Merge tag 'char-misc-5.15-rc1-lkdtm' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull misc driver fix from Greg KH:
 "Here is a single patch for 5.15-rc1, for the lkdtm misc driver.

  It resolves a build issue that many people were hitting with your
  current tree, and Kees and others felt would be good to get merged
  before -rc1 comes out, to prevent them from having to constantly hit
  it as many development trees restart on -rc1, not older -rc releases.

  It has NOT been in linux-next, but has passed 0-day testing and looks
  'obviously correct' when reviewing it locally :)"

* tag 'char-misc-5.15-rc1-lkdtm' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
  lkdtm: Use init_uts_ns.name instead of macros
diff --git a/Documentation/ABI/testing/debugfs-driver-habanalabs b/Documentation/ABI/testing/debugfs-driver-habanalabs
index a5c28f6..284e2df 100644
--- a/Documentation/ABI/testing/debugfs-driver-habanalabs
+++ b/Documentation/ABI/testing/debugfs-driver-habanalabs
@@ -215,6 +215,17 @@
                 "0" means device will be reset in case some CS has timed out,
                 otherwise it will not be reset.
 
+What:           /sys/kernel/debug/habanalabs/hl<n>/state_dump
+Date:           Oct 2021
+KernelVersion:  5.15
+Contact:        ynudelman@habana.ai
+Description:    Gets the state dump occurring on a CS timeout or failure.
+                State dump is used for debug and is created each time in case of
+                a problem in a CS execution, before reset.
+                Reading from the node returns the newest state dump available.
+                Writing an integer X discards X state dumps, so that the
+                next read would return X+1-st newest state dump.
+
 What:           /sys/kernel/debug/habanalabs/hl<n>/stop_on_err
 Date:           Mar 2020
 KernelVersion:  5.6
@@ -230,6 +241,14 @@
                 pointers (user virtual addresses) that are pinned and mapped
                 to DMA addresses
 
+What:           /sys/kernel/debug/habanalabs/hl<n>/userptr_lookup
+Date:           Aug 2021
+KernelVersion:  5.15
+Contact:        ogabbay@kernel.org
+Description:    Allows to search for specific user pointers (user virtual
+                addresses) that are pinned and mapped to DMA addresses, and see
+                their resolution to the specific dma address.
+
 What:           /sys/kernel/debug/habanalabs/hl<n>/vm
 Date:           Jan 2019
 KernelVersion:  5.1
diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 2a7444e..2e71868 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -315,6 +315,9 @@
 .. kernel-doc:: block/genhd.c
    :export:
 
+.. kernel-doc:: block/bdev.c
+   :export:
+
 Char devices
 ============
 
diff --git a/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml b/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml
index 4265399..c851770 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml
+++ b/Documentation/devicetree/bindings/display/msm/dsi-phy-7nm.yaml
@@ -14,10 +14,10 @@
 
 properties:
   compatible:
-    oneOf:
-      - const: qcom,dsi-phy-7nm
-      - const: qcom,dsi-phy-7nm-8150
-      - const: qcom,sc7280-dsi-phy-7nm
+    enum:
+      - qcom,dsi-phy-7nm
+      - qcom,dsi-phy-7nm-8150
+      - qcom,sc7280-dsi-phy-7nm
 
   reg:
     items:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-virtio.yaml b/Documentation/devicetree/bindings/gpio/gpio-virtio.yaml
new file mode 100644
index 0000000..601d857
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/gpio-virtio.yaml
@@ -0,0 +1,59 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/gpio/gpio-virtio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Virtio GPIO controller
+
+maintainers:
+  - Viresh Kumar <viresh.kumar@linaro.org>
+
+allOf:
+  - $ref: /schemas/virtio/virtio-device.yaml#
+
+description:
+  Virtio GPIO controller, see /schemas/virtio/virtio-device.yaml for more
+  details.
+
+properties:
+  $nodename:
+    const: gpio
+
+  compatible:
+    const: virtio,device29
+
+  gpio-controller: true
+
+  "#gpio-cells":
+    const: 2
+
+  interrupt-controller: true
+
+  "#interrupt-cells":
+    const: 2
+
+required:
+  - compatible
+  - gpio-controller
+  - "#gpio-cells"
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    virtio@3000 {
+        compatible = "virtio,mmio";
+        reg = <0x3000 0x100>;
+        interrupts = <41>;
+
+        gpio {
+            compatible = "virtio,device29";
+            gpio-controller;
+            #gpio-cells = <2>;
+            interrupt-controller;
+            #interrupt-cells = <2>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/i2c/i2c-virtio.yaml b/Documentation/devicetree/bindings/i2c/i2c-virtio.yaml
new file mode 100644
index 0000000..7d87ed8
--- /dev/null
+++ b/Documentation/devicetree/bindings/i2c/i2c-virtio.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/i2c/i2c-virtio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Virtio I2C Adapter
+
+maintainers:
+  - Viresh Kumar <viresh.kumar@linaro.org>
+
+allOf:
+  - $ref: /schemas/i2c/i2c-controller.yaml#
+  - $ref: /schemas/virtio/virtio-device.yaml#
+
+description:
+  Virtio I2C device, see /schemas/virtio/virtio-device.yaml for more details.
+
+properties:
+  $nodename:
+    const: i2c
+
+  compatible:
+    const: virtio,device22
+
+required:
+  - compatible
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    virtio@3000 {
+        compatible = "virtio,mmio";
+        reg = <0x3000 0x100>;
+        interrupts = <41>;
+
+        i2c {
+            compatible = "virtio,device22";
+
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            light-sensor@20 {
+                compatible = "dynaimage,al3320a";
+                reg = <0x20>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml b/Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
index cffd020..d74f200 100644
--- a/Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
+++ b/Documentation/devicetree/bindings/input/allwinner,sun4i-a10-lradc-keys.yaml
@@ -29,6 +29,8 @@
     description:
       Regulator for the LRADC reference voltage
 
+  wakeup-source: true
+
 patternProperties:
   "^button-[0-9]+$":
     type: object
diff --git a/Documentation/devicetree/bindings/input/qcom,pm8941-pwrkey.txt b/Documentation/devicetree/bindings/input/qcom,pm8941-pwrkey.txt
deleted file mode 100644
index 6cd08bc..0000000
--- a/Documentation/devicetree/bindings/input/qcom,pm8941-pwrkey.txt
+++ /dev/null
@@ -1,55 +0,0 @@
-Qualcomm PM8941 PMIC Power Key
-
-PROPERTIES
-
-- compatible:
-	Usage: required
-	Value type: <string>
-	Definition: must be one of:
-		    "qcom,pm8941-pwrkey"
-		    "qcom,pm8941-resin"
-		    "qcom,pmk8350-pwrkey"
-		    "qcom,pmk8350-resin"
-
-- reg:
-	Usage: required
-	Value type: <prop-encoded-array>
-	Definition: base address of registers for block
-
-- interrupts:
-	Usage: required
-	Value type: <prop-encoded-array>
-	Definition: key change interrupt; The format of the specifier is
-		    defined by the binding document describing the node's
-		    interrupt parent.
-
-- debounce:
-	Usage: optional
-	Value type: <u32>
-	Definition: time in microseconds that key must be pressed or released
-		    for state change interrupt to trigger.
-
-- bias-pull-up:
-	Usage: optional
-	Value type: <empty>
-	Definition: presence of this property indicates that the KPDPWR_N pin
-		    should be configured for pull up.
-
-- linux,code:
-	Usage: optional
-	Value type: <u32>
-	Definition: The input key-code associated with the power key.
-		    Use the linux event codes defined in
-		    include/dt-bindings/input/linux-event-codes.h
-		    When property is omitted KEY_POWER is assumed.
-
-EXAMPLE
-
-	pwrkey@800 {
-		compatible = "qcom,pm8941-pwrkey";
-		reg = <0x800>;
-		interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
-		debounce = <15625>;
-		bias-pull-up;
-		linux,code = <KEY_POWER>;
-	};
diff --git a/Documentation/devicetree/bindings/input/qcom,pm8941-pwrkey.yaml b/Documentation/devicetree/bindings/input/qcom,pm8941-pwrkey.yaml
new file mode 100644
index 0000000..62314a5
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/qcom,pm8941-pwrkey.yaml
@@ -0,0 +1,51 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/qcom,pm8941-pwrkey.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm PM8941 PMIC Power Key
+
+maintainers:
+  - Courtney Cavin <courtney.cavin@sonymobile.com>
+  - Vinod Koul <vkoul@kernel.org>
+
+allOf:
+  - $ref: input.yaml#
+
+properties:
+  compatible:
+    enum:
+      - qcom,pm8941-pwrkey
+      - qcom,pm8941-resin
+      - qcom,pmk8350-pwrkey
+      - qcom,pmk8350-resin
+
+  interrupts:
+    maxItems: 1
+
+  debounce:
+    description: |
+          Time in microseconds that key must be pressed or
+          released for state change interrupt to trigger.
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  bias-pull-up:
+    description: |
+           Presence of this property indicates that the KPDPWR_N
+           pin should be configured for pull up.
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  linux,code:
+    description: |
+           The input key-code associated with the power key.
+           Use the linux event codes defined in
+           include/dt-bindings/input/linux-event-codes.h
+           When property is omitted KEY_POWER is assumed.
+
+required:
+  - compatible
+  - interrupts
+
+unevaluatedProperties: false
+...
diff --git a/Documentation/devicetree/bindings/input/regulator-haptic.txt b/Documentation/devicetree/bindings/input/regulator-haptic.txt
deleted file mode 100644
index 3ed1c7e..0000000
--- a/Documentation/devicetree/bindings/input/regulator-haptic.txt
+++ /dev/null
@@ -1,21 +0,0 @@
-* Regulator Haptic Device Tree Bindings
-
-Required Properties:
- - compatible : Should be "regulator-haptic"
- - haptic-supply : Power supply to the haptic motor.
-	[*] refer Documentation/devicetree/bindings/regulator/regulator.txt
-
- - max-microvolt : The maximum voltage value supplied to the haptic motor.
-		[The unit of the voltage is a micro]
-
- - min-microvolt : The minimum voltage value supplied to the haptic motor.
-		[The unit of the voltage is a micro]
-
-Example:
-
-	haptics {
-		compatible = "regulator-haptic";
-		haptic-supply = <&motor_regulator>;
-		max-microvolt = <2700000>;
-		min-microvolt = <1100000>;
-	};
diff --git a/Documentation/devicetree/bindings/input/regulator-haptic.yaml b/Documentation/devicetree/bindings/input/regulator-haptic.yaml
new file mode 100644
index 0000000..b1ae72f
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/regulator-haptic.yaml
@@ -0,0 +1,43 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: "http://devicetree.org/schemas/input/regulator-haptic.yaml#"
+$schema: "http://devicetree.org/meta-schemas/core.yaml#"
+
+title: Regulator Haptic Device Tree Bindings
+
+maintainers:
+  - Jaewon Kim <jaewon02.kim@samsung.com>
+
+properties:
+  compatible:
+    const: regulator-haptic
+
+  haptic-supply:
+    description: >
+      Power supply to the haptic motor
+
+  max-microvolt:
+    description: >
+      The maximum voltage value supplied to the haptic motor
+
+  min-microvolt:
+    description: >
+      The minimum voltage value supplied to the haptic motor
+
+required:
+  - compatible
+  - haptic-supply
+  - max-microvolt
+  - min-microvolt
+
+additionalProperties: false
+
+examples:
+  - |
+    haptics {
+        compatible = "regulator-haptic";
+        haptic-supply = <&motor_regulator>;
+        max-microvolt = <2700000>;
+        min-microvolt = <1100000>;
+    };
diff --git a/Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml b/Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml
new file mode 100644
index 0000000..9df685b
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/chipone,icn8318.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/chipone,icn8318.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ChipOne ICN8318 Touchscreen Controller Device Tree Bindings
+
+maintainers:
+  - Dmitry Torokhov <dmitry.torokhov@gmail.com>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    const: chipone,icn8318
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  wake-gpios:
+    maxItems: 1
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - wake-gpios
+  - touchscreen-size-x
+  - touchscreen-size-y
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        touchscreen@40 {
+            compatible = "chipone,icn8318";
+            reg = <0x40>;
+            interrupt-parent = <&pio>;
+            interrupts = <9 IRQ_TYPE_EDGE_FALLING>; /* EINT9 (PG9) */
+            pinctrl-names = "default";
+            pinctrl-0 = <&ts_wake_pin_p66>;
+            wake-gpios = <&pio 1 3 GPIO_ACTIVE_HIGH>; /* PB3 */
+            touchscreen-size-x = <800>;
+            touchscreen-size-y = <480>;
+            touchscreen-inverted-x;
+            touchscreen-swapped-x-y;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt b/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
deleted file mode 100644
index 38b0603..0000000
--- a/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
+++ /dev/null
@@ -1,44 +0,0 @@
-* ChipOne icn8318 I2C touchscreen controller
-
-Required properties:
- - compatible		  : "chipone,icn8318"
- - reg			  : I2C slave address of the chip (0x40)
- - interrupts		  : interrupt specification for the icn8318 interrupt
- - wake-gpios		  : GPIO specification for the WAKE input
- - touchscreen-size-x	  : horizontal resolution of touchscreen (in pixels)
- - touchscreen-size-y	  : vertical resolution of touchscreen (in pixels)
-
-Optional properties:
- - pinctrl-names	  : should be "default"
- - pinctrl-0:		  : a phandle pointing to the pin settings for the
-			    control gpios
- - touchscreen-fuzz-x	  : horizontal noise value of the absolute input
-			    device (in pixels)
- - touchscreen-fuzz-y	  : vertical noise value of the absolute input
-			    device (in pixels)
- - touchscreen-inverted-x : X axis is inverted (boolean)
- - touchscreen-inverted-y : Y axis is inverted (boolean)
- - touchscreen-swapped-x-y	  : X and Y axis are swapped (boolean)
-			    Swapping is done after inverting the axis
-
-Example:
-
-i2c@00000000 {
-	/* ... */
-
-	chipone_icn8318@40 {
-		compatible = "chipone,icn8318";
-		reg = <0x40>;
-		interrupt-parent = <&pio>;
-		interrupts = <9 IRQ_TYPE_EDGE_FALLING>; /* EINT9 (PG9) */
-		pinctrl-names = "default";
-		pinctrl-0 = <&ts_wake_pin_p66>;
-		wake-gpios = <&pio 1 3 GPIO_ACTIVE_HIGH>; /* PB3 */
-		touchscreen-size-x = <800>;
-		touchscreen-size-y = <480>;
-		touchscreen-inverted-x;
-		touchscreen-swapped-x-y;
-	};
-
-	/* ... */
-};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/pixcir,pixcir_ts.yaml b/Documentation/devicetree/bindings/input/touchscreen/pixcir,pixcir_ts.yaml
new file mode 100644
index 0000000..f9998ed
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/pixcir,pixcir_ts.yaml
@@ -0,0 +1,68 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/pixcir,pixcir_ts.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Pixcir Touchscreen Controller Device Tree Bindings
+
+maintainers:
+  - Dmitry Torokhov <dmitry.torokhov@gmail.com>
+
+allOf:
+  - $ref: touchscreen.yaml#
+
+properties:
+  compatible:
+    enum:
+      - pixcir,pixcir_ts
+      - pixcir,pixcir_tangoc
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  attb-gpio:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+
+  enable-gpios:
+    maxItems: 1
+
+  wake-gpios:
+    maxItems: 1
+
+unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - attb-gpio
+  - touchscreen-size-x
+  - touchscreen-size-y
+
+examples:
+  - |
+    #include <dt-bindings/gpio/gpio.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        touchscreen@5c {
+            compatible = "pixcir,pixcir_ts";
+            reg = <0x5c>;
+            interrupts = <2 0>;
+            attb-gpio = <&gpf 2 0 2>;
+            touchscreen-size-x = <800>;
+            touchscreen-size-y = <600>;
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt b/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
deleted file mode 100644
index 697a3e7..0000000
--- a/Documentation/devicetree/bindings/input/touchscreen/pixcir_i2c_ts.txt
+++ /dev/null
@@ -1,31 +0,0 @@
-* Pixcir I2C touchscreen controllers
-
-Required properties:
-- compatible: must be "pixcir,pixcir_ts" or "pixcir,pixcir_tangoc"
-- reg: I2C address of the chip
-- interrupts: interrupt to which the chip is connected
-- attb-gpio: GPIO connected to the ATTB line of the chip
-- touchscreen-size-x: horizontal resolution of touchscreen (in pixels)
-- touchscreen-size-y: vertical resolution of touchscreen (in pixels)
-
-Optional properties:
-- reset-gpios: GPIO connected to the RESET line of the chip
-- enable-gpios: GPIO connected to the ENABLE line of the chip
-- wake-gpios: GPIO connected to the WAKE line of the chip
-
-Example:
-
-	i2c@00000000 {
-		/* ... */
-
-		pixcir_ts@5c {
-			compatible = "pixcir,pixcir_ts";
-			reg = <0x5c>;
-			interrupts = <2 0>;
-			attb-gpio = <&gpf 2 0 2>;
-			touchscreen-size-x = <800>;
-			touchscreen-size-y = <600>;
-		};
-
-		/* ... */
-	};
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ti,tsc2005.yaml b/Documentation/devicetree/bindings/input/touchscreen/ti,tsc2005.yaml
new file mode 100644
index 0000000..938aab0
--- /dev/null
+++ b/Documentation/devicetree/bindings/input/touchscreen/ti,tsc2005.yaml
@@ -0,0 +1,128 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/input/touchscreen/ti,tsc2005.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Texas Instruments TSC2004 and TSC2005 touchscreen controller bindings
+
+maintainers:
+  - Marek Vasut <marex@denx.de>
+  - Michael Welling <mwelling@ieee.org>
+
+properties:
+  $nodename:
+    pattern: "^touchscreen(@.*)?$"
+
+  compatible:
+    enum:
+      - ti,tsc2004
+      - ti,tsc2005
+
+  reg:
+    maxItems: 1
+    description: |
+      I2C address when used on the I2C bus, or the SPI chip select index
+      when used on the SPI bus
+
+  interrupts:
+    maxItems: 1
+
+  reset-gpios:
+    maxItems: 1
+    description: GPIO specifier for the controller reset line
+
+  spi-max-frequency:
+    description: TSC2005 SPI bus clock frequency.
+    maximum: 25000000
+
+  ti,x-plate-ohms:
+    description: resistance of the touchscreen's X plates in ohm (defaults to 280)
+
+  ti,esd-recovery-timeout-ms:
+    description: |
+        if the touchscreen does not respond after the configured time
+        (in milli seconds), the driver will reset it. This is disabled
+        by default.
+
+  vio-supply:
+    description: Regulator specifier
+
+  touchscreen-fuzz-pressure: true
+  touchscreen-fuzz-x: true
+  touchscreen-fuzz-y: true
+  touchscreen-max-pressure: true
+  touchscreen-size-x: true
+  touchscreen-size-y: true
+
+allOf:
+  - $ref: touchscreen.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ti,tsc2004
+    then:
+      properties:
+        spi-max-frequency: false
+
+additionalProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/gpio/gpio.h>
+    i2c {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        touchscreen@48 {
+            compatible = "ti,tsc2004";
+            reg = <0x48>;
+            vio-supply = <&vio>;
+
+            reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>;
+            interrupts-extended = <&gpio1 27 IRQ_TYPE_EDGE_RISING>;
+
+            touchscreen-fuzz-x = <4>;
+            touchscreen-fuzz-y = <7>;
+            touchscreen-fuzz-pressure = <2>;
+            touchscreen-size-x = <4096>;
+            touchscreen-size-y = <4096>;
+            touchscreen-max-pressure = <2048>;
+
+            ti,x-plate-ohms = <280>;
+            ti,esd-recovery-timeout-ms = <8000>;
+        };
+    };
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/gpio/gpio.h>
+    spi {
+        #address-cells = <1>;
+        #size-cells = <0>;
+        touchscreen@0 {
+            compatible = "ti,tsc2005";
+            spi-max-frequency = <6000000>;
+            reg = <0>;
+
+            vio-supply = <&vio>;
+
+            reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; /* 104 */
+            interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>; /* 100 */
+
+            touchscreen-fuzz-x = <4>;
+            touchscreen-fuzz-y = <7>;
+            touchscreen-fuzz-pressure = <2>;
+            touchscreen-size-x = <4096>;
+            touchscreen-size-y = <4096>;
+            touchscreen-max-pressure = <2048>;
+
+            ti,x-plate-ohms = <280>;
+            ti,esd-recovery-timeout-ms = <8000>;
+        };
+    };
diff --git a/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt b/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
deleted file mode 100644
index b80c04b..0000000
--- a/Documentation/devicetree/bindings/input/touchscreen/tsc2005.txt
+++ /dev/null
@@ -1,64 +0,0 @@
-* Texas Instruments tsc2004 and tsc2005 touchscreen controllers
-
-Required properties:
- - compatible		      : "ti,tsc2004" or "ti,tsc2005"
- - reg			      : Device address
- - interrupts		      : IRQ specifier
- - spi-max-frequency	      : Maximum SPI clocking speed of the device
-			        (for tsc2005)
-
-Optional properties:
- - vio-supply		      : Regulator specifier
- - reset-gpios		      : GPIO specifier for the controller reset line
- - ti,x-plate-ohms	      : integer, resistance of the touchscreen's X plates
-				in ohm (defaults to 280)
- - ti,esd-recovery-timeout-ms : integer, if the touchscreen does not respond after
-				the configured time (in milli seconds), the driver
-				will reset it. This is disabled by default.
- - properties defined in touchscreen.txt
-
-Example:
-
-&i2c3 {
-	tsc2004@48 {
-		compatible = "ti,tsc2004";
-		reg = <0x48>;
-		vio-supply = <&vio>;
-
-		reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>;
-		interrupts-extended = <&gpio1 27 IRQ_TYPE_EDGE_RISING>;
-
-		touchscreen-fuzz-x = <4>;
-		touchscreen-fuzz-y = <7>;
-		touchscreen-fuzz-pressure = <2>;
-		touchscreen-size-x = <4096>;
-		touchscreen-size-y = <4096>;
-		touchscreen-max-pressure = <2048>;
-
-		ti,x-plate-ohms = <280>;
-		ti,esd-recovery-timeout-ms = <8000>;
-	};
-}
-
-&mcspi1 {
-	tsc2005@0 {
-		compatible = "ti,tsc2005";
-		spi-max-frequency = <6000000>;
-		reg = <0>;
-
-		vio-supply = <&vio>;
-
-		reset-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; /* 104 */
-		interrupts-extended = <&gpio4 4 IRQ_TYPE_EDGE_RISING>; /* 100 */
-
-		touchscreen-fuzz-x = <4>;
-		touchscreen-fuzz-y = <7>;
-		touchscreen-fuzz-pressure = <2>;
-		touchscreen-size-x = <4096>;
-		touchscreen-size-y = <4096>;
-		touchscreen-max-pressure = <2048>;
-
-		ti,x-plate-ohms = <280>;
-		ti,esd-recovery-timeout-ms = <8000>;
-	};
-}
diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.txt b/Documentation/devicetree/bindings/power/reset/qcom,pon.txt
deleted file mode 100644
index 0c0dc3a..0000000
--- a/Documentation/devicetree/bindings/power/reset/qcom,pon.txt
+++ /dev/null
@@ -1,49 +0,0 @@
-Qualcomm PON Device
-
-The Power On device for Qualcomm PM8xxx is MFD supporting pwrkey
-and resin along with the Android reboot-mode.
-
-This DT node has pwrkey and resin as sub nodes.
-
-Required Properties:
--compatible: Must be one of:
-	"qcom,pm8916-pon"
-	"qcom,pms405-pon"
-	"qcom,pm8998-pon"
-
--reg: Specifies the physical address of the pon register
-
-Optional subnode:
--pwrkey: Specifies the subnode pwrkey and should follow the
- qcom,pm8941-pwrkey.txt description.
--resin: Specifies the subnode resin and should follow the
- qcom,pm8xxx-pwrkey.txt description.
-
-The rest of the properties should follow the generic reboot-mode description
-found in reboot-mode.txt
-
-Example:
-
-	pon@800 {
-		compatible = "qcom,pm8916-pon";
-
-		reg = <0x800>;
-		mode-bootloader = <0x2>;
-		mode-recovery = <0x1>;
-
-		pwrkey {
-			compatible = "qcom,pm8941-pwrkey";
-			interrupts = <0x0 0x8 0 IRQ_TYPE_EDGE_BOTH>;
-			debounce = <15625>;
-			bias-pull-up;
-			linux,code = <KEY_POWER>;
-		};
-
-		resin {
-			compatible = "qcom,pm8941-resin";
-			interrupts = <0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>;
-			debounce = <15625>;
-			bias-pull-up;
-			linux,code = <KEY_VOLUMEDOWN>;
-		};
-	};
diff --git a/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
new file mode 100644
index 0000000..353f155
--- /dev/null
+++ b/Documentation/devicetree/bindings/power/reset/qcom,pon.yaml
@@ -0,0 +1,80 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/power/reset/qcom,pon.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm PON Device
+
+maintainers:
+  - Vinod Koul <vkoul@kernel.org>
+
+description: |
+  The Power On device for Qualcomm PM8xxx is MFD supporting pwrkey
+  and resin along with the Android reboot-mode.
+
+  This DT node has pwrkey and resin as sub nodes.
+
+allOf:
+  - $ref: reboot-mode.yaml#
+
+properties:
+  compatible:
+    enum:
+      - qcom,pm8916-pon
+      - qcom,pms405-pon
+      - qcom,pm8998-pon
+
+  reg:
+    maxItems: 1
+
+  pwrkey:
+    type: object
+    $ref: "../../input/qcom,pm8941-pwrkey.yaml#"
+
+  resin:
+    type: object
+    $ref: "../../input/qcom,pm8941-pwrkey.yaml#"
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+   #include <dt-bindings/interrupt-controller/irq.h>
+   #include <dt-bindings/input/linux-event-codes.h>
+   #include <dt-bindings/spmi/spmi.h>
+   spmi_bus: spmi@c440000 {
+     reg = <0x0c440000 0x1100>;
+     #address-cells = <2>;
+     #size-cells = <0>;
+     pmk8350: pmic@0 {
+       reg = <0x0 SPMI_USID>;
+       #address-cells = <1>;
+       #size-cells = <0>;
+       pmk8350_pon: pon_hlos@1300 {
+         reg = <0x1300>;
+         compatible = "qcom,pm8998-pon";
+
+         pwrkey {
+            compatible = "qcom,pm8941-pwrkey";
+            interrupts = < 0x0 0x8 0 IRQ_TYPE_EDGE_BOTH >;
+            debounce = <15625>;
+            bias-pull-up;
+            linux,code = <KEY_POWER>;
+         };
+
+         resin {
+            compatible = "qcom,pm8941-resin";
+            interrupts = <0x0 0x8 1 IRQ_TYPE_EDGE_BOTH>;
+            debounce = <15625>;
+            bias-pull-up;
+            linux,code = <KEY_VOLUMEDOWN>;
+         };
+       };
+     };
+   };
+...
diff --git a/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml b/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
index 9c6fda6..ad0a0b95 100644
--- a/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
+++ b/Documentation/devicetree/bindings/power/reset/reboot-mode.yaml
@@ -36,7 +36,7 @@
   "^mode-.*$":
     $ref: /schemas/types.yaml#/definitions/uint32
 
