */
-		if (!(other & domain))
-			continue;
-
-		/* Check if we can move this BO somewhere else */
-		other = bo->allowed_domains & ~domain;
-		if (!other)
-			continue;
-
-		/* Good we can try to move this BO somewhere else */
-		update_bytes_moved_vis =
-				!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
-				amdgpu_bo_in_cpu_visible_vram(bo);
-		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)
-			p->bytes_moved_vis += ctx.bytes_moved;
-
-		if (unlikely(r))
-			break;
-
-		p->evictable = list_prev_entry(p->evictable, tv.head);
-		list_move(&candidate->tv.head, &p->validated);
-
-		return true;
-	}
-
-	return false;
-}
-
 static int amdgpu_cs_validate(void *param, struct amdgpu_bo *bo)
 {
 	struct amdgpu_cs_parser *p = param;
 	int r;
 
-	do {
-		r = amdgpu_cs_bo_validate(p, bo);
-	} while (r == -ENOMEM && amdgpu_cs_try_evict(p, bo));
+	r = amdgpu_cs_bo_validate(p, bo);
 	if (r)
 		return r;
 
@@ -536,7 +474,6 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 
 	list_for_each_entry(lobj, validated, tv.head) {
 		struct amdgpu_bo *bo = ttm_to_amdgpu_bo(lobj->tv.bo);
-		bool binding_userptr = false;
 		struct mm_struct *usermm;
 
 		usermm = amdgpu_ttm_tt_get_usermm(bo->tbo.ttm);
@@ -553,20 +490,14 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
 						     lobj->user_pages);
-			binding_userptr = true;
 		}
 
-		if (p->evictable == lobj)
-			p->evictable = NULL;
-
 		r = amdgpu_cs_validate(p, bo);
 		if (r)
 			return r;
 
-		if (binding_userptr) {
-			kvfree(lobj->user_pages);
-			lobj->user_pages = NULL;
-		}
+		kvfree(lobj->user_pages);
+		lobj->user_pages = NULL;
 	}
 	return 0;
 }
@@ -650,7 +581,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	}
 
 	r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
-				   &duplicates, false);
+				   &duplicates);
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("ttm_eu_reserve_buffers failed.\n");
@@ -661,9 +592,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 					  &p->bytes_moved_vis_threshold);
 	p->bytes_moved = 0;
 	p->bytes_moved_vis = 0;
-	p->evictable = list_last_entry(&p->validated,
-				       struct amdgpu_bo_list_entry,
-				       tv.head);
 
 	r = amdgpu_vm_validate_pt_bos(p->adev, &fpriv->vm,
 				      amdgpu_cs_validate, p);
@@ -915,7 +843,7 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	r = amdgpu_vm_update_directories(adev, vm);
+	r = amdgpu_vm_update_pdes(adev, vm, false);
 	if (r)
 		return r;
 
@@ -1359,6 +1287,9 @@ int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	bool reserved_buffers = false;
 	int i, r;
 
+	if (amdgpu_ras_intr_triggered())
+		return -EHWPOISON;
+
 	if (!adev->accel_working)
 		return -EBUSY;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
index 35a8d3c96fc9..08047bc4d588 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_csa.c
@@ -80,7 +80,7 @@ int amdgpu_map_static_csa(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	list_add(&csa_tv.head, &list);
 	amdgpu_vm_get_pd_bo(vm, &list, &pd);
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL, false);
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL);
 	if (r) {
 		DRM_ERROR("failed to reserve CSA,PD BOs: err=%d\n", r);
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 6614d8a6f4c8..2cdaf3b2a721 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -604,8 +604,11 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 			continue;
 		}
 
-		for (i = 0; i < num_entities; i++)
+		for (i = 0; i < num_entities; i++) {
+			mutex_lock(&ctx->adev->lock_reset);
 			drm_sched_entity_fini(&ctx->entities[0][i].entity);
+			mutex_unlock(&ctx->adev->lock_reset);
+		}
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
index 5652cc72ed3a..8e6726e0d035 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
@@ -859,6 +859,9 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 	struct amdgpu_device *adev = dev->dev_private;
 	int r = 0, i;
 
+	/* Avoid accidently unparking the sched thread during GPU reset */
+	mutex_lock(&adev->lock_reset);
+
 	/* hold on the scheduler */
 	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
 		struct amdgpu_ring *ring = adev->rings[i];
@@ -884,6 +887,8 @@ static int amdgpu_debugfs_test_ib(struct seq_file *m, void *data)
 		kthread_unpark(ring->sched.thread);
 	}
 
+	mutex_unlock(&adev->lock_reset);
+
 	return 0;
 }
 
@@ -1036,6 +1041,9 @@ static int amdgpu_debugfs_ib_preempt(void *data, u64 val)
 	if (!fences)
 		return -ENOMEM;
 
+	/* Avoid accidently unparking the sched thread during GPU reset */
+	mutex_lock(&adev->lock_reset);
+
 	/* stop the scheduler */
 	kthread_park(ring->sched.thread);
 
@@ -1075,10 +1083,11 @@ failure:
 	/* restart the scheduler */
 	kthread_unpark(ring->sched.thread);
 
+	mutex_unlock(&adev->lock_reset);
+
 	ttm_bo_unlock_delayed_workqueue(&adev->mman.bdev, resched);
 
-	if (fences)
-		kfree(fences);
+	kfree(fences);
 
 	return 0;
 }
@@ -1090,8 +1099,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 {
 	adev->debugfs_preempt =
 		debugfs_create_file("amdgpu_preempt_ib", 0600,
-				    adev->ddev->primary->debugfs_root,
-				    (void *)adev, &fops_ib_preempt);
+				    adev->ddev->primary->debugfs_root, adev,
+				    &fops_ib_preempt);
 	if (!(adev->debugfs_preempt)) {
 		DRM_ERROR("unable to create amdgpu_preempt_ib debugsfs file\n");
 		return -EIO;
@@ -1103,8 +1112,7 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
 
 void amdgpu_debugfs_preempt_cleanup(struct amdgpu_device *adev)
 {
-	if (adev->debugfs_preempt)
-		debugfs_remove(adev->debugfs_preempt);
+	debugfs_remove(adev->debugfs_preempt);
 }
 
 #else
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5a1939dbd4e3..4f76beafb2fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -65,6 +65,8 @@
 #include "amdgpu_ras.h"
 #include "amdgpu_pmu.h"
 
+#include <linux/suspend.h>
+
 MODULE_FIRMWARE("amdgpu/vega10_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/vega12_gpu_info.bin");
 MODULE_FIRMWARE("amdgpu/raven_gpu_info.bin");
@@ -78,7 +80,7 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
 
 #define AMDGPU_RESUME_MS		2000
 
-static const char *amdgpu_asic_name[] = {
+const char *amdgpu_asic_name[] = {
 	"TAHITI",
 	"PITCAIRN",
 	"VERDE",
@@ -151,6 +153,36 @@ bool amdgpu_device_is_px(struct drm_device *dev)
 	return false;
 }
 
+/**
+ * VRAM access helper functions.
+ *
+ * amdgpu_device_vram_access - read/write a buffer in vram
+ *
+ * @adev: amdgpu_device pointer
+ * @pos: offset of the buffer in vram
+ * @buf: virtual address of the buffer in system memory
+ * @size: read/write size, sizeof(@buf) must > @size
+ * @write: true - write to vram, otherwise - read from vram
+ */
+void amdgpu_device_vram_access(struct amdgpu_device *adev, loff_t pos,
+			       uint32_t *buf, size_t size, bool write)
+{
+	uint64_t last;
+	unsigned long flags;
+
+	last = size - 4;
+	for (last += pos; pos <= last; pos += 4) {
+		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
+		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
+		WREG32_NO_KIQ(mmMM_INDEX_HI, pos >> 31);
+		if (write)
+			WREG32_NO_KIQ(mmMM_DATA, *buf++);
+		else
+			*buf++ = RREG32_NO_KIQ(mmMM_DATA);
+		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
+	}
+}
+
 /*
  * MMIO register access helper functions.
  */
@@ -1023,12 +1055,6 @@ static int amdgpu_device_check_arguments(struct amdgpu_device *adev)
 
 	amdgpu_device_check_block_size(adev);
 
-	ret = amdgpu_device_get_job_timeout_settings(adev);
-	if (ret) {
-		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
-		return ret;
-	}
-
 	adev->firmware.load_type = amdgpu_ucode_get_load_type(adev, amdgpu_fw_load_type);
 
 	return ret;
@@ -1469,6 +1495,9 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 			(const struct gpu_info_firmware_v1_0 *)(adev->firmware.gpu_info_fw->data +
 								le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 
+		if (amdgpu_discovery && adev->asic_type >= CHIP_NAVI10)
+			goto parse_soc_bounding_box;
+
 		adev->gfx.config.max_shader_engines = le32_to_cpu(gpu_info_fw->gc_num_se);
 		adev->gfx.config.max_cu_per_sh = le32_to_cpu(gpu_info_fw->gc_num_cu_per_sh);
 		adev->gfx.config.max_sh_per_se = le32_to_cpu(gpu_info_fw->gc_num_sh_per_se);
@@ -1496,7 +1525,13 @@ static int amdgpu_device_parse_gpu_info_fw(struct amdgpu_device *adev)
 			adev->gfx.config.num_packer_per_sc =
 				le32_to_cpu(gpu_info_fw->num_packer_per_sc);
 		}
+
+parse_soc_bounding_box:
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
+		/*
+		 * soc bounding box info is not integrated in disocovery table,
+		 * we always need to parse it from gpu info firmware.
+		 */
 		if (hdr->version_minor == 2) {
 			const struct gpu_info_firmware_v1_2 *gpu_info_fw =
 				(const struct gpu_info_firmware_v1_2 *)(adev->firmware.gpu_info_fw->data +
@@ -1613,6 +1648,9 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
+	if (amdgpu_discovery && adev->asic_type >= CHIP_NAVI10)
+		amdgpu_discovery_get_gfx_info(adev);
+
 	amdgpu_amdkfd_device_probe(adev);
 
 	if (amdgpu_sriov_vf(adev)) {
@@ -1622,7 +1660,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	}
 
 	adev->pm.pp_feature = amdgpu_pp_feature_mask;
-	if (amdgpu_sriov_vf(adev))
+	if (amdgpu_sriov_vf(adev) || sched_policy == KFD_SCHED_POLICY_NO_HWS)
 		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
@@ -1839,6 +1877,19 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 	if (r)
 		goto init_failed;
 
+	/*
+	 * retired pages will be loaded from eeprom and reserved here,
+	 * it should be called after amdgpu_device_ip_hw_init_phase2  since
+	 * for some ASICs the RAS EEPROM code relies on SMU fully functioning
+	 * for I2C communication which only true at this point.
+	 * recovery_init may fail, but it can free all resources allocated by
+	 * itself and its failure should not stop amdgpu init process.
+	 *
+	 * Note: theoretically, this should be called before all vram allocations
+	 * to protect retired page from abusing
+	 */
+	amdgpu_ras_recovery_init(adev);
+
 	if (adev->gmc.xgmi.num_physical_nodes > 1)
 		amdgpu_xgmi_add_device(adev);
 	amdgpu_amdkfd_device_init(adev);
@@ -2006,6 +2057,7 @@ out:
  */
 static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 {
+	struct amdgpu_gpu_instance *gpu_instance;
 	int i = 0, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
@@ -2031,8 +2083,39 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 	if (r)
 		DRM_ERROR("enable mgpu fan boost failed (%d).\n", r);
 
-	/* set to low pstate by default */
-	amdgpu_xgmi_set_pstate(adev, 0);
+
+	if (adev->gmc.xgmi.num_physical_nodes > 1) {
+		mutex_lock(&mgpu_info.mutex);
+
+		/*
+		 * Reset device p-state to low as this was booted with high.
+		 *
+		 * This should be performed only after all devices from the same
+		 * hive get initialized.
+		 *
+		 * However, it's unknown how many device in the hive in advance.
+		 * As this is counted one by one during devices initializations.
+		 *
+		 * So, we wait for all XGMI interlinked devices initialized.
+		 * This may bring some delays as those devices may come from
+		 * different hives. But that should be OK.
+		 */
+		if (mgpu_info.num_dgpu == adev->gmc.xgmi.num_physical_nodes) {
+			for (i = 0; i < mgpu_info.num_gpu; i++) {
+				gpu_instance = &(mgpu_info.gpu_ins[i]);
+				if (gpu_instance->adev->flags & AMD_IS_APU)
+					continue;
+
+				r = amdgpu_xgmi_set_pstate(gpu_instance->adev, 0);
+				if (r) {
+					DRM_ERROR("pstate setting failed (%d).\n", r);
+					break;
+				}
+			}
+		}
+
+		mutex_unlock(&mgpu_info.mutex);
+	}
 
 	return 0;
 }
@@ -2220,6 +2303,12 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		/* displays are handled in phase1 */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)
 			continue;
+		/* PSP lost connection when err_event_athub occurs */
+		if (amdgpu_ras_intr_triggered() &&
+		    adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_PSP) {
+			adev->ip_blocks[i].status.hw = false;
+			continue;
+		}
 		/* XXX handle errors */
 		r = adev->ip_blocks[i].version->funcs->suspend(adev);
 		/* XXX handle errors */
@@ -2231,17 +2320,17 @@ static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 		/* handle putting the SMC in the appropriate state */
 		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_SMC) {
 			if (is_support_sw_smu(adev)) {
-				/* todo */
+				r = smu_set_mp1_state(&adev->smu, adev->mp1_state);
 			} else if (adev->powerplay.pp_funcs &&
 					   adev->powerplay.pp_funcs->set_mp1_state) {
 				r = adev->powerplay.pp_funcs->set_mp1_state(
 					adev->powerplay.pp_handle,
 					adev->mp1_state);
-				if (r) {
-					DRM_ERROR("SMC failed to set mp1 state %d, %d\n",
-						  adev->mp1_state, r);
-					return r;
-				}
+			}
+			if (r) {
+				DRM_ERROR("SMC failed to set mp1 state %d, %d\n",
+					  adev->mp1_state, r);
+				return r;
 			}
 		}
 
@@ -2556,6 +2645,73 @@ static void amdgpu_device_xgmi_reset_func(struct work_struct *__work)
 			 adev->asic_reset_res, adev->ddev->unique);
 }
 
+static int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
+{
+	char *input = amdgpu_lockup_timeout;
+	char *timeout_setting = NULL;
+	int index = 0;
+	long timeout;
+	int ret = 0;
+
+	/*
+	 * By default timeout for non compute jobs is 10000.
+	 * And there is no timeout enforced on compute jobs.
+	 * In SR-IOV or passthrough mode, timeout for compute
+	 * jobs are 10000 by default.
+	 */
+	adev->gfx_timeout = msecs_to_jiffies(10000);
+	adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
+	if (amdgpu_sriov_vf(adev) || amdgpu_passthrough(adev))
+		adev->compute_timeout = adev->gfx_timeout;
+	else
+		adev->compute_timeout = MAX_SCHEDULE_TIMEOUT;
+
+	if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
+		while ((timeout_setting = strsep(&input, ",")) &&
+				strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENGTH)) {
+			ret = kstrtol(timeout_setting, 0, &timeout);
+			if (ret)
+				return ret;
+
+			if (timeout == 0) {
+				index++;
+				continue;
+			} else if (timeout < 0) {
+				timeout = MAX_SCHEDULE_TIMEOUT;
+			} else {
+				timeout = msecs_to_jiffies(timeout);
+			}
+
+			switch (index++) {
+			case 0:
+				adev->gfx_timeout = timeout;
+				break;
+			case 1:
+				adev->compute_timeout = timeout;
+				break;
+			case 2:
+				adev->sdma_timeout = timeout;
+				break;
+			case 3:
+				adev->video_timeout = timeout;
+				break;
+			default:
+				break;
+			}
+		}
+		/*
+		 * There is only one value specified and
+		 * it should apply to all non-compute jobs.
+		 */
+		if (index == 1) {
+			adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
+			if (amdgpu_sriov_vf(adev) || amdgpu_passthrough(adev))
+				adev->compute_timeout = adev->gfx_timeout;
+		}
+	}
+
+	return ret;
+}
 
 /**
  * amdgpu_device_init - initialize the driver
@@ -2583,7 +2739,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	adev->ddev = ddev;
 	adev->pdev = pdev;
 	adev->flags = flags;
-	adev->asic_type = flags & AMD_ASIC_MASK;
+
+	if (amdgpu_force_asic_type >= 0 && amdgpu_force_asic_type < CHIP_LAST)
+		adev->asic_type = amdgpu_force_asic_type;
+	else
+		adev->asic_type = flags & AMD_ASIC_MASK;
+
 	adev->usec_timeout = AMDGPU_MAX_USEC_TIMEOUT;
 	if (amdgpu_emu_mode == 1)
 		adev->usec_timeout *= 2;
@@ -2726,6 +2887,12 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	r = amdgpu_device_get_job_timeout_settings(adev);
+	if (r) {
+		dev_err(adev->dev, "invalid lockup_timeout parameter syntax\n");
+		return r;
+	}
+
 	/* doorbell bar mapping and doorbell index init*/
 	amdgpu_device_doorbell_init(adev);
 
@@ -2885,6 +3052,13 @@ fence_driver_init:
 			DRM_INFO("amdgpu: acceleration disabled, skipping benchmarks\n");
 	}
 
+	/*
+	 * Register gpu instance before amdgpu_device_enable_mgpu_fan_boost.
+	 * Otherwise the mgpu fan boost feature will be skipped due to the
+	 * gpu instance is counted less.
+	 */
+	amdgpu_register_gpu_instance(adev);
+
 	/* enable clockgating, etc. after ib tests, etc. since some blocks require
 	 * explicit gating rather than handling it automatically.
 	 */
@@ -2935,7 +3109,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 	int r;
 
 	DRM_INFO("amdgpu: finishing device.\n");
+	flush_delayed_work(&adev->delayed_init_work);
 	adev->shutdown = true;
+
 	/* disable all interrupts */
 	amdgpu_irq_disable_all(adev);
 	if (adev->mode_info.mode_config_initialized){
@@ -2953,7 +3129,6 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 		adev->firmware.gpu_info_fw = NULL;
 	}
 	adev->accel_working = false;
-	cancel_delayed_work_sync(&adev->delayed_init_work);
 	/* free i2c buses */
 	if (!amdgpu_device_has_dc_support(adev))
 		amdgpu_i2c_fini(adev);
@@ -3007,6 +3182,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	struct amdgpu_device *adev;
 	struct drm_crtc *crtc;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	int r;
 
 	if (dev == NULL || dev->dev_private == NULL) {
@@ -3029,9 +3205,11 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	if (!amdgpu_device_has_dc_support(adev)) {
 		/* turn off display hw */
 		drm_modeset_lock_all(dev);
-		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
-		}
+		drm_connector_list_iter_begin(dev, &iter);
+		drm_for_each_connector_iter(connector, &iter)
+			drm_helper_connector_dpms(connector,
+						  DRM_MODE_DPMS_OFF);
+		drm_connector_list_iter_end(&iter);
 		drm_modeset_unlock_all(dev);
 			/* unpin the front buffers and cursors */
 		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -3082,15 +3260,11 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 	 */
 	amdgpu_bo_evict_vram(adev);
 
-	pci_save_state(dev->pdev);
 	if (suspend) {
+		pci_save_state(dev->pdev);
 		/* Shut down the device */
 		pci_disable_device(dev->pdev);
 		pci_set_power_state(dev->pdev, PCI_D3hot);
-	} else {
-		r = amdgpu_asic_reset(adev);
-		if (r)
-			DRM_ERROR("amdgpu asic reset failed\n");
 	}
 
 	return 0;
@@ -3110,6 +3284,7 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 {
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct drm_crtc *crtc;
 	int r = 0;
@@ -3180,9 +3355,13 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 
 			/* turn on display hw */
 			drm_modeset_lock_all(dev);
-			list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-				drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
-			}
+
+			drm_connector_list_iter_begin(dev, &iter);
+			drm_for_each_connector_iter(connector, &iter)
+				drm_helper_connector_dpms(connector,
+							  DRM_MODE_DPMS_ON);
+			drm_connector_list_iter_end(&iter);
+
 			drm_modeset_unlock_all(dev);
 		}
 		amdgpu_fbdev_set_suspend(adev, 0);
@@ -3628,11 +3807,6 @@ static int amdgpu_do_asic_reset(struct amdgpu_hive_info *hive,
 						break;
 				}
 			}
-
-			list_for_each_entry(tmp_adev, device_list_handle,
-					gmc.xgmi.head) {
-				amdgpu_ras_reserve_bad_pages(tmp_adev);
-			}
 		}
 	}
 
@@ -3736,25 +3910,18 @@ static bool amdgpu_device_lock_adev(struct amdgpu_device *adev, bool trylock)
 		adev->mp1_state = PP_MP1_STATE_NONE;
 		break;
 	}
-	/* Block kfd: SRIOV would do it separately */
-	if (!amdgpu_sriov_vf(adev))
-                amdgpu_amdkfd_pre_reset(adev);
 
 	return true;
 }
 
 static void amdgpu_device_unlock_adev(struct amdgpu_device *adev)
 {
-	/*unlock kfd: SRIOV would do it separately */
-	if (!amdgpu_sriov_vf(adev))
-                amdgpu_amdkfd_post_reset(adev);
 	amdgpu_vf_error_trans_all(adev);
 	adev->mp1_state = PP_MP1_STATE_NONE;
 	adev->in_gpu_reset = 0;
 	mutex_unlock(&adev->lock_reset);
 }
 
-
 /**
  * amdgpu_device_gpu_recover - reset the asic and recover scheduler
  *
@@ -3774,11 +3941,24 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	struct amdgpu_hive_info *hive = NULL;
 	struct amdgpu_device *tmp_adev = NULL;
 	int i, r = 0;
+	bool in_ras_intr = amdgpu_ras_intr_triggered();
+
+	/*
+	 * Flush RAM to disk so that after reboot
+	 * the user can read log and see why the system rebooted.
+	 */
+	if (in_ras_intr && amdgpu_ras_get_context(adev)->reboot) {
+
+		DRM_WARN("Emergency reboot.");
+
+		ksys_sync_helper();
+		emergency_restart();
+	}
 
 	need_full_reset = job_signaled = false;
 	INIT_LIST_HEAD(&device_list);
 
-	dev_info(adev->dev, "GPU reset begin!\n");
+	dev_info(adev->dev, "GPU %s begin!\n", in_ras_intr ? "jobs stop":"reset");
 
 	cancel_delayed_work_sync(&adev->delayed_init_work);
 
@@ -3805,9 +3985,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		return 0;
 	}
 
+	/* Block kfd: SRIOV would do it separately */
+	if (!amdgpu_sriov_vf(adev))
+                amdgpu_amdkfd_pre_reset(adev);
+
 	/* Build list of devices to reset */
 	if  (adev->gmc.xgmi.num_physical_nodes > 1) {
 		if (!hive) {
+			/*unlock kfd: SRIOV would do it separately */
+			if (!amdgpu_sriov_vf(adev))
+		                amdgpu_amdkfd_post_reset(adev);
 			amdgpu_device_unlock_adev(adev);
 			return -ENODEV;
 		}
@@ -3823,17 +4010,22 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		device_list_handle = &device_list;
 	}
 
-	/*
-	 * Mark these ASICs to be reseted as untracked first
-	 * And add them back after reset completed
-	 */
-	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head)
-		amdgpu_unregister_gpu_instance(tmp_adev);
-
 	/* block all schedulers and reset given job's ring */
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
+		if (tmp_adev != adev) {
+			amdgpu_device_lock_adev(tmp_adev, false);
+			if (!amdgpu_sriov_vf(tmp_adev))
+			                amdgpu_amdkfd_pre_reset(tmp_adev);
+		}
+
+		/*
+		 * Mark these ASICs to be reseted as untracked first
+		 * And add them back after reset completed
+		 */
+		amdgpu_unregister_gpu_instance(tmp_adev);
+
 		/* disable ras on ALL IPs */
-		if (amdgpu_device_ip_need_full_reset(tmp_adev))
+		if (!in_ras_intr && amdgpu_device_ip_need_full_reset(tmp_adev))
 			amdgpu_ras_suspend(tmp_adev);
 
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
@@ -3843,10 +4035,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 				continue;
 
 			drm_sched_stop(&ring->sched, job ? &job->base : NULL);
+
+			if (in_ras_intr)
+				amdgpu_job_stop_all_jobs_on_sched(&ring->sched);
 		}
 	}
 
 
+	if (in_ras_intr)
+		goto skip_sched_resume;
+
 	/*
 	 * Must check guilty signal here since after this point all old
 	 * HW fences are force signaled.
@@ -3857,9 +4055,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	    dma_fence_is_signaled(job->base.s_fence->parent))
 		job_signaled = true;
 
-	if (!amdgpu_device_ip_need_full_reset(adev))
-		device_list_handle = &device_list;
-
 	if (job_signaled) {
 		dev_info(adev->dev, "Guilty job already signaled, skipping HW reset");
 		goto skip_hw_reset;
@@ -3881,7 +4076,6 @@ retry:	/* Rest of adevs pre asic reset from XGMI hive. */
 		if (tmp_adev == adev)
 			continue;
 
-		amdgpu_device_lock_adev(tmp_adev, false);
 		r = amdgpu_device_pre_asic_reset(tmp_adev,
 						 NULL,
 						 &need_full_reset);
@@ -3909,6 +4103,7 @@ skip_hw_reset:
 
 	/* Post ASIC reset for all devs .*/
 	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
+
 		for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
 			struct amdgpu_ring *ring = tmp_adev->rings[i];
 
@@ -3930,12 +4125,18 @@ skip_hw_reset:
 
 		if (r) {
 			/* bad news, how to tell it to userspace ? */
-			dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
+			dev_info(tmp_adev->dev, "GPU reset(%d) failed\n", atomic_read(&tmp_adev->gpu_reset_counter));
 			amdgpu_vf_error_put(tmp_adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
 		} else {
-			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&adev->gpu_reset_counter));
+			dev_info(tmp_adev->dev, "GPU reset(%d) succeeded!\n", atomic_read(&tmp_adev->gpu_reset_counter));
 		}
+	}
 
+skip_sched_resume:
+	list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
+		/*unlock kfd: SRIOV would do it separately */
+		if (!in_ras_intr && !amdgpu_sriov_vf(tmp_adev))
+	                amdgpu_amdkfd_post_reset(tmp_adev);
 		amdgpu_device_unlock_adev(tmp_adev);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
index 1481899f86c1..f95092741c38 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
@@ -134,20 +134,10 @@ static int hw_id_map[MAX_HWIP] = {
 
 static int amdgpu_discovery_read_binary(struct amdgpu_device *adev, uint8_t *binary)
 {
-	uint32_t *p = (uint32_t *)binary;
 	uint64_t vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
-	uint64_t pos = vram_size - BINARY_MAX_SIZE;
-	unsigned long flags;
-
-	while (pos < vram_size) {
-		spin_lock_irqsave(&adev->mmio_idx_lock, flags);
-		WREG32_NO_KIQ(mmMM_INDEX, ((uint32_t)pos) | 0x80000000);
-		WREG32_NO_KIQ(mmMM_INDEX_HI, pos >> 31);
-		*p++ = RREG32_NO_KIQ(mmMM_DATA);
-		spin_unlock_irqrestore(&adev->mmio_idx_lock, flags);
-		pos += 4;
-	}
+	uint64_t pos = vram_size - DISCOVERY_TMR_SIZE;
 
+	amdgpu_device_vram_access(adev, pos, (uint32_t *)binary, DISCOVERY_TMR_SIZE, false);
 	return 0;
 }
 
@@ -179,7 +169,7 @@ int amdgpu_discovery_init(struct amdgpu_device *adev)
 	uint16_t checksum;
 	int r;
 
-	adev->discovery = kzalloc(BINARY_MAX_SIZE, GFP_KERNEL);
+	adev->discovery = kzalloc(DISCOVERY_TMR_SIZE, GFP_KERNEL);
 	if (!adev->discovery)
 		return -ENOMEM;
 
@@ -333,7 +323,7 @@ int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev)
 }
 
 int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
-				    int *major, int *minor)
+				    int *major, int *minor, int *revision)
 {
 	struct binary_header *bhdr;
 	struct ip_discovery_header *ihdr;
@@ -369,6 +359,8 @@ int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
 					*major = ip->major;
 				if (minor)
 					*minor = ip->minor;
+				if (revision)
+					*revision = ip->revision;
 				return 0;
 			}
 			ip_offset += sizeof(*ip) + 4 * (ip->num_base_address - 1);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
index 85b8c4d4d576..ba78e15d9b05 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.h
@@ -24,11 +24,13 @@
 #ifndef __AMDGPU_DISCOVERY__
 #define __AMDGPU_DISCOVERY__
 
+#define DISCOVERY_TMR_SIZE  (64 << 10)
+
 int amdgpu_discovery_init(struct amdgpu_device *adev);
 void amdgpu_discovery_fini(struct amdgpu_device *adev);
 int amdgpu_discovery_reg_base_init(struct amdgpu_device *adev);
 int amdgpu_discovery_get_ip_version(struct amdgpu_device *adev, int hw_id,
-                                    int *major, int *minor);
+                                    int *major, int *minor, int *revision);
 int amdgpu_discovery_get_gfx_info(struct amdgpu_device *adev);
 
 #endif /* __AMDGPU_DISCOVERY__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 1d4aaa9580f4..3cadb0b76f22 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -370,11 +370,13 @@ void amdgpu_display_print_display_setup(struct drm_device *dev)
 	struct amdgpu_connector *amdgpu_connector;
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
+	struct drm_connector_list_iter iter;
 	uint32_t devices;
 	int i = 0;
 
+	drm_connector_list_iter_begin(dev, &iter);
 	DRM_INFO("AMDGPU Display Connectors\n");
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_for_each_connector_iter(connector, &iter) {
 		amdgpu_connector = to_amdgpu_connector(connector);
 		DRM_INFO("Connector %d:\n", i);
 		DRM_INFO("  %s\n", connector->name);
@@ -438,6 +440,7 @@ void amdgpu_display_print_display_setup(struct drm_device *dev)
 		}
 		i++;
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 /**
@@ -511,7 +514,7 @@ uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev,
 	 * Also, don't allow GTT domain if the BO doens't have USWC falg set.
 	 */
 	if (adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type <= CHIP_RAVEN &&
+	    adev->asic_type < CHIP_RAVEN &&
 	    (adev->flags & AMD_IS_APU) &&
 	    (bo_flags & AMDGPU_GEM_CREATE_CPU_GTT_USWC) &&
 	    amdgpu_bo_support_uswc(bo_flags) &&
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
index 61f108ec2b5c..e2eec7b66334 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c
@@ -34,27 +34,12 @@
 #include "amdgpu.h"
 #include "amdgpu_display.h"
 #include "amdgpu_gem.h"
+#include "amdgpu_dma_buf.h"
 #include <drm/amdgpu_drm.h>
 #include <linux/dma-buf.h>
 #include <linux/dma-fence-array.h>
 
 /**
- * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table
- * implementation
- * @obj: GEM buffer object (BO)
- *
- * Returns:
- * A scatter/gather table for the pinned pages of the BO's memory.
- */
-struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
-{
-	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	int npages = bo->tbo.num_pages;
-
-	return drm_prime_pages_to_sg(bo->tbo.ttm->pages, npages);
-}
-
-/**
  * amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
  * @obj: GEM BO
  *
@@ -179,92 +164,126 @@ err_fences_put:
 }
 
 /**
- * amdgpu_dma_buf_map_attach - &dma_buf_ops.attach implementation
- * @dma_buf: Shared DMA buffer
+ * amdgpu_dma_buf_attach - &dma_buf_ops.attach implementation
+ *
+ * @dmabuf: DMA-buf where we attach to
+ * @attach: attachment to add
+ *
+ * Add the attachment as user to the exported DMA-buf.
+ */
+static int amdgpu_dma_buf_attach(struct dma_buf *dmabuf,
+				 struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	int r;
+
+	if (attach->dev->driver == adev->dev->driver)
+		return 0;
+
+	r = amdgpu_bo_reserve(bo, false);
+	if (unlikely(r != 0))
+		return r;
+
+	/*
+	 * We only create shared fences for internal use, but importers
+	 * of the dmabuf rely on exclusive fences for implicitly
+	 * tracking write hazards. As any of the current fences may
+	 * correspond to a write, we need to convert all existing
+	 * fences on the reservation object into a single exclusive
+	 * fence.
+	 */
+	r = __dma_resv_make_exclusive(bo->tbo.base.resv);
+	if (r)
+		return r;
+
+	bo->prime_shared_count++;
+	amdgpu_bo_unreserve(bo);
+	return 0;
+}
+
+/**
+ * amdgpu_dma_buf_detach - &dma_buf_ops.detach implementation
+ *
+ * @dmabuf: DMA-buf where we remove the attachment from
+ * @attach: the attachment to remove
+ *
+ * Called when an attachment is removed from the DMA-buf.
+ */
+static void amdgpu_dma_buf_detach(struct dma_buf *dmabuf,
+				  struct dma_buf_attachment *attach)
+{
+	struct drm_gem_object *obj = dmabuf->priv;
+	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
+		bo->prime_shared_count--;
+}
+
+/**
+ * amdgpu_dma_buf_map - &dma_buf_ops.map_dma_buf implementation
  * @attach: DMA-buf attachment
+ * @dir: DMA direction
  *
  * Makes sure that the shared DMA buffer can be accessed by the target device.
  * For now, simply pins it to the GTT domain, where it should be accessible by
  * all DMA devices.
  *
  * Returns:
- * 0 on success or a negative error code on failure.
+ * sg_table filled with the DMA addresses to use or ERR_PRT with negative error
+ * code.
  */
-static int amdgpu_dma_buf_map_attach(struct dma_buf *dma_buf,
-				     struct dma_buf_attachment *attach)
+static struct sg_table *amdgpu_dma_buf_map(struct dma_buf_attachment *attach,
+					   enum dma_data_direction dir)
 {
+	struct dma_buf *dma_buf = attach->dmabuf;
 	struct drm_gem_object *obj = dma_buf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+	struct sg_table *sgt;
 	long r;
 
-	r = drm_gem_map_attach(dma_buf, attach);
-	if (r)
-		return r;
-
-	r = amdgpu_bo_reserve(bo, false);
-	if (unlikely(r != 0))
-		goto error_detach;
-
-
-	if (attach->dev->driver != adev->dev->driver) {
-		/*
-		 * We only create shared fences for internal use, but importers
-		 * of the dmabuf rely on exclusive fences for implicitly
-		 * tracking write hazards. As any of the current fences may
-		 * correspond to a write, we need to convert all existing
-		 * fences on the reservation object into a single exclusive
-		 * fence.
-		 */
-		r = __dma_resv_make_exclusive(bo->tbo.base.resv);
-		if (r)
-			goto error_unreserve;
-	}
-
-	/* pin buffer into GTT */
 	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r)
-		goto error_unreserve;
+		return ERR_PTR(r);
 
-	if (attach->dev->driver != adev->dev->driver)
-		bo->prime_shared_count++;
+	sgt = drm_prime_pages_to_sg(bo->tbo.ttm->pages, bo->tbo.num_pages);
+	if (IS_ERR(sgt))
+		return sgt;
 
-error_unreserve:
-	amdgpu_bo_unreserve(bo);
+	if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+			      DMA_ATTR_SKIP_CPU_SYNC))
+		goto error_free;
 
-error_detach:
-	if (r)
-		drm_gem_map_detach(dma_buf, attach);
-	return r;
+	return sgt;
+
+error_free:
+	sg_free_table(sgt);
+	kfree(sgt);
+	return ERR_PTR(-ENOMEM);
 }
 
 /**
- * amdgpu_dma_buf_map_detach - &dma_buf_ops.detach implementation
- * @dma_buf: Shared DMA buffer
+ * amdgpu_dma_buf_unmap - &dma_buf_ops.unmap_dma_buf implementation
  * @attach: DMA-buf attachment
+ * @sgt: sg_table to unmap
+ * @dir: DMA direction
  *
  * This is called when a shared DMA buffer no longer needs to be accessible by
  * another device. For now, simply unpins the buffer from GTT.
  */
-static void amdgpu_dma_buf_map_detach(struct dma_buf *dma_buf,
-				      struct dma_buf_attachment *attach)
+static void amdgpu_dma_buf_unmap(struct dma_buf_attachment *attach,
+				 struct sg_table *sgt,
+				 enum dma_data_direction dir)
 {
-	struct drm_gem_object *obj = dma_buf->priv;
+	struct drm_gem_object *obj = attach->dmabuf->priv;
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
-	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	int ret = 0;
-
-	ret = amdgpu_bo_reserve(bo, true);
-	if (unlikely(ret != 0))
-		goto error;
 
+	dma_unmap_sg(attach->dev, sgt->sgl, sgt->nents, dir);
+	sg_free_table(sgt);
+	kfree(sgt);
 	amdgpu_bo_unpin(bo);
-	if (attach->dev->driver != adev->dev->driver && bo->prime_shared_count)
-		bo->prime_shared_count--;
-	amdgpu_bo_unreserve(bo);
-
-error:
-	drm_gem_map_detach(dma_buf, attach);
 }
 
 /**
@@ -308,10 +327,11 @@ static int amdgpu_dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 }
 
 const struct dma_buf_ops amdgpu_dmabuf_ops = {
-	.attach = amdgpu_dma_buf_map_attach,
-	.detach = amdgpu_dma_buf_map_detach,
-	.map_dma_buf = drm_gem_map_dma_buf,
-	.unmap_dma_buf = drm_gem_unmap_dma_buf,
+	.dynamic_mapping = true,
+	.attach = amdgpu_dma_buf_attach,
+	.detach = amdgpu_dma_buf_detach,
+	.map_dma_buf = amdgpu_dma_buf_map,
+	.unmap_dma_buf = amdgpu_dma_buf_unmap,
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_dma_buf_begin_cpu_access,
 	.mmap = drm_gem_dmabuf_mmap,
@@ -321,7 +341,6 @@ const struct dma_buf_ops amdgpu_dmabuf_ops = {
 
 /**
  * amdgpu_gem_prime_export - &drm_driver.gem_prime_export implementation
- * @dev: DRM device
  * @gobj: GEM BO
  * @flags: Flags such as DRM_CLOEXEC and DRM_RDWR.
  *
@@ -350,31 +369,28 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 }
 
 /**
- * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table
- * implementation
+ * amdgpu_dma_buf_create_obj - create BO for DMA-buf import
+ *
  * @dev: DRM device
- * @attach: DMA-buf attachment
- * @sg: Scatter/gather table
+ * @dma_buf: DMA-buf
  *
- * Imports shared DMA buffer memory exported by another device.
+ * Creates an empty SG BO for DMA-buf import.
  *
  * Returns:
  * A new GEM BO of the given DRM device, representing the memory
  * described by the given DMA-buf attachment and scatter/gather table.
  */
-struct drm_gem_object *
-amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
-				 struct dma_buf_attachment *attach,
-				 struct sg_table *sg)
+static struct drm_gem_object *
+amdgpu_dma_buf_create_obj(struct drm_device *dev, struct dma_buf *dma_buf)
 {
-	struct dma_resv *resv = attach->dmabuf->resv;
+	struct dma_resv *resv = dma_buf->resv;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_bo *bo;
 	struct amdgpu_bo_param bp;
 	int ret;
 
 	memset(&bp, 0, sizeof(bp));
-	bp.size = attach->dmabuf->size;
+	bp.size = dma_buf->size;
 	bp.byte_align = PAGE_SIZE;
 	bp.domain = AMDGPU_GEM_DOMAIN_CPU;
 	bp.flags = 0;
@@ -385,11 +401,9 @@ amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 	if (ret)
 		goto error;
 
-	bo->tbo.sg = sg;
-	bo->tbo.ttm->sg = sg;
 	bo->allowed_domains = AMDGPU_GEM_DOMAIN_GTT;
 	bo->preferred_domains = AMDGPU_GEM_DOMAIN_GTT;
-	if (attach->dmabuf->ops != &amdgpu_dmabuf_ops)
+	if (dma_buf->ops != &amdgpu_dmabuf_ops)
 		bo->prime_shared_count = 1;
 
 	dma_resv_unlock(resv);
@@ -405,15 +419,15 @@ error:
  * @dev: DRM device
  * @dma_buf: Shared DMA buffer
  *
- * The main work is done by the &drm_gem_prime_import helper, which in turn
- * uses &amdgpu_gem_prime_import_sg_table.
+ * Import a dma_buf into a the driver and potentially create a new GEM object.
  *
  * Returns:
  * GEM BO representing the shared DMA buffer for the given device.
  */
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
-					    struct dma_buf *dma_buf)
+					       struct dma_buf *dma_buf)
 {
+	struct dma_buf_attachment *attach;
 	struct drm_gem_object *obj;
 
 	if (dma_buf->ops == &amdgpu_dmabuf_ops) {
@@ -428,5 +442,17 @@ struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 		}
 	}
 
-	return drm_gem_prime_import(dev, dma_buf);
+	obj = amdgpu_dma_buf_create_obj(dev, dma_buf);
+	if (IS_ERR(obj))
+		return obj;
+
+	attach = dma_buf_dynamic_attach(dma_buf, dev->dev, true);
+	if (IS_ERR(attach)) {
+		drm_gem_object_put(obj);
+		return ERR_CAST(attach);
+	}
+
+	get_dma_buf(dma_buf);
+	obj->import_attach = attach;
+	return obj;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
index 5012e6ab58f1..ec447a7b6b28 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.h
@@ -25,11 +25,6 @@
 
 #include <drm/drm_gem.h>
 
-struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj);
-struct drm_gem_object *
-amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
-				 struct dma_buf_attachment *attach,
-				 struct sg_table *sg);
 struct dma_buf *amdgpu_gem_prime_export(struct drm_gem_object *gobj,
 					int flags);
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 5803fcbae22f..9cc270efee7c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -911,7 +911,8 @@ int amdgpu_dpm_get_sclk(struct amdgpu_device *adev, bool low)
 	if (is_support_sw_smu(adev)) {
 		ret = smu_get_dpm_freq_range(&adev->smu, SMU_GFXCLK,
 					     low ? &clk_freq : NULL,
-					     !low ? &clk_freq : NULL);
+					     !low ? &clk_freq : NULL,
+					     true);
 		if (ret)
 			return 0;
 		return clk_freq * 100;
@@ -928,7 +929,8 @@ int amdgpu_dpm_get_mclk(struct amdgpu_device *adev, bool low)
 	if (is_support_sw_smu(adev)) {
 		ret = smu_get_dpm_freq_range(&adev->smu, SMU_UCLK,
 					     low ? &clk_freq : NULL,
-					     !low ? &clk_freq : NULL);
+					     !low ? &clk_freq : NULL,
+					     true);
 		if (ret)
 			return 0;
 		return clk_freq * 100;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 1c5c0fd76dbf..2cfb677272af 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -298,12 +298,6 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_get_current_power_state(adev) \
 		((adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle))
 
-#define amdgpu_smu_get_current_power_state(adev) \
-		((adev)->smu.ppt_funcs->get_current_power_state(&((adev)->smu)))
-
-#define amdgpu_smu_set_power_state(adev) \
-		((adev)->smu.ppt_funcs->set_power_state(&((adev)->smu)))
-
 #define amdgpu_dpm_get_pp_num_states(adev, data) \
 		((adev)->powerplay.pp_funcs->get_pp_num_states((adev)->powerplay.pp_handle, data))
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 4da1d7fb10f4..0ffc9447b573 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -43,6 +43,8 @@
 
 #include "amdgpu_amdkfd.h"
 
+#include "amdgpu_ras.h"
+
 /*
  * KMS wrapper.
  * - 3.0.0 - initial driver
@@ -82,13 +84,12 @@
  * - 3.33.0 - Fixes for GDS ENOMEM failures in AMDGPU_CS.
  * - 3.34.0 - Non-DC can flip correctly between buffers with different pitches
  * - 3.35.0 - Add drm_amdgpu_info_device::tcc_disabled_mask
+ * - 3.36.0 - Allow reading more status registers on si/cik
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	35
+#define KMS_DRIVER_MINOR	36
 #define KMS_DRIVER_PATCHLEVEL	0
 
-#define AMDGPU_MAX_TIMEOUT_PARAM_LENTH	256
-
 int amdgpu_vram_limit = 0;
 int amdgpu_vis_vram_limit = 0;
 int amdgpu_gart_size = -1; /* auto */
@@ -101,7 +102,7 @@ int amdgpu_disp_priority = 0;
 int amdgpu_hw_i2c = 0;
 int amdgpu_pcie_gen2 = -1;
 int amdgpu_msi = -1;
-char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENTH];
+char amdgpu_lockup_timeout[AMDGPU_MAX_TIMEOUT_PARAM_LENGTH];
 int amdgpu_dpm = -1;
 int amdgpu_fw_load_type = -1;
 int amdgpu_aspm = -1;
@@ -128,11 +129,7 @@ char *amdgpu_disable_cu = NULL;
 char *amdgpu_virtual_display = NULL;
 /* OverDrive(bit 14) disabled by default*/
 uint amdgpu_pp_feature_mask = 0xffffbfff;
-int amdgpu_ngg = 0;
-int amdgpu_prim_buf_per_se = 0;
-int amdgpu_pos_buf_per_se = 0;
-int amdgpu_cntl_sb_buf_per_se = 0;
-int amdgpu_param_buf_per_se = 0;
+uint amdgpu_force_long_training = 0;
 int amdgpu_job_hang_limit = 0;
 int amdgpu_lbpw = -1;
 int amdgpu_compute_multipipe = -1;
@@ -146,12 +143,13 @@ int amdgpu_mcbp = 0;
 int amdgpu_discovery = -1;
 int amdgpu_mes = 0;
 int amdgpu_noretry = 1;
+int amdgpu_force_asic_type = -1;
 
 struct amdgpu_mgpu_info mgpu_info = {
 	.mutex = __MUTEX_INITIALIZER(mgpu_info.mutex),
 };
 int amdgpu_ras_enable = -1;
-uint amdgpu_ras_mask = 0xfffffffb;
+uint amdgpu_ras_mask = 0xffffffff;
 
 /**
  * DOC: vramlimit (int)
@@ -244,16 +242,21 @@ module_param_named(msi, amdgpu_msi, int, 0444);
  *
  * The format can be [Non-Compute] or [GFX,Compute,SDMA,Video]. That is there can be one or
  * multiple values specified. 0 and negative values are invalidated. They will be adjusted
- * to default timeout.
- *  - With one value specified, the setting will apply to all non-compute jobs.
- *  - With multiple values specified, the first one will be for GFX. The second one is for Compute.
- *    And the third and fourth ones are for SDMA and Video.
+ * to the default timeout.
+ *
+ * - With one value specified, the setting will apply to all non-compute jobs.
+ * - With multiple values specified, the first one will be for GFX.
+ *   The second one is for Compute. The third and fourth ones are
+ *   for SDMA and Video.
+ *
  * By default(with no lockup_timeout settings), the timeout for all non-compute(GFX, SDMA and Video)
  * jobs is 10000. And there is no timeout enforced on compute jobs.
  */
-MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: 10000 for non-compute jobs and infinity timeout for compute jobs."
+MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms (default: for bare metal 10000 for non-compute jobs and infinity timeout for compute jobs; "
+		"for passthrough or sriov, 10000 for all jobs."
 		" 0: keep default value. negative: infinity timeout), "
-		"format is [Non-Compute] or [GFX,Compute,SDMA,Video]");
+		"format: for bare metal [Non-Compute] or [GFX,Compute,SDMA,Video]; "
+		"for passthrough or sriov [all jobs] or [GFX,Compute,SDMA,Video].");
 module_param_string(lockup_timeout, amdgpu_lockup_timeout, sizeof(amdgpu_lockup_timeout), 0444);
 
 /**
@@ -392,6 +395,14 @@ MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
 module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
 
 /**
+ * DOC: forcelongtraining (uint)
+ * Force long memory training in resume.
+ * The default is zero, indicates short training in resume.
+ */
+MODULE_PARM_DESC(forcelongtraining, "force memory long training");
+module_param_named(forcelongtraining, amdgpu_force_long_training, uint, 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).
@@ -449,42 +460,6 @@ MODULE_PARM_DESC(virtual_display,
 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 Parameter 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 Parameter 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.
  */
@@ -616,6 +591,16 @@ MODULE_PARM_DESC(noretry,
 	"Disable retry faults (0 = retry enabled, 1 = retry disabled (default))");
 module_param_named(noretry, amdgpu_noretry, int, 0644);
 
+/**
+ * DOC: force_asic_type (int)
+ * A non negative value used to specify the asic type for all supported GPUs.
+ */
+MODULE_PARM_DESC(force_asic_type,
+	"A non negative value used to specify the asic type for all supported GPUs");
+module_param_named(force_asic_type, amdgpu_force_asic_type, int, 0444);
+
+
+
 #ifdef CONFIG_HSA_AMD
 /**
  * DOC: sched_policy (int)
@@ -1013,15 +998,17 @@ static const struct pci_device_id pciidlist[] = {
 	{0x1002, 0x731B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	{0x1002, 0x731F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI10},
 	/* Navi14 */
-	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
-	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7340, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7341, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x7347, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
+	{0x1002, 0x734F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI14},
 
 	/* Renoir */
 	{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU|AMD_EXP_HW_SUPPORT},
 
 	/* Navi12 */
 	{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
+	{0x1002, 0x7362, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12|AMD_EXP_HW_SUPPORT},
 
 	{0, 0, 0}
 };
@@ -1127,7 +1114,10 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 {
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
-	DRM_ERROR("Device removal is currently not supported outside of fbcon\n");
+#ifdef MODULE
+	if (THIS_MODULE->state != MODULE_STATE_GOING)
+#endif
+		DRM_ERROR("Hotplug removal is not supported\n");
 	drm_dev_unplug(dev);
 	drm_dev_put(dev);
 	pci_disable_device(pdev);
@@ -1140,6 +1130,9 @@ amdgpu_pci_shutdown(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 	struct amdgpu_device *adev = dev->dev_private;
 
+	if (amdgpu_ras_intr_triggered())
+		return;
+
 	/* if we are running in a VM, make sure the device
 	 * torn down properly on reboot/shutdown.
 	 * unfortunately we can't detect certain
@@ -1174,8 +1167,13 @@ static int amdgpu_pmops_resume(struct device *dev)
 static int amdgpu_pmops_freeze(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_dev->dev_private;
+	int r;
 
-	return amdgpu_device_suspend(drm_dev, false, true);
+	r = amdgpu_device_suspend(drm_dev, false, true);
+	if (r)
+		return r;
+	return amdgpu_asic_reset(adev);
 }
 
 static int amdgpu_pmops_thaw(struct device *dev)
@@ -1347,66 +1345,6 @@ int amdgpu_file_to_fpriv(struct file *filp, struct amdgpu_fpriv **fpriv)
 	return 0;
 }
 
-int amdgpu_device_get_job_timeout_settings(struct amdgpu_device *adev)
-{
-	char *input = amdgpu_lockup_timeout;
-	char *timeout_setting = NULL;
-	int index = 0;
-	long timeout;
-	int ret = 0;
-
-	/*
-	 * By default timeout for non compute jobs is 10000.
-	 * And there is no timeout enforced on compute jobs.
-	 */
-	adev->gfx_timeout = msecs_to_jiffies(10000);
-	adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
-	adev->compute_timeout = MAX_SCHEDULE_TIMEOUT;
-
-	if (strnlen(input, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
-		while ((timeout_setting = strsep(&input, ",")) &&
-				strnlen(timeout_setting, AMDGPU_MAX_TIMEOUT_PARAM_LENTH)) {
-			ret = kstrtol(timeout_setting, 0, &timeout);
-			if (ret)
-				return ret;
-
-			if (timeout == 0) {
-				index++;
-				continue;
-			} else if (timeout < 0) {
-				timeout = MAX_SCHEDULE_TIMEOUT;
-			} else {
-				timeout = msecs_to_jiffies(timeout);
-			}
-
-			switch (index++) {
-			case 0:
-				adev->gfx_timeout = timeout;
-				break;
-			case 1:
-				adev->compute_timeout = timeout;
-				break;
-			case 2:
-				adev->sdma_timeout = timeout;
-				break;
-			case 3:
-				adev->video_timeout = timeout;
-				break;
-			default:
-				break;
-			}
-		}
-		/*
-		 * There is only one value specified and
-		 * it should apply to all non-compute jobs.
-		 */
-		if (index == 1)
-			adev->sdma_timeout = adev->video_timeout = adev->gfx_timeout;
-	}
-
-	return ret;
-}
-
 static bool
 amdgpu_get_crtc_scanout_position(struct drm_device *dev, unsigned int pipe,
 				 bool in_vblank_irq, int *vpos, int *hpos,
@@ -1445,8 +1383,6 @@ static struct drm_driver kms_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = amdgpu_gem_prime_export,
 	.gem_prime_import = amdgpu_gem_prime_import,
-	.gem_prime_get_sg_table = amdgpu_gem_prime_get_sg_table,
-	.gem_prime_import_sg_table = amdgpu_gem_prime_import_sg_table,
 	.gem_prime_vmap = amdgpu_gem_prime_vmap,
 	.gem_prime_vunmap = amdgpu_gem_prime_vunmap,
 	.gem_prime_mmap = amdgpu_gem_prime_mmap,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
index 571a6dfb473e..61fcf247a638 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
@@ -37,12 +37,14 @@ amdgpu_link_encoder_connector(struct drm_device *dev)
 {
 	struct amdgpu_device *adev = dev->dev_private;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector;
 	struct drm_encoder *encoder;
 	struct amdgpu_encoder *amdgpu_encoder;
 
+	drm_connector_list_iter_begin(dev, &iter);
 	/* walk the list and link encoders to connectors */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_for_each_connector_iter(connector, &iter) {
 		amdgpu_connector = to_amdgpu_connector(connector);
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			amdgpu_encoder = to_amdgpu_encoder(encoder);
@@ -55,6 +57,7 @@ amdgpu_link_encoder_connector(struct drm_device *dev)
 			}
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 void amdgpu_encoder_set_active_device(struct drm_encoder *encoder)
@@ -62,8 +65,10 @@ void amdgpu_encoder_set_active_device(struct drm_encoder *encoder)
 	struct drm_device *dev = encoder->dev;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 			amdgpu_encoder->active_device = amdgpu_encoder->devices & amdgpu_connector->devices;
@@ -72,6 +77,7 @@ void amdgpu_encoder_set_active_device(struct drm_encoder *encoder)
 				  amdgpu_connector->devices, encoder->encoder_type);
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 struct drm_connector *
@@ -79,15 +85,20 @@ amdgpu_get_connector_for_encoder(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
-	struct drm_connector *connector;
+	struct drm_connector *connector, *found = NULL;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		amdgpu_connector = to_amdgpu_connector(connector);
-		if (amdgpu_encoder->active_device & amdgpu_connector->devices)
-			return connector;
+		if (amdgpu_encoder->active_device & amdgpu_connector->devices) {
+			found = connector;
+			break;
+		}
 	}
-	return NULL;
+	drm_connector_list_iter_end(&iter);
+	return found;
 }
 
 struct drm_connector *
@@ -95,15 +106,20 @@ amdgpu_get_connector_for_encoder_init(struct drm_encoder *encoder)
 {
 	struct drm_device *dev = encoder->dev;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
-	struct drm_connector *connector;
+	struct drm_connector *connector, *found = NULL;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		amdgpu_connector = to_amdgpu_connector(connector);
-		if (amdgpu_encoder->devices & amdgpu_connector->devices)
-			return connector;
+		if (amdgpu_encoder->devices & amdgpu_connector->devices) {
+			found = connector;
+			break;
+		}
 	}
-	return NULL;
+	drm_connector_list_iter_end(&iter);
+	return found;
 }
 
 struct drm_encoder *amdgpu_get_external_encoder(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 23085b352cf2..377fe20bce23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -462,18 +462,7 @@ int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
 			timeout = adev->gfx_timeout;
 			break;
 		case AMDGPU_RING_TYPE_COMPUTE:
-			/*
-			 * For non-sriov case, no timeout enforce
-			 * on compute ring by default. Unless user
-			 * specifies a timeout for compute ring.
-			 *
-			 * For sriov case, always use the timeout
-			 * as gfx ring
-			 */
-			if (!amdgpu_sriov_vf(ring->adev))
-				timeout = adev->compute_timeout;
-			else
-				timeout = adev->gfx_timeout;
+			timeout = adev->compute_timeout;
 			break;
 		case AMDGPU_RING_TYPE_SDMA:
 			timeout = adev->sdma_timeout;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 5e8bdded265f..19705e399905 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -71,7 +71,7 @@
  */
 static int amdgpu_gart_dummy_page_init(struct amdgpu_device *adev)
 {
-	struct page *dummy_page = adev->mman.bdev.glob->dummy_read_page;
+	struct page *dummy_page = ttm_bo_glob.dummy_read_page;
 
 	if (adev->dummy_page_addr)
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 8ceb44925947..4277125a79ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -175,7 +175,7 @@ void amdgpu_gem_object_close(struct drm_gem_object *obj,
 
 	amdgpu_vm_get_pd_bo(vm, &list, &vm_pd);
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates, false);
+	r = ttm_eu_reserve_buffers(&ticket, &list, false, &duplicates);
 	if (r) {
 		dev_err(adev->dev, "leaking bo va because "
 			"we fail to reserve bo (%d)\n", r);
@@ -527,13 +527,41 @@ static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 			goto error;
 	}
 
-	r = amdgpu_vm_update_directories(adev, vm);
+	r = amdgpu_vm_update_pdes(adev, vm, false);
 
 error:
 	if (r && r != -ERESTARTSYS)
 		DRM_ERROR("Couldn't update BO_VA (%d)\n", r);
 }
 
+/**
+ * amdgpu_gem_va_map_flags - map GEM UAPI flags into hardware flags
+ *
+ * @adev: amdgpu_device pointer
+ * @flags: GEM UAPI flags
+ *
+ * Returns the GEM UAPI flags mapped into hardware for the ASIC.
+ */
+uint64_t amdgpu_gem_va_map_flags(struct amdgpu_device *adev, uint32_t flags)
+{
+	uint64_t pte_flag = 0;
+
+	if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
+		pte_flag |= AMDGPU_PTE_EXECUTABLE;
+	if (flags & AMDGPU_VM_PAGE_READABLE)
+		pte_flag |= AMDGPU_PTE_READABLE;
+	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
+		pte_flag |= AMDGPU_PTE_WRITEABLE;
+	if (flags & AMDGPU_VM_PAGE_PRT)
+		pte_flag |= AMDGPU_PTE_PRT;
+
+	if (adev->gmc.gmc_funcs->map_mtype)
+		pte_flag |= amdgpu_gmc_map_mtype(adev,
+						 flags & AMDGPU_VM_MTYPE_MASK);
+
+	return pte_flag;
+}
+
 int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
@@ -613,7 +641,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &list, &vm_pd);
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates, false);
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, &duplicates);
 	if (r)
 		goto error_unref;
 
@@ -631,7 +659,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 
 	switch (args->operation) {
 	case AMDGPU_VA_OP_MAP:
-		va_flags = amdgpu_gmc_get_pte_flags(adev, args->flags);
+		va_flags = amdgpu_gem_va_map_flags(adev, args->flags);
 		r = amdgpu_vm_bo_map(adev, bo_va, args->va_address,
 				     args->offset_in_bo, args->map_size,
 				     va_flags);
@@ -646,7 +674,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 						args->map_size);
 		break;
 	case AMDGPU_VA_OP_REPLACE:
-		va_flags = amdgpu_gmc_get_pte_flags(adev, args->flags);
+		va_flags = amdgpu_gem_va_map_flags(adev, args->flags);
 		r = amdgpu_vm_bo_replace_map(adev, bo_va, args->va_address,
 					     args->offset_in_bo, args->map_size,
 					     va_flags);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
index 0b66d2e6b5d5..e0f025dd1b14 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.h
@@ -67,6 +67,7 @@ int amdgpu_gem_mmap_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int amdgpu_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 			      struct drm_file *filp);
+uint64_t amdgpu_gem_va_map_flags(struct amdgpu_device *adev, uint32_t flags);
 int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp);
 int amdgpu_gem_op_ioctl(struct drm_device *dev, void *data,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index f9bef3154b99..e00b46180d2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "amdgpu_gfx.h"
 #include "amdgpu_rlc.h"
+#include "amdgpu_ras.h"
 
 /* delay 0.1 second to enable gfx off feature */
 #define GFX_OFF_DELAY_ENABLE         msecs_to_jiffies(100)
@@ -231,12 +232,10 @@ void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev)
 
 void amdgpu_gfx_graphics_queue_acquire(struct amdgpu_device *adev)
 {
-	int i, queue, pipe, me;
+	int i, queue, me;
 
 	for (i = 0; i < AMDGPU_MAX_GFX_QUEUES; ++i) {
 		queue = i % adev->gfx.me.num_queue_per_pipe;
-		pipe = (i / adev->gfx.me.num_queue_per_pipe)
-			% adev->gfx.me.num_pipe_per_me;
 		me = (i / adev->gfx.me.num_queue_per_pipe)
 		      / adev->gfx.me.num_pipe_per_me;
 
@@ -320,8 +319,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 	return r;
 }
 
-void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring,
-			      struct amdgpu_irq_src *irq)
+void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring)
 {
 	amdgpu_device_wb_free(ring->adev, ring->adev->virt.reg_val_offs);
 	amdgpu_ring_fini(ring);
@@ -456,8 +454,6 @@ void amdgpu_gfx_mqd_sw_fini(struct amdgpu_device *adev)
 	}
 
 	ring = &adev->gfx.kiq.ring;
-	if (adev->asic_type >= CHIP_NAVI10 && amdgpu_async_gfx_ring)
-		kfree(adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS]);
 	kfree(adev->gfx.mec.mqd_backup[AMDGPU_MAX_COMPUTE_RINGS]);
 	amdgpu_bo_free_kernel(&ring->mqd_obj,
 			      &ring->mqd_gpu_addr,
@@ -569,3 +565,102 @@ void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable)
 
 	mutex_unlock(&adev->gfx.gfx_off_mutex);
 }
+
+int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "gfx_err_count",
+		.debugfs_name = "gfx_err_inject",
+	};
+	struct ras_ih_if ih_info = {
+		.cb = amdgpu_gfx_process_ras_data_cb,
+	};
+
+	if (!adev->gfx.ras_if) {
+		adev->gfx.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->gfx.ras_if)
+			return -ENOMEM;
+		adev->gfx.ras_if->block = AMDGPU_RAS_BLOCK__GFX;
+		adev->gfx.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->gfx.ras_if->sub_block_index = 0;
+		strcpy(adev->gfx.ras_if->name, "gfx");
+	}
+	fs_info.head = ih_info.head = *adev->gfx.ras_if;
+
+	r = amdgpu_ras_late_init(adev, adev->gfx.ras_if,
+				 &fs_info, &ih_info);
+	if (r)
+		goto free;
+
+	if (amdgpu_ras_is_supported(adev, adev->gfx.ras_if->block)) {
+		r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
+		if (r)
+			goto late_fini;
+	} else {
+		/* free gfx ras_if if ras is not supported */
+		r = 0;
+		goto free;
+	}
+
+	return 0;
+late_fini:
+	amdgpu_ras_late_fini(adev, adev->gfx.ras_if, &ih_info);
+free:
+	kfree(adev->gfx.ras_if);
+	adev->gfx.ras_if = NULL;
+	return r;
+}
+
+void amdgpu_gfx_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX) &&
+			adev->gfx.ras_if) {
+		struct ras_common_if *ras_if = adev->gfx.ras_if;
+		struct ras_ih_if ih_info = {
+			.head = *ras_if,
+			.cb = amdgpu_gfx_process_ras_data_cb,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
+
+int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
+		void *err_data,
+		struct amdgpu_iv_entry *entry)
+{
+	/* TODO ue will trigger an interrupt.
+	 *
+	 * When “Full RAS” is enabled, the per-IP interrupt sources should
+	 * be disabled and the driver should only look for the aggregated
+	 * interrupt via sync flood
+	 */
+	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) {
+		kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+		if (adev->gfx.funcs->query_ras_error_count)
+			adev->gfx.funcs->query_ras_error_count(adev, err_data);
+		amdgpu_ras_reset_gpu(adev, 0);
+	}
+	return AMDGPU_RAS_SUCCESS;
+}
+
+int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev,
+				  struct amdgpu_irq_src *source,
+				  struct amdgpu_iv_entry *entry)
+{
+	struct ras_common_if *ras_if = adev->gfx.ras_if;
+	struct ras_dispatch_if ih_data = {
+		.entry = entry,
+	};
+
+	if (!ras_if)
+		return 0;
+
+	ih_data.head = *ras_if;
+
+	DRM_ERROR("CP ECC ERROR IRQ\n");
+	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
index 6ee4021910e2..0ae0a2715b0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h
@@ -201,28 +201,6 @@ struct amdgpu_gfx_funcs {
 	int (*query_ras_error_count) (struct amdgpu_device *adev, void *ras_error_status);
 };
 
-struct amdgpu_ngg_buf {
-	struct amdgpu_bo	*bo;
-	uint64_t		gpu_addr;
-	uint32_t		size;
-	uint32_t		bo_size;
-};
-
-enum {
-	NGG_PRIM = 0,
-	NGG_POS,
-	NGG_CNTL,
-	NGG_PARAM,
-	NGG_BUF_MAX
-};
-
-struct amdgpu_ngg {
-	struct amdgpu_ngg_buf	buf[NGG_BUF_MAX];
-	uint32_t		gds_reserve_addr;
-	uint32_t		gds_reserve_size;
-	bool			init;
-};
-
 struct sq_work {
 	struct work_struct	work;
 	unsigned ih_data;
@@ -247,7 +225,7 @@ struct amdgpu_me {
 	uint32_t			num_me;
 	uint32_t			num_pipe_per_me;
 	uint32_t			num_queue_per_pipe;
-	void				*mqd_backup[AMDGPU_MAX_GFX_RINGS + 1];
+	void				*mqd_backup[AMDGPU_MAX_GFX_RINGS];
 
 	/* These are the resources for which amdgpu takes ownership */
 	DECLARE_BITMAP(queue_bitmap, AMDGPU_MAX_GFX_QUEUES);
@@ -289,6 +267,7 @@ struct amdgpu_gfx {
 	uint32_t			mec2_feature_version;
 	bool				mec_fw_write_wait;
 	bool				me_fw_write_wait;
+	bool				cp_fw_write_wait;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
@@ -311,9 +290,6 @@ struct amdgpu_gfx {
 	uint32_t                        grbm_soft_reset;
 	uint32_t                        srbm_soft_reset;
 
-	/* NGG */
-	struct amdgpu_ngg		ngg;
-
 	/* gfx off */
 	bool                            gfx_off_state; /* true: enabled, false: disabled */
 	struct mutex                    gfx_off_mutex;
@@ -355,8 +331,7 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev,
 			     struct amdgpu_ring *ring,
 			     struct amdgpu_irq_src *irq);
 
-void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring,
-			      struct amdgpu_irq_src *irq);
+void amdgpu_gfx_kiq_free_ring(struct amdgpu_ring *ring);
 
 void amdgpu_gfx_kiq_fini(struct amdgpu_device *adev);
 int amdgpu_gfx_kiq_init(struct amdgpu_device *adev,
@@ -384,5 +359,12 @@ void amdgpu_gfx_bit_to_me_queue(struct amdgpu_device *adev, int bit,
 bool amdgpu_gfx_is_me_queue_enabled(struct amdgpu_device *adev, int me,
 				    int pipe, int queue);
 void amdgpu_gfx_off_ctrl(struct amdgpu_device *adev, bool enable);
-
+int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev);
+void amdgpu_gfx_ras_fini(struct amdgpu_device *adev);
+int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
+		void *err_data,
+		struct amdgpu_iv_entry *entry);
+int amdgpu_gfx_cp_ecc_error_irq(struct amdgpu_device *adev,
+				  struct amdgpu_irq_src *source,
+				  struct amdgpu_iv_entry *entry);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 5790db61fa2c..a12f33c0f5df 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -27,6 +27,8 @@
 #include <linux/io-64-nonatomic-lo-hi.h>
 
 #include "amdgpu.h"
+#include "amdgpu_ras.h"
+#include "amdgpu_xgmi.h"
 
 /**
  * amdgpu_gmc_get_pde_for_bo - get the PDE for a BO
@@ -305,3 +307,29 @@ bool amdgpu_gmc_filter_faults(struct amdgpu_device *adev, uint64_t addr,
 	gmc->fault_hash[hash].idx = gmc->last_fault++;
 	return false;
 }
+
+int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (adev->umc.funcs && adev->umc.funcs->ras_late_init) {
+		r = adev->umc.funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
+	if (adev->mmhub.funcs && adev->mmhub.funcs->ras_late_init) {
+		r = adev->mmhub.funcs->ras_late_init(adev);
+		if (r)
+			return r;
+	}
+
+	return amdgpu_xgmi_ras_late_init(adev);
+}
+
+void amdgpu_gmc_ras_fini(struct amdgpu_device *adev)
+{
+	amdgpu_umc_ras_fini(adev);
+	amdgpu_mmhub_ras_fini(adev);
+	amdgpu_xgmi_ras_fini(adev);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index b6e1d98ef01e..b499a3de8bb6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -77,6 +77,7 @@ struct amdgpu_gmc_fault {
 struct amdgpu_vmhub {
 	uint32_t	ctx0_ptb_addr_lo32;
 	uint32_t	ctx0_ptb_addr_hi32;
+	uint32_t	vm_inv_eng0_sem;
 	uint32_t	vm_inv_eng0_req;
 	uint32_t	vm_inv_eng0_ack;
 	uint32_t	vm_context0_cntl;
@@ -99,12 +100,15 @@ struct amdgpu_gmc_funcs {
 				   unsigned pasid);
 	/* enable/disable PRT support */
 	void (*set_prt)(struct amdgpu_device *adev, bool enable);
-	/* set pte flags based per asic */
-	uint64_t (*get_vm_pte_flags)(struct amdgpu_device *adev,
-				     uint32_t flags);
+	/* map mtype to hardware flags */
+	uint64_t (*map_mtype)(struct amdgpu_device *adev, uint32_t flags);
 	/* get the pde for a given mc addr */
 	void (*get_vm_pde)(struct amdgpu_device *adev, int level,
 			   u64 *dst, u64 *flags);
+	/* get the pte flags to use for a BO VA mapping */
+	void (*get_vm_pte)(struct amdgpu_device *adev,
+			   struct amdgpu_bo_va_mapping *mapping,
+			   uint64_t *flags);
 };
 
 struct amdgpu_xgmi {
@@ -120,21 +124,52 @@ struct amdgpu_xgmi {
 	/* gpu list in the same hive */
 	struct list_head head;
 	bool supported;
+	struct ras_common_if *ras_if;
 };
 
 struct amdgpu_gmc {
+	/* FB's physical address in MMIO space (for CPU to
+	 * map FB). This is different compared to the agp/
+	 * gart/vram_start/end field as the later is from
+	 * GPU's view and aper_base is from CPU's view.
+	 */
 	resource_size_t		aper_size;
 	resource_size_t		aper_base;
 	/* for some chips with <= 32MB we need to lie
 	 * about vram size near mc fb location */
 	u64			mc_vram_size;
 	u64			visible_vram_size;
+	/* AGP aperture start and end in MC address space
+	 * Driver find a hole in the MC address space
+	 * to place AGP by setting MC_VM_AGP_BOT/TOP registers
+	 * Under VMID0, logical address == MC address. AGP
+	 * aperture maps to physical bus or IOVA addressed.
+	 * AGP aperture is used to simulate FB in ZFB case.
+	 * AGP aperture is also used for page table in system
+	 * memory (mainly for APU).
+	 *
+	 */
 	u64			agp_size;
 	u64			agp_start;
 	u64			agp_end;
+	/* GART aperture start and end in MC address space
+	 * Driver find a hole in the MC address space
+	 * to place GART by setting VM_CONTEXT0_PAGE_TABLE_START/END_ADDR
+	 * registers
+	 * Under VMID0, logical address inside GART aperture will
+	 * be translated through gpuvm gart page table to access
+	 * paged system memory
+	 */
 	u64			gart_size;
 	u64			gart_start;
 	u64			gart_end;
+	/* Frame buffer aperture of this GPU device. Different from
+	 * fb_start (see below), this only covers the local GPU device.
+	 * Driver get fb_start from MC_VM_FB_LOCATION_BASE (set by vbios)
+	 * and calculate vram_start of this local device by adding an
+	 * offset inside the XGMI hive.
+	 * Under VMID0, logical address == MC address
+	 */
 	u64			vram_start;
 	u64			vram_end;
 	/* FB region , it's same as local vram region in single GPU, in XGMI
@@ -153,6 +188,7 @@ struct amdgpu_gmc {
 	uint32_t                fw_version;
 	struct amdgpu_irq_src	vm_fault;
 	uint32_t		vram_type;
+	uint8_t			vram_vendor;
 	uint32_t                srbm_soft_reset;
 	bool			prt_warning;
 	uint64_t		stolen_size;
@@ -177,15 +213,14 @@ struct amdgpu_gmc {
 
 	struct amdgpu_xgmi xgmi;
 	struct amdgpu_irq_src	ecc_irq;
-	struct ras_common_if    *umc_ras_if;
-	struct ras_common_if    *mmhub_ras_if;
 };
 
 #define amdgpu_gmc_flush_gpu_tlb(adev, vmid, vmhub, type) ((adev)->gmc.gmc_funcs->flush_gpu_tlb((adev), (vmid), (vmhub), (type)))
 #define amdgpu_gmc_emit_flush_gpu_tlb(r, vmid, addr) (r)->adev->gmc.gmc_funcs->emit_flush_gpu_tlb((r), (vmid), (addr))
 #define amdgpu_gmc_emit_pasid_mapping(r, vmid, pasid) (r)->adev->gmc.gmc_funcs->emit_pasid_mapping((r), (vmid), (pasid))
+#define amdgpu_gmc_map_mtype(adev, flags) (adev)->gmc.gmc_funcs->map_mtype((adev),(flags))
 #define amdgpu_gmc_get_vm_pde(adev, level, dst, flags) (adev)->gmc.gmc_funcs->get_vm_pde((adev), (level), (dst), (flags))
-#define amdgpu_gmc_get_pte_flags(adev, flags) (adev)->gmc.gmc_funcs->get_vm_pte_flags((adev),(flags))
+#define amdgpu_gmc_get_vm_pte(adev, mapping, flags) (adev)->gmc.gmc_funcs->get_vm_pte((adev), (mapping), (flags))
 
 /**
  * amdgpu_gmc_vram_full_visible - Check if full VRAM is visible through the BAR
@@ -230,5 +265,7 @@ void amdgpu_gmc_agp_location(struct amdgpu_device *adev,
 			     struct amdgpu_gmc *mc);
 bool amdgpu_gmc_filter_faults(struct amdgpu_device *adev, uint64_t addr,
 			      uint16_t pasid, uint64_t timestamp);
+int amdgpu_gmc_ras_late_init(struct amdgpu_device *adev);
+void amdgpu_gmc_ras_fini(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index 53734da1c2df..6f9289735e31 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -282,7 +282,7 @@ static int amdgpu_vmid_grab_reserved(struct amdgpu_vm *vm,
 	    !dma_fence_is_later(updates, (*id)->flushed_updates))
 	    updates = NULL;
 
-	if ((*id)->owner != vm->entity.fence_context ||
+	if ((*id)->owner != vm->direct.fence_context ||
 	    job->vm_pd_addr != (*id)->pd_gpu_addr ||
 	    updates || !(*id)->last_flush ||
 	    ((*id)->last_flush->context != fence_context &&
@@ -349,7 +349,7 @@ static int amdgpu_vmid_grab_used(struct amdgpu_vm *vm,
 		struct dma_fence *flushed;
 
 		/* Check all the prerequisites to using this VMID */
-		if ((*id)->owner != vm->entity.fence_context)
+		if ((*id)->owner != vm->direct.fence_context)
 			continue;
 
 		if ((*id)->pd_gpu_addr != job->vm_pd_addr)
@@ -449,7 +449,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
 	}
 
 	id->pd_gpu_addr = job->vm_pd_addr;
-	id->owner = vm->entity.fence_context;
+	id->owner = vm->direct.fence_context;
 
 	if (job->vm_needs_flush) {
 		dma_fence_put(id->last_flush);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 2a3f5ec298db..30d540d23b77 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -87,10 +87,13 @@ static void amdgpu_hotplug_work_func(struct work_struct *work)
 	struct drm_device *dev = adev->ddev;
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 
 	mutex_lock(&mode_config->mutex);
-	list_for_each_entry(connector, &mode_config->connector_list, head)
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter)
 		amdgpu_connector_hotplug(connector);
+	drm_connector_list_iter_end(&iter);
 	mutex_unlock(&mode_config->mutex);
 	/* Just fire off a uevent and let userspace tell us what to do */
 	drm_helper_hpd_irq_event(dev);
@@ -153,6 +156,20 @@ irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 	ret = amdgpu_ih_process(adev, &adev->irq.ih);
 	if (ret == IRQ_HANDLED)
 		pm_runtime_mark_last_busy(dev->dev);
+
+	/* For the hardware that cannot enable bif ring for both ras_controller_irq
+         * and ras_err_evnet_athub_irq ih cookies, the driver has to poll status
+	 * register to check whether the interrupt is triggered or not, and properly
+	 * ack the interrupt if it is there
+	 */
+	if (adev->nbio.funcs &&
+	    adev->nbio.funcs->handle_ras_controller_intr_no_bifring)
+		adev->nbio.funcs->handle_ras_controller_intr_no_bifring(adev);
+
+	if (adev->nbio.funcs &&
+	    adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring)
+		adev->nbio.funcs->handle_ras_err_event_athub_intr_no_bifring(adev);
+
 	return ret;
 }
 
@@ -228,10 +245,19 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	adev->irq.msi_enabled = false;
 
 	if (amdgpu_msi_ok(adev)) {
-		int ret = pci_enable_msi(adev->pdev);
-		if (!ret) {
+		int nvec = pci_msix_vec_count(adev->pdev);
+		unsigned int flags;
+
+		if (nvec <= 0) {
+			flags = PCI_IRQ_MSI;
+		} else {
+			flags = PCI_IRQ_MSI | PCI_IRQ_MSIX;
+		}
+		/* we only need one vector */
+		nvec = pci_alloc_irq_vectors(adev->pdev, 1, 1, flags);
+		if (nvec > 0) {
 			adev->irq.msi_enabled = true;
-			dev_dbg(adev->dev, "amdgpu: using MSI.\n");
+			dev_dbg(adev->dev, "amdgpu: using MSI/MSI-X.\n");
 		}
 	}
 
@@ -254,7 +280,8 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 	INIT_WORK(&adev->irq.ih2_work, amdgpu_irq_handle_ih2);
 
 	adev->irq.installed = true;
-	r = drm_irq_install(adev->ddev, adev->ddev->pdev->irq);
+	/* Use vector 0 for MSI-X */
+	r = drm_irq_install(adev->ddev, pci_irq_vector(adev->pdev, 0));
 	if (r) {
 		adev->irq.installed = false;
 		if (!amdgpu_device_has_dc_support(adev))
@@ -284,7 +311,7 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
 		drm_irq_uninstall(adev->ddev);
 		adev->irq.installed = false;
 		if (adev->irq.msi_enabled)
-			pci_disable_msi(adev->pdev);
+			pci_free_irq_vectors(adev->pdev);
 		if (!amdgpu_device_has_dc_support(adev))
 			flush_work(&adev->hotplug_work);
 	}
@@ -369,7 +396,7 @@ int amdgpu_irq_add_id(struct amdgpu_device *adev,
  * amdgpu_irq_dispatch - dispatch IRQ to IP blocks
  *
  * @adev: amdgpu device pointer
- * @entry: interrupt vector pointer
+ * @ih: interrupt ring instance
  *
  * Dispatches IRQ to IP blocks.
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9d76e0923a5a..4fb20e870e63 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -218,7 +218,7 @@ 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_job *job;
-	int r;
+	int r = 0;
 
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
@@ -243,9 +243,49 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	job->fence = dma_fence_get(fence);
 
 	amdgpu_job_free_resources(job);
+
+	fence = r ? ERR_PTR(r) : fence;
 	return fence;
 }
 
+#define to_drm_sched_job(sched_job)		\
+		container_of((sched_job), struct drm_sched_job, queue_node)
+
+void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched)
+{
+	struct drm_sched_job *s_job;
+	struct drm_sched_entity *s_entity = NULL;
+	int i;
+
+	/* Signal all jobs not yet scheduled */
+	for (i = DRM_SCHED_PRIORITY_MAX - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) {
+		struct drm_sched_rq *rq = &sched->sched_rq[i];
+
+		if (!rq)
+			continue;
+
+		spin_lock(&rq->lock);
+		list_for_each_entry(s_entity, &rq->entities, list) {
+			while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) {
+				struct drm_sched_fence *s_fence = s_job->s_fence;
+
+				dma_fence_signal(&s_fence->scheduled);
+				dma_fence_set_error(&s_fence->finished, -EHWPOISON);
+				dma_fence_signal(&s_fence->finished);
+			}
+		}
+		spin_unlock(&rq->lock);
+	}
+
+	/* Signal all jobs already scheduled to HW */
+	list_for_each_entry(s_job, &sched->ring_mirror_list, node) {
+		struct drm_sched_fence *s_fence = s_job->s_fence;
+
+		dma_fence_set_error(&s_fence->finished, -EHWPOISON);
+		dma_fence_signal(&s_fence->finished);
+	}
+}
+
 const struct drm_sched_backend_ops amdgpu_sched_ops = {
 	.dependency = amdgpu_job_dependency,
 	.run_job = amdgpu_job_run,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 51e62504c279..dc7ee9358dcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -76,4 +76,7 @@ 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);
+
+void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index d55f5baa83d3..b6db28a570c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -190,7 +190,6 @@ int amdgpu_driver_load_kms(struct drm_device *dev, unsigned long flags)
 		pm_runtime_put_autosuspend(dev->dev);
 	}
 
-	amdgpu_register_gpu_instance(adev);
 out:
 	if (r) {
 		/* balance pm_runtime_get_sync in amdgpu_driver_unload_kms */
@@ -584,9 +583,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		struct drm_amdgpu_info_vram_gtt vram_gtt;
 
 		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);
+			atomic64_read(&adev->vram_pin_size) -
+			AMDGPU_VM_RESERVED_VRAM;
+		vram_gtt.vram_cpu_accessible_size =
+			min(adev->gmc.visible_vram_size -
+			    atomic64_read(&adev->visible_pin_size),
+			    vram_gtt.vram_size);
 		vram_gtt.gtt_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		vram_gtt.gtt_size *= PAGE_SIZE;
 		vram_gtt.gtt_size -= atomic64_read(&adev->gart_pin_size);
@@ -599,15 +601,18 @@ 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 -
-			atomic64_read(&adev->vram_pin_size);
+			atomic64_read(&adev->vram_pin_size) -
+			AMDGPU_VM_RESERVED_VRAM;
 		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 -
-			atomic64_read(&adev->visible_pin_size);
+		mem.cpu_accessible_vram.usable_heap_size =
+			min(adev->gmc.visible_vram_size -
+			    atomic64_read(&adev->visible_pin_size),
+			    mem.vram.usable_heap_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 =
@@ -650,15 +655,19 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			return -ENOMEM;
 		alloc_size = info->read_mmr_reg.count * sizeof(*regs);
 
-		for (i = 0; i < info->read_mmr_reg.count; i++)
+		amdgpu_gfx_off_ctrl(adev, false);
+		for (i = 0; i < info->read_mmr_reg.count; i++) {
 			if (amdgpu_asic_read_register(adev, se_num, sh_num,
 						      info->read_mmr_reg.dword_offset + i,
 						      &regs[i])) {
 				DRM_DEBUG_KMS("unallowed offset %#x\n",
 					      info->read_mmr_reg.dword_offset + i);
 				kfree(regs);
+				amdgpu_gfx_off_ctrl(adev, true);
 				return -EFAULT;
 			}
+		}
+		amdgpu_gfx_off_ctrl(adev, true);
 		n = copy_to_user(out, regs, min(size, alloc_size));
 		kfree(regs);
 		return n ? -EFAULT : 0;
@@ -729,17 +738,6 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		dev_info.vce_harvest_config = adev->vce.harvest_config;
 		dev_info.gc_double_offchip_lds_buf =
 			adev->gfx.config.double_offchip_lds_buf;
-
-		if (amdgpu_ngg) {
-			dev_info.prim_buf_gpu_addr = adev->gfx.ngg.buf[NGG_PRIM].gpu_addr;
-			dev_info.prim_buf_size = adev->gfx.ngg.buf[NGG_PRIM].size;
-			dev_info.pos_buf_gpu_addr = adev->gfx.ngg.buf[NGG_POS].gpu_addr;
-			dev_info.pos_buf_size = adev->gfx.ngg.buf[NGG_POS].size;
-			dev_info.cntl_sb_buf_gpu_addr = adev->gfx.ngg.buf[NGG_CNTL].gpu_addr;
-			dev_info.cntl_sb_buf_size = adev->gfx.ngg.buf[NGG_CNTL].size;
-			dev_info.param_buf_gpu_addr = adev->gfx.ngg.buf[NGG_PARAM].gpu_addr;
-			dev_info.param_buf_size = adev->gfx.ngg.buf[NGG_PARAM].size;
-		}
 		dev_info.wave_front_size = adev->gfx.cu_info.wave_front_size;
 		dev_info.num_shader_visible_vgprs = adev->gfx.config.max_gprs;
 		dev_info.num_cu_per_sh = adev->gfx.config.max_cu_per_sh;
@@ -968,6 +966,12 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 	/* Ensure IB tests are run on ring */
 	flush_delayed_work(&adev->delayed_init_work);
 
+
+	if (amdgpu_ras_intr_triggered()) {
+		DRM_ERROR("RAS Intr triggered, device disabled!!");
+		return -EHWPOISON;
+	}
+
 	file_priv->driver_priv = NULL;
 
 	r = pm_runtime_get_sync(dev->dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c
new file mode 100644
index 000000000000..676c48c02d77
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.c
@@ -0,0 +1,70 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_ras.h"
+
+int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "mmhub_err_count",
+		.debugfs_name = "mmhub_err_inject",
+	};
+
+	if (!adev->mmhub.ras_if) {
+		adev->mmhub.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->mmhub.ras_if)
+			return -ENOMEM;
+		adev->mmhub.ras_if->block = AMDGPU_RAS_BLOCK__MMHUB;
+		adev->mmhub.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->mmhub.ras_if->sub_block_index = 0;
+		strcpy(adev->mmhub.ras_if->name, "mmhub");
+	}
+	ih_info.head = fs_info.head = *adev->mmhub.ras_if;
+	r = amdgpu_ras_late_init(adev, adev->mmhub.ras_if,
+				 &fs_info, &ih_info);
+	if (r || !amdgpu_ras_is_supported(adev, adev->mmhub.ras_if->block)) {
+		kfree(adev->mmhub.ras_if);
+		adev->mmhub.ras_if = NULL;
+	}
+
+	return r;
+}
+
+void amdgpu_mmhub_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB) &&
+			adev->mmhub.ras_if) {
+		struct ras_common_if *ras_if = adev->mmhub.ras_if;
+		struct ras_ih_if ih_info = {
+			.cb = NULL,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
index 2d75ecfa199b..1cd78940cf82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mmhub.h
@@ -23,9 +23,17 @@
 
 struct amdgpu_mmhub_funcs {
 	void (*ras_init)(struct amdgpu_device *adev);
+	int (*ras_late_init)(struct amdgpu_device *adev);
 	void (*query_ras_error_count)(struct amdgpu_device *adev,
 					void *ras_error_status);
 };
 
+struct amdgpu_mmhub {
+	struct ras_common_if *ras_if;
+	const struct amdgpu_mmhub_funcs *funcs;
+};
+
+int amdgpu_mmhub_ras_late_init(struct amdgpu_device *adev);
+void amdgpu_mmhub_ras_fini(struct amdgpu_device *adev);
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 31d4deb5d294..392300f77b13 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -136,6 +136,7 @@ void amdgpu_mn_unlock(struct amdgpu_mn *mn)
  * amdgpu_mn_read_lock - take the read side lock for this notifier
  *
  * @amn: our notifier
+ * @blockable: is the notifier blockable
  */
 static int amdgpu_mn_read_lock(struct amdgpu_mn *amn, bool blockable)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
new file mode 100644
index 000000000000..7d5c3a9de9ea
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) 2019  Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included
+ * in all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN
+ * AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#include "amdgpu.h"
+#include "amdgpu_ras.h"
+
+int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "pcie_bif_err_count",
+		.debugfs_name = "pcie_bif_err_inject",
+	};
+
+	if (!adev->nbio.ras_if) {
+		adev->nbio.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->nbio.ras_if)
+			return -ENOMEM;
+		adev->nbio.ras_if->block = AMDGPU_RAS_BLOCK__PCIE_BIF;
+		adev->nbio.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->nbio.ras_if->sub_block_index = 0;
+		strcpy(adev->nbio.ras_if->name, "pcie_bif");
+	}
+	ih_info.head = fs_info.head = *adev->nbio.ras_if;
+	r = amdgpu_ras_late_init(adev, adev->nbio.ras_if,
+				 &fs_info, &ih_info);
+	if (r)
+		goto free;
+
+	if (amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) {
+		r = amdgpu_irq_get(adev, &adev->nbio.ras_controller_irq, 0);
+		if (r)
+			goto late_fini;
+		r = amdgpu_irq_get(adev, &adev->nbio.ras_err_event_athub_irq, 0);
+		if (r)
+			goto late_fini;
+	} else {
+		r = 0;
+		goto free;
+	}
+
+	return 0;
+late_fini:
+	amdgpu_ras_late_fini(adev, adev->nbio.ras_if, &ih_info);
+free:
+	kfree(adev->nbio.ras_if);
+	adev->nbio.ras_if = NULL;
+	return r;
+}
+
+void amdgpu_nbio_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__PCIE_BIF) &&
+			adev->nbio.ras_if) {
+		struct ras_common_if *ras_if = adev->nbio.ras_if;
+		struct ras_ih_if ih_info = {
+			.cb = NULL,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
new file mode 100644
index 000000000000..919bd566ba3c
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_NBIO_H__
+#define __AMDGPU_NBIO_H__
+
+/*
+ * amdgpu nbio functions
+ */
+struct nbio_hdp_flush_reg {
+	u32 ref_and_mask_cp0;
+	u32 ref_and_mask_cp1;
+	u32 ref_and_mask_cp2;
+	u32 ref_and_mask_cp3;
+	u32 ref_and_mask_cp4;
+	u32 ref_and_mask_cp5;
+	u32 ref_and_mask_cp6;
+	u32 ref_and_mask_cp7;
+	u32 ref_and_mask_cp8;
+	u32 ref_and_mask_cp9;
+	u32 ref_and_mask_sdma0;
+	u32 ref_and_mask_sdma1;
+	u32 ref_and_mask_sdma2;
+	u32 ref_and_mask_sdma3;
+	u32 ref_and_mask_sdma4;
+	u32 ref_and_mask_sdma5;
+	u32 ref_and_mask_sdma6;
+	u32 ref_and_mask_sdma7;
+};
+
+struct amdgpu_nbio_funcs {
+	const struct nbio_hdp_flush_reg *hdp_flush_reg;
+	u32 (*get_hdp_flush_req_offset)(struct amdgpu_device *adev);
+	u32 (*get_hdp_flush_done_offset)(struct amdgpu_device *adev);
+	u32 (*get_pcie_index_offset)(struct amdgpu_device *adev);
+	u32 (*get_pcie_data_offset)(struct amdgpu_device *adev);
+	u32 (*get_rev_id)(struct amdgpu_device *adev);
+	void (*mc_access_enable)(struct amdgpu_device *adev, bool enable);
+	void (*hdp_flush)(struct amdgpu_device *adev, struct amdgpu_ring *ring);
+	u32 (*get_memsize)(struct amdgpu_device *adev);
+	void (*sdma_doorbell_range)(struct amdgpu_device *adev, int instance,
+			bool use_doorbell, int doorbell_index, int doorbell_size);
+	void (*vcn_doorbell_range)(struct amdgpu_device *adev, bool use_doorbell,
+				   int doorbell_index, int instance);
+	void (*enable_doorbell_aperture)(struct amdgpu_device *adev,
+					 bool enable);
+	void (*enable_doorbell_selfring_aperture)(struct amdgpu_device *adev,
+						  bool enable);
+	void (*ih_doorbell_range)(struct amdgpu_device *adev,
+				  bool use_doorbell, int doorbell_index);
+	void (*enable_doorbell_interrupt)(struct amdgpu_device *adev,
+					  bool enable);
+	void (*update_medium_grain_clock_gating)(struct amdgpu_device *adev,
+						 bool enable);
+	void (*update_medium_grain_light_sleep)(struct amdgpu_device *adev,
+						bool enable);
+	void (*get_clockgating_state)(struct amdgpu_device *adev,
+				      u32 *flags);
+	void (*ih_control)(struct amdgpu_device *adev);
+	void (*init_registers)(struct amdgpu_device *adev);
+	void (*detect_hw_virt)(struct amdgpu_device *adev);
+	void (*remap_hdp_registers)(struct amdgpu_device *adev);
+	void (*handle_ras_controller_intr_no_bifring)(struct amdgpu_device *adev);
+	void (*handle_ras_err_event_athub_intr_no_bifring)(struct amdgpu_device *adev);
+	int (*init_ras_controller_interrupt)(struct amdgpu_device *adev);
+	int (*init_ras_err_event_athub_interrupt)(struct amdgpu_device *adev);
+	void (*query_ras_error_count)(struct amdgpu_device *adev,
+					void *ras_error_status);
+	int (*ras_late_init)(struct amdgpu_device *adev);
+};
+
+struct amdgpu_nbio {
+	const struct nbio_hdp_flush_reg *hdp_flush_reg;
+	struct amdgpu_irq_src ras_controller_irq;
+	struct amdgpu_irq_src ras_err_event_athub_irq;
+	struct ras_common_if *ras_if;
+	const struct amdgpu_nbio_funcs *funcs;
+};
+
+int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev);
+void amdgpu_nbio_ras_fini(struct amdgpu_device *adev);
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 6f0b789a0b49..e3f16b49e970 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -343,6 +343,70 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
 }
 
 /**
+ * amdgpu_bo_create_kernel_at - create BO for kernel use at specific location
+ *
+ * @adev: amdgpu device object
+ * @offset: offset of the BO
+ * @size: size of the BO
+ * @domain: where to place it
+ * @bo_ptr:  used to initialize BOs in structures
+ * @cpu_addr: optional CPU address mapping
+ *
+ * Creates a kernel BO at a specific offset in the address space of the domain.
+ *
+ * Returns:
+ * 0 on success, negative error code otherwise.
+ */
+int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev,
+			       uint64_t offset, uint64_t size, uint32_t domain,
+			       struct amdgpu_bo **bo_ptr, void **cpu_addr)
+{
+	struct ttm_operation_ctx ctx = { false, false };
+	unsigned int i;
+	int r;
+
+	offset &= PAGE_MASK;
+	size = ALIGN(size, PAGE_SIZE);
+
+	r = amdgpu_bo_create_reserved(adev, size, PAGE_SIZE, domain, bo_ptr,
+				      NULL, cpu_addr);
+	if (r)
+		return r;
+
+	/*
+	 * Remove the original mem node and create a new one at the request
+	 * position.
+	 */
+	if (cpu_addr)
+		amdgpu_bo_kunmap(*bo_ptr);
+
+	ttm_bo_mem_put(&(*bo_ptr)->tbo, &(*bo_ptr)->tbo.mem);
+
+	for (i = 0; i < (*bo_ptr)->placement.num_placement; ++i) {
+		(*bo_ptr)->placements[i].fpfn = offset >> PAGE_SHIFT;
+		(*bo_ptr)->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
+	}
+	r = ttm_bo_mem_space(&(*bo_ptr)->tbo, &(*bo_ptr)->placement,
+			     &(*bo_ptr)->tbo.mem, &ctx);
+	if (r)
+		goto error;
+
+	if (cpu_addr) {
+		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
+		if (r)
+			goto error;
+	}
+
+	amdgpu_bo_unreserve(*bo_ptr);
+	return 0;
+
+error:
+	amdgpu_bo_unreserve(*bo_ptr);
+	amdgpu_bo_unref(bo_ptr);
+	return r;
+}
+
+/**
  * amdgpu_bo_free_kernel - free BO for kernel use
  *
  * @bo: amdgpu BO to free
@@ -451,9 +515,10 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 {
 	struct ttm_operation_ctx ctx = {
 		.interruptible = (bp->type != ttm_bo_type_kernel),
-		.no_wait_gpu = false,
+		.no_wait_gpu = bp->no_wait_gpu,
 		.resv = bp->resv,
-		.flags = TTM_OPT_FLAG_ALLOW_RES_EVICT
+		.flags = bp->type != ttm_bo_type_kernel ?
+			TTM_OPT_FLAG_ALLOW_RES_EVICT : 0
 	};
 	struct amdgpu_bo *bo;
 	unsigned long page_align, size = bp->size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 658f4c9779b7..7e99f6c58c48 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -41,6 +41,7 @@ struct amdgpu_bo_param {
 	u32				preferred_domain;
 	u64				flags;
 	enum ttm_bo_type		type;
+	bool				no_wait_gpu;
 	struct dma_resv	*resv;
 };
 
@@ -237,6 +238,9 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
 			    unsigned long size, int align,
 			    u32 domain, struct amdgpu_bo **bo_ptr,
 			    u64 *gpu_addr, void **cpu_addr);
+int amdgpu_bo_create_kernel_at(struct amdgpu_device *adev,
+			       uint64_t offset, uint64_t size, uint32_t domain,
+			       struct amdgpu_bo **bo_ptr, void **cpu_addr);
 void amdgpu_bo_free_kernel(struct amdgpu_bo **bo, u64 *gpu_addr,
 			   void **cpu_addr);
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 03930313c263..f205f56e3358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -161,7 +161,7 @@ static ssize_t amdgpu_get_dpm_state(struct device *dev,
 
 	if (is_support_sw_smu(adev)) {
 		if (adev->smu.ppt_funcs->get_current_power_state)
-			pm = amdgpu_smu_get_current_power_state(adev);
+			pm = smu_get_current_power_state(&adev->smu);
 		else
 			pm = adev->pm.dpm.user_state;
 	} else if (adev->powerplay.pp_funcs->get_current_power_state) {
@@ -805,8 +805,7 @@ static ssize_t amdgpu_get_pp_feature_status(struct device *dev,
 }
 
 /**
- * DOC: pp_dpm_sclk pp_dpm_mclk pp_dpm_socclk pp_dpm_fclk pp_dpm_dcefclk
- * pp_dpm_pcie
+ * DOC: pp_dpm_sclk pp_dpm_mclk pp_dpm_socclk pp_dpm_fclk pp_dpm_dcefclk pp_dpm_pcie
  *
  * The amdgpu driver provides a sysfs API for adjusting what power levels
  * are enabled for a given power state.  The files pp_dpm_sclk, pp_dpm_mclk,
@@ -822,9 +821,15 @@ static ssize_t amdgpu_get_pp_feature_status(struct device *dev,
  *
  * To manually adjust these states, first select manual using
  * power_dpm_force_performance_level.
- * Secondly,Enter a new value for each level by inputing a string that
+ * Secondly, enter a new value for each level by inputing a string that
  * contains " echo xx xx xx > pp_dpm_sclk/mclk/pcie"
- * E.g., echo 4 5 6 to > pp_dpm_sclk will enable sclk levels 4, 5, and 6.
+ * E.g.,
+ *
+ * .. code-block:: bash
+ *
+ *	echo "4 5 6" > pp_dpm_sclk
+ *
+ * will enable sclk levels 4, 5, and 6.
  *
  * NOTE: change to the dcefclk max dpm level is not supported now
  */
@@ -902,7 +907,7 @@ static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_SCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_SCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
@@ -949,7 +954,7 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_MCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_MCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
@@ -989,7 +994,7 @@ static ssize_t amdgpu_set_pp_dpm_socclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_SOCCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_SOCCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_SOCCLK, mask);
 
@@ -1029,7 +1034,7 @@ static ssize_t amdgpu_set_pp_dpm_fclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_FCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_FCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_FCLK, mask);
 
@@ -1069,7 +1074,7 @@ static ssize_t amdgpu_set_pp_dpm_dcefclk(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_DCEFCLK, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_DCEFCLK, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_DCEFCLK, mask);
 
@@ -1109,7 +1114,7 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 		return ret;
 
 	if (is_support_sw_smu(adev))
-		ret = smu_force_clk_levels(&adev->smu, SMU_PCIE, mask);
+		ret = smu_force_clk_levels(&adev->smu, SMU_PCIE, mask, true);
 	else if (adev->powerplay.pp_funcs->force_clock_level)
 		ret = amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
 
@@ -1301,7 +1306,7 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev,
 	}
 	parameter[parameter_size] = profile_mode;
 	if (is_support_sw_smu(adev))
-		ret = smu_set_power_profile_mode(&adev->smu, parameter, parameter_size);
+		ret = smu_set_power_profile_mode(&adev->smu, parameter, parameter_size, true);
 	else if (adev->powerplay.pp_funcs->set_power_profile_mode)
 		ret = amdgpu_dpm_set_power_profile_mode(adev, parameter, parameter_size);
 	if (!ret)
@@ -2010,7 +2015,7 @@ static ssize_t amdgpu_hwmon_show_power_cap_max(struct device *dev,
 	uint32_t limit = 0;
 
 	if (is_support_sw_smu(adev)) {
-		smu_get_power_limit(&adev->smu, &limit, true);
+		smu_get_power_limit(&adev->smu, &limit, true, true);
 		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, true);
@@ -2028,7 +2033,7 @@ static ssize_t amdgpu_hwmon_show_power_cap(struct device *dev,
 	uint32_t limit = 0;
 
 	if (is_support_sw_smu(adev)) {
-		smu_get_power_limit(&adev->smu, &limit, false);
+		smu_get_power_limit(&adev->smu, &limit, false,  true);
 		return snprintf(buf, PAGE_SIZE, "%u\n", limit * 1000000);
 	} else if (adev->powerplay.pp_funcs && adev->powerplay.pp_funcs->get_power_limit) {
 		adev->powerplay.pp_funcs->get_power_limit(adev->powerplay.pp_handle, &limit, false);
@@ -2196,9 +2201,9 @@ static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev,
  *
  * - fan1_input: fan speed in RPM
  *
- * - fan[1-*]_target: Desired fan speed Unit: revolution/min (RPM)
+ * - fan[1-\*]_target: Desired fan speed Unit: revolution/min (RPM)
  *
- * - fan[1-*]_enable: Enable or disable the sensors.1: Enable 0: Disable
+ * - fan[1-\*]_enable: Enable or disable the sensors.1: Enable 0: Disable
  *
  * hwmon interfaces for GPU clocks:
  *
@@ -2825,6 +2830,19 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 		DRM_ERROR("failed to create device file pp_dpm_sclk\n");
 		return ret;
 	}
+
+	/* Arcturus does not support standalone mclk/socclk/fclk level setting */
+	if (adev->asic_type == CHIP_ARCTURUS) {
+		dev_attr_pp_dpm_mclk.attr.mode &= ~S_IWUGO;
+		dev_attr_pp_dpm_mclk.store = NULL;
+
+		dev_attr_pp_dpm_socclk.attr.mode &= ~S_IWUGO;
+		dev_attr_pp_dpm_socclk.store = NULL;
+
+		dev_attr_pp_dpm_fclk.attr.mode &= ~S_IWUGO;
+		dev_attr_pp_dpm_fclk.store = NULL;
+	}
+
 	ret = device_create_file(adev->dev, &dev_attr_pp_dpm_mclk);
 	if (ret) {
 		DRM_ERROR("failed to create device file pp_dpm_mclk\n");
@@ -3008,7 +3026,8 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 		struct smu_dpm_context *smu_dpm = &adev->smu.smu_dpm;
 		smu_handle_task(&adev->smu,
 				smu_dpm->dpm_level,
-				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE);
+				AMD_PP_TASK_DISPLAY_CONFIG_CHANGE,
+				true);
 	} else {
 		if (adev->powerplay.pp_funcs->dispatch_tasks) {
 			if (!amdgpu_device_has_dc_support(adev)) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 4d71537a960d..44be3a45b25e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -34,6 +34,8 @@
 #include "psp_v11_0.h"
 #include "psp_v12_0.h"
 
+#include "amdgpu_ras.h"
+
 static void psp_set_funcs(struct amdgpu_device *adev);
 
 static int psp_early_init(void *handle)
@@ -88,6 +90,17 @@ static int psp_sw_init(void *handle)
 		return ret;
 	}
 
+	ret = psp_mem_training_init(psp);
+	if (ret) {
+		DRM_ERROR("Failed to initialize memory training!\n");
+		return ret;
+	}
+	ret = psp_mem_training(psp, PSP_MEM_TRAIN_COLD_BOOT);
+	if (ret) {
+		DRM_ERROR("Failed to process memory training!\n");
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -95,6 +108,7 @@ static int psp_sw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	psp_mem_training_fini(&adev->psp);
 	release_firmware(adev->psp.sos_fw);
 	adev->psp.sos_fw = NULL;
 	release_firmware(adev->psp.asd_fw);
@@ -151,10 +165,19 @@ psp_cmd_submit_buf(struct psp_context *psp,
 		return ret;
 	}
 
+	amdgpu_asic_invalidate_hdp(psp->adev, NULL);
 	while (*((unsigned int *)psp->fence_buf) != index) {
 		if (--timeout == 0)
 			break;
+		/*
+		 * Shouldn't wait for timeout when err_event_athub occurs,
+		 * because gpu reset thread triggered and lock resource should
+		 * be released for psp resume sequence.
+		 */
+		if (amdgpu_ras_intr_triggered())
+			break;
 		msleep(1);
+		amdgpu_asic_invalidate_hdp(psp->adev, NULL);
 	}
 
 	/* In some cases, psp response status is not 0 even there is no
@@ -168,8 +191,9 @@ psp_cmd_submit_buf(struct psp_context *psp,
 		if (ucode)
 			DRM_WARN("failed to load ucode id (%d) ",
 				  ucode->ucode_id);
-		DRM_WARN("psp command failed and response status is (0x%X)\n",
-			  psp->cmd_buf_mem->resp.status & GFX_CMD_STATUS_MASK);
+		DRM_DEBUG_DRIVER("psp command (0x%X) failed and response status is (0x%X)\n",
+			 psp->cmd_buf_mem->cmd_id,
+			 psp->cmd_buf_mem->resp.status & GFX_CMD_STATUS_MASK);
 		if (!timeout) {
 			mutex_unlock(&psp->mutex);
 			return -EINVAL;
@@ -253,7 +277,8 @@ static int psp_tmr_init(struct psp_context *psp)
 
 	/* For ASICs support RLC autoload, psp will parse the toc
 	 * and calculate the total size of TMR needed */
-	if (psp->toc_start_addr &&
+	if (!amdgpu_sriov_vf(psp->adev) &&
+	    psp->toc_start_addr &&
 	    psp->toc_bin_size &&
 	    psp->fw_pri_buf) {
 		ret = psp_load_toc(psp, &tmr_size);
@@ -287,15 +312,9 @@ static int psp_tmr_load(struct psp_context *psp)
 
 	ret = psp_cmd_submit_buf(psp, NULL, cmd,
 				 psp->fence_buf_mc_addr);
-	if (ret)
-		goto failed;
 
 	kfree(cmd);
 
-	return 0;
-
-failed:
-	kfree(cmd);
 	return ret;
 }
 
@@ -548,7 +567,9 @@ static int psp_xgmi_initialize(struct psp_context *psp)
 	struct ta_xgmi_shared_memory *xgmi_cmd;
 	int ret;
 
-	if (!psp->adev->psp.ta_fw)
+	if (!psp->adev->psp.ta_fw ||
+	    !psp->adev->psp.ta_xgmi_ucode_size ||
+	    !psp->adev->psp.ta_xgmi_start_addr)
 		return -ENOENT;
 
 	if (!psp->xgmi_context.initialized) {
@@ -737,6 +758,12 @@ static int psp_ras_terminate(struct psp_context *psp)
 {
 	int ret;
 
+	/*
+	 * TODO: bypass the terminate in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
 	if (!psp->ras.ras_initialized)
 		return 0;
 
@@ -758,6 +785,18 @@ static int psp_ras_initialize(struct psp_context *psp)
 {
 	int ret;
 
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->adev->psp.ta_ras_ucode_size ||
+	    !psp->adev->psp.ta_ras_start_addr) {
+		dev_warn(psp->adev->dev, "RAS: ras ta ucode is not available\n");
+		return 0;
+	}
+
 	if (!psp->ras.ras_initialized) {
 		ret = psp_ras_init_shared_buf(psp);
 		if (ret)
@@ -772,6 +811,360 @@ static int psp_ras_initialize(struct psp_context *psp)
 }
 // ras end
 
+// HDCP start
+static void psp_prep_hdcp_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+					  uint64_t hdcp_ta_mc,
+					  uint64_t hdcp_mc_shared,
+					  uint32_t hdcp_ta_size,
+					  uint32_t shared_size)
+{
+	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
+	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(hdcp_ta_mc);
+	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(hdcp_ta_mc);
+	cmd->cmd.cmd_load_ta.app_len = hdcp_ta_size;
+
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo =
+		lower_32_bits(hdcp_mc_shared);
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi =
+		upper_32_bits(hdcp_mc_shared);
+	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
+}
+
+static int psp_hdcp_init_shared_buf(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
+	 * physical) for hdcp ta <-> Driver
+	 */
+	ret = amdgpu_bo_create_kernel(psp->adev, PSP_HDCP_SHARED_MEM_SIZE,
+				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
+				      &psp->hdcp_context.hdcp_shared_bo,
+				      &psp->hdcp_context.hdcp_shared_mc_addr,
+				      &psp->hdcp_context.hdcp_shared_buf);
+
+	return ret;
+}
+
+static int psp_hdcp_load(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	/*
+	 * TODO: bypass the loading in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
+	memcpy(psp->fw_pri_buf, psp->ta_hdcp_start_addr,
+	       psp->ta_hdcp_ucode_size);
+
+	psp_prep_hdcp_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
+				      psp->hdcp_context.hdcp_shared_mc_addr,
+				      psp->ta_hdcp_ucode_size,
+				      PSP_HDCP_SHARED_MEM_SIZE);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	if (!ret) {
+		psp->hdcp_context.hdcp_initialized = 1;
+		psp->hdcp_context.session_id = cmd->resp.session_id;
+	}
+
+	kfree(cmd);
+
+	return ret;
+}
+static int psp_hdcp_initialize(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->adev->psp.ta_hdcp_ucode_size ||
+	    !psp->adev->psp.ta_hdcp_start_addr) {
+		dev_warn(psp->adev->dev, "HDCP: hdcp ta ucode is not available\n");
+		return 0;
+	}
+
+	if (!psp->hdcp_context.hdcp_initialized) {
+		ret = psp_hdcp_init_shared_buf(psp);
+		if (ret)
+			return ret;
+	}
+
+	ret = psp_hdcp_load(psp);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+static void psp_prep_hdcp_ta_unload_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+					    uint32_t hdcp_session_id)
+{
+	cmd->cmd_id = GFX_CMD_ID_UNLOAD_TA;
+	cmd->cmd.cmd_unload_ta.session_id = hdcp_session_id;
+}
+
+static int psp_hdcp_unload(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	/*
+	 * TODO: bypass the unloading in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_hdcp_ta_unload_cmd_buf(cmd, psp->hdcp_context.session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static void psp_prep_hdcp_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+					    uint32_t ta_cmd_id,
+					    uint32_t hdcp_session_id)
+{
+	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
+	cmd->cmd.cmd_invoke_cmd.session_id = hdcp_session_id;
+	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
+	/* Note: cmd_invoke_cmd.buf is not used for now */
+}
+
+int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	/*
+	 * TODO: bypass the loading in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_hdcp_ta_invoke_cmd_buf(cmd, ta_cmd_id,
+					psp->hdcp_context.session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_hdcp_terminate(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * TODO: bypass the terminate in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->hdcp_context.hdcp_initialized)
+		return 0;
+
+	ret = psp_hdcp_unload(psp);
+	if (ret)
+		return ret;
+
+	psp->hdcp_context.hdcp_initialized = 0;
+
+	/* free hdcp shared memory */
+	amdgpu_bo_free_kernel(&psp->hdcp_context.hdcp_shared_bo,
+			      &psp->hdcp_context.hdcp_shared_mc_addr,
+			      &psp->hdcp_context.hdcp_shared_buf);
+
+	return 0;
+}
+// HDCP end
+
+// DTM start
+static void psp_prep_dtm_ta_load_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+					 uint64_t dtm_ta_mc,
+					 uint64_t dtm_mc_shared,
+					 uint32_t dtm_ta_size,
+					 uint32_t shared_size)
+{
+	cmd->cmd_id = GFX_CMD_ID_LOAD_TA;
+	cmd->cmd.cmd_load_ta.app_phy_addr_lo = lower_32_bits(dtm_ta_mc);
+	cmd->cmd.cmd_load_ta.app_phy_addr_hi = upper_32_bits(dtm_ta_mc);
+	cmd->cmd.cmd_load_ta.app_len = dtm_ta_size;
+
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_lo = lower_32_bits(dtm_mc_shared);
+	cmd->cmd.cmd_load_ta.cmd_buf_phy_addr_hi = upper_32_bits(dtm_mc_shared);
+	cmd->cmd.cmd_load_ta.cmd_buf_len = shared_size;
+}
+
+static int psp_dtm_init_shared_buf(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * Allocate 16k memory aligned to 4k from Frame Buffer (local
+	 * physical) for dtm ta <-> Driver
+	 */
+	ret = amdgpu_bo_create_kernel(psp->adev, PSP_DTM_SHARED_MEM_SIZE,
+				      PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
+				      &psp->dtm_context.dtm_shared_bo,
+				      &psp->dtm_context.dtm_shared_mc_addr,
+				      &psp->dtm_context.dtm_shared_buf);
+
+	return ret;
+}
+
+static int psp_dtm_load(struct psp_context *psp)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	/*
+	 * TODO: bypass the loading in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	memset(psp->fw_pri_buf, 0, PSP_1_MEG);
+	memcpy(psp->fw_pri_buf, psp->ta_dtm_start_addr, psp->ta_dtm_ucode_size);
+
+	psp_prep_dtm_ta_load_cmd_buf(cmd, psp->fw_pri_mc_addr,
+				     psp->dtm_context.dtm_shared_mc_addr,
+				     psp->ta_dtm_ucode_size,
+				     PSP_DTM_SHARED_MEM_SIZE);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	if (!ret) {
+		psp->dtm_context.dtm_initialized = 1;
+		psp->dtm_context.session_id = cmd->resp.session_id;
+	}
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_dtm_initialize(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * TODO: bypass the initialize in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->adev->psp.ta_dtm_ucode_size ||
+	    !psp->adev->psp.ta_dtm_start_addr) {
+		dev_warn(psp->adev->dev, "DTM: dtm ta ucode is not available\n");
+		return 0;
+	}
+
+	if (!psp->dtm_context.dtm_initialized) {
+		ret = psp_dtm_init_shared_buf(psp);
+		if (ret)
+			return ret;
+	}
+
+	ret = psp_dtm_load(psp);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void psp_prep_dtm_ta_invoke_cmd_buf(struct psp_gfx_cmd_resp *cmd,
+					   uint32_t ta_cmd_id,
+					   uint32_t dtm_session_id)
+{
+	cmd->cmd_id = GFX_CMD_ID_INVOKE_CMD;
+	cmd->cmd.cmd_invoke_cmd.session_id = dtm_session_id;
+	cmd->cmd.cmd_invoke_cmd.ta_cmd_id = ta_cmd_id;
+	/* Note: cmd_invoke_cmd.buf is not used for now */
+}
+
+int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
+{
+	int ret;
+	struct psp_gfx_cmd_resp *cmd;
+
+	/*
+	 * TODO: bypass the loading in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	psp_prep_dtm_ta_invoke_cmd_buf(cmd, ta_cmd_id,
+				       psp->dtm_context.session_id);
+
+	ret = psp_cmd_submit_buf(psp, NULL, cmd, psp->fence_buf_mc_addr);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int psp_dtm_terminate(struct psp_context *psp)
+{
+	int ret;
+
+	/*
+	 * TODO: bypass the terminate in sriov for now
+	 */
+	if (amdgpu_sriov_vf(psp->adev))
+		return 0;
+
+	if (!psp->dtm_context.dtm_initialized)
+		return 0;
+
+	ret = psp_hdcp_unload(psp);
+	if (ret)
+		return ret;
+
+	psp->dtm_context.dtm_initialized = 0;
+
+	/* free hdcp shared memory */
+	amdgpu_bo_free_kernel(&psp->dtm_context.dtm_shared_bo,
+			      &psp->dtm_context.dtm_shared_mc_addr,
+			      &psp->dtm_context.dtm_shared_buf);
+
+	return 0;
+}
+// DTM end
+
 static int psp_hw_start(struct psp_context *psp)
 {
 	struct amdgpu_device *adev = psp->adev;
@@ -845,6 +1238,16 @@ static int psp_hw_start(struct psp_context *psp)
 		if (ret)
 			dev_err(psp->adev->dev,
 					"RAS: Failed to initialize RAS\n");
+
+		ret = psp_hdcp_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"HDCP: Failed to initialize HDCP\n");
+
+		ret = psp_dtm_initialize(psp);
+		if (ret)
+			dev_err(psp->adev->dev,
+				"DTM: Failed to initialize DTM\n");
 	}
 
 	return 0;
@@ -950,21 +1353,7 @@ static void psp_print_fw_hdr(struct psp_context *psp,
 			     struct amdgpu_firmware_info *ucode)
 {
 	struct amdgpu_device *adev = psp->adev;
-	const struct sdma_firmware_header_v1_0 *sdma_hdr =
-		(const struct sdma_firmware_header_v1_0 *)
-		adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
-	const struct gfx_firmware_header_v1_0 *ce_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
-	const struct gfx_firmware_header_v1_0 *pfp_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
-	const struct gfx_firmware_header_v1_0 *me_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
-	const struct gfx_firmware_header_v1_0 *mec_hdr =
-		(const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
-	const struct rlc_firmware_header_v2_0 *rlc_hdr =
-		(const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
-	const struct smc_firmware_header_v1_0 *smc_hdr =
-		(const struct smc_firmware_header_v1_0 *)adev->pm.fw->data;
+	struct common_firmware_header *hdr;
 
 	switch (ucode->ucode_id) {
 	case AMDGPU_UCODE_ID_SDMA0:
@@ -975,25 +1364,33 @@ static void psp_print_fw_hdr(struct psp_context *psp,
 	case AMDGPU_UCODE_ID_SDMA5:
 	case AMDGPU_UCODE_ID_SDMA6:
 	case AMDGPU_UCODE_ID_SDMA7:
-		amdgpu_ucode_print_sdma_hdr(&sdma_hdr->header);
+		hdr = (struct common_firmware_header *)
+			adev->sdma.instance[ucode->ucode_id - AMDGPU_UCODE_ID_SDMA0].fw->data;
+		amdgpu_ucode_print_sdma_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_CE:
-		amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.ce_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_PFP:
-		amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.pfp_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_ME:
-		amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.me_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_CP_MEC1:
-		amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.mec_fw->data;
+		amdgpu_ucode_print_gfx_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_RLC_G:
-		amdgpu_ucode_print_rlc_hdr(&rlc_hdr->header);
+		hdr = (struct common_firmware_header *)adev->gfx.rlc_fw->data;
+		amdgpu_ucode_print_rlc_hdr(hdr);
 		break;
 	case AMDGPU_UCODE_ID_SMC:
-		amdgpu_ucode_print_smc_hdr(&smc_hdr->header);
+		hdr = (struct common_firmware_header *)adev->pm.fw->data;
+		amdgpu_ucode_print_smc_hdr(hdr);
 		break;
 	default:
 		break;
@@ -1070,7 +1467,10 @@ out:
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA5
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA6
 		    || ucode->ucode_id == AMDGPU_UCODE_ID_SDMA7
-		    || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G))
+                    || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_G
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM
+	            || ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM))
 			/*skip ucode loading in SRIOV VF */
 			continue;
 
@@ -1079,10 +1479,6 @@ out:
 		     ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC2_JT))
 			/* skip mec JT when autoload is enabled */
 			continue;
-		/* Renoir only needs to load mec jump table one time */
-		if (adev->asic_type == CHIP_RENOIR &&
-		    ucode->ucode_id == AMDGPU_UCODE_ID_CP_MEC2_JT)
-			continue;
 
 		psp_print_fw_hdr(psp, ucode);
 
@@ -1091,7 +1487,8 @@ out:
 			return ret;
 
 		/* Start rlc autoload after psp recieved all the gfx firmware */
-		if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM) {
+		if (psp->autoload_supported && ucode->ucode_id == (amdgpu_sriov_vf(adev) ?
+		    AMDGPU_UCODE_ID_CP_MEC2 : AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM)) {
 			ret = psp_rlc_autoload(psp);
 			if (ret) {
 				DRM_ERROR("Failed to start rlc autoload\n");
@@ -1216,8 +1613,11 @@ static int psp_hw_fini(void *handle)
 	    psp->xgmi_context.initialized == 1)
                 psp_xgmi_terminate(psp);
 
-	if (psp->adev->psp.ta_fw)
+	if (psp->adev->psp.ta_fw) {
 		psp_ras_terminate(psp);
+		psp_dtm_terminate(psp);
+		psp_hdcp_terminate(psp);
+	}
 
 	psp_ring_destroy(psp, PSP_RING_TYPE__KM);
 
@@ -1259,6 +1659,16 @@ static int psp_suspend(void *handle)
 			DRM_ERROR("Failed to terminate ras ta\n");
 			return ret;
 		}
+		ret = psp_hdcp_terminate(psp);
+		if (ret) {
+			DRM_ERROR("Failed to terminate hdcp ta\n");
+			return ret;
+		}
+		ret = psp_dtm_terminate(psp);
+		if (ret) {
+			DRM_ERROR("Failed to terminate dtm ta\n");
+			return ret;
+		}
 	}
 
 	ret = psp_ring_stop(psp, PSP_RING_TYPE__KM);
@@ -1278,6 +1688,12 @@ static int psp_resume(void *handle)
 
 	DRM_INFO("PSP is resuming...\n");
 
+	ret = psp_mem_training(psp, PSP_MEM_TRAIN_RESUME);
+	if (ret) {
+		DRM_ERROR("Failed to process memory training!\n");
+		return ret;
+	}
+
 	mutex_lock(&adev->firmware.mutex);
 
 	ret = psp_hw_start(psp);
@@ -1317,9 +1733,6 @@ int psp_rlc_autoload_start(struct psp_context *psp)
 	int ret;
 	struct psp_gfx_cmd_resp *cmd;
 
-	if (amdgpu_sriov_vf(psp->adev))
-		return 0;
-
 	cmd = kzalloc(sizeof(struct psp_gfx_cmd_resp), GFP_KERNEL);
 	if (!cmd)
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
index bc0947f6bc8a..09c5474ebcc3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
@@ -37,6 +37,9 @@
 #define PSP_RAS_SHARED_MEM_SIZE 0x4000
 #define PSP_1_MEG		0x100000
 #define PSP_TMR_SIZE	0x400000
+#define PSP_HDCP_SHARED_MEM_SIZE	0x4000
+#define PSP_DTM_SHARED_MEM_SIZE	0x4000
+#define PSP_SHARED_MEM_SIZE		0x4000
 
 struct psp_context;
 struct psp_xgmi_node_info;
@@ -46,6 +49,8 @@ enum psp_bootloader_cmd {
 	PSP_BL__LOAD_SYSDRV		= 0x10000,
 	PSP_BL__LOAD_SOSDRV		= 0x20000,
 	PSP_BL__LOAD_KEY_DATABASE	= 0x80000,
+	PSP_BL__DRAM_LONG_TRAIN		= 0x100000,
+	PSP_BL__DRAM_SHORT_TRAIN	= 0x200000,
 };
 
 enum psp_ring_type
@@ -108,6 +113,9 @@ struct psp_funcs
 			struct ta_ras_trigger_error_input *info);
 	int (*ras_cure_posion)(struct psp_context *psp, uint64_t *mode_ptr);
 	int (*rlc_autoload_start)(struct psp_context *psp);
+	int (*mem_training_init)(struct psp_context *psp);
+	void (*mem_training_fini)(struct psp_context *psp);
+	int (*mem_training)(struct psp_context *psp, uint32_t ops);
 };
 
 #define AMDGPU_XGMI_MAX_CONNECTED_NODES		64
@@ -142,6 +150,65 @@ struct psp_ras_context {
 	struct amdgpu_ras	*ras;
 };
 
+struct psp_hdcp_context {
+	bool			hdcp_initialized;
+	uint32_t		session_id;
+	struct amdgpu_bo	*hdcp_shared_bo;
+	uint64_t		hdcp_shared_mc_addr;
+	void			*hdcp_shared_buf;
+};
+
+struct psp_dtm_context {
+	bool			dtm_initialized;
+	uint32_t		session_id;
+	struct amdgpu_bo	*dtm_shared_bo;
+	uint64_t		dtm_shared_mc_addr;
+	void			*dtm_shared_buf;
+};
+
+#define MEM_TRAIN_SYSTEM_SIGNATURE		0x54534942
+#define GDDR6_MEM_TRAINING_DATA_SIZE_IN_BYTES	0x1000
+#define GDDR6_MEM_TRAINING_OFFSET		0x8000
+
+enum psp_memory_training_init_flag {
+	PSP_MEM_TRAIN_NOT_SUPPORT	= 0x0,
+	PSP_MEM_TRAIN_SUPPORT		= 0x1,
+	PSP_MEM_TRAIN_INIT_FAILED	= 0x2,
+	PSP_MEM_TRAIN_RESERVE_SUCCESS	= 0x4,
+	PSP_MEM_TRAIN_INIT_SUCCESS	= 0x8,
+};
+
+enum psp_memory_training_ops {
+	PSP_MEM_TRAIN_SEND_LONG_MSG	= 0x1,
+	PSP_MEM_TRAIN_SAVE		= 0x2,
+	PSP_MEM_TRAIN_RESTORE		= 0x4,
+	PSP_MEM_TRAIN_SEND_SHORT_MSG	= 0x8,
+	PSP_MEM_TRAIN_COLD_BOOT		= PSP_MEM_TRAIN_SEND_LONG_MSG,
+	PSP_MEM_TRAIN_RESUME		= PSP_MEM_TRAIN_SEND_SHORT_MSG,
+};
+
+struct psp_memory_training_context {
+	/*training data size*/
+	u64 train_data_size;
+	/*
+	 * sys_cache
+	 * cpu virtual address
+	 * system memory buffer that used to store the training data.
+	 */
+	void *sys_cache;
+
+	/*vram offset of the p2c training data*/
+	u64 p2c_train_data_offset;
+	struct amdgpu_bo *p2c_bo;
+
+	/*vram offset of the c2p training data*/
+	u64 c2p_train_data_offset;
+	struct amdgpu_bo *c2p_bo;
+
+	enum psp_memory_training_init_flag init;
+	u32 training_cnt;
+};
+
 struct psp_context
 {
 	struct amdgpu_device            *adev;
@@ -206,9 +273,21 @@ struct psp_context
 	uint32_t			ta_ras_ucode_version;
 	uint32_t			ta_ras_ucode_size;
 	uint8_t				*ta_ras_start_addr;
+
+	uint32_t			ta_hdcp_ucode_version;
+	uint32_t			ta_hdcp_ucode_size;
+	uint8_t				*ta_hdcp_start_addr;
+
+	uint32_t			ta_dtm_ucode_version;
+	uint32_t			ta_dtm_ucode_size;
+	uint8_t				*ta_dtm_start_addr;
+
 	struct psp_xgmi_context		xgmi_context;
 	struct psp_ras_context		ras;
+	struct psp_hdcp_context 	hdcp_context;
+	struct psp_dtm_context		dtm_context;
 	struct mutex			mutex;
+	struct psp_memory_training_context mem_train_ctx;
 };
 
 struct amdgpu_psp_funcs {
@@ -251,6 +330,12 @@ struct amdgpu_psp_funcs {
 		(psp)->funcs->xgmi_set_topology_info((psp), (num_device), (topology)) : -EINVAL)
 #define psp_rlc_autoload(psp) \
 		((psp)->funcs->rlc_autoload_start ? (psp)->funcs->rlc_autoload_start((psp)) : 0)
+#define psp_mem_training_init(psp) \
+	((psp)->funcs->mem_training_init ? (psp)->funcs->mem_training_init((psp)) : 0)
+#define psp_mem_training_fini(psp) \
+	((psp)->funcs->mem_training_fini ? (psp)->funcs->mem_training_fini((psp)) : 0)
+#define psp_mem_training(psp, ops) \
+	((psp)->funcs->mem_training ? (psp)->funcs->mem_training((psp), (ops)) : 0)
 
 #define amdgpu_psp_check_fw_loading_status(adev, i) (adev)->firmware.funcs->check_fw_loading_status((adev), (i))
 
@@ -279,6 +364,8 @@ int psp_xgmi_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 int psp_ras_enable_features(struct psp_context *psp,
 		union ta_ras_cmd_input *info, bool enable);
+int psp_hdcp_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
+int psp_dtm_invoke(struct psp_context *psp, uint32_t ta_cmd_id);
 
 int psp_rlc_autoload_start(struct psp_context *psp);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 016ea274b955..404483437bd3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -25,10 +25,13 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/uaccess.h>
+#include <linux/reboot.h>
+#include <linux/syscalls.h>
 
 #include "amdgpu.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_atomfirmware.h"
+#include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
 
 const char *ras_error_string[] = {
 	"none",
@@ -65,11 +68,16 @@ const char *ras_block_string[] = {
 /* inject address is 52 bits */
 #define	RAS_UMC_INJECT_ADDR_LIMIT	(0x1ULL << 52)
 
-static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev,
-		uint64_t offset, uint64_t size,
-		struct amdgpu_bo **bo_ptr);
-static int amdgpu_ras_release_vram(struct amdgpu_device *adev,
-		struct amdgpu_bo **bo_ptr);
+enum amdgpu_ras_retire_page_reservation {
+	AMDGPU_RAS_RETIRE_PAGE_RESERVED,
+	AMDGPU_RAS_RETIRE_PAGE_PENDING,
+	AMDGPU_RAS_RETIRE_PAGE_FAULT,
+};
+
+atomic_t amdgpu_ras_in_intr = ATOMIC_INIT(0);
+
+static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
+				uint64_t addr);
 
 static ssize_t amdgpu_ras_debugfs_read(struct file *f, char __user *buf,
 					size_t size, loff_t *pos)
@@ -189,6 +197,10 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
 
 	return 0;
 }
+
+static struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev,
+		struct ras_common_if *head);
+
 /**
  * DOC: AMDGPU RAS debugfs control interface
  *
@@ -208,31 +220,44 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
  * As their names indicate, inject operation will write the
  * value to the address.
  *
- * Second member: struct ras_debug_if::op.
+ * The second member: struct ras_debug_if::op.
  * It has three kinds of operations.
- *  0: disable RAS on the block. Take ::head as its data.
- *  1: enable RAS on the block. Take ::head as its data.
- *  2: inject errors on the block. Take ::inject as its data.
+ *
+ * - 0: disable RAS on the block. Take ::head as its data.
+ * - 1: enable RAS on the block. Take ::head as its data.
+ * - 2: inject errors on the block. Take ::inject as its data.
  *
  * How to use the interface?
- * programs:
- * copy the struct ras_debug_if in your codes and initialize it.
- * write the struct to the control node.
  *
- * bash:
- * echo op block [error [sub_blcok address value]] > .../ras/ras_ctrl
- *	op: disable, enable, inject
- *		disable: only block is needed
- *		enable: block and error are needed
- *		inject: error, address, value are needed
- *	block: umc, smda, gfx, .........
- *		see ras_block_string[] for details
- *	error: ue, ce
- *		ue: multi_uncorrectable
- *		ce: single_correctable
- *	sub_block: sub block index, pass 0 if there is no sub block
+ * Programs
+ *
+ * Copy the struct ras_debug_if in your codes and initialize it.
+ * Write the struct to the control node.
+ *
+ * Shells
+ *
+ * .. code-block:: bash
+ *
+ *	echo op block [error [sub_block address value]] > .../ras/ras_ctrl
+ *
+ * Parameters:
+ *
+ * op: disable, enable, inject
+ *	disable: only block is needed
+ *	enable: block and error are needed
+ *	inject: error, address, value are needed
+ * block: umc, sdma, gfx, .........
+ *	see ras_block_string[] for details
+ * error: ue, ce
+ *	ue: multi_uncorrectable
+ *	ce: single_correctable
+ * sub_block:
+ *	sub block index, pass 0 if there is no sub block
+ *
+ * here are some examples for bash commands:
+ *
+ * .. code-block:: bash
  *
- * here are some examples for bash commands,
  *	echo inject umc ue 0x0 0x0 0x0 > /sys/kernel/debug/dri/0/ras/ras_ctrl
  *	echo inject umc ce 0 0 0 > /sys/kernel/debug/dri/0/ras/ras_ctrl
  *	echo disable umc > /sys/kernel/debug/dri/0/ras/ras_ctrl
@@ -245,8 +270,11 @@ static int amdgpu_ras_debugfs_ctrl_parse_data(struct file *f,
  * For inject, please check corresponding err count at
  * /sys/class/drm/card[0/1/2...]/device/ras/[gfx/sdma/...]_err_count
  *
- * NOTE: operation is only allowed on blocks which are supported.
- * Please check ras mask at /sys/module/amdgpu/parameters/ras_mask
+ * .. note::
+ *	Operations are only allowed on blocks which are supported.
+ *	Please check ras mask at /sys/module/amdgpu/parameters/ras_mask
+ *	to see which blocks support RAS on a particular asic.
+ *
  */
 static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *buf,
 		size_t size, loff_t *pos)
@@ -276,6 +304,14 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 			break;
 		}
 
+		/* umc ce/ue error injection for a bad page is not allowed */
+		if ((data.head.block == AMDGPU_RAS_BLOCK__UMC) &&
+		    amdgpu_ras_check_bad_page(adev, data.inject.address)) {
+			DRM_WARN("RAS WARN: 0x%llx has been marked as bad before error injection!\n",
+					data.inject.address);
+			break;
+		}
+
 		/* data.inject.address is offset instead of absolute gpu address */
 		ret = amdgpu_ras_error_inject(adev, &data.inject);
 		break;
@@ -290,6 +326,33 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user *
 	return size;
 }
 
+/**
+ * DOC: AMDGPU RAS debugfs EEPROM table reset interface
+ *
+ * Some boards contain an EEPROM which is used to persistently store a list of
+ * bad pages which experiences ECC errors in vram.  This interface provides
+ * a way to reset the EEPROM, e.g., after testing error injection.
+ *
+ * Usage:
+ *
+ * .. code-block:: bash
+ *
+ *	echo 1 > ../ras/ras_eeprom_reset
+ *
+ * will reset EEPROM table to 0 entries.
+ *
+ */
+static ssize_t amdgpu_ras_debugfs_eeprom_write(struct file *f, const char __user *buf,
+		size_t size, loff_t *pos)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
+	int ret;
+
+	ret = amdgpu_ras_eeprom_reset_table(&adev->psp.ras.ras->eeprom_control);
+
+	return ret == 1 ? size : -EIO;
+}
+
 static const struct file_operations amdgpu_ras_debugfs_ctrl_ops = {
 	.owner = THIS_MODULE,
 	.read = NULL,
@@ -297,6 +360,34 @@ static const struct file_operations amdgpu_ras_debugfs_ctrl_ops = {
 	.llseek = default_llseek
 };
 
+static const struct file_operations amdgpu_ras_debugfs_eeprom_ops = {
+	.owner = THIS_MODULE,
+	.read = NULL,
+	.write = amdgpu_ras_debugfs_eeprom_write,
+	.llseek = default_llseek
+};
+
+/**
+ * DOC: AMDGPU RAS sysfs Error Count Interface
+ *
+ * It allows the user to read the error count for each IP block on the gpu through
+ * /sys/class/drm/card[0/1/2...]/device/ras/[gfx/sdma/...]_err_count
+ *
+ * It outputs the multiple lines which report the uncorrected (ue) and corrected
+ * (ce) error counts.
+ *
+ * The format of one line is below,
+ *
+ * [ce|ue]: count
+ *
+ * Example:
+ *
+ * .. code-block:: bash
+ *
+ *	ue: 0
+ *	ce: 1
+ *
+ */
 static ssize_t amdgpu_ras_sysfs_read(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -475,15 +566,17 @@ int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 	if (!(!!enable ^ !!amdgpu_ras_is_feature_enabled(adev, head)))
 		return 0;
 
-	ret = psp_ras_enable_features(&adev->psp, &info, enable);
-	if (ret) {
-		DRM_ERROR("RAS ERROR: %s %s feature failed ret %d\n",
-				enable ? "enable":"disable",
-				ras_block_str(head->block),
-				ret);
-		if (ret == TA_RAS_STATUS__RESET_NEEDED)
-			return -EAGAIN;
-		return -EINVAL;
+	if (!amdgpu_ras_intr_triggered()) {
+		ret = psp_ras_enable_features(&adev->psp, &info, enable);
+		if (ret) {
+			DRM_ERROR("RAS ERROR: %s %s feature failed ret %d\n",
+					enable ? "enable":"disable",
+					ras_block_str(head->block),
+					ret);
+			if (ret == TA_RAS_STATUS__RESET_NEEDED)
+				return -EAGAIN;
+			return -EINVAL;
+		}
 	}
 
 	/* setup the obj */
@@ -615,8 +708,12 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 			adev->gfx.funcs->query_ras_error_count(adev, &err_data);
 		break;
 	case AMDGPU_RAS_BLOCK__MMHUB:
-		if (adev->mmhub_funcs->query_ras_error_count)
-			adev->mmhub_funcs->query_ras_error_count(adev, &err_data);
+		if (adev->mmhub.funcs->query_ras_error_count)
+			adev->mmhub.funcs->query_ras_error_count(adev, &err_data);
+		break;
+	case AMDGPU_RAS_BLOCK__PCIE_BIF:
+		if (adev->nbio.funcs->query_ras_error_count)
+			adev->nbio.funcs->query_ras_error_count(adev, &err_data);
 		break;
 	default:
 		break;
@@ -628,12 +725,14 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev,
 	info->ue_count = obj->err_data.ue_count;
 	info->ce_count = obj->err_data.ce_count;
 
-	if (err_data.ce_count)
+	if (err_data.ce_count) {
 		dev_info(adev->dev, "%ld correctable errors detected in %s block\n",
 			 obj->err_data.ce_count, ras_block_str(info->head.block));
-	if (err_data.ue_count)
+	}
+	if (err_data.ue_count) {
 		dev_info(adev->dev, "%ld uncorrectable errors detected in %s block\n",
 			 obj->err_data.ue_count, ras_block_str(info->head.block));
+	}
 
 	return 0;
 }
@@ -664,6 +763,8 @@ int amdgpu_ras_error_inject(struct amdgpu_device *adev,
 		break;
 	case AMDGPU_RAS_BLOCK__UMC:
 	case AMDGPU_RAS_BLOCK__MMHUB:
+	case AMDGPU_RAS_BLOCK__XGMI_WAFL:
+	case AMDGPU_RAS_BLOCK__PCIE_BIF:
 		ret = psp_ras_trigger_error(&adev->psp, &block_info);
 		break;
 	default:
@@ -723,18 +824,18 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 static char *amdgpu_ras_badpage_flags_str(unsigned int flags)
 {
 	switch (flags) {
-	case 0:
+	case AMDGPU_RAS_RETIRE_PAGE_RESERVED:
 		return "R";
-	case 1:
+	case AMDGPU_RAS_RETIRE_PAGE_PENDING:
 		return "P";
-	case 2:
+	case AMDGPU_RAS_RETIRE_PAGE_FAULT:
 	default:
 		return "F";
 	};
 }
 
-/*
- * DOC: ras sysfs gpu_vram_bad_pages interface
+/**
+ * DOC: AMDGPU RAS sysfs gpu_vram_bad_pages Interface
  *
  * It allows user to read the bad pages of vram on the gpu through
  * /sys/class/drm/card[0/1/2...]/device/ras/gpu_vram_bad_pages
@@ -746,14 +847,21 @@ static char *amdgpu_ras_badpage_flags_str(unsigned int flags)
  *
  * gpu pfn and gpu page size are printed in hex format.
  * flags can be one of below character,
+ *
  * R: reserved, this gpu page is reserved and not able to use.
+ *
  * P: pending for reserve, this gpu page is marked as bad, will be reserved
- *    in next window of page_reserve.
+ * in next window of page_reserve.
+ *
  * F: unable to reserve. this gpu page can't be reserved due to some reasons.
  *
- * examples:
- * 0x00000001 : 0x00001000 : R
- * 0x00000002 : 0x00001000 : P
+ * Examples:
+ *
+ * .. code-block:: bash
+ *
+ *	0x00000001 : 0x00001000 : R
+ *	0x00000002 : 0x00001000 : P
+ *
  */
 
 static ssize_t amdgpu_ras_sysfs_badpages_read(struct file *f,
@@ -927,6 +1035,24 @@ static int amdgpu_ras_sysfs_remove_all(struct amdgpu_device *adev)
 }
 /* sysfs end */
 
+/**
+ * DOC: AMDGPU RAS Reboot Behavior for Unrecoverable Errors
+ *
+ * Normally when there is an uncorrectable error, the driver will reset
+ * the GPU to recover.  However, in the event of an unrecoverable error,
+ * the driver provides an interface to reboot the system automatically
+ * in that event.
+ *
+ * The following file in debugfs provides that interface:
+ * /sys/kernel/debug/dri/[0/1/2...]/ras/auto_reboot
+ *
+ * Usage:
+ *
+ * .. code-block:: bash
+ *
+ *	echo true > .../ras/auto_reboot
+ *
+ */
 /* debugfs begin */
 static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
 {
@@ -934,8 +1060,21 @@ static void amdgpu_ras_debugfs_create_ctrl_node(struct amdgpu_device *adev)
 	struct drm_minor *minor = adev->ddev->primary;
 
 	con->dir = debugfs_create_dir("ras", minor->debugfs_root);
-	con->ent = debugfs_create_file("ras_ctrl", S_IWUGO | S_IRUGO, con->dir,
-				       adev, &amdgpu_ras_debugfs_ctrl_ops);
+	debugfs_create_file("ras_ctrl", S_IWUGO | S_IRUGO, con->dir,
+				adev, &amdgpu_ras_debugfs_ctrl_ops);
+	debugfs_create_file("ras_eeprom_reset", S_IWUGO | S_IRUGO, con->dir,
+				adev, &amdgpu_ras_debugfs_eeprom_ops);
+
+	/*
+	 * After one uncorrectable error happens, usually GPU recovery will
+	 * be scheduled. But due to the known problem in GPU recovery failing
+	 * to bring GPU back, below interface provides one direct way to
+	 * user to reboot system automatically in such case within
+	 * ERREVENT_ATHUB_INTERRUPT generated. Normal GPU recovery routine
+	 * will never be called.
+	 */
+	debugfs_create_bool("auto_reboot", S_IWUGO | S_IRUGO, con->dir,
+				&con->reboot);
 }
 
 void amdgpu_ras_debugfs_create(struct amdgpu_device *adev,
@@ -980,10 +1119,8 @@ static void amdgpu_ras_debugfs_remove_all(struct amdgpu_device *adev)
 		amdgpu_ras_debugfs_remove(adev, &obj->head);
 	}
 
-	debugfs_remove(con->ent);
-	debugfs_remove(con->dir);
+	debugfs_remove_recursive(con->dir);
 	con->dir = NULL;
-	con->ent = NULL;
 }
 /* debugfs end */
 
@@ -1188,15 +1325,15 @@ static int amdgpu_ras_badpages_read(struct amdgpu_device *adev,
 
 	for (; i < data->count; i++) {
 		(*bps)[i] = (struct ras_badpage){
-			.bp = data->bps[i].bp,
+			.bp = data->bps[i].retired_page,
 			.size = AMDGPU_GPU_PAGE_SIZE,
-			.flags = 0,
+			.flags = AMDGPU_RAS_RETIRE_PAGE_RESERVED,
 		};
 
 		if (data->last_reserved <= i)
-			(*bps)[i].flags = 1;
-		else if (data->bps[i].bo == NULL)
-			(*bps)[i].flags = 2;
+			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_PENDING;
+		else if (data->bps_bo[i] == NULL)
+			(*bps)[i].flags = AMDGPU_RAS_RETIRE_PAGE_FAULT;
 	}
 
 	*count = data->count;
@@ -1214,105 +1351,46 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 	atomic_set(&ras->in_recovery, 0);
 }
 
-static int amdgpu_ras_release_vram(struct amdgpu_device *adev,
-		struct amdgpu_bo **bo_ptr)
-{
-	/* no need to free it actually. */
-	amdgpu_bo_free_kernel(bo_ptr, NULL, NULL);
-	return 0;
-}
-
-/* reserve vram with size@offset */
-static int amdgpu_ras_reserve_vram(struct amdgpu_device *adev,
-		uint64_t offset, uint64_t size,
-		struct amdgpu_bo **bo_ptr)
-{
-	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_bo_param bp;
-	int r = 0;
-	int i;
-	struct amdgpu_bo *bo;
-
-	if (bo_ptr)
-		*bo_ptr = NULL;
-	memset(&bp, 0, sizeof(bp));
-	bp.size = size;
-	bp.byte_align = PAGE_SIZE;
-	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	bp.flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
-		AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
-	bp.type = ttm_bo_type_kernel;
-	bp.resv = NULL;
-
-	r = amdgpu_bo_create(adev, &bp, &bo);
-	if (r)
-		return -EINVAL;
-
-	r = amdgpu_bo_reserve(bo, false);
-	if (r)
-		goto error_reserve;
-
-	offset = ALIGN(offset, PAGE_SIZE);
-	for (i = 0; i < bo->placement.num_placement; ++i) {
-		bo->placements[i].fpfn = offset >> PAGE_SHIFT;
-		bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
-	}
-
-	ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem);
-	r = ttm_bo_mem_space(&bo->tbo, &bo->placement, &bo->tbo.mem, &ctx);
-	if (r)
-		goto error_pin;
-
-	r = amdgpu_bo_pin_restricted(bo,
-			AMDGPU_GEM_DOMAIN_VRAM,
-			offset,
-			offset + size);
-	if (r)
-		goto error_pin;
-
-	if (bo_ptr)
-		*bo_ptr = bo;
-
-	amdgpu_bo_unreserve(bo);
-	return r;
-
-error_pin:
-	amdgpu_bo_unreserve(bo);
-error_reserve:
-	amdgpu_bo_unref(&bo);
-	return r;
-}
-
 /* alloc/realloc bps array */
 static int amdgpu_ras_realloc_eh_data_space(struct amdgpu_device *adev,
 		struct ras_err_handler_data *data, int pages)
 {
 	unsigned int old_space = data->count + data->space_left;
 	unsigned int new_space = old_space + pages;
-	unsigned int align_space = ALIGN(new_space, 1024);
-	void *tmp = kmalloc(align_space * sizeof(*data->bps), GFP_KERNEL);
-
-	if (!tmp)
+	unsigned int align_space = ALIGN(new_space, 512);
+	void *bps = kmalloc(align_space * sizeof(*data->bps), GFP_KERNEL);
+	struct amdgpu_bo **bps_bo =
+			kmalloc(align_space * sizeof(*data->bps_bo), GFP_KERNEL);
+
+	if (!bps || !bps_bo) {
+		kfree(bps);
+		kfree(bps_bo);
 		return -ENOMEM;
+	}
 
 	if (data->bps) {
-		memcpy(tmp, data->bps,
+		memcpy(bps, data->bps,
 				data->count * sizeof(*data->bps));
 		kfree(data->bps);
 	}
+	if (data->bps_bo) {
+		memcpy(bps_bo, data->bps_bo,
+				data->count * sizeof(*data->bps_bo));
+		kfree(data->bps_bo);
+	}
 
-	data->bps = tmp;
+	data->bps = bps;
+	data->bps_bo = bps_bo;
 	data->space_left += align_space - old_space;
 	return 0;
 }
 
 /* it deal with vram only. */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
-		unsigned long *bps, int pages)
+		struct eeprom_table_record *bps, int pages)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
-	int i = pages;
 	int ret = 0;
 
 	if (!con || !con->eh_data || !bps || pages <= 0)
@@ -1329,24 +1407,120 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 			goto out;
 		}
 
-	while (i--)
-		data->bps[data->count++].bp = bps[i];
-
+	memcpy(&data->bps[data->count], bps, pages * sizeof(*data->bps));
+	data->count += pages;
 	data->space_left -= pages;
+
 out:
 	mutex_unlock(&con->recovery_lock);
 
 	return ret;
 }
 
+/*
+ * write error record array to eeprom, the function should be
+ * protected by recovery_lock
+ */
+static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_err_handler_data *data;
+	struct amdgpu_ras_eeprom_control *control;
+	int save_count;
+
+	if (!con || !con->eh_data)
+		return 0;
+
+	control = &con->eeprom_control;
+	data = con->eh_data;
+	save_count = data->count - control->num_recs;
+	/* only new entries are saved */
+	if (save_count > 0)
+		if (amdgpu_ras_eeprom_process_recods(control,
+							&data->bps[control->num_recs],
+							true,
+							save_count)) {
+			DRM_ERROR("Failed to save EEPROM table data!");
+			return -EIO;
+		}
+
+	return 0;
+}
+
+/*
+ * read error record array in eeprom and reserve enough space for
+ * storing new bad pages
+ */
+static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
+{
+	struct amdgpu_ras_eeprom_control *control =
+					&adev->psp.ras.ras->eeprom_control;
+	struct eeprom_table_record *bps = NULL;
+	int ret = 0;
+
+	/* no bad page record, skip eeprom access */
+	if (!control->num_recs)
+		return ret;
+
+	bps = kcalloc(control->num_recs, sizeof(*bps), GFP_KERNEL);
+	if (!bps)
+		return -ENOMEM;
+
+	if (amdgpu_ras_eeprom_process_recods(control, bps, false,
+		control->num_recs)) {
+		DRM_ERROR("Failed to load EEPROM table records!");
+		ret = -EIO;
+		goto out;
+	}
+
+	ret = amdgpu_ras_add_bad_pages(adev, bps, control->num_recs);
+
+out:
+	kfree(bps);
+	return ret;
+}
+
+/*
+ * check if an address belongs to bad page
+ *
+ * Note: this check is only for umc block
+ */
+static bool amdgpu_ras_check_bad_page(struct amdgpu_device *adev,
+				uint64_t addr)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_err_handler_data *data;
+	int i;
+	bool ret = false;
+
+	if (!con || !con->eh_data)
+		return ret;
+
+	mutex_lock(&con->recovery_lock);
+	data = con->eh_data;
+	if (!data)
+		goto out;
+
+	addr >>= AMDGPU_GPU_PAGE_SHIFT;
+	for (i = 0; i < data->count; i++)
+		if (addr == data->bps[i].retired_page) {
+			ret = true;
+			goto out;
+		}
+
+out:
+	mutex_unlock(&con->recovery_lock);
+	return ret;
+}
+
 /* called in gpu recovery/init */
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
 	uint64_t bp;
-	struct amdgpu_bo *bo;
-	int i;
+	struct amdgpu_bo *bo = NULL;
+	int i, ret = 0;
 
 	if (!con || !con->eh_data)
 		return 0;
@@ -1357,18 +1531,29 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev)
 		goto out;
 	/* reserve vram at driver post stage. */
 	for (i = data->last_reserved; i < data->count; i++) {
-		bp = data->bps[i].bp;
+		bp = data->bps[i].retired_page;
 
-		if (amdgpu_ras_reserve_vram(adev, bp << PAGE_SHIFT,
-					PAGE_SIZE, &bo))
-			DRM_ERROR("RAS ERROR: reserve vram %llx fail\n", bp);
+		/* There are two cases of reserve error should be ignored:
+		 * 1) a ras bad page has been allocated (used by someone);
+		 * 2) a ras bad page has been reserved (duplicate error injection
+		 *    for one page);
+		 */
+		if (amdgpu_bo_create_kernel_at(adev, bp << AMDGPU_GPU_PAGE_SHIFT,
+					       AMDGPU_GPU_PAGE_SIZE,
+					       AMDGPU_GEM_DOMAIN_VRAM,
+					       &bo, NULL))
+			DRM_WARN("RAS WARN: reserve vram for retired page %llx fail\n", bp);
 
-		data->bps[i].bo = bo;
+		data->bps_bo[i] = bo;
 		data->last_reserved = i + 1;
+		bo = NULL;
 	}
+
+	/* continue to save bad pages to eeprom even reesrve_vram fails */
+	ret = amdgpu_ras_save_bad_pages(adev);
 out:
 	mutex_unlock(&con->recovery_lock);
-	return 0;
+	return ret;
 }
 
 /* called when driver unload */
@@ -1388,11 +1573,11 @@ static int amdgpu_ras_release_bad_pages(struct amdgpu_device *adev)
 		goto out;
 
 	for (i = data->last_reserved - 1; i >= 0; i--) {
-		bo = data->bps[i].bo;
+		bo = data->bps_bo[i];
 
-		amdgpu_ras_release_vram(adev, &bo);
+		amdgpu_bo_free_kernel(&bo, NULL, NULL);
 
-		data->bps[i].bo = bo;
+		data->bps_bo[i] = bo;
 		data->last_reserved = i;
 	}
 out:
@@ -1400,41 +1585,54 @@ out:
 	return 0;
 }
 
-static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
-{
-	/* TODO
-	 * write the array to eeprom when SMU disabled.
-	 */
-	return 0;
-}
-
-static int amdgpu_ras_load_bad_pages(struct amdgpu_device *adev)
-{
-	/* TODO
-	 * read the array to eeprom when SMU disabled.
-	 */
-	return 0;
-}
-
-static int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
+int amdgpu_ras_recovery_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
-	struct ras_err_handler_data **data = &con->eh_data;
+	struct ras_err_handler_data **data;
+	int ret;
 
-	*data = kmalloc(sizeof(**data),
-			GFP_KERNEL|__GFP_ZERO);
-	if (!*data)
-		return -ENOMEM;
+	if (con)
+		data = &con->eh_data;
+	else
+		return 0;
+
+	*data = kmalloc(sizeof(**data), GFP_KERNEL | __GFP_ZERO);
+	if (!*data) {
+		ret = -ENOMEM;
+		goto out;
+	}
 
 	mutex_init(&con->recovery_lock);
 	INIT_WORK(&con->recovery_work, amdgpu_ras_do_recovery);
 	atomic_set(&con->in_recovery, 0);
 	con->adev = adev;
 
-	amdgpu_ras_load_bad_pages(adev);
-	amdgpu_ras_reserve_bad_pages(adev);
+	ret = amdgpu_ras_eeprom_init(&con->eeprom_control);
+	if (ret)
+		goto free;
+
+	if (con->eeprom_control.num_recs) {
+		ret = amdgpu_ras_load_bad_pages(adev);
+		if (ret)
+			goto free;
+		ret = amdgpu_ras_reserve_bad_pages(adev);
+		if (ret)
+			goto release;
+	}
 
 	return 0;
+
+release:
+	amdgpu_ras_release_bad_pages(adev);
+free:
+	kfree((*data)->bps);
+	kfree((*data)->bps_bo);
+	kfree(*data);
+	con->eh_data = NULL;
+out:
+	DRM_WARN("Failed to initialize ras recovery!\n");
+
+	return ret;
 }
 
 static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev)
@@ -1442,13 +1640,17 @@ static int amdgpu_ras_recovery_fini(struct amdgpu_device *adev)
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data = con->eh_data;
 
+	/* recovery_init failed to init it, fini is useless */
+	if (!data)
+		return 0;
+
 	cancel_work_sync(&con->recovery_work);
-	amdgpu_ras_save_bad_pages(adev);
 	amdgpu_ras_release_bad_pages(adev);
 
 	mutex_lock(&con->recovery_lock);
 	con->eh_data = NULL;
 	kfree(data->bps);
+	kfree(data->bps_bo);
 	kfree(data);
 	mutex_unlock(&con->recovery_lock);
 
@@ -1500,6 +1702,7 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
 int amdgpu_ras_init(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	int r;
 
 	if (con)
 		return 0;
@@ -1527,31 +1730,106 @@ int amdgpu_ras_init(struct amdgpu_device *adev)
 	/* Might need get this flag from vbios. */
 	con->flags = RAS_DEFAULT_FLAGS;
 
-	if (amdgpu_ras_recovery_init(adev))
-		goto recovery_out;
+	if (adev->nbio.funcs->init_ras_controller_interrupt) {
+		r = adev->nbio.funcs->init_ras_controller_interrupt(adev);
+		if (r)
+			return r;
+	}
+
+	if (adev->nbio.funcs->init_ras_err_event_athub_interrupt) {
+		r = adev->nbio.funcs->init_ras_err_event_athub_interrupt(adev);
+		if (r)
+			return r;
+	}
 
 	amdgpu_ras_mask &= AMDGPU_RAS_BLOCK_MASK;
 
 	if (amdgpu_ras_fs_init(adev))
 		goto fs_out;
 
-	/* ras init for each ras block */
-	if (adev->umc.funcs->ras_init)
-		adev->umc.funcs->ras_init(adev);
-
 	DRM_INFO("RAS INFO: ras initialized successfully, "
 			"hardware ability[%x] ras_mask[%x]\n",
 			con->hw_supported, con->supported);
 	return 0;
 fs_out:
-	amdgpu_ras_recovery_fini(adev);
-recovery_out:
 	amdgpu_ras_set_context(adev, NULL);
 	kfree(con);
 
 	return -EINVAL;
 }
 
+/* helper function to handle common stuff in ip late init phase */
+int amdgpu_ras_late_init(struct amdgpu_device *adev,
+			 struct ras_common_if *ras_block,
+			 struct ras_fs_if *fs_info,
+			 struct ras_ih_if *ih_info)
+{
+	int r;
+
+	/* disable RAS feature per IP block if it is not supported */
+	if (!amdgpu_ras_is_supported(adev, ras_block->block)) {
+		amdgpu_ras_feature_enable_on_boot(adev, ras_block, 0);
+		return 0;
+	}
+
+	r = amdgpu_ras_feature_enable_on_boot(adev, ras_block, 1);
+	if (r) {
+		if (r == -EAGAIN) {
+			/* request gpu reset. will run again */
+			amdgpu_ras_request_reset_on_boot(adev,
+					ras_block->block);
+			return 0;
+		} else if (adev->in_suspend || adev->in_gpu_reset) {
+			/* in resume phase, if fail to enable ras,
+			 * clean up all ras fs nodes, and disable ras */
+			goto cleanup;
+		} else
+			return r;
+	}
+
+	/* in resume phase, no need to create ras fs node */
+	if (adev->in_suspend || adev->in_gpu_reset)
+		return 0;
+
+	if (ih_info->cb) {
+		r = amdgpu_ras_interrupt_add_handler(adev, ih_info);
+		if (r)
+			goto interrupt;
+	}
+
+	amdgpu_ras_debugfs_create(adev, fs_info);
+
+	r = amdgpu_ras_sysfs_create(adev, fs_info);
+	if (r)
+		goto sysfs;
+
+	return 0;
+cleanup:
+	amdgpu_ras_sysfs_remove(adev, ras_block);
+sysfs:
+	amdgpu_ras_debugfs_remove(adev, ras_block);
+	if (ih_info->cb)
+		amdgpu_ras_interrupt_remove_handler(adev, ih_info);
+interrupt:
+	amdgpu_ras_feature_enable(adev, ras_block, 0);
+	return r;
+}
+
+/* helper function to remove ras fs node and interrupt handler */
+void amdgpu_ras_late_fini(struct amdgpu_device *adev,
+			  struct ras_common_if *ras_block,
+			  struct ras_ih_if *ih_info)
+{
+	if (!ras_block || !ih_info)
+		return;
+
+	amdgpu_ras_sysfs_remove(adev, ras_block);
+	amdgpu_ras_debugfs_remove(adev, ras_block);
+	if (ih_info->cb)
+                amdgpu_ras_interrupt_remove_handler(adev, ih_info);
+	amdgpu_ras_feature_enable(adev, ras_block, 0);
+}
+
 /* do some init work after IP late init as dependence.
  * and it runs in resume/gpu reset/booting up cases.
  */
@@ -1645,3 +1923,18 @@ int amdgpu_ras_fini(struct amdgpu_device *adev)
 
 	return 0;
 }
+
+void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
+{
+	uint32_t hw_supported, supported;
+
+	amdgpu_ras_check_supported(adev, &hw_supported, &supported);
+	if (!hw_supported)
+		return;
+
+	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
+		DRM_WARN("RAS event of type ERREVENT_ATHUB_INTERRUPT detected!\n");
+
+		amdgpu_ras_reset_gpu(adev, false);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
index 6c76bb2a6843..f80fd3428c98 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
@@ -317,8 +317,6 @@ struct amdgpu_ras {
 	struct list_head head;
 	/* debugfs */
 	struct dentry *dir;
-	/* debugfs ctrl */
-	struct dentry *ent;
 	/* sysfs */
 	struct device_attribute features_attr;
 	struct bin_attribute badpages_attr;
@@ -334,7 +332,7 @@ struct amdgpu_ras {
 	struct mutex recovery_lock;
 
 	uint32_t flags;
-
+	bool reboot;
 	struct amdgpu_ras_eeprom_control eeprom_control;
 };
 
@@ -347,15 +345,14 @@ struct ras_err_data {
 	unsigned long ue_count;
 	unsigned long ce_count;
 	unsigned long err_addr_cnt;
-	uint64_t *err_addr;
+	struct eeprom_table_record *err_addr;
 };
 
 struct ras_err_handler_data {
-	/* point to bad pages array */
-	struct {
-		unsigned long bp;
-		struct amdgpu_bo *bo;
-	} *bps;
+	/* point to bad page records array */
+	struct eeprom_table_record *bps;
+	/* point to reserved bo array */
+	struct amdgpu_bo **bps_bo;
 	/* the count of entries */
 	int count;
 	/* the space can place new entries */
@@ -365,7 +362,7 @@ struct ras_err_handler_data {
 };
 
 typedef int (*ras_ih_cb)(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
+		void *err_data,
 		struct amdgpu_iv_entry *entry);
 
 struct ras_ih_data {
@@ -481,6 +478,7 @@ static inline int amdgpu_ras_is_supported(struct amdgpu_device *adev,
 	return ras && (ras->supported & (1 << block));
 }
 
+int amdgpu_ras_recovery_init(struct amdgpu_device *adev);
 int amdgpu_ras_request_reset_on_boot(struct amdgpu_device *adev,
 		unsigned int block);
 
@@ -492,7 +490,7 @@ unsigned long amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 
 /* error handling functions */
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
-		unsigned long *bps, int pages);
+		struct eeprom_table_record *bps, int pages);
 
 int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev);
 
@@ -501,6 +499,12 @@ static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev,
 {
 	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
+	/* save bad page to eeprom before gpu reset,
+	 * i2c may be unstable in gpu reset
+	 */
+	if (in_task())
+		amdgpu_ras_reserve_bad_pages(adev);
+
 	if (atomic_cmpxchg(&ras->in_recovery, 0, 1) == 0)
 		schedule_work(&ras->recovery_work);
 	return 0;
@@ -566,6 +570,13 @@ amdgpu_ras_error_to_ta(enum amdgpu_ras_error_type error) {
 int amdgpu_ras_init(struct amdgpu_device *adev);
 int amdgpu_ras_fini(struct amdgpu_device *adev);
 int amdgpu_ras_pre_fini(struct amdgpu_device *adev);
+int amdgpu_ras_late_init(struct amdgpu_device *adev,
+			 struct ras_common_if *ras_block,
+			 struct ras_fs_if *fs_info,
+			 struct ras_ih_if *ih_info);
+void amdgpu_ras_late_fini(struct amdgpu_device *adev,
+			  struct ras_common_if *ras_block,
+			  struct ras_ih_if *ih_info);
 
 int amdgpu_ras_feature_enable(struct amdgpu_device *adev,
 		struct ras_common_if *head, bool enable);
@@ -599,4 +610,14 @@ int amdgpu_ras_interrupt_remove_handler(struct amdgpu_device *adev,
 
 int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev,
 		struct ras_dispatch_if *info);
+
+extern atomic_t amdgpu_ras_in_intr;
+
+static inline bool amdgpu_ras_intr_triggered(void)
+{
+	return !!atomic_read(&amdgpu_ras_in_intr);
+}
+
+void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 8a32b5c93778..2a8e04895595 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -27,7 +27,8 @@
 #include <linux/bits.h>
 #include "smu_v11_0_i2c.h"
 
-#define EEPROM_I2C_TARGET_ADDR 0xA0
+#define EEPROM_I2C_TARGET_ADDR_ARCTURUS  0xA8
+#define EEPROM_I2C_TARGET_ADDR_VEGA20    0xA0
 
 /*
  * The 2 macros bellow represent the actual size in bytes that
@@ -83,7 +84,7 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 {
 	int ret = 0;
 	struct i2c_msg msg = {
-			.addr	= EEPROM_I2C_TARGET_ADDR,
+			.addr	= 0,
 			.flags	= 0,
 			.len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
 			.buf	= buff,
@@ -93,6 +94,8 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 	*(uint16_t *)buff = EEPROM_HDR_START;
 	__encode_table_header_to_buff(&control->tbl_hdr, buff + EEPROM_ADDRESS_SIZE);
 
+	msg.addr = control->i2c_address;
+
 	ret = i2c_transfer(&control->eeprom_accessor, &msg, 1);
 	if (ret < 1)
 		DRM_ERROR("Failed to write EEPROM table header, ret:%d", ret);
@@ -100,7 +103,101 @@ static int __update_table_header(struct amdgpu_ras_eeprom_control *control,
 	return ret;
 }
 
-static uint32_t  __calc_hdr_byte_sum(struct amdgpu_ras_eeprom_control *control);
+
+
+static uint32_t  __calc_hdr_byte_sum(struct amdgpu_ras_eeprom_control *control)
+{
+	int i;
+	uint32_t tbl_sum = 0;
+
+	/* Header checksum, skip checksum field in the calculation */
+	for (i = 0; i < sizeof(control->tbl_hdr) - sizeof(control->tbl_hdr.checksum); i++)
+		tbl_sum += *(((unsigned char *)&control->tbl_hdr) + i);
+
+	return tbl_sum;
+}
+
+static uint32_t  __calc_recs_byte_sum(struct eeprom_table_record *records,
+				      int num)
+{
+	int i, j;
+	uint32_t tbl_sum = 0;
+
+	/* Records checksum */
+	for (i = 0; i < num; i++) {
+		struct eeprom_table_record *record = &records[i];
+
+		for (j = 0; j < sizeof(*record); j++) {
+			tbl_sum += *(((unsigned char *)record) + j);
+		}
+	}
+
+	return tbl_sum;
+}
+
+static inline uint32_t  __calc_tbl_byte_sum(struct amdgpu_ras_eeprom_control *control,
+				  struct eeprom_table_record *records, int num)
+{
+	return __calc_hdr_byte_sum(control) + __calc_recs_byte_sum(records, num);
+}
+
+/* Checksum = 256 -((sum of all table entries) mod 256) */
+static void __update_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
+				  struct eeprom_table_record *records, int num,
+				  uint32_t old_hdr_byte_sum)
+{
+	/*
+	 * This will update the table sum with new records.
+	 *
+	 * TODO: What happens when the EEPROM table is to be wrapped around
+	 * and old records from start will get overridden.
+	 */
+
+	/* need to recalculate updated header byte sum */
+	control->tbl_byte_sum -= old_hdr_byte_sum;
+	control->tbl_byte_sum += __calc_tbl_byte_sum(control, records, num);
+
+	control->tbl_hdr.checksum = 256 - (control->tbl_byte_sum % 256);
+}
+
+/* table sum mod 256 + checksum must equals 256 */
+static bool __validate_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
+			    struct eeprom_table_record *records, int num)
+{
+	control->tbl_byte_sum = __calc_tbl_byte_sum(control, records, num);
+
+	if (control->tbl_hdr.checksum + (control->tbl_byte_sum % 256) != 256) {
+		DRM_WARN("Checksum mismatch, checksum: %u ", control->tbl_hdr.checksum);
+		return false;
+	}
+
+	return true;
+}
+
+int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control)
+{
+	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
+	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
+	int ret = 0;
+
+	mutex_lock(&control->tbl_mutex);
+
+	hdr->header = EEPROM_TABLE_HDR_VAL;
+	hdr->version = EEPROM_TABLE_VER;
+	hdr->first_rec_offset = EEPROM_RECORD_START;
+	hdr->tbl_size = EEPROM_TABLE_HEADER_SIZE;
+
+	control->tbl_byte_sum = 0;
+	__update_tbl_checksum(control, NULL, 0, 0);
+	control->next_addr = EEPROM_RECORD_START;
+
+	ret = __update_table_header(control, buff);
+
+	mutex_unlock(&control->tbl_mutex);
+
+	return ret;
+
+}
 
 int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 {
@@ -109,7 +206,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 	unsigned char buff[EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE] = { 0 };
 	struct amdgpu_ras_eeprom_table_header *hdr = &control->tbl_hdr;
 	struct i2c_msg msg = {
-			.addr	= EEPROM_I2C_TARGET_ADDR,
+			.addr	= 0,
 			.flags	= I2C_M_RD,
 			.len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_HEADER_SIZE,
 			.buf	= buff,
@@ -119,9 +216,15 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+		control->i2c_address = EEPROM_I2C_TARGET_ADDR_VEGA20;
 		ret = smu_v11_0_i2c_eeprom_control_init(&control->eeprom_accessor);
 		break;
 
+	case CHIP_ARCTURUS:
+		control->i2c_address = EEPROM_I2C_TARGET_ADDR_ARCTURUS;
+		ret = smu_i2c_eeprom_init(&adev->smu, &control->eeprom_accessor);
+		break;
+
 	default:
 		return 0;
 	}
@@ -131,6 +234,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 		return ret;
 	}
 
+	msg.addr = control->i2c_address;
+
 	/* Read/Create table header from EEPROM address 0 */
 	ret = i2c_transfer(&control->eeprom_accessor, &msg, 1);
 	if (ret < 1) {
@@ -143,25 +248,18 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
 	if (hdr->header == EEPROM_TABLE_HDR_VAL) {
 		control->num_recs = (hdr->tbl_size - EEPROM_TABLE_HEADER_SIZE) /
 				    EEPROM_TABLE_RECORD_SIZE;
+		control->tbl_byte_sum = __calc_hdr_byte_sum(control);
+		control->next_addr = EEPROM_RECORD_START;
+
 		DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
 				 control->num_recs);
 
 	} else {
 		DRM_INFO("Creating new EEPROM table");
 
-		hdr->header = EEPROM_TABLE_HDR_VAL;
-		hdr->version = EEPROM_TABLE_VER;
-		hdr->first_rec_offset = EEPROM_RECORD_START;
-		hdr->tbl_size = EEPROM_TABLE_HEADER_SIZE;
-
-		adev->psp.ras.ras->eeprom_control.tbl_byte_sum =
-				__calc_hdr_byte_sum(&adev->psp.ras.ras->eeprom_control);
-		ret = __update_table_header(control, buff);
+		ret = amdgpu_ras_eeprom_reset_table(control);
 	}
 
-	/* Start inserting records from here */
-	adev->psp.ras.ras->eeprom_control.next_addr = EEPROM_RECORD_START;
-
 	return ret == 1 ? 0 : -EIO;
 }
 
@@ -173,6 +271,9 @@ void amdgpu_ras_eeprom_fini(struct amdgpu_ras_eeprom_control *control)
 	case CHIP_VEGA20:
 		smu_v11_0_i2c_eeprom_control_fini(&control->eeprom_accessor);
 		break;
+	case CHIP_ARCTURUS:
+		smu_i2c_eeprom_fini(&adev->smu, &control->eeprom_accessor);
+		break;
 
 	default:
 		return;
@@ -226,8 +327,8 @@ static void __decode_table_record_from_buff(struct amdgpu_ras_eeprom_control *co
 	record->offset = (le64_to_cpu(tmp) & 0xffffffffffff);
 	i += 6;
 
-	buff[i++] = record->mem_channel;
-	buff[i++] = record->mcumc_id;
+	record->mem_channel = buff[i++];
+	record->mcumc_id = buff[i++];
 
 	memcpy(&tmp, buff + i,  6);
 	record->retired_page = (le64_to_cpu(tmp) & 0xffffffffffff);
@@ -266,87 +367,18 @@ static uint32_t __correct_eeprom_dest_address(uint32_t curr_address)
 	return curr_address;
 }
 
-
-static uint32_t  __calc_hdr_byte_sum(struct amdgpu_ras_eeprom_control *control)
-{
-	int i;
-	uint32_t tbl_sum = 0;
-
-	/* Header checksum, skip checksum field in the calculation */
-	for (i = 0; i < sizeof(control->tbl_hdr) - sizeof(control->tbl_hdr.checksum); i++)
-		tbl_sum += *(((unsigned char *)&control->tbl_hdr) + i);
-
-	return tbl_sum;
-}
-
-static uint32_t  __calc_recs_byte_sum(struct eeprom_table_record *records,
-				      int num)
-{
-	int i, j;
-	uint32_t tbl_sum = 0;
-
-	/* Records checksum */
-	for (i = 0; i < num; i++) {
-		struct eeprom_table_record *record = &records[i];
-
-		for (j = 0; j < sizeof(*record); j++) {
-			tbl_sum += *(((unsigned char *)record) + j);
-		}
-	}
-
-	return tbl_sum;
-}
-
-static inline uint32_t  __calc_tbl_byte_sum(struct amdgpu_ras_eeprom_control *control,
-				  struct eeprom_table_record *records, int num)
-{
-	return __calc_hdr_byte_sum(control) + __calc_recs_byte_sum(records, num);
-}
-
-/* Checksum = 256 -((sum of all table entries) mod 256) */
-static void __update_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
-				  struct eeprom_table_record *records, int num,
-				  uint32_t old_hdr_byte_sum)
-{
-	/*
-	 * This will update the table sum with new records.
-	 *
-	 * TODO: What happens when the EEPROM table is to be wrapped around
-	 * and old records from start will get overridden.
-	 */
-
-	/* need to recalculate updated header byte sum */
-	control->tbl_byte_sum -= old_hdr_byte_sum;
-	control->tbl_byte_sum += __calc_tbl_byte_sum(control, records, num);
-
-	control->tbl_hdr.checksum = 256 - (control->tbl_byte_sum % 256);
-}
-
-/* table sum mod 256 + checksum must equals 256 */
-static bool __validate_tbl_checksum(struct amdgpu_ras_eeprom_control *control,
-			    struct eeprom_table_record *records, int num)
-{
-	control->tbl_byte_sum = __calc_tbl_byte_sum(control, records, num);
-
-	if (control->tbl_hdr.checksum + (control->tbl_byte_sum % 256) != 256) {
-		DRM_WARN("Checksum mismatch, checksum: %u ", control->tbl_hdr.checksum);
-		return false;
-	}
-
-	return true;
-}
-
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
 					    bool write,
 					    int num)
 {
 	int i, ret = 0;
-	struct i2c_msg *msgs;
-	unsigned char *buffs;
+	struct i2c_msg *msgs, *msg;
+	unsigned char *buffs, *buff;
+	struct eeprom_table_record *record;
 	struct amdgpu_device *adev = to_amdgpu_device(control);
 
-	if (adev->asic_type != CHIP_VEGA20)
+	if (adev->asic_type != CHIP_VEGA20 && adev->asic_type != CHIP_ARCTURUS)
 		return 0;
 
 	buffs = kcalloc(num, EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE,
@@ -373,9 +405,9 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 	 * 256b
 	 */
 	for (i = 0; i < num; i++) {
-		unsigned char *buff = &buffs[i * (EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE)];
-		struct eeprom_table_record *record = &records[i];
-		struct i2c_msg *msg = &msgs[i];
+		buff = &buffs[i * (EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE)];
+		record = &records[i];
+		msg = &msgs[i];
 
 		control->next_addr = __correct_eeprom_dest_address(control->next_addr);
 
@@ -383,8 +415,8 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 		 * Update bits 16,17 of EEPROM address in I2C address by setting them
 		 * to bits 1,2 of Device address byte
 		 */
-		msg->addr = EEPROM_I2C_TARGET_ADDR |
-			       ((control->next_addr & EEPROM_ADDR_MSB_MASK) >> 15);
+		msg->addr = control->i2c_address |
+			        ((control->next_addr & EEPROM_ADDR_MSB_MASK) >> 15);
 		msg->flags	= write ? 0 : I2C_M_RD;
 		msg->len	= EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE;
 		msg->buf	= buff;
@@ -415,8 +447,8 @@ int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 
 	if (!write) {
 		for (i = 0; i < num; i++) {
-			unsigned char *buff = &buffs[i*(EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE)];
-			struct eeprom_table_record *record = &records[i];
+			buff = &buffs[i*(EEPROM_ADDRESS_SIZE + EEPROM_TABLE_RECORD_SIZE)];
+			record = &records[i];
 
 			__decode_table_record_from_buff(control, record, buff + EEPROM_ADDRESS_SIZE);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
index 41f3fcb9a29b..ca78f812d436 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.h
@@ -50,6 +50,7 @@ struct amdgpu_ras_eeprom_control {
 	struct mutex tbl_mutex;
 	bool bus_locked;
 	uint32_t tbl_byte_sum;
+	uint16_t i2c_address; // 8-bit represented address
 };
 
 /*
@@ -79,6 +80,7 @@ struct eeprom_table_record {
 
 int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control);
 void amdgpu_ras_eeprom_fini(struct amdgpu_ras_eeprom_control *control);
+int amdgpu_ras_eeprom_reset_table(struct amdgpu_ras_eeprom_control *control);
 
 int amdgpu_ras_eeprom_process_recods(struct amdgpu_ras_eeprom_control *control,
 					    struct eeprom_table_record *records,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
index c8793e6cc3c5..6373bfb47d55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.c
@@ -124,13 +124,12 @@ int amdgpu_gfx_rlc_init_sr(struct amdgpu_device *adev, u32 dws)
  */
 int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev)
 {
-	volatile u32 *dst_ptr;
 	u32 dws;
 	int r;
 
 	/* allocate clear state block */
 	adev->gfx.rlc.clear_state_size = dws = adev->gfx.rlc.funcs->get_csb_size(adev);
-	r = amdgpu_bo_create_reserved(adev, dws * 4, PAGE_SIZE,
+	r = amdgpu_bo_create_kernel(adev, dws * 4, PAGE_SIZE,
 				      AMDGPU_GEM_DOMAIN_VRAM,
 				      &adev->gfx.rlc.clear_state_obj,
 				      &adev->gfx.rlc.clear_state_gpu_addr,
@@ -141,13 +140,6 @@ int amdgpu_gfx_rlc_init_csb(struct amdgpu_device *adev)
 		return r;
 	}
 
-	/* set up the cs buffer */
-	dst_ptr = adev->gfx.rlc.cs_ptr;
-	adev->gfx.rlc.funcs->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);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
index 5c13c503e61f..6010999d9020 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.c
@@ -23,6 +23,7 @@
 
 #include "amdgpu.h"
 #include "amdgpu_sdma.h"
+#include "amdgpu_ras.h"
 
 #define AMDGPU_CSA_SDMA_SIZE 64
 /* SDMA CSA reside in the 3rd page of CSA */
@@ -83,3 +84,101 @@ uint64_t amdgpu_sdma_get_csa_mc_addr(struct amdgpu_ring *ring,
 
 	return csa_mc_addr;
 }
+
+int amdgpu_sdma_ras_late_init(struct amdgpu_device *adev,
+			      void *ras_ih_info)
+{
+	int r, i;
+	struct ras_ih_if *ih_info = (struct ras_ih_if *)ras_ih_info;
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "sdma_err_count",
+		.debugfs_name = "sdma_err_inject",
+	};
+
+	if (!ih_info)
+		return -EINVAL;
+
+	if (!adev->sdma.ras_if) {
+		adev->sdma.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->sdma.ras_if)
+			return -ENOMEM;
+		adev->sdma.ras_if->block = AMDGPU_RAS_BLOCK__SDMA;
+		adev->sdma.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->sdma.ras_if->sub_block_index = 0;
+		strcpy(adev->sdma.ras_if->name, "sdma");
+	}
+	fs_info.head = ih_info->head = *adev->sdma.ras_if;
+
+	r = amdgpu_ras_late_init(adev, adev->sdma.ras_if,
+				 &fs_info, ih_info);
+	if (r)
+		goto free;
+
+	if (amdgpu_ras_is_supported(adev, adev->sdma.ras_if->block)) {
+		for (i = 0; i < adev->sdma.num_instances; i++) {
+			r = amdgpu_irq_get(adev, &adev->sdma.ecc_irq,
+				AMDGPU_SDMA_IRQ_INSTANCE0 + i);
+			if (r)
+				goto late_fini;
+		}
+	} else {
+		r = 0;
+		goto free;
+	}
+
+        return 0;
+
+late_fini:
+	amdgpu_ras_late_fini(adev, adev->sdma.ras_if, ih_info);
+free:
+	kfree(adev->sdma.ras_if);
+	adev->sdma.ras_if = NULL;
+	return r;
+}
+
+void amdgpu_sdma_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA) &&
+			adev->sdma.ras_if) {
+		struct ras_common_if *ras_if = adev->sdma.ras_if;
+		struct ras_ih_if ih_info = {
+			.head = *ras_if,
+			/* the cb member will not be used by
+			 * amdgpu_ras_interrupt_remove_handler, init it only
+			 * to cheat the check in ras_late_fini
+			 */
+			.cb = amdgpu_sdma_process_ras_data_cb,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
+
+int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev,
+		void *err_data,
+		struct amdgpu_iv_entry *entry)
+{
+	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+	amdgpu_ras_reset_gpu(adev, 0);
+
+	return AMDGPU_RAS_SUCCESS;
+}
+
+int amdgpu_sdma_process_ecc_irq(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry)
+{
+	struct ras_common_if *ras_if = adev->sdma.ras_if;
+	struct ras_dispatch_if ih_data = {
+		.entry = entry,
+	};
+
+	if (!ras_if)
+		return 0;
+
+	ih_data.head = *ras_if;
+
+	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
index a9ae0d8a0589..761ff8be6314 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h
@@ -104,4 +104,13 @@ struct amdgpu_sdma_instance *
 amdgpu_sdma_get_instance_from_ring(struct amdgpu_ring *ring);
 int amdgpu_sdma_get_index_from_ring(struct amdgpu_ring *ring, uint32_t *index);
 uint64_t amdgpu_sdma_get_csa_mc_addr(struct amdgpu_ring *ring, unsigned vmid);
+int amdgpu_sdma_ras_late_init(struct amdgpu_device *adev,
+			      void *ras_ih_info);
+void amdgpu_sdma_ras_fini(struct amdgpu_device *adev);
+int amdgpu_sdma_process_ras_data_cb(struct amdgpu_device *adev,
+		void *err_data,
+		struct amdgpu_iv_entry *entry);
+int amdgpu_sdma_process_ecc_irq(struct amdgpu_device *adev,
+				      struct amdgpu_irq_src *source,
+				      struct amdgpu_iv_entry *entry);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index b66d29d5ffa2..b158230af8db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -138,6 +138,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		}
 
 		dma_fence_put(fence);
+		fence = NULL;
 
 		r = amdgpu_bo_kmap(vram_obj, &vram_map);
 		if (r) {
@@ -183,6 +184,7 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		}
 
 		dma_fence_put(fence);
+		fence = NULL;
 
 		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 77674a7b9616..63e734a125fb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -170,7 +170,7 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 			     __field(unsigned int, context)
 			     __field(unsigned int, seqno)
 			     __field(struct dma_fence *, fence)
-			     __field(char *, ring_name)
+			     __string(ring, to_amdgpu_ring(job->base.sched)->name)
 			     __field(u32, num_ibs)
 			     ),
 
@@ -179,12 +179,12 @@ 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 = to_amdgpu_ring(job->base.sched)->name;
+			   __assign_str(ring, 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",
 		      __entry->sched_job_id, __get_str(timeline), __entry->context,
-		      __entry->seqno, __entry->ring_name, __entry->num_ibs)
+		      __entry->seqno, __get_str(ring), __entry->num_ibs)
 );
 
 TRACE_EVENT(amdgpu_sched_run_job,
@@ -195,7 +195,7 @@ TRACE_EVENT(amdgpu_sched_run_job,
 			     __string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			     __field(unsigned int, context)
 			     __field(unsigned int, seqno)
-			     __field(char *, ring_name)
+			     __string(ring, to_amdgpu_ring(job->base.sched)->name)
 			     __field(u32, num_ibs)
 			     ),
 
@@ -204,12 +204,12 @@ 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 = to_amdgpu_ring(job->base.sched)->name;
+			   __assign_str(ring, 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",
 		      __entry->sched_job_id, __get_str(timeline), __entry->context,
-		      __entry->seqno, __entry->ring_name, __entry->num_ibs)
+		      __entry->seqno, __get_str(ring), __entry->num_ibs)
 );
 
 
@@ -323,14 +323,15 @@ DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_cs,
 
 TRACE_EVENT(amdgpu_vm_set_ptes,
 	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
-		     uint32_t incr, uint64_t flags),
-	    TP_ARGS(pe, addr, count, incr, flags),
+		     uint32_t incr, uint64_t flags, bool direct),
+	    TP_ARGS(pe, addr, count, incr, flags, direct),
 	    TP_STRUCT__entry(
 			     __field(u64, pe)
 			     __field(u64, addr)
 			     __field(u32, count)
 			     __field(u32, incr)
 			     __field(u64, flags)
+			     __field(bool, direct)
 			     ),
 
 	    TP_fast_assign(
@@ -339,28 +340,32 @@ TRACE_EVENT(amdgpu_vm_set_ptes,
 			   __entry->count = count;
 			   __entry->incr = incr;
 			   __entry->flags = flags;
+			   __entry->direct = direct;
 			   ),
-	    TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%llx, count=%u",
-		      __entry->pe, __entry->addr, __entry->incr,
-		      __entry->flags, __entry->count)
+	    TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%llx, count=%u, "
+		      "direct=%d", __entry->pe, __entry->addr, __entry->incr,
+		      __entry->flags, __entry->count, __entry->direct)
 );
 
 TRACE_EVENT(amdgpu_vm_copy_ptes,
-	    TP_PROTO(uint64_t pe, uint64_t src, unsigned count),
-	    TP_ARGS(pe, src, count),
+	    TP_PROTO(uint64_t pe, uint64_t src, unsigned count, bool direct),
+	    TP_ARGS(pe, src, count, direct),
 	    TP_STRUCT__entry(
 			     __field(u64, pe)
 			     __field(u64, src)
 			     __field(u32, count)
+			     __field(bool, direct)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->pe = pe;
 			   __entry->src = src;
 			   __entry->count = count;
+			   __entry->direct = direct;
 			   ),
-	    TP_printk("pe=%010Lx, src=%010Lx, count=%u",
-		      __entry->pe, __entry->src, __entry->count)
+	    TP_printk("pe=%010Lx, src=%010Lx, count=%u, direct=%d",
+		      __entry->pe, __entry->src, __entry->count,
+		      __entry->direct)
 );
 
 TRACE_EVENT(amdgpu_vm_flush,
@@ -468,7 +473,7 @@ TRACE_EVENT(amdgpu_ib_pipe_sync,
 	    TP_PROTO(struct amdgpu_job *sched_job, struct dma_fence *fence),
 	    TP_ARGS(sched_job, fence),
 	    TP_STRUCT__entry(
-			     __field(const char *,name)
+			     __string(ring, sched_job->base.sched->name)
 			     __field(uint64_t, id)
 			     __field(struct dma_fence *, fence)
 			     __field(uint64_t, ctx)
@@ -476,14 +481,14 @@ TRACE_EVENT(amdgpu_ib_pipe_sync,
 			     ),
 
 	    TP_fast_assign(
-			   __entry->name = sched_job->base.sched->name;
+			   __assign_str(ring, sched_job->base.sched->name)
 			   __entry->id = sched_job->base.id;
 			   __entry->fence = fence;
 			   __entry->ctx = fence->context;
 			   __entry->seqno = fence->seqno;
 			   ),
 	    TP_printk("job ring=%s, id=%llu, need pipe sync to fence=%p, context=%llu, seq=%u",
-		      __entry->name, __entry->id,
+		      __get_str(ring), __entry->id,
 		      __entry->fence, __entry->ctx,
 		      __entry->seqno)
 );
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 8e867b8b432f..61d9b7774d42 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -39,6 +39,7 @@
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swiotlb.h>
+#include <linux/dma-buf.h>
 
 #include <drm/ttm/ttm_bo_api.h>
 #include <drm/ttm/ttm_bo_driver.h>
@@ -54,6 +55,7 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
 #include "amdgpu_sdma.h"
+#include "amdgpu_ras.h"
 #include "bif/bif_4_1_d.h"
 
 static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
@@ -484,15 +486,12 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
 {
-	struct amdgpu_device *adev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_place placements;
 	struct ttm_placement placement;
 	int r;
 
-	adev = amdgpu_ttm_adev(bo->bdev);
-
 	/* create space/pages for new_mem in GTT space */
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
@@ -543,15 +542,12 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 				struct ttm_operation_ctx *ctx,
 				struct ttm_mem_reg *new_mem)
 {
-	struct amdgpu_device *adev;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 	struct ttm_mem_reg tmp_mem;
 	struct ttm_placement placement;
 	struct ttm_place placements;
 	int r;
 
-	adev = amdgpu_ttm_adev(bo->bdev);
-
 	/* make space in GTT for old_mem buffer */
 	tmp_mem = *new_mem;
 	tmp_mem.mm_node = NULL;
@@ -763,6 +759,7 @@ static unsigned long amdgpu_ttm_io_mem_pfn(struct ttm_buffer_object *bo,
  */
 struct amdgpu_ttm_tt {
 	struct ttm_dma_tt	ttm;
+	struct drm_gem_object	*gobj;
 	u64			offset;
 	uint64_t		userptr;
 	struct task_struct	*usertask;
@@ -1217,16 +1214,14 @@ static struct ttm_backend_func amdgpu_backend_func = {
 static struct ttm_tt *amdgpu_ttm_tt_create(struct ttm_buffer_object *bo,
 					   uint32_t page_flags)
 {
-	struct amdgpu_device *adev;
 	struct amdgpu_ttm_tt *gtt;
 
-	adev = amdgpu_ttm_adev(bo->bdev);
-
 	gtt = kzalloc(sizeof(struct amdgpu_ttm_tt), GFP_KERNEL);
 	if (gtt == NULL) {
 		return NULL;
 	}
 	gtt->ttm.ttm.func = &amdgpu_backend_func;
+	gtt->gobj = &bo->base;
 
 	/* allocate space for the uninitialized page entries */
 	if (ttm_sg_tt_init(&gtt->ttm, bo, page_flags)) {
@@ -1247,7 +1242,6 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(ttm->bdev);
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
 
 	/* user pages are bound by amdgpu_ttm_tt_pin_userptr() */
 	if (gtt && gtt->userptr) {
@@ -1260,7 +1254,19 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
 		return 0;
 	}
 
-	if (slave && ttm->sg) {
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG) {
+		if (!ttm->sg) {
+			struct dma_buf_attachment *attach;
+			struct sg_table *sgt;
+
+			attach = gtt->gobj->import_attach;
+			sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
+			if (IS_ERR(sgt))
+				return PTR_ERR(sgt);
+
+			ttm->sg = sgt;
+		}
+
 		drm_prime_sg_to_page_addr_arrays(ttm->sg, ttm->pages,
 						 gtt->ttm.dma_address,
 						 ttm->num_pages);
@@ -1287,9 +1293,8 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm,
  */
 static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 {
-	struct amdgpu_device *adev;
 	struct amdgpu_ttm_tt *gtt = (void *)ttm;
-	bool slave = !!(ttm->page_flags & TTM_PAGE_FLAG_SG);
+	struct amdgpu_device *adev;
 
 	if (gtt && gtt->userptr) {
 		amdgpu_ttm_tt_set_user_pages(ttm, NULL);
@@ -1298,7 +1303,16 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 		return;
 	}
 
-	if (slave)
+	if (ttm->sg && gtt->gobj->import_attach) {
+		struct dma_buf_attachment *attach;
+
+		attach = gtt->gobj->import_attach;
+		dma_buf_unmap_attachment(attach, ttm->sg, DMA_BIDIRECTIONAL);
+		ttm->sg = NULL;
+		return;
+	}
+
+	if (ttm->page_flags & TTM_PAGE_FLAG_SG)
 		return;
 
 	adev = amdgpu_ttm_adev(ttm->bdev);
@@ -1634,81 +1648,105 @@ static void amdgpu_ttm_fw_reserve_vram_fini(struct amdgpu_device *adev)
  */
 static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 {
-	struct ttm_operation_ctx ctx = { false, false };
-	struct amdgpu_bo_param bp;
-	int r = 0;
-	int i;
-	u64 vram_size = adev->gmc.visible_vram_size;
-	u64 offset = adev->fw_vram_usage.start_offset;
-	u64 size = adev->fw_vram_usage.size;
-	struct amdgpu_bo *bo;
-
-	memset(&bp, 0, sizeof(bp));
-	bp.size = adev->fw_vram_usage.size;
-	bp.byte_align = PAGE_SIZE;
-	bp.domain = AMDGPU_GEM_DOMAIN_VRAM;
-	bp.flags = AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
-		AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
-	bp.type = ttm_bo_type_kernel;
-	bp.resv = NULL;
+	uint64_t vram_size = adev->gmc.visible_vram_size;
+
 	adev->fw_vram_usage.va = NULL;
 	adev->fw_vram_usage.reserved_bo = NULL;
 
-	if (adev->fw_vram_usage.size > 0 &&
-		adev->fw_vram_usage.size <= vram_size) {
+	if (adev->fw_vram_usage.size == 0 ||
+	    adev->fw_vram_usage.size > vram_size)
+		return 0;
 
-		r = amdgpu_bo_create(adev, &bp,
-				     &adev->fw_vram_usage.reserved_bo);
-		if (r)
-			goto error_create;
+	return amdgpu_bo_create_kernel_at(adev,
+					  adev->fw_vram_usage.start_offset,
+					  adev->fw_vram_usage.size,
+					  AMDGPU_GEM_DOMAIN_VRAM,
+					  &adev->fw_vram_usage.reserved_bo,
+					  &adev->fw_vram_usage.va);
+}
 
-		r = amdgpu_bo_reserve(adev->fw_vram_usage.reserved_bo, false);
-		if (r)
-			goto error_reserve;
+/*
+ * Memoy training reservation functions
+ */
 
-		/* remove the original mem node and create a new one at the
-		 * request position
-		 */
-		bo = adev->fw_vram_usage.reserved_bo;
-		offset = ALIGN(offset, PAGE_SIZE);
-		for (i = 0; i < bo->placement.num_placement; ++i) {
-			bo->placements[i].fpfn = offset >> PAGE_SHIFT;
-			bo->placements[i].lpfn = (offset + size) >> PAGE_SHIFT;
-		}
+/**
+ * amdgpu_ttm_training_reserve_vram_fini - free memory training reserved vram
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * free memory training reserved vram if it has been reserved.
+ */
+static int amdgpu_ttm_training_reserve_vram_fini(struct amdgpu_device *adev)
+{
+	struct psp_memory_training_context *ctx = &adev->psp.mem_train_ctx;
 
-		ttm_bo_mem_put(&bo->tbo, &bo->tbo.mem);
-		r = ttm_bo_mem_space(&bo->tbo, &bo->placement,
-				     &bo->tbo.mem, &ctx);
-		if (r)
-			goto error_pin;
+	ctx->init = PSP_MEM_TRAIN_NOT_SUPPORT;
+	amdgpu_bo_free_kernel(&ctx->c2p_bo, NULL, NULL);
+	ctx->c2p_bo = NULL;
 
-		r = amdgpu_bo_pin_restricted(adev->fw_vram_usage.reserved_bo,
-			AMDGPU_GEM_DOMAIN_VRAM,
-			adev->fw_vram_usage.start_offset,
-			(adev->fw_vram_usage.start_offset +
-			adev->fw_vram_usage.size));
-		if (r)
-			goto error_pin;
-		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
-			&adev->fw_vram_usage.va);
-		if (r)
-			goto error_kmap;
+	amdgpu_bo_free_kernel(&ctx->p2c_bo, NULL, NULL);
+	ctx->p2c_bo = NULL;
 
-		amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
+	return 0;
+}
+
+/**
+ * amdgpu_ttm_training_reserve_vram_init - create bo vram reservation from memory training
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * create bo vram reservation from memory training.
+ */
+static int amdgpu_ttm_training_reserve_vram_init(struct amdgpu_device *adev)
+{
+	int ret;
+	struct psp_memory_training_context *ctx = &adev->psp.mem_train_ctx;
+
+	memset(ctx, 0, sizeof(*ctx));
+	if (!adev->fw_vram_usage.mem_train_support) {
+		DRM_DEBUG("memory training does not support!\n");
+		return 0;
 	}
-	return r;
 
-error_kmap:
-	amdgpu_bo_unpin(adev->fw_vram_usage.reserved_bo);
-error_pin:
-	amdgpu_bo_unreserve(adev->fw_vram_usage.reserved_bo);
-error_reserve:
-	amdgpu_bo_unref(&adev->fw_vram_usage.reserved_bo);
-error_create:
-	adev->fw_vram_usage.va = NULL;
-	adev->fw_vram_usage.reserved_bo = NULL;
-	return r;
+	ctx->c2p_train_data_offset = adev->fw_vram_usage.mem_train_fb_loc;
+	ctx->p2c_train_data_offset = (adev->gmc.mc_vram_size - GDDR6_MEM_TRAINING_OFFSET);
+	ctx->train_data_size = GDDR6_MEM_TRAINING_DATA_SIZE_IN_BYTES;
+
+	DRM_DEBUG("train_data_size:%llx,p2c_train_data_offset:%llx,c2p_train_data_offset:%llx.\n",
+		  ctx->train_data_size,
+		  ctx->p2c_train_data_offset,
+		  ctx->c2p_train_data_offset);
+
+	ret = amdgpu_bo_create_kernel_at(adev,
+					 ctx->p2c_train_data_offset,
+					 ctx->train_data_size,
+					 AMDGPU_GEM_DOMAIN_VRAM,
+					 &ctx->p2c_bo,
+					 NULL);
+	if (ret) {
+		DRM_ERROR("alloc p2c_bo failed(%d)!\n", ret);
+		goto Err_out;
+	}
+
+	ret = amdgpu_bo_create_kernel_at(adev,
+					 ctx->c2p_train_data_offset,
+					 ctx->train_data_size,
+					 AMDGPU_GEM_DOMAIN_VRAM,
+					 &ctx->c2p_bo,
+					 NULL);
+	if (ret) {
+		DRM_ERROR("alloc c2p_bo failed(%d)!\n", ret);
+		goto Err_out;
+	}
+
+	ctx->init = PSP_MEM_TRAIN_RESERVE_SUCCESS;
+	return 0;
+
+Err_out:
+	amdgpu_ttm_training_reserve_vram_fini(adev);
+	return ret;
 }
+
 /**
  * amdgpu_ttm_init - Init the memory management (ttm) as well as various
  * gtt/vram related fields.
@@ -1772,6 +1810,14 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 		return r;
 	}
 
+	/*
+	 *The reserved vram for memory training must be pinned to the specified
+	 *place on the VRAM, so reserve it early.
+	 */
+	r = amdgpu_ttm_training_reserve_vram_init(adev);
+	if (r)
+		return r;
+
 	/* allocate memory as required for VGA
 	 * This is used for VGA emulation and pre-OS scanout buffers to
 	 * avoid display artifacts while transitioning between pre-OS
@@ -1782,6 +1828,20 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 				    NULL, &stolen_vga_buf);
 	if (r)
 		return r;
+
+	/*
+	 * reserve one TMR (64K) memory at the top of VRAM which holds
+	 * IP Discovery data and is protected by PSP.
+	 */
+	r = amdgpu_bo_create_kernel_at(adev,
+				       adev->gmc.real_vram_size - DISCOVERY_TMR_SIZE,
+				       DISCOVERY_TMR_SIZE,
+				       AMDGPU_GEM_DOMAIN_VRAM,
+				       &adev->discovery_memory,
+				       NULL);
+	if (r)
+		return r;
+
 	DRM_INFO("amdgpu: %uM of VRAM memory ready\n",
 		 (unsigned) (adev->gmc.real_vram_size / (1024 * 1024)));
 
@@ -1857,7 +1917,11 @@ void amdgpu_ttm_fini(struct amdgpu_device *adev)
 		return;
 
 	amdgpu_ttm_debugfs_fini(adev);
+	amdgpu_ttm_training_reserve_vram_fini(adev);
+	/* return the IP Discovery TMR memory back to VRAM */
+	amdgpu_bo_free_kernel(&adev->discovery_memory, NULL, NULL);
 	amdgpu_ttm_fw_reserve_vram_fini(adev);
+
 	if (adev->mman.aper_base_kaddr)
 		iounmap(adev->mman.aper_base_kaddr);
 	adev->mman.aper_base_kaddr = NULL;
@@ -1953,10 +2017,7 @@ static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
 	*addr += (u64)window * AMDGPU_GTT_MAX_TRANSFER_SIZE *
 		AMDGPU_GPU_PAGE_SIZE;
 
-	num_dw = adev->mman.buffer_funcs->copy_num_dw;
-	while (num_dw & 0x7)
-		num_dw++;
-
+	num_dw = ALIGN(adev->mman.buffer_funcs->copy_num_dw, 8);
 	num_bytes = num_pages * 8;
 
 	r = amdgpu_job_alloc_with_ib(adev, num_dw * 4 + num_bytes, &job);
@@ -2016,11 +2077,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
 
 	max_bytes = adev->mman.buffer_funcs->copy_max_bytes;
 	num_loops = DIV_ROUND_UP(byte_count, max_bytes);
-	num_dw = num_loops * adev->mman.buffer_funcs->copy_num_dw;
-
-	/* for IB padding */
-	while (num_dw & 0x7)
-		num_dw++;
+	num_dw = ALIGN(num_loops * adev->mman.buffer_funcs->copy_num_dw, 8);
 
 	r = amdgpu_job_alloc_with_ib(adev, num_dw * 4, &job);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 3a6115ad0196..833fc4b68940 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -360,6 +360,7 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 	case CHIP_RAVEN:
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
 	case CHIP_RENOIR:
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
@@ -368,8 +369,6 @@ amdgpu_ucode_get_load_type(struct amdgpu_device *adev, int load_type)
 			return AMDGPU_FW_LOAD_DIRECT;
 		else
 			return AMDGPU_FW_LOAD_PSP;
-	case CHIP_ARCTURUS:
-		return AMDGPU_FW_LOAD_DIRECT;
 
 	default:
 		DRM_ERROR("Unknown firmware load type\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index b34f00d42049..410587b950f3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -108,6 +108,12 @@ struct ta_firmware_header_v1_0 {
 	uint32_t ta_ras_ucode_version;
 	uint32_t ta_ras_offset_bytes;
 	uint32_t ta_ras_size_bytes;
+	uint32_t ta_hdcp_ucode_version;
+	uint32_t ta_hdcp_offset_bytes;
+	uint32_t ta_hdcp_size_bytes;
+	uint32_t ta_dtm_ucode_version;
+	uint32_t ta_dtm_offset_bytes;
+	uint32_t ta_dtm_size_bytes;
 };
 
 /* version_major=1, version_minor=0 */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
new file mode 100644
index 000000000000..d4fb9cf27e21
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -0,0 +1,158 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu_ras.h"
+
+int amdgpu_umc_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "umc_err_count",
+		.debugfs_name = "umc_err_inject",
+	};
+	struct ras_ih_if ih_info = {
+		.cb = amdgpu_umc_process_ras_data_cb,
+	};
+
+	if (!adev->umc.ras_if) {
+		adev->umc.ras_if =
+			kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->umc.ras_if)
+			return -ENOMEM;
+		adev->umc.ras_if->block = AMDGPU_RAS_BLOCK__UMC;
+		adev->umc.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->umc.ras_if->sub_block_index = 0;
+		strcpy(adev->umc.ras_if->name, "umc");
+	}
+	ih_info.head = fs_info.head = *adev->umc.ras_if;
+
+	r = amdgpu_ras_late_init(adev, adev->umc.ras_if,
+				 &fs_info, &ih_info);
+	if (r)
+		goto free;
+
+	if (amdgpu_ras_is_supported(adev, adev->umc.ras_if->block)) {
+		r = amdgpu_irq_get(adev, &adev->gmc.ecc_irq, 0);
+		if (r)
+			goto late_fini;
+	} else {
+		r = 0;
+		goto free;
+	}
+
+	/* ras init of specific umc version */
+	if (adev->umc.funcs && adev->umc.funcs->err_cnt_init)
+		adev->umc.funcs->err_cnt_init(adev);
+
+	return 0;
+
+late_fini:
+	amdgpu_ras_late_fini(adev, adev->umc.ras_if, &ih_info);
+free:
+	kfree(adev->umc.ras_if);
+	adev->umc.ras_if = NULL;
+	return r;
+}
+
+void amdgpu_umc_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC) &&
+			adev->umc.ras_if) {
+		struct ras_common_if *ras_if = adev->umc.ras_if;
+		struct ras_ih_if ih_info = {
+			.head = *ras_if,
+			.cb = amdgpu_umc_process_ras_data_cb,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
+
+int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
+		void *ras_error_status,
+		struct amdgpu_iv_entry *entry)
+{
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+
+	/* When “Full RAS” is enabled, the per-IP interrupt sources should
+	 * be disabled and the driver should only look for the aggregated
+	 * interrupt via sync flood
+	 */
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
+		return AMDGPU_RAS_SUCCESS;
+
+	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+	if (adev->umc.funcs &&
+	    adev->umc.funcs->query_ras_error_count)
+	    adev->umc.funcs->query_ras_error_count(adev, ras_error_status);
+
+	if (adev->umc.funcs &&
+	    adev->umc.funcs->query_ras_error_address &&
+	    adev->umc.max_ras_err_cnt_per_query) {
+		err_data->err_addr =
+			kcalloc(adev->umc.max_ras_err_cnt_per_query,
+				sizeof(struct eeprom_table_record), GFP_KERNEL);
+		/* still call query_ras_error_address to clear error status
+		 * even NOMEM error is encountered
+		 */
+		if(!err_data->err_addr)
+			DRM_WARN("Failed to alloc memory for umc error address record!\n");
+
+		/* umc query_ras_error_address is also responsible for clearing
+		 * error status
+		 */
+		adev->umc.funcs->query_ras_error_address(adev, ras_error_status);
+	}
+
+	/* only uncorrectable error needs gpu reset */
+	if (err_data->ue_count) {
+		if (err_data->err_addr_cnt &&
+		    amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
+						err_data->err_addr_cnt))
+			DRM_WARN("Failed to add ras bad page!\n");
+
+		amdgpu_ras_reset_gpu(adev, 0);
+	}
+
+	kfree(err_data->err_addr);
+	return AMDGPU_RAS_SUCCESS;
+}
+
+int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
+		struct amdgpu_irq_src *source,
+		struct amdgpu_iv_entry *entry)
+{
+	struct ras_common_if *ras_if = adev->umc.ras_if;
+	struct ras_dispatch_if ih_data = {
+		.entry = entry,
+	};
+
+	if (!ras_if)
+		return 0;
+
+	ih_data.head = *ras_if;
+
+	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
+	return 0;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
index 975afa04df09..3283032a78e5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.h
@@ -54,7 +54,8 @@
 	adev->umc.funcs->disable_umc_index_mode(adev);
 
 struct amdgpu_umc_funcs {
-	void (*ras_init)(struct amdgpu_device *adev);
+	void (*err_cnt_init)(struct amdgpu_device *adev);
+	int (*ras_late_init)(struct amdgpu_device *adev);
 	void (*query_ras_error_count)(struct amdgpu_device *adev,
 					void *ras_error_status);
 	void (*query_ras_error_address)(struct amdgpu_device *adev,
@@ -62,6 +63,7 @@ struct amdgpu_umc_funcs {
 	void (*enable_umc_index_mode)(struct amdgpu_device *adev,
 					uint32_t umc_instance);
 	void (*disable_umc_index_mode)(struct amdgpu_device *adev);
+	void (*init_registers)(struct amdgpu_device *adev);
 };
 
 struct amdgpu_umc {
@@ -75,8 +77,17 @@ struct amdgpu_umc {
 	uint32_t channel_offs;
 	/* channel index table of interleaved memory */
 	const uint32_t *channel_idx_tbl;
+	struct ras_common_if *ras_if;
 
 	const struct amdgpu_umc_funcs *funcs;
 };
 
+int amdgpu_umc_ras_late_init(struct amdgpu_device *adev);
+void amdgpu_umc_ras_fini(struct amdgpu_device *adev);
+int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
+		void *ras_error_status,
+		struct amdgpu_iv_entry *entry);
+int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
+		struct amdgpu_irq_src *source,
+		struct amdgpu_iv_entry *entry);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index b2c364b8695f..e324bfe6c58f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -39,6 +39,8 @@
 #include "cikd.h"
 #include "uvd/uvd_4_2_d.h"
 
+#include "amdgpu_ras.h"
+
 /* 1 second timeout */
 #define UVD_IDLE_TIMEOUT	msecs_to_jiffies(1000)
 
@@ -297,6 +299,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
+	cancel_delayed_work_sync(&adev->uvd.idle_work);
 	drm_sched_entity_destroy(&adev->uvd.entity);
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
@@ -372,7 +375,13 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 		if (!adev->uvd.inst[j].saved_bo)
 			return -ENOMEM;
 
-		memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
+		/* re-write 0 since err_event_athub will corrupt VCPU buffer */
+		if (amdgpu_ras_intr_triggered()) {
+			DRM_WARN("UVD VCPU state may lost due to RAS ERREVENT_ATHUB_INTERRUPT\n");
+			memset(adev->uvd.inst[j].saved_bo, 0, size);
+		} else {
+			memcpy_fromio(adev->uvd.inst[j].saved_bo, ptr, size);
+		}
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index b70b3c45bb29..46b590af2fd2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -80,6 +80,11 @@ MODULE_FIRMWARE(FIRMWARE_VEGA12);
 MODULE_FIRMWARE(FIRMWARE_VEGA20);
 
 static void amdgpu_vce_idle_work_handler(struct work_struct *work);
+static int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				     struct amdgpu_bo *bo,
+				     struct dma_fence **fence);
+static int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
+				      bool direct, struct dma_fence **fence);
 
 /**
  * amdgpu_vce_init - allocate memory, load vce firmware
@@ -211,6 +216,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
+	cancel_delayed_work_sync(&adev->vce.idle_work);
 	drm_sched_entity_destroy(&adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
@@ -428,14 +434,15 @@ void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
  *
  * Open up a stream for HW test
  */
-int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
-			      struct dma_fence **fence)
+static int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				     struct amdgpu_bo *bo,
+				     struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 1024;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -444,7 +451,7 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	ib = &job->ibs[0];
 
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	/* stitch together an VCE create msg */
 	ib->length_dw = 0;
@@ -476,8 +483,8 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 	ib->ptr[ib->length_dw++] = 0x00000014; /* len */
 	ib->ptr[ib->length_dw++] = 0x05000005; /* feedback buffer */
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
@@ -507,8 +514,8 @@ err:
  *
  * Close up a stream for HW test or if userspace failed to do so
  */
-int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-			       bool direct, struct dma_fence **fence)
+static int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
+				      bool direct, struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 1024;
 	struct amdgpu_job *job;
@@ -1110,13 +1117,20 @@ int amdgpu_vce_ring_test_ring(struct amdgpu_ring *ring)
 int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
 	/* skip vce ring1/2 ib test for now, since it's not reliable */
 	if (ring != &ring->adev->vce.ring[0])
 		return 0;
 
-	r = amdgpu_vce_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 512, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_vce_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
@@ -1132,5 +1146,7 @@ int amdgpu_vce_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
index 30ea54dd9117..d6d83a3ec803 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h
@@ -58,10 +58,6 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev);
 int amdgpu_vce_entity_init(struct amdgpu_device *adev);
 int amdgpu_vce_suspend(struct amdgpu_device *adev);
 int amdgpu_vce_resume(struct amdgpu_device *adev);
-int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
-			      struct dma_fence **fence);
-int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-			       bool direct, struct dma_fence **fence);
 void amdgpu_vce_free_handles(struct amdgpu_device *adev, struct drm_file *filp);
 int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 int amdgpu_vce_ring_parse_cs_vm(struct amdgpu_cs_parser *p, uint32_t ib_idx);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 7a6beb2e7c4e..9d870444d7d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -193,6 +193,8 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
+	cancel_delayed_work_sync(&adev->vcn.idle_work);
+
 	if (adev->vcn.indirect_sram) {
 		amdgpu_bo_free_kernel(&adev->vcn.dpg_sram_bo,
 				      &adev->vcn.dpg_sram_gpu_addr,
@@ -569,13 +571,14 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring)
 }
 
 static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
-			      struct dma_fence **fence)
+					 struct amdgpu_bo *bo,
+					 struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -583,14 +586,14 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x0000000b;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
@@ -621,13 +624,14 @@ err:
 }
 
 static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				struct dma_fence **fence)
+					  struct amdgpu_bo *bo,
+					  struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -635,14 +639,14 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 	ib->ptr[ib->length_dw++] = handle;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 	ib->ptr[ib->length_dw++] = 0x0000000b;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
@@ -675,13 +679,20 @@ err:
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = amdgpu_vcn_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = amdgpu_vcn_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, &fence);
+	r = amdgpu_vcn_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -693,6 +704,8 @@ int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5251352f5922..598c24505c73 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -130,7 +130,8 @@ static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
 
 	if (level == adev->vm_manager.root_level)
 		/* For the root directory */
-		return round_up(adev->vm_manager.max_pfn, 1ULL << shift) >> shift;
+		return round_up(adev->vm_manager.max_pfn, 1ULL << shift)
+			>> shift;
 	else if (level != AMDGPU_VM_PTB)
 		/* Everything in between */
 		return 512;
@@ -341,7 +342,7 @@ static struct amdgpu_vm_pt *amdgpu_vm_pt_parent(struct amdgpu_vm_pt *pt)
 	return container_of(parent->vm_bo, struct amdgpu_vm_pt, base);
 }
 
-/**
+/*
  * amdgpu_vm_pt_cursor - state for for_each_amdgpu_vm_pt
  */
 struct amdgpu_vm_pt_cursor {
@@ -482,6 +483,7 @@ static void amdgpu_vm_pt_next(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device structure
  * @vm: amdgpu_vm structure
+ * @start: optional cursor to start with
  * @cursor: state to initialize
  *
  * Starts a deep first traversal of the PD/PT tree.
@@ -535,7 +537,7 @@ static void amdgpu_vm_pt_next_dfs(struct amdgpu_device *adev,
 		amdgpu_vm_pt_ancestor(cursor);
 }
 
-/**
+/*
  * for_each_amdgpu_vm_pt_dfs_safe - safe deep first search of all PDs/PTs
  */
 #define for_each_amdgpu_vm_pt_dfs_safe(adev, vm, start, cursor, entry)		\
@@ -566,6 +568,14 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
 	list_add(&entry->tv.head, validated);
 }
 
+/**
+ * amdgpu_vm_del_from_lru_notify - update bulk_moveable flag
+ *
+ * @bo: BO which was removed from the LRU
+ *
+ * Make sure the bulk_moveable flag is updated when a BO is removed from the
+ * LRU.
+ */
 void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_bo *abo;
@@ -600,19 +610,18 @@ void amdgpu_vm_del_from_lru_notify(struct ttm_buffer_object *bo)
 void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm)
 {
-	struct ttm_bo_global *glob = adev->mman.bdev.glob;
 	struct amdgpu_vm_bo_base *bo_base;
 
 	if (vm->bulk_moveable) {
-		spin_lock(&glob->lru_lock);
+		spin_lock(&ttm_bo_glob.lru_lock);
 		ttm_bo_bulk_move_lru_tail(&vm->lru_bulk_move);
-		spin_unlock(&glob->lru_lock);
+		spin_unlock(&ttm_bo_glob.lru_lock);
 		return;
 	}
 
 	memset(&vm->lru_bulk_move, 0, sizeof(vm->lru_bulk_move));
 
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 	list_for_each_entry(bo_base, &vm->idle, vm_status) {
 		struct amdgpu_bo *bo = bo_base->bo;
 
@@ -624,7 +633,7 @@ void amdgpu_vm_move_to_lru_tail(struct amdgpu_device *adev,
 			ttm_bo_move_to_lru_tail(&bo->shadow->tbo,
 						&vm->lru_bulk_move);
 	}
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 
 	vm->bulk_moveable = true;
 }
@@ -693,6 +702,7 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
  * @adev: amdgpu_device pointer
  * @vm: VM to clear BO from
  * @bo: BO to clear
+ * @direct: use a direct update
  *
  * Root PD needs to be reserved when calling this.
  *
@@ -701,7 +711,8 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
  */
 static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 			      struct amdgpu_vm *vm,
-			      struct amdgpu_bo *bo)
+			      struct amdgpu_bo *bo,
+			      bool direct)
 {
 	struct ttm_operation_ctx ctx = { true, false };
 	unsigned level = adev->vm_manager.root_level;
@@ -760,6 +771,7 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 	memset(&params, 0, sizeof(params));
 	params.adev = adev;
 	params.vm = vm;
+	params.direct = direct;
 
 	r = vm->update_funcs->prepare(&params, AMDGPU_FENCE_OWNER_KFD, NULL);
 	if (r)
@@ -813,10 +825,13 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @vm: requesting vm
+ * @level: the page table level
+ * @direct: use a direct update
  * @bp: resulting BO allocation parameters
  */
 static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
-			       int level, struct amdgpu_bo_param *bp)
+			       int level, bool direct,
+			       struct amdgpu_bo_param *bp)
 {
 	memset(bp, 0, sizeof(*bp));
 
@@ -831,6 +846,7 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	else if (!vm->root.base.bo || vm->root.base.bo->shadow)
 		bp->flags |= AMDGPU_GEM_CREATE_SHADOW;
 	bp->type = ttm_bo_type_kernel;
+	bp->no_wait_gpu = direct;
 	if (vm->root.base.bo)
 		bp->resv = vm->root.base.bo->tbo.base.resv;
 }
@@ -841,6 +857,7 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  * @adev: amdgpu_device pointer
  * @vm: VM to allocate page tables for
  * @cursor: Which page table to allocate
+ * @direct: use a direct update
  *
  * Make sure a specific page table or directory is allocated.
  *
@@ -850,7 +867,8 @@ static void amdgpu_vm_bo_param(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  */
 static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 			       struct amdgpu_vm *vm,
-			       struct amdgpu_vm_pt_cursor *cursor)
+			       struct amdgpu_vm_pt_cursor *cursor,
+			       bool direct)
 {
 	struct amdgpu_vm_pt *entry = cursor->entry;
 	struct amdgpu_bo_param bp;
@@ -871,7 +889,7 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 	if (entry->base.bo)
 		return 0;
 
-	amdgpu_vm_bo_param(adev, vm, cursor->level, &bp);
+	amdgpu_vm_bo_param(adev, vm, cursor->level, direct, &bp);
 
 	r = amdgpu_bo_create(adev, &bp, &pt);
 	if (r)
@@ -883,7 +901,7 @@ static int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 	pt->parent = amdgpu_bo_ref(cursor->parent->base.bo);
 	amdgpu_vm_bo_base_init(&entry->base, vm, pt);
 
-	r = amdgpu_vm_clear_bo(adev, vm, pt);
+	r = amdgpu_vm_clear_bo(adev, vm, pt, direct);
 	if (r)
 		goto error_free_pt;
 
@@ -1020,7 +1038,8 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
  * Returns:
  * 0 on success, errno otherwise.
  */
-int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync)
+int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
+		    bool need_pipe_sync)
 {
 	struct amdgpu_device *adev = ring->adev;
 	unsigned vmhub = ring->funcs->vmhub;
@@ -1034,10 +1053,8 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 		id->oa_base != job->oa_base ||
 		id->oa_size != job->oa_size);
 	bool vm_flush_needed = job->vm_needs_flush;
-	bool pasid_mapping_needed = id->pasid != job->pasid ||
-		!id->pasid_mapping ||
-		!dma_fence_is_signaled(id->pasid_mapping);
 	struct dma_fence *fence = NULL;
+	bool pasid_mapping_needed = false;
 	unsigned patch_offset = 0;
 	int r;
 
@@ -1047,6 +1064,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 		pasid_mapping_needed = true;
 	}
 
+	mutex_lock(&id_mgr->lock);
+	if (id->pasid != job->pasid || !id->pasid_mapping ||
+	    !dma_fence_is_signaled(id->pasid_mapping))
+		pasid_mapping_needed = true;
+	mutex_unlock(&id_mgr->lock);
+
 	gds_switch_needed &= !!ring->funcs->emit_gds_switch;
 	vm_flush_needed &= !!ring->funcs->emit_vm_flush  &&
 			job->vm_pd_addr != AMDGPU_BO_INVALID_OFFSET;
@@ -1086,9 +1109,11 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
 	}
 
 	if (pasid_mapping_needed) {
+		mutex_lock(&id_mgr->lock);
 		id->pasid = job->pasid;
 		dma_fence_put(id->pasid_mapping);
 		id->pasid_mapping = dma_fence_get(fence);
+		mutex_unlock(&id_mgr->lock);
 	}
 	dma_fence_put(fence);
 
@@ -1172,10 +1197,10 @@ uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr)
 	return result;
 }
 
-/*
+/**
  * amdgpu_vm_update_pde - update a single level in the hierarchy
  *
- * @param: parameters for the update
+ * @params: parameters for the update
  * @vm: requested vm
  * @entry: entry to update
  *
@@ -1199,7 +1224,7 @@ static int amdgpu_vm_update_pde(struct amdgpu_vm_update_params *params,
 	return vm->update_funcs->update(params, bo, pde, pt, 1, 0, flags);
 }
 
-/*
+/**
  * amdgpu_vm_invalidate_pds - mark all PDs as invalid
  *
  * @adev: amdgpu_device pointer
@@ -1218,19 +1243,20 @@ static void amdgpu_vm_invalidate_pds(struct amdgpu_device *adev,
 			amdgpu_vm_bo_relocated(&entry->base);
 }
 
-/*
- * amdgpu_vm_update_directories - make sure that all directories are valid
+/**
+ * amdgpu_vm_update_pdes - make sure that all directories are valid
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
+ * @direct: submit directly to the paging queue
  *
  * Makes sure all directories are up to date.
  *
  * Returns:
  * 0 for success, error for failure.
  */
-int amdgpu_vm_update_directories(struct amdgpu_device *adev,
-				 struct amdgpu_vm *vm)
+int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
+			  struct amdgpu_vm *vm, bool direct)
 {
 	struct amdgpu_vm_update_params params;
 	int r;
@@ -1241,6 +1267,7 @@ int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 	memset(&params, 0, sizeof(params));
 	params.adev = adev;
 	params.vm = vm;
+	params.direct = direct;
 
 	r = vm->update_funcs->prepare(&params, AMDGPU_FENCE_OWNER_VM, NULL);
 	if (r)
@@ -1268,7 +1295,7 @@ error:
 	return r;
 }
 
-/**
+/*
  * amdgpu_vm_update_flags - figure out flags for PTE updates
  *
  * Make sure to set the right flags for the PTEs at the desired level.
@@ -1391,7 +1418,11 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 		uint64_t incr, entry_end, pe_start;
 		struct amdgpu_bo *pt;
 
-		r = amdgpu_vm_alloc_pts(params->adev, params->vm, &cursor);
+		/* make sure that the page tables covering the address range are
+		 * actually allocated
+		 */
+		r = amdgpu_vm_alloc_pts(params->adev, params->vm, &cursor,
+					params->direct);
 		if (r)
 			return r;
 
@@ -1463,7 +1494,12 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
 		} while (frag_start < entry_end);
 
 		if (amdgpu_vm_pt_descendant(adev, &cursor)) {
-			/* Free all child entries */
+			/* Free all child entries.
+			 * Update the tables with the flags and addresses and free up subsequent
+			 * tables in the case of huge pages or freed up areas.
+			 * This is the maximum you can free, because all other page tables are not
+			 * completely covered by the range and so potentially still in use.
+			 */
 			while (cursor.pfn < frag_start) {
 				amdgpu_vm_free_pts(adev, params->vm, &cursor);
 				amdgpu_vm_pt_next(adev, &cursor);
@@ -1482,13 +1518,14 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
  * amdgpu_vm_bo_update_mapping - update a mapping in the vm page table
  *
  * @adev: amdgpu_device pointer
- * @exclusive: fence we need to sync to
- * @pages_addr: DMA addresses to use for mapping
  * @vm: requested vm
+ * @direct: direct submission in a page fault
+ * @exclusive: fence we need to sync to
  * @start: start of mapped range
  * @last: last mapped entry
  * @flags: flags for the entries
  * @addr: addr to set the area to
+ * @pages_addr: DMA addresses to use for mapping
  * @fence: optional resulting fence
  *
  * Fill in the page table entries between @start and @last.
@@ -1497,11 +1534,11 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params,
  * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
+				       struct amdgpu_vm *vm, bool direct,
 				       struct dma_fence *exclusive,
-				       dma_addr_t *pages_addr,
-				       struct amdgpu_vm *vm,
 				       uint64_t start, uint64_t last,
 				       uint64_t flags, uint64_t addr,
+				       dma_addr_t *pages_addr,
 				       struct dma_fence **fence)
 {
 	struct amdgpu_vm_update_params params;
@@ -1511,6 +1548,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 	memset(&params, 0, sizeof(params));
 	params.adev = adev;
 	params.vm = vm;
+	params.direct = direct;
 	params.pages_addr = pages_addr;
 
 	/* sync to everything except eviction fences on unmapping */
@@ -1569,27 +1607,8 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 	if (!(mapping->flags & AMDGPU_PTE_WRITEABLE))
 		flags &= ~AMDGPU_PTE_WRITEABLE;
 
-	flags &= ~AMDGPU_PTE_EXECUTABLE;
-	flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
-
-	if (adev->asic_type >= CHIP_NAVI10) {
-		flags &= ~AMDGPU_PTE_MTYPE_NV10_MASK;
-		flags |= (mapping->flags & AMDGPU_PTE_MTYPE_NV10_MASK);
-	} else {
-		flags &= ~AMDGPU_PTE_MTYPE_VG10_MASK;
-		flags |= (mapping->flags & AMDGPU_PTE_MTYPE_VG10_MASK);
-	}
-
-	if ((mapping->flags & AMDGPU_PTE_PRT) &&
-	    (adev->asic_type >= CHIP_VEGA10)) {
-		flags |= AMDGPU_PTE_PRT;
-		if (adev->asic_type >= CHIP_NAVI10) {
-			flags |= AMDGPU_PTE_SNOOPED;
-			flags |= AMDGPU_PTE_LOG;
-			flags |= AMDGPU_PTE_SYSTEM;
-		}
-		flags &= ~AMDGPU_PTE_VALID;
-	}
+	/* Apply ASIC specific mapping flags */
+	amdgpu_gmc_get_vm_pte(adev, mapping, &flags);
 
 	trace_amdgpu_vm_bo_update(mapping);
 
@@ -1633,7 +1652,8 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				dma_addr = pages_addr;
 			} else {
 				addr = pages_addr[pfn];
-				max_entries = count * AMDGPU_GPU_PAGES_IN_CPU_PAGE;
+				max_entries = count *
+					AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			}
 
 		} else if (flags & AMDGPU_PTE_VALID) {
@@ -1642,9 +1662,9 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		}
 
 		last = min((uint64_t)mapping->last, start + max_entries - 1);
-		r = amdgpu_vm_bo_update_mapping(adev, exclusive, dma_addr, vm,
+		r = amdgpu_vm_bo_update_mapping(adev, vm, false, exclusive,
 						start, last, flags, addr,
-						fence);
+						dma_addr, fence);
 		if (r)
 			return r;
 
@@ -1672,8 +1692,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
  * Returns:
  * 0 for success, -EINVAL for failure.
  */
-int amdgpu_vm_bo_update(struct amdgpu_device *adev,
-			struct amdgpu_bo_va *bo_va,
+int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va,
 			bool clear)
 {
 	struct amdgpu_bo *bo = bo_va->base.bo;
@@ -1700,7 +1719,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			ttm = container_of(bo->tbo.ttm, struct ttm_dma_tt, ttm);
 			pages_addr = ttm->dma_address;
 		}
-		exclusive = dma_resv_get_excl(bo->tbo.base.resv);
+		exclusive = bo->tbo.moving;
 	}
 
 	if (bo) {
@@ -1731,12 +1750,6 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			return r;
 	}
 
-	if (vm->use_cpu_for_update) {
-		/* Flush HDP */
-		mb();
-		amdgpu_asic_flush_hdp(adev, NULL);
-	}
-
 	/* If the BO is not in its preferred location add it back to
 	 * the evicted list so that it gets validated again on the
 	 * next command submission.
@@ -1744,7 +1757,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	if (bo && bo->tbo.base.resv == vm->root.base.bo->tbo.base.resv) {
 		uint32_t mem_type = bo->tbo.mem.mem_type;
 
-		if (!(bo->preferred_domains & amdgpu_mem_type_to_domain(mem_type)))
+		if (!(bo->preferred_domains &
+		      amdgpu_mem_type_to_domain(mem_type)))
 			amdgpu_vm_bo_evicted(&bo_va->base);
 		else
 			amdgpu_vm_bo_idle(&bo_va->base);
@@ -1938,9 +1952,9 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 		    mapping->start < AMDGPU_GMC_HOLE_START)
 			init_pte_value = AMDGPU_PTE_DEFAULT_ATC;
 
-		r = amdgpu_vm_bo_update_mapping(adev, NULL, NULL, vm,
+		r = amdgpu_vm_bo_update_mapping(adev, vm, false, NULL,
 						mapping->start, mapping->last,
-						init_pte_value, 0, &f);
+						init_pte_value, 0, NULL, &f);
 		amdgpu_vm_free_mapping(adev, vm, mapping, f);
 		if (r) {
 			dma_fence_put(f);
@@ -2682,12 +2696,17 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	spin_lock_init(&vm->invalidated_lock);
 	INIT_LIST_HEAD(&vm->freed);
 
-	/* create scheduler entity for page table updates */
-	r = drm_sched_entity_init(&vm->entity, adev->vm_manager.vm_pte_rqs,
+	/* create scheduler entities for page table updates */
+	r = drm_sched_entity_init(&vm->direct, adev->vm_manager.vm_pte_rqs,
 				  adev->vm_manager.vm_pte_num_rqs, NULL);
 	if (r)
 		return r;
 
+	r = drm_sched_entity_init(&vm->delayed, adev->vm_manager.vm_pte_rqs,
+				  adev->vm_manager.vm_pte_num_rqs, NULL);
+	if (r)
+		goto error_free_direct;
+
 	vm->pte_support_ats = false;
 
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE) {
@@ -2702,7 +2721,8 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update && !amdgpu_gmc_vram_full_visible(&adev->gmc)),
+	WARN_ONCE((vm->use_cpu_for_update &&
+		   !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 
 	if (vm->use_cpu_for_update)
@@ -2711,12 +2731,12 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		vm->update_funcs = &amdgpu_vm_sdma_funcs;
 	vm->last_update = NULL;
 
-	amdgpu_vm_bo_param(adev, vm, adev->vm_manager.root_level, &bp);
+	amdgpu_vm_bo_param(adev, vm, adev->vm_manager.root_level, false, &bp);
 	if (vm_context == AMDGPU_VM_CONTEXT_COMPUTE)
 		bp.flags &= ~AMDGPU_GEM_CREATE_SHADOW;
 	r = amdgpu_bo_create(adev, &bp, &root);
 	if (r)
-		goto error_free_sched_entity;
+		goto error_free_delayed;
 
 	r = amdgpu_bo_reserve(root, true);
 	if (r)
@@ -2728,7 +2748,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 
 	amdgpu_vm_bo_base_init(&vm->root.base, vm, root);
 
-	r = amdgpu_vm_clear_bo(adev, vm, root);
+	r = amdgpu_vm_clear_bo(adev, vm, root, false);
 	if (r)
 		goto error_unreserve;
 
@@ -2759,8 +2779,11 @@ error_free_root:
 	amdgpu_bo_unref(&vm->root.base.bo);
 	vm->root.base.bo = NULL;
 
-error_free_sched_entity:
-	drm_sched_entity_destroy(&vm->entity);
+error_free_delayed:
+	drm_sched_entity_destroy(&vm->delayed);
+
+error_free_direct:
+	drm_sched_entity_destroy(&vm->direct);
 
 	return r;
 }
@@ -2801,6 +2824,7 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
+ * @pasid: pasid to use
  *
  * This only works on GFX VMs that don't have any BOs added and no
  * page tables allocated yet.
@@ -2816,7 +2840,8 @@ static int amdgpu_vm_check_clean_reserved(struct amdgpu_device *adev,
  * Returns:
  * 0 for success, -errno for errors.
  */
-int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, unsigned int pasid)
+int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+			   unsigned int pasid)
 {
 	bool pte_support_ats = (adev->asic_type == CHIP_RAVEN);
 	int r;
@@ -2848,7 +2873,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, uns
 	 */
 	if (pte_support_ats != vm->pte_support_ats) {
 		vm->pte_support_ats = pte_support_ats;
-		r = amdgpu_vm_clear_bo(adev, vm, vm->root.base.bo);
+		r = amdgpu_vm_clear_bo(adev, vm, vm->root.base.bo, false);
 		if (r)
 			goto free_idr;
 	}
@@ -2858,7 +2883,8 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm, uns
 				    AMDGPU_VM_USE_CPU_FOR_COMPUTE);
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update && !amdgpu_gmc_vram_full_visible(&adev->gmc)),
+	WARN_ONCE((vm->use_cpu_for_update &&
+		   !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 
 	if (vm->use_cpu_for_update)
@@ -2937,19 +2963,38 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	struct amdgpu_bo_va_mapping *mapping, *tmp;
 	bool prt_fini_needed = !!adev->gmc.gmc_funcs->set_prt;
 	struct amdgpu_bo *root;
-	int i, r;
+	int i;
 
 	amdgpu_amdkfd_gpuvm_destroy_cb(adev, vm);
 
+	root = amdgpu_bo_ref(vm->root.base.bo);
+	amdgpu_bo_reserve(root, true);
 	if (vm->pasid) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags);
 		idr_remove(&adev->vm_manager.pasid_idr, vm->pasid);
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
+		vm->pasid = 0;
+	}
+
+	list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
+		if (mapping->flags & AMDGPU_PTE_PRT && prt_fini_needed) {
+			amdgpu_vm_prt_fini(adev, vm);
+			prt_fini_needed = false;
+		}
+
+		list_del(&mapping->list);
+		amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
 	}
 
-	drm_sched_entity_destroy(&vm->entity);
+	amdgpu_vm_free_pts(adev, vm, NULL);
+	amdgpu_bo_unreserve(root);
+	amdgpu_bo_unref(&root);
+	WARN_ON(vm->root.base.bo);
+
+	drm_sched_entity_destroy(&vm->direct);
+	drm_sched_entity_destroy(&vm->delayed);
 
 	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
@@ -2962,26 +3007,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		list_del(&mapping->list);
 		kfree(mapping);
 	}
-	list_for_each_entry_safe(mapping, tmp, &vm->freed, list) {
-		if (mapping->flags & AMDGPU_PTE_PRT && prt_fini_needed) {
-			amdgpu_vm_prt_fini(adev, vm);
-			prt_fini_needed = false;
-		}
-
-		list_del(&mapping->list);
-		amdgpu_vm_free_mapping(adev, vm, mapping, NULL);
-	}
 
-	root = amdgpu_bo_ref(vm->root.base.bo);
-	r = amdgpu_bo_reserve(root, true);
-	if (r) {
-		dev_err(adev->dev, "Leaking page tables because BO reservation failed\n");
-	} else {
-		amdgpu_vm_free_pts(adev, vm, NULL);
-		amdgpu_bo_unreserve(root);
-	}
-	amdgpu_bo_unref(&root);
-	WARN_ON(vm->root.base.bo);
 	dma_fence_put(vm->last_update);
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; i++)
 		amdgpu_vmid_free_reserved(adev, vm, i);
@@ -3065,8 +3091,9 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	switch (args->in.op) {
 	case AMDGPU_VM_OP_RESERVE_VMID:
-		/* current, we only have requirement to reserve vmid from gfxhub */
-		r = amdgpu_vmid_alloc_reserved(adev, &fpriv->vm, AMDGPU_GFXHUB_0);
+		/* We only have requirement to reserve vmid from gfxhub */
+		r = amdgpu_vmid_alloc_reserved(adev, &fpriv->vm,
+					       AMDGPU_GFXHUB_0);
 		if (r)
 			return r;
 		break;
@@ -3109,13 +3136,88 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
  */
 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 (vm->task_info.pid)
+		return;
 
-		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);
-		}
+	vm->task_info.pid = current->pid;
+	get_task_comm(vm->task_info.task_name, current);
+
+	if (current->group_leader->mm != current->mm)
+		return;
+
+	vm->task_info.tgid = current->group_leader->pid;
+	get_task_comm(vm->task_info.process_name, current->group_leader);
+}
+
+/**
+ * amdgpu_vm_handle_fault - graceful handling of VM faults.
+ * @adev: amdgpu device pointer
+ * @pasid: PASID of the VM
+ * @addr: Address of the fault
+ *
+ * Try to gracefully handle a VM fault. Return true if the fault was handled and
+ * shouldn't be reported any more.
+ */
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+			    uint64_t addr)
+{
+	struct amdgpu_bo *root;
+	uint64_t value, flags;
+	struct amdgpu_vm *vm;
+	long r;
+
+	spin_lock(&adev->vm_manager.pasid_lock);
+	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	if (vm)
+		root = amdgpu_bo_ref(vm->root.base.bo);
+	else
+		root = NULL;
+	spin_unlock(&adev->vm_manager.pasid_lock);
+
+	if (!root)
+		return false;
+
+	r = amdgpu_bo_reserve(root, true);
+	if (r)
+		goto error_unref;
+
+	/* Double check that the VM still exists */
+	spin_lock(&adev->vm_manager.pasid_lock);
+	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	if (vm && vm->root.base.bo != root)
+		vm = NULL;
+	spin_unlock(&adev->vm_manager.pasid_lock);
+	if (!vm)
+		goto error_unlock;
+
+	addr /= AMDGPU_GPU_PAGE_SIZE;
+	flags = AMDGPU_PTE_VALID | AMDGPU_PTE_SNOOPED |
+		AMDGPU_PTE_SYSTEM;
+
+	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_NEVER) {
+		/* Redirect the access to the dummy page */
+		value = adev->dummy_page_addr;
+		flags |= AMDGPU_PTE_EXECUTABLE | AMDGPU_PTE_READABLE |
+			AMDGPU_PTE_WRITEABLE;
+	} else {
+		/* Let the hw retry silently on the PTE */
+		value = 0;
 	}
+
+	r = amdgpu_vm_bo_update_mapping(adev, vm, true, NULL, addr, addr + 1,
+					flags, value, NULL, NULL);
+	if (r)
+		goto error_unlock;
+
+	r = amdgpu_vm_update_pdes(adev, vm, true);
+
+error_unlock:
+	amdgpu_bo_unreserve(root);
+	if (r < 0)
+		DRM_ERROR("Can't handle page fault (%ld)\n", r);
+
+error_unref:
+	amdgpu_bo_unref(&root);
+
+	return false;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 2eda3a8c330d..4dbbe1b6b413 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -99,6 +99,9 @@ struct amdgpu_bo_list_entry;
 #define AMDGPU_VM_FAULT_STOP_FIRST	1
 #define AMDGPU_VM_FAULT_STOP_ALWAYS	2
 
+/* Reserve 4MB VRAM for page tables */
+#define AMDGPU_VM_RESERVED_VRAM		(4ULL << 20)
+
 /* max number of VMHUB */
 #define AMDGPU_MAX_VMHUBS			3
 #define AMDGPU_GFXHUB_0				0
@@ -199,6 +202,11 @@ struct amdgpu_vm_update_params {
 	struct amdgpu_vm *vm;
 
 	/**
+	 * @direct: if changes should be made directly
+	 */
+	bool direct;
+
+	/**
 	 * @pages_addr:
 	 *
 	 * DMA addresses to use for mapping
@@ -254,8 +262,9 @@ struct amdgpu_vm {
 	struct amdgpu_vm_pt     root;
 	struct dma_fence	*last_update;
 
-	/* Scheduler entity for page table updates */
-	struct drm_sched_entity	entity;
+	/* Scheduler entities for page table updates */
+	struct drm_sched_entity	direct;
+	struct drm_sched_entity	delayed;
 
 	unsigned int		pasid;
 	/* dedicated to vm */
@@ -357,8 +366,8 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      int (*callback)(void *p, struct amdgpu_bo *bo),
 			      void *param);
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync);
-int amdgpu_vm_update_directories(struct amdgpu_device *adev,
-				 struct amdgpu_vm *vm);
+int amdgpu_vm_update_pdes(struct amdgpu_device *adev,
+			  struct amdgpu_vm *vm, bool direct);
 int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm,
 			  struct dma_fence **fence);
@@ -404,6 +413,8 @@ 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);
+bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, unsigned int pasid,
+			    uint64_t addr);
 
 void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
index 5222d165abfc..73fec7a0ced5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_cpu.c
@@ -49,13 +49,6 @@ static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p, void *owner,
 {
 	int r;
 
-	/* Wait for PT BOs to be idle. PTs share the same resv. object
-	 * as the root PD BO
-	 */
-	r = amdgpu_bo_sync_wait(p->vm->root.base.bo, owner, true);
-	if (unlikely(r))
-		return r;
-
 	/* Wait for any BO move to be completed */
 	if (exclusive) {
 		r = dma_fence_wait(exclusive, true);
@@ -63,7 +56,14 @@ static int amdgpu_vm_cpu_prepare(struct amdgpu_vm_update_params *p, void *owner,
 			return r;
 	}
 
-	return 0;
+	/* Don't wait for submissions during page fault */
+	if (p->direct)
+		return 0;
+
+	/* Wait for PT BOs to be idle. PTs share the same resv. object
+	 * as the root PD BO
+	 */
+	return amdgpu_bo_sync_wait(p->vm->root.base.bo, owner, true);
 }
 
 /**
@@ -89,7 +89,7 @@ static int amdgpu_vm_cpu_update(struct amdgpu_vm_update_params *p,
 
 	pe += (unsigned long)amdgpu_bo_kptr(bo);
 
-	trace_amdgpu_vm_set_ptes(pe, addr, count, incr, flags);
+	trace_amdgpu_vm_set_ptes(pe, addr, count, incr, flags, p->direct);
 
 	for (i = 0; i < count; i++) {
 		value = p->pages_addr ?
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
index 61fc584cbb1a..832db59f441e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
@@ -68,17 +68,19 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
 	if (r)
 		return r;
 
+	p->num_dw_left = ndw;
+
+	/* Wait for moves to be completed */
 	r = amdgpu_sync_fence(p->adev, &p->job->sync, exclusive, false);
 	if (r)
 		return r;
 
-	r = amdgpu_sync_resv(p->adev, &p->job->sync, root->tbo.base.resv,
-			     owner, false);
-	if (r)
-		return r;
+	/* Don't wait for any submissions during page fault handling */
+	if (p->direct)
+		return 0;
 
-	p->num_dw_left = ndw;
-	return 0;
+	return amdgpu_sync_resv(p->adev, &p->job->sync, root->tbo.base.resv,
+				owner, false);
 }
 
 /**
@@ -95,22 +97,23 @@ static int amdgpu_vm_sdma_commit(struct amdgpu_vm_update_params *p,
 {
 	struct amdgpu_bo *root = p->vm->root.base.bo;
 	struct amdgpu_ib *ib = p->job->ibs;
+	struct drm_sched_entity *entity;
 	struct amdgpu_ring *ring;
 	struct dma_fence *f;
 	int r;
 
-	ring = container_of(p->vm->entity.rq->sched, struct amdgpu_ring, sched);
+	entity = p->direct ? &p->vm->direct : &p->vm->delayed;
+	ring = container_of(entity->rq->sched, struct amdgpu_ring, sched);
 
 	WARN_ON(ib->length_dw == 0);
 	amdgpu_ring_pad_ib(ring, ib);
 	WARN_ON(ib->length_dw > p->num_dw_left);
-	r = amdgpu_job_submit(p->job, &p->vm->entity,
-			      AMDGPU_FENCE_OWNER_VM, &f);
+	r = amdgpu_job_submit(p->job, entity, AMDGPU_FENCE_OWNER_VM, &f);
 	if (r)
 		goto error;
 
 	amdgpu_bo_fence(root, f, true);
-	if (fence)
+	if (fence && !p->direct)
 		swap(*fence, f);
 	dma_fence_put(f);
 	return 0;
@@ -120,7 +123,6 @@ error:
 	return r;
 }
 
-
 /**
  * amdgpu_vm_sdma_copy_ptes - copy the PTEs from mapping
  *
@@ -141,7 +143,7 @@ static void amdgpu_vm_sdma_copy_ptes(struct amdgpu_vm_update_params *p,
 	src += p->num_dw_left * 4;
 
 	pe += amdgpu_bo_gpu_offset(bo);
-	trace_amdgpu_vm_copy_ptes(pe, src, count);
+	trace_amdgpu_vm_copy_ptes(pe, src, count, p->direct);
 
 	amdgpu_vm_copy_pte(p->adev, ib, pe, src, count);
 }
@@ -168,7 +170,7 @@ static void amdgpu_vm_sdma_set_ptes(struct amdgpu_vm_update_params *p,
 	struct amdgpu_ib *ib = p->job->ibs;
 
 	pe += amdgpu_bo_gpu_offset(bo);
-	trace_amdgpu_vm_set_ptes(pe, addr, count, incr, flags);
+	trace_amdgpu_vm_set_ptes(pe, addr, count, incr, flags, p->direct);
 	if (count < 3) {
 		amdgpu_vm_write_pte(p->adev, ib, pe, addr | flags,
 				    count, incr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 3a9d8c15fe9f..82a3299e53c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -23,6 +23,9 @@
  */
 
 #include "amdgpu.h"
+#include "amdgpu_vm.h"
+#include "amdgpu_atomfirmware.h"
+#include "atom.h"
 
 struct amdgpu_vram_mgr {
 	struct drm_mm mm;
@@ -101,6 +104,39 @@ static ssize_t amdgpu_mem_info_vis_vram_used_show(struct device *dev,
 		amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]));
 }
 
+static ssize_t amdgpu_mem_info_vram_vendor(struct device *dev,
+						 struct device_attribute *attr,
+						 char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+
+	switch (adev->gmc.vram_vendor) {
+	case SAMSUNG:
+		return snprintf(buf, PAGE_SIZE, "samsung\n");
+	case INFINEON:
+		return snprintf(buf, PAGE_SIZE, "infineon\n");
+	case ELPIDA:
+		return snprintf(buf, PAGE_SIZE, "elpida\n");
+	case ETRON:
+		return snprintf(buf, PAGE_SIZE, "etron\n");
+	case NANYA:
+		return snprintf(buf, PAGE_SIZE, "nanya\n");
+	case HYNIX:
+		return snprintf(buf, PAGE_SIZE, "hynix\n");
+	case MOSEL:
+		return snprintf(buf, PAGE_SIZE, "mosel\n");
+	case WINBOND:
+		return snprintf(buf, PAGE_SIZE, "winbond\n");
+	case ESMT:
+		return snprintf(buf, PAGE_SIZE, "esmt\n");
+	case MICRON:
+		return snprintf(buf, PAGE_SIZE, "micron\n");
+	default:
+		return snprintf(buf, PAGE_SIZE, "unknown\n");
+	}
+}
+
 static DEVICE_ATTR(mem_info_vram_total, S_IRUGO,
 		   amdgpu_mem_info_vram_total_show, NULL);
 static DEVICE_ATTR(mem_info_vis_vram_total, S_IRUGO,
@@ -109,6 +145,8 @@ static DEVICE_ATTR(mem_info_vram_used, S_IRUGO,
 		   amdgpu_mem_info_vram_used_show, NULL);
 static DEVICE_ATTR(mem_info_vis_vram_used, S_IRUGO,
 		   amdgpu_mem_info_vis_vram_used_show, NULL);
+static DEVICE_ATTR(mem_info_vram_vendor, S_IRUGO,
+		   amdgpu_mem_info_vram_vendor, NULL);
 
 /**
  * amdgpu_vram_mgr_init - init VRAM manager and DRM MM
@@ -154,6 +192,11 @@ static int amdgpu_vram_mgr_init(struct ttm_mem_type_manager *man,
 		DRM_ERROR("Failed to create device file mem_info_vis_vram_used\n");
 		return ret;
 	}
+	ret = device_create_file(adev->dev, &dev_attr_mem_info_vram_vendor);
+	if (ret) {
+		DRM_ERROR("Failed to create device file mem_info_vram_vendor\n");
+		return ret;
+	}
 
 	return 0;
 }
@@ -180,6 +223,7 @@ static int amdgpu_vram_mgr_fini(struct ttm_mem_type_manager *man)
 	device_remove_file(adev->dev, &dev_attr_mem_info_vis_vram_total);
 	device_remove_file(adev->dev, &dev_attr_mem_info_vram_used);
 	device_remove_file(adev->dev, &dev_attr_mem_info_vis_vram_used);
+	device_remove_file(adev->dev, &dev_attr_mem_info_vram_vendor);
 	return 0;
 }
 
@@ -275,7 +319,7 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
 	struct drm_mm_node *nodes;
 	enum drm_mm_insert_mode mode;
 	unsigned long lpfn, num_nodes, pages_per_node, pages_left;
-	uint64_t vis_usage = 0, mem_bytes;
+	uint64_t vis_usage = 0, mem_bytes, max_bytes;
 	unsigned i;
 	int r;
 
@@ -283,9 +327,13 @@ static int amdgpu_vram_mgr_new(struct ttm_mem_type_manager *man,
 	if (!lpfn)
 		lpfn = man->size;
 
+	max_bytes = adev->gmc.mc_vram_size;
+	if (tbo->type != ttm_bo_type_kernel)
+		max_bytes -= AMDGPU_VM_RESERVED_VRAM;
+
 	/* bail out quickly if there's likely not enough VRAM for this BO */
 	mem_bytes = (u64)mem->num_pages << PAGE_SHIFT;
-	if (atomic64_add_return(mem_bytes, &mgr->usage) > adev->gmc.mc_vram_size) {
+	if (atomic64_add_return(mem_bytes, &mgr->usage) > max_bytes) {
 		atomic64_sub(mem_bytes, &mgr->usage);
 		mem->mm_node = NULL;
 		return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
index 65aae75f80fd..61d13d8b7b20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
@@ -25,6 +25,7 @@
 #include "amdgpu.h"
 #include "amdgpu_xgmi.h"
 #include "amdgpu_smu.h"
+#include "amdgpu_ras.h"
 #include "df/df_3_6_offset.h"
 
 static DEFINE_MUTEX(xgmi_mutex);
@@ -273,22 +274,55 @@ int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate)
 {
 	int ret = 0;
 	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(adev, 0);
+	struct amdgpu_device *tmp_adev;
+	bool update_hive_pstate = true;
+	bool is_high_pstate = pstate && adev->asic_type == CHIP_VEGA20;
 
 	if (!hive)
 		return 0;
 
-	if (hive->pstate == pstate)
-		return 0;
+	mutex_lock(&hive->hive_lock);
+
+	if (hive->pstate == pstate) {
+		adev->pstate = is_high_pstate ? pstate : adev->pstate;
+		goto out;
+	}
 
 	dev_dbg(adev->dev, "Set xgmi pstate %d.\n", pstate);
 
 	if (is_support_sw_smu_xgmi(adev))
 		ret = smu_set_xgmi_pstate(&adev->smu, pstate);
-	if (ret)
+	else if (adev->powerplay.pp_funcs &&
+		 adev->powerplay.pp_funcs->set_xgmi_pstate)
+		ret = adev->powerplay.pp_funcs->set_xgmi_pstate(adev->powerplay.pp_handle,
+								pstate);
+
+	if (ret) {
 		dev_err(adev->dev,
 			"XGMI: Set pstate failure on device %llx, hive %llx, ret %d",
 			adev->gmc.xgmi.node_id,
 			adev->gmc.xgmi.hive_id, ret);
+		goto out;
+	}
+
+	/* Update device pstate */
+	adev->pstate = pstate;
+
+	/*
+	 * Update the hive pstate only all devices of the hive
+	 * are in the same pstate
+	 */
+	list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+		if (tmp_adev->pstate != adev->pstate) {
+			update_hive_pstate = false;
+			break;
+		}
+	}
+	if (update_hive_pstate || is_high_pstate)
+		hive->pstate = pstate;
+
+out:
+	mutex_unlock(&hive->hive_lock);
 
 	return ret;
 }
@@ -363,6 +397,9 @@ int amdgpu_xgmi_add_device(struct amdgpu_device *adev)
 		goto exit;
 	}
 
+	/* Set default device pstate */
+	adev->pstate = -1;
+
 	top_info = &adev->psp.xgmi_context.top_info;
 
 	list_add_tail(&adev->gmc.xgmi.head, &hive->device_list);
@@ -437,3 +474,52 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev)
 		mutex_unlock(&hive->hive_lock);
 	}
 }
+
+int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev)
+{
+	int r;
+	struct ras_ih_if ih_info = {
+		.cb = NULL,
+	};
+	struct ras_fs_if fs_info = {
+		.sysfs_name = "xgmi_wafl_err_count",
+		.debugfs_name = "xgmi_wafl_err_inject",
+	};
+
+	if (!adev->gmc.xgmi.supported ||
+	    adev->gmc.xgmi.num_physical_nodes == 0)
+		return 0;
+
+	if (!adev->gmc.xgmi.ras_if) {
+		adev->gmc.xgmi.ras_if = kmalloc(sizeof(struct ras_common_if), GFP_KERNEL);
+		if (!adev->gmc.xgmi.ras_if)
+			return -ENOMEM;
+		adev->gmc.xgmi.ras_if->block = AMDGPU_RAS_BLOCK__XGMI_WAFL;
+		adev->gmc.xgmi.ras_if->type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+		adev->gmc.xgmi.ras_if->sub_block_index = 0;
+		strcpy(adev->gmc.xgmi.ras_if->name, "xgmi_wafl");
+	}
+	ih_info.head = fs_info.head = *adev->gmc.xgmi.ras_if;
+	r = amdgpu_ras_late_init(adev, adev->gmc.xgmi.ras_if,
+				 &fs_info, &ih_info);
+	if (r || !amdgpu_ras_is_supported(adev, adev->gmc.xgmi.ras_if->block)) {
+		kfree(adev->gmc.xgmi.ras_if);
+		adev->gmc.xgmi.ras_if = NULL;
+	}
+
+	return r;
+}
+
+void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev)
+{
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__XGMI_WAFL) &&
+			adev->gmc.xgmi.ras_if) {
+		struct ras_common_if *ras_if = adev->gmc.xgmi.ras_if;
+		struct ras_ih_if ih_info = {
+			.cb = NULL,
+		};
+
+		amdgpu_ras_late_fini(adev, ras_if, &ih_info);
+		kfree(ras_if);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
index fbcee31788c4..bbf504ff7051 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.h
@@ -42,6 +42,8 @@ void amdgpu_xgmi_remove_device(struct amdgpu_device *adev);
 int amdgpu_xgmi_set_pstate(struct amdgpu_device *adev, int pstate);
 int amdgpu_xgmi_get_hops_count(struct amdgpu_device *adev,
 		struct amdgpu_device *peer_adev);
+int amdgpu_xgmi_ras_late_init(struct amdgpu_device *adev);
+void amdgpu_xgmi_ras_fini(struct amdgpu_device *adev);
 
 static inline bool amdgpu_xgmi_same_hive(struct amdgpu_device *adev,
 		struct amdgpu_device *bo_adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/arct_reg_init.c b/drivers/gpu/drm/amd/amdgpu/arct_reg_init.c
index 4853899b1824..fda99c958c3b 100644
--- a/drivers/gpu/drm/amd/amdgpu/arct_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/arct_reg_init.c
@@ -24,7 +24,6 @@
 #include "soc15.h"
 
 #include "soc15_common.h"
-#include "soc15_hw_ip.h"
 #include "arct_ip_offset.h"
 
 int arct_reg_base_init(struct amdgpu_device *adev)
@@ -52,6 +51,8 @@ int arct_reg_base_init(struct amdgpu_device *adev)
 		adev->reg_offset[SDMA7_HWIP][i] = (uint32_t *)(&(SDMA7_BASE.instance[i]));
 		adev->reg_offset[SMUIO_HWIP][i] = (uint32_t *)(&(SMUIO_BASE.instance[i]));
 		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[UMC_HWIP][i] = (uint32_t *)(&(UMC_BASE.instance[i]));
+		adev->reg_offset[RSMU_HWIP][i] = (uint32_t *)(&(RSMU_BASE.instance[i]));
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index b81bb414fcb3..b22a10b2d201 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -966,6 +966,25 @@ static bool cik_read_bios_from_rom(struct amdgpu_device *adev,
 
 static const struct amdgpu_allowed_register_entry cik_allowed_read_registers[] = {
 	{mmGRBM_STATUS},
+	{mmGRBM_STATUS2},
+	{mmGRBM_STATUS_SE0},
+	{mmGRBM_STATUS_SE1},
+	{mmGRBM_STATUS_SE2},
+	{mmGRBM_STATUS_SE3},
+	{mmSRBM_STATUS},
+	{mmSRBM_STATUS2},
+	{mmSDMA0_STATUS_REG + SDMA0_REGISTER_OFFSET},
+	{mmSDMA0_STATUS_REG + SDMA1_REGISTER_OFFSET},
+	{mmCP_STAT},
+	{mmCP_STALLED_STAT1},
+	{mmCP_STALLED_STAT2},
+	{mmCP_STALLED_STAT3},
+	{mmCP_CPF_BUSY_STAT},
+	{mmCP_CPF_STALLED_STAT1},
+	{mmCP_CPF_STATUS},
+	{mmCP_CPC_BUSY_STAT},
+	{mmCP_CPC_STALLED_STAT1},
+	{mmCP_CPC_STATUS},
 	{mmGB_ADDR_CONFIG},
 	{mmMC_ARB_RAMCFG},
 	{mmGB_TILE_MODE0},
@@ -1270,15 +1289,15 @@ static int cik_gpu_pci_config_reset(struct amdgpu_device *adev)
 }
 
 /**
- * cik_asic_reset - soft reset GPU
+ * cik_asic_pci_config_reset - soft reset GPU
  *
  * @adev: amdgpu_device pointer
  *
- * Look up which blocks are hung and attempt
- * to reset them.
+ * Use PCI Config method to reset the GPU.
+ *
  * Returns 0 for success.
  */
-static int cik_asic_reset(struct amdgpu_device *adev)
+static int cik_asic_pci_config_reset(struct amdgpu_device *adev)
 {
 	int r;
 
@@ -1294,7 +1313,48 @@ static int cik_asic_reset(struct amdgpu_device *adev)
 static enum amd_reset_method
 cik_asic_reset_method(struct amdgpu_device *adev)
 {
-	return AMD_RESET_METHOD_LEGACY;
+	bool baco_reset;
+
+	switch (adev->asic_type) {
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+		/* disable baco reset until it works */
+		/* smu7_asic_get_baco_capability(adev, &baco_reset); */
+		baco_reset = false;
+		break;
+	default:
+		baco_reset = false;
+		break;
+	}
+
+	if (baco_reset)
+		return AMD_RESET_METHOD_BACO;
+	else
+		return AMD_RESET_METHOD_LEGACY;
+}
+
+/**
+ * cik_asic_reset - soft reset GPU
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Look up which blocks are hung and attempt
+ * to reset them.
+ * Returns 0 for success.
+ */
+static int cik_asic_reset(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (cik_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
+		r = smu7_asic_baco_reset(adev);
+	} else {
+		r = cik_asic_pci_config_reset(adev);
+	}
+
+	return r;
 }
 
 static u32 cik_get_config_memsize(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/cik.h b/drivers/gpu/drm/amd/amdgpu/cik.h
index 54c625a2e570..9870bf27870e 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.h
+++ b/drivers/gpu/drm/amd/amdgpu/cik.h
@@ -31,4 +31,7 @@ void cik_srbm_select(struct amdgpu_device *adev,
 int cik_set_ip_blocks(struct amdgpu_device *adev);
 
 void legacy_doorbell_index_init(struct amdgpu_device *adev);
+int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap);
+int smu7_asic_baco_reset(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 645550e7caf5..40d2ac723dd6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -330,9 +330,11 @@ static void dce_v10_0_hpd_init(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -368,6 +370,7 @@ static void dce_v10_0_hpd_init(struct amdgpu_device *adev)
 		amdgpu_irq_get(adev, &adev->hpd_irq,
 			       amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 /**
@@ -382,9 +385,11 @@ static void dce_v10_0_hpd_fini(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -397,6 +402,7 @@ static void dce_v10_0_hpd_fini(struct amdgpu_device *adev)
 		amdgpu_irq_put(adev, &adev->hpd_irq,
 			       amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 static u32 dce_v10_0_hpd_get_gpio_reg(struct amdgpu_device *adev)
@@ -1219,10 +1225,12 @@ static void dce_v10_0_afmt_audio_select_pin(struct drm_encoder *encoder)
 static void dce_v10_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u32 tmp;
 	int interlace = 0;
@@ -1230,12 +1238,14 @@ static void dce_v10_0_audio_write_latency_fields(struct drm_encoder *encoder,
 	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1261,10 +1271,12 @@ static void dce_v10_0_audio_write_latency_fields(struct drm_encoder *encoder,
 
 static void dce_v10_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u32 tmp;
 	u8 *sadb = NULL;
@@ -1273,12 +1285,14 @@ static void dce_v10_0_audio_write_speaker_allocation(struct drm_encoder *encoder
 	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1313,10 +1327,12 @@ static void dce_v10_0_audio_write_speaker_allocation(struct drm_encoder *encoder
 
 static void dce_v10_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	struct cea_sad *sads;
 	int i, sad_count;
@@ -1339,12 +1355,14 @@ static void dce_v10_0_audio_write_sad_regs(struct drm_encoder *encoder)
 	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1352,10 +1370,10 @@ static void dce_v10_0_audio_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(amdgpu_connector_edid(connector), &sads);
-	if (sad_count <= 0) {
+	if (sad_count < 0)
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+	if (sad_count <= 0)
 		return;
-	}
 	BUG_ON(!sads);
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index d9f470632b2c..898ef72d423c 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -348,9 +348,11 @@ static void dce_v11_0_hpd_init(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -385,6 +387,7 @@ static void dce_v11_0_hpd_init(struct amdgpu_device *adev)
 		dce_v11_0_hpd_set_polarity(adev, amdgpu_connector->hpd.hpd);
 		amdgpu_irq_get(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 /**
@@ -399,9 +402,11 @@ static void dce_v11_0_hpd_fini(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -413,6 +418,7 @@ static void dce_v11_0_hpd_fini(struct amdgpu_device *adev)
 
 		amdgpu_irq_put(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 static u32 dce_v11_0_hpd_get_gpio_reg(struct amdgpu_device *adev)
@@ -1245,10 +1251,12 @@ static void dce_v11_0_afmt_audio_select_pin(struct drm_encoder *encoder)
 static void dce_v11_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u32 tmp;
 	int interlace = 0;
@@ -1256,12 +1264,14 @@ static void dce_v11_0_audio_write_latency_fields(struct drm_encoder *encoder,
 	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1287,10 +1297,12 @@ static void dce_v11_0_audio_write_latency_fields(struct drm_encoder *encoder,
 
 static void dce_v11_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u32 tmp;
 	u8 *sadb = NULL;
@@ -1299,12 +1311,14 @@ static void dce_v11_0_audio_write_speaker_allocation(struct drm_encoder *encoder
 	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1339,10 +1353,12 @@ static void dce_v11_0_audio_write_speaker_allocation(struct drm_encoder *encoder
 
 static void dce_v11_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	struct cea_sad *sads;
 	int i, sad_count;
@@ -1365,12 +1381,14 @@ static void dce_v11_0_audio_write_sad_regs(struct drm_encoder *encoder)
 	if (!dig || !dig->afmt || !dig->afmt->pin)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1378,10 +1396,10 @@ static void dce_v11_0_audio_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(amdgpu_connector_edid(connector), &sads);
-	if (sad_count <= 0) {
+	if (sad_count < 0)
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+	if (sad_count <= 0)
 		return;
-	}
 	BUG_ON(!sads);
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 3eb2e7429269..db15a112becc 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -281,9 +281,11 @@ static void dce_v6_0_hpd_init(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -309,7 +311,7 @@ static void dce_v6_0_hpd_init(struct amdgpu_device *adev)
 		dce_v6_0_hpd_set_polarity(adev, amdgpu_connector->hpd.hpd);
 		amdgpu_irq_get(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
-
+	drm_connector_list_iter_end(&iter);
 }
 
 /**
@@ -324,9 +326,11 @@ static void dce_v6_0_hpd_fini(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -338,6 +342,7 @@ static void dce_v6_0_hpd_fini(struct amdgpu_device *adev)
 
 		amdgpu_irq_put(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 static u32 dce_v6_0_hpd_get_gpio_reg(struct amdgpu_device *adev)
@@ -1124,20 +1129,24 @@ static void dce_v6_0_audio_select_pin(struct drm_encoder *encoder)
 static void dce_v6_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	int interlace = 0;
 	u32 tmp;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1164,21 +1173,25 @@ static void dce_v6_0_audio_write_latency_fields(struct drm_encoder *encoder,
 
 static void dce_v6_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u8 *sadb = NULL;
 	int sad_count;
 	u32 tmp;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1221,10 +1234,12 @@ static void dce_v6_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 
 static void dce_v6_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	struct cea_sad *sads;
 	int i, sad_count;
@@ -1244,12 +1259,14 @@ static void dce_v6_0_audio_write_sad_regs(struct drm_encoder *encoder)
 		{ ixAZALIA_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
 	};
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1257,10 +1274,10 @@ static void dce_v6_0_audio_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(amdgpu_connector_edid(connector), &sads);
-	if (sad_count <= 0) {
+	if (sad_count < 0)
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+	if (sad_count <= 0)
 		return;
-	}
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 tmp = 0;
@@ -1632,6 +1649,7 @@ static void dce_v6_0_afmt_setmode(struct drm_encoder *encoder,
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	int em = amdgpu_atombios_encoder_get_encoder_mode(encoder);
 	int bpc = 8;
@@ -1639,12 +1657,14 @@ static void dce_v6_0_afmt_setmode(struct drm_encoder *encoder,
 	if (!dig || !dig->afmt)
 		return;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index a16c5e9e610e..f06c9022c1fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -275,9 +275,11 @@ static void dce_v8_0_hpd_init(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -303,6 +305,7 @@ static void dce_v8_0_hpd_init(struct amdgpu_device *adev)
 		dce_v8_0_hpd_set_polarity(adev, amdgpu_connector->hpd.hpd);
 		amdgpu_irq_get(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 /**
@@ -317,9 +320,11 @@ static void dce_v8_0_hpd_fini(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	u32 tmp;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 
 		if (amdgpu_connector->hpd.hpd >= adev->mode_info.num_hpd)
@@ -331,6 +336,7 @@ static void dce_v8_0_hpd_fini(struct amdgpu_device *adev)
 
 		amdgpu_irq_put(adev, &adev->hpd_irq, amdgpu_connector->hpd.hpd);
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 static u32 dce_v8_0_hpd_get_gpio_reg(struct amdgpu_device *adev)
@@ -1157,10 +1163,12 @@ static void dce_v8_0_afmt_audio_select_pin(struct drm_encoder *encoder)
 static void dce_v8_0_audio_write_latency_fields(struct drm_encoder *encoder,
 						struct drm_display_mode *mode)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u32 tmp = 0, offset;
 
@@ -1169,12 +1177,14 @@ static void dce_v8_0_audio_write_latency_fields(struct drm_encoder *encoder,
 
 	offset = dig->afmt->pin->offset;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1214,10 +1224,12 @@ static void dce_v8_0_audio_write_latency_fields(struct drm_encoder *encoder,
 
 static void dce_v8_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	u32 offset, tmp;
 	u8 *sadb = NULL;
@@ -1228,12 +1240,14 @@ static void dce_v8_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 
 	offset = dig->afmt->pin->offset;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1263,11 +1277,13 @@ static void dce_v8_0_audio_write_speaker_allocation(struct drm_encoder *encoder)
 
 static void dce_v8_0_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct amdgpu_device *adev = encoder->dev->dev_private;
+	struct drm_device *dev = encoder->dev;
+	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_encoder *amdgpu_encoder = to_amdgpu_encoder(encoder);
 	struct amdgpu_encoder_atom_dig *dig = amdgpu_encoder->enc_priv;
 	u32 offset;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct amdgpu_connector *amdgpu_connector = NULL;
 	struct cea_sad *sads;
 	int i, sad_count;
@@ -1292,12 +1308,14 @@ static void dce_v8_0_audio_write_sad_regs(struct drm_encoder *encoder)
 
 	offset = dig->afmt->pin->offset;
 
-	list_for_each_entry(connector, &encoder->dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		if (connector->encoder == encoder) {
 			amdgpu_connector = to_amdgpu_connector(connector);
 			break;
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 
 	if (!amdgpu_connector) {
 		DRM_ERROR("Couldn't find encoder's connector\n");
@@ -1305,10 +1323,10 @@ static void dce_v8_0_audio_write_sad_regs(struct drm_encoder *encoder)
 	}
 
 	sad_count = drm_edid_to_sad(amdgpu_connector_edid(connector), &sads);
-	if (sad_count <= 0) {
+	if (sad_count < 0)
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+	if (sad_count <= 0)
 		return;
-	}
 	BUG_ON(!sads);
 
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
index 844c03868248..d6221298b477 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
@@ -33,6 +33,10 @@ static void df_v1_7_sw_init(struct amdgpu_device *adev)
 {
 }
 
+static void df_v1_7_sw_fini(struct amdgpu_device *adev)
+{
+}
+
 static void df_v1_7_enable_broadcast_mode(struct amdgpu_device *adev,
                                           bool enable)
 {
@@ -111,6 +115,7 @@ static void df_v1_7_enable_ecc_force_par_wr_rmw(struct amdgpu_device *adev,
 
 const struct amdgpu_df_funcs df_v1_7_funcs = {
 	.sw_init = df_v1_7_sw_init,
+	.sw_fini = df_v1_7_sw_fini,
 	.enable_broadcast_mode = df_v1_7_enable_broadcast_mode,
 	.get_fb_channel_number = df_v1_7_get_fb_channel_number,
 	.get_hbm_channel_number = df_v1_7_get_hbm_channel_number,
diff --git a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
index 5850c8e34caa..16fbd2bc8ad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
+++ b/drivers/gpu/drm/amd/amdgpu/df_v3_6.c
@@ -99,8 +99,8 @@ static uint64_t df_v3_6_get_fica(struct amdgpu_device *adev,
 	unsigned long flags, address, data;
 	uint32_t ficadl_val, ficadh_val;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessAddress3);
@@ -122,8 +122,8 @@ static void df_v3_6_set_fica(struct amdgpu_device *adev, uint32_t ficaa_val,
 {
 	unsigned long flags, address, data;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, smnDF_PIE_AON_FabricIndirectConfigAccessAddress3);
@@ -150,8 +150,8 @@ static void df_v3_6_perfmon_rreg(struct amdgpu_device *adev,
 {
 	unsigned long flags, address, data;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, lo_addr);
@@ -172,8 +172,8 @@ static void df_v3_6_perfmon_wreg(struct amdgpu_device *adev, uint32_t lo_addr,
 {
 	unsigned long flags, address, data;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, lo_addr);
@@ -220,6 +220,13 @@ static void df_v3_6_sw_init(struct amdgpu_device *adev)
 		adev->df_perfmon_config_assign_mask[i] = 0;
 }
 
+static void df_v3_6_sw_fini(struct amdgpu_device *adev)
+{
+
+	device_remove_file(adev->dev, &dev_attr_df_cntr_avail);
+
+}
+
 static void df_v3_6_enable_broadcast_mode(struct amdgpu_device *adev,
 					  bool enable)
 {
@@ -537,6 +544,7 @@ static void df_v3_6_pmc_get_count(struct amdgpu_device *adev,
 
 const struct amdgpu_df_funcs df_v3_6_funcs = {
 	.sw_init = df_v3_6_sw_init,
+	.sw_fini = df_v3_6_sw_fini,
 	.enable_broadcast_mode = df_v3_6_enable_broadcast_mode,
 	.get_fb_channel_number = df_v3_6_get_fb_channel_number,
 	.get_hbm_channel_number = df_v3_6_get_hbm_channel_number,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 957811b73672..f2c1b026397b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -93,7 +93,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x00400014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_CPF_CLK_CTRL, 0xfcff8fff, 0xf8000100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0x60000ff0, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000000, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -127,7 +127,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CNTL, 0x60000010, 0x479c0010),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CGTT_CLK_CTRL, 0xfeff0fff, 0x40000100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x00800000, 0x00800000)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x00c00000, 0x00c00000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_10_0_nv10[] =
@@ -140,7 +140,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0xffffffff, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xc0000000, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xcd000000, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xf8ff0fff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0x40000ff0, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -171,7 +171,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_LDS_CLK_CTRL, 0xffffffff, 0xffffffff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTA_CNTL_AUX, 0xfff7ffff, 0x01030000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CNTL, 0x60000010, 0x479c0010),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x00800000, 0x00800000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmUTCL1_CTRL, 0x00c00000, 0x00c00000),
 };
 
 static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
@@ -179,7 +179,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_1_2[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_4, 0x003e001f, 0x003c0014),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_GS_NGG_CLK_CTRL, 0xffff8fff, 0xffff8100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_IA_CLK_CTRL, 0xffff0fff, 0xffff0100),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0xc0000100),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SPI_CLK_CTRL, 0xff7f0fff, 0x0d000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQ_CLK_CTRL, 0xffffcfff, 0x60000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_SQG_CLK_CTRL, 0xffff0fff, 0x40000100),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCGTT_VGT_CLK_CTRL, 0xffff8fff, 0xffff8100),
@@ -564,6 +564,32 @@ static void gfx_v10_0_free_microcode(struct amdgpu_device *adev)
 	kfree(adev->gfx.rlc.register_list_format);
 }
 
+static void gfx_v10_0_check_fw_write_wait(struct amdgpu_device *adev)
+{
+	adev->gfx.cp_fw_write_wait = false;
+
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
+		if ((adev->gfx.me_fw_version >= 0x00000046) &&
+		    (adev->gfx.me_feature_version >= 27) &&
+		    (adev->gfx.pfp_fw_version >= 0x00000068) &&
+		    (adev->gfx.pfp_feature_version >= 27) &&
+		    (adev->gfx.mec_fw_version >= 0x0000005b) &&
+		    (adev->gfx.mec_feature_version >= 27))
+			adev->gfx.cp_fw_write_wait = true;
+		break;
+	default:
+		break;
+	}
+
+	if (adev->gfx.cp_fw_write_wait == false)
+		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
+			      GRBM requires 1-cycle delay in cp firmware\n");
+}
+
+
 static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
 {
 	const struct rlc_firmware_header_v2_1 *rlc_hdr;
@@ -664,59 +690,61 @@ static int gfx_v10_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), "amdgpu/%s_rlc.bin", chip_name);
-	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
-	if (err)
-		goto out;
-	err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
-	rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
-	version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
-	version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
-	if (version_major == 2 && version_minor == 1)
-		adev->gfx.rlc.is_rlc_v2_1 = true;
-
-	adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
-	adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
-	adev->gfx.rlc.save_and_restore_offset =
+	if (!amdgpu_sriov_vf(adev)) {
+		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;
+		err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+		rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
+		version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
+		version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
+		if (version_major == 2 && version_minor == 1)
+			adev->gfx.rlc.is_rlc_v2_1 = true;
+
+		adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
+		adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
+		adev->gfx.rlc.save_and_restore_offset =
 			le32_to_cpu(rlc_hdr->save_and_restore_offset);
-	adev->gfx.rlc.clear_state_descriptor_offset =
+		adev->gfx.rlc.clear_state_descriptor_offset =
 			le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
-	adev->gfx.rlc.avail_scratch_ram_locations =
+		adev->gfx.rlc.avail_scratch_ram_locations =
 			le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
-	adev->gfx.rlc.reg_restore_list_size =
+		adev->gfx.rlc.reg_restore_list_size =
 			le32_to_cpu(rlc_hdr->reg_restore_list_size);
-	adev->gfx.rlc.reg_list_format_start =
+		adev->gfx.rlc.reg_list_format_start =
 			le32_to_cpu(rlc_hdr->reg_list_format_start);
-	adev->gfx.rlc.reg_list_format_separate_start =
+		adev->gfx.rlc.reg_list_format_separate_start =
 			le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
-	adev->gfx.rlc.starting_offsets_start =
+		adev->gfx.rlc.starting_offsets_start =
 			le32_to_cpu(rlc_hdr->starting_offsets_start);
-	adev->gfx.rlc.reg_list_format_size_bytes =
+		adev->gfx.rlc.reg_list_format_size_bytes =
 			le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
-	adev->gfx.rlc.reg_list_size_bytes =
+		adev->gfx.rlc.reg_list_size_bytes =
 			le32_to_cpu(rlc_hdr->reg_list_size_bytes);
-	adev->gfx.rlc.register_list_format =
+		adev->gfx.rlc.register_list_format =
 			kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
-				adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
-	if (!adev->gfx.rlc.register_list_format) {
-		err = -ENOMEM;
-		goto out;
-	}
+					adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
+		if (!adev->gfx.rlc.register_list_format) {
+			err = -ENOMEM;
+			goto out;
+		}
 
-	tmp = (unsigned int *)((uintptr_t)rlc_hdr +
-			le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
-	for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
-		adev->gfx.rlc.register_list_format[i] =	le32_to_cpu(tmp[i]);
+		tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+							   le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
+		for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
+			adev->gfx.rlc.register_list_format[i] =	le32_to_cpu(tmp[i]);
 
-	adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
+		adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
 
-	tmp = (unsigned int *)((uintptr_t)rlc_hdr +
-			le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
-	for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
-		adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
+		tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+							   le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
+		for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
+			adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
 
-	if (adev->gfx.rlc.is_rlc_v2_1)
-		gfx_v10_0_init_rlc_ext_microcode(adev);
+		if (adev->gfx.rlc.is_rlc_v2_1)
+			gfx_v10_0_init_rlc_ext_microcode(adev);
+	}
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
@@ -832,6 +860,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
 		}
 	}
 
+	gfx_v10_0_check_fw_write_wait(adev);
 out:
 	if (err) {
 		dev_err(adev->dev,
@@ -966,39 +995,6 @@ static int gfx_v10_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v10_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_v10_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_v10_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -1442,7 +1438,7 @@ static int gfx_v10_0_sw_fini(void *handle)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
 	amdgpu_gfx_mqd_sw_fini(adev);
-	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
+	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring);
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v10_0_pfp_fini(adev);
@@ -1758,27 +1754,18 @@ static void gfx_v10_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 	WREG32_SOC15(GC, 0, mmCP_INT_CNTL_RING0, tmp);
 }
 
-static void gfx_v10_0_init_csb(struct amdgpu_device *adev)
+static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
+
 	/* csib */
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
 		     adev->gfx.rlc.clear_state_gpu_addr >> 32);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_LO,
 		     adev->gfx.rlc.clear_state_gpu_addr & 0xfffffffc);
 	WREG32_SOC15(GC, 0, mmRLC_CSIB_LENGTH, adev->gfx.rlc.clear_state_size);
-}
-
-static void gfx_v10_0_init_pg(struct amdgpu_device *adev)
-{
-	int i;
-
-	gfx_v10_0_init_csb(adev);
-
-	for (i = 0; i < adev->num_vmhubs; i++)
-		amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
 
-	/* TODO: init power gating */
-	return;
+	return 0;
 }
 
 void gfx_v10_0_rlc_stop(struct amdgpu_device *adev)
@@ -1873,18 +1860,16 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
 {
 	int r;
 
-	if (amdgpu_sriov_vf(adev))
-		return 0;
-
 	if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
+
 		r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
 		if (r)
 			return r;
-		gfx_v10_0_init_pg(adev);
 
-		/* enable RLC SRM */
-		gfx_v10_0_rlc_enable_srm(adev);
+		gfx_v10_0_init_csb(adev);
 
+		if (!amdgpu_sriov_vf(adev)) /* enable RLC SRM */
+			gfx_v10_0_rlc_enable_srm(adev);
 	} else {
 		adev->gfx.rlc.funcs->stop(adev);
 
@@ -1906,7 +1891,8 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
 				return r;
 		}
 
-		gfx_v10_0_init_pg(adev);
+		gfx_v10_0_init_csb(adev);
+
 		adev->gfx.rlc.funcs->start(adev);
 
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_RLC_BACKDOOR_AUTO) {
@@ -2373,7 +2359,7 @@ static int gfx_v10_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev)
 	return 0;
 }
 
-static void gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
+static int gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
 {
 	int i;
 	u32 tmp = RREG32_SOC15(GC, 0, mmCP_ME_CNTL);
@@ -2386,7 +2372,17 @@ static void gfx_v10_0_cp_gfx_enable(struct amdgpu_device *adev, bool enable)
 			adev->gfx.gfx_ring[i].sched.ready = false;
 	}
 	WREG32_SOC15(GC, 0, mmCP_ME_CNTL, tmp);
-	udelay(50);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		if (RREG32_SOC15(GC, 0, mmCP_STAT) == 0)
+			break;
+		udelay(1);
+	}
+
+	if (i >= adev->usec_timeout)
+		DRM_ERROR("failed to %s cp gfx\n", enable ? "unhalt" : "halt");
+
+	return 0;
 }
 
 static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
@@ -2443,7 +2439,7 @@ static int gfx_v10_0_cp_gfx_load_pfp_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->nbio_funcs->hdp_flush(adev, NULL);
+		adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_PFP_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_PFP_IC_BASE_CNTL, VMID, 0);
@@ -2513,7 +2509,7 @@ static int gfx_v10_0_cp_gfx_load_ce_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->nbio_funcs->hdp_flush(adev, NULL);
+		adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_CE_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CE_IC_BASE_CNTL, VMID, 0);
@@ -2582,7 +2578,7 @@ static int gfx_v10_0_cp_gfx_load_me_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->nbio_funcs->hdp_flush(adev, NULL);
+		adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_ME_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_ME_IC_BASE_CNTL, VMID, 0);
@@ -2757,7 +2753,7 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	/* Init gfx ring 0 for pipe 0 */
 	mutex_lock(&adev->srbm_mutex);
 	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0);
-	mutex_unlock(&adev->srbm_mutex);
+
 	/* Set ring buffer size */
 	ring = &adev->gfx.gfx_ring[0];
 	rb_bufsz = order_base_2(ring->ring_size / 8);
@@ -2795,11 +2791,11 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB_ACTIVE, 1);
 
 	gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+	mutex_unlock(&adev->srbm_mutex);
 
 	/* Init gfx ring 1 for pipe 1 */
 	mutex_lock(&adev->srbm_mutex);
 	gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
-	mutex_unlock(&adev->srbm_mutex);
 	ring = &adev->gfx.gfx_ring[1];
 	rb_bufsz = order_base_2(ring->ring_size / 8);
 	tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
@@ -2829,6 +2825,7 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
 
 	gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+	mutex_unlock(&adev->srbm_mutex);
 
 	/* Switch to pipe 0 */
 	mutex_lock(&adev->srbm_mutex);
@@ -2903,7 +2900,7 @@ static int gfx_v10_0_cp_compute_load_microcode(struct amdgpu_device *adev)
 	}
 
 	if (amdgpu_emu_mode == 1)
-		adev->nbio_funcs->hdp_flush(adev, NULL);
+		adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	tmp = RREG32_SOC15(GC, 0, mmCP_CPC_IC_BASE_CNTL);
 	tmp = REG_SET_FIELD(tmp, CP_CPC_IC_BASE_CNTL, CACHE_POLICY, 0);
@@ -3087,6 +3084,7 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct v10_gfx_mqd *mqd = ring->mqd_ptr;
+	int mqd_idx = ring - &adev->gfx.gfx_ring[0];
 
 	if (!adev->in_gpu_reset && !adev->in_suspend) {
 		memset((void *)mqd, 0, sizeof(*mqd));
@@ -3098,14 +3096,15 @@ static int gfx_v10_0_gfx_init_queue(struct amdgpu_ring *ring)
 #endif
 		nv_grbm_select(adev, 0, 0, 0, 0);
 		mutex_unlock(&adev->srbm_mutex);
-		if (adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS])
-			memcpy(adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS], mqd, sizeof(*mqd));
+		if (adev->gfx.me.mqd_backup[mqd_idx])
+			memcpy(adev->gfx.me.mqd_backup[mqd_idx], mqd, sizeof(*mqd));
 	} else if (adev->in_gpu_reset) {
 		/* reset mqd with the backup copy */
-		if (adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS])
-			memcpy(mqd, adev->gfx.me.mqd_backup[AMDGPU_MAX_GFX_RINGS], sizeof(*mqd));
+		if (adev->gfx.me.mqd_backup[mqd_idx])
+			memcpy(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
+		adev->wb.wb[ring->wptr_offs] = 0;
 		amdgpu_ring_clear_ring(ring);
 #ifdef BRING_UP_DEBUG
 		mutex_lock(&adev->srbm_mutex);
@@ -3705,10 +3704,6 @@ static int gfx_v10_0_hw_init(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = gfx_v10_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	if (!amdgpu_emu_mode)
 		gfx_v10_0_init_golden_registers(adev);
 
@@ -3791,12 +3786,11 @@ static int gfx_v10_0_hw_fini(void *handle)
 	if (amdgpu_gfx_disable_kcq(adev))
 		DRM_ERROR("KCQ disable failed\n");
 	if (amdgpu_sriov_vf(adev)) {
-		pr_debug("For SRIOV client, shouldn't do anything.\n");
+		gfx_v10_0_cp_gfx_enable(adev, false);
 		return 0;
 	}
 	gfx_v10_0_cp_enable(adev, false);
 	gfx_v10_0_enable_gui_idle_interrupt(adev, false);
-	gfx_v10_0_csb_vram_unpin(adev);
 
 	return 0;
 }
@@ -4357,7 +4351,7 @@ static void gfx_v10_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 ref_and_mask, reg_mem_engine;
-	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
+	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
 
 	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
 		switch (ring->me) {
@@ -4377,8 +4371,8 @@ static void gfx_v10_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	}
 
 	gfx_v10_0_wait_reg_mem(ring, reg_mem_engine, 0, 1,
-			       adev->nbio_funcs->get_hdp_flush_req_offset(adev),
-			       adev->nbio_funcs->get_hdp_flush_done_offset(adev),
+			       adev->nbio.funcs->get_hdp_flush_req_offset(adev),
+			       adev->nbio.funcs->get_hdp_flush_done_offset(adev),
 			       ref_and_mask, ref_and_mask, 0x20);
 }
 
@@ -4765,6 +4759,24 @@ static void gfx_v10_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 	gfx_v10_0_wait_reg_mem(ring, 0, 0, 0, reg, 0, val, mask, 0x20);
 }
 
+static void gfx_v10_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+						   uint32_t reg0, uint32_t reg1,
+						   uint32_t ref, uint32_t mask)
+{
+	int usepfp = (ring->funcs->type == AMDGPU_RING_TYPE_GFX);
+	struct amdgpu_device *adev = ring->adev;
+	bool fw_version_ok = false;
+
+	fw_version_ok = adev->gfx.cp_fw_write_wait;
+
+	if (fw_version_ok)
+		gfx_v10_0_wait_reg_mem(ring, usepfp, 0, 1, reg0, reg1,
+				       ref, mask, 0x20);
+	else
+		amdgpu_ring_emit_reg_write_reg_wait_helper(ring, reg0, reg1,
+							   ref, mask);
+}
+
 static void
 gfx_v10_0_set_gfx_eop_interrupt_state(struct amdgpu_device *adev,
 				      uint32_t me, uint32_t pipe,
@@ -5155,6 +5167,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_gfx = {
 	.emit_tmz = gfx_v10_0_ring_emit_tmz,
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
@@ -5188,6 +5201,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_compute = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
 };
 
 static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
@@ -5218,6 +5232,7 @@ static const struct amdgpu_ring_funcs gfx_v10_0_ring_funcs_kiq = {
 	.emit_rreg = gfx_v10_0_ring_emit_rreg,
 	.emit_wreg = gfx_v10_0_ring_emit_wreg,
 	.emit_reg_wait = gfx_v10_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = gfx_v10_0_ring_emit_reg_write_reg_wait,
 };
 
 static void gfx_v10_0_set_ring_funcs(struct amdgpu_device *adev)
@@ -5283,15 +5298,12 @@ static void gfx_v10_0_set_rlc_funcs(struct amdgpu_device *adev)
 
 static void gfx_v10_0_set_gds_init(struct amdgpu_device *adev)
 {
-	/* init asic gds info */
-	switch (adev->asic_type) {
-	case CHIP_NAVI10:
-	default:
-		adev->gds.gds_size = 0x10000;
-		adev->gds.gds_compute_max_wave_id = 0x4ff;
-		break;
-	}
+	unsigned total_cu = adev->gfx.config.max_cu_per_sh *
+			    adev->gfx.config.max_sh_per_se *
+			    adev->gfx.config.max_shader_engines;
 
+	adev->gds.gds_size = 0x10000;
+	adev->gds.gds_compute_max_wave_id = total_cu * 32 - 1;
 	adev->gds.gws_size = 64;
 	adev->gds.oa_size = 16;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 791ba398f007..d92e92e5d50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4554,6 +4554,8 @@ static int gfx_v7_0_hw_init(void *handle)
 
 	gfx_v7_0_constants_init(adev);
 
+	/* init CSB */
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* init rlc */
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 87dd55e9d72b..983db77999e7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -1321,39 +1321,6 @@ static int gfx_v8_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v8_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_v8_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_v8_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -2103,7 +2070,7 @@ static int gfx_v8_0_sw_fini(void *handle)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
 	amdgpu_gfx_mqd_sw_fini(adev);
-	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
+	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring);
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v8_0_mec_fini(adev);
@@ -3917,6 +3884,7 @@ static void gfx_v8_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 
 static void gfx_v8_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* csib */
 	WREG32(mmRLC_CSIB_ADDR_HI,
 			adev->gfx.rlc.clear_state_gpu_addr >> 32);
@@ -4837,10 +4805,6 @@ static int gfx_v8_0_hw_init(void *handle)
 	gfx_v8_0_init_golden_registers(adev);
 	gfx_v8_0_constants_init(adev);
 
-	r = gfx_v8_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -4958,8 +4922,6 @@ static int gfx_v8_0_hw_fini(void *handle)
 		pr_err("rlc is busy, skip halt rlc\n");
 	amdgpu_gfx_rlc_exit_safe_mode(adev);
 
-	gfx_v8_0_csb_vram_unpin(adev);
-
 	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 dcadc73bffd2..66328ffa395a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -131,6 +131,18 @@ MODULE_FIRMWARE("amdgpu/renoir_rlc.bin");
 #define mmTCP_CHAN_STEER_5_ARCT								0x0b0c
 #define mmTCP_CHAN_STEER_5_ARCT_BASE_IDX							0
 
+struct ras_gfx_subblock_reg {
+	const char *name;
+	uint32_t hwip;
+	uint32_t inst;
+	uint32_t seg;
+	uint32_t reg_offset;
+	uint32_t sec_count_mask;
+	uint32_t sec_count_shift;
+	uint32_t ded_count_mask;
+	uint32_t ded_count_shift;
+};
+
 enum ta_ras_gfx_subblock {
 	/*CPC*/
 	TA_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
@@ -517,9 +529,9 @@ static const struct soc15_reg_golden golden_settings_gc_9_0[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0xb5d3f197),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION, 0x3fff3af3, 0x19200000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000003ff),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000000, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000000, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000, 0x00008000)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00008000, 0x00008000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
@@ -582,9 +594,9 @@ static const struct soc15_reg_golden golden_settings_gc_9_1[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_CACHE_INVALIDATION, 0x3fff3af3, 0x19200000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmVGT_GS_MAX_WAVE_ID, 0x00000fff, 0x000000ff),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000000, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000000, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000, 0x00008000)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00008000, 0x00008000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_1_rv1[] =
@@ -676,9 +688,9 @@ static const struct soc15_reg_golden golden_settings_gc_9_2_1_vg12[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_HI, 0xffffffff, 0x00000000),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_LO, 0xffffffff, 0x76325410),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x01bd9f33, 0x01000000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000000, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000000, 0x00000800),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00000000, 0x00008000)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC1_F32_INT_DIS, 0x00000800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_MEC2_F32_INT_DIS, 0x00000800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCP_DEBUG, 0x00008000, 0x00008000)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] =
@@ -691,6 +703,8 @@ static const struct soc15_reg_golden golden_settings_gc_9_4_1_arct[] =
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_3_ARCT, 0x3fffffff, 0x2ebd9fe3),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_4_ARCT, 0x3fffffff, 0xb90f5b1),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTCP_CHAN_STEER_5_ARCT, 0x3ff, 0x135),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_CONFIG, 0xffffffff, 0x011A0000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSQ_FIFO_SIZES, 0xffffffff, 0x00000f00),
 };
 
 static const u32 GFX_RLC_SRM_INDEX_CNTL_ADDR_OFFSETS[] =
@@ -973,6 +987,13 @@ static void gfx_v9_0_check_fw_write_wait(struct amdgpu_device *adev)
 	adev->gfx.me_fw_write_wait = false;
 	adev->gfx.mec_fw_write_wait = false;
 
+	if ((adev->gfx.mec_fw_version < 0x000001a5) ||
+	    (adev->gfx.mec_feature_version < 46) ||
+	    (adev->gfx.pfp_fw_version < 0x000000b7) ||
+	    (adev->gfx.pfp_feature_version < 46))
+		DRM_WARN_ONCE("Warning: check cp_fw_version and update it to realize \
+			      GRBM requires 1-cycle delay in cp firmware\n");
+
 	switch (adev->asic_type) {
 	case CHIP_VEGA10:
 		if ((adev->gfx.me_fw_version >= 0x0000009c) &&
@@ -1031,8 +1052,13 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 	case CHIP_VEGA20:
 		break;
 	case CHIP_RAVEN:
-		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
-			&&((adev->gfx.rlc_fw_version != 106 &&
+		/* Disable GFXOFF on original raven.  There are combinations
+		 * of sbios and platforms that are not stable.
+		 */
+		if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8))
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		else if (!(adev->rev_id >= 0x8 || adev->pdev->device == 0x15d8)
+			 &&((adev->gfx.rlc_fw_version != 106 &&
 			     adev->gfx.rlc_fw_version < 531) ||
 			    (adev->gfx.rlc_fw_version == 53815) ||
 			    (adev->gfx.rlc_feature_version < 1) ||
@@ -1044,6 +1070,12 @@ static void gfx_v9_0_check_if_need_gfxoff(struct amdgpu_device *adev)
 				AMD_PG_SUPPORT_CP |
 				AMD_PG_SUPPORT_RLC_SMU_HS;
 		break;
+	case CHIP_RENOIR:
+		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
+			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
+				AMD_PG_SUPPORT_CP |
+				AMD_PG_SUPPORT_RLC_SMU_HS;
+		break;
 	default:
 		break;
 	}
@@ -1324,7 +1356,8 @@ static int gfx_v9_0_init_cp_compute_microcode(struct amdgpu_device *adev,
 
 			/* TODO: Determine if MEC2 JT FW loading can be removed
 				 for all GFX V9 asic and above */
-			if (adev->asic_type != CHIP_ARCTURUS) {
+			if (adev->asic_type != CHIP_ARCTURUS &&
+			    adev->asic_type != CHIP_RENOIR) {
 				info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC2_JT];
 				info->ucode_id = AMDGPU_UCODE_ID_CP_MEC2_JT;
 				info->fw = adev->gfx.mec2_fw;
@@ -1662,39 +1695,6 @@ 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);
@@ -1956,190 +1956,6 @@ static int gfx_v9_0_gpu_early_init(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gfx_v9_0_ngg_create_buf(struct amdgpu_device *adev,
-				   struct amdgpu_ngg_buf *ngg_buf,
-				   int size_se,
-				   int default_size_se)
-{
-	int r;
-
-	if (size_se < 0) {
-		dev_err(adev->dev, "Buffer size is invalid: %d\n", size_se);
-		return -EINVAL;
-	}
-	size_se = size_se ? size_se : default_size_se;
-
-	ngg_buf->size = size_se * adev->gfx.config.max_shader_engines;
-	r = amdgpu_bo_create_kernel(adev, ngg_buf->size,
-				    PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM,
-				    &ngg_buf->bo,
-				    &ngg_buf->gpu_addr,
-				    NULL);
-	if (r) {
-		dev_err(adev->dev, "(%d) failed to create NGG buffer\n", r);
-		return r;
-	}
-	ngg_buf->bo_size = amdgpu_bo_size(ngg_buf->bo);
-
-	return r;
-}
-
-static int gfx_v9_0_ngg_fini(struct amdgpu_device *adev)
-{
-	int i;
-
-	for (i = 0; i < NGG_BUF_MAX; i++)
-		amdgpu_bo_free_kernel(&adev->gfx.ngg.buf[i].bo,
-				      &adev->gfx.ngg.buf[i].gpu_addr,
-				      NULL);
-
-	memset(&adev->gfx.ngg.buf[0], 0,
-			sizeof(struct amdgpu_ngg_buf) * NGG_BUF_MAX);
-
-	adev->gfx.ngg.init = false;
-
-	return 0;
-}
-
-static int gfx_v9_0_ngg_init(struct amdgpu_device *adev)
-{
-	int r;
-
-	if (!amdgpu_ngg || adev->gfx.ngg.init == true)
-		return 0;
-
-	/* GDS reserve memory: 64 bytes alignment */
-	adev->gfx.ngg.gds_reserve_size = ALIGN(5 * 4, 0x40);
-	adev->gds.gds_size -= adev->gfx.ngg.gds_reserve_size;
-	adev->gfx.ngg.gds_reserve_addr = RREG32_SOC15(GC, 0, mmGDS_VMID0_BASE);
-	adev->gfx.ngg.gds_reserve_addr += RREG32_SOC15(GC, 0, mmGDS_VMID0_SIZE);
-
-	/* Primitive Buffer */
-	r = gfx_v9_0_ngg_create_buf(adev, &adev->gfx.ngg.buf[NGG_PRIM],
-				    amdgpu_prim_buf_per_se,
-				    64 * 1024);
-	if (r) {
-		dev_err(adev->dev, "Failed to create Primitive Buffer\n");
-		goto err;
-	}
-
-	/* Position Buffer */
-	r = gfx_v9_0_ngg_create_buf(adev, &adev->gfx.ngg.buf[NGG_POS],
-				    amdgpu_pos_buf_per_se,
-				    256 * 1024);
-	if (r) {
-		dev_err(adev->dev, "Failed to create Position Buffer\n");
-		goto err;
-	}
-
-	/* Control Sideband */
-	r = gfx_v9_0_ngg_create_buf(adev, &adev->gfx.ngg.buf[NGG_CNTL],
-				    amdgpu_cntl_sb_buf_per_se,
-				    256);
-	if (r) {
-		dev_err(adev->dev, "Failed to create Control Sideband Buffer\n");
-		goto err;
-	}
-
-	/* Parameter Cache, not created by default */
-	if (amdgpu_param_buf_per_se <= 0)
-		goto out;
-
-	r = gfx_v9_0_ngg_create_buf(adev, &adev->gfx.ngg.buf[NGG_PARAM],
-				    amdgpu_param_buf_per_se,
-				    512 * 1024);
-	if (r) {
-		dev_err(adev->dev, "Failed to create Parameter Cache\n");
-		goto err;
-	}
-
-out:
-	adev->gfx.ngg.init = true;
-	return 0;
-err:
-	gfx_v9_0_ngg_fini(adev);
-	return r;
-}
-
-static int gfx_v9_0_ngg_en(struct amdgpu_device *adev)
-{
-	struct amdgpu_ring *ring = &adev->gfx.gfx_ring[0];
-	int r;
-	u32 data, base;
-
-	if (!amdgpu_ngg)
-		return 0;
-
-	/* Program buffer size */
-	data = REG_SET_FIELD(0, WD_BUF_RESOURCE_1, INDEX_BUF_SIZE,
-			     adev->gfx.ngg.buf[NGG_PRIM].size >> 8);
-	data = REG_SET_FIELD(data, WD_BUF_RESOURCE_1, POS_BUF_SIZE,
-			     adev->gfx.ngg.buf[NGG_POS].size >> 8);
-	WREG32_SOC15(GC, 0, mmWD_BUF_RESOURCE_1, data);
-
-	data = REG_SET_FIELD(0, WD_BUF_RESOURCE_2, CNTL_SB_BUF_SIZE,
-			     adev->gfx.ngg.buf[NGG_CNTL].size >> 8);
-	data = REG_SET_FIELD(data, WD_BUF_RESOURCE_2, PARAM_BUF_SIZE,
-			     adev->gfx.ngg.buf[NGG_PARAM].size >> 10);
-	WREG32_SOC15(GC, 0, mmWD_BUF_RESOURCE_2, data);
-
-	/* Program buffer base address */
-	base = lower_32_bits(adev->gfx.ngg.buf[NGG_PRIM].gpu_addr);
-	data = REG_SET_FIELD(0, WD_INDEX_BUF_BASE, BASE, base);
-	WREG32_SOC15(GC, 0, mmWD_INDEX_BUF_BASE, data);
-
-	base = upper_32_bits(adev->gfx.ngg.buf[NGG_PRIM].gpu_addr);
-	data = REG_SET_FIELD(0, WD_INDEX_BUF_BASE_HI, BASE_HI, base);
-	WREG32_SOC15(GC, 0, mmWD_INDEX_BUF_BASE_HI, data);
-
-	base = lower_32_bits(adev->gfx.ngg.buf[NGG_POS].gpu_addr);
-	data = REG_SET_FIELD(0, WD_POS_BUF_BASE, BASE, base);
-	WREG32_SOC15(GC, 0, mmWD_POS_BUF_BASE, data);
-
-	base = upper_32_bits(adev->gfx.ngg.buf[NGG_POS].gpu_addr);
-	data = REG_SET_FIELD(0, WD_POS_BUF_BASE_HI, BASE_HI, base);
-	WREG32_SOC15(GC, 0, mmWD_POS_BUF_BASE_HI, data);
-
-	base = lower_32_bits(adev->gfx.ngg.buf[NGG_CNTL].gpu_addr);
-	data = REG_SET_FIELD(0, WD_CNTL_SB_BUF_BASE, BASE, base);
-	WREG32_SOC15(GC, 0, mmWD_CNTL_SB_BUF_BASE, data);
-
-	base = upper_32_bits(adev->gfx.ngg.buf[NGG_CNTL].gpu_addr);
-	data = REG_SET_FIELD(0, WD_CNTL_SB_BUF_BASE_HI, BASE_HI, base);
-	WREG32_SOC15(GC, 0, mmWD_CNTL_SB_BUF_BASE_HI, data);
-
-	/* Clear GDS reserved memory */
-	r = amdgpu_ring_alloc(ring, 17);
-	if (r) {
-		DRM_ERROR("amdgpu: NGG failed to lock ring %s (%d).\n",
-			  ring->name, r);
-		return r;
-	}
-
-	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE),
-			           (adev->gds.gds_size +
-				    adev->gfx.ngg.gds_reserve_size));
-
-	amdgpu_ring_write(ring, PACKET3(PACKET3_DMA_DATA, 5));
-	amdgpu_ring_write(ring, (PACKET3_DMA_DATA_CP_SYNC |
-				PACKET3_DMA_DATA_DST_SEL(1) |
-				PACKET3_DMA_DATA_SRC_SEL(2)));
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, adev->gfx.ngg.gds_reserve_addr);
-	amdgpu_ring_write(ring, 0);
-	amdgpu_ring_write(ring, PACKET3_DMA_DATA_CMD_RAW_WAIT |
-				adev->gfx.ngg.gds_reserve_size);
-
-	gfx_v9_0_write_data_to_reg(ring, 0, false,
-				   SOC15_REG_OFFSET(GC, 0, mmGDS_VMID0_SIZE), 0);
-
-	amdgpu_ring_commit(ring);
-
-	return 0;
-}
-
 static int gfx_v9_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 				      int mec, int pipe, int queue)
 {
@@ -2307,10 +2123,6 @@ static int gfx_v9_0_sw_init(void *handle)
 	if (r)
 		return r;
 
-	r = gfx_v9_0_ngg_init(adev);
-	if (r)
-		return r;
-
 	return 0;
 }
 
@@ -2320,19 +2132,7 @@ static int gfx_v9_0_sw_fini(void *handle)
 	int i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX) &&
-			adev->gfx.ras_if) {
-		struct ras_common_if *ras_if = adev->gfx.ras_if;
-		struct ras_ih_if ih_info = {
-			.head = *ras_if,
-		};
-
-		amdgpu_ras_debugfs_remove(adev, ras_if);
-		amdgpu_ras_sysfs_remove(adev, ras_if);
-		amdgpu_ras_interrupt_remove_handler(adev,  &ih_info);
-		amdgpu_ras_feature_enable(adev, ras_if, 0);
-		kfree(ras_if);
-	}
+	amdgpu_gfx_ras_fini(adev);
 
 	for (i = 0; i < adev->gfx.num_gfx_rings; i++)
 		amdgpu_ring_fini(&adev->gfx.gfx_ring[i]);
@@ -2340,11 +2140,10 @@ static int gfx_v9_0_sw_fini(void *handle)
 		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
 
 	amdgpu_gfx_mqd_sw_fini(adev);
-	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring, &adev->gfx.kiq.irq);
+	amdgpu_gfx_kiq_free_ring(&adev->gfx.kiq.ring);
 	amdgpu_gfx_kiq_fini(adev);
 
 	gfx_v9_0_mec_fini(adev);
-	gfx_v9_0_ngg_fini(adev);
 	amdgpu_bo_unref(&adev->gfx.rlc.clear_state_obj);
 	if (adev->asic_type == CHIP_RAVEN || adev->asic_type == CHIP_RENOIR) {
 		amdgpu_bo_free_kernel(&adev->gfx.rlc.cp_table_obj,
@@ -2583,6 +2382,7 @@ static void gfx_v9_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
 
 static void gfx_v9_0_init_csb(struct amdgpu_device *adev)
 {
+	adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
 	/* csib */
 	WREG32_RLC(SOC15_REG_OFFSET(GC, 0, mmRLC_CSIB_ADDR_HI),
 			adev->gfx.rlc.clear_state_gpu_addr >> 32);
@@ -2912,7 +2712,10 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 	 * And it's needed by gfxoff feature.
 	 */
 	if (adev->gfx.rlc.is_rlc_v2_1) {
-		gfx_v9_1_init_rlc_save_restore_list(adev);
+		if (adev->asic_type == CHIP_VEGA12 ||
+		    (adev->asic_type == CHIP_RAVEN &&
+		     adev->rev_id >= 8))
+			gfx_v9_1_init_rlc_save_restore_list(adev);
 		gfx_v9_0_enable_save_restore_machine(adev);
 	}
 
@@ -3871,10 +3674,6 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_constants_init(adev);
 
-	r = gfx_v9_0_csb_vram_pin(adev);
-	if (r)
-		return r;
-
 	r = adev->gfx.rlc.funcs->resume(adev);
 	if (r)
 		return r;
@@ -3883,12 +3682,6 @@ static int gfx_v9_0_hw_init(void *handle)
 	if (r)
 		return r;
 
-	if (adev->asic_type != CHIP_ARCTURUS) {
-		r = gfx_v9_0_ngg_en(adev);
-		if (r)
-			return r;
-	}
-
 	return r;
 }
 
@@ -3930,8 +3723,10 @@ static int gfx_v9_0_hw_fini(void *handle)
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
-	/* disable KCQ to avoid CPC touch memory not valid anymore */
-	gfx_v9_0_kcq_disable(adev);
+	/* DF freeze and kcq disable will fail */
+	if (!amdgpu_ras_intr_triggered())
+		/* disable KCQ to avoid CPC touch memory not valid anymore */
+		gfx_v9_0_kcq_disable(adev);
 
 	if (amdgpu_sriov_vf(adev)) {
 		gfx_v9_0_cp_gfx_enable(adev, false);
@@ -3960,8 +3755,6 @@ static int gfx_v9_0_hw_fini(void *handle)
 	gfx_v9_0_cp_enable(adev, false);
 	adev->gfx.rlc.funcs->stop(adev);
 
-	gfx_v9_0_csb_vram_unpin(adev);
-
 	return 0;
 }
 
@@ -4067,9 +3860,22 @@ static uint64_t gfx_v9_0_get_gpu_clock_counter(struct amdgpu_device *adev)
 	uint64_t clock;
 
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
-	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
-	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
-		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
+		uint32_t tmp, lsb, msb, i = 0;
+		do {
+			if (i != 0)
+				udelay(1);
+			tmp = RREG32_SOC15(GC, 0, mmRLC_REFCLOCK_TIMESTAMP_MSB);
+			lsb = RREG32_SOC15(GC, 0, mmRLC_REFCLOCK_TIMESTAMP_LSB);
+			msb = RREG32_SOC15(GC, 0, mmRLC_REFCLOCK_TIMESTAMP_MSB);
+			i++;
+		} while (unlikely(tmp != msb) && (i < adev->usec_timeout));
+		clock = (uint64_t)lsb | ((uint64_t)msb << 32ULL);
+	} else {
+		WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
+		clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
+			((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
+	}
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
 	return clock;
 }
@@ -4184,6 +3990,7 @@ static const struct soc15_reg_entry sec_ded_counter_registers[] = {
    { SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 1, 16},
    { SOC15_REG_ENTRY(GC, 0, mmTCP_ATC_EDC_GATCL1_CNT), 0, 4, 16},
    { SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT), 0, 4, 16},
+   { SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 0, 4, 16},
    { SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT), 0, 4, 16},
    { SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 0, 4, 6},
    { SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 0, 4, 16},
@@ -4203,6 +4010,10 @@ static int gfx_v9_0_do_edc_gds_workarounds(struct amdgpu_device *adev)
 	struct amdgpu_ring *ring = &adev->gfx.compute_ring[0];
 	int i, r;
 
+	/* only support when RAS is enabled */
+	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
+		return 0;
+
 	r = amdgpu_ring_alloc(ring, 7);
 	if (r) {
 		DRM_ERROR("amdgpu: GDS workarounds failed to lock ring %s (%d).\n",
@@ -4393,33 +4204,14 @@ static int gfx_v9_0_early_init(void *handle)
 	return 0;
 }
 
-static int gfx_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
-		struct amdgpu_iv_entry *entry);
-
 static int gfx_v9_0_ecc_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct ras_common_if **ras_if = &adev->gfx.ras_if;
-	struct ras_ih_if ih_info = {
-		.cb = gfx_v9_0_process_ras_data_cb,
-	};
-	struct ras_fs_if fs_info = {
-		.sysfs_name = "gfx_err_count",
-		.debugfs_name = "gfx_err_inject",
-	};
-	struct ras_common_if ras_block = {
-		.block = AMDGPU_RAS_BLOCK__GFX,
-		.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
-		.sub_block_index = 0,
-		.name = "gfx",
-	};
 	int r;
 
-	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX)) {
-		amdgpu_ras_feature_enable_on_boot(adev, &ras_block, 0);
-		return 0;
-	}
+	r = amdgpu_gfx_ras_late_init(adev);
+	if (r)
+		return r;
 
 	r = gfx_v9_0_do_edc_gds_workarounds(adev);
 	if (r)
@@ -4430,72 +4222,7 @@ static int gfx_v9_0_ecc_late_init(void *handle)
 	if (r)
 		return r;
 
-	/* handle resume path. */
-	if (*ras_if) {
-		/* resend ras TA enable cmd during resume.
-		 * prepare to handle failure.
-		 */
-		ih_info.head = **ras_if;
-		r = amdgpu_ras_feature_enable_on_boot(adev, *ras_if, 1);
-		if (r) {
-			if (r == -EAGAIN) {
-				/* request a gpu reset. will run again. */
-				amdgpu_ras_request_reset_on_boot(adev,
-						AMDGPU_RAS_BLOCK__GFX);
-				return 0;
-			}
-			/* fail to enable ras, cleanup all. */
-			goto irq;
-		}
-		/* enable successfully. continue. */
-		goto resume;
-	}
-
-	*ras_if = kmalloc(sizeof(**ras_if), GFP_KERNEL);
-	if (!*ras_if)
-		return -ENOMEM;
-
-	**ras_if = ras_block;
-
-	r = amdgpu_ras_feature_enable_on_boot(adev, *ras_if, 1);
-	if (r) {
-		if (r == -EAGAIN) {
-			amdgpu_ras_request_reset_on_boot(adev,
-					AMDGPU_RAS_BLOCK__GFX);
-			r = 0;
-		}
-		goto feature;
-	}
-
-	ih_info.head = **ras_if;
-	fs_info.head = **ras_if;
-
-	r = amdgpu_ras_interrupt_add_handler(adev, &ih_info);
-	if (r)
-		goto interrupt;
-
-	amdgpu_ras_debugfs_create(adev, &fs_info);
-
-	r = amdgpu_ras_sysfs_create(adev, &fs_info);
-	if (r)
-		goto sysfs;
-resume:
-	r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
-	if (r)
-		goto irq;
-
 	return 0;
-irq:
-	amdgpu_ras_sysfs_remove(adev, *ras_if);
-sysfs:
-	amdgpu_ras_debugfs_remove(adev, *ras_if);
-	amdgpu_ras_interrupt_remove_handler(adev, &ih_info);
-interrupt:
-	amdgpu_ras_feature_enable(adev, *ras_if, 0);
-feature:
-	kfree(*ras_if);
-	*ras_if = NULL;
-	return r;
 }
 
 static int gfx_v9_0_late_init(void *handle)
@@ -4560,16 +4287,14 @@ static void gfx_v9_0_update_gfx_cg_power_gating(struct amdgpu_device *adev,
 {
 	amdgpu_gfx_rlc_enter_safe_mode(adev);
 
-	if (is_support_sw_smu(adev) && !enable)
-		smu_set_gfx_cgpg(&adev->smu, enable);
-
 	if ((adev->pg_flags & AMD_PG_SUPPORT_GFX_PG) && enable) {
 		gfx_v9_0_enable_gfx_cg_power_gating(adev, true);
 		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PIPELINE)
 			gfx_v9_0_enable_gfx_pipeline_powergating(adev, true);
 	} else {
 		gfx_v9_0_enable_gfx_cg_power_gating(adev, false);
-		gfx_v9_0_enable_gfx_pipeline_powergating(adev, false);
+		if (adev->pg_flags & AMD_PG_SUPPORT_GFX_PIPELINE)
+			gfx_v9_0_enable_gfx_pipeline_powergating(adev, false);
 	}
 
 	amdgpu_gfx_rlc_exit_safe_mode(adev);
@@ -4838,8 +4563,6 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 			gfx_v9_0_enable_cp_power_gating(adev, false);
 
 		/* update gfx cgpg state */
-		if (is_support_sw_smu(adev) && enable)
-			smu_set_gfx_cgpg(&adev->smu, enable);
 		gfx_v9_0_update_gfx_cg_power_gating(adev, enable);
 
 		/* update mgcg state */
@@ -4970,7 +4693,7 @@ static void gfx_v9_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 ref_and_mask, reg_mem_engine;
-	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
+	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
 
 	if (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE) {
 		switch (ring->me) {
@@ -4990,8 +4713,8 @@ static void gfx_v9_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	}
 
 	gfx_v9_0_wait_reg_mem(ring, reg_mem_engine, 0, 1,
-			      adev->nbio_funcs->get_hdp_flush_req_offset(adev),
-			      adev->nbio_funcs->get_hdp_flush_done_offset(adev),
+			      adev->nbio.funcs->get_hdp_flush_req_offset(adev),
+			      adev->nbio.funcs->get_hdp_flush_done_offset(adev),
 			      ref_and_mask, ref_and_mask, 0x20);
 }
 
@@ -5723,313 +5446,446 @@ static int gfx_v9_0_priv_inst_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int gfx_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
-		struct amdgpu_iv_entry *entry)
-{
-	/* TODO ue will trigger an interrupt. */
-	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
-	if (adev->gfx.funcs->query_ras_error_count)
-		adev->gfx.funcs->query_ras_error_count(adev, err_data);
-	amdgpu_ras_reset_gpu(adev, 0);
-	return AMDGPU_RAS_SUCCESS;
-}
 
-static const struct {
-	const char *name;
-	uint32_t ip;
-	uint32_t inst;
-	uint32_t seg;
-	uint32_t reg_offset;
-	uint32_t per_se_instance;
-	int32_t num_instance;
-	uint32_t sec_count_mask;
-	uint32_t ded_count_mask;
-} gfx_ras_edc_regs[] = {
-	{ "CPC_SCRATCH", SOC15_REG_ENTRY(GC, 0, mmCPC_EDC_SCRATCH_CNT), 0, 1,
-	  REG_FIELD_MASK(CPC_EDC_SCRATCH_CNT, SEC_COUNT),
-	  REG_FIELD_MASK(CPC_EDC_SCRATCH_CNT, DED_COUNT) },
-	{ "CPC_UCODE", SOC15_REG_ENTRY(GC, 0, mmCPC_EDC_UCODE_CNT), 0, 1,
-	  REG_FIELD_MASK(CPC_EDC_UCODE_CNT, SEC_COUNT),
-	  REG_FIELD_MASK(CPC_EDC_UCODE_CNT, DED_COUNT) },
-	{ "CPF_ROQ_ME1", SOC15_REG_ENTRY(GC, 0, mmCPF_EDC_ROQ_CNT), 0, 1,
-	  REG_FIELD_MASK(CPF_EDC_ROQ_CNT, COUNT_ME1), 0 },
-	{ "CPF_ROQ_ME2", SOC15_REG_ENTRY(GC, 0, mmCPF_EDC_ROQ_CNT), 0, 1,
-	  REG_FIELD_MASK(CPF_EDC_ROQ_CNT, COUNT_ME2), 0 },
-	{ "CPF_TAG", SOC15_REG_ENTRY(GC, 0, mmCPF_EDC_TAG_CNT), 0, 1,
-	  REG_FIELD_MASK(CPF_EDC_TAG_CNT, SEC_COUNT),
-	  REG_FIELD_MASK(CPF_EDC_TAG_CNT, DED_COUNT) },
-	{ "CPG_DMA_ROQ", SOC15_REG_ENTRY(GC, 0, mmCPG_EDC_DMA_CNT), 0, 1,
-	  REG_FIELD_MASK(CPG_EDC_DMA_CNT, ROQ_COUNT), 0 },
-	{ "CPG_DMA_TAG", SOC15_REG_ENTRY(GC, 0, mmCPG_EDC_DMA_CNT), 0, 1,
-	  REG_FIELD_MASK(CPG_EDC_DMA_CNT, TAG_SEC_COUNT),
-	  REG_FIELD_MASK(CPG_EDC_DMA_CNT, TAG_DED_COUNT) },
-	{ "CPG_TAG", SOC15_REG_ENTRY(GC, 0, mmCPG_EDC_TAG_CNT), 0, 1,
-	  REG_FIELD_MASK(CPG_EDC_TAG_CNT, SEC_COUNT),
-	  REG_FIELD_MASK(CPG_EDC_TAG_CNT, DED_COUNT) },
-	{ "DC_CSINVOC", SOC15_REG_ENTRY(GC, 0, mmDC_EDC_CSINVOC_CNT), 0, 1,
-	  REG_FIELD_MASK(DC_EDC_CSINVOC_CNT, COUNT_ME1), 0 },
-	{ "DC_RESTORE", SOC15_REG_ENTRY(GC, 0, mmDC_EDC_RESTORE_CNT), 0, 1,
-	  REG_FIELD_MASK(DC_EDC_RESTORE_CNT, COUNT_ME1), 0 },
-	{ "DC_STATE", SOC15_REG_ENTRY(GC, 0, mmDC_EDC_STATE_CNT), 0, 1,
-	  REG_FIELD_MASK(DC_EDC_STATE_CNT, COUNT_ME1), 0 },
-	{ "GDS_MEM", SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_CNT, GDS_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_CNT, GDS_MEM_DED) },
-	{ "GDS_INPUT_QUEUE", SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_CNT, GDS_INPUT_QUEUE_SED), 0 },
+static const struct ras_gfx_subblock_reg ras_subblock_regs[] = {
+	{ "CPC_SCRATCH", SOC15_REG_ENTRY(GC, 0, mmCPC_EDC_SCRATCH_CNT),
+	  SOC15_REG_FIELD(CPC_EDC_SCRATCH_CNT, SEC_COUNT),
+	  SOC15_REG_FIELD(CPC_EDC_SCRATCH_CNT, DED_COUNT)
+	},
+	{ "CPC_UCODE", SOC15_REG_ENTRY(GC, 0, mmCPC_EDC_UCODE_CNT),
+	  SOC15_REG_FIELD(CPC_EDC_UCODE_CNT, SEC_COUNT),
+	  SOC15_REG_FIELD(CPC_EDC_UCODE_CNT, DED_COUNT)
+	},
+	{ "CPF_ROQ_ME1", SOC15_REG_ENTRY(GC, 0, mmCPF_EDC_ROQ_CNT),
+	  SOC15_REG_FIELD(CPF_EDC_ROQ_CNT, COUNT_ME1),
+	  0, 0
+	},
+	{ "CPF_ROQ_ME2", SOC15_REG_ENTRY(GC, 0, mmCPF_EDC_ROQ_CNT),
+	  SOC15_REG_FIELD(CPF_EDC_ROQ_CNT, COUNT_ME2),
+	  0, 0
+	},
+	{ "CPF_TAG", SOC15_REG_ENTRY(GC, 0, mmCPF_EDC_TAG_CNT),
+	  SOC15_REG_FIELD(CPF_EDC_TAG_CNT, SEC_COUNT),
+	  SOC15_REG_FIELD(CPF_EDC_TAG_CNT, DED_COUNT)
+	},
+	{ "CPG_DMA_ROQ", SOC15_REG_ENTRY(GC, 0, mmCPG_EDC_DMA_CNT),
+	  SOC15_REG_FIELD(CPG_EDC_DMA_CNT, ROQ_COUNT),
+	  0, 0
+	},
+	{ "CPG_DMA_TAG", SOC15_REG_ENTRY(GC, 0, mmCPG_EDC_DMA_CNT),
+	  SOC15_REG_FIELD(CPG_EDC_DMA_CNT, TAG_SEC_COUNT),
+	  SOC15_REG_FIELD(CPG_EDC_DMA_CNT, TAG_DED_COUNT)
+	},
+	{ "CPG_TAG", SOC15_REG_ENTRY(GC, 0, mmCPG_EDC_TAG_CNT),
+	  SOC15_REG_FIELD(CPG_EDC_TAG_CNT, SEC_COUNT),
+	  SOC15_REG_FIELD(CPG_EDC_TAG_CNT, DED_COUNT)
+	},
+	{ "DC_CSINVOC", SOC15_REG_ENTRY(GC, 0, mmDC_EDC_CSINVOC_CNT),
+	  SOC15_REG_FIELD(DC_EDC_CSINVOC_CNT, COUNT_ME1),
+	  0, 0
+	},
+	{ "DC_RESTORE", SOC15_REG_ENTRY(GC, 0, mmDC_EDC_RESTORE_CNT),
+	  SOC15_REG_FIELD(DC_EDC_RESTORE_CNT, COUNT_ME1),
+	  0, 0
+	},
+	{ "DC_STATE", SOC15_REG_ENTRY(GC, 0, mmDC_EDC_STATE_CNT),
+	  SOC15_REG_FIELD(DC_EDC_STATE_CNT, COUNT_ME1),
+	  0, 0
+	},
+	{ "GDS_MEM", SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_CNT, GDS_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_CNT, GDS_MEM_DED)
+	},
+	{ "GDS_INPUT_QUEUE", SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_CNT, GDS_INPUT_QUEUE_SED),
+	  0, 0
+	},
 	{ "GDS_ME0_CS_PIPE_MEM", SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PHY_CNT),
-	  0, 1, REG_FIELD_MASK(GDS_EDC_OA_PHY_CNT, ME0_CS_PIPE_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_OA_PHY_CNT, ME0_CS_PIPE_MEM_DED) },
+	  SOC15_REG_FIELD(GDS_EDC_OA_PHY_CNT, ME0_CS_PIPE_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PHY_CNT, ME0_CS_PIPE_MEM_DED)
+	},
 	{ "GDS_OA_PHY_PHY_CMD_RAM_MEM",
-	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PHY_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_OA_PHY_CNT, PHY_CMD_RAM_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_OA_PHY_CNT, PHY_CMD_RAM_MEM_DED) },
+	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PHY_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PHY_CNT, PHY_CMD_RAM_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PHY_CNT, PHY_CMD_RAM_MEM_DED)
+	},
 	{ "GDS_OA_PHY_PHY_DATA_RAM_MEM",
-	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PHY_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_OA_PHY_CNT, PHY_DATA_RAM_MEM_SED), 0 },
+	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PHY_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PHY_CNT, PHY_DATA_RAM_MEM_SED),
+	  0, 0
+	},
 	{ "GDS_OA_PIPE_ME1_PIPE0_PIPE_MEM",
-	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE0_PIPE_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE0_PIPE_MEM_DED) },
+	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE0_PIPE_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE0_PIPE_MEM_DED)
+	},
 	{ "GDS_OA_PIPE_ME1_PIPE1_PIPE_MEM",
-	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE1_PIPE_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE1_PIPE_MEM_DED) },
+	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE1_PIPE_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE1_PIPE_MEM_DED)
+	},
 	{ "GDS_OA_PIPE_ME1_PIPE2_PIPE_MEM",
-	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE2_PIPE_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE2_PIPE_MEM_DED) },
+	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE2_PIPE_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE2_PIPE_MEM_DED)
+	},
 	{ "GDS_OA_PIPE_ME1_PIPE3_PIPE_MEM",
-	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT), 0, 1,
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE3_PIPE_MEM_SEC),
-	  REG_FIELD_MASK(GDS_EDC_OA_PIPE_CNT, ME1_PIPE3_PIPE_MEM_DED) },
-	{ "SPI_SR_MEM", SOC15_REG_ENTRY(GC, 0, mmSPI_EDC_CNT), 1, 1,
-	  REG_FIELD_MASK(SPI_EDC_CNT, SPI_SR_MEM_SED_COUNT), 0 },
-	{ "TA_FS_DFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TA_EDC_CNT, TA_FS_DFIFO_SEC_COUNT),
-	  REG_FIELD_MASK(TA_EDC_CNT, TA_FS_DFIFO_DED_COUNT) },
-	{ "TA_FS_AFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TA_EDC_CNT, TA_FS_AFIFO_SED_COUNT), 0 },
-	{ "TA_FL_LFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TA_EDC_CNT, TA_FL_LFIFO_SED_COUNT), 0 },
-	{ "TA_FX_LFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TA_EDC_CNT, TA_FX_LFIFO_SED_COUNT), 0 },
-	{ "TA_FS_CFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TA_EDC_CNT, TA_FS_CFIFO_SED_COUNT), 0 },
-	{ "TCA_HOLE_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT), 0, 2,
-	  REG_FIELD_MASK(TCA_EDC_CNT, HOLE_FIFO_SED_COUNT), 0 },
-	{ "TCA_REQ_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT), 0, 2,
-	  REG_FIELD_MASK(TCA_EDC_CNT, REQ_FIFO_SED_COUNT), 0 },
-	{ "TCC_CACHE_DATA", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, CACHE_DATA_SEC_COUNT),
-	  REG_FIELD_MASK(TCC_EDC_CNT, CACHE_DATA_DED_COUNT) },
-	{ "TCC_CACHE_DIRTY", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, CACHE_DIRTY_SEC_COUNT),
-	  REG_FIELD_MASK(TCC_EDC_CNT, CACHE_DIRTY_DED_COUNT) },
-	{ "TCC_HIGH_RATE_TAG", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, HIGH_RATE_TAG_SEC_COUNT),
-	  REG_FIELD_MASK(TCC_EDC_CNT, HIGH_RATE_TAG_DED_COUNT) },
-	{ "TCC_LOW_RATE_TAG", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, LOW_RATE_TAG_SEC_COUNT),
-	  REG_FIELD_MASK(TCC_EDC_CNT, LOW_RATE_TAG_DED_COUNT) },
-	{ "TCC_SRC_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, SRC_FIFO_SEC_COUNT),
-	  REG_FIELD_MASK(TCC_EDC_CNT, SRC_FIFO_DED_COUNT) },
-	{ "TCC_IN_USE_DEC", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, IN_USE_DEC_SED_COUNT), 0 },
-	{ "TCC_IN_USE_TRANSFER", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, IN_USE_TRANSFER_SED_COUNT), 0 },
-	{ "TCC_LATENCY_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, LATENCY_FIFO_SED_COUNT), 0 },
-	{ "TCC_RETURN_DATA", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, RETURN_DATA_SED_COUNT), 0 },
-	{ "TCC_RETURN_CONTROL", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, RETURN_CONTROL_SED_COUNT), 0 },
-	{ "TCC_UC_ATOMIC_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT, UC_ATOMIC_FIFO_SED_COUNT), 0 },
-	{ "TCC_WRITE_RETURN", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT2, WRITE_RETURN_SED_COUNT), 0 },
-	{ "TCC_WRITE_CACHE_READ", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0, 16,
-	  REG_FIELD_MASK(TCC_EDC_CNT2, WRITE_CACHE_READ_SED_COUNT), 0 },
-	{ "TCC_SRC_FIFO_NEXT_RAM", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0,
-	  16, REG_FIELD_MASK(TCC_EDC_CNT2, SRC_FIFO_NEXT_RAM_SED_COUNT), 0 },
+	  SOC15_REG_ENTRY(GC, 0, mmGDS_EDC_OA_PIPE_CNT),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE3_PIPE_MEM_SEC),
+	  SOC15_REG_FIELD(GDS_EDC_OA_PIPE_CNT, ME1_PIPE3_PIPE_MEM_DED)
+	},
+	{ "SPI_SR_MEM", SOC15_REG_ENTRY(GC, 0, mmSPI_EDC_CNT),
+	  SOC15_REG_FIELD(SPI_EDC_CNT, SPI_SR_MEM_SED_COUNT),
+	  0, 0
+	},
+	{ "TA_FS_DFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT),
+	  SOC15_REG_FIELD(TA_EDC_CNT, TA_FS_DFIFO_SEC_COUNT),
+	  SOC15_REG_FIELD(TA_EDC_CNT, TA_FS_DFIFO_DED_COUNT)
+	},
+	{ "TA_FS_AFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT),
+	  SOC15_REG_FIELD(TA_EDC_CNT, TA_FS_AFIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TA_FL_LFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT),
+	  SOC15_REG_FIELD(TA_EDC_CNT, TA_FL_LFIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TA_FX_LFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT),
+	  SOC15_REG_FIELD(TA_EDC_CNT, TA_FX_LFIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TA_FS_CFIFO", SOC15_REG_ENTRY(GC, 0, mmTA_EDC_CNT),
+	  SOC15_REG_FIELD(TA_EDC_CNT, TA_FS_CFIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TCA_HOLE_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT),
+	  SOC15_REG_FIELD(TCA_EDC_CNT, HOLE_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TCA_REQ_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCA_EDC_CNT),
+	  SOC15_REG_FIELD(TCA_EDC_CNT, REQ_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_CACHE_DATA", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, CACHE_DATA_SEC_COUNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, CACHE_DATA_DED_COUNT)
+	},
+	{ "TCC_CACHE_DIRTY", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, CACHE_DIRTY_SEC_COUNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, CACHE_DIRTY_DED_COUNT)
+	},
+	{ "TCC_HIGH_RATE_TAG", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, HIGH_RATE_TAG_SEC_COUNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, HIGH_RATE_TAG_DED_COUNT)
+	},
+	{ "TCC_LOW_RATE_TAG", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, LOW_RATE_TAG_SEC_COUNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, LOW_RATE_TAG_DED_COUNT)
+	},
+	{ "TCC_SRC_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, SRC_FIFO_SEC_COUNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, SRC_FIFO_DED_COUNT)
+	},
+	{ "TCC_IN_USE_DEC", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, IN_USE_DEC_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_IN_USE_TRANSFER", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, IN_USE_TRANSFER_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_LATENCY_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, LATENCY_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_RETURN_DATA", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, RETURN_DATA_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_RETURN_CONTROL", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, RETURN_CONTROL_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_UC_ATOMIC_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT),
+	  SOC15_REG_FIELD(TCC_EDC_CNT, UC_ATOMIC_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_WRITE_RETURN", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, WRITE_RETURN_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_WRITE_CACHE_READ", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, WRITE_CACHE_READ_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_SRC_FIFO_NEXT_RAM", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, SRC_FIFO_NEXT_RAM_SED_COUNT),
+	  0, 0
+	},
 	{ "TCC_LATENCY_FIFO_NEXT_RAM", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
-	  0, 16, REG_FIELD_MASK(TCC_EDC_CNT2, LATENCY_FIFO_NEXT_RAM_SED_COUNT),
-	  0 },
-	{ "TCC_CACHE_TAG_PROBE_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0,
-	  16, REG_FIELD_MASK(TCC_EDC_CNT2, CACHE_TAG_PROBE_FIFO_SED_COUNT), 0 },
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, LATENCY_FIFO_NEXT_RAM_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_CACHE_TAG_PROBE_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, CACHE_TAG_PROBE_FIFO_SED_COUNT),
+	  0, 0
+	},
 	{ "TCC_WRRET_TAG_WRITE_RETURN", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
-	  0, 16, REG_FIELD_MASK(TCC_EDC_CNT2, WRRET_TAG_WRITE_RETURN_SED_COUNT),
-	  0 },
-	{ "TCC_ATOMIC_RETURN_BUFFER", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2), 0,
-	  16, REG_FIELD_MASK(TCC_EDC_CNT2, ATOMIC_RETURN_BUFFER_SED_COUNT), 0 },
-	{ "TCI_WRITE_RAM", SOC15_REG_ENTRY(GC, 0, mmTCI_EDC_CNT), 0, 72,
-	  REG_FIELD_MASK(TCI_EDC_CNT, WRITE_RAM_SED_COUNT), 0 },
-	{ "TCP_CACHE_RAM", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, CACHE_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, CACHE_RAM_DED_COUNT) },
-	{ "TCP_LFIFO_RAM", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, LFIFO_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, LFIFO_RAM_DED_COUNT) },
-	{ "TCP_CMD_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, CMD_FIFO_SED_COUNT), 0 },
-	{ "TCP_VM_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, VM_FIFO_SEC_COUNT), 0 },
-	{ "TCP_DB_RAM", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, DB_RAM_SED_COUNT), 0 },
-	{ "TCP_UTCL1_LFIFO0", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, UTCL1_LFIFO0_SEC_COUNT),
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, UTCL1_LFIFO0_DED_COUNT) },
-	{ "TCP_UTCL1_LFIFO1", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW), 1, 16,
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, UTCL1_LFIFO1_SEC_COUNT),
-	  REG_FIELD_MASK(TCP_EDC_CNT_NEW, UTCL1_LFIFO1_DED_COUNT) },
-	{ "TD_SS_FIFO_LO", SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TD_EDC_CNT, SS_FIFO_LO_SEC_COUNT),
-	  REG_FIELD_MASK(TD_EDC_CNT, SS_FIFO_LO_DED_COUNT) },
-	{ "TD_SS_FIFO_HI", SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TD_EDC_CNT, SS_FIFO_HI_SEC_COUNT),
-	  REG_FIELD_MASK(TD_EDC_CNT, SS_FIFO_HI_DED_COUNT) },
-	{ "TD_CS_FIFO", SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(TD_EDC_CNT, CS_FIFO_SED_COUNT), 0 },
-	{ "SQ_LDS_D", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, LDS_D_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, LDS_D_DED_COUNT) },
-	{ "SQ_LDS_I", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, LDS_I_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, LDS_I_DED_COUNT) },
-	{ "SQ_SGPR", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, SGPR_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, SGPR_DED_COUNT) },
-	{ "SQ_VGPR0", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR0_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR0_DED_COUNT) },
-	{ "SQ_VGPR1", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR1_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR1_DED_COUNT) },
-	{ "SQ_VGPR2", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR2_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR2_DED_COUNT) },
-	{ "SQ_VGPR3", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT), 1, 16,
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR3_SEC_COUNT),
-	  REG_FIELD_MASK(SQ_EDC_CNT, VGPR3_DED_COUNT) },
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, WRRET_TAG_WRITE_RETURN_SED_COUNT),
+	  0, 0
+	},
+	{ "TCC_ATOMIC_RETURN_BUFFER", SOC15_REG_ENTRY(GC, 0, mmTCC_EDC_CNT2),
+	  SOC15_REG_FIELD(TCC_EDC_CNT2, ATOMIC_RETURN_BUFFER_SED_COUNT),
+	  0, 0
+	},
+	{ "TCI_WRITE_RAM", SOC15_REG_ENTRY(GC, 0, mmTCI_EDC_CNT),
+	  SOC15_REG_FIELD(TCI_EDC_CNT, WRITE_RAM_SED_COUNT),
+	  0, 0
+	},
+	{ "TCP_CACHE_RAM", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, CACHE_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, CACHE_RAM_DED_COUNT)
+	},
+	{ "TCP_LFIFO_RAM", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, LFIFO_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, LFIFO_RAM_DED_COUNT)
+	},
+	{ "TCP_CMD_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, CMD_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "TCP_VM_FIFO", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, VM_FIFO_SEC_COUNT),
+	  0, 0
+	},
+	{ "TCP_DB_RAM", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, DB_RAM_SED_COUNT),
+	  0, 0
+	},
+	{ "TCP_UTCL1_LFIFO0", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, UTCL1_LFIFO0_SEC_COUNT),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, UTCL1_LFIFO0_DED_COUNT)
+	},
+	{ "TCP_UTCL1_LFIFO1", SOC15_REG_ENTRY(GC, 0, mmTCP_EDC_CNT_NEW),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, UTCL1_LFIFO1_SEC_COUNT),
+	  SOC15_REG_FIELD(TCP_EDC_CNT_NEW, UTCL1_LFIFO1_DED_COUNT)
+	},
+	{ "TD_SS_FIFO_LO", SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT),
+	  SOC15_REG_FIELD(TD_EDC_CNT, SS_FIFO_LO_SEC_COUNT),
+	  SOC15_REG_FIELD(TD_EDC_CNT, SS_FIFO_LO_DED_COUNT)
+	},
+	{ "TD_SS_FIFO_HI", SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT),
+	  SOC15_REG_FIELD(TD_EDC_CNT, SS_FIFO_HI_SEC_COUNT),
+	  SOC15_REG_FIELD(TD_EDC_CNT, SS_FIFO_HI_DED_COUNT)
+	},
+	{ "TD_CS_FIFO", SOC15_REG_ENTRY(GC, 0, mmTD_EDC_CNT),
+	  SOC15_REG_FIELD(TD_EDC_CNT, CS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQ_LDS_D", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, LDS_D_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, LDS_D_DED_COUNT)
+	},
+	{ "SQ_LDS_I", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, LDS_I_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, LDS_I_DED_COUNT)
+	},
+	{ "SQ_SGPR", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, SGPR_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, SGPR_DED_COUNT)
+	},
+	{ "SQ_VGPR0", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR0_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR0_DED_COUNT)
+	},
+	{ "SQ_VGPR1", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR1_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR1_DED_COUNT)
+	},
+	{ "SQ_VGPR2", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR2_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR2_DED_COUNT)
+	},
+	{ "SQ_VGPR3", SOC15_REG_ENTRY(GC, 0, mmSQ_EDC_CNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR3_SEC_COUNT),
+	  SOC15_REG_FIELD(SQ_EDC_CNT, VGPR3_DED_COUNT)
+	},
 	{ "SQC_DATA_CU0_WRITE_DATA_BUF", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT),
-	  1, 6, REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU0_WRITE_DATA_BUF_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU0_WRITE_DATA_BUF_DED_COUNT) },
-	{ "SQC_DATA_CU0_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU0_UTCL1_LFIFO_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU0_UTCL1_LFIFO_DED_COUNT) },
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU0_WRITE_DATA_BUF_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU0_WRITE_DATA_BUF_DED_COUNT)
+	},
+	{ "SQC_DATA_CU0_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU0_UTCL1_LFIFO_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU0_UTCL1_LFIFO_DED_COUNT)
+	},
 	{ "SQC_DATA_CU1_WRITE_DATA_BUF", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT),
-	  1, 6, REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU1_WRITE_DATA_BUF_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU1_WRITE_DATA_BUF_DED_COUNT) },
-	{ "SQC_DATA_CU1_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU1_UTCL1_LFIFO_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU1_UTCL1_LFIFO_DED_COUNT) },
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU1_WRITE_DATA_BUF_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU1_WRITE_DATA_BUF_DED_COUNT)
+	},
+	{ "SQC_DATA_CU1_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU1_UTCL1_LFIFO_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU1_UTCL1_LFIFO_DED_COUNT)
+	},
 	{ "SQC_DATA_CU2_WRITE_DATA_BUF", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT),
-	  1, 6, REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU2_WRITE_DATA_BUF_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU2_WRITE_DATA_BUF_DED_COUNT) },
-	{ "SQC_DATA_CU2_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU2_UTCL1_LFIFO_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT, DATA_CU2_UTCL1_LFIFO_DED_COUNT) },
-	{ "SQC_INST_BANKA_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, INST_BANKA_TAG_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT2, INST_BANKA_TAG_RAM_DED_COUNT) },
-	{ "SQC_INST_BANKA_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, INST_BANKA_BANK_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT2, INST_BANKA_BANK_RAM_DED_COUNT) },
-	{ "SQC_DATA_BANKA_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_TAG_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_TAG_RAM_DED_COUNT) },
-	{ "SQC_DATA_BANKA_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_BANK_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_BANK_RAM_DED_COUNT) },
-	{ "SQC_INST_BANKA_UTCL1_MISS_FIFO",
-	  SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1, 6,
-	  REG_FIELD_MASK(SQC_EDC_CNT2, INST_BANKA_UTCL1_MISS_FIFO_SED_COUNT),
-	  0 },
-	{ "SQC_INST_BANKA_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, INST_BANKA_MISS_FIFO_SED_COUNT), 0 },
-	{ "SQC_DATA_BANKA_HIT_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_HIT_FIFO_SED_COUNT), 0 },
-	{ "SQC_DATA_BANKA_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_MISS_FIFO_SED_COUNT), 0 },
-	{ "SQC_DATA_BANKA_DIRTY_BIT_RAM",
-	  SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1, 6,
-	  REG_FIELD_MASK(SQC_EDC_CNT2, DATA_BANKA_DIRTY_BIT_RAM_SED_COUNT), 0 },
-	{ "SQC_INST_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2), 1, 6,
-	  REG_FIELD_MASK(SQC_EDC_CNT2, INST_UTCL1_LFIFO_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT2, INST_UTCL1_LFIFO_DED_COUNT) },
-	{ "SQC_INST_BANKB_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, INST_BANKB_TAG_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT3, INST_BANKB_TAG_RAM_DED_COUNT) },
-	{ "SQC_INST_BANKB_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, INST_BANKB_BANK_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT3, INST_BANKB_BANK_RAM_DED_COUNT) },
-	{ "SQC_DATA_BANKB_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_TAG_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_TAG_RAM_DED_COUNT) },
-	{ "SQC_DATA_BANKB_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_BANK_RAM_SEC_COUNT),
-	  REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_BANK_RAM_DED_COUNT) },
-	{ "SQC_INST_BANKB_UTCL1_MISS_FIFO",
-	  SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1, 6,
-	  REG_FIELD_MASK(SQC_EDC_CNT3, INST_BANKB_UTCL1_MISS_FIFO_SED_COUNT),
-	  0 },
-	{ "SQC_INST_BANKB_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, INST_BANKB_MISS_FIFO_SED_COUNT), 0 },
-	{ "SQC_DATA_BANKB_HIT_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_HIT_FIFO_SED_COUNT), 0 },
-	{ "SQC_DATA_BANKB_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1,
-	  6, REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_MISS_FIFO_SED_COUNT), 0 },
-	{ "SQC_DATA_BANKB_DIRTY_BIT_RAM",
-	  SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3), 1, 6,
-	  REG_FIELD_MASK(SQC_EDC_CNT3, DATA_BANKB_DIRTY_BIT_RAM_SED_COUNT), 0 },
-	{ "EA_DRAMRD_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMRD_CMDMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMRD_CMDMEM_DED_COUNT) },
-	{ "EA_DRAMWR_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMWR_CMDMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMWR_CMDMEM_DED_COUNT) },
-	{ "EA_DRAMWR_DATAMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMWR_DATAMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMWR_DATAMEM_DED_COUNT) },
-	{ "EA_RRET_TAGMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, RRET_TAGMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT, RRET_TAGMEM_DED_COUNT) },
-	{ "EA_WRET_TAGMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, WRET_TAGMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT, WRET_TAGMEM_DED_COUNT) },
-	{ "EA_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMRD_PAGEMEM_SED_COUNT), 0 },
-	{ "EA_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, DRAMWR_PAGEMEM_SED_COUNT), 0 },
-	{ "EA_IORD_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, IORD_CMDMEM_SED_COUNT), 0 },
-	{ "EA_IOWR_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, IOWR_CMDMEM_SED_COUNT), 0 },
-	{ "EA_IOWR_DATAMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT, IOWR_DATAMEM_SED_COUNT), 0 },
-	{ "GMIRD_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIRD_CMDMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIRD_CMDMEM_DED_COUNT) },
-	{ "GMIWR_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIWR_CMDMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIWR_CMDMEM_DED_COUNT) },
-	{ "GMIWR_DATAMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIWR_DATAMEM_SEC_COUNT),
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIWR_DATAMEM_DED_COUNT) },
-	{ "GMIRD_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIRD_PAGEMEM_SED_COUNT), 0 },
-	{ "GMIWR_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, GMIWR_PAGEMEM_SED_COUNT), 0 },
-	{ "MAM_D0MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, MAM_D0MEM_SED_COUNT), 0 },
-	{ "MAM_D1MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, MAM_D1MEM_SED_COUNT), 0 },
-	{ "MAM_D2MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, MAM_D2MEM_SED_COUNT), 0 },
-	{ "MAM_D3MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2), 0, 32,
-	  REG_FIELD_MASK(GCEA_EDC_CNT2, MAM_D3MEM_SED_COUNT), 0 },
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU2_WRITE_DATA_BUF_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU2_WRITE_DATA_BUF_DED_COUNT)
+	},
+	{ "SQC_DATA_CU2_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU2_UTCL1_LFIFO_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT, DATA_CU2_UTCL1_LFIFO_DED_COUNT)
+	},
+	{ "SQC_INST_BANKA_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_BANKA_TAG_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_BANKA_TAG_RAM_DED_COUNT)
+	},
+	{ "SQC_INST_BANKA_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_BANKA_BANK_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_BANKA_BANK_RAM_DED_COUNT)
+	},
+	{ "SQC_DATA_BANKA_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_TAG_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_TAG_RAM_DED_COUNT)
+	},
+	{ "SQC_DATA_BANKA_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_BANK_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_BANK_RAM_DED_COUNT)
+	},
+	{ "SQC_INST_BANKA_UTCL1_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_BANKA_UTCL1_MISS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_INST_BANKA_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_BANKA_MISS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_DATA_BANKA_HIT_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_HIT_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_DATA_BANKA_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_MISS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_DATA_BANKA_DIRTY_BIT_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, DATA_BANKA_DIRTY_BIT_RAM_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_INST_UTCL1_LFIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT2),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_UTCL1_LFIFO_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT2, INST_UTCL1_LFIFO_DED_COUNT)
+	},
+	{ "SQC_INST_BANKB_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, INST_BANKB_TAG_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, INST_BANKB_TAG_RAM_DED_COUNT)
+	},
+	{ "SQC_INST_BANKB_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, INST_BANKB_BANK_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, INST_BANKB_BANK_RAM_DED_COUNT)
+	},
+	{ "SQC_DATA_BANKB_TAG_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_TAG_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_TAG_RAM_DED_COUNT)
+	},
+	{ "SQC_DATA_BANKB_BANK_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_BANK_RAM_SEC_COUNT),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_BANK_RAM_DED_COUNT)
+	},
+	{ "SQC_INST_BANKB_UTCL1_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, INST_BANKB_UTCL1_MISS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_INST_BANKB_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, INST_BANKB_MISS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_DATA_BANKB_HIT_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_HIT_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_DATA_BANKB_MISS_FIFO", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_MISS_FIFO_SED_COUNT),
+	  0, 0
+	},
+	{ "SQC_DATA_BANKB_DIRTY_BIT_RAM", SOC15_REG_ENTRY(GC, 0, mmSQC_EDC_CNT3),
+	  SOC15_REG_FIELD(SQC_EDC_CNT3, DATA_BANKB_DIRTY_BIT_RAM_SED_COUNT),
+	  0, 0
+	},
+	{ "EA_DRAMRD_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMRD_CMDMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMRD_CMDMEM_DED_COUNT)
+	},
+	{ "EA_DRAMWR_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMWR_CMDMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMWR_CMDMEM_DED_COUNT)
+	},
+	{ "EA_DRAMWR_DATAMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMWR_DATAMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMWR_DATAMEM_DED_COUNT)
+	},
+	{ "EA_RRET_TAGMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, RRET_TAGMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, RRET_TAGMEM_DED_COUNT)
+	},
+	{ "EA_WRET_TAGMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, WRET_TAGMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, WRET_TAGMEM_DED_COUNT)
+	},
+	{ "EA_DRAMRD_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMRD_PAGEMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "EA_DRAMWR_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, DRAMWR_PAGEMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "EA_IORD_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, IORD_CMDMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "EA_IOWR_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, IOWR_CMDMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "EA_IOWR_DATAMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT, IOWR_DATAMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "GMIRD_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIRD_CMDMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIRD_CMDMEM_DED_COUNT)
+	},
+	{ "GMIWR_CMDMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIWR_CMDMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIWR_CMDMEM_DED_COUNT)
+	},
+	{ "GMIWR_DATAMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIWR_DATAMEM_SEC_COUNT),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIWR_DATAMEM_DED_COUNT)
+	},
+	{ "GMIRD_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIRD_PAGEMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "GMIWR_PAGEMEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, GMIWR_PAGEMEM_SED_COUNT),
+	  0, 0
+	},
+	{ "MAM_D0MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, MAM_D0MEM_SED_COUNT),
+	  0, 0
+	},
+	{ "MAM_D1MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, MAM_D1MEM_SED_COUNT),
+	  0, 0
+	},
+	{ "MAM_D2MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, MAM_D2MEM_SED_COUNT),
+	  0, 0
+	},
+	{ "MAM_D3MEM", SOC15_REG_ENTRY(GC, 0, mmGCEA_EDC_CNT2),
+	  SOC15_REG_FIELD(GCEA_EDC_CNT2, MAM_D3MEM_SED_COUNT),
+	  0, 0
+	}
 };
 
 static int gfx_v9_0_ras_error_inject(struct amdgpu_device *adev,
@@ -6078,14 +5934,217 @@ static int gfx_v9_0_ras_error_inject(struct amdgpu_device *adev,
 	return ret;
 }
 
+static const char *vml2_mems[] = {
+	"UTC_VML2_BANK_CACHE_0_BIGK_MEM0",
+	"UTC_VML2_BANK_CACHE_0_BIGK_MEM1",
+	"UTC_VML2_BANK_CACHE_0_4K_MEM0",
+	"UTC_VML2_BANK_CACHE_0_4K_MEM1",
+	"UTC_VML2_BANK_CACHE_1_BIGK_MEM0",
+	"UTC_VML2_BANK_CACHE_1_BIGK_MEM1",
+	"UTC_VML2_BANK_CACHE_1_4K_MEM0",
+	"UTC_VML2_BANK_CACHE_1_4K_MEM1",
+	"UTC_VML2_BANK_CACHE_2_BIGK_MEM0",
+	"UTC_VML2_BANK_CACHE_2_BIGK_MEM1",
+	"UTC_VML2_BANK_CACHE_2_4K_MEM0",
+	"UTC_VML2_BANK_CACHE_2_4K_MEM1",
+	"UTC_VML2_BANK_CACHE_3_BIGK_MEM0",
+	"UTC_VML2_BANK_CACHE_3_BIGK_MEM1",
+	"UTC_VML2_BANK_CACHE_3_4K_MEM0",
+	"UTC_VML2_BANK_CACHE_3_4K_MEM1",
+};
+
+static const char *vml2_walker_mems[] = {
+	"UTC_VML2_CACHE_PDE0_MEM0",
+	"UTC_VML2_CACHE_PDE0_MEM1",
+	"UTC_VML2_CACHE_PDE1_MEM0",
+	"UTC_VML2_CACHE_PDE1_MEM1",
+	"UTC_VML2_CACHE_PDE2_MEM0",
+	"UTC_VML2_CACHE_PDE2_MEM1",
+	"UTC_VML2_RDIF_LOG_FIFO",
+};
+
+static const char *atc_l2_cache_2m_mems[] = {
+	"UTC_ATCL2_CACHE_2M_BANK0_WAY0_MEM",
+	"UTC_ATCL2_CACHE_2M_BANK0_WAY1_MEM",
+	"UTC_ATCL2_CACHE_2M_BANK1_WAY0_MEM",
+	"UTC_ATCL2_CACHE_2M_BANK1_WAY1_MEM",
+};
+
+static const char *atc_l2_cache_4k_mems[] = {
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM0",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM1",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM2",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM3",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM4",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM5",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM6",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY0_MEM7",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM0",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM1",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM2",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM3",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM4",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM5",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM6",
+	"UTC_ATCL2_CACHE_4K_BANK0_WAY1_MEM7",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM0",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM1",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM2",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM3",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM4",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM5",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM6",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY0_MEM7",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM0",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM1",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM2",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM3",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM4",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM5",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM6",
+	"UTC_ATCL2_CACHE_4K_BANK1_WAY1_MEM7",
+};
+
+static int gfx_v9_0_query_utc_edc_status(struct amdgpu_device *adev,
+					 struct ras_err_data *err_data)
+{
+	uint32_t i, data;
+	uint32_t sec_count, ded_count;
+
+	WREG32_SOC15(GC, 0, mmVM_L2_MEM_ECC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmVM_L2_MEM_ECC_CNT, 0);
+	WREG32_SOC15(GC, 0, mmVM_L2_WALKER_MEM_ECC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmVM_L2_WALKER_MEM_ECC_CNT, 0);
+	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_2M_EDC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_2M_EDC_CNT, 0);
+	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_EDC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_EDC_CNT, 0);
+
+	for (i = 0; i < 16; i++) {
+		WREG32_SOC15(GC, 0, mmVM_L2_MEM_ECC_INDEX, i);
+		data = RREG32_SOC15(GC, 0, mmVM_L2_MEM_ECC_CNT);
+
+		sec_count = REG_GET_FIELD(data, VM_L2_MEM_ECC_CNT, SEC_COUNT);
+		if (sec_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i,
+				 vml2_mems[i], sec_count);
+			err_data->ce_count += sec_count;
+		}
+
+		ded_count = REG_GET_FIELD(data, VM_L2_MEM_ECC_CNT, DED_COUNT);
+		if (ded_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i,
+				 vml2_mems[i], ded_count);
+			err_data->ue_count += ded_count;
+		}
+	}
+
+	for (i = 0; i < 7; i++) {
+		WREG32_SOC15(GC, 0, mmVM_L2_WALKER_MEM_ECC_INDEX, i);
+		data = RREG32_SOC15(GC, 0, mmVM_L2_WALKER_MEM_ECC_CNT);
+
+		sec_count = REG_GET_FIELD(data, VM_L2_WALKER_MEM_ECC_CNT,
+						SEC_COUNT);
+		if (sec_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i,
+				 vml2_walker_mems[i], sec_count);
+			err_data->ce_count += sec_count;
+		}
+
+		ded_count = REG_GET_FIELD(data, VM_L2_WALKER_MEM_ECC_CNT,
+						DED_COUNT);
+		if (ded_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i,
+				 vml2_walker_mems[i], ded_count);
+			err_data->ue_count += ded_count;
+		}
+	}
+
+	for (i = 0; i < 4; i++) {
+		WREG32_SOC15(GC, 0, mmATC_L2_CACHE_2M_EDC_INDEX, i);
+		data = RREG32_SOC15(GC, 0, mmATC_L2_CACHE_2M_EDC_CNT);
+
+		sec_count = (data & 0x00006000L) >> 0xd;
+		if (sec_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i,
+				 atc_l2_cache_2m_mems[i], sec_count);
+			err_data->ce_count += sec_count;
+		}
+	}
+
+	for (i = 0; i < 32; i++) {
+		WREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_EDC_INDEX, i);
+		data = RREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_EDC_CNT);
+
+		sec_count = (data & 0x00006000L) >> 0xd;
+		if (sec_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, SEC %d\n", i,
+				 atc_l2_cache_4k_mems[i], sec_count);
+			err_data->ce_count += sec_count;
+		}
+
+		ded_count = (data & 0x00018000L) >> 0xf;
+		if (ded_count) {
+			DRM_INFO("Instance[%d]: SubBlock %s, DED %d\n", i,
+				 atc_l2_cache_4k_mems[i], ded_count);
+			err_data->ue_count += ded_count;
+		}
+	}
+
+	WREG32_SOC15(GC, 0, mmVM_L2_MEM_ECC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmVM_L2_WALKER_MEM_ECC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_2M_EDC_INDEX, 255);
+	WREG32_SOC15(GC, 0, mmATC_L2_CACHE_4K_EDC_INDEX, 255);
+
+	return 0;
+}
+
+static int __get_ras_error_count(const struct soc15_reg_entry *reg,
+	uint32_t se_id, uint32_t inst_id, uint32_t value,
+	uint32_t *sec_count, uint32_t *ded_count)
+{
+	uint32_t i;
+	uint32_t sec_cnt, ded_cnt;
+
+	for (i = 0; i < ARRAY_SIZE(ras_subblock_regs); i++) {
+		if(ras_subblock_regs[i].reg_offset != reg->reg_offset ||
+			ras_subblock_regs[i].seg != reg->seg ||
+			ras_subblock_regs[i].inst != reg->inst)
+			continue;
+
+		sec_cnt = (value &
+				ras_subblock_regs[i].sec_count_mask) >>
+				ras_subblock_regs[i].sec_count_shift;
+		if (sec_cnt) {
+			DRM_INFO("GFX SubBlock %s, Instance[%d][%d], SEC %d\n",
+				ras_subblock_regs[i].name,
+				se_id, inst_id,
+				sec_cnt);
+			*sec_count += sec_cnt;
+		}
+
+		ded_cnt = (value &
+				ras_subblock_regs[i].ded_count_mask) >>
+				ras_subblock_regs[i].ded_count_shift;
+		if (ded_cnt) {
+			DRM_INFO("GFX SubBlock %s, Instance[%d][%d], DED %d\n",
+				ras_subblock_regs[i].name,
+				se_id, inst_id,
+				ded_cnt);
+			*ded_count += ded_cnt;
+		}
+	}
+
+	return 0;
+}
+
 static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 					  void *ras_error_status)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
-	uint32_t sec_count, ded_count;
-	uint32_t i;
+	uint32_t sec_count = 0, ded_count = 0;
+	uint32_t i, j, k;
 	uint32_t reg_value;
-	uint32_t se_id, instance_id;
 
 	if (adev->asic_type != CHIP_VEGA20)
 		return -EINVAL;
@@ -6094,71 +6153,29 @@ static int gfx_v9_0_query_ras_error_count(struct amdgpu_device *adev,
 	err_data->ce_count = 0;
 
 	mutex_lock(&adev->grbm_idx_mutex);
-	for (se_id = 0; se_id < adev->gfx.config.max_shader_engines; se_id++) {
-		for (instance_id = 0; instance_id < 256; instance_id++) {
-			for (i = 0;
-			     i < sizeof(gfx_ras_edc_regs) / sizeof(gfx_ras_edc_regs[0]);
-			     i++) {
-				if (se_id != 0 &&
-				    !gfx_ras_edc_regs[i].per_se_instance)
-					continue;
-				if (instance_id >= gfx_ras_edc_regs[i].num_instance)
-					continue;
 
-				gfx_v9_0_select_se_sh(adev, se_id, 0,
-						      instance_id);
-
-				reg_value = RREG32(
-					adev->reg_offset[gfx_ras_edc_regs[i].ip]
-							[gfx_ras_edc_regs[i].inst]
-							[gfx_ras_edc_regs[i].seg] +
-					gfx_ras_edc_regs[i].reg_offset);
-				sec_count = reg_value &
-					    gfx_ras_edc_regs[i].sec_count_mask;
-				ded_count = reg_value &
-					    gfx_ras_edc_regs[i].ded_count_mask;
-				if (sec_count) {
-					DRM_INFO(
-						"Instance[%d][%d]: SubBlock %s, SEC %d\n",
-						se_id, instance_id,
-						gfx_ras_edc_regs[i].name,
-						sec_count);
-					err_data->ce_count++;
-				}
-
-				if (ded_count) {
-					DRM_INFO(
-						"Instance[%d][%d]: SubBlock %s, DED %d\n",
-						se_id, instance_id,
-						gfx_ras_edc_regs[i].name,
-						ded_count);
-					err_data->ue_count++;
-				}
+	for (i = 0; i < ARRAY_SIZE(sec_ded_counter_registers); i++) {
+		for (j = 0; j < sec_ded_counter_registers[i].se_num; j++) {
+			for (k = 0; k < sec_ded_counter_registers[i].instance; k++) {
+				gfx_v9_0_select_se_sh(adev, j, 0, k);
+				reg_value =
+					RREG32(SOC15_REG_ENTRY_OFFSET(sec_ded_counter_registers[i]));
+				if (reg_value)
+					__get_ras_error_count(&sec_ded_counter_registers[i],
+							j, k, reg_value,
+							&sec_count, &ded_count);
 			}
 		}
 	}
-	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
-	mutex_unlock(&adev->grbm_idx_mutex);
-
-	return 0;
-}
 
-static int gfx_v9_0_cp_ecc_error_irq(struct amdgpu_device *adev,
-				  struct amdgpu_irq_src *source,
-				  struct amdgpu_iv_entry *entry)
-{
-	struct ras_common_if *ras_if = adev->gfx.ras_if;
-	struct ras_dispatch_if ih_data = {
-		.entry = entry,
-	};
+	err_data->ce_count += sec_count;
+	err_data->ue_count += ded_count;
 
-	if (!ras_if)
-		return 0;
+	gfx_v9_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+	mutex_unlock(&adev->grbm_idx_mutex);
 
-	ih_data.head = *ras_if;
+	gfx_v9_0_query_utc_edc_status(adev, err_data);
 
-	DRM_ERROR("CP ECC ERROR IRQ\n");
-	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
 	return 0;
 }
 
@@ -6325,7 +6342,7 @@ static const struct amdgpu_irq_src_funcs gfx_v9_0_priv_inst_irq_funcs = {
 
 static const struct amdgpu_irq_src_funcs gfx_v9_0_cp_ecc_error_irq_funcs = {
 	.set = gfx_v9_0_set_cp_ecc_error_state,
-	.process = gfx_v9_0_cp_ecc_error_irq,
+	.process = amdgpu_gfx_cp_ecc_error_irq,
 };
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
index 6ce37ce77d14..e91bd7945777 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_0.c
@@ -178,6 +178,8 @@ static void gfxhub_v1_0_enable_system_domain(struct amdgpu_device *adev)
 	tmp = RREG32_SOC15(GC, 0, mmVM_CONTEXT0_CNTL);
 	tmp = REG_SET_FIELD(tmp, VM_CONTEXT0_CNTL, ENABLE_CONTEXT, 1);
 	tmp = REG_SET_FIELD(tmp, VM_CONTEXT0_CNTL, PAGE_TABLE_DEPTH, 0);
+	tmp = REG_SET_FIELD(tmp, VM_CONTEXT0_CNTL,
+			    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
 	WREG32_SOC15(GC, 0, mmVM_CONTEXT0_CNTL, tmp);
 }
 
@@ -365,6 +367,8 @@ void gfxhub_v1_0_init(struct amdgpu_device *adev)
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(GC, 0,
 				 mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(GC, 0, mmVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
index 5e9ab8eb214a..c0ab71df0d90 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_1.c
@@ -33,16 +33,31 @@ int gfxhub_v1_1_get_xgmi_info(struct amdgpu_device *adev)
 	u32 xgmi_lfb_cntl = RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_CNTL);
 	u32 max_region =
 		REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_MAX_REGION);
+	u32 max_num_physical_nodes   = 0;
+	u32 max_physical_node_id     = 0;
+
+	switch (adev->asic_type) {
+	case CHIP_VEGA20:
+		max_num_physical_nodes   = 4;
+		max_physical_node_id     = 3;
+		break;
+	case CHIP_ARCTURUS:
+		max_num_physical_nodes   = 8;
+		max_physical_node_id     = 7;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	/* PF_MAX_REGION=0 means xgmi is disabled */
 	if (max_region) {
 		adev->gmc.xgmi.num_physical_nodes = max_region + 1;
-		if (adev->gmc.xgmi.num_physical_nodes > 4)
+		if (adev->gmc.xgmi.num_physical_nodes > max_num_physical_nodes)
 			return -EINVAL;
 
 		adev->gmc.xgmi.physical_node_id =
 			REG_GET_FIELD(xgmi_lfb_cntl, MC_VM_XGMI_LFB_CNTL, PF_LFB_REGION);
-		if (adev->gmc.xgmi.physical_node_id > 3)
+		if (adev->gmc.xgmi.physical_node_id > max_physical_node_id)
 			return -EINVAL;
 		adev->gmc.xgmi.node_segment_size = REG_GET_FIELD(
 			RREG32_SOC15(GC, 0, mmMC_VM_XGMI_LFB_SIZE),
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
index 8b789f750b72..b70c7b483c24 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.c
@@ -46,21 +46,25 @@ u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev)
 	return (u64)RREG32_SOC15(GC, 0, mmGCMC_VM_FB_OFFSET) << 24;
 }
 
-static void gfxhub_v2_0_init_gart_pt_regs(struct amdgpu_device *adev)
+void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base)
 {
-	uint64_t value = amdgpu_gmc_pd_addr(adev->gart.bo);
+	/* two registers distance between mmGCVM_CONTEXT0_* to mmGCVM_CONTEXT1_* */
+	int offset = mmGCVM_CONTEXT1_PAGE_TABLE_BASE_ADDR_LO32
+			- mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32;
 
+	WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
+				offset * vmid, lower_32_bits(page_table_base));
 
-	WREG32_SOC15(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
-		     lower_32_bits(value));
-
-	WREG32_SOC15(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
-		     upper_32_bits(value));
+	WREG32_SOC15_OFFSET(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
+				offset * vmid, upper_32_bits(page_table_base));
 }
 
 static void gfxhub_v2_0_init_gart_aperture_regs(struct amdgpu_device *adev)
 {
-	gfxhub_v2_0_init_gart_pt_regs(adev);
+	uint64_t pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
+
+	gfxhub_v2_0_setup_vm_pt_regs(adev, 0, pt_base);
 
 	WREG32_SOC15(GC, 0, mmGCVM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
 		     (u32)(adev->gmc.gart_start >> 12));
@@ -151,6 +155,15 @@ static void gfxhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL2, tmp);
 
 	tmp = mmGCVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, GCVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(GC, 0, mmGCVM_L2_CNTL3, tmp);
 
 	tmp = mmGCVM_L2_CNTL4_DEFAULT;
@@ -166,6 +179,8 @@ static void gfxhub_v2_0_enable_system_domain(struct amdgpu_device *adev)
 	tmp = RREG32_SOC15(GC, 0, mmGCVM_CONTEXT0_CNTL);
 	tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT0_CNTL, ENABLE_CONTEXT, 1);
 	tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT0_CNTL, PAGE_TABLE_DEPTH, 0);
+	tmp = REG_SET_FIELD(tmp, GCVM_CONTEXT0_CNTL,
+			    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
 	WREG32_SOC15(GC, 0, mmGCVM_CONTEXT0_CNTL, tmp);
 }
 
@@ -341,6 +356,8 @@ void gfxhub_v2_0_init(struct amdgpu_device *adev)
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(GC, 0,
 				 mmGCVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(GC, 0, mmGCVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h
index 06807940748b..392b8cd94fc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v2_0.h
@@ -31,5 +31,7 @@ void gfxhub_v2_0_set_fault_enable_default(struct amdgpu_device *adev,
 					  bool value);
 void gfxhub_v2_0_init(struct amdgpu_device *adev);
 u64 gfxhub_v2_0_get_mc_fb_offset(struct amdgpu_device *adev);
+void gfxhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 241a4e57cf4a..232469507446 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -235,6 +235,29 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 	const unsigned eng = 17;
 	unsigned int i;
 
+	spin_lock(&adev->gmc.invalidate_lock);
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1) {
+		for (i = 0; i < adev->usec_timeout; i++) {
+			/* a read return value of 1 means semaphore acuqire */
+			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+			if (tmp & 0x1)
+				break;
+			udelay(1);
+		}
+
+		if (i >= adev->usec_timeout)
+			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+	}
+
 	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
 	/*
@@ -254,6 +277,17 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
 		udelay(1);
 	}
 
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
+	spin_unlock(&adev->gmc.invalidate_lock);
+
 	if (i < adev->usec_timeout)
 		return;
 
@@ -278,7 +312,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	int r;
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	mutex_lock(&adev->mman.gtt_window_lock);
 
@@ -292,7 +326,8 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	if (!adev->mman.buffer_funcs_enabled ||
 	    !adev->ib_pool_ready ||
-	    adev->in_gpu_reset) {
+	    adev->in_gpu_reset ||
+	    ring->sched.ready == false) {
 		gmc_v10_0_flush_vm_hub(adev, vmid, AMDGPU_GFXHUB_0, 0);
 		mutex_unlock(&adev->mman.gtt_window_lock);
 		return;
@@ -309,6 +344,7 @@ static void gmc_v10_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 
 	job->vm_pd_addr = amdgpu_gmc_pd_addr(adev->gart.bo);
 	job->vm_needs_flush = true;
+	job->ibs->ptr[job->ibs->length_dw++] = ring->funcs->nop;
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
@@ -337,17 +373,38 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/* a read return value of 1 means semaphore acuqire */
+		amdgpu_ring_emit_reg_wait(ring,
+					  hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 			      lower_32_bits(pd_addr));
 
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_hi32 + (2 * vmid),
 			      upper_32_bits(pd_addr));
 
-	amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_req + eng, req);
+	amdgpu_ring_emit_reg_write_reg_wait(ring, hub->vm_inv_eng0_req + eng,
+					    hub->vm_inv_eng0_ack + eng,
+					    req, 1 << vmid);
 
-	/* wait for the invalidate to complete */
-	amdgpu_ring_emit_reg_wait(ring, hub->vm_inv_eng0_ack + eng,
-				  1 << vmid, 1 << vmid);
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
 
 	return pd_addr;
 }
@@ -397,43 +454,23 @@ static void gmc_v10_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid
  * 1 system
  * 0 valid
  */
-static uint64_t gmc_v10_0_get_vm_pte_flags(struct amdgpu_device *adev,
-					   uint32_t flags)
-{
-	uint64_t pte_flag = 0;
-
-	if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
-		pte_flag |= AMDGPU_PTE_EXECUTABLE;
-	if (flags & AMDGPU_VM_PAGE_READABLE)
-		pte_flag |= AMDGPU_PTE_READABLE;
-	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
-		pte_flag |= AMDGPU_PTE_WRITEABLE;
 
-	switch (flags & AMDGPU_VM_MTYPE_MASK) {
+static uint64_t gmc_v10_0_map_mtype(struct amdgpu_device *adev, uint32_t flags)
+{
+	switch (flags) {
 	case AMDGPU_VM_MTYPE_DEFAULT:
-		pte_flag |= AMDGPU_PTE_MTYPE_NV10(MTYPE_NC);
-		break;
+		return AMDGPU_PTE_MTYPE_NV10(MTYPE_NC);
 	case AMDGPU_VM_MTYPE_NC:
-		pte_flag |= AMDGPU_PTE_MTYPE_NV10(MTYPE_NC);
-		break;
+		return AMDGPU_PTE_MTYPE_NV10(MTYPE_NC);
 	case AMDGPU_VM_MTYPE_WC:
-		pte_flag |= AMDGPU_PTE_MTYPE_NV10(MTYPE_WC);
-		break;
+		return AMDGPU_PTE_MTYPE_NV10(MTYPE_WC);
 	case AMDGPU_VM_MTYPE_CC:
-		pte_flag |= AMDGPU_PTE_MTYPE_NV10(MTYPE_CC);
-		break;
+		return AMDGPU_PTE_MTYPE_NV10(MTYPE_CC);
 	case AMDGPU_VM_MTYPE_UC:
-		pte_flag |= AMDGPU_PTE_MTYPE_NV10(MTYPE_UC);
-		break;
+		return AMDGPU_PTE_MTYPE_NV10(MTYPE_UC);
 	default:
-		pte_flag |= AMDGPU_PTE_MTYPE_NV10(MTYPE_NC);
-		break;
+		return AMDGPU_PTE_MTYPE_NV10(MTYPE_NC);
 	}
-
-	if (flags & AMDGPU_VM_PAGE_PRT)
-		pte_flag |= AMDGPU_PTE_PRT;
-
-	return pte_flag;
 }
 
 static void gmc_v10_0_get_vm_pde(struct amdgpu_device *adev, int level,
@@ -460,12 +497,32 @@ static void gmc_v10_0_get_vm_pde(struct amdgpu_device *adev, int level,
 	}
 }
 
+static void gmc_v10_0_get_vm_pte(struct amdgpu_device *adev,
+				 struct amdgpu_bo_va_mapping *mapping,
+				 uint64_t *flags)
+{
+	*flags &= ~AMDGPU_PTE_EXECUTABLE;
+	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+
+	*flags &= ~AMDGPU_PTE_MTYPE_NV10_MASK;
+	*flags |= (mapping->flags & AMDGPU_PTE_MTYPE_NV10_MASK);
+
+	if (mapping->flags & AMDGPU_PTE_PRT) {
+		*flags |= AMDGPU_PTE_PRT;
+		*flags |= AMDGPU_PTE_SNOOPED;
+		*flags |= AMDGPU_PTE_LOG;
+		*flags |= AMDGPU_PTE_SYSTEM;
+		*flags &= ~AMDGPU_PTE_VALID;
+	}
+}
+
 static const struct amdgpu_gmc_funcs gmc_v10_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v10_0_flush_gpu_tlb,
 	.emit_flush_gpu_tlb = gmc_v10_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v10_0_emit_pasid_mapping,
-	.get_vm_pte_flags = gmc_v10_0_get_vm_pte_flags,
-	.get_vm_pde = gmc_v10_0_get_vm_pde
+	.map_mtype = gmc_v10_0_map_mtype,
+	.get_vm_pde = gmc_v10_0_get_vm_pde,
+	.get_vm_pte = gmc_v10_0_get_vm_pte
 };
 
 static void gmc_v10_0_set_gmc_funcs(struct amdgpu_device *adev)
@@ -519,8 +576,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
 {
 	u64 base = 0;
 
-	if (!amdgpu_sriov_vf(adev))
-		base = gfxhub_v2_0_get_fb_location(adev);
+	base = gfxhub_v2_0_get_fb_location(adev);
 
 	amdgpu_gmc_vram_location(adev, &adev->gmc, base);
 	amdgpu_gmc_gart_location(adev, mc);
@@ -540,24 +596,13 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev,
  */
 static int gmc_v10_0_mc_init(struct amdgpu_device *adev)
 {
-	int chansize, numchan;
-
-	if (!amdgpu_emu_mode)
-		adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
-	else {
-		/* hard code vram_width for emulation */
-		chansize = 128;
-		numchan = 1;
-		adev->gmc.vram_width = numchan * chansize;
-	}
-
 	/* Could aper size report 0 ? */
 	adev->gmc.aper_base = pci_resource_start(adev->pdev, 0);
 	adev->gmc.aper_size = pci_resource_len(adev->pdev, 0);
 
 	/* size in MB on si */
 	adev->gmc.mc_vram_size =
-		adev->nbio_funcs->get_memsize(adev) * 1024ULL * 1024ULL;
+		adev->nbio.funcs->get_memsize(adev) * 1024ULL * 1024ULL;
 	adev->gmc.real_vram_size = adev->gmc.mc_vram_size;
 	adev->gmc.visible_vram_size = adev->gmc.aper_size;
 
@@ -636,7 +681,7 @@ static unsigned gmc_v10_0_get_vbios_fb_size(struct amdgpu_device *adev)
 
 static int gmc_v10_0_sw_init(void *handle)
 {
-	int r;
+	int r, vram_width = 0, vram_type = 0, vram_vendor = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	gfxhub_v2_0_init(adev);
@@ -644,7 +689,15 @@ static int gmc_v10_0_sw_init(void *handle)
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
-	adev->gmc.vram_type = amdgpu_atomfirmware_get_vram_type(adev);
+	r = amdgpu_atomfirmware_get_vram_info(adev,
+		&vram_width, &vram_type, &vram_vendor);
+	if (!amdgpu_emu_mode)
+		adev->gmc.vram_width = vram_width;
+	else
+		adev->gmc.vram_width = 1 * 128; /* numchan * chansize */
+
+	adev->gmc.vram_type = vram_type;
+	adev->gmc.vram_vendor = vram_vendor;
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
@@ -794,7 +847,7 @@ static int gmc_v10_0_gart_enable(struct amdgpu_device *adev)
 	WREG32_SOC15(HDP, 0, mmHDP_HOST_PATH_CNTL, tmp);
 
 	/* Flush HDP after it is initialized */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	value = (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS) ?
 		false : true;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 9fb1765e92d1..b205039350b6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -386,27 +386,20 @@ static uint64_t gmc_v6_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	return pd_addr;
 }
 
-static uint64_t gmc_v6_0_get_vm_pte_flags(struct amdgpu_device *adev,
-					  uint32_t flags)
-{
-	uint64_t pte_flag = 0;
-
-	if (flags & AMDGPU_VM_PAGE_READABLE)
-		pte_flag |= AMDGPU_PTE_READABLE;
-	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
-		pte_flag |= AMDGPU_PTE_WRITEABLE;
-	if (flags & AMDGPU_VM_PAGE_PRT)
-		pte_flag |= AMDGPU_PTE_PRT;
-
-	return pte_flag;
-}
-
 static void gmc_v6_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				uint64_t *addr, uint64_t *flags)
 {
 	BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
 }
 
+static void gmc_v6_0_get_vm_pte(struct amdgpu_device *adev,
+				struct amdgpu_bo_va_mapping *mapping,
+				uint64_t *flags)
+{
+	*flags &= ~AMDGPU_PTE_EXECUTABLE;
+	*flags &= ~AMDGPU_PTE_PRT;
+}
+
 static void gmc_v6_0_set_fault_enable_default(struct amdgpu_device *adev,
 					      bool value)
 {
@@ -1153,7 +1146,7 @@ static const struct amdgpu_gmc_funcs gmc_v6_0_gmc_funcs = {
 	.emit_flush_gpu_tlb = gmc_v6_0_emit_flush_gpu_tlb,
 	.set_prt = gmc_v6_0_set_prt,
 	.get_vm_pde = gmc_v6_0_get_vm_pde,
-	.get_vm_pte_flags = gmc_v6_0_get_vm_pte_flags
+	.get_vm_pte = gmc_v6_0_get_vm_pte,
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v6_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 0c3d9bc3a641..f08e5330642d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -463,27 +463,20 @@ static void gmc_v7_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
 	amdgpu_ring_emit_wreg(ring, mmIH_VMID_0_LUT + vmid, pasid);
 }
 
-static uint64_t gmc_v7_0_get_vm_pte_flags(struct amdgpu_device *adev,
-					  uint32_t flags)
-{
-	uint64_t pte_flag = 0;
-
-	if (flags & AMDGPU_VM_PAGE_READABLE)
-		pte_flag |= AMDGPU_PTE_READABLE;
-	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
-		pte_flag |= AMDGPU_PTE_WRITEABLE;
-	if (flags & AMDGPU_VM_PAGE_PRT)
-		pte_flag |= AMDGPU_PTE_PRT;
-
-	return pte_flag;
-}
-
 static void gmc_v7_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				uint64_t *addr, uint64_t *flags)
 {
 	BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
 }
 
+static void gmc_v7_0_get_vm_pte(struct amdgpu_device *adev,
+				struct amdgpu_bo_va_mapping *mapping,
+				uint64_t *flags)
+{
+	*flags &= ~AMDGPU_PTE_EXECUTABLE;
+	*flags &= ~AMDGPU_PTE_PRT;
+}
+
 /**
  * gmc_v8_0_set_fault_enable_default - update VM fault handling
  *
@@ -1343,8 +1336,8 @@ static const struct amdgpu_gmc_funcs gmc_v7_0_gmc_funcs = {
 	.emit_flush_gpu_tlb = gmc_v7_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v7_0_emit_pasid_mapping,
 	.set_prt = gmc_v7_0_set_prt,
-	.get_vm_pte_flags = gmc_v7_0_get_vm_pte_flags,
-	.get_vm_pde = gmc_v7_0_get_vm_pde
+	.get_vm_pde = gmc_v7_0_get_vm_pde,
+	.get_vm_pte = gmc_v7_0_get_vm_pte
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v7_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index ea764dd9245d..6d96d40fbcb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -686,29 +686,21 @@ static void gmc_v8_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
  * 0 valid
  */
 
-static uint64_t gmc_v8_0_get_vm_pte_flags(struct amdgpu_device *adev,
-					  uint32_t flags)
-{
-	uint64_t pte_flag = 0;
-
-	if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
-		pte_flag |= AMDGPU_PTE_EXECUTABLE;
-	if (flags & AMDGPU_VM_PAGE_READABLE)
-		pte_flag |= AMDGPU_PTE_READABLE;
-	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
-		pte_flag |= AMDGPU_PTE_WRITEABLE;
-	if (flags & AMDGPU_VM_PAGE_PRT)
-		pte_flag |= AMDGPU_PTE_PRT;
-
-	return pte_flag;
-}
-
 static void gmc_v8_0_get_vm_pde(struct amdgpu_device *adev, int level,
 				uint64_t *addr, uint64_t *flags)
 {
 	BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
 }
 
+static void gmc_v8_0_get_vm_pte(struct amdgpu_device *adev,
+				struct amdgpu_bo_va_mapping *mapping,
+				uint64_t *flags)
+{
+	*flags &= ~AMDGPU_PTE_EXECUTABLE;
+	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+	*flags &= ~AMDGPU_PTE_PRT;
+}
+
 /**
  * gmc_v8_0_set_fault_enable_default - update VM fault handling
  *
@@ -1711,8 +1703,8 @@ static const struct amdgpu_gmc_funcs gmc_v8_0_gmc_funcs = {
 	.emit_flush_gpu_tlb = gmc_v8_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v8_0_emit_pasid_mapping,
 	.set_prt = gmc_v8_0_set_prt,
-	.get_vm_pte_flags = gmc_v8_0_get_vm_pte_flags,
-	.get_vm_pde = gmc_v8_0_get_vm_pde
+	.get_vm_pde = gmc_v8_0_get_vm_pde,
+	.get_vm_pte = gmc_v8_0_get_vm_pte
 };
 
 static const struct amdgpu_irq_src_funcs gmc_v8_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index f91337030dc0..3c355fb5d2b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -51,10 +51,12 @@
 #include "gfxhub_v1_1.h"
 #include "mmhub_v9_4.h"
 #include "umc_v6_1.h"
+#include "umc_v6_0.h"
 
 #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
 
 #include "amdgpu_ras.h"
+#include "amdgpu_xgmi.h"
 
 /* add these here since we already include dce12 headers and these are for DCN */
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION                                                          0x055d
@@ -243,44 +245,6 @@ static int gmc_v9_0_ecc_interrupt_state(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int gmc_v9_0_process_ras_data_cb(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
-		struct amdgpu_iv_entry *entry)
-{
-	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
-	if (adev->umc.funcs->query_ras_error_count)
-		adev->umc.funcs->query_ras_error_count(adev, err_data);
-	/* umc query_ras_error_address is also responsible for clearing
-	 * error status
-	 */
-	if (adev->umc.funcs->query_ras_error_address)
-		adev->umc.funcs->query_ras_error_address(adev, err_data);
-
-	/* only uncorrectable error needs gpu reset */
-	if (err_data->ue_count)
-		amdgpu_ras_reset_gpu(adev, 0);
-
-	return AMDGPU_RAS_SUCCESS;
-}
-
-static int gmc_v9_0_process_ecc_irq(struct amdgpu_device *adev,
-		struct amdgpu_irq_src *source,
-		struct amdgpu_iv_entry *entry)
-{
-	struct ras_common_if *ras_if = adev->gmc.umc_ras_if;
-	struct ras_dispatch_if ih_data = {
-		.entry = entry,
-	};
-
-	if (!ras_if)
-		return 0;
-
-	ih_data.head = *ras_if;
-
-	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
-	return 0;
-}
-
 static int gmc_v9_0_vm_fault_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *src,
 					unsigned type,
@@ -355,6 +319,10 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	}
 
 	/* If it's the first fault for this address, process it normally */
+	if (retry_fault && !in_interrupt() &&
+	    amdgpu_vm_handle_fault(adev, entry->pasid, addr))
+		return 1; /* This also prevents sending it to KFD */
+
 	if (!amdgpu_sriov_vf(adev)) {
 		/*
 		 * Issue a dummy read to wait for the status register to
@@ -417,7 +385,7 @@ static const struct amdgpu_irq_src_funcs gmc_v9_0_irq_funcs = {
 
 static const struct amdgpu_irq_src_funcs gmc_v9_0_ecc_funcs = {
 	.set = gmc_v9_0_ecc_interrupt_state,
-	.process = gmc_v9_0_process_ecc_irq,
+	.process = amdgpu_umc_process_ecc_irq,
 };
 
 static void gmc_v9_0_set_irq_funcs(struct amdgpu_device *adev)
@@ -491,6 +459,29 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	}
 
 	spin_lock(&adev->gmc.invalidate_lock);
+
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1) {
+		for (j = 0; j < adev->usec_timeout; j++) {
+			/* a read return value of 1 means semaphore acuqire */
+			tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+			if (tmp & 0x1)
+				break;
+			udelay(1);
+		}
+
+		if (j >= adev->usec_timeout)
+			DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+	}
+
 	WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
 	/*
@@ -506,7 +497,18 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 			break;
 		udelay(1);
 	}
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (vmhub == AMDGPU_MMHUB_0 ||
+	    vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
 	spin_unlock(&adev->gmc.invalidate_lock);
+
 	if (j < adev->usec_timeout)
 		return;
 
@@ -521,6 +523,20 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 	uint32_t req = gmc_v9_0_get_invalidate_req(vmid, 0);
 	unsigned eng = ring->vm_inv_eng;
 
+	/*
+	 * It may lose gpuvm invalidate acknowldege state across power-gating
+	 * off cycle, add semaphore acquire before invalidation and semaphore
+	 * release after invalidation to avoid entering power gated state
+	 * to WA the Issue
+	 */
+
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/* a read return value of 1 means semaphore acuqire */
+		amdgpu_ring_emit_reg_wait(ring,
+					  hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
 	amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
 			      lower_32_bits(pd_addr));
 
@@ -531,6 +547,15 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
 					    hub->vm_inv_eng0_ack + eng,
 					    req, 1 << vmid);
 
+	/* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+	if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+	    ring->funcs->vmhub == AMDGPU_MMHUB_1)
+		/*
+		 * add semaphore release after invalidation,
+		 * write with 0 means semaphore release
+		 */
+		amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
+
 	return pd_addr;
 }
 
@@ -584,44 +609,25 @@ static void gmc_v9_0_emit_pasid_mapping(struct amdgpu_ring *ring, unsigned vmid,
  * 0 valid
  */
 
-static uint64_t gmc_v9_0_get_vm_pte_flags(struct amdgpu_device *adev,
-						uint32_t flags)
+static uint64_t gmc_v9_0_map_mtype(struct amdgpu_device *adev, uint32_t flags)
 
 {
-	uint64_t pte_flag = 0;
-
-	if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
-		pte_flag |= AMDGPU_PTE_EXECUTABLE;
-	if (flags & AMDGPU_VM_PAGE_READABLE)
-		pte_flag |= AMDGPU_PTE_READABLE;
-	if (flags & AMDGPU_VM_PAGE_WRITEABLE)
-		pte_flag |= AMDGPU_PTE_WRITEABLE;
-
-	switch (flags & AMDGPU_VM_MTYPE_MASK) {
+	switch (flags) {
 	case AMDGPU_VM_MTYPE_DEFAULT:
-		pte_flag |= AMDGPU_PTE_MTYPE_VG10(MTYPE_NC);
-		break;
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_NC);
 	case AMDGPU_VM_MTYPE_NC:
-		pte_flag |= AMDGPU_PTE_MTYPE_VG10(MTYPE_NC);
-		break;
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_NC);
 	case AMDGPU_VM_MTYPE_WC:
-		pte_flag |= AMDGPU_PTE_MTYPE_VG10(MTYPE_WC);
-		break;
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_WC);
+	case AMDGPU_VM_MTYPE_RW:
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_RW);
 	case AMDGPU_VM_MTYPE_CC:
-		pte_flag |= AMDGPU_PTE_MTYPE_VG10(MTYPE_CC);
-		break;
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_CC);
 	case AMDGPU_VM_MTYPE_UC:
-		pte_flag |= AMDGPU_PTE_MTYPE_VG10(MTYPE_UC);
-		break;
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_UC);
 	default:
-		pte_flag |= AMDGPU_PTE_MTYPE_VG10(MTYPE_NC);
-		break;
+		return AMDGPU_PTE_MTYPE_VG10(MTYPE_NC);
 	}
-
-	if (flags & AMDGPU_VM_PAGE_PRT)
-		pte_flag |= AMDGPU_PTE_PRT;
-
-	return pte_flag;
 }
 
 static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
@@ -648,12 +654,34 @@ static void gmc_v9_0_get_vm_pde(struct amdgpu_device *adev, int level,
 	}
 }
 
+static void gmc_v9_0_get_vm_pte(struct amdgpu_device *adev,
+				struct amdgpu_bo_va_mapping *mapping,
+				uint64_t *flags)
+{
+	*flags &= ~AMDGPU_PTE_EXECUTABLE;
+	*flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+
+	*flags &= ~AMDGPU_PTE_MTYPE_VG10_MASK;
+	*flags |= mapping->flags & AMDGPU_PTE_MTYPE_VG10_MASK;
+
+	if (mapping->flags & AMDGPU_PTE_PRT) {
+		*flags |= AMDGPU_PTE_PRT;
+		*flags &= ~AMDGPU_PTE_VALID;
+	}
+
+	if (adev->asic_type == CHIP_ARCTURUS &&
+	    !(*flags & AMDGPU_PTE_SYSTEM) &&
+	    mapping->bo_va->is_xgmi)
+		*flags |= AMDGPU_PTE_SNOOPED;
+}
+
 static const struct amdgpu_gmc_funcs gmc_v9_0_gmc_funcs = {
 	.flush_gpu_tlb = gmc_v9_0_flush_gpu_tlb,
 	.emit_flush_gpu_tlb = gmc_v9_0_emit_flush_gpu_tlb,
 	.emit_pasid_mapping = gmc_v9_0_emit_pasid_mapping,
-	.get_vm_pte_flags = gmc_v9_0_get_vm_pte_flags,
-	.get_vm_pde = gmc_v9_0_get_vm_pde
+	.map_mtype = gmc_v9_0_map_mtype,
+	.get_vm_pde = gmc_v9_0_get_vm_pde,
+	.get_vm_pte = gmc_v9_0_get_vm_pte
 };
 
 static void gmc_v9_0_set_gmc_funcs(struct amdgpu_device *adev)
@@ -664,6 +692,9 @@ static void gmc_v9_0_set_gmc_funcs(struct amdgpu_device *adev)
 static void gmc_v9_0_set_umc_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
+	case CHIP_VEGA10:
+		adev->umc.funcs = &umc_v6_0_funcs;
+		break;
 	case CHIP_VEGA20:
 		adev->umc.max_ras_err_cnt_per_query = UMC_V6_1_TOTAL_CHANNEL_NUM;
 		adev->umc.channel_inst_num = UMC_V6_1_CHANNEL_INSTANCE_NUM;
@@ -681,7 +712,7 @@ static void gmc_v9_0_set_mmhub_funcs(struct amdgpu_device *adev)
 {
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
-		adev->mmhub_funcs = &mmhub_v1_0_funcs;
+		adev->mmhub.funcs = &mmhub_v1_0_funcs;
 		break;
 	default:
 		break;
@@ -762,140 +793,10 @@ static int gmc_v9_0_allocate_vm_inv_eng(struct amdgpu_device *adev)
 	return 0;
 }
 
-static int gmc_v9_0_ecc_ras_block_late_init(void *handle,
-			struct ras_fs_if *fs_info, struct ras_common_if *ras_block)
-{
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct ras_common_if **ras_if = NULL;
-	struct ras_ih_if ih_info = {
-		.cb = gmc_v9_0_process_ras_data_cb,
-	};
-	int r;
-
-	if (ras_block->block == AMDGPU_RAS_BLOCK__UMC)
-		ras_if = &adev->gmc.umc_ras_if;
-	else if (ras_block->block == AMDGPU_RAS_BLOCK__MMHUB)
-		ras_if = &adev->gmc.mmhub_ras_if;
-	else
-		BUG();
-
-	if (!amdgpu_ras_is_supported(adev, ras_block->block)) {
-		amdgpu_ras_feature_enable_on_boot(adev, ras_block, 0);
-		return 0;
-	}
-
-	/* handle resume path. */
-	if (*ras_if) {
-		/* resend ras TA enable cmd during resume.
-		 * prepare to handle failure.
-		 */
-		ih_info.head = **ras_if;
-		r = amdgpu_ras_feature_enable_on_boot(adev, *ras_if, 1);
-		if (r) {
-			if (r == -EAGAIN) {
-				/* request a gpu reset. will run again. */
-				amdgpu_ras_request_reset_on_boot(adev,
-						ras_block->block);
-				return 0;
-			}
-			/* fail to enable ras, cleanup all. */
-			goto irq;
-		}
-		/* enable successfully. continue. */
-		goto resume;
-	}
-
-	*ras_if = kmalloc(sizeof(**ras_if), GFP_KERNEL);
-	if (!*ras_if)
-		return -ENOMEM;
-
-	**ras_if = *ras_block;
-
-	r = amdgpu_ras_feature_enable_on_boot(adev, *ras_if, 1);
-	if (r) {
-		if (r == -EAGAIN) {
-			amdgpu_ras_request_reset_on_boot(adev,
-					ras_block->block);
-			r = 0;
-		}
-		goto feature;
-	}
-
-	ih_info.head = **ras_if;
-	fs_info->head = **ras_if;
-
-	if (ras_block->block == AMDGPU_RAS_BLOCK__UMC) {
-		r = amdgpu_ras_interrupt_add_handler(adev, &ih_info);
-		if (r)
-			goto interrupt;
-	}
-
-	amdgpu_ras_debugfs_create(adev, fs_info);
-
-	r = amdgpu_ras_sysfs_create(adev, fs_info);
-	if (r)
-		goto sysfs;
-resume:
-	if (ras_block->block == AMDGPU_RAS_BLOCK__UMC) {
-		r = amdgpu_irq_get(adev, &adev->gmc.ecc_irq, 0);
-		if (r)
-			goto irq;
-	}
-
-	return 0;
-irq:
-	amdgpu_ras_sysfs_remove(adev, *ras_if);
-sysfs:
-	amdgpu_ras_debugfs_remove(adev, *ras_if);
-	if (ras_block->block == AMDGPU_RAS_BLOCK__UMC)
-		amdgpu_ras_interrupt_remove_handler(adev, &ih_info);
-interrupt:
-	amdgpu_ras_feature_enable(adev, *ras_if, 0);
-feature:
-	kfree(*ras_if);
-	*ras_if = NULL;
-	return r;
-}
-
-static int gmc_v9_0_ecc_late_init(void *handle)
-{
-	int r;
-
-	struct ras_fs_if umc_fs_info = {
-		.sysfs_name = "umc_err_count",
-		.debugfs_name = "umc_err_inject",
-	};
-	struct ras_common_if umc_ras_block = {
-		.block = AMDGPU_RAS_BLOCK__UMC,
-		.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
-		.sub_block_index = 0,
-		.name = "umc",
-	};
-	struct ras_fs_if mmhub_fs_info = {
-		.sysfs_name = "mmhub_err_count",
-		.debugfs_name = "mmhub_err_inject",
-	};
-	struct ras_common_if mmhub_ras_block = {
-		.block = AMDGPU_RAS_BLOCK__MMHUB,
-		.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
-		.sub_block_index = 0,
-		.name = "mmhub",
-	};
-
-	r = gmc_v9_0_ecc_ras_block_late_init(handle,
-			&umc_fs_info, &umc_ras_block);
-	if (r)
-		return r;
-
-	r = gmc_v9_0_ecc_ras_block_late_init(handle,
-			&mmhub_fs_info, &mmhub_ras_block);
-	return r;
-}
-
 static int gmc_v9_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	bool r;
+	int r;
 
 	if (!gmc_v9_0_keep_stolen_memory(adev))
 		amdgpu_bo_late_init(adev);
@@ -929,7 +830,7 @@ static int gmc_v9_0_late_init(void *handle)
 		}
 	}
 
-	r = gmc_v9_0_ecc_late_init(handle);
+	r = amdgpu_gmc_ras_late_init(adev);
 	if (r)
 		return r;
 
@@ -970,33 +871,11 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev,
  */
 static int gmc_v9_0_mc_init(struct amdgpu_device *adev)
 {
-	int chansize, numchan;
 	int r;
 
-	if (amdgpu_sriov_vf(adev)) {
-		/* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN,
-		 * and DF related registers is not readable, seems hardcord is the
-		 * only way to set the correct vram_width
-		 */
-		adev->gmc.vram_width = 2048;
-	} else if (amdgpu_emu_mode != 1) {
-		adev->gmc.vram_width = amdgpu_atomfirmware_get_vram_width(adev);
-	}
-
-	if (!adev->gmc.vram_width) {
-		/* hbm memory channel size */
-		if (adev->flags & AMD_IS_APU)
-			chansize = 64;
-		else
-			chansize = 128;
-
-		numchan = adev->df_funcs->get_hbm_channel_number(adev);
-		adev->gmc.vram_width = numchan * chansize;
-	}
-
 	/* size in MB on si */
 	adev->gmc.mc_vram_size =
-		adev->nbio_funcs->get_memsize(adev) * 1024ULL * 1024ULL;
+		adev->nbio.funcs->get_memsize(adev) * 1024ULL * 1024ULL;
 	adev->gmc.real_vram_size = adev->gmc.mc_vram_size;
 
 	if (!(adev->flags & AMD_IS_APU)) {
@@ -1108,7 +987,7 @@ static unsigned gmc_v9_0_get_vbios_fb_size(struct amdgpu_device *adev)
 
 static int gmc_v9_0_sw_init(void *handle)
 {
-	int r;
+	int r, vram_width = 0, vram_type = 0, vram_vendor = 0;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	gfxhub_v1_0_init(adev);
@@ -1119,7 +998,32 @@ static int gmc_v9_0_sw_init(void *handle)
 
 	spin_lock_init(&adev->gmc.invalidate_lock);
 
-	adev->gmc.vram_type = amdgpu_atomfirmware_get_vram_type(adev);
+	r = amdgpu_atomfirmware_get_vram_info(adev,
+		&vram_width, &vram_type, &vram_vendor);
+	if (amdgpu_sriov_vf(adev))
+		/* For Vega10 SR-IOV, vram_width can't be read from ATOM as RAVEN,
+		 * and DF related registers is not readable, seems hardcord is the
+		 * only way to set the correct vram_width
+		 */
+		adev->gmc.vram_width = 2048;
+	else if (amdgpu_emu_mode != 1)
+		adev->gmc.vram_width = vram_width;
+
+	if (!adev->gmc.vram_width) {
+		int chansize, numchan;
+
+		/* hbm memory channel size */
+		if (adev->flags & AMD_IS_APU)
+			chansize = 64;
+		else
+			chansize = 128;
+
+		numchan = adev->df_funcs->get_hbm_channel_number(adev);
+		adev->gmc.vram_width = numchan * chansize;
+	}
+
+	adev->gmc.vram_type = vram_type;
+	adev->gmc.vram_vendor = vram_vendor;
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
 		adev->num_vmhubs = 2;
@@ -1240,33 +1144,7 @@ static int gmc_v9_0_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	void *stolen_vga_buf;
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__UMC) &&
-			adev->gmc.umc_ras_if) {
-		struct ras_common_if *ras_if = adev->gmc.umc_ras_if;
-		struct ras_ih_if ih_info = {
-			.head = *ras_if,
-		};
-
-		/* remove fs first */
-		amdgpu_ras_debugfs_remove(adev, ras_if);
-		amdgpu_ras_sysfs_remove(adev, ras_if);
-		/* remove the IH */
-		amdgpu_ras_interrupt_remove_handler(adev, &ih_info);
-		amdgpu_ras_feature_enable(adev, ras_if, 0);
-		kfree(ras_if);
-	}
-
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__MMHUB) &&
-			adev->gmc.mmhub_ras_if) {
-		struct ras_common_if *ras_if = adev->gmc.mmhub_ras_if;
-
-		/* remove fs and disable ras feature */
-		amdgpu_ras_debugfs_remove(adev, ras_if);
-		amdgpu_ras_sysfs_remove(adev, ras_if);
-		amdgpu_ras_feature_enable(adev, ras_if, 0);
-		kfree(ras_if);
-	}
-
+	amdgpu_gmc_ras_fini(adev);
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
 
@@ -1316,13 +1194,7 @@ static void gmc_v9_0_init_golden_registers(struct amdgpu_device *adev)
  */
 static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 {
-	int r, i;
-	bool value;
-	u32 tmp;
-
-	amdgpu_device_program_register_sequence(adev,
-						golden_settings_vega10_hdp,
-						ARRAY_SIZE(golden_settings_vega10_hdp));
+	int r;
 
 	if (adev->gart.bo == NULL) {
 		dev_err(adev->dev, "No VRAM object for PCIE GART.\n");
@@ -1332,15 +1204,6 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	switch (adev->asic_type) {
-	case CHIP_RAVEN:
-		/* TODO for renoir */
-		mmhub_v1_0_update_power_gating(adev, true);
-		break;
-	default:
-		break;
-	}
-
 	r = gfxhub_v1_0_gart_enable(adev);
 	if (r)
 		return r;
@@ -1352,6 +1215,49 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
+	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
+		 (unsigned)(adev->gmc.gart_size >> 20),
+		 (unsigned long long)amdgpu_bo_gpu_offset(adev->gart.bo));
+	adev->gart.ready = true;
+	return 0;
+}
+
+static int gmc_v9_0_hw_init(void *handle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	bool value;
+	int r, i;
+	u32 tmp;
+
+	/* The sequence of these two function calls matters.*/
+	gmc_v9_0_init_golden_registers(adev);
+
+	if (adev->mode_info.num_crtc) {
+		if (adev->asic_type != CHIP_ARCTURUS) {
+			/* Lockout access through VGA aperture*/
+			WREG32_FIELD15(DCE, 0, VGA_HDP_CONTROL, VGA_MEMORY_DISABLE, 1);
+
+			/* disable VGA render */
+			WREG32_FIELD15(DCE, 0, VGA_RENDER_CONTROL, VGA_VSTATUS_CNTL, 0);
+		}
+	}
+
+	amdgpu_device_program_register_sequence(adev,
+						golden_settings_vega10_hdp,
+						ARRAY_SIZE(golden_settings_vega10_hdp));
+
+	switch (adev->asic_type) {
+	case CHIP_RAVEN:
+		/* TODO for renoir */
+		mmhub_v1_0_update_power_gating(adev, true);
+		break;
+	case CHIP_ARCTURUS:
+		WREG32_FIELD15(HDP, 0, HDP_MMHUB_CNTL, HDP_MMHUB_GCC, 1);
+		break;
+	default:
+		break;
+	}
+
 	WREG32_FIELD15(HDP, 0, HDP_MISC_CNTL, FLUSH_INVALIDATE_CACHE, 1);
 
 	tmp = RREG32_SOC15(HDP, 0, mmHDP_HOST_PATH_CNTL);
@@ -1361,7 +1267,7 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	WREG32_SOC15(HDP, 0, mmHDP_NONSURFACE_BASE_HI, (adev->gmc.vram_start >> 40));
 
 	/* After HDP is initialized, flush HDP.*/
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_ALWAYS)
 		value = false;
@@ -1377,28 +1283,8 @@ static int gmc_v9_0_gart_enable(struct amdgpu_device *adev)
 	for (i = 0; i < adev->num_vmhubs; ++i)
 		gmc_v9_0_flush_gpu_tlb(adev, 0, i, 0);
 
-	DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
-		 (unsigned)(adev->gmc.gart_size >> 20),
-		 (unsigned long long)amdgpu_bo_gpu_offset(adev->gart.bo));
-	adev->gart.ready = true;
-	return 0;
-}
-
-static int gmc_v9_0_hw_init(void *handle)
-{
-	int r;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-
-	/* The sequence of these two function calls matters.*/
-	gmc_v9_0_init_golden_registers(adev);
-
-	if (adev->mode_info.num_crtc) {
-		/* Lockout access through VGA aperture*/
-		WREG32_FIELD15(DCE, 0, VGA_HDP_CONTROL, VGA_MEMORY_DISABLE, 1);
-
-		/* disable VGA render */
-		WREG32_FIELD15(DCE, 0, VGA_RENDER_CONTROL, VGA_VSTATUS_CNTL, 0);
-	}
+	if (adev->umc.funcs && adev->umc.funcs->init_registers)
+		adev->umc.funcs->init_registers(adev);
 
 	r = gmc_v9_0_gart_enable(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 04cd4b6f95d4..28105e4af507 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -206,6 +206,8 @@ static void mmhub_v1_0_enable_system_domain(struct amdgpu_device *adev)
 	tmp = RREG32_SOC15(MMHUB, 0, mmVM_CONTEXT0_CNTL);
 	tmp = REG_SET_FIELD(tmp, VM_CONTEXT0_CNTL, ENABLE_CONTEXT, 1);
 	tmp = REG_SET_FIELD(tmp, VM_CONTEXT0_CNTL, PAGE_TABLE_DEPTH, 0);
+	tmp = REG_SET_FIELD(tmp, VM_CONTEXT0_CNTL,
+			    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
 	WREG32_SOC15(MMHUB, 0, mmVM_CONTEXT0_CNTL, tmp);
 }
 
@@ -418,6 +420,8 @@ void mmhub_v1_0_init(struct amdgpu_device *adev)
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(MMHUB, 0,
 				 mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(MMHUB, 0, mmVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
@@ -616,5 +620,6 @@ static void mmhub_v1_0_query_ras_error_count(struct amdgpu_device *adev,
 }
 
 const struct amdgpu_mmhub_funcs mmhub_v1_0_funcs = {
+	.ras_late_init = amdgpu_mmhub_ras_late_init,
 	.query_ras_error_count = mmhub_v1_0_query_ras_error_count,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
index 3542c203c3c8..a7cb185d639a 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
@@ -31,20 +31,25 @@
 
 #include "soc15_common.h"
 
-static void mmhub_v2_0_init_gart_pt_regs(struct amdgpu_device *adev)
+void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base)
 {
-	uint64_t value = amdgpu_gmc_pd_addr(adev->gart.bo);
+	/* two registers distance between mmMMVM_CONTEXT0_* to mmMMVM_CONTEXT1_* */
+	int offset = mmMMVM_CONTEXT1_PAGE_TABLE_BASE_ADDR_LO32
+			- mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32;
 
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
-		     lower_32_bits(value));
+	WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
+			offset * vmid, lower_32_bits(page_table_base));
 
-	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
-		     upper_32_bits(value));
+	WREG32_SOC15_OFFSET(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
+			offset * vmid, upper_32_bits(page_table_base));
 }
 
 static void mmhub_v2_0_init_gart_aperture_regs(struct amdgpu_device *adev)
 {
-	mmhub_v2_0_init_gart_pt_regs(adev);
+	uint64_t pt_base = amdgpu_gmc_pd_addr(adev->gart.bo);
+
+	mmhub_v2_0_setup_vm_pt_regs(adev, 0, pt_base);
 
 	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_PAGE_TABLE_START_ADDR_LO32,
 		     (u32)(adev->gmc.gart_start >> 12));
@@ -137,6 +142,15 @@ static void mmhub_v2_0_init_cache_regs(struct amdgpu_device *adev)
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL2, tmp);
 
 	tmp = mmMMVM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, MMVM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15(MMHUB, 0, mmMMVM_L2_CNTL3, tmp);
 
 	tmp = mmMMVM_L2_CNTL4_DEFAULT;
@@ -152,6 +166,8 @@ static void mmhub_v2_0_enable_system_domain(struct amdgpu_device *adev)
 	tmp = RREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_CNTL);
 	tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT0_CNTL, ENABLE_CONTEXT, 1);
 	tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT0_CNTL, PAGE_TABLE_DEPTH, 0);
+	tmp = REG_SET_FIELD(tmp, MMVM_CONTEXT0_CNTL,
+			    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
 	WREG32_SOC15(MMHUB, 0, mmMMVM_CONTEXT0_CNTL, tmp);
 }
 
@@ -332,6 +348,8 @@ void mmhub_v2_0_init(struct amdgpu_device *adev)
 	hub->ctx0_ptb_addr_hi32 =
 		SOC15_REG_OFFSET(MMHUB, 0,
 				 mmMMVM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32);
+	hub->vm_inv_eng0_sem =
+		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_SEM);
 	hub->vm_inv_eng0_req =
 		SOC15_REG_OFFSET(MMHUB, 0, mmMMVM_INVALIDATE_ENG0_REQ);
 	hub->vm_inv_eng0_ack =
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h
index db16f3ece218..3ea4344f0315 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.h
@@ -31,5 +31,7 @@ void mmhub_v2_0_init(struct amdgpu_device *adev);
 int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
 			       enum amd_clockgating_state state);
 void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u32 *flags);
+void mmhub_v2_0_setup_vm_pt_regs(struct amdgpu_device *adev, uint32_t vmid,
+				uint64_t page_table_base);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
index 0cf7ef44b4b5..66efe2f7bd76 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
@@ -219,6 +219,15 @@ static void mmhub_v9_4_init_cache_regs(struct amdgpu_device *adev, int hubid)
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 
 	tmp = mmVML2PF0_VM_L2_CNTL3_DEFAULT;
+	if (adev->gmc.translate_further) {
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 12);
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 9);
+	} else {
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3, BANK_SELECT, 9);
+		tmp = REG_SET_FIELD(tmp, VML2PF0_VM_L2_CNTL3,
+				    L2_CACHE_BIGK_FRAGMENT_SIZE, 6);
+	}
 	WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2PF0_VM_L2_CNTL3,
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 
@@ -240,6 +249,8 @@ static void mmhub_v9_4_enable_system_domain(struct amdgpu_device *adev,
 				  hubid * MMHUB_INSTANCE_REGISTER_OFFSET);
 	tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT0_CNTL, ENABLE_CONTEXT, 1);
 	tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT0_CNTL, PAGE_TABLE_DEPTH, 0);
+	tmp = REG_SET_FIELD(tmp, VML2VC0_VM_CONTEXT0_CNTL,
+			    RETRY_PERMISSION_OR_INVALID_PAGE_FAULT, 0);
 	WREG32_SOC15_OFFSET(MMHUB, 0, mmVML2VC0_VM_CONTEXT0_CNTL,
 			    hubid * MMHUB_INSTANCE_REGISTER_OFFSET, tmp);
 }
@@ -493,6 +504,10 @@ void mmhub_v9_4_init(struct amdgpu_device *adev)
 			SOC15_REG_OFFSET(MMHUB, 0,
 			    mmVML2VC0_VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32) +
 			    i * MMHUB_INSTANCE_REGISTER_OFFSET;
+		hub[i]->vm_inv_eng0_sem =
+			SOC15_REG_OFFSET(MMHUB, 0,
+					 mmVML2VC0_VM_INVALIDATE_ENG0_SEM) +
+					 i * MMHUB_INSTANCE_REGISTER_OFFSET;
 		hub[i]->vm_inv_eng0_req =
 			SOC15_REG_OFFSET(MMHUB, 0,
 					 mmVML2VC0_VM_INVALIDATE_ENG0_REQ) +
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
new file mode 100644
index 000000000000..0d8767eb7a70
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
@@ -0,0 +1,380 @@
+/*
+ * Copyright 2014 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "amdgpu.h"
+#include "nbio/nbio_2_3_offset.h"
+#include "nbio/nbio_2_3_sh_mask.h"
+#include "gc/gc_10_1_0_offset.h"
+#include "gc/gc_10_1_0_sh_mask.h"
+#include "soc15.h"
+#include "navi10_ih.h"
+#include "soc15_common.h"
+#include "mxgpu_nv.h"
+#include "mxgpu_ai.h"
+
+static void xgpu_nv_mailbox_send_ack(struct amdgpu_device *adev)
+{
+	WREG8(NV_MAIBOX_CONTROL_RCV_OFFSET_BYTE, 2);
+}
+
+static void xgpu_nv_mailbox_set_valid(struct amdgpu_device *adev, bool val)
+{
+	WREG8(NV_MAIBOX_CONTROL_TRN_OFFSET_BYTE, val ? 1 : 0);
+}
+
+/*
+ * this peek_msg could *only* be called in IRQ routine becuase in IRQ routine
+ * RCV_MSG_VALID filed of BIF_BX_PF_MAILBOX_CONTROL must already be set to 1
+ * by host.
+ *
+ * if called no in IRQ routine, this peek_msg cannot guaranteed to return the
+ * correct value since it doesn't return the RCV_DW0 under the case that
+ * RCV_MSG_VALID is set by host.
+ */
+static enum idh_event xgpu_nv_mailbox_peek_msg(struct amdgpu_device *adev)
+{
+	return RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0,
+				mmBIF_BX_PF_MAILBOX_MSGBUF_RCV_DW0));
+}
+
+
+static int xgpu_nv_mailbox_rcv_msg(struct amdgpu_device *adev,
+				   enum idh_event event)
+{
+	u32 reg;
+
+	reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0,
+					     mmBIF_BX_PF_MAILBOX_MSGBUF_RCV_DW0));
+	if (reg != event)
+		return -ENOENT;
+
+	xgpu_nv_mailbox_send_ack(adev);
+
+	return 0;
+}
+
+static uint8_t xgpu_nv_peek_ack(struct amdgpu_device *adev)
+{
+	return RREG8(NV_MAIBOX_CONTROL_TRN_OFFSET_BYTE) & 2;
+}
+
+static int xgpu_nv_poll_ack(struct amdgpu_device *adev)
+{
+	int timeout  = NV_MAILBOX_POLL_ACK_TIMEDOUT;
+	u8 reg;
+
+	do {
+		reg = RREG8(NV_MAIBOX_CONTROL_TRN_OFFSET_BYTE);
+		if (reg & 2)
+			return 0;
+
+		mdelay(5);
+		timeout -= 5;
+	} while (timeout > 1);
+
+	pr_err("Doesn't get TRN_MSG_ACK from pf in %d msec\n", NV_MAILBOX_POLL_ACK_TIMEDOUT);
+
+	return -ETIME;
+}
+
+static int xgpu_nv_poll_msg(struct amdgpu_device *adev, enum idh_event event)
+{
+	int r, timeout = NV_MAILBOX_POLL_MSG_TIMEDOUT;
+
+	do {
+		r = xgpu_nv_mailbox_rcv_msg(adev, event);
+		if (!r)
+			return 0;
+
+		msleep(10);
+		timeout -= 10;
+	} while (timeout > 1);
+
+	pr_err("Doesn't get msg:%d from pf, error=%d\n", event, r);
+
+	return -ETIME;
+}
+
+static void xgpu_nv_mailbox_trans_msg (struct amdgpu_device *adev,
+	      enum idh_request req, u32 data1, u32 data2, u32 data3)
+{
+	u32 reg;
+	int r;
+	uint8_t trn;
+
+	/* IMPORTANT:
+	 * clear TRN_MSG_VALID valid to clear host's RCV_MSG_ACK
+	 * and with host's RCV_MSG_ACK cleared hw automatically clear host's RCV_MSG_ACK
+	 * which lead to VF's TRN_MSG_ACK cleared, otherwise below xgpu_nv_poll_ack()
+	 * will return immediatly
+	 */
+	do {
+		xgpu_nv_mailbox_set_valid(adev, false);
+		trn = xgpu_nv_peek_ack(adev);
+		if (trn) {
+			pr_err("trn=%x ACK should not assert! wait again !\n", trn);
+			msleep(1);
+		}
+	} while (trn);
+
+	reg = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0,
+					     mmBIF_BX_PF_MAILBOX_MSGBUF_TRN_DW0));
+	reg = REG_SET_FIELD(reg, BIF_BX_PF_MAILBOX_MSGBUF_TRN_DW0,
+			    MSGBUF_DATA, req);
+	WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_MSGBUF_TRN_DW0),
+		      reg);
+	WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_MSGBUF_TRN_DW1),
+				data1);
+	WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_MSGBUF_TRN_DW2),
+				data2);
+	WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_MSGBUF_TRN_DW3),
+				data3);
+
+	xgpu_nv_mailbox_set_valid(adev, true);
+
+	/* start to poll ack */
+	r = xgpu_nv_poll_ack(adev);
+	if (r)
+		pr_err("Doesn't get ack from pf, continue\n");
+
+	xgpu_nv_mailbox_set_valid(adev, false);
+}
+
+static int xgpu_nv_send_access_requests(struct amdgpu_device *adev,
+					enum idh_request req)
+{
+	int r;
+
+	xgpu_nv_mailbox_trans_msg(adev, req, 0, 0, 0);
+
+	/* start to check msg if request is idh_req_gpu_init_access */
+	if (req == IDH_REQ_GPU_INIT_ACCESS ||
+		req == IDH_REQ_GPU_FINI_ACCESS ||
+		req == IDH_REQ_GPU_RESET_ACCESS) {
+		r = xgpu_nv_poll_msg(adev, IDH_READY_TO_ACCESS_GPU);
+		if (r) {
+			pr_err("Doesn't get READY_TO_ACCESS_GPU from pf, give up\n");
+			return r;
+		}
+		/* Retrieve checksum from mailbox2 */
+		if (req == IDH_REQ_GPU_INIT_ACCESS || req == IDH_REQ_GPU_RESET_ACCESS) {
+			adev->virt.fw_reserve.checksum_key =
+				RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0,
+					mmBIF_BX_PF_MAILBOX_MSGBUF_RCV_DW2));
+		}
+	}
+
+	return 0;
+}
+
+static int xgpu_nv_request_reset(struct amdgpu_device *adev)
+{
+	return xgpu_nv_send_access_requests(adev, IDH_REQ_GPU_RESET_ACCESS);
+}
+
+static int xgpu_nv_request_full_gpu_access(struct amdgpu_device *adev,
+					   bool init)
+{
+	enum idh_request req;
+
+	req = init ? IDH_REQ_GPU_INIT_ACCESS : IDH_REQ_GPU_FINI_ACCESS;
+	return xgpu_nv_send_access_requests(adev, req);
+}
+
+static int xgpu_nv_release_full_gpu_access(struct amdgpu_device *adev,
+					   bool init)
+{
+	enum idh_request req;
+	int r = 0;
+
+	req = init ? IDH_REL_GPU_INIT_ACCESS : IDH_REL_GPU_FINI_ACCESS;
+	r = xgpu_nv_send_access_requests(adev, req);
+
+	return r;
+}
+
+static int xgpu_nv_mailbox_ack_irq(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					struct amdgpu_iv_entry *entry)
+{
+	DRM_DEBUG("get ack intr and do nothing.\n");
+	return 0;
+}
+
+static int xgpu_nv_set_mailbox_ack_irq(struct amdgpu_device *adev,
+					struct amdgpu_irq_src *source,
+					unsigned type,
+					enum amdgpu_interrupt_state state)
+{
+	u32 tmp = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_INT_CNTL));
+
+	tmp = REG_SET_FIELD(tmp, BIF_BX_PF_MAILBOX_INT_CNTL, ACK_INT_EN,
+				(state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0);
+	WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_INT_CNTL), tmp);
+
+	return 0;
+}
+
+static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
+{
+	struct amdgpu_virt *virt = container_of(work, struct amdgpu_virt, flr_work);
+	struct amdgpu_device *adev = container_of(virt, struct amdgpu_device, virt);
+	int timeout = NV_MAILBOX_POLL_FLR_TIMEDOUT;
+	int locked;
+
+	/* block amdgpu_gpu_recover till msg FLR COMPLETE received,
+	 * otherwise the mailbox msg will be ruined/reseted by
+	 * the VF FLR.
+	 *
+	 * we can unlock the lock_reset to allow "amdgpu_job_timedout"
+	 * to run gpu_recover() after FLR_NOTIFICATION_CMPL received
+	 * which means host side had finished this VF's FLR.
+	 */
+	locked = mutex_trylock(&adev->lock_reset);
+	if (locked)
+		adev->in_gpu_reset = 1;
+
+	do {
+		if (xgpu_nv_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
+			goto flr_done;
+
+		msleep(10);
+		timeout -= 10;
+	} while (timeout > 1);
+
+flr_done:
+	if (locked) {
+		adev->in_gpu_reset = 0;
+		mutex_unlock(&adev->lock_reset);
+	}
+
+	/* Trigger recovery for world switch failure if no TDR */
+	if (amdgpu_device_should_recover_gpu(adev))
+		amdgpu_device_gpu_recover(adev, NULL);
+}
+
+static int xgpu_nv_set_mailbox_rcv_irq(struct amdgpu_device *adev,
+				       struct amdgpu_irq_src *src,
+				       unsigned type,
+				       enum amdgpu_interrupt_state state)
+{
+	u32 tmp = RREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_INT_CNTL));
+
+	tmp = REG_SET_FIELD(tmp, BIF_BX_PF_MAILBOX_INT_CNTL, VALID_INT_EN,
+			    (state == AMDGPU_IRQ_STATE_ENABLE) ? 1 : 0);
+	WREG32_NO_KIQ(SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_INT_CNTL), tmp);
+
+	return 0;
+}
+
+static int xgpu_nv_mailbox_rcv_irq(struct amdgpu_device *adev,
+				   struct amdgpu_irq_src *source,
+				   struct amdgpu_iv_entry *entry)
+{
+	enum idh_event event = xgpu_nv_mailbox_peek_msg(adev);
+
+	switch (event) {
+	case IDH_FLR_NOTIFICATION:
+		if (amdgpu_sriov_runtime(adev))
+			schedule_work(&adev->virt.flr_work);
+		break;
+		/* READY_TO_ACCESS_GPU is fetched by kernel polling, IRQ can ignore
+		 * it byfar since that polling thread will handle it,
+		 * other msg like flr complete is not handled here.
+		 */
+	case IDH_CLR_MSG_BUF:
+	case IDH_FLR_NOTIFICATION_CMPL:
+	case IDH_READY_TO_ACCESS_GPU:
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct amdgpu_irq_src_funcs xgpu_nv_mailbox_ack_irq_funcs = {
+	.set = xgpu_nv_set_mailbox_ack_irq,
+	.process = xgpu_nv_mailbox_ack_irq,
+};
+
+static const struct amdgpu_irq_src_funcs xgpu_nv_mailbox_rcv_irq_funcs = {
+	.set = xgpu_nv_set_mailbox_rcv_irq,
+	.process = xgpu_nv_mailbox_rcv_irq,
+};
+
+void xgpu_nv_mailbox_set_irq_funcs(struct amdgpu_device *adev)
+{
+	adev->virt.ack_irq.num_types = 1;
+	adev->virt.ack_irq.funcs = &xgpu_nv_mailbox_ack_irq_funcs;
+	adev->virt.rcv_irq.num_types = 1;
+	adev->virt.rcv_irq.funcs = &xgpu_nv_mailbox_rcv_irq_funcs;
+}
+
+int xgpu_nv_mailbox_add_irq_id(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF, 135, &adev->virt.rcv_irq);
+	if (r)
+		return r;
+
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF, 138, &adev->virt.ack_irq);
+	if (r) {
+		amdgpu_irq_put(adev, &adev->virt.rcv_irq, 0);
+		return r;
+	}
+
+	return 0;
+}
+
+int xgpu_nv_mailbox_get_irq(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_irq_get(adev, &adev->virt.rcv_irq, 0);
+	if (r)
+		return r;
+	r = amdgpu_irq_get(adev, &adev->virt.ack_irq, 0);
+	if (r) {
+		amdgpu_irq_put(adev, &adev->virt.rcv_irq, 0);
+		return r;
+	}
+
+	INIT_WORK(&adev->virt.flr_work, xgpu_nv_mailbox_flr_work);
+
+	return 0;
+}
+
+void xgpu_nv_mailbox_put_irq(struct amdgpu_device *adev)
+{
+	amdgpu_irq_put(adev, &adev->virt.ack_irq, 0);
+	amdgpu_irq_put(adev, &adev->virt.rcv_irq, 0);
+}
+
+const struct amdgpu_virt_ops xgpu_nv_virt_ops = {
+	.req_full_gpu	= xgpu_nv_request_full_gpu_access,
+	.rel_full_gpu	= xgpu_nv_release_full_gpu_access,
+	.reset_gpu = xgpu_nv_request_reset,
+	.wait_reset = NULL,
+	.trans_msg = xgpu_nv_mailbox_trans_msg,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
new file mode 100644
index 000000000000..99b15f6865cb
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.h
@@ -0,0 +1,41 @@
+/*
+ * Copyright 2014 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 __MXGPU_NV_H__
+#define __MXGPU_NV_H__
+
+#define NV_MAILBOX_POLL_ACK_TIMEDOUT	500
+#define NV_MAILBOX_POLL_MSG_TIMEDOUT	12000
+#define NV_MAILBOX_POLL_FLR_TIMEDOUT	500
+
+extern const struct amdgpu_virt_ops xgpu_nv_virt_ops;
+
+void xgpu_nv_mailbox_set_irq_funcs(struct amdgpu_device *adev);
+int xgpu_nv_mailbox_add_irq_id(struct amdgpu_device *adev);
+int xgpu_nv_mailbox_get_irq(struct amdgpu_device *adev);
+void xgpu_nv_mailbox_put_irq(struct amdgpu_device *adev);
+
+#define NV_MAIBOX_CONTROL_TRN_OFFSET_BYTE (SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_CONTROL) * 4)
+#define NV_MAIBOX_CONTROL_RCV_OFFSET_BYTE (SOC15_REG_OFFSET(NBIO, 0, mmBIF_BX_PF_MAILBOX_CONTROL) * 4 + 1)
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 9fe08408db58..9af73567e716 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -117,7 +117,7 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 	/* disable irqs */
 	navi10_ih_disable_interrupts(adev);
 
-	adev->nbio_funcs->ih_control(adev);
+	adev->nbio.funcs->ih_control(adev);
 
 	/* Ring Buffer base. [39:8] of 40-bit address of the beginning of the ring buffer*/
 	WREG32_SOC15(OSSSYS, 0, mmIH_RB_BASE, ih->gpu_addr >> 8);
@@ -162,7 +162,7 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
 	}
 	WREG32_SOC15(OSSSYS, 0, mmIH_DOORBELL_RPTR, ih_doorbell_rtpr);
 
-	adev->nbio_funcs->ih_doorbell_range(adev, ih->use_doorbell,
+	adev->nbio.funcs->ih_doorbell_range(adev, ih->use_doorbell,
 					    ih->doorbell_index);
 
 	tmp = RREG32_SOC15(OSSSYS, 0, mmIH_STORM_CLIENT_LIST_CNTL);
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c
index a56c93620e78..88efaecf9f70 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_reg_init.c
@@ -24,7 +24,6 @@
 #include "nv.h"
 
 #include "soc15_common.h"
-#include "soc15_hw_ip.h"
 #include "navi10_ip_offset.h"
 
 int navi10_reg_base_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c b/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c
index cadc7603ca41..a786d159e5e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi12_reg_init.c
@@ -24,7 +24,6 @@
 #include "nv.h"
 
 #include "soc15_common.h"
-#include "soc15_hw_ip.h"
 #include "navi12_ip_offset.h"
 
 int navi12_reg_base_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c b/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c
index 3b5f0f65e096..4ea1e8fbb601 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi14_reg_init.c
@@ -24,7 +24,6 @@
 #include "nv.h"
 
 #include "soc15_common.h"
-#include "soc15_hw_ip.h"
 #include "navi14_ip_offset.h"
 
 int navi14_reg_base_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
index c05d78d4efc6..f3a3fe746222 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.c
@@ -27,11 +27,21 @@
 #include "nbio/nbio_2_3_default.h"
 #include "nbio/nbio_2_3_offset.h"
 #include "nbio/nbio_2_3_sh_mask.h"
+#include <uapi/linux/kfd_ioctl.h>
 
 #define smnPCIE_CONFIG_CNTL	0x11180044
 #define smnCPM_CONTROL		0x11180460
 #define smnPCIE_CNTL2		0x11180070
 
+
+static void nbio_v2_3_remap_hdp_registers(struct amdgpu_device *adev)
+{
+	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_MEM_FLUSH_CNTL,
+		adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL);
+	WREG32_SOC15(NBIO, 0, mmREMAP_HDP_REG_FLUSH_CNTL,
+		adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_REG_FLUSH_CNTL);
+}
+
 static u32 nbio_v2_3_get_rev_id(struct amdgpu_device *adev)
 {
 	u32 tmp = RREG32_SOC15(NBIO, 0, mmRCC_DEV0_EPF0_STRAP0);
@@ -56,10 +66,9 @@ static void nbio_v2_3_hdp_flush(struct amdgpu_device *adev,
 				struct amdgpu_ring *ring)
 {
 	if (!ring || !ring->funcs->emit_wreg)
-		WREG32_SOC15_NO_KIQ(NBIO, 0, mmBIF_BX_PF_HDP_MEM_COHERENCY_FLUSH_CNTL, 0);
+		WREG32_NO_KIQ((adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 	else
-		amdgpu_ring_emit_wreg(ring, SOC15_REG_OFFSET(
-			NBIO, 0, mmBIF_BX_PF_HDP_MEM_COHERENCY_FLUSH_CNTL), 0);
+		amdgpu_ring_emit_wreg(ring, (adev->rmmio_remap.reg_offset + KFD_MMIO_REMAP_HDP_MEM_FLUSH_CNTL) >> 2, 0);
 }
 
 static u32 nbio_v2_3_get_memsize(struct amdgpu_device *adev)
@@ -311,7 +320,6 @@ static void nbio_v2_3_init_registers(struct amdgpu_device *adev)
 }
 
 const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
-	.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg,
 	.get_hdp_flush_req_offset = nbio_v2_3_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v2_3_get_hdp_flush_done_offset,
 	.get_pcie_index_offset = nbio_v2_3_get_pcie_index_offset,
@@ -331,4 +339,5 @@ const struct amdgpu_nbio_funcs nbio_v2_3_funcs = {
 	.ih_control = nbio_v2_3_ih_control,
 	.init_registers = nbio_v2_3_init_registers,
 	.detect_hw_virt = nbio_v2_3_detect_hw_virt,
+	.remap_hdp_registers = nbio_v2_3_remap_hdp_registers,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h
index 5ae52085f6b7..a43b60acf7f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v2_3.h
@@ -26,6 +26,7 @@
 
 #include "soc15_common.h"
 
+extern const struct nbio_hdp_flush_reg nbio_v2_3_hdp_flush_reg;
 extern const struct amdgpu_nbio_funcs nbio_v2_3_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
index 6590143c3f75..635d9e1fc0a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.c
@@ -226,7 +226,7 @@ static u32 nbio_v6_1_get_pcie_data_offset(struct amdgpu_device *adev)
 	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2);
 }
 
-static const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg = {
+const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg = {
 	.ref_and_mask_cp0 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP0_MASK,
 	.ref_and_mask_cp1 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP1_MASK,
 	.ref_and_mask_cp2 = BIF_BX_PF0_GPU_HDP_FLUSH_DONE__CP2_MASK,
@@ -277,7 +277,6 @@ static void nbio_v6_1_init_registers(struct amdgpu_device *adev)
 }
 
 const struct amdgpu_nbio_funcs nbio_v6_1_funcs = {
-	.hdp_flush_reg = &nbio_v6_1_hdp_flush_reg,
 	.get_hdp_flush_req_offset = nbio_v6_1_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v6_1_get_hdp_flush_done_offset,
 	.get_pcie_index_offset = nbio_v6_1_get_pcie_index_offset,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
index 0743a6f016f3..6dc743b73218 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v6_1.h
@@ -26,6 +26,7 @@
 
 #include "soc15_common.h"
 
+extern const struct nbio_hdp_flush_reg nbio_v6_1_hdp_flush_reg;
 extern const struct amdgpu_nbio_funcs nbio_v6_1_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
index 74eecb768a82..d6cbf26074bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.c
@@ -292,7 +292,6 @@ static void nbio_v7_0_init_registers(struct amdgpu_device *adev)
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_0_funcs = {
-	.hdp_flush_reg = &nbio_v7_0_hdp_flush_reg,
 	.get_hdp_flush_req_offset = nbio_v7_0_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v7_0_get_hdp_flush_done_offset,
 	.get_pcie_index_offset = nbio_v7_0_get_pcie_index_offset,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
index 508d549c5029..e7aefb252550 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_0.h
@@ -26,6 +26,7 @@
 
 #include "soc15_common.h"
 
+extern const struct nbio_hdp_flush_reg nbio_v7_0_hdp_flush_reg;
 extern const struct amdgpu_nbio_funcs nbio_v7_0_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 910fffced43b..0db458f9fafc 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -23,10 +23,12 @@
 #include "amdgpu.h"
 #include "amdgpu_atombios.h"
 #include "nbio_v7_4.h"
+#include "amdgpu_ras.h"
 
 #include "nbio/nbio_7_4_offset.h"
 #include "nbio/nbio_7_4_sh_mask.h"
 #include "nbio/nbio_7_4_0_smn.h"
+#include "ivsrcid/nbio/irqsrcs_nbif_7_4.h"
 #include <uapi/linux/kfd_ioctl.h>
 
 #define smnNBIF_MGCG_CTRL_LCLK	0x1013a21c
@@ -266,7 +268,7 @@ static u32 nbio_v7_4_get_pcie_data_offset(struct amdgpu_device *adev)
 	return SOC15_REG_OFFSET(NBIO, 0, mmPCIE_DATA2);
 }
 
-static const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg = {
+const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg = {
 	.ref_and_mask_cp0 = GPU_HDP_FLUSH_DONE__CP0_MASK,
 	.ref_and_mask_cp1 = GPU_HDP_FLUSH_DONE__CP1_MASK,
 	.ref_and_mask_cp2 = GPU_HDP_FLUSH_DONE__CP2_MASK,
@@ -306,17 +308,208 @@ static void nbio_v7_4_detect_hw_virt(struct amdgpu_device *adev)
 
 static void nbio_v7_4_init_registers(struct amdgpu_device *adev)
 {
-	uint32_t def, data;
 
-	def = data = RREG32_PCIE(smnPCIE_CI_CNTL);
-	data = REG_SET_FIELD(data, PCIE_CI_CNTL, CI_SLV_ORDERING_DIS, 1);
+}
 
-	if (def != data)
-		WREG32_PCIE(smnPCIE_CI_CNTL, data);
+static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device *adev)
+{
+	uint32_t bif_doorbell_intr_cntl;
+
+	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
+		BIF_DOORBELL_INT_CNTL, RAS_CNTLR_INTERRUPT_STATUS)) {
+		/* driver has to clear the interrupt status when bif ring is disabled */
+		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
+						BIF_DOORBELL_INT_CNTL,
+						RAS_CNTLR_INTERRUPT_CLEAR, 1);
+		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		amdgpu_ras_global_ras_isr(adev);
+	}
+}
+
+static void nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring(struct amdgpu_device *adev)
+{
+	uint32_t bif_doorbell_intr_cntl;
+
+	bif_doorbell_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL);
+	if (REG_GET_FIELD(bif_doorbell_intr_cntl,
+		BIF_DOORBELL_INT_CNTL, RAS_ATHUB_ERR_EVENT_INTERRUPT_STATUS)) {
+		/* driver has to clear the interrupt status when bif ring is disabled */
+		bif_doorbell_intr_cntl = REG_SET_FIELD(bif_doorbell_intr_cntl,
+						BIF_DOORBELL_INT_CNTL,
+						RAS_ATHUB_ERR_EVENT_INTERRUPT_CLEAR, 1);
+		WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+		amdgpu_ras_global_ras_isr(adev);
+	}
+}
+
+
+static int nbio_v7_4_set_ras_controller_irq_state(struct amdgpu_device *adev,
+						  struct amdgpu_irq_src *src,
+						  unsigned type,
+						  enum amdgpu_interrupt_state state)
+{
+	/* The ras_controller_irq enablement should be done in psp bl when it
+	 * tries to enable ras feature. Driver only need to set the correct interrupt
+	 * vector for bare-metal and sriov use case respectively
+	 */
+	uint32_t bif_intr_cntl;
+
+	bif_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL);
+	if (state == AMDGPU_IRQ_STATE_ENABLE) {
+		/* set interrupt vector select bit to 0 to select
+		 * vetcor 1 for bare metal case */
+		bif_intr_cntl = REG_SET_FIELD(bif_intr_cntl,
+					      BIF_INTR_CNTL,
+					      RAS_INTR_VEC_SEL, 0);
+		WREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL, bif_intr_cntl);
+	}
+
+	return 0;
+}
+
+static int nbio_v7_4_process_ras_controller_irq(struct amdgpu_device *adev,
+						struct amdgpu_irq_src *source,
+						struct amdgpu_iv_entry *entry)
+{
+	/* By design, the ih cookie for ras_controller_irq should be written
+	 * to BIFring instead of general iv ring. However, due to known bif ring
+	 * hw bug, it has to be disabled. There is no chance the process function
+	 * will be involked. Just left it as a dummy one.
+	 */
+	return 0;
+}
+
+static int nbio_v7_4_set_ras_err_event_athub_irq_state(struct amdgpu_device *adev,
+						       struct amdgpu_irq_src *src,
+						       unsigned type,
+						       enum amdgpu_interrupt_state state)
+{
+	/* The ras_controller_irq enablement should be done in psp bl when it
+	 * tries to enable ras feature. Driver only need to set the correct interrupt
+	 * vector for bare-metal and sriov use case respectively
+	 */
+	uint32_t bif_intr_cntl;
+
+	bif_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL);
+	if (state == AMDGPU_IRQ_STATE_ENABLE) {
+		/* set interrupt vector select bit to 0 to select
+		 * vetcor 1 for bare metal case */
+		bif_intr_cntl = REG_SET_FIELD(bif_intr_cntl,
+					      BIF_INTR_CNTL,
+					      RAS_INTR_VEC_SEL, 0);
+		WREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL, bif_intr_cntl);
+	}
+
+	return 0;
+}
+
+static int nbio_v7_4_process_err_event_athub_irq(struct amdgpu_device *adev,
+						 struct amdgpu_irq_src *source,
+						 struct amdgpu_iv_entry *entry)
+{
+	/* By design, the ih cookie for err_event_athub_irq should be written
+	 * to BIFring instead of general iv ring. However, due to known bif ring
+	 * hw bug, it has to be disabled. There is no chance the process function
+	 * will be involked. Just left it as a dummy one.
+	 */
+	return 0;
+}
+
+static const struct amdgpu_irq_src_funcs nbio_v7_4_ras_controller_irq_funcs = {
+	.set = nbio_v7_4_set_ras_controller_irq_state,
+	.process = nbio_v7_4_process_ras_controller_irq,
+};
+
+static const struct amdgpu_irq_src_funcs nbio_v7_4_ras_err_event_athub_irq_funcs = {
+	.set = nbio_v7_4_set_ras_err_event_athub_irq_state,
+	.process = nbio_v7_4_process_err_event_athub_irq,
+};
+
+static int nbio_v7_4_init_ras_controller_interrupt (struct amdgpu_device *adev)
+{
+	int r;
+
+	/* init the irq funcs */
+	adev->nbio.ras_controller_irq.funcs =
+		&nbio_v7_4_ras_controller_irq_funcs;
+	adev->nbio.ras_controller_irq.num_types = 1;
+
+	/* register ras controller interrupt */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF,
+			      NBIF_7_4__SRCID__RAS_CONTROLLER_INTERRUPT,
+			      &adev->nbio.ras_controller_irq);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+static int nbio_v7_4_init_ras_err_event_athub_interrupt (struct amdgpu_device *adev)
+{
+
+	int r;
+
+	/* init the irq funcs */
+	adev->nbio.ras_err_event_athub_irq.funcs =
+		&nbio_v7_4_ras_err_event_athub_irq_funcs;
+	adev->nbio.ras_err_event_athub_irq.num_types = 1;
+
+	/* register ras err event athub interrupt */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_BIF,
+			      NBIF_7_4__SRCID__ERREVENT_ATHUB_INTERRUPT,
+			      &adev->nbio.ras_err_event_athub_irq);
+	if (r)
+		return r;
+
+	return 0;
+}
+
+static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
+					void *ras_error_status)
+{
+	uint32_t global_sts, central_sts, int_eoi;
+	uint32_t corr, fatal, non_fatal;
+	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
+
+	global_sts = RREG32_PCIE(smnRAS_GLOBAL_STATUS_LO);
+	corr = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO, ParityErrCorr);
+	fatal = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO, ParityErrFatal);
+	non_fatal = REG_GET_FIELD(global_sts, RAS_GLOBAL_STATUS_LO,
+				ParityErrNonFatal);
+
+	if (corr)
+		err_data->ce_count++;
+	if (fatal)
+		err_data->ue_count++;
+
+	if (corr || fatal || non_fatal) {
+		central_sts = RREG32_PCIE(smnBIFL_RAS_CENTRAL_STATUS);
+		/* clear error status register */
+		WREG32_PCIE(smnRAS_GLOBAL_STATUS_LO, global_sts);
+
+		if (REG_GET_FIELD(central_sts, BIFL_RAS_CENTRAL_STATUS,
+				BIFL_RasContller_Intr_Recv)) {
+			/* clear interrupt status register */
+			WREG32_PCIE(smnBIFL_RAS_CENTRAL_STATUS, central_sts);
+			int_eoi = RREG32_PCIE(smnIOHC_INTERRUPT_EOI);
+			int_eoi = REG_SET_FIELD(int_eoi,
+					IOHC_INTERRUPT_EOI, SMI_EOI, 1);
+			WREG32_PCIE(smnIOHC_INTERRUPT_EOI, int_eoi);
+		}
+	}
+}
+
+static void nbio_v7_4_enable_doorbell_interrupt(struct amdgpu_device *adev,
+						bool enable)
+{
+	WREG32_FIELD15(NBIO, 0, BIF_DOORBELL_INT_CNTL,
+		       DOORBELL_INTERRUPT_DISABLE, enable ? 0 : 1);
 }
 
 const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
-	.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg,
 	.get_hdp_flush_req_offset = nbio_v7_4_get_hdp_flush_req_offset,
 	.get_hdp_flush_done_offset = nbio_v7_4_get_hdp_flush_done_offset,
 	.get_pcie_index_offset = nbio_v7_4_get_pcie_index_offset,
@@ -330,6 +523,7 @@ const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
 	.enable_doorbell_aperture = nbio_v7_4_enable_doorbell_aperture,
 	.enable_doorbell_selfring_aperture = nbio_v7_4_enable_doorbell_selfring_aperture,
 	.ih_doorbell_range = nbio_v7_4_ih_doorbell_range,
+	.enable_doorbell_interrupt = nbio_v7_4_enable_doorbell_interrupt,
 	.update_medium_grain_clock_gating = nbio_v7_4_update_medium_grain_clock_gating,
 	.update_medium_grain_light_sleep = nbio_v7_4_update_medium_grain_light_sleep,
 	.get_clockgating_state = nbio_v7_4_get_clockgating_state,
@@ -337,4 +531,10 @@ const struct amdgpu_nbio_funcs nbio_v7_4_funcs = {
 	.init_registers = nbio_v7_4_init_registers,
 	.detect_hw_virt = nbio_v7_4_detect_hw_virt,
 	.remap_hdp_registers = nbio_v7_4_remap_hdp_registers,
+	.handle_ras_controller_intr_no_bifring = nbio_v7_4_handle_ras_controller_intr_no_bifring,
+	.handle_ras_err_event_athub_intr_no_bifring = nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring,
+	.init_ras_controller_interrupt = nbio_v7_4_init_ras_controller_interrupt,
+	.init_ras_err_event_athub_interrupt = nbio_v7_4_init_ras_err_event_athub_interrupt,
+	.query_ras_error_count = nbio_v7_4_query_ras_error_count,
+	.ras_late_init = amdgpu_nbio_ras_late_init,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h
index c442865bac4f..b1ac82872752 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.h
@@ -26,6 +26,7 @@
 
 #include "soc15_common.h"
 
+extern const struct nbio_hdp_flush_reg nbio_v7_4_hdp_flush_reg;
 extern const struct amdgpu_nbio_funcs nbio_v7_4_funcs;
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nv.c b/drivers/gpu/drm/amd/amdgpu/nv.c
index de9b995b65b1..0ba66bef5746 100644
--- a/drivers/gpu/drm/amd/amdgpu/nv.c
+++ b/drivers/gpu/drm/amd/amdgpu/nv.c
@@ -40,12 +40,14 @@
 #include "gc/gc_10_1_0_sh_mask.h"
 #include "hdp/hdp_5_0_0_offset.h"
 #include "hdp/hdp_5_0_0_sh_mask.h"
+#include "smuio/smuio_11_0_0_offset.h"
 
 #include "soc15.h"
 #include "soc15_common.h"
 #include "gmc_v10_0.h"
 #include "gfxhub_v2_0.h"
 #include "mmhub_v2_0.h"
+#include "nbio_v2_3.h"
 #include "nv.h"
 #include "navi10_ih.h"
 #include "gfx_v10_0.h"
@@ -53,6 +55,7 @@
 #include "vcn_v2_0.h"
 #include "dce_virtual.h"
 #include "mes_v10_1.h"
+#include "mxgpu_nv.h"
 
 static const struct amd_ip_funcs nv_common_ip_funcs;
 
@@ -63,8 +66,8 @@ static u32 nv_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags, address, data;
 	u32 r;
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, reg);
@@ -78,8 +81,8 @@ static void nv_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 {
 	unsigned long flags, address, data;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, reg);
@@ -119,7 +122,7 @@ static void nv_didt_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 
 static u32 nv_get_config_memsize(struct amdgpu_device *adev)
 {
-	return adev->nbio_funcs->get_memsize(adev);
+	return adev->nbio.funcs->get_memsize(adev);
 }
 
 static u32 nv_get_xclk(struct amdgpu_device *adev)
@@ -154,8 +157,27 @@ static bool nv_read_disabled_bios(struct amdgpu_device *adev)
 static bool nv_read_bios_from_rom(struct amdgpu_device *adev,
 				  u8 *bios, u32 length_bytes)
 {
-	/* TODO: will implement it when SMU header is available */
-	return false;
+	u32 *dw_ptr;
+	u32 i, length_dw;
+
+	if (bios == NULL)
+		return false;
+	if (length_bytes == 0)
+		return false;
+	/* APU vbios image is part of sbios image */
+	if (adev->flags & AMD_IS_APU)
+		return false;
+
+	dw_ptr = (u32 *)bios;
+	length_dw = ALIGN(length_bytes, 4) / 4;
+
+	/* set rom index to 0 */
+	WREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_INDEX), 0);
+	/* read out the rom data */
+	for (i = 0; i < length_dw; i++)
+		dw_ptr[i] = RREG32(SOC15_REG_OFFSET(SMUIO, 0, mmROM_DATA));
+
+	return true;
 }
 
 static struct soc15_allowed_register_entry nv_allowed_read_registers[] = {
@@ -176,6 +198,7 @@ static struct soc15_allowed_register_entry nv_allowed_read_registers[] = {
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
 	{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
@@ -279,7 +302,7 @@ static int nv_asic_mode1_reset(struct amdgpu_device *adev)
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
-		u32 memsize = adev->nbio_funcs->get_memsize(adev);
+		u32 memsize = adev->nbio.funcs->get_memsize(adev);
 
 		if (memsize != 0xffffffff)
 			break;
@@ -296,7 +319,7 @@ nv_asic_reset_method(struct amdgpu_device *adev)
 {
 	struct smu_context *smu = &adev->smu;
 
-	if (smu_baco_is_support(smu))
+	if (!amdgpu_sriov_vf(adev) && smu_baco_is_support(smu))
 		return AMD_RESET_METHOD_BACO;
 	else
 		return AMD_RESET_METHOD_MODE1;
@@ -368,8 +391,8 @@ static void nv_program_aspm(struct amdgpu_device *adev)
 static void nv_enable_doorbell_aperture(struct amdgpu_device *adev,
 					bool enable)
 {
-	adev->nbio_funcs->enable_doorbell_aperture(adev, enable);
-	adev->nbio_funcs->enable_doorbell_selfring_aperture(adev, enable);
+	adev->nbio.funcs->enable_doorbell_aperture(adev, enable);
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable);
 }
 
 static const struct amdgpu_ip_block_version nv_common_ip_block =
@@ -423,9 +446,13 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
-	adev->nbio_funcs = &nbio_v2_3_funcs;
+	adev->nbio.funcs = &nbio_v2_3_funcs;
+	adev->nbio.hdp_flush_reg = &nbio_v2_3_hdp_flush_reg;
 
-	adev->nbio_funcs->detect_hw_virt(adev);
+	adev->nbio.funcs->detect_hw_virt(adev);
+
+	if (amdgpu_sriov_vf(adev))
+		adev->virt.ops = &xgpu_nv_virt_ops;
 
 	switch (adev->asic_type) {
 	case CHIP_NAVI10:
@@ -435,7 +462,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
-		    is_support_sw_smu(adev))
+		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -446,7 +473,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
-		    is_support_sw_smu(adev))
+		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		if (adev->enable_mes)
@@ -458,7 +485,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &navi10_ih_ip_block);
 		amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP &&
-		    is_support_sw_smu(adev))
+		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
@@ -469,7 +496,7 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gfx_v10_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v5_0_ip_block);
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT &&
-		    is_support_sw_smu(adev))
+		    is_support_sw_smu(adev) && !amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &vcn_v2_0_ip_block);
 		break;
@@ -482,12 +509,12 @@ int nv_set_ip_blocks(struct amdgpu_device *adev)
 
 static uint32_t nv_get_rev_id(struct amdgpu_device *adev)
 {
-	return adev->nbio_funcs->get_rev_id(adev);
+	return adev->nbio.funcs->get_rev_id(adev);
 }
 
 static void nv_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring)
 {
-	adev->nbio_funcs->hdp_flush(adev, ring);
+	adev->nbio.funcs->hdp_flush(adev, ring);
 }
 
 static void nv_invalidate_hdp(struct amdgpu_device *adev,
@@ -532,6 +559,16 @@ static bool nv_need_reset_on_init(struct amdgpu_device *adev)
 	return false;
 }
 
+static uint64_t nv_get_pcie_replay_count(struct amdgpu_device *adev)
+{
+
+	/* TODO
+	 * dummy implement for pcie_replay_count sysfs interface
+	 * */
+
+	return 0;
+}
+
 static void nv_init_doorbell_index(struct amdgpu_device *adev)
 {
 	adev->doorbell_index.kiq = AMDGPU_NAVI10_DOORBELL_KIQ;
@@ -579,12 +616,16 @@ static const struct amdgpu_asic_funcs nv_asic_funcs =
 	.need_full_reset = &nv_need_full_reset,
 	.get_pcie_usage = &nv_get_pcie_usage,
 	.need_reset_on_init = &nv_need_reset_on_init,
+	.get_pcie_replay_count = &nv_get_pcie_replay_count,
 };
 
 static int nv_common_early_init(void *handle)
 {
+#define MMIO_REG_HOLE_OFFSET (0x80000 - PAGE_SIZE)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	adev->rmmio_remap.reg_offset = MMIO_REG_HOLE_OFFSET;
+	adev->rmmio_remap.bus_addr = adev->rmmio_base + MMIO_REG_HOLE_OFFSET;
 	adev->smc_rreg = NULL;
 	adev->smc_wreg = NULL;
 	adev->pcie_rreg = &nv_pcie_rreg;
@@ -667,16 +708,31 @@ static int nv_common_early_init(void *handle)
 		return -EINVAL;
 	}
 
+	if (amdgpu_sriov_vf(adev)) {
+		amdgpu_virt_init_setting(adev);
+		xgpu_nv_mailbox_set_irq_funcs(adev);
+	}
+
 	return 0;
 }
 
 static int nv_common_late_init(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (amdgpu_sriov_vf(adev))
+		xgpu_nv_mailbox_get_irq(adev);
+
 	return 0;
 }
 
 static int nv_common_sw_init(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	if (amdgpu_sriov_vf(adev))
+		xgpu_nv_mailbox_add_irq_id(adev);
+
 	return 0;
 }
 
@@ -694,7 +750,13 @@ static int nv_common_hw_init(void *handle)
 	/* enable aspm */
 	nv_program_aspm(adev);
 	/* setup nbio registers */
-	adev->nbio_funcs->init_registers(adev);
+	adev->nbio.funcs->init_registers(adev);
+	/* remap HDP registers to a hole in mmio space,
+	 * for the purpose of expose those registers
+	 * to process space
+	 */
+	if (adev->nbio.funcs->remap_hdp_registers)
+		adev->nbio.funcs->remap_hdp_registers(adev);
 	/* enable the doorbell aperture */
 	nv_enable_doorbell_aperture(adev, true);
 
@@ -856,9 +918,9 @@ static int nv_common_set_clockgating_state(void *handle,
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
-		adev->nbio_funcs->update_medium_grain_clock_gating(adev,
+		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		adev->nbio_funcs->update_medium_grain_light_sleep(adev,
+		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		nv_update_hdp_mem_power_gating(adev,
 				   state == AMD_CG_STATE_GATE ? true : false);
@@ -886,7 +948,7 @@ static void nv_common_get_clockgating_state(void *handle, u32 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	adev->nbio_funcs->get_clockgating_state(adev, flags);
+	adev->nbio.funcs->get_clockgating_state(adev, flags);
 
 	/* AMD_CG_SUPPORT_HDP_MGCG */
 	tmp = RREG32_SOC15(HDP, 0, mmHDP_CLK_CNTL);
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
index 5d95e614369a..b345e69ba246 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v10_0.c
@@ -40,6 +40,9 @@
 MODULE_FIRMWARE("amdgpu/raven_asd.bin");
 MODULE_FIRMWARE("amdgpu/picasso_asd.bin");
 MODULE_FIRMWARE("amdgpu/raven2_asd.bin");
+MODULE_FIRMWARE("amdgpu/picasso_ta.bin");
+MODULE_FIRMWARE("amdgpu/raven2_ta.bin");
+MODULE_FIRMWARE("amdgpu/raven_ta.bin");
 
 static int psp_v10_0_init_microcode(struct psp_context *psp)
 {
@@ -48,7 +51,7 @@ static int psp_v10_0_init_microcode(struct psp_context *psp)
 	char fw_name[30];
 	int err = 0;
 	const struct psp_firmware_header_v1_0 *hdr;
-
+	const struct ta_firmware_header_v1_0 *ta_hdr;
 	DRM_DEBUG("\n");
 
 	switch (adev->asic_type) {
@@ -79,7 +82,45 @@ static int psp_v10_0_init_microcode(struct psp_context *psp)
 	adev->psp.asd_start_addr = (uint8_t *)hdr +
 				le32_to_cpu(hdr->header.ucode_array_offset_bytes);
 