-additionalProperties: false
+additionalProperties: true
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/pwm/pwm-rockchip.yaml b/Documentation/devicetree/bindings/pwm/pwm-rockchip.yaml
index 5596bee..81a54a4 100644
--- a/Documentation/devicetree/bindings/pwm/pwm-rockchip.yaml
+++ b/Documentation/devicetree/bindings/pwm/pwm-rockchip.yaml
@@ -29,6 +29,7 @@
           - enum:
               - rockchip,px30-pwm
               - rockchip,rk3308-pwm
+              - rockchip,rk3568-pwm
           - const: rockchip,rk3328-pwm
 
   reg:
diff --git a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
index 7548d87..13925bb7 100644
--- a/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
+++ b/Documentation/devicetree/bindings/rtc/trivial-rtc.yaml
@@ -32,6 +32,9 @@
       - dallas,ds3232
       # I2C-BUS INTERFACE REAL TIME CLOCK MODULE
       - epson,rx8010
+      # I2C-BUS INTERFACE REAL TIME CLOCK MODULE
+      - epson,rx8025
+      - epson,rx8035
       # I2C-BUS INTERFACE REAL TIME CLOCK MODULE with Battery Backed RAM
       - epson,rx8571
       # I2C-BUS INTERFACE REAL TIME CLOCK MODULE
diff --git a/Documentation/devicetree/bindings/spi/omap-spi.yaml b/Documentation/devicetree/bindings/spi/omap-spi.yaml
index e555381..9952199 100644
--- a/Documentation/devicetree/bindings/spi/omap-spi.yaml
+++ b/Documentation/devicetree/bindings/spi/omap-spi.yaml
@@ -84,9 +84,9 @@
 if:
   properties:
     compatible:
-      oneOf:
-        - const: ti,omap2-mcspi
-        - const: ti,omap4-mcspi
+      enum:
+        - ti,omap2-mcspi
+        - ti,omap4-mcspi
 
 then:
   properties:
diff --git a/Documentation/devicetree/bindings/spi/spi-xilinx.yaml b/Documentation/devicetree/bindings/spi/spi-xilinx.yaml
index 593f769..03e5dca 100644
--- a/Documentation/devicetree/bindings/spi/spi-xilinx.yaml
+++ b/Documentation/devicetree/bindings/spi/spi-xilinx.yaml
@@ -27,13 +27,11 @@
 
   xlnx,num-ss-bits:
     description: Number of chip selects used.
-    $ref: /schemas/types.yaml#/definitions/uint32
     minimum: 1
     maximum: 32
 
   xlnx,num-transfer-bits:
     description: Number of bits per transfer. This will be 8 if not specified.
-    $ref: /schemas/types.yaml#/definitions/uint32
     enum: [8, 16, 32]
     default: 8
 
diff --git a/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml b/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml
new file mode 100644
index 0000000..289e9a8
--- /dev/null
+++ b/Documentation/devicetree/bindings/thermal/qcom-lmh.yaml
@@ -0,0 +1,82 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+# Copyright 2021 Linaro Ltd.
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/thermal/qcom-lmh.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Limits Management Hardware(LMh)
+
+maintainers:
+  - Thara Gopinath <thara.gopinath@linaro.org>
+
+description:
+  Limits Management Hardware(LMh) is a hardware infrastructure on some
+  Qualcomm SoCs that can enforce temperature and current limits as
+  programmed by software for certain IPs like CPU.
+
+properties:
+  compatible:
+    enum:
+      - qcom,sdm845-lmh
+
+  reg:
+    items:
+      - description: core registers
+
+  interrupts:
+    maxItems: 1
+
+  '#interrupt-cells':
+    const: 1
+
+  interrupt-controller: true
+
+  cpus:
+    description:
+      phandle of the first cpu in the LMh cluster
+    $ref: /schemas/types.yaml#/definitions/phandle
+
+  qcom,lmh-temp-arm-millicelsius:
+    description:
+      An integer expressing temperature threshold at which the LMh thermal
+      FSM is engaged.
+
+  qcom,lmh-temp-low-millicelsius:
+    description:
+      An integer expressing temperature threshold at which the state machine
+      will attempt to remove frequency throttling.
+
+  qcom,lmh-temp-high-millicelsius:
+    description:
+      An integer expressing temperature threshold at which the state machine
+      will attempt to throttle the frequency.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - '#interrupt-cells'
+  - interrupt-controller
+  - cpus
+  - qcom,lmh-temp-arm-millicelsius
+  - qcom,lmh-temp-low-millicelsius
+  - qcom,lmh-temp-high-millicelsius
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    lmh@17d70800 {
+      compatible = "qcom,sdm845-lmh";
+      reg = <0x17d70800 0x400>;
+      interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
+      cpus = <&CPU4>;
+      qcom,lmh-temp-arm-millicelsius = <65000>;
+      qcom,lmh-temp-low-millicelsius = <94500>;
+      qcom,lmh-temp-high-millicelsius = <95000>;
+      interrupt-controller;
+      #interrupt-cells = <1>;
+    };
diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
index 164f715..a07de5e 100644
--- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
+++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
@@ -215,7 +215,7 @@
       - polling-delay
       - polling-delay-passive
       - thermal-sensors
-      - trips
+
     additionalProperties: false
 
 additionalProperties: false
diff --git a/Documentation/devicetree/bindings/virtio/mmio.yaml b/Documentation/devicetree/bindings/virtio/mmio.yaml
index d465970..4b7a027 100644
--- a/Documentation/devicetree/bindings/virtio/mmio.yaml
+++ b/Documentation/devicetree/bindings/virtio/mmio.yaml
@@ -36,7 +36,8 @@
   - reg
   - interrupts
 
-additionalProperties: false
+additionalProperties:
+  type: object
 
 examples:
   - |
diff --git a/Documentation/devicetree/bindings/virtio/virtio-device.yaml b/Documentation/devicetree/bindings/virtio/virtio-device.yaml
new file mode 100644
index 0000000..1778ea9
--- /dev/null
+++ b/Documentation/devicetree/bindings/virtio/virtio-device.yaml
@@ -0,0 +1,41 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/virtio/virtio-device.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Virtio device bindings
+
+maintainers:
+  - Viresh Kumar <viresh.kumar@linaro.org>
+
+description:
+  These bindings are applicable to virtio devices irrespective of the bus they
+  are bound to, like mmio or pci.
+
+# We need a select here so we don't match all nodes with 'virtio,mmio'
+properties:
+  compatible:
+    pattern: "^virtio,device[0-9a-f]{1,8}$"
+    description: Virtio device nodes.
+      "virtio,deviceID", where ID is the virtio device id. The textual
+      representation of ID shall be in lower case hexadecimal with leading
+      zeroes suppressed.
+
+required:
+  - compatible
+
+additionalProperties: true
+
+examples:
+  - |
+    virtio@3000 {
+        compatible = "virtio,mmio";
+        reg = <0x3000 0x100>;
+        interrupts = <43>;
+
+        i2c {
+            compatible = "virtio,device22";
+        };
+    };
+...
diff --git a/Documentation/devicetree/bindings/watchdog/maxim,max63xx.yaml b/Documentation/devicetree/bindings/watchdog/maxim,max63xx.yaml
index f2105ee..ab9641e 100644
--- a/Documentation/devicetree/bindings/watchdog/maxim,max63xx.yaml
+++ b/Documentation/devicetree/bindings/watchdog/maxim,max63xx.yaml
@@ -15,13 +15,13 @@
 
 properties:
   compatible:
-    oneOf:
-      - const: maxim,max6369
-      - const: maxim,max6370
-      - const: maxim,max6371
-      - const: maxim,max6372
-      - const: maxim,max6373
-      - const: maxim,max6374
+    enum:
+      - maxim,max6369
+      - maxim,max6370
+      - maxim,max6371
+      - maxim,max6372
+      - maxim,max6373
+      - maxim,max6374
 
   reg:
     description: This is a 1-byte memory-mapped address
diff --git a/Documentation/features/vm/ELF-ASLR/arch-support.txt b/Documentation/features/vm/ELF-ASLR/arch-support.txt
index 99cb6d7..2949c99 100644
--- a/Documentation/features/vm/ELF-ASLR/arch-support.txt
+++ b/Documentation/features/vm/ELF-ASLR/arch-support.txt
@@ -22,7 +22,7 @@
     |    openrisc: | TODO |
     |      parisc: |  ok  |
     |     powerpc: |  ok  |
-    |       riscv: | TODO |
+    |       riscv: |  ok  |
     |        s390: |  ok  |
     |          sh: | TODO |
     |       sparc: | TODO |
diff --git a/Documentation/filesystems/api-summary.rst b/Documentation/filesystems/api-summary.rst
index 7e5c04c..98db2ea 100644
--- a/Documentation/filesystems/api-summary.rst
+++ b/Documentation/filesystems/api-summary.rst
@@ -71,9 +71,6 @@
 .. kernel-doc:: fs/fs-writeback.c
    :export:
 
-.. kernel-doc:: fs/block_dev.c
-   :export:
-
 .. kernel-doc:: fs/anon_inodes.c
    :export:
 
diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index d5a73fa..8126bea 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -37,7 +37,7 @@
     This section is outdated.
 
 Drivers wishing to support TTM must pass a filled :c:type:`ttm_bo_driver
-<ttm_bo_driver>` structure to ttm_bo_device_init, together with an
+<ttm_bo_driver>` structure to ttm_device_init, together with an
 initialized global reference to the memory manager.  The ttm_bo_driver
 structure contains several fields with function pointers for
 initializing the TTM, allocating and freeing memory, waiting for command
diff --git a/Documentation/power/energy-model.rst b/Documentation/power/energy-model.rst
index 60ac091..8a2788a 100644
--- a/Documentation/power/energy-model.rst
+++ b/Documentation/power/energy-model.rst
@@ -101,8 +101,7 @@
 the same scale. If there are different scales, these subsystems might decide
 to: return warning/error, stop working or panic.
 See Section 3. for an example of driver implementing this
-callback, and kernel/power/energy_model.c for further documentation on this
-API.
+callback, or Section 2.4 for further documentation on this API
 
 
 2.3 Accessing performance domains
@@ -123,7 +122,17 @@
 CPUfreq governor is in use in case of CPU device. Currently this calculation is
 not provided for other type of devices.
 
-More details about the above APIs can be found in include/linux/energy_model.h.
+More details about the above APIs can be found in ``<linux/energy_model.h>``
+or in Section 2.4
+
+
+2.4 Description details of this API
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+.. kernel-doc:: include/linux/energy_model.h
+   :internal:
+
+.. kernel-doc:: kernel/power/energy_model.c
+   :export:
 
 
 3. Example driver
diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst
index 0b5eefe..c432be0 100644
--- a/Documentation/userspace-api/index.rst
+++ b/Documentation/userspace-api/index.rst
@@ -27,6 +27,7 @@
    iommu
    media/index
    sysfs-platform_profile
+   vduse
 
 .. only::  subproject and html
 
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index b7070d7..2e81340 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -299,6 +299,7 @@
 'z'   10-4F  drivers/s390/crypto/zcrypt_api.h                        conflict!
 '|'   00-7F  linux/media.h
 0x80  00-1F  linux/fb.h
+0x81  00-1F  linux/vduse.h
 0x89  00-06  arch/x86/include/asm/sockios.h
 0x89  0B-DF  linux/sockios.h
 0x89  E0-EF  linux/sockios.h                                         SIOCPROTOPRIVATE range
diff --git a/Documentation/userspace-api/vduse.rst b/Documentation/userspace-api/vduse.rst
new file mode 100644
index 0000000..42ef59e
--- /dev/null
+++ b/Documentation/userspace-api/vduse.rst
@@ -0,0 +1,233 @@
+==================================
+VDUSE - "vDPA Device in Userspace"
+==================================
+
+vDPA (virtio data path acceleration) device is a device that uses a
+datapath which complies with the virtio specifications with vendor
+specific control path. vDPA devices can be both physically located on
+the hardware or emulated by software. VDUSE is a framework that makes it
+possible to implement software-emulated vDPA devices in userspace. And
+to make the device emulation more secure, the emulated vDPA device's
+control path is handled in the kernel and only the data path is
+implemented in the userspace.
+
+Note that only virtio block device is supported by VDUSE framework now,
+which can reduce security risks when the userspace process that implements
+the data path is run by an unprivileged user. The support for other device
+types can be added after the security issue of corresponding device driver
+is clarified or fixed in the future.
+
+Create/Destroy VDUSE devices
+------------------------
+
+VDUSE devices are created as follows:
+
+1. Create a new VDUSE instance with ioctl(VDUSE_CREATE_DEV) on
+   /dev/vduse/control.
+
+2. Setup each virtqueue with ioctl(VDUSE_VQ_SETUP) on /dev/vduse/$NAME.
+
+3. Begin processing VDUSE messages from /dev/vduse/$NAME. The first
+   messages will arrive while attaching the VDUSE instance to vDPA bus.
+
+4. Send the VDPA_CMD_DEV_NEW netlink message to attach the VDUSE
+   instance to vDPA bus.
+
+VDUSE devices are destroyed as follows:
+
+1. Send the VDPA_CMD_DEV_DEL netlink message to detach the VDUSE
+   instance from vDPA bus.
+
+2. Close the file descriptor referring to /dev/vduse/$NAME.
+
+3. Destroy the VDUSE instance with ioctl(VDUSE_DESTROY_DEV) on
+   /dev/vduse/control.
+
+The netlink messages can be sent via vdpa tool in iproute2 or use the
+below sample codes:
+
+.. code-block:: c
+
+	static int netlink_add_vduse(const char *name, enum vdpa_command cmd)
+	{
+		struct nl_sock *nlsock;
+		struct nl_msg *msg;
+		int famid;
+
+		nlsock = nl_socket_alloc();
+		if (!nlsock)
+			return -ENOMEM;
+
+		if (genl_connect(nlsock))
+			goto free_sock;
+
+		famid = genl_ctrl_resolve(nlsock, VDPA_GENL_NAME);
+		if (famid < 0)
+			goto close_sock;
+
+		msg = nlmsg_alloc();
+		if (!msg)
+			goto close_sock;
+
+		if (!genlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, famid, 0, 0, cmd, 0))
+			goto nla_put_failure;
+
+		NLA_PUT_STRING(msg, VDPA_ATTR_DEV_NAME, name);
+		if (cmd == VDPA_CMD_DEV_NEW)
+			NLA_PUT_STRING(msg, VDPA_ATTR_MGMTDEV_DEV_NAME, "vduse");
+
+		if (nl_send_sync(nlsock, msg))
+			goto close_sock;
+
+		nl_close(nlsock);
+		nl_socket_free(nlsock);
+
+		return 0;
+	nla_put_failure:
+		nlmsg_free(msg);
+	close_sock:
+		nl_close(nlsock);
+	free_sock:
+		nl_socket_free(nlsock);
+		return -1;
+	}
+
+How VDUSE works
+---------------
+
+As mentioned above, a VDUSE device is created by ioctl(VDUSE_CREATE_DEV) on
+/dev/vduse/control. With this ioctl, userspace can specify some basic configuration
+such as device name (uniquely identify a VDUSE device), virtio features, virtio
+configuration space, the number of virtqueues and so on for this emulated device.
+Then a char device interface (/dev/vduse/$NAME) is exported to userspace for device
+emulation. Userspace can use the VDUSE_VQ_SETUP ioctl on /dev/vduse/$NAME to
+add per-virtqueue configuration such as the max size of virtqueue to the device.
+
+After the initialization, the VDUSE device can be attached to vDPA bus via
+the VDPA_CMD_DEV_NEW netlink message. Userspace needs to read()/write() on
+/dev/vduse/$NAME to receive/reply some control messages from/to VDUSE kernel
+module as follows:
+
+.. code-block:: c
+
+	static int vduse_message_handler(int dev_fd)
+	{
+		int len;
+		struct vduse_dev_request req;
+		struct vduse_dev_response resp;
+
+		len = read(dev_fd, &req, sizeof(req));
+		if (len != sizeof(req))
+			return -1;
+
+		resp.request_id = req.request_id;
+
+		switch (req.type) {
+
+		/* handle different types of messages */
+
+		}
+
+		len = write(dev_fd, &resp, sizeof(resp));
+		if (len != sizeof(resp))
+			return -1;
+
+		return 0;
+	}
+
+There are now three types of messages introduced by VDUSE framework:
+
+- VDUSE_GET_VQ_STATE: Get the state for virtqueue, userspace should return
+  avail index for split virtqueue or the device/driver ring wrap counters and
+  the avail and used index for packed virtqueue.
+
+- VDUSE_SET_STATUS: Set the device status, userspace should follow
+  the virtio spec: https://docs.oasis-open.org/virtio/virtio/v1.1/virtio-v1.1.html
+  to process this message. For example, fail to set the FEATURES_OK device
+  status bit if the device can not accept the negotiated virtio features
+  get from the VDUSE_DEV_GET_FEATURES ioctl.
+
+- VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for specified
+  IOVA range, userspace should firstly remove the old mapping, then setup the new
+  mapping via the VDUSE_IOTLB_GET_FD ioctl.
+
+After DRIVER_OK status bit is set via the VDUSE_SET_STATUS message, userspace is
+able to start the dataplane processing as follows:
+
+1. Get the specified virtqueue's information with the VDUSE_VQ_GET_INFO ioctl,
+   including the size, the IOVAs of descriptor table, available ring and used ring,
+   the state and the ready status.
+
+2. Pass the above IOVAs to the VDUSE_IOTLB_GET_FD ioctl so that those IOVA regions
+   can be mapped into userspace. Some sample codes is shown below:
+
+.. code-block:: c
+
+	static int perm_to_prot(uint8_t perm)
+	{
+		int prot = 0;
+
+		switch (perm) {
+		case VDUSE_ACCESS_WO:
+			prot |= PROT_WRITE;
+			break;
+		case VDUSE_ACCESS_RO:
+			prot |= PROT_READ;
+			break;
+		case VDUSE_ACCESS_RW:
+			prot |= PROT_READ | PROT_WRITE;
+			break;
+		}
+
+		return prot;
+	}
+
+	static void *iova_to_va(int dev_fd, uint64_t iova, uint64_t *len)
+	{
+		int fd;
+		void *addr;
+		size_t size;
+		struct vduse_iotlb_entry entry;
+
+		entry.start = iova;
+		entry.last = iova;
+
+		/*
+		 * Find the first IOVA region that overlaps with the specified
+		 * range [start, last] and return the corresponding file descriptor.
+		 */
+		fd = ioctl(dev_fd, VDUSE_IOTLB_GET_FD, &entry);
+		if (fd < 0)
+			return NULL;
+
+		size = entry.last - entry.start + 1;
+		*len = entry.last - iova + 1;
+		addr = mmap(0, size, perm_to_prot(entry.perm), MAP_SHARED,
+			    fd, entry.offset);
+		close(fd);
+		if (addr == MAP_FAILED)
+			return NULL;
+
+		/*
+		 * Using some data structures such as linked list to store
+		 * the iotlb mapping. The munmap(2) should be called for the
+		 * cached mapping when the corresponding VDUSE_UPDATE_IOTLB
+		 * message is received or the device is reset.
+		 */
+
+		return addr + iova - entry.start;
+	}
+
+3. Setup the kick eventfd for the specified virtqueues with the VDUSE_VQ_SETUP_KICKFD
+   ioctl. The kick eventfd is used by VDUSE kernel module to notify userspace to
+   consume the available ring. This is optional since userspace can choose to poll the
+   available ring instead.
+
+4. Listen to the kick eventfd (optional) and consume the available ring. The buffer
+   described by the descriptors in the descriptor table should be also mapped into
+   userspace via the VDUSE_IOTLB_GET_FD ioctl before accessing.
+
+5. Inject an interrupt for specific virtqueue with the VDUSE_INJECT_VQ_IRQ ioctl
+   after the used ring is filled.
+
+For more details on the uAPI, please see include/uapi/linux/vduse.h.
diff --git a/MAINTAINERS b/MAINTAINERS
index 5ec52be..7d46f03 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -333,7 +333,7 @@
 F:	drivers/platform/x86/acer-wmi.c
 
 ACPI
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Len Brown <lenb@kernel.org>
 L:	linux-acpi@vger.kernel.org
 S:	Supported
@@ -354,7 +354,7 @@
 F:	tools/power/acpi/
 
 ACPI APEI
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Len Brown <lenb@kernel.org>
 R:	James Morse <james.morse@arm.com>
 R:	Tony Luck <tony.luck@intel.com>
@@ -364,7 +364,6 @@
 
 ACPI COMPONENT ARCHITECTURE (ACPICA)
 M:	Robert Moore <robert.moore@intel.com>
-M:	Erik Kaneda <erik.kaneda@intel.com>
 M:	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
 L:	linux-acpi@vger.kernel.org
 L:	devel@acpica.org
@@ -403,7 +402,7 @@
 F:	drivers/platform/x86/i2c-multi-instantiate.c
 
 ACPI PMIC DRIVERS
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Len Brown <lenb@kernel.org>
 R:	Andy Shevchenko <andy@kernel.org>
 R:	Mika Westerberg <mika.westerberg@linux.intel.com>
@@ -3314,7 +3313,6 @@
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
 F:	block/
 F:	drivers/block/
-F:	fs/block_dev.c
 F:	include/linux/blk*
 F:	kernel/trace/blktrace.c
 F:	lib/sbitmap.c
@@ -4827,7 +4825,7 @@
 F:	drivers/cpufreq/vexpress-spc-cpufreq.c
 
 CPU FREQUENCY SCALING FRAMEWORK
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Viresh Kumar <viresh.kumar@linaro.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
@@ -4845,7 +4843,7 @@
 F:	tools/testing/selftests/cpufreq/
 
 CPU IDLE TIME MANAGEMENT FRAMEWORK
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Daniel Lezcano <daniel.lezcano@linaro.org>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
@@ -7591,7 +7589,7 @@
 F:	fs/freevxfs/
 
 FREEZER
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-pm@vger.kernel.org
 S:	Supported
@@ -7844,7 +7842,7 @@
 F:	drivers/i2c/muxes/i2c-demux-pinctrl.c
 
 GENERIC PM DOMAINS
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Kevin Hilman <khilman@kernel.org>
 M:	Ulf Hansson <ulf.hansson@linaro.org>
 L:	linux-pm@vger.kernel.org
@@ -8310,7 +8308,7 @@
 F:	drivers/video/fbdev/hgafb.c
 
 HIBERNATION (aka Software Suspend, aka swsusp)
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-pm@vger.kernel.org
 S:	Supported
@@ -10623,10 +10621,10 @@
 F:	drivers/ata/sata_promise.*
 
 LIBATA SUBSYSTEM (Serial and Parallel ATA drivers)
-M:	Jens Axboe <axboe@kernel.dk>
+M:	Damien Le Moal <damien.lemoal@opensource.wdc.com>
 L:	linux-ide@vger.kernel.org
 S:	Maintained
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dlemoal/libata.git
 F:	Documentation/devicetree/bindings/ata/
 F:	drivers/ata/
 F:	include/linux/ata.h
@@ -13410,7 +13408,7 @@
 NVM EXPRESS TARGET DRIVER
 M:	Christoph Hellwig <hch@lst.de>
 M:	Sagi Grimberg <sagi@grimberg.me>
-M:	Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
+M:	Chaitanya Kulkarni <kch@nvidia.com>
 L:	linux-nvme@lists.infradead.org
 S:	Supported
 W:	http://git.infradead.org/nvme.git
@@ -14969,7 +14967,7 @@
 F:	kernel/time/namespace.c
 
 POWER MANAGEMENT CORE
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 L:	linux-pm@vger.kernel.org
 S:	Supported
 B:	https://bugzilla.kernel.org
@@ -17947,7 +17945,7 @@
 F:	drivers/sh/
 
 SUSPEND TO RAM
-M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
+M:	"Rafael J. Wysocki" <rafael@kernel.org>
 M:	Len Brown <len.brown@intel.com>
 M:	Pavel Machek <pavel@ucw.cz>
 L:	linux-pm@vger.kernel.org
@@ -18567,6 +18565,7 @@
 F:	include/linux/cpu_cooling.h
 F:	include/linux/thermal.h
 F:	include/uapi/linux/thermal.h
+F:	tools/thermal/
 
 THERMAL DRIVER FOR AMLOGIC SOCS
 M:	Guillaume La Roque <glaroque@baylibre.com>
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index b16be52..37a8175 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/crash_dump.h>
 #include <linux/hugetlb.h>
 #include <linux/acpi_iort.h>
+#include <linux/kmemleak.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -101,6 +102,11 @@
 	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
 		crash_base, crash_base + crash_size, crash_size >> 20);
 
+	/*
+	 * The crashkernel memory will be removed from the kernel linear
+	 * map. Inform kmemleak so that it won't try to access it.
+	 */
+	kmemleak_ignore_phys(crash_base);
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 }
@@ -222,7 +228,21 @@
 
 void __init arm64_memblock_init(void)
 {
-	const s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual);
+	s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual);
+
+	/*
+	 * Corner case: 52-bit VA capable systems running KVM in nVHE mode may
+	 * be limited in their ability to support a linear map that exceeds 51
+	 * bits of VA space, depending on the placement of the ID map. Given
+	 * that the placement of the ID map may be randomized, let's simply
+	 * limit the kernel's linear map to 51 bits as well if we detect this
+	 * configuration.
+	 */
+	if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 &&
+	    is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
+		pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n");
+		linear_region_size = min_t(u64, linear_region_size, BIT(51));
+	}
 
 	/* Remove memory above our supported physical address size */
 	memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 3001a7d8f..4742b6f 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -10,7 +10,6 @@
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_HAS_STRNLEN_USER
 	select ARCH_NO_SG_CHAIN
 	select ARCH_SUPPORTS_HUGETLBFS if PA20
 	select ARCH_SUPPORTS_MEMORY_FAILURE
@@ -65,7 +64,6 @@
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS
-	select SET_FS
 	select TRACE_IRQFLAGS_SUPPORT
 
 	help
diff --git a/arch/parisc/boot/compressed/Makefile b/arch/parisc/boot/compressed/Makefile
index dff4536..9fe5487 100644
--- a/arch/parisc/boot/compressed/Makefile
+++ b/arch/parisc/boot/compressed/Makefile
@@ -26,7 +26,7 @@
 OBJECTS += $(obj)/head.o $(obj)/real2.o $(obj)/firmware.o $(obj)/misc.o $(obj)/piggy.o
 
 LDFLAGS_vmlinux := -X -e startup --as-needed -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS) $(LIBGCC)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS) $(LIBGCC) FORCE
 	$(call if_changed,ld)
 
 sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\|parisc_kernel_start\)$$/\#define SZ\2 0x\1/p'
@@ -34,7 +34,7 @@
 quiet_cmd_sizes = GEN $@
       cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
 
-$(obj)/sizes.h: vmlinux
+$(obj)/sizes.h: vmlinux FORCE
 	$(call if_changed,sizes)
 
 AFLAGS_head.o += -I$(objtree)/$(obj) -DBOOTLOADER
@@ -70,19 +70,19 @@
 suffix-$(CONFIG_KERNEL_LZO)  := lzo
 suffix-$(CONFIG_KERNEL_XZ)  := xz
 
-$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,gzip)
-$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.bz2: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,bzip2)
-$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lz4: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lz4)
-$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lzma: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzma)
-$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.lzo: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,lzo)
-$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
+$(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y) FORCE
 	$(call if_changed,xzkern)
 
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
+$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y) FORCE
 	$(call if_changed,ld)
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index b5fbcd2..eeb7da0 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -101,10 +101,6 @@
 
 #define CPU_HVERSION ((boot_cpu_data.hversion >> 4) & 0x0FFF)
 
-typedef struct {
-	int seg;  
-} mm_segment_t;
-
 #define ARCH_MIN_TASKALIGN	8
 
 struct thread_struct {
diff --git a/arch/parisc/include/asm/rt_sigframe.h b/arch/parisc/include/asm/rt_sigframe.h
index 2b3010a..4b9e3d7 100644
--- a/arch/parisc/include/asm/rt_sigframe.h
+++ b/arch/parisc/include/asm/rt_sigframe.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_PARISC_RT_SIGFRAME_H
 #define _ASM_PARISC_RT_SIGFRAME_H
 
-#define SIGRETURN_TRAMP 4
+#define SIGRETURN_TRAMP 3
 #define SIGRESTARTBLOCK_TRAMP 5 
 #define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP)
 
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
index 0bd38a9..00ad50f 100644
--- a/arch/parisc/include/asm/thread_info.h
+++ b/arch/parisc/include/asm/thread_info.h
@@ -11,7 +11,6 @@
 struct thread_info {
 	struct task_struct *task;	/* main task structure */
 	unsigned long flags;		/* thread_info flags (see TIF_*) */
-	mm_segment_t addr_limit;	/* user-level address space limit */
 	__u32 cpu;			/* current CPU */
 	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
 };
@@ -21,7 +20,6 @@
 	.task		= &tsk,			\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.addr_limit	= KERNEL_DS,		\
 	.preempt_count	= INIT_PREEMPT_COUNT,	\
 }
 
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
index 7c13314..192ad9e 100644
--- a/arch/parisc/include/asm/uaccess.h
+++ b/arch/parisc/include/asm/uaccess.h
@@ -11,14 +11,6 @@
 #include <linux/bug.h>
 #include <linux/string.h>
 
-#define KERNEL_DS	((mm_segment_t){0})
-#define USER_DS 	((mm_segment_t){1})
-
-#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
-
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-
 /*
  * Note that since kernel addresses are in a separate address space on
  * parisc, we don't need to do anything for access_ok().
@@ -33,11 +25,11 @@
 #define get_user __get_user
 
 #if !defined(CONFIG_64BIT)
-#define LDD_USER(val, ptr)	__get_user_asm64(val, ptr)
-#define STD_USER(x, ptr)	__put_user_asm64(x, ptr)
+#define LDD_USER(sr, val, ptr)	__get_user_asm64(sr, val, ptr)
+#define STD_USER(sr, x, ptr)	__put_user_asm64(sr, x, ptr)
 #else
-#define LDD_USER(val, ptr)	__get_user_asm(val, "ldd", ptr)
-#define STD_USER(x, ptr)	__put_user_asm("std", x, ptr)
+#define LDD_USER(sr, val, ptr)	__get_user_asm(sr, val, "ldd", ptr)
+#define STD_USER(sr, x, ptr)	__put_user_asm(sr, "std", x, ptr)
 #endif
 
 /*
@@ -67,28 +59,15 @@
 #define ASM_EXCEPTIONTABLE_ENTRY_EFAULT( fault_addr, except_addr )\
 	ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr + 1)
 
-/*
- * load_sr2() preloads the space register %%sr2 - based on the value of
- * get_fs() - with either a value of 0 to access kernel space (KERNEL_DS which
- * is 0), or with the current value of %%sr3 to access user space (USER_DS)
- * memory. The following __get_user_asm() and __put_user_asm() functions have
- * %%sr2 hard-coded to access the requested memory.
- */
-#define load_sr2() \
-	__asm__(" or,=  %0,%%r0,%%r0\n\t"	\
-		" mfsp %%sr3,%0\n\t"		\
-		" mtsp %0,%%sr2\n\t"		\
-		: : "r"(get_fs()) : )
-
-#define __get_user_internal(val, ptr)			\
+#define __get_user_internal(sr, val, ptr)		\
 ({							\
 	register long __gu_err __asm__ ("r8") = 0;	\
 							\
 	switch (sizeof(*(ptr))) {			\
-	case 1: __get_user_asm(val, "ldb", ptr); break;	\
-	case 2: __get_user_asm(val, "ldh", ptr); break; \
-	case 4: __get_user_asm(val, "ldw", ptr); break; \
-	case 8: LDD_USER(val, ptr); break;		\
+	case 1: __get_user_asm(sr, val, "ldb", ptr); break; \
+	case 2: __get_user_asm(sr, val, "ldh", ptr); break; \
+	case 4: __get_user_asm(sr, val, "ldw", ptr); break; \
+	case 8: LDD_USER(sr, val, ptr); break;		\
 	default: BUILD_BUG();				\
 	}						\
 							\
@@ -97,15 +76,14 @@
 
 #define __get_user(val, ptr)				\
 ({							\
-	load_sr2();					\
-	__get_user_internal(val, ptr);			\
+	__get_user_internal("%%sr3,", val, ptr);	\
 })
 
-#define __get_user_asm(val, ldx, ptr)			\
+#define __get_user_asm(sr, val, ldx, ptr)		\
 {							\
 	register long __gu_val;				\
 							\
-	__asm__("1: " ldx " 0(%%sr2,%2),%0\n"		\
+	__asm__("1: " ldx " 0(" sr "%2),%0\n"		\
 		"9:\n"					\
 		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
 		: "=r"(__gu_val), "=r"(__gu_err)        \
@@ -114,9 +92,22 @@
 	(val) = (__force __typeof__(*(ptr))) __gu_val;	\
 }
 
+#define HAVE_GET_KERNEL_NOFAULT
+#define __get_kernel_nofault(dst, src, type, err_label)	\
+{							\
+	type __z;					\
+	long __err;					\
+	__err = __get_user_internal("%%sr0,", __z, (type *)(src)); \
+	if (unlikely(__err))				\
+		goto err_label;				\
+	else						\
+		*(type *)(dst) = __z;			\
+}
+
+
 #if !defined(CONFIG_64BIT)
 
-#define __get_user_asm64(val, ptr)			\
+#define __get_user_asm64(sr, val, ptr)			\
 {							\
 	union {						\
 		unsigned long long	l;		\
@@ -124,8 +115,8 @@
 	} __gu_tmp;					\
 							\
 	__asm__("   copy %%r0,%R0\n"			\
-		"1: ldw 0(%%sr2,%2),%0\n"		\
-		"2: ldw 4(%%sr2,%2),%R0\n"		\
+		"1: ldw 0(" sr "%2),%0\n"		\
+		"2: ldw 4(" sr "%2),%R0\n"		\
 		"9:\n"					\
 		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	\
 		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	\
@@ -138,16 +129,16 @@
 #endif /* !defined(CONFIG_64BIT) */
 
 
-#define __put_user_internal(x, ptr)				\
+#define __put_user_internal(sr, x, ptr)				\
 ({								\
 	register long __pu_err __asm__ ("r8") = 0;      	\
         __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x);	\
 								\
 	switch (sizeof(*(ptr))) {				\
-	case 1: __put_user_asm("stb", __x, ptr); break;		\
-	case 2: __put_user_asm("sth", __x, ptr); break;		\
-	case 4: __put_user_asm("stw", __x, ptr); break;		\
-	case 8: STD_USER(__x, ptr); break;			\
+	case 1: __put_user_asm(sr, "stb", __x, ptr); break;	\
+	case 2: __put_user_asm(sr, "sth", __x, ptr); break;	\
+	case 4: __put_user_asm(sr, "stw", __x, ptr); break;	\
+	case 8: STD_USER(sr, __x, ptr); break;			\
 	default: BUILD_BUG();					\
 	}							\
 								\
@@ -156,10 +147,20 @@
 
 #define __put_user(x, ptr)					\
 ({								\
-	load_sr2();						\
-	__put_user_internal(x, ptr);				\
+	__put_user_internal("%%sr3,", x, ptr);			\
 })
 
+#define __put_kernel_nofault(dst, src, type, err_label)		\
+{								\
+	type __z = *(type *)(src);				\
+	long __err;						\
+	__err = __put_user_internal("%%sr0,", __z, (type *)(dst)); \
+	if (unlikely(__err))					\
+		goto err_label;					\
+}
+
+
+
 
 /*
  * The "__put_user/kernel_asm()" macros tell gcc they read from memory
@@ -170,26 +171,26 @@
  * r8 is already listed as err.
  */
 
-#define __put_user_asm(stx, x, ptr)                         \
-	__asm__ __volatile__ (                              \
-		"1: " stx " %2,0(%%sr2,%1)\n"		    \
-		"9:\n"					    \
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	    \
-		: "=r"(__pu_err)                            \
+#define __put_user_asm(sr, stx, x, ptr)				\
+	__asm__ __volatile__ (					\
+		"1: " stx " %2,0(" sr "%1)\n"			\
+		"9:\n"						\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
+		: "=r"(__pu_err)				\
 		: "r"(ptr), "r"(x), "0"(__pu_err))
 
 
 #if !defined(CONFIG_64BIT)
 
-#define __put_user_asm64(__val, ptr) do {	    	    \
-	__asm__ __volatile__ (				    \
-		"1: stw %2,0(%%sr2,%1)\n"		    \
-		"2: stw %R2,4(%%sr2,%1)\n"		    \
-		"9:\n"					    \
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)	    \
-		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)	    \
-		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(__val), "0"(__pu_err));	    \
+#define __put_user_asm64(sr, __val, ptr) do {			\
+	__asm__ __volatile__ (					\
+		"1: stw %2,0(" sr "%1)\n"			\
+		"2: stw %R2,4(" sr "%1)\n"			\
+		"9:\n"						\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(1b, 9b)		\
+		ASM_EXCEPTIONTABLE_ENTRY_EFAULT(2b, 9b)		\
+		: "=r"(__pu_err)				\
+		: "r"(ptr), "r"(__val), "0"(__pu_err));		\
 } while (0)
 
 #endif /* !defined(CONFIG_64BIT) */
@@ -200,14 +201,12 @@
  */
 
 extern long strncpy_from_user(char *, const char __user *, long);
-extern unsigned lclear_user(void __user *, unsigned long);
-extern long lstrnlen_user(const char __user *, long);
+extern __must_check unsigned lclear_user(void __user *, unsigned long);
+extern __must_check long strnlen_user(const char __user *src, long n);
 /*
  * Complex access routines -- macros
  */
-#define user_addr_max() (~0UL)
 
-#define strnlen_user lstrnlen_user
 #define clear_user lclear_user
 #define __clear_user lclear_user
 
diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index 33113ba..22924a3 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -230,7 +230,6 @@
 	DEFINE(TI_TASK, offsetof(struct thread_info, task));
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
-	DEFINE(TI_SEGMENT, offsetof(struct thread_info, addr_limit));
 	DEFINE(TI_PRE_COUNT, offsetof(struct thread_info, preempt_count));
 	DEFINE(THREAD_SZ, sizeof(struct thread_info));
 	/* THREAD_SZ_ALGN includes space for a stack frame. */
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index e8a6a75..00297e8 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -32,7 +32,6 @@
 
 #include <linux/uaccess.h>
 EXPORT_SYMBOL(lclear_user);
-EXPORT_SYMBOL(lstrnlen_user);
 
 #ifndef CONFIG_64BIT
 /* Needed so insmod can set dp value */
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 3fb86ee..cceb098 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -150,8 +150,6 @@
 #ifdef CONFIG_PA11
 	dma_ops_init();
 #endif
-
-	clear_sched_clock_stable();
 }
 
 /*
diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c
index db1a47c..bbfe23c 100644
--- a/arch/parisc/kernel/signal.c
+++ b/arch/parisc/kernel/signal.c
@@ -237,18 +237,22 @@
 #endif
 	
 	usp = (regs->gr[30] & ~(0x01UL));
+	sigframe_size = PARISC_RT_SIGFRAME_SIZE;
 #ifdef CONFIG_64BIT
 	if (is_compat_task()) {
 		/* The gcc alloca implementation leaves garbage in the upper 32 bits of sp */
 		usp = (compat_uint_t)usp;
+		sigframe_size = PARISC_RT_SIGFRAME_SIZE32;
 	}
 #endif
-	/*FIXME: frame_size parameter is unused, remove it. */
-	frame = get_sigframe(&ksig->ka, usp, sizeof(*frame));
+	frame = get_sigframe(&ksig->ka, usp, sigframe_size);
 
 	DBG(1,"SETUP_RT_FRAME: START\n");
 	DBG(1,"setup_rt_frame: frame %p info %p\n", frame, ksig->info);
 
+	start = (unsigned long) frame;
+	if (start >= user_addr_max() - sigframe_size)
+		return -EFAULT;
 	
 #ifdef CONFIG_64BIT
 
@@ -284,32 +288,21 @@
 	   already in userspace. The first words of tramp are used to
 	   save the previous sigrestartblock trampoline that might be
 	   on the stack. We start the sigreturn trampoline at 
-	   SIGRESTARTBLOCK_TRAMP+X. */
+	   SIGRESTARTBLOCK_TRAMP. */
 	err |= __put_user(in_syscall ? INSN_LDI_R25_1 : INSN_LDI_R25_0,
 			&frame->tramp[SIGRESTARTBLOCK_TRAMP+0]);
-	err |= __put_user(INSN_LDI_R20, 
-			&frame->tramp[SIGRESTARTBLOCK_TRAMP+1]);
 	err |= __put_user(INSN_BLE_SR2_R0, 
+			&frame->tramp[SIGRESTARTBLOCK_TRAMP+1]);
+	err |= __put_user(INSN_LDI_R20,
 			&frame->tramp[SIGRESTARTBLOCK_TRAMP+2]);
-	err |= __put_user(INSN_NOP, &frame->tramp[SIGRESTARTBLOCK_TRAMP+3]);
 
-#if DEBUG_SIG
-	/* Assert that we're flushing in the correct space... */
-	{
-		unsigned long sid;
-		asm ("mfsp %%sr3,%0" : "=r" (sid));
-		DBG(1,"setup_rt_frame: Flushing 64 bytes at space %#x offset %p\n",
-		       sid, frame->tramp);
-	}
-#endif
-
-	start = (unsigned long) &frame->tramp[0];
-	end = (unsigned long) &frame->tramp[TRAMP_SIZE];
+	start = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+0];
+	end = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP+3];
 	flush_user_dcache_range_asm(start, end);
 	flush_user_icache_range_asm(start, end);
 
 	/* TRAMP Words 0-4, Length 5 = SIGRESTARTBLOCK_TRAMP
-	 * TRAMP Words 5-9, Length 4 = SIGRETURN_TRAMP
+	 * TRAMP Words 5-7, Length 3 = SIGRETURN_TRAMP
 	 * So the SIGRETURN_TRAMP is at the end of SIGRESTARTBLOCK_TRAMP
 	 */
 	rp = (unsigned long) &frame->tramp[SIGRESTARTBLOCK_TRAMP];
@@ -353,11 +346,6 @@
 
 	/* The syscall return path will create IAOQ values from r31.
 	 */
-	sigframe_size = PARISC_RT_SIGFRAME_SIZE;
-#ifdef CONFIG_64BIT
-	if (is_compat_task())
-		sigframe_size = PARISC_RT_SIGFRAME_SIZE32;
-#endif
 	if (in_syscall) {
 		regs->gr[31] = haddr;
 #ifdef CONFIG_64BIT
@@ -501,7 +489,6 @@
 		DBG(1,"ERESTARTNOHAND: returning -EINTR\n");
 		regs->gr[28] = -EINTR;
 		break;
-
 	case -ERESTARTSYS:
 		if (!(ka->sa.sa_flags & SA_RESTART)) {
 			DBG(1,"ERESTARTSYS: putting -EINTR\n");
@@ -529,6 +516,10 @@
 		unsigned long end  = (unsigned long) &usp[5];
 		long err = 0;
 
+		/* check that we don't exceed the stack */
+		if (A(&usp[0]) >= user_addr_max() - 5 * sizeof(int))
+			return;
+
 		/* Setup a trampoline to restart the syscall
 		 * with __NR_restart_syscall
 		 *
@@ -569,10 +560,6 @@
 }
 
 /*
- * Note that 'init' is a special process: it doesn't get signals it doesn't
- * want to handle. Thus you cannot kill init even with a SIGKILL even by
- * mistake.
- *
  * We need to be able to restore the syscall arguments (r21-r26) to
  * restart syscalls.  Thus, the syscall path should save them in the
  * pt_regs structure (it's okay to do so since they are caller-save
diff --git a/arch/parisc/kernel/signal32.h b/arch/parisc/kernel/signal32.h
index f166250..a5bdbb56 100644
--- a/arch/parisc/kernel/signal32.h
+++ b/arch/parisc/kernel/signal32.h
@@ -36,7 +36,7 @@
         compat_int_t rf_sar;
 };
 
-#define COMPAT_SIGRETURN_TRAMP 4
+#define COMPAT_SIGRETURN_TRAMP 3
 #define COMPAT_SIGRESTARTBLOCK_TRAMP 5
 #define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + \
 				COMPAT_SIGRESTARTBLOCK_TRAMP)
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index 08e4d48..9fb1e79 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -265,6 +265,9 @@
 			    (cpu0_loc == per_cpu(cpu_data, cpu).cpu_loc))
 				continue;
 
+			/* mark sched_clock unstable */
+			clear_sched_clock_stable();
+
 			clocksource_cr16.name = "cr16_unstable";
 			clocksource_cr16.flags = CLOCK_SOURCE_UNSTABLE;
 			clocksource_cr16.rating = 0;
@@ -272,10 +275,6 @@
 		}
 	}
 
-	/* XXX: We may want to mark sched_clock stable here if cr16 clocks are
-	 *	in sync:
-	 *	(clocksource_cr16.flags == CLOCK_SOURCE_IS_CONTINUOUS) */
-
 	/* register at clocksource framework */
 	clocksource_register_hz(&clocksource_cr16,
 		100 * PAGE0->mem_10msec);
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index 36d6a86..b428d29 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -28,21 +28,6 @@
 #include <linux/linkage.h>
 
 	/*
-	 * get_sr gets the appropriate space value into
-	 * sr1 for kernel/user space access, depending
-	 * on the flag stored in the task structure.
-	 */
-
-	.macro  get_sr
-	mfctl       %cr30,%r1
-	ldw         TI_SEGMENT(%r1),%r22
-	mfsp        %sr3,%r1
-	or,<>       %r22,%r0,%r0
-	copy        %r0,%r1
-	mtsp        %r1,%sr1
-	.endm
-
-	/*
 	 * unsigned long lclear_user(void *to, unsigned long n)
 	 *
 	 * Returns 0 for success.
@@ -51,10 +36,9 @@
 
 ENTRY_CFI(lclear_user)
 	comib,=,n   0,%r25,$lclu_done
-	get_sr
 $lclu_loop:
 	addib,<>    -1,%r25,$lclu_loop
-1:      stbs,ma     %r0,1(%sr1,%r26)
+1:	stbs,ma     %r0,1(%sr3,%r26)
 
 $lclu_done:
 	bv          %r0(%r2)
@@ -67,40 +51,6 @@
 ENDPROC_CFI(lclear_user)
 