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
+	err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
+	if (err) {
+		release_firmware(adev->psp.ta_fw);
+		adev->psp.ta_fw = NULL;
+		dev_info(adev->dev,
+			 "psp v10.0: Failed to load firmware \"%s\"\n",
+			 fw_name);
+	} else {
+		err = amdgpu_ucode_validate(adev->psp.ta_fw);
+		if (err)
+			goto out2;
+
+		ta_hdr = (const struct ta_firmware_header_v1_0 *)
+				 adev->psp.ta_fw->data;
+		adev->psp.ta_hdcp_ucode_version =
+			le32_to_cpu(ta_hdr->ta_hdcp_ucode_version);
+		adev->psp.ta_hdcp_ucode_size =
+			le32_to_cpu(ta_hdr->ta_hdcp_size_bytes);
+		adev->psp.ta_hdcp_start_addr =
+			(uint8_t *)ta_hdr +
+			le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes);
+
+		adev->psp.ta_fw_version = le32_to_cpu(ta_hdr->header.ucode_version);
+
+		adev->psp.ta_dtm_ucode_version =
+			le32_to_cpu(ta_hdr->ta_dtm_ucode_version);
+		adev->psp.ta_dtm_ucode_size =
+			le32_to_cpu(ta_hdr->ta_dtm_size_bytes);
+		adev->psp.ta_dtm_start_addr =
+			(uint8_t *)adev->psp.ta_hdcp_start_addr +
+			le32_to_cpu(ta_hdr->ta_dtm_offset_bytes);
+	}
+
 	return 0;
+
+out2:
+	release_firmware(adev->psp.ta_fw);
+	adev->psp.ta_fw = NULL;
 out:
 	if (err) {
 		dev_err(adev->dev,
@@ -228,6 +269,7 @@ static int psp_v10_0_cmd_submit(struct psp_context *psp,
 	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
 	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
 	write_frame->fence_value = index;
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	/* Update the write Pointer in DWORDs */
 	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
index 10166104b8a3..ffeaa2f5588d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c
@@ -49,6 +49,7 @@ MODULE_FIRMWARE("amdgpu/navi12_sos.bin");
 MODULE_FIRMWARE("amdgpu/navi12_asd.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_sos.bin");
 MODULE_FIRMWARE("amdgpu/arcturus_asd.bin");
+MODULE_FIRMWARE("amdgpu/arcturus_ta.bin");
 
 /* address block */
 #define smnMP1_FIRMWARE_FLAGS		0x3010024
@@ -57,6 +58,8 @@ MODULE_FIRMWARE("amdgpu/arcturus_asd.bin");
 #define mmRLC_GPM_UCODE_DATA_NV10	0x5b62
 #define mmSDMA0_UCODE_ADDR_NV10		0x5880
 #define mmSDMA0_UCODE_DATA_NV10		0x5881
+/* memory training timeout define */
+#define MEM_TRAIN_SEND_MSG_TIMEOUT_US	3000000
 
 static int psp_v11_0_init_microcode(struct psp_context *psp)
 {
@@ -155,6 +158,7 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+	case CHIP_ARCTURUS:
 		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name);
 		err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev);
 		if (err) {
@@ -182,7 +186,6 @@ static int psp_v11_0_init_microcode(struct psp_context *psp)
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
-	case CHIP_ARCTURUS:
 		break;
 	default:
 		BUG();
@@ -205,18 +208,26 @@ out:
 	return err;
 }
 
+static bool psp_v11_0_is_sos_alive(struct psp_context *psp)
+{
+	struct amdgpu_device *adev = psp->adev;
+	uint32_t sol_reg;
+
+	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
+
+	return sol_reg != 0x0;
+}
+
 static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 {
 	int ret;
 	uint32_t psp_gfxdrv_command_reg = 0;
 	struct amdgpu_device *adev = psp->adev;
-	uint32_t sol_reg;
 
 	/* Check tOS sign of life register to confirm sys driver and sOS
 	 * are already been loaded.
 	 */
-	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
-	if (sol_reg) {
+	if (psp_v11_0_is_sos_alive(psp)) {
 		psp->sos_fw_version = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_58);
 		dev_info(adev->dev, "sos fw version = 0x%x.\n", psp->sos_fw_version);
 		return 0;
@@ -233,7 +244,7 @@ static int psp_v11_0_bootloader_load_kdb(struct psp_context *psp)
 	/* Copy PSP KDB binary to memory */
 	memcpy(psp->fw_pri_buf, psp->kdb_start_addr, psp->kdb_bin_size);
 
-	/* Provide the sys driver to bootloader */
+	/* Provide the PSP KDB to bootloader */
 	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36,
 	       (uint32_t)(psp->fw_pri_mc_addr >> 20));
 	psp_gfxdrv_command_reg = PSP_BL__LOAD_KEY_DATABASE;
@@ -252,13 +263,11 @@ static int psp_v11_0_bootloader_load_sysdrv(struct psp_context *psp)
 	int ret;
 	uint32_t psp_gfxdrv_command_reg = 0;
 	struct amdgpu_device *adev = psp->adev;
-	uint32_t sol_reg;
 
 	/* Check sOS sign of life register to confirm sys driver and sOS
 	 * are already been loaded.
 	 */
-	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
-	if (sol_reg) {
+	if (psp_v11_0_is_sos_alive(psp)) {
 		psp->sos_fw_version = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_58);
 		dev_info(adev->dev, "sos fw version = 0x%x.\n", psp->sos_fw_version);
 		return 0;
@@ -296,13 +305,11 @@ static int psp_v11_0_bootloader_load_sos(struct psp_context *psp)
 	int ret;
 	unsigned int psp_gfxdrv_command_reg = 0;
 	struct amdgpu_device *adev = psp->adev;
-	uint32_t sol_reg;
 
 	/* Check sOS sign of life register to confirm sys driver and sOS
 	 * are already been loaded.
 	 */
-	sol_reg = RREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_81);
-	if (sol_reg)
+	if (psp_v11_0_is_sos_alive(psp))
 		return 0;
 
 	/* Wait for bootloader to signify that is ready having bit 31 of C2PMSG_35 set to 1 */
@@ -398,6 +405,34 @@ static bool psp_v11_0_support_vmr_ring(struct psp_context *psp)
 	return false;
 }
 
+static int psp_v11_0_ring_stop(struct psp_context *psp,
+			      enum psp_ring_type ring_type)
+{
+	int ret = 0;
+	struct amdgpu_device *adev = psp->adev;
+
+	/* Write the ring destroy command*/
+	if (psp_v11_0_support_vmr_ring(psp))
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
+				     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING);
+	else
+		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64,
+				     GFX_CTRL_CMD_ID_DESTROY_RINGS);
+
+	/* there might be handshake issue with hardware which needs delay */
+	mdelay(20);
+
+	/* Wait for response flag (bit 31) */
+	if (psp_v11_0_support_vmr_ring(psp))
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
+				   0x80000000, 0x80000000, false);
+	else
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x80000000, false);
+
+	return ret;
+}
+
 static int psp_v11_0_ring_create(struct psp_context *psp,
 				enum psp_ring_type ring_type)
 {
@@ -407,6 +442,12 @@ static int psp_v11_0_ring_create(struct psp_context *psp,
 	struct amdgpu_device *adev = psp->adev;
 
 	if (psp_v11_0_support_vmr_ring(psp)) {
+		ret = psp_v11_0_ring_stop(psp, ring_type);
+		if (ret) {
+			DRM_ERROR("psp_v11_0_ring_stop_sriov failed!\n");
+			return ret;
+		}
+
 		/* Write low address of the ring to C2PMSG_102 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_102, psp_ring_reg);
@@ -426,6 +467,14 @@ static int psp_v11_0_ring_create(struct psp_context *psp,
 				   0x80000000, 0x8000FFFF, false);
 
 	} else {
+		/* Wait for sOS ready for ring creation */
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
+				   0x80000000, 0x80000000, false);
+		if (ret) {
+			DRM_ERROR("Failed to wait for sOS ready for ring creation\n");
+			return ret;
+		}
+
 		/* Write low address of the ring to C2PMSG_69 */
 		psp_ring_reg = lower_32_bits(ring->ring_mem_mc_addr);
 		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_69, psp_ring_reg);
@@ -451,33 +500,6 @@ static int psp_v11_0_ring_create(struct psp_context *psp,
 	return ret;
 }
 
-static int psp_v11_0_ring_stop(struct psp_context *psp,
-			      enum psp_ring_type ring_type)
-{
-	int ret = 0;
-	struct amdgpu_device *adev = psp->adev;
-
-	/* Write the ring destroy command*/
-	if (psp_v11_0_support_vmr_ring(psp))
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_101,
-				     GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING);
-	else
-		WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_64,
-				     GFX_CTRL_CMD_ID_DESTROY_RINGS);
-
-	/* there might be handshake issue with hardware which needs delay */
-	mdelay(20);
-
-	/* Wait for response flag (bit 31) */
-	if (psp_v11_0_support_vmr_ring(psp))
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_101),
-				   0x80000000, 0x80000000, false);
-	else
-		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_64),
-				   0x80000000, 0x80000000, false);
-
-	return ret;
-}
 
 static int psp_v11_0_ring_destroy(struct psp_context *psp,
 				 enum psp_ring_type ring_type)
@@ -541,6 +563,7 @@ static int psp_v11_0_cmd_submit(struct psp_context *psp,
 	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
 	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
 	write_frame->fence_value = index;
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	/* Update the write Pointer in DWORDs */
 	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
@@ -889,6 +912,162 @@ static int psp_v11_0_rlc_autoload_start(struct psp_context *psp)
 	return psp_rlc_autoload_start(psp);
 }
 
+static int psp_v11_0_memory_training_send_msg(struct psp_context *psp, int msg)
+{
+	int ret;
+	int i;
+	uint32_t data_32;
+	int max_wait;
+	struct amdgpu_device *adev = psp->adev;
+
+	data_32 = (psp->mem_train_ctx.c2p_train_data_offset >> 20);
+	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_36, data_32);
+	WREG32_SOC15(MP0, 0, mmMP0_SMN_C2PMSG_35, msg);
+
+	max_wait = MEM_TRAIN_SEND_MSG_TIMEOUT_US / adev->usec_timeout;
+	for (i = 0; i < max_wait; i++) {
+		ret = psp_wait_for(psp, SOC15_REG_OFFSET(MP0, 0, mmMP0_SMN_C2PMSG_35),
+				   0x80000000, 0x80000000, false);
+		if (ret == 0)
+			break;
+	}
+	if (i < max_wait)
+		ret = 0;
+	else
+		ret = -ETIME;
+
+	DRM_DEBUG("training %s %s, cost %d @ %d ms\n",
+		  (msg == PSP_BL__DRAM_SHORT_TRAIN) ? "short" : "long",
+		  (ret == 0) ? "succeed" : "failed",
+		  i, adev->usec_timeout/1000);
+	return ret;
+}
+
+static void psp_v11_0_memory_training_fini(struct psp_context *psp)
+{
+	struct psp_memory_training_context *ctx = &psp->mem_train_ctx;
+
+	ctx->init = PSP_MEM_TRAIN_NOT_SUPPORT;
+	kfree(ctx->sys_cache);
+	ctx->sys_cache = NULL;
+}
+
+static int psp_v11_0_memory_training_init(struct psp_context *psp)
+{
+	int ret;
+	struct psp_memory_training_context *ctx = &psp->mem_train_ctx;
+
+	if (ctx->init != PSP_MEM_TRAIN_RESERVE_SUCCESS) {
+		DRM_DEBUG("memory training is not supported!\n");
+		return 0;
+	}
+
+	ctx->sys_cache = kzalloc(ctx->train_data_size, GFP_KERNEL);
+	if (ctx->sys_cache == NULL) {
+		DRM_ERROR("alloc mem_train_ctx.sys_cache failed!\n");
+		ret = -ENOMEM;
+		goto Err_out;
+	}
+
+	DRM_DEBUG("train_data_size:%llx,p2c_train_data_offset:%llx,c2p_train_data_offset:%llx.\n",
+		  ctx->train_data_size,
+		  ctx->p2c_train_data_offset,
+		  ctx->c2p_train_data_offset);
+	ctx->init = PSP_MEM_TRAIN_INIT_SUCCESS;
+	return 0;
+
+Err_out:
+	psp_v11_0_memory_training_fini(psp);
+	return ret;
+}
+
+/*
+ * save and restore proces
+ */
+static int psp_v11_0_memory_training(struct psp_context *psp, uint32_t ops)
+{
+	int ret;
+	uint32_t p2c_header[4];
+	struct psp_memory_training_context *ctx = &psp->mem_train_ctx;
+	uint32_t *pcache = (uint32_t*)ctx->sys_cache;
+
+	if (ctx->init == PSP_MEM_TRAIN_NOT_SUPPORT) {
+		DRM_DEBUG("Memory training is not supported.\n");
+		return 0;
+	} else if (ctx->init != PSP_MEM_TRAIN_INIT_SUCCESS) {
+		DRM_ERROR("Memory training initialization failure.\n");
+		return -EINVAL;
+	}
+
+	if (psp_v11_0_is_sos_alive(psp)) {
+		DRM_DEBUG("SOS is alive, skip memory training.\n");
+		return 0;
+	}
+
+	amdgpu_device_vram_access(psp->adev, ctx->p2c_train_data_offset, p2c_header, sizeof(p2c_header), false);
+	DRM_DEBUG("sys_cache[%08x,%08x,%08x,%08x] p2c_header[%08x,%08x,%08x,%08x]\n",
+		  pcache[0], pcache[1], pcache[2], pcache[3],
+		  p2c_header[0], p2c_header[1], p2c_header[2], p2c_header[3]);
+
+	if (ops & PSP_MEM_TRAIN_SEND_SHORT_MSG) {
+		DRM_DEBUG("Short training depends on restore.\n");
+		ops |= PSP_MEM_TRAIN_RESTORE;
+	}
+
+	if ((ops & PSP_MEM_TRAIN_RESTORE) &&
+	    pcache[0] != MEM_TRAIN_SYSTEM_SIGNATURE) {
+		DRM_DEBUG("sys_cache[0] is invalid, restore depends on save.\n");
+		ops |= PSP_MEM_TRAIN_SAVE;
+	}
+
+	if (p2c_header[0] == MEM_TRAIN_SYSTEM_SIGNATURE &&
+	    !(pcache[0] == MEM_TRAIN_SYSTEM_SIGNATURE &&
+	      pcache[3] == p2c_header[3])) {
+		DRM_DEBUG("sys_cache is invalid or out-of-date, need save training data to sys_cache.\n");
+		ops |= PSP_MEM_TRAIN_SAVE;
+	}
+
+	if ((ops & PSP_MEM_TRAIN_SAVE) &&
+	    p2c_header[0] != MEM_TRAIN_SYSTEM_SIGNATURE) {
+		DRM_DEBUG("p2c_header[0] is invalid, save depends on long training.\n");
+		ops |= PSP_MEM_TRAIN_SEND_LONG_MSG;
+	}
+
+	if (ops & PSP_MEM_TRAIN_SEND_LONG_MSG) {
+		ops &= ~PSP_MEM_TRAIN_SEND_SHORT_MSG;
+		ops |= PSP_MEM_TRAIN_SAVE;
+	}
+
+	DRM_DEBUG("Memory training ops:%x.\n", ops);
+
+	if (ops & PSP_MEM_TRAIN_SEND_LONG_MSG) {
+		ret = psp_v11_0_memory_training_send_msg(psp, PSP_BL__DRAM_LONG_TRAIN);
+		if (ret) {
+			DRM_ERROR("Send long training msg failed.\n");
+			return ret;
+		}
+	}
+
+	if (ops & PSP_MEM_TRAIN_SAVE) {
+		amdgpu_device_vram_access(psp->adev, ctx->p2c_train_data_offset, ctx->sys_cache, ctx->train_data_size, false);
+	}
+
+	if (ops & PSP_MEM_TRAIN_RESTORE) {
+		amdgpu_device_vram_access(psp->adev, ctx->c2p_train_data_offset, ctx->sys_cache, ctx->train_data_size, true);
+	}
+
+	if (ops & PSP_MEM_TRAIN_SEND_SHORT_MSG) {
+		ret = psp_v11_0_memory_training_send_msg(psp, (amdgpu_force_long_training > 0) ?
+							 PSP_BL__DRAM_LONG_TRAIN : PSP_BL__DRAM_SHORT_TRAIN);
+		if (ret) {
+			DRM_ERROR("send training msg failed.\n");
+			return ret;
+		}
+	}
+	ctx->training_cnt++;
+	return 0;
+}
+
 static const struct psp_funcs psp_v11_0_funcs = {
 	.init_microcode = psp_v11_0_init_microcode,
 	.bootloader_load_kdb = psp_v11_0_bootloader_load_kdb,
@@ -909,6 +1088,9 @@ static const struct psp_funcs psp_v11_0_funcs = {
 	.ras_trigger_error = psp_v11_0_ras_trigger_error,
 	.ras_cure_posion = psp_v11_0_ras_cure_posion,
 	.rlc_autoload_start = psp_v11_0_rlc_autoload_start,
+	.mem_training_init = psp_v11_0_memory_training_init,
+	.mem_training_fini = psp_v11_0_memory_training_fini,
+	.mem_training = psp_v11_0_memory_training,
 };
 
 void psp_v11_0_set_psp_funcs(struct psp_context *psp)
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
index c72e43f8e0be..8f553f6f92d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v12_0.c
@@ -378,6 +378,7 @@ static int psp_v12_0_cmd_submit(struct psp_context *psp,
 	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
 	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
 	write_frame->fence_value = index;
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	/* Update the write Pointer in DWORDs */
 	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
index d2c727f6a8bd..fdc00938327b 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/psp_v3_1.c
@@ -454,6 +454,7 @@ static int psp_v3_1_cmd_submit(struct psp_context *psp,
 	write_frame->fence_addr_hi = upper_32_bits(fence_mc_addr);
 	write_frame->fence_addr_lo = lower_32_bits(fence_mc_addr);
 	write_frame->fence_value = index;
+	amdgpu_asic_flush_hdp(adev, NULL);
 
 	/* Update the write Pointer in DWORDs */
 	psp_write_ptr_reg = (psp_write_ptr_reg + rb_frame_size_dw) % ring_size_dw;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 78452cf0115d..4ef4d31f5231 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -254,6 +254,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4_3[] = {
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000),
 	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0),
+	SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000)
 };
 
 static u32 sdma_v4_0_get_reg_offset(struct amdgpu_device *adev,
@@ -746,13 +747,13 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 ref_and_mask = 0;
-	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
+	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
 
 	ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0 << ring->me;
 
 	sdma_v4_0_wait_reg_mem(ring, 0, 1,
-			       adev->nbio_funcs->get_hdp_flush_done_offset(adev),
-			       adev->nbio_funcs->get_hdp_flush_req_offset(adev),
+			       adev->nbio.funcs->get_hdp_flush_done_offset(adev),
+			       adev->nbio.funcs->get_hdp_flush_req_offset(adev),
 			       ref_and_mask, ref_and_mask, 10);
 }
 
@@ -1690,102 +1691,17 @@ static int sdma_v4_0_early_init(void *handle)
 }
 
 static int sdma_v4_0_process_ras_data_cb(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
+		void *err_data,
 		struct amdgpu_iv_entry *entry);
 
 static int sdma_v4_0_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct ras_common_if **ras_if = &adev->sdma.ras_if;
 	struct ras_ih_if ih_info = {
 		.cb = sdma_v4_0_process_ras_data_cb,
 	};
-	struct ras_fs_if fs_info = {
-		.sysfs_name = "sdma_err_count",
-		.debugfs_name = "sdma_err_inject",
-	};
-	struct ras_common_if ras_block = {
-		.block = AMDGPU_RAS_BLOCK__SDMA,
-		.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
-		.sub_block_index = 0,
-		.name = "sdma",
-	};
-	int r, i;
-
-	if (!amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA)) {
-		amdgpu_ras_feature_enable_on_boot(adev, &ras_block, 0);
-		return 0;
-	}
-
-	/* handle resume path. */
-	if (*ras_if) {
-		/* resend ras TA enable cmd during resume.
-		 * prepare to handle failure.
-		 */
-		ih_info.head = **ras_if;
-		r = amdgpu_ras_feature_enable_on_boot(adev, *ras_if, 1);
-		if (r) {
-			if (r == -EAGAIN) {
-				/* request a gpu reset. will run again. */
-				amdgpu_ras_request_reset_on_boot(adev,
-						AMDGPU_RAS_BLOCK__SDMA);
-				return 0;
-			}
-			/* fail to enable ras, cleanup all. */
-			goto irq;
-		}
-		/* enable successfully. continue. */
-		goto resume;
-	}
-
-	*ras_if = kmalloc(sizeof(**ras_if), GFP_KERNEL);
-	if (!*ras_if)
-		return -ENOMEM;
-
-	**ras_if = ras_block;
-
-	r = amdgpu_ras_feature_enable_on_boot(adev, *ras_if, 1);
-	if (r) {
-		if (r == -EAGAIN) {
-			amdgpu_ras_request_reset_on_boot(adev,
-					AMDGPU_RAS_BLOCK__SDMA);
-			r = 0;
-		}
-		goto feature;
-	}
-
-	ih_info.head = **ras_if;
-	fs_info.head = **ras_if;
-
-	r = amdgpu_ras_interrupt_add_handler(adev, &ih_info);
-	if (r)
-		goto interrupt;
-
-	amdgpu_ras_debugfs_create(adev, &fs_info);
 
-	r = amdgpu_ras_sysfs_create(adev, &fs_info);
-	if (r)
-		goto sysfs;
-resume:
-	for (i = 0; i < adev->sdma.num_instances; i++) {
-		r = amdgpu_irq_get(adev, &adev->sdma.ecc_irq,
-				   AMDGPU_SDMA_IRQ_INSTANCE0 + i);
-		if (r)
-			goto irq;
-	}
-
-	return 0;
-irq:
-	amdgpu_ras_sysfs_remove(adev, *ras_if);
-sysfs:
-	amdgpu_ras_debugfs_remove(adev, *ras_if);
-	amdgpu_ras_interrupt_remove_handler(adev, &ih_info);
-interrupt:
-	amdgpu_ras_feature_enable(adev, *ras_if, 0);
-feature:
-	kfree(*ras_if);
-	*ras_if = NULL;
-	return r;
+	return amdgpu_sdma_ras_late_init(adev, &ih_info);
 }
 
 static int sdma_v4_0_sw_init(void *handle)
@@ -1857,21 +1773,7 @@ static int sdma_v4_0_sw_fini(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	int i;
 
-	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__SDMA) &&
-			adev->sdma.ras_if) {
-		struct ras_common_if *ras_if = adev->sdma.ras_if;
-		struct ras_ih_if ih_info = {
-			.head = *ras_if,
-		};
-
-		/*remove fs first*/
-		amdgpu_ras_debugfs_remove(adev, ras_if);
-		amdgpu_ras_sysfs_remove(adev, ras_if);
-		/*remove the IH*/
-		amdgpu_ras_interrupt_remove_handler(adev, &ih_info);
-		amdgpu_ras_feature_enable(adev, ras_if, 0);
-		kfree(ras_if);
-	}
+	amdgpu_sdma_ras_fini(adev);
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		amdgpu_ring_fini(&adev->sdma.instance[i].ring);
@@ -1891,7 +1793,7 @@ static int sdma_v4_0_hw_init(void *handle)
 
 	if ((adev->asic_type == CHIP_RAVEN && adev->powerplay.pp_funcs &&
 			adev->powerplay.pp_funcs->set_powergating_by_smu) ||
-			adev->asic_type == CHIP_RENOIR)
+			(adev->asic_type == CHIP_RENOIR && !adev->in_gpu_reset))
 		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_SDMA, false);
 
 	if (!amdgpu_sriov_vf(adev))
@@ -2024,52 +1926,28 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev,
 }
 
 static int sdma_v4_0_process_ras_data_cb(struct amdgpu_device *adev,
-		struct ras_err_data *err_data,
+		void *err_data,
 		struct amdgpu_iv_entry *entry)
 {
-	uint32_t err_source;
 	int instance;
 
+	/* When “Full RAS” is enabled, the per-IP interrupt sources should
+	 * be disabled and the driver should only look for the aggregated
+	 * interrupt via sync flood
+	 */
+	if (amdgpu_ras_is_supported(adev, AMDGPU_RAS_BLOCK__GFX))
+		goto out;
+
 	instance = sdma_v4_0_irq_id_to_seq(entry->client_id);
 	if (instance < 0)
-		return 0;
-
-	switch (entry->src_id) {
-	case SDMA0_4_0__SRCID__SDMA_SRAM_ECC:
-		err_source = 0;
-		break;
-	case SDMA0_4_0__SRCID__SDMA_ECC:
-		err_source = 1;
-		break;
-	default:
-		return 0;
-	}
-
-	kgd2kfd_set_sram_ecc_flag(adev->kfd.dev);
+		goto out;
 
-	amdgpu_ras_reset_gpu(adev, 0);
+	amdgpu_sdma_process_ras_data_cb(adev, err_data, entry);
 
+out:
 	return AMDGPU_RAS_SUCCESS;
 }
 
-static int sdma_v4_0_process_ecc_irq(struct amdgpu_device *adev,
-				      struct amdgpu_irq_src *source,
-				      struct amdgpu_iv_entry *entry)
-{
-	struct ras_common_if *ras_if = adev->sdma.ras_if;
-	struct ras_dispatch_if ih_data = {
-		.entry = entry,
-	};
-
-	if (!ras_if)
-		return 0;
-
-	ih_data.head = *ras_if;
-
-	amdgpu_ras_interrupt_dispatch(adev, &ih_data);
-	return 0;
-}
-
 static int sdma_v4_0_process_illegal_inst_irq(struct amdgpu_device *adev,
 					      struct amdgpu_irq_src *source,
 					      struct amdgpu_iv_entry *entry)
@@ -2417,7 +2295,7 @@ static const struct amdgpu_irq_src_funcs sdma_v4_0_illegal_inst_irq_funcs = {
 
 static const struct amdgpu_irq_src_funcs sdma_v4_0_ecc_irq_funcs = {
 	.set = sdma_v4_0_set_ecc_irq_state,
-	.process = sdma_v4_0_process_ecc_irq,
+	.process = amdgpu_sdma_process_ecc_irq,
 };
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
index f6e81680dd7e..f4ad2990f973 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_0.c
@@ -406,7 +406,7 @@ static void sdma_v5_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 	u32 ref_and_mask = 0;
-	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
+	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio.hdp_flush_reg;
 
 	if (ring->me == 0)
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0;
@@ -416,8 +416,8 @@ static void sdma_v5_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_POLL_REGMEM) |
 			  SDMA_PKT_POLL_REGMEM_HEADER_HDP_FLUSH(1) |
 			  SDMA_PKT_POLL_REGMEM_HEADER_FUNC(3)); /* == */
-	amdgpu_ring_write(ring, (adev->nbio_funcs->get_hdp_flush_done_offset(adev)) << 2);
-	amdgpu_ring_write(ring, (adev->nbio_funcs->get_hdp_flush_req_offset(adev)) << 2);
+	amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_done_offset(adev)) << 2);
+	amdgpu_ring_write(ring, (adev->nbio.funcs->get_hdp_flush_req_offset(adev)) << 2);
 	amdgpu_ring_write(ring, ref_and_mask); /* reference */
 	amdgpu_ring_write(ring, ref_and_mask); /* mask */
 	amdgpu_ring_write(ring, SDMA_PKT_POLL_REGMEM_DW5_RETRY_COUNT(0xfff) |
@@ -683,7 +683,7 @@ static int sdma_v5_0_gfx_resume(struct amdgpu_device *adev)
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL), doorbell);
 		WREG32(sdma_v5_0_get_reg_offset(adev, i, mmSDMA0_GFX_DOORBELL_OFFSET), doorbell_offset);
 
-		adev->nbio_funcs->sdma_doorbell_range(adev, i, ring->use_doorbell,
+		adev->nbio.funcs->sdma_doorbell_range(adev, i, ring->use_doorbell,
 						      ring->doorbell_index, 20);
 
 		if (amdgpu_sriov_vf(adev))
@@ -1173,6 +1173,16 @@ static void sdma_v5_0_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 			  SDMA_PKT_POLL_REGMEM_DW5_INTERVAL(10));
 }
 
+static void sdma_v5_0_ring_emit_reg_write_reg_wait(struct amdgpu_ring *ring,
+						   uint32_t reg0, uint32_t reg1,
+						   uint32_t ref, uint32_t mask)
+{
+	amdgpu_ring_emit_wreg(ring, reg0, ref);
+	/* wait for a cycle to reset vm_inv_eng*_ack */
+	amdgpu_ring_emit_reg_wait(ring, reg0, 0, 0);
+	amdgpu_ring_emit_reg_wait(ring, reg1, mask, mask);
+}
+
 static int sdma_v5_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1588,7 +1598,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
 		6 + /* sdma_v5_0_ring_emit_pipeline_sync */
 		/* sdma_v5_0_ring_emit_vm_flush */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
-		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 6 * 2 +
 		10 + 10 + 10, /* sdma_v5_0_ring_emit_fence x3 for user fence, vm fence */
 	.emit_ib_size = 7 + 6, /* sdma_v5_0_ring_emit_ib */
 	.emit_ib = sdma_v5_0_ring_emit_ib,
@@ -1602,6 +1612,7 @@ static const struct amdgpu_ring_funcs sdma_v5_0_ring_funcs = {
 	.pad_ib = sdma_v5_0_ring_pad_ib,
 	.emit_wreg = sdma_v5_0_ring_emit_wreg,
 	.emit_reg_wait = sdma_v5_0_ring_emit_reg_wait,
+	.emit_reg_write_reg_wait = sdma_v5_0_ring_emit_reg_write_reg_wait,
 	.init_cond_exec = sdma_v5_0_ring_init_cond_exec,
 	.patch_cond_exec = sdma_v5_0_ring_patch_cond_exec,
 	.preempt_ib = sdma_v5_0_ring_preempt_ib,
diff --git a/drivers/gpu/drm/amd/amdgpu/si.c b/drivers/gpu/drm/amd/amdgpu/si.c
index 493af42152f2..29024e64c886 100644
--- a/drivers/gpu/drm/amd/amdgpu/si.c
+++ b/drivers/gpu/drm/amd/amdgpu/si.c
@@ -975,6 +975,17 @@ static void si_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 
 static struct amdgpu_allowed_register_entry si_allowed_read_registers[] = {
 	{GRBM_STATUS},
+	{mmGRBM_STATUS2},
+	{mmGRBM_STATUS_SE0},
+	{mmGRBM_STATUS_SE1},
+	{mmSRBM_STATUS},
+	{mmSRBM_STATUS2},
+	{DMA_STATUS_REG + DMA0_REGISTER_OFFSET},
+	{DMA_STATUS_REG + DMA1_REGISTER_OFFSET},
+	{mmCP_STAT},
+	{mmCP_STALLED_STAT1},
+	{mmCP_STALLED_STAT2},
+	{mmCP_STALLED_STAT3},
 	{GB_ADDR_CONFIG},
 	{MC_ARB_RAMCFG},
 	{GB_TILE_MODE0},
diff --git a/drivers/gpu/drm/amd/amdgpu/si_ih.c b/drivers/gpu/drm/amd/amdgpu/si_ih.c
index 57bb5f9e08b2..88ae27a5a03d 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_ih.c
@@ -64,7 +64,8 @@ static int si_ih_irq_init(struct amdgpu_device *adev)
 	u32 interrupt_cntl, ih_cntl, ih_rb_cntl;
 
 	si_ih_disable_interrupts(adev);
-	WREG32(INTERRUPT_CNTL2, adev->irq.ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, adev->dummy_page_addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	interrupt_cntl &= ~IH_DUMMY_RD_OVERRIDE;
 	interrupt_cntl &= ~IH_REQ_NONSNOOP_EN;
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index f8ab80c8801b..8e1640bc07af 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -58,6 +58,9 @@
 #include "mmhub_v1_0.h"
 #include "df_v1_7.h"
 #include "df_v3_6.h"
+#include "nbio_v6_1.h"
+#include "nbio_v7_0.h"
+#include "nbio_v7_4.h"
 #include "vega10_ih.h"
 #include "sdma_v4_0.h"
 #include "uvd_v7_0.h"
@@ -91,8 +94,8 @@ static u32 soc15_pcie_rreg(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags, address, data;
 	u32 r;
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, reg);
@@ -106,8 +109,8 @@ static void soc15_pcie_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 {
 	unsigned long flags, address, data;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	WREG32(address, reg);
@@ -121,8 +124,8 @@ static u64 soc15_pcie_rreg64(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags, address, data;
 	u64 r;
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	/* read low 32 bit */
@@ -142,8 +145,8 @@ static void soc15_pcie_wreg64(struct amdgpu_device *adev, u32 reg, u64 v)
 {
 	unsigned long flags, address, data;
 
-	address = adev->nbio_funcs->get_pcie_index_offset(adev);
-	data = adev->nbio_funcs->get_pcie_data_offset(adev);
+	address = adev->nbio.funcs->get_pcie_index_offset(adev);
+	data = adev->nbio.funcs->get_pcie_data_offset(adev);
 
 	spin_lock_irqsave(&adev->pcie_idx_lock, flags);
 	/* write low 32 bit */
@@ -262,7 +265,7 @@ static void soc15_se_cac_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
 
 static u32 soc15_get_config_memsize(struct amdgpu_device *adev)
 {
-	return adev->nbio_funcs->get_memsize(adev);
+	return adev->nbio.funcs->get_memsize(adev);
 }
 
 static u32 soc15_get_xclk(struct amdgpu_device *adev)
@@ -336,6 +339,7 @@ static struct soc15_allowed_register_entry soc15_allowed_read_registers[] = {
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPF_STATUS)},
+	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_BUSY_STAT)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STALLED_STAT1)},
 	{ SOC15_REG_ENTRY(GC, 0, mmCP_CPC_STATUS)},
 	{ SOC15_REG_ENTRY(GC, 0, mmGB_ADDR_CONFIG)},
@@ -461,7 +465,7 @@ static int soc15_asic_mode1_reset(struct amdgpu_device *adev)
 
 	/* wait for asic to come out of reset */
 	for (i = 0; i < adev->usec_timeout; i++) {
-		u32 memsize = adev->nbio_funcs->get_memsize(adev);
+		u32 memsize = adev->nbio.funcs->get_memsize(adev);
 
 		if (memsize != 0xffffffff)
 			break;
@@ -475,42 +479,66 @@ static int soc15_asic_mode1_reset(struct amdgpu_device *adev)
 
 static int soc15_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap)
 {
-	void *pp_handle = adev->powerplay.pp_handle;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	if (is_support_sw_smu(adev)) {
+		struct smu_context *smu = &adev->smu;
 
-	if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
-		*cap = false;
-		return -ENOENT;
-	}
+		*cap = smu_baco_is_support(smu);
+		return 0;
+	} else {
+		void *pp_handle = adev->powerplay.pp_handle;
+		const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+		if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
+			*cap = false;
+			return -ENOENT;
+		}
 
-	return pp_funcs->get_asic_baco_capability(pp_handle, cap);
+		return pp_funcs->get_asic_baco_capability(pp_handle, cap);
+	}
 }
 
 static int soc15_asic_baco_reset(struct amdgpu_device *adev)
 {
-	void *pp_handle = adev->powerplay.pp_handle;
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 
-	if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
-		return -ENOENT;
+	/* avoid NBIF got stuck when do RAS recovery in BACO reset */
+	if (ras && ras->supported)
+		adev->nbio.funcs->enable_doorbell_interrupt(adev, false);
+
+	dev_info(adev->dev, "GPU BACO reset\n");
 
-	/* enter BACO state */
-	if (pp_funcs->set_asic_baco_state(pp_handle, 1))
-		return -EIO;
+	if (is_support_sw_smu(adev)) {
+		struct smu_context *smu = &adev->smu;
 
-	/* exit BACO state */
-	if (pp_funcs->set_asic_baco_state(pp_handle, 0))
-		return -EIO;
+		if (smu_baco_reset(smu))
+			return -EIO;
+	} else {
+		void *pp_handle = adev->powerplay.pp_handle;
+		const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
 
-	dev_info(adev->dev, "GPU BACO reset\n");
+		if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
+			return -ENOENT;
 
-	adev->in_baco_reset = 1;
+		/* enter BACO state */
+		if (pp_funcs->set_asic_baco_state(pp_handle, 1))
+			return -EIO;
+
+		/* exit BACO state */
+		if (pp_funcs->set_asic_baco_state(pp_handle, 0))
+			return -EIO;
+	}
+
+	/* re-enable doorbell interrupt after BACO exit */
+	if (ras && ras->supported)
+		adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
 
 	return 0;
 }
 
 static int soc15_mode2_reset(struct amdgpu_device *adev)
 {
+	if (is_support_sw_smu(adev))
+		return smu_mode2_reset(&adev->smu);
 	if (!adev->powerplay.pp_funcs ||
 	    !adev->powerplay.pp_funcs->asic_reset_mode_2)
 		return -ENOENT;
@@ -525,6 +553,7 @@ soc15_asic_reset_method(struct amdgpu_device *adev)
 
 	switch (adev->asic_type) {
 	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 		return AMD_RESET_METHOD_MODE2;
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
@@ -626,8 +655,8 @@ static void soc15_program_aspm(struct amdgpu_device *adev)
 static void soc15_enable_doorbell_aperture(struct amdgpu_device *adev,
 					   bool enable)
 {
-	adev->nbio_funcs->enable_doorbell_aperture(adev, enable);
-	adev->nbio_funcs->enable_doorbell_selfring_aperture(adev, enable);
+	adev->nbio.funcs->enable_doorbell_aperture(adev, enable);
+	adev->nbio.funcs->enable_doorbell_selfring_aperture(adev, enable);
 }
 
 static const struct amdgpu_ip_block_version vega10_common_ip_block =
@@ -641,7 +670,7 @@ static const struct amdgpu_ip_block_version vega10_common_ip_block =
 
 static uint32_t soc15_get_rev_id(struct amdgpu_device *adev)
 {
-	return adev->nbio_funcs->get_rev_id(adev);
+	return adev->nbio.funcs->get_rev_id(adev);
 }
 
 int soc15_set_ip_blocks(struct amdgpu_device *adev)
@@ -667,13 +696,17 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 	if (adev->asic_type == CHIP_VEGA20 || adev->asic_type == CHIP_ARCTURUS)
 		adev->gmc.xgmi.supported = true;
 
-	if (adev->flags & AMD_IS_APU)
-		adev->nbio_funcs = &nbio_v7_0_funcs;
-	else if (adev->asic_type == CHIP_VEGA20 ||
-		adev->asic_type == CHIP_ARCTURUS)
-		adev->nbio_funcs = &nbio_v7_4_funcs;
-	else
-		adev->nbio_funcs = &nbio_v6_1_funcs;
+	if (adev->flags & AMD_IS_APU) {
+		adev->nbio.funcs = &nbio_v7_0_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v7_0_hdp_flush_reg;
+	} else if (adev->asic_type == CHIP_VEGA20 ||
+		   adev->asic_type == CHIP_ARCTURUS) {
+		adev->nbio.funcs = &nbio_v7_4_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v7_4_hdp_flush_reg;
+	} else {
+		adev->nbio.funcs = &nbio_v6_1_funcs;
+		adev->nbio.hdp_flush_reg = &nbio_v6_1_hdp_flush_reg;
+	}
 
 	if (adev->asic_type == CHIP_VEGA20 || adev->asic_type == CHIP_ARCTURUS)
 		adev->df_funcs = &df_v3_6_funcs;
@@ -681,7 +714,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 		adev->df_funcs = &df_v1_7_funcs;
 
 	adev->rev_id = soc15_get_rev_id(adev);
-	adev->nbio_funcs->detect_hw_virt(adev);
+	adev->nbio.funcs->detect_hw_virt(adev);
 
 	if (amdgpu_sriov_vf(adev))
 		adev->virt.ops = &xgpu_ai_virt_ops;
@@ -750,13 +783,26 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 	case CHIP_ARCTURUS:
 		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
 		amdgpu_device_ip_block_add(adev, &gmc_v9_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
+
+		if (amdgpu_sriov_vf(adev)) {
+			if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
+				amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
+			amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
+		} else {
+			amdgpu_device_ip_block_add(adev, &vega10_ih_ip_block);
+			if (likely(adev->firmware.load_type == AMDGPU_FW_LOAD_PSP))
+				amdgpu_device_ip_block_add(adev, &psp_v11_0_ip_block);
+		}
+
 		if (adev->enable_virtual_display || amdgpu_sriov_vf(adev))
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 		amdgpu_device_ip_block_add(adev, &gfx_v9_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &sdma_v4_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
-		amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
+		if (!amdgpu_sriov_vf(adev))
+			amdgpu_device_ip_block_add(adev, &smu_v11_0_ip_block);
+
+		if (unlikely(adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT))
+			amdgpu_device_ip_block_add(adev, &vcn_v2_5_ip_block);
 		break;
 	case CHIP_RENOIR:
 		amdgpu_device_ip_block_add(adev, &vega10_common_ip_block);
@@ -785,7 +831,7 @@ int soc15_set_ip_blocks(struct amdgpu_device *adev)
 
 static void soc15_flush_hdp(struct amdgpu_device *adev, struct amdgpu_ring *ring)
 {
-	adev->nbio_funcs->hdp_flush(adev, ring);
+	adev->nbio.funcs->hdp_flush(adev, ring);
 }
 
 static void soc15_invalidate_hdp(struct amdgpu_device *adev,
@@ -1099,7 +1145,9 @@ static int soc15_common_early_init(void *handle)
 				AMD_CG_SUPPORT_SDMA_LS |
 				AMD_CG_SUPPORT_VCN_MGCG;
 
-			adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
+			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
+				AMD_PG_SUPPORT_VCN |
+				AMD_PG_SUPPORT_VCN_DPG;
 		} else if (adev->pdev->device == 0x15d8) {
 			adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG |
 				AMD_CG_SUPPORT_GFX_MGLS |
@@ -1142,7 +1190,9 @@ static int soc15_common_early_init(void *handle)
 				AMD_CG_SUPPORT_SDMA_LS |
 				AMD_CG_SUPPORT_VCN_MGCG;
 
-			adev->pg_flags = AMD_PG_SUPPORT_SDMA | AMD_PG_SUPPORT_VCN;
+			adev->pg_flags = AMD_PG_SUPPORT_SDMA |
+				AMD_PG_SUPPORT_VCN |
+				AMD_PG_SUPPORT_VCN_DPG;
 		}
 		break;
 	case CHIP_ARCTURUS:
@@ -1157,7 +1207,8 @@ static int soc15_common_early_init(void *handle)
 			AMD_CG_SUPPORT_SDMA_MGCG |
 			AMD_CG_SUPPORT_SDMA_LS |
 			AMD_CG_SUPPORT_MC_MGCG |
-			AMD_CG_SUPPORT_MC_LS;
+			AMD_CG_SUPPORT_MC_LS |
+			AMD_CG_SUPPORT_IH_CG;
 		adev->pg_flags = 0;
 		adev->external_rev_id = adev->rev_id + 0x32;
 		break;
@@ -1186,11 +1237,6 @@ static int soc15_common_early_init(void *handle)
 				 AMD_PG_SUPPORT_VCN |
 				 AMD_PG_SUPPORT_VCN_DPG;
 		adev->external_rev_id = adev->rev_id + 0x91;
-
-		if (adev->pm.pp_feature & PP_GFXOFF_MASK)
-			adev->pg_flags |= AMD_PG_SUPPORT_GFX_PG |
-				AMD_PG_SUPPORT_CP |
-				AMD_PG_SUPPORT_RLC_SMU_HS;
 		break;
 	default:
 		/* FIXME: not supported yet */
@@ -1208,11 +1254,15 @@ static int soc15_common_early_init(void *handle)
 static int soc15_common_late_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	int r = 0;
 
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_get_irq(adev);
 
-	return 0;
+	if (adev->nbio.funcs->ras_late_init)
+		r = adev->nbio.funcs->ras_late_init(adev);
+
+	return r;
 }
 
 static int soc15_common_sw_init(void *handle)
@@ -1229,6 +1279,10 @@ static int soc15_common_sw_init(void *handle)
 
 static int soc15_common_sw_fini(void *handle)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	amdgpu_nbio_ras_fini(adev);
+	adev->df_funcs->sw_fini(adev);
 	return 0;
 }
 
@@ -1241,12 +1295,12 @@ static void soc15_doorbell_range_init(struct amdgpu_device *adev)
 	if (!amdgpu_sriov_vf(adev)) {
 		for (i = 0; i < adev->sdma.num_instances; i++) {
 			ring = &adev->sdma.instance[i].ring;
-			adev->nbio_funcs->sdma_doorbell_range(adev, i,
+			adev->nbio.funcs->sdma_doorbell_range(adev, i,
 				ring->use_doorbell, ring->doorbell_index,
 				adev->doorbell_index.sdma_doorbell_range);
 		}
 
-		adev->nbio_funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
+		adev->nbio.funcs->ih_doorbell_range(adev, adev->irq.ih.use_doorbell,
 						adev->irq.ih.doorbell_index);
 	}
 }
@@ -1260,13 +1314,13 @@ static int soc15_common_hw_init(void *handle)
 	/* enable aspm */
 	soc15_program_aspm(adev);
 	/* setup nbio registers */
-	adev->nbio_funcs->init_registers(adev);
+	adev->nbio.funcs->init_registers(adev);
 	/* remap HDP registers to a hole in mmio space,
 	 * for the purpose of expose those registers
 	 * to process space
 	 */
-	if (adev->nbio_funcs->remap_hdp_registers)
-		adev->nbio_funcs->remap_hdp_registers(adev);
+	if (adev->nbio.funcs->remap_hdp_registers)
+		adev->nbio.funcs->remap_hdp_registers(adev);
 
 	/* enable the doorbell aperture */
 	soc15_enable_doorbell_aperture(adev, true);
@@ -1289,6 +1343,14 @@ static int soc15_common_hw_fini(void *handle)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_put_irq(adev);
 
+	if (adev->nbio.ras_if &&
+	    amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) {
+		if (adev->nbio.funcs->init_ras_controller_interrupt)
+			amdgpu_irq_put(adev, &adev->nbio.ras_controller_irq, 0);
+		if (adev->nbio.funcs->init_ras_err_event_athub_interrupt)
+			amdgpu_irq_put(adev, &adev->nbio.ras_err_event_athub_irq, 0);
+	}
+
 	return 0;
 }
 
@@ -1429,9 +1491,9 @@ static int soc15_common_set_clockgating_state(void *handle,
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
-		adev->nbio_funcs->update_medium_grain_clock_gating(adev,
+		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		adev->nbio_funcs->update_medium_grain_light_sleep(adev,
+		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_hdp_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
@@ -1446,9 +1508,9 @@ static int soc15_common_set_clockgating_state(void *handle,
 		break;
 	case CHIP_RAVEN:
 	case CHIP_RENOIR:
-		adev->nbio_funcs->update_medium_grain_clock_gating(adev,
+		adev->nbio.funcs->update_medium_grain_clock_gating(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
-		adev->nbio_funcs->update_medium_grain_light_sleep(adev,
+		adev->nbio.funcs->update_medium_grain_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
 		soc15_update_hdp_light_sleep(adev,
 				state == AMD_CG_STATE_GATE ? true : false);
@@ -1477,7 +1539,7 @@ static void soc15_common_get_clockgating_state(void *handle, u32 *flags)
 	if (amdgpu_sriov_vf(adev))
 		*flags = 0;
 
-	adev->nbio_funcs->get_clockgating_state(adev, flags);
+	adev->nbio.funcs->get_clockgating_state(adev, flags);
 
 	/* AMD_CG_SUPPORT_HDP_LS */
 	data = RREG32(SOC15_REG_OFFSET(HDP, 0, mmHDP_MEM_POWER_LS));
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index a3dde0c31f57..57af489a5de3 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -28,8 +28,8 @@
 #include "nbio_v7_0.h"
 #include "nbio_v7_4.h"
 
-#define SOC15_FLUSH_GPU_TLB_NUM_WREG		4
-#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT	1
+#define SOC15_FLUSH_GPU_TLB_NUM_WREG		6
+#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT	3
 
 extern const struct amd_ip_funcs soc15_common_ip_funcs;
 
@@ -67,6 +67,8 @@ struct soc15_allowed_register_entry {
 #define SOC15_REG_GOLDEN_VALUE(ip, inst, reg, and_mask, or_mask) \
 	{ ip##_HWIP, inst, reg##_BASE_IDX, reg, and_mask, or_mask }
 
+#define SOC15_REG_FIELD(reg, field) reg##__##field##_MASK, reg##__##field##__SHIFT
+
 void soc15_grbm_select(struct amdgpu_device *adev,
 		    u32 me, u32 pipe, u32 queue, u32 vmid);
 int soc15_set_ip_blocks(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_0.c
new file mode 100644
index 000000000000..0d6b50528d76
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_0.c
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "umc_v6_0.h"
+#include "amdgpu.h"
+
+static void umc_v6_0_init_registers(struct amdgpu_device *adev)
+{
+	unsigned i,j;
+
+	for (i = 0; i < 4; i++)
+		for (j = 0; j < 4; j++)
+			WREG32((i*0x100000 + 0x5010c + j*0x2000)/4, 0x1002);
+}
+
+const struct amdgpu_umc_funcs umc_v6_0_funcs = {
+	.init_registers = umc_v6_0_init_registers,
+};
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_0.h b/drivers/gpu/drm/amd/amdgpu/umc_v6_0.h
new file mode 100644
index 000000000000..109f1a57a46e
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_0.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __UMC_V6_0_H__
+#define __UMC_V6_0_H__
+
+#include "soc15_common.h"
+#include "amdgpu.h"
+
+extern const struct amdgpu_umc_funcs umc_v6_0_funcs;
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
index 8502e736f721..47c4b96b14d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
+++ b/drivers/gpu/drm/amd/amdgpu/umc_v6_1.c
@@ -75,6 +75,17 @@ static void umc_v6_1_disable_umc_index_mode(struct amdgpu_device *adev)
 			RSMU_UMC_INDEX_MODE_EN, 0);
 }
 
+static uint32_t umc_v6_1_get_umc_inst(struct amdgpu_device *adev)
+{
+	uint32_t rsmu_umc_index;
+
+	rsmu_umc_index = RREG32_SOC15(RSMU, 0,
+				mmRSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU);
+	return REG_GET_FIELD(rsmu_umc_index,
+				RSMU_UMC_INDEX_REGISTER_NBIF_VG20_GPU,
+				RSMU_UMC_INDEX_INSTANCE);
+}
+
 static void umc_v6_1_query_correctable_error_count(struct amdgpu_device *adev,
 						   uint32_t umc_reg_offset,
 						   unsigned long *error_count)
@@ -165,7 +176,8 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 					 uint32_t umc_reg_offset, uint32_t channel_index)
 {
 	uint32_t lsb, mc_umc_status_addr;
-	uint64_t mc_umc_status, err_addr;
+	uint64_t mc_umc_status, err_addr, retired_page;
+	struct eeprom_table_record *err_rec;
 
 	mc_umc_status_addr =
 		SOC15_REG_OFFSET(UMC, 0, mmMCA_UMC_UMC0_MCUMC_STATUST0);
@@ -177,6 +189,7 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 		return;
 	}
 
+	err_rec = &err_data->err_addr[err_data->err_addr_cnt];
 	mc_umc_status = RREG64_UMC(mc_umc_status_addr + umc_reg_offset);
 
 	/* calculate error address if ue/ce error is detected */
@@ -191,12 +204,24 @@ static void umc_v6_1_query_error_address(struct amdgpu_device *adev,
 		err_addr &= ~((0x1ULL << lsb) - 1);
 
 		/* translate umc channel address to soc pa, 3 parts are included */
-		err_data->err_addr[err_data->err_addr_cnt] =
-						ADDR_OF_8KB_BLOCK(err_addr) |
-						ADDR_OF_256B_BLOCK(channel_index) |
-						OFFSET_IN_256B_BLOCK(err_addr);
-
-		err_data->err_addr_cnt++;
+		retired_page = ADDR_OF_8KB_BLOCK(err_addr) |
+				ADDR_OF_256B_BLOCK(channel_index) |
+				OFFSET_IN_256B_BLOCK(err_addr);
+
+		/* we only save ue error information currently, ce is skipped */
+		if (REG_GET_FIELD(mc_umc_status, MCA_UMC_UMC0_MCUMC_STATUST0, UECC)
+				== 1) {
+			err_rec->address = err_addr;
+			/* page frame address is saved */
+			err_rec->retired_page = retired_page >> AMDGPU_GPU_PAGE_SHIFT;
+			err_rec->ts = (uint64_t)ktime_get_real_seconds();
+			err_rec->err_type = AMDGPU_RAS_EEPROM_ERR_NON_RECOVERABLE;
+			err_rec->cu = 0;
+			err_rec->mem_channel = channel_index;
+			err_rec->mcumc_id = umc_v6_1_get_umc_inst(adev);
+
+			err_data->err_addr_cnt++;
+		}
 	}
 
 	/* clear umc status */
@@ -209,7 +234,7 @@ static void umc_v6_1_query_ras_error_address(struct amdgpu_device *adev,
 	amdgpu_umc_for_each_channel(umc_v6_1_query_error_address);
 }
 
-static void umc_v6_1_ras_init_per_channel(struct amdgpu_device *adev,
+static void umc_v6_1_err_cnt_init_per_channel(struct amdgpu_device *adev,
 					 struct ras_err_data *err_data,
 					 uint32_t umc_reg_offset, uint32_t channel_index)
 {
@@ -239,15 +264,16 @@ static void umc_v6_1_ras_init_per_channel(struct amdgpu_device *adev,
 	WREG32(ecc_err_cnt_addr + umc_reg_offset, UMC_V6_1_CE_CNT_INIT);
 }
 
-static void umc_v6_1_ras_init(struct amdgpu_device *adev)
+static void umc_v6_1_err_cnt_init(struct amdgpu_device *adev)
 {
 	void *ras_error_status = NULL;
 
-	amdgpu_umc_for_each_channel(umc_v6_1_ras_init_per_channel);
+	amdgpu_umc_for_each_channel(umc_v6_1_err_cnt_init_per_channel);
 }
 
 const struct amdgpu_umc_funcs umc_v6_1_funcs = {
-	.ras_init = umc_v6_1_ras_init,
+	.err_cnt_init = umc_v6_1_err_cnt_init,
+	.ras_late_init = amdgpu_umc_ras_late_init,
 	.query_ras_error_count = umc_v6_1_query_ras_error_count,
 	.query_ras_error_address = umc_v6_1_query_ras_error_address,
 	.enable_umc_index_mode = umc_v6_1_enable_umc_index_mode,
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 670784a78512..217084d56ab8 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -206,13 +206,14 @@ static int uvd_v6_0_enc_ring_test_ring(struct amdgpu_ring *ring)
  * Open up a stream for HW test
  */
 static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				       struct amdgpu_bo *bo,
 				       struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -220,15 +221,15 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00010000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -268,13 +269,14 @@ err:
  */
 static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 					uint32_t handle,
+					struct amdgpu_bo *bo,
 					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -282,15 +284,15 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00010000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -327,13 +329,20 @@ err:
 static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = uvd_v6_0_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = uvd_v6_0_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, &fence);
+	r = uvd_v6_0_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -345,6 +354,8 @@ static int uvd_v6_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 01f658fa72c6..0995378d8263 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -214,13 +214,14 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
  * Open up a stream for HW test
  */
 static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+				       struct amdgpu_bo *bo,
 				       struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -228,15 +229,15 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00000000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -275,13 +276,14 @@ err:
  * Close up a stream for HW test or if userspace failed to do so
  */
 static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
-				struct dma_fence **fence)
+					struct amdgpu_bo *bo,
+					struct dma_fence **fence)
 {
 	const unsigned ib_size_dw = 16;
 	struct amdgpu_job *job;
 	struct amdgpu_ib *ib;
 	struct dma_fence *f = NULL;
-	uint64_t dummy;
+	uint64_t addr;
 	int i, r;
 
 	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
@@ -289,15 +291,15 @@ static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handl
 		return r;
 
 	ib = &job->ibs[0];
-	dummy = ib->gpu_addr + 1024;
+	addr = amdgpu_bo_gpu_offset(bo);
 
 	ib->length_dw = 0;
 	ib->ptr[ib->length_dw++] = 0x00000018;
 	ib->ptr[ib->length_dw++] = 0x00000001;
 	ib->ptr[ib->length_dw++] = handle;
 	ib->ptr[ib->length_dw++] = 0x00000000;
-	ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
-	ib->ptr[ib->length_dw++] = dummy;
+	ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+	ib->ptr[ib->length_dw++] = addr;
 
 	ib->ptr[ib->length_dw++] = 0x00000014;
 	ib->ptr[ib->length_dw++] = 0x00000002;
@@ -334,13 +336,20 @@ err:
 static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 {
 	struct dma_fence *fence = NULL;
+	struct amdgpu_bo *bo = NULL;
 	long r;
 
-	r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL);
+	r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+				      AMDGPU_GEM_DOMAIN_VRAM,
+				      &bo, NULL, NULL);
+	if (r)
+		return r;
+
+	r = uvd_v7_0_enc_get_create_msg(ring, 1, bo, NULL);
 	if (r)
 		goto error;
 
-	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, &fence);
+	r = uvd_v7_0_enc_get_destroy_msg(ring, 1, bo, &fence);
 	if (r)
 		goto error;
 
@@ -352,6 +361,8 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 
 error:
 	dma_fence_put(fence);
+	amdgpu_bo_unreserve(bo);
+	amdgpu_bo_unref(&bo);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 93b3500e522b..b4f84a820a44 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -202,7 +202,6 @@ static int vcn_v1_0_hw_init(void *handle)
 
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 		ring = &adev->vcn.inst->ring_enc[i];
-		ring->sched.ready = true;
 		r = amdgpu_ring_test_helper(ring);
 		if (r)
 			goto done;
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 36ad0c0e8efb..38f787a560cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -244,33 +244,24 @@ static int vcn_v2_0_hw_init(void *handle)
 	struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
 	int i, r;
 
-	adev->nbio_funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+	adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
 					     ring->doorbell_index, 0);
 
-	ring->sched.ready = true;
-	r = amdgpu_ring_test_ring(ring);
-	if (r) {
-		ring->sched.ready = false;
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
 		goto done;
-	}
 
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 		ring = &adev->vcn.inst->ring_enc[i];
-		ring->sched.ready = true;
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->sched.ready = false;
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
 			goto done;
-		}
 	}
 
 	ring = &adev->vcn.inst->ring_jpeg;
-	ring->sched.ready = true;
-	r = amdgpu_ring_test_ring(ring);
-	if (r) {
-		ring->sched.ready = false;
+	r = amdgpu_ring_test_helper(ring);
+	if (r)
 		goto done;
-	}
 
 done:
 	if (!r)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
index 395c2259f979..93edf9193a7b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_5.c
@@ -25,6 +25,7 @@
 
 #include "amdgpu.h"
 #include "amdgpu_vcn.h"
+#include "amdgpu_pm.h"
 #include "soc15.h"
 #include "soc15d.h"
 #include "vcn_v2_0.h"
@@ -255,32 +256,24 @@ static int vcn_v2_5_hw_init(void *handle)
 			continue;
 		ring = &adev->vcn.inst[j].ring_dec;
 
-		adev->nbio_funcs->vcn_doorbell_range(adev, ring->use_doorbell,
+		adev->nbio.funcs->vcn_doorbell_range(adev, ring->use_doorbell,
 						     ring->doorbell_index, j);
 
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->sched.ready = false;
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
 			goto done;
-		}
 
 		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
 			ring = &adev->vcn.inst[j].ring_enc[i];
-			ring->sched.ready = false;
-			continue;
-			r = amdgpu_ring_test_ring(ring);
-			if (r) {
-				ring->sched.ready = false;
+			r = amdgpu_ring_test_helper(ring);
+			if (r)
 				goto done;
-			}
 		}
 
 		ring = &adev->vcn.inst[j].ring_jpeg;
-		r = amdgpu_ring_test_ring(ring);
-		if (r) {
-			ring->sched.ready = false;
+		r = amdgpu_ring_test_helper(ring);
+		if (r)
 			goto done;
-		}
 	}
 done:
 	if (!r)
@@ -300,7 +293,7 @@ static int vcn_v2_5_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct amdgpu_ring *ring;
-	int i;
+	int i, j;
 
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
@@ -312,8 +305,8 @@ static int vcn_v2_5_hw_fini(void *handle)
 
 		ring->sched.ready = false;
 
-		for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-			ring = &adev->vcn.inst[i].ring_enc[i];
+		for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
+			ring = &adev->vcn.inst[i].ring_enc[j];
 			ring->sched.ready = false;
 		}
 
@@ -423,7 +416,6 @@ static void vcn_v2_5_mc_resume(struct amdgpu_device *adev)
  * vcn_v2_5_disable_clock_gating - disable VCN clock gating
  *
  * @adev: amdgpu_device pointer
- * @sw: enable SW clock gating
  *
  * Disable clock gating for VCN block
  */
@@ -542,7 +534,6 @@ static void vcn_v2_5_disable_clock_gating(struct amdgpu_device *adev)
  * vcn_v2_5_enable_clock_gating - enable VCN clock gating
  *
  * @adev: amdgpu_device pointer
- * @sw: enable SW clock gating
  *
  * Enable clock gating for VCN block
  */
@@ -716,6 +707,9 @@ static int vcn_v2_5_start(struct amdgpu_device *adev)
 	uint32_t rb_bufsz, tmp;
 	int i, j, k, r;
 
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_uvd(adev, true);
+
 	for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
 		if (adev->vcn.harvest_config & (1 << i))
 			continue;
@@ -946,6 +940,9 @@ static int vcn_v2_5_stop(struct amdgpu_device *adev)
 			~UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
 	}
 
+	if (adev->pm.dpm_enabled)
+		amdgpu_dpm_enable_uvd(adev, false);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
index 9eae3536ddad..5cb7e231de5f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_ih.c
@@ -226,7 +226,7 @@ static int vega10_ih_irq_init(struct amdgpu_device *adev)
 	/* disable irqs */
 	vega10_ih_disable_interrupts(adev);
 
-	adev->nbio_funcs->ih_control(adev);
+	adev->nbio.funcs->ih_control(adev);
 
 	ih = &adev->irq.ih;
 	/* Ring Buffer base. [39:8] of 40-bit address of the beginning of the ring buffer*/
@@ -675,10 +675,49 @@ static int vega10_ih_soft_reset(void *handle)
 	return 0;
 }
 
+static void vega10_ih_update_clockgating_state(struct amdgpu_device *adev,
+					       bool enable)
+{
+	uint32_t data, def, field_val;
+
+	if (adev->cg_flags & AMD_CG_SUPPORT_IH_CG) {
+		def = data = RREG32_SOC15(OSSSYS, 0, mmIH_CLK_CTRL);
+		field_val = enable ? 0 : 1;
+		/**
+		 * Vega10 does not have IH_RETRY_INT_CAM_MEM_CLK_SOFT_OVERRIDE
+		 * and IH_BUFFER_MEM_CLK_SOFT_OVERRIDE field.
+		 */
+		if (adev->asic_type > CHIP_VEGA10) {
+			data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     IH_RETRY_INT_CAM_MEM_CLK_SOFT_OVERRIDE, field_val);
+			data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     IH_BUFFER_MEM_CLK_SOFT_OVERRIDE, field_val);
+		}
+
+		data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     DBUS_MUX_CLK_SOFT_OVERRIDE, field_val);
+		data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     OSSSYS_SHARE_CLK_SOFT_OVERRIDE, field_val);
+		data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     LIMIT_SMN_CLK_SOFT_OVERRIDE, field_val);
+		data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     DYN_CLK_SOFT_OVERRIDE, field_val);
+		data = REG_SET_FIELD(data, IH_CLK_CTRL,
+				     REG_CLK_SOFT_OVERRIDE, field_val);
+		if (def != data)
+			WREG32_SOC15(OSSSYS, 0, mmIH_CLK_CTRL, data);
+	}
+}
+
 static int vega10_ih_set_clockgating_state(void *handle,
 					  enum amd_clockgating_state state)
 {
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+	vega10_ih_update_clockgating_state(adev,
+				state == AMD_CG_STATE_GATE ? true : false);
 	return 0;
+
 }
 
 static int vega10_ih_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
index bd0580334f83..6b52a539d51b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
@@ -24,7 +24,6 @@
 #include "soc15.h"
 
 #include "soc15_common.h"
-#include "soc15_hw_ip.h"
 #include "vega10_ip_offset.h"
 
 int vega10_reg_base_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
index 587e33f5dcce..556f854e3551 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega20_reg_init.c
@@ -24,7 +24,6 @@
 #include "soc15.h"
 
 #include "soc15_common.h"
-#include "soc15_hw_ip.h"
 #include "vega20_ip_offset.h"
 
 int vega20_reg_base_init(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 5f8c8786cac5..f1b171e30774 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -689,16 +689,50 @@ static int vi_gpu_pci_config_reset(struct amdgpu_device *adev)
 	return -EINVAL;
 }
 
+int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap)
+{
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->get_asic_baco_capability) {
+		*cap = false;
+		return -ENOENT;
+	}
+
+	return pp_funcs->get_asic_baco_capability(pp_handle, cap);
+}
+
+int smu7_asic_baco_reset(struct amdgpu_device *adev)
+{
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs ||!pp_funcs->get_asic_baco_state ||!pp_funcs->set_asic_baco_state)
+		return -ENOENT;
+
+	/* enter BACO state */
+	if (pp_funcs->set_asic_baco_state(pp_handle, 1))
+		return -EIO;
+
+	/* exit BACO state */
+	if (pp_funcs->set_asic_baco_state(pp_handle, 0))
+		return -EIO;
+
+	dev_info(adev->dev, "GPU BACO reset\n");
+
+	return 0;
+}
+
 /**
- * vi_asic_reset - soft reset GPU
+ * vi_asic_pci_config_reset - soft reset GPU
  *
  * @adev: amdgpu_device pointer
  *
- * Look up which blocks are hung and attempt
- * to reset them.
+ * Use PCI Config method to reset the GPU.
+ *
  * Returns 0 for success.
  */
-static int vi_asic_reset(struct amdgpu_device *adev)
+static int vi_asic_pci_config_reset(struct amdgpu_device *adev)
 {
 	int r;
 
@@ -714,7 +748,50 @@ static int vi_asic_reset(struct amdgpu_device *adev)
 static enum amd_reset_method
 vi_asic_reset_method(struct amdgpu_device *adev)
 {
-	return AMD_RESET_METHOD_LEGACY;
+	bool baco_reset;
+
+	switch (adev->asic_type) {
+	case CHIP_FIJI:
+	case CHIP_TONGA:
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_TOPAZ:
+		smu7_asic_get_baco_capability(adev, &baco_reset);
+		break;
+	default:
+		baco_reset = false;
+		break;
+	}
+
+	if (baco_reset)
+		return AMD_RESET_METHOD_BACO;
+	else
+		return AMD_RESET_METHOD_LEGACY;
+}
+
+/**
+ * vi_asic_reset - soft reset GPU
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Look up which blocks are hung and attempt
+ * to reset them.
+ * Returns 0 for success.
+ */
+static int vi_asic_reset(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (vi_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) {
+		if (!adev->in_suspend)
+			amdgpu_inc_vram_lost(adev);
+		r = smu7_asic_baco_reset(adev);
+	} else {
+		r = vi_asic_pci_config_reset(adev);
+	}
+
+	return r;
 }
 
 static u32 vi_get_config_memsize(struct amdgpu_device *adev)
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.h b/drivers/gpu/drm/amd/amdgpu/vi.h
index 8de0772f986c..40d4174913a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.h
+++ b/drivers/gpu/drm/amd/amdgpu/vi.h
@@ -31,4 +31,7 @@ void vi_srbm_select(struct amdgpu_device *adev,
 int vi_set_ip_blocks(struct amdgpu_device *adev);
 
 void legacy_doorbell_index_init(struct amdgpu_device *adev);
+int smu7_asic_get_baco_capability(struct amdgpu_device *adev, bool *cap);
+int smu7_asic_baco_reset(struct amdgpu_device *adev);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/Kconfig b/drivers/gpu/drm/amd/amdkfd/Kconfig
index a1a35d4d594b..ba0e68057a89 100644
--- a/drivers/gpu/drm/amd/amdkfd/Kconfig
+++ b/drivers/gpu/drm/amd/amdkfd/Kconfig
@@ -5,7 +5,7 @@
 
 config HSA_AMD
 	bool "HSA kernel driver for AMD GPU devices"
-	depends on DRM_AMDGPU && (X86_64 || ARM64)
+	depends on DRM_AMDGPU && (X86_64 || ARM64 || PPC64)
 	imply AMD_IOMMU_V2 if X86_64
 	select MMU_NOTIFIER
 	help
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 177d1e5329a5..9f59ba93cfe0 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -33,7 +33,9 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 	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;
+	unsigned int vmid;
+	uint16_t pasid;
+	bool ret;
 
 	/* This workaround is due to HW/FW limitation on Hawaii that
 	 * VMID and PASID are not written into ih_ring_entry
@@ -48,13 +50,13 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 		*tmp_ihre = *ihre;
 
 		vmid = f2g->read_vmid_from_vmfault_reg(dev->kgd);
-		pasid = f2g->get_atc_vmid_pasid_mapping_pasid(dev->kgd, vmid);
+		ret = f2g->get_atc_vmid_pasid_mapping_info(dev->kgd, vmid, &pasid);
 
 		tmp_ihre->ring_id &= 0x000000ff;
 		tmp_ihre->ring_id |= vmid << 8;
 		tmp_ihre->ring_id |= pasid << 16;
 
-		return (pasid != 0) &&
+		return ret && (pasid != 0) &&
 			vmid >= dev->vm_info.first_vmid_kfd &&
 			vmid <= dev->vm_info.last_vmid_kfd;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index 901fe3590165..d3400da6ab64 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -905,7 +905,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x7a5d0000, 0x807c817c,
 	0x807aff7a, 0x00000080,
 	0xbf0a717c, 0xbf85fff8,
-	0xbf820141, 0xbef4037e,
+	0xbf820142, 0xbef4037e,
 	0x8775ff7f, 0x0000ffff,
 	0x8875ff75, 0x00040000,
 	0xbef60380, 0xbef703ff,
@@ -967,7 +967,7 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x725d0000, 0xe0304080,
 	0x725d0100, 0xe0304100,
 	0x725d0200, 0xe0304180,
-	0x725d0300, 0xbf820031,
+	0x725d0300, 0xbf820032,
 	0xbef603ff, 0x01000000,
 	0xbef20378, 0x8078ff78,
 	0x00000400, 0xbefc0384,
@@ -992,83 +992,84 @@ static const uint32_t cwsr_trap_gfx10_hex[] = {
 	0x725d0000, 0xe0304100,
 	0x725d0100, 0xe0304200,
 	0x725d0200, 0xe0304300,
-	0x725d0300, 0xb9782a05,
-	0x80788178, 0x907c9973,
-	0x877c817c, 0xbf06817c,
-	0xbf850002, 0x8f788978,
-	0xbf820001, 0x8f788a78,
-	0xb9721e06, 0x8f728a72,
-	0x80787278, 0x8078ff78,
-	0x00000200, 0x80f8ff78,
-	0x00000050, 0xbef603ff,
-	0x01000000, 0xbefc03ff,
-	0x0000006c, 0x80f89078,
-	0xf429003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc847c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0x80f8a078,
-	0xf42d003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc887c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0xbe843104,
-	0xbe863106, 0x80f8c078,
-	0xf431003a, 0xf0000000,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe803100,
-	0xbe823102, 0xbe843104,
-	0xbe863106, 0xbe883108,
-	0xbe8a310a, 0xbe8c310c,
-	0xbe8e310e, 0xbf06807c,
-	0xbf84fff0, 0xb9782a05,
-	0x80788178, 0x907c9973,
-	0x877c817c, 0xbf06817c,
-	0xbf850002, 0x8f788978,
-	0xbf820001, 0x8f788a78,
-	0xb9721e06, 0x8f728a72,
-	0x80787278, 0x8078ff78,
-	0x00000200, 0xbef603ff,
-	0x01000000, 0xf4211bfa,
+	0x725d0300, 0xbf8c3f70,
+	0xb9782a05, 0x80788178,
+	0x907c9973, 0x877c817c,
+	0xbf06817c, 0xbf850002,
+	0x8f788978, 0xbf820001,
+	0x8f788a78, 0xb9721e06,
+	0x8f728a72, 0x80787278,
+	0x8078ff78, 0x00000200,
+	0x80f8ff78, 0x00000050,
+	0xbef603ff, 0x01000000,
+	0xbefc03ff, 0x0000006c,
+	0x80f89078, 0xf429003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc847c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0x80f8a078, 0xf42d003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc887c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0xbe843104, 0xbe863106,
+	0x80f8c078, 0xf431003a,
+	0xf0000000, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe803100, 0xbe823102,
+	0xbe843104, 0xbe863106,
+	0xbe883108, 0xbe8a310a,
+	0xbe8c310c, 0xbe8e310e,
+	0xbf06807c, 0xbf84fff0,
+	0xb9782a05, 0x80788178,
+	0x907c9973, 0x877c817c,
+	0xbf06817c, 0xbf850002,
+	0x8f788978, 0xbf820001,
+	0x8f788a78, 0xb9721e06,
+	0x8f728a72, 0x80787278,
+	0x8078ff78, 0x00000200,
+	0xbef603ff, 0x01000000,
+	0xf4211bfa, 0xf0000000,
+	0x80788478, 0xf4211b3a,
 	0xf0000000, 0x80788478,
-	0xf4211b3a, 0xf0000000,
-	0x80788478, 0xf4211b7a,
+	0xf4211b7a, 0xf0000000,
+	0x80788478, 0xf4211eba,
 	0xf0000000, 0x80788478,
-	0xf4211eba, 0xf0000000,
-	0x80788478, 0xf4211efa,
+	0xf4211efa, 0xf0000000,
+	0x80788478, 0xf4211c3a,
 	0xf0000000, 0x80788478,
-	0xf4211c3a, 0xf0000000,
-	0x80788478, 0xf4211c7a,
+	0xf4211c7a, 0xf0000000,
+	0x80788478, 0xf4211e7a,
 	0xf0000000, 0x80788478,
-	0xf4211e7a, 0xf0000000,
-	0x80788478, 0xf4211cfa,
+	0xf4211cfa, 0xf0000000,
+	0x80788478, 0xf4211bba,
 	0xf0000000, 0x80788478,
+	0xbf8cc07f, 0xb9eef814,
 	0xf4211bba, 0xf0000000,
 	0x80788478, 0xbf8cc07f,
-	0xb9eef814, 0xf4211bba,
-	0xf0000000, 0x80788478,
-	0xbf8cc07f, 0xb9eef815,
-	0xbef2036d, 0x876dff72,
-	0x0000ffff, 0xbefc036f,
-	0xbefe037a, 0xbeff037b,
-	0x876f71ff, 0x000003ff,
-	0xb9ef4803, 0xb9f9f816,
-	0x876f71ff, 0xfffff800,
-	0x906f8b6f, 0xb9efa2c3,
-	0xb9f3f801, 0x876fff72,
-	0xfc000000, 0x906f9a6f,
-	0x8f6f906f, 0xbef30380,
+	0xb9eef815, 0xbef2036d,
+	0x876dff72, 0x0000ffff,
+	0xbefc036f, 0xbefe037a,
+	0xbeff037b, 0x876f71ff,
+	0x000003ff, 0xb9ef4803,
+	0xb9f9f816, 0x876f71ff,
+	0xfffff800, 0x906f8b6f,
+	0xb9efa2c3, 0xb9f3f801,
+	0x876fff72, 0xfc000000,
+	0x906f9a6f, 0x8f6f906f,
+	0xbef30380, 0x88736f73,
+	0x876fff72, 0x02000000,
+	0x906f996f, 0x8f6f8f6f,
 	0x88736f73, 0x876fff72,
-	0x02000000, 0x906f996f,
-	0x8f6f8f6f, 0x88736f73,
-	0x876fff72, 0x01000000,
-	0x906f986f, 0x8f6f996f,
-	0x88736f73, 0x876fff70,
-	0x00800000, 0x906f976f,
-	0xb9f3f807, 0x87fe7e7e,
-	0x87ea6a6a, 0xb9f0f802,
-	0xbf8a0000, 0xbe80226c,
-	0xbf810000, 0xbf9f0000,
+	0x01000000, 0x906f986f,
+	0x8f6f996f, 0x88736f73,
+	0x876fff70, 0x00800000,
+	0x906f976f, 0xb9f3f807,
+	0x87fe7e7e, 0x87ea6a6a,
+	0xb9f0f802, 0xbf8a0000,
+	0xbe80226c, 0xbf810000,
 	0xbf9f0000, 0xbf9f0000,
 	0xbf9f0000, 0xbf9f0000,
+	0xbf9f0000, 0x00000000,
 };
 static const uint32_t cwsr_trap_arcturus_hex[] = {
 	0xbf820001, 0xbf8202c4,
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
index cdaa523ce6be..4433bda2ce25 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx10.asm
@@ -758,6 +758,7 @@ L_RESTORE_V0:
 	buffer_load_dword	v1, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256
 	buffer_load_dword	v2, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*2
 	buffer_load_dword	v3, v0, s_restore_buf_rsrc0, s_restore_mem_offset_save slc:1 glc:1 offset:256*3
+	s_waitcnt	vmcnt(0)
 
 	/* restore SGPRs */
 	//will be 2+8+16*6
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 1d3cd5c50d5f..9af45d07515b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -282,7 +282,7 @@ static int kfd_ioctl_create_queue(struct file *filep, struct kfd_process *p,
 		goto err_bind_process;
 	}
 
-	pr_debug("Creating queue for PASID %d on gpu 0x%x\n",
+	pr_debug("Creating queue for PASID 0x%x on gpu 0x%x\n",
 			p->pasid,
 			dev->id);
 
@@ -332,7 +332,7 @@ static int kfd_ioctl_destroy_queue(struct file *filp, struct kfd_process *p,
 	int retval;
 	struct kfd_ioctl_destroy_queue_args *args = data;
 
-	pr_debug("Destroying queue id %d for pasid %d\n",
+	pr_debug("Destroying queue id %d for pasid 0x%x\n",
 				args->queue_id,
 				p->pasid);
 
@@ -378,7 +378,7 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
 	properties.queue_percent = args->queue_percentage;
 	properties.priority = args->queue_priority;
 
-	pr_debug("Updating queue id %d for pasid %d\n",
+	pr_debug("Updating queue id %d for pasid 0x%x\n",
 			args->queue_id, p->pasid);
 
 	mutex_lock(&p->mutex);
@@ -855,7 +855,7 @@ static int kfd_ioctl_get_process_apertures(struct file *filp,
 	struct kfd_process_device_apertures *pAperture;
 	struct kfd_process_device *pdd;
 
-	dev_dbg(kfd_device, "get apertures for PASID %d", p->pasid);
+	dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid);
 
 	args->num_of_nodes = 0;
 
@@ -913,7 +913,7 @@ static int kfd_ioctl_get_process_apertures_new(struct file *filp,
 	uint32_t nodes = 0;
 	int ret;
 
-	dev_dbg(kfd_device, "get apertures for PASID %d", p->pasid);
+	dev_dbg(kfd_device, "get apertures for PASID 0x%x", p->pasid);
 
 	if (args->num_of_nodes == 0) {
 		/* Return number of nodes, so that user space can alloacate
@@ -1128,7 +1128,7 @@ static int kfd_ioctl_set_scratch_backing_va(struct file *filep,
 	mutex_unlock(&p->mutex);
 
 	if (dev->dqm->sched_policy == KFD_SCHED_POLICY_NO_HWS &&
-	    pdd->qpd.vmid != 0)
+	    pdd->qpd.vmid != 0 && dev->kfd2kgd->set_scratch_backing_va)
 		dev->kfd2kgd->set_scratch_backing_va(
 			dev->kgd, args->va_addr, pdd->qpd.vmid);
 
@@ -1801,7 +1801,7 @@ static long kfd_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 	} else
 		goto err_i1;
 
-	dev_dbg(kfd_device, "ioctl cmd 0x%x (#%d), arg 0x%lx\n", cmd, nr, arg);
+	dev_dbg(kfd_device, "ioctl cmd 0x%x (#0x%x), arg 0x%lx\n", cmd, nr, arg);
 
 	process = kfd_get_process(current);
 	if (IS_ERR(process)) {
@@ -1856,7 +1856,8 @@ err_i1:
 		kfree(kdata);
 
 	if (retcode)
-		dev_dbg(kfd_device, "ret = %d\n", retcode);
+		dev_dbg(kfd_device, "ioctl cmd (#0x%x), arg 0x%lx, ret = %d\n",
+				nr, arg, retcode);
 
 	return retcode;
 }
@@ -1877,7 +1878,7 @@ static int kfd_mmio_mmap(struct kfd_dev *dev, struct kfd_process *process,
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
-	pr_debug("Process %d mapping mmio page\n"
+	pr_debug("pasid 0x%x mapping mmio page\n"
 		 "     target user address == 0x%08llX\n"
 		 "     physical address    == 0x%08llX\n"
 		 "     vm_flags            == 0x%04lX\n"
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 66387caf966e..de9f68d5c312 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -138,6 +138,7 @@ static struct kfd_gpu_cache_info carrizo_cache_info[] = {
 /* TODO - check & update Vega10 cache details */
 #define vega10_cache_info carrizo_cache_info
 #define raven_cache_info carrizo_cache_info
+#define renoir_cache_info carrizo_cache_info
 /* TODO - check & update Navi10 cache details */
 #define navi10_cache_info carrizo_cache_info
 
@@ -670,7 +671,13 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 		pcache_info = raven_cache_info;
 		num_of_cache_types = ARRAY_SIZE(raven_cache_info);
 		break;
+	case CHIP_RENOIR:
+		pcache_info = renoir_cache_info;
+		num_of_cache_types = ARRAY_SIZE(renoir_cache_info);
+		break;
 	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
 		pcache_info = navi10_cache_info;
 		num_of_cache_types = ARRAY_SIZE(navi10_cache_info);
 		break;
@@ -703,7 +710,7 @@ static int kfd_fill_gpu_cache_info(struct kfd_dev *kdev,
 						pcache_info,
 						cu_info,
 						mem_available,
-						cu_info->cu_bitmap[i][j],
+						cu_info->cu_bitmap[i % 4][j + i / 4],
 						ct,
 						cu_processor_id,
 						k);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index a3441b0e385b..d59f2cd056c6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -761,6 +761,7 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p)
 {
 	int status = 0;
 	unsigned int vmid;
+	uint16_t queried_pasid;
 	union SQ_CMD_BITS reg_sq_cmd;
 	union GRBM_GFX_INDEX_BITS reg_gfx_index;
 	struct kfd_process_device *pdd;
@@ -782,19 +783,18 @@ int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p)
 	 */
 
 	for (vmid = first_vmid_to_scan; vmid <= last_vmid_to_scan; vmid++) {
-		if (dev->kfd2kgd->get_atc_vmid_pasid_mapping_valid
-				(dev->kgd, vmid)) {
-			if (dev->kfd2kgd->get_atc_vmid_pasid_mapping_pasid
-					(dev->kgd, vmid) == p->pasid) {
-				pr_debug("Killing wave fronts of vmid %d and pasid %d\n",
-						vmid, p->pasid);
-				break;
-			}
+		status = dev->kfd2kgd->get_atc_vmid_pasid_mapping_info
+				(dev->kgd, vmid, &queried_pasid);
+
+		if (status && queried_pasid == p->pasid) {
+			pr_debug("Killing wave fronts of vmid %d and pasid 0x%x\n",
+					vmid, p->pasid);
+			break;
 		}
 	}
 
 	if (vmid > last_vmid_to_scan) {
-		pr_err("Didn't find vmid for pasid %d\n", p->pasid);
+		pr_err("Didn't find vmid for pasid 0x%x\n", p->pasid);
 		return -EFAULT;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
index 9d4af961c5d1..9bfa50633654 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgmgr.c
@@ -96,7 +96,7 @@ bool kfd_dbgmgr_create(struct kfd_dbgmgr **ppmgr, struct kfd_dev *pdev)
 long kfd_dbgmgr_register(struct kfd_dbgmgr *pmgr, struct kfd_process *p)
 {
 	if (pmgr->pasid != 0) {
-		pr_debug("H/W debugger is already active using pasid %d\n",
+		pr_debug("H/W debugger is already active using pasid 0x%x\n",
 				pmgr->pasid);
 		return -EBUSY;
 	}
@@ -117,7 +117,7 @@ long kfd_dbgmgr_unregister(struct kfd_dbgmgr *pmgr, struct kfd_process *p)
 {
 	/* Is the requests coming from the already registered process? */
 	if (pmgr->pasid != p->pasid) {
-		pr_debug("H/W debugger is not registered by calling pasid %d\n",
+		pr_debug("H/W debugger is not registered by calling pasid 0x%x\n",
 				p->pasid);
 		return -EINVAL;
 	}
@@ -134,7 +134,7 @@ long kfd_dbgmgr_wave_control(struct kfd_dbgmgr *pmgr,
 {
 	/* Is the requests coming from the already registered process? */
 	if (pmgr->pasid != wac_info->process->pasid) {
-		pr_debug("H/W debugger support was not registered for requester pasid %d\n",
+		pr_debug("H/W debugger support was not registered for requester pasid 0x%x\n",
 				wac_info->process->pasid);
 		return -EINVAL;
 	}
@@ -147,7 +147,7 @@ long kfd_dbgmgr_address_watch(struct kfd_dbgmgr *pmgr,
 {
 	/* Is the requests coming from the already registered process? */
 	if (pmgr->pasid != adw_info->process->pasid) {
-		pr_debug("H/W debugger support was not registered for requester pasid %d\n",
+		pr_debug("H/W debugger support was not registered for requester pasid 0x%x\n",
 				adw_info->process->pasid);
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 0dc1084b5e82..4fa8834ce7cb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -39,6 +39,41 @@
  */
 static atomic_t kfd_locked = ATOMIC_INIT(0);
 
+#ifdef CONFIG_DRM_AMDGPU_CIK
+extern const struct kfd2kgd_calls gfx_v7_kfd2kgd;
+#endif
+extern const struct kfd2kgd_calls gfx_v8_kfd2kgd;
+extern const struct kfd2kgd_calls gfx_v9_kfd2kgd;
+extern const struct kfd2kgd_calls arcturus_kfd2kgd;
+extern const struct kfd2kgd_calls gfx_v10_kfd2kgd;
+
+static const struct kfd2kgd_calls *kfd2kgd_funcs[] = {
+#ifdef KFD_SUPPORT_IOMMU_V2
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	[CHIP_KAVERI] = &gfx_v7_kfd2kgd,
+#endif
+	[CHIP_CARRIZO] = &gfx_v8_kfd2kgd,
+	[CHIP_RAVEN] = &gfx_v9_kfd2kgd,
+#endif
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	[CHIP_HAWAII] = &gfx_v7_kfd2kgd,
+#endif
+	[CHIP_TONGA] = &gfx_v8_kfd2kgd,
+	[CHIP_FIJI] = &gfx_v8_kfd2kgd,
+	[CHIP_POLARIS10] = &gfx_v8_kfd2kgd,
+	[CHIP_POLARIS11] = &gfx_v8_kfd2kgd,
+	[CHIP_POLARIS12] = &gfx_v8_kfd2kgd,
+	[CHIP_VEGAM] = &gfx_v8_kfd2kgd,
+	[CHIP_VEGA10] = &gfx_v9_kfd2kgd,
+	[CHIP_VEGA12] = &gfx_v9_kfd2kgd,
+	[CHIP_VEGA20] = &gfx_v9_kfd2kgd,
+	[CHIP_RENOIR] = &gfx_v9_kfd2kgd,
+	[CHIP_ARCTURUS] = &arcturus_kfd2kgd,
+	[CHIP_NAVI10] = &gfx_v10_kfd2kgd,
+	[CHIP_NAVI12] = &gfx_v10_kfd2kgd,
+	[CHIP_NAVI14] = &gfx_v10_kfd2kgd,
+};
+
 #ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
 	.asic_family = CHIP_KAVERI,
@@ -351,6 +386,24 @@ static const struct kfd_device_info arcturus_device_info = {
 	.num_sdma_queues_per_engine = 8,
 };
 
+static const struct kfd_device_info renoir_device_info = {
+	.asic_family = CHIP_RENOIR,
+	.asic_name = "renoir",
+	.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 = false,
+	.needs_pci_atomics = false,
+	.num_sdma_engines = 1,
+	.num_xgmi_sdma_engines = 0,
+	.num_sdma_queues_per_engine = 2,
+};
+
 static const struct kfd_device_info navi10_device_info = {
 	.asic_family = CHIP_NAVI10,
 	.asic_name = "navi10",
@@ -369,133 +422,64 @@ static const struct kfd_device_info navi10_device_info = {
 	.num_sdma_queues_per_engine = 8,
 };
 
-struct kfd_deviceid {
-	unsigned short did;
-	const struct kfd_device_info *device_info;
+static const struct kfd_device_info navi12_device_info = {
+	.asic_family = CHIP_NAVI12,
+	.asic_name = "navi12",
+	.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,
+	.needs_iommu_device = false,
+	.supports_cwsr = true,
+	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
+	.num_sdma_queues_per_engine = 8,
+};
+
+static const struct kfd_device_info navi14_device_info = {
+	.asic_family = CHIP_NAVI14,
+	.asic_name = "navi14",
+	.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,
+	.needs_iommu_device = false,
+	.supports_cwsr = true,
+	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
+	.num_xgmi_sdma_engines = 0,
+	.num_sdma_queues_per_engine = 8,
 };
 
-static const struct kfd_deviceid supported_devices[] = {
+/* For each entry, [0] is regular and [1] is virtualisation device. */
+static const struct kfd_device_info *kfd_supported_devices[][2] = {
 #ifdef KFD_SUPPORT_IOMMU_V2
-	{ 0x1304, &kaveri_device_info },	/* Kaveri */
-	{ 0x1305, &kaveri_device_info },	/* Kaveri */
-	{ 0x1306, &kaveri_device_info },	/* Kaveri */
-	{ 0x1307, &kaveri_device_info },	/* Kaveri */
-	{ 0x1309, &kaveri_device_info },	/* Kaveri */
-	{ 0x130A, &kaveri_device_info },	/* Kaveri */
-	{ 0x130B, &kaveri_device_info },	/* Kaveri */
-	{ 0x130C, &kaveri_device_info },	/* Kaveri */
-	{ 0x130D, &kaveri_device_info },	/* Kaveri */
-	{ 0x130E, &kaveri_device_info },	/* Kaveri */
-	{ 0x130F, &kaveri_device_info },	/* Kaveri */
-	{ 0x1310, &kaveri_device_info },	/* Kaveri */
-	{ 0x1311, &kaveri_device_info },	/* Kaveri */
-	{ 0x1312, &kaveri_device_info },	/* Kaveri */
-	{ 0x1313, &kaveri_device_info },	/* Kaveri */
-	{ 0x1315, &kaveri_device_info },	/* Kaveri */
-	{ 0x1316, &kaveri_device_info },	/* Kaveri */
-	{ 0x1317, &kaveri_device_info },	/* Kaveri */
-	{ 0x1318, &kaveri_device_info },	/* Kaveri */
-	{ 0x131B, &kaveri_device_info },	/* Kaveri */
-	{ 0x131C, &kaveri_device_info },	/* Kaveri */
-	{ 0x131D, &kaveri_device_info },	/* Kaveri */
-	{ 0x9870, &carrizo_device_info },	/* Carrizo */
-	{ 0x9874, &carrizo_device_info },	/* Carrizo */
-	{ 0x9875, &carrizo_device_info },	/* Carrizo */
-	{ 0x9876, &carrizo_device_info },	/* Carrizo */
-	{ 0x9877, &carrizo_device_info },	/* Carrizo */
-	{ 0x15DD, &raven_device_info },		/* Raven */
-	{ 0x15D8, &raven_device_info },		/* Raven */
+	[CHIP_KAVERI] = {&kaveri_device_info, NULL},
+	[CHIP_CARRIZO] = {&carrizo_device_info, NULL},
+	[CHIP_RAVEN] = {&raven_device_info, NULL},
 #endif
-	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
-	{ 0x67A1, &hawaii_device_info },	/* Hawaii */
-	{ 0x67A2, &hawaii_device_info },	/* Hawaii */
-	{ 0x67A8, &hawaii_device_info },	/* Hawaii */
-	{ 0x67A9, &hawaii_device_info },	/* Hawaii */
-	{ 0x67AA, &hawaii_device_info },	/* Hawaii */
-	{ 0x67B0, &hawaii_device_info },	/* Hawaii */
-	{ 0x67B1, &hawaii_device_info },	/* Hawaii */
-	{ 0x67B8, &hawaii_device_info },	/* Hawaii */
-	{ 0x67B9, &hawaii_device_info },	/* Hawaii */
-	{ 0x67BA, &hawaii_device_info },	/* Hawaii */
-	{ 0x67BE, &hawaii_device_info },	/* Hawaii */
-	{ 0x6920, &tonga_device_info },		/* Tonga */
-	{ 0x6921, &tonga_device_info },		/* Tonga */
-	{ 0x6928, &tonga_device_info },		/* Tonga */
-	{ 0x6929, &tonga_device_info },		/* Tonga */
-	{ 0x692B, &tonga_device_info },		/* Tonga */
-	{ 0x6938, &tonga_device_info },		/* Tonga */
-	{ 0x6939, &tonga_device_info },		/* Tonga */
-	{ 0x7300, &fiji_device_info },		/* Fiji */
-	{ 0x730F, &fiji_vf_device_info },	/* Fiji vf*/
-	{ 0x67C0, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67C1, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67C2, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67C4, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67C7, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67C8, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67C9, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67CA, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67CC, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67CF, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67D0, &polaris10_vf_device_info },	/* Polaris10 vf*/
-	{ 0x67DF, &polaris10_device_info },	/* Polaris10 */
-	{ 0x6FDF, &polaris10_device_info },	/* Polaris10 */
-	{ 0x67E0, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67E1, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67E3, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67E7, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67E8, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67E9, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67EB, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67EF, &polaris11_device_info },	/* Polaris11 */
-	{ 0x67FF, &polaris11_device_info },	/* Polaris11 */
-	{ 0x6980, &polaris12_device_info },	/* Polaris12 */
-	{ 0x6981, &polaris12_device_info },	/* Polaris12 */
-	{ 0x6985, &polaris12_device_info },	/* Polaris12 */
-	{ 0x6986, &polaris12_device_info },	/* Polaris12 */
-	{ 0x6987, &polaris12_device_info },	/* Polaris12 */
-	{ 0x6995, &polaris12_device_info },	/* Polaris12 */
-	{ 0x6997, &polaris12_device_info },	/* Polaris12 */
-	{ 0x699F, &polaris12_device_info },	/* Polaris12 */
-	{ 0x694C, &vegam_device_info },		/* VegaM */
-	{ 0x694E, &vegam_device_info },		/* VegaM */
-	{ 0x694F, &vegam_device_info },		/* VegaM */
-	{ 0x6860, &vega10_device_info },	/* Vega10 */
-	{ 0x6861, &vega10_device_info },	/* Vega10 */
-	{ 0x6862, &vega10_device_info },	/* Vega10 */
-	{ 0x6863, &vega10_device_info },	/* Vega10 */
-	{ 0x6864, &vega10_device_info },	/* Vega10 */
-	{ 0x6867, &vega10_device_info },	/* Vega10 */
-	{ 0x6868, &vega10_device_info },	/* Vega10 */
-	{ 0x6869, &vega10_device_info },	/* Vega10 */
-	{ 0x686A, &vega10_device_info },	/* Vega10 */
-	{ 0x686B, &vega10_device_info },	/* Vega10 */
-	{ 0x686C, &vega10_vf_device_info },	/* Vega10  vf*/
-	{ 0x686D, &vega10_device_info },	/* Vega10 */
-	{ 0x686E, &vega10_device_info },	/* Vega10 */
-	{ 0x686F, &vega10_device_info },	/* Vega10 */
-	{ 0x687F, &vega10_device_info },	/* Vega10 */
-	{ 0x69A0, &vega12_device_info },	/* Vega12 */
-	{ 0x69A1, &vega12_device_info },	/* Vega12 */
-	{ 0x69A2, &vega12_device_info },	/* Vega12 */
-	{ 0x69A3, &vega12_device_info },	/* Vega12 */
-	{ 0x69AF, &vega12_device_info },	/* Vega12 */
-	{ 0x66a0, &vega20_device_info },	/* Vega20 */
-	{ 0x66a1, &vega20_device_info },	/* Vega20 */
-	{ 0x66a2, &vega20_device_info },	/* Vega20 */
-	{ 0x66a3, &vega20_device_info },	/* Vega20 */
-	{ 0x66a4, &vega20_device_info },	/* Vega20 */
-	{ 0x66a7, &vega20_device_info },	/* Vega20 */
-	{ 0x66af, &vega20_device_info },	/* Vega20 */
-	{ 0x738C, &arcturus_device_info },	/* Arcturus */
-	{ 0x7388, &arcturus_device_info },	/* Arcturus */
-	{ 0x738E, &arcturus_device_info },	/* Arcturus */
-	{ 0x7390, &arcturus_device_info },	/* Arcturus vf */
-	{ 0x7310, &navi10_device_info },	/* Navi10 */
-	{ 0x7312, &navi10_device_info },	/* Navi10 */
-	{ 0x7318, &navi10_device_info },	/* Navi10 */
-	{ 0x731a, &navi10_device_info },	/* Navi10 */
-	{ 0x731f, &navi10_device_info },	/* Navi10 */
+	[CHIP_HAWAII] = {&hawaii_device_info, NULL},
+	[CHIP_TONGA] = {&tonga_device_info, NULL},
+	[CHIP_FIJI] = {&fiji_device_info, &fiji_vf_device_info},
+	[CHIP_POLARIS10] = {&polaris10_device_info, &polaris10_vf_device_info},
+	[CHIP_POLARIS11] = {&polaris11_device_info, NULL},
+	[CHIP_POLARIS12] = {&polaris12_device_info, NULL},
+	[CHIP_VEGAM] = {&vegam_device_info, NULL},
+	[CHIP_VEGA10] = {&vega10_device_info, &vega10_vf_device_info},
+	[CHIP_VEGA12] = {&vega12_device_info, NULL},
+	[CHIP_VEGA20] = {&vega20_device_info, NULL},
+	[CHIP_RENOIR] = {&renoir_device_info, NULL},
+	[CHIP_ARCTURUS] = {&arcturus_device_info, &arcturus_device_info},
+	[CHIP_NAVI10] = {&navi10_device_info, NULL},
+	[CHIP_NAVI12] = {&navi12_device_info, &navi12_device_info},
+	[CHIP_NAVI14] = {&navi14_device_info, NULL},
 };
 
 static int kfd_gtt_sa_init(struct kfd_dev *kfd, unsigned int buf_size,
@@ -504,32 +488,25 @@ static void kfd_gtt_sa_fini(struct kfd_dev *kfd);
 
 static int kfd_resume(struct kfd_dev *kfd);
 
-static const struct kfd_device_info *lookup_device_info(unsigned short did)
+struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
+	struct pci_dev *pdev, unsigned int asic_type, bool vf)
 {
-	size_t i;
+	struct kfd_dev *kfd;
+	const struct kfd_device_info *device_info;
+	const struct kfd2kgd_calls *f2g;
 
-	for (i = 0; i < ARRAY_SIZE(supported_devices); i++) {
-		if (supported_devices[i].did == did) {
-			WARN_ON(!supported_devices[i].device_info);
-			return supported_devices[i].device_info;
-		}
+	if (asic_type >= sizeof(kfd_supported_devices) / (sizeof(void *) * 2)
+		|| asic_type >= sizeof(kfd2kgd_funcs) / sizeof(void *)) {
+		dev_err(kfd_device, "asic_type %d out of range\n", asic_type);
+		return NULL; /* asic_type out of range */
 	}
 
-	dev_warn(kfd_device, "DID %04x is missing in supported_devices\n",
-		 did);
+	device_info = kfd_supported_devices[asic_type][vf];
+	f2g = kfd2kgd_funcs[asic_type];
 
-	return NULL;
-}
-
-struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
-	struct pci_dev *pdev, const struct kfd2kgd_calls *f2g)
-{
-	struct kfd_dev *kfd;
-	const struct kfd_device_info *device_info =
-					lookup_device_info(pdev->device);
-
-	if (!device_info) {
-		dev_err(kfd_device, "kgd2kfd_probe failed\n");
+	if (!device_info || !f2g) {
+		dev_err(kfd_device, "%s %s not supported in kfd\n",
+			amdgpu_asic_name[asic_type], vf ? "VF" : "");
 		return NULL;
 	}
 
@@ -593,10 +570,12 @@ static void kfd_cwsr_init(struct kfd_dev *kfd)
 }
 
 bool kgd2kfd_device_init(struct kfd_dev *kfd,
+			 struct drm_device *ddev,
 			 const struct kgd2kfd_shared_resources *gpu_resources)
 {
 	unsigned int size;
 
+	kfd->ddev = ddev;
 	kfd->mec_fw_version = amdgpu_amdkfd_get_fw_version(kfd->kgd,
 			KGD_ENGINE_MEC1);
 	kfd->sdma_fw_version = amdgpu_amdkfd_get_fw_version(kfd->kgd,
@@ -751,9 +730,6 @@ int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 		return 0;
 	kgd2kfd_suspend(kfd);
 
-	/* hold dqm->lock to prevent further execution*/
-	dqm_lock(kfd->dqm);
-
 	kfd_signal_reset_event(kfd);
 	return 0;
 }
@@ -771,8 +747,6 @@ int kgd2kfd_post_reset(struct kfd_dev *kfd)
 	if (!kfd->init_complete)
 		return 0;
 
-	dqm_unlock(kfd->dqm);
-
 	ret = kfd_resume(kfd);
 	if (ret)
 		return ret;
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 d985e31fcc1e..984c2f2b24b6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -195,20 +195,30 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 			struct qcm_process_device *qpd,
 			struct queue *q)
 {
-	int bit, allocated_vmid;
+	int allocated_vmid = -1, i;
 
-	if (dqm->vmid_bitmap == 0)
-		return -ENOMEM;
+	for (i = dqm->dev->vm_info.first_vmid_kfd;
+			i <= dqm->dev->vm_info.last_vmid_kfd; i++) {
+		if (!dqm->vmid_pasid[i]) {
+			allocated_vmid = i;
+			break;
+		}
+	}
+
+	if (allocated_vmid < 0) {
+		pr_err("no more vmid to allocate\n");
+		return -ENOSPC;
+	}
+
+	pr_debug("vmid allocated: %d\n", allocated_vmid);
+
+	dqm->vmid_pasid[allocated_vmid] = q->process->pasid;
 
-	bit = ffs(dqm->vmid_bitmap) - 1;
-	dqm->vmid_bitmap &= ~(1 << bit);
+	set_pasid_vmid_mapping(dqm, q->process->pasid, allocated_vmid);
 
-	allocated_vmid = bit + dqm->dev->vm_info.first_vmid_kfd;
-	pr_debug("vmid allocation %d\n", allocated_vmid);
 	qpd->vmid = allocated_vmid;
 	q->properties.vmid = allocated_vmid;
 
-	set_pasid_vmid_mapping(dqm, q->process->pasid, q->properties.vmid);
 	program_sh_mem_settings(dqm, qpd);
 
 	/* qpd->page_table_base is set earlier when register_process()
@@ -220,8 +230,9 @@ static int allocate_vmid(struct device_queue_manager *dqm,
 	/* invalidate the VM context after pasid and vmid mapping is set up */
 	kfd_flush_tlb(qpd_to_pdd(qpd));
 
-	dqm->dev->kfd2kgd->set_scratch_backing_va(
-		dqm->dev->kgd, qpd->sh_hidden_private_base, qpd->vmid);
+	if (dqm->dev->kfd2kgd->set_scratch_backing_va)
+		dqm->dev->kfd2kgd->set_scratch_backing_va(dqm->dev->kgd,
+				qpd->sh_hidden_private_base, qpd->vmid);
 
 	return 0;
 }
@@ -248,8 +259,6 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 				struct qcm_process_device *qpd,
 				struct queue *q)
 {
-	int bit = qpd->vmid - dqm->dev->vm_info.first_vmid_kfd;
-
 	/* On GFX v7, CP doesn't flush TC at dequeue */
 	if (q->device->device_info->asic_family == CHIP_HAWAII)
 		if (flush_texture_cache_nocpsch(q->device, qpd))
@@ -259,8 +268,8 @@ static void deallocate_vmid(struct device_queue_manager *dqm,
 
 	/* Release the vmid mapping */
 	set_pasid_vmid_mapping(dqm, 0, qpd->vmid);
+	dqm->vmid_pasid[qpd->vmid] = 0;
 
-	dqm->vmid_bitmap |= (1 << bit);
 	qpd->vmid = 0;
 	q->properties.vmid = 0;
 }
@@ -331,6 +340,10 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 	mqd_mgr->init_mqd(mqd_mgr, &q->mqd, q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (q->properties.is_active) {
+		if (!dqm->sched_running) {
+			WARN_ONCE(1, "Load non-HWS mqd while stopped\n");
+			goto add_queue_to_list;
+		}
 
 		if (WARN(q->process->mm != current->mm,
 					"should only run in user thread"))
@@ -342,6 +355,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 			goto out_free_mqd;
 	}
 
+add_queue_to_list:
 	list_add(&q->list, &qpd->queues_list);
 	qpd->queue_count++;
 	if (q->properties.is_active)
@@ -449,6 +463,11 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 
 	deallocate_doorbell(qpd, q);
 
+	if (!dqm->sched_running) {
+		WARN_ONCE(1, "Destroy non-HWS queue while stopped\n");
+		return 0;
+	}
+
 	retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 				KFD_UNMAP_LATENCY_MS,
@@ -524,6 +543,12 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		   (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		    q->properties.type == KFD_QUEUE_TYPE_SDMA ||
 		    q->properties.type == KFD_QUEUE_TYPE_SDMA_XGMI)) {
+
+		if (!dqm->sched_running) {
+			WARN_ONCE(1, "Update non-HWS queue while stopped\n");
+			goto out_unlock;
+		}
+
 		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
@@ -579,7 +604,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 		goto out;
 
 	pdd = qpd_to_pdd(qpd);
-	pr_info_ratelimited("Evicting PASID %u queues\n",
+	pr_info_ratelimited("Evicting PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Mark all queues as evicted. Deactivate all active queues on
@@ -593,6 +618,11 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 		mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
 				q->properties.type)];
 		q->properties.is_active = false;
+		dqm->queue_count--;
+
+		if (WARN_ONCE(!dqm->sched_running, "Evict when stopped\n"))
+			continue;
+
 		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
@@ -601,7 +631,6 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 			 * maintain a consistent eviction state
 			 */
 			ret = retval;
-		dqm->queue_count--;
 	}
 
 out:
@@ -621,7 +650,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		goto out;
 
 	pdd = qpd_to_pdd(qpd);
-	pr_info_ratelimited("Evicting PASID %u queues\n",
+	pr_info_ratelimited("Evicting PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Mark all queues as evicted. Deactivate all active queues on
@@ -667,7 +696,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		goto out;
 	}
 
-	pr_info_ratelimited("Restoring PASID %u queues\n",
+	pr_info_ratelimited("Restoring PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Update PD Base in QPD */
@@ -702,6 +731,11 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 		mqd_mgr = dqm->mqd_mgrs[get_mqd_type_from_queue_type(
 				q->properties.type)];
 		q->properties.is_active = true;
+		dqm->queue_count++;
+
+		if (WARN_ONCE(!dqm->sched_running, "Restore when stopped\n"))
+			continue;
+
 		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
 				       q->queue, &q->properties, mm);
 		if (retval && !ret)
@@ -709,7 +743,6 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 			 * maintain a consistent eviction state
 			 */
 			ret = retval;
-		dqm->queue_count++;
 	}
 	qpd->evicted = 0;
 out:
@@ -739,7 +772,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 		goto out;
 	}
 
-	pr_info_ratelimited("Restoring PASID %u queues\n",
+	pr_info_ratelimited("Restoring PASID 0x%x queues\n",
 			    pdd->process->pasid);
 
 	/* Update PD Base in QPD */
@@ -879,7 +912,8 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 				dqm->allocated_queues[pipe] |= 1 << queue;
 	}
 
-	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
+	memset(dqm->vmid_pasid, 0, sizeof(dqm->vmid_pasid));
+
 	dqm->sdma_bitmap = ~0ULL >> (64 - get_num_sdma_queues(dqm));
 	dqm->xgmi_sdma_bitmap = ~0ULL >> (64 - get_num_xgmi_sdma_queues(dqm));
 
@@ -902,12 +936,20 @@ static void uninitialize(struct device_queue_manager *dqm)
 static int start_nocpsch(struct device_queue_manager *dqm)
 {
 	init_interrupts(dqm);
-	return pm_init(&dqm->packets, dqm);
+	
+	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
+		return pm_init(&dqm->packets, dqm);
+	dqm->sched_running = true;
+
+	return 0;
 }
 
 static int stop_nocpsch(struct device_queue_manager *dqm)
 {
-	pm_uninit(&dqm->packets);
+	if (dqm->dev->device_info->asic_family == CHIP_HAWAII)
+		pm_uninit(&dqm->packets);
+	dqm->sched_running = false;
+
 	return 0;
 }
 
@@ -1058,6 +1100,7 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	dqm_lock(dqm);
 	/* clear hang status when driver try to start the hw scheduler */
 	dqm->is_hws_hang = false;
+	dqm->sched_running = true;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	dqm_unlock(dqm);
 
@@ -1073,6 +1116,7 @@ static int stop_cpsch(struct device_queue_manager *dqm)
 {
 	dqm_lock(dqm);
 	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	dqm->sched_running = false;
 	dqm_unlock(dqm);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
@@ -1259,9 +1303,10 @@ static int map_queues_cpsch(struct device_queue_manager *dqm)
 {
 	int retval;
 
+	if (!dqm->sched_running)
+		return 0;
 	if (dqm->queue_count <= 0 || dqm->processes_count <= 0)
 		return 0;
-
 	if (dqm->active_runlist)
 		return 0;
 
@@ -1283,6 +1328,8 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval = 0;
 
+	if (!dqm->sched_running)
+		return 0;
 	if (dqm->is_hws_hang)
 		return -EIO;
 	if (!dqm->active_runlist)
@@ -1676,7 +1723,8 @@ static int allocate_hiq_sdma_mqd(struct device_queue_manager *dqm)
 	struct kfd_dev *dev = dqm->dev;
 	struct kfd_mem_obj *mem_obj = &dqm->hiq_sdma_mqd;
 	uint32_t size = dqm->mqd_mgrs[KFD_MQD_TYPE_SDMA]->mqd_size *
-		dev->device_info->num_sdma_engines *
+		(dev->device_info->num_sdma_engines +
+		dev->device_info->num_xgmi_sdma_engines) *
 		dev->device_info->num_sdma_queues_per_engine +
 		dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ]->mqd_size;
 
@@ -1786,10 +1834,13 @@ struct device_queue_manager *device_queue_manager_init(struct kfd_dev *dev)
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 	case CHIP_ARCTURUS:
 		device_queue_manager_init_v9(&dqm->asic_ops);
 		break;
 	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
 		device_queue_manager_init_v10_navi10(&dqm->asic_ops);
 		break;
 	default:
@@ -1883,6 +1934,12 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	int pipe, queue;
 	int r = 0;
 
+	if (!dqm->sched_running) {
+		seq_printf(m, " Device is stopped\n");
+
+		return 0;
+	}
+
 	r = dqm->dev->kfd2kgd->hqd_dump(dqm->dev->kgd,
 					KFD_CIK_HIQ_PIPE, KFD_CIK_HIQ_QUEUE,
 					&dump, &n_regs);
@@ -1917,7 +1974,8 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 		}
 	}
 
-	for (pipe = 0; pipe < get_num_sdma_engines(dqm); pipe++) {
+	for (pipe = 0; pipe < get_num_sdma_engines(dqm) +
+			get_num_xgmi_sdma_engines(dqm); pipe++) {
 		for (queue = 0;
 		     queue < dqm->dev->device_info->num_sdma_queues_per_engine;
 		     queue++) {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 90db2c9275f6..a8c37e6da027 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -32,6 +32,8 @@
 #include "kfd_mqd_manager.h"
 
 
+#define VMID_NUM 16
+
 struct device_process_node {
 	struct qcm_process_device *qpd;
 	struct list_head list;
@@ -185,7 +187,8 @@ struct device_queue_manager {
 	unsigned int		*allocated_queues;
 	uint64_t		sdma_bitmap;
 	uint64_t		xgmi_sdma_bitmap;
-	unsigned int		vmid_bitmap;
+	/* the pasid mapping for each kfd vmid */
+	uint16_t		vmid_pasid[VMID_NUM];
 	uint64_t		pipelines_addr;
 	struct kfd_mem_obj	*pipeline_mem;
 	uint64_t		fence_gpu_addr;
@@ -198,6 +201,7 @@ struct device_queue_manager {
 	bool			is_hws_hang;
 	struct work_struct	hw_exception_work;
 	struct kfd_mem_obj	hiq_sdma_mqd;
+	bool			sched_running;
 };
 
 void device_queue_manager_init_cik(
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index d674d4b3340f..908081c85de1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -852,8 +852,8 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 
 	if (type == KFD_EVENT_TYPE_MEMORY) {
 		dev_warn(kfd_device,
-			"Sending SIGSEGV to HSA Process with PID %d ",
-				p->lead_thread->pid);
+			"Sending SIGSEGV to process %d (pasid 0x%x)",
+				p->lead_thread->pid, p->pasid);
 		send_sig(SIGSEGV, p->lead_thread, 0);
 	}
 
@@ -861,13 +861,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 	if (send_signal) {
 		if (send_sigterm) {
 			dev_warn(kfd_device,
-				"Sending SIGTERM to HSA Process with PID %d ",
-					p->lead_thread->pid);
+				"Sending SIGTERM to process %d (pasid 0x%x)",
+					p->lead_thread->pid, p->pasid);
 			send_sig(SIGTERM, p->lead_thread, 0);
 		} else {
 			dev_err(kfd_device,
-				"HSA Process (PID %d) got unhandled exception",
-				p->lead_thread->pid);
+				"Process %d (pasid 0x%x) got unhandled exception",
+				p->lead_thread->pid, p->pasid);
 		}
 	}
 }
@@ -936,7 +936,8 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	/* 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) {
+	if (dev->device_info->asic_family != CHIP_RAVEN &&
+	    dev->device_info->asic_family != CHIP_RENOIR) {
 		mutex_lock(&p->event_mutex);
 
 		/* Lookup events by type and signal them */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
index 9dc4bff8085e..bb77b8890e77 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c
@@ -369,8 +369,13 @@ int kfd_init_apertures(struct kfd_process *process)
 
 	/*Iterating over all devices*/
 	while (kfd_topology_enum_kfd_devices(id, &dev) == 0) {
-		if (!dev) {
-			id++; /* Skip non GPU devices */
+		if (!dev || kfd_devcgroup_check_permission(dev)) {
+			/* Skip non GPU devices and devices to which the
+			 * current process have no access to. Access can be
+			 * limited by placing the process in a specific
+			 * cgroup hierarchy
+			 */
+			id++;
 			continue;
 		}
 
@@ -405,8 +410,11 @@ int kfd_init_apertures(struct kfd_process *process)
 			case CHIP_VEGA12:
 			case CHIP_VEGA20:
 			case CHIP_RAVEN:
+			case CHIP_RENOIR:
 			case CHIP_ARCTURUS:
 			case CHIP_NAVI10:
+			case CHIP_NAVI12:
+			case CHIP_NAVI14:
 				kfd_init_apertures_v9(pdd, id);
 				break;
 			default:
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 3ef67d2e0d9f..e05d75ecda21 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -54,8 +54,7 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev,
 		memcpy(patched_ihre, ih_ring_entry,
 				dev->device_info->ih_ring_entry_size);
 
-		pasid = dev->kfd2kgd->get_atc_vmid_pasid_mapping_pasid(
-				dev->kgd, vmid);
+		pasid = dev->dqm->vmid_pasid[vmid];
 
 		/* Patch the pasid field */
 		patched_ihre[3] = cpu_to_le32((le32_to_cpu(patched_ihre[3])
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index c56ac47cd318..bc47f6a44456 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -62,6 +62,11 @@ int kfd_interrupt_init(struct kfd_dev *kfd)
 	}
 
 	kfd->ih_wq = alloc_workqueue("KFD IH", WQ_HIGHPRI, 1);
+	if (unlikely(!kfd->ih_wq)) {
+		kfifo_free(&kfd->ih_fifo);
+		dev_err(kfd_chardev(), "Failed to allocate KFD IH workqueue\n");
+		return -ENOMEM;
+	}
 	spin_lock_init(&kfd->interrupt_lock);
 
 	INIT_WORK(&kfd->interrupt_work, interrupt_wq);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index 5f35df23fb18..193e2835bd4d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -160,7 +160,7 @@ static void iommu_pasid_shutdown_callback(struct pci_dev *pdev, int pasid)
 	if (!p)
 		return;
 
-	pr_debug("Unbinding process %d from IOMMU\n", pasid);
+	pr_debug("Unbinding process 0x%x from IOMMU\n", pasid);
 
 	mutex_lock(kfd_get_dbgmgr_mutex());
 
@@ -194,7 +194,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 	struct kfd_dev *dev;
 
 	dev_warn_ratelimited(kfd_device,
-			"Invalid PPR device %x:%x.%x pasid %d address 0x%lX flags 0x%X",
+			"Invalid PPR device %x:%x.%x pasid 0x%x address 0x%lX flags 0x%X",
 			PCI_BUS_NUM(pdev->devfn),
 			PCI_SLOT(pdev->devfn),
 			PCI_FUNC(pdev->devfn),
@@ -235,7 +235,7 @@ static int kfd_bind_processes_to_device(struct kfd_dev *kfd)
 		err = amd_iommu_bind_pasid(kfd->pdev, p->pasid,
 				p->lead_thread);
 		if (err < 0) {
-			pr_err("Unexpected pasid %d binding failure\n",
+			pr_err("Unexpected pasid 0x%x binding failure\n",
 					p->pasid);
 			mutex_unlock(&p->mutex);
 			break;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 8b4564f71a7a..11d244891393 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -330,10 +330,13 @@ struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 	case CHIP_ARCTURUS:
 		kernel_queue_init_v9(&kq->ops_asic_specific);
 		break;
 	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
 		kernel_queue_init_v10(&kq->ops_asic_specific);
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 986ff52d5750..f4b7f7e6c40e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -82,7 +82,7 @@ static void kfd_exit(void)
 	kfd_chardev_exit();
 }
 
-int kgd2kfd_init()
+int kgd2kfd_init(void)
 {
 	return kfd_init();
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 9cd3eb2d90bd..4a236b2c2354 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -69,35 +69,13 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
 		struct queue_properties *q)
 {
-	int retval;
-	struct kfd_mem_obj *mqd_mem_obj = NULL;
+	struct kfd_mem_obj *mqd_mem_obj;
 
-	/* From V9,  for CWSR, the control stack is located on the next page
-	 * boundary after the mqd, we will use the gtt allocation function
-	 * 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);
-		if (!mqd_mem_obj)
-			return NULL;
-		retval = amdgpu_amdkfd_alloc_gtt_mem(kfd->kgd,
-			ALIGN(q->ctl_stack_size, PAGE_SIZE) +
-				ALIGN(sizeof(struct v10_compute_mqd), PAGE_SIZE),
-			&(mqd_mem_obj->gtt_mem),
-			&(mqd_mem_obj->gpu_addr),
-			(void *)&(mqd_mem_obj->cpu_ptr), true);
-	} else {
-		retval = kfd_gtt_sa_allocate(kfd, sizeof(struct v10_compute_mqd),
-				&mqd_mem_obj);
-	}
-
-	if (retval) {
-		kfree(mqd_mem_obj);
+	if (kfd_gtt_sa_allocate(kfd, sizeof(struct v10_compute_mqd),
+			&mqd_mem_obj))
 		return NULL;
-	}
 
 	return mqd_mem_obj;
-
 }
 
 static void init_mqd(struct mqd_manager *mm, void **mqd,
@@ -250,14 +228,7 @@ static int destroy_mqd(struct mqd_manager *mm, void *mqd,
 static void free_mqd(struct mqd_manager *mm, void *mqd,
 			struct kfd_mem_obj *mqd_mem_obj)
 {
-	struct kfd_dev *kfd = mm->dev;
-
-	if (mqd_mem_obj->gtt_mem) {
-		amdgpu_amdkfd_free_gtt_mem(kfd->kgd, mqd_mem_obj->gtt_mem);
-		kfree(mqd_mem_obj);
-	} else {
-		kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
-	}
+	kfd_gtt_sa_free(mm->dev, mqd_mem_obj);
 }
 
 static bool is_occupied(struct mqd_manager *mm, void *mqd,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index 2c8624c5b42c..83ef4b3dd2fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -239,10 +239,13 @@ int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 	case CHIP_ARCTURUS:
 		pm->pmf = &kfd_v9_pm_funcs;
 		break;
 	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
 		pm->pmf = &kfd_v10_pm_funcs;
 		break;
 	default:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index c89326125d71..060a9e8b301e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -36,6 +36,10 @@
 #include <linux/seq_file.h>
 #include <linux/kref.h>
 #include <linux/sysfs.h>
+#include <linux/device_cgroup.h>
+#include <drm/drm_file.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_device.h>
 #include <kgd_kfd_interface.h>
 
 #include "amd_shared.h"
@@ -179,10 +183,6 @@ enum cache_policy {
 	cache_policy_noncoherent
 };
 
-#define KFD_IS_VI(chip) ((chip) >= CHIP_CARRIZO && (chip) <= CHIP_POLARIS11)
-#define KFD_IS_DGPU(chip) (((chip) >= CHIP_TONGA && \
-			   (chip) <= CHIP_NAVI10) || \
-			   (chip) == CHIP_HAWAII)
 #define KFD_IS_SOC15(chip) ((chip) >= CHIP_VEGA10)
 
 struct kfd_event_interrupt_class {
@@ -230,6 +230,7 @@ struct kfd_dev {
 
 	const struct kfd_device_info *device_info;
 	struct pci_dev *pdev;
+	struct drm_device *ddev;
 
 	unsigned int id;		/* topology stub index */
 
@@ -687,7 +688,7 @@ struct kfd_process {
 	/* We want to receive a notification when the mm_struct is destroyed */
 	struct mmu_notifier mmu_notifier;
 
-	unsigned int pasid;
+	uint16_t pasid;
 	unsigned int doorbell_index;
 
 	/*
@@ -1040,6 +1041,21 @@ bool kfd_is_locked(void);
 void kfd_inc_compute_active(struct kfd_dev *dev);
 void kfd_dec_compute_active(struct kfd_dev *dev);
 
+/* Cgroup Support */
+/* Check with device cgroup if @kfd device is accessible */
+static inline int kfd_devcgroup_check_permission(struct kfd_dev *kfd)
+{
+#if defined(CONFIG_CGROUP_DEVICE)
+	struct drm_device *ddev = kfd->ddev;
+
+	return devcgroup_check_permission(DEVCG_DEV_CHAR, ddev->driver->major,
+					  ddev->render->index,
+					  DEVCG_ACC_WRITE | DEVCG_ACC_READ);
+#else
+	return 0;
+#endif
+}
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 40e3fc0c6942..10f9af5784f2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -416,7 +416,7 @@ static void kfd_process_destroy_pdds(struct kfd_process *p)
 
 	list_for_each_entry_safe(pdd, temp, &p->per_device_data,
 				 per_device_list) {
-		pr_debug("Releasing pdd (topology id %d) for process (pasid %d)\n",
+		pr_debug("Releasing pdd (topology id %d) for process (pasid 0x%x)\n",
 				pdd->dev->id, p->pasid);
 
 		if (pdd->drm_file) {
@@ -687,6 +687,8 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
 			struct kfd_dev *dev)
 {
 	unsigned int i;
+	int range_start = dev->shared_resources.non_cp_doorbells_start;
+	int range_end = dev->shared_resources.non_cp_doorbells_end;
 
 	if (!KFD_IS_SOC15(dev->device_info->asic_family))
 		return 0;
@@ -698,14 +700,16 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
 		return -ENOMEM;
 
 	/* Mask out doorbells reserved for SDMA, IH, and VCN on SOC15. */
+	pr_debug("reserved doorbell 0x%03x - 0x%03x\n", range_start, range_end);
+	pr_debug("reserved doorbell 0x%03x - 0x%03x\n",
+			range_start + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
+			range_end + KFD_QUEUE_DOORBELL_MIRROR_OFFSET);
+
 	for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS / 2; i++) {
-		if (i >= dev->shared_resources.non_cp_doorbells_start
-			&& i <= dev->shared_resources.non_cp_doorbells_end) {
+		if (i >= range_start && i <= range_end) {
 			set_bit(i, qpd->doorbell_bitmap);
 			set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
 				qpd->doorbell_bitmap);
-			pr_debug("reserved doorbell 0x%03x and 0x%03x\n", i,
-				i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET);
 		}
 	}
 
@@ -1020,7 +1024,7 @@ static void evict_process_worker(struct work_struct *work)
 	 */
 	flush_delayed_work(&p->restore_work);
 
-	pr_debug("Started evicting pasid %d\n", p->pasid);
+	pr_debug("Started evicting pasid 0x%x\n", p->pasid);
 	ret = kfd_process_evict_queues(p);
 	if (!ret) {
 		dma_fence_signal(p->ef);
@@ -1029,9 +1033,9 @@ static void evict_process_worker(struct work_struct *work)
 		queue_delayed_work(kfd_restore_wq, &p->restore_work,
 				msecs_to_jiffies(PROCESS_RESTORE_TIME_MS));
 
-		pr_debug("Finished evicting pasid %d\n", p->pasid);
+		pr_debug("Finished evicting pasid 0x%x\n", p->pasid);
 	} else
-		pr_err("Failed to evict queues of pasid %d\n", p->pasid);
+		pr_err("Failed to evict queues of pasid 0x%x\n", p->pasid);
 }
 
 static void restore_process_worker(struct work_struct *work)
@@ -1046,7 +1050,7 @@ static void restore_process_worker(struct work_struct *work)
 	 * lifetime of this thread, kfd_process p will be valid
 	 */
 	p = container_of(dwork, struct kfd_process, restore_work);
-	pr_debug("Started restoring pasid %d\n", p->pasid);
+	pr_debug("Started restoring pasid 0x%x\n", p->pasid);
 
 	/* Setting last_restore_timestamp before successful restoration.
 	 * Otherwise this would have to be set by KGD (restore_process_bos)
@@ -1062,7 +1066,7 @@ static void restore_process_worker(struct work_struct *work)
 	ret = amdgpu_amdkfd_gpuvm_restore_process_bos(p->kgd_process_info,
 						     &p->ef);
 	if (ret) {
-		pr_debug("Failed to restore BOs of pasid %d, retry after %d ms\n",
+		pr_debug("Failed to restore BOs of pasid 0x%x, retry after %d ms\n",
 			 p->pasid, PROCESS_BACK_OFF_TIME_MS);
 		ret = queue_delayed_work(kfd_restore_wq, &p->restore_work,
 				msecs_to_jiffies(PROCESS_BACK_OFF_TIME_MS));
@@ -1072,9 +1076,9 @@ static void restore_process_worker(struct work_struct *work)
 
 	ret = kfd_process_restore_queues(p);
 	if (!ret)
-		pr_debug("Finished restoring pasid %d\n", p->pasid);
+		pr_debug("Finished restoring pasid 0x%x\n", p->pasid);
 	else
-		pr_err("Failed to restore queues of pasid %d\n", p->pasid);
+		pr_err("Failed to restore queues of pasid 0x%x\n", p->pasid);
 }
 
 void kfd_suspend_all_processes(void)
@@ -1088,7 +1092,7 @@ void kfd_suspend_all_processes(void)
 		cancel_delayed_work_sync(&p->restore_work);
 
 		if (kfd_process_evict_queues(p))
-			pr_err("Failed to suspend process %d\n", p->pasid);
+			pr_err("Failed to suspend process 0x%x\n", p->pasid);
 		dma_fence_signal(p->ef);
 		dma_fence_put(p->ef);
 		p->ef = NULL;
@@ -1171,7 +1175,7 @@ int kfd_debugfs_mqds_by_process(struct seq_file *m, void *data)
 	int idx = srcu_read_lock(&kfd_processes_srcu);
 
 	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
-		seq_printf(m, "Process %d PASID %d:\n",
+		seq_printf(m, "Process %d PASID 0x%x:\n",
 			   p->lead_thread->tgid, p->pasid);
 
 		mutex_lock(&p->mutex);
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 7e6c3ee82f5b..2659d226c056 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -53,7 +53,7 @@ static int find_available_queue_slot(struct process_queue_manager *pqm,
 	pr_debug("The new slot id %lu\n", found);
 
 	if (found >= KFD_MAX_NUM_OF_QUEUES_PER_PROCESS) {
-		pr_info("Cannot open more queues for process with pasid %d\n",
+		pr_info("Cannot open more queues for process with pasid 0x%x\n",
 				pqm->process->pasid);
 		return -ENOMEM;
 	}
@@ -298,7 +298,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 	}
 
 	if (retval != 0) {
-		pr_err("Pasid %d DQM create queue %d failed. ret %d\n",
+		pr_err("Pasid 0x%x DQM create queue %d failed. ret %d\n",
 			pqm->process->pasid, type, retval);
 		goto err_create_queue;
 	}
@@ -377,7 +377,7 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 		dqm = pqn->q->device->dqm;
 		retval = dqm->ops.destroy_queue(dqm, &pdd->qpd, pqn->q);
 		if (retval) {
-			pr_err("Pasid %d destroy queue %d failed, ret %d\n",
+			pr_err("Pasid 0x%x destroy queue %d failed, ret %d\n",
 				pqm->process->pasid,
 				pqn->q->properties.queue_id, retval);
 			if (retval != -ETIME)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
index 7551761f2aa9..69bd0628fdc6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
@@ -269,6 +269,8 @@ static ssize_t iolink_show(struct kobject *kobj, struct attribute *attr,
 	buffer[0] = 0;
 
 	iolink = container_of(attr, struct kfd_iolink_properties, attr);
+	if (iolink->gpu && kfd_devcgroup_check_permission(iolink->gpu))
+		return -EPERM;
 	sysfs_show_32bit_prop(buffer, "type", iolink->iolink_type);
 	sysfs_show_32bit_prop(buffer, "version_major", iolink->ver_maj);
 	sysfs_show_32bit_prop(buffer, "version_minor", iolink->ver_min);
@@ -305,6 +307,8 @@ static ssize_t mem_show(struct kobject *kobj, struct attribute *attr,
 	buffer[0] = 0;
 
 	mem = container_of(attr, struct kfd_mem_properties, attr);
+	if (mem->gpu && kfd_devcgroup_check_permission(mem->gpu))
+		return -EPERM;
 	sysfs_show_32bit_prop(buffer, "heap_type", mem->heap_type);
 	sysfs_show_64bit_prop(buffer, "size_in_bytes", mem->size_in_bytes);
 	sysfs_show_32bit_prop(buffer, "flags", mem->flags);
@@ -334,6 +338,8 @@ static ssize_t kfd_cache_show(struct kobject *kobj, struct attribute *attr,
 	buffer[0] = 0;
 
 	cache = container_of(attr, struct kfd_cache_properties, attr);
+	if (cache->gpu && kfd_devcgroup_check_permission(cache->gpu))
+		return -EPERM;
 	sysfs_show_32bit_prop(buffer, "processor_id_low",
 			cache->processor_id_low);
 	sysfs_show_32bit_prop(buffer, "level", cache->cache_level);
@@ -414,6 +420,8 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 	if (strcmp(attr->name, "gpu_id") == 0) {
 		dev = container_of(attr, struct kfd_topology_device,
 				attr_gpuid);
+		if (dev->gpu && kfd_devcgroup_check_permission(dev->gpu))
+			return -EPERM;
 		return sysfs_show_32bit_val(buffer, dev->gpu_id);
 	}
 
@@ -421,11 +429,15 @@ static ssize_t node_show(struct kobject *kobj, struct attribute *attr,
 		dev = container_of(attr, struct kfd_topology_device,
 				attr_name);
 
+		if (dev->gpu && kfd_devcgroup_check_permission(dev->gpu))
+			return -EPERM;
 		return sysfs_show_str_val(buffer, dev->node_props.name);
 	}
 
 	dev = container_of(attr, struct kfd_topology_device,
 			attr_props);
+	if (dev->gpu && kfd_devcgroup_check_permission(dev->gpu))
+		return -EPERM;
 	sysfs_show_32bit_prop(buffer, "cpu_cores_count",
 			dev->node_props.cpu_cores_count);
 	sysfs_show_32bit_prop(buffer, "simd_count",
@@ -1098,6 +1110,9 @@ static struct kfd_topology_device *kfd_assign_gpu(struct kfd_dev *gpu)
 {
 	struct kfd_topology_device *dev;
 	struct kfd_topology_device *out_dev = NULL;
+	struct kfd_mem_properties *mem;
+	struct kfd_cache_properties *cache;
+	struct kfd_iolink_properties *iolink;
 
 	down_write(&topology_lock);
 	list_for_each_entry(dev, &topology_device_list, list) {
@@ -1111,6 +1126,13 @@ static struct kfd_topology_device *kfd_assign_gpu(struct kfd_dev *gpu)
 		if (!dev->gpu && (dev->node_props.simd_count > 0)) {
 			dev->gpu = gpu;
 			out_dev = dev;
+
+			list_for_each_entry(mem, &dev->mem_props, list)
+				mem->gpu = dev->gpu;
+			list_for_each_entry(cache, &dev->cache_props, list)
+				cache->gpu = dev->gpu;
+			list_for_each_entry(iolink, &dev->io_link_props, list)
+				iolink->gpu = dev->gpu;
 			break;
 		}
 	}
@@ -1317,8 +1339,11 @@ int kfd_topology_add_device(struct kfd_dev *gpu)
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
 	case CHIP_RAVEN:
+	case CHIP_RENOIR:
 	case CHIP_ARCTURUS:
 	case CHIP_NAVI10:
+	case CHIP_NAVI12:
+	case CHIP_NAVI14:
 		dev->node_props.capability |= ((HSA_CAP_DOORBELL_TYPE_2_0 <<
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT) &
 			HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
index d4718d58d0f2..15843e0fc756 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
@@ -102,6 +102,7 @@ struct kfd_mem_properties {
 	uint32_t		flags;
 	uint32_t		width;
 	uint32_t		mem_clk_max;
+	struct kfd_dev		*gpu;
 	struct kobject		*kobj;
 	struct attribute	attr;
 };
@@ -123,6 +124,7 @@ struct kfd_cache_properties {
 	uint32_t		cache_latency;
 	uint32_t		cache_type;
 	uint8_t			sibling_map[CRAT_SIBLINGMAP_SIZE];
+	struct kfd_dev		*gpu;
 	struct kobject		*kobj;
 	struct attribute	attr;
 };
@@ -141,6 +143,7 @@ struct kfd_iolink_properties {
 	uint32_t		max_bandwidth;
 	uint32_t		rec_transfer_size;
 	uint32_t		flags;
+	struct kfd_dev		*gpu;
 	struct kobject		*kobj;
 	struct attribute	attr;
 };
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 71991a28a775..313183b80032 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -23,16 +23,16 @@ config DRM_AMD_DC_DCN2_0
 	depends on DRM_AMD_DC && X86
 	depends on DRM_AMD_DC_DCN1_0
 	help
-	    Choose this option if you want to have
-	    Navi support for display engine
+	  Choose this option if you want to have
+	  Navi support for display engine
 
 config DRM_AMD_DC_DCN2_1
-        bool "DCN 2.1 family"
-        depends on DRM_AMD_DC && X86
-        depends on DRM_AMD_DC_DCN2_0
-        help
-            Choose this option if you want to have
-            Renoir support for display engine
+	bool "DCN 2.1 family"
+	depends on DRM_AMD_DC && X86
+	depends on DRM_AMD_DC_DCN2_0
+	help
+	  Choose this option if you want to have
+	  Renoir support for display engine
 
 config DRM_AMD_DC_DSC_SUPPORT
 	bool "DSC support"
@@ -41,8 +41,16 @@ config DRM_AMD_DC_DSC_SUPPORT
 	depends on DRM_AMD_DC_DCN1_0
 	depends on DRM_AMD_DC_DCN2_0
 	help
-	    Choose this option if you want to have
-	    Dynamic Stream Compression support
+	  Choose this option if you want to have
+	  Dynamic Stream Compression support
+
+config DRM_AMD_DC_HDCP
+	bool "Enable HDCP support in DC"
+	depends on DRM_AMD_DC
+	help
+	 Choose this option
+	 if you want to support
+	 HDCP authentication
 
 config DEBUG_KERNEL_DC
 	bool "Enable kgdb break in DC"
diff --git a/drivers/gpu/drm/amd/display/Makefile b/drivers/gpu/drm/amd/display/Makefile
index 496cee000f10..36b3d6a5d04d 100644
--- a/drivers/gpu/drm/amd/display/Makefile
+++ b/drivers/gpu/drm/amd/display/Makefile
@@ -34,12 +34,19 @@ subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/freesync
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/color
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/info_packet
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/power
+ifdef CONFIG_DRM_AMD_DC_HDCP
+subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/modules/hdcp
+endif
 
 #TODO: remove when Timing Sync feature is complete
 subdir-ccflags-y += -DBUILD_FEATURE_TIMING_SYNC=0
 
 DAL_LIBS = amdgpu_dm dc	modules/freesync modules/color modules/info_packet modules/power
 
+ifdef CONFIG_DRM_AMD_DC_HDCP
+DAL_LIBS += modules/hdcp
+endif
+
 AMD_DAL = $(addsuffix /Makefile, $(addprefix $(FULL_AMD_DISPLAY_PATH)/,$(DAL_LIBS)))
 
 include $(AMD_DAL)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index 94911871eb9b..9a3b7bf8ab0b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -31,6 +31,10 @@ ifneq ($(CONFIG_DRM_AMD_DC),)
 AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o
 endif
 
+ifdef CONFIG_DRM_AMD_DC_HDCP
+AMDGPUDM += amdgpu_dm_hdcp.o
+endif
+
 ifneq ($(CONFIG_DEBUG_FS),)
 AMDGPUDM += amdgpu_dm_crc.o amdgpu_dm_debugfs.o
 endif
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 c67d3c41db19..7aac9568d3be 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -37,6 +37,9 @@
 #include "amdgpu_ucode.h"
 #include "atom.h"
 #include "amdgpu_dm.h"
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+#include "amdgpu_dm_hdcp.h"
+#endif
 #include "amdgpu_pm.h"
 
 #include "amd_shared.h"
@@ -67,6 +70,7 @@
 #include <drm/drm_edid.h>
 #include <drm/drm_vblank.h>
 #include <drm/drm_audio_component.h>
+#include <drm/drm_hdcp.h>
 
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
 #include "ivsrcid/dcn/irqsrcs_dcn_1_0.h"
@@ -143,6 +147,12 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 static void handle_cursor_update(struct drm_plane *plane,
 				 struct drm_plane_state *old_plane_state);
 
+static void amdgpu_dm_set_psr_caps(struct dc_link *link);
+static bool amdgpu_dm_psr_enable(struct dc_stream_state *stream);
+static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream);
+static bool amdgpu_dm_psr_disable(struct dc_stream_state *stream);
+
+
 /*
  * dm_vblank_get_counter
  *
@@ -263,6 +273,13 @@ static inline bool amdgpu_dm_vrr_active(struct dm_crtc_state *dm_state)
 	       dm_state->freesync_config.state == VRR_STATE_ACTIVE_FIXED;
 }
 
+/**
+ * dm_pflip_high_irq() - Handle pageflip interrupt
+ * @interrupt_params: ignored
+ *
+ * Handles the pageflip interrupt by notifying all interested parties
+ * that the pageflip has been completed.
+ */
 static void dm_pflip_high_irq(void *interrupt_params)
 {
 	struct amdgpu_crtc *amdgpu_crtc;
@@ -407,6 +424,13 @@ static void dm_vupdate_high_irq(void *interrupt_params)
 	}
 }
 
+/**
+ * dm_crtc_high_irq() - Handles CRTC interrupt
+ * @interrupt_params: ignored
+ *
+ * Handles the CRTC/VSYNC interrupt by notfying DRM's VBLANK
+ * event handler.
+ */
 static void dm_crtc_high_irq(void *interrupt_params)
 {
 	struct common_irq_params *irq_params = interrupt_params;
@@ -646,11 +670,18 @@ void amdgpu_dm_audio_eld_notify(struct amdgpu_device *adev, int pin)
 static int amdgpu_dm_init(struct amdgpu_device *adev)
 {
 	struct dc_init_data init_data;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	struct dc_callback_init init_params;
+#endif
+
 	adev->dm.ddev = adev->ddev;
 	adev->dm.adev = adev;
 
 	/* Zero all the fields */
 	memset(&init_data, 0, sizeof(init_data));
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	memset(&init_params, 0, sizeof(init_params));
+#endif
 
 	mutex_init(&adev->dm.dc_lock);
 	mutex_init(&adev->dm.audio_lock);
@@ -688,7 +719,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	 */
 	if (adev->flags & AMD_IS_APU &&
 	    adev->asic_type >= CHIP_CARRIZO &&
-	    adev->asic_type <= CHIP_RAVEN)
+	    adev->asic_type < CHIP_RAVEN)
 		init_data.flags.gpu_vm_support = true;
 
 	if (amdgpu_dc_feature_mask & DC_FBC_MASK)
@@ -697,6 +728,9 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_dc_feature_mask & DC_MULTI_MON_PP_MCLK_SWITCH_MASK)
 		init_data.flags.multi_mon_pp_mclk_switch = true;
 
+	if (amdgpu_dc_feature_mask & DC_DISABLE_FRACTIONAL_PWM_MASK)
+		init_data.flags.disable_fractional_pwm = true;
+
 	init_data.flags.power_down_display_on_boot = true;
 
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
@@ -713,6 +747,8 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 		goto error;
 	}
 
+	dc_hardware_init(adev->dm.dc);
+
 	adev->dm.freesync_module = mod_freesync_create(adev->dm.dc);
 	if (!adev->dm.freesync_module) {
 		DRM_ERROR(
@@ -723,6 +759,18 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 
 	amdgpu_dm_init_color_mod();
 
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	if (adev->asic_type >= CHIP_RAVEN) {
+		adev->dm.hdcp_workqueue = hdcp_create_workqueue(&adev->psp, &init_params.cp_psp, adev->dm.dc);
+
+		if (!adev->dm.hdcp_workqueue)
+			DRM_ERROR("amdgpu: failed to initialize hdcp_workqueue.\n");
+		else
+			DRM_DEBUG_DRIVER("amdgpu: hdcp_workqueue init done %p.\n", adev->dm.hdcp_workqueue);
+
+		dc_init_callbacks(adev->dm.dc, &init_params);
+	}
+#endif
 	if (amdgpu_dm_initialize_drm_device(adev)) {
 		DRM_ERROR(
 		"amdgpu: failed to initialize sw for display support.\n");
@@ -764,6 +812,16 @@ static void amdgpu_dm_fini(struct amdgpu_device *adev)
 
 	amdgpu_dm_destroy_drm_device(&adev->dm);
 
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	if (adev->dm.hdcp_workqueue) {
+		hdcp_destroy(adev->dm.hdcp_workqueue);
+		adev->dm.hdcp_workqueue = NULL;
+	}
+
+	if (adev->dm.dc)
+		dc_deinit_callbacks(adev->dm.dc);
+#endif
+
 	/* DC Destroy TODO: Replace destroy DAL */
 	if (adev->dm.dc)
 		dc_destroy(&adev->dm.dc);
@@ -897,27 +955,29 @@ static int detect_mst_link_for_all_connectors(struct drm_device *dev)
 {
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	int ret = 0;
 
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		aconnector = to_amdgpu_dm_connector(connector);
 		if (aconnector->dc_link->type == dc_connection_mst_branch &&
 		    aconnector->mst_mgr.aux) {
 			DRM_DEBUG_DRIVER("DM_MST: starting TM on aconnector: %p [id: %d]\n",
-					aconnector, aconnector->base.base.id);
+					 aconnector,
+					 aconnector->base.base.id);
 
 			ret = drm_dp_mst_topology_mgr_set_mst(&aconnector->mst_mgr, true);
 			if (ret < 0) {
 				DRM_ERROR("DM_MST: Failed to start MST\n");
-				((struct dc_link *)aconnector->dc_link)->type = dc_connection_single;
-				return ret;
-				}
+				aconnector->dc_link->type =
+					dc_connection_single;
+				break;
 			}
+		}
 	}
+	drm_connector_list_iter_end(&iter);
 
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 	return ret;
 }
 
@@ -940,6 +1000,11 @@ static int dm_late_init(void *handle)
 	params.backlight_lut_array_size = 16;
 	params.backlight_lut_array = linear_lut;
 
+	/* Min backlight level after ABM reduction,  Don't allow below 1%
+	 * 0xFFFF x 0.01 = 0x28F
+	 */
+	params.min_abm_backlight = 0x28F;
+
 	/* todo will enable for navi10 */
 	if (adev->asic_type <= CHIP_RAVEN) {
 		ret = dmcu_load_iram(dmcu, params);
@@ -955,14 +1020,13 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend)
 {
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct drm_dp_mst_topology_mgr *mgr;
 	int ret;
 	bool need_hotplug = false;
 
-	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
-
-	list_for_each_entry(connector, &dev->mode_config.connector_list,
-			    head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		aconnector = to_amdgpu_dm_connector(connector);
 		if (aconnector->dc_link->type != dc_connection_mst_branch ||
 		    aconnector->mst_port)
@@ -973,15 +1037,14 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend)
 		if (suspend) {
 			drm_dp_mst_topology_mgr_suspend(mgr);
 		} else {
-			ret = drm_dp_mst_topology_mgr_resume(mgr);
+			ret = drm_dp_mst_topology_mgr_resume(mgr, true);
 			if (ret < 0) {
 				drm_dp_mst_topology_mgr_set_mst(mgr, false);
 				need_hotplug = true;
 			}
 		}
 	}
-
-	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+	drm_connector_list_iter_end(&iter);
 
 	if (need_hotplug)
 		drm_kms_helper_hotplug_event(dev);
@@ -989,7 +1052,7 @@ static void s3_handle_mst(struct drm_device *dev, bool suspend)
 
 /**
  * dm_hw_init() - Initialize DC device
- * @handle: The base driver device containing the amdpgu_dm device.
+ * @handle: The base driver device containing the amdgpu_dm device.
  *
  * Initialize the &struct amdgpu_display_manager device. This involves calling
  * the initializers of each DM component, then populating the struct with them.
@@ -1019,7 +1082,7 @@ static int dm_hw_init(void *handle)
 
 /**
  * dm_hw_fini() - Teardown DC device
- * @handle: The base driver device containing the amdpgu_dm device.
+ * @handle: The base driver device containing the amdgpu_dm device.
  *
  * Teardown components within &struct amdgpu_display_manager that require
  * cleanup. This involves cleaning up the DRM device, DC, and any modules that
@@ -1163,6 +1226,7 @@ static int dm_resume(void *handle)
 	struct amdgpu_display_manager *dm = &adev->dm;
 	struct amdgpu_dm_connector *aconnector;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *new_crtc_state;
 	struct dm_crtc_state *dm_new_crtc_state;
@@ -1185,17 +1249,18 @@ static int dm_resume(void *handle)
 	/* program HPD filter */
 	dc_resume(dm->dc);
 
-	/* On resume we need to  rewrite the MSTM control bits to enamble MST*/
-	s3_handle_mst(ddev, false);
-
 	/*
 	 * early enable HPD Rx IRQ, should be done before set mode as short
 	 * pulse interrupts are used for MST
 	 */
 	amdgpu_dm_irq_resume_early(adev);
 
+	/* On resume we need to rewrite the MSTM control bits to enable MST*/
+	s3_handle_mst(ddev, false);
+
 	/* Do detection*/
-	list_for_each_entry(connector, &ddev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(ddev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		aconnector = to_amdgpu_dm_connector(connector);
 
 		/*
@@ -1223,6 +1288,7 @@ static int dm_resume(void *handle)
 		amdgpu_dm_update_connector_after_detect(aconnector);
 		mutex_unlock(&aconnector->hpd_lock);
 	}
+	drm_connector_list_iter_end(&iter);
 
 	/* Force mode set in atomic commit */
 	for_each_new_crtc_in_state(dm->cached_state, crtc, new_crtc_state, i)
@@ -1438,6 +1504,11 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector)
 		dc_sink_release(aconnector->dc_sink);
 		aconnector->dc_sink = NULL;
 		aconnector->edid = NULL;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+		/* Set CP to DESIRED if it was ENABLED, so we can re-enable it again on hotplug */
+		if (connector->state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED)
+			connector->state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+#endif
 	}
 
 	mutex_unlock(&dev->mode_config.mutex);
@@ -1452,6 +1523,9 @@ static void handle_hpd_irq(void *param)
 	struct drm_connector *connector = &aconnector->base;
 	struct drm_device *dev = connector->dev;
 	enum dc_connection_type new_connection_type = dc_connection_none;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	struct amdgpu_device *adev = dev->dev_private;
+#endif
 
 	/*
 	 * In case of failure or MST no need to update connector status or notify the OS
@@ -1459,6 +1533,10 @@ static void handle_hpd_irq(void *param)
 	 */
 	mutex_lock(&aconnector->hpd_lock);
 
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	if (adev->asic_type >= CHIP_RAVEN)
+		hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index);
+#endif
 	if (aconnector->fake_enable)
 		aconnector->fake_enable = false;
 
@@ -1577,6 +1655,12 @@ static void handle_hpd_rx_irq(void *param)
 	struct dc_link *dc_link = aconnector->dc_link;
 	bool is_mst_root_connector = aconnector->mst_mgr.mst_state;
 	enum dc_connection_type new_connection_type = dc_connection_none;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	union hpd_irq_data hpd_irq_data;
+	struct amdgpu_device *adev = dev->dev_private;
+
+	memset(&hpd_irq_data, 0, sizeof(hpd_irq_data));
+#endif
 
 	/*
 	 * TODO:Temporary add mutex to protect hpd interrupt not have a gpio
@@ -1586,7 +1670,12 @@ static void handle_hpd_rx_irq(void *param)
 	if (dc_link->type != dc_connection_mst_branch)
 		mutex_lock(&aconnector->hpd_lock);
 
+
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	if (dc_link_handle_hpd_rx_irq(dc_link, &hpd_irq_data, NULL) &&
+#else
 	if (dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL) &&
+#endif
 			!is_mst_root_connector) {
 		/* Downstream Port status changed. */
 		if (!dc_link_detect_sink(dc_link, &new_connection_type))
@@ -1621,6 +1710,10 @@ static void handle_hpd_rx_irq(void *param)
 			drm_kms_helper_hotplug_event(dev);
 		}
 	}
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	if (hpd_irq_data.bytes.device_service_irq.bits.CP_IRQ)
+		hdcp_handle_cpirq(adev->dm.hdcp_workqueue,  aconnector->base.index);
+#endif
 	if ((dc_link->cur_link_settings.lane_count != LANE_COUNT_UNKNOWN) ||
 	    (dc_link->type == dc_connection_mst_branch))
 		dm_handle_hpd_rx_irq(aconnector);
@@ -2334,6 +2427,8 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		} else if (dc_link_detect(link, DETECT_REASON_BOOT)) {
 			amdgpu_dm_update_connector_after_detect(aconnector);
 			register_backlight_device(dm, link);
+			if (amdgpu_dc_feature_mask & DC_PSR_MASK)
+				amdgpu_dm_set_psr_caps(link);
 		}
 
 
@@ -3311,8 +3406,12 @@ static void fill_stream_properties_from_drm_display_mode(
 {
 	struct dc_crtc_timing *timing_out = &stream->timing;
 	const struct drm_display_info *info = &connector->display_info;
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct hdmi_vendor_infoframe hv_frame;
+	struct hdmi_avi_infoframe avi_frame;
 
-	memset(timing_out, 0, sizeof(struct dc_crtc_timing));
+	memset(&hv_frame, 0, sizeof(hv_frame));
+	memset(&avi_frame, 0, sizeof(avi_frame));
 
 	timing_out->h_border_left = 0;
 	timing_out->h_border_right = 0;
@@ -3322,6 +3421,9 @@ static void fill_stream_properties_from_drm_display_mode(
 	if (drm_mode_is_420_only(info, mode_in)
 			&& stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+	else if (drm_mode_is_420_also(info, mode_in)
+			&& aconnector->force_yuv420_output)
+		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
 	else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
 			&& stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR444;
@@ -3346,6 +3448,13 @@ static void fill_stream_properties_from_drm_display_mode(
 			timing_out->flags.VSYNC_POSITIVE_POLARITY = 1;
 	}
 
+	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+		drm_hdmi_avi_infoframe_from_display_mode(&avi_frame, (struct drm_connector *)connector, mode_in);
+		timing_out->vic = avi_frame.video_code;
+		drm_hdmi_vendor_infoframe_from_display_mode(&hv_frame, (struct drm_connector *)connector, mode_in);
+		timing_out->hdmi_vic = hv_frame.vic;
+	}
+
 	timing_out->h_addressable = mode_in->crtc_hdisplay;
 	timing_out->h_total = mode_in->crtc_htotal;
 	timing_out->h_sync_width =
@@ -3566,6 +3675,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	stream->dm_stream_context = aconnector;
 
+	stream->timing.flags.LTE_340MCSC_SCRAMBLE =
+		drm_connector->display_info.hdmi.scdc.scrambling.low_rates;
+
 	list_for_each_entry(preferred_mode, &aconnector->base.modes, head) {
 		/* Search for preferred mode */
 		if (preferred_mode->type & DRM_MODE_TYPE_PREFERRED) {
@@ -3621,8 +3733,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 							     dc_link_get_link_cap(aconnector->dc_link));
 
 		if (dsc_caps.is_dsc_supported)
-			if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc,
+			if (dc_dsc_compute_config(aconnector->dc_link->ctx->dc->res_pool->dscs[0],
 						  &dsc_caps,
+						  aconnector->dc_link->ctx->dc->debug.dsc_min_slice_height_override,
 						  link_bandwidth_kbps,
 						  &stream->timing,
 						  &stream->timing.dsc_cfg))
@@ -3639,6 +3752,18 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 
 	update_stream_signal(stream, sink);
 
+	if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		mod_build_hf_vsif_infopacket(stream, &stream->vsp_infopacket, false, false);
+	if (stream->link->psr_feature_enabled)	{
+		struct dc  *core_dc = stream->link->ctx->dc;
+
+		if (dc_is_dmcu_initialized(core_dc)) {
+			struct dmcu *dmcu = core_dc->res_pool->dmcu;
+
+			stream->psr_version = dmcu->dmcu_version.psr_version;
+			mod_build_vsc_infopacket(stream, &stream->vsc_infopacket);
+		}
+	}
 finish:
 	dc_sink_release(sink);
 
@@ -4114,8 +4239,8 @@ enum drm_mode_status amdgpu_dm_connector_mode_valid(struct drm_connector *connec
 		result = MODE_OK;
 	else
 		DRM_DEBUG_KMS("Mode %dx%d (clk %d) failed DC validation with error %d\n",
-			      mode->vdisplay,
 			      mode->hdisplay,
+			      mode->vdisplay,
 			      mode->clock,
 			      dc_result);
 
@@ -4494,7 +4619,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	tv.num_shared = 1;
 	list_add(&tv.head, &list);
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, false, NULL, true);
+	r = ttm_eu_reserve_buffers(&ticket, &list, false, NULL);
 	if (r) {
 		dev_err(adev->dev, "fail to reserve bo (%d)\n", r);
 		return r;
@@ -5088,6 +5213,10 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 
 		drm_connector_attach_vrr_capable_property(
 			&aconnector->base);
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+		if (adev->asic_type >= CHIP_RAVEN)
+			drm_connector_attach_content_protection_property(&aconnector->base, false);
+#endif
 	}
 }
 
@@ -5330,6 +5459,53 @@ is_scaling_state_different(const struct dm_connector_state *dm_state,
 	return false;
 }
 
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+static bool is_content_protection_different(struct drm_connector_state *state,
+					    const struct drm_connector_state *old_state,
+					    const struct drm_connector *connector, struct hdcp_workqueue *hdcp_w)
+{
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+
+	/* CP is being re enabled, ignore this */
+	if (old_state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED &&
+	    state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED) {
+		state->content_protection = DRM_MODE_CONTENT_PROTECTION_ENABLED;
+		return false;
+	}
+
+	/* S3 resume case, since old state will always be 0 (UNDESIRED) and the restored state will be ENABLED */
+	if (old_state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED &&
+	    state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED)
+		state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+
+	/* Check if something is connected/enabled, otherwise we start hdcp but nothing is connected/enabled
+	 * hot-plug, headless s3, dpms
+	 */
+	if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED && connector->dpms == DRM_MODE_DPMS_ON &&
+	    aconnector->dc_sink != NULL)
+		return true;
+
+	if (old_state->content_protection == state->content_protection)
+		return false;
+
+	if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED)
+		return true;
+
+	return false;
+}
+
+static void update_content_protection(struct drm_connector_state *state, const struct drm_connector *connector,
+				      struct hdcp_workqueue *hdcp_w)
+{
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+
+	if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_DESIRED)
+		hdcp_add_display(hdcp_w, aconnector->dc_link->link_index, aconnector);
+	else if (state->content_protection == DRM_MODE_CONTENT_PROTECTION_UNDESIRED)
+		hdcp_remove_display(hdcp_w, aconnector->dc_link->link_index, aconnector->base.index);
+
+}
+#endif
 static void remove_stream(struct amdgpu_device *adev,
 			  struct amdgpu_crtc *acrtc,
 			  struct dc_stream_state *stream)
@@ -5671,6 +5847,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	uint32_t target_vblank, last_flip_vblank;
 	bool vrr_active = amdgpu_dm_vrr_active(acrtc_state);
 	bool pflip_present = false;
+	bool swizzle = true;
 	struct {
 		struct dc_surface_update surface_updates[MAX_SURFACES];
 		struct dc_plane_info plane_infos[MAX_SURFACES];
@@ -5716,6 +5893,9 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 
 		dc_plane = dm_new_plane_state->dc_state;
 
+		if (dc_plane && !dc_plane->tiling_info.gfx9.swizzle)
+			swizzle = false;
+
 		bundle->surface_updates[planes_count].surface = dc_plane;
 		if (new_pcrtc_state->color_mgmt_changed) {
 			bundle->surface_updates[planes_count].gamma = dc_plane->gamma_correction;
@@ -5870,6 +6050,7 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 	/* Update the planes if changed or disable if we don't have any. */
 	if ((planes_count || acrtc_state->active_planes == 0) &&
 		acrtc_state->stream) {
+		bundle->stream_update.stream = acrtc_state->stream;
 		if (new_pcrtc_state->mode_changed) {
 			bundle->stream_update.src = acrtc_state->stream->src;
 			bundle->stream_update.dst = acrtc_state->stream->dst;
@@ -5905,14 +6086,29 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
 				&acrtc_state->vrr_params.adjust);
 			spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
 		}
-
 		mutex_lock(&dm->dc_lock);
+		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
+				acrtc_state->stream->link->psr_allow_active)
+			amdgpu_dm_psr_disable(acrtc_state->stream);
+
 		dc_commit_updates_for_stream(dm->dc,
 						     bundle->surface_updates,
 						     planes_count,
 						     acrtc_state->stream,
 						     &bundle->stream_update,
 						     dc_state);
+
+		if ((acrtc_state->update_type > UPDATE_TYPE_FAST) &&
+						acrtc_state->stream->psr_version &&
+						!acrtc_state->stream->link->psr_feature_enabled)
+			amdgpu_dm_link_setup_psr(acrtc_state->stream);
+		else if ((acrtc_state->update_type == UPDATE_TYPE_FAST) &&
+						acrtc_state->stream->link->psr_feature_enabled &&
+						!acrtc_state->stream->link->psr_allow_active &&
+						swizzle) {
+			amdgpu_dm_psr_enable(acrtc_state->stream);
+		}
+
 		mutex_unlock(&dm->dc_lock);
 	}
 
@@ -6221,10 +6417,13 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 			crtc->hwmode = new_crtc_state->mode;
 		} else if (modereset_required(new_crtc_state)) {
 			DRM_DEBUG_DRIVER("Atomic commit: RESET. crtc id %d:[%p]\n", acrtc->crtc_id, acrtc);
-
 			/* i.e. reset mode */
-			if (dm_old_crtc_state->stream)
+			if (dm_old_crtc_state->stream) {
+				if (dm_old_crtc_state->stream->link->psr_allow_active)
+					amdgpu_dm_psr_disable(dm_old_crtc_state->stream);
+
 				remove_stream(adev, acrtc, dm_old_crtc_state->stream);
+			}
 		}
 	} /* for_each_crtc_in_state() */
 
@@ -6254,6 +6453,30 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 				acrtc->otg_inst = status->primary_otg_inst;
 		}
 	}
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
+		struct dm_connector_state *dm_new_con_state = to_dm_connector_state(new_con_state);
+		struct amdgpu_crtc *acrtc = to_amdgpu_crtc(dm_new_con_state->base.crtc);
+		struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+
+		new_crtc_state = NULL;
+
+		if (acrtc)
+			new_crtc_state = drm_atomic_get_new_crtc_state(state, &acrtc->base);
+
+		dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
+
+		if (dm_new_crtc_state && dm_new_crtc_state->stream == NULL &&
+		    connector->state->content_protection == DRM_MODE_CONTENT_PROTECTION_ENABLED) {
+			hdcp_reset_display(adev->dm.hdcp_workqueue, aconnector->dc_link->link_index);
+			new_con_state->content_protection = DRM_MODE_CONTENT_PROTECTION_DESIRED;
+			continue;
+		}
+
+		if (is_content_protection_different(new_con_state, old_con_state, connector, adev->dm.hdcp_workqueue))
+			update_content_protection(new_con_state, connector, adev->dm.hdcp_workqueue);
+	}
+#endif
 
 	/* Handle connector state changes */
 	for_each_oldnew_connector_in_state(state, connector, old_con_state, new_con_state, i) {
@@ -6293,9 +6516,10 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
 		if (!scaling_changed && !abm_changed && !hdr_changed)
 			continue;
 
+		stream_update.stream = dm_new_crtc_state->stream;
 		if (scaling_changed) {
 			update_stream_scaling_settings(&dm_new_con_state->base.crtc->mode,
-					dm_new_con_state, (struct dc_stream_state *)dm_new_crtc_state->stream);
+					dm_new_con_state, dm_new_crtc_state->stream);
 
 			stream_update.src = dm_new_crtc_state->stream->src;
 			stream_update.dst = dm_new_crtc_state->stream->dst;
@@ -7164,7 +7388,7 @@ dm_determine_update_type_for_commit(struct amdgpu_display_manager *dm,
 
 		status = dc_stream_get_status_from_state(old_dm_state->context,
 							 new_dm_crtc_state->stream);
-
+		stream_update.stream = new_dm_crtc_state->stream;
 		/*
 		 * TODO: DC modifies the surface during this call so we need
 		 * to lock here - find a way to do this without locking.
@@ -7575,3 +7799,92 @@ update:
 						       freesync_capable);
 }
 
+static void amdgpu_dm_set_psr_caps(struct dc_link *link)
+{
+	uint8_t dpcd_data[EDP_PSR_RECEIVER_CAP_SIZE];
+
+	if (!(link->connector_signal & SIGNAL_TYPE_EDP))
+		return;
+	if (link->type == dc_connection_none)
+		return;
+	if (dm_helpers_dp_read_dpcd(NULL, link, DP_PSR_SUPPORT,
+					dpcd_data, sizeof(dpcd_data))) {
+		link->psr_feature_enabled = dpcd_data[0] ? true:false;
+		DRM_INFO("PSR support:%d\n", link->psr_feature_enabled);
+	}
+}
+
+/*
+ * amdgpu_dm_link_setup_psr() - configure psr link
+ * @stream: stream state
+ *
+ * Return: true if success
+ */
+static bool amdgpu_dm_link_setup_psr(struct dc_stream_state *stream)
+{
+	struct dc_link *link = NULL;
+	struct psr_config psr_config = {0};
+	struct psr_context psr_context = {0};
+	struct dc *dc = NULL;
+	bool ret = false;
+
+	if (stream == NULL)
+		return false;
+
+	link = stream->link;
+	dc = link->ctx->dc;
+
+	psr_config.psr_version = dc->res_pool->dmcu->dmcu_version.psr_version;
+
+	if (psr_config.psr_version > 0) {
+		psr_config.psr_exit_link_training_required = 0x1;
+		psr_config.psr_frame_capture_indication_req = 0;
+		psr_config.psr_rfb_setup_time = 0x37;
+		psr_config.psr_sdp_transmit_line_num_deadline = 0x20;
+		psr_config.allow_smu_optimizations = 0x0;
+
+		ret = dc_link_setup_psr(link, stream, &psr_config, &psr_context);
+
+	}
+	DRM_DEBUG_DRIVER("PSR link: %d\n",	link->psr_feature_enabled);
+
+	return ret;
+}
+
+/*
+ * amdgpu_dm_psr_enable() - enable psr f/w
+ * @stream: stream state
+ *
+ * Return: true if success
+ */
+bool amdgpu_dm_psr_enable(struct dc_stream_state *stream)
+{
+	struct dc_link *link = stream->link;
+	struct dc_static_screen_events triggers = {0};
+
+	DRM_DEBUG_DRIVER("Enabling psr...\n");
+
+	triggers.cursor_update = true;
+	triggers.overlay_update = true;
+	triggers.surface_update = true;
+
+	dc_stream_set_static_screen_events(link->ctx->dc,
+					   &stream, 1,
+					   &triggers);
+
+	return dc_link_set_psr_allow_active(link, true, false);
+}
+
+/*
+ * amdgpu_dm_psr_disable() - disable psr f/w
+ * @stream:  stream state
+ *
+ * Return: true if success
+ */
+static bool amdgpu_dm_psr_disable(struct dc_stream_state *stream)
+{
+
+	DRM_DEBUG_DRIVER("Disabling psr...\n");
+
+	return dc_link_set_psr_allow_active(stream->link, false, true);
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index c8c525a2b505..77c5166e6b08 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -108,6 +108,12 @@ struct amdgpu_dm_backlight_caps {
  * @display_indexes_num: Max number of display streams supported
  * @irq_handler_list_table_lock: Synchronizes access to IRQ tables
  * @backlight_dev: Backlight control device
+ * @backlight_link: Link on which to control backlight
+ * @backlight_caps: Capabilities of the backlight device
+ * @freesync_module: Module handling freesync calculations
+ * @fw_dmcu: Reference to DMCU firmware
+ * @dmcu_fw_version: Version of the DMCU firmware
+ * @soc_bounding_box: SOC bounding box values provided by gpu_info FW
  * @cached_state: Caches device atomic state for suspend/resume
  * @compressor: Frame buffer compression buffer. See &struct dm_comressor_info
  */
@@ -128,7 +134,7 @@ struct amdgpu_display_manager {
 	u16 display_indexes_num;
 
 	/**
-	 * @atomic_obj
+	 * @atomic_obj:
 	 *
 	 * In combination with &dm_atomic_state it helps manage
 	 * global atomic state that doesn't map cleanly into existing
@@ -225,6 +231,9 @@ struct amdgpu_display_manager {
 	struct amdgpu_dm_backlight_caps backlight_caps;
 
 	struct mod_freesync *freesync_module;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	struct hdcp_workqueue *hdcp_workqueue;
+#endif
 
 	struct drm_atomic_state *cached_state;
 
@@ -234,6 +243,8 @@ struct amdgpu_display_manager {
 	uint32_t dmcu_fw_version;
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	/**
+	 * @soc_bounding_box:
+	 *
 	 * gpu_info FW provided soc bounding box struct or 0 if not
 	 * available in FW
 	 */
@@ -287,6 +298,7 @@ struct amdgpu_dm_connector {
 	uint32_t debugfs_dpcd_address;
 	uint32_t debugfs_dpcd_size;
 #endif
+	bool force_yuv420_output;
 };
 
 #define to_amdgpu_dm_connector(x) container_of(x, struct amdgpu_dm_connector, base)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index b43bb7f90e4e..2233d293a707 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -210,6 +210,8 @@ static int __set_legacy_tf(struct dc_transfer_func *func,
 	res = mod_color_calculate_regamma_params(func, gamma, true, has_rom,
 						 NULL);
 
+	dc_gamma_release(&gamma);
+
 	return res ? 0 : -ENOMEM;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index a549c7c717dd..eaad9099bc0b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -122,11 +122,16 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
 	}
 
 	/* Configure dithering */
-	if (!dm_need_crc_dither(source))
+	if (!dm_need_crc_dither(source)) {
 		dc_stream_set_dither_option(stream_state, DITHER_OPTION_TRUN8);
-	else
+		dc_stream_set_dyn_expansion(stream_state->ctx->dc, stream_state,
+					    DYN_EXPANSION_DISABLE);
+	} else {
 		dc_stream_set_dither_option(stream_state,
 					    DITHER_OPTION_DEFAULT);
+		dc_stream_set_dyn_expansion(stream_state->ctx->dc, stream_state,
+					    DYN_EXPANSION_AUTO);
+	}
 
 unlock:
 	mutex_unlock(&adev->dm.dc_lock);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f3dfb2887ae0..bdb37e611015 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -942,6 +942,52 @@ static const struct {
 		{"aux_dpcd_data", &dp_dpcd_data_debugfs_fops}
 };
 
+/*
+ * Force YUV420 output if available from the given mode
+ */
+static int force_yuv420_output_set(void *data, u64 val)
+{
+	struct amdgpu_dm_connector *connector = data;
+
+	connector->force_yuv420_output = (bool)val;
+
+	return 0;
+}
+
+/*
+ * Check if YUV420 is forced when available from the given mode
+ */
+static int force_yuv420_output_get(void *data, u64 *val)
+{
+	struct amdgpu_dm_connector *connector = data;
+
+	*val = connector->force_yuv420_output;
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(force_yuv420_output_fops, force_yuv420_output_get,
+			 force_yuv420_output_set, "%llu\n");
+
+/*
+ *  Read PSR state
+ */
+static int psr_get(void *data, u64 *val)
+{
+	struct amdgpu_dm_connector *connector = data;
+	struct dc_link *link = connector->dc_link;
+	uint32_t psr_state = 0;
+
+	dc_link_get_psr_state(link, &psr_state);
+
+	*val = psr_state;
+
+	return 0;
+}
+
+
+DEFINE_DEBUGFS_ATTRIBUTE(psr_fops, psr_get, NULL, "%llu\n");
+
 void connector_debugfs_init(struct amdgpu_dm_connector *connector)
 {
 	int i;
@@ -955,6 +1001,12 @@ void connector_debugfs_init(struct amdgpu_dm_connector *connector)
 					    dp_debugfs_entries[i].fops);
 		}
 	}
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_eDP)
+		debugfs_create_file_unsafe("psr_state", 0444, dir, connector, &psr_fops);
+
+	debugfs_create_file_unsafe("force_yuv420_output", 0644, dir, connector,
+				   &force_yuv420_output_fops);
+
 }
 
 /*
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
new file mode 100644
index 000000000000..77181ddf6c8e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -0,0 +1,346 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "amdgpu_dm_hdcp.h"
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "dm_helpers.h"
+#include <drm/drm_hdcp.h>
+
+static bool
+lp_write_i2c(void *handle, uint32_t address, const uint8_t *data, uint32_t size)
+{
+
+	struct dc_link *link = handle;
+	struct i2c_payload i2c_payloads[] = {{true, address, size, (void *)data} };
+	struct i2c_command cmd = {i2c_payloads, 1, I2C_COMMAND_ENGINE_HW, link->dc->caps.i2c_speed_in_khz};
+
+	return dm_helpers_submit_i2c(link->ctx, link, &cmd);
+}
+
+static bool
+lp_read_i2c(void *handle, uint32_t address, uint8_t offset, uint8_t *data, uint32_t size)
+{
+	struct dc_link *link = handle;
+
+	struct i2c_payload i2c_payloads[] = {{true, address, 1, &offset}, {false, address, size, data} };
+	struct i2c_command cmd = {i2c_payloads, 2, I2C_COMMAND_ENGINE_HW, link->dc->caps.i2c_speed_in_khz};
+
+	return dm_helpers_submit_i2c(link->ctx, link, &cmd);
+}
+
+static bool
+lp_write_dpcd(void *handle, uint32_t address, const uint8_t *data, uint32_t size)
+{
+	struct dc_link *link = handle;
+
+	return dm_helpers_dp_write_dpcd(link->ctx, link, address, data, size);
+}
+
+static bool
+lp_read_dpcd(void *handle, uint32_t address, uint8_t *data, uint32_t size)
+{
+	struct dc_link *link = handle;
+
+	return dm_helpers_dp_read_dpcd(link->ctx, link, address, data, size);
+}
+
+static void process_output(struct hdcp_workqueue *hdcp_work)
+{
+	struct mod_hdcp_output output = hdcp_work->output;
+
+	if (output.callback_stop)
+		cancel_delayed_work(&hdcp_work->callback_dwork);
+
+	if (output.callback_needed)
+		schedule_delayed_work(&hdcp_work->callback_dwork,
+				      msecs_to_jiffies(output.callback_delay));
+
+	if (output.watchdog_timer_stop)
+		cancel_delayed_work(&hdcp_work->watchdog_timer_dwork);
+
+	if (output.watchdog_timer_needed)
+		schedule_delayed_work(&hdcp_work->watchdog_timer_dwork,
+				      msecs_to_jiffies(output.watchdog_timer_delay));
+
+}
+
+void hdcp_add_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index, struct amdgpu_dm_connector *aconnector)
+{
+	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
+	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
+	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
+
+	mutex_lock(&hdcp_w->mutex);
+	hdcp_w->aconnector = aconnector;
+
+	mod_hdcp_add_display(&hdcp_w->hdcp, link, display, &hdcp_w->output);
+
+	schedule_delayed_work(&hdcp_w->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
+
+	process_output(hdcp_w);
+
+	mutex_unlock(&hdcp_w->mutex);
+
+}
+
+void hdcp_remove_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index,  unsigned int display_index)
+{
+	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
+
+	mutex_lock(&hdcp_w->mutex);
+
+	mod_hdcp_remove_display(&hdcp_w->hdcp, display_index, &hdcp_w->output);
+
+	cancel_delayed_work(&hdcp_w->property_validate_dwork);
+	hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+
+	process_output(hdcp_w);
+
+	mutex_unlock(&hdcp_w->mutex);
+
+}
+
+void hdcp_reset_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index)
+{
+	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
+
+	mutex_lock(&hdcp_w->mutex);
+
+	mod_hdcp_reset_connection(&hdcp_w->hdcp,  &hdcp_w->output);
+
+	cancel_delayed_work(&hdcp_w->property_validate_dwork);
+	hdcp_w->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+
+	process_output(hdcp_w);
+
+	mutex_unlock(&hdcp_w->mutex);
+}
+
+void hdcp_handle_cpirq(struct hdcp_workqueue *hdcp_work, unsigned int link_index)
+{
+	struct hdcp_workqueue *hdcp_w = &hdcp_work[link_index];
+
+	schedule_work(&hdcp_w->cpirq_work);
+}
+
+
+
+
+static void event_callback(struct work_struct *work)
+{
+	struct hdcp_workqueue *hdcp_work;
+
+	hdcp_work = container_of(to_delayed_work(work), struct hdcp_workqueue,
+				      callback_dwork);
+
+	mutex_lock(&hdcp_work->mutex);
+
+	cancel_delayed_work(&hdcp_work->watchdog_timer_dwork);
+
+	mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_CALLBACK,
+			       &hdcp_work->output);
+
+	process_output(hdcp_work);
+
+	mutex_unlock(&hdcp_work->mutex);
+
+
+}
+static void event_property_update(struct work_struct *work)
+{
+
+	struct hdcp_workqueue *hdcp_work = container_of(work, struct hdcp_workqueue, property_update_work);
+	struct amdgpu_dm_connector *aconnector = hdcp_work->aconnector;
+	struct drm_device *dev = hdcp_work->aconnector->base.dev;
+	long ret;
+
+	drm_modeset_lock(&dev->mode_config.connection_mutex, NULL);
+	mutex_lock(&hdcp_work->mutex);
+
+
+	if (aconnector->base.state->commit) {
+		ret = wait_for_completion_interruptible_timeout(&aconnector->base.state->commit->hw_done, 10 * HZ);
+
+		if (ret == 0) {
+			DRM_ERROR("HDCP state unknown! Setting it to DESIRED");
+			hdcp_work->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+		}
+	}
+
+	if (hdcp_work->encryption_status == MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON)
+		drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_ENABLED);
+	else
+		drm_hdcp_update_content_protection(&aconnector->base, DRM_MODE_CONTENT_PROTECTION_DESIRED);
+
+
+	mutex_unlock(&hdcp_work->mutex);
+	drm_modeset_unlock(&dev->mode_config.connection_mutex);
+}
+
+static void event_property_validate(struct work_struct *work)
+{
+	struct hdcp_workqueue *hdcp_work =
+		container_of(to_delayed_work(work), struct hdcp_workqueue, property_validate_dwork);
+	struct mod_hdcp_display_query query;
+	struct amdgpu_dm_connector *aconnector = hdcp_work->aconnector;
+
+	mutex_lock(&hdcp_work->mutex);
+
+	query.encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+	mod_hdcp_query_display(&hdcp_work->hdcp, aconnector->base.index, &query);
+
+	if (query.encryption_status != hdcp_work->encryption_status) {
+		hdcp_work->encryption_status = query.encryption_status;
+		schedule_work(&hdcp_work->property_update_work);
+	}
+
+	schedule_delayed_work(&hdcp_work->property_validate_dwork, msecs_to_jiffies(DRM_HDCP_CHECK_PERIOD_MS));
+
+	mutex_unlock(&hdcp_work->mutex);
+}
+
+static void event_watchdog_timer(struct work_struct *work)
+{
+	struct hdcp_workqueue *hdcp_work;
+
+	hdcp_work = container_of(to_delayed_work(work),
+				      struct hdcp_workqueue,
+				      watchdog_timer_dwork);
+
+	mutex_lock(&hdcp_work->mutex);
+
+	mod_hdcp_process_event(&hdcp_work->hdcp,
+			       MOD_HDCP_EVENT_WATCHDOG_TIMEOUT,
+			       &hdcp_work->output);
+
+	process_output(hdcp_work);
+
+	mutex_unlock(&hdcp_work->mutex);
+
+}
+
+static void event_cpirq(struct work_struct *work)
+{
+	struct hdcp_workqueue *hdcp_work;
+
+	hdcp_work = container_of(work, struct hdcp_workqueue, cpirq_work);
+
+	mutex_lock(&hdcp_work->mutex);
+
+	mod_hdcp_process_event(&hdcp_work->hdcp, MOD_HDCP_EVENT_CPIRQ, &hdcp_work->output);
+
+	process_output(hdcp_work);
+
+	mutex_unlock(&hdcp_work->mutex);
+
+}
+
+
+void hdcp_destroy(struct hdcp_workqueue *hdcp_work)
+{
+	int i = 0;
+
+	for (i = 0; i < hdcp_work->max_link; i++) {
+		cancel_delayed_work_sync(&hdcp_work[i].callback_dwork);
+		cancel_delayed_work_sync(&hdcp_work[i].watchdog_timer_dwork);
+	}
+
+	kfree(hdcp_work);
+
+}
+
+static void update_config(void *handle, struct cp_psp_stream_config *config)
+{
+	struct hdcp_workqueue *hdcp_work = handle;
+	struct amdgpu_dm_connector *aconnector = config->dm_stream_ctx;
+	int link_index = aconnector->dc_link->link_index;
+	struct mod_hdcp_display *display = &hdcp_work[link_index].display;
+	struct mod_hdcp_link *link = &hdcp_work[link_index].link;
+
+	memset(display, 0, sizeof(*display));
+	memset(link, 0, sizeof(*link));
+
+	display->index = aconnector->base.index;
+	display->state = MOD_HDCP_DISPLAY_ACTIVE;
+
+	if (aconnector->dc_sink != NULL)
+		link->mode = mod_hdcp_signal_type_to_operation_mode(aconnector->dc_sink->sink_signal);
+
+	display->controller = CONTROLLER_ID_D0 + config->otg_inst;
+	display->dig_fe = config->stream_enc_inst;
+	link->dig_be = config->link_enc_inst;
+	link->ddc_line = aconnector->dc_link->ddc_hw_inst + 1;
+	link->dp.rev = aconnector->dc_link->dpcd_caps.dpcd_rev.raw;
+	link->adjust.hdcp2.disable = 1;
+
+}
+
+struct hdcp_workqueue *hdcp_create_workqueue(void *psp_context, struct cp_psp *cp_psp, struct dc *dc)
+{
+
+	int max_caps = dc->caps.max_links;
+	struct hdcp_workqueue *hdcp_work = kzalloc(max_caps*sizeof(*hdcp_work), GFP_KERNEL);
+	int i = 0;
+
+	if (hdcp_work == NULL)
+		goto fail_alloc_context;
+
+	hdcp_work->max_link = max_caps;
+
+	for (i = 0; i < max_caps; i++) {
+
+		mutex_init(&hdcp_work[i].mutex);
+
+		INIT_WORK(&hdcp_work[i].cpirq_work, event_cpirq);
+		INIT_WORK(&hdcp_work[i].property_update_work, event_property_update);
+		INIT_DELAYED_WORK(&hdcp_work[i].callback_dwork, event_callback);
+		INIT_DELAYED_WORK(&hdcp_work[i].watchdog_timer_dwork, event_watchdog_timer);
+		INIT_DELAYED_WORK(&hdcp_work[i].property_validate_dwork, event_property_validate);
+
+		hdcp_work[i].hdcp.config.psp.handle =  psp_context;
+		hdcp_work[i].hdcp.config.ddc.handle = dc_get_link_at_index(dc, i);
+		hdcp_work[i].hdcp.config.ddc.funcs.write_i2c = lp_write_i2c;
+		hdcp_work[i].hdcp.config.ddc.funcs.read_i2c = lp_read_i2c;
+		hdcp_work[i].hdcp.config.ddc.funcs.write_dpcd = lp_write_dpcd;
+		hdcp_work[i].hdcp.config.ddc.funcs.read_dpcd = lp_read_dpcd;
+	}
+
+	cp_psp->funcs.update_stream_config = update_config;
+	cp_psp->handle = hdcp_work;
+
+	return hdcp_work;
+
+fail_alloc_context:
+	kfree(hdcp_work);
+
+	return NULL;
+
+
+
+}
+
+
+
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
new file mode 100644
index 000000000000..d3ba505d0696
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.h
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef AMDGPU_DM_AMDGPU_DM_HDCP_H_
+#define AMDGPU_DM_AMDGPU_DM_HDCP_H_
+
+#include "mod_hdcp.h"
+#include "hdcp.h"
+#include "dc.h"
+#include "dm_cp_psp.h"
+
+struct mod_hdcp;
+struct mod_hdcp_link;
+struct mod_hdcp_display;
+struct cp_psp;
+
+struct hdcp_workqueue {
+	struct work_struct cpirq_work;
+	struct work_struct property_update_work;
+	struct delayed_work callback_dwork;
+	struct delayed_work watchdog_timer_dwork;
+	struct delayed_work property_validate_dwork;
+	struct amdgpu_dm_connector *aconnector;
+	struct mutex mutex;
+
+	struct mod_hdcp hdcp;
+	struct mod_hdcp_output output;
+	struct mod_hdcp_display display;
+	struct mod_hdcp_link link;
+
+	enum mod_hdcp_encryption_status encryption_status;
+	uint8_t max_link;
+};
+
+void hdcp_add_display(struct hdcp_workqueue *hdcp_work, unsigned int link_index,
+		      struct amdgpu_dm_connector *aconnector);
+void hdcp_remove_display(struct hdcp_workqueue *work, unsigned int link_index, unsigned int display_index);
+void hdcp_reset_display(struct hdcp_workqueue *work, unsigned int link_index);
+void hdcp_handle_cpirq(struct hdcp_workqueue *work, unsigned int link_index);
+void hdcp_destroy(struct hdcp_workqueue *work);
+
+struct hdcp_workqueue *hdcp_create_workqueue(void *psp_context, struct cp_psp *cp_psp, struct dc *dc);
+
+#endif /* AMDGPU_DM_AMDGPU_DM_HDCP_H_ */
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 ee1dc75f5ddc..11e5784aa62a 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
@@ -97,11 +97,10 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 			(struct edid *) edid->raw_edid);
 
 	sad_count = drm_edid_to_sad((struct edid *) edid->raw_edid, &sads);
-	if (sad_count <= 0) {
-		DRM_INFO("SADs count is: %d, don't need to read it\n",
-				sad_count);
+	if (sad_count < 0)
+		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+	if (sad_count <= 0)
 		return result;
-	}
 
 	edid_caps->audio_mode_count = sad_count < DC_MAX_AUDIO_DESC_COUNT ? sad_count : DC_MAX_AUDIO_DESC_COUNT;
 	for (i = 0; i < edid_caps->audio_mode_count; ++i) {
@@ -282,7 +281,7 @@ void dm_helpers_dp_mst_clear_payload_allocation_table(
  * Polls for ACT (allocation change trigger) handled and sends
  * ALLOCATE_PAYLOAD message.
  */
-bool dm_helpers_dp_mst_poll_for_allocation_change_trigger(
+enum act_return_status dm_helpers_dp_mst_poll_for_allocation_change_trigger(
 		struct dc_context *ctx,
 		const struct dc_stream_state *stream)
 {
@@ -293,19 +292,19 @@ bool dm_helpers_dp_mst_poll_for_allocation_change_trigger(
 	aconnector = (struct amdgpu_dm_connector *)stream->dm_stream_context;
 
 	if (!aconnector || !aconnector->mst_port)
-		return false;
+		return ACT_FAILED;
 
 	mst_mgr = &aconnector->mst_port->mst_mgr;
 
 	if (!mst_mgr->mst_state)
-		return false;
+		return ACT_FAILED;
 
 	ret = drm_dp_check_act_status(mst_mgr);
 
 	if (ret)
-		return false;
+		return ACT_FAILED;
 
-	return true;
+	return ACT_SUCCESS;
 }
 
 bool dm_helpers_dp_mst_send_payload_allocation(
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index fa5d503d379c..64445c4cc4c2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -732,8 +732,10 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_dm_connector *amdgpu_dm_connector =
 				to_amdgpu_dm_connector(connector);
 
@@ -751,6 +753,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 					true);
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 }
 
 /**
@@ -765,8 +768,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 {
 	struct drm_device *dev = adev->ddev;
 	struct drm_connector *connector;
+	struct drm_connector_list_iter iter;
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+	drm_connector_list_iter_begin(dev, &iter);
+	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_dm_connector *amdgpu_dm_connector =
 				to_amdgpu_dm_connector(connector);
 		const struct dc_link *dc_link = amdgpu_dm_connector->dc_link;
@@ -779,4 +784,5 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 					false);
 		}
 	}
+	drm_connector_list_iter_end(&iter);
 }
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 5ec14efd4d8c..2bf8534c18fb 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
@@ -36,7 +36,9 @@
 #include "dc_link_ddc.h"
 
 #include "i2caux_interface.h"
-
+#if defined(CONFIG_DEBUG_FS)
+#include "amdgpu_dm_debugfs.h"
+#endif
 /* #define TRACE_DPCD */
 
 #ifdef TRACE_DPCD
@@ -113,6 +115,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 			result = -EIO;
 			break;
 		case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		case AUX_CHANNEL_OPERATION_FAILED_ENGINE_ACQUIRE:
 			result = -EBUSY;
 			break;
 		case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
@@ -123,31 +126,14 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	return result;
 }
 
-static enum drm_connector_status
-dm_dp_mst_detect(struct drm_connector *connector, bool force)
-{
-	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
-	struct amdgpu_dm_connector *master = aconnector->mst_port;
-
-	enum drm_connector_status status =
-		drm_dp_mst_detect_port(
-			connector,
-			&master->mst_mgr,
-			aconnector->port);
-
-	return status;
-}
-
 static void
 dm_dp_mst_connector_destroy(struct drm_connector *connector)
 {
 	struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
 	struct amdgpu_encoder *amdgpu_encoder = amdgpu_dm_connector->mst_encoder;
 
-	if (amdgpu_dm_connector->edid) {
-		kfree(amdgpu_dm_connector->edid);
-		amdgpu_dm_connector->edid = NULL;
-	}
+	kfree(amdgpu_dm_connector->edid);
+	amdgpu_dm_connector->edid = NULL;
 
 	drm_encoder_cleanup(&amdgpu_encoder->base);
 	kfree(amdgpu_encoder);
@@ -163,6 +149,12 @@ amdgpu_dm_mst_connector_late_register(struct drm_connector *connector)
 		to_amdgpu_dm_connector(connector);
 	struct drm_dp_mst_port *port = amdgpu_dm_connector->port;
 
+#if defined(CONFIG_DEBUG_FS)
+	connector_debugfs_init(amdgpu_dm_connector);
+	amdgpu_dm_connector->debugfs_dpcd_address = 0;
+	amdgpu_dm_connector->debugfs_dpcd_size = 0;
+#endif
+
 	return drm_dp_mst_connector_late_register(connector, port);
 }
 
@@ -177,7 +169,6 @@ amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector)
 }
 
 static const struct drm_connector_funcs dm_dp_mst_connector_funcs = {
-	.detect = dm_dp_mst_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = dm_dp_mst_connector_destroy,
 	.reset = amdgpu_dm_connector_funcs_reset,
@@ -245,17 +236,29 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static struct drm_encoder *dm_mst_best_encoder(struct drm_connector *connector)
+static struct drm_encoder *
+dm_mst_atomic_best_encoder(struct drm_connector *connector,
+			   struct drm_connector_state *connector_state)
 {
-	struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
+	return &to_amdgpu_dm_connector(connector)->mst_encoder->base;
+}
+
+static int
+dm_dp_mst_detect(struct drm_connector *connector,
+		 struct drm_modeset_acquire_ctx *ctx, bool force)
+{
+	struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector);
+	struct amdgpu_dm_connector *master = aconnector->mst_port;
 
-	return &amdgpu_dm_connector->mst_encoder->base;
+	return drm_dp_mst_detect_port(connector, ctx, &master->mst_mgr,
+				      aconnector->port);
 }
 
 static const struct drm_connector_helper_funcs dm_dp_mst_connector_helper_funcs = {
 	.get_modes = dm_dp_mst_get_modes,
 	.mode_valid = amdgpu_dm_connector_mode_valid,
-	.best_encoder = dm_mst_best_encoder,
+	.atomic_best_encoder = dm_mst_atomic_best_encoder,
+	.detect_ctx = dm_dp_mst_detect,
 };
 
 static void amdgpu_dm_encoder_destroy(struct drm_encoder *encoder)
@@ -417,6 +420,10 @@ void amdgpu_dm_initialize_dp_connector(struct amdgpu_display_manager *dm,
 	drm_dp_aux_register(&aconnector->dm_dp_aux.aux);
 	drm_dp_cec_register_connector(&aconnector->dm_dp_aux.aux,
 				      &aconnector->base);
+
+	if (aconnector->base.connector_type == DRM_MODE_CONNECTOR_eDP)
+		return;
+
 	aconnector->mst_mgr.cbs = &dm_mst_cbs;
 	drm_dp_mst_topology_mgr_init(
 		&aconnector->mst_mgr,
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index f4cfa0caeba8..778f186b3a05 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -342,10 +342,11 @@ bool dm_pp_get_clock_levels_by_type(
 	if (adev->powerplay.pp_funcs && 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. */
+			/* Error in pplib. Provide default values. */
+			get_default_clock_levels(clk_type, dc_clks);
 			return true;
 		}
-	} else if (adev->smu.funcs && adev->smu.funcs->get_clock_by_type) {
+	} else if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->get_clock_by_type) {
 		if (smu_get_clock_by_type(&adev->smu,
 					  dc_to_pp_clock_type(clk_type),
 					  &pp_clks)) {
@@ -365,7 +366,7 @@ bool dm_pp_get_clock_levels_by_type(
 			validation_clks.memory_max_clock = 80000;
 			validation_clks.level = 0;
 		}
-	} else if (adev->smu.funcs && adev->smu.funcs->get_max_high_clocks) {
+	} else if (adev->smu.ppt_funcs && adev->smu.ppt_funcs->get_max_high_clocks) {
 		if (smu_get_max_high_clocks(&adev->smu, &validation_clks)) {
 			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
 			validation_clks.engine_max_clock = 72000;
@@ -506,8 +507,8 @@ bool dm_pp_apply_clock_for_voltage_request(
 		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
 			adev->powerplay.pp_handle,
 			&pp_clock_request);
-	else if (adev->smu.funcs &&
-		 adev->smu.funcs->display_clock_voltage_request)
+	else if (adev->smu.ppt_funcs &&
+		 adev->smu.ppt_funcs->display_clock_voltage_request)
 		ret = smu_display_clock_voltage_request(&adev->smu,
 							&pp_clock_request);
 	if (ret)
@@ -527,7 +528,7 @@ bool dm_pp_get_static_clocks(
 		ret = adev->powerplay.pp_funcs->get_current_clocks(
 			adev->powerplay.pp_handle,
 			&pp_clk_info);
-	else if (adev->smu.funcs)
+	else if (adev->smu.ppt_funcs)
 		ret = smu_get_current_clocks(&adev->smu, &pp_clk_info);
 	if (ret)
 		return false;
@@ -589,10 +590,9 @@ void pp_rv_set_wm_ranges(struct pp_smu *pp,
 	if (pp_funcs && pp_funcs->set_watermarks_for_clocks_ranges)
 		pp_funcs->set_watermarks_for_clocks_ranges(pp_handle,
 							   &wm_with_clock_ranges);
-	else if (adev->smu.funcs &&
-		 adev->smu.funcs->set_watermarks_for_clock_ranges)
+	else
 		smu_set_watermarks_for_clock_ranges(&adev->smu,
-						    &wm_with_clock_ranges);
+				&wm_with_clock_ranges);
 }
 
 void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
@@ -604,7 +604,7 @@ void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
 
 	if (pp_funcs && pp_funcs->notify_smu_enable_pwe)
 		pp_funcs->notify_smu_enable_pwe(pp_handle);
-	else if (adev->smu.funcs)
+	else if (adev->smu.ppt_funcs)
 		smu_notify_smu_enable_pwe(&adev->smu);
 }
 
@@ -665,7 +665,6 @@ enum pp_smu_status pp_nv_set_wm_ranges(struct pp_smu *pp,
 {
 	const struct dc_context *ctx = pp->dm;
 	struct amdgpu_device *adev = ctx->driver_context;
-	struct smu_context *smu = &adev->smu;
 	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;
@@ -708,15 +707,7 @@ enum pp_smu_status pp_nv_set_wm_ranges(struct pp_smu *pp,
 			ranges->writer_wm_sets[i].min_drain_clk_mhz * 1000;
 	}
 
-	if (!smu->funcs)
-		return PP_SMU_RESULT_UNSUPPORTED;
-
-	/* 0: successful or smu.funcs->set_watermarks_for_clock_ranges = NULL;
-	 * 1: fail
-	 */
-	if (smu_set_watermarks_for_clock_ranges(&adev->smu,
-			&wm_with_clock_ranges))
-		return PP_SMU_RESULT_UNSUPPORTED;
+	smu_set_watermarks_for_clock_ranges(&adev->smu,	&wm_with_clock_ranges);
 
 	return PP_SMU_RESULT_OK;
 }
@@ -727,10 +718,10 @@ enum pp_smu_status pp_nv_set_pme_wa_enable(struct pp_smu *pp)
 	struct amdgpu_device *adev = ctx->driver_context;
 	struct smu_context *smu = &adev->smu;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
-	/* 0: successful or smu.funcs->set_azalia_d3_pme = NULL;  1: fail */
+	/* 0: successful or smu.ppt_funcs->set_azalia_d3_pme = NULL;  1: fail */
 	if (smu_set_azalia_d3_pme(smu))
 		return PP_SMU_RESULT_FAIL;
 
@@ -743,10 +734,10 @@ enum pp_smu_status pp_nv_set_display_count(struct pp_smu *pp, int count)
 	struct amdgpu_device *adev = ctx->driver_context;
 	struct smu_context *smu = &adev->smu;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
-	/* 0: successful or smu.funcs->set_display_count = NULL;  1: fail */
+	/* 0: successful or smu.ppt_funcs->set_display_count = NULL;  1: fail */
 	if (smu_set_display_count(smu, count))
 		return PP_SMU_RESULT_FAIL;
 
@@ -759,10 +750,10 @@ enum pp_smu_status pp_nv_set_min_deep_sleep_dcfclk(struct pp_smu *pp, int mhz)
 	struct amdgpu_device *adev = ctx->driver_context;
 	struct smu_context *smu = &adev->smu;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
-	/* 0: successful or smu.funcs->set_deep_sleep_dcefclk = NULL;1: fail */
+	/* 0: successful or smu.ppt_funcs->set_deep_sleep_dcefclk = NULL;1: fail */
 	if (smu_set_deep_sleep_dcefclk(smu, mhz))
 		return PP_SMU_RESULT_FAIL;
 
@@ -777,13 +768,13 @@ enum pp_smu_status pp_nv_set_hard_min_dcefclk_by_freq(
 	struct smu_context *smu = &adev->smu;
 	struct pp_display_clock_request clock_req;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
 	clock_req.clock_type = amd_pp_dcef_clock;
 	clock_req.clock_freq_in_khz = mhz * 1000;
 
-	/* 0: successful or smu.funcs->display_clock_voltage_request = NULL
+	/* 0: successful or smu.ppt_funcs->display_clock_voltage_request = NULL
 	 * 1: fail
 	 */
 	if (smu_display_clock_voltage_request(smu, &clock_req))
@@ -799,13 +790,13 @@ enum pp_smu_status pp_nv_set_hard_min_uclk_by_freq(struct pp_smu *pp, int mhz)
 	struct smu_context *smu = &adev->smu;
 	struct pp_display_clock_request clock_req;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
 	clock_req.clock_type = amd_pp_mem_clock;
 	clock_req.clock_freq_in_khz = mhz * 1000;
 
-	/* 0: successful or smu.funcs->display_clock_voltage_request = NULL
+	/* 0: successful or smu.ppt_funcs->display_clock_voltage_request = NULL
 	 * 1: fail
 	 */
 	if (smu_display_clock_voltage_request(smu, &clock_req))
@@ -835,7 +826,7 @@ enum pp_smu_status pp_nv_set_voltage_by_freq(struct pp_smu *pp,
 	struct smu_context *smu = &adev->smu;
 	struct pp_display_clock_request clock_req;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
 	switch (clock_id) {
@@ -853,7 +844,7 @@ enum pp_smu_status pp_nv_set_voltage_by_freq(struct pp_smu *pp,
 	}
 	clock_req.clock_freq_in_khz = mhz * 1000;
 
-	/* 0: successful or smu.funcs->display_clock_voltage_request = NULL
+	/* 0: successful or smu.ppt_funcs->display_clock_voltage_request = NULL
 	 * 1: fail
 	 */
 	if (smu_display_clock_voltage_request(smu, &clock_req))
@@ -869,13 +860,13 @@ enum pp_smu_status pp_nv_get_maximum_sustainable_clocks(
 	struct amdgpu_device *adev = ctx->driver_context;
 	struct smu_context *smu = &adev->smu;
 
-	if (!smu->funcs)
+	if (!smu->ppt_funcs)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
-	if (!smu->funcs->get_max_sustainable_clocks_by_dc)
+	if (!smu->ppt_funcs->get_max_sustainable_clocks_by_dc)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
-	if (!smu->funcs->get_max_sustainable_clocks_by_dc(smu, max_clocks))
+	if (!smu_get_max_sustainable_clocks_by_dc(smu, max_clocks))
 		return PP_SMU_RESULT_OK;
 
 	return PP_SMU_RESULT_FAIL;
@@ -894,13 +885,97 @@ enum pp_smu_status pp_nv_get_uclk_dpm_states(struct pp_smu *pp,
 	if (!smu->ppt_funcs->get_uclk_dpm_states)
 		return PP_SMU_RESULT_UNSUPPORTED;
 
-	if (!smu->ppt_funcs->get_uclk_dpm_states(smu,
+	if (!smu_get_uclk_dpm_states(smu,
 			clock_values_in_khz, num_states))
 		return PP_SMU_RESULT_OK;
 
 	return PP_SMU_RESULT_FAIL;
 }
 
+#ifdef CONFIG_DRM_AMD_DC_DCN2_1
+enum pp_smu_status pp_rn_get_dpm_clock_table(
+		struct pp_smu *pp, struct dpm_clocks *clock_table)
+{
+	const struct dc_context *ctx = pp->dm;
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct smu_context *smu = &adev->smu;
+
+	if (!smu->ppt_funcs)
+		return PP_SMU_RESULT_UNSUPPORTED;
+
+	if (!smu->ppt_funcs->get_dpm_clock_table)
+		return PP_SMU_RESULT_UNSUPPORTED;
+
+	if (!smu_get_dpm_clock_table(smu, clock_table))
+		return PP_SMU_RESULT_OK;
+
+	return PP_SMU_RESULT_FAIL;
+}
+
+enum pp_smu_status pp_rn_set_wm_ranges(struct pp_smu *pp,
+		struct pp_smu_wm_range_sets *ranges)
+{
+	const struct dc_context *ctx = pp->dm;
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct smu_context *smu = &adev->smu;
+	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;
+
+	if (!smu->ppt_funcs)
+		return PP_SMU_RESULT_UNSUPPORTED;
+
+	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_min_dcfclk_clk_in_khz =
+			ranges->reader_wm_sets[i].min_drain_clk_mhz;
+
+		wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz =
+			ranges->reader_wm_sets[i].max_drain_clk_mhz;
+
+		wm_dce_clocks[i].wm_min_mem_clk_in_khz =
+			ranges->reader_wm_sets[i].min_fill_clk_mhz;
+
+		wm_dce_clocks[i].wm_max_mem_clk_in_khz =
+			ranges->reader_wm_sets[i].max_fill_clk_mhz;
+	}
+
+	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_min_socclk_clk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_mhz;
+
+		wm_soc_clocks[i].wm_max_socclk_clk_in_khz =
+			ranges->writer_wm_sets[i].max_fill_clk_mhz;
+
+		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
+			ranges->writer_wm_sets[i].min_drain_clk_mhz;
+
+		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
+			ranges->writer_wm_sets[i].max_drain_clk_mhz;
+	}
+
+	smu_set_watermarks_for_clock_ranges(&adev->smu, &wm_with_clock_ranges);
+
+	return PP_SMU_RESULT_OK;
+}
+#endif
+
 void dm_pp_get_funcs(
 		struct dc_context *ctx,
 		struct pp_smu_funcs *funcs)
@@ -945,6 +1020,15 @@ void dm_pp_get_funcs(
 		funcs->nv_funcs.set_pstate_handshake_support = pp_nv_set_pstate_handshake_support;
 		break;
 #endif
+
+#ifdef CONFIG_DRM_AMD_DC_DCN2_1
+	case DCN_VERSION_2_1:
+		funcs->ctx.ver = PP_SMU_VER_RN;
+		funcs->rn_funcs.pp_smu.dm = ctx;
+		funcs->rn_funcs.set_wm_ranges = pp_rn_set_wm_ranges;
+		funcs->rn_funcs.get_dpm_clock_table = pp_rn_get_dpm_clock_table;
+		break;
+#endif
 	default:
 		DRM_ERROR("smu version is not supported !\n");
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index 627982cb15d2..a160512a2f04 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -48,6 +48,10 @@ DC_LIBS += dce110
 DC_LIBS += dce100
 DC_LIBS += dce80
 
+ifdef CONFIG_DRM_AMD_DC_HDCP
+DC_LIBS += hdcp
+endif
+
 AMD_DC = $(addsuffix /Makefile, $(addprefix $(FULL_AMD_DISPLAY_PATH)/dc/,$(DC_LIBS)))
 
 include $(AMD_DC)
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 221e0f56389f..823843cd2613 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -2543,7 +2543,6 @@ static enum bp_result construct_integrated_info(
 
 	/* Sort voltage table from low to high*/
 	if (result == BP_RESULT_OK) {
-		struct clock_voltage_caps temp = {0, 0};
 		uint32_t i;
 		uint32_t j;
 
@@ -2553,10 +2552,8 @@ static enum bp_result construct_integrated_info(
 						info->disp_clk_voltage[j].max_supported_clk <
 						info->disp_clk_voltage[j-1].max_supported_clk) {
 					/* swap j and j - 1*/
-					temp = info->disp_clk_voltage[j-1];
-					info->disp_clk_voltage[j-1] =
-							info->disp_clk_voltage[j];
-					info->disp_clk_voltage[j] = temp;
+					swap(info->disp_clk_voltage[j - 1],
+					     info->disp_clk_voltage[j]);
 				}
 			}
 		}
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 dff65c0fe82f..7873abea4112 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -1613,8 +1613,6 @@ static enum bp_result construct_integrated_info(
 
 	struct atom_common_table_header *header;
 	struct atom_data_revision revision;
-
-	struct clock_voltage_caps temp = {0, 0};
 	uint32_t i;
 	uint32_t j;
 
@@ -1644,10 +1642,8 @@ static enum bp_result construct_integrated_info(
 				info->disp_clk_voltage[j-1].max_supported_clk
 				) {
 				/* swap j and j - 1*/
-				temp = info->disp_clk_voltage[j-1];
-				info->disp_clk_voltage[j-1] =
-					info->disp_clk_voltage[j];
-				info->disp_clk_voltage[j] = temp;
+				swap(info->disp_clk_voltage[j - 1],
+				     info->disp_clk_voltage[j]);
 			}
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 985633c08a26..26c6d735cdc7 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -24,15 +24,20 @@
 # It calculates Bandwidth and Watermarks values for HW programming
 #
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+calcs_ccflags := -mhard-float -msse
 
-calcs_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+calcs_ccflags += -mpreferred-stack-boundary=4
+else
 calcs_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
index c43797bea413..8828dd9c3783 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/clk_mgr.c
@@ -65,6 +65,31 @@ int clk_mgr_helper_get_active_display_cnt(
 	return display_count;
 }
 
+void clk_mgr_exit_optimized_pwr_state(const struct dc *dc, struct clk_mgr *clk_mgr)
+{
+	struct dc_link *edp_link = get_edp_link(dc);
+
+	if (dc->hwss.exit_optimized_pwr_state)
+		dc->hwss.exit_optimized_pwr_state(dc, dc->current_state);
+
+	if (edp_link) {
+		clk_mgr->psr_allow_active_cache = edp_link->psr_allow_active;
+		dc_link_set_psr_allow_active(edp_link, false, false);
+	}
+
+}
+
+void clk_mgr_optimize_pwr_state(const struct dc *dc, struct clk_mgr *clk_mgr)
+{
+	struct dc_link *edp_link = get_edp_link(dc);
+
+	if (edp_link)
+		dc_link_set_psr_allow_active(edp_link, clk_mgr->psr_allow_active_cache, false);
+
+	if (dc->hwss.optimize_pwr_state)
+		dc->hwss.optimize_pwr_state(dc, dc->current_state);
+
+}
 
 struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *pp_smu, struct dccg *dccg)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
index c5c8c4901eed..26db1c5d4e4d 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce100/dce_clk_mgr.c
@@ -147,7 +147,7 @@ int dce_get_dp_ref_freq_khz(struct clk_mgr *clk_mgr_base)
 
 	/* Calculate the current DFS clock, in kHz.*/
 	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
-		* clk_mgr->dentist_vco_freq_khz) / target_div;
+		* clk_mgr->base.dentist_vco_freq_khz) / target_div;
 
 	return dce_adjust_dp_ref_freq_for_ss(clk_mgr, dp_ref_clk_khz);
 }
@@ -239,7 +239,7 @@ int dce_set_clock(
 	/* Make sure requested clock isn't lower than minimum threshold*/
 	if (requested_clk_khz > 0)
 		requested_clk_khz = max(requested_clk_khz,
-				clk_mgr_dce->dentist_vco_freq_khz / 64);
+				clk_mgr_dce->base.dentist_vco_freq_khz / 64);
 
 	/* Prepare to program display clock*/
 	pxl_clk_params.target_pixel_clock_100hz = requested_clk_khz * 10;
@@ -276,11 +276,11 @@ static void dce_clock_read_integrated_info(struct clk_mgr_internal *clk_mgr_dce)
 	int i;
 
 	if (bp->integrated_info)
-		clk_mgr_dce->dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
-	if (clk_mgr_dce->dentist_vco_freq_khz == 0) {
-		clk_mgr_dce->dentist_vco_freq_khz = bp->fw_info.smu_gpu_pll_output_freq;
-		if (clk_mgr_dce->dentist_vco_freq_khz == 0)
-			clk_mgr_dce->dentist_vco_freq_khz = 3600000;
+		clk_mgr_dce->base.dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
+	if (clk_mgr_dce->base.dentist_vco_freq_khz == 0) {
+		clk_mgr_dce->base.dentist_vco_freq_khz = bp->fw_info.smu_gpu_pll_output_freq;
+		if (clk_mgr_dce->base.dentist_vco_freq_khz == 0)
+			clk_mgr_dce->base.dentist_vco_freq_khz = 3600000;
 	}
 
 	/*update the maximum display clock for each power state*/
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
index 7c746ef1e32e..a6c46e903ff9 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dce112/dce112_clk_mgr.c
@@ -81,7 +81,7 @@ int dce112_set_clock(struct clk_mgr *clk_mgr_base, int requested_clk_khz)
 	/* Make sure requested clock isn't lower than minimum threshold*/
 	if (requested_clk_khz > 0)
 		requested_clk_khz = max(requested_clk_khz,
-				clk_mgr_dce->dentist_vco_freq_khz / 62);
+				clk_mgr_dce->base.dentist_vco_freq_khz / 62);
 
 	dce_clk_params.target_clock_frequency = requested_clk_khz;
 	dce_clk_params.pll_id = CLOCK_SOURCE_ID_DFS;
@@ -135,7 +135,7 @@ int dce112_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_clk_khz)
 	/* Make sure requested clock isn't lower than minimum threshold*/
 	if (requested_clk_khz > 0)
 		requested_clk_khz = max(requested_clk_khz,
-				clk_mgr->dentist_vco_freq_khz / 62);
+				clk_mgr->base.dentist_vco_freq_khz / 62);
 
 	dce_clk_params.target_clock_frequency = requested_clk_khz;
 	dce_clk_params.pll_id = CLOCK_SOURCE_ID_DFS;
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
index 47f529ce280a..3fab9296918a 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn10/rv1_clk_mgr.c
@@ -139,6 +139,9 @@ static void rv1_update_clocks(struct clk_mgr *clk_mgr_base,
 
 	ASSERT(clk_mgr->pp_smu);
 
+	if (dc->work_arounds.skip_clock_update)
+		return;
+
 	pp_smu = &clk_mgr->pp_smu->rv_funcs;
 
 	display_count = clk_mgr_helper_get_active_display_cnt(dc, context);
@@ -266,11 +269,11 @@ void rv1_clk_mgr_construct(struct dc_context *ctx, struct clk_mgr_internal *clk_
 	clk_mgr->base.dprefclk_khz = 600000;
 
 	if (bp->integrated_info)
-		clk_mgr->dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
-	if (bp->fw_info_valid && clk_mgr->dentist_vco_freq_khz == 0) {
-		clk_mgr->dentist_vco_freq_khz = bp->fw_info.smu_gpu_pll_output_freq;
-		if (clk_mgr->dentist_vco_freq_khz == 0)
-			clk_mgr->dentist_vco_freq_khz = 3600000;
+		clk_mgr->base.dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
+	if (bp->fw_info_valid && clk_mgr->base.dentist_vco_freq_khz == 0) {
+		clk_mgr->base.dentist_vco_freq_khz = bp->fw_info.smu_gpu_pll_output_freq;
+		if (clk_mgr->base.dentist_vco_freq_khz == 0)
+			clk_mgr->base.dentist_vco_freq_khz = 3600000;
 	}
 
 	if (!debug->disable_dfs_bypass && bp->integrated_info)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
index 3e8ac303bd52..25d7b7c6681c 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.c
@@ -104,84 +104,39 @@ void dcn20_update_clocks_update_dpp_dto(struct clk_mgr_internal *clk_mgr,
 {
 	int i;
 
+	clk_mgr->dccg->ref_dppclk = clk_mgr->base.clks.dppclk_khz;
 	for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) {
 		int dpp_inst, dppclk_khz;
 
-		if (!context->res_ctx.pipe_ctx[i].plane_state)
-			continue;
-
-		dpp_inst = context->res_ctx.pipe_ctx[i].plane_res.dpp->inst;
+		/* Loop index will match dpp->inst if resource exists,
+		 * and we want to avoid dependency on dpp object
+		 */
+		dpp_inst = i;
 		dppclk_khz = context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
+
 		clk_mgr->dccg->funcs->update_dpp_dto(
-				clk_mgr->dccg, dpp_inst, dppclk_khz, false);
+				clk_mgr->dccg, dpp_inst, dppclk_khz);
 	}
 }
 
-static void update_global_dpp_clk(struct clk_mgr_internal *clk_mgr, unsigned int khz)
+void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr)
 {
 	int dpp_divider = DENTIST_DIVIDER_RANGE_SCALE_FACTOR
-			* clk_mgr->dentist_vco_freq_khz / khz;
-
-	uint32_t dppclk_wdivider = dentist_get_did_from_divider(dpp_divider);
-
-	REG_UPDATE(DENTIST_DISPCLK_CNTL,
-			DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider);
-	REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100);
-}
-
-static void update_display_clk(struct clk_mgr_internal *clk_mgr, unsigned int khz)
-{
+			* clk_mgr->base.dentist_vco_freq_khz / clk_mgr->base.clks.dppclk_khz;
 	int disp_divider = DENTIST_DIVIDER_RANGE_SCALE_FACTOR
-			* clk_mgr->dentist_vco_freq_khz / khz;
+			* clk_mgr->base.dentist_vco_freq_khz / clk_mgr->base.clks.dispclk_khz;
 
+	uint32_t dppclk_wdivider = dentist_get_did_from_divider(dpp_divider);
 	uint32_t dispclk_wdivider = dentist_get_did_from_divider(disp_divider);
 
 	REG_UPDATE(DENTIST_DISPCLK_CNTL,
 			DENTIST_DISPCLK_WDIVIDER, dispclk_wdivider);
+//	REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, 1, 5, 100);
+	REG_UPDATE(DENTIST_DISPCLK_CNTL,
+			DENTIST_DPPCLK_WDIVIDER, dppclk_wdivider);
+	REG_WAIT(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, 1, 5, 100);
 }
 
-static void request_voltage_and_program_disp_clk(struct clk_mgr *clk_mgr_base, unsigned int khz)
-{
-	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
-	struct dc *dc = clk_mgr_base->ctx->dc;
-	struct pp_smu_funcs_nv *pp_smu = NULL;
-	bool going_up = clk_mgr->base.clks.dispclk_khz < khz;
-
-	if (dc->res_pool->pp_smu)
-		pp_smu = &dc->res_pool->pp_smu->nv_funcs;
-
-	clk_mgr->base.clks.dispclk_khz = khz;
-
-	if (going_up && pp_smu && pp_smu->set_voltage_by_freq)
-		pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_DISPCLK, clk_mgr_base->clks.dispclk_khz / 1000);
-
-	update_display_clk(clk_mgr, khz);
-
-	if (!going_up && pp_smu && pp_smu->set_voltage_by_freq)
-		pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_DISPCLK, clk_mgr_base->clks.dispclk_khz / 1000);
-}
-
-static void request_voltage_and_program_global_dpp_clk(struct clk_mgr *clk_mgr_base, unsigned int khz)
-{
-	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
-	struct dc *dc = clk_mgr_base->ctx->dc;
-	struct pp_smu_funcs_nv *pp_smu = NULL;
-	bool going_up = clk_mgr->base.clks.dppclk_khz < khz;
-
-	if (dc->res_pool->pp_smu)
-		pp_smu = &dc->res_pool->pp_smu->nv_funcs;
-
-	clk_mgr->base.clks.dppclk_khz = khz;
-	clk_mgr->dccg->ref_dppclk = khz;
-
-	if (going_up && pp_smu && pp_smu->set_voltage_by_freq)
-		pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_PIXELCLK, clk_mgr_base->clks.dppclk_khz / 1000);
-
-	update_global_dpp_clk(clk_mgr, khz);
-
-	if (!going_up && pp_smu && pp_smu->set_voltage_by_freq)
-		pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_PIXELCLK, clk_mgr_base->clks.dppclk_khz / 1000);
-}
 
 void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
@@ -192,11 +147,12 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 	struct dc *dc = clk_mgr_base->ctx->dc;
 	struct pp_smu_funcs_nv *pp_smu = NULL;
 	int display_count;
+	bool update_dppclk = false;
 	bool update_dispclk = false;
 	bool enter_display_off = false;
+	bool dpp_clock_lowered = false;
 	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 	bool force_reset = false;
-	int i;
 
 	if (dc->work_arounds.skip_clock_update)
 		return;
@@ -251,12 +207,10 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 
 	if (should_update_pstate_support(safe_to_lower, new_clocks->p_state_change_support, clk_mgr_base->clks.p_state_change_support)) {
 		clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support;
-
 		clk_mgr_base->clks.p_state_change_support = new_clocks->p_state_change_support;
 		if (pp_smu && pp_smu->set_pstate_handshake_support)
 			pp_smu->set_pstate_handshake_support(&pp_smu->pp_smu, clk_mgr_base->clks.p_state_change_support);
 	}
-	clk_mgr_base->clks.prev_p_state_change_support = clk_mgr_base->clks.p_state_change_support;
 
 	if (should_set_clock(safe_to_lower, new_clocks->dramclk_khz, clk_mgr_base->clks.dramclk_khz)) {
 		clk_mgr_base->clks.dramclk_khz = new_clocks->dramclk_khz;
@@ -264,50 +218,40 @@ void dcn2_update_clocks(struct clk_mgr *clk_mgr_base,
 			pp_smu->set_hard_min_uclk_by_freq(&pp_smu->pp_smu, clk_mgr_base->clks.dramclk_khz / 1000);
 	}
 
-	if (dc->config.forced_clocks == false) {
-		// First update display clock
-		if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz))
-			request_voltage_and_program_disp_clk(clk_mgr_base, new_clocks->dispclk_khz);
-
-		// Updating DPP clock requires some more logic
-		if (!safe_to_lower) {
-			// For pre-programming, we need to make sure any DPP clock that will go up has to go up
+	if (should_set_clock(safe_to_lower, new_clocks->dppclk_khz, clk_mgr->base.clks.dppclk_khz)) {
+		if (clk_mgr->base.clks.dppclk_khz > new_clocks->dppclk_khz)
+			dpp_clock_lowered = true;
+		clk_mgr->base.clks.dppclk_khz = new_clocks->dppclk_khz;
 
-			// First raise the global reference if needed
-			if (new_clocks->dppclk_khz > clk_mgr_base->clks.dppclk_khz)
-				request_voltage_and_program_global_dpp_clk(clk_mgr_base, new_clocks->dppclk_khz);
+		if (pp_smu && pp_smu->set_voltage_by_freq)
+			pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_PIXELCLK, clk_mgr_base->clks.dppclk_khz / 1000);
 
-			// Then raise any dividers that need raising
-			for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) {
-				int dpp_inst, dppclk_khz;
+		update_dppclk = true;
+	}
 
-				if (!context->res_ctx.pipe_ctx[i].plane_state)
-					continue;
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, clk_mgr_base->clks.dispclk_khz)) {
+		clk_mgr_base->clks.dispclk_khz = new_clocks->dispclk_khz;
+		if (pp_smu && pp_smu->set_voltage_by_freq)
+			pp_smu->set_voltage_by_freq(&pp_smu->pp_smu, PP_SMU_NV_DISPCLK, clk_mgr_base->clks.dispclk_khz / 1000);
 
-				dpp_inst = context->res_ctx.pipe_ctx[i].plane_res.dpp->inst;
-				dppclk_khz = context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
+		update_dispclk = true;
+	}
 
-				clk_mgr->dccg->funcs->update_dpp_dto(clk_mgr->dccg, dpp_inst, dppclk_khz, true);
-			}
+	if (dc->config.forced_clocks == false || (force_reset && safe_to_lower)) {
+		if (dpp_clock_lowered) {
+			// if clock is being lowered, increase DTO before lowering refclk
+			dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
+			dcn20_update_clocks_update_dentist(clk_mgr);
 		} else {
-			// For post-programming, we can lower ref clk if needed, and unconditionally set all the DTOs
-
-			if (new_clocks->dppclk_khz < clk_mgr_base->clks.dppclk_khz)
-				request_voltage_and_program_global_dpp_clk(clk_mgr_base, new_clocks->dppclk_khz);
-
-			for (i = 0; i < clk_mgr->base.ctx->dc->res_pool->pipe_count; i++) {
-				int dpp_inst, dppclk_khz;
-
-				if (!context->res_ctx.pipe_ctx[i].plane_state)
-					continue;
-
-				dpp_inst = context->res_ctx.pipe_ctx[i].plane_res.dpp->inst;
-				dppclk_khz = context->res_ctx.pipe_ctx[i].plane_res.bw.dppclk_khz;
-
-				clk_mgr->dccg->funcs->update_dpp_dto(clk_mgr->dccg, dpp_inst, dppclk_khz, false);
-			}
+			// if clock is being raised, increase refclk before lowering DTO
+			if (update_dppclk || update_dispclk)
+				dcn20_update_clocks_update_dentist(clk_mgr);
+			// always update dtos unless clock is lowered and not safe to lower
+			if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
+				dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
 		}
 	}
+
 	if (update_dispclk &&
 			dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
 		/*update dmcu for wait_loop count*/
@@ -320,6 +264,8 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr,
 		struct dc_state *context,
 		bool safe_to_lower)
 {
+	struct clk_mgr_internal *clk_mgr_int = TO_CLK_MGR_INTERNAL(clk_mgr);
+
 	struct dc_clocks *new_clocks = &context->bw_ctx.bw.dcn.clk;
 	/* Min fclk = 1.2GHz since all the extra scemi logic seems to run off of it */
 	int fclk_adj = new_clocks->fclk_khz > 1200000 ? new_clocks->fclk_khz : 1200000;
@@ -357,14 +303,18 @@ void dcn2_update_clocks_fpga(struct clk_mgr *clk_mgr,
 		clk_mgr->clks.dispclk_khz = new_clocks->dispclk_khz;
 	}
 
-	/* Both fclk and dppclk ref are run on the same scemi clock so we
-	 * need to keep the same value for both
+	/* Both fclk and ref_dppclk run on the same scemi clock.
+	 * So take the higher value since the DPP DTO is typically programmed
+	 * such that max dppclk is 1:1 with ref_dppclk.
 	 */
 	if (clk_mgr->clks.fclk_khz > clk_mgr->clks.dppclk_khz)
 		clk_mgr->clks.dppclk_khz = clk_mgr->clks.fclk_khz;
 	if (clk_mgr->clks.dppclk_khz > clk_mgr->clks.fclk_khz)
 		clk_mgr->clks.fclk_khz = clk_mgr->clks.dppclk_khz;
 
+	// Both fclk and ref_dppclk run on the same scemi clock.
+	clk_mgr_int->dccg->ref_dppclk = clk_mgr->clks.fclk_khz;
+
 	dm_set_dcn_clocks(clk_mgr->ctx, &clk_mgr->clks);
 }
 
@@ -409,12 +359,36 @@ void dcn2_get_clock(struct clk_mgr *clk_mgr,
 	}
 }
 
+static bool dcn2_are_clock_states_equal(struct dc_clocks *a,
+		struct dc_clocks *b)
+{
+	if (a->dispclk_khz != b->dispclk_khz)
+		return false;
+	else if (a->dppclk_khz != b->dppclk_khz)
+		return false;
+	else if (a->dcfclk_khz != b->dcfclk_khz)
+		return false;
+	else if (a->socclk_khz != b->socclk_khz)
+		return false;
+	else if (a->dcfclk_deep_sleep_khz != b->dcfclk_deep_sleep_khz)
+		return false;
+	else if (a->phyclk_khz != b->phyclk_khz)
+		return false;
+	else if (a->dramclk_khz != b->dramclk_khz)
+		return false;
+	else if (a->p_state_change_support != b->p_state_change_support)
+		return false;
+
+	return true;
+}
+
 static struct clk_mgr_funcs dcn2_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.update_clocks = dcn2_update_clocks,
 	.init_clocks = dcn2_init_clocks,
 	.enable_pme_wa = dcn2_enable_pme_wa,
 	.get_clock = dcn2_get_clock,
+	.are_clock_states_equal = dcn2_are_clock_states_equal,
 };
 
 
@@ -442,7 +416,7 @@ void dcn20_clk_mgr_construct(
 
 	if (IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) {
 		dcn2_funcs.update_clocks = dcn2_update_clocks_fpga;
-		clk_mgr->dentist_vco_freq_khz = 3850000;
+		clk_mgr->base.dentist_vco_freq_khz = 3850000;
 
 	} else {
 		/* DFS Slice 2 should be used for DPREFCLK */
@@ -466,15 +440,15 @@ void dcn20_clk_mgr_construct(
 		pll_req = dc_fixpt_mul_int(pll_req, 100000);
 
 		/* integer part is now VCO frequency in kHz */
-		clk_mgr->dentist_vco_freq_khz = dc_fixpt_floor(pll_req);
+		clk_mgr->base.dentist_vco_freq_khz = dc_fixpt_floor(pll_req);
 
 		/* in case we don't get a value from the register, use default */
-		if (clk_mgr->dentist_vco_freq_khz == 0)
-			clk_mgr->dentist_vco_freq_khz = 3850000;
+		if (clk_mgr->base.dentist_vco_freq_khz == 0)
+			clk_mgr->base.dentist_vco_freq_khz = 3850000;
 
 		/* Calculate the DPREFCLK in kHz.*/
 		clk_mgr->base.dprefclk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
-			* clk_mgr->dentist_vco_freq_khz) / target_div;
+			* clk_mgr->base.dentist_vco_freq_khz) / target_div;
 	}
 	//Integrated_info table does not exist on dGPU projects so should not be referenced
 	//anywhere in code for dGPUs.
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
index ac31a9787305..c9fd824f3c23 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn20/dcn20_clk_mgr.h
@@ -50,4 +50,5 @@ void dcn2_get_clock(struct clk_mgr *clk_mgr,
 			enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg);
 
+void dcn20_update_clocks_update_dentist(struct clk_mgr_internal *clk_mgr);
 #endif //__DCN20_CLK_MGR_H__
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
index 787f94d815f4..790a2d211bd6 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
@@ -52,6 +52,45 @@
 #define REG(reg_name) \
 	(CLK_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
 
+
+/* TODO: evaluate how to lower or disable all dcn clocks in screen off case */
+int rn_get_active_display_cnt_wa(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	int i, display_count;
+	bool hdmi_present = false;
+
+	display_count = 0;
+	for (i = 0; i < context->stream_count; i++) {
+		const struct dc_stream_state *stream = context->streams[i];
+
+		if (stream->signal == SIGNAL_TYPE_HDMI_TYPE_A)
+			hdmi_present = true;
+	}
+
+	for (i = 0; i < dc->link_count; i++) {
+		const struct dc_link *link = dc->links[i];
+
+		/*
+		 * Only notify active stream or virtual stream.
+		 * Need to notify virtual stream to work around
+		 * headless case. HPD does not fire when system is in
+		 * S0i2.
+		 */
+		/* abusing the fact that the dig and phy are coupled to see if the phy is enabled */
+		if (link->connector_signal == SIGNAL_TYPE_VIRTUAL ||
+				link->link_enc->funcs->is_dig_enabled(link->link_enc))
+			display_count++;
+	}
+
+	/* WA for hang on HDMI after display off back back on*/
+	if (display_count == 0 && hdmi_present)
+		display_count = 1;
+
+	return display_count;
+}
+
 void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 			struct dc_state *context,
 			bool safe_to_lower)
@@ -62,17 +101,36 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 	int display_count;
 	bool update_dppclk = false;
 	bool update_dispclk = false;
-	bool enter_display_off = false;
 	bool dpp_clock_lowered = false;
-	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 
-	display_count = clk_mgr_helper_get_active_display_cnt(dc, context);
+	struct dmcu *dmcu = clk_mgr_base->ctx->dc->res_pool->dmcu;
 
-	if (display_count == 0)
-		enter_display_off = true;
+	if (dc->work_arounds.skip_clock_update)
+		return;
 
-	if (enter_display_off == safe_to_lower) {
-		rn_vbios_smu_set_display_count(clk_mgr, display_count);
+	/*
+	 * if it is safe to lower, but we are already in the lower state, we don't have to do anything
+	 * also if safe to lower is false, we just go in the higher state
+	 */
+	if (safe_to_lower) {
+		/* check that we're not already in lower */
+		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_LOW_POWER) {
+
+			display_count = rn_get_active_display_cnt_wa(dc, context);
+			/* if we can go lower, go lower */
+			if (display_count == 0) {
+				rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_LOW_POWER);
+				/* update power state */
+				clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_LOW_POWER;
+			}
+		}
+	} else {
+		/* check that we're not already in D0 */
+		if (clk_mgr_base->clks.pwr_state != DCN_PWR_STATE_MISSION_MODE) {
+			rn_vbios_smu_set_dcn_low_power_state(clk_mgr, DCN_PWR_STATE_MISSION_MODE);
+			/* update power state */
+			clk_mgr_base->clks.pwr_state = DCN_PWR_STATE_MISSION_MODE;
+		}
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, clk_mgr_base->clks.phyclk_khz)) {
@@ -113,7 +171,8 @@ void rn_update_clocks(struct clk_mgr *clk_mgr_base,
 		// if clock is being raised, increase refclk before lowering DTO
 		if (update_dppclk || update_dispclk)
 			rn_vbios_smu_set_dppclk(clk_mgr, clk_mgr_base->clks.dppclk_khz);
-		if (update_dppclk)
+		// always update dtos unless clock is lowered and not safe to lower
+		if (new_clocks->dppclk_khz >= dc->current_state->bw_ctx.bw.dcn.clk.dppclk_khz)
 			dcn20_update_clocks_update_dpp_dto(clk_mgr, context);
 	}
 
@@ -319,7 +378,7 @@ void rn_get_clk_states(struct clk_mgr *clk_mgr_base, struct clk_states *s)
 
 	rn_dump_clk_registers(&sb, clk_mgr_base, &log_info);
 
-	s->dprefclk_khz = sb.dprefclk;
+	s->dprefclk_khz = sb.dprefclk * 1000;
 }
 
 void rn_enable_pme_wa(struct clk_mgr *clk_mgr_base)
@@ -329,12 +388,96 @@ void rn_enable_pme_wa(struct clk_mgr *clk_mgr_base)
 	rn_vbios_smu_enable_pme_wa(clk_mgr);
 }
 
+void rn_init_clocks(struct clk_mgr *clk_mgr)
+{
+	memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks));
+	// Assumption is that boot state always supports pstate
+	clk_mgr->clks.p_state_change_support = true;
+	clk_mgr->clks.prev_p_state_change_support = true;
+	clk_mgr->clks.pwr_state = DCN_PWR_STATE_UNKNOWN;
+}
+
+void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_smu_wm_range_sets *ranges)
+{
+	int i, num_valid_sets;
+
+	num_valid_sets = 0;
+
+	for (i = 0; i < WM_SET_COUNT; i++) {
+		/* skip empty entries, the smu array has no holes*/
+		if (!bw_params->wm_table.entries[i].valid)
+			continue;
+
+		ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst;
+		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;;
+		/* We will not select WM based on dcfclk, so leave it as unconstrained */
+		ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+		ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+		/* fclk wil be used to select WM*/
+
+		if (ranges->reader_wm_sets[num_valid_sets].wm_type == WM_TYPE_PSTATE_CHG) {
+			if (i == 0)
+				ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = 0;
+			else {
+				/* add 1 to make it non-overlapping with next lvl */
+				ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = bw_params->clk_table.entries[i - 1].fclk_mhz + 1;
+			}
+			ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = bw_params->clk_table.entries[i].fclk_mhz;
+
+		} else {
+			/* unconstrained for memory retraining */
+			ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+			ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+
+			/* Modify previous watermark range to cover up to max */
+			ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+		}
+		num_valid_sets++;
+	}
+
+	ASSERT(num_valid_sets != 0); /* Must have at least one set of valid watermarks */
+	ranges->num_reader_wm_sets = num_valid_sets;
+
+	/* modify the min and max to make sure we cover the whole range*/
+	ranges->reader_wm_sets[0].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+	ranges->reader_wm_sets[0].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+	ranges->reader_wm_sets[ranges->num_reader_wm_sets - 1].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+	ranges->reader_wm_sets[ranges->num_reader_wm_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+
+	/* This is for writeback only, does not matter currently as no writeback support*/
+	ranges->num_writer_wm_sets = 1;
+	ranges->writer_wm_sets[0].wm_inst = WM_A;
+	ranges->writer_wm_sets[0].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+	ranges->writer_wm_sets[0].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+	ranges->writer_wm_sets[0].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
+	ranges->writer_wm_sets[0].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+
+}
+
+static void rn_notify_wm_ranges(struct clk_mgr *clk_mgr_base)
+{
+	struct dc_debug_options *debug = &clk_mgr_base->ctx->dc->debug;
+	struct pp_smu_wm_range_sets ranges = {0};
+	struct clk_mgr_internal *clk_mgr = TO_CLK_MGR_INTERNAL(clk_mgr_base);
+	struct pp_smu_funcs *pp_smu = clk_mgr->pp_smu;
+
+	if (!debug->disable_pplib_wm_range) {
+		build_watermark_ranges(clk_mgr_base->bw_params, &ranges);
+
+		/* Notify PP Lib/SMU which Watermarks to use for which clock ranges */
+		if (pp_smu && pp_smu->rn_funcs.set_wm_ranges)
+			pp_smu->rn_funcs.set_wm_ranges(&pp_smu->rn_funcs.pp_smu, &ranges);
+	}
+
+}
+
 static struct clk_mgr_funcs dcn21_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.update_clocks = rn_update_clocks,
-	.init_clocks = dcn2_init_clocks,
+	.init_clocks = rn_init_clocks,
 	.enable_pme_wa = rn_enable_pme_wa,
-	/* .dump_clk_registers = rn_dump_clk_registers */
+	/* .dump_clk_registers = rn_dump_clk_registers, */
+	.notify_wm_ranges = rn_notify_wm_ranges
 };
 
 struct clk_bw_params rn_bw_params = {
@@ -405,80 +548,50 @@ struct clk_bw_params rn_bw_params = {
 	}
 };
 
-void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_smu_wm_range_sets *ranges)
+static unsigned int find_dcfclk_for_voltage(struct dpm_clocks *clock_table, unsigned int voltage)
 {
-	int i, num_valid_sets;
-
-	num_valid_sets = 0;
-
-	for (i = 0; i < WM_SET_COUNT; i++) {
-		/* skip empty entries, the smu array has no holes*/
-		if (!bw_params->wm_table.entries[i].valid)
-			continue;
-
-		ranges->reader_wm_sets[num_valid_sets].wm_inst = bw_params->wm_table.entries[i].wm_inst;
-		ranges->reader_wm_sets[num_valid_sets].wm_type = bw_params->wm_table.entries[i].wm_type;;
-		/* We will not select WM based on dcfclk, so leave it as unconstrained */
-		ranges->reader_wm_sets[num_valid_sets].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-		ranges->reader_wm_sets[num_valid_sets].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-		/* fclk wil be used to select WM*/
-
-		if (ranges->reader_wm_sets[num_valid_sets].wm_type == WM_TYPE_PSTATE_CHG) {
-			if (i == 0)
-				ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = 0;
-			else {
-				/* add 1 to make it non-overlapping with next lvl */
-				ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = bw_params->clk_table.entries[i - 1].fclk_mhz + 1;
-			}
-			ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = bw_params->clk_table.entries[i].fclk_mhz;
-
-		} else {
-			/* unconstrained for memory retraining */
-			ranges->reader_wm_sets[num_valid_sets].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-			ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+	int i;
 
-			/* Modify previous watermark range to cover up to max */
-			ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-		}
-		num_valid_sets++;
+	for (i = 0; i < PP_SMU_NUM_DCFCLK_DPM_LEVELS; i++) {
+		if (clock_table->DcfClocks[i].Vol == voltage)
+			return clock_table->DcfClocks[i].Freq;
 	}
 
-	ASSERT(num_valid_sets != 0); /* Must have at least one set of valid watermarks */
-	ranges->num_reader_wm_sets = num_valid_sets;
-
-	/* modify the min and max to make sure we cover the whole range*/
-	ranges->reader_wm_sets[0].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-	ranges->reader_wm_sets[0].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-	ranges->reader_wm_sets[ranges->num_reader_wm_sets - 1].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-	ranges->reader_wm_sets[ranges->num_reader_wm_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-
-	/* This is for writeback only, does not matter currently as no writeback support*/
-	ranges->num_writer_wm_sets = 1;
-	ranges->writer_wm_sets[0].wm_inst = WM_A;
-	ranges->writer_wm_sets[0].min_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-	ranges->writer_wm_sets[0].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-	ranges->writer_wm_sets[0].min_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MIN;
-	ranges->writer_wm_sets[0].max_drain_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
-
+	ASSERT(0);
+	return 0;
 }
 
-void clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params, struct dpm_clocks *clock_table, struct hw_asic_id *asic_id)
+static void rn_clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params, struct dpm_clocks *clock_table, struct hw_asic_id *asic_id)
 {
-	int i;
+	int i, j = 0;
+
+	j = -1;
 
 	ASSERT(PP_SMU_NUM_FCLK_DPM_LEVELS <= MAX_NUM_DPM_LVL);
 
-	for (i = 0; i < PP_SMU_NUM_FCLK_DPM_LEVELS; i++) {
-		if (clock_table->FClocks[i].Freq == 0)
+	/* Find lowest DPM, FCLK is filled in reverse order*/
+
+	for (i = PP_SMU_NUM_FCLK_DPM_LEVELS - 1; i >= 0; i--) {
+		if (clock_table->FClocks[i].Freq != 0) {
+			j = i;
 			break;
+		}
+	}
+
+	if (j == -1) {
+		/* clock table is all 0s, just use our own hardcode */
+		ASSERT(0);
+		return;
+	}
+
+	bw_params->clk_table.num_entries = j + 1;
 
-		bw_params->clk_table.entries[i].dcfclk_mhz = clock_table->DcfClocks[i].Freq;
-		bw_params->clk_table.entries[i].fclk_mhz = clock_table->FClocks[i].Freq;
-		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemClocks[i].Freq;
-		bw_params->clk_table.entries[i].socclk_mhz = clock_table->SocClocks[i].Freq;
-		bw_params->clk_table.entries[i].voltage = clock_table->FClocks[i].Vol;
+	for (i = 0; i < bw_params->clk_table.num_entries; i++, j--) {
+		bw_params->clk_table.entries[i].fclk_mhz = clock_table->FClocks[j].Freq;
+		bw_params->clk_table.entries[i].memclk_mhz = clock_table->MemClocks[j].Freq;
+		bw_params->clk_table.entries[i].voltage = clock_table->FClocks[j].Vol;
+		bw_params->clk_table.entries[i].dcfclk_mhz = find_dcfclk_for_voltage(clock_table, clock_table->FClocks[j].Vol);
 	}
-	bw_params->clk_table.num_entries = i;
 
 	bw_params->vram_type = asic_id->vram_type;
 	bw_params->num_channels = asic_id->vram_width / DDR4_DRAM_WIDTH;
@@ -486,7 +599,7 @@ void clk_mgr_helper_populate_bw_params(struct clk_bw_params *bw_params, struct d
 	for (i = 0; i < WM_SET_COUNT; i++) {
 		bw_params->wm_table.entries[i].wm_inst = i;
 
-		if (clock_table->FClocks[i].Freq == 0) {
+		if (i >= bw_params->clk_table.num_entries) {
 			bw_params->wm_table.entries[i].valid = false;
 			continue;
 		}
@@ -534,57 +647,42 @@ void rn_clk_mgr_construct(
 
 	if (IS_FPGA_MAXIMUS_DC(ctx->dce_environment)) {
 		dcn21_funcs.update_clocks = dcn2_update_clocks_fpga;
-		clk_mgr->dentist_vco_freq_khz = 3600000;
+		clk_mgr->base.dentist_vco_freq_khz = 3600000;
 		clk_mgr->base.dprefclk_khz = 600000;
 	} else {
 		struct clk_log_info log_info = {0};
 
 		/* TODO: Check we get what we expect during bringup */
-		clk_mgr->dentist_vco_freq_khz = get_vco_frequency_from_reg(clk_mgr);
+		clk_mgr->base.dentist_vco_freq_khz = get_vco_frequency_from_reg(clk_mgr);
 
 		/* in case we don't get a value from the register, use default */
-		if (clk_mgr->dentist_vco_freq_khz == 0)
-			clk_mgr->dentist_vco_freq_khz = 3600000;
+		if (clk_mgr->base.dentist_vco_freq_khz == 0)
+			clk_mgr->base.dentist_vco_freq_khz = 3600000;
 
 		rn_dump_clk_registers(&s, &clk_mgr->base, &log_info);
-		clk_mgr->base.dprefclk_khz = s.dprefclk;
-
-		if (clk_mgr->base.dprefclk_khz != 600000) {
-			clk_mgr->base.dprefclk_khz = 600000;
-			ASSERT(1); //TODO: Renoir follow up.
-		}
+		/* Convert dprefclk units from MHz to KHz */
+		/* Value already divided by 10, some resolution lost */
+		clk_mgr->base.dprefclk_khz = s.dprefclk * 1000;
 
 		/* in case we don't get a value from the register, use default */
-		if (clk_mgr->base.dprefclk_khz == 0)
+		if (clk_mgr->base.dprefclk_khz == 0) {
+			ASSERT(clk_mgr->base.dprefclk_khz == 600000);
 			clk_mgr->base.dprefclk_khz = 600000;
+		}
 	}
 
 	dce_clock_read_ss_info(clk_mgr);
 
 	clk_mgr->base.bw_params = &rn_bw_params;
 
-	if (pp_smu) {
+	if (pp_smu && pp_smu->rn_funcs.get_dpm_clock_table) {
 		pp_smu->rn_funcs.get_dpm_clock_table(&pp_smu->rn_funcs.pp_smu, &clock_table);
-		clk_mgr_helper_populate_bw_params(clk_mgr->base.bw_params, &clock_table, &ctx->asic_id);
+		rn_clk_mgr_helper_populate_bw_params(clk_mgr->base.bw_params, &clock_table, &ctx->asic_id);
 	}
 
-	/*
-	 * Notify SMU which set of WM should be selected for different ranges of fclk
-	 * On Renoir there is a maximumum of 4 DF pstates supported, could be less
-	 * depending on DDR speed and fused maximum fclk.
-	 */
-	if (!debug->disable_pplib_wm_range) {
-		struct pp_smu_wm_range_sets ranges = {0};
-
-		build_watermark_ranges(clk_mgr->base.bw_params, &ranges);
-
-		/* Notify PP Lib/SMU which Watermarks to use for which clock ranges */
-		if (pp_smu && pp_smu->rn_funcs.set_wm_ranges)
-			pp_smu->rn_funcs.set_wm_ranges(&pp_smu->rn_funcs.pp_smu, &ranges);
+	if (!IS_FPGA_MAXIMUS_DC(ctx->dce_environment) && clk_mgr->smu_ver >= 0x00371500) {
+		/* enable powerfeatures when displaycount goes to 0 */
+		rn_vbios_smu_enable_48mhz_tmdp_refclk_pwrdwn(clk_mgr, !debug->disable_48mhz_pwrdwn);
 	}
-
-	/* enable powerfeatures when displaycount goes to 0 */
-	if (!debug->disable_48mhz_pwrdwn)
-		rn_vbios_smu_enable_48mhz_tmdp_refclk_pwrdwn(clk_mgr);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
index aadec06fde10..e4322fa5475b 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.h
@@ -26,11 +26,13 @@
 #ifndef __RN_CLK_MGR_H__
 #define __RN_CLK_MGR_H__
 
+#include "clk_mgr.h"
+#include "dm_pp_smu.h"
+
 struct rn_clk_registers {
 	uint32_t CLK1_CLK0_CURRENT_CNT; /* DPREFCLK */
 };
 
-
 void rn_clk_mgr_construct(struct dc_context *ctx,
 		struct clk_mgr_internal *clk_mgr,
 		struct pp_smu_funcs *pp_smu,
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
index 50984c1811bb..cb7c0e8b7e1b 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.c
@@ -33,7 +33,7 @@
 #include "mp/mp_12_0_0_sh_mask.h"
 
 #define REG(reg_name) \
-	(MP1_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
+	(MP0_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
 
 #define FN(reg_name, field) \
 	FD(reg_name##__##field)
@@ -84,16 +84,12 @@ int rn_vbios_smu_set_dispclk(struct clk_mgr_internal *clk_mgr, int requested_dis
 	int actual_dispclk_set_mhz = -1;
 	struct dc *core_dc = clk_mgr->base.ctx->dc;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
-	uint32_t clk = requested_dispclk_khz / 1000;
-
-	if (clk <= 100)
-		clk = 101;
 
 	/*  Unit of SMU msg parameter is Mhz */
 	actual_dispclk_set_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDispclkFreq,
-			clk);
+			requested_dispclk_khz / 1000);
 
 	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment)) {
 		if (dmcu && dmcu->funcs->is_dmcu_initialized(dmcu)) {
@@ -124,7 +120,7 @@ int rn_vbios_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int reque
 {
 	int actual_dcfclk_set_mhz = -1;
 
-	if (clk_mgr->smu_ver < 0xFFFFFFFF)
+	if (clk_mgr->smu_ver < 0x370c00)
 		return actual_dcfclk_set_mhz;
 
 	actual_dcfclk_set_mhz = rn_vbios_smu_send_msg_with_param(
@@ -139,7 +135,7 @@ int rn_vbios_smu_set_min_deep_sleep_dcfclk(struct clk_mgr_internal *clk_mgr, int
 {
 	int actual_min_ds_dcfclk_mhz = -1;
 
-	if (clk_mgr->smu_ver < 0xFFFFFFFF)
+	if (clk_mgr->smu_ver < 0x370c00)
 		return actual_min_ds_dcfclk_mhz;
 
 	actual_min_ds_dcfclk_mhz = rn_vbios_smu_send_msg_with_param(
@@ -162,33 +158,35 @@ int rn_vbios_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_
 {
 	int actual_dppclk_set_mhz = -1;
 
-	uint32_t clk = requested_dpp_khz / 1000;
-
-	if (clk <= 100)
-		clk = 101;
-
 	actual_dppclk_set_mhz = rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_SetDppclkFreq,
-			clk);
+			requested_dpp_khz / 1000);
 
 	return actual_dppclk_set_mhz * 1000;
 }
 
-void rn_vbios_smu_set_display_count(struct clk_mgr_internal *clk_mgr, int display_count)
+void rn_vbios_smu_set_dcn_low_power_state(struct clk_mgr_internal *clk_mgr, enum dcn_pwr_state state)
 {
+	int disp_count;
+
+	if (state == DCN_PWR_STATE_LOW_POWER)
+		disp_count = 0;
+	else
+		disp_count = 1;
+
 	rn_vbios_smu_send_msg_with_param(
-			clk_mgr,
-			VBIOSSMC_MSG_SetDisplayCount,
-			display_count);
+		clk_mgr,
+		VBIOSSMC_MSG_SetDisplayCount,
+		disp_count);
 }
 
-void rn_vbios_smu_enable_48mhz_tmdp_refclk_pwrdwn(struct clk_mgr_internal *clk_mgr)
+void rn_vbios_smu_enable_48mhz_tmdp_refclk_pwrdwn(struct clk_mgr_internal *clk_mgr, bool enable)
 {
 	rn_vbios_smu_send_msg_with_param(
 			clk_mgr,
 			VBIOSSMC_MSG_EnableTmdp48MHzRefclkPwrDown,
-			0);
+			enable);
 }
 
 void rn_vbios_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr)
diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.h b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.h
index da3a49487c6d..ccc01879c9d4 100644
--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr_vbios_smu.h
@@ -33,8 +33,8 @@ int rn_vbios_smu_set_hard_min_dcfclk(struct clk_mgr_internal *clk_mgr, int reque
 int rn_vbios_smu_set_min_deep_sleep_dcfclk(struct clk_mgr_internal *clk_mgr, int requested_min_ds_dcfclk_khz);
 void rn_vbios_smu_set_phyclk(struct clk_mgr_internal *clk_mgr, int requested_phyclk_khz);
 int rn_vbios_smu_set_dppclk(struct clk_mgr_internal *clk_mgr, int requested_dpp_khz);
-void rn_vbios_smu_set_display_count(struct clk_mgr_internal *clk_mgr, int display_count);
-void rn_vbios_smu_enable_48mhz_tmdp_refclk_pwrdwn(struct clk_mgr_internal *clk_mgr);
+void rn_vbios_smu_set_dcn_low_power_state(struct clk_mgr_internal *clk_mgr, int display_count);
+void rn_vbios_smu_enable_48mhz_tmdp_refclk_pwrdwn(struct clk_mgr_internal *clk_mgr, bool enable);
 void rn_vbios_smu_enable_pme_wa(struct clk_mgr_internal *clk_mgr);
 
 #endif /* DAL_DC_DCN10_RV1_CLK_MGR_VBIOS_SMU_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 5d1adeda4d90..32f31bf91915 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -194,7 +194,7 @@ static bool create_links(
 				}
 			}
 
-			if (!should_destory_link) {
+			if (dc->config.force_enum_edp || !should_destory_link) {
 				dc->links[dc->link_count] = link;
 				link->dc = dc;
 				++dc->link_count;
@@ -411,6 +411,27 @@ bool dc_stream_get_crc(struct dc *dc, struct dc_stream_state *stream,
 	return false;
 }
 
+void dc_stream_set_dyn_expansion(struct dc *dc, struct dc_stream_state *stream,
+		enum dc_dynamic_expansion option)
+{
+	/* OPP FMT dyn expansion updates*/
+	int i = 0;
+	struct pipe_ctx *pipe_ctx;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		if (dc->current_state->res_ctx.pipe_ctx[i].stream
+				== stream) {
+			pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+			pipe_ctx->stream_res.opp->dyn_expansion = option;
+			pipe_ctx->stream_res.opp->funcs->opp_set_dyn_expansion(
+					pipe_ctx->stream_res.opp,
+					COLOR_SPACE_YCBCR601,
+					stream->timing.display_color_depth,
+					stream->signal);
+		}
+	}
+}
+
 void dc_stream_set_dither_option(struct dc_stream_state *stream,
 		enum dc_dither_option option)
 {
@@ -580,6 +601,10 @@ static bool construct(struct dc *dc,
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	// Allocate memory for the vm_helper
 	dc->vm_helper = kzalloc(sizeof(struct vm_helper), GFP_KERNEL);
+	if (!dc->vm_helper) {
+		dm_error("%s: failed to create dc->vm_helper\n", __func__);
+		goto fail;
+	}
 
 #endif
 	memcpy(&dc->bb_overrides, &init_params->bb_overrides, sizeof(dc->bb_overrides));
@@ -761,8 +786,13 @@ static void disable_dangling_plane(struct dc *dc, struct dc_state *context)
 #if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 			disable_all_writeback_pipes_for_stream(dc, old_stream, dangling_context);
 #endif
-			dc->hwss.apply_ctx_for_surface(dc, old_stream, 0, dangling_context);
+			if (dc->hwss.apply_ctx_for_surface)
+				dc->hwss.apply_ctx_for_surface(dc, old_stream, 0, dangling_context);
 		}
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+		if (dc->hwss.program_front_end_for_ctx)
+			dc->hwss.program_front_end_for_ctx(dc, dangling_context);
+#endif
 	}
 
 	current_ctx = dc->current_state;
@@ -785,9 +815,6 @@ struct dc *dc_create(const struct dc_init_data *init_params)
 	if (false == construct(dc, init_params))
 		goto construct_fail;
 
-	/*TODO: separate HW and SW initialization*/
-	dc->hwss.init_hw(dc);
-
 	full_pipe_count = dc->res_pool->pipe_count;
 	if (dc->res_pool->underlay_pipe_index != NO_UNDERLAY_PIPE)
 		full_pipe_count--;
@@ -820,9 +847,24 @@ alloc_fail:
 	return NULL;
 }
 
+void dc_hardware_init(struct dc *dc)
+{
+	dc->hwss.init_hw(dc);
+}
+
 void dc_init_callbacks(struct dc *dc,
 		const struct dc_callback_init *init_params)
 {
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	dc->ctx->cp_psp = init_params->cp_psp;
+#endif
+}
+
+void dc_deinit_callbacks(struct dc *dc)
+{
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	memset(&dc->ctx->cp_psp, 0, sizeof(dc->ctx->cp_psp));
+#endif
 }
 
 void dc_destroy(struct dc **dc)
@@ -901,15 +943,11 @@ static void program_timing_sync(
 
 		/* set first pipe with plane as master */
 		for (j = 0; j < group_size; j++) {
-			struct pipe_ctx *temp;
-
 			if (pipe_set[j]->plane_state) {
 				if (j == 0)
 					break;
 
-				temp = pipe_set[0];
-				pipe_set[0] = pipe_set[j];
-				pipe_set[j] = temp;
+				swap(pipe_set[0], pipe_set[j]);
 				break;
 			}
 		}
@@ -966,40 +1004,87 @@ bool dc_validate_seamless_boot_timing(const struct dc *dc,
 				struct dc_crtc_timing *crtc_timing)
 {
 	struct timing_generator *tg;
+	struct stream_encoder *se = NULL;
+
+	struct dc_crtc_timing hw_crtc_timing = {0};
+
 	struct dc_link *link = sink->link;
-	unsigned int enc_inst, tg_inst;
+	unsigned int i, enc_inst, tg_inst = 0;
+
+	// Seamless port only support single DP and EDP so far
+	if (sink->sink_signal != SIGNAL_TYPE_DISPLAY_PORT &&
+		sink->sink_signal != SIGNAL_TYPE_EDP)
+		return false;
 
 	/* Check for enabled DIG to identify enabled display */
 	if (!link->link_enc->funcs->is_dig_enabled(link->link_enc))
 		return false;
 
-	/* Check for which front end is used by this encoder.
-	 * Note the inst is 1 indexed, where 0 is undefined.
-	 * Note that DIG_FE can source from different OTG but our
-	 * current implementation always map 1-to-1, so this code makes
-	 * the same assumption and doesn't check OTG source.
-	 */
 	enc_inst = link->link_enc->funcs->get_dig_frontend(link->link_enc);
 
-	/* Instance should be within the range of the pool */
-	if (enc_inst >= dc->res_pool->pipe_count)
+	if (enc_inst == ENGINE_ID_UNKNOWN)
 		return false;
 
-	if (enc_inst >= dc->res_pool->stream_enc_count)
-		return false;
+	for (i = 0; i < dc->res_pool->stream_enc_count; i++) {
+		if (dc->res_pool->stream_enc[i]->id == enc_inst) {
+
+			se = dc->res_pool->stream_enc[i];
+
+			tg_inst = dc->res_pool->stream_enc[i]->funcs->dig_source_otg(
+				dc->res_pool->stream_enc[i]);
+			break;
+		}
+	}
 
-	tg_inst = dc->res_pool->stream_enc[enc_inst]->funcs->dig_source_otg(
-		dc->res_pool->stream_enc[enc_inst]);
+	// tg_inst not found
+	if (i == dc->res_pool->stream_enc_count)
+		return false;
 
 	if (tg_inst >= dc->res_pool->timing_generator_count)
 		return false;
 
 	tg = dc->res_pool->timing_generators[tg_inst];
 
-	if (!tg->funcs->is_matching_timing)
+	if (!tg->funcs->get_hw_timing)
+		return false;
+
+	if (!tg->funcs->get_hw_timing(tg, &hw_crtc_timing))
+		return false;
+
+	if (crtc_timing->h_total != hw_crtc_timing.h_total)
+		return false;
+
+	if (crtc_timing->h_border_left != hw_crtc_timing.h_border_left)
+		return false;
+
+	if (crtc_timing->h_addressable != hw_crtc_timing.h_addressable)
+		return false;
+
+	if (crtc_timing->h_border_right != hw_crtc_timing.h_border_right)
+		return false;
+
+	if (crtc_timing->h_front_porch != hw_crtc_timing.h_front_porch)
+		return false;
+
+	if (crtc_timing->h_sync_width != hw_crtc_timing.h_sync_width)
+		return false;
+
+	if (crtc_timing->v_total != hw_crtc_timing.v_total)
+		return false;
+
+	if (crtc_timing->v_border_top != hw_crtc_timing.v_border_top)
 		return false;
 
-	if (!tg->funcs->is_matching_timing(tg, crtc_timing))
+	if (crtc_timing->v_addressable != hw_crtc_timing.v_addressable)
+		return false;
+
+	if (crtc_timing->v_border_bottom != hw_crtc_timing.v_border_bottom)
+		return false;
+
+	if (crtc_timing->v_front_porch != hw_crtc_timing.v_front_porch)
+		return false;
+
+	if (crtc_timing->v_sync_width != hw_crtc_timing.v_sync_width)
 		return false;
 
 	if (dc_is_dp_signal(link->connector_signal)) {
@@ -1012,6 +1097,20 @@ bool dc_validate_seamless_boot_timing(const struct dc *dc,
 		if (crtc_timing->pix_clk_100hz != pix_clk_100hz)
 			return false;
 
+		if (!se->funcs->dp_get_pixel_format)
+			return false;
+
+		if (!se->funcs->dp_get_pixel_format(
+			se,
+			&hw_crtc_timing.pixel_encoding,
+			&hw_crtc_timing.display_color_depth))
+			return false;
+
+		if (hw_crtc_timing.display_color_depth != crtc_timing->display_color_depth)
+			return false;
+
+		if (hw_crtc_timing.pixel_encoding != crtc_timing->pixel_encoding)
+			return false;
 	}
 
 	return true;
@@ -1073,15 +1172,20 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	/* re-program planes for existing stream, in case we need to
 	 * free up plane resource for later use
 	 */
-	for (i = 0; i < context->stream_count; i++) {
-		if (context->streams[i]->mode_changed)
-			continue;
+	if (dc->hwss.apply_ctx_for_surface)
+		for (i = 0; i < context->stream_count; i++) {
+			if (context->streams[i]->mode_changed)
+				continue;
 
-		dc->hwss.apply_ctx_for_surface(
-			dc, context->streams[i],
-			context->stream_status[i].plane_count,
-			context); /* use new pipe config in new context */
-	}
+			dc->hwss.apply_ctx_for_surface(
+				dc, context->streams[i],
+				context->stream_status[i].plane_count,
+				context); /* use new pipe config in new context */
+		}
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+	if (dc->hwss.program_front_end_for_ctx)
+		dc->hwss.program_front_end_for_ctx(dc, context);
+#endif
 
 	/* Program hardware */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -1100,16 +1204,21 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 	}
 
 	/* Program all planes within new context*/
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+	if (dc->hwss.program_front_end_for_ctx)
+		dc->hwss.program_front_end_for_ctx(dc, context);
+#endif
 	for (i = 0; i < context->stream_count; i++) {
 		const struct dc_link *link = context->streams[i]->link;
 
 		if (!context->streams[i]->mode_changed)
 			continue;
 
-		dc->hwss.apply_ctx_for_surface(
-				dc, context->streams[i],
-				context->stream_status[i].plane_count,
-				context);
+		if (dc->hwss.apply_ctx_for_surface)
+			dc->hwss.apply_ctx_for_surface(
+					dc, context->streams[i],
+					context->stream_status[i].plane_count,
+					context);
 
 		/*
 		 * enable stereo
@@ -1136,15 +1245,9 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c
 
 	dc_enable_stereo(dc, context, dc_streams, context->stream_count);
 
-	if (!dc->optimize_seamless_boot)
-		/* pplib is notified if disp_num changed */
-		dc->hwss.optimize_bandwidth(dc, context);
-
 	for (i = 0; i < context->stream_count; i++)
 		context->streams[i]->mode_changed = false;
 
-	memset(&context->commit_hints, 0, sizeof(context->commit_hints));
-
 	dc_release_state(dc->current_state);
 
 	dc->current_state = context;
@@ -1492,20 +1595,15 @@ static enum surface_update_type det_surface_update(const struct dc *dc,
 	enum surface_update_type overall_type = UPDATE_TYPE_FAST;
 	union surface_update_flags *update_flags = &u->surface->update_flags;
 
-	update_flags->raw = 0; // Reset all flags
-
 	if (u->flip_addr)
 		update_flags->bits.addr_update = 1;
 
-	if (!is_surface_in_context(context, u->surface)) {
-		update_flags->bits.new_plane = 1;
+	if (!is_surface_in_context(context, u->surface) || u->surface->force_full_update) {
+		update_flags->raw = 0xFFFFFFFF;
 		return UPDATE_TYPE_FULL;
 	}
 
-	if (u->surface->force_full_update) {
-		update_flags->bits.full_update = 1;
-		return UPDATE_TYPE_FULL;
-	}
+	update_flags->raw = 0; // Reset all flags
 
 	type = get_plane_info_update_type(u);
 	elevate_update_type(&overall_type, type);
@@ -1563,40 +1661,43 @@ static enum surface_update_type check_update_surfaces_for_stream(
 	enum surface_update_type overall_type = UPDATE_TYPE_FAST;
 
 	if (stream_status == NULL || stream_status->plane_count != surface_count)
-		return UPDATE_TYPE_FULL;
+		overall_type = UPDATE_TYPE_FULL;
 
 	/* some stream updates require passive update */
 	if (stream_update) {
-		if ((stream_update->src.height != 0) &&
-				(stream_update->src.width != 0))
-			return UPDATE_TYPE_FULL;
+		union stream_update_flags *su_flags = &stream_update->stream->update_flags;
 
-		if ((stream_update->dst.height != 0) &&
-				(stream_update->dst.width != 0))
-			return UPDATE_TYPE_FULL;
+		if ((stream_update->src.height != 0 && stream_update->src.width != 0) ||
+				(stream_update->dst.height != 0 && stream_update->dst.width != 0))
+			su_flags->bits.scaling = 1;
 
 		if (stream_update->out_transfer_func)
-			return UPDATE_TYPE_FULL;
+			su_flags->bits.out_tf = 1;
 
 		if (stream_update->abm_level)
-			return UPDATE_TYPE_FULL;
+			su_flags->bits.abm_level = 1;
 
 		if (stream_update->dpms_off)
-			return UPDATE_TYPE_FULL;
+			su_flags->bits.dpms_off = 1;
+
+		if (stream_update->gamut_remap)
+			su_flags->bits.gamut_remap = 1;
 
 #if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 		if (stream_update->wb_update)
-			return UPDATE_TYPE_FULL;
+			su_flags->bits.wb_update = 1;
 #endif
+		if (su_flags->raw != 0)
+			overall_type = UPDATE_TYPE_FULL;
+
+		if (stream_update->output_csc_transform || stream_update->output_color_space)
+			su_flags->bits.out_csc = 1;
 	}
 
 	for (i = 0 ; i < surface_count; i++) {
 		enum surface_update_type type =
 				det_surface_update(dc, &updates[i]);
 
-		if (type == UPDATE_TYPE_FULL)
-			return type;
-
 		elevate_update_type(&overall_type, type);
 	}
 
@@ -1618,16 +1719,29 @@ enum surface_update_type dc_check_update_surfaces_for_stream(
 	int i;
 	enum surface_update_type type;
 
+	if (stream_update)
+		stream_update->stream->update_flags.raw = 0;
 	for (i = 0; i < surface_count; i++)
 		updates[i].surface->update_flags.raw = 0;
 
 	type = check_update_surfaces_for_stream(dc, updates, surface_count, stream_update, stream_status);
-	if (type == UPDATE_TYPE_FULL)
+	if (type == UPDATE_TYPE_FULL) {
+		if (stream_update)
+			stream_update->stream->update_flags.raw = 0xFFFFFFFF;
 		for (i = 0; i < surface_count; i++)
 			updates[i].surface->update_flags.raw = 0xFFFFFFFF;
+	}
 
-	if (type == UPDATE_TYPE_FAST && memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0)
-		dc->optimized_required = true;
+	if (type == UPDATE_TYPE_FAST) {
+		// If there's an available clock comparator, we use that.
+		if (dc->clk_mgr->funcs->are_clock_states_equal) {
+			if (!dc->clk_mgr->funcs->are_clock_states_equal(&dc->clk_mgr->clks, &dc->current_state->bw_ctx.bw.dcn.clk))
+				dc->optimized_required = true;
+		// Else we fallback to mem compare.
+		} else if (memcmp(&dc->current_state->bw_ctx.bw.dcn.clk, &dc->clk_mgr->clks, offsetof(struct dc_clocks, prev_p_state_change_support)) != 0) {
+			dc->optimized_required = true;
+		}
+	}
 
 	return type;
 }
@@ -1868,6 +1982,7 @@ static void commit_planes_do_stream_update(struct dc *dc,
 		struct dc_state *context)
 {
 	int j;
+	bool should_program_abm;
 
 	// Stream updates
 	for (j = 0; j < dc->res_pool->pipe_count; j++) {
@@ -1948,14 +2063,21 @@ static void commit_planes_do_stream_update(struct dc *dc,
 			}
 
 			if (stream_update->abm_level && pipe_ctx->stream_res.abm) {
-				if (pipe_ctx->stream_res.tg->funcs->is_blanked) {
-					// if otg funcs defined check if blanked before programming
-					if (!pipe_ctx->stream_res.tg->funcs->is_blanked(pipe_ctx->stream_res.tg))
+				should_program_abm = true;
+
+				// if otg funcs defined check if blanked before programming
+				if (pipe_ctx->stream_res.tg->funcs->is_blanked)
+					if (pipe_ctx->stream_res.tg->funcs->is_blanked(pipe_ctx->stream_res.tg))
+						should_program_abm = false;
+
+				if (should_program_abm) {
+					if (*stream_update->abm_level == ABM_LEVEL_IMMEDIATE_DISABLE) {
+						pipe_ctx->stream_res.abm->funcs->set_abm_immediate_disable(pipe_ctx->stream_res.abm);
+					} else {
 						pipe_ctx->stream_res.abm->funcs->set_abm_level(
 							pipe_ctx->stream_res.abm, stream->abm_level);
-				} else
-					pipe_ctx->stream_res.abm->funcs->set_abm_level(
-						pipe_ctx->stream_res.abm, stream->abm_level);
+					}
+				}
 			}
 		}
 	}
@@ -2000,7 +2122,13 @@ static void commit_planes_for_stream(struct dc *dc,
 		 * In case of turning off screen, no need to program front end a second time.
 		 * just return after program blank.
 		 */
-		dc->hwss.apply_ctx_for_surface(dc, stream, 0, context);
+		if (dc->hwss.apply_ctx_for_surface)
+			dc->hwss.apply_ctx_for_surface(dc, stream, 0, context);
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+		if (dc->hwss.program_front_end_for_ctx)
+			dc->hwss.program_front_end_for_ctx(dc, context);
+#endif
+
 		return;
 	}
 
@@ -2060,10 +2188,15 @@ static void commit_planes_for_stream(struct dc *dc,
 			stream_status =
 				stream_get_status(context, pipe_ctx->stream);
 
-			dc->hwss.apply_ctx_for_surface(
+			if (dc->hwss.apply_ctx_for_surface)
+				dc->hwss.apply_ctx_for_surface(
 					dc, pipe_ctx->stream, stream_status->plane_count, context);
 		}
 	}
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+	if (dc->hwss.program_front_end_for_ctx && update_type != UPDATE_TYPE_FAST)
+		dc->hwss.program_front_end_for_ctx(dc, context);
+#endif
 
 	// Update Type FAST, Surface updates
 	if (update_type == UPDATE_TYPE_FAST) {
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 ca20b150afcc..12ba6fdf89b7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -79,7 +79,6 @@ static void destruct(struct dc_link *link)
 	int i;
 
 	if (link->hpd_gpio != NULL) {
-		dal_gpio_close(link->hpd_gpio);
 		dal_gpio_destroy_irq(&link->hpd_gpio);
 		link->hpd_gpio = NULL;
 	}
@@ -520,7 +519,7 @@ static void link_disconnect_remap(struct dc_sink *prev_sink, struct dc_link *lin
 }
 
 
-static void read_edp_current_link_settings_on_detect(struct dc_link *link)
+static void read_current_link_settings_on_detect(struct dc_link *link)
 {
 	union lane_count_set lane_count_set = { {0} };
 	uint8_t link_bw_set;
@@ -555,17 +554,23 @@ static void read_edp_current_link_settings_on_detect(struct dc_link *link)
 			&link_bw_set, sizeof(link_bw_set));
 
 	if (link_bw_set == 0) {
-		/* If standard link rates are not being used,
-		 * Read DPCD 00115h to find the link rate set used
-		 */
-		core_link_read_dpcd(link, DP_LINK_RATE_SET,
-				&link_rate_set, sizeof(link_rate_set));
-
-		if (link_rate_set < link->dpcd_caps.edp_supported_link_rates_count) {
-			link->cur_link_settings.link_rate =
-				link->dpcd_caps.edp_supported_link_rates[link_rate_set];
-			link->cur_link_settings.link_rate_set = link_rate_set;
-			link->cur_link_settings.use_link_rate_set = true;
+		if (link->connector_signal == SIGNAL_TYPE_EDP) {
+			/* If standard link rates are not being used,
+			 * Read DPCD 00115h to find the edp link rate set used
+			 */
+			core_link_read_dpcd(link, DP_LINK_RATE_SET,
+					&link_rate_set, sizeof(link_rate_set));
+
+			// edp_supported_link_rates_count = 0 for DP
+			if (link_rate_set < link->dpcd_caps.edp_supported_link_rates_count) {
+				link->cur_link_settings.link_rate =
+						link->dpcd_caps.edp_supported_link_rates[link_rate_set];
+				link->cur_link_settings.link_rate_set = link_rate_set;
+				link->cur_link_settings.use_link_rate_set = true;
+			}
+		} else {
+			// Link Rate not found. Seamless boot may not work.
+			ASSERT(false);
 		}
 	} else {
 		link->cur_link_settings.link_rate = link_bw_set;
@@ -680,7 +685,7 @@ static bool is_same_edid(struct dc_edid *old_edid, struct dc_edid *new_edid)
 	return (memcmp(old_edid->raw_edid, new_edid->raw_edid, new_edid->length) == 0);
 }
 
-bool wait_for_alt_mode(struct dc_link *link)
+static bool wait_for_alt_mode(struct dc_link *link)
 {
 
 	/**
@@ -738,7 +743,8 @@ bool wait_for_alt_mode(struct dc_link *link)
  * This does not create remote sinks but will trigger DM
  * to start MST detection if a branch is detected.
  */
-bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
+static bool dc_link_detect_helper(struct dc_link *link,
+				  enum dc_detect_reason reason)
 {
 	struct dc_sink_init_data sink_init_data = { 0 };
 	struct display_sink_capability sink_caps = { 0 };
@@ -753,6 +759,8 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 	struct dpcd_caps prev_dpcd_caps;
 	bool same_dpcd = true;
 	enum dc_connection_type new_connection_type = dc_connection_none;
+	bool perform_dp_seamless_boot = false;
+
 	DC_LOGGER_INIT(link->ctx->logger);
 
 	if (dc_is_virtual_signal(link->connector_signal))
@@ -809,15 +817,15 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		}
 
 		case SIGNAL_TYPE_EDP: {
-			read_edp_current_link_settings_on_detect(link);
+			read_current_link_settings_on_detect(link);
 			detect_edp_sink_caps(link);
-			sink_caps.transaction_type =
-				DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
+			sink_caps.transaction_type = DDC_TRANSACTION_TYPE_I2C_OVER_AUX;
 			sink_caps.signal = SIGNAL_TYPE_EDP;
 			break;
 		}
 
 		case SIGNAL_TYPE_DISPLAY_PORT: {
+
 			/* wa HPD high coming too early*/
 			if (link->link_enc->features.flags.bits.DP_IS_USB_C == 1) {
 
@@ -865,12 +873,24 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				 * empty which leads to allocate_mst_payload() has "0"
 				 * pbn_per_slot value leading to exception on dc_fixpt_div()
 				 */
-				link->verified_link_cap = link->reported_link_cap;
+				dp_verify_mst_link_cap(link);
+
 				if (prev_sink != NULL)
 					dc_sink_release(prev_sink);
 				return false;
 			}
 
+			// For seamless boot, to skip verify link cap, we read UEFI settings and set them as verified.
+			if (reason == DETECT_REASON_BOOT &&
+					dc_ctx->dc->config.power_down_display_on_boot == false &&
+					link->link_status.link_active == true)
+				perform_dp_seamless_boot = true;
+
+			if (perform_dp_seamless_boot) {
+				read_current_link_settings_on_detect(link);
+				link->verified_link_cap = link->reported_link_cap;
+			}
+
 			break;
 		}
 
@@ -955,10 +975,11 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			 *  two link trainings
 			 */
 
-			/* deal with non-mst cases */
-			dp_verify_link_cap_with_retries(link,
-					&link->reported_link_cap,
-					LINK_TRAINING_MAX_VERIFY_RETRY);
+			// verify link cap for SST non-seamless boot
+			if (!perform_dp_seamless_boot)
+				dp_verify_link_cap_with_retries(link,
+						&link->reported_link_cap,
+						LINK_TRAINING_MAX_VERIFY_RETRY);
 		} else {
 			// If edid is the same, then discard new sink and revert back to original sink
 			if (same_edid) {
@@ -1047,6 +1068,23 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		dc_sink_release(prev_sink);
 
 	return true;
+
+}
+
+bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
+{
+	const struct dc *dc = link->dc;
+	bool ret;
+
+	/* get out of low power state */
+	clk_mgr_exit_optimized_pwr_state(dc, dc->clk_mgr);
+
+	ret = dc_link_detect_helper(link, reason);
+
+	/* Go back to power optimized state */
+	clk_mgr_optimize_pwr_state(dc, dc->clk_mgr);
+
+	return ret;
 }
 
 bool dc_link_get_hpd_state(struct dc_link *dc_link)
@@ -1492,7 +1530,7 @@ static enum dc_status enable_link_dp(
 
 	pipe_ctx->stream_res.pix_clk_params.requested_sym_clk =
 			link_settings.link_rate * LINK_RATE_REF_FREQ_IN_KHZ;
-	if (!apply_seamless_boot_optimization)
+	if (state->clk_mgr && !apply_seamless_boot_optimization)
 		state->clk_mgr->funcs->update_clocks(state->clk_mgr, state, false);
 
 	dp_enable_link_phy(
@@ -2169,8 +2207,10 @@ static void disable_link(struct dc_link *link, enum signal_type signal)
 			dp_set_fec_ready(link, false);
 		}
 #endif
-	} else
-		link->link_enc->funcs->disable_output(link->link_enc, signal);
+	} else {
+		if (signal != SIGNAL_TYPE_VIRTUAL)
+			link->link_enc->funcs->disable_output(link->link_enc, signal);
+	}
 
 	if (signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
 		/* MST disable link only when no stream use the link */
@@ -2217,7 +2257,7 @@ static bool dp_active_dongle_validate_timing(
 		break;
 	}
 
-	if (dongle_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
+	if (dpcd_caps->dongle_type != DISPLAY_DONGLE_DP_HDMI_CONVERTER ||
 		dongle_caps->extendedCapValid == false)
 		return true;
 
@@ -2381,17 +2421,206 @@ bool dc_link_set_abm_disable(const struct dc_link *link)
 	return true;
 }
 
-bool dc_link_set_psr_enable(const struct dc_link *link, bool enable, bool wait)
+bool dc_link_set_psr_allow_active(struct dc_link *link, bool allow_active, bool wait)
 {
 	struct dc  *core_dc = link->ctx->dc;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
 
-	if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_enabled)
-		dmcu->funcs->set_psr_enable(dmcu, enable, wait);
+
+
+	if ((dmcu != NULL && dmcu->funcs->is_dmcu_initialized(dmcu)) && link->psr_feature_enabled)
+		dmcu->funcs->set_psr_enable(dmcu, allow_active, wait);
+
+	link->psr_allow_active = allow_active;
 
 	return true;
 }
 
+bool dc_link_get_psr_state(const struct dc_link *link, uint32_t *psr_state)
+{
+	struct dc  *core_dc = link->ctx->dc;
+	struct dmcu *dmcu = core_dc->res_pool->dmcu;
+
+	if (dmcu != NULL && link->psr_feature_enabled)
+		dmcu->funcs->get_psr_state(dmcu, psr_state);
+
+	return true;
+}
+
+static inline enum physical_phy_id
+transmitter_to_phy_id(enum transmitter transmitter_value)
+{
+	switch (transmitter_value) {
+	case TRANSMITTER_UNIPHY_A:
+		return PHYLD_0;
+	case TRANSMITTER_UNIPHY_B:
+		return PHYLD_1;
+	case TRANSMITTER_UNIPHY_C:
+		return PHYLD_2;
+	case TRANSMITTER_UNIPHY_D:
+		return PHYLD_3;
+	case TRANSMITTER_UNIPHY_E:
+		return PHYLD_4;
+	case TRANSMITTER_UNIPHY_F:
+		return PHYLD_5;
+	case TRANSMITTER_NUTMEG_CRT:
+		return PHYLD_6;
+	case TRANSMITTER_TRAVIS_CRT:
+		return PHYLD_7;
+	case TRANSMITTER_TRAVIS_LCD:
+		return PHYLD_8;
+	case TRANSMITTER_UNIPHY_G:
+		return PHYLD_9;
+	case TRANSMITTER_COUNT:
+		return PHYLD_COUNT;
+	case TRANSMITTER_UNKNOWN:
+		return PHYLD_UNKNOWN;
+	default:
+		WARN_ONCE(1, "Unknown transmitter value %d\n",
+			  transmitter_value);
+		return PHYLD_UNKNOWN;
+	}
+}
+
+bool dc_link_setup_psr(struct dc_link *link,
+		const struct dc_stream_state *stream, struct psr_config *psr_config,
+		struct psr_context *psr_context)
+{
+	struct dc *core_dc;
+	struct dmcu *dmcu;
+	int i;
+	/* updateSinkPsrDpcdConfig*/
+	union dpcd_psr_configuration psr_configuration;
+
+	psr_context->controllerId = CONTROLLER_ID_UNDEFINED;
+
+	if (!link)
+		return false;
+
+	core_dc = link->ctx->dc;
+	dmcu = core_dc->res_pool->dmcu;
+
+	if (!dmcu)
+		return false;
+
+
+	memset(&psr_configuration, 0, sizeof(psr_configuration));
+
+	psr_configuration.bits.ENABLE                    = 1;
+	psr_configuration.bits.CRC_VERIFICATION          = 1;
+	psr_configuration.bits.FRAME_CAPTURE_INDICATION  =
+			psr_config->psr_frame_capture_indication_req;
+
+	/* Check for PSR v2*/
+	if (psr_config->psr_version == 0x2) {
+		/* For PSR v2 selective update.
+		 * Indicates whether sink should start capturing
+		 * immediately following active scan line,
+		 * or starting with the 2nd active scan line.
+		 */
+		psr_configuration.bits.LINE_CAPTURE_INDICATION = 0;
+		/*For PSR v2, determines whether Sink should generate
+		 * IRQ_HPD when CRC mismatch is detected.
+		 */
+		psr_configuration.bits.IRQ_HPD_WITH_CRC_ERROR    = 1;
+	}
+
+	dm_helpers_dp_write_dpcd(
+		link->ctx,
+		link,
+		368,
+		&psr_configuration.raw,
+		sizeof(psr_configuration.raw));
+
+	psr_context->channel = link->ddc->ddc_pin->hw_info.ddc_channel;
+	psr_context->transmitterId = link->link_enc->transmitter;
+	psr_context->engineId = link->link_enc->preferred_engine;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		if (core_dc->current_state->res_ctx.pipe_ctx[i].stream
+				== stream) {
+			/* dmcu -1 for all controller id values,
+			 * therefore +1 here
+			 */
+			psr_context->controllerId =
+				core_dc->current_state->res_ctx.
+				pipe_ctx[i].stream_res.tg->inst + 1;
+			break;
+		}
+	}
+
+	/* Hardcoded for now.  Can be Pcie or Uniphy (or Unknown)*/
+	psr_context->phyType = PHY_TYPE_UNIPHY;
+	/*PhyId is associated with the transmitter id*/
+	psr_context->smuPhyId =
+		transmitter_to_phy_id(link->link_enc->transmitter);
+
+	psr_context->crtcTimingVerticalTotal = stream->timing.v_total;
+	psr_context->vsyncRateHz = div64_u64(div64_u64((stream->
+					timing.pix_clk_100hz * 100),
+					stream->timing.v_total),
+					stream->timing.h_total);
+
+	psr_context->psrSupportedDisplayConfig = true;
+	psr_context->psrExitLinkTrainingRequired =
+		psr_config->psr_exit_link_training_required;
+	psr_context->sdpTransmitLineNumDeadline =
+		psr_config->psr_sdp_transmit_line_num_deadline;
+	psr_context->psrFrameCaptureIndicationReq =
+		psr_config->psr_frame_capture_indication_req;
+
+	psr_context->skipPsrWaitForPllLock = 0; /* only = 1 in KV */
+
+	psr_context->numberOfControllers =
+			link->dc->res_pool->timing_generator_count;
+
+	psr_context->rfb_update_auto_en = true;
+
+	/* 2 frames before enter PSR. */
+	psr_context->timehyst_frames = 2;
+	/* half a frame
+	 * (units in 100 lines, i.e. a value of 1 represents 100 lines)
+	 */
+	psr_context->hyst_lines = stream->timing.v_total / 2 / 100;
+	psr_context->aux_repeats = 10;
+
+	psr_context->psr_level.u32all = 0;
+
+#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+	/*skip power down the single pipe since it blocks the cstate*/
+	if (ASICREV_IS_RAVEN(link->ctx->asic_id.hw_internal_rev))
+		psr_context->psr_level.bits.SKIP_CRTC_DISABLE = true;
+#endif
+
+	/* SMU will perform additional powerdown sequence.
+	 * For unsupported ASICs, set psr_level flag to skip PSR
+	 *  static screen notification to SMU.
+	 *  (Always set for DAL2, did not check ASIC)
+	 */
+	psr_context->allow_smu_optimizations = psr_config->allow_smu_optimizations;
+
+	/* Complete PSR entry before aborting to prevent intermittent
+	 * freezes on certain eDPs
+	 */
+	psr_context->psr_level.bits.DISABLE_PSR_ENTRY_ABORT = 1;
+
+	/* Controls additional delay after remote frame capture before
+	 * continuing power down, default = 0
+	 */
+	psr_context->frame_delay = 0;
+
+	link->psr_feature_enabled = dmcu->funcs->setup_psr(dmcu, link, psr_context);
+
+	/* psr_enabled == 0 indicates setup_psr did not succeed, but this
+	 * should not happen since firmware should be running at this point
+	 */
+	if (link->psr_feature_enabled == 0)
+		ASSERT(0);
+
+	return true;
+
+}
+
 const struct dc_link_status *dc_link_get_status(const struct dc_link *link)
 {
 	return &link->link_status;
@@ -2510,7 +2739,7 @@ static void update_mst_stream_alloc_table(
 /* convert link_mst_stream_alloc_table to dm dp_mst_stream_alloc_table
  * because stream_encoder is not exposed to dm
  */
-static enum dc_status allocate_mst_payload(struct pipe_ctx *pipe_ctx)
+enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->link;
@@ -2521,6 +2750,7 @@ static enum dc_status allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 	struct fixed31_32 pbn;
 	struct fixed31_32 pbn_per_slot;
 	uint8_t i;
+	enum act_return_status ret;
 	DC_LOGGER_INIT(link->ctx->logger);
 
 	/* enable_link_dp_mst already check link->enabled_stream_count
@@ -2568,14 +2798,16 @@ static enum dc_status allocate_mst_payload(struct pipe_ctx *pipe_ctx)
 		&link->mst_stream_alloc_table);
 
 	/* send down message */
-	dm_helpers_dp_mst_poll_for_allocation_change_trigger(
+	ret = dm_helpers_dp_mst_poll_for_allocation_change_trigger(
 			stream->ctx,
 			stream);
 
-	dm_helpers_dp_mst_send_payload_allocation(
-			stream->ctx,
-			stream,
-			true);
+	if (ret != ACT_LINK_LOST) {
+		dm_helpers_dp_mst_send_payload_allocation(
+				stream->ctx,
+				stream,
+				true);
+	}
 
 	/* slot X.Y for only current stream */
 	pbn_per_slot = get_pbn_per_slot(stream);
@@ -2667,6 +2899,24 @@ static enum dc_status deallocate_mst_payload(struct pipe_ctx *pipe_ctx)
 
 	return DC_OK;
 }
+#if defined(CONFIG_DRM_AMD_DC_HDCP)
+static void update_psp_stream_config(struct pipe_ctx *pipe_ctx, bool dpms_off)
+{
+	struct cp_psp *cp_psp = &pipe_ctx->stream->ctx->cp_psp;
+	if (cp_psp && cp_psp->funcs.update_stream_config) {
+		struct cp_psp_stream_config config;
+
+		memset(&config, 0, sizeof(config));
+
+		config.otg_inst = (uint8_t) pipe_ctx->stream_res.tg->inst;
+		config.stream_enc_inst = (uint8_t) pipe_ctx->stream_res.stream_enc->id;
+		config.link_enc_inst = pipe_ctx->stream->link->link_enc_hw_inst;
+		config.dpms_off = dpms_off;
+		config.dm_stream_ctx = pipe_ctx->stream->dm_stream_context;
+		cp_psp->funcs.update_stream_config(cp_psp->handle, &config);
+	}
+}
+#endif
 
 void core_link_enable_stream(
 		struct dc_state *state,
@@ -2677,6 +2927,10 @@ void core_link_enable_stream(
 	enum dc_status status;
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
+	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment) &&
+			dc_is_virtual_signal(pipe_ctx->stream->signal))
+		return;
+
 	if (!dc_is_virtual_signal(pipe_ctx->stream->signal)) {
 		stream->link->link_enc->funcs->setup(
 			stream->link->link_enc,
@@ -2727,6 +2981,9 @@ void core_link_enable_stream(
 		/* Do not touch link on seamless boot optimization. */
 		if (pipe_ctx->stream->apply_seamless_boot_optimization) {
 			pipe_ctx->stream->dpms_off = false;
+#if defined(CONFIG_DRM_AMD_DC_HDCP)
+			update_psp_stream_config(pipe_ctx, false);
+#endif
 			return;
 		}
 
@@ -2734,6 +2991,9 @@ void core_link_enable_stream(
 		if (pipe_ctx->stream->signal == SIGNAL_TYPE_EDP &&
 					apply_edp_fast_boot_optimization) {
 			pipe_ctx->stream->dpms_off = false;
+#if defined(CONFIG_DRM_AMD_DC_HDCP)
+			update_psp_stream_config(pipe_ctx, false);
+#endif
 			return;
 		}
 
@@ -2786,13 +3046,16 @@ void core_link_enable_stream(
 #endif
 
 		if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
-			allocate_mst_payload(pipe_ctx);
+			dc_link_allocate_mst_payload(pipe_ctx);
 
 		core_dc->hwss.unblank_stream(pipe_ctx,
 			&pipe_ctx->stream->link->cur_link_settings);
 
 		if (dc_is_dp_signal(pipe_ctx->stream->signal))
 			enable_stream_features(pipe_ctx);
+#if defined(CONFIG_DRM_AMD_DC_HDCP)
+		update_psp_stream_config(pipe_ctx, false);
+#endif
 	}
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	else { // if (IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment))
@@ -2810,6 +3073,14 @@ void core_link_disable_stream(struct pipe_ctx *pipe_ctx)
 	struct dc_stream_state *stream = pipe_ctx->stream;
 	struct dc_link *link = stream->sink->link;
 
+	if (!IS_FPGA_MAXIMUS_DC(core_dc->ctx->dce_environment) &&
+			dc_is_virtual_signal(pipe_ctx->stream->signal))
+		return;
+
+#if defined(CONFIG_DRM_AMD_DC_HDCP)
+	update_psp_stream_config(pipe_ctx, true);
+#endif
+
 	core_dc->hwss.blank_stream(pipe_ctx);
 
 	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)
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 505967b48e14..7f904d55c1bc 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
@@ -374,6 +374,7 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
 	enum display_dongle_type *dongle = &sink_cap->dongle_type;
 	uint8_t type2_dongle_buf[DP_ADAPTOR_TYPE2_SIZE];
 	bool is_type2_dongle = false;
+	int retry_count = 2;
 	struct dp_hdmi_dongle_signature_data *dongle_signature;
 
 	/* Assume we have no valid DP passive dongle connected */
@@ -386,13 +387,24 @@ void dal_ddc_service_i2c_query_dp_dual_mode_adaptor(
 		DP_HDMI_DONGLE_ADDRESS,
 		type2_dongle_buf,
 		sizeof(type2_dongle_buf))) {
-		*dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
-		sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
+		/* Passive HDMI dongles can sometimes fail here without retrying*/
+		while (retry_count > 0) {
+			if (i2c_read(ddc,
+				DP_HDMI_DONGLE_ADDRESS,
+				type2_dongle_buf,
+				sizeof(type2_dongle_buf)))
+				break;
+			retry_count--;
+		}
+		if (retry_count == 0) {
+			*dongle = DISPLAY_DONGLE_DP_DVI_DONGLE;
+			sink_cap->max_hdmi_pixel_clock = DP_ADAPTOR_DVI_MAX_TMDS_CLK;
 
-		CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
-				"DP-DVI passive dongle %dMhz: ",
-				DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
-		return;
+			CONN_DATA_DETECT(ddc->link, type2_dongle_buf, sizeof(type2_dongle_buf),
+					"DP-DVI passive dongle %dMhz: ",
+					DP_ADAPTOR_DVI_MAX_TMDS_CLK / 1000);
+			return;
+		}
 	}
 
 	/* Check if Type 2 dongle.*/
@@ -496,7 +508,7 @@ bool dal_ddc_service_query_ddc_data(
 	uint8_t *read_buf,
 	uint32_t read_size)
 {
-	bool ret;
+	bool ret = false;
 	uint32_t payload_size =
 		dal_ddc_service_is_in_aux_transaction_mode(ddc) ?
 			DEFAULT_AUX_MAX_DATA_SIZE : EDID_SEGMENT_SIZE;
@@ -515,34 +527,32 @@ bool dal_ddc_service_query_ddc_data(
 	/*TODO: len of payload data for i2c and aux is uint8!!!!,
 	 *  but we want to read 256 over i2c!!!!*/
 	if (dal_ddc_service_is_in_aux_transaction_mode(ddc)) {
-		struct aux_payload write_payload = {
-			.i2c_over_aux = true,
-			.write = true,
-			.mot = true,
-			.address = address,
-			.length = write_size,
-			.data = write_buf,
-			.reply = NULL,
-			.defer_delay = get_defer_delay(ddc),
-		};
-
-		struct aux_payload read_payload = {
-			.i2c_over_aux = true,
-			.write = false,
-			.mot = false,
-			.address = address,
-			.length = read_size,
-			.data = read_buf,
-			.reply = NULL,
-			.defer_delay = get_defer_delay(ddc),
-		};
-
-		ret = dc_link_aux_transfer_with_retries(ddc, &write_payload);
+		struct aux_payload payload;
+		bool read_available = true;
+
+		payload.i2c_over_aux = true;
+		payload.address = address;
+		payload.reply = NULL;
+		payload.defer_delay = get_defer_delay(ddc);
+
+		if (write_size != 0) {
+			payload.write = true;
+			payload.mot = false;
+			payload.length = write_size;
+			payload.data = write_buf;
+
+			ret = dal_ddc_submit_aux_command(ddc, &payload);
+			read_available = ret;
+		}
 
-		if (!ret)
-			return false;
+		if (read_size != 0 && read_available) {
+			payload.write = false;
+			payload.mot = false;
+			payload.length = read_size;
+			payload.data = read_buf;
 
-		ret = dc_link_aux_transfer_with_retries(ddc, &read_payload);
+			ret = dal_ddc_submit_aux_command(ddc, &payload);
+		}
 	} else {
 		struct i2c_payloads *payloads =
 			dal_ddc_i2c_payloads_create(ddc->ctx, payloads_num);
@@ -573,6 +583,41 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
+bool dal_ddc_submit_aux_command(struct ddc_service *ddc,
+		struct aux_payload *payload)
+{
+	uint8_t retrieved = 0;
+	bool ret = 0;
+
+	if (!ddc)
+		return false;
+
+	if (!payload)
+		return false;
+
+	do {
+		struct aux_payload current_payload;
+		bool is_end_of_payload = (retrieved + DEFAULT_AUX_MAX_DATA_SIZE) >
+			payload->length ? true : false;
+
+		current_payload.address = payload->address;
+		current_payload.data = &payload->data[retrieved];
+		current_payload.defer_delay = payload->defer_delay;
+		current_payload.i2c_over_aux = payload->i2c_over_aux;
+		current_payload.length = is_end_of_payload ?
+			payload->length - retrieved : DEFAULT_AUX_MAX_DATA_SIZE;
+		current_payload.mot = !is_end_of_payload;
+		current_payload.reply = payload->reply;
+		current_payload.write = payload->write;
+
+		ret = dc_link_aux_transfer_with_retries(ddc, &current_payload);
+
+		retrieved += current_payload.length;
+	} while (retrieved < payload->length && ret == true);
+
+	return ret;
+}
+
 /* dc_link_aux_transfer_raw() - Attempt to transfer
  * the given aux payload.  This function does not perform
  * retries or handle error states.  The reply is returned
@@ -601,6 +646,20 @@ bool dc_link_aux_transfer_with_retries(struct ddc_service *ddc,
 	return dce_aux_transfer_with_retries(ddc, payload);
 }
 
+
+enum dc_status dc_link_aux_configure_timeout(struct ddc_service *ddc,
+		uint32_t timeout)
+{
+	enum dc_status status = DC_OK;
+	struct ddc *ddc_pin = ddc->ddc_pin;
+
+	if (ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout == NULL)
+		return DC_ERROR_UNEXPECTED;
+	if (!ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en]->funcs->configure_timeout(ddc, timeout))
+		status = DC_ERROR_UNEXPECTED;
+	return status;
+}
+
 /*test only function*/
 void dal_ddc_service_set_ddc_pin(
 	struct ddc_service *ddc_service,
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 f5742719b5d9..0f59b68aa4c2 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
@@ -1409,6 +1409,9 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 	if (link->link_enc->features.flags.bits.IS_HBR3_CAPABLE)
 		max_link_cap.link_rate = LINK_RATE_HIGH3;
 
+	if (link->link_enc->funcs->get_max_link_cap)
+		link->link_enc->funcs->get_max_link_cap(link->link_enc, &max_link_cap);
+
 	/* Lower link settings based on sink's link cap */
 	if (link->reported_link_cap.lane_count < max_link_cap.lane_count)
 		max_link_cap.lane_count =
@@ -1653,11 +1656,14 @@ bool dp_verify_link_cap_with_retries(
 
 	for (i = 0; i < attempts; i++) {
 		int fail_count = 0;
-		enum dc_connection_type type;
+		enum dc_connection_type type = dc_connection_none;
 
 		memset(&link->verified_link_cap, 0,
 				sizeof(struct dc_link_settings));
-		if (!dc_link_detect_sink(link, &type)) {
+		if (!dc_link_detect_sink(link, &type) || type == dc_connection_none) {
+			link->verified_link_cap.lane_count = LANE_COUNT_ONE;
+			link->verified_link_cap.link_rate = LINK_RATE_LOW;
+			link->verified_link_cap.link_spread = LINK_SPREAD_DISABLED;
 			break;
 		} else if (dp_verify_link_cap(link,
 				&link->reported_link_cap,
@@ -1670,6 +1676,19 @@ bool dp_verify_link_cap_with_retries(
 	return success;
 }
 
+bool dp_verify_mst_link_cap(
+	struct dc_link *link)
+{
+	struct dc_link_settings max_link_cap = {0};
+
+	max_link_cap = get_max_link_cap(link);
+	link->verified_link_cap = get_common_supported_link_settings(
+		link->reported_link_cap,
+		max_link_cap);
+
+	return true;
+}
+
 static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b)
@@ -2057,11 +2076,11 @@ static bool allow_hpd_rx_irq(const struct dc_link *link)
 	return false;
 }
 
-static bool handle_hpd_irq_psr_sink(const struct dc_link *link)
+static bool handle_hpd_irq_psr_sink(struct dc_link *link)
 {
 	union dpcd_psr_configuration psr_configuration;
 
-	if (!link->psr_enabled)
+	if (!link->psr_feature_enabled)
 		return false;
 
 	dm_helpers_dp_read_dpcd(
@@ -2100,8 +2119,8 @@ static bool handle_hpd_irq_psr_sink(const struct dc_link *link)
 				sizeof(psr_error_status.raw));
 
 			/* PSR error, disable and re-enable PSR */
-			dc_link_set_psr_enable(link, false, true);
-			dc_link_set_psr_enable(link, true, true);
+			dc_link_set_psr_allow_active(link, false, true);
+			dc_link_set_psr_allow_active(link, true, true);
 
 			return true;
 		} else if (psr_sink_psr_status.bits.SINK_SELF_REFRESH_STATUS ==
@@ -2364,6 +2383,8 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 	enum dc_status result;
 
 	bool status = false;
+	struct pipe_ctx *pipe_ctx;
+	int i;
 
 	if (out_link_loss)
 		*out_link_loss = false;
@@ -2440,6 +2461,15 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 			&link->cur_link_settings,
 			true, LINK_TRAINING_ATTEMPTS);
 
+		for (i = 0; i < MAX_PIPES; i++) {
+			pipe_ctx = &link->dc->current_state->res_ctx.pipe_ctx[i];
+			if (pipe_ctx && pipe_ctx->stream && pipe_ctx->stream->link == link &&
+					pipe_ctx->stream->dpms_off == false &&
+					pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+				dc_link_allocate_mst_payload(pipe_ctx);
+			}
+		}
+
 		status = false;
 		if (out_link_loss)
 			*out_link_loss = true;
@@ -2545,6 +2575,7 @@ static void get_active_converter_info(
 	uint8_t data, struct dc_link *link)
 {
 	union dp_downstream_port_present ds_port = { .byte = data };
+	memset(&link->dpcd_caps.dongle_caps, 0, sizeof(link->dpcd_caps.dongle_caps));
 
 	/* decode converter info*/
 	if (!ds_port.fields.PORT_PRESENT) {
@@ -2691,6 +2722,7 @@ static void dp_wa_power_up_0010FA(struct dc_link *link, uint8_t *dpcd_data,
 		 * keep receiver powered all the time.*/
 		case DP_BRANCH_DEVICE_ID_0010FA:
 		case DP_BRANCH_DEVICE_ID_0080E1:
+		case DP_BRANCH_DEVICE_ID_00E04C:
 			link->wa_flags.dp_keep_receiver_powered = true;
 			break;
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
index 79438c4f1e20..a519dbc5ecb6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_hwss.c
@@ -277,7 +277,8 @@ void dp_retrain_link_dp_test(struct dc_link *link,
 		if (pipes[i].stream != NULL &&
 			!pipes[i].top_pipe && !pipes[i].prev_odm_pipe &&
 			pipes[i].stream->link != NULL &&
-			pipes[i].stream_res.stream_enc != NULL) {
+			pipes[i].stream_res.stream_enc != NULL &&
+			pipes[i].stream->link == link) {
 			udelay(100);
 
 			pipes[i].stream_res.stream_enc->funcs->dp_blank(
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 8f70295179ff..37698305a2dc 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -404,6 +404,9 @@ bool resource_are_streams_timing_synchronizable(
 	if (stream1->view_format != stream2->view_format)
 		return false;
 
+	if (stream1->ignore_msa_timing_param || stream2->ignore_msa_timing_param)
+		return false;
+
 	return true;
 }
 static bool is_dp_and_hdmi_sharable(
@@ -948,7 +951,7 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx)
 	data->inits.v_c_bot = dc_fixpt_add(data->inits.v_c, data->ratios.vert_c);
 
 }
-static bool are_rect_integer_multiples(struct rect src, struct rect dest)
+static bool are_rects_integer_multiples(struct rect src, struct rect dest)
 {
 	if (dest.width  >= src.width  && dest.width  % src.width  == 0 &&
 		dest.height >= src.height && dest.height % src.height == 0)
@@ -956,6 +959,38 @@ static bool are_rect_integer_multiples(struct rect src, struct rect dest)
 
 	return false;
 }
+
+static void calculate_integer_scaling(struct pipe_ctx *pipe_ctx)
+{
+	if (!pipe_ctx->plane_state->scaling_quality.integer_scaling)
+		return;
+
+	//for Centered Mode
+	if (pipe_ctx->stream->dst.width  == pipe_ctx->stream->src.width &&
+		pipe_ctx->stream->dst.height == pipe_ctx->stream->src.height) {
+		// calculate maximum # of replication of src onto addressable
+		unsigned int integer_multiple = min(
+				pipe_ctx->stream->timing.h_addressable / pipe_ctx->stream->src.width,
+				pipe_ctx->stream->timing.v_addressable  / pipe_ctx->stream->src.height);
+
+		//scale dst
+		pipe_ctx->stream->dst.width  = integer_multiple * pipe_ctx->stream->src.width;
+		pipe_ctx->stream->dst.height = integer_multiple * pipe_ctx->stream->src.height;
+
+		//center dst onto addressable
+		pipe_ctx->stream->dst.x = (pipe_ctx->stream->timing.h_addressable - pipe_ctx->stream->dst.width)/2;
+		pipe_ctx->stream->dst.y = (pipe_ctx->stream->timing.v_addressable - pipe_ctx->stream->dst.height)/2;
+	}
+
+	//disable taps if src & dst are integer ratio
+	if (are_rects_integer_multiples(pipe_ctx->stream->src, pipe_ctx->stream->dst)) {
+		pipe_ctx->plane_state->scaling_quality.v_taps = 1;
+		pipe_ctx->plane_state->scaling_quality.h_taps = 1;
+		pipe_ctx->plane_state->scaling_quality.v_taps_c = 1;
+		pipe_ctx->plane_state->scaling_quality.h_taps_c = 1;
+	}
+}
+
 bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 {
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
@@ -969,6 +1004,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	pipe_ctx->plane_res.scl_data.format = convert_pixel_format_to_dalsurface(
 			pipe_ctx->plane_state->format);
 
+	calculate_integer_scaling(pipe_ctx);
+
 	calculate_scaling_ratios(pipe_ctx);
 
 	calculate_viewport(pipe_ctx);
@@ -999,13 +1036,6 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 		res = pipe_ctx->plane_res.dpp->funcs->dpp_get_optimal_number_of_taps(
 				pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data, &plane_state->scaling_quality);
 
-	if (res &&
-	    plane_state->scaling_quality.integer_scaling &&
-	    are_rect_integer_multiples(pipe_ctx->plane_res.scl_data.viewport,
-				       pipe_ctx->plane_res.scl_data.recout)) {
-		pipe_ctx->plane_res.scl_data.taps.v_taps = 1;
-		pipe_ctx->plane_res.scl_data.taps.h_taps = 1;
-	}
 
 	if (!res) {
 		/* Try 24 bpp linebuffer */
@@ -1540,6 +1570,9 @@ bool dc_is_stream_unchanged(
 	if (!are_stream_backends_same(old_stream, stream))
 		return false;
 
+	if (old_stream->ignore_msa_timing_param != stream->ignore_msa_timing_param)
+		return false;
+
 	return true;
 }
 
@@ -1629,7 +1662,8 @@ static int acquire_first_free_pipe(
 static struct audio *find_first_free_audio(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
-		enum engine_id id)
+		enum engine_id id,
+		enum dce_version dc_version)
 {
 	int i, available_audio_count;
 
@@ -1848,28 +1882,28 @@ static int acquire_resource_from_hw_enabled_state(
 		struct dc_stream_state *stream)
 {
 	struct dc_link *link = stream->link;
-	unsigned int inst, tg_inst;
+	unsigned int i, inst, tg_inst = 0;
 
 	/* Check for enabled DIG to identify enabled display */
 	if (!link->link_enc->funcs->is_dig_enabled(link->link_enc))
 		return -1;
 
-	/* Check for which front end is used by this encoder.
-	 * Note the inst is 1 indexed, where 0 is undefined.
-	 * Note that DIG_FE can source from different OTG but our
-	 * current implementation always map 1-to-1, so this code makes
-	 * the same assumption and doesn't check OTG source.
-	 */
 	inst = link->link_enc->funcs->get_dig_frontend(link->link_enc);
 
-	/* Instance should be within the range of the pool */
-	if (inst >= pool->pipe_count)
-		return -1;
+	if (inst == ENGINE_ID_UNKNOWN)
+		return false;
 
-	if (inst >= pool->stream_enc_count)
-		return -1;
+	for (i = 0; i < pool->stream_enc_count; i++) {
+		if (pool->stream_enc[i]->id == inst) {
+			tg_inst = pool->stream_enc[i]->funcs->dig_source_otg(
+				pool->stream_enc[i]);
+			break;
+		}
+	}
 
-	tg_inst = pool->stream_enc[inst]->funcs->dig_source_otg(pool->stream_enc[inst]);
+	// tg_inst not found
+	if (i == pool->stream_enc_count)
+		return false;
 
 	if (tg_inst >= pool->timing_generator_count)
 		return false;
@@ -1965,7 +1999,7 @@ enum dc_status resource_map_pool_resources(
 	    dc_is_audio_capable_signal(pipe_ctx->stream->signal) &&
 	    stream->audio_info.mode_count && stream->audio_info.flags.all) {
 		pipe_ctx->stream_res.audio = find_first_free_audio(
-		&context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id);
+		&context->res_ctx, pool, pipe_ctx->stream_res.stream_enc->id, dc_ctx->dce_version);
 
 		/*
 		 * Audio assigned in order first come first get.
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 bf1d7bb90e0f..bb09243758fe 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -423,10 +423,10 @@ bool dc_stream_add_writeback(struct dc *dc,
 
 		if (dwb->funcs->is_enabled(dwb)) {
 			/* writeback pipe already enabled, only need to update */
-			dc->hwss.update_writeback(dc, stream_status, wb_info);
+			dc->hwss.update_writeback(dc, stream_status, wb_info, dc->current_state);
 		} else {
 			/* Enable writeback pipe from scratch*/
-			dc->hwss.enable_writeback(dc, stream_status, wb_info);
+			dc->hwss.enable_writeback(dc, stream_status, wb_info, dc->current_state);
 		}
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index a82352a87808..0416a17b0897 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -39,7 +39,7 @@
 #include "inc/hw/dmcu.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.2.48"
+#define DC_VER "3.2.56"
 
 #define MAX_SURFACES 3
 #define MAX_PLANES 6
@@ -111,19 +111,20 @@ struct dc_caps {
 	bool force_dp_tps4_for_cp2520;
 	bool disable_dp_clk_share;
 	bool psp_setup_panel_mode;
+	bool extended_aux_timeout_support;
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	bool hw_3d_lut;
 #endif
 	struct dc_plane_cap planes[MAX_PLANES];
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 struct dc_bug_wa {
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool no_connect_phy_config;
 	bool dedcn20_305_wa;
+#endif
 	bool skip_clock_update;
 };
-#endif
 
 struct dc_dcc_surface_param {
 	struct dc_size surface_size;
@@ -219,7 +220,9 @@ struct dc_config {
 	bool allow_seamless_boot_optimization;
 	bool power_down_display_on_boot;
 	bool edp_not_connected;
+	bool force_enum_edp;
 	bool forced_clocks;
+	bool disable_extended_timeout_support; // Used to disable extended timeout and lttpr feature as well
 	bool multi_mon_pp_mclk_switch;
 };
 
@@ -227,6 +230,7 @@ enum visual_confirm {
 	VISUAL_CONFIRM_DISABLE = 0,
 	VISUAL_CONFIRM_SURFACE = 1,
 	VISUAL_CONFIRM_HDR = 2,
+	VISUAL_CONFIRM_MPCTREE = 4,
 };
 
 enum dcc_option {
@@ -245,6 +249,19 @@ enum wm_report_mode {
 	WM_REPORT_DEFAULT = 0,
 	WM_REPORT_OVERRIDE = 1,
 };
+enum dtm_pstate{
+	dtm_level_p0 = 0,/*highest voltage*/
+	dtm_level_p1,
+	dtm_level_p2,
+	dtm_level_p3,
+	dtm_level_p4,/*when active_display_count = 0*/
+};
+
+enum dcn_pwr_state {
+	DCN_PWR_STATE_UNKNOWN = -1,
+	DCN_PWR_STATE_MISSION_MODE = 0,
+	DCN_PWR_STATE_LOW_POWER = 3,
+};
 
 /*
  * For any clocks that may differ per pipe
@@ -252,11 +269,7 @@ enum wm_report_mode {
  */
 struct dc_clocks {
 	int dispclk_khz;
-	int max_supported_dppclk_khz;
-	int max_supported_dispclk_khz;
 	int dppclk_khz;
-	int bw_dppclk_khz; /*a copy of dppclk_khz*/
-	int bw_dispclk_khz;
 	int dcfclk_khz;
 	int socclk_khz;
 	int dcfclk_deep_sleep_khz;
@@ -264,12 +277,17 @@ struct dc_clocks {
 	int phyclk_khz;
 	int dramclk_khz;
 	bool p_state_change_support;
-
+	enum dcn_pwr_state pwr_state;
 	/*
 	 * Elements below are not compared for the purposes of
 	 * optimization required
 	 */
 	bool prev_p_state_change_support;
+	enum dtm_pstate dtm_level;
+	int max_supported_dppclk_khz;
+	int max_supported_dispclk_khz;
+	int bw_dppclk_khz; /*a copy of dppclk_khz*/
+	int bw_dispclk_khz;
 };
 
 struct dc_bw_validation_profile {
@@ -347,6 +365,7 @@ struct dc_debug_options {
 	bool disable_hubp_power_gate;
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool disable_dsc_power_gate;
+	int dsc_min_slice_height_override;
 #endif
 	bool disable_pplib_wm_range;
 	enum wm_report_mode pplib_wm_report_mode;
@@ -462,9 +481,7 @@ struct dc {
 	struct dc_config config;
 	struct dc_debug_options debug;
 	struct dc_bounding_box_overrides bb_overrides;
-#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	struct dc_bug_wa work_arounds;
-#endif
 	struct dc_context *ctx;
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 	struct dc_phy_addr_space_config vm_pa_config;
@@ -553,10 +570,16 @@ struct dc_init_data {
 };
 
 struct dc_callback_init {
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	struct cp_psp cp_psp;
+#else
 	uint8_t reserved;
+#endif
 };
 
 struct dc *dc_create(const struct dc_init_data *init_params);
+void dc_hardware_init(struct dc *dc);
+
 int dc_get_vmid_use_vector(struct dc *dc);
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 void dc_setup_vm_context(struct dc *dc, struct dc_virtual_addr_space_config *va_config, int vmid);
@@ -565,6 +588,7 @@ int dc_setup_system_context(struct dc *dc, struct dc_phy_addr_space_config *pa_c
 #endif
 void dc_init_callbacks(struct dc *dc,
 		const struct dc_callback_init *init_params);
+void dc_deinit_callbacks(struct dc *dc);
 void dc_destroy(struct dc **dc);
 
 /*******************************************************************************
diff --git a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
index 4ef97f65e55d..4f8f576d5fcf 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
@@ -49,7 +49,8 @@ enum aux_channel_operation_result {
 	AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN,
 	AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY,
 	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT,
-	AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON
+	AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON,
+	AUX_CHANNEL_OPERATION_FAILED_ENGINE_ACQUIRE
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
index 6e42209f0e20..0ed2962add5a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
@@ -30,6 +30,7 @@
 #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_0  0x0a0   /* DP 1.4a SCR */
 #define DP_DSC_BRANCH_OVERALL_THROUGHPUT_1  0x0a1
 #define DP_DSC_BRANCH_MAX_LINE_WIDTH        0x0a2
+#include "dc_types.h"
 
 struct dc_dsc_bw_range {
 	uint32_t min_kbps; /* Bandwidth if min_target_bpp_x16 is used */
@@ -39,13 +40,21 @@ struct dc_dsc_bw_range {
 	uint32_t stream_kbps; /* Uncompressed stream bandwidth */
 };
 
+struct display_stream_compressor {
+	const struct dsc_funcs *funcs;
+#ifndef AMD_EDID_UTILITY
+	struct dc_context *ctx;
+	int inst;
+#endif
+};
 
 bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data,
 		const uint8_t *dpcd_dsc_ext_data,
 		struct dsc_dec_dpcd_caps *dsc_sink_caps);
 
 bool dc_dsc_compute_bandwidth_range(
-		const struct dc *dc,
+		const struct display_stream_compressor *dsc,
+		const uint32_t dsc_min_slice_height_override,
 		const uint32_t min_kbps,
 		const uint32_t max_kbps,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
@@ -53,8 +62,9 @@ bool dc_dsc_compute_bandwidth_range(
 		struct dc_dsc_bw_range *range);
 
 bool dc_dsc_compute_config(
-		const struct dc *dc,
+		const struct display_stream_compressor *dsc,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
+		const uint32_t dsc_min_slice_height_override,
 		uint32_t target_bandwidth_kbps,
 		const struct dc_crtc_timing *timing,
 		struct dc_dsc_config *dsc_cfg);
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 0b8700a8a94a..e0856bb8511f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -26,6 +26,8 @@
 #ifndef DC_HW_TYPES_H
 #define DC_HW_TYPES_H
 
+#ifndef AMD_EDID_UTILITY
+
 #include "os_types.h"
 #include "fixed31_32.h"
 #include "signal_types.h"
@@ -124,20 +126,6 @@ struct plane_size {
 	int chroma_pitch;
 	struct rect surface_size;
 	struct rect chroma_size;
-
-	union {
-		struct {
-			struct rect surface_size;
-			int surface_pitch;
-		} grph;
-
-		struct {
-			struct rect luma_size;
-			int luma_pitch;
-			struct rect chroma_size;
-			int chroma_pitch;
-		} video;
-	};
 };
 
 struct dc_plane_dcc_param {
@@ -148,21 +136,6 @@ struct dc_plane_dcc_param {
 
 	int meta_pitch_c;
 	bool independent_64b_blks_c;
-
-	union {
-		struct {
-			int meta_pitch;
-			bool independent_64b_blks;
-		} grph;
-
-		struct {
-			int meta_pitch_l;
-			bool independent_64b_blks_l;
-
-			int meta_pitch_c;
-			bool independent_64b_blks_c;
-		} video;
-	};
 };
 
 /*Displayable pixel format in fb*/
@@ -605,6 +578,11 @@ enum dc_quantization_range {
 	QUANTIZATION_RANGE_LIMITED
 };
 
+enum dc_dynamic_expansion {
+	DYN_EXPANSION_AUTO,
+	DYN_EXPANSION_DISABLE
+};
+
 /* XFM */
 
 /* used in  struct dc_plane_state */
@@ -616,6 +594,8 @@ struct scaling_taps {
 	bool integer_scaling;
 };
 
+#endif /* AMD_EDID_UTILITY */
+
 enum dc_timing_standard {
 	DC_TIMING_STANDARD_UNDEFINED,
 	DC_TIMING_STANDARD_DMT,
@@ -737,30 +717,6 @@ enum dc_timing_3d_format {
 	TIMING_3D_FORMAT_MAX,
 };
 
-enum trigger_delay {
-	TRIGGER_DELAY_NEXT_PIXEL = 0,
-	TRIGGER_DELAY_NEXT_LINE,
-};
-
-enum crtc_event {
-	CRTC_EVENT_VSYNC_RISING = 0,
-	CRTC_EVENT_VSYNC_FALLING
-};
-
-struct crtc_trigger_info {
-	bool enabled;
-	struct dc_stream_state *event_source;
-	enum crtc_event event;
-	enum trigger_delay delay;
-};
-
-struct dc_crtc_timing_adjust {
-	uint32_t v_total_min;
-	uint32_t v_total_max;
-	uint32_t v_total_mid;
-	uint32_t v_total_mid_frame_num;
-};
-
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 struct dc_dsc_config {
 	uint32_t num_slices_h; /* Number of DSC slices - horizontal */
@@ -804,6 +760,33 @@ struct dc_crtc_timing {
 #endif
 };
 
+#ifndef AMD_EDID_UTILITY
+
+enum trigger_delay {
+	TRIGGER_DELAY_NEXT_PIXEL = 0,
+	TRIGGER_DELAY_NEXT_LINE,
+};
+
+enum crtc_event {
+	CRTC_EVENT_VSYNC_RISING = 0,
+	CRTC_EVENT_VSYNC_FALLING
+};
+
+struct crtc_trigger_info {
+	bool enabled;
+	struct dc_stream_state *event_source;
+	enum crtc_event event;
+	enum trigger_delay delay;
+};
+
+struct dc_crtc_timing_adjust {
+	uint32_t v_total_min;
+	uint32_t v_total_max;
+	uint32_t v_total_mid;
+	uint32_t v_total_mid_frame_num;
+};
+
+
 /* Passed on init */
 enum vram_type {
 	VIDEO_MEMORY_TYPE_GDDR5  = 2,
@@ -874,5 +857,7 @@ struct tg_color {
 	uint16_t color_b_cb;
 };
 
+#endif /* AMD_EDID_UTILITY */
+
 #endif /* DC_HW_TYPES_H */
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 9ea75db3484e..f24fd19ed93d 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -126,7 +126,8 @@ struct dc_link {
 	unsigned short chip_caps;
 	unsigned int dpcd_sink_count;
 	enum edp_revision edp_revision;
-	bool psr_enabled;
+	bool psr_feature_enabled;
+	bool psr_allow_active;
 
 	/* MST record stream using this link */
 	struct link_flags {
@@ -158,6 +159,18 @@ static inline struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_
 	return dc->links[link_index];
 }
 
+static inline struct dc_link *get_edp_link(const struct dc *dc)
+{
+	int i;
+
+	// report any eDP links, even unconnected DDI's
+	for (i = 0; i < dc->link_count; i++) {
+		if (dc->links[i]->connector_signal == SIGNAL_TYPE_EDP)
+			return dc->links[i];
+	}
+	return NULL;
+}
+
 /* Set backlight level of an embedded panel (eDP, LVDS).
  * backlight_pwm_u16_16 is unsigned 32 bit with 16 bit integer
  * and 16 bit fractional, where 1.0 is max backlight value.
@@ -170,7 +183,7 @@ int dc_link_get_backlight_level(const struct dc_link *dc_link);
 
 bool dc_link_set_abm_disable(const struct dc_link *dc_link);
 
-bool dc_link_set_psr_enable(const struct dc_link *dc_link, bool enable, bool wait);
+bool dc_link_set_psr_allow_active(struct dc_link *dc_link, bool enable, bool wait);
 
 bool dc_link_get_psr_state(const struct dc_link *dc_link, uint32_t *psr_state);
 
@@ -192,6 +205,7 @@ enum dc_detect_reason {
 
 bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
 bool dc_link_get_hpd_state(struct dc_link *dc_link);
+enum dc_status dc_link_allocate_mst_payload(struct pipe_ctx *pipe_ctx);
 
 /* Notify DC about DP RX Interrupt (aka Short Pulse Interrupt).
  * Return:
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 0fa1c26bc20d..fdb6adc37857 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -113,6 +113,21 @@ struct periodic_interrupt_config {
 	int lines_offset;
 };
 
+union stream_update_flags {
+	struct {
+		uint32_t scaling:1;
+		uint32_t out_tf:1;
+		uint32_t out_csc:1;
+		uint32_t abm_level:1;
+		uint32_t dpms_off:1;
+		uint32_t gamut_remap:1;
+#if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+		uint32_t wb_update:1;
+#endif
+	} bits;
+
+	uint32_t raw;
+};
 
 struct dc_stream_state {
 	// sink is deprecated, new code should not reference
@@ -214,9 +229,14 @@ struct dc_stream_state {
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	bool is_dsc_enabled;
 #endif
+	union stream_update_flags update_flags;
 };
 
+#define ABM_LEVEL_IMMEDIATE_DISABLE 0xFFFFFFFF
+
 struct dc_stream_update {
+	struct dc_stream_state *stream;
+
 	struct rect src;
 	struct rect dst;
 	struct dc_transfer_func *out_transfer_func;
@@ -431,6 +451,9 @@ void dc_stream_set_static_screen_events(struct dc *dc,
 					int num_streams,
 					const struct dc_static_screen_events *events);
 
+void dc_stream_set_dyn_expansion(struct dc *dc, struct dc_stream_state *stream,
+		enum dc_dynamic_expansion option);
+
 void dc_stream_set_dither_option(struct dc_stream_state *stream,
 				 enum dc_dither_option option);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index b273735b6a3e..d9be8fc3889f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -25,6 +25,11 @@
 #ifndef DC_TYPES_H_
 #define DC_TYPES_H_
 
+#ifndef AMD_EDID_UTILITY
+/* AND EdidUtility only needs a portion
+ * of this file, including the rest only
+ * causes additional issues.
+ */
 #include "os_types.h"
 #include "fixed31_32.h"
 #include "irq_types.h"
@@ -33,6 +38,10 @@
 #include "dal_types.h"
 #include "grph_object_defs.h"
 
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+#include "dm_cp_psp.h"
+#endif
+
 /* forward declarations */
 struct dc_plane_state;
 struct dc_stream_state;
@@ -100,6 +109,9 @@ struct dc_context {
 	uint32_t dc_sink_id_count;
 	uint32_t dc_stream_id_count;
 	uint64_t fbc_gpu_addr;
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+	struct cp_psp cp_psp;
+#endif
 };
 
 
@@ -159,6 +171,12 @@ enum dc_edid_status {
 	EDID_THE_SAME,
 };
 
+enum act_return_status {
+	ACT_SUCCESS,
+	ACT_LINK_LOST,
+	ACT_FAILED
+};
+
 /* audio capability from EDID*/
 struct dc_cea_audio_mode {
 	uint8_t format_code; /* ucData[0] [6:3]*/
@@ -739,6 +757,9 @@ struct dc_clock_config {
 	uint32_t current_clock_khz;/*current clock in use*/
 };
 
+#endif /*AMD_EDID_UTILITY*/
+//AMD EDID UTILITY does not need any of the above structures
+
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 /* DSC DPCD capabilities */
 union dsc_slice_caps1 {
@@ -810,4 +831,5 @@ struct dsc_dec_dpcd_caps {
 	uint32_t branch_max_line_width;
 };
 #endif
+
 #endif /* DC_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
index 58bd131d5b48..b8a3fc505c9b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_abm.c
@@ -77,6 +77,9 @@ static bool dce_abm_set_pipe(struct abm *abm, uint32_t controller_id)
 	/* notifyDMCUMsg */
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
 
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0,
+			1, 80000);
+
 	return true;
 }
 
@@ -401,6 +404,10 @@ static bool dce_abm_init_backlight(struct abm *abm)
 	/* Enable the backlight output */
 	REG_UPDATE(BL_PWM_CNTL, BL_PWM_EN, 1);
 
+	/* Disable fractional pwm if configured */
+	REG_UPDATE(BL_PWM_CNTL, BL_PWM_FRACTIONAL_EN,
+		   abm->ctx->dc->config.disable_fractional_pwm ? 0 : 1);
+
 	/* Unlock group 2 backlight registers */
 	REG_UPDATE(BL_PWM_GRP1_REG_LOCK,
 			BL_PWM_GRP1_REG_LOCK, 0);
@@ -489,9 +496,6 @@ void dce_abm_destroy(struct abm **abm)
 {
 	struct dce_abm *abm_dce = TO_DCE_ABM(*abm);
 
-	if (abm_dce->base.dmcu_is_running == true)
-		abm_dce->base.funcs->set_abm_immediate_disable(*abm);
-
 	kfree(abm_dce);
 	*abm = NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index c3f9f4185ce8..e472608faf33 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -42,6 +42,10 @@
 
 #include "reg_helper.h"
 
+#undef FN
+#define FN(reg_name, field_name) \
+	aux110->shift->field_name, aux110->mask->field_name
+
 #define FROM_AUX_ENGINE(ptr) \
 	container_of((ptr), struct aux_engine_dce110, base)
 
@@ -55,6 +59,14 @@ enum {
 	AUX_TIMED_OUT_RETRY_COUNTER = 2,
 	AUX_DEFER_RETRY_COUNTER = 6
 };
+
+#define TIME_OUT_INCREMENT      1016
+#define TIME_OUT_MULTIPLIER_8 	8
+#define TIME_OUT_MULTIPLIER_16  16
+#define TIME_OUT_MULTIPLIER_32  32
+#define TIME_OUT_MULTIPLIER_64  64
+#define MAX_TIMEOUT_LENGTH      127
+
 static void release_engine(
 	struct dce_aux *engine)
 {
@@ -198,7 +210,7 @@ static void submit_channel_request(
 	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
 
 	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
-				10, aux110->timeout_period/10);
+				10, aux110->polling_timeout_period/10);
 
 	/* set the delay and the number of bytes to write */
 
@@ -327,7 +339,7 @@ static enum aux_channel_operation_result get_channel_status(
 
 	/* poll to make sure that SW_DONE is asserted */
 	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 1,
-				10, aux110->timeout_period/10);
+				10, aux110->polling_timeout_period/10);
 
 	value = REG_READ(AUX_SW_STATUS);
 	/* in case HPD is LOW, exit AUX transaction */
@@ -414,20 +426,77 @@ void dce110_engine_destroy(struct dce_aux **engine)
 	*engine = NULL;
 
 }
+
+static bool dce_aux_configure_timeout(struct ddc_service *ddc,
+		uint32_t timeout_in_us)
+{
+	uint32_t multiplier = 0;
+	uint32_t length = 0;
+	struct ddc *ddc_pin = ddc->ddc_pin;
+	struct dce_aux *aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(aux_engine);
+
+	/* 1-Update polling timeout period */
+	aux110->polling_timeout_period = timeout_in_us * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER;
+
+	/* 2-Update aux timeout period length and multiplier */
+	if (timeout_in_us <= TIME_OUT_INCREMENT) {
+		multiplier = 0;
+		length = timeout_in_us/TIME_OUT_MULTIPLIER_8;
+		if (timeout_in_us % TIME_OUT_MULTIPLIER_8 != 0)
+			length++;
+	} else if (timeout_in_us <= 2 * TIME_OUT_INCREMENT) {
+		multiplier = 1;
+		length = timeout_in_us/TIME_OUT_MULTIPLIER_16;
+		if (timeout_in_us % TIME_OUT_MULTIPLIER_16 != 0)
+			length++;
+	} else if (timeout_in_us <= 4 * TIME_OUT_INCREMENT) {
+		multiplier = 2;
+		length = timeout_in_us/TIME_OUT_MULTIPLIER_32;
+		if (timeout_in_us % TIME_OUT_MULTIPLIER_32 != 0)
+			length++;
+	} else if (timeout_in_us > 4 * TIME_OUT_INCREMENT) {
+		multiplier = 3;
+		length = timeout_in_us/TIME_OUT_MULTIPLIER_64;
+		if (timeout_in_us % TIME_OUT_MULTIPLIER_64 != 0)
+			length++;
+	}
+
+	length = (length < MAX_TIMEOUT_LENGTH) ? length : MAX_TIMEOUT_LENGTH;
+
+	REG_UPDATE_SEQ_2(AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, length, AUX_RX_TIMEOUT_LEN_MUL, multiplier);
+
+	return true;
+}
+
+static struct dce_aux_funcs aux_functions = {
+	.configure_timeout = NULL,
+	.destroy = NULL,
+};
+
 struct dce_aux *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)
+		const struct dce110_aux_registers *regs,
+		const struct dce110_aux_registers_mask *mask,
+		const struct dce110_aux_registers_shift *shift,
+		bool is_ext_aux_timeout_configurable)
 {
 	aux_engine110->base.ddc = NULL;
 	aux_engine110->base.ctx = ctx;
 	aux_engine110->base.delay = 0;
 	aux_engine110->base.max_defer_write_retry = 0;
 	aux_engine110->base.inst = inst;
-	aux_engine110->timeout_period = timeout_period;
+	aux_engine110->polling_timeout_period = timeout_period;
 	aux_engine110->regs = regs;
 
+	aux_engine110->mask = mask;
+	aux_engine110->shift = shift;
+	aux_engine110->base.funcs = &aux_functions;
+	if (is_ext_aux_timeout_configurable)
+		aux_engine110->base.funcs->configure_timeout = &dce_aux_configure_timeout;
+
 	return &aux_engine110->base;
 }
 
@@ -464,8 +533,10 @@ int dce_aux_transfer_raw(struct ddc_service *ddc,
 	memset(&aux_rep, 0, sizeof(aux_rep));
 
 	aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
-	if (!acquire(aux_engine, ddc_pin))
+	if (!acquire(aux_engine, ddc_pin)) {
+		*operation_result = AUX_CHANNEL_OPERATION_FAILED_ENGINE_ACQUIRE;
 		return -1;
+	}
 
 	if (payload->i2c_over_aux)
 		aux_req.type = AUX_TRANSACTION_TYPE_I2C;
@@ -475,7 +546,7 @@ int dce_aux_transfer_raw(struct ddc_service *ddc,
 	aux_req.action = i2caux_action_from_payload(payload);
 
 	aux_req.address = payload->address;
-	aux_req.delay = payload->defer_delay * 10;
+	aux_req.delay = 0;
 	aux_req.length = payload->length;
 	aux_req.data = payload->data;
 
@@ -544,8 +615,15 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 			case AUX_TRANSACTION_REPLY_AUX_DEFER:
 			case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_NACK:
 			case AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER:
-				if (++aux_defer_retries >= AUX_MAX_DEFER_RETRIES)
+				if (++aux_defer_retries >= AUX_MAX_DEFER_RETRIES) {
 					goto fail;
+				} else {
+					if ((*payload->reply == AUX_TRANSACTION_REPLY_AUX_DEFER) ||
+						(*payload->reply == AUX_TRANSACTION_REPLY_I2C_OVER_AUX_DEFER)) {
+						if (payload->defer_delay > 0)
+							msleep(payload->defer_delay);
+					}
+				}
 				break;
 
 			case AUX_TRANSACTION_REPLY_I2C_DEFER:
@@ -582,6 +660,7 @@ bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 			break;
 
 		case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		case AUX_CHANNEL_OPERATION_FAILED_ENGINE_ACQUIRE:
 		case AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN:
 		default:
 			goto fail;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index ed7fec8fe253..b4b2c79a8073 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -29,6 +29,7 @@
 #include "i2caux_interface.h"
 #include "inc/hw/aux_engine.h"
 
+
 #ifdef CONFIG_DRM_AMD_DC_DCN2_0
 #define AUX_COMMON_REG_LIST0(id)\
 	SRI(AUX_CONTROL, DP_AUX, id), \
@@ -36,6 +37,7 @@
 	SRI(AUX_SW_DATA, DP_AUX, id), \
 	SRI(AUX_SW_CONTROL, DP_AUX, id), \
 	SRI(AUX_INTERRUPT_CONTROL, DP_AUX, id), \
+	SRI(AUX_DPHY_RX_CONTROL1, DP_AUX, id), \
 	SRI(AUX_SW_STATUS, DP_AUX, id)
 #endif
 
@@ -55,6 +57,7 @@ struct dce110_aux_registers {
 	uint32_t AUX_SW_DATA;
 	uint32_t AUX_SW_CONTROL;
 	uint32_t AUX_INTERRUPT_CONTROL;
+	uint32_t AUX_DPHY_RX_CONTROL1;
 	uint32_t AUX_SW_STATUS;
 	uint32_t AUXN_IMPCAL;
 	uint32_t AUXP_IMPCAL;
@@ -62,6 +65,156 @@ struct dce110_aux_registers {
 	uint32_t AUX_RESET_MASK;
 };
 
+#define DCE_AUX_REG_FIELD_LIST(type)\
+	type AUX_EN;\
+	type AUX_RESET;\
+	type AUX_RESET_DONE;\
+	type AUX_REG_RW_CNTL_STATUS;\
+	type AUX_SW_USE_AUX_REG_REQ;\
+	type AUX_SW_DONE_USING_AUX_REG;\
+	type AUX_SW_AUTOINCREMENT_DISABLE;\
+	type AUX_SW_DATA_RW;\
+	type AUX_SW_INDEX;\
+	type AUX_SW_GO;\
+	type AUX_SW_DATA;\
+	type AUX_SW_REPLY_BYTE_COUNT;\
+	type AUX_SW_DONE;\
+	type AUX_SW_DONE_ACK;\
+	type AUXN_IMPCAL_ENABLE;\
+	type AUXP_IMPCAL_ENABLE;\
+	type AUXN_IMPCAL_OVERRIDE_ENABLE;\
+	type AUXP_IMPCAL_OVERRIDE_ENABLE;\
+	type AUX_RX_TIMEOUT_LEN;\
+	type AUX_RX_TIMEOUT_LEN_MUL;\
+	type AUXN_CALOUT_ERROR_AK;\
+	type AUXP_CALOUT_ERROR_AK;\
+	type AUX_SW_START_DELAY;\
+	type AUX_SW_WR_BYTES
+
+#define DCE10_AUX_MASK_SH_LIST(mask_sh)\
+	AUX_SF(AUX_CONTROL, AUX_EN, mask_sh),\
+	AUX_SF(AUX_ARB_CONTROL, AUX_REG_RW_CNTL_STATUS, mask_sh),\
+	AUX_SF(AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, mask_sh),\
+	AUX_SF(AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, mask_sh),\
+	AUX_SF(AUX_SW_CONTROL, AUX_SW_START_DELAY, mask_sh),\
+	AUX_SF(AUX_SW_CONTROL, AUX_SW_WR_BYTES, mask_sh),\
+	AUX_SF(AUX_SW_CONTROL, AUX_SW_GO, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_DATA_RW, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_INDEX, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_DATA, mask_sh),\
+	AUX_SF(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT, mask_sh),\
+	AUX_SF(AUX_SW_STATUS, AUX_SW_DONE, mask_sh),\
+	AUX_SF(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_OVERRIDE_ENABLE, mask_sh)
+
+#define DCE_AUX_MASK_SH_LIST(mask_sh)\
+	AUX_SF(AUX_CONTROL, AUX_EN, mask_sh),\
+	AUX_SF(AUX_CONTROL, AUX_RESET, mask_sh),\
+	AUX_SF(AUX_CONTROL, AUX_RESET_DONE, mask_sh),\
+	AUX_SF(AUX_ARB_CONTROL, AUX_REG_RW_CNTL_STATUS, mask_sh),\
+	AUX_SF(AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, mask_sh),\
+	AUX_SF(AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, mask_sh),\
+	AUX_SF(AUX_SW_CONTROL, AUX_SW_START_DELAY, mask_sh),\
+	AUX_SF(AUX_SW_CONTROL, AUX_SW_WR_BYTES, mask_sh),\
+	AUX_SF(AUX_SW_CONTROL, AUX_SW_GO, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_DATA_RW, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_INDEX, mask_sh),\
+	AUX_SF(AUX_SW_DATA, AUX_SW_DATA, mask_sh),\
+	AUX_SF(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT, mask_sh),\
+	AUX_SF(AUX_SW_STATUS, AUX_SW_DONE, mask_sh),\
+	AUX_SF(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_OVERRIDE_ENABLE, mask_sh)
+
+#define DCE12_AUX_MASK_SH_LIST(mask_sh)\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_EN, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_RESET, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_RESET_DONE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_REG_RW_CNTL_STATUS, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_START_DELAY, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_WR_BYTES, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_GO, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_DATA_RW, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_INDEX, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_DATA, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_STATUS, AUX_SW_DONE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_OVERRIDE_ENABLE, mask_sh)
+
+/* DCN10 MASK */
+#define DCN10_AUX_MASK_SH_LIST(mask_sh)\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_EN, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_RESET, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_RESET_DONE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_REG_RW_CNTL_STATUS, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_START_DELAY, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_WR_BYTES, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_GO, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_DATA_RW, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_INDEX, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_DATA, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_STATUS, AUX_SW_DONE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_ENABLE, mask_sh),\
+	AUX_SF(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE, mask_sh),\
+	AUX_SF(AUXN_IMPCAL, AUXN_IMPCAL_OVERRIDE_ENABLE, mask_sh)
+
+/* for all other DCN */
+#define DCN_AUX_MASK_SH_LIST(mask_sh)\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_EN, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_RESET, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_CONTROL, AUX_RESET_DONE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_REG_RW_CNTL_STATUS, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_START_DELAY, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_WR_BYTES, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_CONTROL, AUX_SW_GO, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_DATA_RW, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_AUTOINCREMENT_DISABLE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_INDEX, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_DATA, AUX_SW_DATA, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_SW_STATUS, AUX_SW_DONE, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN, mask_sh),\
+	AUX_SF(DP_AUX0_AUX_DPHY_RX_CONTROL1, AUX_RX_TIMEOUT_LEN_MUL, mask_sh)
+
+#define AUX_SF(reg_name, field_name, post_fix)\
+	.field_name = reg_name ## __ ## field_name ## post_fix
+
 enum {	/* This is the timeout as defined in DP 1.2a,
 	 * 2.3.4 "Detailed uPacket TX AUX CH State Description".
 	 */
@@ -97,20 +250,34 @@ struct dce_aux {
 	uint32_t max_defer_write_retry;
 
 	bool acquire_reset;
+	struct dce_aux_funcs *funcs;
+};
+
+struct dce110_aux_registers_mask {
+	DCE_AUX_REG_FIELD_LIST(uint32_t);
+};
+
+struct dce110_aux_registers_shift {
+	DCE_AUX_REG_FIELD_LIST(uint8_t);
 };
 
+
 struct aux_engine_dce110 {
 	struct dce_aux base;
 	const struct dce110_aux_registers *regs;
+	const struct dce110_aux_registers_mask *mask;
+	const struct dce110_aux_registers_shift *shift;
 	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_dphy_rx_control1;
+		uint32_t aux_dphy_rx_control0;
 		uint32_t aux_sw_status;
 	} addr;
-	uint32_t timeout_period;
+	uint32_t polling_timeout_period;
 };
 
 struct aux_engine_dce110_init_data {
@@ -120,12 +287,15 @@ struct aux_engine_dce110_init_data {
 	const struct dce110_aux_registers *regs;
 };
 
-struct dce_aux *dce110_aux_engine_construct(
-		struct aux_engine_dce110 *aux_engine110,
+struct dce_aux *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);
+		const struct dce110_aux_registers *regs,
+
+		const struct dce110_aux_registers_mask *mask,
+		const struct dce110_aux_registers_shift *shift,
+		bool is_ext_aux_timeout_configurable);
 
 void dce110_engine_destroy(struct dce_aux **engine);
 
@@ -139,4 +309,13 @@ int dce_aux_transfer_raw(struct ddc_service *ddc,
 
 bool dce_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *cmd);
+
+struct dce_aux_funcs {
+	bool (*configure_timeout)
+		(struct ddc_service *ddc,
+		 uint32_t timeout);
+	void (*destroy)
+		(struct aux_engine **ptr);
+};
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index 0b86cee4876f..ba995d3f2318 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -907,9 +907,6 @@ void dce_dmcu_destroy(struct dmcu **dmcu)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(*dmcu);
 
-	if (dmcu_dce->base.dmcu_state == DMCU_RUNNING)
-		dmcu_dce->base.funcs->set_psr_enable(*dmcu, false, true);
-
 	kfree(dmcu_dce);
 	*dmcu = NULL;
 }
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 ac04d77058f0..32d145a0d6fc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -679,6 +679,7 @@ struct dce_hwseq_registers {
 	HWS_SF(, DOMAIN17_PG_STATUS, DOMAIN17_PGFSM_PWR_STATUS, mask_sh), \
 	HWS_SF(, DOMAIN18_PG_STATUS, DOMAIN18_PGFSM_PWR_STATUS, mask_sh), \
 	HWS_SF(, DC_IP_REQUEST_CNTL, IP_REQUEST_EN, mask_sh), \
+	HWSEQ_LVTMA_MASK_SH_LIST(mask_sh), \
 	HWS_SF(, LVTMA_PWRSEQ_CNTL, LVTMA_BLON, mask_sh), \
 	HWS_SF(, LVTMA_PWRSEQ_STATE, LVTMA_PWRSEQ_TARGET_STATE_R, mask_sh)
 #endif
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 31b698bf9cfc..8aa937f496c4 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
@@ -606,11 +606,11 @@ static void dce_mi_allocate_dmif(
 	}
 
 	if (dce_mi->wa.single_head_rdreq_dmif_limit) {
-		uint32_t eanble =  (total_stream_num > 1) ? 0 :
+		uint32_t enable =  (total_stream_num > 1) ? 0 :
 				dce_mi->wa.single_head_rdreq_dmif_limit;
 
 		REG_UPDATE(MC_HUB_RDREQ_DMIF_LIMIT,
-				ENABLE, eanble);
+				ENABLE, enable);
 	}
 }
 
@@ -636,11 +636,11 @@ static void dce_mi_free_dmif(
 			10, 3500);
 
 	if (dce_mi->wa.single_head_rdreq_dmif_limit) {
-		uint32_t eanble =  (total_stream_num > 1) ? 0 :
+		uint32_t enable =  (total_stream_num > 1) ? 0 :
 				dce_mi->wa.single_head_rdreq_dmif_limit;
 
 		REG_UPDATE(MC_HUB_RDREQ_DMIF_LIMIT,
-				ENABLE, eanble);
+				ENABLE, enable);
 	}
 }
 
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 76d54885374a..a5e122c721ec 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -399,6 +399,37 @@ static const struct dc_plane_cap plane_cap = {
 #define CC_DC_HDMI_STRAPS__AUDIO_STREAM_NUMBER__SHIFT 0x8
 #endif
 
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		return 6;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 static void read_dce_straps(
 	struct dc_context *ctx,
 	struct resource_straps *straps)
@@ -506,6 +537,14 @@ static const struct dce_mem_input_mask mi_masks = {
 		.ENABLE = MC_HUB_RDREQ_DMIF_LIMIT__ENABLE_MASK
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCE10_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCE10_AUX_MASK_SH_LIST(_MASK)
+};
+
 static struct mem_input *dce100_mem_input_create(
 	struct dc_context *ctx,
 	uint32_t inst)
@@ -571,14 +610,18 @@ struct link_encoder *dce100_link_encoder_create(
 {
 	struct dce110_link_encoder *enc110 =
 		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc110)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dce110_link_encoder_construct(enc110,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
@@ -611,7 +654,10 @@ struct dce_aux *dce100_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -997,6 +1043,8 @@ static bool construct(
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
 	dc->caps.disable_dp_clk_share = true;
+	dc->caps.extended_aux_timeout_support = false;
+
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.timing_generators[i] =
 			dce100_timing_generator_create(
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 01a924bf477a..f0e837d14000 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
@@ -944,7 +944,6 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 {
 	/* notify audio driver for audio modes of monitor */
 	struct dc *core_dc;
-	struct pp_smu_funcs *pp_smu = NULL;
 	struct clk_mgr *clk_mgr;
 	unsigned int i, num_audio = 1;
 
@@ -957,9 +956,6 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream_res.audio && pipe_ctx->stream_res.audio->enabled == true)
 		return;
 
-	if (core_dc->res_pool->pp_smu)
-		pp_smu = core_dc->res_pool->pp_smu;
-
 	if (pipe_ctx->stream_res.audio) {
 		for (i = 0; i < MAX_PIPES; i++) {
 			/*current_state not updated yet*/
@@ -984,7 +980,6 @@ void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx)
 {
 	struct dc *dc;
-	struct pp_smu_funcs *pp_smu = NULL;
 	struct clk_mgr *clk_mgr;
 
 	if (!pipe_ctx || !pipe_ctx->stream)
@@ -1001,9 +996,6 @@ void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->stream_res.audio) {
 		pipe_ctx->stream_res.audio->enabled = false;
 
-		if (dc->res_pool->pp_smu)
-			pp_smu = dc->res_pool->pp_smu;
-
 		if (dc_is_dp_signal(pipe_ctx->stream->signal))
 			pipe_ctx->stream_res.stream_enc->funcs->dp_audio_disable(
 					pipe_ctx->stream_res.stream_enc);
@@ -1169,8 +1161,9 @@ static void build_audio_output(
 		}
 	}
 
-	if (pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
-			pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
+	if (state->clk_mgr &&
+		(pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT ||
+			pipe_ctx->stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST)) {
 		audio_output->pll_info.dp_dto_source_clock_in_khz =
 				state->clk_mgr->funcs->get_dp_ref_clk_frequency(
 						state->clk_mgr);
@@ -1418,7 +1411,7 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 
 	pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->bottom_pipe != 0;
 
-	pipe_ctx->stream->link->psr_enabled = false;
+	pipe_ctx->stream->link->psr_feature_enabled = false;
 
 	return DC_OK;
 }
@@ -1428,8 +1421,6 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 static void power_down_encoders(struct dc *dc)
 {
 	int i;
-	enum connector_id connector_id;
-	enum signal_type signal = SIGNAL_TYPE_NONE;
 
 	/* do not know BIOS back-front mapping, simply blank all. It will not
 	 * hurt for non-DP
@@ -1440,15 +1431,12 @@ static void power_down_encoders(struct dc *dc)
 	}
 
 	for (i = 0; i < dc->link_count; i++) {
-		connector_id = dal_graphics_object_id_get_connector_id(dc->links[i]->link_id);
-		if ((connector_id == CONNECTOR_ID_DISPLAY_PORT) ||
-			(connector_id == CONNECTOR_ID_EDP)) {
+		enum signal_type signal = dc->links[i]->connector_signal;
 
+		if ((signal == SIGNAL_TYPE_EDP) ||
+			(signal == SIGNAL_TYPE_DISPLAY_PORT))
 			if (!dc->links[i]->wa_flags.dp_keep_receiver_powered)
 				dp_receiver_power_ctrl(dc->links[i], false);
-			if (connector_id == CONNECTOR_ID_EDP)
-				signal = SIGNAL_TYPE_EDP;
-		}
 
 		dc->links[i]->link_enc->funcs->disable_output(
 				dc->links[i]->link_enc, signal);
@@ -1529,18 +1517,6 @@ static struct dc_stream_state *get_edp_stream(struct dc_state *context)
 	return NULL;
 }
 
-static struct dc_link *get_edp_link(struct dc *dc)
-{
-	int i;
-
-	// report any eDP links, even unconnected DDI's
-	for (i = 0; i < dc->link_count; i++) {
-		if (dc->links[i]->connector_signal == SIGNAL_TYPE_EDP)
-			return dc->links[i];
-	}
-	return NULL;
-}
-
 static struct dc_link *get_edp_link_with_sink(
 		struct dc *dc,
 		struct dc_state *context)
@@ -1834,7 +1810,7 @@ static bool should_enable_fbc(struct dc *dc,
 		return false;
 
 	/* PSR should not be enabled */
-	if (pipe_ctx->stream->link->psr_enabled)
+	if (pipe_ctx->stream->link->psr_feature_enabled)
 		return false;
 
 	/* Nothing to compress */
@@ -2464,7 +2440,6 @@ static void dce110_program_front_end_for_pipe(
 		struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct mem_input *mi = pipe_ctx->plane_res.mi;
-	struct pipe_ctx *old_pipe = NULL;
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
@@ -2472,9 +2447,6 @@ static void dce110_program_front_end_for_pipe(
 	DC_LOGGER_INIT();
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
 
-	if (dc->current_state)
-		old_pipe = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
-
 	memset(&adjust, 0, sizeof(adjust));
 	adjust.gamut_adjust_type = GRAPHICS_GAMUT_ADJUST_TYPE_BYPASS;
 
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 89620adc81d8..83a4dbf6d76e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -275,6 +275,14 @@ static const struct dce_stream_encoder_mask se_mask = {
 		SE_COMMON_MASK_SH_LIST_DCE110(_MASK)
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCE_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCE_AUX_MASK_SH_LIST(_MASK)
+};
+
 #define opp_regs(id)\
 [id] = {\
 	OPP_DCE_110_REG_LIST(id),\
@@ -440,6 +448,37 @@ static const struct dc_plane_cap underlay_plane_cap = {
 #define CC_DC_HDMI_STRAPS__AUDIO_STREAM_NUMBER__SHIFT 0x8
 #endif
 
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		return 6;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 static void read_dce_straps(
 	struct dc_context *ctx,
 	struct resource_straps *straps)
@@ -617,14 +656,18 @@ static struct link_encoder *dce110_link_encoder_create(
 {
 	struct dce110_link_encoder *enc110 =
 		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc110)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dce110_link_encoder_construct(enc110,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
@@ -657,7 +700,10 @@ struct dce_aux *dce110_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -1293,6 +1339,7 @@ static bool construct(
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.is_apu = true;
+	dc->caps.extended_aux_timeout_support = false;
 
 	/*************************************************
 	 *  Create resources                             *
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 21a657e79306..97dcc5d0862b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -172,6 +172,14 @@ static const struct dce_abm_mask abm_mask = {
 		ABM_MASK_SH_LIST_DCE110(_MASK)
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCE_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCE_AUX_MASK_SH_LIST(_MASK)
+};
+
 #define ipp_regs(id)\
 [id] = {\
 		IPP_DCE110_REG_LIST_DCE_BASE(id)\
@@ -417,6 +425,37 @@ static const struct dc_plane_cap plane_cap = {
 #define CC_DC_HDMI_STRAPS__AUDIO_STREAM_NUMBER__SHIFT 0x8
 #endif
 
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		return 6;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 static void read_dce_straps(
 	struct dc_context *ctx,
 	struct resource_straps *straps)
@@ -575,14 +614,18 @@ struct link_encoder *dce112_link_encoder_create(
 {
 	struct dce110_link_encoder *enc110 =
 		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc110)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dce110_link_encoder_construct(enc110,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
@@ -630,7 +673,10 @@ struct dce_aux *dce112_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -1163,7 +1209,7 @@ static bool construct(
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
-
+	dc->caps.extended_aux_timeout_support = false;
 
 	/*************************************************
 	 *  Create resources                             *
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 7c52f7f9196c..63543f6918ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -293,6 +293,14 @@ static const struct dce_stream_encoder_mask se_mask = {
 		SE_COMMON_MASK_SH_LIST_DCE120(_MASK)
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCE12_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCE12_AUX_MASK_SH_LIST(_MASK)
+};
+
 #define opp_regs(id)\
 [id] = {\
 	OPP_DCE_120_REG_LIST(id),\
@@ -356,6 +364,37 @@ static const struct dce_audio_mask audio_mask = {
 		DCE120_AUD_COMMON_MASK_SH_LIST(_MASK)
 };
 
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		return 6;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 #define clk_src_regs(index, id)\
 [index] = {\
 	CS_COMMON_REG_LIST_DCE_112(id),\
@@ -404,7 +443,10 @@ struct dce_aux *dce120_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -655,14 +697,18 @@ static struct link_encoder *dce120_link_encoder_create(
 {
 	struct dce110_link_encoder *enc110 =
 		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc110)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dce110_link_encoder_construct(enc110,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
 
@@ -1006,7 +1052,7 @@ static bool construct(
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
 	dc->caps.psp_setup_panel_mode = true;
-
+	dc->caps.extended_aux_timeout_support = false;
 	dc->debug = debug_defaults;
 
 	/*************************************************
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 643ccb0ade00..3e8d4b49f279 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -288,6 +288,14 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_80(_MASK)
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCE10_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCE10_AUX_MASK_SH_LIST(_MASK)
+};
+
 #define aux_engine_regs(id)\
 [id] = {\
 	AUX_COMMON_REG_LIST(id), \
@@ -431,6 +439,37 @@ static const struct dce_abm_mask abm_mask = {
 #define CC_DC_HDMI_STRAPS__AUDIO_STREAM_NUMBER__SHIFT 0x8
 #endif
 
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		return 6;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 static void read_dce_straps(
 	struct dc_context *ctx,
 	struct resource_straps *straps)
@@ -491,7 +530,10 @@ struct dce_aux *dce80_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -669,14 +711,18 @@ struct link_encoder *dce80_link_encoder_create(
 {
 	struct dce110_link_encoder *enc110 =
 		kzalloc(sizeof(struct dce110_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc110)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dce110_link_encoder_construct(enc110,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source]);
 	return &enc110->base;
@@ -895,6 +941,7 @@ static bool dce80_construct(
 	dc->caps.i2c_speed_in_khz = 40;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
+	dc->caps.extended_aux_timeout_support = false;
 
 	/*************************************************
 	 *  Create resources                             *
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index 01c7e30b9ce1..bbd6e01b3eca 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -393,6 +393,10 @@ bool cm_helper_translate_curve_to_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	// All 3 color channels have same x
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
@@ -464,13 +468,6 @@ bool cm_helper_translate_curve_to_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
@@ -562,6 +559,10 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
 	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
 
+	rgb_resulted[hw_points].red = rgb_resulted[hw_points - 1].red;
+	rgb_resulted[hw_points].green = rgb_resulted[hw_points - 1].green;
+	rgb_resulted[hw_points].blue = rgb_resulted[hw_points - 1].blue;
+
 	corner_points[0].red.x = dc_fixpt_pow(dc_fixpt_from_int(2),
 					     dc_fixpt_from_int(region_start));
 	corner_points[0].green.x = corner_points[0].red.x;
@@ -624,13 +625,6 @@ bool cm_helper_translate_curve_to_degamma_hw_format(
 
 	i = 1;
 	while (i != hw_points + 1) {
-		if (dc_fixpt_lt(rgb_plus_1->red, rgb->red))
-			rgb_plus_1->red = rgb->red;
-		if (dc_fixpt_lt(rgb_plus_1->green, rgb->green))
-			rgb_plus_1->green = rgb->green;
-		if (dc_fixpt_lt(rgb_plus_1->blue, rgb->blue))
-			rgb_plus_1->blue = rgb->blue;
-
 		rgb->delta_red   = dc_fixpt_sub(rgb_plus_1->red,   rgb->red);
 		rgb->delta_green = dc_fixpt_sub(rgb_plus_1->green, rgb->green);
 		rgb->delta_blue  = dc_fixpt_sub(rgb_plus_1->blue,  rgb->blue);
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 d8b2da18db39..997e9582edc7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -129,7 +129,7 @@ void dpp_set_gamut_remap_bypass(struct dcn10_dpp *dpp)
 
 #define IDENTITY_RATIO(ratio) (dc_fixpt_u2d19(ratio) == (1 << 19))
 
-static bool dpp_get_optimal_number_of_taps(
+bool dpp1_get_optimal_number_of_taps(
 		struct dpp *dpp,
 		struct scaler_data *scl_data,
 		const struct scaling_taps *in_taps)
@@ -521,7 +521,7 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_read_state = dpp_read_state,
 		.dpp_reset = dpp_reset,
 		.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
-		.dpp_get_optimal_number_of_taps = dpp_get_optimal_number_of_taps,
+		.dpp_get_optimal_number_of_taps = dpp1_get_optimal_number_of_taps,
 		.dpp_set_gamut_remap = dpp1_cm_set_gamut_remap,
 		.dpp_set_csc_adjustment = dpp1_cm_set_output_csc_adjustment,
 		.dpp_set_csc_default = dpp1_cm_set_output_csc_default,
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 e2c613611ac9..1d4a7d640334 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -1504,6 +1504,11 @@ void dpp1_set_hdr_multiplier(
 		struct dpp *dpp_base,
 		uint32_t multiplier);
 
+bool dpp1_get_optimal_number_of_taps(
+		struct dpp *dpp,
+		struct scaler_data *scl_data,
+		const struct scaling_taps *in_taps);
+
 void dpp1_construct(struct dcn10_dpp *dpp1,
 	struct dc_context *ctx,
 	uint32_t inst,
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 001db49e4bb2..14d1be6c66e6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -841,6 +841,14 @@ void min_set_viewport(
 	REG_SET_2(DCSURF_PRI_VIEWPORT_START_C, 0,
 		  PRI_VIEWPORT_X_START_C, viewport_c->x,
 		  PRI_VIEWPORT_Y_START_C, viewport_c->y);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_DIMENSION_C, 0,
+		  SEC_VIEWPORT_WIDTH_C, viewport_c->width,
+		  SEC_VIEWPORT_HEIGHT_C, viewport_c->height);
+
+	REG_SET_2(DCSURF_SEC_VIEWPORT_START_C, 0,
+		  SEC_VIEWPORT_X_START_C, viewport_c->x,
+		  SEC_VIEWPORT_Y_START_C, viewport_c->y);
 }
 
 void hubp1_read_state_common(struct hubp *hubp)
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 cb20d10288c0..ae70d9c0aa1d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -47,6 +47,8 @@
 	SRI(DCSURF_SEC_VIEWPORT_START, HUBP, id), \
 	SRI(DCSURF_PRI_VIEWPORT_DIMENSION_C, HUBP, id), \
 	SRI(DCSURF_PRI_VIEWPORT_START_C, HUBP, id), \
+	SRI(DCSURF_SEC_VIEWPORT_DIMENSION_C, HUBP, id), \
+	SRI(DCSURF_SEC_VIEWPORT_START_C, HUBP, id), \
 	SRI(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, HUBPREQ, id),\
 	SRI(DCSURF_PRIMARY_SURFACE_ADDRESS, HUBPREQ, id),\
 	SRI(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, HUBPREQ, id),\
@@ -57,8 +59,12 @@
 	SRI(DCSURF_SECONDARY_META_SURFACE_ADDRESS, HUBPREQ, id),\
 	SRI(DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id),\
 	SRI(DCSURF_PRIMARY_SURFACE_ADDRESS_C, HUBPREQ, id),\
+	SRI(DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id),\
+	SRI(DCSURF_SECONDARY_SURFACE_ADDRESS_C, HUBPREQ, id),\
 	SRI(DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id),\
 	SRI(DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, HUBPREQ, id),\
+	SRI(DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH_C, HUBPREQ, id),\
+	SRI(DCSURF_SECONDARY_META_SURFACE_ADDRESS_C, HUBPREQ, id),\
 	SRI(DCSURF_SURFACE_INUSE, HUBPREQ, id),\
 	SRI(DCSURF_SURFACE_INUSE_HIGH, HUBPREQ, id),\
 	SRI(DCSURF_SURFACE_INUSE_C, HUBPREQ, id),\
@@ -150,6 +156,8 @@
 	uint32_t DCSURF_SEC_VIEWPORT_START; \
 	uint32_t DCSURF_PRI_VIEWPORT_DIMENSION_C; \
 	uint32_t DCSURF_PRI_VIEWPORT_START_C; \
+	uint32_t DCSURF_SEC_VIEWPORT_DIMENSION_C; \
+	uint32_t DCSURF_SEC_VIEWPORT_START_C; \
 	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH; \
 	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS; \
 	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH; \
@@ -160,8 +168,12 @@
 	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS; \
 	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C; \
 	uint32_t DCSURF_PRIMARY_SURFACE_ADDRESS_C; \
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH_C; \
+	uint32_t DCSURF_SECONDARY_SURFACE_ADDRESS_C; \
 	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C; \
 	uint32_t DCSURF_PRIMARY_META_SURFACE_ADDRESS_C; \
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH_C; \
+	uint32_t DCSURF_SECONDARY_META_SURFACE_ADDRESS_C; \
 	uint32_t DCSURF_SURFACE_INUSE; \
 	uint32_t DCSURF_SURFACE_INUSE_HIGH; \
 	uint32_t DCSURF_SURFACE_INUSE_C; \
@@ -279,6 +291,10 @@
 	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_C, PRI_VIEWPORT_HEIGHT_C, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_START_C, PRI_VIEWPORT_X_START_C, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_PRI_VIEWPORT_START_C, PRI_VIEWPORT_Y_START_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_DIMENSION_C, SEC_VIEWPORT_WIDTH_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_DIMENSION_C, SEC_VIEWPORT_HEIGHT_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_START_C, SEC_VIEWPORT_X_START_C, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SEC_VIEWPORT_START_C, SEC_VIEWPORT_Y_START_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH, PRIMARY_SURFACE_ADDRESS_HIGH, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS, PRIMARY_SURFACE_ADDRESS, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH, SECONDARY_SURFACE_ADDRESS_HIGH, mask_sh),\
@@ -289,8 +305,12 @@
 	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS, SECONDARY_META_SURFACE_ADDRESS, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_HIGH_C, PRIMARY_SURFACE_ADDRESS_HIGH_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_SURFACE_ADDRESS_C, PRIMARY_SURFACE_ADDRESS_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS_HIGH_C, SECONDARY_SURFACE_ADDRESS_HIGH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_SURFACE_ADDRESS_C, SECONDARY_SURFACE_ADDRESS_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_HIGH_C, PRIMARY_META_SURFACE_ADDRESS_HIGH_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_PRIMARY_META_SURFACE_ADDRESS_C, PRIMARY_META_SURFACE_ADDRESS_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS_HIGH_C, SECONDARY_META_SURFACE_ADDRESS_HIGH_C, mask_sh),\
+	HUBP_SF(HUBPREQ0_DCSURF_SECONDARY_META_SURFACE_ADDRESS_C, SECONDARY_META_SURFACE_ADDRESS_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE, SURFACE_INUSE_ADDRESS, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_HIGH, SURFACE_INUSE_ADDRESS_HIGH, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_INUSE_C, SURFACE_INUSE_ADDRESS_C, mask_sh),\
@@ -469,6 +489,10 @@
 	type PRI_VIEWPORT_HEIGHT_C; \
 	type PRI_VIEWPORT_X_START_C; \
 	type PRI_VIEWPORT_Y_START_C; \
+	type SEC_VIEWPORT_WIDTH_C; \
+	type SEC_VIEWPORT_HEIGHT_C; \
+	type SEC_VIEWPORT_X_START_C; \
+	type SEC_VIEWPORT_Y_START_C; \
 	type PRIMARY_SURFACE_ADDRESS_HIGH;\
 	type PRIMARY_SURFACE_ADDRESS;\
 	type SECONDARY_SURFACE_ADDRESS_HIGH;\
@@ -479,8 +503,12 @@
 	type SECONDARY_META_SURFACE_ADDRESS;\
 	type PRIMARY_SURFACE_ADDRESS_HIGH_C;\
 	type PRIMARY_SURFACE_ADDRESS_C;\
+	type SECONDARY_SURFACE_ADDRESS_HIGH_C;\
+	type SECONDARY_SURFACE_ADDRESS_C;\
 	type PRIMARY_META_SURFACE_ADDRESS_HIGH_C;\
 	type PRIMARY_META_SURFACE_ADDRESS_C;\
+	type SECONDARY_META_SURFACE_ADDRESS_HIGH_C;\
+	type SECONDARY_META_SURFACE_ADDRESS_C;\
 	type SURFACE_INUSE_ADDRESS;\
 	type SURFACE_INUSE_ADDRESS_HIGH;\
 	type SURFACE_INUSE_ADDRESS_C;\
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 60123db7ba02..eb91432621ab 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
@@ -670,6 +670,10 @@ static void dcn10_bios_golden_init(struct dc *dc)
 	int i;
 	bool allow_self_fresh_force_enable = true;
 
+#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+	if (dc->hwss.s0i3_golden_init_wa && dc->hwss.s0i3_golden_init_wa(dc))
+		return;
+#endif
 	if (dc->res_pool->hubbub->funcs->is_allow_self_refresh_enabled)
 		allow_self_fresh_force_enable =
 				dc->res_pool->hubbub->funcs->is_allow_self_refresh_enabled(dc->res_pool->hubbub);
@@ -1300,6 +1304,10 @@ static void dcn10_init_hw(struct dc *dc)
 	}
 
 	dc->hwss.enable_power_gating_plane(dc->hwseq, true);
+
+	if (dc->clk_mgr->funcs->notify_wm_ranges)
+		dc->clk_mgr->funcs->notify_wm_ranges(dc->clk_mgr);
+
 }
 
 static void dcn10_reset_hw_ctx_wrap(
@@ -1452,15 +1460,15 @@ static void log_tf(struct dc_context *ctx,
 	DC_LOG_ALL_TF_CHANNELS("Logging all channels...");
 
 	for (i = 0; i < hw_points_num; i++) {
-		DC_LOG_GAMMA("R\t%d\t%llu\n", i, tf->tf_pts.red[i].value);
-		DC_LOG_ALL_TF_CHANNELS("G\t%d\t%llu\n", i, tf->tf_pts.green[i].value);
-		DC_LOG_ALL_TF_CHANNELS("B\t%d\t%llu\n", i, tf->tf_pts.blue[i].value);
+		DC_LOG_GAMMA("R\t%d\t%llu", i, tf->tf_pts.red[i].value);
+		DC_LOG_ALL_TF_CHANNELS("G\t%d\t%llu", i, tf->tf_pts.green[i].value);
+		DC_LOG_ALL_TF_CHANNELS("B\t%d\t%llu", i, tf->tf_pts.blue[i].value);
 	}
 
 	for (i = hw_points_num; i < MAX_NUM_HW_POINTS; i++) {
-		DC_LOG_ALL_GAMMA("R\t%d\t%llu\n", i, tf->tf_pts.red[i].value);
-		DC_LOG_ALL_TF_CHANNELS("G\t%d\t%llu\n", i, tf->tf_pts.green[i].value);
-		DC_LOG_ALL_TF_CHANNELS("B\t%d\t%llu\n", i, tf->tf_pts.blue[i].value);
+		DC_LOG_ALL_GAMMA("R\t%d\t%llu", i, tf->tf_pts.red[i].value);
+		DC_LOG_ALL_TF_CHANNELS("G\t%d\t%llu", i, tf->tf_pts.green[i].value);
+		DC_LOG_ALL_TF_CHANNELS("B\t%d\t%llu", i, tf->tf_pts.blue[i].value);
 	}
 }
 
@@ -2304,8 +2312,7 @@ void update_dchubp_dpp(
 			dc->res_pool->dccg->funcs->update_dpp_dto(
 					dc->res_pool->dccg,
 					dpp->inst,
-					pipe_ctx->plane_res.bw.dppclk_khz,
-					false);
+					pipe_ctx->plane_res.bw.dppclk_khz);
 		else
 			dc->clk_mgr->clks.dppclk_khz = should_divided_by_2 ?
 						dc->clk_mgr->clks.dispclk_khz / 2 :
@@ -2512,8 +2519,10 @@ static void program_all_pipe_in_tree(
 		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
 				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
 
-		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+		if (dc->hwss.setup_vupdate_interrupt)
+			dc->hwss.setup_vupdate_interrupt(pipe_ctx);
 
+		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
 	}
 
 	if (pipe_ctx->plane_state != NULL)
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 8bf5f0f2301d..88fcc395adf5 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
@@ -113,6 +113,20 @@ struct dcn10_link_enc_registers {
 	uint32_t DIG_LANE_ENABLE;
 	/* UNIPHY */
 	uint32_t CHANNEL_XBAR_CNTL;
+	/* DPCS */
+	uint32_t RDPCSTX_PHY_CNTL3;
+	uint32_t RDPCSTX_PHY_CNTL4;
+	uint32_t RDPCSTX_PHY_CNTL5;
+	uint32_t RDPCSTX_PHY_CNTL6;
+	uint32_t RDPCSTX_PHY_CNTL7;
+	uint32_t RDPCSTX_PHY_CNTL8;
+	uint32_t RDPCSTX_PHY_CNTL9;
+	uint32_t RDPCSTX_PHY_CNTL10;
+	uint32_t RDPCSTX_PHY_CNTL11;
+	uint32_t RDPCSTX_PHY_CNTL12;
+	uint32_t RDPCSTX_PHY_CNTL13;
+	uint32_t RDPCSTX_PHY_CNTL14;
+	uint32_t RDPCSTX_PHY_CNTL15;
 	/* indirect registers */
 	uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_2;
 	uint32_t RAWLANE0_DIG_PCS_XF_RX_OVRD_IN_3;
@@ -250,6 +264,10 @@ struct dcn10_link_enc_registers {
 		type RDPCS_EXT_REFCLK_EN;\
 		type RDPCS_TX_FIFO_EN;\
 		type UNIPHY_LINK_ENABLE;\
+		type UNIPHY_CHANNEL0_XBAR_SOURCE;\
+		type UNIPHY_CHANNEL1_XBAR_SOURCE;\
+		type UNIPHY_CHANNEL2_XBAR_SOURCE;\
+		type UNIPHY_CHANNEL3_XBAR_SOURCE;\
 		type UNIPHY_CHANNEL0_INVERT;\
 		type UNIPHY_CHANNEL1_INVERT;\
 		type UNIPHY_CHANNEL2_INVERT;\
@@ -337,16 +355,46 @@ struct dcn10_link_enc_registers {
 		type RDPCS_TX_FIFO_ERROR_MASK;\
 		type RDPCS_DPALT_DISABLE_TOGGLE_MASK;\
 		type RDPCS_DPALT_4LANE_TOGGLE_MASK;\
+		type RDPCS_PHY_DPALT_DP4;\
 		type RDPCS_PHY_DPALT_DISABLE;\
 		type RDPCS_PHY_DPALT_DISABLE_ACK;\
 		type RDPCS_PHY_DP_MPLLB_V2I;\
 		type RDPCS_PHY_DP_MPLLB_FREQ_VCO;\
+		type RDPCS_PHY_DP_MPLLB_CP_INT_GS;\
+		type RDPCS_PHY_RX_VREF_CTRL;\
 		type RDPCS_PHY_DP_MPLLB_CP_INT;\
 		type RDPCS_PHY_DP_MPLLB_CP_PROP;\
 		type RDPCS_PHY_RX_REF_LD_VAL;\
 		type RDPCS_PHY_RX_VCO_LD_VAL;\
 		type DPCSTX_DEBUG_CONFIG; \
-		type RDPCSTX_DEBUG_CONFIG
+		type RDPCSTX_DEBUG_CONFIG; \
+		type RDPCS_PHY_DP_TX0_EQ_MAIN;\
+		type RDPCS_PHY_DP_TX0_EQ_PRE;\
+		type RDPCS_PHY_DP_TX0_EQ_POST;\
+		type RDPCS_PHY_DP_TX1_EQ_MAIN;\
+		type RDPCS_PHY_DP_TX1_EQ_PRE;\
+		type RDPCS_PHY_DP_TX1_EQ_POST;\
+		type RDPCS_PHY_DP_TX2_EQ_MAIN;\
+		type RDPCS_PHY_DP_MPLLB_CP_PROP_GS;\
+		type RDPCS_PHY_DP_TX2_EQ_PRE;\
+		type RDPCS_PHY_DP_TX2_EQ_POST;\
+		type RDPCS_PHY_DP_TX3_EQ_MAIN;\
+		type RDPCS_PHY_DCO_RANGE;\
+		type RDPCS_PHY_DCO_FINETUNE;\
+		type RDPCS_PHY_DP_TX3_EQ_PRE;\
+		type RDPCS_PHY_DP_TX3_EQ_POST;\
+		type RDPCS_PHY_SUP_PRE_HP;\
+		type RDPCS_PHY_DP_TX0_VREGDRV_BYP;\
+		type RDPCS_PHY_DP_TX1_VREGDRV_BYP;\
+		type RDPCS_PHY_DP_TX2_VREGDRV_BYP;\
+		type RDPCS_PHY_DP_TX3_VREGDRV_BYP;\
+		type RDPCS_DMCU_DPALT_DIS_BLOCK_REG;\
+		type UNIPHYA_SOFT_RESET;\
+		type UNIPHYB_SOFT_RESET;\
+		type UNIPHYC_SOFT_RESET;\
+		type UNIPHYD_SOFT_RESET;\
+		type UNIPHYE_SOFT_RESET;\
+		type UNIPHYF_SOFT_RESET
 
 #define DCN20_LINK_ENCODER_REG_FIELD_LIST(type) \
 	type DIG_LANE0EN;\
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 e9ebbbe256b4..0a9ad692f541 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -168,7 +168,10 @@ static void opp1_set_pixel_encoding(
 		REG_UPDATE(FMT_CONTROL, FMT_PIXEL_ENCODING, 0);
 		break;
 	case PIXEL_ENCODING_YCBCR422:
-		REG_UPDATE(FMT_CONTROL, FMT_PIXEL_ENCODING, 1);
+		REG_UPDATE_3(FMT_CONTROL,
+				FMT_PIXEL_ENCODING, 1,
+				FMT_SUBSAMPLING_MODE, 2,
+				FMT_CBCR_BIT_REDUCTION_BYPASS, 0);
 		break;
 	case PIXEL_ENCODING_YCBCR420:
 		REG_UPDATE(FMT_CONTROL, FMT_PIXEL_ENCODING, 2);
@@ -237,6 +240,9 @@ void opp1_set_dyn_expansion(
 			FMT_DYNAMIC_EXP_EN, 0,
 			FMT_DYNAMIC_EXP_MODE, 0);
 
+	if (opp->dyn_expansion == DYN_EXPANSION_DISABLE)
+		return;
+
 	/*00 - 10-bit -> 12-bit dynamic expansion*/
 	/*01 - 8-bit  -> 12-bit dynamic expansion*/
 	if (signal == SIGNAL_TYPE_HDMI_TYPE_A ||
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h
index 0f10adea000c..2c0ecfa5a643 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.h
@@ -116,6 +116,8 @@
 	type FMT_RAND_G_SEED; \
 	type FMT_RAND_B_SEED; \
 	type FMT_PIXEL_ENCODING; \
+	type FMT_SUBSAMPLING_MODE; \
+	type FMT_CBCR_BIT_REDUCTION_BYPASS; \
 	type FMT_CLAMP_DATA_EN; \
 	type FMT_CLAMP_COLOR_FORMAT; \
 	type FMT_DYNAMIC_EXP_EN; \
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 e74a07d03fde..dabccbd49ad4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -1230,59 +1230,25 @@ bool optc1_is_stereo_left_eye(struct timing_generator *optc)
 	return ret;
 }
 
-bool optc1_is_matching_timing(struct timing_generator *tg,
-		const struct dc_crtc_timing *otg_timing)
+bool optc1_get_hw_timing(struct timing_generator *tg,
+		struct dc_crtc_timing *hw_crtc_timing)
 {
-	struct dc_crtc_timing hw_crtc_timing = {0};
 	struct dcn_otg_state s = {0};
 
-	if (tg == NULL || otg_timing == NULL)
+	if (tg == NULL || hw_crtc_timing == NULL)
 		return false;
 
 	optc1_read_otg_state(DCN10TG_FROM_TG(tg), &s);
 
-	hw_crtc_timing.h_total = s.h_total + 1;
-	hw_crtc_timing.h_addressable = s.h_total - ((s.h_total - s.h_blank_start) + s.h_blank_end);
-	hw_crtc_timing.h_front_porch = s.h_total + 1 - s.h_blank_start;
-	hw_crtc_timing.h_sync_width = s.h_sync_a_end - s.h_sync_a_start;
+	hw_crtc_timing->h_total = s.h_total + 1;
+	hw_crtc_timing->h_addressable = s.h_total - ((s.h_total - s.h_blank_start) + s.h_blank_end);
+	hw_crtc_timing->h_front_porch = s.h_total + 1 - s.h_blank_start;
+	hw_crtc_timing->h_sync_width = s.h_sync_a_end - s.h_sync_a_start;
 
-	hw_crtc_timing.v_total = s.v_total + 1;
-	hw_crtc_timing.v_addressable = s.v_total - ((s.v_total - s.v_blank_start) + s.v_blank_end);
-	hw_crtc_timing.v_front_porch = s.v_total + 1 - s.v_blank_start;
-	hw_crtc_timing.v_sync_width = s.v_sync_a_end - s.v_sync_a_start;
-
-	if (otg_timing->h_total != hw_crtc_timing.h_total)
-		return false;
-
-	if (otg_timing->h_border_left != hw_crtc_timing.h_border_left)
-		return false;
-
-	if (otg_timing->h_addressable != hw_crtc_timing.h_addressable)
-		return false;
-
-	if (otg_timing->h_border_right != hw_crtc_timing.h_border_right)
-		return false;
-
-	if (otg_timing->h_front_porch != hw_crtc_timing.h_front_porch)
-		return false;
-
-	if (otg_timing->h_sync_width != hw_crtc_timing.h_sync_width)
-		return false;
-
-	if (otg_timing->v_total != hw_crtc_timing.v_total)
-		return false;
-
-	if (otg_timing->v_border_top != hw_crtc_timing.v_border_top)
-		return false;
-
-	if (otg_timing->v_addressable != hw_crtc_timing.v_addressable)
-		return false;
-
-	if (otg_timing->v_border_bottom != hw_crtc_timing.v_border_bottom)
-		return false;
-
-	if (otg_timing->v_sync_width != hw_crtc_timing.v_sync_width)
-		return false;
+	hw_crtc_timing->v_total = s.v_total + 1;
+	hw_crtc_timing->v_addressable = s.v_total - ((s.v_total - s.v_blank_start) + s.v_blank_end);
+	hw_crtc_timing->v_front_porch = s.v_total + 1 - s.v_blank_start;
+	hw_crtc_timing->v_sync_width = s.v_sync_a_end - s.v_sync_a_start;
 
 	return true;
 }
@@ -1486,7 +1452,6 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.get_frame_count = optc1_get_vblank_counter,
 		.get_scanoutpos = optc1_get_crtc_scanoutpos,
 		.get_otg_active_size = optc1_get_otg_active_size,
-		.is_matching_timing = optc1_is_matching_timing,
 		.set_early_control = optc1_set_early_control,
 		/* used by enable_timing_synchronization. Not need for FPGA */
 		.wait_for_state = optc1_wait_for_state,
@@ -1514,7 +1479,8 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.configure_crc = optc1_configure_crc,
 		.set_vtg_params = optc1_set_vtg_params,
 		.program_manual_trigger = optc1_program_manual_trigger,
-		.setup_manual_trigger = optc1_setup_manual_trigger
+		.setup_manual_trigger = optc1_setup_manual_trigger,
+		.get_hw_timing = optc1_get_hw_timing,
 };
 
 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 83575599672e..c8d795b335ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -547,9 +547,8 @@ struct dcn_otg_state {
 void optc1_read_otg_state(struct optc *optc1,
 		struct dcn_otg_state *s);
 
-bool optc1_is_matching_timing(
-	struct timing_generator *tg,
-	const struct dc_crtc_timing *otg_timing);
+bool optc1_get_hw_timing(struct timing_generator *tg,
+		struct dc_crtc_timing *hw_crtc_timing);
 
 bool optc1_validate_timing(
 	struct timing_generator *optc,
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 1599bb971111..15640aedd664 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -319,6 +319,14 @@ static const struct dcn10_link_enc_mask le_mask = {
 		LINK_ENCODER_MASK_SH_LIST_DCN10(_MASK)
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCN10_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCN10_AUX_MASK_SH_LIST(_MASK)
+};
+
 #define ipp_regs(id)\
 [id] = {\
 	IPP_REG_LIST_DCN10(id),\
@@ -471,6 +479,28 @@ static const struct dcn_hubbub_mask hubbub_mask = {
 		HUBBUB_MASK_SH_LIST_DCN10(_MASK)
 };
 
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 #define clk_src_regs(index, pllid)\
 [index] = {\
 	CS_COMMON_REG_LIST_DCN1_0(index, pllid),\
@@ -642,7 +672,10 @@ struct dce_aux *dcn10_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -751,14 +784,18 @@ struct link_encoder *dcn10_link_encoder_create(
 {
 	struct dcn10_link_encoder *enc10 =
 		kzalloc(sizeof(struct dcn10_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc10)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dcn10_link_encoder_construct(enc10,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source],
 				      &le_shift,
@@ -1308,6 +1345,8 @@ static bool construct(
 	dc->caps.max_slave_planes = 1;
 	dc->caps.is_apu = true;
 	dc->caps.post_blend_color_processing = false;
+	dc->caps.extended_aux_timeout_support = false;
+
 	/* Raven DP PHY HBR2 eye diagram pattern is not stable. Use TP4 */
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 9aa258f3550b..06e5bbb4545c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -1553,6 +1553,66 @@ unsigned int enc1_dig_source_otg(
 	return tg_inst;
 }
 
+bool enc1_stream_encoder_dp_get_pixel_format(
+	struct stream_encoder *enc,
+	enum dc_pixel_encoding *encoding,
+	enum dc_color_depth *depth)
+{
+	uint32_t hw_encoding = 0;
+	uint32_t hw_depth = 0;
+	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
+
+	if (enc == NULL ||
+		encoding == NULL ||
+		depth == NULL)
+		return false;
+
+	REG_GET_2(DP_PIXEL_FORMAT,
+		DP_PIXEL_ENCODING, &hw_encoding,
+		DP_COMPONENT_DEPTH, &hw_depth);
+
+	switch (hw_depth) {
+	case DP_COMPONENT_PIXEL_DEPTH_6BPC:
+		*depth = COLOR_DEPTH_666;
+		break;
+	case DP_COMPONENT_PIXEL_DEPTH_8BPC:
+		*depth = COLOR_DEPTH_888;
+		break;
+	case DP_COMPONENT_PIXEL_DEPTH_10BPC:
+		*depth = COLOR_DEPTH_101010;
+		break;
+	case DP_COMPONENT_PIXEL_DEPTH_12BPC:
+		*depth = COLOR_DEPTH_121212;
+		break;
+	case DP_COMPONENT_PIXEL_DEPTH_16BPC:
+		*depth = COLOR_DEPTH_161616;
+		break;
+	default:
+		*depth = COLOR_DEPTH_UNDEFINED;
+		break;
+	}
+
+	switch (hw_encoding) {
+	case DP_PIXEL_ENCODING_TYPE_RGB444:
+		*encoding = PIXEL_ENCODING_RGB;
+		break;
+	case DP_PIXEL_ENCODING_TYPE_YCBCR422:
+		*encoding = PIXEL_ENCODING_YCBCR422;
+		break;
+	case DP_PIXEL_ENCODING_TYPE_YCBCR444:
+	case DP_PIXEL_ENCODING_TYPE_Y_ONLY:
+		*encoding = PIXEL_ENCODING_YCBCR444;
+		break;
+	case DP_PIXEL_ENCODING_TYPE_YCBCR420:
+		*encoding = PIXEL_ENCODING_YCBCR420;
+		break;
+	default:
+		*encoding = PIXEL_ENCODING_UNDEFINED;
+		break;
+	}
+	return true;
+}
+
 static const struct stream_encoder_funcs dcn10_str_enc_funcs = {
 	.dp_set_stream_attribute =
 		enc1_stream_encoder_dp_set_stream_attribute,
@@ -1589,6 +1649,8 @@ static const struct stream_encoder_funcs dcn10_str_enc_funcs = {
 	.dig_connect_to_otg  = enc1_dig_connect_to_otg,
 	.hdmi_reset_stream_attribute = enc1_reset_hdmi_stream_attribute,
 	.dig_source_otg = enc1_dig_source_otg,
+
+	.dp_get_pixel_format  = enc1_stream_encoder_dp_get_pixel_format,
 };
 
 void dcn10_stream_encoder_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
index a512cbea00d1..c9cbc21d121e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.h
@@ -621,4 +621,9 @@ void get_audio_clock_info(
 void enc1_reset_hdmi_stream_attribute(
 	struct stream_encoder *enc);
 
+bool enc1_stream_encoder_dp_get_pixel_format(
+	struct stream_encoder *enc,
+	enum dc_pixel_encoding *encoding,
+	enum dc_color_depth *depth);
+
 #endif /* __DC_STREAM_ENCODER_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
index ddb8d5649e79..63f3bddba7da 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/Makefile
@@ -10,15 +10,20 @@ ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 DCN20 += dcn20_dsc.o
 endif
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -mpreferred-stack-boundary=4
+else
 CFLAGS_$(AMDDALPATH)/dc/dcn20/dcn20_resource.o += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
index 16476ed25536..1e1151356e60 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.c
@@ -44,16 +44,12 @@
 #define DC_LOGGER \
 	dccg->ctx->logger
 
-void dccg2_update_dpp_dto(struct dccg *dccg,
-		int dpp_inst,
-		int req_dppclk,
-		bool reduce_divider_only)
+void dccg2_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk)
 {
 	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
 
 	if (dccg->ref_dppclk && req_dppclk) {
 		int ref_dppclk = dccg->ref_dppclk;
-		int current_phase, current_modulo;
 
 		ASSERT(req_dppclk <= ref_dppclk);
 		/* need to clamp to 8 bits */
@@ -65,28 +61,9 @@ void dccg2_update_dpp_dto(struct dccg *dccg,
 			if (req_dppclk > ref_dppclk)
 				req_dppclk = ref_dppclk;
 		}
-
-		REG_GET_2(DPPCLK_DTO_PARAM[dpp_inst],
-				DPPCLK0_DTO_PHASE, &current_phase,
-				DPPCLK0_DTO_MODULO, &current_modulo);
-
-		if (reduce_divider_only) {
-			// requested phase/modulo greater than current
-			if (req_dppclk * current_modulo >= current_phase * ref_dppclk) {
-				REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
-						DPPCLK0_DTO_PHASE, req_dppclk,
-						DPPCLK0_DTO_MODULO, ref_dppclk);
-			} else {
-				REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
-						DPPCLK0_DTO_PHASE, current_phase,
-						DPPCLK0_DTO_MODULO, current_modulo);
-			}
-		} else {
-			REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
-					DPPCLK0_DTO_PHASE, req_dppclk,
-					DPPCLK0_DTO_MODULO, ref_dppclk);
-		}
-
+		REG_SET_2(DPPCLK_DTO_PARAM[dpp_inst], 0,
+				DPPCLK0_DTO_PHASE, req_dppclk,
+				DPPCLK0_DTO_MODULO, ref_dppclk);
 		REG_UPDATE(DPPCLK_DTO_CTRL,
 				DPPCLK_DTO_ENABLE[dpp_inst], 1);
 	} else {
@@ -119,32 +96,6 @@ void dccg2_get_dccg_ref_freq(struct dccg *dccg,
 
 void dccg2_init(struct dccg *dccg)
 {
-	struct dcn_dccg *dccg_dcn = TO_DCN_DCCG(dccg);
-
-	// Fallthrough intentional to program all available dpp_dto's
-	switch (dccg_dcn->base.ctx->dc->res_pool->pipe_count) {
-	case 6:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[5], 1);
-		/* Fall through */
-	case 5:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[4], 1);
-		/* Fall through */
-	case 4:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[3], 1);
-		/* Fall through */
-	case 3:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[2], 1);
-		/* Fall through */
-	case 2:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[1], 1);
-		/* Fall through */
-	case 1:
-		REG_UPDATE(DPPCLK_DTO_CTRL, DPPCLK_DTO_DB_EN[0], 1);
-		break;
-	default:
-		ASSERT(false);
-		break;
-	}
 }
 
 static const struct dccg_funcs dccg2_funcs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h
index 74a074a873cd..2205cb0204e7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dccg.h
@@ -97,7 +97,7 @@ struct dcn_dccg {
 	const struct dccg_mask *dccg_mask;
 };
 
-void dccg2_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk, bool raise_divider_only);
+void dccg2_update_dpp_dto(struct dccg *dccg, int dpp_inst, int req_dppclk);
 
 void dccg2_get_dccg_ref_freq(struct dccg *dccg,
 		unsigned int xtalin_freq_inKhz,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
index 2f5aade1e882..4d7e45892f08 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.c
@@ -376,13 +376,6 @@ bool dpp2_get_optimal_number_of_taps(
 		struct scaler_data *scl_data,
 		const struct scaling_taps *in_taps)
 {
-	uint32_t pixel_width;
-
-	if (scl_data->viewport.width > scl_data->recout.width)
-		pixel_width = scl_data->recout.width;
-	else
-		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 &&
@@ -464,7 +457,7 @@ static struct dpp_funcs dcn20_dpp_funcs = {
 	.dpp_read_state = dpp20_read_state,
 	.dpp_reset = dpp_reset,
 	.dpp_set_scaler = dpp1_dscl_set_scaler_manual_scale,
-	.dpp_get_optimal_number_of_taps = dpp2_get_optimal_number_of_taps,
+	.dpp_get_optimal_number_of_taps = dpp1_get_optimal_number_of_taps,
 	.dpp_set_gamut_remap = dpp1_cm_set_gamut_remap,
 	.dpp_set_csc_adjustment = NULL,
 	.dpp_set_csc_default = NULL,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
index 290b2854bd2c..5b03b737b1d6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dpp.h
@@ -30,16 +30,20 @@
 #define TO_DCN20_DPP(dpp)\
 	container_of(dpp, struct dcn20_dpp, base)
 
-#define TF_REG_LIST_DCN20(id) \
-	TF_REG_LIST_DCN(id), \
+#define TF_REG_LIST_DCN20_COMMON_UPDATED(id) \
 	SRI(CM_BLNDGAM_LUT_WRITE_EN_MASK, CM, id), \
+	SRI(CM_BLNDGAM_RAMB_SLOPE_CNTL_B, CM, id), \
+	SRI(CM_BLNDGAM_RAMB_SLOPE_CNTL_G, CM, id), \
+	SRI(CM_BLNDGAM_RAMB_SLOPE_CNTL_R, CM, id), \
+	SRI(CM_BLNDGAM_RAMA_SLOPE_CNTL_B, CM, id), \
+	SRI(CM_BLNDGAM_RAMA_SLOPE_CNTL_G, CM, id), \
+	SRI(CM_BLNDGAM_RAMA_SLOPE_CNTL_R, CM, id)
+
+#define TF_REG_LIST_DCN20_COMMON(id) \
 	SRI(CM_BLNDGAM_CONTROL, CM, id), \
 	SRI(CM_BLNDGAM_RAMB_START_CNTL_B, CM, id), \
 	SRI(CM_BLNDGAM_RAMB_START_CNTL_G, CM, id), \
 	SRI(CM_BLNDGAM_RAMB_START_CNTL_R, CM, id), \
-	SRI(CM_BLNDGAM_RAMB_SLOPE_CNTL_B, CM, id), \
-	SRI(CM_BLNDGAM_RAMB_SLOPE_CNTL_G, CM, id), \
-	SRI(CM_BLNDGAM_RAMB_SLOPE_CNTL_R, CM, id), \
 	SRI(CM_BLNDGAM_RAMB_END_CNTL1_B, CM, id), \
 	SRI(CM_BLNDGAM_RAMB_END_CNTL2_B, CM, id), \
 	SRI(CM_BLNDGAM_RAMB_END_CNTL1_G, CM, id), \
@@ -66,9 +70,6 @@
 	SRI(CM_BLNDGAM_RAMA_START_CNTL_B, CM, id), \
 	SRI(CM_BLNDGAM_RAMA_START_CNTL_G, CM, id), \
 	SRI(CM_BLNDGAM_RAMA_START_CNTL_R, CM, id), \
-	SRI(CM_BLNDGAM_RAMA_SLOPE_CNTL_B, CM, id), \
-	SRI(CM_BLNDGAM_RAMA_SLOPE_CNTL_G, CM, id), \
-	SRI(CM_BLNDGAM_RAMA_SLOPE_CNTL_R, CM, id), \
 	SRI(CM_BLNDGAM_RAMA_END_CNTL1_B, CM, id), \
 	SRI(CM_BLNDGAM_RAMA_END_CNTL2_B, CM, id), \
 	SRI(CM_BLNDGAM_RAMA_END_CNTL1_G, CM, id), \
@@ -147,7 +148,12 @@
 	SRI(CM_SHAPER_RAMA_REGION_28_29, CM, id), \
 	SRI(CM_SHAPER_RAMA_REGION_30_31, CM, id), \
 	SRI(CM_SHAPER_RAMA_REGION_32_33, CM, id), \
-	SRI(CM_SHAPER_LUT_INDEX, CM, id), \
+	SRI(CM_SHAPER_LUT_INDEX, CM, id)
+
+#define TF_REG_LIST_DCN20(id) \
+	TF_REG_LIST_DCN(id), \
+	TF_REG_LIST_DCN20_COMMON(id), \
+	TF_REG_LIST_DCN20_COMMON_UPDATED(id), \
 	SRI(CURSOR_CONTROL, CURSOR0_, id), \
 	SRI(ALPHA_2BIT_LUT, CNVC_CFG, id), \
 	SRI(FCNV_FP_BIAS_R, CNVC_CFG, id), \
@@ -166,27 +172,41 @@
 	SRI(OBUF_MEM_PWR_CTRL, DSCL, id),\
 	SRI(DSCL_MEM_PWR_CTRL, DSCL, id)
 
-#define TF_REG_LIST_SH_MASK_DCN20(mask_sh)\
-	TF_REG_LIST_SH_MASK_DCN(mask_sh), \
+
+#define TF_REG_LIST_SH_MASK_DCN20_UPDATED(mask_sh)\
+	TF_SF(CM0_CM_BLNDGAM_RAMB_SLOPE_CNTL_B, CM_BLNDGAM_RAMB_EXP_REGION_LINEAR_SLOPE_B, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMB_SLOPE_CNTL_G, CM_BLNDGAM_RAMB_EXP_REGION_LINEAR_SLOPE_G, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMB_SLOPE_CNTL_R, CM_BLNDGAM_RAMB_EXP_REGION_LINEAR_SLOPE_R, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL1_B, CM_BLNDGAM_RAMB_EXP_REGION_END_B, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL1_G, CM_BLNDGAM_RAMB_EXP_REGION_END_G, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL1_R, CM_BLNDGAM_RAMB_EXP_REGION_END_R, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_SLOPE_CNTL_B, CM_BLNDGAM_RAMA_EXP_REGION_LINEAR_SLOPE_B, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_SLOPE_CNTL_G, CM_BLNDGAM_RAMA_EXP_REGION_LINEAR_SLOPE_G, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_SLOPE_CNTL_R, CM_BLNDGAM_RAMA_EXP_REGION_LINEAR_SLOPE_R, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL1_B, CM_BLNDGAM_RAMA_EXP_REGION_END_B, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL1_G, CM_BLNDGAM_RAMA_EXP_REGION_END_G, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL1_R, CM_BLNDGAM_RAMA_EXP_REGION_END_R, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_B, CM_BLNDGAM_RAMA_EXP_REGION_END_BASE_B, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_G, CM_BLNDGAM_RAMA_EXP_REGION_END_BASE_G, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_R, CM_BLNDGAM_RAMA_EXP_REGION_END_BASE_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_CONTROL, CM_BLNDGAM_LUT_MODE, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_LUT_WRITE_EN_MASK, CM_BLNDGAM_LUT_WRITE_EN_MASK, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_LUT_WRITE_EN_MASK, CM_BLNDGAM_LUT_WRITE_SEL, mask_sh), \
+	TF_SF(CM0_CM_BLNDGAM_LUT_WRITE_EN_MASK, CM_BLNDGAM_CONFIG_STATUS, mask_sh), \
+	TF_SF(CM0_CM_SHAPER_CONTROL, CM_SHAPER_LUT_MODE, mask_sh)
+
+
+#define TF_REG_LIST_SH_MASK_DCN20_COMMON(mask_sh)\
+	TF_SF(CM0_CM_3DLUT_MODE, CM_3DLUT_MODE, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_START_CNTL_B, CM_BLNDGAM_RAMB_EXP_REGION_START_B, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_START_CNTL_B, CM_BLNDGAM_RAMB_EXP_REGION_START_SEGMENT_B, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_START_CNTL_G, CM_BLNDGAM_RAMB_EXP_REGION_START_G, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_START_CNTL_G, CM_BLNDGAM_RAMB_EXP_REGION_START_SEGMENT_G, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_START_CNTL_R, CM_BLNDGAM_RAMB_EXP_REGION_START_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_START_CNTL_R, CM_BLNDGAM_RAMB_EXP_REGION_START_SEGMENT_R, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_SLOPE_CNTL_B, CM_BLNDGAM_RAMB_EXP_REGION_LINEAR_SLOPE_B, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_SLOPE_CNTL_G, CM_BLNDGAM_RAMB_EXP_REGION_LINEAR_SLOPE_G, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_SLOPE_CNTL_R, CM_BLNDGAM_RAMB_EXP_REGION_LINEAR_SLOPE_R, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL1_B, CM_BLNDGAM_RAMB_EXP_REGION_END_B, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL2_B, CM_BLNDGAM_RAMB_EXP_REGION_END_SLOPE_B, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL2_B, CM_BLNDGAM_RAMB_EXP_REGION_END_BASE_B, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL1_G, CM_BLNDGAM_RAMB_EXP_REGION_END_G, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL2_G, CM_BLNDGAM_RAMB_EXP_REGION_END_SLOPE_G, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL2_G, CM_BLNDGAM_RAMB_EXP_REGION_END_BASE_G, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL1_R, CM_BLNDGAM_RAMB_EXP_REGION_END_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL2_R, CM_BLNDGAM_RAMB_EXP_REGION_END_SLOPE_R, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMB_END_CNTL2_R, CM_BLNDGAM_RAMB_EXP_REGION_END_BASE_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_REGION_0_1, CM_BLNDGAM_RAMB_EXP_REGION0_LUT_OFFSET, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_REGION_0_1, CM_BLNDGAM_RAMB_EXP_REGION0_NUM_SEGMENTS, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMB_REGION_0_1, CM_BLNDGAM_RAMB_EXP_REGION1_LUT_OFFSET, mask_sh), \
@@ -261,18 +281,9 @@
 	TF_SF(CM0_CM_BLNDGAM_RAMA_START_CNTL_G, CM_BLNDGAM_RAMA_EXP_REGION_START_SEGMENT_G, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_START_CNTL_R, CM_BLNDGAM_RAMA_EXP_REGION_START_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_START_CNTL_R, CM_BLNDGAM_RAMA_EXP_REGION_START_SEGMENT_R, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_SLOPE_CNTL_B, CM_BLNDGAM_RAMA_EXP_REGION_LINEAR_SLOPE_B, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_SLOPE_CNTL_G, CM_BLNDGAM_RAMA_EXP_REGION_LINEAR_SLOPE_G, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_SLOPE_CNTL_R, CM_BLNDGAM_RAMA_EXP_REGION_LINEAR_SLOPE_R, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL1_B, CM_BLNDGAM_RAMA_EXP_REGION_END_B, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_B, CM_BLNDGAM_RAMA_EXP_REGION_END_SLOPE_B, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_B, CM_BLNDGAM_RAMA_EXP_REGION_END_BASE_B, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL1_G, CM_BLNDGAM_RAMA_EXP_REGION_END_G, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_G, CM_BLNDGAM_RAMA_EXP_REGION_END_SLOPE_G, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_G, CM_BLNDGAM_RAMA_EXP_REGION_END_BASE_G, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL1_R, CM_BLNDGAM_RAMA_EXP_REGION_END_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_R, CM_BLNDGAM_RAMA_EXP_REGION_END_SLOPE_R, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_RAMA_END_CNTL2_R, CM_BLNDGAM_RAMA_EXP_REGION_END_BASE_R, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_REGION_0_1, CM_BLNDGAM_RAMA_EXP_REGION0_LUT_OFFSET, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_REGION_0_1, CM_BLNDGAM_RAMA_EXP_REGION0_NUM_SEGMENTS, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_REGION_0_1, CM_BLNDGAM_RAMA_EXP_REGION1_LUT_OFFSET, mask_sh), \
@@ -341,9 +352,6 @@
 	TF_SF(CM0_CM_BLNDGAM_RAMA_REGION_32_33, CM_BLNDGAM_RAMA_EXP_REGION32_NUM_SEGMENTS, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_REGION_32_33, CM_BLNDGAM_RAMA_EXP_REGION33_LUT_OFFSET, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_RAMA_REGION_32_33, CM_BLNDGAM_RAMA_EXP_REGION33_NUM_SEGMENTS, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_LUT_WRITE_EN_MASK, CM_BLNDGAM_LUT_WRITE_EN_MASK, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_LUT_WRITE_EN_MASK, CM_BLNDGAM_LUT_WRITE_SEL, mask_sh), \
-	TF_SF(CM0_CM_BLNDGAM_LUT_WRITE_EN_MASK, CM_BLNDGAM_CONFIG_STATUS, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_LUT_INDEX, CM_BLNDGAM_LUT_INDEX, mask_sh), \
 	TF_SF(CM0_CM_BLNDGAM_LUT_DATA, CM_BLNDGAM_LUT_DATA, mask_sh), \
 	TF_SF(CM0_CM_MEM_PWR_CTRL, BLNDGAM_MEM_PWR_FORCE, mask_sh), \
@@ -356,7 +364,6 @@
 	TF_SF(CM0_CM_3DLUT_READ_WRITE_CONTROL, CM_3DLUT_WRITE_EN_MASK, mask_sh), \
 	TF_SF(CM0_CM_3DLUT_READ_WRITE_CONTROL, CM_3DLUT_RAM_SEL, mask_sh), \
 	TF_SF(CM0_CM_3DLUT_READ_WRITE_CONTROL, CM_3DLUT_30BIT_EN, mask_sh), \
-	TF_SF(CM0_CM_3DLUT_READ_WRITE_CONTROL, CM_3DLUT_CONFIG_STATUS, mask_sh), \
 	TF_SF(CM0_CM_3DLUT_READ_WRITE_CONTROL, CM_3DLUT_READ_SEL, mask_sh), \
 	TF_SF(CM0_CM_SHAPER_CONTROL, CM_SHAPER_LUT_MODE, mask_sh), \
 	TF_SF(CM0_CM_SHAPER_RAMB_START_CNTL_B, CM_SHAPER_RAMB_EXP_REGION_START_B, mask_sh), \
@@ -521,9 +528,14 @@
 	TF_SF(CM0_CM_SHAPER_RAMA_REGION_32_33, CM_SHAPER_RAMA_EXP_REGION33_NUM_SEGMENTS, mask_sh), \
 	TF_SF(CM0_CM_SHAPER_LUT_WRITE_EN_MASK, CM_SHAPER_LUT_WRITE_EN_MASK, mask_sh), \
 	TF_SF(CM0_CM_SHAPER_LUT_WRITE_EN_MASK, CM_SHAPER_LUT_WRITE_SEL, mask_sh), \
-	TF_SF(CM0_CM_SHAPER_LUT_WRITE_EN_MASK, CM_SHAPER_CONFIG_STATUS, mask_sh), \
 	TF_SF(CM0_CM_SHAPER_LUT_INDEX, CM_SHAPER_LUT_INDEX, mask_sh), \
-	TF_SF(CM0_CM_SHAPER_LUT_DATA, CM_SHAPER_LUT_DATA, mask_sh), \
+	TF_SF(CM0_CM_SHAPER_LUT_DATA, CM_SHAPER_LUT_DATA, mask_sh)
+
+
+#define TF_REG_LIST_SH_MASK_DCN20(mask_sh)\
+	TF_REG_LIST_SH_MASK_DCN(mask_sh), \
+	TF_REG_LIST_SH_MASK_DCN20_COMMON(mask_sh), \
+	TF_REG_LIST_SH_MASK_DCN20_UPDATED(mask_sh), \
 	TF_SF(CM0_CM_DGAM_LUT_WRITE_EN_MASK, CM_DGAM_CONFIG_STATUS, mask_sh), \
 	TF_SF(CM0_CM_CONTROL, CM_BYPASS, mask_sh), \
 	TF_SF(CURSOR0_0_CURSOR_CONTROL, CURSOR_MODE, mask_sh), \
@@ -560,6 +572,7 @@
 	TF_SF(DSCL0_OBUF_MEM_PWR_CTRL, OBUF_MEM_PWR_FORCE, mask_sh),\
 	TF_SF(DSCL0_DSCL_MEM_PWR_CTRL, LUT_MEM_PWR_FORCE, mask_sh)
 
+
 #define TF_REG_FIELD_LIST_DCN2_0(type) \
 	TF_REG_FIELD_LIST(type) \
 	type CM_BLNDGAM_LUT_DATA; \
@@ -593,6 +606,7 @@
 	type OBUF_MEM_PWR_FORCE;\
 	type LUT_MEM_PWR_FORCE
 
+
 struct dcn2_dpp_shift {
 	TF_REG_FIELD_LIST_DCN2_0(uint8_t);
 };
@@ -691,11 +705,6 @@ void dpp2_set_hdr_multiplier(
 		struct dpp *dpp_base,
 		uint32_t multiplier);
 
-bool dpp2_get_optimal_number_of_taps(
-		struct dpp *dpp,
-		struct scaler_data *scl_data,
-		const struct scaling_taps *in_taps);
-
 bool dpp2_construct(struct dcn20_dpp *dpp2,
 	struct dc_context *ctx,
 	uint32_t inst,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
index 1b419407af94..63eb377ed9c0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dsc.c
@@ -118,7 +118,7 @@ static void dsc2_get_enc_caps(struct dsc_enc_caps *dsc_enc_caps, int pixel_clock
 
 	dsc_enc_caps->color_formats.bits.RGB = 1;
 	dsc_enc_caps->color_formats.bits.YCBCR_444 = 1;
-	dsc_enc_caps->color_formats.bits.YCBCR_SIMPLE_422 = 0;
+	dsc_enc_caps->color_formats.bits.YCBCR_SIMPLE_422 = 1;
 	dsc_enc_caps->color_formats.bits.YCBCR_NATIVE_422 = 0;
 	dsc_enc_caps->color_formats.bits.YCBCR_NATIVE_420 = 1;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c
index cd8bc92ce3ba..880954ac0b02 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c
@@ -722,7 +722,6 @@ bool dwb_program_horz_scalar(struct dcn20_dwbc *dwbc20,
 		struct scaling_taps num_taps)
 {
 	uint32_t h_ratio_luma = 1;
-	uint32_t h_ratio_chroma = 1;
 	uint32_t h_taps_luma = num_taps.h_taps;
 	uint32_t h_taps_chroma = num_taps.h_taps_c;
 	int32_t h_init_phase_luma = 0;
@@ -747,7 +746,6 @@ bool dwb_program_horz_scalar(struct dcn20_dwbc *dwbc20,
 		h_ratio_luma = -1;
 	else
 		h_ratio_luma = dc_fixpt_u3d19(tmp_h_ratio_luma) << 5;
-	h_ratio_chroma = h_ratio_luma * 2;
 
 	/*Program ratio*/
 	REG_UPDATE(WBSCL_HORZ_FILTER_SCALE_RATIO, WBSCL_H_SCALE_RATIO, h_ratio_luma);
@@ -803,7 +801,6 @@ bool dwb_program_vert_scalar(struct dcn20_dwbc *dwbc20,
 		enum dwb_subsample_position subsample_position)
 {
 	uint32_t v_ratio_luma = 1;
-	uint32_t v_ratio_chroma = 1;
 	uint32_t v_taps_luma = num_taps.v_taps;
 	uint32_t v_taps_chroma = num_taps.v_taps_c;
 	int32_t v_init_phase_luma = 0;
@@ -827,7 +824,6 @@ bool dwb_program_vert_scalar(struct dcn20_dwbc *dwbc20,
 		v_ratio_luma = -1;
 	else
 		v_ratio_luma = dc_fixpt_u3d19(tmp_v_ratio_luma) << 5;
-	v_ratio_chroma = v_ratio_luma * 2;
 
 	/*Program ratio*/
 	REG_UPDATE(WBSCL_VERT_FILTER_SCALE_RATIO, WBSCL_V_SCALE_RATIO, v_ratio_luma);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
index b83c022e2c6f..8b8438566101 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
@@ -186,14 +186,13 @@ static void hubbub2_get_blk256_size(unsigned int *blk256_width, unsigned int *bl
 }
 
 static void hubbub2_det_request_size(
+		unsigned int detile_buf_size,
 		unsigned int height,
 		unsigned int width,
 		unsigned int bpe,
 		bool *req128_horz_wc,
 		bool *req128_vert_wc)
 {
-	unsigned int detile_buf_size = 164 * 1024;  /* 164KB for DCN1.0 */
-
 	unsigned int blk256_height = 0;
 	unsigned int blk256_width = 0;
 	unsigned int swath_bytes_horz_wc, swath_bytes_vert_wc;
@@ -236,7 +235,8 @@ bool hubbub2_get_dcc_compression_cap(struct hubbub *hubbub,
 			&segment_order_horz, &segment_order_vert))
 		return false;
 
-	hubbub2_det_request_size(input->surface_size.height,  input->surface_size.width,
+	hubbub2_det_request_size(TO_DCN20_HUBBUB(hubbub)->detile_buf_size,
+			input->surface_size.height,  input->surface_size.width,
 			bpe, &req128_horz_wc, &req128_vert_wc);
 
 	if (!req128_horz_wc && !req128_vert_wc) {
@@ -588,7 +588,7 @@ static void hubbub2_program_watermarks(
 			DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND, 180);
 
-	hubbub1_allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
+	hubbub->funcs->allow_self_refresh_control(hubbub, !hubbub->ctx->dc->debug.disable_stutter);
 }
 
 static const struct hubbub_funcs hubbub2_funcs = {
@@ -600,7 +600,8 @@ static const struct hubbub_funcs hubbub2_funcs = {
 	.get_dcc_compression_cap = hubbub2_get_dcc_compression_cap,
 	.wm_read_state = hubbub2_wm_read_state,
 	.get_dchub_ref_freq = hubbub2_get_dchub_ref_freq,
-	.program_watermarks = hubbub2_program_watermarks
+	.program_watermarks = hubbub2_program_watermarks,
+	.allow_self_refresh_control = hubbub1_allow_self_refresh_control
 };
 
 void hubbub2_construct(struct dcn20_hubbub *hubbub,
@@ -618,4 +619,5 @@ void hubbub2_construct(struct dcn20_hubbub *hubbub,
 	hubbub->masks = hubbub_mask;
 
 	hubbub->debug_test_index_pstate = 0xB;
+	hubbub->detile_buf_size = 164 * 1024; /* 164KB for DCN2.0 */
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h
index 626117d3b4e9..501532dd523a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.h
@@ -81,6 +81,7 @@ struct dcn20_hubbub {
 	unsigned int debug_test_index_pstate;
 	struct dcn_watermark_set watermarks;
 	struct dcn20_vmid vmid[16];
+	unsigned int detile_buf_size;
 };
 
 void hubbub2_construct(struct dcn20_hubbub *hubbub,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
index 1212da12c414..ac8c18fadefc 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c
@@ -688,7 +688,7 @@ bool dcn20_set_output_transfer_func(struct pipe_ctx *pipe_ctx,
 	return true;
 }
 
-static bool dcn20_set_blend_lut(
+bool dcn20_set_blend_lut(
 	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state)
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
@@ -710,7 +710,7 @@ static bool dcn20_set_blend_lut(
 	return result;
 }
 
-static bool dcn20_set_shaper_3dlut(
+bool dcn20_set_shaper_3dlut(
 	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state)
 {
 	struct dpp *dpp_base = pipe_ctx->plane_res.dpp;
@@ -999,72 +999,6 @@ void dcn20_enable_plane(
 }
 
 
-static void dcn20_program_pipe(
-		struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		struct dc_state *context)
-{
-	pipe_ctx->plane_state->update_flags.bits.full_update =
-			context->commit_hints.full_update_needed ? 1 : pipe_ctx->plane_state->update_flags.bits.full_update;
-
-	if (pipe_ctx->plane_state->update_flags.bits.full_update)
-		dcn20_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 dcn20_program_all_pipe_in_tree(
-		struct dc *dc,
-		struct pipe_ctx *pipe_ctx,
-		struct dc_state *context)
-{
-	if (pipe_ctx->top_pipe == NULL && !pipe_ctx->prev_odm_pipe) {
-		bool blank = !is_pipe_tree_visible(pipe_ctx);
-
-		pipe_ctx->stream_res.tg->funcs->program_global_sync(
-				pipe_ctx->stream_res.tg,
-				pipe_ctx->pipe_dlg_param.vready_offset,
-				pipe_ctx->pipe_dlg_param.vstartup_start,
-				pipe_ctx->pipe_dlg_param.vupdate_offset,
-				pipe_ctx->pipe_dlg_param.vupdate_width);
-
-		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
-				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
-
-		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
-
-		if (dc->hwss.update_odm)
-			dc->hwss.update_odm(dc, context, pipe_ctx);
-	}
-
-	if (pipe_ctx->plane_state != NULL)
-		dcn20_program_pipe(dc, pipe_ctx, context);
-
-	if (pipe_ctx->bottom_pipe != NULL) {
-		ASSERT(pipe_ctx->bottom_pipe != pipe_ctx);
-		dcn20_program_all_pipe_in_tree(dc, pipe_ctx->bottom_pipe, context);
-	} else if (pipe_ctx->next_odm_pipe != NULL) {
-		ASSERT(pipe_ctx->next_odm_pipe != pipe_ctx);
-		dcn20_program_all_pipe_in_tree(dc, pipe_ctx->next_odm_pipe, context);
-	}
-}
-
 void dcn20_pipe_control_lock_global(
 		struct dc *dc,
 		struct pipe_ctx *pipe,
@@ -1103,6 +1037,25 @@ void dcn20_pipe_control_lock(
 	if (pipe->plane_state != NULL)
 		flip_immediate = pipe->plane_state->flip_immediate;
 
+	if (flip_immediate && lock) {
+		const int TIMEOUT_FOR_FLIP_PENDING = 100000;
+		int i;
+
+		for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) {
+			if (!pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->plane_res.hubp))
+				break;
+			udelay(1);
+		}
+
+		if (pipe->bottom_pipe != NULL) {
+			for (i = 0; i < TIMEOUT_FOR_FLIP_PENDING; ++i) {
+				if (!pipe->bottom_pipe->plane_res.hubp->funcs->hubp_is_flip_pending(pipe->bottom_pipe->plane_res.hubp))
+					break;
+				udelay(1);
+			}
+		}
+	}
+
 	/* In flip immediate and pipe splitting case, we need to use GSL
 	 * for synchronization. Only do setup on locking and on flip type change.
 	 */
@@ -1124,114 +1077,456 @@ void dcn20_pipe_control_lock(
 	}
 }
 
-static void dcn20_apply_ctx_for_surface(
-		struct dc *dc,
-		const struct dc_stream_state *stream,
-		int num_planes,
-		struct dc_state *context)
+static void dcn20_detect_pipe_changes(struct pipe_ctx *old_pipe, struct pipe_ctx *new_pipe)
 {
-	const unsigned int TIMEOUT_FOR_PIPE_ENABLE_MS = 100;
-	int i;
-	struct timing_generator *tg;
-	bool removed_pipe[6] = { false };
-	bool interdependent_update = false;
-	struct pipe_ctx *top_pipe_to_program =
-			find_top_pipe_for_stream(dc, context, stream);
-	struct pipe_ctx *prev_top_pipe_to_program =
-			find_top_pipe_for_stream(dc, dc->current_state, stream);
-	DC_LOGGER_INIT(dc->ctx->logger);
+	new_pipe->update_flags.raw = 0;
 
-	if (!top_pipe_to_program)
+	/* Exit on unchanged, unused pipe */
+	if (!old_pipe->plane_state && !new_pipe->plane_state)
 		return;
+	/* Detect pipe enable/disable */
+	if (!old_pipe->plane_state && new_pipe->plane_state) {
+		new_pipe->update_flags.bits.enable = 1;
+		new_pipe->update_flags.bits.mpcc = 1;
+		new_pipe->update_flags.bits.dppclk = 1;
+		new_pipe->update_flags.bits.hubp_interdependent = 1;
+		new_pipe->update_flags.bits.hubp_rq_dlg_ttu = 1;
+		new_pipe->update_flags.bits.gamut_remap = 1;
+		new_pipe->update_flags.bits.scaler = 1;
+		new_pipe->update_flags.bits.viewport = 1;
+		if (!new_pipe->top_pipe && !new_pipe->prev_odm_pipe) {
+			new_pipe->update_flags.bits.odm = 1;
+			new_pipe->update_flags.bits.global_sync = 1;
+		}
+		return;
+	}
+	if (old_pipe->plane_state && !new_pipe->plane_state) {
+		new_pipe->update_flags.bits.disable = 1;
+		return;
+	}
 
-	/* Carry over GSL groups in case the context is changing. */
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *old_pipe_ctx =
-			&dc->current_state->res_ctx.pipe_ctx[i];
-
-		if (pipe_ctx->stream == stream &&
-		    pipe_ctx->stream == old_pipe_ctx->stream)
-			pipe_ctx->stream_res.gsl_group =
-				old_pipe_ctx->stream_res.gsl_group;
+	/* Detect top pipe only changes */
+	if (!new_pipe->top_pipe && !new_pipe->prev_odm_pipe) {
+		/* Detect odm changes */
+		if ((old_pipe->next_odm_pipe && new_pipe->next_odm_pipe
+			&& old_pipe->next_odm_pipe->pipe_idx != new_pipe->next_odm_pipe->pipe_idx)
+				|| (!old_pipe->next_odm_pipe && new_pipe->next_odm_pipe)
+				|| (old_pipe->next_odm_pipe && !new_pipe->next_odm_pipe)
+				|| old_pipe->stream_res.opp != new_pipe->stream_res.opp)
+			new_pipe->update_flags.bits.odm = 1;
+
+		/* Detect global sync changes */
+		if (old_pipe->pipe_dlg_param.vready_offset != new_pipe->pipe_dlg_param.vready_offset
+				|| old_pipe->pipe_dlg_param.vstartup_start != new_pipe->pipe_dlg_param.vstartup_start
+				|| old_pipe->pipe_dlg_param.vupdate_offset != new_pipe->pipe_dlg_param.vupdate_offset
+				|| old_pipe->pipe_dlg_param.vupdate_width != new_pipe->pipe_dlg_param.vupdate_width)
+			new_pipe->update_flags.bits.global_sync = 1;
 	}
 
-	tg = top_pipe_to_program->stream_res.tg;
+	/*
+	 * Detect opp / tg change, only set on change, not on enable
+	 * Assume mpcc inst = pipe index, if not this code needs to be updated
+	 * since mpcc is what is affected by these. In fact all of our sequence
+	 * makes this assumption at the moment with how hubp reset is matched to
+	 * same index mpcc reset.
+	 */
+	if (old_pipe->stream_res.opp != new_pipe->stream_res.opp)
+		new_pipe->update_flags.bits.opp_changed = 1;
+	if (old_pipe->stream_res.tg != new_pipe->stream_res.tg)
+		new_pipe->update_flags.bits.tg_changed = 1;
+
+	/* Detect mpcc blending changes, only dpp inst and bot matter here */
+	if (old_pipe->plane_res.dpp != new_pipe->plane_res.dpp
+			|| old_pipe->stream_res.opp != new_pipe->stream_res.opp
+			|| (!old_pipe->bottom_pipe && new_pipe->bottom_pipe)
+			|| (old_pipe->bottom_pipe && !new_pipe->bottom_pipe)
+			|| (old_pipe->bottom_pipe && new_pipe->bottom_pipe
+				&& old_pipe->bottom_pipe->plane_res.mpcc_inst
+					!= new_pipe->bottom_pipe->plane_res.mpcc_inst))
+		new_pipe->update_flags.bits.mpcc = 1;
+
+	/* Detect dppclk change */
+	if (old_pipe->plane_res.bw.dppclk_khz != new_pipe->plane_res.bw.dppclk_khz)
+		new_pipe->update_flags.bits.dppclk = 1;
+
+	/* Check for scl update */
+	if (memcmp(&old_pipe->plane_res.scl_data, &new_pipe->plane_res.scl_data, sizeof(struct scaler_data)))
+			new_pipe->update_flags.bits.scaler = 1;
+	/* Check for vp update */
+	if (memcmp(&old_pipe->plane_res.scl_data.viewport, &new_pipe->plane_res.scl_data.viewport, sizeof(struct rect))
+			|| memcmp(&old_pipe->plane_res.scl_data.viewport_c,
+				&new_pipe->plane_res.scl_data.viewport_c, sizeof(struct rect)))
+		new_pipe->update_flags.bits.viewport = 1;
+
+	/* Detect dlg/ttu/rq updates */
+	{
+		struct _vcs_dpi_display_dlg_regs_st old_dlg_attr = old_pipe->dlg_regs;
+		struct _vcs_dpi_display_ttu_regs_st old_ttu_attr = old_pipe->ttu_regs;
+		struct _vcs_dpi_display_dlg_regs_st *new_dlg_attr = &new_pipe->dlg_regs;
+		struct _vcs_dpi_display_ttu_regs_st *new_ttu_attr = &new_pipe->ttu_regs;
+
+		/* Detect pipe interdependent updates */
+		if (old_dlg_attr.dst_y_prefetch != new_dlg_attr->dst_y_prefetch ||
+				old_dlg_attr.vratio_prefetch != new_dlg_attr->vratio_prefetch ||
+				old_dlg_attr.vratio_prefetch_c != new_dlg_attr->vratio_prefetch_c ||
+				old_dlg_attr.dst_y_per_vm_vblank != new_dlg_attr->dst_y_per_vm_vblank ||
+				old_dlg_attr.dst_y_per_row_vblank != new_dlg_attr->dst_y_per_row_vblank ||
+				old_dlg_attr.dst_y_per_vm_flip != new_dlg_attr->dst_y_per_vm_flip ||
+				old_dlg_attr.dst_y_per_row_flip != new_dlg_attr->dst_y_per_row_flip ||
+				old_dlg_attr.refcyc_per_meta_chunk_vblank_l != new_dlg_attr->refcyc_per_meta_chunk_vblank_l ||
+				old_dlg_attr.refcyc_per_meta_chunk_vblank_c != new_dlg_attr->refcyc_per_meta_chunk_vblank_c ||
+				old_dlg_attr.refcyc_per_meta_chunk_flip_l != new_dlg_attr->refcyc_per_meta_chunk_flip_l ||
+				old_dlg_attr.refcyc_per_line_delivery_pre_l != new_dlg_attr->refcyc_per_line_delivery_pre_l ||
+				old_dlg_attr.refcyc_per_line_delivery_pre_c != new_dlg_attr->refcyc_per_line_delivery_pre_c ||
+				old_ttu_attr.refcyc_per_req_delivery_pre_l != new_ttu_attr->refcyc_per_req_delivery_pre_l ||
+				old_ttu_attr.refcyc_per_req_delivery_pre_c != new_ttu_attr->refcyc_per_req_delivery_pre_c ||
+				old_ttu_attr.refcyc_per_req_delivery_pre_cur0 != new_ttu_attr->refcyc_per_req_delivery_pre_cur0 ||
+				old_ttu_attr.refcyc_per_req_delivery_pre_cur1 != new_ttu_attr->refcyc_per_req_delivery_pre_cur1 ||
+				old_ttu_attr.min_ttu_vblank != new_ttu_attr->min_ttu_vblank ||
+				old_ttu_attr.qos_level_flip != new_ttu_attr->qos_level_flip) {
+			old_dlg_attr.dst_y_prefetch = new_dlg_attr->dst_y_prefetch;
+			old_dlg_attr.vratio_prefetch = new_dlg_attr->vratio_prefetch;
+			old_dlg_attr.vratio_prefetch_c = new_dlg_attr->vratio_prefetch_c;
+			old_dlg_attr.dst_y_per_vm_vblank = new_dlg_attr->dst_y_per_vm_vblank;
+			old_dlg_attr.dst_y_per_row_vblank = new_dlg_attr->dst_y_per_row_vblank;
+			old_dlg_attr.dst_y_per_vm_flip = new_dlg_attr->dst_y_per_vm_flip;
+			old_dlg_attr.dst_y_per_row_flip = new_dlg_attr->dst_y_per_row_flip;
+			old_dlg_attr.refcyc_per_meta_chunk_vblank_l = new_dlg_attr->refcyc_per_meta_chunk_vblank_l;
+			old_dlg_attr.refcyc_per_meta_chunk_vblank_c = new_dlg_attr->refcyc_per_meta_chunk_vblank_c;
+			old_dlg_attr.refcyc_per_meta_chunk_flip_l = new_dlg_attr->refcyc_per_meta_chunk_flip_l;
+			old_dlg_attr.refcyc_per_line_delivery_pre_l = new_dlg_attr->refcyc_per_line_delivery_pre_l;
+			old_dlg_attr.refcyc_per_line_delivery_pre_c = new_dlg_attr->refcyc_per_line_delivery_pre_c;
+			old_ttu_attr.refcyc_per_req_delivery_pre_l = new_ttu_attr->refcyc_per_req_delivery_pre_l;
+			old_ttu_attr.refcyc_per_req_delivery_pre_c = new_ttu_attr->refcyc_per_req_delivery_pre_c;
+			old_ttu_attr.refcyc_per_req_delivery_pre_cur0 = new_ttu_attr->refcyc_per_req_delivery_pre_cur0;
+			old_ttu_attr.refcyc_per_req_delivery_pre_cur1 = new_ttu_attr->refcyc_per_req_delivery_pre_cur1;
+			old_ttu_attr.min_ttu_vblank = new_ttu_attr->min_ttu_vblank;
+			old_ttu_attr.qos_level_flip = new_ttu_attr->qos_level_flip;
+			new_pipe->update_flags.bits.hubp_interdependent = 1;
+		}
+		/* Detect any other updates to ttu/rq/dlg */
+		if (memcmp(&old_dlg_attr, &new_pipe->dlg_regs, sizeof(old_dlg_attr)) ||
+				memcmp(&old_ttu_attr, &new_pipe->ttu_regs, sizeof(old_ttu_attr)) ||
+				memcmp(&old_pipe->rq_regs, &new_pipe->rq_regs, sizeof(old_pipe->rq_regs)))
+			new_pipe->update_flags.bits.hubp_rq_dlg_ttu = 1;
+	}
+}
 
-	interdependent_update = top_pipe_to_program->plane_state &&
-		top_pipe_to_program->plane_state->update_flags.bits.full_update;
+static void dcn20_update_dchubp_dpp(
+	struct dc *dc,
+	struct pipe_ctx *pipe_ctx,
+	struct dc_state *context)
+{
+	struct hubp *hubp = pipe_ctx->plane_res.hubp;
+	struct dpp *dpp = pipe_ctx->plane_res.dpp;
+	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 
-	if (interdependent_update)
-		lock_all_pipes(dc, context, true);
-	else
-		dcn20_pipe_control_lock(dc, top_pipe_to_program, true);
+	if (pipe_ctx->update_flags.bits.dppclk)
+		dpp->funcs->dpp_dppclk_control(dpp, false, true);
 
-	if (num_planes == 0) {
-		/* OTG blank before remove all front end */
-		dc->hwss.blank_pixel_data(dc, top_pipe_to_program, true);
+	/* TODO: Need input parameter to tell current DCHUB pipe tie to which OTG
+	 * VTG is within DCHUBBUB which is commond block share by each pipe HUBP.
+	 * VTG is 1:1 mapping with OTG. Each pipe HUBP will select which VTG
+	 */
+	if (pipe_ctx->update_flags.bits.hubp_rq_dlg_ttu) {
+		hubp->funcs->hubp_vtg_sel(hubp, pipe_ctx->stream_res.tg->inst);
+
+		hubp->funcs->hubp_setup(
+			hubp,
+			&pipe_ctx->dlg_regs,
+			&pipe_ctx->ttu_regs,
+			&pipe_ctx->rq_regs,
+			&pipe_ctx->pipe_dlg_param);
+	}
+	if (pipe_ctx->update_flags.bits.hubp_interdependent)
+		hubp->funcs->hubp_setup_interdependent(
+			hubp,
+			&pipe_ctx->dlg_regs,
+			&pipe_ctx->ttu_regs);
+
+	if (pipe_ctx->update_flags.bits.enable ||
+			plane_state->update_flags.bits.bpp_change ||
+			plane_state->update_flags.bits.input_csc_change ||
+			plane_state->update_flags.bits.color_space_change ||
+			plane_state->update_flags.bits.coeff_reduction_change) {
+		struct dc_bias_and_scale bns_params = {0};
+
+		// program the input csc
+		dpp->funcs->dpp_setup(dpp,
+				plane_state->format,
+				EXPANSION_MODE_ZERO,
+				plane_state->input_csc_color_matrix,
+				plane_state->color_space,
+				NULL);
+
+		if (dpp->funcs->dpp_program_bias_and_scale) {
+			//TODO :for CNVC set scale and bias registers if necessary
+			dcn10_build_prescale_params(&bns_params, plane_state);
+			dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
+		}
 	}
 
-	/* Disconnect unused mpcc */
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *old_pipe_ctx =
-				&dc->current_state->res_ctx.pipe_ctx[i];
-		/*
-		 * Powergate reused pipes that are not powergated
-		 * fairly hacky right now, using opp_id as indicator
-		 * TODO: After move dc_post to dc_update, this will
-		 * be removed.
-		 */
-		if (pipe_ctx->plane_state && !old_pipe_ctx->plane_state) {
-			if (old_pipe_ctx->stream_res.tg == tg &&
-			    old_pipe_ctx->plane_res.hubp &&
-			    old_pipe_ctx->plane_res.hubp->opp_id != OPP_ID_INVALID)
-				dc->hwss.disable_plane(dc, old_pipe_ctx);
+	if (pipe_ctx->update_flags.bits.mpcc
+			|| plane_state->update_flags.bits.global_alpha_change
+			|| plane_state->update_flags.bits.per_pixel_alpha_change) {
+		/* Need mpcc to be idle if changing opp */
+		if (pipe_ctx->update_flags.bits.opp_changed) {
+			struct pipe_ctx *old_pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[pipe_ctx->pipe_idx];
+			int mpcc_inst;
+
+			for (mpcc_inst = 0; mpcc_inst < MAX_PIPES; mpcc_inst++) {
+				if (!old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst])
+					continue;
+				dc->res_pool->mpc->funcs->wait_for_idle(dc->res_pool->mpc, mpcc_inst);
+				old_pipe_ctx->stream_res.opp->mpcc_disconnect_pending[mpcc_inst] = false;
+			}
 		}
+		dc->hwss.update_mpcc(dc, pipe_ctx);
+	}
 
-		if ((!pipe_ctx->plane_state ||
-		     pipe_ctx->stream_res.tg != old_pipe_ctx->stream_res.tg) &&
-		     old_pipe_ctx->plane_state &&
-		     old_pipe_ctx->stream_res.tg == tg) {
+	if (pipe_ctx->update_flags.bits.scaler ||
+			plane_state->update_flags.bits.scaling_change ||
+			plane_state->update_flags.bits.position_change ||
+			plane_state->update_flags.bits.per_pixel_alpha_change ||
+			pipe_ctx->stream->update_flags.bits.scaling) {
+		pipe_ctx->plane_res.scl_data.lb_params.alpha_en = pipe_ctx->plane_state->per_pixel_alpha;
+		ASSERT(pipe_ctx->plane_res.scl_data.lb_params.depth == LB_PIXEL_DEPTH_30BPP);
+		/* scaler configuration */
+		pipe_ctx->plane_res.dpp->funcs->dpp_set_scaler(
+				pipe_ctx->plane_res.dpp, &pipe_ctx->plane_res.scl_data);
+	}
 
-			dc->hwss.plane_atomic_disconnect(dc, old_pipe_ctx);
-			removed_pipe[i] = true;
+	if (pipe_ctx->update_flags.bits.viewport ||
+			(context == dc->current_state && plane_state->update_flags.bits.scaling_change) ||
+			(context == dc->current_state && pipe_ctx->stream->update_flags.bits.scaling))
+		hubp->funcs->mem_program_viewport(
+			hubp,
+			&pipe_ctx->plane_res.scl_data.viewport,
+			&pipe_ctx->plane_res.scl_data.viewport_c);
+
+	/* Any updates are handled in dc interface, just need to apply existing for plane enable */
+	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed)
+			&& pipe_ctx->stream->cursor_attributes.address.quad_part != 0) {
+		dc->hwss.set_cursor_position(pipe_ctx);
+		dc->hwss.set_cursor_attribute(pipe_ctx);
+
+		if (dc->hwss.set_cursor_sdr_white_level)
+			dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+	}
 
-			DC_LOG_DC("Reset mpcc for pipe %d\n",
-					old_pipe_ctx->pipe_idx);
-		}
+	/* Any updates are handled in dc interface, just need
+	 * to apply existing for plane enable / opp change */
+	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->update_flags.bits.opp_changed
+			|| pipe_ctx->stream->update_flags.bits.gamut_remap
+			|| pipe_ctx->stream->update_flags.bits.out_csc) {
+			/* dpp/cm gamut remap*/
+			dc->hwss.program_gamut_remap(pipe_ctx);
+
+		/*call the dcn2 method which uses mpc csc*/
+		dc->hwss.program_output_csc(dc,
+				pipe_ctx,
+				pipe_ctx->stream->output_color_space,
+				pipe_ctx->stream->csc_color_matrix.matrix,
+				hubp->opp_id);
+	}
+
+	if (pipe_ctx->update_flags.bits.enable ||
+			pipe_ctx->update_flags.bits.opp_changed ||
+			plane_state->update_flags.bits.pixel_format_change ||
+			plane_state->update_flags.bits.horizontal_mirror_change ||
+			plane_state->update_flags.bits.rotation_change ||
+			plane_state->update_flags.bits.swizzle_change ||
+			plane_state->update_flags.bits.dcc_change ||
+			plane_state->update_flags.bits.bpp_change ||
+			plane_state->update_flags.bits.scaling_change ||
+			plane_state->update_flags.bits.plane_size_change) {
+		struct plane_size size = plane_state->plane_size;
+
+		size.surface_size = pipe_ctx->plane_res.scl_data.viewport;
+		hubp->funcs->hubp_program_surface_config(
+			hubp,
+			plane_state->format,
+			&plane_state->tiling_info,
+			&size,
+			plane_state->rotation,
+			&plane_state->dcc,
+			plane_state->horizontal_mirror,
+			0);
+		hubp->power_gated = false;
 	}
 
-	if (num_planes > 0)
-		dcn20_program_all_pipe_in_tree(dc, top_pipe_to_program, context);
+	if (pipe_ctx->update_flags.bits.enable || plane_state->update_flags.bits.addr_update)
+		dc->hwss.update_plane_addr(dc, pipe_ctx);
 
-	/* Program secondary blending tree and writeback pipes */
-	if ((stream->num_wb_info > 0) && (dc->hwss.program_all_writeback_pipes_in_tree))
-		dc->hwss.program_all_writeback_pipes_in_tree(dc, stream, context);
+	if (pipe_ctx->update_flags.bits.enable)
+		hubp->funcs->set_blank(hubp, false);
+}
+
+
+static void dcn20_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context)
+{
+	/* Only need to unblank on top pipe */
+	if ((pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.abm_level)
+			&& !pipe_ctx->top_pipe && !pipe_ctx->prev_odm_pipe)
+		dc->hwss.blank_pixel_data(dc, pipe_ctx, !pipe_ctx->plane_state->visible);
+
+	if (pipe_ctx->update_flags.bits.global_sync) {
+		pipe_ctx->stream_res.tg->funcs->program_global_sync(
+				pipe_ctx->stream_res.tg,
+				pipe_ctx->pipe_dlg_param.vready_offset,
+				pipe_ctx->pipe_dlg_param.vstartup_start,
+				pipe_ctx->pipe_dlg_param.vupdate_offset,
+				pipe_ctx->pipe_dlg_param.vupdate_width);
+
+		pipe_ctx->stream_res.tg->funcs->set_vtg_params(
+				pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
+
+		if (dc->hwss.setup_vupdate_interrupt)
+			dc->hwss.setup_vupdate_interrupt(pipe_ctx);
+	}
+
+	if (pipe_ctx->update_flags.bits.odm)
+		dc->hwss.update_odm(dc, context, pipe_ctx);
+
+	if (pipe_ctx->update_flags.bits.enable)
+		dcn20_enable_plane(dc, pipe_ctx, context);
+
+	if (pipe_ctx->update_flags.raw || pipe_ctx->plane_state->update_flags.raw || pipe_ctx->stream->update_flags.raw)
+		dcn20_update_dchubp_dpp(dc, pipe_ctx, context);
+
+	if (pipe_ctx->update_flags.bits.enable
+			|| pipe_ctx->plane_state->update_flags.bits.sdr_white_level)
+		set_hdr_multiplier(pipe_ctx);
+
+	if (pipe_ctx->update_flags.bits.enable ||
+			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
+			pipe_ctx->plane_state->update_flags.bits.gamma_change)
+		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+
+	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
+	 * only do gamma programming for powering on, internal memcmp to avoid
+	 * updating on slave planes
+	 */
+	if (pipe_ctx->update_flags.bits.enable || pipe_ctx->stream->update_flags.bits.out_tf)
+		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+
+	/* If the pipe has been enabled or has a different opp, we
+	 * should reprogram the fmt. This deals with cases where
+	 * interation between mpc and odm combine on different streams
+	 * causes a different pipe to be chosen to odm combine with.
+	 */
+	if (pipe_ctx->update_flags.bits.enable
+	    || pipe_ctx->update_flags.bits.opp_changed) {
+
+		pipe_ctx->stream_res.opp->funcs->opp_set_dyn_expansion(
+			pipe_ctx->stream_res.opp,
+			COLOR_SPACE_YCBCR601,
+			pipe_ctx->stream->timing.display_color_depth,
+			pipe_ctx->stream->signal);
+
+		pipe_ctx->stream_res.opp->funcs->opp_program_fmt(
+			pipe_ctx->stream_res.opp,
+			&pipe_ctx->stream->bit_depth_params,
+			&pipe_ctx->stream->clamping);
+	}
+}
+
+static bool does_pipe_need_lock(struct pipe_ctx *pipe)
+{
+	if ((pipe->plane_state && pipe->plane_state->update_flags.raw)
+			|| pipe->update_flags.raw)
+		return true;
+	if (pipe->bottom_pipe)
+		return does_pipe_need_lock(pipe->bottom_pipe);
+
+	return false;
+}
+
+static void dcn20_program_front_end_for_ctx(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	const unsigned int TIMEOUT_FOR_PIPE_ENABLE_MS = 100;
+	int i;
+	bool pipe_locked[MAX_PIPES] = {false};
+	DC_LOGGER_INIT(dc->ctx->logger);
+
+	/* Carry over GSL groups in case the context is changing. */
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		if (context->res_ctx.pipe_ctx[i].stream == dc->current_state->res_ctx.pipe_ctx[i].stream)
+			context->res_ctx.pipe_ctx[i].stream_res.gsl_group =
+				dc->current_state->res_ctx.pipe_ctx[i].stream_res.gsl_group;
 
-	if (interdependent_update)
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	/* Set pipe update flags and lock pipes */
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		dcn20_detect_pipe_changes(&dc->current_state->res_ctx.pipe_ctx[i],
+				&context->res_ctx.pipe_ctx[i]);
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		if (!context->res_ctx.pipe_ctx[i].top_pipe &&
+				does_pipe_need_lock(&context->res_ctx.pipe_ctx[i])) {
 			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
-			/* Skip inactive pipes and ones already updated */
-			if (!pipe_ctx->stream || pipe_ctx->stream == stream ||
-			    !pipe_ctx->plane_state || !tg->funcs->is_tg_enabled(tg))
-				continue;
+			if (pipe_ctx->update_flags.bits.tg_changed || pipe_ctx->update_flags.bits.enable)
+				dc->hwss.pipe_control_lock(dc, pipe_ctx, true);
+			if (!pipe_ctx->update_flags.bits.enable)
+				dc->hwss.pipe_control_lock(dc, &dc->current_state->res_ctx.pipe_ctx[i], true);
+			pipe_locked[i] = true;
+		}
 
-			pipe_ctx->plane_res.hubp->funcs->hubp_setup_interdependent(
-				pipe_ctx->plane_res.hubp,
-				&pipe_ctx->dlg_regs,
-				&pipe_ctx->ttu_regs);
+	/* OTG blank before disabling all front ends */
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable
+				&& !context->res_ctx.pipe_ctx[i].top_pipe
+				&& !context->res_ctx.pipe_ctx[i].prev_odm_pipe
+				&& context->res_ctx.pipe_ctx[i].stream)
+			dc->hwss.blank_pixel_data(dc, &context->res_ctx.pipe_ctx[i], true);
+
+	/* Disconnect mpcc */
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable
+				|| context->res_ctx.pipe_ctx[i].update_flags.bits.opp_changed) {
+			dc->hwss.plane_atomic_disconnect(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
+			DC_LOG_DC("Reset mpcc for pipe %d\n", dc->current_state->res_ctx.pipe_ctx[i].pipe_idx);
 		}
 
-	if (interdependent_update)
-		lock_all_pipes(dc, context, false);
-	else
-		dcn20_pipe_control_lock(dc, top_pipe_to_program, false);
+	/*
+	 * Program all updated pipes, order matters for mpcc setup. Start with
+	 * top pipe and program all pipes that follow in order
+	 */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe->plane_state && !pipe->top_pipe) {
+			while (pipe) {
+				dcn20_program_pipe(dc, pipe, context);
+				pipe = pipe->bottom_pipe;
+			}
+			/* Program secondary blending tree and writeback pipes */
+			pipe = &context->res_ctx.pipe_ctx[i];
+			if (!pipe->prev_odm_pipe && pipe->stream->num_wb_info > 0
+					&& (pipe->update_flags.raw || pipe->plane_state->update_flags.raw || pipe->stream->update_flags.raw)
+					&& dc->hwss.program_all_writeback_pipes_in_tree)
+				dc->hwss.program_all_writeback_pipes_in_tree(dc, pipe->stream, context);
+		}
+	}
+
+	/* Unlock all locked pipes */
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
+		if (pipe_locked[i]) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+			if (pipe_ctx->update_flags.bits.tg_changed || pipe_ctx->update_flags.bits.enable)
+				dc->hwss.pipe_control_lock(dc, pipe_ctx, false);
+			if (!pipe_ctx->update_flags.bits.enable)
+				dc->hwss.pipe_control_lock(dc, &dc->current_state->res_ctx.pipe_ctx[i], false);
+		}
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++)
-		if (removed_pipe[i])
-			dcn20_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
+		if (context->res_ctx.pipe_ctx[i].update_flags.bits.disable)
+			dc->hwss.disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 
 	/*
 	 * If we are enabling a pipe, we need to wait for pending clear as this is a critical
@@ -1239,15 +1534,22 @@ static void dcn20_apply_ctx_for_surface(
 	 * will cause HW to perform an "immediate enable" (as opposed to "vsync enable") which
 	 * is unsupported on DCN.
 	 */
-	i = 0;
-	if (num_planes > 0 && top_pipe_to_program &&
-			(prev_top_pipe_to_program == NULL || prev_top_pipe_to_program->plane_state == NULL)) {
-		while (i < TIMEOUT_FOR_PIPE_ENABLE_MS &&
-				top_pipe_to_program->plane_res.hubp->funcs->hubp_is_flip_pending(top_pipe_to_program->plane_res.hubp)) {
-			i += 1;
-			msleep(1);
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe->plane_state && !pipe->top_pipe && pipe->update_flags.bits.enable) {
+			struct hubp *hubp = pipe->plane_res.hubp;
+			int j = 0;
+
+			for (j = 0; j < TIMEOUT_FOR_PIPE_ENABLE_MS
+					&& hubp->funcs->hubp_is_flip_pending(hubp); j++)
+				msleep(1);
 		}
 	}
+
+	/* WA to apply WM setting*/
+	if (dc->hwseq->wa.DEGVIDCN21)
+		dc->res_pool->hubbub->funcs->apply_DEDCN21_147_wa(dc->res_pool->hubbub);
 }
 
 
@@ -1319,8 +1621,12 @@ bool dcn20_update_bandwidth(
 
 			pipe_ctx->stream_res.tg->funcs->set_vtg_params(
 					pipe_ctx->stream_res.tg, &pipe_ctx->stream->timing);
+
 			if (pipe_ctx->prev_odm_pipe == NULL)
 				dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+
+			if (dc->hwss.setup_vupdate_interrupt)
+				dc->hwss.setup_vupdate_interrupt(pipe_ctx);
 		}
 
 		pipe_ctx->plane_res.hubp->funcs->hubp_setup(
@@ -1337,7 +1643,8 @@ bool dcn20_update_bandwidth(
 static void dcn20_enable_writeback(
 		struct dc *dc,
 		const struct dc_stream_status *stream_status,
-		struct dc_writeback_info *wb_info)
+		struct dc_writeback_info *wb_info,
+		struct dc_state *context)
 {
 	struct dwbc *dwb;
 	struct mcif_wb *mcif_wb;
@@ -1354,7 +1661,7 @@ static void dcn20_enable_writeback(
 	optc->funcs->set_dwb_source(optc, wb_info->dwb_pipe_inst);
 	/* set MCIF_WB buffer and arbitration configuration */
 	mcif_wb->funcs->config_mcif_buf(mcif_wb, &wb_info->mcif_buf_params, wb_info->dwb_params.dest_height);
-	mcif_wb->funcs->config_mcif_arb(mcif_wb, &dc->current_state->bw_ctx.bw.dcn.bw_writeback.mcif_wb_arb[wb_info->dwb_pipe_inst]);
+	mcif_wb->funcs->config_mcif_arb(mcif_wb, &context->bw_ctx.bw.dcn.bw_writeback.mcif_wb_arb[wb_info->dwb_pipe_inst]);
 	/* Enable MCIF_WB */
 	mcif_wb->funcs->enable_mcif(mcif_wb);
 	/* Enable DWB */
@@ -1702,6 +2009,28 @@ static void dcn20_reset_hw_ctx_wrap(
 	}
 }
 
+void dcn20_get_mpctree_visual_confirm_color(
+		struct pipe_ctx *pipe_ctx,
+		struct tg_color *color)
+{
+	const struct tg_color pipe_colors[6] = {
+			{MAX_TG_COLOR_VALUE, 0, 0}, // red
+			{MAX_TG_COLOR_VALUE, 0, MAX_TG_COLOR_VALUE}, // yellow
+			{0, MAX_TG_COLOR_VALUE, 0}, // blue
+			{MAX_TG_COLOR_VALUE / 2, 0, MAX_TG_COLOR_VALUE / 2}, // purple
+			{0, 0, MAX_TG_COLOR_VALUE}, // green
+			{MAX_TG_COLOR_VALUE, MAX_TG_COLOR_VALUE * 2 / 3, 0}, // orange
+	};
+
+	struct pipe_ctx *top_pipe = pipe_ctx;
+
+	while (top_pipe->top_pipe) {
+		top_pipe = top_pipe->top_pipe;
+	}
+
+	*color = pipe_colors[top_pipe->pipe_idx];
+}
+
 static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
@@ -1719,6 +2048,9 @@ static void dcn20_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
 		dcn10_get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
+	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_MPCTREE) {
+		dcn20_get_mpctree_visual_confirm_color(
+				pipe_ctx, &blnd_cfg.black_color);
 	}
 
 	if (per_pixel_alpha)
@@ -1919,8 +2251,10 @@ static void dcn20_enable_stream(struct pipe_ctx *pipe_ctx)
 	link->link_enc->funcs->connect_dig_be_to_fe(link->link_enc,
 						    pipe_ctx->stream_res.stream_enc->id, true);
 
-	if (link->dc->hwss.program_dmdata_engine)
-		link->dc->hwss.program_dmdata_engine(pipe_ctx);
+	if (pipe_ctx->plane_state && pipe_ctx->plane_state->flip_immediate != 1) {
+		if (link->dc->hwss.program_dmdata_engine)
+			link->dc->hwss.program_dmdata_engine(pipe_ctx);
+	}
 
 	link->dc->hwss.update_info_frame(pipe_ctx);
 
@@ -2095,7 +2429,8 @@ void dcn20_hw_sequencer_construct(struct dc *dc)
 	dc->hwss.program_triplebuffer = dcn20_program_tripleBuffer;
 	dc->hwss.set_input_transfer_func = dcn20_set_input_transfer_func;
 	dc->hwss.set_output_transfer_func = dcn20_set_output_transfer_func;
-	dc->hwss.apply_ctx_for_surface = dcn20_apply_ctx_for_surface;
+	dc->hwss.apply_ctx_for_surface = NULL;
+	dc->hwss.program_front_end_for_ctx = dcn20_program_front_end_for_ctx;
 	dc->hwss.pipe_control_lock = dcn20_pipe_control_lock;
 	dc->hwss.pipe_control_lock_global = dcn20_pipe_control_lock_global;
 	dc->hwss.optimize_bandwidth = dcn20_optimize_bandwidth;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
index 92ab3dd91814..3098f1049ed7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.h
@@ -96,4 +96,20 @@ void dcn20_init_blank(
 	   struct dc *dc,
 	   struct timing_generator *tg);
 void dcn20_display_init(struct dc *dc);
+void dcn20_pipe_control_lock(
+	struct dc *dc,
+	struct pipe_ctx *pipe,
+	bool lock);
+void dcn20_disable_plane(struct dc *dc, struct pipe_ctx *pipe_ctx);
+void dcn20_enable_plane(
+	struct dc *dc,
+	struct pipe_ctx *pipe_ctx,
+	struct dc_state *context);
+bool dcn20_set_blend_lut(
+	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
+bool dcn20_set_shaper_3dlut(
+	struct pipe_ctx *pipe_ctx, const struct dc_plane_state *plane_state);
+void dcn20_get_mpctree_visual_confirm_color(
+		struct pipe_ctx *pipe_ctx,
+		struct tg_color *color);
 #endif /* __DC_HWSS_DCN20_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
index 3736b5548a25..0c98a0bbbd14 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_link_encoder.h
@@ -91,6 +91,13 @@ struct mpll_cfg {
 	uint32_t ref_range;
 	uint32_t ref_clk;
 	bool hdmimode_enable;
+	bool sup_pre_hp;
+	bool dp_tx0_vergdrv_byp;
+	bool dp_tx1_vergdrv_byp;
+	bool dp_tx2_vergdrv_byp;
+	bool dp_tx3_vergdrv_byp;
+
+
 };
 
 struct dpcssys_phy_seq_cfg {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
index 2137e2be2140..3b613fb93ef8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_optc.c
@@ -287,6 +287,10 @@ void optc2_get_optc_source(struct timing_generator *optc,
 		*num_of_src_opp = 2;
 	else
 		*num_of_src_opp = 1;
+
+	/* Work around VBIOS not updating OPTC_NUM_OF_INPUT_SEGMENT */
+	if (*src_opp_id_1 == 0xf)
+		*num_of_src_opp = 1;
 }
 
 void optc2_set_dwb_source(struct timing_generator *optc,
@@ -456,7 +460,7 @@ static struct timing_generator_funcs dcn20_tg_funcs = {
 		.set_vtg_params = optc1_set_vtg_params,
 		.program_manual_trigger = optc2_program_manual_trigger,
 		.setup_manual_trigger = optc2_setup_manual_trigger,
-		.is_matching_timing = optc1_is_matching_timing
+		.get_hw_timing = optc1_get_hw_timing,
 };
 
 void dcn20_timing_generator_init(struct optc *optc1)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
index 5a2763daff4d..09793336d84f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.c
@@ -157,6 +157,74 @@ struct _vcs_dpi_ip_params_st dcn2_0_ip = {
 	.xfc_fill_constant_bytes = 0,
 };
 
+struct _vcs_dpi_ip_params_st dcn2_0_nv14_ip = {
+	.odm_capable = 1,
+	.gpuvm_enable = 0,
+	.hostvm_enable = 0,
+	.gpuvm_max_page_table_levels = 4,
+	.hostvm_max_page_table_levels = 4,
+	.hostvm_cached_page_table_levels = 0,
+	.num_dsc = 5,
+	.rob_buffer_size_kbytes = 168,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs_luma = 84,
+	.dpte_buffer_size_in_pte_reqs_chroma = 42,//todo
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.max_page_table_levels = 4,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 789504,
+	.is_line_buffer_bpp_fixed = 0,
+	.line_buffer_fixed_bpp = 0,
+	.dcc_supported = true,
+	.max_line_buffer_lines = 12,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.writeback_chroma_line_buffer_width_pixels = 4,
+	.writeback_max_hscl_ratio = 1,
+	.writeback_max_vscl_ratio = 1,
+	.writeback_min_hscl_ratio = 1,
+	.writeback_min_vscl_ratio = 1,
+	.writeback_max_hscl_taps = 12,
+	.writeback_max_vscl_taps = 12,
+	.writeback_line_buffer_luma_buffer_size = 0,
+	.writeback_line_buffer_chroma_buffer_size = 14643,
+	.cursor_buffer_size = 8,
+	.cursor_chunk_size = 2,
+	.max_num_otg = 5,
+	.max_num_dpp = 5,
+	.max_num_wb = 1,
+	.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 = 8,
+	.max_vscl_ratio = 8,
+	.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 = 32, //
+	.dppclk_delay_subtotal = 77, //
+	.dppclk_delay_scl_lb_only = 16,
+	.dppclk_delay_scl = 50,
+	.dppclk_delay_cnvc_formatter = 8,
+	.dppclk_delay_cnvc_cursor = 6,
+	.dispclk_delay_subtotal = 87, //
+	.dcfclk_cstate_latency = 10, // SRExitTime
+	.max_inter_dcn_tile_repeaters = 8,
+	.xfc_supported = true,
+	.xfc_fill_bw_overhead_percent = 10.0,
+	.xfc_fill_constant_bytes = 0,
+	.ptoi_supported = 0
+};
+
 struct _vcs_dpi_soc_bounding_box_st dcn2_0_soc = {
 	/* Defaults that get patched on driver load from firmware. */
 	.clock_limits = {
@@ -581,11 +649,13 @@ static const struct dcn2_dpp_registers tf_regs[] = {
 };
 
 static const struct dcn2_dpp_shift tf_shift = {
-		TF_REG_LIST_SH_MASK_DCN20(__SHIFT)
+		TF_REG_LIST_SH_MASK_DCN20(__SHIFT),
+		TF_DEBUG_REG_LIST_SH_DCN10
 };
 
 static const struct dcn2_dpp_mask tf_mask = {
-		TF_REG_LIST_SH_MASK_DCN20(_MASK)
+		TF_REG_LIST_SH_MASK_DCN20(_MASK),
+		TF_DEBUG_REG_LIST_MASK_DCN10
 };
 
 #define dwbc_regs_dcn2(id)\
@@ -732,6 +802,42 @@ static const struct dcn20_vmid_mask vmid_masks = {
 		DCN20_VMID_MASK_SH_LIST(_MASK)
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+		DCN_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+		DCN_AUX_MASK_SH_LIST(_MASK)
+};
+
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		return 5;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 #define dsc_regsDCN20(id)\
 [id] = {\
@@ -814,8 +920,10 @@ static const struct resource_caps res_cap_nv14 = {
 		.num_audio = 6,
 		.num_stream_encoder = 5,
 		.num_pll = 5,
-		.num_dwb = 0,
+		.num_dwb = 1,
 		.num_ddc = 5,
+		.num_vmid = 16,
+		.num_dsc = 5,
 };
 
 static const struct dc_debug_options debug_defaults_drv = {
@@ -825,7 +933,7 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.clock_trace = true,
 		.disable_pplib_clock_request = true,
 		.pipe_split_policy = MPC_SPLIT_DYNAMIC,
-		.force_single_disp_pipe_split = true,
+		.force_single_disp_pipe_split = false,
 		.disable_dcc = DCC_ENABLE,
 		.vsr_support = true,
 		.performance_trace = false,
@@ -922,7 +1030,10 @@ struct dce_aux *dcn20_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -1042,14 +1153,18 @@ struct link_encoder *dcn20_link_encoder_create(
 {
 	struct dcn20_link_encoder *enc20 =
 		kzalloc(sizeof(struct dcn20_link_encoder), GFP_KERNEL);
+	int link_regs_id;
 
 	if (!enc20)
 		return NULL;
 
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
 	dcn20_link_encoder_construct(enc20,
 				      enc_init_data,
 				      &link_enc_feature,
-				      &link_enc_regs[enc_init_data->transmitter],
+				      &link_enc_regs[link_regs_id],
 				      &link_enc_aux_regs[enc_init_data->channel - 1],
 				      &link_enc_hpd_regs[enc_init_data->hpd_source],
 				      &le_shift,
@@ -1107,6 +1222,11 @@ struct stream_encoder *dcn20_stream_encoder_create(
 	if (!enc1)
 		return NULL;
 
+	if (ASICREV_IS_NAVI14_M(ctx->asic_id.hw_internal_rev)) {
+		if (eng_id >= ENGINE_ID_DIGD)
+			eng_id++;
+	}
+
 	dcn20_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id,
 					&stream_enc_regs[eng_id],
 					&se_shift, &se_mask);
@@ -1154,6 +1274,8 @@ static const struct resource_create_funcs res_create_maximus_funcs = {
 	.create_hwseq = dcn20_hwseq_create,
 };
 
+static void dcn20_pp_smu_destroy(struct pp_smu_funcs **pp_smu);
+
 void dcn20_clock_source_destroy(struct clock_source **clk_src)
 {
 	kfree(TO_DCE110_CLK_SRC(*clk_src));
@@ -1596,7 +1718,7 @@ static void swizzle_to_dml_params(
 	}
 }
 
-static bool dcn20_split_stream_for_odm(
+bool dcn20_split_stream_for_odm(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
 		struct pipe_ctx *prev_odm_pipe,
@@ -1617,7 +1739,6 @@ static bool dcn20_split_stream_for_odm(
 	next_odm_pipe->stream_res.dsc = NULL;
 #endif
 	if (prev_odm_pipe->next_odm_pipe && prev_odm_pipe->next_odm_pipe != next_odm_pipe) {
-		ASSERT(!next_odm_pipe->next_odm_pipe);
 		next_odm_pipe->next_odm_pipe = prev_odm_pipe->next_odm_pipe;
 		next_odm_pipe->next_odm_pipe->prev_odm_pipe = next_odm_pipe;
 	}
@@ -1674,7 +1795,7 @@ static bool dcn20_split_stream_for_odm(
 	return true;
 }
 
-static void dcn20_split_stream_for_mpc(
+void dcn20_split_stream_for_mpc(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
 		struct pipe_ctx *primary_pipe,
@@ -1760,7 +1881,7 @@ int dcn20_populate_dml_pipes_from_context(
 			pipe_cnt = i;
 			continue;
 		}
-		if (!resource_are_streams_timing_synchronizable(
+		if (dc->debug.disable_timing_sync || !resource_are_streams_timing_synchronizable(
 				res_ctx->pipe_ctx[pipe_cnt].stream,
 				res_ctx->pipe_ctx[i].stream)) {
 			synchronized_vblank = false;
@@ -1892,7 +2013,7 @@ int dcn20_populate_dml_pipes_from_context(
 			break;
 		case PIXEL_ENCODING_YCBCR420:
 			pipes[pipe_cnt].dout.output_format = dm_420;
-			pipes[pipe_cnt].dout.output_bpp = (output_bpc * 3) / 2;
+			pipes[pipe_cnt].dout.output_bpp = (output_bpc * 3.0) / 2;
 			break;
 		case PIXEL_ENCODING_YCBCR422:
 			if (true) /* todo */
@@ -1906,6 +2027,11 @@ int dcn20_populate_dml_pipes_from_context(
 			pipes[pipe_cnt].dout.output_bpp = output_bpc * 3;
 		}
 
+#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+		if (res_ctx->pipe_ctx[i].stream->timing.flags.DSC)
+			pipes[pipe_cnt].dout.output_bpp = res_ctx->pipe_ctx[i].stream->timing.dsc_cfg.bits_per_pixel / 16.0;
+#endif
+
 		/* todo: default max for now, until there is logic reflecting this in dc*/
 		pipes[pipe_cnt].dout.output_bpc = 12;
 		/*
@@ -2127,7 +2253,7 @@ void dcn20_set_mcif_arb_params(
 }
 
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-static bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
+bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
 {
 	int i;
 
@@ -2162,7 +2288,7 @@ static bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx)
 }
 #endif
 
-static struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
+struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
 		const struct pipe_ctx *primary_pipe)
@@ -2202,7 +2328,8 @@ static struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 		 */
 		if (secondary_pipe == NULL) {
 			for (j = dc->res_pool->pipe_count - 1; j >= 0; j--) {
-				if (dc->current_state->res_ctx.pipe_ctx[j].top_pipe == NULL) {
+				if (dc->current_state->res_ctx.pipe_ctx[j].top_pipe == NULL
+						&& dc->current_state->res_ctx.pipe_ctx[j].prev_odm_pipe == NULL) {
 					preferred_pipe_idx = j;
 
 					if (res_ctx->pipe_ctx[preferred_pipe_idx].stream == NULL) {
@@ -2238,29 +2365,11 @@ static struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
 	return secondary_pipe;
 }
 
-bool dcn20_fast_validate_bw(
+void dcn20_merge_pipes_for_validate(
 		struct dc *dc,
-		struct dc_state *context,
-		display_e2e_pipe_params_st *pipes,
-		int *pipe_cnt_out,
-		int *pipe_split_from,
-		int *vlevel_out)
+		struct dc_state *context)
 {
-	bool out = false;
-
-	int pipe_cnt, i, pipe_idx, vlevel, vlevel_unsplit;
-	bool odm_capable = context->bw_ctx.dml.ip.odm_capable;
-	bool force_split = false;
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-	bool failed_non_odm_dsc = false;
-#endif
-	int split_threshold = dc->res_pool->pipe_count / 2;
-	bool avoid_split = dc->debug.pipe_split_policy != MPC_SPLIT_DYNAMIC;
-
-
-	ASSERT(pipes);
-	if (!pipes)
-		return false;
+	int i;
 
 	/* merge previously split odm pipes since mode support needs to make the decision */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -2315,51 +2424,19 @@ bool dcn20_fast_validate_bw(
 		if (pipe->plane_state)
 			resource_build_scaling_params(pipe);
 	}
+}
 
-	if (dc->res_pool->funcs->populate_dml_pipes)
-		pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc,
-			&context->res_ctx, pipes);
-	else
-		pipe_cnt = dcn20_populate_dml_pipes_from_context(dc,
-			&context->res_ctx, pipes);
-
-	*pipe_cnt_out = pipe_cnt;
-
-	if (!pipe_cnt) {
-		out = true;
-		goto validate_out;
-	}
-
-	context->bw_ctx.dml.ip.odm_capable = 0;
-
-	vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
-
-	context->bw_ctx.dml.ip.odm_capable = odm_capable;
-
-#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-	/* 1 dsc per stream dsc validation */
-	if (vlevel <= context->bw_ctx.dml.soc.num_states)
-		if (!dcn20_validate_dsc(dc, context)) {
-			failed_non_odm_dsc = true;
-			vlevel = context->bw_ctx.dml.soc.num_states + 1;
-		}
-#endif
-
-	if (vlevel > context->bw_ctx.dml.soc.num_states && odm_capable)
-		vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
-
-	if (vlevel > context->bw_ctx.dml.soc.num_states)
-		goto validate_fail;
-
-	if ((context->stream_count > split_threshold && dc->current_state->stream_count <= split_threshold)
-		|| (context->stream_count <= split_threshold && dc->current_state->stream_count > split_threshold))
-		context->commit_hints.full_update_needed = true;
-
-	/*initialize pipe_just_split_from to invalid idx*/
-	for (i = 0; i < MAX_PIPES; i++)
-		pipe_split_from[i] = -1;
+int dcn20_validate_apply_pipe_split_flags(
+		struct dc *dc,
+		struct dc_state *context,
+		int vlevel,
+		bool *split)
+{
+	int i, pipe_idx, vlevel_split;
+	bool force_split = false;
+	bool avoid_split = dc->debug.pipe_split_policy != MPC_SPLIT_DYNAMIC;
 
-	/* Single display only conditionals get set here */
+	/* Single display loop, exits if there is more than one display */
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 		bool exit_loop = false;
@@ -2386,38 +2463,107 @@ bool dcn20_fast_validate_bw(
 		if (exit_loop)
 			break;
 	}
-
-	if (context->stream_count > split_threshold)
+	/* TODO: fix dc bugs and remove this split threshold thing */
+	if (context->stream_count > dc->res_pool->pipe_count / 2)
 		avoid_split = true;
 
-	vlevel_unsplit = vlevel;
+	/* Avoid split loop looks for lowest voltage level that allows most unsplit pipes possible */
+	if (avoid_split) {
+		for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
+			if (!context->res_ctx.pipe_ctx[i].stream)
+				continue;
+
+			for (vlevel_split = vlevel; vlevel <= context->bw_ctx.dml.soc.num_states; vlevel++)
+				if (context->bw_ctx.dml.vba.NoOfDPP[vlevel][0][pipe_idx] == 1)
+					break;
+			/* Impossible to not split this pipe */
+			if (vlevel > context->bw_ctx.dml.soc.num_states)
+				vlevel = vlevel_split;
+			pipe_idx++;
+		}
+		context->bw_ctx.dml.vba.maxMpcComb = 0;
+	}
+
+	/* Split loop sets which pipe should be split based on dml outputs and dc flags */
 	for (i = 0, pipe_idx = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
+
 		if (!context->res_ctx.pipe_ctx[i].stream)
 			continue;
-		for (; vlevel_unsplit <= context->bw_ctx.dml.soc.num_states; vlevel_unsplit++)
-			if (context->bw_ctx.dml.vba.NoOfDPP[vlevel_unsplit][0][pipe_idx] == 1)
-				break;
+
+		if (force_split || context->bw_ctx.dml.vba.NoOfDPP[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] > 1)
+			split[i] = true;
+		if ((pipe->stream->view_format ==
+				VIEW_3D_FORMAT_SIDE_BY_SIDE ||
+				pipe->stream->view_format ==
+				VIEW_3D_FORMAT_TOP_AND_BOTTOM) &&
+				(pipe->stream->timing.timing_3d_format ==
+				TIMING_3D_FORMAT_TOP_AND_BOTTOM ||
+				 pipe->stream->timing.timing_3d_format ==
+				TIMING_3D_FORMAT_SIDE_BY_SIDE))
+			split[i] = true;
+		if (dc->debug.force_odm_combine & (1 << pipe->stream_res.tg->inst)) {
+			split[i] = true;
+			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = true;
+		}
+		context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx] =
+			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx];
+		/* Adjust dppclk when split is forced, do not bother with dispclk */
+		if (split[i] && context->bw_ctx.dml.vba.NoOfDPP[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] == 1)
+			context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] /= 2;
 		pipe_idx++;
 	}
 
+	return vlevel;
+}
+
+bool dcn20_fast_validate_bw(
+		struct dc *dc,
+		struct dc_state *context,
+		display_e2e_pipe_params_st *pipes,
+		int *pipe_cnt_out,
+		int *pipe_split_from,
+		int *vlevel_out)
+{
+	bool out = false;
+	bool split[MAX_PIPES] = { false };
+	int pipe_cnt, i, pipe_idx, vlevel;
+
+	ASSERT(pipes);
+	if (!pipes)
+		return false;
+
+	dcn20_merge_pipes_for_validate(dc, context);
+
+	pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, &context->res_ctx, pipes);
+
+	*pipe_cnt_out = pipe_cnt;
+
+	if (!pipe_cnt) {
+		out = true;
+		goto validate_out;
+	}
+
+	vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt);
+
+	if (vlevel > context->bw_ctx.dml.soc.num_states)
+		goto validate_fail;
+
+	vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, vlevel, split);
+
+	/*initialize pipe_just_split_from to invalid idx*/
+	for (i = 0; i < MAX_PIPES; i++)
+		pipe_split_from[i] = -1;
+
 	for (i = 0, pipe_idx = -1; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe = &context->res_ctx.pipe_ctx[i];
 		struct pipe_ctx *hsplit_pipe = pipe->bottom_pipe;
-		bool need_split = true;
-		bool need_split3d;
 
 		if (!pipe->stream || pipe_split_from[i] >= 0)
 			continue;
 
 		pipe_idx++;
 
-		if (dc->debug.force_odm_combine & (1 << pipe->stream_res.tg->inst)) {
-			force_split = true;
-			context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx] = true;
-			context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx] = true;
-		}
-		if (force_split && context->bw_ctx.dml.vba.NoOfDPP[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] == 1)
-			context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] /= 2;
 		if (!pipe->top_pipe && !pipe->plane_state && context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx]) {
 			hsplit_pipe = dcn20_find_secondary_pipe(dc, &context->res_ctx, dc->res_pool, pipe);
 			ASSERT(hsplit_pipe);
@@ -2435,40 +2581,26 @@ bool dcn20_fast_validate_bw(
 		if (pipe->top_pipe && pipe->plane_state == pipe->top_pipe->plane_state)
 			continue;
 
-		need_split3d = ((pipe->stream->view_format ==
-				VIEW_3D_FORMAT_SIDE_BY_SIDE ||
-				pipe->stream->view_format ==
-				VIEW_3D_FORMAT_TOP_AND_BOTTOM) &&
-				(pipe->stream->timing.timing_3d_format ==
-				TIMING_3D_FORMAT_TOP_AND_BOTTOM ||
-				 pipe->stream->timing.timing_3d_format ==
-				TIMING_3D_FORMAT_SIDE_BY_SIDE));
-
-		if (avoid_split && vlevel_unsplit <= context->bw_ctx.dml.soc.num_states && !force_split && !need_split3d) {
-			need_split = false;
-			vlevel = vlevel_unsplit;
-			context->bw_ctx.dml.vba.maxMpcComb = 0;
-		} else
-			need_split = context->bw_ctx.dml.vba.NoOfDPP[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] == 2;
-
 		/* We do not support mpo + odm at the moment */
 		if (hsplit_pipe && hsplit_pipe->plane_state != pipe->plane_state
 				&& context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx])
 			goto validate_fail;
 
-		if (need_split3d || need_split || force_split) {
+		if (split[i]) {
 			if (!hsplit_pipe || hsplit_pipe->plane_state != pipe->plane_state) {
 				/* pipe not split previously needs split */
 				hsplit_pipe = dcn20_find_secondary_pipe(dc, &context->res_ctx, dc->res_pool, pipe);
-				ASSERT(hsplit_pipe || force_split);
-				if (!hsplit_pipe)
+				ASSERT(hsplit_pipe);
+				if (!hsplit_pipe) {
+					context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx] *= 2;
 					continue;
-
+				}
 				if (context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx]) {
 					if (!dcn20_split_stream_for_odm(
 							&context->res_ctx, dc->res_pool,
 							pipe, hsplit_pipe))
 						goto validate_fail;
+					dcn20_build_mapped_resource(dc, context, pipe->stream);
 				} else
 					dcn20_split_stream_for_mpc(
 						&context->res_ctx, dc->res_pool,
@@ -2482,7 +2614,7 @@ bool dcn20_fast_validate_bw(
 	}
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	/* Actual dsc count per stream dsc validation*/
-	if (failed_non_odm_dsc && !dcn20_validate_dsc(dc, context)) {
+	if (!dcn20_validate_dsc(dc, context)) {
 		context->bw_ctx.dml.vba.ValidationStatus[context->bw_ctx.dml.vba.soc.num_states] =
 				DML_FAIL_DSC_VALIDATION_FAILURE;
 		goto validate_fail;
@@ -2501,7 +2633,7 @@ validate_out:
 	return out;
 }
 
-void dcn20_calculate_wm(
+static void dcn20_calculate_wm(
 		struct dc *dc, struct dc_state *context,
 		display_e2e_pipe_params_st *pipes,
 		int *out_pipe_cnt,
@@ -2522,7 +2654,7 @@ void dcn20_calculate_wm(
 					context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_idx];
 			if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_idx] == pipe_idx)
 				pipes[pipe_cnt].pipe.dest.odm_combine =
-						context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_idx];
+						context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_idx];
 			else
 				pipes[pipe_cnt].pipe.dest.odm_combine = 0;
 			pipe_idx++;
@@ -2531,7 +2663,7 @@ void dcn20_calculate_wm(
 					context->bw_ctx.dml.vba.RequiredDPPCLK[vlevel][context->bw_ctx.dml.vba.maxMpcComb][pipe_split_from[i]];
 			if (context->bw_ctx.dml.vba.BlendingAndTiming[pipe_split_from[i]] == pipe_split_from[i])
 				pipes[pipe_cnt].pipe.dest.odm_combine =
-						context->bw_ctx.dml.vba.ODMCombineEnablePerState[vlevel][pipe_split_from[i]];
+						context->bw_ctx.dml.vba.ODMCombineEnabled[pipe_split_from[i]];
 			else
 				pipes[pipe_cnt].pipe.dest.odm_combine = 0;
 		}
@@ -2574,6 +2706,11 @@ void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.b.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+	context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.b.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.b.urgent_latency_ns = get_urgent_latency(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#endif
 
 	if (vlevel < 2) {
 		pipes[0].clks_cfg.voltage = 2;
@@ -2585,6 +2722,10 @@ void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.c.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.c.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#endif
 
 	if (vlevel < 3) {
 		pipes[0].clks_cfg.voltage = 3;
@@ -2596,6 +2737,10 @@ void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.d.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.d.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#endif
 
 	pipes[0].clks_cfg.voltage = vlevel;
 	pipes[0].clks_cfg.dcfclk_mhz = context->bw_ctx.dml.soc.clock_limits[vlevel].dcfclk_mhz;
@@ -2605,6 +2750,10 @@ void dcn20_calculate_wm(
 	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns = get_wm_stutter_exit(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns = get_wm_dram_clock_change(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
 	context->bw_ctx.bw.dcn.watermarks.a.pte_meta_urgent_ns = get_wm_memory_trip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+	context->bw_ctx.bw.dcn.watermarks.a.frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(&context->bw_ctx.dml, pipes, pipe_cnt) * 1000;
+#endif
 }
 
 void dcn20_calculate_dlg_params(
@@ -2624,7 +2773,7 @@ void dcn20_calculate_dlg_params(
 	context->bw_ctx.bw.dcn.clk.socclk_khz = context->bw_ctx.dml.vba.SOCCLK * 1000;
 	context->bw_ctx.bw.dcn.clk.dramclk_khz = context->bw_ctx.dml.vba.DRAMSpeed * 1000 / 16;
 	context->bw_ctx.bw.dcn.clk.dcfclk_deep_sleep_khz = context->bw_ctx.dml.vba.DCFCLKDeepSleep * 1000;
-	context->bw_ctx.bw.dcn.clk.fclk_khz = 0;
+	context->bw_ctx.bw.dcn.clk.fclk_khz = context->bw_ctx.dml.vba.FabricClock * 1000;
 	context->bw_ctx.bw.dcn.clk.p_state_change_support =
 		context->bw_ctx.dml.vba.DRAMClockChangeSupport[vlevel][context->bw_ctx.dml.vba.maxMpcComb]
 							!= dm_dram_clock_change_unsupported;
@@ -2640,8 +2789,8 @@ void dcn20_calculate_dlg_params(
 			continue;
 
 		if (!visited[pipe_idx]) {
-			display_pipe_source_params_st *src = &pipes[pipe_idx_unsplit].pipe.src;
-			display_pipe_dest_params_st *dst = &pipes[pipe_idx_unsplit].pipe.dest;
+			display_pipe_source_params_st *src = &pipes[pipe_idx].pipe.src;
+			display_pipe_dest_params_st *dst = &pipes[pipe_idx].pipe.dest;
 
 			dst->vstartup_start = context->bw_ctx.dml.vba.VStartup[pipe_idx_unsplit];
 			dst->vupdate_offset = context->bw_ctx.dml.vba.VUpdateOffsetPix[pipe_idx_unsplit];
@@ -2801,7 +2950,6 @@ bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context,
 	ASSERT(false);
 
 restore_dml_state:
-	memcpy(&context->bw_ctx.dml, &dc->dml, sizeof(struct display_mode_lib));
 	context->bw_ctx.dml.soc.dram_clock_change_latency_us = p_state_latency_us;
 
 	return voltage_supported;
@@ -2887,6 +3035,7 @@ static struct resource_funcs dcn20_res_pool_funcs = {
 	.populate_dml_writeback_from_context = dcn20_populate_dml_writeback_from_context,
 	.get_default_swizzle_mode = dcn20_get_default_swizzle_mode,
 	.set_mcif_arb_params = dcn20_set_mcif_arb_params,
+	.populate_dml_pipes = dcn20_populate_dml_pipes_from_context,
 	.find_first_free_match_stream_enc_for_link = dcn10_find_first_free_match_stream_enc_for_link
 };
 
@@ -2895,8 +3044,6 @@ bool dcn20_dwbc_create(struct dc_context *ctx, struct resource_pool *pool)
 	int i;
 	uint32_t pipe_count = pool->res_cap->num_dwb;
 
-	ASSERT(pipe_count > 0);
-
 	for (i = 0; i < pipe_count; i++) {
 		struct dcn20_dwbc *dwbc20 = kzalloc(sizeof(struct dcn20_dwbc),
 						    GFP_KERNEL);
@@ -2942,7 +3089,7 @@ bool dcn20_mmhubbub_create(struct dc_context *ctx, struct resource_pool *pool)
 	return true;
 }
 
-struct pp_smu_funcs *dcn20_pp_smu_create(struct dc_context *ctx)
+static struct pp_smu_funcs *dcn20_pp_smu_create(struct dc_context *ctx)
 {
 	struct pp_smu_funcs *pp_smu = kzalloc(sizeof(*pp_smu), GFP_KERNEL);
 
@@ -2957,7 +3104,7 @@ struct pp_smu_funcs *dcn20_pp_smu_create(struct dc_context *ctx)
 	return pp_smu;
 }
 
-void dcn20_pp_smu_destroy(struct pp_smu_funcs **pp_smu)
+static void dcn20_pp_smu_destroy(struct pp_smu_funcs **pp_smu)
 {
 	if (pp_smu && *pp_smu) {
 		kfree(*pp_smu);
@@ -2965,7 +3112,7 @@ void dcn20_pp_smu_destroy(struct pp_smu_funcs **pp_smu)
 	}
 }
 
-static void cap_soc_clocks(
+void dcn20_cap_soc_clocks(
 		struct _vcs_dpi_soc_bounding_box_st *bb,
 		struct pp_smu_nv_clock_table max_clocks)
 {
@@ -3032,10 +3179,10 @@ static void cap_soc_clocks(
 	}
 }
 
-static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb,
+void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb,
 		struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states)
 {
-	struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES] = {0};
+	struct _vcs_dpi_voltage_scaling_st calculated_states[MAX_CLOCK_LIMIT_STATES];
 	int i;
 	int num_calculated_states = 0;
 	int min_dcfclk = 0;
@@ -3043,12 +3190,18 @@ static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_
 	if (num_states == 0)
 		return;
 
+	memset(calculated_states, 0, sizeof(calculated_states));
+
 	if (dc->bb_overrides.min_dcfclk_mhz > 0)
 		min_dcfclk = dc->bb_overrides.min_dcfclk_mhz;
-	else
-		// Accounting for SOC/DCF relationship, we can go as high as
-		// 506Mhz in Vmin.  We need to code 507 since SMU will round down to 506.
-		min_dcfclk = 507;
+	else {
+		if (ASICREV_IS_NAVI12_P(dc->ctx->asic_id.hw_internal_rev))
+			min_dcfclk = 310;
+		else
+			// Accounting for SOC/DCF relationship, we can go as high as
+			// 506Mhz in Vmin.
+			min_dcfclk = 506;
+	}
 
 	for (i = 0; i < num_states; i++) {
 		int min_fclk_required_by_uclk;
@@ -3088,7 +3241,7 @@ static void update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_
 	bb->clock_limits[num_calculated_states].state = bb->num_states;
 }
 
-static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb)
+void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb)
 {
 	kernel_fpu_begin();
 	if ((int)(bb->sr_exit_time_us * 1000) != dc->bb_overrides.sr_exit_time_ns
@@ -3129,6 +3282,10 @@ static struct _vcs_dpi_soc_bounding_box_st *get_asic_rev_soc_bb(
 static struct _vcs_dpi_ip_params_st *get_asic_rev_ip_params(
 	uint32_t hw_internal_rev)
 {
+	/* NV14 */
+	if (ASICREV_IS_NAVI14_M(hw_internal_rev))
+		return &dcn2_0_nv14_ip;
+
 	/* NV12 and NV10 */
 	return &dcn2_0_ip;
 }
@@ -3287,14 +3444,14 @@ static bool init_soc_bounding_box(struct dc *dc,
 		}
 
 		if (clock_limits_available && uclk_states_available && num_states)
-			update_bounding_box(dc, loaded_bb, &max_clocks, uclk_states, num_states);
+			dcn20_update_bounding_box(dc, loaded_bb, &max_clocks, uclk_states, num_states);
 		else if (clock_limits_available)
-			cap_soc_clocks(loaded_bb, max_clocks);
+			dcn20_cap_soc_clocks(loaded_bb, max_clocks);
 	}
 
 	loaded_ip->max_num_otg = pool->base.res_cap->num_timing_generator;
 	loaded_ip->max_num_dpp = pool->base.pipe_count;
-	patch_bounding_box(dc, loaded_bb);
+	dcn20_patch_bounding_box(dc, loaded_bb);
 
 	return true;
 }
@@ -3340,6 +3497,7 @@ static bool construct(
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
 	dc->caps.hw_3d_lut = true;
+	dc->caps.extended_aux_timeout_support = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV) {
 		dc->debug = debug_defaults_drv;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
index 44f95aa0d61e..fef473d68a4a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_resource.h
@@ -95,9 +95,12 @@ struct display_stream_compressor *dcn20_dsc_create(
 	struct dc_context *ctx, uint32_t inst);
 void dcn20_dsc_destroy(struct display_stream_compressor **dsc);
 
-struct pp_smu_funcs *dcn20_pp_smu_create(struct dc_context *ctx);
-void dcn20_pp_smu_destroy(struct pp_smu_funcs **pp_smu);
-
+void dcn20_patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb);
+void dcn20_cap_soc_clocks(
+		struct _vcs_dpi_soc_bounding_box_st *bb,
+		struct pp_smu_nv_clock_table max_clocks);
+void dcn20_update_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb,
+		struct pp_smu_nv_clock_table *max_clocks, unsigned int *uclk_states, unsigned int num_states);
 struct hubp *dcn20_hubp_create(
 	struct dc_context *ctx,
 	uint32_t inst);
@@ -116,6 +119,31 @@ void dcn20_set_mcif_arb_params(
 		display_e2e_pipe_params_st *pipes,
 		int pipe_cnt);
 bool dcn20_validate_bandwidth(struct dc *dc, struct dc_state *context, bool fast_validate);
+void dcn20_merge_pipes_for_validate(
+		struct dc *dc,
+		struct dc_state *context);
+int dcn20_validate_apply_pipe_split_flags(
+		struct dc *dc,
+		struct dc_state *context,
+		int vlevel,
+		bool *split);
+#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+bool dcn20_validate_dsc(struct dc *dc, struct dc_state *new_ctx);
+#endif
+void dcn20_split_stream_for_mpc(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool,
+		struct pipe_ctx *primary_pipe,
+		struct pipe_ctx *secondary_pipe);
+bool dcn20_split_stream_for_odm(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool,
+		struct pipe_ctx *prev_odm_pipe,
+		struct pipe_ctx *next_odm_pipe);
+struct pipe_ctx *dcn20_find_secondary_pipe(struct dc *dc,
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool,
+		const struct pipe_ctx *primary_pipe);
 bool dcn20_fast_validate_bw(
 		struct dc *dc,
 		struct dc_state *context,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
index 5ab9d6240498..4b3401616434 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_stream_encoder.c
@@ -578,6 +578,10 @@ static const struct stream_encoder_funcs dcn20_str_enc_funcs = {
 	.set_avmute = enc1_stream_encoder_set_avmute,
 	.dig_connect_to_otg  = enc1_dig_connect_to_otg,
 	.dig_source_otg = enc1_dig_source_otg,
+
+	.dp_get_pixel_format =
+		enc1_stream_encoder_dp_get_pixel_format,
+
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	.enc_read_state = enc2_read_state,
 	.dp_set_dsc_config = enc2_dp_set_dsc_config,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
index ef673bffc241..14113ccf498d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/Makefile
@@ -1,17 +1,22 @@
 #
 # Makefile for DCN21.
 
-DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o
+DCN21 = dcn21_hubp.o dcn21_hubbub.o dcn21_resource.o dcn21_hwseq.o dcn21_link_encoder.o
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse
 
-CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -mpreferred-stack-boundary=4
+else
 CFLAGS_$(AMDDALPATH)/dc/dcn21/dcn21_resource.o += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
index d1266741763b..f546260c15b7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.c
@@ -22,6 +22,7 @@
  * Authors: AMD
  *
  */
+#include <linux/delay.h>
 #include "dm_services.h"
 #include "dcn20/dcn20_hubbub.h"
 #include "dcn21_hubbub.h"
@@ -51,7 +52,7 @@
 #ifdef NUM_VMID
 #undef NUM_VMID
 #endif
-#define NUM_VMID 1
+#define NUM_VMID 16
 
 static uint32_t convert_and_clamp(
 	uint32_t wm_ns,
@@ -71,56 +72,76 @@ static uint32_t convert_and_clamp(
 void dcn21_dchvm_init(struct hubbub *hubbub)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+	uint32_t riommu_active;
+	int i;
 
 	//Init DCHVM block
 	REG_UPDATE(DCHVM_CTRL0, HOSTVM_INIT_REQ, 1);
 
 	//Poll until RIOMMU_ACTIVE = 1
-	//TODO: Figure out interval us and retry count
-	REG_WAIT(DCHVM_RIOMMU_STAT0, RIOMMU_ACTIVE, 1, 5, 100);
+	for (i = 0; i < 100; i++) {
+		REG_GET(DCHVM_RIOMMU_STAT0, RIOMMU_ACTIVE, &riommu_active);
 
-	//Reflect the power status of DCHUBBUB
-	REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_POWERSTATUS, 1);
+		if (riommu_active)
+			break;
+		else
+			udelay(5);
+	}
+
+	if (riommu_active) {
+		//Reflect the power status of DCHUBBUB
+		REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_POWERSTATUS, 1);
 
-	//Start rIOMMU prefetching
-	REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_PREFETCH_REQ, 1);
+		//Start rIOMMU prefetching
+		REG_UPDATE(DCHVM_RIOMMU_CTRL0, HOSTVM_PREFETCH_REQ, 1);
 
-	// Enable dynamic clock gating
-	REG_UPDATE_4(DCHVM_CLK_CTRL,
-					HVM_DISPCLK_R_GATE_DIS, 0,
-					HVM_DISPCLK_G_GATE_DIS, 0,
-					HVM_DCFCLK_R_GATE_DIS, 0,
-					HVM_DCFCLK_G_GATE_DIS, 0);
+		// Enable dynamic clock gating
+		REG_UPDATE_4(DCHVM_CLK_CTRL,
+						HVM_DISPCLK_R_GATE_DIS, 0,
+						HVM_DISPCLK_G_GATE_DIS, 0,
+						HVM_DCFCLK_R_GATE_DIS, 0,
+						HVM_DCFCLK_G_GATE_DIS, 0);
 
-	//Poll until HOSTVM_PREFETCH_DONE = 1
-	//TODO: Figure out interval us and retry count
-	REG_WAIT(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, 1, 5, 100);
+		//Poll until HOSTVM_PREFETCH_DONE = 1
+		REG_WAIT(DCHVM_RIOMMU_STAT0, HOSTVM_PREFETCH_DONE, 1, 5, 100);
+	}
 }
 
-static int hubbub21_init_dchub(struct hubbub *hubbub,
+int hubbub21_init_dchub(struct hubbub *hubbub,
 		struct dcn_hubbub_phys_addr_config *pa_config)
 {
 	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+	struct dcn_vmid_page_table_config phys_config;
 
 	REG_SET(DCN_VM_FB_LOCATION_BASE, 0,
-		FB_BASE, pa_config->system_aperture.fb_base);
+			FB_BASE, pa_config->system_aperture.fb_base >> 24);
 	REG_SET(DCN_VM_FB_LOCATION_TOP, 0,
-			FB_TOP, pa_config->system_aperture.fb_top);
+			FB_TOP, pa_config->system_aperture.fb_top >> 24);
 	REG_SET(DCN_VM_FB_OFFSET, 0,
-			FB_OFFSET, pa_config->system_aperture.fb_offset);
+			FB_OFFSET, pa_config->system_aperture.fb_offset >> 24);
 	REG_SET(DCN_VM_AGP_BOT, 0,
-			AGP_BOT, pa_config->system_aperture.agp_bot);
+			AGP_BOT, pa_config->system_aperture.agp_bot >> 24);
 	REG_SET(DCN_VM_AGP_TOP, 0,
-			AGP_TOP, pa_config->system_aperture.agp_top);
+			AGP_TOP, pa_config->system_aperture.agp_top >> 24);
 	REG_SET(DCN_VM_AGP_BASE, 0,
-			AGP_BASE, pa_config->system_aperture.agp_base);
+			AGP_BASE, pa_config->system_aperture.agp_base >> 24);
+
+	if (pa_config->gart_config.page_table_start_addr != pa_config->gart_config.page_table_end_addr) {
+		phys_config.page_table_start_addr = pa_config->gart_config.page_table_start_addr >> 12;
+		phys_config.page_table_end_addr = pa_config->gart_config.page_table_end_addr >> 12;
+		phys_config.page_table_base_addr = pa_config->gart_config.page_table_base_addr | 1; //Note: hack
+		phys_config.depth = 0;
+		phys_config.block_size = 0;
+		// Init VMID 0 based on PA config
+		dcn20_vmid_setup(&hubbub1->vmid[0], &phys_config);
+	}
 
 	dcn21_dchvm_init(hubbub);
 
 	return NUM_VMID;
 }
 
-static void hubbub21_program_urgent_watermarks(
+void hubbub21_program_urgent_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
@@ -160,6 +181,13 @@ static void hubbub21_program_urgent_watermarks(
 		REG_SET(DCHUBBUB_ARB_FRAC_URG_BW_NOM_A, 0,
 				DCHUBBUB_ARB_FRAC_URG_BW_NOM_A, watermarks->a.frac_urg_bw_nom);
 	}
+	if (safe_to_lower || watermarks->a.urgent_latency_ns > hubbub1->watermarks.a.urgent_latency_ns) {
+		hubbub1->watermarks.a.urgent_latency_ns = watermarks->a.urgent_latency_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.urgent_latency_ns,
+				refclk_mhz, 0x1fffff);
+		REG_SET(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_A, 0,
+				DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_A, prog_wm_value);
+	}
 
 	/* clock state B */
 	if (safe_to_lower || watermarks->b.urgent_ns > hubbub1->watermarks.b.urgent_ns) {
@@ -192,6 +220,14 @@ static void hubbub21_program_urgent_watermarks(
 				DCHUBBUB_ARB_FRAC_URG_BW_NOM_B, watermarks->a.frac_urg_bw_nom);
 	}
 
+	if (safe_to_lower || watermarks->b.urgent_latency_ns > hubbub1->watermarks.b.urgent_latency_ns) {
+		hubbub1->watermarks.b.urgent_latency_ns = watermarks->b.urgent_latency_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.urgent_latency_ns,
+				refclk_mhz, 0x1fffff);
+		REG_SET(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_B, 0,
+				DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_B, prog_wm_value);
+	}
+
 	/* clock state C */
 	if (safe_to_lower || watermarks->c.urgent_ns > hubbub1->watermarks.c.urgent_ns) {
 		hubbub1->watermarks.c.urgent_ns = watermarks->c.urgent_ns;
@@ -223,6 +259,14 @@ static void hubbub21_program_urgent_watermarks(
 				DCHUBBUB_ARB_FRAC_URG_BW_NOM_C, watermarks->a.frac_urg_bw_nom);
 	}
 
+	if (safe_to_lower || watermarks->c.urgent_latency_ns > hubbub1->watermarks.c.urgent_latency_ns) {
+		hubbub1->watermarks.c.urgent_latency_ns = watermarks->c.urgent_latency_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.urgent_latency_ns,
+				refclk_mhz, 0x1fffff);
+		REG_SET(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_C, 0,
+				DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_C, prog_wm_value);
+	}
+
 	/* clock state D */
 	if (safe_to_lower || watermarks->d.urgent_ns > hubbub1->watermarks.d.urgent_ns) {
 		hubbub1->watermarks.d.urgent_ns = watermarks->d.urgent_ns;
@@ -253,9 +297,17 @@ static void hubbub21_program_urgent_watermarks(
 		REG_SET(DCHUBBUB_ARB_FRAC_URG_BW_NOM_D, 0,
 				DCHUBBUB_ARB_FRAC_URG_BW_NOM_D, watermarks->a.frac_urg_bw_nom);
 	}
+
+	if (safe_to_lower || watermarks->d.urgent_latency_ns > hubbub1->watermarks.d.urgent_latency_ns) {
+		hubbub1->watermarks.d.urgent_latency_ns = watermarks->d.urgent_latency_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.urgent_latency_ns,
+				refclk_mhz, 0x1fffff);
+		REG_SET(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D, 0,
+				DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D, prog_wm_value);
+	}
 }
 
-static void hubbub21_program_stutter_watermarks(
+void hubbub21_program_stutter_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
@@ -389,7 +441,7 @@ static void hubbub21_program_stutter_watermarks(
 	}
 }
 
-static void hubbub21_program_pstate_watermarks(
+void hubbub21_program_pstate_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
@@ -564,17 +616,26 @@ void hubbub21_wm_read_state(struct hubbub *hubbub,
 			DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, &s->dram_clk_chanage);
 }
 
+void hubbub21_apply_DEDCN21_147_wa(struct hubbub *hubbub)
+{
+	struct dcn20_hubbub *hubbub1 = TO_DCN20_HUBBUB(hubbub);
+	uint32_t prog_wm_value;
+
+	prog_wm_value = REG_READ(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A);
+	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
+}
 
 static const struct hubbub_funcs hubbub21_funcs = {
 	.update_dchub = hubbub2_update_dchub,
 	.init_dchub_sys_ctx = hubbub21_init_dchub,
-	.init_vm_ctx = NULL,
+	.init_vm_ctx = hubbub2_init_vm_ctx,
 	.dcc_support_swizzle = hubbub2_dcc_support_swizzle,
 	.dcc_support_pixel_format = hubbub2_dcc_support_pixel_format,
 	.get_dcc_compression_cap = hubbub2_get_dcc_compression_cap,
 	.wm_read_state = hubbub21_wm_read_state,
 	.get_dchub_ref_freq = hubbub2_get_dchub_ref_freq,
 	.program_watermarks = hubbub21_program_watermarks,
+	.apply_DEDCN21_147_wa = hubbub21_apply_DEDCN21_147_wa,
 };
 
 void hubbub21_construct(struct dcn20_hubbub *hubbub,
@@ -592,4 +653,5 @@ void hubbub21_construct(struct dcn20_hubbub *hubbub,
 	hubbub->masks = hubbub_mask;
 
 	hubbub->debug_test_index_pstate = 0xB;
+	hubbub->detile_buf_size = 164 * 1024; /* 164KB for DCN2.0 */
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h
index 6ff3cdb89178..c4840dfb1fa5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubbub.h
@@ -36,6 +36,10 @@
 	SR(DCHUBBUB_ARB_FRAC_URG_BW_FLIP_B),\
 	SR(DCHUBBUB_ARB_FRAC_URG_BW_FLIP_C),\
 	SR(DCHUBBUB_ARB_FRAC_URG_BW_FLIP_D),\
+	SR(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_A),\
+	SR(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_B),\
+	SR(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_C),\
+	SR(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D),\
 	SR(DCHUBBUB_ARB_HOSTVM_CNTL), \
 	SR(DCHVM_CTRL0), \
 	SR(DCHVM_MEM_CTRL), \
@@ -44,16 +48,9 @@
 	SR(DCHVM_RIOMMU_STAT0)
 
 #define HUBBUB_REG_LIST_DCN21()\
-	HUBBUB_REG_LIST_DCN_COMMON(), \
+	HUBBUB_REG_LIST_DCN20_COMMON(), \
 	HUBBUB_SR_WATERMARK_REG_LIST(), \
-	HUBBUB_HVM_REG_LIST(), \
-	SR(DCHUBBUB_CRC_CTRL), \
-	SR(DCN_VM_FB_LOCATION_BASE),\
-	SR(DCN_VM_FB_LOCATION_TOP),\
-	SR(DCN_VM_FB_OFFSET),\
-	SR(DCN_VM_AGP_BOT),\
-	SR(DCN_VM_AGP_TOP),\
-	SR(DCN_VM_AGP_BASE)
+	HUBBUB_HVM_REG_LIST()
 
 #define HUBBUB_MASK_SH_LIST_HVM(mask_sh) \
 	HUBBUB_SF(DCHUBBUB_ARB_DF_REQ_OUTSTAND, DCHUBBUB_ARB_MIN_REQ_OUTSTAND_COMMIT_THRESHOLD, mask_sh), \
@@ -102,7 +99,7 @@
 	HUBBUB_SF(DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D, DCHUBBUB_ARB_REFCYC_PER_TRIP_TO_MEMORY_D, mask_sh)
 
 #define HUBBUB_MASK_SH_LIST_DCN21(mask_sh)\
-	HUBBUB_MASK_SH_LIST_HVM(mask_sh),\
+	HUBBUB_MASK_SH_LIST_HVM(mask_sh), \
 	HUBBUB_MASK_SH_LIST_DCN_COMMON(mask_sh), \
 	HUBBUB_MASK_SH_LIST_STUTTER(mask_sh), \
 	HUBBUB_SF(DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_REFDIV, mask_sh), \
@@ -114,11 +111,28 @@
 	HUBBUB_SF(DCN_VM_AGP_BASE, AGP_BASE, mask_sh)
 
 void dcn21_dchvm_init(struct hubbub *hubbub);
+int hubbub21_init_dchub(struct hubbub *hubbub,
+		struct dcn_hubbub_phys_addr_config *pa_config);
 void hubbub21_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
 		unsigned int refclk_mhz,
 		bool safe_to_lower);
+void hubbub21_program_urgent_watermarks(
+		struct hubbub *hubbub,
+		struct dcn_watermark_set *watermarks,
+		unsigned int refclk_mhz,
+		bool safe_to_lower);
+void hubbub21_program_stutter_watermarks(
+		struct hubbub *hubbub,
+		struct dcn_watermark_set *watermarks,
+		unsigned int refclk_mhz,
+		bool safe_to_lower);
+void hubbub21_program_pstate_watermarks(
+		struct hubbub *hubbub,
+		struct dcn_watermark_set *watermarks,
+		unsigned int refclk_mhz,
+		bool safe_to_lower);
 
 void hubbub21_wm_read_state(struct hubbub *hubbub,
 		struct dcn_hubbub_wm *wm);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
index a00af513aa2b..2f5a5867e674 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c
@@ -22,6 +22,8 @@
  * Authors: AMD
  *
  */
+
+#include "dcn10/dcn10_hubp.h"
 #include "dcn21_hubp.h"
 
 #include "dm_services.h"
@@ -202,7 +204,7 @@ static struct hubp_funcs dcn21_hubp_funcs = {
 	.hubp_enable_tripleBuffer = hubp2_enable_triplebuffer,
 	.hubp_is_triplebuffer_enabled = hubp2_is_triplebuffer_enabled,
 	.hubp_program_surface_flip_and_addr = hubp2_program_surface_flip_and_addr,
-	.hubp_program_surface_config = hubp2_program_surface_config,
+	.hubp_program_surface_config = hubp1_program_surface_config,
 	.hubp_is_flip_pending = hubp1_is_flip_pending,
 	.hubp_setup = hubp21_setup,
 	.hubp_setup_interdependent = hubp2_setup_interdependent,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
new file mode 100644
index 000000000000..b25215cadf85
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.c
@@ -0,0 +1,122 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "dm_helpers.h"
+#include "core_types.h"
+#include "resource.h"
+#include "dce/dce_hwseq.h"
+#include "dcn20/dcn20_hwseq.h"
+#include "vmid.h"
+#include "reg_helper.h"
+#include "hw/clk_mgr.h"
+
+
+#define DC_LOGGER_INIT(logger)
+
+#define CTX \
+	hws->ctx
+#define REG(reg)\
+	hws->regs->reg
+
+#undef FN
+#define FN(reg_name, field_name) \
+	hws->shifts->field_name, hws->masks->field_name
+
+/* Temporary read settings, future will get values from kmd directly */
+static void mmhub_update_page_table_config(struct dcn_hubbub_phys_addr_config *config,
+		struct dce_hwseq *hws)
+{
+	uint32_t page_table_base_hi;
+	uint32_t page_table_base_lo;
+
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32,
+			PAGE_DIRECTORY_ENTRY_HI32, &page_table_base_hi);
+	REG_GET(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32,
+			PAGE_DIRECTORY_ENTRY_LO32, &page_table_base_lo);
+
+	config->gart_config.page_table_base_addr = ((uint64_t)page_table_base_hi << 32) | page_table_base_lo;
+
+}
+
+static int dcn21_init_sys_ctx(struct dce_hwseq *hws, struct dc *dc, struct dc_phy_addr_space_config *pa_config)
+{
+	struct dcn_hubbub_phys_addr_config config;
+
+	config.system_aperture.fb_top = pa_config->system_aperture.fb_top;
+	config.system_aperture.fb_offset = pa_config->system_aperture.fb_offset;
+	config.system_aperture.fb_base = pa_config->system_aperture.fb_base;
+	config.system_aperture.agp_top = pa_config->system_aperture.agp_top;
+	config.system_aperture.agp_bot = pa_config->system_aperture.agp_bot;
+	config.system_aperture.agp_base = pa_config->system_aperture.agp_base;
+	config.gart_config.page_table_start_addr = pa_config->gart_config.page_table_start_addr;
+	config.gart_config.page_table_end_addr = pa_config->gart_config.page_table_end_addr;
+	config.gart_config.page_table_base_addr = pa_config->gart_config.page_table_base_addr;
+
+	mmhub_update_page_table_config(&config, hws);
+
+	return dc->res_pool->hubbub->funcs->init_dchub_sys_ctx(dc->res_pool->hubbub, &config);
+}
+
+// work around for Renoir s0i3, if register is programmed, bypass golden init.
+
+static bool dcn21_s0i3_golden_init_wa(struct dc *dc)
+{
+	struct dce_hwseq *hws = dc->hwseq;
+	uint32_t value = 0;
+
+	value = REG_READ(MICROSECOND_TIME_BASE_DIV);
+
+	return value != 0x00120464;
+}
+
+void dcn21_exit_optimized_pwr_state(
+		const struct dc *dc,
+		struct dc_state *context)
+{
+	dc->clk_mgr->funcs->update_clocks(
+			dc->clk_mgr,
+			context,
+			false);
+}
+
+void dcn21_optimize_pwr_state(
+		const struct dc *dc,
+		struct dc_state *context)
+{
+	dc->clk_mgr->funcs->update_clocks(
+			dc->clk_mgr,
+			context,
+			true);
+}
+
+void dcn21_hw_sequencer_construct(struct dc *dc)
+{
+	dcn20_hw_sequencer_construct(dc);
+	dc->hwss.init_sys_ctx = dcn21_init_sys_ctx;
+	dc->hwss.s0i3_golden_init_wa = dcn21_s0i3_golden_init_wa;
+	dc->hwss.optimize_pwr_state = dcn21_optimize_pwr_state;
+	dc->hwss.exit_optimized_pwr_state = dcn21_exit_optimized_pwr_state;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
new file mode 100644
index 000000000000..be67b62e6fb1
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hwseq.h
@@ -0,0 +1,33 @@
+/*
+* Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DC_HWSS_DCN21_H__
+#define __DC_HWSS_DCN21_H__
+
+struct dc;
+
+void dcn21_hw_sequencer_construct(struct dc *dc);
+
+#endif /* __DC_HWSS_DCN21_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
new file mode 100644
index 000000000000..e8a504ca5890
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.c
@@ -0,0 +1,470 @@
+/*
+ * 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 "reg_helper.h"
+
+#include <linux/delay.h>
+#include "core_types.h"
+#include "link_encoder.h"
+#include "dcn21_link_encoder.h"
+#include "stream_encoder.h"
+
+#include "i2caux_interface.h"
+#include "dc_bios_types.h"
+
+#include "gpio_service_interface.h"
+
+#define CTX \
+	enc10->base.ctx
+#define DC_LOGGER \
+	enc10->base.ctx->logger
+
+#define REG(reg)\
+	(enc10->link_regs->reg)
+
+#undef FN
+#define FN(reg_name, field_name) \
+	enc10->link_shift->field_name, enc10->link_mask->field_name
+
+#define IND_REG(index) \
+	(enc10->link_regs->index)
+
+static struct mpll_cfg dcn21_mpll_cfg_ref[] = {
+	// RBR
+	{
+		.hdmimode_enable = 0,
+		.ref_range = 1,
+		.ref_clk_mpllb_div = 1,
+		.mpllb_ssc_en = 1,
+		.mpllb_div5_clk_en = 1,
+		.mpllb_multiplier = 238,
+		.mpllb_fracn_en = 0,
+		.mpllb_fracn_quot = 0,
+		.mpllb_fracn_rem = 0,
+		.mpllb_fracn_den = 1,
+		.mpllb_ssc_up_spread = 0,
+		.mpllb_ssc_peak = 44237,
+		.mpllb_ssc_stepsize = 59454,
+		.mpllb_div_clk_en = 0,
+		.mpllb_div_multiplier = 0,
+		.mpllb_hdmi_div = 0,
+		.mpllb_tx_clk_div = 2,
+		.tx_vboost_lvl = 5,
+		.mpllb_pmix_en = 1,
+		.mpllb_word_div2_en = 0,
+		.mpllb_ana_v2i = 2,
+		.mpllb_ana_freq_vco = 2,
+		.mpllb_ana_cp_int = 9,
+		.mpllb_ana_cp_prop = 15,
+		.hdmi_pixel_clk_div = 0,
+	},
+	// HBR
+	{
+		.hdmimode_enable = 0,
+		.ref_range = 1,
+		.ref_clk_mpllb_div = 1,
+		.mpllb_ssc_en = 1,
+		.mpllb_div5_clk_en = 1,
+		.mpllb_multiplier = 192,
+		.mpllb_fracn_en = 1,
+		.mpllb_fracn_quot = 32768,
+		.mpllb_fracn_rem = 0,
+		.mpllb_fracn_den = 1,
+		.mpllb_ssc_up_spread = 0,
+		.mpllb_ssc_peak = 36864,
+		.mpllb_ssc_stepsize = 49545,
+		.mpllb_div_clk_en = 0,
+		.mpllb_div_multiplier = 0,
+		.mpllb_hdmi_div = 0,
+		.mpllb_tx_clk_div = 1,
+		.tx_vboost_lvl = 5,
+		.mpllb_pmix_en = 1,
+		.mpllb_word_div2_en = 0,
+		.mpllb_ana_v2i = 2,
+		.mpllb_ana_freq_vco = 3,
+		.mpllb_ana_cp_int = 9,
+		.mpllb_ana_cp_prop = 15,
+		.hdmi_pixel_clk_div = 0,
+	},
+	//HBR2
+	{
+		.hdmimode_enable = 0,
+		.ref_range = 1,
+		.ref_clk_mpllb_div = 1,
+		.mpllb_ssc_en = 1,
+		.mpllb_div5_clk_en = 1,
+		.mpllb_multiplier = 192,
+		.mpllb_fracn_en = 1,
+		.mpllb_fracn_quot = 32768,
+		.mpllb_fracn_rem = 0,
+		.mpllb_fracn_den = 1,
+		.mpllb_ssc_up_spread = 0,
+		.mpllb_ssc_peak = 36864,
+		.mpllb_ssc_stepsize = 49545,
+		.mpllb_div_clk_en = 0,
+		.mpllb_div_multiplier = 0,
+		.mpllb_hdmi_div = 0,
+		.mpllb_tx_clk_div = 0,
+		.tx_vboost_lvl = 5,
+		.mpllb_pmix_en = 1,
+		.mpllb_word_div2_en = 0,
+		.mpllb_ana_v2i = 2,
+		.mpllb_ana_freq_vco = 3,
+		.mpllb_ana_cp_int = 9,
+		.mpllb_ana_cp_prop = 15,
+		.hdmi_pixel_clk_div = 0,
+	},
+	//HBR3
+	{
+		.hdmimode_enable = 0,
+		.ref_range = 1,
+		.ref_clk_mpllb_div = 1,
+		.mpllb_ssc_en = 1,
+		.mpllb_div5_clk_en = 1,
+		.mpllb_multiplier = 304,
+		.mpllb_fracn_en = 1,
+		.mpllb_fracn_quot = 49152,
+		.mpllb_fracn_rem = 0,
+		.mpllb_fracn_den = 1,
+		.mpllb_ssc_up_spread = 0,
+		.mpllb_ssc_peak = 55296,
+		.mpllb_ssc_stepsize = 74318,
+		.mpllb_div_clk_en = 0,
+		.mpllb_div_multiplier = 0,
+		.mpllb_hdmi_div = 0,
+		.mpllb_tx_clk_div = 0,
+		.tx_vboost_lvl = 5,
+		.mpllb_pmix_en = 1,
+		.mpllb_word_div2_en = 0,
+		.mpllb_ana_v2i = 2,
+		.mpllb_ana_freq_vco = 1,
+		.mpllb_ana_cp_int = 7,
+		.mpllb_ana_cp_prop = 16,
+		.hdmi_pixel_clk_div = 0,
+	},
+};
+
+
+static bool update_cfg_data(
+		struct dcn10_link_encoder *enc10,
+		const struct dc_link_settings *link_settings,
+		struct dpcssys_phy_seq_cfg *cfg)
+{
+	int i;
+
+	cfg->load_sram_fw = false;
+	cfg->use_calibration_setting = true;
+
+	//TODO: need to implement a proper lane mapping for Renoir.
+	for (i = 0; i < 4; i++)
+		cfg->lane_en[i] = true;
+
+	switch (link_settings->link_rate) {
+	case LINK_RATE_LOW:
+		cfg->mpll_cfg = dcn21_mpll_cfg_ref[0];
+		break;
+	case LINK_RATE_HIGH:
+		cfg->mpll_cfg = dcn21_mpll_cfg_ref[1];
+		break;
+	case LINK_RATE_HIGH2:
+		cfg->mpll_cfg = dcn21_mpll_cfg_ref[2];
+		break;
+	case LINK_RATE_HIGH3:
+		cfg->mpll_cfg = dcn21_mpll_cfg_ref[3];
+		break;
+	default:
+		DC_LOG_ERROR("%s: No supported link rate found %X!\n",
+				__func__, link_settings->link_rate);
+		return false;
+	}
+
+	return true;
+}
+
+void dcn21_link_encoder_get_max_link_cap(struct link_encoder *enc,
+	struct dc_link_settings *link_settings)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t value;
+
+	REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DP4, &value);
+
+	if (!value && link_settings->lane_count > LANE_COUNT_TWO)
+		link_settings->lane_count = LANE_COUNT_TWO;
+}
+
+bool dcn21_link_encoder_is_in_alt_mode(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	uint32_t value;
+
+	REG_GET(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DPALT_DISABLE, &value);
+
+	// if value == 1 alt mode is disabled, otherwise it is enabled
+	return !value;
+}
+
+bool dcn21_link_encoder_acquire_phy(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	int value;
+
+	if (enc->features.flags.bits.DP_IS_USB_C) {
+		REG_GET(RDPCSTX_PHY_CNTL6,
+				RDPCS_PHY_DPALT_DISABLE, &value);
+
+		if (value == 1) {
+			ASSERT(0);
+			return false;
+		}
+		REG_UPDATE(RDPCSTX_PHY_CNTL6,
+				RDPCS_PHY_DPALT_DISABLE_ACK, 0);
+
+		udelay(40);
+
+		REG_GET(RDPCSTX_PHY_CNTL6,
+						RDPCS_PHY_DPALT_DISABLE, &value);
+		if (value == 1) {
+			ASSERT(0);
+			REG_UPDATE(RDPCSTX_PHY_CNTL6,
+					RDPCS_PHY_DPALT_DISABLE_ACK, 1);
+			return false;
+		}
+	}
+
+	REG_UPDATE(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_REF_CLK_EN, 1);
+
+	return true;
+}
+
+
+
+static void dcn21_link_encoder_release_phy(struct link_encoder *enc)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+
+	if (enc->features.flags.bits.DP_IS_USB_C) {
+		REG_UPDATE(RDPCSTX_PHY_CNTL6,
+				RDPCS_PHY_DPALT_DISABLE_ACK, 1);
+	}
+
+	REG_UPDATE(RDPCSTX_PHY_CNTL6, RDPCS_PHY_DP_REF_CLK_EN, 0);
+
+}
+
+void dcn21_link_encoder_enable_dp_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source)
+{
+	struct dcn10_link_encoder *enc10 = TO_DCN10_LINK_ENC(enc);
+	struct dcn21_link_encoder *enc21 = (struct dcn21_link_encoder *) enc10;
+	struct dpcssys_phy_seq_cfg *cfg = &enc21->phy_seq_cfg;
+
+	if (!dcn21_link_encoder_acquire_phy(enc))
+		return;
+
+	if (!enc->ctx->dc->debug.avoid_vbios_exec_table) {
+		dcn10_link_encoder_enable_dp_output(enc, link_settings, clock_source);
+		return;
+	}
+
+	if (!update_cfg_data(enc10, link_settings, cfg))
+		return;
+
+	enc1_configure_encoder(enc10, link_settings);
+
+	dcn10_link_encoder_setup(enc, SIGNAL_TYPE_DISPLAY_PORT);
+
+}
+
+void dcn21_link_encoder_enable_dp_mst_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source)
+{
+	if (!dcn21_link_encoder_acquire_phy(enc))
+		return;
+
+	dcn10_link_encoder_enable_dp_mst_output(enc, link_settings, clock_source);
+}
+
+void dcn21_link_encoder_disable_output(
+	struct link_encoder *enc,
+	enum signal_type signal)
+{
+	dcn10_link_encoder_disable_output(enc, signal);
+
+	if (dc_is_dp_signal(signal))
+		dcn21_link_encoder_release_phy(enc);
+}
+
+
+static const struct link_encoder_funcs dcn21_link_enc_funcs = {
+#ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
+	.read_state = link_enc2_read_state,
+#endif
+	.validate_output_with_stream =
+		dcn10_link_encoder_validate_output_with_stream,
+	.hw_init = enc2_hw_init,
+	.setup = dcn10_link_encoder_setup,
+	.enable_tmds_output = dcn10_link_encoder_enable_tmds_output,
+	.enable_dp_output = dcn21_link_encoder_enable_dp_output,
+	.enable_dp_mst_output = dcn21_link_encoder_enable_dp_mst_output,
+	.disable_output = dcn21_link_encoder_disable_output,
+	.dp_set_lane_settings = dcn10_link_encoder_dp_set_lane_settings,
+	.dp_set_phy_pattern = dcn10_link_encoder_dp_set_phy_pattern,
+	.update_mst_stream_allocation_table =
+		dcn10_link_encoder_update_mst_stream_allocation_table,
+	.psr_program_dp_dphy_fast_training =
+			dcn10_psr_program_dp_dphy_fast_training,
+	.psr_program_secondary_packet = dcn10_psr_program_secondary_packet,
+	.connect_dig_be_to_fe = dcn10_link_encoder_connect_dig_be_to_fe,
+	.enable_hpd = dcn10_link_encoder_enable_hpd,
+	.disable_hpd = dcn10_link_encoder_disable_hpd,
+	.is_dig_enabled = dcn10_is_dig_enabled,
+	.destroy = dcn10_link_encoder_destroy,
+	.fec_set_enable = enc2_fec_set_enable,
+	.fec_set_ready = enc2_fec_set_ready,
+	.fec_is_active = enc2_fec_is_active,
+	.get_dig_frontend = dcn10_get_dig_frontend,
+	.is_in_alt_mode = dcn21_link_encoder_is_in_alt_mode,
+	.get_max_link_cap = dcn21_link_encoder_get_max_link_cap,
+};
+
+void dcn21_link_encoder_construct(
+	struct dcn21_link_encoder *enc21,
+	const struct encoder_init_data *init_data,
+	const struct encoder_feature_support *enc_features,
+	const struct dcn10_link_enc_registers *link_regs,
+	const struct dcn10_link_enc_aux_registers *aux_regs,
+	const struct dcn10_link_enc_hpd_registers *hpd_regs,
+	const struct dcn10_link_enc_shift *link_shift,
+	const struct dcn10_link_enc_mask *link_mask)
+{
+	struct bp_encoder_cap_info bp_cap_info = {0};
+	const struct dc_vbios_funcs *bp_funcs = init_data->ctx->dc_bios->funcs;
+	enum bp_result result = BP_RESULT_OK;
+	struct dcn10_link_encoder *enc10 = &enc21->enc10;
+
+	enc10->base.funcs = &dcn21_link_enc_funcs;
+	enc10->base.ctx = init_data->ctx;
+	enc10->base.id = init_data->encoder;
+
+	enc10->base.hpd_source = init_data->hpd_source;
+	enc10->base.connector = init_data->connector;
+
+	enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
+
+	enc10->base.features = *enc_features;
+
+	enc10->base.transmitter = init_data->transmitter;
+
+	/* set the flag to indicate whether driver poll the I2C data pin
+	 * while doing the DP sink detect
+	 */
+
+/*	if (dal_adapter_service_is_feature_supported(as,
+		FEATURE_DP_SINK_DETECT_POLL_DATA_PIN))
+		enc10->base.features.flags.bits.
+			DP_SINK_DETECT_POLL_DATA_PIN = true;*/
+
+	enc10->base.output_signals =
+		SIGNAL_TYPE_DVI_SINGLE_LINK |
+		SIGNAL_TYPE_DVI_DUAL_LINK |
+		SIGNAL_TYPE_LVDS |
+		SIGNAL_TYPE_DISPLAY_PORT |
+		SIGNAL_TYPE_DISPLAY_PORT_MST |
+		SIGNAL_TYPE_EDP |
+		SIGNAL_TYPE_HDMI_TYPE_A;
+
+	/* For DCE 8.0 and 8.1, by design, UNIPHY is hardwired to DIG_BE.
+	 * SW always assign DIG_FE 1:1 mapped to DIG_FE for non-MST UNIPHY.
+	 * SW assign DIG_FE to non-MST UNIPHY first and MST last. So prefer
+	 * DIG is per UNIPHY and used by SST DP, eDP, HDMI, DVI and LVDS.
+	 * Prefer DIG assignment is decided by board design.
+	 * For DCE 8.0, there are only max 6 UNIPHYs, we assume board design
+	 * and VBIOS will filter out 7 UNIPHY for DCE 8.0.
+	 * By this, adding DIGG should not hurt DCE 8.0.
+	 * This will let DCE 8.1 share DCE 8.0 as much as possible
+	 */
+
+	enc10->link_regs = link_regs;
+	enc10->aux_regs = aux_regs;
+	enc10->hpd_regs = hpd_regs;
+	enc10->link_shift = link_shift;
+	enc10->link_mask = link_mask;
+
+	switch (enc10->base.transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		enc10->base.preferred_engine = ENGINE_ID_DIGA;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		enc10->base.preferred_engine = ENGINE_ID_DIGB;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		enc10->base.preferred_engine = ENGINE_ID_DIGC;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		enc10->base.preferred_engine = ENGINE_ID_DIGD;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		enc10->base.preferred_engine = ENGINE_ID_DIGE;
+	break;
+	case TRANSMITTER_UNIPHY_F:
+		enc10->base.preferred_engine = ENGINE_ID_DIGF;
+	break;
+	case TRANSMITTER_UNIPHY_G:
+		enc10->base.preferred_engine = ENGINE_ID_DIGG;
+	break;
+	default:
+		ASSERT_CRITICAL(false);
+		enc10->base.preferred_engine = ENGINE_ID_UNKNOWN;
+	}
+
+	/* default to one to mirror Windows behavior */
+	enc10->base.features.flags.bits.HDMI_6GB_EN = 1;
+
+	result = bp_funcs->get_encoder_cap_info(enc10->base.ctx->dc_bios,
+						enc10->base.id, &bp_cap_info);
+
+	/* Override features with DCE-specific values */
+	if (result == BP_RESULT_OK) {
+		enc10->base.features.flags.bits.IS_HBR2_CAPABLE =
+				bp_cap_info.DP_HBR2_EN;
+		enc10->base.features.flags.bits.IS_HBR3_CAPABLE =
+				bp_cap_info.DP_HBR3_EN;
+		enc10->base.features.flags.bits.HDMI_6GB_EN = bp_cap_info.HDMI_6GB_EN;
+		enc10->base.features.flags.bits.DP_IS_USB_C =
+				bp_cap_info.DP_IS_USB_C;
+	} else {
+		DC_LOG_WARNING("%s: Failed to get encoder_cap_info from VBIOS with error code %d!\n",
+				__func__,
+				result);
+	}
+	if (enc10->base.ctx->dc->debug.hdmi20_disable) {
+		enc10->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
new file mode 100644
index 000000000000..1d7a1a51f13d
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_link_encoder.h
@@ -0,0 +1,61 @@
+/*
+ * 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 __DC_LINK_ENCODER__DCN21_H__
+#define __DC_LINK_ENCODER__DCN21_H__
+
+#include "dcn20/dcn20_link_encoder.h"
+
+struct dcn21_link_encoder {
+	struct dcn10_link_encoder enc10;
+	struct dpcssys_phy_seq_cfg phy_seq_cfg;
+};
+
+#define LINK_ENCODER_MASK_SH_LIST_DCN21(mask_sh)\
+	LINK_ENCODER_MASK_SH_LIST_DCN20(mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL0_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL1_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL2_XBAR_SOURCE, mask_sh),\
+	LE_SF(UNIPHYA_CHANNEL_XBAR_CNTL, UNIPHY_CHANNEL3_XBAR_SOURCE, mask_sh), \
+	SRI(RDPCSTX_PHY_FUSE2, RDPCSTX, id), \
+	SRI(RDPCSTX_PHY_FUSE3, RDPCSTX, id), \
+	SR(RDPCSTX0_RDPCSTX_SCRATCH)
+
+void dcn21_link_encoder_enable_dp_output(
+	struct link_encoder *enc,
+	const struct dc_link_settings *link_settings,
+	enum clock_source_id clock_source);
+
+void dcn21_link_encoder_construct(
+	struct dcn21_link_encoder *enc21,
+	const struct encoder_init_data *init_data,
+	const struct encoder_feature_support *enc_features,
+	const struct dcn10_link_enc_registers *link_regs,
+	const struct dcn10_link_enc_aux_registers *aux_regs,
+	const struct dcn10_link_enc_hpd_registers *hpd_regs,
+	const struct dcn10_link_enc_shift *link_shift,
+	const struct dcn10_link_enc_mask *link_mask);
+
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
index de182185fe1f..459bd9a5caed 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_resource.c
@@ -23,8 +23,6 @@
  *
  */
 
-#include <linux/slab.h>
-
 #include "dm_services.h"
 #include "dc.h"
 
@@ -42,11 +40,11 @@
 #include "irq/dcn21/irq_service_dcn21.h"
 #include "dcn20/dcn20_dpp.h"
 #include "dcn20/dcn20_optc.h"
-#include "dcn20/dcn20_hwseq.h"
+#include "dcn21/dcn21_hwseq.h"
 #include "dce110/dce110_hw_sequencer.h"
 #include "dcn20/dcn20_opp.h"
 #include "dcn20/dcn20_dsc.h"
-#include "dcn20/dcn20_link_encoder.h"
+#include "dcn21/dcn21_link_encoder.h"
 #include "dcn20/dcn20_stream_encoder.h"
 #include "dce/dce_clock_source.h"
 #include "dce/dce_audio.h"
@@ -84,8 +82,9 @@
 
 
 struct _vcs_dpi_ip_params_st dcn2_1_ip = {
-	.gpuvm_enable = 0,
-	.hostvm_enable = 0,
+	.odm_capable = 1,
+	.gpuvm_enable = 1,
+	.hostvm_enable = 1,
 	.gpuvm_max_page_table_levels = 1,
 	.hostvm_max_page_table_levels = 4,
 	.hostvm_cached_page_table_levels = 2,
@@ -205,11 +204,11 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 				.state = 4,
 				.dcfclk_mhz = 810.0,
 				.fabricclk_mhz = 1600.0,
-				.dispclk_mhz = 1015.0,
-				.dppclk_mhz = 1015.0,
-				.phyclk_mhz = 810.0,
+				.dispclk_mhz = 1395.0,
+				.dppclk_mhz = 1285.0,
+				.phyclk_mhz = 1325.0,
 				.socclk_mhz = 953.0,
-				.dscclk_mhz = 318.334,
+				.dscclk_mhz = 489.0,
 				.dram_speed_mts = 4266.0,
 			},
 			/*Extra state, no dispclk ramping*/
@@ -217,18 +216,18 @@ struct _vcs_dpi_soc_bounding_box_st dcn2_1_soc = {
 				.state = 5,
 				.dcfclk_mhz = 810.0,
 				.fabricclk_mhz = 1600.0,
-				.dispclk_mhz = 1015.0,
-				.dppclk_mhz = 1015.0,
-				.phyclk_mhz = 810.0,
+				.dispclk_mhz = 1395.0,
+				.dppclk_mhz = 1285.0,
+				.phyclk_mhz = 1325.0,
 				.socclk_mhz = 953.0,
-				.dscclk_mhz = 318.334,
+				.dscclk_mhz = 489.0,
 				.dram_speed_mts = 4266.0,
 			},
 
 		},
 
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
+	.sr_exit_time_us = 12.5,
+	.sr_enter_plus_exit_time_us = 17.0,
 	.urgent_latency_us = 4.0,
 	.urgent_latency_pixel_data_only_us = 4.0,
 	.urgent_latency_pixel_mixed_with_vm_data_us = 4.0,
@@ -350,6 +349,30 @@ static const struct bios_registers bios_regs = {
 		NBIO_SR(BIOS_SCRATCH_6)
 };
 
+static const struct dce_dmcu_registers dmcu_regs = {
+		DMCU_DCN10_REG_LIST()
+};
+
+static const struct dce_dmcu_shift dmcu_shift = {
+		DMCU_MASK_SH_LIST_DCN10(__SHIFT)
+};
+
+static const struct dce_dmcu_mask dmcu_mask = {
+		DMCU_MASK_SH_LIST_DCN10(_MASK)
+};
+
+static const struct dce_abm_registers abm_regs = {
+		ABM_DCN20_REG_LIST()
+};
+
+static const struct dce_abm_shift abm_shift = {
+		ABM_MASK_SH_LIST_DCN20(__SHIFT)
+};
+
+static const struct dce_abm_mask abm_mask = {
+		ABM_MASK_SH_LIST_DCN20(_MASK)
+};
+
 #ifdef CONFIG_DRM_AMD_DC_DMUB
 static const struct dcn21_dmcub_registers dmcub_regs = {
 		DMCUB_REG_LIST_DCN()
@@ -628,6 +651,14 @@ static const struct dcn10_stream_enc_registers stream_enc_regs[] = {
 	stream_enc_regs(4),
 };
 
+static const struct dce110_aux_registers_shift aux_shift = {
+	DCN_AUX_MASK_SH_LIST(__SHIFT)
+};
+
+static const struct dce110_aux_registers_mask aux_mask = {
+	DCN_AUX_MASK_SH_LIST(_MASK)
+};
+
 static const struct dcn10_stream_encoder_shift se_shift = {
 		SE_COMMON_MASK_SH_LIST_DCN20(__SHIFT)
 };
@@ -636,6 +667,11 @@ static const struct dcn10_stream_encoder_mask se_mask = {
 		SE_COMMON_MASK_SH_LIST_DCN20(_MASK)
 };
 
+static void dcn21_pp_smu_destroy(struct pp_smu_funcs **pp_smu);
+
+static int dcn21_populate_dml_pipes_from_context(
+		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes);
+
 static struct input_pixel_processor *dcn21_ipp_create(
 	struct dc_context *ctx, uint32_t inst)
 {
@@ -683,7 +719,10 @@ static struct dce_aux *dcn21_aux_engine_create(
 
 	dce110_aux_engine_construct(aux_engine, ctx, inst,
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
-				    &aux_engine_regs[inst]);
+				    &aux_engine_regs[inst],
+					&aux_mask,
+					&aux_shift,
+					ctx->dc->caps.extended_aux_timeout_support);
 
 	return &aux_engine->base;
 }
@@ -726,11 +765,12 @@ static const struct resource_caps res_cap_rn = {
 		.num_timing_generator = 4,
 		.num_opp = 4,
 		.num_video_plane = 4,
-		.num_audio = 6, // 6 audio endpoints.  4 audio streams
+		.num_audio = 4, // 4 audio endpoints.  4 audio streams
 		.num_stream_encoder = 5,
 		.num_pll = 5,  // maybe 3 because the last two used for USB-c
 		.num_dwb = 1,
 		.num_ddc = 5,
+		.num_vmid = 1,
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 		.num_dsc = 3,
 #endif
@@ -796,15 +836,15 @@ static const struct dc_debug_options debug_defaults_drv = {
 		.clock_trace = true,
 		.disable_pplib_clock_request = true,
 		.pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
-		.force_single_disp_pipe_split = true,
+		.force_single_disp_pipe_split = false,
 		.disable_dcc = DCC_ENABLE,
 		.vsr_support = true,
 		.performance_trace = false,
-		.max_downscale_src_width = 5120,/*upto 5K*/
+		.max_downscale_src_width = 3840,
 		.disable_pplib_wm_range = false,
 		.scl_reset_length10 = true,
 		.sanity_checks = true,
-		.disable_48mhz_pwrdwn = true,
+		.disable_48mhz_pwrdwn = false,
 };
 
 static const struct dc_debug_options debug_defaults_diags = {
@@ -939,7 +979,7 @@ static void destruct(struct dcn21_resource_pool *pool)
 		dcn_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.pp_smu != NULL)
-		dcn20_pp_smu_destroy(&pool->base.pp_smu);
+		dcn21_pp_smu_destroy(&pool->base.pp_smu);
 }
 
 
@@ -969,11 +1009,35 @@ static void calculate_wm_set_for_vlevel(
 #if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	wm_set->frac_urg_bw_nom = get_fraction_of_urgent_bandwidth(dml, pipes, pipe_cnt) * 1000;
 	wm_set->frac_urg_bw_flip = get_fraction_of_urgent_bandwidth_imm_flip(dml, pipes, pipe_cnt) * 1000;
+	wm_set->urgent_latency_ns = get_urgent_latency(dml, pipes, pipe_cnt) * 1000;
 #endif
 	dml->soc.dram_clock_change_latency_us = dram_clock_change_latency_cached;
 
 }
 
+static void patch_bounding_box(struct dc *dc, struct _vcs_dpi_soc_bounding_box_st *bb)
+{
+	kernel_fpu_begin();
+	if (dc->bb_overrides.sr_exit_time_ns) {
+		bb->sr_exit_time_us = dc->bb_overrides.sr_exit_time_ns / 1000.0;
+	}
+
+	if (dc->bb_overrides.sr_enter_plus_exit_time_ns) {
+		bb->sr_enter_plus_exit_time_us =
+				dc->bb_overrides.sr_enter_plus_exit_time_ns / 1000.0;
+	}
+
+	if (dc->bb_overrides.urgent_latency_ns) {
+		bb->urgent_latency_us = dc->bb_overrides.urgent_latency_ns / 1000.0;
+	}
+
+	if (dc->bb_overrides.dram_clock_change_latency_ns) {
+		bb->dram_clock_change_latency_us =
+				dc->bb_overrides.dram_clock_change_latency_ns / 1000.0;
+	}
+	kernel_fpu_end();
+}
+
 void dcn21_calculate_wm(
 		struct dc *dc, struct dc_state *context,
 		display_e2e_pipe_params_st *pipes,
@@ -988,6 +1052,8 @@ void dcn21_calculate_wm(
 
 	ASSERT(bw_params);
 
+	patch_bounding_box(dc, &context->bw_ctx.dml.soc);
+
 	for (i = 0, pipe_idx = 0, pipe_cnt = 0; i < dc->res_pool->pipe_count; i++) {
 			if (!context->res_ctx.pipe_ctx[i].stream)
 				continue;
@@ -1021,7 +1087,7 @@ void dcn21_calculate_wm(
 			pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc,
 				&context->res_ctx, pipes);
 		else
-			pipe_cnt = dcn20_populate_dml_pipes_from_context(dc,
+			pipe_cnt = dcn21_populate_dml_pipes_from_context(dc,
 				&context->res_ctx, pipes);
 	}
 
@@ -1271,6 +1337,12 @@ struct display_stream_compressor *dcn21_dsc_create(
 
 static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
 {
+	/*
+	TODO: Fix this function to calcualte correct values.
+	There are known issues with this function currently
+	that will need to be investigated. Use hardcoded known good values for now.
+
+
 	struct dcn21_resource_pool *pool = TO_DCN21_RES_POOL(dc->res_pool);
 	struct clk_limit_table *clk_table = &bw_params->clk_table;
 	int i;
@@ -1278,7 +1350,6 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 	dcn2_1_ip.max_num_otg = pool->base.res_cap->num_timing_generator;
 	dcn2_1_ip.max_num_dpp = pool->base.pipe_count;
 	dcn2_1_soc.num_chans = bw_params->num_channels;
-	dcn2_1_soc.num_states = 0;
 
 	for (i = 0; i < clk_table->num_entries; i++) {
 
@@ -1286,10 +1357,11 @@ static void update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_param
 		dcn2_1_soc.clock_limits[i].dcfclk_mhz = clk_table->entries[i].dcfclk_mhz;
 		dcn2_1_soc.clock_limits[i].fabricclk_mhz = clk_table->entries[i].fclk_mhz;
 		dcn2_1_soc.clock_limits[i].socclk_mhz = clk_table->entries[i].socclk_mhz;
-		/* This is probably wrong, TODO: find correct calculation */
 		dcn2_1_soc.clock_limits[i].dram_speed_mts = clk_table->entries[i].memclk_mhz * 16 / 1000;
-		dcn2_1_soc.num_states++;
 	}
+	dcn2_1_soc.clock_limits[i] = dcn2_1_soc.clock_limits[i - i];
+	dcn2_1_soc.num_states = i;
+	*/
 }
 
 /* Temporary Place holder until we can get them from fuse */
@@ -1317,32 +1389,42 @@ static struct dpm_clocks dummy_clocks = {
 
 };
 
-enum pp_smu_status dummy_set_wm_ranges(struct pp_smu *pp,
+static enum pp_smu_status dummy_set_wm_ranges(struct pp_smu *pp,
 		struct pp_smu_wm_range_sets *ranges)
 {
 	return PP_SMU_RESULT_OK;
 }
 
-enum pp_smu_status dummy_get_dpm_clock_table(struct pp_smu *pp,
+static enum pp_smu_status dummy_get_dpm_clock_table(struct pp_smu *pp,
 		struct dpm_clocks *clock_table)
 {
 	*clock_table = dummy_clocks;
 	return PP_SMU_RESULT_OK;
 }
 
-struct pp_smu_funcs *dcn21_pp_smu_create(struct dc_context *ctx)
+static struct pp_smu_funcs *dcn21_pp_smu_create(struct dc_context *ctx)
 {
 	struct pp_smu_funcs *pp_smu = kzalloc(sizeof(*pp_smu), GFP_KERNEL);
 
-	pp_smu->ctx.ver = PP_SMU_VER_RN;
+	if (!pp_smu)
+		return pp_smu;
+
+	if (IS_FPGA_MAXIMUS_DC(ctx->dce_environment) || IS_DIAG_DC(ctx->dce_environment)) {
+		pp_smu->ctx.ver = PP_SMU_VER_RN;
+		pp_smu->rn_funcs.get_dpm_clock_table = dummy_get_dpm_clock_table;
+		pp_smu->rn_funcs.set_wm_ranges = dummy_set_wm_ranges;
+	} else {
 
-	pp_smu->rn_funcs.get_dpm_clock_table = dummy_get_dpm_clock_table;
-	pp_smu->rn_funcs.set_wm_ranges = dummy_set_wm_ranges;
+		dm_pp_get_funcs(ctx, pp_smu);
+
+		if (pp_smu->ctx.ver != PP_SMU_VER_RN)
+			pp_smu = memset(pp_smu, 0, sizeof(struct pp_smu_funcs));
+	}
 
 	return pp_smu;
 }
 
-void dcn21_pp_smu_destroy(struct pp_smu_funcs **pp_smu)
+static void dcn21_pp_smu_destroy(struct pp_smu_funcs **pp_smu)
 {
 	if (pp_smu && *pp_smu) {
 		kfree(*pp_smu);
@@ -1400,6 +1482,7 @@ static struct dce_hwseq *dcn21_hwseq_create(
 		hws->regs = &hwseq_reg;
 		hws->shifts = &hwseq_shift;
 		hws->masks = &hwseq_mask;
+		hws->wa.DEGVIDCN21 = true;
 	}
 	return hws;
 }
@@ -1418,10 +1501,152 @@ static const struct resource_create_funcs res_create_maximus_funcs = {
 	.create_hwseq = dcn21_hwseq_create,
 };
 
+static const struct encoder_feature_support link_enc_feature = {
+		.max_hdmi_deep_color = COLOR_DEPTH_121212,
+		.max_hdmi_pixel_clock = 600000,
+		.hdmi_ycbcr420_supported = true,
+		.dp_ycbcr420_supported = true,
+		.flags.bits.IS_HBR2_CAPABLE = true,
+		.flags.bits.IS_HBR3_CAPABLE = true,
+		.flags.bits.IS_TPS3_CAPABLE = true,
+		.flags.bits.IS_TPS4_CAPABLE = true
+};
+
+
+#define link_regs(id, phyid)\
+[id] = {\
+	LE_DCN10_REG_LIST(id), \
+	UNIPHY_DCN2_REG_LIST(phyid), \
+	SRI(DP_DPHY_INTERNAL_CTRL, DP, id) \
+}
+
+static const struct dcn10_link_enc_registers link_enc_regs[] = {
+	link_regs(0, A),
+	link_regs(1, B),
+	link_regs(2, C),
+	link_regs(3, D),
+	link_regs(4, E),
+};
+
+#define aux_regs(id)\
+[id] = {\
+	DCN2_AUX_REG_LIST(id)\
+}
+
+static const struct dcn10_link_enc_aux_registers link_enc_aux_regs[] = {
+		aux_regs(0),
+		aux_regs(1),
+		aux_regs(2),
+		aux_regs(3),
+		aux_regs(4)
+};
+
+#define hpd_regs(id)\
+[id] = {\
+	HPD_REG_LIST(id)\
+}
+
+static const struct dcn10_link_enc_hpd_registers link_enc_hpd_regs[] = {
+		hpd_regs(0),
+		hpd_regs(1),
+		hpd_regs(2),
+		hpd_regs(3),
+		hpd_regs(4)
+};
+
+static const struct dcn10_link_enc_shift le_shift = {
+	LINK_ENCODER_MASK_SH_LIST_DCN20(__SHIFT)
+};
+
+static const struct dcn10_link_enc_mask le_mask = {
+	LINK_ENCODER_MASK_SH_LIST_DCN20(_MASK)
+};
+
+static int map_transmitter_id_to_phy_instance(
+	enum transmitter transmitter)
+{
+	switch (transmitter) {
+	case TRANSMITTER_UNIPHY_A:
+		return 0;
+	break;
+	case TRANSMITTER_UNIPHY_B:
+		return 1;
+	break;
+	case TRANSMITTER_UNIPHY_C:
+		return 2;
+	break;
+	case TRANSMITTER_UNIPHY_D:
+		return 3;
+	break;
+	case TRANSMITTER_UNIPHY_E:
+		return 4;
+	break;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
+static struct link_encoder *dcn21_link_encoder_create(
+	const struct encoder_init_data *enc_init_data)
+{
+	struct dcn21_link_encoder *enc21 =
+		kzalloc(sizeof(struct dcn21_link_encoder), GFP_KERNEL);
+	int link_regs_id;
+
+	if (!enc21)
+		return NULL;
+
+	link_regs_id =
+		map_transmitter_id_to_phy_instance(enc_init_data->transmitter);
+
+	dcn21_link_encoder_construct(enc21,
+				      enc_init_data,
+				      &link_enc_feature,
+				      &link_enc_regs[link_regs_id],
+				      &link_enc_aux_regs[enc_init_data->channel - 1],
+				      &link_enc_hpd_regs[enc_init_data->hpd_source],
+				      &le_shift,
+				      &le_mask);
+
+	return &enc21->enc10.base;
+}
+#define CTX ctx
+
+#define REG(reg_name) \
+	(DCN_BASE.instance[0].segment[mm ## reg_name ## _BASE_IDX] + mm ## reg_name)
+
+static uint32_t read_pipe_fuses(struct dc_context *ctx)
+{
+	uint32_t value = REG_READ(CC_DC_PIPE_DIS);
+	/* RV1 support max 4 pipes */
+	value = value & 0xf;
+	return value;
+}
+
+static int dcn21_populate_dml_pipes_from_context(
+		struct dc *dc, struct resource_context *res_ctx, display_e2e_pipe_params_st *pipes)
+{
+	uint32_t pipe_cnt = dcn20_populate_dml_pipes_from_context(dc, res_ctx, pipes);
+	int i;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+
+		if (!res_ctx->pipe_ctx[i].stream)
+			continue;
+
+		pipes[i].pipe.src.hostvm = 1;
+		pipes[i].pipe.src.gpuvm = 1;
+	}
+
+	return pipe_cnt;
+}
+
 static struct resource_funcs dcn21_res_pool_funcs = {
 	.destroy = dcn21_destroy_resource_pool,
-	.link_enc_create = dcn20_link_encoder_create,
+	.link_enc_create = dcn21_link_encoder_create,
 	.validate_bandwidth = dcn21_validate_bandwidth,
+	.populate_dml_pipes = dcn21_populate_dml_pipes_from_context,
 	.add_stream_to_ctx = dcn20_add_stream_to_ctx,
 	.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
 	.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
@@ -1437,9 +1662,11 @@ static bool construct(
 	struct dc *dc,
 	struct dcn21_resource_pool *pool)
 {
-	int i;
+	int i, j;
 	struct dc_context *ctx = dc->ctx;
 	struct irq_service_init_data init_data;
+	uint32_t pipe_fuses = read_pipe_fuses(ctx);
+	uint32_t num_pipes;
 
 	ctx->dc_bios->regs = &bios_regs;
 
@@ -1457,7 +1684,9 @@ static bool construct(
 	 *************************************************/
 	pool->base.underlay_pipe_index = NO_UNDERLAY_PIPE;
 
-	pool->base.pipe_count = 4;
+	/* max pipe num for ASIC before check pipe fuses */
+	pool->base.pipe_count = pool->base.res_cap->num_timing_generator;
+
 	dc->caps.max_downscale_ratio = 200;
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 256;
@@ -1467,6 +1696,7 @@ static bool construct(
 	dc->caps.max_slave_planes = 1;
 	dc->caps.post_blend_color_processing = true;
 	dc->caps.force_dp_tps4_for_cp2520 = true;
+	dc->caps.extended_aux_timeout_support = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
@@ -1516,6 +1746,26 @@ static bool construct(
 		goto create_fail;
 	}
 
+	pool->base.dmcu = dcn20_dmcu_create(ctx,
+			&dmcu_regs,
+			&dmcu_shift,
+			&dmcu_mask);
+	if (pool->base.dmcu == NULL) {
+		dm_error("DC: failed to create dmcu!\n");
+		BREAK_TO_DEBUGGER();
+		goto create_fail;
+	}
+
+	pool->base.abm = dce_abm_create(ctx,
+			&abm_regs,
+			&abm_shift,
+			&abm_mask);
+	if (pool->base.abm == NULL) {
+		dm_error("DC: failed to create abm!\n");
+		BREAK_TO_DEBUGGER();
+		goto create_fail;
+	}
+
 #ifdef CONFIG_DRM_AMD_DC_DMUB
 	pool->base.dmcub = dcn21_dmcub_create(ctx,
 			&dmcub_regs,
@@ -1530,6 +1780,14 @@ static bool construct(
 
 	pool->base.pp_smu = dcn21_pp_smu_create(ctx);
 
+	num_pipes = dcn2_1_ip.max_num_dpp;
+
+	for (i = 0; i < dcn2_1_ip.max_num_dpp; i++)
+		if (pipe_fuses & 1 << i)
+			num_pipes--;
+	dcn2_1_ip.max_num_dpp = num_pipes;
+	dcn2_1_ip.max_num_otg = num_pipes;
+
 	dml_init_instance(&dc->dml, &dcn2_1_soc, &dcn2_1_ip, DML_PROJECT_DCN21);
 
 	init_data.ctx = dc->ctx;
@@ -1537,8 +1795,15 @@ static bool construct(
 	if (!pool->base.irqs)
 		goto create_fail;
 
+	j = 0;
 	/* mem input -> ipp -> dpp -> opp -> TG */
 	for (i = 0; i < pool->base.pipe_count; i++) {
+		/* if pipe is disabled, skip instance of HW pipe,
+		 * i.e, skip ASIC register instance
+		 */
+		if ((pipe_fuses & (1 << i)) != 0)
+			continue;
+
 		pool->base.hubps[i] = dcn21_hubp_create(ctx, i);
 		if (pool->base.hubps[i] == NULL) {
 			BREAK_TO_DEBUGGER();
@@ -1562,6 +1827,23 @@ static bool construct(
 				"DC: failed to create dpps!\n");
 			goto create_fail;
 		}
+
+		pool->base.opps[i] = dcn21_opp_create(ctx, i);
+		if (pool->base.opps[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC: failed to create output pixel processor!\n");
+			goto create_fail;
+		}
+
+		pool->base.timing_generators[i] = dcn21_timing_generator_create(
+				ctx, i);
+		if (pool->base.timing_generators[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error("DC: failed to create tg!\n");
+			goto create_fail;
+		}
+		j++;
 	}
 
 	for (i = 0; i < pool->base.res_cap->num_ddc; i++) {
@@ -1582,27 +1864,9 @@ static bool construct(
 		pool->base.sw_i2cs[i] = NULL;
 	}
 
-	for (i = 0; i < pool->base.res_cap->num_opp; i++) {
-		pool->base.opps[i] = dcn21_opp_create(ctx, i);
-		if (pool->base.opps[i] == NULL) {
-			BREAK_TO_DEBUGGER();
-			dm_error(
-				"DC: failed to create output pixel processor!\n");
-			goto create_fail;
-		}
-	}
-
-	for (i = 0; i < pool->base.res_cap->num_timing_generator; i++) {
-		pool->base.timing_generators[i] = dcn21_timing_generator_create(
-				ctx, i);
-		if (pool->base.timing_generators[i] == NULL) {
-			BREAK_TO_DEBUGGER();
-			dm_error("DC: failed to create tg!\n");
-			goto create_fail;
-		}
-	}
-
-	pool->base.timing_generator_count = i;
+	pool->base.timing_generator_count = j;
+	pool->base.pipe_count = j;
+	pool->base.mpcc_count = j;
 
 	pool->base.mpc = dcn21_mpc_create(ctx);
 	if (pool->base.mpc == NULL) {
@@ -1645,7 +1909,7 @@ static bool construct(
 			&res_create_funcs : &res_create_maximus_funcs)))
 			goto create_fail;
 
-	dcn20_hw_sequencer_construct(dc);
+	dcn21_hw_sequencer_construct(dc);
 
 	dc->caps.max_planes =  pool->base.pipe_count;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h b/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h
new file mode 100644
index 000000000000..626d22d437f4
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dm_cp_psp.h
@@ -0,0 +1,49 @@
+/*
+ * 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 DM_CP_PSP_IF__H
+#define DM_CP_PSP_IF__H
+
+struct dc_link;
+
+struct cp_psp_stream_config {
+	uint8_t otg_inst;
+	uint8_t link_enc_inst;
+	uint8_t stream_enc_inst;
+	void *dm_stream_ctx;
+	bool dpms_off;
+};
+
+struct cp_psp_funcs {
+	void (*update_stream_config)(void *handle, struct cp_psp_stream_config *config);
+};
+
+struct cp_psp {
+	void *handle;
+	struct cp_psp_funcs funcs;
+};
+
+
+#endif /* DM_CP_PSP_IF__H */
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index b6b4333737f2..94b75e942607 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -74,7 +74,7 @@ void dm_helpers_dp_mst_clear_payload_allocation_table(
 /*
  * Polls for ACT (allocation change trigger) handled and
  */
-bool dm_helpers_dp_mst_poll_for_allocation_change_trigger(
+enum act_return_status dm_helpers_dp_mst_poll_for_allocation_change_trigger(
 		struct dc_context *ctx,
 		const struct dc_stream_state *stream);
 /*
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 c03a441ee638..ef7df9ef6d7e 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -249,10 +249,8 @@ struct pp_smu_funcs_nv {
 };
 #endif
 
-#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
-
 #define PP_SMU_NUM_SOCCLK_DPM_LEVELS  8
-#define PP_SMU_NUM_DCFCLK_DPM_LEVELS  4
+#define PP_SMU_NUM_DCFCLK_DPM_LEVELS  8
 #define PP_SMU_NUM_FCLK_DPM_LEVELS    4
 #define PP_SMU_NUM_MEMCLK_DPM_LEVELS  4
 
@@ -288,7 +286,6 @@ struct pp_smu_funcs_rn {
 	enum pp_smu_status (*get_dpm_clock_table) (struct pp_smu *pp,
 			struct dpm_clocks *clock_table);
 };
-#endif
 
 struct pp_smu_funcs {
 	struct pp_smu ctx;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index 5b2a65b42403..8df251626e22 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -24,15 +24,20 @@
 # It provides the general basic services required by other DAL
 # subcomponents.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dml_ccflags := -mhard-float -msse
 
-dml_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dml_ccflags += -mpreferred-stack-boundary=4
+else
 dml_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
index 649883777f62..6c6c486b774a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20.c
@@ -2577,7 +2577,8 @@ static void dml20_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPer
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
 		if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 0fafd693ffb4..3c70dd577292 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -38,6 +38,7 @@
 
 #define BPP_INVALID 0
 #define BPP_BLENDED_PIPE 0xffffffff
+#define DCN20_MAX_DSC_IMAGE_WIDTH 5184
 
 static double adjust_ReturnBW(
 		struct display_mode_lib *mode_lib,
@@ -2610,7 +2611,8 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
 			mode_lib->vba.MinActiveDRAMClockChangeMargin
 					+ mode_lib->vba.DRAMClockChangeLatency;
 
-	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 0) {
+	if (mode_lib->vba.MinActiveDRAMClockChangeMargin > 50) {
+		mode_lib->vba.DRAMClockChangeWatermark += 25;
 		mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
 	} else {
 		if (mode_lib->vba.SynchronizedVBlank || mode_lib->vba.NumberOfActivePlanes == 1) {
@@ -3901,6 +3903,10 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 				mode_lib->vba.MaximumSwathWidthInLineBuffer);
 	}
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
+		double MaxMaxDispclkRoundedDown = RoundToDFSGranularityDown(
+			mode_lib->vba.MaxDispclk[mode_lib->vba.soc.num_states],
+			mode_lib->vba.DISPCLKDPPCLKVCOSpeed);
+
 		for (j = 0; j < 2; j++) {
 			mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity = RoundToDFSGranularityDown(
 				mode_lib->vba.MaxDispclk[i],
@@ -3925,7 +3931,9 @@ void dml20v2_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode
 						&& i == mode_lib->vba.soc.num_states)
 					mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2
 							* (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
-				if (mode_lib->vba.ODMCapability == false || mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine <= mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) {
+				if (mode_lib->vba.ODMCapability == false ||
+						(locals->PlaneRequiredDISPCLKWithoutODMCombine <= MaxMaxDispclkRoundedDown
+							&& (!locals->DSCEnabled[k] || locals->HActive[k] <= DCN20_MAX_DSC_IMAGE_WIDTH))) {
 					locals->ODMCombineEnablePerState[i][k] = false;
 					mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine;
 				} else {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
index 878bf4782ce6..2c7455e22a65 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20.c
@@ -207,7 +207,7 @@ static void extract_rq_regs(struct display_mode_lib *mode_lib,
 	rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height);
 	rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height);
 
-	// FIXME: take the max between luma, chroma chunk size?
+	// TODO: take the max between luma, chroma chunk size?
 	// okay for now, as we are setting chunk_bytes to 8kb anyways
 	if (rq_param.sizing.rq_l.chunk_bytes >= 32 * 1024) { //32kb
 		rq_regs->drq_expansion_mode = 0;
@@ -677,7 +677,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib,
 	unsigned int meta_pitch = 0;
 	unsigned int ppe = mode_422 ? 2 : 1;
 
-	// FIXME check if ppe apply for both luma and chroma in 422 case
+	// TODO check if ppe apply for both luma and chroma in 422 case
 	if (is_chroma) {
 		vp_width = pipe_src_param.viewport_width_c / ppe;
 		vp_height = pipe_src_param.viewport_height_c;
@@ -959,7 +959,7 @@ static void dml20_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	// Source
 //             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class)(src->source_format));
-	mode_422 = 0; // FIXME
+	mode_422 = 0; // TODO
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
@@ -1655,7 +1655,7 @@ static void calculate_ttu_cursor(struct display_mode_lib *mode_lib,
 		cur_width_ub = dml_ceil((double) cur_src_width / (double) cur_req_width, 1)
 				* (double) cur_req_width;
 		cur_req_per_width = cur_width_ub / (double) cur_req_width;
-		hactive_cur = (double) cur_src_width / hscl_ratio; // FIXME: oswin to think about what to do for cursor
+		hactive_cur = (double) cur_src_width / hscl_ratio; // TODO: oswin to think about what to do for cursor
 
 		if (vratio_pre_l <= 1.0) {
 			*refcyc_per_req_delivery_pre_cur = hactive_cur * ref_freq_to_pix_freq
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
index ed8bf5f723c9..1e6aeb1bd2bf 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c
@@ -207,7 +207,7 @@ static void extract_rq_regs(struct display_mode_lib *mode_lib,
 	rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height);
 	rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height);
 
-	// FIXME: take the max between luma, chroma chunk size?
+	// TODO: take the max between luma, chroma chunk size?
 	// okay for now, as we are setting chunk_bytes to 8kb anyways
 	if (rq_param.sizing.rq_l.chunk_bytes >= 32 * 1024) { //32kb
 		rq_regs->drq_expansion_mode = 0;
@@ -677,7 +677,7 @@ static void get_surf_rq_param(struct display_mode_lib *mode_lib,
 	unsigned int meta_pitch = 0;
 	unsigned int ppe = mode_422 ? 2 : 1;
 
-	// FIXME check if ppe apply for both luma and chroma in 422 case
+	// TODO check if ppe apply for both luma and chroma in 422 case
 	if (is_chroma) {
 		vp_width = pipe_src_param.viewport_width_c / ppe;
 		vp_height = pipe_src_param.viewport_height_c;
@@ -959,7 +959,7 @@ static void dml20v2_rq_dlg_get_dlg_params(struct display_mode_lib *mode_lib,
 	// Source
 //             dcc_en              = src.dcc;
 	dual_plane = is_dual_plane((enum source_format_class)(src->source_format));
-	mode_422 = 0; // FIXME
+	mode_422 = 0; // TODO
 	access_dir = (src->source_scan == dm_vert); // vp access direction: horizontal or vertical accessed
 //      bytes_per_element_l = get_bytes_per_element(source_format_class(src.source_format), 0);
 //      bytes_per_element_c = get_bytes_per_element(source_format_class(src.source_format), 1);
@@ -1655,7 +1655,7 @@ static void calculate_ttu_cursor(struct display_mode_lib *mode_lib,
 		cur_width_ub = dml_ceil((double) cur_src_width / (double) cur_req_width, 1)
 				* (double) cur_req_width;
 		cur_req_per_width = cur_width_ub / (double) cur_req_width;
-		hactive_cur = (double) cur_src_width / hscl_ratio; // FIXME: oswin to think about what to do for cursor
+		hactive_cur = (double) cur_src_width / hscl_ratio; // TODO: oswin to think about what to do for cursor
 
 		if (vratio_pre_l <= 1.0) {
 			*refcyc_per_req_delivery_pre_cur = hactive_cur * ref_freq_to_pix_freq
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
index 3b6ed60dcd35..ba77957aefe3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_mode_vba_21.c
@@ -65,6 +65,7 @@ typedef struct {
 
 #define BPP_INVALID 0
 #define BPP_BLENDED_PIPE 0xffffffff
+#define DCN21_MAX_DSC_IMAGE_WIDTH 5184
 
 static void DisplayPipeConfiguration(struct display_mode_lib *mode_lib);
 static void DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndPerformanceCalculation(
@@ -3379,6 +3380,8 @@ static unsigned int TruncToValidBPP(
 				return 30;
 			else if (DecimalBPP >= 24 && (DesiredBPP == 0 || DesiredBPP == 24))
 				return 24;
+			else if (DecimalBPP >= 18 && (DesiredBPP == 0 || DesiredBPP == 18))
+				return 18;
 			else
 				return BPP_INVALID;
 		}
@@ -3936,6 +3939,10 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 				mode_lib->vba.MaximumSwathWidthInLineBuffer);
 	}
 	for (i = 0; i <= mode_lib->vba.soc.num_states; i++) {
+		double MaxMaxDispclkRoundedDown = RoundToDFSGranularityDown(
+			mode_lib->vba.MaxDispclk[mode_lib->vba.soc.num_states],
+			mode_lib->vba.DISPCLKDPPCLKVCOSpeed);
+
 		for (j = 0; j < 2; j++) {
 			mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity = RoundToDFSGranularityDown(
 				mode_lib->vba.MaxDispclk[i],
@@ -3965,7 +3972,9 @@ void dml21_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l
 						&& i == mode_lib->vba.soc.num_states)
 					mode_lib->vba.PlaneRequiredDISPCLKWithODMCombine = mode_lib->vba.PixelClock[k] / 2
 							* (1 + mode_lib->vba.DISPCLKDPPCLKDSCCLKDownSpreading / 100.0);
-				if (mode_lib->vba.ODMCapability == false || mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine <= mode_lib->vba.MaxDispclkRoundedDownToDFSGranularity) {
+				if (mode_lib->vba.ODMCapability == false ||
+						(locals->PlaneRequiredDISPCLKWithoutODMCombine <= MaxMaxDispclkRoundedDown
+							&& (!locals->DSCEnabled[k] || locals->HActive[k] <= DCN21_MAX_DSC_IMAGE_WIDTH))) {
 					locals->ODMCombineEnablePerState[i][k] = false;
 					mode_lib->vba.PlaneRequiredDISPCLK = mode_lib->vba.PlaneRequiredDISPCLKWithoutODMCombine;
 				} else {
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 f4c1ef9046bf..cfacd6027467 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
@@ -269,7 +269,7 @@ struct writeback_st {
 
 struct _vcs_dpi_display_output_params_st {
 	int dp_lanes;
-	int output_bpp;
+	double output_bpp;
 	int dsc_enable;
 	int wb_enable;
 	int num_active_wb;
@@ -318,6 +318,7 @@ struct _vcs_dpi_display_pipe_dest_params_st {
 	unsigned int vupdate_width;
 	unsigned int vready_offset;
 	unsigned char interlaced;
+	unsigned char embedded;
 	double pixel_rate_mhz;
 	unsigned char synchronized_vblank_all_planes;
 	unsigned char otg_inst;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
index 65cf4edddaff..7f9a5621922f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
@@ -375,6 +375,7 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 
 		mode_lib->vba.pipe_plane[j] = mode_lib->vba.NumberOfActivePlanes;
 
+		mode_lib->vba.EmbeddedPanel[mode_lib->vba.NumberOfActivePlanes] = dst->embedded;
 		mode_lib->vba.DPPPerPlane[mode_lib->vba.NumberOfActivePlanes] = 1;
 		mode_lib->vba.SourceScan[mode_lib->vba.NumberOfActivePlanes] =
 				(enum scan_direction_class) (src->source_scan);
@@ -432,8 +433,12 @@ static void fetch_pipe_params(struct display_mode_lib *mode_lib)
 				dst->recout_width; // TODO: or should this be full_recout_width???...maybe only when in hsplit mode?
 		mode_lib->vba.ODMCombineEnabled[mode_lib->vba.NumberOfActivePlanes] =
 				dst->odm_combine;
+		mode_lib->vba.ODMCombineTypeEnabled[mode_lib->vba.NumberOfActivePlanes] =
+				dst->odm_combine;
 		mode_lib->vba.OutputFormat[mode_lib->vba.NumberOfActivePlanes] =
 				(enum output_format_class) (dout->output_format);
+		mode_lib->vba.OutputBpp[mode_lib->vba.NumberOfActivePlanes] =
+				dout->output_bpp;
 		mode_lib->vba.Output[mode_lib->vba.NumberOfActivePlanes] =
 				(enum output_encoder_class) (dout->output_type);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
index 91decac50557..1540ffbe3979 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.h
@@ -387,6 +387,7 @@ struct vba_vars_st {
 
 	/* vba mode support */
 	/*inputs*/
+	bool EmbeddedPanel[DC__NUM_DPP__MAX];
 	bool SupportGFX7CompatibleTilingIn32bppAnd64bpp;
 	double MaxHSCLRatio;
 	double MaxVSCLRatio;
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
index ad8571f5a142..4c3e9cc30167 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
@@ -243,7 +243,7 @@ void dml1_extract_rq_regs(
 	rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height);
 	rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height);
 
-	/* FIXME: take the max between luma, chroma chunk size?
+	/* TODO: take the max between luma, chroma chunk size?
 	 * okay for now, as we are setting chunk_bytes to 8kb anyways
 	 */
 	if (rq_param.sizing.rq_l.chunk_bytes >= 32 * 1024) { /*32kb */
@@ -602,7 +602,7 @@ static void get_surf_rq_param(
 	unsigned int log2_dpte_group_length;
 	unsigned int func_meta_row_height, func_dpte_row_height;
 
-	/* FIXME check if ppe apply for both luma and chroma in 422 case */
+	/* TODO check if ppe apply for both luma and chroma in 422 case */
 	if (is_chroma) {
 		vp_width = pipe_src_param.viewport_width_c / ppe;
 		vp_height = pipe_src_param.viewport_height_c;
@@ -1141,7 +1141,7 @@ void dml1_rq_dlg_get_dlg_params(
 	ASSERT(disp_dlg_regs->refcyc_h_blank_end < (unsigned int) dml_pow(2, 13));
 	disp_dlg_regs->dlg_vblank_end = interlaced ? (vblank_end / 2) : vblank_end; /* 15 bits */
 
-	prefetch_xy_calc_in_dcfclk = 24.0; /* FIXME: ip_param */
+	prefetch_xy_calc_in_dcfclk = 24.0; /* TODO: ip_param */
 	min_dcfclk_mhz = dlg_sys_param.deepsleep_dcfclk_mhz;
 	t_calc_us = prefetch_xy_calc_in_dcfclk / min_dcfclk_mhz;
 	min_ttu_vblank = dlg_sys_param.t_urg_wm_us;
@@ -1182,7 +1182,7 @@ void dml1_rq_dlg_get_dlg_params(
 	dcc_en = e2e_pipe_param.pipe.src.dcc;
 	dual_plane = is_dual_plane(
 			(enum source_format_class) e2e_pipe_param.pipe.src.source_format);
-	mode_422 = 0; /* FIXME */
+	mode_422 = 0; /* TODO */
 	access_dir = (e2e_pipe_param.pipe.src.source_scan == dm_vert); /* vp access direction: horizontal or vertical accessed */
 	bytes_per_element_l = get_bytes_per_element(
 			(enum source_format_class) e2e_pipe_param.pipe.src.source_format,
@@ -1837,7 +1837,7 @@ void dml1_rq_dlg_get_dlg_params(
 		cur0_width_ub = dml_ceil((double) cur0_src_width / (double) cur0_req_width, 1)
 				* (double) cur0_req_width;
 		cur0_req_per_width = cur0_width_ub / (double) cur0_req_width;
-		hactive_cur0 = (double) cur0_src_width / hratios_cur0; /* FIXME: oswin to think about what to do for cursor */
+		hactive_cur0 = (double) cur0_src_width / hratios_cur0; /* TODO: oswin to think about what to do for cursor */
 
 		if (vratio_pre_l <= 1.0) {
 			refcyc_per_req_delivery_pre_cur0 = hactive_cur0 * ref_freq_to_pix_freq
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/Makefile b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
index b456cd23c6fa..970737217e53 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dsc/Makefile
@@ -1,15 +1,20 @@
 #
 # Makefile for the 'dsc' sub-component of DAL.
 
-ifneq ($(call cc-option, -mpreferred-stack-boundary=4),)
-	cc_stack_align := -mpreferred-stack-boundary=4
-else ifneq ($(call cc-option, -mstack-alignment=16),)
-	cc_stack_align := -mstack-alignment=16
-endif
+dsc_ccflags := -mhard-float -msse
 
-dsc_ccflags := -mhard-float -msse $(cc_stack_align)
+ifdef CONFIG_CC_IS_GCC
+ifeq ($(call cc-ifversion, -lt, 0701, y), y)
+IS_OLD_GCC = 1
+endif
+endif
 
-ifdef CONFIG_CC_IS_CLANG
+ifdef IS_OLD_GCC
+# Stack alignment mismatch, proceed with caution.
+# GCC < 7.1 cannot compile code using `double` and -mpreferred-stack-boundary=3
+# (8B stack alignment).
+dsc_ccflags += -mpreferred-stack-boundary=4
+else
 dsc_ccflags += -msse2
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
index 5995bcdfed54..e60f760585e4 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
@@ -23,8 +23,7 @@
  */
 
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
-#include "dc.h"
-#include "core_types.h"
+#include "dc_hw_types.h"
 #include "dsc.h"
 #include <drm/drm_dp_helper.h>
 
@@ -47,6 +46,59 @@ const struct dc_dsc_policy dsc_policy = {
 
 /* This module's internal functions */
 
+static uint32_t dc_dsc_bandwidth_in_kbps_from_timing(
+	const struct dc_crtc_timing *timing)
+{
+	uint32_t bits_per_channel = 0;
+	uint32_t kbps;
+
+	if (timing->flags.DSC) {
+		kbps = (timing->pix_clk_100hz * timing->dsc_cfg.bits_per_pixel);
+		kbps = kbps / 160 + ((kbps % 160) ? 1 : 0);
+		return kbps;
+	}
+
+	switch (timing->display_color_depth) {
+	case COLOR_DEPTH_666:
+		bits_per_channel = 6;
+		break;
+	case COLOR_DEPTH_888:
+		bits_per_channel = 8;
+		break;
+	case COLOR_DEPTH_101010:
+		bits_per_channel = 10;
+		break;
+	case COLOR_DEPTH_121212:
+		bits_per_channel = 12;
+		break;
+	case COLOR_DEPTH_141414:
+		bits_per_channel = 14;
+		break;
+	case COLOR_DEPTH_161616:
+		bits_per_channel = 16;
+		break;
+	default:
+		break;
+	}
+
+	ASSERT(bits_per_channel != 0);
+
+	kbps = timing->pix_clk_100hz / 10;
+	kbps *= bits_per_channel;
+
+	if (timing->flags.Y_ONLY != 1) {
+		/*Only YOnly make reduce bandwidth by 1/3 compares to RGB*/
+		kbps *= 3;
+		if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			kbps /= 2;
+		else if (timing->pixel_encoding == PIXEL_ENCODING_YCBCR422)
+			kbps = kbps * 2 / 3;
+	}
+
+	return kbps;
+
+}
+
 static bool dsc_buff_block_size_from_dpcd(int dpcd_buff_block_size, int *buff_block_size)
 {
 
@@ -178,12 +230,11 @@ static bool dsc_bpp_increment_div_from_dpcd(int bpp_increment_dpcd, uint32_t *bp
 }
 
 static void get_dsc_enc_caps(
-	const struct dc *dc,
+	const struct display_stream_compressor *dsc,
 	struct dsc_enc_caps *dsc_enc_caps,
 	int pixel_clock_100Hz)
 {
 	// This is a static HW query, so we can use any DSC
-	struct display_stream_compressor *dsc = dc->res_pool->dscs[0];
 
 	memset(dsc_enc_caps, 0, sizeof(struct dsc_enc_caps));
 	if (dsc)
@@ -290,7 +341,7 @@ static void get_dsc_bandwidth_range(
 		struct dc_dsc_bw_range *range)
 {
 	/* native stream bandwidth */
-	range->stream_kbps = dc_bandwidth_in_kbps_from_timing(timing);
+	range->stream_kbps = dc_dsc_bandwidth_in_kbps_from_timing(timing);
 
 	/* max dsc target bpp */
 	range->max_kbps = dsc_div_by_10_round_up(max_bpp * timing->pix_clk_100hz);
@@ -512,6 +563,7 @@ static bool setup_dsc_config(
 		const struct dsc_enc_caps *dsc_enc_caps,
 		int target_bandwidth_kbps,
 		const struct dc_crtc_timing *timing,
+		int min_slice_height_override,
 		struct dc_dsc_config *dsc_cfg)
 {
 	struct dsc_enc_caps dsc_common_caps;
@@ -680,7 +732,10 @@ static bool setup_dsc_config(
 
 	// Slice height (i.e. number of slices per column): start with policy and pick the first one that height is divisible by.
 	// For 4:2:0 make sure the slice height is divisible by 2 as well.
-	slice_height = min(dsc_policy.min_sice_height, pic_height);
+	if (min_slice_height_override == 0)
+		slice_height = min(dsc_policy.min_sice_height, pic_height);
+	else
+		slice_height = min(min_slice_height_override, pic_height);
 
 	while (slice_height < pic_height && (pic_height % slice_height != 0 ||
 		(timing->pixel_encoding == PIXEL_ENCODING_YCBCR420 && slice_height % 2 != 0)))
@@ -802,7 +857,8 @@ bool dc_dsc_parse_dsc_dpcd(const uint8_t *dpcd_dsc_basic_data, const uint8_t *dp
  * If DSC is not possible, leave '*range' untouched.
  */
 bool dc_dsc_compute_bandwidth_range(
-		const struct dc *dc,
+		const struct display_stream_compressor *dsc,
+		const uint32_t dsc_min_slice_height_override,
 		const uint32_t min_bpp,
 		const uint32_t max_bpp,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
@@ -814,16 +870,14 @@ bool dc_dsc_compute_bandwidth_range(
 	struct dsc_enc_caps dsc_common_caps;
 	struct dc_dsc_config config;
 
-	get_dsc_enc_caps(dc, &dsc_enc_caps, timing->pix_clk_100hz);
+	get_dsc_enc_caps(dsc, &dsc_enc_caps, timing->pix_clk_100hz);
 
 	is_dsc_possible = intersect_dsc_caps(dsc_sink_caps, &dsc_enc_caps,
 			timing->pixel_encoding, &dsc_common_caps);
 
 	if (is_dsc_possible)
-		is_dsc_possible = setup_dsc_config(dsc_sink_caps,
-				&dsc_enc_caps,
-				0,
-				timing, &config);
+		is_dsc_possible = setup_dsc_config(dsc_sink_caps, &dsc_enc_caps, 0, timing,
+				dsc_min_slice_height_override, &config);
 
 	if (is_dsc_possible)
 		get_dsc_bandwidth_range(min_bpp, max_bpp, &dsc_common_caps, timing, range);
@@ -832,8 +886,9 @@ bool dc_dsc_compute_bandwidth_range(
 }
 
 bool dc_dsc_compute_config(
-		const struct dc *dc,
+		const struct display_stream_compressor *dsc,
 		const struct dsc_dec_dpcd_caps *dsc_sink_caps,
+		const uint32_t dsc_min_slice_height_override,
 		uint32_t target_bandwidth_kbps,
 		const struct dc_crtc_timing *timing,
 		struct dc_dsc_config *dsc_cfg)
@@ -841,11 +896,11 @@ bool dc_dsc_compute_config(
 	bool is_dsc_possible = false;
 	struct dsc_enc_caps dsc_enc_caps;
 
-	get_dsc_enc_caps(dc, &dsc_enc_caps, timing->pix_clk_100hz);
+	get_dsc_enc_caps(dsc, &dsc_enc_caps, timing->pix_clk_100hz);
 	is_dsc_possible = setup_dsc_config(dsc_sink_caps,
 			&dsc_enc_caps,
 			target_bandwidth_kbps,
-			timing, dsc_cfg);
+			timing, dsc_min_slice_height_override, dsc_cfg);
 	return is_dsc_possible;
 }
 #endif /* CONFIG_DRM_AMD_DC_DSC_SUPPORT */
diff --git a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
index ca51e83f8764..76c4b12d6824 100644
--- a/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dsc/rc_calc.c
@@ -177,7 +177,6 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 {
 	float bpp_group;
 	float initial_xmit_delay_factor;
-	int source_bpp;
 	int padding_pixels;
 	int i;
 
@@ -217,8 +216,6 @@ void calc_rc_params(struct rc_params *rc, enum colour_mode cm, enum bits_per_com
 			rc->initial_xmit_delay++;
 	}
 
-	source_bpp = MODE_SELECT(bpc * 3, bpc * 2, bpc * 1.5);
-
 	rc->flatness_min_qp     = ((bpc == BPC_8) ?  (3) : ((bpc == BPC_10) ? (7)  : (11))) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 	rc->flatness_max_qp     = ((bpc == BPC_8) ? (12) : ((bpc == BPC_10) ? (16) : (20))) - ((minor_version == 1 && cm == CM_444) ? 1 : 0);
 	rc->flatness_det_thresh = 2 << (bpc - 8);
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
index f8f85490e77e..f67c18375bfd 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_base.c
@@ -321,8 +321,6 @@ void dal_gpio_destroy(
 		return;
 	}
 
-	dal_gpio_close(*gpio);
-
 	switch ((*gpio)->id) {
 	case GPIO_ID_DDC_DATA:
 		kfree((*gpio)->hw_container.ddc);
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 d03165e71dc6..92280cc05e2d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
@@ -169,7 +169,6 @@ void dal_gpio_destroy_generic_mux(
 		return;
 	}
 
-	dal_gpio_close(*mux);
 	dal_gpio_destroy(mux);
 	kfree(*mux);
 
@@ -460,7 +459,6 @@ void dal_gpio_destroy_irq(
 		return;
 	}
 
-	dal_gpio_close(*irq);
 	dal_gpio_destroy(irq);
 	kfree(*irq);
 
diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/Makefile b/drivers/gpu/drm/amd/display/dc/hdcp/Makefile
new file mode 100644
index 000000000000..4170b6eb9ec0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/hdcp/Makefile
@@ -0,0 +1,28 @@
+# Copyright 2019 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+# Makefile for the 'hdcp' sub-component of DAL.
+#
+
+HDCP_MSG = hdcp_msg.o
+
+AMD_DAL_HDCP_MSG = $(addprefix $(AMDDALPATH)/dc/hdcp/,$(HDCP_MSG))
+
+AMD_DISPLAY_FILES += $(AMD_DAL_HDCP_MSG)
diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c
new file mode 100644
index 000000000000..6f730b5bfe42
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c
@@ -0,0 +1,324 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/slab.h>
+
+#include "dm_services.h"
+#include "dm_helpers.h"
+#include "include/hdcp_types.h"
+#include "include/i2caux_interface.h"
+#include "include/signal_types.h"
+#include "core_types.h"
+#include "dc_link_ddc.h"
+#include "link_hwss.h"
+
+#define DC_LOGGER \
+	link->ctx->logger
+#define HDCP14_KSV_SIZE 5
+#define HDCP14_MAX_KSV_FIFO_SIZE 127*HDCP14_KSV_SIZE
+
+static const bool hdcp_cmd_is_read[] = {
+	[HDCP_MESSAGE_ID_READ_BKSV] = true,
+	[HDCP_MESSAGE_ID_READ_RI_R0] = true,
+	[HDCP_MESSAGE_ID_READ_PJ] = true,
+	[HDCP_MESSAGE_ID_WRITE_AKSV] = false,
+	[HDCP_MESSAGE_ID_WRITE_AINFO] = false,
+	[HDCP_MESSAGE_ID_WRITE_AN] = false,
+	[HDCP_MESSAGE_ID_READ_VH_X] = true,
+	[HDCP_MESSAGE_ID_READ_VH_0] = true,
+	[HDCP_MESSAGE_ID_READ_VH_1] = true,
+	[HDCP_MESSAGE_ID_READ_VH_2] = true,
+	[HDCP_MESSAGE_ID_READ_VH_3] = true,
+	[HDCP_MESSAGE_ID_READ_VH_4] = true,
+	[HDCP_MESSAGE_ID_READ_BCAPS] = true,
+	[HDCP_MESSAGE_ID_READ_BSTATUS] = true,
+	[HDCP_MESSAGE_ID_READ_KSV_FIFO] = true,
+	[HDCP_MESSAGE_ID_READ_BINFO] = true,
+	[HDCP_MESSAGE_ID_HDCP2VERSION] = true,
+	[HDCP_MESSAGE_ID_RX_CAPS] = true,
+	[HDCP_MESSAGE_ID_WRITE_AKE_INIT] = false,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = true,
+	[HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = false,
+	[HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = false,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = true,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = true,
+	[HDCP_MESSAGE_ID_WRITE_LC_INIT] = false,
+	[HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = true,
+	[HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = false,
+	[HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = true,
+	[HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = false,
+	[HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = false,
+	[HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = true,
+	[HDCP_MESSAGE_ID_READ_RXSTATUS] = true,
+	[HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE] = false
+};
+
+static const uint8_t hdcp_i2c_offsets[] = {
+	[HDCP_MESSAGE_ID_READ_BKSV] = 0x0,
+	[HDCP_MESSAGE_ID_READ_RI_R0] = 0x8,
+	[HDCP_MESSAGE_ID_READ_PJ] = 0xA,
+	[HDCP_MESSAGE_ID_WRITE_AKSV] = 0x10,
+	[HDCP_MESSAGE_ID_WRITE_AINFO] = 0x15,
+	[HDCP_MESSAGE_ID_WRITE_AN] = 0x18,
+	[HDCP_MESSAGE_ID_READ_VH_X] = 0x20,
+	[HDCP_MESSAGE_ID_READ_VH_0] = 0x20,
+	[HDCP_MESSAGE_ID_READ_VH_1] = 0x24,
+	[HDCP_MESSAGE_ID_READ_VH_2] = 0x28,
+	[HDCP_MESSAGE_ID_READ_VH_3] = 0x2C,
+	[HDCP_MESSAGE_ID_READ_VH_4] = 0x30,
+	[HDCP_MESSAGE_ID_READ_BCAPS] = 0x40,
+	[HDCP_MESSAGE_ID_READ_BSTATUS] = 0x41,
+	[HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x43,
+	[HDCP_MESSAGE_ID_READ_BINFO] = 0xFF,
+	[HDCP_MESSAGE_ID_HDCP2VERSION] = 0x50,
+	[HDCP_MESSAGE_ID_WRITE_AKE_INIT] = 0x60,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = 0x80,
+	[HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = 0x60,
+	[HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = 0x60,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = 0x80,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = 0x80,
+	[HDCP_MESSAGE_ID_WRITE_LC_INIT] = 0x60,
+	[HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = 0x80,
+	[HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = 0x60,
+	[HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = 0x80,
+	[HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = 0x60,
+	[HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = 0x60,
+	[HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = 0x80,
+	[HDCP_MESSAGE_ID_READ_RXSTATUS] = 0x70
+};
+
+struct protection_properties {
+	bool supported;
+	bool (*process_transaction)(
+		struct dc_link *link,
+		struct hdcp_protection_message *message_info);
+};
+
+static const struct protection_properties non_supported_protection = {
+	.supported = false
+};
+
+static bool hdmi_14_process_transaction(
+	struct dc_link *link,
+	struct hdcp_protection_message *message_info)
+{
+	uint8_t *buff = NULL;
+	bool result;
+	const uint8_t hdcp_i2c_addr_link_primary = 0x3a; /* 0x74 >> 1*/
+	const uint8_t hdcp_i2c_addr_link_secondary = 0x3b; /* 0x76 >> 1*/
+	struct i2c_command i2c_command;
+	uint8_t offset = hdcp_i2c_offsets[message_info->msg_id];
+	struct i2c_payload i2c_payloads[] = {
+		{ true, 0, 1, &offset },
+		/* actual hdcp payload, will be filled later, zeroed for now*/
+		{ 0 }
+	};
+
+	switch (message_info->link) {
+	case HDCP_LINK_SECONDARY:
+		i2c_payloads[0].address = hdcp_i2c_addr_link_secondary;
+		i2c_payloads[1].address = hdcp_i2c_addr_link_secondary;
+		break;
+	case HDCP_LINK_PRIMARY:
+	default:
+		i2c_payloads[0].address = hdcp_i2c_addr_link_primary;
+		i2c_payloads[1].address = hdcp_i2c_addr_link_primary;
+		break;
+	}
+
+	if (hdcp_cmd_is_read[message_info->msg_id]) {
+		i2c_payloads[1].write = false;
+		i2c_command.number_of_payloads = ARRAY_SIZE(i2c_payloads);
+		i2c_payloads[1].length = message_info->length;
+		i2c_payloads[1].data = message_info->data;
+	} else {
+		i2c_command.number_of_payloads = 1;
+		buff = kzalloc(message_info->length + 1, GFP_KERNEL);
+
+		if (!buff)
+			return false;
+
+		buff[0] = offset;
+		memmove(&buff[1], message_info->data, message_info->length);
+		i2c_payloads[0].length = message_info->length + 1;
+		i2c_payloads[0].data = buff;
+	}
+
+	i2c_command.payloads = i2c_payloads;
+	i2c_command.engine = I2C_COMMAND_ENGINE_HW;//only HW
+	i2c_command.speed = link->ddc->ctx->dc->caps.i2c_speed_in_khz;
+
+	result = dm_helpers_submit_i2c(
+			link->ctx,
+			link,
+			&i2c_command);
+	kfree(buff);
+
+	return result;
+}
+
+static const struct protection_properties hdmi_14_protection = {
+	.supported = true,
+	.process_transaction = hdmi_14_process_transaction
+};
+
+static const uint32_t hdcp_dpcd_addrs[] = {
+	[HDCP_MESSAGE_ID_READ_BKSV] = 0x68000,
+	[HDCP_MESSAGE_ID_READ_RI_R0] = 0x68005,
+	[HDCP_MESSAGE_ID_READ_PJ] = 0xFFFFFFFF,
+	[HDCP_MESSAGE_ID_WRITE_AKSV] = 0x68007,
+	[HDCP_MESSAGE_ID_WRITE_AINFO] = 0x6803B,
+	[HDCP_MESSAGE_ID_WRITE_AN] = 0x6800c,
+	[HDCP_MESSAGE_ID_READ_VH_X] = 0x68014,
+	[HDCP_MESSAGE_ID_READ_VH_0] = 0x68014,
+	[HDCP_MESSAGE_ID_READ_VH_1] = 0x68018,
+	[HDCP_MESSAGE_ID_READ_VH_2] = 0x6801c,
+	[HDCP_MESSAGE_ID_READ_VH_3] = 0x68020,
+	[HDCP_MESSAGE_ID_READ_VH_4] = 0x68024,
+	[HDCP_MESSAGE_ID_READ_BCAPS] = 0x68028,
+	[HDCP_MESSAGE_ID_READ_BSTATUS] = 0x68029,
+	[HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x6802c,
+	[HDCP_MESSAGE_ID_READ_BINFO] = 0x6802a,
+	[HDCP_MESSAGE_ID_RX_CAPS] = 0x6921d,
+	[HDCP_MESSAGE_ID_WRITE_AKE_INIT] = 0x69000,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_CERT] = 0x6900b,
+	[HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM] = 0x69220,
+	[HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM] = 0x692a0,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME] = 0x692c0,
+	[HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO] = 0x692e0,
+	[HDCP_MESSAGE_ID_WRITE_LC_INIT] = 0x692f0,
+	[HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME] = 0x692f8,
+	[HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS] = 0x69318,
+	[HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST] = 0x69330,
+	[HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK] = 0x693e0,
+	[HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE] = 0x693f0,
+	[HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY] = 0x69473,
+	[HDCP_MESSAGE_ID_READ_RXSTATUS] = 0x69493,
+	[HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE] = 0x69494
+};
+
+static bool dpcd_access_helper(
+	struct dc_link *link,
+	uint32_t length,
+	uint8_t *data,
+	uint32_t dpcd_addr,
+	bool is_read)
+{
+	enum dc_status status;
+	uint32_t cur_length = 0;
+	uint32_t offset = 0;
+	uint32_t ksv_read_size = 0x6803b - 0x6802c;
+
+	/* Read KSV, need repeatedly handle */
+	if (dpcd_addr == 0x6802c) {
+		if (length % HDCP14_KSV_SIZE) {
+			DC_LOG_ERROR("%s: KsvFifo Size(%d) is not a multiple of HDCP14_KSV_SIZE(%d)\n",
+				__func__,
+				length,
+				HDCP14_KSV_SIZE);
+		}
+		if (length > HDCP14_MAX_KSV_FIFO_SIZE) {
+			DC_LOG_ERROR("%s: KsvFifo Size(%d) is greater than HDCP14_MAX_KSV_FIFO_SIZE(%d)\n",
+				__func__,
+				length,
+				HDCP14_MAX_KSV_FIFO_SIZE);
+		}
+
+		DC_LOG_ERROR("%s: Reading %d Ksv(s) from KsvFifo\n",
+			__func__,
+			length / HDCP14_KSV_SIZE);
+
+		while (length > 0) {
+			if (length > ksv_read_size) {
+				status = core_link_read_dpcd(
+					link,
+					dpcd_addr + offset,
+					data + offset,
+					ksv_read_size);
+
+				data += ksv_read_size;
+				length -= ksv_read_size;
+			} else {
+				status = core_link_read_dpcd(
+					link,
+					dpcd_addr + offset,
+					data + offset,
+					length);
+
+				data += length;
+				length = 0;
+			}
+
+			if (status != DC_OK)
+				return false;
+		}
+	} else {
+		while (length > 0) {
+			if (length > DEFAULT_AUX_MAX_DATA_SIZE)
+				cur_length = DEFAULT_AUX_MAX_DATA_SIZE;
+			else
+				cur_length = length;
+
+			if (is_read) {
+				status = core_link_read_dpcd(
+					link,
+					dpcd_addr + offset,
+					data + offset,
+					cur_length);
+			} else {
+				status = core_link_write_dpcd(
+					link,
+					dpcd_addr + offset,
+					data + offset,
+					cur_length);
+			}
+
+			if (status != DC_OK)
+				return false;
+
+			length -= cur_length;
+			offset += cur_length;
+		}
+	}
+	return true;
+}
+
+static bool dp_11_process_transaction(
+	struct dc_link *link,
+	struct hdcp_protection_message *message_info)
+{
+	return dpcd_access_helper(
+		link,
+		message_info->length,
+		message_info->data,
+		hdcp_dpcd_addrs[message_info->msg_id],
+		hdcp_cmd_is_read[message_info->msg_id]);
+}
+
+static const struct protection_properties dp_11_protection = {
+	.supported = true,
+	.process_transaction = dp_11_process_transaction
+};
+
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 f189307750ab..a831079607cd 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -52,7 +52,9 @@ void enable_surface_flip_reporting(struct dc_plane_state *plane_state,
 #include "clock_source.h"
 #include "audio.h"
 #include "dm_pp_smu.h"
-
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+#include "dm_cp_psp.h"
+#endif
 
 /************ link *****************/
 struct link_init_data {
@@ -231,6 +233,7 @@ struct resource_pool {
 
 struct dcn_fe_bandwidth {
 	int dppclk_khz;
+
 };
 
 struct stream_resource {
@@ -395,10 +398,6 @@ struct dc_state {
 
 	struct clk_mgr *clk_mgr;
 
-	struct {
-		bool full_update_needed : 1;
-	} commit_hints;
-
 	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 b1fab251c09b..14716ba35662 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
@@ -95,6 +95,9 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
+bool dal_ddc_submit_aux_command(struct ddc_service *ddc,
+		struct aux_payload *payload);
+
 int dc_link_aux_transfer_raw(struct ddc_service *ddc,
 		struct aux_payload *payload,
 		enum aux_channel_operation_result *operation_result);
@@ -102,6 +105,9 @@ int dc_link_aux_transfer_raw(struct ddc_service *ddc,
 bool dc_link_aux_transfer_with_retries(struct ddc_service *ddc,
 		struct aux_payload *payload);
 
+enum dc_status dc_link_aux_configure_timeout(struct ddc_service *ddc,
+		uint32_t timeout);
+
 void dal_ddc_service_write_scdc_data(
 		struct ddc_service *ddc_service,
 		uint32_t pix_clk,
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 08a4df2c61a8..045138dbdccb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -28,6 +28,8 @@
 
 #define LINK_TRAINING_ATTEMPTS 4
 #define LINK_TRAINING_RETRY_DELAY 50 /* ms */
+#define LINK_AUX_DEFAULT_EXTENDED_TIMEOUT_PERIOD 32000 /*us*/
+#define LINK_AUX_DEFAULT_TIMEOUT_PERIOD 400 /*us*/
 
 struct dc_link;
 struct dc_stream_state;
@@ -43,6 +45,9 @@ bool dp_verify_link_cap_with_retries(
 	struct dc_link_settings *known_limit_link_setting,
 	int attempts);
 
+bool dp_verify_mst_link_cap(
+	struct dc_link *link);
+
 bool dp_validate_mode_timing(
 	struct dc_link *link,
 	const struct dc_crtc_timing *timing);
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
index e79cd4e92919..e77b3a76766d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
@@ -140,6 +140,9 @@ struct write_command_context {
 
 
 struct aux_engine_funcs {
+	bool (*configure_timeout)(
+		struct ddc_service *ddc,
+		uint32_t timeout);
 	void (*destroy)(
 		struct aux_engine **ptr);
 	bool (*acquire_engine)(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
index 76f9ad1b23df..4e18e77dcf42 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr.h
@@ -47,7 +47,7 @@
 #ifdef CONFIG_DRM_AMD_DC_DCN2_1
 /* Will these bw structures be ASIC specific? */
 
-#define MAX_NUM_DPM_LVL		4
+#define MAX_NUM_DPM_LVL		8
 #define WM_SET_COUNT 		4
 
 
@@ -180,13 +180,19 @@ struct clk_mgr_funcs {
 			struct dc_state *context,
 			enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg);
+
+	bool (*are_clock_states_equal) (struct dc_clocks *a,
+			struct dc_clocks *b);
+	void (*notify_wm_ranges)(struct clk_mgr *clk_mgr);
 };
 
 struct clk_mgr {
 	struct dc_context *ctx;
 	struct clk_mgr_funcs *funcs;
 	struct dc_clocks clks;
+	bool psr_allow_active_cache;
 	int dprefclk_khz; // Used by program pixel clock in clock source funcs, need to figureout where this goes
+	int dentist_vco_freq_khz;
 #ifdef CONFIG_DRM_AMD_DC_DCN2_1
 	struct clk_bw_params *bw_params;
 #endif
@@ -199,4 +205,8 @@ struct clk_mgr *dc_clk_mgr_create(struct dc_context *ctx, struct pp_smu_funcs *p
 
 void dc_destroy_clk_mgr(struct clk_mgr *clk_mgr);
 
+void clk_mgr_exit_optimized_pwr_state(const struct dc *dc, struct clk_mgr *clk_mgr);
+
+void clk_mgr_optimize_pwr_state(const struct dc *dc, struct clk_mgr *clk_mgr);
+
 #endif /* __DAL_CLK_MGR_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
index 7dd46eb96d67..a17a77192690 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/clk_mgr_internal.h
@@ -184,6 +184,21 @@ struct clk_mgr_registers {
 	uint32_t MP1_SMN_C2PMSG_91;
 };
 
+enum clock_type {
+	clock_type_dispclk = 1,
+	clock_type_dcfclk,
+	clock_type_socclk,
+	clock_type_pixelclk,
+	clock_type_phyclk,
+	clock_type_dppclk,
+	clock_type_fclk,
+	clock_type_dcfdsclk,
+	clock_type_dscclk,
+	clock_type_uclk,
+	clock_type_dramclk,
+};
+
+
 struct state_dependent_clocks {
 	int display_clk_khz;
 	int pixel_clk_khz;
@@ -210,8 +225,6 @@ struct clk_mgr_internal {
 	struct state_dependent_clocks max_clks_by_state[DM_PP_CLOCKS_MAX_STATES];
 
 	/*TODO: figure out which of the below fields should be here vs in asic specific portion */
-	int dentist_vco_freq_khz;
-
 	/* Cache the status of DFS-bypass feature*/
 	bool dfs_bypass_enabled;
 	/* True if the DFS-bypass feature is enabled and active. */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
index d8e744f366e5..05ee5295d2c1 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dccg.h
@@ -38,8 +38,7 @@ struct dccg {
 struct dccg_funcs {
 	void (*update_dpp_dto)(struct dccg *dccg,
 			int dpp_inst,
-			int req_dppclk,
-			bool reduce_divider_only);
+			int req_dppclk);
 	void (*get_dccg_ref_freq)(struct dccg *dccg,
 			unsigned int xtalin_freq_inKhz,
 			unsigned int *dccg_ref_freq_inKhz);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
index a6297219d7fc..c81a17aeaa25 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dchubbub.h
@@ -147,6 +147,7 @@ struct hubbub_funcs {
 	bool (*is_allow_self_refresh_enabled)(struct hubbub *hubbub);
 	void (*allow_self_refresh_control)(struct hubbub *hubbub, bool allow);
 
+	void (*apply_DEDCN21_147_wa)(struct hubbub *hubbub);
 };
 
 struct hubbub {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
index 1ddb1c6fa149..c6ff3d78b435 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dsc.h
@@ -28,7 +28,11 @@
 
 #include "dc_dsc.h"
 #include "dc_hw_types.h"
-#include "dc_dp_types.h"
+#include "dc_types.h"
+/* do not include any other headers
+ * or else it might break Edid Utility functionality.
+ */
+
 
 /* Input parameters for configuring DSC from the outside of DSC */
 struct dsc_config {
@@ -81,12 +85,6 @@ struct dsc_enc_caps {
 	uint32_t bpp_increment_div; /* bpp increment divisor, e.g. if 16, it's 1/16th of a bit */
 };
 
-struct display_stream_compressor {
-	const struct dsc_funcs *funcs;
-	struct dc_context *ctx;
-	int inst;
-};
-
 struct dsc_funcs {
 	void (*dsc_get_enc_caps)(struct dsc_enc_caps *dsc_enc_caps, int pixel_clock_100Hz);
 	void (*dsc_read_state)(struct display_stream_compressor *dsc, struct dcn_dsc_state *s);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
index abb4e4237fb6..b21909216fb6 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/link_encoder.h
@@ -184,6 +184,10 @@ struct link_encoder_funcs {
 	bool (*fec_is_active)(struct link_encoder *enc);
 #endif
 	bool (*is_in_alt_mode) (struct link_encoder *enc);
+
+	void (*get_max_link_cap)(struct link_encoder *enc,
+		struct dc_link_settings *link_settings);
+
 	enum signal_type (*get_dig_mode)(
 		struct link_encoder *enc);
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
index e8668388581b..67b610d6d91f 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
@@ -43,6 +43,7 @@ struct dcn_watermarks {
 #if defined(CONFIG_DRM_AMD_DC_DCN2_1)
 	uint32_t frac_urg_bw_nom;
 	uint32_t frac_urg_bw_flip;
+	int32_t urgent_latency_ns;
 #endif
 	struct cstate_pstate_watermarks_st cstate_pstate;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
index 957e9047381a..18def2b6fafe 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h
@@ -208,6 +208,7 @@ struct output_pixel_processor {
 	struct mpc_tree mpc_tree_params;
 	bool mpcc_disconnect_pending[MAX_PIPES];
 	const struct opp_funcs *funcs;
+	uint32_t dyn_expansion;
 };
 
 enum fmt_stereo_action {
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
index fe9b7a10a1c3..6305e388612a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/stream_encoder.h
@@ -214,6 +214,11 @@ struct stream_encoder_funcs {
 	unsigned int (*dig_source_otg)(
 		struct stream_encoder *enc);
 
+	bool (*dp_get_pixel_format)(
+		struct stream_encoder *enc,
+		enum dc_pixel_encoding *encoding,
+		enum dc_color_depth *depth);
+
 #if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 #ifdef CONFIG_DRM_AMD_DC_DSC_SUPPORT
 	void (*enc_read_state)(struct stream_encoder *enc, struct enc_state *s);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 6196cc32356e..27c73caf74ee 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -261,6 +261,8 @@ struct timing_generator_funcs {
 
 	void (*program_manual_trigger)(struct timing_generator *optc);
 	void (*setup_manual_trigger)(struct timing_generator *optc);
+	bool (*get_hw_timing)(struct timing_generator *optc,
+			struct dc_crtc_timing *hw_crtc_timing);
 
 	void (*set_vtg_params)(struct timing_generator *optc,
 			const struct dc_crtc_timing *dc_crtc_timing);
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 3a938cd414ea..d39c1e11def5 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -114,6 +114,9 @@ struct hw_sequencer_funcs {
 			int opp_id);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN2_0)
+	void (*program_front_end_for_ctx)(
+			struct dc *dc,
+			struct dc_state *context);
 	void (*program_triplebuffer)(
 		const struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
@@ -229,6 +232,13 @@ struct hw_sequencer_funcs {
 			struct dc *dc,
 			struct dc_state *context);
 
+	void (*exit_optimized_pwr_state)(
+			const struct dc *dc,
+			struct dc_state *context);
+	void (*optimize_pwr_state)(
+			const struct dc *dc,
+			struct dc_state *context);
+
 #if defined(CONFIG_DRM_AMD_DC_DCN2_0)
 	bool (*update_bandwidth)(
 			struct dc *dc,
@@ -321,10 +331,12 @@ struct hw_sequencer_funcs {
 			struct dc_state *context);
 	void (*update_writeback)(struct dc *dc,
 			const struct dc_stream_status *stream_status,
-			struct dc_writeback_info *wb_info);
+			struct dc_writeback_info *wb_info,
+			struct dc_state *context);
 	void (*enable_writeback)(struct dc *dc,
 			const struct dc_stream_status *stream_status,
-			struct dc_writeback_info *wb_info);
+			struct dc_writeback_info *wb_info,
+			struct dc_state *context);
 	void (*disable_writeback)(struct dc *dc,
 			unsigned int dwb_pipe_inst);
 #endif
@@ -337,6 +349,9 @@ struct hw_sequencer_funcs {
 			enum dc_clock_type clock_type,
 			struct dc_clock_config *clock_cfg);
 
+#if defined(CONFIG_DRM_AMD_DC_DCN2_1)
+	bool (*s0i3_golden_init_wa)(struct dc *dc);
+#endif
 };
 
 void color_space_to_black_color(
diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
index 18961707db23..9ad49da50a17 100644
--- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
@@ -31,6 +31,8 @@
 #define DP_BRANCH_DEVICE_ID_0022B9 0x0022B9
 #define DP_BRANCH_DEVICE_ID_00001A 0x00001A
 #define DP_BRANCH_DEVICE_ID_0080E1 0x0080e1
+#define DP_BRANCH_DEVICE_ID_90CC24 0x90CC24
+#define DP_BRANCH_DEVICE_ID_00E04C 0x00E04C
 
 enum ddc_result {
 	DDC_RESULT_UNKNOWN = 0,
diff --git a/drivers/gpu/drm/amd/display/include/hdcp_types.h b/drivers/gpu/drm/amd/display/include/hdcp_types.h
new file mode 100644
index 000000000000..f31e6befc8d6
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/include/hdcp_types.h
@@ -0,0 +1,96 @@
+/*
+* Copyright 2019 Advanced Micro Devices, Inc.
+*
+* Permission is hereby granted, free of charge, to any person obtaining a
+* copy of this software and associated documentation files (the "Software"),
+* to deal in the Software without restriction, including without limitation
+* the rights to use, copy, modify, merge, publish, distribute, sublicense,
+* and/or sell copies of the Software, and to permit persons to whom the
+* Software is furnished to do so, subject to the following conditions:
+*
+* The above copyright notice and this permission notice shall be included in
+* all copies or substantial portions of the Software.
+*
+* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+* THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+* OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+* ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+* OTHER DEALINGS IN THE SOFTWARE.
+*
+* Authors: AMD
+*
+*/
+
+#ifndef __DC_HDCP_TYPES_H__
+#define __DC_HDCP_TYPES_H__
+
+enum hdcp_message_id {
+	HDCP_MESSAGE_ID_INVALID = -1,
+
+	/* HDCP 1.4 */
+
+	HDCP_MESSAGE_ID_READ_BKSV = 0,
+	/* HDMI is called Ri', DP is called R0' */
+	HDCP_MESSAGE_ID_READ_RI_R0,
+	HDCP_MESSAGE_ID_READ_PJ,
+	HDCP_MESSAGE_ID_WRITE_AKSV,
+	HDCP_MESSAGE_ID_WRITE_AINFO,
+	HDCP_MESSAGE_ID_WRITE_AN,
+	HDCP_MESSAGE_ID_READ_VH_X,
+	HDCP_MESSAGE_ID_READ_VH_0,
+	HDCP_MESSAGE_ID_READ_VH_1,
+	HDCP_MESSAGE_ID_READ_VH_2,
+	HDCP_MESSAGE_ID_READ_VH_3,
+	HDCP_MESSAGE_ID_READ_VH_4,
+	HDCP_MESSAGE_ID_READ_BCAPS,
+	HDCP_MESSAGE_ID_READ_BSTATUS,
+	HDCP_MESSAGE_ID_READ_KSV_FIFO,
+	HDCP_MESSAGE_ID_READ_BINFO,
+
+	/* HDCP 2.2 */
+
+	HDCP_MESSAGE_ID_HDCP2VERSION,
+	HDCP_MESSAGE_ID_RX_CAPS,
+	HDCP_MESSAGE_ID_WRITE_AKE_INIT,
+	HDCP_MESSAGE_ID_READ_AKE_SEND_CERT,
+	HDCP_MESSAGE_ID_WRITE_AKE_NO_STORED_KM,
+	HDCP_MESSAGE_ID_WRITE_AKE_STORED_KM,
+	HDCP_MESSAGE_ID_READ_AKE_SEND_H_PRIME,
+	HDCP_MESSAGE_ID_READ_AKE_SEND_PAIRING_INFO,
+	HDCP_MESSAGE_ID_WRITE_LC_INIT,
+	HDCP_MESSAGE_ID_READ_LC_SEND_L_PRIME,
+	HDCP_MESSAGE_ID_WRITE_SKE_SEND_EKS,
+	HDCP_MESSAGE_ID_READ_REPEATER_AUTH_SEND_RECEIVERID_LIST,
+	HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_SEND_ACK,
+	HDCP_MESSAGE_ID_WRITE_REPEATER_AUTH_STREAM_MANAGE,
+	HDCP_MESSAGE_ID_READ_REPEATER_AUTH_STREAM_READY,
+	HDCP_MESSAGE_ID_READ_RXSTATUS,
+	HDCP_MESSAGE_ID_WRITE_CONTENT_STREAM_TYPE,
+
+	HDCP_MESSAGE_ID_MAX
+};
+
+enum hdcp_version {
+	HDCP_Unknown = 0,
+	HDCP_VERSION_14,
+	HDCP_VERSION_22,
+};
+
+enum hdcp_link {
+	HDCP_LINK_PRIMARY,
+	HDCP_LINK_SECONDARY
+};
+
+struct hdcp_protection_message {
+	enum hdcp_version version;
+	/* relevant only for DVI */
+	enum hdcp_link link;
+	enum hdcp_message_id msg_id;
+	uint32_t length;
+	uint8_t max_retries;
+	uint8_t *data;
+};
+
+#endif
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 2d8f14b69117..1de4805cb8c7 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -373,7 +373,42 @@ static struct fixed31_32 translate_from_linear_space(
 		return dc_fixpt_mul(args->arg, args->a1);
 }
 
-static struct fixed31_32 calculate_gamma22(struct fixed31_32 arg)
+
+static struct fixed31_32 translate_from_linear_space_long(
+		struct translate_from_linear_space_args *args)
+{
+	const struct fixed31_32 one = dc_fixpt_from_int(1);
+
+	if (dc_fixpt_lt(one, args->arg))
+		return one;
+
+	if (dc_fixpt_le(args->arg, dc_fixpt_neg(args->a0)))
+		return dc_fixpt_sub(
+			args->a2,
+			dc_fixpt_mul(
+				dc_fixpt_add(
+					one,
+					args->a3),
+				dc_fixpt_pow(
+					dc_fixpt_neg(args->arg),
+					dc_fixpt_recip(args->gamma))));
+	else if (dc_fixpt_le(args->a0, args->arg))
+		return dc_fixpt_sub(
+			dc_fixpt_mul(
+				dc_fixpt_add(
+					one,
+					args->a3),
+				dc_fixpt_pow(
+						args->arg,
+					dc_fixpt_recip(args->gamma))),
+					args->a2);
+	else
+		return dc_fixpt_mul(
+			args->arg,
+			args->a1);
+}
+
+static struct fixed31_32 calculate_gamma22(struct fixed31_32 arg, bool use_eetf)
 {
 	struct fixed31_32 gamma = dc_fixpt_from_fraction(22, 10);
 
@@ -384,9 +419,13 @@ static struct fixed31_32 calculate_gamma22(struct fixed31_32 arg)
 	scratch_gamma_args.a3 = dc_fixpt_zero;
 	scratch_gamma_args.gamma = gamma;
 
+	if (use_eetf)
+		return translate_from_linear_space_long(&scratch_gamma_args);
+
 	return translate_from_linear_space(&scratch_gamma_args);
 }
 
+
 static struct fixed31_32 translate_to_linear_space(
 	struct fixed31_32 arg,
 	struct fixed31_32 a0,
@@ -920,11 +959,7 @@ static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma,
 	if (fs_params->max_display < 100) // cap at 100 at the top
 		max_display = dc_fixpt_from_int(100);
 
-	if (fs_params->min_content < fs_params->min_display)
-		use_eetf = true;
-	else
-		min_content = min_display;
-
+	// only max used, we don't adjust min luminance
 	if (fs_params->max_content > fs_params->max_display)
 		use_eetf = true;
 	else
@@ -950,7 +985,7 @@ static bool build_freesync_hdr(struct pwl_float_data_ex *rgb_regamma,
 				if (dc_fixpt_lt(scaledX, dc_fixpt_zero))
 					output = dc_fixpt_zero;
 				else
-					output = calculate_gamma22(scaledX);
+					output = calculate_gamma22(scaledX, use_eetf);
 
 				rgb->r = output;
 				rgb->g = output;
@@ -2173,5 +2208,3 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 rgb_degamma_alloc_fail:
 	return ret;
 }
-
-
diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
index ec70c9b12e1a..16e69bbc69aa 100644
--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
@@ -37,8 +37,8 @@
 #define STATIC_SCREEN_RAMP_DELTA_REFRESH_RATE_PER_FRAME ((1000 / 60) * 65)
 /* Number of elements in the render times cache array */
 #define RENDER_TIMES_MAX_COUNT 10
-/* Threshold to exit BTR (to avoid frequent enter-exits at the lower limit) */
-#define BTR_EXIT_MARGIN 2000
+/* Threshold to exit/exit BTR (to avoid frequent enter-exits at the lower limit) */
+#define BTR_MAX_MARGIN 2500
 /* Threshold to change BTR multiplier (to avoid frequent changes) */
 #define BTR_DRIFT_MARGIN 2000
 /*Threshold to exit fixed refresh rate*/
@@ -234,6 +234,10 @@ static void update_v_total_for_static_ramp(
 			current_duration_in_us) * (stream->timing.pix_clk_100hz / 10)),
 				stream->timing.h_total), 1000);
 
+	/* v_total cannot be less than nominal */
+	if (v_total < stream->timing.v_total)
+		v_total = stream->timing.v_total;
+
 	in_out_vrr->adjust.v_total_min = v_total;
 	in_out_vrr->adjust.v_total_max = v_total;
 }
@@ -250,24 +254,22 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 	unsigned int delta_from_mid_point_in_us_1 = 0xFFFFFFFF;
 	unsigned int delta_from_mid_point_in_us_2 = 0xFFFFFFFF;
 	unsigned int frames_to_insert = 0;
-	unsigned int min_frame_duration_in_ns = 0;
-	unsigned int max_render_time_in_us = in_out_vrr->max_duration_in_us;
 	unsigned int delta_from_mid_point_delta_in_us;
-
-	min_frame_duration_in_ns = ((unsigned int) (div64_u64(
-		(1000000000ULL * 1000000),
-		in_out_vrr->max_refresh_in_uhz)));
+	unsigned int max_render_time_in_us =
+			in_out_vrr->max_duration_in_us - in_out_vrr->btr.margin_in_us;
 
 	/* Program BTR */
-	if (last_render_time_in_us + BTR_EXIT_MARGIN < max_render_time_in_us) {
+	if ((last_render_time_in_us + in_out_vrr->btr.margin_in_us / 2) < max_render_time_in_us) {
 		/* Exit Below the Range */
 		if (in_out_vrr->btr.btr_active) {
 			in_out_vrr->btr.frame_counter = 0;
 			in_out_vrr->btr.btr_active = false;
 		}
-	} else if (last_render_time_in_us > max_render_time_in_us) {
+	} else if (last_render_time_in_us > (max_render_time_in_us + in_out_vrr->btr.margin_in_us / 2)) {
 		/* Enter Below the Range */
-		in_out_vrr->btr.btr_active = true;
+		if (!in_out_vrr->btr.btr_active) {
+			in_out_vrr->btr.btr_active = true;
+		}
 	}
 
 	/* BTR set to "not active" so disengage */
@@ -323,7 +325,9 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		/* Choose number of frames to insert based on how close it
 		 * can get to the mid point of the variable range.
 		 */
-		if (delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2) {
+		if ((frame_time_in_us / mid_point_frames_ceil) > in_out_vrr->min_duration_in_us &&
+				(delta_from_mid_point_in_us_1 < delta_from_mid_point_in_us_2 ||
+						mid_point_frames_floor < 2)) {
 			frames_to_insert = mid_point_frames_ceil;
 			delta_from_mid_point_delta_in_us = delta_from_mid_point_in_us_2 -
 					delta_from_mid_point_in_us_1;
@@ -339,7 +343,7 @@ static void apply_below_the_range(struct core_freesync *core_freesync,
 		if (in_out_vrr->btr.frames_to_insert != 0 &&
 				delta_from_mid_point_delta_in_us < BTR_DRIFT_MARGIN) {
 			if (((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) <
-					in_out_vrr->max_duration_in_us) &&
+					max_render_time_in_us) &&
 				((last_render_time_in_us / in_out_vrr->btr.frames_to_insert) >
 					in_out_vrr->min_duration_in_us))
 				frames_to_insert = in_out_vrr->btr.frames_to_insert;
@@ -743,6 +747,10 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 	nominal_field_rate_in_uhz =
 			mod_freesync_calc_nominal_field_rate(stream);
 
+	/* Rounded to the nearest Hz */
+	nominal_field_rate_in_uhz = 1000000ULL *
+			div_u64(nominal_field_rate_in_uhz + 500000, 1000000);
+
 	min_refresh_in_uhz = in_config->min_refresh_in_uhz;
 	max_refresh_in_uhz = in_config->max_refresh_in_uhz;
 
@@ -788,6 +796,11 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 		refresh_range = in_out_vrr->max_refresh_in_uhz -
 				in_out_vrr->min_refresh_in_uhz;
 
+		in_out_vrr->btr.margin_in_us = in_out_vrr->max_duration_in_us -
+				2 * in_out_vrr->min_duration_in_us;
+		if (in_out_vrr->btr.margin_in_us > BTR_MAX_MARGIN)
+			in_out_vrr->btr.margin_in_us = BTR_MAX_MARGIN;
+
 		in_out_vrr->supported = true;
 	}
 
@@ -803,6 +816,7 @@ void mod_freesync_build_vrr_params(struct mod_freesync *mod_freesync,
 	in_out_vrr->btr.inserted_duration_in_us = 0;
 	in_out_vrr->btr.frames_to_insert = 0;
 	in_out_vrr->btr.frame_counter = 0;
+
 	in_out_vrr->btr.mid_point_in_us =
 				(in_out_vrr->min_duration_in_us +
 				 in_out_vrr->max_duration_in_us) / 2;
@@ -975,13 +989,9 @@ void mod_freesync_get_settings(struct mod_freesync *mod_freesync,
 		unsigned int *inserted_frames,
 		unsigned int *inserted_duration_in_us)
 {
-	struct core_freesync *core_freesync = NULL;
-
 	if (mod_freesync == NULL)
 		return;
 
-	core_freesync = MOD_FREESYNC_TO_CORE(mod_freesync);
-
 	if (vrr->supported) {
 		*v_total_min = vrr->adjust.v_total_min;
 		*v_total_max = vrr->adjust.v_total_max;
@@ -996,14 +1006,13 @@ unsigned long long mod_freesync_calc_nominal_field_rate(
 			const struct dc_stream_state *stream)
 {
 	unsigned long long nominal_field_rate_in_uhz = 0;
+	unsigned int total = stream->timing.h_total * stream->timing.v_total;
 
-	/* Calculate nominal field rate for stream */
+	/* Calculate nominal field rate for stream, rounded up to nearest integer */
 	nominal_field_rate_in_uhz = stream->timing.pix_clk_100hz / 10;
 	nominal_field_rate_in_uhz *= 1000ULL * 1000ULL * 1000ULL;
-	nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz,
-						stream->timing.h_total);
-	nominal_field_rate_in_uhz = div_u64(nominal_field_rate_in_uhz,
-						stream->timing.v_total);
+
+	nominal_field_rate_in_uhz =	div_u64(nominal_field_rate_in_uhz, total);
 
 	return nominal_field_rate_in_uhz;
 }
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/Makefile b/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
new file mode 100644
index 000000000000..1c3c6d47973a
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/Makefile
@@ -0,0 +1,32 @@
+#
+# Copyright 2019 Advanced Micro Devices, Inc.
+#
+# Permission is hereby granted, free of charge, to any person obtaining a
+# copy of this software and associated documentation files (the "Software"),
+# to deal in the Software without restriction, including without limitation
+# the rights to use, copy, modify, merge, publish, distribute, sublicense,
+# and/or sell copies of the Software, and to permit persons to whom the
+# Software is furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+# THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+# OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+# ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+# OTHER DEALINGS IN THE SOFTWARE.
+#
+#
+# Makefile for the 'hdcp' sub-module of DAL.
+#
+
+HDCP = hdcp_ddc.o hdcp_log.o hdcp_psp.o hdcp.o \
+		hdcp1_execution.o hdcp1_transition.o
+
+AMD_DAL_HDCP = $(addprefix $(AMDDALPATH)/modules/hdcp/,$(HDCP))
+#$(info ************  DAL-HDCP_MAKEFILE ************)
+
+AMD_DISPLAY_FILES += $(AMD_DAL_HDCP)
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
new file mode 100644
index 000000000000..d7ac445dec6f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.c
@@ -0,0 +1,426 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hdcp.h"
+
+static void push_error_status(struct mod_hdcp *hdcp,
+		enum mod_hdcp_status status)
+{
+	struct mod_hdcp_trace *trace = &hdcp->connection.trace;
+
+	if (trace->error_count < MAX_NUM_OF_ERROR_TRACE) {
+		trace->errors[trace->error_count].status = status;
+		trace->errors[trace->error_count].state_id = hdcp->state.id;
+		trace->error_count++;
+		HDCP_ERROR_TRACE(hdcp, status);
+	}
+
+	hdcp->connection.hdcp1_retry_count++;
+}
+
+static uint8_t is_cp_desired_hdcp1(struct mod_hdcp *hdcp)
+{
+	int i, display_enabled = 0;
+
+	/* if all displays on the link are disabled, hdcp is not desired */
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_INACTIVE &&
+				!hdcp->connection.displays[i].adjust.disable) {
+			display_enabled = 1;
+			break;
+		}
+	}
+
+	return (hdcp->connection.hdcp1_retry_count < MAX_NUM_OF_ATTEMPTS) &&
+			display_enabled && !hdcp->connection.link.adjust.hdcp1.disable;
+}
+
+static enum mod_hdcp_status execution(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		union mod_hdcp_transition_input *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (is_in_initialized_state(hdcp)) {
+		if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+			event_ctx->unexpected_event = 1;
+			goto out;
+		}
+		/* initialize transition input */
+		memset(input, 0, sizeof(union mod_hdcp_transition_input));
+	} else if (is_in_cp_not_desired_state(hdcp)) {
+		if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+			event_ctx->unexpected_event = 1;
+			goto out;
+		}
+		/* update topology event if hdcp is not desired */
+		status = mod_hdcp_add_display_topology(hdcp);
+	} else if (is_in_hdcp1_states(hdcp)) {
+		status = mod_hdcp_hdcp1_execution(hdcp, event_ctx, &input->hdcp1);
+	} else if (is_in_hdcp1_dp_states(hdcp)) {
+		status = mod_hdcp_hdcp1_dp_execution(hdcp,
+				event_ctx, &input->hdcp1);
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		union mod_hdcp_transition_input *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->unexpected_event)
+		goto out;
+
+	if (is_in_initialized_state(hdcp)) {
+		if (is_dp_hdcp(hdcp))
+			if (is_cp_desired_hdcp1(hdcp)) {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, D1_A0_DETERMINE_RX_HDCP_CAPABLE);
+			} else {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
+			}
+		else if (is_hdmi_dvi_sl_hdcp(hdcp))
+			if (is_cp_desired_hdcp1(hdcp)) {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, H1_A0_WAIT_FOR_ACTIVE_RX);
+			} else {
+				callback_in_ms(0, output);
+				set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
+			}
+		else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, HDCP_CP_NOT_DESIRED);
+		}
+	} else if (is_in_cp_not_desired_state(hdcp)) {
+		increment_stay_counter(hdcp);
+	} else if (is_in_hdcp1_states(hdcp)) {
+		status = mod_hdcp_hdcp1_transition(hdcp,
+				event_ctx, &input->hdcp1, output);
+	} else if (is_in_hdcp1_dp_states(hdcp)) {
+		status = mod_hdcp_hdcp1_dp_transition(hdcp,
+				event_ctx, &input->hdcp1, output);
+	} else {
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status reset_authentication(struct mod_hdcp *hdcp,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (is_hdcp1(hdcp)) {
+		if (hdcp->auth.trans_input.hdcp1.create_session != UNKNOWN)
+			mod_hdcp_hdcp1_destroy_session(hdcp);
+
+		if (hdcp->auth.trans_input.hdcp1.add_topology == PASS) {
+			status = mod_hdcp_remove_display_topology(hdcp);
+			if (status != MOD_HDCP_STATUS_SUCCESS) {
+				output->callback_needed = 0;
+				output->watchdog_timer_needed = 0;
+				goto out;
+			}
+		}
+		HDCP_TOP_RESET_AUTH_TRACE(hdcp);
+		memset(&hdcp->auth, 0, sizeof(struct mod_hdcp_authentication));
+		memset(&hdcp->state, 0, sizeof(struct mod_hdcp_state));
+		set_state_id(hdcp, output, HDCP_INITIALIZED);
+	} else if (is_in_cp_not_desired_state(hdcp)) {
+		status = mod_hdcp_remove_display_topology(hdcp);
+		if (status != MOD_HDCP_STATUS_SUCCESS) {
+			output->callback_needed = 0;
+			output->watchdog_timer_needed = 0;
+			goto out;
+		}
+		HDCP_TOP_RESET_AUTH_TRACE(hdcp);
+		memset(&hdcp->auth, 0, sizeof(struct mod_hdcp_authentication));
+		memset(&hdcp->state, 0, sizeof(struct mod_hdcp_state));
+		set_state_id(hdcp, output, HDCP_INITIALIZED);
+	}
+
+out:
+	/* stop callback and watchdog requests from previous authentication*/
+	output->watchdog_timer_stop = 1;
+	output->callback_stop = 1;
+	return status;
+}
+
+static enum mod_hdcp_status reset_connection(struct mod_hdcp *hdcp,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	memset(output, 0, sizeof(struct mod_hdcp_output));
+
+	status = reset_authentication(hdcp, output);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	if (current_state(hdcp) != HDCP_UNINITIALIZED) {
+		HDCP_TOP_RESET_CONN_TRACE(hdcp);
+		set_state_id(hdcp, output, HDCP_UNINITIALIZED);
+	}
+	memset(&hdcp->connection, 0, sizeof(hdcp->connection));
+out:
+	return status;
+}
+
+/*
+ * Implementation of functions in mod_hdcp.h
+ */
+size_t mod_hdcp_get_memory_size(void)
+{
+	return sizeof(struct mod_hdcp);
+}
+
+enum mod_hdcp_status mod_hdcp_setup(struct mod_hdcp *hdcp,
+		struct mod_hdcp_config *config)
+{
+	struct mod_hdcp_output output;
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	memset(hdcp, 0, sizeof(struct mod_hdcp));
+	memset(&output, 0, sizeof(output));
+	hdcp->config = *config;
+	HDCP_TOP_INTERFACE_TRACE(hdcp);
+	status = reset_connection(hdcp, &output);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		push_error_status(hdcp, status);
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_teardown(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_output output;
+
+	HDCP_TOP_INTERFACE_TRACE(hdcp);
+	memset(&output, 0,  sizeof(output));
+	status = reset_connection(hdcp, &output);
+	if (status == MOD_HDCP_STATUS_SUCCESS)
+		memset(hdcp, 0, sizeof(struct mod_hdcp));
+	else
+		push_error_status(hdcp, status);
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp,
+		struct mod_hdcp_link *link, struct mod_hdcp_display *display,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_display *display_container = NULL;
+
+	HDCP_TOP_INTERFACE_TRACE_WITH_INDEX(hdcp, display->index);
+	memset(output, 0, sizeof(struct mod_hdcp_output));
+
+	/* skip inactive display */
+	if (display->state != MOD_HDCP_DISPLAY_ACTIVE) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+		goto out;
+	}
+
+	/* check existing display container */
+	if (get_active_display_at_index(hdcp, display->index)) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+		goto out;
+	}
+
+	/* find an empty display container */
+	display_container = get_empty_display_container(hdcp);
+	if (!display_container) {
+		status = MOD_HDCP_STATUS_DISPLAY_OUT_OF_BOUND;
+		goto out;
+	}
+
+	/* reset existing authentication status */
+	status = reset_authentication(hdcp, output);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	/* add display to connection */
+	hdcp->connection.link = *link;
+	*display_container = *display;
+
+	/* reset retry counters */
+	reset_retry_counts(hdcp);
+
+	/* reset error trace */
+	memset(&hdcp->connection.trace, 0, sizeof(hdcp->connection.trace));
+
+	/* request authentication */
+	if (current_state(hdcp) != HDCP_INITIALIZED)
+		set_state_id(hdcp, output, HDCP_INITIALIZED);
+	callback_in_ms(hdcp->connection.link.adjust.auth_delay * 1000, output);
+out:
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		push_error_status(hdcp, status);
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp,
+		uint8_t index, struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_display *display = NULL;
+
+	HDCP_TOP_INTERFACE_TRACE_WITH_INDEX(hdcp, index);
+	memset(output, 0, sizeof(struct mod_hdcp_output));
+
+	/* find display in connection */
+	display = get_active_display_at_index(hdcp, index);
+	if (!display) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+		goto out;
+	}
+
+	/* stop current authentication */
+	status = reset_authentication(hdcp, output);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	/* remove display */
+	display->state = MOD_HDCP_DISPLAY_INACTIVE;
+
+	/* clear retry counters */
+	reset_retry_counts(hdcp);
+
+	/* reset error trace */
+	memset(&hdcp->connection.trace, 0, sizeof(hdcp->connection.trace));
+
+	/* request authentication for remaining displays*/
+	if (get_active_display_count(hdcp) > 0)
+		callback_in_ms(hdcp->connection.link.adjust.auth_delay * 1000,
+				output);
+out:
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		push_error_status(hdcp, status);
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_query_display(struct mod_hdcp *hdcp,
+		uint8_t index, struct mod_hdcp_display_query *query)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_display *display = NULL;
+
+	/* find display in connection */
+	display = get_active_display_at_index(hdcp, index);
+	if (!display) {
+		status = MOD_HDCP_STATUS_DISPLAY_NOT_FOUND;
+		goto out;
+	}
+
+	/* populate query */
+	query->link = &hdcp->connection.link;
+	query->display = display;
+	query->trace = &hdcp->connection.trace;
+	query->encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+
+	mod_hdcp_hdcp1_get_link_encryption_status(hdcp, &query->encryption_status);
+
+out:
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_reset_connection(struct mod_hdcp *hdcp,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	HDCP_TOP_INTERFACE_TRACE(hdcp);
+	status = reset_connection(hdcp, output);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		push_error_status(hdcp, status);
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp,
+		enum mod_hdcp_event event, struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status exec_status, trans_status, reset_status, status;
+	struct mod_hdcp_event_context event_ctx;
+
+	HDCP_EVENT_TRACE(hdcp, event);
+	memset(output, 0, sizeof(struct mod_hdcp_output));
+	memset(&event_ctx, 0, sizeof(struct mod_hdcp_event_context));
+	event_ctx.event = event;
+
+	/* execute and transition */
+	exec_status = execution(hdcp, &event_ctx, &hdcp->auth.trans_input);
+	trans_status = transition(
+			hdcp, &event_ctx, &hdcp->auth.trans_input, output);
+	if (trans_status == MOD_HDCP_STATUS_SUCCESS) {
+		status = MOD_HDCP_STATUS_SUCCESS;
+	} else if (exec_status == MOD_HDCP_STATUS_SUCCESS) {
+		status = MOD_HDCP_STATUS_INTERNAL_POLICY_FAILURE;
+		push_error_status(hdcp, status);
+	} else {
+		status = exec_status;
+		push_error_status(hdcp, status);
+	}
+
+	/* reset authentication if needed */
+	if (trans_status == MOD_HDCP_STATUS_RESET_NEEDED) {
+		HDCP_FULL_DDC_TRACE(hdcp);
+		reset_status = reset_authentication(hdcp, output);
+		if (reset_status != MOD_HDCP_STATUS_SUCCESS)
+			push_error_status(hdcp, reset_status);
+	}
+	return status;
+}
+
+enum mod_hdcp_operation_mode mod_hdcp_signal_type_to_operation_mode(
+		enum signal_type signal)
+{
+	enum mod_hdcp_operation_mode mode = MOD_HDCP_MODE_OFF;
+
+	switch (signal) {
+	case SIGNAL_TYPE_DVI_SINGLE_LINK:
+	case SIGNAL_TYPE_HDMI_TYPE_A:
+		mode = MOD_HDCP_MODE_DEFAULT;
+		break;
+	case SIGNAL_TYPE_EDP:
+	case SIGNAL_TYPE_DISPLAY_PORT:
+		mode = MOD_HDCP_MODE_DP;
+		break;
+	case SIGNAL_TYPE_DISPLAY_PORT_MST:
+		mode = MOD_HDCP_MODE_DP_MST;
+		break;
+	default:
+		break;
+	};
+
+	return mode;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
new file mode 100644
index 000000000000..5664bc0b5bd0
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp.h
@@ -0,0 +1,442 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef HDCP_H_
+#define HDCP_H_
+
+#include "mod_hdcp.h"
+#include "hdcp_log.h"
+
+#define BCAPS_READY_MASK				0x20
+#define BCAPS_REPEATER_MASK				0x40
+#define BSTATUS_DEVICE_COUNT_MASK			0X007F
+#define BSTATUS_MAX_DEVS_EXCEEDED_MASK			0x0080
+#define BSTATUS_MAX_CASCADE_EXCEEDED_MASK		0x0800
+#define BCAPS_HDCP_CAPABLE_MASK_DP			0x01
+#define BCAPS_REPEATER_MASK_DP				0x02
+#define BSTATUS_READY_MASK_DP				0x01
+#define BSTATUS_R0_P_AVAILABLE_MASK_DP			0x02
+#define BSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP		0x04
+#define BSTATUS_REAUTH_REQUEST_MASK_DP			0x08
+#define BINFO_DEVICE_COUNT_MASK_DP			0X007F
+#define BINFO_MAX_DEVS_EXCEEDED_MASK_DP			0x0080
+#define BINFO_MAX_CASCADE_EXCEEDED_MASK_DP		0x0800
+
+#define RXSTATUS_MSG_SIZE_MASK				0x03FF
+#define RXSTATUS_READY_MASK				0x0400
+#define RXSTATUS_REAUTH_REQUEST_MASK			0x0800
+#define RXIDLIST_DEVICE_COUNT_LOWER_MASK		0xf0
+#define RXIDLIST_DEVICE_COUNT_UPPER_MASK		0x01
+#define RXCAPS_BYTE0_HDCP_CAPABLE_MASK_DP		0x02
+#define RXSTATUS_READY_MASK_DP				0x0001
+#define RXSTATUS_H_P_AVAILABLE_MASK_DP			0x0002
+#define RXSTATUS_PAIRING_AVAILABLE_MASK_DP		0x0004
+#define RXSTATUS_REAUTH_REQUEST_MASK_DP			0x0008
+#define RXSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP		0x0010
+
+enum mod_hdcp_trans_input_result {
+	UNKNOWN = 0,
+	PASS,
+	FAIL
+};
+
+struct mod_hdcp_transition_input_hdcp1 {
+	uint8_t bksv_read;
+	uint8_t bksv_validation;
+	uint8_t add_topology;
+	uint8_t create_session;
+	uint8_t an_write;
+	uint8_t aksv_write;
+	uint8_t ainfo_write;
+	uint8_t bcaps_read;
+	uint8_t r0p_read;
+	uint8_t rx_validation;
+	uint8_t encryption;
+	uint8_t link_maintenance;
+	uint8_t ready_check;
+	uint8_t bstatus_read;
+	uint8_t max_cascade_check;
+	uint8_t max_devs_check;
+	uint8_t device_count_check;
+	uint8_t ksvlist_read;
+	uint8_t vp_read;
+	uint8_t ksvlist_vp_validation;
+
+	uint8_t hdcp_capable_dp;
+	uint8_t binfo_read_dp;
+	uint8_t r0p_available_dp;
+	uint8_t link_integiry_check;
+	uint8_t reauth_request_check;
+	uint8_t stream_encryption_dp;
+};
+
+union mod_hdcp_transition_input {
+	struct mod_hdcp_transition_input_hdcp1 hdcp1;
+};
+
+struct mod_hdcp_message_hdcp1 {
+	uint8_t		an[8];
+	uint8_t		aksv[5];
+	uint8_t		ainfo;
+	uint8_t		bksv[5];
+	uint16_t	r0p;
+	uint8_t		bcaps;
+	uint16_t	bstatus;
+	uint8_t		ksvlist[635];
+	uint16_t	ksvlist_size;
+	uint8_t		vp[20];
+
+	uint16_t	binfo_dp;
+};
+
+union mod_hdcp_message {
+	struct mod_hdcp_message_hdcp1 hdcp1;
+};
+
+struct mod_hdcp_auth_counters {
+	uint8_t stream_management_retry_count;
+};
+
+/* contains values per connection */
+struct mod_hdcp_connection {
+	struct mod_hdcp_link link;
+	struct mod_hdcp_display displays[MAX_NUM_OF_DISPLAYS];
+	uint8_t is_repeater;
+	uint8_t is_km_stored;
+	struct mod_hdcp_trace trace;
+	uint8_t hdcp1_retry_count;
+};
+
+/* contains values per authentication cycle */
+struct mod_hdcp_authentication {
+	uint32_t id;
+	union mod_hdcp_message msg;
+	union mod_hdcp_transition_input trans_input;
+	struct mod_hdcp_auth_counters count;
+};
+
+/* contains values per state change */
+struct mod_hdcp_state {
+	uint8_t id;
+	uint32_t stay_count;
+};
+
+/* per event in a state */
+struct mod_hdcp_event_context {
+	enum mod_hdcp_event event;
+	uint8_t rx_id_list_ready;
+	uint8_t unexpected_event;
+};
+
+struct mod_hdcp {
+	/* per link */
+	struct mod_hdcp_config config;
+	/* per connection */
+	struct mod_hdcp_connection connection;
+	/* per authentication attempt */
+	struct mod_hdcp_authentication auth;
+	/* per state in an authentication */
+	struct mod_hdcp_state state;
+	/* reserved memory buffer */
+	uint8_t buf[2025];
+};
+
+enum mod_hdcp_initial_state_id {
+	HDCP_UNINITIALIZED = 0x0,
+	HDCP_INITIAL_STATE_START = HDCP_UNINITIALIZED,
+	HDCP_INITIALIZED,
+	HDCP_CP_NOT_DESIRED,
+	HDCP_INITIAL_STATE_END = HDCP_CP_NOT_DESIRED
+};
+
+enum mod_hdcp_hdcp1_state_id {
+	HDCP1_STATE_START = HDCP_INITIAL_STATE_END,
+	H1_A0_WAIT_FOR_ACTIVE_RX,
+	H1_A1_EXCHANGE_KSVS,
+	H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER,
+	H1_A45_AUTHENTICATED,
+	H1_A8_WAIT_FOR_READY,
+	H1_A9_READ_KSV_LIST,
+	HDCP1_STATE_END = H1_A9_READ_KSV_LIST
+};
+
+enum mod_hdcp_hdcp1_dp_state_id {
+	HDCP1_DP_STATE_START = HDCP1_STATE_END,
+	D1_A0_DETERMINE_RX_HDCP_CAPABLE,
+	D1_A1_EXCHANGE_KSVS,
+	D1_A23_WAIT_FOR_R0_PRIME,
+	D1_A2_COMPUTATIONS_A3_VALIDATE_RX_A5_TEST_FOR_REPEATER,
+	D1_A4_AUTHENTICATED,
+	D1_A6_WAIT_FOR_READY,
+	D1_A7_READ_KSV_LIST,
+	HDCP1_DP_STATE_END = D1_A7_READ_KSV_LIST,
+};
+
+/* hdcp1 executions and transitions */
+typedef enum mod_hdcp_status (*mod_hdcp_action)(struct mod_hdcp *hdcp);
+uint8_t mod_hdcp_execute_and_set(
+		mod_hdcp_action func, uint8_t *flag,
+		enum mod_hdcp_status *status, struct mod_hdcp *hdcp, char *str);
+enum mod_hdcp_status mod_hdcp_hdcp1_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp1 *input);
+enum mod_hdcp_status mod_hdcp_hdcp1_dp_execution(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp1 *input);
+enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp1 *input,
+	struct mod_hdcp_output *output);
+enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
+	struct mod_hdcp_event_context *event_ctx,
+	struct mod_hdcp_transition_input_hdcp1 *input,
+	struct mod_hdcp_output *output);
+
+/* log functions */
+void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size,
+		uint8_t *buf, uint32_t buf_size);
+/* TODO: add adjustment log */
+
+/* psp functions */
+enum mod_hdcp_status mod_hdcp_add_display_topology(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_remove_display_topology(
+		struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_validate_rx(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_enable_encryption(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_validate_ksvlist_vp(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(
+	struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_link_maintenance(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *hdcp,
+							       enum mod_hdcp_encryption_status *encryption_status);
+/* ddc functions */
+enum mod_hdcp_status mod_hdcp_read_bksv(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_bcaps(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_bstatus(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_r0p(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_ksvlist(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_vp(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_binfo(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_aksv(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_ainfo(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_an(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_rxcaps(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_rxstatus(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_ake_cert(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_h_prime(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_pairing_info(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_l_prime(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_rx_id_list(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_read_stream_ready(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_ake_init(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_no_stored_km(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_stored_km(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_lc_init(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_eks(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_repeater_auth_ack(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_stream_manage(struct mod_hdcp *hdcp);
+enum mod_hdcp_status mod_hdcp_write_content_type(struct mod_hdcp *hdcp);
+
+/* hdcp version helpers */
+static inline uint8_t is_dp_hdcp(struct mod_hdcp *hdcp)
+{
+	return (hdcp->connection.link.mode == MOD_HDCP_MODE_DP ||
+			hdcp->connection.link.mode == MOD_HDCP_MODE_DP_MST);
+}
+
+static inline uint8_t is_dp_mst_hdcp(struct mod_hdcp *hdcp)
+{
+	return (hdcp->connection.link.mode == MOD_HDCP_MODE_DP_MST);
+}
+
+static inline uint8_t is_hdmi_dvi_sl_hdcp(struct mod_hdcp *hdcp)
+{
+	return (hdcp->connection.link.mode == MOD_HDCP_MODE_DEFAULT);
+}
+
+/* hdcp state helpers */
+static inline uint8_t current_state(struct mod_hdcp *hdcp)
+{
+	return hdcp->state.id;
+}
+
+static inline void set_state_id(struct mod_hdcp *hdcp,
+		struct mod_hdcp_output *output, uint8_t id)
+{
+	memset(&hdcp->state, 0, sizeof(hdcp->state));
+	hdcp->state.id = id;
+	/* callback timer should be reset per state */
+	output->callback_stop = 1;
+	output->watchdog_timer_stop = 1;
+	HDCP_NEXT_STATE_TRACE(hdcp, id, output);
+}
+
+static inline uint8_t is_in_hdcp1_states(struct mod_hdcp *hdcp)
+{
+	return (current_state(hdcp) > HDCP1_STATE_START &&
+			current_state(hdcp) <= HDCP1_STATE_END);
+}
+
+static inline uint8_t is_in_hdcp1_dp_states(struct mod_hdcp *hdcp)
+{
+	return (current_state(hdcp) > HDCP1_DP_STATE_START &&
+			current_state(hdcp) <= HDCP1_DP_STATE_END);
+}
+
+static inline uint8_t is_hdcp1(struct mod_hdcp *hdcp)
+{
+	return (is_in_hdcp1_states(hdcp) || is_in_hdcp1_dp_states(hdcp));
+}
+
+static inline uint8_t is_in_cp_not_desired_state(struct mod_hdcp *hdcp)
+{
+	return current_state(hdcp) == HDCP_CP_NOT_DESIRED;
+}
+
+static inline uint8_t is_in_initialized_state(struct mod_hdcp *hdcp)
+{
+	return current_state(hdcp) == HDCP_INITIALIZED;
+}
+
+/* transition operation helpers */
+static inline void increment_stay_counter(struct mod_hdcp *hdcp)
+{
+	hdcp->state.stay_count++;
+}
+
+static inline void fail_and_restart_in_ms(uint16_t time,
+		enum mod_hdcp_status *status,
+		struct mod_hdcp_output *output)
+{
+	output->callback_needed = 1;
+	output->callback_delay = time;
+	output->watchdog_timer_needed = 0;
+	output->watchdog_timer_delay = 0;
+	*status = MOD_HDCP_STATUS_RESET_NEEDED;
+}
+
+static inline void callback_in_ms(uint16_t time, struct mod_hdcp_output *output)
+{
+	output->callback_needed = 1;
+	output->callback_delay = time;
+}
+
+static inline void set_watchdog_in_ms(struct mod_hdcp *hdcp, uint16_t time,
+		struct mod_hdcp_output *output)
+{
+	output->watchdog_timer_needed = 1;
+	output->watchdog_timer_delay = time;
+}
+
+/* connection topology helpers */
+static inline uint8_t is_display_active(struct mod_hdcp_display *display)
+{
+	return display->state >= MOD_HDCP_DISPLAY_ACTIVE;
+}
+
+static inline uint8_t is_display_added(struct mod_hdcp_display *display)
+{
+	return display->state >= MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED;
+}
+
+static inline uint8_t is_display_encryption_enabled(struct mod_hdcp_display *display)
+{
+	return display->state >= MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+}
+
+static inline uint8_t get_active_display_count(struct mod_hdcp *hdcp)
+{
+	uint8_t added_count = 0;
+	uint8_t i;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++)
+		if (is_display_active(&hdcp->connection.displays[i]))
+			added_count++;
+	return added_count;
+}
+
+static inline uint8_t get_added_display_count(struct mod_hdcp *hdcp)
+{
+	uint8_t added_count = 0;
+	uint8_t i;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++)
+		if (is_display_added(&hdcp->connection.displays[i]))
+			added_count++;
+	return added_count;
+}
+
+static inline struct mod_hdcp_display *get_first_added_display(
+		struct mod_hdcp *hdcp)
+{
+	uint8_t i;
+	struct mod_hdcp_display *display = NULL;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++)
+		if (is_display_added(&hdcp->connection.displays[i])) {
+			display = &hdcp->connection.displays[i];
+			break;
+		}
+	return display;
+}
+
+static inline struct mod_hdcp_display *get_active_display_at_index(
+		struct mod_hdcp *hdcp, uint8_t index)
+{
+	uint8_t i;
+	struct mod_hdcp_display *display = NULL;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++)
+		if (hdcp->connection.displays[i].index == index &&
+				is_display_active(&hdcp->connection.displays[i])) {
+			display = &hdcp->connection.displays[i];
+			break;
+		}
+	return display;
+}
+
+static inline struct mod_hdcp_display *get_empty_display_container(
+		struct mod_hdcp *hdcp)
+{
+	uint8_t i;
+	struct mod_hdcp_display *display = NULL;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++)
+		if (!is_display_active(&hdcp->connection.displays[i])) {
+			display = &hdcp->connection.displays[i];
+			break;
+		}
+	return display;
+}
+
+static inline void reset_retry_counts(struct mod_hdcp *hdcp)
+{
+	hdcp->connection.hdcp1_retry_count = 0;
+}
+
+#endif /* HDCP_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
new file mode 100644
index 000000000000..3db4a7da414f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
@@ -0,0 +1,531 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hdcp.h"
+
+static inline enum mod_hdcp_status validate_bksv(struct mod_hdcp *hdcp)
+{
+	uint64_t n = *(uint64_t *)hdcp->auth.msg.hdcp1.bksv;
+	uint8_t count = 0;
+
+	while (n) {
+		count++;
+		n &= (n - 1);
+	}
+	return (count == 20) ? MOD_HDCP_STATUS_SUCCESS :
+			MOD_HDCP_STATUS_HDCP1_INVALID_BKSV;
+}
+
+static inline enum mod_hdcp_status check_ksv_ready(struct mod_hdcp *hdcp)
+{
+	if (is_dp_hdcp(hdcp))
+		return (hdcp->auth.msg.hdcp1.bstatus & BSTATUS_READY_MASK_DP) ?
+				MOD_HDCP_STATUS_SUCCESS :
+				MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY;
+	return (hdcp->auth.msg.hdcp1.bcaps & BCAPS_READY_MASK) ?
+			MOD_HDCP_STATUS_SUCCESS :
+			MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY;
+}
+
+static inline enum mod_hdcp_status check_hdcp_capable_dp(struct mod_hdcp *hdcp)
+{
+	return (hdcp->auth.msg.hdcp1.bcaps & BCAPS_HDCP_CAPABLE_MASK_DP) ?
+			MOD_HDCP_STATUS_SUCCESS :
+			MOD_HDCP_STATUS_HDCP1_NOT_CAPABLE;
+}
+
+static inline enum mod_hdcp_status check_r0p_available_dp(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+	if (is_dp_hdcp(hdcp)) {
+		status = (hdcp->auth.msg.hdcp1.bstatus &
+				BSTATUS_R0_P_AVAILABLE_MASK_DP) ?
+			MOD_HDCP_STATUS_SUCCESS :
+			MOD_HDCP_STATUS_HDCP1_R0_PRIME_PENDING;
+	} else {
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+	}
+	return status;
+}
+
+static inline enum mod_hdcp_status check_link_integrity_dp(
+		struct mod_hdcp *hdcp)
+{
+	return (hdcp->auth.msg.hdcp1.bstatus &
+			BSTATUS_LINK_INTEGRITY_FAILURE_MASK_DP) ?
+			MOD_HDCP_STATUS_HDCP1_LINK_INTEGRITY_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static inline enum mod_hdcp_status check_no_reauthentication_request_dp(
+		struct mod_hdcp *hdcp)
+{
+	return (hdcp->auth.msg.hdcp1.bstatus & BSTATUS_REAUTH_REQUEST_MASK_DP) ?
+			MOD_HDCP_STATUS_HDCP1_REAUTH_REQUEST_ISSUED :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static inline enum mod_hdcp_status check_no_max_cascade(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = (hdcp->auth.msg.hdcp1.binfo_dp &
+				BINFO_MAX_CASCADE_EXCEEDED_MASK_DP) ?
+			MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+	else
+		status = (hdcp->auth.msg.hdcp1.bstatus &
+				BSTATUS_MAX_CASCADE_EXCEEDED_MASK) ?
+				MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE :
+				MOD_HDCP_STATUS_SUCCESS;
+	return status;
+}
+
+static inline enum mod_hdcp_status check_no_max_devs(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = (hdcp->auth.msg.hdcp1.binfo_dp &
+				BINFO_MAX_DEVS_EXCEEDED_MASK_DP) ?
+				MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE :
+				MOD_HDCP_STATUS_SUCCESS;
+	else
+		status = (hdcp->auth.msg.hdcp1.bstatus &
+				BSTATUS_MAX_DEVS_EXCEEDED_MASK) ?
+				MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE :
+				MOD_HDCP_STATUS_SUCCESS;
+	return status;
+}
+
+static inline uint8_t get_device_count(struct mod_hdcp *hdcp)
+{
+	return is_dp_hdcp(hdcp) ?
+			(hdcp->auth.msg.hdcp1.binfo_dp & BINFO_DEVICE_COUNT_MASK_DP) :
+			(hdcp->auth.msg.hdcp1.bstatus & BSTATUS_DEVICE_COUNT_MASK);
+}
+
+static inline enum mod_hdcp_status check_device_count(struct mod_hdcp *hdcp)
+{
+	/* device count must be greater than or equal to tracked hdcp displays */
+	return (get_device_count(hdcp) < get_added_display_count(hdcp)) ?
+			MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE :
+			MOD_HDCP_STATUS_SUCCESS;
+}
+
+static enum mod_hdcp_status wait_for_active_rx(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_bksv,
+			&input->bksv_read, &status,
+			hdcp, "bksv_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_bcaps,
+			&input->bcaps_read, &status,
+			hdcp, "bcaps_read"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status exchange_ksvs(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_add_display_topology,
+			&input->add_topology, &status,
+			hdcp, "add_topology"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_create_session,
+			&input->create_session, &status,
+			hdcp, "create_session"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_an,
+			&input->an_write, &status,
+			hdcp, "an_write"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_write_aksv,
+			&input->aksv_write, &status,
+			hdcp, "aksv_write"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_bksv,
+			&input->bksv_read, &status,
+			hdcp, "bksv_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(validate_bksv,
+			&input->bksv_validation, &status,
+			hdcp, "bksv_validation"))
+		goto out;
+	if (hdcp->auth.msg.hdcp1.ainfo) {
+		if (!mod_hdcp_execute_and_set(mod_hdcp_write_ainfo,
+				&input->ainfo_write, &status,
+				hdcp, "ainfo_write"))
+			goto out;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status computations_validate_rx_test_for_repeater(
+		struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_r0p,
+			&input->r0p_read, &status,
+			hdcp, "r0p_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_validate_rx,
+			&input->rx_validation, &status,
+			hdcp, "rx_validation"))
+		goto out;
+	if (hdcp->connection.is_repeater) {
+		if (!hdcp->connection.link.adjust.hdcp1.postpone_encryption)
+			if (!mod_hdcp_execute_and_set(
+					mod_hdcp_hdcp1_enable_encryption,
+					&input->encryption, &status,
+					hdcp, "encryption"))
+				goto out;
+	} else {
+		if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_enable_encryption,
+				&input->encryption, &status,
+				hdcp, "encryption"))
+			goto out;
+		if (is_dp_mst_hdcp(hdcp))
+			if (!mod_hdcp_execute_and_set(
+					mod_hdcp_hdcp1_enable_dp_stream_encryption,
+					&input->stream_encryption_dp, &status,
+					hdcp, "stream_encryption_dp"))
+				goto out;
+	}
+out:
+	return status;
+}
+
+static enum mod_hdcp_status authenticated(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_link_maintenance,
+			&input->link_maintenance, &status,
+			hdcp, "link_maintenance"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status wait_for_ready(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK &&
+			event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (is_dp_hdcp(hdcp)) {
+		if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus,
+				&input->bstatus_read, &status,
+				hdcp, "bstatus_read"))
+			goto out;
+		if (!mod_hdcp_execute_and_set(check_link_integrity_dp,
+				&input->link_integiry_check, &status,
+				hdcp, "link_integiry_check"))
+			goto out;
+		if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp,
+				&input->reauth_request_check, &status,
+				hdcp, "reauth_request_check"))
+			goto out;
+	} else {
+		if (!mod_hdcp_execute_and_set(mod_hdcp_read_bcaps,
+				&input->bcaps_read, &status,
+				hdcp, "bcaps_read"))
+			goto out;
+	}
+	if (!mod_hdcp_execute_and_set(check_ksv_ready,
+			&input->ready_check, &status,
+			hdcp, "ready_check"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status read_ksv_list(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	uint8_t device_count;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (is_dp_hdcp(hdcp)) {
+		if (!mod_hdcp_execute_and_set(mod_hdcp_read_binfo,
+				&input->binfo_read_dp, &status,
+				hdcp, "binfo_read_dp"))
+			goto out;
+	} else {
+		if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus,
+				&input->bstatus_read, &status,
+				hdcp, "bstatus_read"))
+			goto out;
+	}
+	if (!mod_hdcp_execute_and_set(check_no_max_cascade,
+			&input->max_cascade_check, &status,
+			hdcp, "max_cascade_check"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_no_max_devs,
+			&input->max_devs_check, &status,
+			hdcp, "max_devs_check"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_device_count,
+			&input->device_count_check, &status,
+			hdcp, "device_count_check"))
+		goto out;
+	device_count = get_device_count(hdcp);
+	hdcp->auth.msg.hdcp1.ksvlist_size = device_count*5;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_ksvlist,
+			&input->ksvlist_read, &status,
+			hdcp, "ksvlist_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_vp,
+			&input->vp_read, &status,
+			hdcp, "vp_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_validate_ksvlist_vp,
+			&input->ksvlist_vp_validation, &status,
+			hdcp, "ksvlist_vp_validation"))
+		goto out;
+	if (input->encryption != PASS)
+		if (!mod_hdcp_execute_and_set(mod_hdcp_hdcp1_enable_encryption,
+				&input->encryption, &status,
+				hdcp, "encryption"))
+			goto out;
+	if (is_dp_mst_hdcp(hdcp))
+		if (!mod_hdcp_execute_and_set(
+				mod_hdcp_hdcp1_enable_dp_stream_encryption,
+				&input->stream_encryption_dp, &status,
+				hdcp, "stream_encryption_dp"))
+			goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status determine_rx_hdcp_capable_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CALLBACK) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_bcaps,
+			&input->bcaps_read, &status,
+			hdcp, "bcaps_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_hdcp_capable_dp,
+			&input->hdcp_capable_dp, &status,
+			hdcp, "hdcp_capable_dp"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status wait_for_r0_prime_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CPIRQ &&
+			event_ctx->event != MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus,
+			&input->bstatus_read, &status,
+			hdcp, "bstatus_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_r0p_available_dp,
+			&input->r0p_available_dp, &status,
+			hdcp, "r0p_available_dp"))
+		goto out;
+out:
+	return status;
+}
+
+static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	if (event_ctx->event != MOD_HDCP_EVENT_CPIRQ) {
+		event_ctx->unexpected_event = 1;
+		goto out;
+	}
+
+	if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus,
+			&input->bstatus_read, &status,
+			hdcp, "bstatus_read"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_link_integrity_dp,
+			&input->link_integiry_check, &status,
+			hdcp, "link_integiry_check"))
+		goto out;
+	if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp,
+			&input->reauth_request_check, &status,
+			hdcp, "reauth_request_check"))
+		goto out;
+out:
+	return status;
+}
+
+uint8_t mod_hdcp_execute_and_set(
+		mod_hdcp_action func, uint8_t *flag,
+		enum mod_hdcp_status *status, struct mod_hdcp *hdcp, char *str)
+{
+	*status = func(hdcp);
+	if (*status == MOD_HDCP_STATUS_SUCCESS && *flag != PASS) {
+		HDCP_INPUT_PASS_TRACE(hdcp, str);
+		*flag = PASS;
+	} else if (*status != MOD_HDCP_STATUS_SUCCESS && *flag != FAIL) {
+		HDCP_INPUT_FAIL_TRACE(hdcp, str);
+		*flag = FAIL;
+	}
+	return (*status == MOD_HDCP_STATUS_SUCCESS);
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_execution(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	switch (current_state(hdcp)) {
+	case H1_A0_WAIT_FOR_ACTIVE_RX:
+		status = wait_for_active_rx(hdcp, event_ctx, input);
+		break;
+	case H1_A1_EXCHANGE_KSVS:
+		status = exchange_ksvs(hdcp, event_ctx, input);
+		break;
+	case H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER:
+		status = computations_validate_rx_test_for_repeater(hdcp,
+				event_ctx, input);
+		break;
+	case H1_A45_AUTHENTICATED:
+		status = authenticated(hdcp, event_ctx, input);
+		break;
+	case H1_A8_WAIT_FOR_READY:
+		status = wait_for_ready(hdcp, event_ctx, input);
+		break;
+	case H1_A9_READ_KSV_LIST:
+		status = read_ksv_list(hdcp, event_ctx, input);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		break;
+	}
+
+	return status;
+}
+
+extern enum mod_hdcp_status mod_hdcp_hdcp1_dp_execution(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+
+	switch (current_state(hdcp)) {
+	case D1_A0_DETERMINE_RX_HDCP_CAPABLE:
+		status = determine_rx_hdcp_capable_dp(hdcp, event_ctx, input);
+		break;
+	case D1_A1_EXCHANGE_KSVS:
+		status = exchange_ksvs(hdcp, event_ctx, input);
+		break;
+	case D1_A23_WAIT_FOR_R0_PRIME:
+		status = wait_for_r0_prime_dp(hdcp, event_ctx, input);
+		break;
+	case D1_A2_COMPUTATIONS_A3_VALIDATE_RX_A5_TEST_FOR_REPEATER:
+		status = computations_validate_rx_test_for_repeater(
+				hdcp, event_ctx, input);
+		break;
+	case D1_A4_AUTHENTICATED:
+		status = authenticated_dp(hdcp, event_ctx, input);
+		break;
+	case D1_A6_WAIT_FOR_READY:
+		status = wait_for_ready(hdcp, event_ctx, input);
+		break;
+	case D1_A7_READ_KSV_LIST:
+		status = read_ksv_list(hdcp, event_ctx, input);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		break;
+	}
+
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
new file mode 100644
index 000000000000..136b8011ff3f
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_transition.c
@@ -0,0 +1,307 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hdcp.h"
+
+enum mod_hdcp_status mod_hdcp_hdcp1_transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_connection *conn = &hdcp->connection;
+	struct mod_hdcp_link_adjustment *adjust = &hdcp->connection.link.adjust;
+
+	switch (current_state(hdcp)) {
+	case H1_A0_WAIT_FOR_ACTIVE_RX:
+		if (input->bksv_read != PASS || input->bcaps_read != PASS) {
+			/* 1A-04: repeatedly attempts on port access failure */
+			callback_in_ms(500, output);
+			increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H1_A1_EXCHANGE_KSVS);
+		break;
+	case H1_A1_EXCHANGE_KSVS:
+		if (input->add_topology != PASS ||
+				input->create_session != PASS) {
+			/* out of sync with psp state */
+			adjust->hdcp1.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->an_write != PASS ||
+				input->aksv_write != PASS ||
+				input->bksv_read != PASS ||
+				input->bksv_validation != PASS ||
+				input->ainfo_write == FAIL) {
+			/* 1A-05: consider invalid bksv a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(300, output);
+		set_state_id(hdcp, output,
+			H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER);
+		break;
+	case H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER:
+		if (input->bcaps_read != PASS ||
+				input->r0p_read != PASS ||
+				input->rx_validation != PASS ||
+				(!conn->is_repeater && input->encryption != PASS)) {
+			/* 1A-06: consider invalid r0' a failure */
+			/* 1A-08: consider bksv listed in SRM a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_repeater) {
+			callback_in_ms(0, output);
+			set_watchdog_in_ms(hdcp, 5000, output);
+			set_state_id(hdcp, output, H1_A8_WAIT_FOR_READY);
+		} else {
+			callback_in_ms(0, output);
+			set_state_id(hdcp, output, H1_A45_AUTHENTICATED);
+			HDCP_FULL_DDC_TRACE(hdcp);
+		}
+		break;
+	case H1_A45_AUTHENTICATED:
+		if (input->link_maintenance != PASS) {
+			/* 1A-07: consider invalid ri' a failure */
+			/* 1A-07a: consider read ri' not returned a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(500, output);
+		increment_stay_counter(hdcp);
+		break;
+	case H1_A8_WAIT_FOR_READY:
+		if (input->ready_check != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1B-03: fail hdcp on ksv list READY timeout */
+				/* prevent black screen in next attempt */
+				adjust->hdcp1.postpone_encryption = 1;
+				fail_and_restart_in_ms(0, &status, output);
+			} else {
+				/* continue ksv list READY polling*/
+				callback_in_ms(500, output);
+				increment_stay_counter(hdcp);
+			}
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H1_A9_READ_KSV_LIST);
+		break;
+	case H1_A9_READ_KSV_LIST:
+		if (input->bstatus_read != PASS ||
+				input->max_cascade_check != PASS ||
+				input->max_devs_check != PASS ||
+				input->device_count_check != PASS ||
+				input->ksvlist_read != PASS ||
+				input->vp_read != PASS ||
+				input->ksvlist_vp_validation != PASS ||
+				input->encryption != PASS) {
+			/* 1B-06: consider MAX_CASCADE_EXCEEDED a failure */
+			/* 1B-05: consider MAX_DEVS_EXCEEDED a failure */
+			/* 1B-04: consider invalid v' a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, H1_A45_AUTHENTICATED);
+		HDCP_FULL_DDC_TRACE(hdcp);
+		break;
+	default:
+		status = MOD_HDCP_STATUS_INVALID_STATE;
+		fail_and_restart_in_ms(0, &status, output);
+		break;
+	}
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_dp_transition(struct mod_hdcp *hdcp,
+		struct mod_hdcp_event_context *event_ctx,
+		struct mod_hdcp_transition_input_hdcp1 *input,
+		struct mod_hdcp_output *output)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_SUCCESS;
+	struct mod_hdcp_connection *conn = &hdcp->connection;
+	struct mod_hdcp_link_adjustment *adjust = &hdcp->connection.link.adjust;
+
+	switch (current_state(hdcp)) {
+	case D1_A0_DETERMINE_RX_HDCP_CAPABLE:
+		if (input->bcaps_read != PASS) {
+			/* 1A-04: no authentication on bcaps read failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->hdcp_capable_dp != PASS) {
+			adjust->hdcp1.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D1_A1_EXCHANGE_KSVS);
+		break;
+	case D1_A1_EXCHANGE_KSVS:
+		if (input->add_topology != PASS ||
+				input->create_session != PASS) {
+			/* out of sync with psp state */
+			adjust->hdcp1.disable = 1;
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->an_write != PASS ||
+				input->aksv_write != PASS ||
+				input->bksv_read != PASS ||
+				input->bksv_validation != PASS ||
+				input->ainfo_write == FAIL) {
+			/* 1A-05: consider invalid bksv a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_watchdog_in_ms(hdcp, 100, output);
+		set_state_id(hdcp, output, D1_A23_WAIT_FOR_R0_PRIME);
+		break;
+	case D1_A23_WAIT_FOR_R0_PRIME:
+		if (input->bstatus_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->r0p_available_dp != PASS) {
+			if (event_ctx->event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT)
+				fail_and_restart_in_ms(0, &status, output);
+			else
+				increment_stay_counter(hdcp);
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D1_A2_COMPUTATIONS_A3_VALIDATE_RX_A5_TEST_FOR_REPEATER);
+		break;
+	case D1_A2_COMPUTATIONS_A3_VALIDATE_RX_A5_TEST_FOR_REPEATER:
+		if (input->r0p_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->rx_validation != PASS) {
+			if (hdcp->state.stay_count < 2) {
+				/* allow 2 additional retries */
+				callback_in_ms(0, output);
+				increment_stay_counter(hdcp);
+			} else {
+				/*
+				 * 1A-06: consider invalid r0' a failure
+				 * after 3 attempts.
+				 * 1A-08: consider bksv listed in SRM a failure
+				 */
+				fail_and_restart_in_ms(0, &status, output);
+			}
+			break;
+		} else if ((!conn->is_repeater && input->encryption != PASS) ||
+				(!conn->is_repeater && is_dp_mst_hdcp(hdcp) && input->stream_encryption_dp != PASS)) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		if (conn->is_repeater) {
+			set_watchdog_in_ms(hdcp, 5000, output);
+			set_state_id(hdcp, output, D1_A6_WAIT_FOR_READY);
+		} else {
+			set_state_id(hdcp, output, D1_A4_AUTHENTICATED);
+			HDCP_FULL_DDC_TRACE(hdcp);
+		}
+		break;
+	case D1_A4_AUTHENTICATED:
+		if (input->link_integiry_check != PASS ||
+				input->reauth_request_check != PASS) {
+			/* 1A-07: restart hdcp on a link integrity failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		break;
+	case D1_A6_WAIT_FOR_READY:
+		if (input->link_integiry_check == FAIL ||
+				input->reauth_request_check == FAIL) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->ready_check != PASS) {
+			if (event_ctx->event ==
+					MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) {
+				/* 1B-04: fail hdcp on ksv list READY timeout */
+				/* prevent black screen in next attempt */
+				adjust->hdcp1.postpone_encryption = 1;
+				fail_and_restart_in_ms(0, &status, output);
+			} else {
+				increment_stay_counter(hdcp);
+			}
+			break;
+		}
+		callback_in_ms(0, output);
+		set_state_id(hdcp, output, D1_A7_READ_KSV_LIST);
+		break;
+	case D1_A7_READ_KSV_LIST:
+		if (input->binfo_read_dp != PASS ||
+				input->max_cascade_check != PASS ||
+				input->max_devs_check != PASS) {
+			/* 1B-06: consider MAX_DEVS_EXCEEDED a failure */
+			/* 1B-07: consider MAX_CASCADE_EXCEEDED a failure */
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->device_count_check != PASS) {
+			/*
+			 * some slow dongle doesn't update
+			 * device count as soon as downstream is connected.
+			 * give it more time to react.
+			 */
+			adjust->hdcp1.postpone_encryption = 1;
+			fail_and_restart_in_ms(1000, &status, output);
+			break;
+		} else if (input->ksvlist_read != PASS ||
+				input->vp_read != PASS) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		} else if (input->ksvlist_vp_validation != PASS) {
+			if (hdcp->state.stay_count < 2) {
+				/* allow 2 additional retries */
+				callback_in_ms(0, output);
+				increment_stay_counter(hdcp);
+			} else {
+				/*
+				 * 1B-05: consider invalid v' a failure
+				 * after 3 attempts.
+				 */
+				fail_and_restart_in_ms(0, &status, output);
+			}
+			break;
+		} else if (input->encryption != PASS ||
+				(is_dp_mst_hdcp(hdcp) && input->stream_encryption_dp != PASS)) {
+			fail_and_restart_in_ms(0, &status, output);
+			break;
+		}
+		set_state_id(hdcp, output, D1_A4_AUTHENTICATED);
+		HDCP_FULL_DDC_TRACE(hdcp);
+		break;
+	default:
+		fail_and_restart_in_ms(0, &status, output);
+		break;
+	}
+
+	return status;
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
new file mode 100644
index 000000000000..e7baae059b85
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
@@ -0,0 +1,305 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "hdcp.h"
+
+#define MIN(a, b) ((a) < (b) ? (a) : (b))
+#define HDCP_I2C_ADDR 0x3a	/* 0x74 >> 1*/
+#define KSV_READ_SIZE 0xf	/* 0x6803b - 0x6802c */
+#define HDCP_MAX_AUX_TRANSACTION_SIZE 16
+
+enum mod_hdcp_ddc_message_id {
+	MOD_HDCP_MESSAGE_ID_INVALID = -1,
+
+	/* HDCP 1.4 */
+
+	MOD_HDCP_MESSAGE_ID_READ_BKSV = 0,
+	MOD_HDCP_MESSAGE_ID_READ_RI_R0,
+	MOD_HDCP_MESSAGE_ID_WRITE_AKSV,
+	MOD_HDCP_MESSAGE_ID_WRITE_AINFO,
+	MOD_HDCP_MESSAGE_ID_WRITE_AN,
+	MOD_HDCP_MESSAGE_ID_READ_VH_X,
+	MOD_HDCP_MESSAGE_ID_READ_VH_0,
+	MOD_HDCP_MESSAGE_ID_READ_VH_1,
+	MOD_HDCP_MESSAGE_ID_READ_VH_2,
+	MOD_HDCP_MESSAGE_ID_READ_VH_3,
+	MOD_HDCP_MESSAGE_ID_READ_VH_4,
+	MOD_HDCP_MESSAGE_ID_READ_BCAPS,
+	MOD_HDCP_MESSAGE_ID_READ_BSTATUS,
+	MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO,
+	MOD_HDCP_MESSAGE_ID_READ_BINFO,
+
+	MOD_HDCP_MESSAGE_ID_MAX
+};
+
+static const uint8_t hdcp_i2c_offsets[] = {
+	[MOD_HDCP_MESSAGE_ID_READ_BKSV] = 0x0,
+	[MOD_HDCP_MESSAGE_ID_READ_RI_R0] = 0x8,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKSV] = 0x10,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AINFO] = 0x15,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AN] = 0x18,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_X] = 0x20,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_0] = 0x20,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_1] = 0x24,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_2] = 0x28,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_3] = 0x2C,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_4] = 0x30,
+	[MOD_HDCP_MESSAGE_ID_READ_BCAPS] = 0x40,
+	[MOD_HDCP_MESSAGE_ID_READ_BSTATUS] = 0x41,
+	[MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x43,
+	[MOD_HDCP_MESSAGE_ID_READ_BINFO] = 0xFF,
+};
+
+static const uint32_t hdcp_dpcd_addrs[] = {
+	[MOD_HDCP_MESSAGE_ID_READ_BKSV] = 0x68000,
+	[MOD_HDCP_MESSAGE_ID_READ_RI_R0] = 0x68005,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AKSV] = 0x68007,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AINFO] = 0x6803B,
+	[MOD_HDCP_MESSAGE_ID_WRITE_AN] = 0x6800c,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_X] = 0x68014,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_0] = 0x68014,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_1] = 0x68018,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_2] = 0x6801c,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_3] = 0x68020,
+	[MOD_HDCP_MESSAGE_ID_READ_VH_4] = 0x68024,
+	[MOD_HDCP_MESSAGE_ID_READ_BCAPS] = 0x68028,
+	[MOD_HDCP_MESSAGE_ID_READ_BSTATUS] = 0x68029,
+	[MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO] = 0x6802c,
+	[MOD_HDCP_MESSAGE_ID_READ_BINFO] = 0x6802a,
+};
+
+static enum mod_hdcp_status read(struct mod_hdcp *hdcp,
+		enum mod_hdcp_ddc_message_id msg_id,
+		uint8_t *buf,
+		uint32_t buf_len)
+{
+	bool success = true;
+	uint32_t cur_size = 0;
+	uint32_t data_offset = 0;
+
+	if (is_dp_hdcp(hdcp)) {
+		while (buf_len > 0) {
+			cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE);
+			success = hdcp->config.ddc.funcs.read_dpcd(hdcp->config.ddc.handle,
+					hdcp_dpcd_addrs[msg_id] + data_offset,
+					buf + data_offset,
+					cur_size);
+
+			if (!success)
+				break;
+
+			buf_len -= cur_size;
+			data_offset += cur_size;
+		}
+	} else {
+		success = hdcp->config.ddc.funcs.read_i2c(
+				hdcp->config.ddc.handle,
+				HDCP_I2C_ADDR,
+				hdcp_i2c_offsets[msg_id],
+				buf,
+				(uint32_t)buf_len);
+	}
+
+	return success ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_DDC_FAILURE;
+}
+
+static enum mod_hdcp_status read_repeatedly(struct mod_hdcp *hdcp,
+		enum mod_hdcp_ddc_message_id msg_id,
+		uint8_t *buf,
+		uint32_t buf_len,
+		uint8_t read_size)
+{
+	enum mod_hdcp_status status = MOD_HDCP_STATUS_DDC_FAILURE;
+	uint32_t cur_size = 0;
+	uint32_t data_offset = 0;
+
+	while (buf_len > 0) {
+		cur_size = MIN(buf_len, read_size);
+		status = read(hdcp, msg_id, buf + data_offset, cur_size);
+
+		if (status != MOD_HDCP_STATUS_SUCCESS)
+			break;
+
+		buf_len -= cur_size;
+		data_offset += cur_size;
+	}
+
+	return status;
+}
+
+static enum mod_hdcp_status write(struct mod_hdcp *hdcp,
+		enum mod_hdcp_ddc_message_id msg_id,
+		uint8_t *buf,
+		uint32_t buf_len)
+{
+	bool success = true;
+	uint32_t cur_size = 0;
+	uint32_t data_offset = 0;
+
+	if (is_dp_hdcp(hdcp)) {
+		while (buf_len > 0) {
+			cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE);
+			success = hdcp->config.ddc.funcs.write_dpcd(
+					hdcp->config.ddc.handle,
+					hdcp_dpcd_addrs[msg_id] + data_offset,
+					buf + data_offset,
+					cur_size);
+
+			if (!success)
+				break;
+
+			buf_len -= cur_size;
+			data_offset += cur_size;
+		}
+	} else {
+		hdcp->buf[0] = hdcp_i2c_offsets[msg_id];
+		memmove(&hdcp->buf[1], buf, buf_len);
+		success = hdcp->config.ddc.funcs.write_i2c(
+				hdcp->config.ddc.handle,
+				HDCP_I2C_ADDR,
+				hdcp->buf,
+				(uint32_t)(buf_len+1));
+	}
+
+	return success ? MOD_HDCP_STATUS_SUCCESS : MOD_HDCP_STATUS_DDC_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_read_bksv(struct mod_hdcp *hdcp)
+{
+	return read(hdcp, MOD_HDCP_MESSAGE_ID_READ_BKSV,
+			hdcp->auth.msg.hdcp1.bksv,
+			sizeof(hdcp->auth.msg.hdcp1.bksv));
+}
+
+enum mod_hdcp_status mod_hdcp_read_bcaps(struct mod_hdcp *hdcp)
+{
+	return read(hdcp, MOD_HDCP_MESSAGE_ID_READ_BCAPS,
+			&hdcp->auth.msg.hdcp1.bcaps,
+			sizeof(hdcp->auth.msg.hdcp1.bcaps));
+}
+
+enum mod_hdcp_status mod_hdcp_read_bstatus(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_BSTATUS,
+					(uint8_t *)&hdcp->auth.msg.hdcp1.bstatus,
+					1);
+	else
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_BSTATUS,
+				(uint8_t *)&hdcp->auth.msg.hdcp1.bstatus,
+				sizeof(hdcp->auth.msg.hdcp1.bstatus));
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_r0p(struct mod_hdcp *hdcp)
+{
+	return read(hdcp, MOD_HDCP_MESSAGE_ID_READ_RI_R0,
+			(uint8_t *)&hdcp->auth.msg.hdcp1.r0p,
+			sizeof(hdcp->auth.msg.hdcp1.r0p));
+}
+
+/* special case, reading repeatedly at the same address, don't use read() */
+enum mod_hdcp_status mod_hdcp_read_ksvlist(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = read_repeatedly(hdcp, MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO,
+				hdcp->auth.msg.hdcp1.ksvlist,
+				hdcp->auth.msg.hdcp1.ksvlist_size,
+				KSV_READ_SIZE);
+	else
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_KSV_FIFO,
+				(uint8_t *)&hdcp->auth.msg.hdcp1.ksvlist,
+				hdcp->auth.msg.hdcp1.ksvlist_size);
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_vp(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_VH_0,
+			&hdcp->auth.msg.hdcp1.vp[0], 4);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_VH_1,
+			&hdcp->auth.msg.hdcp1.vp[4], 4);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_VH_2,
+			&hdcp->auth.msg.hdcp1.vp[8], 4);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_VH_3,
+			&hdcp->auth.msg.hdcp1.vp[12], 4);
+	if (status != MOD_HDCP_STATUS_SUCCESS)
+		goto out;
+
+	status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_VH_4,
+			&hdcp->auth.msg.hdcp1.vp[16], 4);
+out:
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_read_binfo(struct mod_hdcp *hdcp)
+{
+	enum mod_hdcp_status status;
+
+	if (is_dp_hdcp(hdcp))
+		status = read(hdcp, MOD_HDCP_MESSAGE_ID_READ_BINFO,
+				(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp,
+				sizeof(hdcp->auth.msg.hdcp1.binfo_dp));
+	else
+		status = MOD_HDCP_STATUS_INVALID_OPERATION;
+
+	return status;
+}
+
+enum mod_hdcp_status mod_hdcp_write_aksv(struct mod_hdcp *hdcp)
+{
+	return write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AKSV,
+			hdcp->auth.msg.hdcp1.aksv,
+			sizeof(hdcp->auth.msg.hdcp1.aksv));
+}
+
+enum mod_hdcp_status mod_hdcp_write_ainfo(struct mod_hdcp *hdcp)
+{
+	return write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AINFO,
+			&hdcp->auth.msg.hdcp1.ainfo,
+			sizeof(hdcp->auth.msg.hdcp1.ainfo));
+}
+
+enum mod_hdcp_status mod_hdcp_write_an(struct mod_hdcp *hdcp)
+{
+	return write(hdcp, MOD_HDCP_MESSAGE_ID_WRITE_AN,
+			hdcp->auth.msg.hdcp1.an,
+			sizeof(hdcp->auth.msg.hdcp1.an));
+}
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
new file mode 100644
index 000000000000..3982ced5f969
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.c
@@ -0,0 +1,163 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+
+#include "hdcp.h"
+
+void mod_hdcp_dump_binary_message(uint8_t *msg, uint32_t msg_size,
+		uint8_t *buf, uint32_t buf_size)
+{
+	const uint8_t bytes_per_line = 16,
+			byte_size = 3,
+			newline_size = 1,
+			terminator_size = 1;
+	uint32_t line_count = msg_size / bytes_per_line,
+			trailing_bytes = msg_size % bytes_per_line;
+	uint32_t target_size = (byte_size * bytes_per_line + newline_size) * line_count +
+			byte_size * trailing_bytes + newline_size + terminator_size;
+	uint32_t buf_pos = 0;
+	uint32_t i = 0;
+
+	if (buf_size >= target_size) {
+		for (i = 0; i < msg_size; i++) {
+			if (i % bytes_per_line == 0)
+				buf[buf_pos++] = '\n';
+			sprintf(&buf[buf_pos], "%02X ", msg[i]);
+			buf_pos += byte_size;
+		}
+		buf[buf_pos++] = '\0';
+	}
+}
+
+char *mod_hdcp_status_to_str(int32_t status)
+{
+	switch (status) {
+	case MOD_HDCP_STATUS_SUCCESS:
+		return "MOD_HDCP_STATUS_SUCCESS";
+	case MOD_HDCP_STATUS_FAILURE:
+		return "MOD_HDCP_STATUS_FAILURE";
+	case MOD_HDCP_STATUS_RESET_NEEDED:
+		return "MOD_HDCP_STATUS_RESET_NEEDED";
+	case MOD_HDCP_STATUS_DISPLAY_OUT_OF_BOUND:
+		return "MOD_HDCP_STATUS_DISPLAY_OUT_OF_BOUND";
+	case MOD_HDCP_STATUS_DISPLAY_NOT_FOUND:
+		return "MOD_HDCP_STATUS_DISPLAY_NOT_FOUND";
+	case MOD_HDCP_STATUS_INVALID_STATE:
+		return "MOD_HDCP_STATUS_INVALID_STATE";
+	case MOD_HDCP_STATUS_NOT_IMPLEMENTED:
+		return "MOD_HDCP_STATUS_NOT_IMPLEMENTED";
+	case MOD_HDCP_STATUS_INTERNAL_POLICY_FAILURE:
+		return "MOD_HDCP_STATUS_INTERNAL_POLICY_FAILURE";
+	case MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE:
+		return "MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE";
+	case MOD_HDCP_STATUS_CREATE_PSP_SERVICE_FAILURE:
+		return "MOD_HDCP_STATUS_CREATE_PSP_SERVICE_FAILURE";
+	case MOD_HDCP_STATUS_DESTROY_PSP_SERVICE_FAILURE:
+		return "MOD_HDCP_STATUS_DESTROY_PSP_SERVICE_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_DESTROY_SESSION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_DESTROY_SESSION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_VALIDATE_ENCRYPTION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_VALIDATE_ENCRYPTION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_NOT_HDCP_REPEATER:
+		return "MOD_HDCP_STATUS_HDCP1_NOT_HDCP_REPEATER";
+	case MOD_HDCP_STATUS_HDCP1_NOT_CAPABLE:
+		return "MOD_HDCP_STATUS_HDCP1_NOT_CAPABLE";
+	case MOD_HDCP_STATUS_HDCP1_R0_PRIME_PENDING:
+		return "MOD_HDCP_STATUS_HDCP1_R0_PRIME_PENDING";
+	case MOD_HDCP_STATUS_HDCP1_VALIDATE_RX_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_VALIDATE_RX_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY:
+		return "MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY";
+	case MOD_HDCP_STATUS_HDCP1_VALIDATE_KSV_LIST_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_VALIDATE_KSV_LIST_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_ENABLE_ENCRYPTION:
+		return "MOD_HDCP_STATUS_HDCP1_ENABLE_ENCRYPTION";
+	case MOD_HDCP_STATUS_HDCP1_ENABLE_STREAM_ENCRYPTION_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_ENABLE_STREAM_ENCRYPTION_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_LINK_INTEGRITY_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_LINK_INTEGRITY_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_REAUTH_REQUEST_ISSUED:
+		return "MOD_HDCP_STATUS_HDCP1_REAUTH_REQUEST_ISSUED";
+	case MOD_HDCP_STATUS_HDCP1_LINK_MAINTENANCE_FAILURE:
+		return "MOD_HDCP_STATUS_HDCP1_LINK_MAINTENANCE_FAILURE";
+	case MOD_HDCP_STATUS_HDCP1_INVALID_BKSV:
+		return "MOD_HDCP_STATUS_HDCP1_INVALID_BKSV";
+	case MOD_HDCP_STATUS_DDC_FAILURE:
+		return "MOD_HDCP_STATUS_DDC_FAILURE";
+	case MOD_HDCP_STATUS_INVALID_OPERATION:
+		return "MOD_HDCP_STATUS_INVALID_OPERATION";
+	default:
+		return "MOD_HDCP_STATUS_UNKNOWN";
+	}
+}
+
+char *mod_hdcp_state_id_to_str(int32_t id)
+{
+	switch (id) {
+	case HDCP_UNINITIALIZED:
+		return "HDCP_UNINITIALIZED";
+	case HDCP_INITIALIZED:
+		return "HDCP_INITIALIZED";
+	case HDCP_CP_NOT_DESIRED:
+		return "HDCP_CP_NOT_DESIRED";
+	case H1_A0_WAIT_FOR_ACTIVE_RX:
+		return "H1_A0_WAIT_FOR_ACTIVE_RX";
+	case H1_A1_EXCHANGE_KSVS:
+		return "H1_A1_EXCHANGE_KSVS";
+	case H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER:
+		return "H1_A2_COMPUTATIONS_A3_VALIDATE_RX_A6_TEST_FOR_REPEATER";
+	case H1_A45_AUTHENTICATED:
+		return "H1_A45_AUTHENTICATED";
+	case H1_A8_WAIT_FOR_READY:
+		return "H1_A8_WAIT_FOR_READY";
+	case H1_A9_READ_KSV_LIST:
+		return "H1_A9_READ_KSV_LIST";
+	case D1_A0_DETERMINE_RX_HDCP_CAPABLE:
+		return "D1_A0_DETERMINE_RX_HDCP_CAPABLE";
+	case D1_A1_EXCHANGE_KSVS:
+		return "D1_A1_EXCHANGE_KSVS";
+	case D1_A23_WAIT_FOR_R0_PRIME:
+		return "D1_A23_WAIT_FOR_R0_PRIME";
+	case D1_A2_COMPUTATIONS_A3_VALIDATE_RX_A5_TEST_FOR_REPEATER:
+		return "D1_A2_COMPUTATIONS_A3_VALIDATE_RX_A5_TEST_FOR_REPEATER";
+	case D1_A4_AUTHENTICATED:
+		return "D1_A4_AUTHENTICATED";
+	case D1_A6_WAIT_FOR_READY:
+		return "D1_A6_WAIT_FOR_READY";
+	case D1_A7_READ_KSV_LIST:
+		return "D1_A7_READ_KSV_LIST";
+	default:
+		return "UNKNOWN_STATE_ID";
+	};
+}
+
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
new file mode 100644
index 000000000000..2fd0e0a893ef
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_log.h
@@ -0,0 +1,139 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef MOD_HDCP_LOG_H_
+#define MOD_HDCP_LOG_H_
+
+#ifdef CONFIG_DRM_AMD_DC_HDCP
+#define HDCP_LOG_ERR(hdcp, ...) DRM_ERROR(__VA_ARGS__)
+#define HDCP_LOG_VER(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define HDCP_LOG_FSM(hdcp, ...) DRM_DEBUG_KMS(__VA_ARGS__)
+#define HDCP_LOG_TOP(hdcp, ...) pr_debug("[HDCP_TOP]:"__VA_ARGS__)
+#define HDCP_LOG_DDC(hdcp, ...) pr_debug("[HDCP_DDC]:"__VA_ARGS__)
+#endif
+
+/* default logs */
+#define HDCP_ERROR_TRACE(hdcp, status) \
+		HDCP_LOG_ERR(hdcp, \
+			"[Link %d] ERROR %s IN STATE %s", \
+			hdcp->config.index, \
+			mod_hdcp_status_to_str(status), \
+			mod_hdcp_state_id_to_str(hdcp->state.id))
+#define HDCP_HDCP1_ENABLED_TRACE(hdcp, displayIndex) \
+		HDCP_LOG_VER(hdcp, \
+			"[Link %d] HDCP 1.4 enabled on display %d", \
+			hdcp->config.index, displayIndex)
+/* state machine logs */
+#define HDCP_REMOVE_DISPLAY_TRACE(hdcp, displayIndex) \
+		HDCP_LOG_FSM(hdcp, \
+			"[Link %d] HDCP_REMOVE_DISPLAY index %d", \
+			hdcp->config.index, displayIndex)
+#define HDCP_INPUT_PASS_TRACE(hdcp, str) \
+		HDCP_LOG_FSM(hdcp, \
+			"[Link %d]\tPASS %s", \
+			hdcp->config.index, str)
+#define HDCP_INPUT_FAIL_TRACE(hdcp, str) \
+		HDCP_LOG_FSM(hdcp, \
+			"[Link %d]\tFAIL %s", \
+			hdcp->config.index, str)
+#define HDCP_NEXT_STATE_TRACE(hdcp, id, output) do { \
+		if (output->watchdog_timer_needed) \
+			HDCP_LOG_FSM(hdcp, \
+				"[Link %d] > %s with %d ms watchdog", \
+				hdcp->config.index, \
+				mod_hdcp_state_id_to_str(id), output->watchdog_timer_delay); \
+		else \
+			HDCP_LOG_FSM(hdcp, \
+				"[Link %d] > %s", hdcp->config.index, \
+				mod_hdcp_state_id_to_str(id)); \
+} while (0)
+#define HDCP_TIMEOUT_TRACE(hdcp) \
+		HDCP_LOG_FSM(hdcp, "[Link %d] --> TIMEOUT", hdcp->config.index)
+#define HDCP_CPIRQ_TRACE(hdcp) \
+		HDCP_LOG_FSM(hdcp, "[Link %d] --> CPIRQ", hdcp->config.index)
+#define HDCP_EVENT_TRACE(hdcp, event) \
+		if (event == MOD_HDCP_EVENT_WATCHDOG_TIMEOUT) \
+			HDCP_TIMEOUT_TRACE(hdcp); \
+		else if (event == MOD_HDCP_EVENT_CPIRQ) \
+			HDCP_CPIRQ_TRACE(hdcp)
+/* TODO: find some way to tell if logging is off to save time */
+#define HDCP_DDC_READ_TRACE(hdcp, msg_name, msg, msg_size) do { \
+		mod_hdcp_dump_binary_message(msg, msg_size, hdcp->buf, \
+				sizeof(hdcp->buf)); \
+		HDCP_LOG_DDC(hdcp, "[Link %d] Read %s%s", hdcp->config.index, \
+				msg_name, hdcp->buf); \
+} while (0)
+#define HDCP_DDC_WRITE_TRACE(hdcp, msg_name, msg, msg_size) do { \
+		mod_hdcp_dump_binary_message(msg, msg_size, hdcp->buf, \
+				sizeof(hdcp->buf)); \
+		HDCP_LOG_DDC(hdcp, "[Link %d] Write %s%s", \
+				hdcp->config.index, msg_name,\
+				hdcp->buf); \
+} while (0)
+#define HDCP_FULL_DDC_TRACE(hdcp) do { \
+	HDCP_DDC_READ_TRACE(hdcp, "BKSV", hdcp->auth.msg.hdcp1.bksv, \
+			sizeof(hdcp->auth.msg.hdcp1.bksv)); \
+	HDCP_DDC_READ_TRACE(hdcp, "BCAPS", &hdcp->auth.msg.hdcp1.bcaps, \
+			sizeof(hdcp->auth.msg.hdcp1.bcaps)); \
+	HDCP_DDC_WRITE_TRACE(hdcp, "AN", hdcp->auth.msg.hdcp1.an, \
+			sizeof(hdcp->auth.msg.hdcp1.an)); \
+	HDCP_DDC_WRITE_TRACE(hdcp, "AKSV", hdcp->auth.msg.hdcp1.aksv, \
+			sizeof(hdcp->auth.msg.hdcp1.aksv)); \
+	HDCP_DDC_WRITE_TRACE(hdcp, "AINFO", &hdcp->auth.msg.hdcp1.ainfo, \
+			sizeof(hdcp->auth.msg.hdcp1.ainfo)); \
+	HDCP_DDC_READ_TRACE(hdcp, "RI' / R0'", \
+			(uint8_t *)&hdcp->auth.msg.hdcp1.r0p, \
+			sizeof(hdcp->auth.msg.hdcp1.r0p)); \
+	HDCP_DDC_READ_TRACE(hdcp, "BINFO", \
+			(uint8_t *)&hdcp->auth.msg.hdcp1.binfo_dp, \
+			sizeof(hdcp->auth.msg.hdcp1.binfo_dp)); \
+	HDCP_DDC_READ_TRACE(hdcp, "KSVLIST", hdcp->auth.msg.hdcp1.ksvlist, \
+			hdcp->auth.msg.hdcp1.ksvlist_size); \
+	HDCP_DDC_READ_TRACE(hdcp, "V'", hdcp->auth.msg.hdcp1.vp, \
+			sizeof(hdcp->auth.msg.hdcp1.vp)); \
+} while (0)
+#define HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, i) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\tadd display %d", \
+				hdcp->config.index, i)
+#define HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, i) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\tremove display %d", \
+				hdcp->config.index, i)
+#define HDCP_TOP_HDCP1_DESTROY_SESSION_TRACE(hdcp) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\tdestroy hdcp1 session", \
+				hdcp->config.index)
+#define HDCP_TOP_RESET_AUTH_TRACE(hdcp) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\treset authentication", hdcp->config.index)
+#define HDCP_TOP_RESET_CONN_TRACE(hdcp) \
+		HDCP_LOG_TOP(hdcp, "[Link %d]\treset connection", hdcp->config.index)
+#define HDCP_TOP_INTERFACE_TRACE(hdcp) do { \
+		HDCP_LOG_TOP(hdcp, "\n"); \
+		HDCP_LOG_TOP(hdcp, "[Link %d] %s", hdcp->config.index, __func__); \
+} while (0)
+#define HDCP_TOP_INTERFACE_TRACE_WITH_INDEX(hdcp, i) do { \
+		HDCP_LOG_TOP(hdcp, "\n"); \
+		HDCP_LOG_TOP(hdcp, "[Link %d] %s display %d", hdcp->config.index, __func__, i); \
+} while (0)
+
+#endif // MOD_HDCP_LOG_H_
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
new file mode 100644
index 000000000000..646d909bbc37
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.c
@@ -0,0 +1,328 @@
+/*
+ * 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
+ *
+ */
+
+#define MAX_NUM_DISPLAYS 24
+
+
+#include "hdcp.h"
+
+#include "amdgpu.h"
+#include "hdcp_psp.h"
+
+enum mod_hdcp_status mod_hdcp_remove_display_topology(struct mod_hdcp *hdcp)
+{
+
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_dtm_shared_memory *dtm_cmd;
+	struct mod_hdcp_display *display = NULL;
+	uint8_t i;
+
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state == MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED) {
+
+			memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
+
+			display = &hdcp->connection.displays[i];
+
+			dtm_cmd->cmd_id = TA_DTM_COMMAND__TOPOLOGY_UPDATE_V2;
+			dtm_cmd->dtm_in_message.topology_update_v2.display_handle = display->index;
+			dtm_cmd->dtm_in_message.topology_update_v2.is_active = 0;
+			dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE;
+
+			psp_dtm_invoke(psp, dtm_cmd->cmd_id);
+
+			if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS)
+				return MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE;
+
+			display->state = MOD_HDCP_DISPLAY_ACTIVE;
+			HDCP_TOP_REMOVE_DISPLAY_TRACE(hdcp, display->index);
+		}
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_add_display_topology(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_dtm_shared_memory *dtm_cmd;
+	struct mod_hdcp_display *display = NULL;
+	struct mod_hdcp_link *link = &hdcp->connection.link;
+	uint8_t i;
+
+	if (!psp->dtm_context.dtm_initialized) {
+		DRM_ERROR("Failed to add display topology, DTM TA is not initialized.");
+		return MOD_HDCP_STATUS_FAILURE;
+	}
+
+	dtm_cmd = (struct ta_dtm_shared_memory *)psp->dtm_context.dtm_shared_buf;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+		if (hdcp->connection.displays[i].state == MOD_HDCP_DISPLAY_ACTIVE) {
+			display = &hdcp->connection.displays[i];
+
+			memset(dtm_cmd, 0, sizeof(struct ta_dtm_shared_memory));
+
+			dtm_cmd->cmd_id = TA_DTM_COMMAND__TOPOLOGY_UPDATE_V2;
+			dtm_cmd->dtm_in_message.topology_update_v2.display_handle = display->index;
+			dtm_cmd->dtm_in_message.topology_update_v2.is_active = 1;
+			dtm_cmd->dtm_in_message.topology_update_v2.controller = display->controller;
+			dtm_cmd->dtm_in_message.topology_update_v2.ddc_line = link->ddc_line;
+			dtm_cmd->dtm_in_message.topology_update_v2.dig_be = link->dig_be;
+			dtm_cmd->dtm_in_message.topology_update_v2.dig_fe = display->dig_fe;
+			dtm_cmd->dtm_in_message.topology_update_v2.dp_mst_vcid = display->vc_id;
+			dtm_cmd->dtm_in_message.topology_update_v2.max_hdcp_supported_version =
+				TA_DTM_HDCP_VERSION_MAX_SUPPORTED__1_x;
+			dtm_cmd->dtm_status = TA_DTM_STATUS__GENERIC_FAILURE;
+
+			psp_dtm_invoke(psp, dtm_cmd->cmd_id);
+
+			if (dtm_cmd->dtm_status != TA_DTM_STATUS__SUCCESS)
+				return MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE;
+
+			display->state = MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED;
+			HDCP_TOP_ADD_DISPLAY_TRACE(hdcp, display->index);
+		}
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_create_session(struct mod_hdcp *hdcp)
+{
+
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct mod_hdcp_display *display = get_first_added_display(hdcp);
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	if (!psp->hdcp_context.hdcp_initialized) {
+		DRM_ERROR("Failed to create hdcp session. HDCP TA is not initialized.");
+		return MOD_HDCP_STATUS_FAILURE;
+	}
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp1_create_session.display_handle = display->index;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_CREATE_SESSION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE;
+
+	hdcp->auth.id = hdcp_cmd->out_msg.hdcp1_create_session.session_handle;
+	hdcp->auth.msg.hdcp1.ainfo = hdcp_cmd->out_msg.hdcp1_create_session.ainfo_primary;
+	memcpy(hdcp->auth.msg.hdcp1.aksv, hdcp_cmd->out_msg.hdcp1_create_session.aksv_primary,
+		sizeof(hdcp->auth.msg.hdcp1.aksv));
+	memcpy(hdcp->auth.msg.hdcp1.an, hdcp_cmd->out_msg.hdcp1_create_session.an_primary,
+		sizeof(hdcp->auth.msg.hdcp1.an));
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_destroy_session(struct mod_hdcp *hdcp)
+{
+
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp1_destroy_session.session_handle = hdcp->auth.id;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_DESTROY_SESSION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP1_DESTROY_SESSION_FAILURE;
+
+	HDCP_TOP_HDCP1_DESTROY_SESSION_TRACE(hdcp);
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_validate_rx(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp1_first_part_authentication.session_handle = hdcp->auth.id;
+
+	memcpy(hdcp_cmd->in_msg.hdcp1_first_part_authentication.bksv_primary, hdcp->auth.msg.hdcp1.bksv,
+		TA_HDCP__HDCP1_KSV_SIZE);
+
+	hdcp_cmd->in_msg.hdcp1_first_part_authentication.r0_prime_primary = hdcp->auth.msg.hdcp1.r0p;
+	hdcp_cmd->in_msg.hdcp1_first_part_authentication.bcaps = hdcp->auth.msg.hdcp1.bcaps;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_FIRST_PART_AUTHENTICATION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP1_VALIDATE_RX_FAILURE;
+
+	if (hdcp_cmd->out_msg.hdcp1_first_part_authentication.authentication_status ==
+	    TA_HDCP_AUTHENTICATION_STATUS__HDCP1_FIRST_PART_COMPLETE) {
+		/* needs second part of authentication */
+		hdcp->connection.is_repeater = 1;
+	} else if (hdcp_cmd->out_msg.hdcp1_first_part_authentication.authentication_status ==
+		   TA_HDCP_AUTHENTICATION_STATUS__HDCP1_AUTHENTICATED) {
+		hdcp->connection.is_repeater = 0;
+	} else
+		return MOD_HDCP_STATUS_HDCP1_VALIDATE_RX_FAILURE;
+
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_enable_encryption(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	struct mod_hdcp_display *display = get_first_added_display(hdcp);
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp1_enable_encryption.session_handle = hdcp->auth.id;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_ENABLE_ENCRYPTION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP1_ENABLE_ENCRYPTION;
+
+	if (!is_dp_mst_hdcp(hdcp)) {
+		display->state = MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+		HDCP_HDCP1_ENABLED_TRACE(hdcp, display->index);
+	}
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_validate_ksvlist_vp(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp1_second_part_authentication.session_handle = hdcp->auth.id;
+
+	hdcp_cmd->in_msg.hdcp1_second_part_authentication.ksv_list_size = hdcp->auth.msg.hdcp1.ksvlist_size;
+	memcpy(hdcp_cmd->in_msg.hdcp1_second_part_authentication.ksv_list, hdcp->auth.msg.hdcp1.ksvlist,
+	       hdcp->auth.msg.hdcp1.ksvlist_size);
+
+	memcpy(hdcp_cmd->in_msg.hdcp1_second_part_authentication.v_prime, hdcp->auth.msg.hdcp1.vp,
+	       sizeof(hdcp->auth.msg.hdcp1.vp));
+
+	hdcp_cmd->in_msg.hdcp1_second_part_authentication.bstatus_binfo =
+		is_dp_hdcp(hdcp) ? hdcp->auth.msg.hdcp1.binfo_dp : hdcp->auth.msg.hdcp1.bstatus;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_SECOND_PART_AUTHENTICATION;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP1_VALIDATE_KSV_LIST_FAILURE;
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_enable_dp_stream_encryption(struct mod_hdcp *hdcp)
+{
+
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+	int i = 0;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+
+	for (i = 0; i < MAX_NUM_OF_DISPLAYS; i++) {
+
+		if (hdcp->connection.displays[i].state != MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED ||
+		    hdcp->connection.displays[i].adjust.disable)
+			continue;
+
+		memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+		hdcp_cmd->in_msg.hdcp1_enable_dp_stream_encryption.session_handle = hdcp->auth.id;
+		hdcp_cmd->in_msg.hdcp1_enable_dp_stream_encryption.display_handle = hdcp->connection.displays[i].index;
+		hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_ENABLE_DP_STREAM_ENCRYPTION;
+
+		psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+		if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+			return MOD_HDCP_STATUS_HDCP1_ENABLE_STREAM_ENCRYPTION_FAILURE;
+
+		hdcp->connection.displays[i].state = MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED;
+		HDCP_HDCP1_ENABLED_TRACE(hdcp, hdcp->connection.displays[i].index);
+	}
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_link_maintenance(struct mod_hdcp *hdcp)
+{
+	struct psp_context *psp = hdcp->config.psp.handle;
+	struct ta_hdcp_shared_memory *hdcp_cmd;
+
+	hdcp_cmd = (struct ta_hdcp_shared_memory *)psp->hdcp_context.hdcp_shared_buf;
+
+	memset(hdcp_cmd, 0, sizeof(struct ta_hdcp_shared_memory));
+
+	hdcp_cmd->in_msg.hdcp1_get_encryption_status.session_handle = hdcp->auth.id;
+
+	hdcp_cmd->out_msg.hdcp1_get_encryption_status.protection_level = 0;
+	hdcp_cmd->cmd_id = TA_HDCP_COMMAND__HDCP1_GET_ENCRYPTION_STATUS;
+
+	psp_hdcp_invoke(psp, hdcp_cmd->cmd_id);
+
+	if (hdcp_cmd->hdcp_status != TA_HDCP_STATUS__SUCCESS)
+		return MOD_HDCP_STATUS_HDCP1_LINK_MAINTENANCE_FAILURE;
+
+	return (hdcp_cmd->out_msg.hdcp1_get_encryption_status.protection_level == 1)
+		       ? MOD_HDCP_STATUS_SUCCESS
+		       : MOD_HDCP_STATUS_HDCP1_LINK_MAINTENANCE_FAILURE;
+}
+
+enum mod_hdcp_status mod_hdcp_hdcp1_get_link_encryption_status(struct mod_hdcp *hdcp,
+							       enum mod_hdcp_encryption_status *encryption_status)
+{
+	*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF;
+
+	if (mod_hdcp_hdcp1_link_maintenance(hdcp) != MOD_HDCP_STATUS_SUCCESS)
+		return MOD_HDCP_STATUS_FAILURE;
+
+	*encryption_status = MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON;
+
+	return MOD_HDCP_STATUS_SUCCESS;
+}
+
diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
new file mode 100644
index 000000000000..986fc07ea9ea
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_psp.h
@@ -0,0 +1,272 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef MODULES_HDCP_HDCP_PSP_H_
+#define MODULES_HDCP_HDCP_PSP_H_
+
+/*
+ * NOTE: These parameters are a one-to-one copy of the
+ * parameters required by PSP
+ */
+enum bgd_security_hdcp_encryption_level {
+	HDCP_ENCRYPTION_LEVEL__INVALID = 0,
+	HDCP_ENCRYPTION_LEVEL__OFF,
+	HDCP_ENCRYPTION_LEVEL__ON
+};
+
+enum ta_dtm_command {
+	TA_DTM_COMMAND__UNUSED_1 = 1,
+	TA_DTM_COMMAND__TOPOLOGY_UPDATE_V2,
+	TA_DTM_COMMAND__TOPOLOGY_ASSR_ENABLE
+};
+
+/* DTM related enumerations */
+/**********************************************************/
+
+enum ta_dtm_status {
+	TA_DTM_STATUS__SUCCESS = 0x00,
+	TA_DTM_STATUS__GENERIC_FAILURE = 0x01,
+	TA_DTM_STATUS__INVALID_PARAMETER = 0x02,
+	TA_DTM_STATUS__NULL_POINTER = 0x3
+};
+
+/* input/output structures for DTM commands */
+/**********************************************************/
+/**
+ * Input structures
+ */
+enum ta_dtm_hdcp_version_max_supported {
+	TA_DTM_HDCP_VERSION_MAX_SUPPORTED__NONE = 0,
+	TA_DTM_HDCP_VERSION_MAX_SUPPORTED__1_x = 10,
+	TA_DTM_HDCP_VERSION_MAX_SUPPORTED__2_0 = 20,
+	TA_DTM_HDCP_VERSION_MAX_SUPPORTED__2_1 = 21,
+	TA_DTM_HDCP_VERSION_MAX_SUPPORTED__2_2 = 22,
+	TA_DTM_HDCP_VERSION_MAX_SUPPORTED__2_3 = 23
+};
+
+struct ta_dtm_topology_update_input_v2 {
+	/* display handle is unique across the driver and is used to identify a display */
+	/* for all security interfaces which reference displays such as HDCP */
+	uint32_t display_handle;
+	uint32_t is_active;
+	uint32_t is_miracast;
+	uint32_t controller;
+	uint32_t ddc_line;
+	uint32_t dig_be;
+	uint32_t dig_fe;
+	uint32_t dp_mst_vcid;
+	uint32_t is_assr;
+	uint32_t max_hdcp_supported_version;
+};
+
+struct ta_dtm_topology_assr_enable {
+	uint32_t display_topology_dig_be_index;
+};
+
+/**
+ * Output structures
+ */
+
+/* No output structures yet */
+
+union ta_dtm_cmd_input {
+	struct ta_dtm_topology_update_input_v2 topology_update_v2;
+	struct ta_dtm_topology_assr_enable topology_assr_enable;
+};
+
+union ta_dtm_cmd_output {
+	uint32_t reserved;
+};
+
+struct ta_dtm_shared_memory {
+	uint32_t cmd_id;
+	uint32_t resp_id;
+	enum ta_dtm_status dtm_status;
+	uint32_t reserved;
+	union ta_dtm_cmd_input dtm_in_message;
+	union ta_dtm_cmd_output dtm_out_message;
+};
+
+int psp_cmd_submit_buf(struct psp_context *psp, struct amdgpu_firmware_info *ucode, struct psp_gfx_cmd_resp *cmd,
+		uint64_t fence_mc_addr);
+
+enum ta_hdcp_command {
+	TA_HDCP_COMMAND__INITIALIZE,
+	TA_HDCP_COMMAND__HDCP1_CREATE_SESSION,
+	TA_HDCP_COMMAND__HDCP1_DESTROY_SESSION,
+	TA_HDCP_COMMAND__HDCP1_FIRST_PART_AUTHENTICATION,
+	TA_HDCP_COMMAND__HDCP1_SECOND_PART_AUTHENTICATION,
+	TA_HDCP_COMMAND__HDCP1_ENABLE_ENCRYPTION,
+	TA_HDCP_COMMAND__HDCP1_ENABLE_DP_STREAM_ENCRYPTION,
+	TA_HDCP_COMMAND__HDCP1_GET_ENCRYPTION_STATUS,
+};
+
+
+/* HDCP related enumerations */
+/**********************************************************/
+#define TA_HDCP__INVALID_SESSION 0xFFFF
+#define TA_HDCP__HDCP1_AN_SIZE 8
+#define TA_HDCP__HDCP1_KSV_SIZE 5
+#define TA_HDCP__HDCP1_KSV_LIST_MAX_ENTRIES 127
+#define TA_HDCP__HDCP1_V_PRIME_SIZE 20
+
+enum ta_hdcp_status {
+	TA_HDCP_STATUS__SUCCESS = 0x00,
+	TA_HDCP_STATUS__GENERIC_FAILURE = 0x01,
+	TA_HDCP_STATUS__NULL_POINTER = 0x02,
+	TA_HDCP_STATUS__FAILED_ALLOCATING_SESSION = 0x03,
+	TA_HDCP_STATUS__FAILED_SETUP_TX = 0x04,
+	TA_HDCP_STATUS__INVALID_PARAMETER = 0x05,
+	TA_HDCP_STATUS__VHX_ERROR = 0x06,
+	TA_HDCP_STATUS__SESSION_NOT_CLOSED_PROPERLY = 0x07,
+	TA_HDCP_STATUS__SRM_FAILURE = 0x08,
+	TA_HDCP_STATUS__MST_AUTHENTICATED_ALREADY_STARTED = 0x09,
+	TA_HDCP_STATUS__AKE_SEND_CERT_FAILURE = 0x0A,
+	TA_HDCP_STATUS__AKE_NO_STORED_KM_FAILURE = 0x0B,
+	TA_HDCP_STATUS__AKE_SEND_HPRIME_FAILURE = 0x0C,
+	TA_HDCP_STATUS__LC_SEND_LPRIME_FAILURE = 0x0D,
+	TA_HDCP_STATUS__SKE_SEND_EKS_FAILURE = 0x0E,
+	TA_HDCP_STATUS__REPAUTH_SEND_RXIDLIST_FAILURE = 0x0F,
+	TA_HDCP_STATUS__REPAUTH_STREAM_READY_FAILURE = 0x10,
+	TA_HDCP_STATUS__ASD_GENERIC_FAILURE = 0x11,
+	TA_HDCP_STATUS__UNWRAP_SECRET_FAILURE = 0x12,
+	TA_HDCP_STATUS__ENABLE_ENCR_FAILURE = 0x13,
+	TA_HDCP_STATUS__DISABLE_ENCR_FAILURE = 0x14,
+	TA_HDCP_STATUS__NOT_ENOUGH_MEMORY_FAILURE = 0x15,
+	TA_HDCP_STATUS__UNKNOWN_MESSAGE = 0x16,
+	TA_HDCP_STATUS__TOO_MANY_STREAM = 0x17
+};
+
+enum ta_hdcp_authentication_status {
+	TA_HDCP_AUTHENTICATION_STATUS__NOT_STARTED = 0x00,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_FIRST_PART_FAILED = 0x01,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_FIRST_PART_COMPLETE = 0x02,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_SECOND_PART_FAILED = 0x03,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_AUTHENTICATED = 0x04,
+	TA_HDCP_AUTHENTICATION_STATUS__HDCP1_KSV_VALIDATION_FAILED = 0x09
+};
+
+
+/* input/output structures for HDCP commands */
+/**********************************************************/
+struct ta_hdcp_cmd_hdcp1_create_session_input {
+	uint8_t display_handle;
+};
+
+struct ta_hdcp_cmd_hdcp1_create_session_output {
+	uint32_t session_handle;
+	uint8_t an_primary[TA_HDCP__HDCP1_AN_SIZE];
+	uint8_t aksv_primary[TA_HDCP__HDCP1_KSV_SIZE];
+	uint8_t ainfo_primary;
+	uint8_t an_secondary[TA_HDCP__HDCP1_AN_SIZE];
+	uint8_t aksv_secondary[TA_HDCP__HDCP1_KSV_SIZE];
+	uint8_t ainfo_secondary;
+};
+
+struct ta_hdcp_cmd_hdcp1_destroy_session_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp1_first_part_authentication_input {
+	uint32_t session_handle;
+	uint8_t bksv_primary[TA_HDCP__HDCP1_KSV_SIZE];
+	uint8_t bksv_secondary[TA_HDCP__HDCP1_KSV_SIZE];
+	uint8_t bcaps;
+	uint16_t r0_prime_primary;
+	uint16_t r0_prime_secondary;
+};
+
+struct ta_hdcp_cmd_hdcp1_first_part_authentication_output {
+	enum ta_hdcp_authentication_status authentication_status;
+};
+
+struct ta_hdcp_cmd_hdcp1_second_part_authentication_input {
+	uint32_t session_handle;
+	uint16_t bstatus_binfo;
+	uint8_t ksv_list[TA_HDCP__HDCP1_KSV_LIST_MAX_ENTRIES][TA_HDCP__HDCP1_KSV_SIZE];
+	uint32_t ksv_list_size;
+	uint8_t pj_prime;
+	uint8_t v_prime[TA_HDCP__HDCP1_V_PRIME_SIZE];
+};
+
+struct ta_hdcp_cmd_hdcp1_second_part_authentication_output {
+	enum ta_hdcp_authentication_status authentication_status;
+};
+
+struct ta_hdcp_cmd_hdcp1_enable_encryption_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp1_enable_dp_stream_encryption_input {
+	uint32_t session_handle;
+	uint32_t display_handle;
+};
+
+struct ta_hdcp_cmd_hdcp1_get_encryption_status_input {
+	uint32_t session_handle;
+};
+
+struct ta_hdcp_cmd_hdcp1_get_encryption_status_output {
+	uint32_t protection_level;
+};
+
+/**********************************************************/
+/* Common input structure for HDCP callbacks */
+union ta_hdcp_cmd_input {
+	struct ta_hdcp_cmd_hdcp1_create_session_input hdcp1_create_session;
+	struct ta_hdcp_cmd_hdcp1_destroy_session_input hdcp1_destroy_session;
+	struct ta_hdcp_cmd_hdcp1_first_part_authentication_input hdcp1_first_part_authentication;
+	struct ta_hdcp_cmd_hdcp1_second_part_authentication_input hdcp1_second_part_authentication;
+	struct ta_hdcp_cmd_hdcp1_enable_encryption_input hdcp1_enable_encryption;
+	struct ta_hdcp_cmd_hdcp1_enable_dp_stream_encryption_input hdcp1_enable_dp_stream_encryption;
+	struct ta_hdcp_cmd_hdcp1_get_encryption_status_input hdcp1_get_encryption_status;
+};
+
+/* Common output structure for HDCP callbacks */
+union ta_hdcp_cmd_output {
+	struct ta_hdcp_cmd_hdcp1_create_session_output hdcp1_create_session;
+	struct ta_hdcp_cmd_hdcp1_first_part_authentication_output hdcp1_first_part_authentication;
+	struct ta_hdcp_cmd_hdcp1_second_part_authentication_output hdcp1_second_part_authentication;
+	struct ta_hdcp_cmd_hdcp1_get_encryption_status_output hdcp1_get_encryption_status;
+};
+/**********************************************************/
+
+struct ta_hdcp_shared_memory {
+	uint32_t cmd_id;
+	enum ta_hdcp_status hdcp_status;
+	uint32_t reserved;
+	union ta_hdcp_cmd_input in_msg;
+	union ta_hdcp_cmd_output out_msg;
+};
+
+enum psp_status {
+	PSP_STATUS__SUCCESS = 0,
+	PSP_STATUS__ERROR_INVALID_PARAMS,
+	PSP_STATUS__ERROR_GENERIC,
+	PSP_STATUS__ERROR_OUT_OF_MEMORY,
+	PSP_STATUS__ERROR_UNSUPPORTED_FEATURE
+};
+
+#endif /* MODULES_HDCP_HDCP_PSP_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
index dc187844d10b..dbe7835aabcf 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_freesync.h
@@ -92,6 +92,7 @@ struct mod_vrr_params_btr {
 	uint32_t inserted_duration_in_us;
 	uint32_t frames_to_insert;
 	uint32_t frame_counter;
+	uint32_t margin_in_us;
 };
 
 struct mod_vrr_params_fixed_refresh {
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
new file mode 100644
index 000000000000..dea21702edff
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_hdcp.h
@@ -0,0 +1,289 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef MOD_HDCP_H_
+#define MOD_HDCP_H_
+
+#include "os_types.h"
+#include "signal_types.h"
+
+/* Forward Declarations */
+struct mod_hdcp;
+
+#define MAX_NUM_OF_DISPLAYS 6
+#define MAX_NUM_OF_ATTEMPTS 4
+#define MAX_NUM_OF_ERROR_TRACE 10
+
+/* detailed return status */
+enum mod_hdcp_status {
+	MOD_HDCP_STATUS_SUCCESS = 0,
+	MOD_HDCP_STATUS_FAILURE,
+	MOD_HDCP_STATUS_RESET_NEEDED,
+	MOD_HDCP_STATUS_DISPLAY_OUT_OF_BOUND,
+	MOD_HDCP_STATUS_DISPLAY_NOT_FOUND,
+	MOD_HDCP_STATUS_INVALID_STATE,
+	MOD_HDCP_STATUS_NOT_IMPLEMENTED,
+	MOD_HDCP_STATUS_INTERNAL_POLICY_FAILURE,
+	MOD_HDCP_STATUS_UPDATE_TOPOLOGY_FAILURE,
+	MOD_HDCP_STATUS_CREATE_PSP_SERVICE_FAILURE,
+	MOD_HDCP_STATUS_DESTROY_PSP_SERVICE_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_CREATE_SESSION_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_DESTROY_SESSION_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_VALIDATE_ENCRYPTION_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_NOT_HDCP_REPEATER,
+	MOD_HDCP_STATUS_HDCP1_NOT_CAPABLE,
+	MOD_HDCP_STATUS_HDCP1_R0_PRIME_PENDING,
+	MOD_HDCP_STATUS_HDCP1_VALIDATE_RX_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_KSV_LIST_NOT_READY,
+	MOD_HDCP_STATUS_HDCP1_VALIDATE_KSV_LIST_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_ENABLE_ENCRYPTION,
+	MOD_HDCP_STATUS_HDCP1_ENABLE_STREAM_ENCRYPTION_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_MAX_CASCADE_EXCEEDED_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_MAX_DEVS_EXCEEDED_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_DEVICE_COUNT_MISMATCH_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_LINK_INTEGRITY_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_REAUTH_REQUEST_ISSUED,
+	MOD_HDCP_STATUS_HDCP1_LINK_MAINTENANCE_FAILURE,
+	MOD_HDCP_STATUS_HDCP1_INVALID_BKSV,
+	MOD_HDCP_STATUS_DDC_FAILURE, /* TODO: specific errors */
+	MOD_HDCP_STATUS_INVALID_OPERATION,
+	MOD_HDCP_STATUS_HDCP2_NOT_CAPABLE,
+	MOD_HDCP_STATUS_HDCP2_CREATE_SESSION_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_DESTROY_SESSION_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_PREP_AKE_INIT_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_AKE_CERT_PENDING,
+	MOD_HDCP_STATUS_HDCP2_H_PRIME_PENDING,
+	MOD_HDCP_STATUS_HDCP2_PAIRING_INFO_PENDING,
+	MOD_HDCP_STATUS_HDCP2_VALIDATE_AKE_CERT_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_VALIDATE_H_PRIME_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_VALIDATE_PAIRING_INFO_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_PREP_LC_INIT_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_L_PRIME_PENDING,
+	MOD_HDCP_STATUS_HDCP2_VALIDATE_L_PRIME_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_PREP_EKS_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_ENABLE_ENCRYPTION_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_RX_ID_LIST_NOT_READY,
+	MOD_HDCP_STATUS_HDCP2_VALIDATE_RX_ID_LIST_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_ENABLE_STREAM_ENCRYPTION,
+	MOD_HDCP_STATUS_HDCP2_STREAM_READY_PENDING,
+	MOD_HDCP_STATUS_HDCP2_VALIDATE_STREAM_READY_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_PREPARE_STREAM_MANAGEMENT_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_REAUTH_REQUEST,
+	MOD_HDCP_STATUS_HDCP2_REAUTH_LINK_INTEGRITY_FAILURE,
+	MOD_HDCP_STATUS_HDCP2_DEVICE_COUNT_MISMATCH_FAILURE,
+};
+
+struct mod_hdcp_displayport {
+	uint8_t rev;
+	uint8_t assr_supported;
+};
+
+struct mod_hdcp_hdmi {
+	uint8_t reserved;
+};
+enum mod_hdcp_operation_mode {
+	MOD_HDCP_MODE_OFF,
+	MOD_HDCP_MODE_DEFAULT,
+	MOD_HDCP_MODE_DP,
+	MOD_HDCP_MODE_DP_MST
+};
+
+enum mod_hdcp_display_state {
+	MOD_HDCP_DISPLAY_INACTIVE = 0,
+	MOD_HDCP_DISPLAY_ACTIVE,
+	MOD_HDCP_DISPLAY_ACTIVE_AND_ADDED,
+	MOD_HDCP_DISPLAY_ENCRYPTION_ENABLED
+};
+
+struct mod_hdcp_ddc {
+	void *handle;
+	struct {
+		bool (*read_i2c)(void *handle,
+				uint32_t address,
+				uint8_t offset,
+				uint8_t *data,
+				uint32_t size);
+		bool (*write_i2c)(void *handle,
+				uint32_t address,
+				const uint8_t *data,
+				uint32_t size);
+		bool (*read_dpcd)(void *handle,
+				uint32_t address,
+				uint8_t *data,
+				uint32_t size);
+		bool (*write_dpcd)(void *handle,
+				uint32_t address,
+				const uint8_t *data,
+				uint32_t size);
+	} funcs;
+};
+
+struct mod_hdcp_psp {
+	void *handle;
+	void *funcs;
+};
+
+struct mod_hdcp_display_adjustment {
+	uint8_t disable			: 1;
+	uint8_t reserved		: 7;
+};
+
+struct mod_hdcp_link_adjustment_hdcp1 {
+	uint8_t disable			: 1;
+	uint8_t postpone_encryption	: 1;
+	uint8_t reserved		: 6;
+};
+
+struct mod_hdcp_link_adjustment_hdcp2 {
+	uint8_t disable			: 1;
+	uint8_t disable_type1		: 1;
+	uint8_t force_no_stored_km	: 1;
+	uint8_t increase_h_prime_timeout: 1;
+	uint8_t reserved		: 4;
+};
+
+struct mod_hdcp_link_adjustment {
+	uint8_t auth_delay;
+	struct mod_hdcp_link_adjustment_hdcp1 hdcp1;
+	struct mod_hdcp_link_adjustment_hdcp2 hdcp2;
+};
+
+struct mod_hdcp_error {
+	enum mod_hdcp_status status;
+	uint8_t state_id;
+};
+
+struct mod_hdcp_trace {
+	struct mod_hdcp_error errors[MAX_NUM_OF_ERROR_TRACE];
+	uint8_t error_count;
+};
+
+enum mod_hdcp_encryption_status {
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP_OFF = 0,
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP1_ON,
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE0_ON,
+	MOD_HDCP_ENCRYPTION_STATUS_HDCP2_TYPE1_ON
+};
+
+/* per link events dm has to notify to hdcp module */
+enum mod_hdcp_event {
+	MOD_HDCP_EVENT_CALLBACK = 0,
+	MOD_HDCP_EVENT_WATCHDOG_TIMEOUT,
+	MOD_HDCP_EVENT_CPIRQ
+};
+
+/* output flags from module requesting timer operations */
+struct mod_hdcp_output {
+	uint8_t callback_needed;
+	uint8_t callback_stop;
+	uint8_t watchdog_timer_needed;
+	uint8_t watchdog_timer_stop;
+	uint16_t callback_delay;
+	uint16_t watchdog_timer_delay;
+};
+
+/* used to represent per display info */
+struct mod_hdcp_display {
+	enum mod_hdcp_display_state state;
+	uint8_t index;
+	uint8_t controller;
+	uint8_t dig_fe;
+	union {
+		uint8_t vc_id;
+	};
+	struct mod_hdcp_display_adjustment adjust;
+};
+
+/* used to represent per link info */
+/* in case a link has multiple displays, they share the same link info */
+struct mod_hdcp_link {
+	enum mod_hdcp_operation_mode mode;
+	uint8_t dig_be;
+	uint8_t ddc_line;
+	union {
+		struct mod_hdcp_displayport dp;
+		struct mod_hdcp_hdmi hdmi;
+	};
+	struct mod_hdcp_link_adjustment adjust;
+};
+
+/* a query structure for a display's hdcp information */
+struct mod_hdcp_display_query {
+	const struct mod_hdcp_display *display;
+	const struct mod_hdcp_link *link;
+	const struct mod_hdcp_trace *trace;
+	enum mod_hdcp_encryption_status encryption_status;
+};
+
+/* contains values per on external display configuration change */
+struct mod_hdcp_config {
+	struct mod_hdcp_psp psp;
+	struct mod_hdcp_ddc ddc;
+	uint8_t index;
+};
+
+struct mod_hdcp;
+
+/* dm allocates memory of mod_hdcp per dc_link on dm init based on memory size*/
+size_t mod_hdcp_get_memory_size(void);
+
+/* called per link on link creation */
+enum mod_hdcp_status mod_hdcp_setup(struct mod_hdcp *hdcp,
+		struct mod_hdcp_config *config);
+
+/* called per link on link destroy */
+enum mod_hdcp_status mod_hdcp_teardown(struct mod_hdcp *hdcp);
+
+/* called per display on cp_desired set to true */
+enum mod_hdcp_status mod_hdcp_add_display(struct mod_hdcp *hdcp,
+		struct mod_hdcp_link *link, struct mod_hdcp_display *display,
+		struct mod_hdcp_output *output);
+
+/* called per display on cp_desired set to false */
+enum mod_hdcp_status mod_hdcp_remove_display(struct mod_hdcp *hdcp,
+		uint8_t index, struct mod_hdcp_output *output);
+
+/* called to query hdcp information on a specific index */
+enum mod_hdcp_status mod_hdcp_query_display(struct mod_hdcp *hdcp,
+		uint8_t index, struct mod_hdcp_display_query *query);
+
+/* called per link on connectivity change */
+enum mod_hdcp_status mod_hdcp_reset_connection(struct mod_hdcp *hdcp,
+		struct mod_hdcp_output *output);
+
+/* called per link on events (i.e. callback, watchdog, CP_IRQ) */
+enum mod_hdcp_status mod_hdcp_process_event(struct mod_hdcp *hdcp,
+		enum mod_hdcp_event event, struct mod_hdcp_output *output);
+
+/* called to convert enum mod_hdcp_status to c string */
+char *mod_hdcp_status_to_str(int32_t status);
+
+/* called to convert state id to c string */
+char *mod_hdcp_state_id_to_str(int32_t id);
+
+/* called to convert signal type to operation mode */
+enum mod_hdcp_operation_mode mod_hdcp_signal_type_to_operation_mode(
+		enum signal_type signal);
+#endif /* MOD_HDCP_H_ */
diff --git a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
index d930bdecb117..ca8ce3c55337 100644
--- a/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
+++ b/drivers/gpu/drm/amd/display/modules/inc/mod_info_packet.h
@@ -35,4 +35,7 @@ struct mod_vrr_params;
 void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 		struct dc_info_packet *info_packet);
 
+void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
+		struct dc_info_packet *info_packet, int ALLMEnabled, int ALLMValue);
+
 #endif
diff --git a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
index d885d642ed7f..db6b08f6d093 100644
--- a/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
+++ b/drivers/gpu/drm/amd/display/modules/info_packet/info_packet.c
@@ -31,6 +31,7 @@
 #include "dc.h"
 
 #define HDMI_INFOFRAME_TYPE_VENDOR 0x81
+#define HF_VSIF_VERSION 1
 
 // VTEM Byte Offset
 #define VTEM_PB0		0
@@ -395,3 +396,100 @@ void mod_build_vsc_infopacket(const struct dc_stream_state *stream,
 
 }
 
+/**
+ *****************************************************************************
+ *  Function: mod_build_hf_vsif_infopacket
+ *
+ *  @brief
+ *     Prepare HDMI Vendor Specific info frame.
+ *     Follows HDMI Spec to build up Vendor Specific info frame
+ *
+ *  @param [in] stream: contains data we may need to construct VSIF (i.e. timing_3d_format, etc.)
+ *  @param [out] info_packet:   output structure where to store VSIF
+ *****************************************************************************
+ */
+void mod_build_hf_vsif_infopacket(const struct dc_stream_state *stream,
+		struct dc_info_packet *info_packet, int ALLMEnabled, int ALLMValue)
+{
+		unsigned int length = 5;
+		bool hdmi_vic_mode = false;
+		uint8_t checksum = 0;
+		uint32_t i = 0;
+		enum dc_timing_3d_format format;
+		bool bALLM = (bool)ALLMEnabled;
+		bool bALLMVal = (bool)ALLMValue;
+
+		info_packet->valid = false;
+		format = stream->timing.timing_3d_format;
+		if (stream->view_format == VIEW_3D_FORMAT_NONE)
+			format = TIMING_3D_FORMAT_NONE;
+
+		if (stream->timing.hdmi_vic != 0
+				&& stream->timing.h_total >= 3840
+				&& stream->timing.v_total >= 2160
+				&& format == TIMING_3D_FORMAT_NONE)
+			hdmi_vic_mode = true;
+
+		if ((format == TIMING_3D_FORMAT_NONE) && !hdmi_vic_mode && !bALLM)
+			return;
+
+		info_packet->sb[1] = 0x03;
+		info_packet->sb[2] = 0x0C;
+		info_packet->sb[3] = 0x00;
+
+		if (bALLM) {
+			info_packet->sb[1] = 0xD8;
+			info_packet->sb[2] = 0x5D;
+			info_packet->sb[3] = 0xC4;
+			info_packet->sb[4] = HF_VSIF_VERSION;
+		}
+
+		if (format != TIMING_3D_FORMAT_NONE)
+			info_packet->sb[4] = (2 << 5);
+
+		else if (hdmi_vic_mode)
+			info_packet->sb[4] = (1 << 5);
+
+		switch (format) {
+		case TIMING_3D_FORMAT_HW_FRAME_PACKING:
+		case TIMING_3D_FORMAT_SW_FRAME_PACKING:
+			info_packet->sb[5] = (0x0 << 4);
+			break;
+
+		case TIMING_3D_FORMAT_SIDE_BY_SIDE:
+		case TIMING_3D_FORMAT_SBS_SW_PACKED:
+			info_packet->sb[5] = (0x8 << 4);
+			length = 6;
+			break;
+
+		case TIMING_3D_FORMAT_TOP_AND_BOTTOM:
+		case TIMING_3D_FORMAT_TB_SW_PACKED:
+			info_packet->sb[5] = (0x6 << 4);
+			break;
+
+		default:
+			break;
+		}
+
+		if (hdmi_vic_mode)
+			info_packet->sb[5] = stream->timing.hdmi_vic;
+
+		info_packet->hb0 = HDMI_INFOFRAME_TYPE_VENDOR;
+		info_packet->hb1 = 0x01;
+		info_packet->hb2 = (uint8_t) (length);
+
+		if (bALLM)
+			info_packet->sb[5] = (info_packet->sb[5] & ~0x02) | (bALLMVal << 1);
+
+		checksum += info_packet->hb0;
+		checksum += info_packet->hb1;
+		checksum += info_packet->hb2;
+
+		for (i = 1; i <= length; i++)
+			checksum += info_packet->sb[i];
+
+		info_packet->sb[0] = (uint8_t) (0x100 - checksum);
+
+		info_packet->valid = true;
+}
+
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
index 05e2be856037..4e2f615c3566 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c
@@ -80,18 +80,18 @@ struct abm_parameters {
 
 static const struct abm_parameters abm_settings_config0[abm_defines_max_level] = {
 //  min_red  max_red  bright_pos  dark_pos  brightness_gain  contrast  deviation  min_knee  max_knee
-	{0xff,   0xbf,    0x20,       0x00,     0xff,            0x99,     0xb3,      0x40,     0xE0},
-	{0xff,   0x85,    0x20,       0x00,     0xff,            0x90,     0xa8,      0x40,     0xE0},
-	{0xff,   0x40,    0x20,       0x00,     0xff,            0x90,     0x68,      0x40,     0xE0},
-	{0x82,   0x4d,    0x20,       0x00,     0x00,            0x90,     0xb3,      0x70,     0x70},
+	{0xff,   0xbf,    0x20,       0x00,     0xff,            0x99,     0xb3,      0x40,     0xe0},
+	{0xde,   0x85,    0x20,       0x00,     0xff,            0x90,     0xa8,      0x40,     0xdf},
+	{0xb0,   0x50,    0x20,       0x00,     0xc0,            0x88,     0x78,      0x70,     0xa0},
+	{0x82,   0x40,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
 };
 
 static const struct abm_parameters abm_settings_config1[abm_defines_max_level] = {
 //  min_red  max_red  bright_pos  dark_pos  brightness_gain  contrast  deviation  min_knee  max_knee
-	{0xf0,   0xd9,    0x20,       0x00,     0x00,            0xa8,     0xb3,      0x70,     0x70},
-	{0xcd,   0xa5,    0x20,       0x00,     0x00,            0xa8,     0xb3,      0x70,     0x70},
-	{0x99,   0x65,    0x20,       0x00,     0x00,            0xa8,     0xb3,      0x70,     0x70},
-	{0x82,   0x4d,    0x20,       0x00,     0x00,            0xa8,     0xb3,      0x70,     0x70},
+	{0xf0,   0xd9,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
+	{0xcd,   0xa5,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
+	{0x99,   0x65,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
+	{0x82,   0x4d,    0x20,       0x00,     0x00,            0xff,     0xb3,      0x70,     0x70},
 };
 
 static const struct abm_parameters * const abm_settings[] = {
@@ -115,7 +115,7 @@ static const struct abm_parameters * const abm_settings[] = {
 /* NOTE: iRAM is 256B in size */
 struct iram_table_v_2 {
 	/* flags                      */
-	uint16_t flags;							/* 0x00 U16  */
+	uint16_t min_abm_backlight;					/* 0x00 U16  */
 
 	/* parameters for ABM2.0 algorithm */
 	uint8_t min_reduction[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];		/* 0x02 U0.8 */
@@ -140,10 +140,10 @@ struct iram_table_v_2 {
 
 	/* For reading PSR State directly from IRAM */
 	uint8_t psr_state;						/* 0xf0       */
-	uint8_t dmcu_mcp_interface_version;							/* 0xf1       */
-	uint8_t dmcu_abm_feature_version;							/* 0xf2       */
-	uint8_t dmcu_psr_feature_version;							/* 0xf3       */
-	uint16_t dmcu_version;										/* 0xf4       */
+	uint8_t dmcu_mcp_interface_version;				/* 0xf1       */
+	uint8_t dmcu_abm_feature_version;				/* 0xf2       */
+	uint8_t dmcu_psr_feature_version;				/* 0xf3       */
+	uint16_t dmcu_version;						/* 0xf4       */
 	uint8_t dmcu_state;						/* 0xf6       */
 
 	uint16_t blRampReduction;					/* 0xf7       */
@@ -164,42 +164,43 @@ struct iram_table_v_2_2 {
 	uint8_t max_reduction[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];		/* 0x16 U0.8 */
 	uint8_t bright_pos_gain[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];	/* 0x2a U2.6 */
 	uint8_t dark_pos_gain[NUM_AMBI_LEVEL][NUM_AGGR_LEVEL];		/* 0x3e U2.6 */
-	uint8_t hybrid_factor[NUM_AGGR_LEVEL];						/* 0x52 U0.8 */
-	uint8_t contrast_factor[NUM_AGGR_LEVEL];					/* 0x56 U0.8 */
-	uint8_t deviation_gain[NUM_AGGR_LEVEL];						/* 0x5a U0.8 */
-	uint8_t iir_curve[NUM_AMBI_LEVEL];							/* 0x5e U0.8 */
-	uint8_t min_knee[NUM_AGGR_LEVEL];							/* 0x63 U0.8 */
-	uint8_t max_knee[NUM_AGGR_LEVEL];							/* 0x67 U0.8 */
-	uint8_t pad[21];											/* 0x6b U0.8 */
+	uint8_t hybrid_factor[NUM_AGGR_LEVEL];				/* 0x52 U0.8 */
+	uint8_t contrast_factor[NUM_AGGR_LEVEL];			/* 0x56 U0.8 */
+	uint8_t deviation_gain[NUM_AGGR_LEVEL];				/* 0x5a U0.8 */
+	uint8_t iir_curve[NUM_AMBI_LEVEL];				/* 0x5e U0.8 */
+	uint8_t min_knee[NUM_AGGR_LEVEL];				/* 0x63 U0.8 */
+	uint8_t max_knee[NUM_AGGR_LEVEL];				/* 0x67 U0.8 */
+	uint16_t min_abm_backlight;					/* 0x6b U16  */
+	uint8_t pad[19];						/* 0x6d U0.8 */
 
 	/* parameters for crgb conversion */
-	uint16_t crgb_thresh[NUM_POWER_FN_SEGS];					/* 0x80 U3.13 */
-	uint16_t crgb_offset[NUM_POWER_FN_SEGS];					/* 0x90 U1.15 */
-	uint16_t crgb_slope[NUM_POWER_FN_SEGS];						/* 0xa0 U4.12 */
+	uint16_t crgb_thresh[NUM_POWER_FN_SEGS];			/* 0x80 U3.13 */
+	uint16_t crgb_offset[NUM_POWER_FN_SEGS];			/* 0x90 U1.15 */
+	uint16_t crgb_slope[NUM_POWER_FN_SEGS];				/* 0xa0 U4.12 */
 
 	/* parameters for custom curve */
 	/* thresholds for brightness --> backlight */
-	uint16_t backlight_thresholds[NUM_BL_CURVE_SEGS];			/* 0xb0 U16.0 */
+	uint16_t backlight_thresholds[NUM_BL_CURVE_SEGS];		/* 0xb0 U16.0 */
 	/* offsets for brightness --> backlight */
-	uint16_t backlight_offsets[NUM_BL_CURVE_SEGS];				/* 0xd0 U16.0 */
+	uint16_t backlight_offsets[NUM_BL_CURVE_SEGS];			/* 0xd0 U16.0 */
 
 	/* For reading PSR State directly from IRAM */
-	uint8_t psr_state;											/* 0xf0       */
-	uint8_t dmcu_mcp_interface_version;							/* 0xf1       */
-	uint8_t dmcu_abm_feature_version;							/* 0xf2       */
-	uint8_t dmcu_psr_feature_version;							/* 0xf3       */
-	uint16_t dmcu_version;										/* 0xf4       */
-	uint8_t dmcu_state;											/* 0xf6       */
-
-	uint8_t dummy1;												/* 0xf7       */
-	uint8_t dummy2;												/* 0xf8       */
-	uint8_t dummy3;												/* 0xf9       */
-	uint8_t dummy4;												/* 0xfa       */
-	uint8_t dummy5;												/* 0xfb       */
-	uint8_t dummy6;												/* 0xfc       */
-	uint8_t dummy7;												/* 0xfd       */
-	uint8_t dummy8;												/* 0xfe       */
-	uint8_t dummy9;												/* 0xff       */
+	uint8_t psr_state;						/* 0xf0       */
+	uint8_t dmcu_mcp_interface_version;				/* 0xf1       */
+	uint8_t dmcu_abm_feature_version;				/* 0xf2       */
+	uint8_t dmcu_psr_feature_version;				/* 0xf3       */
+	uint16_t dmcu_version;						/* 0xf4       */
+	uint8_t dmcu_state;						/* 0xf6       */
+
+	uint8_t dummy1;							/* 0xf7       */
+	uint8_t dummy2;							/* 0xf8       */
+	uint8_t dummy3;							/* 0xf9       */
+	uint8_t dummy4;							/* 0xfa       */
+	uint8_t dummy5;							/* 0xfb       */
+	uint8_t dummy6;							/* 0xfc       */
+	uint8_t dummy7;							/* 0xfd       */
+	uint8_t dummy8;							/* 0xfe       */
+	uint8_t dummy9;							/* 0xff       */
 };
 #pragma pack(pop)
 
@@ -271,7 +272,8 @@ void fill_iram_v_2(struct iram_table_v_2 *ram_table, struct dmcu_iram_parameters
 {
 	unsigned int set = params.set;
 
-	ram_table->flags = 0x0;
+	ram_table->min_abm_backlight =
+			cpu_to_be16(params.min_abm_backlight);
 	ram_table->deviation_gain = 0xb3;
 
 	ram_table->blRampReduction =
@@ -445,6 +447,9 @@ void fill_iram_v_2_2(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame
 
 	ram_table->flags = 0x0;
 
+	ram_table->min_abm_backlight =
+			cpu_to_be16(params.min_abm_backlight);
+
 	ram_table->deviation_gain[0] = 0xb3;
 	ram_table->deviation_gain[1] = 0xa8;
 	ram_table->deviation_gain[2] = 0x98;
@@ -588,6 +593,10 @@ void fill_iram_v_2_3(struct iram_table_v_2_2 *ram_table, struct dmcu_iram_parame
 	unsigned int set = params.set;
 
 	ram_table->flags = 0x0;
+
+	ram_table->min_abm_backlight =
+			cpu_to_be16(params.min_abm_backlight);
+
 	for (i = 0; i < NUM_AGGR_LEVEL; i++) {
 		ram_table->hybrid_factor[i] = abm_settings[set][i].brightness_gain;
 		ram_table->contrast_factor[i] = abm_settings[set][i].contrast_factor;
diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
index da5df00fedce..e54157026330 100644
--- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
+++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.h
@@ -38,6 +38,7 @@ struct dmcu_iram_parameters {
 	unsigned int backlight_lut_array_size;
 	unsigned int backlight_ramping_reduction;
 	unsigned int backlight_ramping_start;
+	unsigned int min_abm_backlight;
 	unsigned int set;
 };
 
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index 8889aaceec60..dc7eb28f0296 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -143,6 +143,8 @@ enum PP_FEATURE_MASK {
 enum DC_FEATURE_MASK {
 	DC_FBC_MASK = 0x1,
 	DC_MULTI_MON_PP_MCLK_SWITCH_MASK = 0x2,
+	DC_DISABLE_FRACTIONAL_PWM_MASK = 0x4,
+	DC_PSR_MASK = 0x8,
 };
 
 enum amd_dpm_forced_level;
diff --git a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_d.h b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_d.h
index a761ba07f937..fce965984e76 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_d.h
@@ -27,6 +27,7 @@
 #define mmMM_INDEX                                                              0x0
 #define mmMM_INDEX_HI                                                           0x6
 #define mmMM_DATA                                                               0x1
+#define mmCC_BIF_BX_FUSESTRAP0							0x14D7
 #define mmBUS_CNTL                                                              0x1508
 #define mmCONFIG_CNTL                                                           0x1509
 #define mmCONFIG_MEMSIZE                                                        0x150a
diff --git a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_sh_mask.h
index 8fbfd0261d27..39cc4880beb4 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_4_1_sh_mask.h
@@ -32,6 +32,8 @@
 #define MM_INDEX_HI__MM_OFFSET_HI__SHIFT 0x0
 #define MM_DATA__MM_DATA_MASK 0xffffffff
 #define MM_DATA__MM_DATA__SHIFT 0x0
+#define CC_BIF_BX_FUSESTRAP0__STRAP_BIF_PX_CAPABLE_MASK    0x2
+#define CC_BIF_BX_FUSESTRAP0__STRAP_BIF_PX_CAPABLE__SHIFT  0x1
 #define BUS_CNTL__BIOS_ROM_WRT_EN_MASK 0x1
 #define BUS_CNTL__BIOS_ROM_WRT_EN__SHIFT 0x0
 #define BUS_CNTL__BIOS_ROM_DIS_MASK 0x2
diff --git a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h
index 809759f7bb81..8d05d6ca1c8d 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_d.h
@@ -27,6 +27,7 @@
 #define mmMM_INDEX                                                              0x0
 #define mmMM_INDEX_HI                                                           0x6
 #define mmMM_DATA                                                               0x1
+#define mmCC_BIF_BX_FUSESTRAP0							0x14D7
 #define mmCC_BIF_BX_STRAP2							0x152A
 #define mmBIF_MM_INDACCESS_CNTL                                                 0x1500
 #define mmBIF_DOORBELL_APER_EN                                                  0x1501
diff --git a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_sh_mask.h
index adc71b01f793..73435687d049 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/bif/bif_5_0_sh_mask.h
@@ -32,6 +32,8 @@
 #define MM_INDEX_HI__MM_OFFSET_HI__SHIFT 0x0
 #define MM_DATA__MM_DATA_MASK 0xffffffff
 #define MM_DATA__MM_DATA__SHIFT 0x0
+#define CC_BIF_BX_FUSESTRAP0__STRAP_BIF_PX_CAPABLE_MASK    0x2
+#define CC_BIF_BX_FUSESTRAP0__STRAP_BIF_PX_CAPABLE__SHIFT  0x1
 #define BIF_MM_INDACCESS_CNTL__MM_INDACCESS_DIS_MASK 0x2
 #define BIF_MM_INDACCESS_CNTL__MM_INDACCESS_DIS__SHIFT 0x1
 #define BIF_DOORBELL_APER_EN__BIF_DOORBELL_APER_EN_MASK 0x1
diff --git a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
index be4249adb356..eddf83ec1c39 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/dcn/dcn_2_1_0_offset.h
@@ -9859,6 +9859,8 @@
 #define mmDP0_DP_STEER_FIFO_BASE_IDX                                                                   2
 #define mmDP0_DP_MSA_MISC                                                                              0x210e
 #define mmDP0_DP_MSA_MISC_BASE_IDX                                                                     2
+#define mmDP0_DP_DPHY_INTERNAL_CTRL                                                                    0x210f
+#define mmDP0_DP_DPHY_INTERNAL_CTRL_BASE_IDX                                                           2
 #define mmDP0_DP_VID_TIMING                                                                            0x2110
 #define mmDP0_DP_VID_TIMING_BASE_IDX                                                                   2
 #define mmDP0_DP_VID_N                                                                                 0x2111
@@ -10187,6 +10189,8 @@
 #define mmDP1_DP_STEER_FIFO_BASE_IDX                                                                   2
 #define mmDP1_DP_MSA_MISC                                                                              0x220e
 #define mmDP1_DP_MSA_MISC_BASE_IDX                                                                     2
+#define mmDP1_DP_DPHY_INTERNAL_CTRL                                                                    0x220f
+#define mmDP1_DP_DPHY_INTERNAL_CTRL_BASE_IDX                                                           2
 #define mmDP1_DP_VID_TIMING                                                                            0x2210
 #define mmDP1_DP_VID_TIMING_BASE_IDX                                                                   2
 #define mmDP1_DP_VID_N                                                                                 0x2211
@@ -10515,6 +10519,8 @@
 #define mmDP2_DP_STEER_FIFO_BASE_IDX                                                                   2
 #define mmDP2_DP_MSA_MISC                                                                              0x230e
 #define mmDP2_DP_MSA_MISC_BASE_IDX                                                                     2
+#define mmDP2_DP_DPHY_INTERNAL_CTRL                                                                    0x230f
+#define mmDP2_DP_DPHY_INTERNAL_CTRL_BASE_IDX                                                           2
 #define mmDP2_DP_VID_TIMING                                                                            0x2310
 #define mmDP2_DP_VID_TIMING_BASE_IDX                                                                   2
 #define mmDP2_DP_VID_N                                                                                 0x2311
@@ -10843,6 +10849,8 @@
 #define mmDP3_DP_STEER_FIFO_BASE_IDX                                                                   2
 #define mmDP3_DP_MSA_MISC                                                                              0x240e
 #define mmDP3_DP_MSA_MISC_BASE_IDX                                                                     2
+#define mmDP3_DP_DPHY_INTERNAL_CTRL                                                                    0x240f
+#define mmDP3_DP_DPHY_INTERNAL_CTRL_BASE_IDX                                                           2
 #define mmDP3_DP_VID_TIMING                                                                            0x2410
 #define mmDP3_DP_VID_TIMING_BASE_IDX                                                                   2
 #define mmDP3_DP_VID_N                                                                                 0x2411
@@ -11171,6 +11179,8 @@
 #define mmDP4_DP_STEER_FIFO_BASE_IDX                                                                   2
 #define mmDP4_DP_MSA_MISC                                                                              0x250e
 #define mmDP4_DP_MSA_MISC_BASE_IDX                                                                     2
+#define mmDP4_DP_DPHY_INTERNAL_CTRL                                                                    0x250f
+#define mmDP4_DP_DPHY_INTERNAL_CTRL_BASE_IDX                                                           2
 #define mmDP4_DP_VID_TIMING                                                                            0x2510
 #define mmDP4_DP_VID_TIMING_BASE_IDX                                                                   2
 #define mmDP4_DP_VID_N                                                                                 0x2511
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
index ca16d9125fbc..2bfaaa8157d0 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_offset.h
@@ -1146,7 +1146,14 @@
 #define mmATC_L2_MEM_POWER_LS_BASE_IDX                                                                 0
 #define mmATC_L2_CGTT_CLK_CTRL                                                                         0x080c
 #define mmATC_L2_CGTT_CLK_CTRL_BASE_IDX                                                                0
-
+#define mmATC_L2_CACHE_4K_EDC_INDEX                                                                    0x080e
+#define mmATC_L2_CACHE_4K_EDC_INDEX_BASE_IDX                                                           0
+#define mmATC_L2_CACHE_2M_EDC_INDEX                                                                    0x080f
+#define mmATC_L2_CACHE_2M_EDC_INDEX_BASE_IDX                                                           0
+#define mmATC_L2_CACHE_4K_EDC_CNT                                                                      0x0810
+#define mmATC_L2_CACHE_4K_EDC_CNT_BASE_IDX                                                             0
+#define mmATC_L2_CACHE_2M_EDC_CNT                                                                      0x0811
+#define mmATC_L2_CACHE_2M_EDC_CNT_BASE_IDX                                                             0
 
 // addressBlock: gc_utcl2_vml2pfdec
 // base address: 0xa100
@@ -1206,7 +1213,14 @@
 #define mmVM_L2_CACHE_PARITY_CNTL_BASE_IDX                                                             0
 #define mmVM_L2_CGTT_CLK_CTRL                                                                          0x085e
 #define mmVM_L2_CGTT_CLK_CTRL_BASE_IDX                                                                 0
-
+#define mmVM_L2_MEM_ECC_INDEX                                                                          0x0860
+#define mmVM_L2_MEM_ECC_INDEX_BASE_IDX                                                                 0
+#define mmVM_L2_WALKER_MEM_ECC_INDEX                                                                   0x0861
+#define mmVM_L2_WALKER_MEM_ECC_INDEX_BASE_IDX                                                          0
+#define mmVM_L2_MEM_ECC_CNT                                                                            0x0862
+#define mmVM_L2_MEM_ECC_CNT_BASE_IDX                                                                   0
+#define mmVM_L2_WALKER_MEM_ECC_CNT                                                                     0x0863
+#define mmVM_L2_WALKER_MEM_ECC_CNT_BASE_IDX                                                            0
 
 // addressBlock: gc_utcl2_vml2vcdec
 // base address: 0xa200
diff --git a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
index 064c4bb1dc62..d4c613a85352 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/gc/gc_9_0_sh_mask.h
@@ -6661,7 +6661,6 @@
 #define ATC_L2_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_MASK                                                        0x00FF0000L
 #define ATC_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK                                                              0xFF000000L
 
-
 // addressBlock: gc_utcl2_vml2pfdec
 //VM_L2_CNTL
 #define VM_L2_CNTL__ENABLE_L2_CACHE__SHIFT                                                                    0x0
@@ -6991,7 +6990,22 @@
 #define VM_L2_CGTT_CLK_CTRL__MGLS_OVERRIDE_MASK                                                               0x00008000L
 #define VM_L2_CGTT_CLK_CTRL__SOFT_STALL_OVERRIDE_MASK                                                         0x00FF0000L
 #define VM_L2_CGTT_CLK_CTRL__SOFT_OVERRIDE_MASK                                                               0xFF000000L
-
+//VM_L2_MEM_ECC_INDEX
+#define VM_L2_MEM_ECC_INDEX__INDEX__SHIFT                                                                     0x0
+#define VM_L2_MEM_ECC_INDEX__INDEX_MASK                                                                       0x000000FFL
+//VM_L2_WALKER_MEM_ECC_INDEX
+#define VM_L2_WALKER_MEM_ECC_INDEX__INDEX__SHIFT                                                              0x0
+#define VM_L2_WALKER_MEM_ECC_INDEX__INDEX_MASK                                                                0x000000FFL
+//VM_L2_MEM_ECC_CNT
+#define VM_L2_MEM_ECC_CNT__SEC_COUNT__SHIFT                                                                   0xc
+#define VM_L2_MEM_ECC_CNT__DED_COUNT__SHIFT                                                                   0xe
+#define VM_L2_MEM_ECC_CNT__SEC_COUNT_MASK                                                                     0x00003000L
+#define VM_L2_MEM_ECC_CNT__DED_COUNT_MASK                                                                     0x0000C000L
+//VM_L2_WALKER_MEM_ECC_CNT
+#define VM_L2_WALKER_MEM_ECC_CNT__SEC_COUNT__SHIFT                                                            0xc
+#define VM_L2_WALKER_MEM_ECC_CNT__DED_COUNT__SHIFT                                                            0xe
+#define VM_L2_WALKER_MEM_ECC_CNT__SEC_COUNT_MASK                                                              0x00003000L
+#define VM_L2_WALKER_MEM_ECC_CNT__DED_COUNT_MASK                                                              0x0000C000L
 
 // addressBlock: gc_utcl2_vml2vcdec
 //VM_CONTEXT0_CNTL
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_0_smn.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_0_smn.h
index 4bcacf529852..991128bb9476 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_0_smn.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_0_smn.h
@@ -22,6 +22,9 @@
 #ifndef _nbio_7_4_0_SMN_HEADER
 #define _nbio_7_4_0_SMN_HEADER
 
+// addressBlock: nbio_nbif0_bif_ras_bif_ras_regblk
+// base address: 0x10100000
+#define smnBIFL_RAS_CENTRAL_STATUS			0x10139040
 
 #define smnNBIF_MGCG_CTRL_LCLK				0x1013a21c
 #define smnCPM_CONTROL					0x11180460
@@ -53,4 +56,13 @@
 #define smnPCIE_RX_NUM_NAK				0x11180038
 #define smnPCIE_RX_NUM_NAK_GENERATED			0x1118003c
 
+// addressBlock: nbio_iohub_nb_misc_misc_cfgdec
+// base address: 0x13a10000
+#define smnIOHC_INTERRUPT_EOI				0x13a10120
+
+// addressBlock: nbio_iohub_nb_rascfg_ras_cfgdec
+// base address: 0x13a20000
+#define smnRAS_GLOBAL_STATUS_LO				0x13a20020
+#define smnRAS_GLOBAL_STATUS_HI				0x13a20024
+
 #endif	// _nbio_7_4_0_SMN_HEADER
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_offset.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_offset.h
index 994e796a28d7..ce5830ebe095 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_offset.h
@@ -2793,8 +2793,8 @@
 #define mmBIF_DOORBELL_INT_CNTL_BASE_IDX                                                               2
 #define mmBIF_FB_EN                                                                                    0x00ff
 #define mmBIF_FB_EN_BASE_IDX                                                                           2
-#define mmBIF_BUSY_DELAY_CNTR                                                                          0x0100
-#define mmBIF_BUSY_DELAY_CNTR_BASE_IDX                                                                 2
+#define mmBIF_INTR_CNTL                                                                                0x0100
+#define mmBIF_INTR_CNTL_BASE_IDX                                                                       2
 #define mmBIF_MST_TRANS_PENDING_VF                                                                     0x0109
 #define mmBIF_MST_TRANS_PENDING_VF_BASE_IDX                                                            2
 #define mmBIF_SLV_TRANS_PENDING_VF                                                                     0x010a
diff --git a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_sh_mask.h
index d467b939c971..07f04b2b5bdd 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/nbio/nbio_7_4_sh_mask.h
@@ -20420,9 +20420,9 @@
 #define BIF_FB_EN__FB_WRITE_EN__SHIFT                                                                         0x1
 #define BIF_FB_EN__FB_READ_EN_MASK                                                                            0x00000001L
 #define BIF_FB_EN__FB_WRITE_EN_MASK                                                                           0x00000002L
-//BIF_BUSY_DELAY_CNTR
-#define BIF_BUSY_DELAY_CNTR__DELAY_CNT__SHIFT                                                                 0x0
-#define BIF_BUSY_DELAY_CNTR__DELAY_CNT_MASK                                                                   0x0000003FL
+//BIF_INTR_CNTL
+#define BIF_INTR_CNTL__RAS_INTR_VEC_SEL__SHIFT                                                                0x0
+#define BIF_INTR_CNTL__RAS_INTR_VEC_SEL_MASK                                                                  0x00000001L
 //BIF_MST_TRANS_PENDING_VF
 #define BIF_MST_TRANS_PENDING_VF__BIF_MST_TRANS_PENDING__SHIFT                                                0x0
 #define BIF_MST_TRANS_PENDING_VF__BIF_MST_TRANS_PENDING_MASK                                                  0x7FFFFFFFL
@@ -48436,4 +48436,47 @@
 #define RCC_DEV0_EPF0_VF15_GFXMSIX_PBA__MSIX_PENDING_BITS_1_MASK                                              0x00000002L
 #define RCC_DEV0_EPF0_VF15_GFXMSIX_PBA__MSIX_PENDING_BITS_2_MASK                                              0x00000004L
 
+//IOHC_INTERRUPT_EOI
+#define IOHC_INTERRUPT_EOI__SMI_EOI__SHIFT                                                                    0x0
+#define IOHC_INTERRUPT_EOI__SCI_EOI__SHIFT                                                                    0x1
+#define IOHC_INTERRUPT_EOI__NMI_EOI__SHIFT                                                                    0x2
+#define IOHC_INTERRUPT_EOI__SMI_EOI_MASK                                                                      0x00000001L
+#define IOHC_INTERRUPT_EOI__SCI_EOI_MASK                                                                      0x00000002L
+#define IOHC_INTERRUPT_EOI__NMI_EOI_MASK                                                                      0x00000004L
+
+//RAS_GLOBAL_STATUS_LO
+#define RAS_GLOBAL_STATUS_LO__ParityErrCorr__SHIFT                                                            0x0
+#define RAS_GLOBAL_STATUS_LO__ParityErrNonFatal__SHIFT                                                        0x1
+#define RAS_GLOBAL_STATUS_LO__ParityErrFatal__SHIFT                                                           0x2
+#define RAS_GLOBAL_STATUS_LO__ParityErrSerr__SHIFT                                                            0x3
+#define RAS_GLOBAL_STATUS_LO__HPLGWA_NMI__SHIFT                                                               0x6
+#define RAS_GLOBAL_STATUS_LO__HPLGWA_SCI__SHIFT                                                               0x7
+#define RAS_GLOBAL_STATUS_LO__HPLGWA_SMI__SHIFT                                                               0x8
+#define RAS_GLOBAL_STATUS_LO__SW_SMI__SHIFT                                                                   0x9
+#define RAS_GLOBAL_STATUS_LO__SW_SCI__SHIFT                                                                   0xa
+#define RAS_GLOBAL_STATUS_LO__SW_NMI__SHIFT                                                                   0xb
+#define RAS_GLOBAL_STATUS_LO__APML_NMI__SHIFT                                                                 0xc
+#define RAS_GLOBAL_STATUS_LO__APML_SyncFld__SHIFT                                                             0xd
+#define RAS_GLOBAL_STATUS_LO__PIN_SyncFld_NMI__SHIFT                                                          0xe
+#define RAS_GLOBAL_STATUS_LO__APML_SyncFld_Private__SHIFT                                                     0xf
+#define RAS_GLOBAL_STATUS_LO__ParityErrCorr_MASK                                                              0x00000001L
+#define RAS_GLOBAL_STATUS_LO__ParityErrNonFatal_MASK                                                          0x00000002L
+#define RAS_GLOBAL_STATUS_LO__ParityErrFatal_MASK                                                             0x00000004L
+#define RAS_GLOBAL_STATUS_LO__ParityErrSerr_MASK                                                              0x00000008L
+#define RAS_GLOBAL_STATUS_LO__HPLGWA_NMI_MASK                                                                 0x00000040L
+#define RAS_GLOBAL_STATUS_LO__HPLGWA_SCI_MASK                                                                 0x00000080L
+#define RAS_GLOBAL_STATUS_LO__HPLGWA_SMI_MASK                                                                 0x00000100L
+#define RAS_GLOBAL_STATUS_LO__SW_SMI_MASK                                                                     0x00000200L
+#define RAS_GLOBAL_STATUS_LO__SW_SCI_MASK                                                                     0x00000400L
+#define RAS_GLOBAL_STATUS_LO__SW_NMI_MASK                                                                     0x00000800L
+#define RAS_GLOBAL_STATUS_LO__APML_NMI_MASK                                                                   0x00001000L
+#define RAS_GLOBAL_STATUS_LO__APML_SyncFld_MASK                                                               0x00002000L
+#define RAS_GLOBAL_STATUS_LO__PIN_SyncFld_NMI_MASK                                                            0x00004000L
+#define RAS_GLOBAL_STATUS_LO__APML_SyncFld_Private_MASK                                                       0x00008000L
+//RAS_GLOBAL_STATUS_HI
+#define RAS_GLOBAL_STATUS_HI__PCIE0PortAErr__SHIFT                                                            0x0
+#define RAS_GLOBAL_STATUS_HI__NBIF0PortAErr__SHIFT                                                            0x1
+#define RAS_GLOBAL_STATUS_HI__PCIE0PortAErr_MASK                                                              0x00000001L
+#define RAS_GLOBAL_STATUS_HI__NBIF0PortAErr_MASK                                                              0x00000002L
+
 #endif
diff --git a/drivers/gpu/drm/amd/include/asic_reg/oss/osssys_4_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/oss/osssys_4_0_sh_mask.h
index dc9895a684fe..096d878eb1de 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/oss/osssys_4_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/oss/osssys_4_0_sh_mask.h
@@ -588,11 +588,15 @@
 #define IH_STORM_CLIENT_LIST_CNTL__CLIENT30_IS_STORM_CLIENT_MASK                                              0x40000000L
 #define IH_STORM_CLIENT_LIST_CNTL__CLIENT31_IS_STORM_CLIENT_MASK                                              0x80000000L
 //IH_CLK_CTRL
+#define IH_CLK_CTRL__IH_RETRY_INT_CAM_MEM_CLK_SOFT_OVERRIDE__SHIFT                                             0x19
+#define IH_CLK_CTRL__IH_BUFFER_MEM_CLK_SOFT_OVERRIDE__SHIFT                                             		  0x1a
 #define IH_CLK_CTRL__DBUS_MUX_CLK_SOFT_OVERRIDE__SHIFT                                                        0x1b
 #define IH_CLK_CTRL__OSSSYS_SHARE_CLK_SOFT_OVERRIDE__SHIFT                                                    0x1c
 #define IH_CLK_CTRL__LIMIT_SMN_CLK_SOFT_OVERRIDE__SHIFT                                                       0x1d
 #define IH_CLK_CTRL__DYN_CLK_SOFT_OVERRIDE__SHIFT                                                             0x1e
 #define IH_CLK_CTRL__REG_CLK_SOFT_OVERRIDE__SHIFT                                                             0x1f
+#define IH_CLK_CTRL__IH_RETRY_INT_CAM_MEM_CLK_SOFT_OVERRIDE_MASK                                              0x02000000L
+#define IH_CLK_CTRL__IH_BUFFER_MEM_CLK_SOFT_OVERRIDE_MASK                                             		  0x04000000L
 #define IH_CLK_CTRL__DBUS_MUX_CLK_SOFT_OVERRIDE_MASK                                                          0x08000000L
 #define IH_CLK_CTRL__OSSSYS_SHARE_CLK_SOFT_OVERRIDE_MASK                                                      0x10000000L
 #define IH_CLK_CTRL__LIMIT_SMN_CLK_SOFT_OVERRIDE_MASK                                                         0x20000000L
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h
index dbc2e723f659..71169daa701a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_d.h
@@ -49,6 +49,7 @@
 #define ixCG_SPLL_FUNC_CNTL_5                                                   0xc0500150
 #define ixCG_SPLL_FUNC_CNTL_6                                                   0xc0500154
 #define ixCG_SPLL_FUNC_CNTL_7                                                   0xc0500158
+#define ixCG_SPLL_STATUS                                                        0xC050015C
 #define ixSPLL_CNTL_MODE                                                        0xc0500160
 #define ixCG_SPLL_SPREAD_SPECTRUM                                               0xc0500164
 #define ixCG_SPLL_SPREAD_SPECTRUM_2                                             0xc0500168
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h
index 6af9f0217b34..61a9a84e0c3a 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_0_1_sh_mask.h
@@ -194,6 +194,8 @@
 #define CG_SPLL_FUNC_CNTL_6__SPLL_LF_CNTR__SHIFT 0x19
 #define CG_SPLL_FUNC_CNTL_7__SPLL_BW_CNTRL_MASK 0xfff
 #define CG_SPLL_FUNC_CNTL_7__SPLL_BW_CNTRL__SHIFT 0x0
+#define CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK 0x2
+#define CG_SPLL_STATUS__SPLL_CHG_STATUS__SHIFT 0x1
 #define SPLL_CNTL_MODE__SPLL_SW_DIR_CONTROL_MASK 0x1
 #define SPLL_CNTL_MODE__SPLL_SW_DIR_CONTROL__SHIFT 0x0
 #define SPLL_CNTL_MODE__SPLL_LEGACY_PDIV_MASK 0x2
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h
index bd3685166779..351446754c72 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_d.h
@@ -49,6 +49,7 @@
 #define ixCG_SPLL_FUNC_CNTL_5                                                   0xc0500150
 #define ixCG_SPLL_FUNC_CNTL_6                                                   0xc0500154
 #define ixCG_SPLL_FUNC_CNTL_7                                                   0xc0500158
+#define ixCG_SPLL_STATUS                                                        0xC050015C
 #define ixSPLL_CNTL_MODE                                                        0xc0500160
 #define ixCG_SPLL_SPREAD_SPECTRUM                                               0xc0500164
 #define ixCG_SPLL_SPREAD_SPECTRUM_2                                             0xc0500168
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h
index 627906674fe8..4bfd5f8ba66c 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_2_sh_mask.h
@@ -194,6 +194,8 @@
 #define CG_SPLL_FUNC_CNTL_6__SPLL_LF_CNTR__SHIFT 0x19
 #define CG_SPLL_FUNC_CNTL_7__SPLL_BW_CNTRL_MASK 0xfff
 #define CG_SPLL_FUNC_CNTL_7__SPLL_BW_CNTRL__SHIFT 0x0
+#define CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK 0x2
+#define CG_SPLL_STATUS__SPLL_CHG_STATUS__SHIFT 0x1
 #define SPLL_CNTL_MODE__SPLL_SW_DIR_CONTROL_MASK 0x1
 #define SPLL_CNTL_MODE__SPLL_SW_DIR_CONTROL__SHIFT 0x0
 #define SPLL_CNTL_MODE__SPLL_LEGACY_PDIV_MASK 0x2
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h
index f35aba72e640..21da61c398f5 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_d.h
@@ -52,6 +52,7 @@
 #define ixCG_SPLL_FUNC_CNTL_5                                                   0xc0500150
 #define ixCG_SPLL_FUNC_CNTL_6                                                   0xc0500154
 #define ixCG_SPLL_FUNC_CNTL_7                                                   0xc0500158
+#define ixCG_SPLL_STATUS                                                        0xC050015C
 #define ixSPLL_CNTL_MODE                                                        0xc0500160
 #define ixCG_SPLL_SPREAD_SPECTRUM                                               0xc0500164
 #define ixCG_SPLL_SPREAD_SPECTRUM_2                                             0xc0500168
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h
index 481ee6560aa9..f64fe0fbcb32 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smu/smu_7_1_3_sh_mask.h
@@ -220,6 +220,8 @@
 #define CG_SPLL_FUNC_CNTL_6__SPLL_LF_CNTR__SHIFT 0x19
 #define CG_SPLL_FUNC_CNTL_7__SPLL_BW_CNTRL_MASK 0xfff
 #define CG_SPLL_FUNC_CNTL_7__SPLL_BW_CNTRL__SHIFT 0x0
+#define CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK 0x2
+#define CG_SPLL_STATUS__SPLL_CHG_STATUS__SHIFT 0x1
 #define SPLL_CNTL_MODE__SPLL_SW_DIR_CONTROL_MASK 0x1
 #define SPLL_CNTL_MODE__SPLL_SW_DIR_CONTROL__SHIFT 0x0
 #define SPLL_CNTL_MODE__SPLL_LEGACY_PDIV_MASK 0x2
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_offset.h
index d3876052562b..687d6843c258 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_offset.h
@@ -121,6 +121,98 @@
 #define mmCKSVII2C_IC_COMP_VERSION_BASE_IDX                                                            0
 #define mmCKSVII2C_IC_COMP_TYPE                                                                        0x006d
 #define mmCKSVII2C_IC_COMP_TYPE_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_CON                                                                             0x0080
+#define mmCKSVII2C1_IC_CON_BASE_IDX                                                                    0
+#define mmCKSVII2C1_IC_TAR                                                                             0x0081
+#define mmCKSVII2C1_IC_TAR_BASE_IDX                                                                    0
+#define mmCKSVII2C1_IC_SAR                                                                             0x0082
+#define mmCKSVII2C1_IC_SAR_BASE_IDX                                                                    0
+#define mmCKSVII2C1_IC_HS_MADDR                                                                        0x0083
+#define mmCKSVII2C1_IC_HS_MADDR_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_DATA_CMD                                                                        0x0084
+#define mmCKSVII2C1_IC_DATA_CMD_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_SS_SCL_HCNT                                                                     0x0085
+#define mmCKSVII2C1_IC_SS_SCL_HCNT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_SS_SCL_LCNT                                                                     0x0086
+#define mmCKSVII2C1_IC_SS_SCL_LCNT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_FS_SCL_HCNT                                                                     0x0087
+#define mmCKSVII2C1_IC_FS_SCL_HCNT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_FS_SCL_LCNT                                                                     0x0088
+#define mmCKSVII2C1_IC_FS_SCL_LCNT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_HS_SCL_HCNT                                                                     0x0089
+#define mmCKSVII2C1_IC_HS_SCL_HCNT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_HS_SCL_LCNT                                                                     0x008a
+#define mmCKSVII2C1_IC_HS_SCL_LCNT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_INTR_STAT                                                                       0x008b
+#define mmCKSVII2C1_IC_INTR_STAT_BASE_IDX                                                              0
+#define mmCKSVII2C1_IC_INTR_MASK                                                                       0x008c
+#define mmCKSVII2C1_IC_INTR_MASK_BASE_IDX                                                              0
+#define mmCKSVII2C1_IC_RAW_INTR_STAT                                                                   0x008d
+#define mmCKSVII2C1_IC_RAW_INTR_STAT_BASE_IDX                                                          0
+#define mmCKSVII2C1_IC_RX_TL                                                                           0x008e
+#define mmCKSVII2C1_IC_RX_TL_BASE_IDX                                                                  0
+#define mmCKSVII2C1_IC_TX_TL                                                                           0x008f
+#define mmCKSVII2C1_IC_TX_TL_BASE_IDX                                                                  0
+#define mmCKSVII2C1_IC_CLR_INTR                                                                        0x0090
+#define mmCKSVII2C1_IC_CLR_INTR_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_CLR_RX_UNDER                                                                    0x0091
+#define mmCKSVII2C1_IC_CLR_RX_UNDER_BASE_IDX                                                           0
+#define mmCKSVII2C1_IC_CLR_RX_OVER                                                                     0x0092
+#define mmCKSVII2C1_IC_CLR_RX_OVER_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_CLR_TX_OVER                                                                     0x0093
+#define mmCKSVII2C1_IC_CLR_TX_OVER_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_CLR_RD_REQ                                                                      0x0094
+#define mmCKSVII2C1_IC_CLR_RD_REQ_BASE_IDX                                                             0
+#define mmCKSVII2C1_IC_CLR_TX_ABRT                                                                     0x0095
+#define mmCKSVII2C1_IC_CLR_TX_ABRT_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_CLR_RX_DONE                                                                     0x0096
+#define mmCKSVII2C1_IC_CLR_RX_DONE_BASE_IDX                                                            0
+#define mmCKSVII2C1_IC_CLR_ACTIVITY                                                                    0x0097
+#define mmCKSVII2C1_IC_CLR_ACTIVITY_BASE_IDX                                                           0
+#define mmCKSVII2C1_IC_CLR_STOP_DET                                                                    0x0098
+#define mmCKSVII2C1_IC_CLR_STOP_DET_BASE_IDX                                                           0
+#define mmCKSVII2C1_IC_CLR_START_DET                                                                   0x0099
+#define mmCKSVII2C1_IC_CLR_START_DET_BASE_IDX                                                          0
+#define mmCKSVII2C1_IC_CLR_GEN_CALL                                                                    0x009a
+#define mmCKSVII2C1_IC_CLR_GEN_CALL_BASE_IDX                                                           0
+#define mmCKSVII2C1_IC_ENABLE                                                                          0x009b
+#define mmCKSVII2C1_IC_ENABLE_BASE_IDX                                                                 0
+#define mmCKSVII2C1_IC_STATUS                                                                          0x009c
+#define mmCKSVII2C1_IC_STATUS_BASE_IDX                                                                 0
+#define mmCKSVII2C1_IC_TXFLR                                                                           0x009d
+#define mmCKSVII2C1_IC_TXFLR_BASE_IDX                                                                  0
+#define mmCKSVII2C1_IC_RXFLR                                                                           0x009e
+#define mmCKSVII2C1_IC_RXFLR_BASE_IDX                                                                  0
+#define mmCKSVII2C1_IC_SDA_HOLD                                                                        0x009f
+#define mmCKSVII2C1_IC_SDA_HOLD_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_TX_ABRT_SOURCE                                                                  0x00a0
+#define mmCKSVII2C1_IC_TX_ABRT_SOURCE_BASE_IDX                                                         0
+#define mmCKSVII2C1_IC_SLV_DATA_NACK_ONLY                                                              0x00a1
+#define mmCKSVII2C1_IC_SLV_DATA_NACK_ONLY_BASE_IDX                                                     0
+#define mmCKSVII2C1_IC_DMA_CR                                                                          0x00a2
+#define mmCKSVII2C1_IC_DMA_CR_BASE_IDX                                                                 0
+#define mmCKSVII2C1_IC_DMA_TDLR                                                                        0x00a3
+#define mmCKSVII2C1_IC_DMA_TDLR_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_DMA_RDLR                                                                        0x00a4
+#define mmCKSVII2C1_IC_DMA_RDLR_BASE_IDX                                                               0
+#define mmCKSVII2C1_IC_SDA_SETUP                                                                       0x00a5
+#define mmCKSVII2C1_IC_SDA_SETUP_BASE_IDX                                                              0
+#define mmCKSVII2C1_IC_ACK_GENERAL_CALL                                                                0x00a6
+#define mmCKSVII2C1_IC_ACK_GENERAL_CALL_BASE_IDX                                                       0
+#define mmCKSVII2C1_IC_ENABLE_STATUS                                                                   0x00a7
+#define mmCKSVII2C1_IC_ENABLE_STATUS_BASE_IDX                                                          0
+#define mmCKSVII2C1_IC_FS_SPKLEN                                                                       0x00a8
+#define mmCKSVII2C1_IC_FS_SPKLEN_BASE_IDX                                                              0
+#define mmCKSVII2C1_IC_HS_SPKLEN                                                                       0x00a9
+#define mmCKSVII2C1_IC_HS_SPKLEN_BASE_IDX                                                              0
+#define mmCKSVII2C1_IC_CLR_RESTART_DET                                                                 0x00aa
+#define mmCKSVII2C1_IC_CLR_RESTART_DET_BASE_IDX                                                        0
+#define mmCKSVII2C1_IC_COMP_PARAM_1                                                                    0x00ab
+#define mmCKSVII2C1_IC_COMP_PARAM_1_BASE_IDX                                                           0
+#define mmCKSVII2C1_IC_COMP_VERSION                                                                    0x00ac
+#define mmCKSVII2C1_IC_COMP_VERSION_BASE_IDX                                                           0
+#define mmCKSVII2C1_IC_COMP_TYPE                                                                       0x00ad
+#define mmCKSVII2C1_IC_COMP_TYPE_BASE_IDX                                                              0
 #define mmSMUIO_MP_RESET_INTR                                                                          0x00c1
 #define mmSMUIO_MP_RESET_INTR_BASE_IDX                                                                 0
 #define mmSMUIO_SOC_HALT                                                                               0x00c2
diff --git a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_sh_mask.h b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_sh_mask.h
index f8afa3518bf2..6905a9618127 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_sh_mask.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/smuio/smuio_11_0_0_sh_mask.h
@@ -268,6 +268,182 @@
 //CKSVII2C_IC_COMP_TYPE
 #define CKSVII2C_IC_COMP_TYPE__COMP_TYPE__SHIFT                                                               0x0
 #define CKSVII2C_IC_COMP_TYPE__COMP_TYPE_MASK                                                                 0xFFFFFFFFL
+//CKSVII2C1_IC_CON
+#define CKSVII2C1_IC_CON__IC1_MASTER_MODE__SHIFT                                                              0x0
+#define CKSVII2C1_IC_CON__IC1_MAX_SPEED_MODE__SHIFT                                                           0x1
+#define CKSVII2C1_IC_CON__IC1_10BITADDR_SLAVE__SHIFT                                                          0x3
+#define CKSVII2C1_IC_CON__IC1_10BITADDR_MASTER__SHIFT                                                         0x4
+#define CKSVII2C1_IC_CON__IC1_RESTART_EN__SHIFT                                                               0x5
+#define CKSVII2C1_IC_CON__IC1_SLAVE_DISABLE__SHIFT                                                            0x6
+#define CKSVII2C1_IC_CON__STOP1_DET_IFADDRESSED__SHIFT                                                        0x7
+#define CKSVII2C1_IC_CON__TX1_EMPTY_CTRL__SHIFT                                                               0x8
+#define CKSVII2C1_IC_CON__RX1_FIFO_FULL_HLD_CTRL__SHIFT                                                       0x9
+#define CKSVII2C1_IC_CON__IC1_MASTER_MODE_MASK                                                                0x00000001L
+#define CKSVII2C1_IC_CON__IC1_MAX_SPEED_MODE_MASK                                                             0x00000006L
+#define CKSVII2C1_IC_CON__IC1_10BITADDR_SLAVE_MASK                                                            0x00000008L
+#define CKSVII2C1_IC_CON__IC1_10BITADDR_MASTER_MASK                                                           0x00000010L
+#define CKSVII2C1_IC_CON__IC1_RESTART_EN_MASK                                                                 0x00000020L
+#define CKSVII2C1_IC_CON__IC1_SLAVE_DISABLE_MASK                                                              0x00000040L
+#define CKSVII2C1_IC_CON__STOP1_DET_IFADDRESSED_MASK                                                          0x00000080L
+#define CKSVII2C1_IC_CON__TX1_EMPTY_CTRL_MASK                                                                 0x00000100L
+#define CKSVII2C1_IC_CON__RX1_FIFO_FULL_HLD_CTRL_MASK                                                         0x00000200L
+//CKSVII2C1_IC_TAR
+#define CKSVII2C1_IC_TAR__IC1_TAR__SHIFT                                                                      0x0
+#define CKSVII2C1_IC_TAR__GC1_OR_START__SHIFT                                                                 0xa
+#define CKSVII2C1_IC_TAR__SPECIAL1__SHIFT                                                                     0xb
+#define CKSVII2C1_IC_TAR__IC1_10BITADDR_MASTER__SHIFT                                                         0xc
+#define CKSVII2C1_IC_TAR__IC1_TAR_MASK                                                                        0x000003FFL
+#define CKSVII2C1_IC_TAR__GC1_OR_START_MASK                                                                   0x00000400L
+#define CKSVII2C1_IC_TAR__SPECIAL1_MASK                                                                       0x00000800L
+#define CKSVII2C1_IC_TAR__IC1_10BITADDR_MASTER_MASK                                                           0x00001000L
+//CKSVII2C1_IC_SAR
+#define CKSVII2C1_IC_SAR__IC1_SAR__SHIFT                                                                      0x0
+#define CKSVII2C1_IC_SAR__IC1_SAR_MASK                                                                        0x000003FFL
+//CKSVII2C1_IC_HS_MADDR
+#define CKSVII2C1_IC_HS_MADDR__IC1_HS_MADDR__SHIFT                                                            0x0
+#define CKSVII2C1_IC_HS_MADDR__IC1_HS_MADDR_MASK                                                              0x00000007L
+//CKSVII2C1_IC_DATA_CMD
+#define CKSVII2C1_IC_DATA_CMD__DAT1__SHIFT                                                                    0x0
+#define CKSVII2C1_IC_DATA_CMD__CMD1__SHIFT                                                                    0x8
+#define CKSVII2C1_IC_DATA_CMD__STOP1__SHIFT                                                                   0x9
+#define CKSVII2C1_IC_DATA_CMD__RESTART1__SHIFT                                                                0xa
+#define CKSVII2C1_IC_DATA_CMD__DAT1_MASK                                                                      0x000000FFL
+#define CKSVII2C1_IC_DATA_CMD__CMD1_MASK                                                                      0x00000100L
+#define CKSVII2C1_IC_DATA_CMD__STOP1_MASK                                                                     0x00000200L
+#define CKSVII2C1_IC_DATA_CMD__RESTART1_MASK                                                                  0x00000400L
+//CKSVII2C1_IC_SS_SCL_HCNT
+#define CKSVII2C1_IC_SS_SCL_HCNT__IC1_SS_SCL_HCNT__SHIFT                                                      0x0
+#define CKSVII2C1_IC_SS_SCL_HCNT__IC1_SS_SCL_HCNT_MASK                                                        0x0000FFFFL
+//CKSVII2C1_IC_SS_SCL_LCNT
+#define CKSVII2C1_IC_SS_SCL_LCNT__IC1_SS_SCL_LCNT__SHIFT                                                      0x0
+#define CKSVII2C1_IC_SS_SCL_LCNT__IC1_SS_SCL_LCNT_MASK                                                        0x0000FFFFL
+//CKSVII2C1_IC_FS_SCL_HCNT
+#define CKSVII2C1_IC_FS_SCL_HCNT__IC1_FS_SCL_HCNT__SHIFT                                                      0x0
+#define CKSVII2C1_IC_FS_SCL_HCNT__IC1_FS_SCL_HCNT_MASK                                                        0x0000FFFFL
+//CKSVII2C1_IC_FS_SCL_LCNT
+#define CKSVII2C1_IC_FS_SCL_LCNT__IC1_FS_SCL_LCNT__SHIFT                                                      0x0
+#define CKSVII2C1_IC_FS_SCL_LCNT__IC1_FS_SCL_LCNT_MASK                                                        0x0000FFFFL
+//CKSVII2C1_IC_HS_SCL_HCNT
+#define CKSVII2C1_IC_HS_SCL_HCNT__IC1_HS_SCL_HCNT__SHIFT                                                      0x0
+#define CKSVII2C1_IC_HS_SCL_HCNT__IC1_HS_SCL_HCNT_MASK                                                        0x0000FFFFL
+//CKSVII2C1_IC_HS_SCL_LCNT
+#define CKSVII2C1_IC_HS_SCL_LCNT__IC1_HS_SCL_LCNT__SHIFT                                                      0x0
+#define CKSVII2C1_IC_HS_SCL_LCNT__IC1_HS_SCL_LCNT_MASK                                                        0x0000FFFFL
+//CKSVII2C1_IC_INTR_STAT
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_UNDER__SHIFT                                                            0x0
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_OVER__SHIFT                                                             0x1
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_FULL__SHIFT                                                             0x2
+#define CKSVII2C1_IC_INTR_STAT__R1_TX_OVER__SHIFT                                                             0x3
+#define CKSVII2C1_IC_INTR_STAT__R1_TX_EMPTY__SHIFT                                                            0x4
+#define CKSVII2C1_IC_INTR_STAT__R1_RD_REQ__SHIFT                                                              0x5
+#define CKSVII2C1_IC_INTR_STAT__R1_TX_ABRT__SHIFT                                                             0x6
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_DONE__SHIFT                                                             0x7
+#define CKSVII2C1_IC_INTR_STAT__R1_ACTIVITY__SHIFT                                                            0x8
+#define CKSVII2C1_IC_INTR_STAT__R1_STOP_DET__SHIFT                                                            0x9
+#define CKSVII2C1_IC_INTR_STAT__R1_START_DET__SHIFT                                                           0xa
+#define CKSVII2C1_IC_INTR_STAT__R1_GEN_CALL__SHIFT                                                            0xb
+#define CKSVII2C1_IC_INTR_STAT__R1_RESTART_DET__SHIFT                                                         0xc
+#define CKSVII2C1_IC_INTR_STAT__R1_MST_ON_HOLD__SHIFT                                                         0xd
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_UNDER_MASK                                                              0x00000001L
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_OVER_MASK                                                               0x00000002L
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_FULL_MASK                                                               0x00000004L
+#define CKSVII2C1_IC_INTR_STAT__R1_TX_OVER_MASK                                                               0x00000008L
+#define CKSVII2C1_IC_INTR_STAT__R1_TX_EMPTY_MASK                                                              0x00000010L
+#define CKSVII2C1_IC_INTR_STAT__R1_RD_REQ_MASK                                                                0x00000020L
+#define CKSVII2C1_IC_INTR_STAT__R1_TX_ABRT_MASK                                                               0x00000040L
+#define CKSVII2C1_IC_INTR_STAT__R1_RX_DONE_MASK                                                               0x00000080L
+#define CKSVII2C1_IC_INTR_STAT__R1_ACTIVITY_MASK                                                              0x00000100L
+#define CKSVII2C1_IC_INTR_STAT__R1_STOP_DET_MASK                                                              0x00000200L
+#define CKSVII2C1_IC_INTR_STAT__R1_START_DET_MASK                                                             0x00000400L
+#define CKSVII2C1_IC_INTR_STAT__R1_GEN_CALL_MASK                                                              0x00000800L
+#define CKSVII2C1_IC_INTR_STAT__R1_RESTART_DET_MASK                                                           0x00001000L
+#define CKSVII2C1_IC_INTR_STAT__R1_MST_ON_HOLD_MASK                                                           0x00002000L
+//CKSVII2C1_IC_INTR_MASK
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_UNDER__SHIFT                                                            0x0
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_OVER__SHIFT                                                             0x1
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_FULL__SHIFT                                                             0x2
+#define CKSVII2C1_IC_INTR_MASK__M1_TX_OVER__SHIFT                                                             0x3
+#define CKSVII2C1_IC_INTR_MASK__M1_TX_EMPTY__SHIFT                                                            0x4
+#define CKSVII2C1_IC_INTR_MASK__M1_RD_REQ__SHIFT                                                              0x5
+#define CKSVII2C1_IC_INTR_MASK__M1_TX_ABRT__SHIFT                                                             0x6
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_DONE__SHIFT                                                             0x7
+#define CKSVII2C1_IC_INTR_MASK__M1_ACTIVITY__SHIFT                                                            0x8
+#define CKSVII2C1_IC_INTR_MASK__M1_STOP_DET__SHIFT                                                            0x9
+#define CKSVII2C1_IC_INTR_MASK__M1_START_DET__SHIFT                                                           0xa
+#define CKSVII2C1_IC_INTR_MASK__M1_GEN_CALL__SHIFT                                                            0xb
+#define CKSVII2C1_IC_INTR_MASK__M1_RESTART_DET__SHIFT                                                         0xc
+#define CKSVII2C1_IC_INTR_MASK__M1_MST_ON_HOLD__SHIFT                                                         0xd
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_UNDER_MASK                                                              0x00000001L
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_OVER_MASK                                                               0x00000002L
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_FULL_MASK                                                               0x00000004L
+#define CKSVII2C1_IC_INTR_MASK__M1_TX_OVER_MASK                                                               0x00000008L
+#define CKSVII2C1_IC_INTR_MASK__M1_TX_EMPTY_MASK                                                              0x00000010L
+#define CKSVII2C1_IC_INTR_MASK__M1_RD_REQ_MASK                                                                0x00000020L
+#define CKSVII2C1_IC_INTR_MASK__M1_TX_ABRT_MASK                                                               0x00000040L
+#define CKSVII2C1_IC_INTR_MASK__M1_RX_DONE_MASK                                                               0x00000080L
+#define CKSVII2C1_IC_INTR_MASK__M1_ACTIVITY_MASK                                                              0x00000100L
+#define CKSVII2C1_IC_INTR_MASK__M1_STOP_DET_MASK                                                              0x00000200L
+#define CKSVII2C1_IC_INTR_MASK__M1_START_DET_MASK                                                             0x00000400L
+#define CKSVII2C1_IC_INTR_MASK__M1_GEN_CALL_MASK                                                              0x00000800L
+#define CKSVII2C1_IC_INTR_MASK__M1_RESTART_DET_MASK                                                           0x00001000L
+#define CKSVII2C1_IC_INTR_MASK__M1_MST_ON_HOLD_MASK                                                           0x00002000L
+//CKSVII2C1_IC_RAW_INTR_STAT
+//CKSVII2C1_IC_RX_TL
+//CKSVII2C1_IC_TX_TL
+//CKSVII2C1_IC_CLR_INTR
+//CKSVII2C1_IC_CLR_RX_UNDER
+//CKSVII2C1_IC_CLR_RX_OVER
+//CKSVII2C1_IC_CLR_TX_OVER
+//CKSVII2C1_IC_CLR_RD_REQ
+//CKSVII2C1_IC_CLR_TX_ABRT
+//CKSVII2C1_IC_CLR_RX_DONE
+//CKSVII2C1_IC_CLR_ACTIVITY
+//CKSVII2C1_IC_CLR_STOP_DET
+//CKSVII2C1_IC_CLR_START_DET
+//CKSVII2C1_IC_CLR_GEN_CALL
+//CKSVII2C1_IC_ENABLE
+#define CKSVII2C1_IC_ENABLE__ENABLE1__SHIFT                                                                   0x0
+#define CKSVII2C1_IC_ENABLE__ABORT1__SHIFT                                                                    0x1
+#define CKSVII2C1_IC_ENABLE__ENABLE1_MASK                                                                     0x00000001L
+#define CKSVII2C1_IC_ENABLE__ABORT1_MASK                                                                      0x00000002L
+//CKSVII2C1_IC_STATUS
+#define CKSVII2C1_IC_STATUS__ACTIVITY1__SHIFT                                                                 0x0
+#define CKSVII2C1_IC_STATUS__TFNF1__SHIFT                                                                     0x1
+#define CKSVII2C1_IC_STATUS__TFE1__SHIFT                                                                      0x2
+#define CKSVII2C1_IC_STATUS__RFNE1__SHIFT                                                                     0x3
+#define CKSVII2C1_IC_STATUS__RFF1__SHIFT                                                                      0x4
+#define CKSVII2C1_IC_STATUS__MST1_ACTIVITY__SHIFT                                                             0x5
+#define CKSVII2C1_IC_STATUS__SLV1_ACTIVITY__SHIFT                                                             0x6
+#define CKSVII2C1_IC_STATUS__ACTIVITY1_MASK                                                                   0x00000001L
+#define CKSVII2C1_IC_STATUS__TFNF1_MASK                                                                       0x00000002L
+#define CKSVII2C1_IC_STATUS__TFE1_MASK                                                                        0x00000004L
+#define CKSVII2C1_IC_STATUS__RFNE1_MASK                                                                       0x00000008L
+#define CKSVII2C1_IC_STATUS__RFF1_MASK                                                                        0x00000010L
+#define CKSVII2C1_IC_STATUS__MST1_ACTIVITY_MASK                                                               0x00000020L
+#define CKSVII2C1_IC_STATUS__SLV1_ACTIVITY_MASK                                                               0x00000040L
+//CKSVII2C1_IC_TXFLR
+//CKSVII2C1_IC_RXFLR
+//CKSVII2C1_IC_SDA_HOLD
+#define CKSVII2C1_IC_SDA_HOLD__IC1_SDA_HOLD__SHIFT                                                            0x0
+#define CKSVII2C1_IC_SDA_HOLD__IC1_SDA_HOLD_MASK                                                              0x00FFFFFFL
+//CKSVII2C1_IC_TX_ABRT_SOURCE
+//CKSVII2C1_IC_SLV_DATA_NACK_ONLY
+//CKSVII2C1_IC_DMA_CR
+//CKSVII2C1_IC_DMA_TDLR
+//CKSVII2C1_IC_DMA_RDLR
+//CKSVII2C1_IC_SDA_SETUP
+#define CKSVII2C1_IC_SDA_SETUP__SDA1_SETUP__SHIFT                                                             0x0
+#define CKSVII2C1_IC_SDA_SETUP__SDA1_SETUP_MASK                                                               0x000000FFL
+//CKSVII2C1_IC_ACK_GENERAL_CALL
+#define CKSVII2C1_IC_ACK_GENERAL_CALL__ACK1_GENERAL_CALL__SHIFT                                               0x0
+#define CKSVII2C1_IC_ACK_GENERAL_CALL__ACK1_GENERAL_CALL_MASK                                                 0x00000001L
+//CKSVII2C1_IC_ENABLE_STATUS
+#define CKSVII2C1_IC_ENABLE_STATUS__IC1_EN__SHIFT                                                             0x0
+#define CKSVII2C1_IC_ENABLE_STATUS__SLV1_RX_ABORTED__SHIFT                                                    0x1
+#define CKSVII2C1_IC_ENABLE_STATUS__SLV1_FIFO_FILLED_AND_FLUSHED__SHIFT                                       0x2
+#define CKSVII2C1_IC_ENABLE_STATUS__IC1_EN_MASK                                                               0x00000001L
+#define CKSVII2C1_IC_ENABLE_STATUS__SLV1_RX_ABORTED_MASK                                                      0x00000002L
+#define CKSVII2C1_IC_ENABLE_STATUS__SLV1_FIFO_FILLED_AND_FLUSHED_MASK                                         0x00000004L
 //SMUIO_MP_RESET_INTR
 #define SMUIO_MP_RESET_INTR__SMUIO_MP_RESET_INTR__SHIFT                                                       0x0
 #define SMUIO_MP_RESET_INTR__SMUIO_MP_RESET_INTR_MASK                                                         0x00000001L
diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h
index cf2149cc12ee..90350f46a0c4 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_2_5_offset.h
@@ -24,6 +24,18 @@
 
 // addressBlock: uvd0_mmsch_dec
 // base address: 0x1e000
+#define mmMMSCH_VF_VMID                                                                                0x000b
+#define mmMMSCH_VF_VMID_BASE_IDX                                                                       0
+#define mmMMSCH_VF_CTX_ADDR_LO                                                                         0x000c
+#define mmMMSCH_VF_CTX_ADDR_LO_BASE_IDX                                                                0
+#define mmMMSCH_VF_CTX_ADDR_HI                                                                         0x000d
+#define mmMMSCH_VF_CTX_ADDR_HI_BASE_IDX                                                                0
+#define mmMMSCH_VF_CTX_SIZE                                                                            0x000e
+#define mmMMSCH_VF_CTX_SIZE_BASE_IDX                                                                   0
+#define mmMMSCH_VF_MAILBOX_HOST                                                                        0x0012
+#define mmMMSCH_VF_MAILBOX_HOST_BASE_IDX                                                               0
+#define mmMMSCH_VF_MAILBOX_RESP                                                                        0x0013
+#define mmMMSCH_VF_MAILBOX_RESP_BASE_IDX                                                               0
 
 
 // addressBlock: uvd0_jpegnpdec
diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index e88541d67aa0..dd7cbc00a0aa 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -492,12 +492,13 @@ struct atom_firmware_info_v3_1
 /* Total 32bit cap indication */
 enum atombios_firmware_capability
 {
-  ATOM_FIRMWARE_CAP_FIRMWARE_POSTED = 0x00000001,
-  ATOM_FIRMWARE_CAP_GPU_VIRTUALIZATION  = 0x00000002,
-  ATOM_FIRMWARE_CAP_WMI_SUPPORT  = 0x00000040,
-  ATOM_FIRMWARE_CAP_HWEMU_ENABLE  = 0x00000080,
-  ATOM_FIRMWARE_CAP_HWEMU_UMC_CFG = 0x00000100,
-  ATOM_FIRMWARE_CAP_SRAM_ECC      = 0x00000200,
+	ATOM_FIRMWARE_CAP_FIRMWARE_POSTED = 0x00000001,
+	ATOM_FIRMWARE_CAP_GPU_VIRTUALIZATION  = 0x00000002,
+	ATOM_FIRMWARE_CAP_WMI_SUPPORT  = 0x00000040,
+	ATOM_FIRMWARE_CAP_HWEMU_ENABLE  = 0x00000080,
+	ATOM_FIRMWARE_CAP_HWEMU_UMC_CFG = 0x00000100,
+	ATOM_FIRMWARE_CAP_SRAM_ECC      = 0x00000200,
+	ATOM_FIRMWARE_CAP_ENABLE_2STAGE_BIST_TRAINING  = 0x00000400,
 };
 
 enum atom_cooling_solution_id{
@@ -671,6 +672,20 @@ struct vram_usagebyfirmware_v2_1
   uint16_t  used_by_driver_in_kb; 
 };
 
+/* This is part of vram_usagebyfirmware_v2_1 */
+struct vram_reserve_block
+{
+	uint32_t start_address_in_kb;
+	uint16_t used_by_firmware_in_kb;
+	uint16_t used_by_driver_in_kb;
+};
+
+/* Definitions for constance */
+enum atomfirmware_internal_constants
+{
+	ONE_KiB	= 0x400,
+	ONE_MiB	= 0x100000,
+};
 
 /* 
   ***************************************************************************
diff --git a/drivers/gpu/drm/amd/include/discovery.h b/drivers/gpu/drm/amd/include/discovery.h
index 5dcb776548d8..7ec4331e67f2 100644
--- a/drivers/gpu/drm/amd/include/discovery.h
+++ b/drivers/gpu/drm/amd/include/discovery.h
@@ -25,7 +25,6 @@
 #define _DISCOVERY_H_
 
 #define PSP_HEADER_SIZE                 256
-#define BINARY_MAX_SIZE                 (64 << 10)
 #define BINARY_SIGNATURE                0x28211407
 #define DISCOVERY_TABLE_SIGNATURE       0x53445049
 
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/nbio/irqsrcs_nbif_7_4.h b/drivers/gpu/drm/amd/include/ivsrcid/nbio/irqsrcs_nbif_7_4.h
new file mode 100644
index 000000000000..79af4258f259
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/nbio/irqsrcs_nbif_7_4.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_NBIF_7_4_H__
+#define __IRQSRCS_NBIF_7_4_H__
+
+#define NBIF_7_4__SRCID__CHIP_ERR_INT_EVENT            0x5E        // Error generated
+#define NBIF_7_4__SRCID__DOORBELL_INTERRUPT            0x5F        // Interrupt for doorbell event during VDDGFX off
+#define NBIF_7_4__SRCID__RAS_CONTROLLER_INTERRUPT      0x60        // Interrupt for ras_intr_valid from RAS controller
+#define NBIF_7_4__SRCID__ERREVENT_ATHUB_INTERRUPT      0x61        // Interrupt for SDP ErrEvent received from ATHUB
+#define NBIF_7_4__SRCID__PF_VF_MSGBUF_VALID            0x87        // Valid message in PF->VF mailbox message buffer (The interrupt is sent on behalf of PF)
+#define NBIF_7_4__SRCID__PF_VF_MSGBUF_ACK              0x88        // Acknowledge message in PF->VF mailbox message buffer (The interrupt is sent on behalf of VF)
+#define NBIF_7_4__SRCID__VF_PF_MSGBUF_VALID            0x89        // Valid message in VF->PF mailbox message buffer (The interrupt is sent on behalf of VF)
+#define NBIF_7_4__SRCID__VF_PF_MSGBUF_ACK              0x8A        // Acknowledge message in VF->PF mailbox message buffer (The interrupt is sent on behalf of PF)
+#define NBIF_7_4__SRCID__CHIP_DPA_INT_EVENT            0xA0        // BIF_CHIP_DPA_INT_EVENT
+#define NBIF_7_4__SRCID__CHIP_SLOT_POWER_CHG_INT_EVENT 0xA1        // BIF_CHIP_SLOT_POWER_CHG_INT_EVENT
+#define NBIF_7_4__SRCID__ATOMIC_UR_OPCODE              0xCE        // BIF receives unsupported atomic opcode from MC
+#define NBIF_7_4__SRCID__ATOMIC_REQESTEREN_LOW         0xCF        // BIF receive atomic request from MC while AtomicOp Requester is not enabled in PCIE config space
+
+#endif // __IRQSRCS_NBIF_7_4_H__
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 98b9533e672b..2cd217e60125 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -291,15 +291,18 @@ struct kfd2kgd_calls {
 	uint32_t (*address_watch_get_offset)(struct kgd_dev *kgd,
 					unsigned int watch_point_id,
 					unsigned int reg_offset);
-	bool (*get_atc_vmid_pasid_mapping_valid)(
+	bool (*get_atc_vmid_pasid_mapping_info)(
 					struct kgd_dev *kgd,
-					uint8_t vmid);
-	uint16_t (*get_atc_vmid_pasid_mapping_pasid)(
-					struct kgd_dev *kgd,
-					uint8_t vmid);
+					uint8_t vmid,
+					uint16_t *p_pasid);
 
+	/* No longer needed from GFXv9 onward. The scratch base address is
+	 * passed to the shader by the CP. It's the user mode driver's
+	 * responsibility.
+	 */
 	void (*set_scratch_backing_va)(struct kgd_dev *kgd,
 				uint64_t va, uint32_t vmid);
+
 	int (*get_tile_config)(struct kgd_dev *kgd, struct tile_config *config);
 
 	void (*set_vm_context_page_table_base)(struct kgd_dev *kgd,
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 27cf0afaa0b4..a7f92d0b3a90 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -179,6 +179,11 @@ enum pp_mp1_state {
 	PP_MP1_STATE_RESET,
 };
 
+enum pp_df_cstate {
+	DF_CSTATE_DISALLOW = 0,
+	DF_CSTATE_ALLOW,
+};
+
 #define PP_GROUP_MASK        0xF0000000
 #define PP_GROUP_SHIFT       28
 
@@ -215,6 +220,9 @@ enum pp_mp1_state {
 		((group) << PP_GROUP_SHIFT | (block) << PP_BLOCK_SHIFT | \
 		(support) << PP_STATE_SUPPORT_SHIFT | (state) << PP_STATE_SHIFT)
 
+#define XGMI_MODE_PSTATE_D3 0
+#define XGMI_MODE_PSTATE_D0 1
+
 struct seq_file;
 enum amd_pp_clock_type;
 struct amd_pp_simple_clock_info;
@@ -312,6 +320,8 @@ struct amd_pm_funcs {
 	int (*get_ppfeature_status)(void *handle, char *buf);
 	int (*set_ppfeature_status)(void *handle, uint64_t ppfeature_masks);
 	int (*asic_reset_mode_2)(void *handle);
+	int (*set_df_cstate)(void *handle, enum pp_df_cstate state);
+	int (*set_xgmi_pstate)(void *handle, uint32_t pstate);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/include/renoir_ip_offset.h b/drivers/gpu/drm/amd/include/renoir_ip_offset.h
index 094648cac392..07633e22e99a 100644
--- a/drivers/gpu/drm/amd/include/renoir_ip_offset.h
+++ b/drivers/gpu/drm/amd/include/renoir_ip_offset.h
@@ -169,6 +169,11 @@ static const struct IP_BASE NBIF0_BASE ={ { { { 0x00000000, 0x00000014, 0x00000D
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } } } };
+static const struct IP_BASE DCN_BASE   ={ { { { 0x00000012, 0x000000C0, 0x000034C0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } },
+                                        { { 0, 0, 0, 0, 0 } } } };
 static const struct IP_BASE OSSSYS_BASE ={ { { { 0x000010A0, 0x0240A000, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
                                         { { 0, 0, 0, 0, 0 } },
@@ -1361,4 +1366,33 @@ static const struct IP_BASE UVD0_BASE ={ { { { 0x00007800, 0x00007E00, 0x0240300
 #define UVD0_BASE__INST6_SEG3                      0
 #define UVD0_BASE__INST6_SEG4                      0
 
+#define DCN_BASE__INST0_SEG0                      0x00000012
+#define DCN_BASE__INST0_SEG1                      0x000000C0
+#define DCN_BASE__INST0_SEG2                      0x000034C0
+#define DCN_BASE__INST0_SEG3                      0
+#define DCN_BASE__INST0_SEG4                      0
+
+#define DCN_BASE__INST1_SEG0                      0
+#define DCN_BASE__INST1_SEG1                      0
+#define DCN_BASE__INST1_SEG2                      0
+#define DCN_BASE__INST1_SEG3                      0
+#define DCN_BASE__INST1_SEG4                      0
+
+#define DCN_BASE__INST2_SEG0                      0
+#define DCN_BASE__INST2_SEG1                      0
+#define DCN_BASE__INST2_SEG2                      0
+#define DCN_BASE__INST2_SEG3                      0
+#define DCN_BASE__INST2_SEG4                      0
+
+#define DCN_BASE__INST3_SEG0                      0
+#define DCN_BASE__INST3_SEG1                      0
+#define DCN_BASE__INST3_SEG2                      0
+#define DCN_BASE__INST3_SEG3                      0
+#define DCN_BASE__INST3_SEG4                      0
+
+#define DCN_BASE__INST4_SEG0                      0
+#define DCN_BASE__INST4_SEG1                      0
+#define DCN_BASE__INST4_SEG2                      0
+#define DCN_BASE__INST4_SEG3                      0
+#define DCN_BASE__INST4_SEG4                      0
 #endif
diff --git a/drivers/gpu/drm/amd/include/vega10_enum.h b/drivers/gpu/drm/amd/include/vega10_enum.h
index c14ba65a2415..adf1b754666e 100644
--- a/drivers/gpu/drm/amd/include/vega10_enum.h
+++ b/drivers/gpu/drm/amd/include/vega10_enum.h
@@ -1037,6 +1037,7 @@ TCC_CACHE_POLICY_STREAM                  = 0x00000001,
 typedef enum MTYPE {
 MTYPE_NC                                 = 0x00000000,
 MTYPE_WC                                 = 0x00000001,
+MTYPE_RW                                 = 0x00000001,
 MTYPE_CC                                 = 0x00000002,
 MTYPE_UC                                 = 0x00000003,
 } MTYPE;
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index fa8ad7db2b3a..7932eb163a00 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -969,6 +969,14 @@ static int pp_dpm_switch_power_profile(void *handle,
 		workload = hwmgr->workload_setting[index];
 	}
 
+	if (type == PP_SMC_POWER_PROFILE_COMPUTE &&
+		hwmgr->hwmgr_func->disable_power_features_for_compute_performance) {
+			if (hwmgr->hwmgr_func->disable_power_features_for_compute_performance(hwmgr, en)) {
+				mutex_unlock(&hwmgr->smu_lock);
+				return -EINVAL;
+			}
+	}
+
 	if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL)
 		hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0);
 	mutex_unlock(&hwmgr->smu_lock);
@@ -1421,6 +1429,7 @@ static int pp_get_asic_baco_capability(void *handle, bool *cap)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
+	*cap = false;
 	if (!hwmgr)
 		return -EINVAL;
 
@@ -1548,6 +1557,40 @@ static int pp_smu_i2c_bus_access(void *handle, bool acquire)
 	return ret;
 }
 
+static int pp_set_df_cstate(void *handle, enum pp_df_cstate state)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr)
+		return -EINVAL;
+
+	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->set_df_cstate)
+		return 0;
+
+	mutex_lock(&hwmgr->smu_lock);
+	hwmgr->hwmgr_func->set_df_cstate(hwmgr, state);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return 0;
+}
+
+static int pp_set_xgmi_pstate(void *handle, uint32_t pstate)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr)
+		return -EINVAL;
+
+	if (!hwmgr->pm_en || !hwmgr->hwmgr_func->set_xgmi_pstate)
+		return 0;
+
+	mutex_lock(&hwmgr->smu_lock);
+	hwmgr->hwmgr_func->set_xgmi_pstate(hwmgr, pstate);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return 0;
+}
+
 static const struct amd_pm_funcs pp_dpm_funcs = {
 	.load_firmware = pp_dpm_load_fw,
 	.wait_for_fw_loading_complete = pp_dpm_fw_loading_complete,
@@ -1606,4 +1649,6 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_ppfeature_status = pp_set_ppfeature_status,
 	.asic_reset_mode_2 = pp_asic_reset_mode_2,
 	.smu_i2c_bus_access = pp_smu_i2c_bus_access,
+	.set_df_cstate = pp_set_df_cstate,
+	.set_xgmi_pstate = pp_set_xgmi_pstate,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
index 4acf139ea014..5ff7ccedfbed 100644
--- a/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
+++ b/drivers/gpu/drm/amd/powerplay/amdgpu_smu.c
@@ -25,11 +25,16 @@
 #include "pp_debug.h"
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "soc15_common.h"
 #include "smu_v11_0.h"
 #include "smu_v12_0.h"
 #include "atom.h"
 #include "amd_pcie.h"
+#include "vega20_ppt.h"
+#include "arcturus_ppt.h"
+#include "navi10_ppt.h"
+#include "renoir_ppt.h"
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	#type
@@ -67,6 +72,8 @@ size_t smu_sys_get_pp_feature_mask(struct smu_context *smu, char *buf)
 	uint32_t sort_feature[SMU_FEATURE_COUNT];
 	uint64_t hw_feature_count = 0;
 
+	mutex_lock(&smu->mutex);
+
 	ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
 	if (ret)
 		goto failed;
@@ -92,9 +99,57 @@ size_t smu_sys_get_pp_feature_mask(struct smu_context *smu, char *buf)
 	}
 
 failed:
+	mutex_unlock(&smu->mutex);
+
 	return size;
 }
 
+static int smu_feature_update_enable_state(struct smu_context *smu,
+					   uint64_t feature_mask,
+					   bool enabled)
+{
+	struct smu_feature *feature = &smu->smu_feature;
+	uint32_t feature_low = 0, feature_high = 0;
+	int ret = 0;
+
+	if (!smu->pm_enabled)
+		return ret;
+
+	feature_low = (feature_mask >> 0 ) & 0xffffffff;
+	feature_high = (feature_mask >> 32) & 0xffffffff;
+
+	if (enabled) {
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnableSmuFeaturesLow,
+						  feature_low);
+		if (ret)
+			return ret;
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnableSmuFeaturesHigh,
+						  feature_high);
+		if (ret)
+			return ret;
+	} else {
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_DisableSmuFeaturesLow,
+						  feature_low);
+		if (ret)
+			return ret;
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_DisableSmuFeaturesHigh,
+						  feature_high);
+		if (ret)
+			return ret;
+	}
+
+	mutex_lock(&feature->mutex);
+	if (enabled)
+		bitmap_or(feature->enabled, feature->enabled,
+				(unsigned long *)(&feature_mask), SMU_FEATURE_MAX);
+	else
+		bitmap_andnot(feature->enabled, feature->enabled,
+				(unsigned long *)(&feature_mask), SMU_FEATURE_MAX);
+	mutex_unlock(&feature->mutex);
+
+	return ret;
+}
+
 int smu_sys_set_pp_feature_mask(struct smu_context *smu, uint64_t new_mask)
 {
 	int ret = 0;
@@ -103,9 +158,11 @@ int smu_sys_set_pp_feature_mask(struct smu_context *smu, uint64_t new_mask)
 	uint64_t feature_2_disabled = 0;
 	uint64_t feature_enables = 0;
 
+	mutex_lock(&smu->mutex);
+
 	ret = smu_feature_get_enabled_mask(smu, feature_mask, 2);
 	if (ret)
-		return ret;
+		goto out;
 
 	feature_enables = ((uint64_t)feature_mask[1] << 32 | (uint64_t)feature_mask[0]);
 
@@ -115,14 +172,17 @@ int smu_sys_set_pp_feature_mask(struct smu_context *smu, uint64_t new_mask)
 	if (feature_2_enabled) {
 		ret = smu_feature_update_enable_state(smu, feature_2_enabled, true);
 		if (ret)
-			return ret;
+			goto out;
 	}
 	if (feature_2_disabled) {
 		ret = smu_feature_update_enable_state(smu, feature_2_disabled, false);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+out:
+	mutex_unlock(&smu->mutex);
+
 	return ret;
 }
 
@@ -159,8 +219,7 @@ int smu_get_smc_version(struct smu_context *smu, uint32_t *if_version, uint32_t
 int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max)
 {
-	int ret = 0, clk_id = 0;
-	uint32_t param;
+	int ret = 0;
 
 	if (min <= 0 && max <= 0)
 		return -EINVAL;
@@ -168,27 +227,7 @@ int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 	if (!smu_clk_dpm_is_enabled(smu, clk_type))
 		return 0;
 
-	clk_id = smu_clk_get_index(smu, clk_type);
-	if (clk_id < 0)
-		return clk_id;
-
-	if (max > 0) {
-		param = (uint32_t)((clk_id << 16) | (max & 0xffff));
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxByFreq,
-						  param);
-		if (ret)
-			return ret;
-	}
-
-	if (min > 0) {
-		param = (uint32_t)((clk_id << 16) | (min & 0xffff));
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMinByFreq,
-						  param);
-		if (ret)
-			return ret;
-	}
-
-
+	ret = smu_set_soft_freq_limited_range(smu, clk_type, min, max);
 	return ret;
 }
 
@@ -229,7 +268,7 @@ int smu_set_hard_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 }
 
 int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
-			   uint32_t *min, uint32_t *max)
+			   uint32_t *min, uint32_t *max, bool lock_needed)
 {
 	uint32_t clock_limit;
 	int ret = 0;
@@ -237,6 +276,9 @@ int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 	if (!min && !max)
 		return -EINVAL;
 
+	if (lock_needed)
+		mutex_lock(&smu->mutex);
+
 	if (!smu_clk_dpm_is_enabled(smu, clk_type)) {
 		switch (clk_type) {
 		case SMU_MCLK:
@@ -260,14 +302,17 @@ int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			*min = clock_limit / 100;
 		if (max)
 			*max = clock_limit / 100;
-
-		return 0;
+	} else {
+		/*
+		 * Todo: Use each asic(ASIC_ppt funcs) control the callbacks exposed to the
+		 * core driver and then have helpers for stuff that is common(SMU_v11_x | SMU_v12_x funcs).
+		 */
+		ret = smu_get_dpm_ultimate_freq(smu, clk_type, min, max);
 	}
-	/*
-	 * Todo: Use each asic(ASIC_ppt funcs) control the callbacks exposed to the
-	 * core driver and then have helpers for stuff that is common(SMU_v11_x | SMU_v12_x funcs).
-	 */
-	ret = smu_get_dpm_ultimate_freq(smu, clk_type, min, max);
+
+	if (lock_needed)
+		mutex_unlock(&smu->mutex);
+
 	return ret;
 }
 
@@ -338,7 +383,20 @@ bool smu_clk_dpm_is_enabled(struct smu_context *smu, enum smu_clk_type clk_type)
 	return true;
 }
 
-
+/**
+ * smu_dpm_set_power_gate - power gate/ungate the specific IP block
+ *
+ * @smu:        smu_context pointer
+ * @block_type: the IP block to power gate/ungate
+ * @gate:       to power gate if true, ungate otherwise
+ *
+ * This API uses no smu->mutex lock protection due to:
+ * 1. It is either called by other IP block(gfx/sdma/vcn/uvd/vce).
+ *    This is guarded to be race condition free by the caller.
+ * 2. Or get called on user setting request of power_dpm_force_performance_level.
+ *    Under this case, the smu->mutex lock protection is already enforced on
+ *    the parent API smu_force_performance_level of the call path.
+ */
 int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 			   bool gate)
 {
@@ -364,12 +422,6 @@ int smu_dpm_set_power_gate(struct smu_context *smu, uint32_t block_type,
 	return ret;
 }
 
-enum amd_pm_state_type smu_get_current_power_state(struct smu_context *smu)
-{
-	/* not support power state */
-	return POWER_STATE_TYPE_DEFAULT;
-}
-
 int smu_get_power_num_states(struct smu_context *smu,
 			     struct pp_states_info *state_info)
 {
@@ -439,7 +491,7 @@ int smu_update_table(struct smu_context *smu, enum smu_table_id table_index, int
 	int ret = 0;
 	int table_id = smu_table_get_index(smu, table_index);
 
-	if (!table_data || table_id >= smu_table->table_count || table_id < 0)
+	if (!table_data || table_id >= SMU_TABLE_COUNT || table_id < 0)
 		return -EINVAL;
 
 	table = &smu_table->tables[table_index];
@@ -463,7 +515,7 @@ int smu_update_table(struct smu_context *smu, enum smu_table_id table_index, int
 		return ret;
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	if (!drv2smu)
 		memcpy(table_data, table->cpu_addr, table->size);
@@ -483,7 +535,7 @@ bool is_support_sw_smu(struct amdgpu_device *adev)
 
 bool is_support_sw_smu_xgmi(struct amdgpu_device *adev)
 {
-	if (amdgpu_dpm != 1)
+	if (!is_support_sw_smu(adev))
 		return false;
 
 	if (adev->asic_type == CHIP_VEGA20)
@@ -495,16 +547,23 @@ bool is_support_sw_smu_xgmi(struct amdgpu_device *adev)
 int smu_sys_get_pp_table(struct smu_context *smu, void **table)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
+	uint32_t powerplay_table_size;
 
 	if (!smu_table->power_play_table && !smu_table->hardcode_pptable)
 		return -EINVAL;
 
+	mutex_lock(&smu->mutex);
+
 	if (smu_table->hardcode_pptable)
 		*table = smu_table->hardcode_pptable;
 	else
 		*table = smu_table->power_play_table;
 
-	return smu_table->power_play_table_size;
+	powerplay_table_size = smu_table->power_play_table_size;
+
+	mutex_unlock(&smu->mutex);
+
+	return powerplay_table_size;
 }
 
 int smu_sys_set_pp_table(struct smu_context *smu,  void *buf, size_t size)
@@ -531,13 +590,18 @@ int smu_sys_set_pp_table(struct smu_context *smu,  void *buf, size_t size)
 	memcpy(smu_table->hardcode_pptable, buf, size);
 	smu_table->power_play_table = smu_table->hardcode_pptable;
 	smu_table->power_play_table_size = size;
-	mutex_unlock(&smu->mutex);
+
+	/*
+	 * Special hw_fini action(for Navi1x, the DPMs disablement will be
+	 * skipped) may be needed for custom pptable uploading.
+	 */
+	smu->uploading_custom_pp_table = true;
 
 	ret = smu_reset(smu);
 	if (ret)
 		pr_info("smu reset failed, ret = %d\n", ret);
 
-	return ret;
+	smu->uploading_custom_pp_table = false;
 
 failed:
 	mutex_unlock(&smu->mutex);
@@ -569,41 +633,7 @@ int smu_feature_init_dpm(struct smu_context *smu)
 
 	return ret;
 }
-int smu_feature_update_enable_state(struct smu_context *smu, uint64_t feature_mask, bool enabled)
-{
-	uint32_t feature_low = 0, feature_high = 0;
-	int ret = 0;
-
-	if (!smu->pm_enabled)
-		return ret;
-
-	feature_low = (feature_mask >> 0 ) & 0xffffffff;
-	feature_high = (feature_mask >> 32) & 0xffffffff;
-
-	if (enabled) {
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnableSmuFeaturesLow,
-						  feature_low);
-		if (ret)
-			return ret;
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_EnableSmuFeaturesHigh,
-						  feature_high);
-		if (ret)
-			return ret;
 
-	} else {
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_DisableSmuFeaturesLow,
-						  feature_low);
-		if (ret)
-			return ret;
-		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_DisableSmuFeaturesHigh,
-						  feature_high);
-		if (ret)
-			return ret;
-
-	}
-
-	return ret;
-}
 
 int smu_feature_is_enabled(struct smu_context *smu, enum smu_feature_mask mask)
 {
@@ -633,8 +663,6 @@ int smu_feature_set_enabled(struct smu_context *smu, enum smu_feature_mask mask,
 {
 	struct smu_feature *feature = &smu->smu_feature;
 	int feature_id;
-	uint64_t feature_mask = 0;
-	int ret = 0;
 
 	feature_id = smu_feature_get_index(smu, mask);
 	if (feature_id < 0)
@@ -642,22 +670,9 @@ int smu_feature_set_enabled(struct smu_context *smu, enum smu_feature_mask mask,
 
 	WARN_ON(feature_id > feature->feature_num);
 
-	feature_mask = 1ULL << feature_id;
-
-	mutex_lock(&feature->mutex);
-	ret = smu_feature_update_enable_state(smu, feature_mask, enable);
-	if (ret)
-		goto failed;
-
-	if (enable)
-		test_and_set_bit(feature_id, feature->enabled);
-	else
-		test_and_clear_bit(feature_id, feature->enabled);
-
-failed:
-	mutex_unlock(&feature->mutex);
-
-	return ret;
+	return smu_feature_update_enable_state(smu,
+					       1ULL << feature_id,
+					       enable);
 }
 
 int smu_feature_is_supported(struct smu_context *smu, enum smu_feature_mask mask)
@@ -707,20 +722,27 @@ static int smu_set_funcs(struct amdgpu_device *adev)
 {
 	struct smu_context *smu = &adev->smu;
 
+	if (adev->pm.pp_feature & PP_OVERDRIVE_MASK)
+		smu->od_enabled = true;
+
 	switch (adev->asic_type) {
 	case CHIP_VEGA20:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		vega20_set_ppt_funcs(smu);
+		break;
 	case CHIP_NAVI10:
 	case CHIP_NAVI14:
 	case CHIP_NAVI12:
+		navi10_set_ppt_funcs(smu);
+		break;
 	case CHIP_ARCTURUS:
-		if (adev->pm.pp_feature & PP_OVERDRIVE_MASK)
-			smu->od_enabled = true;
-		smu_v11_0_set_smu_funcs(smu);
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
+		arcturus_set_ppt_funcs(smu);
+		/* OD is not supported on Arcturus */
+		smu->od_enabled =false;
 		break;
 	case CHIP_RENOIR:
-		if (adev->pm.pp_feature & PP_OVERDRIVE_MASK)
-			smu->od_enabled = true;
-		smu_v12_0_set_smu_funcs(smu);
+		renoir_set_ppt_funcs(smu);
 		break;
 	default:
 		return -EINVAL;
@@ -736,6 +758,7 @@ static int smu_early_init(void *handle)
 
 	smu->adev = adev;
 	smu->pm_enabled = !!amdgpu_dpm;
+	smu->is_apu = false;
 	mutex_init(&smu->mutex);
 
 	return smu_set_funcs(adev);
@@ -749,11 +772,10 @@ static int smu_late_init(void *handle)
 	if (!smu->pm_enabled)
 		return 0;
 
-	mutex_lock(&smu->mutex);
 	smu_handle_task(&adev->smu,
 			smu->smu_dpm.dpm_level,
-			AMD_PP_TASK_COMPLETE_INIT);
-	mutex_unlock(&smu->mutex);
+			AMD_PP_TASK_COMPLETE_INIT,
+			false);
 
 	return 0;
 }
@@ -919,14 +941,9 @@ static int smu_init_fb_allocations(struct smu_context *smu)
 	struct amdgpu_device *adev = smu->adev;
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
-	uint32_t table_count = smu_table->table_count;
-	uint32_t i = 0;
-	int32_t ret = 0;
+	int ret, i;
 
-	if (table_count <= 0)
-		return -EINVAL;
-
-	for (i = 0 ; i < table_count; i++) {
+	for (i = 0; i < SMU_TABLE_COUNT; i++) {
 		if (tables[i].size == 0)
 			continue;
 		ret = amdgpu_bo_create_kernel(adev,
@@ -942,7 +959,7 @@ static int smu_init_fb_allocations(struct smu_context *smu)
 
 	return 0;
 failed:
-	for (; i > 0; i--) {
+	while (--i >= 0) {
 		if (tables[i].size == 0)
 			continue;
 		amdgpu_bo_free_kernel(&tables[i].bo,
@@ -957,13 +974,12 @@ static int smu_fini_fb_allocations(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = smu_table->tables;
-	uint32_t table_count = smu_table->table_count;
 	uint32_t i = 0;
 
-	if (table_count == 0 || tables == NULL)
+	if (!tables)
 		return 0;
 
-	for (i = 0 ; i < table_count; i++) {
+	for (i = 0; i < SMU_TABLE_COUNT; i++) {
 		if (tables[i].size == 0)
 			continue;
 		amdgpu_bo_free_kernel(&tables[i].bo,
@@ -974,50 +990,6 @@ static int smu_fini_fb_allocations(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_override_pcie_parameters(struct smu_context *smu)
-{
-	struct amdgpu_device *adev = smu->adev;
-	uint32_t pcie_gen = 0, pcie_width = 0, smu_pcie_arg;
-	int ret;
-
-	if (adev->flags & AMD_IS_APU)
-		return 0;
-
-	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
-		pcie_gen = 3;
-	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
-		pcie_gen = 2;
-	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
-		pcie_gen = 1;
-	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1)
-		pcie_gen = 0;
-
-	/* Bit 31:16: LCLK DPM level. 0 is DPM0, and 1 is DPM1
-	 * Bit 15:8:  PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
-	 * Bit 7:0:   PCIE lane width, 1 to 7 corresponds is x1 to x32
-	 */
-	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
-		pcie_width = 6;
-	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
-		pcie_width = 5;
-	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
-		pcie_width = 4;
-	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
-		pcie_width = 3;
-	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
-		pcie_width = 2;
-	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
-		pcie_width = 1;
-
-	smu_pcie_arg = (1 << 16) | (pcie_gen << 8) | pcie_width;
-	ret = smu_send_smc_msg_with_param(smu,
-					  SMU_MSG_OverridePcieParameters,
-					  smu_pcie_arg);
-	if (ret)
-		pr_err("[%s] Attempt to override pcie params failed!\n", __func__);
-	return ret;
-}
-
 static int smu_smc_table_hw_init(struct smu_context *smu,
 				 bool initialize)
 {
@@ -1092,8 +1064,8 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 	if (ret)
 		return ret;
 
-	/* issue RunAfllBtc msg */
-	ret = smu_run_afll_btc(smu);
+	/* issue Run*Btc msg */
+	ret = smu_run_btc(smu);
 	if (ret)
 		return ret;
 
@@ -1106,10 +1078,6 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 		return ret;
 
 	if (adev->asic_type != CHIP_ARCTURUS) {
-		ret = smu_override_pcie_parameters(smu);
-		if (ret)
-			return ret;
-
 		ret = smu_notify_display_change(smu);
 		if (ret)
 			return ret;
@@ -1138,6 +1106,12 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 			return ret;
 	}
 
+	if (adev->asic_type != CHIP_ARCTURUS) {
+		ret = smu_override_pcie_parameters(smu);
+		if (ret)
+			return ret;
+	}
+
 	ret = smu_set_default_od_settings(smu, initialize);
 	if (ret)
 		return ret;
@@ -1147,7 +1121,7 @@ static int smu_smc_table_hw_init(struct smu_context *smu,
 		if (ret)
 			return ret;
 
-		ret = smu_get_power_limit(smu, &smu->default_power_limit, true);
+		ret = smu_get_power_limit(smu, &smu->default_power_limit, false, false);
 		if (ret)
 			return ret;
 	}
@@ -1226,29 +1200,46 @@ static int smu_free_memory_pool(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_hw_init(void *handle)
+static int smu_start_smc_engine(struct smu_context *smu)
 {
-	int ret;
-	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	struct smu_context *smu = &adev->smu;
+	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
 
 	if (adev->firmware.load_type != AMDGPU_FW_LOAD_PSP) {
 		if (adev->asic_type < CHIP_NAVI10) {
-			ret = smu_load_microcode(smu);
-			if (ret)
-				return ret;
+			if (smu->ppt_funcs->load_microcode) {
+				ret = smu->ppt_funcs->load_microcode(smu);
+				if (ret)
+					return ret;
+			}
 		}
 	}
 
-	ret = smu_check_fw_status(smu);
+	if (smu->ppt_funcs->check_fw_status) {
+		ret = smu->ppt_funcs->check_fw_status(smu);
+		if (ret)
+			pr_err("SMC is not ready\n");
+	}
+
+	return ret;
+}
+
+static int smu_hw_init(void *handle)
+{
+	int ret;
+	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+	struct smu_context *smu = &adev->smu;
+
+	ret = smu_start_smc_engine(smu);
 	if (ret) {
-		pr_err("SMC firmware status is not correct\n");
+		pr_err("SMU is not ready yet!\n");
 		return ret;
 	}
 
 	if (adev->flags & AMD_IS_APU) {
 		smu_powergate_sdma(&adev->smu, false);
 		smu_powergate_vcn(&adev->smu, false);
+		smu_set_gfx_cgpg(&adev->smu, true);
 	}
 
 	if (!smu->pm_enabled)
@@ -1291,6 +1282,11 @@ failed:
 	return ret;
 }
 
+static int smu_stop_dpms(struct smu_context *smu)
+{
+	return smu_send_smc_msg(smu, SMU_MSG_DisableAllSmuFeatures);
+}
+
 static int smu_hw_fini(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -1303,6 +1299,33 @@ static int smu_hw_fini(void *handle)
 		smu_powergate_vcn(&adev->smu, true);
 	}
 
+	ret = smu_stop_thermal_control(smu);
+	if (ret) {
+		pr_warn("Fail to stop thermal control!\n");
+		return ret;
+	}
+
+	/*
+	 * For custom pptable uploading, skip the DPM features
+	 * disable process on Navi1x ASICs.
+	 *   - As the gfx related features are under control of
+	 *     RLC on those ASICs. RLC reinitialization will be
+	 *     needed to reenable them. That will cost much more
+	 *     efforts.
+	 *
+	 *   - SMU firmware can handle the DPM reenablement
+	 *     properly.
+	 */
+	if (!smu->uploading_custom_pp_table ||
+	    !((adev->asic_type >= CHIP_NAVI10) &&
+	      (adev->asic_type <= CHIP_NAVI12))) {
+		ret = smu_stop_dpms(smu);
+		if (ret) {
+			pr_warn("Fail to stop Dpms!\n");
+			return ret;
+		}
+	}
+
 	kfree(table_context->driver_pptable);
 	table_context->driver_pptable = NULL;
 
@@ -1344,7 +1367,10 @@ static int smu_suspend(void *handle)
 	int ret;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 	struct smu_context *smu = &adev->smu;
-	bool baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT);
+	bool baco_feature_is_enabled = false;
+
+	if(!(adev->flags & AMD_IS_APU))
+		baco_feature_is_enabled = smu_feature_is_enabled(smu, SMU_FEATURE_BACO_BIT);
 
 	ret = smu_system_features_control(smu, false);
 	if (ret)
@@ -1363,6 +1389,8 @@ static int smu_suspend(void *handle)
 	if (adev->asic_type >= CHIP_NAVI10 &&
 	    adev->gfx.rlc.funcs->stop)
 		adev->gfx.rlc.funcs->stop(adev);
+	if (smu->is_apu)
+		smu_set_gfx_cgpg(&adev->smu, false);
 
 	return 0;
 }
@@ -1375,7 +1403,11 @@ static int smu_resume(void *handle)
 
 	pr_info("SMU is resuming...\n");
 
-	mutex_lock(&smu->mutex);
+	ret = smu_start_smc_engine(smu);
+	if (ret) {
+		pr_err("SMU is not ready yet!\n");
+		goto failed;
+	}
 
 	ret = smu_smc_table_hw_init(smu, false);
 	if (ret)
@@ -1385,13 +1417,16 @@ static int smu_resume(void *handle)
 	if (ret)
 		goto failed;
 
-	mutex_unlock(&smu->mutex);
+	if (smu->is_apu)
+		smu_set_gfx_cgpg(&adev->smu, true);
+
+	smu->disable_uclk_switch = 0;
 
 	pr_info("SMU is resumed successfully!\n");
 
 	return 0;
+
 failed:
-	mutex_unlock(&smu->mutex);
 	return ret;
 }
 
@@ -1409,8 +1444,9 @@ int smu_display_configuration_change(struct smu_context *smu,
 
 	mutex_lock(&smu->mutex);
 
-	smu_set_deep_sleep_dcefclk(smu,
-				   display_config->min_dcef_deep_sleep_set_clk / 100);
+	if (smu->ppt_funcs->set_deep_sleep_dcefclk)
+		smu->ppt_funcs->set_deep_sleep_dcefclk(smu,
+				display_config->min_dcef_deep_sleep_set_clk / 100);
 
 	for (index = 0; index < display_config->num_path_including_non_display; index++) {
 		if (display_config->displays[index].controller_id != 0)
@@ -1529,7 +1565,8 @@ static int smu_enable_umd_pstate(void *handle,
 
 	struct smu_context *smu = (struct smu_context*)(handle);
 	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
-	if (!smu->pm_enabled || !smu_dpm_ctx->dpm_context)
+
+	if (!smu->is_apu && (!smu->pm_enabled || !smu_dpm_ctx->dpm_context))
 		return -EINVAL;
 
 	if (!(smu_dpm_ctx->dpm_level & profile_mode_mask)) {
@@ -1587,9 +1624,9 @@ static int smu_default_set_performance_level(struct smu_context *smu, enum amd_d
 						 &soc_mask);
 		if (ret)
 			return ret;
-		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask);
-		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask);
-		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask);
+		smu_force_clk_levels(smu, SMU_SCLK, 1 << sclk_mask, false);
+		smu_force_clk_levels(smu, SMU_MCLK, 1 << mclk_mask, false);
+		smu_force_clk_levels(smu, SMU_SOCCLK, 1 << soc_mask, false);
 		break;
 	case AMD_DPM_FORCED_LEVEL_MANUAL:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
@@ -1653,7 +1690,7 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu,
 		workload = smu->workload_setting[index];
 
 		if (smu->power_profile_mode != workload)
-			smu_set_power_profile_mode(smu, &workload, 0);
+			smu_set_power_profile_mode(smu, &workload, 0, false);
 	}
 
 	return ret;
@@ -1661,18 +1698,22 @@ int smu_adjust_power_state_dynamic(struct smu_context *smu,
 
 int smu_handle_task(struct smu_context *smu,
 		    enum amd_dpm_forced_level level,
-		    enum amd_pp_task task_id)
+		    enum amd_pp_task task_id,
+		    bool lock_needed)
 {
 	int ret = 0;
 
+	if (lock_needed)
+		mutex_lock(&smu->mutex);
+
 	switch (task_id) {
 	case AMD_PP_TASK_DISPLAY_CONFIG_CHANGE:
 		ret = smu_pre_display_config_changed(smu);
 		if (ret)
-			return ret;
+			goto out;
 		ret = smu_set_cpu_power_state(smu);
 		if (ret)
-			return ret;
+			goto out;
 		ret = smu_adjust_power_state_dynamic(smu, level, false);
 		break;
 	case AMD_PP_TASK_COMPLETE_INIT:
@@ -1683,6 +1724,10 @@ int smu_handle_task(struct smu_context *smu,
 		break;
 	}
 
+out:
+	if (lock_needed)
+		mutex_unlock(&smu->mutex);
+
 	return ret;
 }
 
@@ -1715,7 +1760,7 @@ int smu_switch_power_profile(struct smu_context *smu,
 	}
 
 	if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL)
-		smu_set_power_profile_mode(smu, &workload, 0);
+		smu_set_power_profile_mode(smu, &workload, 0, false);
 
 	mutex_unlock(&smu->mutex);
 
@@ -1727,7 +1772,7 @@ enum amd_dpm_forced_level smu_get_performance_level(struct smu_context *smu)
 	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
 	enum amd_dpm_forced_level level;
 
-	if (!smu_dpm_ctx->dpm_context)
+	if (!smu->is_apu && !smu_dpm_ctx->dpm_context)
 		return -EINVAL;
 
 	mutex_lock(&(smu->mutex));
@@ -1742,15 +1787,22 @@ int smu_force_performance_level(struct smu_context *smu, enum amd_dpm_forced_lev
 	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
 	int ret = 0;
 
-	if (!smu_dpm_ctx->dpm_context)
+	if (!smu->is_apu && !smu_dpm_ctx->dpm_context)
 		return -EINVAL;
 
+	mutex_lock(&smu->mutex);
+
 	ret = smu_enable_umd_pstate(smu, &level);
-	if (ret)
+	if (ret) {
+		mutex_unlock(&smu->mutex);
 		return ret;
+	}
 
 	ret = smu_handle_task(smu, level,
-			      AMD_PP_TASK_READJUST_POWER_STATE);
+			      AMD_PP_TASK_READJUST_POWER_STATE,
+			      false);
+
+	mutex_unlock(&smu->mutex);
 
 	return ret;
 }
@@ -1766,6 +1818,144 @@ int smu_set_display_count(struct smu_context *smu, uint32_t count)
 	return ret;
 }
 
+int smu_force_clk_levels(struct smu_context *smu,
+			 enum smu_clk_type clk_type,
+			 uint32_t mask,
+			 bool lock_needed)
+{
+	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+	int ret = 0;
+
+	if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) {
+		pr_debug("force clock level is for dpm manual mode only.\n");
+		return -EINVAL;
+	}
+
+	if (lock_needed)
+		mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs && smu->ppt_funcs->force_clk_levels)
+		ret = smu->ppt_funcs->force_clk_levels(smu, clk_type, mask);
+
+	if (lock_needed)
+		mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_mp1_state(struct smu_context *smu,
+		      enum pp_mp1_state mp1_state)
+{
+	uint16_t msg;
+	int ret;
+
+	/*
+	 * The SMC is not fully ready. That may be
+	 * expected as the IP may be masked.
+	 * So, just return without error.
+	 */
+	if (!smu->pm_enabled)
+		return 0;
+
+	mutex_lock(&smu->mutex);
+
+	switch (mp1_state) {
+	case PP_MP1_STATE_SHUTDOWN:
+		msg = SMU_MSG_PrepareMp1ForShutdown;
+		break;
+	case PP_MP1_STATE_UNLOAD:
+		msg = SMU_MSG_PrepareMp1ForUnload;
+		break;
+	case PP_MP1_STATE_RESET:
+		msg = SMU_MSG_PrepareMp1ForReset;
+		break;
+	case PP_MP1_STATE_NONE:
+	default:
+		mutex_unlock(&smu->mutex);
+		return 0;
+	}
+
+	/* some asics may not support those messages */
+	if (smu_msg_get_index(smu, msg) < 0) {
+		mutex_unlock(&smu->mutex);
+		return 0;
+	}
+
+	ret = smu_send_smc_msg(smu, msg);
+	if (ret)
+		pr_err("[PrepareMp1] Failed!\n");
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_df_cstate(struct smu_context *smu,
+		      enum pp_df_cstate state)
+{
+	int ret = 0;
+
+	/*
+	 * The SMC is not fully ready. That may be
+	 * expected as the IP may be masked.
+	 * So, just return without error.
+	 */
+	if (!smu->pm_enabled)
+		return 0;
+
+	if (!smu->ppt_funcs || !smu->ppt_funcs->set_df_cstate)
+		return 0;
+
+	mutex_lock(&smu->mutex);
+
+	ret = smu->ppt_funcs->set_df_cstate(smu, state);
+	if (ret)
+		pr_err("[SetDfCstate] failed!\n");
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_write_watermarks_table(struct smu_context *smu)
+{
+	int ret = 0;
+	struct smu_table_context *smu_table = &smu->smu_table;
+	struct smu_table *table = NULL;
+
+	table = &smu_table->tables[SMU_TABLE_WATERMARKS];
+
+	if (!table->cpu_addr)
+		return -EINVAL;
+
+	ret = smu_update_table(smu, SMU_TABLE_WATERMARKS, 0, table->cpu_addr,
+				true);
+
+	return ret;
+}
+
+int smu_set_watermarks_for_clock_ranges(struct smu_context *smu,
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
+{
+	int ret = 0;
+	struct smu_table *watermarks = &smu->smu_table.tables[SMU_TABLE_WATERMARKS];
+	void *table = watermarks->cpu_addr;
+
+	mutex_lock(&smu->mutex);
+
+	if (!smu->disable_watermark &&
+			smu_feature_is_enabled(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) &&
+			smu_feature_is_enabled(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) {
+		smu_set_watermarks_table(smu, table, clock_ranges);
+		smu->watermarks_bitmap |= WATERMARKS_EXIST;
+		smu->watermarks_bitmap &= ~WATERMARKS_LOADED;
+	}
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
 const struct amd_ip_funcs smu_ip_funcs = {
 	.name = "smu",
 	.early_init = smu_early_init,
@@ -1802,3 +1992,568 @@ const struct amdgpu_ip_block_version smu_v12_0_ip_block =
 	.rev = 0,
 	.funcs = &smu_ip_funcs,
 };
+
+int smu_load_microcode(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->load_microcode)
+		ret = smu->ppt_funcs->load_microcode(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_check_fw_status(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->check_fw_status)
+		ret = smu->ppt_funcs->check_fw_status(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_gfx_cgpg)
+		ret = smu->ppt_funcs->set_gfx_cgpg(smu, enabled);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_fan_speed_rpm)
+		ret = smu->ppt_funcs->set_fan_speed_rpm(smu, speed);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_power_limit(struct smu_context *smu,
+			uint32_t *limit,
+			bool def,
+			bool lock_needed)
+{
+	int ret = 0;
+
+	if (lock_needed)
+		mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_power_limit)
+		ret = smu->ppt_funcs->get_power_limit(smu, limit, def);
+
+	if (lock_needed)
+		mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_power_limit(struct smu_context *smu, uint32_t limit)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_power_limit)
+		ret = smu->ppt_funcs->set_power_limit(smu, limit);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->print_clk_levels)
+		ret = smu->ppt_funcs->print_clk_levels(smu, clk_type, buf);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_od_percentage(struct smu_context *smu, enum smu_clk_type type)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_od_percentage)
+		ret = smu->ppt_funcs->get_od_percentage(smu, type);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_od_percentage(struct smu_context *smu, enum smu_clk_type type, uint32_t value)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_od_percentage)
+		ret = smu->ppt_funcs->set_od_percentage(smu, type, value);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_od_edit_dpm_table(struct smu_context *smu,
+			  enum PP_OD_DPM_TABLE_COMMAND type,
+			  long *input, uint32_t size)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->od_edit_dpm_table)
+		ret = smu->ppt_funcs->od_edit_dpm_table(smu, type, input, size);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_read_sensor(struct smu_context *smu,
+		    enum amd_pp_sensors sensor,
+		    void *data, uint32_t *size)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->read_sensor)
+		ret = smu->ppt_funcs->read_sensor(smu, sensor, data, size);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_power_profile_mode(struct smu_context *smu, char *buf)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_power_profile_mode)
+		ret = smu->ppt_funcs->get_power_profile_mode(smu, buf);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_power_profile_mode(struct smu_context *smu,
+			       long *param,
+			       uint32_t param_size,
+			       bool lock_needed)
+{
+	int ret = 0;
+
+	if (lock_needed)
+		mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_power_profile_mode)
+		ret = smu->ppt_funcs->set_power_profile_mode(smu, param, param_size);
+
+	if (lock_needed)
+		mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+
+int smu_get_fan_control_mode(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_fan_control_mode)
+		ret = smu->ppt_funcs->get_fan_control_mode(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_fan_control_mode(struct smu_context *smu, int value)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_fan_control_mode)
+		ret = smu->ppt_funcs->set_fan_control_mode(smu, value);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_fan_speed_percent)
+		ret = smu->ppt_funcs->get_fan_speed_percent(smu, speed);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_fan_speed_percent)
+		ret = smu->ppt_funcs->set_fan_speed_percent(smu, speed);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_fan_speed_rpm(struct smu_context *smu, uint32_t *speed)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_fan_speed_rpm)
+		ret = smu->ppt_funcs->get_fan_speed_rpm(smu, speed);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_deep_sleep_dcefclk)
+		ret = smu->ppt_funcs->set_deep_sleep_dcefclk(smu, clk);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_active_display_count(struct smu_context *smu, uint32_t count)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_active_display_count)
+		ret = smu->ppt_funcs->set_active_display_count(smu, count);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_clock_by_type(struct smu_context *smu,
+			  enum amd_pp_clock_type type,
+			  struct amd_pp_clocks *clocks)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_clock_by_type)
+		ret = smu->ppt_funcs->get_clock_by_type(smu, type, clocks);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_max_high_clocks(struct smu_context *smu,
+			    struct amd_pp_simple_clock_info *clocks)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_max_high_clocks)
+		ret = smu->ppt_funcs->get_max_high_clocks(smu, clocks);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_clock_by_type_with_latency(struct smu_context *smu,
+				       enum smu_clk_type clk_type,
+				       struct pp_clock_levels_with_latency *clocks)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_clock_by_type_with_latency)
+		ret = smu->ppt_funcs->get_clock_by_type_with_latency(smu, clk_type, clocks);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_clock_by_type_with_voltage(struct smu_context *smu,
+				       enum amd_pp_clock_type type,
+				       struct pp_clock_levels_with_voltage *clocks)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_clock_by_type_with_voltage)
+		ret = smu->ppt_funcs->get_clock_by_type_with_voltage(smu, type, clocks);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+
+int smu_display_clock_voltage_request(struct smu_context *smu,
+				      struct pp_display_clock_request *clock_req)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->display_clock_voltage_request)
+		ret = smu->ppt_funcs->display_clock_voltage_request(smu, clock_req);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+
+int smu_display_disable_memory_clock_switch(struct smu_context *smu, bool disable_memory_clock_switch)
+{
+	int ret = -EINVAL;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->display_disable_memory_clock_switch)
+		ret = smu->ppt_funcs->display_disable_memory_clock_switch(smu, disable_memory_clock_switch);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_notify_smu_enable_pwe(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->notify_smu_enable_pwe)
+		ret = smu->ppt_funcs->notify_smu_enable_pwe(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_xgmi_pstate(struct smu_context *smu,
+			uint32_t pstate)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_xgmi_pstate)
+		ret = smu->ppt_funcs->set_xgmi_pstate(smu, pstate);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_set_azalia_d3_pme(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->set_azalia_d3_pme)
+		ret = smu->ppt_funcs->set_azalia_d3_pme(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+bool smu_baco_is_support(struct smu_context *smu)
+{
+	bool ret = false;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->baco_is_support)
+		ret = smu->ppt_funcs->baco_is_support(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state)
+{
+	if (smu->ppt_funcs->baco_get_state)
+		return -EINVAL;
+
+	mutex_lock(&smu->mutex);
+	*state = smu->ppt_funcs->baco_get_state(smu);
+	mutex_unlock(&smu->mutex);
+
+	return 0;
+}
+
+int smu_baco_reset(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->baco_reset)
+		ret = smu->ppt_funcs->baco_reset(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_mode2_reset(struct smu_context *smu)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->mode2_reset)
+		ret = smu->ppt_funcs->mode2_reset(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
+					 struct pp_smu_nv_clock_table *max_clocks)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_max_sustainable_clocks_by_dc)
+		ret = smu->ppt_funcs->get_max_sustainable_clocks_by_dc(smu, max_clocks);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+int smu_get_uclk_dpm_states(struct smu_context *smu,
+			    unsigned int *clock_values_in_khz,
+			    unsigned int *num_states)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_uclk_dpm_states)
+		ret = smu->ppt_funcs->get_uclk_dpm_states(smu, clock_values_in_khz, num_states);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+enum amd_pm_state_type smu_get_current_power_state(struct smu_context *smu)
+{
+	enum amd_pm_state_type pm_state = POWER_STATE_TYPE_DEFAULT;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_current_power_state)
+		pm_state = smu->ppt_funcs->get_current_power_state(smu);
+
+	mutex_unlock(&smu->mutex);
+
+	return pm_state;
+}
+
+int smu_get_dpm_clock_table(struct smu_context *smu,
+			    struct dpm_clocks *clock_table)
+{
+	int ret = 0;
+
+	mutex_lock(&smu->mutex);
+
+	if (smu->ppt_funcs->get_dpm_clock_table)
+		ret = smu->ppt_funcs->get_dpm_clock_table(smu, clock_table);
+
+	mutex_unlock(&smu->mutex);
+
+	return ret;
+}
+
+uint32_t smu_get_pptable_power_limit(struct smu_context *smu)
+{
+	uint32_t ret = 0;
+
+	if (smu->ppt_funcs->get_pptable_power_limit)
+		ret = smu->ppt_funcs->get_pptable_power_limit(smu);
+
+	return ret;
+}
+
+int smu_send_smc_msg(struct smu_context *smu,
+		     enum smu_message_type msg)
+{
+	int ret;
+
+	ret = smu_send_smc_msg_with_param(smu, msg, 0);
+	return ret;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
index d493a3f8c07a..ce3566ca3e24 100644
--- a/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/arcturus_ppt.c
@@ -25,6 +25,7 @@
 #include <linux/firmware.h>
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "atomfirmware.h"
 #include "amdgpu_atomfirmware.h"
 #include "smu_v11_0.h"
@@ -36,6 +37,12 @@
 #include "smu_v11_0_pptable.h"
 #include "arcturus_ppsmc.h"
 #include "nbio/nbio_7_4_sh_mask.h"
+#include "amdgpu_xgmi.h"
+#include <linux/i2c.h>
+#include <linux/pci.h>
+#include "amdgpu_ras.h"
+
+#define to_amdgpu_device(x) (container_of(x, struct amdgpu_ras, eeprom_control.eeprom_accessor))->adev
 
 #define CTF_OFFSET_EDGE			5
 #define CTF_OFFSET_HOTSPOT		5
@@ -112,8 +119,7 @@ static struct smu_11_0_cmn2aisc_mapping arcturus_message_map[SMU_MSG_MAX_COUNT]
 	MSG_MAP(PrepareMp1ForShutdown,		     PPSMC_MSG_PrepareMp1ForShutdown),
 	MSG_MAP(SoftReset,			     PPSMC_MSG_SoftReset),
 	MSG_MAP(RunAfllBtc,			     PPSMC_MSG_RunAfllBtc),
-	MSG_MAP(RunGfxDcBtc,			     PPSMC_MSG_RunGfxDcBtc),
-	MSG_MAP(RunSocDcBtc,			     PPSMC_MSG_RunSocDcBtc),
+	MSG_MAP(RunDcBtc,			     PPSMC_MSG_RunDcBtc),
 	MSG_MAP(DramLogSetDramAddrHigh,		     PPSMC_MSG_DramLogSetDramAddrHigh),
 	MSG_MAP(DramLogSetDramAddrLow,		     PPSMC_MSG_DramLogSetDramAddrLow),
 	MSG_MAP(DramLogSetDramSize,		     PPSMC_MSG_DramLogSetDramSize),
@@ -172,6 +178,7 @@ static struct smu_11_0_cmn2aisc_mapping arcturus_table_map[SMU_TABLE_COUNT] = {
 	TAB_MAP(SMU_METRICS),
 	TAB_MAP(DRIVER_SMU_CONFIG),
 	TAB_MAP(OVERDRIVE),
+	TAB_MAP(I2C_COMMANDS),
 };
 
 static struct smu_11_0_cmn2aisc_mapping arcturus_pwr_src_map[SMU_POWER_SOURCE_COUNT] = {
@@ -294,6 +301,9 @@ static int arcturus_tables_init(struct smu_context *smu, struct smu_table *table
 	SMU_TABLE_INIT(tables, SMU_TABLE_SMU_METRICS, sizeof(SmuMetrics_t),
 		       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
 
+	SMU_TABLE_INIT(tables, SMU_TABLE_I2C_COMMANDS, sizeof(SwI2cRequest_t),
+			       PAGE_SIZE, AMDGPU_GEM_DOMAIN_VRAM);
+
 	smu_table->metrics_table = kzalloc(sizeof(SmuMetrics_t), GFP_KERNEL);
 	if (!smu_table->metrics_table)
 		return -ENOMEM;
@@ -528,9 +538,17 @@ static int arcturus_append_powerplay_table(struct smu_context *smu)
 	return 0;
 }
 
-static int arcturus_run_btc_afll(struct smu_context *smu)
+static int arcturus_run_btc(struct smu_context *smu)
 {
-	return smu_send_smc_msg(smu, SMU_MSG_RunAfllBtc);
+	int ret = 0;
+
+	ret = smu_send_smc_msg(smu, SMU_MSG_RunAfllBtc);
+	if (ret) {
+		pr_err("RunAfllBtc failed!\n");
+		return ret;
+	}
+
+	return smu_send_smc_msg(smu, SMU_MSG_RunDcBtc);
 }
 
 static int arcturus_populate_umd_state_clk(struct smu_context *smu)
@@ -610,12 +628,17 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 			return ret;
 		}
 
+		/*
+		 * For DPM disabled case, there will be only one clock level.
+		 * And it's safe to assume that is always the current clock.
+		 */
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n", i,
 					clocks.data[i].clocks_in_khz / 1000,
-					arcturus_freqs_in_same_level(
+					(clocks.num_levels == 1) ? "*" :
+					(arcturus_freqs_in_same_level(
 					clocks.data[i].clocks_in_khz / 1000,
-					now / 100) ? "*" : "");
+					now / 100) ? "*" : ""));
 		break;
 
 	case SMU_MCLK:
@@ -635,9 +658,10 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
-				arcturus_freqs_in_same_level(
+				(clocks.num_levels == 1) ? "*" :
+				(arcturus_freqs_in_same_level(
 				clocks.data[i].clocks_in_khz / 1000,
-				now / 100) ? "*" : "");
+				now / 100) ? "*" : ""));
 		break;
 
 	case SMU_SOCCLK:
@@ -657,9 +681,10 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
-				arcturus_freqs_in_same_level(
+				(clocks.num_levels == 1) ? "*" :
+				(arcturus_freqs_in_same_level(
 				clocks.data[i].clocks_in_khz / 1000,
-				now / 100) ? "*" : "");
+				now / 100) ? "*" : ""));
 		break;
 
 	case SMU_FCLK:
@@ -679,9 +704,10 @@ static int arcturus_print_clk_levels(struct smu_context *smu,
 		for (i = 0; i < single_dpm_table->count; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, single_dpm_table->dpm_levels[i].value,
-				arcturus_freqs_in_same_level(
+				(clocks.num_levels == 1) ? "*" :
+				(arcturus_freqs_in_same_level(
 				clocks.data[i].clocks_in_khz / 1000,
-				now / 100) ? "*" : "");
+				now / 100) ? "*" : ""));
 		break;
 
 	default:
@@ -756,8 +782,6 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
 	uint32_t soft_min_level, soft_max_level;
 	int ret = 0;
 
-	mutex_lock(&(smu->mutex));
-
 	soft_min_level = mask ? (ffs(mask) - 1) : 0;
 	soft_max_level = mask ? (fls(mask) - 1) : 0;
 
@@ -792,91 +816,19 @@ static int arcturus_force_clk_levels(struct smu_context *smu,
 		break;
 
 	case SMU_MCLK:
-		single_dpm_table = &(dpm_table->mem_table);
-
-		if (soft_max_level >= single_dpm_table->count) {
-			pr_err("Clock level specified %d is over max allowed %d\n",
-					soft_max_level, single_dpm_table->count - 1);
-			ret = -EINVAL;
-			break;
-		}
-
-		single_dpm_table->dpm_state.soft_min_level =
-			single_dpm_table->dpm_levels[soft_min_level].value;
-		single_dpm_table->dpm_state.soft_max_level =
-			single_dpm_table->dpm_levels[soft_max_level].value;
-
-		ret = arcturus_upload_dpm_level(smu, false, FEATURE_DPM_UCLK_MASK);
-		if (ret) {
-			pr_err("Failed to upload boot level to lowest!\n");
-			break;
-		}
-
-		ret = arcturus_upload_dpm_level(smu, true, FEATURE_DPM_UCLK_MASK);
-		if (ret)
-			pr_err("Failed to upload dpm max level to highest!\n");
-
-		break;
-
 	case SMU_SOCCLK:
-		single_dpm_table = &(dpm_table->soc_table);
-
-		if (soft_max_level >= single_dpm_table->count) {
-			pr_err("Clock level specified %d is over max allowed %d\n",
-					soft_max_level, single_dpm_table->count - 1);
-			ret = -EINVAL;
-			break;
-		}
-
-		single_dpm_table->dpm_state.soft_min_level =
-			single_dpm_table->dpm_levels[soft_min_level].value;
-		single_dpm_table->dpm_state.soft_max_level =
-			single_dpm_table->dpm_levels[soft_max_level].value;
-
-		ret = arcturus_upload_dpm_level(smu, false, FEATURE_DPM_SOCCLK_MASK);
-		if (ret) {
-			pr_err("Failed to upload boot level to lowest!\n");
-			break;
-		}
-
-		ret = arcturus_upload_dpm_level(smu, true, FEATURE_DPM_SOCCLK_MASK);
-		if (ret)
-			pr_err("Failed to upload dpm max level to highest!\n");
-
-		break;
-
 	case SMU_FCLK:
-		single_dpm_table = &(dpm_table->fclk_table);
-
-		if (soft_max_level >= single_dpm_table->count) {
-			pr_err("Clock level specified %d is over max allowed %d\n",
-					soft_max_level, single_dpm_table->count - 1);
-			ret = -EINVAL;
-			break;
-		}
-
-		single_dpm_table->dpm_state.soft_min_level =
-			single_dpm_table->dpm_levels[soft_min_level].value;
-		single_dpm_table->dpm_state.soft_max_level =
-			single_dpm_table->dpm_levels[soft_max_level].value;
-
-		ret = arcturus_upload_dpm_level(smu, false, FEATURE_DPM_FCLK_MASK);
-		if (ret) {
-			pr_err("Failed to upload boot level to lowest!\n");
-			break;
-		}
-
-		ret = arcturus_upload_dpm_level(smu, true, FEATURE_DPM_FCLK_MASK);
-		if (ret)
-			pr_err("Failed to upload dpm max level to highest!\n");
-
+		/*
+		 * Should not arrive here since Arcturus does not
+		 * support mclk/socclk/fclk softmin/softmax settings
+		 */
+		ret = -EINVAL;
 		break;
 
 	default:
 		break;
 	}
 
-	mutex_unlock(&(smu->mutex));
 	return ret;
 }
 
@@ -1043,7 +995,7 @@ static int arcturus_read_sensor(struct smu_context *smu,
 		*size = 4;
 		break;
 	default:
-		ret = smu_smc_read_sensor(smu, sensor, data, size);
+		ret = smu_v11_0_read_sensor(smu, sensor, data, size);
 	}
 	mutex_unlock(&smu->sensor_lock);
 
@@ -1186,6 +1138,7 @@ static int arcturus_force_dpm_limit_value(struct smu_context *smu, bool highest)
 {
 	struct arcturus_dpm_table *dpm_table =
 		(struct arcturus_dpm_table *)smu->smu_dpm.dpm_context;
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(smu->adev, 0);
 	uint32_t soft_level;
 	int ret = 0;
 
@@ -1199,40 +1152,27 @@ static int arcturus_force_dpm_limit_value(struct smu_context *smu, bool highest)
 		dpm_table->gfx_table.dpm_state.soft_max_level =
 		dpm_table->gfx_table.dpm_levels[soft_level].value;
 
-	/* uclk */
-	if (highest)
-		soft_level = arcturus_find_highest_dpm_level(&(dpm_table->mem_table));
-	else
-		soft_level = arcturus_find_lowest_dpm_level(&(dpm_table->mem_table));
-
-	dpm_table->mem_table.dpm_state.soft_min_level =
-		dpm_table->mem_table.dpm_state.soft_max_level =
-		dpm_table->mem_table.dpm_levels[soft_level].value;
-
-	/* socclk */
-	if (highest)
-		soft_level = arcturus_find_highest_dpm_level(&(dpm_table->soc_table));
-	else
-		soft_level = arcturus_find_lowest_dpm_level(&(dpm_table->soc_table));
-
-	dpm_table->soc_table.dpm_state.soft_min_level =
-		dpm_table->soc_table.dpm_state.soft_max_level =
-		dpm_table->soc_table.dpm_levels[soft_level].value;
-
-	ret = arcturus_upload_dpm_level(smu, false, 0xFFFFFFFF);
+	ret = arcturus_upload_dpm_level(smu, false, FEATURE_DPM_GFXCLK_MASK);
 	if (ret) {
 		pr_err("Failed to upload boot level to %s!\n",
 				highest ? "highest" : "lowest");
 		return ret;
 	}
 
-	ret = arcturus_upload_dpm_level(smu, true, 0xFFFFFFFF);
+	ret = arcturus_upload_dpm_level(smu, true, FEATURE_DPM_GFXCLK_MASK);
 	if (ret) {
 		pr_err("Failed to upload dpm max level to %s!\n!",
 				highest ? "highest" : "lowest");
 		return ret;
 	}
 
+	if (hive)
+		/*
+		 * Force XGMI Pstate to highest or lowest
+		 * TODO: revise this when xgmi dpm is functional
+		 */
+		ret = smu_v11_0_set_xgmi_pstate(smu, highest ? 1 : 0);
+
 	return ret;
 }
 
@@ -1240,6 +1180,7 @@ static int arcturus_unforce_dpm_levels(struct smu_context *smu)
 {
 	struct arcturus_dpm_table *dpm_table =
 		(struct arcturus_dpm_table *)smu->smu_dpm.dpm_context;
+	struct amdgpu_hive_info *hive = amdgpu_get_xgmi_hive(smu->adev, 0);
 	uint32_t soft_min_level, soft_max_level;
 	int ret = 0;
 
@@ -1251,34 +1192,25 @@ static int arcturus_unforce_dpm_levels(struct smu_context *smu)
 	dpm_table->gfx_table.dpm_state.soft_max_level =
 		dpm_table->gfx_table.dpm_levels[soft_max_level].value;
 
-	/* uclk */
-	soft_min_level = arcturus_find_lowest_dpm_level(&(dpm_table->mem_table));
-	soft_max_level = arcturus_find_highest_dpm_level(&(dpm_table->mem_table));
-	dpm_table->mem_table.dpm_state.soft_min_level =
-		dpm_table->gfx_table.dpm_levels[soft_min_level].value;
-	dpm_table->mem_table.dpm_state.soft_max_level =
-		dpm_table->gfx_table.dpm_levels[soft_max_level].value;
-
-	/* socclk */
-	soft_min_level = arcturus_find_lowest_dpm_level(&(dpm_table->soc_table));
-	soft_max_level = arcturus_find_highest_dpm_level(&(dpm_table->soc_table));
-	dpm_table->soc_table.dpm_state.soft_min_level =
-		dpm_table->soc_table.dpm_levels[soft_min_level].value;
-	dpm_table->soc_table.dpm_state.soft_max_level =
-		dpm_table->soc_table.dpm_levels[soft_max_level].value;
-
-	ret = arcturus_upload_dpm_level(smu, false, 0xFFFFFFFF);
+	ret = arcturus_upload_dpm_level(smu, false, FEATURE_DPM_GFXCLK_MASK);
 	if (ret) {
 		pr_err("Failed to upload DPM Bootup Levels!");
 		return ret;
 	}
 
-	ret = arcturus_upload_dpm_level(smu, true, 0xFFFFFFFF);
+	ret = arcturus_upload_dpm_level(smu, true, FEATURE_DPM_GFXCLK_MASK);
 	if (ret) {
 		pr_err("Failed to upload DPM Max Levels!");
 		return ret;
 	}
 
+	if (hive)
+		/*
+		 * Reset XGMI Pstate back to default
+		 * TODO: revise this when xgmi dpm is functional
+		 */
+		ret = smu_v11_0_set_xgmi_pstate(smu, 0);
+
 	return ret;
 }
 
@@ -1329,15 +1261,14 @@ arcturus_get_profiling_clk_mask(struct smu_context *smu,
 
 static int arcturus_get_power_limit(struct smu_context *smu,
 				     uint32_t *limit,
-				     bool asic_default)
+				     bool cap)
 {
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	uint32_t asic_default_power_limit = 0;
 	int ret = 0;
 	int power_src;
 
-	if (!smu->default_power_limit ||
-	    !smu->power_limit) {
+	if (!smu->power_limit) {
 		if (smu_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) {
 			power_src = smu_power_get_index(smu, SMU_POWER_SOURCE_AC);
 			if (power_src < 0)
@@ -1360,17 +1291,11 @@ static int arcturus_get_power_limit(struct smu_context *smu,
 				pptable->SocketPowerLimitAc[PPT_THROTTLER_PPT0];
 		}
 
-		if (smu->od_enabled) {
-			asic_default_power_limit *= (100 + smu->smu_table.TDPODLimit);
-			asic_default_power_limit /= 100;
-		}
-
-		smu->default_power_limit = asic_default_power_limit;
 		smu->power_limit = asic_default_power_limit;
 	}
 
-	if (asic_default)
-		*limit = smu->default_power_limit;
+	if (cap)
+		*limit = smu_v11_0_get_max_power_limit(smu);
 	else
 		*limit = smu->power_limit;
 
@@ -1891,6 +1816,260 @@ static bool arcturus_is_dpm_running(struct smu_context *smu)
 	return !!(feature_enabled & SMC_DPM_FEATURE);
 }
 
+static int arcturus_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (enable) {
+		if (!smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
+			ret = smu_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, 1);
+			if (ret) {
+				pr_err("[EnableVCNDPM] failed!\n");
+				return ret;
+			}
+		}
+		power_gate->vcn_gated = false;
+	} else {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
+			ret = smu_feature_set_enabled(smu, SMU_FEATURE_VCN_PG_BIT, 0);
+			if (ret) {
+				pr_err("[DisableVCNDPM] failed!\n");
+				return ret;
+			}
+		}
+		power_gate->vcn_gated = true;
+	}
+
+	return ret;
+}
+
+
+static void arcturus_fill_eeprom_i2c_req(SwI2cRequest_t  *req, bool write,
+				  uint8_t address, uint32_t numbytes,
+				  uint8_t *data)
+{
+	int i;
+
+	BUG_ON(numbytes > MAX_SW_I2C_COMMANDS);
+
+	req->I2CcontrollerPort = 0;
+	req->I2CSpeed = 2;
+	req->SlaveAddress = address;
+	req->NumCmds = numbytes;
+
+	for (i = 0; i < numbytes; i++) {
+		SwI2cCmd_t *cmd =  &req->SwI2cCmds[i];
+
+		/* First 2 bytes are always write for lower 2b EEPROM address */
+		if (i < 2)
+			cmd->Cmd = 1;
+		else
+			cmd->Cmd = write;
+
+
+		/* Add RESTART for read  after address filled */
+		cmd->CmdConfig |= (i == 2 && !write) ? CMDCONFIG_RESTART_MASK : 0;
+
+		/* Add STOP in the end */
+		cmd->CmdConfig |= (i == (numbytes - 1)) ? CMDCONFIG_STOP_MASK : 0;
+
+		/* Fill with data regardless if read or write to simplify code */
+		cmd->RegisterAddr = data[i];
+	}
+}
+
+static int arcturus_i2c_eeprom_read_data(struct i2c_adapter *control,
+					       uint8_t address,
+					       uint8_t *data,
+					       uint32_t numbytes)
+{
+	uint32_t  i, ret = 0;
+	SwI2cRequest_t req;
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	struct smu_table_context *smu_table = &adev->smu.smu_table;
+	struct smu_table *table = &smu_table->tables[SMU_TABLE_I2C_COMMANDS];
+
+	memset(&req, 0, sizeof(req));
+	arcturus_fill_eeprom_i2c_req(&req, false, address, numbytes, data);
+
+	mutex_lock(&adev->smu.mutex);
+	/* Now read data starting with that address */
+	ret = smu_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req,
+					true);
+	mutex_unlock(&adev->smu.mutex);
+
+	if (!ret) {
+		SwI2cRequest_t *res = (SwI2cRequest_t *)table->cpu_addr;
+
+		/* Assume SMU  fills res.SwI2cCmds[i].Data with read bytes */
+		for (i = 0; i < numbytes; i++)
+			data[i] = res->SwI2cCmds[i].Data;
+
+		pr_debug("arcturus_i2c_eeprom_read_data, address = %x, bytes = %d, data :",
+				  (uint16_t)address, numbytes);
+
+		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
+			       8, 1, data, numbytes, false);
+	} else
+		pr_err("arcturus_i2c_eeprom_read_data - error occurred :%x", ret);
+
+	return ret;
+}
+
+static int arcturus_i2c_eeprom_write_data(struct i2c_adapter *control,
+						uint8_t address,
+						uint8_t *data,
+						uint32_t numbytes)
+{
+	uint32_t ret;
+	SwI2cRequest_t req;
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+
+	memset(&req, 0, sizeof(req));
+	arcturus_fill_eeprom_i2c_req(&req, true, address, numbytes, data);
+
+	mutex_lock(&adev->smu.mutex);
+	ret = smu_update_table(&adev->smu, SMU_TABLE_I2C_COMMANDS, 0, &req, true);
+	mutex_unlock(&adev->smu.mutex);
+
+	if (!ret) {
+		pr_debug("arcturus_i2c_write(), address = %x, bytes = %d , data: ",
+					 (uint16_t)address, numbytes);
+
+		print_hex_dump(KERN_DEBUG, "data: ", DUMP_PREFIX_NONE,
+			       8, 1, data, numbytes, false);
+		/*
+		 * According to EEPROM spec there is a MAX of 10 ms required for
+		 * EEPROM to flush internal RX buffer after STOP was issued at the
+		 * end of write transaction. During this time the EEPROM will not be
+		 * responsive to any more commands - so wait a bit more.
+		 */
+		msleep(10);
+
+	} else
+		pr_err("arcturus_i2c_write- error occurred :%x", ret);
+
+	return ret;
+}
+
+static int arcturus_i2c_eeprom_i2c_xfer(struct i2c_adapter *i2c_adap,
+			      struct i2c_msg *msgs, int num)
+{
+	uint32_t  i, j, ret, data_size, data_chunk_size, next_eeprom_addr = 0;
+	uint8_t *data_ptr, data_chunk[MAX_SW_I2C_COMMANDS] = { 0 };
+
+	for (i = 0; i < num; i++) {
+		/*
+		 * SMU interface allows at most MAX_SW_I2C_COMMANDS bytes of data at
+		 * once and hence the data needs to be spliced into chunks and sent each
+		 * chunk separately
+		 */
+		data_size = msgs[i].len - 2;
+		data_chunk_size = MAX_SW_I2C_COMMANDS - 2;
+		next_eeprom_addr = (msgs[i].buf[0] << 8 & 0xff00) | (msgs[i].buf[1] & 0xff);
+		data_ptr = msgs[i].buf + 2;
+
+		for (j = 0; j < data_size / data_chunk_size; j++) {
+			/* Insert the EEPROM dest addess, bits 0-15 */
+			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
+			data_chunk[1] = (next_eeprom_addr & 0xff);
+
+			if (msgs[i].flags & I2C_M_RD) {
+				ret = arcturus_i2c_eeprom_read_data(i2c_adap,
+								(uint8_t)msgs[i].addr,
+								data_chunk, MAX_SW_I2C_COMMANDS);
+
+				memcpy(data_ptr, data_chunk + 2, data_chunk_size);
+			} else {
+
+				memcpy(data_chunk + 2, data_ptr, data_chunk_size);
+
+				ret = arcturus_i2c_eeprom_write_data(i2c_adap,
+								 (uint8_t)msgs[i].addr,
+								 data_chunk, MAX_SW_I2C_COMMANDS);
+			}
+
+			if (ret) {
+				num = -EIO;
+				goto fail;
+			}
+
+			next_eeprom_addr += data_chunk_size;
+			data_ptr += data_chunk_size;
+		}
+
+		if (data_size % data_chunk_size) {
+			data_chunk[0] = ((next_eeprom_addr >> 8) & 0xff);
+			data_chunk[1] = (next_eeprom_addr & 0xff);
+
+			if (msgs[i].flags & I2C_M_RD) {
+				ret = arcturus_i2c_eeprom_read_data(i2c_adap,
+								(uint8_t)msgs[i].addr,
+								data_chunk, (data_size % data_chunk_size) + 2);
+
+				memcpy(data_ptr, data_chunk + 2, data_size % data_chunk_size);
+			} else {
+				memcpy(data_chunk + 2, data_ptr, data_size % data_chunk_size);
+
+				ret = arcturus_i2c_eeprom_write_data(i2c_adap,
+								 (uint8_t)msgs[i].addr,
+								 data_chunk, (data_size % data_chunk_size) + 2);
+			}
+
+			if (ret) {
+				num = -EIO;
+				goto fail;
+			}
+		}
+	}
+
+fail:
+	return num;
+}
+
+static u32 arcturus_i2c_eeprom_i2c_func(struct i2c_adapter *adap)
+{
+	return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL;
+}
+
+
+static const struct i2c_algorithm arcturus_i2c_eeprom_i2c_algo = {
+	.master_xfer = arcturus_i2c_eeprom_i2c_xfer,
+	.functionality = arcturus_i2c_eeprom_i2c_func,
+};
+
+static int arcturus_i2c_eeprom_control_init(struct i2c_adapter *control)
+{
+	struct amdgpu_device *adev = to_amdgpu_device(control);
+	int res;
+
+	control->owner = THIS_MODULE;
+	control->class = I2C_CLASS_SPD;
+	control->dev.parent = &adev->pdev->dev;
+	control->algo = &arcturus_i2c_eeprom_i2c_algo;
+	snprintf(control->name, sizeof(control->name), "RAS EEPROM");
+
+	res = i2c_add_adapter(control);
+	if (res)
+		DRM_ERROR("Failed to register hw i2c, err: %d\n", res);
+
+	return res;
+}
+
+static void arcturus_i2c_eeprom_control_fini(struct i2c_adapter *control)
+{
+	i2c_del_adapter(control);
+}
+
+static uint32_t arcturus_get_pptable_power_limit(struct smu_context *smu)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+
+	return pptable->SocketPowerLimitAc[PPT_THROTTLER_PPT0];
+}
+
 static const struct pptable_funcs arcturus_ppt_funcs = {
 	/* translate smu index into arcturus specific index */
 	.get_smu_msg_index = arcturus_get_smu_msg_index,
@@ -1909,7 +2088,7 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	/* init dpm */
 	.get_allowed_feature_mask = arcturus_get_allowed_feature_mask,
 	/* btc */
-	.run_afll_btc = arcturus_run_btc_afll,
+	.run_btc = arcturus_run_btc,
 	/* dpm/clk tables */
 	.set_default_dpm_table = arcturus_set_default_dpm_table,
 	.populate_umd_state_clk = arcturus_populate_umd_state_clk,
@@ -1929,12 +2108,61 @@ static const struct pptable_funcs arcturus_ppt_funcs = {
 	.dump_pptable = arcturus_dump_pptable,
 	.get_power_limit = arcturus_get_power_limit,
 	.is_dpm_running = arcturus_is_dpm_running,
+	.dpm_set_uvd_enable = arcturus_dpm_set_uvd_enable,
+	.i2c_eeprom_init = arcturus_i2c_eeprom_control_init,
+	.i2c_eeprom_fini = arcturus_i2c_eeprom_control_fini,
+	.init_microcode = smu_v11_0_init_microcode,
+	.load_microcode = smu_v11_0_load_microcode,
+	.init_smc_tables = smu_v11_0_init_smc_tables,
+	.fini_smc_tables = smu_v11_0_fini_smc_tables,
+	.init_power = smu_v11_0_init_power,
+	.fini_power = smu_v11_0_fini_power,
+	.check_fw_status = smu_v11_0_check_fw_status,
+	.setup_pptable = smu_v11_0_setup_pptable,
+	.get_vbios_bootup_values = smu_v11_0_get_vbios_bootup_values,
+	.get_clk_info_from_vbios = smu_v11_0_get_clk_info_from_vbios,
+	.check_pptable = smu_v11_0_check_pptable,
+	.parse_pptable = smu_v11_0_parse_pptable,
+	.populate_smc_tables = smu_v11_0_populate_smc_pptable,
+	.check_fw_version = smu_v11_0_check_fw_version,
+	.write_pptable = smu_v11_0_write_pptable,
+	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_tool_table_location = smu_v11_0_set_tool_table_location,
+	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
+	.system_features_control = smu_v11_0_system_features_control,
+	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
+	.read_smc_arg = smu_v11_0_read_arg,
+	.init_display_count = smu_v11_0_init_display_count,
+	.set_allowed_mask = smu_v11_0_set_allowed_mask,
+	.get_enabled_mask = smu_v11_0_get_enabled_mask,
+	.notify_display_change = smu_v11_0_notify_display_change,
+	.set_power_limit = smu_v11_0_set_power_limit,
+	.get_current_clk_freq = smu_v11_0_get_current_clk_freq,
+	.init_max_sustainable_clocks = smu_v11_0_init_max_sustainable_clocks,
+	.start_thermal_control = smu_v11_0_start_thermal_control,
+	.stop_thermal_control = smu_v11_0_stop_thermal_control,
+	.set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk,
+	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
+	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
+	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
+	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
+	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
+	.gfx_off_control = smu_v11_0_gfx_off_control,
+	.register_irq_handler = smu_v11_0_register_irq_handler,
+	.set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme,
+	.get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc,
+	.baco_is_support= smu_v11_0_baco_is_support,
+	.baco_get_state = smu_v11_0_baco_get_state,
+	.baco_set_state = smu_v11_0_baco_set_state,
+	.baco_reset = smu_v11_0_baco_reset,
+	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
+	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
+	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
+	.get_pptable_power_limit = arcturus_get_pptable_power_limit,
 };
 
 void arcturus_set_ppt_funcs(struct smu_context *smu)
 {
-	struct smu_table_context *smu_table = &smu->smu_table;
-
 	smu->ppt_funcs = &arcturus_ppt_funcs;
-	smu_table->table_count = TABLE_COUNT;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile b/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile
index cc63705920dc..2773966ae434 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/Makefile
@@ -36,7 +36,8 @@ HARDWARE_MGR = hwmgr.o processpptables.o \
 		pp_overdriver.o smu_helper.o \
 		vega20_processpptables.o vega20_hwmgr.o vega20_powertune.o \
 		vega20_thermal.o common_baco.o vega10_baco.o  vega20_baco.o \
-		vega12_baco.o smu9_baco.o
+		vega12_baco.o smu9_baco.o tonga_baco.o polaris_baco.o fiji_baco.o \
+		ci_baco.o smu7_baco.o
 
 AMD_PP_HWMGR = $(addprefix $(AMD_PP_PATH)/hwmgr/,$(HARDWARE_MGR))
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.c
new file mode 100644
index 000000000000..3be40114e63d
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.c
@@ -0,0 +1,195 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "ci_baco.h"
+
+#include "gmc/gmc_7_1_d.h"
+#include "gmc/gmc_7_1_sh_mask.h"
+
+#include "bif/bif_4_1_d.h"
+#include "bif/bif_4_1_sh_mask.h"
+
+#include "dce/dce_8_0_d.h"
+#include "dce/dce_8_0_sh_mask.h"
+
+#include "smu/smu_7_0_1_d.h"
+#include "smu/smu_7_0_1_sh_mask.h"
+
+#include "gca/gfx_7_2_d.h"
+#include "gca/gfx_7_2_sh_mask.h"
+
+static const struct baco_cmd_entry gpio_tbl[] =
+{
+	{ CMD_WRITE, mmGPIOPAD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PU_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_MASK, 0, 0, 0, 0xff77ffff },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_MASK, 0, 0, 0, 0xffffffff },
+	{ CMD_WRITE, mmDC_GPIO_GENERIC_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_GENERIC_MASK, 0, 0, 0, 0x03333333 },
+	{ CMD_WRITE, mmDC_GPIO_SYNCA_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_SYNCA_MASK, 0, 0, 0, 0x00001111 }
+};
+
+static const struct baco_cmd_entry enable_fb_req_rej_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0300024 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x1, 0x0, 0, 0x1 },
+	{ CMD_WRITE, mmBIF_FB_EN, 0, 0, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry use_bclk_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN_MASK, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_STATUS },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK, 0, 0xffffffff, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_STATUS },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK, 0, 0xffffffff, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x4000000, 0x1a, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x2 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__MPLL_SW_DIR_CONTROL_MASK, MPLL_CNTL_MODE__MPLL_SW_DIR_CONTROL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__MPLL_MCLK_SEL_MASK, MPLL_CNTL_MODE__MPLL_MCLK_SEL__SHIFT, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry turn_off_plls_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmDISPPLL_BG_CNTL, DISPPLL_BG_CNTL__DISPPLL_BG_PDN_MASK, DISPPLL_BG_CNTL__DISPPLL_BG_PDN__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL_DC },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL_DC__OSC_EN_MASK, CG_CLKPIN_CNTL_DC__OSC_EN__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL_DC__XTALIN_SEL_MASK, CG_CLKPIN_CNTL_DC__XTALIN_SEL__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmPLL_CNTL, PLL_CNTL__PLL_RESET_MASK, PLL_CNTL__PLL_RESET__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmPLL_CNTL, PLL_CNTL__PLL_POWER_DOWN_MASK, PLL_CNTL__PLL_POWER_DOWN__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmPLL_CNTL, PLL_CNTL__PLL_BYPASS_CAL_MASK, PLL_CNTL__PLL_BYPASS_CAL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_RESET_MASK, CG_SPLL_FUNC_CNTL__SPLL_RESET__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_PWRON_MASK, CG_SPLL_FUNC_CNTL__SPLL_PWRON__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x2000000, 0x19, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x8000000, 0x1b, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__GLOBAL_MPLL_RESET_MASK, MPLL_CNTL_MODE__GLOBAL_MPLL_RESET__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmMPLL_CONTROL, 0, 0, 0, 0x00000006 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY0_D0, 0, 0, 0, 0x00007740 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY0_D1, 0, 0, 0, 0x00007740 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY1_D0, 0, 0, 0, 0x00007740 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY1_D1, 0, 0, 0, 0x00007740 },
+	{ CMD_READMODIFYWRITE, mmMCLK_PWRMGT_CNTL, MCLK_PWRMGT_CNTL__MRDCK0_PDNB_MASK, MCLK_PWRMGT_CNTL__MRDCK0_PDNB__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMCLK_PWRMGT_CNTL, MCLK_PWRMGT_CNTL__MRDCK1_PDNB_MASK, MCLK_PWRMGT_CNTL__MRDCK1_PDNB__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMC_SEQ_CNTL_2, MC_SEQ_CNTL_2__DRST_PU_MASK, MC_SEQ_CNTL_2__DRST_PU__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMC_SEQ_CNTL_2, MC_SEQ_CNTL_2__DRST_PD_MASK, MC_SEQ_CNTL_2__DRST_PD__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN_MASK, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x4 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMISC_CLK_CTRL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL_MASK, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL__SHIFT, 0, 0x2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__ZCLK_SEL_MASK, MISC_CLK_CTRL__ZCLK_SEL__SHIFT, 0, 0x2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__DFT_SMS_PG_CLK_SEL_MASK, MISC_CLK_CTRL__DFT_SMS_PG_CLK_SEL__SHIFT, 0, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixTHM_CLK_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__CMON_CLK_SEL_MASK, THM_CLK_CNTL__CMON_CLK_SEL__SHIFT, 0, 0x2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__TMON_CLK_SEL_MASK, THM_CLK_CNTL__TMON_CLK_SEL__SHIFT, 0, 0x2 }
+};
+
+static const struct baco_cmd_entry enter_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR,         mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, 0, 5, 0x02 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR,         mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, 0, 5,  0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR,         mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR,         mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, 0, 5, 0x08 },
+	{ CMD_WAITFOR,         mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x40 }
+};
+
+#define BACO_CNTL__PWRGOOD_MASK  BACO_CNTL__PWRGOOD_GPIO_MASK+BACO_CNTL__PWRGOOD_MEM_MASK+BACO_CNTL__PWRGOOD_DVO_MASK
+
+static const struct baco_cmd_entry exit_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK,           BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK,          BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
+	{ CMD_DELAY_MS, 0, 0, 0, 20, 0 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x20 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x10 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
+};
+
+static const struct baco_cmd_entry clean_baco_tbl[] =
+{
+	{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmCP_PFP_UCODE_ADDR, 0, 0, 0, 0 }
+};
+
+int ci_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
+{
+	enum BACO_STATE cur_state;
+
+	smu7_baco_get_state(hwmgr, &cur_state);
+
+	if (cur_state == state)
+		/* aisc already in the target state */
+		return 0;
+
+	if (state == BACO_STATE_IN) {
+		baco_program_registers(hwmgr, gpio_tbl, ARRAY_SIZE(gpio_tbl));
+		baco_program_registers(hwmgr, enable_fb_req_rej_tbl,
+				       ARRAY_SIZE(enable_fb_req_rej_tbl));
+		baco_program_registers(hwmgr, use_bclk_tbl, ARRAY_SIZE(use_bclk_tbl));
+		baco_program_registers(hwmgr, turn_off_plls_tbl,
+				       ARRAY_SIZE(turn_off_plls_tbl));
+		if (baco_program_registers(hwmgr, enter_baco_tbl,
+					   ARRAY_SIZE(enter_baco_tbl)))
+			return 0;
+
+	} else if (state == BACO_STATE_OUT) {
+		/* HW requires at least 20ms between regulator off and on */
+		msleep(20);
+		/* Execute Hardware BACO exit sequence */
+		if (baco_program_registers(hwmgr, exit_baco_tbl,
+					   ARRAY_SIZE(exit_baco_tbl))) {
+			if (baco_program_registers(hwmgr, clean_baco_tbl,
+						   ARRAY_SIZE(clean_baco_tbl)))
+				return 0;
+		}
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.h
new file mode 100644
index 000000000000..17041f187020
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ci_baco.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __CI_BACO_H__
+#define __CI_BACO_H__
+#include "smu7_baco.h"
+
+extern int ci_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.c
index 9c57c1f67749..1c73776bd606 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.c
@@ -79,6 +79,25 @@ static bool baco_cmd_handler(struct pp_hwmgr *hwmgr, u32 command, u32 reg, u32 m
 	return ret;
 }
 
+bool baco_program_registers(struct pp_hwmgr *hwmgr,
+			    const struct baco_cmd_entry *entry,
+			    const u32 array_size)
+{
+	u32 i, reg = 0;
+
+	for (i = 0; i < array_size; i++) {
+		if ((entry[i].cmd == CMD_WRITE) ||
+		    (entry[i].cmd == CMD_READMODIFYWRITE) ||
+		    (entry[i].cmd == CMD_WAITFOR))
+			reg = entry[i].reg_offset;
+		if (!baco_cmd_handler(hwmgr, entry[i].cmd, reg, entry[i].mask,
+				     entry[i].shift, entry[i].val, entry[i].timeout))
+			return false;
+	}
+
+	return true;
+}
+
 bool soc15_baco_program_registers(struct pp_hwmgr *hwmgr,
 				 const struct soc15_baco_cmd_entry *entry,
 				 const u32 array_size)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.h b/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.h
index 95296c916f4e..8393eb62706d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/common_baco.h
@@ -33,6 +33,15 @@ enum baco_cmd_type {
 	CMD_DELAY_US,
 };
 
+struct baco_cmd_entry {
+	enum baco_cmd_type cmd;
+	uint32_t 	reg_offset;
+	uint32_t     	mask;
+	uint32_t     	shift;
+	uint32_t     	timeout;
+	uint32_t     	val;
+};
+
 struct soc15_baco_cmd_entry {
 	enum baco_cmd_type cmd;
 	uint32_t 	hwip;
@@ -44,6 +53,10 @@ struct soc15_baco_cmd_entry {
 	uint32_t     	timeout;
 	uint32_t     	val;
 };
+
+extern bool baco_program_registers(struct pp_hwmgr *hwmgr,
+				   const struct baco_cmd_entry *entry,
+				   const u32 array_size);
 extern bool soc15_baco_program_registers(struct pp_hwmgr *hwmgr,
 					const struct soc15_baco_cmd_entry *entry,
 					const u32 array_size);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.c
new file mode 100644
index 000000000000..c0368f2dfb21
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.c
@@ -0,0 +1,196 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "fiji_baco.h"
+
+#include "gmc/gmc_8_1_d.h"
+#include "gmc/gmc_8_1_sh_mask.h"
+
+#include "bif/bif_5_0_d.h"
+#include "bif/bif_5_0_sh_mask.h"
+
+#include "dce/dce_10_0_d.h"
+#include "dce/dce_10_0_sh_mask.h"
+
+#include "smu/smu_7_1_3_d.h"
+#include "smu/smu_7_1_3_sh_mask.h"
+
+
+static const struct baco_cmd_entry gpio_tbl[] =
+{
+	{ CMD_WRITE, mmGPIOPAD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PU_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_MASK, 0, 0, 0, 0xff77ffff },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_MASK, 0, 0, 0, 0xffffffff },
+	{ CMD_WRITE, mmDC_GPIO_GENERIC_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_GENERIC_MASK, 0, 0, 0, 0x03333333 },
+	{ CMD_WRITE, mmDC_GPIO_SYNCA_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_SYNCA_MASK, 0, 0, 0, 0x00001111 }
+};
+
+static const struct baco_cmd_entry enable_fb_req_rej_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0300024 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x1, 0x0, 0, 0x1 },
+	{ CMD_WRITE, mmBIF_FB_EN, 0, 0, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry use_bclk_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN_MASK, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_STATUS },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK, 0, 0xffffffff, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG__SHIFT, 0,  0x0 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG__SHIFT, 0,  0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_STATUS },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK, 0, 0xffffffff, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x4000000, 0x1a, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x2 }
+};
+
+static const struct baco_cmd_entry turn_off_plls_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_RESET_MASK, CG_SPLL_FUNC_CNTL__SPLL_RESET__SHIFT, 0,     0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_PWRON_MASK, CG_SPLL_FUNC_CNTL__SPLL_PWRON__SHIFT, 0,     0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x2000000, 0x19, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x8000000, 0x1b, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry clk_req_b_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN_MASK, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x4 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMISC_CLK_CTRL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL_MASK, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__ZCLK_SEL_MASK, MISC_CLK_CTRL__ZCLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL__BCLK_AS_XCLK_MASK, CG_CLKPIN_CNTL__BCLK_AS_XCLK__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixTHM_CLK_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__CMON_CLK_SEL_MASK, THM_CLK_CNTL__CMON_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__TMON_CLK_SEL_MASK, THM_CLK_CNTL__TMON_CLK_SEL__SHIFT, 0, 0x1 }
+};
+
+static const struct baco_cmd_entry enter_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, 0, 5, 0x40000 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, 0, 5, 0x02 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, 0, 5, 0x08 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x40 }
+};
+
+#define BACO_CNTL__PWRGOOD_MASK  BACO_CNTL__PWRGOOD_GPIO_MASK+BACO_CNTL__PWRGOOD_MEM_MASK+BACO_CNTL__PWRGOOD_DVO_MASK
+
+static const struct baco_cmd_entry exit_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
+};
+
+static const struct baco_cmd_entry clean_baco_tbl[] =
+{
+	{ CMD_WRITE, mmBIOS_SCRATCH_0, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_1, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_2, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_3, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_4, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_5, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_8, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_9, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_10, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_11, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_12, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_13, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_14, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_15, 0, 0, 0, 0 }
+};
+
+int fiji_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
+{
+	enum BACO_STATE cur_state;
+
+	smu7_baco_get_state(hwmgr, &cur_state);
+
+	if (cur_state == state)
+		/* aisc already in the target state */
+		return 0;
+
+	if (state == BACO_STATE_IN) {
+		baco_program_registers(hwmgr, gpio_tbl, ARRAY_SIZE(gpio_tbl));
+		baco_program_registers(hwmgr, enable_fb_req_rej_tbl,
+				       ARRAY_SIZE(enable_fb_req_rej_tbl));
+		baco_program_registers(hwmgr, use_bclk_tbl, ARRAY_SIZE(use_bclk_tbl));
+		baco_program_registers(hwmgr, turn_off_plls_tbl,
+				       ARRAY_SIZE(turn_off_plls_tbl));
+		baco_program_registers(hwmgr, clk_req_b_tbl, ARRAY_SIZE(clk_req_b_tbl));
+		if (baco_program_registers(hwmgr, enter_baco_tbl,
+					   ARRAY_SIZE(enter_baco_tbl)))
+			return 0;
+
+	} else if (state == BACO_STATE_OUT) {
+		/* HW requires at least 20ms between regulator off and on */
+		msleep(20);
+		/* Execute Hardware BACO exit sequence */
+		if (baco_program_registers(hwmgr, exit_baco_tbl,
+					   ARRAY_SIZE(exit_baco_tbl))) {
+			if (baco_program_registers(hwmgr, clean_baco_tbl,
+						   ARRAY_SIZE(clean_baco_tbl)))
+				return 0;
+		}
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.h b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.h
new file mode 100644
index 000000000000..47f402900bdb
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/fiji_baco.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __FIJI_BACO_H__
+#define __FIJI_BACO_H__
+#include "smu7_baco.h"
+
+extern int fiji_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index a24beaa4fb01..d2909c91d65b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -81,6 +81,8 @@ static void hwmgr_init_workload_prority(struct pp_hwmgr *hwmgr)
 
 int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 {
+	struct amdgpu_device *adev;
+
 	if (!hwmgr)
 		return -EINVAL;
 
@@ -94,8 +96,11 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 	hwmgr_init_workload_prority(hwmgr);
 	hwmgr->gfxoff_state_changed_by_workload = false;
 
+	adev = hwmgr->adev;
+
 	switch (hwmgr->chip_family) {
 	case AMDGPU_FAMILY_CI:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		hwmgr->smumgr_funcs = &ci_smu_funcs;
 		ci_set_asic_special_caps(hwmgr);
 		hwmgr->feature_mask &= ~(PP_VBI_TIME_SUPPORT_MASK |
@@ -106,12 +111,14 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		smu7_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_CZ:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		hwmgr->od_enabled = false;
 		hwmgr->smumgr_funcs = &smu8_smu_funcs;
 		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		smu8_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_VI:
+		adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_TOPAZ:
@@ -153,6 +160,7 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 	case AMDGPU_FAMILY_AI:
 		switch (hwmgr->chip_id) {
 		case CHIP_VEGA10:
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega10_smu_funcs;
 			vega10_hwmgr_init(hwmgr);
@@ -162,6 +170,7 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 			vega12_hwmgr_init(hwmgr);
 			break;
 		case CHIP_VEGA20:
+			adev->pm.pp_feature &= ~PP_GFXOFF_MASK;
 			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega20_smu_funcs;
 			vega20_hwmgr_init(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.c
new file mode 100644
index 000000000000..8f8e296f2fe9
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.c
@@ -0,0 +1,222 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "polaris_baco.h"
+
+#include "gmc/gmc_8_1_d.h"
+#include "gmc/gmc_8_1_sh_mask.h"
+
+#include "bif/bif_5_0_d.h"
+#include "bif/bif_5_0_sh_mask.h"
+
+#include "dce/dce_11_0_d.h"
+#include "dce/dce_11_0_sh_mask.h"
+
+#include "smu/smu_7_1_3_d.h"
+#include "smu/smu_7_1_3_sh_mask.h"
+
+static const struct baco_cmd_entry gpio_tbl[] =
+{
+	{ CMD_WRITE, mmGPIOPAD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PU_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_MASK, 0, 0, 0, 0xff77ffff },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_MASK, 0, 0, 0, 0xffffffff },
+	{ CMD_WRITE, mmDC_GPIO_GENERIC_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_GENERIC_MASK, 0, 0, 0, 0x03333333 },
+	{ CMD_WRITE, mmDC_GPIO_SYNCA_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_SYNCA_MASK, 0, 0, 0, 0x00001111 }
+};
+
+static const struct baco_cmd_entry enable_fb_req_rej_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0300024 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x1, 0x0, 0, 0x1 },
+	{ CMD_WRITE, mmBIF_FB_EN, 0, 0, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry use_bclk_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN_MASK, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x4000000, 0x1a, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixGCK_DFS_BYPASS_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, GCK_DFS_BYPASS_CNTL__BYPASSACLK_MASK, GCK_DFS_BYPASS_CNTL__BYPASSACLK__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x2 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__MPLL_SW_DIR_CONTROL_MASK, MPLL_CNTL_MODE__MPLL_SW_DIR_CONTROL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__MPLL_MCLK_SEL_MASK, MPLL_CNTL_MODE__MPLL_MCLK_SEL__SHIFT, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry turn_off_plls_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_PAD_STRENGTH_1, DC_GPIO_PAD_STRENGTH_1__GENLK_STRENGTH_SP_MASK, DC_GPIO_PAD_STRENGTH_1__GENLK_STRENGTH_SP__SHIFT, 0, 0x1 },
+	{ CMD_DELAY_US, 0, 0, 0, 1, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMC_SEQ_DRAM, MC_SEQ_DRAM__RST_CTL_MASK, MC_SEQ_DRAM__RST_CTL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC05002B0 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x10, 0x4, 0, 0x1 },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, 0x10, 0, 1, 0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC050032C },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x10, 0x4, 0, 0x1 },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, 0x10, 0, 1, 0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500080 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x1, 0x0, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, 0xda2, 0x40, 0x6, 0, 0x0 },
+	{ CMD_DELAY_US, 0, 0, 0, 3, 0x0 },
+	{ CMD_READMODIFYWRITE, 0xda2, 0x8, 0x3, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, 0xda2, 0x3fff00, 0x8, 0, 0x32 },
+	{ CMD_DELAY_US, 0, 0, 0, 3, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMPLL_FUNC_CNTL_2, MPLL_FUNC_CNTL_2__ISO_DIS_P_MASK, MPLL_FUNC_CNTL_2__ISO_DIS_P__SHIFT, 0, 0x0 },
+	{ CMD_DELAY_US, 0, 0, 0, 5, 0x0 }
+};
+
+static const struct baco_cmd_entry clk_req_b_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixTHM_CLK_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__CMON_CLK_SEL_MASK, THM_CLK_CNTL__CMON_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__TMON_CLK_SEL_MASK, THM_CLK_CNTL__TMON_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMISC_CLK_CTRL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL_MASK, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__ZCLK_SEL_MASK, MISC_CLK_CTRL__ZCLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL__BCLK_AS_XCLK_MASK, CG_CLKPIN_CNTL__BCLK_AS_XCLK__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN_MASK, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0,     0x4 }
+};
+
+static const struct baco_cmd_entry enter_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, 0, 5, 0x40000 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, 0, 5, 0x02 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, 0, 5, 0x08 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x40 }
+};
+
+#define BACO_CNTL__PWRGOOD_MASK  BACO_CNTL__PWRGOOD_GPIO_MASK+BACO_CNTL__PWRGOOD_MEM_MASK+BACO_CNTL__PWRGOOD_DVO_MASK
+
+static const struct baco_cmd_entry exit_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
+};
+
+static const struct baco_cmd_entry clean_baco_tbl[] =
+{
+	{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 }
+};
+
+static const struct baco_cmd_entry use_bclk_tbl_vg[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN_MASK, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x4000000, 0x1a, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixGCK_DFS_BYPASS_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, GCK_DFS_BYPASS_CNTL__BYPASSACLK_MASK, GCK_DFS_BYPASS_CNTL__BYPASSACLK__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x2 }
+};
+
+static const struct baco_cmd_entry turn_off_plls_tbl_vg[] =
+{
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_PAD_STRENGTH_1, DC_GPIO_PAD_STRENGTH_1__GENLK_STRENGTH_SP_MASK, DC_GPIO_PAD_STRENGTH_1__GENLK_STRENGTH_SP__SHIFT, 0, 0x1 },
+	{ CMD_DELAY_US, 0, 0, 0, 1, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMC_SEQ_DRAM, MC_SEQ_DRAM__RST_CTL_MASK, MC_SEQ_DRAM__RST_CTL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC05002B0 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x10, 0x4, 0, 0x1 },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, 0x10, 0, 1, 0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC050032C },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x10, 0x4, 0, 0x1 },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, 0x10, 0, 1, 0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500080 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x1, 0x0, 0, 0x1 },
+	{ CMD_DELAY_US, 0, 0, 0, 3, 0x0 },
+	{ CMD_DELAY_US, 0, 0, 0, 3, 0x0 },
+	{ CMD_DELAY_US, 0, 0, 0, 5, 0x0 }
+};
+
+int polaris_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
+{
+	enum BACO_STATE cur_state;
+
+	smu7_baco_get_state(hwmgr, &cur_state);
+
+	if (cur_state == state)
+		/* aisc already in the target state */
+		return 0;
+
+	if (state == BACO_STATE_IN) {
+		baco_program_registers(hwmgr, gpio_tbl, ARRAY_SIZE(gpio_tbl));
+		baco_program_registers(hwmgr, enable_fb_req_rej_tbl,
+				       ARRAY_SIZE(enable_fb_req_rej_tbl));
+		if (hwmgr->chip_id == CHIP_VEGAM) {
+			baco_program_registers(hwmgr, use_bclk_tbl_vg, ARRAY_SIZE(use_bclk_tbl_vg));
+			baco_program_registers(hwmgr, turn_off_plls_tbl_vg,
+					       ARRAY_SIZE(turn_off_plls_tbl_vg));
+		} else {
+			baco_program_registers(hwmgr, use_bclk_tbl, ARRAY_SIZE(use_bclk_tbl));
+			baco_program_registers(hwmgr, turn_off_plls_tbl,
+					       ARRAY_SIZE(turn_off_plls_tbl));
+		}
+		baco_program_registers(hwmgr, clk_req_b_tbl, ARRAY_SIZE(clk_req_b_tbl));
+		if (baco_program_registers(hwmgr, enter_baco_tbl,
+					   ARRAY_SIZE(enter_baco_tbl)))
+			return 0;
+
+	} else if (state == BACO_STATE_OUT) {
+		/* HW requires at least 20ms between regulator off and on */
+		msleep(20);
+		/* Execute Hardware BACO exit sequence */
+		if (baco_program_registers(hwmgr, exit_baco_tbl,
+					   ARRAY_SIZE(exit_baco_tbl))) {
+			if (baco_program_registers(hwmgr, clean_baco_tbl,
+						   ARRAY_SIZE(clean_baco_tbl)))
+				return 0;
+		}
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.h b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.h
new file mode 100644
index 000000000000..87a5fa0a157a
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/polaris_baco.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __POLARIS_BACO_H__
+#define __POLARIS_BACO_H__
+#include "smu7_baco.h"
+
+extern int polaris_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.c
new file mode 100644
index 000000000000..044cda005aed
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.c
@@ -0,0 +1,91 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "smu7_baco.h"
+#include "tonga_baco.h"
+#include "fiji_baco.h"
+#include "polaris_baco.h"
+#include "ci_baco.h"
+
+#include "bif/bif_5_0_d.h"
+#include "bif/bif_5_0_sh_mask.h"
+
+#include "smu/smu_7_1_2_d.h"
+#include "smu/smu_7_1_2_sh_mask.h"
+
+int smu7_baco_get_capability(struct pp_hwmgr *hwmgr, bool *cap)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	uint32_t reg;
+
+	*cap = false;
+	if (!phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_BACO))
+		return 0;
+
+	reg = RREG32(mmCC_BIF_BX_FUSESTRAP0);
+
+	if (reg & CC_BIF_BX_FUSESTRAP0__STRAP_BIF_PX_CAPABLE_MASK)
+		*cap = true;
+
+	return 0;
+}
+
+int smu7_baco_get_state(struct pp_hwmgr *hwmgr, enum BACO_STATE *state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	uint32_t reg;
+
+	reg = RREG32(mmBACO_CNTL);
+
+	if (reg & BACO_CNTL__BACO_MODE_MASK)
+		/* gfx has already entered BACO state */
+		*state = BACO_STATE_IN;
+	else
+		*state = BACO_STATE_OUT;
+	return 0;
+}
+
+int smu7_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+
+	switch (adev->asic_type) {
+	case CHIP_TOPAZ:
+	case CHIP_TONGA:
+		return tonga_baco_set_state(hwmgr, state);
+	case CHIP_FIJI:
+		return fiji_baco_set_state(hwmgr, state);
+	case CHIP_POLARIS10:
+	case CHIP_POLARIS11:
+	case CHIP_POLARIS12:
+	case CHIP_VEGAM:
+		return polaris_baco_set_state(hwmgr, state);
+#ifdef CONFIG_DRM_AMDGPU_CIK
+	case CHIP_BONAIRE:
+	case CHIP_HAWAII:
+		return ci_baco_set_state(hwmgr, state);
+#endif
+	default:
+		return -EINVAL;
+	}
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.h
new file mode 100644
index 000000000000..be0d98abb536
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_baco.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __SMU7_BACO_H__
+#define __SMU7_BACO_H__
+#include "hwmgr.h"
+#include "common_baco.h"
+
+extern int smu7_baco_get_capability(struct pp_hwmgr *hwmgr, bool *cap);
+extern int smu7_baco_get_state(struct pp_hwmgr *hwmgr, enum BACO_STATE *state);
+extern int smu7_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 34f95e0e3ea4..f73dff68e799 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -48,6 +48,7 @@
 #include "smu7_clockpowergating.h"
 #include "processpptables.h"
 #include "pp_thermal.h"
+#include "smu7_baco.h"
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
@@ -1994,7 +1995,6 @@ static int smu7_sort_lookup_table(struct pp_hwmgr *hwmgr,
 		struct phm_ppt_v1_voltage_lookup_table *lookup_table)
 {
 	uint32_t table_size, i, j;
-	struct phm_ppt_v1_voltage_lookup_record tmp_voltage_lookup_record;
 	table_size = lookup_table->count;
 
 	PP_ASSERT_WITH_CODE(0 != lookup_table->count,
@@ -2005,9 +2005,8 @@ static int smu7_sort_lookup_table(struct pp_hwmgr *hwmgr,
 		for (j = i + 1; j > 0; j--) {
 			if (lookup_table->entries[j].us_vdd <
 					lookup_table->entries[j - 1].us_vdd) {
-				tmp_voltage_lookup_record = lookup_table->entries[j - 1];
-				lookup_table->entries[j - 1] = lookup_table->entries[j];
-				lookup_table->entries[j] = tmp_voltage_lookup_record;
+				swap(lookup_table->entries[j - 1],
+				     lookup_table->entries[j]);
 			}
 		}
 	}
@@ -3478,18 +3477,31 @@ static int smu7_get_pp_table_entry(struct pp_hwmgr *hwmgr,
 
 static int smu7_get_gpu_power(struct pp_hwmgr *hwmgr, u32 *query)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	int i;
 	u32 tmp = 0;
 
 	if (!query)
 		return -EINVAL;
 
-	smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
-	tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
-	*query = tmp;
+	/*
+	 * PPSMC_MSG_GetCurrPkgPwr is not supported on:
+	 *  - Hawaii
+	 *  - Bonaire
+	 *  - Fiji
+	 *  - Tonga
+	 */
+	if ((adev->asic_type != CHIP_HAWAII) &&
+	    (adev->asic_type != CHIP_BONAIRE) &&
+	    (adev->asic_type != CHIP_FIJI) &&
+	    (adev->asic_type != CHIP_TONGA)) {
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetCurrPkgPwr, 0);
+		tmp = cgs_read_register(hwmgr->device, mmSMC_MSG_ARG_0);
+		*query = tmp;
 
-	if (tmp != 0)
-		return 0;
+		if (tmp != 0)
+			return 0;
+	}
 
 	smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PmStatusLogStart);
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC,
@@ -3970,6 +3982,13 @@ static int smu7_set_power_state_tasks(struct pp_hwmgr *hwmgr, const void *input)
 			"Failed to populate and upload SCLK MCLK DPM levels!",
 			result = tmp_result);
 
+	/*
+	 * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag.
+	 * That effectively disables AVFS feature.
+	 */
+	if (hwmgr->hardcode_pp_table != NULL)
+		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
+
 	tmp_result = smu7_update_avfs(hwmgr);
 	PP_ASSERT_WITH_CODE((0 == tmp_result),
 			"Failed to update avfs voltages!",
@@ -5145,6 +5164,9 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = {
 	.get_power_profile_mode = smu7_get_power_profile_mode,
 	.set_power_profile_mode = smu7_set_power_profile_mode,
 	.get_performance_level = smu7_get_performance_level,
+	.get_asic_baco_capability = smu7_baco_get_capability,
+	.get_asic_baco_state = smu7_baco_get_state,
+	.set_asic_baco_state = smu7_baco_set_state,
 	.power_off_asic = smu7_power_off_asic,
 };
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.c
new file mode 100644
index 000000000000..ea743bea8e29
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#include "amdgpu.h"
+#include "tonga_baco.h"
+
+#include "gmc/gmc_8_1_d.h"
+#include "gmc/gmc_8_1_sh_mask.h"
+
+#include "bif/bif_5_0_d.h"
+#include "bif/bif_5_0_sh_mask.h"
+
+#include "dce/dce_10_0_d.h"
+#include "dce/dce_10_0_sh_mask.h"
+
+#include "smu/smu_7_1_2_d.h"
+#include "smu/smu_7_1_2_sh_mask.h"
+
+
+static const struct baco_cmd_entry gpio_tbl[] =
+{
+	{ CMD_WRITE, mmGPIOPAD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PU_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_MASK, 0, 0, 0, 0xff77ffff },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmDC_GPIO_DVODATA_MASK, 0, 0, 0, 0xffffffff },
+	{ CMD_WRITE, mmDC_GPIO_GENERIC_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_GENERIC_MASK, 0, 0, 0, 0x03333333 },
+	{ CMD_WRITE, mmDC_GPIO_SYNCA_EN, 0, 0, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmDC_GPIO_SYNCA_MASK, 0, 0, 0, 0x00001111 }
+};
+
+static const struct baco_cmd_entry enable_fb_req_rej_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0300024 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x1, 0x0, 0, 0x1 },
+	{ CMD_WRITE, mmBIF_FB_EN, 0, 0, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry use_bclk_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN_MASK, CG_SPLL_FUNC_CNTL__SPLL_BYPASS_EN__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_STATUS },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK, 0, 0xffffffff, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_BYPASS_CHG__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_STATUS },
+	{ CMD_WAITFOR, mmGCK_SMC_IND_DATA, CG_SPLL_STATUS__SPLL_CHG_STATUS_MASK, 0, 0xffffffff, 0x2 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG_MASK, CG_SPLL_FUNC_CNTL_2__SPLL_CTLREQ_CHG__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x4000000, 0x1a, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x2 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__MPLL_SW_DIR_CONTROL_MASK, MPLL_CNTL_MODE__MPLL_SW_DIR_CONTROL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__MPLL_MCLK_SEL_MASK, MPLL_CNTL_MODE__MPLL_MCLK_SEL__SHIFT, 0, 0x0 }
+};
+
+static const struct baco_cmd_entry turn_off_plls_tbl[] =
+{
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_SPLL_FUNC_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_RESET_MASK, CG_SPLL_FUNC_CNTL__SPLL_RESET__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_SPLL_FUNC_CNTL__SPLL_PWRON_MASK, CG_SPLL_FUNC_CNTL__SPLL_PWRON__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, 0xC0500170 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x2000000, 0x19, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, 0x8000000, 0x1b, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMPLL_CNTL_MODE, MPLL_CNTL_MODE__GLOBAL_MPLL_RESET_MASK, MPLL_CNTL_MODE__GLOBAL_MPLL_RESET__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmMPLL_CONTROL, 0, 0, 0, 0x00000006 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY0_D0, 0, 0, 0, 0x00007740 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY0_D1, 0, 0, 0, 0x00007740 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY1_D0, 0, 0, 0, 0x00007740 },
+	{ CMD_WRITE, mmMC_IO_RXCNTL_DPHY1_D1, 0, 0, 0, 0x00007740 },
+	{ CMD_READMODIFYWRITE, mmMCLK_PWRMGT_CNTL, MCLK_PWRMGT_CNTL__MRDCK0_PDNB_MASK, MCLK_PWRMGT_CNTL__MRDCK0_PDNB__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMCLK_PWRMGT_CNTL, MCLK_PWRMGT_CNTL__MRDCK1_PDNB_MASK, MCLK_PWRMGT_CNTL__MRDCK1_PDNB__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMC_SEQ_CNTL_2, MC_SEQ_CNTL_2__DRST_PU_MASK, MC_SEQ_CNTL_2__DRST_PU__SHIFT, 0, 0x0 },
+	{ CMD_READMODIFYWRITE, mmMC_SEQ_CNTL_2, MC_SEQ_CNTL_2__DRST_PD_MASK, MC_SEQ_CNTL_2__DRST_PD__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL_2 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN_MASK, CG_CLKPIN_CNTL_2__FORCE_BIF_REFCLK_EN__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMPLL_BYPASSCLK_SEL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL_MASK, MPLL_BYPASSCLK_SEL__MPLL_CLKOUT_SEL__SHIFT, 0, 0x4 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixMISC_CLK_CTRL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL_MASK, MISC_CLK_CTRL__DEEP_SLEEP_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, MISC_CLK_CTRL__ZCLK_SEL_MASK, MISC_CLK_CTRL__ZCLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixCG_CLKPIN_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, CG_CLKPIN_CNTL__BCLK_AS_XCLK_MASK, CG_CLKPIN_CNTL__BCLK_AS_XCLK__SHIFT, 0, 0x0 },
+	{ CMD_WRITE, mmGCK_SMC_IND_INDEX, 0, 0, 0, ixTHM_CLK_CNTL },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__CMON_CLK_SEL_MASK,  THM_CLK_CNTL__CMON_CLK_SEL__SHIFT, 0, 0x1 },
+	{ CMD_READMODIFYWRITE, mmGCK_SMC_IND_DATA, THM_CLK_CNTL__TMON_CLK_SEL_MASK,  THM_CLK_CNTL__TMON_CLK_SEL__SHIFT, 0, 0x1 }
+};
+
+static const struct baco_cmd_entry enter_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, 0, 5, 0x40000 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, 0, 5, 0x02 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, 0, 5, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, 0, 5, 0x08 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x40 }
+};
+
+#define BACO_CNTL__PWRGOOD_MASK  BACO_CNTL__PWRGOOD_GPIO_MASK+BACO_CNTL__PWRGOOD_MEM_MASK+BACO_CNTL__PWRGOOD_DVO_MASK
+
+static const struct baco_cmd_entry exit_baco_tbl[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
+};
+
+static const struct baco_cmd_entry clean_baco_tbl[] =
+{
+	{ CMD_WRITE, mmBIOS_SCRATCH_6, 0, 0, 0, 0 },
+	{ CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 }
+};
+
+static const struct baco_cmd_entry gpio_tbl_iceland[] =
+{
+	{ CMD_WRITE, mmGPIOPAD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PD_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_PU_EN, 0, 0, 0, 0x0 },
+	{ CMD_WRITE, mmGPIOPAD_MASK, 0, 0, 0, 0xff77ffff }
+};
+
+static const struct baco_cmd_entry exit_baco_tbl_iceland[] =
+{
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BCLK_OFF_MASK, BACO_CNTL__BACO_BCLK_OFF__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_POWER_OFF_MASK, BACO_CNTL__BACO_POWER_OFF__SHIFT, 0, 0x00 },
+	{ CMD_DELAY_MS, 0, 0, 0, 20, 0 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_BF_MASK, 0, 0xffffffff, 0x200 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ISO_DIS_MASK, BACO_CNTL__BACO_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__PWRGOOD_MASK, 0, 5, 0x1c00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_ANA_ISO_DIS_MASK, BACO_CNTL__BACO_ANA_ISO_DIS__SHIFT, 0, 0x01 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_BIF_SCLK_SWITCH_MASK, BACO_CNTL__BACO_BIF_SCLK_SWITCH__SHIFT, 0, 0x00 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_RESET_EN_MASK, BACO_CNTL__BACO_RESET_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__RCU_BIF_CONFIG_DONE_MASK, 0, 5, 0x100 },
+	{ CMD_READMODIFYWRITE, mmBACO_CNTL, BACO_CNTL__BACO_EN_MASK, BACO_CNTL__BACO_EN__SHIFT, 0, 0x00 },
+	{ CMD_WAITFOR, mmBACO_CNTL, BACO_CNTL__BACO_MODE_MASK, 0, 0xffffffff, 0x00 }
+};
+
+static const struct baco_cmd_entry clean_baco_tbl_iceland[] =
+{
+	{ CMD_WRITE, mmBIOS_SCRATCH_7, 0, 0, 0, 0 }
+};
+
+int tonga_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
+{
+	enum BACO_STATE cur_state;
+
+	smu7_baco_get_state(hwmgr, &cur_state);
+
+	if (cur_state == state)
+		/* aisc already in the target state */
+		return 0;
+
+	if (state == BACO_STATE_IN) {
+		if (hwmgr->chip_id == CHIP_TOPAZ)
+			baco_program_registers(hwmgr, gpio_tbl_iceland, ARRAY_SIZE(gpio_tbl_iceland));
+		else
+			baco_program_registers(hwmgr, gpio_tbl, ARRAY_SIZE(gpio_tbl));
+		baco_program_registers(hwmgr, enable_fb_req_rej_tbl,
+				       ARRAY_SIZE(enable_fb_req_rej_tbl));
+		baco_program_registers(hwmgr, use_bclk_tbl, ARRAY_SIZE(use_bclk_tbl));
+		baco_program_registers(hwmgr, turn_off_plls_tbl,
+				       ARRAY_SIZE(turn_off_plls_tbl));
+		if (baco_program_registers(hwmgr, enter_baco_tbl,
+					   ARRAY_SIZE(enter_baco_tbl)))
+			return 0;
+
+	} else if (state == BACO_STATE_OUT) {
+		/* HW requires at least 20ms between regulator off and on */
+		msleep(20);
+		/* Execute Hardware BACO exit sequence */
+		if (hwmgr->chip_id == CHIP_TOPAZ) {
+			if (baco_program_registers(hwmgr, exit_baco_tbl_iceland,
+						   ARRAY_SIZE(exit_baco_tbl_iceland))) {
+				if (baco_program_registers(hwmgr, clean_baco_tbl_iceland,
+							   ARRAY_SIZE(clean_baco_tbl_iceland)))
+					return 0;
+			}
+		} else {
+			if (baco_program_registers(hwmgr, exit_baco_tbl,
+						   ARRAY_SIZE(exit_baco_tbl))) {
+				if (baco_program_registers(hwmgr, clean_baco_tbl,
+							   ARRAY_SIZE(clean_baco_tbl)))
+					return 0;
+			}
+		}
+	}
+
+	return -EINVAL;
+}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.h b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.h
new file mode 100644
index 000000000000..5dc16cc8a295
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/tonga_baco.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __TONGA_BACO_H__
+#define __TONGA_BACO_H__
+#include "smu7_baco.h"
+
+extern int tonga_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d08493b67b67..d71a492c87a3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -712,7 +712,6 @@ static int vega10_sort_lookup_table(struct pp_hwmgr *hwmgr,
 		struct phm_ppt_v1_voltage_lookup_table *lookup_table)
 {
 	uint32_t table_size, i, j;
-	struct phm_ppt_v1_voltage_lookup_record tmp_voltage_lookup_record;
 
 	PP_ASSERT_WITH_CODE(lookup_table && lookup_table->count,
 		"Lookup table is empty", return -EINVAL);
@@ -724,9 +723,8 @@ static int vega10_sort_lookup_table(struct pp_hwmgr *hwmgr,
 		for (j = i + 1; j > 0; j--) {
 			if (lookup_table->entries[j].us_vdd <
 					lookup_table->entries[j - 1].us_vdd) {
-				tmp_voltage_lookup_record = lookup_table->entries[j - 1];
-				lookup_table->entries[j - 1] = lookup_table->entries[j];
-				lookup_table->entries[j] = tmp_voltage_lookup_record;
+				swap(lookup_table->entries[j - 1],
+				     lookup_table->entries[j]);
 			}
 		}
 	}
@@ -3691,6 +3689,13 @@ static int vega10_set_power_state_tasks(struct pp_hwmgr *hwmgr,
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to upload PPtable!", return result);
 
+	/*
+	 * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag.
+	 * That effectively disables AVFS feature.
+	 */
+	if(hwmgr->hardcode_pp_table != NULL)
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC;
+
 	vega10_update_avfs(hwmgr);
 
 	/*
@@ -5098,9 +5103,7 @@ static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
 
 	if (type == PP_OD_EDIT_SCLK_VDDC_TABLE) {
 		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_sclk;
-		for (i = 0; i < podn_vdd_dep->count - 1; i++)
-			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
-		if (od_vddc_lookup_table->entries[i].us_vdd < podn_vdd_dep->entries[i].vddc)
+		for (i = 0; i < podn_vdd_dep->count; i++)
 			od_vddc_lookup_table->entries[i].us_vdd = podn_vdd_dep->entries[i].vddc;
 	} else if (type == PP_OD_EDIT_MCLK_VDDC_TABLE) {
 		podn_vdd_dep = &data->odn_dpm_table.vdd_dep_on_mclk;
@@ -5267,6 +5270,59 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_
 	return 0;
 }
 