 
-	/*
-	 * long lstrnlen_user(char *s, long n)
-	 *
-	 * Returns 0 if exception before zero byte or reaching N,
-	 *         N+1 if N would be exceeded,
-	 *         else strlen + 1 (i.e. includes zero byte).
-	 */
-
-ENTRY_CFI(lstrnlen_user)
-	comib,=     0,%r25,$lslen_nzero
-	copy	    %r26,%r24
-	get_sr
-1:      ldbs,ma     1(%sr1,%r26),%r1
-$lslen_loop:
-	comib,=,n   0,%r1,$lslen_done
-	addib,<>    -1,%r25,$lslen_loop
-2:      ldbs,ma     1(%sr1,%r26),%r1
-$lslen_done:
-	bv          %r0(%r2)
-	sub	    %r26,%r24,%r28
-
-$lslen_nzero:
-	b           $lslen_done
-	ldo         1(%r26),%r26 /* special case for N == 0 */
-
-3:      b	    $lslen_done
-	copy        %r24,%r26    /* reset r26 so 0 is returned on fault */
-
-	ASM_EXCEPTIONTABLE_ENTRY(1b,3b)
-	ASM_EXCEPTIONTABLE_ENTRY(2b,3b)
-
-ENDPROC_CFI(lstrnlen_user)
-
-
 /*
  * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
  *
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index c799556..c3f3fd5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -41,6 +41,7 @@
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_HUGE_PMD_SHARE if 64BIT
 	select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU
+	select BUILDTIME_TABLE_SORT if MMU
 	select CLONE_BACKWARDS
 	select CLINT_TIMER if !MMU
 	select COMMON_CLK
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 01906a9..0eb4568 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -132,8 +132,11 @@
 Image.%: Image
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
-zinstall install:
-	$(Q)$(MAKE) $(build)=$(boot) $@
+install: install-image = Image
+zinstall: install-image = Image.gz
+install zinstall:
+	$(CONFIG_SHELL) $(srctree)/$(boot)/install.sh $(KERNELRELEASE) \
+	$(boot)/$(install-image) System.map "$(INSTALL_PATH)"
 
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile
index 6bf299f..becd062 100644
--- a/arch/riscv/boot/Makefile
+++ b/arch/riscv/boot/Makefile
@@ -58,11 +58,3 @@
 
 $(obj)/loader.bin: $(obj)/loader FORCE
 	$(call if_changed,objcopy)
-
-install:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
-	$(obj)/Image System.map "$(INSTALL_PATH)"
-
-zinstall:
-	$(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \
-	$(obj)/Image.gz System.map "$(INSTALL_PATH)"
diff --git a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
index baea7d2..b254c60 100644
--- a/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
+++ b/arch/riscv/boot/dts/microchip/microchip-mpfs-icicle-kit.dts
@@ -16,10 +16,14 @@
 
 	aliases {
 		ethernet0 = &emac1;
+		serial0 = &serial0;
+		serial1 = &serial1;
+		serial2 = &serial2;
+		serial3 = &serial3;
 	};
 
 	chosen {
-		stdout-path = &serial0;
+		stdout-path = "serial0:115200n8";
 	};
 
 	cpus {
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index bc68231..4ebc803 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -39,10 +39,12 @@
 CONFIG_PCIEPORTBUS=y
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCIE_XILINX=y
+CONFIG_PCIE_FU740=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
+CONFIG_BLK_DEV_NVME=m
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=y
 CONFIG_SCSI_VIRTIO=y
@@ -108,6 +110,8 @@
 CONFIG_NFS_V4_2=y
 CONFIG_ROOT_NFS=y
 CONFIG_9P_FS=y
+CONFIG_NLS_CODEPAGE_437=y
+CONFIG_NLS_ISO8859_1=m
 CONFIG_CRYPTO_USER_API_HASH=y
 CONFIG_CRYPTO_DEV_VIRTIO=y
 CONFIG_PRINTK_TIME=y
diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h
index f4b490c..f53c400 100644
--- a/arch/riscv/include/asm/elf.h
+++ b/arch/riscv/include/asm/elf.h
@@ -42,6 +42,9 @@
  */
 #define ELF_ET_DYN_BASE		((TASK_SIZE / 3) * 2)
 
+#ifdef CONFIG_64BIT
+#define STACK_RND_MASK		(0x3ffff >> (PAGE_SHIFT - 12))
+#endif
 /*
  * This yields a mask that user programs can use to figure out what
  * instruction set this CPU supports.  This could be done in user space,
diff --git a/arch/riscv/kernel/vmlinux-xip.lds.S b/arch/riscv/kernel/vmlinux-xip.lds.S
index af776555..9c9f350 100644
--- a/arch/riscv/kernel/vmlinux-xip.lds.S
+++ b/arch/riscv/kernel/vmlinux-xip.lds.S
@@ -121,7 +121,6 @@
 	}
 
 	BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0)
-	EXCEPTION_TABLE(0x10)
 
 	.rel.dyn : AT(ADDR(.rel.dyn) - LOAD_OFFSET) {
 		*(.rel.dyn*)
diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S
index 502d082..5104f3a 100644
--- a/arch/riscv/kernel/vmlinux.lds.S
+++ b/arch/riscv/kernel/vmlinux.lds.S
@@ -4,6 +4,8 @@
  * Copyright (C) 2017 SiFive
  */
 
+#define RO_EXCEPTION_TABLE_ALIGN	16
+
 #ifdef CONFIG_XIP_KERNEL
 #include "vmlinux-xip.lds.S"
 #else
@@ -112,8 +114,6 @@
 		*(.srodata*)
 	}
 
-	EXCEPTION_TABLE(0x10)
-
 	. = ALIGN(SECTION_ALIGN);
 	_data = .;
 
diff --git a/block/Makefile b/block/Makefile
index 6cf4027..41aa1ba 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the kernel block layer
 #
 
-obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \
+obj-$(CONFIG_BLOCK) := bdev.o fops.o bio.o elevator.o blk-core.o blk-sysfs.o \
 			blk-flush.o blk-settings.o blk-ioc.o blk-map.o \
 			blk-exec.o blk-merge.o blk-timeout.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
diff --git a/fs/block_dev.c b/block/bdev.c
similarity index 63%
rename from fs/block_dev.c
rename to block/bdev.c
index 45df6cb..cf2780c 100644
--- a/fs/block_dev.c
+++ b/block/bdev.c
@@ -7,12 +7,10 @@
 
 #include <linux/init.h>
 #include <linux/mm.h>
-#include <linux/fcntl.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
 #include <linux/major.h>
 #include <linux/device_cgroup.h>
-#include <linux/highmem.h>
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/module.h>
@@ -20,30 +18,22 @@
 #include <linux/magic.h>
 #include <linux/buffer_head.h>
 #include <linux/swap.h>
-#include <linux/pagevec.h>
 #include <linux/writeback.h>
-#include <linux/mpage.h>
 #include <linux/mount.h>
 #include <linux/pseudo_fs.h>
 #include <linux/uio.h>
 #include <linux/namei.h>
-#include <linux/log2.h>
 #include <linux/cleancache.h>
-#include <linux/task_io_accounting_ops.h>
-#include <linux/falloc.h>
 #include <linux/part_stat.h>
 #include <linux/uaccess.h>
-#include <linux/suspend.h>
-#include "internal.h"
-#include "../block/blk.h"
+#include "../fs/internal.h"
+#include "blk.h"
 
 struct bdev_inode {
 	struct block_device bdev;
 	struct inode vfs_inode;
 };
 
-static const struct address_space_operations def_blk_aops;
-
 static inline struct bdev_inode *BDEV_I(struct inode *inode)
 {
 	return container_of(inode, struct bdev_inode, vfs_inode);
@@ -194,332 +184,6 @@
 
 EXPORT_SYMBOL(sb_min_blocksize);
 
-static int
-blkdev_get_block(struct inode *inode, sector_t iblock,
-		struct buffer_head *bh, int create)
-{
-	bh->b_bdev = I_BDEV(inode);
-	bh->b_blocknr = iblock;
-	set_buffer_mapped(bh);
-	return 0;
-}
-
-static struct inode *bdev_file_inode(struct file *file)
-{
-	return file->f_mapping->host;
-}
-
-static unsigned int dio_bio_write_op(struct kiocb *iocb)
-{
-	unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
-
-	/* avoid the need for a I/O completion work item */
-	if (iocb->ki_flags & IOCB_DSYNC)
-		op |= REQ_FUA;
-	return op;
-}
-
-#define DIO_INLINE_BIO_VECS 4
-
-static void blkdev_bio_end_io_simple(struct bio *bio)
-{
-	struct task_struct *waiter = bio->bi_private;
-
-	WRITE_ONCE(bio->bi_private, NULL);
-	blk_wake_io_task(waiter);
-}
-
-static ssize_t
-__blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
-		unsigned int nr_pages)
-{
-	struct file *file = iocb->ki_filp;
-	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
-	loff_t pos = iocb->ki_pos;
-	bool should_dirty = false;
-	struct bio bio;
-	ssize_t ret;
-	blk_qc_t qc;
-
-	if ((pos | iov_iter_alignment(iter)) &
-	    (bdev_logical_block_size(bdev) - 1))
-		return -EINVAL;
-
-	if (nr_pages <= DIO_INLINE_BIO_VECS)
-		vecs = inline_vecs;
-	else {
-		vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
-				     GFP_KERNEL);
-		if (!vecs)
-			return -ENOMEM;
-	}
-
-	bio_init(&bio, vecs, nr_pages);
-	bio_set_dev(&bio, bdev);
-	bio.bi_iter.bi_sector = pos >> 9;
-	bio.bi_write_hint = iocb->ki_hint;
-	bio.bi_private = current;
-	bio.bi_end_io = blkdev_bio_end_io_simple;
-	bio.bi_ioprio = iocb->ki_ioprio;
-
-	ret = bio_iov_iter_get_pages(&bio, iter);
-	if (unlikely(ret))
-		goto out;
-	ret = bio.bi_iter.bi_size;
-
-	if (iov_iter_rw(iter) == READ) {
-		bio.bi_opf = REQ_OP_READ;
-		if (iter_is_iovec(iter))
-			should_dirty = true;
-	} else {
-		bio.bi_opf = dio_bio_write_op(iocb);
-		task_io_account_write(ret);
-	}
-	if (iocb->ki_flags & IOCB_NOWAIT)
-		bio.bi_opf |= REQ_NOWAIT;
-	if (iocb->ki_flags & IOCB_HIPRI)
-		bio_set_polled(&bio, iocb);
-
-	qc = submit_bio(&bio);
-	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (!READ_ONCE(bio.bi_private))
-			break;
-		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc, true))
-			blk_io_schedule();
-	}
-	__set_current_state(TASK_RUNNING);
-
-	bio_release_pages(&bio, should_dirty);
-	if (unlikely(bio.bi_status))
-		ret = blk_status_to_errno(bio.bi_status);
-
-out:
-	if (vecs != inline_vecs)
-		kfree(vecs);
-
-	bio_uninit(&bio);
-
-	return ret;
-}
-
-struct blkdev_dio {
-	union {
-		struct kiocb		*iocb;
-		struct task_struct	*waiter;
-	};
-	size_t			size;
-	atomic_t		ref;
-	bool			multi_bio : 1;
-	bool			should_dirty : 1;
-	bool			is_sync : 1;
-	struct bio		bio;
-};
-
-static struct bio_set blkdev_dio_pool;
-
-static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
-{
-	struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
-}
-
-static void blkdev_bio_end_io(struct bio *bio)
-{
-	struct blkdev_dio *dio = bio->bi_private;
-	bool should_dirty = dio->should_dirty;
-
-	if (bio->bi_status && !dio->bio.bi_status)
-		dio->bio.bi_status = bio->bi_status;
-
-	if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
-		if (!dio->is_sync) {
-			struct kiocb *iocb = dio->iocb;
-			ssize_t ret;
-
-			if (likely(!dio->bio.bi_status)) {
-				ret = dio->size;
-				iocb->ki_pos += ret;
-			} else {
-				ret = blk_status_to_errno(dio->bio.bi_status);
-			}
-
-			dio->iocb->ki_complete(iocb, ret, 0);
-			if (dio->multi_bio)
-				bio_put(&dio->bio);
-		} else {
-			struct task_struct *waiter = dio->waiter;
-
-			WRITE_ONCE(dio->waiter, NULL);
-			blk_wake_io_task(waiter);
-		}
-	}
-
-	if (should_dirty) {
-		bio_check_pages_dirty(bio);
-	} else {
-		bio_release_pages(bio, false);
-		bio_put(bio);
-	}
-}
-
-static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
-		unsigned int nr_pages)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = bdev_file_inode(file);
-	struct block_device *bdev = I_BDEV(inode);
-	struct blk_plug plug;
-	struct blkdev_dio *dio;
-	struct bio *bio;
-	bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
-	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
-	loff_t pos = iocb->ki_pos;
-	blk_qc_t qc = BLK_QC_T_NONE;
-	int ret = 0;
-
-	if ((pos | iov_iter_alignment(iter)) &
-	    (bdev_logical_block_size(bdev) - 1))
-		return -EINVAL;
-
-	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
-
-	dio = container_of(bio, struct blkdev_dio, bio);
-	dio->is_sync = is_sync = is_sync_kiocb(iocb);
-	if (dio->is_sync) {
-		dio->waiter = current;
-		bio_get(bio);
-	} else {
-		dio->iocb = iocb;
-	}
-
-	dio->size = 0;
-	dio->multi_bio = false;
-	dio->should_dirty = is_read && iter_is_iovec(iter);
-
-	/*
-	 * Don't plug for HIPRI/polled IO, as those should go straight
-	 * to issue
-	 */
-	if (!is_poll)
-		blk_start_plug(&plug);
-
-	for (;;) {
-		bio_set_dev(bio, bdev);
-		bio->bi_iter.bi_sector = pos >> 9;
-		bio->bi_write_hint = iocb->ki_hint;
-		bio->bi_private = dio;
-		bio->bi_end_io = blkdev_bio_end_io;
-		bio->bi_ioprio = iocb->ki_ioprio;
-
-		ret = bio_iov_iter_get_pages(bio, iter);
-		if (unlikely(ret)) {
-			bio->bi_status = BLK_STS_IOERR;
-			bio_endio(bio);
-			break;
-		}
-
-		if (is_read) {
-			bio->bi_opf = REQ_OP_READ;
-			if (dio->should_dirty)
-				bio_set_pages_dirty(bio);
-		} else {
-			bio->bi_opf = dio_bio_write_op(iocb);
-			task_io_account_write(bio->bi_iter.bi_size);
-		}
-		if (iocb->ki_flags & IOCB_NOWAIT)
-			bio->bi_opf |= REQ_NOWAIT;
-
-		dio->size += bio->bi_iter.bi_size;
-		pos += bio->bi_iter.bi_size;
-
-		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
-		if (!nr_pages) {
-			bool polled = false;
-
-			if (iocb->ki_flags & IOCB_HIPRI) {
-				bio_set_polled(bio, iocb);
-				polled = true;
-			}
-
-			qc = submit_bio(bio);
-
-			if (polled)
-				WRITE_ONCE(iocb->ki_cookie, qc);
-			break;
-		}
-
-		if (!dio->multi_bio) {
-			/*
-			 * AIO needs an extra reference to ensure the dio
-			 * structure which is embedded into the first bio
-			 * stays around.
-			 */
-			if (!is_sync)
-				bio_get(bio);
-			dio->multi_bio = true;
-			atomic_set(&dio->ref, 2);
-		} else {
-			atomic_inc(&dio->ref);
-		}
-
-		submit_bio(bio);
-		bio = bio_alloc(GFP_KERNEL, nr_pages);
-	}
-
-	if (!is_poll)
-		blk_finish_plug(&plug);
-
-	if (!is_sync)
-		return -EIOCBQUEUED;
-
-	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (!READ_ONCE(dio->waiter))
-			break;
-
-		if (!(iocb->ki_flags & IOCB_HIPRI) ||
-		    !blk_poll(bdev_get_queue(bdev), qc, true))
-			blk_io_schedule();
-	}
-	__set_current_state(TASK_RUNNING);
-
-	if (!ret)
-		ret = blk_status_to_errno(dio->bio.bi_status);
-	if (likely(!ret))
-		ret = dio->size;
-
-	bio_put(&dio->bio);
-	return ret;
-}
-
-static ssize_t
-blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
-	unsigned int nr_pages;
-
-	if (!iov_iter_count(iter))
-		return 0;
-
-	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
-	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
-		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
-
-	return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
-}
-
-static __init int blkdev_init(void)
-{
-	return bioset_init(&blkdev_dio_pool, 4,
-				offsetof(struct blkdev_dio, bio),
-				BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE);
-}
-module_init(blkdev_init);
-
 int __sync_blockdev(struct block_device *bdev, int wait)
 {
 	if (!bdev)
@@ -637,81 +301,6 @@
 }
 EXPORT_SYMBOL(thaw_bdev);
 
-static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
-{
-	return block_write_full_page(page, blkdev_get_block, wbc);
-}
-
-static int blkdev_readpage(struct file * file, struct page * page)
-{
-	return block_read_full_page(page, blkdev_get_block);
-}
-
-static void blkdev_readahead(struct readahead_control *rac)
-{
-	mpage_readahead(rac, blkdev_get_block);
-}
-
-static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned flags,
-			struct page **pagep, void **fsdata)
-{
-	return block_write_begin(mapping, pos, len, flags, pagep,
-				 blkdev_get_block);
-}
-
-static int blkdev_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata)
-{
-	int ret;
-	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	unlock_page(page);
-	put_page(page);
-
-	return ret;
-}
-
-/*
- * private llseek:
- * for a block special file file_inode(file)->i_size is zero
- * so we compute the size by hand (just as in block_read/write above)
- */
-static loff_t block_llseek(struct file *file, loff_t offset, int whence)
-{
-	struct inode *bd_inode = bdev_file_inode(file);
-	loff_t retval;
-
-	inode_lock(bd_inode);
-	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
-	inode_unlock(bd_inode);
-	return retval;
-}
-	
-static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
-		int datasync)
-{
-	struct inode *bd_inode = bdev_file_inode(filp);
-	struct block_device *bdev = I_BDEV(bd_inode);
-	int error;
-	
-	error = file_write_and_wait_range(filp, start, end);
-	if (error)
-		return error;
-
-	/*
-	 * There is no need to serialise calls to blkdev_issue_flush with
-	 * i_mutex and doing so causes performance issues with concurrent
-	 * O_SYNC writers to a block device.
-	 */
-	error = blkdev_issue_flush(bdev);
-	if (error == -EOPNOTSUPP)
-		error = 0;
-
-	return error;
-}
-
 /**
  * bdev_read_page() - Start reading a page from a block device
  * @bdev: The device to read the page from
@@ -1305,35 +894,6 @@
 }
 EXPORT_SYMBOL(blkdev_get_by_path);
 
-static int blkdev_open(struct inode * inode, struct file * filp)
-{
-	struct block_device *bdev;
-
-	/*
-	 * Preserve backwards compatibility and allow large file access
-	 * even if userspace doesn't ask for it explicitly. Some mkfs
-	 * binary needs it. We might want to drop this workaround
-	 * during an unstable branch.
-	 */
-	filp->f_flags |= O_LARGEFILE;
-
-	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
-
-	if (filp->f_flags & O_NDELAY)
-		filp->f_mode |= FMODE_NDELAY;
-	if (filp->f_flags & O_EXCL)
-		filp->f_mode |= FMODE_EXCL;
-	if ((filp->f_flags & O_ACCMODE) == 3)
-		filp->f_mode |= FMODE_WRITE_IOCTL;
-
-	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
-	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
-	filp->f_mapping = bdev->bd_inode->i_mapping;
-	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
-	return 0;
-}
-
 void blkdev_put(struct block_device *bdev, fmode_t mode)
 {
 	struct gendisk *disk = bdev->bd_disk;
@@ -1397,203 +957,6 @@
 }
 EXPORT_SYMBOL(blkdev_put);
 
-static int blkdev_close(struct inode * inode, struct file * filp)
-{
-	struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
-	blkdev_put(bdev, filp->f_mode);
-	return 0;
-}
-
-static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
-{
-	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	fmode_t mode = file->f_mode;
-
-	/*
-	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
-	 * to updated it before every ioctl.
-	 */
-	if (file->f_flags & O_NDELAY)
-		mode |= FMODE_NDELAY;
-	else
-		mode &= ~FMODE_NDELAY;
-
-	return blkdev_ioctl(bdev, mode, cmd, arg);
-}
-
-/*
- * Write data to the block device.  Only intended for the block device itself
- * and the raw driver which basically is a fake block device.
- *
- * Does not take i_mutex for the write and thus is not for general purpose
- * use.
- */
-static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *bd_inode = bdev_file_inode(file);
-	loff_t size = i_size_read(bd_inode);
-	struct blk_plug plug;
-	size_t shorted = 0;
-	ssize_t ret;
-
-	if (bdev_read_only(I_BDEV(bd_inode)))
-		return -EPERM;
-
-	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
-		return -ETXTBSY;
-
-	if (!iov_iter_count(from))
-		return 0;
-
-	if (iocb->ki_pos >= size)
-		return -ENOSPC;
-
-	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
-		return -EOPNOTSUPP;
-
-	size -= iocb->ki_pos;
-	if (iov_iter_count(from) > size) {
-		shorted = iov_iter_count(from) - size;
-		iov_iter_truncate(from, size);
-	}
-
-	blk_start_plug(&plug);
-	ret = __generic_file_write_iter(iocb, from);
-	if (ret > 0)
-		ret = generic_write_sync(iocb, ret);
-	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
-	blk_finish_plug(&plug);
-	return ret;
-}
-
-static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *bd_inode = bdev_file_inode(file);
-	loff_t size = i_size_read(bd_inode);
-	loff_t pos = iocb->ki_pos;
-	size_t shorted = 0;
-	ssize_t ret;
-
-	if (pos >= size)
-		return 0;
-
-	size -= pos;
-	if (iov_iter_count(to) > size) {
-		shorted = iov_iter_count(to) - size;
-		iov_iter_truncate(to, size);
-	}
-
-	ret = generic_file_read_iter(iocb, to);
-	iov_iter_reexpand(to, iov_iter_count(to) + shorted);
-	return ret;
-}
-
-static int blkdev_writepages(struct address_space *mapping,
-			     struct writeback_control *wbc)
-{
-	return generic_writepages(mapping, wbc);
-}
-
-static const struct address_space_operations def_blk_aops = {
-	.set_page_dirty	= __set_page_dirty_buffers,
-	.readpage	= blkdev_readpage,
-	.readahead	= blkdev_readahead,
-	.writepage	= blkdev_writepage,
-	.write_begin	= blkdev_write_begin,
-	.write_end	= blkdev_write_end,
-	.writepages	= blkdev_writepages,
-	.direct_IO	= blkdev_direct_IO,
-	.migratepage	= buffer_migrate_page_norefs,
-	.is_dirty_writeback = buffer_check_dirty_writeback,
-};
-
-#define	BLKDEV_FALLOC_FL_SUPPORTED					\
-		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
-		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
-
-static long blkdev_fallocate(struct file *file, int mode, loff_t start,
-			     loff_t len)
-{
-	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	loff_t end = start + len - 1;
-	loff_t isize;
-	int error;
-
-	/* Fail if we don't recognize the flags. */
-	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
-		return -EOPNOTSUPP;
-
-	/* Don't go off the end of the device. */
-	isize = i_size_read(bdev->bd_inode);
-	if (start >= isize)
-		return -EINVAL;
-	if (end >= isize) {
-		if (mode & FALLOC_FL_KEEP_SIZE) {
-			len = isize - start;
-			end = start + len - 1;
-		} else
-			return -EINVAL;
-	}
-
-	/*
-	 * Don't allow IO that isn't aligned to logical block size.
-	 */
-	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
-		return -EINVAL;
-
-	/* Invalidate the page cache, including dirty pages. */
-	error = truncate_bdev_range(bdev, file->f_mode, start, end);
-	if (error)
-		return error;
-
-	switch (mode) {
-	case FALLOC_FL_ZERO_RANGE:
-	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
-		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
-					    GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
-		break;
-	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
-		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
-					     GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
-		break;
-	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
-		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
-					     GFP_KERNEL, 0);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-	if (error)
-		return error;
-
-	/*
-	 * Invalidate the page cache again; if someone wandered in and dirtied
-	 * a page, we just discard it - userspace has no way of knowing whether
-	 * the write happened before or after discard completing...
-	 */
-	return truncate_bdev_range(bdev, file->f_mode, start, end);
-}
-
-const struct file_operations def_blk_fops = {
-	.open		= blkdev_open,
-	.release	= blkdev_close,
-	.llseek		= block_llseek,
-	.read_iter	= blkdev_read_iter,
-	.write_iter	= blkdev_write_iter,
-	.iopoll		= blkdev_iopoll,
-	.mmap		= generic_file_mmap,
-	.fsync		= blkdev_fsync,
-	.unlocked_ioctl	= block_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= compat_blkdev_ioctl,
-#endif
-	.splice_read	= generic_file_splice_read,
-	.splice_write	= iter_file_splice_write,
-	.fallocate	= blkdev_fallocate,
-};
-
 /**
  * lookup_bdev  - lookup a struct block_device by name
  * @pathname:	special file representing the block device
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 65d3a63..108a352 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2135,6 +2135,18 @@
 	}
 }
 
+/*
+ * Allow 4x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
+ * queues. This is important for md arrays to benefit from merging
+ * requests.
+ */
+static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
+{
+	if (plug->multiple_queues)
+		return BLK_MAX_REQUEST_COUNT * 4;
+	return BLK_MAX_REQUEST_COUNT;
+}
+
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
@@ -2231,7 +2243,7 @@
 		else
 			last = list_entry_rq(plug->mq_list.prev);
 