+static int vega10_disable_power_features_for_compute_performance(struct pp_hwmgr *hwmgr, bool disable)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	uint32_t feature_mask = 0;
+
+	if (disable) {
+		feature_mask |= data->smu_features[GNLD_ULV].enabled ?
+			data->smu_features[GNLD_ULV].smu_feature_bitmap : 0;
+		feature_mask |= data->smu_features[GNLD_DS_GFXCLK].enabled ?
+			data->smu_features[GNLD_DS_GFXCLK].smu_feature_bitmap : 0;
+		feature_mask |= data->smu_features[GNLD_DS_SOCCLK].enabled ?
+			data->smu_features[GNLD_DS_SOCCLK].smu_feature_bitmap : 0;
+		feature_mask |= data->smu_features[GNLD_DS_LCLK].enabled ?
+			data->smu_features[GNLD_DS_LCLK].smu_feature_bitmap : 0;
+		feature_mask |= data->smu_features[GNLD_DS_DCEFCLK].enabled ?
+			data->smu_features[GNLD_DS_DCEFCLK].smu_feature_bitmap : 0;
+	} else {
+		feature_mask |= (!data->smu_features[GNLD_ULV].enabled) ?
+			data->smu_features[GNLD_ULV].smu_feature_bitmap : 0;
+		feature_mask |= (!data->smu_features[GNLD_DS_GFXCLK].enabled) ?
+			data->smu_features[GNLD_DS_GFXCLK].smu_feature_bitmap : 0;
+		feature_mask |= (!data->smu_features[GNLD_DS_SOCCLK].enabled) ?
+			data->smu_features[GNLD_DS_SOCCLK].smu_feature_bitmap : 0;
+		feature_mask |= (!data->smu_features[GNLD_DS_LCLK].enabled) ?
+			data->smu_features[GNLD_DS_LCLK].smu_feature_bitmap : 0;
+		feature_mask |= (!data->smu_features[GNLD_DS_DCEFCLK].enabled) ?
+			data->smu_features[GNLD_DS_DCEFCLK].smu_feature_bitmap : 0;
+	}
+
+	if (feature_mask)
+		PP_ASSERT_WITH_CODE(!vega10_enable_smc_features(hwmgr,
+				!disable, feature_mask),
+				"enable/disable power features for compute performance Failed!",
+				return -EINVAL);
+
+	if (disable) {
+		data->smu_features[GNLD_ULV].enabled = false;
+		data->smu_features[GNLD_DS_GFXCLK].enabled = false;
+		data->smu_features[GNLD_DS_SOCCLK].enabled = false;
+		data->smu_features[GNLD_DS_LCLK].enabled = false;
+		data->smu_features[GNLD_DS_DCEFCLK].enabled = false;
+	} else {
+		data->smu_features[GNLD_ULV].enabled = true;
+		data->smu_features[GNLD_DS_GFXCLK].enabled = true;
+		data->smu_features[GNLD_DS_SOCCLK].enabled = true;
+		data->smu_features[GNLD_DS_LCLK].enabled = true;
+		data->smu_features[GNLD_DS_DCEFCLK].enabled = true;
+	}
+
+	return 0;
+
+}
+
 static const struct pp_hwmgr_func vega10_hwmgr_funcs = {
 	.backend_init = vega10_hwmgr_backend_init,
 	.backend_fini = vega10_hwmgr_backend_fini,
@@ -5334,6 +5390,8 @@ static const struct pp_hwmgr_func vega10_hwmgr_funcs = {
 	.get_ppfeature_status = vega10_get_ppfeature_status,
 	.set_ppfeature_status = vega10_set_ppfeature_status,
 	.set_mp1_state = vega10_set_mp1_state,
+	.disable_power_features_for_compute_performance =
+			vega10_disable_power_features_for_compute_performance,
 };
 
 int vega10_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
index df6ff9252401..9b5e72bdceca 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_baco.c
@@ -29,7 +29,7 @@
 #include "vega20_baco.h"
 #include "vega20_smumgr.h"
 
-
+#include "amdgpu_ras.h"
 
 static const struct soc15_baco_cmd_entry clean_baco_tbl[] =
 {
@@ -74,6 +74,7 @@ int vega20_baco_get_state(struct pp_hwmgr *hwmgr, enum BACO_STATE *state)
 int vega20_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)(hwmgr->adev);
+	struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
 	enum BACO_STATE cur_state;
 	uint32_t data;
 
@@ -84,13 +85,19 @@ int vega20_baco_set_state(struct pp_hwmgr *hwmgr, enum BACO_STATE state)
 		return 0;
 
 	if (state == BACO_STATE_IN) {
-		data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL);
-		data |= 0x80000000;
-		WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data);
-
-
-		if(smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_EnterBaco, 0))
-			return -EINVAL;
+		if (!ras || !ras->supported) {
+			data = RREG32_SOC15(THM, 0, mmTHM_BACO_CNTL);
+			data |= 0x80000000;
+			WREG32_SOC15(THM, 0, mmTHM_BACO_CNTL, data);
+
+			if(smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_EnterBaco, 0))
+				return -EINVAL;
+		} else {
+			if(smum_send_msg_to_smc_with_parameter(hwmgr,
+					PPSMC_MSG_EnterBaco, 1))
+				return -EINVAL;
+		}
 
 	} else if (state == BACO_STATE_OUT) {
 		if (smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ExitBaco))
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
index f5915308e643..5bcf0d684151 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c
@@ -183,6 +183,9 @@ static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr)
 			PHM_PlatformCaps_TablelessHardwareInterface);
 
 	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
+			PHM_PlatformCaps_BACO);
+
+	phm_cap_set(hwmgr->platform_descriptor.platformCaps,
 			PHM_PlatformCaps_EnableSMU7ThermalManagement);
 
 	if (adev->pg_flags & AMD_PG_SUPPORT_UVD)
@@ -490,8 +493,8 @@ static int vega20_setup_asic_task(struct pp_hwmgr *hwmgr)
 			"Failed to init sclk threshold!",
 			return ret);
 
-	if (adev->in_baco_reset) {
-		adev->in_baco_reset = 0;
+	if (adev->in_gpu_reset &&
+	    (amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO)) {
 
 		ret = vega20_baco_apply_vdci_flush_workaround(hwmgr);
 		if (ret)
@@ -4155,6 +4158,38 @@ static int vega20_smu_i2c_bus_access(struct pp_hwmgr *hwmgr, bool acquire)
 	return res;
 }
 
+static int vega20_set_df_cstate(struct pp_hwmgr *hwmgr,
+				enum pp_df_cstate state)
+{
+	int ret;
+
+	/* PPSMC_MSG_DFCstateControl is supported with 40.50 and later fws */
+	if (hwmgr->smu_version < 0x283200) {
+		pr_err("Df cstate control is supported with 40.50 and later SMC fw!\n");
+		return -EINVAL;
+	}
+
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DFCstateControl, state);
+	if (ret)
+		pr_err("SetDfCstate failed!\n");
+
+	return ret;
+}
+
+static int vega20_set_xgmi_pstate(struct pp_hwmgr *hwmgr,
+				  uint32_t pstate)
+{
+	int ret;
+
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+						  PPSMC_MSG_SetXgmiMode,
+						  pstate ? XGMI_MODE_PSTATE_D0 : XGMI_MODE_PSTATE_D3);
+	if (ret)
+		pr_err("SetXgmiPstate failed!\n");
+
+	return ret;
+}
+
 static const struct pp_hwmgr_func vega20_hwmgr_funcs = {
 	/* init/fini related */
 	.backend_init = vega20_hwmgr_backend_init,
@@ -4223,6 +4258,8 @@ static const struct pp_hwmgr_func vega20_hwmgr_funcs = {
 	.set_asic_baco_state = vega20_baco_set_state,
 	.set_mp1_state = vega20_set_mp1_state,
 	.smu_i2c_bus_access = vega20_smu_i2c_bus_access,
+	.set_df_cstate = vega20_set_df_cstate,
+	.set_xgmi_pstate = vega20_set_xgmi_pstate,
 };
 
 int vega20_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
index 23171a4d9a31..ac9758305ab3 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/amdgpu_smu.h
@@ -259,10 +259,8 @@ struct smu_table_context
 	struct smu_bios_boot_up_values	boot_values;
 	void                            *driver_pptable;
 	struct smu_table		*tables;
-	uint32_t			table_count;
 	struct smu_table		memory_pool;
 	uint8_t                         thermal_controller_type;
-	uint16_t			TDPODLimit;
 
 	void				*overdrive_table;
 };
@@ -322,6 +320,13 @@ struct mclock_latency_table {
 	struct mclk_latency_entries  entries[MAX_REGULAR_DPM_NUM];
 };
 
+enum smu_reset_mode
+{
+    SMU_RESET_MODE_0,
+    SMU_RESET_MODE_1,
+    SMU_RESET_MODE_2,
+};
+
 enum smu_baco_state
 {
 	SMU_BACO_STATE_ENTER = 0,
@@ -341,7 +346,6 @@ struct smu_context
 	struct amdgpu_device            *adev;
 	struct amdgpu_irq_src		*irq_source;
 
-	const struct smu_funcs		*funcs;
 	const struct pptable_funcs	*ppt_funcs;
 	struct mutex			mutex;
 	struct mutex			sensor_lock;
@@ -382,11 +386,15 @@ struct smu_context
 	uint32_t power_profile_mode;
 	uint32_t default_power_profile_mode;
 	bool pm_enabled;
+	bool is_apu;
 
 	uint32_t smc_if_version;
 
+	bool uploading_custom_pp_table;
 };
 
+struct i2c_adapter;
+
 struct pptable_funcs {
 	int (*alloc_dpm_context)(struct smu_context *smu);
 	int (*store_powerplay_table)(struct smu_context *smu);
@@ -398,7 +406,7 @@ struct pptable_funcs {
 	int (*get_smu_table_index)(struct smu_context *smu, uint32_t index);
 	int (*get_smu_power_index)(struct smu_context *smu, uint32_t index);
 	int (*get_workload_type)(struct smu_context *smu, enum PP_SMC_POWER_PROFILE profile);
-	int (*run_afll_btc)(struct smu_context *smu);
+	int (*run_btc)(struct smu_context *smu);
 	int (*get_allowed_feature_mask)(struct smu_context *smu, uint32_t *feature_mask, uint32_t num);
 	enum amd_pm_state_type (*get_current_power_state)(struct smu_context *smu);
 	int (*set_default_dpm_table)(struct smu_context *smu);
@@ -459,17 +467,19 @@ struct pptable_funcs {
 	int (*display_disable_memory_clock_switch)(struct smu_context *smu, bool disable_memory_clock_switch);
 	void (*dump_pptable)(struct smu_context *smu);
 	int (*get_power_limit)(struct smu_context *smu, uint32_t *limit, bool asic_default);
-	int (*get_dpm_uclk_limited)(struct smu_context *smu, uint32_t *clock, bool max);
-};
-
-struct smu_funcs
-{
+	int (*get_dpm_clk_limited)(struct smu_context *smu, enum smu_clk_type clk_type,
+				   uint32_t dpm_level, uint32_t *freq);
+	int (*set_df_cstate)(struct smu_context *smu, enum pp_df_cstate state);
+	int (*update_pcie_parameters)(struct smu_context *smu, uint32_t pcie_gen_cap, uint32_t pcie_width_cap);
+	int (*i2c_eeprom_init)(struct i2c_adapter *control);
+	void (*i2c_eeprom_fini)(struct i2c_adapter *control);
+	int (*get_dpm_clock_table)(struct smu_context *smu, struct dpm_clocks *clock_table);
 	int (*init_microcode)(struct smu_context *smu);
+	int (*load_microcode)(struct smu_context *smu);
 	int (*init_smc_tables)(struct smu_context *smu);
 	int (*fini_smc_tables)(struct smu_context *smu);
 	int (*init_power)(struct smu_context *smu);
 	int (*fini_power)(struct smu_context *smu);
-	int (*load_microcode)(struct smu_context *smu);
 	int (*check_fw_status)(struct smu_context *smu);
 	int (*setup_pptable)(struct smu_context *smu);
 	int (*get_vbios_bootup_values)(struct smu_context *smu);
@@ -485,11 +495,10 @@ struct smu_funcs
 	int (*set_min_dcef_deep_sleep)(struct smu_context *smu);
 	int (*set_tool_table_location)(struct smu_context *smu);
 	int (*notify_memory_pool_location)(struct smu_context *smu);
-	int (*write_watermarks_table)(struct smu_context *smu);
 	int (*set_last_dcef_min_deep_sleep_clk)(struct smu_context *smu);
 	int (*system_features_control)(struct smu_context *smu, bool en);
-	int (*send_smc_msg)(struct smu_context *smu, uint16_t msg);
-	int (*send_smc_msg_with_param)(struct smu_context *smu, uint16_t msg, uint32_t param);
+	int (*send_smc_msg_with_param)(struct smu_context *smu,
+				       enum smu_message_type msg, uint32_t param);
 	int (*read_smc_arg)(struct smu_context *smu, uint32_t *arg);
 	int (*init_display_count)(struct smu_context *smu, uint32_t count);
 	int (*set_allowed_mask)(struct smu_context *smu);
@@ -499,8 +508,7 @@ struct smu_funcs
 	int (*get_current_clk_freq)(struct smu_context *smu, enum smu_clk_type clk_id, uint32_t *value);
 	int (*init_max_sustainable_clocks)(struct smu_context *smu);
 	int (*start_thermal_control)(struct smu_context *smu);
-	int (*read_sensor)(struct smu_context *smu, enum amd_pp_sensors sensor,
-			   void *data, uint32_t *size);
+	int (*stop_thermal_control)(struct smu_context *smu);
 	int (*set_deep_sleep_dcefclk)(struct smu_context *smu, uint32_t clk);
 	int (*set_active_display_count)(struct smu_context *smu, uint32_t count);
 	int (*store_cc6_data)(struct smu_context *smu, uint32_t separation_time,
@@ -522,8 +530,6 @@ struct smu_funcs
 	int (*get_current_shallow_sleep_clocks)(struct smu_context *smu,
 						struct smu_clock_info *clocks);
 	int (*notify_smu_enable_pwe)(struct smu_context *smu);
-	int (*set_watermarks_for_clock_ranges)(struct smu_context *smu,
-					       struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
 	int (*conv_power_profile_to_pplib_workload)(int power_profile);
 	uint32_t (*get_fan_control_mode)(struct smu_context *smu);
 	int (*set_fan_control_mode)(struct smu_context *smu, uint32_t mode);
@@ -538,234 +544,90 @@ struct smu_funcs
 	enum smu_baco_state (*baco_get_state)(struct smu_context *smu);
 	int (*baco_set_state)(struct smu_context *smu, enum smu_baco_state state);
 	int (*baco_reset)(struct smu_context *smu);
+	int (*mode2_reset)(struct smu_context *smu);
 	int (*get_dpm_ultimate_freq)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t *min, uint32_t *max);
+	int (*set_soft_freq_limited_range)(struct smu_context *smu, enum smu_clk_type clk_type, uint32_t min, uint32_t max);
+	int (*override_pcie_parameters)(struct smu_context *smu);
+	uint32_t (*get_pptable_power_limit)(struct smu_context *smu);
 };
 
-#define smu_init_microcode(smu) \
-	((smu)->funcs->init_microcode ? (smu)->funcs->init_microcode((smu)) : 0)
-#define smu_init_smc_tables(smu) \
-	((smu)->funcs->init_smc_tables ? (smu)->funcs->init_smc_tables((smu)) : 0)
-#define smu_fini_smc_tables(smu) \
-	((smu)->funcs->fini_smc_tables ? (smu)->funcs->fini_smc_tables((smu)) : 0)
-#define smu_init_power(smu) \
-	((smu)->funcs->init_power ? (smu)->funcs->init_power((smu)) : 0)
-#define smu_fini_power(smu) \
-	((smu)->funcs->fini_power ? (smu)->funcs->fini_power((smu)) : 0)
-#define smu_load_microcode(smu) \
-	((smu)->funcs->load_microcode ? (smu)->funcs->load_microcode((smu)) : 0)
-#define smu_check_fw_status(smu) \
-	((smu)->funcs->check_fw_status ? (smu)->funcs->check_fw_status((smu)) : 0)
-#define smu_setup_pptable(smu) \
-	((smu)->funcs->setup_pptable ? (smu)->funcs->setup_pptable((smu)) : 0)
-#define smu_powergate_sdma(smu, gate) \
-	((smu)->funcs->powergate_sdma ? (smu)->funcs->powergate_sdma((smu), (gate)) : 0)
-#define smu_powergate_vcn(smu, gate) \
-	((smu)->funcs->powergate_vcn ? (smu)->funcs->powergate_vcn((smu), (gate)) : 0)
-#define smu_set_gfx_cgpg(smu, enabled) \
-	((smu)->funcs->set_gfx_cgpg ? (smu)->funcs->set_gfx_cgpg((smu), (enabled)) : 0)
-#define smu_get_vbios_bootup_values(smu) \
-	((smu)->funcs->get_vbios_bootup_values ? (smu)->funcs->get_vbios_bootup_values((smu)) : 0)
-#define smu_get_clk_info_from_vbios(smu) \
-	((smu)->funcs->get_clk_info_from_vbios ? (smu)->funcs->get_clk_info_from_vbios((smu)) : 0)
-#define smu_check_pptable(smu) \
-	((smu)->funcs->check_pptable ? (smu)->funcs->check_pptable((smu)) : 0)
-#define smu_parse_pptable(smu) \
-	((smu)->funcs->parse_pptable ? (smu)->funcs->parse_pptable((smu)) : 0)
-#define smu_populate_smc_tables(smu) \
-	((smu)->funcs->populate_smc_tables ? (smu)->funcs->populate_smc_tables((smu)) : 0)
-#define smu_check_fw_version(smu) \
-	((smu)->funcs->check_fw_version ? (smu)->funcs->check_fw_version((smu)) : 0)
-#define smu_write_pptable(smu) \
-	((smu)->funcs->write_pptable ? (smu)->funcs->write_pptable((smu)) : 0)
-#define smu_set_min_dcef_deep_sleep(smu) \
-	((smu)->funcs->set_min_dcef_deep_sleep ? (smu)->funcs->set_min_dcef_deep_sleep((smu)) : 0)
-#define smu_set_tool_table_location(smu) \
-	((smu)->funcs->set_tool_table_location ? (smu)->funcs->set_tool_table_location((smu)) : 0)
-#define smu_notify_memory_pool_location(smu) \
-	((smu)->funcs->notify_memory_pool_location ? (smu)->funcs->notify_memory_pool_location((smu)) : 0)
-#define smu_gfx_off_control(smu, enable) \
-	((smu)->funcs->gfx_off_control ? (smu)->funcs->gfx_off_control((smu), (enable)) : 0)
-
-#define smu_write_watermarks_table(smu) \
-	((smu)->funcs->write_watermarks_table ? (smu)->funcs->write_watermarks_table((smu)) : 0)
-#define smu_set_last_dcef_min_deep_sleep_clk(smu) \
-	((smu)->funcs->set_last_dcef_min_deep_sleep_clk ? (smu)->funcs->set_last_dcef_min_deep_sleep_clk((smu)) : 0)
-#define smu_system_features_control(smu, en) \
-	((smu)->funcs->system_features_control ? (smu)->funcs->system_features_control((smu), (en)) : 0)
-#define smu_init_max_sustainable_clocks(smu) \
-	((smu)->funcs->init_max_sustainable_clocks ? (smu)->funcs->init_max_sustainable_clocks((smu)) : 0)
-#define smu_set_default_od_settings(smu, initialize) \
-	((smu)->ppt_funcs->set_default_od_settings ? (smu)->ppt_funcs->set_default_od_settings((smu), (initialize)) : 0)
-#define smu_set_fan_speed_rpm(smu, speed) \
-	((smu)->funcs->set_fan_speed_rpm ? (smu)->funcs->set_fan_speed_rpm((smu), (speed)) : 0)
-#define smu_send_smc_msg(smu, msg) \
-	((smu)->funcs->send_smc_msg? (smu)->funcs->send_smc_msg((smu), (msg)) : 0)
-#define smu_send_smc_msg_with_param(smu, msg, param) \
-	((smu)->funcs->send_smc_msg_with_param? (smu)->funcs->send_smc_msg_with_param((smu), (msg), (param)) : 0)
-#define smu_read_smc_arg(smu, arg) \
-	((smu)->funcs->read_smc_arg? (smu)->funcs->read_smc_arg((smu), (arg)) : 0)
-#define smu_alloc_dpm_context(smu) \
-	((smu)->ppt_funcs->alloc_dpm_context ? (smu)->ppt_funcs->alloc_dpm_context((smu)) : 0)
-#define smu_init_display_count(smu, count) \
-	((smu)->funcs->init_display_count ? (smu)->funcs->init_display_count((smu), (count)) : 0)
-#define smu_feature_set_allowed_mask(smu) \
-	((smu)->funcs->set_allowed_mask? (smu)->funcs->set_allowed_mask((smu)) : 0)
-#define smu_feature_get_enabled_mask(smu, mask, num) \
-	((smu)->funcs->get_enabled_mask? (smu)->funcs->get_enabled_mask((smu), (mask), (num)) : 0)
-#define smu_is_dpm_running(smu) \
-	((smu)->ppt_funcs->is_dpm_running ? (smu)->ppt_funcs->is_dpm_running((smu)) : 0)
-#define smu_notify_display_change(smu) \
-	((smu)->funcs->notify_display_change? (smu)->funcs->notify_display_change((smu)) : 0)
-#define smu_store_powerplay_table(smu) \
-	((smu)->ppt_funcs->store_powerplay_table ? (smu)->ppt_funcs->store_powerplay_table((smu)) : 0)
-#define smu_check_powerplay_table(smu) \
-	((smu)->ppt_funcs->check_powerplay_table ? (smu)->ppt_funcs->check_powerplay_table((smu)) : 0)
-#define smu_append_powerplay_table(smu) \
-	((smu)->ppt_funcs->append_powerplay_table ? (smu)->ppt_funcs->append_powerplay_table((smu)) : 0)
-#define smu_set_default_dpm_table(smu) \
-	((smu)->ppt_funcs->set_default_dpm_table ? (smu)->ppt_funcs->set_default_dpm_table((smu)) : 0)
-#define smu_populate_umd_state_clk(smu) \
-	((smu)->ppt_funcs->populate_umd_state_clk ? (smu)->ppt_funcs->populate_umd_state_clk((smu)) : 0)
-#define smu_set_default_od8_settings(smu) \
-	((smu)->ppt_funcs->set_default_od8_settings ? (smu)->ppt_funcs->set_default_od8_settings((smu)) : 0)
-#define smu_get_power_limit(smu, limit, def) \
-	((smu)->ppt_funcs->get_power_limit ? (smu)->ppt_funcs->get_power_limit((smu), (limit), (def)) : 0)
-#define smu_set_power_limit(smu, limit) \
-	((smu)->funcs->set_power_limit ? (smu)->funcs->set_power_limit((smu), (limit)) : 0)
-#define smu_get_current_clk_freq(smu, clk_id, value) \
-	((smu)->funcs->get_current_clk_freq? (smu)->funcs->get_current_clk_freq((smu), (clk_id), (value)) : 0)
-#define smu_print_clk_levels(smu, clk_type, buf) \
-	((smu)->ppt_funcs->print_clk_levels ? (smu)->ppt_funcs->print_clk_levels((smu), (clk_type), (buf)) : 0)
-#define smu_force_clk_levels(smu, clk_type, level) \
-	((smu)->ppt_funcs->force_clk_levels ? (smu)->ppt_funcs->force_clk_levels((smu), (clk_type), (level)) : 0)
-#define smu_get_od_percentage(smu, type) \
-	((smu)->ppt_funcs->get_od_percentage ? (smu)->ppt_funcs->get_od_percentage((smu), (type)) : 0)
-#define smu_set_od_percentage(smu, type, value) \
-	((smu)->ppt_funcs->set_od_percentage ? (smu)->ppt_funcs->set_od_percentage((smu), (type), (value)) : 0)
-#define smu_od_edit_dpm_table(smu, type, input, size) \
-	((smu)->ppt_funcs->od_edit_dpm_table ? (smu)->ppt_funcs->od_edit_dpm_table((smu), (type), (input), (size)) : 0)
-#define smu_tables_init(smu, tab) \
-	((smu)->ppt_funcs->tables_init ? (smu)->ppt_funcs->tables_init((smu), (tab)) : 0)
-#define smu_set_thermal_fan_table(smu) \
-	((smu)->ppt_funcs->set_thermal_fan_table ? (smu)->ppt_funcs->set_thermal_fan_table((smu)) : 0)
-#define smu_start_thermal_control(smu) \
-	((smu)->funcs->start_thermal_control? (smu)->funcs->start_thermal_control((smu)) : 0)
-#define smu_read_sensor(smu, sensor, data, size) \
-	((smu)->ppt_funcs->read_sensor? (smu)->ppt_funcs->read_sensor((smu), (sensor), (data), (size)) : 0)
-#define smu_smc_read_sensor(smu, sensor, data, size) \
-	((smu)->funcs->read_sensor? (smu)->funcs->read_sensor((smu), (sensor), (data), (size)) : -EINVAL)
-#define smu_get_power_profile_mode(smu, buf) \
-	((smu)->ppt_funcs->get_power_profile_mode ? (smu)->ppt_funcs->get_power_profile_mode((smu), buf) : 0)
-#define smu_set_power_profile_mode(smu, param, param_size) \
-	((smu)->ppt_funcs->set_power_profile_mode ? (smu)->ppt_funcs->set_power_profile_mode((smu), (param), (param_size)) : 0)
-#define smu_pre_display_config_changed(smu) \
-	((smu)->ppt_funcs->pre_display_config_changed ? (smu)->ppt_funcs->pre_display_config_changed((smu)) : 0)
-#define smu_display_config_changed(smu) \
-	((smu)->ppt_funcs->display_config_changed ? (smu)->ppt_funcs->display_config_changed((smu)) : 0)
-#define smu_apply_clocks_adjust_rules(smu) \
-	((smu)->ppt_funcs->apply_clocks_adjust_rules ? (smu)->ppt_funcs->apply_clocks_adjust_rules((smu)) : 0)
-#define smu_notify_smc_dispaly_config(smu) \
-	((smu)->ppt_funcs->notify_smc_dispaly_config ? (smu)->ppt_funcs->notify_smc_dispaly_config((smu)) : 0)
-#define smu_force_dpm_limit_value(smu, highest) \
-	((smu)->ppt_funcs->force_dpm_limit_value ? (smu)->ppt_funcs->force_dpm_limit_value((smu), (highest)) : 0)
-#define smu_unforce_dpm_levels(smu) \
-	((smu)->ppt_funcs->unforce_dpm_levels ? (smu)->ppt_funcs->unforce_dpm_levels((smu)) : 0)
-#define smu_get_profiling_clk_mask(smu, level, sclk_mask, mclk_mask, soc_mask) \
-	((smu)->ppt_funcs->get_profiling_clk_mask ? (smu)->ppt_funcs->get_profiling_clk_mask((smu), (level), (sclk_mask), (mclk_mask), (soc_mask)) : 0)
-#define smu_set_cpu_power_state(smu) \
-	((smu)->ppt_funcs->set_cpu_power_state ? (smu)->ppt_funcs->set_cpu_power_state((smu)) : 0)
-#define smu_get_fan_control_mode(smu) \
-	((smu)->funcs->get_fan_control_mode ? (smu)->funcs->get_fan_control_mode((smu)) : 0)
-#define smu_set_fan_control_mode(smu, value) \
-	((smu)->funcs->set_fan_control_mode ? (smu)->funcs->set_fan_control_mode((smu), (value)) : 0)
-#define smu_get_fan_speed_percent(smu, speed) \
-	((smu)->ppt_funcs->get_fan_speed_percent ? (smu)->ppt_funcs->get_fan_speed_percent((smu), (speed)) : 0)
-#define smu_set_fan_speed_percent(smu, speed) \
-	((smu)->funcs->set_fan_speed_percent ? (smu)->funcs->set_fan_speed_percent((smu), (speed)) : 0)
-#define smu_get_fan_speed_rpm(smu, speed) \
-	((smu)->ppt_funcs->get_fan_speed_rpm ? (smu)->ppt_funcs->get_fan_speed_rpm((smu), (speed)) : 0)
-
-#define smu_msg_get_index(smu, msg) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_msg_index? (smu)->ppt_funcs->get_smu_msg_index((smu), (msg)) : -EINVAL) : -EINVAL)
-#define smu_clk_get_index(smu, msg) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_clk_index? (smu)->ppt_funcs->get_smu_clk_index((smu), (msg)) : -EINVAL) : -EINVAL)
-#define smu_feature_get_index(smu, msg) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_feature_index? (smu)->ppt_funcs->get_smu_feature_index((smu), (msg)) : -EINVAL) : -EINVAL)
-#define smu_table_get_index(smu, tab) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_table_index? (smu)->ppt_funcs->get_smu_table_index((smu), (tab)) : -EINVAL) : -EINVAL)
-#define smu_power_get_index(smu, src) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_power_index? (smu)->ppt_funcs->get_smu_power_index((smu), (src)) : -EINVAL) : -EINVAL)
-#define smu_workload_get_type(smu, profile) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_workload_type? (smu)->ppt_funcs->get_workload_type((smu), (profile)) : -EINVAL) : -EINVAL)
-#define smu_run_afll_btc(smu) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->run_afll_btc? (smu)->ppt_funcs->run_afll_btc((smu)) : 0) : 0)
-#define smu_get_allowed_feature_mask(smu, feature_mask, num) \
-	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_allowed_feature_mask? (smu)->ppt_funcs->get_allowed_feature_mask((smu), (feature_mask), (num)) : 0) : 0)
-#define smu_set_deep_sleep_dcefclk(smu, clk) \
-	((smu)->funcs->set_deep_sleep_dcefclk ? (smu)->funcs->set_deep_sleep_dcefclk((smu), (clk)) : 0)
-#define smu_set_active_display_count(smu, count) \
-	((smu)->funcs->set_active_display_count ? (smu)->funcs->set_active_display_count((smu), (count)) : 0)
-#define smu_store_cc6_data(smu, st, cc6_dis, pst_dis, pst_sw_dis) \
-	((smu)->funcs->store_cc6_data ? (smu)->funcs->store_cc6_data((smu), (st), (cc6_dis), (pst_dis), (pst_sw_dis)) : 0)
-#define smu_get_clock_by_type(smu, type, clocks) \
-	((smu)->funcs->get_clock_by_type ? (smu)->funcs->get_clock_by_type((smu), (type), (clocks)) : 0)
-#define smu_get_max_high_clocks(smu, clocks) \
-	((smu)->funcs->get_max_high_clocks ? (smu)->funcs->get_max_high_clocks((smu), (clocks)) : 0)
-#define smu_get_clock_by_type_with_latency(smu, clk_type, clocks) \
-	((smu)->ppt_funcs->get_clock_by_type_with_latency ? (smu)->ppt_funcs->get_clock_by_type_with_latency((smu), (clk_type), (clocks)) : 0)
-#define smu_get_clock_by_type_with_voltage(smu, type, clocks) \
-	((smu)->ppt_funcs->get_clock_by_type_with_voltage ? (smu)->ppt_funcs->get_clock_by_type_with_voltage((smu), (type), (clocks)) : 0)
-#define smu_display_clock_voltage_request(smu, clock_req) \
-	((smu)->funcs->display_clock_voltage_request ? (smu)->funcs->display_clock_voltage_request((smu), (clock_req)) : 0)
-#define smu_display_disable_memory_clock_switch(smu, disable_memory_clock_switch) \
-	((smu)->ppt_funcs->display_disable_memory_clock_switch ? (smu)->ppt_funcs->display_disable_memory_clock_switch((smu), (disable_memory_clock_switch)) : -EINVAL)
-#define smu_get_dal_power_level(smu, clocks) \
-	((smu)->funcs->get_dal_power_level ? (smu)->funcs->get_dal_power_level((smu), (clocks)) : 0)
-#define smu_get_perf_level(smu, designation, level) \
-	((smu)->funcs->get_perf_level ? (smu)->funcs->get_perf_level((smu), (designation), (level)) : 0)
-#define smu_get_current_shallow_sleep_clocks(smu, clocks) \
-	((smu)->funcs->get_current_shallow_sleep_clocks ? (smu)->funcs->get_current_shallow_sleep_clocks((smu), (clocks)) : 0)
-#define smu_notify_smu_enable_pwe(smu) \
-	((smu)->funcs->notify_smu_enable_pwe ? (smu)->funcs->notify_smu_enable_pwe((smu)) : 0)
-#define smu_set_watermarks_for_clock_ranges(smu, clock_ranges) \
-	((smu)->funcs->set_watermarks_for_clock_ranges ? (smu)->funcs->set_watermarks_for_clock_ranges((smu), (clock_ranges)) : 0)
-#define smu_dpm_set_uvd_enable(smu, enable) \
-	((smu)->ppt_funcs->dpm_set_uvd_enable ? (smu)->ppt_funcs->dpm_set_uvd_enable((smu), (enable)) : 0)
-#define smu_dpm_set_vce_enable(smu, enable) \
-	((smu)->ppt_funcs->dpm_set_vce_enable ? (smu)->ppt_funcs->dpm_set_vce_enable((smu), (enable)) : 0)
-#define smu_set_xgmi_pstate(smu, pstate) \
-		((smu)->funcs->set_xgmi_pstate ? (smu)->funcs->set_xgmi_pstate((smu), (pstate)) : 0)
-#define smu_set_watermarks_table(smu, tab, clock_ranges) \
-	((smu)->ppt_funcs->set_watermarks_table ? (smu)->ppt_funcs->set_watermarks_table((smu), (tab), (clock_ranges)) : 0)
-#define smu_get_current_clk_freq_by_table(smu, clk_type, value) \
-	((smu)->ppt_funcs->get_current_clk_freq_by_table ? (smu)->ppt_funcs->get_current_clk_freq_by_table((smu), (clk_type), (value)) : 0)
-#define smu_thermal_temperature_range_update(smu, range, rw) \
-	((smu)->ppt_funcs->thermal_temperature_range_update? (smu)->ppt_funcs->thermal_temperature_range_update((smu), (range), (rw)) : 0)
-#define smu_get_thermal_temperature_range(smu, range) \
-	((smu)->ppt_funcs->get_thermal_temperature_range? (smu)->ppt_funcs->get_thermal_temperature_range((smu), (range)) : 0)
-#define smu_register_irq_handler(smu) \
-	((smu)->funcs->register_irq_handler ? (smu)->funcs->register_irq_handler(smu) : 0)
-#define smu_set_azalia_d3_pme(smu) \
-	((smu)->funcs->set_azalia_d3_pme ? (smu)->funcs->set_azalia_d3_pme((smu)) : 0)
-#define smu_get_dpm_ultimate_freq(smu, param, min, max) \
-		((smu)->funcs->get_dpm_ultimate_freq ? (smu)->funcs->get_dpm_ultimate_freq((smu), (param), (min), (max)) : 0)
-#define smu_get_max_sustainable_clocks_by_dc(smu, max_clocks) \
-	((smu)->funcs->get_max_sustainable_clocks_by_dc ? (smu)->funcs->get_max_sustainable_clocks_by_dc((smu), (max_clocks)) : 0)
-#define smu_get_uclk_dpm_states(smu, clocks_in_khz, num_states) \
-	((smu)->ppt_funcs->get_uclk_dpm_states ? (smu)->ppt_funcs->get_uclk_dpm_states((smu), (clocks_in_khz), (num_states)) : 0)
-#define smu_baco_is_support(smu) \
-	((smu)->funcs->baco_is_support? (smu)->funcs->baco_is_support((smu)) : false)
-#define smu_baco_get_state(smu, state) \
-	((smu)->funcs->baco_get_state? (smu)->funcs->baco_get_state((smu), (state)) : 0)
-#define smu_baco_reset(smu) \
-	((smu)->funcs->baco_reset? (smu)->funcs->baco_reset((smu)) : 0)
-#define smu_asic_set_performance_level(smu, level) \
-	((smu)->ppt_funcs->set_performance_level? (smu)->ppt_funcs->set_performance_level((smu), (level)) : -EINVAL);
-#define smu_dump_pptable(smu) \
-	((smu)->ppt_funcs->dump_pptable ? (smu)->ppt_funcs->dump_pptable((smu)) : 0)
-#define smu_get_dpm_uclk_limited(smu, clock, max) \
-		((smu)->ppt_funcs->get_dpm_uclk_limited ? (smu)->ppt_funcs->get_dpm_uclk_limited((smu), (clock), (max)) : -EINVAL)
+int smu_load_microcode(struct smu_context *smu);
+
+int smu_check_fw_status(struct smu_context *smu);
+
+int smu_set_gfx_cgpg(struct smu_context *smu, bool enabled);
+
+#define smu_i2c_eeprom_init(smu, control) \
+		((smu)->ppt_funcs->i2c_eeprom_init ? (smu)->ppt_funcs->i2c_eeprom_init((control)) : -EINVAL)
+#define smu_i2c_eeprom_fini(smu, control) \
+		((smu)->ppt_funcs->i2c_eeprom_fini ? (smu)->ppt_funcs->i2c_eeprom_fini((control)) : -EINVAL)
+
+int smu_set_fan_speed_rpm(struct smu_context *smu, uint32_t speed);
+
+int smu_get_power_limit(struct smu_context *smu,
+			uint32_t *limit,
+			bool def,
+			bool lock_needed);
+
+int smu_set_power_limit(struct smu_context *smu, uint32_t limit);
+int smu_print_clk_levels(struct smu_context *smu, enum smu_clk_type clk_type, char *buf);
+int smu_get_od_percentage(struct smu_context *smu, enum smu_clk_type type);
+int smu_set_od_percentage(struct smu_context *smu, enum smu_clk_type type, uint32_t value);
+
+int smu_od_edit_dpm_table(struct smu_context *smu,
+			  enum PP_OD_DPM_TABLE_COMMAND type,
+			  long *input, uint32_t size);
+
+int smu_read_sensor(struct smu_context *smu,
+		    enum amd_pp_sensors sensor,
+		    void *data, uint32_t *size);
+int smu_get_power_profile_mode(struct smu_context *smu, char *buf);
+
+int smu_set_power_profile_mode(struct smu_context *smu,
+			       long *param,
+			       uint32_t param_size,
+			       bool lock_needed);
+int smu_get_fan_control_mode(struct smu_context *smu);
+int smu_set_fan_control_mode(struct smu_context *smu, int value);
+int smu_get_fan_speed_percent(struct smu_context *smu, uint32_t *speed);
+int smu_set_fan_speed_percent(struct smu_context *smu, uint32_t speed);
+int smu_get_fan_speed_rpm(struct smu_context *smu, uint32_t *speed);
+
+int smu_set_deep_sleep_dcefclk(struct smu_context *smu, int clk);
+int smu_set_active_display_count(struct smu_context *smu, uint32_t count);
+
+int smu_get_clock_by_type(struct smu_context *smu,
+			  enum amd_pp_clock_type type,
+			  struct amd_pp_clocks *clocks);
+
+int smu_get_max_high_clocks(struct smu_context *smu,
+			    struct amd_pp_simple_clock_info *clocks);
+
+int smu_get_clock_by_type_with_latency(struct smu_context *smu,
+				       enum smu_clk_type clk_type,
+				       struct pp_clock_levels_with_latency *clocks);
+
+int smu_get_clock_by_type_with_voltage(struct smu_context *smu,
+				       enum amd_pp_clock_type type,
+				       struct pp_clock_levels_with_voltage *clocks);
+
+int smu_display_clock_voltage_request(struct smu_context *smu,
+				      struct pp_display_clock_request *clock_req);
+int smu_display_disable_memory_clock_switch(struct smu_context *smu, bool disable_memory_clock_switch);
+int smu_notify_smu_enable_pwe(struct smu_context *smu);
+
+int smu_set_xgmi_pstate(struct smu_context *smu,
+			uint32_t pstate);
+
+int smu_set_azalia_d3_pme(struct smu_context *smu);
+
+bool smu_baco_is_support(struct smu_context *smu);
+
+int smu_baco_get_state(struct smu_context *smu, enum smu_baco_state *state);
+
+int smu_baco_reset(struct smu_context *smu);
 
+int smu_mode2_reset(struct smu_context *smu);
 
 extern int smu_get_atom_data_table(struct smu_context *smu, uint32_t table,
 				   uint16_t *size, uint8_t *frev, uint8_t *crev,
@@ -799,6 +661,10 @@ int smu_sys_get_pp_table(struct smu_context *smu, void **table);
 int smu_sys_set_pp_table(struct smu_context *smu,  void *buf, size_t size);
 int smu_get_power_num_states(struct smu_context *smu, struct pp_states_info *state_info);
 enum amd_pm_state_type smu_get_current_power_state(struct smu_context *smu);
+int smu_write_watermarks_table(struct smu_context *smu);
+int smu_set_watermarks_for_clock_ranges(
+		struct smu_context *smu,
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges);
 
 /* smu to display interface */
 extern int smu_display_configuration_change(struct smu_context *smu, const
@@ -809,7 +675,8 @@ extern int smu_get_current_clocks(struct smu_context *smu,
 extern int smu_dpm_set_power_gate(struct smu_context *smu,uint32_t block_type, bool gate);
 extern int smu_handle_task(struct smu_context *smu,
 			   enum amd_dpm_forced_level level,
-			   enum amd_pp_task task_id);
+			   enum amd_pp_task task_id,
+			   bool lock_needed);
 int smu_switch_power_profile(struct smu_context *smu,
 			     enum PP_SMC_POWER_PROFILE type,
 			     bool en);
@@ -819,7 +686,7 @@ int smu_get_dpm_freq_by_index(struct smu_context *smu, enum smu_clk_type clk_typ
 int smu_get_dpm_level_count(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t *value);
 int smu_get_dpm_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
-			   uint32_t *min, uint32_t *max);
+			   uint32_t *min, uint32_t *max, bool lock_needed);
 int smu_set_soft_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
 			    uint32_t min, uint32_t max);
 int smu_set_hard_freq_range(struct smu_context *smu, enum smu_clk_type clk_type,
@@ -828,10 +695,29 @@ enum amd_dpm_forced_level smu_get_performance_level(struct smu_context *smu);
 int smu_force_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level);
 int smu_set_display_count(struct smu_context *smu, uint32_t count);
 bool smu_clk_dpm_is_enabled(struct smu_context *smu, enum smu_clk_type clk_type);
-int smu_feature_update_enable_state(struct smu_context *smu, uint64_t feature_mask, bool enabled);
 const char *smu_get_message_name(struct smu_context *smu, enum smu_message_type type);
 const char *smu_get_feature_name(struct smu_context *smu, enum smu_feature_mask feature);
 size_t smu_sys_get_pp_feature_mask(struct smu_context *smu, char *buf);
 int smu_sys_set_pp_feature_mask(struct smu_context *smu, uint64_t new_mask);
+int smu_force_clk_levels(struct smu_context *smu,
+			 enum smu_clk_type clk_type,
+			 uint32_t mask,
+			 bool lock_needed);
+int smu_set_mp1_state(struct smu_context *smu,
+		      enum pp_mp1_state mp1_state);
+int smu_set_df_cstate(struct smu_context *smu,
+		      enum pp_df_cstate state);
+
+int smu_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
+					 struct pp_smu_nv_clock_table *max_clocks);
+
+int smu_get_uclk_dpm_states(struct smu_context *smu,
+			    unsigned int *clock_values_in_khz,
+			    unsigned int *num_states);
+
+int smu_get_dpm_clock_table(struct smu_context *smu,
+			    struct dpm_clocks *clock_table);
+
+uint32_t smu_get_pptable_power_limit(struct smu_context *smu);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h
index 78e5927b7711..e3291259b249 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/arcturus_ppsmc.h
@@ -95,8 +95,7 @@
 
 //BTC
 #define PPSMC_MSG_RunAfllBtc                     0x30
-#define PPSMC_MSG_RunGfxDcBtc                    0x31
-#define PPSMC_MSG_RunSocDcBtc                    0x32
+#define PPSMC_MSG_RunDcBtc                       0x31
 
 //Debug
 #define PPSMC_MSG_DramLogSetDramAddrHigh         0x33
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 7bf9a14bfa0b..af977675fd33 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -355,6 +355,10 @@ struct pp_hwmgr_func {
 	int (*set_mp1_state)(struct pp_hwmgr *hwmgr, enum pp_mp1_state mp1_state);
 	int (*asic_reset)(struct pp_hwmgr *hwmgr, enum SMU_ASIC_RESET_MODE mode);
 	int (*smu_i2c_bus_access)(struct pp_hwmgr *hwmgr, bool aquire);
+	int (*set_df_cstate)(struct pp_hwmgr *hwmgr, enum pp_df_cstate state);
+	int (*set_xgmi_pstate)(struct pp_hwmgr *hwmgr, uint32_t pstate);
+	int (*disable_power_features_for_compute_performance)(struct pp_hwmgr *hwmgr,
+					bool disable);
 };
 
 struct pp_table_func {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
index e02950b505fa..a886f0644d24 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu11_driver_if_arcturus.h
@@ -137,29 +137,29 @@
 #define FEATURE_DS_SOCCLK_MASK            (1 << FEATURE_DS_SOCCLK_BIT            )
 #define FEATURE_DS_LCLK_MASK              (1 << FEATURE_DS_LCLK_BIT              )
 #define FEATURE_DS_FCLK_MASK              (1 << FEATURE_DS_FCLK_BIT              )
-#define FEATURE_DS_LCLK_MASK              (1 << FEATURE_DS_LCLK_BIT              )
+#define FEATURE_DS_UCLK_MASK              (1 << FEATURE_DS_UCLK_BIT              )
 #define FEATURE_GFX_ULV_MASK              (1 << FEATURE_GFX_ULV_BIT              )
-#define FEATURE_VCN_PG_MASK               (1 << FEATURE_VCN_PG_BIT               )
+#define FEATURE_DPM_VCN_MASK              (1 << FEATURE_DPM_VCN_BIT              )
 #define FEATURE_RSMU_SMN_CG_MASK          (1 << FEATURE_RSMU_SMN_CG_BIT          )
 #define FEATURE_WAFL_CG_MASK              (1 << FEATURE_WAFL_CG_BIT              )
 
 #define FEATURE_PPT_MASK                  (1 << FEATURE_PPT_BIT                  )
 #define FEATURE_TDC_MASK                  (1 << FEATURE_TDC_BIT                  )
-#define FEATURE_APCC_MASK                 (1 << FEATURE_APCC_BIT                 )
+#define FEATURE_APCC_PLUS_MASK            (1 << FEATURE_APCC_PLUS_BIT            )
 #define FEATURE_VR0HOT_MASK               (1 << FEATURE_VR0HOT_BIT               )
 #define FEATURE_VR1HOT_MASK               (1 << FEATURE_VR1HOT_BIT               )
 #define FEATURE_FW_CTF_MASK               (1 << FEATURE_FW_CTF_BIT               )
 #define FEATURE_FAN_CONTROL_MASK          (1 << FEATURE_FAN_CONTROL_BIT          )
 #define FEATURE_THERMAL_MASK              (1 << FEATURE_THERMAL_BIT              )
 
-#define FEATURE_OUT_OF_BAND_MONITOR_MASK  (1 << EATURE_OUT_OF_BAND_MONITOR_BIT   )
-#define FEATURE_TEMP_DEPENDENT_VMIN_MASK  (1 << FEATURE_TEMP_DEPENDENT_VMIN_MASK )
+#define FEATURE_OUT_OF_BAND_MONITOR_MASK  (1 << FEATURE_OUT_OF_BAND_MONITOR_BIT   )
+#define FEATURE_TEMP_DEPENDENT_VMIN_MASK  (1 << FEATURE_TEMP_DEPENDENT_VMIN_BIT )
 
 
 //FIXME need updating
 // Debug Overrides Bitmask
 #define DPM_OVERRIDE_DISABLE_UCLK_PID               0x00000001
-#define DPM_OVERRIDE_ENABLE_VOLT_LINK_VCN_FCLK      0x00000002
+#define DPM_OVERRIDE_DISABLE_VOLT_LINK_VCN_FCLK     0x00000002
 
 // I2C Config Bit Defines
 #define I2C_CONTROLLER_ENABLED           1
@@ -423,18 +423,30 @@ typedef enum {
 } PwrConfig_e;
 
 typedef enum {
-  XGMI_LINK_RATE_12 = 0,  // 12Gbps
-  XGMI_LINK_RATE_16,      // 16Gbps
-  XGMI_LINK_RATE_22,      // 22Gbps
-  XGMI_LINK_RATE_25,      // 25Gbps
+  XGMI_LINK_RATE_2 = 2,    // 2Gbps
+  XGMI_LINK_RATE_4 = 4,    // 4Gbps
+  XGMI_LINK_RATE_8 = 8,    // 8Gbps
+  XGMI_LINK_RATE_12 = 12,  // 12Gbps
+  XGMI_LINK_RATE_16 = 16,  // 16Gbps
+  XGMI_LINK_RATE_17 = 17,  // 17Gbps
+  XGMI_LINK_RATE_18 = 18,  // 18Gbps
+  XGMI_LINK_RATE_19 = 19,  // 19Gbps
+  XGMI_LINK_RATE_20 = 20,  // 20Gbps
+  XGMI_LINK_RATE_21 = 21,  // 21Gbps
+  XGMI_LINK_RATE_22 = 22,  // 22Gbps
+  XGMI_LINK_RATE_23 = 23,  // 23Gbps
+  XGMI_LINK_RATE_24 = 24,  // 24Gbps
+  XGMI_LINK_RATE_25 = 25,  // 25Gbps
   XGMI_LINK_RATE_COUNT
 } XGMI_LINK_RATE_e;
 
 typedef enum {
-  XGMI_LINK_WIDTH_2 = 0, // x2
-  XGMI_LINK_WIDTH_4,     // x4
-  XGMI_LINK_WIDTH_8,     // x8
-  XGMI_LINK_WIDTH_16,    // x16
+  XGMI_LINK_WIDTH_1 = 1,   // x1
+  XGMI_LINK_WIDTH_2 = 2,   // x2
+  XGMI_LINK_WIDTH_4 = 4,   // x4
+  XGMI_LINK_WIDTH_8 = 8,   // x8
+  XGMI_LINK_WIDTH_9 = 9,   // x9
+  XGMI_LINK_WIDTH_16 = 16, // x16
   XGMI_LINK_WIDTH_COUNT
 } XGMI_LINK_WIDTH_e;
 
@@ -696,7 +708,11 @@ typedef struct {
   uint8_t      GpioI2cSda;          // Serial Data
   uint16_t     GpioPadding;
 
-  uint32_t     BoardReserved[9];
+  // Platform input telemetry voltage coefficient
+  uint32_t     BoardVoltageCoeffA;    // decode by /1000
+  uint32_t     BoardVoltageCoeffB;    // decode by /1000
+
+  uint32_t     BoardReserved[7];
 
   // Padding for MMHUB - do not modify this
   uint32_t     MmHubPadding[8]; // SMU internal use
@@ -802,7 +818,7 @@ typedef struct {
 
   uint32_t P2VCharzFreq[AVFS_VOLTAGE_COUNT]; // in 10KHz units
 
-  uint32_t EnabledAvfsModules[2];
+  uint32_t EnabledAvfsModules[3];
 
   uint32_t MmHubPadding[8]; // SMU internal use
 } AvfsFuseOverride_t;
@@ -865,7 +881,8 @@ typedef struct {
 //#define TABLE_ACTIVITY_MONITOR_COEFF  7
 #define TABLE_OVERDRIVE               7
 #define TABLE_WAFL_XGMI_TOPOLOGY      8
-#define TABLE_COUNT                   9
+#define TABLE_I2C_COMMANDS            9
+#define TABLE_COUNT                   10
 
 // These defines are used with the SMC_MSG_SetUclkFastSwitch message.
 typedef enum {
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_types.h b/drivers/gpu/drm/amd/powerplay/inc/smu_types.h
index b0dd05d431dd..d8c9b7f91fcc 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_types.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_types.h
@@ -114,6 +114,7 @@
        __SMU_DUMMY_MAP(PowerDownJpeg),                \
        __SMU_DUMMY_MAP(BacoAudioD3PME),               \
        __SMU_DUMMY_MAP(ArmD3),                        \
+       __SMU_DUMMY_MAP(RunDcBtc),                     \
        __SMU_DUMMY_MAP(RunGfxDcBtc),                  \
        __SMU_DUMMY_MAP(RunSocDcBtc),                  \
        __SMU_DUMMY_MAP(SetMemoryChannelEnable),       \
@@ -168,6 +169,7 @@
 	__SMU_DUMMY_MAP(PowerGateAtHub),              \
 	__SMU_DUMMY_MAP(SetSoftMinJpeg),              \
 	__SMU_DUMMY_MAP(SetHardMinFclkByFreq),        \
+	__SMU_DUMMY_MAP(DFCstateControl), \
 
 #undef __SMU_DUMMY_MAP
 #define __SMU_DUMMY_MAP(type)	SMU_MSG_##type
@@ -251,6 +253,7 @@ enum smu_clk_type {
        __SMU_DUMMY_MAP(TEMP_DEPENDENT_VMIN),           	\
        __SMU_DUMMY_MAP(MMHUB_PG),                      	\
        __SMU_DUMMY_MAP(ATHUB_PG),                      	\
+       __SMU_DUMMY_MAP(APCC_DFLL),                     	\
        __SMU_DUMMY_MAP(WAFL_CG),
 
 #undef __SMU_DUMMY_MAP
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
index 5bda8539447a..719844257713 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0.h
@@ -27,7 +27,7 @@
 
 #define SMU11_DRIVER_IF_VERSION_INV 0xFFFFFFFF
 #define SMU11_DRIVER_IF_VERSION_VG20 0x13
-#define SMU11_DRIVER_IF_VERSION_ARCT 0x09
+#define SMU11_DRIVER_IF_VERSION_ARCT 0x10
 #define SMU11_DRIVER_IF_VERSION_NV10 0x33
 #define SMU11_DRIVER_IF_VERSION_NV14 0x34
 
@@ -48,6 +48,8 @@
 
 #define SMU11_TOOL_SIZE			0x19000
 
+#define MAX_PCIE_CONF 2
+
 #define CLK_MAP(clk, index) \
 	[SMU_##clk] = {1, (index)}
 
@@ -88,6 +90,11 @@ struct smu_11_0_dpm_table {
 	uint32_t    max;        /* MHz */
 };
 
+struct smu_11_0_pcie_table {
+        uint8_t  pcie_gen[MAX_PCIE_CONF];
+        uint8_t  pcie_lane[MAX_PCIE_CONF];
+};
+
 struct smu_11_0_dpm_tables {
 	struct smu_11_0_dpm_table        soc_table;
 	struct smu_11_0_dpm_table        gfx_table;
@@ -100,6 +107,7 @@ struct smu_11_0_dpm_tables {
 	struct smu_11_0_dpm_table        display_table;
 	struct smu_11_0_dpm_table        phy_table;
 	struct smu_11_0_dpm_table        fclk_table;
+	struct smu_11_0_pcie_table       pcie_table;
 };
 
 struct smu_11_0_dpm_context {
@@ -130,6 +138,127 @@ enum smu_v11_0_baco_seq {
 	BACO_SEQ_COUNT,
 };
 
-void smu_v11_0_set_smu_funcs(struct smu_context *smu);
+int smu_v11_0_init_microcode(struct smu_context *smu);
+
+int smu_v11_0_load_microcode(struct smu_context *smu);
+
+int smu_v11_0_init_smc_tables(struct smu_context *smu);
+
+int smu_v11_0_fini_smc_tables(struct smu_context *smu);
+
+int smu_v11_0_init_power(struct smu_context *smu);
+
+int smu_v11_0_fini_power(struct smu_context *smu);
+
+int smu_v11_0_check_fw_status(struct smu_context *smu);
+
+int smu_v11_0_setup_pptable(struct smu_context *smu);
+
+int smu_v11_0_get_vbios_bootup_values(struct smu_context *smu);
+
+int smu_v11_0_get_clk_info_from_vbios(struct smu_context *smu);
+
+int smu_v11_0_check_pptable(struct smu_context *smu);
+
+int smu_v11_0_parse_pptable(struct smu_context *smu);
+
+int smu_v11_0_populate_smc_pptable(struct smu_context *smu);
+
+int smu_v11_0_check_fw_version(struct smu_context *smu);
+
+int smu_v11_0_write_pptable(struct smu_context *smu);
+
+int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu);
+
+int smu_v11_0_set_tool_table_location(struct smu_context *smu);
+
+int smu_v11_0_notify_memory_pool_location(struct smu_context *smu);
+
+int smu_v11_0_system_features_control(struct smu_context *smu,
+					     bool en);
+
+int
+smu_v11_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
+			      uint32_t param);
+
+int smu_v11_0_read_arg(struct smu_context *smu, uint32_t *arg);
+
+int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count);
+
+int smu_v11_0_set_allowed_mask(struct smu_context *smu);
+
+int smu_v11_0_get_enabled_mask(struct smu_context *smu,
+				      uint32_t *feature_mask, uint32_t num);
+
+int smu_v11_0_notify_display_change(struct smu_context *smu);
+
+int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n);
+
+int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
+					  enum smu_clk_type clk_id,
+					  uint32_t *value);
+
+int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu);
+
+int smu_v11_0_start_thermal_control(struct smu_context *smu);
+
+int smu_v11_0_stop_thermal_control(struct smu_context *smu);
+
+int smu_v11_0_read_sensor(struct smu_context *smu,
+				 enum amd_pp_sensors sensor,
+				 void *data, uint32_t *size);
+
+int smu_v11_0_set_deep_sleep_dcefclk(struct smu_context *smu, uint32_t clk);
+
+int
+smu_v11_0_display_clock_voltage_request(struct smu_context *smu,
+					struct pp_display_clock_request
+					*clock_req);
+
+uint32_t
+smu_v11_0_get_fan_control_mode(struct smu_context *smu);
+
+int
+smu_v11_0_set_fan_control_mode(struct smu_context *smu,
+			       uint32_t mode);
+
+int
+smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed);
+
+int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
+				       uint32_t speed);
+
+int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
+				     uint32_t pstate);
+
+int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable);
+
+int smu_v11_0_register_irq_handler(struct smu_context *smu);
+
+int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu);
+
+int smu_v11_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
+		struct pp_smu_nv_clock_table *max_clocks);
+
+bool smu_v11_0_baco_is_support(struct smu_context *smu);
+
+enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu);
+
+int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state);
+
+int smu_v11_0_baco_reset(struct smu_context *smu);
+
+int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
+						 uint32_t *min, uint32_t *max);
+
+int smu_v11_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t min, uint32_t max);
+
+int smu_v11_0_override_pcie_parameters(struct smu_context *smu);
+
+int smu_v11_0_set_default_od_settings(struct smu_context *smu, bool initialize, size_t overdrive_table_size);
+
+uint32_t smu_v11_0_get_max_power_limit(struct smu_context *smu);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
index 86cdc3393eac..b2f96a101124 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v11_0_pptable.h
@@ -141,7 +141,9 @@ struct smu_11_0_powerplay_table
       struct smu_11_0_power_saving_clock_table      power_saving_clock;
       struct smu_11_0_overdrive_table               overdrive_table;
 
+#ifndef SMU_11_0_PARTIAL_PPTABLE
       PPTable_t smc_pptable;                        //PPTable_t in smu11_driver_if.h
+#endif
 } __attribute__((packed));
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
index acf3db12f59f..9d81d789c713 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smu_v12_0.h
@@ -37,6 +37,44 @@ struct smu_12_0_cmn2aisc_mapping {
 	int	map_to;
 };
 
-void smu_v12_0_set_smu_funcs(struct smu_context *smu);
+int smu_v12_0_send_msg_without_waiting(struct smu_context *smu,
+					      uint16_t msg);
+
+int smu_v12_0_read_arg(struct smu_context *smu, uint32_t *arg);
+
+int smu_v12_0_wait_for_response(struct smu_context *smu);
+
+int
+smu_v12_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
+			      uint32_t param);
+
+int smu_v12_0_check_fw_status(struct smu_context *smu);
+
+int smu_v12_0_check_fw_version(struct smu_context *smu);
+
+int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate);
+
+int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate);
+
+int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable);
+
+uint32_t smu_v12_0_get_gfxoff_status(struct smu_context *smu);
+
+int smu_v12_0_gfx_off_control(struct smu_context *smu, bool enable);
+
+int smu_v12_0_init_smc_tables(struct smu_context *smu);
+
+int smu_v12_0_fini_smc_tables(struct smu_context *smu);
+
+int smu_v12_0_populate_smc_tables(struct smu_context *smu);
+
+int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
+						 uint32_t *min, uint32_t *max);
+
+int smu_v12_0_mode2_reset(struct smu_context *smu);
+
+int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t min, uint32_t max);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
index a0883038f3c3..0c66f0fe1aaf 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega20_ppsmc.h
@@ -120,7 +120,8 @@
 #define PPSMC_MSG_SetMGpuFanBoostLimitRpm        0x5D
 #define PPSMC_MSG_GetAVFSVoltageByDpm            0x5F
 #define PPSMC_MSG_BacoWorkAroundFlushVDCI        0x60
-#define PPSMC_Message_Count                      0x61
+#define PPSMC_MSG_DFCstateControl                0x63
+#define PPSMC_Message_Count                      0x64
 
 typedef uint32_t PPSMC_Result;
 typedef uint32_t PPSMC_Msg;
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
index 0b461404af6b..4a14fd1f9fd5 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.c
@@ -26,6 +26,7 @@
 #include <linux/pci.h>
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "atomfirmware.h"
 #include "amdgpu_atomfirmware.h"
 #include "smu_v11_0.h"
@@ -35,6 +36,7 @@
 #include "navi10_ppt.h"
 #include "smu_v11_0_pptable.h"
 #include "smu_v11_0_ppsmc.h"
+#include "nbio/nbio_7_4_sh_mask.h"
 
 #include "asic_reg/mp/mp_11_0_sh_mask.h"
 
@@ -177,6 +179,7 @@ static struct smu_11_0_cmn2aisc_mapping navi10_feature_mask_map[SMU_FEATURE_COUN
 	FEA_MAP(TEMP_DEPENDENT_VMIN),
 	FEA_MAP(MMHUB_PG),
 	FEA_MAP(ATHUB_PG),
+	FEA_MAP(APCC_DFLL),
 };
 
 static struct smu_11_0_cmn2aisc_mapping navi10_table_map[SMU_TABLE_COUNT] = {
@@ -205,7 +208,7 @@ static struct smu_11_0_cmn2aisc_mapping navi10_workload_map[PP_SMC_POWER_PROFILE
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING,		WORKLOAD_PPLIB_POWER_SAVING_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO,		WORKLOAD_PPLIB_VIDEO_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR,			WORKLOAD_PPLIB_VR_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_CUSTOM_BIT),
+	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_COMPUTE_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
 };
 
@@ -327,40 +330,52 @@ navi10_get_allowed_feature_mask(struct smu_context *smu,
 	memset(feature_mask, 0, sizeof(uint32_t) * num);
 
 	*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_PREFETCHER_BIT)
-				| FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT)
-				| FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT)
 				| FEATURE_MASK(FEATURE_DPM_MP0CLK_BIT)
-				| FEATURE_MASK(FEATURE_DPM_LINK_BIT)
-				| FEATURE_MASK(FEATURE_GFX_ULV_BIT)
 				| FEATURE_MASK(FEATURE_RSMU_SMN_CG_BIT)
 				| FEATURE_MASK(FEATURE_DS_SOCCLK_BIT)
 				| FEATURE_MASK(FEATURE_PPT_BIT)
 				| FEATURE_MASK(FEATURE_TDC_BIT)
 				| FEATURE_MASK(FEATURE_GFX_EDC_BIT)
+				| FEATURE_MASK(FEATURE_APCC_PLUS_BIT)
 				| FEATURE_MASK(FEATURE_VR0HOT_BIT)
 				| FEATURE_MASK(FEATURE_FAN_CONTROL_BIT)
 				| FEATURE_MASK(FEATURE_THERMAL_BIT)
 				| FEATURE_MASK(FEATURE_LED_DISPLAY_BIT)
-				| FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT)
-				| FEATURE_MASK(FEATURE_DS_GFXCLK_BIT)
+				| FEATURE_MASK(FEATURE_DS_LCLK_BIT)
 				| FEATURE_MASK(FEATURE_DS_DCEFCLK_BIT)
 				| FEATURE_MASK(FEATURE_FW_DSTATE_BIT)
 				| FEATURE_MASK(FEATURE_BACO_BIT)
 				| FEATURE_MASK(FEATURE_ACDC_BIT)
 				| FEATURE_MASK(FEATURE_GFX_SS_BIT)
 				| FEATURE_MASK(FEATURE_APCC_DFLL_BIT)
-				| FEATURE_MASK(FEATURE_FW_CTF_BIT);
+				| FEATURE_MASK(FEATURE_FW_CTF_BIT)
+				| FEATURE_MASK(FEATURE_OUT_OF_BAND_MONITOR_BIT);
+
+	if (adev->pm.pp_feature & PP_SOCCLK_DPM_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_SOCCLK_BIT);
+
+	if (adev->pm.pp_feature & PP_SCLK_DPM_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_GFXCLK_BIT);
+
+	if (adev->pm.pp_feature & PP_PCIE_DPM_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_LINK_BIT);
+
+	if (adev->pm.pp_feature & PP_DCEFCLK_DPM_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_DCEFCLK_BIT);
 
 	if (adev->pm.pp_feature & PP_MCLK_DPM_MASK)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DPM_UCLK_BIT)
 				| FEATURE_MASK(FEATURE_MEM_VDDCI_SCALING_BIT)
 				| FEATURE_MASK(FEATURE_MEM_MVDD_SCALING_BIT);
 
-	if (adev->pm.pp_feature & PP_GFXOFF_MASK) {
+	if (adev->pm.pp_feature & PP_ULV_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFX_ULV_BIT);
+
+	if (adev->pm.pp_feature & PP_SCLK_DEEP_SLEEP_MASK)
+		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_DS_GFXCLK_BIT);
+
+	if (adev->pm.pp_feature & PP_GFXOFF_MASK)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_GFXOFF_BIT);
-		/* TODO: remove it once fw fix the bug */
-		*(uint64_t *)feature_mask &= ~FEATURE_MASK(FEATURE_FW_DSTATE_BIT);
-	}
 
 	if (smu->adev->pg_flags & AMD_PG_SUPPORT_MMHUB)
 		*(uint64_t *)feature_mask |= FEATURE_MASK(FEATURE_MMHUB_PG_BIT);
@@ -585,6 +600,7 @@ static int navi10_set_default_dpm_table(struct smu_context *smu)
 	struct smu_table_context *table_context = &smu->smu_table;
 	struct smu_11_0_dpm_context *dpm_context = smu_dpm->dpm_context;
 	PPTable_t *driver_ppt = NULL;
+	int i;
 
 	driver_ppt = table_context->driver_pptable;
 
@@ -615,6 +631,11 @@ static int navi10_set_default_dpm_table(struct smu_context *smu)
 	dpm_context->dpm_tables.phy_table.min = driver_ppt->FreqTablePhyclk[0];
 	dpm_context->dpm_tables.phy_table.max = driver_ppt->FreqTablePhyclk[NUM_PHYCLK_DPM_LEVELS - 1];
 
+	for (i = 0; i < MAX_PCIE_CONF; i++) {
+		dpm_context->dpm_tables.pcie_table.pcie_gen[i] = driver_ppt->PcieGenSpeed[i];
+		dpm_context->dpm_tables.pcie_table.pcie_lane[i] = driver_ppt->PcieLaneCount[i];
+	}
+
 	return 0;
 }
 
@@ -677,13 +698,29 @@ static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu
 	return dpm_desc->SnapToDiscrete == 0 ? true : false;
 }
 
+static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_ID feature)
+{
+	return od_table->cap[feature];
+}
+
+
 static int navi10_print_clk_levels(struct smu_context *smu,
 			enum smu_clk_type clk_type, char *buf)
 {
+	uint16_t *curve_settings;
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0;
 	uint32_t freq_values[3] = {0};
 	uint32_t mark_index = 0;
+	struct smu_table_context *table_context = &smu->smu_table;
+	uint32_t gen_speed, lane_width;
+	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
+	struct smu_11_0_dpm_context *dpm_context = smu_dpm->dpm_context;
+	struct amdgpu_device *adev = smu->adev;
+	PPTable_t *pptable = (PPTable_t *)table_context->driver_pptable;
+	OverDriveTable_t *od_table =
+		(OverDriveTable_t *)table_context->overdrive_table;
+	struct smu_11_0_overdrive_table *od_settings = smu->od_settings;
 
 	switch (clk_type) {
 	case SMU_GFXCLK:
@@ -734,6 +771,69 @@ static int navi10_print_clk_levels(struct smu_context *smu,
 
 		}
 		break;
+	case SMU_PCIE:
+		gen_speed = (RREG32_PCIE(smnPCIE_LC_SPEED_CNTL) &
+			     PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK)
+			>> PSWUSP0_PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT;
+		lane_width = (RREG32_PCIE(smnPCIE_LC_LINK_WIDTH_CNTL) &
+			      PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK)
+			>> PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT;
+		for (i = 0; i < NUM_LINK_LEVELS; i++)
+			size += sprintf(buf + size, "%d: %s %s %dMhz %s\n", i,
+					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 0) ? "2.5GT/s," :
+					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 1) ? "5.0GT/s," :
+					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 2) ? "8.0GT/s," :
+					(dpm_context->dpm_tables.pcie_table.pcie_gen[i] == 3) ? "16.0GT/s," : "",
+					(dpm_context->dpm_tables.pcie_table.pcie_lane[i] == 1) ? "x1" :
+					(dpm_context->dpm_tables.pcie_table.pcie_lane[i] == 2) ? "x2" :
+					(dpm_context->dpm_tables.pcie_table.pcie_lane[i] == 3) ? "x4" :
+					(dpm_context->dpm_tables.pcie_table.pcie_lane[i] == 4) ? "x8" :
+					(dpm_context->dpm_tables.pcie_table.pcie_lane[i] == 5) ? "x12" :
+					(dpm_context->dpm_tables.pcie_table.pcie_lane[i] == 6) ? "x16" : "",
+					pptable->LclkFreq[i],
+					(gen_speed == dpm_context->dpm_tables.pcie_table.pcie_gen[i]) &&
+					(lane_width == dpm_context->dpm_tables.pcie_table.pcie_lane[i]) ?
+					"*" : "");
+		break;
+	case SMU_OD_SCLK:
+		if (!smu->od_enabled || !od_table || !od_settings)
+			break;
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS))
+			break;
+		size += sprintf(buf + size, "OD_SCLK:\n");
+		size += sprintf(buf + size, "0: %uMhz\n1: %uMhz\n", od_table->GfxclkFmin, od_table->GfxclkFmax);
+		break;
+	case SMU_OD_MCLK:
+		if (!smu->od_enabled || !od_table || !od_settings)
+			break;
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX))
+			break;
+		size += sprintf(buf + size, "OD_MCLK:\n");
+		size += sprintf(buf + size, "0: %uMHz\n", od_table->UclkFmax);
+		break;
+	case SMU_OD_VDDC_CURVE:
+		if (!smu->od_enabled || !od_table || !od_settings)
+			break;
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE))
+			break;
+		size += sprintf(buf + size, "OD_VDDC_CURVE:\n");
+		for (i = 0; i < 3; i++) {
+			switch (i) {
+			case 0:
+				curve_settings = &od_table->GfxclkFreq1;
+				break;
+			case 1:
+				curve_settings = &od_table->GfxclkFreq2;
+				break;
+			case 2:
+				curve_settings = &od_table->GfxclkFreq3;
+				break;
+			default:
+				break;
+			}
+			size += sprintf(buf + size, "%d: %uMHz @ %umV\n", i, curve_settings[0], curve_settings[1] / NAVI10_VOLTAGE_SCALE);
+		}
+		break;
 	default:
 		break;
 	}
@@ -759,6 +859,12 @@ static int navi10_force_clk_levels(struct smu_context *smu,
 	case SMU_UCLK:
 	case SMU_DCEFCLK:
 	case SMU_FCLK:
+		/* There is only 2 levels for fine grained DPM */
+		if (navi10_is_support_fine_grained_dpm(smu, clk_type)) {
+			soft_max_level = (soft_max_level >= 1 ? 1 : 0);
+			soft_min_level = (soft_min_level >= 1 ? 1 : 0);
+		}
+
 		ret = smu_get_dpm_freq_by_index(smu, clk_type, soft_min_level, &min_freq);
 		if (ret)
 			return size;
@@ -783,13 +889,13 @@ static int navi10_populate_umd_state_clk(struct smu_context *smu)
 	int ret = 0;
 	uint32_t min_sclk_freq = 0, min_mclk_freq = 0;
 
-	ret = smu_get_dpm_freq_range(smu, SMU_SCLK, &min_sclk_freq, NULL);
+	ret = smu_get_dpm_freq_range(smu, SMU_SCLK, &min_sclk_freq, NULL, false);
 	if (ret)
 		return ret;
 
 	smu->pstate_sclk = min_sclk_freq * 100;
 
-	ret = smu_get_dpm_freq_range(smu, SMU_MCLK, &min_mclk_freq, NULL);
+	ret = smu_get_dpm_freq_range(smu, SMU_MCLK, &min_mclk_freq, NULL, false);
 	if (ret)
 		return ret;
 
@@ -842,7 +948,7 @@ static int navi10_pre_display_config_changed(struct smu_context *smu)
 		return ret;
 
 	if (smu_feature_is_enabled(smu, SMU_FEATURE_DPM_UCLK_BIT)) {
-		ret = smu_get_dpm_freq_range(smu, SMU_UCLK, NULL, &max_freq);
+		ret = smu_get_dpm_freq_range(smu, SMU_UCLK, NULL, &max_freq, false);
 		if (ret)
 			return ret;
 		ret = smu_set_hard_freq_range(smu, SMU_UCLK, 0, max_freq);
@@ -892,7 +998,7 @@ static int navi10_force_dpm_limit_value(struct smu_context *smu, bool highest)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++) {
 		clk_type = clks[i];
-		ret = smu_get_dpm_freq_range(smu, clk_type, &min_freq, &max_freq);
+		ret = smu_get_dpm_freq_range(smu, clk_type, &min_freq, &max_freq, false);
 		if (ret)
 			return ret;
 
@@ -919,7 +1025,7 @@ static int navi10_unforce_dpm_levels(struct smu_context *smu)
 
 	for (i = 0; i < ARRAY_SIZE(clks); i++) {
 		clk_type = clks[i];
-		ret = smu_get_dpm_freq_range(smu, clk_type, &min_freq, &max_freq);
+		ret = smu_get_dpm_freq_range(smu, clk_type, &min_freq, &max_freq, false);
 		if (ret)
 			return ret;
 
@@ -1254,7 +1360,9 @@ static int navi10_notify_smc_dispaly_config(struct smu_context *smu)
 	if (smu_feature_is_supported(smu, SMU_FEATURE_DPM_DCEFCLK_BIT)) {
 		clock_req.clock_type = amd_pp_dcef_clock;
 		clock_req.clock_freq_in_khz = min_clocks.dcef_clock * 10;
-		if (!smu_display_clock_voltage_request(smu, &clock_req)) {
+
+		ret = smu_v11_0_display_clock_voltage_request(smu, &clock_req);
+		if (!ret) {
 			if (smu_feature_is_supported(smu, SMU_FEATURE_DS_DCEFCLK_BIT)) {
 				ret = smu_send_smc_msg_with_param(smu,
 								  SMU_MSG_SetMinDeepSleepDcefclk,
@@ -1408,7 +1516,7 @@ static int navi10_read_sensor(struct smu_context *smu,
 		*size = 4;
 		break;
 	default:
-		ret = smu_smc_read_sensor(smu, sensor, data, size);
+		ret = smu_v11_0_read_sensor(smu, sensor, data, size);
 	}
 	mutex_unlock(&smu->sensor_lock);
 
@@ -1451,18 +1559,47 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu)
 	uint32_t sclk_freq = 0, uclk_freq = 0;
 	uint32_t uclk_level = 0;
 
-	switch (adev->pdev->revision) {
-	case 0xf0: /* XTX */
-	case 0xc0:
-		sclk_freq = NAVI10_PEAK_SCLK_XTX;
-		break;
-	case 0xf1: /* XT */
-	case 0xc1:
-		sclk_freq = NAVI10_PEAK_SCLK_XT;
+	switch (adev->asic_type) {
+	case CHIP_NAVI10:
+		switch (adev->pdev->revision) {
+		case 0xf0: /* XTX */
+		case 0xc0:
+			sclk_freq = NAVI10_PEAK_SCLK_XTX;
+			break;
+		case 0xf1: /* XT */
+		case 0xc1:
+			sclk_freq = NAVI10_PEAK_SCLK_XT;
+			break;
+		default: /* XL */
+			sclk_freq = NAVI10_PEAK_SCLK_XL;
+			break;
+		}
 		break;
-	default: /* XL */
-		sclk_freq = NAVI10_PEAK_SCLK_XL;
+	case CHIP_NAVI14:
+		switch (adev->pdev->revision) {
+		case 0xc7: /* XT */
+		case 0xf4:
+			sclk_freq = NAVI14_UMD_PSTATE_PEAK_XT_GFXCLK;
+			break;
+		case 0xc1: /* XTM */
+		case 0xf2:
+			sclk_freq = NAVI14_UMD_PSTATE_PEAK_XTM_GFXCLK;
+			break;
+		case 0xc3: /* XLM */
+		case 0xf3:
+			sclk_freq = NAVI14_UMD_PSTATE_PEAK_XLM_GFXCLK;
+			break;
+		case 0xc5: /* XTX */
+		case 0xf6:
+			sclk_freq = NAVI14_UMD_PSTATE_PEAK_XLM_GFXCLK;
+			break;
+		default: /* XL */
+			sclk_freq = NAVI14_UMD_PSTATE_PEAK_XL_GFXCLK;
+			break;
+		}
 		break;
+	default:
+		return -EINVAL;
 	}
 
 	ret = smu_get_dpm_level_count(smu, SMU_UCLK, &uclk_level);
@@ -1485,10 +1622,6 @@ static int navi10_set_peak_clock_by_device(struct smu_context *smu)
 static int navi10_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
 {
 	int ret = 0;
-	struct amdgpu_device *adev = smu->adev;
-
-	if (adev->asic_type != CHIP_NAVI10)
-		return -EINVAL;
 
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
@@ -1541,17 +1674,22 @@ static int navi10_display_disable_memory_clock_switch(struct smu_context *smu,
 	return ret;
 }
 
+static uint32_t navi10_get_pptable_power_limit(struct smu_context *smu)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	return pptable->SocketPowerLimitAc[PPT_THROTTLER_PPT0];
+}
+
 static int navi10_get_power_limit(struct smu_context *smu,
 				     uint32_t *limit,
-				     bool asic_default)
+				     bool cap)
 {
 	PPTable_t *pptable = smu->smu_table.driver_pptable;
 	uint32_t asic_default_power_limit = 0;
 	int ret = 0;
 	int power_src;
 
-	if (!smu->default_power_limit ||
-	    !smu->power_limit) {
+	if (!smu->power_limit) {
 		if (smu_feature_is_enabled(smu, SMU_FEATURE_PPT_BIT)) {
 			power_src = smu_power_get_index(smu, SMU_POWER_SOURCE_AC);
 			if (power_src < 0)
@@ -1574,23 +1712,291 @@ static int navi10_get_power_limit(struct smu_context *smu,
 				pptable->SocketPowerLimitAc[PPT_THROTTLER_PPT0];
 		}
 
-		if (smu->od_enabled) {
-			asic_default_power_limit *= (100 + smu->smu_table.TDPODLimit);
-			asic_default_power_limit /= 100;
-		}
-
-		smu->default_power_limit = asic_default_power_limit;
 		smu->power_limit = asic_default_power_limit;
 	}
 
-	if (asic_default)
-		*limit = smu->default_power_limit;
+	if (cap)
+		*limit = smu_v11_0_get_max_power_limit(smu);
 	else
 		*limit = smu->power_limit;
 
 	return 0;
 }
 
+static int navi10_update_pcie_parameters(struct smu_context *smu,
+				     uint32_t pcie_gen_cap,
+				     uint32_t pcie_width_cap)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	int ret, i;
+	uint32_t smu_pcie_arg;
+
+	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
+	struct smu_11_0_dpm_context *dpm_context = smu_dpm->dpm_context;
+
+	for (i = 0; i < NUM_LINK_LEVELS; i++) {
+		smu_pcie_arg = (i << 16) |
+			((pptable->PcieGenSpeed[i] <= pcie_gen_cap) ? (pptable->PcieGenSpeed[i] << 8) :
+				(pcie_gen_cap << 8)) | ((pptable->PcieLaneCount[i] <= pcie_width_cap) ?
+					pptable->PcieLaneCount[i] : pcie_width_cap);
+		ret = smu_send_smc_msg_with_param(smu,
+					  SMU_MSG_OverridePcieParameters,
+					  smu_pcie_arg);
+
+		if (ret)
+			return ret;
+
+		if (pptable->PcieGenSpeed[i] > pcie_gen_cap)
+			dpm_context->dpm_tables.pcie_table.pcie_gen[i] = pcie_gen_cap;
+		if (pptable->PcieLaneCount[i] > pcie_width_cap)
+			dpm_context->dpm_tables.pcie_table.pcie_lane[i] = pcie_width_cap;
+	}
+
+	return 0;
+}
+
+static inline void navi10_dump_od_table(OverDriveTable_t *od_table) {
+	pr_debug("OD: Gfxclk: (%d, %d)\n", od_table->GfxclkFmin, od_table->GfxclkFmax);
+	pr_debug("OD: Gfx1: (%d, %d)\n", od_table->GfxclkFreq1, od_table->GfxclkVolt1);
+	pr_debug("OD: Gfx2: (%d, %d)\n", od_table->GfxclkFreq2, od_table->GfxclkVolt2);
+	pr_debug("OD: Gfx3: (%d, %d)\n", od_table->GfxclkFreq3, od_table->GfxclkVolt3);
+	pr_debug("OD: UclkFmax: %d\n", od_table->UclkFmax);
+	pr_debug("OD: OverDrivePct: %d\n", od_table->OverDrivePct);
+}
+
+static int navi10_od_setting_check_range(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODSETTING_ID setting, uint32_t value)
+{
+	if (value < od_table->min[setting]) {
+		pr_warn("OD setting (%d, %d) is less than the minimum allowed (%d)\n", setting, value, od_table->min[setting]);
+		return -EINVAL;
+	}
+	if (value > od_table->max[setting]) {
+		pr_warn("OD setting (%d, %d) is greater than the maximum allowed (%d)\n", setting, value, od_table->max[setting]);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int navi10_setup_od_limits(struct smu_context *smu) {
+	struct smu_11_0_overdrive_table *overdrive_table = NULL;
+	struct smu_11_0_powerplay_table *powerplay_table = NULL;
+
+	if (!smu->smu_table.power_play_table) {
+		pr_err("powerplay table uninitialized!\n");
+		return -ENOENT;
+	}
+	powerplay_table = (struct smu_11_0_powerplay_table *)smu->smu_table.power_play_table;
+	overdrive_table = &powerplay_table->overdrive_table;
+	if (!smu->od_settings) {
+		smu->od_settings = kmemdup(overdrive_table, sizeof(struct smu_11_0_overdrive_table), GFP_KERNEL);
+	} else {
+		memcpy(smu->od_settings, overdrive_table, sizeof(struct smu_11_0_overdrive_table));
+	}
+	return 0;
+}
+
+static int navi10_set_default_od_settings(struct smu_context *smu, bool initialize) {
+	OverDriveTable_t *od_table;
+	int ret = 0;
+
+	ret = smu_v11_0_set_default_od_settings(smu, initialize, sizeof(OverDriveTable_t));
+	if (ret)
+		return ret;
+
+	if (initialize) {
+		ret = navi10_setup_od_limits(smu);
+		if (ret) {
+			pr_err("Failed to retrieve board OD limits\n");
+			return ret;
+		}
+
+	}
+
+	od_table = (OverDriveTable_t *)smu->smu_table.overdrive_table;
+	if (od_table) {
+		navi10_dump_od_table(od_table);
+	}
+
+	return ret;
+}
+
+static int navi10_od_edit_dpm_table(struct smu_context *smu, enum PP_OD_DPM_TABLE_COMMAND type, long input[], uint32_t size) {
+	int i;
+	int ret = 0;
+	struct smu_table_context *table_context = &smu->smu_table;
+	OverDriveTable_t *od_table;
+	struct smu_11_0_overdrive_table *od_settings;
+	enum SMU_11_0_ODSETTING_ID freq_setting, voltage_setting;
+	uint16_t *freq_ptr, *voltage_ptr;
+	od_table = (OverDriveTable_t *)table_context->overdrive_table;
+
+	if (!smu->od_enabled) {
+		pr_warn("OverDrive is not enabled!\n");
+		return -EINVAL;
+	}
+
+	if (!smu->od_settings) {
+		pr_err("OD board limits are not set!\n");
+		return -ENOENT;
+	}
+
+	od_settings = smu->od_settings;
+
+	switch (type) {
+	case PP_OD_EDIT_SCLK_VDDC_TABLE:
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_LIMITS)) {
+			pr_warn("GFXCLK_LIMITS not supported!\n");
+			return -ENOTSUPP;
+		}
+		if (!table_context->overdrive_table) {
+			pr_err("Overdrive is not initialized\n");
+			return -EINVAL;
+		}
+		for (i = 0; i < size; i += 2) {
+			if (i + 2 > size) {
+				pr_info("invalid number of input parameters %d\n", size);
+				return -EINVAL;
+			}
+			switch (input[i]) {
+			case 0:
+				freq_setting = SMU_11_0_ODSETTING_GFXCLKFMIN;
+				freq_ptr = &od_table->GfxclkFmin;
+				if (input[i + 1] > od_table->GfxclkFmax) {
+					pr_info("GfxclkFmin (%ld) must be <= GfxclkFmax (%u)!\n",
+						input[i + 1],
+						od_table->GfxclkFmin);
+					return -EINVAL;
+				}
+				break;
+			case 1:
+				freq_setting = SMU_11_0_ODSETTING_GFXCLKFMAX;
+				freq_ptr = &od_table->GfxclkFmax;
+				if (input[i + 1] < od_table->GfxclkFmin) {
+					pr_info("GfxclkFmax (%ld) must be >= GfxclkFmin (%u)!\n",
+						input[i + 1],
+						od_table->GfxclkFmax);
+					return -EINVAL;
+				}
+				break;
+			default:
+				pr_info("Invalid SCLK_VDDC_TABLE index: %ld\n", input[i]);
+				pr_info("Supported indices: [0:min,1:max]\n");
+				return -EINVAL;
+			}
+			ret = navi10_od_setting_check_range(od_settings, freq_setting, input[i + 1]);
+			if (ret)
+				return ret;
+			*freq_ptr = input[i + 1];
+		}
+		break;
+	case PP_OD_EDIT_MCLK_VDDC_TABLE:
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_UCLK_MAX)) {
+			pr_warn("UCLK_MAX not supported!\n");
+			return -ENOTSUPP;
+		}
+		if (size < 2) {
+			pr_info("invalid number of parameters: %d\n", size);
+			return -EINVAL;
+		}
+		if (input[0] != 1) {
+			pr_info("Invalid MCLK_VDDC_TABLE index: %ld\n", input[0]);
+			pr_info("Supported indices: [1:max]\n");
+			return -EINVAL;
+		}
+		ret = navi10_od_setting_check_range(od_settings, SMU_11_0_ODSETTING_UCLKFMAX, input[1]);
+		if (ret)
+			return ret;
+		od_table->UclkFmax = input[1];
+		break;
+	case PP_OD_COMMIT_DPM_TABLE:
+		navi10_dump_od_table(od_table);
+		ret = smu_update_table(smu, SMU_TABLE_OVERDRIVE, 0, (void *)od_table, true);
+		if (ret) {
+			pr_err("Failed to import overdrive table!\n");
+			return ret;
+		}
+		// no lock needed because smu_od_edit_dpm_table has it
+		ret = smu_handle_task(smu, smu->smu_dpm.dpm_level,
+			AMD_PP_TASK_READJUST_POWER_STATE,
+			false);
+		if (ret) {
+			return ret;
+		}
+		break;
+	case PP_OD_EDIT_VDDC_CURVE:
+		if (!navi10_od_feature_is_supported(od_settings, SMU_11_0_ODFEATURE_GFXCLK_CURVE)) {
+			pr_warn("GFXCLK_CURVE not supported!\n");
+			return -ENOTSUPP;
+		}
+		if (size < 3) {
+			pr_info("invalid number of parameters: %d\n", size);
+			return -EINVAL;
+		}
+		if (!od_table) {
+			pr_info("Overdrive is not initialized\n");
+			return -EINVAL;
+		}
+
+		switch (input[0]) {
+		case 0:
+			freq_setting = SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P1;
+			voltage_setting = SMU_11_0_ODSETTING_VDDGFXCURVEVOLTAGE_P1;
+			freq_ptr = &od_table->GfxclkFreq1;
+			voltage_ptr = &od_table->GfxclkVolt1;
+			break;
+		case 1:
+			freq_setting = SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P2;
+			voltage_setting = SMU_11_0_ODSETTING_VDDGFXCURVEVOLTAGE_P2;
+			freq_ptr = &od_table->GfxclkFreq2;
+			voltage_ptr = &od_table->GfxclkVolt2;
+			break;
+		case 2:
+			freq_setting = SMU_11_0_ODSETTING_VDDGFXCURVEFREQ_P3;
+			voltage_setting = SMU_11_0_ODSETTING_VDDGFXCURVEVOLTAGE_P3;
+			freq_ptr = &od_table->GfxclkFreq3;
+			voltage_ptr = &od_table->GfxclkVolt3;
+			break;
+		default:
+			pr_info("Invalid VDDC_CURVE index: %ld\n", input[0]);
+			pr_info("Supported indices: [0, 1, 2]\n");
+			return -EINVAL;
+		}
+		ret = navi10_od_setting_check_range(od_settings, freq_setting, input[1]);
+		if (ret)
+			return ret;
+		// Allow setting zero to disable the OverDrive VDDC curve
+		if (input[2] != 0) {
+			ret = navi10_od_setting_check_range(od_settings, voltage_setting, input[2]);
+			if (ret)
+				return ret;
+			*freq_ptr = input[1];
+			*voltage_ptr = ((uint16_t)input[2]) * NAVI10_VOLTAGE_SCALE;
+			pr_debug("OD: set curve %ld: (%d, %d)\n", input[0], *freq_ptr, *voltage_ptr);
+		} else {
+			// If setting 0, disable all voltage curve settings
+			od_table->GfxclkVolt1 = 0;
+			od_table->GfxclkVolt2 = 0;
+			od_table->GfxclkVolt3 = 0;
+		}
+		navi10_dump_od_table(od_table);
+		break;
+	default:
+		return -ENOSYS;
+	}
+	return ret;
+}
+
+static int navi10_run_btc(struct smu_context *smu)
+{
+	int ret = 0;
+
+	ret = smu_send_smc_msg(smu, SMU_MSG_RunBtc);
+	if (ret)
+		pr_err("RunBtc failed!\n");
+
+	return ret;
+}
+
 static const struct pptable_funcs navi10_ppt_funcs = {
 	.tables_init = navi10_tables_init,
 	.alloc_dpm_context = navi10_allocate_dpm_context,
@@ -1629,12 +2035,62 @@ static const struct pptable_funcs navi10_ppt_funcs = {
 	.get_thermal_temperature_range = navi10_get_thermal_temperature_range,
 	.display_disable_memory_clock_switch = navi10_display_disable_memory_clock_switch,
 	.get_power_limit = navi10_get_power_limit,
+	.update_pcie_parameters = navi10_update_pcie_parameters,
+	.init_microcode = smu_v11_0_init_microcode,
+	.load_microcode = smu_v11_0_load_microcode,
+	.init_smc_tables = smu_v11_0_init_smc_tables,
+	.fini_smc_tables = smu_v11_0_fini_smc_tables,
+	.init_power = smu_v11_0_init_power,
+	.fini_power = smu_v11_0_fini_power,
+	.check_fw_status = smu_v11_0_check_fw_status,
+	.setup_pptable = smu_v11_0_setup_pptable,
+	.get_vbios_bootup_values = smu_v11_0_get_vbios_bootup_values,
+	.get_clk_info_from_vbios = smu_v11_0_get_clk_info_from_vbios,
+	.check_pptable = smu_v11_0_check_pptable,
+	.parse_pptable = smu_v11_0_parse_pptable,
+	.populate_smc_tables = smu_v11_0_populate_smc_pptable,
+	.check_fw_version = smu_v11_0_check_fw_version,
+	.write_pptable = smu_v11_0_write_pptable,
+	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_tool_table_location = smu_v11_0_set_tool_table_location,
+	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
+	.system_features_control = smu_v11_0_system_features_control,
+	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
+	.read_smc_arg = smu_v11_0_read_arg,
+	.init_display_count = smu_v11_0_init_display_count,
+	.set_allowed_mask = smu_v11_0_set_allowed_mask,
+	.get_enabled_mask = smu_v11_0_get_enabled_mask,
+	.notify_display_change = smu_v11_0_notify_display_change,
+	.set_power_limit = smu_v11_0_set_power_limit,
+	.get_current_clk_freq = smu_v11_0_get_current_clk_freq,
+	.init_max_sustainable_clocks = smu_v11_0_init_max_sustainable_clocks,
+	.start_thermal_control = smu_v11_0_start_thermal_control,
+	.stop_thermal_control = smu_v11_0_stop_thermal_control,
+	.set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk,
+	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
+	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
+	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
+	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
+	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
+	.gfx_off_control = smu_v11_0_gfx_off_control,
+	.register_irq_handler = smu_v11_0_register_irq_handler,
+	.set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme,
+	.get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc,
+	.baco_is_support= smu_v11_0_baco_is_support,
+	.baco_get_state = smu_v11_0_baco_get_state,
+	.baco_set_state = smu_v11_0_baco_set_state,
+	.baco_reset = smu_v11_0_baco_reset,
+	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
+	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
+	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
+	.set_default_od_settings = navi10_set_default_od_settings,
+	.od_edit_dpm_table = navi10_od_edit_dpm_table,
+	.get_pptable_power_limit = navi10_get_pptable_power_limit,
+	.run_btc = navi10_run_btc,
 };
 
 void navi10_set_ppt_funcs(struct smu_context *smu)
 {
-	struct smu_table_context *smu_table = &smu->smu_table;
-
 	smu->ppt_funcs = &navi10_ppt_funcs;
-	smu_table->table_count = TABLE_COUNT;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
index 620ff17c2fef..ec03c7992f6d 100644
--- a/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
+++ b/drivers/gpu/drm/amd/powerplay/navi10_ppt.h
@@ -27,6 +27,17 @@
 #define NAVI10_PEAK_SCLK_XT  		(1755)
 #define NAVI10_PEAK_SCLK_XL  		(1625)
 
+#define NAVI14_UMD_PSTATE_PEAK_XT_GFXCLK      (1670)
+#define NAVI14_UMD_PSTATE_PEAK_XTM_GFXCLK     (1448)
+#define NAVI14_UMD_PSTATE_PEAK_XLM_GFXCLK     (1181)
+#define NAVI14_UMD_PSTATE_PEAK_XTX_GFXCLK     (1717)
+#define NAVI14_UMD_PSTATE_PEAK_XL_GFXCLK      (1448)
+
+#define NAVI10_VOLTAGE_SCALE (4)
+
+#define smnPCIE_LC_SPEED_CNTL			0x11140290
+#define smnPCIE_LC_LINK_WIDTH_CNTL		0x11140288
+
 extern void navi10_set_ppt_funcs(struct smu_context *smu);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
index e62bfba51562..977bdd962e98 100644
--- a/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/renoir_ppt.c
@@ -23,6 +23,7 @@
 
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "soc15_common.h"
 #include "smu_v12_0_ppsmc.h"
 #include "smu12_driver_if.h"
@@ -160,21 +161,17 @@ static int renoir_tables_init(struct smu_context *smu, struct smu_table *tables)
  * This interface just for getting uclk ultimate freq and should't introduce
  * other likewise function result in overmuch callback.
  */
-static int renoir_get_dpm_uclk_limited(struct smu_context *smu, uint32_t *clock, bool max)
+static int renoir_get_dpm_clk_limited(struct smu_context *smu, enum smu_clk_type clk_type,
+						uint32_t dpm_level, uint32_t *freq)
 {
+	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
 
-	DpmClocks_t *table = smu->smu_table.clocks_table;
-
-	if (!clock || !table)
+	if (!clk_table || clk_type >= SMU_CLK_COUNT)
 		return -EINVAL;
 
-	if (max)
-		*clock = table->FClocks[NUM_FCLK_DPM_LEVELS-1].Freq;
-	else
-		*clock = table->FClocks[0].Freq;
+	GET_DPM_CUR_FREQ(clk_table, clk_type, dpm_level, *freq);
 
 	return 0;
-
 }
 
 static int renoir_print_clk_levels(struct smu_context *smu,
@@ -183,11 +180,13 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 	int i, size = 0, ret = 0;
 	uint32_t cur_value = 0, value = 0, count = 0, min = 0, max = 0;
 	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
-	SmuMetrics_t metrics = {0};
+	SmuMetrics_t metrics;
 
 	if (!clk_table || clk_type >= SMU_CLK_COUNT)
 		return -EINVAL;
 
+	memset(&metrics, 0, sizeof(metrics));
+
 	ret = smu_update_table(smu, SMU_TABLE_SMU_METRICS, 0,
 			       (void *)&metrics, false);
 	if (ret)
@@ -198,7 +197,7 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 	case SMU_SCLK:
 		/* retirve table returned paramters unit is MHz */
 		cur_value = metrics.ClockFrequency[CLOCK_GFXCLK];
-		ret = smu_get_dpm_freq_range(smu, SMU_GFXCLK, &min, &max);
+		ret = smu_get_dpm_freq_range(smu, SMU_GFXCLK, &min, &max, false);
 		if (!ret) {
 			/* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */
 			if (cur_value  == max)
@@ -246,20 +245,473 @@ static int renoir_print_clk_levels(struct smu_context *smu,
 	return size;
 }
 
+static enum amd_pm_state_type renoir_get_current_power_state(struct smu_context *smu)
+{
+	enum amd_pm_state_type pm_type;
+	struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+
+	if (!smu_dpm_ctx->dpm_context ||
+	    !smu_dpm_ctx->dpm_current_power_state)
+		return -EINVAL;
+
+	switch (smu_dpm_ctx->dpm_current_power_state->classification.ui_label) {
+	case SMU_STATE_UI_LABEL_BATTERY:
+		pm_type = POWER_STATE_TYPE_BATTERY;
+		break;
+	case SMU_STATE_UI_LABEL_BALLANCED:
+		pm_type = POWER_STATE_TYPE_BALANCED;
+		break;
+	case SMU_STATE_UI_LABEL_PERFORMANCE:
+		pm_type = POWER_STATE_TYPE_PERFORMANCE;
+		break;
+	default:
+		if (smu_dpm_ctx->dpm_current_power_state->classification.flags & SMU_STATE_CLASSIFICATION_FLAG_BOOT)
+			pm_type = POWER_STATE_TYPE_INTERNAL_BOOT;
+		else
+			pm_type = POWER_STATE_TYPE_DEFAULT;
+		break;
+	}
+
+	return pm_type;
+}
+
+static int renoir_dpm_set_uvd_enable(struct smu_context *smu, bool enable)
+{
+	struct smu_power_context *smu_power = &smu->smu_power;
+	struct smu_power_gate *power_gate = &smu_power->power_gate;
+	int ret = 0;
+
+	if (enable) {
+		/* vcn dpm on is a prerequisite for vcn power gate messages */
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
+			ret = smu_send_smc_msg_with_param(smu, SMU_MSG_PowerUpVcn, 0);
+			if (ret)
+				return ret;
+		}
+		power_gate->vcn_gated = false;
+	} else {
+		if (smu_feature_is_enabled(smu, SMU_FEATURE_VCN_PG_BIT)) {
+			ret = smu_send_smc_msg(smu, SMU_MSG_PowerDownVcn);
+			if (ret)
+				return ret;
+		}
+		power_gate->vcn_gated = true;
+	}
+
+	return ret;
+}
+
+static int renoir_force_dpm_limit_value(struct smu_context *smu, bool highest)
+{
+	int ret = 0, i = 0;
+	uint32_t min_freq, max_freq, force_freq;
+	enum smu_clk_type clk_type;
+
+	enum smu_clk_type clks[] = {
+		SMU_GFXCLK,
+		SMU_MCLK,
+		SMU_SOCCLK,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(clks); i++) {
+		clk_type = clks[i];
+		ret = smu_get_dpm_freq_range(smu, clk_type, &min_freq, &max_freq, false);
+		if (ret)
+			return ret;
+
+		force_freq = highest ? max_freq : min_freq;
+		ret = smu_set_soft_freq_range(smu, clk_type, force_freq, force_freq);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int renoir_unforce_dpm_levels(struct smu_context *smu) {
+
+	int ret = 0, i = 0;
+	uint32_t min_freq, max_freq;
+	enum smu_clk_type clk_type;
+
+	struct clk_feature_map {
+		enum smu_clk_type clk_type;
+		uint32_t	feature;
+	} clk_feature_map[] = {
+		{SMU_GFXCLK, SMU_FEATURE_DPM_GFXCLK_BIT},
+		{SMU_MCLK,   SMU_FEATURE_DPM_UCLK_BIT},
+		{SMU_SOCCLK, SMU_FEATURE_DPM_SOCCLK_BIT},
+	};
+
+	for (i = 0; i < ARRAY_SIZE(clk_feature_map); i++) {
+		if (!smu_feature_is_enabled(smu, clk_feature_map[i].feature))
+		    continue;
+
+		clk_type = clk_feature_map[i].clk_type;
+
+		ret = smu_get_dpm_freq_range(smu, clk_type, &min_freq, &max_freq, false);
+		if (ret)
+			return ret;
+
+		ret = smu_set_soft_freq_range(smu, clk_type, min_freq, max_freq);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int renoir_get_workload_type(struct smu_context *smu, uint32_t profile)
+{
+
+	uint32_t  pplib_workload = 0;
+
+	switch (profile) {
+	case PP_SMC_POWER_PROFILE_FULLSCREEN3D:
+		pplib_workload = WORKLOAD_PPLIB_FULL_SCREEN_3D_BIT;
+		break;
+	case PP_SMC_POWER_PROFILE_CUSTOM:
+		pplib_workload = WORKLOAD_PPLIB_COUNT;
+		break;
+	case PP_SMC_POWER_PROFILE_VIDEO:
+		pplib_workload = WORKLOAD_PPLIB_VIDEO_BIT;
+		break;
+	case PP_SMC_POWER_PROFILE_VR:
+		pplib_workload = WORKLOAD_PPLIB_VR_BIT;
+		break;
+	case PP_SMC_POWER_PROFILE_COMPUTE:
+		pplib_workload = WORKLOAD_PPLIB_COMPUTE_BIT;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return pplib_workload;
+}
+
+static int renoir_get_profiling_clk_mask(struct smu_context *smu,
+					 enum amd_dpm_forced_level level,
+					 uint32_t *sclk_mask,
+					 uint32_t *mclk_mask,
+					 uint32_t *soc_mask)
+{
+
+	if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
+		if (sclk_mask)
+			*sclk_mask = 0;
+	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
+		if (mclk_mask)
+			*mclk_mask = 0;
+	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+		if(sclk_mask)
+			/* The sclk as gfxclk and has three level about max/min/current */
+			*sclk_mask = 3 - 1;
+
+		if(mclk_mask)
+			*mclk_mask = NUM_MEMCLK_DPM_LEVELS - 1;
+
+		if(soc_mask)
+			*soc_mask = NUM_SOCCLK_DPM_LEVELS - 1;
+	}
+
+	return 0;
+}
+
+/**
+ * This interface get dpm clock table for dc
+ */
+static int renoir_get_dpm_clock_table(struct smu_context *smu, struct dpm_clocks *clock_table)
+{
+	DpmClocks_t *table = smu->smu_table.clocks_table;
+	int i;
+
+	if (!clock_table || !table)
+		return -EINVAL;
+
+	for (i = 0; i < NUM_DCFCLK_DPM_LEVELS; i++) {
+		clock_table->DcfClocks[i].Freq = table->DcfClocks[i].Freq;
+		clock_table->DcfClocks[i].Vol = table->DcfClocks[i].Vol;
+	}
+
+	for (i = 0; i < NUM_SOCCLK_DPM_LEVELS; i++) {
+		clock_table->SocClocks[i].Freq = table->SocClocks[i].Freq;
+		clock_table->SocClocks[i].Vol = table->SocClocks[i].Vol;
+	}
+
+	for (i = 0; i < NUM_FCLK_DPM_LEVELS; i++) {
+		clock_table->FClocks[i].Freq = table->FClocks[i].Freq;
+		clock_table->FClocks[i].Vol = table->FClocks[i].Vol;
+	}
+
+	for (i = 0; i<  NUM_MEMCLK_DPM_LEVELS; i++) {
+		clock_table->MemClocks[i].Freq = table->MemClocks[i].Freq;
+		clock_table->MemClocks[i].Vol = table->MemClocks[i].Vol;
+	}
+
+	return 0;
+}
+
+static int renoir_force_clk_levels(struct smu_context *smu,
+				   enum smu_clk_type clk_type, uint32_t mask)
+{
+
+	int ret = 0 ;
+	uint32_t soft_min_level = 0, soft_max_level = 0, min_freq = 0, max_freq = 0;
+	DpmClocks_t *clk_table = smu->smu_table.clocks_table;
+
+	soft_min_level = mask ? (ffs(mask) - 1) : 0;
+	soft_max_level = mask ? (fls(mask) - 1) : 0;
+
+	switch (clk_type) {
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		if (soft_min_level > 2 || soft_max_level > 2) {
+			pr_info("Currently sclk only support 3 levels on APU\n");
+			return -EINVAL;
+		}
+
+		ret = smu_get_dpm_freq_range(smu, SMU_GFXCLK, &min_freq, &max_freq, false);
+		if (ret)
+			return ret;
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk,
+					soft_max_level == 0 ? min_freq :
+					soft_max_level == 1 ? RENOIR_UMD_PSTATE_GFXCLK : max_freq);
+		if (ret)
+			return ret;
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk,
+					soft_min_level == 2 ? max_freq :
+					soft_min_level == 1 ? RENOIR_UMD_PSTATE_GFXCLK : min_freq);
+		if (ret)
+			return ret;
+		break;
+	case SMU_SOCCLK:
+		GET_DPM_CUR_FREQ(clk_table, clk_type, soft_min_level, min_freq);
+		GET_DPM_CUR_FREQ(clk_table, clk_type, soft_max_level, max_freq);
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxSocclkByFreq, max_freq);
+		if (ret)
+			return ret;
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinSocclkByFreq, min_freq);
+		if (ret)
+			return ret;
+		break;
+	case SMU_MCLK:
+	case SMU_FCLK:
+		GET_DPM_CUR_FREQ(clk_table, clk_type, soft_min_level, min_freq);
+		GET_DPM_CUR_FREQ(clk_table, clk_type, soft_max_level, max_freq);
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxFclkByFreq, max_freq);
+		if (ret)
+			return ret;
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinFclkByFreq, min_freq);
+		if (ret)
+			return ret;
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int renoir_set_power_profile_mode(struct smu_context *smu, long *input, uint32_t size)
+{
+	int workload_type, ret;
+	uint32_t profile_mode = input[size];
+
+	if (profile_mode > PP_SMC_POWER_PROFILE_CUSTOM) {
+		pr_err("Invalid power profile mode %d\n", smu->power_profile_mode);
+		return -EINVAL;
+	}
+
+	/* conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT */
+	workload_type = smu_workload_get_type(smu, smu->power_profile_mode);
+	if (workload_type < 0) {
+		pr_err("Unsupported power profile mode %d on RENOIR\n",smu->power_profile_mode);
+		return -EINVAL;
+	}
+
+	ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetWorkloadMask,
+				    1 << workload_type);
+	if (ret) {
+		pr_err("Fail to set workload type %d\n", workload_type);
+		return ret;
+	}
+
+	smu->power_profile_mode = profile_mode;
+
+	return 0;
+}
+
+static int renoir_set_peak_clock_by_device(struct smu_context *smu)
+{
+	int ret = 0;
+	uint32_t sclk_freq = 0, uclk_freq = 0;
+
+	ret = smu_get_dpm_freq_range(smu, SMU_SCLK, NULL, &sclk_freq, false);
+	if (ret)
+		return ret;
+
+	ret = smu_set_soft_freq_range(smu, SMU_SCLK, sclk_freq, sclk_freq);
+	if (ret)
+		return ret;
+
+	ret = smu_get_dpm_freq_range(smu, SMU_UCLK, NULL, &uclk_freq, false);
+	if (ret)
+		return ret;
+
+	ret = smu_set_soft_freq_range(smu, SMU_UCLK, uclk_freq, uclk_freq);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int renoir_set_performance_level(struct smu_context *smu, enum amd_dpm_forced_level level)
+{
+	int ret = 0;
+
+	switch (level) {
+	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
+		ret = renoir_set_peak_clock_by_device(smu);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+/* save watermark settings into pplib smu structure,
+ * also pass data to smu controller
+ */
+static int renoir_set_watermarks_table(
+		struct smu_context *smu,
+		void *watermarks,
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *clock_ranges)
+{
+	int i;
+	int ret = 0;
+	Watermarks_t *table = watermarks;
+
+	if (!table || !clock_ranges)
+		return -EINVAL;
+
+	if (clock_ranges->num_wm_dmif_sets > 4 ||
+			clock_ranges->num_wm_mcif_sets > 4)
+		return -EINVAL;
+
+	/* save into smu->smu_table.tables[SMU_TABLE_WATERMARKS]->cpu_addr*/
+	for (i = 0; i < clock_ranges->num_wm_dmif_sets; i++) {
+		table->WatermarkRow[WM_DCFCLK][i].MinClock =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz));
+		table->WatermarkRow[WM_DCFCLK][i].MaxClock =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz));
+		table->WatermarkRow[WM_DCFCLK][i].MinMclk =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz));
+		table->WatermarkRow[WM_DCFCLK][i].MaxMclk =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz));
+		table->WatermarkRow[WM_DCFCLK][i].WmSetting = (uint8_t)
+				clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
+	}
+
+	for (i = 0; i < clock_ranges->num_wm_mcif_sets; i++) {
+		table->WatermarkRow[WM_SOCCLK][i].MinClock =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz));
+		table->WatermarkRow[WM_SOCCLK][i].MaxClock =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz));
+		table->WatermarkRow[WM_SOCCLK][i].MinMclk =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz));
+		table->WatermarkRow[WM_SOCCLK][i].MaxMclk =
+			cpu_to_le16((uint16_t)
+			(clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz));
+		table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t)
+				clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
+	}
+
+	/* pass data to smu controller */
+	ret = smu_write_watermarks_table(smu);
+
+	return ret;
+}
+
+static int renoir_get_power_profile_mode(struct smu_context *smu,
+					   char *buf)
+{
+	static const char *profile_name[] = {
+					"BOOTUP_DEFAULT",
+					"3D_FULL_SCREEN",
+					"POWER_SAVING",
+					"VIDEO",
+					"VR",
+					"COMPUTE",
+					"CUSTOM"};
+	uint32_t i, size = 0;
+	int16_t workload_type = 0;
+
+	if (!smu->pm_enabled || !buf)
+		return -EINVAL;
+
+	for (i = 0; i <= PP_SMC_POWER_PROFILE_CUSTOM; i++) {
+		/*
+		 * Conv PP_SMC_POWER_PROFILE* to WORKLOAD_PPLIB_*_BIT
+		 * Not all profile modes are supported on arcturus.
+		 */
+		workload_type = smu_workload_get_type(smu, i);
+		if (workload_type < 0)
+			continue;
+
+		size += sprintf(buf + size, "%2d %14s%s\n",
+			i, profile_name[i], (i == smu->power_profile_mode) ? "*" : " ");
+	}
+
+	return size;
+}
+
 static const struct pptable_funcs renoir_ppt_funcs = {
 	.get_smu_msg_index = renoir_get_smu_msg_index,
 	.get_smu_table_index = renoir_get_smu_table_index,
 	.tables_init = renoir_tables_init,
 	.set_power_state = NULL,
-	.get_dpm_uclk_limited = renoir_get_dpm_uclk_limited,
+	.get_dpm_clk_limited = renoir_get_dpm_clk_limited,
 	.print_clk_levels = renoir_print_clk_levels,
+	.get_current_power_state = renoir_get_current_power_state,
+	.dpm_set_uvd_enable = renoir_dpm_set_uvd_enable,
+	.force_dpm_limit_value = renoir_force_dpm_limit_value,
+	.unforce_dpm_levels = renoir_unforce_dpm_levels,
+	.get_workload_type = renoir_get_workload_type,
+	.get_profiling_clk_mask = renoir_get_profiling_clk_mask,
+	.force_clk_levels = renoir_force_clk_levels,
+	.set_power_profile_mode = renoir_set_power_profile_mode,
+	.set_performance_level = renoir_set_performance_level,
+	.get_dpm_clock_table = renoir_get_dpm_clock_table,
+	.set_watermarks_table = renoir_set_watermarks_table,
+	.get_power_profile_mode = renoir_get_power_profile_mode,
+	.check_fw_status = smu_v12_0_check_fw_status,
+	.check_fw_version = smu_v12_0_check_fw_version,
+	.powergate_sdma = smu_v12_0_powergate_sdma,
+	.powergate_vcn = smu_v12_0_powergate_vcn,
+	.send_smc_msg_with_param = smu_v12_0_send_msg_with_param,
+	.read_smc_arg = smu_v12_0_read_arg,
+	.set_gfx_cgpg = smu_v12_0_set_gfx_cgpg,
+	.gfx_off_control = smu_v12_0_gfx_off_control,
+	.init_smc_tables = smu_v12_0_init_smc_tables,
+	.fini_smc_tables = smu_v12_0_fini_smc_tables,
+	.populate_smc_tables = smu_v12_0_populate_smc_tables,
+	.get_dpm_ultimate_freq = smu_v12_0_get_dpm_ultimate_freq,
+	.mode2_reset = smu_v12_0_mode2_reset,
+	.set_soft_freq_limited_range = smu_v12_0_set_soft_freq_limited_range,
 };
 
 void renoir_set_ppt_funcs(struct smu_context *smu)
 {
-	struct smu_table_context *smu_table = &smu->smu_table;
-
 	smu->ppt_funcs = &renoir_ppt_funcs;
 	smu->smc_if_version = SMU12_DRIVER_IF_VERSION;
-	smu_table->table_count = TABLE_COUNT;
+	smu->is_apu = true;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_internal.h b/drivers/gpu/drm/amd/powerplay/smu_internal.h
new file mode 100644
index 000000000000..8872f8b2d502
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smu_internal.h
@@ -0,0 +1,204 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef __SMU_INTERNAL_H__
+#define __SMU_INTERNAL_H__
+
+#include "amdgpu_smu.h"
+
+#define smu_init_microcode(smu) \
+	((smu)->ppt_funcs->init_microcode ? (smu)->ppt_funcs->init_microcode((smu)) : 0)
+#define smu_init_smc_tables(smu) \
+	((smu)->ppt_funcs->init_smc_tables ? (smu)->ppt_funcs->init_smc_tables((smu)) : 0)
+#define smu_fini_smc_tables(smu) \
+	((smu)->ppt_funcs->fini_smc_tables ? (smu)->ppt_funcs->fini_smc_tables((smu)) : 0)
+#define smu_init_power(smu) \
+	((smu)->ppt_funcs->init_power ? (smu)->ppt_funcs->init_power((smu)) : 0)
+#define smu_fini_power(smu) \
+	((smu)->ppt_funcs->fini_power ? (smu)->ppt_funcs->fini_power((smu)) : 0)
+
+#define smu_setup_pptable(smu) \
+	((smu)->ppt_funcs->setup_pptable ? (smu)->ppt_funcs->setup_pptable((smu)) : 0)
+#define smu_powergate_sdma(smu, gate) \
+	((smu)->ppt_funcs->powergate_sdma ? (smu)->ppt_funcs->powergate_sdma((smu), (gate)) : 0)
+#define smu_powergate_vcn(smu, gate) \
+	((smu)->ppt_funcs->powergate_vcn ? (smu)->ppt_funcs->powergate_vcn((smu), (gate)) : 0)
+
+#define smu_get_vbios_bootup_values(smu) \
+	((smu)->ppt_funcs->get_vbios_bootup_values ? (smu)->ppt_funcs->get_vbios_bootup_values((smu)) : 0)
+#define smu_get_clk_info_from_vbios(smu) \
+	((smu)->ppt_funcs->get_clk_info_from_vbios ? (smu)->ppt_funcs->get_clk_info_from_vbios((smu)) : 0)
+#define smu_check_pptable(smu) \
+	((smu)->ppt_funcs->check_pptable ? (smu)->ppt_funcs->check_pptable((smu)) : 0)
+#define smu_parse_pptable(smu) \
+	((smu)->ppt_funcs->parse_pptable ? (smu)->ppt_funcs->parse_pptable((smu)) : 0)
+#define smu_populate_smc_tables(smu) \
+	((smu)->ppt_funcs->populate_smc_tables ? (smu)->ppt_funcs->populate_smc_tables((smu)) : 0)
+#define smu_check_fw_version(smu) \
+	((smu)->ppt_funcs->check_fw_version ? (smu)->ppt_funcs->check_fw_version((smu)) : 0)
+#define smu_write_pptable(smu) \
+	((smu)->ppt_funcs->write_pptable ? (smu)->ppt_funcs->write_pptable((smu)) : 0)
+#define smu_set_min_dcef_deep_sleep(smu) \
+	((smu)->ppt_funcs->set_min_dcef_deep_sleep ? (smu)->ppt_funcs->set_min_dcef_deep_sleep((smu)) : 0)
+#define smu_set_tool_table_location(smu) \
+	((smu)->ppt_funcs->set_tool_table_location ? (smu)->ppt_funcs->set_tool_table_location((smu)) : 0)
+#define smu_notify_memory_pool_location(smu) \
+	((smu)->ppt_funcs->notify_memory_pool_location ? (smu)->ppt_funcs->notify_memory_pool_location((smu)) : 0)
+#define smu_gfx_off_control(smu, enable) \
+	((smu)->ppt_funcs->gfx_off_control ? (smu)->ppt_funcs->gfx_off_control((smu), (enable)) : 0)
+
+#define smu_set_last_dcef_min_deep_sleep_clk(smu) \
+	((smu)->ppt_funcs->set_last_dcef_min_deep_sleep_clk ? (smu)->ppt_funcs->set_last_dcef_min_deep_sleep_clk((smu)) : 0)
+#define smu_system_features_control(smu, en) \
+	((smu)->ppt_funcs->system_features_control ? (smu)->ppt_funcs->system_features_control((smu), (en)) : 0)
+#define smu_init_max_sustainable_clocks(smu) \
+	((smu)->ppt_funcs->init_max_sustainable_clocks ? (smu)->ppt_funcs->init_max_sustainable_clocks((smu)) : 0)
+#define smu_set_default_od_settings(smu, initialize) \
+	((smu)->ppt_funcs->set_default_od_settings ? (smu)->ppt_funcs->set_default_od_settings((smu), (initialize)) : 0)
+
+int smu_send_smc_msg(struct smu_context *smu, enum smu_message_type msg);
+
+#define smu_send_smc_msg_with_param(smu, msg, param) \
+	((smu)->ppt_funcs->send_smc_msg_with_param? (smu)->ppt_funcs->send_smc_msg_with_param((smu), (msg), (param)) : 0)
+#define smu_read_smc_arg(smu, arg) \
+	((smu)->ppt_funcs->read_smc_arg? (smu)->ppt_funcs->read_smc_arg((smu), (arg)) : 0)
+#define smu_alloc_dpm_context(smu) \
+	((smu)->ppt_funcs->alloc_dpm_context ? (smu)->ppt_funcs->alloc_dpm_context((smu)) : 0)
+#define smu_init_display_count(smu, count) \
+	((smu)->ppt_funcs->init_display_count ? (smu)->ppt_funcs->init_display_count((smu), (count)) : 0)
+#define smu_feature_set_allowed_mask(smu) \
+	((smu)->ppt_funcs->set_allowed_mask? (smu)->ppt_funcs->set_allowed_mask((smu)) : 0)
+#define smu_feature_get_enabled_mask(smu, mask, num) \
+	((smu)->ppt_funcs->get_enabled_mask? (smu)->ppt_funcs->get_enabled_mask((smu), (mask), (num)) : 0)
+#define smu_is_dpm_running(smu) \
+	((smu)->ppt_funcs->is_dpm_running ? (smu)->ppt_funcs->is_dpm_running((smu)) : 0)
+#define smu_notify_display_change(smu) \
+	((smu)->ppt_funcs->notify_display_change? (smu)->ppt_funcs->notify_display_change((smu)) : 0)
+#define smu_store_powerplay_table(smu) \
+	((smu)->ppt_funcs->store_powerplay_table ? (smu)->ppt_funcs->store_powerplay_table((smu)) : 0)
+#define smu_check_powerplay_table(smu) \
+	((smu)->ppt_funcs->check_powerplay_table ? (smu)->ppt_funcs->check_powerplay_table((smu)) : 0)
+#define smu_append_powerplay_table(smu) \
+	((smu)->ppt_funcs->append_powerplay_table ? (smu)->ppt_funcs->append_powerplay_table((smu)) : 0)
+#define smu_set_default_dpm_table(smu) \
+	((smu)->ppt_funcs->set_default_dpm_table ? (smu)->ppt_funcs->set_default_dpm_table((smu)) : 0)
+#define smu_populate_umd_state_clk(smu) \
+	((smu)->ppt_funcs->populate_umd_state_clk ? (smu)->ppt_funcs->populate_umd_state_clk((smu)) : 0)
+#define smu_set_default_od8_settings(smu) \
+	((smu)->ppt_funcs->set_default_od8_settings ? (smu)->ppt_funcs->set_default_od8_settings((smu)) : 0)
+
+#define smu_get_current_clk_freq(smu, clk_id, value) \
+	((smu)->ppt_funcs->get_current_clk_freq? (smu)->ppt_funcs->get_current_clk_freq((smu), (clk_id), (value)) : 0)
+
+#define smu_tables_init(smu, tab) \
+	((smu)->ppt_funcs->tables_init ? (smu)->ppt_funcs->tables_init((smu), (tab)) : 0)
+#define smu_set_thermal_fan_table(smu) \
+	((smu)->ppt_funcs->set_thermal_fan_table ? (smu)->ppt_funcs->set_thermal_fan_table((smu)) : 0)
+#define smu_start_thermal_control(smu) \
+	((smu)->ppt_funcs->start_thermal_control? (smu)->ppt_funcs->start_thermal_control((smu)) : 0)
+#define smu_stop_thermal_control(smu) \
+	((smu)->ppt_funcs->stop_thermal_control? (smu)->ppt_funcs->stop_thermal_control((smu)) : 0)
+
+#define smu_smc_read_sensor(smu, sensor, data, size) \
+	((smu)->ppt_funcs->read_sensor? (smu)->ppt_funcs->read_sensor((smu), (sensor), (data), (size)) : -EINVAL)
+
+#define smu_pre_display_config_changed(smu) \
+	((smu)->ppt_funcs->pre_display_config_changed ? (smu)->ppt_funcs->pre_display_config_changed((smu)) : 0)
+#define smu_display_config_changed(smu) \
+	((smu)->ppt_funcs->display_config_changed ? (smu)->ppt_funcs->display_config_changed((smu)) : 0)
+#define smu_apply_clocks_adjust_rules(smu) \
+	((smu)->ppt_funcs->apply_clocks_adjust_rules ? (smu)->ppt_funcs->apply_clocks_adjust_rules((smu)) : 0)
+#define smu_notify_smc_dispaly_config(smu) \
+	((smu)->ppt_funcs->notify_smc_dispaly_config ? (smu)->ppt_funcs->notify_smc_dispaly_config((smu)) : 0)
+#define smu_force_dpm_limit_value(smu, highest) \
+	((smu)->ppt_funcs->force_dpm_limit_value ? (smu)->ppt_funcs->force_dpm_limit_value((smu), (highest)) : 0)
+#define smu_unforce_dpm_levels(smu) \
+	((smu)->ppt_funcs->unforce_dpm_levels ? (smu)->ppt_funcs->unforce_dpm_levels((smu)) : 0)
+#define smu_get_profiling_clk_mask(smu, level, sclk_mask, mclk_mask, soc_mask) \
+	((smu)->ppt_funcs->get_profiling_clk_mask ? (smu)->ppt_funcs->get_profiling_clk_mask((smu), (level), (sclk_mask), (mclk_mask), (soc_mask)) : 0)
+#define smu_set_cpu_power_state(smu) \
+	((smu)->ppt_funcs->set_cpu_power_state ? (smu)->ppt_funcs->set_cpu_power_state((smu)) : 0)
+
+#define smu_msg_get_index(smu, msg) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_msg_index? (smu)->ppt_funcs->get_smu_msg_index((smu), (msg)) : -EINVAL) : -EINVAL)
+#define smu_clk_get_index(smu, msg) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_clk_index? (smu)->ppt_funcs->get_smu_clk_index((smu), (msg)) : -EINVAL) : -EINVAL)
+#define smu_feature_get_index(smu, msg) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_feature_index? (smu)->ppt_funcs->get_smu_feature_index((smu), (msg)) : -EINVAL) : -EINVAL)
+#define smu_table_get_index(smu, tab) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_table_index? (smu)->ppt_funcs->get_smu_table_index((smu), (tab)) : -EINVAL) : -EINVAL)
+#define smu_power_get_index(smu, src) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_smu_power_index? (smu)->ppt_funcs->get_smu_power_index((smu), (src)) : -EINVAL) : -EINVAL)
+#define smu_workload_get_type(smu, profile) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_workload_type? (smu)->ppt_funcs->get_workload_type((smu), (profile)) : -EINVAL) : -EINVAL)
+#define smu_run_btc(smu) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->run_btc? (smu)->ppt_funcs->run_btc((smu)) : 0) : 0)
+#define smu_get_allowed_feature_mask(smu, feature_mask, num) \
+	((smu)->ppt_funcs? ((smu)->ppt_funcs->get_allowed_feature_mask? (smu)->ppt_funcs->get_allowed_feature_mask((smu), (feature_mask), (num)) : 0) : 0)
+
+
+#define smu_store_cc6_data(smu, st, cc6_dis, pst_dis, pst_sw_dis) \
+	((smu)->ppt_funcs->store_cc6_data ? (smu)->ppt_funcs->store_cc6_data((smu), (st), (cc6_dis), (pst_dis), (pst_sw_dis)) : 0)
+
+#define smu_get_dal_power_level(smu, clocks) \
+	((smu)->ppt_funcs->get_dal_power_level ? (smu)->ppt_funcs->get_dal_power_level((smu), (clocks)) : 0)
+#define smu_get_perf_level(smu, designation, level) \
+	((smu)->ppt_funcs->get_perf_level ? (smu)->ppt_funcs->get_perf_level((smu), (designation), (level)) : 0)
+#define smu_get_current_shallow_sleep_clocks(smu, clocks) \
+	((smu)->ppt_funcs->get_current_shallow_sleep_clocks ? (smu)->ppt_funcs->get_current_shallow_sleep_clocks((smu), (clocks)) : 0)
+
+#define smu_dpm_set_uvd_enable(smu, enable) \
+	((smu)->ppt_funcs->dpm_set_uvd_enable ? (smu)->ppt_funcs->dpm_set_uvd_enable((smu), (enable)) : 0)
+#define smu_dpm_set_vce_enable(smu, enable) \
+	((smu)->ppt_funcs->dpm_set_vce_enable ? (smu)->ppt_funcs->dpm_set_vce_enable((smu), (enable)) : 0)
+
+#define smu_set_watermarks_table(smu, tab, clock_ranges) \
+	((smu)->ppt_funcs->set_watermarks_table ? (smu)->ppt_funcs->set_watermarks_table((smu), (tab), (clock_ranges)) : 0)
+#define smu_get_current_clk_freq_by_table(smu, clk_type, value) \
+	((smu)->ppt_funcs->get_current_clk_freq_by_table ? (smu)->ppt_funcs->get_current_clk_freq_by_table((smu), (clk_type), (value)) : 0)
+#define smu_thermal_temperature_range_update(smu, range, rw) \
+	((smu)->ppt_funcs->thermal_temperature_range_update? (smu)->ppt_funcs->thermal_temperature_range_update((smu), (range), (rw)) : 0)
+#define smu_get_thermal_temperature_range(smu, range) \
+	((smu)->ppt_funcs->get_thermal_temperature_range? (smu)->ppt_funcs->get_thermal_temperature_range((smu), (range)) : 0)
+#define smu_register_irq_handler(smu) \
+	((smu)->ppt_funcs->register_irq_handler ? (smu)->ppt_funcs->register_irq_handler(smu) : 0)
+
+#define smu_get_dpm_ultimate_freq(smu, param, min, max) \
+		((smu)->ppt_funcs->get_dpm_ultimate_freq ? (smu)->ppt_funcs->get_dpm_ultimate_freq((smu), (param), (min), (max)) : 0)
+
+#define smu_asic_set_performance_level(smu, level) \
+	((smu)->ppt_funcs->set_performance_level? (smu)->ppt_funcs->set_performance_level((smu), (level)) : -EINVAL);
+#define smu_dump_pptable(smu) \
+	((smu)->ppt_funcs->dump_pptable ? (smu)->ppt_funcs->dump_pptable((smu)) : 0)
+#define smu_get_dpm_clk_limited(smu, clk_type, dpm_level, freq) \
+		((smu)->ppt_funcs->get_dpm_clk_limited ? (smu)->ppt_funcs->get_dpm_clk_limited((smu), (clk_type), (dpm_level), (freq)) : -EINVAL)
+
+#define smu_set_soft_freq_limited_range(smu, clk_type, min, max) \
+		((smu)->ppt_funcs->set_soft_freq_limited_range ? (smu)->ppt_funcs->set_soft_freq_limited_range((smu), (clk_type), (min), (max)) : -EINVAL)
+
+#define smu_override_pcie_parameters(smu) \
+		((smu)->ppt_funcs->override_pcie_parameters ? (smu)->ppt_funcs->override_pcie_parameters((smu)) : 0)
+
+#define smu_update_pcie_parameters(smu, pcie_gen_cap, pcie_width_cap) \
+		((smu)->ppt_funcs->update_pcie_parameters ? (smu)->ppt_funcs->update_pcie_parameters((smu), (pcie_gen_cap), (pcie_width_cap)) : 0)
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
index c5257ae3188a..e4268a627eff 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v11_0.c
@@ -24,17 +24,19 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 
+#define SMU_11_0_PARTIAL_PPTABLE
+
 #include "pp_debug.h"
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "atomfirmware.h"
 #include "amdgpu_atomfirmware.h"
 #include "smu_v11_0.h"
+#include "smu_v11_0_pptable.h"
 #include "soc15_common.h"
 #include "atom.h"
-#include "vega20_ppt.h"
-#include "arcturus_ppt.h"
-#include "navi10_ppt.h"
+#include "amd_pcie.h"
 
 #include "asic_reg/thm/thm_11_0_2_offset.h"
 #include "asic_reg/thm/thm_11_0_2_sh_mask.h"
@@ -61,7 +63,7 @@ static int smu_v11_0_send_msg_without_waiting(struct smu_context *smu,
 	return 0;
 }
 
-static int smu_v11_0_read_arg(struct smu_context *smu, uint32_t *arg)
+int smu_v11_0_read_arg(struct smu_context *smu, uint32_t *arg)
 {
 	struct amdgpu_device *adev = smu->adev;
 
@@ -88,36 +90,11 @@ static int smu_v11_0_wait_for_response(struct smu_context *smu)
 	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
 }
 
-static int smu_v11_0_send_msg(struct smu_context *smu, uint16_t msg)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, index = 0;
-
-	index = smu_msg_get_index(smu, msg);
-	if (index < 0)
-		return index;
-
-	smu_v11_0_wait_for_response(smu);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	smu_v11_0_send_msg_without_waiting(smu, (uint16_t)index);
-
-	ret = smu_v11_0_wait_for_response(smu);
-
-	if (ret)
-		pr_err("failed send message: %10s (%d) response %#x\n",
-		       smu_get_message_name(smu, msg), index, ret);
-
-	return ret;
-
-}
-
-static int
-smu_v11_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
+int
+smu_v11_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
 			      uint32_t param)
 {
-
 	struct amdgpu_device *adev = smu->adev;
 	int ret = 0, index = 0;
 
@@ -144,7 +121,7 @@ smu_v11_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
 	return ret;
 }
 
-static int smu_v11_0_init_microcode(struct smu_context *smu)
+int smu_v11_0_init_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	const char *chip_name;
@@ -206,7 +183,7 @@ out:
 	return err;
 }
 
-static int smu_v11_0_load_microcode(struct smu_context *smu)
+int smu_v11_0_load_microcode(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	const uint32_t *src;
@@ -244,7 +221,7 @@ static int smu_v11_0_load_microcode(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_check_fw_status(struct smu_context *smu)
+int smu_v11_0_check_fw_status(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t mp1_fw_flags;
@@ -259,7 +236,7 @@ static int smu_v11_0_check_fw_status(struct smu_context *smu)
 	return -EIO;
 }
 
-static int smu_v11_0_check_fw_version(struct smu_context *smu)
+int smu_v11_0_check_fw_version(struct smu_context *smu)
 {
 	uint32_t if_version = 0xff, smu_version = 0xff;
 	uint16_t smu_major;
@@ -354,7 +331,7 @@ static int smu_v11_0_set_pptable_v2_1(struct smu_context *smu, void **table,
 	return 0;
 }
 
-static int smu_v11_0_setup_pptable(struct smu_context *smu)
+int smu_v11_0_setup_pptable(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	const struct smc_firmware_header_v1_0 *hdr;
@@ -369,6 +346,7 @@ static int smu_v11_0_setup_pptable(struct smu_context *smu)
 	version_major = le16_to_cpu(hdr->header.header_version_major);
 	version_minor = le16_to_cpu(hdr->header.header_version_minor);
 	if (version_major == 2 && smu->smu_table.boot_values.pp_table_id > 0) {
+		pr_info("use driver provided pptable %d\n", smu->smu_table.boot_values.pp_table_id);
 		switch (version_minor) {
 		case 0:
 			ret = smu_v11_0_set_pptable_v2_0(smu, &table, &size);
@@ -385,6 +363,7 @@ static int smu_v11_0_setup_pptable(struct smu_context *smu)
 			return ret;
 
 	} else {
+		pr_info("use vbios provided pptable\n");
 		index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
 						    powerplayinfo);
 
@@ -433,13 +412,13 @@ static int smu_v11_0_fini_dpm_context(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_init_smc_tables(struct smu_context *smu)
+int smu_v11_0_init_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = NULL;
 	int ret = 0;
 
-	if (smu_table->tables || smu_table->table_count == 0)
+	if (smu_table->tables)
 		return -EINVAL;
 
 	tables = kcalloc(SMU_TABLE_COUNT, sizeof(struct smu_table),
@@ -460,18 +439,17 @@ static int smu_v11_0_init_smc_tables(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_fini_smc_tables(struct smu_context *smu)
+int smu_v11_0_fini_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	int ret = 0;
 
-	if (!smu_table->tables || smu_table->table_count == 0)
+	if (!smu_table->tables)
 		return -EINVAL;
 
 	kfree(smu_table->tables);
 	kfree(smu_table->metrics_table);
 	smu_table->tables = NULL;
-	smu_table->table_count = 0;
 	smu_table->metrics_table = NULL;
 	smu_table->metrics_time = 0;
 
@@ -481,7 +459,7 @@ static int smu_v11_0_fini_smc_tables(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_init_power(struct smu_context *smu)
+int smu_v11_0_init_power(struct smu_context *smu)
 {
 	struct smu_power_context *smu_power = &smu->smu_power;
 
@@ -499,7 +477,7 @@ static int smu_v11_0_init_power(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_fini_power(struct smu_context *smu)
+int smu_v11_0_fini_power(struct smu_context *smu)
 {
 	struct smu_power_context *smu_power = &smu->smu_power;
 
@@ -576,7 +554,7 @@ int smu_v11_0_get_vbios_bootup_values(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_get_clk_info_from_vbios(struct smu_context *smu)
+int smu_v11_0_get_clk_info_from_vbios(struct smu_context *smu)
 {
 	int ret, index;
 	struct amdgpu_device *adev = smu->adev;
@@ -673,7 +651,7 @@ static int smu_v11_0_get_clk_info_from_vbios(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_notify_memory_pool_location(struct smu_context *smu)
+int smu_v11_0_notify_memory_pool_location(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *memory_pool = &smu_table->memory_pool;
@@ -719,7 +697,7 @@ static int smu_v11_0_notify_memory_pool_location(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_check_pptable(struct smu_context *smu)
+int smu_v11_0_check_pptable(struct smu_context *smu)
 {
 	int ret;
 
@@ -727,7 +705,7 @@ static int smu_v11_0_check_pptable(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_parse_pptable(struct smu_context *smu)
+int smu_v11_0_parse_pptable(struct smu_context *smu)
 {
 	int ret;
 
@@ -751,7 +729,7 @@ static int smu_v11_0_parse_pptable(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_populate_smc_pptable(struct smu_context *smu)
+int smu_v11_0_populate_smc_pptable(struct smu_context *smu)
 {
 	int ret;
 
@@ -760,7 +738,7 @@ static int smu_v11_0_populate_smc_pptable(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_write_pptable(struct smu_context *smu)
+int smu_v11_0_write_pptable(struct smu_context *smu)
 {
 	struct smu_table_context *table_context = &smu->smu_table;
 	int ret = 0;
@@ -771,24 +749,7 @@ static int smu_v11_0_write_pptable(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_write_watermarks_table(struct smu_context *smu)
-{
-	int ret = 0;
-	struct smu_table_context *smu_table = &smu->smu_table;
-	struct smu_table *table = NULL;
-
-	table = &smu_table->tables[SMU_TABLE_WATERMARKS];
-
-	if (!table->cpu_addr)
-		return -EINVAL;
-
-	ret = smu_update_table(smu, SMU_TABLE_WATERMARKS, 0, table->cpu_addr,
-				true);
-
-	return ret;
-}
-
-static int smu_v11_0_set_deep_sleep_dcefclk(struct smu_context *smu, uint32_t clk)
+int smu_v11_0_set_deep_sleep_dcefclk(struct smu_context *smu, uint32_t clk)
 {
 	int ret;
 
@@ -800,7 +761,7 @@ static int smu_v11_0_set_deep_sleep_dcefclk(struct smu_context *smu, uint32_t cl
 	return ret;
 }
 
-static int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu)
+int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu)
 {
 	struct smu_table_context *table_context = &smu->smu_table;
 
@@ -809,11 +770,10 @@ static int smu_v11_0_set_min_dcef_deep_sleep(struct smu_context *smu)
 	if (!table_context)
 		return -EINVAL;
 
-	return smu_set_deep_sleep_dcefclk(smu,
-					  table_context->boot_values.dcefclk / 100);
+	return smu_v11_0_set_deep_sleep_dcefclk(smu, table_context->boot_values.dcefclk / 100);
 }
 
-static int smu_v11_0_set_tool_table_location(struct smu_context *smu)
+int smu_v11_0_set_tool_table_location(struct smu_context *smu)
 {
 	int ret = 0;
 	struct smu_table *tool_table = &smu->smu_table.tables[SMU_TABLE_PMSTATUSLOG];
@@ -831,7 +791,7 @@ static int smu_v11_0_set_tool_table_location(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count)
+int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count)
 {
 	int ret = 0;
 
@@ -843,7 +803,7 @@ static int smu_v11_0_init_display_count(struct smu_context *smu, uint32_t count)
 }
 
 
-static int smu_v11_0_set_allowed_mask(struct smu_context *smu)
+int smu_v11_0_set_allowed_mask(struct smu_context *smu)
 {
 	struct smu_feature *feature = &smu->smu_feature;
 	int ret = 0;
@@ -870,7 +830,7 @@ failed:
 	return ret;
 }
 
-static int smu_v11_0_get_enabled_mask(struct smu_context *smu,
+int smu_v11_0_get_enabled_mask(struct smu_context *smu,
 				      uint32_t *feature_mask, uint32_t num)
 {
 	uint32_t feature_mask_high = 0, feature_mask_low = 0;
@@ -899,7 +859,7 @@ static int smu_v11_0_get_enabled_mask(struct smu_context *smu,
 	return ret;
 }
 
-static int smu_v11_0_system_features_control(struct smu_context *smu,
+int smu_v11_0_system_features_control(struct smu_context *smu,
 					     bool en)
 {
 	struct smu_feature *feature = &smu->smu_feature;
@@ -925,7 +885,7 @@ static int smu_v11_0_system_features_control(struct smu_context *smu,
 	return ret;
 }
 
-static int smu_v11_0_notify_display_change(struct smu_context *smu)
+int smu_v11_0_notify_display_change(struct smu_context *smu)
 {
 	int ret = 0;
 
@@ -983,7 +943,7 @@ smu_v11_0_get_max_sustainable_clock(struct smu_context *smu, uint32_t *clock,
 	return ret;
 }
 
-static int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu)
+int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu)
 {
 	struct smu_11_0_max_sustainable_clocks *max_sustainable_clocks;
 	int ret = 0;
@@ -1063,13 +1023,44 @@ static int smu_v11_0_init_max_sustainable_clocks(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n)
+uint32_t smu_v11_0_get_max_power_limit(struct smu_context *smu) {
+	uint32_t od_limit, max_power_limit;
+	struct smu_11_0_powerplay_table *powerplay_table = NULL;
+	struct smu_table_context *table_context = &smu->smu_table;
+	powerplay_table = table_context->power_play_table;
+
+	max_power_limit = smu_get_pptable_power_limit(smu);
+
+	if (!max_power_limit) {
+		// If we couldn't get the table limit, fall back on first-read value
+		if (!smu->default_power_limit)
+			smu->default_power_limit = smu->power_limit;
+		max_power_limit = smu->default_power_limit;
+	}
+
+	if (smu->od_enabled) {
+		od_limit = le32_to_cpu(powerplay_table->overdrive_table.max[SMU_11_0_ODSETTING_POWERPERCENTAGE]);
+
+		pr_debug("ODSETTING_POWERPERCENTAGE: %d (default: %d)\n", od_limit, smu->default_power_limit);
+
+		max_power_limit *= (100 + od_limit);
+		max_power_limit /= 100;
+	}
+
+	return max_power_limit;
+}
+
+int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n)
 {
 	int ret = 0;
+	uint32_t max_power_limit;
+
+	max_power_limit = smu_v11_0_get_max_power_limit(smu);
 
-	if (n > smu->default_power_limit) {
-		pr_err("New power limit is over the max allowed %d\n",
-				smu->default_power_limit);
+	if (n > max_power_limit) {
+		pr_err("New power limit (%d) is over the max allowed %d\n",
+				n,
+				max_power_limit);
 		return -EINVAL;
 	}
 
@@ -1091,7 +1082,7 @@ static int smu_v11_0_set_power_limit(struct smu_context *smu, uint32_t n)
 	return 0;
 }
 
-static int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
+int smu_v11_0_get_current_clk_freq(struct smu_context *smu,
 					  enum smu_clk_type clk_id,
 					  uint32_t *value)
 {
@@ -1170,7 +1161,7 @@ static int smu_v11_0_enable_thermal_alert(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v11_0_start_thermal_control(struct smu_context *smu)
+int smu_v11_0_start_thermal_control(struct smu_context *smu)
 {
 	int ret = 0;
 	struct smu_temperature_range range;
@@ -1212,6 +1203,15 @@ static int smu_v11_0_start_thermal_control(struct smu_context *smu)
 	return ret;
 }
 
+int smu_v11_0_stop_thermal_control(struct smu_context *smu)
+{
+	struct amdgpu_device *adev = smu->adev;
+
+	WREG32_SOC15(THM, 0, mmTHM_THERMAL_INT_ENA, 0);
+
+	return 0;
+}
+
 static uint16_t convert_to_vddc(uint8_t vid)
 {
 	return (uint16_t) ((6200 - (vid * 25)) / SMU11_VOLTAGE_SCALE);
@@ -1236,7 +1236,7 @@ static int smu_v11_0_get_gfx_vdd(struct smu_context *smu, uint32_t *value)
 
 }
 
-static int smu_v11_0_read_sensor(struct smu_context *smu,
+int smu_v11_0_read_sensor(struct smu_context *smu,
 				 enum amd_pp_sensors sensor,
 				 void *data, uint32_t *size)
 {
@@ -1273,7 +1273,7 @@ static int smu_v11_0_read_sensor(struct smu_context *smu,
 	return ret;
 }
 
-static int
+int
 smu_v11_0_display_clock_voltage_request(struct smu_context *smu,
 					struct pp_display_clock_request
 					*clock_req)
@@ -1316,9 +1316,7 @@ smu_v11_0_display_clock_voltage_request(struct smu_context *smu,
 		if (clk_select == SMU_UCLK && smu->disable_uclk_switch)
 			return 0;
 
-		mutex_lock(&smu->mutex);
 		ret = smu_set_hard_freq_range(smu, clk_select, clk_freq, 0);
-		mutex_unlock(&smu->mutex);
 
 		if(clk_select == SMU_UCLK)
 			smu->hard_min_uclk_req_from_dal = clk_freq;
@@ -1328,27 +1326,7 @@ failed:
 	return ret;
 }
 
-static int
-smu_v11_0_set_watermarks_for_clock_ranges(struct smu_context *smu, struct
-					  dm_pp_wm_sets_with_clock_ranges_soc15
-					  *clock_ranges)
-{
-	int ret = 0;
-	struct smu_table *watermarks = &smu->smu_table.tables[SMU_TABLE_WATERMARKS];
-	void *table = watermarks->cpu_addr;
-
-	if (!smu->disable_watermark &&
-	    smu_feature_is_enabled(smu, SMU_FEATURE_DPM_DCEFCLK_BIT) &&
-	    smu_feature_is_enabled(smu, SMU_FEATURE_DPM_SOCCLK_BIT)) {
-		smu_set_watermarks_table(smu, table, clock_ranges);
-		smu->watermarks_bitmap |= WATERMARKS_EXIST;
-		smu->watermarks_bitmap &= ~WATERMARKS_LOADED;
-	}
-
-	return ret;
-}
-
-static int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable)
+int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable)
 {
 	int ret = 0;
 	struct amdgpu_device *adev = smu->adev;
@@ -1361,12 +1339,10 @@ static int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable)
 	case CHIP_NAVI12:
 		if (!(adev->pm.pp_feature & PP_GFXOFF_MASK))
 			return 0;
-		mutex_lock(&smu->mutex);
 		if (enable)
 			ret = smu_send_smc_msg(smu, SMU_MSG_AllowGfxOff);
 		else
 			ret = smu_send_smc_msg(smu, SMU_MSG_DisallowGfxOff);
-		mutex_unlock(&smu->mutex);
 		break;
 	default:
 		break;
@@ -1375,7 +1351,7 @@ static int smu_v11_0_gfx_off_control(struct smu_context *smu, bool enable)
 	return ret;
 }
 
-static uint32_t
+uint32_t
 smu_v11_0_get_fan_control_mode(struct smu_context *smu)
 {
 	if (!smu_feature_is_enabled(smu, SMU_FEATURE_FAN_CONTROL_BIT))
@@ -1415,7 +1391,7 @@ smu_v11_0_set_fan_static_mode(struct smu_context *smu, uint32_t mode)
 	return 0;
 }
 
-static int
+int
 smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -1444,7 +1420,7 @@ smu_v11_0_set_fan_speed_percent(struct smu_context *smu, uint32_t speed)
 	return smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC);
 }
 
-static int
+int
 smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 			       uint32_t mode)
 {
@@ -1472,7 +1448,7 @@ smu_v11_0_set_fan_control_mode(struct smu_context *smu,
 	return ret;
 }
 
-static int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
+int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 				       uint32_t speed)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -1482,10 +1458,9 @@ static int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 	if (!speed)
 		return -EINVAL;
 
-	mutex_lock(&(smu->mutex));
 	ret = smu_v11_0_auto_fan_control(smu, 0);
 	if (ret)
-		goto set_fan_speed_rpm_failed;
+		return ret;
 
 	crystal_clock_freq = amdgpu_asic_get_xclk(adev);
 	tach_period = 60 * crystal_clock_freq * 10000 / (8 * speed);
@@ -1496,23 +1471,16 @@ static int smu_v11_0_set_fan_speed_rpm(struct smu_context *smu,
 
 	ret = smu_v11_0_set_fan_static_mode(smu, FDO_PWM_MODE_STATIC_RPM);
 
-set_fan_speed_rpm_failed:
-	mutex_unlock(&(smu->mutex));
 	return ret;
 }
 
-#define XGMI_STATE_D0 1
-#define XGMI_STATE_D3 0
-
-static int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
+int smu_v11_0_set_xgmi_pstate(struct smu_context *smu,
 				     uint32_t pstate)
 {
 	int ret = 0;
-	mutex_lock(&(smu->mutex));
 	ret = smu_send_smc_msg_with_param(smu,
 					  SMU_MSG_SetXgmiMode,
-					  pstate ? XGMI_STATE_D0 : XGMI_STATE_D3);
-	mutex_unlock(&(smu->mutex));
+					  pstate ? XGMI_MODE_PSTATE_D0 : XGMI_MODE_PSTATE_D3);
 	return ret;
 }
 
@@ -1559,7 +1527,7 @@ static const struct amdgpu_irq_src_funcs smu_v11_0_irq_funcs =
 	.process = smu_v11_0_irq_process,
 };
 
-static int smu_v11_0_register_irq_handler(struct smu_context *smu)
+int smu_v11_0_register_irq_handler(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	struct amdgpu_irq_src *irq_src = smu->irq_source;
@@ -1591,7 +1559,7 @@ static int smu_v11_0_register_irq_handler(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
+int smu_v11_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
 		struct pp_smu_nv_clock_table *max_clocks)
 {
 	struct smu_table_context *table_context = &smu->smu_table;
@@ -1621,13 +1589,11 @@ static int smu_v11_0_get_max_sustainable_clocks_by_dc(struct smu_context *smu,
 	return 0;
 }
 
-static int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu)
+int smu_v11_0_set_azalia_d3_pme(struct smu_context *smu)
 {
 	int ret = 0;
 
-	mutex_lock(&smu->mutex);
 	ret = smu_send_smc_msg(smu, SMU_MSG_BacoAudioD3PME);
-	mutex_unlock(&smu->mutex);
 
 	return ret;
 }
@@ -1637,7 +1603,7 @@ static int smu_v11_0_baco_set_armd3_sequence(struct smu_context *smu, enum smu_v
 	return smu_send_smc_msg_with_param(smu, SMU_MSG_ArmD3, baco_seq);
 }
 
-static bool smu_v11_0_baco_is_support(struct smu_context *smu)
+bool smu_v11_0_baco_is_support(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
@@ -1661,7 +1627,7 @@ static bool smu_v11_0_baco_is_support(struct smu_context *smu)
 	return false;
 }
 
-static enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu)
+enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu)
 {
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
 	enum smu_baco_state baco_state;
@@ -1673,7 +1639,7 @@ static enum smu_baco_state smu_v11_0_baco_get_state(struct smu_context *smu)
 	return baco_state;
 }
 
-static int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
+int smu_v11_0_baco_set_state(struct smu_context *smu, enum smu_baco_state state)
 {
 
 	struct smu_baco_context *smu_baco = &smu->smu_baco;
@@ -1697,7 +1663,7 @@ out:
 	return ret;
 }
 
-static int smu_v11_0_baco_reset(struct smu_context *smu)
+int smu_v11_0_baco_reset(struct smu_context *smu)
 {
 	int ret = 0;
 
@@ -1718,13 +1684,12 @@ static int smu_v11_0_baco_reset(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
+int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
 						 uint32_t *min, uint32_t *max)
 {
 	int ret = 0, clk_id = 0;
 	uint32_t param = 0;
 
-	mutex_lock(&smu->mutex);
 	clk_id = smu_clk_get_index(smu, clk_type);
 	if (clk_id < 0) {
 		ret = -EINVAL;
@@ -1751,80 +1716,102 @@ static int smu_v11_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk
 	}
 
 failed:
-	mutex_unlock(&smu->mutex);
 	return ret;
 }
 
-static const struct smu_funcs smu_v11_0_funcs = {
-	.init_microcode = smu_v11_0_init_microcode,
-	.load_microcode = smu_v11_0_load_microcode,
-	.check_fw_status = smu_v11_0_check_fw_status,
-	.check_fw_version = smu_v11_0_check_fw_version,
-	.send_smc_msg = smu_v11_0_send_msg,
-	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
-	.read_smc_arg = smu_v11_0_read_arg,
-	.setup_pptable = smu_v11_0_setup_pptable,
-	.init_smc_tables = smu_v11_0_init_smc_tables,
-	.fini_smc_tables = smu_v11_0_fini_smc_tables,
-	.init_power = smu_v11_0_init_power,
-	.fini_power = smu_v11_0_fini_power,
-	.get_vbios_bootup_values = smu_v11_0_get_vbios_bootup_values,
-	.get_clk_info_from_vbios = smu_v11_0_get_clk_info_from_vbios,
-	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
-	.check_pptable = smu_v11_0_check_pptable,
-	.parse_pptable = smu_v11_0_parse_pptable,
-	.populate_smc_tables = smu_v11_0_populate_smc_pptable,
-	.write_pptable = smu_v11_0_write_pptable,
-	.write_watermarks_table = smu_v11_0_write_watermarks_table,
-	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
-	.set_tool_table_location = smu_v11_0_set_tool_table_location,
-	.init_display_count = smu_v11_0_init_display_count,
-	.set_allowed_mask = smu_v11_0_set_allowed_mask,
-	.get_enabled_mask = smu_v11_0_get_enabled_mask,
-	.system_features_control = smu_v11_0_system_features_control,
-	.notify_display_change = smu_v11_0_notify_display_change,
-	.set_power_limit = smu_v11_0_set_power_limit,
-	.get_current_clk_freq = smu_v11_0_get_current_clk_freq,
-	.init_max_sustainable_clocks = smu_v11_0_init_max_sustainable_clocks,
-	.start_thermal_control = smu_v11_0_start_thermal_control,
-	.read_sensor = smu_v11_0_read_sensor,
-	.set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk,
-	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
-	.set_watermarks_for_clock_ranges = smu_v11_0_set_watermarks_for_clock_ranges,
-	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
-	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
-	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
-	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
-	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
-	.gfx_off_control = smu_v11_0_gfx_off_control,
-	.register_irq_handler = smu_v11_0_register_irq_handler,
-	.set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme,
-	.get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc,
-	.baco_is_support = smu_v11_0_baco_is_support,
-	.baco_get_state = smu_v11_0_baco_get_state,
-	.baco_set_state = smu_v11_0_baco_set_state,
-	.baco_reset = smu_v11_0_baco_reset,
-	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
-};
+int smu_v11_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t min, uint32_t max)
+{
+	int ret = 0, clk_id = 0;
+	uint32_t param;
 
-void smu_v11_0_set_smu_funcs(struct smu_context *smu)
+	clk_id = smu_clk_get_index(smu, clk_type);
+	if (clk_id < 0)
+		return clk_id;
+
+	if (max > 0) {
+		param = (uint32_t)((clk_id << 16) | (max & 0xffff));
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxByFreq,
+						  param);
+		if (ret)
+			return ret;
+	}
+
+	if (min > 0) {
+		param = (uint32_t)((clk_id << 16) | (min & 0xffff));
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMinByFreq,
+						  param);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+int smu_v11_0_override_pcie_parameters(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
+	uint32_t pcie_gen = 0, pcie_width = 0;
+	int ret;
 
-	smu->funcs = &smu_v11_0_funcs;
-	switch (adev->asic_type) {
-	case CHIP_VEGA20:
-		vega20_set_ppt_funcs(smu);
-		break;
-	case CHIP_ARCTURUS:
-		arcturus_set_ppt_funcs(smu);
-		break;
-	case CHIP_NAVI10:
-	case CHIP_NAVI14:
-	case CHIP_NAVI12:
-		navi10_set_ppt_funcs(smu);
-		break;
-	default:
-		pr_warn("Unknown asic for smu11\n");
+	if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4)
+		pcie_gen = 3;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
+		pcie_gen = 2;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2)
+		pcie_gen = 1;
+	else if (adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1)
+		pcie_gen = 0;
+
+	/* Bit 31:16: LCLK DPM level. 0 is DPM0, and 1 is DPM1
+	 * Bit 15:8:  PCIE GEN, 0 to 3 corresponds to GEN1 to GEN4
+	 * Bit 7:0:   PCIE lane width, 1 to 7 corresponds is x1 to x32
+	 */
+	if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X16)
+		pcie_width = 6;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X12)
+		pcie_width = 5;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X8)
+		pcie_width = 4;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4)
+		pcie_width = 3;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2)
+		pcie_width = 2;
+	else if (adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X1)
+		pcie_width = 1;
+
+	ret = smu_update_pcie_parameters(smu, pcie_gen, pcie_width);
+
+	if (ret)
+		pr_err("[%s] Attempt to override pcie params failed!\n", __func__);
+
+	return ret;
+
+}
+
+int smu_v11_0_set_default_od_settings(struct smu_context *smu, bool initialize, size_t overdrive_table_size)
+{
+	struct smu_table_context *table_context = &smu->smu_table;
+	int ret = 0;
+
+	if (initialize) {
+		if (table_context->overdrive_table) {
+			return -EINVAL;
+		}
+		table_context->overdrive_table = kzalloc(overdrive_table_size, GFP_KERNEL);
+		if (!table_context->overdrive_table) {
+			return -ENOMEM;
+		}
+		ret = smu_update_table(smu, SMU_TABLE_OVERDRIVE, 0, table_context->overdrive_table, false);
+		if (ret) {
+			pr_err("Failed to export overdrive table!\n");
+			return ret;
+		}
 	}
+	ret = smu_update_table(smu, SMU_TABLE_OVERDRIVE, 0, table_context->overdrive_table, true);
+	if (ret) {
+		pr_err("Failed to import overdrive table!\n");
+		return ret;
+	}
+	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
index 9d2280ca1f4b..094cfc46adac 100644
--- a/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
+++ b/drivers/gpu/drm/amd/powerplay/smu_v12_0.c
@@ -24,12 +24,12 @@
 #include <linux/firmware.h>
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "atomfirmware.h"
 #include "amdgpu_atomfirmware.h"
 #include "smu_v12_0.h"
 #include "soc15_common.h"
 #include "atom.h"
-#include "renoir_ppt.h"
 
 #include "asic_reg/mp/mp_12_0_0_offset.h"
 #include "asic_reg/mp/mp_12_0_0_sh_mask.h"
@@ -41,7 +41,7 @@
 #define SMUIO_GFX_MISC_CNTL__PWR_GFXOFF_STATUS_MASK          0x00000006L
 #define SMUIO_GFX_MISC_CNTL__PWR_GFXOFF_STATUS__SHIFT        0x1
 
-static int smu_v12_0_send_msg_without_waiting(struct smu_context *smu,
+int smu_v12_0_send_msg_without_waiting(struct smu_context *smu,
 					      uint16_t msg)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -50,7 +50,7 @@ static int smu_v12_0_send_msg_without_waiting(struct smu_context *smu,
 	return 0;
 }
 
-static int smu_v12_0_read_arg(struct smu_context *smu, uint32_t *arg)
+int smu_v12_0_read_arg(struct smu_context *smu, uint32_t *arg)
 {
 	struct amdgpu_device *adev = smu->adev;
 
@@ -58,7 +58,7 @@ static int smu_v12_0_read_arg(struct smu_context *smu, uint32_t *arg)
 	return 0;
 }
 
-static int smu_v12_0_wait_for_response(struct smu_context *smu)
+int smu_v12_0_wait_for_response(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t cur_value, i;
@@ -77,33 +77,9 @@ static int smu_v12_0_wait_for_response(struct smu_context *smu)
 	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90) == 0x1 ? 0 : -EIO;
 }
 
-static int smu_v12_0_send_msg(struct smu_context *smu, uint16_t msg)
-{
-	struct amdgpu_device *adev = smu->adev;
-	int ret = 0, index = 0;
-
-	index = smu_msg_get_index(smu, msg);
-	if (index < 0)
-		return index;
-
-	smu_v12_0_wait_for_response(smu);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	smu_v12_0_send_msg_without_waiting(smu, (uint16_t)index);
-
-	ret = smu_v12_0_wait_for_response(smu);
-
-	if (ret)
-		pr_err("Failed to send message 0x%x, response 0x%x\n", index,
-		       ret);
-
-	return ret;
-
-}
-
-static int
-smu_v12_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
+int
+smu_v12_0_send_msg_with_param(struct smu_context *smu,
+			      enum smu_message_type msg,
 			      uint32_t param)
 {
 	struct amdgpu_device *adev = smu->adev;
@@ -132,7 +108,7 @@ smu_v12_0_send_msg_with_param(struct smu_context *smu, uint16_t msg,
 	return ret;
 }
 
-static int smu_v12_0_check_fw_status(struct smu_context *smu)
+int smu_v12_0_check_fw_status(struct smu_context *smu)
 {
 	struct amdgpu_device *adev = smu->adev;
 	uint32_t mp1_fw_flags;
@@ -147,7 +123,7 @@ static int smu_v12_0_check_fw_status(struct smu_context *smu)
 	return -EIO;
 }
 
-static int smu_v12_0_check_fw_version(struct smu_context *smu)
+int smu_v12_0_check_fw_version(struct smu_context *smu)
 {
 	uint32_t if_version = 0xff, smu_version = 0xff;
 	uint16_t smu_major;
@@ -181,7 +157,7 @@ static int smu_v12_0_check_fw_version(struct smu_context *smu)
 	return ret;
 }
 
-static int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
+int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
 {
 	if (!(smu->adev->flags & AMD_IS_APU))
 		return 0;
@@ -192,7 +168,7 @@ static int smu_v12_0_powergate_sdma(struct smu_context *smu, bool gate)
 		return smu_send_smc_msg(smu, SMU_MSG_PowerUpSdma);
 }
 
-static int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
+int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
 {
 	if (!(smu->adev->flags & AMD_IS_APU))
 		return 0;
@@ -203,7 +179,7 @@ static int smu_v12_0_powergate_vcn(struct smu_context *smu, bool gate)
 		return smu_send_smc_msg(smu, SMU_MSG_PowerUpVcn);
 }
 
-static int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
+int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
 {
 	if (!(smu->adev->pg_flags & AMD_PG_SUPPORT_GFX_PG))
 		return 0;
@@ -224,7 +200,7 @@ static int smu_v12_0_set_gfx_cgpg(struct smu_context *smu, bool enable)
  * Returns 2=Not in GFXOFF.
  * Returns 3=Transition into GFXOFF.
  */
-static uint32_t smu_v12_0_get_gfxoff_status(struct smu_context *smu)
+uint32_t smu_v12_0_get_gfxoff_status(struct smu_context *smu)
 {
 	uint32_t reg;
 	uint32_t gfxOff_Status = 0;
@@ -237,22 +213,13 @@ static uint32_t smu_v12_0_get_gfxoff_status(struct smu_context *smu)
 	return gfxOff_Status;
 }
 
-static int smu_v12_0_gfx_off_control(struct smu_context *smu, bool enable)
+int smu_v12_0_gfx_off_control(struct smu_context *smu, bool enable)
 {
 	int ret = 0, timeout = 500;
 
 	if (enable) {
 		ret = smu_send_smc_msg(smu, SMU_MSG_AllowGfxOff);
 
-		/* confirm gfx is back to "off" state, timeout is 5 seconds */
-		while (!(smu_v12_0_get_gfxoff_status(smu) == 0)) {
-			msleep(10);
-			timeout--;
-			if (timeout == 0) {
-				DRM_ERROR("enable gfxoff timeout and failed!\n");
-				break;
-			}
-		}
 	} else {
 		ret = smu_send_smc_msg(smu, SMU_MSG_DisallowGfxOff);
 
@@ -270,12 +237,12 @@ static int smu_v12_0_gfx_off_control(struct smu_context *smu, bool enable)
 	return ret;
 }
 
-static int smu_v12_0_init_smc_tables(struct smu_context *smu)
+int smu_v12_0_init_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *tables = NULL;
 
-	if (smu_table->tables || smu_table->table_count == 0)
+	if (smu_table->tables)
 		return -EINVAL;
 
 	tables = kcalloc(SMU_TABLE_COUNT, sizeof(struct smu_table),
@@ -288,11 +255,11 @@ static int smu_v12_0_init_smc_tables(struct smu_context *smu)
 	return smu_tables_init(smu, tables);
 }
 
-static int smu_v12_0_fini_smc_tables(struct smu_context *smu)
+int smu_v12_0_fini_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 
-	if (!smu_table->tables || smu_table->table_count == 0)
+	if (!smu_table->tables)
 		return -EINVAL;
 
 	kfree(smu_table->clocks_table);
@@ -304,7 +271,7 @@ static int smu_v12_0_fini_smc_tables(struct smu_context *smu)
 	return 0;
 }
 
-static int smu_v12_0_populate_smc_tables(struct smu_context *smu)
+int smu_v12_0_populate_smc_tables(struct smu_context *smu)
 {
 	struct smu_table_context *smu_table = &smu->smu_table;
 	struct smu_table *table = NULL;
@@ -319,14 +286,20 @@ static int smu_v12_0_populate_smc_tables(struct smu_context *smu)
 	return smu_update_table(smu, SMU_TABLE_DPMCLOCKS, 0, smu_table->clocks_table, false);
 }
 
-static int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
+int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type clk_type,
 						 uint32_t *min, uint32_t *max)
 {
 	int ret = 0;
-
-	mutex_lock(&smu->mutex);
+	uint32_t mclk_mask, soc_mask;
 
 	if (max) {
+		ret = smu_get_profiling_clk_mask(smu, AMD_DPM_FORCED_LEVEL_PROFILE_PEAK,
+						 NULL,
+						 &mclk_mask,
+						 &soc_mask);
+		if (ret)
+			goto failed;
+
 		switch (clk_type) {
 		case SMU_GFXCLK:
 		case SMU_SCLK:
@@ -340,14 +313,20 @@ static int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk
 				goto failed;
 			break;
 		case SMU_UCLK:
-			ret = smu_get_dpm_uclk_limited(smu, max, true);
+		case SMU_FCLK:
+		case SMU_MCLK:
+			ret = smu_get_dpm_clk_limited(smu, clk_type, mclk_mask, max);
+			if (ret)
+				goto failed;
+			break;
+		case SMU_SOCCLK:
+			ret = smu_get_dpm_clk_limited(smu, clk_type, soc_mask, max);
 			if (ret)
 				goto failed;
 			break;
 		default:
 			ret = -EINVAL;
 			goto failed;
-
 		}
 	}
 
@@ -365,7 +344,14 @@ static int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk
 				goto failed;
 			break;
 		case SMU_UCLK:
-			ret = smu_get_dpm_uclk_limited(smu, min, false);
+		case SMU_FCLK:
+		case SMU_MCLK:
+			ret = smu_get_dpm_clk_limited(smu, clk_type, 0, min);
+			if (ret)
+				goto failed;
+			break;
+		case SMU_SOCCLK:
+			ret = smu_get_dpm_clk_limited(smu, clk_type, 0, min);
 			if (ret)
 				goto failed;
 			break;
@@ -373,40 +359,65 @@ static int smu_v12_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk
 			ret = -EINVAL;
 			goto failed;
 		}
-
 	}
 failed:
-	mutex_unlock(&smu->mutex);
 	return ret;
 }
 
-static const struct smu_funcs smu_v12_0_funcs = {
-	.check_fw_status = smu_v12_0_check_fw_status,
-	.check_fw_version = smu_v12_0_check_fw_version,
-	.powergate_sdma = smu_v12_0_powergate_sdma,
-	.powergate_vcn = smu_v12_0_powergate_vcn,
-	.send_smc_msg = smu_v12_0_send_msg,
-	.send_smc_msg_with_param = smu_v12_0_send_msg_with_param,
-	.read_smc_arg = smu_v12_0_read_arg,
-	.set_gfx_cgpg = smu_v12_0_set_gfx_cgpg,
-	.gfx_off_control = smu_v12_0_gfx_off_control,
-	.init_smc_tables = smu_v12_0_init_smc_tables,
-	.fini_smc_tables = smu_v12_0_fini_smc_tables,
-	.populate_smc_tables = smu_v12_0_populate_smc_tables,
-	.get_dpm_ultimate_freq = smu_v12_0_get_dpm_ultimate_freq,
-};
-
-void smu_v12_0_set_smu_funcs(struct smu_context *smu)
+int smu_v12_0_mode2_reset(struct smu_context *smu){
+	return smu_v12_0_send_msg_with_param(smu, SMU_MSG_GfxDeviceDriverReset, SMU_RESET_MODE_2);
+}
+
+int smu_v12_0_set_soft_freq_limited_range(struct smu_context *smu, enum smu_clk_type clk_type,
+			    uint32_t min, uint32_t max)
 {
-	struct amdgpu_device *adev = smu->adev;
+	int ret = 0;
 
-	smu->funcs = &smu_v12_0_funcs;
+	if (max < min)
+		return -EINVAL;
 
-	switch (adev->asic_type) {
-	case CHIP_RENOIR:
-		renoir_set_ppt_funcs(smu);
-		break;
+	switch (clk_type) {
+	case SMU_GFXCLK:
+	case SMU_SCLK:
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinGfxClk, min);
+		if (ret)
+			return ret;
+
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxGfxClk, max);
+		if (ret)
+			return ret;
+	break;
+	case SMU_FCLK:
+	case SMU_MCLK:
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinFclkByFreq, min);
+		if (ret)
+			return ret;
+
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxFclkByFreq, max);
+		if (ret)
+			return ret;
+	break;
+	case SMU_SOCCLK:
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinSocclkByFreq, min);
+		if (ret)
+			return ret;
+
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxSocclkByFreq, max);
+		if (ret)
+			return ret;
+	break;
+	case SMU_VCLK:
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetHardMinVcn, min);
+		if (ret)
+			return ret;
+
+		ret = smu_send_smc_msg_with_param(smu, SMU_MSG_SetSoftMaxVcn, max);
+		if (ret)
+			return ret;
+	break;
 	default:
-		pr_warn("Unknown asic for smu12\n");
+		return -EINVAL;
 	}
+
+	return ret;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index 3f12cf341511..aa0ee2b46135 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -137,7 +137,7 @@ static int smu10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			priv->smu_tables.entry[table_id].table_id);
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	memcpy(table, (uint8_t *)priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
index 4728aa23a818..7dca04a89217 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
@@ -177,12 +177,10 @@ static int smu8_load_mec_firmware(struct pp_hwmgr *hwmgr)
 	uint32_t tmp;
 	int ret = 0;
 	struct cgs_firmware_info info = {0};
-	struct smu8_smumgr *smu8_smu;
 
 	if (hwmgr == NULL || hwmgr->device == NULL)
 		return -EINVAL;
 
-	smu8_smu = hwmgr->smu_backend;
 	ret = cgs_get_firmware_info(hwmgr->device,
 						CGS_UCODE_ID_CP_MEC, &info);
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index 0dbdde69f2d9..0f3836fd9666 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -58,7 +58,7 @@ static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			priv->smu_tables.entry[table_id].table_id);
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index f9589806bf83..90c782c132d2 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -66,7 +66,7 @@ static int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			return -EINVAL);
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
index b9089c6bea85..f604612f411f 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c
@@ -189,7 +189,7 @@ static int vega20_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			return ret);
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[table_id].table,
 			priv->smu_tables.entry[table_id].size);
@@ -290,7 +290,7 @@ int vega20_get_activity_monitor_coeff(struct pp_hwmgr *hwmgr,
 			return ret);
 
 	/* flush hdp cache */
-	adev->nbio_funcs->hdp_flush(adev, NULL);
+	adev->nbio.funcs->hdp_flush(adev, NULL);
 
 	memcpy(table, priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].table,
 			priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size);
diff --git a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
index bbd8ebd58434..60b9ff097142 100644
--- a/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
+++ b/drivers/gpu/drm/amd/powerplay/vega20_ppt.c
@@ -25,6 +25,7 @@
 #include <linux/firmware.h>
 #include "amdgpu.h"
 #include "amdgpu_smu.h"
+#include "smu_internal.h"
 #include "atomfirmware.h"
 #include "amdgpu_atomfirmware.h"
 #include "smu_v11_0.h"
@@ -143,6 +144,7 @@ static struct smu_11_0_cmn2aisc_mapping vega20_message_map[SMU_MSG_MAX_COUNT] =
 	MSG_MAP(PrepareMp1ForShutdown),
 	MSG_MAP(SetMGpuFanBoostLimitRpm),
 	MSG_MAP(GetAVFSVoltageByDpm),
+	MSG_MAP(DFCstateControl),
 };
 
 static struct smu_11_0_cmn2aisc_mapping vega20_clk_map[SMU_CLK_COUNT] = {
@@ -219,7 +221,7 @@ static struct smu_11_0_cmn2aisc_mapping vega20_workload_map[PP_SMC_POWER_PROFILE
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_POWERSAVING,		WORKLOAD_PPLIB_POWER_SAVING_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VIDEO,		WORKLOAD_PPLIB_VIDEO_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_VR,			WORKLOAD_PPLIB_VR_BIT),
-	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_CUSTOM_BIT),
+	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_COMPUTE,		WORKLOAD_PPLIB_COMPUTE_BIT),
 	WORKLOAD_MAP(PP_SMC_POWER_PROFILE_CUSTOM,		WORKLOAD_PPLIB_CUSTOM_BIT),
 };
 
@@ -464,7 +466,6 @@ static int vega20_store_powerplay_table(struct smu_context *smu)
 	       sizeof(PPTable_t));
 
 	table_context->thermal_controller_type = powerplay_table->ucThermalControllerType;
-	table_context->TDPODLimit = le32_to_cpu(powerplay_table->OverDrive8Table.ODSettingsMax[ATOM_VEGA20_ODSETTING_POWERPERCENTAGE]);
 
 	return 0;
 }
@@ -634,7 +635,6 @@ amd_pm_state_type vega20_get_current_power_state(struct smu_context *smu)
 	    !smu_dpm_ctx->dpm_current_power_state)
 		return -EINVAL;
 
-	mutex_lock(&(smu->mutex));
 	switch (smu_dpm_ctx->dpm_current_power_state->classification.ui_label) {
 	case SMU_STATE_UI_LABEL_BATTERY:
 		pm_type = POWER_STATE_TYPE_BATTERY;
@@ -652,7 +652,6 @@ amd_pm_state_type vega20_get_current_power_state(struct smu_context *smu)
 			pm_type = POWER_STATE_TYPE_DEFAULT;
 		break;
 	}
-	mutex_unlock(&(smu->mutex));
 
 	return pm_type;
 }
@@ -1274,16 +1273,8 @@ static int vega20_force_clk_levels(struct smu_context *smu,
 	struct vega20_dpm_table *dpm_table;
 	struct vega20_single_dpm_table *single_dpm_table;
 	uint32_t soft_min_level, soft_max_level, hard_min_level;
-	struct smu_dpm_context *smu_dpm = &smu->smu_dpm;
 	int ret = 0;
 
-	if (smu_dpm->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) {
-		pr_info("force clock level is for dpm manual mode only.\n");
-		return -EINVAL;
-	}
-
-	mutex_lock(&(smu->mutex));
-
 	soft_min_level = mask ? (ffs(mask) - 1) : 0;
 	soft_max_level = mask ? (fls(mask) - 1) : 0;
 
@@ -1436,7 +1427,6 @@ static int vega20_force_clk_levels(struct smu_context *smu,
 		break;
 	}
 
-	mutex_unlock(&(smu->mutex));
 	return ret;
 }
 
@@ -1451,8 +1441,6 @@ static int vega20_get_clock_by_type_with_latency(struct smu_context *smu,
 
 	dpm_table = smu_dpm->dpm_context;
 
-	mutex_lock(&smu->mutex);
-
 	switch (clk_type) {
 	case SMU_GFXCLK:
 		single_dpm_table = &(dpm_table->gfx_table);
@@ -1474,7 +1462,6 @@ static int vega20_get_clock_by_type_with_latency(struct smu_context *smu,
 		ret = -EINVAL;
 	}
 
-	mutex_unlock(&smu->mutex);
 	return ret;
 }
 
@@ -2260,7 +2247,7 @@ vega20_notify_smc_dispaly_config(struct smu_context *smu)
 	if (smu_feature_is_supported(smu, SMU_FEATURE_DPM_DCEFCLK_BIT)) {
 		clock_req.clock_type = amd_pp_dcef_clock;
 		clock_req.clock_freq_in_khz = min_clocks.dcef_clock * 10;
-		if (!smu->funcs->display_clock_voltage_request(smu, &clock_req)) {
+		if (!smu_v11_0_display_clock_voltage_request(smu, &clock_req)) {
 			if (smu_feature_is_supported(smu, SMU_FEATURE_DS_DCEFCLK_BIT)) {
 				ret = smu_send_smc_msg_with_param(smu,
 								  SMU_MSG_SetMinDeepSleepDcefclk,
@@ -2547,8 +2534,6 @@ static int vega20_set_od_percentage(struct smu_context *smu,
 	int feature_enabled;
 	PPCLK_e clk_id;
 
-	mutex_lock(&(smu->mutex));
-
 	dpm_table = smu_dpm->dpm_context;
 	golden_table = smu_dpm->golden_dpm_context;
 
@@ -2598,11 +2583,10 @@ static int vega20_set_od_percentage(struct smu_context *smu,
 	}
 
 	ret = smu_handle_task(smu, smu_dpm->dpm_level,
-			      AMD_PP_TASK_READJUST_POWER_STATE);
+			      AMD_PP_TASK_READJUST_POWER_STATE,
+			      false);
 
 set_od_failed:
-	mutex_unlock(&(smu->mutex));
-
 	return ret;
 }
 
@@ -2827,10 +2811,9 @@ static int vega20_odn_edit_dpm_table(struct smu_context *smu,
 	}
 
 	if (type == PP_OD_COMMIT_DPM_TABLE) {
-		mutex_lock(&(smu->mutex));
 		ret = smu_handle_task(smu, smu_dpm->dpm_level,
-				      AMD_PP_TASK_READJUST_POWER_STATE);
-		mutex_unlock(&(smu->mutex));
+				      AMD_PP_TASK_READJUST_POWER_STATE,
+				      false);
 	}
 
 	return ret;
@@ -3047,7 +3030,7 @@ static int vega20_read_sensor(struct smu_context *smu,
 		*size = 4;
 		break;
 	default:
-		ret = smu_smc_read_sensor(smu, sensor, data, size);
+		ret = smu_v11_0_read_sensor(smu, sensor, data, size);
 	}
 	mutex_unlock(&smu->sensor_lock);
 
@@ -3141,6 +3124,49 @@ static int vega20_get_thermal_temperature_range(struct smu_context *smu,
 	return 0;
 }
 
+static int vega20_set_df_cstate(struct smu_context *smu,
+				enum pp_df_cstate state)
+{
+	uint32_t smu_version;
+	int ret;
+
+	ret = smu_get_smc_version(smu, NULL, &smu_version);
+	if (ret) {
+		pr_err("Failed to get smu version!\n");
+		return ret;
+	}
+
+	/* PPSMC_MSG_DFCstateControl is supported with 40.50 and later fws */
+	if (smu_version < 0x283200) {
+		pr_err("Df cstate control is supported with 40.50 and later SMC fw!\n");
+		return -EINVAL;
+	}
+
+	return smu_send_smc_msg_with_param(smu, SMU_MSG_DFCstateControl, state);
+}
+
+static int vega20_update_pcie_parameters(struct smu_context *smu,
+				     uint32_t pcie_gen_cap,
+				     uint32_t pcie_width_cap)
+{
+	PPTable_t *pptable = smu->smu_table.driver_pptable;
+	int ret, i;
+	uint32_t smu_pcie_arg;
+
+	for (i = 0; i < NUM_LINK_LEVELS; i++) {
+		smu_pcie_arg = (i << 16) |
+			((pptable->PcieGenSpeed[i] <= pcie_gen_cap) ? (pptable->PcieGenSpeed[i] << 8) :
+				(pcie_gen_cap << 8)) | ((pptable->PcieLaneCount[i] <= pcie_width_cap) ?
+					pptable->PcieLaneCount[i] : pcie_width_cap);
+		ret = smu_send_smc_msg_with_param(smu,
+					  SMU_MSG_OverridePcieParameters,
+					  smu_pcie_arg);
+	}
+
+	return ret;
+}
+
+
 static const struct pptable_funcs vega20_ppt_funcs = {
 	.tables_init = vega20_tables_init,
 	.alloc_dpm_context = vega20_allocate_dpm_context,
@@ -3153,7 +3179,7 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.get_smu_table_index = vega20_get_smu_table_index,
 	.get_smu_power_index = vega20_get_pwr_src_index,
 	.get_workload_type = vega20_get_workload_type,
-	.run_afll_btc = vega20_run_btc_afll,
+	.run_btc = vega20_run_btc_afll,
 	.get_allowed_feature_mask = vega20_get_allowed_feature_mask,
 	.get_current_power_state = vega20_get_current_power_state,
 	.set_default_dpm_table = vega20_set_default_dpm_table,
@@ -3183,13 +3209,60 @@ static const struct pptable_funcs vega20_ppt_funcs = {
 	.get_fan_speed_percent = vega20_get_fan_speed_percent,
 	.get_fan_speed_rpm = vega20_get_fan_speed_rpm,
 	.set_watermarks_table = vega20_set_watermarks_table,
-	.get_thermal_temperature_range = vega20_get_thermal_temperature_range
+	.get_thermal_temperature_range = vega20_get_thermal_temperature_range,
+	.set_df_cstate = vega20_set_df_cstate,
+	.update_pcie_parameters = vega20_update_pcie_parameters,
+	.init_microcode = smu_v11_0_init_microcode,
+	.load_microcode = smu_v11_0_load_microcode,
+	.init_smc_tables = smu_v11_0_init_smc_tables,
+	.fini_smc_tables = smu_v11_0_fini_smc_tables,
+	.init_power = smu_v11_0_init_power,
+	.fini_power = smu_v11_0_fini_power,
+	.check_fw_status = smu_v11_0_check_fw_status,
+	.setup_pptable = smu_v11_0_setup_pptable,
+	.get_vbios_bootup_values = smu_v11_0_get_vbios_bootup_values,
+	.get_clk_info_from_vbios = smu_v11_0_get_clk_info_from_vbios,
+	.check_pptable = smu_v11_0_check_pptable,
+	.parse_pptable = smu_v11_0_parse_pptable,
+	.populate_smc_tables = smu_v11_0_populate_smc_pptable,
+	.check_fw_version = smu_v11_0_check_fw_version,
+	.write_pptable = smu_v11_0_write_pptable,
+	.set_min_dcef_deep_sleep = smu_v11_0_set_min_dcef_deep_sleep,
+	.set_tool_table_location = smu_v11_0_set_tool_table_location,
+	.notify_memory_pool_location = smu_v11_0_notify_memory_pool_location,
+	.system_features_control = smu_v11_0_system_features_control,
+	.send_smc_msg_with_param = smu_v11_0_send_msg_with_param,
+	.read_smc_arg = smu_v11_0_read_arg,
+	.init_display_count = smu_v11_0_init_display_count,
+	.set_allowed_mask = smu_v11_0_set_allowed_mask,
+	.get_enabled_mask = smu_v11_0_get_enabled_mask,
+	.notify_display_change = smu_v11_0_notify_display_change,
+	.set_power_limit = smu_v11_0_set_power_limit,
+	.get_current_clk_freq = smu_v11_0_get_current_clk_freq,
+	.init_max_sustainable_clocks = smu_v11_0_init_max_sustainable_clocks,
+	.start_thermal_control = smu_v11_0_start_thermal_control,
+	.stop_thermal_control = smu_v11_0_stop_thermal_control,
+	.set_deep_sleep_dcefclk = smu_v11_0_set_deep_sleep_dcefclk,
+	.display_clock_voltage_request = smu_v11_0_display_clock_voltage_request,
+	.get_fan_control_mode = smu_v11_0_get_fan_control_mode,
+	.set_fan_control_mode = smu_v11_0_set_fan_control_mode,
+	.set_fan_speed_percent = smu_v11_0_set_fan_speed_percent,
+	.set_fan_speed_rpm = smu_v11_0_set_fan_speed_rpm,
+	.set_xgmi_pstate = smu_v11_0_set_xgmi_pstate,
+	.gfx_off_control = smu_v11_0_gfx_off_control,
+	.register_irq_handler = smu_v11_0_register_irq_handler,
+	.set_azalia_d3_pme = smu_v11_0_set_azalia_d3_pme,
+	.get_max_sustainable_clocks_by_dc = smu_v11_0_get_max_sustainable_clocks_by_dc,
+	.baco_is_support= smu_v11_0_baco_is_support,
+	.baco_get_state = smu_v11_0_baco_get_state,
+	.baco_set_state = smu_v11_0_baco_set_state,
+	.baco_reset = smu_v11_0_baco_reset,
+	.get_dpm_ultimate_freq = smu_v11_0_get_dpm_ultimate_freq,
+	.set_soft_freq_limited_range = smu_v11_0_set_soft_freq_limited_range,
+	.override_pcie_parameters = smu_v11_0_override_pcie_parameters,
 };
 
 void vega20_set_ppt_funcs(struct smu_context *smu)
 {
-	struct smu_table_context *smu_table = &smu->smu_table;
-
 	smu->ppt_funcs = &vega20_ppt_funcs;
-	smu_table->table_count = TABLE_COUNT;
 }
diff --git a/drivers/gpu/drm/arc/arcpgu_drv.c b/drivers/gpu/drm/arc/arcpgu_drv.c
index 6b7f791685ec..d6a6692db0ac 100644
--- a/drivers/gpu/drm/arc/arcpgu_drv.c
+++ b/drivers/gpu/drm/arc/arcpgu_drv.c
@@ -14,6 +14,7 @@
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_of.h>
 #include <drm/drm_probe_helper.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
@@ -45,7 +46,7 @@ static int arcpgu_load(struct drm_device *drm)
 {
 	struct platform_device *pdev = to_platform_device(drm->dev);
 	struct arcpgu_drm_private *arcpgu;
-	struct device_node *encoder_node;
+	struct device_node *encoder_node = NULL, *endpoint_node = NULL;
 	struct resource *res;
 	int ret;
 
@@ -80,14 +81,23 @@ static int arcpgu_load(struct drm_device *drm)
 	if (arc_pgu_setup_crtc(drm) < 0)
 		return -ENODEV;
 
-	/* find the encoder node and initialize it */
-	encoder_node = of_parse_phandle(drm->dev->of_node, "encoder-slave", 0);
+	/*
+	 * There is only one output port inside each device. It is linked with
+	 * encoder endpoint.
+	 */
+	endpoint_node = of_graph_get_next_endpoint(pdev->dev.of_node, NULL);
+	if (endpoint_node) {
+		encoder_node = of_graph_get_remote_port_parent(endpoint_node);
+		of_node_put(endpoint_node);
+	}
+
 	if (encoder_node) {
 		ret = arcpgu_drm_hdmi_init(drm, encoder_node);
 		of_node_put(encoder_node);
 		if (ret < 0)
 			return ret;
 	} else {
+		dev_info(drm->dev, "no encoder found. Assumed virtual LCD on simulation platform\n");
 		ret = arcpgu_drm_sim_init(drm, NULL);
 		if (ret < 0)
 			return ret;
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
index d49772de93e0..52648b4008bc 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
@@ -84,7 +84,8 @@ static void komeda_kms_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_disables(dev, old_state);
 
-	drm_atomic_helper_commit_planes(dev, old_state, 0);
+	drm_atomic_helper_commit_planes(dev, old_state,
+					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
index 42bdc63dcffa..52750116aa19 100644
--- a/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
+++ b/drivers/gpu/drm/arm/display/komeda/komeda_pipeline_state.c
@@ -581,8 +581,8 @@ komeda_splitter_validate(struct komeda_splitter *splitter,
 	}
 
 	if (!in_range(&splitter->vsize, dflow->in_h)) {
-		DRM_DEBUG_ATOMIC("split in_in: %d exceed the acceptable range.\n",
-				 dflow->in_w);
+		DRM_DEBUG_ATOMIC("split in_h: %d exceeds the acceptable range.\n",
+				 dflow->in_h);
 		return -EINVAL;
 	}
 
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 02a9c1ed165b..3f0006c2470d 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -69,33 +69,11 @@ static void bochs_pipe_update(struct drm_simple_display_pipe *pipe,
 	}
 }
 
-static int bochs_pipe_prepare_fb(struct drm_simple_display_pipe *pipe,
-				 struct drm_plane_state *new_state)
-{
-	struct drm_gem_vram_object *gbo;
-
-	if (!new_state->fb)
-		return 0;
-	gbo = drm_gem_vram_of_gem(new_state->fb->obj[0]);
-	return drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-}
-
-static void bochs_pipe_cleanup_fb(struct drm_simple_display_pipe *pipe,
-				  struct drm_plane_state *old_state)
-{
-	struct drm_gem_vram_object *gbo;
-
-	if (!old_state->fb)
-		return;
-	gbo = drm_gem_vram_of_gem(old_state->fb->obj[0]);
-	drm_gem_vram_unpin(gbo);
-}
-
 static const struct drm_simple_display_pipe_funcs bochs_pipe_funcs = {
 	.enable	    = bochs_pipe_enable,
 	.update	    = bochs_pipe_update,
-	.prepare_fb = bochs_pipe_prepare_fb,
-	.cleanup_fb = bochs_pipe_cleanup_fb,
+	.prepare_fb = drm_gem_vram_simple_display_pipe_prepare_fb,
+	.cleanup_fb = drm_gem_vram_simple_display_pipe_cleanup_fb,
 };
 
 static int bochs_connector_get_modes(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/cirrus/cirrus.c b/drivers/gpu/drm/cirrus/cirrus.c
index 7d08d067e1a4..248c9f765c45 100644
--- a/drivers/gpu/drm/cirrus/cirrus.c
+++ b/drivers/gpu/drm/cirrus/cirrus.c
@@ -390,7 +390,7 @@ static int cirrus_conn_init(struct cirrus_device *cirrus)
 /* ------------------------------------------------------------------ */
 /* cirrus (simple) display pipe					      */
 
-static enum drm_mode_status cirrus_pipe_mode_valid(struct drm_crtc *crtc,
+static enum drm_mode_status cirrus_pipe_mode_valid(struct drm_simple_display_pipe *pipe,
 						   const struct drm_display_mode *mode)
 {
 	if (cirrus_check_size(mode->hdisplay, mode->vdisplay, NULL) < 0)
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 587052751b48..b191d39c071d 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1571,8 +1571,11 @@ static void commit_tail(struct drm_atomic_state *old_state)
 {
 	struct drm_device *dev = old_state->dev;
 	const struct drm_mode_config_helper_funcs *funcs;
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
 	ktime_t start;
 	s64 commit_time_ms;
+	unsigned int i, new_self_refresh_mask = 0;
 
 	funcs = dev->mode_config.helper_private;
 
@@ -1592,6 +1595,15 @@ static void commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_wait_for_dependencies(old_state);
 
+	/*
+	 * We cannot safely access new_crtc_state after
+	 * drm_atomic_helper_commit_hw_done() so figure out which crtc's have
+	 * self-refresh active beforehand:
+	 */
+	for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i)
+		if (new_crtc_state->self_refresh_active)
+			new_self_refresh_mask |= BIT(i);
+
 	if (funcs && funcs->atomic_commit_tail)
 		funcs->atomic_commit_tail(old_state);
 	else
@@ -1600,7 +1612,8 @@ static void commit_tail(struct drm_atomic_state *old_state)
 	commit_time_ms = ktime_ms_delta(ktime_get(), start);
 	if (commit_time_ms > 0)
 		drm_self_refresh_helper_update_avg_times(old_state,
-						 (unsigned long)commit_time_ms);
+						 (unsigned long)commit_time_ms,
+						 new_self_refresh_mask);
 
 	drm_atomic_helper_commit_cleanup_done(old_state);
 
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
index 3bd76e918b5d..03e01b000f7a 100644
--- a/drivers/gpu/drm/drm_cache.c
+++ b/drivers/gpu/drm/drm_cache.c
@@ -62,10 +62,10 @@ static void drm_cache_flush_clflush(struct page *pages[],
 {
 	unsigned long i;
 
-	mb();
+	mb(); /*Full memory barrier used before so that CLFLUSH is ordered*/
 	for (i = 0; i < num_pages; i++)
 		drm_clflush_page(*pages++);
-	mb();
+	mb(); /*Also used after CLFLUSH so that all cache is flushed*/
 }
 #endif
 
@@ -92,6 +92,7 @@ drm_clflush_pages(struct page *pages[], unsigned long num_pages)
 
 #elif defined(__powerpc__)
 	unsigned long i;
+
 	for (i = 0; i < num_pages; i++) {
 		struct page *page = pages[i];
 		void *page_virtual;
@@ -125,10 +126,10 @@ drm_clflush_sg(struct sg_table *st)
 	if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
 		struct sg_page_iter sg_iter;
 
-		mb();
+		mb(); /*CLFLUSH is ordered only by using memory barriers*/
 		for_each_sg_page(st->sgl, &sg_iter, st->nents, 0)
 			drm_clflush_page(sg_page_iter_page(&sg_iter));
-		mb();
+		mb(); /*Make sure that all cache line entry is flushed*/
 
 		return;
 	}
@@ -157,12 +158,13 @@ drm_clflush_virt_range(void *addr, unsigned long length)
 	if (static_cpu_has(X86_FEATURE_CLFLUSH)) {
 		const int size = boot_cpu_data.x86_clflush_size;
 		void *end = addr + length;
+
 		addr = (void *)(((unsigned long)addr) & -size);
-		mb();
+		mb(); /*CLFLUSH is only ordered with a full memory barrier*/
 		for (; addr < end; addr += size)
 			clflushopt(addr);
 		clflushopt(end - 1); /* force serialisation */
-		mb();
+		mb(); /*Ensure that evry data cache line entry is flushed*/
 		return;
 	}
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index b854a422a523..ae5809a1f19a 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -28,6 +28,13 @@
 #include <linux/sched.h>
 #include <linux/seq_file.h>
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+#include <linux/stacktrace.h>
+#include <linux/sort.h>
+#include <linux/timekeeping.h>
+#include <linux/math64.h>
+#endif
+
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_dp_mst_helper.h>
@@ -45,6 +52,12 @@
  * protocol. The helpers contain a topology manager and bandwidth manager.
  * The helpers encapsulate the sending and received of sideband msgs.
  */
+struct drm_dp_pending_up_req {
+	struct drm_dp_sideband_msg_hdr hdr;
+	struct drm_dp_sideband_msg_req_body msg;
+	struct list_head next;
+};
+
 static bool dump_dp_payload_table(struct drm_dp_mst_topology_mgr *mgr,
 				  char *buf);
 
@@ -61,8 +74,8 @@ static int drm_dp_send_dpcd_write(struct drm_dp_mst_topology_mgr *mgr,
 				  struct drm_dp_mst_port *port,
 				  int offset, int size, u8 *bytes);
 
-static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
-				     struct drm_dp_mst_branch *mstb);
+static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+				    struct drm_dp_mst_branch *mstb);
 static int drm_dp_send_enum_path_resources(struct drm_dp_mst_topology_mgr *mgr,
 					   struct drm_dp_mst_branch *mstb,
 					   struct drm_dp_mst_port *port);
@@ -1393,39 +1406,194 @@ drm_dp_mst_put_port_malloc(struct drm_dp_mst_port *port)
 }
 EXPORT_SYMBOL(drm_dp_mst_put_port_malloc);
 
-static void drm_dp_destroy_mst_branch_device(struct kref *kref)
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+
+#define STACK_DEPTH 8
+
+static noinline void
+__topology_ref_save(struct drm_dp_mst_topology_mgr *mgr,
+		    struct drm_dp_mst_topology_ref_history *history,
+		    enum drm_dp_mst_topology_ref_type type)
 {
-	struct drm_dp_mst_branch *mstb =
-		container_of(kref, struct drm_dp_mst_branch, topology_kref);
-	struct drm_dp_mst_topology_mgr *mgr = mstb->mgr;
-	struct drm_dp_mst_port *port, *tmp;
-	bool wake_tx = false;
+	struct drm_dp_mst_topology_ref_entry *entry = NULL;
+	depot_stack_handle_t backtrace;
+	ulong stack_entries[STACK_DEPTH];
+	uint n;
+	int i;
 
-	mutex_lock(&mgr->lock);
-	list_for_each_entry_safe(port, tmp, &mstb->ports, next) {
-		list_del(&port->next);
-		drm_dp_mst_topology_put_port(port);
+	n = stack_trace_save(stack_entries, ARRAY_SIZE(stack_entries), 1);
+	backtrace = stack_depot_save(stack_entries, n, GFP_KERNEL);
+	if (!backtrace)
+		return;
+
+	/* Try to find an existing entry for this backtrace */
+	for (i = 0; i < history->len; i++) {
+		if (history->entries[i].backtrace == backtrace) {
+			entry = &history->entries[i];
+			break;
+		}
 	}
-	mutex_unlock(&mgr->lock);
 
-	/* drop any tx slots msg */
-	mutex_lock(&mstb->mgr->qlock);
-	if (mstb->tx_slots[0]) {
-		mstb->tx_slots[0]->state = DRM_DP_SIDEBAND_TX_TIMEOUT;
-		mstb->tx_slots[0] = NULL;
-		wake_tx = true;
+	/* Otherwise add one */
+	if (!entry) {
+		struct drm_dp_mst_topology_ref_entry *new;
+		int new_len = history->len + 1;
+
+		new = krealloc(history->entries, sizeof(*new) * new_len,
+			       GFP_KERNEL);
+		if (!new)
+			return;
+
+		entry = &new[history->len];
+		history->len = new_len;
+		history->entries = new;
+
+		entry->backtrace = backtrace;
+		entry->type = type;
+		entry->count = 0;
 	}
-	if (mstb->tx_slots[1]) {
-		mstb->tx_slots[1]->state = DRM_DP_SIDEBAND_TX_TIMEOUT;
-		mstb->tx_slots[1] = NULL;
-		wake_tx = true;
+	entry->count++;
+	entry->ts_nsec = ktime_get_ns();
+}
+
+static int
+topology_ref_history_cmp(const void *a, const void *b)
+{
+	const struct drm_dp_mst_topology_ref_entry *entry_a = a, *entry_b = b;
+
+	if (entry_a->ts_nsec > entry_b->ts_nsec)
+		return 1;
+	else if (entry_a->ts_nsec < entry_b->ts_nsec)
+		return -1;
+	else
+		return 0;
+}
+
+static inline const char *
+topology_ref_type_to_str(enum drm_dp_mst_topology_ref_type type)
+{
+	if (type == DRM_DP_MST_TOPOLOGY_REF_GET)
+		return "get";
+	else
+		return "put";
+}
+
+static void
+__dump_topology_ref_history(struct drm_dp_mst_topology_ref_history *history,
+			    void *ptr, const char *type_str)
+{
+	struct drm_printer p = drm_debug_printer(DBG_PREFIX);
+	char *buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	int i;
+
+	if (!buf)
+		return;
+
+	if (!history->len)
+		goto out;
+
+	/* First, sort the list so that it goes from oldest to newest
+	 * reference entry
+	 */
+	sort(history->entries, history->len, sizeof(*history->entries),
+	     topology_ref_history_cmp, NULL);
+
+	drm_printf(&p, "%s (%p) topology count reached 0, dumping history:\n",
+		   type_str, ptr);
+
+	for (i = 0; i < history->len; i++) {
+		const struct drm_dp_mst_topology_ref_entry *entry =
+			&history->entries[i];
+		ulong *entries;
+		uint nr_entries;
+		u64 ts_nsec = entry->ts_nsec;
+		u32 rem_nsec = do_div(ts_nsec, 1000000000);
+
+		nr_entries = stack_depot_fetch(entry->backtrace, &entries);
+		stack_trace_snprint(buf, PAGE_SIZE, entries, nr_entries, 4);
+
+		drm_printf(&p, "  %d %ss (last at %5llu.%06u):\n%s",
+			   entry->count,
+			   topology_ref_type_to_str(entry->type),
+			   ts_nsec, rem_nsec / 1000, buf);
 	}
-	mutex_unlock(&mstb->mgr->qlock);
 
-	if (wake_tx)
-		wake_up_all(&mstb->mgr->tx_waitq);
+	/* Now free the history, since this is the only time we expose it */
+	kfree(history->entries);
+out:
+	kfree(buf);
+}
 
-	drm_dp_mst_put_mstb_malloc(mstb);
+static __always_inline void
+drm_dp_mst_dump_mstb_topology_history(struct drm_dp_mst_branch *mstb)
+{
+	__dump_topology_ref_history(&mstb->topology_ref_history, mstb,
+				    "MSTB");
+}
+
+static __always_inline void
+drm_dp_mst_dump_port_topology_history(struct drm_dp_mst_port *port)
+{
+	__dump_topology_ref_history(&port->topology_ref_history, port,
+				    "Port");
+}
+
+static __always_inline void
+save_mstb_topology_ref(struct drm_dp_mst_branch *mstb,
+		       enum drm_dp_mst_topology_ref_type type)
+{
+	__topology_ref_save(mstb->mgr, &mstb->topology_ref_history, type);
+}
+
+static __always_inline void
+save_port_topology_ref(struct drm_dp_mst_port *port,
+		       enum drm_dp_mst_topology_ref_type type)
+{
+	__topology_ref_save(port->mgr, &port->topology_ref_history, type);
+}
+
+static inline void
+topology_ref_history_lock(struct drm_dp_mst_topology_mgr *mgr)
+{
+	mutex_lock(&mgr->topology_ref_history_lock);
+}
+
+static inline void
+topology_ref_history_unlock(struct drm_dp_mst_topology_mgr *mgr)
+{
+	mutex_unlock(&mgr->topology_ref_history_lock);
+}
+#else
+static inline void
+topology_ref_history_lock(struct drm_dp_mst_topology_mgr *mgr) {}
+static inline void
+topology_ref_history_unlock(struct drm_dp_mst_topology_mgr *mgr) {}
+static inline void
+drm_dp_mst_dump_mstb_topology_history(struct drm_dp_mst_branch *mstb) {}
+static inline void
+drm_dp_mst_dump_port_topology_history(struct drm_dp_mst_port *port) {}
+#define save_mstb_topology_ref(mstb, type)
+#define save_port_topology_ref(port, type)
+#endif
+
+static void drm_dp_destroy_mst_branch_device(struct kref *kref)
+{
+	struct drm_dp_mst_branch *mstb =
+		container_of(kref, struct drm_dp_mst_branch, topology_kref);
+	struct drm_dp_mst_topology_mgr *mgr = mstb->mgr;
+
+	drm_dp_mst_dump_mstb_topology_history(mstb);
+
+	INIT_LIST_HEAD(&mstb->destroy_next);
+
+	/*
+	 * This can get called under mgr->mutex, so we need to perform the
+	 * actual destruction of the mstb in another worker
+	 */
+	mutex_lock(&mgr->delayed_destroy_lock);
+	list_add(&mstb->destroy_next, &mgr->destroy_branch_device_list);
+	mutex_unlock(&mgr->delayed_destroy_lock);
+	schedule_work(&mgr->delayed_destroy_work);
 }
 
 /**
@@ -1453,11 +1621,17 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref)
 static int __must_check
 drm_dp_mst_topology_try_get_mstb(struct drm_dp_mst_branch *mstb)
 {
-	int ret = kref_get_unless_zero(&mstb->topology_kref);
+	int ret;
 
-	if (ret)
-		DRM_DEBUG("mstb %p (%d)\n", mstb,
-			  kref_read(&mstb->topology_kref));
+	topology_ref_history_lock(mstb->mgr);
+	ret = kref_get_unless_zero(&mstb->topology_kref);
+	if (ret) {
+		DRM_DEBUG("mstb %p (%d)\n",
+			  mstb, kref_read(&mstb->topology_kref));
+		save_mstb_topology_ref(mstb, DRM_DP_MST_TOPOLOGY_REF_GET);
+	}
+
+	topology_ref_history_unlock(mstb->mgr);
 
 	return ret;
 }
@@ -1478,9 +1652,14 @@ drm_dp_mst_topology_try_get_mstb(struct drm_dp_mst_branch *mstb)
  */
 static void drm_dp_mst_topology_get_mstb(struct drm_dp_mst_branch *mstb)
 {
+	topology_ref_history_lock(mstb->mgr);
+
+	save_mstb_topology_ref(mstb, DRM_DP_MST_TOPOLOGY_REF_GET);
 	WARN_ON(kref_read(&mstb->topology_kref) == 0);
 	kref_get(&mstb->topology_kref);
 	DRM_DEBUG("mstb %p (%d)\n", mstb, kref_read(&mstb->topology_kref));
+
+	topology_ref_history_unlock(mstb->mgr);
 }
 
 /**
@@ -1498,27 +1677,14 @@ static void drm_dp_mst_topology_get_mstb(struct drm_dp_mst_branch *mstb)
 static void
 drm_dp_mst_topology_put_mstb(struct drm_dp_mst_branch *mstb)
 {
+	topology_ref_history_lock(mstb->mgr);
+
 	DRM_DEBUG("mstb %p (%d)\n",
 		  mstb, kref_read(&mstb->topology_kref) - 1);
-	kref_put(&mstb->topology_kref, drm_dp_destroy_mst_branch_device);
-}
+	save_mstb_topology_ref(mstb, DRM_DP_MST_TOPOLOGY_REF_PUT);
 
-static void drm_dp_port_teardown_pdt(struct drm_dp_mst_port *port, int old_pdt)
-{
-	struct drm_dp_mst_branch *mstb;
-
-	switch (old_pdt) {
-	case DP_PEER_DEVICE_DP_LEGACY_CONV:
-	case DP_PEER_DEVICE_SST_SINK:
-		/* remove i2c over sideband */
-		drm_dp_mst_unregister_i2c_bus(&port->aux);
-		break;
-	case DP_PEER_DEVICE_MST_BRANCHING:
-		mstb = port->mstb;
-		port->mstb = NULL;
-		drm_dp_mst_topology_put_mstb(mstb);
-		break;
-	}
+	topology_ref_history_unlock(mstb->mgr);
+	kref_put(&mstb->topology_kref, drm_dp_destroy_mst_branch_device);
 }
 
 static void drm_dp_destroy_port(struct kref *kref)
@@ -1527,31 +1693,24 @@ static void drm_dp_destroy_port(struct kref *kref)
 		container_of(kref, struct drm_dp_mst_port, topology_kref);
 	struct drm_dp_mst_topology_mgr *mgr = port->mgr;
 
-	if (!port->input) {
-		kfree(port->cached_edid);
+	drm_dp_mst_dump_port_topology_history(port);
 
-		/*
-		 * The only time we don't have a connector
-		 * on an output port is if the connector init
-		 * fails.
-		 */
-		if (port->connector) {
-			/* we can't destroy the connector here, as
-			 * we might be holding the mode_config.mutex
-			 * from an EDID retrieval */
-
-			mutex_lock(&mgr->destroy_connector_lock);
-			list_add(&port->next, &mgr->destroy_connector_list);
-			mutex_unlock(&mgr->destroy_connector_lock);
-			schedule_work(&mgr->destroy_connector_work);
-			return;
-		}
-		/* no need to clean up vcpi
-		 * as if we have no connector we never setup a vcpi */
-		drm_dp_port_teardown_pdt(port, port->pdt);
-		port->pdt = DP_PEER_DEVICE_NONE;
+	/* There's nothing that needs locking to destroy an input port yet */
+	if (port->input) {
+		drm_dp_mst_put_port_malloc(port);
+		return;
 	}
-	drm_dp_mst_put_port_malloc(port);
+
+	kfree(port->cached_edid);
+
+	/*
+	 * we can't destroy the connector here, as we might be holding the
+	 * mode_config.mutex from an EDID retrieval
+	 */
+	mutex_lock(&mgr->delayed_destroy_lock);
+	list_add(&port->next, &mgr->destroy_port_list);
+	mutex_unlock(&mgr->delayed_destroy_lock);
+	schedule_work(&mgr->delayed_destroy_work);
 }
 
 /**
@@ -1579,12 +1738,17 @@ static void drm_dp_destroy_port(struct kref *kref)
 static int __must_check
 drm_dp_mst_topology_try_get_port(struct drm_dp_mst_port *port)
 {
-	int ret = kref_get_unless_zero(&port->topology_kref);
+	int ret;
 
-	if (ret)
-		DRM_DEBUG("port %p (%d)\n", port,
-			  kref_read(&port->topology_kref));
+	topology_ref_history_lock(port->mgr);
+	ret = kref_get_unless_zero(&port->topology_kref);
+	if (ret) {
+		DRM_DEBUG("port %p (%d)\n",
+			  port, kref_read(&port->topology_kref));
+		save_port_topology_ref(port, DRM_DP_MST_TOPOLOGY_REF_GET);
+	}
 
+	topology_ref_history_unlock(port->mgr);
 	return ret;
 }
 
@@ -1603,9 +1767,14 @@ drm_dp_mst_topology_try_get_port(struct drm_dp_mst_port *port)
  */
 static void drm_dp_mst_topology_get_port(struct drm_dp_mst_port *port)
 {
+	topology_ref_history_lock(port->mgr);
+
 	WARN_ON(kref_read(&port->topology_kref) == 0);
 	kref_get(&port->topology_kref);
 	DRM_DEBUG("port %p (%d)\n", port, kref_read(&port->topology_kref));
+	save_port_topology_ref(port, DRM_DP_MST_TOPOLOGY_REF_GET);
+
+	topology_ref_history_unlock(port->mgr);
 }
 
 /**
@@ -1621,8 +1790,13 @@ static void drm_dp_mst_topology_get_port(struct drm_dp_mst_port *port)
  */
 static void drm_dp_mst_topology_put_port(struct drm_dp_mst_port *port)
 {
+	topology_ref_history_lock(port->mgr);
+
 	DRM_DEBUG("port %p (%d)\n",
 		  port, kref_read(&port->topology_kref) - 1);
+	save_port_topology_ref(port, DRM_DP_MST_TOPOLOGY_REF_PUT);
+
+	topology_ref_history_unlock(port->mgr);
 	kref_put(&port->topology_kref, drm_dp_destroy_port);
 }
 
@@ -1739,38 +1913,79 @@ static u8 drm_dp_calculate_rad(struct drm_dp_mst_port *port,
 	return parent_lct + 1;
 }
 
-/*
- * return sends link address for new mstb
- */
-static bool drm_dp_port_setup_pdt(struct drm_dp_mst_port *port)
+static int drm_dp_port_set_pdt(struct drm_dp_mst_port *port, u8 new_pdt)
 {
-	int ret;
-	u8 rad[6], lct;
-	bool send_link = false;
+	struct drm_dp_mst_topology_mgr *mgr = port->mgr;
+	struct drm_dp_mst_branch *mstb;
+	u8 rad[8], lct;
+	int ret = 0;
+
+	if (port->pdt == new_pdt)
+		return 0;
+
+	/* Teardown the old pdt, if there is one */
+	switch (port->pdt) {
+	case DP_PEER_DEVICE_DP_LEGACY_CONV:
+	case DP_PEER_DEVICE_SST_SINK:
+		/*
+		 * If the new PDT would also have an i2c bus, don't bother
+		 * with reregistering it
+		 */
+		if (new_pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
+		    new_pdt == DP_PEER_DEVICE_SST_SINK) {
+			port->pdt = new_pdt;
+			return 0;
+		}
+
+		/* remove i2c over sideband */
+		drm_dp_mst_unregister_i2c_bus(&port->aux);
+		break;
+	case DP_PEER_DEVICE_MST_BRANCHING:
+		mutex_lock(&mgr->lock);
+		drm_dp_mst_topology_put_mstb(port->mstb);
+		port->mstb = NULL;
+		mutex_unlock(&mgr->lock);
+		break;
+	}
+
+	port->pdt = new_pdt;
 	switch (port->pdt) {
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 	case DP_PEER_DEVICE_SST_SINK:
 		/* add i2c over sideband */
 		ret = drm_dp_mst_register_i2c_bus(&port->aux);
 		break;
+
 	case DP_PEER_DEVICE_MST_BRANCHING:
 		lct = drm_dp_calculate_rad(port, rad);
+		mstb = drm_dp_add_mst_branch_device(lct, rad);
+		if (!mstb) {
+			ret = -ENOMEM;
+			DRM_ERROR("Failed to create MSTB for port %p", port);
+			goto out;
+		}
 
-		port->mstb = drm_dp_add_mst_branch_device(lct, rad);
-		if (port->mstb) {
-			port->mstb->mgr = port->mgr;
-			port->mstb->port_parent = port;
-			/*
-			 * Make sure this port's memory allocation stays
-			 * around until its child MSTB releases it
-			 */
-			drm_dp_mst_get_port_malloc(port);
+		mutex_lock(&mgr->lock);
+		port->mstb = mstb;
+		mstb->mgr = port->mgr;
+		mstb->port_parent = port;
 
-			send_link = true;
-		}
+		/*
+		 * Make sure this port's memory allocation stays
+		 * around until its child MSTB releases it
+		 */
+		drm_dp_mst_get_port_malloc(port);
+		mutex_unlock(&mgr->lock);
+
+		/* And make sure we send a link address for this */
+		ret = 1;
 		break;
 	}
-	return send_link;
+
+out:
+	if (ret < 0)
+		port->pdt = DP_PEER_DEVICE_NONE;
+	return ret;
 }
 
 /**
@@ -1903,44 +2118,130 @@ void drm_dp_mst_connector_early_unregister(struct drm_connector *connector,
 EXPORT_SYMBOL(drm_dp_mst_connector_early_unregister);
 
 static void
+drm_dp_mst_port_add_connector(struct drm_dp_mst_branch *mstb,
+			      struct drm_dp_mst_port *port)
+{
+	struct drm_dp_mst_topology_mgr *mgr = port->mgr;
+	char proppath[255];
+	int ret;
+
+	build_mst_prop_path(mstb, port->port_num, proppath, sizeof(proppath));
+	port->connector = mgr->cbs->add_connector(mgr, port, proppath);
+	if (!port->connector) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
+	     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_connector_set_tile_property(port->connector);
+	}
+
+	mgr->cbs->register_connector(port->connector);
+	return;
+
+error:
+	DRM_ERROR("Failed to create connector for port %p: %d\n", port, ret);
+}
+
+/*
+ * Drop a topology reference, and unlink the port from the in-memory topology
+ * layout
+ */
+static void
+drm_dp_mst_topology_unlink_port(struct drm_dp_mst_topology_mgr *mgr,
+				struct drm_dp_mst_port *port)
+{
+	mutex_lock(&mgr->lock);
+	list_del(&port->next);
+	mutex_unlock(&mgr->lock);
+	drm_dp_mst_topology_put_port(port);
+}
+
+static struct drm_dp_mst_port *
+drm_dp_mst_add_port(struct drm_device *dev,
+		    struct drm_dp_mst_topology_mgr *mgr,
+		    struct drm_dp_mst_branch *mstb, u8 port_number)
+{
+	struct drm_dp_mst_port *port = kzalloc(sizeof(*port), GFP_KERNEL);
+
+	if (!port)
+		return NULL;
+
+	kref_init(&port->topology_kref);
+	kref_init(&port->malloc_kref);
+	port->parent = mstb;
+	port->port_num = port_number;
+	port->mgr = mgr;
+	port->aux.name = "DPMST";
+	port->aux.dev = dev->dev;
+	port->aux.is_remote = true;
+
+	/*
+	 * Make sure the memory allocation for our parent branch stays
+	 * around until our own memory allocation is released
+	 */
+	drm_dp_mst_get_mstb_malloc(mstb);
+
+	return port;
+}
+
+static int
 drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
 				    struct drm_device *dev,
 				    struct drm_dp_link_addr_reply_port *port_msg)
 {
+	struct drm_dp_mst_topology_mgr *mgr = mstb->mgr;
 	struct drm_dp_mst_port *port;
-	bool ret;
-	bool created = false;
-	int old_pdt = 0;
-	int old_ddps = 0;
+	int old_ddps = 0, ret;
+	u8 new_pdt = DP_PEER_DEVICE_NONE;
+	bool created = false, send_link_addr = false, changed = false;
 
 	port = drm_dp_get_port(mstb, port_msg->port_number);
 	if (!port) {
-		port = kzalloc(sizeof(*port), GFP_KERNEL);
+		port = drm_dp_mst_add_port(dev, mgr, mstb,
+					   port_msg->port_number);
 		if (!port)
-			return;
-		kref_init(&port->topology_kref);
-		kref_init(&port->malloc_kref);
-		port->parent = mstb;
-		port->port_num = port_msg->port_number;
-		port->mgr = mstb->mgr;
-		port->aux.name = "DPMST";
-		port->aux.dev = dev->dev;
-		port->aux.is_remote = true;
-
-		/*
-		 * Make sure the memory allocation for our parent branch stays
-		 * around until our own memory allocation is released
+			return -ENOMEM;
+		created = true;
+		changed = true;
+	} else if (!port->input && port_msg->input_port && port->connector) {
+		/* Since port->connector can't be changed here, we create a
+		 * new port if input_port changes from 0 to 1
 		 */
-		drm_dp_mst_get_mstb_malloc(mstb);
-
+		drm_dp_mst_topology_unlink_port(mgr, port);
+		drm_dp_mst_topology_put_port(port);
+		port = drm_dp_mst_add_port(dev, mgr, mstb,
+					   port_msg->port_number);
+		if (!port)
+			return -ENOMEM;
+		changed = true;
 		created = true;
-	} else {
-		old_pdt = port->pdt;
+	} else if (port->input && !port_msg->input_port) {
+		changed = true;
+	} else if (port->connector) {
+		/* We're updating a port that's exposed to userspace, so do it
+		 * under lock
+		 */
+		drm_modeset_lock(&mgr->base.lock, NULL);
+
 		old_ddps = port->ddps;
+		changed = port->ddps != port_msg->ddps ||
+			(port->ddps &&
+			 (port->ldps != port_msg->legacy_device_plug_status ||
+			  port->dpcd_rev != port_msg->dpcd_revision ||
+			  port->mcs != port_msg->mcs ||
+			  port->pdt != port_msg->peer_device_type ||
+			  port->num_sdp_stream_sinks !=
+			  port_msg->num_sdp_stream_sinks));
 	}
 
-	port->pdt = port_msg->peer_device_type;
 	port->input = port_msg->input_port;
+	if (!port->input)
+		new_pdt = port_msg->peer_device_type;
 	port->mcs = port_msg->mcs;
 	port->ddps = port_msg->ddps;
 	port->ldps = port_msg->legacy_device_plug_status;
@@ -1951,78 +2252,104 @@ drm_dp_mst_handle_link_address_port(struct drm_dp_mst_branch *mstb,
 	/* manage mstb port lists with mgr lock - take a reference
 	   for this list */
 	if (created) {
-		mutex_lock(&mstb->mgr->lock);
+		mutex_lock(&mgr->lock);
 		drm_dp_mst_topology_get_port(port);
 		list_add(&port->next, &mstb->ports);
-		mutex_unlock(&mstb->mgr->lock);
+		mutex_unlock(&mgr->lock);
 	}
 
 	if (old_ddps != port->ddps) {
 		if (port->ddps) {
 			if (!port->input) {
-				drm_dp_send_enum_path_resources(mstb->mgr,
-								mstb, port);
+				drm_dp_send_enum_path_resources(mgr, mstb,
+								port);
 			}
 		} else {
 			port->available_pbn = 0;
 		}
 	}
 
-	if (old_pdt != port->pdt && !port->input) {
-		drm_dp_port_teardown_pdt(port, old_pdt);
-
-		ret = drm_dp_port_setup_pdt(port);
-		if (ret == true)
-			drm_dp_send_link_address(mstb->mgr, port->mstb);
+	ret = drm_dp_port_set_pdt(port, new_pdt);
+	if (ret == 1) {
+		send_link_addr = true;
+	} else if (ret < 0) {
+		DRM_ERROR("Failed to change PDT on port %p: %d\n",
+			  port, ret);
+		goto fail;
 	}
 
-	if (created && !port->input) {
-		char proppath[255];
-
-		build_mst_prop_path(mstb, port->port_num, proppath,
-				    sizeof(proppath));
-		port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr,
-								   port,
-								   proppath);
-		if (!port->connector) {
-			/* remove it from the port list */
-			mutex_lock(&mstb->mgr->lock);
-			list_del(&port->next);
-			mutex_unlock(&mstb->mgr->lock);
-			/* drop port list reference */
-			drm_dp_mst_topology_put_port(port);
-			goto out;
-		}
-		if ((port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV ||
-		     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_connector_set_tile_property(port->connector);
-		}
-		(*mstb->mgr->cbs->register_connector)(port->connector);
+	/*
+	 * If this port wasn't just created, then we're reprobing because
+	 * we're coming out of suspend. In this case, always resend the link
+	 * address if there's an MSTB on this port
+	 */
+	if (!created && port->pdt == DP_PEER_DEVICE_MST_BRANCHING)
+		send_link_addr = true;
+
+	if (port->connector)
+		drm_modeset_unlock(&mgr->base.lock);
+	else if (!port->input)
+		drm_dp_mst_port_add_connector(mstb, port);
+
+	if (send_link_addr && port->mstb) {
+		ret = drm_dp_send_link_address(mgr, port->mstb);
+		if (ret == 1) /* MSTB below us changed */
+			changed = true;
+		else if (ret < 0)
+			goto fail_put;
 	}
 
-out:
 	/* put reference to this port */
 	drm_dp_mst_topology_put_port(port);
+	return changed;
+
+fail:
+	drm_dp_mst_topology_unlink_port(mgr, port);
+	if (port->connector)
+		drm_modeset_unlock(&mgr->base.lock);
+fail_put:
+	drm_dp_mst_topology_put_port(port);
+	return ret;
 }
 
 static void
 drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb,
 			    struct drm_dp_connection_status_notify *conn_stat)
 {
+	struct drm_dp_mst_topology_mgr *mgr = mstb->mgr;
 	struct drm_dp_mst_port *port;
-	int old_pdt;
-	int old_ddps;
-	bool dowork = false;
+	int old_ddps, ret;
+	u8 new_pdt;
+	bool dowork = false, create_connector = false;
+
 	port = drm_dp_get_port(mstb, conn_stat->port_number);
 	if (!port)
 		return;
 
+	if (port->connector) {
+		if (!port->input && conn_stat->input_port) {
+			/*
+			 * We can't remove a connector from an already exposed
+			 * port, so just throw the port out and make sure we
+			 * reprobe the link address of it's parent MSTB
+			 */
+			drm_dp_mst_topology_unlink_port(mgr, port);
+			mstb->link_address_sent = false;
+			dowork = true;
+			goto out;
+		}
+
+		/* Locking is only needed if the port's exposed to userspace */
+		drm_modeset_lock(&mgr->base.lock, NULL);
+	} else if (port->input && !conn_stat->input_port) {
+		create_connector = true;
+		/* Reprobe link address so we get num_sdp_streams */
+		mstb->link_address_sent = false;
+		dowork = true;
+	}
+
 	old_ddps = port->ddps;
-	old_pdt = port->pdt;
-	port->pdt = conn_stat->peer_device_type;
+	port->input = conn_stat->input_port;
 	port->mcs = conn_stat->message_capability_status;
 	port->ldps = conn_stat->legacy_device_plug_status;
 	port->ddps = conn_stat->displayport_device_plug_status;
@@ -2034,17 +2361,27 @@ drm_dp_mst_handle_conn_stat(struct drm_dp_mst_branch *mstb,
 			port->available_pbn = 0;
 		}
 	}
-	if (old_pdt != port->pdt && !port->input) {
-		drm_dp_port_teardown_pdt(port, old_pdt);
 
-		if (drm_dp_port_setup_pdt(port))
-			dowork = true;
+	new_pdt = port->input ? DP_PEER_DEVICE_NONE : conn_stat->peer_device_type;
+
+	ret = drm_dp_port_set_pdt(port, new_pdt);
+	if (ret == 1) {
+		dowork = true;
+	} else if (ret < 0) {
+		DRM_ERROR("Failed to change PDT for port %p: %d\n",
+			  port, ret);
+		dowork = false;
 	}
 
+	if (port->connector)
+		drm_modeset_unlock(&mgr->base.lock);
+	else if (create_connector)
+		drm_dp_mst_port_add_connector(mstb, port);
+
+out:
 	drm_dp_mst_topology_put_port(port);
 	if (dowork)
 		queue_work(system_long_wq, &mstb->mgr->work);
-
 }
 
 static struct drm_dp_mst_branch *drm_dp_get_mst_branch_device(struct drm_dp_mst_topology_mgr *mgr,
@@ -2130,41 +2467,62 @@ drm_dp_get_mst_branch_device_by_guid(struct drm_dp_mst_topology_mgr *mgr,
 	return mstb;
 }
 
-static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+static int drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 					       struct drm_dp_mst_branch *mstb)
 {
 	struct drm_dp_mst_port *port;
-	struct drm_dp_mst_branch *mstb_child;
-	if (!mstb->link_address_sent)
-		drm_dp_send_link_address(mgr, mstb);
+	int ret;
+	bool changed = false;
+
+	if (!mstb->link_address_sent) {
+		ret = drm_dp_send_link_address(mgr, mstb);
+		if (ret == 1)
+			changed = true;
+		else if (ret < 0)
+			return ret;
+	}
 
 	list_for_each_entry(port, &mstb->ports, next) {
-		if (port->input)
-			continue;
+		struct drm_dp_mst_branch *mstb_child = NULL;
 
-		if (!port->ddps)
+		if (port->input || !port->ddps)
 			continue;
 
-		if (!port->available_pbn)
+		if (!port->available_pbn) {
+			drm_modeset_lock(&mgr->base.lock, NULL);
 			drm_dp_send_enum_path_resources(mgr, mstb, port);
+			drm_modeset_unlock(&mgr->base.lock);
+			changed = true;
+		}
 
-		if (port->mstb) {
+		if (port->mstb)
 			mstb_child = drm_dp_mst_topology_get_mstb_validated(
 			    mgr, port->mstb);
-			if (mstb_child) {
-				drm_dp_check_and_send_link_address(mgr, mstb_child);
-				drm_dp_mst_topology_put_mstb(mstb_child);
-			}
+
+		if (mstb_child) {
+			ret = drm_dp_check_and_send_link_address(mgr,
+								 mstb_child);
+			drm_dp_mst_topology_put_mstb(mstb_child);
+			if (ret == 1)
+				changed = true;
+			else if (ret < 0)
+				return ret;
 		}
 	}
+
+	return changed;
 }
 
 static void drm_dp_mst_link_probe_work(struct work_struct *work)
 {
-	struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, work);
+	struct drm_dp_mst_topology_mgr *mgr =
+		container_of(work, struct drm_dp_mst_topology_mgr, work);
+	struct drm_device *dev = mgr->dev;
 	struct drm_dp_mst_branch *mstb;
 	int ret;
 
+	mutex_lock(&mgr->probe_lock);
+
 	mutex_lock(&mgr->lock);
 	mstb = mgr->mst_primary;
 	if (mstb) {
@@ -2173,10 +2531,17 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work)
 			mstb = NULL;
 	}
 	mutex_unlock(&mgr->lock);
-	if (mstb) {
-		drm_dp_check_and_send_link_address(mgr, mstb);
-		drm_dp_mst_topology_put_mstb(mstb);
+	if (!mstb) {
+		mutex_unlock(&mgr->probe_lock);
+		return;
 	}
+
+	ret = drm_dp_check_and_send_link_address(mgr, mstb);
+	drm_dp_mst_topology_put_mstb(mstb);
+
+	mutex_unlock(&mgr->probe_lock);
+	if (ret)
+		drm_kms_helper_hotplug_event(dev);
 }
 
 static bool drm_dp_validate_guid(struct drm_dp_mst_topology_mgr *mgr,
@@ -2422,16 +2787,18 @@ drm_dp_dump_link_address(struct drm_dp_link_address_ack_reply *reply)
 	}
 }
 
-static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 				     struct drm_dp_mst_branch *mstb)
 {
 	struct drm_dp_sideband_msg_tx *txmsg;
 	struct drm_dp_link_address_ack_reply *reply;
-	int i, len, ret;
+	struct drm_dp_mst_port *port, *tmp;
+	int i, len, ret, port_mask = 0;
+	bool changed = false;
 
 	txmsg = kzalloc(sizeof(*txmsg), GFP_KERNEL);
 	if (!txmsg)
-		return;
+		return -ENOMEM;
 
 	txmsg->dst = mstb;
 	len = build_link_address(txmsg);
@@ -2457,16 +2824,39 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
 
 	drm_dp_check_mstb_guid(mstb, reply->guid);
 
-	for (i = 0; i < reply->nports; i++)
-		drm_dp_mst_handle_link_address_port(mstb, mgr->dev,
-						    &reply->ports[i]);
+	for (i = 0; i < reply->nports; i++) {
+		port_mask |= BIT(reply->ports[i].port_number);
+		ret = drm_dp_mst_handle_link_address_port(mstb, mgr->dev,
+							  &reply->ports[i]);
+		if (ret == 1)
+			changed = true;
+		else if (ret < 0)
+			goto out;
+	}
 
-	drm_kms_helper_hotplug_event(mgr->dev);
+	/* Prune any ports that are currently a part of mstb in our in-memory
+	 * topology, but were not seen in this link address. Usually this
+	 * means that they were removed while the topology was out of sync,
+	 * e.g. during suspend/resume
+	 */
+	mutex_lock(&mgr->lock);
+	list_for_each_entry_safe(port, tmp, &mstb->ports, next) {
+		if (port_mask & BIT(port->port_num))
+			continue;
+
+		DRM_DEBUG_KMS("port %d was not in link address, removing\n",
+			      port->port_num);
+		list_del(&port->next);
+		drm_dp_mst_topology_put_port(port);
+		changed = true;
+	}
+	mutex_unlock(&mgr->lock);
 
 out:
 	if (ret <= 0)
 		mstb->link_address_sent = false;
 	kfree(txmsg);
+	return ret < 0 ? ret : changed;
 }
 
 static int
@@ -3071,6 +3461,23 @@ out_unlock:
 }
 EXPORT_SYMBOL(drm_dp_mst_topology_mgr_set_mst);
 
+static void
+drm_dp_mst_topology_mgr_invalidate_mstb(struct drm_dp_mst_branch *mstb)
+{
+	struct drm_dp_mst_port *port;
+
+	/* The link address will need to be re-sent on resume */
+	mstb->link_address_sent = false;
+
+	list_for_each_entry(port, &mstb->ports, next) {
+		/* The PBN for each port will also need to be re-probed */
+		port->available_pbn = 0;
+
+		if (port->mstb)
+			drm_dp_mst_topology_mgr_invalidate_mstb(port->mstb);
+	}
+}
+
 /**
  * drm_dp_mst_topology_mgr_suspend() - suspend the MST manager
  * @mgr: manager to suspend
@@ -3084,62 +3491,89 @@ void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr)
 	drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
 			   DP_MST_EN | DP_UPSTREAM_IS_SRC);
 	mutex_unlock(&mgr->lock);
+	flush_work(&mgr->up_req_work);
 	flush_work(&mgr->work);
-	flush_work(&mgr->destroy_connector_work);
+	flush_work(&mgr->delayed_destroy_work);
+
+	mutex_lock(&mgr->lock);
+	if (mgr->mst_state && mgr->mst_primary)
+		drm_dp_mst_topology_mgr_invalidate_mstb(mgr->mst_primary);
+	mutex_unlock(&mgr->lock);
 }
 EXPORT_SYMBOL(drm_dp_mst_topology_mgr_suspend);
 
 /**
  * drm_dp_mst_topology_mgr_resume() - resume the MST manager
  * @mgr: manager to resume
+ * @sync: whether or not to perform topology reprobing synchronously
  *
  * This will fetch DPCD and see if the device is still there,
  * if it is, it will rewrite the MSTM control bits, and return.
  *
- * if the device fails this returns -1, and the driver should do
+ * If the device fails this returns -1, and the driver should do
  * a full MST reprobe, in case we were undocked.
+ *
+ * During system resume (where it is assumed that the driver will be calling
+ * drm_atomic_helper_resume()) this function should be called beforehand with
+ * @sync set to true. In contexts like runtime resume where the driver is not
+ * expected to be calling drm_atomic_helper_resume(), this function should be
+ * called with @sync set to false in order to avoid deadlocking.
+ *
+ * Returns: -1 if the MST topology was removed while we were suspended, 0
+ * otherwise.
  */
-int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr)
+int drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr,
+				   bool sync)
 {
-	int ret = 0;
+	int ret;
+	u8 guid[16];
 
 	mutex_lock(&mgr->lock);
+	if (!mgr->mst_primary)
+		goto out_fail;
 
-	if (mgr->mst_primary) {
-		int sret;
-		u8 guid[16];
+	ret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd,
+			       DP_RECEIVER_CAP_SIZE);
+	if (ret != DP_RECEIVER_CAP_SIZE) {
+		DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
+		goto out_fail;
+	}
 
-		sret = drm_dp_dpcd_read(mgr->aux, DP_DPCD_REV, mgr->dpcd, DP_RECEIVER_CAP_SIZE);
-		if (sret != DP_RECEIVER_CAP_SIZE) {
-			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
-			ret = -1;
-			goto out_unlock;
-		}
+	ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
+				 DP_MST_EN |
+				 DP_UP_REQ_EN |
+				 DP_UPSTREAM_IS_SRC);
+	if (ret < 0) {
+		DRM_DEBUG_KMS("mst write failed - undocked during suspend?\n");
+		goto out_fail;
+	}
 
-		ret = drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
-					 DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC);
-		if (ret < 0) {
-			DRM_DEBUG_KMS("mst write failed - undocked during suspend?\n");
-			ret = -1;
-			goto out_unlock;
-		}
+	/* Some hubs forget their guids after they resume */
+	ret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
+	if (ret != 16) {
+		DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
+		goto out_fail;
+	}
+	drm_dp_check_mstb_guid(mgr->mst_primary, guid);
 
-		/* Some hubs forget their guids after they resume */
-		sret = drm_dp_dpcd_read(mgr->aux, DP_GUID, guid, 16);
-		if (sret != 16) {
-			DRM_DEBUG_KMS("dpcd read failed - undocked during suspend?\n");
-			ret = -1;
-			goto out_unlock;
-		}
-		drm_dp_check_mstb_guid(mgr->mst_primary, guid);
+	/*
+	 * For the final step of resuming the topology, we need to bring the
+	 * state of our in-memory topology back into sync with reality. So,
+	 * restart the probing process as if we're probing a new hub
+	 */
+	queue_work(system_long_wq, &mgr->work);
+	mutex_unlock(&mgr->lock);
 
-		ret = 0;
-	} else
-		ret = -1;
+	if (sync) {
+		DRM_DEBUG_KMS("Waiting for link probe work to finish re-syncing topology...\n");
+		flush_work(&mgr->work);
+	}
 
-out_unlock:
+	return 0;
+
+out_fail:
 	mutex_unlock(&mgr->lock);
-	return ret;
+	return -1;
 }
 EXPORT_SYMBOL(drm_dp_mst_topology_mgr_resume);
 
@@ -3256,12 +3690,78 @@ clear_down_rep_recv:
 	return 0;
 }
 
+static inline bool
+drm_dp_mst_process_up_req(struct drm_dp_mst_topology_mgr *mgr,
+			  struct drm_dp_pending_up_req *up_req)
+{
+	struct drm_dp_mst_branch *mstb = NULL;
+	struct drm_dp_sideband_msg_req_body *msg = &up_req->msg;
+	struct drm_dp_sideband_msg_hdr *hdr = &up_req->hdr;
+	bool hotplug = false;
+
+	if (hdr->broadcast) {
+		const u8 *guid = NULL;
+
+		if (msg->req_type == DP_CONNECTION_STATUS_NOTIFY)
+			guid = msg->u.conn_stat.guid;
+		else if (msg->req_type == DP_RESOURCE_STATUS_NOTIFY)
+			guid = msg->u.resource_stat.guid;
+
+		mstb = drm_dp_get_mst_branch_device_by_guid(mgr, guid);
+	} else {
+		mstb = drm_dp_get_mst_branch_device(mgr, hdr->lct, hdr->rad);
+	}
+
+	if (!mstb) {
+		DRM_DEBUG_KMS("Got MST reply from unknown device %d\n",
+			      hdr->lct);
+		return false;
+	}
+
+	/* TODO: Add missing handler for DP_RESOURCE_STATUS_NOTIFY events */
+	if (msg->req_type == DP_CONNECTION_STATUS_NOTIFY) {
+		drm_dp_mst_handle_conn_stat(mstb, &msg->u.conn_stat);
+		hotplug = true;
+	}
+
+	drm_dp_mst_topology_put_mstb(mstb);
+	return hotplug;
+}
+
+static void drm_dp_mst_up_req_work(struct work_struct *work)
+{
+	struct drm_dp_mst_topology_mgr *mgr =
+		container_of(work, struct drm_dp_mst_topology_mgr,
+			     up_req_work);
+	struct drm_dp_pending_up_req *up_req;
+	bool send_hotplug = false;
+
+	mutex_lock(&mgr->probe_lock);
+	while (true) {
+		mutex_lock(&mgr->up_req_lock);
+		up_req = list_first_entry_or_null(&mgr->up_req_list,
+						  struct drm_dp_pending_up_req,
+						  next);
+		if (up_req)
+			list_del(&up_req->next);
+		mutex_unlock(&mgr->up_req_lock);
+
+		if (!up_req)
+			break;
+
+		send_hotplug |= drm_dp_mst_process_up_req(mgr, up_req);
+		kfree(up_req);
+	}
+	mutex_unlock(&mgr->probe_lock);
+
+	if (send_hotplug)
+		drm_kms_helper_hotplug_event(mgr->dev);
+}
+
 static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 {
-	struct drm_dp_sideband_msg_req_body msg;
 	struct drm_dp_sideband_msg_hdr *hdr = &mgr->up_req_recv.initial_hdr;
-	struct drm_dp_mst_branch *mstb = NULL;
-	const u8 *guid;
+	struct drm_dp_pending_up_req *up_req;
 	bool seqno;
 
 	if (!drm_dp_get_one_sb_msg(mgr, true))
@@ -3270,56 +3770,53 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 	if (!mgr->up_req_recv.have_eomt)
 		return 0;
 
-	if (!hdr->broadcast) {
-		mstb = drm_dp_get_mst_branch_device(mgr, hdr->lct, hdr->rad);
-		if (!mstb) {
-			DRM_DEBUG_KMS("Got MST reply from unknown device %d\n",
-				      hdr->lct);
-			goto out;
-		}
+	up_req = kzalloc(sizeof(*up_req), GFP_KERNEL);
+	if (!up_req) {
+		DRM_ERROR("Not enough memory to process MST up req\n");
+		return -ENOMEM;
 	}
+	INIT_LIST_HEAD(&up_req->next);
 
 	seqno = hdr->seqno;
-	drm_dp_sideband_parse_req(&mgr->up_req_recv, &msg);
+	drm_dp_sideband_parse_req(&mgr->up_req_recv, &up_req->msg);
 
-	if (msg.req_type == DP_CONNECTION_STATUS_NOTIFY)
-		guid = msg.u.conn_stat.guid;
-	else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY)
-		guid = msg.u.resource_stat.guid;
-	else
+	if (up_req->msg.req_type != DP_CONNECTION_STATUS_NOTIFY &&
+	    up_req->msg.req_type != DP_RESOURCE_STATUS_NOTIFY) {
+		DRM_DEBUG_KMS("Received unknown up req type, ignoring: %x\n",
+			      up_req->msg.req_type);
+		kfree(up_req);
 		goto out;
-
-	drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno,
-				 false);
-
-	if (!mstb) {
-		mstb = drm_dp_get_mst_branch_device_by_guid(mgr, guid);
-		if (!mstb) {
-			DRM_DEBUG_KMS("Got MST reply from unknown device %d\n",
-				      hdr->lct);
-			goto out;
-		}
 	}
 
-	if (msg.req_type == DP_CONNECTION_STATUS_NOTIFY) {
-		drm_dp_mst_handle_conn_stat(mstb, &msg.u.conn_stat);
+	drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, up_req->msg.req_type,
+				 seqno, false);
+
+	if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) {
+		const struct drm_dp_connection_status_notify *conn_stat =
+			&up_req->msg.u.conn_stat;
 
 		DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n",
-			      msg.u.conn_stat.port_number,
-			      msg.u.conn_stat.legacy_device_plug_status,
-			      msg.u.conn_stat.displayport_device_plug_status,
-			      msg.u.conn_stat.message_capability_status,
-			      msg.u.conn_stat.input_port,
-			      msg.u.conn_stat.peer_device_type);
+			      conn_stat->port_number,
+			      conn_stat->legacy_device_plug_status,
+			      conn_stat->displayport_device_plug_status,
+			      conn_stat->message_capability_status,
+			      conn_stat->input_port,
+			      conn_stat->peer_device_type);
+	} else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
+		const struct drm_dp_resource_status_notify *res_stat =
+			&up_req->msg.u.resource_stat;
 
-		drm_kms_helper_hotplug_event(mgr->dev);
-	} else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
 		DRM_DEBUG_KMS("Got RSN: pn: %d avail_pbn %d\n",
-			      msg.u.resource_stat.port_number,
-			      msg.u.resource_stat.available_pbn);
+			      res_stat->port_number,
+			      res_stat->available_pbn);
 	}
 
-	drm_dp_mst_topology_put_mstb(mstb);
+	up_req->hdr = *hdr;
+	mutex_lock(&mgr->up_req_lock);
+	list_add_tail(&up_req->next, &mgr->up_req_list);
+	mutex_unlock(&mgr->up_req_lock);
+	queue_work(system_long_wq, &mgr->up_req_work);
+
 out:
 	memset(&mgr->up_req_recv, 0, sizeof(struct drm_dp_sideband_msg_rx));
 	return 0;
@@ -3366,22 +3863,31 @@ EXPORT_SYMBOL(drm_dp_mst_hpd_irq);
 /**
  * drm_dp_mst_detect_port() - get connection status for an MST port
  * @connector: DRM connector for this port
+ * @ctx: The acquisition context to use for grabbing locks
  * @mgr: manager for this port
- * @port: unverified pointer to a port
+ * @port: pointer to a port
  *
- * This returns the current connection state for a port. It validates the
- * port pointer still exists so the caller doesn't require a reference
+ * This returns the current connection state for a port.
  */
-enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector,
-						 struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port)
+int
+drm_dp_mst_detect_port(struct drm_connector *connector,
+		       struct drm_modeset_acquire_ctx *ctx,
+		       struct drm_dp_mst_topology_mgr *mgr,
+		       struct drm_dp_mst_port *port)
 {
-	enum drm_connector_status status = connector_status_disconnected;
+	int ret;
 
 	/* we need to search for the port in the mgr in case it's gone */
 	port = drm_dp_mst_topology_get_port_validated(mgr, port);
 	if (!port)
 		return connector_status_disconnected;
 
+	ret = drm_modeset_lock(&mgr->base.lock, ctx);
+	if (ret)
+		goto out;
+
+	ret = connector_status_disconnected;
+
 	if (!port->ddps)
 		goto out;
 
@@ -3391,7 +3897,7 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector
 		break;
 
 	case DP_PEER_DEVICE_SST_SINK:
-		status = connector_status_connected;
+		ret = connector_status_connected;
 		/* for logical ports - cache the EDID */
 		if (port->port_num >= 8 && !port->cached_edid) {
 			port->cached_edid = drm_get_edid(connector, &port->aux.ddc);
@@ -3399,12 +3905,12 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector
 		break;
 	case DP_PEER_DEVICE_DP_LEGACY_CONV:
 		if (port->ldps)
-			status = connector_status_connected;
+			ret = connector_status_connected;
 		break;
 	}
 out:
 	drm_dp_mst_topology_put_port(port);
-	return status;
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_mst_detect_port);
 
@@ -3994,34 +4500,103 @@ static void drm_dp_tx_work(struct work_struct *work)
 	mutex_unlock(&mgr->qlock);
 }
 
-static void drm_dp_destroy_connector_work(struct work_struct *work)
+static inline void
+drm_dp_delayed_destroy_port(struct drm_dp_mst_port *port)
 {
-	struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work);
-	struct drm_dp_mst_port *port;
-	bool send_hotplug = false;
+	if (port->connector)
+		port->mgr->cbs->destroy_connector(port->mgr, port->connector);
+
+	drm_dp_port_set_pdt(port, DP_PEER_DEVICE_NONE);
+	drm_dp_mst_put_port_malloc(port);
+}
+
+static inline void
+drm_dp_delayed_destroy_mstb(struct drm_dp_mst_branch *mstb)
+{
+	struct drm_dp_mst_topology_mgr *mgr = mstb->mgr;
+	struct drm_dp_mst_port *port, *tmp;
+	bool wake_tx = false;
+
+	mutex_lock(&mgr->lock);
+	list_for_each_entry_safe(port, tmp, &mstb->ports, next) {
+		list_del(&port->next);
+		drm_dp_mst_topology_put_port(port);
+	}
+	mutex_unlock(&mgr->lock);
+
+	/* drop any tx slots msg */
+	mutex_lock(&mstb->mgr->qlock);
+	if (mstb->tx_slots[0]) {
+		mstb->tx_slots[0]->state = DRM_DP_SIDEBAND_TX_TIMEOUT;
+		mstb->tx_slots[0] = NULL;
+		wake_tx = true;
+	}
+	if (mstb->tx_slots[1]) {
+		mstb->tx_slots[1]->state = DRM_DP_SIDEBAND_TX_TIMEOUT;
+		mstb->tx_slots[1] = NULL;
+		wake_tx = true;
+	}
+	mutex_unlock(&mstb->mgr->qlock);
+
+	if (wake_tx)
+		wake_up_all(&mstb->mgr->tx_waitq);
+
+	drm_dp_mst_put_mstb_malloc(mstb);
+}
+
+static void drm_dp_delayed_destroy_work(struct work_struct *work)
+{
+	struct drm_dp_mst_topology_mgr *mgr =
+		container_of(work, struct drm_dp_mst_topology_mgr,
+			     delayed_destroy_work);
+	bool send_hotplug = false, go_again;
+
 	/*
 	 * Not a regular list traverse as we have to drop the destroy
-	 * connector lock before destroying the connector, to avoid AB->BA
+	 * connector lock before destroying the mstb/port, to avoid AB->BA
 	 * ordering between this lock and the config mutex.
 	 */
-	for (;;) {
-		mutex_lock(&mgr->destroy_connector_lock);
-		port = list_first_entry_or_null(&mgr->destroy_connector_list, struct drm_dp_mst_port, next);
-		if (!port) {
-			mutex_unlock(&mgr->destroy_connector_lock);
-			break;
+	do {
+		go_again = false;
+
+		for (;;) {
+			struct drm_dp_mst_branch *mstb;
+
+			mutex_lock(&mgr->delayed_destroy_lock);
+			mstb = list_first_entry_or_null(&mgr->destroy_branch_device_list,
+							struct drm_dp_mst_branch,
+							destroy_next);
+			if (mstb)
+				list_del(&mstb->destroy_next);
+			mutex_unlock(&mgr->delayed_destroy_lock);
+
+			if (!mstb)
+				break;
+
+			drm_dp_delayed_destroy_mstb(mstb);
+			go_again = true;
 		}
-		list_del(&port->next);
-		mutex_unlock(&mgr->destroy_connector_lock);
 
-		mgr->cbs->destroy_connector(mgr, port->connector);
+		for (;;) {
+			struct drm_dp_mst_port *port;
 
-		drm_dp_port_teardown_pdt(port, port->pdt);
-		port->pdt = DP_PEER_DEVICE_NONE;
+			mutex_lock(&mgr->delayed_destroy_lock);
+			port = list_first_entry_or_null(&mgr->destroy_port_list,
+							struct drm_dp_mst_port,
+							next);
+			if (port)
+				list_del(&port->next);
+			mutex_unlock(&mgr->delayed_destroy_lock);
+
+			if (!port)
+				break;
+
+			drm_dp_delayed_destroy_port(port);
+			send_hotplug = true;
+			go_again = true;
+		}
+	} while (go_again);
 
-		drm_dp_mst_put_port_malloc(port);
-		send_hotplug = true;
-	}
 	if (send_hotplug)
 		drm_kms_helper_hotplug_event(mgr->dev);
 }
@@ -4208,12 +4783,20 @@ int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr,
 	mutex_init(&mgr->lock);
 	mutex_init(&mgr->qlock);
 	mutex_init(&mgr->payload_lock);
-	mutex_init(&mgr->destroy_connector_lock);
+	mutex_init(&mgr->delayed_destroy_lock);
+	mutex_init(&mgr->up_req_lock);
+	mutex_init(&mgr->probe_lock);
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	mutex_init(&mgr->topology_ref_history_lock);
+#endif
 	INIT_LIST_HEAD(&mgr->tx_msg_downq);
-	INIT_LIST_HEAD(&mgr->destroy_connector_list);
+	INIT_LIST_HEAD(&mgr->destroy_port_list);
+	INIT_LIST_HEAD(&mgr->destroy_branch_device_list);
+	INIT_LIST_HEAD(&mgr->up_req_list);
 	INIT_WORK(&mgr->work, drm_dp_mst_link_probe_work);
 	INIT_WORK(&mgr->tx_work, drm_dp_tx_work);
-	INIT_WORK(&mgr->destroy_connector_work, drm_dp_destroy_connector_work);
+	INIT_WORK(&mgr->delayed_destroy_work, drm_dp_delayed_destroy_work);
+	INIT_WORK(&mgr->up_req_work, drm_dp_mst_up_req_work);
 	init_waitqueue_head(&mgr->tx_waitq);
 	mgr->dev = dev;
 	mgr->aux = aux;
@@ -4254,7 +4837,7 @@ void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr)
 {
 	drm_dp_mst_topology_mgr_set_mst(mgr, false);
 	flush_work(&mgr->work);
-	flush_work(&mgr->destroy_connector_work);
+	cancel_work_sync(&mgr->delayed_destroy_work);
 	mutex_lock(&mgr->payload_lock);
 	kfree(mgr->payloads);
 	mgr->payloads = NULL;
@@ -4266,10 +4849,15 @@ void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr)
 	drm_atomic_private_obj_fini(&mgr->base);
 	mgr->funcs = NULL;
 
-	mutex_destroy(&mgr->destroy_connector_lock);
+	mutex_destroy(&mgr->delayed_destroy_lock);
 	mutex_destroy(&mgr->payload_lock);
 	mutex_destroy(&mgr->qlock);
 	mutex_destroy(&mgr->lock);
+	mutex_destroy(&mgr->up_req_lock);
+	mutex_destroy(&mgr->probe_lock);
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	mutex_destroy(&mgr->topology_ref_history_lock);
+#endif
 }
 EXPORT_SYMBOL(drm_dp_mst_topology_mgr_destroy);
 
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index b75ae8555baf..8ebeccdeed23 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -92,9 +92,12 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  *
  * 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().
+ * It will automatically set up deferred I/O if the driver requires a shadow
+ * buffer.
  *
- * Setup fbdev emulation by calling drm_fb_helper_fbdev_setup() and tear it
- * down by calling drm_fb_helper_fbdev_teardown().
+ * For other drivers, setup fbdev emulation by calling
+ * drm_fb_helper_fbdev_setup() and tear it down by calling
+ * drm_fb_helper_fbdev_teardown().
  *
  * At runtime drivers should restore the fbdev console by using
  * drm_fb_helper_lastclose() as their &drm_driver.lastclose callback.
@@ -127,8 +130,10 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  * always run in process context since the fb_*() function could be running in
  * atomic context. If drm_fb_helper_deferred_io() is used as the deferred_io
  * callback it will also schedule dirty_work with the damage collected from the
- * mmap page writes. Drivers can use drm_fb_helper_defio_init() to setup
- * deferred I/O (coupled with drm_fb_helper_fbdev_teardown()).
+ * mmap page writes.
+ *
+ * Deferred I/O is not compatible with SHMEM. Such drivers should request an
+ * fbdev shadow buffer and call drm_fbdev_generic_setup() instead.
  */
 
 static void drm_fb_helper_restore_lut_atomic(struct drm_crtc *crtc)
@@ -680,49 +685,6 @@ void drm_fb_helper_deferred_io(struct fb_info *info,
 EXPORT_SYMBOL(drm_fb_helper_deferred_io);
 
 /**
- * drm_fb_helper_defio_init - fbdev deferred I/O initialization
- * @fb_helper: driver-allocated fbdev helper
- *
- * This function allocates &fb_deferred_io, sets callback to
- * drm_fb_helper_deferred_io(), delay to 50ms and calls fb_deferred_io_init().
- * It should be called from the &drm_fb_helper_funcs->fb_probe callback.
- * drm_fb_helper_fbdev_teardown() cleans up deferred I/O.
- *
- * NOTE: A copy of &fb_ops is made and assigned to &info->fbops. This is done
- * because fb_deferred_io_cleanup() clears &fbops->fb_mmap and would thereby
- * affect other instances of that &fb_ops.
- *
- * Returns:
- * 0 on success or a negative error code on failure.
- */
-int drm_fb_helper_defio_init(struct drm_fb_helper *fb_helper)
-{
-	struct fb_info *info = fb_helper->fbdev;
-	struct fb_deferred_io *fbdefio;
-	struct fb_ops *fbops;
-
-	fbdefio = kzalloc(sizeof(*fbdefio), GFP_KERNEL);
-	fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
-	if (!fbdefio || !fbops) {
-		kfree(fbdefio);
-		kfree(fbops);
-		return -ENOMEM;
-	}
-
-	info->fbdefio = fbdefio;
-	fbdefio->delay = msecs_to_jiffies(50);
-	fbdefio->deferred_io = drm_fb_helper_deferred_io;
-
-	*fbops = *info->fbops;
-	info->fbops = fbops;
-
-	fb_deferred_io_init(info);
-
-	return 0;
-}
-EXPORT_SYMBOL(drm_fb_helper_defio_init);
-
-/**
  * drm_fb_helper_sys_read - wrapper around fb_sys_read
  * @info: fb_info struct pointer
  * @buf: userspace buffer to read from framebuffer memory
@@ -2356,7 +2318,10 @@ static const struct drm_client_funcs drm_fbdev_client_funcs = {
  *
  * 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.
+ * make deferred I/O work with all kinds of buffers. A shadow buffer can be
+ * requested explicitly by setting struct drm_mode_config.prefer_shadow or
+ * struct drm_mode_config.prefer_shadow_fbdev to true beforehand. This is
+ * required to use generic fbdev emulation with SHMEM helpers.
  *
  * This function is safe to call even when there are no connectors present.
  * Setup will be retried on the next hotplug event.
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 56f42e0f2584..000fa4a1899f 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1105,18 +1105,33 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
 	if (obj_size < vma->vm_end - vma->vm_start)
 		return -EINVAL;
 
+	/* Take a ref for this mapping of the object, so that the fault
+	 * handler can dereference the mmap offset's pointer to the object.
+	 * This reference is cleaned up by the corresponding vm_close
+	 * (which should happen whether the vma was created by this call, or
+	 * by a vm_open due to mremap or partial unmap or whatever).
+	 */
+	drm_gem_object_get(obj);
+
 	if (obj->funcs && obj->funcs->mmap) {
+		/* Remove the fake offset */
+		vma->vm_pgoff -= drm_vma_node_start(&obj->vma_node);
+
 		ret = obj->funcs->mmap(obj, vma);
-		if (ret)
+		if (ret) {
+			drm_gem_object_put_unlocked(obj);
 			return ret;
+		}
 		WARN_ON(!(vma->vm_flags & VM_DONTEXPAND));
 	} else {
 		if (obj->funcs && obj->funcs->vm_ops)
 			vma->vm_ops = obj->funcs->vm_ops;
 		else if (dev->driver->gem_vm_ops)
 			vma->vm_ops = dev->driver->gem_vm_ops;
-		else
+		else {
+			drm_gem_object_put_unlocked(obj);
 			return -EINVAL;
+		}
 
 		vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
 		vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
@@ -1125,14 +1140,6 @@ int drm_gem_mmap_obj(struct drm_gem_object *obj, unsigned long obj_size,
 
 	vma->vm_private_data = obj;
 
-	/* Take a ref for this mapping of the object, so that the fault
-	 * handler can dereference the mmap offset's pointer to the object.
-	 * This reference is cleaned up by the corresponding vm_close
-	 * (which should happen whether the vma was created by this call, or
-	 * by a vm_open due to mremap or partial unmap or whatever).
-	 */
-	drm_gem_object_get(obj);
-
 	return 0;
 }
 EXPORT_SYMBOL(drm_gem_mmap_obj);
diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c
index 3bc69b1ffa7d..0810d3ef6961 100644
--- a/drivers/gpu/drm/drm_gem_shmem_helper.c
+++ b/drivers/gpu/drm/drm_gem_shmem_helper.c
@@ -541,9 +541,6 @@ int drm_gem_shmem_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
 	vma->vm_ops = &drm_gem_shmem_vm_ops;
 
-	/* Remove the fake offset */
-	vma->vm_pgoff -= drm_vma_node_start(&shmem->base.vma_node);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(drm_gem_shmem_mmap);
diff --git a/drivers/gpu/drm/drm_gem_ttm_helper.c b/drivers/gpu/drm/drm_gem_ttm_helper.c
index 7412bfc5c05a..605a8a3da7f9 100644
--- a/drivers/gpu/drm/drm_gem_ttm_helper.c
+++ b/drivers/gpu/drm/drm_gem_ttm_helper.c
@@ -64,8 +64,19 @@ int drm_gem_ttm_mmap(struct drm_gem_object *gem,
 		     struct vm_area_struct *vma)
 {
 	struct ttm_buffer_object *bo = drm_gem_ttm_of_gem(gem);
+	int ret;
 
-	return ttm_bo_mmap_obj(vma, bo);
+	ret = ttm_bo_mmap_obj(vma, bo);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * ttm has its own object refcounting, so drop gem reference
+	 * to avoid double accounting counting.
+	 */
+	drm_gem_object_put_unlocked(gem);
+
+	return 0;
 }
 EXPORT_SYMBOL(drm_gem_ttm_mmap);
 
diff --git a/drivers/gpu/drm/drm_gem_vram_helper.c b/drivers/gpu/drm/drm_gem_vram_helper.c
index b86fe0fa9d05..666cb4c22bb9 100644
--- a/drivers/gpu/drm/drm_gem_vram_helper.c
+++ b/drivers/gpu/drm/drm_gem_vram_helper.c
@@ -3,10 +3,13 @@
 #include <drm/drm_debugfs.h>
 #include <drm/drm_device.h>
 #include <drm/drm_file.h>
+#include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_ttm_helper.h>
 #include <drm/drm_gem_vram_helper.h>
 #include <drm/drm_mode.h>
+#include <drm/drm_plane.h>
 #include <drm/drm_prime.h>
+#include <drm/drm_simple_kms_helper.h>
 #include <drm/ttm/ttm_page_alloc.h>
 
 static const struct drm_gem_object_funcs drm_gem_vram_object_funcs;
@@ -647,6 +650,129 @@ int drm_gem_vram_driver_dumb_mmap_offset(struct drm_file *file,
 EXPORT_SYMBOL(drm_gem_vram_driver_dumb_mmap_offset);
 
 /*
+ * Helpers for struct drm_plane_helper_funcs
+ */
+
+/**
+ * drm_gem_vram_plane_helper_prepare_fb() - \
+ *	Implements &struct drm_plane_helper_funcs.prepare_fb
+ * @plane:	a DRM plane
+ * @new_state:	the plane's new state
+ *
+ * During plane updates, this function pins the GEM VRAM
+ * objects of the plane's new framebuffer to VRAM. Call
+ * drm_gem_vram_plane_helper_cleanup_fb() to unpin them.
+ *
+ * Returns:
+ *	0 on success, or
+ *	a negative errno code otherwise.
+ */
+int
+drm_gem_vram_plane_helper_prepare_fb(struct drm_plane *plane,
+				     struct drm_plane_state *new_state)
+{
+	size_t i;
+	struct drm_gem_vram_object *gbo;
+	int ret;
+
+	if (!new_state->fb)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(new_state->fb->obj); ++i) {
+		if (!new_state->fb->obj[i])
+			continue;
+		gbo = drm_gem_vram_of_gem(new_state->fb->obj[i]);
+		ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
+		if (ret)
+			goto err_drm_gem_vram_unpin;
+	}
+
+	return 0;
+
+err_drm_gem_vram_unpin:
+	while (i) {
+		--i;
+		gbo = drm_gem_vram_of_gem(new_state->fb->obj[i]);
+		drm_gem_vram_unpin(gbo);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(drm_gem_vram_plane_helper_prepare_fb);
+
+/**
+ * drm_gem_vram_plane_helper_cleanup_fb() - \
+ *	Implements &struct drm_plane_helper_funcs.cleanup_fb
+ * @plane:	a DRM plane
+ * @old_state:	the plane's old state
+ *
+ * During plane updates, this function unpins the GEM VRAM
+ * objects of the plane's old framebuffer from VRAM. Complements
+ * drm_gem_vram_plane_helper_prepare_fb().
+ */
+void
+drm_gem_vram_plane_helper_cleanup_fb(struct drm_plane *plane,
+				     struct drm_plane_state *old_state)
+{
+	size_t i;
+	struct drm_gem_vram_object *gbo;
+
+	if (!old_state->fb)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(old_state->fb->obj); ++i) {
+		if (!old_state->fb->obj[i])
+			continue;
+		gbo = drm_gem_vram_of_gem(old_state->fb->obj[i]);
+		drm_gem_vram_unpin(gbo);
+	}
+}
+EXPORT_SYMBOL(drm_gem_vram_plane_helper_cleanup_fb);
+
+/*
+ * Helpers for struct drm_simple_display_pipe_funcs
+ */
+
+/**
+ * drm_gem_vram_simple_display_pipe_prepare_fb() - \
+ *	Implements &struct drm_simple_display_pipe_funcs.prepare_fb
+ * @pipe:	a simple display pipe
+ * @new_state:	the plane's new state
+ *
+ * During plane updates, this function pins the GEM VRAM
+ * objects of the plane's new framebuffer to VRAM. Call
+ * drm_gem_vram_simple_display_pipe_cleanup_fb() to unpin them.
+ *
+ * Returns:
+ *	0 on success, or
+ *	a negative errno code otherwise.
+ */
+int drm_gem_vram_simple_display_pipe_prepare_fb(
+	struct drm_simple_display_pipe *pipe,
+	struct drm_plane_state *new_state)
+{
+	return drm_gem_vram_plane_helper_prepare_fb(&pipe->plane, new_state);
+}
+EXPORT_SYMBOL(drm_gem_vram_simple_display_pipe_prepare_fb);
+
+/**
+ * drm_gem_vram_simple_display_pipe_cleanup_fb() - \
+ *	Implements &struct drm_simple_display_pipe_funcs.cleanup_fb
+ * @pipe:	a simple display pipe
+ * @old_state:	the plane's old state
+ *
+ * During plane updates, this function unpins the GEM VRAM
+ * objects of the plane's old framebuffer from VRAM. Complements
+ * drm_gem_vram_simple_display_pipe_prepare_fb().
+ */
+void drm_gem_vram_simple_display_pipe_cleanup_fb(
+	struct drm_simple_display_pipe *pipe,
+	struct drm_plane_state *old_state)
+{
+	drm_gem_vram_plane_helper_cleanup_fb(&pipe->plane, old_state);
+}
+EXPORT_SYMBOL(drm_gem_vram_simple_display_pipe_cleanup_fb);
+
+/*
  * PRIME helpers
  */
 
@@ -887,12 +1013,11 @@ static int drm_vram_mm_debugfs(struct seq_file *m, void *data)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_vram_mm *vmm = node->minor->dev->vram_mm;
 	struct drm_mm *mm = vmm->bdev.man[TTM_PL_VRAM].priv;
-	struct ttm_bo_global *glob = vmm->bdev.glob;
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 	drm_mm_print(mm, &p);
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/drm_self_refresh_helper.c b/drivers/gpu/drm/drm_self_refresh_helper.c
index 68f4765a5896..dd33fec5aabd 100644
--- a/drivers/gpu/drm/drm_self_refresh_helper.c
+++ b/drivers/gpu/drm/drm_self_refresh_helper.c
@@ -133,29 +133,33 @@ out_drop_locks:
  * drm_self_refresh_helper_update_avg_times - Updates a crtc's SR time averages
  * @state: the state which has just been applied to hardware
  * @commit_time_ms: the amount of time in ms that this commit took to complete
+ * @new_self_refresh_mask: bitmask of crtc's that have self_refresh_active in
+ *    new state
  *
  * Called after &drm_mode_config_funcs.atomic_commit_tail, this function will
  * update the average entry/exit self refresh times on self refresh transitions.
  * These averages will be used when calculating how long to delay before
  * entering self refresh mode after activity.
  */
-void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
-					      unsigned int commit_time_ms)
+void
+drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
+					 unsigned int commit_time_ms,
+					 unsigned int new_self_refresh_mask)
 {
 	struct drm_crtc *crtc;
-	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_crtc_state *old_crtc_state;
 	int i;
 
-	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
-				      new_crtc_state, i) {
+	for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
+		bool new_self_refresh_active = new_self_refresh_mask & BIT(i);
 		struct drm_self_refresh_data *sr_data = crtc->self_refresh_data;
 		struct ewma_psr_time *time;
 
 		if (old_crtc_state->self_refresh_active ==
-		    new_crtc_state->self_refresh_active)
+		    new_self_refresh_active)
 			continue;
 
-		if (new_crtc_state->self_refresh_active)
+		if (new_self_refresh_active)
 			time = &sr_data->entry_avg_ms;
 		else
 			time = &sr_data->exit_avg_ms;
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 046055719245..15fb516ae2d8 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -43,7 +43,7 @@ drm_simple_kms_crtc_mode_valid(struct drm_crtc *crtc,
 		/* Anything goes */
 		return MODE_OK;
 
-	return pipe->funcs->mode_valid(crtc, mode);
+	return pipe->funcs->mode_valid(pipe, mode);
 }
 
 static int drm_simple_kms_crtc_check(struct drm_crtc *crtc,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_dump.c b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
index 698db540972c..648cf0207309 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_dump.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_dump.c
@@ -180,6 +180,8 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
 			      etnaviv_cmdbuf_get_va(&submit->cmdbuf,
 					&gpu->mmu_context->cmdbuf_mapping));
 
+	mutex_unlock(&gpu->mmu_context->lock);
+
 	/* Reserve space for the bomap */
 	if (n_bomap_pages) {
 		bomap_start = bomap = iter.data;
@@ -221,8 +223,6 @@ void etnaviv_core_dump(struct etnaviv_gem_submit *submit)
 					 obj->base.size);
 	}
 
-	mutex_unlock(&gpu->mmu_context->lock);
-
 	etnaviv_core_dump_header(&iter, ETDUMP_BUF_END, iter.data);
 
 	dev_coredumpv(gpu->dev, iter.start, iter.data - iter.start, GFP_KERNEL);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 043111a1d60c..f8bf488e9d71 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -155,9 +155,11 @@ static void etnaviv_iommuv2_dump(struct etnaviv_iommu_context *context, void *bu
 
 	memcpy(buf, v2_context->mtlb_cpu, SZ_4K);
 	buf += SZ_4K;
-	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++, buf += SZ_4K)
-		if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT)
+	for (i = 0; i < MMUv2_MAX_STLB_ENTRIES; i++)
+		if (v2_context->mtlb_cpu[i] & MMUv2_PTE_PRESENT) {
 			memcpy(buf, v2_context->stlb_cpu[i], SZ_4K);
+			buf += SZ_4K;
+		}
 }
 
 static void etnaviv_iommuv2_restore_nonsec(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
index 35ebae6a1be7..3607d348c298 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_mmu.c
@@ -328,12 +328,23 @@ etnaviv_iommu_context_init(struct etnaviv_iommu_global *global,
 
 	ret = etnaviv_cmdbuf_suballoc_map(suballoc, ctx, &ctx->cmdbuf_mapping,
 					  global->memory_base);
-	if (ret) {
-		global->ops->free(ctx);
-		return NULL;
+	if (ret)
+		goto out_free;
+
+	if (global->version == ETNAVIV_IOMMU_V1 &&
+	    ctx->cmdbuf_mapping.iova > 0x80000000) {
+		dev_err(global->dev,
+		        "command buffer outside valid memory window\n");
+		goto out_unmap;
 	}
 
 	return ctx;
+
+out_unmap:
+	etnaviv_cmdbuf_suballoc_unmap(ctx, &ctx->cmdbuf_mapping);
+out_free:
+	global->ops->free(ctx);
+	return NULL;
 }
 
 void etnaviv_iommu_restore(struct etnaviv_gpu *gpu,
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 7b24338fad3c..6cfdb95fef2f 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -1069,9 +1069,9 @@ static bool mixer_mode_fixup(struct exynos_drm_crtc *crtc,
 	struct mixer_context *ctx = crtc->ctx;
 	int width = mode->hdisplay, height = mode->vdisplay, i;
 
-	struct {
+	static const struct {
 		int hdisplay, vdisplay, htotal, vtotal, scan_val;
-	} static const modes[] = {
+	} modes[] = {
 		{ 720, 480, 858, 525, MXR_CFG_SCAN_NTSC | MXR_CFG_SCAN_SD },
 		{ 720, 576, 864, 625, MXR_CFG_SCAN_PAL | MXR_CFG_SCAN_SD },
 		{ 1280, 720, 1650, 750, MXR_CFG_SCAN_HD_720 | MXR_CFG_SCAN_HD },
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_output.c b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
index 03023fa0fb6f..f350ac1ead18 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_output.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_output.c
@@ -498,7 +498,7 @@ void mdfld_dsi_output_init(struct drm_device *dev,
 		return;
 	}
 
-	/*create a new connetor*/
+	/*create a new connector*/
 	dsi_connector = kzalloc(sizeof(struct mdfld_dsi_connector), GFP_KERNEL);
 	if (!dsi_connector) {
 		DRM_ERROR("No memory");
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
index cc4c41748cfb..6527a97f68a3 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_de.c
@@ -96,7 +96,6 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
 {
 	struct drm_plane_state	*state	= plane->state;
 	u32 reg;
-	int ret;
 	s64 gpu_addr = 0;
 	unsigned int line_l;
 	struct hibmc_drm_private *priv = plane->dev->dev_private;
@@ -109,16 +108,9 @@ static void hibmc_plane_atomic_update(struct drm_plane *plane,
 	hibmc_fb = to_hibmc_framebuffer(state->fb);
 	gbo = drm_gem_vram_of_gem(hibmc_fb->obj);
 
-	ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-	if (ret) {
-		DRM_ERROR("failed to pin bo: %d", ret);
-		return;
-	}
 	gpu_addr = drm_gem_vram_offset(gbo);
-	if (gpu_addr < 0) {
-		drm_gem_vram_unpin(gbo);
-		return;
-	}
+	if (WARN_ON_ONCE(gpu_addr < 0))
+		return; /* Bug: we didn't pin the BO to VRAM in prepare_fb. */
 
 	writel(gpu_addr, priv->mmio + HIBMC_CRT_FB_ADDRESS);
 
@@ -157,6 +149,8 @@ static struct drm_plane_funcs hibmc_plane_funcs = {
 };
 
 static const struct drm_plane_helper_funcs hibmc_plane_helper_funcs = {
+	.prepare_fb	= drm_gem_vram_plane_helper_prepare_fb,
+	.cleanup_fb	= drm_gem_vram_plane_helper_cleanup_fb,
 	.atomic_check = hibmc_plane_atomic_check,
 	.atomic_update = hibmc_plane_atomic_update,
 };
diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index 3c6d57df262d..ba9595960bbe 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -148,3 +148,9 @@ menu "drm/i915 Profile Guided Optimisation"
 	depends on DRM_I915
 	source "drivers/gpu/drm/i915/Kconfig.profile"
 endmenu
+
+menu "drm/i915 Unstable Evolution"
+	visible if EXPERT && STAGING && BROKEN
+	depends on DRM_I915
+	source "drivers/gpu/drm/i915/Kconfig.unstable"
+endmenu
diff --git a/drivers/gpu/drm/i915/Kconfig.profile b/drivers/gpu/drm/i915/Kconfig.profile
index 48df8889a88a..c280b6ae38eb 100644
--- a/drivers/gpu/drm/i915/Kconfig.profile
+++ b/drivers/gpu/drm/i915/Kconfig.profile
@@ -12,6 +12,29 @@ config DRM_I915_USERFAULT_AUTOSUSPEND
 	  May be 0 to disable the extra delay and solely use the device level
 	  runtime pm autosuspend delay tunable.
 
+config DRM_I915_HEARTBEAT_INTERVAL
+	int "Interval between heartbeat pulses (ms)"
+	default 2500 # milliseconds
+	help
+	  The driver sends a periodic heartbeat down all active engines to
+	  check the health of the GPU and undertake regular house-keeping of
+	  internal driver state.
+
+	  May be 0 to disable heartbeats and therefore disable automatic GPU
+	  hang detection.
+
+config DRM_I915_PREEMPT_TIMEOUT
+	int "Preempt timeout (ms, jiffy granularity)"
+	default 640 # milliseconds
+	help
+	  How long to wait (in milliseconds) for a preemption event to occur
+	  when submitting a new context via execlists. If the current context
+	  does not hit an arbitration point and yield to HW before the timer
+	  expires, the HW will be reset to allow the more important context
+	  to execute.
+
+	  May be 0 to disable the timeout.
+
 config DRM_I915_SPIN_REQUEST
 	int "Busywait for request completion (us)"
 	default 5 # microseconds
@@ -25,3 +48,29 @@ config DRM_I915_SPIN_REQUEST
 	  May be 0 to disable the initial spin. In practice, we estimate
 	  the cost of enabling the interrupt (if currently disabled) to be
 	  a few microseconds.
+
+config DRM_I915_STOP_TIMEOUT
+	int "How long to wait for an engine to quiesce gracefully before reset (ms)"
+	default 100 # milliseconds
+	help
+	  By stopping submission and sleeping for a short time before resetting
+	  the GPU, we allow the innocent contexts also on the system to quiesce.
+	  It is then less likely for a hanging context to cause collateral
+	  damage as the system is reset in order to recover. The corollary is
+	  that the reset itself may take longer and so be more disruptive to
+	  interactive or low latency workloads.
+
+config DRM_I915_TIMESLICE_DURATION
+	int "Scheduling quantum for userspace batches (ms, jiffy granularity)"
+	default 1 # milliseconds
+	help
+	  When two user batches of equal priority are executing, we will
+	  alternate execution of each batch to ensure forward progress of
+	  all users. This is necessary in some cases where there may be
+	  an implicit dependency between those batches that requires
+	  concurrent execution in order for them to proceed, e.g. they
+	  interact with each other via userspace semaphores. Each context
+	  is scheduled for execution for the timeslice duration, before
+	  switching to the next context.
+
+	  May be 0 to disable timeslicing.
diff --git a/drivers/gpu/drm/i915/Kconfig.unstable b/drivers/gpu/drm/i915/Kconfig.unstable
new file mode 100644
index 000000000000..0c2276155c2b
--- /dev/null
+++ b/drivers/gpu/drm/i915/Kconfig.unstable
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config DRM_I915_UNSTABLE
+	bool "Enable unstable API for early prototype development"
+	depends on EXPERT
+	depends on STAGING
+	depends on BROKEN # should never be enabled by distros!
+	# We use the dependency on !COMPILE_TEST to not be enabled in
+	# allmodconfig or allyesconfig configurations
+	depends on !COMPILE_TEST
+	default n
+	help
+	  Enable prototype uAPI under general discussion before they are
+	  finalized. Such prototypes may be withdrawn or substantially
+	  changed before release. They are only enabled here so that a wide
+	  number of interested parties (userspace driver developers) can
+	  verify that the uAPI meet their expectations. These uAPI should
+	  never be used in production.
+
+	  Recommended for driver developers _only_.
+
+	  If in the slightest bit of doubt, say "N".
+
+config DRM_I915_UNSTABLE_FAKE_LMEM
+	bool "Enable the experimental fake lmem"
+	depends on DRM_I915_UNSTABLE
+	default n
+	help
+	  Convert some system memory into a fake local memory region for
+	  testing.
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index a16a2daef977..90dcf09f52cc 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -78,22 +78,24 @@ gt-y += \
 	gt/intel_breadcrumbs.o \
 	gt/intel_context.o \
 	gt/intel_engine_cs.o \
-	gt/intel_engine_pool.o \
+	gt/intel_engine_heartbeat.o \
 	gt/intel_engine_pm.o \
+	gt/intel_engine_pool.o \
 	gt/intel_engine_user.o \
 	gt/intel_gt.o \
 	gt/intel_gt_irq.o \
 	gt/intel_gt_pm.o \
 	gt/intel_gt_pm_irq.o \
 	gt/intel_gt_requests.o \
-	gt/intel_hangcheck.o \
 	gt/intel_llc.o \
 	gt/intel_lrc.o \
+	gt/intel_mocs.o \
 	gt/intel_rc6.o \
 	gt/intel_renderstate.o \
 	gt/intel_reset.o \
-	gt/intel_ringbuffer.o \
-	gt/intel_mocs.o \
+	gt/intel_ring.o \
+	gt/intel_ring_submission.o \
+	gt/intel_rps.o \
 	gt/intel_sseu.o \
 	gt/intel_timeline.o \
 	gt/intel_workarounds.o
@@ -119,6 +121,7 @@ gem-y += \
 	gem/i915_gem_internal.o \
 	gem/i915_gem_object.o \
 	gem/i915_gem_object_blt.o \
+	gem/i915_gem_lmem.o \
 	gem/i915_gem_mman.o \
 	gem/i915_gem_pages.o \
 	gem/i915_gem_phys.o \
@@ -147,6 +150,7 @@ i915-y += \
 	  i915_scheduler.o \
 	  i915_trace_points.o \
 	  i915_vma.o \
+	  intel_region_lmem.o \
 	  intel_wopcm.o
 
 # general-purpose microcontroller (GuC) support
@@ -243,7 +247,8 @@ i915-y += \
 	oa/i915_oa_cflgt2.o \
 	oa/i915_oa_cflgt3.o \
 	oa/i915_oa_cnl.o \
-	oa/i915_oa_icl.o
+	oa/i915_oa_icl.o \
+	oa/i915_oa_tgl.o
 i915-y += i915_perf.o
 
 # Post-mortem debug and GPU hang state capture
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index 6e398c33a524..325df29b0447 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1584,7 +1584,7 @@ void icl_dsi_init(struct drm_i915_private *dev_priv)
 	encoder->get_hw_state = gen11_dsi_get_hw_state;
 	encoder->type = INTEL_OUTPUT_DSI;
 	encoder->cloneable = 0;
-	encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+	encoder->pipe_mask = ~0;
 	encoder->power_domain = POWER_DOMAIN_PORT_DSI;
 	encoder->get_power_domains = gen11_dsi_get_power_domains;
 
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.c b/drivers/gpu/drm/i915/display/intel_atomic.c
index c5a552a69752..c2875b10adf9 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic.c
@@ -200,6 +200,7 @@ intel_crtc_duplicate_state(struct drm_crtc *crtc)
 	crtc_state->update_wm_pre = false;
 	crtc_state->update_wm_post = false;
 	crtc_state->fifo_changed = false;
+	crtc_state->preload_luts = false;
 	crtc_state->wm.need_postvbl_update = false;
 	crtc_state->fb_bits = 0;
 	crtc_state->update_planes = 0;
@@ -429,6 +430,13 @@ void intel_atomic_state_clear(struct drm_atomic_state *s)
 	struct intel_atomic_state *state = to_intel_atomic_state(s);
 	drm_atomic_state_default_clear(&state->base);
 	state->dpll_set = state->modeset = false;
+	state->global_state_changed = false;
+	state->active_pipes = 0;
+	memset(&state->min_cdclk, 0, sizeof(state->min_cdclk));
+	memset(&state->min_voltage_level, 0, sizeof(state->min_voltage_level));
+	memset(&state->cdclk.logical, 0, sizeof(state->cdclk.logical));
+	memset(&state->cdclk.actual, 0, sizeof(state->cdclk.actual));
+	state->cdclk.pipe = INVALID_PIPE;
 }
 
 struct intel_crtc_state *
@@ -442,3 +450,40 @@ intel_atomic_get_crtc_state(struct drm_atomic_state *state,
 
 	return to_intel_crtc_state(crtc_state);
 }
+
+int intel_atomic_lock_global_state(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+
+	state->global_state_changed = true;
+
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		int ret;
+
+		ret = drm_modeset_lock(&crtc->base.mutex,
+				       state->base.acquire_ctx);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int intel_atomic_serialize_global_state(struct intel_atomic_state *state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc *crtc;
+
+	state->global_state_changed = true;
+
+	for_each_intel_crtc(&dev_priv->drm, crtc) {
+		struct intel_crtc_state *crtc_state;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/display/intel_atomic.h b/drivers/gpu/drm/i915/display/intel_atomic.h
index 58065d3161a3..49d5cb1b9e0a 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic.h
@@ -16,6 +16,7 @@ struct drm_crtc_state;
 struct drm_device;
 struct drm_i915_private;
 struct drm_property;
+struct intel_atomic_state;
 struct intel_crtc;
 struct intel_crtc_state;
 
@@ -46,4 +47,8 @@ int intel_atomic_setup_scalers(struct drm_i915_private *dev_priv,
 			       struct intel_crtc *intel_crtc,
 			       struct intel_crtc_state *crtc_state);
 
+int intel_atomic_lock_global_state(struct intel_atomic_state *state);
+
+int intel_atomic_serialize_global_state(struct intel_atomic_state *state);
+
 #endif /* __INTEL_ATOMIC_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.c b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
index a6cff5a160fb..98f557a9f8ee 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.c
@@ -138,6 +138,44 @@ unsigned int intel_plane_data_rate(const struct intel_crtc_state *crtc_state,
 	return cpp * crtc_state->pixel_rate;
 }
 
+bool intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
+				struct intel_plane *plane)
+{
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	const struct intel_plane_state *plane_state =
+		intel_atomic_get_new_plane_state(state, plane);
+	struct intel_crtc *crtc = to_intel_crtc(plane_state->base.crtc);
+	struct intel_crtc_state *crtc_state;
+
+	if (!plane_state->base.visible || !plane->min_cdclk)
+		return false;
+
+	crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
+
+	crtc_state->min_cdclk[plane->id] =
+		plane->min_cdclk(crtc_state, plane_state);
+
+	/*
+	 * Does the cdclk need to be bumbed up?
+	 *
+	 * Note: we obviously need to be called before the new
+	 * cdclk frequency is calculated so state->cdclk.logical
+	 * hasn't been populated yet. Hence we look at the old
+	 * cdclk state under dev_priv->cdclk.logical. This is
+	 * safe as long we hold at least one crtc mutex (which
+	 * must be true since we have crtc_state).
+	 */
+	if (crtc_state->min_cdclk[plane->id] > dev_priv->cdclk.logical.cdclk) {
+		DRM_DEBUG_KMS("[PLANE:%d:%s] min_cdclk (%d kHz) > logical cdclk (%d kHz)\n",
+			      plane->base.base.id, plane->base.name,
+			      crtc_state->min_cdclk[plane->id],
+			      dev_priv->cdclk.logical.cdclk);
+		return true;
+	}
+
+	return false;
+}
+
 int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_state,
 					struct intel_crtc_state *new_crtc_state,
 					const struct intel_plane_state *old_plane_state,
@@ -151,6 +189,7 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 	new_crtc_state->nv12_planes &= ~BIT(plane->id);
 	new_crtc_state->c8_planes &= ~BIT(plane->id);
 	new_crtc_state->data_rate[plane->id] = 0;
+	new_crtc_state->min_cdclk[plane->id] = 0;
 	new_plane_state->base.visible = false;
 
 	if (!new_plane_state->base.crtc && !old_plane_state->base.crtc)
diff --git a/drivers/gpu/drm/i915/display/intel_atomic_plane.h b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
index dc85af02e9b7..e61e9a82aadf 100644
--- a/drivers/gpu/drm/i915/display/intel_atomic_plane.h
+++ b/drivers/gpu/drm/i915/display/intel_atomic_plane.h
@@ -47,5 +47,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 				    struct intel_crtc_state *crtc_state,
 				    const struct intel_plane_state *old_plane_state,
 				    struct intel_plane_state *plane_state);
+bool intel_plane_calc_min_cdclk(struct intel_atomic_state *state,
+				struct intel_plane *plane);
 
 #endif /* __INTEL_ATOMIC_PLANE_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_audio.c b/drivers/gpu/drm/i915/display/intel_audio.c
index ed18511befa3..85e6b2bbb34f 100644
--- a/drivers/gpu/drm/i915/display/intel_audio.c
+++ b/drivers/gpu/drm/i915/display/intel_audio.c
@@ -28,6 +28,7 @@
 #include <drm/i915_component.h>
 
 #include "i915_drv.h"
+#include "intel_atomic.h"
 #include "intel_audio.h"
 #include "intel_display_types.h"
 #include "intel_lpe_audio.h"
@@ -818,13 +819,8 @@ retry:
 	to_intel_atomic_state(state)->cdclk.force_min_cdclk =
 		enable ? 2 * 96000 : 0;
 
-	/*
-	 * Protects dev_priv->cdclk.force_min_cdclk
-	 * Need to lock this here in case we have no active pipes
-	 * and thus wouldn't lock it during the commit otherwise.
-	 */
-	ret = drm_modeset_lock(&dev_priv->drm.mode_config.connection_mutex,
-			       &ctx);
+	/* Protects dev_priv->cdclk.force_min_cdclk */
+	ret = intel_atomic_lock_global_state(to_intel_atomic_state(state));
 	if (!ret)
 		ret = drm_atomic_commit(state);
 
diff --git a/drivers/gpu/drm/i915/display/intel_cdclk.c b/drivers/gpu/drm/i915/display/intel_cdclk.c
index 3d867963a6d1..ed8c7ce62119 100644
--- a/drivers/gpu/drm/i915/display/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/display/intel_cdclk.c
@@ -1273,7 +1273,9 @@ static u8 icl_calc_voltage_level(int cdclk)
 
 static u8 ehl_calc_voltage_level(int cdclk)
 {
-	if (cdclk > 312000)
+	if (cdclk > 326400)
+		return 3;
+	else if (cdclk > 312000)
 		return 2;
 	else if (cdclk > 180000)
 		return 1;
@@ -1918,6 +1920,19 @@ static int intel_pixel_rate_to_cdclk(const struct intel_crtc_state *crtc_state)
 		return DIV_ROUND_UP(pixel_rate * 100, 90);
 }
 
+static int intel_planes_min_cdclk(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	struct intel_plane *plane;
+	int min_cdclk = 0;
+
+	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane)
+		min_cdclk = max(crtc_state->min_cdclk[plane->id], min_cdclk);
+
+	return min_cdclk;
+}
+
 int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv =
@@ -1986,6 +2001,9 @@ int intel_crtc_compute_min_cdclk(const struct intel_crtc_state *crtc_state)
 	    IS_GEMINILAKE(dev_priv))
 		min_cdclk = max(158400, min_cdclk);
 
+	/* Account for additional needs from the planes */
+	min_cdclk = max(intel_planes_min_cdclk(crtc_state), min_cdclk);
+
 	if (min_cdclk > dev_priv->max_cdclk_freq) {
 		DRM_DEBUG_KMS("required cdclk (%d kHz) exceeds max (%d kHz)\n",
 			      min_cdclk, dev_priv->max_cdclk_freq);
@@ -2007,11 +2025,20 @@ static int intel_compute_min_cdclk(struct intel_atomic_state *state)
 	       sizeof(state->min_cdclk));
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
+		int ret;
+
 		min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
 		if (min_cdclk < 0)
 			return min_cdclk;
 
+		if (state->min_cdclk[i] == min_cdclk)
+			continue;
+
 		state->min_cdclk[i] = min_cdclk;
+
+		ret = intel_atomic_lock_global_state(state);
+		if (ret)
+			return ret;
 	}
 
 	min_cdclk = state->cdclk.force_min_cdclk;
@@ -2034,7 +2061,7 @@ static int intel_compute_min_cdclk(struct intel_atomic_state *state)
  * future platforms this code will need to be
  * adjusted.
  */
-static u8 bxt_compute_min_voltage_level(struct intel_atomic_state *state)
+static int bxt_compute_min_voltage_level(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
 	struct intel_crtc *crtc;
@@ -2047,11 +2074,21 @@ static u8 bxt_compute_min_voltage_level(struct intel_atomic_state *state)
 	       sizeof(state->min_voltage_level));
 
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
+		int ret;
+
 		if (crtc_state->base.enable)
-			state->min_voltage_level[i] =
-				crtc_state->min_voltage_level;
+			min_voltage_level = crtc_state->min_voltage_level;
 		else
-			state->min_voltage_level[i] = 0;
+			min_voltage_level = 0;
+
+		if (state->min_voltage_level[i] == min_voltage_level)
+			continue;
+
+		state->min_voltage_level[i] = min_voltage_level;
+
+		ret = intel_atomic_lock_global_state(state);
+		if (ret)
+			return ret;
 	}
 
 	min_voltage_level = 0;
@@ -2195,20 +2232,24 @@ static int skl_modeset_calc_cdclk(struct intel_atomic_state *state)
 static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	int min_cdclk, cdclk, vco;
+	int min_cdclk, min_voltage_level, cdclk, vco;
 
 	min_cdclk = intel_compute_min_cdclk(state);
 	if (min_cdclk < 0)
 		return min_cdclk;
 
+	min_voltage_level = bxt_compute_min_voltage_level(state);
+	if (min_voltage_level < 0)
+		return min_voltage_level;
+
 	cdclk = bxt_calc_cdclk(dev_priv, min_cdclk);
 	vco = bxt_calc_cdclk_pll_vco(dev_priv, cdclk);
 
 	state->cdclk.logical.vco = vco;
 	state->cdclk.logical.cdclk = cdclk;
 	state->cdclk.logical.voltage_level =
-		max(dev_priv->display.calc_voltage_level(cdclk),
-		    bxt_compute_min_voltage_level(state));
+		max_t(int, min_voltage_level,
+		      dev_priv->display.calc_voltage_level(cdclk));
 
 	if (!state->active_pipes) {
 		cdclk = bxt_calc_cdclk(dev_priv, state->cdclk.force_min_cdclk);
@@ -2225,23 +2266,6 @@ static int bxt_modeset_calc_cdclk(struct intel_atomic_state *state)
 	return 0;
 }
 
-static int intel_lock_all_pipes(struct intel_atomic_state *state)
-{
-	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
-	struct intel_crtc *crtc;
-
-	/* Add all pipes to the state */
-	for_each_intel_crtc(&dev_priv->drm, crtc) {
-		struct intel_crtc_state *crtc_state;
-
-		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
-		if (IS_ERR(crtc_state))
-			return PTR_ERR(crtc_state);
-	}
-
-	return 0;
-}
-
 static int intel_modeset_all_pipes(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
@@ -2308,48 +2332,63 @@ int intel_modeset_calc_cdclk(struct intel_atomic_state *state)
 		return ret;
 
 	/*
-	 * Writes to dev_priv->cdclk.logical must protected by
-	 * holding all the crtc locks, even if we don't end up
+	 * Writes to dev_priv->cdclk.{actual,logical} must protected
+	 * by holding all the crtc mutexes even if we don't end up
 	 * touching the hardware
 	 */
-	if (intel_cdclk_changed(&dev_priv->cdclk.logical,
-				&state->cdclk.logical)) {
-		ret = intel_lock_all_pipes(state);
-		if (ret < 0)
+	if (intel_cdclk_changed(&dev_priv->cdclk.actual,
+				&state->cdclk.actual)) {
+		/*
+		 * Also serialize commits across all crtcs
+		 * if the actual hw needs to be poked.
+		 */
+		ret = intel_atomic_serialize_global_state(state);
+		if (ret)
+			return ret;
+	} else if (intel_cdclk_changed(&dev_priv->cdclk.logical,
+				       &state->cdclk.logical)) {
+		ret = intel_atomic_lock_global_state(state);
+		if (ret)
 			return ret;
+	} else {
+		return 0;
 	}
 
-	if (is_power_of_2(state->active_pipes)) {
+	if (is_power_of_2(state->active_pipes) &&
+	    intel_cdclk_needs_cd2x_update(dev_priv,
+					  &dev_priv->cdclk.actual,
+					  &state->cdclk.actual)) {
 		struct intel_crtc *crtc;
 		struct intel_crtc_state *crtc_state;
 
 		pipe = ilog2(state->active_pipes);
 		crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-		crtc_state = intel_atomic_get_new_crtc_state(state, crtc);
-		if (crtc_state &&
-		    drm_atomic_crtc_needs_modeset(&crtc_state->base))
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+
+		if (drm_atomic_crtc_needs_modeset(&crtc_state->base))
 			pipe = INVALID_PIPE;
 	} else {
 		pipe = INVALID_PIPE;
 	}
 
-	/* All pipes must be switched off while we change the cdclk. */
-	if (pipe != INVALID_PIPE &&
-	    intel_cdclk_needs_cd2x_update(dev_priv,
-					  &dev_priv->cdclk.actual,
-					  &state->cdclk.actual)) {
-		ret = intel_lock_all_pipes(state);
-		if (ret)
-			return ret;
-
+	if (pipe != INVALID_PIPE) {
 		state->cdclk.pipe = pipe;
+
+		DRM_DEBUG_KMS("Can change cdclk with pipe %c active\n",
+			      pipe_name(pipe));
 	} else if (intel_cdclk_needs_modeset(&dev_priv->cdclk.actual,
 					     &state->cdclk.actual)) {
+		/* All pipes must be switched off while we change the cdclk. */
 		ret = intel_modeset_all_pipes(state);
 		if (ret)
 			return ret;
 
 		state->cdclk.pipe = INVALID_PIPE;
+
+		DRM_DEBUG_KMS("Modeset required for cdclk change\n");
 	}
 
 	DRM_DEBUG_KMS("New cdclk calculated to be logical %u kHz, actual %u kHz\n",
diff --git a/drivers/gpu/drm/i915/display/intel_color.c b/drivers/gpu/drm/i915/display/intel_color.c
index fa44eb73d088..aa3a063549c3 100644
--- a/drivers/gpu/drm/i915/display/intel_color.c
+++ b/drivers/gpu/drm/i915/display/intel_color.c
@@ -1022,6 +1022,55 @@ void intel_color_commit(const struct intel_crtc_state *crtc_state)
 	dev_priv->display.color_commit(crtc_state);
 }
 
+static bool intel_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(new_crtc_state->base.state);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	return !old_crtc_state->base.gamma_lut &&
+		!old_crtc_state->base.degamma_lut;
+}
+
+static bool chv_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(new_crtc_state->base.state);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	/*
+	 * CGM_PIPE_MODE is itself single buffered. We'd have to
+	 * somehow split it out from chv_load_luts() if we wanted
+	 * the ability to preload the CGM LUTs/CSC without tearing.
+	 */
+	if (old_crtc_state->cgm_mode || new_crtc_state->cgm_mode)
+		return false;
+
+	return !old_crtc_state->base.gamma_lut;
+}
+
+static bool glk_can_preload_luts(const struct intel_crtc_state *new_crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(new_crtc_state->base.state);
+	const struct intel_crtc_state *old_crtc_state =
+		intel_atomic_get_old_crtc_state(state, crtc);
+
+	/*
+	 * The hardware degamma is active whenever the pipe
+	 * CSC is active. Thus even if the old state has no
+	 * software degamma we need to avoid clobbering the
+	 * linear hardware degamma mid scanout.
+	 */
+	return !old_crtc_state->csc_enable &&
+		!old_crtc_state->base.gamma_lut;
+}
+
 int intel_color_check(struct intel_crtc_state *crtc_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev);
@@ -1165,6 +1214,8 @@ static int i9xx_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1217,6 +1268,8 @@ static int chv_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = chv_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1271,6 +1324,8 @@ static int ilk_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1328,6 +1383,8 @@ static int ivb_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1366,6 +1423,8 @@ static int glk_color_check(struct intel_crtc_state *crtc_state)
 	if (ret)
 		return ret;
 
+	crtc_state->preload_luts = glk_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
@@ -1415,6 +1474,8 @@ static int icl_color_check(struct intel_crtc_state *crtc_state)
 
 	crtc_state->csc_mode = icl_csc_mode(crtc_state);
 
+	crtc_state->preload_luts = intel_can_preload_luts(crtc_state);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c
index ff6126ea793c..39cc6d79dc85 100644
--- a/drivers/gpu/drm/i915/display/intel_crt.c
+++ b/drivers/gpu/drm/i915/display/intel_crt.c
@@ -844,7 +844,7 @@ load_detect:
 	}
 
 	/* for pre-945g platforms use load detect */
-	ret = intel_get_load_detect_pipe(connector, NULL, &tmp, ctx);
+	ret = intel_get_load_detect_pipe(connector, &tmp, ctx);
 	if (ret > 0) {
 		if (intel_crt_detect_ddc(connector))
 			status = connector_status_connected;
@@ -864,6 +864,13 @@ load_detect:
 
 out:
 	intel_display_power_put(dev_priv, intel_encoder->power_domain, wakeref);
+
+	/*
+	 * Make sure the refs for power wells enabled during detect are
+	 * dropped to avoid a new detect cycle triggered by HPD polling.
+	 */
+	intel_display_power_flush_work(dev_priv);
+
 	return status;
 }
 
@@ -994,9 +1001,9 @@ void intel_crt_init(struct drm_i915_private *dev_priv)
 	crt->base.type = INTEL_OUTPUT_ANALOG;
 	crt->base.cloneable = (1 << INTEL_OUTPUT_DVO) | (1 << INTEL_OUTPUT_HDMI);
 	if (IS_I830(dev_priv))
-		crt->base.crtc_mask = BIT(PIPE_A);
+		crt->base.pipe_mask = BIT(PIPE_A);
 	else
-		crt->base.crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+		crt->base.pipe_mask = ~0;
 
 	if (IS_GEN(dev_priv, 2))
 		connector->interlace_allowed = 0;
diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 9ba794cb9b4f..c7c2b349858d 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -593,7 +593,7 @@ struct tgl_dkl_phy_ddi_buf_trans {
 	u32 dkl_de_emphasis_control;
 };
 
-static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_ddi_translations[] = {
+static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_dp_ddi_trans[] = {
 				/* VS	pre-emp	Non-trans mV	Pre-emph dB */
 	{ 0x7, 0x0, 0x00 },	/* 0	0	400mV		0 dB */
 	{ 0x5, 0x0, 0x03 },	/* 0	1	400mV		3.5 dB */
@@ -607,6 +607,20 @@ static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_ddi_translations[] = {
 	{ 0x0, 0x0, 0x00 },	/* 3	0	1200mV		0 dB HDMI default */
 };
 
+static const struct tgl_dkl_phy_ddi_buf_trans tgl_dkl_phy_hdmi_ddi_trans[] = {
+				/* HDMI Preset	VS	Pre-emph */
+	{ 0x7, 0x0, 0x0 },	/* 1		400mV	0dB */
+	{ 0x6, 0x0, 0x0 },	/* 2		500mV	0dB */
+	{ 0x4, 0x0, 0x0 },	/* 3		650mV	0dB */
+	{ 0x2, 0x0, 0x0 },	/* 4		800mV	0dB */
+	{ 0x0, 0x0, 0x0 },	/* 5		1000mV	0dB */
+	{ 0x0, 0x0, 0x5 },	/* 6		Full	-1.5 dB */
+	{ 0x0, 0x0, 0x6 },	/* 7		Full	-1.8 dB */
+	{ 0x0, 0x0, 0x7 },	/* 8		Full	-2 dB */
+	{ 0x0, 0x0, 0x8 },	/* 9		Full	-2.5 dB */
+	{ 0x0, 0x0, 0xA },	/* 10		Full	-3 dB */
+};
+
 static const struct ddi_buf_trans *
 bdw_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries)
 {
@@ -898,7 +912,7 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 			icl_get_combo_buf_trans(dev_priv, INTEL_OUTPUT_HDMI,
 						0, &n_entries);
 		else
-			n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+			n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
 		default_entry = n_entries - 1;
 	} else if (INTEL_GEN(dev_priv) == 11) {
 		if (intel_phy_is_combo(dev_priv, phy))
@@ -1794,10 +1808,8 @@ void intel_ddi_set_dp_msa(const struct intel_crtc_state *crtc_state,
 	 * of Color Encoding Format and Content Color Gamut] while sending
 	 * YCBCR 420, HDR BT.2020 signals we should program MSA MISC1 fields
 	 * which indicate VSC SDP for the Pixel Encoding/Colorimetry Format.
-	 *
-	 * FIXME MST doesn't pass in the conn_state
 	 */
-	if (conn_state && intel_dp_needs_vsc_sdp(crtc_state, conn_state))
+	if (intel_dp_needs_vsc_sdp(crtc_state, conn_state))
 		temp |= DP_MSA_MISC_COLOR_VSC_SDP;
 
 	I915_WRITE(TRANS_MSA_MISC(cpu_transcoder), temp);
@@ -1905,6 +1917,9 @@ intel_ddi_transcoder_func_reg_val_get(const struct intel_crtc_state *crtc_state)
 	} else if (intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)) {
 		temp |= TRANS_DDI_MODE_SELECT_DP_MST;
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
+
+		if (INTEL_GEN(dev_priv) >= 12)
+			temp |= TRANS_DDI_MST_TRANSPORT_SELECT(crtc_state->cpu_transcoder);
 	} else {
 		temp |= TRANS_DDI_MODE_SELECT_DP_SST;
 		temp |= DDI_PORT_WIDTH(crtc_state->lane_count);
@@ -2234,7 +2249,7 @@ static void intel_ddi_get_power_domains(struct intel_encoder *encoder,
 	/*
 	 * VDSC power is needed when DSC is enabled
 	 */
-	if (crtc_state->dsc_params.compression_enable)
+	if (crtc_state->dsc.compression_enable)
 		intel_display_power_get(dev_priv,
 					intel_dsc_power_domain(crtc_state));
 }
@@ -2370,7 +2385,7 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 			icl_get_combo_buf_trans(dev_priv, encoder->type,
 						intel_dp->link_rate, &n_entries);
 		else
-			n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
+			n_entries = ARRAY_SIZE(tgl_dkl_phy_dp_ddi_trans);
 	} else if (INTEL_GEN(dev_priv) == 11) {
 		if (intel_phy_is_combo(dev_priv, phy))
 			icl_get_combo_buf_trans(dev_priv, encoder->type,
@@ -2822,8 +2837,13 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock,
 	const struct tgl_dkl_phy_ddi_buf_trans *ddi_translations;
 	u32 n_entries, val, ln, dpcnt_mask, dpcnt_val;
 
-	n_entries = ARRAY_SIZE(tgl_dkl_phy_ddi_translations);
-	ddi_translations = tgl_dkl_phy_ddi_translations;
+	if (encoder->type == INTEL_OUTPUT_HDMI) {
+		n_entries = ARRAY_SIZE(tgl_dkl_phy_hdmi_ddi_trans);
+		ddi_translations = tgl_dkl_phy_hdmi_ddi_trans;
+	} else {
+		n_entries = ARRAY_SIZE(tgl_dkl_phy_dp_ddi_trans);
+		ddi_translations = tgl_dkl_phy_dp_ddi_trans;
+	}
 
 	if (level >= n_entries)
 		level = n_entries - 1;
@@ -2838,6 +2858,8 @@ tgl_dkl_phy_ddi_vswing_sequence(struct intel_encoder *encoder, int link_clock,
 	for (ln = 0; ln < 2; ln++) {
 		I915_WRITE(HIP_INDEX_REG(tc_port), HIP_INDEX_VAL(tc_port, ln));
 
+		I915_WRITE(DKL_TX_PMD_LANE_SUS(tc_port), 0);
+
 		/* All the registers are RMW */
 		val = I915_READ(DKL_TX_DPCNTL0(tc_port));
 		val &= ~dpcnt_mask;
@@ -3600,7 +3622,11 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	else
 		hsw_ddi_pre_enable_dp(encoder, crtc_state, conn_state);
 
-	intel_ddi_set_dp_msa(crtc_state, conn_state);
+	/* MST will call a setting of MSA after an allocating of Virtual Channel
+	 * from MST encoder pre_enable callback.
+	 */
+	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
+		intel_ddi_set_dp_msa(crtc_state, conn_state);
 }
 
 static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
@@ -3870,12 +3896,12 @@ static i915_reg_t
 gen9_chicken_trans_reg_by_port(struct drm_i915_private *dev_priv,
 			       enum port port)
 {
-	static const i915_reg_t regs[] = {
-		[PORT_A] = CHICKEN_TRANS_EDP,
-		[PORT_B] = CHICKEN_TRANS_A,
-		[PORT_C] = CHICKEN_TRANS_B,
-		[PORT_D] = CHICKEN_TRANS_C,
-		[PORT_E] = CHICKEN_TRANS_A,
+	static const enum transcoder trans[] = {
+		[PORT_A] = TRANSCODER_EDP,
+		[PORT_B] = TRANSCODER_A,
+		[PORT_C] = TRANSCODER_B,
+		[PORT_D] = TRANSCODER_C,
+		[PORT_E] = TRANSCODER_A,
 	};
 
 	WARN_ON(INTEL_GEN(dev_priv) < 9);
@@ -3883,7 +3909,7 @@ gen9_chicken_trans_reg_by_port(struct drm_i915_private *dev_priv,
 	if (WARN_ON(port < PORT_A || port > PORT_E))
 		port = PORT_A;
 
-	return regs[port];
+	return CHICKEN_TRANS(trans[port]);
 }
 
 static void intel_enable_ddi_hdmi(struct intel_encoder *encoder,
@@ -4683,7 +4709,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	struct intel_encoder *intel_encoder;
 	struct drm_encoder *encoder;
 	bool init_hdmi, init_dp, init_lspcon = false;
-	enum pipe pipe;
 	enum phy phy = intel_port_to_phy(dev_priv, port);
 
 	init_hdmi = port_info->supports_dvi || port_info->supports_hdmi;
@@ -4735,8 +4760,7 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 	intel_encoder->power_domain = intel_port_to_power_domain(port);
 	intel_encoder->port = port;
 	intel_encoder->cloneable = 0;
-	for_each_pipe(dev_priv, pipe)
-		intel_encoder->crtc_mask |= BIT(pipe);
+	intel_encoder->pipe_mask = ~0;
 
 	if (INTEL_GEN(dev_priv) >= 11)
 		intel_dig_port->saved_port_bits = I915_READ(DDI_BUF_CTL(port)) &
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 2912abd85148..6f5e3bd13ad1 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -55,6 +55,8 @@
 #include "display/intel_tv.h"
 #include "display/intel_vdsc.h"
 
+#include "gt/intel_rps.h"
+
 #include "i915_drv.h"
 #include "i915_trace.h"
 #include "intel_acpi.h"
@@ -64,6 +66,7 @@
 #include "intel_cdclk.h"
 #include "intel_color.h"
 #include "intel_display_types.h"
+#include "intel_dp_link_training.h"
 #include "intel_fbc.h"
 #include "intel_fbdev.h"
 #include "intel_fifo_underrun.h"
@@ -88,7 +91,17 @@ static const u32 i8xx_primary_formats[] = {
 	DRM_FORMAT_XRGB8888,
 };
 
-/* Primary plane formats for gen >= 4 */
+/* Primary plane formats for ivb (no fp16 due to hw issue) */
+static const u32 ivb_primary_formats[] = {
+	DRM_FORMAT_C8,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB2101010,
+	DRM_FORMAT_XBGR2101010,
+};
+
+/* Primary plane formats for gen >= 4, except ivb */
 static const u32 i965_primary_formats[] = {
 	DRM_FORMAT_C8,
 	DRM_FORMAT_RGB565,
@@ -96,6 +109,7 @@ static const u32 i965_primary_formats[] = {
 	DRM_FORMAT_XBGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_XBGR16161616F,
 };
 
 static const u64 i9xx_format_modifiers[] = {
@@ -2515,6 +2529,9 @@ u32 intel_plane_fb_max_stride(struct drm_i915_private *dev_priv,
 	 * the highest stride limits of them all.
 	 */
 	crtc = intel_get_crtc_for_pipe(dev_priv, PIPE_A);
+	if (!crtc)
+		return 0;
+
 	plane = to_intel_plane(crtc->base.primary);
 
 	return plane->max_stride(plane, pixel_format, modifier,
@@ -2971,6 +2988,8 @@ static int i9xx_format_to_fourcc(int format)
 		return DRM_FORMAT_XRGB2101010;
 	case DISPPLANE_RGBX101010:
 		return DRM_FORMAT_XBGR2101010;
+	case DISPPLANE_RGBX161616:
+		return DRM_FORMAT_XBGR16161616F;
 	}
 }
 
@@ -3154,6 +3173,7 @@ static void intel_plane_disable_noatomic(struct intel_crtc *crtc,
 	intel_set_plane_visible(crtc_state, plane_state, false);
 	fixup_active_planes(crtc_state);
 	crtc_state->data_rate[plane->id] = 0;
+	crtc_state->min_cdclk[plane->id] = 0;
 
 	if (plane->id == PLANE_PRIMARY)
 		intel_pre_disable_primary_noatomic(&crtc->base);
@@ -3577,6 +3597,53 @@ int skl_check_plane_surface(struct intel_plane_state *plane_state)
 	return 0;
 }
 
+static void i9xx_plane_ratio(const struct intel_crtc_state *crtc_state,
+			     const struct intel_plane_state *plane_state,
+			     unsigned int *num, unsigned int *den)
+{
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int cpp = fb->format->cpp[0];
+
+	/*
+	 * g4x bspec says 64bpp pixel rate can't exceed 80%
+	 * of cdclk when the sprite plane is enabled on the
+	 * same pipe. ilk/snb bspec says 64bpp pixel rate is
+	 * never allowed to exceed 80% of cdclk. Let's just go
+	 * with the ilk/snb limit always.
+	 */
+	if (cpp == 8) {
+		*num = 10;
+		*den = 8;
+	} else {
+		*num = 1;
+		*den = 1;
+	}
+}
+
+static int i9xx_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+				const struct intel_plane_state *plane_state)
+{
+	unsigned int pixel_rate;
+	unsigned int num, den;
+
+	/*
+	 * Note that crtc_state->pixel_rate accounts for both
+	 * horizontal and vertical panel fitter downscaling factors.
+	 * Pre-HSW bspec tells us to only consider the horizontal
+	 * downscaling factor here. We ignore that and just consider
+	 * both for simplicity.
+	 */
+	pixel_rate = crtc_state->pixel_rate;
+
+	i9xx_plane_ratio(crtc_state, plane_state, &num, &den);
+
+	/* two pixels per clock with double wide pipe */
+	if (crtc_state->double_wide)
+		den *= 2;
+
+	return DIV_ROUND_UP(pixel_rate * num, den);
+}
+
 unsigned int
 i9xx_plane_max_stride(struct intel_plane *plane,
 		      u32 pixel_format, u64 modifier,
@@ -3659,6 +3726,9 @@ static u32 i9xx_plane_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XBGR2101010:
 		dspcntr |= DISPPLANE_RGBX101010;
 		break;
+	case DRM_FORMAT_XBGR16161616F:
+		dspcntr |= DISPPLANE_RGBX161616;
+		break;
 	default:
 		MISSING_CASE(fb->format->format);
 		return 0;
@@ -3681,7 +3751,8 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(plane_state->base.plane->dev);
-	int src_x, src_y;
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	int src_x, src_y, src_w;
 	u32 offset;
 	int ret;
 
@@ -3692,9 +3763,14 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	if (!plane_state->base.visible)
 		return 0;
 
+	src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	src_x = plane_state->base.src.x1 >> 16;
 	src_y = plane_state->base.src.y1 >> 16;
 
+	/* Undocumented hardware limit on i965/g4x/vlv/chv */
+	if (HAS_GMCH(dev_priv) && fb->format->cpp[0] == 8 && src_w > 2048)
+		return -EINVAL;
+
 	intel_add_fb_offsets(&src_x, &src_y, plane_state, 0);
 
 	if (INTEL_GEN(dev_priv) >= 4)
@@ -5592,10 +5668,6 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
-	case DRM_FORMAT_XBGR16161616F:
-	case DRM_FORMAT_ABGR16161616F:
-	case DRM_FORMAT_XRGB16161616F:
-	case DRM_FORMAT_ARGB16161616F:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -5611,6 +5683,13 @@ static int skl_update_scaler_plane(struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XVYU12_16161616:
 	case DRM_FORMAT_XVYU16161616:
 		break;
+	case DRM_FORMAT_XBGR16161616F:
+	case DRM_FORMAT_ABGR16161616F:
+	case DRM_FORMAT_XRGB16161616F:
+	case DRM_FORMAT_ARGB16161616F:
+		if (INTEL_GEN(dev_priv) >= 11)
+			break;
+		/* fall through */
 	default:
 		DRM_DEBUG_KMS("[PLANE:%d:%s] FB:%d unsupported scaling format 0x%x\n",
 			      intel_plane->base.base.id, intel_plane->base.name,
@@ -9359,7 +9438,6 @@ static bool wrpll_uses_pch_ssc(struct drm_i915_private *dev_priv,
 static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 {
 	struct intel_encoder *encoder;
-	bool pch_ssc_in_use = false;
 	bool has_fdi = false;
 
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
@@ -9387,22 +9465,24 @@ static void lpt_init_pch_refclk(struct drm_i915_private *dev_priv)
 	 * clock hierarchy. That would also allow us to do
 	 * clock bending finally.
 	 */
+	dev_priv->pch_ssc_use = 0;
+
 	if (spll_uses_pch_ssc(dev_priv)) {
 		DRM_DEBUG_KMS("SPLL using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_SPLL);
 	}
 
 	if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL1)) {
 		DRM_DEBUG_KMS("WRPLL1 using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL1);
 	}
 
 	if (wrpll_uses_pch_ssc(dev_priv, DPLL_ID_WRPLL2)) {
 		DRM_DEBUG_KMS("WRPLL2 using PCH SSC\n");
-		pch_ssc_in_use = true;
+		dev_priv->pch_ssc_use |= BIT(DPLL_ID_WRPLL2);
 	}
 
-	if (pch_ssc_in_use)
+	if (dev_priv->pch_ssc_use)
 		return;
 
 	if (has_fdi) {
@@ -10871,7 +10951,7 @@ static void i845_update_cursor(struct intel_plane *plane,
 	unsigned long irqflags;
 
 	if (plane_state && plane_state->base.visible) {
-		unsigned int width = drm_rect_width(&plane_state->base.src);
+		unsigned int width = drm_rect_width(&plane_state->base.dst);
 		unsigned int height = drm_rect_height(&plane_state->base.dst);
 
 		cntl = plane_state->ctl |
@@ -11252,7 +11332,6 @@ static int intel_modeset_disable_planes(struct drm_atomic_state *state,
 }
 
 int intel_get_load_detect_pipe(struct drm_connector *connector,
-			       const struct drm_display_mode *mode,
 			       struct intel_load_detect_pipe *old,
 			       struct drm_modeset_acquire_ctx *ctx)
 {
@@ -11359,10 +11438,8 @@ found:
 
 	crtc_state->base.active = crtc_state->base.enable = true;
 
-	if (!mode)
-		mode = &load_detect_mode;
-
-	ret = drm_atomic_set_mode_for_crtc(&crtc_state->base, mode);
+	ret = drm_atomic_set_mode_for_crtc(&crtc_state->base,
+					   &load_detect_mode);
 	if (ret)
 		goto fail;
 
@@ -11706,6 +11783,7 @@ int intel_plane_atomic_calc_changes(const struct intel_crtc_state *old_crtc_stat
 		plane_state->base.visible = visible = false;
 		crtc_state->active_planes &= ~BIT(plane->id);
 		crtc_state->data_rate[plane->id] = 0;
+		crtc_state->min_cdclk[plane->id] = 0;
 	}
 
 	if (!was_visible && !visible)
@@ -12072,11 +12150,6 @@ static int intel_crtc_atomic_check(struct intel_atomic_state *state,
 	if (INTEL_GEN(dev_priv) >= 9) {
 		if (mode_changed || crtc_state->update_pipe)
 			ret = skl_update_scaler_crtc(crtc_state);
-
-		if (!ret)
-			ret = icl_check_nv12_planes(crtc_state);
-		if (!ret)
-			ret = skl_check_pipe_max_pixel_rate(crtc, crtc_state);
 		if (!ret)
 			ret = intel_atomic_setup_scalers(dev_priv, crtc,
 							 crtc_state);
@@ -12426,6 +12499,12 @@ static bool check_digital_port_conflicts(struct intel_atomic_state *state)
 	bool ret = true;
 
 	/*
+	 * We're going to peek into connector->state,
+	 * hence connection_mutex must be held.
+	 */
+	drm_modeset_lock_assert_held(&dev->mode_config.connection_mutex);
+
+	/*
 	 * Walk the connector list instead of the encoder
 	 * list to detect the problem on ddi platforms
 	 * where there's just one encoder per digital port.
@@ -13712,11 +13791,6 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 	struct intel_crtc *crtc;
 	int ret, i;
 
-	if (!check_digital_port_conflicts(state)) {
-		DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
-		return -EINVAL;
-	}
-
 	/* keep the current setting */
 	if (!state->cdclk.force_min_cdclk_changed)
 		state->cdclk.force_min_cdclk = dev_priv->cdclk.force_min_cdclk;
@@ -13725,7 +13799,6 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 	state->active_pipes = dev_priv->active_pipes;
 	state->cdclk.logical = dev_priv->cdclk.logical;
 	state->cdclk.actual = dev_priv->cdclk.actual;
-	state->cdclk.pipe = INVALID_PIPE;
 
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
 					    new_crtc_state, i) {
@@ -13738,6 +13811,12 @@ static int intel_modeset_checks(struct intel_atomic_state *state)
 			state->active_pipe_changes |= BIT(crtc->pipe);
 	}
 
+	if (state->active_pipe_changes) {
+		ret = intel_atomic_lock_global_state(state);
+		if (ret)
+			return ret;
+	}
+
 	ret = intel_modeset_calc_cdclk(state);
 	if (ret)
 		return ret;
@@ -13790,12 +13869,49 @@ static void intel_crtc_check_fastset(const struct intel_crtc_state *old_crtc_sta
 	new_crtc_state->has_drrs = old_crtc_state->has_drrs;
 }
 
-static int intel_atomic_check_planes(struct intel_atomic_state *state)
+static int intel_crtc_add_planes_to_state(struct intel_atomic_state *state,
+					  struct intel_crtc *crtc,
+					  u8 plane_ids_mask)
 {
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_plane *plane;
+
+	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
+		struct intel_plane_state *plane_state;
+
+		if ((plane_ids_mask & BIT(plane->id)) == 0)
+			continue;
+
+		plane_state = intel_atomic_get_plane_state(state, plane);
+		if (IS_ERR(plane_state))
+			return PTR_ERR(plane_state);
+	}
+
+	return 0;
+}
+
+static bool active_planes_affects_min_cdclk(struct drm_i915_private *dev_priv)
+{
+	/* See {hsw,vlv,ivb}_plane_ratio() */
+	return IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv) ||
+		IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv) ||
+		IS_IVYBRIDGE(dev_priv);
+}
+
+static int intel_atomic_check_planes(struct intel_atomic_state *state,
+				     bool *need_modeset)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
 	struct intel_plane_state *plane_state;
 	struct intel_plane *plane;
+	struct intel_crtc *crtc;
 	int i, ret;
 
+	ret = icl_add_linked_planes(state);
+	if (ret)
+		return ret;
+
 	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
 		ret = intel_plane_atomic_check(state, plane);
 		if (ret) {
@@ -13805,6 +13921,41 @@ static int intel_atomic_check_planes(struct intel_atomic_state *state)
 		}
 	}
 
+	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
+					    new_crtc_state, i) {
+		u8 old_active_planes, new_active_planes;
+
+		ret = icl_check_nv12_planes(new_crtc_state);
+		if (ret)
+			return ret;
+
+		/*
+		 * On some platforms the number of active planes affects
+		 * the planes' minimum cdclk calculation. Add such planes
+		 * to the state before we compute the minimum cdclk.
+		 */
+		if (!active_planes_affects_min_cdclk(dev_priv))
+			continue;
+
+		old_active_planes = old_crtc_state->active_planes & ~BIT(PLANE_CURSOR);
+		new_active_planes = new_crtc_state->active_planes & ~BIT(PLANE_CURSOR);
+
+		if (hweight8(old_active_planes) == hweight8(new_active_planes))
+			continue;
+
+		ret = intel_crtc_add_planes_to_state(state, crtc, new_active_planes);
+		if (ret)
+			return ret;
+	}
+
+	/*
+	 * active_planes bitmask has been updated, and potentially
+	 * affected planes are part of the state. We can now
+	 * compute the minimum cdclk for each plane.
+	 */
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i)
+		*need_modeset |= intel_plane_calc_min_cdclk(state, plane);
+
 	return 0;
 }
 
@@ -13839,7 +13990,7 @@ static int intel_atomic_check(struct drm_device *dev,
 	struct intel_crtc_state *old_crtc_state, *new_crtc_state;
 	struct intel_crtc *crtc;
 	int ret, i;
-	bool any_ms = state->cdclk.force_min_cdclk_changed;
+	bool any_ms = false;
 
 	/* Catch I915_MODE_FLAG_INHERITED */
 	for_each_oldnew_intel_crtc_in_state(state, crtc, old_crtc_state,
@@ -13873,10 +14024,22 @@ static int intel_atomic_check(struct drm_device *dev,
 			any_ms = true;
 	}
 
+	if (any_ms && !check_digital_port_conflicts(state)) {
+		DRM_DEBUG_KMS("rejecting conflicting digital port configuration\n");
+		ret = EINVAL;
+		goto fail;
+	}
+
 	ret = drm_dp_mst_atomic_check(&state->base);
 	if (ret)
 		goto fail;
 
+	any_ms |= state->cdclk.force_min_cdclk_changed;
+
+	ret = intel_atomic_check_planes(state, &any_ms);
+	if (ret)
+		goto fail;
+
 	if (any_ms) {
 		ret = intel_modeset_checks(state);
 		if (ret)
@@ -13885,14 +14048,6 @@ static int intel_atomic_check(struct drm_device *dev,
 		state->cdclk.logical = dev_priv->cdclk.logical;
 	}
 
-	ret = icl_add_linked_planes(state);
-	if (ret)
-		goto fail;
-
-	ret = intel_atomic_check_planes(state);
-	if (ret)
-		goto fail;
-
 	ret = intel_atomic_check_crtcs(state);
 	if (ret)
 		goto fail;
@@ -13973,9 +14128,6 @@ static void intel_pipe_fastset(const struct intel_crtc_state *old_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);
 
-	/* drm_atomic_helper_update_legacy_modeset_state might not be called. */
-	crtc->base.mode = new_crtc_state->base.mode;
-
 	/*
 	 * Update pipe size and adjust fitter if needed: the reason for this is
 	 * that in compute_mode_changes we check the native mode (not the pfit
@@ -14053,6 +14205,11 @@ static void intel_update_crtc(struct intel_crtc *crtc,
 		/* vblanks work again, re-enable pipe CRC. */
 		intel_crtc_enable_pipe_crc(crtc);
 	} else {
+		if (new_crtc_state->preload_luts &&
+		    (new_crtc_state->base.color_mgmt_changed ||
+		     new_crtc_state->update_pipe))
+			intel_color_load_luts(new_crtc_state);
+
 		intel_pre_plane_update(old_crtc_state, new_crtc_state);
 
 		if (new_crtc_state->update_pipe)
@@ -14237,8 +14394,8 @@ static void intel_crtc_enable_trans_port_sync(struct intel_crtc *crtc,
 static void intel_set_dp_tp_ctl_normal(struct intel_crtc *crtc,
 				       struct intel_atomic_state *state)
 {
+	struct drm_connector *uninitialized_var(conn);
 	struct drm_connector_state *conn_state;
-	struct drm_connector *conn;
 	struct intel_dp *intel_dp;
 	int i;
 
@@ -14565,6 +14722,7 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 	for_each_new_intel_crtc_in_state(state, crtc, new_crtc_state, i) {
 		if (new_crtc_state->base.active &&
 		    !needs_modeset(new_crtc_state) &&
+		    !new_crtc_state->preload_luts &&
 		    (new_crtc_state->base.color_mgmt_changed ||
 		     new_crtc_state->update_pipe))
 			intel_color_load_luts(new_crtc_state);
@@ -14670,6 +14828,14 @@ static void intel_atomic_track_fbs(struct intel_atomic_state *state)
 					plane->frontbuffer_bit);
 }
 
+static void assert_global_state_locked(struct drm_i915_private *dev_priv)
+{
+	struct intel_crtc *crtc;
+
+	for_each_intel_crtc(&dev_priv->drm, crtc)
+		drm_modeset_lock_assert_held(&crtc->base.mutex);
+}
+
 static int intel_atomic_commit(struct drm_device *dev,
 			       struct drm_atomic_state *_state,
 			       bool nonblock)
@@ -14735,7 +14901,9 @@ static int intel_atomic_commit(struct drm_device *dev,
 	intel_shared_dpll_swap_state(state);
 	intel_atomic_track_fbs(state);
 
-	if (state->modeset) {
+	if (state->global_state_changed) {
+		assert_global_state_locked(dev_priv);
+
 		memcpy(dev_priv->min_cdclk, state->min_cdclk,
 		       sizeof(state->min_cdclk));
 		memcpy(dev_priv->min_voltage_level, state->min_voltage_level,
@@ -14782,7 +14950,7 @@ static int do_rps_boost(struct wait_queue_entry *_wait,
 	 * vblank without our intervention, so leave RPS alone.
 	 */
 	if (!i915_request_started(rq))
-		gen6_rps_boost(rq);
+		intel_rps_boost(rq);
 	i915_request_put(rq);
 
 	drm_crtc_vblank_put(wait->crtc);
@@ -14863,7 +15031,7 @@ static void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state)
 static void fb_obj_bump_render_priority(struct drm_i915_gem_object *obj)
 {
 	struct i915_sched_attr attr = {
-		.priority = I915_PRIORITY_DISPLAY,
+		.priority = I915_USER_PRIORITY(I915_PRIORITY_DISPLAY),
 	};
 
 	i915_gem_object_wait_priority(obj, 0, &attr);
@@ -14976,7 +15144,7 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 	 * maximum clocks following a vblank miss (see do_rps_boost()).
 	 */
 	if (!intel_state->rps_interactive) {
-		intel_rps_mark_interactive(dev_priv, true);
+		intel_rps_mark_interactive(&dev_priv->gt.rps, true);
 		intel_state->rps_interactive = true;
 	}
 
@@ -15001,7 +15169,7 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
 	if (intel_state->rps_interactive) {
-		intel_rps_mark_interactive(dev_priv, false);
+		intel_rps_mark_interactive(&dev_priv->gt.rps, false);
 		intel_state->rps_interactive = false;
 	}
 
@@ -15009,44 +15177,6 @@ intel_cleanup_plane_fb(struct drm_plane *plane,
 	intel_plane_unpin_fb(old_plane_state);
 }
 
-int
-skl_max_scale(const struct intel_crtc_state *crtc_state,
-	      const struct drm_format_info *format)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	int max_scale;
-	int crtc_clock, max_dotclk, tmpclk1, tmpclk2;
-
-	if (!crtc_state->base.enable)
-		return DRM_PLANE_HELPER_NO_SCALING;
-
-	crtc_clock = crtc_state->base.adjusted_mode.crtc_clock;
-	max_dotclk = to_intel_atomic_state(crtc_state->base.state)->cdclk.logical.cdclk;
-
-	if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 10)
-		max_dotclk *= 2;
-
-	if (WARN_ON_ONCE(!crtc_clock || max_dotclk < crtc_clock))
-		return DRM_PLANE_HELPER_NO_SCALING;
-
-	/*
-	 * skl max scale is lower of:
-	 *    close to 3 but not 3, -1 is for that purpose
-	 *            or
-	 *    cdclk/crtc_clock
-	 */
-	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
-	    !drm_format_info_is_yuv_semiplanar(format))
-		tmpclk1 = 0x30000 - 1;
-	else
-		tmpclk1 = 0x20000 - 1;
-	tmpclk2 = (1 << 8) * ((max_dotclk << 8) / crtc_clock);
-	max_scale = min(tmpclk1, tmpclk2);
-
-	return max_scale;
-}
-
 /**
  * intel_plane_destroy - destroy a plane
  * @plane: plane to destroy
@@ -15101,6 +15231,7 @@ static bool i965_plane_format_mod_supported(struct drm_plane *_plane,
 	case DRM_FORMAT_XBGR8888:
 	case DRM_FORMAT_XRGB2101010:
 	case DRM_FORMAT_XBGR2101010:
+	case DRM_FORMAT_XBGR16161616F:
 		return modifier == DRM_FORMAT_MOD_LINEAR ||
 			modifier == I915_FORMAT_MOD_X_TILED;
 	default:
@@ -15321,8 +15452,26 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	}
 
 	if (INTEL_GEN(dev_priv) >= 4) {
-		formats = i965_primary_formats;
-		num_formats = ARRAY_SIZE(i965_primary_formats);
+		/*
+		 * WaFP16GammaEnabling:ivb
+		 * "Workaround : When using the 64-bit format, the plane
+		 *  output on each color channel has one quarter amplitude.
+		 *  It can be brought up to full amplitude by using pipe
+		 *  gamma correction or pipe color space conversion to
+		 *  multiply the plane output by four."
+		 *
+		 * There is no dedicated plane gamma for the primary plane,
+		 * and using the pipe gamma/csc could conflict with other
+		 * planes, so we choose not to expose fp16 on IVB primary
+		 * planes. HSW primary planes no longer have this problem.
+		 */
+		if (IS_IVYBRIDGE(dev_priv)) {
+			formats = ivb_primary_formats;
+			num_formats = ARRAY_SIZE(ivb_primary_formats);
+		} else {
+			formats = i965_primary_formats;
+			num_formats = ARRAY_SIZE(i965_primary_formats);
+		}
 		modifiers = i9xx_format_modifiers;
 
 		plane->max_stride = i9xx_plane_max_stride;
@@ -15331,6 +15480,15 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		plane->get_hw_state = i9xx_plane_get_hw_state;
 		plane->check_plane = i9xx_plane_check;
 
+		if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
+			plane->min_cdclk = hsw_plane_min_cdclk;
+		else if (IS_IVYBRIDGE(dev_priv))
+			plane->min_cdclk = ivb_plane_min_cdclk;
+		else if (IS_CHERRYVIEW(dev_priv) || IS_VALLEYVIEW(dev_priv))
+			plane->min_cdclk = vlv_plane_min_cdclk;
+		else
+			plane->min_cdclk = i9xx_plane_min_cdclk;
+
 		plane_funcs = &i965_plane_funcs;
 	} else {
 		formats = i8xx_primary_formats;
@@ -15342,6 +15500,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		plane->disable_plane = i9xx_disable_plane;
 		plane->get_hw_state = i9xx_plane_get_hw_state;
 		plane->check_plane = i9xx_plane_check;
+		plane->min_cdclk = i9xx_plane_min_cdclk;
 
 		plane_funcs = &i8xx_plane_funcs;
 	}
@@ -15693,7 +15852,7 @@ static u32 intel_encoder_possible_crtcs(struct intel_encoder *encoder)
 	u32 possible_crtcs = 0;
 
 	for_each_intel_crtc(dev, crtc) {
-		if (encoder->crtc_mask & BIT(crtc->pipe))
+		if (encoder->pipe_mask & BIT(crtc->pipe))
 			possible_crtcs |= drm_crtc_mask(&crtc->base);
 	}
 
@@ -16294,6 +16453,21 @@ intel_mode_valid(struct drm_device *dev,
 	    mode->vtotal > vtotal_max)
 		return MODE_V_ILLEGAL;
 
+	if (INTEL_GEN(dev_priv) >= 5) {
+		if (mode->hdisplay < 64 ||
+		    mode->htotal - mode->hdisplay < 32)
+			return MODE_H_ILLEGAL;
+
+		if (mode->vtotal - mode->vdisplay < 5)
+			return MODE_V_ILLEGAL;
+	} else {
+		if (mode->htotal - mode->hdisplay < 32)
+			return MODE_H_ILLEGAL;
+
+		if (mode->vtotal - mode->vdisplay < 3)
+			return MODE_V_ILLEGAL;
+	}
+
 	return MODE_OK;
 }
 
@@ -17224,13 +17398,16 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 		struct intel_plane *plane;
 		int min_cdclk = 0;
 
-		memset(&crtc->base.mode, 0, sizeof(crtc->base.mode));
 		if (crtc_state->base.active) {
-			intel_mode_from_pipe_config(&crtc->base.mode, crtc_state);
-			crtc->base.mode.hdisplay = crtc_state->pipe_src_w;
-			crtc->base.mode.vdisplay = crtc_state->pipe_src_h;
-			intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode, crtc_state);
-			WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->base, &crtc->base.mode));
+			struct drm_display_mode mode;
+
+			intel_mode_from_pipe_config(&crtc_state->base.adjusted_mode,
+						    crtc_state);
+
+			mode = crtc_state->base.adjusted_mode;
+			mode.hdisplay = crtc_state->pipe_src_w;
+			mode.vdisplay = crtc_state->pipe_src_h;
+			WARN_ON(drm_atomic_set_mode_for_crtc(&crtc_state->base, &mode));
 
 			/*
 			 * The initial mode needs to be set in order to keep
@@ -17245,17 +17422,9 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 
 			intel_crtc_compute_pixel_rate(crtc_state);
 
-			min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
-			if (WARN_ON(min_cdclk < 0))
-				min_cdclk = 0;
-
 			intel_crtc_update_active_timings(crtc_state);
 		}
 
-		dev_priv->min_cdclk[crtc->pipe] = min_cdclk;
-		dev_priv->min_voltage_level[crtc->pipe] =
-			crtc_state->min_voltage_level;
-
 		for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 			const struct intel_plane_state *plane_state =
 				to_intel_plane_state(plane->base.state);
@@ -17267,8 +17436,34 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			if (plane_state->base.visible)
 				crtc_state->data_rate[plane->id] =
 					4 * crtc_state->pixel_rate;
+			/*
+			 * FIXME don't have the fb yet, so can't
+			 * use plane->min_cdclk() :(
+			 */
+			if (plane_state->base.visible && plane->min_cdclk) {
+				if (crtc_state->double_wide ||
+				    INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+					crtc_state->min_cdclk[plane->id] =
+						DIV_ROUND_UP(crtc_state->pixel_rate, 2);
+				else
+					crtc_state->min_cdclk[plane->id] =
+						crtc_state->pixel_rate;
+			}
+			DRM_DEBUG_KMS("[PLANE:%d:%s] min_cdclk %d kHz\n",
+				      plane->base.base.id, plane->base.name,
+				      crtc_state->min_cdclk[plane->id]);
 		}
 
+		if (crtc_state->base.active) {
+			min_cdclk = intel_crtc_compute_min_cdclk(crtc_state);
+			if (WARN_ON(min_cdclk < 0))
+				min_cdclk = 0;
+		}
+
+		dev_priv->min_cdclk[crtc->pipe] = min_cdclk;
+		dev_priv->min_voltage_level[crtc->pipe] =
+			crtc_state->min_voltage_level;
+
 		intel_bw_crtc_update(bw_state, crtc_state);
 
 		intel_pipe_config_sanity_check(dev_priv, crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h
index 7dcb176d91b0..f417e0948001 100644
--- a/drivers/gpu/drm/i915/display/intel_display.h
+++ b/drivers/gpu/drm/i915/display/intel_display.h
@@ -27,7 +27,6 @@
 
 #include <drm/drm_util.h>
 #include <drm/i915_drm.h>
-#include "intel_dp_link_training.h"
 
 enum link_m_n_set;
 struct dpll;
@@ -509,7 +508,6 @@ void vlv_wait_port_ready(struct drm_i915_private *dev_priv,
 			 struct intel_digital_port *dport,
 			 unsigned int expected_mask);
 int intel_get_load_detect_pipe(struct drm_connector *connector,
-			       const struct drm_display_mode *mode,
 			       struct intel_load_detect_pipe *old,
 			       struct drm_modeset_acquire_ctx *ctx);
 void intel_release_load_detect_pipe(struct drm_connector *connector,
@@ -563,8 +561,6 @@ void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 
 u16 skl_scaler_calc_phase(int sub, int scale, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
-int skl_max_scale(const struct intel_crtc_state *crtc_state,
-		  const struct drm_format_info *format);
 u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 			const struct intel_plane_state *plane_state);
 u32 glk_plane_color_ctl_crtc(const struct intel_crtc_state *crtc_state);
diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c
index 6f9e7927e248..707ac110e271 100644
--- a/drivers/gpu/drm/i915/display/intel_display_power.c
+++ b/drivers/gpu/drm/i915/display/intel_display_power.c
@@ -2682,6 +2682,8 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	TGL_PW_2_POWER_DOMAINS |			\
 	BIT_ULL(POWER_DOMAIN_MODESET) |			\
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
 #define TGL_DDI_IO_D_TC1_POWER_DOMAINS (	\
diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
index 8358152e403e..1a7334dbe802 100644
--- a/drivers/gpu/drm/i915/display/intel_display_types.h
+++ b/drivers/gpu/drm/i915/display/intel_display_types.h
@@ -128,7 +128,8 @@ struct intel_encoder {
 
 	enum intel_output_type type;
 	enum port port;
-	unsigned int cloneable;
+	u16 cloneable;
+	u8 pipe_mask;
 	enum intel_hotplug_state (*hotplug)(struct intel_encoder *encoder,
 					    struct intel_connector *connector,
 					    bool irq_received);
@@ -187,7 +188,6 @@ struct intel_encoder {
 	 * device interrupts are disabled.
 	 */
 	void (*suspend)(struct intel_encoder *);
-	int crtc_mask;
 	enum hpd_pin hpd_pin;
 	enum intel_display_power_domain power_domain;
 	/* for communication with audio component; protected by av_mutex */
@@ -506,6 +506,14 @@ struct intel_atomic_state {
 
 	bool rps_interactive;
 
+	/*
+	 * active_pipes
+	 * min_cdclk[]
+	 * min_voltage_level[]
+	 * cdclk.*
+	 */
+	bool global_state_changed;
+
 	/* Gen9+ only */
 	struct skl_ddb_values wm_results;
 
@@ -767,6 +775,7 @@ struct intel_crtc_state {
 	bool disable_cxsr;
 	bool update_wm_pre, update_wm_post; /* watermarks are updated */
 	bool fifo_changed; /* FIFO split is changed */
+	bool preload_luts;
 
 	/* Pipe source size (ie. panel fitter input size)
 	 * All planes will be positioned inside this space,
@@ -932,6 +941,8 @@ struct intel_crtc_state {
 
 	struct intel_crtc_wm_state wm;
 
+	int min_cdclk[I915_MAX_PLANES];
+
 	u32 data_rate[I915_MAX_PLANES];
 
 	/* Gamma mode programmed on the pipe */
@@ -986,8 +997,8 @@ struct intel_crtc_state {
 		bool dsc_split;
 		u16 compressed_bpp;
 		u8 slice_count;
-	} dsc_params;
-	struct drm_dsc_config dp_dsc_cfg;
+		struct drm_dsc_config config;
+	} dsc;
 
 	/* Forward Error correction State */
 	bool fec_enable;
@@ -1077,6 +1088,8 @@ struct intel_plane {
 	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
 	int (*check_plane)(struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *plane_state);
+	int (*min_cdclk)(const struct intel_crtc_state *crtc_state,
+			 const struct intel_plane_state *plane_state);
 };
 
 struct intel_watermark_params {
diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
index 5eeafa45831a..c61ac0c3acb5 100644
--- a/drivers/gpu/drm/i915/display/intel_dp.c
+++ b/drivers/gpu/drm/i915/display/intel_dp.c
@@ -1179,18 +1179,20 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *i915 = dp_to_i915(intel_dp);
 	i915_reg_t ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
+	const unsigned int timeout_ms = 10;
 	u32 status;
 	bool done;
 
 #define C (((status = intel_uncore_read_notrace(&i915->uncore, ch_ctl)) & DP_AUX_CH_CTL_SEND_BUSY) == 0)
 	done = wait_event_timeout(i915->gmbus_wait_queue, C,
-				  msecs_to_jiffies_timeout(10));
+				  msecs_to_jiffies_timeout(timeout_ms));
 
 	/* just trace the final value */
 	trace_i915_reg_rw(false, ch_ctl, status, sizeof(status), true);
 
 	if (!done)
-		DRM_ERROR("dp aux hw did not signal timeout!\n");
+		DRM_ERROR("%s did not complete or timeout within %ums (status 0x%08x)\n",
+			  intel_dp->aux.name, timeout_ms, status);
 #undef C
 
 	return status;
@@ -1291,6 +1293,9 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 				u32 unused)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_i915_private *i915 =
+			to_i915(intel_dig_port->base.base.dev);
+	enum phy phy = intel_port_to_phy(i915, intel_dig_port->base.port);
 	u32 ret;
 
 	ret = DP_AUX_CH_CTL_SEND_BUSY |
@@ -1303,7 +1308,8 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
 	      DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(32) |
 	      DP_AUX_CH_CTL_SYNC_PULSE_SKL(32);
 
-	if (intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
+	if (intel_phy_is_tc(i915, phy) &&
+	    intel_dig_port->tc_mode == TC_PORT_TBT_ALT)
 		ret |= DP_AUX_CH_CTL_TBT_IO;
 
 	return ret;
@@ -1888,6 +1894,9 @@ static bool intel_dp_source_supports_dsc(struct intel_dp *intel_dp,
 {
 	struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
 
+	if (!INTEL_INFO(dev_priv)->display.has_dsc)
+		return false;
+
 	/* On TGL, DSC is supported on all Pipes */
 	if (INTEL_GEN(dev_priv) >= 12)
 		return true;
@@ -2080,10 +2089,10 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 	pipe_config->lane_count = limits->max_lane_count;
 
 	if (intel_dp_is_edp(intel_dp)) {
-		pipe_config->dsc_params.compressed_bpp =
+		pipe_config->dsc.compressed_bpp =
 			min_t(u16, drm_edp_dsc_sink_output_bpp(intel_dp->dsc_dpcd) >> 4,
 			      pipe_config->pipe_bpp);
-		pipe_config->dsc_params.slice_count =
+		pipe_config->dsc.slice_count =
 			drm_dp_dsc_sink_max_slice_count(intel_dp->dsc_dpcd,
 							true);
 	} else {
@@ -2104,10 +2113,10 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 			DRM_DEBUG_KMS("Compressed BPP/Slice Count not supported\n");
 			return -EINVAL;
 		}
-		pipe_config->dsc_params.compressed_bpp = min_t(u16,
+		pipe_config->dsc.compressed_bpp = min_t(u16,
 							       dsc_max_output_bpp >> 4,
 							       pipe_config->pipe_bpp);
-		pipe_config->dsc_params.slice_count = dsc_dp_slice_count;
+		pipe_config->dsc.slice_count = dsc_dp_slice_count;
 	}
 	/*
 	 * VDSC engine operates at 1 Pixel per clock, so if peak pixel rate
@@ -2115,8 +2124,8 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 	 * then we need to use 2 VDSC instances.
 	 */
 	if (adjusted_mode->crtc_clock > dev_priv->max_cdclk_freq) {
-		if (pipe_config->dsc_params.slice_count > 1) {
-			pipe_config->dsc_params.dsc_split = true;
+		if (pipe_config->dsc.slice_count > 1) {
+			pipe_config->dsc.dsc_split = true;
 		} else {
 			DRM_DEBUG_KMS("Cannot split stream to use 2 VDSC instances\n");
 			return -EINVAL;
@@ -2128,16 +2137,16 @@ static int intel_dp_dsc_compute_config(struct intel_dp *intel_dp,
 		DRM_DEBUG_KMS("Cannot compute valid DSC parameters for Input Bpp = %d "
 			      "Compressed BPP = %d\n",
 			      pipe_config->pipe_bpp,
-			      pipe_config->dsc_params.compressed_bpp);
+			      pipe_config->dsc.compressed_bpp);
 		return ret;
 	}
 
-	pipe_config->dsc_params.compression_enable = true;
+	pipe_config->dsc.compression_enable = true;
 	DRM_DEBUG_KMS("DP DSC computed with Input Bpp = %d "
 		      "Compressed Bpp = %d Slice Count = %d\n",
 		      pipe_config->pipe_bpp,
-		      pipe_config->dsc_params.compressed_bpp,
-		      pipe_config->dsc_params.slice_count);
+		      pipe_config->dsc.compressed_bpp,
+		      pipe_config->dsc.slice_count);
 
 	return 0;
 }
@@ -2211,15 +2220,15 @@ intel_dp_compute_link_config(struct intel_encoder *encoder,
 			return ret;
 	}
 
-	if (pipe_config->dsc_params.compression_enable) {
+	if (pipe_config->dsc.compression_enable) {
 		DRM_DEBUG_KMS("DP lane count %d clock %d Input bpp %d Compressed bpp %d\n",
 			      pipe_config->lane_count, pipe_config->port_clock,
 			      pipe_config->pipe_bpp,
-			      pipe_config->dsc_params.compressed_bpp);
+			      pipe_config->dsc.compressed_bpp);
 
 		DRM_DEBUG_KMS("DP link rate required %i available %i\n",
 			      intel_dp_link_required(adjusted_mode->crtc_clock,
-						     pipe_config->dsc_params.compressed_bpp),
+						     pipe_config->dsc.compressed_bpp),
 			      intel_dp_max_data_rate(pipe_config->port_clock,
 						     pipe_config->lane_count));
 	} else {
@@ -2377,8 +2386,8 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	pipe_config->limited_color_range =
 		intel_dp_limited_color_range(pipe_config, conn_state);
 
-	if (pipe_config->dsc_params.compression_enable)
-		output_bpp = pipe_config->dsc_params.compressed_bpp;
+	if (pipe_config->dsc.compression_enable)
+		output_bpp = pipe_config->dsc.compressed_bpp;
 	else
 		output_bpp = intel_dp_output_bpp(pipe_config, pipe_config->pipe_bpp);
 
@@ -3102,7 +3111,7 @@ void intel_dp_sink_set_decompression_state(struct intel_dp *intel_dp,
 {
 	int ret;
 
-	if (!crtc_state->dsc_params.compression_enable)
+	if (!crtc_state->dsc.compression_enable)
 		return;
 
 	ret = drm_dp_dpcd_writeb(&intel_dp->aux, DP_DSC_ENABLE,
@@ -5688,6 +5697,12 @@ out:
 	if (status != connector_status_connected && !intel_dp->is_mst)
 		intel_dp_unset_edid(intel_dp);
 
+	/*
+	 * Make sure the refs for power wells enabled during detect are
+	 * dropped to avoid a new detect cycle triggered by HPD polling.
+	 */
+	intel_display_power_flush_work(dev_priv);
+
 	return status;
 }
 
@@ -7560,11 +7575,11 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 	intel_encoder->power_domain = intel_port_to_power_domain(port);
 	if (IS_CHERRYVIEW(dev_priv)) {
 		if (port == PORT_D)
-			intel_encoder->crtc_mask = BIT(PIPE_C);
+			intel_encoder->pipe_mask = BIT(PIPE_C);
 		else
-			intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
+			intel_encoder->pipe_mask = BIT(PIPE_A) | BIT(PIPE_B);
 	} else {
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+		intel_encoder->pipe_mask = ~0;
 	}
 	intel_encoder->cloneable = 0;
 	intel_encoder->port = port;
@@ -7625,7 +7640,8 @@ void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 		if (!intel_dp->can_mst)
 			continue;
 
-		ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr);
+		ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr,
+						     true);
 		if (ret) {
 			intel_dp->is_mst = false;
 			drm_dp_mst_topology_mgr_set_mst(&intel_dp->mst_mgr,
diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index bbcab27644dc..03d1cba0b696 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -331,6 +331,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder,
 	ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr);
 
 	intel_ddi_enable_pipe_clock(pipe_config);
+
+	intel_ddi_set_dp_msa(pipe_config, conn_state);
 }
 
 static void intel_mst_enable_dp(struct intel_encoder *encoder,
@@ -391,20 +393,7 @@ static int intel_dp_mst_get_ddc_modes(struct drm_connector *connector)
 	return ret;
 }
 
-static enum drm_connector_status
-intel_dp_mst_detect(struct drm_connector *connector, bool force)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_dp *intel_dp = intel_connector->mst_port;
-
-	if (drm_connector_is_unregistered(connector))
-		return connector_status_disconnected;
-	return drm_dp_mst_detect_port(connector, &intel_dp->mst_mgr,
-				      intel_connector->port);
-}
-
 static const struct drm_connector_funcs intel_dp_mst_connector_funcs = {
-	.detect = intel_dp_mst_detect,
 	.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,
@@ -465,11 +454,26 @@ static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *c
 	return &intel_dp->mst_encoders[crtc->pipe]->base.base;
 }
 
+static int
+intel_dp_mst_detect(struct drm_connector *connector,
+		    struct drm_modeset_acquire_ctx *ctx, bool force)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_dp *intel_dp = intel_connector->mst_port;
+
+	if (drm_connector_is_unregistered(connector))
+		return connector_status_disconnected;
+
+	return drm_dp_mst_detect_port(connector, ctx, &intel_dp->mst_mgr,
+				      intel_connector->port);
+}
+
 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,
 	.atomic_check = intel_dp_mst_atomic_check,
+	.detect_ctx = intel_dp_mst_detect,
 };
 
 static void intel_dp_mst_encoder_destroy(struct drm_encoder *encoder)
@@ -598,8 +602,6 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	struct intel_dp_mst_encoder *intel_mst;
 	struct intel_encoder *intel_encoder;
 	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	enum pipe pipe_iter;
 
 	intel_mst = kzalloc(sizeof(*intel_mst), GFP_KERNEL);
 
@@ -617,8 +619,15 @@ intel_dp_create_fake_mst_encoder(struct intel_digital_port *intel_dig_port, enum
 	intel_encoder->power_domain = intel_dig_port->base.power_domain;
 	intel_encoder->port = intel_dig_port->base.port;
 	intel_encoder->cloneable = 0;
-	for_each_pipe(dev_priv, pipe_iter)
-		intel_encoder->crtc_mask |= BIT(pipe_iter);
+	/*
+	 * This is wrong, but broken userspace uses the intersection
+	 * of possible_crtcs of all the encoders of a given connector
+	 * to figure out which crtcs can drive said connector. What
+	 * should be used instead is the union of possible_crtcs.
+	 * To keep such userspace functioning we must misconfigure
+	 * this to make sure the intersection is not empty :(
+	 */
+	intel_encoder->pipe_mask = ~0;
 
 	intel_encoder->compute_config = intel_dp_mst_compute_config;
 	intel_encoder->disable = intel_mst_disable_dp;
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
index ec10fa7d3c69..3ce0a023eee0 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
@@ -526,16 +526,31 @@ static void hsw_ddi_wrpll_disable(struct drm_i915_private *dev_priv,
 	val = I915_READ(WRPLL_CTL(id));
 	I915_WRITE(WRPLL_CTL(id), val & ~WRPLL_PLL_ENABLE);
 	POSTING_READ(WRPLL_CTL(id));
+
+	/*
+	 * Try to set up the PCH reference clock once all DPLLs
+	 * that depend on it have been shut down.
+	 */
+	if (dev_priv->pch_ssc_use & BIT(id))
+		intel_init_pch_refclk(dev_priv);
 }
 
 static void hsw_ddi_spll_disable(struct drm_i915_private *dev_priv,
 				 struct intel_shared_dpll *pll)
 {
+	enum intel_dpll_id id = pll->info->id;
 	u32 val;
 
 	val = I915_READ(SPLL_CTL);
 	I915_WRITE(SPLL_CTL, val & ~SPLL_PLL_ENABLE);
 	POSTING_READ(SPLL_CTL);
+
+	/*
+	 * Try to set up the PCH reference clock once all DPLLs
+	 * that depend on it have been shut down.
+	 */
+	if (dev_priv->pch_ssc_use & BIT(id))
+		intel_init_pch_refclk(dev_priv);
 }
 
 static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
index e7588799fce5..2a104c64291d 100644
--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.h
@@ -147,11 +147,11 @@ enum intel_dpll_id {
 	 */
 	DPLL_ID_ICL_MGPLL4 = 6,
 	/**
-	 * @DPLL_ID_TGL_TCPLL5: TGL TC PLL port 5 (TC5)
+	 * @DPLL_ID_TGL_MGPLL5: TGL TC PLL port 5 (TC5)
 	 */
 	DPLL_ID_TGL_MGPLL5 = 7,
 	/**
-	 * @DPLL_ID_TGL_TCPLL6: TGL TC PLL port 6 (TC6)
+	 * @DPLL_ID_TGL_MGPLL6: TGL TC PLL port 6 (TC6)
 	 */
 	DPLL_ID_TGL_MGPLL6 = 8,
 };
@@ -337,6 +337,11 @@ struct intel_shared_dpll {
 	 * @info: platform specific info
 	 */
 	const struct dpll_info *info;
+
+	/**
+	 * @wakeref: In some platforms a device-level runtime pm reference may
+	 * need to be grabbed to disable DC states while this DPLL is enabled
+	 */
 	intel_wakeref_t wakeref;
 };
 
diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c
index 9827f99491d1..bcfbcb743e7d 100644
--- a/drivers/gpu/drm/i915/display/intel_dvo.c
+++ b/drivers/gpu/drm/i915/display/intel_dvo.c
@@ -505,7 +505,7 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 		intel_encoder->type = INTEL_OUTPUT_DVO;
 		intel_encoder->power_domain = POWER_DOMAIN_PORT_OTHER;
 		intel_encoder->port = port;
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
+		intel_encoder->pipe_mask = ~0;
 
 		switch (dvo->type) {
 		case INTEL_DVO_CHIP_TMDS:
diff --git a/drivers/gpu/drm/i915/display/intel_fbdev.c b/drivers/gpu/drm/i915/display/intel_fbdev.c
index 3d1061470e76..48c960ca12fb 100644
--- a/drivers/gpu/drm/i915/display/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/display/intel_fbdev.c
@@ -234,6 +234,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = ggtt->gmadr.start;
 	info->apertures->ranges[0].size = ggtt->mappable_end;
 
+	/* Our framebuffer is the entirety of fbdev's system memory */
+	info->fix.smem_start =
+		(unsigned long)(ggtt->gmadr.start + vma->node.start);
+	info->fix.smem_len = vma->node.size;
+
 	vaddr = i915_vma_pin_iomap(vma);
 	if (IS_ERR(vaddr)) {
 		DRM_ERROR("Failed to remap framebuffer into virtual memory\n");
@@ -243,10 +248,6 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->screen_base = vaddr;
 	info->screen_size = vma->node.size;
 
-	/* Our framebuffer is the entirety of fbdev's system memory */
-	info->fix.smem_start = (unsigned long)info->screen_base;
-	info->fix.smem_len = info->screen_size;
-
 	drm_fb_helper_fill_info(info, &ifbdev->helper, sizes);
 
 	/* If the object is shmemfs backed, it will have given us zeroed pages.
diff --git a/drivers/gpu/drm/i915/display/intel_hdcp.c b/drivers/gpu/drm/i915/display/intel_hdcp.c
index e69fa34528df..f1f41ca8402b 100644
--- a/drivers/gpu/drm/i915/display/intel_hdcp.c
+++ b/drivers/gpu/drm/i915/display/intel_hdcp.c
@@ -922,7 +922,7 @@ static void intel_hdcp_prop_work(struct work_struct *work)
 bool is_hdcp_supported(struct drm_i915_private *dev_priv, enum port port)
 {
 	/* PORT E doesn't have HDCP, and PORT F is disabled */
-	return INTEL_GEN(dev_priv) >= 9 && port < PORT_E;
+	return INTEL_INFO(dev_priv)->display.has_hdcp && port < PORT_E;
 }
 
 static int
diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c
index b54ccbb5aad5..f6f5312205c4 100644
--- a/drivers/gpu/drm/i915/display/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/display/intel_hdmi.c
@@ -2626,6 +2626,12 @@ out:
 	if (status != connector_status_connected)
 		cec_notifier_phys_addr_invalidate(intel_hdmi->cec_notifier);
 
+	/*
+	 * Make sure the refs for power wells enabled during detect are
+	 * dropped to avoid a new detect cycle triggered by HPD polling.
+	 */
+	intel_display_power_flush_work(dev_priv);
+
 	return status;
 }
 
@@ -3277,11 +3283,11 @@ void intel_hdmi_init(struct drm_i915_private *dev_priv,
 	intel_encoder->port = port;
 	if (IS_CHERRYVIEW(dev_priv)) {
 		if (port == PORT_D)
-			intel_encoder->crtc_mask = BIT(PIPE_C);
+			intel_encoder->pipe_mask = BIT(PIPE_C);
 		else
-			intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
+			intel_encoder->pipe_mask = BIT(PIPE_A) | BIT(PIPE_B);
 	} else {
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+		intel_encoder->pipe_mask = ~0;
 	}
 	intel_encoder->cloneable = 1 << INTEL_OUTPUT_ANALOG;
 	/*
diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c
index 13841d7c455b..b1bc78623647 100644
--- a/drivers/gpu/drm/i915/display/intel_lvds.c
+++ b/drivers/gpu/drm/i915/display/intel_lvds.c
@@ -899,12 +899,10 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	intel_encoder->power_domain = POWER_DOMAIN_PORT_OTHER;
 	intel_encoder->port = PORT_NONE;
 	intel_encoder->cloneable = 0;
-	if (HAS_PCH_SPLIT(dev_priv))
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
-	else if (IS_GEN(dev_priv, 4))
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
+	if (INTEL_GEN(dev_priv) < 4)
+		intel_encoder->pipe_mask = BIT(PIPE_B);
 	else
-		intel_encoder->crtc_mask = BIT(PIPE_B);
+		intel_encoder->pipe_mask = ~0;
 
 	drm_connector_helper_add(connector, &intel_lvds_connector_helper_funcs);
 	connector->display_info.subpixel_order = SubPixelHorizontalRGB;
diff --git a/drivers/gpu/drm/i915/display/intel_overlay.c b/drivers/gpu/drm/i915/display/intel_overlay.c
index 2360f19f9694..848ce07a8ec2 100644
--- a/drivers/gpu/drm/i915/display/intel_overlay.c
+++ b/drivers/gpu/drm/i915/display/intel_overlay.c
@@ -30,6 +30,7 @@
 #include <drm/i915_drm.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_ring.h"
 
 #include "i915_drv.h"
 #include "i915_reg.h"
diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
index 50f22abcd30e..6a9f322d3fca 100644
--- a/drivers/gpu/drm/i915/display/intel_psr.c
+++ b/drivers/gpu/drm/i915/display/intel_psr.c
@@ -76,7 +76,7 @@ static bool intel_psr2_enabled(struct drm_i915_private *dev_priv,
 			       const struct intel_crtc_state *crtc_state)
 {
 	/* Cannot enable DSC and PSR2 simultaneously */
-	WARN_ON(crtc_state->dsc_params.compression_enable &&
+	WARN_ON(crtc_state->dsc.compression_enable &&
 		crtc_state->has_psr2);
 
 	switch (dev_priv->psr.debug & I915_PSR_DEBUG_MODE_MASK) {
@@ -623,7 +623,7 @@ static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 	 * resolution requires DSC to be enabled, priority is given to DSC
 	 * over PSR2.
 	 */
-	if (crtc_state->dsc_params.compression_enable) {
+	if (crtc_state->dsc.compression_enable) {
 		DRM_DEBUG_KMS("PSR2 cannot be enabled since DSC is enabled\n");
 		return false;
 	}
@@ -740,25 +740,6 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	dev_priv->psr.active = true;
 }
 
-static i915_reg_t gen9_chicken_trans_reg(struct drm_i915_private *dev_priv,
-					 enum transcoder cpu_transcoder)
-{
-	static const i915_reg_t regs[] = {
-		[TRANSCODER_A] = CHICKEN_TRANS_A,
-		[TRANSCODER_B] = CHICKEN_TRANS_B,
-		[TRANSCODER_C] = CHICKEN_TRANS_C,
-		[TRANSCODER_EDP] = CHICKEN_TRANS_EDP,
-	};
-
-	WARN_ON(INTEL_GEN(dev_priv) < 9);
-
-	if (WARN_ON(cpu_transcoder >= ARRAY_SIZE(regs) ||
-		    !regs[cpu_transcoder].reg))
-		cpu_transcoder = TRANSCODER_A;
-
-	return regs[cpu_transcoder];
-}
-
 static void intel_psr_enable_source(struct intel_dp *intel_dp,
 				    const struct intel_crtc_state *crtc_state)
 {
@@ -774,8 +755,7 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 
 	if (dev_priv->psr.psr2_enabled && (IS_GEN(dev_priv, 9) &&
 					   !IS_GEMINILAKE(dev_priv))) {
-		i915_reg_t reg = gen9_chicken_trans_reg(dev_priv,
-							cpu_transcoder);
+		i915_reg_t reg = CHICKEN_TRANS(cpu_transcoder);
 		u32 chicken = I915_READ(reg);
 
 		chicken |= PSR2_VSC_ENABLE_PROG_HEADER |
@@ -1437,7 +1417,7 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 	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");
+		DRM_DEBUG_KMS("PSR Link CRC error, disabling PSR\n");
 
 	if (val & ~errors)
 		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c
index 47f5d87a938a..5b7f4baf7348 100644
--- a/drivers/gpu/drm/i915/display/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/display/intel_sdvo.c
@@ -2921,7 +2921,7 @@ intel_sdvo_output_setup(struct intel_sdvo *intel_sdvo, u16 flags)
 			      bytes[0], bytes[1]);
 		return false;
 	}
-	intel_sdvo->base.crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+	intel_sdvo->base.pipe_mask = ~0;
 
 	return true;
 }
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index 5ae12ab3c5b7..72fda0430062 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -322,6 +322,55 @@ bool icl_is_hdr_plane(struct drm_i915_private *dev_priv, enum plane_id plane_id)
 		icl_hdr_plane_mask() & BIT(plane_id);
 }
 
+static void
+skl_plane_ratio(const struct intel_crtc_state *crtc_state,
+		const struct intel_plane_state *plane_state,
+		unsigned int *num, unsigned int *den)
+{
+	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+
+	if (fb->format->cpp[0] == 8) {
+		if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv)) {
+			*num = 10;
+			*den = 8;
+		} else {
+			*num = 9;
+			*den = 8;
+		}
+	} else {
+		*num = 1;
+		*den = 1;
+	}
+}
+
+static int skl_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			       const struct intel_plane_state *plane_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(plane_state->base.plane->dev);
+	unsigned int pixel_rate = crtc_state->pixel_rate;
+	unsigned int src_w, src_h, dst_w, dst_h;
+	unsigned int num, den;
+
+	skl_plane_ratio(crtc_state, plane_state, &num, &den);
+
+	/* two pixels per clock on glk+ */
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv))
+		den *= 2;
+
+	src_w = drm_rect_width(&plane_state->base.src) >> 16;
+	src_h = drm_rect_height(&plane_state->base.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->base.dst);
+	dst_h = drm_rect_height(&plane_state->base.dst);
+
+	/* Downscaling limits the maximum pixel rate */
+	dst_w = min(src_w, dst_w);
+	dst_h = min(src_h, dst_h);
+
+	return DIV64_U64_ROUND_UP(mul_u32_u32(pixel_rate * num, src_w * src_h),
+				  mul_u32_u32(den, dst_w * dst_h));
+}
+
 static unsigned int
 skl_plane_max_stride(struct intel_plane *plane,
 		     u32 pixel_format, u64 modifier,
@@ -811,6 +860,85 @@ vlv_update_clrc(const struct intel_plane_state *plane_state)
 		      SP_SH_SIN(sh_sin) | SP_SH_COS(sh_cos));
 }
 
+static void
+vlv_plane_ratio(const struct intel_crtc_state *crtc_state,
+		const struct intel_plane_state *plane_state,
+		unsigned int *num, unsigned int *den)
+{
+	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int cpp = fb->format->cpp[0];
+
+	/*
+	 * VLV bspec only considers cases where all three planes are
+	 * enabled, and cases where the primary and one sprite is enabled.
+	 * Let's assume the case with just two sprites enabled also
+	 * maps to the latter case.
+	 */
+	if (hweight8(active_planes) == 3) {
+		switch (cpp) {
+		case 8:
+			*num = 11;
+			*den = 8;
+			break;
+		case 4:
+			*num = 18;
+			*den = 16;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	} else if (hweight8(active_planes) == 2) {
+		switch (cpp) {
+		case 8:
+			*num = 10;
+			*den = 8;
+			break;
+		case 4:
+			*num = 17;
+			*den = 16;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	} else {
+		switch (cpp) {
+		case 8:
+			*num = 10;
+			*den = 8;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	}
+}
+
+int vlv_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			const struct intel_plane_state *plane_state)
+{
+	unsigned int pixel_rate;
+	unsigned int num, den;
+
+	/*
+	 * Note that crtc_state->pixel_rate accounts for both
+	 * horizontal and vertical panel fitter downscaling factors.
+	 * Pre-HSW bspec tells us to only consider the horizontal
+	 * downscaling factor here. We ignore that and just consider
+	 * both for simplicity.
+	 */
+	pixel_rate = crtc_state->pixel_rate;
+
+	vlv_plane_ratio(crtc_state, plane_state, &num, &den);
+
+	return DIV_ROUND_UP(pixel_rate * num, den);
+}
+
 static u32 vlv_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
 	u32 sprctl = 0;
@@ -1017,6 +1145,164 @@ vlv_plane_get_hw_state(struct intel_plane *plane,
 	return ret;
 }
 
+static void ivb_plane_ratio(const struct intel_crtc_state *crtc_state,
+			    const struct intel_plane_state *plane_state,
+			    unsigned int *num, unsigned int *den)
+{
+	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int cpp = fb->format->cpp[0];
+
+	if (hweight8(active_planes) == 2) {
+		switch (cpp) {
+		case 8:
+			*num = 10;
+			*den = 8;
+			break;
+		case 4:
+			*num = 17;
+			*den = 16;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	} else {
+		switch (cpp) {
+		case 8:
+			*num = 9;
+			*den = 8;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	}
+}
+
+static void ivb_plane_ratio_scaling(const struct intel_crtc_state *crtc_state,
+				    const struct intel_plane_state *plane_state,
+				    unsigned int *num, unsigned int *den)
+{
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int cpp = fb->format->cpp[0];
+
+	switch (cpp) {
+	case 8:
+		*num = 12;
+		*den = 8;
+		break;
+	case 4:
+		*num = 19;
+		*den = 16;
+		break;
+	case 2:
+		*num = 33;
+		*den = 32;
+		break;
+	default:
+		*num = 1;
+		*den = 1;
+		break;
+	}
+}
+
+int ivb_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			const struct intel_plane_state *plane_state)
+{
+	unsigned int pixel_rate;
+	unsigned int num, den;
+
+	/*
+	 * Note that crtc_state->pixel_rate accounts for both
+	 * horizontal and vertical panel fitter downscaling factors.
+	 * Pre-HSW bspec tells us to only consider the horizontal
+	 * downscaling factor here. We ignore that and just consider
+	 * both for simplicity.
+	 */
+	pixel_rate = crtc_state->pixel_rate;
+
+	ivb_plane_ratio(crtc_state, plane_state, &num, &den);
+
+	return DIV_ROUND_UP(pixel_rate * num, den);
+}
+
+static int ivb_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
+				const struct intel_plane_state *plane_state)
+{
+	unsigned int src_w, dst_w, pixel_rate;
+	unsigned int num, den;
+
+	/*
+	 * Note that crtc_state->pixel_rate accounts for both
+	 * horizontal and vertical panel fitter downscaling factors.
+	 * Pre-HSW bspec tells us to only consider the horizontal
+	 * downscaling factor here. We ignore that and just consider
+	 * both for simplicity.
+	 */
+	pixel_rate = crtc_state->pixel_rate;
+
+	src_w = drm_rect_width(&plane_state->base.src) >> 16;
+	dst_w = drm_rect_width(&plane_state->base.dst);
+
+	if (src_w != dst_w)
+		ivb_plane_ratio_scaling(crtc_state, plane_state, &num, &den);
+	else
+		ivb_plane_ratio(crtc_state, plane_state, &num, &den);
+
+	/* Horizontal downscaling limits the maximum pixel rate */
+	dst_w = min(src_w, dst_w);
+
+	return DIV_ROUND_UP_ULL(mul_u32_u32(pixel_rate, num * src_w),
+				den * dst_w);
+}
+
+static void hsw_plane_ratio(const struct intel_crtc_state *crtc_state,
+			    const struct intel_plane_state *plane_state,
+			    unsigned int *num, unsigned int *den)
+{
+	u8 active_planes = crtc_state->active_planes & ~BIT(PLANE_CURSOR);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int cpp = fb->format->cpp[0];
+
+	if (hweight8(active_planes) == 2) {
+		switch (cpp) {
+		case 8:
+			*num = 10;
+			*den = 8;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	} else {
+		switch (cpp) {
+		case 8:
+			*num = 9;
+			*den = 8;
+			break;
+		default:
+			*num = 1;
+			*den = 1;
+			break;
+		}
+	}
+}
+
+int hsw_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			const struct intel_plane_state *plane_state)
+{
+	unsigned int pixel_rate = crtc_state->pixel_rate;
+	unsigned int num, den;
+
+	hsw_plane_ratio(crtc_state, plane_state, &num, &den);
+
+	return DIV_ROUND_UP(pixel_rate * num, den);
+}
+
 static u32 ivb_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 {
 	u32 sprctl = 0;
@@ -1030,6 +1316,16 @@ static u32 ivb_sprite_ctl_crtc(const struct intel_crtc_state *crtc_state)
 	return sprctl;
 }
 
+static bool ivb_need_sprite_gamma(const struct intel_plane_state *plane_state)
+{
+	struct drm_i915_private *dev_priv =
+		to_i915(plane_state->base.plane->dev);
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+
+	return fb->format->cpp[0] == 8 &&
+		(IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv));
+}
+
 static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 			  const struct intel_plane_state *plane_state)
 {
@@ -1052,6 +1348,12 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB8888:
 		sprctl |= SPRITE_FORMAT_RGBX888;
 		break;
+	case DRM_FORMAT_XBGR16161616F:
+		sprctl |= SPRITE_FORMAT_RGBX161616 | SPRITE_RGB_ORDER_RGBX;
+		break;
+	case DRM_FORMAT_XRGB16161616F:
+		sprctl |= SPRITE_FORMAT_RGBX161616;
+		break;
 	case DRM_FORMAT_YUYV:
 		sprctl |= SPRITE_FORMAT_YUV422 | SPRITE_YUV_ORDER_YUYV;
 		break;
@@ -1069,7 +1371,8 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 		return 0;
 	}
 
-	sprctl |= SPRITE_INT_GAMMA_DISABLE;
+	if (!ivb_need_sprite_gamma(plane_state))
+		sprctl |= SPRITE_INT_GAMMA_DISABLE;
 
 	if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 		sprctl |= SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709;
@@ -1091,12 +1394,26 @@ static u32 ivb_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	return sprctl;
 }
 
-static void ivb_sprite_linear_gamma(u16 gamma[18])
+static void ivb_sprite_linear_gamma(const struct intel_plane_state *plane_state,
+				    u16 gamma[18])
 {
-	int i;
+	int scale, i;
 
-	for (i = 0; i < 17; i++)
-		gamma[i] = (i << 10) / 16;
+	/*
+	 * WaFP16GammaEnabling:ivb,hsw
+	 * "Workaround : When using the 64-bit format, the sprite output
+	 *  on each color channel has one quarter amplitude. It can be
+	 *  brought up to full amplitude by using sprite internal gamma
+	 *  correction, pipe gamma correction, or pipe color space
+	 *  conversion to multiply the sprite output by four."
+	 */
+	scale = 4;
+
+	for (i = 0; i < 16; i++)
+		gamma[i] = min((scale * i << 10) / 16, (1 << 10) - 1);
+
+	gamma[i] = min((scale * i << 10) / 16, 1 << 10);
+	i++;
 
 	gamma[i] = 3 << 10;
 	i++;
@@ -1110,7 +1427,10 @@ static void ivb_update_gamma(const struct intel_plane_state *plane_state)
 	u16 gamma[18];
 	int i;
 
-	ivb_sprite_linear_gamma(gamma);
+	if (!ivb_need_sprite_gamma(plane_state))
+		return;
+
+	ivb_sprite_linear_gamma(plane_state, gamma);
 
 	/* FIXME these register are single buffered :( */
 	for (i = 0; i < 16; i++)
@@ -1243,6 +1563,53 @@ ivb_plane_get_hw_state(struct intel_plane *plane,
 	return ret;
 }
 
+static int g4x_sprite_min_cdclk(const struct intel_crtc_state *crtc_state,
+				const struct intel_plane_state *plane_state)
+{
+	const struct drm_framebuffer *fb = plane_state->base.fb;
+	unsigned int hscale, pixel_rate;
+	unsigned int limit, decimate;
+
+	/*
+	 * Note that crtc_state->pixel_rate accounts for both
+	 * horizontal and vertical panel fitter downscaling factors.
+	 * Pre-HSW bspec tells us to only consider the horizontal
+	 * downscaling factor here. We ignore that and just consider
+	 * both for simplicity.
+	 */
+	pixel_rate = crtc_state->pixel_rate;
+
+	/* Horizontal downscaling limits the maximum pixel rate */
+	hscale = drm_rect_calc_hscale(&plane_state->base.src,
+				      &plane_state->base.dst,
+				      0, INT_MAX);
+	if (hscale < 0x10000)
+		return pixel_rate;
+
+	/* Decimation steps at 2x,4x,8x,16x */
+	decimate = ilog2(hscale >> 16);
+	hscale >>= decimate;
+
+	/* Starting limit is 90% of cdclk */
+	limit = 9;
+
+	/* -10% per decimation step */
+	limit -= decimate;
+
+	/* -10% for RGB */
+	if (fb->format->cpp[0] >= 4)
+		limit--; /* -10% for RGB */
+
+	/*
+	 * We should also do -10% if sprite scaling is enabled
+	 * on the other pipe, but we can't really check for that,
+	 * so we ignore it.
+	 */
+
+	return DIV_ROUND_UP_ULL(mul_u32_u32(pixel_rate, 10 * hscale),
+				limit << 16);
+}
+
 static unsigned int
 g4x_sprite_max_stride(struct intel_plane *plane,
 		      u32 pixel_format, u64 modifier,
@@ -1286,6 +1653,12 @@ static u32 g4x_sprite_ctl(const struct intel_crtc_state *crtc_state,
 	case DRM_FORMAT_XRGB8888:
 		dvscntr |= DVS_FORMAT_RGBX888;
 		break;
+	case DRM_FORMAT_XBGR16161616F:
+		dvscntr |= DVS_FORMAT_RGBX161616 | DVS_RGB_ORDER_XBGR;
+		break;
+	case DRM_FORMAT_XRGB16161616F:
+		dvscntr |= DVS_FORMAT_RGBX161616;
+		break;
 	case DRM_FORMAT_YUYV:
 		dvscntr |= DVS_FORMAT_YUV422 | DVS_YUV_ORDER_YUYV;
 		break;
@@ -1499,6 +1872,11 @@ static bool intel_fb_scalable(const struct drm_framebuffer *fb)
 	switch (fb->format->format) {
 	case DRM_FORMAT_C8:
 		return false;
+	case DRM_FORMAT_XRGB16161616F:
+	case DRM_FORMAT_ARGB16161616F:
+	case DRM_FORMAT_XBGR16161616F:
+	case DRM_FORMAT_ABGR16161616F:
+		return INTEL_GEN(to_i915(fb->dev)) >= 11;
 	default:
 		return true;
 	}
@@ -1787,6 +2165,22 @@ static int skl_plane_check_nv12_rotation(const struct intel_plane_state *plane_s
 	return 0;
 }
 
+static int skl_plane_max_scale(struct drm_i915_private *dev_priv,
+			       const struct drm_framebuffer *fb)
+{
+	/*
+	 * We don't yet know the final source width nor
+	 * whether we can use the HQ scaler mode. Assume
+	 * the best case.
+	 * FIXME need to properly check this later.
+	 */
+	if (INTEL_GEN(dev_priv) >= 10 || IS_GEMINILAKE(dev_priv) ||
+	    !drm_format_info_is_yuv_semiplanar(fb->format))
+		return 0x30000 - 1;
+	else
+		return 0x20000 - 1;
+}
+
 static int skl_plane_check(struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *plane_state)
 {
@@ -1804,7 +2198,7 @@ static int skl_plane_check(struct intel_crtc_state *crtc_state,
 	/* use scaler when colorkey is not required */
 	if (!plane_state->ckey.flags && intel_fb_scalable(fb)) {
 		min_scale = 1;
-		max_scale = skl_max_scale(crtc_state, fb->format);
+		max_scale = skl_plane_max_scale(dev_priv, fb);
 	}
 
 	ret = drm_atomic_helper_check_plane_state(&plane_state->base,
@@ -1979,8 +2373,10 @@ static const u64 i9xx_plane_format_modifiers[] = {
 };
 
 static const u32 snb_plane_formats[] = {
-	DRM_FORMAT_XBGR8888,
 	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_XRGB16161616F,
+	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2010,6 +2406,8 @@ static const u32 skl_plane_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_XRGB16161616F,
+	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2025,6 +2423,8 @@ static const u32 skl_planar_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_XRGB16161616F,
+	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2041,6 +2441,8 @@ static const u32 glk_planar_formats[] = {
 	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_XRGB2101010,
 	DRM_FORMAT_XBGR2101010,
+	DRM_FORMAT_XRGB16161616F,
+	DRM_FORMAT_XBGR16161616F,
 	DRM_FORMAT_YUYV,
 	DRM_FORMAT_YVYU,
 	DRM_FORMAT_UYVY,
@@ -2191,6 +2593,8 @@ static bool snb_sprite_format_mod_supported(struct drm_plane *_plane,
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_XRGB16161616F:
+	case DRM_FORMAT_XBGR16161616F:
 	case DRM_FORMAT_YUYV:
 	case DRM_FORMAT_YVYU:
 	case DRM_FORMAT_UYVY:
@@ -2481,7 +2885,7 @@ struct intel_plane *
 skl_universal_plane_create(struct drm_i915_private *dev_priv,
 			   enum pipe pipe, enum plane_id plane_id)
 {
-	static const struct drm_plane_funcs *plane_funcs;
+	const struct drm_plane_funcs *plane_funcs;
 	struct intel_plane *plane;
 	enum drm_plane_type plane_type;
 	unsigned int supported_rotations;
@@ -2511,6 +2915,7 @@ skl_universal_plane_create(struct drm_i915_private *dev_priv,
 	plane->disable_plane = skl_disable_plane;
 	plane->get_hw_state = skl_plane_get_hw_state;
 	plane->check_plane = skl_plane_check;
+	plane->min_cdclk = skl_plane_min_cdclk;
 	if (icl_is_nv12_y_plane(plane_id))
 		plane->update_slave = icl_update_slave;
 
@@ -2618,6 +3023,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane->disable_plane = vlv_disable_plane;
 		plane->get_hw_state = vlv_plane_get_hw_state;
 		plane->check_plane = vlv_sprite_check;
+		plane->min_cdclk = vlv_plane_min_cdclk;
 
 		formats = vlv_plane_formats;
 		num_formats = ARRAY_SIZE(vlv_plane_formats);
@@ -2631,6 +3037,11 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane->get_hw_state = ivb_plane_get_hw_state;
 		plane->check_plane = g4x_sprite_check;
 
+		if (IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv))
+			plane->min_cdclk = hsw_plane_min_cdclk;
+		else
+			plane->min_cdclk = ivb_sprite_min_cdclk;
+
 		formats = snb_plane_formats;
 		num_formats = ARRAY_SIZE(snb_plane_formats);
 		modifiers = i9xx_plane_format_modifiers;
@@ -2642,6 +3053,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane->disable_plane = g4x_disable_plane;
 		plane->get_hw_state = g4x_plane_get_hw_state;
 		plane->check_plane = g4x_sprite_check;
+		plane->min_cdclk = g4x_sprite_min_cdclk;
 
 		modifiers = i9xx_plane_format_modifiers;
 		if (IS_GEN(dev_priv, 6)) {
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.h b/drivers/gpu/drm/i915/display/intel_sprite.h
index 229336214f68..5eeaa92420d1 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.h
+++ b/drivers/gpu/drm/i915/display/intel_sprite.h
@@ -49,4 +49,11 @@ static inline u8 icl_hdr_plane_mask(void)
 
 bool icl_is_hdr_plane(struct drm_i915_private *dev_priv, enum plane_id plane_id);
 
+int ivb_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			const struct intel_plane_state *plane_state);
+int hsw_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			const struct intel_plane_state *plane_state);
+int vlv_plane_min_cdclk(const struct intel_crtc_state *crtc_state,
+			const struct intel_plane_state *plane_state);
+
 #endif /* __INTEL_SPRITE_H__ */
diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c
index 70726b481244..9983fadf6c28 100644
--- a/drivers/gpu/drm/i915/display/intel_tv.c
+++ b/drivers/gpu/drm/i915/display/intel_tv.c
@@ -1701,7 +1701,7 @@ intel_tv_detect(struct drm_connector *connector,
 		struct intel_load_detect_pipe tmp;
 		int ret;
 
-		ret = intel_get_load_detect_pipe(connector, NULL, &tmp, ctx);
+		ret = intel_get_load_detect_pipe(connector, &tmp, ctx);
 		if (ret < 0)
 			return ret;
 
@@ -1947,7 +1947,7 @@ intel_tv_init(struct drm_i915_private *dev_priv)
 	intel_encoder->type = INTEL_OUTPUT_TVOUT;
 	intel_encoder->power_domain = POWER_DOMAIN_PORT_OTHER;
 	intel_encoder->port = PORT_NONE;
-	intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B);
+	intel_encoder->pipe_mask = ~0;
 	intel_encoder->cloneable = 0;
 	intel_tv->type = DRM_MODE_CONNECTOR_Unknown;
 
diff --git a/drivers/gpu/drm/i915/display/intel_vbt_defs.h b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
index e3045ced4bfe..69a7cb1fa121 100644
--- a/drivers/gpu/drm/i915/display/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/display/intel_vbt_defs.h
@@ -114,6 +114,7 @@ enum bdb_block_id {
 	BDB_LVDS_POWER			= 44,
 	BDB_MIPI_CONFIG			= 52,
 	BDB_MIPI_SEQUENCE		= 53,
+	BDB_COMPRESSION_PARAMETERS	= 56,
 	BDB_SKIP			= 254, /* VBIOS private block, ignore */
 };
 
@@ -811,4 +812,55 @@ struct bdb_mipi_sequence {
 	u8 data[0]; /* up to 6 variable length blocks */
 } __packed;
 
+/*
+ * Block 56 - Compression Parameters
+ */
+
+#define VBT_RC_BUFFER_BLOCK_SIZE_1KB	0
+#define VBT_RC_BUFFER_BLOCK_SIZE_4KB	1
+#define VBT_RC_BUFFER_BLOCK_SIZE_16KB	2
+#define VBT_RC_BUFFER_BLOCK_SIZE_64KB	3
+
+#define VBT_DSC_LINE_BUFFER_DEPTH(vbt_value)	((vbt_value) + 8) /* bits */
+#define VBT_DSC_MAX_BPP(vbt_value)		(6 + (vbt_value) * 2)
+
+struct dsc_compression_parameters_entry {
+	u8 version_major:4;
+	u8 version_minor:4;
+
+	u8 rc_buffer_block_size:2;
+	u8 reserved1:6;
+
+	/*
+	 * Buffer size in bytes:
+	 *
+	 * 4 ^ rc_buffer_block_size * 1024 * (rc_buffer_size + 1) bytes
+	 */
+	u8 rc_buffer_size;
+	u32 slices_per_line;
+
+	u8 line_buffer_depth:4;
+	u8 reserved2:4;
+
+	/* Flag Bits 1 */
+	u8 block_prediction_enable:1;
+	u8 reserved3:7;
+
+	u8 max_bpp; /* mapping */
+
+	/* Color depth capabilities */
+	u8 reserved4:1;
+	u8 support_8bpc:1;
+	u8 support_10bpc:1;
+	u8 support_12bpc:1;
+	u8 reserved5:4;
+
+	u16 slice_height;
+} __packed;
+
+struct bdb_compression_parameters {
+	u16 entry_size;
+	struct dsc_compression_parameters_entry data[16];
+} __packed;
+
 #endif /* _INTEL_VBT_DEFS_H_ */
diff --git a/drivers/gpu/drm/i915/display/intel_vdsc.c b/drivers/gpu/drm/i915/display/intel_vdsc.c
index d4fb7f16f9f6..896b0c334f5e 100644
--- a/drivers/gpu/drm/i915/display/intel_vdsc.c
+++ b/drivers/gpu/drm/i915/display/intel_vdsc.c
@@ -322,8 +322,8 @@ static int get_column_index_for_rc_params(u8 bits_per_component)
 int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
 				struct intel_crtc_state *pipe_config)
 {
-	struct drm_dsc_config *vdsc_cfg = &pipe_config->dp_dsc_cfg;
-	u16 compressed_bpp = pipe_config->dsc_params.compressed_bpp;
+	struct drm_dsc_config *vdsc_cfg = &pipe_config->dsc.config;
+	u16 compressed_bpp = pipe_config->dsc.compressed_bpp;
 	u8 i = 0;
 	int row_index = 0;
 	int column_index = 0;
@@ -332,7 +332,7 @@ int intel_dp_compute_dsc_params(struct intel_dp *intel_dp,
 	vdsc_cfg->pic_width = pipe_config->base.adjusted_mode.crtc_hdisplay;
 	vdsc_cfg->pic_height = pipe_config->base.adjusted_mode.crtc_vdisplay;
 	vdsc_cfg->slice_width = DIV_ROUND_UP(vdsc_cfg->pic_width,
-					     pipe_config->dsc_params.slice_count);
+					     pipe_config->dsc.slice_count);
 	/*
 	 * Slice Height of 8 works for all currently available panels. So start
 	 * with that if pic_height is an integral multiple of 8.
@@ -485,13 +485,13 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dp_dsc_cfg;
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	enum pipe pipe = crtc->pipe;
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	u32 pps_val = 0;
 	u32 rc_buf_thresh_dword[4];
 	u32 rc_range_params_dword[8];
-	u8 num_vdsc_instances = (crtc_state->dsc_params.dsc_split) ? 2 : 1;
+	u8 num_vdsc_instances = (crtc_state->dsc.dsc_split) ? 2 : 1;
 	int i = 0;
 
 	/* Populate PICTURE_PARAMETER_SET_0 registers */
@@ -514,11 +514,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_0, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_0(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe),
 				   pps_val);
 	}
@@ -533,11 +533,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_1, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_1(pipe),
 				   pps_val);
 	}
@@ -553,11 +553,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_2, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_2(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_2(pipe),
 				   pps_val);
 	}
@@ -573,11 +573,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_3, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_3(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_3(pipe),
 				   pps_val);
 	}
@@ -593,11 +593,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_4, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_4(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe),
 				   pps_val);
 	}
@@ -613,11 +613,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_5, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_5(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe),
 				   pps_val);
 	}
@@ -635,11 +635,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_6, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_6(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_6(pipe),
 				   pps_val);
 	}
@@ -655,11 +655,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_7, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_7(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_7(pipe),
 				   pps_val);
 	}
@@ -675,11 +675,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_8, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_8(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_8(pipe),
 				   pps_val);
 	}
@@ -695,11 +695,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_9, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_9(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_9(pipe),
 				   pps_val);
 	}
@@ -717,11 +717,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_10, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_10(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_10(pipe),
 				   pps_val);
 	}
@@ -740,11 +740,11 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		 * If 2 VDSC instances are needed, configure PPS for second
 		 * VDSC
 		 */
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(DSCC_PICTURE_PARAMETER_SET_16, pps_val);
 	} else {
 		I915_WRITE(ICL_DSC0_PICTURE_PARAMETER_SET_16(pipe), pps_val);
-		if (crtc_state->dsc_params.dsc_split)
+		if (crtc_state->dsc.dsc_split)
 			I915_WRITE(ICL_DSC1_PICTURE_PARAMETER_SET_16(pipe),
 				   pps_val);
 	}
@@ -763,7 +763,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 		I915_WRITE(DSCA_RC_BUF_THRESH_0_UDW, rc_buf_thresh_dword[1]);
 		I915_WRITE(DSCA_RC_BUF_THRESH_1, rc_buf_thresh_dword[2]);
 		I915_WRITE(DSCA_RC_BUF_THRESH_1_UDW, rc_buf_thresh_dword[3]);
-		if (crtc_state->dsc_params.dsc_split) {
+		if (crtc_state->dsc.dsc_split) {
 			I915_WRITE(DSCC_RC_BUF_THRESH_0,
 				   rc_buf_thresh_dword[0]);
 			I915_WRITE(DSCC_RC_BUF_THRESH_0_UDW,
@@ -782,7 +782,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 			   rc_buf_thresh_dword[2]);
 		I915_WRITE(ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe),
 			   rc_buf_thresh_dword[3]);
-		if (crtc_state->dsc_params.dsc_split) {
+		if (crtc_state->dsc.dsc_split) {
 			I915_WRITE(ICL_DSC1_RC_BUF_THRESH_0(pipe),
 				   rc_buf_thresh_dword[0]);
 			I915_WRITE(ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe),
@@ -824,7 +824,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 			   rc_range_params_dword[6]);
 		I915_WRITE(DSCA_RC_RANGE_PARAMETERS_3_UDW,
 			   rc_range_params_dword[7]);
-		if (crtc_state->dsc_params.dsc_split) {
+		if (crtc_state->dsc.dsc_split) {
 			I915_WRITE(DSCC_RC_RANGE_PARAMETERS_0,
 				   rc_range_params_dword[0]);
 			I915_WRITE(DSCC_RC_RANGE_PARAMETERS_0_UDW,
@@ -859,7 +859,7 @@ static void intel_configure_pps_for_dsc_encoder(struct intel_encoder *encoder,
 			   rc_range_params_dword[6]);
 		I915_WRITE(ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe),
 			   rc_range_params_dword[7]);
-		if (crtc_state->dsc_params.dsc_split) {
+		if (crtc_state->dsc.dsc_split) {
 			I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe),
 				   rc_range_params_dword[0]);
 			I915_WRITE(ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe),
@@ -885,7 +885,7 @@ static void intel_dp_write_dsc_pps_sdp(struct intel_encoder *encoder,
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dp_dsc_cfg;
+	const struct drm_dsc_config *vdsc_cfg = &crtc_state->dsc.config;
 	struct drm_dsc_pps_infoframe dp_dsc_pps_sdp;
 
 	/* Prepare DP SDP PPS header as per DP 1.4 spec, Table 2-123 */
@@ -909,7 +909,7 @@ void intel_dsc_enable(struct intel_encoder *encoder,
 	u32 dss_ctl1_val = 0;
 	u32 dss_ctl2_val = 0;
 
-	if (!crtc_state->dsc_params.compression_enable)
+	if (!crtc_state->dsc.compression_enable)
 		return;
 
 	/* Enable Power wells for VDSC/joining */
@@ -928,7 +928,7 @@ void intel_dsc_enable(struct intel_encoder *encoder,
 		dss_ctl2_reg = ICL_PIPE_DSS_CTL2(pipe);
 	}
 	dss_ctl2_val |= LEFT_BRANCH_VDSC_ENABLE;
-	if (crtc_state->dsc_params.dsc_split) {
+	if (crtc_state->dsc.dsc_split) {
 		dss_ctl2_val |= RIGHT_BRANCH_VDSC_ENABLE;
 		dss_ctl1_val |= JOINER_ENABLE;
 	}
@@ -944,7 +944,7 @@ void intel_dsc_disable(const struct intel_crtc_state *old_crtc_state)
 	i915_reg_t dss_ctl1_reg, dss_ctl2_reg;
 	u32 dss_ctl1_val = 0, dss_ctl2_val = 0;
 
-	if (!old_crtc_state->dsc_params.compression_enable)
+	if (!old_crtc_state->dsc.compression_enable)
 		return;
 
 	if (old_crtc_state->cpu_transcoder == TRANSCODER_EDP) {
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index 50064cde0724..0ca49b1604c6 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -1870,11 +1870,11 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 	 * port C. BXT isn't limited like this.
 	 */
 	if (IS_GEN9_LP(dev_priv))
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+		intel_encoder->pipe_mask = ~0;
 	else if (port == PORT_A)
-		intel_encoder->crtc_mask = BIT(PIPE_A);
+		intel_encoder->pipe_mask = BIT(PIPE_A);
 	else
-		intel_encoder->crtc_mask = BIT(PIPE_B);
+		intel_encoder->pipe_mask = BIT(PIPE_B);
 
 	if (dev_priv->vbt.dsi.config->dual_link)
 		intel_dsi->ports = BIT(PORT_A) | BIT(PORT_C);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 7b01f4605f21..255ab040022e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -69,8 +69,10 @@
 
 #include <drm/i915_drm.h>
 
-#include "gt/intel_lrc_reg.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_engine_user.h"
+#include "gt/intel_lrc_reg.h"
+#include "gt/intel_ring.h"
 
 #include "i915_gem_context.h"
 #include "i915_globals.h"
@@ -234,6 +236,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	free_engines(rcu_access_pointer(ctx->engines));
 	mutex_destroy(&ctx->engines_mutex);
 
+	kfree(ctx->jump_whitelist);
+
 	if (ctx->timeline)
 		intel_timeline_put(ctx->timeline);
 
@@ -276,6 +280,153 @@ void i915_gem_context_release(struct kref *ref)
 		schedule_work(&gc->free_work);
 }
 
+static inline struct i915_gem_engines *
+__context_engines_static(const struct i915_gem_context *ctx)
+{
+	return rcu_dereference_protected(ctx->engines, true);
+}
+
+static bool __reset_engine(struct intel_engine_cs *engine)
+{
+	struct intel_gt *gt = engine->gt;
+	bool success = false;
+
+	if (!intel_has_reset_engine(gt))
+		return false;
+
+	if (!test_and_set_bit(I915_RESET_ENGINE + engine->id,
+			      &gt->reset.flags)) {
+		success = intel_engine_reset(engine, NULL) == 0;
+		clear_and_wake_up_bit(I915_RESET_ENGINE + engine->id,
+				      &gt->reset.flags);
+	}
+
+	return success;
+}
+
+static void __reset_context(struct i915_gem_context *ctx,
+			    struct intel_engine_cs *engine)
+{
+	intel_gt_handle_error(engine->gt, engine->mask, 0,
+			      "context closure in %s", ctx->name);
+}
+
+static bool __cancel_engine(struct intel_engine_cs *engine)
+{
+	/*
+	 * Send a "high priority pulse" down the engine to cause the
+	 * current request to be momentarily preempted. (If it fails to
+	 * be preempted, it will be reset). As we have marked our context
+	 * as banned, any incomplete request, including any running, will
+	 * be skipped following the preemption.
+	 *
+	 * If there is no hangchecking (one of the reasons why we try to
+	 * cancel the context) and no forced preemption, there may be no
+	 * means by which we reset the GPU and evict the persistent hog.
+	 * Ergo if we are unable to inject a preemptive pulse that can
+	 * kill the banned context, we fallback to doing a local reset
+	 * instead.
+	 */
+	if (IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT) &&
+	    !intel_engine_pulse(engine))
+		return true;
+
+	/* If we are unable to send a pulse, try resetting this engine. */
+	return __reset_engine(engine);
+}
+
+static struct intel_engine_cs *__active_engine(struct i915_request *rq)
+{
+	struct intel_engine_cs *engine, *locked;
+
+	/*
+	 * Serialise with __i915_request_submit() so that it sees
+	 * is-banned?, or we know the request is already inflight.
+	 */
+	locked = READ_ONCE(rq->engine);
+	spin_lock_irq(&locked->active.lock);
+	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
+		spin_unlock(&locked->active.lock);
+		spin_lock(&engine->active.lock);
+		locked = engine;
+	}
+
+	engine = NULL;
+	if (i915_request_is_active(rq) && !rq->fence.error)
+		engine = rq->engine;
+
+	spin_unlock_irq(&locked->active.lock);
+
+	return engine;
+}
+
+static struct intel_engine_cs *active_engine(struct intel_context *ce)
+{
+	struct intel_engine_cs *engine = NULL;
+	struct i915_request *rq;
+
+	if (!ce->timeline)
+		return NULL;
+
+	rcu_read_lock();
+	list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
+		if (i915_request_completed(rq))
+			break;
+
+		/* Check with the backend if the request is inflight */
+		engine = __active_engine(rq);
+		if (engine)
+			break;
+	}
+	rcu_read_unlock();
+
+	return engine;
+}
+
+static void kill_context(struct i915_gem_context *ctx)
+{
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
+
+	/*
+	 * If we are already banned, it was due to a guilty request causing
+	 * a reset and the entire context being evicted from the GPU.
+	 */
+	if (i915_gem_context_is_banned(ctx))
+		return;
+
+	i915_gem_context_set_banned(ctx);
+
+	/*
+	 * Map the user's engine back to the actual engines; one virtual
+	 * engine will be mapped to multiple engines, and using ctx->engine[]
+	 * the same engine may be have multiple instances in the user's map.
+	 * However, we only care about pending requests, so only include
+	 * engines on which there are incomplete requests.
+	 */
+	for_each_gem_engine(ce, __context_engines_static(ctx), it) {
+		struct intel_engine_cs *engine;
+
+		/*
+		 * Check the current active state of this context; if we
+		 * are currently executing on the GPU we need to evict
+		 * ourselves. On the other hand, if we haven't yet been
+		 * submitted to the GPU or if everything is complete,
+		 * we have nothing to do.
+		 */
+		engine = active_engine(ce);
+
+		/* First attempt to gracefully cancel the context */
+		if (engine && !__cancel_engine(engine))
+			/*
+			 * If we are unable to send a preemptive pulse to bump
+			 * the context from the GPU, we have to resort to a full
+			 * reset. We hope the collateral damage is worth it.
+			 */
+			__reset_context(ctx, engine);
+	}
+}
+
 static void context_close(struct i915_gem_context *ctx)
 {
 	struct i915_address_space *vm;
@@ -298,9 +449,47 @@ static void context_close(struct i915_gem_context *ctx)
 	lut_close(ctx);
 
 	mutex_unlock(&ctx->mutex);
+
+	/*
+	 * If the user has disabled hangchecking, we can not be sure that
+	 * the batches will ever complete after the context is closed,
+	 * keeping the context and all resources pinned forever. So in this
+	 * case we opt to forcibly kill off all remaining requests on
+	 * context close.
+	 */
+	if (!i915_gem_context_is_persistent(ctx) ||
+	    !i915_modparams.enable_hangcheck)
+		kill_context(ctx);
+
 	i915_gem_context_put(ctx);
 }
 
+static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
+{
+	if (i915_gem_context_is_persistent(ctx) == state)
+		return 0;
+
+	if (state) {
+		/*
+		 * Only contexts that are short-lived [that will expire or be
+		 * reset] are allowed to survive past termination. We require
+		 * hangcheck to ensure that the persistent requests are healthy.
+		 */
+		if (!i915_modparams.enable_hangcheck)
+			return -EINVAL;
+
+		i915_gem_context_set_persistence(ctx);
+	} else {
+		/* To cancel a context we use "preempt-to-idle" */
+		if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
+			return -ENODEV;
+
+		i915_gem_context_clear_persistence(ctx);
+	}
+
+	return 0;
+}
+
 static struct i915_gem_context *
 __create_context(struct drm_i915_private *i915)
 {
@@ -335,10 +524,14 @@ __create_context(struct drm_i915_private *i915)
 
 	i915_gem_context_set_bannable(ctx);
 	i915_gem_context_set_recoverable(ctx);
+	__context_set_persistence(ctx, true /* cgroup hook? */);
 
 	for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
 		ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
 
+	ctx->jump_whitelist = NULL;
+	ctx->jump_whitelist_cmds = 0;
+
 	spin_lock(&i915->gem.contexts.lock);
 	list_add_tail(&ctx->link, &i915->gem.contexts.list);
 	spin_unlock(&i915->gem.contexts.lock);
@@ -491,6 +684,7 @@ i915_gem_context_create_kernel(struct drm_i915_private *i915, int prio)
 		return ctx;
 
 	i915_gem_context_clear_bannable(ctx);
+	i915_gem_context_set_persistence(ctx);
 	ctx->sched.priority = I915_USER_PRIORITY(prio);
 
 	GEM_BUG_ON(!i915_gem_context_is_kernel(ctx));
@@ -533,6 +727,7 @@ int i915_gem_init_contexts(struct drm_i915_private *i915)
 void i915_gem_driver_release__contexts(struct drm_i915_private *i915)
 {
 	destroy_kernel_context(&i915->kernel_context);
+	flush_work(&i915->gem.contexts.free_work);
 }
 
 static int context_idr_cleanup(int id, void *p, void *data)
@@ -947,7 +1142,7 @@ static int set_ppgtt(struct drm_i915_file_private *file_priv,
 
 	if (i915_gem_context_is_closed(ctx)) {
 		err = -ENOENT;
-		goto out;
+		goto unlock;
 	}
 
 	if (vm == rcu_access_pointer(ctx->vm))
@@ -1601,6 +1796,16 @@ err_free:
 	return err;
 }
 
+static int
+set_persistence(struct i915_gem_context *ctx,
+		const struct drm_i915_gem_context_param *args)
+{
+	if (args->size)
+		return -EINVAL;
+
+	return __context_set_persistence(ctx, args->value);
+}
+
 static int ctx_setparam(struct drm_i915_file_private *fpriv,
 			struct i915_gem_context *ctx,
 			struct drm_i915_gem_context_param *args)
@@ -1678,6 +1883,10 @@ static int ctx_setparam(struct drm_i915_file_private *fpriv,
 		ret = set_engines(ctx, args);
 		break;
 
+	case I915_CONTEXT_PARAM_PERSISTENCE:
+		ret = set_persistence(ctx, args);
+		break;
+
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	default:
 		ret = -EINVAL;
@@ -2130,6 +2339,11 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		ret = get_engines(ctx, args);
 		break;
 
+	case I915_CONTEXT_PARAM_PERSISTENCE:
+		args->size = 0;
+		args->value = i915_gem_context_is_persistent(ctx);
+		break;
+
 	case I915_CONTEXT_PARAM_BAN_PERIOD:
 	default:
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.h b/drivers/gpu/drm/i915/gem/i915_gem_context.h
index cfe80590f0ed..18e50a769a6e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.h
@@ -76,6 +76,21 @@ static inline void i915_gem_context_clear_recoverable(struct i915_gem_context *c
 	clear_bit(UCONTEXT_RECOVERABLE, &ctx->user_flags);
 }
 
+static inline bool i915_gem_context_is_persistent(const struct i915_gem_context *ctx)
+{
+	return test_bit(UCONTEXT_PERSISTENCE, &ctx->user_flags);
+}
+
+static inline void i915_gem_context_set_persistence(struct i915_gem_context *ctx)
+{
+	set_bit(UCONTEXT_PERSISTENCE, &ctx->user_flags);
+}
+
+static inline void i915_gem_context_clear_persistence(struct i915_gem_context *ctx)
+{
+	clear_bit(UCONTEXT_PERSISTENCE, &ctx->user_flags);
+}
+
 static inline bool i915_gem_context_is_banned(const struct i915_gem_context *ctx)
 {
 	return test_bit(CONTEXT_BANNED, &ctx->flags);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
index fe97b8ba4fda..3870dd5daaa0 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context_types.h
@@ -137,6 +137,7 @@ struct i915_gem_context {
 #define UCONTEXT_NO_ERROR_CAPTURE	1
 #define UCONTEXT_BANNABLE		2
 #define UCONTEXT_RECOVERABLE		3
+#define UCONTEXT_PERSISTENCE		4
 
 	/**
 	 * @flags: small set of booleans
@@ -175,6 +176,13 @@ struct i915_gem_context {
 	 * per vm, which may be one per context or shared with the global GTT)
 	 */
 	struct radix_tree_root handles_vma;
+
+	/** jump_whitelist: Bit array for tracking cmds during cmdparsing
+	 *  Guarded by struct_mutex
+	 */
+	unsigned long *jump_whitelist;
+	/** jump_whitelist_cmds: No of cmd slots available */
+	u32 jump_whitelist_cmds;
 };
 
 #endif /* __I915_GEM_CONTEXT_TYPES_H__ */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 96ce95c8ac5a..eaea49d08eb5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -256,6 +256,7 @@ static const struct drm_i915_gem_object_ops i915_gem_object_dmabuf_ops = {
 struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 					     struct dma_buf *dma_buf)
 {
+	static struct lock_class_key lock_class;
 	struct dma_buf_attachment *attach;
 	struct drm_i915_gem_object *obj;
 	int ret;
@@ -287,7 +288,7 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 	}
 
 	drm_gem_private_object_init(dev, &obj->base, dma_buf->size);
-	i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops);
+	i915_gem_object_init(obj, &i915_gem_object_dmabuf_ops, &lock_class);
 	obj->base.import_attach = attach;
 	obj->base.resv = dma_buf->resv;
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index e96901888323..f0998f1225af 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -19,6 +19,7 @@
 #include "gt/intel_engine_pool.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_ring.h"
 
 #include "i915_drv.h"
 #include "i915_gem_clflush.h"
@@ -297,7 +298,9 @@ static inline u64 gen8_noncanonical_addr(u64 address)
 
 static inline bool eb_use_cmdparser(const struct i915_execbuffer *eb)
 {
-	return intel_engine_needs_cmd_parser(eb->engine) && eb->batch_len;
+	return intel_engine_requires_cmd_parser(eb->engine) ||
+		(intel_engine_using_cmd_parser(eb->engine) &&
+		 eb->args->batch_len);
 }
 
 static int eb_create(struct i915_execbuffer *eb)
@@ -1989,40 +1992,94 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 	return 0;
 }
 
-static struct i915_vma *eb_parse(struct i915_execbuffer *eb, bool is_master)
+static struct i915_vma *
+shadow_batch_pin(struct i915_execbuffer *eb, struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *dev_priv = eb->i915;
+	struct i915_vma * const vma = *eb->vma;
+	struct i915_address_space *vm;
+	u64 flags;
+
+	/*
+	 * PPGTT backed shadow buffers must be mapped RO, to prevent
+	 * post-scan tampering
+	 */
+	if (CMDPARSER_USES_GGTT(dev_priv)) {
+		flags = PIN_GLOBAL;
+		vm = &dev_priv->ggtt.vm;
+	} else if (vma->vm->has_read_only) {
+		flags = PIN_USER;
+		vm = vma->vm;
+		i915_gem_object_set_readonly(obj);
+	} else {
+		DRM_DEBUG("Cannot prevent post-scan tampering without RO capable vm\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return i915_gem_object_pin(obj, vm, NULL, 0, 0, flags);
+}
+
+static struct i915_vma *eb_parse(struct i915_execbuffer *eb)
 {
 	struct intel_engine_pool_node *pool;
 	struct i915_vma *vma;
+	u64 batch_start;
+	u64 shadow_batch_start;
 	int err;
 
 	pool = intel_engine_get_pool(eb->engine, eb->batch_len);
 	if (IS_ERR(pool))
 		return ERR_CAST(pool);
 
-	err = intel_engine_cmd_parser(eb->engine,
+	vma = shadow_batch_pin(eb, pool->obj);
+	if (IS_ERR(vma))
+		goto err;
+
+	batch_start = gen8_canonical_addr(eb->batch->node.start) +
+		      eb->batch_start_offset;
+
+	shadow_batch_start = gen8_canonical_addr(vma->node.start);
+
+	err = intel_engine_cmd_parser(eb->gem_context,
+				      eb->engine,
 				      eb->batch->obj,
-				      pool->obj,
+				      batch_start,
 				      eb->batch_start_offset,
 				      eb->batch_len,
-				      is_master);
+				      pool->obj,
+				      shadow_batch_start);
+
 	if (err) {
-		if (err == -EACCES) /* unhandled chained batch */
+		i915_vma_unpin(vma);
+
+		/*
+		 * Unsafe GGTT-backed buffers can still be submitted safely
+		 * as non-secure.
+		 * For PPGTT backing however, we have no choice but to forcibly
+		 * reject unsafe buffers
+		 */
+		if (CMDPARSER_USES_GGTT(eb->i915) && (err == -EACCES))
+			/* Execute original buffer non-secure */
 			vma = NULL;
 		else
 			vma = ERR_PTR(err);
 		goto err;
 	}
 
-	vma = i915_gem_object_ggtt_pin(pool->obj, NULL, 0, 0, 0);
-	if (IS_ERR(vma))
-		goto err;
-
 	eb->vma[eb->buffer_count] = i915_vma_get(vma);
 	eb->flags[eb->buffer_count] =
 		__EXEC_OBJECT_HAS_PIN | __EXEC_OBJECT_HAS_REF;
 	vma->exec_flags = &eb->flags[eb->buffer_count];
 	eb->buffer_count++;
 
+	eb->batch_start_offset = 0;
+	eb->batch = vma;
+
+	if (CMDPARSER_USES_GGTT(eb->i915))
+		eb->batch_flags |= I915_DISPATCH_SECURE;
+
+	/* eb->batch_len unchanged */
+
 	vma->private = pool;
 	return vma;
 
@@ -2429,6 +2486,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		       struct drm_i915_gem_exec_object2 *exec,
 		       struct drm_syncobj **fences)
 {
+	struct drm_i915_private *i915 = to_i915(dev);
 	struct i915_execbuffer eb;
 	struct dma_fence *in_fence = NULL;
 	struct dma_fence *exec_fence = NULL;
@@ -2440,7 +2498,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	BUILD_BUG_ON(__EXEC_OBJECT_INTERNAL_FLAGS &
 		     ~__EXEC_OBJECT_UNKNOWN_FLAGS);
 
-	eb.i915 = to_i915(dev);
+	eb.i915 = i915;
 	eb.file = file;
 	eb.args = args;
 	if (DBG_FORCE_RELOC || !(args->flags & I915_EXEC_NO_RELOC))
@@ -2460,8 +2518,15 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 
 	eb.batch_flags = 0;
 	if (args->flags & I915_EXEC_SECURE) {
+		if (INTEL_GEN(i915) >= 11)
+			return -ENODEV;
+
+		/* Return -EPERM to trigger fallback code on old binaries. */
+		if (!HAS_SECURE_BATCHES(i915))
+			return -EPERM;
+
 		if (!drm_is_current_master(file) || !capable(CAP_SYS_ADMIN))
-		    return -EPERM;
+			return -EPERM;
 
 		eb.batch_flags |= I915_DISPATCH_SECURE;
 	}
@@ -2538,34 +2603,19 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 		goto err_vma;
 	}
 
+	if (eb.batch_len == 0)
+		eb.batch_len = eb.batch->size - eb.batch_start_offset;
+
 	if (eb_use_cmdparser(&eb)) {
 		struct i915_vma *vma;
 
-		vma = eb_parse(&eb, drm_is_current_master(file));
+		vma = eb_parse(&eb);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto err_vma;
 		}
-
-		if (vma) {
-			/*
-			 * Batch parsed and accepted:
-			 *
-			 * Set the DISPATCH_SECURE bit to remove the NON_SECURE
-			 * bit from MI_BATCH_BUFFER_START commands issued in
-			 * the dispatch_execbuffer implementations. We
-			 * specifically don't want that set on batches the
-			 * command parser has accepted.
-			 */
-			eb.batch_flags |= I915_DISPATCH_SECURE;
-			eb.batch_start_offset = 0;
-			eb.batch = vma;
-		}
 	}
 
-	if (eb.batch_len == 0)
-		eb.batch_len = eb.batch->size - eb.batch_start_offset;
-
 	/*
 	 * snb/ivb/vlv conflate the "batch in ppgtt" bit with the "non-secure
 	 * batch" bit. Hence we need to pin secure batches into the global gtt.
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_internal.c b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
index 5ae694c24df4..9cfb0e41ff06 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_internal.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_internal.c
@@ -164,6 +164,7 @@ struct drm_i915_gem_object *
 i915_gem_object_create_internal(struct drm_i915_private *i915,
 				phys_addr_t size)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
 	unsigned int cache_level;
 
@@ -178,7 +179,7 @@ i915_gem_object_create_internal(struct drm_i915_private *i915,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &i915_gem_object_internal_ops);
+	i915_gem_object_init(obj, &i915_gem_object_internal_ops, &lock_class);
 
 	/*
 	 * Mark the object as volatile, such that the pages are marked as
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.c b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
new file mode 100644
index 000000000000..0e2bf6b7e143
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "intel_memory_region.h"
+#include "gem/i915_gem_region.h"
+#include "gem/i915_gem_lmem.h"
+#include "i915_drv.h"
+
+const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops = {
+	.flags = I915_GEM_OBJECT_HAS_IOMEM,
+
+	.get_pages = i915_gem_object_get_pages_buddy,
+	.put_pages = i915_gem_object_put_pages_buddy,
+	.release = i915_gem_object_release_memory_region,
+};
+
+/* XXX: Time to vfunc your life up? */
+void __iomem *
+i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj,
+				 unsigned long n)
+{
+	resource_size_t offset;
+
+	offset = i915_gem_object_get_dma_address(obj, n);
+	offset -= obj->mm.region->region.start;
+
+	return io_mapping_map_wc(&obj->mm.region->iomap, offset, PAGE_SIZE);
+}
+
+void __iomem *
+i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj,
+					unsigned long n)
+{
+	resource_size_t offset;
+
+	offset = i915_gem_object_get_dma_address(obj, n);
+	offset -= obj->mm.region->region.start;
+
+	return io_mapping_map_atomic_wc(&obj->mm.region->iomap, offset);
+}
+
+void __iomem *
+i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
+			    unsigned long n,
+			    unsigned long size)
+{
+	resource_size_t offset;
+
+	GEM_BUG_ON(!i915_gem_object_is_contiguous(obj));
+
+	offset = i915_gem_object_get_dma_address(obj, n);
+	offset -= obj->mm.region->region.start;
+
+	return io_mapping_map_wc(&obj->mm.region->iomap, offset, size);
+}
+
+bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj)
+{
+	return obj->ops == &i915_gem_lmem_obj_ops;
+}
+
+struct drm_i915_gem_object *
+i915_gem_object_create_lmem(struct drm_i915_private *i915,
+			    resource_size_t size,
+			    unsigned int flags)
+{
+	return i915_gem_object_create_region(i915->mm.regions[INTEL_REGION_LMEM],
+					     size, flags);
+}
+
+struct drm_i915_gem_object *
+__i915_gem_lmem_object_create(struct intel_memory_region *mem,
+			      resource_size_t size,
+			      unsigned int flags)
+{
+	static struct lock_class_key lock_class;
+	struct drm_i915_private *i915 = mem->i915;
+	struct drm_i915_gem_object *obj;
+
+	if (size > BIT(mem->mm.max_order) * mem->mm.chunk_size)
+		return ERR_PTR(-E2BIG);
+
+	obj = i915_gem_object_alloc();
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	drm_gem_private_object_init(&i915->drm, &obj->base, size);
+	i915_gem_object_init(obj, &i915_gem_lmem_obj_ops, &lock_class);
+
+	obj->read_domains = I915_GEM_DOMAIN_WC | I915_GEM_DOMAIN_GTT;
+
+	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
+
+	i915_gem_object_init_memory_region(obj, mem, flags);
+
+	return obj;
+}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_lmem.h b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
new file mode 100644
index 000000000000..7c176b8b7d2f
--- /dev/null
+++ b/drivers/gpu/drm/i915/gem/i915_gem_lmem.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __I915_GEM_LMEM_H
+#define __I915_GEM_LMEM_H
+
+#include <linux/types.h>
+
+struct drm_i915_private;
+struct drm_i915_gem_object;
+struct intel_memory_region;
+
+extern const struct drm_i915_gem_object_ops i915_gem_lmem_obj_ops;
+
+void __iomem *i915_gem_object_lmem_io_map(struct drm_i915_gem_object *obj,
+					  unsigned long n, unsigned long size);
+void __iomem *i915_gem_object_lmem_io_map_page(struct drm_i915_gem_object *obj,
+					       unsigned long n);
+void __iomem *
+i915_gem_object_lmem_io_map_page_atomic(struct drm_i915_gem_object *obj,
+					unsigned long n);
+
+bool i915_gem_object_is_lmem(struct drm_i915_gem_object *obj);
+
+struct drm_i915_gem_object *
+i915_gem_object_create_lmem(struct drm_i915_private *i915,
+			    resource_size_t size,
+			    unsigned int flags);
+
+struct drm_i915_gem_object *
+__i915_gem_lmem_object_create(struct intel_memory_region *mem,
+			      resource_size_t size,
+			      unsigned int flags);
+
+#endif /* !__I915_GEM_LMEM_H */
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index fd4122d8c0a9..e3002849844b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -312,7 +312,7 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		list_add(&obj->userfault_link, &i915->ggtt.userfault_list);
 	mutex_unlock(&i915->ggtt.vm.mutex);
 
-	if (CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)
+	if (IS_ACTIVE(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND))
 		intel_wakeref_auto(&i915->ggtt.userfault_wakeref,
 				   msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND));
 
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.c b/drivers/gpu/drm/i915/gem/i915_gem_object.c
index dbf9be9a79f4..a50296cce0d8 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.c
@@ -47,9 +47,10 @@ void i915_gem_object_free(struct drm_i915_gem_object *obj)
 }
 
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
-			  const struct drm_i915_gem_object_ops *ops)
+			  const struct drm_i915_gem_object_ops *ops,
+			  struct lock_class_key *key)
 {
-	mutex_init(&obj->mm.lock);
+	__mutex_init(&obj->mm.lock, "obj->mm.lock", key);
 
 	spin_lock_init(&obj->vma.lock);
 	INIT_LIST_HEAD(&obj->vma.list);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object.h b/drivers/gpu/drm/i915/gem/i915_gem_object.h
index 85921796851f..458cd51331f1 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object.h
@@ -23,7 +23,8 @@ struct drm_i915_gem_object *i915_gem_object_alloc(void);
 void i915_gem_object_free(struct drm_i915_gem_object *obj);
 
 void i915_gem_object_init(struct drm_i915_gem_object *obj,
-			  const struct drm_i915_gem_object_ops *ops);
+			  const struct drm_i915_gem_object_ops *ops,
+			  struct lock_class_key *key);
 struct drm_i915_gem_object *
 i915_gem_object_create_shmem(struct drm_i915_private *i915,
 			     resource_size_t size);
@@ -461,6 +462,5 @@ int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 int i915_gem_object_wait_priority(struct drm_i915_gem_object *obj,
 				  unsigned int flags,
 				  const struct i915_sched_attr *attr);
-#define I915_PRIORITY_DISPLAY I915_USER_PRIORITY(I915_PRIORITY_MAX)
 
 #endif
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
index 5bd8de124d74..70809d8897cd 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_blt.c
@@ -8,6 +8,7 @@
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_pool.h"
 #include "gt/intel_gt.h"
+#include "gt/intel_ring.h"
 #include "i915_gem_clflush.h"
 #include "i915_gem_object_blt.h"
 
@@ -16,7 +17,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 					 u32 value)
 {
 	struct drm_i915_private *i915 = ce->vm->i915;
-	const u32 block_size = S16_MAX * PAGE_SIZE;
+	const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
 	struct intel_engine_pool_node *pool;
 	struct i915_vma *batch;
 	u64 offset;
@@ -29,7 +30,7 @@ struct i915_vma *intel_emit_vma_fill_blt(struct intel_context *ce,
 	GEM_BUG_ON(intel_engine_is_virtual(ce->engine));
 	intel_engine_pm_get(ce->engine);
 
-	count = div_u64(vma->size, block_size);
+	count = div_u64(round_up(vma->size, block_size), block_size);
 	size = (1 + 8 * count) * sizeof(u32);
 	size = round_up(size, PAGE_SIZE);
 	pool = intel_engine_get_pool(ce->engine, size);
@@ -200,7 +201,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 					 struct i915_vma *dst)
 {
 	struct drm_i915_private *i915 = ce->vm->i915;
-	const u32 block_size = S16_MAX * PAGE_SIZE;
+	const u32 block_size = SZ_8M; /* ~1ms at 8GiB/s preemption delay */
 	struct intel_engine_pool_node *pool;
 	struct i915_vma *batch;
 	u64 src_offset, dst_offset;
@@ -213,7 +214,7 @@ struct i915_vma *intel_emit_vma_copy_blt(struct intel_context *ce,
 	GEM_BUG_ON(intel_engine_is_virtual(ce->engine));
 	intel_engine_pm_get(ce->engine);
 
-	count = div_u64(dst->size, block_size);
+	count = div_u64(round_up(dst->size, block_size), block_size);
 	size = (1 + 11 * count) * sizeof(u32);
 	size = round_up(size, PAGE_SIZE);
 	pool = intel_engine_get_pool(ce->engine, size);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
index a387e3ee728b..96008374a412 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_object_types.h
@@ -31,10 +31,11 @@ struct i915_lut_handle {
 struct drm_i915_gem_object_ops {
 	unsigned int flags;
 #define I915_GEM_OBJECT_HAS_STRUCT_PAGE	BIT(0)
-#define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(1)
-#define I915_GEM_OBJECT_IS_PROXY	BIT(2)
-#define I915_GEM_OBJECT_NO_GGTT		BIT(3)
-#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(4)
+#define I915_GEM_OBJECT_HAS_IOMEM	BIT(1)
+#define I915_GEM_OBJECT_IS_SHRINKABLE	BIT(2)
+#define I915_GEM_OBJECT_IS_PROXY	BIT(3)
+#define I915_GEM_OBJECT_NO_GGTT		BIT(4)
+#define I915_GEM_OBJECT_ASYNC_CANCEL	BIT(5)
 
 	/* Interface between the GEM object and its backing storage.
 	 * get_pages() is called once prior to the use of the associated set
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index b0ec0959c13f..29f4c2850745 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -7,6 +7,7 @@
 #include "i915_drv.h"
 #include "i915_gem_object.h"
 #include "i915_scatterlist.h"
+#include "i915_gem_lmem.h"
 
 void __i915_gem_object_set_pages(struct drm_i915_gem_object *obj,
 				 struct sg_table *pages,
@@ -154,6 +155,16 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj)
 	rcu_read_unlock();
 }
 
+static void unmap_object(struct drm_i915_gem_object *obj, void *ptr)
+{
+	if (i915_gem_object_is_lmem(obj))
+		io_mapping_unmap((void __force __iomem *)ptr);
+	else if (is_vmalloc_addr(ptr))
+		vunmap(ptr);
+	else
+		kunmap(kmap_to_page(ptr));
+}
+
 struct sg_table *
 __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 {
@@ -169,14 +180,7 @@ __i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 	i915_gem_object_make_unshrinkable(obj);
 
 	if (obj->mm.mapping) {
-		void *ptr;
-
-		ptr = page_mask_bits(obj->mm.mapping);
-		if (is_vmalloc_addr(ptr))
-			vunmap(ptr);
-		else
-			kunmap(kmap_to_page(ptr));
-
+		unmap_object(obj, page_mask_bits(obj->mm.mapping));
 		obj->mm.mapping = NULL;
 	}
 
@@ -231,7 +235,7 @@ unlock:
 }
 
 /* The 'mapping' part of i915_gem_object_pin_map() below */
-static void *i915_gem_object_map(const struct drm_i915_gem_object *obj,
+static void *i915_gem_object_map(struct drm_i915_gem_object *obj,
 				 enum i915_map_type type)
 {
 	unsigned long n_pages = obj->base.size >> PAGE_SHIFT;
@@ -244,6 +248,16 @@ static void *i915_gem_object_map(const struct drm_i915_gem_object *obj,
 	pgprot_t pgprot;
 	void *addr;
 
+	if (i915_gem_object_is_lmem(obj)) {
+		void __iomem *io;
+
+		if (type != I915_MAP_WC)
+			return NULL;
+
+		io = i915_gem_object_lmem_io_map(obj, 0, obj->base.size);
+		return (void __force *)io;
+	}
+
 	/* A single page can always be kmapped */
 	if (n_pages == 1 && type == I915_MAP_WB)
 		return kmap(sg_page(sgt->sgl));
@@ -285,11 +299,13 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 			      enum i915_map_type type)
 {
 	enum i915_map_type has_type;
+	unsigned int flags;
 	bool pinned;
 	void *ptr;
 	int err;
 
-	if (unlikely(!i915_gem_object_has_struct_page(obj)))
+	flags = I915_GEM_OBJECT_HAS_STRUCT_PAGE | I915_GEM_OBJECT_HAS_IOMEM;
+	if (!i915_gem_object_type_has(obj, flags))
 		return ERR_PTR(-ENXIO);
 
 	err = mutex_lock_interruptible(&obj->mm.lock);
@@ -321,10 +337,7 @@ void *i915_gem_object_pin_map(struct drm_i915_gem_object *obj,
 			goto err_unpin;
 		}
 
-		if (is_vmalloc_addr(ptr))
-			vunmap(ptr);
-		else
-			kunmap(kmap_to_page(ptr));
+		unmap_object(obj, ptr);
 
 		ptr = obj->mm.mapping = NULL;
 	}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.c b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
index 7987b54fb1f5..f88ee1317bb4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.c
@@ -11,74 +11,6 @@
 
 #include "i915_drv.h"
 
-static int pm_notifier(struct notifier_block *nb,
-		       unsigned long action,
-		       void *data)
-{
-	struct drm_i915_private *i915 =
-		container_of(nb, typeof(*i915), gem.pm_notifier);
-
-	switch (action) {
-	case INTEL_GT_UNPARK:
-		break;
-
-	case INTEL_GT_PARK:
-		i915_vma_parked(i915);
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static bool switch_to_kernel_context_sync(struct intel_gt *gt)
-{
-	bool result = !intel_gt_is_wedged(gt);
-
-	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
-		/* XXX hide warning from gem_eio */
-		if (i915_modparams.reset) {
-			dev_err(gt->i915->drm.dev,
-				"Failed to idle engines, declaring wedged!\n");
-			GEM_TRACE_DUMP();
-		}
-
-		/*
-		 * Forcibly cancel outstanding work and leave
-		 * the gpu quiet.
-		 */
-		intel_gt_set_wedged(gt);
-		result = false;
-	}
-
-	if (intel_gt_pm_wait_for_idle(gt))
-		result = false;
-
-	return result;
-}
-
-bool i915_gem_load_power_context(struct drm_i915_private *i915)
-{
-	return switch_to_kernel_context_sync(&i915->gt);
-}
-
-static void user_forcewake(struct intel_gt *gt, bool suspend)
-{
-	int count = atomic_read(&gt->user_wakeref);
-
-	/* Inside suspend/resume so single threaded, no races to worry about. */
-	if (likely(!count))
-		return;
-
-	intel_gt_pm_get(gt);
-	if (suspend) {
-		GEM_BUG_ON(count > atomic_read(&gt->wakeref.count));
-		atomic_sub(count, &gt->wakeref.count);
-	} else {
-		atomic_add(count, &gt->wakeref.count);
-	}
-	intel_gt_pm_put(gt);
-}
-
 void i915_gem_suspend(struct drm_i915_private *i915)
 {
 	GEM_TRACE("\n");
@@ -86,8 +18,6 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	intel_wakeref_auto(&i915->ggtt.userfault_wakeref, 0);
 	flush_workqueue(i915->wq);
 
-	user_forcewake(&i915->gt, true);
-
 	/*
 	 * We have to flush all the executing contexts to main memory so
 	 * that they can saved in the hibernation image. To ensure the last
@@ -97,10 +27,7 @@ void i915_gem_suspend(struct drm_i915_private *i915)
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	intel_gt_suspend(&i915->gt);
-	intel_uc_suspend(&i915->gt.uc);
-
-	cancel_delayed_work_sync(&i915->gt.hangcheck.work);
+	intel_gt_suspend_prepare(&i915->gt);
 
 	i915_gem_drain_freed_objects(i915);
 }
@@ -142,6 +69,8 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 	 * machine in an unusable condition.
 	 */
 
+	intel_gt_suspend_late(&i915->gt);
+
 	spin_lock_irqsave(&i915->mm.obj_lock, flags);
 	for (phase = phases; *phase; phase++) {
 		LIST_HEAD(keep);
@@ -166,8 +95,6 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 		list_splice_tail(&keep, *phase);
 	}
 	spin_unlock_irqrestore(&i915->mm.obj_lock, flags);
-
-	i915_gem_sanitize(i915);
 }
 
 void i915_gem_resume(struct drm_i915_private *i915)
@@ -187,14 +114,6 @@ void i915_gem_resume(struct drm_i915_private *i915)
 	if (intel_gt_resume(&i915->gt))
 		goto err_wedged;
 
-	intel_uc_resume(&i915->gt.uc);
-
-	/* Always reload a context for powersaving. */
-	if (!i915_gem_load_power_context(i915))
-		goto err_wedged;
-
-	user_forcewake(&i915->gt, false);
-
 out_unlock:
 	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
 	return;
@@ -207,10 +126,3 @@ err_wedged:
 	}
 	goto out_unlock;
 }
-
-void i915_gem_init__pm(struct drm_i915_private *i915)
-{
-	i915->gem.pm_notifier.notifier_call = pm_notifier;
-	blocking_notifier_chain_register(&i915->gt.pm_notifications,
-					 &i915->gem.pm_notifier);
-}
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pm.h b/drivers/gpu/drm/i915/gem/i915_gem_pm.h
index 6f7d5d11ac3b..26b78dbdc225 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pm.h
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pm.h
@@ -12,9 +12,6 @@
 struct drm_i915_private;
 struct work_struct;
 
-void i915_gem_init__pm(struct drm_i915_private *i915);
-
-bool i915_gem_load_power_context(struct drm_i915_private *i915);
 void i915_gem_resume(struct drm_i915_private *i915);
 
 void i915_gem_idle_work_handler(struct work_struct *work);
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index be68b76e13b3..4d69c3fc3439 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -465,6 +465,7 @@ create_shmem(struct intel_memory_region *mem,
 	     resource_size_t size,
 	     unsigned int flags)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 	struct address_space *mapping;
@@ -491,7 +492,7 @@ create_shmem(struct intel_memory_region *mem,
 	mapping_set_gfp_mask(mapping, mask);
 	GEM_BUG_ON(!(mapping_gfp_mask(mapping) & __GFP_RECLAIM));
 
-	i915_gem_object_init(obj, &i915_gem_shmem_ops);
+	i915_gem_object_init(obj, &i915_gem_shmem_ops, &lock_class);
 
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
index 57cd8bc2657c..a2d49c04e6a4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_stolen.c
@@ -556,6 +556,7 @@ __i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 				struct drm_mm_node *stolen,
 				struct intel_memory_region *mem)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
 	unsigned int cache_level;
 	int err = -ENOMEM;
@@ -565,7 +566,7 @@ __i915_gem_object_create_stolen(struct drm_i915_private *dev_priv,
 		goto err;
 
 	drm_gem_private_object_init(&dev_priv->drm, &obj->base, stolen->size);
-	i915_gem_object_init(obj, &i915_gem_object_stolen_ops);
+	i915_gem_object_init(obj, &i915_gem_object_stolen_ops, &lock_class);
 
 	obj->stolen = stolen;
 	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index 4f970474013f..4c72d74d6576 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -646,8 +646,28 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 		obj->mm.dirty = false;
 
 	for_each_sgt_page(page, sgt_iter, pages) {
-		if (obj->mm.dirty)
+		if (obj->mm.dirty && trylock_page(page)) {
+			/*
+			 * As this may not be anonymous memory (e.g. shmem)
+			 * but exist on a real mapping, we have to lock
+			 * the page in order to dirty it -- holding
+			 * the page reference is not sufficient to
+			 * prevent the inode from being truncated.
+			 * Play safe and take the lock.
+			 *
+			 * However...!
+			 *
+			 * The mmu-notifier can be invalidated for a
+			 * migrate_page, that is alreadying holding the lock
+			 * on the page. Such a try_to_unmap() will result
+			 * in us calling put_pages() and so recursively try
+			 * to lock the page. We avoid that deadlock with
+			 * a trylock_page() and in exchange we risk missing
+			 * some page dirtying.
+			 */
 			set_page_dirty(page);
+			unlock_page(page);
+		}
 
 		mark_page_accessed(page);
 		put_page(page);
@@ -725,6 +745,7 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		       void *data,
 		       struct drm_file *file)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_userptr *args = data;
 	struct drm_i915_gem_object *obj;
@@ -769,7 +790,7 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -ENOMEM;
 
 	drm_gem_private_object_init(dev, &obj->base, args->user_size);
-	i915_gem_object_init(obj, &i915_gem_userptr_ops);
+	i915_gem_object_init(obj, &i915_gem_userptr_ops, &lock_class);
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
index 3c5d17b2b670..892d12db6c49 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_gem_object.c
@@ -96,6 +96,7 @@ huge_gem_object(struct drm_i915_private *i915,
 		phys_addr_t phys_size,
 		dma_addr_t dma_size)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
 	unsigned int cache_level;
 
@@ -111,7 +112,7 @@ huge_gem_object(struct drm_i915_private *i915,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, dma_size);
-	i915_gem_object_init(obj, &huge_ops);
+	i915_gem_object_init(obj, &huge_ops, &lock_class);
 
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
diff --git a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
index f27772f6779a..688c49a24f32 100644
--- a/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/gem/selftests/huge_pages.c
@@ -9,6 +9,7 @@
 #include "i915_selftest.h"
 
 #include "gem/i915_gem_region.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_pm.h"
 
 #include "gt/intel_gt.h"
@@ -149,6 +150,7 @@ huge_pages_object(struct drm_i915_private *i915,
 		  u64 size,
 		  unsigned int page_mask)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
 
 	GEM_BUG_ON(!size);
@@ -165,7 +167,7 @@ huge_pages_object(struct drm_i915_private *i915,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &huge_page_ops);
+	i915_gem_object_init(obj, &huge_page_ops, &lock_class);
 
 	i915_gem_object_set_volatile(obj);
 
@@ -295,6 +297,7 @@ static const struct drm_i915_gem_object_ops fake_ops_single = {
 static struct drm_i915_gem_object *
 fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
 
 	GEM_BUG_ON(!size);
@@ -313,9 +316,9 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
 
 	if (single)
-		i915_gem_object_init(obj, &fake_ops_single);
+		i915_gem_object_init(obj, &fake_ops_single, &lock_class);
 	else
-		i915_gem_object_init(obj, &fake_ops);
+		i915_gem_object_init(obj, &fake_ops, &lock_class);
 
 	i915_gem_object_set_volatile(obj);
 
@@ -981,7 +984,8 @@ static int gpu_write(struct intel_context *ce,
 			       vma->size >> PAGE_SHIFT, val);
 }
 
-static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
+static int
+__cpu_check_shmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 {
 	unsigned int needs_flush;
 	unsigned long n;
@@ -1013,6 +1017,51 @@ static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
 	return err;
 }
 
+static int __cpu_check_lmem(struct drm_i915_gem_object *obj, u32 dword, u32 val)
+{
+	unsigned long n;
+	int err;
+
+	i915_gem_object_lock(obj);
+	err = i915_gem_object_set_to_wc_domain(obj, false);
+	i915_gem_object_unlock(obj);
+	if (err)
+		return err;
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		return err;
+
+	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
+		u32 __iomem *base;
+		u32 read_val;
+
+		base = i915_gem_object_lmem_io_map_page_atomic(obj, n);
+
+		read_val = ioread32(base + dword);
+		io_mapping_unmap_atomic(base);
+		if (read_val != val) {
+			pr_err("n=%lu base[%u]=%u, val=%u\n",
+			       n, dword, read_val, val);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	i915_gem_object_unpin_pages(obj);
+	return err;
+}
+
+static int cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
+{
+	if (i915_gem_object_has_struct_page(obj))
+		return __cpu_check_shmem(obj, dword, val);
+	else if (i915_gem_object_is_lmem(obj))
+		return __cpu_check_lmem(obj, dword, val);
+
+	return -ENODEV;
+}
+
 static int __igt_write_huge(struct intel_context *ce,
 			    struct drm_i915_gem_object *obj,
 			    u64 size, u64 offset,
@@ -1268,131 +1317,235 @@ out_device:
 	return err;
 }
 
-static int igt_ppgtt_internal_huge(void *arg)
+typedef struct drm_i915_gem_object *
+(*igt_create_fn)(struct drm_i915_private *i915, u32 size, u32 flags);
+
+static inline bool igt_can_allocate_thp(struct drm_i915_private *i915)
+{
+	return i915->mm.gemfs && has_transparent_hugepage();
+}
+
+static struct drm_i915_gem_object *
+igt_create_shmem(struct drm_i915_private *i915, u32 size, u32 flags)
+{
+	if (!igt_can_allocate_thp(i915)) {
+		pr_info("%s missing THP support, skipping\n", __func__);
+		return ERR_PTR(-ENODEV);
+	}
+
+	return i915_gem_object_create_shmem(i915, size);
+}
+
+static struct drm_i915_gem_object *
+igt_create_internal(struct drm_i915_private *i915, u32 size, u32 flags)
+{
+	return i915_gem_object_create_internal(i915, size);
+}
+
+static struct drm_i915_gem_object *
+igt_create_system(struct drm_i915_private *i915, u32 size, u32 flags)
+{
+	return huge_pages_object(i915, size, size);
+}
+
+static struct drm_i915_gem_object *
+igt_create_local(struct drm_i915_private *i915, u32 size, u32 flags)
+{
+	return i915_gem_object_create_lmem(i915, size, flags);
+}
+
+static u32 igt_random_size(struct rnd_state *prng,
+			   u32 min_page_size,
+			   u32 max_page_size)
+{
+	u64 mask;
+	u32 size;
+
+	GEM_BUG_ON(!is_power_of_2(min_page_size));
+	GEM_BUG_ON(!is_power_of_2(max_page_size));
+	GEM_BUG_ON(min_page_size < PAGE_SIZE);
+	GEM_BUG_ON(min_page_size > max_page_size);
+
+	mask = ((max_page_size << 1ULL) - 1) & PAGE_MASK;
+	size = prandom_u32_state(prng) & mask;
+	if (size < min_page_size)
+		size |= min_page_size;
+
+	return size;
+}
+
+static int igt_ppgtt_smoke_huge(void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
 	struct drm_i915_gem_object *obj;
-	static const unsigned int sizes[] = {
-		SZ_64K,
-		SZ_128K,
-		SZ_256K,
-		SZ_512K,
-		SZ_1M,
-		SZ_2M,
+	I915_RND_STATE(prng);
+	struct {
+		igt_create_fn fn;
+		u32 min;
+		u32 max;
+	} backends[] = {
+		{ igt_create_internal, SZ_64K, SZ_2M,  },
+		{ igt_create_shmem,    SZ_64K, SZ_32M, },
+		{ igt_create_local,    SZ_64K, SZ_1G,  },
 	};
-	int i;
 	int err;
+	int i;
 
 	/*
-	 * Sanity check that the HW uses huge pages correctly through internal
-	 * -- ensure that our writes land in the right place.
+	 * Sanity check that the HW uses huge pages correctly through our
+	 * various backends -- ensure that our writes land in the right place.
 	 */
 
-	for (i = 0; i < ARRAY_SIZE(sizes); ++i) {
-		unsigned int size = sizes[i];
+	for (i = 0; i < ARRAY_SIZE(backends); ++i) {
+		u32 min = backends[i].min;
+		u32 max = backends[i].max;
+		u32 size = max;
+try_again:
+		size = igt_random_size(&prng, min, rounddown_pow_of_two(size));
 
-		obj = i915_gem_object_create_internal(i915, size);
-		if (IS_ERR(obj))
-			return PTR_ERR(obj);
+		obj = backends[i].fn(i915, size, 0);
+		if (IS_ERR(obj)) {
+			err = PTR_ERR(obj);
+			if (err == -E2BIG) {
+				size >>= 1;
+				goto try_again;
+			} else if (err == -ENODEV) {
+				err = 0;
+				continue;
+			}
+
+			return err;
+		}
 
 		err = i915_gem_object_pin_pages(obj);
-		if (err)
+		if (err) {
+			if (err == -ENXIO) {
+				i915_gem_object_put(obj);
+				size >>= 1;
+				goto try_again;
+			}
 			goto out_put;
+		}
 
-		if (obj->mm.page_sizes.phys < I915_GTT_PAGE_SIZE_64K) {
-			pr_info("internal unable to allocate huge-page(s) with size=%u\n",
-				size);
+		if (obj->mm.page_sizes.phys < min) {
+			pr_info("%s unable to allocate huge-page(s) with size=%u, i=%d\n",
+				__func__, size, i);
+			err = -ENOMEM;
 			goto out_unpin;
 		}
 
 		err = igt_write_huge(ctx, obj);
 		if (err) {
-			pr_err("internal write-huge failed with size=%u\n",
-			       size);
-			goto out_unpin;
+			pr_err("%s write-huge failed with size=%u, i=%d\n",
+			       __func__, size, i);
 		}
-
+out_unpin:
 		i915_gem_object_unpin_pages(obj);
 		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+out_put:
 		i915_gem_object_put(obj);
-	}
 
-	return 0;
+		if (err == -ENOMEM || err == -ENXIO)
+			err = 0;
 
-out_unpin:
-	i915_gem_object_unpin_pages(obj);
-out_put:
-	i915_gem_object_put(obj);
+		if (err)
+			break;
 
-	return err;
-}
+		cond_resched();
+	}
 
-static inline bool igt_can_allocate_thp(struct drm_i915_private *i915)
-{
-	return i915->mm.gemfs && has_transparent_hugepage();
+	return err;
 }
 
-static int igt_ppgtt_gemfs_huge(void *arg)
+static int igt_ppgtt_sanity_check(void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
-	struct drm_i915_gem_object *obj;
-	static const unsigned int sizes[] = {
-		SZ_2M,
-		SZ_4M,
-		SZ_8M,
-		SZ_16M,
-		SZ_32M,
+	unsigned int supported = INTEL_INFO(i915)->page_sizes;
+	struct {
+		igt_create_fn fn;
+		unsigned int flags;
+	} backends[] = {
+		{ igt_create_system, 0,                        },
+		{ igt_create_local,  I915_BO_ALLOC_CONTIGUOUS, },
 	};
-	int i;
+	struct {
+		u32 size;
+		u32 pages;
+	} combos[] = {
+		{ SZ_64K,		SZ_64K		},
+		{ SZ_2M,		SZ_2M		},
+		{ SZ_2M,		SZ_64K		},
+		{ SZ_2M - SZ_64K,	SZ_64K		},
+		{ SZ_2M - SZ_4K,	SZ_64K | SZ_4K	},
+		{ SZ_2M + SZ_4K,	SZ_64K | SZ_4K	},
+		{ SZ_2M + SZ_4K,	SZ_2M  | SZ_4K	},
+		{ SZ_2M + SZ_64K,	SZ_2M  | SZ_64K },
+	};
+	int i, j;
 	int err;
 
+	if (supported == I915_GTT_PAGE_SIZE_4K)
+		return 0;
+
 	/*
-	 * Sanity check that the HW uses huge pages correctly through gemfs --
-	 * ensure that our writes land in the right place.
+	 * Sanity check that the HW behaves with a limited set of combinations.
+	 * We already have a bunch of randomised testing, which should give us
+	 * a decent amount of variation between runs, however we should keep
+	 * this to limit the chances of introducing a temporary regression, by
+	 * testing the most obvious cases that might make something blow up.
 	 */
 
-	if (!igt_can_allocate_thp(i915)) {
-		pr_info("missing THP support, skipping\n");
-		return 0;
-	}
+	for (i = 0; i < ARRAY_SIZE(backends); ++i) {
+		for (j = 0; j < ARRAY_SIZE(combos); ++j) {
+			struct drm_i915_gem_object *obj;
+			u32 size = combos[j].size;
+			u32 pages = combos[j].pages;
+
+			obj = backends[i].fn(i915, size, backends[i].flags);
+			if (IS_ERR(obj)) {
+				err = PTR_ERR(obj);
+				if (err == -ENODEV) {
+					pr_info("Device lacks local memory, skipping\n");
+					err = 0;
+					break;
+				}
 
-	for (i = 0; i < ARRAY_SIZE(sizes); ++i) {
-		unsigned int size = sizes[i];
+				return err;
+			}
 
-		obj = i915_gem_object_create_shmem(i915, size);
-		if (IS_ERR(obj))
-			return PTR_ERR(obj);
+			err = i915_gem_object_pin_pages(obj);
+			if (err) {
+				i915_gem_object_put(obj);
+				goto out;
+			}
 
-		err = i915_gem_object_pin_pages(obj);
-		if (err)
-			goto out_put;
+			GEM_BUG_ON(pages > obj->base.size);
+			pages = pages & supported;
 
-		if (obj->mm.page_sizes.phys < I915_GTT_PAGE_SIZE_2M) {
-			pr_info("finishing test early, gemfs unable to allocate huge-page(s) with size=%u\n",
-				size);
-			goto out_unpin;
-		}
+			if (pages)
+				obj->mm.page_sizes.sg = pages;
 
-		err = igt_write_huge(ctx, obj);
-		if (err) {
-			pr_err("gemfs write-huge failed with size=%u\n",
-			       size);
-			goto out_unpin;
+			err = igt_write_huge(ctx, obj);
+
+			i915_gem_object_unpin_pages(obj);
+			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
+			i915_gem_object_put(obj);
+
+			if (err) {
+				pr_err("%s write-huge failed with size=%u pages=%u i=%d, j=%d\n",
+				       __func__, size, pages, i, j);
+				goto out;
+			}
 		}
 
-		i915_gem_object_unpin_pages(obj);
-		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
-		i915_gem_object_put(obj);
+		cond_resched();
 	}
 
-	return 0;
-
-out_unpin:
-	i915_gem_object_unpin_pages(obj);
-out_put:
-	i915_gem_object_put(obj);
+out:
+	if (err == -ENOMEM)
+		err = 0;
 
 	return err;
 }
@@ -1756,8 +1909,8 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ppgtt_pin_update),
 		SUBTEST(igt_tmpfs_fallback),
 		SUBTEST(igt_ppgtt_exhaust_huge),
-		SUBTEST(igt_ppgtt_gemfs_huge),
-		SUBTEST(igt_ppgtt_internal_huge),
+		SUBTEST(igt_ppgtt_smoke_huge),
+		SUBTEST(igt_ppgtt_sanity_check),
 	};
 	struct drm_file *file;
 	struct i915_gem_context *ctx;
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
index d8804a847945..da8edee4fe0a 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_client_blt.c
@@ -5,6 +5,7 @@
 
 #include "i915_selftest.h"
 
+#include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 
 #include "selftests/igt_flush_test.h"
@@ -12,10 +13,9 @@
 #include "huge_gem_object.h"
 #include "mock_context.h"
 
-static int igt_client_fill(void *arg)
+static int __igt_client_fill(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *i915 = arg;
-	struct intel_context *ce = i915->engine[BCS0]->kernel_context;
+	struct intel_context *ce = engine->kernel_context;
 	struct drm_i915_gem_object *obj;
 	struct rnd_state prng;
 	IGT_TIMEOUT(end);
@@ -37,7 +37,7 @@ static int igt_client_fill(void *arg)
 		pr_debug("%s with phys_sz= %x, sz=%x, val=%x\n", __func__,
 			 phys_sz, sz, val);
 
-		obj = huge_gem_object(i915, phys_sz, sz);
+		obj = huge_gem_object(engine->i915, phys_sz, sz);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
 			goto err_flush;
@@ -103,6 +103,28 @@ err_flush:
 	return err;
 }
 
+static int igt_client_fill(void *arg)
+{
+	int inst = 0;
+
+	do {
+		struct intel_engine_cs *engine;
+		int err;
+
+		engine = intel_engine_lookup_user(arg,
+						  I915_ENGINE_CLASS_COPY,
+						  inst++);
+		if (!engine)
+			return 0;
+
+		err = __igt_client_fill(engine);
+		if (err == -ENOMEM)
+			err = 0;
+		if (err)
+			return err;
+	} while (1);
+}
+
 int i915_gem_client_blt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
index 549810f70aeb..2b29f6b4e1dd 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_coherency.c
@@ -8,13 +8,17 @@
 
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_ring.h"
 
 #include "i915_selftest.h"
 #include "selftests/i915_random.h"
 
-static int cpu_set(struct drm_i915_gem_object *obj,
-		   unsigned long offset,
-		   u32 v)
+struct context {
+	struct drm_i915_gem_object *obj;
+	struct intel_engine_cs *engine;
+};
+
+static int cpu_set(struct context *ctx, unsigned long offset, u32 v)
 {
 	unsigned int needs_clflush;
 	struct page *page;
@@ -22,11 +26,11 @@ static int cpu_set(struct drm_i915_gem_object *obj,
 	u32 *cpu;
 	int err;
 
-	err = i915_gem_object_prepare_write(obj, &needs_clflush);
+	err = i915_gem_object_prepare_write(ctx->obj, &needs_clflush);
 	if (err)
 		return err;
 
-	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
+	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
 	cpu = map + offset_in_page(offset);
 
@@ -39,14 +43,12 @@ static int cpu_set(struct drm_i915_gem_object *obj,
 		drm_clflush_virt_range(cpu, sizeof(*cpu));
 
 	kunmap_atomic(map);
-	i915_gem_object_finish_access(obj);
+	i915_gem_object_finish_access(ctx->obj);
 
 	return 0;
 }
 
-static int cpu_get(struct drm_i915_gem_object *obj,
-		   unsigned long offset,
-		   u32 *v)
+static int cpu_get(struct context *ctx, unsigned long offset, u32 *v)
 {
 	unsigned int needs_clflush;
 	struct page *page;
@@ -54,11 +56,11 @@ static int cpu_get(struct drm_i915_gem_object *obj,
 	u32 *cpu;
 	int err;
 
-	err = i915_gem_object_prepare_read(obj, &needs_clflush);
+	err = i915_gem_object_prepare_read(ctx->obj, &needs_clflush);
 	if (err)
 		return err;
 
-	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
+	page = i915_gem_object_get_page(ctx->obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
 	cpu = map + offset_in_page(offset);
 
@@ -68,26 +70,24 @@ static int cpu_get(struct drm_i915_gem_object *obj,
 	*v = *cpu;
 
 	kunmap_atomic(map);
-	i915_gem_object_finish_access(obj);
+	i915_gem_object_finish_access(ctx->obj);
 
 	return 0;
 }
 
-static int gtt_set(struct drm_i915_gem_object *obj,
-		   unsigned long offset,
-		   u32 v)
+static int gtt_set(struct context *ctx, unsigned long offset, u32 v)
 {
 	struct i915_vma *vma;
 	u32 __iomem *map;
 	int err = 0;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_gtt_domain(obj, true);
-	i915_gem_object_unlock(obj);
+	i915_gem_object_lock(ctx->obj);
+	err = i915_gem_object_set_to_gtt_domain(ctx->obj, true);
+	i915_gem_object_unlock(ctx->obj);
 	if (err)
 		return err;
 
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	vma = i915_gem_object_ggtt_pin(ctx->obj, NULL, 0, 0, PIN_MAPPABLE);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -108,21 +108,19 @@ out_rpm:
 	return err;
 }
 
-static int gtt_get(struct drm_i915_gem_object *obj,
-		   unsigned long offset,
-		   u32 *v)
+static int gtt_get(struct context *ctx, unsigned long offset, u32 *v)
 {
 	struct i915_vma *vma;
 	u32 __iomem *map;
 	int err = 0;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_gtt_domain(obj, false);
-	i915_gem_object_unlock(obj);
+	i915_gem_object_lock(ctx->obj);
+	err = i915_gem_object_set_to_gtt_domain(ctx->obj, false);
+	i915_gem_object_unlock(ctx->obj);
 	if (err)
 		return err;
 
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE);
+	vma = i915_gem_object_ggtt_pin(ctx->obj, NULL, 0, 0, PIN_MAPPABLE);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -143,73 +141,66 @@ out_rpm:
 	return err;
 }
 
-static int wc_set(struct drm_i915_gem_object *obj,
-		  unsigned long offset,
-		  u32 v)
+static int wc_set(struct context *ctx, unsigned long offset, u32 v)
 {
 	u32 *map;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_wc_domain(obj, true);
-	i915_gem_object_unlock(obj);
+	i915_gem_object_lock(ctx->obj);
+	err = i915_gem_object_set_to_wc_domain(ctx->obj, true);
+	i915_gem_object_unlock(ctx->obj);
 	if (err)
 		return err;
 
-	map = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	map = i915_gem_object_pin_map(ctx->obj, I915_MAP_WC);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
 	map[offset / sizeof(*map)] = v;
-	i915_gem_object_unpin_map(obj);
+	i915_gem_object_unpin_map(ctx->obj);
 
 	return 0;
 }
 
-static int wc_get(struct drm_i915_gem_object *obj,
-		  unsigned long offset,
-		  u32 *v)
+static int wc_get(struct context *ctx, unsigned long offset, u32 *v)
 {
 	u32 *map;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_wc_domain(obj, false);
-	i915_gem_object_unlock(obj);
+	i915_gem_object_lock(ctx->obj);
+	err = i915_gem_object_set_to_wc_domain(ctx->obj, false);
+	i915_gem_object_unlock(ctx->obj);
 	if (err)
 		return err;
 
-	map = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	map = i915_gem_object_pin_map(ctx->obj, I915_MAP_WC);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
 
 	*v = map[offset / sizeof(*map)];
-	i915_gem_object_unpin_map(obj);
+	i915_gem_object_unpin_map(ctx->obj);
 
 	return 0;
 }
 
-static int gpu_set(struct drm_i915_gem_object *obj,
-		   unsigned long offset,
-		   u32 v)
+static int gpu_set(struct context *ctx, unsigned long offset, u32 v)
 {
-	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_request *rq;
 	struct i915_vma *vma;
 	u32 *cs;
 	int err;
 
-	i915_gem_object_lock(obj);
-	err = i915_gem_object_set_to_gtt_domain(obj, true);
-	i915_gem_object_unlock(obj);
+	i915_gem_object_lock(ctx->obj);
+	err = i915_gem_object_set_to_gtt_domain(ctx->obj, true);
+	i915_gem_object_unlock(ctx->obj);
 	if (err)
 		return err;
 
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, 0);
+	vma = i915_gem_object_ggtt_pin(ctx->obj, NULL, 0, 0, 0);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
-	rq = i915_request_create(i915->engine[RCS0]->kernel_context);
+	rq = i915_request_create(ctx->engine->kernel_context);
 	if (IS_ERR(rq)) {
 		i915_vma_unpin(vma);
 		return PTR_ERR(rq);
@@ -222,12 +213,12 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 		return PTR_ERR(cs);
 	}
 
-	if (INTEL_GEN(i915) >= 8) {
+	if (INTEL_GEN(ctx->engine->i915) >= 8) {
 		*cs++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
 		*cs++ = lower_32_bits(i915_ggtt_offset(vma) + offset);
 		*cs++ = upper_32_bits(i915_ggtt_offset(vma) + offset);
 		*cs++ = v;
-	} else if (INTEL_GEN(i915) >= 4) {
+	} else if (INTEL_GEN(ctx->engine->i915) >= 4) {
 		*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*cs++ = 0;
 		*cs++ = i915_ggtt_offset(vma) + offset;
@@ -252,32 +243,34 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 	return err;
 }
 
-static bool always_valid(struct drm_i915_private *i915)
+static bool always_valid(struct context *ctx)
 {
 	return true;
 }
 
-static bool needs_fence_registers(struct drm_i915_private *i915)
+static bool needs_fence_registers(struct context *ctx)
 {
-	return !intel_gt_is_wedged(&i915->gt);
-}
+	struct intel_gt *gt = ctx->engine->gt;
 
-static bool needs_mi_store_dword(struct drm_i915_private *i915)
-{
-	if (intel_gt_is_wedged(&i915->gt))
+	if (intel_gt_is_wedged(gt))
 		return false;
 
-	if (!HAS_ENGINE(i915, RCS0))
+	return gt->ggtt->num_fences;
+}
+
+static bool needs_mi_store_dword(struct context *ctx)
+{
+	if (intel_gt_is_wedged(ctx->engine->gt))
 		return false;
 
-	return intel_engine_can_store_dword(i915->engine[RCS0]);
+	return intel_engine_can_store_dword(ctx->engine);
 }
 
 static const struct igt_coherency_mode {
 	const char *name;
-	int (*set)(struct drm_i915_gem_object *, unsigned long offset, u32 v);
-	int (*get)(struct drm_i915_gem_object *, unsigned long offset, u32 *v);
-	bool (*valid)(struct drm_i915_private *i915);
+	int (*set)(struct context *ctx, unsigned long offset, u32 v);
+	int (*get)(struct context *ctx, unsigned long offset, u32 *v);
+	bool (*valid)(struct context *ctx);
 } igt_coherency_mode[] = {
 	{ "cpu", cpu_set, cpu_get, always_valid },
 	{ "gtt", gtt_set, gtt_get, needs_fence_registers },
@@ -286,18 +279,37 @@ static const struct igt_coherency_mode {
 	{ },
 };
 