-		if (request_count >= BLK_MAX_REQUEST_COUNT || (last &&
+		if (request_count >= blk_plug_max_rq_count(plug) || (last &&
 		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
 			blk_flush_plug_list(plug, false);
 			trace_block_plug(q);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 55c4901..7c4e799 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2458,6 +2458,7 @@
 void blk_throtl_exit(struct request_queue *q)
 {
 	BUG_ON(!q->td);
+	del_timer_sync(&q->td->service_queue.pending_timer);
 	throtl_shutdown_wq(q);
 	blkcg_deactivate_policy(q, &blkcg_policy_throtl);
 	free_percpu(q->td->latency_buckets[READ]);
diff --git a/block/blk.h b/block/blk.h
index 8c96b0c..7d2a0ba 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -373,4 +373,6 @@
 	bio->bi_opf &= ~REQ_HIPRI;
 }
 
+extern const struct address_space_operations def_blk_aops;
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/fops.c b/block/fops.c
new file mode 100644
index 0000000..ffce6f6
--- /dev/null
+++ b/block/fops.c
@@ -0,0 +1,640 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 1991, 1992  Linus Torvalds
+ * Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
+ * Copyright (C) 2016 - 2020 Christoph Hellwig
+ */
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/blkdev.h>
+#include <linux/buffer_head.h>
+#include <linux/mpage.h>
+#include <linux/uio.h>
+#include <linux/namei.h>
+#include <linux/task_io_accounting_ops.h>
+#include <linux/falloc.h>
+#include <linux/suspend.h>
+#include "blk.h"
+
+static struct inode *bdev_file_inode(struct file *file)
+{
+	return file->f_mapping->host;
+}
+
+static int blkdev_get_block(struct inode *inode, sector_t iblock,
+		struct buffer_head *bh, int create)
+{
+	bh->b_bdev = I_BDEV(inode);
+	bh->b_blocknr = iblock;
+	set_buffer_mapped(bh);
+	return 0;
+}
+
+static unsigned int dio_bio_write_op(struct kiocb *iocb)
+{
+	unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;
+
+	/* avoid the need for a I/O completion work item */
+	if (iocb->ki_flags & IOCB_DSYNC)
+		op |= REQ_FUA;
+	return op;
+}
+
+#define DIO_INLINE_BIO_VECS 4
+
+static void blkdev_bio_end_io_simple(struct bio *bio)
+{
+	struct task_struct *waiter = bio->bi_private;
+
+	WRITE_ONCE(bio->bi_private, NULL);
+	blk_wake_io_task(waiter);
+}
+
+static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
+		struct iov_iter *iter, unsigned int nr_pages)
+{
+	struct file *file = iocb->ki_filp;
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs;
+	loff_t pos = iocb->ki_pos;
+	bool should_dirty = false;
+	struct bio bio;
+	ssize_t ret;
+	blk_qc_t qc;
+
+	if ((pos | iov_iter_alignment(iter)) &
+	    (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	if (nr_pages <= DIO_INLINE_BIO_VECS)
+		vecs = inline_vecs;
+	else {
+		vecs = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+				     GFP_KERNEL);
+		if (!vecs)
+			return -ENOMEM;
+	}
+
+	bio_init(&bio, vecs, nr_pages);
+	bio_set_dev(&bio, bdev);
+	bio.bi_iter.bi_sector = pos >> 9;
+	bio.bi_write_hint = iocb->ki_hint;
+	bio.bi_private = current;
+	bio.bi_end_io = blkdev_bio_end_io_simple;
+	bio.bi_ioprio = iocb->ki_ioprio;
+
+	ret = bio_iov_iter_get_pages(&bio, iter);
+	if (unlikely(ret))
+		goto out;
+	ret = bio.bi_iter.bi_size;
+
+	if (iov_iter_rw(iter) == READ) {
+		bio.bi_opf = REQ_OP_READ;
+		if (iter_is_iovec(iter))
+			should_dirty = true;
+	} else {
+		bio.bi_opf = dio_bio_write_op(iocb);
+		task_io_account_write(ret);
+	}
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		bio.bi_opf |= REQ_NOWAIT;
+	if (iocb->ki_flags & IOCB_HIPRI)
+		bio_set_polled(&bio, iocb);
+
+	qc = submit_bio(&bio);
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(bio.bi_private))
+			break;
+		if (!(iocb->ki_flags & IOCB_HIPRI) ||
+		    !blk_poll(bdev_get_queue(bdev), qc, true))
+			blk_io_schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	bio_release_pages(&bio, should_dirty);
+	if (unlikely(bio.bi_status))
+		ret = blk_status_to_errno(bio.bi_status);
+
+out:
+	if (vecs != inline_vecs)
+		kfree(vecs);
+
+	bio_uninit(&bio);
+
+	return ret;
+}
+
+struct blkdev_dio {
+	union {
+		struct kiocb		*iocb;
+		struct task_struct	*waiter;
+	};
+	size_t			size;
+	atomic_t		ref;
+	bool			multi_bio : 1;
+	bool			should_dirty : 1;
+	bool			is_sync : 1;
+	struct bio		bio;
+};
+
+static struct bio_set blkdev_dio_pool;
+
+static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
+{
+	struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
+}
+
+static void blkdev_bio_end_io(struct bio *bio)
+{
+	struct blkdev_dio *dio = bio->bi_private;
+	bool should_dirty = dio->should_dirty;
+
+	if (bio->bi_status && !dio->bio.bi_status)
+		dio->bio.bi_status = bio->bi_status;
+
+	if (!dio->multi_bio || atomic_dec_and_test(&dio->ref)) {
+		if (!dio->is_sync) {
+			struct kiocb *iocb = dio->iocb;
+			ssize_t ret;
+
+			if (likely(!dio->bio.bi_status)) {
+				ret = dio->size;
+				iocb->ki_pos += ret;
+			} else {
+				ret = blk_status_to_errno(dio->bio.bi_status);
+			}
+
+			dio->iocb->ki_complete(iocb, ret, 0);
+			if (dio->multi_bio)
+				bio_put(&dio->bio);
+		} else {
+			struct task_struct *waiter = dio->waiter;
+
+			WRITE_ONCE(dio->waiter, NULL);
+			blk_wake_io_task(waiter);
+		}
+	}
+
+	if (should_dirty) {
+		bio_check_pages_dirty(bio);
+	} else {
+		bio_release_pages(bio, false);
+		bio_put(bio);
+	}
+}
+
+static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+		unsigned int nr_pages)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = bdev_file_inode(file);
+	struct block_device *bdev = I_BDEV(inode);
+	struct blk_plug plug;
+	struct blkdev_dio *dio;
+	struct bio *bio;
+	bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0;
+	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
+	loff_t pos = iocb->ki_pos;
+	blk_qc_t qc = BLK_QC_T_NONE;
+	int ret = 0;
+
+	if ((pos | iov_iter_alignment(iter)) &
+	    (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	bio = bio_alloc_kiocb(iocb, nr_pages, &blkdev_dio_pool);
+
+	dio = container_of(bio, struct blkdev_dio, bio);
+	dio->is_sync = is_sync = is_sync_kiocb(iocb);
+	if (dio->is_sync) {
+		dio->waiter = current;
+		bio_get(bio);
+	} else {
+		dio->iocb = iocb;
+	}
+
+	dio->size = 0;
+	dio->multi_bio = false;
+	dio->should_dirty = is_read && iter_is_iovec(iter);
+
+	/*
+	 * Don't plug for HIPRI/polled IO, as those should go straight
+	 * to issue
+	 */
+	if (!is_poll)
+		blk_start_plug(&plug);
+
+	for (;;) {
+		bio_set_dev(bio, bdev);
+		bio->bi_iter.bi_sector = pos >> 9;
+		bio->bi_write_hint = iocb->ki_hint;
+		bio->bi_private = dio;
+		bio->bi_end_io = blkdev_bio_end_io;
+		bio->bi_ioprio = iocb->ki_ioprio;
+
+		ret = bio_iov_iter_get_pages(bio, iter);
+		if (unlikely(ret)) {
+			bio->bi_status = BLK_STS_IOERR;
+			bio_endio(bio);
+			break;
+		}
+
+		if (is_read) {
+			bio->bi_opf = REQ_OP_READ;
+			if (dio->should_dirty)
+				bio_set_pages_dirty(bio);
+		} else {
+			bio->bi_opf = dio_bio_write_op(iocb);
+			task_io_account_write(bio->bi_iter.bi_size);
+		}
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			bio->bi_opf |= REQ_NOWAIT;
+
+		dio->size += bio->bi_iter.bi_size;
+		pos += bio->bi_iter.bi_size;
+
+		nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS);
+		if (!nr_pages) {
+			bool polled = false;
+
+			if (iocb->ki_flags & IOCB_HIPRI) {
+				bio_set_polled(bio, iocb);
+				polled = true;
+			}
+
+			qc = submit_bio(bio);
+
+			if (polled)
+				WRITE_ONCE(iocb->ki_cookie, qc);
+			break;
+		}
+
+		if (!dio->multi_bio) {
+			/*
+			 * AIO needs an extra reference to ensure the dio
+			 * structure which is embedded into the first bio
+			 * stays around.
+			 */
+			if (!is_sync)
+				bio_get(bio);
+			dio->multi_bio = true;
+			atomic_set(&dio->ref, 2);
+		} else {
+			atomic_inc(&dio->ref);
+		}
+
+		submit_bio(bio);
+		bio = bio_alloc(GFP_KERNEL, nr_pages);
+	}
+
+	if (!is_poll)
+		blk_finish_plug(&plug);
+
+	if (!is_sync)
+		return -EIOCBQUEUED;
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!READ_ONCE(dio->waiter))
+			break;
+
+		if (!(iocb->ki_flags & IOCB_HIPRI) ||
+		    !blk_poll(bdev_get_queue(bdev), qc, true))
+			blk_io_schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+
+	if (!ret)
+		ret = blk_status_to_errno(dio->bio.bi_status);
+	if (likely(!ret))
+		ret = dio->size;
+
+	bio_put(&dio->bio);
+	return ret;
+}
+
+static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+{
+	unsigned int nr_pages;
+
+	if (!iov_iter_count(iter))
+		return 0;
+
+	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
+	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_VECS)
+		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);
+
+	return __blkdev_direct_IO(iocb, iter, bio_max_segs(nr_pages));
+}
+
+static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
+{
+	return block_write_full_page(page, blkdev_get_block, wbc);
+}
+
+static int blkdev_readpage(struct file * file, struct page * page)
+{
+	return block_read_full_page(page, blkdev_get_block);
+}
+
+static void blkdev_readahead(struct readahead_control *rac)
+{
+	mpage_readahead(rac, blkdev_get_block);
+}
+
+static int blkdev_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags, struct page **pagep,
+		void **fsdata)
+{
+	return block_write_begin(mapping, pos, len, flags, pagep,
+				 blkdev_get_block);
+}
+
+static int blkdev_write_end(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned copied, struct page *page,
+		void *fsdata)
+{
+	int ret;
+	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+
+	unlock_page(page);
+	put_page(page);
+
+	return ret;
+}
+
+static int blkdev_writepages(struct address_space *mapping,
+			     struct writeback_control *wbc)
+{
+	return generic_writepages(mapping, wbc);
+}
+
+const struct address_space_operations def_blk_aops = {
+	.set_page_dirty	= __set_page_dirty_buffers,
+	.readpage	= blkdev_readpage,
+	.readahead	= blkdev_readahead,
+	.writepage	= blkdev_writepage,
+	.write_begin	= blkdev_write_begin,
+	.write_end	= blkdev_write_end,
+	.writepages	= blkdev_writepages,
+	.direct_IO	= blkdev_direct_IO,
+	.migratepage	= buffer_migrate_page_norefs,
+	.is_dirty_writeback = buffer_check_dirty_writeback,
+};
+
+/*
+ * for a block special file file_inode(file)->i_size is zero
+ * so we compute the size by hand (just as in block_read/write above)
+ */
+static loff_t blkdev_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t retval;
+
+	inode_lock(bd_inode);
+	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
+	inode_unlock(bd_inode);
+	return retval;
+}
+
+static int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
+		int datasync)
+{
+	struct inode *bd_inode = bdev_file_inode(filp);
+	struct block_device *bdev = I_BDEV(bd_inode);
+	int error;
+
+	error = file_write_and_wait_range(filp, start, end);
+	if (error)
+		return error;
+
+	/*
+	 * There is no need to serialise calls to blkdev_issue_flush with
+	 * i_mutex and doing so causes performance issues with concurrent
+	 * O_SYNC writers to a block device.
+	 */
+	error = blkdev_issue_flush(bdev);
+	if (error == -EOPNOTSUPP)
+		error = 0;
+
+	return error;
+}
+
+static int blkdev_open(struct inode *inode, struct file *filp)
+{
+	struct block_device *bdev;
+
+	/*
+	 * Preserve backwards compatibility and allow large file access
+	 * even if userspace doesn't ask for it explicitly. Some mkfs
+	 * binary needs it. We might want to drop this workaround
+	 * during an unstable branch.
+	 */
+	filp->f_flags |= O_LARGEFILE;
+	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;
+
+	if (filp->f_flags & O_NDELAY)
+		filp->f_mode |= FMODE_NDELAY;
+	if (filp->f_flags & O_EXCL)
+		filp->f_mode |= FMODE_EXCL;
+	if ((filp->f_flags & O_ACCMODE) == 3)
+		filp->f_mode |= FMODE_WRITE_IOCTL;
+
+	bdev = blkdev_get_by_dev(inode->i_rdev, filp->f_mode, filp);
+	if (IS_ERR(bdev))
+		return PTR_ERR(bdev);
+	filp->f_mapping = bdev->bd_inode->i_mapping;
+	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
+	return 0;
+}
+
+static int blkdev_close(struct inode *inode, struct file *filp)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
+
+	blkdev_put(bdev, filp->f_mode);
+	return 0;
+}
+
+static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	fmode_t mode = file->f_mode;
+
+	/*
+	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
+	 * to updated it before every ioctl.
+	 */
+	if (file->f_flags & O_NDELAY)
+		mode |= FMODE_NDELAY;
+	else
+		mode &= ~FMODE_NDELAY;
+
+	return blkdev_ioctl(bdev, mode, cmd, arg);
+}
+
+/*
+ * Write data to the block device.  Only intended for the block device itself
+ * and the raw driver which basically is a fake block device.
+ *
+ * Does not take i_mutex for the write and thus is not for general purpose
+ * use.
+ */
+static ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t size = i_size_read(bd_inode);
+	struct blk_plug plug;
+	size_t shorted = 0;
+	ssize_t ret;
+
+	if (bdev_read_only(I_BDEV(bd_inode)))
+		return -EPERM;
+
+	if (IS_SWAPFILE(bd_inode) && !is_hibernate_resume_dev(bd_inode->i_rdev))
+		return -ETXTBSY;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	if (iocb->ki_pos >= size)
+		return -ENOSPC;
+
+	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
+		return -EOPNOTSUPP;
+
+	size -= iocb->ki_pos;
+	if (iov_iter_count(from) > size) {
+		shorted = iov_iter_count(from) - size;
+		iov_iter_truncate(from, size);
+	}
+
+	blk_start_plug(&plug);
+	ret = __generic_file_write_iter(iocb, from);
+	if (ret > 0)
+		ret = generic_write_sync(iocb, ret);
+	iov_iter_reexpand(from, iov_iter_count(from) + shorted);
+	blk_finish_plug(&plug);
+	return ret;
+}
+
+static ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *bd_inode = bdev_file_inode(file);
+	loff_t size = i_size_read(bd_inode);
+	loff_t pos = iocb->ki_pos;
+	size_t shorted = 0;
+	ssize_t ret;
+
+	if (pos >= size)
+		return 0;
+
+	size -= pos;
+	if (iov_iter_count(to) > size) {
+		shorted = iov_iter_count(to) - size;
+		iov_iter_truncate(to, size);
+	}
+
+	ret = generic_file_read_iter(iocb, to);
+	iov_iter_reexpand(to, iov_iter_count(to) + shorted);
+	return ret;
+}
+
+#define	BLKDEV_FALLOC_FL_SUPPORTED					\
+		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
+		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)
+
+static long blkdev_fallocate(struct file *file, int mode, loff_t start,
+			     loff_t len)
+{
+	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
+	loff_t end = start + len - 1;
+	loff_t isize;
+	int error;
+
+	/* Fail if we don't recognize the flags. */
+	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
+		return -EOPNOTSUPP;
+
+	/* Don't go off the end of the device. */
+	isize = i_size_read(bdev->bd_inode);
+	if (start >= isize)
+		return -EINVAL;
+	if (end >= isize) {
+		if (mode & FALLOC_FL_KEEP_SIZE) {
+			len = isize - start;
+			end = start + len - 1;
+		} else
+			return -EINVAL;
+	}
+
+	/*
+	 * Don't allow IO that isn't aligned to logical block size.
+	 */
+	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
+		return -EINVAL;
+
+	/* Invalidate the page cache, including dirty pages. */
+	error = truncate_bdev_range(bdev, file->f_mode, start, end);
+	if (error)
+		return error;
+
+	switch (mode) {
+	case FALLOC_FL_ZERO_RANGE:
+	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					    GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
+		break;
+	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
+		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, 0);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	if (error)
+		return error;
+
+	/*
+	 * Invalidate the page cache again; if someone wandered in and dirtied
+	 * a page, we just discard it - userspace has no way of knowing whether
+	 * the write happened before or after discard completing...
+	 */
+	return truncate_bdev_range(bdev, file->f_mode, start, end);
+}
+
+const struct file_operations def_blk_fops = {
+	.open		= blkdev_open,
+	.release	= blkdev_close,
+	.llseek		= blkdev_llseek,
+	.read_iter	= blkdev_read_iter,
+	.write_iter	= blkdev_write_iter,
+	.iopoll		= blkdev_iopoll,
+	.mmap		= generic_file_mmap,
+	.fsync		= blkdev_fsync,
+	.unlocked_ioctl	= block_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= compat_blkdev_ioctl,
+#endif
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= iter_file_splice_write,
+	.fallocate	= blkdev_fallocate,
+};
+
+static __init int blkdev_init(void)
+{
+	return bioset_init(&blkdev_dio_pool, 4,
+				offsetof(struct blkdev_dio, bio),
+				BIOSET_NEED_BVECS|BIOSET_PERCPU_CACHE);
+}
+module_init(blkdev_init);
diff --git a/block/genhd.c b/block/genhd.c
index 567549a..7b6e5e1 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -183,6 +183,7 @@
 	void (*probe)(dev_t devt);
 } *major_names[BLKDEV_MAJOR_HASH_SIZE];
 static DEFINE_MUTEX(major_names_lock);
+static DEFINE_SPINLOCK(major_names_spinlock);
 
 /* index in the above - for now: assume no multimajor ranges */
 static inline int major_to_index(unsigned major)
@@ -195,11 +196,11 @@
 {
 	struct blk_major_name *dp;
 
-	mutex_lock(&major_names_lock);
+	spin_lock(&major_names_spinlock);
 	for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
 		if (dp->major == offset)
 			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
-	mutex_unlock(&major_names_lock);
+	spin_unlock(&major_names_spinlock);
 }
 #endif /* CONFIG_PROC_FS */
 
@@ -271,6 +272,7 @@
 	p->next = NULL;
 	index = major_to_index(major);
 
+	spin_lock(&major_names_spinlock);
 	for (n = &major_names[index]; *n; n = &(*n)->next) {
 		if ((*n)->major == major)
 			break;
@@ -279,6 +281,7 @@
 		*n = p;
 	else
 		ret = -EBUSY;
+	spin_unlock(&major_names_spinlock);
 
 	if (ret < 0) {
 		printk("register_blkdev: cannot get major %u for %s\n",
@@ -298,6 +301,7 @@
 	int index = major_to_index(major);
 
 	mutex_lock(&major_names_lock);
+	spin_lock(&major_names_spinlock);
 	for (n = &major_names[index]; *n; n = &(*n)->next)
 		if ((*n)->major == major)
 			break;
@@ -307,6 +311,7 @@
 		p = *n;
 		*n = p->next;
 	}
+	spin_unlock(&major_names_spinlock);
 	mutex_unlock(&major_names_lock);
 	kfree(p);
 }
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index a4d4eeb..bd48210 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1008,23 +1008,14 @@
 	return ret_val;
 }
 
-/**
- * cppc_get_desired_perf - Get the value of desired performance register.
- * @cpunum: CPU from which to get desired performance.
- * @desired_perf: address of a variable to store the returned desired performance
- *
- * Return: 0 for success, -EIO otherwise.
- */
-int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
+static int cppc_get_perf(int cpunum, enum cppc_regs reg_idx, u64 *perf)
 {
 	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
-	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
-	struct cpc_register_resource *desired_reg;
-	struct cppc_pcc_data *pcc_ss_data = NULL;
+	struct cpc_register_resource *reg = &cpc_desc->cpc_regs[reg_idx];
 
-	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];
-
-	if (CPC_IN_PCC(desired_reg)) {
+	if (CPC_IN_PCC(reg)) {
+		int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
+		struct cppc_pcc_data *pcc_ss_data = NULL;
 		int ret = 0;
 
 		if (pcc_ss_id < 0)
@@ -1035,7 +1026,7 @@
 		down_write(&pcc_ss_data->pcc_lock);
 
 		if (send_pcc_cmd(pcc_ss_id, CMD_READ) >= 0)
-			cpc_read(cpunum, desired_reg, desired_perf);
+			cpc_read(cpunum, reg, perf);
 		else
 			ret = -EIO;
 
@@ -1044,13 +1035,37 @@
 		return ret;
 	}
 
-	cpc_read(cpunum, desired_reg, desired_perf);
+	cpc_read(cpunum, reg, perf);
 
 	return 0;
 }
+
+/**
+ * cppc_get_desired_perf - Get the desired performance register value.
+ * @cpunum: CPU from which to get desired performance.
+ * @desired_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_desired_perf(int cpunum, u64 *desired_perf)
+{
+	return cppc_get_perf(cpunum, DESIRED_PERF, desired_perf);
+}
 EXPORT_SYMBOL_GPL(cppc_get_desired_perf);
 
 /**
+ * cppc_get_nominal_perf - Get the nominal performance register value.
+ * @cpunum: CPU from which to get nominal performance.
+ * @nominal_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
+{
+	return cppc_get_perf(cpunum, NOMINAL_PERF, nominal_perf);
+}
+
+/**
  * cppc_get_perf_caps - Get a CPU's performance capabilities.
  * @cpunum: CPU from which to get capabilities info.
  * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c
index 1f6007a..89c22bc 100644
--- a/drivers/acpi/prmt.c
+++ b/drivers/acpi/prmt.c
@@ -288,10 +288,18 @@
 
 void __init init_prmt(void)
 {
+	struct acpi_table_header *tbl;
 	acpi_status status;
-	int mc = acpi_table_parse_entries(ACPI_SIG_PRMT, sizeof(struct acpi_table_prmt) +
+	int mc;
+
+	status = acpi_get_table(ACPI_SIG_PRMT, 0, &tbl);
+	if (ACPI_FAILURE(status))
+		return;
+
+	mc = acpi_table_parse_entries(ACPI_SIG_PRMT, sizeof(struct acpi_table_prmt) +
 					  sizeof (struct acpi_table_prmt_header),
 					  0, acpi_parse_prmt, 0);
+	acpi_put_table(tbl);
 	/*
 	 * Return immediately if PRMT table is not present or no PRM module found.
 	 */
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index b24513e..5b54c80 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -16,7 +16,6 @@
 #include <linux/signal.h>
 #include <linux/kthread.h>
 #include <linux/dmi.h>
-#include <linux/nls.h>
 #include <linux/dma-map-ops.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pgtable.h>
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index d568772..cbea78e 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1642,7 +1642,7 @@
 	}
 
 	dev->power.may_skip_resume = true;
-	dev->power.must_resume = false;
+	dev->power.must_resume = !dev_pm_test_driver_flags(dev, DPM_FLAG_MAY_SKIP_RESUME);
 
 	dpm_watchdog_set(&wd, dev);
 	device_lock(dev);
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 3bad326..b91a3a9 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -12,14 +12,11 @@
 /**
  * dev_pm_attach_wake_irq - Attach device interrupt as a wake IRQ
  * @dev: Device entry
- * @irq: Device wake-up capable interrupt
  * @wirq: Wake irq specific data
  *
- * Internal function to attach either a device IO interrupt or a
- * dedicated wake-up interrupt as a wake IRQ.
+ * Internal function to attach a dedicated wake-up interrupt as a wake IRQ.
  */
-static int dev_pm_attach_wake_irq(struct device *dev, int irq,
-				  struct wake_irq *wirq)
+static int dev_pm_attach_wake_irq(struct device *dev, struct wake_irq *wirq)
 {
 	unsigned long flags;
 