+static struct intel_engine_cs *
+random_engine(struct drm_i915_private *i915, struct rnd_state *prng)
+{
+	struct intel_engine_cs *engine;
+	unsigned int count;
+
+	count = 0;
+	for_each_uabi_engine(engine, i915)
+		count++;
+
+	count = i915_prandom_u32_max_state(count, prng);
+	for_each_uabi_engine(engine, i915)
+		if (count-- == 0)
+			return engine;
+
+	return NULL;
+}
+
 static int igt_gem_coherency(void *arg)
 {
 	const unsigned int ncachelines = PAGE_SIZE/64;
-	I915_RND_STATE(prng);
 	struct drm_i915_private *i915 = arg;
 	const struct igt_coherency_mode *read, *write, *over;
-	struct drm_i915_gem_object *obj;
 	unsigned long count, n;
 	u32 *offsets, *values;
+	I915_RND_STATE(prng);
+	struct context ctx;
 	int err = 0;
 
-	/* We repeatedly write, overwrite and read from a sequence of
+	/*
+	 * We repeatedly write, overwrite and read from a sequence of
 	 * cachelines in order to try and detect incoherency (unflushed writes
 	 * from either the CPU or GPU). Each setter/getter uses our cache
 	 * domain API which should prevent incoherency.
@@ -311,31 +323,35 @@ static int igt_gem_coherency(void *arg)
 
 	values = offsets + ncachelines;
 
+	ctx.engine = random_engine(i915, &prng);
+	GEM_BUG_ON(!ctx.engine);
+	pr_info("%s: using %s\n", __func__, ctx.engine->name);
+
 	for (over = igt_coherency_mode; over->name; over++) {
 		if (!over->set)
 			continue;
 
-		if (!over->valid(i915))
+		if (!over->valid(&ctx))
 			continue;
 
 		for (write = igt_coherency_mode; write->name; write++) {
 			if (!write->set)
 				continue;
 
-			if (!write->valid(i915))
+			if (!write->valid(&ctx))
 				continue;
 
 			for (read = igt_coherency_mode; read->name; read++) {
 				if (!read->get)
 					continue;
 
-				if (!read->valid(i915))
+				if (!read->valid(&ctx))
 					continue;
 
 				for_each_prime_number_from(count, 1, ncachelines) {
-					obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
-					if (IS_ERR(obj)) {
-						err = PTR_ERR(obj);
+					ctx.obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+					if (IS_ERR(ctx.obj)) {
+						err = PTR_ERR(ctx.obj);
 						goto free;
 					}
 
@@ -344,7 +360,7 @@ static int igt_gem_coherency(void *arg)
 						values[n] = prandom_u32_state(&prng);
 
 					for (n = 0; n < count; n++) {
-						err = over->set(obj, offsets[n], ~values[n]);
+						err = over->set(&ctx, offsets[n], ~values[n]);
 						if (err) {
 							pr_err("Failed to set stale value[%ld/%ld] in object using %s, err=%d\n",
 							       n, count, over->name, err);
@@ -353,7 +369,7 @@ static int igt_gem_coherency(void *arg)
 					}
 
 					for (n = 0; n < count; n++) {
-						err = write->set(obj, offsets[n], values[n]);
+						err = write->set(&ctx, offsets[n], values[n]);
 						if (err) {
 							pr_err("Failed to set value[%ld/%ld] in object using %s, err=%d\n",
 							       n, count, write->name, err);
@@ -364,7 +380,7 @@ static int igt_gem_coherency(void *arg)
 					for (n = 0; n < count; n++) {
 						u32 found;
 
-						err = read->get(obj, offsets[n], &found);
+						err = read->get(&ctx, offsets[n], &found);
 						if (err) {
 							pr_err("Failed to get value[%ld/%ld] in object using %s, err=%d\n",
 							       n, count, read->name, err);
@@ -382,7 +398,7 @@ static int igt_gem_coherency(void *arg)
 						}
 					}
 
-					i915_gem_object_put(obj);
+					i915_gem_object_put(ctx.obj);
 				}
 			}
 		}
@@ -392,7 +408,7 @@ free:
 	return err;
 
 put_object:
-	i915_gem_object_put(obj);
+	i915_gem_object_put(ctx.obj);
 	goto free;
 }
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
index e5c235051ae5..62fabc023a83 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_context.c
@@ -32,7 +32,6 @@ static int live_nop_switch(void *arg)
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
 	struct i915_gem_context **ctx;
-	enum intel_engine_id id;
 	struct igt_live_test t;
 	struct drm_file *file;
 	unsigned long n;
@@ -67,7 +66,7 @@ static int live_nop_switch(void *arg)
 		}
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		struct i915_request *rq;
 		unsigned long end_time, prime;
 		ktime_t times[2] = {};
@@ -170,18 +169,24 @@ static int __live_parallel_switch1(void *data)
 		struct i915_request *rq = NULL;
 		int err, n;
 
-		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
-			i915_request_put(rq);
+		err = 0;
+		for (n = 0; !err && n < ARRAY_SIZE(arg->ce); n++) {
+			struct i915_request *prev = rq;
 
 			rq = i915_request_create(arg->ce[n]);
-			if (IS_ERR(rq))
+			if (IS_ERR(rq)) {
+				i915_request_put(prev);
 				return PTR_ERR(rq);
+			}
 
 			i915_request_get(rq);
+			if (prev) {
+				err = i915_request_await_dma_fence(rq, &prev->fence);
+				i915_request_put(prev);
+			}
+
 			i915_request_add(rq);
 		}
-
-		err = 0;
 		if (i915_request_wait(rq, 0, HZ / 5) < 0)
 			err = -ETIME;
 		i915_request_put(rq);
@@ -198,6 +203,7 @@ static int __live_parallel_switch1(void *data)
 static int __live_parallel_switchN(void *data)
 {
 	struct parallel_switch *arg = data;
+	struct i915_request *rq = NULL;
 	IGT_TIMEOUT(end_time);
 	unsigned long count;
 	int n;
@@ -205,17 +211,31 @@ static int __live_parallel_switchN(void *data)
 	count = 0;
 	do {
 		for (n = 0; n < ARRAY_SIZE(arg->ce); n++) {
-			struct i915_request *rq;
+			struct i915_request *prev = rq;
+			int err = 0;
 
 			rq = i915_request_create(arg->ce[n]);
-			if (IS_ERR(rq))
+			if (IS_ERR(rq)) {
+				i915_request_put(prev);
 				return PTR_ERR(rq);
+			}
+
+			i915_request_get(rq);
+			if (prev) {
+				err = i915_request_await_dma_fence(rq, &prev->fence);
+				i915_request_put(prev);
+			}
 
 			i915_request_add(rq);
+			if (err) {
+				i915_request_put(rq);
+				return err;
+			}
 		}
 
 		count++;
 	} while (!__igt_timeout(end_time, NULL));
+	i915_request_put(rq);
 
 	pr_info("%s: %lu switches (many)\n", arg->ce[0]->engine->name, count);
 	return 0;
@@ -325,6 +345,8 @@ static int live_parallel_switch(void *arg)
 			get_task_struct(data[n].tsk);
 		}
 
+		yield(); /* start all threads before we kthread_stop() */
+
 		for (n = 0; n < count; n++) {
 			int status;
 
@@ -583,7 +605,6 @@ static int igt_ctx_exec(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	int err = -ENODEV;
 
 	/*
@@ -595,7 +616,7 @@ static int igt_ctx_exec(void *arg)
 	if (!DRIVER_CAPS(i915)->has_logical_contexts)
 		return 0;
 
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		struct drm_i915_gem_object *obj = NULL;
 		unsigned long ncontexts, ndwords, dw;
 		struct i915_request *tq[5] = {};
@@ -711,7 +732,6 @@ static int igt_shared_ctx_exec(void *arg)
 	struct i915_request *tq[5] = {};
 	struct i915_gem_context *parent;
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	struct igt_live_test t;
 	struct drm_file *file;
 	int err = 0;
@@ -743,7 +763,7 @@ static int igt_shared_ctx_exec(void *arg)
 	if (err)
 		goto out_file;
 
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		unsigned long ncontexts, ndwords, dw;
 		struct drm_i915_gem_object *obj = NULL;
 		IGT_TIMEOUT(end_time);
@@ -1168,93 +1188,90 @@ __igt_ctx_sseu(struct drm_i915_private *i915,
 	       const char *name,
 	       unsigned int flags)
 {
-	struct intel_engine_cs *engine = i915->engine[RCS0];
 	struct drm_i915_gem_object *obj;
-	struct i915_gem_context *ctx;
-	struct intel_context *ce;
-	struct intel_sseu pg_sseu;
-	struct drm_file *file;
-	int ret;
-
-	if (INTEL_GEN(i915) < 9 || !engine)
-		return 0;
-
-	if (!RUNTIME_INFO(i915)->sseu.has_slice_pg)
-		return 0;
+	int inst = 0;
+	int ret = 0;
 
-	if (hweight32(engine->sseu.slice_mask) < 2)
+	if (INTEL_GEN(i915) < 9 || !RUNTIME_INFO(i915)->sseu.has_slice_pg)
 		return 0;
 
-	/*
-	 * Gen11 VME friendly power-gated configuration with half enabled
-	 * sub-slices.
-	 */
-	pg_sseu = engine->sseu;
-	pg_sseu.slice_mask = 1;
-	pg_sseu.subslice_mask =
-		~(~0 << (hweight32(engine->sseu.subslice_mask) / 2));
-
-	pr_info("SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
-		name, flags, hweight32(engine->sseu.slice_mask),
-		hweight32(pg_sseu.slice_mask));
-
-	file = mock_file(i915);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
 	if (flags & TEST_RESET)
 		igt_global_reset_lock(&i915->gt);
 
-	ctx = live_context(i915, file);
-	if (IS_ERR(ctx)) {
-		ret = PTR_ERR(ctx);
-		goto out_unlock;
-	}
-	i915_gem_context_clear_bannable(ctx); /* to reset and beyond! */
-
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		ret = PTR_ERR(obj);
 		goto out_unlock;
 	}
 
-	ce = i915_gem_context_get_engine(ctx, RCS0);
-	if (IS_ERR(ce)) {
-		ret = PTR_ERR(ce);
-		goto out_put;
-	}
+	do {
+		struct intel_engine_cs *engine;
+		struct intel_context *ce;
+		struct intel_sseu pg_sseu;
 
-	ret = intel_context_pin(ce);
-	if (ret)
-		goto out_context;
+		engine = intel_engine_lookup_user(i915,
+						  I915_ENGINE_CLASS_RENDER,
+						  inst++);
+		if (!engine)
+			break;
 
-	/* First set the default mask. */
-	ret = __sseu_test(name, flags, ce, obj, engine->sseu);
-	if (ret)
-		goto out_fail;
+		if (hweight32(engine->sseu.slice_mask) < 2)
+			continue;
 
-	/* Then set a power-gated configuration. */
-	ret = __sseu_test(name, flags, ce, obj, pg_sseu);
-	if (ret)
-		goto out_fail;
+		/*
+		 * Gen11 VME friendly power-gated configuration with
+		 * half enabled sub-slices.
+		 */
+		pg_sseu = engine->sseu;
+		pg_sseu.slice_mask = 1;
+		pg_sseu.subslice_mask =
+			~(~0 << (hweight32(engine->sseu.subslice_mask) / 2));
+
+		pr_info("%s: SSEU subtest '%s', flags=%x, def_slices=%u, pg_slices=%u\n",
+			engine->name, name, flags,
+			hweight32(engine->sseu.slice_mask),
+			hweight32(pg_sseu.slice_mask));
+
+		ce = intel_context_create(engine->kernel_context->gem_context,
+					  engine);
+		if (IS_ERR(ce)) {
+			ret = PTR_ERR(ce);
+			goto out_put;
+		}
 
-	/* Back to defaults. */
-	ret = __sseu_test(name, flags, ce, obj, engine->sseu);
-	if (ret)
-		goto out_fail;
+		ret = intel_context_pin(ce);
+		if (ret)
+			goto out_ce;
 
-	/* One last power-gated configuration for the road. */
-	ret = __sseu_test(name, flags, ce, obj, pg_sseu);
-	if (ret)
-		goto out_fail;
+		/* First set the default mask. */
+		ret = __sseu_test(name, flags, ce, obj, engine->sseu);
+		if (ret)
+			goto out_unpin;
+
+		/* Then set a power-gated configuration. */
+		ret = __sseu_test(name, flags, ce, obj, pg_sseu);
+		if (ret)
+			goto out_unpin;
+
+		/* Back to defaults. */
+		ret = __sseu_test(name, flags, ce, obj, engine->sseu);
+		if (ret)
+			goto out_unpin;
+
+		/* One last power-gated configuration for the road. */
+		ret = __sseu_test(name, flags, ce, obj, pg_sseu);
+		if (ret)
+			goto out_unpin;
+
+out_unpin:
+		intel_context_unpin(ce);
+out_ce:
+		intel_context_put(ce);
+	} while (!ret);
 
-out_fail:
 	if (igt_flush_test(i915))
 		ret = -EIO;
 
-	intel_context_unpin(ce);
-out_context:
-	intel_context_put(ce);
 out_put:
 	i915_gem_object_put(obj);
 
@@ -1262,8 +1279,6 @@ out_unlock:
 	if (flags & TEST_RESET)
 		igt_global_reset_unlock(&i915->gt);
 
-	mock_file_free(i915, file);
-
 	if (ret)
 		pr_err("%s: Failed with %d!\n", name, ret);
 
@@ -1651,7 +1666,6 @@ static int igt_vm_isolation(void *arg)
 	struct drm_file *file;
 	I915_RND_STATE(prng);
 	unsigned long count;
-	unsigned int id;
 	u64 vm_total;
 	int err;
 
@@ -1692,7 +1706,7 @@ static int igt_vm_isolation(void *arg)
 	vm_total -= I915_GTT_PAGE_SIZE;
 
 	count = 0;
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		IGT_TIMEOUT(end_time);
 		unsigned long this = 0;
 
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
index 65d4dbf91999..29b2077b73d2 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_mman.c
@@ -301,6 +301,9 @@ static int igt_partial_tiling(void *arg)
 	int tiling;
 	int err;
 
+	if (!i915_ggtt_has_aperture(&i915->ggtt))
+		return 0;
+
 	/* We want to check the page mapping and fencing of a large object
 	 * mmapped through the GTT. The object we create is larger than can
 	 * possibly be mmaped as a whole, and so we must use partial GGTT vma.
@@ -431,6 +434,9 @@ static int igt_smoke_tiling(void *arg)
 	IGT_TIMEOUT(end);
 	int err;
 
+	if (!i915_ggtt_has_aperture(&i915->ggtt))
+		return 0;
+
 	/*
 	 * igt_partial_tiling() does an exhastive check of partial tiling
 	 * chunking, but will undoubtably run out of time. Here, we do a
@@ -515,20 +521,19 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	struct i915_vma *vma;
-	int err;
 
-	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
+	for_each_uabi_engine(engine, i915) {
+		struct i915_request *rq;
+		struct i915_vma *vma;
+		int err;
 
-	err = i915_vma_pin(vma, 0, 0, PIN_USER);
-	if (err)
-		return err;
+		vma = i915_vma_instance(obj, &engine->gt->ggtt->vm, NULL);
+		if (IS_ERR(vma))
+			return PTR_ERR(vma);
 
-	for_each_engine(engine, i915, id) {
-		struct i915_request *rq;
+		err = i915_vma_pin(vma, 0, 0, PIN_USER);
+		if (err)
+			return err;
 
 		rq = i915_request_create(engine->kernel_context);
 		if (IS_ERR(rq)) {
@@ -544,12 +549,13 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		i915_vma_unlock(vma);
 
 		i915_request_add(rq);
+		i915_vma_unpin(vma);
+		if (err)
+			return err;
 	}
 
-	i915_vma_unpin(vma);
 	i915_gem_object_put(obj); /* leave it only alive via its active ref */
-
-	return err;
+	return 0;
 }
 
 static bool assert_mmap_offset(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
index 9ec55b3a3815..e8132aca0bb6 100644
--- a/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
+++ b/drivers/gpu/drm/i915/gem/selftests/i915_gem_object_blt.c
@@ -3,40 +3,241 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/sort.h>
+
 #include "gt/intel_gt.h"
+#include "gt/intel_engine_user.h"
 
 #include "i915_selftest.h"
 
+#include "gem/i915_gem_context.h"
 #include "selftests/igt_flush_test.h"
+#include "selftests/i915_random.h"
 #include "selftests/mock_drm.h"
 #include "huge_gem_object.h"
 #include "mock_context.h"
 
-static int igt_fill_blt(void *arg)
+static int wrap_ktime_compare(const void *A, const void *B)
+{
+	const ktime_t *a = A, *b = B;
+
+	return ktime_compare(*a, *b);
+}
+
+static int __perf_fill_blt(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	int inst = 0;
+
+	do {
+		struct intel_engine_cs *engine;
+		ktime_t t[5];
+		int pass;
+		int err;
+
+		engine = intel_engine_lookup_user(i915,
+						  I915_ENGINE_CLASS_COPY,
+						  inst++);
+		if (!engine)
+			return 0;
+
+		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
+			struct intel_context *ce = engine->kernel_context;
+			ktime_t t0, t1;
+
+			t0 = ktime_get();
+
+			err = i915_gem_object_fill_blt(obj, ce, 0);
+			if (err)
+				return err;
+
+			err = i915_gem_object_wait(obj,
+						   I915_WAIT_ALL,
+						   MAX_SCHEDULE_TIMEOUT);
+			if (err)
+				return err;
+
+			t1 = ktime_get();
+			t[pass] = ktime_sub(t1, t0);
+		}
+
+		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
+		pr_info("%s: blt %zd KiB fill: %lld MiB/s\n",
+			engine->name,
+			obj->base.size >> 10,
+			div64_u64(mul_u32_u32(4 * obj->base.size,
+					      1000 * 1000 * 1000),
+				  t[1] + 2 * t[2] + t[3]) >> 20);
+	} while (1);
+}
+
+static int perf_fill_blt(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct intel_context *ce = i915->engine[BCS0]->kernel_context;
-	struct drm_i915_gem_object *obj;
+	static const unsigned long sizes[] = {
+		SZ_4K,
+		SZ_64K,
+		SZ_2M,
+		SZ_64M
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		struct drm_i915_gem_object *obj;
+		int err;
+
+		obj = i915_gem_object_create_internal(i915, sizes[i]);
+		if (IS_ERR(obj))
+			return PTR_ERR(obj);
+
+		err = __perf_fill_blt(obj);
+		i915_gem_object_put(obj);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int __perf_copy_blt(struct drm_i915_gem_object *src,
+			   struct drm_i915_gem_object *dst)
+{
+	struct drm_i915_private *i915 = to_i915(src->base.dev);
+	int inst = 0;
+
+	do {
+		struct intel_engine_cs *engine;
+		ktime_t t[5];
+		int pass;
+
+		engine = intel_engine_lookup_user(i915,
+						  I915_ENGINE_CLASS_COPY,
+						  inst++);
+		if (!engine)
+			return 0;
+
+		for (pass = 0; pass < ARRAY_SIZE(t); pass++) {
+			struct intel_context *ce = engine->kernel_context;
+			ktime_t t0, t1;
+			int err;
+
+			t0 = ktime_get();
+
+			err = i915_gem_object_copy_blt(src, dst, ce);
+			if (err)
+				return err;
+
+			err = i915_gem_object_wait(dst,
+						   I915_WAIT_ALL,
+						   MAX_SCHEDULE_TIMEOUT);
+			if (err)
+				return err;
+
+			t1 = ktime_get();
+			t[pass] = ktime_sub(t1, t0);
+		}
+
+		sort(t, ARRAY_SIZE(t), sizeof(*t), wrap_ktime_compare, NULL);
+		pr_info("%s: blt %zd KiB copy: %lld MiB/s\n",
+			engine->name,
+			src->base.size >> 10,
+			div64_u64(mul_u32_u32(4 * src->base.size,
+					      1000 * 1000 * 1000),
+				  t[1] + 2 * t[2] + t[3]) >> 20);
+	} while (1);
+}
+
+static int perf_copy_blt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	static const unsigned long sizes[] = {
+		SZ_4K,
+		SZ_64K,
+		SZ_2M,
+		SZ_64M
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(sizes); i++) {
+		struct drm_i915_gem_object *src, *dst;
+		int err;
+
+		src = i915_gem_object_create_internal(i915, sizes[i]);
+		if (IS_ERR(src))
+			return PTR_ERR(src);
+
+		dst = i915_gem_object_create_internal(i915, sizes[i]);
+		if (IS_ERR(dst)) {
+			err = PTR_ERR(dst);
+			goto err_src;
+		}
+
+		err = __perf_copy_blt(src, dst);
+
+		i915_gem_object_put(dst);
+err_src:
+		i915_gem_object_put(src);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+struct igt_thread_arg {
+	struct drm_i915_private *i915;
 	struct rnd_state prng;
+	unsigned int n_cpus;
+};
+
+static int igt_fill_blt_thread(void *arg)
+{
+	struct igt_thread_arg *thread = arg;
+	struct drm_i915_private *i915 = thread->i915;
+	struct rnd_state *prng = &thread->prng;
+	struct drm_i915_gem_object *obj;
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct drm_file *file;
+	unsigned int prio;
 	IGT_TIMEOUT(end);
-	u32 *vaddr;
-	int err = 0;
+	int err;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ctx = live_context(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_file;
+	}
 
-	prandom_seed_state(&prng, i915_selftest.random_seed);
+	prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
+	ctx->sched.priority = I915_USER_PRIORITY(prio);
 
-	/*
-	 * XXX: needs some threads to scale all these tests, also maybe throw
-	 * in submission from higher priority context to see if we are
-	 * preempted for very large objects...
-	 */
+	ce = i915_gem_context_get_engine(ctx, BCS0);
+	GEM_BUG_ON(IS_ERR(ce));
 
 	do {
 		const u32 max_block_size = S16_MAX * PAGE_SIZE;
-		u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
-		u32 phys_sz = sz % (max_block_size + 1);
-		u32 val = prandom_u32_state(&prng);
+		u32 val = prandom_u32_state(prng);
+		u64 total = ce->vm->total;
+		u32 phys_sz;
+		u32 sz;
+		u32 *vaddr;
 		u32 i;
 
+		/*
+		 * If we have a tiny shared address space, like for the GGTT
+		 * then we can't be too greedy.
+		 */
+		if (i915_is_ggtt(ce->vm))
+			total = div64_u64(total, thread->n_cpus);
+
+		sz = min_t(u64, total >> 4, prandom_u32_state(prng));
+		phys_sz = sz % (max_block_size + 1);
+
 		sz = round_up(sz, PAGE_SIZE);
 		phys_sz = round_up(phys_sz, PAGE_SIZE);
 
@@ -98,28 +299,56 @@ err_flush:
 	if (err == -ENOMEM)
 		err = 0;
 
+	intel_context_put(ce);
+out_file:
+	mock_file_free(i915, file);
 	return err;
 }
 
-static int igt_copy_blt(void *arg)
+static int igt_copy_blt_thread(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct intel_context *ce = i915->engine[BCS0]->kernel_context;
+	struct igt_thread_arg *thread = arg;
+	struct drm_i915_private *i915 = thread->i915;
+	struct rnd_state *prng = &thread->prng;
 	struct drm_i915_gem_object *src, *dst;
-	struct rnd_state prng;
+	struct i915_gem_context *ctx;
+	struct intel_context *ce;
+	struct drm_file *file;
+	unsigned int prio;
 	IGT_TIMEOUT(end);
-	u32 *vaddr;
-	int err = 0;
+	int err;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
 
-	prandom_seed_state(&prng, i915_selftest.random_seed);
+	ctx = live_context(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_file;
+	}
+
+	prio = i915_prandom_u32_max_state(I915_PRIORITY_MAX, prng);
+	ctx->sched.priority = I915_USER_PRIORITY(prio);
+
+	ce = i915_gem_context_get_engine(ctx, BCS0);
+	GEM_BUG_ON(IS_ERR(ce));
 
 	do {
 		const u32 max_block_size = S16_MAX * PAGE_SIZE;
-		u32 sz = min_t(u64, ce->vm->total >> 4, prandom_u32_state(&prng));
-		u32 phys_sz = sz % (max_block_size + 1);
-		u32 val = prandom_u32_state(&prng);
+		u32 val = prandom_u32_state(prng);
+		u64 total = ce->vm->total;
+		u32 phys_sz;
+		u32 sz;
+		u32 *vaddr;
 		u32 i;
 
+		if (i915_is_ggtt(ce->vm))
+			total = div64_u64(total, thread->n_cpus);
+
+		sz = min_t(u64, total >> 4, prandom_u32_state(prng));
+		phys_sz = sz % (max_block_size + 1);
+
 		sz = round_up(sz, PAGE_SIZE);
 		phys_sz = round_up(phys_sz, PAGE_SIZE);
 
@@ -201,12 +430,85 @@ err_flush:
 	if (err == -ENOMEM)
 		err = 0;
 
+	intel_context_put(ce);
+out_file:
+	mock_file_free(i915, file);
+	return err;
+}
+
+static int igt_threaded_blt(struct drm_i915_private *i915,
+			    int (*blt_fn)(void *arg))
+{
+	struct igt_thread_arg *thread;
+	struct task_struct **tsk;
+	I915_RND_STATE(prng);
+	unsigned int n_cpus;
+	unsigned int i;
+	int err = 0;
+
+	n_cpus = num_online_cpus() + 1;
+
+	tsk = kcalloc(n_cpus, sizeof(struct task_struct *), GFP_KERNEL);
+	if (!tsk)
+		return 0;
+
+	thread = kcalloc(n_cpus, sizeof(struct igt_thread_arg), GFP_KERNEL);
+	if (!thread) {
+		kfree(tsk);
+		return 0;
+	}
+
+	for (i = 0; i < n_cpus; ++i) {
+		thread[i].i915 = i915;
+		thread[i].n_cpus = n_cpus;
+		thread[i].prng =
+			I915_RND_STATE_INITIALIZER(prandom_u32_state(&prng));
+
+		tsk[i] = kthread_run(blt_fn, &thread[i], "igt/blt-%d", i);
+		if (IS_ERR(tsk[i])) {
+			err = PTR_ERR(tsk[i]);
+			break;
+		}
+
+		get_task_struct(tsk[i]);
+	}
+
+	yield(); /* start all threads before we kthread_stop() */
+
+	for (i = 0; i < n_cpus; ++i) {
+		int status;
+
+		if (IS_ERR_OR_NULL(tsk[i]))
+			continue;
+
+		status = kthread_stop(tsk[i]);
+		if (status && !err)
+			err = status;
+
+		put_task_struct(tsk[i]);
+	}
+
+	kfree(tsk);
+	kfree(thread);
+
 	return err;
 }
 
+static int igt_fill_blt(void *arg)
+{
+	return igt_threaded_blt(arg, igt_fill_blt_thread);
+}
+
+static int igt_copy_blt(void *arg)
+{
+	return igt_threaded_blt(arg, igt_copy_blt_thread);
+}
+
 int i915_gem_object_blt_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(perf_fill_blt),
+		SUBTEST(perf_copy_blt),
 		SUBTEST(igt_fill_blt),
 		SUBTEST(igt_copy_blt),
 	};
diff --git a/drivers/gpu/drm/i915/gem/selftests/mock_context.c b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
index 74ddd682c9cd..29b8984f0e47 100644
--- a/drivers/gpu/drm/i915/gem/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/gem/selftests/mock_context.c
@@ -22,6 +22,8 @@ mock_context(struct drm_i915_private *i915,
 	INIT_LIST_HEAD(&ctx->link);
 	ctx->i915 = i915;
 
+	i915_gem_context_set_persistence(ctx);
+
 	mutex_init(&ctx->engines_mutex);
 	e = default_engines(ctx);
 	if (IS_ERR(e))
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index 59c3083c1ec1..ef7bc41ffffa 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -13,6 +13,7 @@
 #include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_pm.h"
+#include "intel_ring.h"
 
 static struct i915_global_context {
 	struct i915_global base;
@@ -309,10 +310,23 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
 	GEM_BUG_ON(rq->hw_context == ce);
 
 	if (rcu_access_pointer(rq->timeline) != tl) { /* timeline sharing! */
-		err = mutex_lock_interruptible_nested(&tl->mutex,
-						      SINGLE_DEPTH_NESTING);
-		if (err)
-			return err;
+		/*
+		 * Ideally, we just want to insert our foreign fence as
+		 * a barrier into the remove context, such that this operation
+		 * occurs after all current operations in that context, and
+		 * all future operations must occur after this.
+		 *
+		 * Currently, the timeline->last_request tracking is guarded
+		 * by its mutex and so we must obtain that to atomically
+		 * insert our barrier. However, since we already hold our
+		 * timeline->mutex, we must be careful against potential
+		 * inversion if we are the kernel_context as the remote context
+		 * will itself poke at the kernel_context when it needs to
+		 * unpin. Ergo, if already locked, we drop both locks and
+		 * try again (through the magic of userspace repeating EAGAIN).
+		 */
+		if (!mutex_trylock(&tl->mutex))
+			return -EAGAIN;
 
 		/* Queue this switch after current activity by this context. */
 		err = i915_active_fence_set(&tl->last_request, rq);
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index dd742ac2fbdb..68b3d317d959 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -12,6 +12,7 @@
 #include "i915_active.h"
 #include "intel_context_types.h"
 #include "intel_engine_types.h"
+#include "intel_ring_types.h"
 #include "intel_timeline_types.h"
 
 void intel_context_init(struct intel_context *ce,
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 93ea367fe624..01765a7ec18f 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -19,6 +19,7 @@
 #include "intel_workarounds.h"
 
 struct drm_printer;
+struct intel_gt;
 
 /* Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
  * but keeps the logic simple. Indeed, the whole purpose of this macro is just
@@ -89,38 +90,6 @@ struct drm_printer;
 /* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
  * do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
  */
-enum intel_engine_hangcheck_action {
-	ENGINE_IDLE = 0,
-	ENGINE_WAIT,
-	ENGINE_ACTIVE_SEQNO,
-	ENGINE_ACTIVE_HEAD,
-	ENGINE_ACTIVE_SUBUNITS,
-	ENGINE_WAIT_KICK,
-	ENGINE_DEAD,
-};
-
-static inline const char *
-hangcheck_action_to_str(const enum intel_engine_hangcheck_action a)
-{
-	switch (a) {
-	case ENGINE_IDLE:
-		return "idle";
-	case ENGINE_WAIT:
-		return "wait";
-	case ENGINE_ACTIVE_SEQNO:
-		return "active seqno";
-	case ENGINE_ACTIVE_HEAD:
-		return "active head";
-	case ENGINE_ACTIVE_SUBUNITS:
-		return "active subunits";
-	case ENGINE_WAIT_KICK:
-		return "wait kick";
-	case ENGINE_DEAD:
-		return "dead";
-	}
-
-	return "unknown";
-}
 
 static inline unsigned int
 execlists_num_ports(const struct intel_engine_execlists * const execlists)
@@ -131,9 +100,7 @@ execlists_num_ports(const struct intel_engine_execlists * const execlists)
 static inline struct i915_request *
 execlists_active(const struct intel_engine_execlists *execlists)
 {
-	GEM_BUG_ON(execlists->active - execlists->inflight >
-		   execlists_num_ports(execlists));
-	return READ_ONCE(*execlists->active);
+	return *READ_ONCE(execlists->active);
 }
 
 static inline void
@@ -206,126 +173,13 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)
 #define I915_HWS_CSB_WRITE_INDEX	0x1f
 #define CNL_HWS_CSB_WRITE_INDEX		0x2f
 
-struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size);
-int intel_ring_pin(struct intel_ring *ring);
-void intel_ring_reset(struct intel_ring *ring, u32 tail);
-unsigned int intel_ring_update_space(struct intel_ring *ring);
-void intel_ring_unpin(struct intel_ring *ring);
-void intel_ring_free(struct kref *ref);
-
-static inline struct intel_ring *intel_ring_get(struct intel_ring *ring)
-{
-	kref_get(&ring->ref);
-	return ring;
-}
-
-static inline void intel_ring_put(struct intel_ring *ring)
-{
-	kref_put(&ring->ref, intel_ring_free);
-}
-
 void intel_engine_stop(struct intel_engine_cs *engine);
 void intel_engine_cleanup(struct intel_engine_cs *engine);
 
-int __must_check intel_ring_cacheline_align(struct i915_request *rq);
-
-u32 __must_check *intel_ring_begin(struct i915_request *rq, unsigned int n);
-
-static inline void intel_ring_advance(struct i915_request *rq, u32 *cs)
-{
-	/* Dummy function.
-	 *
-	 * This serves as a placeholder in the code so that the reader
-	 * can compare against the preceding intel_ring_begin() and
-	 * check that the number of dwords emitted matches the space
-	 * reserved for the command packet (i.e. the value passed to
-	 * intel_ring_begin()).
-	 */
-	GEM_BUG_ON((rq->ring->vaddr + rq->ring->emit) != cs);
-}
-
-static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
-{
-	return pos & (ring->size - 1);
-}
-
-static inline bool
-intel_ring_offset_valid(const struct intel_ring *ring,
-			unsigned int pos)
-{
-	if (pos & -ring->size) /* must be strictly within the ring */
-		return false;
-
-	if (!IS_ALIGNED(pos, 8)) /* must be qword aligned */
-		return false;
-
-	return true;
-}
-
-static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
-{
-	/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
-	u32 offset = addr - rq->ring->vaddr;
-	GEM_BUG_ON(offset > rq->ring->size);
-	return intel_ring_wrap(rq->ring, offset);
-}
-
-static inline void
-assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
-{
-	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
-
-	/*
-	 * "Ring Buffer Use"
-	 *	Gen2 BSpec "1. Programming Environment" / 1.4.4.6
-	 *	Gen3 BSpec "1c Memory Interface Functions" / 2.3.4.5
-	 *	Gen4+ BSpec "1c Memory Interface and Command Stream" / 5.3.4.5
-	 * "If the Ring Buffer Head Pointer and the Tail Pointer are on the
-	 * same cacheline, the Head Pointer must not be greater than the Tail
-	 * Pointer."
-	 *
-	 * We use ring->head as the last known location of the actual RING_HEAD,
-	 * it may have advanced but in the worst case it is equally the same
-	 * as ring->head and so we should never program RING_TAIL to advance
-	 * into the same cacheline as ring->head.
-	 */
-#define cacheline(a) round_down(a, CACHELINE_BYTES)
-	GEM_BUG_ON(cacheline(tail) == cacheline(ring->head) &&
-		   tail < ring->head);
-#undef cacheline
-}
-
-static inline unsigned int
-intel_ring_set_tail(struct intel_ring *ring, unsigned int tail)
-{
-	/* Whilst writes to the tail are strictly order, there is no
-	 * serialisation between readers and the writers. The tail may be
-	 * read by i915_request_retire() just as it is being updated
-	 * by execlists, as although the breadcrumb is complete, the context
-	 * switch hasn't been seen.
-	 */
-	assert_ring_tail_valid(ring, tail);
-	ring->tail = tail;
-	return tail;
-}
-
-static inline unsigned int
-__intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
-{
-	/*
-	 * "If the Ring Buffer Head Pointer and the Tail Pointer are on the
-	 * same cacheline, the Head Pointer must not be greater than the Tail
-	 * Pointer."
-	 */
-	GEM_BUG_ON(!is_power_of_2(size));
-	return (head - tail - CACHELINE_BYTES) & (size - 1);
-}
-
-int intel_engines_init_mmio(struct drm_i915_private *i915);
-int intel_engines_setup(struct drm_i915_private *i915);
-int intel_engines_init(struct drm_i915_private *i915);
-void intel_engines_cleanup(struct drm_i915_private *i915);
+int intel_engines_init_mmio(struct intel_gt *gt);
+int intel_engines_setup(struct intel_gt *gt);
+int intel_engines_init(struct intel_gt *gt);
+void intel_engines_cleanup(struct intel_gt *gt);
 
 int intel_engine_init_common(struct intel_engine_cs *engine);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
@@ -434,61 +288,6 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...);
 
-static inline void intel_engine_context_in(struct intel_engine_cs *engine)
-{
-	unsigned long flags;
-
-	if (READ_ONCE(engine->stats.enabled) == 0)
-		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-
-	if (engine->stats.enabled > 0) {
-		if (engine->stats.active++ == 0)
-			engine->stats.start = ktime_get();
-		GEM_BUG_ON(engine->stats.active == 0);
-	}
-
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-}
-
-static inline void intel_engine_context_out(struct intel_engine_cs *engine)
-{
-	unsigned long flags;
-
-	if (READ_ONCE(engine->stats.enabled) == 0)
-		return;
-
-	write_seqlock_irqsave(&engine->stats.lock, flags);
-
-	if (engine->stats.enabled > 0) {
-		ktime_t last;
-
-		if (engine->stats.active && --engine->stats.active == 0) {
-			/*
-			 * Decrement the active context count and in case GPU
-			 * is now idle add up to the running total.
-			 */
-			last = ktime_sub(ktime_get(), engine->stats.start);
-
-			engine->stats.total = ktime_add(engine->stats.total,
-							last);
-		} else if (engine->stats.active == 0) {
-			/*
-			 * After turning on engine stats, context out might be
-			 * the first event in which case we account from the
-			 * time stats gathering was turned on.
-			 */
-			last = ktime_sub(ktime_get(), engine->stats.enabled_at);
-
-			engine->stats.total = ktime_add(engine->stats.total,
-							last);
-		}
-	}
-
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-}
-
 int intel_enable_engine_stats(struct intel_engine_cs *engine);
 void intel_disable_engine_stats(struct intel_engine_cs *engine);
 
@@ -525,4 +324,22 @@ void intel_engine_init_active(struct intel_engine_cs *engine,
 #define ENGINE_MOCK	1
 #define ENGINE_VIRTUAL	2
 
+static inline bool
+intel_engine_has_preempt_reset(const struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT))
+		return false;
+
+	return intel_engine_has_preemption(engine);
+}
+
+static inline bool
+intel_engine_has_timeslices(const struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return false;
+
+	return intel_engine_has_semaphores(engine);
+}
+
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index 051734c9b733..813bd3a610d2 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -28,15 +28,16 @@
 
 #include "i915_drv.h"
 
-#include "gt/intel_gt.h"
-
+#include "intel_context.h"
 #include "intel_engine.h"
 #include "intel_engine_pm.h"
 #include "intel_engine_pool.h"
 #include "intel_engine_user.h"
-#include "intel_context.h"
+#include "intel_gt.h"
+#include "intel_gt_requests.h"
 #include "intel_lrc.h"
 #include "intel_reset.h"
+#include "intel_ring.h"
 
 /* Haswell does have the CXT_SIZE register however it does not appear to be
  * valid. Now, docs explain in dwords what is in the context object. The full
@@ -308,6 +309,15 @@ static int intel_engine_setup(struct intel_gt *gt, enum intel_engine_id id)
 	engine->instance = info->instance;
 	__sprint_engine_name(engine);
 
+	engine->props.heartbeat_interval_ms =
+		CONFIG_DRM_I915_HEARTBEAT_INTERVAL;
+	engine->props.preempt_timeout_ms =
+		CONFIG_DRM_I915_PREEMPT_TIMEOUT;
+	engine->props.stop_timeout_ms =
+		CONFIG_DRM_I915_STOP_TIMEOUT;
+	engine->props.timeslice_duration_ms =
+		CONFIG_DRM_I915_TIMESLICE_DURATION;
+
 	/*
 	 * To be overridden by the backend on setup. However to facilitate
 	 * cleanup on error during setup, we always provide the destroy vfunc.
@@ -370,38 +380,40 @@ static void __setup_engine_capabilities(struct intel_engine_cs *engine)
 	}
 }
 
-static void intel_setup_engine_capabilities(struct drm_i915_private *i915)
+static void intel_setup_engine_capabilities(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, gt, id)
 		__setup_engine_capabilities(engine);
 }
 
 /**
  * intel_engines_cleanup() - free the resources allocated for Command Streamers
- * @i915: the i915 devic
+ * @gt: pointer to struct intel_gt
  */
-void intel_engines_cleanup(struct drm_i915_private *i915)
+void intel_engines_cleanup(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		engine->destroy(engine);
-		i915->engine[id] = NULL;
+		gt->engine[id] = NULL;
+		gt->i915->engine[id] = NULL;
 	}
 }
 
 /**
  * intel_engines_init_mmio() - allocate and prepare the Engine Command Streamers
- * @i915: the i915 device
+ * @gt: pointer to struct intel_gt
  *
  * Return: non-zero if the initialization failed.
  */
-int intel_engines_init_mmio(struct drm_i915_private *i915)
+int intel_engines_init_mmio(struct intel_gt *gt)
 {
+	struct drm_i915_private *i915 = gt->i915;
 	struct intel_device_info *device_info = mkwrite_device_info(i915);
 	const unsigned int engine_mask = INTEL_INFO(i915)->engine_mask;
 	unsigned int mask = 0;
@@ -419,7 +431,7 @@ int intel_engines_init_mmio(struct drm_i915_private *i915)
 		if (!HAS_ENGINE(i915, i))
 			continue;
 
-		err = intel_engine_setup(&i915->gt, i);
+		err = intel_engine_setup(gt, i);
 		if (err)
 			goto cleanup;
 
@@ -436,36 +448,36 @@ int intel_engines_init_mmio(struct drm_i915_private *i915)
 
 	RUNTIME_INFO(i915)->num_engines = hweight32(mask);
 
-	intel_gt_check_and_clear_faults(&i915->gt);
+	intel_gt_check_and_clear_faults(gt);
 
-	intel_setup_engine_capabilities(i915);
+	intel_setup_engine_capabilities(gt);
 
 	return 0;
 
 cleanup:
-	intel_engines_cleanup(i915);
+	intel_engines_cleanup(gt);
 	return err;
 }
 
 /**
  * intel_engines_init() - init the Engine Command Streamers
- * @i915: i915 device private
+ * @gt: pointer to struct intel_gt
  *
  * Return: non-zero if the initialization failed.
  */
-int intel_engines_init(struct drm_i915_private *i915)
+int intel_engines_init(struct intel_gt *gt)
 {
 	int (*init)(struct intel_engine_cs *engine);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err;
 
-	if (HAS_EXECLISTS(i915))
+	if (HAS_EXECLISTS(gt->i915))
 		init = intel_execlists_submission_init;
 	else
 		init = intel_ring_submission_init;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = init(engine);
 		if (err)
 			goto cleanup;
@@ -474,7 +486,7 @@ int intel_engines_init(struct drm_i915_private *i915)
 	return 0;
 
 cleanup:
-	intel_engines_cleanup(i915);
+	intel_engines_cleanup(gt);
 	return err;
 }
 
@@ -518,7 +530,7 @@ static int pin_ggtt_status_page(struct intel_engine_cs *engine,
 	unsigned int flags;
 
 	flags = PIN_GLOBAL;
-	if (!HAS_LLC(engine->i915))
+	if (!HAS_LLC(engine->i915) && i915_ggtt_has_aperture(engine->gt->ggtt))
 		/*
 		 * On g33, we cannot place HWS above 256MiB, so
 		 * restrict its pinning to the low mappable arena.
@@ -602,9 +614,9 @@ static int intel_engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_active(engine, ENGINE_PHYSICAL);
 	intel_engine_init_breadcrumbs(engine);
 	intel_engine_init_execlists(engine);
-	intel_engine_init_hangcheck(engine);
 	intel_engine_init_cmd_parser(engine);
 	intel_engine_init__pm(engine);
+	intel_engine_init_retire(engine);
 
 	intel_engine_pool_init(&engine->pool);
 
@@ -621,26 +633,26 @@ static int intel_engine_setup_common(struct intel_engine_cs *engine)
 
 /**
  * intel_engines_setup- setup engine state not requiring hw access
- * @i915: Device to setup.
+ * @gt: pointer to struct intel_gt
  *
  * Initializes engine structure members shared between legacy and execlists
  * submission modes which do not require hardware access.
  *
  * Typically done early in the submission mode specific engine setup stage.
  */
-int intel_engines_setup(struct drm_i915_private *i915)
+int intel_engines_setup(struct intel_gt *gt)
 {
 	int (*setup)(struct intel_engine_cs *engine);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err;
 
-	if (HAS_EXECLISTS(i915))
+	if (HAS_EXECLISTS(gt->i915))
 		setup = intel_execlists_submission_setup;
 	else
 		setup = intel_ring_submission_setup;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		err = intel_engine_setup_common(engine);
 		if (err)
 			goto cleanup;
@@ -658,7 +670,7 @@ int intel_engines_setup(struct drm_i915_private *i915)
 	return 0;
 
 cleanup:
-	intel_engines_cleanup(i915);
+	intel_engines_cleanup(gt);
 	return err;
 }
 
@@ -827,6 +839,7 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 
 	cleanup_status_page(engine);
 
+	intel_engine_fini_retire(engine);
 	intel_engine_pool_fini(&engine->pool);
 	intel_engine_fini_breadcrumbs(engine);
 	intel_engine_cleanup_cmd_parser(engine);
@@ -873,6 +886,21 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 	return bbaddr;
 }
 
+static unsigned long stop_timeout(const struct intel_engine_cs *engine)
+{
+	if (in_atomic() || irqs_disabled()) /* inside atomic preempt-reset? */
+		return 0;
+
+	/*
+	 * If we are doing a normal GPU reset, we can take our time and allow
+	 * the engine to quiesce. We've stopped submission to the engine, and
+	 * if we wait long enough an innocent context should complete and
+	 * leave the engine idle. So they should not be caught unaware by
+	 * the forthcoming GPU reset (which usually follows the stop_cs)!
+	 */
+	return READ_ONCE(engine->props.stop_timeout_ms);
+}
+
 int intel_engine_stop_cs(struct intel_engine_cs *engine)
 {
 	struct intel_uncore *uncore = engine->uncore;
@@ -890,7 +918,7 @@ int intel_engine_stop_cs(struct intel_engine_cs *engine)
 	err = 0;
 	if (__intel_wait_for_register_fw(uncore,
 					 mode, MODE_IDLE, MODE_IDLE,
-					 1000, 0,
+					 1000, stop_timeout(engine),
 					 NULL)) {
 		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
 		err = -ETIMEDOUT;
@@ -1318,10 +1346,11 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 		unsigned int idx;
 		u8 read, write;
 
-		drm_printf(m, "\tExeclist tasklet queued? %s (%s), timeslice? %s\n",
+		drm_printf(m, "\tExeclist tasklet queued? %s (%s), preempt? %s, timeslice? %s\n",
 			   yesno(test_bit(TASKLET_STATE_SCHED,
 					  &engine->execlists.tasklet.state)),
 			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)),
+			   repr_timer(&engine->execlists.preempt),
 			   repr_timer(&engine->execlists.timer));
 
 		read = execlists->csb_head;
@@ -1345,6 +1374,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 		}
 
 		execlists_active_lock_bh(execlists);
+		rcu_read_lock();
 		for (port = execlists->active; (rq = *port); port++) {
 			char hdr[80];
 			int len;
@@ -1382,6 +1412,7 @@ static void intel_engine_print_registers(struct intel_engine_cs *engine,
 			if (tl)
 				intel_timeline_put(tl);
 		}
+		rcu_read_unlock();
 		execlists_active_unlock_bh(execlists);
 	} else if (INTEL_GEN(dev_priv) > 6) {
 		drm_printf(m, "\tPP_DIR_BASE: 0x%08x\n",
@@ -1447,8 +1478,13 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "*** WEDGED ***\n");
 
 	drm_printf(m, "\tAwake? %d\n", atomic_read(&engine->wakeref.count));
-	drm_printf(m, "\tHangcheck: %d ms ago\n",
-		   jiffies_to_msecs(jiffies - engine->hangcheck.action_timestamp));
+
+	rcu_read_lock();
+	rq = READ_ONCE(engine->heartbeat.systole);
+	if (rq)
+		drm_printf(m, "\tHeartbeat: %d ms ago\n",
+			   jiffies_to_msecs(jiffies - rq->emitted_jiffies));
+	rcu_read_unlock();
 	drm_printf(m, "\tReset count: %d (global %d)\n",
 		   i915_reset_engine_count(error, engine),
 		   i915_reset_count(error));
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
new file mode 100644
index 000000000000..06aa14c7aa8c
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.c
@@ -0,0 +1,234 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_request.h"
+
+#include "intel_context.h"
+#include "intel_engine_heartbeat.h"
+#include "intel_engine_pm.h"
+#include "intel_engine.h"
+#include "intel_gt.h"
+#include "intel_reset.h"
+
+/*
+ * While the engine is active, we send a periodic pulse along the engine
+ * to check on its health and to flush any idle-barriers. If that request
+ * is stuck, and we fail to preempt it, we declare the engine hung and
+ * issue a reset -- in the hope that restores progress.
+ */
+
+static bool next_heartbeat(struct intel_engine_cs *engine)
+{
+	long delay;
+
+	delay = READ_ONCE(engine->props.heartbeat_interval_ms);
+	if (!delay)
+		return false;
+
+	delay = msecs_to_jiffies_timeout(delay);
+	if (delay >= HZ)
+		delay = round_jiffies_up_relative(delay);
+	schedule_delayed_work(&engine->heartbeat.work, delay);
+
+	return true;
+}
+
+static void idle_pulse(struct intel_engine_cs *engine, struct i915_request *rq)
+{
+	engine->wakeref_serial = READ_ONCE(engine->serial) + 1;
+	i915_request_add_active_barriers(rq);
+}
+
+static void show_heartbeat(const struct i915_request *rq,
+			   struct intel_engine_cs *engine)
+{
+	struct drm_printer p = drm_debug_printer("heartbeat");
+
+	intel_engine_dump(engine, &p,
+			  "%s heartbeat {prio:%d} not ticking\n",
+			  engine->name,
+			  rq->sched.attr.priority);
+}
+
+static void heartbeat(struct work_struct *wrk)
+{
+	struct i915_sched_attr attr = {
+		.priority = I915_USER_PRIORITY(I915_PRIORITY_MIN),
+	};
+	struct intel_engine_cs *engine =
+		container_of(wrk, typeof(*engine), heartbeat.work.work);
+	struct intel_context *ce = engine->kernel_context;
+	struct i915_request *rq;
+
+	if (!intel_engine_pm_get_if_awake(engine))
+		return;
+
+	rq = engine->heartbeat.systole;
+	if (rq && i915_request_completed(rq)) {
+		i915_request_put(rq);
+		engine->heartbeat.systole = NULL;
+	}
+
+	if (intel_gt_is_wedged(engine->gt))
+		goto out;
+
+	if (engine->heartbeat.systole) {
+		if (engine->schedule &&
+		    rq->sched.attr.priority < I915_PRIORITY_BARRIER) {
+			/*
+			 * Gradually raise the priority of the heartbeat to
+			 * give high priority work [which presumably desires
+			 * low latency and no jitter] the chance to naturally
+			 * complete before being preempted.
+			 */
+			attr.priority = I915_PRIORITY_MASK;
+			if (rq->sched.attr.priority >= attr.priority)
+				attr.priority |= I915_USER_PRIORITY(I915_PRIORITY_HEARTBEAT);
+			if (rq->sched.attr.priority >= attr.priority)
+				attr.priority = I915_PRIORITY_BARRIER;
+
+			local_bh_disable();
+			engine->schedule(rq, &attr);
+			local_bh_enable();
+		} else {
+			if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
+				show_heartbeat(rq, engine);
+
+			intel_gt_handle_error(engine->gt, engine->mask,
+					      I915_ERROR_CAPTURE,
+					      "stopped heartbeat on %s",
+					      engine->name);
+		}
+		goto out;
+	}
+
+	if (engine->wakeref_serial == engine->serial)
+		goto out;
+
+	mutex_lock(&ce->timeline->mutex);
+
+	intel_context_enter(ce);
+	rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN);
+	intel_context_exit(ce);
+	if (IS_ERR(rq))
+		goto unlock;
+
+	idle_pulse(engine, rq);
+	if (i915_modparams.enable_hangcheck)
+		engine->heartbeat.systole = i915_request_get(rq);
+
+	__i915_request_commit(rq);
+	__i915_request_queue(rq, &attr);
+
+unlock:
+	mutex_unlock(&ce->timeline->mutex);
+out:
+	if (!next_heartbeat(engine))
+		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
+	intel_engine_pm_put(engine);
+}
+
+void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine)
+{
+	if (!IS_ACTIVE(CONFIG_DRM_I915_HEARTBEAT_INTERVAL))
+		return;
+
+	next_heartbeat(engine);
+}
+
+void intel_engine_park_heartbeat(struct intel_engine_cs *engine)
+{
+	if (cancel_delayed_work(&engine->heartbeat.work))
+		i915_request_put(fetch_and_zero(&engine->heartbeat.systole));
+}
+
+void intel_engine_init_heartbeat(struct intel_engine_cs *engine)
+{
+	INIT_DELAYED_WORK(&engine->heartbeat.work, heartbeat);
+}
+
+int intel_engine_set_heartbeat(struct intel_engine_cs *engine,
+			       unsigned long delay)
+{
+	int err;
+
+	/* Send one last pulse before to cleanup persistent hogs */
+	if (!delay && IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT)) {
+		err = intel_engine_pulse(engine);
+		if (err)
+			return err;
+	}
+
+	WRITE_ONCE(engine->props.heartbeat_interval_ms, delay);
+
+	if (intel_engine_pm_get_if_awake(engine)) {
+		if (delay)
+			intel_engine_unpark_heartbeat(engine);
+		else
+			intel_engine_park_heartbeat(engine);
+		intel_engine_pm_put(engine);
+	}
+
+	return 0;
+}
+
+int intel_engine_pulse(struct intel_engine_cs *engine)
+{
+	struct i915_sched_attr attr = { .priority = I915_PRIORITY_BARRIER };
+	struct intel_context *ce = engine->kernel_context;
+	struct i915_request *rq;
+	int err = 0;
+
+	if (!intel_engine_has_preemption(engine))
+		return -ENODEV;
+
+	if (!intel_engine_pm_get_if_awake(engine))
+		return 0;
+
+	if (mutex_lock_interruptible(&ce->timeline->mutex))
+		goto out_rpm;
+
+	intel_context_enter(ce);
+	rq = __i915_request_create(ce, GFP_NOWAIT | __GFP_NOWARN);
+	intel_context_exit(ce);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_unlock;
+	}
+
+	rq->flags |= I915_REQUEST_SENTINEL;
+	idle_pulse(engine, rq);
+
+	__i915_request_commit(rq);
+	__i915_request_queue(rq, &attr);
+
+out_unlock:
+	mutex_unlock(&ce->timeline->mutex);
+out_rpm:
+	intel_engine_pm_put(engine);
+	return err;
+}
+
+int intel_engine_flush_barriers(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	if (llist_empty(&engine->barrier_tasks))
+		return 0;
+
+	rq = i915_request_create(engine->kernel_context);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	idle_pulse(engine, rq);
+	i915_request_add(rq);
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_engine_heartbeat.c"
+#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h
new file mode 100644
index 000000000000..a7b8c0f9e005
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_engine_heartbeat.h
@@ -0,0 +1,23 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_ENGINE_HEARTBEAT_H
+#define INTEL_ENGINE_HEARTBEAT_H
+
+struct intel_engine_cs;
+
+void intel_engine_init_heartbeat(struct intel_engine_cs *engine);
+
+int intel_engine_set_heartbeat(struct intel_engine_cs *engine,
+			       unsigned long delay);
+
+void intel_engine_park_heartbeat(struct intel_engine_cs *engine);
+void intel_engine_unpark_heartbeat(struct intel_engine_cs *engine);
+
+int intel_engine_pulse(struct intel_engine_cs *engine);
+int intel_engine_flush_barriers(struct intel_engine_cs *engine);
+
+#endif /* INTEL_ENGINE_HEARTBEAT_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.c b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
index 67eb6183648a..0e1ad4a4bd97 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.c
@@ -7,11 +7,13 @@
 #include "i915_drv.h"
 
 #include "intel_engine.h"
+#include "intel_engine_heartbeat.h"
 #include "intel_engine_pm.h"
 #include "intel_engine_pool.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_rc6.h"
+#include "intel_ring.h"
 
 static int __engine_unpark(struct intel_wakeref *wf)
 {
@@ -34,7 +36,7 @@ static int __engine_unpark(struct intel_wakeref *wf)
 	if (engine->unpark)
 		engine->unpark(engine);
 
-	intel_engine_init_hangcheck(engine);
+	intel_engine_unpark_heartbeat(engine);
 	return 0;
 }
 
@@ -71,8 +73,42 @@ static inline void __timeline_mark_unlock(struct intel_context *ce,
 
 #endif /* !IS_ENABLED(CONFIG_LOCKDEP) */
 
+static void
+__queue_and_release_pm(struct i915_request *rq,
+		       struct intel_timeline *tl,
+		       struct intel_engine_cs *engine)
+{
+	struct intel_gt_timelines *timelines = &engine->gt->timelines;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * We have to serialise all potential retirement paths with our
+	 * submission, as we don't want to underflow either the
+	 * engine->wakeref.counter or our timeline->active_count.
+	 *
+	 * Equally, we cannot allow a new submission to start until
+	 * after we finish queueing, nor could we allow that submitter
+	 * to retire us before we are ready!
+	 */
+	spin_lock(&timelines->lock);
+
+	/* Let intel_gt_retire_requests() retire us (acquired under lock) */
+	if (!atomic_fetch_inc(&tl->active_count))
+		list_add_tail(&tl->link, &timelines->active_list);
+
+	/* Hand the request over to HW and so engine_retire() */
+	__i915_request_queue(rq, NULL);
+
+	/* Let new submissions commence (and maybe retire this timeline) */
+	__intel_wakeref_defer_park(&engine->wakeref);
+
+	spin_unlock(&timelines->lock);
+}
+
 static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 {
+	struct intel_context *ce = engine->kernel_context;
 	struct i915_request *rq;
 	unsigned long flags;
 	bool result = true;
@@ -96,31 +132,45 @@ static bool switch_to_kernel_context(struct intel_engine_cs *engine)
 	 * This should hold true as we can only park the engine after
 	 * retiring the last request, thus all rings should be empty and
 	 * all timelines idle.
+	 *
+	 * For unlocking, there are 2 other parties and the GPU who have a
+	 * stake here.
+	 *
+	 * A new gpu user will be waiting on the engine-pm to start their
+	 * engine_unpark. New waiters are predicated on engine->wakeref.count
+	 * and so intel_wakeref_defer_park() acts like a mutex_unlock of the
+	 * engine->wakeref.
+	 *
+	 * The other party is intel_gt_retire_requests(), which is walking the
+	 * list of active timelines looking for completions. Meanwhile as soon
+	 * as we call __i915_request_queue(), the GPU may complete our request.
+	 * Ergo, if we put ourselves on the timelines.active_list
+	 * (se intel_timeline_enter()) before we increment the
+	 * engine->wakeref.count, we may see the request completion and retire
+	 * it causing an undeflow of the engine->wakeref.
 	 */
-	flags = __timeline_mark_lock(engine->kernel_context);
+	flags = __timeline_mark_lock(ce);
+	GEM_BUG_ON(atomic_read(&ce->timeline->active_count) < 0);
 
-	rq = __i915_request_create(engine->kernel_context, GFP_NOWAIT);
+	rq = __i915_request_create(ce, GFP_NOWAIT);
 	if (IS_ERR(rq))
 		/* Context switch failed, hope for the best! Maybe reset? */
 		goto out_unlock;
 
-	intel_timeline_enter(i915_request_timeline(rq));
-
 	/* Check again on the next retirement. */
 	engine->wakeref_serial = engine->serial + 1;
 	i915_request_add_active_barriers(rq);
 
 	/* Install ourselves as a preemption barrier */
-	rq->sched.attr.priority = I915_PRIORITY_UNPREEMPTABLE;
+	rq->sched.attr.priority = I915_PRIORITY_BARRIER;
 	__i915_request_commit(rq);
 
-	/* Release our exclusive hold on the engine */
-	__intel_wakeref_defer_park(&engine->wakeref);
-	__i915_request_queue(rq, NULL);
+	/* Expose ourselves to the world */
+	__queue_and_release_pm(rq, ce->timeline, engine);
 
 	result = false;
 out_unlock:
-	__timeline_mark_unlock(engine->kernel_context, flags);
+	__timeline_mark_unlock(ce, flags);
 	return result;
 }
 
@@ -158,6 +208,7 @@ static int __engine_park(struct intel_wakeref *wf)
 
 	call_idle_barriers(engine); /* cleanup after wedging */
 
+	intel_engine_park_heartbeat(engine);
 	intel_engine_disarm_breadcrumbs(engine);
 	intel_engine_pool_park(&engine->pool);
 
@@ -174,7 +225,8 @@ static int __engine_park(struct intel_wakeref *wf)
 
 	engine->execlists.no_priolist = false;
 
-	intel_gt_pm_put(engine->gt);
+	/* While gt calls i915_vma_parked(), we have to break the lock cycle */
+	intel_gt_pm_put_async(engine->gt);
 	return 0;
 }
 
@@ -188,6 +240,7 @@ void intel_engine_init__pm(struct intel_engine_cs *engine)
 	struct intel_runtime_pm *rpm = engine->uncore->rpm;
 
 	intel_wakeref_init(&engine->wakeref, rpm, &wf_ops);
+	intel_engine_init_heartbeat(engine);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_pm.h b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
index 739c50fefcef..24e20344dc22 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_pm.h
@@ -31,6 +31,16 @@ static inline void intel_engine_pm_put(struct intel_engine_cs *engine)
 	intel_wakeref_put(&engine->wakeref);
 }
 
+static inline void intel_engine_pm_put_async(struct intel_engine_cs *engine)
+{
+	intel_wakeref_put_async(&engine->wakeref);
+}
+
+static inline void intel_engine_pm_flush(struct intel_engine_cs *engine)
+{
+	intel_wakeref_unlock_wait(&engine->wakeref);
+}
+
 void intel_engine_init__pm(struct intel_engine_cs *engine);
 
 #endif /* INTEL_ENGINE_PM_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_types.h b/drivers/gpu/drm/i915/gt/intel_engine_types.h
index 3451be034caf..17f1f1441efc 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine_types.h
@@ -15,6 +15,7 @@
 #include <linux/rbtree.h>
 #include <linux/timer.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
 
 #include "i915_gem.h"
 #include "i915_pmu.h"
@@ -58,6 +59,7 @@ struct i915_gem_context;
 struct i915_request;
 struct i915_sched_attr;
 struct intel_gt;
+struct intel_ring;
 struct intel_uncore;
 
 typedef u8 intel_engine_mask_t;
@@ -76,40 +78,6 @@ struct intel_instdone {
 	u32 row[I915_MAX_SLICES][I915_MAX_SUBSLICES];
 };
 
-struct intel_engine_hangcheck {
-	u64 acthd;
-	u32 last_ring;
-	u32 last_head;
-	unsigned long action_timestamp;
-	struct intel_instdone instdone;
-};
-
-struct intel_ring {
-	struct kref ref;
-	struct i915_vma *vma;
-	void *vaddr;
-
-	/*
-	 * As we have two types of rings, one global to the engine used
-	 * by ringbuffer submission and those that are exclusive to a
-	 * context used by execlists, we have to play safe and allow
-	 * atomic updates to the pin_count. However, the actual pinning
-	 * of the context is either done during initialisation for
-	 * ringbuffer submission or serialised as part of the context
-	 * pinning for execlists, and so we do not need a mutex ourselves
-	 * to serialise intel_ring_pin/intel_ring_unpin.
-	 */
-	atomic_t pin_count;
-
-	u32 head;
-	u32 tail;
-	u32 emit;
-
-	u32 space;
-	u32 size;
-	u32 effective_size;
-};
-
 /*
  * we use a single page to load ctx workarounds so all of these
  * values are referred in terms of dwords
@@ -175,6 +143,11 @@ struct intel_engine_execlists {
 	struct timer_list timer;
 
 	/**
+	 * @preempt: reset the current context if it fails to give way
+	 */
+	struct timer_list preempt;
+
+	/**
 	 * @default_priolist: priority list for I915_PRIORITY_NORMAL
 	 */
 	struct i915_priolist default_priolist;
@@ -326,6 +299,11 @@ struct intel_engine_cs {
 
 	intel_engine_mask_t saturated; /* submitting semaphores too late? */
 
+	struct {
+		struct delayed_work work;
+		struct i915_request *systole;
+	} heartbeat;
+
 	unsigned long serial;
 
 	unsigned long wakeref_serial;
@@ -473,18 +451,25 @@ struct intel_engine_cs {
 
 	struct intel_engine_execlists execlists;
 
+	/*
+	 * Keep track of completed timelines on this engine for early
+	 * retirement with the goal of quickly enabling powersaving as
+	 * soon as the engine is idle.
+	 */
+	struct intel_timeline *retire;
+	struct work_struct retire_work;
+
 	/* status_notifier: list of callbacks for context-switch changes */
 	struct atomic_notifier_head context_status_notifier;
 
-	struct intel_engine_hangcheck hangcheck;
-
-#define I915_ENGINE_NEEDS_CMD_PARSER BIT(0)
+#define I915_ENGINE_USING_CMD_PARSER BIT(0)
 #define I915_ENGINE_SUPPORTS_STATS   BIT(1)
 #define I915_ENGINE_HAS_PREEMPTION   BIT(2)
 #define I915_ENGINE_HAS_SEMAPHORES   BIT(3)
 #define I915_ENGINE_NEEDS_BREADCRUMB_TASKLET BIT(4)
 #define I915_ENGINE_IS_VIRTUAL       BIT(5)
 #define I915_ENGINE_HAS_RELATIVE_MMIO BIT(6)
+#define I915_ENGINE_REQUIRES_CMD_PARSER BIT(7)
 	unsigned int flags;
 
 	/*
@@ -542,12 +527,25 @@ struct intel_engine_cs {
 		 */
 		ktime_t total;
 	} stats;
+
+	struct {
+		unsigned long heartbeat_interval_ms;
+		unsigned long preempt_timeout_ms;
+		unsigned long stop_timeout_ms;
+		unsigned long timeslice_duration_ms;
+	} props;
 };
 
 static inline bool
-intel_engine_needs_cmd_parser(const struct intel_engine_cs *engine)
+intel_engine_using_cmd_parser(const struct intel_engine_cs *engine)
+{
+	return engine->flags & I915_ENGINE_USING_CMD_PARSER;
+}
+
+static inline bool
+intel_engine_requires_cmd_parser(const struct intel_engine_cs *engine)
 {
-	return engine->flags & I915_ENGINE_NEEDS_CMD_PARSER;
+	return engine->flags & I915_ENGINE_REQUIRES_CMD_PARSER;
 }
 
 static inline bool
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 1c4b6c9642ad..4c26daf7ee46 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -9,6 +9,7 @@
 #include "intel_gt_requests.h"
 #include "intel_mocs.h"
 #include "intel_rc6.h"
+#include "intel_rps.h"
 #include "intel_uncore.h"
 #include "intel_pm.h"
 
@@ -22,19 +23,19 @@ void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915)
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
-	intel_gt_init_hangcheck(gt);
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
 	intel_gt_pm_init_early(gt);
+
+	intel_rps_init_early(&gt->rps);
 	intel_uc_init_early(&gt->uc);
 }
 
-void intel_gt_init_hw_early(struct drm_i915_private *i915)
+void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt)
 {
-	i915->gt.ggtt = &i915->ggtt;
+	gt->ggtt = ggtt;
 
-	/* BIOS often leaves RC6 enabled, but disable it for hw init */
-	intel_gt_pm_disable(&i915->gt);
+	intel_gt_sanitize(gt, false);
 }
 
 static void init_unused_ring(struct intel_gt *gt, u32 base)
@@ -321,8 +322,7 @@ void intel_gt_chipset_flush(struct intel_gt *gt)
 
 void intel_gt_driver_register(struct intel_gt *gt)
 {
-	if (IS_GEN(gt->i915, 5))
-		intel_gpu_ips_init(gt->i915);
+	intel_rps_driver_register(&gt->rps);
 }
 
 static int intel_gt_init_scratch(struct intel_gt *gt, unsigned int size)
@@ -380,20 +380,16 @@ int intel_gt_init(struct intel_gt *gt)
 void intel_gt_driver_remove(struct intel_gt *gt)
 {
 	GEM_BUG_ON(gt->awake);
-	intel_gt_pm_disable(gt);
 }
 
 void intel_gt_driver_unregister(struct intel_gt *gt)
 {
-	intel_gpu_ips_teardown();
+	intel_rps_driver_unregister(&gt->rps);
 }
 
 void intel_gt_driver_release(struct intel_gt *gt)
 {
-	/* Paranoia: make sure we have disabled everything before we exit. */
-	intel_gt_pm_disable(gt);
 	intel_gt_pm_fini(gt);
-
 	intel_gt_fini_scratch(gt);
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index e6ab0bff0efb..5436f8c30708 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -28,7 +28,7 @@ static inline struct intel_gt *huc_to_gt(struct intel_huc *huc)
 }
 
 void intel_gt_init_early(struct intel_gt *gt, struct drm_i915_private *i915);
-void intel_gt_init_hw_early(struct drm_i915_private *i915);
+void intel_gt_init_hw_early(struct intel_gt *gt, struct i915_ggtt *ggtt);
 int __must_check intel_gt_init_hw(struct intel_gt *gt);
 int intel_gt_init(struct intel_gt *gt);
 void intel_gt_driver_register(struct intel_gt *gt);
@@ -46,8 +46,6 @@ void intel_gt_clear_error_registers(struct intel_gt *gt,
 void intel_gt_flush_ggtt_writes(struct intel_gt *gt);
 void intel_gt_chipset_flush(struct intel_gt *gt);
 
-void intel_gt_init_hangcheck(struct intel_gt *gt);
-
 static inline u32 intel_gt_scratch_offset(const struct intel_gt *gt,
 					  enum intel_gt_scratch_field field)
 {
@@ -59,6 +57,4 @@ static inline bool intel_gt_is_wedged(struct intel_gt *gt)
 	return __intel_reset_failed(&gt->reset);
 }
 
-void intel_gt_queue_hangcheck(struct intel_gt *gt);
-
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_irq.c b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
index 34a4fb624bf7..973ee7eded64 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_irq.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_irq.c
@@ -11,6 +11,7 @@
 #include "intel_gt.h"
 #include "intel_gt_irq.h"
 #include "intel_uncore.h"
+#include "intel_rps.h"
 
 static void guc_irq_handler(struct intel_guc *guc, u16 iir)
 {
@@ -77,7 +78,7 @@ gen11_other_irq_handler(struct intel_gt *gt, const u8 instance,
 		return guc_irq_handler(&gt->uc.guc, iir);
 
 	if (instance == OTHER_GTPM_INSTANCE)
-		return gen11_rps_irq_handler(gt, iir);
+		return gen11_rps_irq_handler(&gt->rps, iir);
 
 	WARN_ONCE(1, "unhandled other interrupt instance=0x%x, iir=0x%x\n",
 		  instance, iir);
@@ -336,7 +337,7 @@ void gen8_gt_irq_handler(struct intel_gt *gt, u32 master_ctl, u32 gt_iir[4])
 	}
 
 	if (master_ctl & (GEN8_GT_PM_IRQ | GEN8_GT_GUC_IRQ)) {
-		gen6_rps_irq_handler(gt->i915, gt_iir[2]);
+		gen6_rps_irq_handler(&gt->rps, gt_iir[2]);
 		guc_irq_handler(&gt->uc.guc, gt_iir[2] >> 16);
 	}
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.c b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
index b866d5b1eee0..a459a42ad5c2 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.c
@@ -4,6 +4,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/suspend.h>
+
 #include "i915_drv.h"
 #include "i915_globals.h"
 #include "i915_params.h"
@@ -12,13 +14,28 @@
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
 #include "intel_gt_requests.h"
+#include "intel_llc.h"
 #include "intel_pm.h"
 #include "intel_rc6.h"
+#include "intel_rps.h"
 #include "intel_wakeref.h"
 
-static void pm_notify(struct intel_gt *gt, int state)
+static void user_forcewake(struct intel_gt *gt, bool suspend)
 {
-	blocking_notifier_call_chain(&gt->pm_notifications, state, gt->i915);
+	int count = atomic_read(&gt->user_wakeref);
+
+	/* Inside suspend/resume so single threaded, no races to worry about. */
+	if (likely(!count))
+		return;
+
+	intel_gt_pm_get(gt);
+	if (suspend) {
+		GEM_BUG_ON(count > atomic_read(&gt->wakeref.count));
+		atomic_sub(count, &gt->wakeref.count);
+	} else {
+		atomic_add(count, &gt->wakeref.count);
+	}
+	intel_gt_pm_put(gt);
 }
 
 static int __gt_unpark(struct intel_wakeref *wf)
@@ -44,19 +61,14 @@ static int __gt_unpark(struct intel_wakeref *wf)
 	gt->awake = intel_display_power_get(i915, POWER_DOMAIN_GT_IRQ);
 	GEM_BUG_ON(!gt->awake);
 
-	intel_enable_gt_powersave(i915);
-
-	i915_update_gfx_val(i915);
-	if (INTEL_GEN(i915) >= 6)
-		gen6_rps_busy(i915);
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
 
+	intel_rps_unpark(&gt->rps);
 	i915_pmu_gt_unparked(i915);
 
-	intel_gt_queue_hangcheck(gt);
 	intel_gt_unpark_requests(gt);
 
-	pm_notify(gt, INTEL_GT_UNPARK);
-
 	return 0;
 }
 
@@ -68,16 +80,20 @@ static int __gt_park(struct intel_wakeref *wf)
 
 	GEM_TRACE("\n");
 
-	pm_notify(gt, INTEL_GT_PARK);
 	intel_gt_park_requests(gt);
 
+	i915_vma_parked(gt);
 	i915_pmu_gt_parked(i915);
-	if (INTEL_GEN(i915) >= 6)
-		gen6_rps_idle(i915);
+	intel_rps_park(&gt->rps);
 
 	/* Everything switched off, flush any residual interrupt just in case */
 	intel_synchronize_irq(i915);
 
+	if (NEEDS_RC6_CTX_CORRUPTION_WA(i915)) {
+		intel_rc6_ctx_wa_check(&i915->gt.rc6);
+		intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
+	}
+
 	GEM_BUG_ON(!wakeref);
 	intel_display_power_put(i915, POWER_DOMAIN_GT_IRQ, wakeref);
 
@@ -89,14 +105,11 @@ static int __gt_park(struct intel_wakeref *wf)
 static const struct intel_wakeref_ops wf_ops = {
 	.get = __gt_unpark,
 	.put = __gt_park,
-	.flags = INTEL_WAKEREF_PUT_ASYNC,
 };
 
 void intel_gt_pm_init_early(struct intel_gt *gt)
 {
 	intel_wakeref_init(&gt->wakeref, gt->uncore->rpm, &wf_ops);
-
-	BLOCKING_INIT_NOTIFIER_HEAD(&gt->pm_notifications);
 }
 
 void intel_gt_pm_init(struct intel_gt *gt)
@@ -107,6 +120,7 @@ void intel_gt_pm_init(struct intel_gt *gt)
 	 * user.
 	 */
 	intel_rc6_init(&gt->rc6);
+	intel_rps_init(&gt->rps);
 }
 
 static bool reset_engines(struct intel_gt *gt)
@@ -131,8 +145,22 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
+	intel_wakeref_t wakeref;
 
-	GEM_TRACE("\n");
+	GEM_TRACE("force:%s\n", yesno(force));
+
+	/* Use a raw wakeref to avoid calling intel_display_power_get early */
+	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
+	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
+
+	/*
+	 * As we have just resumed the machine and woken the device up from
+	 * deep PCI sleep (presumably D3_cold), assume the HW has been reset
+	 * back to defaults, recovering from whatever wedged state we left it
+	 * in and so worth trying to use the device once more.
+	 */
+	if (intel_gt_is_wedged(gt))
+		intel_gt_unset_wedged(gt);
 
 	intel_uc_sanitize(&gt->uc);
 
@@ -140,6 +168,8 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 		if (engine->reset.prepare)
 			engine->reset.prepare(engine);
 
+	intel_uc_reset_prepare(&gt->uc);
+
 	if (reset_engines(gt) || force) {
 		for_each_engine(engine, gt, id)
 			__intel_engine_reset(engine, false);
@@ -148,12 +178,9 @@ void intel_gt_sanitize(struct intel_gt *gt, bool force)
 	for_each_engine(engine, gt, id)
 		if (engine->reset.finish)
 			engine->reset.finish(engine);
-}
 
-void intel_gt_pm_disable(struct intel_gt *gt)
-{
-	if (!is_mock_gt(gt))
-		intel_sanitize_gt_powersave(gt->i915);
+	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
+	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 }
 
 void intel_gt_pm_fini(struct intel_gt *gt)
@@ -167,6 +194,8 @@ int intel_gt_resume(struct intel_gt *gt)
 	enum intel_engine_id id;
 	int err = 0;
 
+	GEM_TRACE("\n");
+
 	/*
 	 * After resume, we may need to poke into the pinned kernel
 	 * contexts to paper over any damage caused by the sudden suspend.
@@ -174,9 +203,13 @@ int intel_gt_resume(struct intel_gt *gt)
 	 * allowing us to fixup the user contexts on their first pin.
 	 */
 	intel_gt_pm_get(gt);
+
 	intel_uncore_forcewake_get(gt->uncore, FORCEWAKE_ALL);
 	intel_rc6_sanitize(&gt->rc6);
 
+	intel_rps_enable(&gt->rps);
+	intel_llc_enable(&gt->llc);
+
 	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 
@@ -185,9 +218,7 @@ int intel_gt_resume(struct intel_gt *gt)
 		ce = engine->kernel_context;
 		if (ce) {
 			GEM_BUG_ON(!intel_context_is_pinned(ce));
-			mutex_acquire(&ce->pin_mutex.dep_map, 0, 0, _THIS_IP_);
 			ce->ops->reset(ce);
-			mutex_release(&ce->pin_mutex.dep_map, 0, _THIS_IP_);
 		}
 
 		engine->serial++; /* kernel context lost */
@@ -203,14 +234,22 @@ int intel_gt_resume(struct intel_gt *gt)
 	}
 
 	intel_rc6_enable(&gt->rc6);
+
+	intel_uc_resume(&gt->uc);
+
+	user_forcewake(gt, false);
+
 	intel_uncore_forcewake_put(gt->uncore, FORCEWAKE_ALL);
 	intel_gt_pm_put(gt);
 
 	return err;
 }
 
-static void wait_for_idle(struct intel_gt *gt)
+static void wait_for_suspend(struct intel_gt *gt)
 {
+	if (!intel_gt_pm_is_awake(gt))
+		return;
+
 	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 		/*
 		 * Forcibly cancel outstanding work and leave
@@ -222,24 +261,65 @@ static void wait_for_idle(struct intel_gt *gt)
 	intel_gt_pm_wait_for_idle(gt);
 }
 
-void intel_gt_suspend(struct intel_gt *gt)
+void intel_gt_suspend_prepare(struct intel_gt *gt)
+{
+	user_forcewake(gt, true);
+	wait_for_suspend(gt);
+
+	intel_uc_suspend(&gt->uc);
+}
+
+static suspend_state_t pm_suspend_target(void)
+{
+#if IS_ENABLED(CONFIG_SUSPEND) && IS_ENABLED(CONFIG_PM_SLEEP)
+	return pm_suspend_target_state;
+#else
+	return PM_SUSPEND_TO_IDLE;
+#endif
+}
+
+void intel_gt_suspend_late(struct intel_gt *gt)
 {
 	intel_wakeref_t wakeref;
 
 	/* We expect to be idle already; but also want to be independent */
-	wait_for_idle(gt);
+	wait_for_suspend(gt);
 
-	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+	/*
+	 * On disabling the device, we want to turn off HW access to memory
+	 * that we no longer own.
+	 *
+	 * However, not all suspend-states disable the device. S0 (s2idle)
+	 * is effectively runtime-suspend, the device is left powered on
+	 * but needs to be put into a low power state. We need to keep
+	 * powermanagement enabled, but we also retain system state and so
+	 * it remains safe to keep on using our allocated memory.
+	 */
+	if (pm_suspend_target() == PM_SUSPEND_TO_IDLE)
+		return;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref) {
+		intel_rps_disable(&gt->rps);
 		intel_rc6_disable(&gt->rc6);
+		intel_llc_disable(&gt->llc);
+	}
+
+	intel_gt_sanitize(gt, false);
+
+	GEM_TRACE("\n");
 }
 
 void intel_gt_runtime_suspend(struct intel_gt *gt)
 {
 	intel_uc_runtime_suspend(&gt->uc);
+
+	GEM_TRACE("\n");
 }
 
 int intel_gt_runtime_resume(struct intel_gt *gt)
 {
+	GEM_TRACE("\n");
+
 	intel_gt_init_swizzling(gt);
 
 	return intel_uc_runtime_resume(&gt->uc);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index 997770d3a968..990efc27a4e4 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -12,11 +12,6 @@
 #include "intel_gt_types.h"
 #include "intel_wakeref.h"
 
-enum {
-	INTEL_GT_UNPARK,
-	INTEL_GT_PARK,
-};
-
 static inline bool intel_gt_pm_is_awake(const struct intel_gt *gt)
 {
 	return intel_wakeref_is_active(&gt->wakeref);
@@ -37,6 +32,11 @@ static inline void intel_gt_pm_put(struct intel_gt *gt)
 	intel_wakeref_put(&gt->wakeref);
 }
 
+static inline void intel_gt_pm_put_async(struct intel_gt *gt)
+{
+	intel_wakeref_put_async(&gt->wakeref);
+}
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);
@@ -44,13 +44,13 @@ static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 
 void intel_gt_pm_init_early(struct intel_gt *gt);
 void intel_gt_pm_init(struct intel_gt *gt);
-void intel_gt_pm_disable(struct intel_gt *gt);
 void intel_gt_pm_fini(struct intel_gt *gt);
 
 void intel_gt_sanitize(struct intel_gt *gt, bool force);
 
+void intel_gt_suspend_prepare(struct intel_gt *gt);
+void intel_gt_suspend_late(struct intel_gt *gt);
 int intel_gt_resume(struct intel_gt *gt);
-void intel_gt_suspend(struct intel_gt *gt);
 
 void intel_gt_runtime_suspend(struct intel_gt *gt);
 int intel_gt_runtime_resume(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
index b73229a84d85..3dc13ecf41bf 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -4,6 +4,8 @@
  * Copyright © 2019 Intel Corporation
  */
 
+#include <linux/workqueue.h>
+
 #include "i915_drv.h" /* for_each_engine() */
 #include "i915_request.h"
 #include "intel_gt.h"
@@ -29,6 +31,79 @@ static void flush_submission(struct intel_gt *gt)
 		intel_engine_flush_submission(engine);
 }
 
+static void engine_retire(struct work_struct *work)
+{
+	struct intel_engine_cs *engine =
+		container_of(work, typeof(*engine), retire_work);
+	struct intel_timeline *tl = xchg(&engine->retire, NULL);
+
+	do {
+		struct intel_timeline *next = xchg(&tl->retire, NULL);
+
+		/*
+		 * Our goal here is to retire _idle_ timelines as soon as
+		 * possible (as they are idle, we do not expect userspace
+		 * to be cleaning up anytime soon).
+		 *
+		 * If the timeline is currently locked, either it is being
+		 * retired elsewhere or about to be!
+		 */
+		if (mutex_trylock(&tl->mutex)) {
+			retire_requests(tl);
+			mutex_unlock(&tl->mutex);
+		}
+		intel_timeline_put(tl);
+
+		GEM_BUG_ON(!next);
+		tl = ptr_mask_bits(next, 1);
+	} while (tl);
+}
+
+static bool add_retire(struct intel_engine_cs *engine,
+		       struct intel_timeline *tl)
+{
+	struct intel_timeline *first;
+
+	/*
+	 * We open-code a llist here to include the additional tag [BIT(0)]
+	 * so that we know when the timeline is already on a
+	 * retirement queue: either this engine or another.
+	 *
+	 * However, we rely on that a timeline can only be active on a single
+	 * engine at any one time and that add_retire() is called before the
+	 * engine releases the timeline and transferred to another to retire.
+	 */
+
+	if (READ_ONCE(tl->retire)) /* already queued */
+		return false;
+
+	intel_timeline_get(tl);
+	first = READ_ONCE(engine->retire);
+	do
+		tl->retire = ptr_pack_bits(first, 1, 1);
+	while (!try_cmpxchg(&engine->retire, &first, tl));
+
+	return !first;
+}
+
+void intel_engine_add_retire(struct intel_engine_cs *engine,
+			     struct intel_timeline *tl)
+{
+	if (add_retire(engine, tl))
+		schedule_work(&engine->retire_work);
+}
+
+void intel_engine_init_retire(struct intel_engine_cs *engine)
+{
+	INIT_WORK(&engine->retire_work, engine_retire);
+}
+
+void intel_engine_fini_retire(struct intel_engine_cs *engine)
+{
+	flush_work(&engine->retire_work);
+	GEM_BUG_ON(engine->retire);
+}
+
 long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 {
 	struct intel_gt_timelines *timelines = &gt->timelines;
@@ -52,8 +127,8 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 		}
 
 		intel_timeline_get(tl);
-		GEM_BUG_ON(!tl->active_count);
-		tl->active_count++; /* pin the list element */
+		GEM_BUG_ON(!atomic_read(&tl->active_count));
+		atomic_inc(&tl->active_count); /* pin the list element */
 		spin_unlock_irqrestore(&timelines->lock, flags);
 
 		if (timeout > 0) {
@@ -74,16 +149,16 @@ long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout)
 
 		/* Resume iteration after dropping lock */
 		list_safe_reset_next(tl, tn, link);
-		if (--tl->active_count)
-			active_count += !!rcu_access_pointer(tl->last_request.fence);
-		else
+		if (atomic_dec_and_test(&tl->active_count))
 			list_del(&tl->link);
+		else
+			active_count += !!rcu_access_pointer(tl->last_request.fence);
 
 		mutex_unlock(&tl->mutex);
 
 		/* Defer the final release to after the spinlock */
 		if (refcount_dec_and_test(&tl->kref.refcount)) {
-			GEM_BUG_ON(tl->active_count);
+			GEM_BUG_ON(atomic_read(&tl->active_count));
 			list_add(&tl->link, &free);
 		}
 	}
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
index bd31cbce47e0..d626fb115386 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -7,7 +7,9 @@
 #ifndef INTEL_GT_REQUESTS_H
 #define INTEL_GT_REQUESTS_H
 
+struct intel_engine_cs;
 struct intel_gt;
+struct intel_timeline;
 
 long intel_gt_retire_requests_timeout(struct intel_gt *gt, long timeout);
 static inline void intel_gt_retire_requests(struct intel_gt *gt)
@@ -15,6 +17,11 @@ static inline void intel_gt_retire_requests(struct intel_gt *gt)
 	intel_gt_retire_requests_timeout(gt, 0);
 }
 
+void intel_engine_init_retire(struct intel_engine_cs *engine);
+void intel_engine_add_retire(struct intel_engine_cs *engine,
+			     struct intel_timeline *tl);
+void intel_engine_fini_retire(struct intel_engine_cs *engine);
+
 int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout);
 
 void intel_gt_init_requests(struct intel_gt *gt);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index ae4aaf75ac78..d4e14dbd172e 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -20,6 +20,7 @@
 #include "intel_llc_types.h"
 #include "intel_reset_types.h"
 #include "intel_rc6_types.h"
+#include "intel_rps_types.h"
 #include "intel_wakeref.h"
 
 struct drm_i915_private;
@@ -27,14 +28,6 @@ struct i915_ggtt;
 struct intel_engine_cs;
 struct intel_uncore;
 
-struct intel_hangcheck {
-	/* For hangcheck timer */
-#define DRM_I915_HANGCHECK_PERIOD 1500 /* in ms */
-#define DRM_I915_HANGCHECK_JIFFIES msecs_to_jiffies(DRM_I915_HANGCHECK_PERIOD)
-
-	struct delayed_work work;
-};
-
 struct intel_gt {
 	struct drm_i915_private *i915;
 	struct intel_uncore *uncore;
@@ -68,7 +61,6 @@ struct intel_gt {
 	struct list_head closed_vma;
 	spinlock_t closed_lock; /* guards the list of closed_vma */
 
-	struct intel_hangcheck hangcheck;
 	struct intel_reset reset;
 
 	/**
@@ -82,8 +74,7 @@ struct intel_gt {
 
 	struct intel_llc llc;
 	struct intel_rc6 rc6;
-
-	struct blocking_notifier_head pm_notifications;
+	struct intel_rps rps;
 
 	ktime_t last_init_time;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
deleted file mode 100644
index 0fdef00af9e4..000000000000
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ /dev/null
@@ -1,361 +0,0 @@
-/*
- * Copyright © 2016 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- *
- */
-
-#include "i915_drv.h"
-#include "intel_engine.h"
-#include "intel_gt.h"
-#include "intel_reset.h"
-
-struct hangcheck {
-	u64 acthd;
-	u32 ring;
-	u32 head;
-	enum intel_engine_hangcheck_action action;
-	unsigned long action_timestamp;
-	int deadlock;
-	struct intel_instdone instdone;
-	bool wedged:1;
-	bool stalled:1;
-};
-
-static bool instdone_unchanged(u32 current_instdone, u32 *old_instdone)
-{
-	u32 tmp = current_instdone | *old_instdone;
-	bool unchanged;
-
-	unchanged = tmp == *old_instdone;
-	*old_instdone |= tmp;
-
-	return unchanged;
-}
-
-static bool subunits_stuck(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
-	struct intel_instdone instdone;
-	struct intel_instdone *accu_instdone = &engine->hangcheck.instdone;
-	bool stuck;
-	int slice;
-	int subslice;
-
-	intel_engine_get_instdone(engine, &instdone);
-
-	/* There might be unstable subunit states even when
-	 * actual head is not moving. Filter out the unstable ones by
-	 * accumulating the undone -> done transitions and only
-	 * consider those as progress.
-	 */
-	stuck = instdone_unchanged(instdone.instdone,
-				   &accu_instdone->instdone);
-	stuck &= instdone_unchanged(instdone.slice_common,
-				    &accu_instdone->slice_common);
-
-	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice) {
-		stuck &= instdone_unchanged(instdone.sampler[slice][subslice],
-					    &accu_instdone->sampler[slice][subslice]);
-		stuck &= instdone_unchanged(instdone.row[slice][subslice],
-					    &accu_instdone->row[slice][subslice]);
-	}
-
-	return stuck;
-}
-
-static enum intel_engine_hangcheck_action
-head_stuck(struct intel_engine_cs *engine, u64 acthd)
-{
-	if (acthd != engine->hangcheck.acthd) {
-
-		/* Clear subunit states on head movement */
-		memset(&engine->hangcheck.instdone, 0,
-		       sizeof(engine->hangcheck.instdone));
-
-		return ENGINE_ACTIVE_HEAD;
-	}
-
-	if (!subunits_stuck(engine))
-		return ENGINE_ACTIVE_SUBUNITS;
-
-	return ENGINE_DEAD;
-}
-
-static enum intel_engine_hangcheck_action
-engine_stuck(struct intel_engine_cs *engine, u64 acthd)
-{
-	enum intel_engine_hangcheck_action ha;
-	u32 tmp;
-
-	ha = head_stuck(engine, acthd);
-	if (ha != ENGINE_DEAD)
-		return ha;
-
-	if (IS_GEN(engine->i915, 2))
-		return ENGINE_DEAD;
-
-	/* Is the chip hanging on a WAIT_FOR_EVENT?
-	 * If so we can simply poke the RB_WAIT bit
-	 * and break the hang. This should work on
-	 * all but the second generation chipsets.
-	 */
-	tmp = ENGINE_READ(engine, RING_CTL);
-	if (tmp & RING_WAIT) {
-		intel_gt_handle_error(engine->gt, engine->mask, 0,
-				      "stuck wait on %s", engine->name);
-		ENGINE_WRITE(engine, RING_CTL, tmp);
-		return ENGINE_WAIT_KICK;
-	}
-
-	return ENGINE_DEAD;
-}
-
-static void hangcheck_load_sample(struct intel_engine_cs *engine,
-				  struct hangcheck *hc)
-{
-	hc->acthd = intel_engine_get_active_head(engine);
-	hc->ring = ENGINE_READ(engine, RING_START);
-	hc->head = ENGINE_READ(engine, RING_HEAD);
-}
-
-static void hangcheck_store_sample(struct intel_engine_cs *engine,
-				   const struct hangcheck *hc)
-{
-	engine->hangcheck.acthd = hc->acthd;
-	engine->hangcheck.last_ring = hc->ring;
-	engine->hangcheck.last_head = hc->head;
-}
-
-static enum intel_engine_hangcheck_action
-hangcheck_get_action(struct intel_engine_cs *engine,
-		     const struct hangcheck *hc)
-{
-	if (intel_engine_is_idle(engine))
-		return ENGINE_IDLE;
-
-	if (engine->hangcheck.last_ring != hc->ring)
-		return ENGINE_ACTIVE_SEQNO;
-
-	if (engine->hangcheck.last_head != hc->head)
-		return ENGINE_ACTIVE_SEQNO;
-
-	return engine_stuck(engine, hc->acthd);
-}
-
-static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
-					struct hangcheck *hc)
-{
-	unsigned long timeout = I915_ENGINE_DEAD_TIMEOUT;
-
-	hc->action = hangcheck_get_action(engine, hc);
-
-	/* We always increment the progress
-	 * if the engine is busy and still processing
-	 * the same request, so that no single request
-	 * can run indefinitely (such as a chain of
-	 * batches). The only time we do not increment
-	 * the hangcheck score on this ring, if this
-	 * engine is in a legitimate wait for another
-	 * engine. In that case the waiting engine is a
-	 * victim and we want to be sure we catch the
-	 * right culprit. Then every time we do kick
-	 * the ring, make it as a progress as the seqno
-	 * advancement might ensure and if not, it
-	 * will catch the hanging engine.
-	 */
-
-	switch (hc->action) {
-	case ENGINE_IDLE:
-	case ENGINE_ACTIVE_SEQNO:
-		/* Clear head and subunit states on seqno movement */
-		hc->acthd = 0;
-
-		memset(&engine->hangcheck.instdone, 0,
-		       sizeof(engine->hangcheck.instdone));
-
-		/* Intentional fall through */
-	case ENGINE_WAIT_KICK:
-	case ENGINE_WAIT:
-		engine->hangcheck.action_timestamp = jiffies;
-		break;
-
-	case ENGINE_ACTIVE_HEAD:
-	case ENGINE_ACTIVE_SUBUNITS:
-		/*
-		 * Seqno stuck with still active engine gets leeway,
-		 * in hopes that it is just a long shader.
-		 */
-		timeout = I915_SEQNO_DEAD_TIMEOUT;
-		break;
-
-	case ENGINE_DEAD:
-		break;
-
-	default:
-		MISSING_CASE(hc->action);
-	}
-
-	hc->stalled = time_after(jiffies,
-				 engine->hangcheck.action_timestamp + timeout);
-	hc->wedged = time_after(jiffies,
-				 engine->hangcheck.action_timestamp +
-				 I915_ENGINE_WEDGED_TIMEOUT);
-}
-
-static void hangcheck_declare_hang(struct intel_gt *gt,
-				   intel_engine_mask_t hung,
-				   intel_engine_mask_t stuck)
-{
-	struct intel_engine_cs *engine;
-	intel_engine_mask_t tmp;
-	char msg[80];
-	int len;
-
-	/* If some rings hung but others were still busy, only
-	 * blame the hanging rings in the synopsis.
-	 */
-	if (stuck != hung)
-		hung &= ~stuck;
-	len = scnprintf(msg, sizeof(msg),
-			"%s on ", stuck == hung ? "no progress" : "hang");
-	for_each_engine_masked(engine, gt, hung, tmp)
-		len += scnprintf(msg + len, sizeof(msg) - len,
-				 "%s, ", engine->name);
-	msg[len-2] = '\0';
-
-	return intel_gt_handle_error(gt, hung, I915_ERROR_CAPTURE, "%s", msg);
-}
-
-/*
- * This is called when the chip hasn't reported back with completed
- * batchbuffers in a long time. We keep track per ring seqno progress and
- * if there are no progress, hangcheck score for that ring is increased.
- * Further, acthd is inspected to see if the ring is stuck. On stuck case
- * we kick the ring. If we see no progress on three subsequent calls
- * we assume chip is wedged and try to fix it by resetting the chip.
- */
-static void hangcheck_elapsed(struct work_struct *work)
-{
-	struct intel_gt *gt =
-		container_of(work, typeof(*gt), hangcheck.work.work);
-	intel_engine_mask_t hung = 0, stuck = 0, wedged = 0;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-	intel_wakeref_t wakeref;
-
-	if (!i915_modparams.enable_hangcheck)
-		return;
-
-	if (!READ_ONCE(gt->awake))
-		return;
-
-	if (intel_gt_is_wedged(gt))
-		return;
-
-	wakeref = intel_runtime_pm_get_if_in_use(gt->uncore->rpm);
-	if (!wakeref)
-		return;
-
-	/* As enabling the GPU requires fairly extensive mmio access,
-	 * periodically arm the mmio checker to see if we are triggering
-	 * any invalid access.
-	 */
-	intel_uncore_arm_unclaimed_mmio_detection(gt->uncore);
-
-	for_each_engine(engine, gt, id) {
-		struct hangcheck hc;
-
-		intel_engine_breadcrumbs_irq(engine);
-
-		hangcheck_load_sample(engine, &hc);
-		hangcheck_accumulate_sample(engine, &hc);
-		hangcheck_store_sample(engine, &hc);
-
-		if (hc.stalled) {
-			hung |= engine->mask;
-			if (hc.action != ENGINE_DEAD)
-				stuck |= engine->mask;
-		}
-
-		if (hc.wedged)
-			wedged |= engine->mask;
-	}
-
-	if (GEM_SHOW_DEBUG() && (hung | stuck)) {
-		struct drm_printer p = drm_debug_printer("hangcheck");
-
-		for_each_engine(engine, gt, id) {
-			if (intel_engine_is_idle(engine))
-				continue;
-
-			intel_engine_dump(engine, &p, "%s\n", engine->name);
-		}
-	}
-
-	if (wedged) {
-		dev_err(gt->i915->drm.dev,
-			"GPU recovery timed out,"
-			" cancelling all in-flight rendering.\n");
-		GEM_TRACE_DUMP();
-		intel_gt_set_wedged(gt);
-	}
-
-	if (hung)
-		hangcheck_declare_hang(gt, hung, stuck);
-
-	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
-
-	/* Reset timer in case GPU hangs without another request being added */
-	intel_gt_queue_hangcheck(gt);
-}
-
-void intel_gt_queue_hangcheck(struct intel_gt *gt)
-{
-	unsigned long delay;
-
-	if (unlikely(!i915_modparams.enable_hangcheck))
-		return;
-
-	/*
-	 * Don't continually defer the hangcheck so that it is always run at
-	 * least once after work has been scheduled on any ring. Otherwise,
-	 * we will ignore a hung ring if a second ring is kept busy.
-	 */
-
-	delay = round_jiffies_up_relative(DRM_I915_HANGCHECK_JIFFIES);
-	queue_delayed_work(system_long_wq, &gt->hangcheck.work, delay);
-}
-
-void intel_engine_init_hangcheck(struct intel_engine_cs *engine)
-{
-	memset(&engine->hangcheck, 0, sizeof(engine->hangcheck));
-	engine->hangcheck.action_timestamp = jiffies;
-}
-
-void intel_gt_init_hangcheck(struct intel_gt *gt)
-{
-	INIT_DELAYED_WORK(&gt->hangcheck.work, hangcheck_elapsed);
-}
-
-#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
-#include "selftest_hangcheck.c"
-#endif
diff --git a/drivers/gpu/drm/i915/gt/intel_llc.c b/drivers/gpu/drm/i915/gt/intel_llc.c
index 35093eb5f24e..ceb785b75c25 100644
--- a/drivers/gpu/drm/i915/gt/intel_llc.c
+++ b/drivers/gpu/drm/i915/gt/intel_llc.c
@@ -48,7 +48,7 @@ static bool get_ia_constants(struct intel_llc *llc,
 			     struct ia_constants *consts)
 {
 	struct drm_i915_private *i915 = llc_to_gt(llc)->i915;
-	struct intel_rps *rps = &i915->gt_pm.rps;
+	struct intel_rps *rps = &llc_to_gt(llc)->rps;
 
 	if (rps->max_freq <= rps->min_freq)
 		return false;
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index d0088d020220..9fdefbdc3546 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -142,9 +142,11 @@
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_pm.h"
+#include "intel_gt_requests.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 #include "intel_reset.h"
+#include "intel_ring.h"
 #include "intel_workarounds.h"
 
 #define RING_EXECLIST_QFULL		(1 << 0x2)
@@ -234,16 +236,9 @@ static void execlists_init_reg_state(u32 *reg_state,
 				     const struct intel_engine_cs *engine,
 				     const struct intel_ring *ring,
 				     bool close);
-
-static void __context_pin_acquire(struct intel_context *ce)
-{
-	mutex_acquire(&ce->pin_mutex.dep_map, 2, 0, _RET_IP_);
-}
-
-static void __context_pin_release(struct intel_context *ce)
-{
-	mutex_release(&ce->pin_mutex.dep_map, 0, _RET_IP_);
-}
+static void
+__execlists_update_reg_state(const struct intel_context *ce,
+			     const struct intel_engine_cs *engine);
 
 static void mark_eio(struct i915_request *rq)
 {
@@ -256,6 +251,23 @@ static void mark_eio(struct i915_request *rq)
 	i915_request_mark_complete(rq);
 }
 
+static struct i915_request *
+active_request(const struct intel_timeline * const tl, struct i915_request *rq)
+{
+	struct i915_request *active = rq;
+
+	rcu_read_lock();
+	list_for_each_entry_continue_reverse(rq, &tl->requests, link) {
+		if (i915_request_completed(rq))
+			break;
+
+		active = rq;
+	}
+	rcu_read_unlock();
+
+	return active;
+}
+
 static inline u32 intel_hws_preempt_address(struct intel_engine_cs *engine)
 {
 	return (i915_ggtt_offset(engine->status_page.vma) +
@@ -460,8 +472,7 @@ lrc_descriptor(struct intel_context *ce, struct intel_engine_cs *engine)
 	if (IS_GEN(engine->i915, 8))
 		desc |= GEN8_CTX_L3LLC_COHERENT;
 
-	desc |= i915_ggtt_offset(ce->state) + LRC_HEADER_PAGES * PAGE_SIZE;
-								/* bits 12-31 */
+	desc |= i915_ggtt_offset(ce->state); /* bits 12-31 */
 	/*
 	 * The following 32bits are copied into the OA reports (dword 2).
 	 * Consider updating oa_get_render_ctx_id in i915_perf.c when changing
@@ -925,6 +936,114 @@ execlists_context_status_change(struct i915_request *rq, unsigned long status)
 				   status, rq);
 }
 
+static void intel_engine_context_in(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (READ_ONCE(engine->stats.enabled) == 0)
+		return;
+
+	write_seqlock_irqsave(&engine->stats.lock, flags);
+
+	if (engine->stats.enabled > 0) {
+		if (engine->stats.active++ == 0)
+			engine->stats.start = ktime_get();
+		GEM_BUG_ON(engine->stats.active == 0);
+	}
+
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+}
+
+static void intel_engine_context_out(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (READ_ONCE(engine->stats.enabled) == 0)
+		return;
+
+	write_seqlock_irqsave(&engine->stats.lock, flags);
+
+	if (engine->stats.enabled > 0) {
+		ktime_t last;
+
+		if (engine->stats.active && --engine->stats.active == 0) {
+			/*
+			 * Decrement the active context count and in case GPU
+			 * is now idle add up to the running total.
+			 */
+			last = ktime_sub(ktime_get(), engine->stats.start);
+
+			engine->stats.total = ktime_add(engine->stats.total,
+							last);
+		} else if (engine->stats.active == 0) {
+			/*
+			 * After turning on engine stats, context out might be
+			 * the first event in which case we account from the
+			 * time stats gathering was turned on.
+			 */
+			last = ktime_sub(ktime_get(), engine->stats.enabled_at);
+
+			engine->stats.total = ktime_add(engine->stats.total,
+							last);
+		}
+	}
+
+	write_sequnlock_irqrestore(&engine->stats.lock, flags);
+}
+
+static void restore_default_state(struct intel_context *ce,
+				  struct intel_engine_cs *engine)
+{
+	u32 *regs = ce->lrc_reg_state;
+
+	if (engine->pinned_default_state)
+		memcpy(regs, /* skip restoring the vanilla PPHWSP */
+		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
+		       engine->context_size - PAGE_SIZE);
+
+	execlists_init_reg_state(regs, ce, engine, ce->ring, false);
+}
+
+static void reset_active(struct i915_request *rq,
+			 struct intel_engine_cs *engine)
+{
+	struct intel_context * const ce = rq->hw_context;
+	u32 head;
+
+	/*
+	 * The executing context has been cancelled. We want to prevent
+	 * further execution along this context and propagate the error on
+	 * to anything depending on its results.
+	 *
+	 * In __i915_request_submit(), we apply the -EIO and remove the
+	 * requests' payloads for any banned requests. But first, we must
+	 * rewind the context back to the start of the incomplete request so
+	 * that we do not jump back into the middle of the batch.
+	 *
+	 * We preserve the breadcrumbs and semaphores of the incomplete
+	 * requests so that inter-timeline dependencies (i.e other timelines)
+	 * remain correctly ordered. And we defer to __i915_request_submit()
+	 * so that all asynchronous waits are correctly handled.
+	 */
+	GEM_TRACE("%s(%s): { rq=%llx:%lld }\n",
+		  __func__, engine->name, rq->fence.context, rq->fence.seqno);
+
+	/* On resubmission of the active request, payload will be scrubbed */
+	if (i915_request_completed(rq))
+		head = rq->tail;
+	else
+		head = active_request(ce->timeline, rq)->head;
+	ce->ring->head = intel_ring_wrap(ce->ring, head);
+	intel_ring_update_space(ce->ring);
+
+	/* Scrub the context image to prevent replaying the previous batch */
+	restore_default_state(ce, engine);
+	__execlists_update_reg_state(ce, engine);
+
+	/* We've switched away, so this should be a no-op, but intent matters */
+	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE;
+}
+
 static inline struct intel_engine_cs *
 __execlists_schedule_in(struct i915_request *rq)
 {
@@ -933,6 +1052,9 @@ __execlists_schedule_in(struct i915_request *rq)
 
 	intel_context_get(ce);
 
+	if (unlikely(i915_gem_context_is_banned(ce->gem_context)))
+		reset_active(rq, engine);
+
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
 		ce->lrc_desc |= (u64)ce->tag << 32;
@@ -988,9 +1110,23 @@ __execlists_schedule_out(struct i915_request *rq,
 {
 	struct intel_context * const ce = rq->hw_context;
 
+	/*
+	 * NB process_csb() is not under the engine->active.lock and hence
+	 * schedule_out can race with schedule_in meaning that we should
+	 * refrain from doing non-trivial work here.
+	 */
+
+	/*
+	 * If we have just completed this context, the engine may now be
+	 * idle and we want to re-enter powersaving.
+	 */
+	if (list_is_last(&rq->link, &ce->timeline->requests) &&
+	    i915_request_completed(rq))
+		intel_engine_add_retire(engine, ce->timeline);
+
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
-	intel_gt_pm_put(engine->gt);
+	intel_gt_pm_put_async(engine->gt);
 
 	/*
 	 * If this is part of a virtual engine, its next request may
@@ -1345,7 +1481,7 @@ need_timeslice(struct intel_engine_cs *engine, const struct i915_request *rq)
 {
 	int hint;
 
-	if (!intel_engine_has_semaphores(engine))
+	if (!intel_engine_has_timeslices(engine))
 		return false;
 
 	if (list_is_last(&rq->sched.link, &engine->active.requests))
@@ -1366,15 +1502,32 @@ switch_prio(struct intel_engine_cs *engine, const struct i915_request *rq)
 	return rq_prio(list_next_entry(rq, sched.link));
 }
 
-static bool
-enable_timeslice(const struct intel_engine_execlists *execlists)
+static inline unsigned long
+timeslice(const struct intel_engine_cs *engine)
 {
-	const struct i915_request *rq = *execlists->active;
+	return READ_ONCE(engine->props.timeslice_duration_ms);
+}
+
+static unsigned long
+active_timeslice(const struct intel_engine_cs *engine)
+{
+	const struct i915_request *rq = *engine->execlists.active;
 
 	if (i915_request_completed(rq))
-		return false;
+		return 0;
+
+	if (engine->execlists.switch_priority_hint < effective_prio(rq))
+		return 0;
+
+	return timeslice(engine);
+}
+
+static void set_timeslice(struct intel_engine_cs *engine)
+{
+	if (!intel_engine_has_timeslices(engine))
+		return;
 
-	return execlists->switch_priority_hint >= effective_prio(rq);
+	set_timer_ms(&engine->execlists.timer, active_timeslice(engine));
 }
 
 static void record_preemption(struct intel_engine_execlists *execlists)
@@ -1382,6 +1535,30 @@ static void record_preemption(struct intel_engine_execlists *execlists)
 	(void)I915_SELFTEST_ONLY(execlists->preempt_hang.count++);
 }
 
+static unsigned long active_preempt_timeout(struct intel_engine_cs *engine)
+{
+	struct i915_request *rq;
+
+	rq = last_active(&engine->execlists);
+	if (!rq)
+		return 0;
+
+	/* Force a fast reset for terminated contexts (ignoring sysfs!) */
+	if (unlikely(i915_gem_context_is_banned(rq->gem_context)))
+		return 1;
+
+	return READ_ONCE(engine->props.preempt_timeout_ms);
+}
+
+static void set_preempt_timeout(struct intel_engine_cs *engine)
+{
+	if (!intel_engine_has_preempt_reset(engine))
+		return;
+
+	set_timer_ms(&engine->execlists.preempt,
+		     active_preempt_timeout(engine));
+}
+
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1521,8 +1698,9 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 				 */
 				if (!execlists->timer.expires &&
 				    need_timeslice(engine, last))
-					mod_timer(&execlists->timer,
-						  jiffies + 1);
+					set_timer_ms(&execlists->timer,
+						     timeslice(engine));
+
 				return;
 			}
 
@@ -1757,6 +1935,8 @@ done:
 
 		memset(port + 1, 0, (last_port - port) * sizeof(*port));
 		execlists_submit_ports(engine);
+
+		set_preempt_timeout(engine);
 	} else {
 skip_submit:
 		ring_set_paused(engine, 0);
@@ -1766,16 +1946,17 @@ skip_submit:
 static void
 cancel_port_requests(struct intel_engine_execlists * const execlists)
 {
-	struct i915_request * const *port, *rq;
+	struct i915_request * const *port;
 
-	for (port = execlists->pending; (rq = *port); port++)
-		execlists_schedule_out(rq);
+	for (port = execlists->pending; *port; port++)
+		execlists_schedule_out(*port);
 	memset(execlists->pending, 0, sizeof(execlists->pending));
 
-	for (port = execlists->active; (rq = *port); port++)
-		execlists_schedule_out(rq);
-	execlists->active =
-		memset(execlists->inflight, 0, sizeof(execlists->inflight));
+	/* Mark the end of active before we overwrite *active */
+	for (port = xchg(&execlists->active, execlists->pending); *port; port++)
+		execlists_schedule_out(*port);
+	WRITE_ONCE(execlists->active,
+		   memset(execlists->inflight, 0, sizeof(execlists->inflight)));
 }
 
 static inline void
@@ -1867,7 +2048,7 @@ static void process_csb(struct intel_engine_cs *engine)
 	 */
 	GEM_BUG_ON(!tasklet_is_locked(&execlists->tasklet) &&
 		   !reset_in_progress(execlists));
-	GEM_BUG_ON(USES_GUC_SUBMISSION(engine->i915));
+	GEM_BUG_ON(!intel_engine_in_execlists_submission_mode(engine));
 
 	/*
 	 * Note that csb_write, csb_status may be either in HWSP or mmio.
@@ -1928,26 +2109,27 @@ static void process_csb(struct intel_engine_cs *engine)
 		else
 			promote = gen8_csb_parse(execlists, buf + 2 * head);
 		if (promote) {
+			struct i915_request * const *old = execlists->active;
+
+			/* Point active to the new ELSP; prevent overwriting */
+			WRITE_ONCE(execlists->active, execlists->pending);
+			set_timeslice(engine);
+
 			if (!inject_preempt_hang(execlists))
 				ring_set_paused(engine, 0);
 
 			/* cancel old inflight, prepare for switch */
-			trace_ports(execlists, "preempted", execlists->active);
-			while (*execlists->active)
-				execlists_schedule_out(*execlists->active++);
+			trace_ports(execlists, "preempted", old);
+			while (*old)
+				execlists_schedule_out(*old++);
 
 			/* switch pending to inflight */
 			GEM_BUG_ON(!assert_pending_valid(execlists, "promote"));
-			execlists->active =
-				memcpy(execlists->inflight,
-				       execlists->pending,
-				       execlists_num_ports(execlists) *
-				       sizeof(*execlists->pending));
-
-			if (enable_timeslice(execlists))
-				mod_timer(&execlists->timer, jiffies + 1);
-			else
-				cancel_timer(&execlists->timer);
+			WRITE_ONCE(execlists->active,
+				   memcpy(execlists->inflight,
+					  execlists->pending,
+					  execlists_num_ports(execlists) *
+					  sizeof(*execlists->pending)));
 
 			WRITE_ONCE(execlists->pending[0], NULL);
 		} else {
@@ -1997,6 +2179,43 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 	}
 }
 
+static noinline void preempt_reset(struct intel_engine_cs *engine)
+{
+	const unsigned int bit = I915_RESET_ENGINE + engine->id;
+	unsigned long *lock = &engine->gt->reset.flags;
+
+	if (i915_modparams.reset < 3)
+		return;
+
+	if (test_and_set_bit(bit, lock))
+		return;
+
+	/* Mark this tasklet as disabled to avoid waiting for it to complete */
+	tasklet_disable_nosync(&engine->execlists.tasklet);
+
+	GEM_TRACE("%s: preempt timeout %lu+%ums\n",
+		  engine->name,
+		  READ_ONCE(engine->props.preempt_timeout_ms),
+		  jiffies_to_msecs(jiffies - engine->execlists.preempt.expires));
+	intel_engine_reset(engine, "preemption time out");
+
+	tasklet_enable(&engine->execlists.tasklet);
+	clear_and_wake_up_bit(bit, lock);
+}
+
+static bool preempt_timeout(const struct intel_engine_cs *const engine)
+{
+	const struct timer_list *t = &engine->execlists.preempt;
+
+	if (!CONFIG_DRM_I915_PREEMPT_TIMEOUT)
+		return false;
+
+	if (!timer_expired(t))
+		return false;
+
+	return READ_ONCE(engine->execlists.pending[0]);
+}
+
 /*
  * Check the unread Context Status Buffers and manage the submission of new
  * contexts to the ELSP accordingly.
@@ -2004,23 +2223,39 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
-	unsigned long flags;
+	bool timeout = preempt_timeout(engine);
 
 	process_csb(engine);
-	if (!READ_ONCE(engine->execlists.pending[0])) {
+	if (!READ_ONCE(engine->execlists.pending[0]) || timeout) {
+		unsigned long flags;
+
 		spin_lock_irqsave(&engine->active.lock, flags);
 		__execlists_submission_tasklet(engine);
 		spin_unlock_irqrestore(&engine->active.lock, flags);
+
+		/* Recheck after serialising with direct-submission */
+		if (timeout && preempt_timeout(engine))
+			preempt_reset(engine);
 	}
 }
 
-static void execlists_submission_timer(struct timer_list *timer)
+static void __execlists_kick(struct intel_engine_execlists *execlists)
 {
-	struct intel_engine_cs *engine =
-		from_timer(engine, timer, execlists.timer);
-
 	/* Kick the tasklet for some interrupt coalescing and reset handling */
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	tasklet_hi_schedule(&execlists->tasklet);
+}
+
+#define execlists_kick(t, member) \
+	__execlists_kick(container_of(t, struct intel_engine_execlists, member))
+
+static void execlists_timeslice(struct timer_list *timer)
+{
+	execlists_kick(timer, timer);
+}
+
+static void execlists_preempt(struct timer_list *timer)
+{
+	execlists_kick(timer, preempt);
 }
 
 static void queue_request(struct intel_engine_cs *engine,
@@ -2100,7 +2335,6 @@ set_redzone(void *vaddr, const struct intel_engine_cs *engine)
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return;
 
-	vaddr += LRC_HEADER_PAGES * PAGE_SIZE;
 	vaddr += engine->context_size;
 
 	memset(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE);
@@ -2112,7 +2346,6 @@ check_redzone(const void *vaddr, const struct intel_engine_cs *engine)
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return;
 
-	vaddr += LRC_HEADER_PAGES * PAGE_SIZE;
 	vaddr += engine->context_size;
 
 	if (memchr_inv(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE))
@@ -2727,37 +2960,28 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)
 			       &execlists->csb_status[reset_value]);
 }
 
-static struct i915_request *active_request(struct i915_request *rq)
+static int lrc_ring_mi_mode(const struct intel_engine_cs *engine)
 {
-	const struct intel_context * const ce = rq->hw_context;
-	struct i915_request *active = NULL;
-	struct list_head *list;
-
-	if (!i915_request_is_active(rq)) /* unwound, but incomplete! */
-		return rq;
-
-	list = &i915_request_active_timeline(rq)->requests;
-	list_for_each_entry_from_reverse(rq, list, link) {
-		if (i915_request_completed(rq))
-			break;
-
-		if (rq->hw_context != ce)
-			break;
-
-		active = rq;
-	}
-
-	return active;
+	if (INTEL_GEN(engine->i915) >= 12)
+		return 0x60;
+	else if (INTEL_GEN(engine->i915) >= 9)
+		return 0x54;
+	else if (engine->class == RENDER_CLASS)
+		return 0x58;
+	else
+		return -1;
 }
 
 static void __execlists_reset_reg_state(const struct intel_context *ce,
 					const struct intel_engine_cs *engine)
 {
 	u32 *regs = ce->lrc_reg_state;
+	int x;
 
-	if (INTEL_GEN(engine->i915) >= 9) {
-		regs[GEN9_CTX_RING_MI_MODE + 1] &= ~STOP_RING;
-		regs[GEN9_CTX_RING_MI_MODE + 1] |= STOP_RING << 16;
+	x = lrc_ring_mi_mode(engine);
+	if (x != -1) {
+		regs[x + 1] &= ~STOP_RING;
+		regs[x + 1] |= STOP_RING << 16;
 	}
 }
 
@@ -2766,7 +2990,6 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct intel_context *ce;
 	struct i915_request *rq;
-	u32 *regs;
 
 	mb(); /* paranoia: read the CSB pointers from after the reset */
 	clflush(execlists->csb_write);
@@ -2792,19 +3015,17 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	ce = rq->hw_context;
 	GEM_BUG_ON(!i915_vma_is_pinned(ce->state));
 
-	/* Proclaim we have exclusive access to the context image! */
-	__context_pin_acquire(ce);
-
-	rq = active_request(rq);
-	if (!rq) {
+	if (i915_request_completed(rq)) {
 		/* Idle context; tidy up the ring so we can restart afresh */
-		ce->ring->head = ce->ring->tail;
+		ce->ring->head = intel_ring_wrap(ce->ring, rq->tail);
 		goto out_replay;
 	}
 
 	/* Context has requests still in-flight; it should not be idle! */
 	GEM_BUG_ON(i915_active_is_idle(&ce->active));
+	rq = active_request(ce->timeline, rq);
 	ce->ring->head = intel_ring_wrap(ce->ring, rq->head);
+	GEM_BUG_ON(ce->ring->head == ce->ring->tail);
 
 	/*
 	 * If this request hasn't started yet, e.g. it is waiting on a
@@ -2845,22 +3066,15 @@ static void __execlists_reset(struct intel_engine_cs *engine, bool stalled)
 	 * to recreate its own state.
 	 */
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
-	regs = ce->lrc_reg_state;
-	if (engine->pinned_default_state) {
-		memcpy(regs, /* skip restoring the vanilla PPHWSP */
-		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
-		       engine->context_size - PAGE_SIZE);
-	}
-	execlists_init_reg_state(regs, ce, engine, ce->ring, false);
+	restore_default_state(ce, engine);
 
 out_replay:
-	GEM_TRACE("%s replay {head:%04x, tail:%04x\n",
+	GEM_TRACE("%s replay {head:%04x, tail:%04x}\n",
 		  engine->name, ce->ring->head, ce->ring->tail);
 	intel_ring_update_space(ce->ring);
 	__execlists_reset_reg_state(ce, engine);
 	__execlists_update_reg_state(ce, engine);
 	ce->lrc_desc |= CTX_DESC_FORCE_RESTORE; /* paranoid: GPU was reset! */
-	__context_pin_release(ce);
 
 unwind:
 	/* Push back any incomplete requests for replay after the reset. */
@@ -3469,6 +3683,7 @@ gen12_emit_fini_breadcrumb_rcs(struct i915_request *request, u32 *cs)
 static void execlists_park(struct intel_engine_cs *engine)
 {
 	cancel_timer(&engine->execlists.timer);
+	cancel_timer(&engine->execlists.preempt);
 }
 
 void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
@@ -3586,7 +3801,8 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine)
 {
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
-	timer_setup(&engine->execlists.timer, execlists_submission_timer, 0);
+	timer_setup(&engine->execlists.timer, execlists_timeslice, 0);
+	timer_setup(&engine->execlists.preempt, execlists_preempt, 0);
 
 	logical_ring_default_vfuncs(engine);
 	logical_ring_default_irqs(engine);
@@ -3796,12 +4012,6 @@ populate_lr_context(struct intel_context *ce,
 	set_redzone(vaddr, engine);
 
 	if (engine->default_state) {
-		/*
-		 * We only want to copy over the template context state;
-		 * skipping over the headers reserved for GuC communication,
-		 * leaving those as zero.
-		 */
-		const unsigned long start = LRC_HEADER_PAGES * PAGE_SIZE;
 		void *defaults;
 
 		defaults = i915_gem_object_pin_map(engine->default_state,
@@ -3811,7 +4021,7 @@ populate_lr_context(struct intel_context *ce,
 			goto err_unpin_ctx;
 		}
 
-		memcpy(vaddr + start, defaults + start, engine->context_size);
+		memcpy(vaddr, defaults, engine->context_size);
 		i915_gem_object_unpin_map(engine->default_state);
 		inhibit = false;
 	}
@@ -3826,9 +4036,7 @@ populate_lr_context(struct intel_context *ce,
 
 	ret = 0;
 err_unpin_ctx:
-	__i915_gem_object_flush_map(ctx_obj,
-				    LRC_HEADER_PAGES * PAGE_SIZE,
-				    engine->context_size);
+	__i915_gem_object_flush_map(ctx_obj, 0, engine->context_size);
 	i915_gem_object_unpin_map(ctx_obj);
 	return ret;
 }
@@ -3845,11 +4053,6 @@ static int __execlists_context_alloc(struct intel_context *ce,
 	GEM_BUG_ON(ce->state);
 	context_size = round_up(engine->context_size, I915_GTT_PAGE_SIZE);
 
-	/*
-	 * Before the actual start of the context image, we insert a few pages
-	 * for our own use and for sharing with the GuC.
-	 */
-	context_size += LRC_HEADER_PAGES * PAGE_SIZE;
 	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		context_size += I915_GTT_PAGE_SIZE; /* for redzone */
 
@@ -4502,7 +4705,6 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 			    bool scrub)
 {
 	GEM_BUG_ON(!intel_context_is_pinned(ce));
-	__context_pin_acquire(ce);
 
 	/*
 	 * We want a simple context + ring to execute the breadcrumb update.
@@ -4512,23 +4714,21 @@ void intel_lr_context_reset(struct intel_engine_cs *engine,
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
-	if (scrub) {
-		u32 *regs = ce->lrc_reg_state;
-
-		if (engine->pinned_default_state) {
-			memcpy(regs, /* skip restoring the vanilla PPHWSP */
-			       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
-			       engine->context_size - PAGE_SIZE);
-		}
-		execlists_init_reg_state(regs, ce, engine, ce->ring, false);
-	}
+	if (scrub)
+		restore_default_state(ce, engine);
 
 	/* Rerun the request; its payload has been neutered (if guilty). */
 	ce->ring->head = head;
 	intel_ring_update_space(ce->ring);
 
 	__execlists_update_reg_state(ce, engine);
-	__context_pin_release(ce);
+}
+
+bool
+intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine)
+{
+	return engine->set_default_submission ==
+	       intel_execlists_set_default_submission;
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 99dc576a4e25..04511d8ebdc1 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -43,6 +43,7 @@ struct intel_engine_cs;
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
 #define   CTX_CTRL_RS_CTX_ENABLE		(1 << 1)
 #define	  CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT	(1 << 2)
+#define	  GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE	(1 << 8)
 #define RING_CONTEXT_STATUS_PTR(base)		_MMIO((base) + 0x3a0)
 #define RING_EXECLIST_SQ_CONTENTS(base)		_MMIO((base) + 0x510)
 #define RING_EXECLIST_CONTROL(base)		_MMIO((base) + 0x550)
@@ -85,31 +86,12 @@ int intel_execlists_submission_setup(struct intel_engine_cs *engine);
 int intel_execlists_submission_init(struct intel_engine_cs *engine);
 
 /* Logical Ring Contexts */
-
-/*
- * We allocate a header at the start of the context image for our own
- * use, therefore the actual location of the logical state is offset
- * from the start of the VMA. The layout is
- *
- * | [guc]          | [hwsp] [logical state] |
- * |<- our header ->|<- context image      ->|
- *
- */
-/* The first page is used for sharing data with the GuC */
-#define LRC_GUCSHR_PN	(0)
-#define LRC_GUCSHR_SZ	(1)
 /* At the start of the context image is its per-process HWS page */
-#define LRC_PPHWSP_PN	(LRC_GUCSHR_PN + LRC_GUCSHR_SZ)
+#define LRC_PPHWSP_PN	(0)
 #define LRC_PPHWSP_SZ	(1)
-/* Finally we have the logical state for the context */
+/* After the PPHWSP we have the logical state for the context */
 #define LRC_STATE_PN	(LRC_PPHWSP_PN + LRC_PPHWSP_SZ)
 
-/*
- * Currently we include the PPHWSP in __intel_engine_context_size() so
- * the size of the header is synonymous with the start of the PPHWSP.
- */
-#define LRC_HEADER_PAGES LRC_PPHWSP_PN
-
 /* Space within PPHWSP reserved to be used as scratch */
 #define LRC_PPHWSP_SCRATCH		0x34
 #define LRC_PPHWSP_SCRATCH_ADDR		(LRC_PPHWSP_SCRATCH * sizeof(u32))
@@ -145,4 +127,7 @@ struct intel_engine_cs *
 intel_virtual_engine_get_sibling(struct intel_engine_cs *engine,
 				 unsigned int sibling);
 
+bool
+intel_engine_in_execlists_submission_mode(const struct intel_engine_cs *engine);
+
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/gt/intel_mocs.c b/drivers/gpu/drm/i915/gt/intel_mocs.c
index 5bac3966906b..6e881c735b20 100644
--- a/drivers/gpu/drm/i915/gt/intel_mocs.c
+++ b/drivers/gpu/drm/i915/gt/intel_mocs.c
@@ -26,6 +26,7 @@
 #include "intel_gt.h"
 #include "intel_mocs.h"
 #include "intel_lrc.h"
+#include "intel_ring.h"
 
 /* structures required */
 struct drm_i915_mocs_entry {
@@ -461,6 +462,12 @@ static void intel_mocs_init_global(struct intel_gt *gt)
 	struct drm_i915_mocs_table table;
 	unsigned int index;
 
+	/*
+	 * LLC and eDRAM control values are not applicable to dgfx
+	 */
+	if (IS_DGFX(gt->i915))
+		return;
+
 	GEM_BUG_ON(!HAS_GLOBAL_MOCS_REGISTERS(gt->i915));
 
 	if (!get_mocs_settings(gt->i915, &table))
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.c b/drivers/gpu/drm/i915/gt/intel_rc6.c
index 70f0e01a38b9..700104b90163 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.c
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.c
@@ -178,8 +178,13 @@ static void gen9_rc6_enable(struct intel_rc6 *rc6)
 	    GEN6_RC_CTL_RC6_ENABLE |
 	    rc6_mode);
 
-	set(uncore, GEN9_PG_ENABLE,
-	    GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
+	/*
+	 * WaRsDisableCoarsePowerGating:skl,cnl
+	 *   - Render/Media PG need to be disabled with RC6.
+	 */
+	if (!NEEDS_WaRsDisableCoarsePowerGating(rc6_to_i915(rc6)))
+		set(uncore, GEN9_PG_ENABLE,
+		    GEN9_RENDER_PG_ENABLE | GEN9_MEDIA_PG_ENABLE);
 }
 
 static void gen8_rc6_enable(struct intel_rc6 *rc6)
@@ -486,6 +491,66 @@ static void rpm_put(struct intel_rc6 *rc6)
 	rc6->wakeref = false;
 }
 
+static bool intel_rc6_ctx_corrupted(struct intel_rc6 *rc6)
+{
+	return !intel_uncore_read(rc6_to_uncore(rc6), GEN8_RC6_CTX_INFO);
+}
+
+static void intel_rc6_ctx_wa_init(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return;
+
+	if (intel_rc6_ctx_corrupted(rc6)) {
+		DRM_INFO("RC6 context corrupted, disabling runtime power management\n");
+		rc6->ctx_corrupted = true;
+	}
+}
+
+/**
+ * intel_rc6_ctx_wa_resume - system resume sequence for the RC6 CTX WA
+ * @rc6: rc6 state
+ *
+ * Perform any steps needed to re-init the RC6 CTX WA after system resume.
+ */
+void intel_rc6_ctx_wa_resume(struct intel_rc6 *rc6)
+{
+	if (rc6->ctx_corrupted && !intel_rc6_ctx_corrupted(rc6)) {
+		DRM_INFO("RC6 context restored, re-enabling runtime power management\n");
+		rc6->ctx_corrupted = false;
+	}
+}
+
+/**
+ * intel_rc6_ctx_wa_check - check for a new RC6 CTX corruption
+ * @rc6: rc6 state
+ *
+ * Check if an RC6 CTX corruption has happened since the last check and if so
+ * disable RC6 and runtime power management.
+*/
+void intel_rc6_ctx_wa_check(struct intel_rc6 *rc6)
+{
+	struct drm_i915_private *i915 = rc6_to_i915(rc6);
+
+	if (!NEEDS_RC6_CTX_CORRUPTION_WA(i915))
+		return;
+
+	if (rc6->ctx_corrupted)
+		return;
+
+	if (!intel_rc6_ctx_corrupted(rc6))
+		return;
+
+	DRM_NOTE("RC6 context corruption, disabling runtime power management\n");
+
+	intel_rc6_disable(rc6);
+	rc6->ctx_corrupted = true;
+
+	return;
+}
+
 static void __intel_rc6_disable(struct intel_rc6 *rc6)
 {
 	struct drm_i915_private *i915 = rc6_to_i915(rc6);
@@ -510,6 +575,8 @@ void intel_rc6_init(struct intel_rc6 *rc6)
 	if (!rc6_supported(rc6))
 		return;
 
+	intel_rc6_ctx_wa_init(rc6);
+
 	if (IS_CHERRYVIEW(i915))
 		err = chv_rc6_init(rc6);
 	else if (IS_VALLEYVIEW(i915))
@@ -525,6 +592,11 @@ void intel_rc6_init(struct intel_rc6 *rc6)
 
 void intel_rc6_sanitize(struct intel_rc6 *rc6)
 {
+	if (rc6->enabled) { /* unbalanced suspend/resume */
+		rpm_get(rc6);
+		rc6->enabled = false;
+	}
+
 	if (rc6->supported)
 		__intel_rc6_disable(rc6);
 }
@@ -539,6 +611,9 @@ void intel_rc6_enable(struct intel_rc6 *rc6)
 
 	GEM_BUG_ON(rc6->enabled);
 
+	if (rc6->ctx_corrupted)
+		return;
+
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	if (IS_CHERRYVIEW(i915))
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6.h b/drivers/gpu/drm/i915/gt/intel_rc6.h
index 5e6711f36457..1370f6834a4c 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6.h
+++ b/drivers/gpu/drm/i915/gt/intel_rc6.h
@@ -22,4 +22,7 @@ void intel_rc6_disable(struct intel_rc6 *rc6);
 u64 intel_rc6_residency_ns(struct intel_rc6 *rc6, i915_reg_t reg);
 u64 intel_rc6_residency_us(struct intel_rc6 *rc6, i915_reg_t reg);
 
+void intel_rc6_ctx_wa_check(struct intel_rc6 *rc6);
+void intel_rc6_ctx_wa_resume(struct intel_rc6 *rc6);
+
 #endif /* INTEL_RC6_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rc6_types.h b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
index 214f354d6ae4..89ad5697a8d4 100644
--- a/drivers/gpu/drm/i915/gt/intel_rc6_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_rc6_types.h
@@ -23,6 +23,7 @@ struct intel_rc6 {
 	bool supported : 1;
 	bool enabled : 1;
 	bool wakeref : 1;
+	bool ctx_corrupted : 1;
 };
 
 #endif /* INTEL_RC6_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_renderstate.c b/drivers/gpu/drm/i915/gt/intel_renderstate.c
index 6d05f9c64178..c4edc35e7d89 100644
--- a/drivers/gpu/drm/i915/gt/intel_renderstate.c
+++ b/drivers/gpu/drm/i915/gt/intel_renderstate.c
@@ -27,6 +27,7 @@
 
 #include "i915_drv.h"
 #include "intel_renderstate.h"
+#include "intel_ring.h"
 
 struct intel_renderstate {
 	const struct intel_renderstate_rodata *rodata;
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index bf8d1ed4b1d8..c97423a76642 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -1024,8 +1024,6 @@ void intel_gt_reset(struct intel_gt *gt,
 	if (ret)
 		goto taint;
 
-	intel_gt_queue_hangcheck(gt);
-
 finish:
 	reset_finish(gt, awake);
 unlock:
@@ -1116,7 +1114,7 @@ int intel_engine_reset(struct intel_engine_cs *engine, const char *msg)
 out:
 	intel_engine_cancel_stop_cs(engine);
 	reset_finish_engine(engine);
-	intel_engine_pm_put(engine);
+	intel_engine_pm_put_async(engine);
 	return ret;
 }
 
@@ -1353,4 +1351,5 @@ void __intel_fini_wedge(struct intel_wedge_me *w)
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftest_reset.c"
+#include "selftest_hangcheck.c"
 #endif
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
new file mode 100644
index 000000000000..374b28f13ca0
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -0,0 +1,318 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "gem/i915_gem_object.h"
+#include "i915_drv.h"
+#include "i915_vma.h"
+#include "intel_engine.h"
+#include "intel_ring.h"
+#include "intel_timeline.h"
+
+unsigned int intel_ring_update_space(struct intel_ring *ring)
+{
+	unsigned int space;
+
+	space = __intel_ring_space(ring->head, ring->emit, ring->size);
+
+	ring->space = space;
+	return space;
+}
+
+int intel_ring_pin(struct intel_ring *ring)
+{
+	struct i915_vma *vma = ring->vma;
+	unsigned int flags;
+	void *addr;
+	int ret;
+
+	if (atomic_fetch_inc(&ring->pin_count))
+		return 0;
+
+	flags = PIN_GLOBAL;
+
+	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
+	flags |= PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
+
+	if (vma->obj->stolen)
+		flags |= PIN_MAPPABLE;
+	else
+		flags |= PIN_HIGH;
+
+	ret = i915_vma_pin(vma, 0, 0, flags);
+	if (unlikely(ret))
+		goto err_unpin;
+
+	if (i915_vma_is_map_and_fenceable(vma))
+		addr = (void __force *)i915_vma_pin_iomap(vma);
+	else
+		addr = i915_gem_object_pin_map(vma->obj,
+					       i915_coherent_map_type(vma->vm->i915));
+	if (IS_ERR(addr)) {
+		ret = PTR_ERR(addr);
+		goto err_ring;
+	}
+
+	i915_vma_make_unshrinkable(vma);
+
+	/* Discard any unused bytes beyond that submitted to hw. */
+	intel_ring_reset(ring, ring->emit);
+
+	ring->vaddr = addr;
+	return 0;
+
+err_ring:
+	i915_vma_unpin(vma);
+err_unpin:
+	atomic_dec(&ring->pin_count);
+	return ret;
+}
+
+void intel_ring_reset(struct intel_ring *ring, u32 tail)
+{
+	tail = intel_ring_wrap(ring, tail);
+	ring->tail = tail;
+	ring->head = tail;
+	ring->emit = tail;
+	intel_ring_update_space(ring);
+}
+
+void intel_ring_unpin(struct intel_ring *ring)
+{
+	struct i915_vma *vma = ring->vma;
+
+	if (!atomic_dec_and_test(&ring->pin_count))
+		return;
+
+	i915_vma_unset_ggtt_write(vma);
+	if (i915_vma_is_map_and_fenceable(vma))
+		i915_vma_unpin_iomap(vma);
+	else
+		i915_gem_object_unpin_map(vma->obj);
+
+	i915_vma_make_purgeable(vma);
+	i915_vma_unpin(vma);
+}
+
+static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
+{
+	struct i915_address_space *vm = &ggtt->vm;
+	struct drm_i915_private *i915 = vm->i915;
+	struct drm_i915_gem_object *obj;
+	struct i915_vma *vma;
+
+	obj = ERR_PTR(-ENODEV);
+	if (i915_ggtt_has_aperture(ggtt))
+		obj = i915_gem_object_create_stolen(i915, size);
+	if (IS_ERR(obj))
+		obj = i915_gem_object_create_internal(i915, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	/*
+	 * 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, vm, NULL);
+	if (IS_ERR(vma))
+		goto err;
+
+	return vma;
+
+err:
+	i915_gem_object_put(obj);
+	return vma;
+}
+
+struct intel_ring *
+intel_engine_create_ring(struct intel_engine_cs *engine, int size)
+{
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_ring *ring;
+	struct i915_vma *vma;
+
+	GEM_BUG_ON(!is_power_of_2(size));
+	GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES);
+
+	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
+	if (!ring)
+		return ERR_PTR(-ENOMEM);
+
+	kref_init(&ring->ref);
+	ring->size = size;
+
+	/*
+	 * Workaround an erratum on the i830 which causes a hang if
+	 * the TAIL pointer points to within the last 2 cachelines
+	 * of the buffer.
+	 */
+	ring->effective_size = size;
+	if (IS_I830(i915) || IS_I845G(i915))
+		ring->effective_size -= 2 * CACHELINE_BYTES;
+
+	intel_ring_update_space(ring);
+
+	vma = create_ring_vma(engine->gt->ggtt, size);
+	if (IS_ERR(vma)) {
+		kfree(ring);
+		return ERR_CAST(vma);
+	}
+	ring->vma = vma;
+
+	return ring;
+}
+
+void intel_ring_free(struct kref *ref)
+{
+	struct intel_ring *ring = container_of(ref, typeof(*ring), ref);
+
+	i915_vma_put(ring->vma);
+	kfree(ring);
+}
+
+static noinline int
+wait_for_space(struct intel_ring *ring,
+	       struct intel_timeline *tl,
+	       unsigned int bytes)
+{
+	struct i915_request *target;
+	long timeout;
+
+	if (intel_ring_update_space(ring) >= bytes)
+		return 0;
+
+	GEM_BUG_ON(list_empty(&tl->requests));
+	list_for_each_entry(target, &tl->requests, link) {
+		if (target->ring != ring)
+			continue;
+
+		/* Would completion of this request free enough space? */
+		if (bytes <= __intel_ring_space(target->postfix,
+						ring->emit, ring->size))
+			break;
+	}
+
+	if (GEM_WARN_ON(&target->link == &tl->requests))
+		return -ENOSPC;
+
+	timeout = i915_request_wait(target,
+				    I915_WAIT_INTERRUPTIBLE,
+				    MAX_SCHEDULE_TIMEOUT);
+	if (timeout < 0)
+		return timeout;
+
+	i915_request_retire_upto(target);
+
+	intel_ring_update_space(ring);
+	GEM_BUG_ON(ring->space < bytes);
+	return 0;
+}
+
+u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
+{
+	struct intel_ring *ring = rq->ring;
+	const unsigned int remain_usable = ring->effective_size - ring->emit;
+	const unsigned int bytes = num_dwords * sizeof(u32);
+	unsigned int need_wrap = 0;
+	unsigned int total_bytes;
+	u32 *cs;
+
+	/* Packets must be qword aligned. */
+	GEM_BUG_ON(num_dwords & 1);
+
+	total_bytes = bytes + rq->reserved_space;
+	GEM_BUG_ON(total_bytes > ring->effective_size);
+
+	if (unlikely(total_bytes > remain_usable)) {
+		const int remain_actual = ring->size - ring->emit;
+
+		if (bytes > remain_usable) {
+			/*
+			 * Not enough space for the basic request. So need to
+			 * flush out the remainder and then wait for
+			 * base + reserved.
+			 */
+			total_bytes += remain_actual;
+			need_wrap = remain_actual | 1;
+		} else  {
+			/*
+			 * The base request will fit but the reserved space
+			 * falls off the end. So we don't need an immediate
+			 * wrap and only need to effectively wait for the
+			 * reserved size from the start of ringbuffer.
+			 */
+			total_bytes = rq->reserved_space + remain_actual;
+		}
+	}
+
+	if (unlikely(total_bytes > ring->space)) {
+		int ret;
+
+		/*
+		 * Space is reserved in the ringbuffer for finalising the
+		 * request, as that cannot be allowed to fail. During request
+		 * finalisation, reserved_space is set to 0 to stop the
+		 * overallocation and the assumption is that then we never need
+		 * to wait (which has the risk of failing with EINTR).
+		 *
+		 * See also i915_request_alloc() and i915_request_add().
+		 */
+		GEM_BUG_ON(!rq->reserved_space);
+
+		ret = wait_for_space(ring,
+				     i915_request_timeline(rq),
+				     total_bytes);
+		if (unlikely(ret))
+			return ERR_PTR(ret);
+	}
+
+	if (unlikely(need_wrap)) {
+		need_wrap &= ~1;
+		GEM_BUG_ON(need_wrap > ring->space);
+		GEM_BUG_ON(ring->emit + need_wrap > ring->size);
+		GEM_BUG_ON(!IS_ALIGNED(need_wrap, sizeof(u64)));
+
+		/* Fill the tail with MI_NOOP */
+		memset64(ring->vaddr + ring->emit, 0, need_wrap / sizeof(u64));
+		ring->space -= need_wrap;
+		ring->emit = 0;
+	}
+
+	GEM_BUG_ON(ring->emit > ring->size - bytes);
+	GEM_BUG_ON(ring->space < bytes);
+	cs = ring->vaddr + ring->emit;
+	GEM_DEBUG_EXEC(memset32(cs, POISON_INUSE, bytes / sizeof(*cs)));
+	ring->emit += bytes;
+	ring->space -= bytes;
+
+	return cs;
+}
+
+/* Align the ring tail to a cacheline boundary */
+int intel_ring_cacheline_align(struct i915_request *rq)
+{
+	int num_dwords;
+	void *cs;
+
+	num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
+	if (num_dwords == 0)
+		return 0;
+
+	num_dwords = CACHELINE_DWORDS - num_dwords;
+	GEM_BUG_ON(num_dwords & 1);
+
+	cs = intel_ring_begin(rq, num_dwords);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	memset64(cs, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2);
+	intel_ring_advance(rq, cs + num_dwords);
+
+	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
new file mode 100644
index 000000000000..ea2839d9e044
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -0,0 +1,131 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_RING_H
+#define INTEL_RING_H
+
+#include "i915_gem.h" /* GEM_BUG_ON */
+#include "i915_request.h"
+#include "intel_ring_types.h"
+
+struct intel_engine_cs;
+
+struct intel_ring *
+intel_engine_create_ring(struct intel_engine_cs *engine, int size);
+
+u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords);
+int intel_ring_cacheline_align(struct i915_request *rq);
+
+unsigned int intel_ring_update_space(struct intel_ring *ring);
+
+int intel_ring_pin(struct intel_ring *ring);
+void intel_ring_unpin(struct intel_ring *ring);
+void intel_ring_reset(struct intel_ring *ring, u32 tail);
+
+void intel_ring_free(struct kref *ref);
+
+static inline struct intel_ring *intel_ring_get(struct intel_ring *ring)
+{
+	kref_get(&ring->ref);
+	return ring;
+}
+
+static inline void intel_ring_put(struct intel_ring *ring)
+{
+	kref_put(&ring->ref, intel_ring_free);
+}
+
+static inline void intel_ring_advance(struct i915_request *rq, u32 *cs)
+{
+	/* Dummy function.
+	 *
+	 * This serves as a placeholder in the code so that the reader
+	 * can compare against the preceding intel_ring_begin() and
+	 * check that the number of dwords emitted matches the space
+	 * reserved for the command packet (i.e. the value passed to
+	 * intel_ring_begin()).
+	 */
+	GEM_BUG_ON((rq->ring->vaddr + rq->ring->emit) != cs);
+}
+
+static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
+{
+	return pos & (ring->size - 1);
+}
+
+static inline bool
+intel_ring_offset_valid(const struct intel_ring *ring,
+			unsigned int pos)
+{
+	if (pos & -ring->size) /* must be strictly within the ring */
+		return false;
+
+	if (!IS_ALIGNED(pos, 8)) /* must be qword aligned */
+		return false;
+
+	return true;
+}
+
+static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
+{
+	/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
+	u32 offset = addr - rq->ring->vaddr;
+	GEM_BUG_ON(offset > rq->ring->size);
+	return intel_ring_wrap(rq->ring, offset);
+}
+
+static inline void
+assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
+{
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
+
+	/*
+	 * "Ring Buffer Use"
+	 *	Gen2 BSpec "1. Programming Environment" / 1.4.4.6
+	 *	Gen3 BSpec "1c Memory Interface Functions" / 2.3.4.5
+	 *	Gen4+ BSpec "1c Memory Interface and Command Stream" / 5.3.4.5
+	 * "If the Ring Buffer Head Pointer and the Tail Pointer are on the
+	 * same cacheline, the Head Pointer must not be greater than the Tail
+	 * Pointer."
+	 *
+	 * We use ring->head as the last known location of the actual RING_HEAD,
+	 * it may have advanced but in the worst case it is equally the same
+	 * as ring->head and so we should never program RING_TAIL to advance
+	 * into the same cacheline as ring->head.
+	 */
+#define cacheline(a) round_down(a, CACHELINE_BYTES)
+	GEM_BUG_ON(cacheline(tail) == cacheline(ring->head) &&
+		   tail < ring->head);
+#undef cacheline
+}
+
+static inline unsigned int
+intel_ring_set_tail(struct intel_ring *ring, unsigned int tail)
+{
+	/* Whilst writes to the tail are strictly order, there is no
+	 * serialisation between readers and the writers. The tail may be
+	 * read by i915_request_retire() just as it is being updated
+	 * by execlists, as although the breadcrumb is complete, the context
+	 * switch hasn't been seen.
+	 */
+	assert_ring_tail_valid(ring, tail);
+	ring->tail = tail;
+	return tail;
+}
+
+static inline unsigned int
+__intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
+{
+	/*
+	 * "If the Ring Buffer Head Pointer and the Tail Pointer are on the
+	 * same cacheline, the Head Pointer must not be greater than the Tail
+	 * Pointer."
+	 */
+	GEM_BUG_ON(!is_power_of_2(size));
+	return (head - tail - CACHELINE_BYTES) & (size - 1);
+}
+
+#endif /* INTEL_RING_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index bf631f15aa78..a47d5a7c32c9 100644
--- a/drivers/gpu/drm/i915/gt/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -40,6 +40,7 @@
 #include "intel_gt_irq.h"
 #include "intel_gt_pm_irq.h"
 #include "intel_reset.h"
+#include "intel_ring.h"
 #include "intel_workarounds.h"
 
 /* Rough estimate of the typical request size, performing a flush,
@@ -47,16 +48,6 @@
  */
 #define LEGACY_REQUEST_SIZE 200
 
-unsigned int intel_ring_update_space(struct intel_ring *ring)
-{
-	unsigned int space;
-
-	space = __intel_ring_space(ring->head, ring->emit, ring->size);
-
-	ring->space = space;
-	return space;
-}
-
 static int
 gen2_render_ring_flush(struct i915_request *rq, u32 mode)
 {
@@ -1186,162 +1177,6 @@ i915_emit_bb_start(struct i915_request *rq,
 	return 0;
 }
 
-int intel_ring_pin(struct intel_ring *ring)
-{
-	struct i915_vma *vma = ring->vma;
-	unsigned int flags;
-	void *addr;
-	int ret;
-
-	if (atomic_fetch_inc(&ring->pin_count))
-		return 0;
-
-	flags = PIN_GLOBAL;
-
-	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
-	flags |= PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
-
-	if (vma->obj->stolen)
-		flags |= PIN_MAPPABLE;
-	else
-		flags |= PIN_HIGH;
-
-	ret = i915_vma_pin(vma, 0, 0, flags);
-	if (unlikely(ret))
-		goto err_unpin;
-
-	if (i915_vma_is_map_and_fenceable(vma))
-		addr = (void __force *)i915_vma_pin_iomap(vma);
-	else
-		addr = i915_gem_object_pin_map(vma->obj,
-					       i915_coherent_map_type(vma->vm->i915));
-	if (IS_ERR(addr)) {
-		ret = PTR_ERR(addr);
-		goto err_ring;
-	}
-
-	i915_vma_make_unshrinkable(vma);
-
-	GEM_BUG_ON(ring->vaddr);
-	ring->vaddr = addr;
-
-	return 0;
-
-err_ring:
-	i915_vma_unpin(vma);
-err_unpin:
-	atomic_dec(&ring->pin_count);
-	return ret;
-}
-
-void intel_ring_reset(struct intel_ring *ring, u32 tail)
-{
-	tail = intel_ring_wrap(ring, tail);
-	ring->tail = tail;
-	ring->head = tail;
-	ring->emit = tail;
-	intel_ring_update_space(ring);
-}
-
-void intel_ring_unpin(struct intel_ring *ring)
-{
-	struct i915_vma *vma = ring->vma;
-
-	if (!atomic_dec_and_test(&ring->pin_count))
-		return;
-
-	/* Discard any unused bytes beyond that submitted to hw. */
-	intel_ring_reset(ring, ring->emit);
-
-	i915_vma_unset_ggtt_write(vma);
-	if (i915_vma_is_map_and_fenceable(vma))
-		i915_vma_unpin_iomap(vma);
-	else
-		i915_gem_object_unpin_map(vma->obj);
-
-	GEM_BUG_ON(!ring->vaddr);
-	ring->vaddr = NULL;
-
-	i915_vma_unpin(vma);
-	i915_vma_make_purgeable(vma);
-}
-
-static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
-{
-	struct i915_address_space *vm = &ggtt->vm;
-	struct drm_i915_private *i915 = vm->i915;
-	struct drm_i915_gem_object *obj;
-	struct i915_vma *vma;
-
-	obj = i915_gem_object_create_stolen(i915, size);
-	if (IS_ERR(obj))
-		obj = i915_gem_object_create_internal(i915, size);
-	if (IS_ERR(obj))
-		return ERR_CAST(obj);
-
-	/*
-	 * 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, vm, NULL);
-	if (IS_ERR(vma))
-		goto err;
-
-	return vma;
-
-err:
-	i915_gem_object_put(obj);
-	return vma;
-}
-
-struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size)
-{
-	struct drm_i915_private *i915 = engine->i915;
-	struct intel_ring *ring;
-	struct i915_vma *vma;
-
-	GEM_BUG_ON(!is_power_of_2(size));
-	GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES);
-
-	ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-	if (!ring)
-		return ERR_PTR(-ENOMEM);
-
-	kref_init(&ring->ref);
-
-	ring->size = size;
-	/* Workaround an erratum on the i830 which causes a hang if
-	 * the TAIL pointer points to within the last 2 cachelines
-	 * of the buffer.
-	 */
-	ring->effective_size = size;
-	if (IS_I830(i915) || IS_I845G(i915))
-		ring->effective_size -= 2 * CACHELINE_BYTES;
-
-	intel_ring_update_space(ring);
-
-	vma = create_ring_vma(engine->gt->ggtt, size);
-	if (IS_ERR(vma)) {
-		kfree(ring);
-		return ERR_CAST(vma);
-	}
-	ring->vma = vma;
-
-	return ring;
-}
-
-void intel_ring_free(struct kref *ref)
-{
-	struct intel_ring *ring = container_of(ref, typeof(*ring), ref);
-
-	i915_vma_put(ring->vma);
-	kfree(ring);
-}
-
 static void __ring_context_fini(struct intel_context *ce)
 {
 	i915_vma_put(ce->state);
@@ -1836,148 +1671,6 @@ static int ring_request_alloc(struct i915_request *request)
 	return 0;
 }
 
-static noinline int
-wait_for_space(struct intel_ring *ring,
-	       struct intel_timeline *tl,
-	       unsigned int bytes)
-{
-	struct i915_request *target;
-	long timeout;
-
-	if (intel_ring_update_space(ring) >= bytes)
-		return 0;
-
-	GEM_BUG_ON(list_empty(&tl->requests));
-	list_for_each_entry(target, &tl->requests, link) {
-		if (target->ring != ring)
-			continue;
-
-		/* Would completion of this request free enough space? */
-		if (bytes <= __intel_ring_space(target->postfix,
-						ring->emit, ring->size))
-			break;
-	}
-
-	if (GEM_WARN_ON(&target->link == &tl->requests))
-		return -ENOSPC;
-
-	timeout = i915_request_wait(target,
-				    I915_WAIT_INTERRUPTIBLE,
-				    MAX_SCHEDULE_TIMEOUT);
-	if (timeout < 0)
-		return timeout;
-
-	i915_request_retire_upto(target);
-
-	intel_ring_update_space(ring);
-	GEM_BUG_ON(ring->space < bytes);
-	return 0;
-}
-
-u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords)
-{
-	struct intel_ring *ring = rq->ring;
-	const unsigned int remain_usable = ring->effective_size - ring->emit;
-	const unsigned int bytes = num_dwords * sizeof(u32);
-	unsigned int need_wrap = 0;
-	unsigned int total_bytes;
-	u32 *cs;
-
-	/* Packets must be qword aligned. */
-	GEM_BUG_ON(num_dwords & 1);
-
-	total_bytes = bytes + rq->reserved_space;
-	GEM_BUG_ON(total_bytes > ring->effective_size);
-
-	if (unlikely(total_bytes > remain_usable)) {
-		const int remain_actual = ring->size - ring->emit;
-
-		if (bytes > remain_usable) {
-			/*
-			 * Not enough space for the basic request. So need to
-			 * flush out the remainder and then wait for
-			 * base + reserved.
-			 */
-			total_bytes += remain_actual;
-			need_wrap = remain_actual | 1;
-		} else  {
-			/*
-			 * The base request will fit but the reserved space
-			 * falls off the end. So we don't need an immediate
-			 * wrap and only need to effectively wait for the
-			 * reserved size from the start of ringbuffer.
-			 */
-			total_bytes = rq->reserved_space + remain_actual;
-		}
-	}
-
-	if (unlikely(total_bytes > ring->space)) {
-		int ret;
-
-		/*
-		 * Space is reserved in the ringbuffer for finalising the
-		 * request, as that cannot be allowed to fail. During request
-		 * finalisation, reserved_space is set to 0 to stop the
-		 * overallocation and the assumption is that then we never need
-		 * to wait (which has the risk of failing with EINTR).
-		 *
-		 * See also i915_request_alloc() and i915_request_add().
-		 */
-		GEM_BUG_ON(!rq->reserved_space);
-
-		ret = wait_for_space(ring,
-				     i915_request_timeline(rq),
-				     total_bytes);
-		if (unlikely(ret))
-			return ERR_PTR(ret);
-	}
-
-	if (unlikely(need_wrap)) {
-		need_wrap &= ~1;
-		GEM_BUG_ON(need_wrap > ring->space);
-		GEM_BUG_ON(ring->emit + need_wrap > ring->size);
-		GEM_BUG_ON(!IS_ALIGNED(need_wrap, sizeof(u64)));
-
-		/* Fill the tail with MI_NOOP */
-		memset64(ring->vaddr + ring->emit, 0, need_wrap / sizeof(u64));
-		ring->space -= need_wrap;
-		ring->emit = 0;
-	}
-
-	GEM_BUG_ON(ring->emit > ring->size - bytes);
-	GEM_BUG_ON(ring->space < bytes);
-	cs = ring->vaddr + ring->emit;
-	GEM_DEBUG_EXEC(memset32(cs, POISON_INUSE, bytes / sizeof(*cs)));
-	ring->emit += bytes;
-	ring->space -= bytes;
-
-	return cs;
-}
-
-/* Align the ring tail to a cacheline boundary */
-int intel_ring_cacheline_align(struct i915_request *rq)
-{
-	int num_dwords;
-	void *cs;
-
-	num_dwords = (rq->ring->emit & (CACHELINE_BYTES - 1)) / sizeof(u32);
-	if (num_dwords == 0)
-		return 0;
-
-	num_dwords = CACHELINE_DWORDS - num_dwords;
-	GEM_BUG_ON(num_dwords & 1);
-
-	cs = intel_ring_begin(rq, num_dwords);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	memset64(cs, (u64)MI_NOOP << 32 | MI_NOOP, num_dwords / 2);
-	intel_ring_advance(rq, cs);
-
-	GEM_BUG_ON(rq->ring->emit & (CACHELINE_BYTES - 1));
-	return 0;
-}
-
 static void gen6_bsd_submit_request(struct i915_request *request)
 {
 	struct intel_uncore *uncore = request->engine->uncore;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h
new file mode 100644
index 000000000000..d9f17f38e0cc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h
@@ -0,0 +1,51 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_RING_TYPES_H
+#define INTEL_RING_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/kref.h>
+#include <linux/types.h>
+
+/*
+ * Early gen2 devices have a cacheline of just 32 bytes, using 64 is overkill,
+ * but keeps the logic simple. Indeed, the whole purpose of this macro is just
+ * to give some inclination as to some of the magic values used in the various
+ * workarounds!
+ */
+#define CACHELINE_BYTES 64
+#define CACHELINE_DWORDS (CACHELINE_BYTES / sizeof(u32))
+
+struct i915_vma;
+
+struct intel_ring {
+	struct kref ref;
+	struct i915_vma *vma;
+	void *vaddr;
+
+	/*
+	 * As we have two types of rings, one global to the engine used
+	 * by ringbuffer submission and those that are exclusive to a
+	 * context used by execlists, we have to play safe and allow
+	 * atomic updates to the pin_count. However, the actual pinning
+	 * of the context is either done during initialisation for
+	 * ringbuffer submission or serialised as part of the context
+	 * pinning for execlists, and so we do not need a mutex ourselves
+	 * to serialise intel_ring_pin/intel_ring_unpin.
+	 */
+	atomic_t pin_count;
+
+	u32 head;
+	u32 tail;
+	u32 emit;
+
+	u32 space;
+	u32 size;
+	u32 effective_size;
+};
+
+#endif /* INTEL_RING_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.c b/drivers/gpu/drm/i915/gt/intel_rps.c
new file mode 100644
index 000000000000..20d6ee148afc
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_rps.c
@@ -0,0 +1,1872 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_gt.h"
+#include "intel_gt_irq.h"
+#include "intel_gt_pm_irq.h"
+#include "intel_rps.h"
+#include "intel_sideband.h"
+#include "../../../platform/x86/intel_ips.h"
+
+/*
+ * Lock protecting IPS related data structures
+ */
+static DEFINE_SPINLOCK(mchdev_lock);
+
+static struct intel_gt *rps_to_gt(struct intel_rps *rps)
+{
+	return container_of(rps, struct intel_gt, rps);
+}
+
+static struct drm_i915_private *rps_to_i915(struct intel_rps *rps)
+{
+	return rps_to_gt(rps)->i915;
+}
+
+static struct intel_uncore *rps_to_uncore(struct intel_rps *rps)
+{
+	return rps_to_gt(rps)->uncore;
+}
+
+static u32 rps_pm_sanitize_mask(struct intel_rps *rps, u32 mask)
+{
+	return mask & ~rps->pm_intrmsk_mbz;
+}
+
+static u32 rps_pm_mask(struct intel_rps *rps, u8 val)
+{
+	u32 mask = 0;
+
+	/* We use UP_EI_EXPIRED interrupts for both up/down in manual mode */
+	if (val > rps->min_freq_softlimit)
+		mask |= (GEN6_PM_RP_UP_EI_EXPIRED |
+			 GEN6_PM_RP_DOWN_THRESHOLD |
+			 GEN6_PM_RP_DOWN_TIMEOUT);
+
+	if (val < rps->max_freq_softlimit)
+		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
+
+	mask &= rps->pm_events;
+
+	return rps_pm_sanitize_mask(rps, ~mask);
+}
+
+static void rps_reset_ei(struct intel_rps *rps)
+{
+	memset(&rps->ei, 0, sizeof(rps->ei));
+}
+
+static void rps_enable_interrupts(struct intel_rps *rps)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	rps_reset_ei(rps);
+
+	if (IS_VALLEYVIEW(gt->i915))
+		/* WaGsvRC0ResidencyMethod:vlv */
+		rps->pm_events = GEN6_PM_RP_UP_EI_EXPIRED;
+	else
+		rps->pm_events = (GEN6_PM_RP_UP_THRESHOLD |
+				  GEN6_PM_RP_DOWN_THRESHOLD |
+				  GEN6_PM_RP_DOWN_TIMEOUT);
+
+	spin_lock_irq(&gt->irq_lock);
+	gen6_gt_pm_enable_irq(gt, rps->pm_events);
+	spin_unlock_irq(&gt->irq_lock);
+
+	intel_uncore_write(gt->uncore, GEN6_PMINTRMSK,
+			   rps_pm_mask(rps, rps->cur_freq));
+}
+
+static void gen6_rps_reset_interrupts(struct intel_rps *rps)
+{
+	gen6_gt_pm_reset_iir(rps_to_gt(rps), GEN6_PM_RPS_EVENTS);
+}
+
+static void gen11_rps_reset_interrupts(struct intel_rps *rps)
+{
+	while (gen11_gt_reset_one_iir(rps_to_gt(rps), 0, GEN11_GTPM))
+		;
+}
+
+static void rps_reset_interrupts(struct intel_rps *rps)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	spin_lock_irq(&gt->irq_lock);
+	if (INTEL_GEN(gt->i915) >= 11)
+		gen11_rps_reset_interrupts(rps);
+	else
+		gen6_rps_reset_interrupts(rps);
+
+	rps->pm_iir = 0;
+	spin_unlock_irq(&gt->irq_lock);
+}
+
+static void rps_disable_interrupts(struct intel_rps *rps)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	rps->pm_events = 0;
+
+	intel_uncore_write(gt->uncore, GEN6_PMINTRMSK,
+			   rps_pm_sanitize_mask(rps, ~0u));
+
+	spin_lock_irq(&gt->irq_lock);
+	gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
+	spin_unlock_irq(&gt->irq_lock);
+
+	intel_synchronize_irq(gt->i915);
+
+	/*
+	 * Now that we will not be generating any more work, flush any
+	 * outstanding tasks. As we are called on the RPS idle path,
+	 * we will reset the GPU to minimum frequencies, so the current
+	 * state of the worker can be discarded.
+	 */
+	cancel_work_sync(&rps->work);
+
+	rps_reset_interrupts(rps);
+}
+
+static const struct cparams {
+	u16 i;
+	u16 t;
+	u16 m;
+	u16 c;
+} cparams[] = {
+	{ 1, 1333, 301, 28664 },
+	{ 1, 1066, 294, 24460 },
+	{ 1, 800, 294, 25192 },
+	{ 0, 1333, 276, 27605 },
+	{ 0, 1066, 276, 27605 },
+	{ 0, 800, 231, 23784 },
+};
+
+static void gen5_rps_init(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u8 fmax, fmin, fstart;
+	u32 rgvmodectl;
+	int c_m, i;
+
+	if (i915->fsb_freq <= 3200)
+		c_m = 0;
+	else if (i915->fsb_freq <= 4800)
+		c_m = 1;
+	else
+		c_m = 2;
+
+	for (i = 0; i < ARRAY_SIZE(cparams); i++) {
+		if (cparams[i].i == c_m && cparams[i].t == i915->mem_freq) {
+			rps->ips.m = cparams[i].m;
+			rps->ips.c = cparams[i].c;
+			break;
+		}
+	}
+
+	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);
+
+	/* Set up min, max, and cur for interrupt handling */
+	fmax = (rgvmodectl & MEMMODE_FMAX_MASK) >> MEMMODE_FMAX_SHIFT;
+	fmin = (rgvmodectl & MEMMODE_FMIN_MASK);
+	fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
+		MEMMODE_FSTART_SHIFT;
+	DRM_DEBUG_DRIVER("fmax: %d, fmin: %d, fstart: %d\n",
+			 fmax, fmin, fstart);
+
+	rps->min_freq = fmax;
+	rps->max_freq = fmin;
+
+	rps->idle_freq = rps->min_freq;
+	rps->cur_freq = rps->idle_freq;
+}
+
+static unsigned long
+__ips_chipset_val(struct intel_ips *ips)
+{
+	struct intel_uncore *uncore =
+		rps_to_uncore(container_of(ips, struct intel_rps, ips));
+	unsigned long now = jiffies_to_msecs(jiffies), dt;
+	unsigned long result;
+	u64 total, delta;
+
+	lockdep_assert_held(&mchdev_lock);
+
+	/*
+	 * Prevent division-by-zero if we are asking too fast.
+	 * Also, we don't get interesting results if we are polling
+	 * faster than once in 10ms, so just return the saved value
+	 * in such cases.
+	 */
+	dt = now - ips->last_time1;
+	if (dt <= 10)
+		return ips->chipset_power;
+
+	/* FIXME: handle per-counter overflow */
+	total = intel_uncore_read(uncore, DMIEC);
+	total += intel_uncore_read(uncore, DDREC);
+	total += intel_uncore_read(uncore, CSIEC);
+
+	delta = total - ips->last_count1;
+
+	result = div_u64(div_u64(ips->m * delta, dt) + ips->c, 10);
+
+	ips->last_count1 = total;
+	ips->last_time1 = now;
+
+	ips->chipset_power = result;
+
+	return result;
+}
+
+static unsigned long ips_mch_val(struct intel_uncore *uncore)
+{
+	unsigned int m, x, b;
+	u32 tsfs;
+
+	tsfs = intel_uncore_read(uncore, TSFS);
+	x = intel_uncore_read8(uncore, TR1);
+
+	b = tsfs & TSFS_INTR_MASK;
+	m = (tsfs & TSFS_SLOPE_MASK) >> TSFS_SLOPE_SHIFT;
+
+	return m * x / 127 - b;
+}
+
+static int _pxvid_to_vd(u8 pxvid)
+{
+	if (pxvid == 0)
+		return 0;
+
+	if (pxvid >= 8 && pxvid < 31)
+		pxvid = 31;
+
+	return (pxvid + 2) * 125;
+}
+
+static u32 pvid_to_extvid(struct drm_i915_private *i915, u8 pxvid)
+{
+	const int vd = _pxvid_to_vd(pxvid);
+
+	if (INTEL_INFO(i915)->is_mobile)
+		return max(vd - 1125, 0);
+
+	return vd;
+}
+
+static void __gen5_ips_update(struct intel_ips *ips)
+{
+	struct intel_uncore *uncore =
+		rps_to_uncore(container_of(ips, struct intel_rps, ips));
+	u64 now, delta, dt;
+	u32 count;
+
+	lockdep_assert_held(&mchdev_lock);
+
+	now = ktime_get_raw_ns();
+	dt = now - ips->last_time2;
+	do_div(dt, NSEC_PER_MSEC);
+
+	/* Don't divide by 0 */
+	if (dt <= 10)
+		return;
+
+	count = intel_uncore_read(uncore, GFXEC);
+	delta = count - ips->last_count2;
+
+	ips->last_count2 = count;
+	ips->last_time2 = now;
+
+	/* More magic constants... */
+	ips->gfx_power = div_u64(delta * 1181, dt * 10);
+}
+
+static void gen5_rps_update(struct intel_rps *rps)
+{
+	spin_lock_irq(&mchdev_lock);
+	__gen5_ips_update(&rps->ips);
+	spin_unlock_irq(&mchdev_lock);
+}
+
+static bool gen5_rps_set(struct intel_rps *rps, u8 val)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u16 rgvswctl;
+
+	lockdep_assert_held(&mchdev_lock);
+
+	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
+	if (rgvswctl & MEMCTL_CMD_STS) {
+		DRM_DEBUG("gpu busy, RCS change rejected\n");
+		return false; /* still busy with another command */
+	}
+
+	/* Invert the frequency bin into an ips delay */
+	val = rps->max_freq - val;
+	val = rps->min_freq + val;
+
+	rgvswctl =
+		(MEMCTL_CMD_CHFREQ << MEMCTL_CMD_SHIFT) |
+		(val << MEMCTL_FREQ_SHIFT) |
+		MEMCTL_SFCAVM;
+	intel_uncore_write16(uncore, MEMSWCTL, rgvswctl);
+	intel_uncore_posting_read16(uncore, MEMSWCTL);
+
+	rgvswctl |= MEMCTL_CMD_STS;
+	intel_uncore_write16(uncore, MEMSWCTL, rgvswctl);
+
+	return true;
+}
+
+static unsigned long intel_pxfreq(u32 vidfreq)
+{
+	int div = (vidfreq & 0x3f0000) >> 16;
+	int post = (vidfreq & 0x3000) >> 12;
+	int pre = (vidfreq & 0x7);
+
+	if (!pre)
+		return 0;
+
+	return div * 133333 / (pre << post);
+}
+
+static unsigned int init_emon(struct intel_uncore *uncore)
+{
+	u8 pxw[16];
+	int i;
+
+	/* Disable to program */
+	intel_uncore_write(uncore, ECR, 0);
+	intel_uncore_posting_read(uncore, ECR);
+
+	/* Program energy weights for various events */
+	intel_uncore_write(uncore, SDEW, 0x15040d00);
+	intel_uncore_write(uncore, CSIEW0, 0x007f0000);
+	intel_uncore_write(uncore, CSIEW1, 0x1e220004);
+	intel_uncore_write(uncore, CSIEW2, 0x04000004);
+
+	for (i = 0; i < 5; i++)
+		intel_uncore_write(uncore, PEW(i), 0);
+	for (i = 0; i < 3; i++)
+		intel_uncore_write(uncore, DEW(i), 0);
+
+	/* Program P-state weights to account for frequency power adjustment */
+	for (i = 0; i < 16; i++) {
+		u32 pxvidfreq = intel_uncore_read(uncore, PXVFREQ(i));
+		unsigned int freq = intel_pxfreq(pxvidfreq);
+		unsigned int vid =
+			(pxvidfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT;
+		unsigned int val;
+
+		val = vid * vid * freq / 1000 * 255;
+		val /= 127 * 127 * 900;
+
+		pxw[i] = val;
+	}
+	/* Render standby states get 0 weight */
+	pxw[14] = 0;
+	pxw[15] = 0;
+
+	for (i = 0; i < 4; i++) {
+		intel_uncore_write(uncore, PXW(i),
+				   pxw[i * 4 + 0] << 24 |
+				   pxw[i * 4 + 1] << 16 |
+				   pxw[i * 4 + 2] <<  8 |
+				   pxw[i * 4 + 3] <<  0);
+	}
+
+	/* Adjust magic regs to magic values (more experimental results) */
+	intel_uncore_write(uncore, OGW0, 0);
+	intel_uncore_write(uncore, OGW1, 0);
+	intel_uncore_write(uncore, EG0, 0x00007f00);
+	intel_uncore_write(uncore, EG1, 0x0000000e);
+	intel_uncore_write(uncore, EG2, 0x000e0000);
+	intel_uncore_write(uncore, EG3, 0x68000300);
+	intel_uncore_write(uncore, EG4, 0x42000000);
+	intel_uncore_write(uncore, EG5, 0x00140031);
+	intel_uncore_write(uncore, EG6, 0);
+	intel_uncore_write(uncore, EG7, 0);
+
+	for (i = 0; i < 8; i++)
+		intel_uncore_write(uncore, PXWL(i), 0);
+
+	/* Enable PMON + select events */
+	intel_uncore_write(uncore, ECR, 0x80000019);
+
+	return intel_uncore_read(uncore, LCFUSE02) & LCFUSE_HIV_MASK;
+}
+
+static bool gen5_rps_enable(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u8 fstart, vstart;
+	u32 rgvmodectl;
+
+	spin_lock_irq(&mchdev_lock);
+
+	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);
+
+	/* Enable temp reporting */
+	intel_uncore_write16(uncore, PMMISC,
+			     intel_uncore_read16(uncore, PMMISC) | MCPPCE_EN);
+	intel_uncore_write16(uncore, TSC1,
+			     intel_uncore_read16(uncore, TSC1) | TSE);
+
+	/* 100ms RC evaluation intervals */
+	intel_uncore_write(uncore, RCUPEI, 100000);
+	intel_uncore_write(uncore, RCDNEI, 100000);
+
+	/* Set max/min thresholds to 90ms and 80ms respectively */
+	intel_uncore_write(uncore, RCBMAXAVG, 90000);
+	intel_uncore_write(uncore, RCBMINAVG, 80000);
+
+	intel_uncore_write(uncore, MEMIHYST, 1);
+
+	/* Set up min, max, and cur for interrupt handling */
+	fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
+		MEMMODE_FSTART_SHIFT;
+
+	vstart = (intel_uncore_read(uncore, PXVFREQ(fstart)) &
+		  PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT;
+
+	intel_uncore_write(uncore,
+			   MEMINTREN,
+			   MEMINT_CX_SUPR_EN | MEMINT_EVAL_CHG_EN);
+
+	intel_uncore_write(uncore, VIDSTART, vstart);
+	intel_uncore_posting_read(uncore, VIDSTART);
+
+	rgvmodectl |= MEMMODE_SWMODE_EN;
+	intel_uncore_write(uncore, MEMMODECTL, rgvmodectl);
+
+	if (wait_for_atomic((intel_uncore_read(uncore, MEMSWCTL) &
+			     MEMCTL_CMD_STS) == 0, 10))
+		DRM_ERROR("stuck trying to change perf mode\n");
+	mdelay(1);
+
+	gen5_rps_set(rps, rps->cur_freq);
+
+	rps->ips.last_count1 = intel_uncore_read(uncore, DMIEC);
+	rps->ips.last_count1 += intel_uncore_read(uncore, DDREC);
+	rps->ips.last_count1 += intel_uncore_read(uncore, CSIEC);
+	rps->ips.last_time1 = jiffies_to_msecs(jiffies);
+
+	rps->ips.last_count2 = intel_uncore_read(uncore, GFXEC);
+	rps->ips.last_time2 = ktime_get_raw_ns();
+
+	spin_unlock_irq(&mchdev_lock);
+
+	rps->ips.corr = init_emon(uncore);
+
+	return true;
+}
+
+static void gen5_rps_disable(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u16 rgvswctl;
+
+	spin_lock_irq(&mchdev_lock);
+
+	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
+
+	/* Ack interrupts, disable EFC interrupt */
+	intel_uncore_write(uncore, MEMINTREN,
+			   intel_uncore_read(uncore, MEMINTREN) &
+			   ~MEMINT_EVAL_CHG_EN);
+	intel_uncore_write(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
+	intel_uncore_write(uncore, DEIER,
+			   intel_uncore_read(uncore, DEIER) & ~DE_PCU_EVENT);
+	intel_uncore_write(uncore, DEIIR, DE_PCU_EVENT);
+	intel_uncore_write(uncore, DEIMR,
+			   intel_uncore_read(uncore, DEIMR) | DE_PCU_EVENT);
+
+	/* Go back to the starting frequency */
+	gen5_rps_set(rps, rps->idle_freq);
+	mdelay(1);
+	rgvswctl |= MEMCTL_CMD_STS;
+	intel_uncore_write(uncore, MEMSWCTL, rgvswctl);
+	mdelay(1);
+
+	spin_unlock_irq(&mchdev_lock);
+}
+
+static u32 rps_limits(struct intel_rps *rps, u8 val)
+{
+	u32 limits;
+
+	/*
+	 * Only set the down limit when we've reached the lowest level to avoid
+	 * getting more interrupts, otherwise leave this clear. This prevents a
+	 * race in the hw when coming out of rc6: There's a tiny window where
+	 * the hw runs at the minimal clock before selecting the desired
+	 * frequency, if the down threshold expires in that window we will not
+	 * receive a down interrupt.
+	 */
+	if (INTEL_GEN(rps_to_i915(rps)) >= 9) {
+		limits = rps->max_freq_softlimit << 23;
+		if (val <= rps->min_freq_softlimit)
+			limits |= rps->min_freq_softlimit << 14;
+	} else {
+		limits = rps->max_freq_softlimit << 24;
+		if (val <= rps->min_freq_softlimit)
+			limits |= rps->min_freq_softlimit << 16;
+	}
+
+	return limits;
+}
+
+static void rps_set_power(struct intel_rps *rps, int new_power)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 threshold_up = 0, threshold_down = 0; /* in % */
+	u32 ei_up = 0, ei_down = 0;
+
+	lockdep_assert_held(&rps->power.mutex);
+
+	if (new_power == rps->power.mode)
+		return;
+
+	/* Note the units here are not exactly 1us, but 1280ns. */
+	switch (new_power) {
+	case LOW_POWER:
+		/* Upclock if more than 95% busy over 16ms */
+		ei_up = 16000;
+		threshold_up = 95;
+
+		/* Downclock if less than 85% busy over 32ms */
+		ei_down = 32000;
+		threshold_down = 85;
+		break;
+
+	case BETWEEN:
+		/* Upclock if more than 90% busy over 13ms */
+		ei_up = 13000;
+		threshold_up = 90;
+
+		/* Downclock if less than 75% busy over 32ms */
+		ei_down = 32000;
+		threshold_down = 75;
+		break;
+
+	case HIGH_POWER:
+		/* Upclock if more than 85% busy over 10ms */
+		ei_up = 10000;
+		threshold_up = 85;
+
+		/* Downclock if less than 60% busy over 32ms */
+		ei_down = 32000;
+		threshold_down = 60;
+		break;
+	}
+
+	/* When byt can survive without system hang with dynamic
+	 * sw freq adjustments, this restriction can be lifted.
+	 */
+	if (IS_VALLEYVIEW(i915))
+		goto skip_hw_write;
+
+	intel_uncore_write(uncore, GEN6_RP_UP_EI,
+			   GT_INTERVAL_FROM_US(i915, ei_up));
+	intel_uncore_write(uncore, GEN6_RP_UP_THRESHOLD,
+			   GT_INTERVAL_FROM_US(i915,
+					       ei_up * threshold_up / 100));
+
+	intel_uncore_write(uncore, GEN6_RP_DOWN_EI,
+			   GT_INTERVAL_FROM_US(i915, ei_down));
+	intel_uncore_write(uncore, GEN6_RP_DOWN_THRESHOLD,
+			   GT_INTERVAL_FROM_US(i915,
+					       ei_down * threshold_down / 100));
+
+	intel_uncore_write(uncore, GEN6_RP_CONTROL,
+			   (INTEL_GEN(i915) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
+			   GEN6_RP_MEDIA_HW_NORMAL_MODE |
+			   GEN6_RP_MEDIA_IS_GFX |
+			   GEN6_RP_ENABLE |
+			   GEN6_RP_UP_BUSY_AVG |
+			   GEN6_RP_DOWN_IDLE_AVG);
+
+skip_hw_write:
+	rps->power.mode = new_power;
+	rps->power.up_threshold = threshold_up;
+	rps->power.down_threshold = threshold_down;
+}
+
+static void gen6_rps_set_thresholds(struct intel_rps *rps, u8 val)
+{
+	int new_power;
+
+	new_power = rps->power.mode;
+	switch (rps->power.mode) {
+	case LOW_POWER:
+		if (val > rps->efficient_freq + 1 &&
+		    val > rps->cur_freq)
+			new_power = BETWEEN;
+		break;
+
+	case BETWEEN:
+		if (val <= rps->efficient_freq &&
+		    val < rps->cur_freq)
+			new_power = LOW_POWER;
+		else if (val >= rps->rp0_freq &&
+			 val > rps->cur_freq)
+			new_power = HIGH_POWER;
+		break;
+
+	case HIGH_POWER:
+		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
+		    val < rps->cur_freq)
+			new_power = BETWEEN;
+		break;
+	}
+	/* Max/min bins are special */
+	if (val <= rps->min_freq_softlimit)
+		new_power = LOW_POWER;
+	if (val >= rps->max_freq_softlimit)
+		new_power = HIGH_POWER;
+
+	mutex_lock(&rps->power.mutex);
+	if (rps->power.interactive)
+		new_power = HIGH_POWER;
+	rps_set_power(rps, new_power);
+	mutex_unlock(&rps->power.mutex);
+}
+
+void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive)
+{
+	mutex_lock(&rps->power.mutex);
+	if (interactive) {
+		if (!rps->power.interactive++ && rps->active)
+			rps_set_power(rps, HIGH_POWER);
+	} else {
+		GEM_BUG_ON(!rps->power.interactive);
+		rps->power.interactive--;
+	}
+	mutex_unlock(&rps->power.mutex);
+}
+
+static int gen6_rps_set(struct intel_rps *rps, u8 val)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 swreq;
+
+	if (INTEL_GEN(i915) >= 9)
+		swreq = GEN9_FREQUENCY(val);
+	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+		swreq = HSW_FREQUENCY(val);
+	else
+		swreq = (GEN6_FREQUENCY(val) |
+			 GEN6_OFFSET(0) |
+			 GEN6_AGGRESSIVE_TURBO);
+	intel_uncore_write(uncore, GEN6_RPNSWREQ, swreq);
+
+	return 0;
+}
+
+static int vlv_rps_set(struct intel_rps *rps, u8 val)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	int err;
+
+	vlv_punit_get(i915);
+	err = vlv_punit_write(i915, PUNIT_REG_GPU_FREQ_REQ, val);
+	vlv_punit_put(i915);
+
+	return err;
+}
+
+static int rps_set(struct intel_rps *rps, u8 val)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	int err;
+
+	if (INTEL_GEN(i915) < 6)
+		return 0;
+
+	if (val == rps->last_freq)
+		return 0;
+
+	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
+		err = vlv_rps_set(rps, val);
+	else
+		err = gen6_rps_set(rps, val);
+	if (err)
+		return err;
+
+	gen6_rps_set_thresholds(rps, val);
+	rps->last_freq = val;
+
+	return 0;
+}
+
+void intel_rps_unpark(struct intel_rps *rps)
+{
+	u8 freq;
+
+	if (!rps->enabled)
+		return;
+
+	/*
+	 * Use the user's desired frequency as a guide, but for better
+	 * performance, jump directly to RPe as our starting frequency.
+	 */
+	mutex_lock(&rps->lock);
+	rps->active = true;
+	freq = max(rps->cur_freq, rps->efficient_freq),
+	freq = clamp(freq, rps->min_freq_softlimit, rps->max_freq_softlimit);
+	intel_rps_set(rps, freq);
+	rps->last_adj = 0;
+	mutex_unlock(&rps->lock);
+
+	if (INTEL_GEN(rps_to_i915(rps)) >= 6)
+		rps_enable_interrupts(rps);
+
+	if (IS_GEN(rps_to_i915(rps), 5))
+		gen5_rps_update(rps);
+}
+
+void intel_rps_park(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	if (!rps->enabled)
+		return;
+
+	if (INTEL_GEN(i915) >= 6)
+		rps_disable_interrupts(rps);
+
+	rps->active = false;
+	if (rps->last_freq <= rps->idle_freq)
+		return;
+
+	/*
+	 * The punit delays the write of the frequency and voltage until it
+	 * determines the GPU is awake. During normal usage we don't want to
+	 * waste power changing the frequency if the GPU is sleeping (rc6).
+	 * However, the GPU and driver is now idle and we do not want to delay
+	 * switching to minimum voltage (reducing power whilst idle) as we do
+	 * not expect to be woken in the near future and so must flush the
+	 * change by waking the device.
+	 *
+	 * We choose to take the media powerwell (either would do to trick the
+	 * punit into committing the voltage change) as that takes a lot less
+	 * power than the render powerwell.
+	 */
+	intel_uncore_forcewake_get(rps_to_uncore(rps), FORCEWAKE_MEDIA);
+	rps_set(rps, rps->idle_freq);
+	intel_uncore_forcewake_put(rps_to_uncore(rps), FORCEWAKE_MEDIA);
+}
+
+void intel_rps_boost(struct i915_request *rq)
+{
+	struct intel_rps *rps = &rq->engine->gt->rps;
+	unsigned long flags;
+
+	if (i915_request_signaled(rq) || !rps->active)
+		return;
+
+	/* Serializes with i915_request_retire() */
+	spin_lock_irqsave(&rq->lock, flags);
+	if (!i915_request_has_waitboost(rq) &&
+	    !dma_fence_is_signaled_locked(&rq->fence)) {
+		rq->flags |= I915_REQUEST_WAITBOOST;
+
+		if (!atomic_fetch_inc(&rps->num_waiters) &&
+		    READ_ONCE(rps->cur_freq) < rps->boost_freq)
+			schedule_work(&rps->work);
+
+		atomic_inc(&rps->boosts);
+	}
+	spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+int intel_rps_set(struct intel_rps *rps, u8 val)
+{
+	int err = 0;
+
+	lockdep_assert_held(&rps->lock);
+	GEM_BUG_ON(val > rps->max_freq);
+	GEM_BUG_ON(val < rps->min_freq);
+
+	if (rps->active) {
+		err = rps_set(rps, val);
+
+		/*
+		 * Make sure we continue to get interrupts
+		 * until we hit the minimum or maximum frequencies.
+		 */
+		if (INTEL_GEN(rps_to_i915(rps)) >= 6) {
+			struct intel_uncore *uncore = rps_to_uncore(rps);
+
+			intel_uncore_write(uncore, GEN6_RP_INTERRUPT_LIMITS,
+					   rps_limits(rps, val));
+
+			intel_uncore_write(uncore, GEN6_PMINTRMSK,
+					   rps_pm_mask(rps, val));
+		}
+	}
+
+	if (err == 0)
+		rps->cur_freq = val;
+
+	return err;
+}
+
+static void gen6_rps_init(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	/* All of these values are in units of 50MHz */
+
+	/* static values from HW: RP0 > RP1 > RPn (min_freq) */
+	if (IS_GEN9_LP(i915)) {
+		u32 rp_state_cap = intel_uncore_read(uncore, BXT_RP_STATE_CAP);
+
+		rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
+		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
+		rps->min_freq = (rp_state_cap >>  0) & 0xff;
+	} else {
+		u32 rp_state_cap = intel_uncore_read(uncore, GEN6_RP_STATE_CAP);
+
+		rps->rp0_freq = (rp_state_cap >>  0) & 0xff;
+		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
+		rps->min_freq = (rp_state_cap >> 16) & 0xff;
+	}
+
+	/* hw_max = RP0 until we check for overclocking */
+	rps->max_freq = rps->rp0_freq;
+
+	rps->efficient_freq = rps->rp1_freq;
+	if (IS_HASWELL(i915) || IS_BROADWELL(i915) ||
+	    IS_GEN9_BC(i915) || INTEL_GEN(i915) >= 10) {
+		u32 ddcc_status = 0;
+
+		if (sandybridge_pcode_read(i915,
+					   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
+					   &ddcc_status, NULL) == 0)
+			rps->efficient_freq =
+				clamp_t(u8,
+					(ddcc_status >> 8) & 0xff,
+					rps->min_freq,
+					rps->max_freq);
+	}
+
+	if (IS_GEN9_BC(i915) || INTEL_GEN(i915) >= 10) {
+		/* Store the frequency values in 16.66 MHZ units, which is
+		 * the natural hardware unit for SKL
+		 */
+		rps->rp0_freq *= GEN9_FREQ_SCALER;
+		rps->rp1_freq *= GEN9_FREQ_SCALER;
+		rps->min_freq *= GEN9_FREQ_SCALER;
+		rps->max_freq *= GEN9_FREQ_SCALER;
+		rps->efficient_freq *= GEN9_FREQ_SCALER;
+	}
+}
+
+static bool rps_reset(struct intel_rps *rps)
+{
+	/* force a reset */
+	rps->power.mode = -1;
+	rps->last_freq = -1;
+
+	if (rps_set(rps, rps->min_freq)) {
+		DRM_ERROR("Failed to reset RPS to initial values\n");
+		return false;
+	}
+
+	rps->cur_freq = rps->min_freq;
+	return true;
+}
+
+/* See the Gen9_GT_PM_Programming_Guide doc for the below */
+static bool gen9_rps_enable(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	/* Program defaults and thresholds for RPS */
+	if (IS_GEN(i915, 9))
+		intel_uncore_write_fw(uncore, GEN6_RC_VIDEO_FREQ,
+				      GEN9_FREQUENCY(rps->rp1_freq));
+
+	/* 1 second timeout */
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT,
+			      GT_INTERVAL_FROM_US(i915, 1000000));
+
+	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 0xa);
+
+	return rps_reset(rps);
+}
+
+static bool gen8_rps_enable(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	intel_uncore_write_fw(uncore, GEN6_RC_VIDEO_FREQ,
+			      HSW_FREQUENCY(rps->rp1_freq));
+
+	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT,
+			      100000000 / 128); /* 1 second timeout */
+
+	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	return rps_reset(rps);
+}
+
+static bool gen6_rps_enable(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	/* Power down if completely idle for over 50ms */
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 50000);
+	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	return rps_reset(rps);
+}
+
+static int chv_rps_max_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	val = vlv_punit_read(i915, FB_GFX_FMAX_AT_VMAX_FUSE);
+
+	switch (RUNTIME_INFO(i915)->sseu.eu_total) {
+	case 8:
+		/* (2 * 4) config */
+		val >>= FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT;
+		break;
+	case 12:
+		/* (2 * 6) config */
+		val >>= FB_GFX_FMAX_AT_VMAX_2SS6EU_FUSE_SHIFT;
+		break;
+	case 16:
+		/* (2 * 8) config */
+	default:
+		/* Setting (2 * 8) Min RP0 for any other combination */
+		val >>= FB_GFX_FMAX_AT_VMAX_2SS8EU_FUSE_SHIFT;
+		break;
+	}
+
+	return val & FB_GFX_FREQ_FUSE_MASK;
+}
+
+static int chv_rps_rpe_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	val = vlv_punit_read(i915, PUNIT_GPU_DUTYCYCLE_REG);
+	val >>= PUNIT_GPU_DUTYCYCLE_RPE_FREQ_SHIFT;
+
+	return val & PUNIT_GPU_DUTYCYCLE_RPE_FREQ_MASK;
+}
+
+static int chv_rps_guar_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	val = vlv_punit_read(i915, FB_GFX_FMAX_AT_VMAX_FUSE);
+
+	return val & FB_GFX_FREQ_FUSE_MASK;
+}
+
+static u32 chv_rps_min_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	val = vlv_punit_read(i915, FB_GFX_FMIN_AT_VMIN_FUSE);
+	val >>= FB_GFX_FMIN_AT_VMIN_FUSE_SHIFT;
+
+	return val & FB_GFX_FREQ_FUSE_MASK;
+}
+
+static bool chv_rps_enable(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	/* 1: Program defaults and thresholds for RPS*/
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 1000000);
+	intel_uncore_write_fw(uncore, GEN6_RP_UP_THRESHOLD, 59400);
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_THRESHOLD, 245000);
+	intel_uncore_write_fw(uncore, GEN6_RP_UP_EI, 66000);
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_EI, 350000);
+
+	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	/* 2: Enable RPS */
+	intel_uncore_write_fw(uncore, GEN6_RP_CONTROL,
+			      GEN6_RP_MEDIA_HW_NORMAL_MODE |
+			      GEN6_RP_MEDIA_IS_GFX |
+			      GEN6_RP_ENABLE |
+			      GEN6_RP_UP_BUSY_AVG |
+			      GEN6_RP_DOWN_IDLE_AVG);
+
+	/* Setting Fixed Bias */
+	vlv_punit_get(i915);
+
+	val = VLV_OVERRIDE_EN | VLV_SOC_TDP_EN | CHV_BIAS_CPU_50_SOC_50;
+	vlv_punit_write(i915, VLV_TURBO_SOC_OVERRIDE, val);
+
+	val = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+
+	vlv_punit_put(i915);
+
+	/* RPS code assumes GPLL is used */
+	WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
+
+	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
+	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+
+	return rps_reset(rps);
+}
+
+static int vlv_rps_guar_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val, rp1;
+
+	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FREQ_FUSE);
+
+	rp1 = val & FB_GFX_FGUARANTEED_FREQ_FUSE_MASK;
+	rp1 >>= FB_GFX_FGUARANTEED_FREQ_FUSE_SHIFT;
+
+	return rp1;
+}
+
+static int vlv_rps_max_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val, rp0;
+
+	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FREQ_FUSE);
+
+	rp0 = (val & FB_GFX_MAX_FREQ_FUSE_MASK) >> FB_GFX_MAX_FREQ_FUSE_SHIFT;
+	/* Clamp to max */
+	rp0 = min_t(u32, rp0, 0xea);
+
+	return rp0;
+}
+
+static int vlv_rps_rpe_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val, rpe;
+
+	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FMAX_FUSE_LO);
+	rpe = (val & FB_FMAX_VMIN_FREQ_LO_MASK) >> FB_FMAX_VMIN_FREQ_LO_SHIFT;
+	val = vlv_nc_read(i915, IOSF_NC_FB_GFX_FMAX_FUSE_HI);
+	rpe |= (val & FB_FMAX_VMIN_FREQ_HI_MASK) << 5;
+
+	return rpe;
+}
+
+static int vlv_rps_min_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	val = vlv_punit_read(i915, PUNIT_REG_GPU_LFM) & 0xff;
+	/*
+	 * According to the BYT Punit GPU turbo HAS 1.1.6.3 the minimum value
+	 * for the minimum frequency in GPLL mode is 0xc1. Contrary to this on
+	 * a BYT-M B0 the above register contains 0xbf. Moreover when setting
+	 * a frequency Punit will not allow values below 0xc0. Clamp it 0xc0
+	 * to make sure it matches what Punit accepts.
+	 */
+	return max_t(u32, val, 0xc0);
+}
+
+static bool vlv_rps_enable(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_TIMEOUT, 1000000);
+	intel_uncore_write_fw(uncore, GEN6_RP_UP_THRESHOLD, 59400);
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_THRESHOLD, 245000);
+	intel_uncore_write_fw(uncore, GEN6_RP_UP_EI, 66000);
+	intel_uncore_write_fw(uncore, GEN6_RP_DOWN_EI, 350000);
+
+	intel_uncore_write_fw(uncore, GEN6_RP_IDLE_HYSTERSIS, 10);
+
+	intel_uncore_write_fw(uncore, GEN6_RP_CONTROL,
+			      GEN6_RP_MEDIA_TURBO |
+			      GEN6_RP_MEDIA_HW_NORMAL_MODE |
+			      GEN6_RP_MEDIA_IS_GFX |
+			      GEN6_RP_ENABLE |
+			      GEN6_RP_UP_BUSY_AVG |
+			      GEN6_RP_DOWN_IDLE_CONT);
+
+	vlv_punit_get(i915);
+
+	/* Setting Fixed Bias */
+	val = VLV_OVERRIDE_EN | VLV_SOC_TDP_EN | VLV_BIAS_CPU_125_SOC_875;
+	vlv_punit_write(i915, VLV_TURBO_SOC_OVERRIDE, val);
+
+	val = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+
+	vlv_punit_put(i915);
+
+	/* RPS code assumes GPLL is used */
+	WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
+
+	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
+	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
+
+	return rps_reset(rps);
+}
+
+static unsigned long __ips_gfx_val(struct intel_ips *ips)
+{
+	struct intel_rps *rps = container_of(ips, typeof(*rps), ips);
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	unsigned long t, corr, state1, corr2, state2;
+	u32 pxvid, ext_v;
+
+	lockdep_assert_held(&mchdev_lock);
+
+	pxvid = intel_uncore_read(uncore, PXVFREQ(rps->cur_freq));
+	pxvid = (pxvid >> 24) & 0x7f;
+	ext_v = pvid_to_extvid(rps_to_i915(rps), pxvid);
+
+	state1 = ext_v;
+
+	/* Revel in the empirically derived constants */
+
+	/* Correction factor in 1/100000 units */
+	t = ips_mch_val(uncore);
+	if (t > 80)
+		corr = t * 2349 + 135940;
+	else if (t >= 50)
+		corr = t * 964 + 29317;
+	else /* < 50 */
+		corr = t * 301 + 1004;
+
+	corr = corr * 150142 * state1 / 10000 - 78642;
+	corr /= 100000;
+	corr2 = corr * ips->corr;
+
+	state2 = corr2 * state1 / 10000;
+	state2 /= 100; /* convert to mW */
+
+	__gen5_ips_update(ips);
+
+	return ips->gfx_power + state2;
+}
+
+void intel_rps_enable(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+
+	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
+	if (IS_CHERRYVIEW(i915))
+		rps->enabled = chv_rps_enable(rps);
+	else if (IS_VALLEYVIEW(i915))
+		rps->enabled = vlv_rps_enable(rps);
+	else if (INTEL_GEN(i915) >= 9)
+		rps->enabled = gen9_rps_enable(rps);
+	else if (INTEL_GEN(i915) >= 8)
+		rps->enabled = gen8_rps_enable(rps);
+	else if (INTEL_GEN(i915) >= 6)
+		rps->enabled = gen6_rps_enable(rps);
+	else if (IS_IRONLAKE_M(i915))
+		rps->enabled = gen5_rps_enable(rps);
+	intel_uncore_forcewake_put(uncore, FORCEWAKE_ALL);
+	if (!rps->enabled)
+		return;
+
+	WARN_ON(rps->max_freq < rps->min_freq);
+	WARN_ON(rps->idle_freq > rps->max_freq);
+
+	WARN_ON(rps->efficient_freq < rps->min_freq);
+	WARN_ON(rps->efficient_freq > rps->max_freq);
+}
+
+static void gen6_rps_disable(struct intel_rps *rps)
+{
+	intel_uncore_write(rps_to_uncore(rps), GEN6_RP_CONTROL, 0);
+}
+
+void intel_rps_disable(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	rps->enabled = false;
+
+	if (INTEL_GEN(i915) >= 6)
+		gen6_rps_disable(rps);
+	else if (IS_IRONLAKE_M(i915))
+		gen5_rps_disable(rps);
+}
+
+static int byt_gpu_freq(struct intel_rps *rps, int val)
+{
+	/*
+	 * N = val - 0xb7
+	 * Slow = Fast = GPLL ref * N
+	 */
+	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * (val - 0xb7), 1000);
+}
+
+static int byt_freq_opcode(struct intel_rps *rps, int val)
+{
+	return DIV_ROUND_CLOSEST(1000 * val, rps->gpll_ref_freq) + 0xb7;
+}
+
+static int chv_gpu_freq(struct intel_rps *rps, int val)
+{
+	/*
+	 * N = val / 2
+	 * CU (slow) = CU2x (fast) / 2 = GPLL ref * N / 2
+	 */
+	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * val, 2 * 2 * 1000);
+}
+
+static int chv_freq_opcode(struct intel_rps *rps, int val)
+{
+	/* CHV needs even values */
+	return DIV_ROUND_CLOSEST(2 * 1000 * val, rps->gpll_ref_freq) * 2;
+}
+
+int intel_gpu_freq(struct intel_rps *rps, int val)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	if (INTEL_GEN(i915) >= 9)
+		return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
+					 GEN9_FREQ_SCALER);
+	else if (IS_CHERRYVIEW(i915))
+		return chv_gpu_freq(rps, val);
+	else if (IS_VALLEYVIEW(i915))
+		return byt_gpu_freq(rps, val);
+	else
+		return val * GT_FREQUENCY_MULTIPLIER;
+}
+
+int intel_freq_opcode(struct intel_rps *rps, int val)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	if (INTEL_GEN(i915) >= 9)
+		return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
+					 GT_FREQUENCY_MULTIPLIER);
+	else if (IS_CHERRYVIEW(i915))
+		return chv_freq_opcode(rps, val);
+	else if (IS_VALLEYVIEW(i915))
+		return byt_freq_opcode(rps, val);
+	else
+		return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
+}
+
+static void vlv_init_gpll_ref_freq(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	rps->gpll_ref_freq =
+		vlv_get_cck_clock(i915, "GPLL ref",
+				  CCK_GPLL_CLOCK_CONTROL,
+				  i915->czclk_freq);
+
+	DRM_DEBUG_DRIVER("GPLL reference freq: %d kHz\n", rps->gpll_ref_freq);
+}
+
+static void vlv_rps_init(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	vlv_iosf_sb_get(i915,
+			BIT(VLV_IOSF_SB_PUNIT) |
+			BIT(VLV_IOSF_SB_NC) |
+			BIT(VLV_IOSF_SB_CCK));
+
+	vlv_init_gpll_ref_freq(rps);
+
+	val = vlv_punit_read(i915, PUNIT_REG_GPU_FREQ_STS);
+	switch ((val >> 6) & 3) {
+	case 0:
+	case 1:
+		i915->mem_freq = 800;
+		break;
+	case 2:
+		i915->mem_freq = 1066;
+		break;
+	case 3:
+		i915->mem_freq = 1333;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", i915->mem_freq);
+
+	rps->max_freq = vlv_rps_max_freq(rps);
+	rps->rp0_freq = rps->max_freq;
+	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->max_freq),
+			 rps->max_freq);
+
+	rps->efficient_freq = vlv_rps_rpe_freq(rps);
+	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->efficient_freq),
+			 rps->efficient_freq);
+
+	rps->rp1_freq = vlv_rps_guar_freq(rps);
+	DRM_DEBUG_DRIVER("RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->rp1_freq),
+			 rps->rp1_freq);
+
+	rps->min_freq = vlv_rps_min_freq(rps);
+	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->min_freq),
+			 rps->min_freq);
+
+	vlv_iosf_sb_put(i915,
+			BIT(VLV_IOSF_SB_PUNIT) |
+			BIT(VLV_IOSF_SB_NC) |
+			BIT(VLV_IOSF_SB_CCK));
+}
+
+static void chv_rps_init(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 val;
+
+	vlv_iosf_sb_get(i915,
+			BIT(VLV_IOSF_SB_PUNIT) |
+			BIT(VLV_IOSF_SB_NC) |
+			BIT(VLV_IOSF_SB_CCK));
+
+	vlv_init_gpll_ref_freq(rps);
+
+	val = vlv_cck_read(i915, CCK_FUSE_REG);
+
+	switch ((val >> 2) & 0x7) {
+	case 3:
+		i915->mem_freq = 2000;
+		break;
+	default:
+		i915->mem_freq = 1600;
+		break;
+	}
+	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", i915->mem_freq);
+
+	rps->max_freq = chv_rps_max_freq(rps);
+	rps->rp0_freq = rps->max_freq;
+	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->max_freq),
+			 rps->max_freq);
+
+	rps->efficient_freq = chv_rps_rpe_freq(rps);
+	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->efficient_freq),
+			 rps->efficient_freq);
+
+	rps->rp1_freq = chv_rps_guar_freq(rps);
+	DRM_DEBUG_DRIVER("RP1(Guar) GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->rp1_freq),
+			 rps->rp1_freq);
+
+	rps->min_freq = chv_rps_min_freq(rps);
+	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
+			 intel_gpu_freq(rps, rps->min_freq),
+			 rps->min_freq);
+
+	vlv_iosf_sb_put(i915,
+			BIT(VLV_IOSF_SB_PUNIT) |
+			BIT(VLV_IOSF_SB_NC) |
+			BIT(VLV_IOSF_SB_CCK));
+
+	WARN_ONCE((rps->max_freq | rps->efficient_freq | rps->rp1_freq |
+		   rps->min_freq) & 1,
+		  "Odd GPU freq values\n");
+}
+
+static void vlv_c0_read(struct intel_uncore *uncore, struct intel_rps_ei *ei)
+{
+	ei->ktime = ktime_get_raw();
+	ei->render_c0 = intel_uncore_read(uncore, VLV_RENDER_C0_COUNT);
+	ei->media_c0 = intel_uncore_read(uncore, VLV_MEDIA_C0_COUNT);
+}
+
+static u32 vlv_wa_c0_ei(struct intel_rps *rps, u32 pm_iir)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	const struct intel_rps_ei *prev = &rps->ei;
+	struct intel_rps_ei now;
+	u32 events = 0;
+
+	if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0)
+		return 0;
+
+	vlv_c0_read(uncore, &now);
+
+	if (prev->ktime) {
+		u64 time, c0;
+		u32 render, media;
+
+		time = ktime_us_delta(now.ktime, prev->ktime);
+
+		time *= rps_to_i915(rps)->czclk_freq;
+
+		/* Workload can be split between render + media,
+		 * e.g. SwapBuffers being blitted in X after being rendered in
+		 * mesa. To account for this we need to combine both engines
+		 * into our activity counter.
+		 */
+		render = now.render_c0 - prev->render_c0;
+		media = now.media_c0 - prev->media_c0;
+		c0 = max(render, media);
+		c0 *= 1000 * 100 << 8; /* to usecs and scale to threshold% */
+
+		if (c0 > time * rps->power.up_threshold)
+			events = GEN6_PM_RP_UP_THRESHOLD;
+		else if (c0 < time * rps->power.down_threshold)
+			events = GEN6_PM_RP_DOWN_THRESHOLD;
+	}
+
+	rps->ei = now;
+	return events;
+}
+
+static void rps_work(struct work_struct *work)
+{
+	struct intel_rps *rps = container_of(work, typeof(*rps), work);
+	struct intel_gt *gt = rps_to_gt(rps);
+	bool client_boost = false;
+	int new_freq, adj, min, max;
+	u32 pm_iir = 0;
+
+	spin_lock_irq(&gt->irq_lock);
+	pm_iir = fetch_and_zero(&rps->pm_iir);
+	client_boost = atomic_read(&rps->num_waiters);
+	spin_unlock_irq(&gt->irq_lock);
+
+	/* Make sure we didn't queue anything we're not going to process. */
+	if ((pm_iir & rps->pm_events) == 0 && !client_boost)
+		goto out;
+
+	mutex_lock(&rps->lock);
+
+	pm_iir |= vlv_wa_c0_ei(rps, pm_iir);
+
+	adj = rps->last_adj;
+	new_freq = rps->cur_freq;
+	min = rps->min_freq_softlimit;
+	max = rps->max_freq_softlimit;
+	if (client_boost)
+		max = rps->max_freq;
+	if (client_boost && new_freq < rps->boost_freq) {
+		new_freq = rps->boost_freq;
+		adj = 0;
+	} else if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
+		if (adj > 0)
+			adj *= 2;
+		else /* CHV needs even encode values */
+			adj = IS_CHERRYVIEW(gt->i915) ? 2 : 1;
+
+		if (new_freq >= rps->max_freq_softlimit)
+			adj = 0;
+	} else if (client_boost) {
+		adj = 0;
+	} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
+		if (rps->cur_freq > rps->efficient_freq)
+			new_freq = rps->efficient_freq;
+		else if (rps->cur_freq > rps->min_freq_softlimit)
+			new_freq = rps->min_freq_softlimit;
+		adj = 0;
+	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
+		if (adj < 0)
+			adj *= 2;
+		else /* CHV needs even encode values */
+			adj = IS_CHERRYVIEW(gt->i915) ? -2 : -1;
+
+		if (new_freq <= rps->min_freq_softlimit)
+			adj = 0;
+	} else { /* unknown event */
+		adj = 0;
+	}
+
+	rps->last_adj = adj;
+
+	/*
+	 * Limit deboosting and boosting to keep ourselves at the extremes
+	 * when in the respective power modes (i.e. slowly decrease frequencies
+	 * while in the HIGH_POWER zone and slowly increase frequencies while
+	 * in the LOW_POWER zone). On idle, we will hit the timeout and drop
+	 * to the next level quickly, and conversely if busy we expect to
+	 * hit a waitboost and rapidly switch into max power.
+	 */
+	if ((adj < 0 && rps->power.mode == HIGH_POWER) ||
+	    (adj > 0 && rps->power.mode == LOW_POWER))
+		rps->last_adj = 0;
+
+	/* sysfs frequency interfaces may have snuck in while servicing the
+	 * interrupt
+	 */
+	new_freq += adj;
+	new_freq = clamp_t(int, new_freq, min, max);
+
+	if (intel_rps_set(rps, new_freq)) {
+		DRM_DEBUG_DRIVER("Failed to set new GPU frequency\n");
+		rps->last_adj = 0;
+	}
+
+	mutex_unlock(&rps->lock);
+
+out:
+	spin_lock_irq(&gt->irq_lock);
+	gen6_gt_pm_unmask_irq(gt, rps->pm_events);
+	spin_unlock_irq(&gt->irq_lock);
+}
+
+void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+	const u32 events = rps->pm_events & pm_iir;
+
+	lockdep_assert_held(&gt->irq_lock);
+
+	if (unlikely(!events))
+		return;
+
+	gen6_gt_pm_mask_irq(gt, events);
+
+	rps->pm_iir |= events;
+	schedule_work(&rps->work);
+}
+
+void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	if (pm_iir & rps->pm_events) {
+		spin_lock(&gt->irq_lock);
+		gen6_gt_pm_mask_irq(gt, pm_iir & rps->pm_events);
+		rps->pm_iir |= pm_iir & rps->pm_events;
+		schedule_work(&rps->work);
+		spin_unlock(&gt->irq_lock);
+	}
+
+	if (INTEL_GEN(gt->i915) >= 8)
+		return;
+
+	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
+		intel_engine_breadcrumbs_irq(gt->engine[VECS0]);
+
+	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
+		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
+}
+
+void gen5_rps_irq_handler(struct intel_rps *rps)
+{
+	struct intel_uncore *uncore = rps_to_uncore(rps);
+	u32 busy_up, busy_down, max_avg, min_avg;
+	u8 new_freq;
+
+	spin_lock(&mchdev_lock);
+
+	intel_uncore_write16(uncore,
+			     MEMINTRSTS,
+			     intel_uncore_read(uncore, MEMINTRSTS));
+
+	intel_uncore_write16(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
+	busy_up = intel_uncore_read(uncore, RCPREVBSYTUPAVG);
+	busy_down = intel_uncore_read(uncore, RCPREVBSYTDNAVG);
+	max_avg = intel_uncore_read(uncore, RCBMAXAVG);
+	min_avg = intel_uncore_read(uncore, RCBMINAVG);
+
+	/* Handle RCS change request from hw */
+	new_freq = rps->cur_freq;
+	if (busy_up > max_avg)
+		new_freq++;
+	else if (busy_down < min_avg)
+		new_freq--;
+	new_freq = clamp(new_freq,
+			 rps->min_freq_softlimit,
+			 rps->max_freq_softlimit);
+
+	if (new_freq != rps->cur_freq && gen5_rps_set(rps, new_freq))
+		rps->cur_freq = new_freq;
+
+	spin_unlock(&mchdev_lock);
+}
+
+void intel_rps_init_early(struct intel_rps *rps)
+{
+	mutex_init(&rps->lock);
+	mutex_init(&rps->power.mutex);
+
+	INIT_WORK(&rps->work, rps_work);
+
+	atomic_set(&rps->num_waiters, 0);
+}
+
+void intel_rps_init(struct intel_rps *rps)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+
+	if (IS_CHERRYVIEW(i915))
+		chv_rps_init(rps);
+	else if (IS_VALLEYVIEW(i915))
+		vlv_rps_init(rps);
+	else if (INTEL_GEN(i915) >= 6)
+		gen6_rps_init(rps);
+	else if (IS_IRONLAKE_M(i915))
+		gen5_rps_init(rps);
+
+	/* Derive initial user preferences/limits from the hardware limits */
+	rps->max_freq_softlimit = rps->max_freq;
+	rps->min_freq_softlimit = rps->min_freq;
+
+	/* After setting max-softlimit, find the overclock max freq */
+	if (IS_GEN(i915, 6) || IS_IVYBRIDGE(i915) || IS_HASWELL(i915)) {
+		u32 params = 0;
+
+		sandybridge_pcode_read(i915, GEN6_READ_OC_PARAMS,
+				       &params, NULL);
+		if (params & BIT(31)) { /* OC supported */
+			DRM_DEBUG_DRIVER("Overclocking supported, max: %dMHz, overclock: %dMHz\n",
+					 (rps->max_freq & 0xff) * 50,
+					 (params & 0xff) * 50);
+			rps->max_freq = params & 0xff;
+		}
+	}
+
+	/* Finally allow us to boost to max by default */
+	rps->boost_freq = rps->max_freq;
+	rps->idle_freq = rps->min_freq;
+	rps->cur_freq = rps->idle_freq;
+
+	rps->pm_intrmsk_mbz = 0;
+
+	/*
+	 * SNB,IVB,HSW can while VLV,CHV may hard hang on looping batchbuffer
+	 * if GEN6_PM_UP_EI_EXPIRED is masked.
+	 *
+	 * TODO: verify if this can be reproduced on VLV,CHV.
+	 */
+	if (INTEL_GEN(i915) <= 7)
+		rps->pm_intrmsk_mbz |= GEN6_PM_RP_UP_EI_EXPIRED;
+
+	if (INTEL_GEN(i915) >= 8)
+		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
+}
+
+u32 intel_get_cagf(struct intel_rps *rps, u32 rpstat)
+{
+	struct drm_i915_private *i915 = rps_to_i915(rps);
+	u32 cagf;
+
+	if (INTEL_GEN(i915) >= 9)
+		cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
+	else if (IS_HASWELL(i915) || IS_BROADWELL(i915))
+		cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
+	else
+		cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
+
+	return  cagf;
+}
+
+/* External interface for intel_ips.ko */
+
+static struct drm_i915_private __rcu *ips_mchdev;
+
+/**
+ * Tells the intel_ips driver that the i915 driver is now loaded, if
+ * IPS got loaded first.
+ *
+ * This awkward dance is so that neither module has to depend on the
+ * other in order for IPS to do the appropriate communication of
+ * GPU turbo limits to i915.
+ */
+static void
+ips_ping_for_i915_load(void)
+{
+	void (*link)(void);
+
+	link = symbol_get(ips_link_to_i915_driver);
+	if (link) {
+		link();
+		symbol_put(ips_link_to_i915_driver);
+	}
+}
+
+void intel_rps_driver_register(struct intel_rps *rps)
+{
+	struct intel_gt *gt = rps_to_gt(rps);
+
+	/*
+	 * We only register the i915 ips part with intel-ips once everything is
+	 * set up, to avoid intel-ips sneaking in and reading bogus values.
+	 */
+	if (IS_GEN(gt->i915, 5)) {
+		rcu_assign_pointer(ips_mchdev, gt->i915);
+		ips_ping_for_i915_load();
+	}
+}
+
+void intel_rps_driver_unregister(struct intel_rps *rps)
+{
+	rcu_assign_pointer(ips_mchdev, NULL);
+}
+
+static struct drm_i915_private *mchdev_get(void)
+{
+	struct drm_i915_private *i915;
+
+	rcu_read_lock();
+	i915 = rcu_dereference(ips_mchdev);
+	if (!kref_get_unless_zero(&i915->drm.ref))
+		i915 = NULL;
+	rcu_read_unlock();
+
+	return i915;
+}
+
+/**
+ * i915_read_mch_val - return value for IPS use
+ *
+ * Calculate and return a value for the IPS driver to use when deciding whether
+ * we have thermal and power headroom to increase CPU or GPU power budget.
+ */
+unsigned long i915_read_mch_val(void)
+{
+	struct drm_i915_private *i915;
+	unsigned long chipset_val = 0;
+	unsigned long graphics_val = 0;
+	intel_wakeref_t wakeref;
+
+	i915 = mchdev_get();
+	if (!i915)
+		return 0;
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
+		struct intel_ips *ips = &i915->gt.rps.ips;
+
+		spin_lock_irq(&mchdev_lock);
+		chipset_val = __ips_chipset_val(ips);
+		graphics_val = __ips_gfx_val(ips);
+		spin_unlock_irq(&mchdev_lock);
+	}
+
+	drm_dev_put(&i915->drm);
+	return chipset_val + graphics_val;
+}
+EXPORT_SYMBOL_GPL(i915_read_mch_val);
+
+/**
+ * i915_gpu_raise - raise GPU frequency limit
+ *
+ * Raise the limit; IPS indicates we have thermal headroom.
+ */
+bool i915_gpu_raise(void)
+{
+	struct drm_i915_private *i915;
+	struct intel_rps *rps;
+
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
+
+	rps = &i915->gt.rps;
+
+	spin_lock_irq(&mchdev_lock);
+	if (rps->max_freq_softlimit < rps->max_freq)
+		rps->max_freq_softlimit++;
+	spin_unlock_irq(&mchdev_lock);
+
+	drm_dev_put(&i915->drm);
+	return true;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_raise);
+
+/**
+ * i915_gpu_lower - lower GPU frequency limit
+ *
+ * IPS indicates we're close to a thermal limit, so throttle back the GPU
+ * frequency maximum.
+ */
+bool i915_gpu_lower(void)
+{
+	struct drm_i915_private *i915;
+	struct intel_rps *rps;
+
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
+
+	rps = &i915->gt.rps;
+
+	spin_lock_irq(&mchdev_lock);
+	if (rps->max_freq_softlimit > rps->min_freq)
+		rps->max_freq_softlimit--;
+	spin_unlock_irq(&mchdev_lock);
+
+	drm_dev_put(&i915->drm);
+	return true;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_lower);
+
+/**
+ * i915_gpu_busy - indicate GPU business to IPS
+ *
+ * Tell the IPS driver whether or not the GPU is busy.
+ */
+bool i915_gpu_busy(void)
+{
+	struct drm_i915_private *i915;
+	bool ret;
+
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
+
+	ret = i915->gt.awake;
+
+	drm_dev_put(&i915->drm);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_busy);
+
+/**
+ * i915_gpu_turbo_disable - disable graphics turbo
+ *
+ * Disable graphics turbo by resetting the max frequency and setting the
+ * current frequency to the default.
+ */
+bool i915_gpu_turbo_disable(void)
+{
+	struct drm_i915_private *i915;
+	struct intel_rps *rps;
+	bool ret;
+
+	i915 = mchdev_get();
+	if (!i915)
+		return false;
+
+	rps = &i915->gt.rps;
+
+	spin_lock_irq(&mchdev_lock);
+	rps->max_freq_softlimit = rps->min_freq;
+	ret = gen5_rps_set(&i915->gt.rps, rps->min_freq);
+	spin_unlock_irq(&mchdev_lock);
+
+	drm_dev_put(&i915->drm);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
diff --git a/drivers/gpu/drm/i915/gt/intel_rps.h b/drivers/gpu/drm/i915/gt/intel_rps.h
new file mode 100644
index 000000000000..9518c66c9792
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_rps.h
@@ -0,0 +1,38 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_RPS_H
+#define INTEL_RPS_H
+
+#include "intel_rps_types.h"
+
+struct i915_request;
+
+void intel_rps_init_early(struct intel_rps *rps);
+void intel_rps_init(struct intel_rps *rps);
+
+void intel_rps_driver_register(struct intel_rps *rps);
+void intel_rps_driver_unregister(struct intel_rps *rps);
+
+void intel_rps_enable(struct intel_rps *rps);
+void intel_rps_disable(struct intel_rps *rps);
+
+void intel_rps_park(struct intel_rps *rps);
+void intel_rps_unpark(struct intel_rps *rps);
+void intel_rps_boost(struct i915_request *rq);
+
+int intel_rps_set(struct intel_rps *rps, u8 val);
+void intel_rps_mark_interactive(struct intel_rps *rps, bool interactive);
+
+int intel_gpu_freq(struct intel_rps *rps, int val);
+int intel_freq_opcode(struct intel_rps *rps, int val);
+u32 intel_get_cagf(struct intel_rps *rps, u32 rpstat1);
+
+void gen5_rps_irq_handler(struct intel_rps *rps);
+void gen6_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
+void gen11_rps_irq_handler(struct intel_rps *rps, u32 pm_iir);
+
+#endif /* INTEL_RPS_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_rps_types.h b/drivers/gpu/drm/i915/gt/intel_rps_types.h
new file mode 100644
index 000000000000..c2e279154bd5
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_rps_types.h
@@ -0,0 +1,93 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef INTEL_RPS_TYPES_H
+#define INTEL_RPS_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/ktime.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+struct intel_ips {
+	u64 last_count1;
+	unsigned long last_time1;
+	unsigned long chipset_power;
+	u64 last_count2;
+	u64 last_time2;
+	unsigned long gfx_power;
+	u8 corr;
+
+	int c, m;
+};
+
+struct intel_rps_ei {
+	ktime_t ktime;
+	u32 render_c0;
+	u32 media_c0;
+};
+
+struct intel_rps {
+	struct mutex lock; /* protects enabling and the worker */
+
+	/*
+	 * work, interrupts_enabled and pm_iir are protected by
+	 * dev_priv->irq_lock
+	 */
+	struct work_struct work;
+	bool enabled;
+	bool active;
+	u32 pm_iir;
+
+	/* PM interrupt bits that should never be masked */
+	u32 pm_intrmsk_mbz;
+	u32 pm_events;
+
+	/* Frequencies are stored in potentially platform dependent multiples.
+	 * In other words, *_freq needs to be multiplied by X to be interesting.
+	 * Soft limits are those which are used for the dynamic reclocking done
+	 * by the driver (raise frequencies under heavy loads, and lower for
+	 * lighter loads). Hard limits are those imposed by the hardware.
+	 *
+	 * A distinction is made for overclocking, which is never enabled by
+	 * default, and is considered to be above the hard limit if it's
+	 * possible at all.
+	 */
+	u8 cur_freq;		/* Current frequency (cached, may not == HW) */
+	u8 last_freq;		/* Last SWREQ frequency */
+	u8 min_freq_softlimit;	/* Minimum frequency permitted by the driver */
+	u8 max_freq_softlimit;	/* Max frequency permitted by the driver */
+	u8 max_freq;		/* Maximum frequency, RP0 if not overclocking */
+	u8 min_freq;		/* AKA RPn. Minimum frequency */
+	u8 boost_freq;		/* Frequency to request when wait boosting */
+	u8 idle_freq;		/* Frequency to request when we are idle */
+	u8 efficient_freq;	/* AKA RPe. Pre-determined balanced frequency */
+	u8 rp1_freq;		/* "less than" RP0 power/freqency */
+	u8 rp0_freq;		/* Non-overclocked max frequency. */
+	u16 gpll_ref_freq;	/* vlv/chv GPLL reference frequency */
+
+	int last_adj;
+
+	struct {
+		struct mutex mutex;
+
+		enum { LOW_POWER, BETWEEN, HIGH_POWER } mode;
+		unsigned int interactive;
+
+		u8 up_threshold; /* Current %busy required to uplock */
+		u8 down_threshold; /* Current %busy required to downclock */
+	} power;
+
+	atomic_t num_waiters;
+	atomic_t boosts;
+
+	/* manual wa residency calculations */
+	struct intel_rps_ei ei;
+	struct intel_ips ips;
+};
+
+#endif /* INTEL_RPS_TYPES_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline.c b/drivers/gpu/drm/i915/gt/intel_timeline.c
index 0f959694303c..649798c184fb 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline.c
+++ b/drivers/gpu/drm/i915/gt/intel_timeline.c
@@ -4,13 +4,13 @@
  * Copyright © 2016-2018 Intel Corporation
  */
 
-#include "gt/intel_gt_types.h"
-
 #include "i915_drv.h"
 
 #include "i915_active.h"
 #include "i915_syncmap.h"
-#include "gt/intel_timeline.h"
+#include "intel_gt.h"
+#include "intel_ring.h"
+#include "intel_timeline.h"
 
 #define ptr_set_bit(ptr, bit) ((typeof(ptr))((unsigned long)(ptr) | BIT(bit)))
 #define ptr_test_bit(ptr, bit) ((unsigned long)(ptr) & BIT(bit))
@@ -282,6 +282,7 @@ void intel_timeline_fini(struct intel_timeline *timeline)
 {
 	GEM_BUG_ON(atomic_read(&timeline->pin_count));
 	GEM_BUG_ON(!list_empty(&timeline->requests));
+	GEM_BUG_ON(timeline->retire);
 
 	if (timeline->hwsp_cacheline)
 		cacheline_free(timeline->hwsp_cacheline);
@@ -339,15 +340,33 @@ void intel_timeline_enter(struct intel_timeline *tl)
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 	unsigned long flags;
 
+	/*
+	 * Pretend we are serialised by the timeline->mutex.
+	 *
+	 * While generally true, there are a few exceptions to the rule
+	 * for the engine->kernel_context being used to manage power
+	 * transitions. As the engine_park may be called from under any
+	 * timeline, it uses the power mutex as a global serialisation
+	 * lock to prevent any other request entering its timeline.
+	 *
+	 * The rule is generally tl->mutex, otherwise engine->wakeref.mutex.
+	 *
+	 * However, intel_gt_retire_request() does not know which engine
+	 * it is retiring along and so cannot partake in the engine-pm
+	 * barrier, and there we use the tl->active_count as a means to
+	 * pin the timeline in the active_list while the locks are dropped.
+	 * Ergo, as that is outside of the engine-pm barrier, we need to
+	 * use atomic to manipulate tl->active_count.
+	 */
 	lockdep_assert_held(&tl->mutex);
-
 	GEM_BUG_ON(!atomic_read(&tl->pin_count));
-	if (tl->active_count++)
+
+	if (atomic_add_unless(&tl->active_count, 1, 0))
 		return;
-	GEM_BUG_ON(!tl->active_count); /* overflow? */
 
 	spin_lock_irqsave(&timelines->lock, flags);
-	list_add(&tl->link, &timelines->active_list);
+	if (!atomic_fetch_inc(&tl->active_count))
+		list_add_tail(&tl->link, &timelines->active_list);
 	spin_unlock_irqrestore(&timelines->lock, flags);
 }
 
@@ -356,14 +375,16 @@ void intel_timeline_exit(struct intel_timeline *tl)
 	struct intel_gt_timelines *timelines = &tl->gt->timelines;
 	unsigned long flags;
 
+	/* See intel_timeline_enter() */
 	lockdep_assert_held(&tl->mutex);
 
-	GEM_BUG_ON(!tl->active_count);
-	if (--tl->active_count)
+	GEM_BUG_ON(!atomic_read(&tl->active_count));
+	if (atomic_add_unless(&tl->active_count, -1, 1))
 		return;
 
 	spin_lock_irqsave(&timelines->lock, flags);
-	list_del(&tl->link);
+	if (atomic_dec_and_test(&tl->active_count))
+		list_del(&tl->link);
 	spin_unlock_irqrestore(&timelines->lock, flags);
 
 	/*
diff --git a/drivers/gpu/drm/i915/gt/intel_timeline_types.h b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
index 98d9ee166379..aaf15cbe1ce1 100644
--- a/drivers/gpu/drm/i915/gt/intel_timeline_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_timeline_types.h
@@ -42,7 +42,7 @@ struct intel_timeline {
 	 * from the intel_context caller plus internal atomicity.
 	 */
 	atomic_t pin_count;
-	unsigned int active_count;
+	atomic_t active_count;
 
 	const u32 *hwsp_seqno;
 	struct i915_vma *hwsp_ggtt;
@@ -66,6 +66,9 @@ struct intel_timeline {
 	 */
 	struct i915_active_fence last_request;
 
+	/** A chain of completed timelines ready for early retirement. */
+	struct intel_timeline *retire;
+
 	/**
 	 * We track the most recent seqno that we wait on in every context so
 	 * that we only have to emit a new await and dependency on a more
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
index af8a8183154a..e4bccc14602f 100644
--- a/drivers/gpu/drm/i915/gt/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -7,6 +7,7 @@
 #include "i915_drv.h"
 #include "intel_context.h"
 #include "intel_gt.h"
+#include "intel_ring.h"
 #include "intel_workarounds.h"
 
 /**
@@ -1215,6 +1216,26 @@ static void icl_whitelist_build(struct intel_engine_cs *engine)
 
 static void tgl_whitelist_build(struct intel_engine_cs *engine)
 {
+	struct i915_wa_list *w = &engine->whitelist;
+
+	switch (engine->class) {
+	case RENDER_CLASS:
+		/*
+		 * WaAllowPMDepthAndInvocationCountAccessFromUMD:tgl
+		 *
+		 * This covers 4 registers which are next to one another :
+		 *   - PS_INVOCATION_COUNT
+		 *   - PS_INVOCATION_COUNT_UDW
+		 *   - PS_DEPTH_COUNT
+		 *   - PS_DEPTH_COUNT_UDW
+		 */
+		whitelist_reg_ext(w, PS_INVOCATION_COUNT,
+				  RING_FORCE_TO_NONPRIV_ACCESS_RD |
+				  RING_FORCE_TO_NONPRIV_RANGE_4);
+		break;
+	default:
+		break;
+	}
 }
 
 void intel_engine_init_whitelist(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/gt/mock_engine.c b/drivers/gpu/drm/i915/gt/mock_engine.c
index 123db2c3f956..83f549d203a0 100644
--- a/drivers/gpu/drm/i915/gt/mock_engine.c
+++ b/drivers/gpu/drm/i915/gt/mock_engine.c
@@ -23,6 +23,7 @@
  */
 
 #include "gem/i915_gem_context.h"
+#include "gt/intel_ring.h"
 
 #include "i915_drv.h"
 #include "intel_context.h"
diff --git a/drivers/gpu/drm/i915/gt/selftest_context.c b/drivers/gpu/drm/i915/gt/selftest_context.c
index f63a26a3e620..bc720defc6b8 100644
--- a/drivers/gpu/drm/i915/gt/selftest_context.c
+++ b/drivers/gpu/drm/i915/gt/selftest_context.c
@@ -103,9 +103,6 @@ static int __live_context_size(struct intel_engine_cs *engine,
 	 *
 	 * TLDR; this overlaps with the execlists redzone.
 	 */
-	if (HAS_EXECLISTS(engine->i915))
-		vaddr += LRC_HEADER_PAGES * PAGE_SIZE;
-
 	vaddr += engine->context_size - I915_GTT_PAGE_SIZE;
 	memset(vaddr, POISON_INUSE, I915_GTT_PAGE_SIZE);
 
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
new file mode 100644
index 000000000000..e864406bd2d9
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_heartbeat.c
@@ -0,0 +1,350 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#include <linux/sort.h>
+
+#include "i915_drv.h"
+
+#include "intel_gt_requests.h"
+#include "i915_selftest.h"
+
+struct pulse {
+	struct i915_active active;
+	struct kref kref;
+};
+
+static int pulse_active(struct i915_active *active)
+{
+	kref_get(&container_of(active, struct pulse, active)->kref);
+	return 0;
+}
+
+static void pulse_free(struct kref *kref)
+{
+	kfree(container_of(kref, struct pulse, kref));
+}
+
+static void pulse_put(struct pulse *p)
+{
+	kref_put(&p->kref, pulse_free);
+}
+
+static void pulse_retire(struct i915_active *active)
+{
+	pulse_put(container_of(active, struct pulse, active));
+}
+
+static struct pulse *pulse_create(void)
+{
+	struct pulse *p;
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return p;
+
+	kref_init(&p->kref);
+	i915_active_init(&p->active, pulse_active, pulse_retire);
+
+	return p;
+}
+
+static void pulse_unlock_wait(struct pulse *p)
+{
+	mutex_lock(&p->active.mutex);
+	mutex_unlock(&p->active.mutex);
+	flush_work(&p->active.work);
+}
+
+static int __live_idle_pulse(struct intel_engine_cs *engine,
+			     int (*fn)(struct intel_engine_cs *cs))
+{
+	struct pulse *p;
+	int err;
+
+	GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
+
+	p = pulse_create();
+	if (!p)
+		return -ENOMEM;
+
+	err = i915_active_acquire(&p->active);
+	if (err)
+		goto out;
+
+	err = i915_active_acquire_preallocate_barrier(&p->active, engine);
+	if (err) {
+		i915_active_release(&p->active);
+		goto out;
+	}
+
+	i915_active_acquire_barrier(&p->active);
+	i915_active_release(&p->active);
+
+	GEM_BUG_ON(i915_active_is_idle(&p->active));
+	GEM_BUG_ON(llist_empty(&engine->barrier_tasks));
+
+	err = fn(engine);
+	if (err)
+		goto out;
+
+	GEM_BUG_ON(!llist_empty(&engine->barrier_tasks));
+
+	if (intel_gt_retire_requests_timeout(engine->gt, HZ / 5)) {
+		err = -ETIME;
+		goto out;
+	}
+
+	GEM_BUG_ON(READ_ONCE(engine->serial) != engine->wakeref_serial);
+
+	pulse_unlock_wait(p); /* synchronize with the retirement callback */
+
+	if (!i915_active_is_idle(&p->active)) {
+		struct drm_printer m = drm_err_printer("pulse");
+
+		pr_err("%s: heartbeat pulse did not flush idle tasks\n",
+		       engine->name);
+		i915_active_print(&p->active, &m);
+
+		err = -EINVAL;
+		goto out;
+	}
+
+out:
+	pulse_put(p);
+	return err;
+}
+
+static int live_idle_flush(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/* Check that we can flush the idle barriers */
+
+	for_each_engine(engine, gt, id) {
+		intel_engine_pm_get(engine);
+		err = __live_idle_pulse(engine, intel_engine_flush_barriers);
+		intel_engine_pm_put(engine);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static int live_idle_pulse(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/* Check that heartbeat pulses flush the idle barriers */
+
+	for_each_engine(engine, gt, id) {
+		intel_engine_pm_get(engine);
+		err = __live_idle_pulse(engine, intel_engine_pulse);
+		intel_engine_pm_put(engine);
+		if (err && err != -ENODEV)
+			break;
+
+		err = 0;
+	}
+
+	return err;
+}
+
+static int cmp_u32(const void *_a, const void *_b)
+{
+	const u32 *a = _a, *b = _b;
+
+	return *a - *b;
+}
+
+static int __live_heartbeat_fast(struct intel_engine_cs *engine)
+{
+	struct intel_context *ce;
+	struct i915_request *rq;
+	ktime_t t0, t1;
+	u32 times[5];
+	int err;
+	int i;
+
+	ce = intel_context_create(engine->kernel_context->gem_context,
+				  engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
+
+	intel_engine_pm_get(engine);
+
+	err = intel_engine_set_heartbeat(engine, 1);
+	if (err)
+		goto err_pm;
+
+	for (i = 0; i < ARRAY_SIZE(times); i++) {
+		/* Manufacture a tick */
+		do {
+			while (READ_ONCE(engine->heartbeat.systole))
+				flush_delayed_work(&engine->heartbeat.work);
+
+			engine->serial++; /* quick, pretend we are not idle! */
+			flush_delayed_work(&engine->heartbeat.work);
+			if (!delayed_work_pending(&engine->heartbeat.work)) {
+				pr_err("%s: heartbeat did not start\n",
+				       engine->name);
+				err = -EINVAL;
+				goto err_pm;
+			}
+
+			rcu_read_lock();
+			rq = READ_ONCE(engine->heartbeat.systole);
+			if (rq)
+				rq = i915_request_get_rcu(rq);
+			rcu_read_unlock();
+		} while (!rq);
+
+		t0 = ktime_get();
+		while (rq == READ_ONCE(engine->heartbeat.systole))
+			yield(); /* work is on the local cpu! */
+		t1 = ktime_get();
+
+		i915_request_put(rq);
+		times[i] = ktime_us_delta(t1, t0);
+	}
+
+	sort(times, ARRAY_SIZE(times), sizeof(times[0]), cmp_u32, NULL);
+
+	pr_info("%s: Heartbeat delay: %uus [%u, %u]\n",
+		engine->name,
+		times[ARRAY_SIZE(times) / 2],
+		times[0],
+		times[ARRAY_SIZE(times) - 1]);
+
+	/* Min work delay is 2 * 2 (worst), +1 for scheduling, +1 for slack */
+	if (times[ARRAY_SIZE(times) / 2] > jiffies_to_usecs(6)) {
+		pr_err("%s: Heartbeat delay was %uus, expected less than %dus\n",
+		       engine->name,
+		       times[ARRAY_SIZE(times) / 2],
+		       jiffies_to_usecs(6));
+		err = -EINVAL;
+	}
+
+	intel_engine_set_heartbeat(engine, CONFIG_DRM_I915_HEARTBEAT_INTERVAL);
+err_pm:
+	intel_engine_pm_put(engine);
+	intel_context_put(ce);
+	return err;
+}
+
+static int live_heartbeat_fast(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/* Check that the heartbeat ticks at the desired rate. */
+	if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL)
+		return 0;
+
+	for_each_engine(engine, gt, id) {
+		err = __live_heartbeat_fast(engine);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+static int __live_heartbeat_off(struct intel_engine_cs *engine)
+{
+	int err;
+
+	intel_engine_pm_get(engine);
+
+	engine->serial++;
+	flush_delayed_work(&engine->heartbeat.work);
+	if (!delayed_work_pending(&engine->heartbeat.work)) {
+		pr_err("%s: heartbeat not running\n",
+		       engine->name);
+		err = -EINVAL;
+		goto err_pm;
+	}
+
+	err = intel_engine_set_heartbeat(engine, 0);
+	if (err)
+		goto err_pm;
+
+	engine->serial++;
+	flush_delayed_work(&engine->heartbeat.work);
+	if (delayed_work_pending(&engine->heartbeat.work)) {
+		pr_err("%s: heartbeat still running\n",
+		       engine->name);
+		err = -EINVAL;
+		goto err_beat;
+	}
+
+	if (READ_ONCE(engine->heartbeat.systole)) {
+		pr_err("%s: heartbeat still allocated\n",
+		       engine->name);
+		err = -EINVAL;
+		goto err_beat;
+	}
+
+err_beat:
+	intel_engine_set_heartbeat(engine, CONFIG_DRM_I915_HEARTBEAT_INTERVAL);
+err_pm:
+	intel_engine_pm_put(engine);
+	return err;
+}
+
+static int live_heartbeat_off(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/* Check that we can turn off heartbeat and not interrupt VIP */
+	if (!CONFIG_DRM_I915_HEARTBEAT_INTERVAL)
+		return 0;
+
+	for_each_engine(engine, gt, id) {
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		err = __live_heartbeat_off(engine);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+int intel_heartbeat_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(live_idle_flush),
+		SUBTEST(live_idle_pulse),
+		SUBTEST(live_heartbeat_fast),
+		SUBTEST(live_heartbeat_off),
+	};
+	int saved_hangcheck;
+	int err;
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	saved_hangcheck = i915_modparams.enable_hangcheck;
+	i915_modparams.enable_hangcheck = INT_MAX;
+
+	err = intel_gt_live_subtests(tests, &i915->gt);
+
+	i915_modparams.enable_hangcheck = saved_hangcheck;
+	return err;
+}
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
index 20b9c83f43ad..cbf6b0735272 100644
--- a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -51,11 +51,12 @@ static int live_engine_pm(void *arg)
 				pr_err("intel_engine_pm_get_if_awake(%s) failed under %s\n",
 				       engine->name, p->name);
 			else
-				intel_engine_pm_put(engine);
-			intel_engine_pm_put(engine);
+				intel_engine_pm_put_async(engine);
+			intel_engine_pm_put_async(engine);
 			p->critical_section_end();
 
-			/* engine wakeref is sync (instant) */
+			intel_engine_pm_flush(engine);
+
 			if (intel_engine_pm_is_awake(engine)) {
 				pr_err("%s is still awake after flushing pm\n",
 				       engine->name);
diff --git a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
index 5d429037cdad..d1752f15702a 100644
--- a/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
+++ b/drivers/gpu/drm/i915/gt/selftest_gt_pm.c
@@ -15,7 +15,8 @@ static int live_gt_resume(void *arg)
 
 	/* Do several suspend/resume cycles to check we don't explode! */
 	do {
-		intel_gt_suspend(gt);
+		intel_gt_suspend_prepare(gt);
+		intel_gt_suspend_late(gt);
 
 		if (gt->rc6.enabled) {
 			pr_err("rc6 still enabled after suspend!\n");
diff --git a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
index 8e0016464325..85e9ccf5c304 100644
--- a/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/selftest_hangcheck.c
@@ -826,6 +826,8 @@ static int __igt_reset_engines(struct intel_gt *gt,
 			get_task_struct(tsk);
 		}
 
+		yield(); /* start all threads before we begin */
+
 		intel_engine_pm_get(engine);
 		set_bit(I915_RESET_ENGINE + id, &gt->reset.flags);
 		do {
@@ -1016,7 +1018,7 @@ static int igt_reset_wait(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
-	struct intel_engine_cs *engine = gt->i915->engine[RCS0];
+	struct intel_engine_cs *engine = gt->engine[RCS0];
 	struct i915_request *rq;
 	unsigned int reset_count;
 	struct hang h;
@@ -1143,14 +1145,18 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 				 int (*fn)(void *),
 				 unsigned int flags)
 {
-	struct intel_engine_cs *engine = gt->i915->engine[RCS0];
+	struct intel_engine_cs *engine = gt->engine[RCS0];
 	struct drm_i915_gem_object *obj;
 	struct task_struct *tsk = NULL;
 	struct i915_request *rq;
 	struct evict_vma arg;
 	struct hang h;
+	unsigned int pin_flags;
 	int err;
 
+	if (!gt->ggtt->num_fences && flags & EXEC_OBJECT_NEEDS_FENCE)
+		return 0;
+
 	if (!engine || !intel_engine_can_store_dword(engine))
 		return 0;
 
@@ -1186,10 +1192,12 @@ static int __igt_reset_evict_vma(struct intel_gt *gt,
 		goto out_obj;
 	}
 
-	err = i915_vma_pin(arg.vma, 0, 0,
-			   i915_vma_is_ggtt(arg.vma) ?
-			   PIN_GLOBAL | PIN_MAPPABLE :
-			   PIN_USER);
+	pin_flags = i915_vma_is_ggtt(arg.vma) ? PIN_GLOBAL : PIN_USER;
+
+	if (flags & EXEC_OBJECT_NEEDS_FENCE)
+		pin_flags |= PIN_MAPPABLE;
+
+	err = i915_vma_pin(arg.vma, 0, 0, pin_flags);
 	if (err) {
 		i915_request_add(rq);
 		goto out_obj;
@@ -1493,7 +1501,7 @@ static int igt_handle_error(void *arg)
 {
 	struct intel_gt *gt = arg;
 	struct i915_gpu_error *global = &gt->i915->gpu_error;
-	struct intel_engine_cs *engine = gt->i915->engine[RCS0];
+	struct intel_engine_cs *engine = gt->engine[RCS0];
 	struct hang h;
 	struct i915_request *rq;
 	struct i915_gpu_state *error;
@@ -1563,7 +1571,7 @@ static int __igt_atomic_reset_engine(struct intel_engine_cs *engine,
 	GEM_TRACE("i915_reset_engine(%s:%s) under %s\n",
 		  engine->name, mode, p->name);
 
-	tasklet_disable_nosync(t);
+	tasklet_disable(t);
 	p->critical_section_begin();
 
 	err = intel_engine_reset(engine, NULL);
@@ -1686,7 +1694,6 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	};
 	struct intel_gt *gt = &i915->gt;
 	intel_wakeref_t wakeref;
-	bool saved_hangcheck;
 	int err;
 
 	if (!intel_has_gpu_reset(gt))
@@ -1696,12 +1703,9 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		return -EIO; /* we're long past hope of a successful reset */
 
 	wakeref = intel_runtime_pm_get(gt->uncore->rpm);
-	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
-	drain_delayed_work(&gt->hangcheck.work); /* flush param */
 
 	err = intel_gt_live_subtests(tests, gt);
 
-	i915_modparams.enable_hangcheck = saved_hangcheck;
 	intel_runtime_pm_put(gt->uncore->rpm, wakeref);
 
 	return err;
diff --git a/drivers/gpu/drm/i915/gt/selftest_llc.c b/drivers/gpu/drm/i915/gt/selftest_llc.c
index a7057785e420..fd3770e48ac7 100644
--- a/drivers/gpu/drm/i915/gt/selftest_llc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_llc.c
@@ -6,6 +6,7 @@
 
 #include "intel_pm.h" /* intel_gpu_freq() */
 #include "selftest_llc.h"
+#include "intel_rps.h"
 
 static int gen6_verify_ring_freq(struct intel_llc *llc)
 {
@@ -25,6 +26,8 @@ static int gen6_verify_ring_freq(struct intel_llc *llc)
 	for (gpu_freq = consts.min_gpu_freq;
 	     gpu_freq <= consts.max_gpu_freq;
 	     gpu_freq++) {
+		struct intel_rps *rps = &llc_to_gt(llc)->rps;
+
 		unsigned int ia_freq, ring_freq, found;
 		u32 val;
 
@@ -44,7 +47,7 @@ static int gen6_verify_ring_freq(struct intel_llc *llc)
 		if (found != ia_freq) {
 			pr_err("Min freq table(%d/[%d, %d]):%dMHz did not match expected CPU freq, found %d, expected %d\n",
 			       gpu_freq, consts.min_gpu_freq, consts.max_gpu_freq,
-			       intel_gpu_freq(i915, gpu_freq * (INTEL_GEN(i915) >= 9 ? GEN9_FREQ_SCALER : 1)),
+			       intel_gpu_freq(rps, gpu_freq * (INTEL_GEN(i915) >= 9 ? GEN9_FREQ_SCALER : 1)),
 			       found, ia_freq);
 			err = -EINVAL;
 			break;
@@ -54,7 +57,7 @@ static int gen6_verify_ring_freq(struct intel_llc *llc)
 		if (found != ring_freq) {
 			pr_err("Min freq table(%d/[%d, %d]):%dMHz did not match expected ring freq, found %d, expected %d\n",
 			       gpu_freq, consts.min_gpu_freq, consts.max_gpu_freq,
-			       intel_gpu_freq(i915, gpu_freq * (INTEL_GEN(i915) >= 9 ? GEN9_FREQ_SCALER : 1)),
+			       intel_gpu_freq(rps, gpu_freq * (INTEL_GEN(i915) >= 9 ? GEN9_FREQ_SCALER : 1)),
 			       found, ring_freq);
 			err = -EINVAL;
 			break;
diff --git a/drivers/gpu/drm/i915/gt/selftest_lrc.c b/drivers/gpu/drm/i915/gt/selftest_lrc.c
index 5dc679781a08..eb71ac2f992c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_lrc.c
+++ b/drivers/gpu/drm/i915/gt/selftest_lrc.c
@@ -7,6 +7,7 @@
 #include <linux/prime_numbers.h>
 
 #include "gem/i915_gem_pm.h"
+#include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_reset.h"
 
 #include "i915_selftest.h"
@@ -168,12 +169,7 @@ static int live_unlite_restore(struct intel_gt *gt, int prio)
 		}
 		GEM_BUG_ON(!ce[1]->ring->size);
 		intel_ring_reset(ce[1]->ring, ce[1]->ring->size / 2);
-
-		local_irq_disable(); /* appease lockdep */
-		__context_pin_acquire(ce[1]);
 		__execlists_update_reg_state(ce[1], engine);
-		__context_pin_release(ce[1]);
-		local_irq_enable();
 
 		rq[0] = igt_spinner_create_request(&spin, ce[0], MI_ARB_CHECK);
 		if (IS_ERR(rq[0])) {
@@ -444,6 +440,8 @@ static int live_timeslice_preempt(void *arg)
 	 * need to preempt the current task and replace it with another
 	 * ready task.
 	 */
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return 0;
 
 	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(obj))
@@ -518,6 +516,11 @@ static void wait_for_submit(struct intel_engine_cs *engine,
 	} while (!i915_request_is_active(rq));
 }
 
+static long timeslice_threshold(const struct intel_engine_cs *engine)
+{
+	return 2 * msecs_to_jiffies_timeout(timeslice(engine)) + 1;
+}
+
 static int live_timeslice_queue(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -535,6 +538,8 @@ static int live_timeslice_queue(void *arg)
 	 * ELSP[1] is already occupied, so must rely on timeslicing to
 	 * eject ELSP[0] in favour of the queue.)
 	 */
+	if (!IS_ACTIVE(CONFIG_DRM_I915_TIMESLICE_DURATION))
+		return 0;
 
 	obj = i915_gem_object_create_internal(gt->i915, PAGE_SIZE);
 	if (IS_ERR(obj))
@@ -612,8 +617,8 @@ static int live_timeslice_queue(void *arg)
 			err = -EINVAL;
 		}
 
-		/* Timeslice every jiffie, so within 2 we should signal */
-		if (i915_request_wait(rq, 0, 3) < 0) {
+		/* Timeslice every jiffy, so within 2 we should signal */
+		if (i915_request_wait(rq, 0, timeslice_threshold(engine)) < 0) {
 			struct drm_printer p =
 				drm_info_printer(gt->i915->drm.dev);
 
@@ -1165,6 +1170,325 @@ err_wedged:
 	goto err_client_b;
 }
 
+struct live_preempt_cancel {
+	struct intel_engine_cs *engine;
+	struct preempt_client a, b;
+};
+
+static int __cancel_active0(struct live_preempt_cancel *arg)
+{
+	struct i915_request *rq;
+	struct igt_live_test t;
+	int err;
+
+	/* Preempt cancel of ELSP0 */
+	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+	if (igt_live_test_begin(&t, arg->engine->i915,
+				__func__, arg->engine->name))
+		return -EIO;
+
+	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+	rq = spinner_create_request(&arg->a.spin,
+				    arg->a.ctx, arg->engine,
+				    MI_ARB_CHECK);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
+		err = -EIO;
+		goto out;
+	}
+
+	i915_gem_context_set_banned(arg->a.ctx);
+	err = intel_engine_pulse(arg->engine);
+	if (err)
+		goto out;
+
+	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (rq->fence.error != -EIO) {
+		pr_err("Cancelled inflight0 request did not report -EIO\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+out:
+	i915_request_put(rq);
+	if (igt_live_test_end(&t))
+		err = -EIO;
+	return err;
+}
+
+static int __cancel_active1(struct live_preempt_cancel *arg)
+{
+	struct i915_request *rq[2] = {};
+	struct igt_live_test t;
+	int err;
+
+	/* Preempt cancel of ELSP1 */
+	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+	if (igt_live_test_begin(&t, arg->engine->i915,
+				__func__, arg->engine->name))
+		return -EIO;
+
+	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+	rq[0] = spinner_create_request(&arg->a.spin,
+				       arg->a.ctx, arg->engine,
+				       MI_NOOP); /* no preemption */
+	if (IS_ERR(rq[0]))
+		return PTR_ERR(rq[0]);
+
+	i915_request_get(rq[0]);
+	i915_request_add(rq[0]);
+	if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
+		err = -EIO;
+		goto out;
+	}
+
+	clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
+	rq[1] = spinner_create_request(&arg->b.spin,
+				       arg->b.ctx, arg->engine,
+				       MI_ARB_CHECK);
+	if (IS_ERR(rq[1])) {
+		err = PTR_ERR(rq[1]);
+		goto out;
+	}
+
+	i915_request_get(rq[1]);
+	err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
+	i915_request_add(rq[1]);
+	if (err)
+		goto out;
+
+	i915_gem_context_set_banned(arg->b.ctx);
+	err = intel_engine_pulse(arg->engine);
+	if (err)
+		goto out;
+
+	igt_spinner_end(&arg->a.spin);
+	if (i915_request_wait(rq[1], 0, HZ / 5) < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (rq[0]->fence.error != 0) {
+		pr_err("Normal inflight0 request did not complete\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (rq[1]->fence.error != -EIO) {
+		pr_err("Cancelled inflight1 request did not report -EIO\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+out:
+	i915_request_put(rq[1]);
+	i915_request_put(rq[0]);
+	if (igt_live_test_end(&t))
+		err = -EIO;
+	return err;
+}
+
+static int __cancel_queued(struct live_preempt_cancel *arg)
+{
+	struct i915_request *rq[3] = {};
+	struct igt_live_test t;
+	int err;
+
+	/* Full ELSP and one in the wings */
+	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+	if (igt_live_test_begin(&t, arg->engine->i915,
+				__func__, arg->engine->name))
+		return -EIO;
+
+	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+	rq[0] = spinner_create_request(&arg->a.spin,
+				       arg->a.ctx, arg->engine,
+				       MI_ARB_CHECK);
+	if (IS_ERR(rq[0]))
+		return PTR_ERR(rq[0]);
+
+	i915_request_get(rq[0]);
+	i915_request_add(rq[0]);
+	if (!igt_wait_for_spinner(&arg->a.spin, rq[0])) {
+		err = -EIO;
+		goto out;
+	}
+
+	clear_bit(CONTEXT_BANNED, &arg->b.ctx->flags);
+	rq[1] = igt_request_alloc(arg->b.ctx, arg->engine);
+	if (IS_ERR(rq[1])) {
+		err = PTR_ERR(rq[1]);
+		goto out;
+	}
+
+	i915_request_get(rq[1]);
+	err = i915_request_await_dma_fence(rq[1], &rq[0]->fence);
+	i915_request_add(rq[1]);
+	if (err)
+		goto out;
+
+	rq[2] = spinner_create_request(&arg->b.spin,
+				       arg->a.ctx, arg->engine,
+				       MI_ARB_CHECK);
+	if (IS_ERR(rq[2])) {
+		err = PTR_ERR(rq[2]);
+		goto out;
+	}
+
+	i915_request_get(rq[2]);
+	err = i915_request_await_dma_fence(rq[2], &rq[1]->fence);
+	i915_request_add(rq[2]);
+	if (err)
+		goto out;
+
+	i915_gem_context_set_banned(arg->a.ctx);
+	err = intel_engine_pulse(arg->engine);
+	if (err)
+		goto out;
+
+	if (i915_request_wait(rq[2], 0, HZ / 5) < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (rq[0]->fence.error != -EIO) {
+		pr_err("Cancelled inflight0 request did not report -EIO\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (rq[1]->fence.error != 0) {
+		pr_err("Normal inflight1 request did not complete\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (rq[2]->fence.error != -EIO) {
+		pr_err("Cancelled queued request did not report -EIO\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+out:
+	i915_request_put(rq[2]);
+	i915_request_put(rq[1]);
+	i915_request_put(rq[0]);
+	if (igt_live_test_end(&t))
+		err = -EIO;
+	return err;
+}
+
+static int __cancel_hostile(struct live_preempt_cancel *arg)
+{
+	struct i915_request *rq;
+	int err;
+
+	/* Preempt cancel non-preemptible spinner in ELSP0 */
+	if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT))
+		return 0;
+
+	GEM_TRACE("%s(%s)\n", __func__, arg->engine->name);
+	clear_bit(CONTEXT_BANNED, &arg->a.ctx->flags);
+	rq = spinner_create_request(&arg->a.spin,
+				    arg->a.ctx, arg->engine,
+				    MI_NOOP); /* preemption disabled */
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (!igt_wait_for_spinner(&arg->a.spin, rq)) {
+		err = -EIO;
+		goto out;
+	}
+
+	i915_gem_context_set_banned(arg->a.ctx);
+	err = intel_engine_pulse(arg->engine); /* force reset */
+	if (err)
+		goto out;
+
+	if (i915_request_wait(rq, 0, HZ / 5) < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	if (rq->fence.error != -EIO) {
+		pr_err("Cancelled inflight0 request did not report -EIO\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+out:
+	i915_request_put(rq);
+	if (igt_flush_test(arg->engine->i915))
+		err = -EIO;
+	return err;
+}
+
+static int live_preempt_cancel(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct live_preempt_cancel data;
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	/*
+	 * To cancel an inflight context, we need to first remove it from the
+	 * GPU. That sounds like preemption! Plus a little bit of bookkeeping.
+	 */
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
+		return 0;
+
+	if (preempt_client_init(gt, &data.a))
+		return -ENOMEM;
+	if (preempt_client_init(gt, &data.b))
+		goto err_client_a;
+
+	for_each_engine(data.engine, gt, id) {
+		if (!intel_engine_has_preemption(data.engine))
+			continue;
+
+		err = __cancel_active0(&data);
+		if (err)
+			goto err_wedged;
+
+		err = __cancel_active1(&data);
+		if (err)
+			goto err_wedged;
+
+		err = __cancel_queued(&data);
+		if (err)
+			goto err_wedged;
+
+		err = __cancel_hostile(&data);
+		if (err)
+			goto err_wedged;
+	}
+
+	err = 0;
+err_client_b:
+	preempt_client_fini(&data.b);
+err_client_a:
+	preempt_client_fini(&data.a);
+	return err;
+
+err_wedged:
+	GEM_TRACE_DUMP();
+	igt_spinner_end(&data.b.spin);
+	igt_spinner_end(&data.a.spin);
+	intel_gt_set_wedged(gt);
+	goto err_client_b;
+}
+
 static int live_suppress_self_preempt(void *arg)
 {
 	struct intel_gt *gt = arg;
@@ -1702,6 +2026,105 @@ err_spin_hi:
 	return err;
 }
 
+static int live_preempt_timeout(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct i915_gem_context *ctx_hi, *ctx_lo;
+	struct igt_spinner spin_lo;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	/*
+	 * Check that we force preemption to occur by cancelling the previous
+	 * context if it refuses to yield the GPU.
+	 */
+	if (!IS_ACTIVE(CONFIG_DRM_I915_PREEMPT_TIMEOUT))
+		return 0;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(gt->i915))
+		return 0;
+
+	if (!intel_has_reset_engine(gt))
+		return 0;
+
+	if (igt_spinner_init(&spin_lo, gt))
+		return -ENOMEM;
+
+	ctx_hi = kernel_context(gt->i915);
+	if (!ctx_hi)
+		goto err_spin_lo;
+	ctx_hi->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MAX_USER_PRIORITY);
+
+	ctx_lo = kernel_context(gt->i915);
+	if (!ctx_lo)
+		goto err_ctx_hi;
+	ctx_lo->sched.priority =
+		I915_USER_PRIORITY(I915_CONTEXT_MIN_USER_PRIORITY);
+
+	for_each_engine(engine, gt, id) {
+		unsigned long saved_timeout;
+		struct i915_request *rq;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		rq = spinner_create_request(&spin_lo, ctx_lo, engine,
+					    MI_NOOP); /* preemption disabled */
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!igt_wait_for_spinner(&spin_lo, rq)) {
+			intel_gt_set_wedged(gt);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		rq = igt_request_alloc(ctx_hi, engine);
+		if (IS_ERR(rq)) {
+			igt_spinner_end(&spin_lo);
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		/* Flush the previous CS ack before changing timeouts */
+		while (READ_ONCE(engine->execlists.pending[0]))
+			cpu_relax();
+
+		saved_timeout = engine->props.preempt_timeout_ms;
+		engine->props.preempt_timeout_ms = 1; /* in ms, -> 1 jiffie */
+
+		i915_request_get(rq);
+		i915_request_add(rq);
+
+		intel_engine_flush_submission(engine);
+		engine->props.preempt_timeout_ms = saved_timeout;
+
+		if (i915_request_wait(rq, 0, HZ / 10) < 0) {
+			intel_gt_set_wedged(gt);
+			i915_request_put(rq);
+			err = -ETIME;
+			goto err_ctx_lo;
+		}
+
+		igt_spinner_end(&spin_lo);
+		i915_request_put(rq);
+	}
+
+	err = 0;
+err_ctx_lo:
+	kernel_context_close(ctx_lo);
+err_ctx_hi:
+	kernel_context_close(ctx_hi);
+err_spin_lo:
+	igt_spinner_fini(&spin_lo);
+	return err;
+}
+
 static int random_range(struct rnd_state *rnd, int min, int max)
 {
 	return i915_prandom_u32_max_state(max - min, rnd) + min;
@@ -1829,6 +2252,8 @@ static int smoke_crescendo(struct preempt_smoke *smoke, unsigned int flags)
 		get_task_struct(tsk[id]);
 	}
 
+	yield(); /* start all threads before we kthread_stop() */
+
 	count = 0;
 	for_each_engine(engine, smoke->gt, id) {
 		int status;
@@ -2599,10 +3024,12 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
 		SUBTEST(live_nopreempt),
+		SUBTEST(live_preempt_cancel),
 		SUBTEST(live_suppress_self_preempt),
 		SUBTEST(live_suppress_wait_preempt),
 		SUBTEST(live_chain_preempt),
 		SUBTEST(live_preempt_hang),
+		SUBTEST(live_preempt_timeout),
 		SUBTEST(live_preempt_smoke),
 		SUBTEST(live_virtual_engine),
 		SUBTEST(live_virtual_mask),
@@ -2749,6 +3176,100 @@ static int live_lrc_layout(void *arg)
 	return err;
 }
 
+static int find_offset(const u32 *lri, u32 offset)
+{
+	int i;
+
+	for (i = 0; i < PAGE_SIZE / sizeof(u32); i++)
+		if (lri[i] == offset)
+			return i;
+
+	return -1;
+}
+
+static int live_lrc_fixed(void *arg)
+{
+	struct intel_gt *gt = arg;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = 0;
+
+	/*
+	 * Check the assumed register offsets match the actual locations in
+	 * the context image.
+	 */
+
+	for_each_engine(engine, gt, id) {
+		const struct {
+			u32 reg;
+			u32 offset;
+			const char *name;
+		} tbl[] = {
+			{
+				i915_mmio_reg_offset(RING_START(engine->mmio_base)),
+				CTX_RING_BUFFER_START - 1,
+				"RING_START"
+			},
+			{
+				i915_mmio_reg_offset(RING_CTL(engine->mmio_base)),
+				CTX_RING_BUFFER_CONTROL - 1,
+				"RING_CTL"
+			},
+			{
+				i915_mmio_reg_offset(RING_HEAD(engine->mmio_base)),
+				CTX_RING_HEAD - 1,
+				"RING_HEAD"
+			},
+			{
+				i915_mmio_reg_offset(RING_TAIL(engine->mmio_base)),
+				CTX_RING_TAIL - 1,
+				"RING_TAIL"
+			},
+			{
+				i915_mmio_reg_offset(RING_MI_MODE(engine->mmio_base)),
+				lrc_ring_mi_mode(engine),
+				"RING_MI_MODE"
+			},
+			{
+				engine->mmio_base + 0x110,
+				CTX_BB_STATE - 1,
+				"BB_STATE"
+			},
+			{ },
+		}, *t;
+		u32 *hw;
+
+		if (!engine->default_state)
+			continue;
+
+		hw = i915_gem_object_pin_map(engine->default_state,
+					     I915_MAP_WB);
+		if (IS_ERR(hw)) {
+			err = PTR_ERR(hw);
+			break;
+		}
+		hw += LRC_STATE_PN * PAGE_SIZE / sizeof(*hw);
+
+		for (t = tbl; t->name; t++) {
+			int dw = find_offset(hw, t->reg);
+
+			if (dw != t->offset) {
+				pr_err("%s: Offset for %s [0x%x] mismatch, found %x, expected %x\n",
+				       engine->name,
+				       t->name,
+				       t->reg,
+				       dw,
+				       t->offset);
+				err = -EINVAL;
+			}
+		}
+
+		i915_gem_object_unpin_map(engine->default_state);
+	}
+
+	return err;
+}
+
 static int __live_lrc_state(struct i915_gem_context *fixme,
 			    struct intel_engine_cs *engine,
 			    struct i915_vma *scratch)
@@ -3021,6 +3542,7 @@ int intel_lrc_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_lrc_layout),
+		SUBTEST(live_lrc_fixed),
 		SUBTEST(live_lrc_state),
 		SUBTEST(live_gpr_clear),
 	};
diff --git a/drivers/gpu/drm/i915/gt/selftest_reset.c b/drivers/gpu/drm/i915/gt/selftest_reset.c
index 6efb9221b7fa..6ad6aca315f6 100644
--- a/drivers/gpu/drm/i915/gt/selftest_reset.c
+++ b/drivers/gpu/drm/i915/gt/selftest_reset.c
@@ -126,7 +126,7 @@ static int igt_atomic_engine_reset(void *arg)
 		goto out_unlock;
 
 	for_each_engine(engine, gt, id) {
-		tasklet_disable_nosync(&engine->execlists.tasklet);
+		tasklet_disable(&engine->execlists.tasklet);
 		intel_engine_pm_get(engine);
 
 		for (p = igt_atomic_phases; p->name; p++) {
diff --git a/drivers/gpu/drm/i915/gt/selftest_timeline.c b/drivers/gpu/drm/i915/gt/selftest_timeline.c
index dac86f699a4c..f04a59fe5d2c 100644
--- a/drivers/gpu/drm/i915/gt/selftest_timeline.c
+++ b/drivers/gpu/drm/i915/gt/selftest_timeline.c
@@ -9,6 +9,7 @@
 #include "intel_engine_pm.h"
 #include "intel_gt.h"
 #include "intel_gt_requests.h"
+#include "intel_ring.h"
 
 #include "../selftests/i915_random.h"
 #include "../i915_selftest.h"
diff --git a/drivers/gpu/drm/i915/gt/selftest_workarounds.c b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
index ef02920cec29..abce6e4ec9c0 100644
--- a/drivers/gpu/drm/i915/gt/selftest_workarounds.c
+++ b/drivers/gpu/drm/i915/gt/selftest_workarounds.c
@@ -513,6 +513,9 @@ static int check_dirty_whitelist(struct i915_gem_context *ctx,
 
 		ro_reg = ro_register(reg);
 
+		/* Clear non priv flags */
+		reg &= RING_FORCE_TO_NONPRIV_ADDRESS_MASK;
+
 		srm = MI_STORE_REGISTER_MEM;
 		lrm = MI_LOAD_REGISTER_MEM;
 		if (INTEL_GEN(ctx->i915) >= 8)
@@ -810,8 +813,8 @@ static int read_whitelisted_registers(struct i915_gem_context *ctx,
 		u64 offset = results->node.start + sizeof(u32) * i;
 		u32 reg = i915_mmio_reg_offset(engine->whitelist.list[i].reg);
 
-		/* Clear access permission field */
-		reg &= ~RING_FORCE_TO_NONPRIV_ACCESS_MASK;
+		/* Clear non priv flags */
+		reg &= RING_FORCE_TO_NONPRIV_ADDRESS_MASK;
 
 		*cs++ = srm;
 		*cs++ = reg;
@@ -849,6 +852,9 @@ static int scrub_whitelisted_registers(struct i915_gem_context *ctx,
 		if (ro_register(reg))
 			continue;
 
+		/* Clear non priv flags */
+		reg &= RING_FORCE_TO_NONPRIV_ADDRESS_MASK;
+
 		*cs++ = reg;
 		*cs++ = 0xffffffff;
 	}
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.c b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
index 37f7bcbf7dac..3ee4a4e7689d 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.c
@@ -4,6 +4,8 @@
  */
 
 #include "gt/intel_gt.h"
+#include "gt/intel_gt_irq.h"
+#include "gt/intel_gt_pm_irq.h"
 #include "intel_guc.h"
 #include "intel_guc_ads.h"
 #include "intel_guc_submission.h"
@@ -77,6 +79,93 @@ void intel_guc_init_send_regs(struct intel_guc *guc)
 	guc->send_regs.fw_domains = fw_domains;
 }
 
+static void gen9_reset_guc_interrupts(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	assert_rpm_wakelock_held(&gt->i915->runtime_pm);
+
+	spin_lock_irq(&gt->irq_lock);
+	gen6_gt_pm_reset_iir(gt, gt->pm_guc_events);
+	spin_unlock_irq(&gt->irq_lock);
+}
+
+static void gen9_enable_guc_interrupts(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	assert_rpm_wakelock_held(&gt->i915->runtime_pm);
+
+	spin_lock_irq(&gt->irq_lock);
+	if (!guc->interrupts.enabled) {
+		WARN_ON_ONCE(intel_uncore_read(gt->uncore, GEN8_GT_IIR(2)) &
+			     gt->pm_guc_events);
+		guc->interrupts.enabled = true;
+		gen6_gt_pm_enable_irq(gt, gt->pm_guc_events);
+	}
+	spin_unlock_irq(&gt->irq_lock);
+}
+
+static void gen9_disable_guc_interrupts(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	assert_rpm_wakelock_held(&gt->i915->runtime_pm);
+
+	spin_lock_irq(&gt->irq_lock);
+	guc->interrupts.enabled = false;
+
+	gen6_gt_pm_disable_irq(gt, gt->pm_guc_events);
+
+	spin_unlock_irq(&gt->irq_lock);
+	intel_synchronize_irq(gt->i915);
+
+	gen9_reset_guc_interrupts(guc);
+}
+
+static void gen11_reset_guc_interrupts(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	spin_lock_irq(&gt->irq_lock);
+	gen11_gt_reset_one_iir(gt, 0, GEN11_GUC);
+	spin_unlock_irq(&gt->irq_lock);
+}
+
+static void gen11_enable_guc_interrupts(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	spin_lock_irq(&gt->irq_lock);
+	if (!guc->interrupts.enabled) {
+		u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST);
+
+		WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC));
+		intel_uncore_write(gt->uncore,
+				   GEN11_GUC_SG_INTR_ENABLE, events);
+		intel_uncore_write(gt->uncore,
+				   GEN11_GUC_SG_INTR_MASK, ~events);
+		guc->interrupts.enabled = true;
+	}
+	spin_unlock_irq(&gt->irq_lock);
+}
+
+static void gen11_disable_guc_interrupts(struct intel_guc *guc)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+
+	spin_lock_irq(&gt->irq_lock);
+	guc->interrupts.enabled = false;
+
+	intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0);
+	intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0);
+
+	spin_unlock_irq(&gt->irq_lock);
+	intel_synchronize_irq(gt->i915);
+
+	gen11_reset_guc_interrupts(guc);
+}
+
 void intel_guc_init_early(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
@@ -103,32 +192,6 @@ void intel_guc_init_early(struct intel_guc *guc)
 	}
 }
 
-static int guc_shared_data_create(struct intel_guc *guc)
-{
-	struct i915_vma *vma;
-	void *vaddr;
-
-	vma = intel_guc_allocate_vma(guc, PAGE_SIZE);
-	if (IS_ERR(vma))
-		return PTR_ERR(vma);
-
-	vaddr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
-	if (IS_ERR(vaddr)) {
-		i915_vma_unpin_and_release(&vma, 0);
-		return PTR_ERR(vaddr);
-	}
-
-	guc->shared_data = vma;
-	guc->shared_data_vaddr = vaddr;
-
-	return 0;
-}
-
-static void guc_shared_data_destroy(struct intel_guc *guc)
-{
-	i915_vma_unpin_and_release(&guc->shared_data, I915_VMA_RELEASE_MAP);
-}
-
 static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
 	u32 level = intel_guc_log_get_level(&guc->log);
@@ -275,14 +338,9 @@ int intel_guc_init(struct intel_guc *guc)
 	if (ret)
 		goto err_fetch;
 
-	ret = guc_shared_data_create(guc);
-	if (ret)
-		goto err_fw;
-	GEM_BUG_ON(!guc->shared_data);
-
 	ret = intel_guc_log_create(&guc->log);
 	if (ret)
-		goto err_shared;
+		goto err_fw;
 
 	ret = intel_guc_ads_create(guc);
 	if (ret)
@@ -317,8 +375,6 @@ err_ads:
 	intel_guc_ads_destroy(guc);
 err_log:
 	intel_guc_log_destroy(&guc->log);
-err_shared:
-	guc_shared_data_destroy(guc);
 err_fw:
 	intel_uc_fw_fini(&guc->fw);
 err_fetch:
@@ -343,7 +399,6 @@ 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);
 	intel_uc_fw_cleanup_fetch(&guc->fw);
 }
@@ -499,6 +554,13 @@ int intel_guc_suspend(struct intel_guc *guc)
 	};
 
 	/*
+	 * If GuC communication is enabled but submission is not supported,
+	 * we do not need to suspend the GuC.
+	 */
+	if (!intel_guc_submission_is_enabled(guc))
+		return 0;
+
+	/*
 	 * The ENTER_S_STATE action queues the save/restore operation in GuC FW
 	 * and then returns, so waiting on the H2G is not enough to guarantee
 	 * GuC is done. When all the processing is done, GuC writes
@@ -539,19 +601,9 @@ int intel_guc_suspend(struct intel_guc *guc)
 int intel_guc_reset_engine(struct intel_guc *guc,
 			   struct intel_engine_cs *engine)
 {
-	u32 data[7];
-
-	GEM_BUG_ON(!guc->execbuf_client);
-
-	data[0] = INTEL_GUC_ACTION_REQUEST_ENGINE_RESET;
-	data[1] = engine->guc_id;
-	data[2] = 0;
-	data[3] = 0;
-	data[4] = 0;
-	data[5] = guc->execbuf_client->stage_id;
-	data[6] = intel_guc_ggtt_offset(guc, guc->shared_data);
+	/* XXX: to be implemented with submission interface rework */
 
-	return intel_guc_send(guc, data, ARRAY_SIZE(data));
+	return -ENODEV;
 }
 
 /**
@@ -565,6 +617,14 @@ int intel_guc_resume(struct intel_guc *guc)
 		GUC_POWER_D0,
 	};
 
+	/*
+	 * If GuC communication is enabled but submission is not supported,
+	 * we do not need to resume the GuC but we do need to enable the
+	 * GuC communication on resume (above).
+	 */
+	if (!intel_guc_submission_is_enabled(guc))
+		return 0;
+
 	return intel_guc_send(guc, action, ARRAY_SIZE(action));
 }
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index 2b2f046d3cc3..e6400204a2bd 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -47,8 +47,6 @@ struct intel_guc {
 	struct i915_vma *stage_desc_pool;
 	void *stage_desc_pool_vaddr;
 	struct ida stage_ids;
-	struct i915_vma *shared_data;
-	void *shared_data_vaddr;
 
 	struct intel_guc_client *execbuf_client;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
index 1d3cdd67ca2f..a26a85d50209 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h
@@ -548,6 +548,7 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_ALLOCATE_DOORBELL = 0x10,
 	INTEL_GUC_ACTION_DEALLOCATE_DOORBELL = 0x20,
 	INTEL_GUC_ACTION_LOG_BUFFER_FILE_FLUSH_COMPLETE = 0x30,
+	INTEL_GUC_ACTION_UK_LOG_ENABLE_LOGGING = 0x40,
 	INTEL_GUC_ACTION_FORCE_LOG_BUFFER_FLUSH = 0x302,
 	INTEL_GUC_ACTION_ENTER_S_STATE = 0x501,
 	INTEL_GUC_ACTION_EXIT_S_STATE = 0x502,
@@ -556,7 +557,6 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_AUTHENTICATE_HUC = 0x4000,
 	INTEL_GUC_ACTION_REGISTER_COMMAND_TRANSPORT_BUFFER = 0x4505,
 	INTEL_GUC_ACTION_DEREGISTER_COMMAND_TRANSPORT_BUFFER = 0x4506,
-	INTEL_GUC_ACTION_UK_LOG_ENABLE_LOGGING = 0x0E000,
 	INTEL_GUC_ACTION_LIMIT
 };
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index 2cf2d3314f62..caed0d57e704 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -226,7 +226,7 @@ static void guc_read_update_log_buffer(struct intel_guc_log *log)
 
 	mutex_lock(&log->relay.lock);
 
-	if (WARN_ON(!intel_guc_log_relay_enabled(log)))
+	if (WARN_ON(!intel_guc_log_relay_created(log)))
 		goto out_unlock;
 
 	/* Get the pointer to shared GuC log buffer */
@@ -361,6 +361,7 @@ void intel_guc_log_init_early(struct intel_guc_log *log)
 {
 	mutex_init(&log->relay.lock);
 	INIT_WORK(&log->relay.flush_work, capture_logs_work);
+	log->relay.started = false;
 }
 
 static int guc_log_relay_create(struct intel_guc_log *log)
@@ -546,7 +547,7 @@ out_unlock:
 	return ret;
 }
 
-bool intel_guc_log_relay_enabled(const struct intel_guc_log *log)
+bool intel_guc_log_relay_created(const struct intel_guc_log *log)
 {
 	return log->relay.buf_addr;
 }
@@ -560,7 +561,7 @@ int intel_guc_log_relay_open(struct intel_guc_log *log)
 
 	mutex_lock(&log->relay.lock);
 
-	if (intel_guc_log_relay_enabled(log)) {
+	if (intel_guc_log_relay_created(log)) {
 		ret = -EEXIST;
 		goto out_unlock;
 	}
@@ -585,6 +586,21 @@ int intel_guc_log_relay_open(struct intel_guc_log *log)
 
 	mutex_unlock(&log->relay.lock);
 
+	return 0;
+
+out_relay:
+	guc_log_relay_destroy(log);
+out_unlock:
+	mutex_unlock(&log->relay.lock);
+
+	return ret;
+}
+
+int intel_guc_log_relay_start(struct intel_guc_log *log)
+{
+	if (log->relay.started)
+		return -EEXIST;
+
 	guc_log_enable_flush_events(log);
 
 	/*
@@ -594,14 +610,9 @@ int intel_guc_log_relay_open(struct intel_guc_log *log)
 	 */
 	queue_work(system_highpri_wq, &log->relay.flush_work);
 
-	return 0;
-
-out_relay:
-	guc_log_relay_destroy(log);
-out_unlock:
-	mutex_unlock(&log->relay.lock);
+	log->relay.started = true;
 
-	return ret;
+	return 0;
 }
 
 void intel_guc_log_relay_flush(struct intel_guc_log *log)
@@ -609,6 +620,9 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 	struct intel_guc *guc = log_to_guc(log);
 	intel_wakeref_t wakeref;
 
+	if (!log->relay.started)
+		return;
+
 	/*
 	 * Before initiating the forceful flush, wait for any pending/ongoing
 	 * flush to complete otherwise forceful flush may not actually happen.
@@ -622,18 +636,33 @@ void intel_guc_log_relay_flush(struct intel_guc_log *log)
 	guc_log_capture_logs(log);
 }
 
-void intel_guc_log_relay_close(struct intel_guc_log *log)
+/*
+ * Stops the relay log. Called from intel_guc_log_relay_close(), so no
+ * possibility of race with start/flush since relay_write cannot race
+ * relay_close.
+ */
+static void guc_log_relay_stop(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *i915 = guc_to_gt(guc)->i915;
 
+	if (!log->relay.started)
+		return;
+
 	guc_log_disable_flush_events(log);
 	intel_synchronize_irq(i915);
 
 	flush_work(&log->relay.flush_work);
 
+	log->relay.started = false;
+}
+
+void intel_guc_log_relay_close(struct intel_guc_log *log)
+{
+	guc_log_relay_stop(log);
+
 	mutex_lock(&log->relay.lock);
-	GEM_BUG_ON(!intel_guc_log_relay_enabled(log));
+	GEM_BUG_ON(!intel_guc_log_relay_created(log));
 	guc_log_unmap(log);
 	guc_log_relay_destroy(log);
 	mutex_unlock(&log->relay.lock);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
index 6f764879acb1..c252c022c5fc 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.h
@@ -47,6 +47,7 @@ struct intel_guc_log {
 	struct i915_vma *vma;
 	struct {
 		void *buf_addr;
+		bool started;
 		struct work_struct flush_work;
 		struct rchan *channel;
 		struct mutex lock;
@@ -65,8 +66,9 @@ int intel_guc_log_create(struct intel_guc_log *log);
 void intel_guc_log_destroy(struct intel_guc_log *log);
 
 int intel_guc_log_set_level(struct intel_guc_log *log, u32 level);
-bool intel_guc_log_relay_enabled(const struct intel_guc_log *log);
+bool intel_guc_log_relay_created(const struct intel_guc_log *log);
 int intel_guc_log_relay_open(struct intel_guc_log *log);
+int intel_guc_log_relay_start(struct intel_guc_log *log);
 void intel_guc_log_relay_flush(struct intel_guc_log *log);
 void intel_guc_log_relay_close(struct intel_guc_log *log);
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 009e54a3764f..2498c55e0ea5 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -6,12 +6,13 @@
 #include <linux/circ_buf.h>
 
 #include "gem/i915_gem_context.h"
-
 #include "gt/intel_context.h"
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_lrc_reg.h"
+#include "gt/intel_ring.h"
+
 #include "intel_guc_submission.h"
 
 #include "i915_drv.h"
@@ -1010,7 +1011,7 @@ void intel_guc_submission_fini(struct intel_guc *guc)
 
 static void guc_interrupts_capture(struct intel_gt *gt)
 {
-	struct intel_rps *rps = &gt->i915->gt_pm.rps;
+	struct intel_rps *rps = &gt->rps;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -1056,7 +1057,7 @@ static void guc_interrupts_capture(struct intel_gt *gt)
 
 static void guc_interrupts_release(struct intel_gt *gt)
 {
-	struct intel_rps *rps = &gt->i915->gt_pm.rps;
+	struct intel_rps *rps = &gt->rps;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -1125,7 +1126,7 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	enum intel_engine_id id;
 	int err;
 
-	err = i915_inject_load_error(gt->i915, -ENXIO);
+	err = i915_inject_probe_error(gt->i915, -ENXIO);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index 8be515c8d0f0..32a069841c14 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -63,7 +63,7 @@ static int intel_huc_rsa_data_create(struct intel_huc *huc)
 	void *vaddr;
 	int err;
 
-	err = i915_inject_load_error(gt->i915, -ENXIO);
+	err = i915_inject_probe_error(gt->i915, -ENXIO);
 	if (err)
 		return err;
 
@@ -161,7 +161,7 @@ int intel_huc_auth(struct intel_huc *huc)
 	if (!intel_uc_fw_is_loaded(&huc->fw))
 		return -ENOEXEC;
 
-	ret = i915_inject_load_error(gt->i915, -ENXIO);
+	ret = i915_inject_probe_error(gt->i915, -ENXIO);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index 3fdbc935d155..629b19377a29 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -20,7 +20,7 @@ static int __intel_uc_reset_hw(struct intel_uc *uc)
 	int ret;
 	u32 guc_status;
 
-	ret = i915_inject_load_error(gt->i915, -ENXIO);
+	ret = i915_inject_probe_error(gt->i915, -ENXIO);
 	if (ret)
 		return ret;
 
@@ -197,7 +197,7 @@ static int guc_enable_communication(struct intel_guc *guc)
 
 	GEM_BUG_ON(guc_communication_enabled(guc));
 
-	ret = i915_inject_load_error(i915, -ENXIO);
+	ret = i915_inject_probe_error(i915, -ENXIO);
 	if (ret)
 		return ret;
 
@@ -372,7 +372,7 @@ static int uc_init_wopcm(struct intel_uc *uc)
 	GEM_BUG_ON(!(size & GUC_WOPCM_SIZE_MASK));
 	GEM_BUG_ON(size & ~GUC_WOPCM_SIZE_MASK);
 
-	err = i915_inject_load_error(gt->i915, -ENXIO);
+	err = i915_inject_probe_error(gt->i915, -ENXIO);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index bb4889d2346d..66a30ab7044a 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -37,8 +37,13 @@ void intel_uc_fw_change_status(struct intel_uc_fw *uc_fw,
 /*
  * List of required GuC and HuC binaries per-platform.
  * Must be ordered based on platform + revid, from newer to older.
+ *
+ * TGL 35.2 is interface-compatible with 33.0 for previous Gens. The deltas
+ * between 33.0 and 35.2 are only related to new additions to support new Gen12
+ * features.
  */
 #define INTEL_UC_FIRMWARE_DEFS(fw_def, guc_def, huc_def) \
+	fw_def(TIGERLAKE,   0, guc_def(tgl, 35, 2, 0), huc_def(tgl,  7, 0, 3)) \
 	fw_def(ELKHARTLAKE, 0, guc_def(ehl, 33, 0, 4), huc_def(ehl,  9, 0, 0)) \
 	fw_def(ICELAKE,     0, guc_def(icl, 33, 0, 0), huc_def(icl,  9, 0, 0)) \
 	fw_def(COFFEELAKE,  5, guc_def(cml, 33, 0, 0), huc_def(cml,  4, 0, 0)) \
@@ -220,29 +225,31 @@ static void __force_fw_fetch_failures(struct intel_uc_fw *uc_fw,
 {
 	bool user = e == -EINVAL;
 
-	if (i915_inject_load_error(i915, e)) {
+	if (i915_inject_probe_error(i915, e)) {
 		/* non-existing blob */
 		uc_fw->path = "<invalid>";
 		uc_fw->user_overridden = user;
-	} else if (i915_inject_load_error(i915, e)) {
+	} else if (i915_inject_probe_error(i915, e)) {
 		/* require next major version */
 		uc_fw->major_ver_wanted += 1;
 		uc_fw->minor_ver_wanted = 0;
 		uc_fw->user_overridden = user;
-	} else if (i915_inject_load_error(i915, e)) {
+	} else if (i915_inject_probe_error(i915, e)) {
 		/* require next minor version */
 		uc_fw->minor_ver_wanted += 1;
 		uc_fw->user_overridden = user;
-	} else if (uc_fw->major_ver_wanted && i915_inject_load_error(i915, e)) {
+	} else if (uc_fw->major_ver_wanted &&
+		   i915_inject_probe_error(i915, e)) {
 		/* require prev major version */
 		uc_fw->major_ver_wanted -= 1;
 		uc_fw->minor_ver_wanted = 0;
 		uc_fw->user_overridden = user;
-	} else if (uc_fw->minor_ver_wanted && i915_inject_load_error(i915, e)) {
+	} else if (uc_fw->minor_ver_wanted &&
+		   i915_inject_probe_error(i915, e)) {
 		/* require prev minor version - hey, this should work! */
 		uc_fw->minor_ver_wanted -= 1;
 		uc_fw->user_overridden = user;
-	} else if (user && i915_inject_load_error(i915, e)) {
+	} else if (user && i915_inject_probe_error(i915, e)) {
 		/* officially unsupported platform */
 		uc_fw->major_ver_wanted = 0;
 		uc_fw->minor_ver_wanted = 0;
@@ -271,7 +278,7 @@ int intel_uc_fw_fetch(struct intel_uc_fw *uc_fw, struct drm_i915_private *i915)
 	GEM_BUG_ON(!i915->wopcm.size);
 	GEM_BUG_ON(!intel_uc_fw_is_enabled(uc_fw));
 
-	err = i915_inject_load_error(i915, -ENXIO);
+	err = i915_inject_probe_error(i915, -ENXIO);
 	if (err)
 		return err;
 
@@ -432,7 +439,7 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	u64 offset;
 	int ret;
 
-	ret = i915_inject_load_error(gt->i915, -ETIMEDOUT);
+	ret = i915_inject_probe_error(gt->i915, -ETIMEDOUT);
 	if (ret)
 		return ret;
 
@@ -493,7 +500,7 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	/* make sure the status was cleared the last time we reset the uc */
 	GEM_BUG_ON(intel_uc_fw_is_loaded(uc_fw));
 
-	err = i915_inject_load_error(gt->i915, -ENOEXEC);
+	err = i915_inject_probe_error(gt->i915, -ENOEXEC);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index e753b1e706e2..6a3ac8cde95d 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -35,7 +35,9 @@
  */
 
 #include <linux/slab.h>
+
 #include "i915_drv.h"
+#include "gt/intel_ring.h"
 #include "gvt.h"
 #include "i915_pvinfo.h"
 #include "trace.h"
diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 13044c027f27..a816aef6142b 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -152,6 +152,7 @@ static const struct drm_i915_gem_object_ops intel_vgpu_gem_ops = {
 static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 		struct intel_vgpu_fb_info *info)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_i915_gem_object *obj;
 
@@ -161,7 +162,7 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 
 	drm_gem_private_object_init(dev, &obj->base,
 		roundup(info->size, PAGE_SIZE));
-	i915_gem_object_init(obj, &intel_vgpu_gem_ops);
+	i915_gem_object_init(obj, &intel_vgpu_gem_ops, &lock_class);
 
 	obj->read_domains = I915_GEM_DOMAIN_GTT;
 	obj->write_domain = 0;
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 45a9124e53b6..bd12af349123 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -819,13 +819,16 @@ static int trigger_aux_channel_interrupt(struct intel_vgpu *vgpu,
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	enum intel_gvt_event_type event;
 
-	if (reg == _DPA_AUX_CH_CTL)
+	if (reg == i915_mmio_reg_offset(DP_AUX_CH_CTL(AUX_CH_A)))
 		event = AUX_CHANNEL_A;
-	else if (reg == _PCH_DPB_AUX_CH_CTL || reg == _DPB_AUX_CH_CTL)
+	else if (reg == _PCH_DPB_AUX_CH_CTL ||
+		 reg == i915_mmio_reg_offset(DP_AUX_CH_CTL(AUX_CH_B)))
 		event = AUX_CHANNEL_B;
-	else if (reg == _PCH_DPC_AUX_CH_CTL || reg == _DPC_AUX_CH_CTL)
+	else if (reg == _PCH_DPC_AUX_CH_CTL ||
+		 reg == i915_mmio_reg_offset(DP_AUX_CH_CTL(AUX_CH_C)))
 		event = AUX_CHANNEL_C;
-	else if (reg == _PCH_DPD_AUX_CH_CTL || reg == _DPD_AUX_CH_CTL)
+	else if (reg == _PCH_DPD_AUX_CH_CTL ||
+		 reg == i915_mmio_reg_offset(DP_AUX_CH_CTL(AUX_CH_D)))
 		event = AUX_CHANNEL_D;
 	else {
 		WARN_ON(true);
@@ -2872,11 +2875,11 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(FORCEWAKE_MEDIA_GEN9, D_SKL_PLUS, NULL, mul_force_wake_write);
 	MMIO_DH(FORCEWAKE_ACK_MEDIA_GEN9, D_SKL_PLUS, NULL, NULL);
 
-	MMIO_F(_MMIO(_DPB_AUX_CH_CTL), 6 * 4, 0, 0, 0, D_SKL_PLUS, NULL,
+	MMIO_F(DP_AUX_CH_CTL(AUX_CH_B), 6 * 4, 0, 0, 0, D_SKL_PLUS, NULL,
 						dp_aux_ch_ctl_mmio_write);
-	MMIO_F(_MMIO(_DPC_AUX_CH_CTL), 6 * 4, 0, 0, 0, D_SKL_PLUS, NULL,
+	MMIO_F(DP_AUX_CH_CTL(AUX_CH_C), 6 * 4, 0, 0, 0, D_SKL_PLUS, NULL,
 						dp_aux_ch_ctl_mmio_write);
-	MMIO_F(_MMIO(_DPD_AUX_CH_CTL), 6 * 4, 0, 0, 0, D_SKL_PLUS, NULL,
+	MMIO_F(DP_AUX_CH_CTL(AUX_CH_D), 6 * 4, 0, 0, 0, D_SKL_PLUS, NULL,
 						dp_aux_ch_ctl_mmio_write);
 
 	MMIO_D(HSW_PWR_WELL_CTL1, D_SKL_PLUS);
@@ -3417,6 +3420,10 @@ int intel_gvt_for_each_tracked_mmio(struct intel_gvt *gvt,
 	}
 
 	for (i = 0; i < gvt->mmio.num_mmio_block; i++, block++) {
+		/* pvinfo data doesn't come from hw mmio */
+		if (i915_mmio_reg_offset(block->offset) == VGT_PVINFO_PAGE)
+			continue;
+
 		for (j = 0; j < block->size; j += 4) {
 			ret = handler(gvt,
 				      i915_mmio_reg_offset(block->offset) + j,
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 4208e40445b1..aaf15916d29a 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -35,6 +35,7 @@
 
 #include "i915_drv.h"
 #include "gt/intel_context.h"
+#include "gt/intel_ring.h"
 #include "gvt.h"
 #include "trace.h"
 
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 36bb7639e82f..5b2a7d072ec9 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -38,6 +38,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_pm.h"
 #include "gt/intel_context.h"
+#include "gt/intel_ring.h"
 
 #include "i915_drv.h"
 #include "gvt.h"
@@ -194,7 +195,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 			return -EFAULT;
 		}
 
-		page = i915_gem_object_get_page(ctx_obj, LRC_HEADER_PAGES + i);
+		page = i915_gem_object_get_page(ctx_obj, i);
 		dst = kmap(page);
 		intel_gvt_hypervisor_read_gpa(vgpu, context_gpa, dst,
 				I915_GTT_PAGE_SIZE);
@@ -834,7 +835,7 @@ static void update_guest_context(struct intel_vgpu_workload *workload)
 			return;
 		}
 
-		page = i915_gem_object_get_page(ctx_obj, LRC_HEADER_PAGES + i);
+		page = i915_gem_object_get_page(ctx_obj, i);
 		src = kmap(page);
 		intel_gvt_hypervisor_write_gpa(vgpu, context_gpa, src,
 				I915_GTT_PAGE_SIZE);
@@ -1584,9 +1585,7 @@ intel_vgpu_create_workload(struct intel_vgpu *vgpu, int ring_id,
 	 */
 	if (list_empty(workload_q_head(vgpu, ring_id))) {
 		intel_runtime_pm_get(&dev_priv->runtime_pm);
-		mutex_lock(&vgpu->vgpu_lock);
 		ret = intel_gvt_scan_and_shadow_workload(workload);
-		mutex_unlock(&vgpu->vgpu_lock);
 		intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_active.c b/drivers/gpu/drm/i915/i915_active.c
index 7927b1a0c7a6..dca15ace88f6 100644
--- a/drivers/gpu/drm/i915/i915_active.c
+++ b/drivers/gpu/drm/i915/i915_active.c
@@ -7,6 +7,7 @@
 #include <linux/debugobjects.h>
 
 #include "gt/intel_engine_pm.h"
+#include "gt/intel_ring.h"
 
 #include "i915_drv.h"
 #include "i915_active.h"
@@ -90,14 +91,15 @@ static void debug_active_init(struct i915_active *ref)
 
 static void debug_active_activate(struct i915_active *ref)
 {
-	lockdep_assert_held(&ref->mutex);
+	spin_lock_irq(&ref->tree_lock);
 	if (!atomic_read(&ref->count)) /* before the first inc */
 		debug_object_activate(ref, &active_debug_desc);
+	spin_unlock_irq(&ref->tree_lock);
 }
 
 static void debug_active_deactivate(struct i915_active *ref)
 {
-	lockdep_assert_held(&ref->mutex);
+	lockdep_assert_held(&ref->tree_lock);
 	if (!atomic_read(&ref->count)) /* after the last dec */
 		debug_object_deactivate(ref, &active_debug_desc);
 }
@@ -127,29 +129,22 @@ __active_retire(struct i915_active *ref)
 {
 	struct active_node *it, *n;
 	struct rb_root root;
-	bool retire = false;
+	unsigned long flags;
 
-	lockdep_assert_held(&ref->mutex);
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	/* return the unused nodes to our slabcache -- flushing the allocator */
-	if (atomic_dec_and_test(&ref->count)) {
-		debug_active_deactivate(ref);
-		root = ref->tree;
-		ref->tree = RB_ROOT;
-		ref->cache = NULL;
-		retire = true;
-	}
-
-	mutex_unlock(&ref->mutex);
-	if (!retire)
+	if (!atomic_dec_and_lock_irqsave(&ref->count, &ref->tree_lock, flags))
 		return;
 
 	GEM_BUG_ON(rcu_access_pointer(ref->excl.fence));
-	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
-		GEM_BUG_ON(i915_active_fence_isset(&it->base));
-		kmem_cache_free(global.slab_cache, it);
-	}
+	debug_active_deactivate(ref);
+
+	root = ref->tree;
+	ref->tree = RB_ROOT;
+	ref->cache = NULL;
+
+	spin_unlock_irqrestore(&ref->tree_lock, flags);
 
 	/* After the final retire, the entire struct may be freed */
 	if (ref->retire)
@@ -157,6 +152,11 @@ __active_retire(struct i915_active *ref)
 
 	/* ... except if you wait on it, you must manage your own references! */
 	wake_up_var(ref);
+
+	rbtree_postorder_for_each_entry_safe(it, n, &root, node) {
+		GEM_BUG_ON(i915_active_fence_isset(&it->base));
+		kmem_cache_free(global.slab_cache, it);
+	}
 }
 
 static void
@@ -168,7 +168,6 @@ active_work(struct work_struct *wrk)
 	if (atomic_add_unless(&ref->count, -1, 1))
 		return;
 
-	mutex_lock(&ref->mutex);
 	__active_retire(ref);
 }
 
@@ -179,9 +178,7 @@ active_retire(struct i915_active *ref)
 	if (atomic_add_unless(&ref->count, -1, 1))
 		return;
 
-	/* If we are inside interrupt context (fence signaling), defer */
-	if (ref->flags & I915_ACTIVE_RETIRE_SLEEPS ||
-	    !mutex_trylock(&ref->mutex)) {
+	if (ref->flags & I915_ACTIVE_RETIRE_SLEEPS) {
 		queue_work(system_unbound_wq, &ref->work);
 		return;
 	}
@@ -226,7 +223,7 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 	if (!prealloc)
 		return NULL;
 
-	mutex_lock(&ref->mutex);
+	spin_lock_irq(&ref->tree_lock);
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	parent = NULL;
@@ -256,7 +253,7 @@ active_instance(struct i915_active *ref, struct intel_timeline *tl)
 
 out:
 	ref->cache = node;
-	mutex_unlock(&ref->mutex);
+	spin_unlock_irq(&ref->tree_lock);
 
 	BUILD_BUG_ON(offsetof(typeof(*node), base));
 	return &node->base;
@@ -277,8 +274,10 @@ void __i915_active_init(struct i915_active *ref,
 	if (bits & I915_ACTIVE_MAY_SLEEP)
 		ref->flags |= I915_ACTIVE_RETIRE_SLEEPS;
 
+	spin_lock_init(&ref->tree_lock);
 	ref->tree = RB_ROOT;
 	ref->cache = NULL;
+
 	init_llist_head(&ref->preallocated_barriers);
 	atomic_set(&ref->count, 0);
 	__mutex_init(&ref->mutex, "i915_active", key);
@@ -509,7 +508,7 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 	if (RB_EMPTY_ROOT(&ref->tree))
 		return NULL;
 
-	mutex_lock(&ref->mutex);
+	spin_lock_irq(&ref->tree_lock);
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
 	/*
@@ -574,7 +573,7 @@ static struct active_node *reuse_idle_barrier(struct i915_active *ref, u64 idx)
 			goto match;
 	}
 
-	mutex_unlock(&ref->mutex);
+	spin_unlock_irq(&ref->tree_lock);
 
 	return NULL;
 
@@ -582,7 +581,7 @@ match:
 	rb_erase(p, &ref->tree); /* Hide from waits and sibling allocations */
 	if (p == &ref->cache->node)
 		ref->cache = NULL;
-	mutex_unlock(&ref->mutex);
+	spin_unlock_irq(&ref->tree_lock);
 
 	return rb_entry(p, struct active_node, node);
 }
@@ -595,6 +594,7 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 	struct llist_node *pos, *next;
 	int err;
 
+	GEM_BUG_ON(i915_active_is_idle(ref));
 	GEM_BUG_ON(!llist_empty(&ref->preallocated_barriers));
 
 	/*
@@ -662,6 +662,7 @@ unwind:
 void i915_active_acquire_barrier(struct i915_active *ref)
 {
 	struct llist_node *pos, *next;
+	unsigned long flags;
 
 	GEM_BUG_ON(i915_active_is_idle(ref));
 
@@ -671,12 +672,13 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 	 * populated by i915_request_add_active_barriers() to point to the
 	 * request that will eventually release them.
 	 */
-	mutex_lock_nested(&ref->mutex, SINGLE_DEPTH_NESTING);
 	llist_for_each_safe(pos, next, take_preallocated_barriers(ref)) {
 		struct active_node *node = barrier_from_ll(pos);
 		struct intel_engine_cs *engine = barrier_to_engine(node);
 		struct rb_node **p, *parent;
 
+		spin_lock_irqsave_nested(&ref->tree_lock, flags,
+					 SINGLE_DEPTH_NESTING);
 		parent = NULL;
 		p = &ref->tree.rb_node;
 		while (*p) {
@@ -692,12 +694,12 @@ void i915_active_acquire_barrier(struct i915_active *ref)
 		}
 		rb_link_node(&node->node, parent, p);
 		rb_insert_color(&node->node, &ref->tree);
+		spin_unlock_irqrestore(&ref->tree_lock, flags);
 
 		GEM_BUG_ON(!intel_engine_pm_is_awake(engine));
 		llist_add(barrier_to_ll(node), &engine->barrier_tasks);
 		intel_engine_pm_put(engine);
 	}
-	mutex_unlock(&ref->mutex);
 }
 
 void i915_request_add_active_barriers(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/i915_active.h b/drivers/gpu/drm/i915/i915_active.h
index 4f52fe6146d2..44859356ce97 100644
--- a/drivers/gpu/drm/i915/i915_active.h
+++ b/drivers/gpu/drm/i915/i915_active.h
@@ -214,4 +214,6 @@ int i915_active_acquire_preallocate_barrier(struct i915_active *ref,
 void i915_active_acquire_barrier(struct i915_active *ref);
 void i915_request_add_active_barriers(struct i915_request *rq);
 
+void i915_active_print(struct i915_active *ref, struct drm_printer *m);
+
 #endif /* _I915_ACTIVE_H_ */
diff --git a/drivers/gpu/drm/i915/i915_active_types.h b/drivers/gpu/drm/i915/i915_active_types.h
index d89a74c142c6..96aed0ee700a 100644
--- a/drivers/gpu/drm/i915/i915_active_types.h
+++ b/drivers/gpu/drm/i915/i915_active_types.h
@@ -48,6 +48,7 @@ struct i915_active {
 	atomic_t count;
 	struct mutex mutex;
 
+	spinlock_t tree_lock;
 	struct active_node *cache;
 	struct rb_root tree;
 
diff --git a/drivers/gpu/drm/i915/i915_cmd_parser.c b/drivers/gpu/drm/i915/i915_cmd_parser.c
index 24555102e198..f24096e27bef 100644
--- a/drivers/gpu/drm/i915/i915_cmd_parser.c
+++ b/drivers/gpu/drm/i915/i915_cmd_parser.c
@@ -53,13 +53,11 @@
  * granting userspace undue privileges. There are three categories of privilege.
  *
  * First, commands which are explicitly defined as privileged or which should
- * only be used by the kernel driver. The parser generally rejects such
- * commands, though it may allow some from the drm master process.
+ * only be used by the kernel driver. The parser rejects such commands
  *
  * Second, commands which access registers. To support correct/enhanced
  * userspace functionality, particularly certain OpenGL extensions, the parser
- * provides a whitelist of registers which userspace may safely access (for both
- * normal and drm master processes).
+ * provides a whitelist of registers which userspace may safely access
  *
  * Third, commands which access privileged memory (i.e. GGTT, HWS page, etc).
  * The parser always rejects such commands.
@@ -84,9 +82,9 @@
  * in the per-engine command tables.
  *
  * Other command table entries map fairly directly to high level categories
- * mentioned above: rejected, master-only, register whitelist. The parser
- * implements a number of checks, including the privileged memory checks, via a
- * general bitmasking mechanism.
+ * mentioned above: rejected, register whitelist. The parser implements a number
+ * of checks, including the privileged memory checks, via a general bitmasking
+ * mechanism.
  */
 
 /*
@@ -104,8 +102,6 @@ struct drm_i915_cmd_descriptor {
 	 * CMD_DESC_REJECT: The command is never allowed
 	 * CMD_DESC_REGISTER: The command should be checked against the
 	 *                    register whitelist for the appropriate ring
-	 * CMD_DESC_MASTER: The command is allowed if the submitting process
-	 *                  is the DRM master
 	 */
 	u32 flags;
 #define CMD_DESC_FIXED    (1<<0)
@@ -113,7 +109,6 @@ struct drm_i915_cmd_descriptor {
 #define CMD_DESC_REJECT   (1<<2)
 #define CMD_DESC_REGISTER (1<<3)
 #define CMD_DESC_BITMASK  (1<<4)
-#define CMD_DESC_MASTER   (1<<5)
 
 	/*
 	 * The command's unique identification bits and the bitmask to get them.
@@ -194,7 +189,7 @@ struct drm_i915_cmd_table {
 #define CMD(op, opm, f, lm, fl, ...)				\
 	{							\
 		.flags = (fl) | ((f) ? CMD_DESC_FIXED : 0),	\
-		.cmd = { (op), ~0u << (opm) },			\
+		.cmd = { (op & ~0u << (opm)), ~0u << (opm) },	\
 		.length = { (lm) },				\
 		__VA_ARGS__					\
 	}
@@ -209,14 +204,13 @@ struct drm_i915_cmd_table {
 #define R CMD_DESC_REJECT
 #define W CMD_DESC_REGISTER
 #define B CMD_DESC_BITMASK
-#define M CMD_DESC_MASTER
 
 /*            Command                          Mask   Fixed Len   Action
 	      ---------------------------------------------------------- */
-static const struct drm_i915_cmd_descriptor common_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_common_cmds[] = {
 	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
 	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      R  ),
-	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      M  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      R  ),
 	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
 	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
 	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
@@ -246,7 +240,7 @@ static const struct drm_i915_cmd_descriptor common_cmds[] = {
 	CMD(  MI_BATCH_BUFFER_START,            SMI,   !F,  0xFF,   S  ),
 };
 
-static const struct drm_i915_cmd_descriptor render_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_render_cmds[] = {
 	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_PREDICATE,                     SMI,    F,  1,      S  ),
@@ -313,7 +307,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  MI_URB_ATOMIC_ALLOC,              SMI,    F,  1,      S  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_RS_CONTEXT,                    SMI,    F,  1,      S  ),
-	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_REGISTER_REG,             SMI,   !F,  0xFF,   W,
 	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
@@ -330,7 +324,7 @@ static const struct drm_i915_cmd_descriptor hsw_render_cmds[] = {
 	CMD(  GFX_OP_3DSTATE_BINDING_TABLE_EDIT_PS,  S3D,   !F,  0x1FF,  S  ),
 };
 
-static const struct drm_i915_cmd_descriptor video_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_video_cmds[] = {
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
@@ -374,7 +368,7 @@ static const struct drm_i915_cmd_descriptor video_cmds[] = {
 	CMD(  MFX_WAIT,                         SMFX,   F,  1,      S  ),
 };
 
-static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_vecs_cmds[] = {
 	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      R  ),
 	CMD(  MI_SET_APPID,                     SMI,    F,  1,      S  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0xFF,   B,
@@ -412,7 +406,7 @@ static const struct drm_i915_cmd_descriptor vecs_cmds[] = {
 	      }},						       ),
 };
 
-static const struct drm_i915_cmd_descriptor blt_cmds[] = {
+static const struct drm_i915_cmd_descriptor gen7_blt_cmds[] = {
 	CMD(  MI_DISPLAY_FLIP,                  SMI,   !F,  0xFF,   R  ),
 	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  B,
 	      .bits = {{
@@ -446,10 +440,64 @@ static const struct drm_i915_cmd_descriptor blt_cmds[] = {
 };
 
 static const struct drm_i915_cmd_descriptor hsw_blt_cmds[] = {
-	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   M  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   R  ),
 	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   R  ),
 };
 
+/*
+ * For Gen9 we can still rely on the h/w to enforce cmd security, and only
+ * need to re-enforce the register access checks. We therefore only need to
+ * teach the cmdparser how to find the end of each command, and identify
+ * register accesses. The table doesn't need to reject any commands, and so
+ * the only commands listed here are:
+ *   1) Those that touch registers
+ *   2) Those that do not have the default 8-bit length
+ *
+ * Note that the default MI length mask chosen for this table is 0xFF, not
+ * the 0x3F used on older devices. This is because the vast majority of MI
+ * cmds on Gen9 use a standard 8-bit Length field.
+ * All the Gen9 blitter instructions are standard 0xFF length mask, and
+ * none allow access to non-general registers, so in fact no BLT cmds are
+ * included in the table at all.
+ *
+ */
+static const struct drm_i915_cmd_descriptor gen9_blt_cmds[] = {
+	CMD(  MI_NOOP,                          SMI,    F,  1,      S  ),
+	CMD(  MI_USER_INTERRUPT,                SMI,    F,  1,      S  ),
+	CMD(  MI_WAIT_FOR_EVENT,                SMI,    F,  1,      S  ),
+	CMD(  MI_FLUSH,                         SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_CHECK,                     SMI,    F,  1,      S  ),
+	CMD(  MI_REPORT_HEAD,                   SMI,    F,  1,      S  ),
+	CMD(  MI_ARB_ON_OFF,                    SMI,    F,  1,      S  ),
+	CMD(  MI_SUSPEND_FLUSH,                 SMI,    F,  1,      S  ),
+	CMD(  MI_LOAD_SCAN_LINES_INCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_SCAN_LINES_EXCL,          SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_STORE_DWORD_IMM,               SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_LOAD_REGISTER_IMM(1),          SMI,   !F,  0xFF,   W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 2 }    ),
+	CMD(  MI_UPDATE_GTT,                    SMI,   !F,  0x3FF,  S  ),
+	CMD(  MI_STORE_REGISTER_MEM_GEN8,       SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_FLUSH_DW,                      SMI,   !F,  0x3F,   S  ),
+	CMD(  MI_LOAD_REGISTER_MEM_GEN8,        SMI,    F,  4,      W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC }               ),
+	CMD(  MI_LOAD_REGISTER_REG,             SMI,    !F,  0xFF,  W,
+	      .reg = { .offset = 1, .mask = 0x007FFFFC, .step = 1 }    ),
+
+	/*
+	 * We allow BB_START but apply further checks. We just sanitize the
+	 * basic fields here.
+	 */
+#define MI_BB_START_OPERAND_MASK   GENMASK(SMI-1, 0)
+#define MI_BB_START_OPERAND_EXPECT (MI_BATCH_PPGTT_HSW | 1)
+	CMD(  MI_BATCH_BUFFER_START_GEN8,       SMI,    !F,  0xFF,  B,
+	      .bits = {{
+			.offset = 0,
+			.mask = MI_BB_START_OPERAND_MASK,
+			.expected = MI_BB_START_OPERAND_EXPECT,
+	      }},						       ),
+};
+
 static const struct drm_i915_cmd_descriptor noop_desc =
 	CMD(MI_NOOP, SMI, F, 1, S);
 
@@ -463,40 +511,44 @@ static const struct drm_i915_cmd_descriptor noop_desc =
 #undef R
 #undef W
 #undef B
-#undef M
 
-static const struct drm_i915_cmd_table gen7_render_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ render_cmds, ARRAY_SIZE(render_cmds) },
+static const struct drm_i915_cmd_table gen7_render_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_render_ring_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ render_cmds, ARRAY_SIZE(render_cmds) },
+static const struct drm_i915_cmd_table hsw_render_ring_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_render_cmds, ARRAY_SIZE(gen7_render_cmds) },
 	{ hsw_render_cmds, ARRAY_SIZE(hsw_render_cmds) },
 };
 
-static const struct drm_i915_cmd_table gen7_video_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ video_cmds, ARRAY_SIZE(video_cmds) },
+static const struct drm_i915_cmd_table gen7_video_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_video_cmds, ARRAY_SIZE(gen7_video_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_vebox_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ vecs_cmds, ARRAY_SIZE(vecs_cmds) },
+static const struct drm_i915_cmd_table hsw_vebox_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_vecs_cmds, ARRAY_SIZE(gen7_vecs_cmds) },
 };
 
-static const struct drm_i915_cmd_table gen7_blt_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+static const struct drm_i915_cmd_table gen7_blt_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
 };
 
-static const struct drm_i915_cmd_table hsw_blt_ring_cmds[] = {
-	{ common_cmds, ARRAY_SIZE(common_cmds) },
-	{ blt_cmds, ARRAY_SIZE(blt_cmds) },
+static const struct drm_i915_cmd_table hsw_blt_ring_cmd_table[] = {
+	{ gen7_common_cmds, ARRAY_SIZE(gen7_common_cmds) },
+	{ gen7_blt_cmds, ARRAY_SIZE(gen7_blt_cmds) },
 	{ hsw_blt_cmds, ARRAY_SIZE(hsw_blt_cmds) },
 };
 
+static const struct drm_i915_cmd_table gen9_blt_cmd_table[] = {
+	{ gen9_blt_cmds, ARRAY_SIZE(gen9_blt_cmds) },
+};
+
+
 /*
  * Register whitelists, sorted by increasing register offset.
  */
@@ -612,17 +664,27 @@ static const struct drm_i915_reg_descriptor gen7_blt_regs[] = {
 	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
 };
 
-static const struct drm_i915_reg_descriptor ivb_master_regs[] = {
-	REG32(FORCEWAKE_MT),
-	REG32(DERRMR),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_A)),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_B)),
-	REG32(GEN7_PIPE_DE_LOAD_SL(PIPE_C)),
-};
-
-static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
-	REG32(FORCEWAKE_MT),
-	REG32(DERRMR),
+static const struct drm_i915_reg_descriptor gen9_blt_regs[] = {
+	REG64_IDX(RING_TIMESTAMP, RENDER_RING_BASE),
+	REG64_IDX(RING_TIMESTAMP, BSD_RING_BASE),
+	REG32(BCS_SWCTRL),
+	REG64_IDX(RING_TIMESTAMP, BLT_RING_BASE),
+	REG64_IDX(BCS_GPR, 0),
+	REG64_IDX(BCS_GPR, 1),
+	REG64_IDX(BCS_GPR, 2),
+	REG64_IDX(BCS_GPR, 3),
+	REG64_IDX(BCS_GPR, 4),
+	REG64_IDX(BCS_GPR, 5),
+	REG64_IDX(BCS_GPR, 6),
+	REG64_IDX(BCS_GPR, 7),
+	REG64_IDX(BCS_GPR, 8),
+	REG64_IDX(BCS_GPR, 9),
+	REG64_IDX(BCS_GPR, 10),
+	REG64_IDX(BCS_GPR, 11),
+	REG64_IDX(BCS_GPR, 12),
+	REG64_IDX(BCS_GPR, 13),
+	REG64_IDX(BCS_GPR, 14),
+	REG64_IDX(BCS_GPR, 15),
 };
 
 #undef REG64
@@ -631,28 +693,27 @@ static const struct drm_i915_reg_descriptor hsw_master_regs[] = {
 struct drm_i915_reg_table {
 	const struct drm_i915_reg_descriptor *regs;
 	int num_regs;
-	bool master;
 };
 
 static const struct drm_i915_reg_table ivb_render_reg_tables[] = {
-	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
-	{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
+	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
 };
 
 static const struct drm_i915_reg_table ivb_blt_reg_tables[] = {
-	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
-	{ ivb_master_regs, ARRAY_SIZE(ivb_master_regs), true },
+	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
 };
 
 static const struct drm_i915_reg_table hsw_render_reg_tables[] = {
-	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs), false },
-	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs), false },
-	{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+	{ gen7_render_regs, ARRAY_SIZE(gen7_render_regs) },
+	{ hsw_render_regs, ARRAY_SIZE(hsw_render_regs) },
 };
 
 static const struct drm_i915_reg_table hsw_blt_reg_tables[] = {
-	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs), false },
-	{ hsw_master_regs, ARRAY_SIZE(hsw_master_regs), true },
+	{ gen7_blt_regs, ARRAY_SIZE(gen7_blt_regs) },
+};
+
+static const struct drm_i915_reg_table gen9_blt_reg_tables[] = {
+	{ gen9_blt_regs, ARRAY_SIZE(gen9_blt_regs) },
 };
 
 static u32 gen7_render_get_cmd_length_mask(u32 cmd_header)
@@ -710,6 +771,17 @@ static u32 gen7_blt_get_cmd_length_mask(u32 cmd_header)
 	return 0;
 }
 
+static u32 gen9_blt_get_cmd_length_mask(u32 cmd_header)
+{
+	u32 client = cmd_header >> INSTR_CLIENT_SHIFT;
+
+	if (client == INSTR_MI_CLIENT || client == INSTR_BC_CLIENT)
+		return 0xFF;
+
+	DRM_DEBUG_DRIVER("CMD: Abnormal blt cmd length! 0x%08X\n", cmd_header);
+	return 0;
+}
+
 static bool validate_cmds_sorted(const struct intel_engine_cs *engine,
 				 const struct drm_i915_cmd_table *cmd_tables,
 				 int cmd_table_count)
@@ -867,18 +939,19 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 	int cmd_table_count;
 	int ret;
 
-	if (!IS_GEN(engine->i915, 7))
+	if (!IS_GEN(engine->i915, 7) && !(IS_GEN(engine->i915, 9) &&
+					  engine->class == COPY_ENGINE_CLASS))
 		return;
 
 	switch (engine->class) {
 	case RENDER_CLASS:
 		if (IS_HASWELL(engine->i915)) {
-			cmd_tables = hsw_render_ring_cmds;
+			cmd_tables = hsw_render_ring_cmd_table;
 			cmd_table_count =
-				ARRAY_SIZE(hsw_render_ring_cmds);
+				ARRAY_SIZE(hsw_render_ring_cmd_table);
 		} else {
-			cmd_tables = gen7_render_cmds;
-			cmd_table_count = ARRAY_SIZE(gen7_render_cmds);
+			cmd_tables = gen7_render_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen7_render_cmd_table);
 		}
 
 		if (IS_HASWELL(engine->i915)) {
@@ -888,36 +961,46 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 			engine->reg_tables = ivb_render_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_render_reg_tables);
 		}
-
 		engine->get_cmd_length_mask = gen7_render_get_cmd_length_mask;
 		break;
 	case VIDEO_DECODE_CLASS:
-		cmd_tables = gen7_video_cmds;
-		cmd_table_count = ARRAY_SIZE(gen7_video_cmds);
+		cmd_tables = gen7_video_cmd_table;
+		cmd_table_count = ARRAY_SIZE(gen7_video_cmd_table);
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
 	case COPY_ENGINE_CLASS:
-		if (IS_HASWELL(engine->i915)) {
-			cmd_tables = hsw_blt_ring_cmds;
-			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmds);
+		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
+		if (IS_GEN(engine->i915, 9)) {
+			cmd_tables = gen9_blt_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen9_blt_cmd_table);
+			engine->get_cmd_length_mask =
+				gen9_blt_get_cmd_length_mask;
+
+			/* BCS Engine unsafe without parser */
+			engine->flags |= I915_ENGINE_REQUIRES_CMD_PARSER;
+		} else if (IS_HASWELL(engine->i915)) {
+			cmd_tables = hsw_blt_ring_cmd_table;
+			cmd_table_count = ARRAY_SIZE(hsw_blt_ring_cmd_table);
 		} else {
-			cmd_tables = gen7_blt_cmds;
-			cmd_table_count = ARRAY_SIZE(gen7_blt_cmds);
+			cmd_tables = gen7_blt_cmd_table;
+			cmd_table_count = ARRAY_SIZE(gen7_blt_cmd_table);
 		}
 
-		if (IS_HASWELL(engine->i915)) {
+		if (IS_GEN(engine->i915, 9)) {
+			engine->reg_tables = gen9_blt_reg_tables;
+			engine->reg_table_count =
+				ARRAY_SIZE(gen9_blt_reg_tables);
+		} else if (IS_HASWELL(engine->i915)) {
 			engine->reg_tables = hsw_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(hsw_blt_reg_tables);
 		} else {
 			engine->reg_tables = ivb_blt_reg_tables;
 			engine->reg_table_count = ARRAY_SIZE(ivb_blt_reg_tables);
 		}
-
-		engine->get_cmd_length_mask = gen7_blt_get_cmd_length_mask;
 		break;
 	case VIDEO_ENHANCEMENT_CLASS:
-		cmd_tables = hsw_vebox_cmds;
-		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmds);
+		cmd_tables = hsw_vebox_cmd_table;
+		cmd_table_count = ARRAY_SIZE(hsw_vebox_cmd_table);
 		/* VECS can use the same length_mask function as VCS */
 		engine->get_cmd_length_mask = gen7_bsd_get_cmd_length_mask;
 		break;
@@ -943,7 +1026,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
 		return;
 	}
 
-	engine->flags |= I915_ENGINE_NEEDS_CMD_PARSER;
+	engine->flags |= I915_ENGINE_USING_CMD_PARSER;
 }
 
 /**
@@ -955,7 +1038,7 @@ void intel_engine_init_cmd_parser(struct intel_engine_cs *engine)
  */
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine)
 {
-	if (!intel_engine_needs_cmd_parser(engine))
+	if (!intel_engine_using_cmd_parser(engine))
 		return;
 
 	fini_hash_table(engine);
@@ -1029,22 +1112,16 @@ __find_reg(const struct drm_i915_reg_descriptor *table, int count, u32 addr)
 }
 
 static const struct drm_i915_reg_descriptor *
-find_reg(const struct intel_engine_cs *engine, bool is_master, u32 addr)
+find_reg(const struct intel_engine_cs *engine, u32 addr)
 {
 	const struct drm_i915_reg_table *table = engine->reg_tables;
+	const struct drm_i915_reg_descriptor *reg = NULL;
 	int count = engine->reg_table_count;
 
-	for (; count > 0; ++table, --count) {
-		if (!table->master || is_master) {
-			const struct drm_i915_reg_descriptor *reg;
+	for (; !reg && (count > 0); ++table, --count)
+		reg = __find_reg(table->regs, table->num_regs, addr);
 
-			reg = __find_reg(table->regs, table->num_regs, addr);
-			if (reg != NULL)
-				return reg;
-		}
-	}
-
-	return NULL;
+	return reg;
 }
 
 /* Returns a vmap'd pointer to dst_obj, which the caller must unmap */
@@ -1128,8 +1205,7 @@ static u32 *copy_batch(struct drm_i915_gem_object *dst_obj,
 
 static bool check_cmd(const struct intel_engine_cs *engine,
 		      const struct drm_i915_cmd_descriptor *desc,
-		      const u32 *cmd, u32 length,
-		      const bool is_master)
+		      const u32 *cmd, u32 length)
 {
 	if (desc->flags & CMD_DESC_SKIP)
 		return true;
@@ -1139,12 +1215,6 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		return false;
 	}
 
-	if ((desc->flags & CMD_DESC_MASTER) && !is_master) {
-		DRM_DEBUG_DRIVER("CMD: Rejected master-only command: 0x%08X\n",
-				 *cmd);
-		return false;
-	}
-
 	if (desc->flags & CMD_DESC_REGISTER) {
 		/*
 		 * Get the distance between individual register offset
@@ -1158,7 +1228,7 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 		     offset += step) {
 			const u32 reg_addr = cmd[offset] & desc->reg.mask;
 			const struct drm_i915_reg_descriptor *reg =
-				find_reg(engine, is_master, reg_addr);
+				find_reg(engine, reg_addr);
 
 			if (!reg) {
 				DRM_DEBUG_DRIVER("CMD: Rejected register 0x%08X in command: 0x%08X (%s)\n",
@@ -1236,16 +1306,112 @@ static bool check_cmd(const struct intel_engine_cs *engine,
 	return true;
 }
 
+static int check_bbstart(const struct i915_gem_context *ctx,
+			 u32 *cmd, u32 offset, u32 length,
+			 u32 batch_len,
+			 u64 batch_start,
+			 u64 shadow_batch_start)
+{
+	u64 jump_offset, jump_target;
+	u32 target_cmd_offset, target_cmd_index;
+
+	/* For igt compatibility on older platforms */
+	if (CMDPARSER_USES_GGTT(ctx->i915)) {
+		DRM_DEBUG("CMD: Rejecting BB_START for ggtt based submission\n");
+		return -EACCES;
+	}
+
+	if (length != 3) {
+		DRM_DEBUG("CMD: Recursive BB_START with bad length(%u)\n",
+			  length);
+		return -EINVAL;
+	}
+
+	jump_target = *(u64*)(cmd+1);
+	jump_offset = jump_target - batch_start;
+
+	/*
+	 * Any underflow of jump_target is guaranteed to be outside the range
+	 * of a u32, so >= test catches both too large and too small
+	 */
+	if (jump_offset >= batch_len) {
+		DRM_DEBUG("CMD: BB_START to 0x%llx jumps out of BB\n",
+			  jump_target);
+		return -EINVAL;
+	}
+
+	/*
+	 * This cannot overflow a u32 because we already checked jump_offset
+	 * is within the BB, and the batch_len is a u32
+	 */
+	target_cmd_offset = lower_32_bits(jump_offset);
+	target_cmd_index = target_cmd_offset / sizeof(u32);
+
+	*(u64*)(cmd + 1) = shadow_batch_start + target_cmd_offset;
+
+	if (target_cmd_index == offset)
+		return 0;
+
+	if (ctx->jump_whitelist_cmds <= target_cmd_index) {
+		DRM_DEBUG("CMD: Rejecting BB_START - truncated whitelist array\n");
+		return -EINVAL;
+	} else if (!test_bit(target_cmd_index, ctx->jump_whitelist)) {
+		DRM_DEBUG("CMD: BB_START to 0x%llx not a previously executed cmd\n",
+			  jump_target);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void init_whitelist(struct i915_gem_context *ctx, u32 batch_len)
+{
+	const u32 batch_cmds = DIV_ROUND_UP(batch_len, sizeof(u32));
+	const u32 exact_size = BITS_TO_LONGS(batch_cmds);
+	u32 next_size = BITS_TO_LONGS(roundup_pow_of_two(batch_cmds));
+	unsigned long *next_whitelist;
+
+	if (CMDPARSER_USES_GGTT(ctx->i915))
+		return;
+
+	if (batch_cmds <= ctx->jump_whitelist_cmds) {
+		bitmap_zero(ctx->jump_whitelist, batch_cmds);
+		return;
+	}
+
+again:
+	next_whitelist = kcalloc(next_size, sizeof(long), GFP_KERNEL);
+	if (next_whitelist) {
+		kfree(ctx->jump_whitelist);
+		ctx->jump_whitelist = next_whitelist;
+		ctx->jump_whitelist_cmds =
+			next_size * BITS_PER_BYTE * sizeof(long);
+		return;
+	}
+
+	if (next_size > exact_size) {
+		next_size = exact_size;
+		goto again;
+	}
+
+	DRM_DEBUG("CMD: Failed to extend whitelist. BB_START may be disallowed\n");
+	bitmap_zero(ctx->jump_whitelist, ctx->jump_whitelist_cmds);
+
+	return;
+}
+
 #define LENGTH_BIAS 2
 
 /**
  * i915_parse_cmds() - parse a submitted batch buffer for privilege violations
+ * @ctx: the context in which the batch is to execute
  * @engine: the engine on which the batch is to execute
  * @batch_obj: the batch buffer in question
- * @shadow_batch_obj: copy of the batch buffer in question
+ * @batch_start: Canonical base address of batch
  * @batch_start_offset: byte offset in the batch at which execution starts
  * @batch_len: length of the commands in batch_obj
- * @is_master: is the submitting process the drm master?
+ * @shadow_batch_obj: copy of the batch buffer in question
+ * @shadow_batch_start: Canonical base address of shadow_batch_obj
  *
  * Parses the specified batch buffer looking for privilege violations as
  * described in the overview.
@@ -1253,14 +1419,17 @@ static bool check_cmd(const struct intel_engine_cs *engine,
  * Return: non-zero if the parser finds violations or otherwise fails; -EACCES
  * if the batch appears legal but should use hardware parsing
  */
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+
+int intel_engine_cmd_parser(struct i915_gem_context *ctx,
+			    struct intel_engine_cs *engine,
 			    struct drm_i915_gem_object *batch_obj,
-			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 batch_start,
 			    u32 batch_start_offset,
 			    u32 batch_len,
-			    bool is_master)
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 shadow_batch_start)
 {
-	u32 *cmd, *batch_end;
+	u32 *cmd, *batch_end, offset = 0;
 	struct drm_i915_cmd_descriptor default_desc = noop_desc;
 	const struct drm_i915_cmd_descriptor *desc = &default_desc;
 	bool needs_clflush_after = false;
@@ -1274,6 +1443,8 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 		return PTR_ERR(cmd);
 	}
 
+	init_whitelist(ctx, batch_len);
+
 	/*
 	 * We use the batch length as size because the shadow object is as
 	 * large or larger and copy_batch() will write MI_NOPs to the extra
@@ -1283,31 +1454,15 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 	do {
 		u32 length;
 
-		if (*cmd == MI_BATCH_BUFFER_END) {
-			if (needs_clflush_after) {
-				void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
-				drm_clflush_virt_range(ptr,
-						       (void *)(cmd + 1) - ptr);
-			}
+		if (*cmd == MI_BATCH_BUFFER_END)
 			break;
-		}
 
 		desc = find_cmd(engine, *cmd, desc, &default_desc);
 		if (!desc) {
 			DRM_DEBUG_DRIVER("CMD: Unrecognized command: 0x%08X\n",
 					 *cmd);
 			ret = -EINVAL;
-			break;
-		}
-
-		/*
-		 * If the batch buffer contains a chained batch, return an
-		 * error that tells the caller to abort and dispatch the
-		 * workload as a non-secure batch.
-		 */
-		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
-			ret = -EACCES;
-			break;
+			goto err;
 		}
 
 		if (desc->flags & CMD_DESC_FIXED)
@@ -1321,22 +1476,43 @@ int intel_engine_cmd_parser(struct intel_engine_cs *engine,
 					 length,
 					 batch_end - cmd);
 			ret = -EINVAL;
-			break;
+			goto err;
 		}
 
-		if (!check_cmd(engine, desc, cmd, length, is_master)) {
+		if (!check_cmd(engine, desc, cmd, length)) {
 			ret = -EACCES;
+			goto err;
+		}
+
+		if (desc->cmd.value == MI_BATCH_BUFFER_START) {
+			ret = check_bbstart(ctx, cmd, offset, length,
+					    batch_len, batch_start,
+					    shadow_batch_start);
+
+			if (ret)
+				goto err;
 			break;
 		}
 
+		if (ctx->jump_whitelist_cmds > offset)
+			set_bit(offset, ctx->jump_whitelist);
+
 		cmd += length;
+		offset += length;
 		if  (cmd >= batch_end) {
 			DRM_DEBUG_DRIVER("CMD: Got to the end of the buffer w/o a BBE cmd!\n");
 			ret = -EINVAL;
-			break;
+			goto err;
 		}
 	} while (1);
 
+	if (needs_clflush_after) {
+		void *ptr = page_mask_bits(shadow_batch_obj->mm.mapping);
+
+		drm_clflush_virt_range(ptr, (void *)(cmd + 1) - ptr);
+	}
+
+err:
 	i915_gem_object_unpin_map(shadow_batch_obj);
 	return ret;
 }
@@ -1357,7 +1533,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 
 	/* If the command parser is not enabled, report 0 - unsupported */
 	for_each_uabi_engine(engine, dev_priv) {
-		if (intel_engine_needs_cmd_parser(engine)) {
+		if (intel_engine_using_cmd_parser(engine)) {
 			active = true;
 			break;
 		}
@@ -1382,6 +1558,7 @@ int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv)
 	 *    the parser enabled.
 	 * 9. Don't whitelist or handle oacontrol specially, as ownership
 	 *    for oacontrol state is moving to i915-perf.
+	 * 10. Support for Gen9 BCS Parsing
 	 */
-	return 9;
+	return 10;
 }
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index ada57eee914a..8016484ebcd3 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -44,6 +44,7 @@
 #include "gt/intel_gt_requests.h"
 #include "gt/intel_reset.h"
 #include "gt/intel_rc6.h"
+#include "gt/intel_rps.h"
 #include "gt/uc/intel_guc_submission.h"
 
 #include "i915_debugfs.h"
@@ -791,7 +792,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	struct intel_uncore *uncore = &dev_priv->uncore;
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	intel_wakeref_t wakeref;
 	int ret = 0;
 
@@ -827,23 +828,23 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m, "DDR freq: %d MHz\n", dev_priv->mem_freq);
 
 		seq_printf(m, "actual GPU freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, (freq_sts >> 8) & 0xff));
+			   intel_gpu_freq(rps, (freq_sts >> 8) & 0xff));
 
 		seq_printf(m, "current GPU freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->cur_freq));
+			   intel_gpu_freq(rps, rps->cur_freq));
 
 		seq_printf(m, "max GPU freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->max_freq));
+			   intel_gpu_freq(rps, rps->max_freq));
 
 		seq_printf(m, "min GPU freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->min_freq));
+			   intel_gpu_freq(rps, rps->min_freq));
 
 		seq_printf(m, "idle GPU freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->idle_freq));
+			   intel_gpu_freq(rps, rps->idle_freq));
 
 		seq_printf(m,
 			   "efficient (RPe) frequency: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->efficient_freq));
+			   intel_gpu_freq(rps, rps->efficient_freq));
 	} else if (INTEL_GEN(dev_priv) >= 6) {
 		u32 rp_state_limits;
 		u32 gt_perf_status;
@@ -877,7 +878,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			else
 				reqf >>= 25;
 		}
-		reqf = intel_gpu_freq(dev_priv, reqf);
+		reqf = intel_gpu_freq(rps, reqf);
 
 		rpmodectl = I915_READ(GEN6_RP_CONTROL);
 		rpinclimit = I915_READ(GEN6_RP_UP_THRESHOLD);
@@ -890,8 +891,7 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
-		cagf = intel_gpu_freq(dev_priv,
-				      intel_get_cagf(dev_priv, rpstat));
+		cagf = intel_gpu_freq(rps, intel_get_cagf(rps, rpstat));
 
 		intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
 
@@ -968,37 +968,37 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
 			     INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Lowest (RPN) frequency: %dMHz\n",
-			   intel_gpu_freq(dev_priv, max_freq));
+			   intel_gpu_freq(rps, max_freq));
 
 		max_freq = (rp_state_cap & 0xff00) >> 8;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
 			     INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Nominal (RP1) frequency: %dMHz\n",
-			   intel_gpu_freq(dev_priv, max_freq));
+			   intel_gpu_freq(rps, max_freq));
 
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 16 :
 			    rp_state_cap >> 0) & 0xff;
 		max_freq *= (IS_GEN9_BC(dev_priv) ||
 			     INTEL_GEN(dev_priv) >= 10 ? GEN9_FREQ_SCALER : 1);
 		seq_printf(m, "Max non-overclocked (RP0) frequency: %dMHz\n",
-			   intel_gpu_freq(dev_priv, max_freq));
+			   intel_gpu_freq(rps, max_freq));
 		seq_printf(m, "Max overclocked frequency: %dMHz\n",
-			   intel_gpu_freq(dev_priv, rps->max_freq));
+			   intel_gpu_freq(rps, rps->max_freq));
 
 		seq_printf(m, "Current freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->cur_freq));
+			   intel_gpu_freq(rps, rps->cur_freq));
 		seq_printf(m, "Actual freq: %d MHz\n", cagf);
 		seq_printf(m, "Idle freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->idle_freq));
+			   intel_gpu_freq(rps, rps->idle_freq));
 		seq_printf(m, "Min freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->min_freq));
+			   intel_gpu_freq(rps, rps->min_freq));
 		seq_printf(m, "Boost freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->boost_freq));
+			   intel_gpu_freq(rps, rps->boost_freq));
 		seq_printf(m, "Max freq: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->max_freq));
+			   intel_gpu_freq(rps, rps->max_freq));
 		seq_printf(m,
 			   "efficient (RPe) frequency: %d MHz\n",
-			   intel_gpu_freq(dev_priv, rps->efficient_freq));
+			   intel_gpu_freq(rps, rps->efficient_freq));
 	} else {
 		seq_puts(m, "no P-state info available\n");
 	}
@@ -1011,92 +1011,6 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 	return ret;
 }
 
-static void i915_instdone_info(struct drm_i915_private *dev_priv,
-			       struct seq_file *m,
-			       struct intel_instdone *instdone)
-{
-	const struct sseu_dev_info *sseu = &RUNTIME_INFO(dev_priv)->sseu;
-	int slice;
-	int subslice;
-
-	seq_printf(m, "\t\tINSTDONE: 0x%08x\n",
-		   instdone->instdone);
-
-	if (INTEL_GEN(dev_priv) <= 3)
-		return;
-
-	seq_printf(m, "\t\tSC_INSTDONE: 0x%08x\n",
-		   instdone->slice_common);
-
-	if (INTEL_GEN(dev_priv) <= 6)
-		return;
-
-	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
-		seq_printf(m, "\t\tSAMPLER_INSTDONE[%d][%d]: 0x%08x\n",
-			   slice, subslice, instdone->sampler[slice][subslice]);
-
-	for_each_instdone_slice_subslice(dev_priv, sseu, slice, subslice)
-		seq_printf(m, "\t\tROW_INSTDONE[%d][%d]: 0x%08x\n",
-			   slice, subslice, instdone->row[slice][subslice]);
-}
-
-static int i915_hangcheck_info(struct seq_file *m, void *unused)
-{
-	struct drm_i915_private *i915 = node_to_i915(m->private);
-	struct intel_gt *gt = &i915->gt;
-	struct intel_engine_cs *engine;
-	intel_wakeref_t wakeref;
-	enum intel_engine_id id;
-
-	seq_printf(m, "Reset flags: %lx\n", gt->reset.flags);
-	if (test_bit(I915_WEDGED, &gt->reset.flags))
-		seq_puts(m, "\tWedged\n");
-	if (test_bit(I915_RESET_BACKOFF, &gt->reset.flags))
-		seq_puts(m, "\tDevice (global) reset in progress\n");
-
-	if (!i915_modparams.enable_hangcheck) {
-		seq_puts(m, "Hangcheck disabled\n");
-		return 0;
-	}
-
-	if (timer_pending(&gt->hangcheck.work.timer))
-		seq_printf(m, "Hangcheck active, timer fires in %dms\n",
-			   jiffies_to_msecs(gt->hangcheck.work.timer.expires -
-					    jiffies));
-	else if (delayed_work_pending(&gt->hangcheck.work))
-		seq_puts(m, "Hangcheck active, work pending\n");
-	else
-		seq_puts(m, "Hangcheck inactive\n");
-
-	seq_printf(m, "GT active? %s\n", yesno(gt->awake));
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-		for_each_engine(engine, i915, id) {
-			struct intel_instdone instdone;
-
-			seq_printf(m, "%s: %d ms ago\n",
-				   engine->name,
-				   jiffies_to_msecs(jiffies -
-						    engine->hangcheck.action_timestamp));
-
-			seq_printf(m, "\tACTHD = 0x%08llx [current 0x%08llx]\n",
-				   (long long)engine->hangcheck.acthd,
-				   intel_engine_get_active_head(engine));
-
-			intel_engine_get_instdone(engine, &instdone);
-
-			seq_puts(m, "\tinstdone read =\n");
-			i915_instdone_info(i915, m, &instdone);
-
-			seq_puts(m, "\tinstdone accu =\n");
-			i915_instdone_info(i915, m,
-					   &engine->hangcheck.instdone);
-		}
-	}
-
-	return 0;
-}
-
 static int ironlake_drpc_info(struct seq_file *m)
 {
 	struct drm_i915_private *i915 = node_to_i915(m->private);
@@ -1461,7 +1375,7 @@ static int i915_sr_status(struct seq_file *m, void *unused)
 static int i915_ring_freq_table(struct seq_file *m, void *unused)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	unsigned int max_gpu_freq, min_gpu_freq;
 	intel_wakeref_t wakeref;
 	int gpu_freq, ia_freq;
@@ -1486,10 +1400,11 @@ static int i915_ring_freq_table(struct seq_file *m, void *unused)
 				       GEN6_PCODE_READ_MIN_FREQ_TABLE,
 				       &ia_freq, NULL);
 		seq_printf(m, "%d\t\t%d\t\t\t\t%d\n",
-			   intel_gpu_freq(dev_priv, (gpu_freq *
-						     (IS_GEN9_BC(dev_priv) ||
-						      INTEL_GEN(dev_priv) >= 10 ?
-						      GEN9_FREQ_SCALER : 1))),
+			   intel_gpu_freq(rps,
+					  (gpu_freq *
+					   (IS_GEN9_BC(dev_priv) ||
+					    INTEL_GEN(dev_priv) >= 10 ?
+					    GEN9_FREQ_SCALER : 1))),
 			   ((ia_freq >> 0) & 0xff) * 100,
 			   ((ia_freq >> 8) & 0xff) * 100);
 	}
@@ -1717,7 +1632,7 @@ static const char *rps_power_to_str(unsigned int power)
 static int i915_rps_boost_info(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	u32 act_freq = rps->cur_freq;
 	intel_wakeref_t wakeref;
 
@@ -1729,7 +1644,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 			vlv_punit_put(dev_priv);
 			act_freq = (act_freq >> 8) & 0xff;
 		} else {
-			act_freq = intel_get_cagf(dev_priv,
+			act_freq = intel_get_cagf(rps,
 						  I915_READ(GEN6_RPSTAT1));
 		}
 	}
@@ -1740,17 +1655,17 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 		   atomic_read(&rps->num_waiters));
 	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
 	seq_printf(m, "Frequency requested %d, actual %d\n",
-		   intel_gpu_freq(dev_priv, rps->cur_freq),
-		   intel_gpu_freq(dev_priv, act_freq));
+		   intel_gpu_freq(rps, rps->cur_freq),
+		   intel_gpu_freq(rps, act_freq));
 	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
-		   intel_gpu_freq(dev_priv, rps->min_freq),
-		   intel_gpu_freq(dev_priv, rps->min_freq_softlimit),
-		   intel_gpu_freq(dev_priv, rps->max_freq_softlimit),
-		   intel_gpu_freq(dev_priv, rps->max_freq));
+		   intel_gpu_freq(rps, rps->min_freq),
+		   intel_gpu_freq(rps, rps->min_freq_softlimit),
+		   intel_gpu_freq(rps, rps->max_freq_softlimit),
+		   intel_gpu_freq(rps, rps->max_freq));
 	seq_printf(m, "  idle:%d, efficient:%d, boost:%d\n",
-		   intel_gpu_freq(dev_priv, rps->idle_freq),
-		   intel_gpu_freq(dev_priv, rps->efficient_freq),
-		   intel_gpu_freq(dev_priv, rps->boost_freq));
+		   intel_gpu_freq(rps, rps->idle_freq),
+		   intel_gpu_freq(rps, rps->efficient_freq),
+		   intel_gpu_freq(rps, rps->boost_freq));
 
 	seq_printf(m, "Wait boosts: %d\n", atomic_read(&rps->boosts));
 
@@ -1866,8 +1781,8 @@ static void i915_guc_log_info(struct seq_file *m,
 	struct intel_guc_log *log = &dev_priv->gt.uc.guc.log;
 	enum guc_log_buffer_type type;
 
-	if (!intel_guc_log_relay_enabled(log)) {
-		seq_puts(m, "GuC log relay disabled\n");
+	if (!intel_guc_log_relay_created(log)) {
+		seq_puts(m, "GuC log relay not created\n");
 		return;
 	}
 
@@ -2054,9 +1969,23 @@ i915_guc_log_relay_write(struct file *filp,
 			 loff_t *ppos)
 {
 	struct intel_guc_log *log = filp->private_data;
+	int val;
+	int ret;
 
-	intel_guc_log_relay_flush(log);
-	return cnt;
+	ret = kstrtoint_from_user(ubuf, cnt, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Enable and start the guc log relay on value of 1.
+	 * Flush log relay for any other value.
+	 */
+	if (val == 1)
+		ret = intel_guc_log_relay_start(log);
+	else
+		intel_guc_log_relay_flush(log);
+
+	return ret ?: cnt;
 }
 
 static int i915_guc_log_relay_release(struct inode *inode, struct file *file)
@@ -2194,8 +2123,12 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 		status = "disabled";
 	seq_printf(m, "PSR mode: %s\n", status);
 
-	if (!psr->enabled)
+	if (!psr->enabled) {
+		seq_printf(m, "PSR sink not reliable: %s\n",
+			   yesno(psr->sink_not_reliable));
+
 		goto unlock;
+	}
 
 	if (psr->psr2_enabled) {
 		val = I915_READ(EDP_PSR2_CTL(dev_priv->psr.transcoder));
@@ -3648,17 +3581,11 @@ i915_drop_caches_get(void *data, u64 *val)
 
 	return 0;
 }
-
 static int
-i915_drop_caches_set(void *data, u64 val)
+gt_drop_caches(struct intel_gt *gt, u64 val)
 {
-	struct drm_i915_private *i915 = data;
-	struct intel_gt *gt = &i915->gt;
 	int ret;
 
-	DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n",
-		  val, val & DROP_ALL);
-
 	if (val & DROP_RESET_ACTIVE &&
 	    wait_for(intel_engines_are_idle(gt), I915_IDLE_ENGINES_TIMEOUT))
 		intel_gt_set_wedged(gt);
@@ -3681,6 +3608,22 @@ i915_drop_caches_set(void *data, u64 val)
 	if (val & DROP_RESET_ACTIVE && intel_gt_terminally_wedged(gt))
 		intel_gt_handle_error(gt, ALL_ENGINES, 0, NULL);
 
+	return 0;
+}
+
+static int
+i915_drop_caches_set(void *data, u64 val)
+{
+	struct drm_i915_private *i915 = data;
+	int ret;
+
+	DRM_DEBUG("Dropping caches: 0x%08llx [0x%08llx]\n",
+		  val, val & DROP_ALL);
+
+	ret = gt_drop_caches(&i915->gt, val);
+	if (ret)
+		return ret;
+
 	fs_reclaim_acquire(GFP_KERNEL);
 	if (val & DROP_BOUND)
 		i915_gem_shrink(i915, LONG_MAX, NULL, I915_SHRINK_BOUND);
@@ -4339,7 +4282,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_guc_stage_pool", i915_guc_stage_pool, 0},
 	{"i915_huc_load_status", i915_huc_load_status_info, 0},
 	{"i915_frequency_info", i915_frequency_info, 0},
-	{"i915_hangcheck_info", i915_hangcheck_info, 0},
 	{"i915_drpc_info", i915_drpc_info, 0},
 	{"i915_ring_freq_table", i915_ring_freq_table, 0},
 	{"i915_frontbuffer_tracking", i915_frontbuffer_tracking, 0},
@@ -4566,7 +4508,7 @@ static int i915_dsc_fec_support_show(struct seq_file *m, void *data)
 		intel_dp = enc_to_intel_dp(&intel_attached_encoder(connector)->base);
 		crtc_state = to_intel_crtc_state(crtc->state);
 		seq_printf(m, "DSC_Enabled: %s\n",
-			   yesno(crtc_state->dsc_params.compression_enable));
+			   yesno(crtc_state->dsc.compression_enable));
 		seq_printf(m, "DSC_Sink_Support: %s\n",
 			   yesno(drm_dp_sink_supports_dsc(intel_dp->dsc_dpcd)));
 		seq_printf(m, "Force_DSC_Enable: %s\n",
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 157ed22052a2..87e05ca3646a 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -63,6 +63,7 @@
 #include "gem/i915_gem_ioctls.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_rc6.h"
 
 #include "i915_debugfs.h"
 #include "i915_drv.h"
@@ -76,6 +77,7 @@
 #include "i915_trace.h"
 #include "i915_vgpu.h"
 #include "intel_csr.h"
+#include "intel_memory_region.h"
 #include "intel_pm.h"
 
 static struct drm_driver driver;
@@ -598,12 +600,10 @@ static int i915_driver_mmio_probe(struct drm_i915_private *dev_priv)
 
 	intel_uc_init_mmio(&dev_priv->gt.uc);
 
-	ret = intel_engines_init_mmio(dev_priv);
+	ret = intel_engines_init_mmio(&dev_priv->gt);
 	if (ret)
 		goto err_uncore;
 
-	i915_gem_init_mmio(dev_priv);
-
 	return 0;
 
 err_uncore:
@@ -621,7 +621,7 @@ err_bridge:
  */
 static void i915_driver_mmio_release(struct drm_i915_private *dev_priv)
 {
-	intel_engines_cleanup(dev_priv);
+	intel_engines_cleanup(&dev_priv->gt);
 	intel_teardown_mchbar(dev_priv);
 	intel_uncore_fini_mmio(&dev_priv->uncore);
 	pci_dev_put(dev_priv->bridge_dev);
@@ -1172,12 +1172,16 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_ggtt;
 
-	intel_gt_init_hw_early(dev_priv);
+	ret = intel_memory_regions_hw_probe(dev_priv);
+	if (ret)
+		goto err_ggtt;
+
+	intel_gt_init_hw_early(&dev_priv->gt, &dev_priv->ggtt);
 
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret) {
 		DRM_ERROR("failed to enable GGTT\n");
-		goto err_ggtt;
+		goto err_mem_regions;
 	}
 
 	pci_set_master(pdev);
@@ -1194,7 +1198,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 		if (ret) {
 			DRM_ERROR("failed to set DMA mask\n");
 
-			goto err_ggtt;
+			goto err_mem_regions;
 		}
 	}
 
@@ -1212,7 +1216,7 @@ static int i915_driver_hw_probe(struct drm_i915_private *dev_priv)
 		if (ret) {
 			DRM_ERROR("failed to set DMA mask\n");
 
-			goto err_ggtt;
+			goto err_mem_regions;
 		}
 	}
 
@@ -1264,6 +1268,8 @@ err_msi:
 	if (pdev->msi_enabled)
 		pci_disable_msi(pdev);
 	pm_qos_remove_request(&dev_priv->pm_qos);
+err_mem_regions:
+	intel_memory_regions_driver_release(dev_priv);
 err_ggtt:
 	i915_ggtt_driver_release(dev_priv);
 err_perf:
@@ -1476,6 +1482,23 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!i915_modparams.nuclear_pageflip && match_info->gen < 5)
 		dev_priv->drm.driver_features &= ~DRIVER_ATOMIC;
 
+	/*
+	 * Check if we support fake LMEM -- for now we only unleash this for
+	 * the live selftests(test-and-exit).
+	 */
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+	if (IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM)) {
+		if (INTEL_GEN(dev_priv) >= 9 && i915_selftest.live < 0 &&
+		    i915_modparams.fake_lmem_start) {
+			mkwrite_device_info(dev_priv)->memory_regions =
+				REGION_SMEM | REGION_LMEM | REGION_STOLEN;
+			mkwrite_device_info(dev_priv)->is_dgfx = true;
+			GEM_BUG_ON(!HAS_LMEM(dev_priv));
+			GEM_BUG_ON(!IS_DGFX(dev_priv));
+		}
+	}
+#endif
+
 	ret = pci_enable_device(pdev);
 	if (ret)
 		goto out_fini;
@@ -1510,6 +1533,7 @@ int i915_driver_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 out_cleanup_hw:
 	i915_driver_hw_remove(dev_priv);
+	intel_memory_regions_driver_release(dev_priv);
 	i915_ggtt_driver_release(dev_priv);
 out_cleanup_mmio:
 	i915_driver_mmio_release(dev_priv);
@@ -1548,10 +1572,7 @@ void i915_driver_remove(struct drm_i915_private *i915)
 
 	i915_driver_modeset_remove(i915);
 
-	/* Free error state after interrupts are fully disabled. */
-	cancel_delayed_work_sync(&i915->gt.hangcheck.work);
 	i915_reset_error_state(i915);
-
 	i915_gem_driver_remove(i915);
 
 	intel_power_domains_driver_remove(i915);
@@ -1570,6 +1591,7 @@ static void i915_driver_release(struct drm_device *dev)
 
 	i915_gem_driver_release(dev_priv);
 
+	intel_memory_regions_driver_release(dev_priv);
 	i915_ggtt_driver_release(dev_priv);
 
 	i915_driver_mmio_release(dev_priv);
@@ -1797,9 +1819,10 @@ static int i915_drm_resume(struct drm_device *dev)
 	int ret;
 
 	disable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
-	intel_gt_pm_disable(&dev_priv->gt);
 
-	i915_gem_sanitize(dev_priv);
+	intel_rc6_ctx_wa_resume(&dev_priv->gt.rc6);
+
+	intel_gt_sanitize(&dev_priv->gt, true);
 
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret)
@@ -1928,12 +1951,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 
 	intel_display_power_resume_early(dev_priv);
 
-	intel_gt_pm_disable(&dev_priv->gt);
-
 	intel_power_domains_resume(dev_priv);
 
-	intel_gt_sanitize(&dev_priv->gt, true);
-
 	enable_rpm_wakeref_asserts(&dev_priv->runtime_pm);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8882c0908c3b..e29bc137e7ba 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -101,6 +101,8 @@
 #include "i915_vma.h"
 #include "i915_irq.h"
 
+#include "intel_region_lmem.h"
+
 #include "intel_gvt.h"
 
 /* General customization:
@@ -108,8 +110,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20191021"
-#define DRIVER_TIMESTAMP	1571651766
+#define DRIVER_DATE		"20191101"
+#define DRIVER_TIMESTAMP	1572604873
 
 struct drm_i915_gem_object;
 
@@ -543,94 +545,6 @@ struct i915_suspend_saved_registers {
 
 struct vlv_s0ix_state;
 
-struct intel_rps_ei {
-	ktime_t ktime;
-	u32 render_c0;
-	u32 media_c0;
-};
-
-struct intel_rps {
-	struct mutex lock; /* protects enabling and the worker */
-
-	/*
-	 * work, interrupts_enabled and pm_iir are protected by
-	 * dev_priv->irq_lock
-	 */
-	struct work_struct work;
-	bool interrupts_enabled;
-	u32 pm_iir;
-
-	/* PM interrupt bits that should never be masked */
-	u32 pm_intrmsk_mbz;
-
-	/* Frequencies are stored in potentially platform dependent multiples.
-	 * In other words, *_freq needs to be multiplied by X to be interesting.
-	 * Soft limits are those which are used for the dynamic reclocking done
-	 * by the driver (raise frequencies under heavy loads, and lower for
-	 * lighter loads). Hard limits are those imposed by the hardware.
-	 *
-	 * A distinction is made for overclocking, which is never enabled by
-	 * default, and is considered to be above the hard limit if it's
-	 * possible at all.
-	 */
-	u8 cur_freq;		/* Current frequency (cached, may not == HW) */
-	u8 min_freq_softlimit;	/* Minimum frequency permitted by the driver */
-	u8 max_freq_softlimit;	/* Max frequency permitted by the driver */
-	u8 max_freq;		/* Maximum frequency, RP0 if not overclocking */
-	u8 min_freq;		/* AKA RPn. Minimum frequency */
-	u8 boost_freq;		/* Frequency to request when wait boosting */
-	u8 idle_freq;		/* Frequency to request when we are idle */
-	u8 efficient_freq;	/* AKA RPe. Pre-determined balanced frequency */
-	u8 rp1_freq;		/* "less than" RP0 power/freqency */
-	u8 rp0_freq;		/* Non-overclocked max frequency. */
-	u16 gpll_ref_freq;	/* vlv/chv GPLL reference frequency */
-
-	int last_adj;
-
-	struct {
-		struct mutex mutex;
-
-		enum { LOW_POWER, BETWEEN, HIGH_POWER } mode;
-		unsigned int interactive;
-
-		u8 up_threshold; /* Current %busy required to uplock */
-		u8 down_threshold; /* Current %busy required to downclock */
-	} power;
-
-	bool enabled;
-	atomic_t num_waiters;
-	atomic_t boosts;
-
-	/* manual wa residency calculations */
-	struct intel_rps_ei ei;
-};
-
-struct intel_gen6_power_mgmt {
-	struct intel_rps rps;
-};
-
-/* defined intel_pm.c */
-extern spinlock_t mchdev_lock;
-
-struct intel_ilk_power_mgmt {
-	u8 cur_delay;
-	u8 min_delay;
-	u8 max_delay;
-	u8 fmax;
-	u8 fstart;
-
-	u64 last_count1;
-	unsigned long last_time1;
-	unsigned long chipset_power;
-	u64 last_count2;
-	u64 last_time2;
-	unsigned long gfx_power;
-	u8 corr;
-
-	int c_m;
-	int r_t;
-};
-
 #define MAX_L3_SLICES 2
 struct intel_l3_parity {
 	u32 *remap_info[MAX_L3_SLICES];
@@ -1067,7 +981,6 @@ struct drm_i915_private {
 		u32 irq_mask;
 		u32 de_irq_mask[I915_MAX_PIPES];
 	};
-	u32 pm_rps_events;
 	u32 pipestat_irq_mask[I915_MAX_PIPES];
 
 	struct i915_hotplug hotplug;
@@ -1097,13 +1010,14 @@ struct drm_i915_private {
 	unsigned int fdi_pll_freq;
 	unsigned int czclk_freq;
 
+	/*
+	 * For reading holding any crtc lock is sufficient,
+	 * for writing must hold all of them.
+	 */
 	struct {
 		/*
 		 * The current logical cdclk state.
 		 * See intel_atomic_state.cdclk.logical
-		 *
-		 * For reading holding any crtc lock is sufficient,
-		 * for writing must hold all of them.
 		 */
 		struct intel_cdclk_state logical;
 		/*
@@ -1173,6 +1087,10 @@ struct drm_i915_private {
 	 */
 	struct mutex dpll_lock;
 
+	/*
+	 * For reading active_pipes, min_cdclk, min_voltage_level holding
+	 * any crtc lock is sufficient, for writing must hold all of them.
+	 */
 	u8 active_pipes;
 	/* minimum acceptable cdclk for each pipe */
 	int min_cdclk[I915_MAX_PIPES];
@@ -1202,13 +1120,6 @@ struct drm_i915_private {
 	 */
 	u32 edram_size_mb;
 
-	/* gen6+ GT PM state */
-	struct intel_gen6_power_mgmt gt_pm;
-
-	/* ilk-only ips/rps state. Everything in here is protected by the global
-	 * mchdev_lock in intel_pm.c */
-	struct intel_ilk_power_mgmt ips;
-
 	struct i915_power_domains power_domains;
 
 	struct i915_psr psr;
@@ -1348,6 +1259,8 @@ struct drm_i915_private {
 		} contexts;
 	} gem;
 
+	u8 pch_ssc_use;
+
 	/* For i915gm/i945gm vblank irq workaround */
 	u8 vblank_enabled;
 
@@ -1544,6 +1457,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 }
 
 #define IS_MOBILE(dev_priv)	(INTEL_INFO(dev_priv)->is_mobile)
+#define IS_DGFX(dev_priv)   (INTEL_INFO(dev_priv)->is_dgfx)
 
 #define IS_I830(dev_priv)	IS_PLATFORM(dev_priv, INTEL_I830)
 #define IS_I845G(dev_priv)	IS_PLATFORM(dev_priv, INTEL_I845G)
@@ -1700,9 +1614,16 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define VEBOX_MASK(dev_priv) \
 	ENGINE_INSTANCES_MASK(dev_priv, VECS0, I915_MAX_VECS)
 
+/*
+ * The Gen7 cmdparser copies the scanned buffer to the ggtt for execution
+ * All later gens can run the final buffer from the ppgtt
+ */
+#define CMDPARSER_USES_GGTT(dev_priv) IS_GEN(dev_priv, 7)
+
 #define HAS_LLC(dev_priv)	(INTEL_INFO(dev_priv)->has_llc)
 #define HAS_SNOOP(dev_priv)	(INTEL_INFO(dev_priv)->has_snoop)
 #define HAS_EDRAM(dev_priv)	((dev_priv)->edram_size_mb)
+#define HAS_SECURE_BATCHES(dev_priv) (INTEL_GEN(dev_priv) < 6)
 #define HAS_WT(dev_priv)	((IS_HASWELL(dev_priv) || \
 				 IS_BROADWELL(dev_priv)) && HAS_EDRAM(dev_priv))
 
@@ -1735,10 +1656,12 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 /* Early gen2 have a totally busted CS tlb and require pinned batches. */
 #define HAS_BROKEN_CS_TLB(dev_priv)	(IS_I830(dev_priv) || IS_I845G(dev_priv))
 
+#define NEEDS_RC6_CTX_CORRUPTION_WA(dev_priv)	\
+	(IS_BROADWELL(dev_priv) || IS_GEN(dev_priv, 9))
+
 /* WaRsDisableCoarsePowerGating:skl,cnl */
 #define NEEDS_WaRsDisableCoarsePowerGating(dev_priv) \
-	(IS_CANNONLAKE(dev_priv) || \
-	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
+	(IS_CANNONLAKE(dev_priv) || IS_GEN(dev_priv, 9))
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 #define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
@@ -1781,6 +1704,7 @@ IS_SUBPLATFORM(const struct drm_i915_private *i915,
 #define HAS_IPC(dev_priv)		 (INTEL_INFO(dev_priv)->display.has_ipc)
 
 #define HAS_REGION(i915, i) (INTEL_INFO(i915)->memory_regions & (i))
+#define HAS_LMEM(i915) HAS_REGION(i915, REGION_LMEM)
 
 #define HAS_GT_UC(dev_priv)	(INTEL_INFO(dev_priv)->has_gt_uc)
 
@@ -1846,7 +1770,6 @@ void i915_driver_remove(struct drm_i915_private *i915);
 int i915_resume_switcheroo(struct drm_i915_private *i915);
 int i915_suspend_switcheroo(struct drm_i915_private *i915, pm_message_t state);
 
-void intel_engine_init_hangcheck(struct intel_engine_cs *engine);
 int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 
 static inline bool intel_gvt_active(struct drm_i915_private *dev_priv)
@@ -1865,7 +1788,6 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 /* i915_gem.c */
 int i915_gem_init_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
-void i915_gem_sanitize(struct drm_i915_private *i915);
 void i915_gem_init_early(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
 int i915_gem_freeze(struct drm_i915_private *dev_priv);
@@ -1921,6 +1843,14 @@ int i915_gem_object_unbind(struct drm_i915_gem_object *obj,
 			   unsigned long flags);
 #define I915_GEM_OBJECT_UNBIND_ACTIVE BIT(0)
 
+struct i915_vma * __must_check
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view,
+		    u64 size,
+		    u64 alignment,
+		    u64 flags);
+
 void i915_gem_runtime_suspend(struct drm_i915_private *dev_priv);
 
 static inline int __must_check
@@ -1949,7 +1879,6 @@ static inline u32 i915_reset_engine_count(struct i915_gpu_error *error,
 	return atomic_read(&error->reset_engine_count[engine->uabi_class]);
 }
 
-void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
 void i915_gem_driver_register(struct drm_i915_private *i915);
 void i915_gem_driver_unregister(struct drm_i915_private *i915);
@@ -2002,9 +1931,6 @@ int __must_check i915_gem_evict_for_node(struct i915_address_space *vm,
 					 unsigned int flags);
 int i915_gem_evict_vm(struct i915_address_space *vm);
 
-void i915_gem_cleanup_memory_regions(struct drm_i915_private *i915);
-int i915_gem_init_memory_regions(struct drm_i915_private *i915);
-
 /* i915_gem_internal.c */
 struct drm_i915_gem_object *
 i915_gem_object_create_internal(struct drm_i915_private *dev_priv,
@@ -2030,12 +1956,14 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type);
 int i915_cmd_parser_get_version(struct drm_i915_private *dev_priv);
 void intel_engine_init_cmd_parser(struct intel_engine_cs *engine);
 void intel_engine_cleanup_cmd_parser(struct intel_engine_cs *engine);
-int intel_engine_cmd_parser(struct intel_engine_cs *engine,
+int intel_engine_cmd_parser(struct i915_gem_context *cxt,
+			    struct intel_engine_cs *engine,
 			    struct drm_i915_gem_object *batch_obj,
-			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 user_batch_start,
 			    u32 batch_start_offset,
 			    u32 batch_len,
-			    bool is_master);
+			    struct drm_i915_gem_object *shadow_batch_obj,
+			    u64 shadow_batch_start);
 
 /* intel_device_info.c */
 static inline struct intel_device_info *
@@ -2117,4 +2045,10 @@ i915_coherent_map_type(struct drm_i915_private *i915)
 	return HAS_LLC(i915) ? I915_MAP_WB : I915_MAP_WC;
 }
 
+static inline bool intel_guc_submission_is_enabled(struct intel_guc *guc)
+{
+	return intel_guc_is_submission_supported(guc) &&
+		intel_guc_is_running(guc);
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index dd0a3271b4e2..b9eb6b3149b7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -48,9 +48,11 @@
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
+#include "gt/intel_gt_requests.h"
 #include "gt/intel_mocs.h"
 #include "gt/intel_reset.h"
 #include "gt/intel_renderstate.h"
+#include "gt/intel_rps.h"
 #include "gt/intel_workarounds.h"
 
 #include "i915_drv.h"
@@ -891,6 +893,20 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_address_space *vm = &dev_priv->ggtt.vm;
+
+	return i915_gem_object_pin(obj, vm, view, size, alignment,
+				   flags | PIN_GLOBAL);
+}
+
+struct i915_vma *
+i915_gem_object_pin(struct drm_i915_gem_object *obj,
+		    struct i915_address_space *vm,
+		    const struct i915_ggtt_view *view,
+		    u64 size,
+		    u64 alignment,
+		    u64 flags)
+{
+	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
 	struct i915_vma *vma;
 	int ret;
 
@@ -956,7 +972,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			return ERR_PTR(ret);
 	}
 
-	ret = i915_vma_pin(vma, size, alignment, flags | PIN_GLOBAL);
+	ret = i915_vma_pin(vma, size, alignment, flags);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -1037,39 +1053,7 @@ out:
 	return err;
 }
 
-void i915_gem_sanitize(struct drm_i915_private *i915)
-{
-	intel_wakeref_t wakeref;
-
-	GEM_TRACE("\n");
-
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
-	intel_uncore_forcewake_get(&i915->uncore, FORCEWAKE_ALL);
-
-	/*
-	 * As we have just resumed the machine and woken the device up from
-	 * deep PCI sleep (presumably D3_cold), assume the HW has been reset
-	 * back to defaults, recovering from whatever wedged state we left it
-	 * in and so worth trying to use the device once more.
-	 */
-	if (intel_gt_is_wedged(&i915->gt))
-		intel_gt_unset_wedged(&i915->gt);
-
-	/*
-	 * If we inherit context state from the BIOS or earlier occupants
-	 * of the GPU, the GPU may be in an inconsistent state when we
-	 * try to take over. The only way to remove the earlier state
-	 * is by resetting. However, resetting on earlier gen is tricky as
-	 * it may impact the display and we are uncertain about the stability
-	 * of the reset, so this could be applied to even earlier gen.
-	 */
-	intel_gt_sanitize(&i915->gt, false);
-
-	intel_uncore_forcewake_put(&i915->uncore, FORCEWAKE_ALL);
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
-}
-
-static int __intel_engines_record_defaults(struct drm_i915_private *i915)
+static int __intel_engines_record_defaults(struct intel_gt *gt)
 {
 	struct i915_request *requests[I915_NUM_ENGINES] = {};
 	struct intel_engine_cs *engine;
@@ -1085,7 +1069,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	 * from the same default HW values.
 	 */
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct intel_context *ce;
 		struct i915_request *rq;
 
@@ -1093,7 +1077,8 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 		GEM_BUG_ON(!engine->kernel_context);
 		engine->serial++; /* force the kernel context switch */
 
-		ce = intel_context_create(i915->kernel_context, engine);
+		ce = intel_context_create(engine->kernel_context->gem_context,
+					  engine);
 		if (IS_ERR(ce)) {
 			err = PTR_ERR(ce);
 			goto out;
@@ -1122,7 +1107,7 @@ err_rq:
 	}
 
 	/* Flush the default context image to memory, and enable powersaving. */
-	if (!i915_gem_load_power_context(i915)) {
+	if (intel_gt_wait_for_idle(gt, I915_GEM_IDLE_TIMEOUT) == -ETIME) {
 		err = -EIO;
 		goto out;
 	}
@@ -1181,7 +1166,7 @@ out:
 	 * this is by declaring ourselves wedged.
 	 */
 	if (err)
-		intel_gt_set_wedged(&i915->gt);
+		intel_gt_set_wedged(gt);
 
 	for (id = 0; id < ARRAY_SIZE(requests); id++) {
 		struct intel_context *ce;
@@ -1198,7 +1183,7 @@ out:
 	return err;
 }
 
-static int intel_engines_verify_workarounds(struct drm_i915_private *i915)
+static int intel_engines_verify_workarounds(struct intel_gt *gt)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -1207,7 +1192,7 @@ static int intel_engines_verify_workarounds(struct drm_i915_private *i915)
 	if (!IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
 		return 0;
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		if (intel_engine_verify_workarounds(engine, "load"))
 			err = -EIO;
 	}
@@ -1249,7 +1234,7 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 
 	intel_gt_init(&dev_priv->gt);
 
-	ret = intel_engines_setup(dev_priv);
+	ret = intel_engines_setup(&dev_priv->gt);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
 		goto err_unlock;
@@ -1261,14 +1246,12 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		goto err_scratch;
 	}
 
-	ret = intel_engines_init(dev_priv);
+	ret = intel_engines_init(&dev_priv->gt);
 	if (ret) {
 		GEM_BUG_ON(ret == -EIO);
 		goto err_context;
 	}
 
-	intel_init_gt_powersave(dev_priv);
-
 	intel_uc_init(&dev_priv->gt.uc);
 
 	ret = intel_gt_init_hw(&dev_priv->gt);
@@ -1291,19 +1274,19 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 */
 	intel_init_clock_gating(dev_priv);
 
-	ret = intel_engines_verify_workarounds(dev_priv);
+	ret = intel_engines_verify_workarounds(&dev_priv->gt);
 	if (ret)
 		goto err_gt;
 
-	ret = __intel_engines_record_defaults(dev_priv);
+	ret = __intel_engines_record_defaults(&dev_priv->gt);
 	if (ret)
 		goto err_gt;
 
-	ret = i915_inject_load_error(dev_priv, -ENODEV);
+	ret = i915_inject_probe_error(dev_priv, -ENODEV);
 	if (ret)
 		goto err_gt;
 
-	ret = i915_inject_load_error(dev_priv, -EIO);
+	ret = i915_inject_probe_error(dev_priv, -EIO);
 	if (ret)
 		goto err_gt;
 
@@ -1328,7 +1311,7 @@ err_init_hw:
 err_uc_init:
 	if (ret != -EIO) {
 		intel_uc_fini(&dev_priv->gt.uc);
-		intel_engines_cleanup(dev_priv);
+		intel_engines_cleanup(&dev_priv->gt);
 	}
 err_context:
 	if (ret != -EIO)
@@ -1397,7 +1380,7 @@ void i915_gem_driver_remove(struct drm_i915_private *dev_priv)
 
 void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 {
-	intel_engines_cleanup(dev_priv);
+	intel_engines_cleanup(&dev_priv->gt);
 	i915_gem_driver_release__contexts(dev_priv);
 	intel_gt_driver_release(&dev_priv->gt);
 
@@ -1412,11 +1395,6 @@ void i915_gem_driver_release(struct drm_i915_private *dev_priv)
 	WARN_ON(!list_empty(&dev_priv->gem.contexts.list));
 }
 
-void i915_gem_init_mmio(struct drm_i915_private *i915)
-{
-	i915_gem_sanitize(i915);
-}
-
 static void i915_gem_init__mm(struct drm_i915_private *i915)
 {
 	spin_lock_init(&i915->mm.obj_lock);
@@ -1432,7 +1410,6 @@ static void i915_gem_init__mm(struct drm_i915_private *i915)
 void i915_gem_init_early(struct drm_i915_private *dev_priv)
 {
 	i915_gem_init__mm(dev_priv);
-	i915_gem_init__pm(dev_priv);
 
 	spin_lock_init(&dev_priv->fb_tracking.lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 2011f8e9a9f1..f6f9675848b8 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -112,18 +112,4 @@ static inline bool __tasklet_is_scheduled(struct tasklet_struct *t)
 	return test_bit(TASKLET_STATE_SCHED, &t->state);
 }
 
-static inline void cancel_timer(struct timer_list *t)
-{
-	if (!READ_ONCE(t->expires))
-		return;
-
-	del_timer(t);
-	WRITE_ONCE(t->expires, 0);
-}
-
-static inline bool timer_expired(const struct timer_list *t)
-{
-	return READ_ONCE(t->expires) && !timer_pending(t);
-}
-
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/i915_gem_fence_reg.c b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
index 321189e1b0f2..71efccfde122 100644
--- a/drivers/gpu/drm/i915/i915_gem_fence_reg.c
+++ b/drivers/gpu/drm/i915/i915_gem_fence_reg.c
@@ -846,8 +846,10 @@ void i915_ggtt_init_fences(struct i915_ggtt *ggtt)
 
 	detect_bit_6_swizzle(ggtt);
 
-	if (INTEL_GEN(i915) >= 7 &&
-	    !(IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)))
+	if (!i915_ggtt_has_aperture(ggtt))
+		num_fences = 0;
+	else if (INTEL_GEN(i915) >= 7 &&
+		 !(IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)))
 		num_fences = 32;
 	else if (INTEL_GEN(i915) >= 4 ||
 		 IS_I945G(i915) || IS_I945GM(i915) ||
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 3148d5946b63..6239a9adbf14 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2609,8 +2609,6 @@ static int init_aliasing_ppgtt(struct i915_ggtt *ggtt)
 	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
 	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
 
-	ppgtt->vm.total = ggtt->vm.total;
-
 	return 0;
 
 err_ppgtt:
@@ -2661,7 +2659,8 @@ static void ggtt_release_guc_top(struct i915_ggtt *ggtt)
 static void cleanup_init_ggtt(struct i915_ggtt *ggtt)
 {
 	ggtt_release_guc_top(ggtt);
-	drm_mm_remove_node(&ggtt->error_capture);
+	if (drm_mm_node_allocated(&ggtt->error_capture))
+		drm_mm_remove_node(&ggtt->error_capture);
 }
 
 static int init_ggtt(struct i915_ggtt *ggtt)
@@ -2692,13 +2691,15 @@ static int init_ggtt(struct i915_ggtt *ggtt)
 	if (ret)
 		return ret;
 
-	/* Reserve a mappable slot for our lockless error capture */
-	ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture,
-					  PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
-					  0, ggtt->mappable_end,
-					  DRM_MM_INSERT_LOW);
-	if (ret)
-		return ret;
+	if (ggtt->mappable_end) {
+		/* Reserve a mappable slot for our lockless error capture */
+		ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture,
+						  PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
+						  0, ggtt->mappable_end,
+						  DRM_MM_INSERT_LOW);
+		if (ret)
+			return ret;
+	}
 
 	/*
 	 * The upper portion of the GuC address space has a sizeable hole
@@ -2744,59 +2745,6 @@ int i915_init_ggtt(struct drm_i915_private *i915)
 	return 0;
 }
 
-void i915_gem_cleanup_memory_regions(struct drm_i915_private *i915)
-{
-	int i;
-
-	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
-		struct intel_memory_region *region = i915->mm.regions[i];
-
-		if (region)
-			intel_memory_region_put(region);
-	}
-}
-
-int i915_gem_init_memory_regions(struct drm_i915_private *i915)
-{
-	int err, i;
-
-	for (i = 0; i < INTEL_REGION_UNKNOWN; i++) {
-		struct intel_memory_region *mem = ERR_PTR(-ENODEV);
-		u32 type;
-
-		if (!HAS_REGION(i915, BIT(i)))
-			continue;
-
-		type = MEMORY_TYPE_FROM_REGION(intel_region_map[i]);
-		switch (type) {
-		case INTEL_MEMORY_SYSTEM:
-			mem = i915_gem_shmem_setup(i915);
-			break;
-		case INTEL_MEMORY_STOLEN:
-			mem = i915_gem_stolen_setup(i915);
-			break;
-		}
-
-		if (IS_ERR(mem)) {
-			err = PTR_ERR(mem);
-			DRM_ERROR("Failed to setup region(%d) type=%d\n", err, type);
-			goto out_cleanup;
-		}
-
-		mem->id = intel_region_map[i];
-		mem->type = type;
-		mem->instance = MEMORY_INSTANCE_FROM_REGION(intel_region_map[i]);
-
-		i915->mm.regions[i] = mem;
-	}
-
-	return 0;
-
-out_cleanup:
-	i915_gem_cleanup_memory_regions(i915);
-	return err;
-}
-
 static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 {
 	struct i915_vma *vma, *vn;
@@ -2823,7 +2771,9 @@ static void ggtt_cleanup_hw(struct i915_ggtt *ggtt)
 	i915_address_space_fini(&ggtt->vm);
 
 	arch_phys_wc_del(ggtt->mtrr);
-	io_mapping_fini(&ggtt->iomap);
+
+	if (ggtt->iomap.size)
+		io_mapping_fini(&ggtt->iomap);
 }
 
 /**
@@ -2834,8 +2784,6 @@ void i915_ggtt_driver_release(struct drm_i915_private *i915)
 {
 	struct pagevec *pvec;
 
-	i915_gem_cleanup_memory_regions(i915);
-
 	fini_aliasing_ppgtt(&i915->ggtt);
 
 	ggtt_cleanup_hw(&i915->ggtt);
@@ -2922,35 +2870,51 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 	return 0;
 }
 
-static void tgl_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void tgl_setup_private_ppat(struct intel_uncore *uncore)
 {
 	/* TGL doesn't support LLC or AGE settings */
-	I915_WRITE(GEN12_PAT_INDEX(0), GEN8_PPAT_WB);
-	I915_WRITE(GEN12_PAT_INDEX(1), GEN8_PPAT_WC);
-	I915_WRITE(GEN12_PAT_INDEX(2), GEN8_PPAT_WT);
-	I915_WRITE(GEN12_PAT_INDEX(3), GEN8_PPAT_UC);
-	I915_WRITE(GEN12_PAT_INDEX(4), GEN8_PPAT_WB);
-	I915_WRITE(GEN12_PAT_INDEX(5), GEN8_PPAT_WB);
-	I915_WRITE(GEN12_PAT_INDEX(6), GEN8_PPAT_WB);
-	I915_WRITE(GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
-}
-
-static void cnl_setup_private_ppat(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN10_PAT_INDEX(0), GEN8_PPAT_WB | GEN8_PPAT_LLC);
-	I915_WRITE(GEN10_PAT_INDEX(1), GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
-	I915_WRITE(GEN10_PAT_INDEX(2), GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
-	I915_WRITE(GEN10_PAT_INDEX(3), GEN8_PPAT_UC);
-	I915_WRITE(GEN10_PAT_INDEX(4), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
-	I915_WRITE(GEN10_PAT_INDEX(5), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
-	I915_WRITE(GEN10_PAT_INDEX(6), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
-	I915_WRITE(GEN10_PAT_INDEX(7), GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(0), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(1), GEN8_PPAT_WC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(2), GEN8_PPAT_WT);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(3), GEN8_PPAT_UC);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(4), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(5), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(6), GEN8_PPAT_WB);
+	intel_uncore_write(uncore, GEN12_PAT_INDEX(7), GEN8_PPAT_WB);
+}
+
+static void cnl_setup_private_ppat(struct intel_uncore *uncore)
+{
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(0),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(1),
+			   GEN8_PPAT_WC | GEN8_PPAT_LLCELLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(2),
+			   GEN8_PPAT_WT | GEN8_PPAT_LLCELLC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(3),
+			   GEN8_PPAT_UC);
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(4),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(0));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(5),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(1));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(6),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2));
+	intel_uncore_write(uncore,
+			   GEN10_PAT_INDEX(7),
+			   GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
 }
 
 /* The GGTT and PPGTT need a private PPAT setup in order to handle cacheability
  * bits. When using advanced contexts each context stores its own PAT, but
  * writing this data shouldn't be harmful even in those cases. */
-static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void bdw_setup_private_ppat(struct intel_uncore *uncore)
 {
 	u64 pat;
 
@@ -2963,11 +2927,11 @@ static void bdw_setup_private_ppat(struct drm_i915_private *dev_priv)
 	      GEN8_PPAT(6, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(2)) |
 	      GEN8_PPAT(7, GEN8_PPAT_WB | GEN8_PPAT_LLCELLC | GEN8_PPAT_AGE(3));
 
-	I915_WRITE(GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
-	I915_WRITE(GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
 }
 
-static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
+static void chv_setup_private_ppat(struct intel_uncore *uncore)
 {
 	u64 pat;
 
@@ -2999,8 +2963,8 @@ static void chv_setup_private_ppat(struct drm_i915_private *dev_priv)
 	      GEN8_PPAT(6, CHV_PPAT_SNOOP) |
 	      GEN8_PPAT(7, CHV_PPAT_SNOOP);
 
-	I915_WRITE(GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
-	I915_WRITE(GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_LO, lower_32_bits(pat));
+	intel_uncore_write(uncore, GEN8_PRIVATE_PAT_HI, upper_32_bits(pat));
 }
 
 static void gen6_gmch_remove(struct i915_address_space *vm)
@@ -3011,18 +2975,26 @@ static void gen6_gmch_remove(struct i915_address_space *vm)
 	cleanup_scratch_page(vm);
 }
 
-static void setup_private_pat(struct drm_i915_private *dev_priv)
+static void setup_private_pat(struct intel_uncore *uncore)
 {
-	GEM_BUG_ON(INTEL_GEN(dev_priv) < 8);
+	struct drm_i915_private *i915 = uncore->i915;
 
-	if (INTEL_GEN(dev_priv) >= 12)
-		tgl_setup_private_ppat(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 10)
-		cnl_setup_private_ppat(dev_priv);
-	else if (IS_CHERRYVIEW(dev_priv) || IS_GEN9_LP(dev_priv))
-		chv_setup_private_ppat(dev_priv);
+	GEM_BUG_ON(INTEL_GEN(i915) < 8);
+
+	if (INTEL_GEN(i915) >= 12)
+		tgl_setup_private_ppat(uncore);
+	else if (INTEL_GEN(i915) >= 10)
+		cnl_setup_private_ppat(uncore);
+	else if (IS_CHERRYVIEW(i915) || IS_GEN9_LP(i915))
+		chv_setup_private_ppat(uncore);
 	else
-		bdw_setup_private_ppat(dev_priv);
+		bdw_setup_private_ppat(uncore);
+}
+
+static struct resource pci_resource(struct pci_dev *pdev, int bar)
+{
+	return (struct resource)DEFINE_RES_MEM(pci_resource_start(pdev, bar),
+					       pci_resource_len(pdev, bar));
 }
 
 static int gen8_gmch_probe(struct i915_ggtt *ggtt)
@@ -3034,10 +3006,10 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	int err;
 
 	/* TODO: We're not aware of mappable constraints on gen8 yet */
-	ggtt->gmadr =
-		(struct resource) DEFINE_RES_MEM(pci_resource_start(pdev, 2),
-						 pci_resource_len(pdev, 2));
-	ggtt->mappable_end = resource_size(&ggtt->gmadr);
+	if (!IS_DGFX(dev_priv)) {
+		ggtt->gmadr = pci_resource(pdev, 2);
+		ggtt->mappable_end = resource_size(&ggtt->gmadr);
+	}
 
 	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(39));
 	if (!err)
@@ -3078,7 +3050,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->vm.pte_encode = gen8_pte_encode;
 
-	setup_private_pat(dev_priv);
+	setup_private_pat(ggtt->vm.gt->uncore);
 
 	return ggtt_probe_common(ggtt, size);
 }
@@ -3260,14 +3232,17 @@ static int ggtt_init_hw(struct i915_ggtt *ggtt)
 	if (!HAS_LLC(i915) && !HAS_PPGTT(i915))
 		ggtt->vm.mm.color_adjust = i915_ggtt_color_adjust;
 
-	if (!io_mapping_init_wc(&ggtt->iomap,
-				ggtt->gmadr.start,
-				ggtt->mappable_end)) {
-		ggtt->vm.cleanup(&ggtt->vm);
-		return -EIO;
-	}
+	if (ggtt->mappable_end) {
+		if (!io_mapping_init_wc(&ggtt->iomap,
+					ggtt->gmadr.start,
+					ggtt->mappable_end)) {
+			ggtt->vm.cleanup(&ggtt->vm);
+			return -EIO;
+		}
 
-	ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start, ggtt->mappable_end);
+		ggtt->mtrr = arch_phys_wc_add(ggtt->gmadr.start,
+					      ggtt->mappable_end);
+	}
 
 	i915_ggtt_init_fences(ggtt);
 
@@ -3293,15 +3268,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
-	ret = i915_gem_init_memory_regions(dev_priv);
-	if (ret)
-		goto out_gtt_cleanup;
-
 	return 0;
-
-out_gtt_cleanup:
-	dev_priv->ggtt.vm.cleanup(&dev_priv->ggtt.vm);
-	return ret;
 }
 
 int i915_ggtt_enable_hw(struct drm_i915_private *dev_priv)
@@ -3382,10 +3349,12 @@ static void ggtt_restore_mappings(struct i915_ggtt *ggtt)
 
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *i915)
 {
-	ggtt_restore_mappings(&i915->ggtt);
+	struct i915_ggtt *ggtt = &i915->ggtt;
+
+	ggtt_restore_mappings(ggtt);
 
 	if (INTEL_GEN(i915) >= 8)
-		setup_private_pat(i915);
+		setup_private_pat(ggtt->vm.gt->uncore);
 }
 
 static struct scatterlist *
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index f074f1de66e8..402283ce2864 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -575,6 +575,11 @@ void i915_ggtt_disable_guc(struct i915_ggtt *ggtt);
 int i915_init_ggtt(struct drm_i915_private *dev_priv);
 void i915_ggtt_driver_release(struct drm_i915_private *dev_priv);
 
+static inline bool i915_ggtt_has_aperture(const struct i915_ggtt *ggtt)
+{
+	return ggtt->mappable_end > 0;
+}
+
 int i915_ppgtt_init_hw(struct intel_gt *gt);
 
 struct i915_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_getparam.c b/drivers/gpu/drm/i915/i915_getparam.c
index ad33fbe90a28..cf8a8c3ef047 100644
--- a/drivers/gpu/drm/i915/i915_getparam.c
+++ b/drivers/gpu/drm/i915/i915_getparam.c
@@ -63,7 +63,7 @@ int i915_getparam_ioctl(struct drm_device *dev, void *data,
 		value = !!(i915->caps.scheduler & I915_SCHEDULER_CAP_SEMAPHORES);
 		break;
 	case I915_PARAM_HAS_SECURE_BATCHES:
-		value = capable(CAP_SYS_ADMIN);
+		value = HAS_SECURE_BATCHES(i915) && capable(CAP_SYS_ADMIN);
 		break;
 	case I915_PARAM_CMD_PARSER_VERSION:
 		value = i915_cmd_parser_get_version(i915);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 5cf4eed5add8..3c85cb0ee99f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -40,6 +40,7 @@
 #include "display/intel_overlay.h"
 
 #include "gem/i915_gem_context.h"
+#include "gem/i915_gem_lmem.h"
 
 #include "i915_drv.h"
 #include "i915_gpu_error.h"
@@ -235,6 +236,7 @@ struct compress {
 	struct pagevec pool;
 	struct z_stream_s zstream;
 	void *tmp;
+	bool wc;
 };
 
 static bool compress_init(struct compress *c)
@@ -292,7 +294,7 @@ static int compress_page(struct compress *c,
 	struct z_stream_s *zstream = &c->zstream;
 
 	zstream->next_in = src;
-	if (c->tmp && i915_memcpy_from_wc(c->tmp, src, PAGE_SIZE))
+	if (c->wc && c->tmp && i915_memcpy_from_wc(c->tmp, src, PAGE_SIZE))
 		zstream->next_in = c->tmp;
 	zstream->avail_in = PAGE_SIZE;
 
@@ -367,6 +369,7 @@ static void err_compression_marker(struct drm_i915_error_state_buf *m)
 
 struct compress {
 	struct pagevec pool;
+	bool wc;
 };
 
 static bool compress_init(struct compress *c)
@@ -389,7 +392,7 @@ static int compress_page(struct compress *c,
 	if (!ptr)
 		return -ENOMEM;
 
-	if (!i915_memcpy_from_wc(ptr, src, PAGE_SIZE))
+	if (!(c->wc && i915_memcpy_from_wc(ptr, src, PAGE_SIZE)))
 		memcpy(ptr, src, PAGE_SIZE);
 	dst->pages[dst->page_count++] = ptr;
 
@@ -534,10 +537,6 @@ static void error_print_engine(struct drm_i915_error_state_buf *m,
 	}
 	err_printf(m, "  ring->head: 0x%08x\n", ee->cpu_ring_head);
 	err_printf(m, "  ring->tail: 0x%08x\n", ee->cpu_ring_tail);
-	err_printf(m, "  hangcheck timestamp: %dms (%lu%s)\n",
-		   jiffies_to_msecs(ee->hangcheck_timestamp - epoch),
-		   ee->hangcheck_timestamp,
-		   ee->hangcheck_timestamp == epoch ? "; epoch" : "");
 	err_printf(m, "  engine reset count: %u\n", ee->reset_count);
 
 	for (n = 0; n < ee->num_ports; n++) {
@@ -679,11 +678,8 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	ts = ktime_to_timespec64(error->uptime);
 	err_printf(m, "Uptime: %lld s %ld us\n",
 		   (s64)ts.tv_sec, ts.tv_nsec / NSEC_PER_USEC);
-	err_printf(m, "Epoch: %lu jiffies (%u HZ)\n", error->epoch, HZ);
-	err_printf(m, "Capture: %lu jiffies; %d ms ago, %d ms after epoch\n",
-		   error->capture,
-		   jiffies_to_msecs(jiffies - error->capture),
-		   jiffies_to_msecs(error->capture - error->epoch));
+	err_printf(m, "Capture: %lu jiffies; %d ms ago\n",
+		   error->capture, jiffies_to_msecs(jiffies - error->capture));
 
 	for (ee = error->engine; ee; ee = ee->next)
 		err_printf(m, "Active process (on ring %s): %s [%d]\n",
@@ -741,8 +737,21 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 	if (IS_GEN_RANGE(m->i915, 8, 11))
 		err_printf(m, "GTT_CACHE_EN: 0x%08x\n", error->gtt_cache);
 
+	if (IS_GEN(m->i915, 12))
+		err_printf(m, "AUX_ERR_DBG: 0x%08x\n", error->aux_err);
+
+	if (INTEL_GEN(m->i915) >= 12) {
+		int i;
+
+		for (i = 0; i < GEN12_SFC_DONE_MAX; i++)
+			err_printf(m, "  SFC_DONE[%d]: 0x%08x\n", i,
+				   error->sfc_done[i]);
+
+		err_printf(m, "  GAM_DONE: 0x%08x\n", error->gam_done);
+	}
+
 	for (ee = error->engine; ee; ee = ee->next)
-		error_print_engine(m, ee, error->epoch);
+		error_print_engine(m, ee, error->capture);
 
 	for (ee = error->engine; ee; ee = ee->next) {
 		const struct drm_i915_error_object *obj;
@@ -770,7 +779,7 @@ static void __err_print_to_sgl(struct drm_i915_error_state_buf *m,
 			for (j = 0; j < ee->num_requests; j++)
 				error_print_request(m, " ",
 						    &ee->requests[j],
-						    error->epoch);
+						    error->capture);
 		}
 
 		print_error_obj(m, ee->engine, "ringbuffer", ee->ringbuffer);
@@ -970,7 +979,6 @@ i915_error_object_create(struct drm_i915_private *i915,
 	struct drm_i915_error_object *dst;
 	unsigned long num_pages;
 	struct sgt_iter iter;
-	dma_addr_t dma;
 	int ret;
 
 	might_sleep();
@@ -996,17 +1004,54 @@ i915_error_object_create(struct drm_i915_private *i915,
 	dst->page_count = 0;
 	dst->unused = 0;
 
+	compress->wc = i915_gem_object_is_lmem(vma->obj) ||
+		       drm_mm_node_allocated(&ggtt->error_capture);
+
 	ret = -EINVAL;
-	for_each_sgt_daddr(dma, iter, vma->pages) {
+	if (drm_mm_node_allocated(&ggtt->error_capture)) {
 		void __iomem *s;
+		dma_addr_t dma;
 
-		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
+		for_each_sgt_daddr(dma, iter, vma->pages) {
+			ggtt->vm.insert_page(&ggtt->vm, dma, slot,
+					     I915_CACHE_NONE, 0);
 
-		s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE);
-		ret = compress_page(compress, (void  __force *)s, dst);
-		io_mapping_unmap(s);
-		if (ret)
-			break;
+			s = io_mapping_map_wc(&ggtt->iomap, slot, PAGE_SIZE);
+			ret = compress_page(compress, (void  __force *)s, dst);
+			io_mapping_unmap(s);
+			if (ret)
+				break;
+		}
+	} else if (i915_gem_object_is_lmem(vma->obj)) {
+		struct intel_memory_region *mem = vma->obj->mm.region;
+		dma_addr_t dma;
+
+		for_each_sgt_daddr(dma, iter, vma->pages) {
+			void __iomem *s;
+
+			s = io_mapping_map_wc(&mem->iomap, dma, PAGE_SIZE);
+			ret = compress_page(compress, (void __force *)s, dst);
+			io_mapping_unmap(s);
+			if (ret)
+				break;
+		}
+	} else {
+		struct page *page;
+
+		for_each_sgt_page(page, iter, vma->pages) {
+			void *s;
+
+			drm_clflush_pages(&page, 1);
+
+			s = kmap(page);
+			ret = compress_page(compress, s, dst);
+			kunmap(s);
+
+			drm_clflush_pages(&page, 1);
+
+			if (ret)
+				break;
+		}
 	}
 
 	if (ret || compress_flush(compress, dst)) {
@@ -1144,8 +1189,6 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 	}
 
 	ee->idle = intel_engine_is_idle(engine);
-	if (!ee->idle)
-		ee->hangcheck_timestamp = engine->hangcheck.action_timestamp;
 	ee->reset_count = i915_reset_engine_count(&dev_priv->gpu_error,
 						  engine);
 
@@ -1563,6 +1606,18 @@ static void capture_reg_state(struct i915_gpu_state *error)
 	if (IS_GEN_RANGE(i915, 8, 11))
 		error->gtt_cache = intel_uncore_read(uncore, HSW_GTT_CACHE_EN);
 
+	if (IS_GEN(i915, 12))
+		error->aux_err = intel_uncore_read(uncore, GEN12_AUX_ERR_DBG);
+
+	if (INTEL_GEN(i915) >= 12) {
+		for (i = 0; i < GEN12_SFC_DONE_MAX; i++) {
+			error->sfc_done[i] =
+				intel_uncore_read(uncore, GEN12_SFC_DONE(i));
+		}
+
+		error->gam_done = intel_uncore_read(uncore, GEN12_GAM_DONE);
+	}
+
 	/* 4: Everything else */
 	if (INTEL_GEN(i915) >= 11) {
 		error->ier = intel_uncore_read(uncore, GEN8_DE_MISC_IER);
@@ -1657,26 +1712,15 @@ static void capture_params(struct i915_gpu_state *error)
 	i915_params_copy(&error->params, &i915_modparams);
 }
 
-static unsigned long capture_find_epoch(const struct i915_gpu_state *error)
-{
-	const struct drm_i915_error_engine *ee;
-	unsigned long epoch = error->capture;
-
-	for (ee = error->engine; ee; ee = ee->next) {
-		if (ee->hangcheck_timestamp &&
-		    time_before(ee->hangcheck_timestamp, epoch))
-			epoch = ee->hangcheck_timestamp;
-	}
-
-	return epoch;
-}
-
 static void capture_finish(struct i915_gpu_state *error)
 {
 	struct i915_ggtt *ggtt = &error->i915->ggtt;
-	const u64 slot = ggtt->error_capture.start;
 
-	ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
+	if (drm_mm_node_allocated(&ggtt->error_capture)) {
+		const u64 slot = ggtt->error_capture.start;
+
+		ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
+	}
 }
 
 #define DAY_AS_SECONDS(x) (24 * 60 * 60 * (x))
@@ -1722,8 +1766,6 @@ i915_capture_gpu_state(struct drm_i915_private *i915)
 	error->overlay = intel_overlay_capture_error_state(i915);
 	error->display = intel_display_capture_error_state(i915);
 
-	error->epoch = capture_find_epoch(error);
-
 	capture_finish(error);
 	compress_fini(&compress);
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 7f1cd0b1fef7..5d2c3372ff99 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -34,7 +34,6 @@ struct i915_gpu_state {
 	ktime_t boottime;
 	ktime_t uptime;
 	unsigned long capture;
-	unsigned long epoch;
 
 	struct drm_i915_private *i915;
 
@@ -75,6 +74,9 @@ struct i915_gpu_state {
 	u32 gab_ctl;
 	u32 gfx_mode;
 	u32 gtt_cache;
+	u32 aux_err; /* gen12 */
+	u32 sfc_done[GEN12_SFC_DONE_MAX]; /* gen12 */
+	u32 gam_done; /* gen12 */
 
 	u32 nfence;
 	u64 fence[I915_MAX_NUM_FENCES];
@@ -86,7 +88,6 @@ struct i915_gpu_state {
 
 		/* Software tracked state */
 		bool idle;
-		unsigned long hangcheck_timestamp;
 		int num_requests;
 		u32 reset_count;
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 572a5c37cc61..dae00f7dd7df 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -45,6 +45,7 @@
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_irq.h"
 #include "gt/intel_gt_pm_irq.h"
+#include "gt/intel_rps.h"
 
 #include "i915_drv.h"
 #include "i915_irq.h"
@@ -320,180 +321,6 @@ void ilk_update_display_irq(struct drm_i915_private *dev_priv,
 	}
 }
 
-static i915_reg_t gen6_pm_iir(struct drm_i915_private *dev_priv)
-{
-	WARN_ON_ONCE(INTEL_GEN(dev_priv) >= 11);
-
-	return INTEL_GEN(dev_priv) >= 8 ? GEN8_GT_IIR(2) : GEN6_PMIIR;
-}
-
-void gen11_reset_rps_interrupts(struct drm_i915_private *dev_priv)
-{
-	struct intel_gt *gt = &dev_priv->gt;
-
-	spin_lock_irq(&gt->irq_lock);
-
-	while (gen11_gt_reset_one_iir(gt, 0, GEN11_GTPM))
-		;
-
-	dev_priv->gt_pm.rps.pm_iir = 0;
-
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-void gen6_reset_rps_interrupts(struct drm_i915_private *dev_priv)
-{
-	struct intel_gt *gt = &dev_priv->gt;
-
-	spin_lock_irq(&gt->irq_lock);
-	gen6_gt_pm_reset_iir(gt, GEN6_PM_RPS_EVENTS);
-	dev_priv->gt_pm.rps.pm_iir = 0;
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-void gen6_enable_rps_interrupts(struct drm_i915_private *dev_priv)
-{
-	struct intel_gt *gt = &dev_priv->gt;
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	if (READ_ONCE(rps->interrupts_enabled))
-		return;
-
-	spin_lock_irq(&gt->irq_lock);
-	WARN_ON_ONCE(rps->pm_iir);
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GTPM));
-	else
-		WARN_ON_ONCE(I915_READ(gen6_pm_iir(dev_priv)) & dev_priv->pm_rps_events);
-
-	rps->interrupts_enabled = true;
-	gen6_gt_pm_enable_irq(gt, dev_priv->pm_rps_events);
-
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-u32 gen6_sanitize_rps_pm_mask(const struct drm_i915_private *i915, u32 mask)
-{
-	return mask & ~i915->gt_pm.rps.pm_intrmsk_mbz;
-}
-
-void gen6_disable_rps_interrupts(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	struct intel_gt *gt = &dev_priv->gt;
-
-	if (!READ_ONCE(rps->interrupts_enabled))
-		return;
-
-	spin_lock_irq(&gt->irq_lock);
-	rps->interrupts_enabled = false;
-
-	I915_WRITE(GEN6_PMINTRMSK, gen6_sanitize_rps_pm_mask(dev_priv, ~0u));
-
-	gen6_gt_pm_disable_irq(gt, GEN6_PM_RPS_EVENTS);
-
-	spin_unlock_irq(&gt->irq_lock);
-	intel_synchronize_irq(dev_priv);
-
-	/* Now that we will not be generating any more work, flush any
-	 * outstanding tasks. As we are called on the RPS idle path,
-	 * we will reset the GPU to minimum frequencies, so the current
-	 * state of the worker can be discarded.
-	 */
-	cancel_work_sync(&rps->work);
-	if (INTEL_GEN(dev_priv) >= 11)
-		gen11_reset_rps_interrupts(dev_priv);
-	else
-		gen6_reset_rps_interrupts(dev_priv);
-}
-
-void gen9_reset_guc_interrupts(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	assert_rpm_wakelock_held(gt->uncore->rpm);
-
-	spin_lock_irq(&gt->irq_lock);
-	gen6_gt_pm_reset_iir(gt, gt->pm_guc_events);
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-void gen9_enable_guc_interrupts(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	assert_rpm_wakelock_held(gt->uncore->rpm);
-
-	spin_lock_irq(&gt->irq_lock);
-	if (!guc->interrupts.enabled) {
-		WARN_ON_ONCE(intel_uncore_read(gt->uncore,
-					       gen6_pm_iir(gt->i915)) &
-			     gt->pm_guc_events);
-		guc->interrupts.enabled = true;
-		gen6_gt_pm_enable_irq(gt, gt->pm_guc_events);
-	}
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-void gen9_disable_guc_interrupts(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	assert_rpm_wakelock_held(gt->uncore->rpm);
-
-	spin_lock_irq(&gt->irq_lock);
-	guc->interrupts.enabled = false;
-
-	gen6_gt_pm_disable_irq(gt, gt->pm_guc_events);
-
-	spin_unlock_irq(&gt->irq_lock);
-	intel_synchronize_irq(gt->i915);
-
-	gen9_reset_guc_interrupts(guc);
-}
-
-void gen11_reset_guc_interrupts(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	spin_lock_irq(&gt->irq_lock);
-	gen11_gt_reset_one_iir(gt, 0, GEN11_GUC);
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-void gen11_enable_guc_interrupts(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	spin_lock_irq(&gt->irq_lock);
-	if (!guc->interrupts.enabled) {
-		u32 events = REG_FIELD_PREP(ENGINE1_MASK, GUC_INTR_GUC2HOST);
-
-		WARN_ON_ONCE(gen11_gt_reset_one_iir(gt, 0, GEN11_GUC));
-		intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, events);
-		intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~events);
-		guc->interrupts.enabled = true;
-	}
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-void gen11_disable_guc_interrupts(struct intel_guc *guc)
-{
-	struct intel_gt *gt = guc_to_gt(guc);
-
-	spin_lock_irq(&gt->irq_lock);
-	guc->interrupts.enabled = false;
-
-	intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_MASK, ~0);
-	intel_uncore_write(gt->uncore, GEN11_GUC_SG_INTR_ENABLE, 0);
-
-	spin_unlock_irq(&gt->irq_lock);
-	intel_synchronize_irq(gt->i915);
-
-	gen11_reset_guc_interrupts(guc);
-}
-
 /**
  * bdw_update_port_irq - update DE port interrupt
  * @dev_priv: driver private
@@ -1065,199 +892,6 @@ int intel_get_crtc_scanline(struct intel_crtc *crtc)
 	return position;
 }
 
-static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv)
-{
-	struct intel_uncore *uncore = &dev_priv->uncore;
-	u32 busy_up, busy_down, max_avg, min_avg;
-	u8 new_delay;
-
-	spin_lock(&mchdev_lock);
-
-	intel_uncore_write16(uncore,
-			     MEMINTRSTS,
-			     intel_uncore_read(uncore, MEMINTRSTS));
-
-	new_delay = dev_priv->ips.cur_delay;
-
-	intel_uncore_write16(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
-	busy_up = intel_uncore_read(uncore, RCPREVBSYTUPAVG);
-	busy_down = intel_uncore_read(uncore, RCPREVBSYTDNAVG);
-	max_avg = intel_uncore_read(uncore, RCBMAXAVG);
-	min_avg = intel_uncore_read(uncore, RCBMINAVG);
-
-	/* Handle RCS change request from hw */
-	if (busy_up > max_avg) {
-		if (dev_priv->ips.cur_delay != dev_priv->ips.max_delay)
-			new_delay = dev_priv->ips.cur_delay - 1;
-		if (new_delay < dev_priv->ips.max_delay)
-			new_delay = dev_priv->ips.max_delay;
-	} else if (busy_down < min_avg) {
-		if (dev_priv->ips.cur_delay != dev_priv->ips.min_delay)
-			new_delay = dev_priv->ips.cur_delay + 1;
-		if (new_delay > dev_priv->ips.min_delay)
-			new_delay = dev_priv->ips.min_delay;
-	}
-
-	if (ironlake_set_drps(dev_priv, new_delay))
-		dev_priv->ips.cur_delay = new_delay;
-
-	spin_unlock(&mchdev_lock);
-
-	return;
-}
-
-static void vlv_c0_read(struct drm_i915_private *dev_priv,
-			struct intel_rps_ei *ei)
-{
-	ei->ktime = ktime_get_raw();
-	ei->render_c0 = I915_READ(VLV_RENDER_C0_COUNT);
-	ei->media_c0 = I915_READ(VLV_MEDIA_C0_COUNT);
-}
-
-void gen6_rps_reset_ei(struct drm_i915_private *dev_priv)
-{
-	memset(&dev_priv->gt_pm.rps.ei, 0, sizeof(dev_priv->gt_pm.rps.ei));
-}
-
-static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	const struct intel_rps_ei *prev = &rps->ei;
-	struct intel_rps_ei now;
-	u32 events = 0;
-
-	if ((pm_iir & GEN6_PM_RP_UP_EI_EXPIRED) == 0)
-		return 0;
-
-	vlv_c0_read(dev_priv, &now);
-
-	if (prev->ktime) {
-		u64 time, c0;
-		u32 render, media;
-
-		time = ktime_us_delta(now.ktime, prev->ktime);
-
-		time *= dev_priv->czclk_freq;
-
-		/* Workload can be split between render + media,
-		 * e.g. SwapBuffers being blitted in X after being rendered in
-		 * mesa. To account for this we need to combine both engines
-		 * into our activity counter.
-		 */
-		render = now.render_c0 - prev->render_c0;
-		media = now.media_c0 - prev->media_c0;
-		c0 = max(render, media);
-		c0 *= 1000 * 100 << 8; /* to usecs and scale to threshold% */
-
-		if (c0 > time * rps->power.up_threshold)
-			events = GEN6_PM_RP_UP_THRESHOLD;
-		else if (c0 < time * rps->power.down_threshold)
-			events = GEN6_PM_RP_DOWN_THRESHOLD;
-	}
-
-	rps->ei = now;
-	return events;
-}
-
-static void gen6_pm_rps_work(struct work_struct *work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(work, struct drm_i915_private, gt_pm.rps.work);
-	struct intel_gt *gt = &dev_priv->gt;
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	bool client_boost = false;
-	int new_delay, adj, min, max;
-	u32 pm_iir = 0;
-
-	spin_lock_irq(&gt->irq_lock);
-	if (rps->interrupts_enabled) {
-		pm_iir = fetch_and_zero(&rps->pm_iir);
-		client_boost = atomic_read(&rps->num_waiters);
-	}
-	spin_unlock_irq(&gt->irq_lock);
-
-	/* Make sure we didn't queue anything we're not going to process. */
-	WARN_ON(pm_iir & ~dev_priv->pm_rps_events);
-	if ((pm_iir & dev_priv->pm_rps_events) == 0 && !client_boost)
-		goto out;
-
-	mutex_lock(&rps->lock);
-
-	pm_iir |= vlv_wa_c0_ei(dev_priv, pm_iir);
-
-	adj = rps->last_adj;
-	new_delay = rps->cur_freq;
-	min = rps->min_freq_softlimit;
-	max = rps->max_freq_softlimit;
-	if (client_boost)
-		max = rps->max_freq;
-	if (client_boost && new_delay < rps->boost_freq) {
-		new_delay = rps->boost_freq;
-		adj = 0;
-	} else if (pm_iir & GEN6_PM_RP_UP_THRESHOLD) {
-		if (adj > 0)
-			adj *= 2;
-		else /* CHV needs even encode values */
-			adj = IS_CHERRYVIEW(dev_priv) ? 2 : 1;
-
-		if (new_delay >= rps->max_freq_softlimit)
-			adj = 0;
-	} else if (client_boost) {
-		adj = 0;
-	} else if (pm_iir & GEN6_PM_RP_DOWN_TIMEOUT) {
-		if (rps->cur_freq > rps->efficient_freq)
-			new_delay = rps->efficient_freq;
-		else if (rps->cur_freq > rps->min_freq_softlimit)
-			new_delay = rps->min_freq_softlimit;
-		adj = 0;
-	} else if (pm_iir & GEN6_PM_RP_DOWN_THRESHOLD) {
-		if (adj < 0)
-			adj *= 2;
-		else /* CHV needs even encode values */
-			adj = IS_CHERRYVIEW(dev_priv) ? -2 : -1;
-
-		if (new_delay <= rps->min_freq_softlimit)
-			adj = 0;
-	} else { /* unknown event */
-		adj = 0;
-	}
-
-	rps->last_adj = adj;
-
-	/*
-	 * Limit deboosting and boosting to keep ourselves at the extremes
-	 * when in the respective power modes (i.e. slowly decrease frequencies
-	 * while in the HIGH_POWER zone and slowly increase frequencies while
-	 * in the LOW_POWER zone). On idle, we will hit the timeout and drop
-	 * to the next level quickly, and conversely if busy we expect to
-	 * hit a waitboost and rapidly switch into max power.
-	 */
-	if ((adj < 0 && rps->power.mode == HIGH_POWER) ||
-	    (adj > 0 && rps->power.mode == LOW_POWER))
-		rps->last_adj = 0;
-
-	/* sysfs frequency interfaces may have snuck in while servicing the
-	 * interrupt
-	 */
-	new_delay += adj;
-	new_delay = clamp_t(int, new_delay, min, max);
-
-	if (intel_set_rps(dev_priv, new_delay)) {
-		DRM_DEBUG_DRIVER("Failed to set new GPU frequency\n");
-		rps->last_adj = 0;
-	}
-
-	mutex_unlock(&rps->lock);
-
-out:
-	/* Make sure not to corrupt PMIMR state used by ringbuffer on GEN6 */
-	spin_lock_irq(&gt->irq_lock);
-	if (rps->interrupts_enabled)
-		gen6_gt_pm_unmask_irq(gt, dev_priv->pm_rps_events);
-	spin_unlock_irq(&gt->irq_lock);
-}
-
-
 /**
  * ivybridge_parity_work - Workqueue called when a parity error interrupt
  * occurred.
@@ -1631,54 +1265,6 @@ static void i9xx_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
 				     res1, res2);
 }
 
-/* The RPS events need forcewake, so we add them to a work queue and mask their
- * IMR bits until the work is done. Other interrupts can be processed without
- * the work queue. */
-void gen11_rps_irq_handler(struct intel_gt *gt, u32 pm_iir)
-{
-	struct drm_i915_private *i915 = gt->i915;
-	struct intel_rps *rps = &i915->gt_pm.rps;
-	const u32 events = i915->pm_rps_events & pm_iir;
-
-	lockdep_assert_held(&gt->irq_lock);
-
-	if (unlikely(!events))
-		return;
-
-	gen6_gt_pm_mask_irq(gt, events);
-
-	if (!rps->interrupts_enabled)
-		return;
-
-	rps->pm_iir |= events;
-	schedule_work(&rps->work);
-}
-
-void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	struct intel_gt *gt = &dev_priv->gt;
-
-	if (pm_iir & dev_priv->pm_rps_events) {
-		spin_lock(&gt->irq_lock);
-		gen6_gt_pm_mask_irq(gt, pm_iir & dev_priv->pm_rps_events);
-		if (rps->interrupts_enabled) {
-			rps->pm_iir |= pm_iir & dev_priv->pm_rps_events;
-			schedule_work(&rps->work);
-		}
-		spin_unlock(&gt->irq_lock);
-	}
-
-	if (INTEL_GEN(dev_priv) >= 8)
-		return;
-
-	if (pm_iir & PM_VEBOX_USER_INTERRUPT)
-		intel_engine_breadcrumbs_irq(dev_priv->engine[VECS0]);
-
-	if (pm_iir & PM_VEBOX_CS_ERROR_INTERRUPT)
-		DRM_DEBUG("Command parser error, pm_iir 0x%08x\n", pm_iir);
-}
-
 static void i9xx_pipestat_irq_reset(struct drm_i915_private *dev_priv)
 {
 	enum pipe pipe;
@@ -1989,7 +1575,7 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 		if (gt_iir)
 			gen6_gt_irq_handler(&dev_priv->gt, gt_iir);
 		if (pm_iir)
-			gen6_rps_irq_handler(dev_priv, pm_iir);
+			gen6_rps_irq_handler(&dev_priv->gt.rps, pm_iir);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
@@ -2393,7 +1979,7 @@ static void ilk_display_irq_handler(struct drm_i915_private *dev_priv,
 	}
 
 	if (IS_GEN(dev_priv, 5) && de_iir & DE_PCU_EVENT)
-		ironlake_rps_change_irq_handler(dev_priv);
+		gen5_rps_irq_handler(&dev_priv->gt.rps);
 }
 
 static void ivb_display_irq_handler(struct drm_i915_private *dev_priv,
@@ -2498,7 +2084,7 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 		if (pm_iir) {
 			I915_WRITE(GEN6_PMIIR, pm_iir);
 			ret = IRQ_HANDLED;
-			gen6_rps_irq_handler(dev_priv, pm_iir);
+			gen6_rps_irq_handler(&dev_priv->gt.rps, pm_iir);
 		}
 	}
 
@@ -2575,10 +2161,16 @@ static u32 gen8_de_port_aux_mask(struct drm_i915_private *dev_priv)
 	u32 mask;
 
 	if (INTEL_GEN(dev_priv) >= 12)
-		/* TODO: Add AUX entries for USBC */
 		return TGL_DE_PORT_AUX_DDIA |
 			TGL_DE_PORT_AUX_DDIB |
-			TGL_DE_PORT_AUX_DDIC;
+			TGL_DE_PORT_AUX_DDIC |
+			TGL_DE_PORT_AUX_USBC1 |
+			TGL_DE_PORT_AUX_USBC2 |
+			TGL_DE_PORT_AUX_USBC3 |
+			TGL_DE_PORT_AUX_USBC4 |
+			TGL_DE_PORT_AUX_USBC5 |
+			TGL_DE_PORT_AUX_USBC6;
+
 
 	mask = GEN8_AUX_CHANNEL_A;
 	if (INTEL_GEN(dev_priv) >= 9)
@@ -2597,7 +2189,9 @@ static u32 gen8_de_port_aux_mask(struct drm_i915_private *dev_priv)
 
 static u32 gen8_de_pipe_fault_mask(struct drm_i915_private *dev_priv)
 {
-	if (INTEL_GEN(dev_priv) >= 9)
+	if (INTEL_GEN(dev_priv) >= 11)
+		return GEN11_DE_PIPE_IRQ_FAULT_ERRORS;
+	else if (INTEL_GEN(dev_priv) >= 9)
 		return GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
 	else
 		return GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
@@ -2859,9 +2453,11 @@ static inline void gen11_master_intr_enable(void __iomem * const regs)
 	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ);
 }
 
-static irqreturn_t gen11_irq_handler(int irq, void *arg)
+static __always_inline irqreturn_t
+__gen11_irq_handler(struct drm_i915_private * const i915,
+		    u32 (*intr_disable)(void __iomem * const regs),
+		    void (*intr_enable)(void __iomem * const regs))
 {
-	struct drm_i915_private * const i915 = arg;
 	void __iomem * const regs = i915->uncore.regs;
 	struct intel_gt *gt = &i915->gt;
 	u32 master_ctl;
@@ -2870,9 +2466,9 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
 	if (!intel_irqs_enabled(i915))
 		return IRQ_NONE;
 
-	master_ctl = gen11_master_intr_disable(regs);
+	master_ctl = intr_disable(regs);
 	if (!master_ctl) {
-		gen11_master_intr_enable(regs);
+		intr_enable(regs);
 		return IRQ_NONE;
 	}
 
@@ -2894,13 +2490,20 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
 
 	gu_misc_iir = gen11_gu_misc_irq_ack(gt, master_ctl);
 
-	gen11_master_intr_enable(regs);
+	intr_enable(regs);
 
 	gen11_gu_misc_irq_handler(gt, gu_misc_iir);
 
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t gen11_irq_handler(int irq, void *arg)
+{
+	return __gen11_irq_handler(arg,
+				   gen11_master_intr_disable,
+				   gen11_master_intr_enable);
+}
+
 /* Called from drm generic code, passed 'crtc' which
  * we use as a pipe index
  */
@@ -4270,13 +3873,10 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 void intel_irq_init(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
 	int i;
 
 	intel_hpd_init_work(dev_priv);
 
-	INIT_WORK(&rps->work, gen6_pm_rps_work);
-
 	INIT_WORK(&dev_priv->l3_parity.error_work, ivybridge_parity_work);
 	for (i = 0; i < MAX_L3_SLICES; ++i)
 		dev_priv->l3_parity.remap_info[i] = NULL;
@@ -4285,33 +3885,6 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 	if (HAS_GT_UC(dev_priv) && INTEL_GEN(dev_priv) < 11)
 		dev_priv->gt.pm_guc_events = GUC_INTR_GUC2HOST << 16;
 
-	/* Let's track the enabled rps events */
-	if (IS_VALLEYVIEW(dev_priv))
-		/* WaGsvRC0ResidencyMethod:vlv */
-		dev_priv->pm_rps_events = GEN6_PM_RP_UP_EI_EXPIRED;
-	else
-		dev_priv->pm_rps_events = (GEN6_PM_RP_UP_THRESHOLD |
-					   GEN6_PM_RP_DOWN_THRESHOLD |
-					   GEN6_PM_RP_DOWN_TIMEOUT);
-
-	/* We share the register with other engine */
-	if (INTEL_GEN(dev_priv) > 9)
-		GEM_WARN_ON(dev_priv->pm_rps_events & 0xffff0000);
-
-	rps->pm_intrmsk_mbz = 0;
-
-	/*
-	 * SNB,IVB,HSW can while VLV,CHV may hard hang on looping batchbuffer
-	 * if GEN6_PM_UP_EI_EXPIRED is masked.
-	 *
-	 * TODO: verify if this can be reproduced on VLV,CHV.
-	 */
-	if (INTEL_GEN(dev_priv) <= 7)
-		rps->pm_intrmsk_mbz |= GEN6_PM_RP_UP_EI_EXPIRED;
-
-	if (INTEL_GEN(dev_priv) >= 8)
-		rps->pm_intrmsk_mbz |= GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC;
-
 	dev->vblank_disable_immediate = true;
 
 	/* Most platforms treat the display irq block as an always-on
diff --git a/drivers/gpu/drm/i915/i915_irq.h b/drivers/gpu/drm/i915/i915_irq.h
index 19a3bc019535..812c47a9c2d6 100644
--- a/drivers/gpu/drm/i915/i915_irq.h
+++ b/drivers/gpu/drm/i915/i915_irq.h
@@ -17,14 +17,8 @@ struct drm_device;
 struct drm_display_mode;
 struct drm_i915_private;
 struct intel_crtc;
-struct intel_crtc;
-struct intel_gt;
-struct intel_guc;
 struct intel_uncore;
 
-void gen11_rps_irq_handler(struct intel_gt *gt, u32 pm_iir);
-void gen6_rps_irq_handler(struct drm_i915_private *dev_priv, u32 pm_iir);
-
 void intel_irq_init(struct drm_i915_private *dev_priv);
 void intel_irq_fini(struct drm_i915_private *dev_priv);
 int intel_irq_install(struct drm_i915_private *dev_priv);
@@ -106,12 +100,6 @@ void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
 				     u8 pipe_mask);
 void gen8_irq_power_well_pre_disable(struct drm_i915_private *dev_priv,
 				     u8 pipe_mask);
-void gen9_reset_guc_interrupts(struct intel_guc *guc);
-void gen9_enable_guc_interrupts(struct intel_guc *guc);
-void gen9_disable_guc_interrupts(struct intel_guc *guc);
-void gen11_reset_guc_interrupts(struct intel_guc *guc);
-void gen11_enable_guc_interrupts(struct intel_guc *guc);
-void gen11_disable_guc_interrupts(struct intel_guc *guc);
 
 bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 			      bool in_vblank_irq, int *vpos, int *hpos,
diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 4f1806f65040..1dd1f3652795 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -166,7 +166,7 @@ i915_param_named_unsafe(enable_dp_mst, bool, 0600,
 	"Enable multi-stream transport (MST) for new DisplayPort sinks. (default: true)");
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
-i915_param_named_unsafe(inject_load_failure, uint, 0400,
+i915_param_named_unsafe(inject_probe_failure, uint, 0400,
 	"Force an error after a number of failure check points (0:disabled (default), N:force failure at the Nth failure check point)");
 #endif
 
@@ -179,6 +179,11 @@ i915_param_named(enable_gvt, bool, 0400,
 	"Enable support for Intel GVT-g graphics virtualization host support(default:false)");
 #endif
 
+#if IS_ENABLED(CONFIG_DRM_I915_UNSTABLE_FAKE_LMEM)
+i915_param_named_unsafe(fake_lmem_start, ulong, 0600,
+	"Fake LMEM start offset (default: 0)");
+#endif
+
 static __always_inline void _print_param(struct drm_printer *p,
 					 const char *name,
 					 const char *type,
@@ -190,6 +195,8 @@ static __always_inline void _print_param(struct drm_printer *p,
 		drm_printf(p, "i915.%s=%d\n", name, *(const int *)x);
 	else if (!__builtin_strcmp(type, "unsigned int"))
 		drm_printf(p, "i915.%s=%u\n", name, *(const unsigned int *)x);
+	else if (!__builtin_strcmp(type, "unsigned long"))
+		drm_printf(p, "i915.%s=%lu\n", name, *(const unsigned long *)x);
 	else if (!__builtin_strcmp(type, "char *"))
 		drm_printf(p, "i915.%s=%s\n", name, *(const char **)x);
 	else
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index d29ade3b7de6..31b88f297fbc 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -61,11 +61,12 @@ struct drm_printer;
 	param(char *, dmc_firmware_path, NULL) \
 	param(int, mmio_debug, -IS_ENABLED(CONFIG_DRM_I915_DEBUG_MMIO)) \
 	param(int, edp_vswing, 0) \
-	param(int, reset, 2) \
-	param(unsigned int, inject_load_failure, 0) \
+	param(int, reset, 3) \
+	param(unsigned int, inject_probe_failure, 0) \
 	param(int, fastboot, -1) \
 	param(int, enable_dpcd_backlight, 0) \
 	param(char *, force_probe, CONFIG_DRM_I915_FORCE_PROBE) \
+	param(unsigned long, fake_lmem_start, 0) \
 	/* leave bools at the end to not create holes */ \
 	param(bool, alpha_support, IS_ENABLED(CONFIG_DRM_I915_ALPHA_SUPPORT)) \
 	param(bool, enable_hangcheck, true) \
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index f9a3bfe68689..1bb701d32a5d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -612,6 +612,7 @@ static const struct intel_device_info intel_cherryview_info = {
 	.has_logical_ring_preemption = 1, \
 	.display.has_csr = 1, \
 	.has_gt_uc = 1, \
+	.display.has_hdcp = 1, \
 	.display.has_ipc = 1, \
 	.ddb_size = 896
 
@@ -655,6 +656,7 @@ static const struct intel_device_info intel_skylake_gt4_info = {
 	.display.has_ddi = 1, \
 	.has_fpga_dbg = 1, \
 	.display.has_fbc = 1, \
+	.display.has_hdcp = 1, \
 	.display.has_psr = 1, \
 	.has_runtime_pm = 1, \
 	.display.has_csr = 1, \
@@ -735,6 +737,7 @@ static const struct intel_device_info intel_coffeelake_gt3_info = {
 	GEN9_FEATURES, \
 	GEN(10), \
 	.ddb_size = 1024, \
+	.display.has_dsc = 1, \
 	.has_coherent_ggtt = false, \
 	GLK_COLORS
 
@@ -822,6 +825,10 @@ static const struct intel_device_info intel_tigerlake_12_info = {
 	.has_rps = false, /* XXX disabled for debugging */
 };
 
+#define GEN12_DGFX_FEATURES \
+	GEN12_FEATURES, \
+	.is_dgfx = 1
+
 #undef GEN
 #undef PLATFORM
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index d2ac51fe4f04..65d7c2e599de 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -200,6 +200,7 @@
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_lrc_reg.h"
+#include "gt/intel_ring.h"
 
 #include "i915_drv.h"
 #include "i915_perf.h"
@@ -217,6 +218,7 @@
 #include "oa/i915_oa_cflgt3.h"
 #include "oa/i915_oa_cnl.h"
 #include "oa/i915_oa_icl.h"
+#include "oa/i915_oa_tgl.h"
 
 /* HW requires this to be a power of two, between 128k and 16M, though driver
  * is currently generally designed assuming the largest 16M size is used such
@@ -293,6 +295,7 @@ static u32 i915_perf_stream_paranoid = true;
 
 /* On Gen8+ automatically triggered OA reports include a 'reason' field... */
 #define OAREPORT_REASON_MASK           0x3f
+#define OAREPORT_REASON_MASK_EXTENDED  0x7f
 #define OAREPORT_REASON_SHIFT          19
 #define OAREPORT_REASON_TIMER          (1<<0)
 #define OAREPORT_REASON_CTX_SWITCH     (1<<3)
@@ -338,6 +341,10 @@ static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_C4_B8]		    = { 7, 64 },
 };
 
+static const struct i915_oa_format gen12_oa_formats[I915_OA_FORMAT_MAX] = {
+	[I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 },
+};
+
 #define SAMPLE_OA_REPORT      (1<<0)
 
 /**
@@ -418,6 +425,14 @@ static void free_oa_config_bo(struct i915_oa_config_bo *oa_bo)
 	kfree(oa_bo);
 }
 
+static u32 gen12_oa_hw_tail_read(struct i915_perf_stream *stream)
+{
+	struct intel_uncore *uncore = stream->uncore;
+
+	return intel_uncore_read(uncore, GEN12_OAG_OATAILPTR) &
+	       GEN12_OAG_OATAILPTR_MASK;
+}
+
 static u32 gen8_oa_hw_tail_read(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
@@ -538,7 +553,7 @@ static bool oa_buffer_check_unlocked(struct i915_perf_stream *stream)
 				aging_tail = hw_tail;
 			stream->oa_buffer.aging_timestamp = now;
 		} else {
-			DRM_ERROR("Ignoring spurious out of range OA buffer tail pointer = %u\n",
+			DRM_ERROR("Ignoring spurious out of range OA buffer tail pointer = %x\n",
 				  hw_tail);
 		}
 	}
@@ -740,7 +755,9 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * it to userspace...
 		 */
 		reason = ((report32[0] >> OAREPORT_REASON_SHIFT) &
-			  OAREPORT_REASON_MASK);
+			  (IS_GEN(stream->perf->i915, 12) ?
+			   OAREPORT_REASON_MASK_EXTENDED :
+			   OAREPORT_REASON_MASK));
 		if (reason == 0) {
 			if (__ratelimit(&stream->perf->spurious_report_rs))
 				DRM_NOTE("Skipping spurious, invalid OA report\n");
@@ -757,7 +774,8 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * Note: that we don't clear the valid_ctx_bit so userspace can
 		 * understand that the ID has been squashed by the kernel.
 		 */
-		if (!(report32[0] & stream->perf->gen8_valid_ctx_bit))
+		if (!(report32[0] & stream->perf->gen8_valid_ctx_bit) &&
+		    INTEL_GEN(stream->perf->i915) <= 11)
 			ctx_id = report32[2] = INVALID_CTX_ID;
 
 		/*
@@ -824,6 +842,11 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 	}
 
 	if (start_offset != *offset) {
+		i915_reg_t oaheadptr;
+
+		oaheadptr = IS_GEN(stream->perf->i915, 12) ?
+			    GEN12_OAG_OAHEADPTR : GEN8_OAHEADPTR;
+
 		spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
 
 		/*
@@ -831,9 +854,8 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 		 * relative to oa_buf_base so put back here...
 		 */
 		head += gtt_offset;
-
-		intel_uncore_write(uncore, GEN8_OAHEADPTR,
-				   head & GEN8_OAHEADPTR_MASK);
+		intel_uncore_write(uncore, oaheadptr,
+				   head & GEN12_OAG_OAHEADPTR_MASK);
 		stream->oa_buffer.head = head;
 
 		spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
@@ -869,12 +891,16 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 {
 	struct intel_uncore *uncore = stream->uncore;
 	u32 oastatus;
+	i915_reg_t oastatus_reg;
 	int ret;
 
 	if (WARN_ON(!stream->oa_buffer.vaddr))
 		return -EIO;
 
-	oastatus = intel_uncore_read(uncore, GEN8_OASTATUS);
+	oastatus_reg = IS_GEN(stream->perf->i915, 12) ?
+		       GEN12_OAG_OASTATUS : GEN8_OASTATUS;
+
+	oastatus = intel_uncore_read(uncore, oastatus_reg);
 
 	/*
 	 * We treat OABUFFER_OVERFLOW as a significant error:
@@ -906,7 +932,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 		 * Note: .oa_enable() is expected to re-init the oabuffer and
 		 * reset GEN8_OASTATUS for us
 		 */
-		oastatus = intel_uncore_read(uncore, GEN8_OASTATUS);
+		oastatus = intel_uncore_read(uncore, oastatus_reg);
 	}
 
 	if (oastatus & GEN8_OASTATUS_REPORT_LOST) {
@@ -914,7 +940,7 @@ static int gen8_oa_read(struct i915_perf_stream *stream,
 				       DRM_I915_PERF_RECORD_OA_REPORT_LOST);
 		if (ret)
 			return ret;
-		intel_uncore_write(uncore, GEN8_OASTATUS,
+		intel_uncore_write(uncore, oastatus_reg,
 				   oastatus & ~GEN8_OASTATUS_REPORT_LOST);
 	}
 
@@ -1260,7 +1286,11 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 	case 8:
 	case 9:
 	case 10:
-		if (USES_GUC_SUBMISSION(ce->engine->i915)) {
+		if (intel_engine_in_execlists_submission_mode(ce->engine)) {
+			stream->specific_ctx_id_mask =
+				(1U << GEN8_CTX_ID_WIDTH) - 1;
+			stream->specific_ctx_id = stream->specific_ctx_id_mask;
+		} else {
 			/*
 			 * When using GuC, the context descriptor we write in
 			 * i915 is read by GuC and rewritten before it's
@@ -1280,10 +1310,6 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			 */
 			stream->specific_ctx_id_mask =
 				(1U << (GEN8_CTX_ID_WIDTH - 1)) - 1;
-		} else {
-			stream->specific_ctx_id_mask =
-				(1U << GEN8_CTX_ID_WIDTH) - 1;
-			stream->specific_ctx_id = stream->specific_ctx_id_mask;
 		}
 		break;
 
@@ -1488,6 +1514,63 @@ static void gen8_init_oa_buffer(struct i915_perf_stream *stream)
 	stream->pollin = false;
 }
 
+static void gen12_init_oa_buffer(struct i915_perf_stream *stream)
+{
+	struct intel_uncore *uncore = stream->uncore;
+	u32 gtt_offset = i915_ggtt_offset(stream->oa_buffer.vma);
+	unsigned long flags;
+
+	spin_lock_irqsave(&stream->oa_buffer.ptr_lock, flags);
+
+	intel_uncore_write(uncore, GEN12_OAG_OASTATUS, 0);
+	intel_uncore_write(uncore, GEN12_OAG_OAHEADPTR,
+			   gtt_offset & GEN12_OAG_OAHEADPTR_MASK);
+	stream->oa_buffer.head = gtt_offset;
+
+	/*
+	 * PRM says:
+	 *
+	 *  "This MMIO must be set before the OATAILPTR
+	 *  register and after the OAHEADPTR register. This is
+	 *  to enable proper functionality of the overflow
+	 *  bit."
+	 */
+	intel_uncore_write(uncore, GEN12_OAG_OABUFFER, gtt_offset |
+			   OABUFFER_SIZE_16M | GEN8_OABUFFER_MEM_SELECT_GGTT);
+	intel_uncore_write(uncore, GEN12_OAG_OATAILPTR,
+			   gtt_offset & GEN12_OAG_OATAILPTR_MASK);
+
+	/* Mark that we need updated tail pointers to read from... */
+	stream->oa_buffer.tails[0].offset = INVALID_TAIL_PTR;
+	stream->oa_buffer.tails[1].offset = INVALID_TAIL_PTR;
+
+	/*
+	 * Reset state used to recognise context switches, affecting which
+	 * reports we will forward to userspace while filtering for a single
+	 * context.
+	 */
+	stream->oa_buffer.last_ctx_id = INVALID_CTX_ID;
+
+	spin_unlock_irqrestore(&stream->oa_buffer.ptr_lock, flags);
+
+	/*
+	 * NB: although the OA buffer will initially be allocated
+	 * zeroed via shmfs (and so this memset is redundant when
+	 * first allocating), we may re-init the OA buffer, either
+	 * when re-enabling a stream or in error/reset paths.
+	 *
+	 * The reason we clear the buffer for each re-init is for the
+	 * sanity check in gen8_append_oa_reports() that looks at the
+	 * reason field to make sure it's non-zero which relies on
+	 * the assumption that new reports are being written to zeroed
+	 * memory...
+	 */
+	memset(stream->oa_buffer.vaddr, 0,
+	       stream->oa_buffer.vma->size);
+
+	stream->pollin = false;
+}
+
 static int alloc_oa_buffer(struct i915_perf_stream *stream)
 {
 	struct drm_i915_gem_object *bo;
@@ -1787,7 +1870,7 @@ alloc_oa_config_buffer(struct i915_perf_stream *stream,
 	config_length += num_lri_dwords(oa_config->mux_regs_len);
 	config_length += num_lri_dwords(oa_config->b_counter_regs_len);
 	config_length += num_lri_dwords(oa_config->flex_regs_len);
-	config_length++; /* MI_BATCH_BUFFER_END */
+	config_length += 3; /* MI_BATCH_BUFFER_START */
 	config_length = ALIGN(sizeof(u32) * config_length, I915_GTT_PAGE_SIZE);
 
 	obj = i915_gem_object_create_shmem(stream->perf->i915, config_length);
@@ -1812,7 +1895,12 @@ alloc_oa_config_buffer(struct i915_perf_stream *stream,
 			     oa_config->flex_regs,
 			     oa_config->flex_regs_len);
 
-	*cs++ = MI_BATCH_BUFFER_END;
+	/* Jump into the active wait. */
+	*cs++ = (INTEL_GEN(stream->perf->i915) < 8 ?
+		 MI_BATCH_BUFFER_START :
+		 MI_BATCH_BUFFER_START_GEN8);
+	*cs++ = i915_ggtt_offset(stream->noa_wait);
+	*cs++ = 0;
 
 	i915_gem_object_flush_map(obj);
 	i915_gem_object_unpin_map(obj);
@@ -1990,12 +2078,20 @@ gen8_update_reg_state_unlocked(const struct intel_context *ce,
 	u32 *reg_state = ce->lrc_reg_state;
 	int i;
 
-	reg_state[ctx_oactxctrl + 1] =
-		(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
-		(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
-		GEN8_OA_COUNTER_RESUME;
+	if (IS_GEN(stream->perf->i915, 12)) {
+		u32 format = stream->oa_buffer.format;
+
+		reg_state[ctx_oactxctrl + 1] =
+			(format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
+			(stream->oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0);
+	} else {
+		reg_state[ctx_oactxctrl + 1] =
+			(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
+			(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
+			GEN8_OA_COUNTER_RESUME;
+	}
 
-	for (i = 0; i < ARRAY_SIZE(flex_regs); i++)
+	for (i = 0; !!ctx_flexeu0 && i < ARRAY_SIZE(flex_regs); i++)
 		reg_state[ctx_flexeu0 + i * 2 + 1] =
 			oa_config_flex_reg(stream->oa_config, flex_regs[i]);
 
@@ -2128,6 +2224,36 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
 	return err;
 }
 
+static int gen12_emit_oar_config(struct intel_context *ce, bool enable)
+{
+	struct i915_request *rq;
+	u32 *cs;
+	int err = 0;
+
+	rq = i915_request_create(ce);
+	if (IS_ERR(rq))
+		return PTR_ERR(rq);
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs)) {
+		err = PTR_ERR(cs);
+		goto out;
+	}
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_CONTEXT_CONTROL(ce->engine->mmio_base));
+	*cs++ = _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
+			      enable ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0);
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+
+out:
+	i915_request_add(rq);
+
+	return err;
+}
+
 /*
  * Manages updating the per-context aspects of the OA stream
  * configuration across all contexts.
@@ -2152,8 +2278,8 @@ static int gen8_configure_context(struct i915_gem_context *ctx,
  *
  * Note: it's only the RCS/Render context that has any OA state.
  */
-static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
-				       const struct i915_oa_config *oa_config)
+static int lrc_configure_all_contexts(struct i915_perf_stream *stream,
+				      const struct i915_oa_config *oa_config)
 {
 	struct drm_i915_private *i915 = stream->perf->i915;
 	/* The MMIO offsets for Flex EU registers aren't contiguous */
@@ -2165,11 +2291,9 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 			CTX_R_PWR_CLK_STATE,
 		},
 		{
-			GEN8_OACTXCONTROL,
+			IS_GEN(i915, 12) ?
+			GEN12_OAR_OACONTROL : GEN8_OACTXCONTROL,
 			stream->perf->ctx_oactxctrl_offset + 1,
-			((stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
-			 (stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
-			 GEN8_OA_COUNTER_RESUME)
 		},
 		{ EU_PERF_CNTL0, ctx_flexeuN(0) },
 		{ EU_PERF_CNTL1, ctx_flexeuN(1) },
@@ -2182,9 +2306,23 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 #undef ctx_flexeuN
 	struct intel_engine_cs *engine;
 	struct i915_gem_context *ctx, *cn;
+	size_t array_size = IS_GEN(i915, 12) ? 2 : ARRAY_SIZE(regs);
 	int i, err;
 
-	for (i = 2; i < ARRAY_SIZE(regs); i++)
+	if (IS_GEN(i915, 12)) {
+		u32 format = stream->oa_buffer.format;
+
+		regs[1].value =
+			(format << GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT) |
+			(oa_config ? GEN12_OAR_OACONTROL_COUNTER_ENABLE : 0);
+	} else {
+		regs[1].value =
+			(stream->period_exponent << GEN8_OA_TIMER_PERIOD_SHIFT) |
+			(stream->periodic ? GEN8_OA_TIMER_ENABLE : 0) |
+			GEN8_OA_COUNTER_RESUME;
+	}
+
+	for (i = 2; !!ctx_flexeu0 && i < array_size; i++)
 		regs[i].value = oa_config_flex_reg(oa_config, regs[i].reg);
 
 	lockdep_assert_held(&stream->perf->lock);
@@ -2215,7 +2353,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 
 		spin_unlock(&i915->gem.contexts.lock);
 
-		err = gen8_configure_context(ctx, regs, ARRAY_SIZE(regs));
+		err = gen8_configure_context(ctx, regs, array_size);
 		if (err) {
 			i915_gem_context_put(ctx);
 			return err;
@@ -2240,7 +2378,7 @@ static int gen8_configure_all_contexts(struct i915_perf_stream *stream,
 
 		regs[0].value = intel_sseu_make_rpcs(i915, &ce->sseu);
 
-		err = gen8_modify_self(ce, regs, ARRAY_SIZE(regs));
+		err = gen8_modify_self(ce, regs, array_size);
 		if (err)
 			return err;
 	}
@@ -2288,19 +2426,69 @@ static int gen8_enable_metric_set(struct i915_perf_stream *stream)
 	 * to make sure all slices/subslices are ON before writing to NOA
 	 * registers.
 	 */
-	ret = gen8_configure_all_contexts(stream, oa_config);
+	ret = lrc_configure_all_contexts(stream, oa_config);
 	if (ret)
 		return ret;
 
 	return emit_oa_config(stream, oa_config, oa_context(stream));
 }
 
+static int gen12_enable_metric_set(struct i915_perf_stream *stream)
+{
+	struct intel_uncore *uncore = stream->uncore;
+	struct i915_oa_config *oa_config = stream->oa_config;
+	bool periodic = stream->periodic;
+	u32 period_exponent = stream->period_exponent;
+	int ret;
+
+	intel_uncore_write(uncore, GEN12_OAG_OA_DEBUG,
+			   /* Disable clk ratio reports, like previous Gens. */
+			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS |
+					      GEN12_OAG_OA_DEBUG_INCLUDE_CLK_RATIO) |
+			   /*
+			    * If the user didn't require OA reports, instruct the
+			    * hardware not to emit ctx switch reports.
+			    */
+			   !(stream->sample_flags & SAMPLE_OA_REPORT) ?
+			   _MASKED_BIT_ENABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS) :
+			   _MASKED_BIT_DISABLE(GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS));
+
+	intel_uncore_write(uncore, GEN12_OAG_OAGLBCTXCTRL, periodic ?
+			   (GEN12_OAG_OAGLBCTXCTRL_COUNTER_RESUME |
+			    GEN12_OAG_OAGLBCTXCTRL_TIMER_ENABLE |
+			    (period_exponent << GEN12_OAG_OAGLBCTXCTRL_TIMER_PERIOD_SHIFT))
+			    : 0);
+
+	/*
+	 * Update all contexts prior writing the mux configurations as we need
+	 * to make sure all slices/subslices are ON before writing to NOA
+	 * registers.
+	 */
+	ret = lrc_configure_all_contexts(stream, oa_config);
+	if (ret)
+		return ret;
+
+	/*
+	 * For Gen12, performance counters are context
+	 * saved/restored. Only enable it for the context that
+	 * requested this.
+	 */
+	if (stream->ctx) {
+		ret = gen12_emit_oar_config(stream->pinned_ctx,
+					    oa_config != NULL);
+		if (ret)
+			return ret;
+	}
+
+	return emit_oa_config(stream, oa_config, oa_context(stream));
+}
+
 static void gen8_disable_metric_set(struct i915_perf_stream *stream)
 {
 	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
-	gen8_configure_all_contexts(stream, NULL);
+	lrc_configure_all_contexts(stream, NULL);
 
 	intel_uncore_rmw(uncore, GDT_CHICKEN_BITS, GT_NOA_ENABLE, 0);
 }
@@ -2310,7 +2498,22 @@ static void gen10_disable_metric_set(struct i915_perf_stream *stream)
 	struct intel_uncore *uncore = stream->uncore;
 
 	/* Reset all contexts' slices/subslices configurations. */
-	gen8_configure_all_contexts(stream, NULL);
+	lrc_configure_all_contexts(stream, NULL);
+
+	/* Make sure we disable noa to save power. */
+	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
+}
+
+static void gen12_disable_metric_set(struct i915_perf_stream *stream)
+{
+	struct intel_uncore *uncore = stream->uncore;
+
+	/* Reset all contexts' slices/subslices configurations. */
+	lrc_configure_all_contexts(stream, NULL);
+
+	/* disable the context save/restore or OAR counters */
+	if (stream->ctx)
+		gen12_emit_oar_config(stream->pinned_ctx, false);
 
 	/* Make sure we disable noa to save power. */
 	intel_uncore_rmw(uncore, RPM_CONFIG1, GEN10_GT_NOA_ENABLE, 0);
@@ -2372,6 +2575,25 @@ static void gen8_oa_enable(struct i915_perf_stream *stream)
 			   GEN8_OA_COUNTER_ENABLE);
 }
 
+static void gen12_oa_enable(struct i915_perf_stream *stream)
+{
+	struct intel_uncore *uncore = stream->uncore;
+	u32 report_format = stream->oa_buffer.format;
+
+	/*
+	 * If we don't want OA reports from the OA buffer, then we don't even
+	 * need to program the OAG unit.
+	 */
+	if (!(stream->sample_flags & SAMPLE_OA_REPORT))
+		return;
+
+	gen12_init_oa_buffer(stream);
+
+	intel_uncore_write(uncore, GEN12_OAG_OACONTROL,
+			   (report_format << GEN12_OAG_OACONTROL_OA_COUNTER_FORMAT_SHIFT) |
+			   GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE);
+}
+
 /**
  * i915_oa_stream_enable - handle `I915_PERF_IOCTL_ENABLE` for OA stream
  * @stream: An i915 perf stream opened for OA metrics
@@ -2413,6 +2635,18 @@ static void gen8_oa_disable(struct i915_perf_stream *stream)
 		DRM_ERROR("wait for OA to be disabled timed out\n");
 }
 
+static void gen12_oa_disable(struct i915_perf_stream *stream)
+{
+	struct intel_uncore *uncore = stream->uncore;
+
+	intel_uncore_write(uncore, GEN12_OAG_OACONTROL, 0);
+	if (intel_wait_for_register(uncore,
+				    GEN12_OAG_OACONTROL,
+				    GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE, 0,
+				    50))
+		DRM_ERROR("wait for OA to be disabled timed out\n");
+}
+
 /**
  * i915_oa_stream_disable - handle `I915_PERF_IOCTL_DISABLE` for OA stream
  * @stream: An i915 perf stream opened for OA metrics
@@ -2614,8 +2848,7 @@ void i915_oa_init_reg_state(const struct intel_context *ce,
 {
 	struct i915_perf_stream *stream;
 
-	/* perf.exclusive_stream serialised by gen8_configure_all_contexts() */
-	lockdep_assert_held(&ce->pin_mutex);
+	/* perf.exclusive_stream serialised by lrc_configure_all_contexts() */
 
 	if (engine->class != RENDER_CLASS)
 		return;
@@ -3079,32 +3312,40 @@ i915_perf_open_ioctl_locked(struct i915_perf *perf,
 		}
 	}
 
-	if (props->hold_preemption) {
-		if (!props->single_context) {
-			DRM_DEBUG("preemption disable with no context\n");
-			ret = -EINVAL;
-			goto err;
-		}
-		privileged_op = true;
-	}
-
 	/*
 	 * On Haswell the OA unit supports clock gating off for a specific
 	 * context and in this mode there's no visibility of metrics for the
 	 * rest of the system, which we consider acceptable for a
 	 * non-privileged client.
 	 *
-	 * For Gen8+ the OA unit no longer supports clock gating off for a
+	 * For Gen8->11 the OA unit no longer supports clock gating off for a
 	 * specific context and the kernel can't securely stop the counters
 	 * from updating as system-wide / global values. Even though we can
 	 * filter reports based on the included context ID we can't block
 	 * clients from seeing the raw / global counter values via
 	 * MI_REPORT_PERF_COUNT commands and so consider it a privileged op to
 	 * enable the OA unit by default.
+	 *
+	 * For Gen12+ we gain a new OAR unit that only monitors the RCS on a
+	 * per context basis. So we can relax requirements there if the user
+	 * doesn't request global stream access (i.e. query based sampling
+	 * using MI_RECORD_PERF_COUNT.
 	 */
-	if (IS_HASWELL(perf->i915) && specific_ctx && !props->hold_preemption)
+	if (IS_HASWELL(perf->i915) && specific_ctx)
+		privileged_op = false;
+	else if (IS_GEN(perf->i915, 12) && specific_ctx &&
+		 (props->sample_flags & SAMPLE_OA_REPORT) == 0)
 		privileged_op = false;
 
+	if (props->hold_preemption) {
+		if (!props->single_context) {
+			DRM_DEBUG("preemption disable with no context\n");
+			ret = -EINVAL;
+			goto err;
+		}
+		privileged_op = true;
+	}
+
 	/* Similar to perf's kernel.perf_paranoid_cpu sysctl option
 	 * we check a dev.i915.perf_stream_paranoid sysctl option
 	 * to determine if it's ok to access system wide OA counters
@@ -3418,7 +3659,9 @@ void i915_perf_register(struct drm_i915_private *i915)
 
 	sysfs_attr_init(&perf->test_config.sysfs_metric_id.attr);
 
-	if (INTEL_GEN(i915) >= 11) {
+	if (IS_TIGERLAKE(i915)) {
+		i915_perf_load_test_config_tgl(i915);
+	} else if (INTEL_GEN(i915) >= 11) {
 		i915_perf_load_test_config_icl(i915);
 	} else if (IS_CANNONLAKE(i915)) {
 		i915_perf_load_test_config_cnl(i915);
@@ -3515,56 +3758,80 @@ static bool gen8_is_valid_flex_addr(struct i915_perf *perf, u32 addr)
 	return false;
 }
 
+#define ADDR_IN_RANGE(addr, start, end) \
+	((addr) >= (start) && \
+	 (addr) <= (end))
+
+#define REG_IN_RANGE(addr, start, end) \
+	((addr) >= i915_mmio_reg_offset(start) && \
+	 (addr) <= i915_mmio_reg_offset(end))
+
+#define REG_EQUAL(addr, mmio) \
+	((addr) == i915_mmio_reg_offset(mmio))
+
 static bool gen7_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
 {
-	return (addr >= i915_mmio_reg_offset(OASTARTTRIG1) &&
-		addr <= i915_mmio_reg_offset(OASTARTTRIG8)) ||
-		(addr >= i915_mmio_reg_offset(OAREPORTTRIG1) &&
-		 addr <= i915_mmio_reg_offset(OAREPORTTRIG8)) ||
-		(addr >= i915_mmio_reg_offset(OACEC0_0) &&
-		 addr <= i915_mmio_reg_offset(OACEC7_1));
+	return REG_IN_RANGE(addr, OASTARTTRIG1, OASTARTTRIG8) ||
+	       REG_IN_RANGE(addr, OAREPORTTRIG1, OAREPORTTRIG8) ||
+	       REG_IN_RANGE(addr, OACEC0_0, OACEC7_1);
 }
 
 static bool gen7_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
-	return addr == i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) ||
-		(addr >= i915_mmio_reg_offset(MICRO_BP0_0) &&
-		 addr <= i915_mmio_reg_offset(NOA_WRITE)) ||
-		(addr >= i915_mmio_reg_offset(OA_PERFCNT1_LO) &&
-		 addr <= i915_mmio_reg_offset(OA_PERFCNT2_HI)) ||
-		(addr >= i915_mmio_reg_offset(OA_PERFMATRIX_LO) &&
-		 addr <= i915_mmio_reg_offset(OA_PERFMATRIX_HI));
+	return REG_EQUAL(addr, HALF_SLICE_CHICKEN2) ||
+	       REG_IN_RANGE(addr, MICRO_BP0_0, NOA_WRITE) ||
+	       REG_IN_RANGE(addr, OA_PERFCNT1_LO, OA_PERFCNT2_HI) ||
+	       REG_IN_RANGE(addr, OA_PERFMATRIX_LO, OA_PERFMATRIX_HI);
 }
 
 static bool gen8_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return gen7_is_valid_mux_addr(perf, addr) ||
-		addr == i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) ||
-		(addr >= i915_mmio_reg_offset(RPM_CONFIG0) &&
-		 addr <= i915_mmio_reg_offset(NOA_CONFIG(8)));
+	       REG_EQUAL(addr, WAIT_FOR_RC6_EXIT) ||
+	       REG_IN_RANGE(addr, RPM_CONFIG0, NOA_CONFIG(8));
 }
 
 static bool gen10_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return gen8_is_valid_mux_addr(perf, addr) ||
-		addr == i915_mmio_reg_offset(GEN10_NOA_WRITE_HIGH) ||
-		(addr >= i915_mmio_reg_offset(OA_PERFCNT3_LO) &&
-		 addr <= i915_mmio_reg_offset(OA_PERFCNT4_HI));
+	       REG_EQUAL(addr, GEN10_NOA_WRITE_HIGH) ||
+	       REG_IN_RANGE(addr, OA_PERFCNT3_LO, OA_PERFCNT4_HI);
 }
 
 static bool hsw_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return gen7_is_valid_mux_addr(perf, addr) ||
-		(addr >= 0x25100 && addr <= 0x2FF90) ||
-		(addr >= i915_mmio_reg_offset(HSW_MBVID2_NOA0) &&
-		 addr <= i915_mmio_reg_offset(HSW_MBVID2_NOA9)) ||
-		addr == i915_mmio_reg_offset(HSW_MBVID2_MISR0);
+	       ADDR_IN_RANGE(addr, 0x25100, 0x2FF90) ||
+	       REG_IN_RANGE(addr, HSW_MBVID2_NOA0, HSW_MBVID2_NOA9) ||
+	       REG_EQUAL(addr, HSW_MBVID2_MISR0);
 }
 
 static bool chv_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
 {
 	return gen7_is_valid_mux_addr(perf, addr) ||
-		(addr >= 0x182300 && addr <= 0x1823A4);
+	       ADDR_IN_RANGE(addr, 0x182300, 0x1823A4);
+}
+
+static bool gen12_is_valid_b_counter_addr(struct i915_perf *perf, u32 addr)
+{
+	return REG_IN_RANGE(addr, GEN12_OAG_OASTARTTRIG1, GEN12_OAG_OASTARTTRIG8) ||
+	       REG_IN_RANGE(addr, GEN12_OAG_OAREPORTTRIG1, GEN12_OAG_OAREPORTTRIG8) ||
+	       REG_IN_RANGE(addr, GEN12_OAG_CEC0_0, GEN12_OAG_CEC7_1) ||
+	       REG_IN_RANGE(addr, GEN12_OAG_SCEC0_0, GEN12_OAG_SCEC7_1) ||
+	       REG_EQUAL(addr, GEN12_OAA_DBG_REG) ||
+	       REG_EQUAL(addr, GEN12_OAG_OA_PESS) ||
+	       REG_EQUAL(addr, GEN12_OAG_SPCTR_CNF);
+}
+
+static bool gen12_is_valid_mux_addr(struct i915_perf *perf, u32 addr)
+{
+	return REG_EQUAL(addr, NOA_WRITE) ||
+	       REG_EQUAL(addr, GEN10_NOA_WRITE_HIGH) ||
+	       REG_EQUAL(addr, GDT_CHICKEN_BITS) ||
+	       REG_EQUAL(addr, WAIT_FOR_RC6_EXIT) ||
+	       REG_EQUAL(addr, RPM_CONFIG0) ||
+	       REG_EQUAL(addr, RPM_CONFIG1) ||
+	       REG_IN_RANGE(addr, NOA_CONFIG(0), NOA_CONFIG(8));
 }
 
 static u32 mask_reg_value(u32 reg, u32 val)
@@ -3573,14 +3840,14 @@ static u32 mask_reg_value(u32 reg, u32 val)
 	 * WaDisableSTUnitPowerOptimization workaround. Make sure the value
 	 * programmed by userspace doesn't change this.
 	 */
-	if (i915_mmio_reg_offset(HALF_SLICE_CHICKEN2) == reg)
+	if (REG_EQUAL(reg, HALF_SLICE_CHICKEN2))
 		val = val & ~_MASKED_BIT_ENABLE(GEN8_ST_PO_DISABLE);
 
 	/* WAIT_FOR_RC6_EXIT has only one bit fullfilling the function
 	 * indicated by its name and a bunch of selection fields used by OA
 	 * configs.
 	 */
-	if (i915_mmio_reg_offset(WAIT_FOR_RC6_EXIT) == reg)
+	if (REG_EQUAL(reg, WAIT_FOR_RC6_EXIT))
 		val = val & ~_MASKED_BIT_ENABLE(HSW_WAIT_FOR_RC6_EXIT_ENABLE);
 
 	return val;
@@ -3959,14 +4226,11 @@ void i915_perf_init(struct drm_i915_private *i915)
 		 * worth the complexity to maintain now that BDW+ enable
 		 * execlist mode by default.
 		 */
-		perf->oa_formats = gen8_plus_oa_formats;
-
-		perf->ops.oa_enable = gen8_oa_enable;
-		perf->ops.oa_disable = gen8_oa_disable;
 		perf->ops.read = gen8_oa_read;
-		perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 
 		if (IS_GEN_RANGE(i915, 8, 9)) {
+			perf->oa_formats = gen8_plus_oa_formats;
+
 			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
 			perf->ops.is_valid_mux_reg =
@@ -3979,8 +4243,11 @@ void i915_perf_init(struct drm_i915_private *i915)
 					chv_is_valid_mux_addr;
 			}
 
+			perf->ops.oa_enable = gen8_oa_enable;
+			perf->ops.oa_disable = gen8_oa_disable;
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
 			perf->ops.disable_metric_set = gen8_disable_metric_set;
+			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 
 			if (IS_GEN(i915, 8)) {
 				perf->ctx_oactxctrl_offset = 0x120;
@@ -3994,6 +4261,8 @@ void i915_perf_init(struct drm_i915_private *i915)
 				perf->gen8_valid_ctx_bit = BIT(16);
 			}
 		} else if (IS_GEN_RANGE(i915, 10, 11)) {
+			perf->oa_formats = gen8_plus_oa_formats;
+
 			perf->ops.is_valid_b_counter_reg =
 				gen7_is_valid_b_counter_addr;
 			perf->ops.is_valid_mux_reg =
@@ -4001,8 +4270,11 @@ void i915_perf_init(struct drm_i915_private *i915)
 			perf->ops.is_valid_flex_reg =
 				gen8_is_valid_flex_addr;
 
+			perf->ops.oa_enable = gen8_oa_enable;
+			perf->ops.oa_disable = gen8_oa_disable;
 			perf->ops.enable_metric_set = gen8_enable_metric_set;
 			perf->ops.disable_metric_set = gen10_disable_metric_set;
+			perf->ops.oa_hw_tail_read = gen8_oa_hw_tail_read;
 
 			if (IS_GEN(i915, 10)) {
 				perf->ctx_oactxctrl_offset = 0x128;
@@ -4012,6 +4284,24 @@ void i915_perf_init(struct drm_i915_private *i915)
 				perf->ctx_flexeu0_offset = 0x78e;
 			}
 			perf->gen8_valid_ctx_bit = BIT(16);
+		} else if (IS_GEN(i915, 12)) {
+			perf->oa_formats = gen12_oa_formats;
+
+			perf->ops.is_valid_b_counter_reg =
+				gen12_is_valid_b_counter_addr;
+			perf->ops.is_valid_mux_reg =
+				gen12_is_valid_mux_addr;
+			perf->ops.is_valid_flex_reg =
+				gen8_is_valid_flex_addr;
+
+			perf->ops.oa_enable = gen12_oa_enable;
+			perf->ops.oa_disable = gen12_oa_disable;
+			perf->ops.enable_metric_set = gen12_enable_metric_set;
+			perf->ops.disable_metric_set = gen12_disable_metric_set;
+			perf->ops.oa_hw_tail_read = gen12_oa_hw_tail_read;
+
+			perf->ctx_flexeu0_offset = 0;
+			perf->ctx_oactxctrl_offset = 0x144;
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_perf_types.h b/drivers/gpu/drm/i915/i915_perf_types.h
index a1f733fc905a..74ddc20a0d37 100644
--- a/drivers/gpu/drm/i915/i915_perf_types.h
+++ b/drivers/gpu/drm/i915/i915_perf_types.h
@@ -199,14 +199,43 @@ struct i915_perf_stream {
 	 * @pinned_ctx: The OA context specific information.
 	 */
 	struct intel_context *pinned_ctx;
+
+	/**
+	 * @specific_ctx_id: The id of the specific context.
+	 */
 	u32 specific_ctx_id;
+
+	/**
+	 * @specific_ctx_id_mask: The mask used to masking specific_ctx_id bits.
+	 */
 	u32 specific_ctx_id_mask;
 