@@ -65,7 +62,7 @@
 	wirq->dev = dev;
 	wirq->irq = irq;
 
-	err = dev_pm_attach_wake_irq(dev, irq, wirq);
+	err = dev_pm_attach_wake_irq(dev, wirq);
 	if (err)
 		kfree(wirq);
 
@@ -196,7 +193,7 @@
 	if (err)
 		goto err_free_name;
 
-	err = dev_pm_attach_wake_irq(dev, irq, wirq);
+	err = dev_pm_attach_wake_irq(dev, wirq);
 	if (err)
 		goto err_free_irq;
 
diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c
index c84be00..26798da 100644
--- a/drivers/block/n64cart.c
+++ b/drivers/block/n64cart.c
@@ -129,8 +129,8 @@
 	}
 
 	reg_base = devm_platform_ioremap_resource(pdev, 0);
-	if (!reg_base)
-		return -EINVAL;
+	if (IS_ERR(reg_base))
+		return PTR_ERR(reg_base);
 
 	disk = blk_alloc_disk(NUMA_NO_NODE);
 	if (!disk)
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 57c6ae7..9b3bd08 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -762,7 +762,7 @@
 		goto out_free_vblk;
 
 	/* Default queue sizing is to fill the ring. */
-	if (likely(!virtblk_queue_depth)) {
+	if (!virtblk_queue_depth) {
 		queue_depth = vblk->vqs[0].vq->num_free;
 		/* ... but without indirect descs, we use 2 descs per req */
 		if (!virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC))
@@ -836,7 +836,7 @@
 	else
 		blk_size = queue_logical_block_size(q);
 
-	if (unlikely(blk_size < SECTOR_SIZE || blk_size > PAGE_SIZE)) {
+	if (blk_size < SECTOR_SIZE || blk_size > PAGE_SIZE) {
 		dev_err(&vdev->dev,
 			"block size is changed unexpectedly, now is %u\n",
 			blk_size);
diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c
index bb46698..6f3272b 100644
--- a/drivers/char/ipmi/ipmi_si_intf.c
+++ b/drivers/char/ipmi/ipmi_si_intf.c
@@ -591,7 +591,7 @@
 		smi_info->handlers->get_result(smi_info->si_sm, msg, 3);
 		if (msg[2] != 0) {
 			/* Error clearing flags */
-			dev_warn(smi_info->io.dev,
+			dev_warn_ratelimited(smi_info->io.dev,
 				 "Error clearing flags: %2.2x\n", msg[2]);
 		}
 		smi_info->si_state = SI_NORMAL;
@@ -683,10 +683,10 @@
 		/* We got the flags from the SMI, now handle them. */
 		smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
 		if (msg[2] != 0) {
-			dev_warn(smi_info->io.dev,
-				 "Couldn't get irq info: %x.\n", msg[2]);
-			dev_warn(smi_info->io.dev,
-				 "Maybe ok, but ipmi might run very slowly.\n");
+			dev_warn_ratelimited(smi_info->io.dev,
+				"Couldn't get irq info: %x,\n"
+				"Maybe ok, but ipmi might run very slowly.\n",
+				msg[2]);
 			smi_info->si_state = SI_NORMAL;
 			break;
 		}
@@ -721,7 +721,7 @@
 
 		smi_info->handlers->get_result(smi_info->si_sm, msg, 4);
 		if (msg[2] != 0)
-			dev_warn(smi_info->io.dev,
+			dev_warn_ratelimited(smi_info->io.dev,
 				 "Could not set the global enables: 0x%x.\n",
 				 msg[2]);
 
@@ -1343,7 +1343,7 @@
 
 		if (cc != IPMI_CC_NO_ERROR &&
 		    ++retry_count <= GET_DEVICE_ID_MAX_RETRY) {
-			dev_warn(smi_info->io.dev,
+			dev_warn_ratelimited(smi_info->io.dev,
 			    "BMC returned 0x%2.2x, retry get bmc device id\n",
 			    cc);
 			goto retry;
@@ -1605,7 +1605,7 @@
 									\
 	return snprintf(buf, 10, "%u\n", smi_get_stat(smi_info, name));	\
 }									\
-static DEVICE_ATTR(name, 0444, name##_show, NULL)
+static DEVICE_ATTR_RO(name)
 
 static ssize_t type_show(struct device *dev,
 			 struct device_attribute *attr,
@@ -1615,7 +1615,7 @@
 
 	return snprintf(buf, 10, "%s\n", si_to_str[smi_info->io.si_type]);
 }
-static DEVICE_ATTR(type, 0444, type_show, NULL);
+static DEVICE_ATTR_RO(type);
 
 static ssize_t interrupts_enabled_show(struct device *dev,
 				       struct device_attribute *attr,
@@ -1626,8 +1626,7 @@
 
 	return snprintf(buf, 10, "%d\n", enabled);
 }
-static DEVICE_ATTR(interrupts_enabled, 0444,
-		   interrupts_enabled_show, NULL);
+static DEVICE_ATTR_RO(interrupts_enabled);
 
 IPMI_SI_ATTR(short_timeouts);
 IPMI_SI_ATTR(long_timeouts);
@@ -1658,7 +1657,7 @@
 			smi_info->io.irq,
 			smi_info->io.slave_addr);
 }
-static DEVICE_ATTR(params, 0444, params_show, NULL);
+static DEVICE_ATTR_RO(params);
 
 static struct attribute *ipmi_si_dev_attrs[] = {
 	&dev_attr_type.attr,
diff --git a/drivers/clk/qcom/gcc-sm6350.c b/drivers/clk/qcom/gcc-sm6350.c
index 053089f..3236706 100644
--- a/drivers/clk/qcom/gcc-sm6350.c
+++ b/drivers/clk/qcom/gcc-sm6350.c
@@ -176,10 +176,6 @@
 	{ P_GPLL0_OUT_ODD, 2 },
 };
 
-static const struct clk_parent_data gcc_parent_data_2[] = {
-	{ .fw_name = "bi_tcxo" },
-	{ .hw = &gpll0_out_odd.clkr.hw },
-};
 static const struct clk_parent_data gcc_parent_data_2_ao[] = {
 	{ .fw_name = "bi_tcxo_ao" },
 	{ .hw = &gpll0_out_odd.clkr.hw },
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2d83a9f..1097f82 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -268,6 +268,7 @@
  * @get_min:		Callback to get minimum P state
  * @get_turbo:		Callback to get turbo P state
  * @get_scaling:	Callback to get frequency scaling factor
+ * @get_cpu_scaling:	Get frequency scaling factor for a given cpu
  * @get_aperf_mperf_shift: Callback to get the APERF vs MPERF frequency difference
  * @get_val:		Callback to convert P state to actual MSR write value
  * @get_vid:		Callback to get VID data for Atom platforms
@@ -281,6 +282,7 @@
 	int (*get_min)(void);
 	int (*get_turbo)(void);
 	int (*get_scaling)(void);
+	int (*get_cpu_scaling)(int cpu);
 	int (*get_aperf_mperf_shift)(void);
 	u64 (*get_val)(struct cpudata*, int pstate);
 	void (*get_vid)(struct cpudata *);
@@ -384,6 +386,15 @@
 	return cppc_perf.nominal_perf;
 }
 
+static u32 intel_pstate_cppc_nominal(int cpu)
+{
+	u64 nominal_perf;
+
+	if (cppc_get_nominal_perf(cpu, &nominal_perf))
+		return 0;
+
+	return nominal_perf;
+}
 #else /* CONFIG_ACPI_CPPC_LIB */
 static inline void intel_pstate_set_itmt_prio(int cpu)
 {
@@ -470,20 +481,6 @@
 
 	acpi_processor_unregister_performance(policy->cpu);
 }
-
-static bool intel_pstate_cppc_perf_valid(u32 perf, struct cppc_perf_caps *caps)
-{
-	return perf && perf <= caps->highest_perf && perf >= caps->lowest_perf;
-}
-
-static bool intel_pstate_cppc_perf_caps(struct cpudata *cpu,
-					struct cppc_perf_caps *caps)
-{
-	if (cppc_get_perf_caps(cpu->cpu, caps))
-		return false;
-
-	return caps->highest_perf && caps->lowest_perf <= caps->highest_perf;
-}
 #else /* CONFIG_ACPI */
 static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
@@ -506,15 +503,8 @@
 }
 #endif /* CONFIG_ACPI_CPPC_LIB */
 
-static void intel_pstate_hybrid_hwp_perf_ctl_parity(struct cpudata *cpu)
-{
-	pr_debug("CPU%d: Using PERF_CTL scaling for HWP\n", cpu->cpu);
-
-	cpu->pstate.scaling = cpu->pstate.perf_ctl_scaling;
-}
-
 /**
- * intel_pstate_hybrid_hwp_calibrate - Calibrate HWP performance levels.
+ * intel_pstate_hybrid_hwp_adjust - Calibrate HWP performance levels.
  * @cpu: Target CPU.
  *
  * On hybrid processors, HWP may expose more performance levels than there are
@@ -522,115 +512,46 @@
  * scaling factor between HWP performance levels and CPU frequency will be less
  * than the scaling factor between P-state values and CPU frequency.
  *
- * In that case, the scaling factor between HWP performance levels and CPU
- * frequency needs to be determined which can be done with the help of the
- * observation that certain HWP performance levels should correspond to certain
- * P-states, like for example the HWP highest performance should correspond
- * to the maximum turbo P-state of the CPU.
+ * In that case, adjust the CPU parameters used in computations accordingly.
  */
-static void intel_pstate_hybrid_hwp_calibrate(struct cpudata *cpu)
+static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 {
 	int perf_ctl_max_phys = cpu->pstate.max_pstate_physical;
 	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
 	int perf_ctl_turbo = pstate_funcs.get_turbo();
 	int turbo_freq = perf_ctl_turbo * perf_ctl_scaling;
-	int perf_ctl_max = pstate_funcs.get_max();
-	int max_freq = perf_ctl_max * perf_ctl_scaling;
-	int scaling = INT_MAX;
-	int freq;
+	int scaling = cpu->pstate.scaling;
 
 	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
-	pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, perf_ctl_max);
+	pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, pstate_funcs.get_max());
 	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
 	pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling);
-
 	pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate);
 	pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate);
-
-#ifdef CONFIG_ACPI
-	if (IS_ENABLED(CONFIG_ACPI_CPPC_LIB)) {
-		struct cppc_perf_caps caps;
-
-		if (intel_pstate_cppc_perf_caps(cpu, &caps)) {
-			if (intel_pstate_cppc_perf_valid(caps.nominal_perf, &caps)) {
-				pr_debug("CPU%d: Using CPPC nominal\n", cpu->cpu);
-
-				/*
-				 * If the CPPC nominal performance is valid, it
-				 * can be assumed to correspond to cpu_khz.
-				 */
-				if (caps.nominal_perf == perf_ctl_max_phys) {
-					intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
-					return;
-				}
-				scaling = DIV_ROUND_UP(cpu_khz, caps.nominal_perf);
-			} else if (intel_pstate_cppc_perf_valid(caps.guaranteed_perf, &caps)) {
-				pr_debug("CPU%d: Using CPPC guaranteed\n", cpu->cpu);
-
-				/*
-				 * If the CPPC guaranteed performance is valid,
-				 * it can be assumed to correspond to max_freq.
-				 */
-				if (caps.guaranteed_perf == perf_ctl_max) {
-					intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
-					return;
-				}
-				scaling = DIV_ROUND_UP(max_freq, caps.guaranteed_perf);
-			}
-		}
-	}
-#endif
-	/*
-	 * If using the CPPC data to compute the HWP-to-frequency scaling factor
-	 * doesn't work, use the HWP_CAP gauranteed perf for this purpose with
-	 * the assumption that it corresponds to max_freq.
-	 */
-	if (scaling > perf_ctl_scaling) {
-		pr_debug("CPU%d: Using HWP_CAP guaranteed\n", cpu->cpu);
-
-		if (cpu->pstate.max_pstate == perf_ctl_max) {
-			intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
-			return;
-		}
-		scaling = DIV_ROUND_UP(max_freq, cpu->pstate.max_pstate);
-		if (scaling > perf_ctl_scaling) {
-			/*
-			 * This should not happen, because it would mean that
-			 * the number of HWP perf levels was less than the
-			 * number of P-states, so use the PERF_CTL scaling in
-			 * that case.
-			 */
-			pr_debug("CPU%d: scaling (%d) out of range\n", cpu->cpu,
-				scaling);
-
-			intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
-			return;
-		}
-	}
+	pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling);
 
 	/*
-	 * If the product of the HWP performance scaling factor obtained above
-	 * and the HWP_CAP highest performance is greater than the maximum turbo
-	 * frequency corresponding to the pstate_funcs.get_turbo() return value,
-	 * the scaling factor is too high, so recompute it so that the HWP_CAP
-	 * highest performance corresponds to the maximum turbo frequency.
+	 * If the product of the HWP performance scaling factor and the HWP_CAP
+	 * highest performance is greater than the maximum turbo frequency
+	 * corresponding to the pstate_funcs.get_turbo() return value, the
+	 * scaling factor is too high, so recompute it to make the HWP_CAP
+	 * highest performance correspond to the maximum turbo frequency.
 	 */
 	if (turbo_freq < cpu->pstate.turbo_pstate * scaling) {
-		pr_debug("CPU%d: scaling too high (%d)\n", cpu->cpu, scaling);
-
 		cpu->pstate.turbo_freq = turbo_freq;
 		scaling = DIV_ROUND_UP(turbo_freq, cpu->pstate.turbo_pstate);
+		cpu->pstate.scaling = scaling;
+
+		pr_debug("CPU%d: refined HWP-to-frequency scaling factor: %d\n",
+			 cpu->cpu, scaling);
 	}
 
-	cpu->pstate.scaling = scaling;
-
-	pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, scaling);
-
 	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
 					 perf_ctl_scaling);
 
-	freq = perf_ctl_max_phys * perf_ctl_scaling;
-	cpu->pstate.max_pstate_physical = DIV_ROUND_UP(freq, scaling);
+	cpu->pstate.max_pstate_physical =
+			DIV_ROUND_UP(perf_ctl_max_phys * perf_ctl_scaling,
+				     scaling);
 
 	cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
 	/*
@@ -1861,6 +1782,38 @@
 	return ret;
 }
 
+#ifdef CONFIG_ACPI_CPPC_LIB
+static u32 hybrid_ref_perf;
+
+static int hybrid_get_cpu_scaling(int cpu)
+{
+	return DIV_ROUND_UP(core_get_scaling() * hybrid_ref_perf,
+			    intel_pstate_cppc_nominal(cpu));
+}
+
+static void intel_pstate_cppc_set_cpu_scaling(void)
+{
+	u32 min_nominal_perf = U32_MAX;
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		u32 nominal_perf = intel_pstate_cppc_nominal(cpu);
+
+		if (nominal_perf && nominal_perf < min_nominal_perf)
+			min_nominal_perf = nominal_perf;
+	}
+
+	if (min_nominal_perf < U32_MAX) {
+		hybrid_ref_perf = min_nominal_perf;
+		pstate_funcs.get_cpu_scaling = hybrid_get_cpu_scaling;
+	}
+}
+#else
+static inline void intel_pstate_cppc_set_cpu_scaling(void)
+{
+}
+#endif /* CONFIG_ACPI_CPPC_LIB */
+
 static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
 {
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
@@ -1889,10 +1842,8 @@
 
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
-	bool hybrid_cpu = boot_cpu_has(X86_FEATURE_HYBRID_CPU);
 	int perf_ctl_max_phys = pstate_funcs.get_max_physical();
-	int perf_ctl_scaling = hybrid_cpu ? cpu_khz / perf_ctl_max_phys :
-					    pstate_funcs.get_scaling();
+	int perf_ctl_scaling = pstate_funcs.get_scaling();
 
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
 	cpu->pstate.max_pstate_physical = perf_ctl_max_phys;
@@ -1901,10 +1852,13 @@
 	if (hwp_active && !hwp_mode_bdw) {
 		__intel_pstate_get_hwp_cap(cpu);
 
-		if (hybrid_cpu)
-			intel_pstate_hybrid_hwp_calibrate(cpu);
-		else
+		if (pstate_funcs.get_cpu_scaling) {
+			cpu->pstate.scaling = pstate_funcs.get_cpu_scaling(cpu->cpu);
+			if (cpu->pstate.scaling != perf_ctl_scaling)
+				intel_pstate_hybrid_hwp_adjust(cpu);
+		} else {
 			cpu->pstate.scaling = perf_ctl_scaling;
+		}
 	} else {
 		cpu->pstate.scaling = perf_ctl_scaling;
 		cpu->pstate.max_pstate = pstate_funcs.get_max();
@@ -3276,6 +3230,9 @@
 			if (!default_driver)
 				default_driver = &intel_pstate;
 
+			if (boot_cpu_has(X86_FEATURE_HYBRID_CPU))
+				intel_pstate_cppc_set_cpu_scaling();
+
 			goto hwp_cpu_matched;
 		}
 	} else {
diff --git a/drivers/dma-buf/Kconfig b/drivers/dma-buf/Kconfig
index 9561e3d..541efe0 100644
--- a/drivers/dma-buf/Kconfig
+++ b/drivers/dma-buf/Kconfig
@@ -42,6 +42,7 @@
 config DMABUF_MOVE_NOTIFY
 	bool "Move notify between drivers (EXPERIMENTAL)"
 	default n
+	depends on DMA_SHARED_BUFFER
 	help
 	  Don't pin buffers if the dynamic DMA-buf interface is available on
 	  both the exporter as well as the importer. This fixes a security
@@ -52,6 +53,7 @@
 
 config DMABUF_DEBUG
 	bool "DMA-BUF debug checks"
+	depends on DMA_SHARED_BUFFER
 	default y if DMA_API_DEBUG
 	help
 	  This option enables additional checks for DMA-BUF importers and
@@ -74,7 +76,7 @@
 
 menuconfig DMABUF_SYSFS_STATS
 	bool "DMA-BUF sysfs statistics"
-	select DMA_SHARED_BUFFER
+	depends on DMA_SHARED_BUFFER
 	help
 	   Choose this option to enable DMA-BUF sysfs statistics
 	   in location /sys/kernel/dmabuf/buffers.
diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 715e491..4c3fd2e 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -488,9 +488,7 @@
 					struct sk_buff *skb, u16 source_node_id,
 					bool is_broadcast, u16 ether_type)
 {
-	struct fwnet_device *dev;
 	int status;
-	__be64 guid;
 
 	switch (ether_type) {
 	case ETH_P_ARP:
@@ -503,7 +501,6 @@
 		goto err;
 	}
 
-	dev = netdev_priv(net);
 	/* Write metadata, and then pass to the receive level */
 	skb->dev = net;
 	skb->ip_summed = CHECKSUM_NONE;
@@ -512,7 +509,6 @@
 	 * Parse the encapsulation header. This actually does the job of
 	 * converting to an ethernet-like pseudo frame header.
 	 */
-	guid = cpu_to_be64(dev->card->guid);
 	if (dev_hard_header(skb, net, ether_type,
 			   is_broadcast ? net->broadcast : net->dev_addr,
 			   NULL, skb->len) >= 0) {
diff --git a/drivers/firmware/qcom_scm.c b/drivers/firmware/qcom_scm.c
index ced1964..2ee97ba 100644
--- a/drivers/firmware/qcom_scm.c
+++ b/drivers/firmware/qcom_scm.c
@@ -1147,6 +1147,64 @@
 }
 EXPORT_SYMBOL(qcom_scm_qsmmu500_wait_safe_toggle);
 
+bool qcom_scm_lmh_dcvsh_available(void)
+{
+	return __qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_LMH, QCOM_SCM_LMH_LIMIT_DCVSH);
+}
+EXPORT_SYMBOL(qcom_scm_lmh_dcvsh_available);
+
+int qcom_scm_lmh_profile_change(u32 profile_id)
+{
+	struct qcom_scm_desc desc = {
+		.svc = QCOM_SCM_SVC_LMH,
+		.cmd = QCOM_SCM_LMH_LIMIT_PROFILE_CHANGE,
+		.arginfo = QCOM_SCM_ARGS(1, QCOM_SCM_VAL),
+		.args[0] = profile_id,
+		.owner = ARM_SMCCC_OWNER_SIP,
+	};
+
+	return qcom_scm_call(__scm->dev, &desc, NULL);
+}
+EXPORT_SYMBOL(qcom_scm_lmh_profile_change);
+
+int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
+		       u64 limit_node, u32 node_id, u64 version)
+{
+	dma_addr_t payload_phys;
+	u32 *payload_buf;
+	int ret, payload_size = 5 * sizeof(u32);
+
+	struct qcom_scm_desc desc = {
+		.svc = QCOM_SCM_SVC_LMH,
+		.cmd = QCOM_SCM_LMH_LIMIT_DCVSH,
+		.arginfo = QCOM_SCM_ARGS(5, QCOM_SCM_RO, QCOM_SCM_VAL, QCOM_SCM_VAL,
+					QCOM_SCM_VAL, QCOM_SCM_VAL),
+		.args[1] = payload_size,
+		.args[2] = limit_node,
+		.args[3] = node_id,
+		.args[4] = version,
+		.owner = ARM_SMCCC_OWNER_SIP,
+	};
+
+	payload_buf = dma_alloc_coherent(__scm->dev, payload_size, &payload_phys, GFP_KERNEL);
+	if (!payload_buf)
+		return -ENOMEM;
+
+	payload_buf[0] = payload_fn;
+	payload_buf[1] = 0;
+	payload_buf[2] = payload_reg;
+	payload_buf[3] = 1;
+	payload_buf[4] = payload_val;
+
+	desc.args[0] = payload_phys;
+
+	ret = qcom_scm_call(__scm->dev, &desc, NULL);
+
+	dma_free_coherent(__scm->dev, payload_size, payload_buf, payload_phys);
+	return ret;
+}
+EXPORT_SYMBOL(qcom_scm_lmh_dcvsh);
+
 static int qcom_scm_find_dload_address(struct device *dev, u64 *addr)
 {
 	struct device_node *tcsr;
diff --git a/drivers/firmware/qcom_scm.h b/drivers/firmware/qcom_scm.h
index 632fe31..d92156c 100644
--- a/drivers/firmware/qcom_scm.h
+++ b/drivers/firmware/qcom_scm.h
@@ -114,6 +114,10 @@
 #define QCOM_SCM_SVC_HDCP		0x11
 #define QCOM_SCM_HDCP_INVOKE		0x01
 
+#define QCOM_SCM_SVC_LMH			0x13
+#define QCOM_SCM_LMH_LIMIT_PROFILE_CHANGE	0x01
+#define QCOM_SCM_LMH_LIMIT_DCVSH		0x10
+
 #define QCOM_SCM_SVC_SMMU_PROGRAM		0x15
 #define QCOM_SCM_SMMU_CONFIG_ERRATA1		0x03
 #define QCOM_SCM_SMMU_CONFIG_ERRATA1_CLIENT_ALL	0x02
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 8f53837..97178b307 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -468,14 +468,18 @@
 	return (fw_cap & ATOM_FIRMWARE_CAP_DYNAMIC_BOOT_CFG_ENABLE) ? true : false;
 }
 
-/*
- * Helper function to query RAS EEPROM address
+/**
+ * amdgpu_atomfirmware_ras_rom_addr -- Get the RAS EEPROM addr from VBIOS
+ * adev: amdgpu_device pointer
+ * i2c_address: pointer to u8; if not NULL, will contain
+ *    the RAS EEPROM address if the function returns true
  *
- * @adev: amdgpu_device pointer
- *
- * Return true if vbios supports ras rom address reporting
+ * Return true if VBIOS supports RAS EEPROM address reporting,
+ * else return false. If true and @i2c_address is not NULL,
+ * will contain the RAS ROM address.
  */
-bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev, uint8_t* i2c_address)
+bool amdgpu_atomfirmware_ras_rom_addr(struct amdgpu_device *adev,
+				      u8 *i2c_address)
 {
 	struct amdgpu_mode_info *mode_info = &adev->mode_info;
 	int index;
@@ -483,27 +487,39 @@
 	union firmware_info *firmware_info;
 	u8 frev, crev;
 