+	/**
+	 * @poll_check_timer: High resolution timer that will periodically
+	 * check for data in the circular OA buffer for notifying userspace
+	 * (e.g. during a read() or poll()).
+	 */
 	struct hrtimer poll_check_timer;
+
+	/**
+	 * @poll_wq: The wait queue that hrtimer callback wakes when it
+	 * sees data ready to read in the circular OA buffer.
+	 */
 	wait_queue_head_t poll_wq;
+
+	/**
+	 * @pollin: Whether there is data available to read.
+	 */
 	bool pollin;
 
+	/**
+	 * @periodic: Whether periodic sampling is currently enabled.
+	 */
 	bool periodic;
+
+	/**
+	 * @period_exponent: The OA unit sampling frequency is derived from this.
+	 */
 	int period_exponent;
 
 	/**
@@ -276,7 +305,7 @@ struct i915_perf_stream {
 	} oa_buffer;
 
 	/**
-	 * A batch buffer doing a wait on the GPU for the NOA logic to be
+	 * @noa_wait: A batch buffer doing a wait on the GPU for the NOA logic to be
 	 * reprogrammed.
 	 */
 	struct i915_vma *noa_wait;
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 85912917c062..2814218c5ba1 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -12,6 +12,7 @@
 #include "gt/intel_engine_user.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_rc6.h"
+#include "gt/intel_rps.h"
 
 #include "i915_drv.h"
 #include "i915_pmu.h"
@@ -189,7 +190,7 @@ static u64 get_rc6(struct intel_gt *gt)
 	val = 0;
 	if (intel_gt_pm_get_if_awake(gt)) {
 		val = __get_rc6(gt);
-		intel_gt_pm_put(gt);
+		intel_gt_pm_put_async(gt);
 	}
 
 	spin_lock_irqsave(&pmu->lock, flags);
@@ -342,7 +343,7 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 
 skip:
 		spin_unlock_irqrestore(&engine->uncore->lock, flags);
-		intel_engine_pm_put(engine);
+		intel_engine_pm_put_async(engine);
 	}
 }
 
@@ -358,25 +359,26 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uncore *uncore = gt->uncore;
 	struct i915_pmu *pmu = &i915->pmu;
+	struct intel_rps *rps = &gt->rps;
 
 	if (pmu->enable & config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) {
 		u32 val;
 
-		val = i915->gt_pm.rps.cur_freq;
+		val = rps->cur_freq;
 		if (intel_gt_pm_get_if_awake(gt)) {
 			val = intel_uncore_read_notrace(uncore, GEN6_RPSTAT1);
-			val = intel_get_cagf(i915, val);
-			intel_gt_pm_put(gt);
+			val = intel_get_cagf(rps, val);
+			intel_gt_pm_put_async(gt);
 		}
 
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
-				intel_gpu_freq(i915, val),
+				intel_gpu_freq(rps, val),
 				period_ns / 1000);
 	}
 
 	if (pmu->enable & config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) {
 		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_REQ],
-				intel_gpu_freq(i915, i915->gt_pm.rps.cur_freq),
+				intel_gpu_freq(rps, rps->cur_freq),
 				period_ns / 1000);
 	}
 }
@@ -876,8 +878,8 @@ create_event_attributes(struct i915_pmu *pmu)
 		const char *name;
 		const char *unit;
 	} events[] = {
-		__event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "MHz"),
-		__event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "MHz"),
+		__event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "M"),
+		__event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"),
 		__event(I915_PMU_INTERRUPTS, "interrupts", NULL),
 		__event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"),
 	};
@@ -1101,20 +1103,6 @@ void i915_pmu_register(struct drm_i915_private *i915)
 		return;
 	}
 
-	i915_pmu_events_attr_group.attrs = create_event_attributes(pmu);
-	if (!i915_pmu_events_attr_group.attrs)
-		goto err;
-
-	pmu->base.attr_groups	= i915_pmu_attr_groups;
-	pmu->base.task_ctx_nr	= perf_invalid_context;
-	pmu->base.event_init	= i915_pmu_event_init;
-	pmu->base.add		= i915_pmu_event_add;
-	pmu->base.del		= i915_pmu_event_del;
-	pmu->base.start		= i915_pmu_event_start;
-	pmu->base.stop		= i915_pmu_event_stop;
-	pmu->base.read		= i915_pmu_event_read;
-	pmu->base.event_idx	= i915_pmu_event_event_idx;
-
 	spin_lock_init(&pmu->lock);
 	hrtimer_init(&pmu->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	pmu->timer.function = i915_sample;
@@ -1128,9 +1116,23 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	if (!pmu->name)
 		goto err;
 
+	i915_pmu_events_attr_group.attrs = create_event_attributes(pmu);
+	if (!i915_pmu_events_attr_group.attrs)
+		goto err_name;
+
+	pmu->base.attr_groups	= i915_pmu_attr_groups;
+	pmu->base.task_ctx_nr	= perf_invalid_context;
+	pmu->base.event_init	= i915_pmu_event_init;
+	pmu->base.add		= i915_pmu_event_add;
+	pmu->base.del		= i915_pmu_event_del;
+	pmu->base.start		= i915_pmu_event_start;
+	pmu->base.stop		= i915_pmu_event_stop;
+	pmu->base.read		= i915_pmu_event_read;
+	pmu->base.event_idx	= i915_pmu_event_event_idx;
+
 	ret = perf_pmu_register(&pmu->base, pmu->name, -1);
 	if (ret)
-		goto err_name;
+		goto err_attr;
 
 	ret = i915_pmu_register_cpuhp_state(pmu);
 	if (ret)
@@ -1140,13 +1142,14 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 err_unreg:
 	perf_pmu_unregister(&pmu->base);
+err_attr:
+	pmu->base.event_init = NULL;
+	free_event_attributes(pmu);
 err_name:
 	if (!is_igp(i915))
 		kfree(pmu->name);
 err:
-	pmu->base.event_init = NULL;
-	free_event_attributes(pmu);
-	DRM_NOTE("Failed to register PMU! (err=%d)\n", ret);
+	dev_notice(i915->drm.dev, "Failed to register PMU!\n");
 }
 
 void i915_pmu_unregister(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/i915_priolist_types.h b/drivers/gpu/drm/i915/i915_priolist_types.h
index 21037a2e2038..732aad148881 100644
--- a/drivers/gpu/drm/i915/i915_priolist_types.h
+++ b/drivers/gpu/drm/i915/i915_priolist_types.h
@@ -16,6 +16,12 @@ enum {
 	I915_PRIORITY_MIN = I915_CONTEXT_MIN_USER_PRIORITY - 1,
 	I915_PRIORITY_NORMAL = I915_CONTEXT_DEFAULT_PRIORITY,
 	I915_PRIORITY_MAX = I915_CONTEXT_MAX_USER_PRIORITY + 1,
+
+	/* A preemptive pulse used to monitor the health of each engine */
+	I915_PRIORITY_HEARTBEAT,
+
+	/* Interactive workload, scheduled for immediate pageflipping */
+	I915_PRIORITY_DISPLAY,
 };
 
 #define I915_USER_PRIORITY_SHIFT 2
@@ -39,6 +45,7 @@ enum {
  * active request.
  */
 #define I915_PRIORITY_UNPREEMPTABLE INT_MAX
+#define I915_PRIORITY_BARRIER INT_MAX
 
 #define __NO_PREEMPTION (I915_PRIORITY_WAIT)
 
diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index c27cfef9281c..ef25ce6e395e 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -103,15 +103,18 @@ query_engine_info(struct drm_i915_private *i915,
 	struct drm_i915_engine_info __user *info_ptr;
 	struct drm_i915_query_engine_info query;
 	struct drm_i915_engine_info info = { };
+	unsigned int num_uabi_engines = 0;
 	struct intel_engine_cs *engine;
 	int len, ret;
 
 	if (query_item->flags)
 		return -EINVAL;
 
+	for_each_uabi_engine(engine, i915)
+		num_uabi_engines++;
+
 	len = sizeof(struct drm_i915_query_engine_info) +
-	      RUNTIME_INFO(i915)->num_engines *
-	      sizeof(struct drm_i915_engine_info);
+	      num_uabi_engines * sizeof(struct drm_i915_engine_info);
 
 	ret = copy_query_item(&query, sizeof(query), len, query_item);
 	if (ret != 0)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 855db888516c..73079b503724 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -413,6 +413,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN11_VECS_SFC_USAGE(engine)		_MMIO((engine)->mmio_base + 0x2014)
 #define   GEN11_VECS_SFC_USAGE_BIT		(1 << 0)
 
+#define GEN12_SFC_DONE(n)		_MMIO(0x1cc00 + (n) * 0x100)
+#define GEN12_SFC_DONE_MAX		4
+
 #define RING_PP_DIR_BASE(base)		_MMIO((base) + 0x228)
 #define RING_PP_DIR_BASE_READ(base)	_MMIO((base) + 0x518)
 #define RING_PP_DIR_DCLV(base)		_MMIO((base) + 0x220)
@@ -471,6 +474,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
 #define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
 
+#define GEN8_RC6_CTX_INFO		_MMIO(0x8504)
+
 #define GAC_ECO_BITS			_MMIO(0x14090)
 #define   ECOBITS_SNB_BIT		(1 << 13)
 #define   ECOBITS_PPGTT_CACHE64B	(3 << 8)
@@ -557,6 +562,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  */
 #define BCS_SWCTRL _MMIO(0x22200)
 
+/* There are 16 GPR registers */
+#define BCS_GPR(n)	_MMIO(0x22600 + (n) * 8)
+#define BCS_GPR_UDW(n)	_MMIO(0x22600 + (n) * 8 + 4)
+
 #define GPGPU_THREADS_DISPATCHED        _MMIO(0x2290)
 #define GPGPU_THREADS_DISPATCHED_UDW	_MMIO(0x2290 + 4)
 #define HS_INVOCATION_COUNT             _MMIO(0x2300)
@@ -684,6 +693,45 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OABUFFER_SIZE_8M    (6 << 3)
 #define OABUFFER_SIZE_16M   (7 << 3)
 
+/* Gen12 OAR unit */
+#define GEN12_OAR_OACONTROL _MMIO(0x2960)
+#define  GEN12_OAR_OACONTROL_COUNTER_FORMAT_SHIFT 1
+#define  GEN12_OAR_OACONTROL_COUNTER_ENABLE       (1 << 0)
+
+#define GEN12_OACTXCONTROL _MMIO(0x2360)
+#define GEN12_OAR_OASTATUS _MMIO(0x2968)
+
+/* Gen12 OAG unit */
+#define GEN12_OAG_OAHEADPTR _MMIO(0xdb00)
+#define  GEN12_OAG_OAHEADPTR_MASK 0xffffffc0
+#define GEN12_OAG_OATAILPTR _MMIO(0xdb04)
+#define  GEN12_OAG_OATAILPTR_MASK 0xffffffc0
+
+#define GEN12_OAG_OABUFFER  _MMIO(0xdb08)
+#define  GEN12_OAG_OABUFFER_BUFFER_SIZE_MASK  (0x7)
+#define  GEN12_OAG_OABUFFER_BUFFER_SIZE_SHIFT (3)
+#define  GEN12_OAG_OABUFFER_MEMORY_SELECT     (1 << 0) /* 0: PPGTT, 1: GGTT */
+
+#define GEN12_OAG_OAGLBCTXCTRL _MMIO(0x2b28)
+#define  GEN12_OAG_OAGLBCTXCTRL_TIMER_PERIOD_SHIFT 2
+#define  GEN12_OAG_OAGLBCTXCTRL_TIMER_ENABLE       (1 << 1)
+#define  GEN12_OAG_OAGLBCTXCTRL_COUNTER_RESUME     (1 << 0)
+
+#define GEN12_OAG_OACONTROL _MMIO(0xdaf4)
+#define  GEN12_OAG_OACONTROL_OA_COUNTER_FORMAT_SHIFT 2
+#define  GEN12_OAG_OACONTROL_OA_COUNTER_ENABLE       (1 << 0)
+
+#define GEN12_OAG_OA_DEBUG _MMIO(0xdaf8)
+#define  GEN12_OAG_OA_DEBUG_INCLUDE_CLK_RATIO          (1 << 6)
+#define  GEN12_OAG_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS  (1 << 5)
+#define  GEN12_OAG_OA_DEBUG_DISABLE_GO_1_0_REPORTS     (1 << 2)
+#define  GEN12_OAG_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS (1 << 1)
+
+#define GEN12_OAG_OASTATUS _MMIO(0xdafc)
+#define  GEN12_OAG_OASTATUS_COUNTER_OVERFLOW (1 << 2)
+#define  GEN12_OAG_OASTATUS_BUFFER_OVERFLOW  (1 << 1)
+#define  GEN12_OAG_OASTATUS_REPORT_LOST      (1 << 0)
+
 /*
  * Flexible, Aggregate EU Counter Registers.
  * Note: these aren't contiguous
@@ -920,6 +968,26 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OAREPORTTRIG8_NOA_SELECT_6_SHIFT    24
 #define OAREPORTTRIG8_NOA_SELECT_7_SHIFT    28
 
+/* Same layout as OASTARTTRIGX */
+#define GEN12_OAG_OASTARTTRIG1 _MMIO(0xd900)
+#define GEN12_OAG_OASTARTTRIG2 _MMIO(0xd904)
+#define GEN12_OAG_OASTARTTRIG3 _MMIO(0xd908)
+#define GEN12_OAG_OASTARTTRIG4 _MMIO(0xd90c)
+#define GEN12_OAG_OASTARTTRIG5 _MMIO(0xd910)
+#define GEN12_OAG_OASTARTTRIG6 _MMIO(0xd914)
+#define GEN12_OAG_OASTARTTRIG7 _MMIO(0xd918)
+#define GEN12_OAG_OASTARTTRIG8 _MMIO(0xd91c)
+
+/* Same layout as OAREPORTTRIGX */
+#define GEN12_OAG_OAREPORTTRIG1 _MMIO(0xd920)
+#define GEN12_OAG_OAREPORTTRIG2 _MMIO(0xd924)
+#define GEN12_OAG_OAREPORTTRIG3 _MMIO(0xd928)
+#define GEN12_OAG_OAREPORTTRIG4 _MMIO(0xd92c)
+#define GEN12_OAG_OAREPORTTRIG5 _MMIO(0xd930)
+#define GEN12_OAG_OAREPORTTRIG6 _MMIO(0xd934)
+#define GEN12_OAG_OAREPORTTRIG7 _MMIO(0xd938)
+#define GEN12_OAG_OAREPORTTRIG8 _MMIO(0xd93c)
+
 /* CECX_0 */
 #define OACEC_COMPARE_LESS_OR_EQUAL	6
 #define OACEC_COMPARE_NOT_EQUAL		5
@@ -936,6 +1004,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OACEC_SELECT_PREV	(1 << 19)
 #define OACEC_SELECT_BOOLEAN	(2 << 19)
 
+/* 11-bit array 0: pass-through, 1: negated */
+#define GEN12_OASCEC_NEGATE_MASK  0x7ff
+#define GEN12_OASCEC_NEGATE_SHIFT 21
+
 /* CECX_1 */
 #define OACEC_MASK_MASK		    0xffff
 #define OACEC_CONSIDERATIONS_MASK   0xffff
@@ -958,6 +1030,42 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OACEC7_0 _MMIO(0x27a8)
 #define OACEC7_1 _MMIO(0x27ac)
 
+/* Same layout as CECX_Y */
+#define GEN12_OAG_CEC0_0 _MMIO(0xd940)
+#define GEN12_OAG_CEC0_1 _MMIO(0xd944)
+#define GEN12_OAG_CEC1_0 _MMIO(0xd948)
+#define GEN12_OAG_CEC1_1 _MMIO(0xd94c)
+#define GEN12_OAG_CEC2_0 _MMIO(0xd950)
+#define GEN12_OAG_CEC2_1 _MMIO(0xd954)
+#define GEN12_OAG_CEC3_0 _MMIO(0xd958)
+#define GEN12_OAG_CEC3_1 _MMIO(0xd95c)
+#define GEN12_OAG_CEC4_0 _MMIO(0xd960)
+#define GEN12_OAG_CEC4_1 _MMIO(0xd964)
+#define GEN12_OAG_CEC5_0 _MMIO(0xd968)
+#define GEN12_OAG_CEC5_1 _MMIO(0xd96c)
+#define GEN12_OAG_CEC6_0 _MMIO(0xd970)
+#define GEN12_OAG_CEC6_1 _MMIO(0xd974)
+#define GEN12_OAG_CEC7_0 _MMIO(0xd978)
+#define GEN12_OAG_CEC7_1 _MMIO(0xd97c)
+
+/* Same layout as CECX_Y + negate 11-bit array */
+#define GEN12_OAG_SCEC0_0 _MMIO(0xdc00)
+#define GEN12_OAG_SCEC0_1 _MMIO(0xdc04)
+#define GEN12_OAG_SCEC1_0 _MMIO(0xdc08)
+#define GEN12_OAG_SCEC1_1 _MMIO(0xdc0c)
+#define GEN12_OAG_SCEC2_0 _MMIO(0xdc10)
+#define GEN12_OAG_SCEC2_1 _MMIO(0xdc14)
+#define GEN12_OAG_SCEC3_0 _MMIO(0xdc18)
+#define GEN12_OAG_SCEC3_1 _MMIO(0xdc1c)
+#define GEN12_OAG_SCEC4_0 _MMIO(0xdc20)
+#define GEN12_OAG_SCEC4_1 _MMIO(0xdc24)
+#define GEN12_OAG_SCEC5_0 _MMIO(0xdc28)
+#define GEN12_OAG_SCEC5_1 _MMIO(0xdc2c)
+#define GEN12_OAG_SCEC6_0 _MMIO(0xdc30)
+#define GEN12_OAG_SCEC6_1 _MMIO(0xdc34)
+#define GEN12_OAG_SCEC7_0 _MMIO(0xdc38)
+#define GEN12_OAG_SCEC7_1 _MMIO(0xdc3c)
+
 /* OA perf counters */
 #define OA_PERFCNT1_LO      _MMIO(0x91B8)
 #define OA_PERFCNT1_HI      _MMIO(0x91BC)
@@ -1038,6 +1146,10 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MICRO_BP3_COUNT_STATUS23	_MMIO(0x9838)
 #define MICRO_BP_FIRED_ARMED		_MMIO(0x983C)
 
+#define GEN12_OAA_DBG_REG _MMIO(0xdc44)
+#define GEN12_OAG_OA_PESS _MMIO(0x2b2c)
+#define GEN12_OAG_SPCTR_CNF _MMIO(0xdc40)
+
 #define GDT_CHICKEN_BITS    _MMIO(0x9840)
 #define   GT_NOA_ENABLE	    0x00000080
 
@@ -2455,6 +2567,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   RING_FAULT_FAULT_TYPE(x) (((x) >> 1) & 0x3)
 #define   RING_FAULT_VALID	(1 << 0)
 #define DONE_REG		_MMIO(0x40b0)
+#define GEN12_GAM_DONE		_MMIO(0xcf68)
 #define GEN8_PRIVATE_PAT_LO	_MMIO(0x40e0)
 #define GEN8_PRIVATE_PAT_HI	_MMIO(0x40e0 + 4)
 #define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index) * 4)
@@ -2490,6 +2603,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN8_RING_CS_GPR_UDW(base, n)	_MMIO((base) + 0x600 + (n) * 8 + 4)
 
 #define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base) + 0x4D0) + (i) * 4)
+#define   RING_FORCE_TO_NONPRIV_ADDRESS_MASK	REG_GENMASK(25, 2)
 #define   RING_FORCE_TO_NONPRIV_ACCESS_RW	(0 << 28)    /* CFL+ & Gen11+ */
 #define   RING_FORCE_TO_NONPRIV_ACCESS_RD	(1 << 28)
 #define   RING_FORCE_TO_NONPRIV_ACCESS_WR	(2 << 28)
@@ -2602,6 +2716,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   FAULT_VA_HIGH_BITS		(0xf << 0)
 #define   FAULT_GTT_SEL			(1 << 4)
 
+#define GEN12_AUX_ERR_DBG		_MMIO(0x43f4)
+
 #define FPGA_DBG		_MMIO(0x42300)
 #define   FPGA_DBG_RM_NOCLAIM	(1 << 31)
 
@@ -5535,45 +5651,9 @@ enum {
  */
 #define _DPA_AUX_CH_CTL		(DISPLAY_MMIO_BASE(dev_priv) + 0x64010)
 #define _DPA_AUX_CH_DATA1	(DISPLAY_MMIO_BASE(dev_priv) + 0x64014)
-#define _DPA_AUX_CH_DATA2	(DISPLAY_MMIO_BASE(dev_priv) + 0x64018)
-#define _DPA_AUX_CH_DATA3	(DISPLAY_MMIO_BASE(dev_priv) + 0x6401c)
-#define _DPA_AUX_CH_DATA4	(DISPLAY_MMIO_BASE(dev_priv) + 0x64020)
-#define _DPA_AUX_CH_DATA5	(DISPLAY_MMIO_BASE(dev_priv) + 0x64024)
 
 #define _DPB_AUX_CH_CTL		(DISPLAY_MMIO_BASE(dev_priv) + 0x64110)
 #define _DPB_AUX_CH_DATA1	(DISPLAY_MMIO_BASE(dev_priv) + 0x64114)
-#define _DPB_AUX_CH_DATA2	(DISPLAY_MMIO_BASE(dev_priv) + 0x64118)
-#define _DPB_AUX_CH_DATA3	(DISPLAY_MMIO_BASE(dev_priv) + 0x6411c)
-#define _DPB_AUX_CH_DATA4	(DISPLAY_MMIO_BASE(dev_priv) + 0x64120)
-#define _DPB_AUX_CH_DATA5	(DISPLAY_MMIO_BASE(dev_priv) + 0x64124)
-
-#define _DPC_AUX_CH_CTL		(DISPLAY_MMIO_BASE(dev_priv) + 0x64210)
-#define _DPC_AUX_CH_DATA1	(DISPLAY_MMIO_BASE(dev_priv) + 0x64214)
-#define _DPC_AUX_CH_DATA2	(DISPLAY_MMIO_BASE(dev_priv) + 0x64218)
-#define _DPC_AUX_CH_DATA3	(DISPLAY_MMIO_BASE(dev_priv) + 0x6421c)
-#define _DPC_AUX_CH_DATA4	(DISPLAY_MMIO_BASE(dev_priv) + 0x64220)
-#define _DPC_AUX_CH_DATA5	(DISPLAY_MMIO_BASE(dev_priv) + 0x64224)
-
-#define _DPD_AUX_CH_CTL		(DISPLAY_MMIO_BASE(dev_priv) + 0x64310)
-#define _DPD_AUX_CH_DATA1	(DISPLAY_MMIO_BASE(dev_priv) + 0x64314)
-#define _DPD_AUX_CH_DATA2	(DISPLAY_MMIO_BASE(dev_priv) + 0x64318)
-#define _DPD_AUX_CH_DATA3	(DISPLAY_MMIO_BASE(dev_priv) + 0x6431c)
-#define _DPD_AUX_CH_DATA4	(DISPLAY_MMIO_BASE(dev_priv) + 0x64320)
-#define _DPD_AUX_CH_DATA5	(DISPLAY_MMIO_BASE(dev_priv) + 0x64324)
-
-#define _DPE_AUX_CH_CTL		(DISPLAY_MMIO_BASE(dev_priv) + 0x64410)
-#define _DPE_AUX_CH_DATA1	(DISPLAY_MMIO_BASE(dev_priv) + 0x64414)
-#define _DPE_AUX_CH_DATA2	(DISPLAY_MMIO_BASE(dev_priv) + 0x64418)
-#define _DPE_AUX_CH_DATA3	(DISPLAY_MMIO_BASE(dev_priv) + 0x6441c)
-#define _DPE_AUX_CH_DATA4	(DISPLAY_MMIO_BASE(dev_priv) + 0x64420)
-#define _DPE_AUX_CH_DATA5	(DISPLAY_MMIO_BASE(dev_priv) + 0x64424)
-
-#define _DPF_AUX_CH_CTL		(DISPLAY_MMIO_BASE(dev_priv) + 0x64510)
-#define _DPF_AUX_CH_DATA1	(DISPLAY_MMIO_BASE(dev_priv) + 0x64514)
-#define _DPF_AUX_CH_DATA2	(DISPLAY_MMIO_BASE(dev_priv) + 0x64518)
-#define _DPF_AUX_CH_DATA3	(DISPLAY_MMIO_BASE(dev_priv) + 0x6451c)
-#define _DPF_AUX_CH_DATA4	(DISPLAY_MMIO_BASE(dev_priv) + 0x64520)
-#define _DPF_AUX_CH_DATA5	(DISPLAY_MMIO_BASE(dev_priv) + 0x64524)
 
 #define DP_AUX_CH_CTL(aux_ch)	_MMIO_PORT(aux_ch, _DPA_AUX_CH_CTL, _DPB_AUX_CH_CTL)
 #define DP_AUX_CH_DATA(aux_ch, i)	_MMIO(_PORT(aux_ch, _DPA_AUX_CH_DATA1, _DPB_AUX_CH_DATA1) + (i) * 4) /* 5 registers */
@@ -7279,6 +7359,10 @@ enum {
 
 #define DMC_DEBUG3		_MMIO(0x101090)
 
+/* Display Internal Timeout Register */
+#define RM_TIMEOUT		_MMIO(0x42060)
+#define  MMIO_TIMEOUT_US(us)	((us) << 0)
+
 /* interrupts */
 #define DE_MASTER_IRQ_CONTROL   (1 << 31)
 #define DE_SPRITEB_FLIP_DONE    (1 << 29)
@@ -7390,6 +7474,9 @@ enum {
 #define  GEN8_PIPE_VSYNC		(1 << 1)
 #define  GEN8_PIPE_VBLANK		(1 << 0)
 #define  GEN9_PIPE_CURSOR_FAULT		(1 << 11)
+#define  GEN11_PIPE_PLANE7_FAULT	(1 << 22)
+#define  GEN11_PIPE_PLANE6_FAULT	(1 << 21)
+#define  GEN11_PIPE_PLANE5_FAULT	(1 << 20)
 #define  GEN9_PIPE_PLANE4_FAULT		(1 << 10)
 #define  GEN9_PIPE_PLANE3_FAULT		(1 << 9)
 #define  GEN9_PIPE_PLANE2_FAULT		(1 << 8)
@@ -7409,6 +7496,11 @@ enum {
 	 GEN9_PIPE_PLANE3_FAULT | \
 	 GEN9_PIPE_PLANE2_FAULT | \
 	 GEN9_PIPE_PLANE1_FAULT)
+#define GEN11_DE_PIPE_IRQ_FAULT_ERRORS \
+	(GEN9_DE_PIPE_IRQ_FAULT_ERRORS | \
+	 GEN11_PIPE_PLANE7_FAULT | \
+	 GEN11_PIPE_PLANE6_FAULT | \
+	 GEN11_PIPE_PLANE5_FAULT)
 
 #define GEN8_DE_PORT_ISR _MMIO(0x44440)
 #define GEN8_DE_PORT_IMR _MMIO(0x44444)
@@ -7428,6 +7520,12 @@ enum {
 #define  GEN8_PORT_DP_A_HOTPLUG		(1 << 3)
 #define  BXT_DE_PORT_GMBUS		(1 << 1)
 #define  GEN8_AUX_CHANNEL_A		(1 << 0)
+#define  TGL_DE_PORT_AUX_USBC6		(1 << 13)
+#define  TGL_DE_PORT_AUX_USBC5		(1 << 12)
+#define  TGL_DE_PORT_AUX_USBC4		(1 << 11)
+#define  TGL_DE_PORT_AUX_USBC3		(1 << 10)
+#define  TGL_DE_PORT_AUX_USBC2		(1 << 9)
+#define  TGL_DE_PORT_AUX_USBC1		(1 << 8)
 #define  TGL_DE_PORT_AUX_DDIC		(1 << 2)
 #define  TGL_DE_PORT_AUX_DDIB		(1 << 1)
 #define  TGL_DE_PORT_AUX_DDIA		(1 << 0)
@@ -7616,10 +7714,17 @@ enum {
 #define  BDW_DPRS_MASK_VBLANK_SRD	(1 << 0)
 #define CHICKEN_PIPESL_1(pipe) _MMIO_PIPE(pipe, _CHICKEN_PIPESL_1_A, _CHICKEN_PIPESL_1_B)
 
-#define CHICKEN_TRANS_A		_MMIO(0x420c0)
-#define CHICKEN_TRANS_B		_MMIO(0x420c4)
-#define CHICKEN_TRANS_C		_MMIO(0x420c8)
-#define CHICKEN_TRANS_EDP	_MMIO(0x420cc)
+#define _CHICKEN_TRANS_A	0x420c0
+#define _CHICKEN_TRANS_B	0x420c4
+#define _CHICKEN_TRANS_C	0x420c8
+#define _CHICKEN_TRANS_EDP	0x420cc
+#define _CHICKEN_TRANS_D	0x420d8
+#define CHICKEN_TRANS(trans)	_MMIO(_PICK((trans), \
+					    [TRANSCODER_EDP] = _CHICKEN_TRANS_EDP, \
+					    [TRANSCODER_A] = _CHICKEN_TRANS_A, \
+					    [TRANSCODER_B] = _CHICKEN_TRANS_B, \
+					    [TRANSCODER_C] = _CHICKEN_TRANS_C, \
+					    [TRANSCODER_D] = _CHICKEN_TRANS_D))
 #define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1 << 25) /* GLK and CNL+ */
 #define  DDI_TRAINING_OVERRIDE_ENABLE	(1 << 19)
 #define  DDI_TRAINING_OVERRIDE_VALUE	(1 << 18)
@@ -7652,15 +7757,19 @@ enum {
 #define   CNL_DDI_CLOCK_REG_ACCESS_ON	(1 << 7)
 
 #define SKL_DFSM			_MMIO(0x51000)
-#define SKL_DFSM_CDCLK_LIMIT_MASK	(3 << 23)
-#define SKL_DFSM_CDCLK_LIMIT_675	(0 << 23)
-#define SKL_DFSM_CDCLK_LIMIT_540	(1 << 23)
-#define SKL_DFSM_CDCLK_LIMIT_450	(2 << 23)
-#define SKL_DFSM_CDCLK_LIMIT_337_5	(3 << 23)
-#define SKL_DFSM_PIPE_A_DISABLE		(1 << 30)
-#define SKL_DFSM_PIPE_B_DISABLE		(1 << 21)
-#define SKL_DFSM_PIPE_C_DISABLE		(1 << 28)
-#define TGL_DFSM_PIPE_D_DISABLE		(1 << 22)
+#define   SKL_DFSM_DISPLAY_PM_DISABLE	(1 << 27)
+#define   SKL_DFSM_DISPLAY_HDCP_DISABLE	(1 << 25)
+#define   SKL_DFSM_CDCLK_LIMIT_MASK	(3 << 23)
+#define   SKL_DFSM_CDCLK_LIMIT_675	(0 << 23)
+#define   SKL_DFSM_CDCLK_LIMIT_540	(1 << 23)
+#define   SKL_DFSM_CDCLK_LIMIT_450	(2 << 23)
+#define   SKL_DFSM_CDCLK_LIMIT_337_5	(3 << 23)
+#define   ICL_DFSM_DMC_DISABLE		(1 << 23)
+#define   SKL_DFSM_PIPE_A_DISABLE	(1 << 30)
+#define   SKL_DFSM_PIPE_B_DISABLE	(1 << 21)
+#define   SKL_DFSM_PIPE_C_DISABLE	(1 << 28)
+#define   TGL_DFSM_PIPE_D_DISABLE	(1 << 22)
+#define   CNL_DFSM_DISPLAY_DSC_DISABLE	(1 << 7)
 
 #define SKL_DSSM				_MMIO(0x51004)
 #define CNL_DSSM_CDCLK_PLL_REFCLK_24MHz		(1 << 31)
@@ -9562,6 +9671,9 @@ enum skl_power_gate {
 #define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
 #define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5 << 12)
 #define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6 << 12)
+#define  TRANS_DDI_MST_TRANSPORT_SELECT_MASK	REG_GENMASK(11, 10)
+#define  TRANS_DDI_MST_TRANSPORT_SELECT(trans)	\
+	REG_FIELD_PREP(TRANS_DDI_MST_TRANSPORT_SELECT_MASK, trans)
 #define  TRANS_DDI_HDCP_SIGNALLING	(1 << 9)
 #define  TRANS_DDI_DP_VC_PAYLOAD_ALLOC	(1 << 8)
 #define  TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE (1 << 7)
@@ -10249,6 +10361,12 @@ enum skl_power_gate {
 						     _DKL_PHY2_BASE) + \
 						     _DKL_TX_FW_CALIB)
 
+#define _DKL_TX_PMD_LANE_SUS				0xD00
+#define DKL_TX_PMD_LANE_SUS(tc_port) _MMIO(_PORT(tc_port, \
+							  _DKL_PHY1_BASE, \
+							  _DKL_PHY2_BASE) + \
+							  _DKL_TX_PMD_LANE_SUS)
+
 #define _DKL_TX_DW17					0xDC4
 #define DKL_TX_DW17(tc_port) _MMIO(_PORT(tc_port, \
 						     _DKL_PHY1_BASE, \
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 4575f368455d..00011f9533b6 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -31,6 +31,8 @@
 
 #include "gem/i915_gem_context.h"
 #include "gt/intel_context.h"
+#include "gt/intel_ring.h"
+#include "gt/intel_rps.h"
 
 #include "i915_active.h"
 #include "i915_drv.h"
@@ -257,8 +259,8 @@ bool i915_request_retire(struct i915_request *rq)
 	if (test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &rq->fence.flags))
 		i915_request_cancel_breadcrumb(rq);
 	if (i915_request_has_waitboost(rq)) {
-		GEM_BUG_ON(!atomic_read(&rq->i915->gt_pm.rps.num_waiters));
-		atomic_dec(&rq->i915->gt_pm.rps.num_waiters);
+		GEM_BUG_ON(!atomic_read(&rq->engine->gt->rps.num_waiters));
+		atomic_dec(&rq->engine->gt->rps.num_waiters);
 	}
 	if (!test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
 		set_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags);
@@ -1446,7 +1448,7 @@ long i915_request_wait(struct i915_request *rq,
 	 * completion. That requires having a good predictor for the request
 	 * duration, which we currently lack.
 	 */
-	if (CONFIG_DRM_I915_SPIN_REQUEST &&
+	if (IS_ACTIVE(CONFIG_DRM_I915_SPIN_REQUEST) &&
 	    __i915_spin_request(rq, state, CONFIG_DRM_I915_SPIN_REQUEST)) {
 		dma_fence_signal(&rq->fence);
 		goto out;
@@ -1466,7 +1468,7 @@ long i915_request_wait(struct i915_request *rq,
 	 */
 	if (flags & I915_WAIT_PRIORITY) {
 		if (!i915_request_started(rq) && INTEL_GEN(rq->i915) >= 6)
-			gen6_rps_boost(rq);
+			intel_rps_boost(rq);
 		i915_schedule_bump_priority(rq, I915_PRIORITY_WAIT);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_scheduler.c b/drivers/gpu/drm/i915/i915_scheduler.c
index 0ca40f6bf08c..010d67f48ad9 100644
--- a/drivers/gpu/drm/i915/i915_scheduler.c
+++ b/drivers/gpu/drm/i915/i915_scheduler.c
@@ -189,22 +189,39 @@ static inline bool need_preempt(int prio, int active)
 	return prio >= max(I915_PRIORITY_NORMAL, active);
 }
 
-static void kick_submission(struct intel_engine_cs *engine, int prio)
+static void kick_submission(struct intel_engine_cs *engine,
+			    const struct i915_request *rq,
+			    int prio)
 {
-	const struct i915_request *inflight =
-		execlists_active(&engine->execlists);
+	const struct i915_request *inflight;
 
 	/*
-	 * If we are already the currently executing context, don't
-	 * bother evaluating if we should preempt ourselves, or if
-	 * we expect nothing to change as a result of running the
-	 * tasklet, i.e. we have not change the priority queue
-	 * sufficiently to oust the running context.
+	 * We only need to kick the tasklet once for the high priority
+	 * new context we add into the queue.
 	 */
-	if (!inflight || !need_preempt(prio, rq_prio(inflight)))
+	if (prio <= engine->execlists.queue_priority_hint)
 		return;
 
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+	rcu_read_lock();
+
+	/* Nothing currently active? We're overdue for a submission! */
+	inflight = execlists_active(&engine->execlists);
+	if (!inflight)
+		goto unlock;
+
+	/*
+	 * If we are already the currently executing context, don't
+	 * bother evaluating if we should preempt ourselves.
+	 */
+	if (inflight->hw_context == rq->hw_context)
+		goto unlock;
+
+	engine->execlists.queue_priority_hint = prio;
+	if (need_preempt(prio, rq_prio(inflight)))
+		tasklet_hi_schedule(&engine->execlists.tasklet);
+
+unlock:
+	rcu_read_unlock();
 }
 
 static void __i915_schedule(struct i915_sched_node *node,
@@ -330,13 +347,8 @@ static void __i915_schedule(struct i915_sched_node *node,
 			list_move_tail(&node->link, cache.priolist);
 		}
 
-		if (prio <= engine->execlists.queue_priority_hint)
-			continue;
-
-		engine->execlists.queue_priority_hint = prio;
-
 		/* Defer (tasklet) submission until after all of our updates. */
-		kick_submission(engine, prio);
+		kick_submission(engine, node_to_request(node), prio);
 	}
 
 	spin_unlock(&engine->active.lock);
diff --git a/drivers/gpu/drm/i915/i915_sysfs.c b/drivers/gpu/drm/i915/i915_sysfs.c
index bf039b8ba593..65476909d1bf 100644
--- a/drivers/gpu/drm/i915/i915_sysfs.c
+++ b/drivers/gpu/drm/i915/i915_sysfs.c
@@ -31,6 +31,7 @@
 #include <linux/sysfs.h>
 
 #include "gt/intel_rc6.h"
+#include "gt/intel_rps.h"
 
 #include "i915_drv.h"
 #include "i915_sysfs.h"
@@ -259,6 +260,7 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	intel_wakeref_t wakeref;
 	u32 freq;
 
@@ -271,31 +273,31 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 
 		freq = (freq >> 8) & 0xff;
 	} else {
-		freq = intel_get_cagf(dev_priv, I915_READ(GEN6_RPSTAT1));
+		freq = intel_get_cagf(rps, I915_READ(GEN6_RPSTAT1));
 	}
 
 	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 
-	return snprintf(buf, PAGE_SIZE, "%d\n", intel_gpu_freq(dev_priv, freq));
+	return snprintf(buf, PAGE_SIZE, "%d\n", intel_gpu_freq(rps, freq));
 }
 
 static ssize_t gt_cur_freq_mhz_show(struct device *kdev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &dev_priv->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			intel_gpu_freq(dev_priv,
-				       dev_priv->gt_pm.rps.cur_freq));
+			intel_gpu_freq(rps, rps->cur_freq));
 }
 
 static ssize_t gt_boost_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &dev_priv->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			intel_gpu_freq(dev_priv,
-				       dev_priv->gt_pm.rps.boost_freq));
+			intel_gpu_freq(rps, rps->boost_freq));
 }
 
 static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
@@ -303,7 +305,7 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
 				       const char *buf, size_t count)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	bool boost = false;
 	ssize_t ret;
 	u32 val;
@@ -313,7 +315,7 @@ static ssize_t gt_boost_freq_mhz_store(struct device *kdev,
 		return ret;
 
 	/* Validate against (static) hardware limits */
-	val = intel_freq_opcode(dev_priv, val);
+	val = intel_freq_opcode(rps, val);
 	if (val < rps->min_freq || val > rps->max_freq)
 		return -EINVAL;
 
@@ -333,19 +335,19 @@ static ssize_t vlv_rpe_freq_mhz_show(struct device *kdev,
 				     struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &dev_priv->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			intel_gpu_freq(dev_priv,
-				       dev_priv->gt_pm.rps.efficient_freq));
+			intel_gpu_freq(rps, rps->efficient_freq));
 }
 
 static ssize_t gt_max_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &dev_priv->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			intel_gpu_freq(dev_priv,
-				       dev_priv->gt_pm.rps.max_freq_softlimit));
+			intel_gpu_freq(rps, rps->max_freq_softlimit));
 }
 
 static ssize_t gt_max_freq_mhz_store(struct device *kdev,
@@ -353,19 +355,17 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 				     const char *buf, size_t count)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	intel_wakeref_t wakeref;
-	u32 val;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	ssize_t ret;
+	u32 val;
 
 	ret = kstrtou32(buf, 0, &val);
 	if (ret)
 		return ret;
 
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 	mutex_lock(&rps->lock);
 
-	val = intel_freq_opcode(dev_priv, val);
+	val = intel_freq_opcode(rps, val);
 	if (val < rps->min_freq ||
 	    val > rps->max_freq ||
 	    val < rps->min_freq_softlimit) {
@@ -375,7 +375,7 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 
 	if (val > rps->rp0_freq)
 		DRM_DEBUG("User requested overclocking to %d\n",
-			  intel_gpu_freq(dev_priv, val));
+			  intel_gpu_freq(rps, val));
 
 	rps->max_freq_softlimit = val;
 
@@ -383,14 +383,15 @@ static ssize_t gt_max_freq_mhz_store(struct device *kdev,
 		      rps->min_freq_softlimit,
 		      rps->max_freq_softlimit);
 
-	/* We still need *_set_rps to process the new max_delay and
+	/*
+	 * We still need *_set_rps to process the new max_delay and
 	 * update the interrupt limits and PMINTRMSK even though
-	 * frequency request may be unchanged. */
-	ret = intel_set_rps(dev_priv, val);
+	 * frequency request may be unchanged.
+	 */
+	intel_rps_set(rps, val);
 
 unlock:
 	mutex_unlock(&rps->lock);
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 
 	return ret ?: count;
 }
@@ -398,10 +399,10 @@ unlock:
 static ssize_t gt_min_freq_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
+	struct intel_rps *rps = &dev_priv->gt.rps;
 
 	return snprintf(buf, PAGE_SIZE, "%d\n",
-			intel_gpu_freq(dev_priv,
-				       dev_priv->gt_pm.rps.min_freq_softlimit));
+			intel_gpu_freq(rps, rps->min_freq_softlimit));
 }
 
 static ssize_t gt_min_freq_mhz_store(struct device *kdev,
@@ -409,19 +410,17 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 				     const char *buf, size_t count)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	intel_wakeref_t wakeref;
-	u32 val;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	ssize_t ret;
+	u32 val;
 
 	ret = kstrtou32(buf, 0, &val);
 	if (ret)
 		return ret;
 
-	wakeref = intel_runtime_pm_get(&dev_priv->runtime_pm);
 	mutex_lock(&rps->lock);
 
-	val = intel_freq_opcode(dev_priv, val);
+	val = intel_freq_opcode(rps, val);
 	if (val < rps->min_freq ||
 	    val > rps->max_freq ||
 	    val > rps->max_freq_softlimit) {
@@ -435,14 +434,15 @@ static ssize_t gt_min_freq_mhz_store(struct device *kdev,
 		      rps->min_freq_softlimit,
 		      rps->max_freq_softlimit);
 
-	/* We still need *_set_rps to process the new min_delay and
+	/*
+	 * We still need *_set_rps to process the new min_delay and
 	 * update the interrupt limits and PMINTRMSK even though
-	 * frequency request may be unchanged. */
-	ret = intel_set_rps(dev_priv, val);
+	 * frequency request may be unchanged.
+	 */
+	intel_rps_set(rps, val);
 
 unlock:
 	mutex_unlock(&rps->lock);
-	intel_runtime_pm_put(&dev_priv->runtime_pm, wakeref);
 
 	return ret ?: count;
 }
@@ -464,15 +464,15 @@ static DEVICE_ATTR(gt_RPn_freq_mhz, S_IRUGO, gt_rp_mhz_show, NULL);
 static ssize_t gt_rp_mhz_show(struct device *kdev, struct device_attribute *attr, char *buf)
 {
 	struct drm_i915_private *dev_priv = kdev_minor_to_i915(kdev);
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	struct intel_rps *rps = &dev_priv->gt.rps;
 	u32 val;
 
 	if (attr == &dev_attr_gt_RP0_freq_mhz)
-		val = intel_gpu_freq(dev_priv, rps->rp0_freq);
+		val = intel_gpu_freq(rps, rps->rp0_freq);
 	else if (attr == &dev_attr_gt_RP1_freq_mhz)
-		val = intel_gpu_freq(dev_priv, rps->rp1_freq);
+		val = intel_gpu_freq(rps, rps->rp1_freq);
 	else if (attr == &dev_attr_gt_RPn_freq_mhz)
-		val = intel_gpu_freq(dev_priv, rps->min_freq);
+		val = intel_gpu_freq(rps, rps->min_freq);
 	else
 		BUG();
 
diff --git a/drivers/gpu/drm/i915/i915_utils.c b/drivers/gpu/drm/i915/i915_utils.c
index 16acdf7bdbe6..0348c6d0ef5f 100644
--- a/drivers/gpu/drm/i915/i915_utils.c
+++ b/drivers/gpu/drm/i915/i915_utils.c
@@ -54,25 +54,54 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 static unsigned int i915_probe_fail_count;
 
-int __i915_inject_load_error(struct drm_i915_private *i915, int err,
-			     const char *func, int line)
+int __i915_inject_probe_error(struct drm_i915_private *i915, int err,
+			      const char *func, int line)
 {
-	if (i915_probe_fail_count >= i915_modparams.inject_load_failure)
+	if (i915_probe_fail_count >= i915_modparams.inject_probe_failure)
 		return 0;
 
-	if (++i915_probe_fail_count < i915_modparams.inject_load_failure)
+	if (++i915_probe_fail_count < i915_modparams.inject_probe_failure)
 		return 0;
 
 	__i915_printk(i915, KERN_INFO,
 		      "Injecting failure %d at checkpoint %u [%s:%d]\n",
-		      err, i915_modparams.inject_load_failure, func, line);
-	i915_modparams.inject_load_failure = 0;
+		      err, i915_modparams.inject_probe_failure, func, line);
+	i915_modparams.inject_probe_failure = 0;
 	return err;
 }
 
 bool i915_error_injected(void)
 {
-	return i915_probe_fail_count && !i915_modparams.inject_load_failure;
+	return i915_probe_fail_count && !i915_modparams.inject_probe_failure;
 }
 
 #endif
+
+void cancel_timer(struct timer_list *t)
+{
+	if (!READ_ONCE(t->expires))
+		return;
+
+	del_timer(t);
+	WRITE_ONCE(t->expires, 0);
+}
+
+void set_timer_ms(struct timer_list *t, unsigned long timeout)
+{
+	if (!timeout) {
+		cancel_timer(t);
+		return;
+	}
+
+	timeout = msecs_to_jiffies_timeout(timeout);
+
+	/*
+	 * Paranoia to make sure the compiler computes the timeout before
+	 * loading 'jiffies' as jiffies is volatile and may be updated in
+	 * the background by a timer tick. All to reduce the complexity
+	 * of the addition and reduce the risk of losing a jiffie.
+	 */
+	barrier();
+
+	mod_timer(t, jiffies + timeout);
+}
diff --git a/drivers/gpu/drm/i915/i915_utils.h b/drivers/gpu/drm/i915/i915_utils.h
index 562f756da421..04139ba1191e 100644
--- a/drivers/gpu/drm/i915/i915_utils.h
+++ b/drivers/gpu/drm/i915/i915_utils.h
@@ -32,6 +32,7 @@
 #include <linux/workqueue.h>
 
 struct drm_i915_private;
+struct timer_list;
 
 #undef WARN_ON
 /* Many gcc seem to no see through this and fall over :( */
@@ -60,20 +61,20 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
 
-int __i915_inject_load_error(struct drm_i915_private *i915, int err,
-			     const char *func, int line);
-#define i915_inject_load_error(_i915, _err) \
-	__i915_inject_load_error((_i915), (_err), __func__, __LINE__)
+int __i915_inject_probe_error(struct drm_i915_private *i915, int err,
+			      const char *func, int line);
+#define i915_inject_probe_error(_i915, _err) \
+	__i915_inject_probe_error((_i915), (_err), __func__, __LINE__)
 bool i915_error_injected(void);
 
 #else
 
-#define i915_inject_load_error(_i915, _err) 0
+#define i915_inject_probe_error(_i915, _err) 0
 #define i915_error_injected() false
 
 #endif
 
-#define i915_inject_probe_failure(i915) i915_inject_load_error((i915), -ENODEV)
+#define i915_inject_probe_failure(i915) i915_inject_probe_error((i915), -ENODEV)
 
 #define i915_probe_error(i915, fmt, ...)				   \
 	__i915_printk(i915, i915_error_injected() ? KERN_DEBUG : KERN_ERR, \
@@ -421,4 +422,25 @@ static inline void add_taint_for_CI(unsigned int taint)
 	add_taint(taint, LOCKDEP_STILL_OK);
 }
 
+void cancel_timer(struct timer_list *t);
+void set_timer_ms(struct timer_list *t, unsigned long timeout);
+
+static inline bool timer_expired(const struct timer_list *t)
+{
+	return READ_ONCE(t->expires) && !timer_pending(t);
+}
+
+/*
+ * This is a lookalike for IS_ENABLED() that takes a kconfig value,
+ * e.g. CONFIG_DRM_I915_SPIN_REQUEST, and evaluates whether it is non-zero
+ * i.e. whether the configuration is active. Wrapping up the config inside
+ * a boolean context prevents clang and smatch from complaining about potential
+ * issues in confusing logical-&& with bitwise-& for constants.
+ *
+ * Sadly IS_ENABLED() itself does not work with kconfig values.
+ *
+ * Returns 0 if @config is 0, 1 if set to any value.
+ */
+#define IS_ACTIVE(config) ((config) != 0)
+
 #endif /* !__I915_UTILS_H */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index e90c4d0af8fd..e5512f26e20a 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -106,7 +106,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	struct rb_node *rb, **p;
 
 	/* The aliasing_ppgtt should never be used directly! */
-	GEM_BUG_ON(vm == &vm->i915->ggtt.alias->vm);
+	GEM_BUG_ON(vm == &vm->gt->ggtt->alias->vm);
 
 	vma = i915_vma_alloc();
 	if (vma == NULL)
@@ -412,7 +412,7 @@ void __iomem *i915_vma_pin_iomap(struct i915_vma *vma)
 	int err;
 
 	/* Access through the GTT requires the device to be awake. */
-	assert_rpm_wakelock_held(&vma->vm->i915->runtime_pm);
+	assert_rpm_wakelock_held(vma->vm->gt->uncore->rpm);
 	if (GEM_WARN_ON(!i915_vma_is_map_and_fenceable(vma))) {
 		err = -ENODEV;
 		goto err;
@@ -700,41 +700,35 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, color));
 
-	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
-
 	if (vma->obj) {
-		atomic_inc(&vma->obj->bind_count);
-		assert_bind_count(vma->obj);
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		atomic_inc(&obj->bind_count);
+		assert_bind_count(obj);
 	}
+	list_add_tail(&vma->vm_link, &vma->vm->bound_list);
 
 	return 0;
 }
 
 static void
-i915_vma_remove(struct i915_vma *vma)
+i915_vma_detach(struct i915_vma *vma)
 {
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(i915_vma_is_bound(vma, I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 
-	list_del(&vma->vm_link);
-
 	/*
-	 * Since the unbound list is global, only move to that list if
-	 * no more VMAs exist.
+	 * And finally now the object is completely decoupled from this
+	 * vma, we can drop its hold on the backing storage and allow
+	 * it to be reaped by the shrinker.
 	 */
+	list_del(&vma->vm_link);
 	if (vma->obj) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
-		/*
-		 * And finally now the object is completely decoupled from this
-		 * vma, we can drop its hold on the backing storage and allow
-		 * it to be reaped by the shrinker.
-		 */
-		atomic_dec(&obj->bind_count);
 		assert_bind_count(obj);
+		atomic_dec(&obj->bind_count);
 	}
-
-	drm_mm_remove_node(&vma->node);
 }
 
 static bool try_qad_pin(struct i915_vma *vma, unsigned int flags)
@@ -929,8 +923,10 @@ int i915_vma_pin(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	GEM_BUG_ON(i915_vma_misplaced(vma, size, alignment, flags));
 
 err_remove:
-	if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK))
-		i915_vma_remove(vma);
+	if (!i915_vma_is_bound(vma, I915_VMA_BIND_MASK)) {
+		i915_vma_detach(vma);
+		drm_mm_remove_node(&vma->node);
+	}
 err_active:
 	i915_active_release(&vma->active);
 err_unlock:
@@ -945,7 +941,7 @@ err_pages:
 
 void i915_vma_close(struct i915_vma *vma)
 {
-	struct drm_i915_private *i915 = vma->vm->i915;
+	struct intel_gt *gt = vma->vm->gt;
 	unsigned long flags;
 
 	GEM_BUG_ON(i915_vma_is_closed(vma));
@@ -962,18 +958,18 @@ void i915_vma_close(struct i915_vma *vma)
 	 * causing us to rebind the VMA once more. This ends up being a lot
 	 * of wasted work for the steady state.
 	 */
-	spin_lock_irqsave(&i915->gt.closed_lock, flags);
-	list_add(&vma->closed_link, &i915->gt.closed_vma);
-	spin_unlock_irqrestore(&i915->gt.closed_lock, flags);
+	spin_lock_irqsave(&gt->closed_lock, flags);
+	list_add(&vma->closed_link, &gt->closed_vma);
+	spin_unlock_irqrestore(&gt->closed_lock, flags);
 }
 
 static void __i915_vma_remove_closed(struct i915_vma *vma)
 {
-	struct drm_i915_private *i915 = vma->vm->i915;
+	struct intel_gt *gt = vma->vm->gt;
 
-	spin_lock_irq(&i915->gt.closed_lock);
+	spin_lock_irq(&gt->closed_lock);
 	list_del_init(&vma->closed_link);
-	spin_unlock_irq(&i915->gt.closed_lock);
+	spin_unlock_irq(&gt->closed_lock);
 }
 
 void i915_vma_reopen(struct i915_vma *vma)
@@ -1009,12 +1005,12 @@ void i915_vma_destroy(struct i915_vma *vma)
 	i915_vma_free(vma);
 }
 
-void i915_vma_parked(struct drm_i915_private *i915)
+void i915_vma_parked(struct intel_gt *gt)
 {
 	struct i915_vma *vma, *next;
 
-	spin_lock_irq(&i915->gt.closed_lock);
-	list_for_each_entry_safe(vma, next, &i915->gt.closed_vma, closed_link) {
+	spin_lock_irq(&gt->closed_lock);
+	list_for_each_entry_safe(vma, next, &gt->closed_vma, closed_link) {
 		struct drm_i915_gem_object *obj = vma->obj;
 		struct i915_address_space *vm = vma->vm;
 
@@ -1028,7 +1024,7 @@ void i915_vma_parked(struct drm_i915_private *i915)
 			obj = NULL;
 		}
 
-		spin_unlock_irq(&i915->gt.closed_lock);
+		spin_unlock_irq(&gt->closed_lock);
 
 		if (obj) {
 			i915_vma_destroy(vma);
@@ -1038,11 +1034,11 @@ void i915_vma_parked(struct drm_i915_private *i915)
 		i915_vm_close(vm);
 
 		/* Restart after dropping lock */
-		spin_lock_irq(&i915->gt.closed_lock);
-		next = list_first_entry(&i915->gt.closed_vma,
+		spin_lock_irq(&gt->closed_lock);
+		next = list_first_entry(&gt->closed_vma,
 					typeof(*next), closed_link);
 	}
-	spin_unlock_irq(&i915->gt.closed_lock);
+	spin_unlock_irq(&gt->closed_lock);
 }
 
 static void __i915_vma_iounmap(struct i915_vma *vma)
@@ -1187,9 +1183,10 @@ int __i915_vma_unbind(struct i915_vma *vma)
 	}
 	atomic_and(~(I915_VMA_BIND_MASK | I915_VMA_ERROR), &vma->flags);
 
+	i915_vma_detach(vma);
 	vma_unbind_pages(vma);
-	i915_vma_remove(vma);
 
+	drm_mm_remove_node(&vma->node); /* pairs with i915_vma_destroy() */
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 858908e3d1cc..465932813bc5 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -462,7 +462,7 @@ i915_vma_unpin_fence(struct i915_vma *vma)
 		__i915_vma_unpin_fence(vma);
 }
 
-void i915_vma_parked(struct drm_i915_private *i915);
+void i915_vma_parked(struct intel_gt *gt);
 
 #define for_each_until(cond) if (cond) break; else
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 85e480bdc673..a5b571364cf6 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -981,6 +981,19 @@ void intel_device_info_runtime_init(struct drm_i915_private *dev_priv)
 				  enabled_mask);
 		else
 			info->pipe_mask = enabled_mask;
+
+		if (dfsm & SKL_DFSM_DISPLAY_HDCP_DISABLE)
+			info->display.has_hdcp = 0;
+
+		if (dfsm & SKL_DFSM_DISPLAY_PM_DISABLE)
+			info->display.has_fbc = 0;
+
+		if (INTEL_GEN(dev_priv) >= 11 && (dfsm & ICL_DFSM_DMC_DISABLE))
+			info->display.has_csr = 0;
+
+		if (INTEL_GEN(dev_priv) >= 10 &&
+		    (dfsm & CNL_DFSM_DISPLAY_DSC_DISABLE))
+			info->display.has_dsc = 0;
 	}
 
 	/* Initialize slice/subslice/EU info */
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index e9940f932d26..4bdf8a6cfb47 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -107,6 +107,7 @@ enum intel_ppgtt_type {
 	func(is_mobile); \
 	func(is_lp); \
 	func(require_force_probe); \
+	func(is_dgfx); \
 	/* Keep has_* in alphabetical order */ \
 	func(has_64bit_reloc); \
 	func(gpu_reset_clobbers_display); \
@@ -136,8 +137,10 @@ enum intel_ppgtt_type {
 	func(has_ddi); \
 	func(has_dp_mst); \
 	func(has_dsb); \
+	func(has_dsc); \
 	func(has_fbc); \
 	func(has_gmch); \
+	func(has_hdcp); \
 	func(has_hotplug); \
 	func(has_ipc); \
 	func(has_modular_fia); \
diff --git a/drivers/gpu/drm/i915/intel_memory_region.c b/drivers/gpu/drm/i915/intel_memory_region.c
index 72f98a111de1..baaeaecc64af 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/intel_memory_region.c
@@ -207,6 +207,65 @@ void intel_memory_region_put(struct intel_memory_region *mem)
 	kref_put(&mem->kref, __intel_memory_region_destroy);
 }
 
+/* Global memory region registration -- only slight layer inversions! */
+
+int intel_memory_regions_hw_probe(struct drm_i915_private *i915)
+{
+	int err, i;
+
+	for (i = 0; i < ARRAY_SIZE(i915->mm.regions); i++) {
+		struct intel_memory_region *mem = ERR_PTR(-ENODEV);
+		u32 type;
+
+		if (!HAS_REGION(i915, BIT(i)))
+			continue;
+
+		type = MEMORY_TYPE_FROM_REGION(intel_region_map[i]);
+		switch (type) {
+		case INTEL_MEMORY_SYSTEM:
+			mem = i915_gem_shmem_setup(i915);
+			break;
+		case INTEL_MEMORY_STOLEN:
+			mem = i915_gem_stolen_setup(i915);
+			break;
+		case INTEL_MEMORY_LOCAL:
+			mem = intel_setup_fake_lmem(i915);
+			break;
+		}
+
+		if (IS_ERR(mem)) {
+			err = PTR_ERR(mem);
+			DRM_ERROR("Failed to setup region(%d) type=%d\n", err, type);
+			goto out_cleanup;
+		}
+
+		mem->id = intel_region_map[i];
+		mem->type = type;
+		mem->instance = MEMORY_INSTANCE_FROM_REGION(intel_region_map[i]);
+
+		i915->mm.regions[i] = mem;
+	}
+
+	return 0;
+
+out_cleanup:
+	intel_memory_regions_driver_release(i915);
+	return err;
+}
+
+void intel_memory_regions_driver_release(struct drm_i915_private *i915)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(i915->mm.regions); i++) {
+		struct intel_memory_region *region =
+			fetch_and_zero(&i915->mm.regions[i]);
+
+		if (region)
+			intel_memory_region_put(region);
+	}
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/intel_memory_region.c"
 #include "selftests/mock_region.c"
diff --git a/drivers/gpu/drm/i915/intel_memory_region.h b/drivers/gpu/drm/i915/intel_memory_region.h
index 49b059a2be70..238722009677 100644
--- a/drivers/gpu/drm/i915/intel_memory_region.h
+++ b/drivers/gpu/drm/i915/intel_memory_region.h
@@ -10,6 +10,7 @@
 #include <linux/ioport.h>
 #include <linux/mutex.h>
 #include <linux/io-mapping.h>
+#include <drm/drm_mm.h>
 
 #include "i915_buddy.h"
 
@@ -71,6 +72,9 @@ struct intel_memory_region {
 	struct io_mapping iomap;
 	struct resource region;
 
+	/* For fake LMEM */
+	struct drm_mm_node fake_mappable;
+
 	struct i915_buddy_mm mm;
 	struct mutex mm_lock;
 
@@ -83,6 +87,8 @@ struct intel_memory_region {
 	unsigned int instance;
 	unsigned int id;
 
+	dma_addr_t remap_addr;
+
 	struct {
 		struct mutex lock; /* Protects access to objects */
 		struct list_head list;
@@ -117,4 +123,7 @@ struct intel_memory_region *
 intel_memory_region_get(struct intel_memory_region *mem);
 void intel_memory_region_put(struct intel_memory_region *mem);
 
+int intel_memory_regions_hw_probe(struct drm_i915_private *i915);
+void intel_memory_regions_driver_release(struct drm_i915_private *i915);
+
 #endif
diff --git a/drivers/gpu/drm/i915/intel_pch.c b/drivers/gpu/drm/i915/intel_pch.c
index 1035d3d46fd8..8fd92b9130a7 100644
--- a/drivers/gpu/drm/i915/intel_pch.c
+++ b/drivers/gpu/drm/i915/intel_pch.c
@@ -52,7 +52,8 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		return PCH_SPT;
 	case INTEL_PCH_SPT_LP_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found SunrisePoint LP PCH\n");
-		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv));
+		WARN_ON(!IS_SKYLAKE(dev_priv) && !IS_KABYLAKE(dev_priv) &&
+			!IS_COFFEELAKE(dev_priv));
 		return PCH_SPT;
 	case INTEL_PCH_KBP_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Kaby Lake PCH (KBP)\n");
@@ -74,6 +75,11 @@ intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
 		WARN_ON(!IS_COFFEELAKE(dev_priv));
 		/* CometPoint is CNP Compatible */
 		return PCH_CNP;
+	case INTEL_PCH_CMP_V_DEVICE_ID_TYPE:
+		DRM_DEBUG_KMS("Found Comet Lake V PCH (CMP-V)\n");
+		WARN_ON(!IS_COFFEELAKE(dev_priv));
+		/* Comet Lake V PCH is based on KBP, which is SPT compatible */
+		return PCH_SPT;
 	case INTEL_PCH_ICP_DEVICE_ID_TYPE:
 		DRM_DEBUG_KMS("Found Ice Lake PCH\n");
 		WARN_ON(!IS_ICELAKE(dev_priv));
diff --git a/drivers/gpu/drm/i915/intel_pch.h b/drivers/gpu/drm/i915/intel_pch.h
index f4dc18c34291..d26c25dd8d54 100644
--- a/drivers/gpu/drm/i915/intel_pch.h
+++ b/drivers/gpu/drm/i915/intel_pch.h
@@ -43,6 +43,7 @@ enum intel_pch {
 #define INTEL_PCH_CNP_LP_DEVICE_ID_TYPE		0x9D80
 #define INTEL_PCH_CMP_DEVICE_ID_TYPE		0x0280
 #define INTEL_PCH_CMP2_DEVICE_ID_TYPE		0x0680
+#define INTEL_PCH_CMP_V_DEVICE_ID_TYPE		0xA380
 #define INTEL_PCH_ICP_DEVICE_ID_TYPE		0x3480
 #define INTEL_PCH_MCC_DEVICE_ID_TYPE		0x4B00
 #define INTEL_PCH_TGP_DEVICE_ID_TYPE		0xA080
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 362234449087..809bff955b5a 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -107,6 +107,14 @@ static void bxt_init_clock_gating(struct drm_i915_private *dev_priv)
 	 */
 	I915_WRITE(GEN9_CLKGATE_DIS_0, I915_READ(GEN9_CLKGATE_DIS_0) |
 		   PWM1_GATING_DIS | PWM2_GATING_DIS);
+
+	/*
+	 * Lower the display internal timeout.
+	 * This is needed to avoid any hard hangs when DSI port PLL
+	 * is off and a MMIO access is attempted by any privilege
+	 * application, using batch buffers or any other means.
+	 */
+	I915_WRITE(RM_TIMEOUT, MMIO_TIMEOUT_US(950));
 }
 
 static void glk_init_clock_gating(struct drm_i915_private *dev_priv)
@@ -197,8 +205,6 @@ static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
 		break;
 	}
 
-	dev_priv->ips.r_t = dev_priv->mem_freq;
-
 	switch (csipll & 0x3ff) {
 	case 0x00c:
 		dev_priv->fsb_freq = 3200;
@@ -227,14 +233,6 @@ static void i915_ironlake_get_mem_freq(struct drm_i915_private *dev_priv)
 		dev_priv->fsb_freq = 0;
 		break;
 	}
-
-	if (dev_priv->fsb_freq == 3200) {
-		dev_priv->ips.c_m = 0;
-	} else if (dev_priv->fsb_freq > 3200 && dev_priv->fsb_freq <= 4800) {
-		dev_priv->ips.c_m = 1;
-	} else {
-		dev_priv->ips.c_m = 2;
-	}
 }
 
 static const struct cxsr_latency cxsr_latency_table[] = {
@@ -4097,93 +4095,6 @@ skl_plane_downscale_amount(const struct intel_crtc_state *crtc_state,
 	return mul_fixed16(downscale_w, downscale_h);
 }
 
-static uint_fixed_16_16_t
-skl_pipe_downscale_amount(const struct intel_crtc_state *crtc_state)
-{
-	uint_fixed_16_16_t pipe_downscale = u32_to_fixed16(1);
-
-	if (!crtc_state->base.enable)
-		return pipe_downscale;
-
-	if (crtc_state->pch_pfit.enabled) {
-		u32 src_w, src_h, dst_w, dst_h;
-		u32 pfit_size = crtc_state->pch_pfit.size;
-		uint_fixed_16_16_t fp_w_ratio, fp_h_ratio;
-		uint_fixed_16_16_t downscale_h, downscale_w;
-
-		src_w = crtc_state->pipe_src_w;
-		src_h = crtc_state->pipe_src_h;
-		dst_w = pfit_size >> 16;
-		dst_h = pfit_size & 0xffff;
-
-		if (!dst_w || !dst_h)
-			return pipe_downscale;
-
-		fp_w_ratio = div_fixed16(src_w, dst_w);
-		fp_h_ratio = div_fixed16(src_h, dst_h);
-		downscale_w = max_fixed16(fp_w_ratio, u32_to_fixed16(1));
-		downscale_h = max_fixed16(fp_h_ratio, u32_to_fixed16(1));
-
-		pipe_downscale = mul_fixed16(downscale_w, downscale_h);
-	}
-
-	return pipe_downscale;
-}
-
-int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
-				  struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(intel_crtc->base.dev);
-	struct drm_atomic_state *state = crtc_state->base.state;
-	const struct intel_plane_state *plane_state;
-	struct intel_plane *plane;
-	int crtc_clock, dotclk;
-	u32 pipe_max_pixel_rate;
-	uint_fixed_16_16_t pipe_downscale;
-	uint_fixed_16_16_t max_downscale = u32_to_fixed16(1);
-
-	if (!crtc_state->base.enable)
-		return 0;
-
-	intel_atomic_crtc_state_for_each_plane_state(plane, plane_state, crtc_state) {
-		uint_fixed_16_16_t plane_downscale;
-		uint_fixed_16_16_t fp_9_div_8 = div_fixed16(9, 8);
-		int bpp;
-
-		if (!intel_wm_plane_visible(crtc_state, plane_state))
-			continue;
-
-		if (WARN_ON(!plane_state->base.fb))
-			return -EINVAL;
-
-		plane_downscale = skl_plane_downscale_amount(crtc_state, plane_state);
-		bpp = plane_state->base.fb->format->cpp[0] * 8;
-		if (bpp == 64)
-			plane_downscale = mul_fixed16(plane_downscale,
-						      fp_9_div_8);
-
-		max_downscale = max_fixed16(plane_downscale, max_downscale);
-	}
-	pipe_downscale = skl_pipe_downscale_amount(crtc_state);
-
-	pipe_downscale = mul_fixed16(pipe_downscale, max_downscale);
-
-	crtc_clock = crtc_state->base.adjusted_mode.crtc_clock;
-	dotclk = to_intel_atomic_state(state)->cdclk.logical.cdclk;
-
-	if (IS_GEMINILAKE(dev_priv) || INTEL_GEN(dev_priv) >= 10)
-		dotclk *= 2;
-
-	pipe_max_pixel_rate = div_round_up_u32_fixed16(dotclk, pipe_downscale);
-
-	if (pipe_max_pixel_rate < crtc_clock) {
-		DRM_DEBUG_KMS("Max supported pixel clock with scaling exceeded\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static u64
 skl_plane_relative_data_rate(const struct intel_crtc_state *crtc_state,
 			     const struct intel_plane_state *plane_state,
@@ -6339,1627 +6250,6 @@ void intel_init_ipc(struct drm_i915_private *dev_priv)
 	intel_enable_ipc(dev_priv);
 }
 
-/*
- * Lock protecting IPS related data structures
- */
-DEFINE_SPINLOCK(mchdev_lock);
-
-bool ironlake_set_drps(struct drm_i915_private *i915, u8 val)
-{
-	struct intel_uncore *uncore = &i915->uncore;
-	u16 rgvswctl;
-
-	lockdep_assert_held(&mchdev_lock);
-
-	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
-	if (rgvswctl & MEMCTL_CMD_STS) {
-		DRM_DEBUG("gpu busy, RCS change rejected\n");
-		return false; /* still busy with another command */
-	}
-
-	rgvswctl = (MEMCTL_CMD_CHFREQ << MEMCTL_CMD_SHIFT) |
-		(val << MEMCTL_FREQ_SHIFT) | MEMCTL_SFCAVM;
-	intel_uncore_write16(uncore, MEMSWCTL, rgvswctl);
-	intel_uncore_posting_read16(uncore, MEMSWCTL);
-
-	rgvswctl |= MEMCTL_CMD_STS;
-	intel_uncore_write16(uncore, MEMSWCTL, rgvswctl);
-
-	return true;
-}
-
-static void ironlake_enable_drps(struct drm_i915_private *dev_priv)
-{
-	struct intel_uncore *uncore = &dev_priv->uncore;
-	u32 rgvmodectl;
-	u8 fmax, fmin, fstart, vstart;
-
-	spin_lock_irq(&mchdev_lock);
-
-	rgvmodectl = intel_uncore_read(uncore, MEMMODECTL);
-
-	/* Enable temp reporting */
-	intel_uncore_write16(uncore, PMMISC, I915_READ(PMMISC) | MCPPCE_EN);
-	intel_uncore_write16(uncore, TSC1, I915_READ(TSC1) | TSE);
-
-	/* 100ms RC evaluation intervals */
-	intel_uncore_write(uncore, RCUPEI, 100000);
-	intel_uncore_write(uncore, RCDNEI, 100000);
-
-	/* Set max/min thresholds to 90ms and 80ms respectively */
-	intel_uncore_write(uncore, RCBMAXAVG, 90000);
-	intel_uncore_write(uncore, RCBMINAVG, 80000);
-
-	intel_uncore_write(uncore, MEMIHYST, 1);
-
-	/* Set up min, max, and cur for interrupt handling */
-	fmax = (rgvmodectl & MEMMODE_FMAX_MASK) >> MEMMODE_FMAX_SHIFT;
-	fmin = (rgvmodectl & MEMMODE_FMIN_MASK);
-	fstart = (rgvmodectl & MEMMODE_FSTART_MASK) >>
-		MEMMODE_FSTART_SHIFT;
-
-	vstart = (intel_uncore_read(uncore, PXVFREQ(fstart)) &
-		  PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT;
-
-	dev_priv->ips.fmax = fmax; /* IPS callback will increase this */
-	dev_priv->ips.fstart = fstart;
-
-	dev_priv->ips.max_delay = fstart;
-	dev_priv->ips.min_delay = fmin;
-	dev_priv->ips.cur_delay = fstart;
-
-	DRM_DEBUG_DRIVER("fmax: %d, fmin: %d, fstart: %d\n",
-			 fmax, fmin, fstart);
-
-	intel_uncore_write(uncore,
-			   MEMINTREN,
-			   MEMINT_CX_SUPR_EN | MEMINT_EVAL_CHG_EN);
-
-	/*
-	 * Interrupts will be enabled in ironlake_irq_postinstall
-	 */
-
-	intel_uncore_write(uncore, VIDSTART, vstart);
-	intel_uncore_posting_read(uncore, VIDSTART);
-
-	rgvmodectl |= MEMMODE_SWMODE_EN;
-	intel_uncore_write(uncore, MEMMODECTL, rgvmodectl);
-
-	if (wait_for_atomic((intel_uncore_read(uncore, MEMSWCTL) &
-			     MEMCTL_CMD_STS) == 0, 10))
-		DRM_ERROR("stuck trying to change perf mode\n");
-	mdelay(1);
-
-	ironlake_set_drps(dev_priv, fstart);
-
-	dev_priv->ips.last_count1 =
-		intel_uncore_read(uncore, DMIEC) +
-		intel_uncore_read(uncore, DDREC) +
-		intel_uncore_read(uncore, CSIEC);
-	dev_priv->ips.last_time1 = jiffies_to_msecs(jiffies);
-	dev_priv->ips.last_count2 = intel_uncore_read(uncore, GFXEC);
-	dev_priv->ips.last_time2 = ktime_get_raw_ns();
-
-	spin_unlock_irq(&mchdev_lock);
-}
-
-static void ironlake_disable_drps(struct drm_i915_private *i915)
-{
-	struct intel_uncore *uncore = &i915->uncore;
-	u16 rgvswctl;
-
-	spin_lock_irq(&mchdev_lock);
-
-	rgvswctl = intel_uncore_read16(uncore, MEMSWCTL);
-
-	/* Ack interrupts, disable EFC interrupt */
-	intel_uncore_write(uncore,
-			   MEMINTREN,
-			   intel_uncore_read(uncore, MEMINTREN) &
-			   ~MEMINT_EVAL_CHG_EN);
-	intel_uncore_write(uncore, MEMINTRSTS, MEMINT_EVAL_CHG);
-	intel_uncore_write(uncore,
-			   DEIER,
-			   intel_uncore_read(uncore, DEIER) & ~DE_PCU_EVENT);
-	intel_uncore_write(uncore, DEIIR, DE_PCU_EVENT);
-	intel_uncore_write(uncore,
-			   DEIMR,
-			   intel_uncore_read(uncore, DEIMR) | DE_PCU_EVENT);
-
-	/* Go back to the starting frequency */
-	ironlake_set_drps(i915, i915->ips.fstart);
-	mdelay(1);
-	rgvswctl |= MEMCTL_CMD_STS;
-	intel_uncore_write(uncore, MEMSWCTL, rgvswctl);
-	mdelay(1);
-
-	spin_unlock_irq(&mchdev_lock);
-}
-
-/* There's a funny hw issue where the hw returns all 0 when reading from
- * GEN6_RP_INTERRUPT_LIMITS. Hence we always need to compute the desired value
- * ourselves, instead of doing a rmw cycle (which might result in us clearing
- * all limits and the gpu stuck at whatever frequency it is at atm).
- */
-static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 limits;
-
-	/* Only set the down limit when we've reached the lowest level to avoid
-	 * getting more interrupts, otherwise leave this clear. This prevents a
-	 * race in the hw when coming out of rc6: There's a tiny window where
-	 * the hw runs at the minimal clock before selecting the desired
-	 * frequency, if the down threshold expires in that window we will not
-	 * receive a down interrupt. */
-	if (INTEL_GEN(dev_priv) >= 9) {
-		limits = (rps->max_freq_softlimit) << 23;
-		if (val <= rps->min_freq_softlimit)
-			limits |= (rps->min_freq_softlimit) << 14;
-	} else {
-		limits = rps->max_freq_softlimit << 24;
-		if (val <= rps->min_freq_softlimit)
-			limits |= rps->min_freq_softlimit << 16;
-	}
-
-	return limits;
-}
-
-static void rps_set_power(struct drm_i915_private *dev_priv, int new_power)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 threshold_up = 0, threshold_down = 0; /* in % */
-	u32 ei_up = 0, ei_down = 0;
-
-	lockdep_assert_held(&rps->power.mutex);
-
-	if (new_power == rps->power.mode)
-		return;
-
-	/* Note the units here are not exactly 1us, but 1280ns. */
-	switch (new_power) {
-	case LOW_POWER:
-		/* Upclock if more than 95% busy over 16ms */
-		ei_up = 16000;
-		threshold_up = 95;
-
-		/* Downclock if less than 85% busy over 32ms */
-		ei_down = 32000;
-		threshold_down = 85;
-		break;
-
-	case BETWEEN:
-		/* Upclock if more than 90% busy over 13ms */
-		ei_up = 13000;
-		threshold_up = 90;
-
-		/* Downclock if less than 75% busy over 32ms */
-		ei_down = 32000;
-		threshold_down = 75;
-		break;
-
-	case HIGH_POWER:
-		/* Upclock if more than 85% busy over 10ms */
-		ei_up = 10000;
-		threshold_up = 85;
-
-		/* Downclock if less than 60% busy over 32ms */
-		ei_down = 32000;
-		threshold_down = 60;
-		break;
-	}
-
-	/* When byt can survive without system hang with dynamic
-	 * sw freq adjustments, this restriction can be lifted.
-	 */
-	if (IS_VALLEYVIEW(dev_priv))
-		goto skip_hw_write;
-
-	I915_WRITE(GEN6_RP_UP_EI,
-		   GT_INTERVAL_FROM_US(dev_priv, ei_up));
-	I915_WRITE(GEN6_RP_UP_THRESHOLD,
-		   GT_INTERVAL_FROM_US(dev_priv,
-				       ei_up * threshold_up / 100));
-
-	I915_WRITE(GEN6_RP_DOWN_EI,
-		   GT_INTERVAL_FROM_US(dev_priv, ei_down));
-	I915_WRITE(GEN6_RP_DOWN_THRESHOLD,
-		   GT_INTERVAL_FROM_US(dev_priv,
-				       ei_down * threshold_down / 100));
-
-	I915_WRITE(GEN6_RP_CONTROL,
-		   (INTEL_GEN(dev_priv) > 9 ? 0 : GEN6_RP_MEDIA_TURBO) |
-		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX |
-		   GEN6_RP_ENABLE |
-		   GEN6_RP_UP_BUSY_AVG |
-		   GEN6_RP_DOWN_IDLE_AVG);
-
-skip_hw_write:
-	rps->power.mode = new_power;
-	rps->power.up_threshold = threshold_up;
-	rps->power.down_threshold = threshold_down;
-}
-
-static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	int new_power;
-
-	new_power = rps->power.mode;
-	switch (rps->power.mode) {
-	case LOW_POWER:
-		if (val > rps->efficient_freq + 1 &&
-		    val > rps->cur_freq)
-			new_power = BETWEEN;
-		break;
-
-	case BETWEEN:
-		if (val <= rps->efficient_freq &&
-		    val < rps->cur_freq)
-			new_power = LOW_POWER;
-		else if (val >= rps->rp0_freq &&
-			 val > rps->cur_freq)
-			new_power = HIGH_POWER;
-		break;
-
-	case HIGH_POWER:
-		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
-		    val < rps->cur_freq)
-			new_power = BETWEEN;
-		break;
-	}
-	/* Max/min bins are special */
-	if (val <= rps->min_freq_softlimit)
-		new_power = LOW_POWER;
-	if (val >= rps->max_freq_softlimit)
-		new_power = HIGH_POWER;
-
-	mutex_lock(&rps->power.mutex);
-	if (rps->power.interactive)
-		new_power = HIGH_POWER;
-	rps_set_power(dev_priv, new_power);
-	mutex_unlock(&rps->power.mutex);
-}
-
-void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive)
-{
-	struct intel_rps *rps = &i915->gt_pm.rps;
-
-	if (INTEL_GEN(i915) < 6)
-		return;
-
-	mutex_lock(&rps->power.mutex);
-	if (interactive) {
-		if (!rps->power.interactive++ && READ_ONCE(i915->gt.awake))
-			rps_set_power(i915, HIGH_POWER);
-	} else {
-		GEM_BUG_ON(!rps->power.interactive);
-		rps->power.interactive--;
-	}
-	mutex_unlock(&rps->power.mutex);
-}
-
-static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 mask = 0;
-
-	/* We use UP_EI_EXPIRED interupts for both up/down in manual mode */
-	if (val > rps->min_freq_softlimit)
-		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_DOWN_THRESHOLD | GEN6_PM_RP_DOWN_TIMEOUT;
-	if (val < rps->max_freq_softlimit)
-		mask |= GEN6_PM_RP_UP_EI_EXPIRED | GEN6_PM_RP_UP_THRESHOLD;
-
-	mask &= dev_priv->pm_rps_events;
-
-	return gen6_sanitize_rps_pm_mask(dev_priv, ~mask);
-}
-
-/* gen6_set_rps is called to update the frequency request, but should also be
- * called when the range (min_delay and max_delay) is modified so that we can
- * update the GEN6_RP_INTERRUPT_LIMITS register accordingly. */
-static int gen6_set_rps(struct drm_i915_private *dev_priv, u8 val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/* min/max delay may still have been modified so be sure to
-	 * write the limits value.
-	 */
-	if (val != rps->cur_freq) {
-		gen6_set_rps_thresholds(dev_priv, val);
-
-		if (INTEL_GEN(dev_priv) >= 9)
-			I915_WRITE(GEN6_RPNSWREQ,
-				   GEN9_FREQUENCY(val));
-		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			I915_WRITE(GEN6_RPNSWREQ,
-				   HSW_FREQUENCY(val));
-		else
-			I915_WRITE(GEN6_RPNSWREQ,
-				   GEN6_FREQUENCY(val) |
-				   GEN6_OFFSET(0) |
-				   GEN6_AGGRESSIVE_TURBO);
-	}
-
-	/* Make sure we continue to get interrupts
-	 * until we hit the minimum or maximum frequencies.
-	 */
-	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, intel_rps_limits(dev_priv, val));
-	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
-
-	rps->cur_freq = val;
-	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
-
-	return 0;
-}
-
-static int valleyview_set_rps(struct drm_i915_private *dev_priv, u8 val)
-{
-	int err;
-
-	if (WARN_ONCE(IS_CHERRYVIEW(dev_priv) && (val & 1),
-		      "Odd GPU freq value\n"))
-		val &= ~1;
-
-	I915_WRITE(GEN6_PMINTRMSK, gen6_rps_pm_mask(dev_priv, val));
-
-	if (val != dev_priv->gt_pm.rps.cur_freq) {
-		vlv_punit_get(dev_priv);
-		err = vlv_punit_write(dev_priv, PUNIT_REG_GPU_FREQ_REQ, val);
-		vlv_punit_put(dev_priv);
-		if (err)
-			return err;
-
-		gen6_set_rps_thresholds(dev_priv, val);
-	}
-
-	dev_priv->gt_pm.rps.cur_freq = val;
-	trace_intel_gpu_freq_change(intel_gpu_freq(dev_priv, val));
-
-	return 0;
-}
-
-/* vlv_set_rps_idle: Set the frequency to idle, if Gfx clocks are down
- *
- * * If Gfx is Idle, then
- * 1. Forcewake Media well.
- * 2. Request idle freq.
- * 3. Release Forcewake of Media well.
-*/
-static void vlv_set_rps_idle(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 val = rps->idle_freq;
-	int err;
-
-	if (rps->cur_freq <= val)
-		return;
-
-	/* The punit delays the write of the frequency and voltage until it
-	 * determines the GPU is awake. During normal usage we don't want to
-	 * waste power changing the frequency if the GPU is sleeping (rc6).
-	 * However, the GPU and driver is now idle and we do not want to delay
-	 * switching to minimum voltage (reducing power whilst idle) as we do
-	 * not expect to be woken in the near future and so must flush the
-	 * change by waking the device.
-	 *
-	 * We choose to take the media powerwell (either would do to trick the
-	 * punit into committing the voltage change) as that takes a lot less
-	 * power than the render powerwell.
-	 */
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_MEDIA);
-	err = valleyview_set_rps(dev_priv, val);
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_MEDIA);
-
-	if (err)
-		DRM_ERROR("Failed to set RPS for idle\n");
-}
-
-void gen6_rps_busy(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	mutex_lock(&rps->lock);
-	if (rps->enabled) {
-		u8 freq;
-
-		if (dev_priv->pm_rps_events & GEN6_PM_RP_UP_EI_EXPIRED)
-			gen6_rps_reset_ei(dev_priv);
-		I915_WRITE(GEN6_PMINTRMSK,
-			   gen6_rps_pm_mask(dev_priv, rps->cur_freq));
-
-		gen6_enable_rps_interrupts(dev_priv);
-
-		/* Use the user's desired frequency as a guide, but for better
-		 * performance, jump directly to RPe as our starting frequency.
-		 */
-		freq = max(rps->cur_freq,
-			   rps->efficient_freq);
-
-		if (intel_set_rps(dev_priv,
-				  clamp(freq,
-					rps->min_freq_softlimit,
-					rps->max_freq_softlimit)))
-			DRM_DEBUG_DRIVER("Failed to set idle frequency\n");
-	}
-	mutex_unlock(&rps->lock);
-}
-
-void gen6_rps_idle(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/* Flush our bottom-half so that it does not race with us
-	 * setting the idle frequency and so that it is bounded by
-	 * our rpm wakeref. And then disable the interrupts to stop any
-	 * futher RPS reclocking whilst we are asleep.
-	 */
-	gen6_disable_rps_interrupts(dev_priv);
-
-	mutex_lock(&rps->lock);
-	if (rps->enabled) {
-		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-			vlv_set_rps_idle(dev_priv);
-		else
-			gen6_set_rps(dev_priv, rps->idle_freq);
-		rps->last_adj = 0;
-		I915_WRITE(GEN6_PMINTRMSK,
-			   gen6_sanitize_rps_pm_mask(dev_priv, ~0));
-	}
-	mutex_unlock(&rps->lock);
-}
-
-void gen6_rps_boost(struct i915_request *rq)
-{
-	struct intel_rps *rps = &rq->i915->gt_pm.rps;
-	unsigned long flags;
-	bool boost;
-
-	/* This is intentionally racy! We peek at the state here, then
-	 * validate inside the RPS worker.
-	 */
-	if (!rps->enabled)
-		return;
-
-	if (i915_request_signaled(rq))
-		return;
-
-	/* Serializes with i915_request_retire() */
-	boost = false;
-	spin_lock_irqsave(&rq->lock, flags);
-	if (!i915_request_has_waitboost(rq) &&
-	    !dma_fence_is_signaled_locked(&rq->fence)) {
-		boost = !atomic_fetch_inc(&rps->num_waiters);
-		rq->flags |= I915_REQUEST_WAITBOOST;
-	}
-	spin_unlock_irqrestore(&rq->lock, flags);
-	if (!boost)
-		return;
-
-	if (READ_ONCE(rps->cur_freq) < rps->boost_freq)
-		schedule_work(&rps->work);
-
-	atomic_inc(&rps->boosts);
-}
-
-int intel_set_rps(struct drm_i915_private *dev_priv, u8 val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	int err;
-
-	lockdep_assert_held(&rps->lock);
-	GEM_BUG_ON(val > rps->max_freq);
-	GEM_BUG_ON(val < rps->min_freq);
-
-	if (!rps->enabled) {
-		rps->cur_freq = val;
-		return 0;
-	}
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		err = valleyview_set_rps(dev_priv, val);
-	else
-		err = gen6_set_rps(dev_priv, val);
-
-	return err;
-}
-
-static void gen9_disable_rps(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void gen6_disable_rps(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RPNSWREQ, 1 << 31);
-	I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void cherryview_disable_rps(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void valleyview_disable_rps(struct drm_i915_private *dev_priv)
-{
-	I915_WRITE(GEN6_RP_CONTROL, 0);
-}
-
-static void gen6_init_rps_frequencies(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/* All of these values are in units of 50MHz */
-
-	/* static values from HW: RP0 > RP1 > RPn (min_freq) */
-	if (IS_GEN9_LP(dev_priv)) {
-		u32 rp_state_cap = I915_READ(BXT_RP_STATE_CAP);
-		rps->rp0_freq = (rp_state_cap >> 16) & 0xff;
-		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
-		rps->min_freq = (rp_state_cap >>  0) & 0xff;
-	} else {
-		u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
-		rps->rp0_freq = (rp_state_cap >>  0) & 0xff;
-		rps->rp1_freq = (rp_state_cap >>  8) & 0xff;
-		rps->min_freq = (rp_state_cap >> 16) & 0xff;
-	}
-	/* hw_max = RP0 until we check for overclocking */
-	rps->max_freq = rps->rp0_freq;
-
-	rps->efficient_freq = rps->rp1_freq;
-	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv) ||
-	    IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
-		u32 ddcc_status = 0;
-
-		if (sandybridge_pcode_read(dev_priv,
-					   HSW_PCODE_DYNAMIC_DUTY_CYCLE_CONTROL,
-					   &ddcc_status, NULL) == 0)
-			rps->efficient_freq =
-				clamp_t(u8,
-					((ddcc_status >> 8) & 0xff),
-					rps->min_freq,
-					rps->max_freq);
-	}
-
-	if (IS_GEN9_BC(dev_priv) || INTEL_GEN(dev_priv) >= 10) {
-		/* Store the frequency values in 16.66 MHZ units, which is
-		 * the natural hardware unit for SKL
-		 */
-		rps->rp0_freq *= GEN9_FREQ_SCALER;
-		rps->rp1_freq *= GEN9_FREQ_SCALER;
-		rps->min_freq *= GEN9_FREQ_SCALER;
-		rps->max_freq *= GEN9_FREQ_SCALER;
-		rps->efficient_freq *= GEN9_FREQ_SCALER;
-	}
-}
-
-static void reset_rps(struct drm_i915_private *dev_priv,
-		      int (*set)(struct drm_i915_private *, u8))
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u8 freq = rps->cur_freq;
-
-	/* force a reset */
-	rps->power.mode = -1;
-	rps->cur_freq = -1;
-
-	if (set(dev_priv, freq))
-		DRM_ERROR("Failed to reset RPS to initial values\n");
-}
-
-/* See the Gen9_GT_PM_Programming_Guide doc for the below */
-static void gen9_enable_rps(struct drm_i915_private *dev_priv)
-{
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* Program defaults and thresholds for RPS */
-	if (IS_GEN(dev_priv, 9))
-		I915_WRITE(GEN6_RC_VIDEO_FREQ,
-			GEN9_FREQUENCY(dev_priv->gt_pm.rps.rp1_freq));
-
-	/* 1 second timeout*/
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT,
-		GT_INTERVAL_FROM_US(dev_priv, 1000000));
-
-	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 0xa);
-
-	/* Leaning on the below call to gen6_set_rps to program/setup the
-	 * Up/Down EI & threshold registers, as well as the RP_CONTROL,
-	 * RP_INTERRUPT_LIMITS & RPNSWREQ registers */
-	reset_rps(dev_priv, gen6_set_rps);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static void gen8_enable_rps(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* 1 Program defaults and thresholds for RPS*/
-	I915_WRITE(GEN6_RPNSWREQ,
-		   HSW_FREQUENCY(rps->rp1_freq));
-	I915_WRITE(GEN6_RC_VIDEO_FREQ,
-		   HSW_FREQUENCY(rps->rp1_freq));
-	/* NB: Docs say 1s, and 1000000 - which aren't equivalent */
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 100000000 / 128); /* 1 second timeout */
-
-	/* Docs recommend 900MHz, and 300 MHz respectively */
-	I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
-		   rps->max_freq_softlimit << 24 |
-		   rps->min_freq_softlimit << 16);
-
-	I915_WRITE(GEN6_RP_UP_THRESHOLD, 7600000 / 128); /* 76ms busyness per EI, 90% */
-	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 31300000 / 128); /* 313ms busyness per EI, 70%*/
-	I915_WRITE(GEN6_RP_UP_EI, 66000); /* 84.48ms, XXX: random? */
-	I915_WRITE(GEN6_RP_DOWN_EI, 350000); /* 448ms, XXX: random? */
-
-	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
-	/* 2: Enable RPS */
-	I915_WRITE(GEN6_RP_CONTROL,
-		   GEN6_RP_MEDIA_TURBO |
-		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX |
-		   GEN6_RP_ENABLE |
-		   GEN6_RP_UP_BUSY_AVG |
-		   GEN6_RP_DOWN_IDLE_AVG);
-
-	reset_rps(dev_priv, gen6_set_rps);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static void gen6_enable_rps(struct drm_i915_private *dev_priv)
-{
-	/* Here begins a magic sequence of register writes to enable
-	 * auto-downclocking.
-	 *
-	 * Perhaps there might be some value in exposing these to
-	 * userspace...
-	 */
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* Power down if completely idle for over 50ms */
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 50000);
-	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
-	reset_rps(dev_priv, gen6_set_rps);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static int cherryview_rps_max_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rp0;
-
-	val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE);
-
-	switch (RUNTIME_INFO(dev_priv)->sseu.eu_total) {
-	case 8:
-		/* (2 * 4) config */
-		rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS4EU_FUSE_SHIFT);
-		break;
-	case 12:
-		/* (2 * 6) config */
-		rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS6EU_FUSE_SHIFT);
-		break;
-	case 16:
-		/* (2 * 8) config */
-	default:
-		/* Setting (2 * 8) Min RP0 for any other combination */
-		rp0 = (val >> FB_GFX_FMAX_AT_VMAX_2SS8EU_FUSE_SHIFT);
-		break;
-	}
-
-	rp0 = (rp0 & FB_GFX_FREQ_FUSE_MASK);
-
-	return rp0;
-}
-
-static int cherryview_rps_rpe_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rpe;
-
-	val = vlv_punit_read(dev_priv, PUNIT_GPU_DUTYCYCLE_REG);
-	rpe = (val >> PUNIT_GPU_DUTYCYCLE_RPE_FREQ_SHIFT) & PUNIT_GPU_DUTYCYCLE_RPE_FREQ_MASK;
-
-	return rpe;
-}
-
-static int cherryview_rps_guar_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rp1;
-
-	val = vlv_punit_read(dev_priv, FB_GFX_FMAX_AT_VMAX_FUSE);
-	rp1 = (val & FB_GFX_FREQ_FUSE_MASK);
-
-	return rp1;
-}
-
-static u32 cherryview_rps_min_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rpn;
-
-	val = vlv_punit_read(dev_priv, FB_GFX_FMIN_AT_VMIN_FUSE);
-	rpn = ((val >> FB_GFX_FMIN_AT_VMIN_FUSE_SHIFT) &
-		       FB_GFX_FREQ_FUSE_MASK);
-
-	return rpn;
-}
-
-static int valleyview_rps_guar_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rp1;
-
-	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE);
-
-	rp1 = (val & FB_GFX_FGUARANTEED_FREQ_FUSE_MASK) >> FB_GFX_FGUARANTEED_FREQ_FUSE_SHIFT;
-
-	return rp1;
-}
-
-static int valleyview_rps_max_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rp0;
-
-	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FREQ_FUSE);
-
-	rp0 = (val & FB_GFX_MAX_FREQ_FUSE_MASK) >> FB_GFX_MAX_FREQ_FUSE_SHIFT;
-	/* Clamp to max */
-	rp0 = min_t(u32, rp0, 0xea);
-
-	return rp0;
-}
-
-static int valleyview_rps_rpe_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val, rpe;
-
-	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_LO);
-	rpe = (val & FB_FMAX_VMIN_FREQ_LO_MASK) >> FB_FMAX_VMIN_FREQ_LO_SHIFT;
-	val = vlv_nc_read(dev_priv, IOSF_NC_FB_GFX_FMAX_FUSE_HI);
-	rpe |= (val & FB_FMAX_VMIN_FREQ_HI_MASK) << 5;
-
-	return rpe;
-}
-
-static int valleyview_rps_min_freq(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-
-	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_LFM) & 0xff;
-	/*
-	 * According to the BYT Punit GPU turbo HAS 1.1.6.3 the minimum value
-	 * for the minimum frequency in GPLL mode is 0xc1. Contrary to this on
-	 * a BYT-M B0 the above register contains 0xbf. Moreover when setting
-	 * a frequency Punit will not allow values below 0xc0. Clamp it 0xc0
-	 * to make sure it matches what Punit accepts.
-	 */
-	return max_t(u32, val, 0xc0);
-}
-
-static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
-{
-	dev_priv->gt_pm.rps.gpll_ref_freq =
-		vlv_get_cck_clock(dev_priv, "GPLL ref",
-				  CCK_GPLL_CLOCK_CONTROL,
-				  dev_priv->czclk_freq);
-
-	DRM_DEBUG_DRIVER("GPLL reference freq: %d kHz\n",
-			 dev_priv->gt_pm.rps.gpll_ref_freq);
-}
-
-static void valleyview_init_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 val;
-
-	vlv_iosf_sb_get(dev_priv,
-			BIT(VLV_IOSF_SB_PUNIT) |
-			BIT(VLV_IOSF_SB_NC) |
-			BIT(VLV_IOSF_SB_CCK));
-
-	vlv_init_gpll_ref_freq(dev_priv);
-
-	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-	switch ((val >> 6) & 3) {
-	case 0:
-	case 1:
-		dev_priv->mem_freq = 800;
-		break;
-	case 2:
-		dev_priv->mem_freq = 1066;
-		break;
-	case 3:
-		dev_priv->mem_freq = 1333;
-		break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", dev_priv->mem_freq);
-
-	rps->max_freq = valleyview_rps_max_freq(dev_priv);
-	rps->rp0_freq = rps->max_freq;
-	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->max_freq),
-			 rps->max_freq);
-
-	rps->efficient_freq = valleyview_rps_rpe_freq(dev_priv);
-	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->efficient_freq),
-			 rps->efficient_freq);
-
-	rps->rp1_freq = valleyview_rps_guar_freq(dev_priv);
-	DRM_DEBUG_DRIVER("RP1(Guar Freq) GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->rp1_freq),
-			 rps->rp1_freq);
-
-	rps->min_freq = valleyview_rps_min_freq(dev_priv);
-	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->min_freq),
-			 rps->min_freq);
-
-	vlv_iosf_sb_put(dev_priv,
-			BIT(VLV_IOSF_SB_PUNIT) |
-			BIT(VLV_IOSF_SB_NC) |
-			BIT(VLV_IOSF_SB_CCK));
-}
-
-static void cherryview_init_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	u32 val;
-
-	vlv_iosf_sb_get(dev_priv,
-			BIT(VLV_IOSF_SB_PUNIT) |
-			BIT(VLV_IOSF_SB_NC) |
-			BIT(VLV_IOSF_SB_CCK));
-
-	vlv_init_gpll_ref_freq(dev_priv);
-
-	val = vlv_cck_read(dev_priv, CCK_FUSE_REG);
-
-	switch ((val >> 2) & 0x7) {
-	case 3:
-		dev_priv->mem_freq = 2000;
-		break;
-	default:
-		dev_priv->mem_freq = 1600;
-		break;
-	}
-	DRM_DEBUG_DRIVER("DDR speed: %d MHz\n", dev_priv->mem_freq);
-
-	rps->max_freq = cherryview_rps_max_freq(dev_priv);
-	rps->rp0_freq = rps->max_freq;
-	DRM_DEBUG_DRIVER("max GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->max_freq),
-			 rps->max_freq);
-
-	rps->efficient_freq = cherryview_rps_rpe_freq(dev_priv);
-	DRM_DEBUG_DRIVER("RPe GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->efficient_freq),
-			 rps->efficient_freq);
-
-	rps->rp1_freq = cherryview_rps_guar_freq(dev_priv);
-	DRM_DEBUG_DRIVER("RP1(Guar) GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->rp1_freq),
-			 rps->rp1_freq);
-
-	rps->min_freq = cherryview_rps_min_freq(dev_priv);
-	DRM_DEBUG_DRIVER("min GPU freq: %d MHz (%u)\n",
-			 intel_gpu_freq(dev_priv, rps->min_freq),
-			 rps->min_freq);
-
-	vlv_iosf_sb_put(dev_priv,
-			BIT(VLV_IOSF_SB_PUNIT) |
-			BIT(VLV_IOSF_SB_NC) |
-			BIT(VLV_IOSF_SB_CCK));
-
-	WARN_ONCE((rps->max_freq | rps->efficient_freq | rps->rp1_freq |
-		   rps->min_freq) & 1,
-		  "Odd GPU freq values\n");
-}
-
-static void cherryview_enable_rps(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	/* 1: Program defaults and thresholds for RPS*/
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
-	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
-	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
-	I915_WRITE(GEN6_RP_UP_EI, 66000);
-	I915_WRITE(GEN6_RP_DOWN_EI, 350000);
-
-	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
-	/* 2: Enable RPS */
-	I915_WRITE(GEN6_RP_CONTROL,
-		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX |
-		   GEN6_RP_ENABLE |
-		   GEN6_RP_UP_BUSY_AVG |
-		   GEN6_RP_DOWN_IDLE_AVG);
-
-	/* Setting Fixed Bias */
-	vlv_punit_get(dev_priv);
-
-	val = VLV_OVERRIDE_EN | VLV_SOC_TDP_EN | CHV_BIAS_CPU_50_SOC_50;
-	vlv_punit_write(dev_priv, VLV_TURBO_SOC_OVERRIDE, val);
-
-	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-
-	vlv_punit_put(dev_priv);
-
-	/* RPS code assumes GPLL is used */
-	WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
-
-	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
-	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
-
-	reset_rps(dev_priv, valleyview_set_rps);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static void valleyview_enable_rps(struct drm_i915_private *dev_priv)
-{
-	u32 val;
-
-	intel_uncore_forcewake_get(&dev_priv->uncore, FORCEWAKE_ALL);
-
-	I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
-	I915_WRITE(GEN6_RP_UP_THRESHOLD, 59400);
-	I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 245000);
-	I915_WRITE(GEN6_RP_UP_EI, 66000);
-	I915_WRITE(GEN6_RP_DOWN_EI, 350000);
-
-	I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
-
-	I915_WRITE(GEN6_RP_CONTROL,
-		   GEN6_RP_MEDIA_TURBO |
-		   GEN6_RP_MEDIA_HW_NORMAL_MODE |
-		   GEN6_RP_MEDIA_IS_GFX |
-		   GEN6_RP_ENABLE |
-		   GEN6_RP_UP_BUSY_AVG |
-		   GEN6_RP_DOWN_IDLE_CONT);
-
-	vlv_punit_get(dev_priv);
-
-	/* Setting Fixed Bias */
-	val = VLV_OVERRIDE_EN | VLV_SOC_TDP_EN | VLV_BIAS_CPU_125_SOC_875;
-	vlv_punit_write(dev_priv, VLV_TURBO_SOC_OVERRIDE, val);
-
-	val = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
-
-	vlv_punit_put(dev_priv);
-
-	/* RPS code assumes GPLL is used */
-	WARN_ONCE((val & GPLLENABLE) == 0, "GPLL not enabled\n");
-
-	DRM_DEBUG_DRIVER("GPLL enabled? %s\n", yesno(val & GPLLENABLE));
-	DRM_DEBUG_DRIVER("GPU status: 0x%08x\n", val);
-
-	reset_rps(dev_priv, valleyview_set_rps);
-
-	intel_uncore_forcewake_put(&dev_priv->uncore, FORCEWAKE_ALL);
-}
-
-static unsigned long intel_pxfreq(u32 vidfreq)
-{
-	unsigned long freq;
-	int div = (vidfreq & 0x3f0000) >> 16;
-	int post = (vidfreq & 0x3000) >> 12;
-	int pre = (vidfreq & 0x7);
-
-	if (!pre)
-		return 0;
-
-	freq = ((div * 133333) / ((1<<post) * pre));
-
-	return freq;
-}
-
-static const struct cparams {
-	u16 i;
-	u16 t;
-	u16 m;
-	u16 c;
-} cparams[] = {
-	{ 1, 1333, 301, 28664 },
-	{ 1, 1066, 294, 24460 },
-	{ 1, 800, 294, 25192 },
-	{ 0, 1333, 276, 27605 },
-	{ 0, 1066, 276, 27605 },
-	{ 0, 800, 231, 23784 },
-};
-
-static unsigned long __i915_chipset_val(struct drm_i915_private *dev_priv)
-{
-	u64 total_count, diff, ret;
-	u32 count1, count2, count3, m = 0, c = 0;
-	unsigned long now = jiffies_to_msecs(jiffies), diff1;
-	int i;
-
-	lockdep_assert_held(&mchdev_lock);
-
-	diff1 = now - dev_priv->ips.last_time1;
-
-	/* Prevent division-by-zero if we are asking too fast.
-	 * Also, we don't get interesting results if we are polling
-	 * faster than once in 10ms, so just return the saved value
-	 * in such cases.
-	 */
-	if (diff1 <= 10)
-		return dev_priv->ips.chipset_power;
-
-	count1 = I915_READ(DMIEC);
-	count2 = I915_READ(DDREC);
-	count3 = I915_READ(CSIEC);
-
-	total_count = count1 + count2 + count3;
-
-	/* FIXME: handle per-counter overflow */
-	if (total_count < dev_priv->ips.last_count1) {
-		diff = ~0UL - dev_priv->ips.last_count1;
-		diff += total_count;
-	} else {
-		diff = total_count - dev_priv->ips.last_count1;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(cparams); i++) {
-		if (cparams[i].i == dev_priv->ips.c_m &&
-		    cparams[i].t == dev_priv->ips.r_t) {
-			m = cparams[i].m;
-			c = cparams[i].c;
-			break;
-		}
-	}
-
-	diff = div_u64(diff, diff1);
-	ret = ((m * diff) + c);
-	ret = div_u64(ret, 10);
-
-	dev_priv->ips.last_count1 = total_count;
-	dev_priv->ips.last_time1 = now;
-
-	dev_priv->ips.chipset_power = ret;
-
-	return ret;
-}
-
-unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
-{
-	intel_wakeref_t wakeref;
-	unsigned long val = 0;
-
-	if (!IS_GEN(dev_priv, 5))
-		return 0;
-
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
-		spin_lock_irq(&mchdev_lock);
-		val = __i915_chipset_val(dev_priv);
-		spin_unlock_irq(&mchdev_lock);
-	}
-
-	return val;
-}
-
-unsigned long i915_mch_val(struct drm_i915_private *i915)
-{
-	unsigned long m, x, b;
-	u32 tsfs;
-
-	tsfs = intel_uncore_read(&i915->uncore, TSFS);
-
-	m = ((tsfs & TSFS_SLOPE_MASK) >> TSFS_SLOPE_SHIFT);
-	x = intel_uncore_read8(&i915->uncore, TR1);
-
-	b = tsfs & TSFS_INTR_MASK;
-
-	return ((m * x) / 127) - b;
-}
-
-static int _pxvid_to_vd(u8 pxvid)
-{
-	if (pxvid == 0)
-		return 0;
-
-	if (pxvid >= 8 && pxvid < 31)
-		pxvid = 31;
-
-	return (pxvid + 2) * 125;
-}
-
-static u32 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
-{
-	const int vd = _pxvid_to_vd(pxvid);
-	const int vm = vd - 1125;
-
-	if (INTEL_INFO(dev_priv)->is_mobile)
-		return vm > 0 ? vm : 0;
-
-	return vd;
-}
-
-static void __i915_update_gfx_val(struct drm_i915_private *dev_priv)
-{
-	u64 now, diff, diffms;
-	u32 count;
-
-	lockdep_assert_held(&mchdev_lock);
-
-	now = ktime_get_raw_ns();
-	diffms = now - dev_priv->ips.last_time2;
-	do_div(diffms, NSEC_PER_MSEC);
-
-	/* Don't divide by 0 */
-	if (!diffms)
-		return;
-
-	count = I915_READ(GFXEC);
-
-	if (count < dev_priv->ips.last_count2) {
-		diff = ~0UL - dev_priv->ips.last_count2;
-		diff += count;
-	} else {
-		diff = count - dev_priv->ips.last_count2;
-	}
-
-	dev_priv->ips.last_count2 = count;
-	dev_priv->ips.last_time2 = now;
-
-	/* More magic constants... */
-	diff = diff * 1181;
-	diff = div_u64(diff, diffms * 10);
-	dev_priv->ips.gfx_power = diff;
-}
-
-void i915_update_gfx_val(struct drm_i915_private *dev_priv)
-{
-	intel_wakeref_t wakeref;
-
-	if (!IS_GEN(dev_priv, 5))
-		return;
-
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
-		spin_lock_irq(&mchdev_lock);
-		__i915_update_gfx_val(dev_priv);
-		spin_unlock_irq(&mchdev_lock);
-	}
-}
-
-static unsigned long __i915_gfx_val(struct drm_i915_private *dev_priv)
-{
-	unsigned long t, corr, state1, corr2, state2;
-	u32 pxvid, ext_v;
-
-	lockdep_assert_held(&mchdev_lock);
-
-	pxvid = I915_READ(PXVFREQ(dev_priv->gt_pm.rps.cur_freq));
-	pxvid = (pxvid >> 24) & 0x7f;
-	ext_v = pvid_to_extvid(dev_priv, pxvid);
-
-	state1 = ext_v;
-
-	t = i915_mch_val(dev_priv);
-
-	/* Revel in the empirically derived constants */
-
-	/* Correction factor in 1/100000 units */
-	if (t > 80)
-		corr = ((t * 2349) + 135940);
-	else if (t >= 50)
-		corr = ((t * 964) + 29317);
-	else /* < 50 */
-		corr = ((t * 301) + 1004);
-
-	corr = corr * ((150142 * state1) / 10000 - 78642);
-	corr /= 100000;
-	corr2 = (corr * dev_priv->ips.corr);
-
-	state2 = (corr2 * state1) / 10000;
-	state2 /= 100; /* convert to mW */
-
-	__i915_update_gfx_val(dev_priv);
-
-	return dev_priv->ips.gfx_power + state2;
-}
-
-unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
-{
-	intel_wakeref_t wakeref;
-	unsigned long val = 0;
-
-	if (!IS_GEN(dev_priv, 5))
-		return 0;
-
-	with_intel_runtime_pm(&dev_priv->runtime_pm, wakeref) {
-		spin_lock_irq(&mchdev_lock);
-		val = __i915_gfx_val(dev_priv);
-		spin_unlock_irq(&mchdev_lock);
-	}
-
-	return val;
-}
-
-static struct drm_i915_private __rcu *i915_mch_dev;
-
-static struct drm_i915_private *mchdev_get(void)
-{
-	struct drm_i915_private *i915;
-
-	rcu_read_lock();
-	i915 = rcu_dereference(i915_mch_dev);
-	if (!kref_get_unless_zero(&i915->drm.ref))
-		i915 = NULL;
-	rcu_read_unlock();
-
-	return i915;
-}
-
-/**
- * i915_read_mch_val - return value for IPS use
- *
- * Calculate and return a value for the IPS driver to use when deciding whether
- * we have thermal and power headroom to increase CPU or GPU power budget.
- */
-unsigned long i915_read_mch_val(void)
-{
-	struct drm_i915_private *i915;
-	unsigned long chipset_val = 0;
-	unsigned long graphics_val = 0;
-	intel_wakeref_t wakeref;
-
-	i915 = mchdev_get();
-	if (!i915)
-		return 0;
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
-		spin_lock_irq(&mchdev_lock);
-		chipset_val = __i915_chipset_val(i915);
-		graphics_val = __i915_gfx_val(i915);
-		spin_unlock_irq(&mchdev_lock);
-	}
-
-	drm_dev_put(&i915->drm);
-	return chipset_val + graphics_val;
-}
-EXPORT_SYMBOL_GPL(i915_read_mch_val);
-
-/**
- * i915_gpu_raise - raise GPU frequency limit
- *
- * Raise the limit; IPS indicates we have thermal headroom.
- */
-bool i915_gpu_raise(void)
-{
-	struct drm_i915_private *i915;
-
-	i915 = mchdev_get();
-	if (!i915)
-		return false;
-
-	spin_lock_irq(&mchdev_lock);
-	if (i915->ips.max_delay > i915->ips.fmax)
-		i915->ips.max_delay--;
-	spin_unlock_irq(&mchdev_lock);
-
-	drm_dev_put(&i915->drm);
-	return true;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_raise);
-
-/**
- * i915_gpu_lower - lower GPU frequency limit
- *
- * IPS indicates we're close to a thermal limit, so throttle back the GPU
- * frequency maximum.
- */
-bool i915_gpu_lower(void)
-{
-	struct drm_i915_private *i915;
-
-	i915 = mchdev_get();
-	if (!i915)
-		return false;
-
-	spin_lock_irq(&mchdev_lock);
-	if (i915->ips.max_delay < i915->ips.min_delay)
-		i915->ips.max_delay++;
-	spin_unlock_irq(&mchdev_lock);
-
-	drm_dev_put(&i915->drm);
-	return true;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_lower);
-
-/**
- * i915_gpu_busy - indicate GPU business to IPS
- *
- * Tell the IPS driver whether or not the GPU is busy.
- */
-bool i915_gpu_busy(void)
-{
-	struct drm_i915_private *i915;
-	bool ret;
-
-	i915 = mchdev_get();
-	if (!i915)
-		return false;
-
-	ret = i915->gt.awake;
-
-	drm_dev_put(&i915->drm);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_busy);
-
-/**
- * i915_gpu_turbo_disable - disable graphics turbo
- *
- * Disable graphics turbo by resetting the max frequency and setting the
- * current frequency to the default.
- */
-bool i915_gpu_turbo_disable(void)
-{
-	struct drm_i915_private *i915;
-	bool ret;
-
-	i915 = mchdev_get();
-	if (!i915)
-		return false;
-
-	spin_lock_irq(&mchdev_lock);
-	i915->ips.max_delay = i915->ips.fstart;
-	ret = ironlake_set_drps(i915, i915->ips.fstart);
-	spin_unlock_irq(&mchdev_lock);
-
-	drm_dev_put(&i915->drm);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
-
-/**
- * Tells the intel_ips driver that the i915 driver is now loaded, if
- * IPS got loaded first.
- *
- * This awkward dance is so that neither module has to depend on the
- * other in order for IPS to do the appropriate communication of
- * GPU turbo limits to i915.
- */
-static void
-ips_ping_for_i915_load(void)
-{
-	void (*link)(void);
-
-	link = symbol_get(ips_link_to_i915_driver);
-	if (link) {
-		link();
-		symbol_put(ips_link_to_i915_driver);
-	}
-}
-
-void intel_gpu_ips_init(struct drm_i915_private *dev_priv)
-{
-	/* We only register the i915 ips part with intel-ips once everything is
-	 * set up, to avoid intel-ips sneaking in and reading bogus values. */
-	rcu_assign_pointer(i915_mch_dev, dev_priv);
-
-	ips_ping_for_i915_load();
-}
-
-void intel_gpu_ips_teardown(void)
-{
-	rcu_assign_pointer(i915_mch_dev, NULL);
-}
-
-static void intel_init_emon(struct drm_i915_private *dev_priv)
-{
-	u32 lcfuse;
-	u8 pxw[16];
-	int i;
-
-	/* Disable to program */
-	I915_WRITE(ECR, 0);
-	POSTING_READ(ECR);
-
-	/* Program energy weights for various events */
-	I915_WRITE(SDEW, 0x15040d00);
-	I915_WRITE(CSIEW0, 0x007f0000);
-	I915_WRITE(CSIEW1, 0x1e220004);
-	I915_WRITE(CSIEW2, 0x04000004);
-
-	for (i = 0; i < 5; i++)
-		I915_WRITE(PEW(i), 0);
-	for (i = 0; i < 3; i++)
-		I915_WRITE(DEW(i), 0);
-
-	/* Program P-state weights to account for frequency power adjustment */
-	for (i = 0; i < 16; i++) {
-		u32 pxvidfreq = I915_READ(PXVFREQ(i));
-		unsigned long freq = intel_pxfreq(pxvidfreq);
-		unsigned long vid = (pxvidfreq & PXVFREQ_PX_MASK) >>
-			PXVFREQ_PX_SHIFT;
-		unsigned long val;
-
-		val = vid * vid;
-		val *= (freq / 1000);
-		val *= 255;
-		val /= (127*127*900);
-		if (val > 0xff)
-			DRM_ERROR("bad pxval: %ld\n", val);
-		pxw[i] = val;
-	}
-	/* Render standby states get 0 weight */
-	pxw[14] = 0;
-	pxw[15] = 0;
-
-	for (i = 0; i < 4; i++) {
-		u32 val = (pxw[i*4] << 24) | (pxw[(i*4)+1] << 16) |
-			(pxw[(i*4)+2] << 8) | (pxw[(i*4)+3]);
-		I915_WRITE(PXW(i), val);
-	}
-
-	/* Adjust magic regs to magic values (more experimental results) */
-	I915_WRITE(OGW0, 0);
-	I915_WRITE(OGW1, 0);
-	I915_WRITE(EG0, 0x00007f00);
-	I915_WRITE(EG1, 0x0000000e);
-	I915_WRITE(EG2, 0x000e0000);
-	I915_WRITE(EG3, 0x68000300);
-	I915_WRITE(EG4, 0x42000000);
-	I915_WRITE(EG5, 0x00140031);
-	I915_WRITE(EG6, 0);
-	I915_WRITE(EG7, 0);
-
-	for (i = 0; i < 8; i++)
-		I915_WRITE(PXWL(i), 0);
-
-	/* Enable PMON + select events */
-	I915_WRITE(ECR, 0x80000019);
-
-	lcfuse = I915_READ(LCFUSE02);
-
-	dev_priv->ips.corr = (lcfuse & LCFUSE_HIV_MASK);
-}
-
-void intel_init_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(dev_priv))
-		mkwrite_device_info(dev_priv)->has_rps = false;
-
-	/* Initialize RPS limits (for userspace) */
-	if (IS_CHERRYVIEW(dev_priv))
-		cherryview_init_gt_powersave(dev_priv);
-	else if (IS_VALLEYVIEW(dev_priv))
-		valleyview_init_gt_powersave(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		gen6_init_rps_frequencies(dev_priv);
-
-	/* Derive initial user preferences/limits from the hardware limits */
-	rps->max_freq_softlimit = rps->max_freq;
-	rps->min_freq_softlimit = rps->min_freq;
-
-	/* After setting max-softlimit, find the overclock max freq */
-	if (IS_GEN(dev_priv, 6) ||
-	    IS_IVYBRIDGE(dev_priv) || IS_HASWELL(dev_priv)) {
-		u32 params = 0;
-
-		sandybridge_pcode_read(dev_priv, GEN6_READ_OC_PARAMS,
-				       &params, NULL);
-		if (params & BIT(31)) { /* OC supported */
-			DRM_DEBUG_DRIVER("Overclocking supported, max: %dMHz, overclock: %dMHz\n",
-					 (rps->max_freq & 0xff) * 50,
-					 (params & 0xff) * 50);
-			rps->max_freq = params & 0xff;
-		}
-	}
-
-	/* Finally allow us to boost to max by default */
-	rps->boost_freq = rps->max_freq;
-	rps->idle_freq = rps->min_freq;
-	rps->cur_freq = rps->idle_freq;
-}
-
-void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	dev_priv->gt_pm.rps.enabled = true; /* force RPS disabling */
-	intel_disable_gt_powersave(dev_priv);
-
-	if (INTEL_GEN(dev_priv) >= 11)
-		gen11_reset_rps_interrupts(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		gen6_reset_rps_interrupts(dev_priv);
-}
-
-static void intel_disable_rps(struct drm_i915_private *dev_priv)
-{
-	lockdep_assert_held(&dev_priv->gt_pm.rps.lock);
-
-	if (!dev_priv->gt_pm.rps.enabled)
-		return;
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		gen9_disable_rps(dev_priv);
-	else if (IS_CHERRYVIEW(dev_priv))
-		cherryview_disable_rps(dev_priv);
-	else if (IS_VALLEYVIEW(dev_priv))
-		valleyview_disable_rps(dev_priv);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		gen6_disable_rps(dev_priv);
-	else if (IS_IRONLAKE_M(dev_priv))
-		ironlake_disable_drps(dev_priv);
-
-	dev_priv->gt_pm.rps.enabled = false;
-}
-
-void intel_disable_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	mutex_lock(&dev_priv->gt_pm.rps.lock);
-
-	intel_disable_rps(dev_priv);
-	if (HAS_LLC(dev_priv))
-		intel_llc_disable(&dev_priv->gt.llc);
-
-	mutex_unlock(&dev_priv->gt_pm.rps.lock);
-}
-
-static void intel_enable_rps(struct drm_i915_private *dev_priv)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	lockdep_assert_held(&rps->lock);
-
-	if (rps->enabled)
-		return;
-
-	if (IS_CHERRYVIEW(dev_priv)) {
-		cherryview_enable_rps(dev_priv);
-	} else if (IS_VALLEYVIEW(dev_priv)) {
-		valleyview_enable_rps(dev_priv);
-	} else if (INTEL_GEN(dev_priv) >= 9) {
-		gen9_enable_rps(dev_priv);
-	} else if (IS_BROADWELL(dev_priv)) {
-		gen8_enable_rps(dev_priv);
-	} else if (INTEL_GEN(dev_priv) >= 6) {
-		gen6_enable_rps(dev_priv);
-	} else if (IS_IRONLAKE_M(dev_priv)) {
-		ironlake_enable_drps(dev_priv);
-		intel_init_emon(dev_priv);
-	}
-
-	WARN_ON(rps->max_freq < rps->min_freq);
-	WARN_ON(rps->idle_freq > rps->max_freq);
-
-	WARN_ON(rps->efficient_freq < rps->min_freq);
-	WARN_ON(rps->efficient_freq > rps->max_freq);
-
-	rps->enabled = true;
-}
-
-void intel_enable_gt_powersave(struct drm_i915_private *dev_priv)
-{
-	/* Powersaving is controlled by the host when inside a VM */
-	if (intel_vgpu_active(dev_priv))
-		return;
-
-	mutex_lock(&dev_priv->gt_pm.rps.lock);
-
-	if (HAS_RPS(dev_priv))
-		intel_enable_rps(dev_priv);
-
-	intel_llc_enable(&dev_priv->gt.llc);
-
-	mutex_unlock(&dev_priv->gt_pm.rps.lock);
-}
-
 static void ibx_init_clock_gating(struct drm_i915_private *dev_priv)
 {
 	/*
@@ -8942,90 +7232,8 @@ void intel_init_pm(struct drm_i915_private *dev_priv)
 	}
 }
 
-static int byt_gpu_freq(struct drm_i915_private *dev_priv, int val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/*
-	 * N = val - 0xb7
-	 * Slow = Fast = GPLL ref * N
-	 */
-	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * (val - 0xb7), 1000);
-}
-
-static int byt_freq_opcode(struct drm_i915_private *dev_priv, int val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	return DIV_ROUND_CLOSEST(1000 * val, rps->gpll_ref_freq) + 0xb7;
-}
-
-static int chv_gpu_freq(struct drm_i915_private *dev_priv, int val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/*
-	 * N = val / 2
-	 * CU (slow) = CU2x (fast) / 2 = GPLL ref * N / 2
-	 */
-	return DIV_ROUND_CLOSEST(rps->gpll_ref_freq * val, 2 * 2 * 1000);
-}
-
-static int chv_freq_opcode(struct drm_i915_private *dev_priv, int val)
-{
-	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-
-	/* CHV needs even values */
-	return DIV_ROUND_CLOSEST(2 * 1000 * val, rps->gpll_ref_freq) * 2;
-}
-
-int intel_gpu_freq(struct drm_i915_private *dev_priv, int val)
-{
-	if (INTEL_GEN(dev_priv) >= 9)
-		return DIV_ROUND_CLOSEST(val * GT_FREQUENCY_MULTIPLIER,
-					 GEN9_FREQ_SCALER);
-	else if (IS_CHERRYVIEW(dev_priv))
-		return chv_gpu_freq(dev_priv, val);
-	else if (IS_VALLEYVIEW(dev_priv))
-		return byt_gpu_freq(dev_priv, val);
-	else
-		return val * GT_FREQUENCY_MULTIPLIER;
-}
-
-int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
-{
-	if (INTEL_GEN(dev_priv) >= 9)
-		return DIV_ROUND_CLOSEST(val * GEN9_FREQ_SCALER,
-					 GT_FREQUENCY_MULTIPLIER);
-	else if (IS_CHERRYVIEW(dev_priv))
-		return chv_freq_opcode(dev_priv, val);
-	else if (IS_VALLEYVIEW(dev_priv))
-		return byt_freq_opcode(dev_priv, val);
-	else
-		return DIV_ROUND_CLOSEST(val, GT_FREQUENCY_MULTIPLIER);
-}
-
 void intel_pm_setup(struct drm_i915_private *dev_priv)
 {
-	mutex_init(&dev_priv->gt_pm.rps.lock);
-	mutex_init(&dev_priv->gt_pm.rps.power.mutex);
-
-	atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0);
-
 	dev_priv->runtime_pm.suspended = false;
 	atomic_set(&dev_priv->runtime_pm.wakeref_count, 0);
 }
-
-u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat)
-{
-	u32 cagf;
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
-	else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-		cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
-	else
-		cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
-
-	return  cagf;
-}
diff --git a/drivers/gpu/drm/i915/intel_pm.h b/drivers/gpu/drm/i915/intel_pm.h
index 93d192d0610a..b579c724b915 100644
--- a/drivers/gpu/drm/i915/intel_pm.h
+++ b/drivers/gpu/drm/i915/intel_pm.h
@@ -29,15 +29,6 @@ void intel_update_watermarks(struct intel_crtc *crtc);
 void intel_init_pm(struct drm_i915_private *dev_priv);
 void intel_init_clock_gating_hooks(struct drm_i915_private *dev_priv);
 void intel_pm_setup(struct drm_i915_private *dev_priv);
-void intel_gpu_ips_init(struct drm_i915_private *dev_priv);
-void intel_gpu_ips_teardown(void);
-void intel_init_gt_powersave(struct drm_i915_private *dev_priv);
-void intel_sanitize_gt_powersave(struct drm_i915_private *dev_priv);
-void intel_enable_gt_powersave(struct drm_i915_private *dev_priv);
-void intel_disable_gt_powersave(struct drm_i915_private *dev_priv);
-void gen6_rps_busy(struct drm_i915_private *dev_priv);
-void gen6_rps_idle(struct drm_i915_private *dev_priv);
-void gen6_rps_boost(struct i915_request *rq);
 void g4x_wm_get_hw_state(struct drm_i915_private *dev_priv);
 void vlv_wm_get_hw_state(struct drm_i915_private *dev_priv);
 void ilk_wm_get_hw_state(struct drm_i915_private *dev_priv);
@@ -64,24 +55,9 @@ void skl_write_plane_wm(struct intel_plane *plane,
 void skl_write_cursor_wm(struct intel_plane *plane,
 			 const struct intel_crtc_state *crtc_state);
 bool ilk_disable_lp_wm(struct drm_device *dev);
-int skl_check_pipe_max_pixel_rate(struct intel_crtc *intel_crtc,
-				  struct intel_crtc_state *cstate);
 void intel_init_ipc(struct drm_i915_private *dev_priv);
 void intel_enable_ipc(struct drm_i915_private *dev_priv);
 
-int intel_gpu_freq(struct drm_i915_private *dev_priv, int val);
-int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
-
-u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat1);
-
-unsigned long i915_chipset_val(struct drm_i915_private *dev_priv);
-unsigned long i915_mch_val(struct drm_i915_private *dev_priv);
-unsigned long i915_gfx_val(struct drm_i915_private *dev_priv);
-void i915_update_gfx_val(struct drm_i915_private *dev_priv);
-
-bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val);
-int intel_set_rps(struct drm_i915_private *dev_priv, u8 val);
-void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive);
 bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv, bool enable);
 
 #endif /* __INTEL_PM_H__ */
diff --git a/drivers/gpu/drm/i915/intel_region_lmem.c b/drivers/gpu/drm/i915/intel_region_lmem.c
new file mode 100644
index 000000000000..583118095635
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_region_lmem.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "intel_memory_region.h"
+#include "gem/i915_gem_lmem.h"
+#include "gem/i915_gem_region.h"
+#include "intel_region_lmem.h"
+
+static int init_fake_lmem_bar(struct intel_memory_region *mem)
+{
+	struct drm_i915_private *i915 = mem->i915;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	unsigned long n;
+	int ret;
+
+	/* We want to 1:1 map the mappable aperture to our reserved region */
+
+	mem->fake_mappable.start = 0;
+	mem->fake_mappable.size = resource_size(&mem->region);
+	mem->fake_mappable.color = I915_COLOR_UNEVICTABLE;
+
+	ret = drm_mm_reserve_node(&ggtt->vm.mm, &mem->fake_mappable);
+	if (ret)
+		return ret;
+
+	mem->remap_addr = dma_map_resource(&i915->drm.pdev->dev,
+					   mem->region.start,
+					   mem->fake_mappable.size,
+					   PCI_DMA_BIDIRECTIONAL,
+					   DMA_ATTR_FORCE_CONTIGUOUS);
+	if (dma_mapping_error(&i915->drm.pdev->dev, mem->remap_addr)) {
+		drm_mm_remove_node(&mem->fake_mappable);
+		return -EINVAL;
+	}
+
+	for (n = 0; n < mem->fake_mappable.size >> PAGE_SHIFT; ++n) {
+		ggtt->vm.insert_page(&ggtt->vm,
+				     mem->remap_addr + (n << PAGE_SHIFT),
+				     n << PAGE_SHIFT,
+				     I915_CACHE_NONE, 0);
+	}
+
+	mem->region = (struct resource)DEFINE_RES_MEM(mem->remap_addr,
+						      mem->fake_mappable.size);
+
+	return 0;
+}
+
+static void release_fake_lmem_bar(struct intel_memory_region *mem)
+{
+	if (drm_mm_node_allocated(&mem->fake_mappable))
+		drm_mm_remove_node(&mem->fake_mappable);
+
+	dma_unmap_resource(&mem->i915->drm.pdev->dev,
+			   mem->remap_addr,
+			   mem->fake_mappable.size,
+			   PCI_DMA_BIDIRECTIONAL,
+			   DMA_ATTR_FORCE_CONTIGUOUS);
+}
+
+static void
+region_lmem_release(struct intel_memory_region *mem)
+{
+	release_fake_lmem_bar(mem);
+	io_mapping_fini(&mem->iomap);
+	intel_memory_region_release_buddy(mem);
+}
+
+static int
+region_lmem_init(struct intel_memory_region *mem)
+{
+	int ret;
+
+	if (i915_modparams.fake_lmem_start) {
+		ret = init_fake_lmem_bar(mem);
+		GEM_BUG_ON(ret);
+	}
+
+	if (!io_mapping_init_wc(&mem->iomap,
+				mem->io_start,
+				resource_size(&mem->region)))
+		return -EIO;
+
+	ret = intel_memory_region_init_buddy(mem);
+	if (ret)
+		io_mapping_fini(&mem->iomap);
+
+	return ret;
+}
+
+const struct intel_memory_region_ops intel_region_lmem_ops = {
+	.init = region_lmem_init,
+	.release = region_lmem_release,
+	.create_object = __i915_gem_lmem_object_create,
+};
+
+struct intel_memory_region *
+intel_setup_fake_lmem(struct drm_i915_private *i915)
+{
+	struct pci_dev *pdev = i915->drm.pdev;
+	struct intel_memory_region *mem;
+	resource_size_t mappable_end;
+	resource_size_t io_start;
+	resource_size_t start;
+
+	GEM_BUG_ON(i915_ggtt_has_aperture(&i915->ggtt));
+	GEM_BUG_ON(!i915_modparams.fake_lmem_start);
+
+	/* Your mappable aperture belongs to me now! */
+	mappable_end = pci_resource_len(pdev, 2);
+	io_start = pci_resource_start(pdev, 2),
+	start = i915_modparams.fake_lmem_start;
+
+	mem = intel_memory_region_create(i915,
+					 start,
+					 mappable_end,
+					 PAGE_SIZE,
+					 io_start,
+					 &intel_region_lmem_ops);
+	if (!IS_ERR(mem)) {
+		DRM_INFO("Intel graphics fake LMEM: %pR\n", &mem->region);
+		DRM_INFO("Intel graphics fake LMEM IO start: %llx\n",
+			 (u64)mem->io_start);
+		DRM_INFO("Intel graphics fake LMEM size: %llx\n",
+			 (u64)resource_size(&mem->region));
+	}
+
+	return mem;
+}
diff --git a/drivers/gpu/drm/i915/intel_region_lmem.h b/drivers/gpu/drm/i915/intel_region_lmem.h
new file mode 100644
index 000000000000..213def7c7b8a
--- /dev/null
+++ b/drivers/gpu/drm/i915/intel_region_lmem.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2019 Intel Corporation
+ */
+
+#ifndef __INTEL_REGION_LMEM_H
+#define __INTEL_REGION_LMEM_H
+
+struct drm_i915_private;
+
+extern const struct intel_memory_region_ops intel_region_lmem_ops;
+
+struct intel_memory_region *
+intel_setup_fake_lmem(struct drm_i915_private *i915);
+
+#endif /* !__INTEL_REGION_LMEM_H */
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 868cc78048d0..59aa1b6f1827 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -54,7 +54,8 @@ int __intel_wakeref_get_first(struct intel_wakeref *wf)
 
 static void ____intel_wakeref_put_last(struct intel_wakeref *wf)
 {
-	if (!atomic_dec_and_test(&wf->count))
+	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
+	if (unlikely(!atomic_dec_and_test(&wf->count)))
 		goto unlock;
 
 	/* ops->put() must reschedule its own release on error/deferral */
@@ -67,13 +68,12 @@ unlock:
 	mutex_unlock(&wf->mutex);
 }
 
-void __intel_wakeref_put_last(struct intel_wakeref *wf)
+void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags)
 {
 	INTEL_WAKEREF_BUG_ON(work_pending(&wf->work));
 
 	/* Assume we are not in process context and so cannot sleep. */
-	if (wf->ops->flags & INTEL_WAKEREF_PUT_ASYNC ||
-	    !mutex_trylock(&wf->mutex)) {
+	if (flags & INTEL_WAKEREF_PUT_ASYNC || !mutex_trylock(&wf->mutex)) {
 		schedule_work(&wf->work);
 		return;
 	}
@@ -109,8 +109,17 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 
 int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
 {
-	return wait_var_event_killable(&wf->wakeref,
-				       !intel_wakeref_is_active(wf));
+	int err;
+
+	might_sleep();
+
+	err = wait_var_event_killable(&wf->wakeref,
+				      !intel_wakeref_is_active(wf));
+	if (err)
+		return err;
+
+	intel_wakeref_unlock_wait(wf);
+	return 0;
 }
 
 static void wakeref_auto_timeout(struct timer_list *t)
diff --git a/drivers/gpu/drm/i915/intel_wakeref.h b/drivers/gpu/drm/i915/intel_wakeref.h
index 5f0c972a80fb..da6e8fd506e6 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.h
+++ b/drivers/gpu/drm/i915/intel_wakeref.h
@@ -9,6 +9,7 @@
 
 #include <linux/atomic.h>
 #include <linux/bits.h>
+#include <linux/lockdep.h>
 #include <linux/mutex.h>
 #include <linux/refcount.h>
 #include <linux/stackdepot.h>
@@ -29,9 +30,6 @@ typedef depot_stack_handle_t intel_wakeref_t;
 struct intel_wakeref_ops {
 	int (*get)(struct intel_wakeref *wf);
 	int (*put)(struct intel_wakeref *wf);
-
-	unsigned long flags;
-#define INTEL_WAKEREF_PUT_ASYNC BIT(0)
 };
 
 struct intel_wakeref {
@@ -57,7 +55,7 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 } while (0)
 
 int __intel_wakeref_get_first(struct intel_wakeref *wf);
-void __intel_wakeref_put_last(struct intel_wakeref *wf);
+void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags);
 
 /**
  * intel_wakeref_get: Acquire the wakeref
@@ -100,10 +98,9 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf)
 }
 
 /**
- * intel_wakeref_put: Release the wakeref
- * @i915: the drm_i915_private device
+ * intel_wakeref_put_flags: Release the wakeref
  * @wf: the wakeref
- * @fn: callback for releasing the wakeref, called only on final release.
+ * @flags: control flags
  *
  * Release our hold on the wakeref. When there are no more users,
  * the runtime pm wakeref will be released after the @fn callback is called
@@ -116,11 +113,25 @@ intel_wakeref_get_if_active(struct intel_wakeref *wf)
  * code otherwise.
  */
 static inline void
-intel_wakeref_put(struct intel_wakeref *wf)
+__intel_wakeref_put(struct intel_wakeref *wf, unsigned long flags)
+#define INTEL_WAKEREF_PUT_ASYNC BIT(0)
 {
 	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
 	if (unlikely(!atomic_add_unless(&wf->count, -1, 1)))
-		__intel_wakeref_put_last(wf);
+		__intel_wakeref_put_last(wf, flags);
+}
+
+static inline void
+intel_wakeref_put(struct intel_wakeref *wf)
+{
+	might_sleep();
+	__intel_wakeref_put(wf, 0);
+}
+
+static inline void
+intel_wakeref_put_async(struct intel_wakeref *wf)
+{
+	__intel_wakeref_put(wf, INTEL_WAKEREF_PUT_ASYNC);
 }
 
 /**
@@ -152,6 +163,21 @@ intel_wakeref_unlock(struct intel_wakeref *wf)
 }
 
 /**
+ * intel_wakeref_unlock_wait: Wait until the active callback is complete
+ * @wf: the wakeref
+ *
+ * Waits for the active callback (under the @wf->mutex or another CPU) is
+ * complete.
+ */
+static inline void
+intel_wakeref_unlock_wait(struct intel_wakeref *wf)
+{
+	mutex_lock(&wf->mutex);
+	mutex_unlock(&wf->mutex);
+	flush_work(&wf->work);
+}
+
+/**
  * intel_wakeref_is_active: Query whether the wakeref is currently held
  * @wf: the wakeref
  *
@@ -170,6 +196,7 @@ intel_wakeref_is_active(const struct intel_wakeref *wf)
 static inline void
 __intel_wakeref_defer_park(struct intel_wakeref *wf)
 {
+	lockdep_assert_held(&wf->mutex);
 	INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count));
 	atomic_set_release(&wf->count, 1);
 }
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_tgl.c b/drivers/gpu/drm/i915/oa/i915_oa_tgl.c
new file mode 100644
index 000000000000..a29d93707345
--- /dev/null
+++ b/drivers/gpu/drm/i915/oa/i915_oa_tgl.c
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2018 Intel Corporation
+ *
+ * Autogenerated file by GPU Top : https://github.com/rib/gputop
+ * DO NOT EDIT manually!
+ */
+
+#include <linux/sysfs.h>
+
+#include "i915_drv.h"
+#include "i915_oa_tgl.h"
+
+static const struct i915_oa_reg b_counter_config_test_oa[] = {
+	{ _MMIO(0xD920), 0x00000000 },
+	{ _MMIO(0xD900), 0x00000000 },
+	{ _MMIO(0xD904), 0xF0800000 },
+	{ _MMIO(0xD910), 0x00000000 },
+	{ _MMIO(0xD914), 0xF0800000 },
+	{ _MMIO(0xDC40), 0x00FF0000 },
+	{ _MMIO(0xD940), 0x00000004 },
+	{ _MMIO(0xD944), 0x0000FFFF },
+	{ _MMIO(0xDC00), 0x00000004 },
+	{ _MMIO(0xDC04), 0x0000FFFF },
+	{ _MMIO(0xD948), 0x00000003 },
+	{ _MMIO(0xD94C), 0x0000FFFF },
+	{ _MMIO(0xDC08), 0x00000003 },
+	{ _MMIO(0xDC0C), 0x0000FFFF },
+	{ _MMIO(0xD950), 0x00000007 },
+	{ _MMIO(0xD954), 0x0000FFFF },
+	{ _MMIO(0xDC10), 0x00000007 },
+	{ _MMIO(0xDC14), 0x0000FFFF },
+	{ _MMIO(0xD958), 0x00100002 },
+	{ _MMIO(0xD95C), 0x0000FFF7 },
+	{ _MMIO(0xDC18), 0x00100002 },
+	{ _MMIO(0xDC1C), 0x0000FFF7 },
+	{ _MMIO(0xD960), 0x00100002 },
+	{ _MMIO(0xD964), 0x0000FFCF },
+	{ _MMIO(0xDC20), 0x00100002 },
+	{ _MMIO(0xDC24), 0x0000FFCF },
+	{ _MMIO(0xD968), 0x00100082 },
+	{ _MMIO(0xD96C), 0x0000FFEF },
+	{ _MMIO(0xDC28), 0x00100082 },
+	{ _MMIO(0xDC2C), 0x0000FFEF },
+	{ _MMIO(0xD970), 0x001000C2 },
+	{ _MMIO(0xD974), 0x0000FFE7 },
+	{ _MMIO(0xDC30), 0x001000C2 },
+	{ _MMIO(0xDC34), 0x0000FFE7 },
+	{ _MMIO(0xD978), 0x00100001 },
+	{ _MMIO(0xD97C), 0x0000FFE7 },
+	{ _MMIO(0xDC38), 0x00100001 },
+	{ _MMIO(0xDC3C), 0x0000FFE7 },
+};
+
+static const struct i915_oa_reg flex_eu_config_test_oa[] = {
+};
+
+static const struct i915_oa_reg mux_config_test_oa[] = {
+	{ _MMIO(0x0D04), 0x00000200 },
+	{ _MMIO(0x9840), 0x00000000 },
+	{ _MMIO(0x9884), 0x00000000 },
+	{ _MMIO(0x9888), 0x280E0000 },
+	{ _MMIO(0x9888), 0x1E0E0147 },
+	{ _MMIO(0x9888), 0x180E0000 },
+	{ _MMIO(0x9888), 0x160E0000 },
+	{ _MMIO(0x9888), 0x1E0F1000 },
+	{ _MMIO(0x9888), 0x1E104000 },
+	{ _MMIO(0x9888), 0x2E020100 },
+	{ _MMIO(0x9888), 0x2C030004 },
+	{ _MMIO(0x9888), 0x38003000 },
+	{ _MMIO(0x9888), 0x1E0A8000 },
+	{ _MMIO(0x9884), 0x00000003 },
+	{ _MMIO(0x9888), 0x49110000 },
+	{ _MMIO(0x9888), 0x5D101400 },
+	{ _MMIO(0x9888), 0x1D140020 },
+	{ _MMIO(0x9888), 0x1D1103A3 },
+	{ _MMIO(0x9888), 0x01110000 },
+	{ _MMIO(0x9888), 0x61111000 },
+	{ _MMIO(0x9888), 0x1F128000 },
+	{ _MMIO(0x9888), 0x17100000 },
+	{ _MMIO(0x9888), 0x55100630 },
+	{ _MMIO(0x9888), 0x57100000 },
+	{ _MMIO(0x9888), 0x31100000 },
+	{ _MMIO(0x9884), 0x00000003 },
+	{ _MMIO(0x9888), 0x65100002 },
+	{ _MMIO(0x9884), 0x00000000 },
+	{ _MMIO(0x9888), 0x42000001 },
+};
+
+static ssize_t
+show_test_oa_id(struct device *kdev, struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "1\n");
+}
+
+void
+i915_perf_load_test_config_tgl(struct drm_i915_private *dev_priv)
+{
+	strlcpy(dev_priv->perf.test_config.uuid,
+		"80a833f0-2504-4321-8894-e9277844ce7b",
+		sizeof(dev_priv->perf.test_config.uuid));
+	dev_priv->perf.test_config.id = 1;
+
+	dev_priv->perf.test_config.mux_regs = mux_config_test_oa;
+	dev_priv->perf.test_config.mux_regs_len = ARRAY_SIZE(mux_config_test_oa);
+
+	dev_priv->perf.test_config.b_counter_regs = b_counter_config_test_oa;
+	dev_priv->perf.test_config.b_counter_regs_len = ARRAY_SIZE(b_counter_config_test_oa);
+
+	dev_priv->perf.test_config.flex_regs = flex_eu_config_test_oa;
+	dev_priv->perf.test_config.flex_regs_len = ARRAY_SIZE(flex_eu_config_test_oa);
+
+	dev_priv->perf.test_config.sysfs_metric.name = "80a833f0-2504-4321-8894-e9277844ce7b";
+	dev_priv->perf.test_config.sysfs_metric.attrs = dev_priv->perf.test_config.attrs;
+
+	dev_priv->perf.test_config.attrs[0] = &dev_priv->perf.test_config.sysfs_metric_id.attr;
+
+	dev_priv->perf.test_config.sysfs_metric_id.attr.name = "id";
+	dev_priv->perf.test_config.sysfs_metric_id.attr.mode = 0444;
+	dev_priv->perf.test_config.sysfs_metric_id.show = show_test_oa_id;
+}
diff --git a/drivers/gpu/drm/i915/oa/i915_oa_tgl.h b/drivers/gpu/drm/i915/oa/i915_oa_tgl.h
new file mode 100644
index 000000000000..4c25f0be825c
--- /dev/null
+++ b/drivers/gpu/drm/i915/oa/i915_oa_tgl.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2018 Intel Corporation
+ *
+ * Autogenerated file by GPU Top : https://github.com/rib/gputop
+ * DO NOT EDIT manually!
+ */
+
+#ifndef __I915_OA_TGL_H__
+#define __I915_OA_TGL_H__
+
+struct drm_i915_private;
+
+void i915_perf_load_test_config_tgl(struct drm_i915_private *dev_priv);
+
+#endif
diff --git a/drivers/gpu/drm/i915/selftests/i915_active.c b/drivers/gpu/drm/i915/selftests/i915_active.c
index 268192b5613b..260b0ee5d1e3 100644
--- a/drivers/gpu/drm/i915/selftests/i915_active.c
+++ b/drivers/gpu/drm/i915/selftests/i915_active.c
@@ -79,7 +79,6 @@ __live_active_setup(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	struct i915_sw_fence *submit;
 	struct live_active *active;
-	enum intel_engine_id id;
 	unsigned int count = 0;
 	int err = 0;
 
@@ -97,7 +96,7 @@ __live_active_setup(struct drm_i915_private *i915)
 	if (err)
 		goto out;
 
-	for_each_engine(engine, i915, id) {
+	for_each_uabi_engine(engine, i915) {
 		struct i915_request *rq;
 
 		rq = i915_request_create(engine->kernel_context);
@@ -206,3 +205,48 @@ int i915_active_live_selftests(struct drm_i915_private *i915)
 
 	return i915_subtests(tests, i915);
 }
+
+static struct intel_engine_cs *node_to_barrier(struct active_node *it)
+{
+	struct intel_engine_cs *engine;
+
+	if (!is_barrier(&it->base))
+		return NULL;
+
+	engine = __barrier_to_engine(it);
+	smp_rmb(); /* serialise with add_active_barriers */
+	if (!is_barrier(&it->base))
+		return NULL;
+
+	return engine;
+}
+
+void i915_active_print(struct i915_active *ref, struct drm_printer *m)
+{
+	drm_printf(m, "active %pS:%pS\n", ref->active, ref->retire);
+	drm_printf(m, "\tcount: %d\n", atomic_read(&ref->count));
+	drm_printf(m, "\tpreallocated barriers? %s\n",
+		   yesno(!llist_empty(&ref->preallocated_barriers)));
+
+	if (i915_active_acquire_if_busy(ref)) {
+		struct active_node *it, *n;
+
+		rbtree_postorder_for_each_entry_safe(it, n, &ref->tree, node) {
+			struct intel_engine_cs *engine;
+
+			engine = node_to_barrier(it);
+			if (engine) {
+				drm_printf(m, "\tbarrier: %s\n", engine->name);
+				continue;
+			}
+
+			if (i915_active_fence_isset(&it->base)) {
+				drm_printf(m,
+					   "\ttimeline: %llx\n", it->timeline);
+				continue;
+			}
+		}
+
+		i915_active_release(ref);
+	}
+}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem.c b/drivers/gpu/drm/i915/selftests/i915_gem.c
index 97f89f744ee2..d83f6bf6d9d4 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem.c
@@ -15,23 +15,26 @@
 #include "igt_flush_test.h"
 #include "mock_drm.h"
 
-static int switch_to_context(struct drm_i915_private *i915,
-			     struct i915_gem_context *ctx)
+static int switch_to_context(struct i915_gem_context *ctx)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	struct i915_gem_engines_iter it;
+	struct intel_context *ce;
+	int err = 0;
 
-	for_each_engine(engine, i915, id) {
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
 		struct i915_request *rq;
 
-		rq = igt_request_alloc(ctx, engine);
-		if (IS_ERR(rq))
-			return PTR_ERR(rq);
+		rq = intel_context_create_request(ce);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			break;
+		}
 
 		i915_request_add(rq);
 	}
+	i915_gem_context_unlock_engines(ctx);
 
-	return 0;
+	return err;
 }
 
 static void trash_stolen(struct drm_i915_private *i915)
@@ -42,6 +45,10 @@ static void trash_stolen(struct drm_i915_private *i915)
 	unsigned long page;
 	u32 prng = 0x12345678;
 
+	/* XXX: fsck. needs some more thought... */
+	if (!i915_ggtt_has_aperture(ggtt))
+		return;
+
 	for (page = 0; page < size; page += PAGE_SIZE) {
 		const dma_addr_t dma = i915->dsm.start + page;
 		u32 __iomem *s;
@@ -117,7 +124,6 @@ static void pm_resume(struct drm_i915_private *i915)
 	 */
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref) {
 		intel_gt_sanitize(&i915->gt, false);
-		i915_gem_sanitize(i915);
 
 		i915_gem_restore_gtt_mappings(i915);
 		i915_gem_restore_fences(&i915->ggtt);
@@ -140,7 +146,7 @@ static int igt_gem_suspend(void *arg)
 	err = -ENOMEM;
 	ctx = live_context(i915, file);
 	if (!IS_ERR(ctx))
-		err = switch_to_context(i915, ctx);
+		err = switch_to_context(ctx);
 	if (err)
 		goto out;
 
@@ -155,7 +161,7 @@ static int igt_gem_suspend(void *arg)
 
 	pm_resume(i915);
 
-	err = switch_to_context(i915, ctx);
+	err = switch_to_context(ctx);
 out:
 	mock_file_free(i915, file);
 	return err;
@@ -175,7 +181,7 @@ static int igt_gem_hibernate(void *arg)
 	err = -ENOMEM;
 	ctx = live_context(i915, file);
 	if (!IS_ERR(ctx))
-		err = switch_to_context(i915, ctx);
+		err = switch_to_context(ctx);
 	if (err)
 		goto out;
 
@@ -190,7 +196,7 @@ static int igt_gem_hibernate(void *arg)
 
 	pm_resume(i915);
 
-	err = switch_to_context(i915, ctx);
+	err = switch_to_context(ctx);
 out:
 	mock_file_free(i915, file);
 	return err;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 0af9a58d011d..42e948144f1b 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -43,8 +43,7 @@ static void quirk_add(struct drm_i915_gem_object *obj,
 	list_add(&obj->st_link, objects);
 }
 
-static int populate_ggtt(struct drm_i915_private *i915,
-			 struct list_head *objects)
+static int populate_ggtt(struct i915_ggtt *ggtt, struct list_head *objects)
 {
 	unsigned long unbound, bound, count;
 	struct drm_i915_gem_object *obj;
@@ -53,7 +52,8 @@ static int populate_ggtt(struct drm_i915_private *i915,
 	do {
 		struct i915_vma *vma;
 
-		obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
+		obj = i915_gem_object_create_internal(ggtt->vm.i915,
+						      I915_GTT_PAGE_SIZE);
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
@@ -70,7 +70,7 @@ static int populate_ggtt(struct drm_i915_private *i915,
 		count++;
 	} while (1);
 	pr_debug("Filled GGTT with %lu pages [%llu total]\n",
-		 count, i915->ggtt.vm.total / PAGE_SIZE);
+		 count, ggtt->vm.total / PAGE_SIZE);
 
 	bound = 0;
 	unbound = 0;
@@ -96,7 +96,7 @@ static int populate_ggtt(struct drm_i915_private *i915,
 		return -EINVAL;
 	}
 
-	if (list_empty(&i915->ggtt.vm.bound_list)) {
+	if (list_empty(&ggtt->vm.bound_list)) {
 		pr_err("No objects on the GGTT inactive list!\n");
 		return -EINVAL;
 	}
@@ -104,17 +104,16 @@ static int populate_ggtt(struct drm_i915_private *i915,
 	return 0;
 }
 
-static void unpin_ggtt(struct drm_i915_private *i915)
+static void unpin_ggtt(struct i915_ggtt *ggtt)
 {
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &i915->ggtt.vm.bound_list, vm_link)
+	list_for_each_entry(vma, &ggtt->vm.bound_list, vm_link)
 		if (vma->obj->mm.quirked)
 			i915_vma_unpin(vma);
 }
 
-static void cleanup_objects(struct drm_i915_private *i915,
-			    struct list_head *list)
+static void cleanup_objects(struct i915_ggtt *ggtt, struct list_head *list)
 {
 	struct drm_i915_gem_object *obj, *on;
 
@@ -124,19 +123,19 @@ static void cleanup_objects(struct drm_i915_private *i915,
 		i915_gem_object_put(obj);
 	}
 
-	i915_gem_drain_freed_objects(i915);
+	i915_gem_drain_freed_objects(ggtt->vm.i915);
 }
 
 static int igt_evict_something(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	LIST_HEAD(objects);
 	int err;
 
 	/* Fill the GGTT with pinned objects and try to evict one. */
 
-	err = populate_ggtt(i915, &objects);
+	err = populate_ggtt(ggtt, &objects);
 	if (err)
 		goto cleanup;
 
@@ -153,7 +152,7 @@ static int igt_evict_something(void *arg)
 		goto cleanup;
 	}
 
-	unpin_ggtt(i915);
+	unpin_ggtt(ggtt);
 
 	/* Everything is unpinned, we should be able to evict something */
 	mutex_lock(&ggtt->vm.mutex);
@@ -169,13 +168,14 @@ static int igt_evict_something(void *arg)
 	}
 
 cleanup:
-	cleanup_objects(i915, &objects);
+	cleanup_objects(ggtt, &objects);
 	return err;
 }
 
 static int igt_overcommit(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	LIST_HEAD(objects);
@@ -185,11 +185,11 @@ static int igt_overcommit(void *arg)
 	 * We expect it to fail.
 	 */
 
-	err = populate_ggtt(i915, &objects);
+	err = populate_ggtt(ggtt, &objects);
 	if (err)
 		goto cleanup;
 
-	obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
+	obj = i915_gem_object_create_internal(gt->i915, I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto cleanup;
@@ -205,14 +205,14 @@ static int igt_overcommit(void *arg)
 	}
 
 cleanup:
-	cleanup_objects(i915, &objects);
+	cleanup_objects(ggtt, &objects);
 	return err;
 }
 
 static int igt_evict_for_vma(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	struct drm_mm_node target = {
 		.start = 0,
 		.size = 4096,
@@ -222,7 +222,7 @@ static int igt_evict_for_vma(void *arg)
 
 	/* Fill the GGTT with pinned objects and try to evict a range. */
 
-	err = populate_ggtt(i915, &objects);
+	err = populate_ggtt(ggtt, &objects);
 	if (err)
 		goto cleanup;
 
@@ -236,7 +236,7 @@ static int igt_evict_for_vma(void *arg)
 		goto cleanup;
 	}
 
-	unpin_ggtt(i915);
+	unpin_ggtt(ggtt);
 
 	/* Everything is unpinned, we should be able to evict the node */
 	mutex_lock(&ggtt->vm.mutex);
@@ -249,7 +249,7 @@ static int igt_evict_for_vma(void *arg)
 	}
 
 cleanup:
-	cleanup_objects(i915, &objects);
+	cleanup_objects(ggtt, &objects);
 	return err;
 }
 
@@ -262,8 +262,8 @@ static void mock_color_adjust(const struct drm_mm_node *node,
 
 static int igt_evict_for_cache_color(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	const unsigned long flags = PIN_OFFSET_FIXED;
 	struct drm_mm_node target = {
 		.start = I915_GTT_PAGE_SIZE * 2,
@@ -284,7 +284,7 @@ static int igt_evict_for_cache_color(void *arg)
 	ggtt->vm.mm.color_adjust = mock_color_adjust;
 	GEM_BUG_ON(!i915_vm_has_cache_coloring(&ggtt->vm));
 
-	obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
+	obj = i915_gem_object_create_internal(gt->i915, I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto cleanup;
@@ -300,7 +300,7 @@ static int igt_evict_for_cache_color(void *arg)
 		goto cleanup;
 	}
 
-	obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
+	obj = i915_gem_object_create_internal(gt->i915, I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
 		goto cleanup;
@@ -345,22 +345,22 @@ static int igt_evict_for_cache_color(void *arg)
 	err = 0;
 
 cleanup:
-	unpin_ggtt(i915);
-	cleanup_objects(i915, &objects);
+	unpin_ggtt(ggtt);
+	cleanup_objects(ggtt, &objects);
 	ggtt->vm.mm.color_adjust = NULL;
 	return err;
 }
 
 static int igt_evict_vm(void *arg)
 {
-	struct drm_i915_private *i915 = arg;
-	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
 	LIST_HEAD(objects);
 	int err;
 
 	/* Fill the GGTT with pinned objects and try to evict everything. */
 
-	err = populate_ggtt(i915, &objects);
+	err = populate_ggtt(ggtt, &objects);
 	if (err)
 		goto cleanup;
 
@@ -374,7 +374,7 @@ static int igt_evict_vm(void *arg)
 		goto cleanup;
 	}
 
-	unpin_ggtt(i915);
+	unpin_ggtt(ggtt);
 
 	mutex_lock(&ggtt->vm.mutex);
 	err = i915_gem_evict_vm(&ggtt->vm);
@@ -386,14 +386,16 @@ static int igt_evict_vm(void *arg)
 	}
 
 cleanup:
-	cleanup_objects(i915, &objects);
+	cleanup_objects(ggtt, &objects);
 	return err;
 }
 
 static int igt_evict_contexts(void *arg)
 {
 	const u64 PRETEND_GGTT_SIZE = 16ull << 20;
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
+	struct i915_ggtt *ggtt = gt->ggtt;
+	struct drm_i915_private *i915 = gt->i915;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	struct reserved {
@@ -423,10 +425,10 @@ static int igt_evict_contexts(void *arg)
 
 	/* Reserve a block so that we know we have enough to fit a few rq */
 	memset(&hole, 0, sizeof(hole));
-	mutex_lock(&i915->ggtt.vm.mutex);
-	err = i915_gem_gtt_insert(&i915->ggtt.vm, &hole,
+	mutex_lock(&ggtt->vm.mutex);
+	err = i915_gem_gtt_insert(&ggtt->vm, &hole,
 				  PRETEND_GGTT_SIZE, 0, I915_COLOR_UNEVICTABLE,
-				  0, i915->ggtt.vm.total,
+				  0, ggtt->vm.total,
 				  PIN_NOEVICT);
 	if (err)
 		goto out_locked;
@@ -436,17 +438,17 @@ static int igt_evict_contexts(void *arg)
 	do {
 		struct reserved *r;
 
-		mutex_unlock(&i915->ggtt.vm.mutex);
+		mutex_unlock(&ggtt->vm.mutex);
 		r = kcalloc(1, sizeof(*r), GFP_KERNEL);
-		mutex_lock(&i915->ggtt.vm.mutex);
+		mutex_lock(&ggtt->vm.mutex);
 		if (!r) {
 			err = -ENOMEM;
 			goto out_locked;
 		}
 
-		if (i915_gem_gtt_insert(&i915->ggtt.vm, &r->node,
+		if (i915_gem_gtt_insert(&ggtt->vm, &r->node,
 					1ul << 20, 0, I915_COLOR_UNEVICTABLE,
-					0, i915->ggtt.vm.total,
+					0, ggtt->vm.total,
 					PIN_NOEVICT)) {
 			kfree(r);
 			break;
@@ -458,11 +460,11 @@ static int igt_evict_contexts(void *arg)
 		count++;
 	} while (1);
 	drm_mm_remove_node(&hole);
-	mutex_unlock(&i915->ggtt.vm.mutex);
+	mutex_unlock(&ggtt->vm.mutex);
 	pr_info("Filled GGTT with %lu 1MiB nodes\n", count);
 
 	/* Overfill the GGTT with context objects and so try to evict one. */
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		struct i915_sw_fence fence;
 		struct drm_file *file;
 
@@ -518,7 +520,7 @@ static int igt_evict_contexts(void *arg)
 			break;
 	}
 
-	mutex_lock(&i915->ggtt.vm.mutex);
+	mutex_lock(&ggtt->vm.mutex);
 out_locked:
 	if (igt_flush_test(i915))
 		err = -EIO;
@@ -532,7 +534,7 @@ out_locked:
 	}
 	if (drm_mm_node_allocated(&hole))
 		drm_mm_remove_node(&hole);
-	mutex_unlock(&i915->ggtt.vm.mutex);
+	mutex_unlock(&ggtt->vm.mutex);
 	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
 
 	return err;
@@ -556,7 +558,7 @@ int i915_gem_evict_mock_selftests(void)
 		return -ENOMEM;
 
 	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		err = i915_subtests(tests, i915);
+		err = i915_subtests(tests, &i915->gt);
 
 	drm_dev_put(&i915->drm);
 	return err;
@@ -571,5 +573,5 @@ int i915_gem_evict_live_selftests(struct drm_i915_private *i915)
 	if (intel_gt_is_wedged(&i915->gt))
 		return 0;
 
-	return i915_subtests(tests, i915);
+	return intel_gt_live_subtests(tests, &i915->gt);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index ebe735df6504..3f7e80fb3bbd 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -104,6 +104,7 @@ static const struct drm_i915_gem_object_ops fake_ops = {
 static struct drm_i915_gem_object *
 fake_dma_object(struct drm_i915_private *i915, u64 size)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_gem_object *obj;
 
 	GEM_BUG_ON(!size);
@@ -117,7 +118,7 @@ fake_dma_object(struct drm_i915_private *i915, u64 size)
 		goto err;
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &fake_ops);
+	i915_gem_object_init(obj, &fake_ops, &lock_class);
 
 	i915_gem_object_set_volatile(obj);
 
@@ -1148,6 +1149,9 @@ static int igt_ggtt_page(void *arg)
 	unsigned int *order, n;
 	int err;
 
+	if (!i915_ggtt_has_aperture(ggtt))
+		return 0;
+
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
diff --git a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
index 6daf6599ec79..4b3cac73e291 100644
--- a/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_live_selftests.h
@@ -17,6 +17,7 @@ selftest(gt_timelines, intel_timeline_live_selftests)
 selftest(gt_contexts, intel_context_live_selftests)
 selftest(gt_lrc, intel_lrc_live_selftests)
 selftest(gt_pm, intel_gt_pm_live_selftests)
+selftest(gt_heartbeat, intel_heartbeat_live_selftests)
 selftest(requests, i915_request_live_selftests)
 selftest(active, i915_active_live_selftests)
 selftest(objects, i915_gem_object_live_selftests)
@@ -32,6 +33,7 @@ selftest(gem_contexts, i915_gem_context_live_selftests)
 selftest(blt, i915_gem_object_blt_live_selftests)
 selftest(client, i915_gem_client_blt_live_selftests)
 selftest(reset, intel_reset_live_selftests)
+selftest(memory_region, intel_memory_region_live_selftests)
 selftest(hangcheck, intel_hangcheck_live_selftests)
 selftest(execlists, intel_execlists_live_selftests)
 selftest(guc, intel_guc_live_selftest)
diff --git a/drivers/gpu/drm/i915/selftests/i915_perf.c b/drivers/gpu/drm/i915/selftests/i915_perf.c
index dc6d689e4251..aabd07f67e49 100644
--- a/drivers/gpu/drm/i915/selftests/i915_perf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_perf.c
@@ -23,7 +23,8 @@ test_stream(struct i915_perf *perf)
 						   I915_ENGINE_CLASS_RENDER,
 						   0),
 		.sample_flags = SAMPLE_OA_REPORT,
-		.oa_format = I915_OA_FORMAT_C4_B8,
+		.oa_format = IS_GEN(perf->i915, 12) ?
+		I915_OA_FORMAT_A32u40_A4u32_B8_C8 : I915_OA_FORMAT_C4_B8,
 		.metrics_set = 1,
 	};
 	struct i915_perf_stream *stream;
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 30ae34f62176..8618a4dc0701 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -464,6 +464,7 @@ static int mock_breadcrumbs_smoketest(void *arg)
 		get_task_struct(threads[n]);
 	}
 
+	yield(); /* start all threads before we begin */
 	msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies));
 
 	for (n = 0; n < ncpus; n++) {
@@ -1158,6 +1159,8 @@ static int live_parallel_engines(void *arg)
 			get_task_struct(tsk[idx++]);
 		}
 
+		yield(); /* start all threads before we kthread_stop() */
+
 		idx = 0;
 		for_each_uabi_engine(engine, i915) {
 			int status;
@@ -1314,6 +1317,7 @@ static int live_breadcrumbs_smoketest(void *arg)
 		idx++;
 	}
 
+	yield(); /* start all threads before we begin */
 	msleep(jiffies_to_msecs(i915_selftest.timeout_jiffies));
 
 out_flush:
diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index 825a8286cbe8..a6cca4ad96f6 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -23,13 +23,14 @@
 
 #include <linux/random.h>
 
-#include "../i915_drv.h"
-#include "../i915_selftest.h"
+#include "gt/intel_gt_pm.h"
+#include "i915_drv.h"
+#include "i915_selftest.h"
 
 #include "igt_flush_test.h"
 
 struct i915_selftest i915_selftest __read_mostly = {
-	.timeout_ms = 1000,
+	.timeout_ms = 500,
 };
 
 int i915_mock_sanitycheck(void)
@@ -256,6 +257,10 @@ int __i915_live_setup(void *data)
 {
 	struct drm_i915_private *i915 = data;
 
+	/* The selftests expect an idle system */
+	if (intel_gt_pm_wait_for_idle(&i915->gt))
+		return -EIO;
+
 	return intel_gt_terminally_wedged(&i915->gt);
 }
 
@@ -275,6 +280,10 @@ int __intel_gt_live_setup(void *data)
 {
 	struct intel_gt *gt = data;
 
+	/* The selftests expect an idle system */
+	if (intel_gt_pm_wait_for_idle(gt))
+		return -EIO;
+
 	return intel_gt_terminally_wedged(gt);
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/igt_live_test.c b/drivers/gpu/drm/i915/selftests/igt_live_test.c
index 810b60100c2c..c130010a7033 100644
--- a/drivers/gpu/drm/i915/selftests/igt_live_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_live_test.c
@@ -16,6 +16,7 @@ int igt_live_test_begin(struct igt_live_test *t,
 			const char *func,
 			const char *name)
 {
+	struct intel_gt *gt = &i915->gt;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	int err;
@@ -24,7 +25,7 @@ int igt_live_test_begin(struct igt_live_test *t,
 	t->func = func;
 	t->name = name;
 
-	err = intel_gt_wait_for_idle(&i915->gt, MAX_SCHEDULE_TIMEOUT);
+	err = intel_gt_wait_for_idle(gt, MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
 		       func, name, err);
@@ -33,7 +34,7 @@ int igt_live_test_begin(struct igt_live_test *t,
 
 	t->reset_global = i915_reset_count(&i915->gpu_error);
 
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, gt, id)
 		t->reset_engine[id] =
 			i915_reset_engine_count(&i915->gpu_error, engine);
 
@@ -56,7 +57,7 @@ int igt_live_test_end(struct igt_live_test *t)
 		return -EIO;
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, &i915->gt, id) {
 		if (t->reset_engine[id] ==
 		    i915_reset_engine_count(&i915->gpu_error, engine))
 			continue;
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 56091e7e599e..19e1cca8f143 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -11,8 +11,15 @@
 #include "mock_gem_device.h"
 #include "mock_region.h"
 
+#include "gem/i915_gem_context.h"
+#include "gem/i915_gem_lmem.h"
 #include "gem/i915_gem_region.h"
+#include "gem/i915_gem_object_blt.h"
+#include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
+#include "gt/intel_engine_user.h"
+#include "gt/intel_gt.h"
+#include "selftests/igt_flush_test.h"
 #include "selftests/i915_random.h"
 
 static void close_objects(struct intel_memory_region *mem,
@@ -252,6 +259,322 @@ err_close_objects:
 	return err;
 }
 
+static int igt_gpu_write_dw(struct intel_context *ce,
+			    struct i915_vma *vma,
+			    u32 dword,
+			    u32 value)
+{
+	return igt_gpu_fill_dw(ce, vma, dword * sizeof(u32),
+			       vma->size >> PAGE_SHIFT, value);
+}
+
+static int igt_cpu_check(struct drm_i915_gem_object *obj, u32 dword, u32 val)
+{
+	unsigned long n;
+	int err;
+
+	i915_gem_object_lock(obj);
+	err = i915_gem_object_set_to_wc_domain(obj, false);
+	i915_gem_object_unlock(obj);
+	if (err)
+		return err;
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		return err;
+
+	for (n = 0; n < obj->base.size >> PAGE_SHIFT; ++n) {
+		u32 __iomem *base;
+		u32 read_val;
+
+		base = i915_gem_object_lmem_io_map_page_atomic(obj, n);
+
+		read_val = ioread32(base + dword);
+		io_mapping_unmap_atomic(base);
+		if (read_val != val) {
+			pr_err("n=%lu base[%u]=%u, val=%u\n",
+			       n, dword, read_val, val);
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	i915_gem_object_unpin_pages(obj);
+	return err;
+}
+
+static int igt_gpu_write(struct i915_gem_context *ctx,
+			 struct drm_i915_gem_object *obj)
+{
+	struct i915_gem_engines *engines;
+	struct i915_gem_engines_iter it;
+	struct i915_address_space *vm;
+	struct intel_context *ce;
+	I915_RND_STATE(prng);
+	IGT_TIMEOUT(end_time);
+	unsigned int count;
+	struct i915_vma *vma;
+	int *order;
+	int i, n;
+	int err = 0;
+
+	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
+
+	n = 0;
+	count = 0;
+	for_each_gem_engine(ce, i915_gem_context_lock_engines(ctx), it) {
+		count++;
+		if (!intel_engine_can_store_dword(ce->engine))
+			continue;
+
+		vm = ce->vm;
+		n++;
+	}
+	i915_gem_context_unlock_engines(ctx);
+	if (!n)
+		return 0;
+
+	order = i915_random_order(count * count, &prng);
+	if (!order)
+		return -ENOMEM;
+
+	vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(vma)) {
+		err = PTR_ERR(vma);
+		goto out_free;
+	}
+
+	err = i915_vma_pin(vma, 0, 0, PIN_USER);
+	if (err)
+		goto out_free;
+
+	i = 0;
+	engines = i915_gem_context_lock_engines(ctx);
+	do {
+		u32 rng = prandom_u32_state(&prng);
+		u32 dword = offset_in_page(rng) / 4;
+
+		ce = engines->engines[order[i] % engines->num_engines];
+		i = (i + 1) % (count * count);
+		if (!ce || !intel_engine_can_store_dword(ce->engine))
+			continue;
+
+		err = igt_gpu_write_dw(ce, vma, dword, rng);
+		if (err)
+			break;
+
+		err = igt_cpu_check(obj, dword, rng);
+		if (err)
+			break;
+	} while (!__igt_timeout(end_time, NULL));
+	i915_gem_context_unlock_engines(ctx);
+
+out_free:
+	kfree(order);
+
+	if (err == -ENOMEM)
+		err = 0;
+
+	return err;
+}
+
+static int igt_lmem_create(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj;
+	int err = 0;
+
+	obj = i915_gem_object_create_lmem(i915, PAGE_SIZE, 0);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		goto out_put;
+
+	i915_gem_object_unpin_pages(obj);
+out_put:
+	i915_gem_object_put(obj);
+
+	return err;
+}
+
+static int igt_lmem_write_gpu(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj;
+	struct i915_gem_context *ctx;
+	struct drm_file *file;
+	I915_RND_STATE(prng);
+	u32 sz;
+	int err;
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	ctx = live_context(i915, file);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_file;
+	}
+
+	sz = round_up(prandom_u32_state(&prng) % SZ_32M, PAGE_SIZE);
+
+	obj = i915_gem_object_create_lmem(i915, sz, 0);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto out_file;
+	}
+
+	err = i915_gem_object_pin_pages(obj);
+	if (err)
+		goto out_put;
+
+	err = igt_gpu_write(ctx, obj);
+	if (err)
+		pr_err("igt_gpu_write failed(%d)\n", err);
+
+	i915_gem_object_unpin_pages(obj);
+out_put:
+	i915_gem_object_put(obj);
+out_file:
+	mock_file_free(i915, file);
+	return err;
+}
+
+static struct intel_engine_cs *
+random_engine_class(struct drm_i915_private *i915,
+		    unsigned int class,
+		    struct rnd_state *prng)
+{
+	struct intel_engine_cs *engine;
+	unsigned int count;
+
+	count = 0;
+	for (engine = intel_engine_lookup_user(i915, class, 0);
+	     engine && engine->uabi_class == class;
+	     engine = rb_entry_safe(rb_next(&engine->uabi_node),
+				    typeof(*engine), uabi_node))
+		count++;
+
+	count = i915_prandom_u32_max_state(count, prng);
+	return intel_engine_lookup_user(i915, class, count);
+}
+
+static int igt_lmem_write_cpu(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj;
+	I915_RND_STATE(prng);
+	IGT_TIMEOUT(end_time);
+	u32 bytes[] = {
+		0, /* rng placeholder */
+		sizeof(u32),
+		sizeof(u64),
+		64, /* cl */
+		PAGE_SIZE,
+		PAGE_SIZE - sizeof(u32),
+		PAGE_SIZE - sizeof(u64),
+		PAGE_SIZE - 64,
+	};
+	struct intel_engine_cs *engine;
+	u32 *vaddr;
+	u32 sz;
+	u32 i;
+	int *order;
+	int count;
+	int err;
+
+	engine = random_engine_class(i915, I915_ENGINE_CLASS_COPY, &prng);
+	if (!engine)
+		return 0;
+
+	pr_info("%s: using %s\n", __func__, engine->name);
+
+	sz = round_up(prandom_u32_state(&prng) % SZ_32M, PAGE_SIZE);
+	sz = max_t(u32, 2 * PAGE_SIZE, sz);
+
+	obj = i915_gem_object_create_lmem(i915, sz, I915_BO_ALLOC_CONTIGUOUS);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	vaddr = i915_gem_object_pin_map(obj, I915_MAP_WC);
+	if (IS_ERR(vaddr)) {
+		err = PTR_ERR(vaddr);
+		goto out_put;
+	}
+
+	/* Put the pages into a known state -- from the gpu for added fun */
+	err = i915_gem_object_fill_blt(obj, engine->kernel_context, 0xdeadbeaf);
+	if (err)
+		goto out_unpin;
+
+	i915_gem_object_lock(obj);
+	err = i915_gem_object_set_to_wc_domain(obj, true);
+	i915_gem_object_unlock(obj);
+	if (err)
+		goto out_unpin;
+
+	count = ARRAY_SIZE(bytes);
+	order = i915_random_order(count * count, &prng);
+	if (!order) {
+		err = -ENOMEM;
+		goto out_unpin;
+	}
+
+	/* We want to throw in a random width/align */
+	bytes[0] = igt_random_offset(&prng, 0, PAGE_SIZE, sizeof(u32),
+				     sizeof(u32));
+
+	i = 0;
+	do {
+		u32 offset;
+		u32 align;
+		u32 dword;
+		u32 size;
+		u32 val;
+
+		size = bytes[order[i] % count];
+		i = (i + 1) % (count * count);
+
+		align = bytes[order[i] % count];
+		i = (i + 1) % (count * count);
+
+		align = max_t(u32, sizeof(u32), rounddown_pow_of_two(align));
+
+		offset = igt_random_offset(&prng, 0, obj->base.size,
+					   size, align);
+
+		val = prandom_u32_state(&prng);
+		memset32(vaddr + offset / sizeof(u32), val ^ 0xdeadbeaf,
+			 size / sizeof(u32));
+
+		/*
+		 * Sample random dw -- don't waste precious time reading every
+		 * single dw.
+		 */
+		dword = igt_random_offset(&prng, offset,
+					  offset + size,
+					  sizeof(u32), sizeof(u32));
+		dword /= sizeof(u32);
+		if (vaddr[dword] != (val ^ 0xdeadbeaf)) {
+			pr_err("%s vaddr[%u]=%u, val=%u, size=%u, align=%u, offset=%u\n",
+			       __func__, dword, vaddr[dword], val ^ 0xdeadbeaf,
+			       size, align, offset);
+			err = -EINVAL;
+			break;
+		}
+	} while (!__igt_timeout(end_time, NULL));
+
+out_unpin:
+	i915_gem_object_unpin_map(obj);
+out_put:
+	i915_gem_object_put(obj);
+
+	return err;
+}
+
 int intel_memory_region_mock_selftests(void)
 {
 	static const struct i915_subtest tests[] = {
@@ -280,3 +603,22 @@ out_unref:
 	drm_dev_put(&i915->drm);
 	return err;
 }
+
+int intel_memory_region_live_selftests(struct drm_i915_private *i915)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_lmem_create),
+		SUBTEST(igt_lmem_write_cpu),
+		SUBTEST(igt_lmem_write_gpu),
+	};
+
+	if (!HAS_LMEM(i915)) {
+		pr_info("device lacks LMEM support, skipping\n");
+		return 0;
+	}
+
+	if (intel_gt_is_wedged(&i915->gt))
+		return 0;
+
+	return i915_live_subtests(tests, i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/intel_uncore.c b/drivers/gpu/drm/i915/selftests/intel_uncore.c
index 0ffb141eb988..0e4e6be0101d 100644
--- a/drivers/gpu/drm/i915/selftests/intel_uncore.c
+++ b/drivers/gpu/drm/i915/selftests/intel_uncore.c
@@ -140,19 +140,19 @@ static int live_forcewake_ops(void *arg)
 		}
 	};
 	const struct reg *r;
-	struct drm_i915_private *i915 = arg;
+	struct intel_gt *gt = arg;
 	struct intel_uncore_forcewake_domain *domain;
-	struct intel_uncore *uncore = &i915->uncore;
+	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 	intel_wakeref_t wakeref;
 	unsigned int tmp;
 	int err = 0;
 
-	GEM_BUG_ON(i915->gt.awake);
+	GEM_BUG_ON(gt->awake);
 
 	/* vlv/chv with their pcu behave differently wrt reads */
-	if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) {
+	if (IS_VALLEYVIEW(gt->i915) || IS_CHERRYVIEW(gt->i915)) {
 		pr_debug("PCU fakes forcewake badly; skipping\n");
 		return 0;
 	}
@@ -170,15 +170,15 @@ static int live_forcewake_ops(void *arg)
 
 	/* We have to pick carefully to get the exact behaviour we need */
 	for (r = registers; r->name; r++)
-		if (r->platforms & INTEL_INFO(i915)->gen_mask)
+		if (r->platforms & INTEL_INFO(gt->i915)->gen_mask)
 			break;
 	if (!r->name) {
 		pr_debug("Forcewaked register not known for %s; skipping\n",
-			 intel_platform_name(INTEL_INFO(i915)->platform));
+			 intel_platform_name(INTEL_INFO(gt->i915)->platform));
 		return 0;
 	}
 
-	wakeref = intel_runtime_pm_get(&i915->runtime_pm);
+	wakeref = intel_runtime_pm_get(uncore->rpm);
 
 	for_each_fw_domain(domain, uncore, tmp) {
 		smp_store_mb(domain->active, false);
@@ -188,7 +188,7 @@ static int live_forcewake_ops(void *arg)
 		intel_uncore_fw_release_timer(&domain->timer);
 	}
 
-	for_each_engine(engine, i915, id) {
+	for_each_engine(engine, gt, id) {
 		i915_reg_t mmio = _MMIO(engine->mmio_base + r->offset);
 		u32 __iomem *reg = uncore->regs + engine->mmio_base + r->offset;
 		enum forcewake_domains fw_domains;
@@ -249,22 +249,22 @@ static int live_forcewake_ops(void *arg)
 	}
 
 out_rpm:
-	intel_runtime_pm_put(&i915->runtime_pm, wakeref);
+	intel_runtime_pm_put(uncore->rpm, wakeref);
 	return err;
 }
 
 static int live_forcewake_domains(void *arg)
 {
 #define FW_RANGE 0x40000
-	struct drm_i915_private *dev_priv = arg;
-	struct intel_uncore *uncore = &dev_priv->uncore;
+	struct intel_gt *gt = arg;
+	struct intel_uncore *uncore = gt->uncore;
 	unsigned long *valid;
 	u32 offset;
 	int err;
 
-	if (!HAS_FPGA_DBG_UNCLAIMED(dev_priv) &&
-	    !IS_VALLEYVIEW(dev_priv) &&
-	    !IS_CHERRYVIEW(dev_priv))
+	if (!HAS_FPGA_DBG_UNCLAIMED(gt->i915) &&
+	    !IS_VALLEYVIEW(gt->i915) &&
+	    !IS_CHERRYVIEW(gt->i915))
 		return 0;
 
 	/*
@@ -283,7 +283,7 @@ static int live_forcewake_domains(void *arg)
 	for (offset = 0; offset < FW_RANGE; offset += 4) {
 		i915_reg_t reg = { offset };
 
-		(void)I915_READ_FW(reg);
+		intel_uncore_posting_read_fw(uncore, reg);
 		if (!check_for_unclaimed_mmio(uncore))
 			set_bit(offset, valid);
 	}
@@ -300,7 +300,7 @@ static int live_forcewake_domains(void *arg)
 
 		check_for_unclaimed_mmio(uncore);
 
-		(void)I915_READ(reg);
+		intel_uncore_posting_read_fw(uncore, reg);
 		if (check_for_unclaimed_mmio(uncore)) {
 			pr_err("Unclaimed mmio read to register 0x%04x\n",
 			       offset);
@@ -312,21 +312,23 @@ static int live_forcewake_domains(void *arg)
 	return err;
 }
 
+static int live_fw_table(void *arg)
+{
+	struct intel_gt *gt = arg;
+
+	/* Confirm the table we load is still valid */
+	return intel_fw_table_check(gt->uncore->fw_domains_table,
+				    gt->uncore->fw_domains_table_entries,
+				    INTEL_GEN(gt->i915) >= 9);
+}
+
 int intel_uncore_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(live_fw_table),
 		SUBTEST(live_forcewake_ops),
 		SUBTEST(live_forcewake_domains),
 	};
 
-	int err;
-
-	/* Confirm the table we load is still valid */
-	err = intel_fw_table_check(i915->uncore.fw_domains_table,
-				   i915->uncore.fw_domains_table_entries,
-				   INTEL_GEN(i915) >= 9);
-	if (err)
-		return err;
-
-	return i915_subtests(tests, i915);
+	return intel_gt_live_subtests(tests, &i915->gt);
 }
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index cb8c3a501cc7..27ed3cee6a9b 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -28,6 +28,7 @@
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
 #include "gt/mock_engine.h"
+#include "intel_memory_region.h"
 
 #include "mock_request.h"
 #include "mock_gem_device.h"
@@ -40,14 +41,14 @@
 
 void mock_device_flush(struct drm_i915_private *i915)
 {
+	struct intel_gt *gt = &i915->gt;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
 	do {
-		for_each_engine(engine, i915, id)
+		for_each_engine(engine, gt, id)
 			mock_engine_flush(engine);
-	} while (intel_gt_retire_requests_timeout(&i915->gt,
-						  MAX_SCHEDULE_TIMEOUT));
+	} while (intel_gt_retire_requests_timeout(gt, MAX_SCHEDULE_TIMEOUT));
 }
 
 static void mock_device_release(struct drm_device *dev)
@@ -60,7 +61,7 @@ static void mock_device_release(struct drm_device *dev)
 
 	i915_gem_drain_workqueue(i915);
 
-	for_each_engine(engine, i915, id)
+	for_each_engine(engine, &i915->gt, id)
 		mock_engine_free(engine);
 	i915_gem_driver_release__contexts(i915);
 
@@ -72,7 +73,7 @@ static void mock_device_release(struct drm_device *dev)
 	mock_fini_ggtt(&i915->ggtt);
 	destroy_workqueue(i915->wq);
 
-	i915_gem_cleanup_memory_regions(i915);
+	intel_memory_regions_driver_release(i915);
 
 	drm_mode_config_cleanup(&i915->drm);
 
@@ -164,6 +165,7 @@ struct drm_i915_private *mock_gem_device(void)
 		I915_GTT_PAGE_SIZE_2M;
 
 	mkwrite_device_info(i915)->memory_regions = REGION_SMEM;
+	intel_memory_regions_hw_probe(i915);
 
 	mock_uncore_init(&i915->uncore, i915);
 
@@ -197,10 +199,6 @@ struct drm_i915_private *mock_gem_device(void)
 
 	intel_engines_driver_register(i915);
 
-	err = i915_gem_init_memory_regions(i915);
-	if (err)
-		goto err_context;
-
 	return i915;
 
 err_context:
@@ -211,6 +209,7 @@ err_unlock:
 	intel_timelines_fini(i915);
 	destroy_workqueue(i915->wq);
 err_drv:
+	intel_memory_regions_driver_release(i915);
 	drm_mode_config_cleanup(&i915->drm);
 	drm_dev_fini(&i915->drm);
 put_device:
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 173f2d4dbd14..20ac3844edec 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -63,6 +63,7 @@ struct i915_ppgtt *mock_ppgtt(struct drm_i915_private *i915, const char *name)
 	if (!ppgtt)
 		return NULL;
 
+	ppgtt->vm.gt = &i915->gt;
 	ppgtt->vm.i915 = i915;
 	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
 	ppgtt->vm.file = ERR_PTR(-ENODEV);
@@ -117,8 +118,7 @@ void mock_init_ggtt(struct drm_i915_private *i915, struct i915_ggtt *ggtt)
 	ggtt->vm.vma_ops.clear_pages = clear_pages;
 
 	i915_address_space_init(&ggtt->vm, VM_CLASS_GGTT);
-
-	intel_gt_init_hw_early(i915);
+	i915->gt.ggtt = ggtt;
 }
 
 void mock_fini_ggtt(struct i915_ggtt *ggtt)
diff --git a/drivers/gpu/drm/i915/selftests/mock_region.c b/drivers/gpu/drm/i915/selftests/mock_region.c
index 7b0c99ddc2d5..b2ad41c27e67 100644
--- a/drivers/gpu/drm/i915/selftests/mock_region.c
+++ b/drivers/gpu/drm/i915/selftests/mock_region.c
@@ -19,6 +19,7 @@ mock_object_create(struct intel_memory_region *mem,
 		   resource_size_t size,
 		   unsigned int flags)
 {
+	static struct lock_class_key lock_class;
 	struct drm_i915_private *i915 = mem->i915;
 	struct drm_i915_gem_object *obj;
 
@@ -30,7 +31,7 @@ mock_object_create(struct intel_memory_region *mem,
 		return ERR_PTR(-ENOMEM);
 
 	drm_gem_private_object_init(&i915->drm, &obj->base, size);
-	i915_gem_object_init(obj, &mock_region_obj_ops);
+	i915_gem_object_init(obj, &mock_region_obj_ops, &lock_class);
 
 	obj->read_domains = I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
index 14878ebf59d7..4a55bb6e2213 100644
--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
@@ -3,6 +3,8 @@
  * Copyright (c) 2015 MediaTek Inc.
  */
 
+#include <drm/drm_fourcc.h>
+
 #include <linux/clk.h>
 #include <linux/component.h>
 #include <linux/module.h>
@@ -50,6 +52,8 @@
 					OVL_CON_CLRFMT_RGB : 0)
 #define	OVL_CON_AEN		BIT(8)
 #define	OVL_CON_ALPHA		0xff
+#define	OVL_CON_VIRT_FLIP	BIT(9)
+#define	OVL_CON_HORZ_FLIP	BIT(10)
 
 struct mtk_disp_ovl_data {
 	unsigned int addr;
@@ -137,6 +141,40 @@ static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp)
 	return ovl->data->layer_nr;
 }
 
+static unsigned int mtk_ovl_supported_rotations(struct mtk_ddp_comp *comp)
+{
+	return DRM_MODE_ROTATE_0 | DRM_MODE_ROTATE_180 |
+	       DRM_MODE_REFLECT_X | DRM_MODE_REFLECT_Y;
+}
+
+static int mtk_ovl_layer_check(struct mtk_ddp_comp *comp, unsigned int idx,
+			       struct mtk_plane_state *mtk_state)
+{
+	struct drm_plane_state *state = &mtk_state->base;
+	unsigned int rotation = 0;
+
+	rotation = drm_rotation_simplify(state->rotation,
+					 DRM_MODE_ROTATE_0 |
+					 DRM_MODE_REFLECT_X |
+					 DRM_MODE_REFLECT_Y);
+	rotation &= ~DRM_MODE_ROTATE_0;
+
+	/* We can only do reflection, not rotation */
+	if ((rotation & DRM_MODE_ROTATE_MASK) != 0)
+		return -EINVAL;
+
+	/*
+	 * TODO: Rotating/reflecting YUV buffers is not supported at this time.
+	 *	 Only RGB[AX] variants are supported.
+	 */
+	if (state->fb->format->is_yuv && rotation != 0)
+		return -EINVAL;
+
+	state->rotation = rotation;
+
+	return 0;
+}
+
 static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx)
 {
 	unsigned int reg;
@@ -229,6 +267,16 @@ static void mtk_ovl_layer_config(struct mtk_ddp_comp *comp, unsigned int idx,
 	if (idx != 0)
 		con |= OVL_CON_AEN | OVL_CON_ALPHA;
 
+	if (pending->rotation & DRM_MODE_REFLECT_Y) {
+		con |= OVL_CON_VIRT_FLIP;
+		addr += (pending->height - 1) * pending->pitch;
+	}
+
+	if (pending->rotation & DRM_MODE_REFLECT_X) {
+		con |= OVL_CON_HORZ_FLIP;
+		addr += pending->pitch - 1;
+	}
+
 	writel_relaxed(con, comp->regs + DISP_REG_OVL_CON(idx));
 	writel_relaxed(pitch, comp->regs + DISP_REG_OVL_PITCH(idx));
 	writel_relaxed(src_size, comp->regs + DISP_REG_OVL_SRC_SIZE(idx));
@@ -263,9 +311,11 @@ static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = {
 	.stop = mtk_ovl_stop,
 	.enable_vblank = mtk_ovl_enable_vblank,
 	.disable_vblank = mtk_ovl_disable_vblank,
+	.supported_rotations = mtk_ovl_supported_rotations,
 	.layer_nr = mtk_ovl_layer_nr,
 	.layer_on = mtk_ovl_layer_on,
 	.layer_off = mtk_ovl_layer_off,
+	.layer_check = mtk_ovl_layer_check,
 	.layer_config = mtk_ovl_layer_config,
 	.bgclr_in_on = mtk_ovl_bgclr_in_on,
 	.bgclr_in_off = mtk_ovl_bgclr_in_off,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index b841d3706d8b..f80a8ba75977 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -207,6 +207,28 @@ static void mtk_crtc_ddp_clk_disable(struct mtk_drm_crtc *mtk_crtc)
 		clk_disable_unprepare(mtk_crtc->ddp_comp[i]->clk);
 }
 
+static
+struct mtk_ddp_comp *mtk_drm_ddp_comp_for_plane(struct drm_crtc *crtc,
+						struct drm_plane *plane,
+						unsigned int *local_layer)
+{
+	struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc);
+	struct mtk_ddp_comp *comp;
+	int i, count = 0;
+
+	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
+		comp = mtk_crtc->ddp_comp[i];
+		if (plane->index < (count + mtk_ddp_comp_layer_nr(comp))) {
+			*local_layer = plane->index - count;
+			return comp;
+		}
+		count += mtk_ddp_comp_layer_nr(comp);
+	}
+
+	WARN(1, "Failed to find component for plane %d\n", plane->index);
+	return NULL;
+}
+
 static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 {
 	struct drm_crtc *crtc = &mtk_crtc->base;
@@ -283,19 +305,12 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc)
 	for (i = 0; i < mtk_crtc->layer_nr; i++) {
 		struct drm_plane *plane = &mtk_crtc->planes[i];
 		struct mtk_plane_state *plane_state;
-		struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0];
-		unsigned int comp_layer_nr = mtk_ddp_comp_layer_nr(comp);
+		struct mtk_ddp_comp *comp;
 		unsigned int local_layer;
 
 		plane_state = to_mtk_plane_state(plane->state);
-
-		if (i >= comp_layer_nr) {
-			comp = mtk_crtc->ddp_comp[1];
-			local_layer = i - comp_layer_nr;
-		} else
-			local_layer = i;
-		mtk_ddp_comp_layer_config(comp, local_layer,
-					  plane_state);
+		comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
+		mtk_ddp_comp_layer_config(comp, local_layer, plane_state);
 	}
 
 	return 0;
@@ -343,7 +358,6 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 	struct mtk_crtc_state *state = to_mtk_crtc_state(mtk_crtc->base.state);
 	struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0];
 	unsigned int i;
-	unsigned int comp_layer_nr = mtk_ddp_comp_layer_nr(comp);
 	unsigned int local_layer;
 
 	/*
@@ -366,22 +380,30 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc)
 
 			plane_state = to_mtk_plane_state(plane->state);
 
-			if (plane_state->pending.config) {
-				if (i >= comp_layer_nr) {
-					comp = mtk_crtc->ddp_comp[1];
-					local_layer = i - comp_layer_nr;
-				} else
-					local_layer = i;
-
-				mtk_ddp_comp_layer_config(comp, local_layer,
-							  plane_state);
-				plane_state->pending.config = false;
-			}
+			if (!plane_state->pending.config)
+				continue;
+
+			comp = mtk_drm_ddp_comp_for_plane(crtc, plane,
+							  &local_layer);
+
+			mtk_ddp_comp_layer_config(comp, local_layer,
+						  plane_state);
+			plane_state->pending.config = false;
 		}
 		mtk_crtc->pending_planes = false;
 	}
 }
 
+int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
+			     struct mtk_plane_state *state)
+{
+	unsigned int local_layer;
+	struct mtk_ddp_comp *comp;
+
+	comp = mtk_drm_ddp_comp_for_plane(crtc, plane, &local_layer);
+	return mtk_ddp_comp_layer_check(comp, local_layer, state);
+}
+
 static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 				       struct drm_crtc_state *old_state)
 {
@@ -543,14 +565,65 @@ void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp)
 	mtk_drm_finish_page_flip(mtk_crtc);
 }
 
+static int mtk_drm_crtc_num_comp_planes(struct mtk_drm_crtc *mtk_crtc,
+					int comp_idx)
+{
+	struct mtk_ddp_comp *comp;
+
+	if (comp_idx > 1)
+		return 0;
+
+	comp = mtk_crtc->ddp_comp[comp_idx];
+	if (!comp->funcs)
+		return 0;
+
+	if (comp_idx == 1 && !comp->funcs->bgclr_in_on)
+		return 0;
+
+	return mtk_ddp_comp_layer_nr(comp);
+}
+
+static inline
+enum drm_plane_type mtk_drm_crtc_plane_type(unsigned int plane_idx)
+{
+	if (plane_idx == 0)
+		return DRM_PLANE_TYPE_PRIMARY;
+	else if (plane_idx == 1)
+		return DRM_PLANE_TYPE_CURSOR;
+	else
+		return DRM_PLANE_TYPE_OVERLAY;
+
+}
+
+static int mtk_drm_crtc_init_comp_planes(struct drm_device *drm_dev,
+					 struct mtk_drm_crtc *mtk_crtc,
+					 int comp_idx, int pipe)
+{
+	int num_planes = mtk_drm_crtc_num_comp_planes(mtk_crtc, comp_idx);
+	struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[comp_idx];
+	int i, ret;
+
+	for (i = 0; i < num_planes; i++) {
+		ret = mtk_plane_init(drm_dev,
+				&mtk_crtc->planes[mtk_crtc->layer_nr],
+				BIT(pipe),
+				mtk_drm_crtc_plane_type(mtk_crtc->layer_nr),
+				mtk_ddp_comp_supported_rotations(comp));
+		if (ret)
+			return ret;
+
+		mtk_crtc->layer_nr++;
+	}
+	return 0;
+}
+
 int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			const enum mtk_ddp_comp_id *path, unsigned int path_len)
 {
 	struct mtk_drm_private *priv = drm_dev->dev_private;
 	struct device *dev = drm_dev->dev;
 	struct mtk_drm_crtc *mtk_crtc;
-	enum drm_plane_type type;
-	unsigned int zpos;
+	unsigned int num_comp_planes = 0;
 	int pipe = priv->num_pipes;
 	int ret;
 	int i;
@@ -606,23 +679,15 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 		mtk_crtc->ddp_comp[i] = comp;
 	}
 
-	mtk_crtc->layer_nr = mtk_ddp_comp_layer_nr(mtk_crtc->ddp_comp[0]);
-	if (mtk_crtc->ddp_comp_nr > 1) {
-		struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[1];
+	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++)
+		num_comp_planes += mtk_drm_crtc_num_comp_planes(mtk_crtc, i);
 
-		if (comp->funcs->bgclr_in_on)
-			mtk_crtc->layer_nr += mtk_ddp_comp_layer_nr(comp);
-	}
-	mtk_crtc->planes = devm_kcalloc(dev, mtk_crtc->layer_nr,
-					sizeof(struct drm_plane),
-					GFP_KERNEL);
-
-	for (zpos = 0; zpos < mtk_crtc->layer_nr; zpos++) {
-		type = (zpos == 0) ? DRM_PLANE_TYPE_PRIMARY :
-				(zpos == 1) ? DRM_PLANE_TYPE_CURSOR :
-						DRM_PLANE_TYPE_OVERLAY;
-		ret = mtk_plane_init(drm_dev, &mtk_crtc->planes[zpos],
-				     BIT(pipe), type);
+	mtk_crtc->planes = devm_kcalloc(dev, num_comp_planes,
+					sizeof(struct drm_plane), GFP_KERNEL);
+
+	for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
+		ret = mtk_drm_crtc_init_comp_planes(drm_dev, mtk_crtc, i,
+						    pipe);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
index fcc134eb00c9..6afe1c19557a 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h
@@ -19,5 +19,7 @@ void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp);
 int mtk_drm_crtc_create(struct drm_device *drm_dev,
 			const enum mtk_ddp_comp_id *path,
 			unsigned int path_len);
+int mtk_drm_crtc_plane_check(struct drm_crtc *crtc, struct drm_plane *plane,
+			     struct mtk_plane_state *state);
 
 #endif /* MTK_DRM_CRTC_H */
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 26441f4d1ad3..2f1e9e75b8da 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -77,9 +77,13 @@ struct mtk_ddp_comp_funcs {
 	void (*stop)(struct mtk_ddp_comp *comp);
 	void (*enable_vblank)(struct mtk_ddp_comp *comp, struct drm_crtc *crtc);
 	void (*disable_vblank)(struct mtk_ddp_comp *comp);
+	unsigned int (*supported_rotations)(struct mtk_ddp_comp *comp);
 	unsigned int (*layer_nr)(struct mtk_ddp_comp *comp);
 	void (*layer_on)(struct mtk_ddp_comp *comp, unsigned int idx);
 	void (*layer_off)(struct mtk_ddp_comp *comp, unsigned int idx);
+	int (*layer_check)(struct mtk_ddp_comp *comp,
+			   unsigned int idx,
+			   struct mtk_plane_state *state);
 	void (*layer_config)(struct mtk_ddp_comp *comp, unsigned int idx,
 			     struct mtk_plane_state *state);
 	void (*gamma_set)(struct mtk_ddp_comp *comp,
@@ -130,6 +134,15 @@ static inline void mtk_ddp_comp_disable_vblank(struct mtk_ddp_comp *comp)
 		comp->funcs->disable_vblank(comp);
 }
 
+static inline
+unsigned int mtk_ddp_comp_supported_rotations(struct mtk_ddp_comp *comp)
+{
+	if (comp->funcs && comp->funcs->supported_rotations)
+		return comp->funcs->supported_rotations(comp);
+
+	return 0;
+}
+
 static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp)
 {
 	if (comp->funcs && comp->funcs->layer_nr)
@@ -152,6 +165,15 @@ static inline void mtk_ddp_comp_layer_off(struct mtk_ddp_comp *comp,
 		comp->funcs->layer_off(comp, idx);
 }
 
+static inline int mtk_ddp_comp_layer_check(struct mtk_ddp_comp *comp,
+					   unsigned int idx,
+					   struct mtk_plane_state *state)
+{
+	if (comp->funcs && comp->funcs->layer_check)
+		return comp->funcs->layer_check(comp, idx, state);
+	return 0;
+}
+
 static inline void mtk_ddp_comp_layer_config(struct mtk_ddp_comp *comp,
 					     unsigned int idx,
 					     struct mtk_plane_state *state)
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
index ca672f1d140d..b04a3c2b111e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c
@@ -271,7 +271,7 @@ void *mtk_drm_gem_prime_vmap(struct drm_gem_object *obj)
 			       pgprot_writecombine(PAGE_KERNEL));
 
 out:
-	kfree((void *)sgt);
+	kfree(sgt);
 
 	return mtk_gem->kvaddr;
 }
@@ -285,5 +285,5 @@ void mtk_drm_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 
 	vunmap(vaddr);
 	mtk_gem->kvaddr = 0;
-	kfree((void *)mtk_gem->pages);
+	kfree(mtk_gem->pages);
 }
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 584a9ecadce6..3b0cc91c7023 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -20,6 +20,12 @@
 static const u32 formats[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_BGRA8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
 	DRM_FORMAT_RGB565,
 	DRM_FORMAT_UYVY,
 	DRM_FORMAT_YUYV,
@@ -84,6 +90,7 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 {
 	struct drm_framebuffer *fb = state->fb;
 	struct drm_crtc_state *crtc_state;
+	int ret;
 
 	if (!fb)
 		return 0;
@@ -91,6 +98,11 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (!state->crtc)
 		return 0;
 
+	ret = mtk_drm_crtc_plane_check(state->crtc, plane,
+				       to_mtk_plane_state(state));
+	if (ret)
+		return ret;
+
 	crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc);
 	if (IS_ERR(crtc_state))
 		return PTR_ERR(crtc_state);
@@ -132,6 +144,7 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	state->pending.y = plane->state->dst.y1;
 	state->pending.width = drm_rect_width(&plane->state->dst);
 	state->pending.height = drm_rect_height(&plane->state->dst);
+	state->pending.rotation = plane->state->rotation;
 	wmb(); /* Make sure the above parameters are set before update */
 	state->pending.dirty = true;
 }
@@ -154,7 +167,8 @@ static const struct drm_plane_helper_funcs mtk_plane_helper_funcs = {
 };
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
-		   unsigned long possible_crtcs, enum drm_plane_type type)
+		   unsigned long possible_crtcs, enum drm_plane_type type,
+		   unsigned int supported_rotations)
 {
 	int err;
 
@@ -166,6 +180,14 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
 		return err;
 	}
 
+	if (supported_rotations & ~DRM_MODE_ROTATE_0) {
+		err = drm_plane_create_rotation_property(plane,
+							 DRM_MODE_ROTATE_0,
+							 supported_rotations);
+		if (err)
+			DRM_INFO("Create rotation property failed\n");
+	}
+
 	drm_plane_helper_add(plane, &mtk_plane_helper_funcs);
 
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.h b/drivers/gpu/drm/mediatek/mtk_drm_plane.h
index 6f842df722c7..760885e35b27 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.h
@@ -20,6 +20,7 @@ struct mtk_plane_pending_state {
 	unsigned int			y;
 	unsigned int			width;
 	unsigned int			height;
+	unsigned int			rotation;
 	bool				dirty;
 };
 
@@ -35,6 +36,7 @@ to_mtk_plane_state(struct drm_plane_state *state)
 }
 
 int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
-		   unsigned long possible_crtcs, enum drm_plane_type type);
+		   unsigned long possible_crtcs, enum drm_plane_type type,
+		   unsigned int supported_rotations);
 
 #endif
diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index e9160ce39cbb..6deaa7d01654 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -7,6 +7,7 @@ config DRM_MSM
 	depends on OF && COMMON_CLK
 	depends on MMU
 	depends on INTERCONNECT || !INTERCONNECT
+	depends on QCOM_OCMEM || QCOM_OCMEM=n
 	select QCOM_MDT_LOADER if ARCH_QCOM
 	select REGULATOR
 	select DRM_KMS_HELPER
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 5f7e98028eaf..7ad14937fcdf 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -6,10 +6,6 @@
  * Copyright (c) 2014 The Linux Foundation. All rights reserved.
  */
 
-#ifdef CONFIG_MSM_OCMEM
-#  include <mach/ocmem.h>
-#endif
-
 #include "a3xx_gpu.h"
 
 #define A3XX_INT0_MASK \
@@ -195,9 +191,9 @@ static int a3xx_hw_init(struct msm_gpu *gpu)
 		gpu_write(gpu, REG_A3XX_RBBM_GPR0_CTL, 0x00000000);
 
 	/* Set the OCMEM base address for A330, etc */
-	if (a3xx_gpu->ocmem_hdl) {
+	if (a3xx_gpu->ocmem.hdl) {
 		gpu_write(gpu, REG_A3XX_RB_GMEM_BASE_ADDR,
-			(unsigned int)(a3xx_gpu->ocmem_base >> 14));
+			(unsigned int)(a3xx_gpu->ocmem.base >> 14));
 	}
 
 	/* Turn on performance counters: */
@@ -318,10 +314,7 @@ static void a3xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-#ifdef CONFIG_MSM_OCMEM
-	if (a3xx_gpu->ocmem_base)
-		ocmem_free(OCMEM_GRAPHICS, a3xx_gpu->ocmem_hdl);
-#endif
+	adreno_gpu_ocmem_cleanup(&a3xx_gpu->ocmem);
 
 	kfree(a3xx_gpu);
 }
@@ -494,17 +487,10 @@ struct msm_gpu *a3xx_gpu_init(struct drm_device *dev)
 
 	/* if needed, allocate gmem: */
 	if (adreno_is_a330(adreno_gpu)) {
-#ifdef CONFIG_MSM_OCMEM
-		/* TODO this is different/missing upstream: */
-		struct ocmem_buf *ocmem_hdl =
-				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
-
-		a3xx_gpu->ocmem_hdl = ocmem_hdl;
-		a3xx_gpu->ocmem_base = ocmem_hdl->addr;
-		adreno_gpu->gmem = ocmem_hdl->len;
-		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
-				a3xx_gpu->ocmem_base);
-#endif
+		ret = adreno_gpu_ocmem_init(&adreno_gpu->base.pdev->dev,
+					    adreno_gpu, &a3xx_gpu->ocmem);
+		if (ret)
+			goto fail;
 	}
 
 	if (!gpu->aspace) {
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
index 5dc33e5ea53b..c555fb13e0d7 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.h
@@ -19,8 +19,7 @@ struct a3xx_gpu {
 	struct adreno_gpu base;
 
 	/* if OCMEM is used for GMEM: */
-	uint32_t ocmem_base;
-	void *ocmem_hdl;
+	struct adreno_ocmem ocmem;
 };
 #define to_a3xx_gpu(x) container_of(x, struct a3xx_gpu, base)
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index ab2b752566d8..b01388a9e89e 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -2,9 +2,6 @@
 /* Copyright (c) 2014 The Linux Foundation. All rights reserved.
  */
 #include "a4xx_gpu.h"
-#ifdef CONFIG_MSM_OCMEM
-#  include <soc/qcom/ocmem.h>
-#endif
 
 #define A4XX_INT0_MASK \
 	(A4XX_INT0_RBBM_AHB_ERROR |        \
@@ -188,7 +185,7 @@ static int a4xx_hw_init(struct msm_gpu *gpu)
 			(1 << 30) | 0xFFFF);
 
 	gpu_write(gpu, REG_A4XX_RB_GMEM_BASE_ADDR,
-			(unsigned int)(a4xx_gpu->ocmem_base >> 14));
+			(unsigned int)(a4xx_gpu->ocmem.base >> 14));
 
 	/* Turn on performance counters: */
 	gpu_write(gpu, REG_A4XX_RBBM_PERFCTR_CTL, 0x01);
@@ -318,10 +315,7 @@ static void a4xx_destroy(struct msm_gpu *gpu)
 
 	adreno_gpu_cleanup(adreno_gpu);
 
-#ifdef CONFIG_MSM_OCMEM
-	if (a4xx_gpu->ocmem_base)
-		ocmem_free(OCMEM_GRAPHICS, a4xx_gpu->ocmem_hdl);
-#endif
+	adreno_gpu_ocmem_cleanup(&a4xx_gpu->ocmem);
 
 	kfree(a4xx_gpu);
 }
@@ -578,17 +572,10 @@ struct msm_gpu *a4xx_gpu_init(struct drm_device *dev)
 
 	/* if needed, allocate gmem: */
 	if (adreno_is_a4xx(adreno_gpu)) {
-#ifdef CONFIG_MSM_OCMEM
-		/* TODO this is different/missing upstream: */
-		struct ocmem_buf *ocmem_hdl =
-				ocmem_allocate(OCMEM_GRAPHICS, adreno_gpu->gmem);
-
-		a4xx_gpu->ocmem_hdl = ocmem_hdl;
-		a4xx_gpu->ocmem_base = ocmem_hdl->addr;
-		adreno_gpu->gmem = ocmem_hdl->len;
-		DBG("using %dK of OCMEM at 0x%08x", adreno_gpu->gmem / 1024,
-				a4xx_gpu->ocmem_base);
-#endif
+		ret = adreno_gpu_ocmem_init(dev->dev, adreno_gpu,
+					    &a4xx_gpu->ocmem);
+		if (ret)
+			goto fail;
 	}
 
 	if (!gpu->aspace) {
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
index d506311ee240..a01448cba2ea 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.h
@@ -16,8 +16,7 @@ struct a4xx_gpu {
 	struct adreno_gpu base;
 
 	/* if OCMEM is used for GMEM: */
-	uint32_t ocmem_base;
-	void *ocmem_hdl;
+	struct adreno_ocmem ocmem;
 };
 #define to_a4xx_gpu(x) container_of(x, struct a4xx_gpu, base)
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index e9c55d1d6c04..b02e2042547f 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -353,6 +353,9 @@ static int a5xx_me_init(struct msm_gpu *gpu)
 		 * 2D mode 3 draw
 		 */
 		OUT_RING(ring, 0x0000000B);
+	} else if (adreno_is_a510(adreno_gpu)) {
+		/* Workaround for token and syncs */
+		OUT_RING(ring, 0x00000001);
 	} else {
 		/* No workarounds enabled */
 		OUT_RING(ring, 0x00000000);
@@ -568,15 +571,24 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		0x00100000 + adreno_gpu->gmem - 1);
 	gpu_write(gpu, REG_A5XX_UCHE_GMEM_RANGE_MAX_HI, 0x00000000);
 
-	gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
-	if (adreno_is_a530(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
-	if (adreno_is_a540(adreno_gpu))
-		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
-	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
-	gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
-
-	gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL, (0x400 << 11 | 0x300 << 22));
+	if (adreno_is_a510(adreno_gpu)) {
+		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x20);
+		gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x20);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x40000030);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x20100D0A);
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x200 << 11 | 0x200 << 22));
+	} else {
+		gpu_write(gpu, REG_A5XX_CP_MEQ_THRESHOLDS, 0x40);
+		if (adreno_is_a530(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x40);
+		if (adreno_is_a540(adreno_gpu))
+			gpu_write(gpu, REG_A5XX_CP_MERCIU_SIZE, 0x400);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_2, 0x80000060);
+		gpu_write(gpu, REG_A5XX_CP_ROQ_THRESHOLDS_1, 0x40201B16);
+		gpu_write(gpu, REG_A5XX_PC_DBG_ECO_CNTL,
+			  (0x400 << 11 | 0x300 << 22));
+	}
 
 	if (adreno_gpu->info->quirks & ADRENO_QUIRK_TWO_PASS_USE_WFI)
 		gpu_rmw(gpu, REG_A5XX_PC_DBG_ECO_CNTL, 0, (1 << 8));
@@ -589,6 +601,19 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* Enable ME/PFP split notification */
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL1, 0xA6FFFFFF);
 
+	/*
+	 *  In A5x, CCU can send context_done event of a particular context to
+	 *  UCHE which ultimately reaches CP even when there is valid
+	 *  transaction of that context inside CCU. This can let CP to program
+	 *  config registers, which will make the "valid transaction" inside
+	 *  CCU to be interpreted differently. This can cause gpu fault. This
+	 *  bug is fixed in latest A510 revision. To enable this bug fix -
+	 *  bit[11] of RB_DBG_ECO_CNTL need to be set to 0, default is 1
+	 *  (disable). For older A510 version this bit is unused.
+	 */
+	if (adreno_is_a510(adreno_gpu))
+		gpu_rmw(gpu, REG_A5XX_RB_DBG_ECO_CNTL, (1 << 11), 0);
+
 	/* Enable HWCG */
 	a5xx_set_hwcg(gpu, true);
 
@@ -635,7 +660,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	/* UCHE */
 	gpu_write(gpu, REG_A5XX_CP_PROTECT(16), ADRENO_PROTECT_RW(0xE80, 16));
 
-	if (adreno_is_a530(adreno_gpu))
+	if (adreno_is_a530(adreno_gpu) || adreno_is_a510(adreno_gpu))
 		gpu_write(gpu, REG_A5XX_CP_PROTECT(17),
 			ADRENO_PROTECT_RW(0x10000, 0x8000));
 
@@ -679,7 +704,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 
 	a5xx_preempt_hw_init(gpu);
 
-	a5xx_gpmu_ucode_init(gpu);
+	if (!adreno_is_a510(adreno_gpu))
+		a5xx_gpmu_ucode_init(gpu);
 
 	ret = a5xx_ucode_init(gpu);
 	if (ret)
@@ -712,7 +738,8 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	}
 
 	/*
-	 * Try to load a zap shader into the secure world. If successful
+	 * If the chip that we are using does support loading one, then
+	 * try to load a zap shader into the secure world. If successful
 	 * we can use the CP to switch out of secure mode. If not then we
 	 * have no resource but to try to switch ourselves out manually. If we
 	 * guessed wrong then access to the RBBM_SECVID_TRUST_CNTL register will
@@ -1066,6 +1093,7 @@ static void a5xx_dump(struct msm_gpu *gpu)
 
 static int a5xx_pm_resume(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
 	/* Turn on the core power */
@@ -1073,6 +1101,15 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 	if (ret)
 		return ret;
 
+	if (adreno_is_a510(adreno_gpu)) {
+		/* Halt the sp_input_clk at HM level */
+		gpu_write(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0x00000055);
+		a5xx_set_hwcg(gpu, true);
+		/* Turn on sp_input_clk at HM level */
+		gpu_rmw(gpu, REG_A5XX_RBBM_CLOCK_CNTL, 0xff, 0);
+		return 0;
+	}
+
 	/* Turn the RBCCU domain first to limit the chances of voltage droop */
 	gpu_write(gpu, REG_A5XX_GPMU_RBCCU_POWER_CNTL, 0x778000);
 
@@ -1101,9 +1138,17 @@ static int a5xx_pm_resume(struct msm_gpu *gpu)
 
 static int a5xx_pm_suspend(struct msm_gpu *gpu)
 {
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	u32 mask = 0xf;
+
+	/* A510 has 3 XIN ports in VBIF */
+	if (adreno_is_a510(adreno_gpu))
+		mask = 0x7;
+
 	/* Clear the VBIF pipe before shutting down */
-	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0xF);
-	spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) & 0xF) == 0xF);
+	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, mask);
+	spin_until((gpu_read(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL1) &
+				mask) == mask);
 
 	gpu_write(gpu, REG_A5XX_VBIF_XIN_HALT_CTRL0, 0);
 
@@ -1289,7 +1334,7 @@ static void a5xx_gpu_state_destroy(struct kref *kref)
 	kfree(a5xx_state);
 }
 
-int a5xx_gpu_state_put(struct msm_gpu_state *state)
+static int a5xx_gpu_state_put(struct msm_gpu_state *state)
 {
 	if (IS_ERR_OR_NULL(state))
 		return 1;
@@ -1299,8 +1344,8 @@ int a5xx_gpu_state_put(struct msm_gpu_state *state)
 
 
 #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)
+static void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		      struct drm_printer *p)
 {
 	int i, j;
 	u32 pos = 0;
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_power.c b/drivers/gpu/drm/msm/adreno/a5xx_power.c
index a3a06db675ba..321a8061fd32 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_power.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_power.c
@@ -297,6 +297,10 @@ int a5xx_power_init(struct msm_gpu *gpu)
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int ret;
 
+	/* Not all A5xx chips have a GPMU */
+	if (adreno_is_a510(adreno_gpu))
+		return 0;
+
 	/* Set up the limits management */
 	if (adreno_is_a530(adreno_gpu))
 		a530_lm_setup(gpu);
@@ -326,6 +330,9 @@ void a5xx_gpmu_ucode_init(struct msm_gpu *gpu)
 	unsigned int *data, *ptr, *cmds;
 	unsigned int cmds_size;
 
+	if (adreno_is_a510(adreno_gpu))
+		return;
+
 	if (a5xx_gpu->gpmu_bo)
 		return;
 
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
index e686331fa089..691c1a277d91 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
@@ -352,26 +352,26 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
 		cxdbg = ioremap(res->start, resource_size(res));
 
 	if (cxdbg) {
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLT,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLT,
 			A6XX_DBGC_CFG_DBGBUS_CNTLT_SEGT(0xf));
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_CNTLM,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_CNTLM,
 			A6XX_DBGC_CFG_DBGBUS_CNTLM_ENABLE(0xf));
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_0, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_1, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_2, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_IVTL_3, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_0, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_1, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_2, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_IVTL_3, 0);
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_0,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_0,
 			0x76543210);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_BYTEL_1,
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_BYTEL_1,
 			0xFEDCBA98);
 
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_0, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_1, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_2, 0);
-		cxdbg_write(cxdbg, REG_A6XX_DBGC_CFG_DBGBUS_MASKL_3, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_0, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_1, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_2, 0);
+		cxdbg_write(cxdbg, REG_A6XX_CX_DBGC_CFG_DBGBUS_MASKL_3, 0);
 	}
 
 	a6xx_state->debugbus = state_kcalloc(a6xx_state,
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 0888e0df660d..fbbdf86504f5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -115,6 +115,21 @@ static const struct adreno_info gpulist[] = {
 		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
+		.rev   = ADRENO_REV(5, 1, 0, ANY_ID),
+		.revn = 510,
+		.name = "A510",
+		.fw = {
+			[ADRENO_FW_PM4] = "a530_pm4.fw",
+			[ADRENO_FW_PFP] = "a530_pfp.fw",
+		},
+		.gmem = SZ_256K,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
+		.init = a5xx_gpu_init,
+	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
 		.revn = 530,
 		.name = "A530",
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 048c8be426f3..0783e4b5486a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -14,6 +14,7 @@
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
 #include <linux/soc/qcom/mdt_loader.h>
+#include <soc/qcom/ocmem.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
 #include "msm_mmu.h"
@@ -893,6 +894,45 @@ static int adreno_get_pwrlevels(struct device *dev,
 	return 0;
 }
 
+int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
+			  struct adreno_ocmem *adreno_ocmem)
+{
+	struct ocmem_buf *ocmem_hdl;
+	struct ocmem *ocmem;
+
+	ocmem = of_get_ocmem(dev);
+	if (IS_ERR(ocmem)) {
+		if (PTR_ERR(ocmem) == -ENODEV) {
+			/*
+			 * Return success since either the ocmem property was
+			 * not specified in device tree, or ocmem support is
+			 * not compiled into the kernel.
+			 */
+			return 0;
+		}
+
+		return PTR_ERR(ocmem);
+	}
+
+	ocmem_hdl = ocmem_allocate(ocmem, OCMEM_GRAPHICS, adreno_gpu->gmem);
+	if (IS_ERR(ocmem_hdl))
+		return PTR_ERR(ocmem_hdl);
+
+	adreno_ocmem->ocmem = ocmem;
+	adreno_ocmem->base = ocmem_hdl->addr;
+	adreno_ocmem->hdl = ocmem_hdl;
+	adreno_gpu->gmem = ocmem_hdl->len;
+
+	return 0;
+}
+
+void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *adreno_ocmem)
+{
+	if (adreno_ocmem && adreno_ocmem->base)
+		ocmem_free(adreno_ocmem->ocmem, OCMEM_GRAPHICS,
+			   adreno_ocmem->hdl);
+}
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *adreno_gpu,
 		const struct adreno_gpu_funcs *funcs, int nr_rings)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index c7441fb8313e..e71a7570ef72 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -126,6 +126,12 @@ struct adreno_gpu {
 };
 #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base)
 
+struct adreno_ocmem {
+	struct ocmem *ocmem;
+	unsigned long base;
+	void *hdl;
+};
+
 /* platform config data (ie. from DT, or pdata) */
 struct adreno_platform_config {
 	struct adreno_rev rev;
@@ -206,6 +212,11 @@ static inline int adreno_is_a430(struct adreno_gpu *gpu)
        return gpu->revn == 430;
 }
 
+static inline int adreno_is_a510(struct adreno_gpu *gpu)
+{
+	return gpu->revn == 510;
+}
+
 static inline int adreno_is_a530(struct adreno_gpu *gpu)
 {
 	return gpu->revn == 530;
@@ -236,6 +247,10 @@ void adreno_dump(struct msm_gpu *gpu);
 void adreno_wait_ring(struct msm_ringbuffer *ring, uint32_t ndwords);
 struct msm_ringbuffer *adreno_active_ring(struct msm_gpu *gpu);
 
+int adreno_gpu_ocmem_init(struct device *dev, struct adreno_gpu *adreno_gpu,
+			  struct adreno_ocmem *ocmem);
+void adreno_gpu_ocmem_cleanup(struct adreno_ocmem *ocmem);
+
 int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 		struct adreno_gpu *gpu, const struct adreno_gpu_funcs *funcs,
 		int nr_rings);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
index cdbea38b8697..f1bc6a1af7a7 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -55,8 +55,7 @@ static void dpu_core_irq_callback_handler(void *arg, int 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)
+	if (!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,
@@ -73,7 +72,7 @@ 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 ||
+	if (!dpu_kms->hw_intr ||
 			!dpu_kms->irq_obj.enable_counts ||
 			!dpu_kms->irq_obj.irq_counts) {
 		DPU_ERROR("invalid params\n");
@@ -114,7 +113,7 @@ 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) {
+	if (!irq_idxs || !irq_count) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -138,7 +137,7 @@ 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) {
+	if (!dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -169,7 +168,7 @@ 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) {
+	if (!irq_idxs || !irq_count) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -186,7 +185,7 @@ int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
 
 u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear)
 {
-	if (!dpu_kms || !dpu_kms->hw_intr ||
+	if (!dpu_kms->hw_intr ||
 			!dpu_kms->hw_intr->ops.get_interrupt_status)
 		return 0;
 
@@ -205,7 +204,7 @@ int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
 {
 	unsigned long irq_flags;
 
-	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+	if (!dpu_kms->irq_obj.irq_cb_tbl) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -240,7 +239,7 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
 {
 	unsigned long irq_flags;
 
-	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+	if (!dpu_kms->irq_obj.irq_cb_tbl) {
 		DPU_ERROR("invalid params\n");
 		return -EINVAL;
 	}
@@ -274,8 +273,7 @@ int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
 
 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)
+	if (!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);
@@ -283,8 +281,7 @@ static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
 
 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)
+	if (!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);
@@ -343,18 +340,8 @@ void dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
 
 void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 {
-	struct msm_drm_private *priv;
 	int i;
 
-	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);
@@ -379,18 +366,8 @@ void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
 
 void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
 {
-	struct msm_drm_private *priv;
 	int i;
 
-	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]) ||
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
index 09a49b59bb5b..11f2bebe3869 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -32,18 +32,7 @@ enum dpu_perf_mode {
 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);
 }
 
@@ -116,7 +105,7 @@ int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid parameters\n");
 		return 0;
 	}
@@ -215,7 +204,6 @@ static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
 void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 {
 	struct dpu_crtc *dpu_crtc;
-	struct dpu_crtc_state *dpu_cstate;
 	struct dpu_kms *kms;
 
 	if (!crtc) {
@@ -224,13 +212,12 @@ void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!kms->catalog) {
 		DPU_ERROR("invalid kms\n");
 		return;
 	}
 
 	dpu_crtc = to_dpu_crtc(crtc);
-	dpu_cstate = to_dpu_crtc_state(crtc->state);
 
 	if (atomic_dec_return(&kms->bandwidth_ref) > 0)
 		return;
@@ -287,7 +274,6 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	u64 clk_rate = 0;
 	struct dpu_crtc *dpu_crtc;
 	struct dpu_crtc_state *dpu_cstate;
-	struct msm_drm_private *priv;
 	struct dpu_kms *kms;
 	int ret;
 
@@ -297,11 +283,10 @@ int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
 	}
 
 	kms = _dpu_crtc_get_kms(crtc);
-	if (!kms || !kms->catalog) {
+	if (!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);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index ce59adff06aa..f197dce54576 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -266,11 +266,20 @@ enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
 {
 	struct drm_encoder *encoder;
 
-	if (!crtc || !crtc->dev) {
+	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
 		return INTF_MODE_NONE;
 	}
 
+	/*
+	 * TODO: This function is called from dpu debugfs and as part of atomic
+	 * check. When called from debugfs, the crtc->mutex must be held to
+	 * read crtc->state. However reading crtc->state from atomic check isn't
+	 * allowed (unless you have a good reason, a big comment, and a deep
+	 * understanding of how the atomic/modeset locks work (<- and this is
+	 * probably not possible)). So we'll keep the WARN_ON here for now, but
+	 * really we need to figure out a better way to track our operating mode
+	 */
 	WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
 
 	/* TODO: Returns the first INTF_MODE, could there be multiple values? */
@@ -694,7 +703,7 @@ static void dpu_crtc_disable(struct drm_crtc *crtc,
 	unsigned long flags;
 	bool release_bandwidth = false;
 
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
+	if (!crtc || !crtc->state) {
 		DPU_ERROR("invalid crtc\n");
 		return;
 	}
@@ -766,7 +775,7 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 	struct msm_drm_private *priv;
 	bool request_bandwidth;
 
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+	if (!crtc) {
 		DPU_ERROR("invalid crtc\n");
 		return;
 	}
@@ -1288,13 +1297,8 @@ 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);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index d82ea994063f..f96e142c4361 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -645,11 +645,6 @@ static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
 	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");
@@ -735,8 +730,7 @@ static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
 	struct msm_drm_private *priv;
 	bool is_vid_mode = false;
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private ||
-			!drm_enc->crtc) {
+	if (!drm_enc || !drm_enc->dev || !drm_enc->crtc) {
 		DPU_ERROR("invalid parameters\n");
 		return -EINVAL;
 	}
@@ -1092,17 +1086,13 @@ static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
 	struct msm_drm_private *priv;
 	struct dpu_kms *dpu_kms;
 
-	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc || !drm_enc->dev) {
 		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) {
@@ -1184,7 +1174,6 @@ 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) {
@@ -1193,9 +1182,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	} 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;
 	}
 
 	dpu_enc = to_dpu_encoder_virt(drm_enc);
@@ -1204,8 +1190,6 @@ static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
 	mutex_lock(&dpu_enc->enc_lock);
 	dpu_enc->enabled = false;
 
-	mode = &drm_enc->crtc->state->adjusted_mode;
-
 	priv = drm_enc->dev->dev_private;
 	dpu_kms = to_dpu_kms(priv->kms);
 
@@ -1734,8 +1718,7 @@ static void dpu_encoder_vsync_event_handler(struct timer_list *t)
 	struct msm_drm_private *priv;
 	struct msm_drm_thread *event_thread;
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private ||
-			!drm_enc->crtc) {
+	if (!drm_enc->dev || !drm_enc->crtc) {
 		DPU_ERROR("invalid parameters\n");
 		return;
 	}
@@ -1914,8 +1897,6 @@ static int _dpu_encoder_debugfs_status_open(struct inode *inode,
 static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
-	struct msm_drm_private *priv;
-	struct dpu_kms *dpu_kms;
 	int i;
 
 	static const struct file_operations debugfs_status_fops = {
@@ -1927,14 +1908,11 @@ static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
 
 	char name[DPU_NAME_SIZE];
 
-	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+	if (!drm_enc->dev) {
 		DPU_ERROR("invalid encoder or kms\n");
 		return -EINVAL;
 	}
 
-	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 */
@@ -2042,9 +2020,8 @@ static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
 	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);
+	if (!dpu_enc) {
+		DPU_ERROR("invalid arg(s), enc %d\n", dpu_enc != 0);
 		return -EINVAL;
 	}
 
@@ -2133,14 +2110,12 @@ 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) {
+	if (!drm_enc->dev) {
 		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",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 2923b63d95fe..047960949fbb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -124,13 +124,11 @@ static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
 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);
 
@@ -316,13 +314,9 @@ end:
 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));
@@ -355,7 +349,6 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	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) {
@@ -373,11 +366,6 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	}
 
 	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;
@@ -650,13 +638,10 @@ 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",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index b9c84fb4d4a1..3123ef873cdf 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -374,7 +374,7 @@ static void dpu_encoder_phys_vid_mode_set(
 		struct drm_display_mode *mode,
 		struct drm_display_mode *adj_mode)
 {
-	if (!phys_enc || !phys_enc->dpu_kms) {
+	if (!phys_enc) {
 		DPU_ERROR("invalid encoder/kms\n");
 		return;
 	}
@@ -566,16 +566,13 @@ static void dpu_encoder_phys_vid_prepare_for_kickoff(
 
 static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
 {
-	struct msm_drm_private *priv;
 	unsigned long lock_flags;
 	int ret;
 
-	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
-			!phys_enc->parent->dev->dev_private) {
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev) {
 		DPU_ERROR("invalid encoder/device\n");
 		return;
 	}
-	priv = phys_enc->parent->dev->dev_private;
 
 	if (!phys_enc->hw_intf || !phys_enc->hw_ctl) {
 		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 58b0485dc375..6c92f0fbeac9 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -30,10 +30,6 @@
 #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
@@ -68,16 +64,14 @@ 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->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+	if (!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);
@@ -153,13 +147,7 @@ static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
 		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 */
@@ -280,7 +268,6 @@ 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_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
@@ -292,10 +279,6 @@ static void dpu_kms_prepare_commit(struct msm_kms *kms,
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
 
-	if (!dev || !dev->dev_private)
-		return;
-	priv = dev->dev_private;
-
 	/* Call prepare_commit for all affected encoders */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
 		drm_for_each_encoder_mask(encoder, crtc->dev,
@@ -333,7 +316,6 @@ void dpu_kms_encoder_enable(struct drm_encoder *encoder)
 	if (funcs && funcs->commit)
 		funcs->commit(encoder);
 
-	WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
 	drm_for_each_crtc(crtc, dev) {
 		if (!(crtc->state->encoder_mask & drm_encoder_mask(encoder)))
 			continue;
@@ -464,16 +446,6 @@ 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++)
@@ -505,7 +477,6 @@ static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
 
 	int primary_planes_idx = 0, cursor_planes_idx = 0, i, ret;
 	int max_crtc_count;
-
 	dev = dpu_kms->dev;
 	priv = dev->dev_private;
 	catalog = dpu_kms->catalog;
@@ -585,8 +556,6 @@ static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
 	int i;
 
 	dev = dpu_kms->dev;
-	if (!dev)
-		return;
 
 	if (dpu_kms->hw_intr)
 		dpu_hw_intr_destroy(dpu_kms->hw_intr);
@@ -725,8 +694,7 @@ static void _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
 
 	mmu = dpu_kms->base.aspace->mmu;
 
-	mmu->funcs->detach(mmu, (const char **)iommu_ports,
-			ARRAY_SIZE(iommu_ports));
+	mmu->funcs->detach(mmu);
 	msm_gem_address_space_put(dpu_kms->base.aspace);
 
 	dpu_kms->base.aspace = NULL;
@@ -752,8 +720,7 @@ static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
 		return PTR_ERR(aspace);
 	}
 
-	ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-			ARRAY_SIZE(iommu_ports));
+	ret = aspace->mmu->funcs->attach(aspace->mmu);
 	if (ret) {
 		DPU_ERROR("failed to attach iommu %d\n", ret);
 		msm_gem_address_space_put(aspace);
@@ -803,16 +770,7 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 
 	dpu_kms = to_dpu_kms(kms);
 	dev = dpu_kms->dev;
-	if (!dev) {
-		DPU_ERROR("invalid device\n");
-		return rc;
-	}
-
 	priv = dev->dev_private;
-	if (!priv) {
-		DPU_ERROR("invalid private data\n");
-		return rc;
-	}
 
 	atomic_set(&dpu_kms->bandwidth_ref, 0);
 
@@ -974,7 +932,7 @@ struct msm_kms *dpu_kms_init(struct drm_device *dev)
 	struct dpu_kms *dpu_kms;
 	int irq;
 
-	if (!dev || !dev->dev_private) {
+	if (!dev) {
 		DPU_ERROR("drm device node invalid\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -1064,11 +1022,6 @@ static int __maybe_unused dpu_runtime_suspend(struct device *dev)
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
-	if (!ddev) {
-		DPU_ERROR("invalid drm_device\n");
-		return rc;
-	}
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
 	if (rc)
 		DPU_ERROR("clock disable failed rc:%d\n", rc);
@@ -1086,11 +1039,6 @@ static int __maybe_unused dpu_runtime_resume(struct device *dev)
 	struct dss_module_power *mp = &dpu_kms->mp;
 
 	ddev = dpu_kms->dev;
-	if (!ddev) {
-		DPU_ERROR("invalid drm_device\n");
-		return rc;
-	}
-
 	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
 	if (rc) {
 		DPU_ERROR("clock enable failed rc:%d\n", rc);
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index 959d03e007fa..c6169e7df19d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -139,10 +139,6 @@ struct vsync_info {
 
 #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)
-
 /**
  * Debugfs functions - extra helper functions for debugfs support
  *
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
index 8d24b79fd400..991f4c8f8a12 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -154,10 +154,6 @@ void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
 	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++) {
@@ -214,7 +210,7 @@ void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
 	const struct dpu_vbif_qos_tbl *qos_tbl;
 	int i;
 
-	if (!dpu_kms || !params || !dpu_kms->hw_mdp) {
+	if (!params || !dpu_kms->hw_mdp) {
 		DPU_ERROR("invalid arguments\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 50711ccc8691..dda05436f716 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -157,10 +157,6 @@ static long mdp4_round_pixclk(struct msm_kms *kms, unsigned long rate,
 	}
 }
 
-static const char * const iommu_ports[] = {
-	"mdp_port0_cb0", "mdp_port1_cb0",
-};
-
 static void mdp4_destroy(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
@@ -172,8 +168,7 @@ static void mdp4_destroy(struct msm_kms *kms)
 	drm_gem_object_put_unlocked(mdp4_kms->blank_cursor_bo);
 
 	if (aspace) {
-		aspace->mmu->funcs->detach(aspace->mmu,
-				iommu_ports, ARRAY_SIZE(iommu_ports));
+		aspace->mmu->funcs->detach(aspace->mmu);
 		msm_gem_address_space_put(aspace);
 	}
 
@@ -524,8 +519,7 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 
 		kms->aspace = aspace;
 
-		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
+		ret = aspace->mmu->funcs->attach(aspace->mmu);
 		if (ret)
 			goto fail;
 	} else {
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
index f6e71ff539ca..1f48f64539a2 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_cfg.c
@@ -14,7 +14,7 @@ struct mdp5_cfg_handler {
 /* mdp5_cfg must be exposed (used in mdp5.xml.h) */
 const struct mdp5_cfg_hw *mdp5_cfg = NULL;
 
-const struct mdp5_cfg_hw msm8x74v1_config = {
+static const struct mdp5_cfg_hw msm8x74v1_config = {
 	.name = "msm8x74v1",
 	.mdp = {
 		.count = 1,
@@ -98,7 +98,7 @@ const struct mdp5_cfg_hw msm8x74v1_config = {
 	.max_clk = 200000000,
 };
 
-const struct mdp5_cfg_hw msm8x74v2_config = {
+static const struct mdp5_cfg_hw msm8x74v2_config = {
 	.name = "msm8x74",
 	.mdp = {
 		.count = 1,
@@ -180,7 +180,7 @@ const struct mdp5_cfg_hw msm8x74v2_config = {
 	.max_clk = 200000000,
 };
 
-const struct mdp5_cfg_hw apq8084_config = {
+static const struct mdp5_cfg_hw apq8084_config = {
 	.name = "apq8084",
 	.mdp = {
 		.count = 1,
@@ -275,7 +275,7 @@ const struct mdp5_cfg_hw apq8084_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8x16_config = {
+static const struct mdp5_cfg_hw msm8x16_config = {
 	.name = "msm8x16",
 	.mdp = {
 		.count = 1,
@@ -342,7 +342,7 @@ const struct mdp5_cfg_hw msm8x16_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8x94_config = {
+static const struct mdp5_cfg_hw msm8x94_config = {
 	.name = "msm8x94",
 	.mdp = {
 		.count = 1,
@@ -437,7 +437,7 @@ const struct mdp5_cfg_hw msm8x94_config = {
 	.max_clk = 400000000,
 };
 
-const struct mdp5_cfg_hw msm8x96_config = {
+static const struct mdp5_cfg_hw msm8x96_config = {
 	.name = "msm8x96",
 	.mdp = {
 		.count = 1,
@@ -545,7 +545,104 @@ const struct mdp5_cfg_hw msm8x96_config = {
 	.max_clk = 412500000,
 };
 
-const struct mdp5_cfg_hw msm8917_config = {
+const struct mdp5_cfg_hw msm8x76_config = {
+	.name = "msm8x76",
+	.mdp = {
+		.count = 1,
+		.caps = MDP_CAP_SMP |
+			MDP_CAP_DSC |
+			MDP_CAP_SRC_SPLIT |
+			0,
+	},
+	.ctl = {
+		.count = 3,
+		.base = { 0x01000, 0x01200, 0x01400 },
+		.flush_hw_mask = 0xffffffff,
+	},
+	.smp = {
+		.mmb_count = 10,
+		.mmb_size = 10240,
+		.clients = {
+			[SSPP_VIG0] = 1, [SSPP_VIG1] = 9,
+			[SSPP_DMA0] = 4,
+			[SSPP_RGB0] = 7, [SSPP_RGB1] = 8,
+		},
+	},
+	.pipe_vig = {
+		.count = 2,
+		.base = { 0x04000, 0x06000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SCALE	|
+			MDP_PIPE_CAP_CSC	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_rgb = {
+		.count = 2,
+		.base = { 0x14000, 0x16000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_DECIMATION	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_dma = {
+		.count = 1,
+		.base = { 0x24000 },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			0,
+	},
+	.pipe_cursor = {
+		.count = 1,
+		.base = { 0x440DC },
+		.caps = MDP_PIPE_CAP_HFLIP	|
+			MDP_PIPE_CAP_VFLIP	|
+			MDP_PIPE_CAP_SW_PIX_EXT	|
+			MDP_PIPE_CAP_CURSOR	|
+			0,
+	},
+	.lm = {
+		.count = 2,
+		.base = { 0x44000, 0x45000 },
+		.instances = {
+				{ .id = 0, .pp = 0, .dspp = 0,
+				  .caps = MDP_LM_CAP_DISPLAY, },
+				{ .id = 1, .pp = -1, .dspp = -1,
+				  .caps = MDP_LM_CAP_WB },
+			     },
+		.nb_stages = 8,
+		.max_width = 2560,
+		.max_height = 0xFFFF,
+	},
+	.dspp = {
+		.count = 1,
+		.base = { 0x54000 },
+
+	},
+	.pp = {
+		.count = 3,
+		.base = { 0x70000, 0x70800, 0x72000 },
+	},
+	.dsc = {
+		.count = 2,
+		.base = { 0x80000, 0x80400 },
+	},
+	.intf = {
+		.base = { 0x6a000, 0x6a800, 0x6b000 },
+		.connect = {
+			[0] = INTF_DISABLED,
+			[1] = INTF_DSI,
+			[2] = INTF_DSI,
+		},
+	},
+	.max_clk = 360000000,
+};
+
+static const struct mdp5_cfg_hw msm8917_config = {
 	.name = "msm8917",
 	.mdp = {
 		.count = 1,
@@ -630,7 +727,7 @@ const struct mdp5_cfg_hw msm8917_config = {
 	.max_clk = 320000000,
 };
 
-const struct mdp5_cfg_hw msm8998_config = {
+static const struct mdp5_cfg_hw msm8998_config = {
 	.name = "msm8998",
 	.mdp = {
 		.count = 1,
@@ -745,6 +842,7 @@ static const struct mdp5_cfg_handler cfg_handlers_v1[] = {
 	{ .revision = 6, .config = { .hw = &msm8x16_config } },
 	{ .revision = 9, .config = { .hw = &msm8x94_config } },
 	{ .revision = 7, .config = { .hw = &msm8x96_config } },
+	{ .revision = 11, .config = { .hw = &msm8x76_config } },
 	{ .revision = 15, .config = { .hw = &msm8917_config } },
 };
 
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index eb0b4b7dc7cc..05cc04f729d6 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -214,7 +214,6 @@ static void blend_setup(struct drm_crtc *crtc)
 	struct mdp5_pipeline *pipeline = &mdp5_cstate->pipeline;
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	struct drm_plane *plane;
-	const struct mdp5_cfg_hw *hw_cfg;
 	struct mdp5_plane_state *pstate, *pstates[STAGE_MAX + 1] = {NULL};
 	const struct mdp_format *format;
 	struct mdp5_hw_mixer *mixer = pipeline->mixer;
@@ -232,8 +231,6 @@ static void blend_setup(struct drm_crtc *crtc)
 	u32 val;
 #define blender(stage)	((stage) - STAGE0)
 
-	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-
 	spin_lock_irqsave(&mdp5_crtc->lm_lock, flags);
 
 	/* ctl could be released already when we are shutting down: */
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 91cd76a2bab1..e43ecd4be10a 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -19,10 +19,6 @@
 #include "msm_mmu.h"
 #include "mdp5_kms.h"
 
-static const char *iommu_ports[] = {
-		"mdp_0",
-};
-
 static int mdp5_hw_init(struct msm_kms *kms)
 {
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
@@ -233,8 +229,7 @@ static void mdp5_kms_destroy(struct msm_kms *kms)
 		mdp5_pipe_destroy(mdp5_kms->hwpipes[i]);
 
 	if (aspace) {
-		aspace->mmu->funcs->detach(aspace->mmu,
-				iommu_ports, ARRAY_SIZE(iommu_ports));
+		aspace->mmu->funcs->detach(aspace->mmu);
 		msm_gem_address_space_put(aspace);
 	}
 }
@@ -314,6 +309,10 @@ int mdp5_disable(struct mdp5_kms *mdp5_kms)
 	mdp5_kms->enable_count--;
 	WARN_ON(mdp5_kms->enable_count < 0);
 
+	if (mdp5_kms->tbu_rt_clk)
+		clk_disable_unprepare(mdp5_kms->tbu_rt_clk);
+	if (mdp5_kms->tbu_clk)
+		clk_disable_unprepare(mdp5_kms->tbu_clk);
 	clk_disable_unprepare(mdp5_kms->ahb_clk);
 	clk_disable_unprepare(mdp5_kms->axi_clk);
 	clk_disable_unprepare(mdp5_kms->core_clk);
@@ -334,6 +333,10 @@ int mdp5_enable(struct mdp5_kms *mdp5_kms)
 	clk_prepare_enable(mdp5_kms->core_clk);
 	if (mdp5_kms->lut_clk)
 		clk_prepare_enable(mdp5_kms->lut_clk);
+	if (mdp5_kms->tbu_clk)
+		clk_prepare_enable(mdp5_kms->tbu_clk);
+	if (mdp5_kms->tbu_rt_clk)
+		clk_prepare_enable(mdp5_kms->tbu_rt_clk);
 
 	return 0;
 }
@@ -466,14 +469,11 @@ static int modeset_init(struct mdp5_kms *mdp5_kms)
 {
 	struct drm_device *dev = mdp5_kms->dev;
 	struct msm_drm_private *priv = dev->dev_private;
-	const struct mdp5_cfg_hw *hw_cfg;
 	unsigned int num_crtcs;
 	int i, ret, pi = 0, ci = 0;
 	struct drm_plane *primary[MAX_BASES] = { NULL };
 	struct drm_plane *cursor[MAX_BASES] = { NULL };
 
-	hw_cfg = mdp5_cfg_get_hw_config(mdp5_kms->cfg);
-
 	/*
 	 * Construct encoders and modeset initialize connector devices
 	 * for each external display interface.
@@ -737,8 +737,7 @@ struct msm_kms *mdp5_kms_init(struct drm_device *dev)
 
 		kms->aspace = aspace;
 
-		ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
-				ARRAY_SIZE(iommu_ports));
+		ret = aspace->mmu->funcs->attach(aspace->mmu);
 		if (ret) {
 			DRM_DEV_ERROR(&pdev->dev, "failed to attach iommu: %d\n",
 				ret);
@@ -974,6 +973,8 @@ static int mdp5_init(struct platform_device *pdev, struct drm_device *dev)
 
 	/* optional clocks: */
 	get_clk(pdev, &mdp5_kms->lut_clk, "lut", false);
+	get_clk(pdev, &mdp5_kms->tbu_clk, "tbu", false);
+	get_clk(pdev, &mdp5_kms->tbu_rt_clk, "tbu_rt", false);
 
 	/* we need to set a default rate before enabling.  Set a safe
 	 * rate first, then figure out hw revision, and then set a
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
index d1bf4fdfc815..128866742593 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.h
@@ -53,6 +53,8 @@ struct mdp5_kms {
 	struct clk *ahb_clk;
 	struct clk *core_clk;
 	struct clk *lut_clk;
+	struct clk *tbu_clk;
+	struct clk *tbu_rt_clk;
 	struct clk *vsync_clk;
 
 	/*
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
index b31cfb554fa2..d7fa2c49e741 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
@@ -121,7 +121,6 @@ uint32_t mdp5_smp_calculate(struct mdp5_smp *smp,
 	struct mdp5_kms *mdp5_kms = get_kms(smp);
 	int rev = mdp5_cfg_get_hw_rev(mdp5_kms->cfg);
 	int i, hsub, nplanes, nlines;
-	u32 fmt = format->base.pixel_format;
 	uint32_t blkcfg = 0;
 
 	nplanes = info->num_planes;
@@ -135,7 +134,6 @@ uint32_t mdp5_smp_calculate(struct mdp5_smp *smp,
 	 * them together, writes to SMP using a single client.
 	 */
 	if ((rev > 0) && (format->chroma_sample > CHROMA_FULL)) {
-		fmt = DRM_FORMAT_NV24;
 		nplanes = 2;
 
 		/* if decimation is enabled, HW decimates less on the
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index b7b7c1a9164a..86ad3fdf207d 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -66,6 +66,26 @@ static const struct msm_dsi_config msm8916_dsi_cfg = {
 	.num_dsi = 1,
 };
 
+static const char * const dsi_8976_bus_clk_names[] = {
+	"mdp_core", "iface", "bus",
+};
+
+static const struct msm_dsi_config msm8976_dsi_cfg = {
+	.io_offset = DSI_6G_REG_SHIFT,
+	.reg_cfg = {
+		.num = 3,
+		.regs = {
+			{"gdsc", -1, -1},
+			{"vdda", 100000, 100},	/* 1.2 V */
+			{"vddio", 100000, 100},	/* 1.8 V */
+		},
+	},
+	.bus_clk_names = dsi_8976_bus_clk_names,
+	.num_bus_clks = ARRAY_SIZE(dsi_8976_bus_clk_names),
+	.io_start = { 0x1a94000, 0x1a96000 },
+	.num_dsi = 2,
+};
+
 static const struct msm_dsi_config msm8994_dsi_cfg = {
 	.io_offset = DSI_6G_REG_SHIFT,
 	.reg_cfg = {
@@ -147,7 +167,7 @@ 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 = {
+static const 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,
@@ -158,7 +178,7 @@ const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
 	.calc_clk_rate = dsi_calc_clk_rate_v2,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+static const 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,
@@ -169,7 +189,7 @@ const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
 	.calc_clk_rate = dsi_calc_clk_rate_6g,
 };
 
-const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+static const 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,
@@ -197,6 +217,8 @@ static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
 		&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_V1_4_2,
+		&msm8976_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_0,
 		&msm8998_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index e2b7a7dfbe49..50a37ceb6a25 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -17,6 +17,7 @@
 #define MSM_DSI_6G_VER_MINOR_V1_3	0x10030000
 #define MSM_DSI_6G_VER_MINOR_V1_3_1	0x10030001
 #define MSM_DSI_6G_VER_MINOR_V1_4_1	0x10040001
+#define MSM_DSI_6G_VER_MINOR_V1_4_2	0x10040002
 #define MSM_DSI_6G_VER_MINOR_V2_2_0	0x20000000
 #define MSM_DSI_6G_VER_MINOR_V2_2_1	0x20020001
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 1e7b1be25bb0..458cec82ae13 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1293,14 +1293,13 @@ static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 static int dsi_cmd_dma_rx(struct msm_dsi_host *msm_host,
 			u8 *buf, int rx_byte, int pkt_size)
 {
-	u32 *lp, *temp, data;
+	u32 *temp, data;
 	int i, j = 0, cnt;
 	u32 read_cnt;
 	u8 reg[16];
 	int repeated_bytes = 0;
 	int buf_offset = buf - msm_host->rx_buf;
 
-	lp = (u32 *)buf;
 	temp = (u32 *)reg;
 	cnt = (rx_byte + 3) >> 2;
 	if (cnt > 4)
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
index 3522863a4984..b0cfa67d2a57 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c
@@ -145,7 +145,7 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 {
 	const unsigned long bit_rate = clk_req->bitclk_rate;
 	const unsigned long esc_rate = clk_req->escclk_rate;
-	s32 ui, ui_x8, lpx;
+	s32 ui, ui_x8;
 	s32 tmax, tmin;
 	s32 pcnt0 = 50;
 	s32 pcnt1 = 50;
@@ -175,7 +175,6 @@ int msm_dsi_dphy_timing_calc_v2(struct msm_dsi_dphy_timing *timing,
 
 	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
 	ui_x8 = ui << 3;
-	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
 
 	temp = S_DIV_ROUND_UP(38 * coeff - val_ckln * ui, ui_x8);
 	tmin = max_t(s32, temp, 0);
@@ -262,7 +261,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 {
 	const unsigned long bit_rate = clk_req->bitclk_rate;
 	const unsigned long esc_rate = clk_req->escclk_rate;
-	s32 ui, ui_x8, lpx;
+	s32 ui, ui_x8;
 	s32 tmax, tmin;
 	s32 pcnt0 = 50;
 	s32 pcnt1 = 50;
@@ -284,7 +283,6 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing,
 
 	ui = mult_frac(NSEC_PER_MSEC, coeff, bit_rate / 1000);
 	ui_x8 = ui << 3;
-	lpx = mult_frac(NSEC_PER_MSEC, coeff, esc_rate / 1000);
 
 	temp = S_DIV_ROUND_UP(38 * coeff, ui_x8);
 	tmin = max_t(s32, temp, 0);
@@ -485,6 +483,8 @@ static const struct of_device_id dsi_phy_dt_match[] = {
 #ifdef CONFIG_DRM_MSM_DSI_28NM_PHY
 	{ .compatible = "qcom,dsi-phy-28nm-hpm",
 	  .data = &dsi_phy_28nm_hpm_cfgs },
+	{ .compatible = "qcom,dsi-phy-28nm-hpm-fam-b",
+	  .data = &dsi_phy_28nm_hpm_famb_cfgs },
 	{ .compatible = "qcom,dsi-phy-28nm-lp",
 	  .data = &dsi_phy_28nm_lp_cfgs },
 #endif
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
index c4069ce6afe6..24b294ed3059 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.h
@@ -40,6 +40,7 @@ struct msm_dsi_phy_cfg {
 };
 
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs;
+extern const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_20nm_cfgs;
 extern const struct msm_dsi_phy_cfg dsi_phy_28nm_8960_cfgs;
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
index b3f678f6c2aa..c3c580cfd8b1 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_28nm.c
@@ -39,15 +39,10 @@ static void dsi_28nm_dphy_set_timing(struct msm_dsi_phy *phy,
 		DSI_28nm_PHY_TIMING_CTRL_11_TRIG3_CMD(0));
 }
 
-static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
+static void dsi_28nm_phy_regulator_enable_dcdc(struct msm_dsi_phy *phy)
 {
 	void __iomem *base = phy->reg_base;
 
-	if (!enable) {
-		dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
-		return;
-	}
-
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x0);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 1);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_5, 0);
@@ -56,6 +51,39 @@ static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x9);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x7);
 	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20);
+	dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x00);
+}
+
+static void dsi_28nm_phy_regulator_enable_ldo(struct msm_dsi_phy *phy)
+{
+	void __iomem *base = phy->reg_base;
+
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_0, 0x0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_5, 0x7);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_3, 0);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_2, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_1, 0x1);
+	dsi_phy_write(base + REG_DSI_28nm_PHY_REGULATOR_CTRL_4, 0x20);
+
+	if (phy->cfg->type == MSM_DSI_PHY_28NM_LP)
+		dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x05);
+	else
+		dsi_phy_write(phy->base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x0d);
+}
+
+static void dsi_28nm_phy_regulator_ctrl(struct msm_dsi_phy *phy, bool enable)
+{
+	if (!enable) {
+		dsi_phy_write(phy->reg_base +
+			      REG_DSI_28nm_PHY_REGULATOR_CAL_PWR_CFG, 0);
+		return;
+	}
+
+	if (phy->regulator_ldo_mode)
+		dsi_28nm_phy_regulator_enable_ldo(phy);
+	else
+		dsi_28nm_phy_regulator_enable_dcdc(phy);
 }
 
 static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
@@ -77,8 +105,6 @@ static int dsi_28nm_phy_enable(struct msm_dsi_phy *phy, int src_pll_id,
 
 	dsi_28nm_phy_regulator_ctrl(phy, true);
 
-	dsi_phy_write(base + REG_DSI_28nm_PHY_LDO_CNTRL, 0x00);
-
 	dsi_28nm_dphy_set_timing(phy, timing);
 
 	dsi_phy_write(base + REG_DSI_28nm_PHY_CTRL_1, 0x00);
@@ -142,6 +168,24 @@ const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_cfgs = {
 	.num_dsi_phy = 2,
 };
 
+const struct msm_dsi_phy_cfg dsi_phy_28nm_hpm_famb_cfgs = {
+	.type = MSM_DSI_PHY_28NM_HPM,
+	.src_pll_truthtable = { {true, true}, {false, true} },
+	.reg_cfg = {
+		.num = 1,
+		.regs = {
+			{"vddio", 100000, 100},
+		},
+	},
+	.ops = {
+		.enable = dsi_28nm_phy_enable,
+		.disable = dsi_28nm_phy_disable,
+		.init = msm_dsi_phy_init_common,
+	},
+	.io_start = { 0x1a94400, 0x1a96400 },
+	.num_dsi_phy = 2,
+};
+
 const struct msm_dsi_phy_cfg dsi_phy_28nm_lp_cfgs = {
 	.type = MSM_DSI_PHY_28NM_LP,
 	.src_pll_truthtable = { {true, true}, {true, true} },
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
index 1697e61f9c2f..8a38d4b95102 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_phy.c
@@ -29,8 +29,12 @@ static int msm_hdmi_phy_resource_init(struct hdmi_phy *phy)
 		reg = devm_regulator_get(dev, cfg->reg_names[i]);
 		if (IS_ERR(reg)) {
 			ret = PTR_ERR(reg);
-			DRM_DEV_ERROR(dev, "failed to get phy regulator: %s (%d)\n",
-				cfg->reg_names[i], ret);
+			if (ret != -EPROBE_DEFER) {
+				DRM_DEV_ERROR(dev,
+					      "failed to get phy regulator: %s (%d)\n",
+					      cfg->reg_names[i], ret);
+			}
+
 			return ret;
 		}
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 6be879578140..1c74381a4fc9 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -47,12 +47,8 @@ static int msm_gpu_release(struct inode *inode, struct file *file)
 	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;
 
+	mutex_lock(&show_priv->dev->struct_mutex);
 	gpu->funcs->gpu_state_put(show_priv->state);
 	mutex_unlock(&show_priv->dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index a052364a5d74..18f3a5c53ffb 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -16,6 +16,7 @@
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
 #include <linux/devcoredump.h>
+#include <linux/sched/task.h>
 
 /*
  * Power Management:
@@ -838,7 +839,7 @@ msm_gpu_create_address_space(struct msm_gpu *gpu, struct platform_device *pdev,
 		return ERR_CAST(aspace);
 	}
 
-	ret = aspace->mmu->funcs->attach(aspace->mmu, NULL, 0);
+	ret = aspace->mmu->funcs->attach(aspace->mmu);
 	if (ret) {
 		msm_gem_address_space_put(aspace);
 		return ERR_PTR(ret);
@@ -995,8 +996,7 @@ void msm_gpu_cleanup(struct msm_gpu *gpu)
 	msm_gem_kernel_put(gpu->memptrs_bo, gpu->aspace, false);
 
 	if (!IS_ERR_OR_NULL(gpu->aspace)) {
-		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu,
-			NULL, 0);
+		gpu->aspace->mmu->funcs->detach(gpu->aspace->mmu);
 		msm_gem_address_space_put(gpu->aspace);
 	}
 }
diff --git a/drivers/gpu/drm/msm/msm_gpummu.c b/drivers/gpu/drm/msm/msm_gpummu.c
index 34f643a0c28a..34980d8eb7ad 100644
--- a/drivers/gpu/drm/msm/msm_gpummu.c
+++ b/drivers/gpu/drm/msm/msm_gpummu.c
@@ -21,14 +21,12 @@ struct msm_gpummu {
 #define GPUMMU_PAGE_SIZE SZ_4K
 #define TABLE_SIZE (sizeof(uint32_t) * GPUMMU_VA_RANGE / GPUMMU_PAGE_SIZE)
 
-static int msm_gpummu_attach(struct msm_mmu *mmu, const char * const *names,
-		int cnt)
+static int msm_gpummu_attach(struct msm_mmu *mmu)
 {
 	return 0;
 }
 
-static void msm_gpummu_detach(struct msm_mmu *mmu, const char * const *names,
-		int cnt)
+static void msm_gpummu_detach(struct msm_mmu *mmu)
 {
 }
 
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 8c95c31e2b12..ad58cfe5998e 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -23,16 +23,14 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
 	return 0;
 }
 
-static int msm_iommu_attach(struct msm_mmu *mmu, const char * const *names,
-			    int cnt)
+static int msm_iommu_attach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
 	return iommu_attach_device(iommu->domain, mmu->dev);
 }
 
-static void msm_iommu_detach(struct msm_mmu *mmu, const char * const *names,
-			     int cnt)
+static void msm_iommu_detach(struct msm_mmu *mmu)
 {
 	struct msm_iommu *iommu = to_msm_iommu(mmu);
 
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index 871d56303697..67a623f14319 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -10,8 +10,8 @@
 #include <linux/iommu.h>
 
 struct msm_mmu_funcs {
-	int (*attach)(struct msm_mmu *mmu, const char * const *names, int cnt);
-	void (*detach)(struct msm_mmu *mmu, const char * const *names, int cnt);
+	int (*attach)(struct msm_mmu *mmu);
+	void (*detach)(struct msm_mmu *mmu);
 	int (*map)(struct msm_mmu *mmu, uint64_t iova, struct sg_table *sgt,
 			unsigned len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, unsigned len);
diff --git a/drivers/gpu/drm/msm/msm_rd.c b/drivers/gpu/drm/msm/msm_rd.c
index c7832a951039..af7ceb246c7c 100644
--- a/drivers/gpu/drm/msm/msm_rd.c
+++ b/drivers/gpu/drm/msm/msm_rd.c
@@ -298,7 +298,7 @@ void msm_rd_debugfs_cleanup(struct msm_drm_private *priv)
 
 static void snapshot_buf(struct msm_rd_state *rd,
 		struct msm_gem_submit *submit, int idx,
-		uint64_t iova, uint32_t size)
+		uint64_t iova, uint32_t size, bool full)
 {
 	struct msm_gem_object *obj = submit->bos[idx].obj;
 	unsigned offset = 0;
@@ -318,6 +318,9 @@ static void snapshot_buf(struct msm_rd_state *rd,
 	rd_write_section(rd, RD_GPUADDR,
 			(uint32_t[3]){ iova, size, iova >> 32 }, 12);
 
+	if (!full)
+		return;
+
 	/* But only dump the contents of buffers marked READ */
 	if (!(submit->bos[idx].flags & MSM_SUBMIT_BO_READ))
 		return;
@@ -381,18 +384,21 @@ void msm_rd_dump_submit(struct msm_rd_state *rd, struct msm_gem_submit *submit,
 	rd_write_section(rd, RD_CMD, msg, ALIGN(n, 4));
 
 	for (i = 0; i < submit->nr_bos; i++)
-		if (should_dump(submit, i))
-			snapshot_buf(rd, submit, i, 0, 0);
+		snapshot_buf(rd, submit, i, 0, 0, should_dump(submit, i));
 
 	for (i = 0; i < submit->nr_cmds; i++) {
-		uint64_t iova = submit->cmd[i].iova;
 		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		/* snapshot cmdstream bo's (if we haven't already): */
 		if (!should_dump(submit, i)) {
 			snapshot_buf(rd, submit, submit->cmd[i].idx,
-					submit->cmd[i].iova, szd * 4);
+					submit->cmd[i].iova, szd * 4, true);
 		}
+	}
+
+	for (i = 0; i < submit->nr_cmds; i++) {
+		uint64_t iova = submit->cmd[i].iova;
+		uint32_t szd  = submit->cmd[i].size; /* in dwords */
 
 		switch (submit->cmd[i].type) {
 		case MSM_SUBMIT_CMD_IB_TARGET_BUF:
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index a13924ae1992..549486f1d937 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -986,20 +986,11 @@ nv50_mstc_atomic_check(struct drm_connector *connector,
 	return drm_dp_atomic_release_vcpi_slots(state, mgr, mstc->port);
 }
 
-static const struct drm_connector_helper_funcs
-nv50_mstc_help = {
-	.get_modes = nv50_mstc_get_modes,
-	.mode_valid = nv50_mstc_mode_valid,
-	.best_encoder = nv50_mstc_best_encoder,
-	.atomic_best_encoder = nv50_mstc_atomic_best_encoder,
-	.atomic_check = nv50_mstc_atomic_check,
-};
-
-static enum drm_connector_status
-nv50_mstc_detect(struct drm_connector *connector, bool force)
+static int
+nv50_mstc_detect(struct drm_connector *connector,
+		 struct drm_modeset_acquire_ctx *ctx, bool force)
 {
 	struct nv50_mstc *mstc = nv50_mstc(connector);
-	enum drm_connector_status conn_status;
 	int ret;
 
 	if (drm_connector_is_unregistered(connector))
@@ -1009,14 +1000,24 @@ nv50_mstc_detect(struct drm_connector *connector, bool force)
 	if (ret < 0 && ret != -EACCES)
 		return connector_status_disconnected;
 
-	conn_status = drm_dp_mst_detect_port(connector, mstc->port->mgr,
-					     mstc->port);
+	ret = drm_dp_mst_detect_port(connector, ctx, mstc->port->mgr,
+				     mstc->port);
 
 	pm_runtime_mark_last_busy(connector->dev->dev);
 	pm_runtime_put_autosuspend(connector->dev->dev);
-	return conn_status;
+	return ret;
 }
 
+static const struct drm_connector_helper_funcs
+nv50_mstc_help = {
+	.get_modes = nv50_mstc_get_modes,
+	.mode_valid = nv50_mstc_mode_valid,
+	.best_encoder = nv50_mstc_best_encoder,
+	.atomic_best_encoder = nv50_mstc_atomic_best_encoder,
+	.atomic_check = nv50_mstc_atomic_check,
+	.detect_ctx = nv50_mstc_detect,
+};
+
 static void
 nv50_mstc_destroy(struct drm_connector *connector)
 {
@@ -1031,7 +1032,6 @@ nv50_mstc_destroy(struct drm_connector *connector)
 static const struct drm_connector_funcs
 nv50_mstc = {
 	.reset = nouveau_conn_reset,
-	.detect = nv50_mstc_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = nv50_mstc_destroy,
 	.atomic_duplicate_state = nouveau_conn_atomic_duplicate_state,
@@ -1309,14 +1309,14 @@ nv50_mstm_fini(struct nv50_mstm *mstm)
 }
 
 static void
-nv50_mstm_init(struct nv50_mstm *mstm)
+nv50_mstm_init(struct nv50_mstm *mstm, bool runtime)
 {
 	int ret;
 
 	if (!mstm || !mstm->mgr.mst_state)
 		return;
 
-	ret = drm_dp_mst_topology_mgr_resume(&mstm->mgr);
+	ret = drm_dp_mst_topology_mgr_resume(&mstm->mgr, !runtime);
 	if (ret == -1) {
 		drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, false);
 		drm_kms_helper_hotplug_event(mstm->mgr.dev);
@@ -2263,7 +2263,7 @@ nv50_display_init(struct drm_device *dev, bool resume, bool runtime)
 		if (encoder->encoder_type != DRM_MODE_ENCODER_DPMST) {
 			struct nouveau_encoder *nv_encoder =
 				nouveau_encoder(encoder);
-			nv50_mstm_init(nv_encoder->dp.mstm);
+			nv50_mstm_init(nv_encoder->dp.mstm, runtime);
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 3a5db17bc5c7..5b413588b823 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -1130,6 +1130,16 @@ nouveau_connector_hotplug(struct nvif_notify *notify)
 	const char *name = connector->name;
 	struct nouveau_encoder *nv_encoder;
 	int ret;
+	bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG);
+
+	if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) {
+		NV_DEBUG(drm, "service %s\n", name);
+		drm_dp_cec_irq(&nv_connector->aux);
+		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP)))
+			nv50_mstm_service(nv_encoder->dp.mstm);
+
+		return NVIF_NOTIFY_KEEP;
+	}
 
 	ret = pm_runtime_get(drm->dev->dev);
 	if (ret == 0) {
@@ -1150,25 +1160,16 @@ nouveau_connector_hotplug(struct nvif_notify *notify)
 		return NVIF_NOTIFY_DROP;
 	}
 
-	if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) {
-		NV_DEBUG(drm, "service %s\n", name);
-		drm_dp_cec_irq(&nv_connector->aux);
-		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP)))
-			nv50_mstm_service(nv_encoder->dp.mstm);
-	} else {
-		bool plugged = (rep->mask != NVIF_NOTIFY_CONN_V0_UNPLUG);
-
+	if (!plugged)
+		drm_dp_cec_unset_edid(&nv_connector->aux);
+	NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name);
+	if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) {
 		if (!plugged)
-			drm_dp_cec_unset_edid(&nv_connector->aux);
-		NV_DEBUG(drm, "%splugged %s\n", plugged ? "" : "un", name);
-		if ((nv_encoder = find_encoder(connector, DCB_OUTPUT_DP))) {
-			if (!plugged)
-				nv50_mstm_remove(nv_encoder->dp.mstm);
-		}
-
-		drm_helper_hpd_irq_event(connector->dev);
+			nv50_mstm_remove(nv_encoder->dp.mstm);
 	}
 
+	drm_helper_hpd_irq_event(connector->dev);
+
 	pm_runtime_mark_last_busy(drm->dev->dev);
 	pm_runtime_put_autosuspend(drm->dev->dev);
 	return NVIF_NOTIFY_KEEP;
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 6f038511a03a..53f9bceaf17a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -407,6 +407,17 @@ nouveau_display_init(struct drm_device *dev, bool resume, bool runtime)
 	struct drm_connector_list_iter conn_iter;
 	int ret;
 
+	/*
+	 * Enable hotplug interrupts (done as early as possible, since we need
+	 * them for MST)
+	 */
+	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);
+
 	ret = disp->init(dev, resume, runtime);
 	if (ret)
 		return ret;
@@ -416,14 +427,6 @@ nouveau_display_init(struct drm_device *dev, bool resume, bool runtime)
 	 */
 	drm_kms_helper_poll_enable(dev);
 
-	/* enable hotplug interrupts */
-	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);
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.c b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
index 12ff77dacc95..4c4e8a30a1ac 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.c
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.c
@@ -13,97 +13,42 @@
 #include "panfrost_gpu.h"
 #include "panfrost_regs.h"
 
-static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev, int slot);
+static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev);
 
 static int panfrost_devfreq_target(struct device *dev, unsigned long *freq,
 				   u32 flags)
 {
-	struct panfrost_device *pfdev = platform_get_drvdata(to_platform_device(dev));
-	struct dev_pm_opp *opp;
-	unsigned long old_clk_rate = pfdev->devfreq.cur_freq;
-	unsigned long target_volt, target_rate;
+	struct panfrost_device *pfdev = dev_get_drvdata(dev);
 	int err;
 
-	opp = devfreq_recommended_opp(dev, freq, flags);
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
-
-	target_rate = dev_pm_opp_get_freq(opp);
-	target_volt = dev_pm_opp_get_voltage(opp);
-	dev_pm_opp_put(opp);
-
-	if (old_clk_rate == target_rate)
-		return 0;
-
-	/*
-	 * If frequency scaling from low to high, adjust voltage first.
-	 * If frequency scaling from high to low, adjust frequency first.
-	 */
-	if (old_clk_rate < target_rate) {
-		err = regulator_set_voltage(pfdev->regulator, target_volt,
-					    target_volt);
-		if (err) {
-			dev_err(dev, "Cannot set voltage %lu uV\n",
-				target_volt);
-			return err;
-		}
-	}
-
-	err = clk_set_rate(pfdev->clock, target_rate);
-	if (err) {
-		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
-			err);
-		regulator_set_voltage(pfdev->regulator, pfdev->devfreq.cur_volt,
-				      pfdev->devfreq.cur_volt);
+	err = dev_pm_opp_set_rate(dev, *freq);
+	if (err)
 		return err;
-	}
 
-	if (old_clk_rate > target_rate) {
-		err = regulator_set_voltage(pfdev->regulator, target_volt,
-					    target_volt);
-		if (err)
-			dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
-	}
-
-	pfdev->devfreq.cur_freq = target_rate;
-	pfdev->devfreq.cur_volt = target_volt;
+	*freq = clk_get_rate(pfdev->clock);
 
 	return 0;
 }
 
 static void panfrost_devfreq_reset(struct panfrost_device *pfdev)
 {
-	ktime_t now = ktime_get();
-	int i;
-
-	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-		pfdev->devfreq.slot[i].busy_time = 0;
-		pfdev->devfreq.slot[i].idle_time = 0;
-		pfdev->devfreq.slot[i].time_last_update = now;
-	}
+	pfdev->devfreq.busy_time = 0;
+	pfdev->devfreq.idle_time = 0;
+	pfdev->devfreq.time_last_update = ktime_get();
 }
 
 static int panfrost_devfreq_get_dev_status(struct device *dev,
 					   struct devfreq_dev_status *status)
 {
-	struct panfrost_device *pfdev = platform_get_drvdata(to_platform_device(dev));
-	int i;
+	struct panfrost_device *pfdev = dev_get_drvdata(dev);
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-		panfrost_devfreq_update_utilization(pfdev, i);
-	}
+	panfrost_devfreq_update_utilization(pfdev);
 
 	status->current_frequency = clk_get_rate(pfdev->clock);
-	status->total_time = ktime_to_ns(ktime_add(pfdev->devfreq.slot[0].busy_time,
-						   pfdev->devfreq.slot[0].idle_time));
+	status->total_time = ktime_to_ns(ktime_add(pfdev->devfreq.busy_time,
+						   pfdev->devfreq.idle_time));
 
-	status->busy_time = 0;
-	for (i = 0; i < NUM_JOB_SLOTS; i++) {
-		status->busy_time += ktime_to_ns(pfdev->devfreq.slot[i].busy_time);
-	}
-
-	/* We're scheduling only to one core atm, so don't divide for now */
-	/* status->busy_time /= NUM_JOB_SLOTS; */
+	status->busy_time = ktime_to_ns(pfdev->devfreq.busy_time);
 
 	panfrost_devfreq_reset(pfdev);
 
@@ -119,7 +64,7 @@ static int panfrost_devfreq_get_cur_freq(struct device *dev, unsigned long *freq
 {
 	struct panfrost_device *pfdev = platform_get_drvdata(to_platform_device(dev));
 
-	*freq = pfdev->devfreq.cur_freq;
+	*freq = clk_get_rate(pfdev->clock);
 
 	return 0;
 }
@@ -135,6 +80,7 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 {
 	int ret;
 	struct dev_pm_opp *opp;
+	unsigned long cur_freq;
 
 	ret = dev_pm_opp_of_add_table(&pfdev->pdev->dev);
 	if (ret == -ENODEV) /* Optional, continue without devfreq */
@@ -144,13 +90,13 @@ int panfrost_devfreq_init(struct panfrost_device *pfdev)
 
 	panfrost_devfreq_reset(pfdev);
 
-	pfdev->devfreq.cur_freq = clk_get_rate(pfdev->clock);
+	cur_freq = clk_get_rate(pfdev->clock);
 
-	opp = devfreq_recommended_opp(&pfdev->pdev->dev, &pfdev->devfreq.cur_freq, 0);
+	opp = devfreq_recommended_opp(&pfdev->pdev->dev, &cur_freq, 0);
 	if (IS_ERR(opp))
 		return PTR_ERR(opp);
 
-	panfrost_devfreq_profile.initial_freq = pfdev->devfreq.cur_freq;
+	panfrost_devfreq_profile.initial_freq = cur_freq;
 	dev_pm_opp_put(opp);
 
 	pfdev->devfreq.devfreq = devm_devfreq_add_device(&pfdev->pdev->dev,
@@ -174,14 +120,10 @@ void panfrost_devfreq_fini(struct panfrost_device *pfdev)
 
 void panfrost_devfreq_resume(struct panfrost_device *pfdev)
 {
-	int i;
-
 	if (!pfdev->devfreq.devfreq)
 		return;
 
 	panfrost_devfreq_reset(pfdev);
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		pfdev->devfreq.slot[i].busy = false;
 
 	devfreq_resume_device(pfdev->devfreq.devfreq);
 }
@@ -194,9 +136,8 @@ void panfrost_devfreq_suspend(struct panfrost_device *pfdev)
 	devfreq_suspend_device(pfdev->devfreq.devfreq);
 }
 
-static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev, int slot)
+static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev)
 {
-	struct panfrost_devfreq_slot *devfreq_slot = &pfdev->devfreq.slot[slot];
 	ktime_t now;
 	ktime_t last;
 
@@ -204,22 +145,27 @@ static void panfrost_devfreq_update_utilization(struct panfrost_device *pfdev, i
 		return;
 
 	now = ktime_get();
-	last = pfdev->devfreq.slot[slot].time_last_update;
+	last = pfdev->devfreq.time_last_update;
 
-	/* If we last recorded a transition to busy, we have been idle since */
-	if (devfreq_slot->busy)
-		pfdev->devfreq.slot[slot].busy_time += ktime_sub(now, last);
+	if (atomic_read(&pfdev->devfreq.busy_count) > 0)
+		pfdev->devfreq.busy_time += ktime_sub(now, last);
 	else
-		pfdev->devfreq.slot[slot].idle_time += ktime_sub(now, last);
+		pfdev->devfreq.idle_time += ktime_sub(now, last);
 
-	pfdev->devfreq.slot[slot].time_last_update = now;
+	pfdev->devfreq.time_last_update = now;
+}
+
+void panfrost_devfreq_record_busy(struct panfrost_device *pfdev)
+{
+	panfrost_devfreq_update_utilization(pfdev);
+	atomic_inc(&pfdev->devfreq.busy_count);
 }
 
-/* The job scheduler is expected to call this at every transition busy <-> idle */
-void panfrost_devfreq_record_transition(struct panfrost_device *pfdev, int slot)
+void panfrost_devfreq_record_idle(struct panfrost_device *pfdev)
 {
-	struct panfrost_devfreq_slot *devfreq_slot = &pfdev->devfreq.slot[slot];
+	int count;
 
-	panfrost_devfreq_update_utilization(pfdev, slot);
-	devfreq_slot->busy = !devfreq_slot->busy;
+	panfrost_devfreq_update_utilization(pfdev);
+	count = atomic_dec_if_positive(&pfdev->devfreq.busy_count);
+	WARN_ON(count < 0);
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_devfreq.h b/drivers/gpu/drm/panfrost/panfrost_devfreq.h
index e3bc63e82843..0611beffc8d0 100644
--- a/drivers/gpu/drm/panfrost/panfrost_devfreq.h
+++ b/drivers/gpu/drm/panfrost/panfrost_devfreq.h
@@ -10,6 +10,7 @@ void panfrost_devfreq_fini(struct panfrost_device *pfdev);
 void panfrost_devfreq_resume(struct panfrost_device *pfdev);
 void panfrost_devfreq_suspend(struct panfrost_device *pfdev);
 
-void panfrost_devfreq_record_transition(struct panfrost_device *pfdev, int slot);
+void panfrost_devfreq_record_busy(struct panfrost_device *pfdev);
+void panfrost_devfreq_record_idle(struct panfrost_device *pfdev);
 
 #endif /* __PANFROST_DEVFREQ_H__ */
diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
index 9c39b9794811..06713811b92c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_device.h
+++ b/drivers/gpu/drm/panfrost/panfrost_device.h
@@ -51,13 +51,6 @@ struct panfrost_features {
 	unsigned long hw_issues[64 / BITS_PER_LONG];
 };
 
-struct panfrost_devfreq_slot {
-	ktime_t busy_time;
-	ktime_t idle_time;
-	ktime_t time_last_update;
-	bool busy;
-};
-
 struct panfrost_device {
 	struct device *dev;
 	struct drm_device *ddev;
@@ -93,9 +86,10 @@ struct panfrost_device {
 	struct {
 		struct devfreq *devfreq;
 		struct thermal_cooling_device *cooling;
-		unsigned long cur_freq;
-		unsigned long cur_volt;
-		struct panfrost_devfreq_slot slot[NUM_JOB_SLOTS];
+		ktime_t busy_time;
+		ktime_t idle_time;
+		ktime_t time_last_update;
+		atomic_t busy_count;
 	} devfreq;
 };
 
diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
index 9d086133a84e..9458dc6c750c 100644
--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
+++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
@@ -556,11 +556,11 @@ static int panfrost_probe(struct platform_device *pdev)
 	return 0;
 
 err_out2:
+	pm_runtime_disable(pfdev->dev);
 	panfrost_devfreq_fini(pfdev);
 err_out1:
 	panfrost_device_fini(pfdev);
 err_out0:
-	pm_runtime_disable(pfdev->dev);
 	drm_dev_put(ddev);
 	return err;
 }
diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index 33bf25ba506e..d411eb6c8eb9 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -155,8 +155,7 @@ static void panfrost_job_hw_submit(struct panfrost_job *job, int js)
 	}
 
 	cfg = panfrost_mmu_as_get(pfdev, &job->file_priv->mmu);
-
-	panfrost_devfreq_record_transition(pfdev, js);
+	panfrost_devfreq_record_busy(pfdev);
 
 	job_write(pfdev, JS_HEAD_NEXT_LO(js), jc_head & 0xFFFFFFFF);
 	job_write(pfdev, JS_HEAD_NEXT_HI(js), jc_head >> 32);
@@ -404,7 +403,7 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 	}
 	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
 
-	panfrost_devfreq_record_transition(pfdev, js);
+	panfrost_devfreq_record_idle(pfdev);
 	panfrost_device_reset(pfdev);
 
 	for (i = 0; i < NUM_JOB_SLOTS; i++)
@@ -467,7 +466,7 @@ static irqreturn_t panfrost_job_irq_handler(int irq, void *data)
 				pfdev->jobs[j] = NULL;
 
 				panfrost_mmu_as_put(pfdev, &job->file_priv->mmu);
-				panfrost_devfreq_record_transition(pfdev, j);
+				panfrost_devfreq_record_idle(pfdev);
 
 				dma_fence_signal_locked(job->done_fence);
 				pm_runtime_put_autosuspend(pfdev->dev);
@@ -568,14 +567,14 @@ int panfrost_job_is_idle(struct panfrost_device *pfdev)
 	struct panfrost_job_slot *js = pfdev->js;
 	int i;
 
+	/* Check whether the hardware is idle */
+	if (atomic_read(&pfdev->devfreq.busy_count))
+		return false;
+
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
 		/* If there are any jobs in the HW queue, we're not idle */
 		if (atomic_read(&js->queue[i].sched.hw_rq_count))
 			return false;
-
-		/* Check whether the hardware is idle */
-		if (pfdev->devfreq.slot[i].busy)
-			return false;
 	}
 
 	return true;
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index bdd990568476..a3ed64a1f15e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -224,9 +224,9 @@ static size_t get_pgsize(u64 addr, size_t size)
 	return SZ_2M;
 }
 
-void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
-			      struct panfrost_mmu *mmu,
-			      u64 iova, size_t size)
+static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
+				     struct panfrost_mmu *mmu,
+				     u64 iova, size_t size)
 {
 	if (mmu->as < 0)
 		return;
@@ -406,11 +406,11 @@ addr_to_drm_mm_node(struct panfrost_device *pfdev, int as, u64 addr)
 	spin_lock(&pfdev->as_lock);
 	list_for_each_entry(mmu, &pfdev->as_lru_list, list) {
 		if (as == mmu->as)
-			break;
+			goto found_mmu;
 	}
-	if (as != mmu->as)
-		goto out;
+	goto out;
 
+found_mmu:
 	priv = container_of(mmu, struct panfrost_file_priv, mmu);
 
 	spin_lock(&priv->mm_lock);
@@ -432,7 +432,8 @@ out:
 
 #define NUM_FAULT_PAGES (SZ_2M / PAGE_SIZE)
 
-int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as, u64 addr)
+static int panfrost_mmu_map_fault_addr(struct panfrost_device *pfdev, int as,
+				       u64 addr)
 {
 	int ret, i;
 	struct panfrost_gem_object *bo;
diff --git a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
index 83c57d325ca8..2dba192bf198 100644
--- a/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
+++ b/drivers/gpu/drm/panfrost/panfrost_perfcnt.c
@@ -16,6 +16,7 @@
 #include "panfrost_issues.h"
 #include "panfrost_job.h"
 #include "panfrost_mmu.h"
+#include "panfrost_perfcnt.h"
 #include "panfrost_regs.h"
 
 #define COUNTERS_PER_BLOCK		64
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 024771a4083e..703ddc803c55 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -48,10 +48,10 @@ irqreturn_t pl111_irq(int irq, void *data)
 }
 
 static enum drm_mode_status
-pl111_mode_valid(struct drm_crtc *crtc,
+pl111_mode_valid(struct drm_simple_display_pipe *pipe,
 		 const struct drm_display_mode *mode)
 {
-	struct drm_device *drm = crtc->dev;
+	struct drm_device *drm = pipe->crtc.dev;
 	struct pl111_drm_dev_private *priv = drm->dev_private;
 	u32 cpp = priv->variant->fb_bpp / 8;
 	u64 bw;
diff --git a/drivers/gpu/drm/qxl/qxl_drv.h b/drivers/gpu/drm/qxl/qxl_drv.h
index a5cb3864d686..27e45a2d6b52 100644
--- a/drivers/gpu/drm/qxl/qxl_drv.h
+++ b/drivers/gpu/drm/qxl/qxl_drv.h
@@ -355,6 +355,8 @@ int qxl_mode_dumb_mmap(struct drm_file *filp,
 /* qxl ttm */
 int qxl_ttm_init(struct qxl_device *qdev);
 void qxl_ttm_fini(struct qxl_device *qdev);
+int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
+			   struct ttm_mem_reg *mem);
 
 /* qxl image */
 
diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
index ad336c98a0cf..ab72dc3476e9 100644
--- a/drivers/gpu/drm/qxl/qxl_object.c
+++ b/drivers/gpu/drm/qxl/qxl_object.c
@@ -167,7 +167,6 @@ int qxl_bo_kmap(struct qxl_bo *bo, void **ptr)
 void *qxl_bo_kmap_atomic_page(struct qxl_device *qdev,
 			      struct qxl_bo *bo, int page_offset)
 {
-	struct ttm_mem_type_manager *man = &bo->tbo.bdev->man[bo->tbo.mem.mem_type];
 	void *rptr;
 	int ret;
 	struct io_mapping *map;
@@ -179,9 +178,7 @@ void *qxl_bo_kmap_atomic_page(struct qxl_device *qdev,
 	else
 		goto fallback;
 
-	(void) ttm_mem_io_lock(man, false);
-	ret = ttm_mem_io_reserve(bo->tbo.bdev, &bo->tbo.mem);
-	ttm_mem_io_unlock(man);
+	ret = qxl_ttm_io_mem_reserve(bo->tbo.bdev, &bo->tbo.mem);
 
 	return io_mapping_map_atomic_wc(map, bo->tbo.mem.bus.offset + page_offset);
 fallback:
@@ -212,17 +209,11 @@ void qxl_bo_kunmap(struct qxl_bo *bo)
 void qxl_bo_kunmap_atomic_page(struct qxl_device *qdev,
 			       struct qxl_bo *bo, void *pmap)
 {
-	struct ttm_mem_type_manager *man = &bo->tbo.bdev->man[bo->tbo.mem.mem_type];
-
 	if ((bo->tbo.mem.mem_type != TTM_PL_VRAM) &&
 	    (bo->tbo.mem.mem_type != TTM_PL_PRIV))
 		goto fallback;
 
 	io_mapping_unmap_atomic(pmap);
-
-	(void) ttm_mem_io_lock(man, false);
-	ttm_mem_io_free(bo->tbo.bdev, &bo->tbo.mem);
-	ttm_mem_io_unlock(man);
 	return;
  fallback:
 	qxl_bo_kunmap(bo);
diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 312216caeea2..2feca734c7b1 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -260,7 +260,7 @@ int qxl_release_reserve_list(struct qxl_release *release, bool no_intr)
 		return 0;
 
 	ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos,
-				     !no_intr, NULL, true);
+				     !no_intr, NULL);
 	if (ret)
 		return ret;
 
@@ -429,7 +429,6 @@ void qxl_release_unmap(struct qxl_device *qdev,
 void qxl_release_fence_buffer_objects(struct qxl_release *release)
 {
 	struct ttm_buffer_object *bo;
-	struct ttm_bo_global *glob;
 	struct ttm_bo_device *bdev;
 	struct ttm_validate_buffer *entry;
 	struct qxl_device *qdev;
@@ -451,18 +450,16 @@ void qxl_release_fence_buffer_objects(struct qxl_release *release)
 		       release->id | 0xf0000000, release->base.seqno);
 	trace_dma_fence_emit(&release->base);
 
-	glob = bdev->glob;
-
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 
 	list_for_each_entry(entry, &release->bos, head) {
 		bo = entry->bo;
 
 		dma_resv_add_shared_fence(bo->base.resv, &release->base);
-		ttm_bo_add_to_lru(bo);
+		ttm_bo_move_to_lru_tail(bo, NULL);
 		dma_resv_unlock(bo->base.resv);
 	}
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 	ww_acquire_fini(&release->ticket);
 }
 
diff --git a/drivers/gpu/drm/qxl/qxl_ttm.c b/drivers/gpu/drm/qxl/qxl_ttm.c
index 54cc5a5b607e..16a5e903533d 100644
--- a/drivers/gpu/drm/qxl/qxl_ttm.c
+++ b/drivers/gpu/drm/qxl/qxl_ttm.c
@@ -110,8 +110,8 @@ static void qxl_evict_flags(struct ttm_buffer_object *bo,
 	*placement = qbo->placement;
 }
 
-static int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
-				  struct ttm_mem_reg *mem)
+int qxl_ttm_io_mem_reserve(struct ttm_bo_device *bdev,
+			   struct ttm_mem_reg *mem)
 {
 	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
 	struct qxl_device *qdev = qxl_get_qdev(bdev);
@@ -319,14 +319,11 @@ static int qxl_mm_dump_table(struct seq_file *m, void *data)
 {
 	struct drm_info_node *node = (struct drm_info_node *)m->private;
 	struct drm_mm *mm = (struct drm_mm *)node->info_ent->data;
-	struct drm_device *dev = node->minor->dev;
-	struct qxl_device *rdev = dev->dev_private;
-	struct ttm_bo_global *glob = rdev->mman.bdev.glob;
 	struct drm_printer p = drm_seq_file_printer(m);
 
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 	drm_mm_print(mm, &p);
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 	return 0;
 }
 #endif
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 62eab82a64f9..acabeaf28732 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -221,9 +221,7 @@ int ci_get_temp(struct radeon_device *rdev)
 	else
 		actual_temp = temp & 0x1ff;
 
-	actual_temp = actual_temp * 1000;
-
-	return actual_temp;
+	return actual_temp * 1000;
 }
 
 /* get temperature in millidegrees */
@@ -239,9 +237,7 @@ int kv_get_temp(struct radeon_device *rdev)
 	else
 		actual_temp = 0;
 
-	actual_temp = actual_temp * 1000;
-
-	return actual_temp;
+	return actual_temp * 1000;
 }
 
 /*
@@ -6969,8 +6965,8 @@ static int cik_irq_init(struct radeon_device *rdev)
 	}
 
 	/* setup interrupt control */
-	/* XXX this should actually be a bus address, not an MC address. same on older asics */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 7089dfc8c2a9..110fb38004b1 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -1826,8 +1826,8 @@ static int r100_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & RADEON_TXFORMAT_CUBIC_MAP_ENABLE)
 			track->textures[i].tex_coord_type = 2;
diff --git a/drivers/gpu/drm/radeon/r200.c b/drivers/gpu/drm/radeon/r200.c
index 840401413c58..f5f2ffea5ab2 100644
--- a/drivers/gpu/drm/radeon/r200.c
+++ b/drivers/gpu/drm/radeon/r200.c
@@ -476,8 +476,8 @@ int r200_packet0_check(struct radeon_cs_parser *p,
 			track->textures[i].use_pitch = 1;
 		} else {
 			track->textures[i].use_pitch = 0;
-			track->textures[i].width = 1 << ((idx_value >> RADEON_TXFORMAT_WIDTH_SHIFT) & RADEON_TXFORMAT_WIDTH_MASK);
-			track->textures[i].height = 1 << ((idx_value >> RADEON_TXFORMAT_HEIGHT_SHIFT) & RADEON_TXFORMAT_HEIGHT_MASK);
+			track->textures[i].width = 1 << ((idx_value & RADEON_TXFORMAT_WIDTH_MASK) >> RADEON_TXFORMAT_WIDTH_SHIFT);
+			track->textures[i].height = 1 << ((idx_value & RADEON_TXFORMAT_HEIGHT_MASK) >> RADEON_TXFORMAT_HEIGHT_SHIFT);
 		}
 		if (idx_value & R200_TXFORMAT_LOOKUP_DISABLE)
 			track->textures[i].lookup_disable = true;
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index e937cc01910d..033bc466a862 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -3696,8 +3696,8 @@ int r600_irq_init(struct radeon_device *rdev)
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index b9aea5776d3d..72db2b41e96d 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -367,10 +367,10 @@ static void radeon_audio_write_sad_regs(struct drm_encoder *encoder)
 		return;
 
 	sad_count = drm_edid_to_sad(radeon_connector_edid(connector), &sads);
-	if (sad_count <= 0) {
+	if (sad_count < 0)
 		DRM_ERROR("Couldn't read SADs: %d\n", sad_count);
+	if (sad_count <= 0)
 		return;
-	}
 	BUG_ON(!sads);
 
 	if (radeon_encoder->audio && radeon_encoder->audio->write_sad_regs)
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 2994f07fbad9..ee28f5b3785e 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -233,21 +233,26 @@ drm_encoder *radeon_mst_best_encoder(struct drm_connector *connector)
 	return &radeon_connector->mst_encoder->base;
 }
 
+static int
+radeon_dp_mst_detect(struct drm_connector *connector,
+		     struct drm_modeset_acquire_ctx *ctx,
+		     bool force)
+{
+	struct radeon_connector *radeon_connector =
+		to_radeon_connector(connector);
+	struct radeon_connector *master = radeon_connector->mst_port;
+
+	return drm_dp_mst_detect_port(connector, ctx, &master->mst_mgr,
+				      radeon_connector->port);
+}
+
 static const struct drm_connector_helper_funcs radeon_dp_mst_connector_helper_funcs = {
 	.get_modes = radeon_dp_mst_get_modes,
 	.mode_valid = radeon_dp_mst_mode_valid,
 	.best_encoder = radeon_mst_best_encoder,
+	.detect_ctx = radeon_dp_mst_detect,
 };
 
-static enum drm_connector_status
-radeon_dp_mst_detect(struct drm_connector *connector, bool force)
-{
-	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
-	struct radeon_connector *master = radeon_connector->mst_port;
-
-	return drm_dp_mst_detect_port(connector, &master->mst_mgr, radeon_connector->port);
-}
-
 static void
 radeon_dp_mst_connector_destroy(struct drm_connector *connector)
 {
@@ -262,7 +267,6 @@ radeon_dp_mst_connector_destroy(struct drm_connector *connector)
 
 static const struct drm_connector_funcs radeon_dp_mst_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
-	.detect = radeon_dp_mst_detect,
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = radeon_dp_mst_connector_destroy,
 };
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 888e0f384c61..fd74e2611185 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -384,6 +384,17 @@ radeon_pci_shutdown(struct pci_dev *pdev)
 	 */
 	if (radeon_device_is_virtual())
 		radeon_pci_remove(pdev);
+
+#ifdef CONFIG_PPC64
+	/*
+	 * Some adapters need to be suspended before a
+	 * shutdown occurs in order to prevent an error
+	 * during kexec.
+	 * Make this power specific becauase it breaks
+	 * some non-power boards.
+	 */
+	radeon_suspend_kms(pci_get_drvdata(pdev), true, true, false);
+#endif
 }
 
 static int radeon_pmops_suspend(struct device *dev)
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index b2b076606f54..67298a0739cb 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -566,7 +566,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev,
 	if (!vm_bos)
 		return;
 
-	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL, true);
+	r = ttm_eu_reserve_buffers(&ticket, &list, true, NULL);
 	if (r)
 		goto error_free;
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 2abe1eab471f..140d94cc080d 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -542,7 +542,7 @@ int radeon_bo_list_validate(struct radeon_device *rdev,
 	u64 bytes_moved_threshold = radeon_bo_get_threshold_for_moves(rdev);
 
 	INIT_LIST_HEAD(&duplicates);
-	r = ttm_eu_reserve_buffers(ticket, head, true, &duplicates, true);
+	r = ttm_eu_reserve_buffers(ticket, head, true, &duplicates);
 	if (unlikely(r != 0)) {
 		return r;
 	}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 05894d198a79..1d8efb0eefdb 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -5997,8 +5997,8 @@ static int si_irq_init(struct radeon_device *rdev)
 	}
 
 	/* setup interrupt control */
-	/* set dummy read address to ring address */
-	WREG32(INTERRUPT_CNTL2, rdev->ih.gpu_addr >> 8);
+	/* set dummy read address to dummy page address */
+	WREG32(INTERRUPT_CNTL2, rdev->dummy_page.addr >> 8);
 	interrupt_cntl = RREG32(INTERRUPT_CNTL);
 	/* IH_DUMMY_RD_OVERRIDE=0 - dummy read disabled with msi, enabled without msi
 	 * IH_DUMMY_RD_OVERRIDE=1 - dummy read controlled by IH_DUMMY_RD_EN
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 460fd98e40a7..a0b382a637a6 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -1958,6 +1958,7 @@ static void si_initialize_powertune_defaults(struct radeon_device *rdev)
 		case 0x682C:
 			si_pi->cac_weights = cac_weights_cape_verde_pro;
 			si_pi->dte_data = dte_data_sun_xt;
+			update_dte_from_pl2 = true;
 			break;
 		case 0x6825:
 		case 0x6827:
diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 1a5153197fe9..461a7a8129f4 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -23,6 +23,7 @@
 
 #include <linux/kthread.h>
 #include <linux/slab.h>
+#include <linux/completion.h>
 
 #include <drm/drm_print.h>
 #include <drm/gpu_scheduler.h>
@@ -68,6 +69,8 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	if (!entity->rq_list)
 		return -ENOMEM;
 
+	init_completion(&entity->entity_idle);
+
 	for (i = 0; i < num_rq_list; ++i)
 		entity->rq_list[i] = rq_list[i];
 
@@ -286,11 +289,12 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
 	 */
 	if (spsc_queue_count(&entity->job_queue)) {
 		if (sched) {
-			/* Park the kernel for a moment to make sure it isn't processing
-			 * our enity.
+			/*
+			 * Wait for thread to idle to make sure it isn't processing
+			 * this entity.
 			 */
-			kthread_park(sched->thread);
-			kthread_unpark(sched->thread);
+			wait_for_completion(&entity->entity_idle);
+
 		}
 		if (entity->dependency) {
 			dma_fence_remove_callback(entity->dependency,
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 9a0ee74d82dc..3c57e84222ca 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -47,6 +47,7 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
+#include <linux/completion.h>
 #include <uapi/linux/sched/types.h>
 
 #include <drm/drm_print.h>
@@ -134,6 +135,7 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
 		list_for_each_entry_continue(entity, &rq->entities, list) {
 			if (drm_sched_entity_is_ready(entity)) {
 				rq->current_entity = entity;
+				reinit_completion(&entity->entity_idle);
 				spin_unlock(&rq->lock);
 				return entity;
 			}
@@ -144,6 +146,7 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
 
 		if (drm_sched_entity_is_ready(entity)) {
 			rq->current_entity = entity;
+			reinit_completion(&entity->entity_idle);
 			spin_unlock(&rq->lock);
 			return entity;
 		}
@@ -479,6 +482,7 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 	struct drm_sched_job *s_job, *tmp;
 	uint64_t guilty_context;
 	bool found_guilty = false;
+	struct dma_fence *fence;
 
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
@@ -492,7 +496,18 @@ void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
 		dma_fence_put(s_job->s_fence->parent);
-		s_job->s_fence->parent = sched->ops->run_job(s_job);
+		fence = sched->ops->run_job(s_job);
+
+		if (IS_ERR_OR_NULL(fence)) {
+			if (IS_ERR(fence))
+				dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+
+			s_job->s_fence->parent = NULL;
+		} else {
+			s_job->s_fence->parent = fence;
+		}
+
+
 	}
 }
 EXPORT_SYMBOL(drm_sched_resubmit_jobs);
@@ -622,43 +637,45 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 }
 
 /**
- * drm_sched_cleanup_jobs - destroy finished jobs
+ * drm_sched_get_cleanup_job - fetch the next finished job to be destroyed
  *
  * @sched: scheduler instance
  *
- * Remove all finished jobs from the mirror list and destroy them.
+ * Returns the next finished job from the mirror list (if there is one)
+ * ready for it to be destroyed.
  */
-static void drm_sched_cleanup_jobs(struct drm_gpu_scheduler *sched)
+static struct drm_sched_job *
+drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 {
+	struct drm_sched_job *job;
 	unsigned long flags;
 
-	/* Don't destroy jobs while the timeout worker is running */
-	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
-	    !cancel_delayed_work(&sched->work_tdr))
-		return;
-
+	/*
+	 * Don't destroy jobs while the timeout worker is running  OR thread
+	 * is being parked and hence assumed to not touch ring_mirror_list
+	 */
+	if ((sched->timeout != MAX_SCHEDULE_TIMEOUT &&
+	    !cancel_delayed_work(&sched->work_tdr)) ||
+	    __kthread_should_park(sched->thread))
+		return NULL;
 
-	while (!list_empty(&sched->ring_mirror_list)) {
-		struct drm_sched_job *job;
+	spin_lock_irqsave(&sched->job_list_lock, flags);
 
-		job = list_first_entry(&sched->ring_mirror_list,
+	job = list_first_entry_or_null(&sched->ring_mirror_list,
 				       struct drm_sched_job, node);
-		if (!dma_fence_is_signaled(&job->s_fence->finished))
-			break;
 
-		spin_lock_irqsave(&sched->job_list_lock, flags);
+	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from ring_mirror_list */
 		list_del_init(&job->node);
-		spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
-		sched->ops->free_job(job);
+	} else {
+		job = NULL;
+		/* queue timeout for next job */
+		drm_sched_start_timeout(sched);
 	}
 
-	/* queue timeout for next job */
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	drm_sched_start_timeout(sched);
 	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 
+	return job;
 }
 
 /**
@@ -698,17 +715,27 @@ static int drm_sched_main(void *param)
 		struct drm_sched_fence *s_fence;
 		struct drm_sched_job *sched_job;
 		struct dma_fence *fence;
+		struct drm_sched_job *cleanup_job = NULL;
 
 		wait_event_interruptible(sched->wake_up_worker,
-					 (drm_sched_cleanup_jobs(sched),
+					 (cleanup_job = drm_sched_get_cleanup_job(sched)) ||
 					 (!drm_sched_blocked(sched) &&
 					  (entity = drm_sched_select_entity(sched))) ||
-					 kthread_should_stop()));
+					 kthread_should_stop());
+
+		if (cleanup_job) {
+			sched->ops->free_job(cleanup_job);
+			/* queue timeout for next job */
+			drm_sched_start_timeout(sched);
+		}
 
 		if (!entity)
 			continue;
 
 		sched_job = drm_sched_entity_pop_job(entity);
+
+		complete(&entity->entity_idle);
+
 		if (!sched_job)
 			continue;
 
@@ -720,7 +747,7 @@ static int drm_sched_main(void *param)
 		fence = sched->ops->run_job(sched_job);
 		drm_sched_fence_scheduled(s_fence);
 
-		if (fence) {
+		if (!IS_ERR_OR_NULL(fence)) {
 			s_fence->parent = dma_fence_get(fence);
 			r = dma_fence_add_callback(fence, &sched_job->cb,
 						   drm_sched_process_job);
@@ -730,8 +757,12 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else
+		} else {
+			if (IS_ERR(fence))
+				dma_fence_set_error(&s_fence->finished, PTR_ERR(fence));
+
 			drm_sched_process_job(NULL, &sched_job->cb);
+		}
 
 		wake_up(&sched->job_scheduled);
 	}
diff --git a/drivers/gpu/drm/ttm/Makefile b/drivers/gpu/drm/ttm/Makefile
index 01fc670ce7a2..caea2a099496 100644
--- a/drivers/gpu/drm/ttm/Makefile
+++ b/drivers/gpu/drm/ttm/Makefile
@@ -4,8 +4,8 @@
 
 ttm-y := ttm_memory.o ttm_tt.o ttm_bo.o \
 	ttm_bo_util.o ttm_bo_vm.o ttm_module.o \
-	ttm_execbuf_util.o ttm_page_alloc.o ttm_bo_manager.o \
-	ttm_page_alloc_dma.o
+	ttm_execbuf_util.o ttm_page_alloc.o ttm_bo_manager.o
 ttm-$(CONFIG_AGP) += ttm_agp_backend.o
+ttm-$(CONFIG_DRM_TTM_DMA_PAGE_POOL) += ttm_page_alloc_dma.o
 
 obj-$(CONFIG_DRM_TTM) += ttm.o
diff --git a/drivers/gpu/drm/ttm/ttm_agp_backend.c b/drivers/gpu/drm/ttm/ttm_agp_backend.c
index ea4d59eb8966..6050dc846894 100644
--- a/drivers/gpu/drm/ttm/ttm_agp_backend.c
+++ b/drivers/gpu/drm/ttm/ttm_agp_backend.c
@@ -51,7 +51,7 @@ struct ttm_agp_backend {
 static int ttm_agp_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
 {
 	struct ttm_agp_backend *agp_be = container_of(ttm, struct ttm_agp_backend, ttm);
-	struct page *dummy_read_page = ttm->bdev->glob->dummy_read_page;
+	struct page *dummy_read_page = ttm_bo_glob.dummy_read_page;
 	struct drm_mm_node *node = bo_mem->mm_node;
 	struct agp_memory *mem;
 	int ret, cached = (bo_mem->placement & TTM_PL_FLAG_CACHED);
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index f00b2e79882f..8d91b0428af1 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -51,6 +51,7 @@ static void ttm_bo_global_kobj_release(struct kobject *kobj);
 DEFINE_MUTEX(ttm_global_mutex);
 unsigned ttm_bo_glob_use_count;
 struct ttm_bo_global ttm_bo_glob;
+EXPORT_SYMBOL(ttm_bo_glob);
 
 static struct attribute ttm_bo_count = {
 	.name = "bo_count",
@@ -148,23 +149,21 @@ static void ttm_bo_release_list(struct kref *list_kref)
 {
 	struct ttm_buffer_object *bo =
 	    container_of(list_kref, struct ttm_buffer_object, list_kref);
-	struct ttm_bo_device *bdev = bo->bdev;
 	size_t acc_size = bo->acc_size;
 
 	BUG_ON(kref_read(&bo->list_kref));
 	BUG_ON(kref_read(&bo->kref));
-	BUG_ON(atomic_read(&bo->cpu_writers));
 	BUG_ON(bo->mem.mm_node != NULL);
 	BUG_ON(!list_empty(&bo->lru));
 	BUG_ON(!list_empty(&bo->ddestroy));
 	ttm_tt_destroy(bo->ttm);
-	atomic_dec(&bo->bdev->glob->bo_count);
+	atomic_dec(&ttm_bo_glob.bo_count);
 	dma_fence_put(bo->moving);
 	if (!ttm_bo_uses_embedded_gem_object(bo))
 		dma_resv_fini(&bo->base._resv);
 	mutex_destroy(&bo->wu_mutex);
 	bo->destroy(bo);
-	ttm_mem_global_free(bdev->glob->mem_glob, acc_size);
+	ttm_mem_global_free(&ttm_mem_glob, acc_size);
 }
 
 static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
@@ -188,23 +187,17 @@ static void ttm_bo_add_mem_to_lru(struct ttm_buffer_object *bo,
 	if (!(man->flags & TTM_MEMTYPE_FLAG_FIXED) && bo->ttm &&
 	    !(bo->ttm->page_flags & (TTM_PAGE_FLAG_SG |
 				     TTM_PAGE_FLAG_SWAPPED))) {
-		list_add_tail(&bo->swap, &bdev->glob->swap_lru[bo->priority]);
+		list_add_tail(&bo->swap, &ttm_bo_glob.swap_lru[bo->priority]);
 		kref_get(&bo->list_kref);
 	}
 }
 
-void ttm_bo_add_to_lru(struct ttm_buffer_object *bo)
-{
-	ttm_bo_add_mem_to_lru(bo, &bo->mem);
-}
-EXPORT_SYMBOL(ttm_bo_add_to_lru);
-
 static void ttm_bo_ref_bug(struct kref *list_kref)
 {
 	BUG();
 }
 
-void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
+static void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
 	bool notify = false;
@@ -224,16 +217,6 @@ void ttm_bo_del_from_lru(struct ttm_buffer_object *bo)
 		bdev->driver->del_from_lru_notify(bo);
 }
 
-void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo)
-{
-	struct ttm_bo_global *glob = bo->bdev->glob;
-
-	spin_lock(&glob->lru_lock);
-	ttm_bo_del_from_lru(bo);
-	spin_unlock(&glob->lru_lock);
-}
-EXPORT_SYMBOL(ttm_bo_del_sub_from_lru);
-
 static void ttm_bo_bulk_move_set_pos(struct ttm_lru_bulk_move_pos *pos,
 				     struct ttm_buffer_object *bo)
 {
@@ -248,7 +231,7 @@ void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo,
 	dma_resv_assert_held(bo->base.resv);
 
 	ttm_bo_del_from_lru(bo);
-	ttm_bo_add_to_lru(bo);
+	ttm_bo_add_mem_to_lru(bo, &bo->mem);
 
 	if (bulk && !(bo->mem.placement & TTM_PL_FLAG_NO_EVICT)) {
 		switch (bo->mem.mem_type) {
@@ -311,7 +294,7 @@ void ttm_bo_bulk_move_lru_tail(struct ttm_lru_bulk_move *bulk)
 		dma_resv_assert_held(pos->first->base.resv);
 		dma_resv_assert_held(pos->last->base.resv);
 
-		lru = &pos->first->bdev->glob->swap_lru[i];
+		lru = &ttm_bo_glob.swap_lru[i];
 		list_bulk_move_tail(lru, &pos->first->swap, &pos->last->swap);
 	}
 }
@@ -475,7 +458,6 @@ static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo)
 static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 {
 	struct ttm_bo_device *bdev = bo->bdev;
-	struct ttm_bo_global *glob = bdev->glob;
 	int ret;
 
 	ret = ttm_bo_individualize_resv(bo);
@@ -485,16 +467,16 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 		 */
 		dma_resv_wait_timeout_rcu(bo->base.resv, true, false,
 						    30 * HZ);
-		spin_lock(&glob->lru_lock);
+		spin_lock(&ttm_bo_glob.lru_lock);
 		goto error;
 	}
 
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 	ret = dma_resv_trylock(bo->base.resv) ? 0 : -EBUSY;
 	if (!ret) {
 		if (dma_resv_test_signaled_rcu(&bo->base._resv, true)) {
 			ttm_bo_del_from_lru(bo);
-			spin_unlock(&glob->lru_lock);
+			spin_unlock(&ttm_bo_glob.lru_lock);
 			if (bo->base.resv != &bo->base._resv)
 				dma_resv_unlock(&bo->base._resv);
 
@@ -512,7 +494,7 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 		 */
 		if (bo->mem.placement & TTM_PL_FLAG_NO_EVICT) {
 			bo->mem.placement &= ~TTM_PL_FLAG_NO_EVICT;
-			ttm_bo_add_to_lru(bo);
+			ttm_bo_move_to_lru_tail(bo, NULL);
 		}
 
 		dma_resv_unlock(bo->base.resv);
@@ -523,7 +505,7 @@ static void ttm_bo_cleanup_refs_or_queue(struct ttm_buffer_object *bo)
 error:
 	kref_get(&bo->list_kref);
 	list_add_tail(&bo->ddestroy, &bdev->ddestroy);
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 
 	schedule_delayed_work(&bdev->wq,
 			      ((HZ / 100) < 1) ? 1 : HZ / 100);
@@ -546,7 +528,6 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 			       bool interruptible, bool no_wait_gpu,
 			       bool unlock_resv)
 {
-	struct ttm_bo_global *glob = bo->bdev->glob;
 	struct dma_resv *resv;
 	int ret;
 
@@ -565,7 +546,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 
 		if (unlock_resv)
 			dma_resv_unlock(bo->base.resv);
-		spin_unlock(&glob->lru_lock);
+		spin_unlock(&ttm_bo_glob.lru_lock);
 
 		lret = dma_resv_wait_timeout_rcu(resv, true,
 							   interruptible,
@@ -576,7 +557,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 		else if (lret == 0)
 			return -EBUSY;
 
-		spin_lock(&glob->lru_lock);
+		spin_lock(&ttm_bo_glob.lru_lock);
 		if (unlock_resv && !dma_resv_trylock(bo->base.resv)) {
 			/*
 			 * We raced, and lost, someone else holds the reservation now,
@@ -586,7 +567,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 			 * delayed destruction would succeed, so just return success
 			 * here.
 			 */
-			spin_unlock(&glob->lru_lock);
+			spin_unlock(&ttm_bo_glob.lru_lock);
 			return 0;
 		}
 		ret = 0;
@@ -595,7 +576,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 	if (ret || unlikely(list_empty(&bo->ddestroy))) {
 		if (unlock_resv)
 			dma_resv_unlock(bo->base.resv);
-		spin_unlock(&glob->lru_lock);
+		spin_unlock(&ttm_bo_glob.lru_lock);
 		return ret;
 	}
 
@@ -603,7 +584,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
 	list_del_init(&bo->ddestroy);
 	kref_put(&bo->list_kref, ttm_bo_ref_bug);
 
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 	ttm_bo_cleanup_memtype_use(bo);
 
 	if (unlock_resv)
@@ -618,7 +599,7 @@ static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo,
  */
 static bool ttm_bo_delayed_delete(struct ttm_bo_device *bdev, bool remove_all)
 {
-	struct ttm_bo_global *glob = bdev->glob;
+	struct ttm_bo_global *glob = &ttm_bo_glob;
 	struct list_head removed;
 	bool empty;
 
@@ -842,13 +823,12 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 			       struct ww_acquire_ctx *ticket)
 {
 	struct ttm_buffer_object *bo = NULL, *busy_bo = NULL;
-	struct ttm_bo_global *glob = bdev->glob;
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
 	bool locked = false;
 	unsigned i;
 	int ret;
 
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 	for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) {
 		list_for_each_entry(bo, &man->lru[i], lru) {
 			bool busy;
@@ -880,7 +860,7 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 	if (!bo) {
 		if (busy_bo)
 			kref_get(&busy_bo->list_kref);
-		spin_unlock(&glob->lru_lock);
+		spin_unlock(&ttm_bo_glob.lru_lock);
 		ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket);
 		if (busy_bo)
 			kref_put(&busy_bo->list_kref, ttm_bo_release_list);
@@ -896,17 +876,11 @@ static int ttm_mem_evict_first(struct ttm_bo_device *bdev,
 		return ret;
 	}
 
-	ttm_bo_del_from_lru(bo);
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 
 	ret = ttm_bo_evict(bo, ctx);
-	if (locked) {
+	if (locked)
 		ttm_bo_unreserve(bo);
-	} else {
-		spin_lock(&glob->lru_lock);
-		ttm_bo_add_to_lru(bo);
-		spin_unlock(&glob->lru_lock);
-	}
 
 	kref_put(&bo->list_kref, ttm_bo_release_list);
 	return ret;
@@ -926,7 +900,8 @@ EXPORT_SYMBOL(ttm_bo_mem_put);
  */
 static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 				 struct ttm_mem_type_manager *man,
-				 struct ttm_mem_reg *mem)
+				 struct ttm_mem_reg *mem,
+				 bool no_wait_gpu)
 {
 	struct dma_fence *fence;
 	int ret;
@@ -935,19 +910,22 @@ static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo,
 	fence = dma_fence_get(man->move);
 	spin_unlock(&man->move_lock);
 
-	if (fence) {
-		dma_resv_add_shared_fence(bo->base.resv, fence);
+	if (!fence)
+		return 0;
 
-		ret = dma_resv_reserve_shared(bo->base.resv, 1);
-		if (unlikely(ret)) {
-			dma_fence_put(fence);
-			return ret;
-		}
+	if (no_wait_gpu)
+		return -EBUSY;
+
+	dma_resv_add_shared_fence(bo->base.resv, fence);
 
-		dma_fence_put(bo->moving);
-		bo->moving = fence;
+	ret = dma_resv_reserve_shared(bo->base.resv, 1);
+	if (unlikely(ret)) {
+		dma_fence_put(fence);
+		return ret;
 	}
 
+	dma_fence_put(bo->moving);
+	bo->moving = fence;
 	return 0;
 }
 
@@ -978,7 +956,7 @@ static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo,
 			return ret;
 	} while (1);
 
-	return ttm_bo_add_move_fence(bo, man, mem);
+	return ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
 }
 
 static uint32_t ttm_bo_select_caching(struct ttm_mem_type_manager *man,
@@ -1068,12 +1046,10 @@ static int ttm_bo_mem_placement(struct ttm_buffer_object *bo,
 	mem->mem_type = mem_type;
 	mem->placement = cur_flags;
 
-	if (bo->mem.mem_type < mem_type && !list_empty(&bo->lru)) {
-		spin_lock(&bo->bdev->glob->lru_lock);
-		ttm_bo_del_from_lru(bo);
-		ttm_bo_add_mem_to_lru(bo, mem);
-		spin_unlock(&bo->bdev->glob->lru_lock);
-	}
+	spin_lock(&ttm_bo_glob.lru_lock);
+	ttm_bo_del_from_lru(bo);
+	ttm_bo_add_mem_to_lru(bo, mem);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 
 	return 0;
 }
@@ -1120,14 +1096,18 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 		if (unlikely(ret))
 			goto error;
 
-		if (mem->mm_node) {
-			ret = ttm_bo_add_move_fence(bo, man, mem);
-			if (unlikely(ret)) {
-				(*man->func->put_node)(man, mem);
-				goto error;
-			}
-			return 0;
+		if (!mem->mm_node)
+			continue;
+
+		ret = ttm_bo_add_move_fence(bo, man, mem, ctx->no_wait_gpu);
+		if (unlikely(ret)) {
+			(*man->func->put_node)(man, mem);
+			if (ret == -EBUSY)
+				continue;
+
+			goto error;
 		}
+		return 0;
 	}
 
 	for (i = 0; i < placement->num_busy_placement; ++i) {
@@ -1160,9 +1140,9 @@ int ttm_bo_mem_space(struct ttm_buffer_object *bo,
 
 error:
 	if (bo->mem.mem_type == TTM_PL_SYSTEM && !list_empty(&bo->lru)) {
-		spin_lock(&bo->bdev->glob->lru_lock);
+		spin_lock(&ttm_bo_glob.lru_lock);
 		ttm_bo_move_to_lru_tail(bo, NULL);
-		spin_unlock(&bo->bdev->glob->lru_lock);
+		spin_unlock(&ttm_bo_glob.lru_lock);
 	}
 
 	return ret;
@@ -1286,9 +1266,9 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 			 struct dma_resv *resv,
 			 void (*destroy) (struct ttm_buffer_object *))
 {
+	struct ttm_mem_global *mem_glob = &ttm_mem_glob;
 	int ret = 0;
 	unsigned long num_pages;
-	struct ttm_mem_global *mem_glob = bdev->glob->mem_glob;
 	bool locked;
 
 	ret = ttm_mem_global_alloc(mem_glob, acc_size, ctx);
@@ -1315,7 +1295,6 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 
 	kref_init(&bo->kref);
 	kref_init(&bo->list_kref);
-	atomic_set(&bo->cpu_writers, 0);
 	INIT_LIST_HEAD(&bo->lru);
 	INIT_LIST_HEAD(&bo->ddestroy);
 	INIT_LIST_HEAD(&bo->swap);
@@ -1349,7 +1328,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		dma_resv_init(&bo->base._resv);
 		drm_vma_node_reset(&bo->base.vma_node);
 	}
-	atomic_inc(&bo->bdev->glob->bo_count);
+	atomic_inc(&ttm_bo_glob.bo_count);
 
 	/*
 	 * For ttm_bo_type_device buffers, allocate
@@ -1379,11 +1358,9 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		return ret;
 	}
 
-	if (resv && !(bo->mem.placement & TTM_PL_FLAG_NO_EVICT)) {
-		spin_lock(&bdev->glob->lru_lock);
-		ttm_bo_add_to_lru(bo);
-		spin_unlock(&bdev->glob->lru_lock);
-	}
+	spin_lock(&ttm_bo_glob.lru_lock);
+	ttm_bo_move_to_lru_tail(bo, NULL);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 
 	return ret;
 }
@@ -1481,7 +1458,7 @@ static int ttm_bo_force_list_clean(struct ttm_bo_device *bdev,
 		.flags = TTM_OPT_FLAG_FORCE_ALLOC
 	};
 	struct ttm_mem_type_manager *man = &bdev->man[mem_type];
-	struct ttm_bo_global *glob = bdev->glob;
+	struct ttm_bo_global *glob = &ttm_bo_glob;
 	struct dma_fence *fence;
 	int ret;
 	unsigned i;
@@ -1650,8 +1627,6 @@ static int ttm_bo_global_init(void)
 		goto out;
 
 	spin_lock_init(&glob->lru_lock);
-	glob->mem_glob = &ttm_mem_glob;
-	glob->mem_glob->bo_glob = glob;
 	glob->dummy_read_page = alloc_page(__GFP_ZERO | GFP_DMA32);
 
 	if (unlikely(glob->dummy_read_page == NULL)) {
@@ -1675,10 +1650,10 @@ out:
 
 int ttm_bo_device_release(struct ttm_bo_device *bdev)
 {
+	struct ttm_bo_global *glob = &ttm_bo_glob;
 	int ret = 0;
 	unsigned i = TTM_NUM_MEM_TYPES;
 	struct ttm_mem_type_manager *man;
-	struct ttm_bo_global *glob = bdev->glob;
 
 	while (i--) {
 		man = &bdev->man[i];
@@ -1747,7 +1722,6 @@ int ttm_bo_device_init(struct ttm_bo_device *bdev,
 	INIT_DELAYED_WORK(&bdev->wq, ttm_bo_delayed_workqueue);
 	INIT_LIST_HEAD(&bdev->ddestroy);
 	bdev->dev_mapping = mapping;
-	bdev->glob = glob;
 	bdev->need_dma32 = need_dma32;
 	mutex_lock(&ttm_global_mutex);
 	list_add_tail(&bdev->device_list, &glob->device_list);
@@ -1827,31 +1801,6 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 }
 EXPORT_SYMBOL(ttm_bo_wait);
 
-int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait)
-{
-	int ret = 0;
-
-	/*
-	 * Using ttm_bo_reserve makes sure the lru lists are updated.
-	 */
-
-	ret = ttm_bo_reserve(bo, true, no_wait, NULL);
-	if (unlikely(ret != 0))
-		return ret;
-	ret = ttm_bo_wait(bo, true, no_wait);
-	if (likely(ret == 0))
-		atomic_inc(&bo->cpu_writers);
-	ttm_bo_unreserve(bo);
-	return ret;
-}
-EXPORT_SYMBOL(ttm_bo_synccpu_write_grab);
-
-void ttm_bo_synccpu_write_release(struct ttm_buffer_object *bo)
-{
-	atomic_dec(&bo->cpu_writers);
-}
-EXPORT_SYMBOL(ttm_bo_synccpu_write_release);
-
 /**
  * A buffer object shrink method that tries to swap out the first
  * buffer object on the bo_global::swap_lru list.
@@ -1951,8 +1900,7 @@ void ttm_bo_swapout_all(struct ttm_bo_device *bdev)
 		.no_wait_gpu = false
 	};
 
-	while (ttm_bo_swapout(bdev->glob, &ctx) == 0)
-		;
+	while (ttm_bo_swapout(&ttm_bo_glob, &ctx) == 0);
 }
 EXPORT_SYMBOL(ttm_bo_swapout_all);
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index fe81c565e7ef..6b0883a1776e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -102,7 +102,6 @@ int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible)
 	mutex_lock(&man->io_reserve_mutex);
 	return 0;
 }
-EXPORT_SYMBOL(ttm_mem_io_lock);
 
 void ttm_mem_io_unlock(struct ttm_mem_type_manager *man)
 {
@@ -111,7 +110,6 @@ void ttm_mem_io_unlock(struct ttm_mem_type_manager *man)
 
 	mutex_unlock(&man->io_reserve_mutex);
 }
-EXPORT_SYMBOL(ttm_mem_io_unlock);
 
 static int ttm_mem_io_evict(struct ttm_mem_type_manager *man)
 {
@@ -153,7 +151,6 @@ retry:
 	}
 	return ret;
 }
-EXPORT_SYMBOL(ttm_mem_io_reserve);
 
 void ttm_mem_io_free(struct ttm_bo_device *bdev,
 		     struct ttm_mem_reg *mem)
@@ -169,7 +166,6 @@ void ttm_mem_io_free(struct ttm_bo_device *bdev,
 		bdev->driver->io_mem_free(bdev, mem);
 
 }
-EXPORT_SYMBOL(ttm_mem_io_free);
 
 int ttm_mem_io_reserve_vm(struct ttm_buffer_object *bo)
 {
@@ -503,7 +499,7 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	 * TODO: Explicit member copy would probably be better here.
 	 */
 
-	atomic_inc(&bo->bdev->glob->bo_count);
+	atomic_inc(&ttm_bo_glob.bo_count);
 	INIT_LIST_HEAD(&fbo->base.ddestroy);
 	INIT_LIST_HEAD(&fbo->base.lru);
 	INIT_LIST_HEAD(&fbo->base.swap);
@@ -511,15 +507,16 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	mutex_init(&fbo->base.wu_mutex);
 	fbo->base.moving = NULL;
 	drm_vma_node_reset(&fbo->base.base.vma_node);
-	atomic_set(&fbo->base.cpu_writers, 0);
 
 	kref_init(&fbo->base.list_kref);
 	kref_init(&fbo->base.kref);
 	fbo->base.destroy = &ttm_transfered_destroy;
 	fbo->base.acc_size = 0;
-	fbo->base.base.resv = &fbo->base.base._resv;
-	dma_resv_init(fbo->base.base.resv);
-	ret = dma_resv_trylock(fbo->base.base.resv);
+	if (bo->base.resv == &bo->base._resv)
+		fbo->base.base.resv = &fbo->base.base._resv;
+
+	dma_resv_init(&fbo->base.base._resv);
+	ret = dma_resv_trylock(&fbo->base.base._resv);
 	WARN_ON(!ret);
 
 	*new_obj = &fbo->base;
@@ -716,7 +713,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		dma_resv_add_excl_fence(ghost_obj->base.resv, fence);
+		dma_resv_add_excl_fence(&ghost_obj->base._resv, fence);
 
 		/**
 		 * If we're not moving to fixed memory, the TTM object
@@ -729,7 +726,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		else
 			bo->ttm = NULL;
 
-		ttm_bo_unreserve(ghost_obj);
+		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
 	}
 
@@ -772,7 +769,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		if (ret)
 			return ret;
 
-		dma_resv_add_excl_fence(ghost_obj->base.resv, fence);
+		dma_resv_add_excl_fence(&ghost_obj->base._resv, fence);
 
 		/**
 		 * If we're not moving to fixed memory, the TTM object
@@ -785,7 +782,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 		else
 			bo->ttm = NULL;
 
-		ttm_bo_unreserve(ghost_obj);
+		dma_resv_unlock(&ghost_obj->base._resv);
 		ttm_bo_put(ghost_obj);
 
 	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
@@ -841,7 +838,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	if (ret)
 		return ret;
 
-	ret = dma_resv_copy_fences(ghost->base.resv, bo->base.resv);
+	ret = dma_resv_copy_fences(&ghost->base._resv, bo->base.resv);
 	/* Last resort, wait for the BO to be idle when we are OOM */
 	if (ret)
 		ttm_bo_wait(bo, false, false);
@@ -850,7 +847,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	bo->mem.mem_type = TTM_PL_SYSTEM;
 	bo->ttm = NULL;
 
-	ttm_bo_unreserve(ghost);
+	dma_resv_unlock(&ghost->base._resv);
 	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 79f01c5ff65e..4b34a278d65b 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -177,9 +177,9 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 		}
 
 		if (bo->moving != moving) {
-			spin_lock(&bdev->glob->lru_lock);
+			spin_lock(&ttm_bo_glob.lru_lock);
 			ttm_bo_move_to_lru_tail(bo, NULL);
-			spin_unlock(&bdev->glob->lru_lock);
+			spin_unlock(&ttm_bo_glob.lru_lock);
 		}
 		dma_fence_put(moving);
 	}
@@ -480,6 +480,13 @@ EXPORT_SYMBOL(ttm_bo_mmap);
 int ttm_bo_mmap_obj(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 {
 	ttm_bo_get(bo);
+
+	/*
+	 * FIXME: &drm_gem_object_funcs.mmap is called with the fake offset
+	 * removed. Add it back here until the rest of TTM works without it.
+	 */
+	vma->vm_pgoff += drm_vma_node_start(&bo->base.vma_node);
+
 	ttm_bo_mmap_vma_setup(bo, vma);
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_execbuf_util.c b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
index 131dae8f4170..1797f04c0534 100644
--- a/drivers/gpu/drm/ttm/ttm_execbuf_util.c
+++ b/drivers/gpu/drm/ttm/ttm_execbuf_util.c
@@ -43,37 +43,22 @@ static void ttm_eu_backoff_reservation_reverse(struct list_head *list,
 	}
 }
 
-static void ttm_eu_del_from_lru_locked(struct list_head *list)
-{
-	struct ttm_validate_buffer *entry;
-
-	list_for_each_entry(entry, list, head) {
-		struct ttm_buffer_object *bo = entry->bo;
-		ttm_bo_del_from_lru(bo);
-	}
-}
-
 void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 				struct list_head *list)
 {
 	struct ttm_validate_buffer *entry;
-	struct ttm_bo_global *glob;
 
 	if (list_empty(list))
 		return;
 
-	entry = list_first_entry(list, struct ttm_validate_buffer, head);
-	glob = entry->bo->bdev->glob;
-
-	spin_lock(&glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
 	list_for_each_entry(entry, list, head) {
 		struct ttm_buffer_object *bo = entry->bo;
 
-		if (list_empty(&bo->lru))
-			ttm_bo_add_to_lru(bo);
+		ttm_bo_move_to_lru_tail(bo, NULL);
 		dma_resv_unlock(bo->base.resv);
 	}
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 
 	if (ticket)
 		ww_acquire_fini(ticket);
@@ -94,18 +79,14 @@ EXPORT_SYMBOL(ttm_eu_backoff_reservation);
 
 int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 			   struct list_head *list, bool intr,
-			   struct list_head *dups, bool del_lru)
+			   struct list_head *dups)
 {
-	struct ttm_bo_global *glob;
 	struct ttm_validate_buffer *entry;
 	int ret;
 
 	if (list_empty(list))
 		return 0;
 
-	entry = list_first_entry(list, struct ttm_validate_buffer, head);
-	glob = entry->bo->bdev->glob;
-
 	if (ticket)
 		ww_acquire_init(ticket, &reservation_ww_class);
 
@@ -113,12 +94,7 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 		struct ttm_buffer_object *bo = entry->bo;
 
 		ret = __ttm_bo_reserve(bo, intr, (ticket == NULL), ticket);
-		if (!ret && unlikely(atomic_read(&bo->cpu_writers) > 0)) {
-			dma_resv_unlock(bo->base.resv);
-
-			ret = -EBUSY;
-
-		} else if (ret == -EALREADY && dups) {
+		if (ret == -EALREADY && dups) {
 			struct ttm_validate_buffer *safe = entry;
 			entry = list_prev_entry(entry, head);
 			list_del(&safe->head);
@@ -173,11 +149,6 @@ int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 		list_add(&entry->head, list);
 	}
 
-	if (del_lru) {
-		spin_lock(&glob->lru_lock);
-		ttm_eu_del_from_lru_locked(list);
-		spin_unlock(&glob->lru_lock);
-	}
 	return 0;
 }
 EXPORT_SYMBOL(ttm_eu_reserve_buffers);
@@ -187,30 +158,22 @@ void ttm_eu_fence_buffer_objects(struct ww_acquire_ctx *ticket,
 				 struct dma_fence *fence)
 {
 	struct ttm_validate_buffer *entry;
-	struct ttm_buffer_object *bo;
-	struct ttm_bo_global *glob;
 
 	if (list_empty(list))
 		return;
 
-	bo = list_first_entry(list, struct ttm_validate_buffer, head)->bo;
-	glob = bo->bdev->glob;
-
-	spin_lock(&glob->lru_lock);
-
+	spin_lock(&ttm_bo_glob.lru_lock);
 	list_for_each_entry(entry, list, head) {
-		bo = entry->bo;
+		struct ttm_buffer_object *bo = entry->bo;
+
 		if (entry->num_shared)
 			dma_resv_add_shared_fence(bo->base.resv, fence);
 		else
 			dma_resv_add_excl_fence(bo->base.resv, fence);
-		if (list_empty(&bo->lru))
-			ttm_bo_add_to_lru(bo);
-		else
-			ttm_bo_move_to_lru_tail(bo, NULL);
+		ttm_bo_move_to_lru_tail(bo, NULL);
 		dma_resv_unlock(bo->base.resv);
 	}
-	spin_unlock(&glob->lru_lock);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 	if (ticket)
 		ww_acquire_fini(ticket);
 }
diff --git a/drivers/gpu/drm/ttm/ttm_memory.c b/drivers/gpu/drm/ttm/ttm_memory.c
index 8617958b7ae6..acd63b70d814 100644
--- a/drivers/gpu/drm/ttm/ttm_memory.c
+++ b/drivers/gpu/drm/ttm/ttm_memory.c
@@ -275,7 +275,7 @@ static void ttm_shrink(struct ttm_mem_global *glob, bool from_wq,
 
 	while (ttm_zones_above_swap_target(glob, from_wq, extra)) {
 		spin_unlock(&glob->lock);
-		ret = ttm_bo_swapout(glob->bo_glob, ctx);
+		ret = ttm_bo_swapout(&ttm_bo_glob, ctx);
 		spin_lock(&glob->lock);
 		if (unlikely(ret != 0))
 			break;
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 627f8dc91d0e..b40a4678c296 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -1028,7 +1028,7 @@ void ttm_page_alloc_fini(void)
 static void
 ttm_pool_unpopulate_helper(struct ttm_tt *ttm, unsigned mem_count_update)
 {
-	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
+	struct ttm_mem_global *mem_glob = &ttm_mem_glob;
 	unsigned i;
 
 	if (mem_count_update == 0)
@@ -1049,7 +1049,7 @@ put_pages:
 
 int ttm_pool_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
 {
-	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
+	struct ttm_mem_global *mem_glob = &ttm_mem_glob;
 	unsigned i;
 	int ret;
 
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 7d78e6deac89..bf876faea592 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -33,7 +33,6 @@
  *   when freed).
  */
 
-#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
 #define pr_fmt(fmt) "[TTM] " fmt
 
 #include <linux/dma-mapping.h>
@@ -886,8 +885,8 @@ static gfp_t ttm_dma_pool_gfp_flags(struct ttm_dma_tt *ttm_dma, bool huge)
 int ttm_dma_populate(struct ttm_dma_tt *ttm_dma, struct device *dev,
 			struct ttm_operation_ctx *ctx)
 {
+	struct ttm_mem_global *mem_glob = &ttm_mem_glob;
 	struct ttm_tt *ttm = &ttm_dma->ttm;
-	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
 	unsigned long num_pages = ttm->num_pages;
 	struct dma_pool *pool;
 	struct dma_page *d_page;
@@ -991,8 +990,8 @@ EXPORT_SYMBOL_GPL(ttm_dma_populate);
 /* Put all pages in pages list to correct pool to wait for reuse */
 void ttm_dma_unpopulate(struct ttm_dma_tt *ttm_dma, struct device *dev)
 {
+	struct ttm_mem_global *mem_glob = &ttm_mem_glob;
 	struct ttm_tt *ttm = &ttm_dma->ttm;
-	struct ttm_mem_global *mem_glob = ttm->bdev->glob->mem_glob;
 	struct dma_pool *pool;
 	struct dma_page *d_page, *next;
 	enum pool_type type;
@@ -1238,5 +1237,3 @@ int ttm_dma_page_alloc_debugfs(struct seq_file *m, void *data)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ttm_dma_page_alloc_debugfs);
-
-#endif
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 4c4b59ae2c81..549dde83408b 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -560,14 +560,17 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 
 	if (args->bcl_start != args->bcl_end) {
 		bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
-		if (!bin)
+		if (!bin) {
+			v3d_job_put(&render->base);
 			return -ENOMEM;
+		}
 
 		ret = v3d_job_init(v3d, file_priv, &bin->base,
 				   v3d_job_free, args->in_sync_bcl);
 		if (ret) {
 			kfree(bin);
 			v3d_job_put(&render->base);
+			kfree(bin);
 			return ret;
 		}
 
diff --git a/drivers/gpu/drm/vboxvideo/vbox_mode.c b/drivers/gpu/drm/vboxvideo/vbox_mode.c
index b5604d32122e..19612132c8a3 100644
--- a/drivers/gpu/drm/vboxvideo/vbox_mode.c
+++ b/drivers/gpu/drm/vboxvideo/vbox_mode.c
@@ -334,35 +334,6 @@ static void vbox_primary_atomic_disable(struct drm_plane *plane,
 				    old_state->src_y >> 16);
 }
 
-static int vbox_primary_prepare_fb(struct drm_plane *plane,
-				   struct drm_plane_state *new_state)
-{
-	struct drm_gem_vram_object *gbo;
-	int ret;
-
-	if (!new_state->fb)
-		return 0;
-
-	gbo = drm_gem_vram_of_gem(new_state->fb->obj[0]);
-	ret = drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_VRAM);
-	if (ret)
-		DRM_WARN("Error %d pinning new fb, out of video mem?\n", ret);
-
-	return ret;
-}
-
-static void vbox_primary_cleanup_fb(struct drm_plane *plane,
-				    struct drm_plane_state *old_state)
-{
-	struct drm_gem_vram_object *gbo;
-
-	if (!old_state->fb)
-		return;
-
-	gbo = drm_gem_vram_of_gem(old_state->fb->obj[0]);
-	drm_gem_vram_unpin(gbo);
-}
-
 static int vbox_cursor_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *new_state)
 {
@@ -492,30 +463,6 @@ static void vbox_cursor_atomic_disable(struct drm_plane *plane,
 	mutex_unlock(&vbox->hw_mutex);
 }
 
-static int vbox_cursor_prepare_fb(struct drm_plane *plane,
-				  struct drm_plane_state *new_state)
-{
-	struct drm_gem_vram_object *gbo;
-
-	if (!new_state->fb)
-		return 0;
-
-	gbo = drm_gem_vram_of_gem(new_state->fb->obj[0]);
-	return drm_gem_vram_pin(gbo, DRM_GEM_VRAM_PL_FLAG_SYSTEM);
-}
-
-static void vbox_cursor_cleanup_fb(struct drm_plane *plane,
-				   struct drm_plane_state *old_state)
-{
-	struct drm_gem_vram_object *gbo;
-
-	if (!plane->state->fb)
-		return;
-
-	gbo = drm_gem_vram_of_gem(plane->state->fb->obj[0]);
-	drm_gem_vram_unpin(gbo);
-}
-
 static const u32 vbox_cursor_plane_formats[] = {
 	DRM_FORMAT_ARGB8888,
 };
@@ -524,8 +471,8 @@ static const struct drm_plane_helper_funcs vbox_cursor_helper_funcs = {
 	.atomic_check	= vbox_cursor_atomic_check,
 	.atomic_update	= vbox_cursor_atomic_update,
 	.atomic_disable	= vbox_cursor_atomic_disable,
-	.prepare_fb	= vbox_cursor_prepare_fb,
-	.cleanup_fb	= vbox_cursor_cleanup_fb,
+	.prepare_fb	= drm_gem_vram_plane_helper_prepare_fb,
+	.cleanup_fb	= drm_gem_vram_plane_helper_cleanup_fb,
 };
 
 static const struct drm_plane_funcs vbox_cursor_plane_funcs = {
@@ -546,8 +493,8 @@ static const struct drm_plane_helper_funcs vbox_primary_helper_funcs = {
 	.atomic_check = vbox_primary_atomic_check,
 	.atomic_update = vbox_primary_atomic_update,
 	.atomic_disable = vbox_primary_atomic_disable,
-	.prepare_fb = vbox_primary_prepare_fb,
-	.cleanup_fb = vbox_primary_cleanup_fb,
+	.prepare_fb	= drm_gem_vram_plane_helper_prepare_fb,
+	.cleanup_fb	= drm_gem_vram_plane_helper_cleanup_fb,
 };
 
 static const struct drm_plane_funcs vbox_primary_plane_funcs = {
@@ -890,7 +837,7 @@ static int vbox_connector_init(struct drm_device *dev,
 }
 
 static const struct drm_mode_config_funcs vbox_mode_funcs = {
-	.fb_create = drm_gem_fb_create,
+	.fb_create = drm_gem_fb_create_with_dirty,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index aad8d8140259..74016a08d118 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -566,7 +566,7 @@ static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base,
 
 	switch (ref_type) {
 	case TTM_REF_SYNCCPU_WRITE:
-		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+		atomic_dec(&user_bo->vbo.cpu_writers);
 		break;
 	default:
 		WARN_ONCE(true, "Undefined buffer object reference release.\n");
@@ -682,12 +682,12 @@ static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
 				    struct ttm_object_file *tfile,
 				    uint32_t flags)
 {
+	bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
 	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 = dma_resv_wait_timeout_rcu
@@ -700,15 +700,22 @@ static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
 		return 0;
 	}
 
-	ret = ttm_bo_synccpu_write_grab
-		(bo, !!(flags & drm_vmw_synccpu_dontblock));
+	ret = ttm_bo_reserve(bo, true, nonblock, NULL);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_bo_wait(bo, true, nonblock);
+	if (likely(ret == 0))
+		atomic_inc(&user_bo->vbo.cpu_writers);
+
+	ttm_bo_unreserve(bo);
 	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);
+		atomic_dec(&user_bo->vbo.cpu_writers);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 81a95651643f..e962048f65d2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -576,8 +576,7 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv)
 	else
 		dev_priv->map_mode = vmw_dma_map_populate;
 
-	/* No TTM coherent page pool? FIXME: Ask TTM instead! */
-        if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) &&
+        if (!IS_ENABLED(CONFIG_DRM_TTM_DMA_PAGE_POOL) &&
 	    (dev_priv->map_mode == vmw_dma_alloc_coherent))
 		return -EINVAL;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 29f60e027a38..b18842f73081 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -102,6 +102,8 @@ struct vmw_fpriv {
  * @base: The TTM buffer object
  * @res_list: List of resources using this buffer object as a backing MOB
  * @pin_count: pin depth
+ * @cpu_writers: Number of synccpu write grabs. Protected by reservation when
+ * increased. May be decreased without reservation.
  * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB
  * @map: Kmap object for semi-persistent mappings
  * @res_prios: Eviction priority counts for attached resources
@@ -110,6 +112,7 @@ struct vmw_buffer_object {
 	struct ttm_buffer_object base;
 	struct list_head res_list;
 	s32 pin_count;
+	atomic_t cpu_writers;
 	/* Not ref-counted.  Protected by binding_mutex */
 	struct vmw_resource *dx_query_ctx;
 	/* Protected by reservation */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 5581a7826b4c..6dfe36fb817c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -492,8 +492,7 @@ vmw_resource_check_buffer(struct ww_acquire_ctx *ticket,
 	val_buf->bo = &res->backup->base;
 	val_buf->num_shared = 0;
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(ticket, &val_list, interruptible, NULL,
-				     true);
+	ret = ttm_eu_reserve_buffers(ticket, &val_list, interruptible, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 29d8794f0421..de0530b4dc1b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -336,7 +336,6 @@ static void vmw_hw_surface_destroy(struct vmw_resource *res)
 {
 
 	struct vmw_private *dev_priv = res->dev_priv;
-	struct vmw_surface *srf;
 	void *cmd;
 
 	if (res->func->destroy == vmw_gb_surface_destroy) {
@@ -360,7 +359,6 @@ static void vmw_hw_surface_destroy(struct vmw_resource *res)
 		 */
 
 		mutex_lock(&dev_priv->cmdbuf_mutex);
-		srf = vmw_res_to_srf(res);
 		dev_priv->used_memory_size -= res->backup_size;
 		mutex_unlock(&dev_priv->cmdbuf_mutex);
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
index f611b2290a1b..7bff3628fc54 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c
@@ -521,6 +521,9 @@ int vmw_validation_bo_validate_single(struct ttm_buffer_object *bo,
 	};
 	int ret;
 
+	if (atomic_read(&vbo->cpu_writers))
+		return -EBUSY;
+
 	if (vbo->pin_count > 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h
index 0e063743dd86..71ce4b318850 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h
@@ -170,7 +170,7 @@ vmw_validation_bo_reserve(struct vmw_validation_context *ctx,
 			  bool intr)
 {
 	return ttm_eu_reserve_buffers(&ctx->ticket, &ctx->bo_list, intr,
-				      NULL, true);
+				      NULL);
 }
 
 /**
diff --git a/drivers/gpu/drm/xen/xen_drm_front_kms.c b/drivers/gpu/drm/xen/xen_drm_front_kms.c
index 21ad1c359b61..ff506bc99414 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_kms.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_kms.c
@@ -270,11 +270,12 @@ static void display_update(struct drm_simple_display_pipe *pipe,
 }
 
 static enum drm_mode_status
-display_mode_valid(struct drm_crtc *crtc, const struct drm_display_mode *mode)
+display_mode_valid(struct drm_simple_display_pipe *pipe,
+		   const struct drm_display_mode *mode)
 {
 	struct xen_drm_front_drm_pipeline *pipeline =
-			container_of(crtc, struct xen_drm_front_drm_pipeline,
-				     pipe.crtc);
+			container_of(pipe, struct xen_drm_front_drm_pipeline,
+				     pipe);
 
 	if (mode->hdisplay != pipeline->width)
 		return MODE_ERROR;
diff --git a/drivers/hid/hid-axff.c b/drivers/hid/hid-axff.c
index 6654c1550e2e..fbe4e16ab029 100644
--- a/drivers/hid/hid-axff.c
+++ b/drivers/hid/hid-axff.c
@@ -63,13 +63,20 @@ static int axff_init(struct hid_device *hid)
 {
 	struct axff_device *axff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int field_count = 0;
 	int i, j;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 3eaee2c37931..63fdbf09b044 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1139,6 +1139,7 @@ int hid_open_report(struct hid_device *device)
 	__u8 *start;
 	__u8 *buf;
 	__u8 *end;
+	__u8 *next;
 	int ret;
 	static int (*dispatch_type[])(struct hid_parser *parser,
 				      struct hid_item *item) = {
@@ -1192,7 +1193,8 @@ int hid_open_report(struct hid_device *device)
 	device->collection_size = HID_DEFAULT_NUM_COLLECTIONS;
 
 	ret = -EINVAL;
-	while ((start = fetch_item(start, end, &item)) != NULL) {
+	while ((next = fetch_item(start, end, &item)) != NULL) {
+		start = next;
 
 		if (item.format != HID_ITEM_FORMAT_SHORT) {
 			hid_err(device, "unexpected long global item\n");
@@ -1230,7 +1232,8 @@ int hid_open_report(struct hid_device *device)
 		}
 	}
 
-	hid_err(device, "item fetching failed at offset %d\n", (int)(end - start));
+	hid_err(device, "item fetching failed at offset %u/%u\n",
+		size - (unsigned int)(end - start), size);
 err:
 	kfree(parser->collection_stack);
 alloc_err:
diff --git a/drivers/hid/hid-dr.c b/drivers/hid/hid-dr.c
index 17e17f9a597b..947f19f8685f 100644
--- a/drivers/hid/hid-dr.c
+++ b/drivers/hid/hid-dr.c
@@ -75,13 +75,19 @@ static int drff_init(struct hid_device *hid)
 {
 	struct drff_device *drff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_first_entry(&hid->inputs,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-emsff.c b/drivers/hid/hid-emsff.c
index 7cd5651872d3..c34f2e5a049f 100644
--- a/drivers/hid/hid-emsff.c
+++ b/drivers/hid/hid-emsff.c
@@ -47,13 +47,19 @@ static int emsff_init(struct hid_device *hid)
 {
 	struct emsff_device *emsff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_first_entry(&hid->inputs,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_first_entry(&hid->inputs, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-gaff.c b/drivers/hid/hid-gaff.c
index 0f95c96b70f8..ecbd3995a4eb 100644
--- a/drivers/hid/hid-gaff.c
+++ b/drivers/hid/hid-gaff.c
@@ -64,14 +64,20 @@ static int gaff_init(struct hid_device *hid)
 {
 	struct gaff_device *gaff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct list_head *report_ptr = report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output reports found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 84f8c127ebdc..d86a9189e88f 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -470,6 +470,10 @@ static const struct hid_device_id hammer_devices[] = {
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_HAMMER) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MAGNEMITE) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
+		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_MASTERBALL) },
+	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_STAFF) },
 	{ HID_DEVICE(BUS_USB, HID_GROUP_GENERIC,
 		     USB_VENDOR_ID_GOOGLE, USB_DEVICE_ID_GOOGLE_WAND) },
diff --git a/drivers/hid/hid-holtekff.c b/drivers/hid/hid-holtekff.c
index 10a720558830..8619b80c834c 100644
--- a/drivers/hid/hid-holtekff.c
+++ b/drivers/hid/hid-holtekff.c
@@ -124,13 +124,19 @@ static int holtekff_init(struct hid_device *hid)
 {
 	struct holtekff_device *holtekff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
+	struct hid_input *hidinput;
 	struct list_head *report_list =
 			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
-	struct input_dev *dev = hidinput->input;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (list_empty(report_list)) {
 		hid_err(hid, "no output report found\n");
 		return -ENODEV;
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 76969a22b0f2..447e8db21174 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -476,6 +476,8 @@
 #define USB_DEVICE_ID_GOOGLE_STAFF	0x502b
 #define USB_DEVICE_ID_GOOGLE_WAND	0x502d
 #define USB_DEVICE_ID_GOOGLE_WHISKERS	0x5030
+#define USB_DEVICE_ID_GOOGLE_MASTERBALL	0x503c
+#define USB_DEVICE_ID_GOOGLE_MAGNEMITE	0x503d
 
 #define USB_VENDOR_ID_GOTOP		0x08f2
 #define USB_DEVICE_ID_SUPER_Q2		0x007f
diff --git a/drivers/hid/hid-lg2ff.c b/drivers/hid/hid-lg2ff.c
index dd1a6c3a7de6..73d07e35f12a 100644
--- a/drivers/hid/hid-lg2ff.c
+++ b/drivers/hid/hid-lg2ff.c
@@ -50,11 +50,17 @@ int lg2ff_init(struct hid_device *hid)
 {
 	struct lg2ff_device *lg2ff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	int error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7);
 	if (!report)
diff --git a/drivers/hid/hid-lg3ff.c b/drivers/hid/hid-lg3ff.c
index 9ecb6fd06203..b7e1949f3cf7 100644
--- a/drivers/hid/hid-lg3ff.c
+++ b/drivers/hid/hid-lg3ff.c
@@ -117,12 +117,19 @@ static const signed short ff3_joystick_ac[] = {
 
 int lg3ff_init(struct hid_device *hid)
 {
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	const signed short *ff_bits = ff3_joystick_ac;
 	int error;
 	int i;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 35))
 		return -ENODEV;
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index 03f0220062ca..5e6a0cef2a06 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -1253,8 +1253,8 @@ static int lg4ff_handle_multimode_wheel(struct hid_device *hid, u16 *real_produc
 
 int lg4ff_init(struct hid_device *hid)
 {
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	struct list_head *report_list = &hid->report_enum[HID_OUTPUT_REPORT].report_list;
 	struct hid_report *report = list_entry(report_list->next, struct hid_report, list);
 	const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor);
@@ -1266,6 +1266,13 @@ int lg4ff_init(struct hid_device *hid)
 	int mmode_ret, mmode_idx = -1;
 	u16 real_product_id;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -1;
diff --git a/drivers/hid/hid-lgff.c b/drivers/hid/hid-lgff.c
index c79a6ec43745..aed4ddc397a9 100644
--- a/drivers/hid/hid-lgff.c
+++ b/drivers/hid/hid-lgff.c
@@ -115,12 +115,19 @@ static void hid_lgff_set_autocenter(struct input_dev *dev, u16 magnitude)
 
 int lgff_init(struct hid_device* hid)
 {
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	const signed short *ff_bits = ff_joystick;
 	int error;
 	int i;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	/* Check that the report looks ok */
 	if (!hid_validate_values(hid, HID_OUTPUT_REPORT, 0, 0, 7))
 		return -ENODEV;
diff --git a/drivers/hid/hid-logitech-hidpp.c b/drivers/hid/hid-logitech-hidpp.c
index 0179f7ed77e5..8e91e2f06cb4 100644
--- a/drivers/hid/hid-logitech-hidpp.c
+++ b/drivers/hid/hid-logitech-hidpp.c
@@ -1669,6 +1669,7 @@ static void hidpp_touchpad_raw_xy_event(struct hidpp_device *hidpp_dev,
 
 #define HIDPP_FF_EFFECTID_NONE		-1
 #define HIDPP_FF_EFFECTID_AUTOCENTER	-2
+#define HIDPP_AUTOCENTER_PARAMS_LENGTH	18
 
 #define HIDPP_FF_MAX_PARAMS	20
 #define HIDPP_FF_RESERVED_SLOTS	1
@@ -2009,7 +2010,7 @@ static int hidpp_ff_erase_effect(struct input_dev *dev, int effect_id)
 static void hidpp_ff_set_autocenter(struct input_dev *dev, u16 magnitude)
 {
 	struct hidpp_ff_private_data *data = dev->ff->private;
-	u8 params[18];
+	u8 params[HIDPP_AUTOCENTER_PARAMS_LENGTH];
 
 	dbg_hid("Setting autocenter to %d.\n", magnitude);
 
@@ -2077,23 +2078,34 @@ static DEVICE_ATTR(range, S_IRUSR | S_IWUSR | S_IRGRP | S_IWGRP | S_IROTH, hidpp
 static void hidpp_ff_destroy(struct ff_device *ff)
 {
 	struct hidpp_ff_private_data *data = ff->private;
+	struct hid_device *hid = data->hidpp->hid_dev;
 
+	hid_info(hid, "Unloading HID++ force feedback.\n");
+
+	device_remove_file(&hid->dev, &dev_attr_range);
+	destroy_workqueue(data->wq);
 	kfree(data->effect_ids);
 }
 
-static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
+static int hidpp_ff_init(struct hidpp_device *hidpp,
+			 struct hidpp_ff_private_data *data)
 {
 	struct hid_device *hid = hidpp->hid_dev;
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	const struct usb_device_descriptor *udesc = &(hid_to_usb_dev(hid)->descriptor);
 	const u16 bcdDevice = le16_to_cpu(udesc->bcdDevice);
 	struct ff_device *ff;
-	struct hidpp_report response;
-	struct hidpp_ff_private_data *data;
-	int error, j, num_slots;
+	int error, j, num_slots = data->num_effects;
 	u8 version;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	if (!dev) {
 		hid_err(hid, "Struct input_dev not set!\n");
 		return -EINVAL;
@@ -2109,27 +2121,17 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 		for (j = 0; hidpp_ff_effects_v2[j] >= 0; j++)
 			set_bit(hidpp_ff_effects_v2[j], dev->ffbit);
 
-	/* Read number of slots available in device */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_GET_INFO, NULL, 0, &response);
-	if (error) {
-		if (error < 0)
-			return error;
-		hid_err(hidpp->hid_dev, "%s: received protocol error 0x%02x\n",
-			__func__, error);
-		return -EPROTO;
-	}
-
-	num_slots = response.fap.params[0] - HIDPP_FF_RESERVED_SLOTS;
-
 	error = input_ff_create(dev, num_slots);
 
 	if (error) {
 		hid_err(dev, "Failed to create FF device!\n");
 		return error;
 	}
-
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	/*
+	 * Create a copy of passed data, so we can transfer memory
+	 * ownership to FF core
+	 */
+	data = kmemdup(data, sizeof(*data), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 	data->effect_ids = kcalloc(num_slots, sizeof(int), GFP_KERNEL);
@@ -2145,10 +2147,7 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 	}
 
 	data->hidpp = hidpp;
-	data->feature_index = feature_index;
 	data->version = version;
-	data->slot_autocenter = 0;
-	data->num_effects = num_slots;
 	for (j = 0; j < num_slots; j++)
 		data->effect_ids[j] = -1;
 
@@ -2162,68 +2161,20 @@ static int hidpp_ff_init(struct hidpp_device *hidpp, u8 feature_index)
 	ff->set_autocenter = hidpp_ff_set_autocenter;
 	ff->destroy = hidpp_ff_destroy;
 
-
-	/* reset all forces */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_RESET_ALL, NULL, 0, &response);
-
-	/* Read current Range */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_GET_APERTURE, NULL, 0, &response);
-	if (error)
-		hid_warn(hidpp->hid_dev, "Failed to read range from device!\n");
-	data->range = error ? 900 : get_unaligned_be16(&response.fap.params[0]);
-
 	/* Create sysfs interface */
 	error = device_create_file(&(hidpp->hid_dev->dev), &dev_attr_range);
 	if (error)
 		hid_warn(hidpp->hid_dev, "Unable to create sysfs interface for \"range\", errno %d!\n", error);
 
-	/* Read the current gain values */
-	error = hidpp_send_fap_command_sync(hidpp, feature_index,
-		HIDPP_FF_GET_GLOBAL_GAINS, NULL, 0, &response);
-	if (error)
-		hid_warn(hidpp->hid_dev, "Failed to read gain values from device!\n");
-	data->gain = error ? 0xffff : get_unaligned_be16(&response.fap.params[0]);
-	/* ignore boost value at response.fap.params[2] */
-
 	/* init the hardware command queue */
 	atomic_set(&data->workqueue_size, 0);
 
-	/* initialize with zero autocenter to get wheel in usable state */
-	hidpp_ff_set_autocenter(dev, 0);
-
 	hid_info(hid, "Force feedback support loaded (firmware release %d).\n",
 		 version);
 
 	return 0;
 }
 
-static int hidpp_ff_deinit(struct hid_device *hid)
-{
-	struct hid_input *hidinput = list_entry(hid->inputs.next, struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
-	struct hidpp_ff_private_data *data;
-
-	if (!dev) {
-		hid_err(hid, "Struct input_dev not found!\n");
-		return -EINVAL;
-	}
-
-	hid_info(hid, "Unloading HID++ force feedback.\n");
-	data = dev->ff->private;
-	if (!data) {
-		hid_err(hid, "Private data not found!\n");
-		return -EINVAL;
-	}
-
-	destroy_workqueue(data->wq);
-	device_remove_file(&hid->dev, &dev_attr_range);
-
-	return 0;
-}
-
-
 /* ************************************************************************** */
 /*                                                                            */
 /* Device Support                                                             */
@@ -2725,24 +2676,93 @@ static int k400_connect(struct hid_device *hdev, bool connected)
 
 #define HIDPP_PAGE_G920_FORCE_FEEDBACK			0x8123
 
-static int g920_get_config(struct hidpp_device *hidpp)
+static int g920_ff_set_autocenter(struct hidpp_device *hidpp,
+				  struct hidpp_ff_private_data *data)
 {
+	struct hidpp_report response;
+	u8 params[HIDPP_AUTOCENTER_PARAMS_LENGTH] = {
+		[1] = HIDPP_FF_EFFECT_SPRING | HIDPP_FF_EFFECT_AUTOSTART,
+	};
+	int ret;
+
+	/* initialize with zero autocenter to get wheel in usable state */
+
+	dbg_hid("Setting autocenter to 0.\n");
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_DOWNLOAD_EFFECT,
+					  params, ARRAY_SIZE(params),
+					  &response);
+	if (ret)
+		hid_warn(hidpp->hid_dev, "Failed to autocenter device!\n");
+	else
+		data->slot_autocenter = response.fap.params[0];
+
+	return ret;
+}
+
+static int g920_get_config(struct hidpp_device *hidpp,
+			   struct hidpp_ff_private_data *data)
+{
+	struct hidpp_report response;
 	u8 feature_type;
-	u8 feature_index;
 	int ret;
 
+	memset(data, 0, sizeof(*data));
+
 	/* Find feature and store for later use */
 	ret = hidpp_root_get_feature(hidpp, HIDPP_PAGE_G920_FORCE_FEEDBACK,
-		&feature_index, &feature_type);
+				     &data->feature_index, &feature_type);
 	if (ret)
 		return ret;
 
-	ret = hidpp_ff_init(hidpp, feature_index);
+	/* Read number of slots available in device */
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_GET_INFO,
+					  NULL, 0,
+					  &response);
+	if (ret) {
+		if (ret < 0)
+			return ret;
+		hid_err(hidpp->hid_dev,
+			"%s: received protocol error 0x%02x\n", __func__, ret);
+		return -EPROTO;
+	}
+
+	data->num_effects = response.fap.params[0] - HIDPP_FF_RESERVED_SLOTS;
+
+	/* reset all forces */
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_RESET_ALL,
+					  NULL, 0,
+					  &response);
 	if (ret)
-		hid_warn(hidpp->hid_dev, "Unable to initialize force feedback support, errno %d\n",
-				ret);
+		hid_warn(hidpp->hid_dev, "Failed to reset all forces!\n");
 
-	return 0;
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_GET_APERTURE,
+					  NULL, 0,
+					  &response);
+	if (ret) {
+		hid_warn(hidpp->hid_dev,
+			 "Failed to read range from device!\n");
+	}
+	data->range = ret ?
+		900 : get_unaligned_be16(&response.fap.params[0]);
+
+	/* Read the current gain values */
+	ret = hidpp_send_fap_command_sync(hidpp, data->feature_index,
+					  HIDPP_FF_GET_GLOBAL_GAINS,
+					  NULL, 0,
+					  &response);
+	if (ret)
+		hid_warn(hidpp->hid_dev,
+			 "Failed to read gain values from device!\n");
+	data->gain = ret ?
+		0xffff : get_unaligned_be16(&response.fap.params[0]);
+
+	/* ignore boost value at response.fap.params[2] */
+
+	return g920_ff_set_autocenter(hidpp, data);
 }
 
 /* -------------------------------------------------------------------------- */
@@ -3458,34 +3478,45 @@ static int hidpp_get_report_length(struct hid_device *hdev, int id)
 	return report->field[0]->report_count + 1;
 }
 
-static bool hidpp_validate_report(struct hid_device *hdev, int id,
-				  int expected_length, bool optional)
+static bool hidpp_validate_device(struct hid_device *hdev)
 {
-	int report_length;
+	struct hidpp_device *hidpp = hid_get_drvdata(hdev);
+	int id, report_length, supported_reports = 0;
 
-	if (id >= HID_MAX_IDS || id < 0) {
-		hid_err(hdev, "invalid HID report id %u\n", id);
-		return false;
+	id = REPORT_ID_HIDPP_SHORT;
+	report_length = hidpp_get_report_length(hdev, id);
+	if (report_length) {
+		if (report_length < HIDPP_REPORT_SHORT_LENGTH)
+			goto bad_device;
+
+		supported_reports++;
 	}
 
+	id = REPORT_ID_HIDPP_LONG;
 	report_length = hidpp_get_report_length(hdev, id);
-	if (!report_length)
-		return optional;
+	if (report_length) {
+		if (report_length < HIDPP_REPORT_LONG_LENGTH)
+			goto bad_device;
 
-	if (report_length < expected_length) {
-		hid_warn(hdev, "not enough values in hidpp report %d\n", id);
-		return false;
+		supported_reports++;
 	}
 
-	return true;
-}
+	id = REPORT_ID_HIDPP_VERY_LONG;
+	report_length = hidpp_get_report_length(hdev, id);
+	if (report_length) {
+		if (report_length < HIDPP_REPORT_LONG_LENGTH ||
+		    report_length > HIDPP_REPORT_VERY_LONG_MAX_LENGTH)
+			goto bad_device;
 
-static bool hidpp_validate_device(struct hid_device *hdev)
-{
-	return hidpp_validate_report(hdev, REPORT_ID_HIDPP_SHORT,
-				     HIDPP_REPORT_SHORT_LENGTH, false) &&
-	       hidpp_validate_report(hdev, REPORT_ID_HIDPP_LONG,
-				     HIDPP_REPORT_LONG_LENGTH, true);
+		supported_reports++;
+		hidpp->very_long_report_length = report_length;
+	}
+
+	return supported_reports;
+
+bad_device:
+	hid_warn(hdev, "not enough values in hidpp report %d\n", id);
+	return false;
 }
 
 static bool hidpp_application_equals(struct hid_device *hdev,
@@ -3505,6 +3536,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	int ret;
 	bool connected;
 	unsigned int connect_mask = HID_CONNECT_DEFAULT;
+	struct hidpp_ff_private_data data;
 
 	/* report_fixup needs drvdata to be set before we call hid_parse */
 	hidpp = devm_kzalloc(&hdev->dev, sizeof(*hidpp), GFP_KERNEL);
@@ -3531,11 +3563,6 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		return hid_hw_start(hdev, HID_CONNECT_DEFAULT);
 	}
 
-	hidpp->very_long_report_length =
-		hidpp_get_report_length(hdev, REPORT_ID_HIDPP_VERY_LONG);
-	if (hidpp->very_long_report_length > HIDPP_REPORT_VERY_LONG_MAX_LENGTH)
-		hidpp->very_long_report_length = HIDPP_REPORT_VERY_LONG_MAX_LENGTH;
-
 	if (id->group == HID_GROUP_LOGITECH_DJ_DEVICE)
 		hidpp->quirks |= HIDPP_QUIRK_UNIFYING;
 
@@ -3614,7 +3641,7 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		if (ret)
 			goto hid_hw_init_fail;
 	} else if (connected && (hidpp->quirks & HIDPP_QUIRK_CLASS_G920)) {
-		ret = g920_get_config(hidpp);
+		ret = g920_get_config(hidpp, &data);
 		if (ret)
 			goto hid_hw_init_fail;
 	}
@@ -3636,6 +3663,14 @@ static int hidpp_probe(struct hid_device *hdev, const struct hid_device_id *id)
 		goto hid_hw_start_fail;
 	}
 
+	if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920) {
+		ret = hidpp_ff_init(hidpp, &data);
+		if (ret)
+			hid_warn(hidpp->hid_dev,
+		     "Unable to initialize force feedback support, errno %d\n",
+				 ret);
+	}
+
 	return ret;
 
 hid_hw_init_fail:
@@ -3658,9 +3693,6 @@ static void hidpp_remove(struct hid_device *hdev)
 
 	sysfs_remove_group(&hdev->dev.kobj, &ps_attribute_group);
 
-	if (hidpp->quirks & HIDPP_QUIRK_CLASS_G920)
-		hidpp_ff_deinit(hdev);
-
 	hid_hw_stop(hdev);
 	cancel_work_sync(&hidpp->work);
 	mutex_destroy(&hidpp->send_mutex);
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 2cf83856f2e4..2d8b589201a4 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -328,11 +328,17 @@ static int ms_play_effect(struct input_dev *dev, void *data,
 
 static int ms_init_ff(struct hid_device *hdev)
 {
-	struct hid_input *hidinput = list_entry(hdev->inputs.next,
-						struct hid_input, list);
-	struct input_dev *input_dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *input_dev;
 	struct ms_data *ms = hid_get_drvdata(hdev);
 
+	if (list_empty(&hdev->inputs)) {
+		hid_err(hdev, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hdev->inputs.next, struct hid_input, list);
+	input_dev = hidinput->input;
+
 	if (!(ms->quirks & MS_QUIRK_FF))
 		return 0;
 
diff --git a/drivers/hid/hid-prodikeys.c b/drivers/hid/hid-prodikeys.c
index 5a3b3d974d84..2666af02d5c1 100644
--- a/drivers/hid/hid-prodikeys.c
+++ b/drivers/hid/hid-prodikeys.c
@@ -516,7 +516,7 @@ static void pcmidi_setup_extra_keys(
 		MY PICTURES =>	KEY_WORDPROCESSOR
 		MY MUSIC=>	KEY_SPREADSHEET
 	*/
-	unsigned int keys[] = {
+	static const unsigned int keys[] = {
 		KEY_FN,
 		KEY_MESSENGER, KEY_CALENDAR,
 		KEY_ADDRESSBOOK, KEY_DOCUMENTS,
@@ -532,7 +532,7 @@ static void pcmidi_setup_extra_keys(
 		0
 	};
 
-	unsigned int *pkeys = &keys[0];
+	const unsigned int *pkeys = &keys[0];
 	unsigned short i;
 
 	if (pm->ifnum != 1)  /* only set up ONCE for interace 1 */
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 73c0f7a95e2d..4c6ed6ef31f1 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -2254,9 +2254,15 @@ static int sony_play_effect(struct input_dev *dev, void *data,
 
 static int sony_init_ff(struct sony_sc *sc)
 {
-	struct hid_input *hidinput = list_entry(sc->hdev->inputs.next,
-						struct hid_input, list);
-	struct input_dev *input_dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *input_dev;
+
+	if (list_empty(&sc->hdev->inputs)) {
+		hid_err(sc->hdev, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(sc->hdev->inputs.next, struct hid_input, list);
+	input_dev = hidinput->input;
 
 	input_set_capability(input_dev, EV_FF, FF_RUMBLE);
 	return input_ff_create_memless(input_dev, NULL, sony_play_effect);
diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c
index bdfc5ff3b2c5..90acef304536 100644
--- a/drivers/hid/hid-tmff.c
+++ b/drivers/hid/hid-tmff.c
@@ -124,12 +124,18 @@ static int tmff_init(struct hid_device *hid, const signed short *ff_bits)
 	struct tmff_device *tmff;
 	struct hid_report *report;
 	struct list_head *report_list;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-							struct hid_input, list);
-	struct input_dev *input_dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *input_dev;
 	int error;
 	int i;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	input_dev = hidinput->input;
+
 	tmff = kzalloc(sizeof(struct tmff_device), GFP_KERNEL);
 	if (!tmff)
 		return -ENOMEM;
diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c
index f90959e94028..3abaca045869 100644
--- a/drivers/hid/hid-zpff.c
+++ b/drivers/hid/hid-zpff.c
@@ -54,11 +54,17 @@ static int zpff_init(struct hid_device *hid)
 {
 	struct zpff_device *zpff;
 	struct hid_report *report;
-	struct hid_input *hidinput = list_entry(hid->inputs.next,
-						struct hid_input, list);
-	struct input_dev *dev = hidinput->input;
+	struct hid_input *hidinput;
+	struct input_dev *dev;
 	int i, error;
 
+	if (list_empty(&hid->inputs)) {
+		hid_err(hid, "no inputs found\n");
+		return -ENODEV;
+	}
+	hidinput = list_entry(hid->inputs.next, struct hid_input, list);
+	dev = hidinput->input;
+
 	for (i = 0; i < 4; i++) {
 		report = hid_validate_values(hid, HID_OUTPUT_REPORT, 0, i, 1);
 		if (!report)
diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 2a7c6e33bb1c..04c088131e04 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -26,7 +26,6 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/pm.h>
-#include <linux/pm_runtime.h>
 #include <linux/device.h>
 #include <linux/wait.h>
 #include <linux/err.h>
@@ -48,8 +47,6 @@
 /* quirks to control the device */
 #define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV	BIT(0)
 #define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET	BIT(1)
-#define I2C_HID_QUIRK_NO_RUNTIME_PM		BIT(2)
-#define I2C_HID_QUIRK_DELAY_AFTER_SLEEP		BIT(3)
 #define I2C_HID_QUIRK_BOGUS_IRQ			BIT(4)
 
 /* flags */
@@ -172,14 +169,7 @@ static const struct i2c_hid_quirks {
 	{ USB_VENDOR_ID_WEIDA, HID_ANY_ID,
 		I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV },
 	{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
-		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET |
-		I2C_HID_QUIRK_NO_RUNTIME_PM },
-	{ I2C_VENDOR_ID_RAYDIUM, I2C_PRODUCT_ID_RAYDIUM_4B33,
-		I2C_HID_QUIRK_DELAY_AFTER_SLEEP },
-	{ USB_VENDOR_ID_LG, I2C_DEVICE_ID_LG_8001,
-		I2C_HID_QUIRK_NO_RUNTIME_PM },
-	{ I2C_VENDOR_ID_GOODIX, I2C_DEVICE_ID_GOODIX_01F0,
-		I2C_HID_QUIRK_NO_RUNTIME_PM },
+		I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
 	{ USB_VENDOR_ID_ELAN, HID_ANY_ID,
 		 I2C_HID_QUIRK_BOGUS_IRQ },
 	{ 0, 0 }
@@ -397,7 +387,6 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 {
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 	int ret;
-	unsigned long now, delay;
 
 	i2c_hid_dbg(ihid, "%s\n", __func__);
 
@@ -415,22 +404,9 @@ static int i2c_hid_set_power(struct i2c_client *client, int power_state)
 			goto set_pwr_exit;
 	}
 
-	if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP &&
-	    power_state == I2C_HID_PWR_ON) {
-		now = jiffies;
-		if (time_after(ihid->sleep_delay, now)) {
-			delay = jiffies_to_usecs(ihid->sleep_delay - now);
-			usleep_range(delay, delay + 1);
-		}
-	}
-
 	ret = __i2c_hid_command(client, &hid_set_power_cmd, power_state,
 		0, NULL, 0, NULL, 0);
 
-	if (ihid->quirks & I2C_HID_QUIRK_DELAY_AFTER_SLEEP &&
-	    power_state == I2C_HID_PWR_SLEEP)
-		ihid->sleep_delay = jiffies + msecs_to_jiffies(20);
-
 	if (ret)
 		dev_err(&client->dev, "failed to change power setting.\n");
 
@@ -471,8 +447,12 @@ static int i2c_hid_hwreset(struct i2c_client *client)
 	if (ret) {
 		dev_err(&client->dev, "failed to reset device.\n");
 		i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+		goto out_unlock;
 	}
 
+	/* At least some SIS devices need this after reset */
+	ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
+
 out_unlock:
 	mutex_unlock(&ihid->reset_lock);
 	return ret;
@@ -791,11 +771,6 @@ static int i2c_hid_open(struct hid_device *hid)
 {
 	struct i2c_client *client = hid->driver_data;
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
-	int ret = 0;
-
-	ret = pm_runtime_get_sync(&client->dev);
-	if (ret < 0)
-		return ret;
 
 	set_bit(I2C_HID_STARTED, &ihid->flags);
 	return 0;
@@ -807,27 +782,6 @@ static void i2c_hid_close(struct hid_device *hid)
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 
 	clear_bit(I2C_HID_STARTED, &ihid->flags);
-
-	/* Save some power */
-	pm_runtime_put(&client->dev);
-}
-
-static int i2c_hid_power(struct hid_device *hid, int lvl)
-{
-	struct i2c_client *client = hid->driver_data;
-	struct i2c_hid *ihid = i2c_get_clientdata(client);
-
-	i2c_hid_dbg(ihid, "%s lvl:%d\n", __func__, lvl);
-
-	switch (lvl) {
-	case PM_HINT_FULLON:
-		pm_runtime_get_sync(&client->dev);
-		break;
-	case PM_HINT_NORMAL:
-		pm_runtime_put(&client->dev);
-		break;
-	}
-	return 0;
 }
 
 struct hid_ll_driver i2c_hid_ll_driver = {
@@ -836,7 +790,6 @@ struct hid_ll_driver i2c_hid_ll_driver = {
 	.stop = i2c_hid_stop,
 	.open = i2c_hid_open,
 	.close = i2c_hid_close,
-	.power = i2c_hid_power,
 	.output_report = i2c_hid_output_report,
 	.raw_request = i2c_hid_raw_request,
 };
@@ -1104,9 +1057,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 
 	i2c_hid_acpi_fix_up_power(&client->dev);
 
-	pm_runtime_get_noresume(&client->dev);
-	pm_runtime_set_active(&client->dev);
-	pm_runtime_enable(&client->dev);
 	device_enable_async_suspend(&client->dev);
 
 	/* Make sure there is something at this address */
@@ -1114,16 +1064,16 @@ static int i2c_hid_probe(struct i2c_client *client,
 	if (ret < 0) {
 		dev_dbg(&client->dev, "nothing at this address: %d\n", ret);
 		ret = -ENXIO;
-		goto err_pm;
+		goto err_regulator;
 	}
 
 	ret = i2c_hid_fetch_hid_descriptor(ihid);
 	if (ret < 0)
-		goto err_pm;
+		goto err_regulator;
 
 	ret = i2c_hid_init_irq(client);
 	if (ret < 0)
-		goto err_pm;
+		goto err_regulator;
 
 	hid = hid_allocate_device();
 	if (IS_ERR(hid)) {
@@ -1154,9 +1104,6 @@ static int i2c_hid_probe(struct i2c_client *client,
 		goto err_mem_free;
 	}
 
-	if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
-		pm_runtime_put(&client->dev);
-
 	return 0;
 
 err_mem_free:
@@ -1165,10 +1112,6 @@ err_mem_free:
 err_irq:
 	free_irq(client->irq, ihid);
 
-err_pm:
-	pm_runtime_put_noidle(&client->dev);
-	pm_runtime_disable(&client->dev);
-
 err_regulator:
 	regulator_bulk_disable(ARRAY_SIZE(ihid->pdata.supplies),
 			       ihid->pdata.supplies);
@@ -1181,12 +1124,6 @@ static int i2c_hid_remove(struct i2c_client *client)
 	struct i2c_hid *ihid = i2c_get_clientdata(client);
 	struct hid_device *hid;
 
-	if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
-		pm_runtime_get_sync(&client->dev);
-	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
-	pm_runtime_put_noidle(&client->dev);
-
 	hid = ihid->hid;
 	hid_destroy_device(hid);
 
@@ -1219,25 +1156,15 @@ static int i2c_hid_suspend(struct device *dev)
 	int wake_status;
 
 	if (hid->driver && hid->driver->suspend) {
-		/*
-		 * Wake up the device so that IO issues in
-		 * HID driver's suspend code can succeed.
-		 */
-		ret = pm_runtime_resume(dev);
-		if (ret < 0)
-			return ret;
-
 		ret = hid->driver->suspend(hid, PMSG_SUSPEND);
 		if (ret < 0)
 			return ret;
 	}
 
-	if (!pm_runtime_suspended(dev)) {
-		/* Save some power */
-		i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
+	/* Save some power */
+	i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
 
-		disable_irq(client->irq);
-	}
+	disable_irq(client->irq);
 
 	if (device_may_wakeup(&client->dev)) {
 		wake_status = enable_irq_wake(client->irq);
@@ -1279,11 +1206,6 @@ static int i2c_hid_resume(struct device *dev)
 				wake_status);
 	}
 
-	/* We'll resume to full power */
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
-
 	enable_irq(client->irq);
 
 	/* Instead of resetting device, simply powers the device on. This
@@ -1304,30 +1226,8 @@ static int i2c_hid_resume(struct device *dev)
 }
 #endif
 
-#ifdef CONFIG_PM
-static int i2c_hid_runtime_suspend(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	i2c_hid_set_power(client, I2C_HID_PWR_SLEEP);
-	disable_irq(client->irq);
-	return 0;
-}
-
-static int i2c_hid_runtime_resume(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-
-	enable_irq(client->irq);
-	i2c_hid_set_power(client, I2C_HID_PWR_ON);
-	return 0;
-}
-#endif
-
 static const struct dev_pm_ops i2c_hid_pm = {
 	SET_SYSTEM_SLEEP_PM_OPS(i2c_hid_suspend, i2c_hid_resume)
-	SET_RUNTIME_PM_OPS(i2c_hid_runtime_suspend, i2c_hid_runtime_resume,
-			   NULL)
 };
 
 static const struct i2c_device_id i2c_hid_id_table[] = {
diff --git a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
index 75078c83be1a..d31ea82b84c1 100644
--- a/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
+++ b/drivers/hid/i2c-hid/i2c-hid-dmi-quirks.c
@@ -323,6 +323,25 @@ static const struct dmi_system_id i2c_hid_dmi_desc_override_table[] = {
 		.driver_data = (void *)&sipodev_desc
 	},
 	{
+		/*
+		 * There are at least 2 Primebook C11B versions, the older
+		 * version has a product-name of "Primebook C11B", and a
+		 * bios version / release / firmware revision of:
+		 * V2.1.2 / 05/03/2018 / 18.2
+		 * The new version has "PRIMEBOOK C11B" as product-name and a
+		 * bios version / release / firmware revision of:
+		 * CFALKSW05_BIOS_V1.1.2 / 11/19/2018 / 19.2
+		 * Only the older version needs this quirk, note the newer
+		 * version will not match as it has a different product-name.
+		 */
+		.ident = "Trekstor Primebook C11B",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TREKSTOR"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Primebook C11B"),
+		},
+		.driver_data = (void *)&sipodev_desc
+	},
+	{
 		.ident = "Direkt-Tek DTLAPY116-2",
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Direkt-Tek"),
diff --git a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c
index 1b0a0cc605e7..513d7a4a1b8a 100644
--- a/drivers/hid/intel-ish-hid/ishtp/client-buffers.c
+++ b/drivers/hid/intel-ish-hid/ishtp/client-buffers.c
@@ -84,7 +84,7 @@ int ishtp_cl_alloc_tx_ring(struct ishtp_cl *cl)
 	return	0;
 out:
 	dev_err(&cl->device->dev, "error in allocating Tx pool\n");
-	ishtp_cl_free_rx_ring(cl);
+	ishtp_cl_free_tx_ring(cl);
 	return	-ENOMEM;
 }
 
diff --git a/drivers/hid/wacom.h b/drivers/hid/wacom.h
index 4a7f8d363220..203d27d198b8 100644
--- a/drivers/hid/wacom.h
+++ b/drivers/hid/wacom.h
@@ -202,6 +202,21 @@ static inline void wacom_schedule_work(struct wacom_wac *wacom_wac,
 	}
 }
 
+/*
+ * Convert a signed 32-bit integer to an unsigned n-bit integer. Undoes
+ * the normally-helpful work of 'hid_snto32' for fields that use signed
+ * ranges for questionable reasons.
+ */
+static inline __u32 wacom_s32tou(s32 value, __u8 n)
+{
+	switch (n) {
+	case 8:  return ((__u8)value);
+	case 16: return ((__u16)value);
+	case 32: return ((__u32)value);
+	}
+	return value & (1 << (n - 1)) ? value & (~(~0U << n)) : value;
+}
+
 extern const struct hid_device_id wacom_ids[];
 
 void wacom_wac_irq(struct wacom_wac *wacom_wac, size_t len);
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 2b0a5b8ca6e6..ccb74529bc78 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2303,7 +2303,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 	case HID_DG_TOOLSERIALNUMBER:
 		if (value) {
 			wacom_wac->serial[0] = (wacom_wac->serial[0] & ~0xFFFFFFFFULL);
-			wacom_wac->serial[0] |= (__u32)value;
+			wacom_wac->serial[0] |= wacom_s32tou(value, field->report_size);
 		}
 		return;
 	case HID_DG_TWIST:
@@ -2319,15 +2319,17 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 		return;
 	case WACOM_HID_WD_SERIALHI:
 		if (value) {
+			__u32 raw_value = wacom_s32tou(value, field->report_size);
+
 			wacom_wac->serial[0] = (wacom_wac->serial[0] & 0xFFFFFFFF);
-			wacom_wac->serial[0] |= ((__u64)value) << 32;
+			wacom_wac->serial[0] |= ((__u64)raw_value) << 32;
 			/*
 			 * Non-USI EMR devices may contain additional tool type
 			 * information here. See WACOM_HID_WD_TOOLTYPE case for
 			 * more details.
 			 */
 			if (value >> 20 == 1) {
-				wacom_wac->id[0] |= value & 0xFFFFF;
+				wacom_wac->id[0] |= raw_value & 0xFFFFF;
 			}
 		}
 		return;
@@ -2339,7 +2341,7 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
 		 * bitwise OR so the complete value can be built
 		 * up over time :(
 		 */
-		wacom_wac->id[0] |= value;
+		wacom_wac->id[0] |= wacom_s32tou(value, field->report_size);
 		return;
 	case WACOM_HID_WD_OFFSETLEFT:
 		if (features->offset_left && value != features->offset_left)
diff --git a/drivers/hwmon/ina3221.c b/drivers/hwmon/ina3221.c
index 0037e2bdacd6..8a51dcf055ea 100644
--- a/drivers/hwmon/ina3221.c
+++ b/drivers/hwmon/ina3221.c
@@ -170,7 +170,7 @@ static inline int ina3221_wait_for_data(struct ina3221_data *ina)
 
 	/* Polling the CVRF bit to make sure read data is ready */
 	return regmap_field_read_poll_timeout(ina->fields[F_CVRF],
-					      cvrf, cvrf, wait, 100000);
+					      cvrf, cvrf, wait, wait * 2);
 }
 
 static int ina3221_read_value(struct ina3221_data *ina, unsigned int reg,
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index b26419dbe840..281c81edabc6 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -82,6 +82,10 @@
 #define FANCTL1_FMR_REG		0x00	/* Bank 3; 1 reg per channel */
 #define FANCTL1_OUT_REG		0x10	/* Bank 3; 1 reg per channel */
 
+#define VOLT_MONITOR_MODE	0x0
+#define THERMAL_DIODE_MODE	0x1
+#define THERMISTOR_MODE		0x3
+
 #define ENABLE_TSI	BIT(1)
 
 static const unsigned short normal_i2c[] = {
@@ -935,11 +939,16 @@ static int nct7904_probe(struct i2c_client *client,
 	for (i = 0; i < 4; i++) {
 		val = (ret >> (i * 2)) & 0x03;
 		bit = (1 << i);
-		if (val == 0) {
+		if (val == VOLT_MONITOR_MODE) {
 			data->tcpu_mask &= ~bit;
+		} else if (val == THERMAL_DIODE_MODE && i < 2) {
+			data->temp_mode |= bit;
+			data->vsen_mask &= ~(0x06 << (i * 2));
+		} else if (val == THERMISTOR_MODE) {
+			data->vsen_mask &= ~(0x02 << (i * 2));
 		} else {
-			if (val == 0x1 || val == 0x2)
-				data->temp_mode |= bit;
+			/* Reserved */
+			data->tcpu_mask &= ~bit;
 			data->vsen_mask &= ~(0x06 << (i * 2));
 		}
 	}
diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c
index fa9d34af87ac..f72803a02391 100644
--- a/drivers/hwtracing/intel_th/gth.c
+++ b/drivers/hwtracing/intel_th/gth.c
@@ -626,6 +626,9 @@ static void intel_th_gth_switch(struct intel_th_device *thdev,
 	if (!count)
 		dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n");
 
+	/* De-assert the trigger */
+	iowrite32(0, gth->base + REG_CTS_CTL);
+
 	intel_th_gth_stop(gth, output, false);
 	intel_th_gth_start(gth, output);
 }
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index fc9f15f36ad4..6d240dfae9d9 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -164,7 +164,7 @@ struct msc {
 };
 
 static LIST_HEAD(msu_buffer_list);
-static struct mutex msu_buffer_mutex;
+static DEFINE_MUTEX(msu_buffer_mutex);
 
 /**
  * struct msu_buffer_entry - internal MSU buffer bookkeeping
@@ -327,7 +327,7 @@ static size_t msc_win_total_sz(struct msc_window *win)
 		struct msc_block_desc *bdesc = sg_virt(sg);
 
 		if (msc_block_wrapped(bdesc))
-			return win->nr_blocks << PAGE_SHIFT;
+			return (size_t)win->nr_blocks << PAGE_SHIFT;
 
 		size += msc_total_sz(bdesc);
 		if (msc_block_last_written(bdesc))
@@ -1848,9 +1848,14 @@ mode_store(struct device *dev, struct device_attribute *attr, const char *buf,
 		len = cp - buf;
 
 	mode = kstrndup(buf, len, GFP_KERNEL);
+	if (!mode)
+		return -ENOMEM;
+
 	i = match_string(msc_mode, ARRAY_SIZE(msc_mode), mode);
-	if (i >= 0)
+	if (i >= 0) {
+		kfree(mode);
 		goto found;
+	}
 
 	/* Buffer sinks only work with a usable IRQ */
 	if (!msc->do_irq) {
diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 91dfeba62485..03ca5b1bef9f 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -200,6 +200,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
 	{
+		/* Comet Lake PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x06a6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
+	{
 		/* Ice Lake NNPI */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x45c5),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
@@ -209,6 +214,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa0a6),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Jasper Lake PCH */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4da6),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{ 0 },
 };
 
diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
index fa66951b05d0..7b098ff5f5dd 100644
--- a/drivers/i2c/busses/i2c-aspeed.c
+++ b/drivers/i2c/busses/i2c-aspeed.c
@@ -108,6 +108,12 @@
 #define ASPEED_I2CD_S_TX_CMD				BIT(2)
 #define ASPEED_I2CD_M_TX_CMD				BIT(1)
 #define ASPEED_I2CD_M_START_CMD				BIT(0)
+#define ASPEED_I2CD_MASTER_CMDS_MASK					       \
+		(ASPEED_I2CD_M_STOP_CMD |				       \
+		 ASPEED_I2CD_M_S_RX_CMD_LAST |				       \
+		 ASPEED_I2CD_M_RX_CMD |					       \
+		 ASPEED_I2CD_M_TX_CMD |					       \
+		 ASPEED_I2CD_M_START_CMD)
 
 /* 0x18 : I2CD Slave Device Address Register   */
 #define ASPEED_I2CD_DEV_ADDR_MASK			GENMASK(6, 0)
@@ -336,18 +342,19 @@ static void aspeed_i2c_do_start(struct aspeed_i2c_bus *bus)
 	struct i2c_msg *msg = &bus->msgs[bus->msgs_index];
 	u8 slave_addr = i2c_8bit_addr_from_msg(msg);
 
-	bus->master_state = ASPEED_I2C_MASTER_START;
-
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
 	/*
 	 * If it's requested in the middle of a slave session, set the master
 	 * state to 'pending' then H/W will continue handling this master
 	 * command when the bus comes back to the idle state.
 	 */
-	if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE)
+	if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE) {
 		bus->master_state = ASPEED_I2C_MASTER_PENDING;
+		return;
+	}
 #endif /* CONFIG_I2C_SLAVE */
 
+	bus->master_state = ASPEED_I2C_MASTER_START;
 	bus->buf_index = 0;
 
 	if (msg->flags & I2C_M_RD) {
@@ -422,20 +429,6 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 		}
 	}
 
-#if IS_ENABLED(CONFIG_I2C_SLAVE)
-	/*
-	 * A pending master command will be started by H/W when the bus comes
-	 * back to idle state after completing a slave operation so change the
-	 * master state from 'pending' to 'start' at here if slave is inactive.
-	 */
-	if (bus->master_state == ASPEED_I2C_MASTER_PENDING) {
-		if (bus->slave_state != ASPEED_I2C_SLAVE_INACTIVE)
-			goto out_no_complete;
-
-		bus->master_state = ASPEED_I2C_MASTER_START;
-	}
-#endif /* CONFIG_I2C_SLAVE */
-
 	/* Master is not currently active, irq was for someone else. */
 	if (bus->master_state == ASPEED_I2C_MASTER_INACTIVE ||
 	    bus->master_state == ASPEED_I2C_MASTER_PENDING)
@@ -462,11 +455,15 @@ static u32 aspeed_i2c_master_irq(struct aspeed_i2c_bus *bus, u32 irq_status)
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
 		/*
 		 * If a peer master starts a xfer immediately after it queues a
-		 * master command, change its state to 'pending' then H/W will
-		 * continue the queued master xfer just after completing the
-		 * slave mode session.
+		 * master command, clear the queued master command and change
+		 * its state to 'pending'. To simplify handling of pending
+		 * cases, it uses S/W solution instead of H/W command queue
+		 * handling.
 		 */
 		if (unlikely(irq_status & ASPEED_I2CD_INTR_SLAVE_MATCH)) {
+			writel(readl(bus->base + ASPEED_I2C_CMD_REG) &
+				~ASPEED_I2CD_MASTER_CMDS_MASK,
+			       bus->base + ASPEED_I2C_CMD_REG);
 			bus->master_state = ASPEED_I2C_MASTER_PENDING;
 			dev_dbg(bus->dev,
 				"master goes pending due to a slave start\n");
@@ -629,6 +626,14 @@ static irqreturn_t aspeed_i2c_bus_irq(int irq, void *dev_id)
 			irq_handled |= aspeed_i2c_master_irq(bus,
 							     irq_remaining);
 	}
+
+	/*
+	 * Start a pending master command at here if a slave operation is
+	 * completed.
+	 */
+	if (bus->master_state == ASPEED_I2C_MASTER_PENDING &&
+	    bus->slave_state == ASPEED_I2C_SLAVE_INACTIVE)
+		aspeed_i2c_do_start(bus);
 #else
 	irq_handled = aspeed_i2c_master_irq(bus, irq_remaining);
 #endif /* CONFIG_I2C_SLAVE */
@@ -691,6 +696,15 @@ static int aspeed_i2c_master_xfer(struct i2c_adapter *adap,
 		     ASPEED_I2CD_BUS_BUSY_STS))
 			aspeed_i2c_recover_bus(bus);
 
+		/*
+		 * If timed out and the state is still pending, drop the pending
+		 * master command.
+		 */
+		spin_lock_irqsave(&bus->lock, flags);
+		if (bus->master_state == ASPEED_I2C_MASTER_PENDING)
+			bus->master_state = ASPEED_I2C_MASTER_INACTIVE;
+		spin_unlock_irqrestore(&bus->lock, flags);
+
 		return -ETIMEDOUT;
 	}
 
diff --git a/drivers/i2c/busses/i2c-mt65xx.c b/drivers/i2c/busses/i2c-mt65xx.c
index 29eae1bf4f86..2152ec5f535c 100644
--- a/drivers/i2c/busses/i2c-mt65xx.c
+++ b/drivers/i2c/busses/i2c-mt65xx.c
@@ -875,7 +875,7 @@ static irqreturn_t mtk_i2c_irq(int irqno, void *dev_id)
 
 static u32 mtk_i2c_functionality(struct i2c_adapter *adap)
 {
-	if (adap->quirks->flags & I2C_AQ_NO_ZERO_LEN)
+	if (i2c_check_quirks(adap, I2C_AQ_NO_ZERO_LEN))
 		return I2C_FUNC_I2C |
 			(I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK);
 	else
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index d36cf08461f7..b24e7b937f21 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -305,7 +305,7 @@ struct stm32f7_i2c_dev {
 	struct regmap *regmap;
 };
 
-/**
+/*
  * All these values are coming from I2C Specification, Version 6.0, 4th of
  * April 2014.
  *
@@ -1192,6 +1192,8 @@ static void stm32f7_i2c_slave_start(struct stm32f7_i2c_dev *i2c_dev)
 			STM32F7_I2C_CR1_TXIE;
 		stm32f7_i2c_set_bits(base + STM32F7_I2C_CR1, mask);
 
+		/* Write 1st data byte */
+		writel_relaxed(value, base + STM32F7_I2C_TXDR);
 	} else {
 		/* Notify i2c slave that new write transfer is starting */
 		i2c_slave_event(slave, I2C_SLAVE_WRITE_REQUESTED, &value);
@@ -1501,7 +1503,7 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
 	void __iomem *base = i2c_dev->base;
 	struct device *dev = i2c_dev->dev;
 	struct stm32_i2c_dma *dma = i2c_dev->dma;
-	u32 mask, status;
+	u32 status;
 
 	status = readl_relaxed(i2c_dev->base + STM32F7_I2C_ISR);
 
@@ -1526,12 +1528,15 @@ static irqreturn_t stm32f7_i2c_isr_error(int irq, void *data)
 		f7_msg->result = -EINVAL;
 	}
 
-	/* Disable interrupts */
-	if (stm32f7_i2c_is_slave_registered(i2c_dev))
-		mask = STM32F7_I2C_XFER_IRQ_MASK;
-	else
-		mask = STM32F7_I2C_ALL_IRQ_MASK;
-	stm32f7_i2c_disable_irq(i2c_dev, mask);
+	if (!i2c_dev->slave_running) {
+		u32 mask;
+		/* Disable interrupts */
+		if (stm32f7_i2c_is_slave_registered(i2c_dev))
+			mask = STM32F7_I2C_XFER_IRQ_MASK;
+		else
+			mask = STM32F7_I2C_ALL_IRQ_MASK;
+		stm32f7_i2c_disable_irq(i2c_dev, mask);
+	}
 
 	/* Disable dma */
 	if (i2c_dev->use_dma) {
diff --git a/drivers/iio/adc/stm32-adc.c b/drivers/iio/adc/stm32-adc.c
index 663f8a5012d6..73aee5949b6b 100644
--- a/drivers/iio/adc/stm32-adc.c
+++ b/drivers/iio/adc/stm32-adc.c
@@ -1399,7 +1399,7 @@ static int stm32_adc_dma_start(struct iio_dev *indio_dev)
 	cookie = dmaengine_submit(desc);
 	ret = dma_submit_error(cookie);
 	if (ret) {
-		dmaengine_terminate_all(adc->dma_chan);
+		dmaengine_terminate_sync(adc->dma_chan);
 		return ret;
 	}
 
@@ -1477,7 +1477,7 @@ static void __stm32_adc_buffer_predisable(struct iio_dev *indio_dev)
 		stm32_adc_conv_irq_disable(adc);
 
 	if (adc->dma_chan)
-		dmaengine_terminate_all(adc->dma_chan);
+		dmaengine_terminate_sync(adc->dma_chan);
 
 	if (stm32_adc_set_trig(indio_dev, NULL))
 		dev_err(&indio_dev->dev, "Can't clear trigger\n");
diff --git a/drivers/iio/imu/adis16480.c b/drivers/iio/imu/adis16480.c
index b99d73887c9f..8743b2f376e2 100644
--- a/drivers/iio/imu/adis16480.c
+++ b/drivers/iio/imu/adis16480.c
@@ -317,8 +317,11 @@ static int adis16480_set_freq(struct iio_dev *indio_dev, int val, int val2)
 	struct adis16480 *st = iio_priv(indio_dev);
 	unsigned int t, reg;
 
+	if (val < 0 || val2 < 0)
+		return -EINVAL;
+
 	t =  val * 1000 + val2 / 1000;
-	if (t <= 0)
+	if (t == 0)
 		return -EINVAL;
 
 	/*
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index b17f060b52fc..868281b8adb0 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -114,54 +114,63 @@ static const struct inv_mpu6050_hw hw_info[] = {
 		.name = "MPU6050",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU6500_WHOAMI_VALUE,
 		.name = "MPU6500",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU6515_WHOAMI_VALUE,
 		.name = "MPU6515",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU6000_WHOAMI_VALUE,
 		.name = "MPU6000",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU9150_WHOAMI_VALUE,
 		.name = "MPU9150",
 		.reg = &reg_set_6050,
 		.config = &chip_config_6050,
+		.fifo_size = 1024,
 	},
 	{
 		.whoami = INV_MPU9250_WHOAMI_VALUE,
 		.name = "MPU9250",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_MPU9255_WHOAMI_VALUE,
 		.name = "MPU9255",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_ICM20608_WHOAMI_VALUE,
 		.name = "ICM20608",
 		.reg = &reg_set_6500,
 		.config = &chip_config_6050,
+		.fifo_size = 512,
 	},
 	{
 		.whoami = INV_ICM20602_WHOAMI_VALUE,
 		.name = "ICM20602",
 		.reg = &reg_set_icm20602,
 		.config = &chip_config_6050,
+		.fifo_size = 1008,
 	},
 };
 
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
index db1c6904388b..51235677c534 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_iio.h
@@ -100,12 +100,14 @@ struct inv_mpu6050_chip_config {
  *  @name:      name of the chip.
  *  @reg:   register map of the chip.
  *  @config:    configuration of the chip.
+ *  @fifo_size:	size of the FIFO in bytes.
  */
 struct inv_mpu6050_hw {
 	u8 whoami;
 	u8 *name;
 	const struct inv_mpu6050_reg_map *reg;
 	const struct inv_mpu6050_chip_config *config;
+	size_t fifo_size;
 };
 
 /*
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
index 5f9a5de0bab4..72d8c5790076 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c
@@ -180,9 +180,6 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 			"failed to ack interrupt\n");
 		goto flush_fifo;
 	}
-	/* handle fifo overflow by reseting fifo */
-	if (int_status & INV_MPU6050_BIT_FIFO_OVERFLOW_INT)
-		goto flush_fifo;
 	if (!(int_status & INV_MPU6050_BIT_RAW_DATA_RDY_INT)) {
 		dev_warn(regmap_get_device(st->map),
 			"spurious interrupt with status 0x%x\n", int_status);
@@ -211,6 +208,18 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p)
 	if (result)
 		goto end_session;
 	fifo_count = get_unaligned_be16(&data[0]);
+
+	/*
+	 * Handle fifo overflow by resetting fifo.
+	 * Reset if there is only 3 data set free remaining to mitigate
+	 * possible delay between reading fifo count and fifo data.
+	 */
+	nb = 3 * bytes_per_datum;
+	if (fifo_count >= st->hw->fifo_size - nb) {
+		dev_warn(regmap_get_device(st->map), "fifo overflow reset\n");
+		goto flush_fifo;
+	}
+
 	/* compute and process all complete datum */
 	nb = fifo_count / bytes_per_datum;
 	inv_mpu6050_update_period(st, pf->timestamp, nb);
diff --git a/drivers/iio/proximity/srf04.c b/drivers/iio/proximity/srf04.c
index 8b50d56b0a03..01eb8cc63076 100644
--- a/drivers/iio/proximity/srf04.c
+++ b/drivers/iio/proximity/srf04.c
@@ -110,7 +110,7 @@ static int srf04_read(struct srf04_data *data)
 	udelay(data->cfg->trigger_pulse_us);
 	gpiod_set_value(data->gpiod_trig, 0);
 
-	/* it cannot take more than 20 ms */
+	/* it should not take more than 20 ms until echo is rising */
 	ret = wait_for_completion_killable_timeout(&data->rising, HZ/50);
 	if (ret < 0) {
 		mutex_unlock(&data->lock);
@@ -120,7 +120,8 @@ static int srf04_read(struct srf04_data *data)
 		return -ETIMEDOUT;
 	}
 
-	ret = wait_for_completion_killable_timeout(&data->falling, HZ/50);
+	/* it cannot take more than 50 ms until echo is falling */
+	ret = wait_for_completion_killable_timeout(&data->falling, HZ/20);
 	if (ret < 0) {
 		mutex_unlock(&data->lock);
 		return ret;
@@ -135,19 +136,19 @@ static int srf04_read(struct srf04_data *data)
 
 	dt_ns = ktime_to_ns(ktime_dt);
 	/*
-	 * measuring more than 3 meters is beyond the capabilities of
-	 * the sensor
+	 * measuring more than 6,45 meters is beyond the capabilities of
+	 * the supported sensors
 	 * ==> filter out invalid results for not measuring echos of
 	 *     another us sensor
 	 *
 	 * formula:
-	 *         distance       3 m
-	 * time = ---------- = --------- = 9404389 ns
-	 *          speed       319 m/s
+	 *         distance     6,45 * 2 m
+	 * time = ---------- = ------------ = 40438871 ns
+	 *          speed         319 m/s
 	 *
 	 * using a minimum speed at -20 °C of 319 m/s
 	 */
-	if (dt_ns > 9404389)
+	if (dt_ns > 40438871)
 		return -EIO;
 
 	time_ns = dt_ns;
@@ -159,20 +160,20 @@ static int srf04_read(struct srf04_data *data)
 	 *   with Temp in °C
 	 *   and speed in m/s
 	 *
-	 * use 343 m/s as ultrasonic speed at 20 °C here in absence of the
+	 * use 343,5 m/s as ultrasonic speed at 20 °C here in absence of the
 	 * temperature
 	 *
 	 * therefore:
-	 *             time     343
-	 * distance = ------ * -----
-	 *             10^6       2
+	 *             time     343,5     time * 106
+	 * distance = ------ * ------- = ------------
+	 *             10^6         2         617176
 	 *   with time in ns
 	 *   and distance in mm (one way)
 	 *
-	 * because we limit to 3 meters the multiplication with 343 just
+	 * because we limit to 6,45 meters the multiplication with 106 just
 	 * fits into 32 bit
 	 */
-	distance_mm = time_ns * 343 / 2000000;
+	distance_mm = time_ns * 106 / 617176;
 
 	return distance_mm;
 }
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 3a8b0911c3bc..9d07378b5b42 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -199,6 +199,7 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
+void rdma_nl_init(void);
 void rdma_nl_exit(void);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2dd2cfe9b561..50a92442c4f7 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -2716,6 +2716,8 @@ static int __init ib_core_init(void)
 		goto err_comp_unbound;
 	}
 
+	rdma_nl_init();
+
 	ret = addr_init();
 	if (ret) {
 		pr_warn("Could't init IB address resolution\n");
diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index 72141c5b7c95..ade71823370f 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/drivers/infiniband/core/iwcm.c
@@ -372,6 +372,7 @@ EXPORT_SYMBOL(iw_cm_disconnect);
 static void destroy_cm_id(struct iw_cm_id *cm_id)
 {
 	struct iwcm_id_private *cm_id_priv;
+	struct ib_qp *qp;
 	unsigned long flags;
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
@@ -389,6 +390,9 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 	set_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags);
 
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
+	qp = cm_id_priv->qp;
+	cm_id_priv->qp = NULL;
+
 	switch (cm_id_priv->state) {
 	case IW_CM_STATE_LISTEN:
 		cm_id_priv->state = IW_CM_STATE_DESTROYING;
@@ -401,7 +405,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 		cm_id_priv->state = IW_CM_STATE_DESTROYING;
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 		/* Abrupt close of the connection */
-		(void)iwcm_modify_qp_err(cm_id_priv->qp);
+		(void)iwcm_modify_qp_err(qp);
 		spin_lock_irqsave(&cm_id_priv->lock, flags);
 		break;
 	case IW_CM_STATE_IDLE:
@@ -426,11 +430,9 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 		BUG();
 		break;
 	}
-	if (cm_id_priv->qp) {
-		cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp);
-		cm_id_priv->qp = NULL;
-	}
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+	if (qp)
+		cm_id_priv->id.device->ops.iw_rem_ref(qp);
 
 	if (cm_id->mapped) {
 		iwpm_remove_mapinfo(&cm_id->local_addr, &cm_id->m_local_addr);
@@ -671,11 +673,11 @@ int iw_cm_accept(struct iw_cm_id *cm_id,
 		BUG_ON(cm_id_priv->state != IW_CM_STATE_CONN_RECV);
 		cm_id_priv->state = IW_CM_STATE_IDLE;
 		spin_lock_irqsave(&cm_id_priv->lock, flags);
-		if (cm_id_priv->qp) {
-			cm_id->device->ops.iw_rem_ref(qp);
-			cm_id_priv->qp = NULL;
-		}
+		qp = cm_id_priv->qp;
+		cm_id_priv->qp = NULL;
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+		if (qp)
+			cm_id->device->ops.iw_rem_ref(qp);
 		clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
 		wake_up_all(&cm_id_priv->connect_wait);
 	}
@@ -696,7 +698,7 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param)
 	struct iwcm_id_private *cm_id_priv;
 	int ret;
 	unsigned long flags;
-	struct ib_qp *qp;
+	struct ib_qp *qp = NULL;
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
 
@@ -730,13 +732,13 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param)
 		return 0;	/* success */
 
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
-	if (cm_id_priv->qp) {
-		cm_id->device->ops.iw_rem_ref(qp);
-		cm_id_priv->qp = NULL;
-	}
+	qp = cm_id_priv->qp;
+	cm_id_priv->qp = NULL;
 	cm_id_priv->state = IW_CM_STATE_IDLE;
 err:
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+	if (qp)
+		cm_id->device->ops.iw_rem_ref(qp);
 	clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
 	wake_up_all(&cm_id_priv->connect_wait);
 	return ret;
@@ -878,6 +880,7 @@ static int cm_conn_est_handler(struct iwcm_id_private *cm_id_priv,
 static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv,
 			       struct iw_cm_event *iw_event)
 {
+	struct ib_qp *qp = NULL;
 	unsigned long flags;
 	int ret;
 
@@ -896,11 +899,13 @@ static int cm_conn_rep_handler(struct iwcm_id_private *cm_id_priv,
 		cm_id_priv->state = IW_CM_STATE_ESTABLISHED;
 	} else {
 		/* REJECTED or RESET */
-		cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp);
+		qp = cm_id_priv->qp;
 		cm_id_priv->qp = NULL;
 		cm_id_priv->state = IW_CM_STATE_IDLE;
 	}
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+	if (qp)
+		cm_id_priv->id.device->ops.iw_rem_ref(qp);
 	ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event);
 
 	if (iw_event->private_data_len)
@@ -942,21 +947,18 @@ static void cm_disconnect_handler(struct iwcm_id_private *cm_id_priv,
 static int cm_close_handler(struct iwcm_id_private *cm_id_priv,
 				  struct iw_cm_event *iw_event)
 {
+	struct ib_qp *qp;
 	unsigned long flags;
-	int ret = 0;
+	int ret = 0, notify_event = 0;
 	spin_lock_irqsave(&cm_id_priv->lock, flags);
+	qp = cm_id_priv->qp;
+	cm_id_priv->qp = NULL;
 
-	if (cm_id_priv->qp) {
-		cm_id_priv->id.device->ops.iw_rem_ref(cm_id_priv->qp);
-		cm_id_priv->qp = NULL;
-	}
 	switch (cm_id_priv->state) {
 	case IW_CM_STATE_ESTABLISHED:
 	case IW_CM_STATE_CLOSING:
 		cm_id_priv->state = IW_CM_STATE_IDLE;
-		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
-		ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event);
-		spin_lock_irqsave(&cm_id_priv->lock, flags);
+		notify_event = 1;
 		break;
 	case IW_CM_STATE_DESTROYING:
 		break;
@@ -965,6 +967,10 @@ static int cm_close_handler(struct iwcm_id_private *cm_id_priv,
 	}
 	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 
+	if (qp)
+		cm_id_priv->id.device->ops.iw_rem_ref(qp);
+	if (notify_event)
+		ret = cm_id_priv->id.cm_handler(&cm_id_priv->id, iw_event);
 	return ret;
 }
 
diff --git a/drivers/infiniband/core/netlink.c b/drivers/infiniband/core/netlink.c
index 81dbd5f41bed..8cd31ef25eff 100644
--- a/drivers/infiniband/core/netlink.c
+++ b/drivers/infiniband/core/netlink.c
@@ -42,9 +42,12 @@
 #include <linux/module.h>
 #include "core_priv.h"
 
-static DEFINE_MUTEX(rdma_nl_mutex);
 static struct {
-	const struct rdma_nl_cbs   *cb_table;
+	const struct rdma_nl_cbs *cb_table;
+	/* Synchronizes between ongoing netlink commands and netlink client
+	 * unregistration.
+	 */
+	struct rw_semaphore sem;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 bool rdma_nl_chk_listeners(unsigned int group)
@@ -75,70 +78,53 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 	return (op < max_num_ops[type]) ? true : false;
 }
 
-static bool
-is_nl_valid(const struct sk_buff *skb, unsigned int type, unsigned int op)
+static const struct rdma_nl_cbs *
+get_cb_table(const struct sk_buff *skb, unsigned int type, unsigned int op)
 {
 	const struct rdma_nl_cbs *cb_table;
 
-	if (!is_nl_msg_valid(type, op))
-		return false;
-
 	/*
 	 * Currently only NLDEV client is supporting netlink commands in
 	 * non init_net net namespace.
 	 */
 	if (sock_net(skb->sk) != &init_net && type != RDMA_NL_NLDEV)
-		return false;
+		return NULL;
 
-	if (!rdma_nl_types[type].cb_table) {
-		mutex_unlock(&rdma_nl_mutex);
-		request_module("rdma-netlink-subsys-%d", type);
-		mutex_lock(&rdma_nl_mutex);
-	}
+	cb_table = READ_ONCE(rdma_nl_types[type].cb_table);
+	if (!cb_table) {
+		/*
+		 * Didn't get valid reference of the table, attempt module
+		 * load once.
+		 */
+		up_read(&rdma_nl_types[type].sem);
 
-	cb_table = rdma_nl_types[type].cb_table;
+		request_module("rdma-netlink-subsys-%d", type);
 
+		down_read(&rdma_nl_types[type].sem);
+		cb_table = READ_ONCE(rdma_nl_types[type].cb_table);
+	}
 	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
-		return false;
-	return true;
+		return NULL;
+	return cb_table;
 }
 
 void rdma_nl_register(unsigned int index,
 		      const struct rdma_nl_cbs cb_table[])
 {
-	mutex_lock(&rdma_nl_mutex);
-	if (!is_nl_msg_valid(index, 0)) {
-		/*
-		 * All clients are not interesting in success/failure of
-		 * this call. They want to see the print to error log and
-		 * continue their initialization. Print warning for them,
-		 * because it is programmer's error to be here.
-		 */
-		mutex_unlock(&rdma_nl_mutex);
-		WARN(true,
-		     "The not-valid %u index was supplied to RDMA netlink\n",
-		     index);
+	if (WARN_ON(!is_nl_msg_valid(index, 0)) ||
+	    WARN_ON(READ_ONCE(rdma_nl_types[index].cb_table)))
 		return;
-	}
-
-	if (rdma_nl_types[index].cb_table) {
-		mutex_unlock(&rdma_nl_mutex);
-		WARN(true,
-		     "The %u index is already registered in RDMA netlink\n",
-		     index);
-		return;
-	}
 
-	rdma_nl_types[index].cb_table = cb_table;
-	mutex_unlock(&rdma_nl_mutex);
+	/* Pairs with the READ_ONCE in is_nl_valid() */
+	smp_store_release(&rdma_nl_types[index].cb_table, cb_table);
 }
 EXPORT_SYMBOL(rdma_nl_register);
 
 void rdma_nl_unregister(unsigned int index)
 {
-	mutex_lock(&rdma_nl_mutex);
+	down_write(&rdma_nl_types[index].sem);
 	rdma_nl_types[index].cb_table = NULL;
-	mutex_unlock(&rdma_nl_mutex);
+	up_write(&rdma_nl_types[index].sem);
 }
 EXPORT_SYMBOL(rdma_nl_unregister);
 
@@ -170,15 +156,21 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
 	const struct rdma_nl_cbs *cb_table;
+	int err = -EINVAL;
 
-	if (!is_nl_valid(skb, index, op))
+	if (!is_nl_msg_valid(index, op))
 		return -EINVAL;
 
-	cb_table = rdma_nl_types[index].cb_table;
+	down_read(&rdma_nl_types[index].sem);
+	cb_table = get_cb_table(skb, index, op);
+	if (!cb_table)
+		goto done;
 
 	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
-	    !netlink_capable(skb, CAP_NET_ADMIN))
-		return -EPERM;
+	    !netlink_capable(skb, CAP_NET_ADMIN)) {
+		err = -EPERM;
+		goto done;
+	}
 
 	/*
 	 * LS responses overload the 0x100 (NLM_F_ROOT) flag.  Don't
@@ -186,8 +178,8 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	 */
 	if (index == RDMA_NL_LS) {
 		if (cb_table[op].doit)
-			return cb_table[op].doit(skb, nlh, extack);
-		return -EINVAL;
+			err = cb_table[op].doit(skb, nlh, extack);
+		goto done;
 	}
 	/* FIXME: Convert IWCM to properly handle doit callbacks */
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_IWCM) {
@@ -195,14 +187,15 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 			.dump = cb_table[op].dump,
 		};
 		if (c.dump)
-			return netlink_dump_start(skb->sk, skb, nlh, &c);
-		return -EINVAL;
+			err = netlink_dump_start(skb->sk, skb, nlh, &c);
+		goto done;
 	}
 
 	if (cb_table[op].doit)
-		return cb_table[op].doit(skb, nlh, extack);
-
-	return 0;
+		err = cb_table[op].doit(skb, nlh, extack);
+done:
+	up_read(&rdma_nl_types[index].sem);
+	return err;
 }
 
 /*
@@ -263,9 +256,7 @@ skip:
 
 static void rdma_nl_rcv(struct sk_buff *skb)
 {
-	mutex_lock(&rdma_nl_mutex);
 	rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg);
-	mutex_unlock(&rdma_nl_mutex);
 }
 
 int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid)
@@ -297,6 +288,14 @@ int rdma_nl_multicast(struct net *net, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(rdma_nl_multicast);
 
+void rdma_nl_init(void)
+{
+	int idx;
+
+	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
+		init_rwsem(&rdma_nl_types[idx].sem);
+}
+
 void rdma_nl_exit(void)
 {
 	int idx;
diff --git a/drivers/infiniband/core/nldev.c b/drivers/infiniband/core/nldev.c
index 65b36548bc17..c03af08b80e7 100644
--- a/drivers/infiniband/core/nldev.c
+++ b/drivers/infiniband/core/nldev.c
@@ -778,7 +778,7 @@ static int fill_res_counter_entry(struct sk_buff *msg, bool has_cap_net_admin,
 		container_of(res, struct rdma_counter, res);
 
 	if (port && port != counter->port)
-		return 0;
+		return -EAGAIN;
 
 	/* Dump it even query failed */
 	rdma_counter_query_stats(counter);
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 1e5aeb39f774..63f7f7db5902 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -98,7 +98,7 @@ ib_uverbs_init_udata_buf_or_null(struct ib_udata *udata,
 
 struct ib_uverbs_device {
 	atomic_t				refcount;
-	int					num_comp_vectors;
+	u32					num_comp_vectors;
 	struct completion			comp;
 	struct device				dev;
 	/* First group for device attributes, NULL terminated array */
diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index f974b6854224..35c2841a569e 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -662,16 +662,17 @@ static bool find_gid_index(const union ib_gid *gid,
 			   void *context)
 {
 	struct find_gid_index_context *ctx = context;
+	u16 vlan_id = 0xffff;
+	int ret;
 
 	if (ctx->gid_type != gid_attr->gid_type)
 		return false;
 
-	if ((!!(ctx->vlan_id != 0xffff) == !is_vlan_dev(gid_attr->ndev)) ||
-	    (is_vlan_dev(gid_attr->ndev) &&
-	     vlan_dev_vlan_id(gid_attr->ndev) != ctx->vlan_id))
+	ret = rdma_read_gid_l2_fields(gid_attr, &vlan_id, NULL);
+	if (ret)
 		return false;
 
-	return true;
+	return ctx->vlan_id == vlan_id;
 }
 
 static const struct ib_gid_attr *
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index e87fc0408470..347dc242fb88 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -495,7 +495,6 @@ static int _put_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb)
 
 	ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *)));
 	release_ep_resources(ep);
-	kfree_skb(skb);
 	return 0;
 }
 
@@ -506,7 +505,6 @@ static int _put_pass_ep_safe(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = *((struct c4iw_ep **)(skb->cb + 2 * sizeof(void *)));
 	c4iw_put_ep(&ep->parent_ep->com);
 	release_ep_resources(ep);
-	kfree_skb(skb);
 	return 0;
 }
 
@@ -2424,20 +2422,6 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 	enum chip_type adapter_type = ep->com.dev->rdev.lldi.adapter_type;
 
 	pr_debug("ep %p tid %u\n", ep, ep->hwtid);
-
-	skb_get(skb);
-	rpl = cplhdr(skb);
-	if (!is_t4(adapter_type)) {
-		skb_trim(skb, roundup(sizeof(*rpl5), 16));
-		rpl5 = (void *)rpl;
-		INIT_TP_WR(rpl5, ep->hwtid);
-	} else {
-		skb_trim(skb, sizeof(*rpl));
-		INIT_TP_WR(rpl, ep->hwtid);
-	}
-	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
-						    ep->hwtid));
-
 	cxgb_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx,
 		      enable_tcp_timestamps && req->tcpopt.tstamp,
 		      (ep->com.remote_addr.ss_family == AF_INET) ? 0 : 1);
@@ -2483,6 +2467,20 @@ static int accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 		if (tcph->ece && tcph->cwr)
 			opt2 |= CCTRL_ECN_V(1);
 	}
+
+	skb_get(skb);
+	rpl = cplhdr(skb);
+	if (!is_t4(adapter_type)) {
+		skb_trim(skb, roundup(sizeof(*rpl5), 16));
+		rpl5 = (void *)rpl;
+		INIT_TP_WR(rpl5, ep->hwtid);
+	} else {
+		skb_trim(skb, sizeof(*rpl));
+		INIT_TP_WR(rpl, ep->hwtid);
+	}
+	OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_PASS_ACCEPT_RPL,
+						    ep->hwtid));
+
 	if (CHELSIO_CHIP_VERSION(adapter_type) > CHELSIO_T4) {
 		u32 isn = (prandom_u32() & ~7UL) - 1;
 		opt2 |= T5_OPT_2_VALID_F;
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 2ed7bfd5feea..c61b6022575e 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -65,6 +65,7 @@
 #define SDMA_DESCQ_CNT 2048
 #define SDMA_DESC_INTR 64
 #define INVALID_TAIL 0xffff
+#define SDMA_PAD max_t(size_t, MAX_16B_PADDING, sizeof(u32))
 
 static uint sdma_descq_cnt = SDMA_DESCQ_CNT;
 module_param(sdma_descq_cnt, uint, S_IRUGO);
@@ -1296,7 +1297,7 @@ void sdma_clean(struct hfi1_devdata *dd, size_t num_engines)
 	struct sdma_engine *sde;
 
 	if (dd->sdma_pad_dma) {
-		dma_free_coherent(&dd->pcidev->dev, 4,
+		dma_free_coherent(&dd->pcidev->dev, SDMA_PAD,
 				  (void *)dd->sdma_pad_dma,
 				  dd->sdma_pad_phys);
 		dd->sdma_pad_dma = NULL;
@@ -1491,7 +1492,7 @@ int sdma_init(struct hfi1_devdata *dd, u8 port)
 	}
 
 	/* Allocate memory for pad */
-	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u32),
+	dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, SDMA_PAD,
 					      &dd->sdma_pad_phys, GFP_KERNEL);
 	if (!dd->sdma_pad_dma) {
 		dd_dev_err(dd, "failed to allocate SendDMA pad memory\n");
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index b4dcc4d29f84..f21fca3617d5 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -2736,11 +2736,6 @@ static bool handle_read_kdeth_eflags(struct hfi1_ctxtdata *rcd,
 				diff = cmp_psn(psn,
 					       flow->flow_state.r_next_psn);
 				if (diff > 0) {
-					if (!(qp->r_flags & RVT_R_RDMAR_SEQ))
-						restart_tid_rdma_read_req(rcd,
-									  qp,
-									  wqe);
-
 					/* Drop the packet.*/
 					goto s_unlock;
 				} else if (diff < 0) {
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 7bff0a1e713d..089e201d7550 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -147,9 +147,6 @@ static int pio_wait(struct rvt_qp *qp,
 /* Length of buffer to create verbs txreq cache name */
 #define TXREQ_NAME_LEN 24
 
-/* 16B trailing buffer */
-static const u8 trail_buf[MAX_16B_PADDING];
-
 static uint wss_threshold = 80;
 module_param(wss_threshold, uint, S_IRUGO);
 MODULE_PARM_DESC(wss_threshold, "Percentage (1-100) of LLC to use as a threshold for a cacheless copy");
@@ -820,8 +817,8 @@ static int build_verbs_tx_desc(
 
 	/* add icrc, lt byte, and padding to flit */
 	if (extra_bytes)
-		ret = sdma_txadd_kvaddr(sde->dd, &tx->txreq,
-					(void *)trail_buf, extra_bytes);
+		ret = sdma_txadd_daddr(sde->dd, &tx->txreq,
+				       sde->dd->sdma_pad_phys, extra_bytes);
 
 bail_txadd:
 	return ret;
@@ -1089,7 +1086,8 @@ int hfi1_verbs_send_pio(struct rvt_qp *qp, struct hfi1_pkt_state *ps,
 		}
 		/* add icrc, lt byte, and padding to flit */
 		if (extra_bytes)
-			seg_pio_copy_mid(pbuf, trail_buf, extra_bytes);
+			seg_pio_copy_mid(pbuf, ppd->dd->sdma_pad_dma,
+					 extra_bytes);
 
 		seg_pio_copy_end(pbuf);
 	}
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 7a89d669f8bf..e82567fcdeb7 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -5389,9 +5389,9 @@ static void hns_roce_v2_free_eq(struct hns_roce_dev *hr_dev,
 		return;
 	}
 
-	if (eq->buf_list)
-		dma_free_coherent(hr_dev->dev, buf_chk_sz,
-				  eq->buf_list->buf, eq->buf_list->map);
+	dma_free_coherent(hr_dev->dev, buf_chk_sz, eq->buf_list->buf,
+			  eq->buf_list->map);
+	kfree(eq->buf_list);
 }
 
 static void hns_roce_config_eqc(struct hns_roce_dev *hr_dev,
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 630599311586..7019c12005f4 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1967,8 +1967,8 @@ int mlx5_ib_dealloc_mw(struct ib_mw *mw)
 	int err;
 
 	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
-		xa_erase(&dev->mdev->priv.mkey_table,
-			 mlx5_base_mkey(mmw->mmkey.key));
+		xa_erase_irq(&dev->mdev->priv.mkey_table,
+			     mlx5_base_mkey(mmw->mmkey.key));
 		/*
 		 * pagefault_single_data_segment() may be accessing mmw under
 		 * SRCU if the user bound an ODP MR to this MW.
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 8937d72ddcf6..5fd071c05944 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3249,10 +3249,12 @@ static int modify_raw_packet_qp_sq(
 	}
 
 	/* Only remove the old rate after new rate was set */
-	if ((old_rl.rate &&
-	     !mlx5_rl_are_equal(&old_rl, &new_rl)) ||
-	    (new_state != MLX5_SQC_STATE_RDY))
+	if ((old_rl.rate && !mlx5_rl_are_equal(&old_rl, &new_rl)) ||
+	    (new_state != MLX5_SQC_STATE_RDY)) {
 		mlx5_rl_remove_rate(dev, &old_rl);
+		if (new_state != MLX5_SQC_STATE_RDY)
+			memset(&new_rl, 0, sizeof(new_rl));
+	}
 
 	ibqp->rl = new_rl;
 	sq->state = new_state;
diff --git a/drivers/infiniband/hw/qedr/main.c b/drivers/infiniband/hw/qedr/main.c
index 5136b835e1ba..dc71b6e16a07 100644
--- a/drivers/infiniband/hw/qedr/main.c
+++ b/drivers/infiniband/hw/qedr/main.c
@@ -76,7 +76,7 @@ static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str)
 	struct qedr_dev *qedr = get_qedr_dev(ibdev);
 	u32 fw_ver = (u32)qedr->attr.fw_ver;
 
-	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d.%d",
 		 (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF,
 		 (fw_ver >> 8) & 0xFF, fw_ver & 0xFF);
 }
diff --git a/drivers/infiniband/sw/siw/siw_qp.c b/drivers/infiniband/sw/siw/siw_qp.c
index 52d402f39df9..b4317480cee7 100644
--- a/drivers/infiniband/sw/siw/siw_qp.c
+++ b/drivers/infiniband/sw/siw/siw_qp.c
@@ -1312,6 +1312,7 @@ int siw_qp_add(struct siw_device *sdev, struct siw_qp *qp)
 void siw_free_qp(struct kref *ref)
 {
 	struct siw_qp *found, *qp = container_of(ref, struct siw_qp, ref);
+	struct siw_base_qp *siw_base_qp = to_siw_base_qp(qp->ib_qp);
 	struct siw_device *sdev = qp->sdev;
 	unsigned long flags;
 
@@ -1334,4 +1335,5 @@ void siw_free_qp(struct kref *ref)
 	atomic_dec(&sdev->num_qp);
 	siw_dbg_qp(qp, "free QP\n");
 	kfree_rcu(qp, rcu);
+	kfree(siw_base_qp);
 }
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 869e02b69a01..b18a677832e1 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -604,7 +604,6 @@ out:
 int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata)
 {
 	struct siw_qp *qp = to_siw_qp(base_qp);
-	struct siw_base_qp *siw_base_qp = to_siw_base_qp(base_qp);
 	struct siw_ucontext *uctx =
 		rdma_udata_to_drv_context(udata, struct siw_ucontext,
 					  base_ucontext);
@@ -641,7 +640,6 @@ int siw_destroy_qp(struct ib_qp *base_qp, struct ib_udata *udata)
 	qp->scq = qp->rcq = NULL;
 
 	siw_qp_put(qp);
-	kfree(siw_base_qp);
 
 	return 0;
 }
diff --git a/drivers/input/touchscreen/st1232.c b/drivers/input/touchscreen/st1232.c
index 34923399ece4..1139714e72e2 100644
--- a/drivers/input/touchscreen/st1232.c
+++ b/drivers/input/touchscreen/st1232.c
@@ -81,8 +81,10 @@ static int st1232_ts_read_data(struct st1232_ts_data *ts)
 	for (i = 0, y = 0; i < ts->chip_info->max_fingers; i++, y += 3) {
 		finger[i].is_valid = buf[i + y] >> 7;
 		if (finger[i].is_valid) {
-			finger[i].x = ((buf[i + y] & 0x0070) << 4) | buf[i + 1];
-			finger[i].y = ((buf[i + y] & 0x0007) << 8) | buf[i + 2];
+			finger[i].x = ((buf[i + y] & 0x0070) << 4) |
+					buf[i + y + 1];
+			finger[i].y = ((buf[i + y] & 0x0007) << 8) |
+					buf[i + y + 2];
 
 			/* st1232 includes a z-axis / touch strength */
 			if (ts->chip_info->have_z)
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 7b971228df38..c498796adc07 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -405,8 +405,12 @@ void icc_set_tag(struct icc_path *path, u32 tag)
 	if (!path)
 		return;
 
+	mutex_lock(&icc_lock);
+
 	for (i = 0; i < path->num_nodes; i++)
 		path->reqs[i].tag = tag;
+
+	mutex_unlock(&icc_lock);
 }
 EXPORT_SYMBOL_GPL(icc_set_tag);
 
diff --git a/drivers/interconnect/qcom/qcs404.c b/drivers/interconnect/qcom/qcs404.c
index 910081d6ddc0..b4966d8f3348 100644
--- a/drivers/interconnect/qcom/qcs404.c
+++ b/drivers/interconnect/qcom/qcs404.c
@@ -433,7 +433,8 @@ static int qnoc_probe(struct platform_device *pdev)
 	if (!qp)
 		return -ENOMEM;
 
-	data = devm_kcalloc(dev, num_nodes, sizeof(*node), GFP_KERNEL);
+	data = devm_kzalloc(dev, struct_size(data, nodes, num_nodes),
+			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
diff --git a/drivers/interconnect/qcom/sdm845.c b/drivers/interconnect/qcom/sdm845.c
index 57955596bb59..502a6c22b41e 100644
--- a/drivers/interconnect/qcom/sdm845.c
+++ b/drivers/interconnect/qcom/sdm845.c
@@ -790,7 +790,8 @@ static int qnoc_probe(struct platform_device *pdev)
 	if (!qp)
 		return -ENOMEM;
 
-	data = devm_kcalloc(&pdev->dev, num_nodes, sizeof(*node), GFP_KERNEL);
+	data = devm_kzalloc(&pdev->dev, struct_size(data, nodes, num_nodes),
+			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
diff --git a/drivers/iommu/amd_iommu_quirks.c b/drivers/iommu/amd_iommu_quirks.c
index c235f79b7a20..5120ce4fdce3 100644
--- a/drivers/iommu/amd_iommu_quirks.c
+++ b/drivers/iommu/amd_iommu_quirks.c
@@ -74,6 +74,19 @@ static const struct dmi_system_id ivrs_quirks[] __initconst = {
 		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
 	},
 	{
+		/*
+		 * Acer Aspire A315-41 requires the very same workaround as
+		 * Dell Latitude 5495
+		 */
+		.callback = ivrs_ioapic_quirk_cb,
+		.ident = "Acer Aspire A315-41",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Aspire A315-41"),
+		},
+		.driver_data = (void *)&ivrs_ioapic_quirks[DELL_LATITUDE_5495],
+	},
+	{
 		.callback = ivrs_ioapic_quirk_cb,
 		.ident = "Lenovo ideapad 330S-15ARR",
 		.matches = {
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 3f974919d3bd..6db6d969e31c 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -2794,7 +2794,7 @@ static int identity_mapping(struct device *dev)
 	struct device_domain_info *info;
 
 	info = dev->archdata.iommu;
-	if (info && info != DUMMY_DEVICE_DOMAIN_INFO)
+	if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO)
 		return (info->domain == si_domain);
 
 	return 0;
@@ -3471,7 +3471,7 @@ static bool iommu_need_mapping(struct device *dev)
 		if (dev->coherent_dma_mask && dev->coherent_dma_mask < dma_mask)
 			dma_mask = dev->coherent_dma_mask;
 
-		if (dma_mask >= dma_get_required_mask(dev))
+		if (dma_mask >= dma_direct_get_required_mask(dev))
 			return false;
 
 		/*
@@ -3775,6 +3775,13 @@ static int intel_map_sg(struct device *dev, struct scatterlist *sglist, int nele
 	return nelems;
 }
 
+static u64 intel_get_required_mask(struct device *dev)
+{
+	if (!iommu_need_mapping(dev))
+		return dma_direct_get_required_mask(dev);
+	return DMA_BIT_MASK(32);
+}
+
 static const struct dma_map_ops intel_dma_ops = {
 	.alloc = intel_alloc_coherent,
 	.free = intel_free_coherent,
@@ -3787,6 +3794,7 @@ static const struct dma_map_ops intel_dma_ops = {
 	.dma_supported = dma_direct_supported,
 	.mmap = dma_common_mmap,
 	.get_sgtable = dma_common_get_sgtable,
+	.get_required_mask = intel_get_required_mask,
 };
 
 static void
diff --git a/drivers/iommu/ipmmu-vmsa.c b/drivers/iommu/ipmmu-vmsa.c
index 237103465b82..2639fc718117 100644
--- a/drivers/iommu/ipmmu-vmsa.c
+++ b/drivers/iommu/ipmmu-vmsa.c
@@ -1105,10 +1105,8 @@ static int ipmmu_probe(struct platform_device *pdev)
 	/* Root devices have mandatory IRQs */
 	if (ipmmu_is_root(mmu)) {
 		irq = platform_get_irq(pdev, 0);
-		if (irq < 0) {
-			dev_err(&pdev->dev, "no IRQ found\n");
+		if (irq < 0)
 			return irq;
-		}
 
 		ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0,
 				       dev_name(&pdev->dev), mmu);
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 62e54f1a248b..787e8eec9a7f 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -175,6 +175,22 @@ static DEFINE_IDA(its_vpeid_ida);
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 #define gic_data_rdist_vlpi_base()	(gic_data_rdist_rd_base() + SZ_128K)
 
+static u16 get_its_list(struct its_vm *vm)
+{
+	struct its_node *its;
+	unsigned long its_list = 0;
+
+	list_for_each_entry(its, &its_nodes, entry) {
+		if (!its->is_v4)
+			continue;
+
+		if (vm->vlpi_count[its->list_nr])
+			__set_bit(its->list_nr, &its_list);
+	}
+
+	return (u16)its_list;
+}
+
 static struct its_collection *dev_event_to_col(struct its_device *its_dev,
 					       u32 event)
 {
@@ -976,17 +992,15 @@ static void its_send_vmapp(struct its_node *its,
 
 static void its_send_vmovp(struct its_vpe *vpe)
 {
-	struct its_cmd_desc desc;
+	struct its_cmd_desc desc = {};
 	struct its_node *its;
 	unsigned long flags;
 	int col_id = vpe->col_idx;
 
 	desc.its_vmovp_cmd.vpe = vpe;
-	desc.its_vmovp_cmd.its_list = (u16)its_list_map;
 
 	if (!its_list_map) {
 		its = list_first_entry(&its_nodes, struct its_node, entry);
-		desc.its_vmovp_cmd.seq_num = 0;
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
 		its_send_single_vcommand(its, its_build_vmovp_cmd, &desc);
 		return;
@@ -1003,6 +1017,7 @@ static void its_send_vmovp(struct its_vpe *vpe)
 	raw_spin_lock_irqsave(&vmovp_lock, flags);
 
 	desc.its_vmovp_cmd.seq_num = vmovp_seq_num++;
+	desc.its_vmovp_cmd.its_list = get_its_list(vpe->its_vm);
 
 	/* Emit VMOVPs */
 	list_for_each_entry(its, &its_nodes, entry) {
diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
index daefc52b0ec5..7d0a12fe2714 100644
--- a/drivers/irqchip/irq-sifive-plic.c
+++ b/drivers/irqchip/irq-sifive-plic.c
@@ -252,8 +252,8 @@ static int __init plic_init(struct device_node *node,
 			continue;
 		}
 
-		/* skip context holes */
-		if (parent.args[0] == -1)
+		/* skip contexts other than supervisor external interrupt */
+		if (parent.args[0] != IRQ_S_EXT)
 			continue;
 
 		hartid = plic_find_hart_id(parent.np);
diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index c92b405b7646..ba8619524231 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -744,7 +744,7 @@ capi_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &(cdev->recvwait), wait);
 	mask = EPOLLOUT | EPOLLWRNORM;
-	if (!skb_queue_empty(&cdev->recvqueue))
+	if (!skb_queue_empty_lockless(&cdev->recvqueue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 	return mask;
 }
diff --git a/drivers/macintosh/windfarm_cpufreq_clamp.c b/drivers/macintosh/windfarm_cpufreq_clamp.c
index 705c6200814b..7b726f00f183 100644
--- a/drivers/macintosh/windfarm_cpufreq_clamp.c
+++ b/drivers/macintosh/windfarm_cpufreq_clamp.c
@@ -18,7 +18,7 @@
 
 static int clamped;
 static struct wf_control *clamp_control;
-static struct dev_pm_qos_request qos_req;
+static struct freq_qos_request qos_req;
 static unsigned int min_freq, max_freq;
 
 static int clamp_set(struct wf_control *ct, s32 value)
@@ -35,7 +35,7 @@ static int clamp_set(struct wf_control *ct, s32 value)
 	}
 	clamped = value;
 
-	return dev_pm_qos_update_request(&qos_req, freq);
+	return freq_qos_update_request(&qos_req, freq);
 }
 
 static int clamp_get(struct wf_control *ct, s32 *value)
@@ -77,38 +77,44 @@ static int __init wf_cpufreq_clamp_init(void)
 
 	min_freq = policy->cpuinfo.min_freq;
 	max_freq = policy->cpuinfo.max_freq;
+
+	ret = freq_qos_add_request(&policy->constraints, &qos_req, FREQ_QOS_MAX,
+				   max_freq);
+
 	cpufreq_cpu_put(policy);
 
+	if (ret < 0) {
+		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
+		       ret);
+		return ret;
+	}
+
 	dev = get_cpu_device(0);
 	if (unlikely(!dev)) {
 		pr_warn("%s: No cpu device for cpu0\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto fail;
 	}
 
 	clamp = kmalloc(sizeof(struct wf_control), GFP_KERNEL);
-	if (clamp == NULL)
-		return -ENOMEM;
-
-	ret = dev_pm_qos_add_request(dev, &qos_req, DEV_PM_QOS_MAX_FREQUENCY,
-				     max_freq);
-	if (ret < 0) {
-		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
-		       ret);
-		goto free;
+	if (clamp == NULL) {
+		ret = -ENOMEM;
+		goto fail;
 	}
 
 	clamp->ops = &clamp_ops;
 	clamp->name = "cpufreq-clamp";
 	ret = wf_register_control(clamp);
 	if (ret)
-		goto fail;
+		goto free;
+
 	clamp_control = clamp;
 	return 0;
- fail:
-	dev_pm_qos_remove_request(&qos_req);
 
  free:
 	kfree(clamp);
+ fail:
+	freq_qos_remove_request(&qos_req);
 	return ret;
 }
 
@@ -116,7 +122,7 @@ static void __exit wf_cpufreq_clamp_exit(void)
 {
 	if (clamp_control) {
 		wf_unregister_control(clamp_control);
-		dev_pm_qos_remove_request(&qos_req);
+		freq_qos_remove_request(&qos_req);
 	}
 }
 
diff --git a/drivers/mfd/mt6397-core.c b/drivers/mfd/mt6397-core.c
index 310dae26ddff..b2c325ead1c8 100644
--- a/drivers/mfd/mt6397-core.c
+++ b/drivers/mfd/mt6397-core.c
@@ -129,11 +129,27 @@ static int mt6397_irq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(mt6397_pm_ops, mt6397_irq_suspend,
 			mt6397_irq_resume);
 
+struct chip_data {
+	u32 cid_addr;
+	u32 cid_shift;
+};
+
+static const struct chip_data mt6323_core = {
+	.cid_addr = MT6323_CID,
+	.cid_shift = 0,
+};
+
+static const struct chip_data mt6397_core = {
+	.cid_addr = MT6397_CID,
+	.cid_shift = 0,
+};
+
 static int mt6397_probe(struct platform_device *pdev)
 {
 	int ret;
 	unsigned int id;
 	struct mt6397_chip *pmic;
+	const struct chip_data *pmic_core;
 
 	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
 	if (!pmic)
@@ -149,28 +165,30 @@ static int mt6397_probe(struct platform_device *pdev)
 	if (!pmic->regmap)
 		return -ENODEV;
 
-	platform_set_drvdata(pdev, pmic);
+	pmic_core = of_device_get_match_data(&pdev->dev);
+	if (!pmic_core)
+		return -ENODEV;
 
-	ret = regmap_read(pmic->regmap, MT6397_CID, &id);
+	ret = regmap_read(pmic->regmap, pmic_core->cid_addr, &id);
 	if (ret) {
-		dev_err(pmic->dev, "Failed to read chip id: %d\n", ret);
+		dev_err(&pdev->dev, "Failed to read chip id: %d\n", ret);
 		return ret;
 	}
 
+	pmic->chip_id = (id >> pmic_core->cid_shift) & 0xff;
+
+	platform_set_drvdata(pdev, pmic);
+
 	pmic->irq = platform_get_irq(pdev, 0);
 	if (pmic->irq <= 0)
 		return pmic->irq;
 
-	switch (id & 0xff) {
-	case MT6323_CHIP_ID:
-		pmic->int_con[0] = MT6323_INT_CON0;
-		pmic->int_con[1] = MT6323_INT_CON1;
-		pmic->int_status[0] = MT6323_INT_STATUS0;
-		pmic->int_status[1] = MT6323_INT_STATUS1;
-		ret = mt6397_irq_init(pmic);
-		if (ret)
-			return ret;
+	ret = mt6397_irq_init(pmic);
+	if (ret)
+		return ret;
 
+	switch (pmic->chip_id) {
+	case MT6323_CHIP_ID:
 		ret = devm_mfd_add_devices(&pdev->dev, -1, mt6323_devs,
 					   ARRAY_SIZE(mt6323_devs), NULL,
 					   0, pmic->irq_domain);
@@ -178,21 +196,13 @@ static int mt6397_probe(struct platform_device *pdev)
 
 	case MT6391_CHIP_ID:
 	case MT6397_CHIP_ID:
-		pmic->int_con[0] = MT6397_INT_CON0;
-		pmic->int_con[1] = MT6397_INT_CON1;
-		pmic->int_status[0] = MT6397_INT_STATUS0;
-		pmic->int_status[1] = MT6397_INT_STATUS1;
-		ret = mt6397_irq_init(pmic);
-		if (ret)
-			return ret;
-
 		ret = devm_mfd_add_devices(&pdev->dev, -1, mt6397_devs,
 					   ARRAY_SIZE(mt6397_devs), NULL,
 					   0, pmic->irq_domain);
 		break;
 
 	default:
-		dev_err(&pdev->dev, "unsupported chip: %d\n", id);
+		dev_err(&pdev->dev, "unsupported chip: %d\n", pmic->chip_id);
 		return -ENODEV;
 	}
 
@@ -205,9 +215,15 @@ static int mt6397_probe(struct platform_device *pdev)
 }
 
 static const struct of_device_id mt6397_of_match[] = {
-	{ .compatible = "mediatek,mt6397" },
-	{ .compatible = "mediatek,mt6323" },
-	{ }
+	{
+		.compatible = "mediatek,mt6323",
+		.data = &mt6323_core,
+	}, {
+		.compatible = "mediatek,mt6397",
+		.data = &mt6397_core,
+	}, {
+		/* sentinel */
+	}
 };
 MODULE_DEVICE_TABLE(of, mt6397_of_match);
 
diff --git a/drivers/mmc/host/cqhci.c b/drivers/mmc/host/cqhci.c
index f7bdae5354c3..5047f7343ffc 100644
--- a/drivers/mmc/host/cqhci.c
+++ b/drivers/mmc/host/cqhci.c
@@ -611,7 +611,8 @@ static int cqhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 	cq_host->slot[tag].flags = 0;
 
 	cq_host->qcnt += 1;
-
+	/* Make sure descriptors are ready before ringing the doorbell */
+	wmb();
 	cqhci_writel(cq_host, 1 << tag, CQHCI_TDBR);
 	if (!(cqhci_readl(cq_host, CQHCI_TDBR) & (1 << tag)))
 		pr_debug("%s: cqhci: doorbell not set for tag %d\n",
diff --git a/drivers/mmc/host/mxs-mmc.c b/drivers/mmc/host/mxs-mmc.c
index 78e7e350655c..4031217d21c3 100644
--- a/drivers/mmc/host/mxs-mmc.c
+++ b/drivers/mmc/host/mxs-mmc.c
@@ -17,6 +17,7 @@
 #include <linux/interrupt.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
+#include <linux/dma/mxs-dma.h>
 #include <linux/highmem.h>
 #include <linux/clk.h>
 #include <linux/err.h>
@@ -266,7 +267,7 @@ static void mxs_mmc_bc(struct mxs_mmc_host *host)
 	ssp->ssp_pio_words[2] = cmd1;
 	ssp->dma_dir = DMA_NONE;
 	ssp->slave_dirn = DMA_TRANS_NONE;
-	desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK);
+	desc = mxs_mmc_prep_dma(host, MXS_DMA_CTRL_WAIT4END);
 	if (!desc)
 		goto out;
 
@@ -311,7 +312,7 @@ static void mxs_mmc_ac(struct mxs_mmc_host *host)
 	ssp->ssp_pio_words[2] = cmd1;
 	ssp->dma_dir = DMA_NONE;
 	ssp->slave_dirn = DMA_TRANS_NONE;
-	desc = mxs_mmc_prep_dma(host, DMA_CTRL_ACK);
+	desc = mxs_mmc_prep_dma(host, MXS_DMA_CTRL_WAIT4END);
 	if (!desc)
 		goto out;
 
@@ -441,7 +442,7 @@ static void mxs_mmc_adtc(struct mxs_mmc_host *host)
 	host->data = data;
 	ssp->dma_dir = dma_data_dir;
 	ssp->slave_dirn = slave_dirn;
-	desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	desc = mxs_mmc_prep_dma(host, DMA_PREP_INTERRUPT | MXS_DMA_CTRL_WAIT4END);
 	if (!desc)
 		goto out;
 
diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c
index 41c2677c587f..083e7e053c95 100644
--- a/drivers/mmc/host/sdhci-omap.c
+++ b/drivers/mmc/host/sdhci-omap.c
@@ -372,7 +372,7 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode)
 	 * on temperature
 	 */
 	if (temperature < -20000)
-		phase_delay = min(max_window + 4 * max_len - 24,
+		phase_delay = min(max_window + 4 * (max_len - 1) - 24,
 				  max_window +
 				  DIV_ROUND_UP(13 * max_len, 16) * 4);
 	else if (temperature < 20000)
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 8c79bad2a9a5..4f2e6910c623 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -952,7 +952,7 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data)
 	struct bond_vlan_tag *tags;
 
 	if (is_vlan_dev(upper) &&
-	    bond->nest_level == vlan_get_encap_level(upper) - 1) {
+	    bond->dev->lower_level == upper->lower_level - 1) {
 		if (upper->addr_assign_type == NET_ADDR_STOLEN) {
 			alb_send_lp_vid(slave, mac_addr,
 					vlan_dev_vlan_proto(upper),
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 21d8fcc83c9c..62f65573eb04 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1733,8 +1733,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		goto err_upper_unlink;
 	}
 
-	bond->nest_level = dev_get_nest_level(bond_dev) + 1;
-
 	/* If the mode uses primary, then the following is handled by
 	 * bond_change_active_slave().
 	 */
@@ -1816,7 +1814,8 @@ err_detach:
 	slave_disable_netpoll(new_slave);
 
 err_close:
-	slave_dev->priv_flags &= ~IFF_BONDING;
+	if (!netif_is_bond_master(slave_dev))
+		slave_dev->priv_flags &= ~IFF_BONDING;
 	dev_close(slave_dev);
 
 err_restore_mac:
@@ -1956,9 +1955,6 @@ static int __bond_release_one(struct net_device *bond_dev,
 	if (!bond_has_slaves(bond)) {
 		bond_set_carrier(bond);
 		eth_hw_addr_random(bond_dev);
-		bond->nest_level = SINGLE_DEPTH_NESTING;
-	} else {
-		bond->nest_level = dev_get_nest_level(bond_dev) + 1;
 	}
 
 	unblock_netpoll_tx();
@@ -2017,7 +2013,8 @@ static int __bond_release_one(struct net_device *bond_dev,
 	else
 		dev_set_mtu(slave_dev, slave->original_mtu);
 
-	slave_dev->priv_flags &= ~IFF_BONDING;
+	if (!netif_is_bond_master(slave_dev))
+		slave_dev->priv_flags &= ~IFF_BONDING;
 
 	bond_free_slave(slave);
 
@@ -2086,8 +2083,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 	ignore_updelay = !rcu_dereference(bond->curr_active_slave);
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
-		slave->link_new_state = slave->link;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		link_state = bond_check_dev_link(bond, slave->dev, 0);
 
@@ -2121,7 +2117,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 			}
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				commit++;
 				continue;
 			}
@@ -2158,7 +2154,7 @@ static int bond_miimon_inspect(struct bonding *bond)
 				slave->delay = 0;
 
 			if (slave->delay <= 0) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 				ignore_updelay = false;
 				continue;
@@ -2196,7 +2192,7 @@ static void bond_miimon_commit(struct bonding *bond)
 	struct slave *slave, *primary;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			/* For 802.3ad mode, check current slave speed and
 			 * duplex again in case its port was disabled after
@@ -2268,8 +2264,8 @@ static void bond_miimon_commit(struct bonding *bond)
 
 		default:
 			slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n",
-				  slave->new_link);
-			slave->new_link = BOND_LINK_NOCHANGE;
+				  slave->link_new_state);
+			bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 			continue;
 		}
@@ -2677,13 +2673,13 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 	bond_for_each_slave_rcu(bond, slave, iter) {
 		unsigned long trans_start = dev_trans_start(slave->dev);
 
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, trans_start, 1) &&
 			    bond_time_in_interval(bond, slave->last_rx, 1)) {
 
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				slave_state_changed = 1;
 
 				/* primary_slave has no meaning in round-robin
@@ -2708,7 +2704,7 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			if (!bond_time_in_interval(bond, trans_start, 2) ||
 			    !bond_time_in_interval(bond, slave->last_rx, 2)) {
 
-				slave->new_link = BOND_LINK_DOWN;
+				bond_propose_link_state(slave, BOND_LINK_DOWN);
 				slave_state_changed = 1;
 
 				if (slave->link_failure_count < UINT_MAX)
@@ -2739,8 +2735,8 @@ static void bond_loadbalance_arp_mon(struct bonding *bond)
 			goto re_arm;
 
 		bond_for_each_slave(bond, slave, iter) {
-			if (slave->new_link != BOND_LINK_NOCHANGE)
-				slave->link = slave->new_link;
+			if (slave->link_new_state != BOND_LINK_NOCHANGE)
+				slave->link = slave->link_new_state;
 		}
 
 		if (slave_state_changed) {
@@ -2763,9 +2759,9 @@ re_arm:
 }
 
 /* Called to inspect slaves for active-backup mode ARP monitor link state
- * changes.  Sets new_link in slaves to specify what action should take
- * place for the slave.  Returns 0 if no changes are found, >0 if changes
- * to link states must be committed.
+ * changes.  Sets proposed link state in slaves to specify what action
+ * should take place for the slave.  Returns 0 if no changes are found, >0
+ * if changes to link states must be committed.
  *
  * Called with rcu_read_lock held.
  */
@@ -2777,12 +2773,12 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 	int commit = 0;
 
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		slave->new_link = BOND_LINK_NOCHANGE;
+		bond_propose_link_state(slave, BOND_LINK_NOCHANGE);
 		last_rx = slave_last_rx(bond, slave);
 
 		if (slave->link != BOND_LINK_UP) {
 			if (bond_time_in_interval(bond, last_rx, 1)) {
-				slave->new_link = BOND_LINK_UP;
+				bond_propose_link_state(slave, BOND_LINK_UP);
 				commit++;
 			}
 			continue;
@@ -2810,7 +2806,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (!bond_is_active_slave(slave) &&
 		    !rcu_access_pointer(bond->current_arp_slave) &&
 		    !bond_time_in_interval(bond, last_rx, 3)) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 
@@ -2823,7 +2819,7 @@ static int bond_ab_arp_inspect(struct bonding *bond)
 		if (bond_is_active_slave(slave) &&
 		    (!bond_time_in_interval(bond, trans_start, 2) ||
 		     !bond_time_in_interval(bond, last_rx, 2))) {
-			slave->new_link = BOND_LINK_DOWN;
+			bond_propose_link_state(slave, BOND_LINK_DOWN);
 			commit++;
 		}
 	}
@@ -2843,7 +2839,7 @@ static void bond_ab_arp_commit(struct bonding *bond)
 	struct slave *slave;
 
 	bond_for_each_slave(bond, slave, iter) {
-		switch (slave->new_link) {
+		switch (slave->link_new_state) {
 		case BOND_LINK_NOCHANGE:
 			continue;
 
@@ -2893,8 +2889,9 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			continue;
 
 		default:
-			slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n",
-				  slave->new_link);
+			slave_err(bond->dev, slave->dev,
+				  "impossible: link_new_state %d on slave\n",
+				  slave->link_new_state);
 			continue;
 		}
 
@@ -3442,13 +3439,6 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res,
 	}
 }
 
-static int bond_get_nest_level(struct net_device *bond_dev)
-{
-	struct bonding *bond = netdev_priv(bond_dev);
-
-	return bond->nest_level;
-}
-
 static void bond_get_stats(struct net_device *bond_dev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3457,7 +3447,7 @@ static void bond_get_stats(struct net_device *bond_dev,
 	struct list_head *iter;
 	struct slave *slave;
 
-	spin_lock_nested(&bond->stats_lock, bond_get_nest_level(bond_dev));
+	spin_lock(&bond->stats_lock);
 	memcpy(stats, &bond->bond_stats, sizeof(*stats));
 
 	rcu_read_lock();
@@ -4268,7 +4258,6 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_neigh_setup	= bond_neigh_setup,
 	.ndo_vlan_rx_add_vid	= bond_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= bond_vlan_rx_kill_vid,
-	.ndo_get_lock_subclass  = bond_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_netpoll_setup	= bond_netpoll_setup,
 	.ndo_netpoll_cleanup	= bond_netpoll_cleanup,
@@ -4296,7 +4285,6 @@ void bond_setup(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 
 	spin_lock_init(&bond->mode_lock);
-	spin_lock_init(&bond->stats_lock);
 	bond->params = bonding_defaults;
 
 	/* Initialize pointers */
@@ -4365,6 +4353,7 @@ static void bond_uninit(struct net_device *bond_dev)
 
 	list_del(&bond->bond_list);
 
+	lockdep_unregister_key(&bond->stats_lock_key);
 	bond_debug_unregister(bond);
 }
 
@@ -4768,8 +4757,9 @@ static int bond_init(struct net_device *bond_dev)
 	if (!bond->wq)
 		return -ENOMEM;
 
-	bond->nest_level = SINGLE_DEPTH_NESTING;
-	netdev_lockdep_set_classes(bond_dev);
+	spin_lock_init(&bond->stats_lock);
+	lockdep_register_key(&bond->stats_lock_key);
+	lockdep_set_class(&bond->stats_lock, &bond->stats_lock_key);
 
 	list_add_tail(&bond->bond_list, &bn->dev_list);
 
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 606b7d8ffe13..8e9f5620c9a2 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -52,6 +52,7 @@
 #define CONTROL_EX_PDR		BIT(8)
 
 /* control register */
+#define CONTROL_SWR		BIT(15)
 #define CONTROL_TEST		BIT(7)
 #define CONTROL_CCE		BIT(6)
 #define CONTROL_DISABLE_AR	BIT(5)
@@ -97,6 +98,9 @@
 #define BTR_TSEG2_SHIFT		12
 #define BTR_TSEG2_MASK		(0x7 << BTR_TSEG2_SHIFT)
 
+/* interrupt register */
+#define INT_STS_PENDING		0x8000
+
 /* brp extension register */
 #define BRP_EXT_BRPE_MASK	0x0f
 #define BRP_EXT_BRPE_SHIFT	0
@@ -569,6 +573,26 @@ static void c_can_configure_msg_objects(struct net_device *dev)
 				   IF_MCONT_RCV_EOB);
 }
 