-	if (i2c_address == NULL)
-		return false;
-
-	*i2c_address = 0;
-
 	index = get_index_into_master_table(atom_master_list_of_data_tables_v2_1,
-			firmwareinfo);
+					    firmwareinfo);
 
 	if (amdgpu_atom_parse_data_header(adev->mode_info.atom_context,
-				index, &size, &frev, &crev, &data_offset)) {
+					  index, &size, &frev, &crev,
+					  &data_offset)) {
 		/* support firmware_info 3.4 + */
 		if ((frev == 3 && crev >=4) || (frev > 3)) {
 			firmware_info = (union firmware_info *)
 				(mode_info->atom_context->bios + data_offset);
-			*i2c_address = firmware_info->v34.ras_rom_i2c_slave_addr;
+			/* The ras_rom_i2c_slave_addr should ideally
+			 * be a 19-bit EEPROM address, which would be
+			 * used as is by the driver; see top of
+			 * amdgpu_eeprom.c.
+			 *
+			 * When this is the case, 0 is of course a
+			 * valid RAS EEPROM address, in which case,
+			 * we'll drop the first "if (firm...)" and only
+			 * leave the check for the pointer.
+			 *
+			 * The reason this works right now is because
+			 * ras_rom_i2c_slave_addr contains the EEPROM
+			 * device type qualifier 1010b in the top 4
+			 * bits.
+			 */
+			if (firmware_info->v34.ras_rom_i2c_slave_addr) {
+				if (i2c_address)
+					*i2c_address = firmware_info->v34.ras_rom_i2c_slave_addr;
+				return true;
+			}
 		}
 	}
 
-	if (*i2c_address != 0)
-		return true;
-
 	return false;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 8e5a7ac..7a73167 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -522,6 +522,7 @@
 			break;
 		case CHIP_RENOIR:
 		case CHIP_VANGOGH:
+		case CHIP_YELLOW_CARP:
 			domain |= AMDGPU_GEM_DOMAIN_GTT;
 			break;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b664029..f18240f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1181,7 +1181,12 @@
 	{0x1002, 0x73A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73A5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73A8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73A9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73AB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73AC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
+	{0x1002, 0x73AD, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73AE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
 	{0x1002, 0x73BF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SIENNA_CICHLID},
@@ -1197,6 +1202,11 @@
 	{0x1002, 0x73C0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
 	{0x1002, 0x73C1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
 	{0x1002, 0x73C3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
+	{0x1002, 0x73DA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
+	{0x1002, 0x73DB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
+	{0x1002, 0x73DC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
+	{0x1002, 0x73DD, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
+	{0x1002, 0x73DE, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
 	{0x1002, 0x73DF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVY_FLOUNDER},
 
 	/* DIMGREY_CAVEFISH */
@@ -1204,6 +1214,13 @@
 	{0x1002, 0x73E1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73E2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73E3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73E8, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73E9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73EA, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73EB, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73EC, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73ED, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
+	{0x1002, 0x73EF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 	{0x1002, 0x73FF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_DIMGREY_CAVEFISH},
 
 	/* Aldebaran */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c
index d94c541..5a6857c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fdinfo.c
@@ -59,6 +59,7 @@
 	uint64_t vram_mem = 0, gtt_mem = 0, cpu_mem = 0;
 	struct drm_file *file = f->private_data;
 	struct amdgpu_device *adev = drm_to_adev(file->minor->dev);
+	struct amdgpu_bo *root;
 	int ret;
 
 	ret = amdgpu_file_to_fpriv(f, &fpriv);
@@ -69,13 +70,19 @@
 	dev = PCI_SLOT(adev->pdev->devfn);
 	fn = PCI_FUNC(adev->pdev->devfn);
 
-	ret = amdgpu_bo_reserve(fpriv->vm.root.bo, false);
+	root = amdgpu_bo_ref(fpriv->vm.root.bo);
+	if (!root)
+		return;
+
+	ret = amdgpu_bo_reserve(root, false);
 	if (ret) {
 		DRM_ERROR("Fail to reserve bo\n");
 		return;
 	}
 	amdgpu_vm_get_memory(&fpriv->vm, &vram_mem, &gtt_mem, &cpu_mem);
-	amdgpu_bo_unreserve(fpriv->vm.root.bo);
+	amdgpu_bo_unreserve(root);
+	amdgpu_bo_unref(&root);
+
 	seq_printf(m, "pdev:\t%04x:%02x:%02x.%d\npasid:\t%u\n", domain, bus,
 			dev, fn, fpriv->vm.pasid);
 	seq_printf(m, "vram mem:\t%llu kB\n", vram_mem/1024UL);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 14499f0..8d682be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -552,6 +552,9 @@
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler)
+			drm_sched_stop(&ring->sched, NULL);
+
 		/* You can't wait for HW to signal if it's gone */
 		if (!drm_dev_is_unplugged(&adev->ddev))
 			r = amdgpu_fence_wait_empty(ring);
@@ -611,6 +614,11 @@
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
 
+		if (!ring->no_scheduler) {
+			drm_sched_resubmit_jobs(&ring->sched);
+			drm_sched_start(&ring->sched, true);
+		}
+
 		/* enable the interrupt */
 		if (ring->fence_drv.irq_src)
 			amdgpu_irq_get(adev, ring->fence_drv.irq_src,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index cb07cc3..d6aa032 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -341,21 +341,18 @@
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
 				     initial_domain,
 				     flags, ttm_bo_type_device, resv, &gobj);
-	if (r) {
-		if (r != -ERESTARTSYS) {
-			if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
-				flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-				goto retry;
-			}
-
-			if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
-				initial_domain |= AMDGPU_GEM_DOMAIN_GTT;
-				goto retry;
-			}
-			DRM_DEBUG("Failed to allocate GEM object (%llu, %d, %llu, %d)\n",
-				  size, initial_domain, args->in.alignment, r);
+	if (r && r != -ERESTARTSYS) {
+		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) {
+			flags &= ~AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+			goto retry;
 		}
-		return r;
+
+		if (initial_domain == AMDGPU_GEM_DOMAIN_VRAM) {
+			initial_domain |= AMDGPU_GEM_DOMAIN_GTT;
+			goto retry;
+		}
+		DRM_DEBUG("Failed to allocate GEM object (%llu, %d, %llu, %d)\n",
+				size, initial_domain, args->in.alignment, r);
 	}
 
 	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
index 5430003..675a72e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gtt_mgr.c
@@ -118,7 +118,7 @@
  * @man: TTM memory type manager
  * @tbo: TTM BO we need this range for
  * @place: placement flags and restrictions
- * @mem: the resulting mem object
+ * @res: the resulting mem object
  *
  * Dummy, allocate the node but no space for it yet.
  */
@@ -182,7 +182,7 @@
  * amdgpu_gtt_mgr_del - free ranges
  *
  * @man: TTM memory type manager
- * @mem: TTM memory object
+ * @res: TTM memory object
  *
  * Free the allocated GTT again.
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 23efdc6..9b41cb8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -469,10 +469,10 @@
 	 */
 	if (!skip_unsupport && (psp->cmd_buf_mem->resp.status || !timeout) && !ras_intr) {
 		if (ucode)
-			DRM_WARN("failed to load ucode (%s) ",
-				  amdgpu_ucode_name(ucode->ucode_id));
-		DRM_WARN("psp gfx command (%s) failed and response status is (0x%X)\n",
-			 psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id),
+			DRM_WARN("failed to load ucode %s(0x%X) ",
+				  amdgpu_ucode_name(ucode->ucode_id), ucode->ucode_id);
+		DRM_WARN("psp gfx command %s(0x%X) failed and response status is (0x%X)\n",
+			 psp_gfx_cmd_name(psp->cmd_buf_mem->cmd_id), psp->cmd_buf_mem->cmd_id,
 			 psp->cmd_buf_mem->resp.status);
 		if (!timeout) {
 			ret = -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 9dc3b2d..dc44c94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -114,27 +114,24 @@
 static bool __get_eeprom_i2c_addr(struct amdgpu_device *adev,
 				  struct amdgpu_ras_eeprom_control *control)
 {
-	uint8_t ras_rom_i2c_slave_addr;
+	u8 i2c_addr;
 
 	if (!control)
 		return false;
 
-	control->i2c_address = 0;
+	if (amdgpu_atomfirmware_ras_rom_addr(adev, &i2c_addr)) {
+		/* The address given by VBIOS is an 8-bit, wire-format
+		 * address, i.e. the most significant byte.
+		 *
+		 * Normalize it to a 19-bit EEPROM address. Remove the
+		 * device type identifier and make it a 7-bit address;
+		 * then make it a 19-bit EEPROM address. See top of
+		 * amdgpu_eeprom.c.
+		 */
+		i2c_addr = (i2c_addr & 0x0F) >> 1;
+		control->i2c_address = ((u32) i2c_addr) << 16;
 
-	if (amdgpu_atomfirmware_ras_rom_addr(adev, &ras_rom_i2c_slave_addr))
-	{
-		switch (ras_rom_i2c_slave_addr) {
-		case 0xA0:
-			control->i2c_address = 0;
-			return true;
-		case 0xA8:
-			control->i2c_address = 0x40000;
-			return true;
-		default:
-			dev_warn(adev->dev, "RAS EEPROM I2C slave address %02x not supported",
-				 ras_rom_i2c_slave_addr);
-			return false;
-		}
+		return true;
 	}
 
 	switch (adev->asic_type) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 2fd77c3..7b2b098 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -361,7 +361,7 @@
  * @man: TTM memory type manager
  * @tbo: TTM BO we need this range for
  * @place: placement flags and restrictions
- * @mem: the resulting mem object
+ * @res: the resulting mem object
  *
  * Allocate VRAM for the given BO.
  */
@@ -487,7 +487,7 @@
  * amdgpu_vram_mgr_del - free ranges
  *
  * @man: TTM memory type manager
- * @mem: TTM memory object
+ * @res: TTM memory object
  *
  * Free the allocated VRAM again.
  */
@@ -522,7 +522,7 @@
  * amdgpu_vram_mgr_alloc_sgt - allocate and fill a sg table
  *
  * @adev: amdgpu device pointer
- * @mem: TTM memory object
+ * @res: TTM memory object
  * @offset: byte offset from the base of VRAM BO
  * @length: number of bytes to export in sg_table
  * @dev: the other device
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
index ff2307d..23b066b 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
@@ -258,6 +258,8 @@
 	amdgpu_virt_fini_data_exchange(adev);
 	atomic_set(&adev->in_gpu_reset, 1);
 
+	xgpu_ai_mailbox_trans_msg(adev, IDH_READY_TO_RESET, 0, 0, 0);
+
 	do {
 		if (xgpu_ai_mailbox_peek_msg(adev) == IDH_FLR_NOTIFICATION_CMPL)
 			goto flr_done;
diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
index 5057263..bd3b231 100644
--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
+++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.h
@@ -37,6 +37,7 @@
 	IDH_REQ_GPU_RESET_ACCESS,
 
 	IDH_LOG_VF_ERROR       = 200,
+	IDH_READY_TO_RESET 	= 201,
 };
 
 enum idh_event {
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index ba1d3ab..f50045c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -85,11 +85,14 @@
 #define mmRCC_DEV0_EPF0_STRAP0_ALDE			0x0015
 #define mmRCC_DEV0_EPF0_STRAP0_ALDE_BASE_IDX		2
 
-#define mmBIF_DOORBELL_INT_CNTL_ALDE 			0x3878
+#define mmBIF_DOORBELL_INT_CNTL_ALDE 			0x00fe
 #define mmBIF_DOORBELL_INT_CNTL_ALDE_BASE_IDX 		2
 #define BIF_DOORBELL_INT_CNTL_ALDE__DOORBELL_INTERRUPT_DISABLE__SHIFT	0x18
 #define BIF_DOORBELL_INT_CNTL_ALDE__DOORBELL_INTERRUPT_DISABLE_MASK	0x01000000L
 
+#define mmBIF_INTR_CNTL_ALDE 				0x0101
+#define mmBIF_INTR_CNTL_ALDE_BASE_IDX 			2
+
 static void nbio_v7_4_query_ras_error_count(struct amdgpu_device *adev,
 					void *ras_error_status);
 
@@ -440,14 +443,23 @@
 	 */
 	uint32_t bif_intr_cntl;
 
-	bif_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL);
+	if (adev->asic_type == CHIP_ALDEBARAN)
+		bif_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL_ALDE);
+	else
+		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);
+
+		if (adev->asic_type == CHIP_ALDEBARAN)
+			WREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL_ALDE, bif_intr_cntl);
+		else
+			WREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL, bif_intr_cntl);
+
 	}
 
 	return 0;
@@ -476,14 +488,22 @@
 	 */
 	uint32_t bif_intr_cntl;
 
-	bif_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL);
+	if (adev->asic_type == CHIP_ALDEBARAN)
+		bif_intr_cntl = RREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL_ALDE);
+	else
+		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);
+
+		if (adev->asic_type == CHIP_ALDEBARAN)
+			WREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL_ALDE, bif_intr_cntl);
+		else
+			WREG32_SOC15(NBIO, 0, mmBIF_INTR_CNTL, bif_intr_cntl);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 42a35d95..fe9a7cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -904,14 +904,7 @@
 	case CHIP_POLARIS11:
 	case CHIP_POLARIS12:
 	case CHIP_TOPAZ:
-		/* Disable BACO support for the specific polaris12 SKU temporarily */
-		if ((adev->pdev->device == 0x699F) &&
-		     (adev->pdev->revision == 0xC7) &&
-		     (adev->pdev->subsystem_vendor == 0x1028) &&
-		     (adev->pdev->subsystem_device == 0x0039))
-			return false;
-		else
-			return amdgpu_dpm_is_baco_supported(adev);
+		return amdgpu_dpm_is_baco_supported(adev);
 	default:
 		return false;
 	}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 491373f..9fc8021 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -2484,7 +2484,8 @@
 	}
 	if (!p->xnack_enabled) {
 		pr_debug("XNACK not enabled for pasid 0x%x\n", pasid);
-		return -EFAULT;
+		r = -EFAULT;
+		goto out;
 	}
 	svms = &p->svms;
 
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 8167236..9b1fc54 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1200,7 +1200,7 @@
 	dc_hardware_init(adev->dm.dc);
 
 #if defined(CONFIG_DRM_AMD_DC_DCN)
-	if (adev->apu_flags) {
+	if ((adev->flags & AMD_IS_APU) && (adev->asic_type >= CHIP_CARRIZO)) {
 		struct dc_phy_addr_space_config pa_config;
 
 		mmhub_read_system_context(adev, &pa_config);
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 cd025c1..330edd6 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
@@ -1561,7 +1561,7 @@
 	struct dc_link *link,
 	const struct dc_link_settings *link_setting)
 {
-	struct link_training_settings lt_settings;
+	struct link_training_settings lt_settings = {0};
 
 	dp_decide_training_settings(
 			link,
@@ -1707,7 +1707,7 @@
 	bool skip_video_pattern)
 {
 	enum link_training_result status = LINK_TRAINING_SUCCESS;
-	struct link_training_settings lt_settings;
+	struct link_training_settings lt_settings = {0};
 	enum dp_link_encoding encoding =
 			dp_get_link_encoding_format(link_settings);
 
@@ -1923,7 +1923,7 @@
     struct dc_link_settings *link_settings,
     struct dc_link_training_overrides *lt_overrides)
 {
-	struct link_training_settings lt_settings;
+	struct link_training_settings lt_settings = {0};
 	enum link_training_result lt_status = LINK_TRAINING_SUCCESS;
 	enum dp_panel_mode panel_mode = DP_PANEL_MODE_DEFAULT;
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
index dc7823d2..dd38796 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn303/dcn303_resource.c
@@ -510,8 +510,12 @@
 	vpg = dcn303_vpg_create(ctx, vpg_inst);
 	afmt = dcn303_afmt_create(ctx, afmt_inst);
 
-	if (!enc1 || !vpg || !afmt)
+	if (!enc1 || !vpg || !afmt) {
+		kfree(enc1);
+		kfree(vpg);
+		kfree(afmt);
 		return NULL;
+	}
 
 	dcn30_dio_stream_encoder_construct(enc1, ctx, ctx->dc_bios, eng_id, vpg, afmt, &stream_enc_regs[eng_id],
 			&se_shift, &se_mask);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
index 7db268d..3b37213 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c
@@ -109,7 +109,7 @@
 	union dmub_rb_cmd cmd;
 
 	if (!dcn31_query_backlight_info(panel_cntl, &cmd))
-		return 0;
+		return false;
 
 	return cmd.panel_cntl.data.is_backlight_on;
 }
@@ -119,7 +119,7 @@
 	union dmub_rb_cmd cmd;
 
 	if (!dcn31_query_backlight_info(panel_cntl, &cmd))
-		return 0;
+		return false;
 
 	return cmd.panel_cntl.data.is_powered_on;
 }
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 fbed530..63bbdf8 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
@@ -2641,7 +2641,7 @@
 		for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
 			if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
 				if (mode_lib->vba.DRAMClockChangeWatermark >
-				dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
+					dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
 					mode_lib->vba.MinTTUVBlank[k] += 25;
 			}
 		}
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
index 2d55627..249cb0a 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c
@@ -2005,10 +2005,10 @@
 static struct amdgpu_device_attr amdgpu_device_attrs[] = {
 	AMDGPU_DEVICE_ATTR_RW(power_dpm_state,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(power_dpm_force_performance_level,	ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
-	AMDGPU_DEVICE_ATTR_RO(pp_num_states,				ATTR_FLAG_BASIC),
-	AMDGPU_DEVICE_ATTR_RO(pp_cur_state,				ATTR_FLAG_BASIC),
-	AMDGPU_DEVICE_ATTR_RW(pp_force_state,				ATTR_FLAG_BASIC),
-	AMDGPU_DEVICE_ATTR_RW(pp_table,					ATTR_FLAG_BASIC),
+	AMDGPU_DEVICE_ATTR_RO(pp_num_states,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
+	AMDGPU_DEVICE_ATTR_RO(pp_cur_state,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
+	AMDGPU_DEVICE_ATTR_RW(pp_force_state,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
+	AMDGPU_DEVICE_ATTR_RW(pp_table,					ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_sclk,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_mclk,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
 	AMDGPU_DEVICE_ATTR_RW(pp_dpm_socclk,				ATTR_FLAG_BASIC|ATTR_FLAG_ONEVF),
diff --git a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
index 715b422..8156729 100644
--- a/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
+++ b/drivers/gpu/drm/amd/pm/inc/amdgpu_smu.h
@@ -1335,6 +1335,30 @@
 #define WORKLOAD_MAP(profile, workload) \
 	[profile] = {1, (workload)}
 
+/**
+ * smu_memcpy_trailing - Copy the end of one structure into the middle of another
+ *
+ * @dst: Pointer to destination struct
+ * @first_dst_member: The member name in @dst where the overwrite begins
+ * @last_dst_member: The member name in @dst where the overwrite ends after
+ * @src: Pointer to the source struct
+ * @first_src_member: The member name in @src where the copy begins
+ *
+ */
+#define smu_memcpy_trailing(dst, first_dst_member, last_dst_member,	   \
+			    src, first_src_member)			   \
+({									   \
+	size_t __src_offset = offsetof(typeof(*(src)), first_src_member);  \
+	size_t __src_size = sizeof(*(src)) - __src_offset;		   \
+	size_t __dst_offset = offsetof(typeof(*(dst)), first_dst_member);  \
+	size_t __dst_size = offsetofend(typeof(*(dst)), last_dst_member) - \
+			    __dst_offset;				   \
+	BUILD_BUG_ON(__src_size != __dst_size);				   \
+	__builtin_memcpy((u8 *)(dst) + __dst_offset,			   \
+			 (u8 *)(src) + __src_offset,			   \
+			 __dst_size);					   \
+})
+
 #if !defined(SWSMU_CODE_LAYER_L2) && !defined(SWSMU_CODE_LAYER_L3) && !defined(SWSMU_CODE_LAYER_L4)
 int smu_get_power_limit(void *handle,
 			uint32_t *limit,
diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
index 465ff8d..e7803ce 100644
--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
@@ -27,6 +27,9 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <asm/div64.h>
+#if IS_ENABLED(CONFIG_X86_64)
+#include <asm/intel-family.h>
+#endif
 #include <drm/amdgpu_drm.h>
 #include "ppatomctrl.h"
 #include "atombios.h"
@@ -1733,6 +1736,17 @@
 	return result;
 }
 
+static bool intel_core_rkl_chk(void)
+{
+#if IS_ENABLED(CONFIG_X86_64)
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	return (c->x86 == 6 && c->x86_model == INTEL_FAM6_ROCKETLAKE);
+#else
+	return false;
+#endif
+}
+
 static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -1758,7 +1772,8 @@
 
 	data->mclk_dpm_key_disabled = hwmgr->feature_mask & PP_MCLK_DPM_MASK ? false : true;
 	data->sclk_dpm_key_disabled = hwmgr->feature_mask & PP_SCLK_DPM_MASK ? false : true;
-	data->pcie_dpm_key_disabled = hwmgr->feature_mask & PP_PCIE_DPM_MASK ? false : true;
+	data->pcie_dpm_key_disabled =
+		intel_core_rkl_chk() || !(hwmgr->feature_mask & PP_PCIE_DPM_MASK);
 	/* need to set voltage control types before EVV patching */
 	data->voltage_control = SMU7_VOLTAGE_CONTROL_NONE;
 	data->vddci_control = SMU7_VOLTAGE_CONTROL_NONE;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
index 273df66..e343cc2 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
@@ -483,10 +483,8 @@
 
 	if ((smc_dpm_table->table_header.format_revision == 4) &&
 	    (smc_dpm_table->table_header.content_revision == 6))
-		memcpy(&smc_pptable->MaxVoltageStepGfx,
-		       &smc_dpm_table->maxvoltagestepgfx,
-		       sizeof(*smc_dpm_table) - offsetof(struct atom_smc_dpm_info_v4_6, maxvoltagestepgfx));
-
+		smu_memcpy_trailing(smc_pptable, MaxVoltageStepGfx, BoardReserved,
+				    smc_dpm_table, maxvoltagestepgfx);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
index f966817..a5fc5d7 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
@@ -431,16 +431,16 @@
 
 	switch (smc_dpm_table->table_header.content_revision) {
 	case 5: /* nv10 and nv14 */
-		memcpy(smc_pptable->I2cControllers, smc_dpm_table->I2cControllers,
-			sizeof(*smc_dpm_table) - sizeof(smc_dpm_table->table_header));
+		smu_memcpy_trailing(smc_pptable, I2cControllers, BoardReserved,
+				    smc_dpm_table, I2cControllers);
 		break;
 	case 7: /* nv12 */
 		ret = amdgpu_atombios_get_data_table(adev, index, NULL, NULL, NULL,
 					      (uint8_t **)&smc_dpm_table_v4_7);
 		if (ret)
 			return ret;
-		memcpy(smc_pptable->I2cControllers, smc_dpm_table_v4_7->I2cControllers,
-			sizeof(*smc_dpm_table_v4_7) - sizeof(smc_dpm_table_v4_7->table_header));
+		smu_memcpy_trailing(smc_pptable, I2cControllers, BoardReserved,
+				    smc_dpm_table_v4_7, I2cControllers);
 		break;
 	default:
 		dev_err(smu->adev->dev, "smc_dpm_info with unsupported content revision %d!\n",
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
index 6eb50b0..3a34214 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
@@ -1869,7 +1869,7 @@
 		} else {
 			if (smu->gfx_actual_hard_min_freq > smu->gfx_actual_soft_max_freq) {
 				dev_err(smu->adev->dev,
-					"The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+					"The setting minimum sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
 					smu->gfx_actual_hard_min_freq,
 					smu->gfx_actual_soft_max_freq);
 				return -EINVAL;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
index b391380..5aa175e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu12/renoir_ppt.c
@@ -426,7 +426,7 @@
 		} else {
 			if (smu->gfx_actual_hard_min_freq > smu->gfx_actual_soft_max_freq) {
 				dev_err(smu->adev->dev,
-					"The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+					"The setting minimum sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
 					smu->gfx_actual_hard_min_freq,
 					smu->gfx_actual_soft_max_freq);
 				return -EINVAL;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
index ec8c30d..ab65202 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
@@ -409,9 +409,8 @@
 
 	if ((smc_dpm_table->table_header.format_revision == 4) &&
 	    (smc_dpm_table->table_header.content_revision == 10))
-		memcpy(&smc_pptable->GfxMaxCurrent,
-		       &smc_dpm_table->GfxMaxCurrent,
-		       sizeof(*smc_dpm_table) - offsetof(struct atom_smc_dpm_info_v4_10, GfxMaxCurrent));
+		smu_memcpy_trailing(smc_pptable, GfxMaxCurrent, reserved,
+				    smc_dpm_table, GfxMaxCurrent);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
index 0f17c25..627ba2e 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
@@ -731,7 +731,7 @@
 		} else {
 			if (smu->gfx_actual_hard_min_freq > smu->gfx_actual_soft_max_freq) {
 				dev_err(smu->adev->dev,
-					"The setting minimun sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
+					"The setting minimum sclk (%d) MHz is greater than the setting maximum sclk (%d) MHz\n",
 					smu->gfx_actual_hard_min_freq,
 					smu->gfx_actual_soft_max_freq);
 				return -EINVAL;
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.h b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
index 51dbe0e..d2969f6 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_requests.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_requests.h
@@ -6,7 +6,7 @@
 #ifndef INTEL_GT_REQUESTS_H
 #define INTEL_GT_REQUESTS_H
 