+static int c_can_software_reset(struct net_device *dev)
+{
+	struct c_can_priv *priv = netdev_priv(dev);
+	int retry = 0;
+
+	if (priv->type != BOSCH_D_CAN)
+		return 0;
+
+	priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_SWR | CONTROL_INIT);
+	while (priv->read_reg(priv, C_CAN_CTRL_REG) & CONTROL_SWR) {
+		msleep(20);
+		if (retry++ > 100) {
+			netdev_err(dev, "CCTRL: software reset failed\n");
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Configure C_CAN chip:
  * - enable/disable auto-retransmission
@@ -578,6 +602,11 @@ static void c_can_configure_msg_objects(struct net_device *dev)
 static int c_can_chip_config(struct net_device *dev)
 {
 	struct c_can_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = c_can_software_reset(dev);
+	if (err)
+		return err;
 
 	/* enable automatic retransmission */
 	priv->write_reg(priv, C_CAN_CTRL_REG, CONTROL_ENABLE_AR);
@@ -886,6 +915,9 @@ static int c_can_handle_state_change(struct net_device *dev,
 	struct can_berr_counter bec;
 
 	switch (error_type) {
+	case C_CAN_NO_ERROR:
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		break;
 	case C_CAN_ERROR_WARNING:
 		/* error warning state */
 		priv->can.can_stats.error_warning++;
@@ -916,6 +948,13 @@ static int c_can_handle_state_change(struct net_device *dev,
 				ERR_CNT_RP_SHIFT;
 
 	switch (error_type) {
+	case C_CAN_NO_ERROR:
+		/* error warning state */
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+		cf->data[6] = bec.txerr;
+		cf->data[7] = bec.rxerr;
+		break;
 	case C_CAN_ERROR_WARNING:
 		/* error warning state */
 		cf->can_id |= CAN_ERR_CRTL;
@@ -1029,10 +1068,16 @@ static int c_can_poll(struct napi_struct *napi, int quota)
 	u16 curr, last = priv->last_status;
 	int work_done = 0;
 
-	priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG);
-	/* Ack status on C_CAN. D_CAN is self clearing */
-	if (priv->type != BOSCH_D_CAN)
-		priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED);
+	/* Only read the status register if a status interrupt was pending */
+	if (atomic_xchg(&priv->sie_pending, 0)) {
+		priv->last_status = curr = priv->read_reg(priv, C_CAN_STS_REG);
+		/* Ack status on C_CAN. D_CAN is self clearing */
+		if (priv->type != BOSCH_D_CAN)
+			priv->write_reg(priv, C_CAN_STS_REG, LEC_UNUSED);
+	} else {
+		/* no change detected ... */
+		curr = last;
+	}
 
 	/* handle state changes */
 	if ((curr & STATUS_EWARN) && (!(last & STATUS_EWARN))) {
@@ -1054,11 +1099,17 @@ static int c_can_poll(struct napi_struct *napi, int quota)
 	/* handle bus recovery events */
 	if ((!(curr & STATUS_BOFF)) && (last & STATUS_BOFF)) {
 		netdev_dbg(dev, "left bus off state\n");
-		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		work_done += c_can_handle_state_change(dev, C_CAN_ERROR_PASSIVE);
 	}
+
 	if ((!(curr & STATUS_EPASS)) && (last & STATUS_EPASS)) {
 		netdev_dbg(dev, "left error passive state\n");
-		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+		work_done += c_can_handle_state_change(dev, C_CAN_ERROR_WARNING);
+	}
+
+	if ((!(curr & STATUS_EWARN)) && (last & STATUS_EWARN)) {
+		netdev_dbg(dev, "left error warning state\n");
+		work_done += c_can_handle_state_change(dev, C_CAN_NO_ERROR);
 	}
 
 	/* handle lec errors on the bus */
@@ -1083,10 +1134,16 @@ static irqreturn_t c_can_isr(int irq, void *dev_id)
 {
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct c_can_priv *priv = netdev_priv(dev);
+	int reg_int;
 
-	if (!priv->read_reg(priv, C_CAN_INT_REG))
+	reg_int = priv->read_reg(priv, C_CAN_INT_REG);
+	if (!reg_int)
 		return IRQ_NONE;
 
+	/* save for later use */
+	if (reg_int & INT_STS_PENDING)
+		atomic_set(&priv->sie_pending, 1);
+
 	/* disable all interrupts and schedule the NAPI */
 	c_can_irq_control(priv, false);
 	napi_schedule(&priv->napi);
diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h
index 8acdc7fa4792..d5567a7c1c6d 100644
--- a/drivers/net/can/c_can/c_can.h
+++ b/drivers/net/can/c_can/c_can.h
@@ -198,6 +198,7 @@ struct c_can_priv {
 	struct net_device *dev;
 	struct device *device;
 	atomic_t tx_active;
+	atomic_t sie_pending;
 	unsigned long tx_dir;
 	int last_status;
 	u16 (*read_reg) (const struct c_can_priv *priv, enum reg index);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index ac86be52b461..1c88c361938c 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -848,6 +848,7 @@ void of_can_transceiver(struct net_device *dev)
 		return;
 
 	ret = of_property_read_u32(dn, "max-bitrate", &priv->bitrate_max);
+	of_node_put(dn);
 	if ((ret && ret != -EINVAL) || (!ret && !priv->bitrate_max))
 		netdev_warn(dev, "Invalid value for transceiver max bitrate. Ignoring bitrate limit.\n");
 }
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index dc5695dffc2e..57f9a2f51085 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -677,6 +677,7 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr)
 	struct can_frame *cf;
 	bool rx_errors = false, tx_errors = false;
 	u32 timestamp;
+	int err;
 
 	timestamp = priv->read(&regs->timer) << 16;
 
@@ -725,7 +726,9 @@ static void flexcan_irq_bus_err(struct net_device *dev, u32 reg_esr)
 	if (tx_errors)
 		dev->stats.tx_errors++;
 
-	can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	if (err)
+		dev->stats.rx_fifo_errors++;
 }
 
 static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
@@ -738,6 +741,7 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
 	int flt;
 	struct can_berr_counter bec;
 	u32 timestamp;
+	int err;
 
 	timestamp = priv->read(&regs->timer) << 16;
 
@@ -769,7 +773,9 @@ static void flexcan_irq_state(struct net_device *dev, u32 reg_esr)
 	if (unlikely(new_state == CAN_STATE_BUS_OFF))
 		can_bus_off(dev);
 
-	can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	if (err)
+		dev->stats.rx_fifo_errors++;
 }
 
 static inline struct flexcan_priv *rx_offload_to_priv(struct can_rx_offload *offload)
@@ -1188,6 +1194,7 @@ static int flexcan_chip_start(struct net_device *dev)
 		reg_mecr = priv->read(&regs->mecr);
 		reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS;
 		priv->write(reg_mecr, &regs->mecr);
+		reg_mecr |= FLEXCAN_MECR_ECCDIS;
 		reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK |
 			      FLEXCAN_MECR_FANCEI_MSK);
 		priv->write(reg_mecr, &regs->mecr);
diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c
index e6a668ee7730..84cae167e42f 100644
--- a/drivers/net/can/rx-offload.c
+++ b/drivers/net/can/rx-offload.c
@@ -107,37 +107,95 @@ static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b)
 	return cb_b->timestamp - cb_a->timestamp;
 }
 
-static struct sk_buff *can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n)
+/**
+ * can_rx_offload_offload_one() - Read one CAN frame from HW
+ * @offload: pointer to rx_offload context
+ * @n: number of mailbox to read
+ *
+ * The task of this function is to read a CAN frame from mailbox @n
+ * from the device and return the mailbox's content as a struct
+ * sk_buff.
+ *
+ * If the struct can_rx_offload::skb_queue exceeds the maximal queue
+ * length (struct can_rx_offload::skb_queue_len_max) or no skb can be
+ * allocated, the mailbox contents is discarded by reading it into an
+ * overflow buffer. This way the mailbox is marked as free by the
+ * driver.
+ *
+ * Return: A pointer to skb containing the CAN frame on success.
+ *
+ *         NULL if the mailbox @n is empty.
+ *
+ *         ERR_PTR() in case of an error
+ */
+static struct sk_buff *
+can_rx_offload_offload_one(struct can_rx_offload *offload, unsigned int n)
 {
-	struct sk_buff *skb = NULL;
+	struct sk_buff *skb = NULL, *skb_error = NULL;
 	struct can_rx_offload_cb *cb;
 	struct can_frame *cf;
 	int ret;
 
-	/* If queue is full or skb not available, read to discard mailbox */
-	if (likely(skb_queue_len(&offload->skb_queue) <=
-		   offload->skb_queue_len_max))
+	if (likely(skb_queue_len(&offload->skb_queue) <
+		   offload->skb_queue_len_max)) {
 		skb = alloc_can_skb(offload->dev, &cf);
+		if (unlikely(!skb))
+			skb_error = ERR_PTR(-ENOMEM);	/* skb alloc failed */
+	} else {
+		skb_error = ERR_PTR(-ENOBUFS);		/* skb_queue is full */
+	}
 
-	if (!skb) {
+	/* If queue is full or skb not available, drop by reading into
+	 * overflow buffer.
+	 */
+	if (unlikely(skb_error)) {
 		struct can_frame cf_overflow;
 		u32 timestamp;
 
 		ret = offload->mailbox_read(offload, &cf_overflow,
 					    &timestamp, n);
-		if (ret)
-			offload->dev->stats.rx_dropped++;
 
-		return NULL;
+		/* Mailbox was empty. */
+		if (unlikely(!ret))
+			return NULL;
+
+		/* Mailbox has been read and we're dropping it or
+		 * there was a problem reading the mailbox.
+		 *
+		 * Increment error counters in any case.
+		 */
+		offload->dev->stats.rx_dropped++;
+		offload->dev->stats.rx_fifo_errors++;
+
+		/* There was a problem reading the mailbox, propagate
+		 * error value.
+		 */
+		if (unlikely(ret < 0))
+			return ERR_PTR(ret);
+
+		return skb_error;
 	}
 
 	cb = can_rx_offload_get_cb(skb);
 	ret = offload->mailbox_read(offload, cf, &cb->timestamp, n);
-	if (!ret) {
+
+	/* Mailbox was empty. */
+	if (unlikely(!ret)) {
 		kfree_skb(skb);
 		return NULL;
 	}
 
+	/* There was a problem reading the mailbox, propagate error value. */
+	if (unlikely(ret < 0)) {
+		kfree_skb(skb);
+
+		offload->dev->stats.rx_dropped++;
+		offload->dev->stats.rx_fifo_errors++;
+
+		return ERR_PTR(ret);
+	}
+
+	/* Mailbox was read. */
 	return skb;
 }
 
@@ -157,8 +215,8 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload, u64 pen
 			continue;
 
 		skb = can_rx_offload_offload_one(offload, i);
-		if (!skb)
-			break;
+		if (IS_ERR_OR_NULL(skb))
+			continue;
 
 		__skb_queue_add_sort(&skb_queue, skb, can_rx_offload_compare);
 	}
@@ -188,7 +246,13 @@ int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload)
 	struct sk_buff *skb;
 	int received = 0;
 
-	while ((skb = can_rx_offload_offload_one(offload, 0))) {
+	while (1) {
+		skb = can_rx_offload_offload_one(offload, 0);
+		if (IS_ERR(skb))
+			continue;
+		if (!skb)
+			break;
+
 		skb_queue_tail(&offload->skb_queue, skb);
 		received++;
 	}
@@ -207,8 +271,10 @@ int can_rx_offload_queue_sorted(struct can_rx_offload *offload,
 	unsigned long flags;
 
 	if (skb_queue_len(&offload->skb_queue) >
-	    offload->skb_queue_len_max)
-		return -ENOMEM;
+	    offload->skb_queue_len_max) {
+		kfree_skb(skb);
+		return -ENOBUFS;
+	}
 
 	cb = can_rx_offload_get_cb(skb);
 	cb->timestamp = timestamp;
@@ -250,8 +316,10 @@ int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 			      struct sk_buff *skb)
 {
 	if (skb_queue_len(&offload->skb_queue) >
-	    offload->skb_queue_len_max)
-		return -ENOMEM;
+	    offload->skb_queue_len_max) {
+		kfree_skb(skb);
+		return -ENOBUFS;
+	}
 
 	skb_queue_tail(&offload->skb_queue, skb);
 	can_rx_offload_schedule(offload);
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index bee9f7b8dad6..bb20a9b75cc6 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -717,6 +717,7 @@ static void mcp251x_restart_work_handler(struct work_struct *ws)
 	if (priv->after_suspend) {
 		mcp251x_hw_reset(spi);
 		mcp251x_setup(net, spi);
+		priv->force_quit = 0;
 		if (priv->after_suspend & AFTER_SUSPEND_RESTART) {
 			mcp251x_set_normal_mode(spi);
 		} else if (priv->after_suspend & AFTER_SUSPEND_UP) {
@@ -728,7 +729,6 @@ static void mcp251x_restart_work_handler(struct work_struct *ws)
 			mcp251x_hw_sleep(spi);
 		}
 		priv->after_suspend = 0;
-		priv->force_quit = 0;
 	}
 
 	if (priv->restart_tx) {
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index f8b19eef5d26..31ad364a89bb 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -73,6 +73,7 @@ MODULE_VERSION(HECC_MODULE_VERSION);
  */
 #define HECC_MAX_RX_MBOX	(HECC_MAX_MAILBOXES - HECC_MAX_TX_MBOX)
 #define HECC_RX_FIRST_MBOX	(HECC_MAX_MAILBOXES - 1)
+#define HECC_RX_LAST_MBOX	(HECC_MAX_TX_MBOX)
 
 /* TI HECC module registers */
 #define HECC_CANME		0x0	/* Mailbox enable */
@@ -82,7 +83,7 @@ MODULE_VERSION(HECC_MODULE_VERSION);
 #define HECC_CANTA		0x10	/* Transmission acknowledge */
 #define HECC_CANAA		0x14	/* Abort acknowledge */
 #define HECC_CANRMP		0x18	/* Receive message pending */
-#define HECC_CANRML		0x1C	/* Remote message lost */
+#define HECC_CANRML		0x1C	/* Receive message lost */
 #define HECC_CANRFP		0x20	/* Remote frame pending */
 #define HECC_CANGAM		0x24	/* SECC only:Global acceptance mask */
 #define HECC_CANMC		0x28	/* Master control */
@@ -149,6 +150,8 @@ MODULE_VERSION(HECC_MODULE_VERSION);
 #define HECC_BUS_ERROR		(HECC_CANES_FE | HECC_CANES_BE |\
 				HECC_CANES_CRCE | HECC_CANES_SE |\
 				HECC_CANES_ACKE)
+#define HECC_CANES_FLAGS	(HECC_BUS_ERROR | HECC_CANES_BO |\
+				HECC_CANES_EP | HECC_CANES_EW)
 
 #define HECC_CANMCF_RTR		BIT(4)	/* Remote transmit request */
 
@@ -382,8 +385,18 @@ static void ti_hecc_start(struct net_device *ndev)
 		hecc_set_bit(priv, HECC_CANMIM, mbx_mask);
 	}
 
-	/* Prevent message over-write & Enable interrupts */
-	hecc_write(priv, HECC_CANOPC, HECC_SET_REG);
+	/* Enable tx interrupts */
+	hecc_set_bit(priv, HECC_CANMIM, BIT(HECC_MAX_TX_MBOX) - 1);
+
+	/* Prevent message over-write to create a rx fifo, but not for
+	 * the lowest priority mailbox, since that allows detecting
+	 * overflows instead of the hardware silently dropping the
+	 * messages.
+	 */
+	mbx_mask = ~BIT(HECC_RX_LAST_MBOX);
+	hecc_write(priv, HECC_CANOPC, mbx_mask);
+
+	/* Enable interrupts */
 	if (priv->use_hecc1int) {
 		hecc_write(priv, HECC_CANMIL, HECC_SET_REG);
 		hecc_write(priv, HECC_CANGIM, HECC_CANGIM_DEF_MASK |
@@ -400,6 +413,9 @@ static void ti_hecc_stop(struct net_device *ndev)
 {
 	struct ti_hecc_priv *priv = netdev_priv(ndev);
 
+	/* Disable the CPK; stop sending, erroring and acking */
+	hecc_set_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
+
 	/* Disable interrupts and disable mailboxes */
 	hecc_write(priv, HECC_CANGIM, 0);
 	hecc_write(priv, HECC_CANMIM, 0);
@@ -508,8 +524,6 @@ static netdev_tx_t ti_hecc_xmit(struct sk_buff *skb, struct net_device *ndev)
 	hecc_set_bit(priv, HECC_CANME, mbx_mask);
 	spin_unlock_irqrestore(&priv->mbx_lock, flags);
 
-	hecc_clear_bit(priv, HECC_CANMD, mbx_mask);
-	hecc_set_bit(priv, HECC_CANMIM, mbx_mask);
 	hecc_write(priv, HECC_CANTRS, mbx_mask);
 
 	return NETDEV_TX_OK;
@@ -526,8 +540,10 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload,
 					 u32 *timestamp, unsigned int mbxno)
 {
 	struct ti_hecc_priv *priv = rx_offload_to_priv(offload);
-	u32 data;
+	u32 data, mbx_mask;
+	int ret = 1;
 
+	mbx_mask = BIT(mbxno);
 	data = hecc_read_mbx(priv, mbxno, HECC_CANMID);
 	if (data & HECC_CANMID_IDE)
 		cf->can_id = (data & CAN_EFF_MASK) | CAN_EFF_FLAG;
@@ -548,7 +564,25 @@ static unsigned int ti_hecc_mailbox_read(struct can_rx_offload *offload,
 
 	*timestamp = hecc_read_stamp(priv, mbxno);
 
-	return 1;
+	/* Check for FIFO overrun.
+	 *
+	 * All but the last RX mailbox have activated overwrite
+	 * protection. So skip check for overrun, if we're not
+	 * handling the last RX mailbox.
+	 *
+	 * As the overwrite protection for the last RX mailbox is
+	 * disabled, the CAN core might update while we're reading
+	 * it. This means the skb might be inconsistent.
+	 *
+	 * Return an error to let rx-offload discard this CAN frame.
+	 */
+	if (unlikely(mbxno == HECC_RX_LAST_MBOX &&
+		     hecc_read(priv, HECC_CANRML) & mbx_mask))
+		ret = -ENOBUFS;
+
+	hecc_write(priv, HECC_CANRMP, mbx_mask);
+
+	return ret;
 }
 
 static int ti_hecc_error(struct net_device *ndev, int int_status,
@@ -558,92 +592,73 @@ static int ti_hecc_error(struct net_device *ndev, int int_status,
 	struct can_frame *cf;
 	struct sk_buff *skb;
 	u32 timestamp;
+	int err;
 
-	/* propagate the error condition to the can stack */
-	skb = alloc_can_err_skb(ndev, &cf);
-	if (!skb) {
-		if (printk_ratelimit())
-			netdev_err(priv->ndev,
-				   "%s: alloc_can_err_skb() failed\n",
-				   __func__);
-		return -ENOMEM;
-	}
-
-	if (int_status & HECC_CANGIF_WLIF) { /* warning level int */
-		if ((int_status & HECC_CANGIF_BOIF) == 0) {
-			priv->can.state = CAN_STATE_ERROR_WARNING;
-			++priv->can.can_stats.error_warning;
-			cf->can_id |= CAN_ERR_CRTL;
-			if (hecc_read(priv, HECC_CANTEC) > 96)
-				cf->data[1] |= CAN_ERR_CRTL_TX_WARNING;
-			if (hecc_read(priv, HECC_CANREC) > 96)
-				cf->data[1] |= CAN_ERR_CRTL_RX_WARNING;
-		}
-		hecc_set_bit(priv, HECC_CANES, HECC_CANES_EW);
-		netdev_dbg(priv->ndev, "Error Warning interrupt\n");
-		hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
-	}
-
-	if (int_status & HECC_CANGIF_EPIF) { /* error passive int */
-		if ((int_status & HECC_CANGIF_BOIF) == 0) {
-			priv->can.state = CAN_STATE_ERROR_PASSIVE;
-			++priv->can.can_stats.error_passive;
-			cf->can_id |= CAN_ERR_CRTL;
-			if (hecc_read(priv, HECC_CANTEC) > 127)
-				cf->data[1] |= CAN_ERR_CRTL_TX_PASSIVE;
-			if (hecc_read(priv, HECC_CANREC) > 127)
-				cf->data[1] |= CAN_ERR_CRTL_RX_PASSIVE;
+	if (err_status & HECC_BUS_ERROR) {
+		/* propagate the error condition to the can stack */
+		skb = alloc_can_err_skb(ndev, &cf);
+		if (!skb) {
+			if (net_ratelimit())
+				netdev_err(priv->ndev,
+					   "%s: alloc_can_err_skb() failed\n",
+					   __func__);
+			return -ENOMEM;
 		}
-		hecc_set_bit(priv, HECC_CANES, HECC_CANES_EP);
-		netdev_dbg(priv->ndev, "Error passive interrupt\n");
-		hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
-	}
-
-	/* Need to check busoff condition in error status register too to
-	 * ensure warning interrupts don't hog the system
-	 */
-	if ((int_status & HECC_CANGIF_BOIF) || (err_status & HECC_CANES_BO)) {
-		priv->can.state = CAN_STATE_BUS_OFF;
-		cf->can_id |= CAN_ERR_BUSOFF;
-		hecc_set_bit(priv, HECC_CANES, HECC_CANES_BO);
-		hecc_clear_bit(priv, HECC_CANMC, HECC_CANMC_CCR);
-		/* Disable all interrupts in bus-off to avoid int hog */
-		hecc_write(priv, HECC_CANGIM, 0);
-		++priv->can.can_stats.bus_off;
-		can_bus_off(ndev);
-	}
 
-	if (err_status & HECC_BUS_ERROR) {
 		++priv->can.can_stats.bus_error;
 		cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-		if (err_status & HECC_CANES_FE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_FE);
+		if (err_status & HECC_CANES_FE)
 			cf->data[2] |= CAN_ERR_PROT_FORM;
-		}
-		if (err_status & HECC_CANES_BE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_BE);
+		if (err_status & HECC_CANES_BE)
 			cf->data[2] |= CAN_ERR_PROT_BIT;
-		}
-		if (err_status & HECC_CANES_SE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_SE);
+		if (err_status & HECC_CANES_SE)
 			cf->data[2] |= CAN_ERR_PROT_STUFF;
-		}
-		if (err_status & HECC_CANES_CRCE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_CRCE);
+		if (err_status & HECC_CANES_CRCE)
 			cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
-		}
-		if (err_status & HECC_CANES_ACKE) {
-			hecc_set_bit(priv, HECC_CANES, HECC_CANES_ACKE);
+		if (err_status & HECC_CANES_ACKE)
 			cf->data[3] = CAN_ERR_PROT_LOC_ACK;
-		}
+
+		timestamp = hecc_read(priv, HECC_CANLNT);
+		err = can_rx_offload_queue_sorted(&priv->offload, skb,
+						  timestamp);
+		if (err)
+			ndev->stats.rx_fifo_errors++;
 	}
 
-	timestamp = hecc_read(priv, HECC_CANLNT);
-	can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	hecc_write(priv, HECC_CANES, HECC_CANES_FLAGS);
 
 	return 0;
 }
 
+static void ti_hecc_change_state(struct net_device *ndev,
+				 enum can_state rx_state,
+				 enum can_state tx_state)
+{
+	struct ti_hecc_priv *priv = netdev_priv(ndev);
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 timestamp;
+	int err;
+
+	skb = alloc_can_err_skb(priv->ndev, &cf);
+	if (unlikely(!skb)) {
+		priv->can.state = max(tx_state, rx_state);
+		return;
+	}
+
+	can_change_state(priv->ndev, cf, tx_state, rx_state);
+
+	if (max(tx_state, rx_state) != CAN_STATE_BUS_OFF) {
+		cf->data[6] = hecc_read(priv, HECC_CANTEC);
+		cf->data[7] = hecc_read(priv, HECC_CANREC);
+	}
+
+	timestamp = hecc_read(priv, HECC_CANLNT);
+	err = can_rx_offload_queue_sorted(&priv->offload, skb, timestamp);
+	if (err)
+		ndev->stats.rx_fifo_errors++;
+}
+
 static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 {
 	struct net_device *ndev = (struct net_device *)dev_id;
@@ -651,6 +666,7 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 	struct net_device_stats *stats = &ndev->stats;
 	u32 mbxno, mbx_mask, int_status, err_status, stamp;
 	unsigned long flags, rx_pending;
+	u32 handled = 0;
 
 	int_status = hecc_read(priv,
 			       priv->use_hecc1int ?
@@ -660,17 +676,66 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 		return IRQ_NONE;
 
 	err_status = hecc_read(priv, HECC_CANES);
-	if (err_status & (HECC_BUS_ERROR | HECC_CANES_BO |
-			  HECC_CANES_EP | HECC_CANES_EW))
+	if (unlikely(err_status & HECC_CANES_FLAGS))
 		ti_hecc_error(ndev, int_status, err_status);
 
+	if (unlikely(int_status & HECC_CANGIM_DEF_MASK)) {
+		enum can_state rx_state, tx_state;
+		u32 rec = hecc_read(priv, HECC_CANREC);
+		u32 tec = hecc_read(priv, HECC_CANTEC);
+
+		if (int_status & HECC_CANGIF_WLIF) {
+			handled |= HECC_CANGIF_WLIF;
+			rx_state = rec >= tec ? CAN_STATE_ERROR_WARNING : 0;
+			tx_state = rec <= tec ? CAN_STATE_ERROR_WARNING : 0;
+			netdev_dbg(priv->ndev, "Error Warning interrupt\n");
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+
+		if (int_status & HECC_CANGIF_EPIF) {
+			handled |= HECC_CANGIF_EPIF;
+			rx_state = rec >= tec ? CAN_STATE_ERROR_PASSIVE : 0;
+			tx_state = rec <= tec ? CAN_STATE_ERROR_PASSIVE : 0;
+			netdev_dbg(priv->ndev, "Error passive interrupt\n");
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+
+		if (int_status & HECC_CANGIF_BOIF) {
+			handled |= HECC_CANGIF_BOIF;
+			rx_state = CAN_STATE_BUS_OFF;
+			tx_state = CAN_STATE_BUS_OFF;
+			netdev_dbg(priv->ndev, "Bus off interrupt\n");
+
+			/* Disable all interrupts */
+			hecc_write(priv, HECC_CANGIM, 0);
+			can_bus_off(ndev);
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+	} else if (unlikely(priv->can.state != CAN_STATE_ERROR_ACTIVE)) {
+		enum can_state new_state, tx_state, rx_state;
+		u32 rec = hecc_read(priv, HECC_CANREC);
+		u32 tec = hecc_read(priv, HECC_CANTEC);
+
+		if (rec >= 128 || tec >= 128)
+			new_state = CAN_STATE_ERROR_PASSIVE;
+		else if (rec >= 96 || tec >= 96)
+			new_state = CAN_STATE_ERROR_WARNING;
+		else
+			new_state = CAN_STATE_ERROR_ACTIVE;
+
+		if (new_state < priv->can.state) {
+			rx_state = rec >= tec ? new_state : 0;
+			tx_state = rec <= tec ? new_state : 0;
+			ti_hecc_change_state(ndev, rx_state, tx_state);
+		}
+	}
+
 	if (int_status & HECC_CANGIF_GMIF) {
 		while (priv->tx_tail - priv->tx_head > 0) {
 			mbxno = get_tx_tail_mb(priv);
 			mbx_mask = BIT(mbxno);
 			if (!(mbx_mask & hecc_read(priv, HECC_CANTA)))
 				break;
-			hecc_clear_bit(priv, HECC_CANMIM, mbx_mask);
 			hecc_write(priv, HECC_CANTA, mbx_mask);
 			spin_lock_irqsave(&priv->mbx_lock, flags);
 			hecc_clear_bit(priv, HECC_CANME, mbx_mask);
@@ -695,16 +760,15 @@ static irqreturn_t ti_hecc_interrupt(int irq, void *dev_id)
 		while ((rx_pending = hecc_read(priv, HECC_CANRMP))) {
 			can_rx_offload_irq_offload_timestamp(&priv->offload,
 							     rx_pending);
-			hecc_write(priv, HECC_CANRMP, rx_pending);
 		}
 	}
 
 	/* clear all interrupt conditions - read back to avoid spurious ints */
 	if (priv->use_hecc1int) {
-		hecc_write(priv, HECC_CANGIF1, HECC_SET_REG);
+		hecc_write(priv, HECC_CANGIF1, handled);
 		int_status = hecc_read(priv, HECC_CANGIF1);
 	} else {
-		hecc_write(priv, HECC_CANGIF0, HECC_SET_REG);
+		hecc_write(priv, HECC_CANGIF0, handled);
 		int_status = hecc_read(priv, HECC_CANGIF0);
 	}
 
@@ -877,7 +941,7 @@ static int ti_hecc_probe(struct platform_device *pdev)
 
 	priv->offload.mailbox_read = ti_hecc_mailbox_read;
 	priv->offload.mb_first = HECC_RX_FIRST_MBOX;
-	priv->offload.mb_last = HECC_MAX_TX_MBOX;
+	priv->offload.mb_last = HECC_RX_LAST_MBOX;
 	err = can_rx_offload_add_timestamp(ndev, &priv->offload);
 	if (err) {
 		dev_err(&pdev->dev, "can_rx_offload_add_timestamp() failed\n");
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index bd6eb9967630..2f74f6704c12 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -623,6 +623,7 @@ static int gs_can_open(struct net_device *netdev)
 					   rc);
 
 				usb_unanchor_urb(urb);
+				usb_free_urb(urb);
 				break;
 			}
 
diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c
index 19a702ac49e4..21faa2ec4632 100644
--- a/drivers/net/can/usb/mcba_usb.c
+++ b/drivers/net/can/usb/mcba_usb.c
@@ -876,9 +876,8 @@ static void mcba_usb_disconnect(struct usb_interface *intf)
 	netdev_info(priv->netdev, "device disconnected\n");
 
 	unregister_candev(priv->netdev);
-	free_candev(priv->netdev);
-
 	mcba_urb_unlink(priv);
+	free_candev(priv->netdev);
 }
 
 static struct usb_driver mcba_usb_driver = {
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 617da295b6c1..d2539c95adb6 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -100,7 +100,7 @@ struct pcan_usb_msg_context {
 	u8 *end;
 	u8 rec_cnt;
 	u8 rec_idx;
-	u8 rec_data_idx;
+	u8 rec_ts_idx;
 	struct net_device *netdev;
 	struct pcan_usb *pdev;
 };
@@ -436,8 +436,8 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 		}
 		if ((n & PCAN_USB_ERROR_BUS_LIGHT) == 0) {
 			/* no error (back to active state) */
-			mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE;
-			return 0;
+			new_state = CAN_STATE_ERROR_ACTIVE;
+			break;
 		}
 		break;
 
@@ -460,9 +460,9 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 		}
 
 		if ((n & PCAN_USB_ERROR_BUS_HEAVY) == 0) {
-			/* no error (back to active state) */
-			mc->pdev->dev.can.state = CAN_STATE_ERROR_ACTIVE;
-			return 0;
+			/* no error (back to warning state) */
+			new_state = CAN_STATE_ERROR_WARNING;
+			break;
 		}
 		break;
 
@@ -501,6 +501,11 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 		mc->pdev->dev.can.can_stats.error_warning++;
 		break;
 
+	case CAN_STATE_ERROR_ACTIVE:
+		cf->can_id |= CAN_ERR_CRTL;
+		cf->data[1] = CAN_ERR_CRTL_ACTIVE;
+		break;
+
 	default:
 		/* CAN_STATE_MAX (trick to handle other errors) */
 		cf->can_id |= CAN_ERR_CRTL;
@@ -547,10 +552,15 @@ static int pcan_usb_decode_status(struct pcan_usb_msg_context *mc,
 	mc->ptr += PCAN_USB_CMD_ARGS;
 
 	if (status_len & PCAN_USB_STATUSLEN_TIMESTAMP) {
-		int err = pcan_usb_decode_ts(mc, !mc->rec_idx);
+		int err = pcan_usb_decode_ts(mc, !mc->rec_ts_idx);
 
 		if (err)
 			return err;
+
+		/* Next packet in the buffer will have a timestamp on a single
+		 * byte
+		 */
+		mc->rec_ts_idx++;
 	}
 
 	switch (f) {
@@ -632,10 +642,13 @@ static int pcan_usb_decode_data(struct pcan_usb_msg_context *mc, u8 status_len)
 
 	cf->can_dlc = get_can_dlc(rec_len);
 
-	/* first data packet timestamp is a word */
-	if (pcan_usb_decode_ts(mc, !mc->rec_data_idx))
+	/* Only first packet timestamp is a word */
+	if (pcan_usb_decode_ts(mc, !mc->rec_ts_idx))
 		goto decode_failed;
 
+	/* Next packet in the buffer will have a timestamp on a single byte */
+	mc->rec_ts_idx++;
+
 	/* read data */
 	memset(cf->data, 0x0, sizeof(cf->data));
 	if (status_len & PCAN_USB_STATUSLEN_RTR) {
@@ -688,7 +701,6 @@ static int pcan_usb_decode_msg(struct peak_usb_device *dev, u8 *ibuf, u32 lbuf)
 		/* handle normal can frames here */
 		} else {
 			err = pcan_usb_decode_data(&mc, sl);
-			mc.rec_data_idx++;
 		}
 	}
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 65dce642b86b..0b7766b715fd 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -750,7 +750,7 @@ static int peak_usb_create_dev(const struct peak_usb_adapter *peak_usb_adapter,
 	dev = netdev_priv(netdev);
 
 	/* allocate a buffer large enough to send commands */
-	dev->cmd_buf = kmalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
+	dev->cmd_buf = kzalloc(PCAN_USB_MAX_CMD_LEN, GFP_KERNEL);
 	if (!dev->cmd_buf) {
 		err = -ENOMEM;
 		goto lbl_free_candev;
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index d596a2ad7f78..8fa224b28218 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -996,9 +996,8 @@ static void usb_8dev_disconnect(struct usb_interface *intf)
 		netdev_info(priv->netdev, "device disconnected\n");
 
 		unregister_netdev(priv->netdev);
-		free_candev(priv->netdev);
-
 		unlink_all_urbs(priv);
+		free_candev(priv->netdev);
 	}
 
 }
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 911b34316c9d..7c482b2d78d2 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -1599,7 +1599,6 @@ static const struct xcan_devtype_data xcan_zynq_data = {
 
 static const struct xcan_devtype_data xcan_axi_data = {
 	.cantype = XAXI_CAN,
-	.flags = XCAN_FLAG_TXFEMP,
 	.bittiming_const = &xcan_bittiming_const,
 	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT,
 	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT,
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 26509fa37a50..69fc13046ac7 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -37,22 +37,11 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 	unsigned int i;
 	u32 reg, offset;
 
-	if (priv->type == BCM7445_DEVICE_ID)
-		offset = CORE_STS_OVERRIDE_IMP;
-	else
-		offset = CORE_STS_OVERRIDE_IMP2;
-
 	/* Enable the port memories */
 	reg = core_readl(priv, CORE_MEM_PSM_VDD_CTRL);
 	reg &= ~P_TXQ_PSM_VDD(port);
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 
-	/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
-	reg = core_readl(priv, CORE_IMP_CTL);
-	reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN);
-	reg &= ~(RX_DIS | TX_DIS);
-	core_writel(priv, reg, CORE_IMP_CTL);
-
 	/* Enable forwarding */
 	core_writel(priv, SW_FWDG_EN, CORE_SWMODE);
 
@@ -71,10 +60,27 @@ static void bcm_sf2_imp_setup(struct dsa_switch *ds, int port)
 
 	b53_brcm_hdr_setup(ds, port);
 
-	/* Force link status for IMP port */
-	reg = core_readl(priv, offset);
-	reg |= (MII_SW_OR | LINK_STS);
-	core_writel(priv, reg, offset);
+	if (port == 8) {
+		if (priv->type == BCM7445_DEVICE_ID)
+			offset = CORE_STS_OVERRIDE_IMP;
+		else
+			offset = CORE_STS_OVERRIDE_IMP2;
+
+		/* Force link status for IMP port */
+		reg = core_readl(priv, offset);
+		reg |= (MII_SW_OR | LINK_STS);
+		core_writel(priv, reg, offset);
+
+		/* Enable Broadcast, Multicast, Unicast forwarding to IMP port */
+		reg = core_readl(priv, CORE_IMP_CTL);
+		reg |= (RX_BCST_EN | RX_MCST_EN | RX_UCST_EN);
+		reg &= ~(RX_DIS | TX_DIS);
+		core_writel(priv, reg, CORE_IMP_CTL);
+	} else {
+		reg = core_readl(priv, CORE_G_PCTL_PORT(port));
+		reg &= ~(RX_DIS | TX_DIS);
+		core_writel(priv, reg, CORE_G_PCTL_PORT(port));
+	}
 }
 
 static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
@@ -1209,10 +1215,10 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
 	struct bcm_sf2_priv *priv = platform_get_drvdata(pdev);
 
 	priv->wol_ports_mask = 0;
+	/* Disable interrupts */
+	bcm_sf2_intr_disable(priv);
 	dsa_unregister_switch(priv->dev->ds);
 	bcm_sf2_cfp_exit(priv->dev->ds);
-	/* Disable all ports and interrupts */
-	bcm_sf2_sw_suspend(priv->dev->ds);
 	bcm_sf2_mdio_unregister(priv);
 
 	return 0;
diff --git a/drivers/net/dsa/sja1105/Kconfig b/drivers/net/dsa/sja1105/Kconfig
index f40b248f0b23..ffac0ea4e8d5 100644
--- a/drivers/net/dsa/sja1105/Kconfig
+++ b/drivers/net/dsa/sja1105/Kconfig
@@ -26,8 +26,8 @@ config NET_DSA_SJA1105_PTP
 
 config NET_DSA_SJA1105_TAS
 	bool "Support for the Time-Aware Scheduler on NXP SJA1105"
-	depends on NET_DSA_SJA1105
-	depends on NET_SCH_TAPRIO
+	depends on NET_DSA_SJA1105 && NET_SCH_TAPRIO
+	depends on NET_SCH_TAPRIO=y || NET_DSA_SJA1105=m
 	help
 	  This enables support for the TTEthernet-based egress scheduling
 	  engine in the SJA1105 DSA driver, which is controlled using a
diff --git a/drivers/net/ethernet/arc/emac_rockchip.c b/drivers/net/ethernet/arc/emac_rockchip.c
index 42d2e1b02c44..664d664e0925 100644
--- a/drivers/net/ethernet/arc/emac_rockchip.c
+++ b/drivers/net/ethernet/arc/emac_rockchip.c
@@ -256,6 +256,9 @@ static int emac_rockchip_remove(struct platform_device *pdev)
 	if (priv->regulator)
 		regulator_disable(priv->regulator);
 
+	if (priv->soc_data->need_div_macclk)
+		clk_disable_unprepare(priv->macclk);
+
 	free_netdev(ndev);
 	return err;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b4a8cf620a0c..04ec909e06df 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -10382,7 +10382,8 @@ static void bnxt_cleanup_pci(struct bnxt *bp)
 {
 	bnxt_unmap_bars(bp, bp->pdev);
 	pci_release_regions(bp->pdev);
-	pci_disable_device(bp->pdev);
+	if (pci_is_enabled(bp->pdev))
+		pci_disable_device(bp->pdev);
 }
 
 static void bnxt_init_dflt_coal(struct bnxt *bp)
@@ -10669,14 +10670,11 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW;
 	}
 	/* fall through */
-	case BNXT_FW_RESET_STATE_RESET_FW: {
-		u32 wait_dsecs = bp->fw_health->post_reset_wait_dsecs;
-
+	case BNXT_FW_RESET_STATE_RESET_FW:
 		bnxt_reset_all(bp);
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
-		bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10);
+		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
 		return;
-	}
 	case BNXT_FW_RESET_STATE_ENABLE_DEV:
 		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
 		    bp->fw_health) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index e664392dccc0..7151244f8c7d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -29,25 +29,20 @@ static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
 	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);
 	health_status = val & 0xffff;
 
-	if (health_status == BNXT_FW_STATUS_HEALTHY) {
-		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
-						  "Healthy;");
-		if (rc)
-			return rc;
-	} else if (health_status < BNXT_FW_STATUS_HEALTHY) {
-		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
-						  "Not yet completed initialization;");
+	if (health_status < BNXT_FW_STATUS_HEALTHY) {
+		rc = devlink_fmsg_string_pair_put(fmsg, "Description",
+						  "Not yet completed initialization");
 		if (rc)
 			return rc;
 	} else if (health_status > BNXT_FW_STATUS_HEALTHY) {
-		rc = devlink_fmsg_string_pair_put(fmsg, "FW status",
-						  "Encountered fatal error and cannot recover;");
+		rc = devlink_fmsg_string_pair_put(fmsg, "Description",
+						  "Encountered fatal error and cannot recover");
 		if (rc)
 			return rc;
 	}
 
 	if (val >> 16) {
-		rc = devlink_fmsg_u32_pair_put(fmsg, "Error", val >> 16);
+		rc = devlink_fmsg_u32_pair_put(fmsg, "Error code", val >> 16);
 		if (rc)
 			return rc;
 	}
@@ -215,25 +210,68 @@ enum bnxt_dl_param_id {
 
 static const struct bnxt_dl_nvm_param nvm_params[] = {
 	{DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV,
-	 BNXT_NVM_SHARED_CFG, 1},
+	 BNXT_NVM_SHARED_CFG, 1, 1},
 	{DEVLINK_PARAM_GENERIC_ID_IGNORE_ARI, NVM_OFF_IGNORE_ARI,
-	 BNXT_NVM_SHARED_CFG, 1},
+	 BNXT_NVM_SHARED_CFG, 1, 1},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
-	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10},
+	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10, 4},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
-	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7},
+	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7, 4},
 	{BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK,
-	 BNXT_NVM_SHARED_CFG, 1},
+	 BNXT_NVM_SHARED_CFG, 1, 1},
 };
 
+union bnxt_nvm_data {
+	u8	val8;
+	__le32	val32;
+};
+
+static void bnxt_copy_to_nvm_data(union bnxt_nvm_data *dst,
+				  union devlink_param_value *src,
+				  int nvm_num_bits, int dl_num_bytes)
+{
+	u32 val32 = 0;
+
+	if (nvm_num_bits == 1) {
+		dst->val8 = src->vbool;
+		return;
+	}
+	if (dl_num_bytes == 4)
+		val32 = src->vu32;
+	else if (dl_num_bytes == 2)
+		val32 = (u32)src->vu16;
+	else if (dl_num_bytes == 1)
+		val32 = (u32)src->vu8;
+	dst->val32 = cpu_to_le32(val32);
+}
+
+static void bnxt_copy_from_nvm_data(union devlink_param_value *dst,
+				    union bnxt_nvm_data *src,
+				    int nvm_num_bits, int dl_num_bytes)
+{
+	u32 val32;
+
+	if (nvm_num_bits == 1) {
+		dst->vbool = src->val8;
+		return;
+	}
+	val32 = le32_to_cpu(src->val32);
+	if (dl_num_bytes == 4)
+		dst->vu32 = val32;
+	else if (dl_num_bytes == 2)
+		dst->vu16 = (u16)val32;
+	else if (dl_num_bytes == 1)
+		dst->vu8 = (u8)val32;
+}
+
 static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 			     int msg_len, union devlink_param_value *val)
 {
 	struct hwrm_nvm_get_variable_input *req = msg;
-	void *data_addr = NULL, *buf = NULL;
 	struct bnxt_dl_nvm_param nvm_param;
-	int bytesize, idx = 0, rc, i;
+	union bnxt_nvm_data *data;
 	dma_addr_t data_dma_addr;
+	int idx = 0, rc, i;
 
 	/* Get/Set NVM CFG parameter is supported only on PFs */
 	if (BNXT_VF(bp))
@@ -254,47 +292,31 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
 		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
 
-	bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE;
-	switch (bytesize) {
-	case 1:
-		if (nvm_param.num_bits == 1)
-			buf = &val->vbool;
-		else
-			buf = &val->vu8;
-		break;
-	case 2:
-		buf = &val->vu16;
-		break;
-	case 4:
-		buf = &val->vu32;
-		break;
-	default:
-		return -EFAULT;
-	}
-
-	data_addr = dma_alloc_coherent(&bp->pdev->dev, bytesize,
-				       &data_dma_addr, GFP_KERNEL);
-	if (!data_addr)
+	data = dma_alloc_coherent(&bp->pdev->dev, sizeof(*data),
+				  &data_dma_addr, GFP_KERNEL);
+	if (!data)
 		return -ENOMEM;
 
 	req->dest_data_addr = cpu_to_le64(data_dma_addr);
-	req->data_len = cpu_to_le16(nvm_param.num_bits);
+	req->data_len = cpu_to_le16(nvm_param.nvm_num_bits);
 	req->option_num = cpu_to_le16(nvm_param.offset);
 	req->index_0 = cpu_to_le16(idx);
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
 	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
-		memcpy(data_addr, buf, bytesize);
+		bnxt_copy_to_nvm_data(data, val, nvm_param.nvm_num_bits,
+				      nvm_param.dl_num_bytes);
 		rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
 	} else {
 		rc = hwrm_send_message_silent(bp, msg, msg_len,
 					      HWRM_CMD_TIMEOUT);
+		if (!rc)
+			bnxt_copy_from_nvm_data(val, data,
+						nvm_param.nvm_num_bits,
+						nvm_param.dl_num_bytes);
 	}
-	if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE))
-		memcpy(buf, data_addr, bytesize);
-
-	dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
+	dma_free_coherent(&bp->pdev->dev, sizeof(*data), data, data_dma_addr);
 	if (rc == -EACCES)
 		netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n");
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index b97e0baeb42d..2f4fd0a7d04b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -52,7 +52,8 @@ struct bnxt_dl_nvm_param {
 	u16 id;
 	u16 offset;
 	u16 dir_type;
-	u16 num_bits;
+	u16 nvm_num_bits;
+	u8 dl_num_bytes;
 };
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0f138280315a..1de51811fcb4 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1996,8 +1996,6 @@ static void reset_umac(struct bcmgenet_priv *priv)
 
 	/* issue soft reset with (rg)mii loopback to ensure a stable rxclk */
 	bcmgenet_umac_writel(priv, CMD_SW_RESET | CMD_LCL_LOOP_EN, UMAC_CMD);
-	udelay(2);
-	bcmgenet_umac_writel(priv, 0, UMAC_CMD);
 }
 
 static void bcmgenet_intr_disable(struct bcmgenet_priv *priv)
@@ -2614,8 +2612,10 @@ static void bcmgenet_irq_task(struct work_struct *work)
 	spin_unlock_irq(&priv->lock);
 
 	if (status & UMAC_IRQ_PHY_DET_R &&
-	    priv->dev->phydev->autoneg != AUTONEG_ENABLE)
+	    priv->dev->phydev->autoneg != AUTONEG_ENABLE) {
 		phy_init_hw(priv->dev->phydev);
+		genphy_config_aneg(priv->dev->phydev);
+	}
 
 	/* Link UP/DOWN event */
 	if (status & UMAC_IRQ_LINK_EVENT)
@@ -2879,12 +2879,6 @@ static int bcmgenet_open(struct net_device *dev)
 	if (priv->internal_phy)
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
-	ret = bcmgenet_mii_connect(dev);
-	if (ret) {
-		netdev_err(dev, "failed to connect to PHY\n");
-		goto err_clk_disable;
-	}
-
 	/* take MAC out of reset */
 	bcmgenet_umac_reset(priv);
 
@@ -2894,12 +2888,6 @@ static int bcmgenet_open(struct net_device *dev)
 	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
 	priv->crc_fwd_en = !!(reg & CMD_CRC_FWD);
 
-	ret = bcmgenet_mii_config(dev, true);
-	if (ret) {
-		netdev_err(dev, "unsupported PHY\n");
-		goto err_disconnect_phy;
-	}
-
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
 	if (priv->internal_phy) {
@@ -2915,7 +2903,7 @@ static int bcmgenet_open(struct net_device *dev)
 	ret = bcmgenet_init_dma(priv);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
-		goto err_disconnect_phy;
+		goto err_clk_disable;
 	}
 
 	/* Always enable ring 16 - descriptor ring */
@@ -2938,19 +2926,25 @@ static int bcmgenet_open(struct net_device *dev)
 		goto err_irq0;
 	}
 
+	ret = bcmgenet_mii_probe(dev);
+	if (ret) {
+		netdev_err(dev, "failed to connect to PHY\n");
+		goto err_irq1;
+	}
+
 	bcmgenet_netif_start(dev);
 
 	netif_tx_start_all_queues(dev);
 
 	return 0;
 
+err_irq1:
+	free_irq(priv->irq1, priv);
 err_irq0:
 	free_irq(priv->irq0, priv);
 err_fini_dma:
 	bcmgenet_dma_teardown(priv);
 	bcmgenet_fini_dma(priv);
-err_disconnect_phy:
-	phy_disconnect(dev->phydev);
 err_clk_disable:
 	if (priv->internal_phy)
 		bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
@@ -3631,8 +3625,6 @@ static int bcmgenet_resume(struct device *d)
 	if (priv->internal_phy)
 		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
 
-	phy_init_hw(dev->phydev);
-
 	bcmgenet_umac_reset(priv);
 
 	init_umac(priv);
@@ -3641,7 +3633,10 @@ static int bcmgenet_resume(struct device *d)
 	if (priv->wolopts)
 		clk_disable_unprepare(priv->clk_wol);
 
+	phy_init_hw(dev->phydev);
+
 	/* Speed settings must be restored */
+	genphy_config_aneg(dev->phydev);
 	bcmgenet_mii_config(priv->dev, false);
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 7fbf573d8d52..dbc69d8fa05f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -720,8 +720,8 @@ GENET_IO_MACRO(rbuf, GENET_RBUF_OFF);
 
 /* MDIO routines */
 int bcmgenet_mii_init(struct net_device *dev);
-int bcmgenet_mii_connect(struct net_device *dev);
 int bcmgenet_mii_config(struct net_device *dev, bool init);
+int bcmgenet_mii_probe(struct net_device *dev);
 void bcmgenet_mii_exit(struct net_device *dev);
 void bcmgenet_phy_power_set(struct net_device *dev, bool enable);
 void bcmgenet_mii_setup(struct net_device *dev);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index 17bb8d60a157..dbe18cdf6c1b 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -173,46 +173,6 @@ static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 					  bcmgenet_fixed_phy_link_update);
 }
 
-int bcmgenet_mii_connect(struct net_device *dev)
-{
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	struct device_node *dn = priv->pdev->dev.of_node;
-	struct phy_device *phydev;
-	u32 phy_flags = 0;
-	int ret;
-
-	/* Communicate the integrated PHY revision */
-	if (priv->internal_phy)
-		phy_flags = priv->gphy_rev;
-
-	/* Initialize link state variables that bcmgenet_mii_setup() uses */
-	priv->old_link = -1;
-	priv->old_speed = -1;
-	priv->old_duplex = -1;
-	priv->old_pause = -1;
-
-	if (dn) {
-		phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup,
-					phy_flags, priv->phy_interface);
-		if (!phydev) {
-			pr_err("could not attach to PHY\n");
-			return -ENODEV;
-		}
-	} else {
-		phydev = dev->phydev;
-		phydev->dev_flags = phy_flags;
-
-		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
-					 priv->phy_interface);
-		if (ret) {
-			pr_err("could not attach to PHY\n");
-			return -ENODEV;
-		}
-	}
-
-	return 0;
-}
-
 int bcmgenet_mii_config(struct net_device *dev, bool init)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -221,8 +181,38 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 	const char *phy_name = NULL;
 	u32 id_mode_dis = 0;
 	u32 port_ctrl;
+	int bmcr = -1;
+	int ret;
 	u32 reg;
 
+	/* MAC clocking workaround during reset of umac state machines */
+	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+	if (reg & CMD_SW_RESET) {
+		/* An MII PHY must be isolated to prevent TXC contention */
+		if (priv->phy_interface == PHY_INTERFACE_MODE_MII) {
+			ret = phy_read(phydev, MII_BMCR);
+			if (ret >= 0) {
+				bmcr = ret;
+				ret = phy_write(phydev, MII_BMCR,
+						bmcr | BMCR_ISOLATE);
+			}
+			if (ret) {
+				netdev_err(dev, "failed to isolate PHY\n");
+				return ret;
+			}
+		}
+		/* Switch MAC clocking to RGMII generated clock */
+		bcmgenet_sys_writel(priv, PORT_MODE_EXT_GPHY, SYS_PORT_CTRL);
+		/* Ensure 5 clks with Rx disabled
+		 * followed by 5 clks with Reset asserted
+		 */
+		udelay(4);
+		reg &= ~(CMD_SW_RESET | CMD_LCL_LOOP_EN);
+		bcmgenet_umac_writel(priv, reg, UMAC_CMD);
+		/* Ensure 5 more clocks before Rx is enabled */
+		udelay(2);
+	}
+
 	priv->ext_phy = !priv->internal_phy &&
 			(priv->phy_interface != PHY_INTERFACE_MODE_MOCA);
 
@@ -254,6 +244,9 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		phy_set_max_speed(phydev, SPEED_100);
 		bcmgenet_sys_writel(priv,
 				    PORT_MODE_EXT_EPHY, SYS_PORT_CTRL);
+		/* Restore the MII PHY after isolation */
+		if (bmcr >= 0)
+			phy_write(phydev, MII_BMCR, bmcr);
 		break;
 
 	case PHY_INTERFACE_MODE_REVMII:
@@ -306,21 +299,71 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		bcmgenet_ext_writel(priv, reg, EXT_RGMII_OOB_CTRL);
 	}
 
-	if (init) {
-		linkmode_copy(phydev->advertising, phydev->supported);
+	if (init)
+		dev_info(kdev, "configuring instance for %s\n", phy_name);
 
-		/* The internal PHY has its link interrupts routed to the
-		 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
-		 * that prevents the signaling of link UP interrupts when
-		 * the link operates at 10Mbps, so fallback to polling for
-		 * those versions of GENET.
-		 */
-		if (priv->internal_phy && !GENET_IS_V5(priv))
-			phydev->irq = PHY_IGNORE_INTERRUPT;
+	return 0;
+}
 
-		dev_info(kdev, "configuring instance for %s\n", phy_name);
+int bcmgenet_mii_probe(struct net_device *dev)
+{
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device_node *dn = priv->pdev->dev.of_node;
+	struct phy_device *phydev;
+	u32 phy_flags = 0;
+	int ret;
+
+	/* Communicate the integrated PHY revision */
+	if (priv->internal_phy)
+		phy_flags = priv->gphy_rev;
+
+	/* Initialize link state variables that bcmgenet_mii_setup() uses */
+	priv->old_link = -1;
+	priv->old_speed = -1;
+	priv->old_duplex = -1;
+	priv->old_pause = -1;
+
+	if (dn) {
+		phydev = of_phy_connect(dev, priv->phy_dn, bcmgenet_mii_setup,
+					phy_flags, priv->phy_interface);
+		if (!phydev) {
+			pr_err("could not attach to PHY\n");
+			return -ENODEV;
+		}
+	} else {
+		phydev = dev->phydev;
+		phydev->dev_flags = phy_flags;
+
+		ret = phy_connect_direct(dev, phydev, bcmgenet_mii_setup,
+					 priv->phy_interface);
+		if (ret) {
+			pr_err("could not attach to PHY\n");
+			return -ENODEV;
+		}
 	}
 
+	/* Configure port multiplexer based on what the probed PHY device since
+	 * reading the 'max-speed' property determines the maximum supported
+	 * PHY speed which is needed for bcmgenet_mii_config() to configure
+	 * things appropriately.
+	 */
+	ret = bcmgenet_mii_config(dev, true);
+	if (ret) {
+		phy_disconnect(dev->phydev);
+		return ret;
+	}
+
+	linkmode_copy(phydev->advertising, phydev->supported);
+
+	/* The internal PHY has its link interrupts routed to the
+	 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
+	 * that prevents the signaling of link UP interrupts when
+	 * the link operates at 10Mbps, so fallback to polling for
+	 * those versions of GENET.
+	 */
+	if (priv->internal_phy && !GENET_IS_V5(priv))
+		dev->phydev->irq = PHY_IGNORE_INTERRUPT;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 0e5de88fd6e8..cdd7e5da4a74 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1499,7 +1499,7 @@ static int octeon_mgmt_probe(struct platform_device *pdev)
 	netdev->ethtool_ops = &octeon_mgmt_ethtool_ops;
 
 	netdev->min_mtu = 64 - OCTEON_MGMT_RX_HEADROOM;
-	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM;
+	netdev->max_mtu = 16383 - OCTEON_MGMT_RX_HEADROOM - VLAN_HLEN;
 
 	mac = of_get_mac_address(pdev->dev.of_node);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index a4dead4ab0ed..86b528d8364c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -695,10 +695,10 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->write_cmpl_support = adap->params.write_cmpl_support;
 }
 
-static void uld_attach(struct adapter *adap, unsigned int uld)
+static int uld_attach(struct adapter *adap, unsigned int uld)
 {
-	void *handle;
 	struct cxgb4_lld_info lli;
+	void *handle;
 
 	uld_init(adap, &lli);
 	uld_queue_init(adap, uld, &lli);
@@ -708,7 +708,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 		dev_warn(adap->pdev_dev,
 			 "could not attach to the %s driver, error %ld\n",
 			 adap->uld[uld].name, PTR_ERR(handle));
-		return;
+		return PTR_ERR(handle);
 	}
 
 	adap->uld[uld].handle = handle;
@@ -716,22 +716,22 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 
 	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		adap->uld[uld].state_change(handle, CXGB4_STATE_UP);
+
+	return 0;
 }
 
-/**
- *	cxgb4_register_uld - register an upper-layer driver
- *	@type: the ULD type
- *	@p: the ULD methods
+/* cxgb4_register_uld - register an upper-layer driver
+ * @type: the ULD type
+ * @p: the ULD methods
  *
- *	Registers an upper-layer driver with this driver and notifies the ULD
- *	about any presently available devices that support its type.  Returns
- *	%-EBUSY if a ULD of the same type is already registered.
+ * Registers an upper-layer driver with this driver and notifies the ULD
+ * about any presently available devices that support its type.
  */
 void cxgb4_register_uld(enum cxgb4_uld type,
 			const struct cxgb4_uld_info *p)
 {
-	int ret = 0;
 	struct adapter *adap;
+	int ret = 0;
 
 	if (type >= CXGB4_ULD_MAX)
 		return;
@@ -763,8 +763,12 @@ void cxgb4_register_uld(enum cxgb4_uld type,
 		if (ret)
 			goto free_irq;
 		adap->uld[type] = *p;
-		uld_attach(adap, type);
+		ret = uld_attach(adap, type);
+		if (ret)
+			goto free_txq;
 		continue;
+free_txq:
+		release_sge_txq_uld(adap, type);
 free_irq:
 		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			quiesce_rx_uld(adap, type);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index b3da81e90132..928bfea5457b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -3791,15 +3791,11 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	 * write the CIDX Updates into the Status Page at the end of the
 	 * TX Queue.
 	 */
-	c.autoequiqe_to_viid = htonl((dbqt
-				      ? FW_EQ_ETH_CMD_AUTOEQUIQE_F
-				      : FW_EQ_ETH_CMD_AUTOEQUEQE_F) |
+	c.autoequiqe_to_viid = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
 				     FW_EQ_ETH_CMD_VIID_V(pi->viid));
 
 	c.fetchszm_to_iqid =
-		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt
-						 ? HOSTFCMODE_INGRESS_QUEUE_X
-						 : HOSTFCMODE_STATUS_PAGE_X) |
+		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
 		      FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid));
 
diff --git a/drivers/net/ethernet/cortina/gemini.h b/drivers/net/ethernet/cortina/gemini.h
index 0b12f89bf89a..9fdf77d5eb37 100644
--- a/drivers/net/ethernet/cortina/gemini.h
+++ b/drivers/net/ethernet/cortina/gemini.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /* Register definitions for Gemini GMAC Ethernet device driver
  *
  * Copyright (C) 2006 Storlink, Corp.
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 9b7af94a40bb..96e9565f1e08 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -727,6 +727,18 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	 */
 	nfrags = skb_shinfo(skb)->nr_frags;
 
+	/* Setup HW checksumming */
+	csum_vlan = 0;
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
+		goto drop;
+
+	/* Add VLAN tag */
+	if (skb_vlan_tag_present(skb)) {
+		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
+		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
+	}
+
 	/* Get header len */
 	len = skb_headlen(skb);
 
@@ -753,19 +765,6 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
 	if (nfrags == 0)
 		f_ctl_stat |= FTGMAC100_TXDES0_LTS;
 	txdes->txdes3 = cpu_to_le32(map);
-
-	/* Setup HW checksumming */
-	csum_vlan = 0;
-	if (skb->ip_summed == CHECKSUM_PARTIAL &&
-	    !ftgmac100_prep_tx_csum(skb, &csum_vlan))
-		goto drop;
-
-	/* Add VLAN tag */
-	if (skb_vlan_tag_present(skb)) {
-		csum_vlan |= FTGMAC100_TXDES1_INS_VLANTAG;
-		csum_vlan |= skb_vlan_tag_get(skb) & 0xffff;
-	}
-
 	txdes->txdes1 = cpu_to_le32(csum_vlan);
 
 	/* Next descriptor */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h
index ff2e177395d4..df2458a5e9ef 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2018 NXP
  */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
index 720cd50f5895..4ac05bfef338 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc-cmd.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2013-2016 Freescale Semiconductor Inc.
  * Copyright 2016-2018 NXP
diff --git a/drivers/net/ethernet/freescale/dpaa2/dprtc.h b/drivers/net/ethernet/freescale/dpaa2/dprtc.h
index be7914c1634d..311c184e1aef 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dprtc.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dprtc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright 2013-2016 Freescale Semiconductor Inc.
  * Copyright 2016-2018 NXP
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index d4d4c72adf49..a9c386b63581 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3558,7 +3558,7 @@ fec_probe(struct platform_device *pdev)
 
 	for (i = 0; i < irq_cnt; i++) {
 		snprintf(irq_name, sizeof(irq_name), "int%d", i);
-		irq = platform_get_irq_byname(pdev, irq_name);
+		irq = platform_get_irq_byname_optional(pdev, irq_name);
 		if (irq < 0)
 			irq = platform_get_irq(pdev, i);
 		if (irq < 0) {
@@ -3645,6 +3645,8 @@ fec_drv_remove(struct platform_device *pdev)
 		regulator_disable(fep->reg_phy);
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
+	clk_disable_unprepare(fep->clk_ahb);
+	clk_disable_unprepare(fep->clk_ipg);
 	if (of_phy_is_fixed_link(np))
 		of_phy_deregister_fixed_link(np);
 	of_node_put(fep->phy_node);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 19e2365be7d8..945643c02615 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -600,9 +600,9 @@ void fec_ptp_init(struct platform_device *pdev, int irq_idx)
 
 	INIT_DELAYED_WORK(&fep->time_keep, fec_time_keep);
 
-	irq = platform_get_irq_byname(pdev, "pps");
+	irq = platform_get_irq_byname_optional(pdev, "pps");
 	if (irq < 0)
-		irq = platform_get_irq(pdev, irq_idx);
+		irq = platform_get_irq_optional(pdev, irq_idx);
 	/* Failure to get an irq is not fatal,
 	 * only the PTP_CLOCK_PPS clock events should stop
 	 */
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 59564ac99d2a..edec61dfc868 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -289,6 +289,8 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
 
 	len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
 	page_info = &rx->data.page_info[idx];
+	dma_sync_single_for_cpu(&priv->pdev->dev, rx->data.qpl->page_buses[idx],
+				PAGE_SIZE, DMA_FROM_DEVICE);
 
 	/* gvnic can only receive into registered segments. If the buffer
 	 * can't be recycled, our only choice is to copy the data out of
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 778b87b5a06c..0a9a7ee2a866 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -390,7 +390,21 @@ static void gve_tx_fill_seg_desc(union gve_tx_desc *seg_desc,
 	seg_desc->seg.seg_addr = cpu_to_be64(addr);
 }
 
-static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
+static void gve_dma_sync_for_device(struct device *dev, dma_addr_t *page_buses,
+				    u64 iov_offset, u64 iov_len)
+{
+	dma_addr_t dma;
+	u64 addr;
+
+	for (addr = iov_offset; addr < iov_offset + iov_len;
+	     addr += PAGE_SIZE) {
+		dma = page_buses[addr / PAGE_SIZE];
+		dma_sync_single_for_device(dev, dma, PAGE_SIZE, DMA_TO_DEVICE);
+	}
+}
+
+static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb,
+			  struct device *dev)
 {
 	int pad_bytes, hlen, hdr_nfrags, payload_nfrags, l4_hdr_offset;
 	union gve_tx_desc *pkt_desc, *seg_desc;
@@ -432,6 +446,9 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
 	skb_copy_bits(skb, 0,
 		      tx->tx_fifo.base + info->iov[hdr_nfrags - 1].iov_offset,
 		      hlen);
+	gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses,
+				info->iov[hdr_nfrags - 1].iov_offset,
+				info->iov[hdr_nfrags - 1].iov_len);
 	copy_offset = hlen;
 
 	for (i = payload_iov; i < payload_nfrags + payload_iov; i++) {
@@ -445,6 +462,9 @@ static int gve_tx_add_skb(struct gve_tx_ring *tx, struct sk_buff *skb)
 		skb_copy_bits(skb, copy_offset,
 			      tx->tx_fifo.base + info->iov[i].iov_offset,
 			      info->iov[i].iov_len);
+		gve_dma_sync_for_device(dev, tx->tx_fifo.qpl->page_buses,
+					info->iov[i].iov_offset,
+					info->iov[i].iov_len);
 		copy_offset += info->iov[i].iov_len;
 	}
 
@@ -473,7 +493,7 @@ netdev_tx_t gve_tx(struct sk_buff *skb, struct net_device *dev)
 		gve_tx_put_doorbell(priv, tx->q_resources, tx->req);
 		return NETDEV_TX_BUSY;
 	}
-	nsegs = gve_tx_add_skb(tx, skb);
+	nsegs = gve_tx_add_skb(tx, skb, &priv->pdev->dev);
 
 	netdev_tx_sent_queue(tx->netdev_txq, skb->len);
 	skb_tx_timestamp(skb);
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index c84167447abe..4606a7e4a6d1 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -237,6 +237,7 @@ struct hip04_priv {
 	dma_addr_t rx_phys[RX_DESC_NUM];
 	unsigned int rx_head;
 	unsigned int rx_buf_size;
+	unsigned int rx_cnt_remaining;
 
 	struct device_node *phy_node;
 	struct phy_device *phy;
@@ -575,7 +576,6 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 	struct hip04_priv *priv = container_of(napi, struct hip04_priv, napi);
 	struct net_device *ndev = priv->ndev;
 	struct net_device_stats *stats = &ndev->stats;
-	unsigned int cnt = hip04_recv_cnt(priv);
 	struct rx_desc *desc;
 	struct sk_buff *skb;
 	unsigned char *buf;
@@ -588,8 +588,8 @@ static int hip04_rx_poll(struct napi_struct *napi, int budget)
 
 	/* clean up tx descriptors */
 	tx_remaining = hip04_tx_reclaim(ndev, false);
-
-	while (cnt && !last) {
+	priv->rx_cnt_remaining += hip04_recv_cnt(priv);
+	while (priv->rx_cnt_remaining && !last) {
 		buf = priv->rx_buf[priv->rx_head];
 		skb = build_skb(buf, priv->rx_buf_size);
 		if (unlikely(!skb)) {
@@ -635,11 +635,13 @@ refill:
 		hip04_set_recv_desc(priv, phys);
 
 		priv->rx_head = RX_NEXT(priv->rx_head);
-		if (rx >= budget)
+		if (rx >= budget) {
+			--priv->rx_cnt_remaining;
 			goto done;
+		}
 
-		if (--cnt == 0)
-			cnt = hip04_recv_cnt(priv);
+		if (--priv->rx_cnt_remaining == 0)
+			priv->rx_cnt_remaining += hip04_recv_cnt(priv);
 	}
 
 	if (!(priv->reg_inten & RCV_INT)) {
@@ -724,6 +726,7 @@ static int hip04_mac_open(struct net_device *ndev)
 	int i;
 
 	priv->rx_head = 0;
+	priv->rx_cnt_remaining = 0;
 	priv->tx_head = 0;
 	priv->tx_tail = 0;
 	hip04_reset_ppe(priv);
@@ -1038,7 +1041,6 @@ static int hip04_remove(struct platform_device *pdev)
 
 	hip04_free_ring(ndev, d);
 	unregister_netdev(ndev);
-	free_irq(ndev->irq, ndev);
 	of_node_put(priv->phy_node);
 	cancel_work_sync(&priv->tx_timeout_task);
 	free_netdev(ndev);
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 6d0457eb4faa..08339278c722 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -199,7 +199,6 @@ hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags)
 
 	ring->q = q;
 	ring->flags = flags;
-	spin_lock_init(&ring->lock);
 	ring->coal_param = q->handle->coal_param;
 	assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr);
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index e9c67c06bfd2..6ab9458302e1 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -274,9 +274,6 @@ struct hnae_ring {
 	/* statistic */
 	struct ring_stats stats;
 
-	/* ring lock for poll one */
-	spinlock_t lock;
-
 	dma_addr_t desc_dma_addr;
 	u32 buf_size;       /* size for hnae_desc->addr, preset by AE */
 	u16 desc_num;       /* total number of desc */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index a48396dd4ebb..14ab20491fd0 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -943,15 +943,6 @@ static int is_valid_clean_head(struct hnae_ring *ring, int h)
 	return u > c ? (h > c && h <= u) : (h > c || h <= u);
 }
 
-/* netif_tx_lock will turn down the performance, set only when necessary */
-#ifdef CONFIG_NET_POLL_CONTROLLER
-#define NETIF_TX_LOCK(ring) spin_lock(&(ring)->lock)
-#define NETIF_TX_UNLOCK(ring) spin_unlock(&(ring)->lock)
-#else
-#define NETIF_TX_LOCK(ring)
-#define NETIF_TX_UNLOCK(ring)
-#endif
-
 /* reclaim all desc in one budget
  * return error or number of desc left
  */
@@ -965,21 +956,16 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = readl_relaxed(ring->io_base + RCB_REG_HEAD);
 	rmb(); /* make sure head is ready before touch any data */
 
-	if (is_ring_empty(ring) || head == ring->next_to_clean) {
-		NETIF_TX_UNLOCK(ring);
+	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return 0; /* no data to poll */
-	}
 
 	if (!is_valid_clean_head(ring, head)) {
 		netdev_err(ndev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 		ring->stats.io_err_cnt++;
-		NETIF_TX_UNLOCK(ring);
 		return -EIO;
 	}
 
@@ -994,8 +980,6 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 	ring->stats.tx_pkts += pkts;
 	ring->stats.tx_bytes += bytes;
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_completed_queue(dev_queue, pkts, bytes);
 
@@ -1055,16 +1039,12 @@ static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data)
 	int head;
 	int bytes, pkts;
 
-	NETIF_TX_LOCK(ring);
-
 	head = ring->next_to_use; /* ntu :soft setted ring position*/
 	bytes = 0;
 	pkts = 0;
 	while (head != ring->next_to_clean)
 		hns_nic_reclaim_one_desc(ring, &bytes, &pkts);
 
-	NETIF_TX_UNLOCK(ring);
-
 	dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index);
 	netdev_tx_reset_queue(dev_queue);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 75ccc1e7076b..a0998937727d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNAE3_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 2110fa3b4479..5d468ed404a6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNS3_ENET_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 4821fe08b5e4..1426eb5ddf3d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_CMD_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
index 278f21e02736..b04702e65689 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_DCB_H__
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e02e01bd9eff..16f7d0e15b4f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3587,12 +3587,28 @@ static int hclge_set_rst_done(struct hclge_dev *hdev)
 {
 	struct hclge_pf_rst_done_cmd *req;
 	struct hclge_desc desc;
+	int ret;
 
 	req = (struct hclge_pf_rst_done_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PF_RST_DONE, false);
 	req->pf_rst_done |= HCLGE_PF_RESET_DONE_BIT;
 
-	return hclge_cmd_send(&hdev->hw, &desc, 1);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	/* To be compatible with the old firmware, which does not support
+	 * command HCLGE_OPC_PF_RST_DONE, just print a warning and
+	 * return success
+	 */
+	if (ret == -EOPNOTSUPP) {
+		dev_warn(&hdev->pdev->dev,
+			 "current firmware does not support command(0x%x)!\n",
+			 HCLGE_OPC_PF_RST_DONE);
+		return 0;
+	} else if (ret) {
+		dev_err(&hdev->pdev->dev, "assert PF reset done fail %d!\n",
+			ret);
+	}
+
+	return ret;
 }
 
 static int hclge_reset_prepare_up(struct hclge_dev *hdev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index c3d56b872ed7..59b824347ba4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MAIN_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index ef095d9c566f..dd9a1218a7b0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MDIO_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 818610988d34..260f22d19d81 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0+
+/* SPDX-License-Identifier: GPL-2.0+ */
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_TM_H
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 71d3d8854d8f..be56e631d693 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -607,6 +607,7 @@ static int e1000_set_ringparam(struct net_device *netdev,
 	for (i = 0; i < adapter->num_rx_queues; i++)
 		rxdr[i].count = rxdr->count;
 
+	err = 0;
 	if (netif_running(adapter->netdev)) {
 		/* Try to get new resources before deleting old */
 		err = e1000_setup_all_rx_resources(adapter);
@@ -627,14 +628,13 @@ static int e1000_set_ringparam(struct net_device *netdev,
 		adapter->rx_ring = rxdr;
 		adapter->tx_ring = txdr;
 		err = e1000_up(adapter);
-		if (err)
-			goto err_setup;
 	}
 	kfree(tx_old);
 	kfree(rx_old);
 
 	clear_bit(__E1000_RESETTING, &adapter->flags);
-	return 0;
+	return err;
+
 err_setup_tx:
 	e1000_free_all_rx_resources(adapter);
 err_setup_rx:
@@ -646,7 +646,6 @@ err_alloc_rx:
 err_alloc_tx:
 	if (netif_running(adapter->netdev))
 		e1000_up(adapter);
-err_setup:
 	clear_bit(__E1000_RESETTING, &adapter->flags);
 	return err;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 530613f31527..69a2daaca5c5 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -20,6 +20,8 @@
 
 /* API version 1.7 implements additional link and PHY-specific APIs  */
 #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+/* API version 1.9 for X722 implements additional link and PHY-specific APIs */
+#define I40E_MINOR_VER_GET_LINK_INFO_X722 0x0009
 /* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */
 #define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index d37c6e0e5f08..7560f06768e0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1876,7 +1876,8 @@ i40e_status i40e_aq_get_link_info(struct i40e_hw *hw,
 	     hw->aq.fw_min_ver < 40)) && hw_link_info->phy_type == 0xE)
 		hw_link_info->phy_type = I40E_PHY_TYPE_10GBASE_SFPP_CU;
 
-	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE) {
+	if (hw->flags & I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE &&
+	    hw->mac.type != I40E_MAC_X722) {
 		__le32 tmp;
 
 		memcpy(&tmp, resp->link_type, sizeof(tmp));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index b1c3227ae4ab..d07e1a890428 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -157,11 +157,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
-
-		/* Kick start the NAPI context so that receiving will start */
-		err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX);
-		if (err)
-			return err;
 	}
 
 	return 0;
@@ -694,8 +689,6 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget)
 		i40e_xdp_ring_update_tail(xdp_ring);
 
 		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
-		if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
-			xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem);
 	}
 
 	return !!budget && work_done;
@@ -774,12 +767,8 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi,
 	i40e_update_tx_stats(tx_ring, completed_frames, total_bytes);
 
 out_xmit:
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) {
-		if (tx_ring->next_to_clean == tx_ring->next_to_use)
-			xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
-		else
-			xsk_clear_tx_need_wakeup(tx_ring->xsk_umem);
-	}
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
 
 	xmit_done = i40e_xmit_zc(tx_ring, budget);
 
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 8f310e520b06..821987da5698 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -314,7 +314,7 @@ iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx)
 	q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting);
 	q_vector->ring_mask |= BIT(r_idx);
 	wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx),
-	     q_vector->rx.current_itr);
+	     q_vector->rx.current_itr >> 1);
 	q_vector->rx.current_itr = q_vector->rx.target_itr;
 }
 
@@ -340,7 +340,7 @@ iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx)
 	q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting);
 	q_vector->num_ringpairs++;
 	wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx),
-	     q_vector->tx.target_itr);
+	     q_vector->tx.target_itr >> 1);
 	q_vector->tx.current_itr = q_vector->tx.target_itr;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index fc624b73d05d..2fde9653a608 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -1036,7 +1036,7 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw)
 	struct ice_aqc_query_txsched_res_resp *buf;
 	enum ice_status status = 0;
 	__le16 max_sibl;
-	u8 i;
+	u16 i;
 
 	if (hw->layer_info)
 		return status;
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 3ec2ce0725d5..8a6ef3514129 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -466,7 +466,7 @@ static s32 igb_init_mac_params_82575(struct e1000_hw *hw)
 			? igb_setup_copper_link_82575
 			: igb_setup_serdes_link_82575;
 
-	if (mac->type == e1000_82580) {
+	if (mac->type == e1000_82580 || mac->type == e1000_i350) {
 		switch (hw->device_id) {
 		/* feature not supported on these id's */
 		case E1000_DEV_ID_DH89XXCC_SGMII:
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 105b0624081a..ed7e667d7eb2 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -753,7 +753,8 @@ u32 igb_rd32(struct e1000_hw *hw, u32 reg)
 		struct net_device *netdev = igb->netdev;
 		hw->hw_addr = NULL;
 		netdev_err(netdev, "PCIe link lost\n");
-		WARN(1, "igb: Failed to read reg 0x%x!\n", reg);
+		WARN(pci_device_is_present(igb->pdev),
+		     "igb: Failed to read reg 0x%x!\n", reg);
 	}
 
 	return value;
@@ -2064,7 +2065,8 @@ static void igb_check_swap_media(struct igb_adapter *adapter)
 	if ((hw->phy.media_type == e1000_media_type_copper) &&
 	    (!(connsw & E1000_CONNSW_AUTOSENSE_EN))) {
 		swap_now = true;
-	} else if (!(connsw & E1000_CONNSW_SERDESD)) {
+	} else if ((hw->phy.media_type != e1000_media_type_copper) &&
+		   !(connsw & E1000_CONNSW_SERDESD)) {
 		/* copper signal takes time to appear */
 		if (adapter->copper_tries < 4) {
 			adapter->copper_tries++;
@@ -2370,7 +2372,7 @@ void igb_reset(struct igb_adapter *adapter)
 		adapter->ei.get_invariants(hw);
 		adapter->flags &= ~IGB_FLAG_MEDIA_RESET;
 	}
-	if ((mac->type == e1000_82575) &&
+	if ((mac->type == e1000_82575 || mac->type == e1000_i350) &&
 	    (adapter->flags & IGB_FLAG_MAS_ENABLE)) {
 		igb_enable_mas(adapter);
 	}
@@ -5673,8 +5675,8 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
 	 * should have been handled by the upper layers.
 	 */
 	if (tx_ring->launchtime_enable) {
-		ts = ns_to_timespec64(first->skb->tstamp);
-		first->skb->tstamp = 0;
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		first->skb->tstamp = ktime_set(0, 0);
 		context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
 	} else {
 		context_desc->seqnum_seed = 0;
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 63b62d74f961..24888676f69b 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -824,8 +824,8 @@ static void igc_tx_ctxtdesc(struct igc_ring *tx_ring,
 	 * should have been handled by the upper layers.
 	 */
 	if (tx_ring->launchtime_enable) {
-		ts = ns_to_timespec64(first->skb->tstamp);
-		first->skb->tstamp = 0;
+		ts = ktime_to_timespec64(first->skb->tstamp);
+		first->skb->tstamp = ktime_set(0, 0);
 		context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32);
 	} else {
 		context_desc->launch_time = 0;
@@ -4047,7 +4047,8 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 		hw->hw_addr = NULL;
 		netif_device_detach(netdev);
 		netdev_err(netdev, "PCIe link lost, device now detached\n");
-		WARN(1, "igc: Failed to read reg 0x%x!\n", reg);
+		WARN(pci_device_is_present(igc->pdev),
+		     "igc: Failed to read reg 0x%x!\n", reg);
 	}
 
 	return value;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 1ce2397306b9..91b3780ddb04 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4310,7 +4310,6 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter)
 		if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state))
 			set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state);
 
-		clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state);
 		if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY)
 			continue;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 100ac89b345d..d6feaacfbf89 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -622,8 +622,6 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	if (tx_desc) {
 		ixgbe_xdp_ring_update_tail(xdp_ring);
 		xsk_umem_consume_tx_done(xdp_ring->xsk_umem);
-		if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem))
-			xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem);
 	}
 
 	return !!budget && work_done;
@@ -691,12 +689,8 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector,
 	if (xsk_frames)
 		xsk_umem_complete_tx(umem, xsk_frames);
 
-	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) {
-		if (tx_ring->next_to_clean == tx_ring->next_to_use)
-			xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
-		else
-			xsk_clear_tx_need_wakeup(tx_ring->xsk_umem);
-	}
+	if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem))
+		xsk_set_tx_need_wakeup(tx_ring->xsk_umem);
 
 	return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit);
 }
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h
index c8425d35c049..e47783ce77e0 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.h
+++ b/drivers/net/ethernet/marvell/mvneta_bm.h
@@ -160,16 +160,23 @@ static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
 			     (bm_pool->id << MVNETA_BM_POOL_ACCESS_OFFS));
 }
 #else
-void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
-			    struct mvneta_bm_pool *bm_pool, u8 port_map) {}
-void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
-			 u8 port_map) {}
-int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf) { return 0; }
-int mvneta_bm_pool_refill(struct mvneta_bm *priv,
-			  struct mvneta_bm_pool *bm_pool) {return 0; }
-struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv, u8 pool_id,
-					  enum mvneta_bm_type type, u8 port_id,
-					  int pkt_size) { return NULL; }
+static inline void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
+					  struct mvneta_bm_pool *bm_pool,
+					  u8 port_map) {}
+static inline void mvneta_bm_bufs_free(struct mvneta_bm *priv,
+				       struct mvneta_bm_pool *bm_pool,
+				       u8 port_map) {}
+static inline int mvneta_bm_construct(struct hwbm_pool *hwbm_pool, void *buf)
+{ return 0; }
+static inline int mvneta_bm_pool_refill(struct mvneta_bm *priv,
+					struct mvneta_bm_pool *bm_pool)
+{ return 0; }
+static inline struct mvneta_bm_pool *mvneta_bm_pool_use(struct mvneta_bm *priv,
+							u8 pool_id,
+							enum mvneta_bm_type type,
+							u8 port_id,
+							int pkt_size)
+{ return NULL; }
 
 static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
 					 struct mvneta_bm_pool *bm_pool,
@@ -178,7 +185,8 @@ static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
 static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
 					struct mvneta_bm_pool *bm_pool)
 { return 0; }
-struct mvneta_bm *mvneta_bm_get(struct device_node *node) { return NULL; }
-void mvneta_bm_put(struct mvneta_bm *priv) {}
+static inline struct mvneta_bm *mvneta_bm_get(struct device_node *node)
+{ return NULL; }
+static inline void mvneta_bm_put(struct mvneta_bm *priv) {}
 #endif /* CONFIG_MVNETA_BM */
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index fce9b3a24347..69bb6bb06e76 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -514,8 +514,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rq_desc_sz     = dev_cap->max_rq_desc_sz;
 	/*
 	 * Subtract 1 from the limit because we need to allocate a
-	 * spare CQE so the HCA HW can tell the difference between an
-	 * empty CQ and a full CQ.
+	 * spare CQE to enable resizing the CQ.
 	 */
 	dev->caps.max_cqes	     = dev_cap->max_cq_sz - 1;
 	dev->caps.reserved_cqs	     = dev_cap->reserved_cqs;
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 4356f3a58002..1187ef1375e2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -471,12 +471,31 @@ void mlx4_init_quotas(struct mlx4_dev *dev)
 		priv->mfunc.master.res_tracker.res_alloc[RES_MPT].quota[pf];
 }
 
-static int get_max_gauranteed_vfs_counter(struct mlx4_dev *dev)
+static int
+mlx4_calc_res_counter_guaranteed(struct mlx4_dev *dev,
+				 struct resource_allocator *res_alloc,
+				 int vf)
 {
-	/* reduce the sink counter */
-	return (dev->caps.max_counters - 1 -
-		(MLX4_PF_COUNTERS_PER_PORT * MLX4_MAX_PORTS))
-		/ MLX4_MAX_PORTS;
+	struct mlx4_active_ports actv_ports;
+	int ports, counters_guaranteed;
+
+	/* For master, only allocate according to the number of phys ports */
+	if (vf == mlx4_master_func_num(dev))
+		return MLX4_PF_COUNTERS_PER_PORT * dev->caps.num_ports;
+
+	/* calculate real number of ports for the VF */
+	actv_ports = mlx4_get_active_ports(dev, vf);
+	ports = bitmap_weight(actv_ports.ports, dev->caps.num_ports);
+	counters_guaranteed = ports * MLX4_VF_COUNTERS_PER_PORT;
+
+	/* If we do not have enough counters for this VF, do not
+	 * allocate any for it. '-1' to reduce the sink counter.
+	 */
+	if ((res_alloc->res_reserved + counters_guaranteed) >
+	    (dev->caps.max_counters - 1))
+		return 0;
+
+	return counters_guaranteed;
 }
 
 int mlx4_init_resource_tracker(struct mlx4_dev *dev)
@@ -484,7 +503,6 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i, j;
 	int t;
-	int max_vfs_guarantee_counter = get_max_gauranteed_vfs_counter(dev);
 
 	priv->mfunc.master.res_tracker.slave_list =
 		kcalloc(dev->num_slaves, sizeof(struct slave_list),
@@ -603,16 +621,8 @@ int mlx4_init_resource_tracker(struct mlx4_dev *dev)
 				break;
 			case RES_COUNTER:
 				res_alloc->quota[t] = dev->caps.max_counters;
-				if (t == mlx4_master_func_num(dev))
-					res_alloc->guaranteed[t] =
-						MLX4_PF_COUNTERS_PER_PORT *
-						MLX4_MAX_PORTS;
-				else if (t <= max_vfs_guarantee_counter)
-					res_alloc->guaranteed[t] =
-						MLX4_VF_COUNTERS_PER_PORT *
-						MLX4_MAX_PORTS;
-				else
-					res_alloc->guaranteed[t] = 0;
+				res_alloc->guaranteed[t] =
+					mlx4_calc_res_counter_guaranteed(dev, res_alloc, t);
 				break;
 			default:
 				break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8d76452cacdc..f1a7bc46f1c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -345,7 +345,7 @@ struct mlx5e_tx_wqe_info {
 	u8  num_wqebbs;
 	u8  num_dma;
 #ifdef CONFIG_MLX5_EN_TLS
-	skb_frag_t *resync_dump_frag;
+	struct page *resync_dump_frag_page;
 #endif
 };
 
@@ -410,6 +410,7 @@ struct mlx5e_txqsq {
 	struct device             *pdev;
 	__be32                     mkey_be;
 	unsigned long              state;
+	unsigned int               hw_mtu;
 	struct hwtstamp_config    *tstamp;
 	struct mlx5_clock         *clock;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
index b3a249b2a482..ac44bbe95c5c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c
@@ -141,7 +141,7 @@ int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv)
 				    "Failed to create hv vhca stats agent, err = %ld\n",
 				    PTR_ERR(agent));
 
-		kfree(priv->stats_agent.buf);
+		kvfree(priv->stats_agent.buf);
 		return IS_ERR_OR_NULL(agent);
 	}
 
@@ -157,5 +157,5 @@ void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv)
 		return;
 
 	mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent);
-	kfree(priv->stats_agent.buf);
+	kvfree(priv->stats_agent.buf);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index f8ee18b4da6f..13af72556987 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -97,15 +97,19 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	if (ret)
 		return ret;
 
-	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET)
+	if (mlx5_lag_is_multipath(mdev) && rt->rt_gw_family != AF_INET) {
+		ip_rt_put(rt);
 		return -ENETUNREACH;
+	}
 #else
 	return -EOPNOTSUPP;
 #endif
 
 	ret = get_route_and_out_devs(priv, rt->dst.dev, route_dev, out_dev);
-	if (ret < 0)
+	if (ret < 0) {
+		ip_rt_put(rt);
 		return ret;
+	}
 
 	if (!(*out_ttl))
 		*out_ttl = ip4_dst_hoplimit(&rt->dst);
@@ -149,8 +153,10 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 		*out_ttl = ip6_dst_hoplimit(dst);
 
 	ret = get_route_and_out_devs(priv, dst->dev, route_dev, out_dev);
-	if (ret < 0)
+	if (ret < 0) {
+		dst_release(dst);
 		return ret;
+	}
 #else
 	return -EOPNOTSUPP;
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 87be96747902..7c8796d9743f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -15,15 +15,14 @@
 #else
 /* TLS offload requires additional stop_room for:
  *  - a resync SKB.
- * kTLS offload requires additional stop_room for:
- * - static params WQE,
- * - progress params WQE, and
- * - resync DUMP per frag.
+ * kTLS offload requires fixed additional stop_room for:
+ * - a static params WQE, and a progress params WQE.
+ * The additional MTU-depending room for the resync DUMP WQEs
+ * will be calculated and added in runtime.
  */
 #define MLX5E_SQ_TLS_ROOM  \
 	(MLX5_SEND_WQE_MAX_WQEBBS + \
-	 MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS + \
-	 MAX_SKB_FRAGS * MLX5E_KTLS_MAX_DUMP_WQEBBS)
+	 MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS)
 #endif
 
 #define INL_HDR_START_SZ (sizeof(((struct mlx5_wqe_eth_seg *)NULL)->inline_hdr.start))
@@ -92,7 +91,7 @@ mlx5e_fill_sq_frag_edge(struct mlx5e_txqsq *sq, struct mlx5_wq_cyc *wq,
 
 	/* fill sq frag edge with nops to avoid wqe wrapping two pages */
 	for (; wi < edge_wi; wi++) {
-		wi->skb        = NULL;
+		memset(wi, 0, sizeof(*wi));
 		wi->num_wqebbs = 1;
 		mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
index d2ff74d52720..46725cd743a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.c
@@ -38,7 +38,7 @@ static int mlx5e_ktls_add(struct net_device *netdev, struct sock *sk,
 		return -ENOMEM;
 
 	tx_priv->expected_seq = start_offload_tcp_sn;
-	tx_priv->crypto_info  = crypto_info;
+	tx_priv->crypto_info  = *(struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 	mlx5e_set_ktls_tx_priv_ctx(tls_ctx, tx_priv);
 
 	/* tc and underlay_qpn values are not in use for tls tis */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index b7298f9ee3d3..a3efa29a4629 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -21,7 +21,14 @@
 	 MLX5_ST_SZ_BYTES(tls_progress_params))
 #define MLX5E_KTLS_PROGRESS_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB))
-#define MLX5E_KTLS_MAX_DUMP_WQEBBS 2
+
+struct mlx5e_dump_wqe {
+	struct mlx5_wqe_ctrl_seg ctrl;
+	struct mlx5_wqe_data_seg data;
+};
+
+#define MLX5E_KTLS_DUMP_WQEBBS \
+	(DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB))
 
 enum {
 	MLX5E_TLS_PROGRESS_PARAMS_AUTH_STATE_NO_OFFLOAD     = 0,
@@ -37,7 +44,7 @@ enum {
 
 struct mlx5e_ktls_offload_context_tx {
 	struct tls_offload_context_tx *tx_ctx;
-	struct tls_crypto_info *crypto_info;
+	struct tls12_crypto_info_aes_gcm_128 crypto_info;
 	u32 expected_seq;
 	u32 tisn;
 	u32 key_id;
@@ -86,14 +93,28 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 					 struct mlx5e_tx_wqe **wqe, u16 *pi);
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
-					   struct mlx5e_sq_dma *dma);
-
+					   u32 *dma_fifo_cc);
+static inline u8
+mlx5e_ktls_dumps_num_wqebbs(struct mlx5e_txqsq *sq, unsigned int nfrags,
+			    unsigned int sync_len)
+{
+	/* Given the MTU and sync_len, calculates an upper bound for the
+	 * number of WQEBBs needed for the TX resync DUMP WQEs of a record.
+	 */
+	return MLX5E_KTLS_DUMP_WQEBBS *
+		(nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu));
+}
 #else
 
 static inline void mlx5e_ktls_build_netdev(struct mlx5e_priv *priv)
 {
 }
 
+static inline void
+mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
+				      struct mlx5e_tx_wqe_info *wi,
+				      u32 *dma_fifo_cc) {}
+
 #endif
 
 #endif /* __MLX5E_TLS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index d195366461c9..778dab1af8fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -24,17 +24,12 @@ enum {
 static void
 fill_static_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
 {
-	struct tls_crypto_info *crypto_info = priv_tx->crypto_info;
-	struct tls12_crypto_info_aes_gcm_128 *info;
+	struct tls12_crypto_info_aes_gcm_128 *info = &priv_tx->crypto_info;
 	char *initial_rn, *gcm_iv;
 	u16 salt_sz, rec_seq_sz;
 	char *salt, *rec_seq;
 	u8 tls_version;
 
-	if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128))
-		return;
-
-	info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 	EXTRACT_INFO_FIELDS;
 
 	gcm_iv      = MLX5_ADDR_OF(tls_static_params, ctx, gcm_iv);
@@ -108,16 +103,15 @@ build_progress_params(struct mlx5e_tx_wqe *wqe, u16 pc, u32 sqn,
 }
 
 static void tx_fill_wi(struct mlx5e_txqsq *sq,
-		       u16 pi, u8 num_wqebbs,
-		       skb_frag_t *resync_dump_frag,
-		       u32 num_bytes)
+		       u16 pi, u8 num_wqebbs, u32 num_bytes,
+		       struct page *page)
 {
 	struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi];
 
-	wi->skb              = NULL;
-	wi->num_wqebbs       = num_wqebbs;
-	wi->resync_dump_frag = resync_dump_frag;
-	wi->num_bytes        = num_bytes;
+	memset(wi, 0, sizeof(*wi));
+	wi->num_wqebbs = num_wqebbs;
+	wi->num_bytes  = num_bytes;
+	wi->resync_dump_frag_page = page;
 }
 
 void mlx5e_ktls_tx_offload_set_pending(struct mlx5e_ktls_offload_context_tx *priv_tx)
@@ -145,7 +139,7 @@ post_static_params(struct mlx5e_txqsq *sq,
 
 	umr_wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_STATIC_UMR_WQE_SZ, &pi);
 	build_static_params(umr_wqe, sq->pc, sq->sqn, priv_tx, fence);
-	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, NULL, 0);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_STATIC_WQEBBS, 0, NULL);
 	sq->pc += MLX5E_KTLS_STATIC_WQEBBS;
 }
 
@@ -159,7 +153,7 @@ post_progress_params(struct mlx5e_txqsq *sq,
 
 	wqe = mlx5e_sq_fetch_wqe(sq, MLX5E_KTLS_PROGRESS_WQE_SZ, &pi);
 	build_progress_params(wqe, sq->pc, sq->sqn, priv_tx, fence);
-	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, NULL, 0);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_PROGRESS_WQEBBS, 0, NULL);
 	sq->pc += MLX5E_KTLS_PROGRESS_WQEBBS;
 }
 
@@ -169,6 +163,14 @@ mlx5e_ktls_tx_post_param_wqes(struct mlx5e_txqsq *sq,
 			      bool skip_static_post, bool fence_first_post)
 {
 	bool progress_fence = skip_static_post || !fence_first_post;
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 contig_wqebbs_room, pi;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	if (unlikely(contig_wqebbs_room <
+		     MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS))
+		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 
 	if (!skip_static_post)
 		post_static_params(sq, priv_tx, fence_first_post);
@@ -180,29 +182,36 @@ struct tx_sync_info {
 	u64 rcd_sn;
 	s32 sync_len;
 	int nr_frags;
-	skb_frag_t *frags[MAX_SKB_FRAGS];
+	skb_frag_t frags[MAX_SKB_FRAGS];
+};
+
+enum mlx5e_ktls_sync_retval {
+	MLX5E_KTLS_SYNC_DONE,
+	MLX5E_KTLS_SYNC_FAIL,
+	MLX5E_KTLS_SYNC_SKIP_NO_DATA,
 };
 
-static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
-			     u32 tcp_seq, struct tx_sync_info *info)
+static enum mlx5e_ktls_sync_retval
+tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
+		 u32 tcp_seq, struct tx_sync_info *info)
 {
 	struct tls_offload_context_tx *tx_ctx = priv_tx->tx_ctx;
+	enum mlx5e_ktls_sync_retval ret = MLX5E_KTLS_SYNC_DONE;
 	struct tls_record_info *record;
 	int remaining, i = 0;
 	unsigned long flags;
-	bool ret = true;
 
 	spin_lock_irqsave(&tx_ctx->lock, flags);
 	record = tls_get_record(tx_ctx, tcp_seq, &info->rcd_sn);
 
 	if (unlikely(!record)) {
-		ret = false;
+		ret = MLX5E_KTLS_SYNC_FAIL;
 		goto out;
 	}
 
 	if (unlikely(tcp_seq < tls_record_start_seq(record))) {
-		if (!tls_record_is_start_marker(record))
-			ret = false;
+		ret = tls_record_is_start_marker(record) ?
+			MLX5E_KTLS_SYNC_SKIP_NO_DATA : MLX5E_KTLS_SYNC_FAIL;
 		goto out;
 	}
 
@@ -211,13 +220,13 @@ static bool tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	while (remaining > 0) {
 		skb_frag_t *frag = &record->frags[i];
 
-		__skb_frag_ref(frag);
+		get_page(skb_frag_page(frag));
 		remaining -= skb_frag_size(frag);
-		info->frags[i++] = frag;
+		info->frags[i++] = *frag;
 	}
 	/* reduce the part which will be sent with the original SKB */
 	if (remaining < 0)
-		skb_frag_size_add(info->frags[i - 1], remaining);
+		skb_frag_size_add(&info->frags[i - 1], remaining);
 	info->nr_frags = i;
 out:
 	spin_unlock_irqrestore(&tx_ctx->lock, flags);
@@ -229,17 +238,12 @@ tx_post_resync_params(struct mlx5e_txqsq *sq,
 		      struct mlx5e_ktls_offload_context_tx *priv_tx,
 		      u64 rcd_sn)
 {
-	struct tls_crypto_info *crypto_info = priv_tx->crypto_info;
-	struct tls12_crypto_info_aes_gcm_128 *info;
+	struct tls12_crypto_info_aes_gcm_128 *info = &priv_tx->crypto_info;
 	__be64 rn_be = cpu_to_be64(rcd_sn);
 	bool skip_static_post;
 	u16 rec_seq_sz;
 	char *rec_seq;
 
-	if (WARN_ON(crypto_info->cipher_type != TLS_CIPHER_AES_GCM_128))
-		return;
-
-	info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info;
 	rec_seq = info->rec_seq;
 	rec_seq_sz = sizeof(info->rec_seq);
 
@@ -250,11 +254,6 @@ tx_post_resync_params(struct mlx5e_txqsq *sq,
 	mlx5e_ktls_tx_post_param_wqes(sq, priv_tx, skip_static_post, true);
 }
 
-struct mlx5e_dump_wqe {
-	struct mlx5_wqe_ctrl_seg ctrl;
-	struct mlx5_wqe_data_seg data;
-};
-
 static int
 tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool first)
 {
@@ -262,7 +261,6 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	struct mlx5_wqe_data_seg *dseg;
 	struct mlx5e_dump_wqe *wqe;
 	dma_addr_t dma_addr = 0;
-	u8  num_wqebbs;
 	u16 ds_cnt;
 	int fsz;
 	u16 pi;
@@ -270,7 +268,6 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	wqe = mlx5e_sq_fetch_wqe(sq, sizeof(*wqe), &pi);
 
 	ds_cnt = sizeof(*wqe) / MLX5_SEND_WQE_DS;
-	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 
 	cseg = &wqe->ctrl;
 	dseg = &wqe->data;
@@ -291,24 +288,27 @@ tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool fir
 	dseg->byte_count = cpu_to_be32(fsz);
 	mlx5e_dma_push(sq, dma_addr, fsz, MLX5E_DMA_MAP_PAGE);
 
-	tx_fill_wi(sq, pi, num_wqebbs, frag, fsz);
-	sq->pc += num_wqebbs;
-
-	WARN(num_wqebbs > MLX5E_KTLS_MAX_DUMP_WQEBBS,
-	     "unexpected DUMP num_wqebbs, %d > %d",
-	     num_wqebbs, MLX5E_KTLS_MAX_DUMP_WQEBBS);
+	tx_fill_wi(sq, pi, MLX5E_KTLS_DUMP_WQEBBS, fsz, skb_frag_page(frag));
+	sq->pc += MLX5E_KTLS_DUMP_WQEBBS;
 
 	return 0;
 }
 
 void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq,
 					   struct mlx5e_tx_wqe_info *wi,
-					   struct mlx5e_sq_dma *dma)
+					   u32 *dma_fifo_cc)
 {
-	struct mlx5e_sq_stats *stats = sq->stats;
+	struct mlx5e_sq_stats *stats;
+	struct mlx5e_sq_dma *dma;
+
+	if (!wi->resync_dump_frag_page)
+		return;
+
+	dma = mlx5e_dma_get(sq, (*dma_fifo_cc)++);
+	stats = sq->stats;
 
 	mlx5e_tx_dma_unmap(sq->pdev, dma);
-	__skb_frag_unref(wi->resync_dump_frag);
+	put_page(wi->resync_dump_frag_page);
 	stats->tls_dump_packets++;
 	stats->tls_dump_bytes += wi->num_bytes;
 }
@@ -318,25 +318,31 @@ static void tx_post_fence_nop(struct mlx5e_txqsq *sq)
 	struct mlx5_wq_cyc *wq = &sq->wq;
 	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
-	tx_fill_wi(sq, pi, 1, NULL, 0);
+	tx_fill_wi(sq, pi, 1, 0, NULL);
 
 	mlx5e_post_nop_fence(wq, sq->sqn, &sq->pc);
 }
 
-static struct sk_buff *
+static enum mlx5e_ktls_sync_retval
 mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 			 struct mlx5e_txqsq *sq,
-			 struct sk_buff *skb,
+			 int datalen,
 			 u32 seq)
 {
 	struct mlx5e_sq_stats *stats = sq->stats;
 	struct mlx5_wq_cyc *wq = &sq->wq;
+	enum mlx5e_ktls_sync_retval ret;
 	struct tx_sync_info info = {};
 	u16 contig_wqebbs_room, pi;
 	u8 num_wqebbs;
-	int i;
-
-	if (!tx_sync_info_get(priv_tx, seq, &info)) {
+	int i = 0;
+
+	ret = tx_sync_info_get(priv_tx, seq, &info);
+	if (unlikely(ret != MLX5E_KTLS_SYNC_DONE)) {
+		if (ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA) {
+			stats->tls_skip_no_sync_data++;
+			return MLX5E_KTLS_SYNC_SKIP_NO_DATA;
+		}
 		/* We might get here if a retransmission reaches the driver
 		 * after the relevant record is acked.
 		 * It should be safe to drop the packet in this case
@@ -346,13 +352,8 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 	}
 
 	if (unlikely(info.sync_len < 0)) {
-		u32 payload;
-		int headln;
-
-		headln = skb_transport_offset(skb) + tcp_hdrlen(skb);
-		payload = skb->len - headln;
-		if (likely(payload <= -info.sync_len))
-			return skb;
+		if (likely(datalen <= -info.sync_len))
+			return MLX5E_KTLS_SYNC_DONE;
 
 		stats->tls_drop_bypass_req++;
 		goto err_out;
@@ -360,30 +361,62 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx,
 
 	stats->tls_ooo++;
 
-	num_wqebbs = MLX5E_KTLS_STATIC_WQEBBS + MLX5E_KTLS_PROGRESS_WQEBBS +
-		(info.nr_frags ? info.nr_frags * MLX5E_KTLS_MAX_DUMP_WQEBBS : 1);
+	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
+
+	/* If no dump WQE was sent, we need to have a fence NOP WQE before the
+	 * actual data xmit.
+	 */
+	if (!info.nr_frags) {
+		tx_post_fence_nop(sq);
+		return MLX5E_KTLS_SYNC_DONE;
+	}
+
+	num_wqebbs = mlx5e_ktls_dumps_num_wqebbs(sq, info.nr_frags, info.sync_len);
 	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+
 	if (unlikely(contig_wqebbs_room < num_wqebbs))
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 
 	tx_post_resync_params(sq, priv_tx, info.rcd_sn);
 
-	for (i = 0; i < info.nr_frags; i++)
-		if (tx_post_resync_dump(sq, info.frags[i], priv_tx->tisn, !i))
-			goto err_out;
+	for (; i < info.nr_frags; i++) {
+		unsigned int orig_fsz, frag_offset = 0, n = 0;
+		skb_frag_t *f = &info.frags[i];
 
-	/* If no dump WQE was sent, we need to have a fence NOP WQE before the
-	 * actual data xmit.
-	 */
-	if (!info.nr_frags)
-		tx_post_fence_nop(sq);
+		orig_fsz = skb_frag_size(f);
 
-	return skb;
+		do {
+			bool fence = !(i || frag_offset);
+			unsigned int fsz;
+
+			n++;
+			fsz = min_t(unsigned int, sq->hw_mtu, orig_fsz - frag_offset);
+			skb_frag_size_set(f, fsz);
+			if (tx_post_resync_dump(sq, f, priv_tx->tisn, fence)) {
+				page_ref_add(skb_frag_page(f), n - 1);
+				goto err_out;
+			}
+
+			skb_frag_off_add(f, fsz);
+			frag_offset += fsz;
+		} while (frag_offset < orig_fsz);
+
+		page_ref_add(skb_frag_page(f), n - 1);
+	}
+
+	return MLX5E_KTLS_SYNC_DONE;
 
 err_out:
-	dev_kfree_skb_any(skb);
-	return NULL;
+	for (; i < info.nr_frags; i++)
+		/* The put_page() here undoes the page ref obtained in tx_sync_info_get().
+		 * Page refs obtained for the DUMP WQEs above (by page_ref_add) will be
+		 * released only upon their completions (or in mlx5e_free_txqsq_descs,
+		 * if channel closes).
+		 */
+		put_page(skb_frag_page(&info.frags[i]));
+
+	return MLX5E_KTLS_SYNC_FAIL;
 }
 
 struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
@@ -419,10 +452,15 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev,
 
 	seq = ntohl(tcp_hdr(skb)->seq);
 	if (unlikely(priv_tx->expected_seq != seq)) {
-		skb = mlx5e_ktls_tx_handle_ooo(priv_tx, sq, skb, seq);
-		if (unlikely(!skb))
+		enum mlx5e_ktls_sync_retval ret =
+			mlx5e_ktls_tx_handle_ooo(priv_tx, sq, datalen, seq);
+
+		if (likely(ret == MLX5E_KTLS_SYNC_DONE))
+			*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
+		else if (ret == MLX5E_KTLS_SYNC_FAIL)
+			goto err_out;
+		else /* ret == MLX5E_KTLS_SYNC_SKIP_NO_DATA */
 			goto out;
-		*wqe = mlx5e_sq_fetch_wqe(sq, sizeof(**wqe), pi);
 	}
 
 	priv_tx->expected_seq = seq + datalen;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index c5a9c20d7f00..327c93a7bd55 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1021,7 +1021,7 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 {
 #define MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT ETHTOOL_LINK_MODE_50000baseKR_Full_BIT
 	int size = __ETHTOOL_LINK_MODE_MASK_NBITS - MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT;
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(modes) = {0,};
 
 	bitmap_set(modes, MLX5E_MIN_PTYS_EXT_LINK_MODE_BIT, size);
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7569287f8f3c..772bfdbdeb9c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1128,6 +1128,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->txq_ix    = txq_ix;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
 	sq->stop_room = MLX5E_SQ_STOP_ROOM;
 	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
@@ -1135,10 +1136,14 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 		set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
+#ifdef CONFIG_MLX5_EN_TLS
 	if (mlx5_accel_is_tls_device(c->priv->mdev)) {
 		set_bit(MLX5E_SQ_STATE_TLS, &sq->state);
-		sq->stop_room += MLX5E_SQ_TLS_ROOM;
+		sq->stop_room += MLX5E_SQ_TLS_ROOM +
+			mlx5e_ktls_dumps_num_wqebbs(sq, MAX_SKB_FRAGS,
+						    TLS_MAX_PAYLOAD_SIZE);
 	}
+#endif
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1349,9 +1354,13 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
 		u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+		struct mlx5e_tx_wqe_info *wi;
 		struct mlx5e_tx_wqe *nop;
 
-		sq->db.wqe_info[pi].skb = NULL;
+		wi = &sq->db.wqe_info[pi];
+
+		memset(wi, 0, sizeof(*wi));
+		wi->num_wqebbs = 1;
 		nop = mlx5e_post_nop(wq, sq->sqn, &sq->pc);
 		mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nop->ctrl);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 95892a3b63a1..cd9bb7c7b341 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -611,8 +611,8 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 
 	mutex_lock(&esw->offloads.encap_tbl_lock);
 	encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID);
-	if (e->compl_result || (encap_connected == neigh_connected &&
-				ether_addr_equal(e->h_dest, ha)))
+	if (e->compl_result < 0 || (encap_connected == neigh_connected &&
+				    ether_addr_equal(e->h_dest, ha)))
 		goto unlock;
 
 	mlx5e_take_all_encap_flows(e, &flow_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d6a547238de0..82cffb3a9964 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1386,8 +1386,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return 0;
 
-	if (rq->cqd.left)
+	if (rq->cqd.left) {
 		work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget);
+		if (rq->cqd.left || work_done >= budget)
+			goto out;
+	}
 
 	cqe = mlx5_cqwq_get_cqe(cqwq);
 	if (!cqe) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 840ec945ccba..bbff8d8ded76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -35,6 +35,7 @@
 #include <linux/udp.h>
 #include <net/udp.h>
 #include "en.h"
+#include "en/port.h"
 
 enum {
 	MLX5E_ST_LINK_STATE,
@@ -80,22 +81,12 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv)
 
 static int mlx5e_test_link_speed(struct mlx5e_priv *priv)
 {
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	u32 eth_proto_oper;
-	int i;
+	u32 speed;
 
 	if (!netif_carrier_ok(priv->netdev))
 		return 1;
 
-	if (mlx5_query_port_ptys(priv->mdev, out, sizeof(out), MLX5_PTYS_EN, 1))
-		return 1;
-
-	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; i++) {
-		if (eth_proto_oper & MLX5E_PROT_MASK(i))
-			return 0;
-	}
-	return 1;
+	return mlx5e_port_linkspeed(priv->mdev, &speed);
 }
 
 struct mlx5ehdr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index ac6fdcda7019..7e6ebd0505cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -52,11 +52,12 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_encrypted_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ctx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_skip_no_sync_data) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_no_sync_data) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_drop_bypass_req) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_packets) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_dump_bytes) },
 #endif
 
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
@@ -288,11 +289,12 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_encrypted_bytes   += sq_stats->tls_encrypted_bytes;
 			s->tx_tls_ctx               += sq_stats->tls_ctx;
 			s->tx_tls_ooo               += sq_stats->tls_ooo;
+			s->tx_tls_dump_bytes        += sq_stats->tls_dump_bytes;
+			s->tx_tls_dump_packets      += sq_stats->tls_dump_packets;
 			s->tx_tls_resync_bytes      += sq_stats->tls_resync_bytes;
+			s->tx_tls_skip_no_sync_data += sq_stats->tls_skip_no_sync_data;
 			s->tx_tls_drop_no_sync_data += sq_stats->tls_drop_no_sync_data;
 			s->tx_tls_drop_bypass_req   += sq_stats->tls_drop_bypass_req;
-			s->tx_tls_dump_bytes        += sq_stats->tls_dump_bytes;
-			s->tx_tls_dump_packets      += sq_stats->tls_dump_packets;
 #endif
 			s->tx_cqes		+= sq_stats->cqes;
 		}
@@ -1472,10 +1474,12 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_encrypted_bytes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ctx) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_ooo) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) },
-	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_packets) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_dump_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_resync_bytes) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_skip_no_sync_data) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_no_sync_data) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, tls_drop_bypass_req) },
 #endif
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, csum_none) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, stopped) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 79f261bf86ac..869f3502f631 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -129,11 +129,12 @@ struct mlx5e_sw_stats {
 	u64 tx_tls_encrypted_bytes;
 	u64 tx_tls_ctx;
 	u64 tx_tls_ooo;
+	u64 tx_tls_dump_packets;
+	u64 tx_tls_dump_bytes;
 	u64 tx_tls_resync_bytes;
+	u64 tx_tls_skip_no_sync_data;
 	u64 tx_tls_drop_no_sync_data;
 	u64 tx_tls_drop_bypass_req;
-	u64 tx_tls_dump_packets;
-	u64 tx_tls_dump_bytes;
 #endif
 
 	u64 rx_xsk_packets;
@@ -273,11 +274,12 @@ struct mlx5e_sq_stats {
 	u64 tls_encrypted_bytes;
 	u64 tls_ctx;
 	u64 tls_ooo;
+	u64 tls_dump_packets;
+	u64 tls_dump_bytes;
 	u64 tls_resync_bytes;
+	u64 tls_skip_no_sync_data;
 	u64 tls_drop_no_sync_data;
 	u64 tls_drop_bypass_req;
-	u64 tls_dump_packets;
-	u64 tls_dump_bytes;
 #endif
 	/* less likely accessed in data path */
 	u64 csum_none;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3e78a727f3e6..fda0b37075e8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1278,8 +1278,10 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
 	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
-		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) {
 			mlx5e_detach_encap(priv, flow, out_index);
+			kfree(attr->parse_attr->tun_info[out_index]);
+		}
 	kvfree(attr->parse_attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
@@ -1559,6 +1561,7 @@ static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entr
 			mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat);
 	}
 
+	kfree(e->tun_info);
 	kfree(e->encap_header);
 	kfree_rcu(e, rcu);
 }
@@ -2972,6 +2975,13 @@ mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key,
 	return NULL;
 }
 
+static struct ip_tunnel_info *dup_tun_info(const struct ip_tunnel_info *tun_info)
+{
+	size_t tun_size = sizeof(*tun_info) + tun_info->options_len;
+
+	return kmemdup(tun_info, tun_size, GFP_KERNEL);
+}
+
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow,
 			      struct net_device *mirred_dev,
@@ -3028,13 +3038,15 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	refcount_set(&e->refcnt, 1);
 	init_completion(&e->res_ready);
 
+	tun_info = dup_tun_info(tun_info);
+	if (!tun_info) {
+		err = -ENOMEM;
+		goto out_err_init;
+	}
 	e->tun_info = tun_info;
 	err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack);
-	if (err) {
-		kfree(e);
-		e = NULL;
-		goto out_err;
-	}
+	if (err)
+		goto out_err_init;
 
 	INIT_LIST_HEAD(&e->flows);
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
@@ -3075,6 +3087,12 @@ out_err:
 	if (e)
 		mlx5e_encap_put(priv, e);
 	return err;
+
+out_err_init:
+	mutex_unlock(&esw->offloads.encap_tbl_lock);
+	kfree(tun_info);
+	kfree(e);
+	return err;
 }
 
 static int parse_tc_vlan_action(struct mlx5e_priv *priv,
@@ -3160,7 +3178,7 @@ static int add_vlan_pop_action(struct mlx5e_priv *priv,
 			       struct mlx5_esw_flow_attr *attr,
 			       u32 *action)
 {
-	int nest_level = vlan_get_encap_level(attr->parse_attr->filter_dev);
+	int nest_level = attr->parse_attr->filter_dev->lower_level;
 	struct flow_action_entry vlan_act = {
 		.id = FLOW_ACTION_VLAN_POP,
 	};
@@ -3295,7 +3313,9 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			} else if (encap) {
 				parse_attr->mirred_ifindex[attr->out_count] =
 					out_dev->ifindex;
-				parse_attr->tun_info[attr->out_count] = info;
+				parse_attr->tun_info[attr->out_count] = dup_tun_info(info);
+				if (!parse_attr->tun_info[attr->out_count])
+					return -ENOMEM;
 				encap = false;
 				attr->dests[attr->out_count].flags |=
 					MLX5_ESW_DEST_ENCAP;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index d3a67a9b4eba..67dc4f0921b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -403,7 +403,10 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 				 struct mlx5_err_cqe *err_cqe)
 {
-	u32 ci = mlx5_cqwq_get_ci(&sq->cq.wq);
+	struct mlx5_cqwq *wq = &sq->cq.wq;
+	u32 ci;
+
+	ci = mlx5_cqwq_ctr2ix(wq, wq->cc - 1);
 
 	netdev_err(sq->channel->netdev,
 		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
@@ -479,14 +482,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 			skb = wi->skb;
 
 			if (unlikely(!skb)) {
-#ifdef CONFIG_MLX5_EN_TLS
-				if (wi->resync_dump_frag) {
-					struct mlx5e_sq_dma *dma =
-						mlx5e_dma_get(sq, dma_fifo_cc++);
-
-					mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, dma);
-				}
-#endif
+				mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc);
 				sqcc += wi->num_wqebbs;
 				continue;
 			}
@@ -542,29 +538,38 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq)
 {
 	struct mlx5e_tx_wqe_info *wi;
 	struct sk_buff *skb;
+	u32 dma_fifo_cc;
+	u16 sqcc;
 	u16 ci;
 	int i;
 
-	while (sq->cc != sq->pc) {
-		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+	sqcc = sq->cc;
+	dma_fifo_cc = sq->dma_fifo_cc;
+
+	while (sqcc != sq->pc) {
+		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
 		wi = &sq->db.wqe_info[ci];
 		skb = wi->skb;
 
-		if (!skb) { /* nop */
-			sq->cc++;
+		if (!skb) {
+			mlx5e_ktls_tx_handle_resync_dump_comp(sq, wi, &dma_fifo_cc);
+			sqcc += wi->num_wqebbs;
 			continue;
 		}
 
 		for (i = 0; i < wi->num_dma; i++) {
 			struct mlx5e_sq_dma *dma =
-				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+				mlx5e_dma_get(sq, dma_fifo_cc++);
 
 			mlx5e_tx_dma_unmap(sq->pdev, dma);
 		}
 
 		dev_kfree_skb_any(skb);
-		sq->cc += wi->num_wqebbs;
+		sqcc += wi->num_wqebbs;
 	}
+
+	sq->dma_fifo_cc = dma_fifo_cc;
+	sq->cc = sqcc;
 }
 
 #ifdef CONFIG_MLX5_CORE_IPOIB
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 00d71db15f22..9004a07e457a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -285,7 +285,6 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 
 	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
 
-	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
 	if (attr->outer_match_level != MLX5_MATCH_NONE)
 		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
 
@@ -1080,7 +1079,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
 	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
 
-	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(2^%d))\n",
+	esw_debug(dev, "Create offloads FDB table, min (max esw size(2^%d), max counters(%d), groups(%d), max flow table size(%d))\n",
 		  MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size),
 		  max_flow_counter, ESW_OFFLOADS_NUM_GROUPS,
 		  fdb_max);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
index 1d55a324a17e..366bda1bb1c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_termtbl.c
@@ -177,22 +177,33 @@ mlx5_eswitch_termtbl_actions_move(struct mlx5_flow_act *src,
 	memset(&src->vlan[1], 0, sizeof(src->vlan[1]));
 }
 
+static bool mlx5_eswitch_offload_is_uplink_port(const struct mlx5_eswitch *esw,
+						const struct mlx5_flow_spec *spec)
+{
+	u32 port_mask, port_value;
+
+	if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
+		return spec->flow_context.flow_source ==
+					MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+
+	port_mask = MLX5_GET(fte_match_param, spec->match_criteria,
+			     misc_parameters.source_port);
+	port_value = MLX5_GET(fte_match_param, spec->match_value,
+			      misc_parameters.source_port);
+	return (port_mask & port_value & 0xffff) == MLX5_VPORT_UPLINK;
+}
+
 bool
 mlx5_eswitch_termtbl_required(struct mlx5_eswitch *esw,
 			      struct mlx5_flow_act *flow_act,
 			      struct mlx5_flow_spec *spec)
 {
-	u32 port_mask = MLX5_GET(fte_match_param, spec->match_criteria,
-				 misc_parameters.source_port);
-	u32 port_value = MLX5_GET(fte_match_param, spec->match_value,
-				  misc_parameters.source_port);
-
 	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, termination_table))
 		return false;
 
 	/* push vlan on RX */
 	return (flow_act->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) &&
-		((port_mask & port_value) == MLX5_VPORT_UPLINK);
+		mlx5_eswitch_offload_is_uplink_port(esw, spec);
 }
 
 struct mlx5_flow_handle *
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 4c50efe4e7f1..61021133029e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -464,8 +464,10 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	}
 
 	err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn);
-	if (err)
+	if (err) {
+		kvfree(in);
 		goto err_cqwq;
+	}
 
 	cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context);
 	MLX5_SET(cqc, cqc, log_cq_size, ilog2(cq_size));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 579c306caa7b..3c816e81f8d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -507,7 +507,8 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id,
 					 dst->dest_attr.vport.vhca_id);
-				if (extended_dest) {
+				if (extended_dest &&
+				    dst->dest_attr.vport.pkt_reformat) {
 					MLX5_SET(dest_format_struct, in_dests,
 						 packet_reformat,
 						 !!(dst->dest_attr.vport.flags &
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index d685122d9ff7..c07f3154437c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -572,7 +572,7 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
 		return -ENOMEM;
 	err = mlx5_crdump_collect(dev, cr_data);
 	if (err)
-		return err;
+		goto free_data;
 
 	if (priv_ctx) {
 		struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
index b74b7d0f6590..004c56c2fc0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c
@@ -1577,6 +1577,7 @@ int mlx5dr_action_destroy(struct mlx5dr_action *action)
 		break;
 	case DR_ACTION_TYP_MODIFY_HDR:
 		mlx5dr_icm_free_chunk(action->rewrite.chunk);
+		kfree(action->rewrite.data);
 		refcount_dec(&action->rewrite.dmn->refcount);
 		break;
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index e8b656075c6f..5dcb8baf491a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -1096,6 +1096,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 	if (htbl)
 		mlx5dr_htbl_put(htbl);
 
+	kfree(hw_ste_arr);
+
 	return 0;
 
 free_ste:
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index 14dcc786926d..4421ab22182f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1186,7 +1186,7 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 	if (err)
 		goto err_thermal_init;
 
-	if (mlxsw_driver->params_register && !reload)
+	if (mlxsw_driver->params_register)
 		devlink_params_publish(devlink);
 
 	return 0;
@@ -1259,7 +1259,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 			return;
 	}
 
-	if (mlxsw_core->driver->params_unregister && !reload)
+	if (mlxsw_core->driver->params_unregister)
 		devlink_params_unpublish(devlink);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 4d1bce4389c7..672ea1342add 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -261,8 +261,15 @@ static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
 		port->pvid = vid;
 
 	/* Untagged egress vlan clasification */
-	if (untagged)
+	if (untagged && port->vid != vid) {
+		if (port->vid) {
+			dev_err(ocelot->dev,
+				"Port already has a native VLAN: %d\n",
+				port->vid);
+			return -EBUSY;
+		}
 		port->vid = vid;
+	}
 
 	ocelot_vlan_port_apply(ocelot, port);
 
@@ -934,7 +941,7 @@ end:
 static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
 				  u16 vid)
 {
-	return ocelot_vlan_vid_add(dev, vid, false, true);
+	return ocelot_vlan_vid_add(dev, vid, false, false);
 }
 
 static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
@@ -1673,9 +1680,6 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 	struct ocelot_port *ocelot_port = netdev_priv(dev);
 	int err = 0;
 
-	if (!ocelot_netdevice_dev_check(dev))
-		return 0;
-
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
 		if (netif_is_bridge_master(info->upper_dev)) {
@@ -1712,12 +1716,16 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;
 
+	if (!ocelot_netdevice_dev_check(dev))
+		return 0;
+
 	if (event == NETDEV_PRECHANGEUPPER &&
 	    netif_is_lag_master(info->upper_dev)) {
 		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
 		struct netlink_ext_ack *extack;
 
-		if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		if (lag_upper_info &&
+		    lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
 			extack = netdev_notifier_info_to_extack(&info->info);
 			NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
 
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index e40773c01a44..06ac806052bc 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -523,7 +523,7 @@ void __ocelot_write_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 offset);
 #define ocelot_write_rix(ocelot, val, reg, ri) __ocelot_write_ix(ocelot, val, reg, reg##_RSZ * (ri))
 #define ocelot_write(ocelot, val, reg) __ocelot_write_ix(ocelot, val, reg, 0)
 
-void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 reg, u32 mask,
+void __ocelot_rmw_ix(struct ocelot *ocelot, u32 val, u32 mask, u32 reg,
 		     u32 offset);
 #define ocelot_rmw_ix(ocelot, val, m, reg, gi, ri) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi) + reg##_RSZ * (ri))
 #define ocelot_rmw_gix(ocelot, val, m, reg, gi) __ocelot_rmw_ix(ocelot, val, m, reg, reg##_GSZ * (gi))
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index 1eef446036d6..79d72c88bbef 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -299,22 +299,6 @@ static void nfp_repr_clean(struct nfp_repr *repr)
 	nfp_port_free(repr->port);
 }
 
-static struct lock_class_key nfp_repr_netdev_xmit_lock_key;
-static struct lock_class_key nfp_repr_netdev_addr_lock_key;
-
-static void nfp_repr_set_lockdep_class_one(struct net_device *dev,
-					   struct netdev_queue *txq,
-					   void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &nfp_repr_netdev_xmit_lock_key);
-}
-
-static void nfp_repr_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &nfp_repr_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, nfp_repr_set_lockdep_class_one, NULL);
-}
-
 int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  u32 cmsg_port_id, struct nfp_port *port,
 		  struct net_device *pf_netdev)
@@ -324,8 +308,6 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 	u32 repr_cap = nn->tlv_caps.repr_cap;
 	int err;
 
-	nfp_repr_set_lockdep_class(netdev);
-
 	repr->port = port;
 	repr->dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX, GFP_KERNEL);
 	if (!repr->dst)
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
index 72107a0627a9..20faa8d24c9f 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
+#include <linux/printk.h>
+#include <linux/dynamic_debug.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/rtnetlink.h>
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
index 15e432386b35..aab311413412 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
 
+#include <linux/printk.h>
+#include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/utsname.h>
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 2ce70097d018..38f7f40b3a4d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -67,10 +67,9 @@
 #define QED_ROCE_QPS			(8192)
 #define QED_ROCE_DPIS			(8)
 #define QED_RDMA_SRQS                   QED_ROCE_QPS
-#define QED_NVM_CFG_SET_FLAGS		0xE
-#define QED_NVM_CFG_SET_PF_FLAGS	0x1E
 #define QED_NVM_CFG_GET_FLAGS		0xA
 #define QED_NVM_CFG_GET_PF_FLAGS	0x1A
+#define QED_NVM_CFG_MAX_ATTRS		50
 
 static char version[] =
 	"QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n";
@@ -2255,6 +2254,7 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
 	u8 entity_id, len, buf[32];
+	bool need_nvm_init = true;
 	struct qed_ptt *ptt;
 	u16 cfg_id, count;
 	int rc = 0, i;
@@ -2271,8 +2271,10 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data)
 
 	DP_VERBOSE(cdev, NETIF_MSG_DRV,
 		   "Read config ids: num_attrs = %0d\n", count);
-	/* NVM CFG ID attributes */
-	for (i = 0; i < count; i++) {
+	/* NVM CFG ID attributes. Start loop index from 1 to avoid additional
+	 * arithmetic operations in the implementation.
+	 */
+	for (i = 1; i <= count; i++) {
 		cfg_id = *((u16 *)*data);
 		*data += 2;
 		entity_id = **data;
@@ -2282,8 +2284,21 @@ static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data)
 		memcpy(buf, *data, len);
 		*data += len;
 
-		flags = entity_id ? QED_NVM_CFG_SET_PF_FLAGS :
-			QED_NVM_CFG_SET_FLAGS;
+		flags = 0;
+		if (need_nvm_init) {
+			flags |= QED_NVM_CFG_OPTION_INIT;
+			need_nvm_init = false;
+		}
+
+		/* Commit to flash and free the resources */
+		if (!(i % QED_NVM_CFG_MAX_ATTRS) || i == count) {
+			flags |= QED_NVM_CFG_OPTION_COMMIT |
+				 QED_NVM_CFG_OPTION_FREE;
+			need_nvm_init = true;
+		}
+
+		if (entity_id)
+			flags |= QED_NVM_CFG_OPTION_ENTITY_SEL;
 
 		DP_VERBOSE(cdev, NETIF_MSG_DRV,
 			   "cfg_id = %d entity = %d len = %d\n", cfg_id,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 78f77b712b10..dcb5c917f373 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -2005,7 +2005,7 @@ static void qed_iov_vf_mbx_stop_vport(struct qed_hwfn *p_hwfn,
 	    (qed_iov_validate_active_txq(p_hwfn, vf))) {
 		vf->b_malicious = true;
 		DP_NOTICE(p_hwfn,
-			  "VF [%02x] - considered malicious; Unable to stop RX/TX queuess\n",
+			  "VF [%02x] - considered malicious; Unable to stop RX/TX queues\n",
 			  vf->abs_vf_id);
 		status = PFVF_STATUS_MALICIOUS;
 		goto out;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8d1c208f778f..a220cc7c947a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1208,8 +1208,16 @@ enum qede_remove_mode {
 static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 {
 	struct net_device *ndev = pci_get_drvdata(pdev);
-	struct qede_dev *edev = netdev_priv(ndev);
-	struct qed_dev *cdev = edev->cdev;
+	struct qede_dev *edev;
+	struct qed_dev *cdev;
+
+	if (!ndev) {
+		dev_info(&pdev->dev, "Device has already been removed\n");
+		return;
+	}
+
+	edev = netdev_priv(ndev);
+	cdev = edev->cdev;
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 9c54b715228e..06de59521fc4 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -57,10 +57,10 @@ static int rmnet_unregister_real_device(struct net_device *real_dev,
 	if (port->nr_rmnet_devs)
 		return -EINVAL;
 
-	kfree(port);
-
 	netdev_rx_handler_unregister(real_dev);
 
+	kfree(port);
+
 	/* release reference on real_dev */
 	dev_put(real_dev);
 
diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 350b0d949611..c4e961ea44d5 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -916,6 +916,9 @@ static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value)
 
 static int r8168g_mdio_read(struct rtl8169_private *tp, int reg)
 {
+	if (reg == 0x1f)
+		return tp->ocp_base == OCP_STD_PHY_BASE ? 0 : tp->ocp_base >> 4;
+
 	if (tp->ocp_base != OCP_STD_PHY_BASE)
 		reg -= 0x10;
 
@@ -1029,6 +1032,10 @@ static int r8168dp_2_mdio_read(struct rtl8169_private *tp, int reg)
 {
 	int value;
 
+	/* Work around issue with chip reporting wrong PHY ID */
+	if (reg == MII_PHYSID2)
+		return 0xc912;
+
 	r8168dp_2_mdio_start(tp);
 
 	value = r8169_mdio_read(tp, reg);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 5a7b0aca1d31..66e60c7e9850 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -432,7 +432,7 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 			 * bits used depends on the hardware configuration
 			 * selected at core configuration time.
 			 */
-			int bit_nr = bitrev32(~crc32_le(~0, ha->addr,
+			u32 bit_nr = bitrev32(~crc32_le(~0, ha->addr,
 					ETH_ALEN)) >> (32 - mcbitslog2);
 			/* The most significant bit determines the register to
 			 * use (H/L) while the other 5 bits determine the bit
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 5031398e612c..070bd7d1ae4c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -224,6 +224,7 @@ static void dwxgmac2_config_cbs(struct mac_device_info *hw,
 	writel(low_credit, ioaddr + XGMAC_MTL_TCx_LOCREDIT(queue));
 
 	value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue));
+	value &= ~XGMAC_TSA;
 	value |= XGMAC_CC | XGMAC_CBS;
 	writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue));
 }
@@ -463,7 +464,7 @@ static void dwxgmac2_set_filter(struct mac_device_info *hw,
 		value |= XGMAC_FILTER_HMC;
 
 		netdev_for_each_mc_addr(ha, dev) {
-			int nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >>
+			u32 nr = (bitrev32(~crc32_le(~0, ha->addr, 6)) >>
 					(32 - mcbitslog2));
 			mc_filter[nr >> 5] |= (1 << (nr & 0x1F));
 		}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index ae48154f933c..bd5838ce1e8a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -288,7 +288,8 @@ static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash,
 
 static int dwxgmac2_get_rx_header_len(struct dma_desc *p, unsigned int *len)
 {
-	*len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL;
+	if (le32_to_cpu(p->des3) & XGMAC_RDES3_L34T)
+		*len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 965cbe3e6f51..f70ca5300b82 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -369,7 +369,7 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
 	dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13;
 	dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12;
 	dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11;
-	dma_cap->av &= !(hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10;
+	dma_cap->av &= !((hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10);
 	dma_cap->arpoffsel = (hw_cap & XGMAC_HWFEAT_ARPOFFSEL) >> 9;
 	dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8;
 	dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7;
@@ -470,6 +470,7 @@ static void dwxgmac2_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode)
 {
 	u32 value = readl(ioaddr + XGMAC_MTL_TXQ_OPMODE(channel));
+	u32 flow = readl(ioaddr + XGMAC_RX_FLOW_CTRL);
 
 	value &= ~XGMAC_TXQEN;
 	if (qmode != MTL_QUEUE_AVB) {
@@ -477,6 +478,7 @@ static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode)
 		writel(0, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(channel));
 	} else {
 		value |= 0x1 << XGMAC_TXQEN_SHIFT;
+		writel(flow & (~XGMAC_RFE), ioaddr + XGMAC_RX_FLOW_CTRL);
 	}
 
 	writel(value, ioaddr +  XGMAC_MTL_TXQ_OPMODE(channel));
diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
index a223584f5f9a..252cf48c5816 100644
--- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c
@@ -176,6 +176,7 @@
 #define MMC_XGMAC_RX_PKT_SMD_ERR	0x22c
 #define MMC_XGMAC_RX_PKT_ASSEMBLY_OK	0x230
 #define MMC_XGMAC_RX_FPE_FRAG		0x234
+#define MMC_XGMAC_RX_IPC_INTR_MASK	0x25c
 
 static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode)
 {
@@ -333,8 +334,9 @@ static void dwxgmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode)
 
 static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr)
 {
-	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK);
-	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK);
+	writel(0x0, mmcaddr + MMC_RX_INTR_MASK);
+	writel(0x0, mmcaddr + MMC_TX_INTR_MASK);
+	writel(MMC_DEFAULT_MASK, mmcaddr + MMC_XGMAC_RX_IPC_INTR_MASK);
 }
 
 static void dwxgmac_read_mmc_reg(void __iomem *addr, u32 reg, u32 *dest)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3dfd04e0506a..f826365c979d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2995,6 +2995,8 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	} else {
 		stmmac_set_desc_addr(priv, first, des);
 		tmp_pay_len = pay_len;
+		des += proto_hdr_len;
+		pay_len = 0;
 	}
 
 	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
@@ -3022,6 +3024,19 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Only the last descriptor gets to point to the skb. */
 	tx_q->tx_skbuff[tx_q->cur_tx] = skb;
 
+	/* Manage tx mitigation */
+	tx_q->tx_count_frames += nfrags + 1;
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	      priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		desc = &tx_q->dma_tx[tx_q->cur_tx];
+		tx_q->tx_count_frames = 0;
+		stmmac_set_tx_ic(priv, desc);
+		priv->xstats.tx_set_ic_bit++;
+	}
+
 	/* We've used all descriptors we need for this skb, however,
 	 * advance cur_tx so that it references a fresh descriptor.
 	 * ndo_start_xmit will fill this descriptor the next time it's
@@ -3039,19 +3054,6 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 	priv->xstats.tx_tso_frames++;
 	priv->xstats.tx_tso_nfrags += nfrags;
 
-	/* Manage tx mitigation */
-	tx_q->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
-	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
-	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-	    priv->hwts_tx_en)) {
-		stmmac_tx_timer_arm(priv, queue);
-	} else {
-		tx_q->tx_count_frames = 0;
-		stmmac_set_tx_ic(priv, desc);
-		priv->xstats.tx_set_ic_bit++;
-	}
-
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
@@ -3223,6 +3225,27 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Only the last descriptor gets to point to the skb. */
 	tx_q->tx_skbuff[entry] = skb;
 
+	/* According to the coalesce parameter the IC bit for the latest
+	 * segment is reset and the timer re-started to clean the tx status.
+	 * This approach takes care about the fragments: desc is the first
+	 * element in case of no SG.
+	 */
+	tx_q->tx_count_frames += nfrags + 1;
+	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
+	    !((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	      priv->hwts_tx_en)) {
+		stmmac_tx_timer_arm(priv, queue);
+	} else {
+		if (likely(priv->extend_desc))
+			desc = &tx_q->dma_etx[entry].basic;
+		else
+			desc = &tx_q->dma_tx[entry];
+
+		tx_q->tx_count_frames = 0;
+		stmmac_set_tx_ic(priv, desc);
+		priv->xstats.tx_set_ic_bit++;
+	}
+
 	/* We've used all descriptors we need for this skb, however,
 	 * advance cur_tx so that it references a fresh descriptor.
 	 * ndo_start_xmit will fill this descriptor the next time it's
@@ -3258,23 +3281,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	dev->stats.tx_bytes += skb->len;
 
-	/* According to the coalesce parameter the IC bit for the latest
-	 * segment is reset and the timer re-started to clean the tx status.
-	 * This approach takes care about the fragments: desc is the first
-	 * element in case of no SG.
-	 */
-	tx_q->tx_count_frames += nfrags + 1;
-	if (likely(priv->tx_coal_frames > tx_q->tx_count_frames) &&
-	    !(priv->synopsys_id >= DWMAC_CORE_4_00 &&
-	    (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
-	    priv->hwts_tx_en)) {
-		stmmac_tx_timer_arm(priv, queue);
-	} else {
-		tx_q->tx_count_frames = 0;
-		stmmac_set_tx_ic(priv, desc);
-		priv->xstats.tx_set_ic_bit++;
-	}
-
 	if (priv->sarc_type)
 		stmmac_set_desc_sarc(priv, first, priv->sarc_type);
 
@@ -3505,8 +3511,6 @@ read_again:
 		if (unlikely(status & dma_own))
 			break;
 
-		count++;
-
 		rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE);
 		next_entry = rx_q->cur_rx;
 
@@ -3533,6 +3537,7 @@ read_again:
 			goto read_again;
 		if (unlikely(error)) {
 			dev_kfree_skb(skb);
+			count++;
 			continue;
 		}
 
@@ -3572,6 +3577,7 @@ read_again:
 			skb = napi_alloc_skb(&ch->rx_napi, len);
 			if (!skb) {
 				priv->dev->stats.rx_dropped++;
+				count++;
 				continue;
 			}
 
@@ -3637,6 +3643,7 @@ read_again:
 
 		priv->dev->stats.rx_packets++;
 		priv->dev->stats.rx_bytes += len;
+		count++;
 	}
 
 	if (status & rx_not_ls) {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index e4ac3c401432..ac3f658105c0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -6,7 +6,9 @@
  * Author: Jose Abreu <joabreu@synopsys.com>
  */
 
+#include <linux/bitrev.h>
 #include <linux/completion.h>
+#include <linux/crc32.h>
 #include <linux/ethtool.h>
 #include <linux/ip.h>
 #include <linux/phy.h>
@@ -485,12 +487,48 @@ static int stmmac_filter_check(struct stmmac_priv *priv)
 	return -EOPNOTSUPP;
 }
 
+static bool stmmac_hash_check(struct stmmac_priv *priv, unsigned char *addr)
+{
+	int mc_offset = 32 - priv->hw->mcast_bits_log2;
+	struct netdev_hw_addr *ha;
+	u32 hash, hash_nr;
+
+	/* First compute the hash for desired addr */
+	hash = bitrev32(~crc32_le(~0, addr, 6)) >> mc_offset;
+	hash_nr = hash >> 5;
+	hash = 1 << (hash & 0x1f);
+
+	/* Now, check if it collides with any existing one */
+	netdev_for_each_mc_addr(ha, priv->dev) {
+		u32 nr = bitrev32(~crc32_le(~0, ha->addr, ETH_ALEN)) >> mc_offset;
+		if (((nr >> 5) == hash_nr) && ((1 << (nr & 0x1f)) == hash))
+			return false;
+	}
+
+	/* No collisions, address is good to go */
+	return true;
+}
+
+static bool stmmac_perfect_check(struct stmmac_priv *priv, unsigned char *addr)
+{
+	struct netdev_hw_addr *ha;
+
+	/* Check if it collides with any existing one */
+	netdev_for_each_uc_addr(ha, priv->dev) {
+		if (!memcmp(ha->addr, addr, ETH_ALEN))
+			return false;
+	}
+
+	/* No collisions, address is good to go */
+	return true;
+}
+
 static int stmmac_test_hfilt(struct stmmac_priv *priv)
 {
-	unsigned char gd_addr[ETH_ALEN] = {0x01, 0xee, 0xdd, 0xcc, 0xbb, 0xaa};
-	unsigned char bd_addr[ETH_ALEN] = {0x01, 0x01, 0x02, 0x03, 0x04, 0x05};
+	unsigned char gd_addr[ETH_ALEN] = {0xf1, 0xee, 0xdd, 0xcc, 0xbb, 0xaa};
+	unsigned char bd_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff};
 	struct stmmac_packet_attrs attr = { };
-	int ret;
+	int ret, tries = 256;
 
 	ret = stmmac_filter_check(priv);
 	if (ret)
@@ -499,6 +537,16 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv)
 	if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins)
 		return -EOPNOTSUPP;
 
+	while (--tries) {
+		/* We only need to check the bd_addr for collisions */
+		bd_addr[ETH_ALEN - 1] = tries;
+		if (stmmac_hash_check(priv, bd_addr))
+			break;
+	}
+
+	if (!tries)
+		return -EOPNOTSUPP;
+
 	ret = dev_mc_add(priv->dev, gd_addr);
 	if (ret)
 		return ret;
@@ -523,13 +571,25 @@ cleanup:
 
 static int stmmac_test_pfilt(struct stmmac_priv *priv)
 {
-	unsigned char gd_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77};
-	unsigned char bd_addr[ETH_ALEN] = {0x08, 0x00, 0x22, 0x33, 0x44, 0x55};
+	unsigned char gd_addr[ETH_ALEN] = {0xf0, 0x01, 0x44, 0x55, 0x66, 0x77};
+	unsigned char bd_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff};
 	struct stmmac_packet_attrs attr = { };
-	int ret;
+	int ret, tries = 256;
 
 	if (stmmac_filter_check(priv))
 		return -EOPNOTSUPP;
+	if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries)
+		return -EOPNOTSUPP;
+
+	while (--tries) {
+		/* We only need to check the bd_addr for collisions */
+		bd_addr[ETH_ALEN - 1] = tries;
+		if (stmmac_perfect_check(priv, bd_addr))
+			break;
+	}
+
+	if (!tries)
+		return -EOPNOTSUPP;
 
 	ret = dev_uc_add(priv->dev, gd_addr);
 	if (ret)
@@ -553,39 +613,31 @@ cleanup:
 	return ret;
 }
 
-static int stmmac_dummy_sync(struct net_device *netdev, const u8 *addr)
-{
-	return 0;
-}
-
-static void stmmac_test_set_rx_mode(struct net_device *netdev)
-{
-	/* As we are in test mode of ethtool we already own the rtnl lock
-	 * so no address will change from user. We can just call the
-	 * ndo_set_rx_mode() callback directly */
-	if (netdev->netdev_ops->ndo_set_rx_mode)
-		netdev->netdev_ops->ndo_set_rx_mode(netdev);
-}
-
 static int stmmac_test_mcfilt(struct stmmac_priv *priv)
 {
-	unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77};
-	unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77};
+	unsigned char uc_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff};
+	unsigned char mc_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff};
 	struct stmmac_packet_attrs attr = { };
-	int ret;
+	int ret, tries = 256;
 
 	if (stmmac_filter_check(priv))
 		return -EOPNOTSUPP;
-	if (!priv->hw->multicast_filter_bins)
+	if (netdev_uc_count(priv->dev) >= priv->hw->unicast_filter_entries)
 		return -EOPNOTSUPP;
 
-	/* Remove all MC addresses */
-	__dev_mc_unsync(priv->dev, NULL);
-	stmmac_test_set_rx_mode(priv->dev);
+	while (--tries) {
+		/* We only need to check the mc_addr for collisions */
+		mc_addr[ETH_ALEN - 1] = tries;
+		if (stmmac_hash_check(priv, mc_addr))
+			break;
+	}
+
+	if (!tries)
+		return -EOPNOTSUPP;
 
 	ret = dev_uc_add(priv->dev, uc_addr);
 	if (ret)
-		goto cleanup;
+		return ret;
 
 	attr.dst = uc_addr;
 
@@ -602,30 +654,34 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv)
 
 cleanup:
 	dev_uc_del(priv->dev, uc_addr);
-	__dev_mc_sync(priv->dev, stmmac_dummy_sync, NULL);
-	stmmac_test_set_rx_mode(priv->dev);
 	return ret;
 }
 
 static int stmmac_test_ucfilt(struct stmmac_priv *priv)
 {
-	unsigned char uc_addr[ETH_ALEN] = {0x00, 0x01, 0x44, 0x55, 0x66, 0x77};
-	unsigned char mc_addr[ETH_ALEN] = {0x01, 0x01, 0x44, 0x55, 0x66, 0x77};
+	unsigned char uc_addr[ETH_ALEN] = {0xf0, 0xff, 0xff, 0xff, 0xff, 0xff};
+	unsigned char mc_addr[ETH_ALEN] = {0xf1, 0xff, 0xff, 0xff, 0xff, 0xff};
 	struct stmmac_packet_attrs attr = { };
-	int ret;
+	int ret, tries = 256;
 
 	if (stmmac_filter_check(priv))
 		return -EOPNOTSUPP;
-	if (!priv->hw->multicast_filter_bins)
+	if (netdev_mc_count(priv->dev) >= priv->hw->multicast_filter_bins)
 		return -EOPNOTSUPP;
 
-	/* Remove all UC addresses */
-	__dev_uc_unsync(priv->dev, NULL);
-	stmmac_test_set_rx_mode(priv->dev);
+	while (--tries) {
+		/* We only need to check the uc_addr for collisions */
+		uc_addr[ETH_ALEN - 1] = tries;
+		if (stmmac_perfect_check(priv, uc_addr))
+			break;
+	}
+
+	if (!tries)
+		return -EOPNOTSUPP;
 
 	ret = dev_mc_add(priv->dev, mc_addr);
 	if (ret)
-		goto cleanup;
+		return ret;
 
 	attr.dst = mc_addr;
 
@@ -642,8 +698,6 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv)
 
 cleanup:
 	dev_mc_del(priv->dev, mc_addr);
-	__dev_uc_sync(priv->dev, stmmac_dummy_sync, NULL);
-	stmmac_test_set_rx_mode(priv->dev);
 	return ret;
 }
 
diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index bbbc1dcb6ab5..b517c1af9de0 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -1237,8 +1237,17 @@ static int fjes_probe(struct platform_device *plat_dev)
 	adapter->open_guard = false;
 
 	adapter->txrx_wq = alloc_workqueue(DRV_NAME "/txrx", WQ_MEM_RECLAIM, 0);
+	if (unlikely(!adapter->txrx_wq)) {
+		err = -ENOMEM;
+		goto err_free_netdev;
+	}
+
 	adapter->control_wq = alloc_workqueue(DRV_NAME "/control",
 					      WQ_MEM_RECLAIM, 0);
+	if (unlikely(!adapter->control_wq)) {
+		err = -ENOMEM;
+		goto err_free_txrx_wq;
+	}
 
 	INIT_WORK(&adapter->tx_stall_task, fjes_tx_stall_task);
 	INIT_WORK(&adapter->raise_intr_rxdata_task,
@@ -1255,7 +1264,7 @@ static int fjes_probe(struct platform_device *plat_dev)
 	hw->hw_res.irq = platform_get_irq(plat_dev, 0);
 	err = fjes_hw_init(&adapter->hw);
 	if (err)
-		goto err_free_netdev;
+		goto err_free_control_wq;
 
 	/* setup MAC address (02:00:00:00:00:[epid])*/
 	netdev->dev_addr[0] = 2;
@@ -1277,6 +1286,10 @@ static int fjes_probe(struct platform_device *plat_dev)
 
 err_hw_exit:
 	fjes_hw_exit(&adapter->hw);
+err_free_control_wq:
+	destroy_workqueue(adapter->control_wq);
+err_free_txrx_wq:
+	destroy_workqueue(adapter->txrx_wq);
 err_free_netdev:
 	free_netdev(netdev);
 err_out:
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index fbec711ff514..fbea6f232819 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -107,27 +107,6 @@ struct bpqdev {
 
 static LIST_HEAD(bpq_devices);
 
-/*
- * bpqether network devices are paired with ethernet devices below them, so
- * form a special "super class" of normal ethernet devices; split their locks
- * off into a separate class since they always nest.
- */
-static struct lock_class_key bpq_netdev_xmit_lock_key;
-static struct lock_class_key bpq_netdev_addr_lock_key;
-
-static void bpq_set_lockdep_class_one(struct net_device *dev,
-				      struct netdev_queue *txq,
-				      void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key);
-}
-
-static void bpq_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL);
-}
-
 /* ------------------------------------------------------------------------ */
 
 
@@ -498,7 +477,6 @@ static int bpq_new_device(struct net_device *edev)
 	err = register_netdevice(ndev);
 	if (err)
 		goto error;
-	bpq_set_lockdep_class(ndev);
 
 	/* List protected by RTNL */
 	list_add_rcu(&bpq->bpq_list, &bpq_devices);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 39dddcd8b3cb..963509add611 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -982,7 +982,7 @@ static int netvsc_attach(struct net_device *ndev,
 	if (netif_running(ndev)) {
 		ret = rndis_filter_open(nvdev);
 		if (ret)
-			return ret;
+			goto err;
 
 		rdev = nvdev->extension;
 		if (!rdev->link_state)
@@ -990,6 +990,13 @@ static int netvsc_attach(struct net_device *ndev,
 	}
 
 	return 0;
+
+err:
+	netif_device_detach(ndev);
+
+	rndis_filter_device_remove(hdev, nvdev);
+
+	return ret;
 }
 
 static int netvsc_set_channels(struct net_device *net,
@@ -1807,8 +1814,10 @@ static int netvsc_set_features(struct net_device *ndev,
 
 	ret = rndis_filter_set_offload_params(ndev, nvdev, &offloads);
 
-	if (ret)
+	if (ret) {
 		features ^= NETIF_F_LRO;
+		ndev->features = features;
+	}
 
 syncvf:
 	if (!vf_netdev)
@@ -2335,8 +2344,6 @@ static int netvsc_probe(struct hv_device *dev,
 		NETIF_F_HW_VLAN_CTAG_RX;
 	net->vlan_features = net->features;
 
-	netdev_lockdep_set_classes(net);
-
 	/* MTU range: 68 - 1500 or 65521 */
 	net->min_mtu = NETVSC_MTU_MIN;
 	if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2)
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 887bbba4631e..ba3dfac1d904 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -131,8 +131,6 @@ static int ipvlan_init(struct net_device *dev)
 	dev->gso_max_segs = phy_dev->gso_max_segs;
 	dev->hard_header_len = phy_dev->hard_header_len;
 
-	netdev_lockdep_set_classes(dev);
-
 	ipvlan->pcpu_stats = netdev_alloc_pcpu_stats(struct ipvl_pcpu_stats);
 	if (!ipvlan->pcpu_stats)
 		return -ENOMEM;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index cb7637364b40..afd8b2a08245 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -267,7 +267,6 @@ struct macsec_dev {
 	struct pcpu_secy_stats __percpu *stats;
 	struct list_head secys;
 	struct gro_cells gro_cells;
-	unsigned int nest_level;
 };
 
 /**
@@ -2750,7 +2749,6 @@ static netdev_tx_t macsec_start_xmit(struct sk_buff *skb,
 
 #define MACSEC_FEATURES \
 	(NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST)
-static struct lock_class_key macsec_netdev_addr_lock_key;
 
 static int macsec_dev_init(struct net_device *dev)
 {
@@ -2958,11 +2956,6 @@ static int macsec_get_iflink(const struct net_device *dev)
 	return macsec_priv(dev)->real_dev->ifindex;
 }
 
-static int macsec_get_nest_level(struct net_device *dev)
-{
-	return macsec_priv(dev)->nest_level;
-}
-
 static const struct net_device_ops macsec_netdev_ops = {
 	.ndo_init		= macsec_dev_init,
 	.ndo_uninit		= macsec_dev_uninit,
@@ -2976,7 +2969,6 @@ static const struct net_device_ops macsec_netdev_ops = {
 	.ndo_start_xmit		= macsec_start_xmit,
 	.ndo_get_stats64	= macsec_get_stats64,
 	.ndo_get_iflink		= macsec_get_iflink,
-	.ndo_get_lock_subclass  = macsec_get_nest_level,
 };
 
 static const struct device_type macsec_type = {
@@ -3001,12 +2993,10 @@ static const struct nla_policy macsec_rtnl_policy[IFLA_MACSEC_MAX + 1] = {
 static void macsec_free_netdev(struct net_device *dev)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
-	struct net_device *real_dev = macsec->real_dev;
 
 	free_percpu(macsec->stats);
 	free_percpu(macsec->secy.tx_sc.stats);
 
-	dev_put(real_dev);
 }
 
 static void macsec_setup(struct net_device *dev)
@@ -3261,14 +3251,6 @@ static int macsec_newlink(struct net *net, struct net_device *dev,
 	if (err < 0)
 		return err;
 
-	dev_hold(real_dev);
-
-	macsec->nest_level = dev_get_nest_level(real_dev) + 1;
-	netdev_lockdep_set_classes(dev);
-	lockdep_set_class_and_subclass(&dev->addr_list_lock,
-				       &macsec_netdev_addr_lock_key,
-				       macsec_get_nest_level(dev));
-
 	err = netdev_upper_dev_link(real_dev, dev, extack);
 	if (err < 0)
 		goto unregister;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 940192c057b6..34fc59bd1e20 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -852,8 +852,6 @@ static int macvlan_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
  * "super class" of normal network devices; split their locks off into a
  * separate class since they always nest.
  */
-static struct lock_class_key macvlan_netdev_addr_lock_key;
-
 #define ALWAYS_ON_OFFLOADS \
 	(NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE | \
 	 NETIF_F_GSO_ROBUST | NETIF_F_GSO_ENCAP_ALL)
@@ -869,19 +867,6 @@ static struct lock_class_key macvlan_netdev_addr_lock_key;
 #define MACVLAN_STATE_MASK \
 	((1<<__LINK_STATE_NOCARRIER) | (1<<__LINK_STATE_DORMANT))
 
-static int macvlan_get_nest_level(struct net_device *dev)
-{
-	return ((struct macvlan_dev *)netdev_priv(dev))->nest_level;
-}
-
-static void macvlan_set_lockdep_class(struct net_device *dev)
-{
-	netdev_lockdep_set_classes(dev);
-	lockdep_set_class_and_subclass(&dev->addr_list_lock,
-				       &macvlan_netdev_addr_lock_key,
-				       macvlan_get_nest_level(dev));
-}
-
 static int macvlan_init(struct net_device *dev)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
@@ -900,8 +885,6 @@ static int macvlan_init(struct net_device *dev)
 	dev->gso_max_segs	= lowerdev->gso_max_segs;
 	dev->hard_header_len	= lowerdev->hard_header_len;
 
-	macvlan_set_lockdep_class(dev);
-
 	vlan->pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->pcpu_stats)
 		return -ENOMEM;
@@ -1161,7 +1144,6 @@ static const struct net_device_ops macvlan_netdev_ops = {
 	.ndo_fdb_add		= macvlan_fdb_add,
 	.ndo_fdb_del		= macvlan_fdb_del,
 	.ndo_fdb_dump		= ndo_dflt_fdb_dump,
-	.ndo_get_lock_subclass  = macvlan_get_nest_level,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= macvlan_dev_poll_controller,
 	.ndo_netpoll_setup	= macvlan_dev_netpoll_setup,
@@ -1445,7 +1427,6 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 	vlan->dev      = dev;
 	vlan->port     = port;
 	vlan->set_features = MACVLAN_FEATURES;
-	vlan->nest_level = dev_get_nest_level(lowerdev) + 1;
 
 	vlan->mode     = MACVLAN_MODE_VEPA;
 	if (data && data[IFLA_MACVLAN_MODE])
diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c
index 56576d4f34a5..54ca6681ba31 100644
--- a/drivers/net/netdevsim/dev.c
+++ b/drivers/net/netdevsim/dev.c
@@ -806,9 +806,11 @@ static void nsim_dev_port_del_all(struct nsim_dev *nsim_dev)
 {
 	struct nsim_dev_port *nsim_dev_port, *tmp;
 
+	mutex_lock(&nsim_dev->port_list_lock);
 	list_for_each_entry_safe(nsim_dev_port, tmp,
 				 &nsim_dev->port_list, list)
 		__nsim_dev_port_del(nsim_dev_port);
+	mutex_unlock(&nsim_dev->port_list_lock);
 }
 
 int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
@@ -822,14 +824,17 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev)
 		return PTR_ERR(nsim_dev);
 	dev_set_drvdata(&nsim_bus_dev->dev, nsim_dev);
 
+	mutex_lock(&nsim_dev->port_list_lock);
 	for (i = 0; i < nsim_bus_dev->port_count; i++) {
 		err = __nsim_dev_port_add(nsim_dev, i);
 		if (err)
 			goto err_port_del_all;
 	}
+	mutex_unlock(&nsim_dev->port_list_lock);
 	return 0;
 
 err_port_del_all:
+	mutex_unlock(&nsim_dev->port_list_lock);
 	nsim_dev_port_del_all(nsim_dev);
 	nsim_dev_destroy(nsim_dev);
 	return err;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 20e2ebe458f2..a578f7ebf715 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -87,8 +87,24 @@ struct phylink {
 	phylink_printk(KERN_WARNING, pl, fmt, ##__VA_ARGS__)
 #define phylink_info(pl, fmt, ...) \
 	phylink_printk(KERN_INFO, pl, fmt, ##__VA_ARGS__)
+#if defined(CONFIG_DYNAMIC_DEBUG)
 #define phylink_dbg(pl, fmt, ...) \
+do {									\
+	if ((pl)->config->type == PHYLINK_NETDEV)			\
+		netdev_dbg((pl)->netdev, fmt, ##__VA_ARGS__);		\
+	else if ((pl)->config->type == PHYLINK_DEV)			\
+		dev_dbg((pl)->dev, fmt, ##__VA_ARGS__);			\
+} while (0)
+#elif defined(DEBUG)
+#define phylink_dbg(pl, fmt, ...)					\
 	phylink_printk(KERN_DEBUG, pl, fmt, ##__VA_ARGS__)
+#else
+#define phylink_dbg(pl, fmt, ...)					\
+({									\
+	if (0)								\
+		phylink_printk(KERN_DEBUG, pl, fmt, ##__VA_ARGS__);	\
+})
+#endif
 
 /**
  * phylink_set_port_modes() - set the port type modes in the ethtool mask
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index dc3d92d340c4..b73298250793 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -327,6 +327,7 @@ static struct phy_driver smsc_phy_driver[] = {
 	.name		= "SMSC LAN8740",
 
 	/* PHY_BASIC_FEATURES */
+	.flags		= PHY_RST_AFTER_CLK_EN,
 
 	.probe		= smsc_phy_probe,
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 9a1b006904a7..61824bbb5588 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1324,8 +1324,6 @@ static int ppp_dev_init(struct net_device *dev)
 {
 	struct ppp *ppp;
 
-	netdev_lockdep_set_classes(dev);
-
 	ppp = netdev_priv(dev);
 	/* Let the netdevice take a reference on the ppp file. This ensures
 	 * that ppp_destroy_interface() won't run before the device gets
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index e8089def5a46..8156b33ee3e7 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1615,7 +1615,6 @@ static int team_init(struct net_device *dev)
 	int err;
 
 	team->dev = dev;
-	mutex_init(&team->lock);
 	team_set_no_mode(team);
 
 	team->pcpu_stats = netdev_alloc_pcpu_stats(struct team_pcpu_stats);
@@ -1642,7 +1641,8 @@ static int team_init(struct net_device *dev)
 		goto err_options_register;
 	netif_carrier_off(dev);
 
-	netdev_lockdep_set_classes(dev);
+	lockdep_register_key(&team->team_lock_key);
+	__mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key);
 
 	return 0;
 
@@ -1673,6 +1673,7 @@ static void team_uninit(struct net_device *dev)
 	team_queue_override_fini(team);
 	mutex_unlock(&team->lock);
 	netdev_change_features(dev);
+	lockdep_unregister_key(&team->team_lock_key);
 }
 
 static void team_destructor(struct net_device *dev)
@@ -1976,8 +1977,15 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 	err = team_port_del(team, port_dev);
 	mutex_unlock(&team->lock);
 
-	if (!err)
-		netdev_change_features(dev);
+	if (err)
+		return err;
+
+	if (netif_is_team_master(port_dev)) {
+		lockdep_unregister_key(&team->team_lock_key);
+		lockdep_register_key(&team->team_lock_key);
+		lockdep_set_class(&team->lock, &team->team_lock_key);
+	}
+	netdev_change_features(dev);
 
 	return err;
 }
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 32f53de5b1fe..fe630438f67b 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -787,6 +787,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* ThinkPad USB-C Dock Gen 2 (based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa387, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* NVIDIA Tegra USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(NVIDIA_VENDOR_ID, 0x09ff, USB_CLASS_COMM,
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 00cab3f43a4c..a245597a3902 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -578,8 +578,8 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
 	/* read current mtu value from device */
 	err = usbnet_read_cmd(dev, USB_CDC_GET_MAX_DATAGRAM_SIZE,
 			      USB_TYPE_CLASS | USB_DIR_IN | USB_RECIP_INTERFACE,
-			      0, iface_no, &max_datagram_size, 2);
-	if (err < 0) {
+			      0, iface_no, &max_datagram_size, sizeof(max_datagram_size));
+	if (err < sizeof(max_datagram_size)) {
 		dev_dbg(&dev->intf->dev, "GET_MAX_DATAGRAM_SIZE failed\n");
 		goto out;
 	}
@@ -590,7 +590,7 @@ static void cdc_ncm_set_dgram_size(struct usbnet *dev, int new_size)
 	max_datagram_size = cpu_to_le16(ctx->max_datagram_size);
 	err = usbnet_write_cmd(dev, USB_CDC_SET_MAX_DATAGRAM_SIZE,
 			       USB_TYPE_CLASS | USB_DIR_OUT | USB_RECIP_INTERFACE,
-			       0, iface_no, &max_datagram_size, 2);
+			       0, iface_no, &max_datagram_size, sizeof(max_datagram_size));
 	if (err < 0)
 		dev_dbg(&dev->intf->dev, "SET_MAX_DATAGRAM_SIZE failed\n");
 
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 62948098191f..f24a1b0b801f 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1264,8 +1264,11 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb)
 		netif_dbg(dev, link, dev->net, "PHY INTR: 0x%08x\n", intdata);
 		lan78xx_defer_kevent(dev, EVENT_LINK_RESET);
 
-		if (dev->domain_data.phyirq > 0)
+		if (dev->domain_data.phyirq > 0) {
+			local_irq_disable();
 			generic_handle_irq(dev->domain_data.phyirq);
+			local_irq_enable();
+		}
 	} else
 		netdev_warn(dev->net,
 			    "unexpected interrupt: 0x%08x\n", intdata);
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 596428ec71df..56d334b9ad45 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1362,6 +1362,7 @@ static const struct usb_device_id products[] = {
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 8)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81b6, 10)},	/* Dell Wireless 5811e */
 	{QMI_FIXED_INTF(0x413c, 0x81d7, 0)},	/* Dell Wireless 5821e */
+	{QMI_FIXED_INTF(0x413c, 0x81e0, 0)},	/* Dell Wireless 5821e with eSIM support*/
 	{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 */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index cee9fef925cd..d4a95b50bda6 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -5755,6 +5755,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x720c)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7214)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0xa387)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_TPLINK,  0x0601)},
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index ee52bde058df..b8228f50bc94 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -865,7 +865,6 @@ static int vrf_dev_init(struct net_device *dev)
 
 	/* similarly, oper state is irrelevant; set to up to avoid confusion */
 	dev->operstate = IF_OPER_UP;
-	netdev_lockdep_set_classes(dev);
 	return 0;
 
 out_rth:
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 3d9bcc957f7d..8869154fad88 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2487,9 +2487,11 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		vni = tunnel_id_to_key32(info->key.tun_id);
 		ifindex = 0;
 		dst_cache = &info->dst_cache;
-		if (info->options_len &&
-		    info->key.tun_flags & TUNNEL_VXLAN_OPT)
+		if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
+			if (info->options_len < sizeof(*md))
+				goto drop;
 			md = ip_tunnel_info_opts(info);
+		}
 		ttl = info->key.ttl;
 		tos = info->key.tos;
 		label = info->key.label;
@@ -3566,10 +3568,13 @@ 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 net_device *remote_dev = NULL;
 	struct vxlan_fdb *f = NULL;
 	bool unregister = false;
+	struct vxlan_rdst *dst;
 	int err;
 
+	dst = &vxlan->default_dst;
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
 	if (err)
 		return err;
@@ -3577,14 +3582,14 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	dev->ethtool_ops = &vxlan_ethtool_ops;
 
 	/* create an fdb entry for a valid default destination */
-	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
+	if (!vxlan_addr_any(&dst->remote_ip)) {
 		err = vxlan_fdb_create(vxlan, all_zeros_mac,
-				       &vxlan->default_dst.remote_ip,
+				       &dst->remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
 				       vxlan->cfg.dst_port,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_vni,
-				       vxlan->default_dst.remote_ifindex,
+				       dst->remote_vni,
+				       dst->remote_vni,
+				       dst->remote_ifindex,
 				       NTF_SELF, &f);
 		if (err)
 			return err;
@@ -3595,26 +3600,41 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 		goto errout;
 	unregister = true;
 
+	if (dst->remote_ifindex) {
+		remote_dev = __dev_get_by_index(net, dst->remote_ifindex);
+		if (!remote_dev)
+			goto errout;
+
+		err = netdev_upper_dev_link(remote_dev, dev, extack);
+		if (err)
+			goto errout;
+	}
+
 	err = rtnl_configure_link(dev, NULL);
 	if (err)
-		goto errout;
+		goto unlink;
 
 	if (f) {
-		vxlan_fdb_insert(vxlan, all_zeros_mac,
-				 vxlan->default_dst.remote_vni, f);
+		vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f);
 
 		/* notify default fdb entry */
 		err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f),
 				       RTM_NEWNEIGH, true, extack);
 		if (err) {
 			vxlan_fdb_destroy(vxlan, f, false, false);
+			if (remote_dev)
+				netdev_upper_dev_unlink(remote_dev, dev);
 			goto unregister;
 		}
 	}
 
 	list_add(&vxlan->next, &vn->vxlan_list);
+	if (remote_dev)
+		dst->remote_dev = remote_dev;
 	return 0;
-
+unlink:
+	if (remote_dev)
+		netdev_upper_dev_unlink(remote_dev, dev);
 errout:
 	/* unregister_netdevice() destroys the default FDB entry with deletion
 	 * notification. But the addition notification was not sent yet, so
@@ -3932,11 +3952,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
-	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct net_device *lowerdev;
 	struct vxlan_config conf;
+	struct vxlan_rdst *dst;
 	int err;
 
+	dst = &vxlan->default_dst;
 	err = vxlan_nl2conf(tb, data, dev, &conf, true, extack);
 	if (err)
 		return err;
@@ -3946,6 +3967,14 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	if (dst->remote_dev == lowerdev)
+		lowerdev = NULL;
+
+	err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev,
+					     extack);
+	if (err)
+		return err;
+
 	/* handle default dst entry */
 	if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) {
 		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni);
@@ -3962,6 +3991,8 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					       NTF_SELF, true, extack);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+				netdev_adjacent_change_abort(dst->remote_dev,
+							     lowerdev, dev);
 				return err;
 			}
 		}
@@ -3979,6 +4010,11 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (conf.age_interval != vxlan->cfg.age_interval)
 		mod_timer(&vxlan->age_timer, jiffies);
 
+	netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev);
+	if (lowerdev && lowerdev != dst->remote_dev) {
+		dst->remote_dev = lowerdev;
+		netdev_update_lockdep_key(lowerdev);
+	}
 	vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true);
 	return 0;
 }
@@ -3991,6 +4027,8 @@ static void vxlan_dellink(struct net_device *dev, struct list_head *head)
 
 	list_del(&vxlan->next);
 	unregister_netdevice_queue(dev, head);
+	if (vxlan->default_dst.remote_dev)
+		netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev);
 }
 
 static size_t vxlan_get_size(const struct net_device *dev)
diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/net/wimax/i2400m/op-rfkill.c
index 8efb493ceec2..5c79f052cad2 100644
--- a/drivers/net/wimax/i2400m/op-rfkill.c
+++ b/drivers/net/wimax/i2400m/op-rfkill.c
@@ -127,12 +127,12 @@ int i2400m_op_rfkill_sw_toggle(struct wimax_dev *wimax_dev,
 			"%d\n", result);
 	result = 0;
 error_cmd:
-	kfree(cmd);
 	kfree_skb(ack_skb);
 error_msg_to_dev:
 error_alloc:
 	d_fnend(4, dev, "(wimax_dev %p state %d) = %d\n",
 		wimax_dev, state, result);
+	kfree(cmd);
 	return result;
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
index 39c64850cb6f..c0750ced5ac2 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h
@@ -520,7 +520,7 @@ struct iwl_scan_dwell {
 } __packed;
 
 /**
- * struct iwl_scan_config
+ * struct iwl_scan_config_v1
  * @flags:			enum scan_config_flags
  * @tx_chains:			valid_tx antenna - ANT_* definitions
  * @rx_chains:			valid_rx antenna - ANT_* definitions
@@ -552,7 +552,7 @@ struct iwl_scan_config_v1 {
 #define SCAN_LB_LMAC_IDX 0
 #define SCAN_HB_LMAC_IDX 1
 
-struct iwl_scan_config {
+struct iwl_scan_config_v2 {
 	__le32 flags;
 	__le32 tx_chains;
 	__le32 rx_chains;
@@ -564,6 +564,24 @@ struct iwl_scan_config {
 	u8 bcast_sta_id;
 	u8 channel_flags;
 	u8 channel_array[];
+} __packed; /* SCAN_CONFIG_DB_CMD_API_S_2 */
+
+/**
+ * struct iwl_scan_config
+ * @enable_cam_mode: whether to enable CAM mode.
+ * @enable_promiscouos_mode: whether to enable promiscouos mode
+ * @bcast_sta_id: the index of the station in the fw
+ * @reserved: reserved
+ * @tx_chains: valid_tx antenna - ANT_* definitions
+ * @rx_chains: valid_rx antenna - ANT_* definitions
+ */
+struct iwl_scan_config {
+	u8 enable_cam_mode;
+	u8 enable_promiscouos_mode;
+	u8 bcast_sta_id;
+	u8 reserved;
+	__le32 tx_chains;
+	__le32 rx_chains;
 } __packed; /* SCAN_CONFIG_DB_CMD_API_S_3 */
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 423cc0cf8e78..0d5bc4ce5c07 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -288,6 +288,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t;
  *	STA_CONTEXT_DOT11AX_API_S
  * @IWL_UCODE_TLV_CAPA_SAR_TABLE_VER: This ucode supports different sar
  *	version tables.
+ * @IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG: This ucode supports v3 of
+ *  SCAN_CONFIG_DB_CMD_API_S.
  *
  * @NUM_IWL_UCODE_TLV_API: number of bits used
  */
@@ -321,6 +323,7 @@ enum iwl_ucode_tlv_api {
 	IWL_UCODE_TLV_API_WOWLAN_TCP_SYN_WAKE	= (__force iwl_ucode_tlv_api_t)53,
 	IWL_UCODE_TLV_API_FTM_RTT_ACCURACY      = (__force iwl_ucode_tlv_api_t)54,
 	IWL_UCODE_TLV_API_SAR_TABLE_VER         = (__force iwl_ucode_tlv_api_t)55,
+	IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG   = (__force iwl_ucode_tlv_api_t)56,
 	IWL_UCODE_TLV_API_ADWELL_HB_DEF_N_AP	= (__force iwl_ucode_tlv_api_t)57,
 	IWL_UCODE_TLV_API_SCAN_EXT_CHAN_VER	= (__force iwl_ucode_tlv_api_t)58,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index cb4c5514a556..695bbaa86273 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -279,6 +279,7 @@
  *         Indicates MAC is entering a power-saving sleep power-down.
  *         Not a good time to access device-internal resources.
  */
+#define CSR_GP_CNTRL_REG_FLAG_INIT_DONE		     (0x00000004)
 #define CSR_GP_CNTRL_REG_FLAG_GOING_TO_SLEEP         (0x00000010)
 #define CSR_GP_CNTRL_REG_FLAG_XTAL_ON		     (0x00000400)
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
index f47e0f97acf8..23c25a7665f2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h
@@ -449,6 +449,11 @@ enum {
 #define PERSISTENCE_BIT			BIT(12)
 #define PREG_WFPM_ACCESS		BIT(12)
 
+#define HPM_HIPM_GEN_CFG			0xA03458
+#define HPM_HIPM_GEN_CFG_CR_PG_EN		BIT(0)
+#define HPM_HIPM_GEN_CFG_CR_SLP_EN		BIT(1)
+#define HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE	BIT(10)
+
 #define UREG_DOORBELL_TO_ISR6		0xA05C04
 #define UREG_DOORBELL_TO_ISR6_NMI_BIT	BIT(0)
 #define UREG_DOORBELL_TO_ISR6_SUSPEND	BIT(18)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 843d00bf2bd5..5ca50f39a023 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1405,6 +1405,12 @@ static inline bool iwl_mvm_is_scan_ext_chan_supported(struct iwl_mvm *mvm)
 			  IWL_UCODE_TLV_API_SCAN_EXT_CHAN_VER);
 }
 
+static inline bool iwl_mvm_is_reduced_config_scan_supported(struct iwl_mvm *mvm)
+{
+	return fw_has_api(&mvm->fw->ucode_capa,
+			  IWL_UCODE_TLV_API_REDUCED_SCAN_CONFIG);
+}
+
 static inline bool iwl_mvm_has_new_rx_stats_api(struct iwl_mvm *mvm)
 {
 	return fw_has_api(&mvm->fw->ucode_capa,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
index f6b3045badbd..fcafa22ec6ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
@@ -1137,11 +1137,11 @@ static void iwl_mvm_fill_scan_config_v1(struct iwl_mvm *mvm, void *config,
 	iwl_mvm_fill_channels(mvm, cfg->channel_array, max_channels);
 }
 
-static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config,
-				     u32 flags, u8 channel_flags,
-				     u32 max_channels)
+static void iwl_mvm_fill_scan_config_v2(struct iwl_mvm *mvm, void *config,
+					u32 flags, u8 channel_flags,
+					u32 max_channels)
 {
-	struct iwl_scan_config *cfg = config;
+	struct iwl_scan_config_v2 *cfg = config;
 
 	cfg->flags = cpu_to_le32(flags);
 	cfg->tx_chains = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm));
@@ -1185,7 +1185,7 @@ static void iwl_mvm_fill_scan_config(struct iwl_mvm *mvm, void *config,
 	iwl_mvm_fill_channels(mvm, cfg->channel_array, max_channels);
 }
 
-int iwl_mvm_config_scan(struct iwl_mvm *mvm)
+static int iwl_mvm_legacy_config_scan(struct iwl_mvm *mvm)
 {
 	void *cfg;
 	int ret, cmd_size;
@@ -1217,7 +1217,7 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm)
 	}
 
 	if (iwl_mvm_cdb_scan_api(mvm))
-		cmd_size = sizeof(struct iwl_scan_config);
+		cmd_size = sizeof(struct iwl_scan_config_v2);
 	else
 		cmd_size = sizeof(struct iwl_scan_config_v1);
 	cmd_size += num_channels;
@@ -1254,8 +1254,8 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm)
 			flags |= (iwl_mvm_is_scan_fragmented(hb_type)) ?
 				 SCAN_CONFIG_FLAG_SET_LMAC2_FRAGMENTED :
 				 SCAN_CONFIG_FLAG_CLEAR_LMAC2_FRAGMENTED;
-		iwl_mvm_fill_scan_config(mvm, cfg, flags, channel_flags,
-					 num_channels);
+		iwl_mvm_fill_scan_config_v2(mvm, cfg, flags, channel_flags,
+					    num_channels);
 	} else {
 		iwl_mvm_fill_scan_config_v1(mvm, cfg, flags, channel_flags,
 					    num_channels);
@@ -1277,6 +1277,30 @@ int iwl_mvm_config_scan(struct iwl_mvm *mvm)
 	return ret;
 }
 
+int iwl_mvm_config_scan(struct iwl_mvm *mvm)
+{
+	struct iwl_scan_config cfg;
+	struct iwl_host_cmd cmd = {
+		.id = iwl_cmd_id(SCAN_CFG_CMD, IWL_ALWAYS_LONG_GROUP, 0),
+		.len[0] = sizeof(cfg),
+		.data[0] = &cfg,
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
+
+	if (!iwl_mvm_is_reduced_config_scan_supported(mvm))
+		return iwl_mvm_legacy_config_scan(mvm);
+
+	memset(&cfg, 0, sizeof(cfg));
+
+	cfg.bcast_sta_id = mvm->aux_sta.sta_id;
+	cfg.tx_chains = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm));
+	cfg.rx_chains = cpu_to_le32(iwl_mvm_scan_rx_ant(mvm));
+
+	IWL_DEBUG_SCAN(mvm, "Sending UMAC scan config\n");
+
+	return iwl_mvm_send_cmd(mvm, &cmd);
+}
+
 static int iwl_mvm_scan_uid_by_status(struct iwl_mvm *mvm, int status)
 {
 	int i;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 0bedba4c61f2..b3768d5d852a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -1482,6 +1482,13 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm,
 					    mvm_sta->sta_id, i);
 			txq_id = iwl_mvm_tvqm_enable_txq(mvm, mvm_sta->sta_id,
 							 i, wdg);
+			/*
+			 * on failures, just set it to IWL_MVM_INVALID_QUEUE
+			 * to try again later, we have no other good way of
+			 * failing here
+			 */
+			if (txq_id < 0)
+				txq_id = IWL_MVM_INVALID_QUEUE;
 			tid_data->txq_id = txq_id;
 
 			/*
@@ -1950,30 +1957,73 @@ void iwl_mvm_dealloc_int_sta(struct iwl_mvm *mvm, struct iwl_mvm_int_sta *sta)
 	sta->sta_id = IWL_MVM_INVALID_STA;
 }
 
-static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 *queue,
+static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 queue,
 					  u8 sta_id, u8 fifo)
 {
 	unsigned int wdg_timeout = iwlmvm_mod_params.tfd_q_hang_detect ?
 		mvm->trans->trans_cfg->base_params->wd_timeout :
 		IWL_WATCHDOG_DISABLED;
+	struct iwl_trans_txq_scd_cfg cfg = {
+		.fifo = fifo,
+		.sta_id = sta_id,
+		.tid = IWL_MAX_TID_COUNT,
+		.aggregate = false,
+		.frame_limit = IWL_FRAME_LIMIT,
+	};
+
+	WARN_ON(iwl_mvm_has_new_tx_api(mvm));
+
+	iwl_mvm_enable_txq(mvm, NULL, queue, 0, &cfg, wdg_timeout);
+}
+
+static int iwl_mvm_enable_aux_snif_queue_tvqm(struct iwl_mvm *mvm, u8 sta_id)
+{
+	unsigned int wdg_timeout = iwlmvm_mod_params.tfd_q_hang_detect ?
+		mvm->trans->trans_cfg->base_params->wd_timeout :
+		IWL_WATCHDOG_DISABLED;
+
+	WARN_ON(!iwl_mvm_has_new_tx_api(mvm));
+
+	return iwl_mvm_tvqm_enable_txq(mvm, sta_id, IWL_MAX_TID_COUNT,
+				       wdg_timeout);
+}
 
+static int iwl_mvm_add_int_sta_with_queue(struct iwl_mvm *mvm, int macidx,
+					  int maccolor,
+					  struct iwl_mvm_int_sta *sta,
+					  u16 *queue, int fifo)
+{
+	int ret;
+
+	/* Map queue to fifo - needs to happen before adding station */
+	if (!iwl_mvm_has_new_tx_api(mvm))
+		iwl_mvm_enable_aux_snif_queue(mvm, *queue, sta->sta_id, fifo);
+
+	ret = iwl_mvm_add_int_sta_common(mvm, sta, NULL, macidx, maccolor);
+	if (ret) {
+		if (!iwl_mvm_has_new_tx_api(mvm))
+			iwl_mvm_disable_txq(mvm, NULL, *queue,
+					    IWL_MAX_TID_COUNT, 0);
+		return ret;
+	}
+
+	/*
+	 * For 22000 firmware and on we cannot add queue to a station unknown
+	 * to firmware so enable queue here - after the station was added
+	 */
 	if (iwl_mvm_has_new_tx_api(mvm)) {
-		int tvqm_queue =
-			iwl_mvm_tvqm_enable_txq(mvm, sta_id,
-						IWL_MAX_TID_COUNT,
-						wdg_timeout);
-		*queue = tvqm_queue;
-	} else {
-		struct iwl_trans_txq_scd_cfg cfg = {
-			.fifo = fifo,
-			.sta_id = sta_id,
-			.tid = IWL_MAX_TID_COUNT,
-			.aggregate = false,
-			.frame_limit = IWL_FRAME_LIMIT,
-		};
+		int txq;
 
-		iwl_mvm_enable_txq(mvm, NULL, *queue, 0, &cfg, wdg_timeout);
+		txq = iwl_mvm_enable_aux_snif_queue_tvqm(mvm, sta->sta_id);
+		if (txq < 0) {
+			iwl_mvm_rm_sta_common(mvm, sta->sta_id);
+			return txq;
+		}
+
+		*queue = txq;
 	}
+
+	return 0;
 }
 
 int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm)
@@ -1989,59 +2039,26 @@ int iwl_mvm_add_aux_sta(struct iwl_mvm *mvm)
 	if (ret)
 		return ret;
 
-	/* Map Aux queue to fifo - needs to happen before adding Aux station */
-	if (!iwl_mvm_has_new_tx_api(mvm))
-		iwl_mvm_enable_aux_snif_queue(mvm, &mvm->aux_queue,
-					      mvm->aux_sta.sta_id,
-					      IWL_MVM_TX_FIFO_MCAST);
-
-	ret = iwl_mvm_add_int_sta_common(mvm, &mvm->aux_sta, NULL,
-					 MAC_INDEX_AUX, 0);
+	ret = iwl_mvm_add_int_sta_with_queue(mvm, MAC_INDEX_AUX, 0,
+					     &mvm->aux_sta, &mvm->aux_queue,
+					     IWL_MVM_TX_FIFO_MCAST);
 	if (ret) {
 		iwl_mvm_dealloc_int_sta(mvm, &mvm->aux_sta);
 		return ret;
 	}
 
-	/*
-	 * For 22000 firmware and on we cannot add queue to a station unknown
-	 * to firmware so enable queue here - after the station was added
-	 */
-	if (iwl_mvm_has_new_tx_api(mvm))
-		iwl_mvm_enable_aux_snif_queue(mvm, &mvm->aux_queue,
-					      mvm->aux_sta.sta_id,
-					      IWL_MVM_TX_FIFO_MCAST);
-
 	return 0;
 }
 
 int iwl_mvm_add_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 {
 	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
 
-	/* Map snif queue to fifo - must happen before adding snif station */
-	if (!iwl_mvm_has_new_tx_api(mvm))
-		iwl_mvm_enable_aux_snif_queue(mvm, &mvm->snif_queue,
-					      mvm->snif_sta.sta_id,
+	return iwl_mvm_add_int_sta_with_queue(mvm, mvmvif->id, mvmvif->color,
+					      &mvm->snif_sta, &mvm->snif_queue,
 					      IWL_MVM_TX_FIFO_BE);
-
-	ret = iwl_mvm_add_int_sta_common(mvm, &mvm->snif_sta, vif->addr,
-					 mvmvif->id, 0);
-	if (ret)
-		return ret;
-
-	/*
-	 * For 22000 firmware and on we cannot add queue to a station unknown
-	 * to firmware so enable queue here - after the station was added
-	 */
-	if (iwl_mvm_has_new_tx_api(mvm))
-		iwl_mvm_enable_aux_snif_queue(mvm, &mvm->snif_queue,
-					      mvm->snif_sta.sta_id,
-					      IWL_MVM_TX_FIFO_BE);
-
-	return 0;
 }
 
 int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
@@ -2133,6 +2150,10 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		queue = iwl_mvm_tvqm_enable_txq(mvm, bsta->sta_id,
 						IWL_MAX_TID_COUNT,
 						wdg_timeout);
+		if (queue < 0) {
+			iwl_mvm_rm_sta_common(mvm, bsta->sta_id);
+			return queue;
+		}
 
 		if (vif->type == NL80211_IFTYPE_AP ||
 		    vif->type == NL80211_IFTYPE_ADHOC)
@@ -2307,10 +2328,8 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 	}
 	ret = iwl_mvm_add_int_sta_common(mvm, msta, maddr,
 					 mvmvif->id, mvmvif->color);
-	if (ret) {
-		iwl_mvm_dealloc_int_sta(mvm, msta);
-		return ret;
-	}
+	if (ret)
+		goto err;
 
 	/*
 	 * Enable cab queue after the ADD_STA command is sent.
@@ -2323,6 +2342,10 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 		int queue = iwl_mvm_tvqm_enable_txq(mvm, msta->sta_id,
 						    0,
 						    timeout);
+		if (queue < 0) {
+			ret = queue;
+			goto err;
+		}
 		mvmvif->cab_queue = queue;
 	} else if (!fw_has_api(&mvm->fw->ucode_capa,
 			       IWL_UCODE_TLV_API_STA_TYPE))
@@ -2330,6 +2353,9 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif)
 				   timeout);
 
 	return 0;
+err:
+	iwl_mvm_dealloc_int_sta(mvm, msta);
+	return ret;
 }
 
 static int __iwl_mvm_remove_sta_key(struct iwl_mvm *mvm, u8 sta_id,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 6f4bb7ce71a5..040cec17d3ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -573,20 +573,20 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2526, 0x0034, iwl9560_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0038, iwl9560_2ac_160_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x003C, iwl9560_2ac_160_cfg)},
-	{IWL_PCI_DEVICE(0x2526, 0x0060, iwl9460_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2526, 0x0064, iwl9460_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2526, 0x00A0, iwl9460_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2526, 0x00A4, iwl9460_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x2526, 0x0060, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x0064, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x00A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x00A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x0210, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0214, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0230, iwl9560_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0234, iwl9560_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x0238, iwl9560_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x023C, iwl9560_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2526, 0x0260, iwl9460_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x2526, 0x0260, iwl9461_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x0264, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2526, 0x02A0, iwl9460_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2526, 0x02A4, iwl9460_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x2526, 0x02A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x2526, 0x02A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x1010, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x1030, iwl9560_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x1210, iwl9260_2ac_cfg)},
@@ -603,7 +603,7 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2526, 0x401C, iwl9260_2ac_160_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x4030, iwl9560_2ac_160_cfg)},
 	{IWL_PCI_DEVICE(0x2526, 0x4034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)},
 	{IWL_PCI_DEVICE(0x2526, 0x6010, iwl9260_2ac_160_cfg)},
@@ -618,60 +618,61 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x271B, 0x0214, iwl9260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x271C, 0x0214, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x0034, iwl9560_2ac_160_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x0038, iwl9560_2ac_160_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x003C, iwl9560_2ac_160_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x0060, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x0064, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x00A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x00A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x0230, iwl9560_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x0234, iwl9560_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x0238, iwl9560_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x023C, iwl9560_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x0260, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x0264, iwl9461_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x02A0, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x02A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x1010, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_160_cfg)},
-	{IWL_PCI_DEVICE(0x2720, 0x4034, iwl9560_2ac_160_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_soc)},
-	{IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_soc)},
-
-	{IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
-	{IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
+	{IWL_PCI_DEVICE(0x2720, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x00A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0230, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0238, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x023C, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0260, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x0264, iwl9461_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x02A0, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x1030, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)},
+	{IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)},
+
+	{IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9460_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x00A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0230, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0234, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0238, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x023C, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0260, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x0264, iwl9461_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x02A0, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x02A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1010, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1030, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_soc)},
+	{IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_soc)},
 
 	{IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_160_cfg_shared_clk)},
 	{IWL_PCI_DEVICE(0x31DC, 0x0034, iwl9560_2ac_cfg_shared_clk)},
@@ -1067,11 +1068,7 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	} else if (CSR_HW_RF_ID_TYPE_CHIP_ID(iwl_trans->hw_rf_id) ==
 		   CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) &&
-		   ((cfg != &iwl_ax200_cfg_cc &&
-		     cfg != &killer1650x_2ax_cfg &&
-		     cfg != &killer1650w_2ax_cfg &&
-		     cfg != &iwl_ax201_cfg_quz_hr) ||
-		    iwl_trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) {
+		   iwl_trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) {
 		u32 hw_status;
 
 		hw_status = iwl_read_prph(iwl_trans, UMAG_GEN_HW_STATUS);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index df8455f14e4d..ca3bb4d65b00 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -57,6 +57,24 @@
 #include "internal.h"
 #include "fw/dbg.h"
 
+static int iwl_pcie_gen2_force_power_gating(struct iwl_trans *trans)
+{
+	iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG,
+			  HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE);
+	udelay(20);
+	iwl_set_bits_prph(trans, HPM_HIPM_GEN_CFG,
+			  HPM_HIPM_GEN_CFG_CR_PG_EN |
+			  HPM_HIPM_GEN_CFG_CR_SLP_EN);
+	udelay(20);
+	iwl_clear_bits_prph(trans, HPM_HIPM_GEN_CFG,
+			    HPM_HIPM_GEN_CFG_CR_FORCE_ACTIVE);
+
+	iwl_trans_sw_reset(trans);
+	iwl_clear_bit(trans, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
+
+	return 0;
+}
+
 /*
  * Start up NIC's basic functionality after it has been reset
  * (e.g. after platform boot, or shutdown via iwl_pcie_apm_stop())
@@ -92,6 +110,13 @@ int iwl_pcie_gen2_apm_init(struct iwl_trans *trans)
 
 	iwl_pcie_apm_config(trans);
 
+	if (trans->trans_cfg->device_family == IWL_DEVICE_FAMILY_22000 &&
+	    trans->cfg->integrated) {
+		ret = iwl_pcie_gen2_force_power_gating(trans);
+		if (ret)
+			return ret;
+	}
+
 	ret = iwl_finish_nic_init(trans, trans->trans_cfg);
 	if (ret)
 		return ret;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 158a3d762e55..e323e9a5999f 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -3041,30 +3041,6 @@ static void prism2_clear_set_tim_queue(local_info_t *local)
 	}
 }
 
-
-/*
- * HostAP uses two layers of net devices, where the inner
- * layer gets called all the time from the outer layer.
- * This is a natural nesting, which needs a split lock type.
- */
-static struct lock_class_key hostap_netdev_xmit_lock_key;
-static struct lock_class_key hostap_netdev_addr_lock_key;
-
-static void prism2_set_lockdep_class_one(struct net_device *dev,
-					 struct netdev_queue *txq,
-					 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &hostap_netdev_xmit_lock_key);
-}
-
-static void prism2_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock,
-			  &hostap_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, prism2_set_lockdep_class_one, NULL);
-}
-
 static struct net_device *
 prism2_init_local_data(struct prism2_helper_functions *funcs, int card_idx,
 		       struct device *sdev)
@@ -3223,7 +3199,6 @@ while (0)
 	if (ret >= 0)
 		ret = register_netdevice(dev);
 
-	prism2_set_lockdep_class(dev);
 	rtnl_unlock();
 	if (ret < 0) {
 		printk(KERN_WARNING "%s: register netdevice failed!\n",
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 4d03596e891f..d7a1ddc9e407 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -8,6 +8,8 @@ mt76-y := \
 	mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o \
 	tx.o agg-rx.o mcu.o
 
+mt76-$(CONFIG_PCI) += pci.o
+
 mt76-usb-y := usb.o usb_trace.o
 
 CFLAGS_trace.o := -I$(src)
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index c747eb24581c..8f69d00bd940 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -53,8 +53,10 @@ mt76_dma_add_buf(struct mt76_dev *dev, struct mt76_queue *q,
 	u32 ctrl;
 	int i, idx = -1;
 
-	if (txwi)
+	if (txwi) {
 		q->entry[q->head].txwi = DMA_DUMMY_DATA;
+		q->entry[q->head].skip_buf0 = true;
+	}
 
 	for (i = 0; i < nbufs; i += 2, buf += 2) {
 		u32 buf0 = buf[0].addr, buf1 = 0;
@@ -97,7 +99,7 @@ mt76_dma_tx_cleanup_idx(struct mt76_dev *dev, struct mt76_queue *q, int idx,
 	__le32 __ctrl = READ_ONCE(q->desc[idx].ctrl);
 	u32 ctrl = le32_to_cpu(__ctrl);
 
-	if (!e->txwi || !e->skb) {
+	if (!e->skip_buf0) {
 		__le32 addr = READ_ONCE(q->desc[idx].buf0);
 		u32 len = FIELD_GET(MT_DMA_CTL_SD_LEN0, ctrl);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 570c159515a0..8aec7ccf2d79 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -93,8 +93,9 @@ struct mt76_queue_entry {
 		struct urb *urb;
 	};
 	enum mt76_txq_id qid;
-	bool schedule;
-	bool done;
+	bool skip_buf0:1;
+	bool schedule:1;
+	bool done:1;
 };
 
 struct mt76_queue_regs {
@@ -578,6 +579,7 @@ bool __mt76_poll_msec(struct mt76_dev *dev, u32 offset, u32 mask, u32 val,
 #define mt76_poll_msec(dev, ...) __mt76_poll_msec(&((dev)->mt76), __VA_ARGS__)
 
 void mt76_mmio_init(struct mt76_dev *dev, void __iomem *regs);
+void mt76_pci_disable_aspm(struct pci_dev *pdev);
 
 static inline u16 mt76_chip(struct mt76_dev *dev)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index 73c3104f8858..cf611d1b817c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -81,6 +81,8 @@ mt76pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* RG_SSUSB_CDR_BR_PE1D = 0x3 */
 	mt76_rmw_field(dev, 0x15c58, 0x3 << 6, 0x3);
 
+	mt76_pci_disable_aspm(pdev);
+
 	return 0;
 
 error:
diff --git a/drivers/net/wireless/mediatek/mt76/pci.c b/drivers/net/wireless/mediatek/mt76/pci.c
new file mode 100644
index 000000000000..04c5a692bc85
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/pci.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: ISC
+/*
+ * Copyright (C) 2019 Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/pci.h>
+
+void mt76_pci_disable_aspm(struct pci_dev *pdev)
+{
+	struct pci_dev *parent = pdev->bus->self;
+	u16 aspm_conf, parent_aspm_conf = 0;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKCTL, &aspm_conf);
+	aspm_conf &= PCI_EXP_LNKCTL_ASPMC;
+	if (parent) {
+		pcie_capability_read_word(parent, PCI_EXP_LNKCTL,
+					  &parent_aspm_conf);
+		parent_aspm_conf &= PCI_EXP_LNKCTL_ASPMC;
+	}
+
+	if (!aspm_conf && (!parent || !parent_aspm_conf)) {
+		/* aspm already disabled */
+		return;
+	}
+
+	dev_info(&pdev->dev, "disabling ASPM %s %s\n",
+		 (aspm_conf & PCI_EXP_LNKCTL_ASPM_L0S) ? "L0s" : "",
+		 (aspm_conf & PCI_EXP_LNKCTL_ASPM_L1) ? "L1" : "");
+
+	if (IS_ENABLED(CONFIG_PCIEASPM)) {
+		int err;
+
+		err = pci_disable_link_state(pdev, aspm_conf);
+		if (!err)
+			return;
+	}
+
+	/* both device and parent should have the same ASPM setting.
+	 * disable ASPM in downstream component first and then upstream.
+	 */
+	pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, aspm_conf);
+	if (parent)
+		pcie_capability_clear_word(parent, PCI_EXP_LNKCTL,
+					   aspm_conf);
+}
+EXPORT_SYMBOL_GPL(mt76_pci_disable_aspm);
diff --git a/drivers/net/wireless/realtek/rtlwifi/pci.c b/drivers/net/wireless/realtek/rtlwifi/pci.c
index 6087ec7a90a6..f88d26535978 100644
--- a/drivers/net/wireless/realtek/rtlwifi/pci.c
+++ b/drivers/net/wireless/realtek/rtlwifi/pci.c
@@ -822,7 +822,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 		hdr = rtl_get_hdr(skb);
 		fc = rtl_get_fc(skb);
 
-		if (!stats.crc && !stats.hwerror) {
+		if (!stats.crc && !stats.hwerror && (skb->len > FCS_LEN)) {
 			memcpy(IEEE80211_SKB_RXCB(skb), &rx_status,
 			       sizeof(rx_status));
 
@@ -859,6 +859,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
 				_rtl_pci_rx_to_mac80211(hw, skb, rx_status);
 			}
 		} else {
+			/* drop packets with errors or those too short */
 			dev_kfree_skb_any(skb);
 		}
 new_trx_end:
diff --git a/drivers/net/wireless/realtek/rtlwifi/ps.c b/drivers/net/wireless/realtek/rtlwifi/ps.c
index 70f04c2f5b17..fff8dda14023 100644
--- a/drivers/net/wireless/realtek/rtlwifi/ps.c
+++ b/drivers/net/wireless/realtek/rtlwifi/ps.c
@@ -754,6 +754,9 @@ static void rtl_p2p_noa_ie(struct ieee80211_hw *hw, void *data,
 				return;
 			} else {
 				noa_num = (noa_len - 2) / 13;
+				if (noa_num > P2P_MAX_NOA_NUM)
+					noa_num = P2P_MAX_NOA_NUM;
+
 			}
 			noa_index = ie[3];
 			if (rtlpriv->psc.p2p_ps_info.p2p_ps_mode ==
@@ -848,6 +851,9 @@ static void rtl_p2p_action_ie(struct ieee80211_hw *hw, void *data,
 				return;
 			} else {
 				noa_num = (noa_len - 2) / 13;
+				if (noa_num > P2P_MAX_NOA_NUM)
+					noa_num = P2P_MAX_NOA_NUM;
+
 			}
 			noa_index = ie[3];
 			if (rtlpriv->psc.p2p_ps_info.p2p_ps_mode ==
diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c
index be92e1220284..7997cc6de334 100644
--- a/drivers/net/wireless/virt_wifi.c
+++ b/drivers/net/wireless/virt_wifi.c
@@ -548,6 +548,7 @@ static int virt_wifi_newlink(struct net *src_net, struct net_device *dev,
 	priv->is_connected = false;
 	priv->is_up = false;
 	INIT_DELAYED_WORK(&priv->connect, virt_wifi_connect_complete);
+	__module_get(THIS_MODULE);
 
 	return 0;
 unregister_netdev:
@@ -578,6 +579,7 @@ static void virt_wifi_dellink(struct net_device *dev,
 	netdev_upper_dev_unlink(priv->lowerdev, dev);
 
 	unregister_netdevice_queue(dev, head);
+	module_put(THIS_MODULE);
 
 	/* Deleting the wiphy is handled in the module destructor. */
 }
@@ -590,6 +592,42 @@ static struct rtnl_link_ops virt_wifi_link_ops = {
 	.priv_size	= sizeof(struct virt_wifi_netdev_priv),
 };
 
+static bool netif_is_virt_wifi_dev(const struct net_device *dev)
+{
+	return rcu_access_pointer(dev->rx_handler) == virt_wifi_rx_handler;
+}
+
+static int virt_wifi_event(struct notifier_block *this, unsigned long event,
+			   void *ptr)
+{
+	struct net_device *lower_dev = netdev_notifier_info_to_dev(ptr);
+	struct virt_wifi_netdev_priv *priv;
+	struct net_device *upper_dev;
+	LIST_HEAD(list_kill);
+
+	if (!netif_is_virt_wifi_dev(lower_dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		priv = rtnl_dereference(lower_dev->rx_handler_data);
+		if (!priv)
+			return NOTIFY_DONE;
+
+		upper_dev = priv->upperdev;
+
+		upper_dev->rtnl_link_ops->dellink(upper_dev, &list_kill);
+		unregister_netdevice_many(&list_kill);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block virt_wifi_notifier = {
+	.notifier_call = virt_wifi_event,
+};
+
 /* Acquires and releases the rtnl lock. */
 static int __init virt_wifi_init_module(void)
 {
@@ -598,14 +636,25 @@ static int __init virt_wifi_init_module(void)
 	/* Guaranteed to be locallly-administered and not multicast. */
 	eth_random_addr(fake_router_bssid);
 
+	err = register_netdevice_notifier(&virt_wifi_notifier);
+	if (err)
+		return err;
+
+	err = -ENOMEM;
 	common_wiphy = virt_wifi_make_wiphy();
 	if (!common_wiphy)
-		return -ENOMEM;
+		goto notifier;
 
 	err = rtnl_link_register(&virt_wifi_link_ops);
 	if (err)
-		virt_wifi_destroy_wiphy(common_wiphy);
+		goto destroy_wiphy;
 
+	return 0;
+
+destroy_wiphy:
+	virt_wifi_destroy_wiphy(common_wiphy);
+notifier:
+	unregister_netdevice_notifier(&virt_wifi_notifier);
 	return err;
 }
 
@@ -615,6 +664,7 @@ static void __exit virt_wifi_cleanup_module(void)
 	/* Will delete any devices that depend on the wiphy. */
 	rtnl_link_unregister(&virt_wifi_link_ops);
 	virt_wifi_destroy_wiphy(common_wiphy);
+	unregister_netdevice_notifier(&virt_wifi_notifier);
 }
 
 module_init(virt_wifi_init_module);
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 1cd113c8d7cb..ad0abb1f0bae 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -259,7 +259,7 @@ static void fdp_nci_i2c_read_device_properties(struct device *dev,
 						  *fw_vsc_cfg, len);
 
 		if (r) {
-			devm_kfree(dev, fw_vsc_cfg);
+			devm_kfree(dev, *fw_vsc_cfg);
 			goto vsc_read_err;
 		}
 	} else {
diff --git a/drivers/nfc/st21nfca/core.c b/drivers/nfc/st21nfca/core.c
index f9ac176cf257..2ce17932a073 100644
--- a/drivers/nfc/st21nfca/core.c
+++ b/drivers/nfc/st21nfca/core.c
@@ -708,6 +708,7 @@ static int st21nfca_hci_complete_target_discovered(struct nfc_hci_dev *hdev,
 							NFC_PROTO_FELICA_MASK;
 		} else {
 			kfree_skb(nfcid_skb);
+			nfcid_skb = NULL;
 			/* P2P in type A */
 			r = nfc_hci_get_param(hdev, ST21NFCA_RF_READER_F_GATE,
 					ST21NFCA_RF_READER_F_NFCID1,
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 30de7efef003..e0f064dcbd02 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -158,9 +158,11 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 	struct nvme_ns *ns;
 
 	mutex_lock(&ctrl->scan_lock);
+	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		if (nvme_mpath_clear_current_path(ns))
 			kblockd_schedule_work(&ns->head->requeue_work);
+	up_read(&ctrl->namespaces_rwsem);
 	mutex_unlock(&ctrl->scan_lock);
 }
 
@@ -522,14 +524,13 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	return 0;
 }
 
-static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
+static int nvme_read_ana_log(struct nvme_ctrl *ctrl)
 {
 	u32 nr_change_groups = 0;
 	int error;
 
 	mutex_lock(&ctrl->ana_lock);
-	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
-			groups_only ? NVME_ANA_LOG_RGO : 0,
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA, 0,
 			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
 	if (error) {
 		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
@@ -565,7 +566,7 @@ static void nvme_ana_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
 
-	nvme_read_ana_log(ctrl, false);
+	nvme_read_ana_log(ctrl);
 }
 
 static void nvme_anatt_timeout(struct timer_list *t)
@@ -715,7 +716,7 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		goto out;
 	}
 
-	error = nvme_read_ana_log(ctrl, true);
+	error = nvme_read_ana_log(ctrl);
 	if (error)
 		goto out_free_ana_log_buf;
 	return 0;
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index f19a28b4e997..cb4c3000a57e 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -2133,8 +2133,16 @@ err_unreg_client:
 
 static void __exit nvme_rdma_cleanup_module(void)
 {
+	struct nvme_rdma_ctrl *ctrl;
+
 	nvmf_unregister_transport(&nvme_rdma_transport);
 	ib_unregister_client(&nvme_rdma_ib_client);
+
+	mutex_lock(&nvme_rdma_ctrl_mutex);
+	list_for_each_entry(ctrl, &nvme_rdma_ctrl_list, list)
+		nvme_delete_ctrl(&ctrl->ctrl);
+	mutex_unlock(&nvme_rdma_ctrl_mutex);
+	flush_workqueue(nvme_delete_wq);
 }
 
 module_init(nvme_rdma_init_module);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 770dbcbc999e..7544be84ab35 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2219,7 +2219,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx)
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;
 
-	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue))
+	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
 		sk_busy_loop(sk, true);
 	nvme_tcp_try_recv(queue);
 	return queue->nr_cqe;
diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 7989703b883c..6bd610ee2cd7 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -324,8 +324,10 @@ int of_reserved_mem_device_init_by_idx(struct device *dev,
 	if (!target)
 		return -ENODEV;
 
-	if (!of_device_is_available(target))
+	if (!of_device_is_available(target)) {
+		of_node_put(target);
 		return 0;
+	}
 
 	rmem = __find_rmem(target);
 	of_node_put(target);
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 480a21e2ed39..92e895d86458 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -1207,6 +1207,7 @@ static int __init unittest_data_add(void)
 	of_fdt_unflatten_tree(unittest_data, NULL, &unittest_data_node);
 	if (!unittest_data_node) {
 		pr_warn("%s: No tree to attach; not running tests\n", __func__);
+		kfree(unittest_data);
 		return -ENODATA;
 	}
 
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 3b7ffd0234e9..9ff0538ee83a 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -1626,12 +1626,6 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 			goto free_regulators;
 		}
 
-		ret = regulator_enable(reg);
-		if (ret < 0) {
-			regulator_put(reg);
-			goto free_regulators;
-		}
-
 		opp_table->regulators[i] = reg;
 	}
 
@@ -1645,10 +1639,8 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 	return opp_table;
 
 free_regulators:
-	while (i--) {
-		regulator_disable(opp_table->regulators[i]);
-		regulator_put(opp_table->regulators[i]);
-	}
+	while (i != 0)
+		regulator_put(opp_table->regulators[--i]);
 
 	kfree(opp_table->regulators);
 	opp_table->regulators = NULL;
@@ -1674,10 +1666,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	for (i = opp_table->regulator_count - 1; i >= 0; i--) {
-		regulator_disable(opp_table->regulators[i]);
+	for (i = opp_table->regulator_count - 1; i >= 0; i--)
 		regulator_put(opp_table->regulators[i]);
-	}
 
 	_free_set_opp_data(opp_table);
 
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 1813f5ad5fa2..1cbb58240b80 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -77,8 +77,6 @@ static struct dev_pm_opp *_find_opp_of_np(struct opp_table *opp_table,
 {
 	struct dev_pm_opp *opp;
 
-	lockdep_assert_held(&opp_table_lock);
-
 	mutex_lock(&opp_table->lock);
 
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
@@ -665,6 +663,13 @@ static int _of_add_opp_table_v2(struct device *dev, struct opp_table *opp_table)
 		return 0;
 	}
 
+	/*
+	 * Re-initialize list_kref every time we add static OPPs to the OPP
+	 * table as the reference count may be 0 after the last tie static OPPs
+	 * were removed.
+	 */
+	kref_init(&opp_table->list_kref);
+
 	/* We have opp-table node now, iterate over it and add OPPs */
 	for_each_available_child_of_node(opp_table->np, np) {
 		opp = _opp_add_static_v2(opp_table, dev, np);
diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
index 648ddb7f038a..c6800d220920 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed-g6.c
@@ -87,7 +87,7 @@ FUNC_GROUP_DECL(MACLINK3, L23);
 
 #define K25 7
 SIG_EXPR_LIST_DECL_SESG(K25, MACLINK4, MACLINK4, SIG_DESC_SET(SCU410, 7));
-SIG_EXPR_LIST_DECL_SESG(K25, SDA14, SDA14, SIG_DESC_SET(SCU4B0, 7));
+SIG_EXPR_LIST_DECL_SESG(K25, SDA14, I2C14, SIG_DESC_SET(SCU4B0, 7));
 PIN_DECL_2(K25, GPIOA7, MACLINK4, SDA14);
 FUNC_GROUP_DECL(MACLINK4, K25);
 
@@ -1262,13 +1262,13 @@ GROUP_DECL(SPI1, AB11, AC11, AA11);
 #define AD11 206
 SIG_EXPR_LIST_DECL_SEMG(AD11, SPI1DQ2, QSPI1, SPI1, SIG_DESC_SET(SCU438, 14));
 SIG_EXPR_LIST_DECL_SEMG(AD11, TXD13, UART13G1, UART13,
-			SIG_DESC_SET(SCU438, 14));
+			SIG_DESC_CLEAR(SCU4B8, 2), SIG_DESC_SET(SCU4D8, 14));
 PIN_DECL_2(AD11, GPIOZ6, SPI1DQ2, TXD13);
 
 #define AF10 207
 SIG_EXPR_LIST_DECL_SEMG(AF10, SPI1DQ3, QSPI1, SPI1, SIG_DESC_SET(SCU438, 15));
 SIG_EXPR_LIST_DECL_SEMG(AF10, RXD13, UART13G1, UART13,
-			SIG_DESC_SET(SCU438, 15));
+			SIG_DESC_CLEAR(SCU4B8, 3), SIG_DESC_SET(SCU4D8, 15));
 PIN_DECL_2(AF10, GPIOZ7, SPI1DQ3, RXD13);
 
 GROUP_DECL(QSPI1, AB11, AC11, AA11, AD11, AF10);
@@ -1440,91 +1440,85 @@ FUNC_GROUP_DECL(RGMII2, D4, C2, C1, D3, E4, F5, D2, E3, D1, F4, E2, E1);
 FUNC_GROUP_DECL(RMII2, D4, C2, C1, D3, D2, D1, F4, E2, E1);
 
 #define AB4 232
-SIG_EXPR_LIST_DECL_SESG(AB4, SD3CLK, SD3, SIG_DESC_SET(SCU400, 24));
-PIN_DECL_1(AB4, GPIO18D0, SD3CLK);
+SIG_EXPR_LIST_DECL_SEMG(AB4, EMMCCLK, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 24));
+PIN_DECL_1(AB4, GPIO18D0, EMMCCLK);
 
 #define AA4 233
-SIG_EXPR_LIST_DECL_SESG(AA4, SD3CMD, SD3, SIG_DESC_SET(SCU400, 25));
-PIN_DECL_1(AA4, GPIO18D1, SD3CMD);
+SIG_EXPR_LIST_DECL_SEMG(AA4, EMMCCMD, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 25));
+PIN_DECL_1(AA4, GPIO18D1, EMMCCMD);
 
 #define AC4 234
-SIG_EXPR_LIST_DECL_SESG(AC4, SD3DAT0, SD3, SIG_DESC_SET(SCU400, 26));
-PIN_DECL_1(AC4, GPIO18D2, SD3DAT0);
+SIG_EXPR_LIST_DECL_SEMG(AC4, EMMCDAT0, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 26));
+PIN_DECL_1(AC4, GPIO18D2, EMMCDAT0);
 
 #define AA5 235
-SIG_EXPR_LIST_DECL_SESG(AA5, SD3DAT1, SD3, SIG_DESC_SET(SCU400, 27));
-PIN_DECL_1(AA5, GPIO18D3, SD3DAT1);
+SIG_EXPR_LIST_DECL_SEMG(AA5, EMMCDAT1, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 27));
+PIN_DECL_1(AA5, GPIO18D3, EMMCDAT1);
 
 #define Y5 236
-SIG_EXPR_LIST_DECL_SESG(Y5, SD3DAT2, SD3, SIG_DESC_SET(SCU400, 28));
-PIN_DECL_1(Y5, GPIO18D4, SD3DAT2);
+SIG_EXPR_LIST_DECL_SEMG(Y5, EMMCDAT2, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 28));
+PIN_DECL_1(Y5, GPIO18D4, EMMCDAT2);
 
 #define AB5 237
-SIG_EXPR_LIST_DECL_SESG(AB5, SD3DAT3, SD3, SIG_DESC_SET(SCU400, 29));
-PIN_DECL_1(AB5, GPIO18D5, SD3DAT3);
+SIG_EXPR_LIST_DECL_SEMG(AB5, EMMCDAT3, EMMCG4, EMMC, SIG_DESC_SET(SCU400, 29));
+PIN_DECL_1(AB5, GPIO18D5, EMMCDAT3);
 
 #define AB6 238
-SIG_EXPR_LIST_DECL_SESG(AB6, SD3CD, SD3, SIG_DESC_SET(SCU400, 30));
-PIN_DECL_1(AB6, GPIO18D6, SD3CD);
+SIG_EXPR_LIST_DECL_SEMG(AB6, EMMCCD, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 30));
+PIN_DECL_1(AB6, GPIO18D6, EMMCCD);
 
 #define AC5 239
-SIG_EXPR_LIST_DECL_SESG(AC5, SD3WP, SD3, SIG_DESC_SET(SCU400, 31));
-PIN_DECL_1(AC5, GPIO18D7, SD3WP);
+SIG_EXPR_LIST_DECL_SEMG(AC5, EMMCWP, EMMCG1, EMMC, SIG_DESC_SET(SCU400, 31));
+PIN_DECL_1(AC5, GPIO18D7, EMMCWP);
 
-FUNC_GROUP_DECL(SD3, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5);
+GROUP_DECL(EMMCG1, AB4, AA4, AC4, AB6, AC5);
+GROUP_DECL(EMMCG4, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5);
 
 #define Y1 240
 SIG_EXPR_LIST_DECL_SEMG(Y1, FWSPIDCS, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3));
 SIG_EXPR_LIST_DECL_SESG(Y1, VBCS, VB, SIG_DESC_SET(SCU500, 5));
-SIG_EXPR_LIST_DECL_SESG(Y1, SD3DAT4, SD3DAT4, SIG_DESC_SET(SCU404, 0));
-PIN_DECL_3(Y1, GPIO18E0, FWSPIDCS, VBCS, SD3DAT4);
-FUNC_GROUP_DECL(SD3DAT4, Y1);
+SIG_EXPR_LIST_DECL_SEMG(Y1, EMMCDAT4, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 0));
+PIN_DECL_3(Y1, GPIO18E0, FWSPIDCS, VBCS, EMMCDAT4);
 
 #define Y2 241
 SIG_EXPR_LIST_DECL_SEMG(Y2, FWSPIDCK, FWSPID, FWSPID, SIG_DESC_SET(SCU500, 3));
 SIG_EXPR_LIST_DECL_SESG(Y2, VBCK, VB, SIG_DESC_SET(SCU500, 5));
-SIG_EXPR_LIST_DECL_SESG(Y2, SD3DAT5, SD3DAT5, SIG_DESC_SET(SCU404, 1));
-PIN_DECL_3(Y2, GPIO18E1, FWSPIDCK, VBCK, SD3DAT5);
-FUNC_GROUP_DECL(SD3DAT5, Y2);
+SIG_EXPR_LIST_DECL_SEMG(Y2, EMMCDAT5, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 1));
+PIN_DECL_3(Y2, GPIO18E1, FWSPIDCK, VBCK, EMMCDAT5);
 
 #define Y3 242
 SIG_EXPR_LIST_DECL_SEMG(Y3, FWSPIDMOSI, FWSPID, FWSPID,
 			SIG_DESC_SET(SCU500, 3));
 SIG_EXPR_LIST_DECL_SESG(Y3, VBMOSI, VB, SIG_DESC_SET(SCU500, 5));
-SIG_EXPR_LIST_DECL_SESG(Y3, SD3DAT6, SD3DAT6, SIG_DESC_SET(SCU404, 2));
-PIN_DECL_3(Y3, GPIO18E2, FWSPIDMOSI, VBMOSI, SD3DAT6);
-FUNC_GROUP_DECL(SD3DAT6, Y3);
+SIG_EXPR_LIST_DECL_SEMG(Y3, EMMCDAT6, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 2));
+PIN_DECL_3(Y3, GPIO18E2, FWSPIDMOSI, VBMOSI, EMMCDAT6);
 
 #define Y4 243
 SIG_EXPR_LIST_DECL_SEMG(Y4, FWSPIDMISO, FWSPID, FWSPID,
 			SIG_DESC_SET(SCU500, 3));
 SIG_EXPR_LIST_DECL_SESG(Y4, VBMISO, VB, SIG_DESC_SET(SCU500, 5));
-SIG_EXPR_LIST_DECL_SESG(Y4, SD3DAT7, SD3DAT7, SIG_DESC_SET(SCU404, 3));
-PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, SD3DAT7);
-FUNC_GROUP_DECL(SD3DAT7, Y4);
+SIG_EXPR_LIST_DECL_SEMG(Y4, EMMCDAT7, EMMCG8, EMMC, SIG_DESC_SET(SCU404, 3));
+PIN_DECL_3(Y4, GPIO18E3, FWSPIDMISO, VBMISO, EMMCDAT7);
 
 GROUP_DECL(FWSPID, Y1, Y2, Y3, Y4);
 GROUP_DECL(FWQSPID, Y1, Y2, Y3, Y4, AE12, AF12);
+GROUP_DECL(EMMCG8, AB4, AA4, AC4, AA5, Y5, AB5, AB6, AC5, Y1, Y2, Y3, Y4);
 FUNC_DECL_2(FWSPID, FWSPID, FWQSPID);
 FUNC_GROUP_DECL(VB, Y1, Y2, Y3, Y4);
-
+FUNC_DECL_3(EMMC, EMMCG1, EMMCG4, EMMCG8);
 /*
  * FIXME: Confirm bits and priorities are the right way around for the
  * following 4 pins
  */
 #define AF25 244
-SIG_EXPR_LIST_DECL_SEMG(AF25, I3C3SCL, I3C3, I3C3, SIG_DESC_SET(SCU438, 20),
-			SIG_DESC_SET(SCU4D8, 20));
-SIG_EXPR_LIST_DECL_SESG(AF25, FSI1CLK, FSI1, SIG_DESC_CLEAR(SCU438, 20),
-			SIG_DESC_SET(SCU4D8, 20));
+SIG_EXPR_LIST_DECL_SEMG(AF25, I3C3SCL, I3C3, I3C3, SIG_DESC_SET(SCU438, 20));
+SIG_EXPR_LIST_DECL_SESG(AF25, FSI1CLK, FSI1, SIG_DESC_SET(SCU4D8, 20));
 PIN_DECL_(AF25, SIG_EXPR_LIST_PTR(AF25, I3C3SCL),
 	  SIG_EXPR_LIST_PTR(AF25, FSI1CLK));
 
 #define AE26 245
-SIG_EXPR_LIST_DECL_SEMG(AE26, I3C3SDA, I3C3, I3C3, SIG_DESC_SET(SCU438, 21),
-			SIG_DESC_SET(SCU4D8, 21));
-SIG_EXPR_LIST_DECL_SESG(AE26, FSI1DATA, FSI1, SIG_DESC_CLEAR(SCU438, 21),
-			SIG_DESC_SET(SCU4D8, 21));
+SIG_EXPR_LIST_DECL_SEMG(AE26, I3C3SDA, I3C3, I3C3, SIG_DESC_SET(SCU438, 21));
+SIG_EXPR_LIST_DECL_SESG(AE26, FSI1DATA, FSI1, SIG_DESC_SET(SCU4D8, 21));
 PIN_DECL_(AE26, SIG_EXPR_LIST_PTR(AE26, I3C3SDA),
 	  SIG_EXPR_LIST_PTR(AE26, FSI1DATA));
 
@@ -1533,18 +1527,14 @@ FUNC_DECL_2(I3C3, HVI3C3, I3C3);
 FUNC_GROUP_DECL(FSI1, AF25, AE26);
 
 #define AE25 246
-SIG_EXPR_LIST_DECL_SEMG(AE25, I3C4SCL, I3C4, I3C4, SIG_DESC_SET(SCU438, 22),
-			SIG_DESC_SET(SCU4D8, 22));
-SIG_EXPR_LIST_DECL_SESG(AE25, FSI2CLK, FSI2, SIG_DESC_CLEAR(SCU438, 22),
-			SIG_DESC_SET(SCU4D8, 22));
+SIG_EXPR_LIST_DECL_SEMG(AE25, I3C4SCL, I3C4, I3C4, SIG_DESC_SET(SCU438, 22));
+SIG_EXPR_LIST_DECL_SESG(AE25, FSI2CLK, FSI2, SIG_DESC_SET(SCU4D8, 22));
 PIN_DECL_(AE25, SIG_EXPR_LIST_PTR(AE25, I3C4SCL),
 	  SIG_EXPR_LIST_PTR(AE25, FSI2CLK));
 
 #define AF24 247
-SIG_EXPR_LIST_DECL_SEMG(AF24, I3C4SDA, I3C4, I3C4, SIG_DESC_SET(SCU438, 23),
-			SIG_DESC_SET(SCU4D8, 23));
-SIG_EXPR_LIST_DECL_SESG(AF24, FSI2DATA, FSI2, SIG_DESC_CLEAR(SCU438, 23),
-			SIG_DESC_SET(SCU4D8, 23));
+SIG_EXPR_LIST_DECL_SEMG(AF24, I3C4SDA, I3C4, I3C4, SIG_DESC_SET(SCU438, 23));
+SIG_EXPR_LIST_DECL_SESG(AF24, FSI2DATA, FSI2, SIG_DESC_SET(SCU4D8, 23));
 PIN_DECL_(AF24, SIG_EXPR_LIST_PTR(AF24, I3C4SDA),
 	  SIG_EXPR_LIST_PTR(AF24, FSI2DATA));
 
@@ -1574,6 +1564,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(A3),
 	ASPEED_PINCTRL_PIN(AA11),
 	ASPEED_PINCTRL_PIN(AA12),
+	ASPEED_PINCTRL_PIN(AA16),
+	ASPEED_PINCTRL_PIN(AA17),
 	ASPEED_PINCTRL_PIN(AA23),
 	ASPEED_PINCTRL_PIN(AA24),
 	ASPEED_PINCTRL_PIN(AA25),
@@ -1585,6 +1577,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(AB11),
 	ASPEED_PINCTRL_PIN(AB12),
 	ASPEED_PINCTRL_PIN(AB15),
+	ASPEED_PINCTRL_PIN(AB16),
+	ASPEED_PINCTRL_PIN(AB17),
 	ASPEED_PINCTRL_PIN(AB18),
 	ASPEED_PINCTRL_PIN(AB19),
 	ASPEED_PINCTRL_PIN(AB22),
@@ -1602,6 +1596,7 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(AC11),
 	ASPEED_PINCTRL_PIN(AC12),
 	ASPEED_PINCTRL_PIN(AC15),
+	ASPEED_PINCTRL_PIN(AC16),
 	ASPEED_PINCTRL_PIN(AC17),
 	ASPEED_PINCTRL_PIN(AC18),
 	ASPEED_PINCTRL_PIN(AC19),
@@ -1619,6 +1614,7 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(AD12),
 	ASPEED_PINCTRL_PIN(AD14),
 	ASPEED_PINCTRL_PIN(AD15),
+	ASPEED_PINCTRL_PIN(AD16),
 	ASPEED_PINCTRL_PIN(AD19),
 	ASPEED_PINCTRL_PIN(AD20),
 	ASPEED_PINCTRL_PIN(AD22),
@@ -1634,8 +1630,11 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(AE12),
 	ASPEED_PINCTRL_PIN(AE14),
 	ASPEED_PINCTRL_PIN(AE15),
+	ASPEED_PINCTRL_PIN(AE16),
 	ASPEED_PINCTRL_PIN(AE18),
 	ASPEED_PINCTRL_PIN(AE19),
+	ASPEED_PINCTRL_PIN(AE25),
+	ASPEED_PINCTRL_PIN(AE26),
 	ASPEED_PINCTRL_PIN(AE7),
 	ASPEED_PINCTRL_PIN(AE8),
 	ASPEED_PINCTRL_PIN(AF10),
@@ -1643,6 +1642,8 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(AF12),
 	ASPEED_PINCTRL_PIN(AF14),
 	ASPEED_PINCTRL_PIN(AF15),
+	ASPEED_PINCTRL_PIN(AF24),
+	ASPEED_PINCTRL_PIN(AF25),
 	ASPEED_PINCTRL_PIN(AF7),
 	ASPEED_PINCTRL_PIN(AF8),
 	ASPEED_PINCTRL_PIN(AF9),
@@ -1792,17 +1793,6 @@ static struct pinctrl_pin_desc aspeed_g6_pins[ASPEED_G6_NR_PINS] = {
 	ASPEED_PINCTRL_PIN(Y3),
 	ASPEED_PINCTRL_PIN(Y4),
 	ASPEED_PINCTRL_PIN(Y5),
-	ASPEED_PINCTRL_PIN(AB16),
-	ASPEED_PINCTRL_PIN(AA17),
-	ASPEED_PINCTRL_PIN(AB17),
-	ASPEED_PINCTRL_PIN(AE16),
-	ASPEED_PINCTRL_PIN(AC16),
-	ASPEED_PINCTRL_PIN(AA16),
-	ASPEED_PINCTRL_PIN(AD16),
-	ASPEED_PINCTRL_PIN(AF25),
-	ASPEED_PINCTRL_PIN(AE26),
-	ASPEED_PINCTRL_PIN(AE25),
-	ASPEED_PINCTRL_PIN(AF24),
 };
 
 static const struct aspeed_pin_group aspeed_g6_groups[] = {
@@ -1976,11 +1966,9 @@ static const struct aspeed_pin_group aspeed_g6_groups[] = {
 	ASPEED_PINCTRL_GROUP(SALT9G1),
 	ASPEED_PINCTRL_GROUP(SD1),
 	ASPEED_PINCTRL_GROUP(SD2),
-	ASPEED_PINCTRL_GROUP(SD3),
-	ASPEED_PINCTRL_GROUP(SD3DAT4),
-	ASPEED_PINCTRL_GROUP(SD3DAT5),
-	ASPEED_PINCTRL_GROUP(SD3DAT6),
-	ASPEED_PINCTRL_GROUP(SD3DAT7),
+	ASPEED_PINCTRL_GROUP(EMMCG1),
+	ASPEED_PINCTRL_GROUP(EMMCG4),
+	ASPEED_PINCTRL_GROUP(EMMCG8),
 	ASPEED_PINCTRL_GROUP(SGPM1),
 	ASPEED_PINCTRL_GROUP(SGPS1),
 	ASPEED_PINCTRL_GROUP(SIOONCTRL),
@@ -2059,6 +2047,7 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = {
 	ASPEED_PINCTRL_FUNC(ADC8),
 	ASPEED_PINCTRL_FUNC(ADC9),
 	ASPEED_PINCTRL_FUNC(BMCINT),
+	ASPEED_PINCTRL_FUNC(EMMC),
 	ASPEED_PINCTRL_FUNC(ESPI),
 	ASPEED_PINCTRL_FUNC(ESPIALT),
 	ASPEED_PINCTRL_FUNC(FSI1),
@@ -2191,11 +2180,6 @@ static const struct aspeed_pin_function aspeed_g6_functions[] = {
 	ASPEED_PINCTRL_FUNC(SALT9),
 	ASPEED_PINCTRL_FUNC(SD1),
 	ASPEED_PINCTRL_FUNC(SD2),
-	ASPEED_PINCTRL_FUNC(SD3),
-	ASPEED_PINCTRL_FUNC(SD3DAT4),
-	ASPEED_PINCTRL_FUNC(SD3DAT5),
-	ASPEED_PINCTRL_FUNC(SD3DAT6),
-	ASPEED_PINCTRL_FUNC(SD3DAT7),
 	ASPEED_PINCTRL_FUNC(SGPM1),
 	ASPEED_PINCTRL_FUNC(SGPS1),
 	ASPEED_PINCTRL_FUNC(SIOONCTRL),
diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h
index a2c0d52e4f7b..140c5ce9fbc1 100644
--- a/drivers/pinctrl/aspeed/pinmux-aspeed.h
+++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h
@@ -508,7 +508,7 @@ struct aspeed_pin_desc {
  * @idx: The bit index in the register
  */
 #define SIG_DESC_SET(reg, idx) SIG_DESC_IP_BIT(ASPEED_IP_SCU, reg, idx, 1)
-#define SIG_DESC_CLEAR(reg, idx) SIG_DESC_IP_BIT(ASPEED_IP_SCU, reg, idx, 0)
+#define SIG_DESC_CLEAR(reg, idx) { ASPEED_IP_SCU, reg, BIT_MASK(idx), 0, 0 }
 
 #define SIG_DESC_LIST_SYM(sig, group) sig_descs_ ## sig ## _ ## group
 #define SIG_DESC_LIST_DECL(sig, group, ...) \
@@ -738,6 +738,7 @@ struct aspeed_pin_desc {
 	static const char *FUNC_SYM(func)[] = { __VA_ARGS__ }
 
 #define FUNC_DECL_2(func, one, two) FUNC_DECL_(func, #one, #two)
+#define FUNC_DECL_3(func, one, two, three) FUNC_DECL_(func, #one, #two, #three)
 
 #define FUNC_GROUP_DECL(func, ...) \
 	GROUP_DECL(func, __VA_ARGS__); \
diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
index 6f7d3a2f2e97..42f7ab383ad9 100644
--- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2014-2017 Broadcom
- *
- * 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 version 2.
- *
- * This program is distributed "as is" WITHOUT ANY WARRANTY of any
- * kind, whether express or implied; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 /*
@@ -853,7 +845,7 @@ static int iproc_gpio_probe(struct platform_device *pdev)
 
 	/* optional GPIO interrupt support */
 	irq = platform_get_irq(pdev, 0);
-	if (irq) {
+	if (irq > 0) {
 		struct irq_chip *irqc;
 		struct gpio_irq_chip *girq;
 
diff --git a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c
index 2bf6af7df7d9..9fabc451550e 100644
--- a/drivers/pinctrl/bcm/pinctrl-ns2-mux.c
+++ b/drivers/pinctrl/bcm/pinctrl-ns2-mux.c
@@ -640,8 +640,8 @@ static int ns2_pinmux_enable(struct pinctrl_dev *pctrl_dev,
 	const struct ns2_pin_function *func;
 	const struct ns2_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];
diff --git a/drivers/pinctrl/berlin/pinctrl-as370.c b/drivers/pinctrl/berlin/pinctrl-as370.c
index 44f8ccdbeeff..9dfdc275ee33 100644
--- a/drivers/pinctrl/berlin/pinctrl-as370.c
+++ b/drivers/pinctrl/berlin/pinctrl-as370.c
@@ -43,7 +43,7 @@ static const struct berlin_desc_group as370_soc_pinctrl_groups[] = {
 			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO5 */
 			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO3 */
 			BERLIN_PINCTRL_FUNCTION(0x2, "pwm"), /* PWM5 */
-			BERLIN_PINCTRL_FUNCTION(0x3, "spififib"), /* SPDIFIB */
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifib"), /* SPDIFIB */
 			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
 			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG5 */
 	BERLIN_PINCTRL_GROUP("I2S1_MCLK", 0x0, 0x3, 0x12,
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index aae51c507f59..2c419fa5d1c1 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -147,6 +147,7 @@ struct chv_pin_context {
  * @pctldesc: Pin controller description
  * @pctldev: Pointer to the pin controller device
  * @chip: GPIO chip in this pin controller
+ * @irqchip: IRQ chip in this pin controller
  * @regs: MMIO registers
  * @intr_lines: Stores mapping between 16 HW interrupt wires and GPIO
  *		offset (in GPIO number space)
@@ -162,6 +163,7 @@ struct chv_pinctrl {
 	struct pinctrl_desc pctldesc;
 	struct pinctrl_dev *pctldev;
 	struct gpio_chip chip;
+	struct irq_chip irqchip;
 	void __iomem *regs;
 	unsigned intr_lines[16];
 	const struct chv_community *community;
@@ -1466,16 +1468,6 @@ static int chv_gpio_irq_type(struct irq_data *d, unsigned int type)
 	return 0;
 }
 
-static struct irq_chip chv_gpio_irqchip = {
-	.name = "chv-gpio",
-	.irq_startup = chv_gpio_irq_startup,
-	.irq_ack = chv_gpio_irq_ack,
-	.irq_mask = chv_gpio_irq_mask,
-	.irq_unmask = chv_gpio_irq_unmask,
-	.irq_set_type = chv_gpio_irq_type,
-	.flags = IRQCHIP_SKIP_SET_WAKE,
-};
-
 static void chv_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
@@ -1513,7 +1505,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = {
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
 		},
 	},
 	{
@@ -1521,7 +1512,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = {
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
 		},
 	},
 	{
@@ -1529,7 +1519,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = {
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
 		},
 	},
 	{
@@ -1537,7 +1526,6 @@ static const struct dmi_system_id chv_no_valid_mask[] = {
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Celes"),
-			DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"),
 		},
 	},
 	{}
@@ -1563,7 +1551,7 @@ static void chv_init_irq_valid_mask(struct gpio_chip *chip,
 		intsel >>= CHV_PADCTRL0_INTSEL_SHIFT;
 
 		if (intsel >= community->nirqs)
-			clear_bit(i, valid_mask);
+			clear_bit(desc->number, valid_mask);
 	}
 }
 
@@ -1629,7 +1617,15 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 		}
 	}
 
-	ret = gpiochip_irqchip_add(chip, &chv_gpio_irqchip, 0,
+	pctrl->irqchip.name = "chv-gpio";
+	pctrl->irqchip.irq_startup = chv_gpio_irq_startup;
+	pctrl->irqchip.irq_ack = chv_gpio_irq_ack;
+	pctrl->irqchip.irq_mask = chv_gpio_irq_mask;
+	pctrl->irqchip.irq_unmask = chv_gpio_irq_unmask;
+	pctrl->irqchip.irq_set_type = chv_gpio_irq_type;
+	pctrl->irqchip.flags = IRQCHIP_SKIP_SET_WAKE;
+
+	ret = gpiochip_irqchip_add(chip, &pctrl->irqchip, 0,
 				   handle_bad_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to add IRQ chip\n");
@@ -1646,7 +1642,7 @@ static int chv_gpio_probe(struct chv_pinctrl *pctrl, int irq)
 		}
 	}
 
-	gpiochip_set_chained_irqchip(chip, &chv_gpio_irqchip, irq,
+	gpiochip_set_chained_irqchip(chip, &pctrl->irqchip, irq,
 				     chv_gpio_irq_handler);
 	return 0;
 }
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 1f13bcd0e4e1..83981ad66a71 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -52,6 +52,7 @@
 #define PADCFG0_GPIROUTNMI		BIT(17)
 #define PADCFG0_PMODE_SHIFT		10
 #define PADCFG0_PMODE_MASK		GENMASK(13, 10)
+#define PADCFG0_PMODE_GPIO		0
 #define PADCFG0_GPIORXDIS		BIT(9)
 #define PADCFG0_GPIOTXDIS		BIT(8)
 #define PADCFG0_GPIORXSTATE		BIT(1)
@@ -96,6 +97,7 @@ struct intel_pinctrl_context {
  * @pctldesc: Pin controller description
  * @pctldev: Pointer to the pin controller device
  * @chip: GPIO chip in this pin controller
+ * @irqchip: IRQ chip in this pin controller
  * @soc: SoC/PCH specific pin configuration data
  * @communities: All communities in this pin controller
  * @ncommunities: Number of communities in this pin controller
@@ -108,6 +110,7 @@ struct intel_pinctrl {
 	struct pinctrl_desc pctldesc;
 	struct pinctrl_dev *pctldev;
 	struct gpio_chip chip;
+	struct irq_chip irqchip;
 	const struct intel_pinctrl_soc_data *soc;
 	struct intel_community *communities;
 	size_t ncommunities;
@@ -330,7 +333,7 @@ static void intel_pin_dbg_show(struct pinctrl_dev *pctldev, struct seq_file *s,
 	cfg1 = readl(intel_get_padcfg(pctrl, pin, PADCFG1));
 
 	mode = (cfg0 & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT;
-	if (!mode)
+	if (mode == PADCFG0_PMODE_GPIO)
 		seq_puts(s, "GPIO ");
 	else
 		seq_printf(s, "mode %d ", mode);
@@ -456,6 +459,11 @@ static void __intel_gpio_set_direction(void __iomem *padcfg0, bool input)
 	writel(value, padcfg0);
 }
 
+static int intel_gpio_get_gpio_mode(void __iomem *padcfg0)
+{
+	return (readl(padcfg0) & PADCFG0_PMODE_MASK) >> PADCFG0_PMODE_SHIFT;
+}
+
 static void intel_gpio_set_gpio_mode(void __iomem *padcfg0)
 {
 	u32 value;
@@ -489,7 +497,20 @@ static int intel_gpio_request_enable(struct pinctrl_dev *pctldev,
 	}
 
 	padcfg0 = intel_get_padcfg(pctrl, pin, PADCFG0);
+
+	/*
+	 * If pin is already configured in GPIO mode, we assume that
+	 * firmware provides correct settings. In such case we avoid
+	 * potential glitches on the pin. Otherwise, for the pin in
+	 * alternative mode, consumer has to supply respective flags.
+	 */
+	if (intel_gpio_get_gpio_mode(padcfg0) == PADCFG0_PMODE_GPIO) {
+		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+		return 0;
+	}
+
 	intel_gpio_set_gpio_mode(padcfg0);
+
 	/* Disable TX buffer and enable RX (this will be input) */
 	__intel_gpio_set_direction(padcfg0, true);
 
@@ -1139,16 +1160,6 @@ static irqreturn_t intel_gpio_irq(int irq, void *data)
 	return ret;
 }
 
-static struct irq_chip intel_gpio_irqchip = {
-	.name = "intel-gpio",
-	.irq_ack = intel_gpio_irq_ack,
-	.irq_mask = intel_gpio_irq_mask,
-	.irq_unmask = intel_gpio_irq_unmask,
-	.irq_set_type = intel_gpio_irq_type,
-	.irq_set_wake = intel_gpio_irq_wake,
-	.flags = IRQCHIP_MASK_ON_SUSPEND,
-};
-
 static int intel_gpio_add_pin_ranges(struct intel_pinctrl *pctrl,
 				     const struct intel_community *community)
 {
@@ -1198,12 +1209,22 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq)
 
 	pctrl->chip = intel_gpio_chip;
 
+	/* Setup GPIO chip */
 	pctrl->chip.ngpio = intel_gpio_ngpio(pctrl);
 	pctrl->chip.label = dev_name(pctrl->dev);
 	pctrl->chip.parent = pctrl->dev;
 	pctrl->chip.base = -1;
 	pctrl->irq = irq;
 
+	/* Setup IRQ chip */
+	pctrl->irqchip.name = dev_name(pctrl->dev);
+	pctrl->irqchip.irq_ack = intel_gpio_irq_ack;
+	pctrl->irqchip.irq_mask = intel_gpio_irq_mask;
+	pctrl->irqchip.irq_unmask = intel_gpio_irq_unmask;
+	pctrl->irqchip.irq_set_type = intel_gpio_irq_type;
+	pctrl->irqchip.irq_set_wake = intel_gpio_irq_wake;
+	pctrl->irqchip.flags = IRQCHIP_MASK_ON_SUSPEND;
+
 	ret = devm_gpiochip_add_data(pctrl->dev, &pctrl->chip, pctrl);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to register gpiochip\n");
@@ -1233,15 +1254,14 @@ static int intel_gpio_probe(struct intel_pinctrl *pctrl, int irq)
 		return ret;
 	}
 
-	ret = gpiochip_irqchip_add(&pctrl->chip, &intel_gpio_irqchip, 0,
+	ret = gpiochip_irqchip_add(&pctrl->chip, &pctrl->irqchip, 0,
 				   handle_bad_irq, IRQ_TYPE_NONE);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to add irqchip\n");
 		return ret;
 	}
 
-	gpiochip_set_chained_irqchip(&pctrl->chip, &intel_gpio_irqchip, irq,
-				     NULL);
+	gpiochip_set_chained_irqchip(&pctrl->chip, &pctrl->irqchip, irq, NULL);
 	return 0;
 }
 
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 6462d3ca7ceb..f2f5fcd9a237 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -183,10 +183,10 @@ static struct armada_37xx_pin_group armada_37xx_nb_groups[] = {
 	PIN_GRP_EXTRA("uart2", 9, 2, BIT(1) | BIT(13) | BIT(14) | BIT(19),
 		      BIT(1) | BIT(13) | BIT(14), BIT(1) | BIT(19),
 		      18, 2, "gpio", "uart"),
-	PIN_GRP_GPIO("led0_od", 11, 1, BIT(20), "led"),
-	PIN_GRP_GPIO("led1_od", 12, 1, BIT(21), "led"),
-	PIN_GRP_GPIO("led2_od", 13, 1, BIT(22), "led"),
-	PIN_GRP_GPIO("led3_od", 14, 1, BIT(23), "led"),
+	PIN_GRP_GPIO_2("led0_od", 11, 1, BIT(20), BIT(20), 0, "led"),
+	PIN_GRP_GPIO_2("led1_od", 12, 1, BIT(21), BIT(21), 0, "led"),
+	PIN_GRP_GPIO_2("led2_od", 13, 1, BIT(22), BIT(22), 0, "led"),
+	PIN_GRP_GPIO_2("led3_od", 14, 1, BIT(23), BIT(23), 0, "led"),
 
 };
 
@@ -221,11 +221,11 @@ static const struct armada_37xx_pin_data armada_37xx_pin_sb = {
 };
 
 static inline void armada_37xx_update_reg(unsigned int *reg,
-					  unsigned int offset)
+					  unsigned int *offset)
 {
 	/* We never have more than 2 registers */
-	if (offset >= GPIO_PER_REG) {
-		offset -= GPIO_PER_REG;
+	if (*offset >= GPIO_PER_REG) {
+		*offset -= GPIO_PER_REG;
 		*reg += sizeof(u32);
 	}
 }
@@ -376,7 +376,7 @@ static inline void armada_37xx_irq_update_reg(unsigned int *reg,
 {
 	int offset = irqd_to_hwirq(d);
 
-	armada_37xx_update_reg(reg, offset);
+	armada_37xx_update_reg(reg, &offset);
 }
 
 static int armada_37xx_gpio_direction_input(struct gpio_chip *chip,
@@ -386,7 +386,7 @@ static int armada_37xx_gpio_direction_input(struct gpio_chip *chip,
 	unsigned int reg = OUTPUT_EN;
 	unsigned int mask;
 
-	armada_37xx_update_reg(&reg, offset);
+	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
 
 	return regmap_update_bits(info->regmap, reg, mask, 0);
@@ -399,7 +399,7 @@ static int armada_37xx_gpio_get_direction(struct gpio_chip *chip,
 	unsigned int reg = OUTPUT_EN;
 	unsigned int val, mask;
 
-	armada_37xx_update_reg(&reg, offset);
+	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
 	regmap_read(info->regmap, reg, &val);
 
@@ -413,7 +413,7 @@ static int armada_37xx_gpio_direction_output(struct gpio_chip *chip,
 	unsigned int reg = OUTPUT_EN;
 	unsigned int mask, val, ret;
 
-	armada_37xx_update_reg(&reg, offset);
+	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
 
 	ret = regmap_update_bits(info->regmap, reg, mask, mask);
@@ -434,7 +434,7 @@ static int armada_37xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	unsigned int reg = INPUT_VAL;
 	unsigned int val, mask;
 
-	armada_37xx_update_reg(&reg, offset);
+	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
 
 	regmap_read(info->regmap, reg, &val);
@@ -449,7 +449,7 @@ static void armada_37xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
 	unsigned int reg = OUTPUT_VAL;
 	unsigned int mask, val;
 
-	armada_37xx_update_reg(&reg, offset);
+	armada_37xx_update_reg(&reg, &offset);
 	mask = BIT(offset);
 	val = value ? mask : 0;
 
diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c
index 974973777395..ccdf0bb21414 100644
--- a/drivers/pinctrl/pinctrl-stmfx.c
+++ b/drivers/pinctrl/pinctrl-stmfx.c
@@ -585,19 +585,6 @@ static int stmfx_pinctrl_gpio_function_enable(struct stmfx_pinctrl *pctl)
 	return stmfx_function_enable(pctl->stmfx, func);
 }
 
-static int stmfx_pinctrl_gpio_init_valid_mask(struct gpio_chip *gc,
-					      unsigned long *valid_mask,
-					      unsigned int ngpios)
-{
-	struct stmfx_pinctrl *pctl = gpiochip_get_data(gc);
-	u32 n;
-
-	for_each_clear_bit(n, &pctl->gpio_valid_mask, ngpios)
-		clear_bit(n, valid_mask);
-
-	return 0;
-}
-
 static int stmfx_pinctrl_probe(struct platform_device *pdev)
 {
 	struct stmfx *stmfx = dev_get_drvdata(pdev->dev.parent);
@@ -660,7 +647,6 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev)
 	pctl->gpio_chip.ngpio = pctl->pctl_desc.npins;
 	pctl->gpio_chip.can_sleep = true;
 	pctl->gpio_chip.of_node = np;
-	pctl->gpio_chip.init_valid_mask = stmfx_pinctrl_gpio_init_valid_mask;
 
 	ret = devm_gpiochip_add_data(pctl->dev, &pctl->gpio_chip, pctl);
 	if (ret) {
@@ -705,7 +691,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev)
 
 static int stmfx_pinctrl_remove(struct platform_device *pdev)
 {
-	struct stmfx *stmfx = dev_get_platdata(&pdev->dev);
+	struct stmfx *stmfx = dev_get_drvdata(pdev->dev.parent);
 
 	return stmfx_function_disable(stmfx,
 				      STMFX_FUNC_GPIO |
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 6ad51aa60c03..f877e77d9184 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -472,14 +472,7 @@ int pwm_apply_state(struct pwm_device *pwm, const struct pwm_state *state)
 		if (err)
 			return err;
 
-		/*
-		 * .apply might have to round some values in *state, if possible
-		 * read the actually implemented value back.
-		 */
-		if (chip->ops->get_state)
-			chip->ops->get_state(chip, pwm, &pwm->state);
-		else
-			pwm->state = *state;
+		pwm->state = *state;
 	} else {
 		/*
 		 * FIXME: restore the initial state in case of error.
diff --git a/drivers/pwm/pwm-bcm-iproc.c b/drivers/pwm/pwm-bcm-iproc.c
index 56c38cfae92c..1f829edd8ee7 100644
--- a/drivers/pwm/pwm-bcm-iproc.c
+++ b/drivers/pwm/pwm-bcm-iproc.c
@@ -187,6 +187,7 @@ static int iproc_pwmc_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 static const struct pwm_ops iproc_pwm_ops = {
 	.apply = iproc_pwmc_apply,
 	.get_state = iproc_pwmc_get_state,
+	.owner = THIS_MODULE,
 };
 
 static int iproc_pwmc_probe(struct platform_device *pdev)
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index afe94470b67f..a46be221dbdc 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -5053,6 +5053,19 @@ regulator_register(const struct regulator_desc *regulator_desc,
 
 	init_data = regulator_of_get_init_data(dev, regulator_desc, config,
 					       &rdev->dev.of_node);
+
+	/*
+	 * Sometimes not all resources are probed already so we need to take
+	 * that into account. This happens most the time if the ena_gpiod comes
+	 * from a gpio extender or something else.
+	 */
+	if (PTR_ERR(init_data) == -EPROBE_DEFER) {
+		kfree(config);
+		kfree(rdev);
+		ret = -EPROBE_DEFER;
+		goto rinse;
+	}
+
 	/*
 	 * We need to keep track of any GPIO descriptor coming from the
 	 * device tree until we have handled it over to the core. If the
diff --git a/drivers/regulator/da9062-regulator.c b/drivers/regulator/da9062-regulator.c
index 56f3f72d7707..710e67081d53 100644
--- a/drivers/regulator/da9062-regulator.c
+++ b/drivers/regulator/da9062-regulator.c
@@ -136,7 +136,6 @@ static int da9062_buck_set_mode(struct regulator_dev *rdev, unsigned mode)
 static unsigned da9062_buck_get_mode(struct regulator_dev *rdev)
 {
 	struct da9062_regulator *regl = rdev_get_drvdata(rdev);
-	struct regmap_field *field;
 	unsigned int val, mode = 0;
 	int ret;
 
@@ -158,18 +157,7 @@ static unsigned da9062_buck_get_mode(struct regulator_dev *rdev)
 		return REGULATOR_MODE_NORMAL;
 	}
 
-	/* Detect current regulator state */
-	ret = regmap_field_read(regl->suspend, &val);
-	if (ret < 0)
-		return 0;
-
-	/* Read regulator mode from proper register, depending on state */
-	if (val)
-		field = regl->suspend_sleep;
-	else
-		field = regl->sleep;
-
-	ret = regmap_field_read(field, &val);
+	ret = regmap_field_read(regl->sleep, &val);
 	if (ret < 0)
 		return 0;
 
@@ -208,21 +196,9 @@ static int da9062_ldo_set_mode(struct regulator_dev *rdev, unsigned mode)
 static unsigned da9062_ldo_get_mode(struct regulator_dev *rdev)
 {
 	struct da9062_regulator *regl = rdev_get_drvdata(rdev);
-	struct regmap_field *field;
 	int ret, val;
 
-	/* Detect current regulator state */
-	ret = regmap_field_read(regl->suspend, &val);
-	if (ret < 0)
-		return 0;
-
-	/* Read regulator mode from proper register, depending on state */
-	if (val)
-		field = regl->suspend_sleep;
-	else
-		field = regl->sleep;
-
-	ret = regmap_field_read(field, &val);
+	ret = regmap_field_read(regl->sleep, &val);
 	if (ret < 0)
 		return 0;
 
@@ -408,10 +384,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK1_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK1_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK1_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK1_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK1_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK1_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK1_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9061_ID_BUCK2,
@@ -444,10 +420,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK3_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK3_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK3_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK3_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK3_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK3_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK3_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9061_ID_BUCK3,
@@ -480,10 +456,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK4_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK4_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK4_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK4_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK4_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK4_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK4_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9061_ID_LDO1,
@@ -509,10 +485,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO1_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO1_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO1_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO1_CONT,
+			__builtin_ffs((int)DA9062AA_LDO1_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO1_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO1_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO1_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -542,10 +518,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO2_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO2_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO2_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO2_CONT,
+			__builtin_ffs((int)DA9062AA_LDO2_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO2_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO2_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO2_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -575,10 +551,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO3_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO3_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO3_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO3_CONT,
+			__builtin_ffs((int)DA9062AA_LDO3_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO3_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO3_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO3_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -608,10 +584,10 @@ static const struct da9062_regulator_info local_da9061_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO4_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO4_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO4_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO4_CONT,
+			__builtin_ffs((int)DA9062AA_LDO4_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO4_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO4_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO4_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -652,10 +628,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK1_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK1_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK1_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK1_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK1_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK1_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK1_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_BUCK2,
@@ -688,10 +664,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK2_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK2_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK2_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK2_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK2_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK2_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK2_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_BUCK3,
@@ -724,10 +700,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK3_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK3_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK3_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK3_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK3_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK3_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK3_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_BUCK4,
@@ -760,10 +736,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			__builtin_ffs((int)DA9062AA_BUCK4_MODE_MASK) - 1,
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_BUCK4_MODE_MASK)) - 1),
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VBUCK4_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_BUCK4_CONT,
+			__builtin_ffs((int)DA9062AA_BUCK4_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VBUCK4_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_BUCK4_CONF_MASK) - 1),
 	},
 	{
 		.desc.id = DA9062_ID_LDO1,
@@ -789,10 +765,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO1_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO1_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO1_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO1_CONT,
+			__builtin_ffs((int)DA9062AA_LDO1_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO1_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO1_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO1_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -822,10 +798,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO2_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO2_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO2_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO2_CONT,
+			__builtin_ffs((int)DA9062AA_LDO2_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO2_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO2_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO2_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -855,10 +831,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO3_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO3_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO3_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO3_CONT,
+			__builtin_ffs((int)DA9062AA_LDO3_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO3_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO3_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO3_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
@@ -888,10 +864,10 @@ static const struct da9062_regulator_info local_da9062_regulator_info[] = {
 			sizeof(unsigned int) * 8 -
 			__builtin_clz((DA9062AA_LDO4_SL_B_MASK)) - 1),
 		.suspend_vsel_reg = DA9062AA_VLDO4_B,
-		.suspend = REG_FIELD(DA9062AA_DVC_1,
-			__builtin_ffs((int)DA9062AA_VLDO4_SEL_MASK) - 1,
+		.suspend = REG_FIELD(DA9062AA_LDO4_CONT,
+			__builtin_ffs((int)DA9062AA_LDO4_CONF_MASK) - 1,
 			sizeof(unsigned int) * 8 -
-			__builtin_clz((DA9062AA_VLDO4_SEL_MASK)) - 1),
+			__builtin_clz(DA9062AA_LDO4_CONF_MASK) - 1),
 		.oc_event = REG_FIELD(DA9062AA_STATUS_D,
 			__builtin_ffs((int)DA9062AA_LDO4_ILIM_MASK) - 1,
 			sizeof(unsigned int) * 8 -
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index d90a6fd8cbc7..f81533070058 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -144,8 +144,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct fixed_voltage_config *config;
 	struct fixed_voltage_data *drvdata;
-	const struct fixed_dev_type *drvtype =
-		of_match_device(dev->driver->of_match_table, dev)->data;
+	const struct fixed_dev_type *drvtype = of_device_get_match_data(dev);
 	struct regulator_config cfg = { };
 	enum gpiod_flags gflags;
 	int ret;
@@ -177,7 +176,7 @@ static int reg_fixed_voltage_probe(struct platform_device *pdev)
 	drvdata->desc.type = REGULATOR_VOLTAGE;
 	drvdata->desc.owner = THIS_MODULE;
 
-	if (drvtype->has_enable_clock) {
+	if (drvtype && drvtype->has_enable_clock) {
 		drvdata->desc.ops = &fixed_voltage_clkenabled_ops;
 
 		drvdata->enable_clock = devm_clk_get(dev, NULL);
diff --git a/drivers/regulator/lochnagar-regulator.c b/drivers/regulator/lochnagar-regulator.c
index ff97cc50f2eb..9b05e03ba830 100644
--- a/drivers/regulator/lochnagar-regulator.c
+++ b/drivers/regulator/lochnagar-regulator.c
@@ -210,6 +210,7 @@ static const struct regulator_desc lochnagar_regulators[] = {
 
 		.enable_time = 3000,
 		.ramp_delay = 1000,
+		.off_on_delay = 15000,
 
 		.owner = THIS_MODULE,
 	},
diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
index afefb29ce1b0..87637eb6bcbc 100644
--- a/drivers/regulator/of_regulator.c
+++ b/drivers/regulator/of_regulator.c
@@ -231,12 +231,12 @@ static int of_get_regulation_constraints(struct device *dev,
 					"regulator-off-in-suspend"))
 			suspend_state->enabled = DISABLE_IN_SUSPEND;
 
-		if (!of_property_read_u32(np, "regulator-suspend-min-microvolt",
-					  &pval))
+		if (!of_property_read_u32(suspend_np,
+				"regulator-suspend-min-microvolt", &pval))
 			suspend_state->min_uV = pval;
 
-		if (!of_property_read_u32(np, "regulator-suspend-max-microvolt",
-					  &pval))
+		if (!of_property_read_u32(suspend_np,
+				"regulator-suspend-max-microvolt", &pval))
 			suspend_state->max_uV = pval;
 
 		if (!of_property_read_u32(suspend_np,
@@ -445,11 +445,20 @@ struct regulator_init_data *regulator_of_get_init_data(struct device *dev,
 		goto error;
 	}
 
-	if (desc->of_parse_cb && desc->of_parse_cb(child, desc, config)) {
-		dev_err(dev,
-			"driver callback failed to parse DT for regulator %pOFn\n",
-			child);
-		goto error;
+	if (desc->of_parse_cb) {
+		int ret;
+
+		ret = desc->of_parse_cb(child, desc, config);
+		if (ret) {
+			if (ret == -EPROBE_DEFER) {
+				of_node_put(child);
+				return ERR_PTR(-EPROBE_DEFER);
+			}
+			dev_err(dev,
+				"driver callback failed to parse DT for regulator %pOFn\n",
+				child);
+			goto error;
+		}
 	}
 
 	*node = child;
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index df5df1c495ad..689537927f6f 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -788,7 +788,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 		/* SW2~SW4 high bit check and modify the voltage value table */
 		if (i >= sw_check_start && i <= sw_check_end) {
-			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
+			ret = regmap_read(pfuze_chip->regmap,
+						desc->vsel_reg, &val);
+			if (ret) {
+				dev_err(&client->dev, "Fails to read from the register.\n");
+				return ret;
+			}
+
 			if (val & sw_hi) {
 				if (pfuze_chip->chip_id == PFUZE3000 ||
 					pfuze_chip->chip_id == PFUZE3001) {
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
index db6c085da65e..0246b6f99fb5 100644
--- a/drivers/regulator/qcom-rpmh-regulator.c
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -735,8 +735,8 @@ static const struct rpmh_vreg_hw_data pmic5_hfsmps515 = {
 static const struct rpmh_vreg_hw_data pmic5_bob = {
 	.regulator_type = VRM,
 	.ops = &rpmh_regulator_vrm_bypass_ops,
-	.voltage_range = REGULATOR_LINEAR_RANGE(300000, 0, 135, 32000),
-	.n_voltages = 136,
+	.voltage_range = REGULATOR_LINEAR_RANGE(3000000, 0, 31, 32000),
+	.n_voltages = 32,
 	.pmic_mode_map = pmic_mode_map_pmic5_bob,
 	.of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode,
 };
diff --git a/drivers/regulator/ti-abb-regulator.c b/drivers/regulator/ti-abb-regulator.c
index cced1ffb896c..89b9314d64c9 100644
--- a/drivers/regulator/ti-abb-regulator.c
+++ b/drivers/regulator/ti-abb-regulator.c
@@ -173,19 +173,14 @@ static int ti_abb_wait_txdone(struct device *dev, struct ti_abb *abb)
 	while (timeout++ <= abb->settling_time) {
 		status = ti_abb_check_txdone(abb);
 		if (status)
-			break;
+			return 0;
 
 		udelay(1);
 	}
 
-	if (timeout > abb->settling_time) {
-		dev_warn_ratelimited(dev,
-				     "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
-				     __func__, timeout, readl(abb->int_base));
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	dev_warn_ratelimited(dev, "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
+			     __func__, timeout, readl(abb->int_base));
+	return -ETIMEDOUT;
 }
 
 /**
@@ -205,19 +200,14 @@ static int ti_abb_clear_all_txdone(struct device *dev, const struct ti_abb *abb)
 
 		status = ti_abb_check_txdone(abb);
 		if (!status)
-			break;
+			return 0;
 
 		udelay(1);
 	}
 
-	if (timeout > abb->settling_time) {
-		dev_warn_ratelimited(dev,
-				     "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
-				     __func__, timeout, readl(abb->int_base));
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	dev_warn_ratelimited(dev, "%s:TRANXDONE timeout(%duS) int=0x%08x\n",
+			     __func__, timeout, readl(abb->int_base));
+	return -ETIMEDOUT;
 }
 
 /**
diff --git a/drivers/reset/core.c b/drivers/reset/core.c
index 213ff40dda11..3c9a64c1b7a8 100644
--- a/drivers/reset/core.c
+++ b/drivers/reset/core.c
@@ -76,7 +76,6 @@ static const char *rcdev_name(struct reset_controller_dev *rcdev)
  * of_reset_simple_xlate - translate reset_spec to the reset line number
  * @rcdev: a pointer to the reset controller device
  * @reset_spec: reset line specifier as found in the device tree
- * @flags: a flags pointer to fill in (optional)
  *
  * This simple translation function should be used for reset controllers
  * with 1:1 mapping, where reset lines can be indexed by number without gaps.
@@ -748,6 +747,7 @@ static void reset_control_array_put(struct reset_control_array *resets)
 	for (i = 0; i < resets->num_rstcs; i++)
 		__reset_control_put_internal(resets->rstc[i]);
 	mutex_unlock(&reset_list_mutex);
+	kfree(resets);
 }
 
 /**
@@ -825,9 +825,10 @@ int __device_reset(struct device *dev, bool optional)
 }
 EXPORT_SYMBOL_GPL(__device_reset);
 
-/**
+/*
  * APIs to manage an array of reset controls.
  */
+
 /**
  * of_reset_control_get_count - Count number of resets available with a device
  *
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 45bdb47f84c1..9157e728a362 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -522,8 +522,7 @@ static int zcrypt_release(struct inode *inode, struct file *filp)
 	if (filp->f_inode->i_cdev == &zcrypt_cdev) {
 		struct zcdn_device *zcdndev;
 
-		if (mutex_lock_interruptible(&ap_perms_mutex))
-			return -ERESTARTSYS;
+		mutex_lock(&ap_perms_mutex);
 		zcdndev = find_zcdndev_by_devt(filp->f_inode->i_rdev);
 		mutex_unlock(&ap_perms_mutex);
 		if (zcdndev) {
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 1b92f3c19ff3..90cf4691b8c3 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -898,7 +898,7 @@ config SCSI_SNI_53C710
 
 config 53C700_LE_ON_BE
 	bool
-	depends on SCSI_LASI700
+	depends on SCSI_LASI700 || SCSI_SNI_53C710
 	default y
 
 config SCSI_STEX
diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index 5f8153c37f77..76751d6c7f0d 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -579,7 +579,6 @@ ch_release(struct inode *inode, struct file *file)
 	scsi_changer *ch = file->private_data;
 
 	scsi_device_put(ch->device);
-	ch->device = NULL;
 	file->private_data = NULL;
 	kref_put(&ch->ref, ch_destroy);
 	return 0;
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 4971104b1817..f32da0ca529e 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -512,6 +512,7 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 	unsigned int tpg_desc_tbl_off;
 	unsigned char orig_transition_tmo;
 	unsigned long flags;
+	bool transitioning_sense = false;
 
 	if (!pg->expiry) {
 		unsigned long transition_tmo = ALUA_FAILOVER_TIMEOUT * HZ;
@@ -572,13 +573,19 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 			goto retry;
 		}
 		/*
-		 * Retry on ALUA state transition or if any
-		 * UNIT ATTENTION occurred.
+		 * If the array returns with 'ALUA state transition'
+		 * sense code here it cannot return RTPG data during
+		 * transition. So set the state to 'transitioning' directly.
 		 */
 		if (sense_hdr.sense_key == NOT_READY &&
-		    sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a)
-			err = SCSI_DH_RETRY;
-		else if (sense_hdr.sense_key == UNIT_ATTENTION)
+		    sense_hdr.asc == 0x04 && sense_hdr.ascq == 0x0a) {
+			transitioning_sense = true;
+			goto skip_rtpg;
+		}
+		/*
+		 * Retry on any other UNIT ATTENTION occurred.
+		 */
+		if (sense_hdr.sense_key == UNIT_ATTENTION)
 			err = SCSI_DH_RETRY;
 		if (err == SCSI_DH_RETRY &&
 		    pg->expiry != 0 && time_before(jiffies, pg->expiry)) {
@@ -666,7 +673,11 @@ static int alua_rtpg(struct scsi_device *sdev, struct alua_port_group *pg)
 		off = 8 + (desc[7] * 4);
 	}
 
+ skip_rtpg:
 	spin_lock_irqsave(&pg->lock, flags);
+	if (transitioning_sense)
+		pg->state = SCSI_ACCESS_STATE_TRANSITIONING;
+
 	sdev_printk(KERN_INFO, sdev,
 		    "%s: port group %02x state %c %s supports %c%c%c%c%c%c%c\n",
 		    ALUA_DH_NAME, pg->group_id, print_alua_state(pg->state),
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index ac39ed79ccaa..216e557f703e 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -5477,6 +5477,8 @@ static int hpsa_ciss_submit(struct ctlr_info *h,
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
 
+	c->device = dev;
+
 	enqueue_cmd_and_start_io(h, c);
 	/* the cmd'll come back via intr handler in complete_scsi_command()  */
 	return 0;
@@ -5548,6 +5550,7 @@ static int hpsa_ioaccel_submit(struct ctlr_info *h,
 		hpsa_cmd_init(h, c->cmdindex, c);
 		c->cmd_type = CMD_SCSI;
 		c->scsi_cmd = cmd;
+		c->device = dev;
 		rc = hpsa_scsi_ioaccel_raid_map(h, c);
 		if (rc < 0)     /* scsi_dma_map failed. */
 			rc = SCSI_MLQUEUE_HOST_BUSY;
@@ -5555,6 +5558,7 @@ static int hpsa_ioaccel_submit(struct ctlr_info *h,
 		hpsa_cmd_init(h, c->cmdindex, c);
 		c->cmd_type = CMD_SCSI;
 		c->scsi_cmd = cmd;
+		c->device = dev;
 		rc = hpsa_scsi_ioaccel_direct_map(h, c);
 		if (rc < 0)     /* scsi_dma_map failed. */
 			rc = SCSI_MLQUEUE_HOST_BUSY;
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index e91377a4cafe..e8813d26e594 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -9055,7 +9055,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 		}
 	}
 
-#if defined(BUILD_NVME)
 	/* Clear NVME stats */
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME) {
 		for (idx = 0; idx < phba->cfg_hdw_queue; idx++) {
@@ -9063,7 +9062,6 @@ lpfc_sli4_queue_create(struct lpfc_hba *phba)
 			       sizeof(phba->sli4_hba.hdwq[idx].nvme_cstat));
 		}
 	}
-#endif
 
 	/* Clear SCSI stats */
 	if (phba->cfg_enable_fc4_type & LPFC_ENABLE_FCP) {
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index f4b879d25fe9..fc6e4546d738 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -851,9 +851,9 @@ lpfc_disc_set_adisc(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 
 	if (!(vport->fc_flag & FC_PT2PT)) {
 		/* Check config parameter use-adisc or FCP-2 */
-		if ((vport->cfg_use_adisc && (vport->fc_flag & FC_RSCN_MODE)) ||
+		if (vport->cfg_use_adisc && ((vport->fc_flag & FC_RSCN_MODE) ||
 		    ((ndlp->nlp_fcp_info & NLP_FCP_2_DEVICE) &&
-		     (ndlp->nlp_type & NLP_FCP_TARGET))) {
+		     (ndlp->nlp_type & NLP_FCP_TARGET)))) {
 			spin_lock_irq(shost->host_lock);
 			ndlp->nlp_flag |= NLP_NPR_ADISC;
 			spin_unlock_irq(shost->host_lock);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index fe1097666de4..6822cd9ff8f1 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -528,7 +528,6 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 			list_del_init(&psb->list);
 			psb->exch_busy = 0;
 			psb->status = IOSTAT_SUCCESS;
-#ifdef BUILD_NVME
 			if (psb->cur_iocbq.iocb_flag == LPFC_IO_NVME) {
 				qp->abts_nvme_io_bufs--;
 				spin_unlock(&qp->abts_io_buf_list_lock);
@@ -536,7 +535,6 @@ lpfc_sli4_io_xri_aborted(struct lpfc_hba *phba,
 				lpfc_sli4_nvme_xri_aborted(phba, axri, psb);
 				return;
 			}
-#endif
 			qp->abts_scsi_io_bufs--;
 			spin_unlock(&qp->abts_io_buf_list_lock);
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index a0c6945b8139..614f78dddafe 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -7866,7 +7866,7 @@ lpfc_sli4_process_missed_mbox_completions(struct lpfc_hba *phba)
 	if (sli4_hba->hdwq) {
 		for (eqidx = 0; eqidx < phba->cfg_irq_chann; eqidx++) {
 			eq = phba->sli4_hba.hba_eq_hdl[eqidx].eq;
-			if (eq->queue_id == sli4_hba->mbx_cq->assoc_qid) {
+			if (eq && eq->queue_id == sli4_hba->mbx_cq->assoc_qid) {
 				fpeq = eq;
 				break;
 			}
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 30bafd9d21e9..7259bce85e0e 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -440,9 +440,6 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		valid = 0;
 		if (ha->optrom_size == OPTROM_SIZE_2300 && start == 0)
 			valid = 1;
-		else if (start == (ha->flt_region_boot * 4) ||
-		    start == (ha->flt_region_fw * 4))
-			valid = 1;
 		else if (IS_QLA24XX_TYPE(ha) || IS_QLA25XX(ha))
 			valid = 1;
 		if (!valid) {
@@ -489,8 +486,10 @@ qla2x00_sysfs_write_optrom_ctl(struct file *filp, struct kobject *kobj,
 		    "Writing flash region -- 0x%x/0x%x.\n",
 		    ha->optrom_region_start, ha->optrom_region_size);
 
-		ha->isp_ops->write_optrom(vha, ha->optrom_buffer,
+		rval = ha->isp_ops->write_optrom(vha, ha->optrom_buffer,
 		    ha->optrom_region_start, ha->optrom_region_size);
+		if (rval)
+			rval = -EIO;
 		break;
 	default:
 		rval = -EINVAL;
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 28d587a89ba6..99f0a1a08143 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -253,7 +253,7 @@ qla2x00_process_els(struct bsg_job *bsg_job)
 	srb_t *sp;
 	const char *type;
 	int req_sg_cnt, rsp_sg_cnt;
-	int rval =  (DRIVER_ERROR << 16);
+	int rval =  (DID_ERROR << 16);
 	uint16_t nextlid = 0;
 
 	if (bsg_request->msgcode == FC_BSG_RPT_ELS) {
@@ -432,7 +432,7 @@ qla2x00_process_ct(struct bsg_job *bsg_job)
 	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
-	int rval = (DRIVER_ERROR << 16);
+	int rval = (DID_ERROR << 16);
 	int req_sg_cnt, rsp_sg_cnt;
 	uint16_t loop_id;
 	struct fc_port *fcport;
@@ -1950,7 +1950,7 @@ qlafx00_mgmt_cmd(struct bsg_job *bsg_job)
 	struct Scsi_Host *host = fc_bsg_to_shost(bsg_job);
 	scsi_qla_host_t *vha = shost_priv(host);
 	struct qla_hw_data *ha = vha->hw;
-	int rval = (DRIVER_ERROR << 16);
+	int rval = (DID_ERROR << 16);
 	struct qla_mt_iocb_rqst_fx00 *piocb_rqst;
 	srb_t *sp;
 	int req_sg_cnt = 0, rsp_sg_cnt = 0;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 1cc6913f76c4..4a1f21c11758 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -702,6 +702,7 @@ qla2x00_execute_fw(scsi_qla_host_t *vha, uint32_t risc_addr)
 		mcp->mb[2] = LSW(risc_addr);
 		mcp->mb[3] = 0;
 		mcp->mb[4] = 0;
+		mcp->mb[11] = 0;
 		ha->flags.using_lr_setting = 0;
 		if (IS_QLA25XX(ha) || IS_QLA81XX(ha) || IS_QLA83XX(ha) ||
 		    IS_QLA27XX(ha) || IS_QLA28XX(ha)) {
@@ -746,7 +747,7 @@ qla2x00_execute_fw(scsi_qla_host_t *vha, uint32_t risc_addr)
 		if (ha->flags.exchoffld_enabled)
 			mcp->mb[4] |= ENABLE_EXCHANGE_OFFLD;
 
-		mcp->out_mb |= MBX_4|MBX_3|MBX_2|MBX_1;
+		mcp->out_mb |= MBX_4 | MBX_3 | MBX_2 | MBX_1 | MBX_11;
 		mcp->in_mb |= MBX_3 | MBX_2 | MBX_1;
 	} else {
 		mcp->mb[1] = LSW(risc_addr);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 3568031c6504..337162ac3a77 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3224,6 +3224,10 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	    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 (unlikely(!ha->wq)) {
+		ret = -ENOMEM;
+		goto probe_failed;
+	}
 
 	if (ha->isp_ops->initialize_adapter(base_vha)) {
 		ql_log(ql_log_fatal, base_vha, 0x00d6,
@@ -3531,6 +3535,10 @@ qla2x00_shutdown(struct pci_dev *pdev)
 		qla2x00_try_to_stop_firmware(vha);
 	}
 
+	/* Disable timer */
+	if (vha->timer_active)
+		qla2x00_stop_timer(vha);
+
 	/* Turn adapter off line */
 	vha->flags.online = 0;
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 64c96c7828ee..6d7362e7367e 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -730,6 +730,14 @@ sdev_store_delete(struct device *dev, struct device_attribute *attr,
 		  const char *buf, size_t count)
 {
 	struct kernfs_node *kn;
+	struct scsi_device *sdev = to_scsi_device(dev);
+
+	/*
+	 * We need to try to get module, avoiding the module been removed
+	 * during delete.
+	 */
+	if (scsi_device_get(sdev))
+		return -ENODEV;
 
 	kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
 	WARN_ON_ONCE(!kn);
@@ -744,9 +752,10 @@ sdev_store_delete(struct device *dev, struct device_attribute *attr,
 	 * state into SDEV_DEL.
 	 */
 	device_remove_file(dev, attr);
-	scsi_remove_device(to_scsi_device(dev));
+	scsi_remove_device(sdev);
 	if (kn)
 		sysfs_unbreak_active_protection(kn);
+	scsi_device_put(sdev);
 	return count;
 };
 static DEVICE_ATTR(delete, S_IWUSR, NULL, sdev_store_delete);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 03163ac5fe95..ebb40160539f 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1166,11 +1166,12 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd)
 	sector_t lba = sectors_to_logical(sdp, blk_rq_pos(rq));
 	sector_t threshold;
 	unsigned int nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq));
-	bool dif, dix;
 	unsigned int mask = logical_to_sectors(sdp, 1) - 1;
 	bool write = rq_data_dir(rq) == WRITE;
 	unsigned char protect, fua;
 	blk_status_t ret;
+	unsigned int dif;
+	bool dix;
 
 	ret = scsi_init_io(cmd);
 	if (ret != BLK_STS_OK)
diff --git a/drivers/scsi/sni_53c710.c b/drivers/scsi/sni_53c710.c
index aef4881d8e21..a85d52b5dc32 100644
--- a/drivers/scsi/sni_53c710.c
+++ b/drivers/scsi/sni_53c710.c
@@ -66,10 +66,8 @@ static int snirm710_probe(struct platform_device *dev)
 
 	base = res->start;
 	hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL);
-	if (!hostdata) {
-		dev_printk(KERN_ERR, dev, "Failed to allocate host data\n");
+	if (!hostdata)
 		return -ENOMEM;
-	}
 
 	hostdata->dev = &dev->dev;
 	dma_set_mask(&dev->dev, DMA_BIT_MASK(32));
diff --git a/drivers/scsi/ufs/ufs_bsg.c b/drivers/scsi/ufs/ufs_bsg.c
index a9344eb4e047..dc2f6d2b46ed 100644
--- a/drivers/scsi/ufs/ufs_bsg.c
+++ b/drivers/scsi/ufs/ufs_bsg.c
@@ -98,6 +98,8 @@ static int ufs_bsg_request(struct bsg_job *job)
 
 	bsg_reply->reply_payload_rcv_len = 0;
 
+	pm_runtime_get_sync(hba->dev);
+
 	msgcode = bsg_request->msgcode;
 	switch (msgcode) {
 	case UPIU_TRANSACTION_QUERY_REQ:
@@ -135,6 +137,8 @@ static int ufs_bsg_request(struct bsg_job *job)
 		break;
 	}
 
+	pm_runtime_put_sync(hba->dev);
+
 	if (!desc_buff)
 		goto out;
 
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index d9231bd3c691..98b9d9a902ae 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -249,13 +249,13 @@ static struct genpd_power_state imx6_pm_domain_pu_state = {
 };
 
 static struct imx_pm_domain imx_gpc_domains[] = {
-	[GPC_PGC_DOMAIN_ARM] {
+	[GPC_PGC_DOMAIN_ARM] = {
 		.base = {
 			.name = "ARM",
 			.flags = GENPD_FLAG_ALWAYS_ON,
 		},
 	},
-	[GPC_PGC_DOMAIN_PU] {
+	[GPC_PGC_DOMAIN_PU] = {
 		.base = {
 			.name = "PU",
 			.power_off = imx6_pm_domain_power_off,
@@ -266,7 +266,7 @@ static struct imx_pm_domain imx_gpc_domains[] = {
 		.reg_offs = 0x260,
 		.cntr_pdn_bit = 0,
 	},
-	[GPC_PGC_DOMAIN_DISPLAY] {
+	[GPC_PGC_DOMAIN_DISPLAY] = {
 		.base = {
 			.name = "DISPLAY",
 			.power_off = imx6_pm_domain_power_off,
@@ -275,7 +275,7 @@ static struct imx_pm_domain imx_gpc_domains[] = {
 		.reg_offs = 0x240,
 		.cntr_pdn_bit = 4,
 	},
-	[GPC_PGC_DOMAIN_PCI] {
+	[GPC_PGC_DOMAIN_PCI] = {
 		.base = {
 			.name = "PCI",
 			.power_off = imx6_pm_domain_power_off,
diff --git a/drivers/soc/imx/soc-imx-scu.c b/drivers/soc/imx/soc-imx-scu.c
index 50831ebf126a..c68882eb80f7 100644
--- a/drivers/soc/imx/soc-imx-scu.c
+++ b/drivers/soc/imx/soc-imx-scu.c
@@ -46,7 +46,7 @@ static ssize_t soc_uid_show(struct device *dev,
 	hdr->func = IMX_SC_MISC_FUNC_UNIQUE_ID;
 	hdr->size = 1;
 
-	ret = imx_scu_call_rpc(soc_ipc_handle, &msg, false);
+	ret = imx_scu_call_rpc(soc_ipc_handle, &msg, true);
 	if (ret) {
 		pr_err("%s: get soc uid failed, ret %d\n", __func__, ret);
 		return ret;
diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 661e47acc354..adbf3bfae805 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -74,6 +74,16 @@ config QCOM_MDT_LOADER
 	tristate
 	select QCOM_SCM
 
+config QCOM_OCMEM
+	tristate "Qualcomm On Chip Memory (OCMEM) driver"
+	depends on ARCH_QCOM
+	select QCOM_SCM
+	help
+          The On Chip Memory (OCMEM) allocator allows various clients to
+          allocate memory from OCMEM based on performance, latency and power
+          requirements. This is typically used by the GPU, camera/video, and
+          audio components on some Snapdragon SoCs.
+
 config QCOM_PM
 	bool "Qualcomm Power Management"
 	depends on ARCH_QCOM && !ARM64
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 162788701a77..aab333720bfd 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -6,6 +6,7 @@ obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
 obj-$(CONFIG_QCOM_GLINK_SSR) +=	glink_ssr.o
 obj-$(CONFIG_QCOM_GSBI)	+=	qcom_gsbi.o
 obj-$(CONFIG_QCOM_MDT_LOADER)	+= mdt_loader.o
+obj-$(CONFIG_QCOM_OCMEM)	+= ocmem.o
 obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
diff --git a/drivers/soc/qcom/ocmem.c b/drivers/soc/qcom/ocmem.c
new file mode 100644
index 000000000000..7f9e9944d1ea
--- /dev/null
+++ b/drivers/soc/qcom/ocmem.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The On Chip Memory (OCMEM) allocator allows various clients to allocate
+ * memory from OCMEM based on performance, latency and power requirements.
+ * This is typically used by the GPU, camera/video, and audio components on
+ * some Snapdragon SoCs.
+ *
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ * Copyright (C) 2015 Red Hat. Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/qcom_scm.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <soc/qcom/ocmem.h>
+
+enum region_mode {
+	WIDE_MODE = 0x0,
+	THIN_MODE,
+	MODE_DEFAULT = WIDE_MODE,
+};
+
+enum ocmem_macro_state {
+	PASSTHROUGH = 0,
+	PERI_ON = 1,
+	CORE_ON = 2,
+	CLK_OFF = 4,
+};
+
+struct ocmem_region {
+	bool interleaved;
+	enum region_mode mode;
+	unsigned int num_macros;
+	enum ocmem_macro_state macro_state[4];
+	unsigned long macro_size;
+	unsigned long region_size;
+};
+
+struct ocmem_config {
+	uint8_t num_regions;
+	unsigned long macro_size;
+};
+
+struct ocmem {
+	struct device *dev;
+	const struct ocmem_config *config;
+	struct resource *memory;
+	void __iomem *mmio;
+	unsigned int num_ports;
+	unsigned int num_macros;
+	bool interleaved;
+	struct ocmem_region *regions;
+	unsigned long active_allocations;
+};
+
+#define OCMEM_MIN_ALIGN				SZ_64K
+#define OCMEM_MIN_ALLOC				SZ_64K
+
+#define OCMEM_REG_HW_VERSION			0x00000000
+#define OCMEM_REG_HW_PROFILE			0x00000004
+
+#define OCMEM_REG_REGION_MODE_CTL		0x00001000
+#define OCMEM_REGION_MODE_CTL_REG0_THIN		0x00000001
+#define OCMEM_REGION_MODE_CTL_REG1_THIN		0x00000002
+#define OCMEM_REGION_MODE_CTL_REG2_THIN		0x00000004
+#define OCMEM_REGION_MODE_CTL_REG3_THIN		0x00000008
+
+#define OCMEM_REG_GFX_MPU_START			0x00001004
+#define OCMEM_REG_GFX_MPU_END			0x00001008
+
+#define OCMEM_HW_PROFILE_NUM_PORTS(val)		FIELD_PREP(0x0000000f, (val))
+#define OCMEM_HW_PROFILE_NUM_MACROS(val)	FIELD_PREP(0x00003f00, (val))
+
+#define OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE	0x00010000
+#define OCMEM_HW_PROFILE_INTERLEAVING		0x00020000
+#define OCMEM_REG_GEN_STATUS			0x0000000c
+
+#define OCMEM_REG_PSGSC_STATUS			0x00000038
+#define OCMEM_REG_PSGSC_CTL(i0)			(0x0000003c + 0x1*(i0))
+
+#define OCMEM_PSGSC_CTL_MACRO0_MODE(val)	FIELD_PREP(0x00000007, (val))
+#define OCMEM_PSGSC_CTL_MACRO1_MODE(val)	FIELD_PREP(0x00000070, (val))
+#define OCMEM_PSGSC_CTL_MACRO2_MODE(val)	FIELD_PREP(0x00000700, (val))
+#define OCMEM_PSGSC_CTL_MACRO3_MODE(val)	FIELD_PREP(0x00007000, (val))
+
+#define OCMEM_CLK_CORE_IDX			0
+static struct clk_bulk_data ocmem_clks[] = {
+	{
+		.id = "core",
+	},
+	{
+		.id = "iface",
+	},
+};
+
+static inline void ocmem_write(struct ocmem *ocmem, u32 reg, u32 data)
+{
+	writel(data, ocmem->mmio + reg);
+}
+
+static inline u32 ocmem_read(struct ocmem *ocmem, u32 reg)
+{
+	return readl(ocmem->mmio + reg);
+}
+
+static void update_ocmem(struct ocmem *ocmem)
+{
+	uint32_t region_mode_ctrl = 0x0;
+	int i;
+
+	if (!qcom_scm_ocmem_lock_available()) {
+		for (i = 0; i < ocmem->config->num_regions; i++) {
+			struct ocmem_region *region = &ocmem->regions[i];
+
+			if (region->mode == THIN_MODE)
+				region_mode_ctrl |= BIT(i);
+		}
+
+		dev_dbg(ocmem->dev, "ocmem_region_mode_control %x\n",
+			region_mode_ctrl);
+		ocmem_write(ocmem, OCMEM_REG_REGION_MODE_CTL, region_mode_ctrl);
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+		u32 data;
+
+		data = OCMEM_PSGSC_CTL_MACRO0_MODE(region->macro_state[0]) |
+			OCMEM_PSGSC_CTL_MACRO1_MODE(region->macro_state[1]) |
+			OCMEM_PSGSC_CTL_MACRO2_MODE(region->macro_state[2]) |
+			OCMEM_PSGSC_CTL_MACRO3_MODE(region->macro_state[3]);
+
+		ocmem_write(ocmem, OCMEM_REG_PSGSC_CTL(i), data);
+	}
+}
+
+static unsigned long phys_to_offset(struct ocmem *ocmem,
+				    unsigned long addr)
+{
+	if (addr < ocmem->memory->start || addr >= ocmem->memory->end)
+		return 0;
+
+	return addr - ocmem->memory->start;
+}
+
+static unsigned long device_address(struct ocmem *ocmem,
+				    enum ocmem_client client,
+				    unsigned long addr)
+{
+	WARN_ON(client != OCMEM_GRAPHICS);
+
+	/* TODO: gpu uses phys_to_offset, but others do not.. */
+	return phys_to_offset(ocmem, addr);
+}
+
+static void update_range(struct ocmem *ocmem, struct ocmem_buf *buf,
+			 enum ocmem_macro_state mstate, enum region_mode rmode)
+{
+	unsigned long offset = 0;
+	int i, j;
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (buf->offset <= offset && offset < buf->offset + buf->len)
+			region->mode = rmode;
+
+		for (j = 0; j < region->num_macros; j++) {
+			if (buf->offset <= offset &&
+			    offset < buf->offset + buf->len)
+				region->macro_state[j] = mstate;
+
+			offset += region->macro_size;
+		}
+	}
+
+	update_ocmem(ocmem);
+}
+
+struct ocmem *of_get_ocmem(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *devnode;
+
+	devnode = of_parse_phandle(dev->of_node, "sram", 0);
+	if (!devnode || !devnode->parent) {
+		dev_err(dev, "Cannot look up sram phandle\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	pdev = of_find_device_by_node(devnode->parent);
+	if (!pdev) {
+		dev_err(dev, "Cannot find device node %s\n", devnode->name);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+
+	return platform_get_drvdata(pdev);
+}
+EXPORT_SYMBOL(of_get_ocmem);
+
+struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client,
+				 unsigned long size)
+{
+	struct ocmem_buf *buf;
+	int ret;
+
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return ERR_PTR(-ENODEV);
+
+	if (size < OCMEM_MIN_ALLOC || !IS_ALIGNED(size, OCMEM_MIN_ALIGN))
+		return ERR_PTR(-EINVAL);
+
+	if (test_and_set_bit_lock(BIT(client), &ocmem->active_allocations))
+		return ERR_PTR(-EBUSY);
+
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto err_unlock;
+	}
+
+	buf->offset = 0;
+	buf->addr = device_address(ocmem, client, buf->offset);
+	buf->len = size;
+
+	update_range(ocmem, buf, CORE_ON, WIDE_MODE);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		ret = qcom_scm_ocmem_lock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					  buf->offset, buf->len, WIDE_MODE);
+		if (ret) {
+			dev_err(ocmem->dev, "could not lock: %d\n", ret);
+			ret = -EINVAL;
+			goto err_kfree;
+		}
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, buf->offset);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END,
+			    buf->offset + buf->len);
+	}
+
+	dev_dbg(ocmem->dev, "using %ldK of OCMEM at 0x%08lx for client %d\n",
+		size / 1024, buf->addr, client);
+
+	return buf;
+
+err_kfree:
+	kfree(buf);
+err_unlock:
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL(ocmem_allocate);
+
+void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+		struct ocmem_buf *buf)
+{
+	/* TODO: add support for other clients... */
+	if (WARN_ON(client != OCMEM_GRAPHICS))
+		return;
+
+	update_range(ocmem, buf, CLK_OFF, MODE_DEFAULT);
+
+	if (qcom_scm_ocmem_lock_available()) {
+		int ret;
+
+		ret = qcom_scm_ocmem_unlock(QCOM_SCM_OCMEM_GRAPHICS_ID,
+					    buf->offset, buf->len);
+		if (ret)
+			dev_err(ocmem->dev, "could not unlock: %d\n", ret);
+	} else {
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_START, 0x0);
+		ocmem_write(ocmem, OCMEM_REG_GFX_MPU_END, 0x0);
+	}
+
+	kfree(buf);
+
+	clear_bit_unlock(BIT(client), &ocmem->active_allocations);
+}
+EXPORT_SYMBOL(ocmem_free);
+
+static int ocmem_dev_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	unsigned long reg, region_size;
+	int i, j, ret, num_banks;
+	struct resource *res;
+	struct ocmem *ocmem;
+
+	if (!qcom_scm_is_available())
+		return -EPROBE_DEFER;
+
+	ocmem = devm_kzalloc(dev, sizeof(*ocmem), GFP_KERNEL);
+	if (!ocmem)
+		return -ENOMEM;
+
+	ocmem->dev = dev;
+	ocmem->config = device_get_match_data(dev);
+
+	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Unable to get clocks\n");
+
+		return ret;
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl");
+	ocmem->mmio = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ocmem->mmio)) {
+		dev_err(&pdev->dev, "Failed to ioremap ocmem_ctrl resource\n");
+		return PTR_ERR(ocmem->mmio);
+	}
+
+	ocmem->memory = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						     "mem");
+	if (!ocmem->memory) {
+		dev_err(dev, "Could not get mem region\n");
+		return -ENXIO;
+	}
+
+	/* The core clock is synchronous with graphics */
+	WARN_ON(clk_set_rate(ocmem_clks[OCMEM_CLK_CORE_IDX].clk, 1000) < 0);
+
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	if (ret) {
+		dev_info(ocmem->dev, "Failed to enable clocks\n");
+		return ret;
+	}
+
+	if (qcom_scm_restore_sec_cfg_available()) {
+		dev_dbg(dev, "configuring scm\n");
+		ret = qcom_scm_restore_sec_cfg(QCOM_SCM_OCMEM_DEV_ID, 0);
+		if (ret) {
+			dev_err(dev, "Could not enable secure configuration\n");
+			goto err_clk_disable;
+		}
+	}
+
+	reg = ocmem_read(ocmem, OCMEM_REG_HW_PROFILE);
+	ocmem->num_ports = OCMEM_HW_PROFILE_NUM_PORTS(reg);
+	ocmem->num_macros = OCMEM_HW_PROFILE_NUM_MACROS(reg);
+	ocmem->interleaved = !!(reg & OCMEM_HW_PROFILE_INTERLEAVING);
+
+	num_banks = ocmem->num_ports / 2;
+	region_size = ocmem->config->macro_size * num_banks;
+
+	dev_info(dev, "%u ports, %u regions, %u macros, %sinterleaved\n",
+		 ocmem->num_ports, ocmem->config->num_regions,
+		 ocmem->num_macros, ocmem->interleaved ? "" : "not ");
+
+	ocmem->regions = devm_kcalloc(dev, ocmem->config->num_regions,
+				      sizeof(struct ocmem_region), GFP_KERNEL);
+	if (!ocmem->regions) {
+		ret = -ENOMEM;
+		goto err_clk_disable;
+	}
+
+	for (i = 0; i < ocmem->config->num_regions; i++) {
+		struct ocmem_region *region = &ocmem->regions[i];
+
+		if (WARN_ON(num_banks > ARRAY_SIZE(region->macro_state))) {
+			ret = -EINVAL;
+			goto err_clk_disable;
+		}
+
+		region->mode = MODE_DEFAULT;
+		region->num_macros = num_banks;
+
+		if (i == (ocmem->config->num_regions - 1) &&
+		    reg & OCMEM_HW_PROFILE_LAST_REGN_HALFSIZE) {
+			region->macro_size = ocmem->config->macro_size / 2;
+			region->region_size = region_size / 2;
+		} else {
+			region->macro_size = ocmem->config->macro_size;
+			region->region_size = region_size;
+		}
+
+		for (j = 0; j < ARRAY_SIZE(region->macro_state); j++)
+			region->macro_state[j] = CLK_OFF;
+	}
+
+	platform_set_drvdata(pdev, ocmem);
+
+	return 0;
+
+err_clk_disable:
+	clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+	return ret;
+}
+
+static int ocmem_dev_remove(struct platform_device *pdev)
+{
+	clk_bulk_disable_unprepare(ARRAY_SIZE(ocmem_clks), ocmem_clks);
+
+	return 0;
+}
+
+static const struct ocmem_config ocmem_8974_config = {
+	.num_regions = 3,
+	.macro_size = SZ_128K,
+};
+
+static const struct of_device_id ocmem_of_match[] = {
+	{ .compatible = "qcom,msm8974-ocmem", .data = &ocmem_8974_config },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, ocmem_of_match);
+
+static struct platform_driver ocmem_driver = {
+	.probe = ocmem_dev_probe,
+	.remove = ocmem_dev_remove,
+	.driver = {
+		.name = "ocmem",
+		.of_match_table = ocmem_of_match,
+	},
+};
+
+module_platform_driver(ocmem_driver);
+
+MODULE_DESCRIPTION("On Chip Memory (OCMEM) allocator for some Snapdragon SoCs");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig
index f518273cfbe3..c8c80df090d1 100644
--- a/drivers/soundwire/Kconfig
+++ b/drivers/soundwire/Kconfig
@@ -5,6 +5,7 @@
 
 menuconfig SOUNDWIRE
 	tristate "SoundWire support"
+	depends on ACPI || OF
 	help
 	  SoundWire is a 2-Pin interface with data and clock line ratified
 	  by the MIPI Alliance. SoundWire is used for transporting data
diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c
index f1e38a293967..13c54eac0cc3 100644
--- a/drivers/soundwire/intel.c
+++ b/drivers/soundwire/intel.c
@@ -900,7 +900,7 @@ static int intel_register_dai(struct sdw_intel *sdw)
 	/* Create PCM DAIs */
 	stream = &cdns->pcm;
 
-	ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, stream->num_in,
+	ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, cdns->pcm.num_in,
 			       off, stream->num_ch_in, true);
 	if (ret)
 		return ret;
@@ -931,7 +931,7 @@ static int intel_register_dai(struct sdw_intel *sdw)
 	if (ret)
 		return ret;
 
-	off += cdns->pdm.num_bd;
+	off += cdns->pdm.num_out;
 	ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, cdns->pdm.num_bd,
 			       off, stream->num_ch_bd, false);
 	if (ret)
diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c
index 48a63ca130d2..6473fa602f82 100644
--- a/drivers/soundwire/slave.c
+++ b/drivers/soundwire/slave.c
@@ -128,7 +128,8 @@ int sdw_of_find_slaves(struct sdw_bus *bus)
 	struct device_node *node;
 
 	for_each_child_of_node(bus->dev->of_node, node) {
-		int link_id, sdw_version, ret, len;
+		int link_id, ret, len;
+		unsigned int sdw_version;
 		const char *compat = NULL;
 		struct sdw_slave_id id;
 		const __be32 *addr;
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 6f1fa4c849a1..927d29eb92c6 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -125,4 +125,6 @@ source "drivers/staging/exfat/Kconfig"
 
 source "drivers/staging/qlge/Kconfig"
 
+source "drivers/staging/vboxsf/Kconfig"
+
 endif # STAGING
diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile
index a90f9b308c8d..f01f04199073 100644
--- a/drivers/staging/Makefile
+++ b/drivers/staging/Makefile
@@ -53,3 +53,4 @@ obj-$(CONFIG_UWB)		+= uwb/
 obj-$(CONFIG_USB_WUSB)		+= wusbcore/
 obj-$(CONFIG_EXFAT_FS)		+= exfat/
 obj-$(CONFIG_QLGE)		+= qlge/
+obj-$(CONFIG_VBOXSF_FS)		+= vboxsf/
diff --git a/drivers/staging/vboxsf/Kconfig b/drivers/staging/vboxsf/Kconfig
new file mode 100644
index 000000000000..b84586ae08b3
--- /dev/null
+++ b/drivers/staging/vboxsf/Kconfig
@@ -0,0 +1,10 @@
+config VBOXSF_FS
+	tristate "VirtualBox guest shared folder (vboxsf) support"
+	depends on X86 && VBOXGUEST
+	select NLS
+	help
+	  VirtualBox hosts can share folders with guests, this driver
+	  implements the Linux-guest side of this allowing folders exported
+	  by the host to be mounted under Linux.
+
+	  If you want to use shared folders in VirtualBox guests, answer Y or M.
diff --git a/drivers/staging/vboxsf/Makefile b/drivers/staging/vboxsf/Makefile
new file mode 100644
index 000000000000..9e4328e79623
--- /dev/null
+++ b/drivers/staging/vboxsf/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: MIT
+
+obj-$(CONFIG_VBOXSF_FS) += vboxsf.o
+
+vboxsf-y := dir.o file.o utils.o vboxsf_wrappers.o super.o
diff --git a/drivers/staging/vboxsf/TODO b/drivers/staging/vboxsf/TODO
new file mode 100644
index 000000000000..8b9193d0d4f0
--- /dev/null
+++ b/drivers/staging/vboxsf/TODO
@@ -0,0 +1,7 @@
+TODO:
+- Find a file-system developer to review this and give their Reviewed-By
+- Address any items coming up during review
+- Move to fs/vboxfs
+
+Please send any patches to Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+and Hans de Goede <hdegoede@redhat.com>
diff --git a/drivers/staging/vboxsf/dir.c b/drivers/staging/vboxsf/dir.c
new file mode 100644
index 000000000000..f260b5cc1646
--- /dev/null
+++ b/drivers/staging/vboxsf/dir.c
@@ -0,0 +1,418 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Directory inode and file operations
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/namei.h>
+#include <linux/vbox_utils.h>
+#include "vfsmod.h"
+
+static int vboxsf_dir_open(struct inode *inode, struct file *file)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+	struct shfl_createparms params = {};
+	struct vboxsf_dir_info *sf_d;
+	int err;
+
+	sf_d = vboxsf_dir_info_alloc();
+	if (!sf_d)
+		return -ENOMEM;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_DIRECTORY | SHFL_CF_ACT_OPEN_IF_EXISTS |
+			      SHFL_CF_ACT_FAIL_IF_NEW | SHFL_CF_ACCESS_READ;
+
+	err = vboxsf_create_at_dentry(file_dentry(file), &params);
+	if (err)
+		goto err_free_dir_info;
+
+	if (params.result != SHFL_FILE_EXISTS) {
+		err = -ENOENT;
+		goto err_close;
+	}
+
+	err = vboxsf_dir_read_all(sbi, sf_d, params.handle);
+	if (err)
+		goto err_close;
+
+	vboxsf_close(sbi->root, params.handle);
+	file->private_data = sf_d;
+	return 0;
+
+err_close:
+	vboxsf_close(sbi->root, params.handle);
+err_free_dir_info:
+	vboxsf_dir_info_free(sf_d);
+	return err;
+}
+
+static int vboxsf_dir_release(struct inode *inode, struct file *file)
+{
+	if (file->private_data)
+		vboxsf_dir_info_free(file->private_data);
+
+	return 0;
+}
+
+static unsigned int vboxsf_get_d_type(u32 mode)
+{
+	unsigned int d_type;
+
+	switch (mode & SHFL_TYPE_MASK) {
+	case SHFL_TYPE_FIFO:
+		d_type = DT_FIFO;
+		break;
+	case SHFL_TYPE_DEV_CHAR:
+		d_type = DT_CHR;
+		break;
+	case SHFL_TYPE_DIRECTORY:
+		d_type = DT_DIR;
+		break;
+	case SHFL_TYPE_DEV_BLOCK:
+		d_type = DT_BLK;
+		break;
+	case SHFL_TYPE_FILE:
+		d_type = DT_REG;
+		break;
+	case SHFL_TYPE_SYMLINK:
+		d_type = DT_LNK;
+		break;
+	case SHFL_TYPE_SOCKET:
+		d_type = DT_SOCK;
+		break;
+	case SHFL_TYPE_WHITEOUT:
+		d_type = DT_WHT;
+		break;
+	default:
+		d_type = DT_UNKNOWN;
+		break;
+	}
+	return d_type;
+}
+
+static bool vboxsf_dir_emit(struct file *dir, struct dir_context *ctx)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(file_inode(dir)->i_sb);
+	struct vboxsf_dir_info *sf_d = dir->private_data;
+	struct shfl_dirinfo *info;
+	struct vboxsf_dir_buf *b;
+	unsigned int d_type;
+	loff_t i, cur = 0;
+	ino_t fake_ino;
+	size_t size;
+	int err;
+
+	list_for_each_entry(b, &sf_d->info_list, head) {
+try_next_entry:
+		if (ctx->pos >= cur + b->entries) {
+			cur += b->entries;
+			continue;
+		}
+
+		/*
+		 * Note the vboxsf_dir_info objects we are iterating over here
+		 * are variable sized, so the info pointer may end up being
+		 * unaligned. This is how we get the data from the host.
+		 * Since vboxsf is only supported on x86 machines this is not
+		 * a problem.
+		 */
+		for (i = 0, info = b->buf; i < ctx->pos - cur; i++) {
+			size = offsetof(struct shfl_dirinfo, name.string) +
+			       info->name.size;
+			info = (struct shfl_dirinfo *)((uintptr_t)info + size);
+		}
+
+		/* Info now points to the right entry, emit it. */
+		d_type = vboxsf_get_d_type(info->info.attr.mode);
+
+		/*
+		 * On 32 bit systems pos is 64 signed, while ino is 32 bit
+		 * unsigned so fake_ino may overflow, check for this.
+		 */
+		if ((ino_t)(ctx->pos + 1) != (u64)(ctx->pos + 1)) {
+			vbg_err("vboxsf: fake ino overflow, truncating dir\n");
+			return false;
+		}
+		fake_ino = ctx->pos + 1;
+
+		if (sbi->nls) {
+			char d_name[NAME_MAX];
+
+			err = vboxsf_nlscpy(sbi, d_name, NAME_MAX,
+					    info->name.string.utf8,
+					    info->name.length);
+			if (err) {
+				/* skip erroneous entry and proceed */
+				ctx->pos += 1;
+				goto try_next_entry;
+			}
+
+			return dir_emit(ctx, d_name, strlen(d_name),
+					fake_ino, d_type);
+		}
+
+		return dir_emit(ctx, info->name.string.utf8, info->name.length,
+				fake_ino, d_type);
+	}
+
+	return false;
+}
+
+static int vboxsf_dir_iterate(struct file *dir, struct dir_context *ctx)
+{
+	bool keep_iterating;
+
+	for (keep_iterating = true; keep_iterating; ctx->pos += 1)
+		keep_iterating = vboxsf_dir_emit(dir, ctx);
+
+	return 0;
+}
+
+const struct file_operations vboxsf_dir_fops = {
+	.open = vboxsf_dir_open,
+	.iterate = vboxsf_dir_iterate,
+	.release = vboxsf_dir_release,
+	.read = generic_read_dir,
+	.llseek = generic_file_llseek,
+};
+
+/*
+ * This is called during name resolution/lookup to check if the @dentry in
+ * the cache is still valid. the job is handled by vboxsf_inode_revalidate.
+ */
+static int vboxsf_dentry_revalidate(struct dentry *dentry, unsigned int flags)
+{
+	if (flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (d_really_is_positive(dentry))
+		return vboxsf_inode_revalidate(dentry) == 0;
+	else
+		return vboxsf_stat_dentry(dentry, NULL) == -ENOENT;
+}
+
+const struct dentry_operations vboxsf_dentry_ops = {
+	.d_revalidate = vboxsf_dentry_revalidate
+};
+
+/* iops */
+
+static struct dentry *vboxsf_dir_lookup(struct inode *parent,
+					struct dentry *dentry,
+					unsigned int flags)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct shfl_fsobjinfo fsinfo;
+	struct inode *inode;
+	int err;
+
+	dentry->d_time = jiffies;
+
+	err = vboxsf_stat_dentry(dentry, &fsinfo);
+	if (err) {
+		inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
+	} else {
+		inode = vboxsf_new_inode(parent->i_sb);
+		if (!IS_ERR(inode))
+			vboxsf_init_inode(sbi, inode, &fsinfo);
+	}
+
+	return d_splice_alias(inode, dentry);
+}
+
+static int vboxsf_dir_instantiate(struct inode *parent, struct dentry *dentry,
+				  struct shfl_fsobjinfo *info)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct vboxsf_inode *sf_i;
+	struct inode *inode;
+
+	inode = vboxsf_new_inode(parent->i_sb);
+	if (IS_ERR(inode))
+		return PTR_ERR(inode);
+
+	sf_i = VBOXSF_I(inode);
+	/* The host may have given us different attr then requested */
+	sf_i->force_restat = 1;
+	vboxsf_init_inode(sbi, inode, info);
+
+	d_instantiate(dentry, inode);
+
+	return 0;
+}
+
+static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry,
+			     umode_t mode, int is_dir)
+{
+	struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct shfl_createparms params = {};
+	int err;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW |
+			      SHFL_CF_ACT_FAIL_IF_EXISTS |
+			      SHFL_CF_ACCESS_READWRITE |
+			      (is_dir ? SHFL_CF_DIRECTORY : 0);
+	params.info.attr.mode = (mode & 0777) |
+				(is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE);
+	params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING;
+
+	err = vboxsf_create_at_dentry(dentry, &params);
+	if (err)
+		return err;
+
+	if (params.result != SHFL_FILE_CREATED)
+		return -EPERM;
+
+	vboxsf_close(sbi->root, params.handle);
+
+	err = vboxsf_dir_instantiate(parent, dentry, &params.info);
+	if (err)
+		return err;
+
+	/* parent directory access/change time changed */
+	sf_parent_i->force_restat = 1;
+
+	return 0;
+}
+
+static int vboxsf_dir_mkfile(struct inode *parent, struct dentry *dentry,
+			     umode_t mode, bool excl)
+{
+	return vboxsf_dir_create(parent, dentry, mode, 0);
+}
+
+static int vboxsf_dir_mkdir(struct inode *parent, struct dentry *dentry,
+			    umode_t mode)
+{
+	return vboxsf_dir_create(parent, dentry, mode, 1);
+}
+
+static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
+	struct inode *inode = d_inode(dentry);
+	struct shfl_string *path;
+	u32 flags;
+	int err;
+
+	if (S_ISDIR(inode->i_mode))
+		flags = SHFL_REMOVE_DIR;
+	else
+		flags = SHFL_REMOVE_FILE;
+
+	if (S_ISLNK(inode->i_mode))
+		flags |= SHFL_REMOVE_SYMLINK;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	err = vboxsf_remove(sbi->root, path, flags);
+	__putname(path);
+	if (err)
+		return err;
+
+	/* parent directory access/change time changed */
+	sf_parent_i->force_restat = 1;
+
+	return 0;
+}
+
+static int vboxsf_dir_rename(struct inode *old_parent,
+			     struct dentry *old_dentry,
+			     struct inode *new_parent,
+			     struct dentry *new_dentry,
+			     unsigned int flags)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(old_parent->i_sb);
+	struct vboxsf_inode *sf_old_parent_i = VBOXSF_I(old_parent);
+	struct vboxsf_inode *sf_new_parent_i = VBOXSF_I(new_parent);
+	u32 shfl_flags = SHFL_RENAME_FILE | SHFL_RENAME_REPLACE_IF_EXISTS;
+	struct shfl_string *old_path, *new_path;
+	int err;
+
+	if (flags)
+		return -EINVAL;
+
+	old_path = vboxsf_path_from_dentry(sbi, old_dentry);
+	if (IS_ERR(old_path))
+		return PTR_ERR(old_path);
+
+	new_path = vboxsf_path_from_dentry(sbi, new_dentry);
+	if (IS_ERR(new_path)) {
+		err = PTR_ERR(new_path);
+		goto err_put_old_path;
+	}
+
+	if (d_inode(old_dentry)->i_mode & S_IFDIR)
+		shfl_flags = 0;
+
+	err = vboxsf_rename(sbi->root, old_path, new_path, shfl_flags);
+	if (err == 0) {
+		/* parent directories access/change time changed */
+		sf_new_parent_i->force_restat = 1;
+		sf_old_parent_i->force_restat = 1;
+	}
+
+	__putname(new_path);
+err_put_old_path:
+	__putname(old_path);
+	return err;
+}
+
+static int vboxsf_dir_symlink(struct inode *parent, struct dentry *dentry,
+			      const char *symname)
+{
+	struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+	int symname_size = strlen(symname) + 1;
+	struct shfl_string *path, *ssymname;
+	struct shfl_fsobjinfo info;
+	int err;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	ssymname = kmalloc(SHFLSTRING_HEADER_SIZE + symname_size, GFP_KERNEL);
+	if (!ssymname) {
+		__putname(path);
+		return -ENOMEM;
+	}
+	ssymname->length = symname_size - 1;
+	ssymname->size = symname_size;
+	memcpy(ssymname->string.utf8, symname, symname_size);
+
+	err = vboxsf_symlink(sbi->root, path, ssymname, &info);
+	kfree(ssymname);
+	__putname(path);
+	if (err) {
+		/* -EROFS means symlinks are note support -> -EPERM */
+		return (err == -EROFS) ? -EPERM : err;
+	}
+
+	err = vboxsf_dir_instantiate(parent, dentry, &info);
+	if (err)
+		return err;
+
+	/* parent directory access/change time changed */
+	sf_parent_i->force_restat = 1;
+	return 0;
+}
+
+const struct inode_operations vboxsf_dir_iops = {
+	.lookup  = vboxsf_dir_lookup,
+	.create  = vboxsf_dir_mkfile,
+	.mkdir   = vboxsf_dir_mkdir,
+	.rmdir   = vboxsf_dir_unlink,
+	.unlink  = vboxsf_dir_unlink,
+	.rename  = vboxsf_dir_rename,
+	.symlink = vboxsf_dir_symlink,
+	.getattr = vboxsf_getattr,
+	.setattr = vboxsf_setattr,
+};
diff --git a/drivers/staging/vboxsf/file.c b/drivers/staging/vboxsf/file.c
new file mode 100644
index 000000000000..4b61ccf83fca
--- /dev/null
+++ b/drivers/staging/vboxsf/file.c
@@ -0,0 +1,370 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Regular file inode and file ops.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/mm.h>
+#include <linux/page-flags.h>
+#include <linux/pagemap.h>
+#include <linux/highmem.h>
+#include <linux/sizes.h>
+#include "vfsmod.h"
+
+struct vboxsf_handle {
+	u64 handle;
+	u32 root;
+	u32 access_flags;
+	struct kref refcount;
+	struct list_head head;
+};
+
+static int vboxsf_file_open(struct inode *inode, struct file *file)
+{
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+	struct shfl_createparms params = {};
+	struct vboxsf_handle *sf_handle;
+	u32 access_flags = 0;
+	int err;
+
+	sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL);
+	if (!sf_handle)
+		return -ENOMEM;
+
+	/*
+	 * We check the value of params.handle afterwards to find out if
+	 * the call succeeded or failed, as the API does not seem to cleanly
+	 * distinguish error and informational messages.
+	 *
+	 * Furthermore, we must set params.handle to SHFL_HANDLE_NIL to
+	 * make the shared folders host service use our mode parameter.
+	 */
+	params.handle = SHFL_HANDLE_NIL;
+	if (file->f_flags & O_CREAT) {
+		params.create_flags |= SHFL_CF_ACT_CREATE_IF_NEW;
+		/*
+		 * We ignore O_EXCL, as the Linux kernel seems to call create
+		 * beforehand itself, so O_EXCL should always fail.
+		 */
+		if (file->f_flags & O_TRUNC)
+			params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS;
+		else
+			params.create_flags |= SHFL_CF_ACT_OPEN_IF_EXISTS;
+	} else {
+		params.create_flags |= SHFL_CF_ACT_FAIL_IF_NEW;
+		if (file->f_flags & O_TRUNC)
+			params.create_flags |= SHFL_CF_ACT_OVERWRITE_IF_EXISTS;
+	}
+
+	switch (file->f_flags & O_ACCMODE) {
+	case O_RDONLY:
+		access_flags |= SHFL_CF_ACCESS_READ;
+		break;
+
+	case O_WRONLY:
+		access_flags |= SHFL_CF_ACCESS_WRITE;
+		break;
+
+	case O_RDWR:
+		access_flags |= SHFL_CF_ACCESS_READWRITE;
+		break;
+
+	default:
+		WARN_ON(1);
+	}
+
+	if (file->f_flags & O_APPEND)
+		access_flags |= SHFL_CF_ACCESS_APPEND;
+
+	params.create_flags |= access_flags;
+	params.info.attr.mode = inode->i_mode;
+
+	err = vboxsf_create_at_dentry(file_dentry(file), &params);
+	if (err == 0 && params.handle == SHFL_HANDLE_NIL)
+		err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT;
+	if (err) {
+		kfree(sf_handle);
+		return err;
+	}
+
+	/* the host may have given us different attr then requested */
+	sf_i->force_restat = 1;
+
+	/* init our handle struct and add it to the inode's handles list */
+	sf_handle->handle = params.handle;
+	sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
+	sf_handle->access_flags = access_flags;
+	kref_init(&sf_handle->refcount);
+
+	mutex_lock(&sf_i->handle_list_mutex);
+	list_add(&sf_handle->head, &sf_i->handle_list);
+	mutex_unlock(&sf_i->handle_list_mutex);
+
+	file->private_data = sf_handle;
+	return 0;
+}
+
+static void vboxsf_handle_release(struct kref *refcount)
+{
+	struct vboxsf_handle *sf_handle =
+		container_of(refcount, struct vboxsf_handle, refcount);
+
+	vboxsf_close(sf_handle->root, sf_handle->handle);
+	kfree(sf_handle);
+}
+
+static int vboxsf_file_release(struct inode *inode, struct file *file)
+{
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+	struct vboxsf_handle *sf_handle = file->private_data;
+
+	/*
+	 * When a file is closed on our (the guest) side, we want any subsequent
+	 * accesses done on the host side to see all changes done from our side.
+	 */
+	filemap_write_and_wait(inode->i_mapping);
+
+	mutex_lock(&sf_i->handle_list_mutex);
+	list_del(&sf_handle->head);
+	mutex_unlock(&sf_i->handle_list_mutex);
+
+	kref_put(&sf_handle->refcount, vboxsf_handle_release);
+	return 0;
+}
+
+/*
+ * Write back dirty pages now, because there may not be any suitable
+ * open files later
+ */
+static void vboxsf_vma_close(struct vm_area_struct *vma)
+{
+	filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct vboxsf_file_vm_ops = {
+	.close		= vboxsf_vma_close,
+	.fault		= filemap_fault,
+	.map_pages	= filemap_map_pages,
+};
+
+static int vboxsf_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int err;
+
+	err = generic_file_mmap(file, vma);
+	if (!err)
+		vma->vm_ops = &vboxsf_file_vm_ops;
+
+	return err;
+}
+
+/*
+ * Note that since we are accessing files on the host's filesystem, files
+ * may always be changed underneath us by the host!
+ *
+ * The vboxsf API between the guest and the host does not offer any functions
+ * to deal with this. There is no inode-generation to check for changes, no
+ * events / callback on changes and no way to lock files.
+ *
+ * To avoid returning stale data when a file gets *opened* on our (the guest)
+ * side, we do a "stat" on the host side, then compare the mtime with the
+ * last known mtime and invalidate the page-cache if they differ.
+ * This is done from vboxsf_inode_revalidate().
+ *
+ * When reads are done through the read_iter fop, it is possible to do
+ * further cache revalidation then, there are 3 options to deal with this:
+ *
+ * 1)  Rely solely on the revalidation done at open time
+ * 2)  Do another "stat" and compare mtime again. Unfortunately the vboxsf
+ *     host API does not allow stat on handles, so we would need to use
+ *     file->f_path.dentry and the stat will then fail if the file was unlinked
+ *     or renamed (and there is no thing like NFS' silly-rename). So we get:
+ * 2a) "stat" and compare mtime, on stat failure invalidate the cache
+ * 2b) "stat" and compare mtime, on stat failure do nothing
+ * 3)  Simply always call invalidate_inode_pages2_range on the range of the read
+ *
+ * Currently we are keeping things KISS and using option 1. this allows
+ * directly using generic_file_read_iter without wrapping it.
+ *
+ * This means that only data written on the host side before open() on
+ * the guest side is guaranteed to be seen by the guest. If necessary
+ * we may provide other read-cache strategies in the future and make this
+ * configurable through a mount option.
+ */
+const struct file_operations vboxsf_reg_fops = {
+	.llseek = generic_file_llseek,
+	.read_iter = generic_file_read_iter,
+	.write_iter = generic_file_write_iter,
+	.mmap = vboxsf_file_mmap,
+	.open = vboxsf_file_open,
+	.release = vboxsf_file_release,
+	.fsync = noop_fsync,
+	.splice_read = generic_file_splice_read,
+};
+
+const struct inode_operations vboxsf_reg_iops = {
+	.getattr = vboxsf_getattr,
+	.setattr = vboxsf_setattr
+};
+
+static int vboxsf_readpage(struct file *file, struct page *page)
+{
+	struct vboxsf_handle *sf_handle = file->private_data;
+	loff_t off = page_offset(page);
+	u32 nread = PAGE_SIZE;
+	u8 *buf;
+	int err;
+
+	buf = kmap(page);
+
+	err = vboxsf_read(sf_handle->root, sf_handle->handle, off, &nread, buf);
+	if (err == 0) {
+		memset(&buf[nread], 0, PAGE_SIZE - nread);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
+	} else {
+		SetPageError(page);
+	}
+
+	kunmap(page);
+	unlock_page(page);
+	return err;
+}
+
+static struct vboxsf_handle *vboxsf_get_write_handle(struct vboxsf_inode *sf_i)
+{
+	struct vboxsf_handle *h, *sf_handle = NULL;
+
+	mutex_lock(&sf_i->handle_list_mutex);
+	list_for_each_entry(h, &sf_i->handle_list, head) {
+		if (h->access_flags == SHFL_CF_ACCESS_WRITE ||
+		    h->access_flags == SHFL_CF_ACCESS_READWRITE) {
+			kref_get(&h->refcount);
+			sf_handle = h;
+			break;
+		}
+	}
+	mutex_unlock(&sf_i->handle_list_mutex);
+
+	return sf_handle;
+}
+
+static int vboxsf_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct inode *inode = page->mapping->host;
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+	struct vboxsf_handle *sf_handle;
+	loff_t off = page_offset(page);
+	loff_t size = i_size_read(inode);
+	u32 nwrite = PAGE_SIZE;
+	u8 *buf;
+	int err;
+
+	if (off + PAGE_SIZE > size)
+		nwrite = size & ~PAGE_MASK;
+
+	sf_handle = vboxsf_get_write_handle(sf_i);
+	if (!sf_handle)
+		return -EBADF;
+
+	buf = kmap(page);
+	err = vboxsf_write(sf_handle->root, sf_handle->handle,
+			   off, &nwrite, buf);
+	kunmap(page);
+
+	kref_put(&sf_handle->refcount, vboxsf_handle_release);
+
+	if (err == 0) {
+		ClearPageError(page);
+		/* mtime changed */
+		sf_i->force_restat = 1;
+	} else {
+		ClearPageUptodate(page);
+	}
+
+	unlock_page(page);
+	return err;
+}
+
+static int vboxsf_write_end(struct file *file, struct address_space *mapping,
+			    loff_t pos, unsigned int len, unsigned int copied,
+			    struct page *page, void *fsdata)
+{
+	struct inode *inode = mapping->host;
+	struct vboxsf_handle *sf_handle = file->private_data;
+	unsigned int from = pos & ~PAGE_MASK;
+	u32 nwritten = len;
+	u8 *buf;
+	int err;
+
+	buf = kmap(page);
+	err = vboxsf_write(sf_handle->root, sf_handle->handle,
+			   pos, &nwritten, buf + from);
+	kunmap(page);
+
+	if (err) {
+		nwritten = 0;
+		goto out;
+	}
+
+	/* mtime changed */
+	VBOXSF_I(inode)->force_restat = 1;
+
+	if (!PageUptodate(page) && nwritten == PAGE_SIZE)
+		SetPageUptodate(page);
+
+	pos += nwritten;
+	if (pos > inode->i_size)
+		i_size_write(inode, pos);
+
+out:
+	unlock_page(page);
+	put_page(page);
+
+	return nwritten;
+}
+
+const struct address_space_operations vboxsf_reg_aops = {
+	.readpage = vboxsf_readpage,
+	.writepage = vboxsf_writepage,
+	.set_page_dirty = __set_page_dirty_nobuffers,
+	.write_begin = simple_write_begin,
+	.write_end = vboxsf_write_end,
+};
+
+static const char *vboxsf_get_link(struct dentry *dentry, struct inode *inode,
+				   struct delayed_call *done)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+	struct shfl_string *path;
+	char *link;
+	int err;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return (char *)path;
+
+	link = kzalloc(PATH_MAX, GFP_KERNEL);
+	if (!link) {
+		__putname(path);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	err = vboxsf_readlink(sbi->root, path, PATH_MAX, link);
+	__putname(path);
+	if (err) {
+		kfree(link);
+		return ERR_PTR(err);
+	}
+
+	set_delayed_call(done, kfree_link, link);
+	return link;
+}
+
+const struct inode_operations vboxsf_lnk_iops = {
+	.get_link = vboxsf_get_link
+};
diff --git a/drivers/staging/vboxsf/shfl_hostintf.h b/drivers/staging/vboxsf/shfl_hostintf.h
new file mode 100644
index 000000000000..aca829062c12
--- /dev/null
+++ b/drivers/staging/vboxsf/shfl_hostintf.h
@@ -0,0 +1,901 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * VirtualBox Shared Folders: host interface definition.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#ifndef SHFL_HOSTINTF_H
+#define SHFL_HOSTINTF_H
+
+#include <linux/vbox_vmmdev_types.h>
+
+/* The max in/out buffer size for a FN_READ or FN_WRITE call */
+#define SHFL_MAX_RW_COUNT           (16 * SZ_1M)
+
+/*
+ * Structures shared between guest and the service
+ * can be relocated and use offsets to point to variable
+ * length parts.
+ *
+ * Shared folders protocol works with handles.
+ * Before doing any action on a file system object,
+ * one have to obtain the object handle via a SHFL_FN_CREATE
+ * request. A handle must be closed with SHFL_FN_CLOSE.
+ */
+
+enum {
+	SHFL_FN_QUERY_MAPPINGS = 1,	/* Query mappings changes. */
+	SHFL_FN_QUERY_MAP_NAME = 2,	/* Query map name. */
+	SHFL_FN_CREATE = 3,		/* Open/create object. */
+	SHFL_FN_CLOSE = 4,		/* Close object handle. */
+	SHFL_FN_READ = 5,		/* Read object content. */
+	SHFL_FN_WRITE = 6,		/* Write new object content. */
+	SHFL_FN_LOCK = 7,		/* Lock/unlock a range in the object. */
+	SHFL_FN_LIST = 8,		/* List object content. */
+	SHFL_FN_INFORMATION = 9,	/* Query/set object information. */
+	/* Note function number 10 is not used! */
+	SHFL_FN_REMOVE = 11,		/* Remove object */
+	SHFL_FN_MAP_FOLDER_OLD = 12,	/* Map folder (legacy) */
+	SHFL_FN_UNMAP_FOLDER = 13,	/* Unmap folder */
+	SHFL_FN_RENAME = 14,		/* Rename object */
+	SHFL_FN_FLUSH = 15,		/* Flush file */
+	SHFL_FN_SET_UTF8 = 16,		/* Select UTF8 filename encoding */
+	SHFL_FN_MAP_FOLDER = 17,	/* Map folder */
+	SHFL_FN_READLINK = 18,		/* Read symlink dest (as of VBox 4.0) */
+	SHFL_FN_SYMLINK = 19,		/* Create symlink (as of VBox 4.0) */
+	SHFL_FN_SET_SYMLINKS = 20,	/* Ask host to show symlinks (4.0+) */
+};
+
+/* Root handles for a mapping are of type u32, Root handles are unique. */
+#define SHFL_ROOT_NIL		UINT_MAX
+
+/* Shared folders handle for an opened object are of type u64. */
+#define SHFL_HANDLE_NIL		ULLONG_MAX
+
+/* Hardcoded maximum length (in chars) of a shared folder name. */
+#define SHFL_MAX_LEN         (256)
+/* Hardcoded maximum number of shared folder mapping available to the guest. */
+#define SHFL_MAX_MAPPINGS    (64)
+
+/** Shared folder string buffer structure. */
+struct shfl_string {
+	/** Allocated size of the string member in bytes. */
+	u16 size;
+
+	/** Length of string without trailing nul in bytes. */
+	u16 length;
+
+	/** UTF-8 or UTF-16 string. Nul terminated. */
+	union {
+		u8 utf8[2];
+		u16 utf16[1];
+		u16 ucs2[1]; /* misnomer, use utf16. */
+	} string;
+};
+VMMDEV_ASSERT_SIZE(shfl_string, 6);
+
+/* The size of shfl_string w/o the string part. */
+#define SHFLSTRING_HEADER_SIZE  4
+
+/* Calculate size of the string. */
+static inline u32 shfl_string_buf_size(const struct shfl_string *string)
+{
+	return string ? SHFLSTRING_HEADER_SIZE + string->size : 0;
+}
+
+/* Set user id on execution (S_ISUID). */
+#define SHFL_UNIX_ISUID             0004000U
+/* Set group id on execution (S_ISGID). */
+#define SHFL_UNIX_ISGID             0002000U
+/* Sticky bit (S_ISVTX / S_ISTXT). */
+#define SHFL_UNIX_ISTXT             0001000U
+
+/* Owner readable (S_IRUSR). */
+#define SHFL_UNIX_IRUSR             0000400U
+/* Owner writable (S_IWUSR). */
+#define SHFL_UNIX_IWUSR             0000200U
+/* Owner executable (S_IXUSR). */
+#define SHFL_UNIX_IXUSR             0000100U
+
+/* Group readable (S_IRGRP). */
+#define SHFL_UNIX_IRGRP             0000040U
+/* Group writable (S_IWGRP). */
+#define SHFL_UNIX_IWGRP             0000020U
+/* Group executable (S_IXGRP). */
+#define SHFL_UNIX_IXGRP             0000010U
+
+/* Other readable (S_IROTH). */
+#define SHFL_UNIX_IROTH             0000004U
+/* Other writable (S_IWOTH). */
+#define SHFL_UNIX_IWOTH             0000002U
+/* Other executable (S_IXOTH). */
+#define SHFL_UNIX_IXOTH             0000001U
+
+/* Named pipe (fifo) (S_IFIFO). */
+#define SHFL_TYPE_FIFO              0010000U
+/* Character device (S_IFCHR). */
+#define SHFL_TYPE_DEV_CHAR          0020000U
+/* Directory (S_IFDIR). */
+#define SHFL_TYPE_DIRECTORY         0040000U
+/* Block device (S_IFBLK). */
+#define SHFL_TYPE_DEV_BLOCK         0060000U
+/* Regular file (S_IFREG). */
+#define SHFL_TYPE_FILE              0100000U
+/* Symbolic link (S_IFLNK). */
+#define SHFL_TYPE_SYMLINK           0120000U
+/* Socket (S_IFSOCK). */
+#define SHFL_TYPE_SOCKET            0140000U
+/* Whiteout (S_IFWHT). */
+#define SHFL_TYPE_WHITEOUT          0160000U
+/* Type mask (S_IFMT). */
+#define SHFL_TYPE_MASK              0170000U
+
+/* Checks the mode flags indicate a directory (S_ISDIR). */
+#define SHFL_IS_DIRECTORY(m)   (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_DIRECTORY)
+/* Checks the mode flags indicate a symbolic link (S_ISLNK). */
+#define SHFL_IS_SYMLINK(m)     (((m) & SHFL_TYPE_MASK) == SHFL_TYPE_SYMLINK)
+
+/** The available additional information in a shfl_fsobjattr object. */
+enum shfl_fsobjattr_add {
+	/** No additional information is available / requested. */
+	SHFLFSOBJATTRADD_NOTHING = 1,
+	/**
+	 * The additional unix attributes (shfl_fsobjattr::u::unix_attr) are
+	 *  available / requested.
+	 */
+	SHFLFSOBJATTRADD_UNIX,
+	/**
+	 * The additional extended attribute size (shfl_fsobjattr::u::size) is
+	 *  available / requested.
+	 */
+	SHFLFSOBJATTRADD_EASIZE,
+	/**
+	 * The last valid item (inclusive).
+	 * The valid range is SHFLFSOBJATTRADD_NOTHING thru
+	 * SHFLFSOBJATTRADD_LAST.
+	 */
+	SHFLFSOBJATTRADD_LAST = SHFLFSOBJATTRADD_EASIZE,
+
+	/** The usual 32-bit hack. */
+	SHFLFSOBJATTRADD_32BIT_SIZE_HACK = 0x7fffffff
+};
+
+/**
+ * Additional unix Attributes, these are available when
+ * shfl_fsobjattr.additional == SHFLFSOBJATTRADD_UNIX.
+ */
+struct shfl_fsobjattr_unix {
+	/**
+	 * The user owning the filesystem object (st_uid).
+	 * This field is ~0U if not supported.
+	 */
+	u32 uid;
+
+	/**
+	 * The group the filesystem object is assigned (st_gid).
+	 * This field is ~0U if not supported.
+	 */
+	u32 gid;
+
+	/**
+	 * Number of hard links to this filesystem object (st_nlink).
+	 * This field is 1 if the filesystem doesn't support hardlinking or
+	 * the information isn't available.
+	 */
+	u32 hardlinks;
+
+	/**
+	 * The device number of the device which this filesystem object resides
+	 * on (st_dev). This field is 0 if this information is not available.
+	 */
+	u32 inode_id_device;
+
+	/**
+	 * The unique identifier (within the filesystem) of this filesystem
+	 * object (st_ino). Together with inode_id_device, this field can be
+	 * used as a OS wide unique id, when both their values are not 0.
+	 * This field is 0 if the information is not available.
+	 */
+	u64 inode_id;
+
+	/**
+	 * User flags (st_flags).
+	 * This field is 0 if this information is not available.
+	 */
+	u32 flags;
+
+	/**
+	 * The current generation number (st_gen).
+	 * This field is 0 if this information is not available.
+	 */
+	u32 generation_id;
+
+	/**
+	 * The device number of a char. or block device type object (st_rdev).
+	 * This field is 0 if the file isn't a char. or block device or when
+	 * the OS doesn't use the major+minor device idenfication scheme.
+	 */
+	u32 device;
+} __packed;
+
+/** Extended attribute size. */
+struct shfl_fsobjattr_easize {
+	/** Size of EAs. */
+	s64 cb;
+} __packed;
+
+/** Shared folder filesystem object attributes. */
+struct shfl_fsobjattr {
+	/** Mode flags (st_mode). SHFL_UNIX_*, SHFL_TYPE_*, and SHFL_DOS_*. */
+	u32 mode;
+
+	/** The additional attributes available. */
+	enum shfl_fsobjattr_add additional;
+
+	/**
+	 * Additional attributes.
+	 *
+	 * Unless explicitly specified to an API, the API can provide additional
+	 * data as it is provided by the underlying OS.
+	 */
+	union {
+		struct shfl_fsobjattr_unix unix_attr;
+		struct shfl_fsobjattr_easize size;
+	} __packed u;
+} __packed;
+VMMDEV_ASSERT_SIZE(shfl_fsobjattr, 44);
+
+struct shfl_timespec {
+	s64 ns_relative_to_unix_epoch;
+};
+
+/** Filesystem object information structure. */
+struct shfl_fsobjinfo {
+	/**
+	 * Logical size (st_size).
+	 * For normal files this is the size of the file.
+	 * For symbolic links, this is the length of the path name contained
+	 * in the symbolic link.
+	 * For other objects this fields needs to be specified.
+	 */
+	s64 size;
+
+	/** Disk allocation size (st_blocks * DEV_BSIZE). */
+	s64 allocated;
+
+	/** Time of last access (st_atime). */
+	struct shfl_timespec access_time;
+
+	/** Time of last data modification (st_mtime). */
+	struct shfl_timespec modification_time;
+
+	/**
+	 * Time of last status change (st_ctime).
+	 * If not available this is set to modification_time.
+	 */
+	struct shfl_timespec change_time;
+
+	/**
+	 * Time of file birth (st_birthtime).
+	 * If not available this is set to change_time.
+	 */
+	struct shfl_timespec birth_time;
+
+	/** Attributes. */
+	struct shfl_fsobjattr attr;
+
+} __packed;
+VMMDEV_ASSERT_SIZE(shfl_fsobjinfo, 92);
+
+/**
+ * result of an open/create request.
+ * Along with handle value the result code
+ * identifies what has happened while
+ * trying to open the object.
+ */
+enum shfl_create_result {
+	SHFL_NO_RESULT,
+	/** Specified path does not exist. */
+	SHFL_PATH_NOT_FOUND,
+	/** Path to file exists, but the last component does not. */
+	SHFL_FILE_NOT_FOUND,
+	/** File already exists and either has been opened or not. */
+	SHFL_FILE_EXISTS,
+	/** New file was created. */
+	SHFL_FILE_CREATED,
+	/** Existing file was replaced or overwritten. */
+	SHFL_FILE_REPLACED
+};
+
+/* No flags. Initialization value. */
+#define SHFL_CF_NONE                  (0x00000000)
+
+/*
+ * Only lookup the object, do not return a handle. When this is set all other
+ * flags are ignored.
+ */
+#define SHFL_CF_LOOKUP                (0x00000001)
+
+/*
+ * Open parent directory of specified object.
+ * Useful for the corresponding Windows FSD flag
+ * and for opening paths like \\dir\\*.* to search the 'dir'.
+ */
+#define SHFL_CF_OPEN_TARGET_DIRECTORY (0x00000002)
+
+/* Create/open a directory. */
+#define SHFL_CF_DIRECTORY             (0x00000004)
+
+/*
+ *  Open/create action to do if object exists
+ *  and if the object does not exists.
+ *  REPLACE file means atomically DELETE and CREATE.
+ *  OVERWRITE file means truncating the file to 0 and
+ *  setting new size.
+ *  When opening an existing directory REPLACE and OVERWRITE
+ *  actions are considered invalid, and cause returning
+ *  FILE_EXISTS with NIL handle.
+ */
+#define SHFL_CF_ACT_MASK_IF_EXISTS      (0x000000f0)
+#define SHFL_CF_ACT_MASK_IF_NEW         (0x00000f00)
+
+/* What to do if object exists. */
+#define SHFL_CF_ACT_OPEN_IF_EXISTS      (0x00000000)
+#define SHFL_CF_ACT_FAIL_IF_EXISTS      (0x00000010)
+#define SHFL_CF_ACT_REPLACE_IF_EXISTS   (0x00000020)
+#define SHFL_CF_ACT_OVERWRITE_IF_EXISTS (0x00000030)
+
+/* What to do if object does not exist. */
+#define SHFL_CF_ACT_CREATE_IF_NEW       (0x00000000)
+#define SHFL_CF_ACT_FAIL_IF_NEW         (0x00000100)
+
+/* Read/write requested access for the object. */
+#define SHFL_CF_ACCESS_MASK_RW          (0x00003000)
+
+/* No access requested. */
+#define SHFL_CF_ACCESS_NONE             (0x00000000)
+/* Read access requested. */
+#define SHFL_CF_ACCESS_READ             (0x00001000)
+/* Write access requested. */
+#define SHFL_CF_ACCESS_WRITE            (0x00002000)
+/* Read/Write access requested. */
+#define SHFL_CF_ACCESS_READWRITE	(0x00003000)
+
+/* Requested share access for the object. */
+#define SHFL_CF_ACCESS_MASK_DENY        (0x0000c000)
+
+/* Allow any access. */
+#define SHFL_CF_ACCESS_DENYNONE         (0x00000000)
+/* Do not allow read. */
+#define SHFL_CF_ACCESS_DENYREAD         (0x00004000)
+/* Do not allow write. */
+#define SHFL_CF_ACCESS_DENYWRITE        (0x00008000)
+/* Do not allow access. */
+#define SHFL_CF_ACCESS_DENYALL          (0x0000c000)
+
+/* Requested access to attributes of the object. */
+#define SHFL_CF_ACCESS_MASK_ATTR        (0x00030000)
+
+/* No access requested. */
+#define SHFL_CF_ACCESS_ATTR_NONE        (0x00000000)
+/* Read access requested. */
+#define SHFL_CF_ACCESS_ATTR_READ        (0x00010000)
+/* Write access requested. */
+#define SHFL_CF_ACCESS_ATTR_WRITE       (0x00020000)
+/* Read/Write access requested. */
+#define SHFL_CF_ACCESS_ATTR_READWRITE   (0x00030000)
+
+/*
+ * The file is opened in append mode.
+ * Ignored if SHFL_CF_ACCESS_WRITE is not set.
+ */
+#define SHFL_CF_ACCESS_APPEND           (0x00040000)
+
+/** Create parameters buffer struct for SHFL_FN_CREATE call */
+struct shfl_createparms {
+	/** Returned handle of opened object. */
+	u64 handle;
+
+	/** Returned result of the operation */
+	enum shfl_create_result result;
+
+	/** SHFL_CF_* */
+	u32 create_flags;
+
+	/**
+	 * Attributes of object to create and
+	 * returned actual attributes of opened/created object.
+	 */
+	struct shfl_fsobjinfo info;
+} __packed;
+
+/** Shared Folder directory information */
+struct shfl_dirinfo {
+	/** Full information about the object. */
+	struct shfl_fsobjinfo info;
+	/**
+	 * The length of the short field (number of UTF16 chars).
+	 * It is 16-bit for reasons of alignment.
+	 */
+	u16 short_name_len;
+	/**
+	 * The short name for 8.3 compatibility.
+	 * Empty string if not available.
+	 */
+	u16 short_name[14];
+	struct shfl_string name;
+};
+
+/** Shared folder filesystem properties. */
+struct shfl_fsproperties {
+	/**
+	 * The maximum size of a filesystem object name.
+	 * This does not include the '\\0'.
+	 */
+	u32 max_component_len;
+
+	/**
+	 * True if the filesystem is remote.
+	 * False if the filesystem is local.
+	 */
+	bool remote;
+
+	/**
+	 * True if the filesystem is case sensitive.
+	 * False if the filesystem is case insensitive.
+	 */
+	bool case_sensitive;
+
+	/**
+	 * True if the filesystem is mounted read only.
+	 * False if the filesystem is mounted read write.
+	 */
+	bool read_only;
+
+	/**
+	 * True if the filesystem can encode unicode object names.
+	 * False if it can't.
+	 */
+	bool supports_unicode;
+
+	/**
+	 * True if the filesystem is compresses.
+	 * False if it isn't or we don't know.
+	 */
+	bool compressed;
+
+	/**
+	 * True if the filesystem compresses of individual files.
+	 * False if it doesn't or we don't know.
+	 */
+	bool file_compression;
+};
+VMMDEV_ASSERT_SIZE(shfl_fsproperties, 12);
+
+struct shfl_volinfo {
+	s64 total_allocation_bytes;
+	s64 available_allocation_bytes;
+	u32 bytes_per_allocation_unit;
+	u32 bytes_per_sector;
+	u32 serial;
+	struct shfl_fsproperties properties;
+};
+
+
+/** SHFL_FN_MAP_FOLDER Parameters structure. */
+struct shfl_map_folder {
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string buffer.
+	 */
+	struct vmmdev_hgcm_function_parameter path;
+
+	/**
+	 * pointer, out: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * pointer, in: UTF16
+	 * Path delimiter
+	 */
+	struct vmmdev_hgcm_function_parameter delimiter;
+
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Case senstive flag
+	 */
+	struct vmmdev_hgcm_function_parameter case_sensitive;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_MAP_FOLDER (4)
+
+
+/** SHFL_FN_UNMAP_FOLDER Parameters structure. */
+struct shfl_unmap_folder {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_UNMAP_FOLDER (1)
+
+
+/** SHFL_FN_CREATE Parameters structure. */
+struct shfl_create {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string buffer.
+	 */
+	struct vmmdev_hgcm_function_parameter path;
+
+	/**
+	 * pointer, in/out:
+	 * Points to struct shfl_createparms buffer.
+	 */
+	struct vmmdev_hgcm_function_parameter parms;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_CREATE (3)
+
+
+/** SHFL_FN_CLOSE Parameters structure. */
+struct shfl_close {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * value64, in:
+	 * SHFLHANDLE (u64) of object to close.
+	 */
+	struct vmmdev_hgcm_function_parameter handle;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_CLOSE (2)
+
+
+/** SHFL_FN_READ Parameters structure. */
+struct shfl_read {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * value64, in:
+	 * SHFLHANDLE (u64) of object to read from.
+	 */
+	struct vmmdev_hgcm_function_parameter handle;
+
+	/**
+	 * value64, in:
+	 * Offset to read from.
+	 */
+	struct vmmdev_hgcm_function_parameter offset;
+
+	/**
+	 * value64, in/out:
+	 * Bytes to read/How many were read.
+	 */
+	struct vmmdev_hgcm_function_parameter cb;
+
+	/**
+	 * pointer, out:
+	 * Buffer to place data to.
+	 */
+	struct vmmdev_hgcm_function_parameter buffer;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_READ (5)
+
+
+/** SHFL_FN_WRITE Parameters structure. */
+struct shfl_write {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * value64, in:
+	 * SHFLHANDLE (u64) of object to write to.
+	 */
+	struct vmmdev_hgcm_function_parameter handle;
+
+	/**
+	 * value64, in:
+	 * Offset to write to.
+	 */
+	struct vmmdev_hgcm_function_parameter offset;
+
+	/**
+	 * value64, in/out:
+	 * Bytes to write/How many were written.
+	 */
+	struct vmmdev_hgcm_function_parameter cb;
+
+	/**
+	 * pointer, in:
+	 * Data to write.
+	 */
+	struct vmmdev_hgcm_function_parameter buffer;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_WRITE (5)
+
+
+/*
+ * SHFL_FN_LIST
+ * Listing information includes variable length RTDIRENTRY[EX] structures.
+ */
+
+#define SHFL_LIST_NONE			0
+#define SHFL_LIST_RETURN_ONE		1
+
+/** SHFL_FN_LIST Parameters structure. */
+struct shfl_list {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * value64, in:
+	 * SHFLHANDLE (u64) of object to be listed.
+	 */
+	struct vmmdev_hgcm_function_parameter handle;
+
+	/**
+	 * value32, in:
+	 * List flags SHFL_LIST_*.
+	 */
+	struct vmmdev_hgcm_function_parameter flags;
+
+	/**
+	 * value32, in/out:
+	 * Bytes to be used for listing information/How many bytes were used.
+	 */
+	struct vmmdev_hgcm_function_parameter cb;
+
+	/**
+	 * pointer, in/optional
+	 * Points to struct shfl_string buffer that specifies a search path.
+	 */
+	struct vmmdev_hgcm_function_parameter path;
+
+	/**
+	 * pointer, out:
+	 * Buffer to place listing information to. (struct shfl_dirinfo)
+	 */
+	struct vmmdev_hgcm_function_parameter buffer;
+
+	/**
+	 * value32, in/out:
+	 * Indicates a key where the listing must be resumed.
+	 * in: 0 means start from begin of object.
+	 * out: 0 means listing completed.
+	 */
+	struct vmmdev_hgcm_function_parameter resume_point;
+
+	/**
+	 * pointer, out:
+	 * Number of files returned
+	 */
+	struct vmmdev_hgcm_function_parameter file_count;
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_LIST (8)
+
+
+/** SHFL_FN_READLINK Parameters structure. */
+struct shfl_readLink {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string buffer.
+	 */
+	struct vmmdev_hgcm_function_parameter path;
+
+	/**
+	 * pointer, out:
+	 * Buffer to place data to.
+	 */
+	struct vmmdev_hgcm_function_parameter buffer;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_READLINK (3)
+
+
+/* SHFL_FN_INFORMATION */
+
+/* Mask of Set/Get bit. */
+#define SHFL_INFO_MODE_MASK    (0x1)
+/* Get information */
+#define SHFL_INFO_GET          (0x0)
+/* Set information */
+#define SHFL_INFO_SET          (0x1)
+
+/* Get name of the object. */
+#define SHFL_INFO_NAME         (0x2)
+/* Set size of object (extend/trucate); only applies to file objects */
+#define SHFL_INFO_SIZE         (0x4)
+/* Get/Set file object info. */
+#define SHFL_INFO_FILE         (0x8)
+/* Get volume information. */
+#define SHFL_INFO_VOLUME       (0x10)
+
+/** SHFL_FN_INFORMATION Parameters structure. */
+struct shfl_information {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * value64, in:
+	 * SHFLHANDLE (u64) of object to be listed.
+	 */
+	struct vmmdev_hgcm_function_parameter handle;
+
+	/**
+	 * value32, in:
+	 * SHFL_INFO_*
+	 */
+	struct vmmdev_hgcm_function_parameter flags;
+
+	/**
+	 * value32, in/out:
+	 * Bytes to be used for information/How many bytes were used.
+	 */
+	struct vmmdev_hgcm_function_parameter cb;
+
+	/**
+	 * pointer, in/out:
+	 * Information to be set/get (shfl_fsobjinfo or shfl_string). Do not
+	 * forget to set the shfl_fsobjinfo::attr::additional for a get
+	 * operation as well.
+	 */
+	struct vmmdev_hgcm_function_parameter info;
+
+};
+
+/* Number of parameters */
+#define SHFL_CPARMS_INFORMATION (5)
+
+
+/* SHFL_FN_REMOVE */
+
+#define SHFL_REMOVE_FILE        (0x1)
+#define SHFL_REMOVE_DIR         (0x2)
+#define SHFL_REMOVE_SYMLINK     (0x4)
+
+/** SHFL_FN_REMOVE Parameters structure. */
+struct shfl_remove {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string buffer.
+	 */
+	struct vmmdev_hgcm_function_parameter path;
+
+	/**
+	 * value32, in:
+	 * remove flags (file/directory)
+	 */
+	struct vmmdev_hgcm_function_parameter flags;
+
+};
+
+#define SHFL_CPARMS_REMOVE  (3)
+
+
+/* SHFL_FN_RENAME */
+
+#define SHFL_RENAME_FILE                (0x1)
+#define SHFL_RENAME_DIR                 (0x2)
+#define SHFL_RENAME_REPLACE_IF_EXISTS   (0x4)
+
+/** SHFL_FN_RENAME Parameters structure. */
+struct shfl_rename {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string src.
+	 */
+	struct vmmdev_hgcm_function_parameter src;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string dest.
+	 */
+	struct vmmdev_hgcm_function_parameter dest;
+
+	/**
+	 * value32, in:
+	 * rename flags (file/directory)
+	 */
+	struct vmmdev_hgcm_function_parameter flags;
+
+};
+
+#define SHFL_CPARMS_RENAME  (4)
+
+
+/** SHFL_FN_SYMLINK Parameters structure. */
+struct shfl_symlink {
+	/**
+	 * pointer, in: SHFLROOT (u32)
+	 * Root handle of the mapping which name is queried.
+	 */
+	struct vmmdev_hgcm_function_parameter root;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string of path for the new symlink.
+	 */
+	struct vmmdev_hgcm_function_parameter new_path;
+
+	/**
+	 * pointer, in:
+	 * Points to struct shfl_string of destination for symlink.
+	 */
+	struct vmmdev_hgcm_function_parameter old_path;
+
+	/**
+	 * pointer, out:
+	 * Information about created symlink.
+	 */
+	struct vmmdev_hgcm_function_parameter info;
+
+};
+
+#define SHFL_CPARMS_SYMLINK  (4)
+
+#endif
diff --git a/drivers/staging/vboxsf/super.c b/drivers/staging/vboxsf/super.c
new file mode 100644
index 000000000000..0bf4d724aefd
--- /dev/null
+++ b/drivers/staging/vboxsf/super.c
@@ -0,0 +1,501 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Virtual File System.
+ *
+ * Module initialization/finalization
+ * File system registration/deregistration
+ * Superblock reading
+ * Few utility functions
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/idr.h>
+#include <linux/fs_parser.h>
+#include <linux/magic.h>
+#include <linux/module.h>
+#include <linux/nls.h>
+#include <linux/statfs.h>
+#include <linux/vbox_utils.h>
+#include "vfsmod.h"
+
+#define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */
+
+#define VBSF_MOUNT_SIGNATURE_BYTE_0 ('\000')
+#define VBSF_MOUNT_SIGNATURE_BYTE_1 ('\377')
+#define VBSF_MOUNT_SIGNATURE_BYTE_2 ('\376')
+#define VBSF_MOUNT_SIGNATURE_BYTE_3 ('\375')
+
+static int follow_symlinks;
+module_param(follow_symlinks, int, 0444);
+MODULE_PARM_DESC(follow_symlinks,
+		 "Let host resolve symlinks rather than showing them");
+
+static DEFINE_IDA(vboxsf_bdi_ida);
+static DEFINE_MUTEX(vboxsf_setup_mutex);
+static bool vboxsf_setup_done;
+static struct super_operations vboxsf_super_ops; /* forward declaration */
+static struct kmem_cache *vboxsf_inode_cachep;
+
+static char * const vboxsf_default_nls = CONFIG_NLS_DEFAULT;
+
+enum  { opt_nls, opt_uid, opt_gid, opt_ttl, opt_dmode, opt_fmode,
+	opt_dmask, opt_fmask };
+
+static const struct fs_parameter_spec vboxsf_param_specs[] = {
+	fsparam_string	("nls",		opt_nls),
+	fsparam_u32	("uid",		opt_uid),
+	fsparam_u32	("gid",		opt_gid),
+	fsparam_u32	("ttl",		opt_ttl),
+	fsparam_u32oct	("dmode",	opt_dmode),
+	fsparam_u32oct	("fmode",	opt_fmode),
+	fsparam_u32oct	("dmask",	opt_dmask),
+	fsparam_u32oct	("fmask",	opt_fmask),
+	{}
+};
+
+static const struct fs_parameter_description vboxsf_fs_parameters = {
+	.name  = "vboxsf",
+	.specs  = vboxsf_param_specs,
+};
+
+static int vboxsf_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+	struct vboxsf_fs_context *ctx = fc->fs_private;
+	struct fs_parse_result result;
+	kuid_t uid;
+	kgid_t gid;
+	int opt;
+
+	opt = fs_parse(fc, &vboxsf_fs_parameters, param, &result);
+	if (opt < 0)
+		return opt;
+
+	switch (opt) {
+	case opt_nls:
+		if (fc->purpose != FS_CONTEXT_FOR_MOUNT) {
+			vbg_err("vboxsf: Cannot reconfigure nls option\n");
+			return -EINVAL;
+		}
+		ctx->nls_name = param->string;
+		param->string = NULL;
+		break;
+	case opt_uid:
+		uid = make_kuid(current_user_ns(), result.uint_32);
+		if (!uid_valid(uid))
+			return -EINVAL;
+		ctx->o.uid = uid;
+		break;
+	case opt_gid:
+		gid = make_kgid(current_user_ns(), result.uint_32);
+		if (!gid_valid(gid))
+			return -EINVAL;
+		ctx->o.gid = gid;
+		break;
+	case opt_ttl:
+		ctx->o.ttl = msecs_to_jiffies(result.uint_32);
+		break;
+	case opt_dmode:
+		if (result.uint_32 & ~0777)
+			return -EINVAL;
+		ctx->o.dmode = result.uint_32;
+		ctx->o.dmode_set = true;
+		break;
+	case opt_fmode:
+		if (result.uint_32 & ~0777)
+			return -EINVAL;
+		ctx->o.fmode = result.uint_32;
+		ctx->o.fmode_set = true;
+		break;
+	case opt_dmask:
+		if (result.uint_32 & ~07777)
+			return -EINVAL;
+		ctx->o.dmask = result.uint_32;
+		break;
+	case opt_fmask:
+		if (result.uint_32 & ~07777)
+			return -EINVAL;
+		ctx->o.fmask = result.uint_32;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
+{
+	struct vboxsf_fs_context *ctx = fc->fs_private;
+	struct shfl_string *folder_name, root_path;
+	struct vboxsf_sbi *sbi;
+	struct dentry *droot;
+	struct inode *iroot;
+	char *nls_name;
+	size_t size;
+	int err;
+
+	if (!fc->source)
+		return -EINVAL;
+
+	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	if (!sbi)
+		return -ENOMEM;
+
+	sbi->o = ctx->o;
+	idr_init(&sbi->ino_idr);
+	spin_lock_init(&sbi->ino_idr_lock);
+	sbi->next_generation = 1;
+	sbi->bdi_id = -1;
+
+	/* Load nls if not utf8 */
+	nls_name = ctx->nls_name ? ctx->nls_name : vboxsf_default_nls;
+	if (strcmp(nls_name, "utf8") != 0) {
+		if (nls_name == vboxsf_default_nls)
+			sbi->nls = load_nls_default();
+		else
+			sbi->nls = load_nls(nls_name);
+
+		if (!sbi->nls) {
+			vbg_err("vboxsf: Count not load '%s' nls\n", nls_name);
+			err = -EINVAL;
+			goto fail_free;
+		}
+	}
+
+	sbi->bdi_id = ida_simple_get(&vboxsf_bdi_ida, 0, 0, GFP_KERNEL);
+	if (sbi->bdi_id < 0) {
+		err = sbi->bdi_id;
+		goto fail_free;
+	}
+
+	err = super_setup_bdi_name(sb, "vboxsf-%s.%d", fc->source, sbi->bdi_id);
+	if (err)
+		goto fail_free;
+
+	/* Turn source into a shfl_string and map the folder */
+	size = strlen(fc->source) + 1;
+	folder_name = kmalloc(SHFLSTRING_HEADER_SIZE + size, GFP_KERNEL);
+	if (!folder_name) {
+		err = -ENOMEM;
+		goto fail_free;
+	}
+	folder_name->size = size;
+	folder_name->length = size - 1;
+	strlcpy(folder_name->string.utf8, fc->source, size);
+	err = vboxsf_map_folder(folder_name, &sbi->root);
+	kfree(folder_name);
+	if (err) {
+		vbg_err("vboxsf: Host rejected mount of '%s' with error %d\n",
+			fc->source, err);
+		goto fail_free;
+	}
+
+	root_path.length = 1;
+	root_path.size = 2;
+	root_path.string.utf8[0] = '/';
+	root_path.string.utf8[1] = 0;
+	err = vboxsf_stat(sbi, &root_path, &sbi->root_info);
+	if (err)
+		goto fail_unmap;
+
+	sb->s_magic = VBOXSF_SUPER_MAGIC;
+	sb->s_blocksize = 1024;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	sb->s_op = &vboxsf_super_ops;
+	sb->s_d_op = &vboxsf_dentry_ops;
+
+	iroot = iget_locked(sb, 0);
+	if (!iroot) {
+		err = -ENOMEM;
+		goto fail_unmap;
+	}
+	vboxsf_init_inode(sbi, iroot, &sbi->root_info);
+	unlock_new_inode(iroot);
+
+	droot = d_make_root(iroot);
+	if (!droot) {
+		err = -ENOMEM;
+		goto fail_unmap;
+	}
+
+	sb->s_root = droot;
+	sb->s_fs_info = sbi;
+	return 0;
+
+fail_unmap:
+	vboxsf_unmap_folder(sbi->root);
+fail_free:
+	if (sbi->bdi_id >= 0)
+		ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id);
+	if (sbi->nls)
+		unload_nls(sbi->nls);
+	idr_destroy(&sbi->ino_idr);
+	kfree(sbi);
+	return err;
+}
+
+static void vboxsf_inode_init_once(void *data)
+{
+	struct vboxsf_inode *sf_i = data;
+
+	mutex_init(&sf_i->handle_list_mutex);
+	inode_init_once(&sf_i->vfs_inode);
+}
+
+static struct inode *vboxsf_alloc_inode(struct super_block *sb)
+{
+	struct vboxsf_inode *sf_i;
+
+	sf_i = kmem_cache_alloc(vboxsf_inode_cachep, GFP_NOFS);
+	if (!sf_i)
+		return NULL;
+
+	sf_i->force_restat = 0;
+	INIT_LIST_HEAD(&sf_i->handle_list);
+
+	return &sf_i->vfs_inode;
+}
+
+static void vboxsf_free_inode(struct inode *inode)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->ino_idr_lock, flags);
+	idr_remove(&sbi->ino_idr, inode->i_ino);
+	spin_unlock_irqrestore(&sbi->ino_idr_lock, flags);
+	kmem_cache_free(vboxsf_inode_cachep, VBOXSF_I(inode));
+}
+
+static void vboxsf_put_super(struct super_block *sb)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(sb);
+
+	vboxsf_unmap_folder(sbi->root);
+	if (sbi->bdi_id >= 0)
+		ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id);
+	if (sbi->nls)
+		unload_nls(sbi->nls);
+
+	/*
+	 * vboxsf_free_inode uses the idr, make sure all delayed rcu free
+	 * inodes are flushed.
+	 */
+	rcu_barrier();
+	idr_destroy(&sbi->ino_idr);
+	kfree(sbi);
+}
+
+static int vboxsf_statfs(struct dentry *dentry, struct kstatfs *stat)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct shfl_volinfo shfl_volinfo;
+	struct vboxsf_sbi *sbi;
+	u32 buf_len;
+	int err;
+
+	sbi = VBOXSF_SBI(sb);
+	buf_len = sizeof(shfl_volinfo);
+	err = vboxsf_fsinfo(sbi->root, 0, SHFL_INFO_GET | SHFL_INFO_VOLUME,
+			    &buf_len, &shfl_volinfo);
+	if (err)
+		return err;
+
+	stat->f_type = VBOXSF_SUPER_MAGIC;
+	stat->f_bsize = shfl_volinfo.bytes_per_allocation_unit;
+
+	do_div(shfl_volinfo.total_allocation_bytes,
+	       shfl_volinfo.bytes_per_allocation_unit);
+	stat->f_blocks = shfl_volinfo.total_allocation_bytes;
+
+	do_div(shfl_volinfo.available_allocation_bytes,
+	       shfl_volinfo.bytes_per_allocation_unit);
+	stat->f_bfree  = shfl_volinfo.available_allocation_bytes;
+	stat->f_bavail = shfl_volinfo.available_allocation_bytes;
+
+	stat->f_files = 1000;
+	/*
+	 * Don't return 0 here since the guest may then think that it is not
+	 * possible to create any more files.
+	 */
+	stat->f_ffree = 1000000;
+	stat->f_fsid.val[0] = 0;
+	stat->f_fsid.val[1] = 0;
+	stat->f_namelen = 255;
+	return 0;
+}
+
+static struct super_operations vboxsf_super_ops = {
+	.alloc_inode	= vboxsf_alloc_inode,
+	.free_inode	= vboxsf_free_inode,
+	.put_super	= vboxsf_put_super,
+	.statfs		= vboxsf_statfs,
+};
+
+static int vboxsf_setup(void)
+{
+	int err;
+
+	mutex_lock(&vboxsf_setup_mutex);
+
+	if (vboxsf_setup_done)
+		goto success;
+
+	vboxsf_inode_cachep =
+		kmem_cache_create("vboxsf_inode_cache",
+				  sizeof(struct vboxsf_inode), 0,
+				  (SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD |
+				   SLAB_ACCOUNT),
+				  vboxsf_inode_init_once);
+	if (!vboxsf_inode_cachep) {
+		err = -ENOMEM;
+		goto fail_nomem;
+	}
+
+	err = vboxsf_connect();
+	if (err) {
+		vbg_err("vboxsf: err %d connecting to guest PCI-device\n", err);
+		vbg_err("vboxsf: make sure you are inside a VirtualBox VM\n");
+		vbg_err("vboxsf: and check dmesg for vboxguest errors\n");
+		goto fail_free_cache;
+	}
+
+	err = vboxsf_set_utf8();
+	if (err) {
+		vbg_err("vboxsf_setutf8 error %d\n", err);
+		goto fail_disconnect;
+	}
+
+	if (!follow_symlinks) {
+		err = vboxsf_set_symlinks();
+		if (err)
+			vbg_warn("vboxsf: Unable to show symlinks: %d\n", err);
+	}
+
+	vboxsf_setup_done = true;
+success:
+	mutex_unlock(&vboxsf_setup_mutex);
+	return 0;
+
+fail_disconnect:
+	vboxsf_disconnect();
+fail_free_cache:
+	kmem_cache_destroy(vboxsf_inode_cachep);
+fail_nomem:
+	mutex_unlock(&vboxsf_setup_mutex);
+	return err;
+}
+
+static int vboxsf_parse_monolithic(struct fs_context *fc, void *data)
+{
+	char *options = data;
+
+	if (options && options[0] == VBSF_MOUNT_SIGNATURE_BYTE_0 &&
+		       options[1] == VBSF_MOUNT_SIGNATURE_BYTE_1 &&
+		       options[2] == VBSF_MOUNT_SIGNATURE_BYTE_2 &&
+		       options[3] == VBSF_MOUNT_SIGNATURE_BYTE_3) {
+		vbg_err("vboxsf: Old binary mount data not supported, remove obsolete mount.vboxsf and/or update your VBoxService.\n");
+		return -EINVAL;
+	}
+
+	return generic_parse_monolithic(fc, data);
+}
+
+static int vboxsf_get_tree(struct fs_context *fc)
+{
+	int err;
+
+	err = vboxsf_setup();
+	if (err)
+		return err;
+
+	return vfs_get_super(fc, vfs_get_independent_super, vboxsf_fill_super);
+}
+
+static int vboxsf_reconfigure(struct fs_context *fc)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(fc->root->d_sb);
+	struct vboxsf_fs_context *ctx = fc->fs_private;
+	struct inode *iroot;
+
+	iroot = ilookup(fc->root->d_sb, 0);
+	if (!iroot)
+		return -ENOENT;
+
+	/* Apply changed options to the root inode */
+	sbi->o = ctx->o;
+	vboxsf_init_inode(sbi, iroot, &sbi->root_info);
+
+	return 0;
+}
+
+static void vboxsf_free_fc(struct fs_context *fc)
+{
+	struct vboxsf_fs_context *ctx = fc->fs_private;
+
+	kfree(ctx->nls_name);
+	kfree(ctx);
+}
+
+static const struct fs_context_operations vboxsf_context_ops = {
+	.free			= vboxsf_free_fc,
+	.parse_param		= vboxsf_parse_param,
+	.parse_monolithic	= vboxsf_parse_monolithic,
+	.get_tree		= vboxsf_get_tree,
+	.reconfigure		= vboxsf_reconfigure,
+};
+
+static int vboxsf_init_fs_context(struct fs_context *fc)
+{
+	struct vboxsf_fs_context *ctx;
+
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	current_uid_gid(&ctx->o.uid, &ctx->o.gid);
+
+	fc->fs_private = ctx;
+	fc->ops = &vboxsf_context_ops;
+	return 0;
+}
+
+static struct file_system_type vboxsf_fs_type = {
+	.owner			= THIS_MODULE,
+	.name			= "vboxsf",
+	.init_fs_context	= vboxsf_init_fs_context,
+	.parameters		= &vboxsf_fs_parameters,
+	.kill_sb		= kill_anon_super
+};
+
+/* Module initialization/finalization handlers */
+static int __init vboxsf_init(void)
+{
+	return register_filesystem(&vboxsf_fs_type);
+}
+
+static void __exit vboxsf_fini(void)
+{
+	unregister_filesystem(&vboxsf_fs_type);
+
+	mutex_lock(&vboxsf_setup_mutex);
+	if (vboxsf_setup_done) {
+		vboxsf_disconnect();
+		/*
+		 * Make sure all delayed rcu free inodes are flushed
+		 * before we destroy the cache.
+		 */
+		rcu_barrier();
+		kmem_cache_destroy(vboxsf_inode_cachep);
+	}
+	mutex_unlock(&vboxsf_setup_mutex);
+}
+
+module_init(vboxsf_init);
+module_exit(vboxsf_fini);
+
+MODULE_DESCRIPTION("Oracle VM VirtualBox Module for Host File System Access");
+MODULE_AUTHOR("Oracle Corporation");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_FS("vboxsf");
diff --git a/drivers/staging/vboxsf/utils.c b/drivers/staging/vboxsf/utils.c
new file mode 100644
index 000000000000..34a49e6f74fc
--- /dev/null
+++ b/drivers/staging/vboxsf/utils.c
@@ -0,0 +1,551 @@
+// SPDX-License-Identifier: MIT
+/*
+ * VirtualBox Guest Shared Folders support: Utility functions.
+ * Mainly conversion from/to VirtualBox/Linux data structures.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/namei.h>
+#include <linux/nls.h>
+#include <linux/sizes.h>
+#include <linux/vfs.h>
+#include "vfsmod.h"
+
+struct inode *vboxsf_new_inode(struct super_block *sb)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(sb);
+	struct inode *inode;
+	unsigned long flags;
+	int cursor, ret;
+	u32 gen;
+
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	idr_preload(GFP_KERNEL);
+	spin_lock_irqsave(&sbi->ino_idr_lock, flags);
+	cursor = idr_get_cursor(&sbi->ino_idr);
+	ret = idr_alloc_cyclic(&sbi->ino_idr, inode, 1, 0, GFP_ATOMIC);
+	if (ret >= 0 && ret < cursor)
+		sbi->next_generation++;
+	gen = sbi->next_generation;
+	spin_unlock_irqrestore(&sbi->ino_idr_lock, flags);
+	idr_preload_end();
+
+	if (ret < 0) {
+		iput(inode);
+		return ERR_PTR(ret);
+	}
+
+	inode->i_ino = ret;
+	inode->i_generation = gen;
+	return inode;
+}
+
+/* set [inode] attributes based on [info], uid/gid based on [sbi] */
+void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
+		       const struct shfl_fsobjinfo *info)
+{
+	const struct shfl_fsobjattr *attr;
+	s64 allocated;
+	int mode;
+
+	attr = &info->attr;
+
+#define mode_set(r) ((attr->mode & (SHFL_UNIX_##r)) ? (S_##r) : 0)
+
+	mode = mode_set(IRUSR);
+	mode |= mode_set(IWUSR);
+	mode |= mode_set(IXUSR);
+
+	mode |= mode_set(IRGRP);
+	mode |= mode_set(IWGRP);
+	mode |= mode_set(IXGRP);
+
+	mode |= mode_set(IROTH);
+	mode |= mode_set(IWOTH);
+	mode |= mode_set(IXOTH);
+
+#undef mode_set
+
+	/* We use the host-side values for these */
+	inode->i_flags |= S_NOATIME | S_NOCMTIME;
+	inode->i_mapping->a_ops = &vboxsf_reg_aops;
+
+	if (SHFL_IS_DIRECTORY(attr->mode)) {
+		inode->i_mode = sbi->o.dmode_set ? sbi->o.dmode : mode;
+		inode->i_mode &= ~sbi->o.dmask;
+		inode->i_mode |= S_IFDIR;
+		inode->i_op = &vboxsf_dir_iops;
+		inode->i_fop = &vboxsf_dir_fops;
+		/*
+		 * XXX: this probably should be set to the number of entries
+		 * in the directory plus two (. ..)
+		 */
+		set_nlink(inode, 1);
+	} else if (SHFL_IS_SYMLINK(attr->mode)) {
+		inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode;
+		inode->i_mode &= ~sbi->o.fmask;
+		inode->i_mode |= S_IFLNK;
+		inode->i_op = &vboxsf_lnk_iops;
+		set_nlink(inode, 1);
+	} else {
+		inode->i_mode = sbi->o.fmode_set ? sbi->o.fmode : mode;
+		inode->i_mode &= ~sbi->o.fmask;
+		inode->i_mode |= S_IFREG;
+		inode->i_op = &vboxsf_reg_iops;
+		inode->i_fop = &vboxsf_reg_fops;
+		set_nlink(inode, 1);
+	}
+
+	inode->i_uid = sbi->o.uid;
+	inode->i_gid = sbi->o.gid;
+
+	inode->i_size = info->size;
+	inode->i_blkbits = 12;
+	/* i_blocks always in units of 512 bytes! */
+	allocated = info->allocated + 511;
+	do_div(allocated, 512);
+	inode->i_blocks = allocated;
+
+	inode->i_atime = ns_to_timespec64(
+				 info->access_time.ns_relative_to_unix_epoch);
+	inode->i_ctime = ns_to_timespec64(
+				 info->change_time.ns_relative_to_unix_epoch);
+	inode->i_mtime = ns_to_timespec64(
+			   info->modification_time.ns_relative_to_unix_epoch);
+}
+
+int vboxsf_create_at_dentry(struct dentry *dentry,
+			    struct shfl_createparms *params)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+	struct shfl_string *path;
+	int err;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	err = vboxsf_create(sbi->root, path, params);
+	__putname(path);
+
+	return err;
+}
+
+int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path,
+		struct shfl_fsobjinfo *info)
+{
+	struct shfl_createparms params = {};
+	int err;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_LOOKUP | SHFL_CF_ACT_FAIL_IF_NEW;
+
+	err = vboxsf_create(sbi->root, path, &params);
+	if (err)
+		return err;
+
+	if (params.result != SHFL_FILE_EXISTS)
+		return -ENOENT;
+
+	if (info)
+		*info = params.info;
+
+	return 0;
+}
+
+int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info)
+{
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+	struct shfl_string *path;
+	int err;
+
+	path = vboxsf_path_from_dentry(sbi, dentry);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	err = vboxsf_stat(sbi, path, info);
+	__putname(path);
+	return err;
+}
+
+int vboxsf_inode_revalidate(struct dentry *dentry)
+{
+	struct vboxsf_sbi *sbi;
+	struct vboxsf_inode *sf_i;
+	struct shfl_fsobjinfo info;
+	struct timespec64 prev_mtime;
+	struct inode *inode;
+	int err;
+
+	if (!dentry || !d_really_is_positive(dentry))
+		return -EINVAL;
+
+	inode = d_inode(dentry);
+	prev_mtime = inode->i_mtime;
+	sf_i = VBOXSF_I(inode);
+	sbi = VBOXSF_SBI(dentry->d_sb);
+	if (!sf_i->force_restat) {
+		if (time_before(jiffies, dentry->d_time + sbi->o.ttl))
+			return 0;
+	}
+
+	err = vboxsf_stat_dentry(dentry, &info);
+	if (err)
+		return err;
+
+	dentry->d_time = jiffies;
+	sf_i->force_restat = 0;
+	vboxsf_init_inode(sbi, inode, &info);
+
+	/*
+	 * If the file was changed on the host side we need to invalidate the
+	 * page-cache for it.  Note this also gets triggered by our own writes,
+	 * this is unavoidable.
+	 */
+	if (timespec64_compare(&inode->i_mtime, &prev_mtime) > 0)
+		invalidate_inode_pages2(inode->i_mapping);
+
+	return 0;
+}
+
+int vboxsf_getattr(const struct path *path, struct kstat *kstat,
+		   u32 request_mask, unsigned int flags)
+{
+	int err;
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = d_inode(dentry);
+	struct vboxsf_inode *sf_i = VBOXSF_I(inode);
+
+	switch (flags & AT_STATX_SYNC_TYPE) {
+	case AT_STATX_DONT_SYNC:
+		err = 0;
+		break;
+	case AT_STATX_FORCE_SYNC:
+		sf_i->force_restat = 1;
+		/* fall-through */
+	default:
+		err = vboxsf_inode_revalidate(dentry);
+	}
+	if (err)
+		return err;
+
+	generic_fillattr(d_inode(dentry), kstat);
+	return 0;
+}
+
+int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	struct vboxsf_inode *sf_i = VBOXSF_I(d_inode(dentry));
+	struct vboxsf_sbi *sbi = VBOXSF_SBI(dentry->d_sb);
+	struct shfl_createparms params = {};
+	struct shfl_fsobjinfo info = {};
+	u32 buf_len;
+	int err;
+
+	params.handle = SHFL_HANDLE_NIL;
+	params.create_flags = SHFL_CF_ACT_OPEN_IF_EXISTS |
+			      SHFL_CF_ACT_FAIL_IF_NEW |
+			      SHFL_CF_ACCESS_ATTR_WRITE;
+
+	/* this is at least required for Posix hosts */
+	if (iattr->ia_valid & ATTR_SIZE)
+		params.create_flags |= SHFL_CF_ACCESS_WRITE;
+
+	err = vboxsf_create_at_dentry(dentry, &params);
+	if (err || params.result != SHFL_FILE_EXISTS)
+		return err ? err : -ENOENT;
+
+#define mode_set(r) ((iattr->ia_mode & (S_##r)) ? SHFL_UNIX_##r : 0)
+
+	/*
+	 * Setting the file size and setting the other attributes has to
+	 * be handled separately.
+	 */
+	if (iattr->ia_valid & (ATTR_MODE | ATTR_ATIME | ATTR_MTIME)) {
+		if (iattr->ia_valid & ATTR_MODE) {
+			info.attr.mode = mode_set(IRUSR);
+			info.attr.mode |= mode_set(IWUSR);
+			info.attr.mode |= mode_set(IXUSR);
+			info.attr.mode |= mode_set(IRGRP);
+			info.attr.mode |= mode_set(IWGRP);
+			info.attr.mode |= mode_set(IXGRP);
+			info.attr.mode |= mode_set(IROTH);
+			info.attr.mode |= mode_set(IWOTH);
+			info.attr.mode |= mode_set(IXOTH);
+
+			if (iattr->ia_mode & S_IFDIR)
+				info.attr.mode |= SHFL_TYPE_DIRECTORY;
+			else
+				info.attr.mode |= SHFL_TYPE_FILE;
+		}
+
+		if (iattr->ia_valid & ATTR_ATIME)
+			info.access_time.ns_relative_to_unix_epoch =
+					    timespec64_to_ns(&iattr->ia_atime);
+
+		if (iattr->ia_valid & ATTR_MTIME)
+			info.modification_time.ns_relative_to_unix_epoch =
+					    timespec64_to_ns(&iattr->ia_mtime);
+
+		/*
+		 * Ignore ctime (inode change time) as it can't be set
+		 * from userland anyway.
+		 */
+
+		buf_len = sizeof(info);
+		err = vboxsf_fsinfo(sbi->root, params.handle,
+				    SHFL_INFO_SET | SHFL_INFO_FILE, &buf_len,
+				    &info);
+		if (err) {
+			vboxsf_close(sbi->root, params.handle);
+			return err;
+		}
+
+		/* the host may have given us different attr then requested */
+		sf_i->force_restat = 1;
+	}
+
+#undef mode_set
+
+	if (iattr->ia_valid & ATTR_SIZE) {
+		memset(&info, 0, sizeof(info));
+		info.size = iattr->ia_size;
+		buf_len = sizeof(info);
+		err = vboxsf_fsinfo(sbi->root, params.handle,
+				    SHFL_INFO_SET | SHFL_INFO_SIZE, &buf_len,
+				    &info);
+		if (err) {
+			vboxsf_close(sbi->root, params.handle);
+			return err;
+		}
+
+		/* the host may have given us different attr then requested */
+		sf_i->force_restat = 1;
+	}
+
+	vboxsf_close(sbi->root, params.handle);
+
+	/* Update the inode with what the host has actually given us. */
+	if (sf_i->force_restat)
+		vboxsf_inode_revalidate(dentry);
+
+	return 0;
+}
+
+/*
+ * [dentry] contains string encoded in coding system that corresponds
+ * to [sbi]->nls, we must convert it to UTF8 here.
+ * Returns a shfl_string allocated through __getname (must be freed using
+ * __putname), or an ERR_PTR on error.
+ */
+struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi,
+					    struct dentry *dentry)
+{
+	struct shfl_string *shfl_path;
+	int path_len, out_len, nb;
+	char *buf, *path;
+	wchar_t uni;
+	u8 *out;
+
+	buf = __getname();
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	path = dentry_path_raw(dentry, buf, PATH_MAX);
+	if (IS_ERR(path)) {
+		__putname(buf);
+		return (struct shfl_string *)path;
+	}
+	path_len = strlen(path);
+
+	if (sbi->nls) {
+		shfl_path = __getname();
+		if (!shfl_path) {
+			__putname(buf);
+			return ERR_PTR(-ENOMEM);
+		}
+
+		out = shfl_path->string.utf8;
+		out_len = PATH_MAX - SHFLSTRING_HEADER_SIZE - 1;
+
+		while (path_len) {
+			nb = sbi->nls->char2uni(path, path_len, &uni);
+			if (nb < 0) {
+				__putname(shfl_path);
+				__putname(buf);
+				return ERR_PTR(-EINVAL);
+			}
+			path += nb;
+			path_len -= nb;
+
+			nb = utf32_to_utf8(uni, out, out_len);
+			if (nb < 0) {
+				__putname(shfl_path);
+				__putname(buf);
+				return ERR_PTR(-ENAMETOOLONG);
+			}
+			out += nb;
+			out_len -= nb;
+		}
+		*out = 0;
+		shfl_path->length = out - shfl_path->string.utf8;
+		shfl_path->size = shfl_path->length + 1;
+		__putname(buf);
+	} else {
+		if ((SHFLSTRING_HEADER_SIZE + path_len + 1) > PATH_MAX) {
+			__putname(buf);
+			return ERR_PTR(-ENAMETOOLONG);
+		}
+		/*
+		 * dentry_path stores the name at the end of buf, but the
+		 * shfl_string string we return must be properly aligned.
+		 */
+		shfl_path = (struct shfl_string *)buf;
+		memmove(shfl_path->string.utf8, path, path_len);
+		shfl_path->string.utf8[path_len] = 0;
+		shfl_path->length = path_len;
+		shfl_path->size = path_len + 1;
+	}
+
+	return shfl_path;
+}
+
+int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len,
+		  const unsigned char *utf8_name, size_t utf8_len)
+{
+	const char *in;
+	char *out;
+	size_t out_len;
+	size_t out_bound_len;
+	size_t in_bound_len;
+
+	in = utf8_name;
+	in_bound_len = utf8_len;
+
+	out = name;
+	out_len = 0;
+	/* Reserve space for terminating 0 */
+	out_bound_len = name_bound_len - 1;
+
+	while (in_bound_len) {
+		int nb;
+		unicode_t uni;
+
+		nb = utf8_to_utf32(in, in_bound_len, &uni);
+		if (nb < 0)
+			return -EINVAL;
+
+		in += nb;
+		in_bound_len -= nb;
+
+		nb = sbi->nls->uni2char(uni, out, out_bound_len);
+		if (nb < 0)
+			return nb;
+
+		out += nb;
+		out_bound_len -= nb;
+		out_len += nb;
+	}
+
+	*out = 0;
+
+	return 0;
+}
+
+static struct vboxsf_dir_buf *vboxsf_dir_buf_alloc(struct list_head *list)
+{
+	struct vboxsf_dir_buf *b;
+
+	b = kmalloc(sizeof(*b), GFP_KERNEL);
+	if (!b)
+		return NULL;
+
+	b->buf = kmalloc(DIR_BUFFER_SIZE, GFP_KERNEL);
+	if (!b->buf) {
+		kfree(b);
+		return NULL;
+	}
+
+	b->entries = 0;
+	b->used = 0;
+	b->free = DIR_BUFFER_SIZE;
+	list_add(&b->head, list);
+
+	return b;
+}
+
+static void vboxsf_dir_buf_free(struct vboxsf_dir_buf *b)
+{
+	list_del(&b->head);
+	kfree(b->buf);
+	kfree(b);
+}
+
+struct vboxsf_dir_info *vboxsf_dir_info_alloc(void)
+{
+	struct vboxsf_dir_info *p;
+
+	p = kmalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return NULL;
+
+	INIT_LIST_HEAD(&p->info_list);
+	return p;
+}
+
+void vboxsf_dir_info_free(struct vboxsf_dir_info *p)
+{
+	struct list_head *list, *pos, *tmp;
+
+	list = &p->info_list;
+	list_for_each_safe(pos, tmp, list) {
+		struct vboxsf_dir_buf *b;
+
+		b = list_entry(pos, struct vboxsf_dir_buf, head);
+		vboxsf_dir_buf_free(b);
+	}
+	kfree(p);
+}
+
+int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d,
+			u64 handle)
+{
+	struct vboxsf_dir_buf *b;
+	u32 entries, size;
+	int err = 0;
+	void *buf;
+
+	/* vboxsf_dirinfo returns 1 on end of dir */
+	while (err == 0) {
+		b = vboxsf_dir_buf_alloc(&sf_d->info_list);
+		if (!b) {
+			err = -ENOMEM;
+			break;
+		}
+
+		buf = b->buf;
+		size = b->free;
+
+		err = vboxsf_dirinfo(sbi->root, handle, NULL, 0, 0,
+				     &size, buf, &entries);
+		if (err < 0)
+			break;
+
+		b->entries += entries;
+		b->free -= size;
+		b->used += size;
+	}
+
+	if (b && b->used == 0)
+		vboxsf_dir_buf_free(b);
+
+	/* -EILSEQ means the host could not translate a filename, ignore */
+	if (err > 0 || err == -EILSEQ)
+		err = 0;
+
+	return err;
+}
diff --git a/drivers/staging/vboxsf/vboxsf_wrappers.c b/drivers/staging/vboxsf/vboxsf_wrappers.c
new file mode 100644
index 000000000000..bfc78a097dae
--- /dev/null
+++ b/drivers/staging/vboxsf/vboxsf_wrappers.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Wrapper functions for the shfl host calls.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vbox_err.h>
+#include <linux/vbox_utils.h>
+#include "vfsmod.h"
+
+#define SHFL_REQUEST \
+	(VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV_OTHER | \
+	 VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
+
+static u32 vboxsf_client_id;
+
+int vboxsf_connect(void)
+{
+	struct vbg_dev *gdev;
+	struct vmmdev_hgcm_service_location loc;
+	int err, vbox_status;
+
+	loc.type = VMMDEV_HGCM_LOC_LOCALHOST_EXISTING;
+	strcpy(loc.u.localhost.service_name, "VBoxSharedFolders");
+
+	gdev = vbg_get_gdev();
+	if (IS_ERR(gdev))
+		return -ENODEV;	/* No guest-device */
+
+	err = vbg_hgcm_connect(gdev, SHFL_REQUEST, &loc,
+			       &vboxsf_client_id, &vbox_status);
+	vbg_put_gdev(gdev);
+
+	return err ? err : vbg_status_code_to_errno(vbox_status);
+}
+
+void vboxsf_disconnect(void)
+{
+	struct vbg_dev *gdev;
+	int vbox_status;
+
+	gdev = vbg_get_gdev();
+	if (IS_ERR(gdev))
+		return;   /* guest-device is gone, already disconnected */
+
+	vbg_hgcm_disconnect(gdev, SHFL_REQUEST, vboxsf_client_id, &vbox_status);
+	vbg_put_gdev(gdev);
+}
+
+static int vboxsf_call(u32 function, void *parms, u32 parm_count, int *status)
+{
+	struct vbg_dev *gdev;
+	int err, vbox_status;
+
+	gdev = vbg_get_gdev();
+	if (IS_ERR(gdev))
+		return -ESHUTDOWN; /* guest-dev removed underneath us */
+
+	err = vbg_hgcm_call(gdev, SHFL_REQUEST, vboxsf_client_id, function,
+			    U32_MAX, parms, parm_count, &vbox_status);
+	vbg_put_gdev(gdev);
+
+	if (err < 0)
+		return err;
+
+	if (status)
+		*status = vbox_status;
+
+	return vbg_status_code_to_errno(vbox_status);
+}
+
+int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root)
+{
+	struct shfl_map_folder parms;
+	int err, status;
+
+	parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
+	parms.path.u.pointer.size = shfl_string_buf_size(folder_name);
+	parms.path.u.pointer.u.linear_addr = (uintptr_t)folder_name;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = 0;
+
+	parms.delimiter.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.delimiter.u.value32 = '/';
+
+	parms.case_sensitive.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.case_sensitive.u.value32 = 1;
+
+	err = vboxsf_call(SHFL_FN_MAP_FOLDER, &parms, SHFL_CPARMS_MAP_FOLDER,
+			  &status);
+	if (err == -ENOSYS && status == VERR_NOT_IMPLEMENTED)
+		vbg_err("%s: Error host is too old\n", __func__);
+
+	*root = parms.root.u.value32;
+	return err;
+}
+
+int vboxsf_unmap_folder(u32 root)
+{
+	struct shfl_unmap_folder parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	return vboxsf_call(SHFL_FN_UNMAP_FOLDER, &parms,
+			   SHFL_CPARMS_UNMAP_FOLDER, NULL);
+}
+
+/**
+ * vboxsf_create - Create a new file or folder
+ * @root:         Root of the shared folder in which to create the file
+ * @parsed_path:  The path of the file or folder relative to the shared folder
+ * @param:        create_parms Parameters for file/folder creation.
+ *
+ * Create a new file or folder or open an existing one in a shared folder.
+ * Note this function always returns 0 / success unless an exceptional condition
+ * occurs - out of memory, invalid arguments, etc. If the file or folder could
+ * not be opened or created, create_parms->handle will be set to
+ * SHFL_HANDLE_NIL on return.  In this case the value in create_parms->result
+ * provides information as to why (e.g. SHFL_FILE_EXISTS), create_parms->result
+ * is also set on success as additional information.
+ *
+ * Returns:
+ * 0 or negative errno value.
+ */
+int vboxsf_create(u32 root, struct shfl_string *parsed_path,
+		  struct shfl_createparms *create_parms)
+{
+	struct shfl_create parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
+	parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
+	parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
+
+	parms.parms.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
+	parms.parms.u.pointer.size = sizeof(struct shfl_createparms);
+	parms.parms.u.pointer.u.linear_addr = (uintptr_t)create_parms;
+
+	return vboxsf_call(SHFL_FN_CREATE, &parms, SHFL_CPARMS_CREATE, NULL);
+}
+
+int vboxsf_close(u32 root, u64 handle)
+{
+	struct shfl_close parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.handle.u.value64 = handle;
+
+	return vboxsf_call(SHFL_FN_CLOSE, &parms, SHFL_CPARMS_CLOSE, NULL);
+}
+
+int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags)
+{
+	struct shfl_remove parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
+	parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
+
+	parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.flags.u.value32 = flags;
+
+	return vboxsf_call(SHFL_FN_REMOVE, &parms, SHFL_CPARMS_REMOVE, NULL);
+}
+
+int vboxsf_rename(u32 root, struct shfl_string *src_path,
+		  struct shfl_string *dest_path, u32 flags)
+{
+	struct shfl_rename parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.src.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.src.u.pointer.size = shfl_string_buf_size(src_path);
+	parms.src.u.pointer.u.linear_addr = (uintptr_t)src_path;
+
+	parms.dest.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.dest.u.pointer.size = shfl_string_buf_size(dest_path);
+	parms.dest.u.pointer.u.linear_addr = (uintptr_t)dest_path;
+
+	parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.flags.u.value32 = flags;
+
+	return vboxsf_call(SHFL_FN_RENAME, &parms, SHFL_CPARMS_RENAME, NULL);
+}
+
+int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf)
+{
+	struct shfl_read parms;
+	int err;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.handle.u.value64 = handle;
+	parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.offset.u.value64 = offset;
+	parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.cb.u.value32 = *buf_len;
+	parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
+	parms.buffer.u.pointer.size = *buf_len;
+	parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
+
+	err = vboxsf_call(SHFL_FN_READ, &parms, SHFL_CPARMS_READ, NULL);
+
+	*buf_len = parms.cb.u.value32;
+	return err;
+}
+
+int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf)
+{
+	struct shfl_write parms;
+	int err;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.handle.u.value64 = handle;
+	parms.offset.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.offset.u.value64 = offset;
+	parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.cb.u.value32 = *buf_len;
+	parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.buffer.u.pointer.size = *buf_len;
+	parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
+
+	err = vboxsf_call(SHFL_FN_WRITE, &parms, SHFL_CPARMS_WRITE, NULL);
+
+	*buf_len = parms.cb.u.value32;
+	return err;
+}
+
+/* Returns 0 on success, 1 on end-of-dir, negative errno otherwise */
+int vboxsf_dirinfo(u32 root, u64 handle,
+		   struct shfl_string *parsed_path, u32 flags, u32 index,
+		   u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count)
+{
+	struct shfl_list parms;
+	int err, status;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.handle.u.value64 = handle;
+	parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.flags.u.value32 = flags;
+	parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.cb.u.value32 = *buf_len;
+	if (parsed_path) {
+		parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+		parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
+		parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
+	} else {
+		parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_IN;
+		parms.path.u.pointer.size = 0;
+		parms.path.u.pointer.u.linear_addr = 0;
+	}
+
+	parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
+	parms.buffer.u.pointer.size = *buf_len;
+	parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
+
+	parms.resume_point.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.resume_point.u.value32 = index;
+	parms.file_count.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.file_count.u.value32 = 0;	/* out parameter only */
+
+	err = vboxsf_call(SHFL_FN_LIST, &parms, SHFL_CPARMS_LIST, &status);
+	if (err == -ENODATA && status == VERR_NO_MORE_FILES)
+		err = 1;
+
+	*buf_len = parms.cb.u.value32;
+	*file_count = parms.file_count.u.value32;
+	return err;
+}
+
+int vboxsf_fsinfo(u32 root, u64 handle, u32 flags,
+		  u32 *buf_len, void *buf)
+{
+	struct shfl_information parms;
+	int err;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.handle.type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+	parms.handle.u.value64 = handle;
+	parms.flags.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.flags.u.value32 = flags;
+	parms.cb.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.cb.u.value32 = *buf_len;
+	parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL;
+	parms.info.u.pointer.size = *buf_len;
+	parms.info.u.pointer.u.linear_addr = (uintptr_t)buf;
+
+	err = vboxsf_call(SHFL_FN_INFORMATION, &parms, SHFL_CPARMS_INFORMATION,
+			  NULL);
+
+	*buf_len = parms.cb.u.value32;
+	return err;
+}
+
+int vboxsf_readlink(u32 root, struct shfl_string *parsed_path,
+		    u32 buf_len, u8 *buf)
+{
+	struct shfl_readLink parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.path.u.pointer.size = shfl_string_buf_size(parsed_path);
+	parms.path.u.pointer.u.linear_addr = (uintptr_t)parsed_path;
+
+	parms.buffer.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
+	parms.buffer.u.pointer.size = buf_len;
+	parms.buffer.u.pointer.u.linear_addr = (uintptr_t)buf;
+
+	return vboxsf_call(SHFL_FN_READLINK, &parms, SHFL_CPARMS_READLINK,
+			   NULL);
+}
+
+int vboxsf_symlink(u32 root, struct shfl_string *new_path,
+		   struct shfl_string *old_path, struct shfl_fsobjinfo *buf)
+{
+	struct shfl_symlink parms;
+
+	parms.root.type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+	parms.root.u.value32 = root;
+
+	parms.new_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.new_path.u.pointer.size = shfl_string_buf_size(new_path);
+	parms.new_path.u.pointer.u.linear_addr = (uintptr_t)new_path;
+
+	parms.old_path.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN;
+	parms.old_path.u.pointer.size = shfl_string_buf_size(old_path);
+	parms.old_path.u.pointer.u.linear_addr = (uintptr_t)old_path;
+
+	parms.info.type = VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT;
+	parms.info.u.pointer.size = sizeof(struct shfl_fsobjinfo);
+	parms.info.u.pointer.u.linear_addr = (uintptr_t)buf;
+
+	return vboxsf_call(SHFL_FN_SYMLINK, &parms, SHFL_CPARMS_SYMLINK, NULL);
+}
+
+int vboxsf_set_utf8(void)
+{
+	return vboxsf_call(SHFL_FN_SET_UTF8, NULL, 0, NULL);
+}
+
+int vboxsf_set_symlinks(void)
+{
+	return vboxsf_call(SHFL_FN_SET_SYMLINKS, NULL, 0, NULL);
+}
diff --git a/drivers/staging/vboxsf/vfsmod.h b/drivers/staging/vboxsf/vfsmod.h
new file mode 100644
index 000000000000..18f95b00fc33
--- /dev/null
+++ b/drivers/staging/vboxsf/vfsmod.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * VirtualBox Guest Shared Folders support: module header.
+ *
+ * Copyright (C) 2006-2018 Oracle Corporation
+ */
+
+#ifndef VFSMOD_H
+#define VFSMOD_H
+
+#include <linux/backing-dev.h>
+#include <linux/idr.h>
+#include "shfl_hostintf.h"
+
+#define DIR_BUFFER_SIZE SZ_16K
+
+/* The cast is to prevent assignment of void * to pointers of arbitrary type */
+#define VBOXSF_SBI(sb)	((struct vboxsf_sbi *)(sb)->s_fs_info)
+#define VBOXSF_I(i)	container_of(i, struct vboxsf_inode, vfs_inode)
+
+struct vboxsf_options {
+	unsigned long ttl;
+	kuid_t uid;
+	kgid_t gid;
+	bool dmode_set;
+	bool fmode_set;
+	umode_t dmode;
+	umode_t fmode;
+	umode_t dmask;
+	umode_t fmask;
+};
+
+struct vboxsf_fs_context {
+	struct vboxsf_options o;
+	char *nls_name;
+};
+
+/* per-shared folder information */
+struct vboxsf_sbi {
+	struct vboxsf_options o;
+	struct shfl_fsobjinfo root_info;
+	struct idr ino_idr;
+	spinlock_t ino_idr_lock; /* This protects ino_idr */
+	struct nls_table *nls;
+	u32 next_generation;
+	u32 root;
+	int bdi_id;
+};
+
+/* per-inode information */
+struct vboxsf_inode {
+	/* some information was changed, update data on next revalidate */
+	int force_restat;
+	/* list of open handles for this inode + lock protecting it */
+	struct list_head handle_list;
+	/* This mutex protects handle_list accesses */
+	struct mutex handle_list_mutex;
+	/* The VFS inode struct */
+	struct inode vfs_inode;
+};
+
+struct vboxsf_dir_info {
+	struct list_head info_list;
+};
+
+struct vboxsf_dir_buf {
+	size_t entries;
+	size_t free;
+	size_t used;
+	void *buf;
+	struct list_head head;
+};
+
+/* globals */
+extern const struct inode_operations vboxsf_dir_iops;
+extern const struct inode_operations vboxsf_lnk_iops;
+extern const struct inode_operations vboxsf_reg_iops;
+extern const struct file_operations vboxsf_dir_fops;
+extern const struct file_operations vboxsf_reg_fops;
+extern const struct address_space_operations vboxsf_reg_aops;
+extern const struct dentry_operations vboxsf_dentry_ops;
+
+/* from utils.c */
+struct inode *vboxsf_new_inode(struct super_block *sb);
+void vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
+		       const struct shfl_fsobjinfo *info);
+int vboxsf_create_at_dentry(struct dentry *dentry,
+			    struct shfl_createparms *params);
+int vboxsf_stat(struct vboxsf_sbi *sbi, struct shfl_string *path,
+		struct shfl_fsobjinfo *info);
+int vboxsf_stat_dentry(struct dentry *dentry, struct shfl_fsobjinfo *info);
+int vboxsf_inode_revalidate(struct dentry *dentry);
+int vboxsf_getattr(const struct path *path, struct kstat *kstat,
+		   u32 request_mask, unsigned int query_flags);
+int vboxsf_setattr(struct dentry *dentry, struct iattr *iattr);
+struct shfl_string *vboxsf_path_from_dentry(struct vboxsf_sbi *sbi,
+					    struct dentry *dentry);
+int vboxsf_nlscpy(struct vboxsf_sbi *sbi, char *name, size_t name_bound_len,
+		  const unsigned char *utf8_name, size_t utf8_len);
+struct vboxsf_dir_info *vboxsf_dir_info_alloc(void);
+void vboxsf_dir_info_free(struct vboxsf_dir_info *p);
+int vboxsf_dir_read_all(struct vboxsf_sbi *sbi, struct vboxsf_dir_info *sf_d,
+			u64 handle);
+
+/* from vboxsf_wrappers.c */
+int vboxsf_connect(void);
+void vboxsf_disconnect(void);
+
+int vboxsf_create(u32 root, struct shfl_string *parsed_path,
+		  struct shfl_createparms *create_parms);
+
+int vboxsf_close(u32 root, u64 handle);
+int vboxsf_remove(u32 root, struct shfl_string *parsed_path, u32 flags);
+int vboxsf_rename(u32 root, struct shfl_string *src_path,
+		  struct shfl_string *dest_path, u32 flags);
+
+int vboxsf_read(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf);
+int vboxsf_write(u32 root, u64 handle, u64 offset, u32 *buf_len, u8 *buf);
+
+int vboxsf_dirinfo(u32 root, u64 handle,
+		   struct shfl_string *parsed_path, u32 flags, u32 index,
+		   u32 *buf_len, struct shfl_dirinfo *buf, u32 *file_count);
+int vboxsf_fsinfo(u32 root, u64 handle, u32 flags,
+		  u32 *buf_len, void *buf);
+
+int vboxsf_map_folder(struct shfl_string *folder_name, u32 *root);
+int vboxsf_unmap_folder(u32 root);
+
+int vboxsf_readlink(u32 root, struct shfl_string *parsed_path,
+		    u32 buf_len, u8 *buf);
+int vboxsf_symlink(u32 root, struct shfl_string *new_path,
+		   struct shfl_string *old_path, struct shfl_fsobjinfo *buf);
+
+int vboxsf_set_utf8(void);
+int vboxsf_set_symlinks(void);
+
+#endif
diff --git a/drivers/staging/wlan-ng/cfg80211.c b/drivers/staging/wlan-ng/cfg80211.c
index eee1998c4b18..fac38c842ac5 100644
--- a/drivers/staging/wlan-ng/cfg80211.c
+++ b/drivers/staging/wlan-ng/cfg80211.c
@@ -469,10 +469,8 @@ static int prism2_connect(struct wiphy *wiphy, struct net_device *dev,
 	/* Set the encryption - we only support wep */
 	if (is_wep) {
 		if (sme->key) {
-			if (sme->key_idx >= NUM_WEPKEYS) {
-				err = -EINVAL;
-				goto exit;
-			}
+			if (sme->key_idx >= NUM_WEPKEYS)
+				return -EINVAL;
 
 			result = prism2_domibset_uint32(wlandev,
 				DIDMIB_DOT11SMT_PRIVACYTABLE_WEPDEFAULTKEYID,
diff --git a/drivers/target/iscsi/cxgbit/cxgbit_cm.c b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
index c70caf4ea490..a2b5c796bbc4 100644
--- a/drivers/target/iscsi/cxgbit/cxgbit_cm.c
+++ b/drivers/target/iscsi/cxgbit/cxgbit_cm.c
@@ -1831,7 +1831,7 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb)
 
 	while (credits) {
 		struct sk_buff *p = cxgbit_sock_peek_wr(csk);
-		const u32 csum = (__force u32)p->csum;
+		u32 csum;
 
 		if (unlikely(!p)) {
 			pr_err("csk 0x%p,%u, cr %u,%u+%u, empty.\n",
@@ -1840,6 +1840,7 @@ static void cxgbit_fw4_ack(struct cxgbit_sock *csk, struct sk_buff *skb)
 			break;
 		}
 
+		csum = (__force u32)p->csum;
 		if (unlikely(credits < csum)) {
 			pr_warn("csk 0x%p,%u, cr %u,%u+%u, < %u.\n",
 				csk,  csk->tid,
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 04bf2acd3800..2d19f0e332b0 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -1075,27 +1075,6 @@ passthrough_parse_cdb(struct se_cmd *cmd,
 	unsigned int size;
 
 	/*
-	 * Clear a lun set in the cdb if the initiator talking to use spoke
-	 * and old standards version, as we can't assume the underlying device
-	 * won't choke up on it.
-	 */
-	switch (cdb[0]) {
-	case READ_10: /* SBC - RDProtect */
-	case READ_12: /* SBC - RDProtect */
-	case READ_16: /* SBC - RDProtect */
-	case SEND_DIAGNOSTIC: /* SPC - SELF-TEST Code */
-	case VERIFY: /* SBC - VRProtect */
-	case VERIFY_16: /* SBC - VRProtect */
-	case WRITE_VERIFY: /* SBC - VRProtect */
-	case WRITE_VERIFY_12: /* SBC - VRProtect */
-	case MAINTENANCE_IN: /* SPC - Parameter Data Format for SA RTPG */
-		break;
-	default:
-		cdb[1] &= 0x1f; /* clear logical unit number */
-		break;
-	}
-
-	/*
 	 * For REPORT LUNS we always need to emulate the response, for everything
 	 * else, pass it up.
 	 */
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 391f39776c6a..6b9865c786ba 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -88,7 +88,7 @@ struct cpufreq_cooling_device {
 	struct cpufreq_policy *policy;
 	struct list_head node;
 	struct time_in_idle *idle_time;
-	struct dev_pm_qos_request qos_req;
+	struct freq_qos_request qos_req;
 };
 
 static DEFINE_IDA(cpufreq_ida);
@@ -331,7 +331,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 
 	cpufreq_cdev->cpufreq_state = state;
 
-	return dev_pm_qos_update_request(&cpufreq_cdev->qos_req,
+	return freq_qos_update_request(&cpufreq_cdev->qos_req,
 				cpufreq_cdev->freq_table[state].frequency);
 }
 
@@ -615,9 +615,9 @@ __cpufreq_cooling_register(struct device_node *np,
 		cooling_ops = &cpufreq_cooling_ops;
 	}
 
-	ret = dev_pm_qos_add_request(dev, &cpufreq_cdev->qos_req,
-				     DEV_PM_QOS_MAX_FREQUENCY,
-				     cpufreq_cdev->freq_table[0].frequency);
+	ret = freq_qos_add_request(&policy->constraints,
+				   &cpufreq_cdev->qos_req, FREQ_QOS_MAX,
+				   cpufreq_cdev->freq_table[0].frequency);
 	if (ret < 0) {
 		pr_err("%s: Failed to add freq constraint (%d)\n", __func__,
 		       ret);
@@ -637,7 +637,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	return cdev;
 
 remove_qos_req:
-	dev_pm_qos_remove_request(&cpufreq_cdev->qos_req);
+	freq_qos_remove_request(&cpufreq_cdev->qos_req);
 remove_ida:
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 free_table:
@@ -736,7 +736,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 	mutex_unlock(&cooling_list_lock);
 
 	thermal_cooling_device_unregister(cdev);
-	dev_pm_qos_remove_request(&cpufreq_cdev->qos_req);
+	freq_qos_remove_request(&cpufreq_cdev->qos_req);
 	ida_simple_remove(&cpufreq_ida, cpufreq_cdev->id);
 	kfree(cpufreq_cdev->idle_time);
 	kfree(cpufreq_cdev->freq_table);
diff --git a/drivers/thunderbolt/nhi_ops.c b/drivers/thunderbolt/nhi_ops.c
index 61cd09cef943..6795851aac95 100644
--- a/drivers/thunderbolt/nhi_ops.c
+++ b/drivers/thunderbolt/nhi_ops.c
@@ -80,7 +80,6 @@ static void icl_nhi_lc_mailbox_cmd(struct tb_nhi *nhi, enum icl_lc_mailbox_cmd c
 {
 	u32 data;
 
-	pci_read_config_dword(nhi->pdev, VS_CAP_19, &data);
 	data = (cmd << VS_CAP_19_CMD_SHIFT) & VS_CAP_19_CMD_MASK;
 	pci_write_config_dword(nhi->pdev, VS_CAP_19, data | VS_CAP_19_VALID);
 }
diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
index 410bf1bceeee..5ea8db667e83 100644
--- a/drivers/thunderbolt/switch.c
+++ b/drivers/thunderbolt/switch.c
@@ -896,12 +896,13 @@ int tb_dp_port_set_hops(struct tb_port *port, unsigned int video,
  */
 bool tb_dp_port_is_enabled(struct tb_port *port)
 {
-	u32 data;
+	u32 data[2];
 
-	if (tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1))
+	if (tb_port_read(port, data, TB_CFG_PORT, port->cap_adap,
+			 ARRAY_SIZE(data)))
 		return false;
 
-	return !!(data & (TB_DP_VIDEO_EN | TB_DP_AUX_EN));
+	return !!(data[0] & (TB_DP_VIDEO_EN | TB_DP_AUX_EN));
 }
 
 /**
@@ -914,19 +915,21 @@ bool tb_dp_port_is_enabled(struct tb_port *port)
  */
 int tb_dp_port_enable(struct tb_port *port, bool enable)
 {
-	u32 data;
+	u32 data[2];
 	int ret;
 
-	ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1);
+	ret = tb_port_read(port, data, TB_CFG_PORT, port->cap_adap,
+			   ARRAY_SIZE(data));
 	if (ret)
 		return ret;
 
 	if (enable)
-		data |= TB_DP_VIDEO_EN | TB_DP_AUX_EN;
+		data[0] |= TB_DP_VIDEO_EN | TB_DP_AUX_EN;
 	else
-		data &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN);
+		data[0] &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN);
 
-	return tb_port_write(port, &data, TB_CFG_PORT, port->cap_adap, 1);
+	return tb_port_write(port, data, TB_CFG_PORT, port->cap_adap,
+			     ARRAY_SIZE(data));
 }
 
 /* switch utility functions */
@@ -1031,13 +1034,6 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val)
 	if (sw->authorized)
 		goto unlock;
 
-	/*
-	 * Make sure there is no PCIe rescan ongoing when a new PCIe
-	 * tunnel is created. Otherwise the PCIe rescan code might find
-	 * the new tunnel too early.
-	 */
-	pci_lock_rescan_remove();
-
 	switch (val) {
 	/* Approve switch */
 	case 1:
@@ -1057,8 +1053,6 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val)
 		break;
 	}
 
-	pci_unlock_rescan_remove();
-
 	if (!ret) {
 		sw->authorized = val;
 		/* Notify status change to the userspace */
diff --git a/drivers/tty/serial/8250/8250_men_mcb.c b/drivers/tty/serial/8250/8250_men_mcb.c
index 02c5aff58a74..8df89e9cd254 100644
--- a/drivers/tty/serial/8250/8250_men_mcb.c
+++ b/drivers/tty/serial/8250/8250_men_mcb.c
@@ -72,8 +72,8 @@ static int serial_8250_men_mcb_probe(struct mcb_device *mdev,
 {
 	struct serial_8250_men_mcb_data *data;
 	struct resource *mem;
-	unsigned int num_ports;
-	unsigned int i;
+	int num_ports;
+	int i;
 	void __iomem *membase;
 
 	mem = mcb_get_resource(mdev, IORESOURCE_MEM);
@@ -88,7 +88,7 @@ static int serial_8250_men_mcb_probe(struct mcb_device *mdev,
 	dev_dbg(&mdev->dev, "found a 16z%03u with %u ports\n",
 		mdev->id, num_ports);
 
-	if (num_ports == 0 || num_ports > 4) {
+	if (num_ports <= 0 || num_ports > 4) {
 		dev_err(&mdev->dev, "unexpected number of ports: %u\n",
 			num_ports);
 		return -ENODEV;
@@ -133,7 +133,7 @@ static int serial_8250_men_mcb_probe(struct mcb_device *mdev,
 
 static void serial_8250_men_mcb_remove(struct mcb_device *mdev)
 {
-	unsigned int num_ports, i;
+	int num_ports, i;
 	struct serial_8250_men_mcb_data *data = mcb_get_drvdata(mdev);
 
 	if (!data)
diff --git a/drivers/usb/cdns3/core.c b/drivers/usb/cdns3/core.c
index 1109dc5a4c39..c2123ef8d8a3 100644
--- a/drivers/usb/cdns3/core.c
+++ b/drivers/usb/cdns3/core.c
@@ -166,7 +166,6 @@ static int cdns3_core_init_role(struct cdns3 *cdns)
 		goto err;
 
 	switch (cdns->dr_mode) {
-	case USB_DR_MODE_UNKNOWN:
 	case USB_DR_MODE_OTG:
 		ret = cdns3_hw_role_switch(cdns);
 		if (ret)
@@ -182,6 +181,9 @@ static int cdns3_core_init_role(struct cdns3 *cdns)
 		if (ret)
 			goto err;
 		break;
+	default:
+		ret = -EINVAL;
+		goto err;
 	}
 
 	return ret;
diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c
index 2ca280f4c054..4c1e75509303 100644
--- a/drivers/usb/cdns3/gadget.c
+++ b/drivers/usb/cdns3/gadget.c
@@ -1145,6 +1145,14 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,
 		request = cdns3_next_request(&priv_ep->pending_req_list);
 		priv_req = to_cdns3_request(request);
 
+		trb = priv_ep->trb_pool + priv_ep->dequeue;
+
+		/* Request was dequeued and TRB was changed to TRB_LINK. */
+		if (TRB_FIELD_TO_TYPE(trb->control) == TRB_LINK) {
+			trace_cdns3_complete_trb(priv_ep, trb);
+			cdns3_move_deq_to_next_trb(priv_req);
+		}
+
 		/* Re-select endpoint. It could be changed by other CPU during
 		 * handling usb_gadget_giveback_request.
 		 */
@@ -2067,6 +2075,7 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
 	struct usb_request *req, *req_temp;
 	struct cdns3_request *priv_req;
 	struct cdns3_trb *link_trb;
+	u8 req_on_hw_ring = 0;
 	unsigned long flags;
 	int ret = 0;
 
@@ -2083,8 +2092,10 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
 
 	list_for_each_entry_safe(req, req_temp, &priv_ep->pending_req_list,
 				 list) {
-		if (request == req)
+		if (request == req) {
+			req_on_hw_ring = 1;
 			goto found;
+		}
 	}
 
 	list_for_each_entry_safe(req, req_temp, &priv_ep->deferred_req_list,
@@ -2096,27 +2107,21 @@ int cdns3_gadget_ep_dequeue(struct usb_ep *ep,
 	goto not_found;
 
 found:
-
-	if (priv_ep->wa1_trb == priv_req->trb)
-		cdns3_wa1_restore_cycle_bit(priv_ep);
-
 	link_trb = priv_req->trb;
-	cdns3_move_deq_to_next_trb(priv_req);
-	cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET);
-
-	/* Update ring */
-	request = cdns3_next_request(&priv_ep->deferred_req_list);
-	if (request) {
-		priv_req = to_cdns3_request(request);
 
+	/* Update ring only if removed request is on pending_req_list list */
+	if (req_on_hw_ring) {
 		link_trb->buffer = TRB_BUFFER(priv_ep->trb_pool_dma +
 					      (priv_req->start_trb * TRB_SIZE));
 		link_trb->control = (link_trb->control & TRB_CYCLE) |
-				    TRB_TYPE(TRB_LINK) | TRB_CHAIN | TRB_TOGGLE;
-	} else {
-		priv_ep->flags |= EP_UPDATE_EP_TRBADDR;
+				    TRB_TYPE(TRB_LINK) | TRB_CHAIN;
+
+		if (priv_ep->wa1_trb == priv_req->trb)
+			cdns3_wa1_restore_cycle_bit(priv_ep);
 	}
 
+	cdns3_gadget_giveback(priv_ep, priv_req, -ECONNRESET);
+
 not_found:
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
 	return ret;
@@ -2324,8 +2329,6 @@ static void cdns3_gadget_config(struct cdns3_device *priv_dev)
 	writel(USB_CONF_CLK2OFFDS | USB_CONF_L1DS, &regs->usb_conf);
 
 	cdns3_configure_dmult(priv_dev, NULL);
-
-	cdns3_gadget_pullup(&priv_dev->gadget, 1);
 }
 
 /**
@@ -2340,9 +2343,35 @@ static int cdns3_gadget_udc_start(struct usb_gadget *gadget,
 {
 	struct cdns3_device *priv_dev = gadget_to_cdns3_device(gadget);
 	unsigned long flags;
+	enum usb_device_speed max_speed = driver->max_speed;
 
 	spin_lock_irqsave(&priv_dev->lock, flags);
 	priv_dev->gadget_driver = driver;
+
+	/* limit speed if necessary */
+	max_speed = min(driver->max_speed, gadget->max_speed);
+
+	switch (max_speed) {
+	case USB_SPEED_FULL:
+		writel(USB_CONF_SFORCE_FS, &priv_dev->regs->usb_conf);
+		writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf);
+		break;
+	case USB_SPEED_HIGH:
+		writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf);
+		break;
+	case USB_SPEED_SUPER:
+		break;
+	default:
+		dev_err(priv_dev->dev,
+			"invalid maximum_speed parameter %d\n",
+			max_speed);
+		/* fall through */
+	case USB_SPEED_UNKNOWN:
+		/* default to superspeed */
+		max_speed = USB_SPEED_SUPER;
+		break;
+	}
+
 	cdns3_gadget_config(priv_dev);
 	spin_unlock_irqrestore(&priv_dev->lock, flags);
 	return 0;
@@ -2376,6 +2405,8 @@ static int cdns3_gadget_udc_stop(struct usb_gadget *gadget)
 		writel(EP_CMD_EPRST, &priv_dev->regs->ep_cmd);
 		readl_poll_timeout_atomic(&priv_dev->regs->ep_cmd, val,
 					  !(val & EP_CMD_EPRST), 1, 100);
+
+		priv_ep->flags &= ~EP_CLAIMED;
 	}
 
 	/* disable interrupt for device */
@@ -2570,12 +2601,7 @@ static int cdns3_gadget_start(struct cdns3 *cdns)
 	/* Check the maximum_speed parameter */
 	switch (max_speed) {
 	case USB_SPEED_FULL:
-		writel(USB_CONF_SFORCE_FS, &priv_dev->regs->usb_conf);
-		writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf);
-		break;
 	case USB_SPEED_HIGH:
-		writel(USB_CONF_USB3DIS, &priv_dev->regs->usb_conf);
-		break;
 	case USB_SPEED_SUPER:
 		break;
 	default:
@@ -2708,8 +2734,6 @@ static int cdns3_gadget_suspend(struct cdns3 *cdns, bool do_wakeup)
 	/* disable interrupt for device */
 	writel(0, &priv_dev->regs->usb_ien);
 
-	cdns3_gadget_pullup(&priv_dev->gadget, 0);
-
 	return 0;
 }
 
diff --git a/drivers/usb/cdns3/host-export.h b/drivers/usb/cdns3/host-export.h
index b498a170b7e8..ae11810f8826 100644
--- a/drivers/usb/cdns3/host-export.h
+++ b/drivers/usb/cdns3/host-export.h
@@ -12,7 +12,6 @@
 #ifdef CONFIG_USB_CDNS3_HOST
 
 int cdns3_host_init(struct cdns3 *cdns);
-void cdns3_host_exit(struct cdns3 *cdns);
 
 #else
 
diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c
index 2733a8f71fcd..ad788bf3fe4f 100644
--- a/drivers/usb/cdns3/host.c
+++ b/drivers/usb/cdns3/host.c
@@ -12,6 +12,7 @@
 #include <linux/platform_device.h>
 #include "core.h"
 #include "drd.h"
+#include "host-export.h"
 
 static int __cdns3_host_init(struct cdns3 *cdns)
 {
diff --git a/drivers/usb/class/usblp.c b/drivers/usb/class/usblp.c
index fb8bd60c83f4..0d8e3f3804a3 100644
--- a/drivers/usb/class/usblp.c
+++ b/drivers/usb/class/usblp.c
@@ -445,6 +445,7 @@ static void usblp_cleanup(struct usblp *usblp)
 	kfree(usblp->readbuf);
 	kfree(usblp->device_id_string);
 	kfree(usblp->statusbuf);
+	usb_put_intf(usblp->intf);
 	kfree(usblp);
 }
 
@@ -1113,7 +1114,7 @@ static int usblp_probe(struct usb_interface *intf,
 	init_waitqueue_head(&usblp->wwait);
 	init_usb_anchor(&usblp->urbs);
 	usblp->ifnum = intf->cur_altsetting->desc.bInterfaceNumber;
-	usblp->intf = intf;
+	usblp->intf = usb_get_intf(intf);
 
 	/* Malloc device ID string buffer to the largest expected length,
 	 * since we can re-query it on an ioctl and a dynamic string
@@ -1198,6 +1199,7 @@ abort:
 	kfree(usblp->readbuf);
 	kfree(usblp->statusbuf);
 	kfree(usblp->device_id_string);
+	usb_put_intf(usblp->intf);
 	kfree(usblp);
 abort_ret:
 	return retval;
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 151a74a54386..1ac1095bfeac 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -348,6 +348,11 @@ static int usb_parse_endpoint(struct device *ddev, int cfgno, int inum,
 
 	/* Validate the wMaxPacketSize field */
 	maxp = usb_endpoint_maxp(&endpoint->desc);
+	if (maxp == 0) {
+		dev_warn(ddev, "config %d interface %d altsetting %d endpoint 0x%X has wMaxPacketSize 0, skipping\n",
+		    cfgno, inum, asnum, d->bEndpointAddress);
+		goto skip_to_next_endpoint_or_interface_descriptor;
+	}
 
 	/* Find the highest legal maxpacket size for this endpoint */
 	i = 0;		/* additional transactions per microframe */
diff --git a/drivers/usb/dwc3/Kconfig b/drivers/usb/dwc3/Kconfig
index 89abc6078703..556a876c7896 100644
--- a/drivers/usb/dwc3/Kconfig
+++ b/drivers/usb/dwc3/Kconfig
@@ -102,6 +102,7 @@ config USB_DWC3_MESON_G12A
        depends on ARCH_MESON || COMPILE_TEST
        default USB_DWC3
        select USB_ROLE_SWITCH
+	select REGMAP_MMIO
        help
          Support USB2/3 functionality in Amlogic G12A platforms.
 	 Say 'Y' or 'M' if you have one such device.
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 999ce5e84d3c..97d6ae3c4df2 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -312,8 +312,7 @@ static void dwc3_frame_length_adjustment(struct dwc3 *dwc)
 
 	reg = dwc3_readl(dwc->regs, DWC3_GFLADJ);
 	dft = reg & DWC3_GFLADJ_30MHZ_MASK;
-	if (!dev_WARN_ONCE(dwc->dev, dft == dwc->fladj,
-	    "request value same as default, ignoring\n")) {
+	if (dft != dwc->fladj) {
 		reg &= ~DWC3_GFLADJ_30MHZ_MASK;
 		reg |= DWC3_GFLADJ_30MHZ_SDBND_SEL | dwc->fladj;
 		dwc3_writel(dwc->regs, DWC3_GFLADJ, reg);
diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c
index 5e8e18222f92..023f0357efd7 100644
--- a/drivers/usb/dwc3/dwc3-pci.c
+++ b/drivers/usb/dwc3/dwc3-pci.c
@@ -258,7 +258,7 @@ static int dwc3_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
 
 	ret = platform_device_add_properties(dwc->dwc3, p);
 	if (ret < 0)
-		return ret;
+		goto err;
 
 	ret = dwc3_pci_quirks(dwc);
 	if (ret)
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 86dc1db788a9..a9aba716bf80 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -707,6 +707,12 @@ static void dwc3_remove_requests(struct dwc3 *dwc, struct dwc3_ep *dep)
 
 		dwc3_gadget_giveback(dep, req, -ESHUTDOWN);
 	}
+
+	while (!list_empty(&dep->cancelled_list)) {
+		req = next_request(&dep->cancelled_list);
+
+		dwc3_gadget_giveback(dep, req, -ESHUTDOWN);
+	}
 }
 
 /**
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index d516e8d6cd7f..5ec54b69c29c 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2170,14 +2170,18 @@ void composite_dev_cleanup(struct usb_composite_dev *cdev)
 			usb_ep_dequeue(cdev->gadget->ep0, cdev->os_desc_req);
 
 		kfree(cdev->os_desc_req->buf);
+		cdev->os_desc_req->buf = NULL;
 		usb_ep_free_request(cdev->gadget->ep0, cdev->os_desc_req);
+		cdev->os_desc_req = NULL;
 	}
 	if (cdev->req) {
 		if (cdev->setup_pending)
 			usb_ep_dequeue(cdev->gadget->ep0, cdev->req);
 
 		kfree(cdev->req->buf);
+		cdev->req->buf = NULL;
 		usb_ep_free_request(cdev->gadget->ep0, cdev->req);
+		cdev->req = NULL;
 	}
 	cdev->next_string_id = 0;
 	device_remove_file(&cdev->gadget->dev, &dev_attr_suspended);
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 025129942894..33852c2b29d1 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -61,6 +61,8 @@ struct gadget_info {
 	bool use_os_desc;
 	char b_vendor_code;
 	char qw_sign[OS_STRING_QW_SIGN_LEN];
+	spinlock_t spinlock;
+	bool unbind;
 };
 
 static inline struct gadget_info *to_gadget_info(struct config_item *item)
@@ -1244,6 +1246,7 @@ static int configfs_composite_bind(struct usb_gadget *gadget,
 	int				ret;
 
 	/* the gi->lock is hold by the caller */
+	gi->unbind = 0;
 	cdev->gadget = gadget;
 	set_gadget_data(gadget, cdev);
 	ret = composite_dev_prepare(composite, cdev);
@@ -1376,31 +1379,128 @@ static void configfs_composite_unbind(struct usb_gadget *gadget)
 {
 	struct usb_composite_dev	*cdev;
 	struct gadget_info		*gi;
+	unsigned long flags;
 
 	/* the gi->lock is hold by the caller */
 
 	cdev = get_gadget_data(gadget);
 	gi = container_of(cdev, struct gadget_info, cdev);
+	spin_lock_irqsave(&gi->spinlock, flags);
+	gi->unbind = 1;
+	spin_unlock_irqrestore(&gi->spinlock, flags);
 
 	kfree(otg_desc[0]);
 	otg_desc[0] = NULL;
 	purge_configs_funcs(gi);
 	composite_dev_cleanup(cdev);
 	usb_ep_autoconfig_reset(cdev->gadget);
+	spin_lock_irqsave(&gi->spinlock, flags);
 	cdev->gadget = NULL;
 	set_gadget_data(gadget, NULL);
+	spin_unlock_irqrestore(&gi->spinlock, flags);
+}
+
+static int configfs_composite_setup(struct usb_gadget *gadget,
+		const struct usb_ctrlrequest *ctrl)
+{
+	struct usb_composite_dev *cdev;
+	struct gadget_info *gi;
+	unsigned long flags;
+	int ret;
+
+	cdev = get_gadget_data(gadget);
+	if (!cdev)
+		return 0;
+
+	gi = container_of(cdev, struct gadget_info, cdev);
+	spin_lock_irqsave(&gi->spinlock, flags);
+	cdev = get_gadget_data(gadget);
+	if (!cdev || gi->unbind) {
+		spin_unlock_irqrestore(&gi->spinlock, flags);
+		return 0;
+	}
+
+	ret = composite_setup(gadget, ctrl);
+	spin_unlock_irqrestore(&gi->spinlock, flags);
+	return ret;
+}
+
+static void configfs_composite_disconnect(struct usb_gadget *gadget)
+{
+	struct usb_composite_dev *cdev;
+	struct gadget_info *gi;
+	unsigned long flags;
+
+	cdev = get_gadget_data(gadget);
+	if (!cdev)
+		return;
+
+	gi = container_of(cdev, struct gadget_info, cdev);
+	spin_lock_irqsave(&gi->spinlock, flags);
+	cdev = get_gadget_data(gadget);
+	if (!cdev || gi->unbind) {
+		spin_unlock_irqrestore(&gi->spinlock, flags);
+		return;
+	}
+
+	composite_disconnect(gadget);
+	spin_unlock_irqrestore(&gi->spinlock, flags);
+}
+
+static void configfs_composite_suspend(struct usb_gadget *gadget)
+{
+	struct usb_composite_dev *cdev;
+	struct gadget_info *gi;
+	unsigned long flags;
+
+	cdev = get_gadget_data(gadget);
+	if (!cdev)
+		return;
+
+	gi = container_of(cdev, struct gadget_info, cdev);
+	spin_lock_irqsave(&gi->spinlock, flags);
+	cdev = get_gadget_data(gadget);
+	if (!cdev || gi->unbind) {
+		spin_unlock_irqrestore(&gi->spinlock, flags);
+		return;
+	}
+
+	composite_suspend(gadget);
+	spin_unlock_irqrestore(&gi->spinlock, flags);
+}
+
+static void configfs_composite_resume(struct usb_gadget *gadget)
+{
+	struct usb_composite_dev *cdev;
+	struct gadget_info *gi;
+	unsigned long flags;
+
+	cdev = get_gadget_data(gadget);
+	if (!cdev)
+		return;
+
+	gi = container_of(cdev, struct gadget_info, cdev);
+	spin_lock_irqsave(&gi->spinlock, flags);
+	cdev = get_gadget_data(gadget);
+	if (!cdev || gi->unbind) {
+		spin_unlock_irqrestore(&gi->spinlock, flags);
+		return;
+	}
+
+	composite_resume(gadget);
+	spin_unlock_irqrestore(&gi->spinlock, flags);
 }
 
 static const struct usb_gadget_driver configfs_driver_template = {
 	.bind           = configfs_composite_bind,
 	.unbind         = configfs_composite_unbind,
 
-	.setup          = composite_setup,
-	.reset          = composite_disconnect,
-	.disconnect     = composite_disconnect,
+	.setup          = configfs_composite_setup,
+	.reset          = configfs_composite_disconnect,
+	.disconnect     = configfs_composite_disconnect,
 
-	.suspend	= composite_suspend,
-	.resume		= composite_resume,
+	.suspend	= configfs_composite_suspend,
+	.resume		= configfs_composite_resume,
 
 	.max_speed	= USB_SPEED_SUPER,
 	.driver = {
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 86ffc8307864..1d0d8952a74b 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -449,9 +449,11 @@ static void submit_request(struct usba_ep *ep, struct usba_request *req)
 		next_fifo_transaction(ep, req);
 		if (req->last_transaction) {
 			usba_ep_writel(ep, CTL_DIS, USBA_TX_PK_RDY);
-			usba_ep_writel(ep, CTL_ENB, USBA_TX_COMPLETE);
+			if (ep_is_control(ep))
+				usba_ep_writel(ep, CTL_ENB, USBA_TX_COMPLETE);
 		} else {
-			usba_ep_writel(ep, CTL_DIS, USBA_TX_COMPLETE);
+			if (ep_is_control(ep))
+				usba_ep_writel(ep, CTL_DIS, USBA_TX_COMPLETE);
 			usba_ep_writel(ep, CTL_ENB, USBA_TX_PK_RDY);
 		}
 	}
diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
index 92af8dc98c3d..51fa614b4079 100644
--- a/drivers/usb/gadget/udc/core.c
+++ b/drivers/usb/gadget/udc/core.c
@@ -98,6 +98,17 @@ int usb_ep_enable(struct usb_ep *ep)
 	if (ep->enabled)
 		goto out;
 
+	/* UDC drivers can't handle endpoints with maxpacket size 0 */
+	if (usb_endpoint_maxp(ep->desc) == 0) {
+		/*
+		 * We should log an error message here, but we can't call
+		 * dev_err() because there's no way to find the gadget
+		 * given only ep.
+		 */
+		ret = -EINVAL;
+		goto out;
+	}
+
 	ret = ep->ops->enable(ep, ep->desc);
 	if (ret)
 		goto out;
diff --git a/drivers/usb/gadget/udc/fsl_udc_core.c b/drivers/usb/gadget/udc/fsl_udc_core.c
index 20141c3096f6..9a05863b2876 100644
--- a/drivers/usb/gadget/udc/fsl_udc_core.c
+++ b/drivers/usb/gadget/udc/fsl_udc_core.c
@@ -2576,7 +2576,7 @@ static int fsl_udc_remove(struct platform_device *pdev)
 	dma_pool_destroy(udc_controller->td_pool);
 	free_irq(udc_controller->irq, udc_controller);
 	iounmap(dr_regs);
-	if (pdata->operating_mode == FSL_USB2_DR_DEVICE)
+	if (res && (pdata->operating_mode == FSL_USB2_DR_DEVICE))
 		release_mem_region(res->start, resource_size(res));
 
 	/* free udc --wait for the release() finished */
diff --git a/drivers/usb/gadget/udc/lpc32xx_udc.c b/drivers/usb/gadget/udc/lpc32xx_udc.c
index 2b1f3cc7819b..bf6c81e2f8cc 100644
--- a/drivers/usb/gadget/udc/lpc32xx_udc.c
+++ b/drivers/usb/gadget/udc/lpc32xx_udc.c
@@ -1177,11 +1177,11 @@ static void udc_pop_fifo(struct lpc32xx_udc *udc, u8 *data, u32 bytes)
 			tmp = readl(USBD_RXDATA(udc->udp_baseaddr));
 
 			bl = bytes - n;
-			if (bl > 3)
-				bl = 3;
+			if (bl > 4)
+				bl = 4;
 
 			for (i = 0; i < bl; i++)
-				data[n + i] = (u8) ((tmp >> (n * 8)) & 0xFF);
+				data[n + i] = (u8) ((tmp >> (i * 8)) & 0xFF);
 		}
 		break;
 
diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c
index e098f16c01cb..33703140233a 100644
--- a/drivers/usb/gadget/udc/renesas_usb3.c
+++ b/drivers/usb/gadget/udc/renesas_usb3.c
@@ -1544,10 +1544,10 @@ static void usb3_set_device_address(struct renesas_usb3 *usb3, u16 addr)
 static bool usb3_std_req_set_address(struct renesas_usb3 *usb3,
 				     struct usb_ctrlrequest *ctrl)
 {
-	if (ctrl->wValue >= 128)
+	if (le16_to_cpu(ctrl->wValue) >= 128)
 		return true;	/* stall */
 
-	usb3_set_device_address(usb3, ctrl->wValue);
+	usb3_set_device_address(usb3, le16_to_cpu(ctrl->wValue));
 	usb3_set_p0_con_for_no_data(usb3);
 
 	return false;
@@ -1582,6 +1582,7 @@ static bool usb3_std_req_get_status(struct renesas_usb3 *usb3,
 	struct renesas_usb3_ep *usb3_ep;
 	int num;
 	u16 status = 0;
+	__le16 tx_data;
 
 	switch (ctrl->bRequestType & USB_RECIP_MASK) {
 	case USB_RECIP_DEVICE:
@@ -1604,10 +1605,10 @@ static bool usb3_std_req_get_status(struct renesas_usb3 *usb3,
 	}
 
 	if (!stall) {
-		status = cpu_to_le16(status);
+		tx_data = cpu_to_le16(status);
 		dev_dbg(usb3_to_dev(usb3), "get_status: req = %p\n",
 			usb_req_to_usb3_req(usb3->ep0_req));
-		usb3_pipe0_internal_xfer(usb3, &status, sizeof(status),
+		usb3_pipe0_internal_xfer(usb3, &tx_data, sizeof(tx_data),
 					 usb3_pipe0_get_status_completion);
 	}
 
@@ -1772,7 +1773,7 @@ static bool usb3_std_req_set_sel(struct renesas_usb3 *usb3,
 static bool usb3_std_req_set_configuration(struct renesas_usb3 *usb3,
 					   struct usb_ctrlrequest *ctrl)
 {
-	if (ctrl->wValue > 0)
+	if (le16_to_cpu(ctrl->wValue) > 0)
 		usb3_set_bit(usb3, USB_COM_CON_CONF, USB3_USB_COM_CON);
 	else
 		usb3_clear_bit(usb3, USB_COM_CON_CONF, USB3_USB_COM_CON);
diff --git a/drivers/usb/host/xhci-debugfs.c b/drivers/usb/host/xhci-debugfs.c
index 7ba6afc7ef23..76c3f29562d2 100644
--- a/drivers/usb/host/xhci-debugfs.c
+++ b/drivers/usb/host/xhci-debugfs.c
@@ -202,10 +202,10 @@ static void xhci_ring_dump_segment(struct seq_file *s,
 		trb = &seg->trbs[i];
 		dma = seg->dma + i * sizeof(*trb);
 		seq_printf(s, "%pad: %s\n", &dma,
-			   xhci_decode_trb(trb->generic.field[0],
-					   trb->generic.field[1],
-					   trb->generic.field[2],
-					   trb->generic.field[3]));
+			   xhci_decode_trb(le32_to_cpu(trb->generic.field[0]),
+					   le32_to_cpu(trb->generic.field[1]),
+					   le32_to_cpu(trb->generic.field[2]),
+					   le32_to_cpu(trb->generic.field[3])));
 	}
 }
 
@@ -263,10 +263,10 @@ static int xhci_slot_context_show(struct seq_file *s, void *unused)
 	xhci = hcd_to_xhci(bus_to_hcd(dev->udev->bus));
 	slot_ctx = xhci_get_slot_ctx(xhci, dev->out_ctx);
 	seq_printf(s, "%pad: %s\n", &dev->out_ctx->dma,
-		   xhci_decode_slot_context(slot_ctx->dev_info,
-					    slot_ctx->dev_info2,
-					    slot_ctx->tt_info,
-					    slot_ctx->dev_state));
+		   xhci_decode_slot_context(le32_to_cpu(slot_ctx->dev_info),
+					    le32_to_cpu(slot_ctx->dev_info2),
+					    le32_to_cpu(slot_ctx->tt_info),
+					    le32_to_cpu(slot_ctx->dev_state)));
 
 	return 0;
 }
@@ -286,10 +286,10 @@ static int xhci_endpoint_context_show(struct seq_file *s, void *unused)
 		ep_ctx = xhci_get_ep_ctx(xhci, dev->out_ctx, dci);
 		dma = dev->out_ctx->dma + dci * CTX_SIZE(xhci->hcc_params);
 		seq_printf(s, "%pad: %s\n", &dma,
-			   xhci_decode_ep_context(ep_ctx->ep_info,
-						  ep_ctx->ep_info2,
-						  ep_ctx->deq,
-						  ep_ctx->tx_info));
+			   xhci_decode_ep_context(le32_to_cpu(ep_ctx->ep_info),
+						  le32_to_cpu(ep_ctx->ep_info2),
+						  le64_to_cpu(ep_ctx->deq),
+						  le32_to_cpu(ep_ctx->tx_info)));
 	}
 
 	return 0;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 85ceb43e3405..e7aab31fd9a5 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3330,6 +3330,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 			if (xhci_urb_suitable_for_idt(urb)) {
 				memcpy(&send_addr, urb->transfer_buffer,
 				       trb_buff_len);
+				le64_to_cpus(&send_addr);
 				field |= TRB_IDT;
 			}
 		}
@@ -3475,6 +3476,7 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		if (xhci_urb_suitable_for_idt(urb)) {
 			memcpy(&addr, urb->transfer_buffer,
 			       urb->transfer_buffer_length);
+			le64_to_cpus(&addr);
 			field |= TRB_IDT;
 		} else {
 			addr = (u64) urb->transfer_dma;
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 517ec3206f6e..6c17e3fe181a 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3071,6 +3071,48 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, unsigned int ep_index,
 	}
 }
 
+static void xhci_endpoint_disable(struct usb_hcd *hcd,
+				  struct usb_host_endpoint *host_ep)
+{
+	struct xhci_hcd		*xhci;
+	struct xhci_virt_device	*vdev;
+	struct xhci_virt_ep	*ep;
+	struct usb_device	*udev;
+	unsigned long		flags;
+	unsigned int		ep_index;
+
+	xhci = hcd_to_xhci(hcd);
+rescan:
+	spin_lock_irqsave(&xhci->lock, flags);
+
+	udev = (struct usb_device *)host_ep->hcpriv;
+	if (!udev || !udev->slot_id)
+		goto done;
+
+	vdev = xhci->devs[udev->slot_id];
+	if (!vdev)
+		goto done;
+
+	ep_index = xhci_get_endpoint_index(&host_ep->desc);
+	ep = &vdev->eps[ep_index];
+	if (!ep)
+		goto done;
+
+	/* wait for hub_tt_work to finish clearing hub TT */
+	if (ep->ep_state & EP_CLEARING_TT) {
+		spin_unlock_irqrestore(&xhci->lock, flags);
+		schedule_timeout_uninterruptible(1);
+		goto rescan;
+	}
+
+	if (ep->ep_state)
+		xhci_dbg(xhci, "endpoint disable with ep_state 0x%x\n",
+			 ep->ep_state);
+done:
+	host_ep->hcpriv = NULL;
+	spin_unlock_irqrestore(&xhci->lock, flags);
+}
+
 /*
  * Called after usb core issues a clear halt control message.
  * The host side of the halt should already be cleared by a reset endpoint
@@ -5238,20 +5280,13 @@ static void xhci_clear_tt_buffer_complete(struct usb_hcd *hcd,
 	unsigned int ep_index;
 	unsigned long flags;
 
-	/*
-	 * udev might be NULL if tt buffer is cleared during a failed device
-	 * enumeration due to a halted control endpoint. Usb core might
-	 * have allocated a new udev for the next enumeration attempt.
-	 */
-
 	xhci = hcd_to_xhci(hcd);
+
+	spin_lock_irqsave(&xhci->lock, flags);
 	udev = (struct usb_device *)ep->hcpriv;
-	if (!udev)
-		return;
 	slot_id = udev->slot_id;
 	ep_index = xhci_get_endpoint_index(&ep->desc);
 
-	spin_lock_irqsave(&xhci->lock, flags);
 	xhci->devs[slot_id]->eps[ep_index].ep_state &= ~EP_CLEARING_TT;
 	xhci_ring_doorbell_for_active_rings(xhci, slot_id, ep_index);
 	spin_unlock_irqrestore(&xhci->lock, flags);
@@ -5288,6 +5323,7 @@ static const struct hc_driver xhci_hc_driver = {
 	.free_streams =		xhci_free_streams,
 	.add_endpoint =		xhci_add_endpoint,
 	.drop_endpoint =	xhci_drop_endpoint,
+	.endpoint_disable =	xhci_endpoint_disable,
 	.endpoint_reset =	xhci_endpoint_reset,
 	.check_bandwidth =	xhci_check_bandwidth,
 	.reset_bandwidth =	xhci_reset_bandwidth,
diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c
index f3108d85e768..8f86b4ebca89 100644
--- a/drivers/usb/misc/ldusb.c
+++ b/drivers/usb/misc/ldusb.c
@@ -380,10 +380,7 @@ static int ld_usb_release(struct inode *inode, struct file *file)
 		goto exit;
 	}
 
-	if (mutex_lock_interruptible(&dev->mutex)) {
-		retval = -ERESTARTSYS;
-		goto exit;
-	}
+	mutex_lock(&dev->mutex);
 
 	if (dev->open_count != 1) {
 		retval = -ENODEV;
@@ -467,7 +464,7 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count,
 
 	/* wait for data */
 	spin_lock_irq(&dev->rbsl);
-	if (dev->ring_head == dev->ring_tail) {
+	while (dev->ring_head == dev->ring_tail) {
 		dev->interrupt_in_done = 0;
 		spin_unlock_irq(&dev->rbsl);
 		if (file->f_flags & O_NONBLOCK) {
@@ -477,15 +474,20 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count,
 		retval = wait_event_interruptible(dev->read_wait, dev->interrupt_in_done);
 		if (retval < 0)
 			goto unlock_exit;
-	} else {
-		spin_unlock_irq(&dev->rbsl);
+
+		spin_lock_irq(&dev->rbsl);
 	}
+	spin_unlock_irq(&dev->rbsl);
 
 	/* actual_buffer contains actual_length + interrupt_in_buffer */
 	actual_buffer = (size_t *)(dev->ring_buffer + dev->ring_tail * (sizeof(size_t)+dev->interrupt_in_endpoint_size));
+	if (*actual_buffer > dev->interrupt_in_endpoint_size) {
+		retval = -EIO;
+		goto unlock_exit;
+	}
 	bytes_to_read = min(count, *actual_buffer);
 	if (bytes_to_read < *actual_buffer)
-		dev_warn(&dev->intf->dev, "Read buffer overflow, %zd bytes dropped\n",
+		dev_warn(&dev->intf->dev, "Read buffer overflow, %zu bytes dropped\n",
 			 *actual_buffer-bytes_to_read);
 
 	/* copy one interrupt_in_buffer from ring_buffer into userspace */
@@ -493,11 +495,11 @@ static ssize_t ld_usb_read(struct file *file, char __user *buffer, size_t count,
 		retval = -EFAULT;
 		goto unlock_exit;
 	}
-	dev->ring_tail = (dev->ring_tail+1) % ring_buffer_size;
-
 	retval = bytes_to_read;
 
 	spin_lock_irq(&dev->rbsl);
+	dev->ring_tail = (dev->ring_tail + 1) % ring_buffer_size;
+
 	if (dev->buffer_overflow) {
 		dev->buffer_overflow = 0;
 		spin_unlock_irq(&dev->rbsl);
@@ -560,8 +562,9 @@ static ssize_t ld_usb_write(struct file *file, const char __user *buffer,
 	/* write the data into interrupt_out_buffer from userspace */
 	bytes_to_write = min(count, write_buffer_size*dev->interrupt_out_endpoint_size);
 	if (bytes_to_write < count)
-		dev_warn(&dev->intf->dev, "Write buffer overflow, %zd bytes dropped\n", count-bytes_to_write);
-	dev_dbg(&dev->intf->dev, "%s: count = %zd, bytes_to_write = %zd\n",
+		dev_warn(&dev->intf->dev, "Write buffer overflow, %zu bytes dropped\n",
+			count - bytes_to_write);
+	dev_dbg(&dev->intf->dev, "%s: count = %zu, bytes_to_write = %zu\n",
 		__func__, count, bytes_to_write);
 
 	if (copy_from_user(dev->interrupt_out_buffer, buffer, bytes_to_write)) {
@@ -578,7 +581,7 @@ static ssize_t ld_usb_write(struct file *file, const char __user *buffer,
 					 1 << 8, 0,
 					 dev->interrupt_out_buffer,
 					 bytes_to_write,
-					 USB_CTRL_SET_TIMEOUT * HZ);
+					 USB_CTRL_SET_TIMEOUT);
 		if (retval < 0)
 			dev_err(&dev->intf->dev,
 				"Couldn't submit HID_REQ_SET_REPORT %d\n",
@@ -693,10 +696,9 @@ static int ld_usb_probe(struct usb_interface *intf, const struct usb_device_id *
 		dev_warn(&intf->dev, "Interrupt out endpoint not found (using control endpoint instead)\n");
 
 	dev->interrupt_in_endpoint_size = usb_endpoint_maxp(dev->interrupt_in_endpoint);
-	dev->ring_buffer =
-		kmalloc_array(ring_buffer_size,
-			      sizeof(size_t) + dev->interrupt_in_endpoint_size,
-			      GFP_KERNEL);
+	dev->ring_buffer = kcalloc(ring_buffer_size,
+			sizeof(size_t) + dev->interrupt_in_endpoint_size,
+			GFP_KERNEL);
 	if (!dev->ring_buffer)
 		goto error;
 	dev->interrupt_in_buffer = kmalloc(dev->interrupt_in_endpoint_size, GFP_KERNEL);
diff --git a/drivers/usb/misc/legousbtower.c b/drivers/usb/misc/legousbtower.c
index 9d4c52a7ebe0..23061f1526b4 100644
--- a/drivers/usb/misc/legousbtower.c
+++ b/drivers/usb/misc/legousbtower.c
@@ -419,10 +419,7 @@ static int tower_release (struct inode *inode, struct file *file)
 		goto exit;
 	}
 
-	if (mutex_lock_interruptible(&dev->lock)) {
-	        retval = -ERESTARTSYS;
-		goto exit;
-	}
+	mutex_lock(&dev->lock);
 
 	if (dev->open_count != 1) {
 		dev_dbg(&dev->udev->dev, "%s: device not opened exactly once\n",
@@ -881,7 +878,7 @@ static int tower_probe (struct usb_interface *interface, const struct usb_device
 				  get_version_reply,
 				  sizeof(*get_version_reply),
 				  1000);
-	if (result < sizeof(*get_version_reply)) {
+	if (result != sizeof(*get_version_reply)) {
 		if (result >= 0)
 			result = -EIO;
 		dev_err(idev, "get version request failed: %d\n", result);
diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c
index c3d5c1206eec..9dd02160cca9 100644
--- a/drivers/usb/mtu3/mtu3_core.c
+++ b/drivers/usb/mtu3/mtu3_core.c
@@ -16,6 +16,7 @@
 #include <linux/platform_device.h>
 
 #include "mtu3.h"
+#include "mtu3_dr.h"
 #include "mtu3_debug.h"
 #include "mtu3_trace.h"
 
diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index 4c3de777ef6c..a3c30b609433 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -162,17 +162,17 @@ void usbhs_usbreq_get_val(struct usbhs_priv *priv, struct usb_ctrlrequest *req)
 	req->bRequest		= (val >> 8) & 0xFF;
 	req->bRequestType	= (val >> 0) & 0xFF;
 
-	req->wValue	= usbhs_read(priv, USBVAL);
-	req->wIndex	= usbhs_read(priv, USBINDX);
-	req->wLength	= usbhs_read(priv, USBLENG);
+	req->wValue	= cpu_to_le16(usbhs_read(priv, USBVAL));
+	req->wIndex	= cpu_to_le16(usbhs_read(priv, USBINDX));
+	req->wLength	= cpu_to_le16(usbhs_read(priv, USBLENG));
 }
 
 void usbhs_usbreq_set_val(struct usbhs_priv *priv, struct usb_ctrlrequest *req)
 {
 	usbhs_write(priv, USBREQ,  (req->bRequest << 8) | req->bRequestType);
-	usbhs_write(priv, USBVAL,  req->wValue);
-	usbhs_write(priv, USBINDX, req->wIndex);
-	usbhs_write(priv, USBLENG, req->wLength);
+	usbhs_write(priv, USBVAL,  le16_to_cpu(req->wValue));
+	usbhs_write(priv, USBINDX, le16_to_cpu(req->wIndex));
+	usbhs_write(priv, USBLENG, le16_to_cpu(req->wLength));
 
 	usbhs_bset(priv, DCPCTR, SUREQ, SUREQ);
 }
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index e5ef56991dba..cd38d74b3223 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -265,7 +265,7 @@ static int usbhsg_recip_handler_std_set_device(struct usbhs_priv *priv,
 	case USB_DEVICE_TEST_MODE:
 		usbhsg_recip_handler_std_control_done(priv, uep, ctrl);
 		udelay(100);
-		usbhs_sys_set_test_mode(priv, le16_to_cpu(ctrl->wIndex >> 8));
+		usbhs_sys_set_test_mode(priv, le16_to_cpu(ctrl->wIndex) >> 8);
 		break;
 	default:
 		usbhsg_recip_handler_std_control_done(priv, uep, ctrl);
@@ -315,7 +315,7 @@ static void __usbhsg_recip_send_status(struct usbhsg_gpriv *gpriv,
 	struct usbhs_pipe *pipe = usbhsg_uep_to_pipe(dcp);
 	struct device *dev = usbhsg_gpriv_to_dev(gpriv);
 	struct usb_request *req;
-	unsigned short *buf;
+	__le16 *buf;
 
 	/* alloc new usb_request for recip */
 	req = usb_ep_alloc_request(&dcp->ep, GFP_ATOMIC);
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index dd0ad67aa71e..ef23acc9b9ce 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -776,7 +776,6 @@ static void ti_close(struct usb_serial_port *port)
 	struct ti_port *tport;
 	int port_number;
 	int status;
-	int do_unlock;
 	unsigned long flags;
 
 	tdev = usb_get_serial_data(port->serial);
@@ -800,16 +799,13 @@ static void ti_close(struct usb_serial_port *port)
 			"%s - cannot send close port command, %d\n"
 							, __func__, status);
 
-	/* if mutex_lock is interrupted, continue anyway */
-	do_unlock = !mutex_lock_interruptible(&tdev->td_open_close_lock);
-	--tport->tp_tdev->td_open_port_count;
-	if (tport->tp_tdev->td_open_port_count <= 0) {
+	mutex_lock(&tdev->td_open_close_lock);
+	--tdev->td_open_port_count;
+	if (tdev->td_open_port_count == 0) {
 		/* last port is closed, shut down interrupt urb */
 		usb_kill_urb(port->serial->port[0]->interrupt_in_urb);
-		tport->tp_tdev->td_open_port_count = 0;
 	}
-	if (do_unlock)
-		mutex_unlock(&tdev->td_open_close_lock);
+	mutex_unlock(&tdev->td_open_close_lock);
 }
 
 
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 79314d8c94a4..ca3bd58f2025 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -559,6 +559,10 @@ static int firm_send_command(struct usb_serial_port *port, __u8 command,
 
 	command_port = port->serial->port[COMMAND_PORT];
 	command_info = usb_get_serial_port_data(command_port);
+
+	if (command_port->bulk_out_size < datasize + 1)
+		return -EIO;
+
 	mutex_lock(&command_info->mutex);
 	command_info->command_finished = false;
 
@@ -632,6 +636,7 @@ static void firm_setup_port(struct tty_struct *tty)
 	struct device *dev = &port->dev;
 	struct whiteheat_port_settings port_settings;
 	unsigned int cflag = tty->termios.c_cflag;
+	speed_t baud;
 
 	port_settings.port = port->port_number + 1;
 
@@ -692,11 +697,13 @@ static void firm_setup_port(struct tty_struct *tty)
 	dev_dbg(dev, "%s - XON = %2x, XOFF = %2x\n", __func__, port_settings.xon, port_settings.xoff);
 
 	/* get the baud rate wanted */
-	port_settings.baud = tty_get_baud_rate(tty);
-	dev_dbg(dev, "%s - baud rate = %d\n", __func__, port_settings.baud);
+	baud = tty_get_baud_rate(tty);
+	port_settings.baud = cpu_to_le32(baud);
+	dev_dbg(dev, "%s - baud rate = %u\n", __func__, baud);
 
 	/* fixme: should set validated settings */
-	tty_encode_baud_rate(tty, port_settings.baud, port_settings.baud);
+	tty_encode_baud_rate(tty, baud, baud);
+
 	/* handle any settings that aren't specified in the tty structure */
 	port_settings.lloop = 0;
 
diff --git a/drivers/usb/serial/whiteheat.h b/drivers/usb/serial/whiteheat.h
index 00398149cd8d..269e727a92f9 100644
--- a/drivers/usb/serial/whiteheat.h
+++ b/drivers/usb/serial/whiteheat.h
@@ -87,7 +87,7 @@ struct whiteheat_simple {
 
 struct whiteheat_port_settings {
 	__u8	port;		/* port number (1 to N) */
-	__u32	baud;		/* any value 7 - 460800, firmware calculates
+	__le32	baud;		/* any value 7 - 460800, firmware calculates
 				   best fit; arrives little endian */
 	__u8	bits;		/* 5, 6, 7, or 8 */
 	__u8	stop;		/* 1 or 2, default 1 (2 = 1.5 if bits = 5) */
diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c
index 6737fab94959..54a3c8195c96 100644
--- a/drivers/usb/storage/scsiglue.c
+++ b/drivers/usb/storage/scsiglue.c
@@ -68,7 +68,6 @@ static const char* host_info(struct Scsi_Host *host)
 static int slave_alloc (struct scsi_device *sdev)
 {
 	struct us_data *us = host_to_us(sdev->host);
-	int maxp;
 
 	/*
 	 * Set the INQUIRY transfer length to 36.  We don't use any of
@@ -78,15 +77,6 @@ static int slave_alloc (struct scsi_device *sdev)
 	sdev->inquiry_len = 36;
 
 	/*
-	 * USB has unusual scatter-gather requirements: the length of each
-	 * scatterlist element except the last must be divisible by the
-	 * Bulk maxpacket value.  Fortunately this value is always a
-	 * power of 2.  Inform the block layer about this requirement.
-	 */
-	maxp = usb_maxpacket(us->pusb_dev, us->recv_bulk_pipe, 0);
-	blk_queue_virt_boundary(sdev->request_queue, maxp - 1);
-
-	/*
 	 * Some host controllers may have alignment requirements.
 	 * We'll play it safe by requiring 512-byte alignment always.
 	 */
diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
index bf80d6f81f58..34538253f12c 100644
--- a/drivers/usb/storage/uas.c
+++ b/drivers/usb/storage/uas.c
@@ -789,30 +789,10 @@ static int uas_slave_alloc(struct scsi_device *sdev)
 {
 	struct uas_dev_info *devinfo =
 		(struct uas_dev_info *)sdev->host->hostdata;
-	int maxp;
 
 	sdev->hostdata = devinfo;
 
 	/*
-	 * We have two requirements here. We must satisfy the requirements
-	 * of the physical HC and the demands of the protocol, as we
-	 * definitely want no additional memory allocation in this path
-	 * ruling out using bounce buffers.
-	 *
-	 * For a transmission on USB to continue we must never send
-	 * a package that is smaller than maxpacket. Hence the length of each
-         * scatterlist element except the last must be divisible by the
-         * Bulk maxpacket value.
-	 * If the HC does not ensure that through SG,
-	 * the upper layer must do that. We must assume nothing
-	 * about the capabilities off the HC, so we use the most
-	 * pessimistic requirement.
-	 */
-
-	maxp = usb_maxpacket(devinfo->udev, devinfo->data_in_pipe, 0);
-	blk_queue_virt_boundary(sdev->request_queue, maxp - 1);
-
-	/*
 	 * The protocol has no requirements on alignment in the strict sense.
 	 * Controllers may or may not have alignment restrictions.
 	 * As this is not exported, we use an extremely conservative guess.
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
index c3803785f6ef..0ae40a13a9fe 100644
--- a/drivers/usb/usbip/vhci_tx.c
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -147,7 +147,10 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev)
 		}
 
 		kfree(iov);
+		/* This is only for isochronous case */
 		kfree(iso_buffer);
+		iso_buffer = NULL;
+
 		usbip_dbg_vhci_tx("send txdata\n");
 
 		total_size += txsize;
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 96fddc1dafc3..d864277ea16f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1658,7 +1658,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	struct bus_type *bus = NULL;
 	int ret;
 	bool resv_msi, msi_remap;
-	phys_addr_t resv_msi_base;
+	phys_addr_t resv_msi_base = 0;
 	struct iommu_domain_geometry geo;
 	LIST_HEAD(iova_copy);
 	LIST_HEAD(group_resv_regions);
diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index 08ad0d1f0476..a0a2d74967ef 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -852,6 +852,12 @@ static inline int xfer_kern(void *src, void *dst, size_t len)
 	return 0;
 }
 
+static inline int kern_xfer(void *dst, void *src, size_t len)
+{
+	memcpy(dst, src, len);
+	return 0;
+}
+
 /**
  * vringh_init_kern - initialize a vringh for a kernelspace vring.
  * @vrh: the vringh to initialize.
@@ -958,7 +964,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern);
 ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
 			     const void *src, size_t len)
 {
-	return vringh_iov_xfer(wiov, (void *)src, len, xfer_kern);
+	return vringh_iov_xfer(wiov, (void *)src, len, kern_xfer);
 }
 EXPORT_SYMBOL(vringh_iov_push_kern);
 
diff --git a/drivers/video/fbdev/c2p_core.h b/drivers/video/fbdev/c2p_core.h
index e1035a865fb9..45a6d895a7d7 100644
--- a/drivers/video/fbdev/c2p_core.h
+++ b/drivers/video/fbdev/c2p_core.h
@@ -29,7 +29,7 @@ static inline void _transp(u32 d[], unsigned int i1, unsigned int i2,
 
 extern void c2p_unsupported(void);
 
-static inline u32 get_mask(unsigned int n)
+static __always_inline u32 get_mask(unsigned int n)
 {
 	switch (n) {
 	case 1:
@@ -57,7 +57,7 @@ static inline u32 get_mask(unsigned int n)
      *  Transpose operations on 8 32-bit words
      */
 
-static inline void transp8(u32 d[], unsigned int n, unsigned int m)
+static __always_inline void transp8(u32 d[], unsigned int n, unsigned int m)
 {
 	u32 mask = get_mask(n);
 
@@ -99,7 +99,7 @@ static inline void transp8(u32 d[], unsigned int n, unsigned int m)
      *  Transpose operations on 4 32-bit words
      */
 
-static inline void transp4(u32 d[], unsigned int n, unsigned int m)
+static __always_inline void transp4(u32 d[], unsigned int n, unsigned int m)
 {
 	u32 mask = get_mask(n);
 
@@ -126,7 +126,7 @@ static inline void transp4(u32 d[], unsigned int n, unsigned int m)
      *  Transpose operations on 4 32-bit words (reverse order)
      */
 
-static inline void transp4x(u32 d[], unsigned int n, unsigned int m)
+static __always_inline void transp4x(u32 d[], unsigned int n, unsigned int m)
 {
 	u32 mask = get_mask(n);
 
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index bdc08244a648..a8041e451e9e 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1499,9 +1499,6 @@ static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
 		 * counter first before updating event flags.
 		 */
 		virtio_wmb(vq->weak_barriers);
-	} else {
-		used_idx = vq->last_used_idx;
-		wrap_counter = vq->packed.used_wrap_counter;
 	}
 
 	if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
@@ -1518,7 +1515,9 @@ static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
 	 */
 	virtio_mb(vq->weak_barriers);
 
-	if (is_used_desc_packed(vq, used_idx, wrap_counter)) {
+	if (is_used_desc_packed(vq,
+				vq->last_used_idx,
+				vq->packed.used_wrap_counter)) {
 		END_USE(vq);
 		return false;
 	}
diff --git a/drivers/watchdog/bd70528_wdt.c b/drivers/watchdog/bd70528_wdt.c
index b0152fef4fc7..bc60e036627a 100644
--- a/drivers/watchdog/bd70528_wdt.c
+++ b/drivers/watchdog/bd70528_wdt.c
@@ -288,3 +288,4 @@ module_platform_driver(bd70528_wdt);
 MODULE_AUTHOR("Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>");
 MODULE_DESCRIPTION("BD70528 watchdog driver");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:bd70528-wdt");
diff --git a/drivers/watchdog/cpwd.c b/drivers/watchdog/cpwd.c
index 9393be584e72..808eeb4779e4 100644
--- a/drivers/watchdog/cpwd.c
+++ b/drivers/watchdog/cpwd.c
@@ -26,6 +26,7 @@
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/timer.h>
+#include <linux/compat.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/io.h>
@@ -473,6 +474,11 @@ static long cpwd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return 0;
 }
 
+static long cpwd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	return cpwd_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
+}
+
 static ssize_t cpwd_write(struct file *file, const char __user *buf,
 			  size_t count, loff_t *ppos)
 {
@@ -497,7 +503,7 @@ static ssize_t cpwd_read(struct file *file, char __user *buffer,
 static const struct file_operations cpwd_fops = {
 	.owner =		THIS_MODULE,
 	.unlocked_ioctl =	cpwd_ioctl,
-	.compat_ioctl =		compat_ptr_ioctl,
+	.compat_ioctl =		cpwd_compat_ioctl,
 	.open =			cpwd_open,
 	.write =		cpwd_write,
 	.read =			cpwd_read,
diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c
index 7ea5cf54e94a..8ed89f032ebf 100644
--- a/drivers/watchdog/imx_sc_wdt.c
+++ b/drivers/watchdog/imx_sc_wdt.c
@@ -99,8 +99,14 @@ static int imx_sc_wdt_set_pretimeout(struct watchdog_device *wdog,
 {
 	struct arm_smccc_res res;
 
+	/*
+	 * SCU firmware calculates pretimeout based on current time
+	 * stamp instead of watchdog timeout stamp, need to convert
+	 * the pretimeout to SCU firmware's timeout value.
+	 */
 	arm_smccc_smc(IMX_SIP_TIMER, IMX_SIP_TIMER_SET_PRETIME_WDOG,
-		      pretimeout * 1000, 0, 0, 0, 0, 0, &res);
+		      (wdog->timeout - pretimeout) * 1000, 0, 0, 0,
+		      0, 0, &res);
 	if (res.a0)
 		return -EACCES;
 
diff --git a/drivers/watchdog/meson_gxbb_wdt.c b/drivers/watchdog/meson_gxbb_wdt.c
index d17c1a6ed723..5a9ca10fbcfa 100644
--- a/drivers/watchdog/meson_gxbb_wdt.c
+++ b/drivers/watchdog/meson_gxbb_wdt.c
@@ -89,8 +89,8 @@ static unsigned int meson_gxbb_wdt_get_timeleft(struct watchdog_device *wdt_dev)
 
 	reg = readl(data->reg_base + GXBB_WDT_TCNT_REG);
 
-	return ((reg >> GXBB_WDT_TCNT_CNT_SHIFT) -
-		(reg & GXBB_WDT_TCNT_SETUP_MASK)) / 1000;
+	return ((reg & GXBB_WDT_TCNT_SETUP_MASK) -
+		(reg >> GXBB_WDT_TCNT_CNT_SHIFT)) / 1000;
 }
 
 static const struct watchdog_ops meson_gxbb_wdt_ops = {
diff --git a/drivers/watchdog/pm8916_wdt.c b/drivers/watchdog/pm8916_wdt.c
index 2d3652004e39..1213179f863c 100644
--- a/drivers/watchdog/pm8916_wdt.c
+++ b/drivers/watchdog/pm8916_wdt.c
@@ -163,9 +163,17 @@ static int pm8916_wdt_probe(struct platform_device *pdev)
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq > 0) {
-		if (devm_request_irq(dev, irq, pm8916_wdt_isr, 0, "pm8916_wdt",
-				     wdt))
-			irq = 0;
+		err = devm_request_irq(dev, irq, pm8916_wdt_isr, 0,
+				       "pm8916_wdt", wdt);
+		if (err)
+			return err;
+
+		wdt->wdev.info = &pm8916_wdt_pt_ident;
+	} else {
+		if (irq == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
+		wdt->wdev.info = &pm8916_wdt_ident;
 	}
 
 	/* Configure watchdog to hard-reset mode */
@@ -177,7 +185,6 @@ static int pm8916_wdt_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	wdt->wdev.info = (irq > 0) ? &pm8916_wdt_pt_ident : &pm8916_wdt_ident,
 	wdt->wdev.ops = &pm8916_wdt_ops,
 	wdt->wdev.parent = dev;
 	wdt->wdev.min_timeout = PM8916_WDT_MIN_TIMEOUT;
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index bf7e3f23bba7..670700cb1110 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1761,6 +1761,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 			btrfs_err(info,
 "bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
 				  cache->key.objectid);
+			btrfs_put_block_group(cache);
 			ret = -EINVAL;
 			goto error;
 		}
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 19d669d12ca1..fe2b8765d9e6 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -734,8 +734,6 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *fixup_workers;
 	struct btrfs_workqueue *delayed_workers;
 
-	/* the extent workers do delayed refs on the extent allocation tree */
-	struct btrfs_workqueue *extent_workers;
 	struct task_struct *transaction_kthread;
 	struct task_struct *cleaner_kthread;
 	u32 thread_pool_size;
@@ -2489,8 +2487,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     int nitems, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_rsv *rsv);
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
-				    bool qgroup_free);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
diff --git a/fs/btrfs/delalloc-space.c b/fs/btrfs/delalloc-space.c
index d949d7d2abed..db9f2c58eb4a 100644
--- a/fs/btrfs/delalloc-space.c
+++ b/fs/btrfs/delalloc-space.c
@@ -381,7 +381,6 @@ int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 out_qgroup:
 	btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
 out_fail:
-	btrfs_inode_rsv_release(inode, true);
 	if (delalloc_lock)
 		mutex_unlock(&inode->delalloc_mutex);
 	return ret;
@@ -418,7 +417,6 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
  * btrfs_delalloc_release_extents - release our outstanding_extents
  * @inode: the inode to balance the reservation for.
  * @num_bytes: the number of bytes we originally reserved with
- * @qgroup_free: do we need to free qgroup meta reservation or convert them.
  *
  * When we reserve space we increase outstanding_extents for the extents we may
  * add.  Once we've set the range as delalloc or created our ordered extents we
@@ -426,8 +424,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
  * temporarily tracked outstanding_extents.  This _must_ be used in conjunction
  * with btrfs_delalloc_reserve_metadata.
  */
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
-				    bool qgroup_free)
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes)
 {
 	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned num_extents;
@@ -441,7 +438,7 @@ void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
 	if (btrfs_is_testing(fs_info))
 		return;
 
-	btrfs_inode_rsv_release(inode, qgroup_free);
+	btrfs_inode_rsv_release(inode, true);
 }
 
 /**
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 044981cf6df9..402b61bf345c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2008,7 +2008,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->readahead_workers);
 	btrfs_destroy_workqueue(fs_info->flush_workers);
 	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
-	btrfs_destroy_workqueue(fs_info->extent_workers);
 	/*
 	 * Now that all other work queues are destroyed, we can safely destroy
 	 * the queues used for metadata I/O, since tasks from those other work
@@ -2214,10 +2213,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 				      max_active, 2);
 	fs_info->qgroup_rescan_workers =
 		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
-	fs_info->extent_workers =
-		btrfs_alloc_workqueue(fs_info, "extent-refs", flags,
-				      min_t(u64, fs_devices->num_devices,
-					    max_active), 8);
 
 	if (!(fs_info->workers && fs_info->delalloc_workers &&
 	      fs_info->submit_workers && fs_info->flush_workers &&
@@ -2228,7 +2223,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
 	      fs_info->caching_workers && fs_info->readahead_workers &&
 	      fs_info->fixup_workers && fs_info->delayed_workers &&
-	      fs_info->extent_workers &&
 	      fs_info->qgroup_rescan_workers)) {
 		return -ENOMEM;
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 27e5b269e729..435a502a3226 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1692,7 +1692,7 @@ again:
 				    force_page_uptodate);
 		if (ret) {
 			btrfs_delalloc_release_extents(BTRFS_I(inode),
-						       reserve_bytes, true);
+						       reserve_bytes);
 			break;
 		}
 
@@ -1704,7 +1704,7 @@ again:
 			if (extents_locked == -EAGAIN)
 				goto again;
 			btrfs_delalloc_release_extents(BTRFS_I(inode),
-						       reserve_bytes, true);
+						       reserve_bytes);
 			ret = extents_locked;
 			break;
 		}
@@ -1772,8 +1772,7 @@ again:
 		else
 			free_extent_state(cached_state);
 
-		btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes,
-					       true);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes);
 		if (ret) {
 			btrfs_drop_pages(pages, num_pages);
 			break;
@@ -2068,25 +2067,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0, err;
-	u64 len;
 
-	/*
-	 * If the inode needs a full sync, make sure we use a full range to
-	 * avoid log tree corruption, due to hole detection racing with ordered
-	 * extent completion for adjacent ranges, and assertion failures during
-	 * hole detection.
-	 */
-	if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-		     &BTRFS_I(inode)->runtime_flags)) {
-		start = 0;
-		end = LLONG_MAX;
-	}
-
-	/*
-	 * The range length can be represented by u64, we have to do the typecasts
-	 * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
-	 */
-	len = (u64)end - (u64)start + 1;
 	trace_btrfs_sync_file(file, datasync);
 
 	btrfs_init_log_ctx(&ctx, inode);
@@ -2113,6 +2094,19 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 
 	/*
+	 * If the inode needs a full sync, make sure we use a full range to
+	 * avoid log tree corruption, due to hole detection racing with ordered
+	 * extent completion for adjacent ranges, and assertion failures during
+	 * hole detection. Do this while holding the inode lock, to avoid races
+	 * with other tasks.
+	 */
+	if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
+		     &BTRFS_I(inode)->runtime_flags)) {
+		start = 0;
+		end = LLONG_MAX;
+	}
+
+	/*
 	 * Before we acquired the inode's lock, someone may have dirtied more
 	 * pages in the target range. We need to make sure that writeback for
 	 * any such pages does not start while we are logging the inode, because
@@ -2139,8 +2133,11 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	/*
 	 * We have to do this here to avoid the priority inversion of waiting on
 	 * IO of a lower priority task while holding a transaction open.
+	 *
+	 * Also, the range length can be represented by u64, we have to do the
+	 * typecasts to avoid signed overflow if it's [0, LLONG_MAX].
 	 */
-	ret = btrfs_wait_ordered_range(inode, start, len);
+	ret = btrfs_wait_ordered_range(inode, start, (u64)end - (u64)start + 1);
 	if (ret) {
 		up_write(&BTRFS_I(inode)->dio_sem);
 		inode_unlock(inode);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 63cad7865d75..37345fb6191d 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -501,13 +501,13 @@ again:
 	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
 					      prealloc, prealloc, &alloc_hint);
 	if (ret) {
-		btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, true);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
 		btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc, true);
 		goto out_put;
 	}
 
 	ret = btrfs_write_out_ino_cache(root, trans, path, inode);
-	btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc, false);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), prealloc);
 out_put:
 	iput(inode);
 out_release:
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0f2754eaa05b..c6dc4dd16cf7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -474,6 +474,7 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
 	u64 start = async_chunk->start;
 	u64 end = async_chunk->end;
 	u64 actual_end;
+	u64 i_size;
 	int ret = 0;
 	struct page **pages = NULL;
 	unsigned long nr_pages;
@@ -488,7 +489,19 @@ static noinline int compress_file_range(struct async_chunk *async_chunk)
 	inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
 			SZ_16K);
 
-	actual_end = min_t(u64, i_size_read(inode), end + 1);
+	/*
+	 * We need to save i_size before now because it could change in between
+	 * us evaluating the size and assigning it.  This is because we lock and
+	 * unlock the page in truncate and fallocate, and then modify the i_size
+	 * later on.
+	 *
+	 * The barriers are to emulate READ_ONCE, remove that once i_size_read
+	 * does that for us.
+	 */
+	barrier();
+	i_size = i_size_read(inode);
+	barrier();
+	actual_end = min_t(u64, i_size, end + 1);
 again:
 	will_compress = 0;
 	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
@@ -2206,7 +2219,7 @@ again:
 
 	ClearPageChecked(page);
 	set_page_dirty(page);
-	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, false);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
 out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			     &cached_state);
@@ -4951,7 +4964,7 @@ again:
 	if (!page) {
 		btrfs_delalloc_release_space(inode, data_reserved,
 					     block_start, blocksize, true);
-		btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, true);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -5018,7 +5031,7 @@ out_unlock:
 	if (ret)
 		btrfs_delalloc_release_space(inode, data_reserved, block_start,
 					     blocksize, true);
-	btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize, (ret != 0));
+	btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
 	unlock_page(page);
 	put_page(page);
 out:
@@ -8709,7 +8722,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		} else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode, data_reserved,
 					offset, count - (size_t)ret, true);
-		btrfs_delalloc_release_extents(BTRFS_I(inode), count, false);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), count);
 	}
 out:
 	if (wakeup)
@@ -9059,7 +9072,7 @@ again:
 	unlock_extent_cached(io_tree, page_start, page_end, &cached_state);
 
 	if (!ret2) {
-		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
 		sb_end_pagefault(inode->i_sb);
 		extent_changeset_free(data_reserved);
 		return VM_FAULT_LOCKED;
@@ -9068,7 +9081,7 @@ again:
 out_unlock:
 	unlock_page(page);
 out:
-	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, (ret != 0));
+	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
 	btrfs_delalloc_release_space(inode, data_reserved, page_start,
 				     reserved_space, (ret != 0));
 out_noreserve:
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index de730e56d3f5..23272d9154f3 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1360,8 +1360,7 @@ again:
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
-	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT,
-				       false);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
 	extent_changeset_free(data_reserved);
 	return i_done;
 out:
@@ -1372,8 +1371,7 @@ out:
 	btrfs_delalloc_release_space(inode, data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT, true);
-	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT,
-				       true);
+	btrfs_delalloc_release_extents(BTRFS_I(inode), page_cnt << PAGE_SHIFT);
 	extent_changeset_free(data_reserved);
 	return ret;
 
@@ -4197,9 +4195,6 @@ static noinline long btrfs_ioctl_start_sync(struct btrfs_root *root,
 	u64 transid;
 	int ret;
 
-	btrfs_warn(root->fs_info,
-	"START_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
 	trans = btrfs_attach_transaction_barrier(root);
 	if (IS_ERR(trans)) {
 		if (PTR_ERR(trans) != -ENOENT)
@@ -4227,9 +4222,6 @@ static noinline long btrfs_ioctl_wait_sync(struct btrfs_fs_info *fs_info,
 {
 	u64 transid;
 
-	btrfs_warn(fs_info,
-		"WAIT_SYNC ioctl is deprecated and will be removed in kernel 5.7");
-
 	if (argp) {
 		if (copy_from_user(&transid, argp, sizeof(transid)))
 			return -EFAULT;
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c4bb69941c77..3ad151655eb8 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3629,7 +3629,7 @@ int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
 		return 0;
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
-	trace_qgroup_meta_reserve(root, type, (s64)num_bytes);
+	trace_qgroup_meta_reserve(root, (s64)num_bytes, type);
 	ret = qgroup_reserve(root, num_bytes, enforce, type);
 	if (ret < 0)
 		return ret;
@@ -3676,7 +3676,7 @@ void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
 	 */
 	num_bytes = sub_root_meta_rsv(root, num_bytes, type);
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
-	trace_qgroup_meta_reserve(root, type, -(s64)num_bytes);
+	trace_qgroup_meta_reserve(root, -(s64)num_bytes, type);
 	btrfs_qgroup_free_refroot(fs_info, root->root_key.objectid,
 				  num_bytes, type);
 }
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 00504657b602..5cd42b66818c 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3277,6 +3277,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			if (!page) {
 				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							PAGE_SIZE, true);
+				btrfs_delalloc_release_extents(BTRFS_I(inode),
+							PAGE_SIZE);
 				ret = -ENOMEM;
 				goto out;
 			}
@@ -3297,7 +3299,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							PAGE_SIZE, true);
 				btrfs_delalloc_release_extents(BTRFS_I(inode),
-							       PAGE_SIZE, true);
+							       PAGE_SIZE);
 				ret = -EIO;
 				goto out;
 			}
@@ -3326,7 +3328,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							 PAGE_SIZE, true);
 			btrfs_delalloc_release_extents(BTRFS_I(inode),
-			                               PAGE_SIZE, true);
+			                               PAGE_SIZE);
 
 			clear_extent_bits(&BTRFS_I(inode)->io_tree,
 					  page_start, page_end,
@@ -3342,8 +3344,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 		put_page(page);
 
 		index++;
-		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE,
-					       false);
+		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
 		balance_dirty_pages_ratelimited(inode->i_mapping);
 		btrfs_throttle(fs_info);
 	}
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 98dc092a905e..e8a4b0ebe97f 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -893,6 +893,15 @@ static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
 	while (ticket->bytes > 0 && ticket->error == 0) {
 		ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
 		if (ret) {
+			/*
+			 * Delete us from the list. After we unlock the space
+			 * info, we don't want the async reclaim job to reserve
+			 * space for this ticket. If that would happen, then the
+			 * ticket's task would not known that space was reserved
+			 * despite getting an error, resulting in a space leak
+			 * (bytes_may_use counter of our space_info).
+			 */
+			list_del_init(&ticket->list);
 			ticket->error = -EINTR;
 			break;
 		}
@@ -945,12 +954,24 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
 	spin_lock(&space_info->lock);
 	ret = ticket->error;
 	if (ticket->bytes || ticket->error) {
+		/*
+		 * Need to delete here for priority tickets. For regular tickets
+		 * either the async reclaim job deletes the ticket from the list
+		 * or we delete it ourselves at wait_reserve_ticket().
+		 */
 		list_del_init(&ticket->list);
 		if (!ret)
 			ret = -ENOSPC;
 	}
 	spin_unlock(&space_info->lock);
 	ASSERT(list_empty(&ticket->list));
+	/*
+	 * Check that we can't have an error set if the reservation succeeded,
+	 * as that would confuse tasks and lead them to error out without
+	 * releasing reserved space (if an error happens the expectation is that
+	 * space wasn't reserved at all).
+	 */
+	ASSERT(!(ticket->bytes == 0 && ticket->error));
 	return ret;
 }
 
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 43e488f5d063..076d5b8014fb 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -686,9 +686,7 @@ static void dev_item_err(const struct extent_buffer *eb, int slot,
 static int check_dev_item(struct extent_buffer *leaf,
 			  struct btrfs_key *key, int slot)
 {
-	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_dev_item *ditem;
-	u64 max_devid = max(BTRFS_MAX_DEVS(fs_info), BTRFS_MAX_DEVS_SYS_CHUNK);
 
 	if (key->objectid != BTRFS_DEV_ITEMS_OBJECTID) {
 		dev_item_err(leaf, slot,
@@ -696,12 +694,6 @@ static int check_dev_item(struct extent_buffer *leaf,
 			     key->objectid, BTRFS_DEV_ITEMS_OBJECTID);
 		return -EUCLEAN;
 	}
-	if (key->offset > max_devid) {
-		dev_item_err(leaf, slot,
-			     "invalid devid: has=%llu expect=[0, %llu]",
-			     key->offset, max_devid);
-		return -EUCLEAN;
-	}
 	ditem = btrfs_item_ptr(leaf, slot, struct btrfs_dev_item);
 	if (btrfs_device_id(leaf, ditem) != key->offset) {
 		dev_item_err(leaf, slot,
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index bdfe4493e43a..e04409f85063 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4967,6 +4967,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	} else if (type & BTRFS_BLOCK_GROUP_SYSTEM) {
 		max_stripe_size = SZ_32M;
 		max_chunk_size = 2 * max_stripe_size;
+		devs_max = min_t(int, devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
 	} else {
 		btrfs_err(info, "invalid chunk type 0x%llx requested",
 		       type);
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index d3b9c9d5c1bd..f5a38910a82b 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1058,6 +1058,11 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	dout("__ceph_remove_cap %p from %p\n", cap, &ci->vfs_inode);
 
+	/* remove from inode's cap rbtree, and clear auth cap */
+	rb_erase(&cap->ci_node, &ci->i_caps);
+	if (ci->i_auth_cap == cap)
+		ci->i_auth_cap = NULL;
+
 	/* remove from session list */
 	spin_lock(&session->s_cap_lock);
 	if (session->s_cap_iterator == cap) {
@@ -1091,11 +1096,6 @@ void __ceph_remove_cap(struct ceph_cap *cap, bool queue_release)
 
 	spin_unlock(&session->s_cap_lock);
 
-	/* remove from inode list */
-	rb_erase(&cap->ci_node, &ci->i_caps);
-	if (ci->i_auth_cap == cap)
-		ci->i_auth_cap = NULL;
-
 	if (removed)
 		ceph_put_cap(mdsc, cap);
 
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 4ca0b8ff9a72..d17a789fd856 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1553,36 +1553,37 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	int valid = 0;
 	struct dentry *parent;
-	struct inode *dir;
+	struct inode *dir, *inode;
 
 	if (flags & LOOKUP_RCU) {
 		parent = READ_ONCE(dentry->d_parent);
 		dir = d_inode_rcu(parent);
 		if (!dir)
 			return -ECHILD;
+		inode = d_inode_rcu(dentry);
 	} else {
 		parent = dget_parent(dentry);
 		dir = d_inode(parent);
+		inode = d_inode(dentry);
 	}
 
 	dout("d_revalidate %p '%pd' inode %p offset %lld\n", dentry,
-	     dentry, d_inode(dentry), ceph_dentry(dentry)->offset);
+	     dentry, inode, ceph_dentry(dentry)->offset);
 
 	/* always trust cached snapped dentries, snapdir dentry */
 	if (ceph_snap(dir) != CEPH_NOSNAP) {
 		dout("d_revalidate %p '%pd' inode %p is SNAPPED\n", dentry,
-		     dentry, d_inode(dentry));
+		     dentry, inode);
 		valid = 1;
-	} else if (d_really_is_positive(dentry) &&
-		   ceph_snap(d_inode(dentry)) == CEPH_SNAPDIR) {
+	} else if (inode && ceph_snap(inode) == CEPH_SNAPDIR) {
 		valid = 1;
 	} else {
 		valid = dentry_lease_is_valid(dentry, flags);
 		if (valid == -ECHILD)
 			return valid;
 		if (valid || dir_lease_is_valid(dir, dentry)) {
-			if (d_really_is_positive(dentry))
-				valid = ceph_is_any_caps(d_inode(dentry));
+			if (inode)
+				valid = ceph_is_any_caps(inode);
 			else
 				valid = 1;
 		}
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index d277f71abe0b..bd77adb64bfd 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -462,6 +462,9 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		err = ceph_security_init_secctx(dentry, mode, &as_ctx);
 		if (err < 0)
 			goto out_ctx;
+	} else if (!d_in_lookup(dentry)) {
+		/* If it's not being looked up, it's negative */
+		return -ENOENT;
 	}
 
 	/* do the open */
@@ -1956,10 +1959,18 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
 		return -EOPNOTSUPP;
 
+	/*
+	 * Striped file layouts require that we copy partial objects, but the
+	 * OSD copy-from operation only supports full-object copies.  Limit
+	 * this to non-striped file layouts for now.
+	 */
 	if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) ||
-	    (src_ci->i_layout.stripe_count != dst_ci->i_layout.stripe_count) ||
-	    (src_ci->i_layout.object_size != dst_ci->i_layout.object_size))
+	    (src_ci->i_layout.stripe_count != 1) ||
+	    (dst_ci->i_layout.stripe_count != 1) ||
+	    (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) {
+		dout("Invalid src/dst files layout\n");
 		return -EOPNOTSUPP;
+	}
 
 	if (len < src_ci->i_layout.object_size)
 		return -EOPNOTSUPP; /* no remote copy will be done */
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 9f135624ae47..c07407586ce8 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1434,6 +1434,7 @@ retry_lookup:
 		dout(" final dn %p\n", dn);
 	} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
 		    req->r_op == CEPH_MDS_OP_MKSNAP) &&
+	           test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
 		   !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 		struct inode *dir = req->r_parent;
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index edfd643a8205..b47f43fc2d68 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -268,6 +268,7 @@ static int parse_fsopt_token(char *c, void *private)
 		}
 		break;
 	case Opt_fscache_uniq:
+#ifdef CONFIG_CEPH_FSCACHE
 		kfree(fsopt->fscache_uniq);
 		fsopt->fscache_uniq = kstrndup(argstr[0].from,
 					       argstr[0].to-argstr[0].from,
@@ -276,7 +277,10 @@ static int parse_fsopt_token(char *c, void *private)
 			return -ENOMEM;
 		fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
 		break;
-		/* misc */
+#else
+		pr_err("fscache support is disabled\n");
+		return -EINVAL;
+#endif
 	case Opt_wsize:
 		if (intval < (int)PAGE_SIZE || intval > CEPH_MAX_WRITE_SIZE)
 			return -EINVAL;
@@ -353,10 +357,15 @@ static int parse_fsopt_token(char *c, void *private)
 		fsopt->flags &= ~CEPH_MOUNT_OPT_INO32;
 		break;
 	case Opt_fscache:
+#ifdef CONFIG_CEPH_FSCACHE
 		fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
 		kfree(fsopt->fscache_uniq);
 		fsopt->fscache_uniq = NULL;
 		break;
+#else
+		pr_err("fscache support is disabled\n");
+		return -EINVAL;
+#endif
 	case Opt_nofscache:
 		fsopt->flags &= ~CEPH_MOUNT_OPT_FSCACHE;
 		kfree(fsopt->fscache_uniq);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c049c7b3aa87..1a135d1b85bd 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -169,7 +169,13 @@ cifs_read_super(struct super_block *sb)
 	else
 		sb->s_maxbytes = MAX_NON_LFS;
 
-	/* Some very old servers like DOS and OS/2 used 2 second granularity */
+	/*
+	 * Some very old servers like DOS and OS/2 used 2 second granularity
+	 * (while all current servers use 100ns granularity - see MS-DTYP)
+	 * but 1 second is the maximum allowed granularity for the VFS
+	 * so for old servers set time granularity to 1 second while for
+	 * everything else (current servers) set it to 100ns.
+	 */
 	if ((tcon->ses->server->vals->protocol_id == SMB10_PROT_ID) &&
 	    ((tcon->ses->capabilities &
 	      tcon->ses->server->vals->cap_nt_find) == 0) &&
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 50dfd9049370..d78bfcc19156 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1391,6 +1391,11 @@ void cifsFileInfo_put(struct cifsFileInfo *cifs_file);
 struct cifsInodeInfo {
 	bool can_cache_brlcks;
 	struct list_head llist;	/* locks helb by this inode */
+	/*
+	 * NOTE: Some code paths call down_read(lock_sem) twice, so
+	 * we must always use use cifs_down_write() instead of down_write()
+	 * for this semaphore to avoid deadlocks.
+	 */
 	struct rw_semaphore lock_sem;	/* protect the fields above */
 	/* BB add in lists for dirty pages i.e. write caching info for oplock */
 	struct list_head openFileList;
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index e53e9f62b87b..fe597d3d5208 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -170,6 +170,7 @@ extern int cifs_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int cifs_push_mandatory_locks(struct cifsFileInfo *cfile);
 
+extern void cifs_down_write(struct rw_semaphore *sem);
 extern struct cifsFileInfo *cifs_new_fileinfo(struct cifs_fid *fid,
 					      struct file *file,
 					      struct tcon_link *tlink,
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index a64dfa95a925..ccaa8bad336f 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -564,9 +564,11 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	spin_lock(&GlobalMid_Lock);
 	list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
+		kref_get(&mid_entry->refcount);
 		if (mid_entry->mid_state == MID_REQUEST_SUBMITTED)
 			mid_entry->mid_state = MID_RETRY_NEEDED;
 		list_move(&mid_entry->qhead, &retry_list);
+		mid_entry->mid_flags |= MID_DELETED;
 	}
 	spin_unlock(&GlobalMid_Lock);
 	mutex_unlock(&server->srv_mutex);
@@ -576,6 +578,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
 		list_del_init(&mid_entry->qhead);
 		mid_entry->callback(mid_entry);
+		cifs_mid_q_entry_release(mid_entry);
 	}
 
 	if (cifs_rdma_enabled(server)) {
@@ -895,8 +898,10 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
 	if (mid->mid_flags & MID_DELETED)
 		printk_once(KERN_WARNING
 			    "trying to dequeue a deleted mid\n");
-	else
+	else {
 		list_del_init(&mid->qhead);
+		mid->mid_flags |= MID_DELETED;
+	}
 	spin_unlock(&GlobalMid_Lock);
 }
 
@@ -966,8 +971,10 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 		list_for_each_safe(tmp, tmp2, &server->pending_mid_q) {
 			mid_entry = list_entry(tmp, struct mid_q_entry, qhead);
 			cifs_dbg(FYI, "Clearing mid 0x%llx\n", mid_entry->mid);
+			kref_get(&mid_entry->refcount);
 			mid_entry->mid_state = MID_SHUTDOWN;
 			list_move(&mid_entry->qhead, &dispose_list);
+			mid_entry->mid_flags |= MID_DELETED;
 		}
 		spin_unlock(&GlobalMid_Lock);
 
@@ -977,6 +984,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server)
 			cifs_dbg(FYI, "Callback mid 0x%llx\n", mid_entry->mid);
 			list_del_init(&mid_entry->qhead);
 			mid_entry->callback(mid_entry);
+			cifs_mid_q_entry_release(mid_entry);
 		}
 		/* 1/8th of sec is more than enough time for them to exit */
 		msleep(125);
@@ -3882,8 +3890,12 @@ generic_ip_connect(struct TCP_Server_Info *server)
 
 	rc = socket->ops->connect(socket, saddr, slen,
 				  server->noblockcnt ? O_NONBLOCK : 0);
-
-	if (rc == -EINPROGRESS)
+	/*
+	 * When mounting SMB root file systems, we do not want to block in
+	 * connect. Otherwise bail out and then let cifs_reconnect() perform
+	 * reconnect failover - if possible.
+	 */
+	if (server->noblockcnt && rc == -EINPROGRESS)
 		rc = 0;
 	if (rc < 0) {
 		cifs_dbg(FYI, "Error %d connecting to server\n", rc);
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 5ad15de2bb4f..fa7b0fa72bb3 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -281,6 +281,13 @@ cifs_has_mand_locks(struct cifsInodeInfo *cinode)
 	return has_locks;
 }
 
+void
+cifs_down_write(struct rw_semaphore *sem)
+{
+	while (!down_write_trylock(sem))
+		msleep(10);
+}
+
 struct cifsFileInfo *
 cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 		  struct tcon_link *tlink, __u32 oplock)
@@ -306,7 +313,7 @@ cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
 	INIT_LIST_HEAD(&fdlocks->locks);
 	fdlocks->cfile = cfile;
 	cfile->llist = fdlocks;
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	list_add(&fdlocks->llist, &cinode->llist);
 	up_write(&cinode->lock_sem);
 
@@ -405,10 +412,11 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
 	bool oplock_break_cancelled;
 
 	spin_lock(&tcon->open_file_lock);
-
+	spin_lock(&cifsi->open_file_lock);
 	spin_lock(&cifs_file->file_info_lock);
 	if (--cifs_file->count > 0) {
 		spin_unlock(&cifs_file->file_info_lock);
+		spin_unlock(&cifsi->open_file_lock);
 		spin_unlock(&tcon->open_file_lock);
 		return;
 	}
@@ -421,9 +429,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
 	cifs_add_pending_open_locked(&fid, cifs_file->tlink, &open);
 
 	/* remove it from the lists */
-	spin_lock(&cifsi->open_file_lock);
 	list_del(&cifs_file->flist);
-	spin_unlock(&cifsi->open_file_lock);
 	list_del(&cifs_file->tlist);
 	atomic_dec(&tcon->num_local_opens);
 
@@ -440,6 +446,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
 		cifs_set_oplock_level(cifsi, 0);
 	}
 
+	spin_unlock(&cifsi->open_file_lock);
 	spin_unlock(&tcon->open_file_lock);
 
 	oplock_break_cancelled = wait_oplock_handler ?
@@ -464,7 +471,7 @@ void _cifsFileInfo_put(struct cifsFileInfo *cifs_file, bool wait_oplock_handler)
 	 * Delete any outstanding lock records. We'll lose them when the file
 	 * is closed anyway.
 	 */
-	down_write(&cifsi->lock_sem);
+	cifs_down_write(&cifsi->lock_sem);
 	list_for_each_entry_safe(li, tmp, &cifs_file->llist->locks, llist) {
 		list_del(&li->llist);
 		cifs_del_lock_waiters(li);
@@ -1027,7 +1034,7 @@ static void
 cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
 {
 	struct cifsInodeInfo *cinode = CIFS_I(d_inode(cfile->dentry));
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	list_add_tail(&lock->llist, &cfile->llist->locks);
 	up_write(&cinode->lock_sem);
 }
@@ -1049,7 +1056,7 @@ cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
 
 try_again:
 	exist = false;
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 
 	exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
 					lock->type, lock->flags, &conf_lock,
@@ -1072,7 +1079,7 @@ try_again:
 					(lock->blist.next == &lock->blist));
 		if (!rc)
 			goto try_again;
-		down_write(&cinode->lock_sem);
+		cifs_down_write(&cinode->lock_sem);
 		list_del_init(&lock->blist);
 	}
 
@@ -1125,7 +1132,7 @@ cifs_posix_lock_set(struct file *file, struct file_lock *flock)
 		return rc;
 
 try_again:
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	if (!cinode->can_cache_brlcks) {
 		up_write(&cinode->lock_sem);
 		return rc;
@@ -1331,7 +1338,7 @@ cifs_push_locks(struct cifsFileInfo *cfile)
 	int rc = 0;
 
 	/* we are going to update can_cache_brlcks here - need a write access */
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	if (!cinode->can_cache_brlcks) {
 		up_write(&cinode->lock_sem);
 		return rc;
@@ -1522,7 +1529,7 @@ cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 	if (!buf)
 		return -ENOMEM;
 
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	for (i = 0; i < 2; i++) {
 		cur = buf;
 		num = 0;
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 5dcc95b38310..df9377828e2f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2475,9 +2475,9 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs)
 			rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid);
 			cifsFileInfo_put(wfile);
 			if (rc)
-				return rc;
+				goto cifs_setattr_exit;
 		} else if (rc != -EBADF)
-			return rc;
+			goto cifs_setattr_exit;
 		else
 			rc = 0;
 	}
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index b7421a096319..514810694c0f 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -171,6 +171,9 @@ cifs_get_next_mid(struct TCP_Server_Info *server)
 	/* we do not want to loop forever */
 	last_mid = cur_mid;
 	cur_mid++;
+	/* avoid 0xFFFF MID */
+	if (cur_mid == 0xffff)
+		cur_mid++;
 
 	/*
 	 * This nested loop looks more expensive than it is.
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index e6a1fc72018f..8b0b512c5792 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -145,7 +145,7 @@ smb2_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
 
 	cur = buf;
 
-	down_write(&cinode->lock_sem);
+	cifs_down_write(&cinode->lock_sem);
 	list_for_each_entry_safe(li, tmp, &cfile->llist->locks, llist) {
 		if (flock->fl_start > li->offset ||
 		    (flock->fl_start + length) <
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 4c0922596467..cd55af9b7cc5 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -4084,6 +4084,7 @@ free_pages:
 
 	kfree(dw->ppages);
 	cifs_small_buf_release(dw->buf);
+	kfree(dw);
 }
 
 
@@ -4157,7 +4158,7 @@ receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid,
 		dw->server = server;
 		dw->ppages = pages;
 		dw->len = len;
-		queue_work(cifsiod_wq, &dw->decrypt);
+		queue_work(decrypt_wq, &dw->decrypt);
 		*num_mids = 0; /* worker thread takes care of finding mid */
 		return -1;
 	}
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index ea735d59c36e..0abfde6d0b05 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -838,6 +838,7 @@ struct create_durable_handle_reconnect_v2 {
 	struct create_context ccontext;
 	__u8   Name[8];
 	struct durable_reconnect_context_v2 dcontext;
+	__u8   Pad[4];
 } __packed;
 
 /* See MS-SMB2 2.2.13.2.5 */
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 308ad0f495e1..ca3de62688d6 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -86,22 +86,8 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 
 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)
-{
+	struct mid_q_entry *midEntry =
+			container_of(refcount, struct mid_q_entry, refcount);
 #ifdef CONFIG_CIFS_STATS2
 	__le16 command = midEntry->server->vals->lock_cmd;
 	__u16 smb_cmd = le16_to_cpu(midEntry->command);
@@ -166,6 +152,19 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 		}
 	}
 #endif
+
+	mempool_free(midEntry, 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)
+{
 	cifs_mid_q_entry_release(midEntry);
 }
 
@@ -173,8 +172,10 @@ void
 cifs_delete_mid(struct mid_q_entry *mid)
 {
 	spin_lock(&GlobalMid_Lock);
-	list_del_init(&mid->qhead);
-	mid->mid_flags |= MID_DELETED;
+	if (!(mid->mid_flags & MID_DELETED)) {
+		list_del_init(&mid->qhead);
+		mid->mid_flags |= MID_DELETED;
+	}
 	spin_unlock(&GlobalMid_Lock);
 
 	DeleteMidQEntry(mid);
@@ -872,7 +873,10 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 		rc = -EHOSTDOWN;
 		break;
 	default:
-		list_del_init(&mid->qhead);
+		if (!(mid->mid_flags & MID_DELETED)) {
+			list_del_init(&mid->qhead);
+			mid->mid_flags |= MID_DELETED;
+		}
 		cifs_server_dbg(VFS, "%s: invalid mid state mid=%llu state=%d\n",
 			 __func__, mid->mid, mid->mid_state);
 		rc = -EIO;
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index dc5dbf6a81d7..cb61467478ca 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -101,7 +101,7 @@ static int create_link(struct config_item *parent_item,
 	}
 	target_sd->s_links++;
 	spin_unlock(&configfs_dirent_lock);
-	ret = configfs_get_target_path(item, item, body);
+	ret = configfs_get_target_path(parent_item, item, body);
 	if (!ret)
 		ret = configfs_create_link(target_sd, parent_item->ci_dentry,
 					   dentry, body);
diff --git a/fs/dax.c b/fs/dax.c
index 6bf81f931de3..2cc43cd914eb 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -220,10 +220,11 @@ static void *get_unlocked_entry(struct xa_state *xas, unsigned int order)
 
 	for (;;) {
 		entry = xas_find_conflict(xas);
+		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)))
+			return entry;
 		if (dax_entry_order(entry) < order)
 			return XA_RETRY_ENTRY;
-		if (!entry || WARN_ON_ONCE(!xa_is_value(entry)) ||
-				!dax_is_locked(entry))
+		if (!dax_is_locked(entry))
 			return entry;
 
 		wq = dax_entry_waitqueue(xas, entry, &ewait.key);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 8461a6322039..335607b8c5c0 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -576,10 +576,13 @@ void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
 	spin_unlock(&inode->i_lock);
 
 	/*
-	 * A dying wb indicates that the memcg-blkcg mapping has changed
-	 * and a new wb is already serving the memcg.  Switch immediately.
+	 * A dying wb indicates that either the blkcg associated with the
+	 * memcg changed or the associated memcg is dying.  In the first
+	 * case, a replacement wb should already be available and we should
+	 * refresh the wb immediately.  In the second case, trying to
+	 * refresh will keep failing.
 	 */
-	if (unlikely(wb_dying(wbc->wb)))
+	if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css)))
 		inode_switch_wbs(inode, wbc->wb_id);
 }
 EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode);
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 6419a2b3510d..3e8cebfb59b7 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -5,6 +5,7 @@
 
 obj-$(CONFIG_FUSE_FS) += fuse.o
 obj-$(CONFIG_CUSE) += cuse.o
-obj-$(CONFIG_VIRTIO_FS) += virtio_fs.o
+obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
 
 fuse-objs := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o
+virtiofs-y += virtio_fs.o
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index dadd617d826c..ed1abc9e33cf 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -276,10 +276,12 @@ static void flush_bg_queue(struct fuse_conn *fc)
 void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req)
 {
 	struct fuse_iqueue *fiq = &fc->iq;
-	bool async = req->args->end;
+	bool async;
 
 	if (test_and_set_bit(FR_FINISHED, &req->flags))
 		goto put_request;
+
+	async = req->args->end;
 	/*
 	 * test_and_set_bit() implies smp_mb() between bit
 	 * changing and below intr_entry check. Pairs with
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d572c900bb0f..54d638f9ba1c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -405,7 +405,8 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
 	else
 		fuse_invalidate_entry_cache(entry);
 
-	fuse_advise_use_readdirplus(dir);
+	if (inode)
+		fuse_advise_use_readdirplus(dir);
 	return newent;
 
  out_iput:
@@ -1521,6 +1522,19 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
 		is_truncate = true;
 	}
 
+	/* Flush dirty data/metadata before non-truncate SETATTR */
+	if (is_wb && S_ISREG(inode->i_mode) &&
+	    attr->ia_valid &
+			(ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_MTIME_SET |
+			 ATTR_TIMES_SET)) {
+		err = write_inode_now(inode, true);
+		if (err)
+			return err;
+
+		fuse_set_nowrite(inode);
+		fuse_release_nowrite(inode);
+	}
+
 	if (is_truncate) {
 		fuse_set_nowrite(inode);
 		set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 0f0225686aee..db48a5cf8620 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -217,7 +217,7 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 {
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	int err;
-	bool lock_inode = (file->f_flags & O_TRUNC) &&
+	bool is_wb_truncate = (file->f_flags & O_TRUNC) &&
 			  fc->atomic_o_trunc &&
 			  fc->writeback_cache;
 
@@ -225,16 +225,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
 	if (err)
 		return err;
 
-	if (lock_inode)
+	if (is_wb_truncate) {
 		inode_lock(inode);
+		fuse_set_nowrite(inode);
+	}
 
 	err = fuse_do_open(fc, get_node_id(inode), file, isdir);
 
 	if (!err)
 		fuse_finish_open(inode, file);
 
-	if (lock_inode)
+	if (is_wb_truncate) {
+		fuse_release_nowrite(inode);
 		inode_unlock(inode);
+	}
 
 	return err;
 }
@@ -1997,7 +2001,7 @@ static int fuse_writepages_fill(struct page *page,
 
 	if (!data->ff) {
 		err = -EIO;
-		data->ff = fuse_write_file_get(fc, get_fuse_inode(inode));
+		data->ff = fuse_write_file_get(fc, fi);
 		if (!data->ff)
 			goto out_unlock;
 	}
@@ -2042,8 +2046,6 @@ static int fuse_writepages_fill(struct page *page,
 	 * under writeback, so we can release the page lock.
 	 */
 	if (data->wpa == NULL) {
-		struct fuse_inode *fi = get_fuse_inode(inode);
-
 		err = -ENOMEM;
 		wpa = fuse_writepage_args_alloc();
 		if (!wpa) {
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 956aeaf961ae..d148188cfca4 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -479,6 +479,7 @@ struct fuse_fs_context {
 	bool destroy:1;
 	bool no_control:1;
 	bool no_force_umount:1;
+	bool no_mount_options:1;
 	unsigned int max_read;
 	unsigned int blksize;
 	const char *subtype;
@@ -713,6 +714,9 @@ struct fuse_conn {
 	/** Do not allow MNT_FORCE umount */
 	unsigned int no_force_umount:1;
 
+	/* Do not show mount options */
+	unsigned int no_mount_options:1;
+
 	/** The number of requests waiting for completion */
 	atomic_t num_waiting;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index e040e2a2b621..16aec32f7f3d 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -558,6 +558,9 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
 	struct super_block *sb = root->d_sb;
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
 
+	if (fc->no_mount_options)
+		return 0;
+
 	seq_printf(m, ",user_id=%u", from_kuid_munged(fc->user_ns, fc->user_id));
 	seq_printf(m, ",group_id=%u", from_kgid_munged(fc->user_ns, fc->group_id));
 	if (fc->default_permissions)
@@ -1180,6 +1183,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 	fc->destroy = ctx->destroy;
 	fc->no_control = ctx->no_control;
 	fc->no_force_umount = ctx->no_force_umount;
+	fc->no_mount_options = ctx->no_mount_options;
 
 	err = -ENOMEM;
 	root = fuse_get_root_inode(sb, ctx->rootmode);
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 6af3f131e468..a5c86048b96e 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -30,6 +30,7 @@ struct virtio_fs_vq {
 	struct virtqueue *vq;     /* protected by ->lock */
 	struct work_struct done_work;
 	struct list_head queued_reqs;
+	struct list_head end_reqs;	/* End these requests */
 	struct delayed_work dispatch_work;
 	struct fuse_dev *fud;
 	bool connected;
@@ -54,6 +55,9 @@ struct virtio_fs_forget {
 	struct list_head list;
 };
 
+static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
+				 struct fuse_req *req, bool in_flight);
+
 static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
 {
 	struct virtio_fs *fs = vq->vdev->priv;
@@ -66,6 +70,19 @@ static inline struct fuse_pqueue *vq_to_fpq(struct virtqueue *vq)
 	return &vq_to_fsvq(vq)->fud->pq;
 }
 
+/* Should be called with fsvq->lock held. */
+static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+	fsvq->in_flight++;
+}
+
+/* Should be called with fsvq->lock held. */
+static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
+{
+	WARN_ON(fsvq->in_flight <= 0);
+	fsvq->in_flight--;
+}
+
 static void release_virtio_fs_obj(struct kref *ref)
 {
 	struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
@@ -109,22 +126,6 @@ static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
 	flush_delayed_work(&fsvq->dispatch_work);
 }
 
-static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq)
-{
-	struct virtio_fs_forget *forget;
-
-	spin_lock(&fsvq->lock);
-	while (1) {
-		forget = list_first_entry_or_null(&fsvq->queued_reqs,
-						struct virtio_fs_forget, list);
-		if (!forget)
-			break;
-		list_del(&forget->list);
-		kfree(forget);
-	}
-	spin_unlock(&fsvq->lock);
-}
-
 static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
 {
 	struct virtio_fs_vq *fsvq;
@@ -132,9 +133,6 @@ static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
 
 	for (i = 0; i < fs->nvqs; i++) {
 		fsvq = &fs->vqs[i];
-		if (i == VQ_HIPRIO)
-			drain_hiprio_queued_reqs(fsvq);
-
 		virtio_fs_drain_queue(fsvq);
 	}
 }
@@ -253,14 +251,66 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
 
 		while ((req = virtqueue_get_buf(vq, &len)) != NULL) {
 			kfree(req);
-			fsvq->in_flight--;
+			dec_in_flight_req(fsvq);
 		}
 	} while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
 	spin_unlock(&fsvq->lock);
 }
 
-static void virtio_fs_dummy_dispatch_work(struct work_struct *work)
+static void virtio_fs_request_dispatch_work(struct work_struct *work)
 {
+	struct fuse_req *req;
+	struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq,
+						 dispatch_work.work);
+	struct fuse_conn *fc = fsvq->fud->fc;
+	int ret;
+
+	pr_debug("virtio-fs: worker %s called.\n", __func__);
+	while (1) {
+		spin_lock(&fsvq->lock);
+		req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req,
+					       list);
+		if (!req) {
+			spin_unlock(&fsvq->lock);
+			break;
+		}
+
+		list_del_init(&req->list);
+		spin_unlock(&fsvq->lock);
+		fuse_request_end(fc, req);
+	}
+
+	/* Dispatch pending requests */
+	while (1) {
+		spin_lock(&fsvq->lock);
+		req = list_first_entry_or_null(&fsvq->queued_reqs,
+					       struct fuse_req, list);
+		if (!req) {
+			spin_unlock(&fsvq->lock);
+			return;
+		}
+		list_del_init(&req->list);
+		spin_unlock(&fsvq->lock);
+
+		ret = virtio_fs_enqueue_req(fsvq, req, true);
+		if (ret < 0) {
+			if (ret == -ENOMEM || ret == -ENOSPC) {
+				spin_lock(&fsvq->lock);
+				list_add_tail(&req->list, &fsvq->queued_reqs);
+				schedule_delayed_work(&fsvq->dispatch_work,
+						      msecs_to_jiffies(1));
+				spin_unlock(&fsvq->lock);
+				return;
+			}
+			req->out.h.error = ret;
+			spin_lock(&fsvq->lock);
+			dec_in_flight_req(fsvq);
+			spin_unlock(&fsvq->lock);
+			pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n",
+			       ret);
+			fuse_request_end(fc, req);
+		}
+	}
 }
 
 static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
@@ -286,6 +336,7 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
 
 		list_del(&forget->list);
 		if (!fsvq->connected) {
+			dec_in_flight_req(fsvq);
 			spin_unlock(&fsvq->lock);
 			kfree(forget);
 			continue;
@@ -307,13 +358,13 @@ static void virtio_fs_hiprio_dispatch_work(struct work_struct *work)
 			} else {
 				pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
 					 ret);
+				dec_in_flight_req(fsvq);
 				kfree(forget);
 			}
 			spin_unlock(&fsvq->lock);
 			return;
 		}
 
-		fsvq->in_flight++;
 		notify = virtqueue_kick_prepare(vq);
 		spin_unlock(&fsvq->lock);
 
@@ -452,7 +503,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
 
 		fuse_request_end(fc, req);
 		spin_lock(&fsvq->lock);
-		fsvq->in_flight--;
+		dec_in_flight_req(fsvq);
 		spin_unlock(&fsvq->lock);
 	}
 }
@@ -502,6 +553,7 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 	names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name;
 	INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work);
 	INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs);
+	INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs);
 	INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work,
 			virtio_fs_hiprio_dispatch_work);
 	spin_lock_init(&fs->vqs[VQ_HIPRIO].lock);
@@ -511,8 +563,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
 		spin_lock_init(&fs->vqs[i].lock);
 		INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work);
 		INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work,
-					virtio_fs_dummy_dispatch_work);
+				  virtio_fs_request_dispatch_work);
 		INIT_LIST_HEAD(&fs->vqs[i].queued_reqs);
+		INIT_LIST_HEAD(&fs->vqs[i].end_reqs);
 		snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name),
 			 "requests.%u", i - VQ_REQUEST);
 		callbacks[i] = virtio_fs_vq_done;
@@ -708,6 +761,7 @@ __releases(fiq->lock)
 			list_add_tail(&forget->list, &fsvq->queued_reqs);
 			schedule_delayed_work(&fsvq->dispatch_work,
 					msecs_to_jiffies(1));
+			inc_in_flight_req(fsvq);
 		} else {
 			pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n",
 				 ret);
@@ -717,7 +771,7 @@ __releases(fiq->lock)
 		goto out;
 	}
 
-	fsvq->in_flight++;
+	inc_in_flight_req(fsvq);
 	notify = virtqueue_kick_prepare(vq);
 
 	spin_unlock(&fsvq->lock);
@@ -819,7 +873,7 @@ static unsigned int sg_init_fuse_args(struct scatterlist *sg,
 
 /* Add a request to a virtqueue and kick the device */
 static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
-				 struct fuse_req *req)
+				 struct fuse_req *req, bool in_flight)
 {
 	/* requests need at least 4 elements */
 	struct scatterlist *stack_sgs[6];
@@ -835,6 +889,7 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 	unsigned int i;
 	int ret;
 	bool notify;
+	struct fuse_pqueue *fpq;
 
 	/* Does the sglist fit on the stack? */
 	total_sgs = sg_count_fuse_req(req);
@@ -889,7 +944,17 @@ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
 		goto out;
 	}
 
-	fsvq->in_flight++;
+	/* Request successfully sent. */
+	fpq = &fsvq->fud->pq;
+	spin_lock(&fpq->lock);
+	list_add_tail(&req->list, fpq->processing);
+	spin_unlock(&fpq->lock);
+	set_bit(FR_SENT, &req->flags);
+	/* matches barrier in request_wait_answer() */
+	smp_mb__after_atomic();
+
+	if (!in_flight)
+		inc_in_flight_req(fsvq);
 	notify = virtqueue_kick_prepare(vq);
 
 	spin_unlock(&fsvq->lock);
@@ -915,9 +980,8 @@ __releases(fiq->lock)
 {
 	unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */
 	struct virtio_fs *fs;
-	struct fuse_conn *fc;
 	struct fuse_req *req;
-	struct fuse_pqueue *fpq;
+	struct virtio_fs_vq *fsvq;
 	int ret;
 
 	WARN_ON(list_empty(&fiq->pending));
@@ -928,44 +992,36 @@ __releases(fiq->lock)
 	spin_unlock(&fiq->lock);
 
 	fs = fiq->priv;
-	fc = fs->vqs[queue_id].fud->fc;
 
 	pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n",
 		  __func__, req->in.h.opcode, req->in.h.unique,
 		 req->in.h.nodeid, req->in.h.len,
 		 fuse_len_args(req->args->out_numargs, req->args->out_args));
 
-	fpq = &fs->vqs[queue_id].fud->pq;
-	spin_lock(&fpq->lock);
-	if (!fpq->connected) {
-		spin_unlock(&fpq->lock);
-		req->out.h.error = -ENODEV;
-		pr_err("virtio-fs: %s disconnected\n", __func__);
-		fuse_request_end(fc, req);
-		return;
-	}
-	list_add_tail(&req->list, fpq->processing);
-	spin_unlock(&fpq->lock);
-	set_bit(FR_SENT, &req->flags);
-	/* matches barrier in request_wait_answer() */
-	smp_mb__after_atomic();
-
-retry:
-	ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req);
+	fsvq = &fs->vqs[queue_id];
+	ret = virtio_fs_enqueue_req(fsvq, req, false);
 	if (ret < 0) {
 		if (ret == -ENOMEM || ret == -ENOSPC) {
-			/* Virtqueue full. Retry submission */
-			/* TODO use completion instead of timeout */
-			usleep_range(20, 30);
-			goto retry;
+			/*
+			 * Virtqueue full. Retry submission from worker
+			 * context as we might be holding fc->bg_lock.
+			 */
+			spin_lock(&fsvq->lock);
+			list_add_tail(&req->list, &fsvq->queued_reqs);
+			inc_in_flight_req(fsvq);
+			schedule_delayed_work(&fsvq->dispatch_work,
+						msecs_to_jiffies(1));
+			spin_unlock(&fsvq->lock);
+			return;
 		}
 		req->out.h.error = ret;
 		pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret);
-		spin_lock(&fpq->lock);
-		clear_bit(FR_SENT, &req->flags);
-		list_del_init(&req->list);
-		spin_unlock(&fpq->lock);
-		fuse_request_end(fc, req);
+
+		/* Can't end request in submission context. Use a worker */
+		spin_lock(&fsvq->lock);
+		list_add_tail(&req->list, &fsvq->end_reqs);
+		schedule_delayed_work(&fsvq->dispatch_work, 0);
+		spin_unlock(&fsvq->lock);
 		return;
 	}
 }
@@ -992,6 +1048,7 @@ static int virtio_fs_fill_super(struct super_block *sb)
 		.destroy = true,
 		.no_control = true,
 		.no_force_umount = true,
+		.no_mount_options = true,
 	};
 
 	mutex_lock(&virtio_fs_mutex);
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 681b44682b0d..18daf494abab 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1540,17 +1540,23 @@ static int gfs2_init_fs_context(struct fs_context *fc)
 {
 	struct gfs2_args *args;
 
-	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	args = kmalloc(sizeof(*args), GFP_KERNEL);
 	if (args == NULL)
 		return -ENOMEM;
 
-	args->ar_quota = GFS2_QUOTA_DEFAULT;
-	args->ar_data = GFS2_DATA_DEFAULT;
-	args->ar_commit = 30;
-	args->ar_statfs_quantum = 30;
-	args->ar_quota_quantum = 60;
-	args->ar_errors = GFS2_ERRORS_DEFAULT;
+	if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+		struct gfs2_sbd *sdp = fc->root->d_sb->s_fs_info;
 
+		*args = sdp->sd_args;
+	} else {
+		memset(args, 0, sizeof(*args));
+		args->ar_quota = GFS2_QUOTA_DEFAULT;
+		args->ar_data = GFS2_DATA_DEFAULT;
+		args->ar_commit = 30;
+		args->ar_statfs_quantum = 30;
+		args->ar_quota_quantum = 60;
+		args->ar_errors = GFS2_ERRORS_DEFAULT;
+	}
 	fc->fs_private = args;
 	fc->ops = &gfs2_context_ops;
 	return 0;
@@ -1600,6 +1606,7 @@ static int gfs2_meta_get_tree(struct fs_context *fc)
 }
 
 static const struct fs_context_operations gfs2_meta_context_ops = {
+	.free        = gfs2_fc_free,
 	.get_tree    = gfs2_meta_get_tree,
 };
 
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 67dbe0201e0d..f9a38998f2fc 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -197,6 +197,7 @@ struct io_ring_ctx {
 		unsigned		sq_entries;
 		unsigned		sq_mask;
 		unsigned		sq_thread_idle;
+		unsigned		cached_sq_dropped;
 		struct io_uring_sqe	*sq_sqes;
 
 		struct list_head	defer_list;
@@ -212,6 +213,7 @@ struct io_ring_ctx {
 
 	struct {
 		unsigned		cached_cq_tail;
+		atomic_t		cached_cq_overflow;
 		unsigned		cq_entries;
 		unsigned		cq_mask;
 		struct wait_queue_head	cq_wait;
@@ -420,7 +422,8 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
 static inline bool __io_sequence_defer(struct io_ring_ctx *ctx,
 				       struct io_kiocb *req)
 {
-	return req->sequence != ctx->cached_cq_tail + ctx->rings->sq_dropped;
+	return req->sequence != ctx->cached_cq_tail + ctx->cached_sq_dropped
+					+ atomic_read(&ctx->cached_cq_overflow);
 }
 
 static inline bool io_sequence_defer(struct io_ring_ctx *ctx,
@@ -567,9 +570,8 @@ static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, 0);
 	} else {
-		unsigned overflow = READ_ONCE(ctx->rings->cq_overflow);
-
-		WRITE_ONCE(ctx->rings->cq_overflow, overflow + 1);
+		WRITE_ONCE(ctx->rings->cq_overflow,
+				atomic_inc_return(&ctx->cached_cq_overflow));
 	}
 }
 
@@ -735,6 +737,14 @@ static unsigned io_cqring_events(struct io_rings *rings)
 	return READ_ONCE(rings->cq.tail) - READ_ONCE(rings->cq.head);
 }
 
+static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+{
+	struct io_rings *rings = ctx->rings;
+
+	/* make sure SQ entry isn't read before tail */
+	return smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
+}
+
 /*
  * Find and free completed poll iocbs
  */
@@ -864,19 +874,11 @@ static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
 	mutex_unlock(&ctx->uring_lock);
 }
 
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
-			   long min)
+static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+			    long min)
 {
-	int iters, ret = 0;
+	int iters = 0, ret = 0;
 
-	/*
-	 * We disallow the app entering submit/complete with polling, but we
-	 * still need to lock the ring to prevent racing with polled issue
-	 * that got punted to a workqueue.
-	 */
-	mutex_lock(&ctx->uring_lock);
-
-	iters = 0;
 	do {
 		int tmin = 0;
 
@@ -912,6 +914,21 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
 		ret = 0;
 	} while (min && !*nr_events && !need_resched());
 
+	return ret;
+}
+
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+			   long min)
+{
+	int ret;
+
+	/*
+	 * We disallow the app entering submit/complete with polling, but we
+	 * still need to lock the ring to prevent racing with polled issue
+	 * that got punted to a workqueue.
+	 */
+	mutex_lock(&ctx->uring_lock);
+	ret = __io_iopoll_check(ctx, nr_events, min);
 	mutex_unlock(&ctx->uring_lock);
 	return ret;
 }
@@ -1107,6 +1124,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct sqe_submit *s,
 
 		kiocb->ki_flags |= IOCB_HIPRI;
 		kiocb->ki_complete = io_complete_rw_iopoll;
+		req->result = 0;
 	} else {
 		if (kiocb->ki_flags & IOCB_HIPRI)
 			return -EINVAL;
@@ -1877,7 +1895,7 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 {
 	struct io_ring_ctx *ctx;
-	struct io_kiocb *req;
+	struct io_kiocb *req, *prev;
 	unsigned long flags;
 
 	req = container_of(timer, struct io_kiocb, timeout.timer);
@@ -1885,6 +1903,15 @@ static enum hrtimer_restart io_timeout_fn(struct hrtimer *timer)
 	atomic_inc(&ctx->cq_timeouts);
 
 	spin_lock_irqsave(&ctx->completion_lock, flags);
+	/*
+	 * Adjust the reqs sequence before the current one because it
+	 * will consume a slot in the cq_ring and the the cq_tail pointer
+	 * will be increased, otherwise other timeout reqs may return in
+	 * advance without waiting for enough wait_nr.
+	 */
+	prev = req;
+	list_for_each_entry_continue_reverse(prev, &ctx->timeout_list, list)
+		prev->sequence++;
 	list_del(&req->list);
 
 	io_cqring_fill_event(ctx, req->user_data, -ETIME);
@@ -1903,6 +1930,7 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_ring_ctx *ctx = req->ctx;
 	struct list_head *entry;
 	struct timespec64 ts;
+	unsigned span = 0;
 
 	if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
 		return -EINVAL;
@@ -1951,9 +1979,17 @@ static int io_timeout(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		if (ctx->cached_sq_head < nxt_sq_head)
 			tmp += UINT_MAX;
 
-		if (tmp >= tmp_nxt)
+		if (tmp > tmp_nxt)
 			break;
+
+		/*
+		 * Sequence of reqs after the insert one and itself should
+		 * be adjusted because each timeout req consumes a slot.
+		 */
+		span++;
+		nxt->sequence++;
 	}
+	req->sequence -= span;
 	list_add(&req->list, entry);
 	spin_unlock_irq(&ctx->completion_lock);
 
@@ -2292,11 +2328,11 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 }
 
 static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			struct sqe_submit *s, bool force_nonblock)
+			struct sqe_submit *s)
 {
 	int ret;
 
-	ret = __io_submit_sqe(ctx, req, s, force_nonblock);
+	ret = __io_submit_sqe(ctx, req, s, true);
 
 	/*
 	 * We async punt it if the file wasn't marked NOWAIT, or if the file
@@ -2343,7 +2379,7 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 }
 
 static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			struct sqe_submit *s, bool force_nonblock)
+			struct sqe_submit *s)
 {
 	int ret;
 
@@ -2356,18 +2392,17 @@ static int io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		return 0;
 	}
 
-	return __io_queue_sqe(ctx, req, s, force_nonblock);
+	return __io_queue_sqe(ctx, req, s);
 }
 
 static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
-			      struct sqe_submit *s, struct io_kiocb *shadow,
-			      bool force_nonblock)
+			      struct sqe_submit *s, struct io_kiocb *shadow)
 {
 	int ret;
 	int need_submit = false;
 
 	if (!shadow)
-		return io_queue_sqe(ctx, req, s, force_nonblock);
+		return io_queue_sqe(ctx, req, s);
 
 	/*
 	 * Mark the first IO in link list as DRAIN, let all the following
@@ -2379,6 +2414,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	if (ret) {
 		if (ret != -EIOCBQUEUED) {
 			io_free_req(req);
+			__io_free_req(shadow);
 			io_cqring_add_event(ctx, s->sqe->user_data, ret);
 			return 0;
 		}
@@ -2396,7 +2432,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	spin_unlock_irq(&ctx->completion_lock);
 
 	if (need_submit)
-		return __io_queue_sqe(ctx, req, s, force_nonblock);
+		return __io_queue_sqe(ctx, req, s);
 
 	return 0;
 }
@@ -2404,8 +2440,7 @@ static int io_queue_link_head(struct io_ring_ctx *ctx, struct io_kiocb *req,
 #define SQE_VALID_FLAGS	(IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK)
 
 static void io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
-			  struct io_submit_state *state, struct io_kiocb **link,
-			  bool force_nonblock)
+			  struct io_submit_state *state, struct io_kiocb **link)
 {
 	struct io_uring_sqe *sqe_copy;
 	struct io_kiocb *req;
@@ -2432,6 +2467,8 @@ err:
 		return;
 	}
 
+	req->user_data = s->sqe->user_data;
+
 	/*
 	 * If we already have a head request, queue this one for async
 	 * submittal once the head completes. If we don't have a head but
@@ -2458,7 +2495,7 @@ err:
 		INIT_LIST_HEAD(&req->link_list);
 		*link = req;
 	} else {
-		io_queue_sqe(ctx, req, s, force_nonblock);
+		io_queue_sqe(ctx, req, s);
 	}
 }
 
@@ -2538,12 +2575,13 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 
 	/* drop invalid entries */
 	ctx->cached_sq_head++;
-	rings->sq_dropped++;
+	ctx->cached_sq_dropped++;
+	WRITE_ONCE(rings->sq_dropped, ctx->cached_sq_dropped);
 	return false;
 }
 
-static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
-			  unsigned int nr, bool has_user, bool mm_fault)
+static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr,
+			  bool has_user, bool mm_fault)
 {
 	struct io_submit_state state, *statep = NULL;
 	struct io_kiocb *link = NULL;
@@ -2557,19 +2595,23 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
 	}
 
 	for (i = 0; i < nr; i++) {
+		struct sqe_submit s;
+
+		if (!io_get_sqring(ctx, &s))
+			break;
+
 		/*
 		 * If previous wasn't linked and we have a linked command,
 		 * that's the end of the chain. Submit the previous link.
 		 */
 		if (!prev_was_link && link) {
-			io_queue_link_head(ctx, link, &link->submit, shadow_req,
-						true);
+			io_queue_link_head(ctx, link, &link->submit, shadow_req);
 			link = NULL;
 			shadow_req = NULL;
 		}
-		prev_was_link = (sqes[i].sqe->flags & IOSQE_IO_LINK) != 0;
+		prev_was_link = (s.sqe->flags & IOSQE_IO_LINK) != 0;
 
-		if (link && (sqes[i].sqe->flags & IOSQE_IO_DRAIN)) {
+		if (link && (s.sqe->flags & IOSQE_IO_DRAIN)) {
 			if (!shadow_req) {
 				shadow_req = io_get_req(ctx, NULL);
 				if (unlikely(!shadow_req))
@@ -2577,24 +2619,24 @@ static int io_submit_sqes(struct io_ring_ctx *ctx, struct sqe_submit *sqes,
 				shadow_req->flags |= (REQ_F_IO_DRAIN | REQ_F_SHADOW_DRAIN);
 				refcount_dec(&shadow_req->refs);
 			}
-			shadow_req->sequence = sqes[i].sequence;
+			shadow_req->sequence = s.sequence;
 		}
 
 out:
 		if (unlikely(mm_fault)) {
-			io_cqring_add_event(ctx, sqes[i].sqe->user_data,
+			io_cqring_add_event(ctx, s.sqe->user_data,
 						-EFAULT);
 		} else {
-			sqes[i].has_user = has_user;
-			sqes[i].needs_lock = true;
-			sqes[i].needs_fixed_file = true;
-			io_submit_sqe(ctx, &sqes[i], statep, &link, true);
+			s.has_user = has_user;
+			s.needs_lock = true;
+			s.needs_fixed_file = true;
+			io_submit_sqe(ctx, &s, statep, &link);
 			submitted++;
 		}
 	}
 
 	if (link)
-		io_queue_link_head(ctx, link, &link->submit, shadow_req, true);
+		io_queue_link_head(ctx, link, &link->submit, shadow_req);
 	if (statep)
 		io_submit_state_end(&state);
 
@@ -2603,7 +2645,6 @@ out:
 
 static int io_sq_thread(void *data)
 {
-	struct sqe_submit sqes[IO_IOPOLL_BATCH];
 	struct io_ring_ctx *ctx = data;
 	struct mm_struct *cur_mm = NULL;
 	mm_segment_t old_fs;
@@ -2618,14 +2659,27 @@ static int io_sq_thread(void *data)
 
 	timeout = inflight = 0;
 	while (!kthread_should_park()) {
-		bool all_fixed, mm_fault = false;
-		int i;
+		bool mm_fault = false;
+		unsigned int to_submit;
 
 		if (inflight) {
 			unsigned nr_events = 0;
 
 			if (ctx->flags & IORING_SETUP_IOPOLL) {
-				io_iopoll_check(ctx, &nr_events, 0);
+				/*
+				 * inflight is the count of the maximum possible
+				 * entries we submitted, but it can be smaller
+				 * if we dropped some of them. If we don't have
+				 * poll entries available, then we know that we
+				 * have nothing left to poll for. Reset the
+				 * inflight count to zero in that case.
+				 */
+				mutex_lock(&ctx->uring_lock);
+				if (!list_empty(&ctx->poll_list))
+					__io_iopoll_check(ctx, &nr_events, 0);
+				else
+					inflight = 0;
+				mutex_unlock(&ctx->uring_lock);
 			} else {
 				/*
 				 * Normal IO, just pretend everything completed.
@@ -2639,7 +2693,8 @@ static int io_sq_thread(void *data)
 				timeout = jiffies + ctx->sq_thread_idle;
 		}
 
-		if (!io_get_sqring(ctx, &sqes[0])) {
+		to_submit = io_sqring_entries(ctx);
+		if (!to_submit) {
 			/*
 			 * We're polling. If we're within the defined idle
 			 * period, then let us spin without work before going
@@ -2670,7 +2725,8 @@ static int io_sq_thread(void *data)
 			/* make sure to read SQ tail after writing flags */
 			smp_mb();
 
-			if (!io_get_sqring(ctx, &sqes[0])) {
+			to_submit = io_sqring_entries(ctx);
+			if (!to_submit) {
 				if (kthread_should_park()) {
 					finish_wait(&ctx->sqo_wait, &wait);
 					break;
@@ -2688,19 +2744,8 @@ static int io_sq_thread(void *data)
 			ctx->rings->sq_flags &= ~IORING_SQ_NEED_WAKEUP;
 		}
 
-		i = 0;
-		all_fixed = true;
-		do {
-			if (all_fixed && io_sqe_needs_user(sqes[i].sqe))
-				all_fixed = false;
-
-			i++;
-			if (i == ARRAY_SIZE(sqes))
-				break;
-		} while (io_get_sqring(ctx, &sqes[i]));
-
 		/* Unless all new commands are FIXED regions, grab mm */
-		if (!all_fixed && !cur_mm) {
+		if (!cur_mm) {
 			mm_fault = !mmget_not_zero(ctx->sqo_mm);
 			if (!mm_fault) {
 				use_mm(ctx->sqo_mm);
@@ -2708,8 +2753,9 @@ static int io_sq_thread(void *data)
 			}
 		}
 
-		inflight += io_submit_sqes(ctx, sqes, i, cur_mm != NULL,
-						mm_fault);
+		to_submit = min(to_submit, ctx->sq_entries);
+		inflight += io_submit_sqes(ctx, to_submit, cur_mm != NULL,
+					   mm_fault);
 
 		/* Commit SQ ring head once we've consumed all SQEs */
 		io_commit_sqring(ctx);
@@ -2726,8 +2772,7 @@ static int io_sq_thread(void *data)
 	return 0;
 }
 
-static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
-			  bool block_for_last)
+static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
 {
 	struct io_submit_state state, *statep = NULL;
 	struct io_kiocb *link = NULL;
@@ -2741,7 +2786,6 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
 	}
 
 	for (i = 0; i < to_submit; i++) {
-		bool force_nonblock = true;
 		struct sqe_submit s;
 
 		if (!io_get_sqring(ctx, &s))
@@ -2752,8 +2796,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit,
 		 * that's the end of the chain. Submit the previous link.
 		 */
 		if (!prev_was_link && link) {
-			io_queue_link_head(ctx, link, &link->submit, shadow_req,
-						force_nonblock);
+			io_queue_link_head(ctx, link, &link->submit, shadow_req);
 			link = NULL;
 			shadow_req = NULL;
 		}
@@ -2775,27 +2818,16 @@ out:
 		s.needs_lock = false;
 		s.needs_fixed_file = false;
 		submit++;
-
-		/*
-		 * The caller will block for events after submit, submit the
-		 * last IO non-blocking. This is either the only IO it's
-		 * submitting, or it already submitted the previous ones. This
-		 * improves performance by avoiding an async punt that we don't
-		 * need to do.
-		 */
-		if (block_for_last && submit == to_submit)
-			force_nonblock = false;
-
-		io_submit_sqe(ctx, &s, statep, &link, force_nonblock);
+		io_submit_sqe(ctx, &s, statep, &link);
 	}
-	io_commit_sqring(ctx);
 
 	if (link)
-		io_queue_link_head(ctx, link, &link->submit, shadow_req,
-					!block_for_last);
+		io_queue_link_head(ctx, link, &link->submit, shadow_req);
 	if (statep)
 		io_submit_state_end(statep);
 
+	io_commit_sqring(ctx);
+
 	return submit;
 }
 
@@ -3636,21 +3668,10 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 			wake_up(&ctx->sqo_wait);
 		submitted = to_submit;
 	} else if (to_submit) {
-		bool block_for_last = false;
-
 		to_submit = min(to_submit, ctx->sq_entries);
 
-		/*
-		 * Allow last submission to block in a series, IFF the caller
-		 * asked to wait for events and we don't currently have
-		 * enough. This potentially avoids an async punt.
-		 */
-		if (to_submit == min_complete &&
-		    io_cqring_events(ctx->rings) < min_complete)
-			block_for_last = true;
-
 		mutex_lock(&ctx->uring_lock);
-		submitted = io_ring_submit(ctx, to_submit, block_for_last);
+		submitted = io_ring_submit(ctx, to_submit);
 		mutex_unlock(&ctx->uring_lock);
 	}
 	if (flags & IORING_ENTER_GETEVENTS) {
@@ -3809,10 +3830,6 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	if (ret)
 		goto err;
 
-	ret = io_uring_get_fd(ctx);
-	if (ret < 0)
-		goto err;
-
 	memset(&p->sq_off, 0, sizeof(p->sq_off));
 	p->sq_off.head = offsetof(struct io_rings, sq.head);
 	p->sq_off.tail = offsetof(struct io_rings, sq.tail);
@@ -3830,6 +3847,14 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p)
 	p->cq_off.overflow = offsetof(struct io_rings, cq_overflow);
 	p->cq_off.cqes = offsetof(struct io_rings, cqes);
 
+	/*
+	 * Install ring fd as the very last thing, so we don't risk someone
+	 * having closed it before we finish setup
+	 */
+	ret = io_uring_get_fd(ctx);
+	if (ret < 0)
+		goto err;
+
 	p->features = IORING_FEAT_SINGLE_MMAP;
 	return ret;
 err:
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 071b90a45933..af549d70ec50 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -53,6 +53,16 @@ nfs4_is_valid_delegation(const struct nfs_delegation *delegation,
 	return false;
 }
 
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+
+	delegation = rcu_dereference(NFS_I(inode)->delegation);
+	if (nfs4_is_valid_delegation(delegation, 0))
+		return delegation;
+	return NULL;
+}
+
 static int
 nfs4_do_check_delegation(struct inode *inode, fmode_t flags, bool mark)
 {
@@ -1181,7 +1191,7 @@ bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode)
 	if (delegation != NULL &&
 	    nfs4_stateid_match_other(dst, &delegation->stateid)) {
 		dst->seqid = delegation->stateid.seqid;
-		return ret;
+		ret = true;
 	}
 	rcu_read_unlock();
 out:
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 9eb87ae4c982..8b14d441e699 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -68,6 +68,7 @@ int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state,
 bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, nfs4_stateid *dst, const struct cred **cred);
 bool nfs4_refresh_delegation_stateid(nfs4_stateid *dst, struct inode *inode);
 
+struct nfs_delegation *nfs4_get_valid_delegation(const struct inode *inode);
 void nfs_mark_delegation_referenced(struct nfs_delegation *delegation);
 int nfs4_have_delegation(struct inode *inode, fmode_t flags);
 int nfs4_check_delegation(struct inode *inode, fmode_t flags);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ab8ca20fd579..caacf5e7f5e1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1440,8 +1440,6 @@ static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode,
 		return 0;
 	if ((delegation->type & fmode) != fmode)
 		return 0;
-	if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
-		return 0;
 	switch (claim) {
 	case NFS4_OPEN_CLAIM_NULL:
 	case NFS4_OPEN_CLAIM_FH:
@@ -1810,7 +1808,6 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo
 static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 {
 	struct nfs4_state *state = opendata->state;
-	struct nfs_inode *nfsi = NFS_I(state->inode);
 	struct nfs_delegation *delegation;
 	int open_mode = opendata->o_arg.open_flags;
 	fmode_t fmode = opendata->o_arg.fmode;
@@ -1827,7 +1824,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 		}
 		spin_unlock(&state->owner->so_lock);
 		rcu_read_lock();
-		delegation = rcu_dereference(nfsi->delegation);
+		delegation = nfs4_get_valid_delegation(state->inode);
 		if (!can_open_delegated(delegation, fmode, claim)) {
 			rcu_read_unlock();
 			break;
@@ -2371,7 +2368,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 					data->o_arg.open_flags, claim))
 			goto out_no_action;
 		rcu_read_lock();
-		delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
+		delegation = nfs4_get_valid_delegation(data->state->inode);
 		if (can_open_delegated(delegation, data->o_arg.fmode, claim))
 			goto unlock_no_action;
 		rcu_read_unlock();
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 53939bf9d7d2..9876db52913a 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
 	return 0;
 }
 
-static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
-					    struct file *file,
-					    loff_t pos, size_t count,
-					    int *meta_level)
+static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
+					    struct buffer_head **di_bh,
+					    int meta_level,
+					    int overwrite_io,
+					    int write_sem,
+					    int wait)
 {
-	int ret;
-	struct buffer_head *di_bh = NULL;
-	u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
-	u32 clusters =
-		ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+	int ret = 0;
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (ret) {
-		mlog_errno(ret);
+	if (wait)
+		ret = ocfs2_inode_lock(inode, NULL, meta_level);
+	else
+		ret = ocfs2_try_inode_lock(inode,
+			overwrite_io ? NULL : di_bh, meta_level);
+	if (ret < 0)
 		goto out;
+
+	if (wait) {
+		if (write_sem)
+			down_write(&OCFS2_I(inode)->ip_alloc_sem);
+		else
+			down_read(&OCFS2_I(inode)->ip_alloc_sem);
+	} else {
+		if (write_sem)
+			ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+		else
+			ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem);
+
+		if (!ret) {
+			ret = -EAGAIN;
+			goto out_unlock;
+		}
 	}
 
-	*meta_level = 1;
+	return ret;
 
-	ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
-	if (ret)
-		mlog_errno(ret);
+out_unlock:
+	brelse(*di_bh);
+	ocfs2_inode_unlock(inode, meta_level);
 out:
-	brelse(di_bh);
 	return ret;
 }
 
+static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode,
+					       struct buffer_head **di_bh,
+					       int meta_level,
+					       int write_sem)
+{
+	if (write_sem)
+		up_write(&OCFS2_I(inode)->ip_alloc_sem);
+	else
+		up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	brelse(*di_bh);
+	*di_bh = NULL;
+
+	if (meta_level >= 0)
+		ocfs2_inode_unlock(inode, meta_level);
+}
+
 static int ocfs2_prepare_inode_for_write(struct file *file,
 					 loff_t pos, size_t count, int wait)
 {
 	int ret = 0, meta_level = 0, overwrite_io = 0;
+	int write_sem = 0;
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
 	struct buffer_head *di_bh = NULL;
+	u32 cpos;
+	u32 clusters;
 
 	/*
 	 * We start with a read level meta lock and only jump to an ex
 	 * if we need to make modifications here.
 	 */
 	for(;;) {
-		if (wait)
-			ret = ocfs2_inode_lock(inode, NULL, meta_level);
-		else
-			ret = ocfs2_try_inode_lock(inode,
-				overwrite_io ? NULL : &di_bh, meta_level);
+		ret = ocfs2_inode_lock_for_extent_tree(inode,
+						       &di_bh,
+						       meta_level,
+						       overwrite_io,
+						       write_sem,
+						       wait);
 		if (ret < 0) {
-			meta_level = -1;
 			if (ret != -EAGAIN)
 				mlog_errno(ret);
 			goto out;
@@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 */
 		if (!wait && !overwrite_io) {
 			overwrite_io = 1;
-			if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
-				ret = -EAGAIN;
-				goto out_unlock;
-			}
 
 			ret = ocfs2_overwrite_io(inode, di_bh, pos, count);
-			brelse(di_bh);
-			di_bh = NULL;
-			up_read(&OCFS2_I(inode)->ip_alloc_sem);
 			if (ret < 0) {
 				if (ret != -EAGAIN)
 					mlog_errno(ret);
@@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 		 * set inode->i_size at the end of a write. */
 		if (should_remove_suid(dentry)) {
 			if (meta_level == 0) {
-				ocfs2_inode_unlock(inode, meta_level);
+				ocfs2_inode_unlock_for_extent_tree(inode,
+								   &di_bh,
+								   meta_level,
+								   write_sem);
 				meta_level = 1;
 				continue;
 			}
@@ -2197,18 +2229,32 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
 
 		ret = ocfs2_check_range_for_refcount(inode, pos, count);
 		if (ret == 1) {
-			ocfs2_inode_unlock(inode, meta_level);
-			meta_level = -1;
-
-			ret = ocfs2_prepare_inode_for_refcount(inode,
-							       file,
-							       pos,
-							       count,
-							       &meta_level);
+			ocfs2_inode_unlock_for_extent_tree(inode,
+							   &di_bh,
+							   meta_level,
+							   write_sem);
+			ret = ocfs2_inode_lock_for_extent_tree(inode,
+							       &di_bh,
+							       meta_level,
+							       overwrite_io,
+							       1,
+							       wait);
+			write_sem = 1;
+			if (ret < 0) {
+				if (ret != -EAGAIN)
+					mlog_errno(ret);
+				goto out;
+			}
+
+			cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+			clusters =
+				ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
+			ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
 		}
 
 		if (ret < 0) {
-			mlog_errno(ret);
+			if (ret != -EAGAIN)
+				mlog_errno(ret);
 			goto out_unlock;
 		}
 
@@ -2219,10 +2265,10 @@ out_unlock:
 	trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
 					    pos, count, wait);
 
-	brelse(di_bh);
-
-	if (meta_level >= 0)
-		ocfs2_inode_unlock(inode, meta_level);
+	ocfs2_inode_unlock_for_extent_tree(inode,
+					   &di_bh,
+					   meta_level,
+					   write_sem);
 
 out:
 	return ret;
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index f936033cb9e6..47805172e73d 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -232,8 +232,8 @@ struct acpi_processor {
 	struct acpi_processor_limit limit;
 	struct thermal_cooling_device *cdev;
 	struct device *dev; /* Processor device. */
-	struct dev_pm_qos_request perflib_req;
-	struct dev_pm_qos_request thermal_req;
+	struct freq_qos_request perflib_req;
+	struct freq_qos_request thermal_req;
 };
 
 struct acpi_processor_errata {
@@ -302,8 +302,8 @@ static inline void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx
 #ifdef CONFIG_CPU_FREQ
 extern bool acpi_processor_cpufreq_init;
 void acpi_processor_ignore_ppc_init(void);
-void acpi_processor_ppc_init(int cpu);
-void acpi_processor_ppc_exit(int cpu);
+void acpi_processor_ppc_init(struct cpufreq_policy *policy);
+void acpi_processor_ppc_exit(struct cpufreq_policy *policy);
 void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag);
 extern int acpi_processor_get_bios_limit(int cpu, unsigned int *limit);
 #else
@@ -311,11 +311,11 @@ static inline void acpi_processor_ignore_ppc_init(void)
 {
 	return;
 }
-static inline void acpi_processor_ppc_init(int cpu)
+static inline void acpi_processor_ppc_init(struct cpufreq_policy *policy)
 {
 	return;
 }
-static inline void acpi_processor_ppc_exit(int cpu)
+static inline void acpi_processor_ppc_exit(struct cpufreq_policy *policy)
 {
 	return;
 }
@@ -431,14 +431,14 @@ static inline int acpi_processor_hotplug(struct acpi_processor *pr)
 int acpi_processor_get_limit_info(struct acpi_processor *pr);
 extern const struct thermal_cooling_device_ops processor_cooling_ops;
 #if defined(CONFIG_ACPI_CPU_FREQ_PSS) & defined(CONFIG_CPU_FREQ)
-void acpi_thermal_cpufreq_init(int cpu);
-void acpi_thermal_cpufreq_exit(int cpu);
+void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy);
+void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy);
 #else
-static inline void acpi_thermal_cpufreq_init(int cpu)
+static inline void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
 	return;
 }
-static inline void acpi_thermal_cpufreq_exit(int cpu)
+static inline void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
 {
 	return;
 }
diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index e94b19782c92..ce4103208619 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -25,13 +25,6 @@ static __always_inline int __arch_get_clock_mode(struct timekeeper *tk)
 }
 #endif /* __arch_get_clock_mode */
 
-#ifndef __arch_use_vsyscall
-static __always_inline int __arch_use_vsyscall(struct vdso_data *vdata)
-{
-	return 1;
-}
-#endif /* __arch_use_vsyscall */
-
 #ifndef __arch_update_vsyscall
 static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata,
 						   struct timekeeper *tk)
diff --git a/include/drm/amd_asic_type.h b/include/drm/amd_asic_type.h
index 296aab724677..b1230e33d506 100644
--- a/include/drm/amd_asic_type.h
+++ b/include/drm/amd_asic_type.h
@@ -27,34 +27,36 @@
  */
 enum amd_asic_type {
 	CHIP_TAHITI = 0,
-	CHIP_PITCAIRN,
-	CHIP_VERDE,
-	CHIP_OLAND,
-	CHIP_HAINAN,
-	CHIP_BONAIRE,
-	CHIP_KAVERI,
-	CHIP_KABINI,
-	CHIP_HAWAII,
-	CHIP_MULLINS,
-	CHIP_TOPAZ,
-	CHIP_TONGA,
-	CHIP_FIJI,
-	CHIP_CARRIZO,
-	CHIP_STONEY,
-	CHIP_POLARIS10,
-	CHIP_POLARIS11,
-	CHIP_POLARIS12,
-	CHIP_VEGAM,
-	CHIP_VEGA10,
-	CHIP_VEGA12,
-	CHIP_VEGA20,
-	CHIP_RAVEN,
-	CHIP_ARCTURUS,
-	CHIP_RENOIR,
-	CHIP_NAVI10,
-	CHIP_NAVI14,
-	CHIP_NAVI12,
+	CHIP_PITCAIRN,	/* 1 */
+	CHIP_VERDE,	/* 2 */
+	CHIP_OLAND,	/* 3 */
+	CHIP_HAINAN,	/* 4 */
+	CHIP_BONAIRE,	/* 5 */
+	CHIP_KAVERI,	/* 6 */
+	CHIP_KABINI,	/* 7 */
+	CHIP_HAWAII,	/* 8 */
+	CHIP_MULLINS,	/* 9 */
+	CHIP_TOPAZ,	/* 10 */
+	CHIP_TONGA,	/* 11 */
+	CHIP_FIJI,	/* 12 */
+	CHIP_CARRIZO,	/* 13 */
+	CHIP_STONEY,	/* 14 */
+	CHIP_POLARIS10,	/* 15 */
+	CHIP_POLARIS11,	/* 16 */
+	CHIP_POLARIS12,	/* 17 */
+	CHIP_VEGAM,	/* 18 */
+	CHIP_VEGA10,	/* 19 */
+	CHIP_VEGA12,	/* 20 */
+	CHIP_VEGA20,	/* 21 */
+	CHIP_RAVEN,	/* 22 */
+	CHIP_ARCTURUS,	/* 23 */
+	CHIP_RENOIR,	/* 24 */
+	CHIP_NAVI10,	/* 25 */
+	CHIP_NAVI14,	/* 26 */
+	CHIP_NAVI12,	/* 27 */
 	CHIP_LAST,
 };
 
+extern const char *amdgpu_asic_name[];
+
 #endif /*__AMD_ASIC_TYPE_H__ */
diff --git a/include/drm/drm_dp_mst_helper.h b/include/drm/drm_dp_mst_helper.h
index 4a25e0577ae0..d5fc90b30487 100644
--- a/include/drm/drm_dp_mst_helper.h
+++ b/include/drm/drm_dp_mst_helper.h
@@ -26,6 +26,26 @@
 #include <drm/drm_dp_helper.h>
 #include <drm/drm_atomic.h>
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+#include <linux/stackdepot.h>
+#include <linux/timekeeping.h>
+
+enum drm_dp_mst_topology_ref_type {
+	DRM_DP_MST_TOPOLOGY_REF_GET,
+	DRM_DP_MST_TOPOLOGY_REF_PUT,
+};
+
+struct drm_dp_mst_topology_ref_history {
+	struct drm_dp_mst_topology_ref_entry {
+		enum drm_dp_mst_topology_ref_type type;
+		int count;
+		ktime_t ts_nsec;
+		depot_stack_handle_t backtrace;
+	} *entries;
+	int len;
+};
+#endif /* IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS) */
+
 struct drm_dp_mst_branch;
 
 /**
@@ -45,21 +65,31 @@ struct drm_dp_vcpi {
 /**
  * struct drm_dp_mst_port - MST port
  * @port_num: port number
- * @input: if this port is an input port.
- * @mcs: message capability status - DP 1.2 spec.
- * @ddps: DisplayPort Device Plug Status - DP 1.2
- * @pdt: Peer Device Type
- * @ldps: Legacy Device Plug Status
- * @dpcd_rev: DPCD revision of device on this port
- * @num_sdp_streams: Number of simultaneous streams
- * @num_sdp_stream_sinks: Number of stream sinks
- * @available_pbn: Available bandwidth for this port.
+ * @input: if this port is an input port. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @mcs: message capability status - DP 1.2 spec. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @ddps: DisplayPort Device Plug Status - DP 1.2. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @pdt: Peer Device Type. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @ldps: Legacy Device Plug Status. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @dpcd_rev: DPCD revision of device on this port. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @num_sdp_streams: Number of simultaneous streams. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @num_sdp_stream_sinks: Number of stream sinks. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
+ * @available_pbn: Available bandwidth for this port. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
  * @next: link to next port on this branch device
- * @mstb: branch device attach below this port
- * @aux: i2c aux transport to talk to device connected to this port.
+ * @aux: i2c aux transport to talk to device connected to this port, protected
+ * by &drm_dp_mst_topology_mgr.base.lock.
  * @parent: branch device parent of this port
  * @vcpi: Virtual Channel Payload info for this port.
- * @connector: DRM connector this port is connected to.
+ * @connector: DRM connector this port is connected to. Protected by
+ * &drm_dp_mst_topology_mgr.base.lock.
  * @mgr: topology manager this port lives under.
  *
  * This structure represents an MST port endpoint on a device somewhere
@@ -79,6 +109,14 @@ struct drm_dp_mst_port {
 	 */
 	struct kref malloc_kref;
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	/**
+	 * @topology_ref_history: A history of each topology
+	 * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS.
+	 */
+	struct drm_dp_mst_topology_ref_history topology_ref_history;
+#endif
+
 	u8 port_num;
 	bool input;
 	bool mcs;
@@ -90,7 +128,17 @@ struct drm_dp_mst_port {
 	u8 num_sdp_stream_sinks;
 	uint16_t available_pbn;
 	struct list_head next;
-	struct drm_dp_mst_branch *mstb; /* pointer to an mstb if this port has one */
+	/**
+	 * @mstb: the branch device connected to this port, if there is one.
+	 * This should be considered protected for reading by
+	 * &drm_dp_mst_topology_mgr.lock. There are two exceptions to this:
+	 * &drm_dp_mst_topology_mgr.up_req_work and
+	 * &drm_dp_mst_topology_mgr.work, which do not grab
+	 * &drm_dp_mst_topology_mgr.lock during reads but are the only
+	 * updaters of this list and are protected from writing concurrently
+	 * by &drm_dp_mst_topology_mgr.probe_lock.
+	 */
+	struct drm_dp_mst_branch *mstb;
 	struct drm_dp_aux aux; /* i2c bus for this port? */
 	struct drm_dp_mst_branch *parent;
 
@@ -116,7 +164,6 @@ struct drm_dp_mst_port {
  * @lct: Link count total to talk to this branch device.
  * @num_ports: number of ports on the branch.
  * @msg_slots: one bit per transmitted msg slot.
- * @ports: linked list of ports on this branch.
  * @port_parent: pointer to the port parent, NULL if toplevel.
  * @mgr: topology manager for this branch device.
  * @tx_slots: transmission slots for this device.
@@ -143,11 +190,35 @@ struct drm_dp_mst_branch {
 	 */
 	struct kref malloc_kref;
 
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	/**
+	 * @topology_ref_history: A history of each topology
+	 * reference/dereference. See CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS.
+	 */
+	struct drm_dp_mst_topology_ref_history topology_ref_history;
+#endif
+
+	/**
+	 * @destroy_next: linked-list entry used by
+	 * drm_dp_delayed_destroy_work()
+	 */
+	struct list_head destroy_next;
+
 	u8 rad[8];
 	u8 lct;
 	int num_ports;
 
 	int msg_slots;
+	/**
+	 * @ports: the list of ports on this branch device. This should be
+	 * considered protected for reading by &drm_dp_mst_topology_mgr.lock.
+	 * There are two exceptions to this:
+	 * &drm_dp_mst_topology_mgr.up_req_work and
+	 * &drm_dp_mst_topology_mgr.work, which do not grab
+	 * &drm_dp_mst_topology_mgr.lock during reads but are the only
+	 * updaters of this list and are protected from updating the list
+	 * concurrently by @drm_dp_mst_topology_mgr.probe_lock
+	 */
 	struct list_head ports;
 
 	/* list of tx ops queue for this port */
@@ -495,6 +566,13 @@ struct drm_dp_mst_topology_mgr {
 	struct mutex lock;
 
 	/**
+	 * @probe_lock: Prevents @work and @up_req_work, the only writers of
+	 * &drm_dp_mst_port.mstb and &drm_dp_mst_branch.ports, from racing
+	 * while they update the topology.
+	 */
+	struct mutex probe_lock;
+
+	/**
 	 * @mst_state: If this manager is enabled for an MST capable port. False
 	 * if no MST sink/branch devices is connected.
 	 */
@@ -571,18 +649,49 @@ struct drm_dp_mst_topology_mgr {
 	struct work_struct tx_work;
 
 	/**
-	 * @destroy_connector_list: List of to be destroyed connectors.
+	 * @destroy_port_list: List of to be destroyed connectors.
+	 */
+	struct list_head destroy_port_list;
+	/**
+	 * @destroy_branch_device_list: List of to be destroyed branch
+	 * devices.
+	 */
+	struct list_head destroy_branch_device_list;
+	/**
+	 * @delayed_destroy_lock: Protects @destroy_port_list and
+	 * @destroy_branch_device_list.
+	 */
+	struct mutex delayed_destroy_lock;
+	/**
+	 * @delayed_destroy_work: Work item to destroy MST port and branch
+	 * devices, needed to avoid locking inversion.
+	 */
+	struct work_struct delayed_destroy_work;
+
+	/**
+	 * @up_req_list: List of pending up requests from the topology that
+	 * need to be processed, in chronological order.
 	 */
-	struct list_head destroy_connector_list;
+	struct list_head up_req_list;
 	/**
-	 * @destroy_connector_lock: Protects @connector_list.
+	 * @up_req_lock: Protects @up_req_list
 	 */
-	struct mutex destroy_connector_lock;
+	struct mutex up_req_lock;
 	/**
-	 * @destroy_connector_work: Work item to destroy connectors. Needed to
-	 * avoid locking inversion.
+	 * @up_req_work: Work item to process up requests received from the
+	 * topology. Needed to avoid blocking hotplug handling and sideband
+	 * transmissions.
 	 */
-	struct work_struct destroy_connector_work;
+	struct work_struct up_req_work;
+
+#if IS_ENABLED(CONFIG_DRM_DEBUG_DP_MST_TOPOLOGY_REFS)
+	/**
+	 * @topology_ref_history_lock: protects
+	 * &drm_dp_mst_port.topology_ref_history and
+	 * &drm_dp_mst_branch.topology_ref_history.
+	 */
+	struct mutex topology_ref_history_lock;
+#endif
 };
 
 int drm_dp_mst_topology_mgr_init(struct drm_dp_mst_topology_mgr *mgr,
@@ -599,7 +708,11 @@ int drm_dp_mst_topology_mgr_set_mst(struct drm_dp_mst_topology_mgr *mgr, bool ms
 int drm_dp_mst_hpd_irq(struct drm_dp_mst_topology_mgr *mgr, u8 *esi, bool *handled);
 
 
-enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector, struct drm_dp_mst_topology_mgr *mgr, struct drm_dp_mst_port *port);
+int
+drm_dp_mst_detect_port(struct drm_connector *connector,
+		       struct drm_modeset_acquire_ctx *ctx,
+		       struct drm_dp_mst_topology_mgr *mgr,
+		       struct drm_dp_mst_port *port);
 
 bool drm_dp_mst_port_has_audio(struct drm_dp_mst_topology_mgr *mgr,
 					struct drm_dp_mst_port *port);
@@ -638,7 +751,8 @@ void drm_dp_mst_dump_topology(struct seq_file *m,
 
 void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr);
 int __must_check
-drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr);
+drm_dp_mst_topology_mgr_resume(struct drm_dp_mst_topology_mgr *mgr,
+			       bool sync);
 
 ssize_t drm_dp_mst_dpcd_read(struct drm_dp_aux *aux,
 			     unsigned int offset, void *buffer, size_t size);
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index 8dcc012ccbc8..2338e9f94a03 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -235,7 +235,6 @@ void drm_fb_helper_unlink_fbi(struct drm_fb_helper *fb_helper);
 
 void drm_fb_helper_deferred_io(struct fb_info *info,
 			       struct list_head *pagelist);
-int drm_fb_helper_defio_init(struct drm_fb_helper *fb_helper);
 
 ssize_t drm_fb_helper_sys_read(struct fb_info *info, char __user *buf,
 			       size_t count, loff_t *ppos);
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index e71f75a2ab57..97a48165642c 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -159,8 +159,9 @@ struct drm_gem_object_funcs {
 	 *
 	 * The callback is used by by both drm_gem_mmap_obj() and
 	 * drm_gem_prime_mmap().  When @mmap is present @vm_ops is not
-	 * used, the @mmap callback must set vma->vm_ops instead.
-	 *
+	 * used, the @mmap callback must set vma->vm_ops instead. The @mmap
+	 * callback is always called with a 0 offset. The caller will remove
+	 * the fake offset as necessary.
 	 */
 	int (*mmap)(struct drm_gem_object *obj, struct vm_area_struct *vma);
 
diff --git a/include/drm/drm_gem_shmem_helper.h b/include/drm/drm_gem_shmem_helper.h
index 6748379a0b44..e34a7b7f848a 100644
--- a/include/drm/drm_gem_shmem_helper.h
+++ b/include/drm/drm_gem_shmem_helper.h
@@ -44,7 +44,20 @@ struct drm_gem_shmem_object {
 	 */
 	unsigned int pages_use_count;
 
+	/**
+	 * @madv: State for madvise
+	 *
+	 * 0 is active/inuse.
+	 * A negative value is the object is purged.
+	 * Positive values are driver specific and not used by the helpers.
+	 */
 	int madv;
+
+	/**
+	 * @madv_list: List entry for madvise tracking
+	 *
+	 * Typically used by drivers to track purgeable objects
+	 */
 	struct list_head madv_list;
 
 	/**
diff --git a/include/drm/drm_gem_vram_helper.h b/include/drm/drm_gem_vram_helper.h
index b8ad4531ebb4..e040541a105f 100644
--- a/include/drm/drm_gem_vram_helper.h
+++ b/include/drm/drm_gem_vram_helper.h
@@ -13,6 +13,9 @@
 #include <linux/kernel.h> /* for container_of() */
 
 struct drm_mode_create_dumb;
+struct drm_plane;
+struct drm_plane_state;
+struct drm_simple_display_pipe;
 struct drm_vram_mm_funcs;
 struct filp;
 struct vm_area_struct;
@@ -124,6 +127,28 @@ int drm_gem_vram_driver_dumb_mmap_offset(struct drm_file *file,
 					 struct drm_device *dev,
 					 uint32_t handle, uint64_t *offset);
 
+/*
+ * Helpers for struct drm_plane_helper_funcs
+ */
+int
+drm_gem_vram_plane_helper_prepare_fb(struct drm_plane *plane,
+				     struct drm_plane_state *new_state);
+void
+drm_gem_vram_plane_helper_cleanup_fb(struct drm_plane *plane,
+				     struct drm_plane_state *old_state);
+
+/*
+ * Helpers for struct drm_simple_display_pipe_funcs
+ */
+
+int drm_gem_vram_simple_display_pipe_prepare_fb(
+	struct drm_simple_display_pipe *pipe,
+	struct drm_plane_state *new_state);
+
+void drm_gem_vram_simple_display_pipe_cleanup_fb(
+	struct drm_simple_display_pipe *pipe,
+	struct drm_plane_state *old_state);
+
 /**
  * define DRM_GEM_VRAM_DRIVER - default callback functions for \
 	&struct drm_driver
diff --git a/include/drm/drm_self_refresh_helper.h b/include/drm/drm_self_refresh_helper.h
index 5b79d253fb46..520235c20708 100644
--- a/include/drm/drm_self_refresh_helper.h
+++ b/include/drm/drm_self_refresh_helper.h
@@ -13,7 +13,8 @@ struct drm_crtc;
 
 void drm_self_refresh_helper_alter_state(struct drm_atomic_state *state);
 void drm_self_refresh_helper_update_avg_times(struct drm_atomic_state *state,
-					      unsigned int commit_time_ms);
+					unsigned int commit_time_ms,
+					unsigned int new_self_refresh_mask);
 
 int drm_self_refresh_helper_init(struct drm_crtc *crtc);
 void drm_self_refresh_helper_cleanup(struct drm_crtc *crtc);
diff --git a/include/drm/drm_simple_kms_helper.h b/include/drm/drm_simple_kms_helper.h
index 4d89cd0a60db..15afee9cf049 100644
--- a/include/drm/drm_simple_kms_helper.h
+++ b/include/drm/drm_simple_kms_helper.h
@@ -49,7 +49,7 @@ struct drm_simple_display_pipe_funcs {
 	 *
 	 * drm_mode_status Enum
 	 */
-	enum drm_mode_status (*mode_valid)(struct drm_crtc *crtc,
+	enum drm_mode_status (*mode_valid)(struct drm_simple_display_pipe *pipe,
 					   const struct drm_display_mode *mode);
 
 	/**
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 57b4121c750a..684692a8ed76 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -26,6 +26,7 @@
 
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
+#include <linux/completion.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
@@ -71,6 +72,7 @@ enum drm_sched_priority {
  * @last_scheduled: points to the finished fence of the last scheduled job.
  * @last_user: last group leader pushing a job into the entity.
  * @stopped: Marks the enity as removed from rq and destined for termination.
+ * @entity_idle: Signals when enityt is not in use
  *
  * Entities will emit jobs in order to their corresponding hardware
  * ring, and the scheduler will alternate between entities based on
@@ -94,6 +96,7 @@ struct drm_sched_entity {
 	struct dma_fence                *last_scheduled;
 	struct task_struct		*last_user;
 	bool 				stopped;
+	struct completion		entity_idle;
 };
 
 /**
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index d2277e06316d..54fa457b26ab 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -147,7 +147,6 @@ struct ttm_tt;
  * holds a pointer to a persistent shmem object.
  * @ttm: TTM structure holding system pages.
  * @evicted: Whether the object was evicted without user-space knowing.
- * @cpu_writes: For synchronization. Number of cpu writers.
  * @lru: List head for the lru list.
  * @ddestroy: List head for the delayed destroy list.
  * @swap: List head for swap LRU list.
@@ -199,12 +198,6 @@ struct ttm_buffer_object {
 	bool evicted;
 
 	/**
-	 * Members protected by the bo::reserved lock only when written to.
-	 */
-
-	atomic_t cpu_writers;
-
-	/**
 	 * Members protected by the bdev::lru_lock.
 	 */
 
@@ -368,30 +361,6 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 void ttm_bo_put(struct ttm_buffer_object *bo);
 
 /**
- * ttm_bo_add_to_lru
- *
- * @bo: The buffer object.
- *
- * Add this bo to the relevant mem type lru and, if it's backed by
- * system pages (ttms) to the swap list.
- * This function must be called with struct ttm_bo_global::lru_lock held, and
- * is typically called immediately prior to unreserving a bo.
- */
-void ttm_bo_add_to_lru(struct ttm_buffer_object *bo);
-
-/**
- * ttm_bo_del_from_lru
- *
- * @bo: The buffer object.
- *
- * Remove this bo from all lru lists used to lookup and reserve an object.
- * This function must be called with struct ttm_bo_global::lru_lock held,
- * and is usually called just immediately after the bo has been reserved to
- * avoid recursive reservation from lru lists.
- */
-void ttm_bo_del_from_lru(struct ttm_buffer_object *bo);
-
-/**
  * ttm_bo_move_to_lru_tail
  *
  * @bo: The buffer object.
@@ -442,31 +411,6 @@ bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 			      const struct ttm_place *place);
 
 /**
- * ttm_bo_synccpu_write_grab
- *
- * @bo: The buffer object:
- * @no_wait: Return immediately if buffer is busy.
- *
- * Synchronizes a buffer object for CPU RW access. This means
- * command submission that affects the buffer will return -EBUSY
- * until ttm_bo_synccpu_write_release is called.
- *
- * Returns
- * -EBUSY if the buffer is busy and no_wait is true.
- * -ERESTARTSYS if interrupted by a signal.
- */
-int ttm_bo_synccpu_write_grab(struct ttm_buffer_object *bo, bool no_wait);
-
-/**
- * ttm_bo_synccpu_write_release:
- *
- * @bo : The buffer object.
- *
- * Releases a synccpu lock.
- */
-void ttm_bo_synccpu_write_release(struct ttm_buffer_object *bo);
-
-/**
  * ttm_bo_acc_size
  *
  * @bdev: Pointer to a ttm_bo_device struct.
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 27b9d5be197f..cac7a8a0825a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -423,7 +423,6 @@ extern struct ttm_bo_global {
 	 */
 
 	struct kobject kobj;
-	struct ttm_mem_global *mem_glob;
 	struct page *dummy_read_page;
 	spinlock_t lru_lock;
 
@@ -467,7 +466,6 @@ struct ttm_bo_device {
 	 * Constant after bo device init / atomic.
 	 */
 	struct list_head device_list;
-	struct ttm_bo_global *glob;
 	struct ttm_bo_driver *driver;
 	struct ttm_mem_type_manager man[TTM_NUM_MEM_TYPES];
 
@@ -631,9 +629,6 @@ void ttm_mem_io_free_vm(struct ttm_buffer_object *bo);
 int ttm_mem_io_lock(struct ttm_mem_type_manager *man, bool interruptible);
 void ttm_mem_io_unlock(struct ttm_mem_type_manager *man);
 
-void ttm_bo_del_sub_from_lru(struct ttm_buffer_object *bo);
-void ttm_bo_add_to_lru(struct ttm_buffer_object *bo);
-
 /**
  * __ttm_bo_reserve:
  *
@@ -727,15 +722,9 @@ static inline int ttm_bo_reserve(struct ttm_buffer_object *bo,
 				 bool interruptible, bool no_wait,
 				 struct ww_acquire_ctx *ticket)
 {
-	int ret;
-
 	WARN_ON(!kref_read(&bo->kref));
 
-	ret = __ttm_bo_reserve(bo, interruptible, no_wait, ticket);
-	if (likely(ret == 0))
-		ttm_bo_del_sub_from_lru(bo);
-
-	return ret;
+	return __ttm_bo_reserve(bo, interruptible, no_wait, ticket);
 }
 
 /**
@@ -762,9 +751,7 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
 	else
 		dma_resv_lock_slow(bo->base.resv, ticket);
 
-	if (likely(ret == 0))
-		ttm_bo_del_sub_from_lru(bo);
-	else if (ret == -EINTR)
+	if (ret == -EINTR)
 		ret = -ERESTARTSYS;
 
 	return ret;
@@ -779,12 +766,9 @@ static inline int ttm_bo_reserve_slowpath(struct ttm_buffer_object *bo,
  */
 static inline void ttm_bo_unreserve(struct ttm_buffer_object *bo)
 {
-	spin_lock(&bo->bdev->glob->lru_lock);
-	if (list_empty(&bo->lru))
-		ttm_bo_add_to_lru(bo);
-	else
-		ttm_bo_move_to_lru_tail(bo, NULL);
-	spin_unlock(&bo->bdev->glob->lru_lock);
+	spin_lock(&ttm_bo_glob.lru_lock);
+	ttm_bo_move_to_lru_tail(bo, NULL);
+	spin_unlock(&ttm_bo_glob.lru_lock);
 	dma_resv_unlock(bo->base.resv);
 }
 
diff --git a/include/drm/ttm/ttm_execbuf_util.h b/include/drm/ttm/ttm_execbuf_util.h
index 7e46cc678e7e..5a19843bb80d 100644
--- a/include/drm/ttm/ttm_execbuf_util.h
+++ b/include/drm/ttm/ttm_execbuf_util.h
@@ -99,7 +99,7 @@ extern void ttm_eu_backoff_reservation(struct ww_acquire_ctx *ticket,
 
 extern int ttm_eu_reserve_buffers(struct ww_acquire_ctx *ticket,
 				  struct list_head *list, bool intr,
-				  struct list_head *dups, bool del_lru);
+				  struct list_head *dups);
 
 /**
  * function ttm_eu_fence_buffer_objects.
diff --git a/include/drm/ttm/ttm_memory.h b/include/drm/ttm/ttm_memory.h
index 3ff48a0a2d7b..c78ea99c42cf 100644
--- a/include/drm/ttm/ttm_memory.h
+++ b/include/drm/ttm/ttm_memory.h
@@ -65,7 +65,6 @@
 struct ttm_mem_zone;
 extern struct ttm_mem_global {
 	struct kobject kobj;
-	struct ttm_bo_global *bo_glob;
 	struct workqueue_struct *swap_queue;
 	struct work_struct work;
 	spinlock_t lock;
diff --git a/include/drm/ttm/ttm_page_alloc.h b/include/drm/ttm/ttm_page_alloc.h
index 4d9b019d253c..a6b6ef5f9bf4 100644
--- a/include/drm/ttm/ttm_page_alloc.h
+++ b/include/drm/ttm/ttm_page_alloc.h
@@ -74,7 +74,7 @@ void ttm_unmap_and_unpopulate_pages(struct device *dev, struct ttm_dma_tt *tt);
  */
 int ttm_page_alloc_debugfs(struct seq_file *m, void *data);
 
-#if defined(CONFIG_SWIOTLB) || defined(CONFIG_INTEL_IOMMU)
+#if defined(CONFIG_DRM_TTM_DMA_PAGE_POOL)
 /**
  * Initialize pool allocator.
  */
diff --git a/include/linux/agpgart.h b/include/linux/agpgart.h
index c6b61ca97053..21b34a96cfd8 100644
--- a/include/linux/agpgart.h
+++ b/include/linux/agpgart.h
@@ -30,8 +30,6 @@
 #include <linux/agp_backend.h>
 #include <uapi/linux/agpgart.h>
 
-#define AGPGART_MINOR 175
-
 struct agp_info {
 	struct agp_version version;	/* version of the driver        */
 	u32 bridge_id;		/* bridge vendor/device         */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b9d22338606..3bf3835d0e86 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -656,11 +656,11 @@ void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
 void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size);
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size);
 void bpf_map_charge_finish(struct bpf_map_memory *mem);
 void bpf_map_charge_move(struct bpf_map_memory *dst,
 			 struct bpf_map_memory *src);
-void *bpf_map_area_alloc(size_t size, int numa_node);
+void *bpf_map_area_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
 
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index c57e88e85c41..92d5fdc8154e 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -13,6 +13,7 @@
 #include <linux/completion.h>
 #include <linux/kobject.h>
 #include <linux/notifier.h>
+#include <linux/pm_qos.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
 
@@ -76,8 +77,10 @@ struct cpufreq_policy {
 	struct work_struct	update; /* if update_policy() needs to be
 					 * called, but you're in IRQ context */
 
-	struct dev_pm_qos_request *min_freq_req;
-	struct dev_pm_qos_request *max_freq_req;
+	struct freq_constraints	constraints;
+	struct freq_qos_request	*min_freq_req;
+	struct freq_qos_request	*max_freq_req;
+
 	struct cpufreq_frequency_table	*freq_table;
 	enum cpufreq_table_sorting freq_table_sorted;
 
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index 8557efe096dc..fa35b52e0002 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -12,26 +12,15 @@
 #define DEVCG_DEV_ALL   4  /* this represents all devices */
 
 #ifdef CONFIG_CGROUP_DEVICE
-extern int __devcgroup_check_permission(short type, u32 major, u32 minor,
-					short access);
+int devcgroup_check_permission(short type, u32 major, u32 minor,
+			       short access);
 #else
-static inline int __devcgroup_check_permission(short type, u32 major, u32 minor,
-					       short access)
+static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
+					     short access)
 { return 0; }
 #endif
 
 #if defined(CONFIG_CGROUP_DEVICE) || defined(CONFIG_CGROUP_BPF)
-static inline int devcgroup_check_permission(short type, u32 major, u32 minor,
-					     short access)
-{
-	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
-
-	if (rc)
-		return -EPERM;
-
-	return __devcgroup_check_permission(type, major, minor, access);
-}
-
 static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 {
 	short type, access = 0;
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index ec212cb27fdc..af73f835c51c 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -43,6 +43,18 @@ struct dma_buf_ops {
 	bool cache_sgt_mapping;
 
 	/**
+	 * @dynamic_mapping:
+	 *
+	 * If true the framework makes sure that the map/unmap_dma_buf
+	 * callbacks are always called with the dma_resv object locked.
+	 *
+	 * If false the framework makes sure that the map/unmap_dma_buf
+	 * callbacks are always called without the dma_resv object locked.
+	 * Mutual exclusive with @cache_sgt_mapping.
+	 */
+	bool dynamic_mapping;
+
+	/**
 	 * @attach:
 	 *
 	 * This is called from dma_buf_attach() to make sure that a given
@@ -109,6 +121,9 @@ struct dma_buf_ops {
 	 * any other kind of sharing that the exporter might wish to make
 	 * available to buffer-users.
 	 *
+	 * This is always called with the dmabuf->resv object locked when
+	 * the dynamic_mapping flag is true.
+	 *
 	 * Returns:
 	 *
 	 * A &sg_table scatter list of or the backing storage of the DMA buffer,
@@ -267,14 +282,16 @@ struct dma_buf_ops {
  * struct dma_buf - shared buffer object
  * @size: size of the buffer
  * @file: file pointer used for sharing buffers across, and for refcounting.
- * @attachments: list of dma_buf_attachment that denotes all devices attached.
+ * @attachments: list of dma_buf_attachment that denotes all devices attached,
+ *               protected by dma_resv lock.
  * @ops: dma_buf_ops associated with this buffer object.
  * @lock: used internally to serialize list manipulation, attach/detach and
- *        vmap/unmap, and accesses to name
+ *        vmap/unmap
  * @vmapping_counter: used internally to refcnt the vmaps
  * @vmap_ptr: the current vmap ptr if vmapping_counter > 0
  * @exp_name: name of the exporter; useful for debugging.
- * @name: userspace-provided name; useful for accounting and debugging.
+ * @name: userspace-provided name; useful for accounting and debugging,
+ *        protected by @resv.
  * @owner: pointer to exporter module; used for refcounting when exporter is a
  *         kernel module.
  * @list_node: node for dma_buf accounting and debugging.
@@ -323,10 +340,12 @@ struct dma_buf {
  * struct dma_buf_attachment - holds device-buffer attachment data
  * @dmabuf: buffer for this attachment.
  * @dev: device attached to the buffer.
- * @node: list of dma_buf_attachment.
+ * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf.
  * @sgt: cached mapping.
  * @dir: direction of cached mapping.
  * @priv: exporter specific attachment data.
+ * @dynamic_mapping: true if dma_buf_map/unmap_attachment() is called with the
+ * dma_resv lock held.
  *
  * This structure holds the attachment information between the dma_buf buffer
  * and its user device(s). The list contains one attachment struct per device
@@ -343,6 +362,7 @@ struct dma_buf_attachment {
 	struct list_head node;
 	struct sg_table *sgt;
 	enum dma_data_direction dir;
+	bool dynamic_mapping;
 	void *priv;
 };
 
@@ -394,10 +414,40 @@ static inline void get_dma_buf(struct dma_buf *dmabuf)
 	get_file(dmabuf->file);
 }
 
+/**
+ * dma_buf_is_dynamic - check if a DMA-buf uses dynamic mappings.
+ * @dmabuf: the DMA-buf to check
+ *
+ * Returns true if a DMA-buf exporter wants to be called with the dma_resv
+ * locked for the map/unmap callbacks, false if it doesn't wants to be called
+ * with the lock held.
+ */
+static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf)
+{
+	return dmabuf->ops->dynamic_mapping;
+}
+
+/**
+ * dma_buf_attachment_is_dynamic - check if a DMA-buf attachment uses dynamic
+ * mappinsg
+ * @attach: the DMA-buf attachment to check
+ *
+ * Returns true if a DMA-buf importer wants to call the map/unmap functions with
+ * the dma_resv lock held.
+ */
+static inline bool
+dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach)
+{
+	return attach->dynamic_mapping;
+}
+
 struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
-							struct device *dev);
+					  struct device *dev);
+struct dma_buf_attachment *
+dma_buf_dynamic_attach(struct dma_buf *dmabuf, struct device *dev,
+		       bool dynamic_mapping);
 void dma_buf_detach(struct dma_buf *dmabuf,
-				struct dma_buf_attachment *dmabuf_attach);
+		    struct dma_buf_attachment *attach);
 
 struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info);
 
@@ -409,6 +459,7 @@ struct sg_table *dma_buf_map_attachment(struct dma_buf_attachment *,
 					enum dma_data_direction);
 void dma_buf_unmap_attachment(struct dma_buf_attachment *, struct sg_table *,
 				enum dma_data_direction);
+void dma_buf_move_notify(struct dma_buf *dma_buf);
 int dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 			     enum dma_data_direction dir);
 int dma_buf_end_cpu_access(struct dma_buf *dma_buf,
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 6c809440f319..4cf02ecd67de 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -204,6 +204,12 @@ static inline int ddebug_dyndbg_module_param_cb(char *param, char *val,
 	do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0)
 #define dynamic_dev_dbg(dev, fmt, ...)					\
 	do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0)
+#define dynamic_hex_dump(prefix_str, prefix_type, rowsize,		\
+			 groupsize, buf, len, ascii)			\
+	do { if (0)							\
+		print_hex_dump(KERN_DEBUG, prefix_str, prefix_type,	\
+				rowsize, groupsize, buf, len, ascii);	\
+	} while (0)
 #endif
 
 #endif
diff --git a/include/linux/efi.h b/include/linux/efi.h
index bd3837022307..d87acf62958e 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1579,9 +1579,22 @@ char *efi_convert_cmdline(efi_system_table_t *sys_table_arg,
 efi_status_t efi_get_memory_map(efi_system_table_t *sys_table_arg,
 				struct efi_boot_memmap *map);
 
+efi_status_t efi_low_alloc_above(efi_system_table_t *sys_table_arg,
+				 unsigned long size, unsigned long align,
+				 unsigned long *addr, unsigned long min);
+
+static inline
 efi_status_t efi_low_alloc(efi_system_table_t *sys_table_arg,
 			   unsigned long size, unsigned long align,
-			   unsigned long *addr);
+			   unsigned long *addr)
+{
+	/*
+	 * Don't allocate at 0x0. It will confuse code that
+	 * checks pointers against NULL. Skip the first 8
+	 * bytes so we start at a nice even number.
+	 */
+	return efi_low_alloc_above(sys_table_arg, size, align, addr, 0x8);
+}
 
 efi_status_t efi_high_alloc(efi_system_table_t *sys_table_arg,
 			    unsigned long size, unsigned long align,
@@ -1592,7 +1605,8 @@ efi_status_t efi_relocate_kernel(efi_system_table_t *sys_table_arg,
 				 unsigned long image_size,
 				 unsigned long alloc_size,
 				 unsigned long preferred_addr,
-				 unsigned long alignment);
+				 unsigned long alignment,
+				 unsigned long min_addr);
 
 efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 				  efi_loaded_image_t *image,
diff --git a/include/linux/export.h b/include/linux/export.h
index 621158ecd2e2..941d075f03d6 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -18,8 +18,6 @@ extern struct module __this_module;
 #define THIS_MODULE ((struct module *)0)
 #endif
 
-#define NS_SEPARATOR "."
-
 #ifdef CONFIG_MODVERSIONS
 /* Mark the CRC weak since genksyms apparently decides not to
  * generate a checksums for some symbols */
@@ -48,11 +46,11 @@ extern struct module __this_module;
  * absolute relocations that require runtime processing on relocatable
  * kernels.
  */
-#define __KSYMTAB_ENTRY_NS(sym, sec, ns)				\
+#define __KSYMTAB_ENTRY_NS(sym, sec)					\
 	__ADDRESSABLE(sym)						\
 	asm("	.section \"___ksymtab" sec "+" #sym "\", \"a\"	\n"	\
 	    "	.balign	4					\n"	\
-	    "__ksymtab_" #ns NS_SEPARATOR #sym ":		\n"	\
+	    "__ksymtab_" #sym ":				\n"	\
 	    "	.long	" #sym "- .				\n"	\
 	    "	.long	__kstrtab_" #sym "- .			\n"	\
 	    "	.long	__kstrtabns_" #sym "- .			\n"	\
@@ -74,16 +72,14 @@ struct kernel_symbol {
 	int namespace_offset;
 };
 #else
-#define __KSYMTAB_ENTRY_NS(sym, sec, ns)				\
-	static const struct kernel_symbol __ksymtab_##sym##__##ns	\
-	asm("__ksymtab_" #ns NS_SEPARATOR #sym)				\
+#define __KSYMTAB_ENTRY_NS(sym, sec)					\
+	static const struct kernel_symbol __ksymtab_##sym		\
 	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
 	__aligned(sizeof(void *))					\
 	= { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym }
 
 #define __KSYMTAB_ENTRY(sym, sec)					\
 	static const struct kernel_symbol __ksymtab_##sym		\
-	asm("__ksymtab_" #sym)						\
 	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
 	__aligned(sizeof(void *))					\
 	= { (unsigned long)&sym, __kstrtab_##sym, NULL }
@@ -115,7 +111,7 @@ struct kernel_symbol {
 	static const char __kstrtabns_##sym[]				\
 	__attribute__((section("__ksymtab_strings"), used, aligned(1)))	\
 	= #ns;								\
-	__KSYMTAB_ENTRY_NS(sym, sec, ns)
+	__KSYMTAB_ENTRY_NS(sym, sec)
 
 #define ___EXPORT_SYMBOL(sym, sec)					\
 	___export_symbol_common(sym, sec);				\
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2ce57645f3cd..0367a75f873b 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1099,7 +1099,6 @@ static inline void bpf_get_prog_name(const struct bpf_prog *prog, char *sym)
 
 #endif /* CONFIG_BPF_JIT */
 
-void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp);
 void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);
 
 #define BPF_ANC		BIT(15)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index fb07b503dc45..61f2f6ff9467 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -325,6 +325,29 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
 }
 
+/**
+ * gfpflags_normal_context - is gfp_flags a normal sleepable context?
+ * @gfp_flags: gfp_flags to test
+ *
+ * Test whether @gfp_flags indicates that the allocation is from the
+ * %current context and allowed to sleep.
+ *
+ * An allocation being allowed to block doesn't mean it owns the %current
+ * context.  When direct reclaim path tries to allocate memory, the
+ * allocation context is nested inside whatever %current was doing at the
+ * time of the original allocation.  The nested allocation may be allowed
+ * to block but modifying anything %current owns can corrupt the outer
+ * context's expectations.
+ *
+ * %true result from this function indicates that the allocation context
+ * can sleep and use anything that's associated with %current.
+ */
+static inline bool gfpflags_normal_context(const gfp_t gfp_flags)
+{
+	return (gfp_flags & (__GFP_DIRECT_RECLAIM | __GFP_MEMALLOC)) ==
+		__GFP_DIRECT_RECLAIM;
+}
+
 #ifdef CONFIG_HIGHMEM
 #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
 #else
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 4ec8986e5dfb..ac6e946b6767 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -185,7 +185,7 @@ static inline void idr_preload_end(void)
  * is convenient for a "not found" value.
  */
 #define idr_for_each_entry(idr, entry, id)			\
-	for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; ++id)
+	for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U)
 
 /**
  * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type.
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 2e55e4cdbd8a..a367ead4bf4b 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -29,7 +29,6 @@ struct macvlan_dev {
 	netdev_features_t	set_features;
 	enum macvlan_mode	mode;
 	u16			flags;
-	int			nest_level;
 	unsigned int		macaddr_count;
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll		*netpoll;
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 06faa066496f..ec7e4bd07f82 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -223,6 +223,7 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
+	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 244278d5c222..b05e855f1ddd 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -182,7 +182,6 @@ struct vlan_dev_priv {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	struct netpoll				*netpoll;
 #endif
-	unsigned int				nest_level;
 };
 
 static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
@@ -221,11 +220,6 @@ extern void vlan_vids_del_by_dev(struct net_device *dev,
 
 extern bool vlan_uses_dev(const struct net_device *dev);
 
-static inline int vlan_get_encap_level(struct net_device *dev)
-{
-	BUG_ON(!is_vlan_dev(dev));
-	return vlan_dev_priv(dev)->nest_level;
-}
 #else
 static inline struct net_device *
 __vlan_find_dev_deep_rcu(struct net_device *real_dev,
@@ -295,11 +289,6 @@ static inline bool vlan_uses_dev(const struct net_device *dev)
 {
 	return false;
 }
-static inline int vlan_get_encap_level(struct net_device *dev)
-{
-	BUG();
-	return 0;
-}
 #endif
 
 /**
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 3247a3dc7934..6f2ca42152a0 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -33,6 +33,7 @@
 #define SGI_MMTIMER		153
 #define STORE_QUEUE_MINOR	155	/* unused */
 #define I2O_MINOR		166
+#define AGPGART_MINOR		175
 #define HWRNG_MINOR		183
 #define MICROCODE_MINOR		184
 #define IRNET_MINOR		187
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 138c50d5a353..0836fe232f97 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1545,9 +1545,8 @@ struct mlx5_ifc_extended_dest_format_bits {
 };
 
 union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits {
-	struct mlx5_ifc_dest_format_struct_bits dest_format_struct;
+	struct mlx5_ifc_extended_dest_format_bits extended_dest_format;
 	struct mlx5_ifc_flow_counter_list_bits flow_counter_list;
-	u8         reserved_at_0[0x40];
 };
 
 struct mlx5_ifc_fte_match_param_bits {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cc292273e6ba..a2adf95b3f9c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -695,11 +695,6 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 
 extern void kvfree(const void *addr);
 
-static inline atomic_t *compound_mapcount_ptr(struct page *page)
-{
-	return &page[1].compound_mapcount;
-}
-
 static inline int compound_mapcount(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 2222fa795284..270aa8fd2800 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -221,6 +221,11 @@ struct page {
 #endif
 } _struct_page_alignment;
 
+static inline atomic_t *compound_mapcount_ptr(struct page *page)
+{
+	return &page[1].compound_mapcount;
+}
+
 /*
  * Used for sizing the vmemmap region on some architectures
  */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9eda1c31d1f7..c20f190b4c18 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -925,6 +925,7 @@ struct dev_ifalias {
 struct devlink;
 struct tlsdev_ops;
 
+
 /*
  * This structure defines the management hooks for network devices.
  * The following hooks can be defined; unless noted otherwise, they are
@@ -1421,7 +1422,6 @@ struct net_device_ops {
 	void			(*ndo_dfwd_del_station)(struct net_device *pdev,
 							void *priv);
 
-	int			(*ndo_get_lock_subclass)(struct net_device *dev);
 	int			(*ndo_set_tx_maxrate)(struct net_device *dev,
 						      int queue_index,
 						      u32 maxrate);
@@ -1649,6 +1649,8 @@ enum netdev_priv_flags {
  * 	@perm_addr:		Permanent hw address
  * 	@addr_assign_type:	Hw address assignment type
  * 	@addr_len:		Hardware address length
+ *	@upper_level:		Maximum depth level of upper devices.
+ *	@lower_level:		Maximum depth level of lower devices.
  *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
@@ -1758,9 +1760,13 @@ enum netdev_priv_flags {
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
- *
- *	@qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock
- *	@qdisc_running_key: lockdep class annotating Qdisc->running seqcount
+ *	@qdisc_tx_busylock_key: lockdep class annotating Qdisc->busylock
+				spinlock
+ *	@qdisc_running_key:	lockdep class annotating Qdisc->running seqcount
+ *	@qdisc_xmit_lock_key:	lockdep class annotating
+ *				netdev_queue->_xmit_lock spinlock
+ *	@addr_list_lock_key:	lockdep class annotating
+ *				net_device->addr_list_lock spinlock
  *
  *	@proto_down:	protocol port state information can be sent to the
  *			switch driver and used to set the phys state of the
@@ -1875,6 +1881,8 @@ struct net_device {
 	unsigned char		perm_addr[MAX_ADDR_LEN];
 	unsigned char		addr_assign_type;
 	unsigned char		addr_len;
+	unsigned char		upper_level;
+	unsigned char		lower_level;
 	unsigned short		neigh_priv_len;
 	unsigned short          dev_id;
 	unsigned short          dev_port;
@@ -2045,8 +2053,10 @@ struct net_device {
 #endif
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
-	struct lock_class_key	*qdisc_tx_busylock;
-	struct lock_class_key	*qdisc_running_key;
+	struct lock_class_key	qdisc_tx_busylock_key;
+	struct lock_class_key	qdisc_running_key;
+	struct lock_class_key	qdisc_xmit_lock_key;
+	struct lock_class_key	addr_list_lock_key;
 	bool			proto_down;
 	unsigned		wol_enabled:1;
 };
@@ -2124,23 +2134,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
-#define netdev_lockdep_set_classes(dev)				\
-{								\
-	static struct lock_class_key qdisc_tx_busylock_key;	\
-	static struct lock_class_key qdisc_running_key;		\
-	static struct lock_class_key qdisc_xmit_lock_key;	\
-	static struct lock_class_key dev_addr_list_lock_key;	\
-	unsigned int i;						\
-								\
-	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
-	(dev)->qdisc_running_key = &qdisc_running_key;		\
-	lockdep_set_class(&(dev)->addr_list_lock,		\
-			  &dev_addr_list_lock_key); 		\
-	for (i = 0; i < (dev)->num_tx_queues; i++)		\
-		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
-				  &qdisc_xmit_lock_key);	\
-}
-
 u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
@@ -3139,6 +3132,7 @@ static inline void netif_stop_queue(struct net_device *dev)
 }
 
 void netif_tx_stop_all_queues(struct net_device *dev);
+void netdev_update_lockdep_key(struct net_device *dev);
 
 static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
 {
@@ -4056,16 +4050,6 @@ static inline void netif_addr_lock(struct net_device *dev)
 	spin_lock(&dev->addr_list_lock);
 }
 
-static inline void netif_addr_lock_nested(struct net_device *dev)
-{
-	int subclass = SINGLE_DEPTH_NESTING;
-
-	if (dev->netdev_ops->ndo_get_lock_subclass)
-		subclass = dev->netdev_ops->ndo_get_lock_subclass(dev);
-
-	spin_lock_nested(&dev->addr_list_lock, subclass);
-}
-
 static inline void netif_addr_lock_bh(struct net_device *dev)
 {
 	spin_lock_bh(&dev->addr_list_lock);
@@ -4329,6 +4313,16 @@ int netdev_master_upper_dev_link(struct net_device *dev,
 				 struct netlink_ext_ack *extack);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev,
+				   struct netlink_ext_ack *extack);
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev);
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+				  struct net_device *new_dev,
+				  struct net_device *dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
@@ -4340,7 +4334,6 @@ void netdev_lower_state_changed(struct net_device *lower_dev,
 extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly;
 void netdev_rss_key_fill(void *buffer, size_t len);
 
-int dev_get_nest_level(struct net_device *dev);
 int skb_checksum_help(struct sk_buff *skb);
 int skb_crc32c_csum_help(struct sk_buff *skb);
 int skb_csum_hwoffload_help(struct sk_buff *skb,
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f91cb8898ff0..1bf83c8fcaa7 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -622,12 +622,28 @@ static inline int PageTransCompound(struct page *page)
  *
  * Unlike PageTransCompound, this is safe to be called only while
  * split_huge_pmd() cannot run from under us, like if protected by the
- * MMU notifier, otherwise it may result in page->_mapcount < 0 false
+ * MMU notifier, otherwise it may result in page->_mapcount check false
  * positives.
+ *
+ * We have to treat page cache THP differently since every subpage of it
+ * would get _mapcount inc'ed once it is PMD mapped.  But, it may be PTE
+ * mapped in the current process so comparing subpage's _mapcount to
+ * compound_mapcount to filter out PTE mapped case.
  */
 static inline int PageTransCompoundMap(struct page *page)
 {
-	return PageTransCompound(page) && atomic_read(&page->_mapcount) < 0;
+	struct page *head;
+
+	if (!PageTransCompound(page))
+		return 0;
+
+	if (PageAnon(page))
+		return atomic_read(&page->_mapcount) < 0;
+
+	head = compound_head(page);
+	/* File THP is PMD mapped and not PTE mapped */
+	return atomic_read(&page->_mapcount) ==
+	       atomic_read(compound_mapcount_ptr(head));
 }
 
 /*
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 61448c19a132..68ccc5b1913b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -292,7 +292,7 @@ struct pmu {
 	 *  -EBUSY	-- @event is for this PMU but PMU temporarily unavailable
 	 *  -EINVAL	-- @event is for this PMU but @event is not valid
 	 *  -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported
-	 *  -EACCESS	-- @event is for this PMU, @event is valid, but no privilidges
+	 *  -EACCES	-- @event is for this PMU, @event is valid, but no privileges
 	 *
 	 *  0		-- @event is for this PMU and valid
 	 *
diff --git a/include/linux/platform_data/dma-imx-sdma.h b/include/linux/platform_data/dma-imx-sdma.h
index 6eaa53cef0bd..30e676b36b24 100644
--- a/include/linux/platform_data/dma-imx-sdma.h
+++ b/include/linux/platform_data/dma-imx-sdma.h
@@ -51,7 +51,10 @@ struct sdma_script_start_addrs {
 	/* End of v2 array */
 	s32 zcanfd_2_mcu_addr;
 	s32 zqspi_2_mcu_addr;
+	s32 mcu_2_ecspi_addr;
 	/* End of v3 array */
+	s32 mcu_2_zqspi_addr;
+	/* End of v4 array */
 };
 
 /**
diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h
index 222c3e01397c..ebf5ef17cc2a 100644
--- a/include/linux/pm_qos.h
+++ b/include/linux/pm_qos.h
@@ -34,8 +34,6 @@ enum pm_qos_flags_status {
 #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT	PM_QOS_LATENCY_ANY
 #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS	PM_QOS_LATENCY_ANY_NS
 #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE	0
-#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE	0
-#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE	(-1)
 #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT	(-1)
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
@@ -54,8 +52,6 @@ struct pm_qos_flags_request {
 enum dev_pm_qos_req_type {
 	DEV_PM_QOS_RESUME_LATENCY = 1,
 	DEV_PM_QOS_LATENCY_TOLERANCE,
-	DEV_PM_QOS_MIN_FREQUENCY,
-	DEV_PM_QOS_MAX_FREQUENCY,
 	DEV_PM_QOS_FLAGS,
 };
 
@@ -97,14 +93,10 @@ struct pm_qos_flags {
 struct dev_pm_qos {
 	struct pm_qos_constraints resume_latency;
 	struct pm_qos_constraints latency_tolerance;
-	struct pm_qos_constraints min_frequency;
-	struct pm_qos_constraints max_frequency;
 	struct pm_qos_flags flags;
 	struct dev_pm_qos_request *resume_latency_req;
 	struct dev_pm_qos_request *latency_tolerance_req;
 	struct dev_pm_qos_request *flags_req;
-	struct dev_pm_qos_request *min_frequency_req;
-	struct dev_pm_qos_request *max_frequency_req;
 };
 
 /* Action requested to pm_qos_update_target */
@@ -199,10 +191,6 @@ static inline s32 dev_pm_qos_read_value(struct device *dev,
 	switch (type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
 		return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
-	case DEV_PM_QOS_MIN_FREQUENCY:
-		return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE;
-	case DEV_PM_QOS_MAX_FREQUENCY:
-		return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE;
 	default:
 		WARN_ON(1);
 		return 0;
@@ -267,4 +255,48 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev)
 }
 #endif
 
+#define FREQ_QOS_MIN_DEFAULT_VALUE	0
+#define FREQ_QOS_MAX_DEFAULT_VALUE	(-1)
+
+enum freq_qos_req_type {
+	FREQ_QOS_MIN = 1,
+	FREQ_QOS_MAX,
+};
+
+struct freq_constraints {
+	struct pm_qos_constraints min_freq;
+	struct blocking_notifier_head min_freq_notifiers;
+	struct pm_qos_constraints max_freq;
+	struct blocking_notifier_head max_freq_notifiers;
+};
+
+struct freq_qos_request {
+	enum freq_qos_req_type type;
+	struct plist_node pnode;
+	struct freq_constraints *qos;
+};
+
+static inline int freq_qos_request_active(struct freq_qos_request *req)
+{
+	return !IS_ERR_OR_NULL(req->qos);
+}
+
+void freq_constraints_init(struct freq_constraints *qos);
+
+s32 freq_qos_read_value(struct freq_constraints *qos,
+			enum freq_qos_req_type type);
+
+int freq_qos_add_request(struct freq_constraints *qos,
+			 struct freq_qos_request *req,
+			 enum freq_qos_req_type type, s32 value);
+int freq_qos_update_request(struct freq_qos_request *req, s32 new_value);
+int freq_qos_remove_request(struct freq_qos_request *req);
+
+int freq_qos_add_notifier(struct freq_constraints *qos,
+			  enum freq_qos_req_type type,
+			  struct notifier_block *notifier);
+int freq_qos_remove_notifier(struct freq_constraints *qos,
+			     enum freq_qos_req_type type,
+			     struct notifier_block *notifier);
+
 #endif
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 2d5eff506e13..04382e1798e4 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -24,6 +24,26 @@ struct qcom_scm_vmperm {
 	int perm;
 };
 
+enum qcom_scm_ocmem_client {
+	QCOM_SCM_OCMEM_UNUSED_ID = 0x0,
+	QCOM_SCM_OCMEM_GRAPHICS_ID,
+	QCOM_SCM_OCMEM_VIDEO_ID,
+	QCOM_SCM_OCMEM_LP_AUDIO_ID,
+	QCOM_SCM_OCMEM_SENSORS_ID,
+	QCOM_SCM_OCMEM_OTHER_OS_ID,
+	QCOM_SCM_OCMEM_DEBUG_ID,
+};
+
+enum qcom_scm_sec_dev_id {
+	QCOM_SCM_MDSS_DEV_ID    = 1,
+	QCOM_SCM_OCMEM_DEV_ID   = 5,
+	QCOM_SCM_PCIE0_DEV_ID   = 11,
+	QCOM_SCM_PCIE1_DEV_ID   = 12,
+	QCOM_SCM_GFX_DEV_ID     = 18,
+	QCOM_SCM_UFS_DEV_ID     = 19,
+	QCOM_SCM_ICE_DEV_ID     = 20,
+};
+
 #define QCOM_SCM_VMID_HLOS       0x3
 #define QCOM_SCM_VMID_MSS_MSA    0xF
 #define QCOM_SCM_VMID_WLAN       0x18
@@ -41,6 +61,11 @@ extern bool qcom_scm_is_available(void);
 extern bool qcom_scm_hdcp_available(void);
 extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
 			     u32 *resp);
+extern bool qcom_scm_ocmem_lock_available(void);
+extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset,
+			       u32 size, u32 mode);
+extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset,
+				 u32 size);
 extern bool qcom_scm_pas_supported(u32 peripheral);
 extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata,
 				   size_t size);
@@ -55,6 +80,7 @@ extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
 extern void qcom_scm_cpu_power_down(u32 flags);
 extern u32 qcom_scm_get_version(void);
 extern int qcom_scm_set_remote_state(u32 state, u32 id);
+extern bool qcom_scm_restore_sec_cfg_available(void);
 extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
 extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
 extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index b5116013f27e..63e62372443a 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -316,24 +316,6 @@ radix_tree_iter_lookup(const struct radix_tree_root *root,
 }
 
 /**
- * radix_tree_iter_find - find a present entry
- * @root: radix tree root
- * @iter: iterator state
- * @index: start location
- *
- * This function returns the slot containing the entry with the lowest index
- * which is at least @index.  If @index is larger than any present entry, this
- * function returns NULL.  The @iter is updated to describe the entry found.
- */
-static inline void __rcu **
-radix_tree_iter_find(const struct radix_tree_root *root,
-			struct radix_tree_iter *iter, unsigned long index)
-{
-	radix_tree_iter_init(iter, index);
-	return radix_tree_next_chunk(root, iter, 0);
-}
-
-/**
  * radix_tree_iter_retry - retry this chunk of the iteration
  * @iter:	iterator state
  *
diff --git a/include/linux/reset-controller.h b/include/linux/reset-controller.h
index 9326d671b6e6..eaae6b4e9f24 100644
--- a/include/linux/reset-controller.h
+++ b/include/linux/reset-controller.h
@@ -7,7 +7,7 @@
 struct reset_controller_dev;
 
 /**
- * struct reset_control_ops
+ * struct reset_control_ops - reset controller driver callbacks
  *
  * @reset: for self-deasserting resets, does all necessary
  *         things to reset the device
@@ -33,7 +33,7 @@ struct of_phandle_args;
  * @provider: name of the reset controller device controlling this reset line
  * @index: ID of the reset controller in the reset controller device
  * @dev_id: name of the device associated with this reset line
- * @con_id name of the reset line (can be NULL)
+ * @con_id: name of the reset line (can be NULL)
  */
 struct reset_control_lookup {
 	struct list_head list;
diff --git a/include/linux/reset.h b/include/linux/reset.h
index e7793fc0fa93..eb597e8aa430 100644
--- a/include/linux/reset.h
+++ b/include/linux/reset.h
@@ -143,7 +143,7 @@ static inline int device_reset_optional(struct device *dev)
  * If this function is called more than once for the same reset_control it will
  * return -EBUSY.
  *
- * See reset_control_get_shared for details on shared references to
+ * See reset_control_get_shared() for details on shared references to
  * reset-controls.
  *
  * Use of id names is optional.
diff --git a/include/linux/security.h b/include/linux/security.h
index a8d59d612d27..9df7547afc0c 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -105,6 +105,7 @@ enum lockdown_reason {
 	LOCKDOWN_NONE,
 	LOCKDOWN_MODULE_SIGNATURE,
 	LOCKDOWN_DEV_MEM,
+	LOCKDOWN_EFI_TEST,
 	LOCKDOWN_KEXEC,
 	LOCKDOWN_HIBERNATION,
 	LOCKDOWN_PCI_ACCESS,
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7914fdaf4226..64a395c7f689 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1354,7 +1354,8 @@ static inline __u32 skb_get_hash_flowi6(struct sk_buff *skb, const struct flowi6
 	return skb->hash;
 }
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb);
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+			   const siphash_key_t *perturb);
 
 static inline __u32 skb_get_hash_raw(const struct sk_buff *skb)
 {
@@ -1495,6 +1496,19 @@ static inline int skb_queue_empty(const struct sk_buff_head *list)
 }
 
 /**
+ *	skb_queue_empty_lockless - check if a queue is empty
+ *	@list: queue head
+ *
+ *	Returns true if the queue is empty, false otherwise.
+ *	This variant can be used in lockless contexts.
+ */
+static inline bool skb_queue_empty_lockless(const struct sk_buff_head *list)
+{
+	return READ_ONCE(list->next) == (const struct sk_buff *) list;
+}
+
+
+/**
  *	skb_queue_is_last - check if skb is the last entry in the queue
  *	@list: queue head
  *	@skb: buffer
@@ -1847,9 +1861,11 @@ static inline void __skb_insert(struct sk_buff *newsk,
 				struct sk_buff *prev, struct sk_buff *next,
 				struct sk_buff_head *list)
 {
-	newsk->next = next;
-	newsk->prev = prev;
-	next->prev  = prev->next = newsk;
+	/* see skb_queue_empty_lockless() for the opposite READ_ONCE() */
+	WRITE_ONCE(newsk->next, next);
+	WRITE_ONCE(newsk->prev, prev);
+	WRITE_ONCE(next->prev, newsk);
+	WRITE_ONCE(prev->next, newsk);
 	list->qlen++;
 }
 
@@ -1860,11 +1876,11 @@ static inline void __skb_queue_splice(const struct sk_buff_head *list,
 	struct sk_buff *first = list->next;
 	struct sk_buff *last = list->prev;
 
-	first->prev = prev;
-	prev->next = first;
+	WRITE_ONCE(first->prev, prev);
+	WRITE_ONCE(prev->next, first);
 
-	last->next = next;
-	next->prev = last;
+	WRITE_ONCE(last->next, next);
+	WRITE_ONCE(next->prev, last);
 }
 
 /**
@@ -2005,8 +2021,8 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list)
 	next	   = skb->next;
 	prev	   = skb->prev;
 	skb->next  = skb->prev = NULL;
-	next->prev = prev;
-	prev->next = next;
+	WRITE_ONCE(next->prev, prev);
+	WRITE_ONCE(prev->next, next);
 }
 
 /**
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h
index e4b3fb4bb77c..ce7055259877 100644
--- a/include/linux/skmsg.h
+++ b/include/linux/skmsg.h
@@ -139,6 +139,11 @@ static inline void sk_msg_apply_bytes(struct sk_psock *psock, u32 bytes)
 	}
 }
 
+static inline u32 sk_msg_iter_dist(u32 start, u32 end)
+{
+	return end >= start ? end - start : end + (MAX_MSG_FRAGS - start);
+}
+
 #define sk_msg_iter_var_prev(var)			\
 	do {						\
 		if (var == 0)				\
@@ -198,9 +203,7 @@ static inline u32 sk_msg_elem_used(const struct sk_msg *msg)
 	if (sk_msg_full(msg))
 		return MAX_MSG_FRAGS;
 
-	return msg->sg.end >= msg->sg.start ?
-		msg->sg.end - msg->sg.start :
-		msg->sg.end + (MAX_MSG_FRAGS - msg->sg.start);
+	return sk_msg_iter_dist(msg->sg.start, msg->sg.end);
 }
 
 static inline struct scatterlist *sk_msg_elem(struct sk_msg *msg, int which)
diff --git a/include/linux/socket.h b/include/linux/socket.h
index fc0bed59fc84..4049d9755cf1 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -263,7 +263,7 @@ struct ucred {
 #define PF_MAX		AF_MAX
 
 /* Maximum queue length specifiable by listen.  */
-#define SOMAXCONN	128
+#define SOMAXCONN	4096
 
 /* Flags we can use with send/ and recv.
    Added those for 1003.1g not all are supported yet
diff --git a/include/linux/sunrpc/bc_xprt.h b/include/linux/sunrpc/bc_xprt.h
index 87d27e13d885..d796058cdff2 100644
--- a/include/linux/sunrpc/bc_xprt.h
+++ b/include/linux/sunrpc/bc_xprt.h
@@ -64,6 +64,11 @@ static inline int xprt_setup_backchannel(struct rpc_xprt *xprt,
 	return 0;
 }
 
+static inline void xprt_destroy_backchannel(struct rpc_xprt *xprt,
+					    unsigned int max_reqs)
+{
+}
+
 static inline bool svc_is_backchannel(const struct svc_rqst *rqstp)
 {
 	return false;
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index 5420817ed317..fa7ee503fb76 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -196,9 +196,9 @@ struct bin_attribute {
 	.size	= _size,						\
 }
 
-#define __BIN_ATTR_WO(_name) {						\
+#define __BIN_ATTR_WO(_name, _size) {					\
 	.attr	= { .name = __stringify(_name), .mode = 0200 },		\
-	.store	= _name##_store,					\
+	.write	= _name##_write,					\
 	.size	= _size,						\
 }
 
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 4c7781f4b29b..07875ccc7bb5 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -48,7 +48,6 @@ struct virtio_vsock_sock {
 
 struct virtio_vsock_pkt {
 	struct virtio_vsock_hdr	hdr;
-	struct work_struct work;
 	struct list_head list;
 	/* socket refcnt not held, only use for cancellation */
 	struct vsock_sock *vsk;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index f7fe45689142..3d56b026bb9e 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -159,7 +159,6 @@ struct slave {
 	unsigned long target_last_arp_rx[BOND_MAX_ARP_TARGETS];
 	s8     link;		/* one of BOND_LINK_XXXX */
 	s8     link_new_state;	/* one of BOND_LINK_XXXX */
-	s8     new_link;
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
 	       inactive:1, /* indicates inactive slave */
@@ -203,7 +202,6 @@ struct bonding {
 	struct   slave __rcu *primary_slave;
 	struct   bond_up_slave __rcu *slave_arr; /* Array of usable slaves */
 	bool     force_primary;
-	u32      nest_level;
 	s32      slave_cnt; /* never change this value outside the attach/detach wrappers */
 	int     (*recv_probe)(const struct sk_buff *, struct bonding *,
 			      struct slave *);
@@ -239,6 +237,7 @@ struct bonding {
 	struct	 dentry *debug_dir;
 #endif /* CONFIG_DEBUG_FS */
 	struct rtnl_link_stats64 bond_stats;
+	struct lock_class_key stats_lock_key;
 };
 
 #define bond_slave_get_rcu(dev) \
@@ -549,7 +548,7 @@ static inline void bond_propose_link_state(struct slave *slave, int state)
 
 static inline void bond_commit_link_state(struct slave *slave, bool notify)
 {
-	if (slave->link == slave->link_new_state)
+	if (slave->link_new_state == BOND_LINK_NOCHANGE)
 		return;
 
 	slave->link = slave->link_new_state;
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 127a5c4e3699..86e028388bad 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -122,7 +122,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	sk->sk_napi_id = skb->napi_id;
+	WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
 #endif
 	sk_rx_queue_set(sk, skb);
 }
@@ -132,8 +132,8 @@ static inline void sk_mark_napi_id_once(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
-	if (!sk->sk_napi_id)
-		sk->sk_napi_id = skb->napi_id;
+	if (!READ_ONCE(sk->sk_napi_id))
+		WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
 #endif
 }
 
diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 90bd210be060..5cd12276ae21 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/in6.h>
+#include <linux/siphash.h>
 #include <uapi/linux/if_ether.h>
 
 /**
@@ -276,7 +277,7 @@ struct flow_keys_basic {
 struct flow_keys {
 	struct flow_dissector_key_control control;
 #define FLOW_KEYS_HASH_START_FIELD basic
-	struct flow_dissector_key_basic basic;
+	struct flow_dissector_key_basic basic __aligned(SIPHASH_ALIGNMENT);
 	struct flow_dissector_key_tags tags;
 	struct flow_dissector_key_vlan vlan;
 	struct flow_dissector_key_vlan cvlan;
diff --git a/include/net/fq.h b/include/net/fq.h
index d126b5d20261..2ad85e683041 100644
--- a/include/net/fq.h
+++ b/include/net/fq.h
@@ -69,7 +69,7 @@ struct fq {
 	struct list_head backlogs;
 	spinlock_t lock;
 	u32 flows_cnt;
-	u32 perturbation;
+	siphash_key_t	perturbation;
 	u32 limit;
 	u32 memory_limit;
 	u32 memory_usage;
diff --git a/include/net/fq_impl.h b/include/net/fq_impl.h
index be40a4b327e3..38a9a3d1222b 100644
--- a/include/net/fq_impl.h
+++ b/include/net/fq_impl.h
@@ -108,7 +108,7 @@ begin:
 
 static u32 fq_flow_idx(struct fq *fq, struct sk_buff *skb)
 {
-	u32 hash = skb_get_hash_perturb(skb, fq->perturbation);
+	u32 hash = skb_get_hash_perturb(skb, &fq->perturbation);
 
 	return reciprocal_scale(hash, fq->flows_cnt);
 }
@@ -308,12 +308,12 @@ static int fq_init(struct fq *fq, int flows_cnt)
 	INIT_LIST_HEAD(&fq->backlogs);
 	spin_lock_init(&fq->lock);
 	fq->flows_cnt = max_t(u32, flows_cnt, 1);
-	fq->perturbation = prandom_u32();
+	get_random_bytes(&fq->perturbation, sizeof(fq->perturbation));
 	fq->quantum = 300;
 	fq->limit = 8192;
 	fq->memory_limit = 16 << 20; /* 16 MBytes */
 
-	fq->flows = kcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL);
+	fq->flows = kvcalloc(fq->flows_cnt, sizeof(fq->flows[0]), GFP_KERNEL);
 	if (!fq->flows)
 		return -ENOMEM;
 
@@ -331,7 +331,7 @@ static void fq_reset(struct fq *fq,
 	for (i = 0; i < fq->flows_cnt; i++)
 		fq_flow_reset(fq, &fq->flows[i], free_func);
 
-	kfree(fq->flows);
+	kvfree(fq->flows);
 	fq->flows = NULL;
 }
 
diff --git a/include/net/hwbm.h b/include/net/hwbm.h
index 81643cf8a1c4..c81444611a22 100644
--- a/include/net/hwbm.h
+++ b/include/net/hwbm.h
@@ -21,9 +21,13 @@ void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf);
 int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp);
 int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num);
 #else
-void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {}
-int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp) { return 0; }
-int hwbm_pool_add(struct hwbm_pool *bm_pool, unsigned int buf_num)
+static inline void hwbm_buf_free(struct hwbm_pool *bm_pool, void *buf) {}
+
+static inline int hwbm_pool_refill(struct hwbm_pool *bm_pool, gfp_t gfp)
+{ return 0; }
+
+static inline int hwbm_pool_add(struct hwbm_pool *bm_pool,
+				unsigned int buf_num)
 { return 0; }
 #endif /* CONFIG_HWBM */
 #endif /* _HWBM_H */
diff --git a/include/net/ip.h b/include/net/ip.h
index 95bb77f95bcc..a2c61c36dc4a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -185,7 +185,7 @@ static inline struct sk_buff *ip_fraglist_next(struct ip_fraglist_iter *iter)
 }
 
 struct ip_frag_state {
-	struct iphdr	*iph;
+	bool		DF;
 	unsigned int	hlen;
 	unsigned int	ll_rs;
 	unsigned int	mtu;
@@ -196,7 +196,7 @@ struct ip_frag_state {
 };
 
 void ip_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int ll_rs,
-		  unsigned int mtu, struct ip_frag_state *state);
+		  unsigned int mtu, bool DF, struct ip_frag_state *state);
 struct sk_buff *ip_frag_next(struct sk_buff *skb,
 			     struct ip_frag_state *state);
 
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 3759167f91f5..078887c8c586 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -889,6 +889,7 @@ struct netns_ipvs {
 	struct delayed_work	defense_work;   /* Work handler */
 	int			drop_rate;
 	int			drop_counter;
+	int			old_secure_tcp;
 	atomic_t		dropentry;
 	/* locks in ctl.c */
 	spinlock_t		dropentry_lock;  /* drop entry handling */
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 50a67bd6a434..b8452cc0e059 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -439,8 +439,8 @@ static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 {
 	unsigned long now = jiffies;
 	
-	if (neigh->used != now)
-		neigh->used = now;
+	if (READ_ONCE(neigh->used) != now)
+		WRITE_ONCE(neigh->used, now);
 	if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE)))
 		return __neigh_event_send(neigh, skb);
 	return 0;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 4c2cd9378699..c7e15a213ef2 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -342,7 +342,7 @@ static inline struct net *read_pnet(const possible_net_t *pnet)
 #define __net_initconst	__initconst
 #endif
 
-int peernet2id_alloc(struct net *net, struct net *peer);
+int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp);
 int peernet2id(struct net *net, struct net *peer);
 bool peernet_has_id(struct net *net, struct net *peer);
 struct net *get_net_ns_by_id(struct net *net, int id);
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 001d294edf57..2d0275f13bbf 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -820,7 +820,8 @@ struct nft_expr_ops {
  */
 struct nft_expr {
 	const struct nft_expr_ops	*ops;
-	unsigned char			data[];
+	unsigned char			data[]
+		__attribute__((aligned(__alignof__(u64))));
 };
 
 static inline void *nft_expr_priv(const struct nft_expr *expr)
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 637548d54b3e..d80acda231ae 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -15,6 +15,7 @@
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <linux/hashtable.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
 #include <net/flow_offload.h>
@@ -362,6 +363,7 @@ struct tcf_proto {
 	bool			deleting;
 	refcount_t		refcnt;
 	struct rcu_head		rcu;
+	struct hlist_node	destroy_ht_node;
 };
 
 struct qdisc_skb_cb {
@@ -414,6 +416,8 @@ struct tcf_block {
 		struct list_head filter_chain_list;
 	} chain0;
 	struct rcu_head rcu;
+	DECLARE_HASHTABLE(proto_destroy_ht, 7);
+	struct mutex proto_destroy_lock; /* Lock for proto_destroy hashtable. */
 };
 
 #ifdef CONFIG_PROVE_LOCKING
diff --git a/include/net/sock.h b/include/net/sock.h
index f69b58bff7e5..718e62fbe869 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -954,8 +954,8 @@ static inline void sk_incoming_cpu_update(struct sock *sk)
 {
 	int cpu = raw_smp_processor_id();
 
-	if (unlikely(sk->sk_incoming_cpu != cpu))
-		sk->sk_incoming_cpu = cpu;
+	if (unlikely(READ_ONCE(sk->sk_incoming_cpu) != cpu))
+		WRITE_ONCE(sk->sk_incoming_cpu, cpu);
 }
 
 static inline void sock_rps_record_flow_hash(__u32 hash)
@@ -2242,12 +2242,17 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
  * sk_page_frag - return an appropriate page_frag
  * @sk: socket
  *
- * If socket allocation mode allows current thread to sleep, it means its
- * safe to use the per task page_frag instead of the per socket one.
+ * Use the per task page_frag instead of the per socket one for
+ * optimization when we know that we're in the normal context and owns
+ * everything that's associated with %current.
+ *
+ * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest
+ * inside other socket operations and end up recursing into sk_page_frag()
+ * while it's already in use.
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (gfpflags_allow_blocking(sk->sk_allocation))
+	if (gfpflags_normal_context(sk->sk_allocation))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
@@ -2337,7 +2342,7 @@ static inline ktime_t sock_read_timestamp(struct sock *sk)
 
 	return kt;
 #else
-	return sk->sk_stamp;
+	return READ_ONCE(sk->sk_stamp);
 #endif
 }
 
@@ -2348,7 +2353,7 @@ static inline void sock_write_timestamp(struct sock *sk, ktime_t kt)
 	sk->sk_stamp = kt;
 	write_sequnlock(&sk->sk_stamp_seq);
 #else
-	sk->sk_stamp = kt;
+	WRITE_ONCE(sk->sk_stamp, kt);
 #endif
 }
 
diff --git a/include/net/tls.h b/include/net/tls.h
index c664e6dba0d1..794e297483ea 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -40,6 +40,7 @@
 #include <linux/socket.h>
 #include <linux/tcp.h>
 #include <linux/skmsg.h>
+#include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/rcupdate.h>
 
@@ -269,6 +270,10 @@ struct tls_context {
 
 	bool in_tcp_sendpages;
 	bool pending_open_record_frags;
+
+	struct mutex tx_lock; /* protects partially_sent_* fields and
+			       * per-type TX fields
+			       */
 	unsigned long flags;
 
 	/* cache cold stuff */
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 335283dbe9b3..373aadcfea21 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -197,6 +197,7 @@ struct vxlan_rdst {
 	u8			 offloaded:1;
 	__be32			 remote_vni;
 	u32			 remote_ifindex;
+	struct net_device	 *remote_dev;
 	struct list_head	 list;
 	struct rcu_head		 rcu;
 	struct dst_cache	 dst_cache;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6a47ba85c54c..e7e733add99f 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -366,7 +366,7 @@ struct ib_tm_caps {
 
 struct ib_cq_init_attr {
 	unsigned int	cqe;
-	int		comp_vector;
+	u32		comp_vector;
 	u32		flags;
 };
 
diff --git a/include/soc/qcom/ocmem.h b/include/soc/qcom/ocmem.h
new file mode 100644
index 000000000000..02a8bc2677b1
--- /dev/null
+++ b/include/soc/qcom/ocmem.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * The On Chip Memory (OCMEM) allocator allows various clients to allocate
+ * memory from OCMEM based on performance, latency and power requirements.
+ * This is typically used by the GPU, camera/video, and audio components on
+ * some Snapdragon SoCs.
+ *
+ * Copyright (C) 2019 Brian Masney <masneyb@onstation.org>
+ * Copyright (C) 2015 Red Hat. Author: Rob Clark <robdclark@gmail.com>
+ */
+
+#include <linux/device.h>
+#include <linux/err.h>
+
+#ifndef __OCMEM_H__
+#define __OCMEM_H__
+
+enum ocmem_client {
+	/* GMEM clients */
+	OCMEM_GRAPHICS = 0x0,
+	/*
+	 * TODO add more once ocmem_allocate() is clever enough to
+	 * deal with multiple clients.
+	 */
+	OCMEM_CLIENT_MAX,
+};
+
+struct ocmem;
+
+struct ocmem_buf {
+	unsigned long offset;
+	unsigned long addr;
+	unsigned long len;
+};
+
+#if IS_ENABLED(CONFIG_QCOM_OCMEM)
+
+struct ocmem *of_get_ocmem(struct device *dev);
+struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem, enum ocmem_client client,
+				 unsigned long size);
+void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+		struct ocmem_buf *buf);
+
+#else /* IS_ENABLED(CONFIG_QCOM_OCMEM) */
+
+static inline struct ocmem *of_get_ocmem(struct device *dev)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline struct ocmem_buf *ocmem_allocate(struct ocmem *ocmem,
+					       enum ocmem_client client,
+					       unsigned long size)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline void ocmem_free(struct ocmem *ocmem, enum ocmem_client client,
+			      struct ocmem_buf *buf)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_QCOM_OCMEM) */
+
+#endif /* __OCMEM_H__ */
diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index 985a5f583de4..31f76b6abf71 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -135,9 +135,9 @@ int asoc_simple_init_priv(struct asoc_simple_priv *priv,
 			       struct link_info *li);
 
 #ifdef DEBUG
-inline void asoc_simple_debug_dai(struct asoc_simple_priv *priv,
-				  char *name,
-				  struct asoc_simple_dai *dai)
+static inline void asoc_simple_debug_dai(struct asoc_simple_priv *priv,
+					 char *name,
+					 struct asoc_simple_dai *dai)
 {
 	struct device *dev = simple_priv_to_dev(priv);
 
@@ -167,7 +167,7 @@ inline void asoc_simple_debug_dai(struct asoc_simple_priv *priv,
 		dev_dbg(dev, "%s clk %luHz\n", name, clk_get_rate(dai->clk));
 }
 
-inline void asoc_simple_debug_info(struct asoc_simple_priv *priv)
+static inline void asoc_simple_debug_info(struct asoc_simple_priv *priv)
 {
 	struct snd_soc_card *card = simple_priv_to_card(priv);
 	struct device *dev = simple_priv_to_dev(priv);
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 5df604de4f11..75ae1899452b 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -1688,6 +1688,7 @@ TRACE_EVENT(qgroup_update_reserve,
 		__entry->qgid		= qgroup->qgroupid;
 		__entry->cur_reserved	= qgroup->rsv.values[type];
 		__entry->diff		= diff;
+		__entry->type		= type;
 	),
 
 	TP_printk_btrfs("qgid=%llu type=%s cur_reserved=%llu diff=%lld",
@@ -1710,6 +1711,7 @@ TRACE_EVENT(qgroup_meta_reserve,
 	TP_fast_assign_btrfs(root->fs_info,
 		__entry->refroot	= root->root_key.objectid;
 		__entry->diff		= diff;
+		__entry->type		= type;
 	),
 
 	TP_printk_btrfs("refroot=%llu(%s) type=%s diff=%lld",
@@ -1726,7 +1728,6 @@ TRACE_EVENT(qgroup_meta_convert,
 	TP_STRUCT__entry_btrfs(
 		__field(	u64,	refroot			)
 		__field(	s64,	diff			)
-		__field(	int,	type			)
 	),
 
 	TP_fast_assign_btrfs(root->fs_info,
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 4fe35d600ab8..bbdad866e3fe 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -500,6 +500,8 @@ struct drm_amdgpu_gem_op {
 #define AMDGPU_VM_MTYPE_CC		(3 << 5)
 /* Use UC MTYPE instead of default MTYPE */
 #define AMDGPU_VM_MTYPE_UC		(4 << 5)
+/* Use RW MTYPE instead of default MTYPE */
+#define AMDGPU_VM_MTYPE_RW		(5 << 5)
 
 struct drm_amdgpu_gem_va {
 	/** GEM object handle */
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
index 3e59b8382dd8..45c6582b3df3 100644
--- a/include/uapi/drm/exynos_drm.h
+++ b/include/uapi/drm/exynos_drm.h
@@ -68,7 +68,7 @@ struct drm_exynos_gem_info {
 /**
  * A structure for user connection request of virtual display.
  *
- * @connection: indicate whether doing connetion or not by user.
+ * @connection: indicate whether doing connection or not by user.
  * @extensions: if this value is 1 then the vidi driver would need additional
  *	128bytes edid data.
  * @edid: the edid data pointer from user side.
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 63d40cba97e0..5400d7e057f1 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1572,6 +1572,21 @@ struct drm_i915_gem_context_param {
  *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
  */
 #define I915_CONTEXT_PARAM_ENGINES	0xa
+
+/*
+ * I915_CONTEXT_PARAM_PERSISTENCE:
+ *
+ * Allow the context and active rendering to survive the process until
+ * completion. Persistence allows fire-and-forget clients to queue up a
+ * bunch of work, hand the output over to a display server and then quit.
+ * If the context is marked as not persistent, upon closing (either via
+ * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
+ * or process termination), the context and any outstanding requests will be
+ * cancelled (and exported fences for cancelled requests marked as -EIO).
+ *
+ * By default, new contexts allow persistence.
+ */
+#define I915_CONTEXT_PARAM_PERSISTENCE	0xb
 /* Must be kept compact -- no holes and well documented */
 
 	__u64 value;
diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index 1e988fdeba34..6a6d2c7655ff 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * linux/can.h
  *
diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h
index 0fb328d93148..dd2b925b09ac 100644
--- a/include/uapi/linux/can/bcm.h
+++ b/include/uapi/linux/can/bcm.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * linux/can/bcm.h
  *
diff --git a/include/uapi/linux/can/error.h b/include/uapi/linux/can/error.h
index bfc4b5d22a5e..34633283de64 100644
--- a/include/uapi/linux/can/error.h
+++ b/include/uapi/linux/can/error.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * linux/can/error.h
  *
diff --git a/include/uapi/linux/can/gw.h b/include/uapi/linux/can/gw.h
index 3aea5388c8e4..c2190bbe21d8 100644
--- a/include/uapi/linux/can/gw.h
+++ b/include/uapi/linux/can/gw.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * linux/can/gw.h
  *
diff --git a/include/uapi/linux/can/j1939.h b/include/uapi/linux/can/j1939.h
index c32325342d30..df6e821075c1 100644
--- a/include/uapi/linux/can/j1939.h
+++ b/include/uapi/linux/can/j1939.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 /*
  * j1939.h
  *
diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h
index 1bc70d3a4d39..6f598b73839e 100644
--- a/include/uapi/linux/can/netlink.h
+++ b/include/uapi/linux/can/netlink.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 /*
  * linux/can/netlink.h
  *
diff --git a/include/uapi/linux/can/raw.h b/include/uapi/linux/can/raw.h
index be3b36e7ff61..6a11d308eb5c 100644
--- a/include/uapi/linux/can/raw.h
+++ b/include/uapi/linux/can/raw.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* SPDX-License-Identifier: ((GPL-2.0-only WITH Linux-syscall-note) OR BSD-3-Clause) */
 /*
  * linux/can/raw.h
  *
diff --git a/include/uapi/linux/can/vxcan.h b/include/uapi/linux/can/vxcan.h
index 066812d118a2..4fa9d8777a07 100644
--- a/include/uapi/linux/can/vxcan.h
+++ b/include/uapi/linux/can/vxcan.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
 #ifndef _UAPI_CAN_VXCAN_H
 #define _UAPI_CAN_VXCAN_H
 
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 802b0377a49e..373cada89815 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -38,6 +38,43 @@
  *
  * Protocol changelog:
  *
+ * 7.1:
+ *  - add the following messages:
+ *      FUSE_SETATTR, FUSE_SYMLINK, FUSE_MKNOD, FUSE_MKDIR, FUSE_UNLINK,
+ *      FUSE_RMDIR, FUSE_RENAME, FUSE_LINK, FUSE_OPEN, FUSE_READ, FUSE_WRITE,
+ *      FUSE_RELEASE, FUSE_FSYNC, FUSE_FLUSH, FUSE_SETXATTR, FUSE_GETXATTR,
+ *      FUSE_LISTXATTR, FUSE_REMOVEXATTR, FUSE_OPENDIR, FUSE_READDIR,
+ *      FUSE_RELEASEDIR
+ *  - add padding to messages to accommodate 32-bit servers on 64-bit kernels
+ *
+ * 7.2:
+ *  - add FOPEN_DIRECT_IO and FOPEN_KEEP_CACHE flags
+ *  - add FUSE_FSYNCDIR message
+ *
+ * 7.3:
+ *  - add FUSE_ACCESS message
+ *  - add FUSE_CREATE message
+ *  - add filehandle to fuse_setattr_in
+ *
+ * 7.4:
+ *  - add frsize to fuse_kstatfs
+ *  - clean up request size limit checking
+ *
+ * 7.5:
+ *  - add flags and max_write to fuse_init_out
+ *
+ * 7.6:
+ *  - add max_readahead to fuse_init_in and fuse_init_out
+ *
+ * 7.7:
+ *  - add FUSE_INTERRUPT message
+ *  - add POSIX file lock support
+ *
+ * 7.8:
+ *  - add lock_owner and flags fields to fuse_release_in
+ *  - add FUSE_BMAP message
+ *  - add FUSE_DESTROY message
+ *
  * 7.9:
  *  - new fuse_getattr_in input argument of GETATTR
  *  - add lk_flags in fuse_lk_in
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index e168dc59e9a0..d99b5a772698 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -63,6 +63,7 @@ struct nvme_passthru_cmd64 {
 	__u32	cdw14;
 	__u32	cdw15;
 	__u32	timeout_ms;
+	__u32   rsvd2;
 	__u64	result;
 };
 
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 99335e1f4a27..25b4fa00bad1 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -51,6 +51,10 @@
  *               sent when the child exits.
  * @stack:       Specify the location of the stack for the
  *               child process.
+ *               Note, @stack is expected to point to the
+ *               lowest address. The stack direction will be
+ *               determined by the kernel and set up
+ *               appropriately based on @stack_size.
  * @stack_size:  The size of the stack for the child process.
  * @tls:         If CLONE_SETTLS is set, the tls descriptor
  *               is set to tls.
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ddd8addcdb5c..a3eaf08e7dd3 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1311,12 +1311,12 @@ static bool sysctl_is_valid_access(int off, int size, enum bpf_access_type type,
 		return false;
 
 	switch (off) {
-	case offsetof(struct bpf_sysctl, write):
+	case bpf_ctx_range(struct bpf_sysctl, write):
 		if (type != BPF_READ)
 			return false;
 		bpf_ctx_record_field_size(info, size_default);
 		return bpf_ctx_narrow_access_ok(off, size, size_default);
-	case offsetof(struct bpf_sysctl, file_pos):
+	case bpf_ctx_range(struct bpf_sysctl, file_pos):
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
 			return bpf_ctx_narrow_access_ok(off, size, size_default);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 66088a9e9b9e..ef0e1e3e66f4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -502,7 +502,7 @@ int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt)
 	return WARN_ON_ONCE(bpf_adj_branches(prog, off, off + cnt, off, false));
 }
 
-void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+static void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
 {
 	int i;
 
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d27f3b60ff6d..3867864cdc2f 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -128,7 +128,7 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr)
 
 		if (!dtab->n_buckets) /* Overflow check */
 			return -EINVAL;
-		cost += sizeof(struct hlist_head) * dtab->n_buckets;
+		cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets;
 	}
 
 	/* if map size is larger than memlock limit, reject it */
@@ -719,6 +719,32 @@ const struct bpf_map_ops dev_map_hash_ops = {
 	.map_check_btf = map_check_no_btf,
 };
 
+static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab,
+				       struct net_device *netdev)
+{
+	unsigned long flags;
+	u32 i;
+
+	spin_lock_irqsave(&dtab->index_lock, flags);
+	for (i = 0; i < dtab->n_buckets; i++) {
+		struct bpf_dtab_netdev *dev;
+		struct hlist_head *head;
+		struct hlist_node *next;
+
+		head = dev_map_index_hash(dtab, i);
+
+		hlist_for_each_entry_safe(dev, next, head, index_hlist) {
+			if (netdev != dev->dev)
+				continue;
+
+			dtab->items--;
+			hlist_del_rcu(&dev->index_hlist);
+			call_rcu(&dev->rcu, __dev_map_entry_free);
+		}
+	}
+	spin_unlock_irqrestore(&dtab->index_lock, flags);
+}
+
 static int dev_map_notification(struct notifier_block *notifier,
 				ulong event, void *ptr)
 {
@@ -735,6 +761,11 @@ static int dev_map_notification(struct notifier_block *notifier,
 		 */
 		rcu_read_lock();
 		list_for_each_entry_rcu(dtab, &dev_map_list, list) {
+			if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) {
+				dev_map_hash_remove_netdev(dtab, netdev);
+				continue;
+			}
+
 			for (i = 0; i < dtab->map.max_entries; i++) {
 				struct bpf_dtab_netdev *dev, *odev;
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 82eabd4e38ad..ace1cfaa24b6 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -126,7 +126,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
 	return map;
 }
 
-void *bpf_map_area_alloc(size_t size, int numa_node)
+void *bpf_map_area_alloc(u64 size, int numa_node)
 {
 	/* We really just want to fail instead of triggering OOM killer
 	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,
@@ -141,6 +141,9 @@ void *bpf_map_area_alloc(size_t size, int numa_node)
 	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;
 	void *area;
 
+	if (size >= SIZE_MAX)
+		return NULL;
+
 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
 		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,
 				    numa_node);
@@ -197,7 +200,7 @@ static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
 		atomic_long_sub(pages, &user->locked_vm);
 }
 
-int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size)
+int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size)
 {
 	u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;
 	struct user_struct *user;
@@ -1326,24 +1329,32 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
 {
 	struct bpf_prog_aux *aux = container_of(rcu, struct bpf_prog_aux, rcu);
 
+	kvfree(aux->func_info);
 	free_used_maps(aux);
 	bpf_prog_uncharge_memlock(aux->prog);
 	security_bpf_prog_free(aux);
 	bpf_prog_free(aux->prog);
 }
 
+static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred)
+{
+	bpf_prog_kallsyms_del_all(prog);
+	btf_put(prog->aux->btf);
+	bpf_prog_free_linfo(prog);
+
+	if (deferred)
+		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+	else
+		__bpf_prog_put_rcu(&prog->aux->rcu);
+}
+
 static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
 {
 	if (atomic_dec_and_test(&prog->aux->refcnt)) {
 		perf_event_bpf_event(prog, PERF_BPF_EVENT_PROG_UNLOAD, 0);
 		/* bpf_prog_free_id() must be called first */
 		bpf_prog_free_id(prog, do_idr_lock);
-		bpf_prog_kallsyms_del_all(prog);
-		btf_put(prog->aux->btf);
-		kvfree(prog->aux->func_info);
-		bpf_prog_free_linfo(prog);
-
-		call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
+		__bpf_prog_put_noref(prog, true);
 	}
 }
 
@@ -1741,11 +1752,12 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	return err;
 
 free_used_maps:
-	bpf_prog_free_linfo(prog);
-	kvfree(prog->aux->func_info);
-	btf_put(prog->aux->btf);
-	bpf_prog_kallsyms_del_subprogs(prog);
-	free_used_maps(prog->aux);
+	/* In case we have subprogs, we need to wait for a grace
+	 * period before we can tear down JIT memory since symbols
+	 * are already exposed under kallsyms.
+	 */
+	__bpf_prog_put_noref(prog, prog->aux->func_cnt);
+	return err;
 free_prog:
 	bpf_prog_uncharge_memlock(prog);
 free_prog_sec:
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c52bc91f882b..c87ee6412b36 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -798,7 +798,8 @@ static int generate_sched_domains(cpumask_var_t **domains,
 		    cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
 			continue;
 
-		if (is_sched_load_balance(cp))
+		if (is_sched_load_balance(cp) &&
+		    !cpumask_empty(cp->effective_cpus))
 			csa[csn++] = cp;
 
 		/* skip @cp's subtree if not a partition root */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9ec0b0bfddbd..aec8dba2bea4 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5607,8 +5607,10 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		perf_pmu_output_stop(event);
 
 		/* now it's safe to free the pages */
-		atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
-		atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
+		if (!rb->aux_mmap_locked)
+			atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
+		else
+			atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
 
 		/* this has to be the last one */
 		rb_free_aux(rb);
@@ -6947,7 +6949,7 @@ static void __perf_event_output_stop(struct perf_event *event, void *data)
 static int __perf_pmu_output_stop(void *info)
 {
 	struct perf_event *event = info;
-	struct pmu *pmu = event->pmu;
+	struct pmu *pmu = event->ctx->pmu;
 	struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
 	struct remote_output ro = {
 		.rb	= event->rb,
@@ -10633,7 +10635,7 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 
 	attr->size = size;
 
-	if (attr->__reserved_1)
+	if (attr->__reserved_1 || attr->__reserved_2)
 		return -EINVAL;
 
 	if (attr->sample_type & ~(PERF_SAMPLE_MAX-1))
diff --git a/kernel/fork.c b/kernel/fork.c
index bcdf53125210..55af6931c6ec 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2561,7 +2561,35 @@ noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
 	return 0;
 }
 
-static bool clone3_args_valid(const struct kernel_clone_args *kargs)
+/**
+ * clone3_stack_valid - check and prepare stack
+ * @kargs: kernel clone args
+ *
+ * Verify that the stack arguments userspace gave us are sane.
+ * In addition, set the stack direction for userspace since it's easy for us to
+ * determine.
+ */
+static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
+{
+	if (kargs->stack == 0) {
+		if (kargs->stack_size > 0)
+			return false;
+	} else {
+		if (kargs->stack_size == 0)
+			return false;
+
+		if (!access_ok((void __user *)kargs->stack, kargs->stack_size))
+			return false;
+
+#if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64)
+		kargs->stack += kargs->stack_size;
+#endif
+	}
+
+	return true;
+}
+
+static bool clone3_args_valid(struct kernel_clone_args *kargs)
 {
 	/*
 	 * All lower bits of the flag word are taken.
@@ -2581,6 +2609,9 @@ static bool clone3_args_valid(const struct kernel_clone_args *kargs)
 	    kargs->exit_signal)
 		return false;
 
+	if (!clone3_stack_valid(kargs))
+		return false;
+
 	return true;
 }
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 132672b74e4b..dd822fd8a7d5 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
  * @type:	Type of irqchip_fwnode. See linux/irqdomain.h
  * @name:	Optional user provided domain name
  * @id:		Optional user provided id if name != NULL
- * @data:	Optional user-provided data
+ * @pa:		Optional user-provided physical address
  *
  * Allocate a struct irqchip_fwid, and return a poiner to the embedded
  * fwnode_handle (or NULL on failure).
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 9568a2fe7c11..04e83fdfbe80 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -650,3 +650,243 @@ static int __init pm_qos_power_init(void)
 }
 
 late_initcall(pm_qos_power_init);
+
+/* Definitions related to the frequency QoS below. */
+
+/**
+ * freq_constraints_init - Initialize frequency QoS constraints.
+ * @qos: Frequency QoS constraints to initialize.
+ */
+void freq_constraints_init(struct freq_constraints *qos)
+{
+	struct pm_qos_constraints *c;
+
+	c = &qos->min_freq;
+	plist_head_init(&c->list);
+	c->target_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+	c->default_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+	c->no_constraint_value = FREQ_QOS_MIN_DEFAULT_VALUE;
+	c->type = PM_QOS_MAX;
+	c->notifiers = &qos->min_freq_notifiers;
+	BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers);
+
+	c = &qos->max_freq;
+	plist_head_init(&c->list);
+	c->target_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+	c->default_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+	c->no_constraint_value = FREQ_QOS_MAX_DEFAULT_VALUE;
+	c->type = PM_QOS_MIN;
+	c->notifiers = &qos->max_freq_notifiers;
+	BLOCKING_INIT_NOTIFIER_HEAD(c->notifiers);
+}
+
+/**
+ * freq_qos_read_value - Get frequency QoS constraint for a given list.
+ * @qos: Constraints to evaluate.
+ * @type: QoS request type.
+ */
+s32 freq_qos_read_value(struct freq_constraints *qos,
+			enum freq_qos_req_type type)
+{
+	s32 ret;
+
+	switch (type) {
+	case FREQ_QOS_MIN:
+		ret = IS_ERR_OR_NULL(qos) ?
+			FREQ_QOS_MIN_DEFAULT_VALUE :
+			pm_qos_read_value(&qos->min_freq);
+		break;
+	case FREQ_QOS_MAX:
+		ret = IS_ERR_OR_NULL(qos) ?
+			FREQ_QOS_MAX_DEFAULT_VALUE :
+			pm_qos_read_value(&qos->max_freq);
+		break;
+	default:
+		WARN_ON(1);
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/**
+ * freq_qos_apply - Add/modify/remove frequency QoS request.
+ * @req: Constraint request to apply.
+ * @action: Action to perform (add/update/remove).
+ * @value: Value to assign to the QoS request.
+ */
+static int freq_qos_apply(struct freq_qos_request *req,
+			  enum pm_qos_req_action action, s32 value)
+{
+	int ret;
+
+	switch(req->type) {
+	case FREQ_QOS_MIN:
+		ret = pm_qos_update_target(&req->qos->min_freq, &req->pnode,
+					   action, value);
+		break;
+	case FREQ_QOS_MAX:
+		ret = pm_qos_update_target(&req->qos->max_freq, &req->pnode,
+					   action, value);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/**
+ * freq_qos_add_request - Insert new frequency QoS request into a given list.
+ * @qos: Constraints to update.
+ * @req: Preallocated request object.
+ * @type: Request type.
+ * @value: Request value.
+ *
+ * Insert a new entry into the @qos list of requests, recompute the effective
+ * QoS constraint value for that list and initialize the @req object.  The
+ * caller needs to save that object for later use in updates and removal.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_add_request(struct freq_constraints *qos,
+			 struct freq_qos_request *req,
+			 enum freq_qos_req_type type, s32 value)
+{
+	int ret;
+
+	if (IS_ERR_OR_NULL(qos) || !req)
+		return -EINVAL;
+
+	if (WARN(freq_qos_request_active(req),
+		 "%s() called for active request\n", __func__))
+		return -EINVAL;
+
+	req->qos = qos;
+	req->type = type;
+	ret = freq_qos_apply(req, PM_QOS_ADD_REQ, value);
+	if (ret < 0) {
+		req->qos = NULL;
+		req->type = 0;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_add_request);
+
+/**
+ * freq_qos_update_request - Modify existing frequency QoS request.
+ * @req: Request to modify.
+ * @new_value: New request value.
+ *
+ * Update an existing frequency QoS request along with the effective constraint
+ * value for the list of requests it belongs to.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_update_request(struct freq_qos_request *req, s32 new_value)
+{
+	if (!req)
+		return -EINVAL;
+
+	if (WARN(!freq_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	if (req->pnode.prio == new_value)
+		return 0;
+
+	return freq_qos_apply(req, PM_QOS_UPDATE_REQ, new_value);
+}
+EXPORT_SYMBOL_GPL(freq_qos_update_request);
+
+/**
+ * freq_qos_remove_request - Remove frequency QoS request from its list.
+ * @req: Request to remove.
+ *
+ * Remove the given frequency QoS request from the list of constraints it
+ * belongs to and recompute the effective constraint value for that list.
+ *
+ * Return 1 if the effective constraint value has changed, 0 if the effective
+ * constraint value has not changed, or a negative error code on failures.
+ */
+int freq_qos_remove_request(struct freq_qos_request *req)
+{
+	if (!req)
+		return -EINVAL;
+
+	if (WARN(!freq_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
+		return -EINVAL;
+
+	return freq_qos_apply(req, PM_QOS_REMOVE_REQ, PM_QOS_DEFAULT_VALUE);
+}
+EXPORT_SYMBOL_GPL(freq_qos_remove_request);
+
+/**
+ * freq_qos_add_notifier - Add frequency QoS change notifier.
+ * @qos: List of requests to add the notifier to.
+ * @type: Request type.
+ * @notifier: Notifier block to add.
+ */
+int freq_qos_add_notifier(struct freq_constraints *qos,
+			  enum freq_qos_req_type type,
+			  struct notifier_block *notifier)
+{
+	int ret;
+
+	if (IS_ERR_OR_NULL(qos) || !notifier)
+		return -EINVAL;
+
+	switch (type) {
+	case FREQ_QOS_MIN:
+		ret = blocking_notifier_chain_register(qos->min_freq.notifiers,
+						       notifier);
+		break;
+	case FREQ_QOS_MAX:
+		ret = blocking_notifier_chain_register(qos->max_freq.notifiers,
+						       notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_add_notifier);
+
+/**
+ * freq_qos_remove_notifier - Remove frequency QoS change notifier.
+ * @qos: List of requests to remove the notifier from.
+ * @type: Request type.
+ * @notifier: Notifier block to remove.
+ */
+int freq_qos_remove_notifier(struct freq_constraints *qos,
+			     enum freq_qos_req_type type,
+			     struct notifier_block *notifier)
+{
+	int ret;
+
+	if (IS_ERR_OR_NULL(qos) || !notifier)
+		return -EINVAL;
+
+	switch (type) {
+	case FREQ_QOS_MIN:
+		ret = blocking_notifier_chain_unregister(qos->min_freq.notifiers,
+							 notifier);
+		break;
+	case FREQ_QOS_MAX:
+		ret = blocking_notifier_chain_unregister(qos->max_freq.notifiers,
+							 notifier);
+		break;
+	default:
+		WARN_ON(1);
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(freq_qos_remove_notifier);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dd05a378631a..0f2eb3629070 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1073,6 +1073,7 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
 	task_rq_unlock(rq, p, &rf);
 }
 
+#ifdef CONFIG_UCLAMP_TASK_GROUP
 static inline void
 uclamp_update_active_tasks(struct cgroup_subsys_state *css,
 			   unsigned int clamps)
@@ -1091,7 +1092,6 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css,
 	css_task_iter_end(&it);
 }
 
-#ifdef CONFIG_UCLAMP_TASK_GROUP
 static void cpu_util_update_eff(struct cgroup_subsys_state *css);
 static void uclamp_update_root_tg(void)
 {
@@ -3929,13 +3929,22 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	}
 
 restart:
+#ifdef CONFIG_SMP
 	/*
-	 * Ensure that we put DL/RT tasks before the pick loop, such that they
-	 * can PULL higher prio tasks when we lower the RQ 'priority'.
+	 * We must do the balancing pass before put_next_task(), such
+	 * that when we release the rq->lock the task is in the same
+	 * state as before we took rq->lock.
+	 *
+	 * We can terminate the balance pass as soon as we know there is
+	 * a runnable task of @class priority or higher.
 	 */
-	prev->sched_class->put_prev_task(rq, prev, rf);
-	if (!rq->nr_running)
-		newidle_balance(rq, rf);
+	for_class_range(class, prev->sched_class, &idle_sched_class) {
+		if (class->balance(rq, prev, rf))
+			break;
+	}
+#endif
+
+	put_prev_task(rq, prev);
 
 	for_each_class(class) {
 		p = class->pick_next_task(rq, NULL, NULL);
@@ -6201,7 +6210,7 @@ static struct task_struct *__pick_migrate_task(struct rq *rq)
 	for_each_class(class) {
 		next = class->pick_next_task(rq, NULL, NULL);
 		if (next) {
-			next->sched_class->put_prev_task(rq, next, NULL);
+			next->sched_class->put_prev_task(rq, next);
 			return next;
 		}
 	}
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 2dc48720f189..a8a08030a8f7 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1691,6 +1691,22 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 	resched_curr(rq);
 }
 
+static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+{
+	if (!on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
+		/*
+		 * This is OK, because current is on_cpu, which avoids it being
+		 * picked for load-balance and preemption/IRQs are still
+		 * disabled avoiding further scheduler activity on it and we've
+		 * not yet started the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_dl_task(rq);
+		rq_repin_lock(rq, rf);
+	}
+
+	return sched_stop_runnable(rq) || sched_dl_runnable(rq);
+}
 #endif /* CONFIG_SMP */
 
 /*
@@ -1758,45 +1774,28 @@ static struct task_struct *
 pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct sched_dl_entity *dl_se;
+	struct dl_rq *dl_rq = &rq->dl;
 	struct task_struct *p;
-	struct dl_rq *dl_rq;
 
 	WARN_ON_ONCE(prev || rf);
 
-	dl_rq = &rq->dl;
-
-	if (unlikely(!dl_rq->dl_nr_running))
+	if (!sched_dl_runnable(rq))
 		return NULL;
 
 	dl_se = pick_next_dl_entity(rq, dl_rq);
 	BUG_ON(!dl_se);
-
 	p = dl_task_of(dl_se);
-
 	set_next_task_dl(rq, p);
-
 	return p;
 }
 
-static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
 
 	update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
-
-	if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet started the picking loop.
-		 */
-		rq_unpin_lock(rq, rf);
-		pull_dl_task(rq);
-		rq_repin_lock(rq, rf);
-	}
 }
 
 /*
@@ -2442,6 +2441,7 @@ const struct sched_class dl_sched_class = {
 	.set_next_task		= set_next_task_dl,
 
 #ifdef CONFIG_SMP
+	.balance		= balance_dl,
 	.select_task_rq		= select_task_rq_dl,
 	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 682a754ea3e1..22a2fed29054 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6570,6 +6570,15 @@ static void task_dead_fair(struct task_struct *p)
 {
 	remove_entity_load_avg(&p->se);
 }
+
+static int
+balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	if (rq->nr_running)
+		return 1;
+
+	return newidle_balance(rq, rf) != 0;
+}
 #endif /* CONFIG_SMP */
 
 static unsigned long wakeup_gran(struct sched_entity *se)
@@ -6746,7 +6755,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
 	int new_tasks;
 
 again:
-	if (!cfs_rq->nr_running)
+	if (!sched_fair_runnable(rq))
 		goto idle;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6884,7 +6893,7 @@ idle:
 /*
  * Account for a descheduled task:
  */
-static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
 {
 	struct sched_entity *se = &prev->se;
 	struct cfs_rq *cfs_rq;
@@ -10414,11 +10423,11 @@ const struct sched_class fair_sched_class = {
 	.check_preempt_curr	= check_preempt_wakeup,
 
 	.pick_next_task		= pick_next_task_fair,
-
 	.put_prev_task		= put_prev_task_fair,
 	.set_next_task          = set_next_task_fair,
 
 #ifdef CONFIG_SMP
+	.balance		= balance_fair,
 	.select_task_rq		= select_task_rq_fair,
 	.migrate_task_rq	= migrate_task_rq_fair,
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8dad5aa600ea..f65ef1e2f204 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -365,6 +365,12 @@ select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* IDLE tasks as never migrated */
 }
+
+static int
+balance_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	return WARN_ON_ONCE(1);
+}
 #endif
 
 /*
@@ -375,7 +381,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
 	resched_curr(rq);
 }
 
-static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
 }
 
@@ -460,6 +466,7 @@ const struct sched_class idle_sched_class = {
 	.set_next_task          = set_next_task_idle,
 
 #ifdef CONFIG_SMP
+	.balance		= balance_idle,
 	.select_task_rq		= select_task_rq_idle,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ebaa4e619684..9b8adc01be3d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1469,6 +1469,22 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
 	resched_curr(rq);
 }
 
+static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+{
+	if (!on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
+		/*
+		 * This is OK, because current is on_cpu, which avoids it being
+		 * picked for load-balance and preemption/IRQs are still
+		 * disabled avoiding further scheduler activity on it and we've
+		 * not yet started the picking loop.
+		 */
+		rq_unpin_lock(rq, rf);
+		pull_rt_task(rq);
+		rq_repin_lock(rq, rf);
+	}
+
+	return sched_stop_runnable(rq) || sched_dl_runnable(rq) || sched_rt_runnable(rq);
+}
 #endif /* CONFIG_SMP */
 
 /*
@@ -1552,21 +1568,18 @@ static struct task_struct *
 pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
 	struct task_struct *p;
-	struct rt_rq *rt_rq = &rq->rt;
 
 	WARN_ON_ONCE(prev || rf);
 
-	if (!rt_rq->rt_queued)
+	if (!sched_rt_runnable(rq))
 		return NULL;
 
 	p = _pick_next_task_rt(rq);
-
 	set_next_task_rt(rq, p);
-
 	return p;
 }
 
-static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
 
@@ -1578,18 +1591,6 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_fla
 	 */
 	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_task(rq, p);
-
-	if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet started the picking loop.
-		 */
-		rq_unpin_lock(rq, rf);
-		pull_rt_task(rq);
-		rq_repin_lock(rq, rf);
-	}
 }
 
 #ifdef CONFIG_SMP
@@ -2366,8 +2367,8 @@ const struct sched_class rt_sched_class = {
 	.set_next_task          = set_next_task_rt,
 
 #ifdef CONFIG_SMP
+	.balance		= balance_rt,
 	.select_task_rq		= select_task_rq_rt,
-
 	.set_cpus_allowed       = set_cpus_allowed_common,
 	.rq_online              = rq_online_rt,
 	.rq_offline             = rq_offline_rt,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0db2c1b3361e..c8870c5bd7df 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1727,10 +1727,11 @@ struct sched_class {
 	struct task_struct * (*pick_next_task)(struct rq *rq,
 					       struct task_struct *prev,
 					       struct rq_flags *rf);
-	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf);
+	void (*put_prev_task)(struct rq *rq, struct task_struct *p);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p);
 
 #ifdef CONFIG_SMP
+	int (*balance)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf);
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
 
@@ -1773,7 +1774,7 @@ struct sched_class {
 static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	WARN_ON_ONCE(rq->curr != prev);
-	prev->sched_class->put_prev_task(rq, prev, NULL);
+	prev->sched_class->put_prev_task(rq, prev);
 }
 
 static inline void set_next_task(struct rq *rq, struct task_struct *next)
@@ -1787,8 +1788,12 @@ static inline void set_next_task(struct rq *rq, struct task_struct *next)
 #else
 #define sched_class_highest (&dl_sched_class)
 #endif
+
+#define for_class_range(class, _from, _to) \
+	for (class = (_from); class != (_to); class = class->next)
+
 #define for_each_class(class) \
-   for (class = sched_class_highest; class; class = class->next)
+	for_class_range(class, sched_class_highest, NULL)
 
 extern const struct sched_class stop_sched_class;
 extern const struct sched_class dl_sched_class;
@@ -1796,6 +1801,25 @@ extern const struct sched_class rt_sched_class;
 extern const struct sched_class fair_sched_class;
 extern const struct sched_class idle_sched_class;
 
+static inline bool sched_stop_runnable(struct rq *rq)
+{
+	return rq->stop && task_on_rq_queued(rq->stop);
+}
+
+static inline bool sched_dl_runnable(struct rq *rq)
+{
+	return rq->dl.dl_nr_running > 0;
+}
+
+static inline bool sched_rt_runnable(struct rq *rq)
+{
+	return rq->rt.rt_queued > 0;
+}
+
+static inline bool sched_fair_runnable(struct rq *rq)
+{
+	return rq->cfs.nr_running > 0;
+}
 
 #ifdef CONFIG_SMP
 
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index 7e1cee4e65b2..c0640739e05e 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -15,6 +15,12 @@ select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	return task_cpu(p); /* stop tasks as never migrate */
 }
+
+static int
+balance_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+{
+	return sched_stop_runnable(rq);
+}
 #endif /* CONFIG_SMP */
 
 static void
@@ -31,16 +37,13 @@ static void set_next_task_stop(struct rq *rq, struct task_struct *stop)
 static struct task_struct *
 pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct task_struct *stop = rq->stop;
-
 	WARN_ON_ONCE(prev || rf);
 
-	if (!stop || !task_on_rq_queued(stop))
+	if (!sched_stop_runnable(rq))
 		return NULL;
 
-	set_next_task_stop(rq, stop);
-
-	return stop;
+	set_next_task_stop(rq, rq->stop);
+	return rq->stop;
 }
 
 static void
@@ -60,7 +63,7 @@ static void yield_task_stop(struct rq *rq)
 	BUG(); /* the stop task should never yield, its pointless. */
 }
 
-static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
+static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
 {
 	struct task_struct *curr = rq->curr;
 	u64 delta_exec;
@@ -129,6 +132,7 @@ const struct sched_class stop_sched_class = {
 	.set_next_task          = set_next_task_stop,
 
 #ifdef CONFIG_SMP
+	.balance		= balance_stop,
 	.select_task_rq		= select_task_rq_stop,
 	.set_cpus_allowed	= set_cpus_allowed_common,
 #endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index b5667a273bf6..49b835f1305f 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1948,7 +1948,7 @@ next_level:
 static int
 build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
 {
-	enum s_alloc alloc_state;
+	enum s_alloc alloc_state = sa_none;
 	struct sched_domain *sd;
 	struct s_data d;
 	struct rq *rq = NULL;
@@ -1956,6 +1956,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	struct sched_domain_topology_level *tl_asym;
 	bool has_asym = false;
 
+	if (WARN_ON(cpumask_empty(cpu_map)))
+		goto error;
+
 	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
 	if (alloc_state != sa_rootdomain)
 		goto error;
@@ -2026,7 +2029,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	rcu_read_unlock();
 
 	if (has_asym)
-		static_branch_enable_cpuslocked(&sched_asym_cpucapacity);
+		static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
 
 	if (rq && sched_debug_enabled) {
 		pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
@@ -2121,8 +2124,12 @@ int sched_init_domains(const struct cpumask *cpu_map)
  */
 static void detach_destroy_domains(const struct cpumask *cpu_map)
 {
+	unsigned int cpu = cpumask_any(cpu_map);
 	int i;
 
+	if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
+		static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
+
 	rcu_read_lock();
 	for_each_cpu(i, cpu_map)
 		cpu_attach_domain(NULL, &def_root_domain, i);
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 6d1f68b7e528..c9ea7eb2cb1a 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -141,7 +141,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store,
 	struct stacktrace_cookie c = {
 		.store	= store,
 		.size	= size,
-		.skip	= skipnr + 1,
+		/* skip this function if they are tracing us */
+		.skip	= skipnr + !!(current == tsk),
 	};
 
 	if (!try_get_task_stack(tsk))
@@ -298,7 +299,8 @@ unsigned int stack_trace_save_tsk(struct task_struct *task,
 	struct stack_trace trace = {
 		.entries	= store,
 		.max_entries	= size,
-		.skip		= skipnr + 1,
+		/* skip this function if they are tracing us */
+		.skip	= skipnr + !!(current == task),
 	};
 
 	save_stack_trace_tsk(task, &trace);
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 92a431981b1c..42d512fcfda2 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -266,7 +266,7 @@ static void update_gt_cputime(struct task_cputime_atomic *cputime_atomic,
 /**
  * thread_group_sample_cputime - Sample cputime for a given task
  * @tsk:	Task for which cputime needs to be started
- * @iimes:	Storage for time samples
+ * @samples:	Storage for time samples
  *
  * Called from sys_getitimer() to calculate the expiry time of an active
  * timer. That means group cputime accounting is already active. Called
@@ -1038,12 +1038,12 @@ unlock:
  * member of @pct->bases[CLK].nextevt. False otherwise
  */
 static inline bool
-task_cputimers_expired(const u64 *sample, struct posix_cputimers *pct)
+task_cputimers_expired(const u64 *samples, struct posix_cputimers *pct)
 {
 	int i;
 
 	for (i = 0; i < CPUCLOCK_MAX; i++) {
-		if (sample[i] >= pct->bases[i].nextevt)
+		if (samples[i] >= pct->bases[i].nextevt)
 			return true;
 	}
 	return false;
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 142b07619918..dbd69052eaa6 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -17,6 +17,8 @@
 #include <linux/seqlock.h>
 #include <linux/bitops.h>
 
+#include "timekeeping.h"
+
 /**
  * struct clock_read_data - data required to read from sched_clock()
  *
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index 4bc37ac3bb05..5ee0f7709410 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -110,8 +110,7 @@ void update_vsyscall(struct timekeeper *tk)
 	nsec		= nsec + tk->wall_to_monotonic.tv_nsec;
 	vdso_ts->sec	+= __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec);
 
-	if (__arch_use_vsyscall(vdata))
-		update_vdso_data(vdata, tk);
+	update_vdso_data(vdata, tk);
 
 	__arch_update_vsyscall(vdata, tk);
 
@@ -124,10 +123,8 @@ void update_vsyscall_tz(void)
 {
 	struct vdso_data *vdata = __arch_get_k_vdso_data();
 
-	if (__arch_use_vsyscall(vdata)) {
-		vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
-		vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
-	}
+	vdata[CS_HRES_COARSE].tz_minuteswest = sys_tz.tz_minuteswest;
+	vdata[CS_HRES_COARSE].tz_dsttime = sys_tz.tz_dsttime;
 
 	__arch_sync_vdso_data(vdata);
 }
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 0892e38ed6fb..a9dfa04ffa44 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -272,9 +272,11 @@ int perf_kprobe_init(struct perf_event *p_event, bool is_retprobe)
 		goto out;
 	}
 
+	mutex_lock(&event_mutex);
 	ret = perf_trace_event_init(tp_event, p_event);
 	if (ret)
 		destroy_local_trace_kprobe(tp_event);
+	mutex_unlock(&event_mutex);
 out:
 	kfree(func);
 	return ret;
@@ -282,8 +284,10 @@ out:
 
 void perf_kprobe_destroy(struct perf_event *p_event)
 {
+	mutex_lock(&event_mutex);
 	perf_trace_event_close(p_event);
 	perf_trace_event_unreg(p_event);
+	mutex_unlock(&event_mutex);
 
 	destroy_local_trace_kprobe(p_event->tp_event);
 }
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 57648c5aa679..7482a1466ebf 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -679,6 +679,8 @@ static bool synth_field_signed(char *type)
 {
 	if (str_has_prefix(type, "u"))
 		return false;
+	if (strcmp(type, "gfp_t") == 0)
+		return false;
 
 	return true;
 }
diff --git a/lib/Kconfig b/lib/Kconfig
index 183f92a297ca..3321d04dfa5a 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -447,7 +447,6 @@ config ASSOCIATIVE_ARRAY
 config HAS_IOMEM
 	bool
 	depends on !NO_IOMEM
-	select GENERIC_IO
 	default y
 
 config HAS_IOPORT_MAP
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 5cff72f18c4a..33ffbf308853 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -106,7 +106,12 @@ retry:
 		was_locked = 1;
 	} else {
 		local_irq_restore(flags);
-		cpu_relax();
+		/*
+		 * Wait for the lock to release before jumping to
+		 * atomic_cmpxchg() in order to mitigate the thundering herd
+		 * problem.
+		 */
+		do { cpu_relax(); } while (atomic_read(&dump_lock) != -1);
 		goto retry;
 	}
 
diff --git a/lib/idr.c b/lib/idr.c
index 66a374892482..c2cf2c52bbde 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -215,7 +215,7 @@ int idr_for_each(const struct idr *idr,
 EXPORT_SYMBOL(idr_for_each);
 
 /**
- * idr_get_next() - Find next populated entry.
+ * idr_get_next_ul() - Find next populated entry.
  * @idr: IDR handle.
  * @nextid: Pointer to an ID.
  *
@@ -224,7 +224,7 @@ EXPORT_SYMBOL(idr_for_each);
  * to the ID of the found value.  To use in a loop, the value pointed to by
  * nextid must be incremented by the user.
  */
-void *idr_get_next(struct idr *idr, int *nextid)
+void *idr_get_next_ul(struct idr *idr, unsigned long *nextid)
 {
 	struct radix_tree_iter iter;
 	void __rcu **slot;
@@ -245,18 +245,14 @@ void *idr_get_next(struct idr *idr, int *nextid)
 	}
 	if (!slot)
 		return NULL;
-	id = iter.index + base;
-
-	if (WARN_ON_ONCE(id > INT_MAX))
-		return NULL;
 
-	*nextid = id;
+	*nextid = iter.index + base;
 	return entry;
 }
-EXPORT_SYMBOL(idr_get_next);
+EXPORT_SYMBOL(idr_get_next_ul);
 
 /**
- * idr_get_next_ul() - Find next populated entry.
+ * idr_get_next() - Find next populated entry.
  * @idr: IDR handle.
  * @nextid: Pointer to an ID.
  *
@@ -265,22 +261,17 @@ EXPORT_SYMBOL(idr_get_next);
  * to the ID of the found value.  To use in a loop, the value pointed to by
  * nextid must be incremented by the user.
  */
-void *idr_get_next_ul(struct idr *idr, unsigned long *nextid)
+void *idr_get_next(struct idr *idr, int *nextid)
 {
-	struct radix_tree_iter iter;
-	void __rcu **slot;
-	unsigned long base = idr->idr_base;
 	unsigned long id = *nextid;
+	void *entry = idr_get_next_ul(idr, &id);
 
-	id = (id < base) ? 0 : id - base;
-	slot = radix_tree_iter_find(&idr->idr_rt, &iter, id);
-	if (!slot)
+	if (WARN_ON_ONCE(id > INT_MAX))
 		return NULL;
-
-	*nextid = iter.index + base;
-	return rcu_dereference_raw(*slot);
+	*nextid = id;
+	return entry;
 }
-EXPORT_SYMBOL(idr_get_next_ul);
+EXPORT_SYMBOL(idr_get_next);
 
 /**
  * idr_replace() - replace pointer for given ID.
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 18c1dfbb1765..c8fa1d274530 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1529,7 +1529,7 @@ void __rcu **idr_get_free(struct radix_tree_root *root,
 			offset = radix_tree_find_next_bit(node, IDR_FREE,
 							offset + 1);
 			start = next_index(start, node, offset);
-			if (start > max)
+			if (start > max || start == 0)
 				return ERR_PTR(-ENOSPC);
 			while (offset == RADIX_TREE_MAP_SIZE) {
 				offset = node->offset + 1;
diff --git a/lib/test_xarray.c b/lib/test_xarray.c
index 9d631a7b6a70..7df4f7f395bf 100644
--- a/lib/test_xarray.c
+++ b/lib/test_xarray.c
@@ -1110,6 +1110,28 @@ static noinline void check_find_entry(struct xarray *xa)
 	XA_BUG_ON(xa, !xa_empty(xa));
 }
 
+static noinline void check_move_tiny(struct xarray *xa)
+{
+	XA_STATE(xas, xa, 0);
+
+	XA_BUG_ON(xa, !xa_empty(xa));
+	rcu_read_lock();
+	XA_BUG_ON(xa, xas_next(&xas) != NULL);
+	XA_BUG_ON(xa, xas_next(&xas) != NULL);
+	rcu_read_unlock();
+	xa_store_index(xa, 0, GFP_KERNEL);
+	rcu_read_lock();
+	xas_set(&xas, 0);
+	XA_BUG_ON(xa, xas_next(&xas) != xa_mk_index(0));
+	XA_BUG_ON(xa, xas_next(&xas) != NULL);
+	xas_set(&xas, 0);
+	XA_BUG_ON(xa, xas_prev(&xas) != xa_mk_index(0));
+	XA_BUG_ON(xa, xas_prev(&xas) != NULL);
+	rcu_read_unlock();
+	xa_erase_index(xa, 0);
+	XA_BUG_ON(xa, !xa_empty(xa));
+}
+
 static noinline void check_move_small(struct xarray *xa, unsigned long idx)
 {
 	XA_STATE(xas, xa, 0);
@@ -1217,6 +1239,8 @@ static noinline void check_move(struct xarray *xa)
 
 	xa_destroy(xa);
 
+	check_move_tiny(xa);
+
 	for (i = 0; i < 16; i++)
 		check_move_small(xa, 1UL << i);
 
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index e630e7ff57f1..45f57fd2db64 100644
--- a/lib/vdso/gettimeofday.c
+++ b/lib/vdso/gettimeofday.c
@@ -214,9 +214,10 @@ int __cvdso_clock_getres_common(clockid_t clock, struct __kernel_timespec *res)
 		return -1;
 	}
 
-	res->tv_sec = 0;
-	res->tv_nsec = ns;
-
+	if (likely(res)) {
+		res->tv_sec = 0;
+		res->tv_nsec = ns;
+	}
 	return 0;
 }
 
@@ -245,7 +246,7 @@ __cvdso_clock_getres_time32(clockid_t clock, struct old_timespec32 *res)
 		ret = clock_getres_fallback(clock, &ts);
 #endif
 
-	if (likely(!ret)) {
+	if (likely(!ret && res)) {
 		res->tv_sec = ts.tv_sec;
 		res->tv_nsec = ts.tv_nsec;
 	}
diff --git a/lib/xarray.c b/lib/xarray.c
index 446b956c9188..1237c213f52b 100644
--- a/lib/xarray.c
+++ b/lib/xarray.c
@@ -994,6 +994,8 @@ void *__xas_prev(struct xa_state *xas)
 
 	if (!xas_frozen(xas->xa_node))
 		xas->xa_index--;
+	if (!xas->xa_node)
+		return set_bounds(xas);
 	if (xas_not_node(xas->xa_node))
 		return xas_load(xas);
 
@@ -1031,6 +1033,8 @@ void *__xas_next(struct xa_state *xas)
 
 	if (!xas_frozen(xas->xa_node))
 		xas->xa_index++;
+	if (!xas->xa_node)
+		return set_bounds(xas);
 	if (xas_not_node(xas->xa_node))
 		return xas_load(xas);
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 0a1b4b484ac5..f05d27b7183d 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	anon_vma_lock_write(vma->anon_vma);
 
-	pte = pte_offset_map(pmd, address);
-	pte_ptl = pte_lockptr(mm, pmd);
-
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
 				address, address + HPAGE_PMD_SIZE);
 	mmu_notifier_invalidate_range_start(&range);
+
+	pte = pte_offset_map(pmd, address);
+	pte_ptl = pte_lockptr(mm, pmd);
+
 	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
 	/*
 	 * After this gup_fast can't run anymore. This also removes
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 363106578876..37592dd7ae32 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageHead(page) && PageSlab(page))
+	if (PageSlab(page) && !PageTail(page))
 		memcg = memcg_from_slab_page(page);
 	else
 		memcg = READ_ONCE(page->mem_cgroup);
@@ -2535,6 +2535,15 @@ retry:
 	}
 
 	/*
+	 * Memcg doesn't have a dedicated reserve for atomic
+	 * allocations. But like the global atomic pool, we need to
+	 * put the burden of reclaim on regular allocation requests
+	 * and let these go through as privileged allocations.
+	 */
+	if (gfp_mask & __GFP_ATOMIC)
+		goto force;
+
+	/*
 	 * Unlike in global OOM situations, memcg is not in a physical
 	 * memory shortage.  Allow dying and OOM-killed tasks to
 	 * bypass the last charges so that they can exit quickly and
@@ -5014,12 +5023,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	/*
-	 * Flush percpu vmstats and vmevents to guarantee the value correctness
-	 * on parent's and all ancestor levels.
-	 */
-	memcg_flush_percpu_vmstats(memcg, false);
-	memcg_flush_percpu_vmevents(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
@@ -5030,6 +5033,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	memcg_wb_domain_exit(memcg);
+	/*
+	 * Flush percpu vmstats and vmevents to guarantee the value correctness
+	 * on parent's and all ancestor levels.
+	 */
+	memcg_flush_percpu_vmstats(memcg, false);
+	memcg_flush_percpu_vmevents(memcg);
 	__mem_cgroup_free(memcg);
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index df570e5c71cc..07e5c67f48a8 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -447,6 +447,14 @@ static void update_pgdat_span(struct pglist_data *pgdat)
 					     zone->spanned_pages;
 
 		/* No need to lock the zones, they can't change. */
+		if (!zone->spanned_pages)
+			continue;
+		if (!node_end_pfn) {
+			node_start_pfn = zone->zone_start_pfn;
+			node_end_pfn = zone_end_pfn;
+			continue;
+		}
+
 		if (zone_end_pfn > node_end_pfn)
 			node_end_pfn = zone_end_pfn;
 		if (zone->zone_start_pfn < node_start_pfn)
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 7fde88695f35..9a889e456168 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -180,7 +180,7 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 					mn->ops->invalidate_range_start, _ret,
 					!mmu_notifier_range_blockable(range) ? "non-" : "");
 				WARN_ON(mmu_notifier_range_blockable(range) ||
-					ret != -EAGAIN);
+					_ret != -EAGAIN);
 				ret = _ret;
 			}
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ecc3dbad606b..f391c0c4ed1d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void)
 	wait_for_completion(&pgdat_init_all_done_comp);
 
 	/*
+	 * The number of managed pages has changed due to the initialisation
+	 * so the pcpu batch and high limits needs to be updated or the limits
+	 * will be artificially small.
+	 */
+	for_each_populated_zone(zone)
+		zone_pcp_update(zone);
+
+	/*
 	 * We initialized the rest of the deferred pages.  Permanently disable
 	 * on-demand struct page initialization.
 	 */
@@ -3720,10 +3728,6 @@ try_this_zone:
 static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
-	static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
-
-	if (!__ratelimit(&show_mem_rs))
-		return;
 
 	/*
 	 * This documents exceptions given to allocations in certain
@@ -3744,8 +3748,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
-				      DEFAULT_RATELIMIT_BURST);
+	static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
 
 	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
 		return;
@@ -8514,7 +8517,6 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages)
 	WARN(count != 0, "%d pages are still in use!\n", count);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.
@@ -8528,7 +8530,6 @@ void __meminit zone_pcp_update(struct zone *zone)
 				per_cpu_ptr(zone->pageset, cpu));
 	mutex_unlock(&pcp_batch_high_lock);
 }
-#endif
 
 void zone_pcp_reset(struct zone *zone)
 {
diff --git a/mm/slab.h b/mm/slab.h
index 68e455f2b698..b2b01694dc43 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
  * Expects a pointer to a slab page. Please note, that PageSlab() check
  * isn't sufficient, as it returns true also for tail compound slab pages,
  * which do not have slab_cache pointer set.
- * So this function assumes that the page can pass PageHead() and PageSlab()
- * checks.
+ * So this function assumes that the page can pass PageSlab() && !PageTail()
+ * check.
  *
  * The kmem_cache can be reparented asynchronously. The caller must ensure
  * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6afc892a148a..a8222041bd44 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1383,12 +1383,29 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
 			unsigned long freecount = 0;
 			struct free_area *area;
 			struct list_head *curr;
+			bool overflow = false;
 
 			area = &(zone->free_area[order]);
 
-			list_for_each(curr, &area->free_list[mtype])
-				freecount++;
-			seq_printf(m, "%6lu ", freecount);
+			list_for_each(curr, &area->free_list[mtype]) {
+				/*
+				 * Cap the free_list iteration because it might
+				 * be really large and we are under a spinlock
+				 * so a long time spent here could trigger a
+				 * hard lockup detector. Anyway this is a
+				 * debugging tool so knowing there is a handful
+				 * of pages of this order should be more than
+				 * sufficient.
+				 */
+				if (++freecount >= 100000) {
+					overflow = true;
+					break;
+				}
+			}
+			seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount);
+			spin_unlock_irq(&zone->lock);
+			cond_resched();
+			spin_lock_irq(&zone->lock);
 		}
 		seq_putc(m, '\n');
 	}
@@ -1972,7 +1989,7 @@ void __init init_mm_internals(void)
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
-	proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op);
+	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
 	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
 	proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
 #endif
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 54728d2eda18..d4bcfd8f95bf 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -172,7 +172,6 @@ int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (err < 0)
 		goto out_uninit_mvrp;
 
-	vlan->nest_level = dev_get_nest_level(real_dev) + 1;
 	err = register_netdevice(dev);
 	if (err < 0)
 		goto out_uninit_mvrp;
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 93eadf179123..e5bff5cc6f97 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -489,36 +489,6 @@ static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
 	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
-/*
- * vlan network devices have devices nesting below it, and are a special
- * "super class" of normal network devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key vlan_netdev_xmit_lock_key;
-static struct lock_class_key vlan_netdev_addr_lock_key;
-
-static void vlan_dev_set_lockdep_one(struct net_device *dev,
-				     struct netdev_queue *txq,
-				     void *_subclass)
-{
-	lockdep_set_class_and_subclass(&txq->_xmit_lock,
-				       &vlan_netdev_xmit_lock_key,
-				       *(int *)_subclass);
-}
-
-static void vlan_dev_set_lockdep_class(struct net_device *dev, int subclass)
-{
-	lockdep_set_class_and_subclass(&dev->addr_list_lock,
-				       &vlan_netdev_addr_lock_key,
-				       subclass);
-	netdev_for_each_tx_queue(dev, vlan_dev_set_lockdep_one, &subclass);
-}
-
-static int vlan_dev_get_lock_subclass(struct net_device *dev)
-{
-	return vlan_dev_priv(dev)->nest_level;
-}
-
 static const struct header_ops vlan_header_ops = {
 	.create	 = vlan_dev_hard_header,
 	.parse	 = eth_header_parse,
@@ -609,8 +579,6 @@ static int vlan_dev_init(struct net_device *dev)
 
 	SET_NETDEV_DEVTYPE(dev, &vlan_type);
 
-	vlan_dev_set_lockdep_class(dev, vlan_dev_get_lock_subclass(dev));
-
 	vlan->vlan_pcpu_stats = netdev_alloc_pcpu_stats(struct vlan_pcpu_stats);
 	if (!vlan->vlan_pcpu_stats)
 		return -ENOMEM;
@@ -812,7 +780,6 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
 #endif
 	.ndo_fix_features	= vlan_dev_fix_features,
-	.ndo_get_lock_subclass  = vlan_dev_get_lock_subclass,
 	.ndo_get_iflink		= vlan_dev_get_iflink,
 };
 
diff --git a/net/atm/common.c b/net/atm/common.c
index b7528e77997c..0ce530af534d 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -668,7 +668,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 		mask |= EPOLLHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* writable? */
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index d78938e3e008..5b0b20e6da95 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -22,6 +22,8 @@
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
+#include <linux/lockdep.h>
+#include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/pkt_sched.h>
@@ -193,14 +195,18 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 	unsigned char *ogm_buff;
 	u32 random_seqno;
 
+	mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
 	/* randomize initial seqno to avoid collision */
 	get_random_bytes(&random_seqno, sizeof(random_seqno));
 	atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno);
 
 	hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN;
 	ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC);
-	if (!ogm_buff)
+	if (!ogm_buff) {
+		mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
 		return -ENOMEM;
+	}
 
 	hard_iface->bat_iv.ogm_buff = ogm_buff;
 
@@ -212,35 +218,59 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 	batadv_ogm_packet->reserved = 0;
 	batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE;
 
+	mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
+
 	return 0;
 }
 
 static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
 {
+	mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
 	kfree(hard_iface->bat_iv.ogm_buff);
 	hard_iface->bat_iv.ogm_buff = NULL;
+
+	mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
 }
 
 static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface)
 {
 	struct batadv_ogm_packet *batadv_ogm_packet;
-	unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff;
+	void *ogm_buff;
 
-	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
+	mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
+	ogm_buff = hard_iface->bat_iv.ogm_buff;
+	if (!ogm_buff)
+		goto unlock;
+
+	batadv_ogm_packet = ogm_buff;
 	ether_addr_copy(batadv_ogm_packet->orig,
 			hard_iface->net_dev->dev_addr);
 	ether_addr_copy(batadv_ogm_packet->prev_sender,
 			hard_iface->net_dev->dev_addr);
+
+unlock:
+	mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
 }
 
 static void
 batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface)
 {
 	struct batadv_ogm_packet *batadv_ogm_packet;
-	unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff;
+	void *ogm_buff;
 
-	batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff;
+	mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+
+	ogm_buff = hard_iface->bat_iv.ogm_buff;
+	if (!ogm_buff)
+		goto unlock;
+
+	batadv_ogm_packet = ogm_buff;
 	batadv_ogm_packet->ttl = BATADV_TTL;
+
+unlock:
+	mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
 }
 
 /* when do we schedule our own ogm to be sent */
@@ -742,7 +772,11 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
 	}
 }
 
-static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
+/**
+ * batadv_iv_ogm_schedule_buff() - schedule submission of hardif ogm buffer
+ * @hard_iface: interface whose ogm buffer should be transmitted
+ */
+static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
 	unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff;
@@ -753,9 +787,7 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
 	u16 tvlv_len = 0;
 	unsigned long send_time;
 
-	if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
-	    hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
-		return;
+	lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex);
 
 	/* the interface gets activated here to avoid race conditions between
 	 * the moment of activating the interface in
@@ -823,6 +855,17 @@ out:
 		batadv_hardif_put(primary_if);
 }
 
+static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface)
+{
+	if (hard_iface->if_status == BATADV_IF_NOT_IN_USE ||
+	    hard_iface->if_status == BATADV_IF_TO_BE_REMOVED)
+		return;
+
+	mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex);
+	batadv_iv_ogm_schedule_buff(hard_iface);
+	mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex);
+}
+
 /**
  * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over iterface
  * @orig_node: originator which reproadcasted the OGMs directly
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index dc4f7430cb5a..8033f24f506c 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -18,6 +18,7 @@
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
+#include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
@@ -256,14 +257,12 @@ static void batadv_v_ogm_queue_on_if(struct sk_buff *skb,
 }
 
 /**
- * batadv_v_ogm_send() - periodic worker broadcasting the own OGM
- * @work: work queue item
+ * batadv_v_ogm_send_softif() - periodic worker broadcasting the own OGM
+ * @bat_priv: the bat priv with all the soft interface information
  */
-static void batadv_v_ogm_send(struct work_struct *work)
+static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv)
 {
 	struct batadv_hard_iface *hard_iface;
-	struct batadv_priv_bat_v *bat_v;
-	struct batadv_priv *bat_priv;
 	struct batadv_ogm2_packet *ogm_packet;
 	struct sk_buff *skb, *skb_tmp;
 	unsigned char *ogm_buff;
@@ -271,8 +270,7 @@ static void batadv_v_ogm_send(struct work_struct *work)
 	u16 tvlv_len = 0;
 	int ret;
 
-	bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work);
-	bat_priv = container_of(bat_v, struct batadv_priv, bat_v);
+	lockdep_assert_held(&bat_priv->bat_v.ogm_buff_mutex);
 
 	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
 		goto out;
@@ -364,6 +362,23 @@ out:
 }
 
 /**
+ * batadv_v_ogm_send() - periodic worker broadcasting the own OGM
+ * @work: work queue item
+ */
+static void batadv_v_ogm_send(struct work_struct *work)
+{
+	struct batadv_priv_bat_v *bat_v;
+	struct batadv_priv *bat_priv;
+
+	bat_v = container_of(work, struct batadv_priv_bat_v, ogm_wq.work);
+	bat_priv = container_of(bat_v, struct batadv_priv, bat_v);
+
+	mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
+	batadv_v_ogm_send_softif(bat_priv);
+	mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
+}
+
+/**
  * batadv_v_ogm_aggr_work() - OGM queue periodic task per interface
  * @work: work queue item
  *
@@ -424,11 +439,15 @@ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface)
 	struct batadv_priv *bat_priv = netdev_priv(primary_iface->soft_iface);
 	struct batadv_ogm2_packet *ogm_packet;
 
+	mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
 	if (!bat_priv->bat_v.ogm_buff)
-		return;
+		goto unlock;
 
 	ogm_packet = (struct batadv_ogm2_packet *)bat_priv->bat_v.ogm_buff;
 	ether_addr_copy(ogm_packet->orig, primary_iface->net_dev->dev_addr);
+
+unlock:
+	mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
 }
 
 /**
@@ -1050,6 +1069,8 @@ int batadv_v_ogm_init(struct batadv_priv *bat_priv)
 	atomic_set(&bat_priv->bat_v.ogm_seqno, random_seqno);
 	INIT_DELAYED_WORK(&bat_priv->bat_v.ogm_wq, batadv_v_ogm_send);
 
+	mutex_init(&bat_priv->bat_v.ogm_buff_mutex);
+
 	return 0;
 }
 
@@ -1061,7 +1082,11 @@ void batadv_v_ogm_free(struct batadv_priv *bat_priv)
 {
 	cancel_delayed_work_sync(&bat_priv->bat_v.ogm_wq);
 
+	mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
+
 	kfree(bat_priv->bat_v.ogm_buff);
 	bat_priv->bat_v.ogm_buff = NULL;
 	bat_priv->bat_v.ogm_buff_len = 0;
+
+	mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
 }
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index c90e47342bb0..afb52282d5bd 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -18,6 +18,7 @@
 #include <linux/kref.h>
 #include <linux/limits.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
 #include <linux/rculist.h>
@@ -929,6 +930,7 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	INIT_LIST_HEAD(&hard_iface->list);
 	INIT_HLIST_HEAD(&hard_iface->neigh_list);
 
+	mutex_init(&hard_iface->bat_iv.ogm_buff_mutex);
 	spin_lock_init(&hard_iface->neigh_list_lock);
 	kref_init(&hard_iface->refcount);
 
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 9cbed6f5a85a..5ee8e9a100f9 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -740,36 +740,6 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
 	return 0;
 }
 
-/* batman-adv network devices have devices nesting below it and are a special
- * "super class" of normal network devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key batadv_netdev_xmit_lock_key;
-static struct lock_class_key batadv_netdev_addr_lock_key;
-
-/**
- * batadv_set_lockdep_class_one() - Set lockdep class for a single tx queue
- * @dev: device which owns the tx queue
- * @txq: tx queue to modify
- * @_unused: always NULL
- */
-static void batadv_set_lockdep_class_one(struct net_device *dev,
-					 struct netdev_queue *txq,
-					 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &batadv_netdev_xmit_lock_key);
-}
-
-/**
- * batadv_set_lockdep_class() - Set txq and addr_list lockdep class
- * @dev: network device to modify
- */
-static void batadv_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &batadv_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, batadv_set_lockdep_class_one, NULL);
-}
-
 /**
  * batadv_softif_init_late() - late stage initialization of soft interface
  * @dev: registered network device to modify
@@ -783,8 +753,6 @@ static int batadv_softif_init_late(struct net_device *dev)
 	int ret;
 	size_t cnt_len = sizeof(u64) * BATADV_CNT_NUM;
 
-	batadv_set_lockdep_class(dev);
-
 	bat_priv = netdev_priv(dev);
 	bat_priv->soft_iface = dev;
 
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index be7c02aa91e2..4d7f1baee7b7 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -17,6 +17,7 @@
 #include <linux/if.h>
 #include <linux/if_ether.h>
 #include <linux/kref.h>
+#include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/sched.h> /* for linux/wait.h */
@@ -81,6 +82,9 @@ struct batadv_hard_iface_bat_iv {
 
 	/** @ogm_seqno: OGM sequence number - used to identify each OGM */
 	atomic_t ogm_seqno;
+
+	/** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */
+	struct mutex ogm_buff_mutex;
 };
 
 /**
@@ -1539,6 +1543,9 @@ struct batadv_priv_bat_v {
 	/** @ogm_seqno: OGM sequence number - used to identify each OGM */
 	atomic_t ogm_seqno;
 
+	/** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */
+	struct mutex ogm_buff_mutex;
+
 	/** @ogm_wq: workqueue used to schedule OGM transmissions */
 	struct delayed_work ogm_wq;
 };
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index bb55d92691b0..4febc82a7c76 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -571,15 +571,7 @@ static netdev_tx_t bt_xmit(struct sk_buff *skb, struct net_device *netdev)
 	return err < 0 ? NET_XMIT_DROP : err;
 }
 
-static int bt_dev_init(struct net_device *dev)
-{
-	netdev_lockdep_set_classes(dev);
-
-	return 0;
-}
-
 static const struct net_device_ops netdev_ops = {
-	.ndo_init		= bt_dev_init,
 	.ndo_start_xmit		= bt_xmit,
 };
 
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 94ddf19998c7..5f508c50649d 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -460,7 +460,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
 	if (sk->sk_state == BT_LISTEN)
 		return bt_accept_poll(sk);
 
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
@@ -470,7 +470,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock,
 	if (sk->sk_shutdown == SHUTDOWN_MASK)
 		mask |= EPOLLHUP;
 
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	if (sk->sk_state == BT_CLOSED)
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 681b72862c16..e804a3016902 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -24,8 +24,6 @@
 const struct nf_br_ops __rcu *nf_br_ops __read_mostly;
 EXPORT_SYMBOL_GPL(nf_br_ops);
 
-static struct lock_class_key bridge_netdev_addr_lock_key;
-
 /* net device transmit always called with BH disabled */
 netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 {
@@ -108,11 +106,6 @@ out:
 	return NETDEV_TX_OK;
 }
 
-static void br_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &bridge_netdev_addr_lock_key);
-}
-
 static int br_dev_init(struct net_device *dev)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -150,7 +143,6 @@ static int br_dev_init(struct net_device *dev)
 		br_mdb_hash_fini(br);
 		br_fdb_hash_fini(br);
 	}
-	br_set_lockdep_class(dev);
 
 	return err;
 }
diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index ed91ea31978a..12a4f4d93681 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -20,7 +20,6 @@ static unsigned int
 ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_nat_info *info = par->targinfo;
-	struct net_device *dev;
 
 	if (skb_ensure_writable(skb, ETH_ALEN))
 		return EBT_DROP;
@@ -33,10 +32,22 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		else
 			skb->pkt_type = PACKET_MULTICAST;
 	} else {
-		if (xt_hooknum(par) != NF_BR_BROUTING)
-			dev = br_port_get_rcu(xt_in(par))->br->dev;
-		else
+		const struct net_device *dev;
+
+		switch (xt_hooknum(par)) {
+		case NF_BR_BROUTING:
 			dev = xt_in(par);
+			break;
+		case NF_BR_PRE_ROUTING:
+			dev = br_port_get_rcu(xt_in(par))->br->dev;
+			break;
+		default:
+			dev = NULL;
+			break;
+		}
+
+		if (!dev) /* NF_BR_LOCAL_OUT */
+			return info->target;
 
 		if (ether_addr_equal(info->mac, dev->dev_addr))
 			skb->pkt_type = PACKET_HOST;
diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c
index 506d6141e44e..809673222382 100644
--- a/net/bridge/netfilter/nf_conntrack_bridge.c
+++ b/net/bridge/netfilter/nf_conntrack_bridge.c
@@ -95,7 +95,7 @@ slow_path:
 	 * This may also be a clone skbuff, we could preserve the geometry for
 	 * the copies but probably not worth the effort.
 	 */
-	ip_frag_init(skb, hlen, ll_rs, frag_max_size, &state);
+	ip_frag_init(skb, hlen, ll_rs, frag_max_size, false, &state);
 
 	while (state.left > 0) {
 		struct sk_buff *skb2;
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 13ea920600ae..ef14da50a981 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -953,7 +953,7 @@ static __poll_t caif_poll(struct file *file,
 		mask |= EPOLLRDHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue) ||
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
 		(sk->sk_shutdown & RCV_SHUTDOWN))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 37c1040bcb9c..4d8ba701e15d 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -580,6 +580,7 @@ static int j1939_sk_release(struct socket *sock)
 		j1939_netdev_stop(priv);
 	}
 
+	kfree(jsk->filters);
 	sock_orphan(sk);
 	sock->sk = NULL;
 
@@ -909,8 +910,10 @@ void j1939_sk_errqueue(struct j1939_session *session,
 	memset(serr, 0, sizeof(*serr));
 	switch (type) {
 	case J1939_ERRQUEUE_ACK:
-		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK))
+		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_ACK)) {
+			kfree_skb(skb);
 			return;
+		}
 
 		serr->ee.ee_errno = ENOMSG;
 		serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
@@ -918,8 +921,10 @@ void j1939_sk_errqueue(struct j1939_session *session,
 		state = "ACK";
 		break;
 	case J1939_ERRQUEUE_SCHED:
-		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED))
+		if (!(sk->sk_tsflags & SOF_TIMESTAMPING_TX_SCHED)) {
+			kfree_skb(skb);
 			return;
+		}
 
 		serr->ee.ee_errno = ENOMSG;
 		serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING;
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index fe000ea757ea..e5f1a56994c6 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1273,9 +1273,27 @@ j1939_xtp_rx_abort(struct j1939_priv *priv, struct sk_buff *skb,
 static void
 j1939_xtp_rx_eoma_one(struct j1939_session *session, struct sk_buff *skb)
 {
+	struct j1939_sk_buff_cb *skcb = j1939_skb_to_cb(skb);
+	const u8 *dat;
+	int len;
+
 	if (j1939_xtp_rx_cmd_bad_pgn(session, skb))
 		return;
 
+	dat = skb->data;
+
+	if (skcb->addr.type == J1939_ETP)
+		len = j1939_etp_ctl_to_size(dat);
+	else
+		len = j1939_tp_ctl_to_size(dat);
+
+	if (session->total_message_size != len) {
+		netdev_warn_once(session->priv->ndev,
+				 "%s: 0x%p: Incorrect size. Expected: %i; got: %i.\n",
+				 __func__, session, session->total_message_size,
+				 len);
+	}
+
 	netdev_dbg(session->priv->ndev, "%s: 0x%p\n", __func__, session);
 
 	session->pkt.tx_acked = session->pkt.total;
@@ -1432,7 +1450,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv,
 	skcb = j1939_skb_to_cb(skb);
 	memcpy(skcb, rel_skcb, sizeof(*skcb));
 
-	session = j1939_session_new(priv, skb, skb->len);
+	session = j1939_session_new(priv, skb, size);
 	if (!session) {
 		kfree_skb(skb);
 		return NULL;
diff --git a/net/core/datagram.c b/net/core/datagram.c
index c210fc116103..da3c24ed129c 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -97,7 +97,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
 	if (error)
 		goto out_err;
 
-	if (sk->sk_receive_queue.prev != skb)
+	if (READ_ONCE(sk->sk_receive_queue.prev) != skb)
 		goto out;
 
 	/* Socket shut down? */
@@ -278,7 +278,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags,
 			break;
 
 		sk_busy_loop(sk, flags & MSG_DONTWAIT);
-	} while (sk->sk_receive_queue.prev != *last);
+	} while (READ_ONCE(sk->sk_receive_queue.prev) != *last);
 
 	error = -EAGAIN;
 
@@ -767,7 +767,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 	mask = 0;
 
 	/* exceptional events? */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
@@ -777,7 +777,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
diff --git a/net/core/dev.c b/net/core/dev.c
index bf3ed413abaf..99ac84ff398f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -146,6 +146,7 @@
 #include "net-sysfs.h"
 
 #define MAX_GRO_SKBS 8
+#define MAX_NEST_DEV 8
 
 /* This should be increased if a protocol with a bigger head is added. */
 #define GRO_MAX_HEAD (MAX_HEADER + 128)
@@ -276,88 +277,6 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
 DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 EXPORT_PER_CPU_SYMBOL(softnet_data);
 
-#ifdef CONFIG_LOCKDEP
-/*
- * register_netdevice() inits txq->_xmit_lock and sets lockdep class
- * according to dev->type
- */
-static const unsigned short netdev_lock_type[] = {
-	 ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25,
-	 ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET,
-	 ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM,
-	 ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP,
-	 ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD,
-	 ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25,
-	 ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP,
-	 ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD,
-	 ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI,
-	 ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE,
-	 ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET,
-	 ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL,
-	 ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM,
-	 ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE,
-	 ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE};
-
-static const char *const netdev_lock_name[] = {
-	"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25",
-	"_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET",
-	"_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM",
-	"_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP",
-	"_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD",
-	"_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25",
-	"_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP",
-	"_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD",
-	"_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI",
-	"_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE",
-	"_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET",
-	"_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL",
-	"_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM",
-	"_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE",
-	"_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"};
-
-static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)];
-static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)];
-
-static inline unsigned short netdev_lock_pos(unsigned short dev_type)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++)
-		if (netdev_lock_type[i] == dev_type)
-			return i;
-	/* the last key is used by default */
-	return ARRAY_SIZE(netdev_lock_type) - 1;
-}
-
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
-						 unsigned short dev_type)
-{
-	int i;
-
-	i = netdev_lock_pos(dev_type);
-	lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i],
-				   netdev_lock_name[i]);
-}
-
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
-	int i;
-
-	i = netdev_lock_pos(dev->type);
-	lockdep_set_class_and_name(&dev->addr_list_lock,
-				   &netdev_addr_lock_key[i],
-				   netdev_lock_name[i]);
-}
-#else
-static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock,
-						 unsigned short dev_type)
-{
-}
-static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
-{
-}
-#endif
-
 /*******************************************************************************
  *
  *		Protocol management and registration routines
@@ -6489,6 +6408,9 @@ struct netdev_adjacent {
 	/* upper master flag, there can only be one master device per list */
 	bool master;
 
+	/* lookup ignore flag */
+	bool ignore;
+
 	/* counter for the number of times this device was added to us */
 	u16 ref_nr;
 
@@ -6511,7 +6433,7 @@ static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev,
 	return NULL;
 }
 
-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data)
+static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data)
 {
 	struct net_device *dev = data;
 
@@ -6532,7 +6454,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
 {
 	ASSERT_RTNL();
 
-	return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+	return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
 					     upper_dev);
 }
 EXPORT_SYMBOL(netdev_has_upper_dev);
@@ -6550,7 +6472,7 @@ EXPORT_SYMBOL(netdev_has_upper_dev);
 bool netdev_has_upper_dev_all_rcu(struct net_device *dev,
 				  struct net_device *upper_dev)
 {
-	return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev,
+	return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev,
 					       upper_dev);
 }
 EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu);
@@ -6594,6 +6516,22 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_master_upper_dev_get);
 
+static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev)
+{
+	struct netdev_adjacent *upper;
+
+	ASSERT_RTNL();
+
+	if (list_empty(&dev->adj_list.upper))
+		return NULL;
+
+	upper = list_first_entry(&dev->adj_list.upper,
+				 struct netdev_adjacent, list);
+	if (likely(upper->master) && !upper->ignore)
+		return upper->dev;
+	return NULL;
+}
+
 /**
  * netdev_has_any_lower_dev - Check if device is linked to some device
  * @dev: device
@@ -6644,6 +6582,23 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev,
 }
 EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);
 
+static struct net_device *__netdev_next_upper_dev(struct net_device *dev,
+						  struct list_head **iter,
+						  bool *ignore)
+{
+	struct netdev_adjacent *upper;
+
+	upper = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&upper->list == &dev->adj_list.upper)
+		return NULL;
+
+	*iter = &upper->list;
+	*ignore = upper->ignore;
+
+	return upper->dev;
+}
+
 static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
 						    struct list_head **iter)
 {
@@ -6661,34 +6616,111 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev,
 	return upper->dev;
 }
 
+static int __netdev_walk_all_upper_dev(struct net_device *dev,
+				       int (*fn)(struct net_device *dev,
+						 void *data),
+				       void *data)
+{
+	struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
+	bool ignore;
+
+	now = dev;
+	iter = &dev->adj_list.upper;
+
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			udev = __netdev_next_upper_dev(now, &iter, &ignore);
+			if (!udev)
+				break;
+			if (ignore)
+				continue;
+
+			next = udev;
+			niter = &udev->adj_list.upper;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return 0;
+}
+
 int netdev_walk_all_upper_dev_rcu(struct net_device *dev,
 				  int (*fn)(struct net_device *dev,
 					    void *data),
 				  void *data)
 {
-	struct net_device *udev;
-	struct list_head *iter;
-	int ret;
+	struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
 
-	for (iter = &dev->adj_list.upper,
-	     udev = netdev_next_upper_dev_rcu(dev, &iter);
-	     udev;
-	     udev = netdev_next_upper_dev_rcu(dev, &iter)) {
-		/* first is the upper device itself */
-		ret = fn(udev, data);
-		if (ret)
-			return ret;
+	now = dev;
+	iter = &dev->adj_list.upper;
 
-		/* then look at all of its upper devices */
-		ret = netdev_walk_all_upper_dev_rcu(udev, fn, data);
-		if (ret)
-			return ret;
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			udev = netdev_next_upper_dev_rcu(now, &iter);
+			if (!udev)
+				break;
+
+			next = udev;
+			niter = &udev->adj_list.upper;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
 	}
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);
 
+static bool __netdev_has_upper_dev(struct net_device *dev,
+				   struct net_device *upper_dev)
+{
+	ASSERT_RTNL();
+
+	return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev,
+					   upper_dev);
+}
+
 /**
  * netdev_lower_get_next_private - Get the next ->private from the
  *				   lower neighbour list
@@ -6785,34 +6817,119 @@ static struct net_device *netdev_next_lower_dev(struct net_device *dev,
 	return lower->dev;
 }
 
+static struct net_device *__netdev_next_lower_dev(struct net_device *dev,
+						  struct list_head **iter,
+						  bool *ignore)
+{
+	struct netdev_adjacent *lower;
+
+	lower = list_entry((*iter)->next, struct netdev_adjacent, list);
+
+	if (&lower->list == &dev->adj_list.lower)
+		return NULL;
+
+	*iter = &lower->list;
+	*ignore = lower->ignore;
+
+	return lower->dev;
+}
+
 int netdev_walk_all_lower_dev(struct net_device *dev,
 			      int (*fn)(struct net_device *dev,
 					void *data),
 			      void *data)
 {
-	struct net_device *ldev;
-	struct list_head *iter;
-	int ret;
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
 
-	for (iter = &dev->adj_list.lower,
-	     ldev = netdev_next_lower_dev(dev, &iter);
-	     ldev;
-	     ldev = netdev_next_lower_dev(dev, &iter)) {
-		/* first is the lower device itself */
-		ret = fn(ldev, data);
-		if (ret)
-			return ret;
+	now = dev;
+	iter = &dev->adj_list.lower;
 
-		/* then look at all of its lower devices */
-		ret = netdev_walk_all_lower_dev(ldev, fn, data);
-		if (ret)
-			return ret;
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
 	}
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);
 
+static int __netdev_walk_all_lower_dev(struct net_device *dev,
+				       int (*fn)(struct net_device *dev,
+						 void *data),
+				       void *data)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
+	bool ignore;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			ldev = __netdev_next_lower_dev(now, &iter, &ignore);
+			if (!ldev)
+				break;
+			if (ignore)
+				continue;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
+	}
+
+	return 0;
+}
+
 static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 						    struct list_head **iter)
 {
@@ -6827,28 +6944,99 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev,
 	return lower->dev;
 }
 
-int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
-				  int (*fn)(struct net_device *dev,
-					    void *data),
-				  void *data)
+static u8 __netdev_upper_depth(struct net_device *dev)
+{
+	struct net_device *udev;
+	struct list_head *iter;
+	u8 max_depth = 0;
+	bool ignore;
+
+	for (iter = &dev->adj_list.upper,
+	     udev = __netdev_next_upper_dev(dev, &iter, &ignore);
+	     udev;
+	     udev = __netdev_next_upper_dev(dev, &iter, &ignore)) {
+		if (ignore)
+			continue;
+		if (max_depth < udev->upper_level)
+			max_depth = udev->upper_level;
+	}
+
+	return max_depth;
+}
+
+static u8 __netdev_lower_depth(struct net_device *dev)
 {
 	struct net_device *ldev;
 	struct list_head *iter;
-	int ret;
+	u8 max_depth = 0;
+	bool ignore;
 
 	for (iter = &dev->adj_list.lower,
-	     ldev = netdev_next_lower_dev_rcu(dev, &iter);
+	     ldev = __netdev_next_lower_dev(dev, &iter, &ignore);
 	     ldev;
-	     ldev = netdev_next_lower_dev_rcu(dev, &iter)) {
-		/* first is the lower device itself */
-		ret = fn(ldev, data);
-		if (ret)
-			return ret;
+	     ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) {
+		if (ignore)
+			continue;
+		if (max_depth < ldev->lower_level)
+			max_depth = ldev->lower_level;
+	}
 
-		/* then look at all of its lower devices */
-		ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data);
-		if (ret)
-			return ret;
+	return max_depth;
+}
+
+static int __netdev_update_upper_level(struct net_device *dev, void *data)
+{
+	dev->upper_level = __netdev_upper_depth(dev) + 1;
+	return 0;
+}
+
+static int __netdev_update_lower_level(struct net_device *dev, void *data)
+{
+	dev->lower_level = __netdev_lower_depth(dev) + 1;
+	return 0;
+}
+
+int netdev_walk_all_lower_dev_rcu(struct net_device *dev,
+				  int (*fn)(struct net_device *dev,
+					    void *data),
+				  void *data)
+{
+	struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1];
+	struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1];
+	int ret, cur = 0;
+
+	now = dev;
+	iter = &dev->adj_list.lower;
+
+	while (1) {
+		if (now != dev) {
+			ret = fn(now, data);
+			if (ret)
+				return ret;
+		}
+
+		next = NULL;
+		while (1) {
+			ldev = netdev_next_lower_dev_rcu(now, &iter);
+			if (!ldev)
+				break;
+
+			next = ldev;
+			niter = &ldev->adj_list.lower;
+			dev_stack[cur] = now;
+			iter_stack[cur++] = iter;
+			break;
+		}
+
+		if (!next) {
+			if (!cur)
+				return 0;
+			next = dev_stack[--cur];
+			niter = iter_stack[cur];
+		}
+
+		now = next;
+		iter = niter;
 	}
 
 	return 0;
@@ -6952,6 +7140,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev,
 	adj->master = master;
 	adj->ref_nr = 1;
 	adj->private = private;
+	adj->ignore = false;
 	dev_hold(adj_dev);
 
 	pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n",
@@ -7102,14 +7291,17 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 		return -EBUSY;
 
 	/* To prevent loops, check if dev is not upper device to upper_dev. */
-	if (netdev_has_upper_dev(upper_dev, dev))
+	if (__netdev_has_upper_dev(upper_dev, dev))
 		return -EBUSY;
 
+	if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV)
+		return -EMLINK;
+
 	if (!master) {
-		if (netdev_has_upper_dev(dev, upper_dev))
+		if (__netdev_has_upper_dev(dev, upper_dev))
 			return -EEXIST;
 	} else {
-		master_dev = netdev_master_upper_dev_get(dev);
+		master_dev = __netdev_master_upper_dev_get(dev);
 		if (master_dev)
 			return master_dev == upper_dev ? -EEXIST : -EBUSY;
 	}
@@ -7131,6 +7323,13 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (ret)
 		goto rollback;
 
+	__netdev_update_upper_level(dev, NULL);
+	__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+	__netdev_update_lower_level(upper_dev, NULL);
+	__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+				    NULL);
+
 	return 0;
 
 rollback:
@@ -7213,9 +7412,96 @@ void netdev_upper_dev_unlink(struct net_device *dev,
 
 	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER,
 				      &changeupper_info.info);
+
+	__netdev_update_upper_level(dev, NULL);
+	__netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL);
+
+	__netdev_update_lower_level(upper_dev, NULL);
+	__netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level,
+				    NULL);
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
+static void __netdev_adjacent_dev_set(struct net_device *upper_dev,
+				      struct net_device *lower_dev,
+				      bool val)
+{
+	struct netdev_adjacent *adj;
+
+	adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower);
+	if (adj)
+		adj->ignore = val;
+
+	adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper);
+	if (adj)
+		adj->ignore = val;
+}
+
+static void netdev_adjacent_dev_disable(struct net_device *upper_dev,
+					struct net_device *lower_dev)
+{
+	__netdev_adjacent_dev_set(upper_dev, lower_dev, true);
+}
+
+static void netdev_adjacent_dev_enable(struct net_device *upper_dev,
+				       struct net_device *lower_dev)
+{
+	__netdev_adjacent_dev_set(upper_dev, lower_dev, false);
+}
+
+int netdev_adjacent_change_prepare(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev,
+				   struct netlink_ext_ack *extack)
+{
+	int err;
+
+	if (!new_dev)
+		return 0;
+
+	if (old_dev && new_dev != old_dev)
+		netdev_adjacent_dev_disable(dev, old_dev);
+
+	err = netdev_upper_dev_link(new_dev, dev, extack);
+	if (err) {
+		if (old_dev && new_dev != old_dev)
+			netdev_adjacent_dev_enable(dev, old_dev);
+		return err;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(netdev_adjacent_change_prepare);
+
+void netdev_adjacent_change_commit(struct net_device *old_dev,
+				   struct net_device *new_dev,
+				   struct net_device *dev)
+{
+	if (!new_dev || !old_dev)
+		return;
+
+	if (new_dev == old_dev)
+		return;
+
+	netdev_adjacent_dev_enable(dev, old_dev);
+	netdev_upper_dev_unlink(old_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_commit);
+
+void netdev_adjacent_change_abort(struct net_device *old_dev,
+				  struct net_device *new_dev,
+				  struct net_device *dev)
+{
+	if (!new_dev)
+		return;
+
+	if (old_dev && new_dev != old_dev)
+		netdev_adjacent_dev_enable(dev, old_dev);
+
+	netdev_upper_dev_unlink(new_dev, dev);
+}
+EXPORT_SYMBOL(netdev_adjacent_change_abort);
+
 /**
  * netdev_bonding_info_change - Dispatch event about slave change
  * @dev: device
@@ -7329,25 +7615,6 @@ void *netdev_lower_dev_get_private(struct net_device *dev,
 EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
 
-int dev_get_nest_level(struct net_device *dev)
-{
-	struct net_device *lower = NULL;
-	struct list_head *iter;
-	int max_nest = -1;
-	int nest;
-
-	ASSERT_RTNL();
-
-	netdev_for_each_lower_dev(dev, lower, iter) {
-		nest = dev_get_nest_level(lower);
-		if (max_nest < nest)
-			max_nest = nest;
-	}
-
-	return max_nest + 1;
-}
-EXPORT_SYMBOL(dev_get_nest_level);
-
 /**
  * netdev_lower_change - Dispatch event about lower device state change
  * @lower_dev: device
@@ -8154,7 +8421,8 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 			return -EINVAL;
 		}
 
-		if (prog->aux->id == prog_id) {
+		/* prog->aux->id may be 0 for orphaned device-bound progs */
+		if (prog->aux->id && prog->aux->id == prog_id) {
 			bpf_prog_put(prog);
 			return 0;
 		}
@@ -8619,7 +8887,7 @@ static void netdev_init_one_queue(struct net_device *dev,
 {
 	/* Initialize queue lock */
 	spin_lock_init(&queue->_xmit_lock);
-	netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type);
+	lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key);
 	queue->xmit_lock_owner = -1;
 	netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
 	queue->dev = dev;
@@ -8666,6 +8934,43 @@ void netif_tx_stop_all_queues(struct net_device *dev)
 }
 EXPORT_SYMBOL(netif_tx_stop_all_queues);
 
+static void netdev_register_lockdep_key(struct net_device *dev)
+{
+	lockdep_register_key(&dev->qdisc_tx_busylock_key);
+	lockdep_register_key(&dev->qdisc_running_key);
+	lockdep_register_key(&dev->qdisc_xmit_lock_key);
+	lockdep_register_key(&dev->addr_list_lock_key);
+}
+
+static void netdev_unregister_lockdep_key(struct net_device *dev)
+{
+	lockdep_unregister_key(&dev->qdisc_tx_busylock_key);
+	lockdep_unregister_key(&dev->qdisc_running_key);
+	lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+	lockdep_unregister_key(&dev->addr_list_lock_key);
+}
+
+void netdev_update_lockdep_key(struct net_device *dev)
+{
+	struct netdev_queue *queue;
+	int i;
+
+	lockdep_unregister_key(&dev->qdisc_xmit_lock_key);
+	lockdep_unregister_key(&dev->addr_list_lock_key);
+
+	lockdep_register_key(&dev->qdisc_xmit_lock_key);
+	lockdep_register_key(&dev->addr_list_lock_key);
+
+	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
+	for (i = 0; i < dev->num_tx_queues; i++) {
+		queue = netdev_get_tx_queue(dev, i);
+
+		lockdep_set_class(&queue->_xmit_lock,
+				  &dev->qdisc_xmit_lock_key);
+	}
+}
+EXPORT_SYMBOL(netdev_update_lockdep_key);
+
 /**
  *	register_netdevice	- register a network device
  *	@dev: device to register
@@ -8700,7 +9005,7 @@ int register_netdevice(struct net_device *dev)
 	BUG_ON(!net);
 
 	spin_lock_init(&dev->addr_list_lock);
-	netdev_set_addr_lockdep_class(dev);
+	lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);
 
 	ret = dev_get_valid_name(net, dev, dev->name);
 	if (ret < 0)
@@ -9210,8 +9515,12 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev_net_set(dev, &init_net);
 
+	netdev_register_lockdep_key(dev);
+
 	dev->gso_max_size = GSO_MAX_SIZE;
 	dev->gso_max_segs = GSO_MAX_SEGS;
+	dev->upper_level = 1;
+	dev->lower_level = 1;
 
 	INIT_LIST_HEAD(&dev->napi_list);
 	INIT_LIST_HEAD(&dev->unreg_list);
@@ -9292,6 +9601,8 @@ void free_netdev(struct net_device *dev)
 	free_percpu(dev->pcpu_refcnt);
 	dev->pcpu_refcnt = NULL;
 
+	netdev_unregister_lockdep_key(dev);
+
 	/*  Compatibility with error handling in drivers */
 	if (dev->reg_state == NETREG_UNINITIALIZED) {
 		netdev_freemem(dev);
@@ -9460,7 +9771,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
 	call_netdevice_notifiers(NETDEV_UNREGISTER, dev);
 	rcu_barrier();
 
-	new_nsid = peernet2id_alloc(dev_net(dev), net);
+	new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL);
 	/* If there is an ifindex conflict assign a new one */
 	if (__dev_get_by_index(net, dev->ifindex))
 		new_ifindex = dev_new_index(net);
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 6393ba930097..2f949b5a1eb9 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -637,7 +637,7 @@ int dev_uc_sync(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock_nested(to);
+	netif_addr_lock(to);
 	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -667,7 +667,7 @@ int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock_nested(to);
+	netif_addr_lock(to);
 	err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -691,7 +691,7 @@ void dev_uc_unsync(struct net_device *to, struct net_device *from)
 		return;
 
 	netif_addr_lock_bh(from);
-	netif_addr_lock_nested(to);
+	netif_addr_lock(to);
 	__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
 	__dev_set_rx_mode(to);
 	netif_addr_unlock(to);
@@ -858,7 +858,7 @@ int dev_mc_sync(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock_nested(to);
+	netif_addr_lock(to);
 	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -888,7 +888,7 @@ int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
 	if (to->addr_len != from->addr_len)
 		return -EINVAL;
 
-	netif_addr_lock_nested(to);
+	netif_addr_lock(to);
 	err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
 	if (!err)
 		__dev_set_rx_mode(to);
@@ -912,7 +912,7 @@ void dev_mc_unsync(struct net_device *to, struct net_device *from)
 		return;
 
 	netif_addr_lock_bh(from);
-	netif_addr_lock_nested(to);
+	netif_addr_lock(to);
 	__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
 	__dev_set_rx_mode(to);
 	netif_addr_unlock(to);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index c763106c73fc..cd9bc67381b2 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1396,11 +1396,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr)
 
 static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
 {
-	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+	struct ethtool_wolinfo wol;
 
 	if (!dev->ethtool_ops->get_wol)
 		return -EOPNOTSUPP;
 
+	memset(&wol, 0, sizeof(struct ethtool_wolinfo));
+	wol.cmd = ETHTOOL_GWOL;
 	dev->ethtool_ops->get_wol(dev, &wol);
 
 	if (copy_to_user(useraddr, &wol, sizeof(wol)))
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 7c09d87d3269..68eda10d0680 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1350,30 +1350,21 @@ out_bad:
 }
 EXPORT_SYMBOL(__skb_flow_dissect);
 
-static u32 hashrnd __read_mostly;
+static siphash_key_t hashrnd __read_mostly;
 static __always_inline void __flow_hash_secret_init(void)
 {
 	net_get_random_once(&hashrnd, sizeof(hashrnd));
 }
 
-static __always_inline u32 __flow_hash_words(const u32 *words, u32 length,
-					     u32 keyval)
+static const void *flow_keys_hash_start(const struct flow_keys *flow)
 {
-	return jhash2(words, length, keyval);
-}
-
-static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow)
-{
-	const void *p = flow;
-
-	BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32));
-	return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET);
+	BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT);
+	return &flow->FLOW_KEYS_HASH_START_FIELD;
 }
 
 static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
 {
 	size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs);
-	BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32));
 	BUILD_BUG_ON(offsetof(typeof(*flow), addrs) !=
 		     sizeof(*flow) - sizeof(flow->addrs));
 
@@ -1388,7 +1379,7 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow)
 		diff -= sizeof(flow->addrs.tipckey);
 		break;
 	}
-	return (sizeof(*flow) - diff) / sizeof(u32);
+	return sizeof(*flow) - diff;
 }
 
 __be32 flow_get_u32_src(const struct flow_keys *flow)
@@ -1454,14 +1445,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys)
 	}
 }
 
-static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys,
+					const siphash_key_t *keyval)
 {
 	u32 hash;
 
 	__flow_hash_consistentify(keys);
 
-	hash = __flow_hash_words(flow_keys_hash_start(keys),
-				 flow_keys_hash_length(keys), keyval);
+	hash = siphash(flow_keys_hash_start(keys),
+		       flow_keys_hash_length(keys), keyval);
 	if (!hash)
 		hash = 1;
 
@@ -1471,12 +1463,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval)
 u32 flow_hash_from_keys(struct flow_keys *keys)
 {
 	__flow_hash_secret_init();
-	return __flow_hash_from_keys(keys, hashrnd);
+	return __flow_hash_from_keys(keys, &hashrnd);
 }
 EXPORT_SYMBOL(flow_hash_from_keys);
 
 static inline u32 ___skb_get_hash(const struct sk_buff *skb,
-				  struct flow_keys *keys, u32 keyval)
+				  struct flow_keys *keys,
+				  const siphash_key_t *keyval)
 {
 	skb_flow_dissect_flow_keys(skb, keys,
 				   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
@@ -1524,7 +1517,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb)
 			   &keys, NULL, 0, 0, 0,
 			   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
 
-	return __flow_hash_from_keys(&keys, hashrnd);
+	return __flow_hash_from_keys(&keys, &hashrnd);
 }
 EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);
 
@@ -1544,13 +1537,14 @@ void __skb_get_hash(struct sk_buff *skb)
 
 	__flow_hash_secret_init();
 
-	hash = ___skb_get_hash(skb, &keys, hashrnd);
+	hash = ___skb_get_hash(skb, &keys, &hashrnd);
 
 	__skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys));
 }
 EXPORT_SYMBOL(__skb_get_hash);
 
-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb)
+__u32 skb_get_hash_perturb(const struct sk_buff *skb,
+			   const siphash_key_t *perturb)
 {
 	struct flow_keys keys;
 
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index f93785e5833c..74cfb8b5ab33 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -88,11 +88,16 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb)
 	int err = -EINVAL;
 
 	if (skb->protocol == htons(ETH_P_IP)) {
+		struct net_device *dev = skb_dst(skb)->dev;
 		struct iphdr *iph = ip_hdr(skb);
 
+		dev_hold(dev);
+		skb_dst_drop(skb);
 		err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					   iph->tos, skb_dst(skb)->dev);
+					   iph->tos, dev);
+		dev_put(dev);
 	} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		skb_dst_drop(skb);
 		err = ipv6_stub->ipv6_route_input(skb);
 	} else {
 		err = -EAFNOSUPPORT;
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6d3e4821b02d..39402840025e 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -246,11 +246,11 @@ static int __peernet2id(struct net *net, struct net *peer)
 }
 
 static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
-			      struct nlmsghdr *nlh);
+			      struct nlmsghdr *nlh, gfp_t gfp);
 /* This function returns the id of a peer netns. If no id is assigned, one will
  * be allocated and returned.
  */
-int peernet2id_alloc(struct net *net, struct net *peer)
+int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 {
 	bool alloc = false, alive = false;
 	int id;
@@ -269,7 +269,7 @@ int peernet2id_alloc(struct net *net, struct net *peer)
 	id = __peernet2id_alloc(net, peer, &alloc);
 	spin_unlock_bh(&net->nsid_lock);
 	if (alloc && id >= 0)
-		rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL);
+		rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp);
 	if (alive)
 		put_net(peer);
 	return id;
@@ -479,6 +479,7 @@ struct net *copy_net_ns(unsigned long flags,
 
 	if (rv < 0) {
 put_userns:
+		key_remove_domain(net->key_domain);
 		put_user_ns(user_ns);
 		net_drop_ns(net);
 dec_ucounts:
@@ -533,7 +534,8 @@ static void unhash_nsid(struct net *net, struct net *last)
 			idr_remove(&tmp->netns_ids, id);
 		spin_unlock_bh(&tmp->nsid_lock);
 		if (id >= 0)
-			rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL);
+			rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL,
+					  GFP_KERNEL);
 		if (tmp == last)
 			break;
 	}
@@ -766,7 +768,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh,
 	spin_unlock_bh(&net->nsid_lock);
 	if (err >= 0) {
 		rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid,
-				  nlh);
+				  nlh, GFP_KERNEL);
 		err = 0;
 	} else if (err == -ENOSPC && nsid >= 0) {
 		err = -EEXIST;
@@ -1054,7 +1056,7 @@ end:
 }
 
 static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
-			      struct nlmsghdr *nlh)
+			      struct nlmsghdr *nlh, gfp_t gfp)
 {
 	struct net_fill_args fillargs = {
 		.portid = portid,
@@ -1065,7 +1067,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
 	struct sk_buff *msg;
 	int err = -ENOMEM;
 
-	msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL);
+	msg = nlmsg_new(rtnl_net_get_size(), gfp);
 	if (!msg)
 		goto out;
 
@@ -1073,7 +1075,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid,
 	if (err < 0)
 		goto err_out;
 
-	rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, 0);
+	rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp);
 	return;
 
 err_out:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1ee6460f8275..c81cd80114d9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1523,7 +1523,7 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb,
 
 static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 				  const struct net_device *dev,
-				  struct net *src_net)
+				  struct net *src_net, gfp_t gfp)
 {
 	bool put_iflink = false;
 
@@ -1531,7 +1531,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb,
 		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
 
 		if (!net_eq(dev_net(dev), link_net)) {
-			int id = peernet2id_alloc(src_net, link_net);
+			int id = peernet2id_alloc(src_net, link_net, gfp);
 
 			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
 				return -EMSGSIZE;
@@ -1589,7 +1589,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			    int type, u32 pid, u32 seq, u32 change,
 			    unsigned int flags, u32 ext_filter_mask,
 			    u32 event, int *new_nsid, int new_ifindex,
-			    int tgt_netnsid)
+			    int tgt_netnsid, gfp_t gfp)
 {
 	struct ifinfomsg *ifm;
 	struct nlmsghdr *nlh;
@@ -1681,7 +1681,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 			goto nla_put_failure;
 	}
 
-	if (rtnl_fill_link_netnsid(skb, dev, src_net))
+	if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp))
 		goto nla_put_failure;
 
 	if (new_nsid &&
@@ -2001,7 +2001,7 @@ walk_entries:
 					       NETLINK_CB(cb->skb).portid,
 					       nlh->nlmsg_seq, 0, flags,
 					       ext_filter_mask, 0, NULL, 0,
-					       netnsid);
+					       netnsid, GFP_KERNEL);
 
 			if (err < 0) {
 				if (likely(skb->len))
@@ -2355,6 +2355,7 @@ static int do_set_master(struct net_device *dev, int ifindex,
 			err = ops->ndo_del_slave(upper_dev, dev);
 			if (err)
 				return err;
+			netdev_update_lockdep_key(dev);
 		} else {
 			return -EOPNOTSUPP;
 		}
@@ -3359,7 +3360,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 	err = rtnl_fill_ifinfo(nskb, dev, net,
 			       RTM_NEWLINK, NETLINK_CB(skb).portid,
 			       nlh->nlmsg_seq, 0, 0, ext_filter_mask,
-			       0, NULL, 0, netnsid);
+			       0, NULL, 0, netnsid, GFP_KERNEL);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size */
 		WARN_ON(err == -EMSGSIZE);
@@ -3471,7 +3472,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,
 
 	err = rtnl_fill_ifinfo(skb, dev, dev_net(dev),
 			       type, 0, 0, change, 0, 0, event,
-			       new_nsid, new_ifindex, -1);
+			       new_nsid, new_ifindex, -1, flags);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in if_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -3916,7 +3917,7 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh,
 	ndm = nlmsg_data(nlh);
 	if (ndm->ndm_pad1  || ndm->ndm_pad2  || ndm->ndm_state ||
 	    ndm->ndm_flags || ndm->ndm_type) {
-		NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request");
+		NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request");
 		return -EINVAL;
 	}
 
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index cf390e0aa73d..ad31e4e53d0a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -270,18 +270,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len)
 
 	msg->sg.data[i].length -= trim;
 	sk_mem_uncharge(sk, trim);
+	/* Adjust copybreak if it falls into the trimmed part of last buf */
+	if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length)
+		msg->sg.copybreak = msg->sg.data[i].length;
 out:
-	/* If we trim data before curr pointer update copybreak and current
-	 * so that any future copy operations start at new copy location.
+	sk_msg_iter_var_next(i);
+	msg->sg.end = i;
+
+	/* If we trim data a full sg elem before curr pointer update
+	 * copybreak and current so that any future copy operations
+	 * start at new copy location.
 	 * However trimed data that has not yet been used in a copy op
 	 * does not require an update.
 	 */
-	if (msg->sg.curr >= i) {
+	if (!msg->sg.size) {
+		msg->sg.curr = msg->sg.start;
+		msg->sg.copybreak = 0;
+	} else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >=
+		   sk_msg_iter_dist(msg->sg.start, msg->sg.end)) {
+		sk_msg_iter_var_prev(i);
 		msg->sg.curr = i;
 		msg->sg.copybreak = msg->sg.data[i].length;
 	}
-	sk_msg_iter_var_next(i);
-	msg->sg.end = i;
 }
 EXPORT_SYMBOL_GPL(sk_msg_trim);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index a515392ba84b..ac78a570e43a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1127,7 +1127,7 @@ set_rcvbuf:
 		break;
 		}
 	case SO_INCOMING_CPU:
-		sk->sk_incoming_cpu = val;
+		WRITE_ONCE(sk->sk_incoming_cpu, val);
 		break;
 
 	case SO_CNX_ADVICE:
@@ -1476,7 +1476,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_INCOMING_CPU:
-		v.val = sk->sk_incoming_cpu;
+		v.val = READ_ONCE(sk->sk_incoming_cpu);
 		break;
 
 	case SO_MEMINFO:
@@ -3600,7 +3600,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time)
 {
 	struct sock *sk = p;
 
-	return !skb_queue_empty(&sk->sk_receive_queue) ||
+	return !skb_queue_empty_lockless(&sk->sk_receive_queue) ||
 	       sk_busy_loop_timeout(sk, start_time);
 }
 EXPORT_SYMBOL(sk_busy_loop_end);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d9b4200ed12d..d19557c6d04b 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -117,7 +117,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 						    inet->inet_daddr,
 						    inet->inet_sport,
 						    inet->inet_dport);
-	inet->inet_id = dp->dccps_iss ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	err = dccp_connect(sk);
 	rt = NULL;
@@ -416,7 +416,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
-	newinet->inet_id   = jiffies;
+	newinet->inet_id   = prandom_u32();
 
 	if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL)
 		goto put_and_exit;
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index 0ea75286abf4..3349ea81f901 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1205,7 +1205,7 @@ static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table  *wai
 	struct dn_scp *scp = DN_SK(sk);
 	__poll_t mask = datagram_poll(file, sock, wait);
 
-	if (!skb_queue_empty(&scp->other_receive_queue))
+	if (!skb_queue_empty_lockless(&scp->other_receive_queue))
 		mask |= EPOLLRDBAND;
 
 	return mask;
diff --git a/net/dsa/master.c b/net/dsa/master.c
index a8e52c9967f4..3255dfc97f86 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -310,8 +310,6 @@ static void dsa_master_reset_mtu(struct net_device *dev)
 	rtnl_unlock();
 }
 
-static struct lock_class_key dsa_master_addr_list_lock_key;
-
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
 	int ret;
@@ -325,9 +323,6 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	wmb();
 
 	dev->dsa_ptr = cpu_dp;
-	lockdep_set_class(&dev->addr_list_lock,
-			  &dsa_master_addr_list_lock_key);
-
 	ret = dsa_master_ethtool_setup(dev);
 	if (ret)
 		return ret;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 75d58229a4bd..028e65f4b5ba 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -1341,15 +1341,6 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev)
 	return ret;
 }
 
-static struct lock_class_key dsa_slave_netdev_xmit_lock_key;
-static void dsa_slave_set_lockdep_class_one(struct net_device *dev,
-					    struct netdev_queue *txq,
-					    void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock,
-			  &dsa_slave_netdev_xmit_lock_key);
-}
-
 int dsa_slave_suspend(struct net_device *slave_dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(slave_dev);
@@ -1433,9 +1424,6 @@ int dsa_slave_create(struct dsa_port *port)
 	slave_dev->max_mtu = ETH_MAX_MTU;
 	SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
 
-	netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
-				 NULL);
-
 	SET_NETDEV_DEV(slave_dev, port->ds->dev);
 	slave_dev->dev.of_node = port->dn;
 	slave_dev->vlan_features = master->vlan_features;
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 3297e7fa9945..c0b107cdd715 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -58,13 +58,6 @@ static const struct header_ops lowpan_header_ops = {
 	.create	= lowpan_header_create,
 };
 
-static int lowpan_dev_init(struct net_device *ldev)
-{
-	netdev_lockdep_set_classes(ldev);
-
-	return 0;
-}
-
 static int lowpan_open(struct net_device *dev)
 {
 	if (!open_count)
@@ -96,7 +89,6 @@ static int lowpan_get_iflink(const struct net_device *dev)
 }
 
 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,
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 9a0fe0c2fa02..4a8550c49202 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len
 	reuseport_has_conns(sk, true);
 	sk->sk_state = TCP_ESTABLISHED;
 	sk_set_txhash(sk);
-	inet->inet_id = jiffies;
+	inet->inet_id = prandom_u32();
 
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index dde77f72e03e..71c78d223dfd 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1148,7 +1148,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric)
 	if (!(dev->flags & IFF_UP) ||
 	    ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) ||
 	    ipv4_is_zeronet(prefix) ||
-	    prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32)
+	    (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32))
 		return;
 
 	/* add the new */
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0913a090b2bf..f1888c683426 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1814,8 +1814,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	int ret = 0;
 	unsigned int hash = fib_laddr_hashfn(local);
 	struct hlist_head *head = &fib_info_laddrhash[hash];
+	int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
 	struct net *net = dev_net(dev);
-	int tb_id = l3mdev_fib_table(dev);
 	struct fib_info *fi;
 
 	if (!fib_info_laddrhash || local == 0)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 97824864e40d..83fb00153018 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -240,7 +240,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			return -1;
 
 		score = sk->sk_family == PF_INET ? 2 : 1;
-		if (sk->sk_incoming_cpu == raw_smp_processor_id())
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 			score++;
 	}
 	return score;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 52690bb3e40f..10636fb6093e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -509,9 +509,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev)
 	key = &tun_info->key;
 	if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
 		goto err_free_skb;
-	md = ip_tunnel_info_opts(tun_info);
-	if (!md)
+	if (tun_info->options_len < sizeof(*md))
 		goto err_free_skb;
+	md = ip_tunnel_info_opts(tun_info);
 
 	/* ERSPAN has fixed 8 byte GRE header */
 	version = md->version;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 814b9b8882a0..3d8baaaf7086 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -645,11 +645,12 @@ void ip_fraglist_prepare(struct sk_buff *skb, struct ip_fraglist_iter *iter)
 EXPORT_SYMBOL(ip_fraglist_prepare);
 
 void ip_frag_init(struct sk_buff *skb, unsigned int hlen,
-		  unsigned int ll_rs, unsigned int mtu,
+		  unsigned int ll_rs, unsigned int mtu, bool DF,
 		  struct ip_frag_state *state)
 {
 	struct iphdr *iph = ip_hdr(skb);
 
+	state->DF = DF;
 	state->hlen = hlen;
 	state->ll_rs = ll_rs;
 	state->mtu = mtu;
@@ -668,9 +669,6 @@ static void ip_frag_ipcb(struct sk_buff *from, struct sk_buff *to,
 	/* Copy the flags to each fragment. */
 	IPCB(to)->flags = IPCB(from)->flags;
 
-	if (IPCB(from)->flags & IPSKB_FRAG_PMTU)
-		state->iph->frag_off |= htons(IP_DF);
-
 	/* ANK: dirty, but effective trick. Upgrade options only if
 	 * the segment to be fragmented was THE FIRST (otherwise,
 	 * options are already fixed) and make it ONCE
@@ -738,6 +736,8 @@ struct sk_buff *ip_frag_next(struct sk_buff *skb, struct ip_frag_state *state)
 	 */
 	iph = ip_hdr(skb2);
 	iph->frag_off = htons((state->offset >> 3));
+	if (state->DF)
+		iph->frag_off |= htons(IP_DF);
 
 	/*
 	 *	Added AC : If we are fragmenting a fragment that's not the
@@ -883,7 +883,8 @@ slow_path:
 	 *	Fragment the datagram.
 	 */
 
-	ip_frag_init(skb, hlen, ll_rs, mtu, &state);
+	ip_frag_init(skb, hlen, ll_rs, mtu, IPCB(skb)->flags & IPSKB_FRAG_PMTU,
+		     &state);
 
 	/*
 	 *	Keep copying data until we run out.
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 42187a3b82f4..d8876f0e9672 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -584,7 +584,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR;
 
 	return mask;
@@ -1964,7 +1964,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (unlikely(flags & MSG_ERRQUEUE))
 		return inet_recv_error(sk, msg, len, addr_len);
 
-	if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) &&
+	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    (sk->sk_state == TCP_ESTABLISHED))
 		sk_busy_loop(sk, nonblock);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6be568334848..67b2dc7a1727 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -303,7 +303,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 						 inet->inet_daddr);
 	}
 
-	inet->inet_id = tp->write_seq ^ jiffies;
+	inet->inet_id = prandom_u32();
 
 	if (tcp_fastopen_defer_connect(sk, &err))
 		return err;
@@ -1450,7 +1450,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	inet_csk(newsk)->icsk_ext_hdr_len = 0;
 	if (inet_opt)
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
-	newinet->inet_id = newtp->write_seq ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
@@ -2681,7 +2681,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
 	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
 
-	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256);
+	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
 	net->ipv4.sysctl_tcp_sack = 1;
 	net->ipv4.sysctl_tcp_window_scaling = 1;
 	net->ipv4.sysctl_tcp_timestamps = 1;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 14bc654b6842..1d58ce829dca 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -388,7 +388,7 @@ static int compute_score(struct sock *sk, struct net *net,
 		return -1;
 	score += 4;
 
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
+	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 		score++;
 	return score;
 }
@@ -1316,6 +1316,20 @@ static void udp_set_dev_scratch(struct sk_buff *skb)
 		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;
 }
 
+static void udp_skb_csum_unnecessary_set(struct sk_buff *skb)
+{
+	/* We come here after udp_lib_checksum_complete() returned 0.
+	 * This means that __skb_checksum_complete() might have
+	 * set skb->csum_valid to 1.
+	 * On 64bit platforms, we can set csum_unnecessary
+	 * to true, but only if the skb is not shared.
+	 */
+#if BITS_PER_LONG == 64
+	if (!skb_shared(skb))
+		udp_skb_scratch(skb)->csum_unnecessary = true;
+#endif
+}
+
 static int udp_skb_truesize(struct sk_buff *skb)
 {
 	return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;
@@ -1550,10 +1564,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk,
 			*total += skb->truesize;
 			kfree_skb(skb);
 		} else {
-			/* the csum related bits could be changed, refresh
-			 * the scratch area
-			 */
-			udp_set_dev_scratch(skb);
+			udp_skb_csum_unnecessary_set(skb);
 			break;
 		}
 	}
@@ -1577,7 +1588,7 @@ static int first_packet_length(struct sock *sk)
 
 	spin_lock_bh(&rcvq->lock);
 	skb = __first_packet_length(sk, rcvq, &total);
-	if (!skb && !skb_queue_empty(sk_queue)) {
+	if (!skb && !skb_queue_empty_lockless(sk_queue)) {
 		spin_lock(&sk_queue->lock);
 		skb_queue_splice_tail_init(sk_queue, rcvq);
 		spin_unlock(&sk_queue->lock);
@@ -1650,7 +1661,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 				return skb;
 			}
 
-			if (skb_queue_empty(sk_queue)) {
+			if (skb_queue_empty_lockless(sk_queue)) {
 				spin_unlock_bh(&queue->lock);
 				goto busy_check;
 			}
@@ -1676,7 +1687,7 @@ busy_check:
 				break;
 
 			sk_busy_loop(sk, flags & MSG_DONTWAIT);
-		} while (!skb_queue_empty(sk_queue));
+		} while (!skb_queue_empty_lockless(sk_queue));
 
 		/* sk_queue is empty, reader_queue may contain peeked packets */
 	} while (timeo &&
@@ -2712,7 +2723,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	__poll_t mask = datagram_poll(file, sock, wait);
 	struct sock *sk = sock->sk;
 
-	if (!skb_queue_empty(&udp_sk(sk)->reader_queue))
+	if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Check for false positives due to checksum errors */
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 783f3c1466da..2fc079284ca4 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <net/ipv6.h>
 #include <net/ipv6_stubs.h>
+#include <net/addrconf.h>
 #include <net/ip.h>
 
 /* if ipv6 module registers this function is used by xfrm to force all
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index cf60fae9533b..fbe9d4295eac 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -105,7 +105,7 @@ static inline int compute_score(struct sock *sk, struct net *net,
 			return -1;
 
 		score = 1;
-		if (sk->sk_incoming_cpu == raw_smp_processor_id())
+		if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 			score++;
 	}
 	return score;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 787d9f2a6e99..923034c52ce4 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -980,9 +980,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 		dsfield = key->tos;
 		if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
 			goto tx_err;
-		md = ip_tunnel_info_opts(tun_info);
-		if (!md)
+		if (tun_info->options_len < sizeof(*md))
 			goto tx_err;
+		md = ip_tunnel_info_opts(tun_info);
 
 		tun_id = tunnel_id_to_key32(key->tun_id);
 		if (md->version == 1) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a63ff85fe141..e60bf8e7dd1a 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -621,6 +621,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 {
 	struct __rt6_probe_work *work = NULL;
 	const struct in6_addr *nh_gw;
+	unsigned long last_probe;
 	struct neighbour *neigh;
 	struct net_device *dev;
 	struct inet6_dev *idev;
@@ -639,6 +640,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 	nh_gw = &fib6_nh->fib_nh_gw6;
 	dev = fib6_nh->fib_nh_dev;
 	rcu_read_lock_bh();
+	last_probe = READ_ONCE(fib6_nh->last_probe);
 	idev = __in6_dev_get(dev);
 	neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
 	if (neigh) {
@@ -654,13 +656,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh)
 				__neigh_set_probe_once(neigh);
 		}
 		write_unlock(&neigh->lock);
-	} else if (time_after(jiffies, fib6_nh->last_probe +
+	} else if (time_after(jiffies, last_probe +
 				       idev->cnf.rtr_probe_interval)) {
 		work = kmalloc(sizeof(*work), GFP_ATOMIC);
 	}
 
-	if (work) {
-		fib6_nh->last_probe = jiffies;
+	if (!work || cmpxchg(&fib6_nh->last_probe,
+			     last_probe, jiffies) != last_probe) {
+		kfree(work);
+	} else {
 		INIT_WORK(&work->work, rt6_probe_deferred);
 		work->target = *nh_gw;
 		dev_hold(dev);
@@ -3383,6 +3387,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 	int err;
 
 	fib6_nh->fib_nh_family = AF_INET6;
+#ifdef CONFIG_IPV6_ROUTER_PREF
+	fib6_nh->last_probe = jiffies;
+#endif
 
 	err = -ENODEV;
 	if (cfg->fc_ifindex) {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6324d3a8cb53..9fec580c968e 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -135,7 +135,7 @@ static int compute_score(struct sock *sk, struct net *net,
 		return -1;
 	score++;
 
-	if (sk->sk_incoming_cpu == raw_smp_processor_id())
+	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
 		score++;
 
 	return score;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index fd5ac2788e45..d3b520b9b2c9 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -56,7 +56,6 @@ static int l2tp_eth_dev_init(struct net_device *dev)
 {
 	eth_hw_addr_random(dev);
 	eth_broadcast_addr(dev->broadcast);
-	netdev_lockdep_set_classes(dev);
 
 	return 0;
 }
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index aba094b4ccfc..2d05c4cfaf6d 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1292,8 +1292,8 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	ieee80211_remove_interfaces(local);
  fail_rate:
 	rtnl_unlock();
-	ieee80211_led_exit(local);
  fail_flows:
+	ieee80211_led_exit(local);
 	destroy_workqueue(local->workqueue);
  fail_workqueue:
 	wiphy_unregister(local->hw.wiphy);
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index bd11fef2139f..8d3a2389b055 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2457,7 +2457,8 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta)
 {
 	struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta);
 
-	if (time_after(stats->last_rx, sta->status_stats.last_ack))
+	if (!sta->status_stats.last_ack ||
+	    time_after(stats->last_rx, sta->status_stats.last_ack))
 		return stats->last_rx;
 	return sta->status_stats.last_ack;
 }
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index e64d5f9a89dd..d73d1828216a 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -296,7 +296,8 @@ ip_set_get_ipaddr4(struct nlattr *nla,  __be32 *ipaddr)
 
 	if (unlikely(!flag_nested(nla)))
 		return -IPSET_ERR_PROTOCOL;
-	if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL))
+	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
+			     ipaddr_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4)))
 		return -IPSET_ERR_PROTOCOL;
@@ -314,7 +315,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr)
 	if (unlikely(!flag_nested(nla)))
 		return -IPSET_ERR_PROTOCOL;
 
-	if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL))
+	if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla,
+			     ipaddr_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 	if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6)))
 		return -IPSET_ERR_PROTOCOL;
@@ -934,7 +936,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 
 	/* Without holding any locks, create private part. */
 	if (attr[IPSET_ATTR_DATA] &&
-	    nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) {
+	    nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA],
+			     set->type->create_policy, NULL)) {
 		ret = -IPSET_ERR_PROTOCOL;
 		goto put_out;
 	}
@@ -1281,6 +1284,14 @@ dump_attrs(struct nlmsghdr *nlh)
 	}
 }
 
+static const struct nla_policy
+ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = {
+	[IPSET_ATTR_PROTOCOL]	= { .type = NLA_U8 },
+	[IPSET_ATTR_SETNAME]	= { .type = NLA_NUL_STRING,
+				    .len = IPSET_MAXNAMELEN - 1 },
+	[IPSET_ATTR_FLAGS]	= { .type = NLA_U32 },
+};
+
 static int
 dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 {
@@ -1292,9 +1303,9 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst)
 	ip_set_id_t index;
 	int ret;
 
-	ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr,
-				   nlh->nlmsg_len - min_len,
-				   ip_set_setname_policy, NULL);
+	ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr,
+			nlh->nlmsg_len - min_len,
+			ip_set_dump_policy, NULL);
 	if (ret)
 		return ret;
 
@@ -1543,9 +1554,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 		memcpy(&errmsg->msg, nlh, nlh->nlmsg_len);
 		cmdattr = (void *)&errmsg->msg + min_len;
 
-		ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr,
-					   nlh->nlmsg_len - min_len,
-					   ip_set_adt_policy, NULL);
+		ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr,
+				nlh->nlmsg_len - min_len, ip_set_adt_policy,
+				NULL);
 
 		if (ret) {
 			nlmsg_free(skb2);
@@ -1596,7 +1607,9 @@ static int ip_set_ad(struct net *net, struct sock *ctnl,
 
 	use_lineno = !!attr[IPSET_ATTR_LINENO];
 	if (attr[IPSET_ATTR_DATA]) {
-		if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
+		if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX,
+				     attr[IPSET_ATTR_DATA],
+				     set->type->adt_policy, NULL))
 			return -IPSET_ERR_PROTOCOL;
 		ret = call_ad(ctnl, skb, set, tb, adt, flags,
 			      use_lineno);
@@ -1606,7 +1619,8 @@ static int ip_set_ad(struct net *net, struct sock *ctnl,
 		nla_for_each_nested(nla, attr[IPSET_ATTR_ADT], nla_rem) {
 			if (nla_type(nla) != IPSET_ATTR_DATA ||
 			    !flag_nested(nla) ||
-			    nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL))
+			    nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla,
+					     set->type->adt_policy, NULL))
 				return -IPSET_ERR_PROTOCOL;
 			ret = call_ad(ctnl, skb, set, tb, adt,
 				      flags, use_lineno);
@@ -1655,7 +1669,8 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb,
 	if (!set)
 		return -ENOENT;
 
-	if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL))
+	if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA],
+			     set->type->adt_policy, NULL))
 		return -IPSET_ERR_PROTOCOL;
 
 	rcu_read_lock_bh();
@@ -1961,7 +1976,7 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = {
 	[IPSET_CMD_LIST]	= {
 		.call		= ip_set_dump,
 		.attr_count	= IPSET_ATTR_CMD_MAX,
-		.policy		= ip_set_setname_policy,
+		.policy		= ip_set_dump_policy,
 	},
 	[IPSET_CMD_SAVE]	= {
 		.call		= ip_set_dump,
@@ -2069,8 +2084,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 		}
 
 		req_version->version = IPSET_PROTOCOL;
-		ret = copy_to_user(user, req_version,
-				   sizeof(struct ip_set_req_version));
+		if (copy_to_user(user, req_version,
+				 sizeof(struct ip_set_req_version)))
+			ret = -EFAULT;
 		goto done;
 	}
 	case IP_SET_OP_GET_BYNAME: {
@@ -2129,7 +2145,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len)
 	}	/* end of switch(op) */
 
 copy:
-	ret = copy_to_user(user, data, copylen);
+	if (copy_to_user(user, data, copylen))
+		ret = -EFAULT;
 
 done:
 	vfree(data);
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index 24d8f4df4230..4ce563eb927d 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -209,7 +209,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb,
 	    (skb_mac_header(skb) + ETH_HLEN) > skb->data)
 		return -EINVAL;
 
-	if (opt->flags & IPSET_DIM_ONE_SRC)
+	if (opt->flags & IPSET_DIM_TWO_SRC)
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_source);
 	else
 		ether_addr_copy(e.ether, eth_hdr(skb)->h_dest);
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index c259cbc3ef45..3d932de0ad29 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -368,6 +368,7 @@ static struct ip_set_type hash_net_type __read_mostly = {
 		[IPSET_ATTR_IP_TO]	= { .type = NLA_NESTED },
 		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
 		[IPSET_ATTR_BYTES]	= { .type = NLA_U64 },
 		[IPSET_ATTR_PACKETS]	= { .type = NLA_U64 },
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index a3ae69bfee66..4398322fad59 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -476,6 +476,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = {
 		[IPSET_ATTR_CIDR]	= { .type = NLA_U8 },
 		[IPSET_ATTR_CIDR2]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
+		[IPSET_ATTR_LINENO]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
 		[IPSET_ATTR_BYTES]	= { .type = NLA_U64 },
 		[IPSET_ATTR_PACKETS]	= { .type = NLA_U64 },
diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c
index 4515056ef1c2..f9b16f2b2219 100644
--- a/net/netfilter/ipvs/ip_vs_app.c
+++ b/net/netfilter/ipvs/ip_vs_app.c
@@ -193,21 +193,29 @@ struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *
 
 	mutex_lock(&__ip_vs_app_mutex);
 
+	/* increase the module use count */
+	if (!ip_vs_use_count_inc()) {
+		err = -ENOENT;
+		goto out_unlock;
+	}
+
 	list_for_each_entry(a, &ipvs->app_list, a_list) {
 		if (!strcmp(app->name, a->name)) {
 			err = -EEXIST;
+			/* decrease the module use count */
+			ip_vs_use_count_dec();
 			goto out_unlock;
 		}
 	}
 	a = kmemdup(app, sizeof(*app), GFP_KERNEL);
 	if (!a) {
 		err = -ENOMEM;
+		/* decrease the module use count */
+		ip_vs_use_count_dec();
 		goto out_unlock;
 	}
 	INIT_LIST_HEAD(&a->incs_list);
 	list_add(&a->a_list, &ipvs->app_list);
-	/* increase the module use count */
-	ip_vs_use_count_inc();
 
 out_unlock:
 	mutex_unlock(&__ip_vs_app_mutex);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 8b48e7ce1c2c..3cccc88ef817 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -93,7 +93,6 @@ static bool __ip_vs_addr_is_local_v6(struct net *net,
 static void update_defense_level(struct netns_ipvs *ipvs)
 {
 	struct sysinfo i;
-	static int old_secure_tcp = 0;
 	int availmem;
 	int nomem;
 	int to_change = -1;
@@ -174,35 +173,35 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 	spin_lock(&ipvs->securetcp_lock);
 	switch (ipvs->sysctl_secure_tcp) {
 	case 0:
-		if (old_secure_tcp >= 2)
+		if (ipvs->old_secure_tcp >= 2)
 			to_change = 0;
 		break;
 	case 1:
 		if (nomem) {
-			if (old_secure_tcp < 2)
+			if (ipvs->old_secure_tcp < 2)
 				to_change = 1;
 			ipvs->sysctl_secure_tcp = 2;
 		} else {
-			if (old_secure_tcp >= 2)
+			if (ipvs->old_secure_tcp >= 2)
 				to_change = 0;
 		}
 		break;
 	case 2:
 		if (nomem) {
-			if (old_secure_tcp < 2)
+			if (ipvs->old_secure_tcp < 2)
 				to_change = 1;
 		} else {
-			if (old_secure_tcp >= 2)
+			if (ipvs->old_secure_tcp >= 2)
 				to_change = 0;
 			ipvs->sysctl_secure_tcp = 1;
 		}
 		break;
 	case 3:
-		if (old_secure_tcp < 2)
+		if (ipvs->old_secure_tcp < 2)
 			to_change = 1;
 		break;
 	}
-	old_secure_tcp = ipvs->sysctl_secure_tcp;
+	ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp;
 	if (to_change >= 0)
 		ip_vs_protocol_timeout_change(ipvs,
 					      ipvs->sysctl_secure_tcp > 1);
@@ -1275,7 +1274,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
 	struct ip_vs_service *svc = NULL;
 
 	/* increase the module use count */
-	ip_vs_use_count_inc();
+	if (!ip_vs_use_count_inc())
+		return -ENOPROTOOPT;
 
 	/* Lookup the scheduler by 'u->sched_name' */
 	if (strcmp(u->sched_name, "none")) {
@@ -2435,9 +2435,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 	if (copy_from_user(arg, user, len) != 0)
 		return -EFAULT;
 
-	/* increase the module use count */
-	ip_vs_use_count_inc();
-
 	/* Handle daemons since they have another lock */
 	if (cmd == IP_VS_SO_SET_STARTDAEMON ||
 	    cmd == IP_VS_SO_SET_STOPDAEMON) {
@@ -2450,13 +2447,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 			ret = -EINVAL;
 			if (strscpy(cfg.mcast_ifn, dm->mcast_ifn,
 				    sizeof(cfg.mcast_ifn)) <= 0)
-				goto out_dec;
+				return ret;
 			cfg.syncid = dm->syncid;
 			ret = start_sync_thread(ipvs, &cfg, dm->state);
 		} else {
 			ret = stop_sync_thread(ipvs, dm->state);
 		}
-		goto out_dec;
+		return ret;
 	}
 
 	mutex_lock(&__ip_vs_mutex);
@@ -2551,10 +2548,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 
   out_unlock:
 	mutex_unlock(&__ip_vs_mutex);
-  out_dec:
-	/* decrease the module use count */
-	ip_vs_use_count_dec();
-
 	return ret;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c
index 8e104dff7abc..166c669f0763 100644
--- a/net/netfilter/ipvs/ip_vs_pe.c
+++ b/net/netfilter/ipvs/ip_vs_pe.c
@@ -68,7 +68,8 @@ int register_ip_vs_pe(struct ip_vs_pe *pe)
 	struct ip_vs_pe *tmp;
 
 	/* increase the module use count */
-	ip_vs_use_count_inc();
+	if (!ip_vs_use_count_inc())
+		return -ENOENT;
 
 	mutex_lock(&ip_vs_pe_mutex);
 	/* Make sure that the pe with this name doesn't exist
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 2f9d5cd5daee..d4903723be7e 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -179,7 +179,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler)
 	}
 
 	/* increase the module use count */
-	ip_vs_use_count_inc();
+	if (!ip_vs_use_count_inc())
+		return -ENOENT;
 
 	mutex_lock(&ip_vs_sched_mutex);
 
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index a4a78c4b06de..8dc892a9dc91 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1762,6 +1762,10 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n",
 		  sizeof(struct ip_vs_sync_conn_v0));
 
+	/* increase the module use count */
+	if (!ip_vs_use_count_inc())
+		return -ENOPROTOOPT;
+
 	/* Do not hold one mutex and then to block on another */
 	for (;;) {
 		rtnl_lock();
@@ -1892,9 +1896,6 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 	mutex_unlock(&ipvs->sync_mutex);
 	rtnl_unlock();
 
-	/* increase the module use count */
-	ip_vs_use_count_inc();
-
 	return 0;
 
 out:
@@ -1924,11 +1925,17 @@ out:
 		}
 		kfree(ti);
 	}
+
+	/* decrease the module use count */
+	ip_vs_use_count_dec();
 	return result;
 
 out_early:
 	mutex_unlock(&ipvs->sync_mutex);
 	rtnl_unlock();
+
+	/* decrease the module use count */
+	ip_vs_use_count_dec();
 	return result;
 }
 
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 132f5228b431..128245efe84a 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -202,6 +202,8 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 {
 	int err;
 
+	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+
 	err = rhashtable_insert_fast(&flow_table->rhashtable,
 				     &flow->tuplehash[0].node,
 				     nf_flow_offload_rhash_params);
@@ -218,7 +220,6 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow)
 		return err;
 	}
 
-	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(flow_offload_add);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d481f9baca2f..712a428509ad 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1922,6 +1922,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
+		flags |= chain->flags & NFT_BASE_CHAIN;
 		return nf_tables_updchain(&ctx, genmask, policy, flags);
 	}
 
@@ -5143,9 +5144,6 @@ static int nf_tables_updobj(const struct nft_ctx *ctx,
 	struct nft_trans *trans;
 	int err;
 
-	if (!obj->ops->update)
-		return -EOPNOTSUPP;
-
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWOBJ,
 				sizeof(struct nft_trans_obj));
 	if (!trans)
@@ -6499,7 +6497,8 @@ static void nft_obj_commit_update(struct nft_trans *trans)
 	obj = nft_trans_obj(trans);
 	newobj = nft_trans_obj_newobj(trans);
 
-	obj->ops->update(obj, newobj);
+	if (obj->ops->update)
+		obj->ops->update(obj, newobj);
 
 	kfree(newobj);
 }
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index e546f759b7a7..e25dab8128db 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -334,7 +334,8 @@ int nft_flow_rule_offload_commit(struct net *net)
 
 		switch (trans->msg_type) {
 		case NFT_MSG_NEWCHAIN:
-			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD))
+			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD) ||
+			    nft_trans_chain_update(trans))
 				continue;
 
 			policy = nft_trans_chain_policy(trans);
@@ -347,7 +348,7 @@ int nft_flow_rule_offload_commit(struct net *net)
 
 			policy = nft_trans_chain_policy(trans);
 			err = nft_flow_offload_chain(trans->ctx.chain, &policy,
-						     FLOW_BLOCK_BIND);
+						     FLOW_BLOCK_UNBIND);
 			break;
 		case NFT_MSG_NEWRULE:
 			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD))
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index 974300178fa9..02afa752dd2e 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -134,12 +134,13 @@ static int nft_bitwise_offload(struct nft_offload_ctx *ctx,
                                const struct nft_expr *expr)
 {
 	const struct nft_bitwise *priv = nft_expr_priv(expr);
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
 
 	if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) ||
-	    priv->sreg != priv->dreg)
+	    priv->sreg != priv->dreg || priv->len != reg->len)
 		return -EOPNOTSUPP;
 
-	memcpy(&ctx->regs[priv->dreg].mask, &priv->mask, sizeof(priv->mask));
+	memcpy(&reg->mask, &priv->mask, sizeof(priv->mask));
 
 	return 0;
 }
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index bd173b1824c6..0744b2bb46da 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -116,7 +116,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx,
 	u8 *mask = (u8 *)&flow->match.mask;
 	u8 *key = (u8 *)&flow->match.key;
 
-	if (priv->op != NFT_CMP_EQ)
+	if (priv->op != NFT_CMP_EQ || reg->len != priv->len)
 		return -EOPNOTSUPP;
 
 	memcpy(key + reg->offset, &priv->data, priv->len);
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 22a80eb60222..5cb2d8908d2a 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -161,13 +161,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct ethhdr, h_source):
+		if (priv->len != ETH_ALEN)
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
 				  src, ETH_ALEN, reg);
 		break;
 	case offsetof(struct ethhdr, h_dest):
+		if (priv->len != ETH_ALEN)
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
 				  dst, ETH_ALEN, reg);
 		break;
+	default:
+		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -181,14 +189,23 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct iphdr, saddr):
+		if (priv->len != sizeof(struct in_addr))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src,
 				  sizeof(struct in_addr), reg);
 		break;
 	case offsetof(struct iphdr, daddr):
+		if (priv->len != sizeof(struct in_addr))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst,
 				  sizeof(struct in_addr), reg);
 		break;
 	case offsetof(struct iphdr, protocol):
+		if (priv->len != sizeof(__u8))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
 				  sizeof(__u8), reg);
 		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
@@ -208,14 +225,23 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct ipv6hdr, saddr):
+		if (priv->len != sizeof(struct in6_addr))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src,
 				  sizeof(struct in6_addr), reg);
 		break;
 	case offsetof(struct ipv6hdr, daddr):
+		if (priv->len != sizeof(struct in6_addr))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst,
 				  sizeof(struct in6_addr), reg);
 		break;
 	case offsetof(struct ipv6hdr, nexthdr):
+		if (priv->len != sizeof(__u8))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
 				  sizeof(__u8), reg);
 		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
@@ -255,10 +281,16 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct tcphdr, source):
+		if (priv->len != sizeof(__be16))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
 				  sizeof(__be16), reg);
 		break;
 	case offsetof(struct tcphdr, dest):
+		if (priv->len != sizeof(__be16))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
 				  sizeof(__be16), reg);
 		break;
@@ -277,10 +309,16 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct udphdr, source):
+		if (priv->len != sizeof(__be16))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
 				  sizeof(__be16), reg);
 		break;
 	case offsetof(struct udphdr, dest):
+		if (priv->len != sizeof(__be16))
+			return -EOPNOTSUPP;
+
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
 				  sizeof(__be16), reg);
 		break;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index c4f54ad2b98a..58d5373c513c 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -64,28 +64,6 @@ static DEFINE_SPINLOCK(nr_list_lock);
 static const struct proto_ops nr_proto_ops;
 
 /*
- * NETROM network devices are virtual network devices encapsulating NETROM
- * frames into AX.25 which will be sent through an AX.25 device, so form a
- * special "super class" of normal net devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key nr_netdev_xmit_lock_key;
-static struct lock_class_key nr_netdev_addr_lock_key;
-
-static void nr_set_lockdep_one(struct net_device *dev,
-			       struct netdev_queue *txq,
-			       void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &nr_netdev_xmit_lock_key);
-}
-
-static void nr_set_lockdep_key(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &nr_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, nr_set_lockdep_one, NULL);
-}
-
-/*
  *	Socket removal during an interrupt is now safe.
  */
 static void nr_remove_socket(struct sock *sk)
@@ -1414,7 +1392,6 @@ static int __init nr_proto_init(void)
 			free_netdev(dev);
 			goto fail;
 		}
-		nr_set_lockdep_key(dev);
 		dev_nr[i] = dev;
 	}
 
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ccdd790e163a..28604414dec1 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -554,11 +554,11 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
 
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	if (sk->sk_state == LLCP_CLOSED)
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index 17e6ca62f1be..afde0d763039 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -1099,7 +1099,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info)
 
 	local = nfc_llcp_find_local(dev);
 	if (!local) {
-		nfc_put_device(dev);
 		rc = -ENODEV;
 		goto exit;
 	}
@@ -1159,7 +1158,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info)
 
 	local = nfc_llcp_find_local(dev);
 	if (!local) {
-		nfc_put_device(dev);
 		rc = -ENODEV;
 		goto exit;
 	}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index f30e406fbec5..d8c364d637b1 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -1881,7 +1881,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 /* Called with ovs_mutex or RCU read lock. */
 static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 				   struct net *net, u32 portid, u32 seq,
-				   u32 flags, u8 cmd)
+				   u32 flags, u8 cmd, gfp_t gfp)
 {
 	struct ovs_header *ovs_header;
 	struct ovs_vport_stats vport_stats;
@@ -1902,7 +1902,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
 		goto nla_put_failure;
 
 	if (!net_eq(net, dev_net(vport->dev))) {
-		int id = peernet2id_alloc(net, dev_net(vport->dev));
+		int id = peernet2id_alloc(net, dev_net(vport->dev), gfp);
 
 		if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id))
 			goto nla_put_failure;
@@ -1943,11 +1943,12 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net,
 	struct sk_buff *skb;
 	int retval;
 
-	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
-	retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd);
+	retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd,
+					 GFP_KERNEL);
 	BUG_ON(retval < 0);
 
 	return skb;
@@ -2089,7 +2090,7 @@ restart:
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_NEW);
+				      OVS_VPORT_CMD_NEW, GFP_KERNEL);
 
 	new_headroom = netdev_get_fwd_headroom(vport->dev);
 
@@ -2150,7 +2151,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_SET);
+				      OVS_VPORT_CMD_SET, GFP_KERNEL);
 	BUG_ON(err < 0);
 
 	ovs_unlock();
@@ -2190,7 +2191,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
 
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_DEL);
+				      OVS_VPORT_CMD_DEL, GFP_KERNEL);
 	BUG_ON(err < 0);
 
 	/* the vport deletion may trigger dp headroom update */
@@ -2237,7 +2238,7 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
 		goto exit_unlock_free;
 	err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info),
 				      info->snd_portid, info->snd_seq, 0,
-				      OVS_VPORT_CMD_GET);
+				      OVS_VPORT_CMD_GET, GFP_ATOMIC);
 	BUG_ON(err < 0);
 	rcu_read_unlock();
 
@@ -2273,7 +2274,8 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
 						    NETLINK_CB(cb->skb).portid,
 						    cb->nlh->nlmsg_seq,
 						    NLM_F_MULTI,
-						    OVS_VPORT_CMD_GET) < 0)
+						    OVS_VPORT_CMD_GET,
+						    GFP_ATOMIC) < 0)
 				goto out;
 
 			j++;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 21c90d3a7ebf..58a7b8312c28 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -137,7 +137,7 @@ static void do_setup(struct net_device *netdev)
 	netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH |
 			      IFF_NO_QUEUE;
 	netdev->needs_free_netdev = true;
-	netdev->priv_destructor = internal_dev_destructor;
+	netdev->priv_destructor = NULL;
 	netdev->ethtool_ops = &internal_dev_ethtool_ops;
 	netdev->rtnl_link_ops = &internal_dev_link_ops;
 
@@ -159,7 +159,6 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 	struct internal_dev *internal_dev;
 	struct net_device *dev;
 	int err;
-	bool free_vport = true;
 
 	vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms);
 	if (IS_ERR(vport)) {
@@ -190,10 +189,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 	rtnl_lock();
 	err = register_netdevice(vport->dev);
-	if (err) {
-		free_vport = false;
+	if (err)
 		goto error_unlock;
-	}
+	vport->dev->priv_destructor = internal_dev_destructor;
 
 	dev_set_promiscuity(vport->dev, 1);
 	rtnl_unlock();
@@ -207,8 +205,7 @@ error_unlock:
 error_free_netdev:
 	free_netdev(dev);
 error_free_vport:
-	if (free_vport)
-		ovs_vport_free(vport);
+	ovs_vport_free(vport);
 error:
 	return ERR_PTR(err);
 }
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index 96ea9f254ae9..76d499f6af9a 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -338,9 +338,9 @@ static __poll_t pn_socket_poll(struct file *file, struct socket *sock,
 
 	if (sk->sk_state == TCP_CLOSE)
 		return EPOLLERR;
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
-	if (!skb_queue_empty(&pn->ctrlreq_queue))
+	if (!skb_queue_empty_lockless(&pn->ctrlreq_queue))
 		mask |= EPOLLPRI;
 	if (!mask && sk->sk_state == TCP_CLOSE_WAIT)
 		return EPOLLHUP;
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index f0e9ccf472a9..6a0df7c8a939 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -65,28 +65,6 @@ static const struct proto_ops rose_proto_ops;
 ax25_address rose_callsign;
 
 /*
- * ROSE network devices are virtual network devices encapsulating ROSE
- * frames into AX.25 which will be sent through an AX.25 device, so form a
- * special "super class" of normal net devices; split their locks off into a
- * separate class since they always nest.
- */
-static struct lock_class_key rose_netdev_xmit_lock_key;
-static struct lock_class_key rose_netdev_addr_lock_key;
-
-static void rose_set_lockdep_one(struct net_device *dev,
-				 struct netdev_queue *txq,
-				 void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &rose_netdev_xmit_lock_key);
-}
-
-static void rose_set_lockdep_key(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &rose_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, rose_set_lockdep_one, NULL);
-}
-
-/*
  *	Convert a ROSE address into text.
  */
 char *rose2asc(char *buf, const rose_address *addr)
@@ -1533,7 +1511,6 @@ static int __init rose_proto_init(void)
 			free_netdev(dev);
 			goto fail;
 		}
-		rose_set_lockdep_key(dev);
 		dev_rose[i] = dev;
 	}
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index ecc17dabec8f..7c7d10f2e0c1 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -601,6 +601,7 @@ struct rxrpc_call {
 	int			debug_id;	/* debug ID for printks */
 	unsigned short		rx_pkt_offset;	/* Current recvmsg packet offset */
 	unsigned short		rx_pkt_len;	/* Current recvmsg packet len */
+	bool			rx_pkt_last;	/* Current recvmsg packet is last */
 
 	/* Rx/Tx circular buffer, depending on phase.
 	 *
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index a4090797c9b2..8578c39ec839 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -267,11 +267,13 @@ static int rxrpc_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
  */
 static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
 			     u8 *_annotation,
-			     unsigned int *_offset, unsigned int *_len)
+			     unsigned int *_offset, unsigned int *_len,
+			     bool *_last)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	unsigned int offset = sizeof(struct rxrpc_wire_header);
 	unsigned int len;
+	bool last = false;
 	int ret;
 	u8 annotation = *_annotation;
 	u8 subpacket = annotation & RXRPC_RX_ANNO_SUBPACKET;
@@ -281,6 +283,8 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
 	len = skb->len - offset;
 	if (subpacket < sp->nr_subpackets - 1)
 		len = RXRPC_JUMBO_DATALEN;
+	else if (sp->rx_flags & RXRPC_SKB_INCL_LAST)
+		last = true;
 
 	if (!(annotation & RXRPC_RX_ANNO_VERIFIED)) {
 		ret = rxrpc_verify_packet(call, skb, annotation, offset, len);
@@ -291,6 +295,7 @@ static int rxrpc_locate_data(struct rxrpc_call *call, struct sk_buff *skb,
 
 	*_offset = offset;
 	*_len = len;
+	*_last = last;
 	call->security->locate_data(call, skb, _offset, _len);
 	return 0;
 }
@@ -309,7 +314,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 	rxrpc_serial_t serial;
 	rxrpc_seq_t hard_ack, top, seq;
 	size_t remain;
-	bool last;
+	bool rx_pkt_last;
 	unsigned int rx_pkt_offset, rx_pkt_len;
 	int ix, copy, ret = -EAGAIN, ret2;
 
@@ -319,6 +324,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 
 	rx_pkt_offset = call->rx_pkt_offset;
 	rx_pkt_len = call->rx_pkt_len;
+	rx_pkt_last = call->rx_pkt_last;
 
 	if (call->state >= RXRPC_CALL_SERVER_ACK_REQUEST) {
 		seq = call->rx_hard_ack;
@@ -329,6 +335,7 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 	/* Barriers against rxrpc_input_data(). */
 	hard_ack = call->rx_hard_ack;
 	seq = hard_ack + 1;
+
 	while (top = smp_load_acquire(&call->rx_top),
 	       before_eq(seq, top)
 	       ) {
@@ -356,7 +363,8 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 		if (rx_pkt_offset == 0) {
 			ret2 = rxrpc_locate_data(call, skb,
 						 &call->rxtx_annotations[ix],
-						 &rx_pkt_offset, &rx_pkt_len);
+						 &rx_pkt_offset, &rx_pkt_len,
+						 &rx_pkt_last);
 			trace_rxrpc_recvmsg(call, rxrpc_recvmsg_next, seq,
 					    rx_pkt_offset, rx_pkt_len, ret2);
 			if (ret2 < 0) {
@@ -396,13 +404,12 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 		}
 
 		/* The whole packet has been transferred. */
-		last = sp->hdr.flags & RXRPC_LAST_PACKET;
 		if (!(flags & MSG_PEEK))
 			rxrpc_rotate_rx_window(call);
 		rx_pkt_offset = 0;
 		rx_pkt_len = 0;
 
-		if (last) {
+		if (rx_pkt_last) {
 			ASSERTCMP(seq, ==, READ_ONCE(call->rx_top));
 			ret = 1;
 			goto out;
@@ -415,6 +422,7 @@ out:
 	if (!(flags & MSG_PEEK)) {
 		call->rx_pkt_offset = rx_pkt_offset;
 		call->rx_pkt_len = rx_pkt_len;
+		call->rx_pkt_last = rx_pkt_last;
 	}
 done:
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8717c0b26c90..20d60b8fcb70 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
+#include <linux/jhash.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -47,6 +48,62 @@ static LIST_HEAD(tcf_proto_base);
 /* Protects list of registered TC modules. It is pure SMP lock. */
 static DEFINE_RWLOCK(cls_mod_lock);
 
+static u32 destroy_obj_hashfn(const struct tcf_proto *tp)
+{
+	return jhash_3words(tp->chain->index, tp->prio,
+			    (__force __u32)tp->protocol, 0);
+}
+
+static void tcf_proto_signal_destroying(struct tcf_chain *chain,
+					struct tcf_proto *tp)
+{
+	struct tcf_block *block = chain->block;
+
+	mutex_lock(&block->proto_destroy_lock);
+	hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node,
+		     destroy_obj_hashfn(tp));
+	mutex_unlock(&block->proto_destroy_lock);
+}
+
+static bool tcf_proto_cmp(const struct tcf_proto *tp1,
+			  const struct tcf_proto *tp2)
+{
+	return tp1->chain->index == tp2->chain->index &&
+	       tp1->prio == tp2->prio &&
+	       tp1->protocol == tp2->protocol;
+}
+
+static bool tcf_proto_exists_destroying(struct tcf_chain *chain,
+					struct tcf_proto *tp)
+{
+	u32 hash = destroy_obj_hashfn(tp);
+	struct tcf_proto *iter;
+	bool found = false;
+
+	rcu_read_lock();
+	hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter,
+				   destroy_ht_node, hash) {
+		if (tcf_proto_cmp(tp, iter)) {
+			found = true;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return found;
+}
+
+static void
+tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp)
+{
+	struct tcf_block *block = chain->block;
+
+	mutex_lock(&block->proto_destroy_lock);
+	if (hash_hashed(&tp->destroy_ht_node))
+		hash_del_rcu(&tp->destroy_ht_node);
+	mutex_unlock(&block->proto_destroy_lock);
+}
+
 /* Find classifier type by string name */
 
 static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
@@ -234,9 +291,11 @@ static void tcf_proto_get(struct tcf_proto *tp)
 static void tcf_chain_put(struct tcf_chain *chain);
 
 static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held,
-			      struct netlink_ext_ack *extack)
+			      bool sig_destroy, struct netlink_ext_ack *extack)
 {
 	tp->ops->destroy(tp, rtnl_held, extack);
+	if (sig_destroy)
+		tcf_proto_signal_destroyed(tp->chain, tp);
 	tcf_chain_put(tp->chain);
 	module_put(tp->ops->owner);
 	kfree_rcu(tp, rcu);
@@ -246,7 +305,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held,
 			  struct netlink_ext_ack *extack)
 {
 	if (refcount_dec_and_test(&tp->refcnt))
-		tcf_proto_destroy(tp, rtnl_held, extack);
+		tcf_proto_destroy(tp, rtnl_held, true, extack);
 }
 
 static int walker_check_empty(struct tcf_proto *tp, void *fh,
@@ -370,6 +429,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain)
 static void tcf_block_destroy(struct tcf_block *block)
 {
 	mutex_destroy(&block->lock);
+	mutex_destroy(&block->proto_destroy_lock);
 	kfree_rcu(block, rcu);
 }
 
@@ -545,6 +605,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
 
 	mutex_lock(&chain->filter_chain_lock);
 	tp = tcf_chain_dereference(chain->filter_chain, chain);
+	while (tp) {
+		tp_next = rcu_dereference_protected(tp->next, 1);
+		tcf_proto_signal_destroying(chain, tp);
+		tp = tp_next;
+	}
+	tp = tcf_chain_dereference(chain->filter_chain, chain);
 	RCU_INIT_POINTER(chain->filter_chain, NULL);
 	tcf_chain0_head_change(chain, NULL);
 	chain->flushing = true;
@@ -844,6 +910,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 		return ERR_PTR(-ENOMEM);
 	}
 	mutex_init(&block->lock);
+	mutex_init(&block->proto_destroy_lock);
 	init_rwsem(&block->cb_lock);
 	flow_block_init(&block->flow_block);
 	INIT_LIST_HEAD(&block->chain_list);
@@ -1621,6 +1688,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
 
 	mutex_lock(&chain->filter_chain_lock);
 
+	if (tcf_proto_exists_destroying(chain, tp_new)) {
+		mutex_unlock(&chain->filter_chain_lock);
+		tcf_proto_destroy(tp_new, rtnl_held, false, NULL);
+		return ERR_PTR(-EAGAIN);
+	}
+
 	tp = tcf_chain_tp_find(chain, &chain_info,
 			       protocol, prio, false);
 	if (!tp)
@@ -1628,10 +1701,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain,
 	mutex_unlock(&chain->filter_chain_lock);
 
 	if (tp) {
-		tcf_proto_destroy(tp_new, rtnl_held, NULL);
+		tcf_proto_destroy(tp_new, rtnl_held, false, NULL);
 		tp_new = tp;
 	} else if (err) {
-		tcf_proto_destroy(tp_new, rtnl_held, NULL);
+		tcf_proto_destroy(tp_new, rtnl_held, false, NULL);
 		tp_new = ERR_PTR(err);
 	}
 
@@ -1669,6 +1742,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain,
 		return;
 	}
 
+	tcf_proto_signal_destroying(chain, tp);
 	next = tcf_chain_dereference(chain_info.next, chain);
 	if (tp == chain->filter_chain)
 		tcf_chain0_head_change(chain, next);
@@ -2188,6 +2262,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 		err = -EINVAL;
 		goto errout_locked;
 	} else if (t->tcm_handle == 0) {
+		tcf_proto_signal_destroying(chain, tp);
 		tcf_chain_tp_remove(chain, &chain_info, tp);
 		mutex_unlock(&chain->filter_chain_lock);
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index bf10bdaf5012..8229ed4a67be 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -162,16 +162,20 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	cls_bpf.name = obj->bpf_name;
 	cls_bpf.exts_integrated = obj->exts_integrated;
 
-	if (oldprog)
+	if (oldprog && prog)
 		err = tc_setup_cb_replace(block, tp, TC_SETUP_CLSBPF, &cls_bpf,
 					  skip_sw, &oldprog->gen_flags,
 					  &oldprog->in_hw_count,
 					  &prog->gen_flags, &prog->in_hw_count,
 					  true);
-	else
+	else if (prog)
 		err = tc_setup_cb_add(block, tp, TC_SETUP_CLSBPF, &cls_bpf,
 				      skip_sw, &prog->gen_flags,
 				      &prog->in_hw_count, true);
+	else
+		err = tc_setup_cb_destroy(block, tp, TC_SETUP_CLSBPF, &cls_bpf,
+					  skip_sw, &oldprog->gen_flags,
+					  &oldprog->in_hw_count, true);
 
 	if (prog && err) {
 		cls_bpf_offload_cmd(tp, oldprog, prog, extack);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 17bd8f539bc7..8769b4b8807d 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -799,9 +799,6 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = {
 };
 EXPORT_SYMBOL(pfifo_fast_ops);
 
-static struct lock_class_key qdisc_tx_busylock;
-static struct lock_class_key qdisc_running_key;
-
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
 			  struct netlink_ext_ack *extack)
@@ -854,17 +851,9 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	}
 
 	spin_lock_init(&sch->busylock);
-	lockdep_set_class(&sch->busylock,
-			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
-
 	/* seqlock has the same scope of busylock, for NOLOCK qdisc */
 	spin_lock_init(&sch->seqlock);
-	lockdep_set_class(&sch->busylock,
-			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
-
 	seqcount_init(&sch->running);
-	lockdep_set_class(&sch->running,
-			  dev->qdisc_running_key ?: &qdisc_running_key);
 
 	sch->ops = ops;
 	sch->flags = ops->static_flags;
@@ -875,6 +864,12 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	dev_hold(dev);
 	refcount_set(&sch->refcnt, 1);
 
+	if (sch != &noop_qdisc) {
+		lockdep_set_class(&sch->busylock, &dev->qdisc_tx_busylock_key);
+		lockdep_set_class(&sch->seqlock, &dev->qdisc_tx_busylock_key);
+		lockdep_set_class(&sch->running, &dev->qdisc_running_key);
+	}
+
 	return sch;
 errout1:
 	kfree(p);
@@ -1043,6 +1038,8 @@ static void attach_one_default_qdisc(struct net_device *dev,
 
 	if (dev->priv_flags & IFF_NO_QUEUE)
 		ops = &noqueue_qdisc_ops;
+	else if(dev->type == ARPHRD_CAN)
+		ops = &pfifo_fast_ops;
 
 	qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL);
 	if (!qdisc) {
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index 23cd1c873a2c..be35f03b657b 100644
--- a/net/sched/sch_hhf.c
+++ b/net/sched/sch_hhf.c
@@ -5,11 +5,11 @@
  * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com>
  */
 
-#include <linux/jhash.h>
 #include <linux/jiffies.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
+#include <linux/siphash.h>
 #include <net/pkt_sched.h>
 #include <net/sock.h>
 
@@ -126,7 +126,7 @@ struct wdrr_bucket {
 
 struct hhf_sched_data {
 	struct wdrr_bucket buckets[WDRR_BUCKET_CNT];
-	u32		   perturbation;   /* hash perturbation */
+	siphash_key_t	   perturbation;   /* hash perturbation */
 	u32		   quantum;        /* psched_mtu(qdisc_dev(sch)); */
 	u32		   drop_overlimit; /* number of times max qdisc packet
 					    * limit was hit
@@ -264,7 +264,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch)
 	}
 
 	/* Get hashed flow-id of the skb. */
-	hash = skb_get_hash_perturb(skb, q->perturbation);
+	hash = skb_get_hash_perturb(skb, &q->perturbation);
 
 	/* Check if this packet belongs to an already established HH flow. */
 	flow_pos = hash & HHF_BIT_MASK;
@@ -582,7 +582,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt,
 
 	sch->limit = 1000;
 	q->quantum = psched_mtu(qdisc_dev(sch));
-	q->perturbation = prandom_u32();
+	get_random_bytes(&q->perturbation, sizeof(q->perturbation));
 	INIT_LIST_HEAD(&q->new_buckets);
 	INIT_LIST_HEAD(&q->old_buckets);
 
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index d448fe3068e5..4074c50ac3d7 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -18,7 +18,7 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <linux/random.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <net/ip.h>
 #include <net/pkt_sched.h>
 #include <net/pkt_cls.h>
@@ -45,7 +45,7 @@ struct sfb_bucket {
  * (Section 4.4 of SFB reference : moving hash functions)
  */
 struct sfb_bins {
-	u32		  perturbation; /* jhash perturbation */
+	siphash_key_t	  perturbation; /* siphash key */
 	struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS];
 };
 
@@ -217,7 +217,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da
 
 static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q)
 {
-	q->bins[slot].perturbation = prandom_u32();
+	get_random_bytes(&q->bins[slot].perturbation,
+			 sizeof(q->bins[slot].perturbation));
 }
 
 static void sfb_swap_slot(struct sfb_sched_data *q)
@@ -314,9 +315,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		/* If using external classifiers, get result and record it. */
 		if (!sfb_classify(skb, fl, &ret, &salt))
 			goto other_drop;
-		sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+		sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation);
 	} else {
-		sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation);
+		sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation);
 	}
 
 
@@ -352,7 +353,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		/* Inelastic flow */
 		if (q->double_buffering) {
 			sfbhash = skb_get_hash_perturb(skb,
-			    q->bins[slot].perturbation);
+			    &q->bins[slot].perturbation);
 			if (!sfbhash)
 				sfbhash = 1;
 			sfb_skb_cb(skb)->hashes[slot] = sfbhash;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 68404a9d2ce4..c787d4d46017 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -14,7 +14,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/skbuff.h>
-#include <linux/jhash.h>
+#include <linux/siphash.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <net/netlink.h>
@@ -117,7 +117,7 @@ struct sfq_sched_data {
 	u8		headdrop;
 	u8		maxdepth;	/* limit of packets per flow */
 
-	u32		perturbation;
+	siphash_key_t 	perturbation;
 	u8		cur_depth;	/* depth of longest slot */
 	u8		flags;
 	unsigned short  scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */
@@ -157,7 +157,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index
 static unsigned int sfq_hash(const struct sfq_sched_data *q,
 			     const struct sk_buff *skb)
 {
-	return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1);
+	return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1);
 }
 
 static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
@@ -607,9 +607,11 @@ static void sfq_perturbation(struct timer_list *t)
 	struct sfq_sched_data *q = from_timer(q, t, perturb_timer);
 	struct Qdisc *sch = q->sch;
 	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+	siphash_key_t nkey;
 
+	get_random_bytes(&nkey, sizeof(nkey));
 	spin_lock(root_lock);
-	q->perturbation = prandom_u32();
+	q->perturbation = nkey;
 	if (!q->filter_list && q->tail)
 		sfq_rehash(sch);
 	spin_unlock(root_lock);
@@ -688,7 +690,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	del_timer(&q->perturb_timer);
 	if (q->perturb_period) {
 		mod_timer(&q->perturb_timer, jiffies + q->perturb_period);
-		q->perturbation = prandom_u32();
+		get_random_bytes(&q->perturbation, sizeof(q->perturbation));
 	}
 	sch_tree_unlock(sch);
 	kfree(p);
@@ -745,7 +747,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt,
 	q->quantum = psched_mtu(qdisc_dev(sch));
 	q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum);
 	q->perturb_period = 0;
-	q->perturbation = prandom_u32();
+	get_random_bytes(&q->perturbation, sizeof(q->perturbation));
 
 	if (opt) {
 		int err = sfq_change(sch, opt);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 6719a65169d4..7cd68628c637 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1152,7 +1152,7 @@ EXPORT_SYMBOL_GPL(taprio_offload_free);
  * offload state (PENDING, ACTIVE, INACTIVE) so it can be visible in dump().
  * This is left as TODO.
  */
-void taprio_offload_config_changed(struct taprio_sched *q)
+static void taprio_offload_config_changed(struct taprio_sched *q)
 {
 	struct sched_gate_list *oper, *admin;
 
@@ -1224,8 +1224,6 @@ static int taprio_enable_offload(struct net_device *dev,
 		goto done;
 	}
 
-	taprio_offload_config_changed(q);
-
 done:
 	taprio_offload_free(offload);
 
@@ -1505,6 +1503,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			call_rcu(&admin->rcu, taprio_free_sched_cb);
 
 		spin_unlock_irqrestore(&q->current_entry_lock, flags);
+
+		if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+			taprio_offload_config_changed(q);
 	}
 
 	new_admin = NULL;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 5ca0ec0e823c..ffd3262b7a41 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -8476,7 +8476,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	mask = 0;
 
 	/* Is there any exceptional events?  */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
@@ -8485,7 +8485,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait)
 		mask |= EPOLLHUP;
 
 	/* Is it readable?  Reconsider this code with TCP-style support.  */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* The association is either gone or not ready.  */
@@ -8871,7 +8871,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags,
 		if (sk_can_busy_loop(sk)) {
 			sk_busy_loop(sk, noblock);
 
-			if (!skb_queue_empty(&sk->sk_receive_queue))
+			if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 				continue;
 		}
 
@@ -9306,7 +9306,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newinet->inet_rcv_saddr = inet->inet_rcv_saddr;
 	newinet->inet_dport = htons(asoc->peer.port);
 	newinet->pmtudisc = inet->pmtudisc;
-	newinet->inet_id = asoc->next_tsn ^ jiffies;
+	newinet->inet_id = prandom_u32();
 
 	newinet->uc_ttl = inet->uc_ttl;
 	newinet->mc_loop = 1;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 5b932583e407..47946f489fd4 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -123,6 +123,12 @@ struct proto smc_proto6 = {
 };
 EXPORT_SYMBOL_GPL(smc_proto6);
 
+static void smc_restore_fallback_changes(struct smc_sock *smc)
+{
+	smc->clcsock->file->private_data = smc->sk.sk_socket;
+	smc->clcsock->file = NULL;
+}
+
 static int __smc_release(struct smc_sock *smc)
 {
 	struct sock *sk = &smc->sk;
@@ -141,6 +147,7 @@ static int __smc_release(struct smc_sock *smc)
 		}
 		sk->sk_state = SMC_CLOSED;
 		sk->sk_state_change(sk);
+		smc_restore_fallback_changes(smc);
 	}
 
 	sk->sk_prot->unhash(sk);
@@ -700,8 +707,6 @@ static int __smc_connect(struct smc_sock *smc)
 	int smc_type;
 	int rc = 0;
 
-	sock_hold(&smc->sk); /* sock put in passive closing */
-
 	if (smc->use_fallback)
 		return smc_connect_fallback(smc, smc->fallback_rsn);
 
@@ -846,6 +851,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 	rc = kernel_connect(smc->clcsock, addr, alen, flags);
 	if (rc && rc != -EINPROGRESS)
 		goto out;
+
+	sock_hold(&smc->sk); /* sock put in passive closing */
 	if (flags & O_NONBLOCK) {
 		if (schedule_work(&smc->connect_work))
 			smc->connect_nonblock = 1;
@@ -1291,8 +1298,8 @@ static void smc_listen_work(struct work_struct *work)
 	/* check if RDMA is available */
 	if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */
 		/* prepare RDMA check */
-		memset(&ini, 0, sizeof(ini));
 		ini.is_smcd = false;
+		ini.ism_dev = NULL;
 		ini.ib_lcl = &pclc->lcl;
 		rc = smc_find_rdma_device(new_smc, &ini);
 		if (rc) {
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 88556f0251ab..2ba97ff325a5 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -561,7 +561,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini)
 	}
 
 	rtnl_lock();
-	nest_lvl = dev_get_nest_level(ndev);
+	nest_lvl = ndev->lower_level;
 	for (i = 0; i < nest_lvl; i++) {
 		struct list_head *lower = &ndev->adj_list.lower;
 
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index bab2da8cf17a..571e6d84da3b 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -376,8 +376,6 @@ static int smc_pnet_fill_entry(struct net *net,
 	return 0;
 
 error:
-	if (pnetelem->ndev)
-		dev_put(pnetelem->ndev);
 	return rc;
 }
 
@@ -718,7 +716,7 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 	int i, nest_lvl;
 
 	rtnl_lock();
-	nest_lvl = dev_get_nest_level(ndev);
+	nest_lvl = ndev->lower_level;
 	for (i = 0; i < nest_lvl; i++) {
 		struct list_head *lower = &ndev->adj_list.lower;
 
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 339e8c077c2d..195b40c5dae4 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -220,7 +220,7 @@ void xprt_destroy_bc(struct rpc_xprt *xprt, unsigned int max_reqs)
 		goto out;
 
 	spin_lock_bh(&xprt->bc_pa_lock);
-	xprt->bc_alloc_max -= max_reqs;
+	xprt->bc_alloc_max -= min(max_reqs, xprt->bc_alloc_max);
 	list_for_each_entry_safe(req, tmp, &xprt->bc_pa_list, rq_bc_pa_list) {
 		dprintk("RPC:        req=%p\n", req);
 		list_del(&req->rq_bc_pa_list);
@@ -307,8 +307,8 @@ void xprt_free_bc_rqst(struct rpc_rqst *req)
 		 */
 		dprintk("RPC:       Last session removed req=%p\n", req);
 		xprt_free_allocation(req);
-		return;
 	}
+	xprt_put(xprt);
 }
 
 /*
@@ -339,7 +339,7 @@ found:
 		spin_unlock(&xprt->bc_pa_lock);
 		if (new) {
 			if (req != new)
-				xprt_free_bc_rqst(new);
+				xprt_free_allocation(new);
 			break;
 		} else if (req)
 			break;
@@ -368,6 +368,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied)
 	set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
 
 	dprintk("RPC:       add callback request to list\n");
+	xprt_get(xprt);
 	spin_lock(&bc_serv->sv_cb_lock);
 	list_add(&req->rq_bc_list, &bc_serv->sv_cb_list);
 	wake_up(&bc_serv->sv_cb_waitq);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 8a45b3ccc313..41df4c507193 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1943,6 +1943,11 @@ static void xprt_destroy_cb(struct work_struct *work)
 	rpc_destroy_wait_queue(&xprt->backlog);
 	kfree(xprt->servername);
 	/*
+	 * Destroy any existing back channel
+	 */
+	xprt_destroy_backchannel(xprt, UINT_MAX);
+
+	/*
 	 * Tear down transport state and free the rpc_xprt
 	 */
 	xprt->ops->destroy(xprt);
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index 50e075fcdd8f..b458bf53ca69 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -163,6 +163,7 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst)
 	spin_lock(&xprt->bc_pa_lock);
 	list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list);
 	spin_unlock(&xprt->bc_pa_lock);
+	xprt_put(xprt);
 }
 
 static struct rpc_rqst *rpcrdma_bc_rqst_get(struct rpcrdma_xprt *r_xprt)
@@ -259,6 +260,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt,
 
 	/* Queue rqst for ULP's callback service */
 	bc_serv = xprt->bc_serv;
+	xprt_get(xprt);
 	spin_lock(&bc_serv->sv_cb_lock);
 	list_add(&rqst->rq_bc_list, &bc_serv->sv_cb_list);
 	spin_unlock(&bc_serv->sv_cb_lock);
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index f8bbc4aab213..4b92b196cfa6 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -740,7 +740,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 		/* fall through */
 	case TIPC_LISTEN:
 	case TIPC_CONNECTING:
-		if (!skb_queue_empty(&sk->sk_receive_queue))
+		if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 			revents |= EPOLLIN | EPOLLRDNORM;
 		break;
 	case TIPC_OPEN:
@@ -748,7 +748,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 			revents |= EPOLLOUT;
 		if (!tipc_sk_type_connectionless(sk))
 			break;
-		if (skb_queue_empty(&sk->sk_receive_queue))
+		if (skb_queue_empty_lockless(&sk->sk_receive_queue))
 			break;
 		revents |= EPOLLIN | EPOLLRDNORM;
 		break;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index f959487c5cd1..683d00837693 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -523,8 +523,10 @@ last_record:
 int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	int rc;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
 	if (unlikely(msg->msg_controllen)) {
@@ -538,12 +540,14 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 
 out:
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return rc;
 }
 
 int tls_device_sendpage(struct sock *sk, struct page *page,
 			int offset, size_t size, int flags)
 {
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct iov_iter	msg_iter;
 	char *kaddr = kmap(page);
 	struct kvec iov;
@@ -552,6 +556,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 	if (flags & MSG_SENDPAGE_NOTLAST)
 		flags |= MSG_MORE;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
 	if (flags & MSG_OOB) {
@@ -568,6 +573,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 
 out:
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return rc;
 }
 
@@ -623,9 +629,11 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
 
 void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 {
-	if (!sk->sk_write_pending && tls_is_partially_sent_record(ctx)) {
+	if (tls_is_partially_sent_record(ctx)) {
 		gfp_t sk_allocation = sk->sk_allocation;
 
+		WARN_ON_ONCE(sk->sk_write_pending);
+
 		sk->sk_allocation = GFP_ATOMIC;
 		tls_push_partial_record(sk, ctx,
 					MSG_DONTWAIT | MSG_NOSIGNAL |
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index ac88877dcade..0775ae40fcfb 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -267,6 +267,7 @@ void tls_ctx_free(struct sock *sk, struct tls_context *ctx)
 
 	memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send));
 	memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv));
+	mutex_destroy(&ctx->tx_lock);
 
 	if (sk)
 		kfree_rcu(ctx, rcu);
@@ -612,6 +613,7 @@ static struct tls_context *create_ctx(struct sock *sk)
 	if (!ctx)
 		return NULL;
 
+	mutex_init(&ctx->tx_lock);
 	rcu_assign_pointer(icsk->icsk_ulp_data, ctx);
 	ctx->sk_proto = sk->sk_prot;
 	return ctx;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index c2b5e0d2ba1a..446f23c1f3ce 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -897,15 +897,9 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -ENOTSUPP;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 
-	/* Wait till there is any pending write on socket */
-	if (unlikely(sk->sk_write_pending)) {
-		ret = wait_on_pending_writer(sk, &timeo);
-		if (unlikely(ret))
-			goto send_end;
-	}
-
 	if (unlikely(msg->msg_controllen)) {
 		ret = tls_proccess_cmsg(sk, msg, &record_type);
 		if (ret) {
@@ -1091,6 +1085,7 @@ send_end:
 	ret = sk_stream_error(sk, msg->msg_flags, ret);
 
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return copied ? copied : ret;
 }
 
@@ -1114,13 +1109,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page,
 	eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST));
 	sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
 
-	/* Wait till there is any pending write on socket */
-	if (unlikely(sk->sk_write_pending)) {
-		ret = wait_on_pending_writer(sk, &timeo);
-		if (unlikely(ret))
-			goto sendpage_end;
-	}
-
 	/* Call the sk_stream functions to manage the sndbuf mem. */
 	while (size > 0) {
 		size_t copy, required_size;
@@ -1219,15 +1207,18 @@ sendpage_end:
 int tls_sw_sendpage(struct sock *sk, struct page *page,
 		    int offset, size_t size, int flags)
 {
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	int ret;
 
 	if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL |
 		      MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY))
 		return -ENOTSUPP;
 
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 	ret = tls_sw_do_sendpage(sk, page, offset, size, flags);
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 	return ret;
 }
 
@@ -2170,9 +2161,11 @@ static void tx_work_handler(struct work_struct *work)
 
 	if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask))
 		return;
+	mutex_lock(&tls_ctx->tx_lock);
 	lock_sock(sk);
 	tls_tx_records(sk, -1);
 	release_sock(sk);
+	mutex_unlock(&tls_ctx->tx_lock);
 }
 
 void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
@@ -2180,12 +2173,9 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx)
 	struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx);
 
 	/* Schedule the transmission if tx list is ready */
-	if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) {
-		/* Schedule the transmission */
-		if (!test_and_set_bit(BIT_TX_SCHEDULED,
-				      &tx_ctx->tx_bitmask))
-			schedule_delayed_work(&tx_ctx->tx_work.work, 0);
-	}
+	if (is_tx_ready(tx_ctx) &&
+	    !test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask))
+		schedule_delayed_work(&tx_ctx->tx_work.work, 0);
 }
 
 void tls_sw_strparser_arm(struct sock *sk, struct tls_context *tls_ctx)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 67e87db5877f..0d8da809bea2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2599,7 +2599,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 		mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
@@ -2628,7 +2628,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	mask = 0;
 
 	/* exceptional events? */
-	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+	if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue))
 		mask |= EPOLLERR |
 			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);
 
@@ -2638,7 +2638,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 		mask |= EPOLLHUP;
 
 	/* readable? */
-	if (!skb_queue_empty(&sk->sk_receive_queue))
+	if (!skb_queue_empty_lockless(&sk->sk_receive_queue))
 		mask |= EPOLLIN | EPOLLRDNORM;
 
 	/* Connection-based need to check for termination and startup */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 2ab43b2bba31..582a3e4dfce2 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -870,7 +870,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		 * the queue and write as long as the socket isn't shutdown for
 		 * sending.
 		 */
-		if (!skb_queue_empty(&sk->sk_receive_queue) ||
+		if (!skb_queue_empty_lockless(&sk->sk_receive_queue) ||
 		    (sk->sk_shutdown & RCV_SHUTDOWN)) {
 			mask |= EPOLLIN | EPOLLRDNORM;
 		}
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 481f7f8a1655..fb2060dffb0a 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -947,9 +947,11 @@ virtio_transport_recv_connected(struct sock *sk,
 		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
 			vsk->peer_shutdown |= SEND_SHUTDOWN;
 		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
-		    vsock_stream_has_data(vsk) <= 0) {
-			sock_set_flag(sk, SOCK_DONE);
-			sk->sk_state = TCP_CLOSING;
+		    vsock_stream_has_data(vsk) <= 0 &&
+		    !sock_flag(sk, SOCK_DONE)) {
+			(void)virtio_transport_reset(vsk, NULL);
+
+			virtio_transport_do_close(vsk, true);
 		}
 		if (le32_to_cpu(pkt->hdr.flags))
 			sk->sk_state_change(sk);
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index e851cafd8e2f..fcac5c6366e1 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -204,6 +204,11 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 		return false;
 	}
 
+	/* channel 14 is only for IEEE 802.11b */
+	if (chandef->center_freq1 == 2484 &&
+	    chandef->width != NL80211_CHAN_WIDTH_20_NOHT)
+		return false;
+
 	if (cfg80211_chandef_is_edmg(chandef) &&
 	    !cfg80211_edmg_chandef_valid(chandef))
 		return false;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4453dd375de9..7b72286922f7 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -393,7 +393,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ },
 	[NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY,
 				   .len = IEEE80211_MAX_MESH_ID_LEN },
-	[NL80211_ATTR_MPATH_NEXT_HOP] = { .type = NLA_U32 },
+	[NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT,
 
 	[NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 },
 	[NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED },
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 419eb12c1e93..5b4ed5bbc542 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1559,7 +1559,8 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef,
 	}
 
 	if (freq == 2484) {
-		if (chandef->width > NL80211_CHAN_WIDTH_40)
+		/* channel 14 is only for IEEE 802.11b */
+		if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT)
 			return false;
 
 		*op_class = 82; /* channel 14 */
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 16d5f353163a..3049af269fbf 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -27,6 +27,9 @@ void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
 	unsigned long flags;
 
+	if (!xs->tx)
+		return;
+
 	spin_lock_irqsave(&umem->xsk_list_lock, flags);
 	list_add_rcu(&xs->list, &umem->xsk_list);
 	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
@@ -36,6 +39,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
 	unsigned long flags;
 
+	if (!xs->tx)
+		return;
+
 	spin_lock_irqsave(&umem->xsk_list_lock, flags);
 	list_del_rcu(&xs->list);
 	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 1d9be26b4edd..42b571cde177 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -176,6 +176,7 @@ KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
 KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
+KBUILD_HOSTCFLAGS += -DHAVE_ATTR_TEST=0
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 
diff --git a/scripts/gdb/linux/symbols.py b/scripts/gdb/linux/symbols.py
index 7b7c2fafbc68..be984aa29b75 100644
--- a/scripts/gdb/linux/symbols.py
+++ b/scripts/gdb/linux/symbols.py
@@ -99,7 +99,8 @@ lx-symbols command."""
             attrs[n]['name'].string(): attrs[n]['address']
             for n in range(int(sect_attrs['nsections']))}
         args = []
-        for section_name in [".data", ".data..read_mostly", ".rodata", ".bss"]:
+        for section_name in [".data", ".data..read_mostly", ".rodata", ".bss",
+                             ".text", ".text.hot", ".text.unlikely"]:
             address = section_name_to_address.get(section_name)
             if address:
                 args.append(" -s {name} {addr}".format(
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 936d3ad23c83..d2a30a7b3f07 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -348,26 +348,38 @@ static enum export export_from_sec(struct elf_info *elf, unsigned int sec)
 		return export_unknown;
 }
 
-static char *sym_extract_namespace(const char **symname)
+static const char *namespace_from_kstrtabns(struct elf_info *info,
+					    Elf_Sym *kstrtabns)
 {
-	char *namespace = NULL;
-	char *ns_separator;
+	char *value = info->ksymtab_strings + kstrtabns->st_value;
+	return value[0] ? value : NULL;
+}
+
+static void sym_update_namespace(const char *symname, const char *namespace)
+{
+	struct symbol *s = find_symbol(symname);
 
-	ns_separator = strchr(*symname, '.');
-	if (ns_separator) {
-		namespace = NOFAIL(strndup(*symname, ns_separator - *symname));
-		*symname = ns_separator + 1;
+	/*
+	 * That symbol should have been created earlier and thus this is
+	 * actually an assertion.
+	 */
+	if (!s) {
+		merror("Could not update namespace(%s) for symbol %s\n",
+		       namespace, symname);
+		return;
 	}
 
-	return namespace;
+	free(s->namespace);
+	s->namespace =
+		namespace && namespace[0] ? NOFAIL(strdup(namespace)) : NULL;
 }
 
 /**
  * Add an exported symbol - it may have already been added without a
  * CRC, in this case just update the CRC
  **/
-static struct symbol *sym_add_exported(const char *name, const char *namespace,
-				       struct module *mod, enum export export)
+static struct symbol *sym_add_exported(const char *name, struct module *mod,
+				       enum export export)
 {
 	struct symbol *s = find_symbol(name);
 
@@ -383,8 +395,6 @@ static struct symbol *sym_add_exported(const char *name, const char *namespace,
 			s->module = mod;
 		}
 	}
-	free(s->namespace);
-	s->namespace = namespace ? strdup(namespace) : NULL;
 	s->preloaded = 0;
 	s->vmlinux   = is_vmlinux(mod->name);
 	s->kernel    = 0;
@@ -583,6 +593,10 @@ static int parse_elf(struct elf_info *info, const char *filename)
 			info->export_unused_gpl_sec = i;
 		else if (strcmp(secname, "__ksymtab_gpl_future") == 0)
 			info->export_gpl_future_sec = i;
+		else if (strcmp(secname, "__ksymtab_strings") == 0)
+			info->ksymtab_strings = (void *)hdr +
+						sechdrs[i].sh_offset -
+						sechdrs[i].sh_addr;
 
 		if (sechdrs[i].sh_type == SHT_SYMTAB) {
 			unsigned int sh_link_idx;
@@ -672,7 +686,6 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 	enum export export;
 	bool is_crc = false;
 	const char *name;
-	char *namespace;
 
 	if ((!is_vmlinux(mod->name) || mod->is_dot_o) &&
 	    strstarts(symname, "__ksymtab"))
@@ -745,9 +758,7 @@ static void handle_modversions(struct module *mod, struct elf_info *info,
 		/* All exported symbols */
 		if (strstarts(symname, "__ksymtab_")) {
 			name = symname + strlen("__ksymtab_");
-			namespace = sym_extract_namespace(&name);
-			sym_add_exported(name, namespace, mod, export);
-			free(namespace);
+			sym_add_exported(name, mod, export);
 		}
 		if (strcmp(symname, "init_module") == 0)
 			mod->has_init = 1;
@@ -2043,6 +2054,16 @@ static void read_symbols(const char *modname)
 		handle_moddevtable(mod, &info, sym, symname);
 	}
 
+	/* Apply symbol namespaces from __kstrtabns_<symbol> entries. */
+	for (sym = info.symtab_start; sym < info.symtab_stop; sym++) {
+		symname = remove_dot(info.strtab + sym->st_name);
+
+		if (strstarts(symname, "__kstrtabns_"))
+			sym_update_namespace(symname + strlen("__kstrtabns_"),
+					     namespace_from_kstrtabns(&info,
+								      sym));
+	}
+
 	// check for static EXPORT_SYMBOL_* functions && global vars
 	for (sym = info.symtab_start; sym < info.symtab_stop; sym++) {
 		unsigned char bind = ELF_ST_BIND(sym->st_info);
@@ -2196,7 +2217,7 @@ static int check_exports(struct module *mod)
 		else
 			basename = mod->name;
 
-		if (exp->namespace && exp->namespace[0]) {
+		if (exp->namespace) {
 			add_namespace(&mod->required_namespaces,
 				      exp->namespace);
 
@@ -2454,12 +2475,12 @@ static void read_dump(const char *fname, unsigned int kernel)
 			mod = new_module(modname);
 			mod->skip = 1;
 		}
-		s = sym_add_exported(symname, namespace, mod,
-				     export_no(export));
+		s = sym_add_exported(symname, mod, export_no(export));
 		s->kernel    = kernel;
 		s->preloaded = 1;
 		s->is_static = 0;
 		sym_update_crc(symname, mod, crc, export_no(export));
+		sym_update_namespace(symname, namespace);
 	}
 	release_file(file, size);
 	return;
diff --git a/scripts/mod/modpost.h b/scripts/mod/modpost.h
index 92a926d375d2..ad271bc6c313 100644
--- a/scripts/mod/modpost.h
+++ b/scripts/mod/modpost.h
@@ -143,6 +143,7 @@ struct elf_info {
 	Elf_Section  export_gpl_sec;
 	Elf_Section  export_unused_gpl_sec;
 	Elf_Section  export_gpl_future_sec;
+	char	     *ksymtab_strings;
 	char         *strtab;
 	char	     *modinfo;
 	unsigned int modinfo_len;
diff --git a/scripts/nsdeps b/scripts/nsdeps
index 3754dac13b31..04cea0921673 100644
--- a/scripts/nsdeps
+++ b/scripts/nsdeps
@@ -31,12 +31,12 @@ generate_deps() {
 	local mod_file=`echo $@ | sed -e 's/\.ko/\.mod/'`
 	local ns_deps_file=`echo $@ | sed -e 's/\.ko/\.ns_deps/'`
 	if [ ! -f "$ns_deps_file" ]; then return; fi
-	local mod_source_files=`cat $mod_file | sed -n 1p                      \
+	local mod_source_files="`cat $mod_file | sed -n 1p                      \
 					      | sed -e 's/\.o/\.c/g'           \
-					      | sed "s/[^ ]* */${srctree}\/&/g"`
+					      | sed "s|[^ ]* *|${srctree}/&|g"`"
 	for ns in `cat $ns_deps_file`; do
 		echo "Adding namespace $ns to module $mod_name (if needed)."
-		generate_deps_for_ns $ns $mod_source_files
+		generate_deps_for_ns $ns "$mod_source_files"
 		# sort the imports
 		for source_file in $mod_source_files; do
 			sed '/MODULE_IMPORT_NS/Q' $source_file > ${source_file}.tmp
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 725674f3276d..7d0f8f7431ff 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -801,8 +801,8 @@ struct cgroup_subsys devices_cgrp_subsys = {
  *
  * returns 0 on success, -EPERM case the operation is not permitted
  */
-int __devcgroup_check_permission(short type, u32 major, u32 minor,
-				 short access)
+static int __devcgroup_check_permission(short type, u32 major, u32 minor,
+					short access)
 {
 	struct dev_cgroup *dev_cgroup;
 	bool rc;
@@ -824,3 +824,14 @@ int __devcgroup_check_permission(short type, u32 major, u32 minor,
 
 	return 0;
 }
+
+int devcgroup_check_permission(short type, u32 major, u32 minor, short access)
+{
+	int rc = BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type, major, minor, access);
+
+	if (rc)
+		return -EPERM;
+
+	return __devcgroup_check_permission(type, major, minor, access);
+}
+EXPORT_SYMBOL(devcgroup_check_permission);
diff --git a/security/lockdown/lockdown.c b/security/lockdown/lockdown.c
index 8a10b43daf74..40b790536def 100644
--- a/security/lockdown/lockdown.c
+++ b/security/lockdown/lockdown.c
@@ -20,6 +20,7 @@ static const char *const lockdown_reasons[LOCKDOWN_CONFIDENTIALITY_MAX+1] = {
 	[LOCKDOWN_NONE] = "none",
 	[LOCKDOWN_MODULE_SIGNATURE] = "unsigned module loading",
 	[LOCKDOWN_DEV_MEM] = "/dev/mem,kmem,port",
+	[LOCKDOWN_EFI_TEST] = "/dev/efi_test access",
 	[LOCKDOWN_KEXEC] = "kexec of unsigned images",
 	[LOCKDOWN_HIBERNATION] = "hibernation",
 	[LOCKDOWN_PCI_ACCESS] = "direct PCI access",
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 41905afada63..f34ce564d92c 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -528,7 +528,7 @@ static int snd_compress_check_input(struct snd_compr_params *params)
 {
 	/* first let's check the buffer parameter's */
 	if (params->buffer.fragment_size == 0 ||
-	    params->buffer.fragments > INT_MAX / params->buffer.fragment_size ||
+	    params->buffer.fragments > U32_MAX / params->buffer.fragment_size ||
 	    params->buffer.fragments == 0)
 		return -EINVAL;
 
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 5c9fbf3f4340..59ae21b0bb93 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -226,7 +226,8 @@ static int snd_timer_check_master(struct snd_timer_instance *master)
 	return 0;
 }
 
-static int snd_timer_close_locked(struct snd_timer_instance *timeri);
+static int snd_timer_close_locked(struct snd_timer_instance *timeri,
+				  struct device **card_devp_to_put);
 
 /*
  * open a timer instance
@@ -238,6 +239,7 @@ int snd_timer_open(struct snd_timer_instance **ti,
 {
 	struct snd_timer *timer;
 	struct snd_timer_instance *timeri = NULL;
+	struct device *card_dev_to_put = NULL;
 	int err;
 
 	mutex_lock(&register_mutex);
@@ -261,7 +263,7 @@ int snd_timer_open(struct snd_timer_instance **ti,
 		list_add_tail(&timeri->open_list, &snd_timer_slave_list);
 		err = snd_timer_check_slave(timeri);
 		if (err < 0) {
-			snd_timer_close_locked(timeri);
+			snd_timer_close_locked(timeri, &card_dev_to_put);
 			timeri = NULL;
 		}
 		goto unlock;
@@ -282,11 +284,11 @@ int snd_timer_open(struct snd_timer_instance **ti,
 		goto unlock;
 	}
 	if (!list_empty(&timer->open_list_head)) {
-		timeri = list_entry(timer->open_list_head.next,
+		struct snd_timer_instance *t =
+			list_entry(timer->open_list_head.next,
 				    struct snd_timer_instance, open_list);
-		if (timeri->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) {
+		if (t->flags & SNDRV_TIMER_IFLG_EXCLUSIVE) {
 			err = -EBUSY;
-			timeri = NULL;
 			goto unlock;
 		}
 	}
@@ -313,7 +315,7 @@ int snd_timer_open(struct snd_timer_instance **ti,
 			timeri = NULL;
 
 			if (timer->card)
-				put_device(&timer->card->card_dev);
+				card_dev_to_put = &timer->card->card_dev;
 			module_put(timer->module);
 			goto unlock;
 		}
@@ -323,12 +325,15 @@ int snd_timer_open(struct snd_timer_instance **ti,
 	timer->num_instances++;
 	err = snd_timer_check_master(timeri);
 	if (err < 0) {
-		snd_timer_close_locked(timeri);
+		snd_timer_close_locked(timeri, &card_dev_to_put);
 		timeri = NULL;
 	}
 
  unlock:
 	mutex_unlock(&register_mutex);
+	/* put_device() is called after unlock for avoiding deadlock */
+	if (card_dev_to_put)
+		put_device(card_dev_to_put);
 	*ti = timeri;
 	return err;
 }
@@ -338,7 +343,8 @@ EXPORT_SYMBOL(snd_timer_open);
  * close a timer instance
  * call this with register_mutex down.
  */
-static int snd_timer_close_locked(struct snd_timer_instance *timeri)
+static int snd_timer_close_locked(struct snd_timer_instance *timeri,
+				  struct device **card_devp_to_put)
 {
 	struct snd_timer *timer = timeri->timer;
 	struct snd_timer_instance *slave, *tmp;
@@ -395,7 +401,7 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri)
 			timer->hw.close(timer);
 		/* release a card refcount for safe disconnection */
 		if (timer->card)
-			put_device(&timer->card->card_dev);
+			*card_devp_to_put = &timer->card->card_dev;
 		module_put(timer->module);
 	}
 
@@ -407,14 +413,18 @@ static int snd_timer_close_locked(struct snd_timer_instance *timeri)
  */
 int snd_timer_close(struct snd_timer_instance *timeri)
 {
+	struct device *card_dev_to_put = NULL;
 	int err;
 
 	if (snd_BUG_ON(!timeri))
 		return -ENXIO;
 
 	mutex_lock(&register_mutex);
-	err = snd_timer_close_locked(timeri);
+	err = snd_timer_close_locked(timeri, &card_dev_to_put);
 	mutex_unlock(&register_mutex);
+	/* put_device() is called after unlock for avoiding deadlock */
+	if (card_dev_to_put)
+		put_device(card_dev_to_put);
 	return err;
 }
 EXPORT_SYMBOL(snd_timer_close);
diff --git a/sound/firewire/bebob/bebob_focusrite.c b/sound/firewire/bebob/bebob_focusrite.c
index 32b864bee25f..06d6a37cd853 100644
--- a/sound/firewire/bebob/bebob_focusrite.c
+++ b/sound/firewire/bebob/bebob_focusrite.c
@@ -27,6 +27,8 @@
 #define SAFFIRE_CLOCK_SOURCE_SPDIF		1
 
 /* clock sources as returned from register of Saffire Pro 10 and 26 */
+#define SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK	0x000000ff
+#define SAFFIREPRO_CLOCK_SOURCE_DETECT_MASK	0x0000ff00
 #define SAFFIREPRO_CLOCK_SOURCE_INTERNAL	0
 #define SAFFIREPRO_CLOCK_SOURCE_SKIP		1 /* never used on hardware */
 #define SAFFIREPRO_CLOCK_SOURCE_SPDIF		2
@@ -189,6 +191,7 @@ saffirepro_both_clk_src_get(struct snd_bebob *bebob, unsigned int *id)
 		map = saffirepro_clk_maps[1];
 
 	/* In a case that this driver cannot handle the value of register. */
+	value &= SAFFIREPRO_CLOCK_SOURCE_SELECT_MASK;
 	if (value >= SAFFIREPRO_CLOCK_SOURCE_COUNT || map[value] < 0) {
 		err = -EIO;
 		goto end;
diff --git a/sound/firewire/bebob/bebob_stream.c b/sound/firewire/bebob/bebob_stream.c
index 73fee991bd75..6c1497d9f52b 100644
--- a/sound/firewire/bebob/bebob_stream.c
+++ b/sound/firewire/bebob/bebob_stream.c
@@ -252,8 +252,7 @@ end:
 	return err;
 }
 
-static unsigned int
-map_data_channels(struct snd_bebob *bebob, struct amdtp_stream *s)
+static int map_data_channels(struct snd_bebob *bebob, struct amdtp_stream *s)
 {
 	unsigned int sec, sections, ch, channels;
 	unsigned int pcm, midi, location;
diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c
index d3999e7b0705..7e7be8e4dcf9 100644
--- a/sound/hda/hdac_controller.c
+++ b/sound/hda/hdac_controller.c
@@ -447,8 +447,6 @@ static void azx_int_disable(struct hdac_bus *bus)
 	list_for_each_entry(azx_dev, &bus->stream_list, list)
 		snd_hdac_stream_updateb(azx_dev, SD_CTL, SD_INT_MASK, 0);
 
-	synchronize_irq(bus->irq);
-
 	/* disable SIE for all streams */
 	snd_hdac_chip_writeb(bus, INTCTL, 0);
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 240f4ca76391..cf53fbd872ee 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1348,9 +1348,9 @@ static int azx_free(struct azx *chip)
 	}
 
 	if (bus->chip_init) {
-		azx_stop_chip(chip);
 		azx_clear_irq_pending(chip);
 		azx_stop_all_streams(chip);
+		azx_stop_chip(chip);
 	}
 
 	if (bus->irq >= 0)
@@ -2399,6 +2399,12 @@ static const struct pci_device_id azx_ids[] = {
 	/* Icelake */
 	{ PCI_DEVICE(0x8086, 0x34c8),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	/* Jasperlake */
+	{ PCI_DEVICE(0x8086, 0x38c8),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
+	/* Tigerlake */
+	{ PCI_DEVICE(0x8086, 0xa0c8),
+	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
 	/* Elkhart Lake */
 	{ PCI_DEVICE(0x8086, 0x4b55),
 	  .driver_data = AZX_DRIVER_SKL | AZX_DCAPS_INTEL_SKYLAKE},
diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 6d1fb7c11f17..b7a1abb3e231 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -7604,7 +7604,7 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 	/* Delay enabling the HP amp, to let the mic-detection
 	 * state machine run.
 	 */
-	cancel_delayed_work_sync(&spec->unsol_hp_work);
+	cancel_delayed_work(&spec->unsol_hp_work);
 	schedule_delayed_work(&spec->unsol_hp_work, msecs_to_jiffies(500));
 	tbl = snd_hda_jack_tbl_get(codec, cb->nid);
 	if (tbl)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 795cbda32cbb..3c720703ebb8 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -145,6 +145,7 @@ struct hdmi_spec {
 	struct snd_array pins; /* struct hdmi_spec_per_pin */
 	struct hdmi_pcm pcm_rec[16];
 	struct mutex pcm_lock;
+	struct mutex bind_lock; /* for audio component binding */
 	/* pcm_bitmap means which pcms have been assigned to pins*/
 	unsigned long pcm_bitmap;
 	int pcm_used;	/* counter of pcm_rec[] */
@@ -2258,7 +2259,7 @@ static int generic_hdmi_init(struct hda_codec *codec)
 	struct hdmi_spec *spec = codec->spec;
 	int pin_idx;
 
-	mutex_lock(&spec->pcm_lock);
+	mutex_lock(&spec->bind_lock);
 	spec->use_jack_detect = !codec->jackpoll_interval;
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
@@ -2275,7 +2276,7 @@ static int generic_hdmi_init(struct hda_codec *codec)
 			snd_hda_jack_detect_enable_callback(codec, pin_nid,
 							    jack_callback);
 	}
-	mutex_unlock(&spec->pcm_lock);
+	mutex_unlock(&spec->bind_lock);
 	return 0;
 }
 
@@ -2382,6 +2383,7 @@ static int alloc_generic_hdmi(struct hda_codec *codec)
 	spec->ops = generic_standard_hdmi_ops;
 	spec->dev_num = 1;	/* initialize to 1 */
 	mutex_init(&spec->pcm_lock);
+	mutex_init(&spec->bind_lock);
 	snd_hdac_register_chmap_ops(&codec->core, &spec->chmap);
 
 	spec->chmap.ops.get_chmap = hdmi_get_chmap;
@@ -2451,7 +2453,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp,
 	int i;
 
 	spec = container_of(acomp->audio_ops, struct hdmi_spec, drm_audio_ops);
-	mutex_lock(&spec->pcm_lock);
+	mutex_lock(&spec->bind_lock);
 	spec->use_acomp_notifier = use_acomp;
 	spec->codec->relaxed_resume = use_acomp;
 	/* reprogram each jack detection logic depending on the notifier */
@@ -2461,7 +2463,7 @@ static void generic_acomp_notifier_set(struct drm_audio_component *acomp,
 					      get_pin(spec, i)->pin_nid,
 					      use_acomp);
 	}
-	mutex_unlock(&spec->pcm_lock);
+	mutex_unlock(&spec->bind_lock);
 }
 
 /* enable / disable the notifier via master bind / unbind */
@@ -2849,6 +2851,18 @@ static int patch_i915_icl_hdmi(struct hda_codec *codec)
 	return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map));
 }
 
+static int patch_i915_tgl_hdmi(struct hda_codec *codec)
+{
+	/*
+	 * pin to port mapping table where the value indicate the pin number and
+	 * the index indicate the port number with 1 base.
+	 */
+	static const int map[] = {0x4, 0x6, 0x8, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf};
+
+	return intel_hsw_common_init(codec, 0x02, map, ARRAY_SIZE(map));
+}
+
+
 /* Intel Baytrail and Braswell; with eld notifier */
 static int patch_i915_byt_hdmi(struct hda_codec *codec)
 {
@@ -4151,6 +4165,7 @@ HDA_CODEC_ENTRY(0x8086280b, "Kabylake HDMI",	patch_i915_hsw_hdmi),
 HDA_CODEC_ENTRY(0x8086280c, "Cannonlake HDMI",	patch_i915_glk_hdmi),
 HDA_CODEC_ENTRY(0x8086280d, "Geminilake HDMI",	patch_i915_glk_hdmi),
 HDA_CODEC_ENTRY(0x8086280f, "Icelake HDMI",	patch_i915_icl_hdmi),
+HDA_CODEC_ENTRY(0x80862812, "Tigerlake HDMI",	patch_i915_tgl_hdmi),
 HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI",	patch_generic_hdmi),
 HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI",	patch_i915_byt_hdmi),
 HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI",	patch_i915_byt_hdmi),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index ce4f11659765..80f66ba85f87 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -393,6 +393,7 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0700:
 	case 0x10ec0701:
 	case 0x10ec0703:
+	case 0x10ec0711:
 		alc_update_coef_idx(codec, 0x10, 1<<15, 0);
 		break;
 	case 0x10ec0662:
@@ -408,6 +409,9 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
 	case 0x10ec0672:
 		alc_update_coef_idx(codec, 0xd, 0, 1<<14); /* EAPD Ctrl */
 		break;
+	case 0x10ec0623:
+		alc_update_coef_idx(codec, 0x19, 1<<13, 0);
+		break;
 	case 0x10ec0668:
 		alc_update_coef_idx(codec, 0x7, 3<<13, 0);
 		break;
@@ -2919,6 +2923,7 @@ enum {
 	ALC269_TYPE_ALC225,
 	ALC269_TYPE_ALC294,
 	ALC269_TYPE_ALC300,
+	ALC269_TYPE_ALC623,
 	ALC269_TYPE_ALC700,
 };
 
@@ -2954,6 +2959,7 @@ static int alc269_parse_auto_config(struct hda_codec *codec)
 	case ALC269_TYPE_ALC225:
 	case ALC269_TYPE_ALC294:
 	case ALC269_TYPE_ALC300:
+	case ALC269_TYPE_ALC623:
 	case ALC269_TYPE_ALC700:
 		ssids = alc269_ssids;
 		break;
@@ -7215,6 +7221,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
 	SND_PCI_QUIRK(0x17aa, 0x3151, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x3176, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
@@ -8016,9 +8024,13 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->codec_variant = ALC269_TYPE_ALC300;
 		spec->gen.mixer_nid = 0; /* no loopback on ALC300 */
 		break;
+	case 0x10ec0623:
+		spec->codec_variant = ALC269_TYPE_ALC623;
+		break;
 	case 0x10ec0700:
 	case 0x10ec0701:
 	case 0x10ec0703:
+	case 0x10ec0711:
 		spec->codec_variant = ALC269_TYPE_ALC700;
 		spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */
 		alc_update_coef_idx(codec, 0x4a, 1 << 15, 0); /* Combo jack auto trigger control */
@@ -9216,6 +9228,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0298, "ALC298", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0299, "ALC299", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0300, "ALC300", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0623, "ALC623", patch_alc269),
 	HDA_CODEC_REV_ENTRY(0x10ec0861, 0x100340, "ALC660", patch_alc861),
 	HDA_CODEC_ENTRY(0x10ec0660, "ALC660-VD", patch_alc861vd),
 	HDA_CODEC_ENTRY(0x10ec0861, "ALC861", patch_alc861),
@@ -9233,6 +9246,7 @@ static const struct hda_device_id snd_hda_id_realtek[] = {
 	HDA_CODEC_ENTRY(0x10ec0700, "ALC700", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0701, "ALC701", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0703, "ALC703", patch_alc269),
+	HDA_CODEC_ENTRY(0x10ec0711, "ALC711", patch_alc269),
 	HDA_CODEC_ENTRY(0x10ec0867, "ALC891", patch_alc662),
 	HDA_CODEC_ENTRY(0x10ec0880, "ALC880", patch_alc880),
 	HDA_CODEC_ENTRY(0x10ec0882, "ALC882", patch_alc882),
diff --git a/sound/soc/codecs/hdac_hda.c b/sound/soc/codecs/hdac_hda.c
index 91242b6f8ea7..4570f662fb48 100644
--- a/sound/soc/codecs/hdac_hda.c
+++ b/sound/soc/codecs/hdac_hda.c
@@ -410,8 +410,8 @@ static void hdac_hda_codec_remove(struct snd_soc_component *component)
 		return;
 	}
 
-	snd_hdac_ext_bus_link_put(hdev->bus, hlink);
 	pm_runtime_disable(&hdev->dev);
+	snd_hdac_ext_bus_link_put(hdev->bus, hlink);
 }
 
 static const struct snd_soc_dapm_route hdac_hda_dapm_routes[] = {
diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index b5fd8f08726e..f8b5b960e597 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -274,7 +274,7 @@ struct hdmi_codec_priv {
 	uint8_t eld[MAX_ELD_BYTES];
 	struct snd_pcm_chmap *chmap_info;
 	unsigned int chmap_idx;
-	struct mutex lock;
+	unsigned long busy;
 	struct snd_soc_jack *jack;
 	unsigned int jack_status;
 };
@@ -390,8 +390,8 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream,
 	struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai);
 	int ret = 0;
 
-	ret = mutex_trylock(&hcp->lock);
-	if (!ret) {
+	ret = test_and_set_bit(0, &hcp->busy);
+	if (ret) {
 		dev_err(dai->dev, "Only one simultaneous stream supported!\n");
 		return -EINVAL;
 	}
@@ -419,7 +419,7 @@ static int hdmi_codec_startup(struct snd_pcm_substream *substream,
 
 err:
 	/* Release the exclusive lock on error */
-	mutex_unlock(&hcp->lock);
+	clear_bit(0, &hcp->busy);
 	return ret;
 }
 
@@ -431,7 +431,7 @@ static void hdmi_codec_shutdown(struct snd_pcm_substream *substream,
 	hcp->chmap_idx = HDMI_CODEC_CHMAP_IDX_UNKNOWN;
 	hcp->hcd.ops->audio_shutdown(dai->dev->parent, hcp->hcd.data);
 
-	mutex_unlock(&hcp->lock);
+	clear_bit(0, &hcp->busy);
 }
 
 static int hdmi_codec_hw_params(struct snd_pcm_substream *substream,
@@ -811,8 +811,6 @@ static int hdmi_codec_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	hcp->hcd = *hcd;
-	mutex_init(&hcp->lock);
-
 	daidrv = devm_kcalloc(dev, dai_count, sizeof(*daidrv), GFP_KERNEL);
 	if (!daidrv)
 		return -ENOMEM;
diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c
index e609abcf3220..cae1def8902d 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -901,16 +901,20 @@ static void max98373_slot_config(struct i2c_client *i2c,
 		max98373->i_slot = value & 0xF;
 	else
 		max98373->i_slot = 1;
-
-	max98373->reset_gpio = of_get_named_gpio(dev->of_node,
+	if (dev->of_node) {
+		max98373->reset_gpio = of_get_named_gpio(dev->of_node,
 						"maxim,reset-gpio", 0);
-	if (!gpio_is_valid(max98373->reset_gpio)) {
-		dev_err(dev, "Looking up %s property in node %s failed %d\n",
-			"maxim,reset-gpio", dev->of_node->full_name,
-			max98373->reset_gpio);
+		if (!gpio_is_valid(max98373->reset_gpio)) {
+			dev_err(dev, "Looking up %s property in node %s failed %d\n",
+				"maxim,reset-gpio", dev->of_node->full_name,
+				max98373->reset_gpio);
+		} else {
+			dev_dbg(dev, "maxim,reset-gpio=%d",
+				max98373->reset_gpio);
+		}
 	} else {
-		dev_dbg(dev, "maxim,reset-gpio=%d",
-			max98373->reset_gpio);
+		/* this makes reset_gpio as invalid */
+		max98373->reset_gpio = -1;
 	}
 
 	if (!device_property_read_u32(dev, "maxim,spkfb-slot-no", &value))
@@ -956,11 +960,11 @@ static int max98373_i2c_probe(struct i2c_client *i2c,
 
 	/* Power on device */
 	if (gpio_is_valid(max98373->reset_gpio)) {
-		ret = gpio_request(max98373->reset_gpio, "MAX98373_RESET");
+		ret = devm_gpio_request(&i2c->dev, max98373->reset_gpio,
+					"MAX98373_RESET");
 		if (ret) {
 			dev_err(&i2c->dev, "%s: Failed to request gpio %d\n",
 				__func__, max98373->reset_gpio);
-			gpio_free(max98373->reset_gpio);
 			return -EINVAL;
 		}
 		gpio_direction_output(max98373->reset_gpio, 0);
diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 667e9f73aba3..e3d311fb510e 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -306,7 +306,7 @@ struct pm8916_wcd_analog_priv {
 };
 
 static const char *const adc2_mux_text[] = { "ZERO", "INP2", "INP3" };
-static const char *const rdac2_mux_text[] = { "ZERO", "RX2", "RX1" };
+static const char *const rdac2_mux_text[] = { "RX1", "RX2" };
 static const char *const hph_text[] = { "ZERO", "Switch", };
 
 static const struct soc_enum hph_enum = SOC_ENUM_SINGLE_VIRT(
@@ -321,7 +321,7 @@ static const struct soc_enum adc2_enum = SOC_ENUM_SINGLE_VIRT(
 
 /* RDAC2 MUX */
 static const struct soc_enum rdac2_mux_enum = SOC_ENUM_SINGLE(
-			CDC_D_CDC_CONN_HPHR_DAC_CTL, 0, 3, rdac2_mux_text);
+			CDC_D_CDC_CONN_HPHR_DAC_CTL, 0, 2, rdac2_mux_text);
 
 static const struct snd_kcontrol_new spkr_switch[] = {
 	SOC_DAPM_SINGLE("Switch", CDC_A_SPKR_DAC_CTL, 7, 1, 0)
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index 9fa5d44fdc79..58b2468fb2a7 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -243,6 +243,10 @@ static const char *const rx_mix1_text[] = {
 	"ZERO", "IIR1", "IIR2", "RX1", "RX2", "RX3"
 };
 
+static const char * const rx_mix2_text[] = {
+	"ZERO", "IIR1", "IIR2"
+};
+
 static const char *const dec_mux_text[] = {
 	"ZERO", "ADC1", "ADC2", "ADC3", "DMIC1", "DMIC2"
 };
@@ -270,6 +274,16 @@ static const struct soc_enum rx3_mix1_inp_enum[] = {
 	SOC_ENUM_SINGLE(LPASS_CDC_CONN_RX3_B2_CTL, 0, 6, rx_mix1_text),
 };
 
+/* RX1 MIX2 */
+static const struct soc_enum rx_mix2_inp1_chain_enum =
+	SOC_ENUM_SINGLE(LPASS_CDC_CONN_RX1_B3_CTL,
+		0, 3, rx_mix2_text);
+
+/* RX2 MIX2 */
+static const struct soc_enum rx2_mix2_inp1_chain_enum =
+	SOC_ENUM_SINGLE(LPASS_CDC_CONN_RX2_B3_CTL,
+		0, 3, rx_mix2_text);
+
 /* DEC */
 static const struct soc_enum dec1_mux_enum = SOC_ENUM_SINGLE(
 				LPASS_CDC_CONN_TX_B1_CTL, 0, 6, dec_mux_text);
@@ -309,6 +323,10 @@ static const struct snd_kcontrol_new rx3_mix1_inp2_mux = SOC_DAPM_ENUM(
 				"RX3 MIX1 INP2 Mux", rx3_mix1_inp_enum[1]);
 static const struct snd_kcontrol_new rx3_mix1_inp3_mux = SOC_DAPM_ENUM(
 				"RX3 MIX1 INP3 Mux", rx3_mix1_inp_enum[2]);
+static const struct snd_kcontrol_new rx1_mix2_inp1_mux = SOC_DAPM_ENUM(
+				"RX1 MIX2 INP1 Mux", rx_mix2_inp1_chain_enum);
+static const struct snd_kcontrol_new rx2_mix2_inp1_mux = SOC_DAPM_ENUM(
+				"RX2 MIX2 INP1 Mux", rx2_mix2_inp1_chain_enum);
 
 /* Digital Gain control -38.4 dB to +38.4 dB in 0.3 dB steps */
 static const DECLARE_TLV_DB_SCALE(digital_gain, -3840, 30, 0);
@@ -740,6 +758,10 @@ static const struct snd_soc_dapm_widget msm8916_wcd_digital_dapm_widgets[] = {
 			 &rx3_mix1_inp2_mux),
 	SND_SOC_DAPM_MUX("RX3 MIX1 INP3", SND_SOC_NOPM, 0, 0,
 			 &rx3_mix1_inp3_mux),
+	SND_SOC_DAPM_MUX("RX1 MIX2 INP1", SND_SOC_NOPM, 0, 0,
+			 &rx1_mix2_inp1_mux),
+	SND_SOC_DAPM_MUX("RX2 MIX2 INP1", SND_SOC_NOPM, 0, 0,
+			 &rx2_mix2_inp1_mux),
 
 	SND_SOC_DAPM_MUX("CIC1 MUX", SND_SOC_NOPM, 0, 0, &cic1_mux),
 	SND_SOC_DAPM_MUX("CIC2 MUX", SND_SOC_NOPM, 0, 0, &cic2_mux),
diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index 762595de956c..c506c9305043 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -1770,6 +1770,9 @@ static int rt5651_detect_headset(struct snd_soc_component *component)
 
 static bool rt5651_support_button_press(struct rt5651_priv *rt5651)
 {
+	if (!rt5651->hp_jack)
+		return false;
+
 	/* Button press support only works with internal jack-detection */
 	return (rt5651->hp_jack->status & SND_JACK_MICROPHONE) &&
 		rt5651->gpiod_hp_det == NULL;
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index 1ef470700ed5..c50b75ce82e0 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -995,6 +995,16 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component,
 {
 	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
 
+	rt5682->hs_jack = hs_jack;
+
+	if (!hs_jack) {
+		regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2,
+				   RT5682_JD1_EN_MASK, RT5682_JD1_DIS);
+		regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL,
+				   RT5682_POW_JDH | RT5682_POW_JDL, 0);
+		return 0;
+	}
+
 	switch (rt5682->pdata.jd_src) {
 	case RT5682_JD1:
 		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_2,
@@ -1032,8 +1042,6 @@ static int rt5682_set_jack_detect(struct snd_soc_component *component,
 		break;
 	}
 
-	rt5682->hs_jack = hs_jack;
-
 	return 0;
 }
 
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index c3d06e8bc54f..d5fb7f5dd551 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -533,13 +533,10 @@ static SOC_ENUM_SINGLE_DECL(dac_osr,
 static SOC_ENUM_SINGLE_DECL(adc_osr,
 			    WM8994_OVERSAMPLING, 1, osr_text);
 
-static const struct snd_kcontrol_new wm8994_snd_controls[] = {
+static const struct snd_kcontrol_new wm8994_common_snd_controls[] = {
 SOC_DOUBLE_R_TLV("AIF1ADC1 Volume", WM8994_AIF1_ADC1_LEFT_VOLUME,
 		 WM8994_AIF1_ADC1_RIGHT_VOLUME,
 		 1, 119, 0, digital_tlv),
-SOC_DOUBLE_R_TLV("AIF1ADC2 Volume", WM8994_AIF1_ADC2_LEFT_VOLUME,
-		 WM8994_AIF1_ADC2_RIGHT_VOLUME,
-		 1, 119, 0, digital_tlv),
 SOC_DOUBLE_R_TLV("AIF2ADC Volume", WM8994_AIF2_ADC_LEFT_VOLUME,
 		 WM8994_AIF2_ADC_RIGHT_VOLUME,
 		 1, 119, 0, digital_tlv),
@@ -556,8 +553,6 @@ SOC_ENUM("AIF2DACR Source", aif2dacr_src),
 
 SOC_DOUBLE_R_TLV("AIF1DAC1 Volume", WM8994_AIF1_DAC1_LEFT_VOLUME,
 		 WM8994_AIF1_DAC1_RIGHT_VOLUME, 1, 96, 0, digital_tlv),
-SOC_DOUBLE_R_TLV("AIF1DAC2 Volume", WM8994_AIF1_DAC2_LEFT_VOLUME,
-		 WM8994_AIF1_DAC2_RIGHT_VOLUME, 1, 96, 0, digital_tlv),
 SOC_DOUBLE_R_TLV("AIF2DAC Volume", WM8994_AIF2_DAC_LEFT_VOLUME,
 		 WM8994_AIF2_DAC_RIGHT_VOLUME, 1, 96, 0, digital_tlv),
 
@@ -565,17 +560,12 @@ SOC_SINGLE_TLV("AIF1 Boost Volume", WM8994_AIF1_CONTROL_2, 10, 3, 0, aif_tlv),
 SOC_SINGLE_TLV("AIF2 Boost Volume", WM8994_AIF2_CONTROL_2, 10, 3, 0, aif_tlv),
 
 SOC_SINGLE("AIF1DAC1 EQ Switch", WM8994_AIF1_DAC1_EQ_GAINS_1, 0, 1, 0),
-SOC_SINGLE("AIF1DAC2 EQ Switch", WM8994_AIF1_DAC2_EQ_GAINS_1, 0, 1, 0),
 SOC_SINGLE("AIF2 EQ Switch", WM8994_AIF2_EQ_GAINS_1, 0, 1, 0),
 
 WM8994_DRC_SWITCH("AIF1DAC1 DRC Switch", WM8994_AIF1_DRC1_1, 2),
 WM8994_DRC_SWITCH("AIF1ADC1L DRC Switch", WM8994_AIF1_DRC1_1, 1),
 WM8994_DRC_SWITCH("AIF1ADC1R DRC Switch", WM8994_AIF1_DRC1_1, 0),
 
-WM8994_DRC_SWITCH("AIF1DAC2 DRC Switch", WM8994_AIF1_DRC2_1, 2),
-WM8994_DRC_SWITCH("AIF1ADC2L DRC Switch", WM8994_AIF1_DRC2_1, 1),
-WM8994_DRC_SWITCH("AIF1ADC2R DRC Switch", WM8994_AIF1_DRC2_1, 0),
-
 WM8994_DRC_SWITCH("AIF2DAC DRC Switch", WM8994_AIF2_DRC_1, 2),
 WM8994_DRC_SWITCH("AIF2ADCL DRC Switch", WM8994_AIF2_DRC_1, 1),
 WM8994_DRC_SWITCH("AIF2ADCR DRC Switch", WM8994_AIF2_DRC_1, 0),
@@ -594,9 +584,6 @@ SOC_SINGLE("Sidetone HPF Switch", WM8994_SIDETONE, 6, 1, 0),
 SOC_ENUM("AIF1ADC1 HPF Mode", aif1adc1_hpf),
 SOC_DOUBLE("AIF1ADC1 HPF Switch", WM8994_AIF1_ADC1_FILTERS, 12, 11, 1, 0),
 
-SOC_ENUM("AIF1ADC2 HPF Mode", aif1adc2_hpf),
-SOC_DOUBLE("AIF1ADC2 HPF Switch", WM8994_AIF1_ADC2_FILTERS, 12, 11, 1, 0),
-
 SOC_ENUM("AIF2ADC HPF Mode", aif2adc_hpf),
 SOC_DOUBLE("AIF2ADC HPF Switch", WM8994_AIF2_ADC_FILTERS, 12, 11, 1, 0),
 
@@ -637,6 +624,24 @@ SOC_SINGLE("AIF2DAC 3D Stereo Switch", WM8994_AIF2_DAC_FILTERS_2,
 	   8, 1, 0),
 };
 
+/* Controls not available on WM1811 */
+static const struct snd_kcontrol_new wm8994_snd_controls[] = {
+SOC_DOUBLE_R_TLV("AIF1ADC2 Volume", WM8994_AIF1_ADC2_LEFT_VOLUME,
+		 WM8994_AIF1_ADC2_RIGHT_VOLUME,
+		 1, 119, 0, digital_tlv),
+SOC_DOUBLE_R_TLV("AIF1DAC2 Volume", WM8994_AIF1_DAC2_LEFT_VOLUME,
+		 WM8994_AIF1_DAC2_RIGHT_VOLUME, 1, 96, 0, digital_tlv),
+
+SOC_SINGLE("AIF1DAC2 EQ Switch", WM8994_AIF1_DAC2_EQ_GAINS_1, 0, 1, 0),
+
+WM8994_DRC_SWITCH("AIF1DAC2 DRC Switch", WM8994_AIF1_DRC2_1, 2),
+WM8994_DRC_SWITCH("AIF1ADC2L DRC Switch", WM8994_AIF1_DRC2_1, 1),
+WM8994_DRC_SWITCH("AIF1ADC2R DRC Switch", WM8994_AIF1_DRC2_1, 0),
+
+SOC_ENUM("AIF1ADC2 HPF Mode", aif1adc2_hpf),
+SOC_DOUBLE("AIF1ADC2 HPF Switch", WM8994_AIF1_ADC2_FILTERS, 12, 11, 1, 0),
+};
+
 static const struct snd_kcontrol_new wm8994_eq_controls[] = {
 SOC_SINGLE_TLV("AIF1DAC1 EQ1 Volume", WM8994_AIF1_DAC1_EQ_GAINS_1, 11, 31, 0,
 	       eq_tlv),
@@ -4258,13 +4263,15 @@ static int wm8994_component_probe(struct snd_soc_component *component)
 	wm8994_handle_pdata(wm8994);
 
 	wm_hubs_add_analogue_controls(component);
-	snd_soc_add_component_controls(component, wm8994_snd_controls,
-			     ARRAY_SIZE(wm8994_snd_controls));
+	snd_soc_add_component_controls(component, wm8994_common_snd_controls,
+				       ARRAY_SIZE(wm8994_common_snd_controls));
 	snd_soc_dapm_new_controls(dapm, wm8994_dapm_widgets,
 				  ARRAY_SIZE(wm8994_dapm_widgets));
 
 	switch (control->type) {
 	case WM8994:
+		snd_soc_add_component_controls(component, wm8994_snd_controls,
+					       ARRAY_SIZE(wm8994_snd_controls));
 		snd_soc_dapm_new_controls(dapm, wm8994_specific_dapm_widgets,
 					  ARRAY_SIZE(wm8994_specific_dapm_widgets));
 		if (control->revision < 4) {
@@ -4284,8 +4291,10 @@ static int wm8994_component_probe(struct snd_soc_component *component)
 		}
 		break;
 	case WM8958:
+		snd_soc_add_component_controls(component, wm8994_snd_controls,
+					       ARRAY_SIZE(wm8994_snd_controls));
 		snd_soc_add_component_controls(component, wm8958_snd_controls,
-				     ARRAY_SIZE(wm8958_snd_controls));
+					       ARRAY_SIZE(wm8958_snd_controls));
 		snd_soc_dapm_new_controls(dapm, wm8958_dapm_widgets,
 					  ARRAY_SIZE(wm8958_dapm_widgets));
 		if (control->revision < 1) {
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index ae28d9907c30..9b8bb7bbe945 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1259,8 +1259,7 @@ static unsigned int wmfw_convert_flags(unsigned int in, unsigned int len)
 	}
 
 	if (in) {
-		if (in & WMFW_CTL_FLAG_READABLE)
-			out |= rd;
+		out |= rd;
 		if (in & WMFW_CTL_FLAG_WRITEABLE)
 			out |= wr;
 		if (in & WMFW_CTL_FLAG_VOLATILE)
@@ -3697,11 +3696,16 @@ static int wm_adsp_buffer_parse_legacy(struct wm_adsp *dsp)
 	u32 xmalg, addr, magic;
 	int i, ret;
 
+	alg_region = wm_adsp_find_alg_region(dsp, WMFW_ADSP2_XM, dsp->fw_id);
+	if (!alg_region) {
+		adsp_err(dsp, "No algorithm region found\n");
+		return -EINVAL;
+	}
+
 	buf = wm_adsp_buffer_alloc(dsp);
 	if (!buf)
 		return -ENOMEM;
 
-	alg_region = wm_adsp_find_alg_region(dsp, WMFW_ADSP2_XM, dsp->fw_id);
 	xmalg = dsp->ops->sys_config_size / sizeof(__be32);
 
 	addr = alg_region->base + xmalg + ALG_XM_FIELD(magic);
diff --git a/sound/soc/intel/boards/sof_rt5682.c b/sound/soc/intel/boards/sof_rt5682.c
index a437567b8cee..4f6e58c3954a 100644
--- a/sound/soc/intel/boards/sof_rt5682.c
+++ b/sound/soc/intel/boards/sof_rt5682.c
@@ -308,6 +308,9 @@ static const struct snd_soc_dapm_widget sof_widgets[] = {
 	SND_SOC_DAPM_HP("Headphone Jack", NULL),
 	SND_SOC_DAPM_MIC("Headset Mic", NULL),
 	SND_SOC_DAPM_SPK("Spk", NULL),
+};
+
+static const struct snd_soc_dapm_widget dmic_widgets[] = {
 	SND_SOC_DAPM_MIC("SoC DMIC", NULL),
 };
 
@@ -318,10 +321,6 @@ static const struct snd_soc_dapm_route sof_map[] = {
 
 	/* other jacks */
 	{ "IN1P", NULL, "Headset Mic" },
-
-	/* digital mics */
-	{"DMic", NULL, "SoC DMIC"},
-
 };
 
 static const struct snd_soc_dapm_route speaker_map[] = {
@@ -329,6 +328,11 @@ static const struct snd_soc_dapm_route speaker_map[] = {
 	{ "Spk", NULL, "Speaker" },
 };
 
+static const struct snd_soc_dapm_route dmic_map[] = {
+	/* digital mics */
+	{"DMic", NULL, "SoC DMIC"},
+};
+
 static int speaker_codec_init(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_card *card = rtd->card;
@@ -342,6 +346,28 @@ static int speaker_codec_init(struct snd_soc_pcm_runtime *rtd)
 	return ret;
 }
 
+static int dmic_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_soc_card *card = rtd->card;
+	int ret;
+
+	ret = snd_soc_dapm_new_controls(&card->dapm, dmic_widgets,
+					ARRAY_SIZE(dmic_widgets));
+	if (ret) {
+		dev_err(card->dev, "DMic widget addition failed: %d\n", ret);
+		/* Don't need to add routes if widget addition failed */
+		return ret;
+	}
+
+	ret = snd_soc_dapm_add_routes(&card->dapm, dmic_map,
+				      ARRAY_SIZE(dmic_map));
+
+	if (ret)
+		dev_err(card->dev, "DMic map addition failed: %d\n", ret);
+
+	return ret;
+}
+
 /* sof audio machine driver for rt5682 codec */
 static struct snd_soc_card sof_audio_card_rt5682 = {
 	.name = "sof_rt5682",
@@ -445,6 +471,7 @@ static struct snd_soc_dai_link *sof_card_dai_links_create(struct device *dev,
 		links[id].name = "dmic01";
 		links[id].cpus = &cpus[id];
 		links[id].cpus->dai_name = "DMIC01 Pin";
+		links[id].init = dmic_init;
 		if (dmic_be_num > 1) {
 			/* set up 2 BE links at most */
 			links[id + 1].name = "dmic16k";
@@ -576,6 +603,15 @@ static int sof_audio_probe(struct platform_device *pdev)
 	/* need to get main clock from pmc */
 	if (sof_rt5682_quirk & SOF_RT5682_MCLK_BYTCHT_EN) {
 		ctx->mclk = devm_clk_get(&pdev->dev, "pmc_plt_clk_3");
+		if (IS_ERR(ctx->mclk)) {
+			ret = PTR_ERR(ctx->mclk);
+
+			dev_err(&pdev->dev,
+				"Failed to get MCLK from pmc_plt_clk_3: %d\n",
+				ret);
+			return ret;
+		}
+
 		ret = clk_prepare_enable(ctx->mclk);
 		if (ret < 0) {
 			dev_err(&pdev->dev,
@@ -621,8 +657,24 @@ static int sof_audio_probe(struct platform_device *pdev)
 					  &sof_audio_card_rt5682);
 }
 
+static int sof_rt5682_remove(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+	struct snd_soc_component *component = NULL;
+
+	for_each_card_components(card, component) {
+		if (!strcmp(component->name, rt5682_component[0].name)) {
+			snd_soc_component_set_jack(component, NULL, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct platform_driver sof_audio = {
 	.probe = sof_audio_probe,
+	.remove = sof_rt5682_remove,
 	.driver = {
 		.name = "sof_rt5682",
 		.pm = &snd_soc_pm_ops,
diff --git a/sound/soc/kirkwood/kirkwood-i2s.c b/sound/soc/kirkwood/kirkwood-i2s.c
index 61226fefe1c4..2a4ffe945177 100644
--- a/sound/soc/kirkwood/kirkwood-i2s.c
+++ b/sound/soc/kirkwood/kirkwood-i2s.c
@@ -555,10 +555,6 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev)
 		return PTR_ERR(priv->clk);
 	}
 
-	err = clk_prepare_enable(priv->clk);
-	if (err < 0)
-		return err;
-
 	priv->extclk = devm_clk_get(&pdev->dev, "extclk");
 	if (IS_ERR(priv->extclk)) {
 		if (PTR_ERR(priv->extclk) == -EPROBE_DEFER)
@@ -574,6 +570,10 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev)
 		}
 	}
 
+	err = clk_prepare_enable(priv->clk);
+	if (err < 0)
+		return err;
+
 	/* Some sensible defaults - this reflects the powerup values */
 	priv->ctl_play = KIRKWOOD_PLAYCTL_SIZE_24;
 	priv->ctl_rec = KIRKWOOD_RECCTL_SIZE_24;
@@ -587,7 +587,7 @@ static int kirkwood_i2s_dev_probe(struct platform_device *pdev)
 		priv->ctl_rec |= KIRKWOOD_RECCTL_BURST_128;
 	}
 
-	err = devm_snd_soc_register_component(&pdev->dev, &kirkwood_soc_component,
+	err = snd_soc_register_component(&pdev->dev, &kirkwood_soc_component,
 					 soc_dai, 2);
 	if (err) {
 		dev_err(&pdev->dev, "snd_soc_register_component failed\n");
@@ -610,6 +610,7 @@ static int kirkwood_i2s_dev_remove(struct platform_device *pdev)
 {
 	struct kirkwood_dma_data *priv = dev_get_drvdata(&pdev->dev);
 
+	snd_soc_unregister_component(&pdev->dev);
 	if (!IS_ERR(priv->extclk))
 		clk_disable_unprepare(priv->extclk);
 	clk_disable_unprepare(priv->clk);
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index af2d5a6124c8..61c984f10d8e 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -677,7 +677,7 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 	ret = rockchip_pcm_platform_register(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not register PCM\n");
-		return ret;
+		goto err_suspend;
 	}
 
 	return 0;
diff --git a/sound/soc/rockchip/rockchip_max98090.c b/sound/soc/rockchip/rockchip_max98090.c
index 0097df1fae66..e80b09143b63 100644
--- a/sound/soc/rockchip/rockchip_max98090.c
+++ b/sound/soc/rockchip/rockchip_max98090.c
@@ -66,10 +66,13 @@ static int rk_jack_event(struct notifier_block *nb, unsigned long event,
 	struct snd_soc_jack *jack = (struct snd_soc_jack *)data;
 	struct snd_soc_dapm_context *dapm = &jack->card->dapm;
 
-	if (event & SND_JACK_MICROPHONE)
+	if (event & SND_JACK_MICROPHONE) {
 		snd_soc_dapm_force_enable_pin(dapm, "MICBIAS");
-	else
+		snd_soc_dapm_force_enable_pin(dapm, "SHDN");
+	} else {
 		snd_soc_dapm_disable_pin(dapm, "MICBIAS");
+		snd_soc_dapm_disable_pin(dapm, "SHDN");
+	}
 
 	snd_soc_dapm_sync(dapm);
 
diff --git a/sound/soc/samsung/arndale_rt5631.c b/sound/soc/samsung/arndale_rt5631.c
index c213913eb984..fd8c6642fb0d 100644
--- a/sound/soc/samsung/arndale_rt5631.c
+++ b/sound/soc/samsung/arndale_rt5631.c
@@ -5,6 +5,7 @@
 //  Author: Claude <claude@insginal.co.kr>
 
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 
@@ -74,6 +75,17 @@ static struct snd_soc_card arndale_rt5631 = {
 	.num_links = ARRAY_SIZE(arndale_rt5631_dai),
 };
 
+static void arndale_put_of_nodes(struct snd_soc_card *card)
+{
+	struct snd_soc_dai_link *dai_link;
+	int i;
+
+	for_each_card_prelinks(card, i, dai_link) {
+		of_node_put(dai_link->cpus->of_node);
+		of_node_put(dai_link->codecs->of_node);
+	}
+}
+
 static int arndale_audio_probe(struct platform_device *pdev)
 {
 	int n, ret;
@@ -103,18 +115,31 @@ static int arndale_audio_probe(struct platform_device *pdev)
 		if (!arndale_rt5631_dai[0].codecs->of_node) {
 			dev_err(&pdev->dev,
 			"Property 'samsung,audio-codec' missing or invalid\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_put_of_nodes;
 		}
 	}
 
 	ret = devm_snd_soc_register_card(card->dev, card);
+	if (ret) {
+		dev_err(&pdev->dev, "snd_soc_register_card() failed: %d\n", ret);
+		goto err_put_of_nodes;
+	}
+	return 0;
 
-	if (ret)
-		dev_err(&pdev->dev, "snd_soc_register_card() failed:%d\n", ret);
-
+err_put_of_nodes:
+	arndale_put_of_nodes(card);
 	return ret;
 }
 
+static int arndale_audio_remove(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = platform_get_drvdata(pdev);
+
+	arndale_put_of_nodes(card);
+	return 0;
+}
+
 static const struct of_device_id samsung_arndale_rt5631_of_match[] __maybe_unused = {
 	{ .compatible = "samsung,arndale-rt5631", },
 	{ .compatible = "samsung,arndale-alc5631", },
@@ -129,6 +154,7 @@ static struct platform_driver arndale_audio_driver = {
 		.of_match_table = of_match_ptr(samsung_arndale_rt5631_of_match),
 	},
 	.probe = arndale_audio_probe,
+	.remove = arndale_audio_remove,
 };
 
 module_platform_driver(arndale_audio_driver);
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index bda5b958d0dc..e9596c2096cd 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -761,6 +761,7 @@ static int rsnd_soc_dai_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	}
 
 	/* set format */
+	rdai->bit_clk_inv = 0;
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		rdai->sys_delay = 0;
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index 0324a5c39619..28f65eba2bb4 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -508,10 +508,10 @@ static struct rsnd_mod_ops rsnd_dmapp_ops = {
 #define RDMA_SSI_I_N(addr, i)	(addr ##_reg - 0x00300000 + (0x40 * i) + 0x8)
 #define RDMA_SSI_O_N(addr, i)	(addr ##_reg - 0x00300000 + (0x40 * i) + 0xc)
 
-#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400))
+#define RDMA_SSIU_I_N(addr, i, j) (addr ##_reg - 0x00441000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4)))
 #define RDMA_SSIU_O_N(addr, i, j) RDMA_SSIU_I_N(addr, i, j)
 
-#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400))
+#define RDMA_SSIU_I_P(addr, i, j) (addr ##_reg - 0x00141000 + (0x1000 * (i)) + (((j) / 4) * 0xA000) + (((j) % 4) * 0x400) - (0x4000 * ((i) / 9) * ((j) / 4)))
 #define RDMA_SSIU_O_P(addr, i, j) RDMA_SSIU_I_P(addr, i, j)
 
 #define RDMA_SRC_I_N(addr, i)	(addr ##_reg - 0x00500000 + (0x400 * i))
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index e163dde5eab1..b600d3eaaf5c 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1070,7 +1070,7 @@ static int soc_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 			return ret;
 	}
 
-	snd_soc_dai_trigger(cpu_dai, substream, cmd);
+	ret = snd_soc_dai_trigger(cpu_dai, substream, cmd);
 	if (ret < 0)
 		return ret;
 
@@ -1097,7 +1097,7 @@ static int soc_pcm_bespoke_trigger(struct snd_pcm_substream *substream,
 			return ret;
 	}
 
-	snd_soc_dai_bespoke_trigger(cpu_dai, substream, cmd);
+	ret = snd_soc_dai_bespoke_trigger(cpu_dai, substream, cmd);
 	if (ret < 0)
 		return ret;
 
@@ -1146,6 +1146,7 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
 {
 	struct snd_soc_dpcm *dpcm;
 	unsigned long flags;
+	char *name;
 
 	/* only add new dpcms */
 	for_each_dpcm_be(fe, stream, dpcm) {
@@ -1171,9 +1172,15 @@ static int dpcm_be_connect(struct snd_soc_pcm_runtime *fe,
 			stream ? "<-" : "->", be->dai_link->name);
 
 #ifdef CONFIG_DEBUG_FS
-	dpcm->debugfs_state = debugfs_create_dir(be->dai_link->name,
-						 fe->debugfs_dpcm_root);
-	debugfs_create_u32("state", 0644, dpcm->debugfs_state, &dpcm->state);
+	name = kasprintf(GFP_KERNEL, "%s:%s", be->dai_link->name,
+			 stream ? "capture" : "playback");
+	if (name) {
+		dpcm->debugfs_state = debugfs_create_dir(name,
+							 fe->debugfs_dpcm_root);
+		debugfs_create_u32("state", 0644, dpcm->debugfs_state,
+				   &dpcm->state);
+		kfree(name);
+	}
 #endif
 	return 1;
 }
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index aa9a1fca46fa..0fd032914a31 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1582,7 +1582,7 @@ static int soc_tplg_dapm_widget_create(struct soc_tplg *tplg,
 
 	/* map user to kernel widget ID */
 	template.id = get_widget_id(le32_to_cpu(w->id));
-	if (template.id < 0)
+	if ((int)template.id < 0)
 		return template.id;
 
 	/* strings are allocated here, but used and freed by the widget */
diff --git a/sound/soc/sof/control.c b/sound/soc/sof/control.c
index a4983f90ff5b..2b8711eda362 100644
--- a/sound/soc/sof/control.c
+++ b/sound/soc/sof/control.c
@@ -60,13 +60,16 @@ int snd_sof_volume_put(struct snd_kcontrol *kcontrol,
 	struct snd_sof_dev *sdev = scontrol->sdev;
 	struct sof_ipc_ctrl_data *cdata = scontrol->control_data;
 	unsigned int i, channels = scontrol->num_channels;
+	bool change = false;
+	u32 value;
 
 	/* update each channel */
 	for (i = 0; i < channels; i++) {
-		cdata->chanv[i].value =
-			mixer_to_ipc(ucontrol->value.integer.value[i],
+		value = mixer_to_ipc(ucontrol->value.integer.value[i],
 				     scontrol->volume_table, sm->max + 1);
+		change = change || (value != cdata->chanv[i].value);
 		cdata->chanv[i].channel = i;
+		cdata->chanv[i].value = value;
 	}
 
 	/* notify DSP of mixer updates */
@@ -76,8 +79,7 @@ int snd_sof_volume_put(struct snd_kcontrol *kcontrol,
 					      SOF_CTRL_TYPE_VALUE_CHAN_GET,
 					      SOF_CTRL_CMD_VOLUME,
 					      true);
-
-	return 0;
+	return change;
 }
 
 int snd_sof_switch_get(struct snd_kcontrol *kcontrol,
@@ -105,11 +107,15 @@ int snd_sof_switch_put(struct snd_kcontrol *kcontrol,
 	struct snd_sof_dev *sdev = scontrol->sdev;
 	struct sof_ipc_ctrl_data *cdata = scontrol->control_data;
 	unsigned int i, channels = scontrol->num_channels;
+	bool change = false;
+	u32 value;
 
 	/* update each channel */
 	for (i = 0; i < channels; i++) {
-		cdata->chanv[i].value = ucontrol->value.integer.value[i];
+		value = ucontrol->value.integer.value[i];
+		change = change || (value != cdata->chanv[i].value);
 		cdata->chanv[i].channel = i;
+		cdata->chanv[i].value = value;
 	}
 
 	/* notify DSP of mixer updates */
@@ -120,7 +126,7 @@ int snd_sof_switch_put(struct snd_kcontrol *kcontrol,
 					      SOF_CTRL_CMD_SWITCH,
 					      true);
 
-	return 0;
+	return change;
 }
 
 int snd_sof_enum_get(struct snd_kcontrol *kcontrol,
@@ -148,11 +154,15 @@ int snd_sof_enum_put(struct snd_kcontrol *kcontrol,
 	struct snd_sof_dev *sdev = scontrol->sdev;
 	struct sof_ipc_ctrl_data *cdata = scontrol->control_data;
 	unsigned int i, channels = scontrol->num_channels;
+	bool change = false;
+	u32 value;
 
 	/* update each channel */
 	for (i = 0; i < channels; i++) {
-		cdata->chanv[i].value = ucontrol->value.enumerated.item[i];
+		value = ucontrol->value.enumerated.item[i];
+		change = change || (value != cdata->chanv[i].value);
 		cdata->chanv[i].channel = i;
+		cdata->chanv[i].value = value;
 	}
 
 	/* notify DSP of enum updates */
@@ -163,7 +173,7 @@ int snd_sof_enum_put(struct snd_kcontrol *kcontrol,
 					      SOF_CTRL_CMD_ENUM,
 					      true);
 
-	return 0;
+	return change;
 }
 
 int snd_sof_bytes_get(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/sof/debug.c b/sound/soc/sof/debug.c
index 54cd431faab7..5529e8eeca46 100644
--- a/sound/soc/sof/debug.c
+++ b/sound/soc/sof/debug.c
@@ -152,8 +152,10 @@ static ssize_t sof_dfsentry_write(struct file *file, const char __user *buffer,
 	 */
 	dentry = file->f_path.dentry;
 	if (strcmp(dentry->d_name.name, "ipc_flood_count") &&
-	    strcmp(dentry->d_name.name, "ipc_flood_duration_ms"))
-		return -EINVAL;
+	    strcmp(dentry->d_name.name, "ipc_flood_duration_ms")) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	if (!strcmp(dentry->d_name.name, "ipc_flood_duration_ms"))
 		flood_duration_test = true;
diff --git a/sound/soc/sof/intel/Kconfig b/sound/soc/sof/intel/Kconfig
index 479ba249e219..d62f51d33be1 100644
--- a/sound/soc/sof/intel/Kconfig
+++ b/sound/soc/sof/intel/Kconfig
@@ -273,6 +273,16 @@ config SND_SOC_SOF_HDA_AUDIO_CODEC
 	  Say Y if you want to enable HDAudio codecs with SOF.
 	  If unsure select "N".
 
+config SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1
+	bool "SOF enable DMI Link L1"
+	help
+	  This option enables DMI L1 for both playback and capture
+	  and disables known workarounds for specific HDaudio platforms.
+	  Only use to look into power optimizations on platforms not
+	  affected by DMI L1 issues. This option is not recommended.
+	  Say Y if you want to enable DMI Link L1
+	  If unsure, select "N".
+
 endif ## SND_SOC_SOF_HDA_COMMON
 
 config SND_SOC_SOF_HDA_LINK_BASELINE
diff --git a/sound/soc/sof/intel/bdw.c b/sound/soc/sof/intel/bdw.c
index e282179263e8..80e2826fb447 100644
--- a/sound/soc/sof/intel/bdw.c
+++ b/sound/soc/sof/intel/bdw.c
@@ -37,6 +37,7 @@
 #define MBOX_SIZE       0x1000
 #define MBOX_DUMP_SIZE 0x30
 #define EXCEPT_OFFSET	0x800
+#define EXCEPT_MAX_HDR_SIZE	0x400
 
 /* DSP peripherals */
 #define DMAC0_OFFSET    0xFE000
@@ -228,6 +229,11 @@ static void bdw_get_registers(struct snd_sof_dev *sdev,
 	/* note: variable AR register array is not read */
 
 	/* then get panic info */
+	if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) {
+		dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n",
+			xoops->arch_hdr.totalsize);
+		return;
+	}
 	offset += xoops->arch_hdr.totalsize;
 	sof_mailbox_read(sdev, offset, panic_info, sizeof(*panic_info));
 
@@ -451,6 +457,7 @@ static int bdw_probe(struct snd_sof_dev *sdev)
 	/* TODO: add offsets */
 	sdev->mmio_bar = BDW_DSP_BAR;
 	sdev->mailbox_bar = BDW_DSP_BAR;
+	sdev->dsp_oops_offset = MBOX_OFFSET;
 
 	/* PCI base */
 	mmio = platform_get_resource(pdev, IORESOURCE_MEM,
diff --git a/sound/soc/sof/intel/byt.c b/sound/soc/sof/intel/byt.c
index 5e7a6aaa627a..a1e514f71739 100644
--- a/sound/soc/sof/intel/byt.c
+++ b/sound/soc/sof/intel/byt.c
@@ -28,6 +28,7 @@
 #define MBOX_OFFSET		0x144000
 #define MBOX_SIZE		0x1000
 #define EXCEPT_OFFSET		0x800
+#define EXCEPT_MAX_HDR_SIZE	0x400
 
 /* DSP peripherals */
 #define DMAC0_OFFSET		0x098000
@@ -126,6 +127,11 @@ static void byt_get_registers(struct snd_sof_dev *sdev,
 	/* note: variable AR register array is not read */
 
 	/* then get panic info */
+	if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) {
+		dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n",
+			xoops->arch_hdr.totalsize);
+		return;
+	}
 	offset += xoops->arch_hdr.totalsize;
 	sof_mailbox_read(sdev, offset, panic_info, sizeof(*panic_info));
 
diff --git a/sound/soc/sof/intel/hda-ctrl.c b/sound/soc/sof/intel/hda-ctrl.c
index bc41028a7a01..df1909e1d950 100644
--- a/sound/soc/sof/intel/hda-ctrl.c
+++ b/sound/soc/sof/intel/hda-ctrl.c
@@ -139,20 +139,16 @@ void hda_dsp_ctrl_misc_clock_gating(struct snd_sof_dev *sdev, bool enable)
  */
 int hda_dsp_ctrl_clock_power_gating(struct snd_sof_dev *sdev, bool enable)
 {
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
-	struct hdac_bus *bus = sof_to_bus(sdev);
-#endif
 	u32 val;
 
 	/* enable/disable audio dsp clock gating */
 	val = enable ? PCI_CGCTL_ADSPDCGE : 0;
 	snd_sof_pci_update_bits(sdev, PCI_CGCTL, PCI_CGCTL_ADSPDCGE, val);
 
-#if IS_ENABLED(CONFIG_SND_SOC_SOF_HDA)
-	/* enable/disable L1 support */
-	val = enable ? SOF_HDA_VS_EM2_L1SEN : 0;
-	snd_hdac_chip_updatel(bus, VS_EM2, SOF_HDA_VS_EM2_L1SEN, val);
-#endif
+	/* enable/disable DMI Link L1 support */
+	val = enable ? HDA_VS_INTEL_EM2_L1SEN : 0;
+	snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR, HDA_VS_INTEL_EM2,
+				HDA_VS_INTEL_EM2_L1SEN, val);
 
 	/* enable/disable audio dsp power gating */
 	val = enable ? 0 : PCI_PGCTL_ADSPPGD;
diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
index 6427f0b3a2f1..65c2af3fcaab 100644
--- a/sound/soc/sof/intel/hda-loader.c
+++ b/sound/soc/sof/intel/hda-loader.c
@@ -44,6 +44,7 @@ static int cl_stream_prepare(struct snd_sof_dev *sdev, unsigned int format,
 		return -ENODEV;
 	}
 	hstream = &dsp_stream->hstream;
+	hstream->substream = NULL;
 
 	/* allocate DMA buffer */
 	ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV_SG, &pci->dev, size, dmab);
diff --git a/sound/soc/sof/intel/hda-stream.c b/sound/soc/sof/intel/hda-stream.c
index ad8d41f22e92..0c11fceb28a7 100644
--- a/sound/soc/sof/intel/hda-stream.c
+++ b/sound/soc/sof/intel/hda-stream.c
@@ -185,6 +185,17 @@ hda_dsp_stream_get(struct snd_sof_dev *sdev, int direction)
 			direction == SNDRV_PCM_STREAM_PLAYBACK ?
 			"playback" : "capture");
 
+	/*
+	 * Disable DMI Link L1 entry when capture stream is opened.
+	 * Workaround to address a known issue with host DMA that results
+	 * in xruns during pause/release in capture scenarios.
+	 */
+	if (!IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1))
+		if (stream && direction == SNDRV_PCM_STREAM_CAPTURE)
+			snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
+						HDA_VS_INTEL_EM2,
+						HDA_VS_INTEL_EM2_L1SEN, 0);
+
 	return stream;
 }
 
@@ -193,23 +204,43 @@ int hda_dsp_stream_put(struct snd_sof_dev *sdev, int direction, int stream_tag)
 {
 	struct hdac_bus *bus = sof_to_bus(sdev);
 	struct hdac_stream *s;
+	bool active_capture_stream = false;
+	bool found = false;
 
 	spin_lock_irq(&bus->reg_lock);
 
-	/* find used stream */
+	/*
+	 * close stream matching the stream tag
+	 * and check if there are any open capture streams.
+	 */
 	list_for_each_entry(s, &bus->stream_list, list) {
-		if (s->direction == direction &&
-		    s->opened && s->stream_tag == stream_tag) {
+		if (!s->opened)
+			continue;
+
+		if (s->direction == direction && s->stream_tag == stream_tag) {
 			s->opened = false;
-			spin_unlock_irq(&bus->reg_lock);
-			return 0;
+			found = true;
+		} else if (s->direction == SNDRV_PCM_STREAM_CAPTURE) {
+			active_capture_stream = true;
 		}
 	}
 
 	spin_unlock_irq(&bus->reg_lock);
 
-	dev_dbg(sdev->dev, "stream_tag %d not opened!\n", stream_tag);
-	return -ENODEV;
+	/* Enable DMI L1 entry if there are no capture streams open */
+	if (!IS_ENABLED(CONFIG_SND_SOC_SOF_HDA_ALWAYS_ENABLE_DMI_L1))
+		if (!active_capture_stream)
+			snd_sof_dsp_update_bits(sdev, HDA_DSP_HDA_BAR,
+						HDA_VS_INTEL_EM2,
+						HDA_VS_INTEL_EM2_L1SEN,
+						HDA_VS_INTEL_EM2_L1SEN);
+
+	if (!found) {
+		dev_dbg(sdev->dev, "stream_tag %d not opened!\n", stream_tag);
+		return -ENODEV;
+	}
+
+	return 0;
 }
 
 int hda_dsp_stream_trigger(struct snd_sof_dev *sdev,
diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index c72e9a09eee1..06e84679087b 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -35,6 +35,8 @@
 #define IS_CFL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa348)
 #define IS_CNL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9dc8)
 
+#define EXCEPT_MAX_HDR_SIZE	0x400
+
 /*
  * Debug
  */
@@ -131,6 +133,11 @@ static void hda_dsp_get_registers(struct snd_sof_dev *sdev,
 	/* note: variable AR register array is not read */
 
 	/* then get panic info */
+	if (xoops->arch_hdr.totalsize > EXCEPT_MAX_HDR_SIZE) {
+		dev_err(sdev->dev, "invalid header size 0x%x. FW oops is bogus\n",
+			xoops->arch_hdr.totalsize);
+		return;
+	}
 	offset += xoops->arch_hdr.totalsize;
 	sof_block_read(sdev, sdev->mmio_bar, offset,
 		       panic_info, sizeof(*panic_info));
diff --git a/sound/soc/sof/intel/hda.h b/sound/soc/sof/intel/hda.h
index 5591841a1b6f..23e430d3e056 100644
--- a/sound/soc/sof/intel/hda.h
+++ b/sound/soc/sof/intel/hda.h
@@ -39,7 +39,6 @@
 #define SOF_HDA_WAKESTS			0x0E
 #define SOF_HDA_WAKESTS_INT_MASK	((1 << 8) - 1)
 #define SOF_HDA_RIRBSTS			0x5d
-#define SOF_HDA_VS_EM2_L1SEN            BIT(13)
 
 /* SOF_HDA_GCTL register bist */
 #define SOF_HDA_GCTL_RESET		BIT(0)
@@ -228,6 +227,10 @@
 #define HDA_DSP_REG_HIPCIE		(HDA_DSP_IPC_BASE + 0x0C)
 #define HDA_DSP_REG_HIPCCTL		(HDA_DSP_IPC_BASE + 0x10)
 
+/* Intel Vendor Specific Registers */
+#define HDA_VS_INTEL_EM2		0x1030
+#define HDA_VS_INTEL_EM2_L1SEN		BIT(13)
+
 /*  HIPCI */
 #define HDA_DSP_REG_HIPCI_BUSY		BIT(31)
 #define HDA_DSP_REG_HIPCI_MSG_MASK	0x7FFFFFFF
diff --git a/sound/soc/sof/ipc.c b/sound/soc/sof/ipc.c
index b2f359d2f7e5..086eeeab8679 100644
--- a/sound/soc/sof/ipc.c
+++ b/sound/soc/sof/ipc.c
@@ -572,8 +572,10 @@ static int sof_set_get_large_ctrl_data(struct snd_sof_dev *sdev,
 	else
 		err = sof_get_ctrl_copy_params(cdata->type, partdata, cdata,
 					       sparams);
-	if (err < 0)
+	if (err < 0) {
+		kfree(partdata);
 		return err;
+	}
 
 	msg_bytes = sparams->msg_bytes;
 	pl_size = sparams->pl_size;
diff --git a/sound/soc/sof/loader.c b/sound/soc/sof/loader.c
index d7f32745fefe..9a9a381a908d 100644
--- a/sound/soc/sof/loader.c
+++ b/sound/soc/sof/loader.c
@@ -546,10 +546,10 @@ int snd_sof_run_firmware(struct snd_sof_dev *sdev)
 				 msecs_to_jiffies(sdev->boot_timeout));
 	if (ret == 0) {
 		dev_err(sdev->dev, "error: firmware boot failure\n");
-		/* after this point FW_READY msg should be ignored */
-		sdev->boot_complete = true;
 		snd_sof_dsp_dbg_dump(sdev, SOF_DBG_REGS | SOF_DBG_MBOX |
 			SOF_DBG_TEXT | SOF_DBG_PCI);
+		/* after this point FW_READY msg should be ignored */
+		sdev->boot_complete = true;
 		return -EIO;
 	}
 
diff --git a/sound/soc/sof/pcm.c b/sound/soc/sof/pcm.c
index e3f6a6dc0f36..2b876d497447 100644
--- a/sound/soc/sof/pcm.c
+++ b/sound/soc/sof/pcm.c
@@ -244,7 +244,7 @@ static int sof_pcm_hw_free(struct snd_pcm_substream *substream)
 		snd_soc_rtdcom_lookup(rtd, DRV_NAME);
 	struct snd_sof_dev *sdev = snd_soc_component_get_drvdata(component);
 	struct snd_sof_pcm *spcm;
-	int ret;
+	int ret, err = 0;
 
 	/* nothing to do for BE */
 	if (rtd->dai_link->no_pcm)
@@ -254,26 +254,26 @@ static int sof_pcm_hw_free(struct snd_pcm_substream *substream)
 	if (!spcm)
 		return -EINVAL;
 
-	if (!spcm->prepared[substream->stream])
-		return 0;
-
 	dev_dbg(sdev->dev, "pcm: free stream %d dir %d\n", spcm->pcm.pcm_id,
 		substream->stream);
 
-	ret = sof_pcm_dsp_pcm_free(substream, sdev, spcm);
+	if (spcm->prepared[substream->stream]) {
+		ret = sof_pcm_dsp_pcm_free(substream, sdev, spcm);
+		if (ret < 0)
+			err = ret;
+	}
 
 	snd_pcm_lib_free_pages(substream);
 
 	cancel_work_sync(&spcm->stream[substream->stream].period_elapsed_work);
 
-	if (ret < 0)
-		return ret;
-
 	ret = snd_sof_pcm_platform_hw_free(sdev, substream);
-	if (ret < 0)
+	if (ret < 0) {
 		dev_err(sdev->dev, "error: platform hw free failed\n");
+		err = ret;
+	}
 
-	return ret;
+	return err;
 }
 
 static int sof_pcm_prepare(struct snd_pcm_substream *substream)
@@ -323,6 +323,7 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	struct sof_ipc_stream stream;
 	struct sof_ipc_reply reply;
 	bool reset_hw_params = false;
+	bool ipc_first = false;
 	int ret;
 
 	/* nothing to do for BE */
@@ -343,6 +344,7 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_PAUSE;
+		ipc_first = true;
 		break;
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_RELEASE;
@@ -363,6 +365,7 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 	case SNDRV_PCM_TRIGGER_STOP:
 		stream.hdr.cmd |= SOF_IPC_STREAM_TRIG_STOP;
+		ipc_first = true;
 		reset_hw_params = true;
 		break;
 	default:
@@ -370,12 +373,22 @@ static int sof_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 		return -EINVAL;
 	}
 
-	snd_sof_pcm_platform_trigger(sdev, substream, cmd);
+	/*
+	 * DMA and IPC sequence is different for start and stop. Need to send
+	 * STOP IPC before stop DMA
+	 */
+	if (!ipc_first)
+		snd_sof_pcm_platform_trigger(sdev, substream, cmd);
 
 	/* send IPC to the DSP */
 	ret = sof_ipc_tx_message(sdev->ipc, stream.hdr.cmd, &stream,
 				 sizeof(stream), &reply, sizeof(reply));
 
+	/* need to STOP DMA even if STOP IPC failed */
+	if (ipc_first)
+		snd_sof_pcm_platform_trigger(sdev, substream, cmd);
+
+	/* free PCM if reset_hw_params is set and the STOP IPC is successful */
 	if (!ret && reset_hw_params)
 		ret = sof_pcm_dsp_pcm_free(substream, sdev, spcm);
 
diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
index fc85efbad378..4452594c2e17 100644
--- a/sound/soc/sof/topology.c
+++ b/sound/soc/sof/topology.c
@@ -543,15 +543,16 @@ static int sof_control_load_bytes(struct snd_soc_component *scomp,
 	struct soc_bytes_ext *sbe = (struct soc_bytes_ext *)kc->private_value;
 	int max_size = sbe->max;
 
-	if (le32_to_cpu(control->priv.size) > max_size) {
+	/* init the get/put bytes data */
+	scontrol->size = sizeof(struct sof_ipc_ctrl_data) +
+		le32_to_cpu(control->priv.size);
+
+	if (scontrol->size > max_size) {
 		dev_err(sdev->dev, "err: bytes data size %d exceeds max %d.\n",
-			control->priv.size, max_size);
+			scontrol->size, max_size);
 		return -EINVAL;
 	}
 
-	/* init the get/put bytes data */
-	scontrol->size = sizeof(struct sof_ipc_ctrl_data) +
-		le32_to_cpu(control->priv.size);
 	scontrol->control_data = kzalloc(max_size, GFP_KERNEL);
 	cdata = scontrol->control_data;
 	if (!scontrol->control_data)
@@ -920,7 +921,9 @@ static void sof_parse_word_tokens(struct snd_soc_component *scomp,
 		for (j = 0; j < count; j++) {
 			/* match token type */
 			if (!(tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_WORD ||
-			      tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_SHORT))
+			      tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_SHORT ||
+			      tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_BYTE ||
+			      tokens[j].type == SND_SOC_TPLG_TUPLE_TYPE_BOOL))
 				continue;
 
 			/* match token id */
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index d7501f88aaa6..48e629ac2d88 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -505,10 +505,20 @@ static int stm32_sai_set_sysclk(struct snd_soc_dai *cpu_dai,
 	if (dir == SND_SOC_CLOCK_OUT && sai->sai_mclk) {
 		ret = regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX,
 					 SAI_XCR1_NODIV,
-					 (unsigned int)~SAI_XCR1_NODIV);
+					 freq ? 0 : SAI_XCR1_NODIV);
 		if (ret < 0)
 			return ret;
 
+		/* Assume shutdown if requested frequency is 0Hz */
+		if (!freq) {
+			/* Release mclk rate only if rate was actually set */
+			if (sai->mclk_rate) {
+				clk_rate_exclusive_put(sai->sai_mclk);
+				sai->mclk_rate = 0;
+			}
+			return 0;
+		}
+
 		/* If master clock is used, set parent clock now */
 		ret = stm32_sai_set_parent_clock(sai, freq);
 		if (ret)
@@ -1093,15 +1103,6 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream,
 
 	regmap_update_bits(sai->regmap, STM_SAI_IMR_REGX, SAI_XIMR_MASK, 0);
 
-	regmap_update_bits(sai->regmap, STM_SAI_CR1_REGX, SAI_XCR1_NODIV,
-			   SAI_XCR1_NODIV);
-
-	/* Release mclk rate only if rate was actually set */
-	if (sai->mclk_rate) {
-		clk_rate_exclusive_put(sai->sai_mclk);
-		sai->mclk_rate = 0;
-	}
-
 	clk_disable_unprepare(sai->sai_ck);
 
 	spin_lock_irqsave(&sai->irq_lock, flags);
@@ -1217,6 +1218,16 @@ static int stm32_sai_pcm_process_spdif(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+/* No support of mmap in S/PDIF mode */
+static const struct snd_pcm_hardware stm32_sai_pcm_hw_spdif = {
+	.info = SNDRV_PCM_INFO_INTERLEAVED,
+	.buffer_bytes_max = 8 * PAGE_SIZE,
+	.period_bytes_min = 1024,
+	.period_bytes_max = PAGE_SIZE,
+	.periods_min = 2,
+	.periods_max = 8,
+};
+
 static const struct snd_pcm_hardware stm32_sai_pcm_hw = {
 	.info = SNDRV_PCM_INFO_INTERLEAVED | SNDRV_PCM_INFO_MMAP,
 	.buffer_bytes_max = 8 * PAGE_SIZE,
@@ -1269,7 +1280,7 @@ static const struct snd_dmaengine_pcm_config stm32_sai_pcm_config = {
 };
 
 static const struct snd_dmaengine_pcm_config stm32_sai_pcm_config_spdif = {
-	.pcm_hardware = &stm32_sai_pcm_hw,
+	.pcm_hardware = &stm32_sai_pcm_hw_spdif,
 	.prepare_slave_config = snd_dmaengine_pcm_prepare_slave_config,
 	.process = stm32_sai_pcm_process_spdif,
 };
diff --git a/sound/soc/ti/sdma-pcm.c b/sound/soc/ti/sdma-pcm.c
index a236350beb10..2b0bc234e1b6 100644
--- a/sound/soc/ti/sdma-pcm.c
+++ b/sound/soc/ti/sdma-pcm.c
@@ -62,7 +62,7 @@ int sdma_pcm_platform_register(struct device *dev,
 	config->chan_names[0] = txdmachan;
 	config->chan_names[1] = rxdmachan;
 
-	return devm_snd_dmaengine_pcm_register(dev, config, 0);
+	return devm_snd_dmaengine_pcm_register(dev, config, flags);
 }
 EXPORT_SYMBOL_GPL(sdma_pcm_platform_register);
 
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index fbfde996fee7..0bbe1201a6ac 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1657,6 +1657,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 	case 0x23ba:  /* Playback Designs */
 	case 0x25ce:  /* Mytek devices */
 	case 0x278b:  /* Rotel? */
+	case 0x292b:  /* Gustard/Ess based devices */
 	case 0x2ab6:  /* T+A devices */
 	case 0x3842:  /* EVGA */
 	case 0xc502:  /* HiBy devices */
diff --git a/sound/usb/validate.c b/sound/usb/validate.c
index 3c8f73a0eb12..a5e584b60dcd 100644
--- a/sound/usb/validate.c
+++ b/sound/usb/validate.c
@@ -75,7 +75,7 @@ static bool validate_processing_unit(const void *p,
 
 	if (d->bLength < sizeof(*d))
 		return false;
-	len = d->bLength < sizeof(*d) + d->bNrInPins;
+	len = sizeof(*d) + d->bNrInPins;
 	if (d->bLength < len)
 		return false;
 	switch (v->protocol) {
diff --git a/tools/arch/x86/include/uapi/asm/svm.h b/tools/arch/x86/include/uapi/asm/svm.h
index a9731f8a480f..2e8a30f06c74 100644
--- a/tools/arch/x86/include/uapi/asm/svm.h
+++ b/tools/arch/x86/include/uapi/asm/svm.h
@@ -75,6 +75,7 @@
 #define SVM_EXIT_MWAIT         0x08b
 #define SVM_EXIT_MWAIT_COND    0x08c
 #define SVM_EXIT_XSETBV        0x08d
+#define SVM_EXIT_RDPRU         0x08e
 #define SVM_EXIT_NPF           0x400
 #define SVM_EXIT_AVIC_INCOMPLETE_IPI		0x401
 #define SVM_EXIT_AVIC_UNACCELERATED_ACCESS	0x402
diff --git a/tools/arch/x86/include/uapi/asm/vmx.h b/tools/arch/x86/include/uapi/asm/vmx.h
index f01950aa7fae..3eb8411ab60e 100644
--- a/tools/arch/x86/include/uapi/asm/vmx.h
+++ b/tools/arch/x86/include/uapi/asm/vmx.h
@@ -86,6 +86,8 @@
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
+#define EXIT_REASON_UMWAIT              67
+#define EXIT_REASON_TPAUSE              68
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -144,7 +146,9 @@
 	{ EXIT_REASON_RDSEED,                "RDSEED" }, \
 	{ EXIT_REASON_PML_FULL,              "PML_FULL" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
-	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
+	{ EXIT_REASON_UMWAIT,                "UMWAIT" }, \
+	{ EXIT_REASON_TPAUSE,                "TPAUSE" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_PDPTE_FAIL       2
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 6ecdd1067826..1178d302757e 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -3,7 +3,11 @@ include ../scripts/Makefile.include
 
 bindir ?= /usr/bin
 
-ifeq ($(srctree),)
+# This will work when gpio is built in tools env. where srctree
+# isn't set and when invoked from selftests build, where srctree
+# is set to ".". building_out_of_srctree is undefined for in srctree
+# builds
+ifndef building_out_of_srctree
 srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 233efbb1c81c..52641d8ca9e8 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -999,6 +999,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
+#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1145,6 +1146,7 @@ struct kvm_dirty_tlb {
 #define KVM_REG_S390		0x5000000000000000ULL
 #define KVM_REG_ARM64		0x6000000000000000ULL
 #define KVM_REG_MIPS		0x7000000000000000ULL
+#define KVM_REG_RISCV		0x8000000000000000ULL
 
 #define KVM_REG_SIZE_SHIFT	52
 #define KVM_REG_SIZE_MASK	0x00f0000000000000ULL
diff --git a/tools/include/uapi/linux/sched.h b/tools/include/uapi/linux/sched.h
index b3105ac1381a..99335e1f4a27 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/include/uapi/linux/sched.h
@@ -33,8 +33,31 @@
 #define CLONE_NEWNET		0x40000000	/* New network namespace */
 #define CLONE_IO		0x80000000	/* Clone io context */
 
-/*
- * Arguments for the clone3 syscall
+#ifndef __ASSEMBLY__
+/**
+ * struct clone_args - arguments for the clone3 syscall
+ * @flags:       Flags for the new process as listed above.
+ *               All flags are valid except for CSIGNAL and
+ *               CLONE_DETACHED.
+ * @pidfd:       If CLONE_PIDFD is set, a pidfd will be
+ *               returned in this argument.
+ * @child_tid:   If CLONE_CHILD_SETTID is set, the TID of the
+ *               child process will be returned in the child's
+ *               memory.
+ * @parent_tid:  If CLONE_PARENT_SETTID is set, the TID of
+ *               the child process will be returned in the
+ *               parent's memory.
+ * @exit_signal: The exit_signal the parent process will be
+ *               sent when the child exits.
+ * @stack:       Specify the location of the stack for the
+ *               child process.
+ * @stack_size:  The size of the stack for the child process.
+ * @tls:         If CLONE_SETTLS is set, the tls descriptor
+ *               is set to tls.
+ *
+ * The structure is versioned by size and thus extensible.
+ * New struct members must go at the end of the struct and
+ * must be properly 64bit aligned.
  */
 struct clone_args {
 	__aligned_u64 flags;
@@ -46,6 +69,9 @@ struct clone_args {
 	__aligned_u64 stack_size;
 	__aligned_u64 tls;
 };
+#endif
+
+#define CLONE_ARGS_SIZE_VER0 64 /* sizeof first published struct */
 
 /*
  * Scheduling policies
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 3542b6ab9813..e69f44941aad 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2635,6 +2635,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 	bool add_sym   = false;
 	bool add_dso   = false;
 	bool add_src   = false;
+	int ret = 0;
 
 	if (!buf)
 		return -ENOMEM;
@@ -2653,7 +2654,8 @@ static int build_cl_output(char *cl_sort, bool no_source)
 			add_dso = true;
 		} else if (strcmp(tok, "offset")) {
 			pr_err("unrecognized sort token: %s\n", tok);
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err;
 		}
 	}
 
@@ -2676,13 +2678,15 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		add_sym ? "symbol," : "",
 		add_dso ? "dso," : "",
 		add_src ? "cl_srcline," : "",
-		"node") < 0)
-		return -ENOMEM;
+		"node") < 0) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	c2c.show_src = add_src;
-
+err:
 	free(buf);
-	return 0;
+	return ret;
 }
 
 static int setup_coalesce(const char *coalesce, bool no_source)
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 1e61e353f579..9661671cc26e 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -691,6 +691,7 @@ static char *compact_gfp_flags(char *gfp_flags)
 			new = realloc(new_flags, len + strlen(cpt) + 2);
 			if (new == NULL) {
 				free(new_flags);
+				free(orig_flags);
 				return NULL;
 			}
 
diff --git a/tools/perf/jvmti/Build b/tools/perf/jvmti/Build
index 1e148bbdf820..202cadaaf097 100644
--- a/tools/perf/jvmti/Build
+++ b/tools/perf/jvmti/Build
@@ -2,7 +2,7 @@ jvmti-y += libjvmti.o
 jvmti-y += jvmti_agent.o
 
 # For strlcpy
-jvmti-y += libstring.o
+jvmti-y += libstring.o libctype.o
 
 CFLAGS_jvmti         = -fPIC -DPIC -I$(JDIR)/include -I$(JDIR)/include/linux
 CFLAGS_REMOVE_jvmti  = -Wmissing-declarations
@@ -15,3 +15,7 @@ CFLAGS_libstring.o += -Wno-unused-parameter -DETC_PERFCONFIG="BUILD_STR($(ETC_PE
 $(OUTPUT)jvmti/libstring.o: ../lib/string.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)jvmti/libctype.o: ../lib/ctype.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/perf-sys.h b/tools/perf/perf-sys.h
index 63e4349a772a..15e458e150bd 100644
--- a/tools/perf/perf-sys.h
+++ b/tools/perf/perf-sys.h
@@ -15,7 +15,9 @@ void test_attr__init(void);
 void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
 		     int fd, int group_fd, unsigned long flags);
 
-#define HAVE_ATTR_TEST
+#ifndef HAVE_ATTR_TEST
+#define HAVE_ATTR_TEST 1
+#endif
 
 static inline int
 sys_perf_event_open(struct perf_event_attr *attr,
@@ -27,7 +29,7 @@ sys_perf_event_open(struct perf_event_attr *attr,
 	fd = syscall(__NR_perf_event_open, attr, pid, cpu,
 		     group_fd, flags);
 
-#ifdef HAVE_ATTR_TEST
+#if HAVE_ATTR_TEST
 	if (unlikely(test_attr__enabled))
 		test_attr__open(attr, pid, cpu, fd, group_fd, flags);
 #endif
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 4036c7f7b0fb..e42bf572358c 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -1758,7 +1758,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
 	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
 						 dso->bpf_prog.id);
 	if (!info_node) {
-		return SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
 		goto out;
 	}
 	info_linear = info_node->info_linear;
diff --git a/tools/perf/util/copyfile.c b/tools/perf/util/copyfile.c
index 3fa0db136667..47e03de7c235 100644
--- a/tools/perf/util/copyfile.c
+++ b/tools/perf/util/copyfile.c
@@ -101,14 +101,16 @@ static int copyfile_mode_ns(const char *from, const char *to, mode_t mode,
 	if (tofd < 0)
 		goto out;
 
-	if (fchmod(tofd, mode))
-		goto out_close_to;
-
 	if (st.st_size == 0) { /* /proc? do it slowly... */
 		err = slow_copyfile(from, tmp, nsi);
+		if (!err && fchmod(tofd, mode))
+			err = -1;
 		goto out_close_to;
 	}
 
+	if (fchmod(tofd, mode))
+		goto out_close_to;
+
 	nsinfo__mountns_enter(nsi, &nsc);
 	fromfd = open(from, O_RDONLY);
 	nsinfo__mountns_exit(&nsc);
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d277a98e62df..de79c735e441 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -1659,7 +1659,7 @@ struct evsel *perf_evlist__reset_weak_group(struct evlist *evsel_list,
 			is_open = false;
 		if (c2->leader == leader) {
 			if (is_open)
-				perf_evsel__close(&evsel->core);
+				perf_evsel__close(&c2->core);
 			c2->leader = c2;
 			c2->core.nr_members = 0;
 		}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 86d9396cb131..becc2d109423 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1296,8 +1296,10 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
 			continue;
 
 		if (WARN_ONCE(cnt >= size,
-			      "failed to write MEM_TOPOLOGY, way too many nodes\n"))
+			"failed to write MEM_TOPOLOGY, way too many nodes\n")) {
+			closedir(dir);
 			return -1;
+		}
 
 		ret = memory_node__read(&nodes[cnt++], idx);
 	}
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 679a1d75090c..7b6eaf5e0bda 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1625,7 +1625,7 @@ int hists__collapse_resort(struct hists *hists, struct ui_progress *prog)
 	return 0;
 }
 
-static int hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
+static int64_t hist_entry__sort(struct hist_entry *a, struct hist_entry *b)
 {
 	struct hists *hists = a->hists;
 	struct perf_hpp_fmt *fmt;
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 15961854ba67..741f040648b5 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -539,10 +539,11 @@ static int perl_stop_script(void)
 
 static int perl_generate_script(struct tep_handle *pevent, const char *outfile)
 {
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
 	struct tep_event *event = NULL;
 	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.pl", outfile);
@@ -603,8 +604,11 @@ sub print_backtrace\n\
 }\n\n\
 ");
 
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "sub %s::%s\n{\n", event->system, event->name);
 		fprintf(ofp, "\tmy (");
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 5d341efc3237..93c03b39cd9c 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1687,10 +1687,11 @@ static int python_stop_script(void)
 
 static int python_generate_script(struct tep_handle *pevent, const char *outfile)
 {
+	int i, not_first, count, nr_events;
+	struct tep_event **all_events;
 	struct tep_event *event = NULL;
 	struct tep_format_field *f;
 	char fname[PATH_MAX];
-	int not_first, count;
 	FILE *ofp;
 
 	sprintf(fname, "%s.py", outfile);
@@ -1735,7 +1736,11 @@ static int python_generate_script(struct tep_handle *pevent, const char *outfile
 	fprintf(ofp, "def trace_end():\n");
 	fprintf(ofp, "\tprint(\"in trace_end\")\n\n");
 
-	while ((event = trace_find_next_event(pevent, event))) {
+	nr_events = tep_get_events_count(pevent);
+	all_events = tep_list_events(pevent, TEP_EVENT_SORT_ID);
+
+	for (i = 0; all_events && i < nr_events; i++) {
+		event = all_events[i];
 		fprintf(ofp, "def %s__%s(", event->system, event->name);
 		fprintf(ofp, "event_name, ");
 		fprintf(ofp, "context, ");
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 5d6bfc70b210..9634f0ae57be 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -173,37 +173,6 @@ int parse_event_file(struct tep_handle *pevent,
 	return tep_parse_event(pevent, buf, size, sys);
 }
 
-struct tep_event *trace_find_next_event(struct tep_handle *pevent,
-					struct tep_event *event)
-{
-	static int idx;
-	int events_count;
-	struct tep_event *all_events;
-
-	all_events = tep_get_first_event(pevent);
-	events_count = tep_get_events_count(pevent);
-	if (!pevent || !all_events || events_count < 1)
-		return NULL;
-
-	if (!event) {
-		idx = 0;
-		return all_events;
-	}
-
-	if (idx < events_count && event == (all_events + idx)) {
-		idx++;
-		if (idx == events_count)
-			return NULL;
-		return (all_events + idx);
-	}
-
-	for (idx = 1; idx < events_count; idx++) {
-		if (event == (all_events + (idx - 1)))
-			return (all_events + idx);
-	}
-	return NULL;
-}
-
 struct flag {
 	const char *name;
 	unsigned long long value;
diff --git a/tools/perf/util/trace-event.h b/tools/perf/util/trace-event.h
index 2e158387b3d7..72fdf2a3577c 100644
--- a/tools/perf/util/trace-event.h
+++ b/tools/perf/util/trace-event.h
@@ -47,8 +47,6 @@ void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int siz
 
 ssize_t trace_report(int fd, struct trace_event *tevent, bool repipe);
 
-struct tep_event *trace_find_next_event(struct tep_handle *pevent,
-					struct tep_event *event);
 unsigned long long read_size(struct tep_event *event, void *ptr, int size);
 unsigned long long eval_flag(const char *flag);
 
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 5eda6e19c947..ae56c766eda1 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -154,8 +154,10 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat)
 		if (!strcmp(d->d_name, ".") || !strcmp(d->d_name, ".."))
 			continue;
 
-		if (!match_pat(d->d_name, pat))
-			return -2;
+		if (!match_pat(d->d_name, pat)) {
+			ret =  -2;
+			break;
+		}
 
 		scnprintf(namebuf, sizeof(namebuf), "%s/%s",
 			  path, d->d_name);
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 15a666329a34..1afa22c88e42 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -22,6 +22,7 @@ import os
 import pprint
 import random
 import re
+import stat
 import string
 import struct
 import subprocess
@@ -311,7 +312,11 @@ class DebugfsDir:
         for f in out.split():
             if f == "ports":
                 continue
+
             p = os.path.join(path, f)
+            if not os.stat(p).st_mode & stat.S_IRUSR:
+                continue
+
             if os.path.isfile(p):
                 _, out = cmd('cat %s/%s' % (path, f))
                 dfs[f] = out.strip()
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index a320e3844b17..7c6e5b173f33 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -161,9 +161,14 @@ static struct sysctl_test tests[] = {
 		.descr = "ctx:file_pos sysctl:read read ok narrow",
 		.insns = {
 			/* If (file_pos == X) */
+#if __BYTE_ORDER == __LITTLE_ENDIAN
 			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
 				    offsetof(struct bpf_sysctl, file_pos)),
-			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0, 2),
+#else
+			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
+				    offsetof(struct bpf_sysctl, file_pos) + 3),
+#endif
+			BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 4, 2),
 
 			/* return ALLOW; */
 			BPF_MOV64_IMM(BPF_REG_0, 1),
@@ -176,6 +181,7 @@ static struct sysctl_test tests[] = {
 		.attach_type = BPF_CGROUP_SYSCTL,
 		.sysctl = "kernel/ostype",
 		.open_flags = O_RDONLY,
+		.seek = 4,
 		.result = SUCCESS,
 	},
 	{
diff --git a/tools/testing/selftests/bpf/test_tc_edt.sh b/tools/testing/selftests/bpf/test_tc_edt.sh
index f38567ef694b..daa7d1b8d309 100755
--- a/tools/testing/selftests/bpf/test_tc_edt.sh
+++ b/tools/testing/selftests/bpf/test_tc_edt.sh
@@ -59,7 +59,7 @@ ip netns exec ${NS_SRC} tc filter add dev veth_src egress \
 
 # start the listener
 ip netns exec ${NS_DST} bash -c \
-	"nc -4 -l -s ${IP_DST} -p 9000 >/dev/null &"
+	"nc -4 -l -p 9000 >/dev/null &"
 declare -i NC_PID=$!
 sleep 1
 
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index b35da375530a..409c1fa75e03 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,4 +1,5 @@
 /s390x/sync_regs_test
+/s390x/memop
 /x86_64/cr4_cpuid_sync_test
 /x86_64/evmcs_test
 /x86_64/hyperv_cpuid
@@ -9,6 +10,7 @@
 /x86_64/state_test
 /x86_64/sync_regs_test
 /x86_64/vmx_close_while_nested_test
+/x86_64/vmx_dirty_log_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
 /clear_dirty_log_test
diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86_64/vmx.h
index 6ae5a47fe067..f52e0ba84fed 100644
--- a/tools/testing/selftests/kvm/include/x86_64/vmx.h
+++ b/tools/testing/selftests/kvm/include/x86_64/vmx.h
@@ -580,6 +580,8 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx);
 void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
 bool load_vmcs(struct vmx_pages *vmx);
 
+void nested_vmx_check_supported(void);
+
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		   uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot);
 void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,
diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
index fab8f6b0bf52..f6ec97b7eaef 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/vmx.c
@@ -376,6 +376,16 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
 	init_vmcs_guest_state(guest_rip, guest_rsp);
 }
 
+void nested_vmx_check_supported(void)
+{
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	if (!(entry->ecx & CPUID_VMX)) {
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+}
+
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 	 	   uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot)
 {
diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
index 11c2a70a7b87..5c8224256294 100644
--- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
+++ b/tools/testing/selftests/kvm/x86_64/sync_regs_test.c
@@ -22,18 +22,19 @@
 
 #define VCPU_ID 5
 
+#define UCALL_PIO_PORT ((uint16_t)0x1000)
+
+/*
+ * ucall is embedded here to protect against compiler reshuffling registers
+ * before calling a function. In this test we only need to get KVM_EXIT_IO
+ * vmexit and preserve RBX, no additional information is needed.
+ */
 void guest_code(void)
 {
-	/*
-	 * use a callee-save register, otherwise the compiler
-	 * saves it around the call to GUEST_SYNC.
-	 */
-	register u32 stage asm("rbx");
-	for (;;) {
-		GUEST_SYNC(0);
-		stage++;
-		asm volatile ("" : : "r" (stage));
-	}
+	asm volatile("1: in %[port], %%al\n"
+		     "add $0x1, %%rbx\n"
+		     "jmp 1b"
+		     : : [port] "d" (UCALL_PIO_PORT) : "rax", "rbx");
 }
 
 static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
index 3b0ffe01dacd..5dfb53546a26 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c
@@ -53,12 +53,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t vmx_pages_gva;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
+	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
index 0bca1cfe2c1e..a223a6401258 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c
@@ -78,6 +78,8 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	bool done = false;
 
+	nested_vmx_check_supported();
+
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, l1_guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
index 853e370e8a39..9ef7fab39d48 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c
@@ -224,7 +224,6 @@ int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
 	struct kvm_nested_state state;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
 	have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS);
 
@@ -237,10 +236,7 @@ int main(int argc, char *argv[])
 	 * AMD currently does not implement set_nested_state, so for now we
 	 * just early out.
 	 */
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
+	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, 0);
 
@@ -271,12 +267,7 @@ int main(int argc, char *argv[])
 	state.flags = KVM_STATE_NESTED_RUN_PENDING;
 	test_nested_state_expect_einval(vm, &state);
 
-	/*
-	 * TODO: When SVM support is added for KVM_SET_NESTED_STATE
-	 *       add tests here to support it like VMX.
-	 */
-	if (entry->ecx & CPUID_VMX)
-		test_vmx_nested_state(vm);
+	test_vmx_nested_state(vm);
 
 	kvm_vm_free(vm);
 	return 0;
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index f36c10eba71e..5590fd2bcf87 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -128,12 +128,8 @@ static void report(int64_t val)
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t vmx_pages_gva;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
+	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index c4ba0ff4a53f..76c1897e6352 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -1438,6 +1438,27 @@ ipv4_addr_metric_test()
 	fi
 	log_test $rc 0 "Prefix route with metric on link up"
 
+	# explicitly check for metric changes on edge scenarios
+	run_cmd "$IP addr flush dev dummy2"
+	run_cmd "$IP addr add dev dummy2 172.16.104.0/24 metric 259"
+	run_cmd "$IP addr change dev dummy2 172.16.104.0/24 metric 260"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.0 metric 260"
+		rc=$?
+	fi
+	log_test $rc 0 "Modify metric of .0/24 address"
+
+	run_cmd "$IP addr flush dev dummy2"
+	run_cmd "$IP addr add dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 260"
+	run_cmd "$IP addr change dev dummy2 172.16.104.1/32 peer 172.16.104.2 metric 261"
+	rc=$?
+	if [ $rc -eq 0 ]; then
+		check_route "172.16.104.2 dev dummy2 proto kernel scope link src 172.16.104.1 metric 261"
+		rc=$?
+	fi
+	log_test $rc 0 "Modify metric of address with peer route"
+
 	$IP li del dummy1
 	$IP li del dummy2
 	cleanup
diff --git a/tools/testing/selftests/net/l2tp.sh b/tools/testing/selftests/net/l2tp.sh
index 5782433886fc..5782433886fc 100644..100755
--- a/tools/testing/selftests/net/l2tp.sh
+++ b/tools/testing/selftests/net/l2tp.sh
diff --git a/tools/testing/selftests/net/reuseport_dualstack.c b/tools/testing/selftests/net/reuseport_dualstack.c
index fe3230c55986..fb7a59ed759e 100644
--- a/tools/testing/selftests/net/reuseport_dualstack.c
+++ b/tools/testing/selftests/net/reuseport_dualstack.c
@@ -129,7 +129,7 @@ static void test(int *rcv_fds, int count, int proto)
 {
 	struct epoll_event ev;
 	int epfd, i, test_fd;
-	uint16_t test_family;
+	int test_family;
 	socklen_t len;
 
 	epfd = epoll_create(1);
@@ -146,6 +146,7 @@ static void test(int *rcv_fds, int count, int proto)
 	send_from_v4(proto);
 
 	test_fd = receive_once(epfd, proto);
+	len = sizeof(test_family);
 	if (getsockopt(test_fd, SOL_SOCKET, SO_DOMAIN, &test_family, &len))
 		error(1, errno, "failed to read socket domain");
 	if (test_family != AF_INET)
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 4c285b6e1db8..1c8f194d6556 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -898,6 +898,114 @@ TEST_F(tls, nonblocking)
 	}
 }
 
+static void
+test_mutliproc(struct __test_metadata *_metadata, struct _test_data_tls *self,
+	       bool sendpg, unsigned int n_readers, unsigned int n_writers)
+{
+	const unsigned int n_children = n_readers + n_writers;
+	const size_t data = 6 * 1000 * 1000;
+	const size_t file_sz = data / 100;
+	size_t read_bias, write_bias;
+	int i, fd, child_id;
+	char buf[file_sz];
+	pid_t pid;
+
+	/* Only allow multiples for simplicity */
+	ASSERT_EQ(!(n_readers % n_writers) || !(n_writers % n_readers), true);
+	read_bias = n_writers / n_readers ?: 1;
+	write_bias = n_readers / n_writers ?: 1;
+
+	/* prep a file to send */
+	fd = open("/tmp/", O_TMPFILE | O_RDWR, 0600);
+	ASSERT_GE(fd, 0);
+
+	memset(buf, 0xac, file_sz);
+	ASSERT_EQ(write(fd, buf, file_sz), file_sz);
+
+	/* spawn children */
+	for (child_id = 0; child_id < n_children; child_id++) {
+		pid = fork();
+		ASSERT_NE(pid, -1);
+		if (!pid)
+			break;
+	}
+
+	/* parent waits for all children */
+	if (pid) {
+		for (i = 0; i < n_children; i++) {
+			int status;
+
+			wait(&status);
+			EXPECT_EQ(status, 0);
+		}
+
+		return;
+	}
+
+	/* Split threads for reading and writing */
+	if (child_id < n_readers) {
+		size_t left = data * read_bias;
+		char rb[8001];
+
+		while (left) {
+			int res;
+
+			res = recv(self->cfd, rb,
+				   left > sizeof(rb) ? sizeof(rb) : left, 0);
+
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+	} else {
+		size_t left = data * write_bias;
+
+		while (left) {
+			int res;
+
+			ASSERT_EQ(lseek(fd, 0, SEEK_SET), 0);
+			if (sendpg)
+				res = sendfile(self->fd, fd, NULL,
+					       left > file_sz ? file_sz : left);
+			else
+				res = send(self->fd, buf,
+					   left > file_sz ? file_sz : left, 0);
+
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+	}
+}
+
+TEST_F(tls, mutliproc_even)
+{
+	test_mutliproc(_metadata, self, false, 6, 6);
+}
+
+TEST_F(tls, mutliproc_readers)
+{
+	test_mutliproc(_metadata, self, false, 4, 12);
+}
+
+TEST_F(tls, mutliproc_writers)
+{
+	test_mutliproc(_metadata, self, false, 10, 2);
+}
+
+TEST_F(tls, mutliproc_sendpage_even)
+{
+	test_mutliproc(_metadata, self, true, 6, 6);
+}
+
+TEST_F(tls, mutliproc_sendpage_readers)
+{
+	test_mutliproc(_metadata, self, true, 4, 12);
+}
+
+TEST_F(tls, mutliproc_sendpage_writers)
+{
+	test_mutliproc(_metadata, self, true, 10, 2);
+}
+
 TEST_F(tls, control_msg)
 {
 	if (self->notls)
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index cb3fc09645c4..485cf06ef013 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/tools/testing/selftests/vm/gup_benchmark.c
@@ -71,7 +71,7 @@ int main(int argc, char **argv)
 			flags |= MAP_SHARED;
 			break;
 		case 'H':
-			flags |= MAP_HUGETLB;
+			flags |= (MAP_HUGETLB | MAP_ANONYMOUS);
 			break;
 		default:
 			return -1;
diff --git a/tools/usb/usbip/libsrc/usbip_device_driver.c b/tools/usb/usbip/libsrc/usbip_device_driver.c
index 051d7d3f443b..927a151fa9aa 100644
--- a/tools/usb/usbip/libsrc/usbip_device_driver.c
+++ b/tools/usb/usbip/libsrc/usbip_device_driver.c
@@ -69,7 +69,7 @@ int read_usb_vudc_device(struct udev_device *sdev, struct usbip_usb_device *dev)
 	FILE *fd = NULL;
 	struct udev_device *plat;
 	const char *speed;
-	int ret = 0;
+	size_t ret;
 
 	plat = udev_device_get_parent(sdev);
 	path = udev_device_get_syspath(plat);
@@ -79,8 +79,10 @@ int read_usb_vudc_device(struct udev_device *sdev, struct usbip_usb_device *dev)
 	if (!fd)
 		return -1;
 	ret = fread((char *) &descr, sizeof(descr), 1, fd);
-	if (ret < 0)
+	if (ret != 1) {
+		err("Cannot read vudc device descr file: %s", strerror(errno));
 		goto err;
+	}
 	fclose(fd);
 
 	copy_descr_attr(dev, &descr, bDeviceClass);
diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 362a01886bab..8731dfeced8b 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -8,6 +8,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/uaccess.h>
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
@@ -146,8 +147,7 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 	if (kvm_pmu_pmc_is_chained(pmc) &&
 	    kvm_pmu_idx_is_high_counter(select_idx))
 		counter = upper_32_bits(counter);
-
-	else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -193,7 +193,7 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
  */
 static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
-	u64 counter, reg;
+	u64 counter, reg, val;
 
 	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (!pmc->perf_event)
@@ -201,16 +201,19 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		reg = PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
-		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	if (pmc->idx == ARMV8_PMU_CYCLE_IDX) {
+		reg = PMCCNTR_EL0;
+		val = counter;
 	} else {
-		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		val = lower_32_bits(counter);
 	}
 
+	__vcpu_sys_reg(vcpu, reg) = val;
+
+	if (kvm_pmu_pmc_is_chained(pmc))
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+
 	kvm_pmu_release_perf_event(pmc);
 }
 
@@ -440,8 +443,25 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 				  struct pt_regs *regs)
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	int idx = pmc->idx;
+	u64 period;
+
+	cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE);
+
+	/*
+	 * Reset the sample period to the architectural limit,
+	 * i.e. the point where the counter overflows.
+	 */
+	period = -(local64_read(&perf_event->count));
+
+	if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+		period &= GENMASK(31, 0);
+
+	local64_set(&perf_event->hw.period_left, 0);
+	perf_event->attr.sample_period = period;
+	perf_event->hw.sample_period = period;
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
 
@@ -449,6 +469,8 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 		kvm_vcpu_kick(vcpu);
 	}
+
+	cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
 }
 
 /**
@@ -567,12 +589,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 		 * high counter.
 		 */
 		attr.sample_period = (-counter) & GENMASK(63, 0);
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+
 		event = perf_event_create_kernel_counter(&attr, -1, current,
 							 kvm_pmu_perf_overflow,
 							 pmc + 1);
-
-		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
-			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
 	} else {
 		/* The initial sample period (overflow count) of an event. */
 		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fd68fbe0a75d..d6f0696d98ef 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -627,8 +627,9 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 
 static struct kvm *kvm_create_vm(unsigned long type)
 {
-	int r, i;
 	struct kvm *kvm = kvm_arch_alloc_vm();
+	int r = -ENOMEM;
+	int i;
 
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
@@ -640,44 +641,45 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
-	refcount_set(&kvm->users_count, 1);
 	INIT_LIST_HEAD(&kvm->devices);
 
-	r = kvm_arch_init_vm(kvm, type);
-	if (r)
-		goto out_err_no_disable;
-
-	r = hardware_enable_all();
-	if (r)
-		goto out_err_no_disable;
-
-#ifdef CONFIG_HAVE_KVM_IRQFD
-	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
-#endif
-
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
-	r = -ENOMEM;
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		struct kvm_memslots *slots = kvm_alloc_memslots();
+
 		if (!slots)
-			goto out_err_no_srcu;
+			goto out_err_no_arch_destroy_vm;
 		/* Generations must be different for each address space. */
 		slots->generation = i;
 		rcu_assign_pointer(kvm->memslots[i], slots);
 	}
 
-	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_no_srcu;
-	if (init_srcu_struct(&kvm->irq_srcu))
-		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		rcu_assign_pointer(kvm->buses[i],
 			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
 		if (!kvm->buses[i])
-			goto out_err;
+			goto out_err_no_arch_destroy_vm;
 	}
 
+	refcount_set(&kvm->users_count, 1);
+	r = kvm_arch_init_vm(kvm, type);
+	if (r)
+		goto out_err_no_arch_destroy_vm;
+
+	r = hardware_enable_all();
+	if (r)
+		goto out_err_no_disable;
+
+#ifdef CONFIG_HAVE_KVM_IRQFD
+	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
+#endif
+
+	if (init_srcu_struct(&kvm->srcu))
+		goto out_err_no_srcu;
+	if (init_srcu_struct(&kvm->irq_srcu))
+		goto out_err_no_irq_srcu;
+
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
 		goto out_err;
@@ -697,7 +699,9 @@ out_err_no_irq_srcu:
 out_err_no_srcu:
 	hardware_disable_all();
 out_err_no_disable:
-	refcount_set(&kvm->users_count, 0);
+	kvm_arch_destroy_vm(kvm);
+	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
+out_err_no_arch_destroy_vm:
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm_get_bus(kvm, i));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
@@ -2360,20 +2364,23 @@ out:
 	kvm_arch_vcpu_unblocking(vcpu);
 	block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
 
-	if (!vcpu_valid_wakeup(vcpu))
-		shrink_halt_poll_ns(vcpu);
-	else if (halt_poll_ns) {
-		if (block_ns <= vcpu->halt_poll_ns)
-			;
-		/* we had a long block, shrink polling */
-		else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+	if (!kvm_arch_no_poll(vcpu)) {
+		if (!vcpu_valid_wakeup(vcpu)) {
 			shrink_halt_poll_ns(vcpu);
-		/* we had a short halt and our poll time is too small */
-		else if (vcpu->halt_poll_ns < halt_poll_ns &&
-			block_ns < halt_poll_ns)
-			grow_halt_poll_ns(vcpu);
-	} else
-		vcpu->halt_poll_ns = 0;
+		} else if (halt_poll_ns) {
+			if (block_ns <= vcpu->halt_poll_ns)
+				;
+			/* we had a long block, shrink polling */
+			else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+				shrink_halt_poll_ns(vcpu);
+			/* we had a short halt and our poll time is too small */
+			else if (vcpu->halt_poll_ns < halt_poll_ns &&
+				block_ns < halt_poll_ns)
+				grow_halt_poll_ns(vcpu);
+		} else {
+			vcpu->halt_poll_ns = 0;
+		}
+	}
 
 	trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu));
 	kvm_arch_vcpu_block_finish(vcpu);