-#include <stddef.h>
+#include <linux/stddef.h>
 
 struct intel_engine_cs;
 struct intel_gt;
diff --git a/drivers/gpu/drm/mgag200/mgag200_pll.c b/drivers/gpu/drm/mgag200/mgag200_pll.c
index 7c903cf..e9ae22b 100644
--- a/drivers/gpu/drm/mgag200/mgag200_pll.c
+++ b/drivers/gpu/drm/mgag200/mgag200_pll.c
@@ -124,6 +124,7 @@
 	unsigned int computed;
 
 	m = n = p = s = 0;
+	delta = 0xffffffff;
 	permitteddelta = clock * 5 / 1000;
 
 	for (testp = 8; testp > 0; testp /= 2) {
diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
index 0da5b31..dfe5f1d 100644
--- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
+++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
@@ -58,25 +58,16 @@
 }
 
 static void lock_region(struct panfrost_device *pfdev, u32 as_nr,
-			u64 iova, size_t size)
+			u64 iova, u64 size)
 {
 	u8 region_width;
 	u64 region = iova & PAGE_MASK;
-	/*
-	 * fls returns:
-	 * 1 .. 32
-	 *
-	 * 10 + fls(num_pages)
-	 * results in the range (11 .. 42)
+
+	/* The size is encoded as ceil(log2) minus(1), which may be calculated
+	 * with fls. The size must be clamped to hardware bounds.
 	 */
-
-	size = round_up(size, PAGE_SIZE);
-
-	region_width = 10 + fls(size >> PAGE_SHIFT);
-	if ((size >> PAGE_SHIFT) != (1ul << (region_width - 11))) {
-		/* not pow2, so must go up to the next pow2 */
-		region_width += 1;
-	}
+	size = max_t(u64, size, AS_LOCK_REGION_MIN_SIZE);
+	region_width = fls64(size - 1) - 1;
 	region |= region_width;
 
 	/* Lock the region that needs to be updated */
@@ -87,7 +78,7 @@
 
 
 static int mmu_hw_do_operation_locked(struct panfrost_device *pfdev, int as_nr,
-				      u64 iova, size_t size, u32 op)
+				      u64 iova, u64 size, u32 op)
 {
 	if (as_nr < 0)
 		return 0;
@@ -104,7 +95,7 @@
 
 static int mmu_hw_do_operation(struct panfrost_device *pfdev,
 			       struct panfrost_mmu *mmu,
-			       u64 iova, size_t size, u32 op)
+			       u64 iova, u64 size, u32 op)
 {
 	int ret;
 
@@ -121,7 +112,7 @@
 	u64 transtab = cfg->arm_mali_lpae_cfg.transtab;
 	u64 memattr = cfg->arm_mali_lpae_cfg.memattr;
 
-	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0ULL, AS_COMMAND_FLUSH_MEM);
 
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), transtab & 0xffffffffUL);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), transtab >> 32);
@@ -137,7 +128,7 @@
 
 static void panfrost_mmu_disable(struct panfrost_device *pfdev, u32 as_nr)
 {
-	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0UL, AS_COMMAND_FLUSH_MEM);
+	mmu_hw_do_operation_locked(pfdev, as_nr, 0, ~0ULL, AS_COMMAND_FLUSH_MEM);
 
 	mmu_write(pfdev, AS_TRANSTAB_LO(as_nr), 0);
 	mmu_write(pfdev, AS_TRANSTAB_HI(as_nr), 0);
@@ -251,7 +242,7 @@
 
 static void panfrost_mmu_flush_range(struct panfrost_device *pfdev,
 				     struct panfrost_mmu *mmu,
-				     u64 iova, size_t size)
+				     u64 iova, u64 size)
 {
 	if (mmu->as < 0)
 		return;
diff --git a/drivers/gpu/drm/panfrost/panfrost_regs.h b/drivers/gpu/drm/panfrost/panfrost_regs.h
index 1940ff8..6c5a11e 100644
--- a/drivers/gpu/drm/panfrost/panfrost_regs.h
+++ b/drivers/gpu/drm/panfrost/panfrost_regs.h
@@ -316,6 +316,8 @@
 #define AS_FAULTSTATUS_ACCESS_TYPE_READ		(0x2 << 8)
 #define AS_FAULTSTATUS_ACCESS_TYPE_WRITE	(0x3 << 8)
 
+#define AS_LOCK_REGION_MIN_SIZE                 (1ULL << 15)
+
 #define gpu_write(dev, reg, data) writel(data, dev->iomem + reg)
 #define gpu_read(dev, reg) readl(dev->iomem + reg)
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index ea4add2..bb9e02c 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1160,9 +1160,9 @@
 	}
 
 	if (bo->deleted) {
-		ttm_bo_cleanup_refs(bo, false, false, locked);
+		ret = ttm_bo_cleanup_refs(bo, false, false, locked);
 		ttm_bo_put(bo);
-		return 0;
+		return ret == -EBUSY ? -ENOSPC : ret;
 	}
 
 	ttm_bo_del_from_lru(bo);
@@ -1216,7 +1216,7 @@
 	if (locked)
 		dma_resv_unlock(bo->base.resv);
 	ttm_bo_put(bo);
-	return ret;
+	return ret == -EBUSY ? -ENOSPC : ret;
 }
 
 void ttm_bo_tt_destroy(struct ttm_buffer_object *bo)
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 763fa6f..1c5ffe2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -143,7 +143,6 @@
 	struct ttm_resource *src_mem = bo->resource;
 	struct ttm_resource_manager *src_man =
 		ttm_manager_type(bdev, src_mem->mem_type);
-	struct ttm_resource src_copy = *src_mem;
 	union {
 		struct ttm_kmap_iter_tt tt;
 		struct ttm_kmap_iter_linear_io io;
@@ -173,11 +172,11 @@
 	}
 
 	ttm_move_memcpy(bo, dst_mem->num_pages, dst_iter, src_iter);
-	src_copy = *src_mem;
-	ttm_bo_move_sync_cleanup(bo, dst_mem);
 
 	if (!src_iter->ops->maps_tt)
-		ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, &src_copy);
+		ttm_kmap_iter_linear_io_fini(&_src_iter.io, bdev, src_mem);
+	ttm_bo_move_sync_cleanup(bo, dst_mem);
+
 out_src_iter:
 	if (!dst_iter->ops->maps_tt)
 		ttm_kmap_iter_linear_io_fini(&_dst_iter.io, bdev, dst_mem);
diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index 24031a8..d5cd8b5 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -32,7 +32,6 @@
 #define pr_fmt(fmt) "[TTM] " fmt
 
 #include <linux/sched.h>
-#include <linux/pagemap.h>
 #include <linux/shmem_fs.h>
 #include <linux/file.h>
 #include <drm/drm_cache.h>
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index b7dc32a..4a11150 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -1462,7 +1462,7 @@
 	.audio_startup = vc4_hdmi_audio_startup,
 };
 
-struct hdmi_codec_pdata vc4_hdmi_codec_pdata = {
+static struct hdmi_codec_pdata vc4_hdmi_codec_pdata = {
 	.ops = &vc4_hdmi_codec_ops,
 	.max_i2s_channels = 8,
 	.i2s = 1,
diff --git a/drivers/input/joystick/analog.c b/drivers/input/joystick/analog.c
index f798922..882c3c8b 100644
--- a/drivers/input/joystick/analog.c
+++ b/drivers/input/joystick/analog.c
@@ -28,10 +28,6 @@
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
 
-static bool use_ktime = true;
-module_param(use_ktime, bool, 0400);
-MODULE_PARM_DESC(use_ktime, "Use ktime for measuring I/O speed");
-
 /*
  * Option parsing.
  */
@@ -110,7 +106,6 @@
 	char cooked;
 	int bads;
 	int reads;
-	int speed;
 	int loop;
 	int fuzz;
 	int axes[4];
@@ -120,66 +115,6 @@
 };
 
 /*
- * Time macros.
- */
-
-#ifdef __i386__
-
-#include <linux/i8253.h>
-
-#define GET_TIME(x)	do { if (boot_cpu_has(X86_FEATURE_TSC)) x = (unsigned int)rdtsc(); else x = get_time_pit(); } while (0)
-#define DELTA(x,y)	(boot_cpu_has(X86_FEATURE_TSC) ? ((y) - (x)) : ((x) - (y) + ((x) < (y) ? PIT_TICK_RATE / HZ : 0)))
-#define TIME_NAME	(boot_cpu_has(X86_FEATURE_TSC)?"TSC":"PIT")
-static unsigned int get_time_pit(void)
-{
-        unsigned long flags;
-        unsigned int count;
-
-        raw_spin_lock_irqsave(&i8253_lock, flags);
-        outb_p(0x00, 0x43);
-        count = inb_p(0x40);
-        count |= inb_p(0x40) << 8;
-        raw_spin_unlock_irqrestore(&i8253_lock, flags);
-
-        return count;
-}
-#elif defined(__x86_64__)
-#define GET_TIME(x)	do { x = (unsigned int)rdtsc(); } while (0)
-#define DELTA(x,y)	((y)-(x))
-#define TIME_NAME	"TSC"
-#elif defined(__alpha__) || defined(CONFIG_ARM) || defined(CONFIG_ARM64) || defined(CONFIG_PPC) || defined(CONFIG_RISCV)
-#define GET_TIME(x)	do { x = get_cycles(); } while (0)
-#define DELTA(x,y)	((y)-(x))
-#define TIME_NAME	"get_cycles"
-#else
-#define FAKE_TIME
-static unsigned long analog_faketime = 0;
-#define GET_TIME(x)     do { x = analog_faketime++; } while(0)
-#define DELTA(x,y)	((y)-(x))
-#define TIME_NAME	"Unreliable"
-#warning Precise timer not defined for this architecture.
-#endif
-
-static inline u64 get_time(void)
-{
-	if (use_ktime) {
-		return ktime_get_ns();
-	} else {
-		unsigned int x;
-		GET_TIME(x);
-		return x;
-	}
-}
-
-static inline unsigned int delta(u64 x, u64 y)
-{
-	if (use_ktime)
-		return y - x;
-	else
-		return DELTA((unsigned int)x, (unsigned int)y);
-}
-
-/*
  * analog_decode() decodes analog joystick data and reports input events.
  */
 
@@ -234,18 +169,18 @@
 static int analog_cooked_read(struct analog_port *port)
 {
 	struct gameport *gameport = port->gameport;
-	u64 time[4], start, loop, now;
+	ktime_t time[4], start, loop, now;
 	unsigned int loopout, timeout;
 	unsigned char data[4], this, last;
 	unsigned long flags;
 	int i, j;
 
 	loopout = (ANALOG_LOOP_TIME * port->loop) / 1000;
-	timeout = ANALOG_MAX_TIME * port->speed;
+	timeout = ANALOG_MAX_TIME * NSEC_PER_MSEC;
 
 	local_irq_save(flags);
 	gameport_trigger(gameport);
-	now = get_time();
+	now = ktime_get();
 	local_irq_restore(flags);
 
 	start = now;
@@ -258,16 +193,16 @@
 
 		local_irq_disable();
 		this = gameport_read(gameport) & port->mask;
-		now = get_time();
+		now = ktime_get();
 		local_irq_restore(flags);
 
-		if ((last ^ this) && (delta(loop, now) < loopout)) {
+		if ((last ^ this) && (ktime_sub(now, loop) < loopout)) {
 			data[i] = last ^ this;
 			time[i] = now;
 			i++;
 		}
 
-	} while (this && (i < 4) && (delta(start, now) < timeout));
+	} while (this && (i < 4) && (ktime_sub(now, start) < timeout));
 
 	this <<= 4;
 
@@ -275,7 +210,7 @@
 		this |= data[i];
 		for (j = 0; j < 4; j++)
 			if (data[i] & (1 << j))
-				port->axes[j] = (delta(start, time[i]) << ANALOG_FUZZ_BITS) / port->loop;
+				port->axes[j] = ((u32)ktime_sub(time[i], start) << ANALOG_FUZZ_BITS) / port->loop;
 	}
 
 	return -(this != port->mask);
@@ -375,38 +310,22 @@
 {
 	struct gameport *gameport = port->gameport;
 	unsigned int i, t, tx;
-	u64 t1, t2, t3;
+	ktime_t t1, t2, t3;
 	unsigned long flags;
 
-	if (use_ktime) {
-		port->speed = 1000000;
-	} else {
-		local_irq_save(flags);
-		t1 = get_time();
-#ifdef FAKE_TIME
-		analog_faketime += 830;
-#endif
-		mdelay(1);
-		t2 = get_time();
-		t3 = get_time();
-		local_irq_restore(flags);
-
-		port->speed = delta(t1, t2) - delta(t2, t3);
-	}
-
 	tx = ~0;
 
 	for (i = 0; i < 50; i++) {
 		local_irq_save(flags);
-		t1 = get_time();
+		t1 = ktime_get();
 		for (t = 0; t < 50; t++) {
 			gameport_read(gameport);
-			t2 = get_time();
+			t2 = ktime_get();
 		}
-		t3 = get_time();
+		t3 = ktime_get();
 		local_irq_restore(flags);
 		udelay(i);
-		t = delta(t1, t2) - delta(t2, t3);
+		t = ktime_sub(t2, t1) - ktime_sub(t3, t2);
 		if (t < tx) tx = t;
 	}
 
@@ -611,7 +530,7 @@
 		t = gameport_read(gameport);
 		msleep(ANALOG_MAX_TIME);
 		port->mask = (gameport_read(gameport) ^ t) & t & 0xf;
-		port->fuzz = (port->speed * ANALOG_FUZZ_MAGIC) / port->loop / 1000 + ANALOG_FUZZ_BITS;
+		port->fuzz = (NSEC_PER_MSEC * ANALOG_FUZZ_MAGIC) / port->loop / 1000 + ANALOG_FUZZ_BITS;
 
 		for (i = 0; i < ANALOG_INIT_RETRIES; i++) {
 			if (!analog_cooked_read(port))
diff --git a/drivers/input/keyboard/Kconfig b/drivers/input/keyboard/Kconfig
index 40a070a..e75650e 100644
--- a/drivers/input/keyboard/Kconfig
+++ b/drivers/input/keyboard/Kconfig
@@ -210,7 +210,7 @@
 	select SERIO
 	help
 	  Say Y here if you want to use a LK201 or LK401 style serial
-	  keyboard. This keyboard is also useable on PCs if you attach
+	  keyboard. This keyboard is also usable on PCs if you attach
 	  it with the inputattach program. The connector pinout is
 	  described within lkkbd.c.
 
diff --git a/drivers/input/keyboard/adc-keys.c b/drivers/input/keyboard/adc-keys.c
index 6d5be48..bf72ab8 100644
--- a/drivers/input/keyboard/adc-keys.c
+++ b/drivers/input/keyboard/adc-keys.c
@@ -193,7 +193,7 @@
 MODULE_DEVICE_TABLE(of, adc_keys_of_match);
 #endif
 
-static struct platform_driver __refdata adc_keys_driver = {
+static struct platform_driver adc_keys_driver = {
 	.driver = {
 		.name = "adc_keys",
 		.of_match_table = of_match_ptr(adc_keys_of_match),
diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
index 90a59b9..1592da4 100644
--- a/drivers/input/keyboard/adp5588-keys.c
+++ b/drivers/input/keyboard/adp5588-keys.c
@@ -17,7 +17,7 @@
 #include <linux/platform_device.h>
 #include <linux/input.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 
 #include <linux/platform_data/adp5588.h>
diff --git a/drivers/input/keyboard/adp5589-keys.c b/drivers/input/keyboard/adp5589-keys.c
index 654e047..bdd2644 100644
--- a/drivers/input/keyboard/adp5589-keys.c
+++ b/drivers/input/keyboard/adp5589-keys.c
@@ -18,7 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/input.h>
 #include <linux/i2c.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 
 #include <linux/input/adp5589.h>
diff --git a/drivers/input/keyboard/ep93xx_keypad.c b/drivers/input/keyboard/ep93xx_keypad.c
index c819433..e0e931e 100644
--- a/drivers/input/keyboard/ep93xx_keypad.c
+++ b/drivers/input/keyboard/ep93xx_keypad.c
@@ -157,7 +157,7 @@
 
 	if (!keypad->enabled) {
 		ep93xx_keypad_config(keypad);
-		clk_enable(keypad->clk);
+		clk_prepare_enable(keypad->clk);
 		keypad->enabled = true;
 	}
 
@@ -169,7 +169,7 @@
 	struct ep93xx_keypad *keypad = input_get_drvdata(pdev);
 
 	if (keypad->enabled) {
-		clk_disable(keypad->clk);
+		clk_disable_unprepare(keypad->clk);
 		keypad->enabled = false;
 	}
 }
diff --git a/drivers/input/misc/Kconfig b/drivers/input/misc/Kconfig
index 498cde3..dd5227c 100644
--- a/drivers/input/misc/Kconfig
+++ b/drivers/input/misc/Kconfig
@@ -309,18 +309,6 @@
 	  To compile this driver as a module, choose M here: the module will be
 	  called gpio-vibra.
 
-config INPUT_IXP4XX_BEEPER
-	tristate "IXP4XX Beeper support"
-	depends on ARCH_IXP4XX
-	help
-	  If you say yes here, you can connect a beeper to the
-	  ixp4xx gpio pins. This is used by the LinkSys NSLU2.
-
-	  If unsure, say Y.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called ixp4xx-beeper.
-
 config INPUT_COBALT_BTNS
 	tristate "Cobalt button interface"
 	depends on MIPS_COBALT
@@ -811,16 +799,6 @@
 	  To compile this driver as a module, choose M here: the
 	  module will be called xen-kbdfront.
 
-config INPUT_SIRFSOC_ONKEY
-	tristate "CSR SiRFSoC power on/off/suspend key support"
-	depends on ARCH_SIRF && OF
-	default y
-	help
-	  Say Y here if you want to support for the SiRFSoC power on/off/suspend key
-	  in Linux, after you press the onkey, system will suspend.
-
-	  If unsure, say N.
-
 config INPUT_IDEAPAD_SLIDEBAR
 	tristate "IdeaPad Laptop Slidebar"
 	depends on INPUT
diff --git a/drivers/input/misc/Makefile b/drivers/input/misc/Makefile
index f593bee..b92c53a 100644
--- a/drivers/input/misc/Makefile
+++ b/drivers/input/misc/Makefile
@@ -44,7 +44,6 @@
 obj-$(CONFIG_INPUT_IMS_PCU)		+= ims-pcu.o
 obj-$(CONFIG_INPUT_IQS269A)		+= iqs269a.o
 obj-$(CONFIG_INPUT_IQS626A)		+= iqs626a.o
-obj-$(CONFIG_INPUT_IXP4XX_BEEPER)	+= ixp4xx-beeper.o
 obj-$(CONFIG_INPUT_KEYSPAN_REMOTE)	+= keyspan_remote.o
 obj-$(CONFIG_INPUT_KXTJ9)		+= kxtj9.o
 obj-$(CONFIG_INPUT_M68K_BEEP)		+= m68kspkr.o
@@ -74,7 +73,6 @@
 obj-$(CONFIG_INPUT_RK805_PWRKEY)	+= rk805-pwrkey.o
 obj-$(CONFIG_INPUT_SC27XX_VIBRA)	+= sc27xx-vibra.o
 obj-$(CONFIG_INPUT_SGI_BTNS)		+= sgi_btns.o
-obj-$(CONFIG_INPUT_SIRFSOC_ONKEY)	+= sirfsoc-onkey.o
 obj-$(CONFIG_INPUT_SOC_BUTTON_ARRAY)	+= soc_button_array.o
 obj-$(CONFIG_INPUT_SPARCSPKR)		+= sparcspkr.o
 obj-$(CONFIG_INPUT_STPMIC1_ONKEY)  	+= stpmic1_onkey.o
diff --git a/drivers/input/misc/ixp4xx-beeper.c b/drivers/input/misc/ixp4xx-beeper.c
deleted file mode 100644
index 05018d0..0000000
--- a/drivers/input/misc/ixp4xx-beeper.c
+++ /dev/null
@@ -1,183 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Generic IXP4xx beeper driver
- *
- * Copyright (C) 2005 Tower Technologies
- *
- * based on nslu2-io.c
- *  Copyright (C) 2004 Karen Spearel
- *
- * Author: Alessandro Zummo <a.zummo@towertech.it>
- * Maintainers: http://www.nslu2-linux.org/
- */
-
-#include <linux/module.h>
-#include <linux/input.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
-#include <linux/gpio.h>
-#include <mach/hardware.h>
-
-MODULE_AUTHOR("Alessandro Zummo <a.zummo@towertech.it>");
-MODULE_DESCRIPTION("ixp4xx beeper driver");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("platform:ixp4xx-beeper");
-
-static DEFINE_SPINLOCK(beep_lock);
-
-static int ixp4xx_timer2_irq;
-
-static void ixp4xx_spkr_control(unsigned int pin, unsigned int count)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&beep_lock, flags);
-
-	if (count) {
-		gpio_direction_output(pin, 0);
-		*IXP4XX_OSRT2 = (count & ~IXP4XX_OST_RELOAD_MASK) | IXP4XX_OST_ENABLE;
-	} else {
-		gpio_direction_output(pin, 1);
-		gpio_direction_input(pin);
-		*IXP4XX_OSRT2 = 0;
-	}
-
-	spin_unlock_irqrestore(&beep_lock, flags);
-}
-
-static int ixp4xx_spkr_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
-{
-	unsigned int pin = (unsigned int) input_get_drvdata(dev);
-	unsigned int count = 0;
-
-	if (type != EV_SND)
-		return -1;
-
-	switch (code) {
-		case SND_BELL:
-			if (value)
-				value = 1000;
-		case SND_TONE:
-			break;
-		default:
-			return -1;
-	}
-
-	if (value > 20 && value < 32767)
-		count = (ixp4xx_timer_freq / (value * 4)) - 1;
-
-	ixp4xx_spkr_control(pin, count);
-
-	return 0;
-}
-
-static irqreturn_t ixp4xx_spkr_interrupt(int irq, void *dev_id)
-{
-	unsigned int pin = (unsigned int) dev_id;
-
-	/* clear interrupt */
-	*IXP4XX_OSST = IXP4XX_OSST_TIMER_2_PEND;
-
-	/* flip the beeper output */
-	gpio_set_value(pin, !gpio_get_value(pin));
-
-	return IRQ_HANDLED;
-}
-
-static int ixp4xx_spkr_probe(struct platform_device *dev)
-{
-	struct input_dev *input_dev;
-	int irq;
-	int err;
-
-	input_dev = input_allocate_device();
-	if (!input_dev)
-		return -ENOMEM;
-
-	input_set_drvdata(input_dev, (void *) dev->id);
-
-	input_dev->name = "ixp4xx beeper";
-	input_dev->phys = "ixp4xx/gpio";
-	input_dev->id.bustype = BUS_HOST;
-	input_dev->id.vendor  = 0x001f;
-	input_dev->id.product = 0x0001;
-	input_dev->id.version = 0x0100;
-	input_dev->dev.parent = &dev->dev;
-
-	input_dev->evbit[0] = BIT_MASK(EV_SND);
-	input_dev->sndbit[0] = BIT_MASK(SND_BELL) | BIT_MASK(SND_TONE);
-	input_dev->event = ixp4xx_spkr_event;
-
-	irq = platform_get_irq(dev, 0);
-	if (irq < 0) {
-		err = irq;
-		goto err_free_device;
-	}
-
-	err = gpio_request(dev->id, "ixp4-beeper");
-	if (err)
-		goto err_free_device;
-
-	err = request_irq(irq, &ixp4xx_spkr_interrupt,
-			  IRQF_NO_SUSPEND, "ixp4xx-beeper",
-			  (void *) dev->id);
-	if (err)
-		goto err_free_gpio;
-	ixp4xx_timer2_irq = irq;
-
-	err = input_register_device(input_dev);
-	if (err)
-		goto err_free_irq;
-
-	platform_set_drvdata(dev, input_dev);
-
-	return 0;
-
- err_free_irq:
-	free_irq(irq, (void *)dev->id);
- err_free_gpio:
-	gpio_free(dev->id);
- err_free_device:
-	input_free_device(input_dev);
-
-	return err;
-}
-
-static int ixp4xx_spkr_remove(struct platform_device *dev)
-{
-	struct input_dev *input_dev = platform_get_drvdata(dev);
-	unsigned int pin = (unsigned int) input_get_drvdata(input_dev);
-
-	input_unregister_device(input_dev);
-
-	/* turn the speaker off */
-	disable_irq(ixp4xx_timer2_irq);
-	ixp4xx_spkr_control(pin, 0);
-
-	free_irq(ixp4xx_timer2_irq, (void *)dev->id);
-	gpio_free(dev->id);
-
-	return 0;
-}
-
-static void ixp4xx_spkr_shutdown(struct platform_device *dev)
-{
-	struct input_dev *input_dev = platform_get_drvdata(dev);
-	unsigned int pin = (unsigned int) input_get_drvdata(input_dev);
-
-	/* turn off the speaker */
-	disable_irq(ixp4xx_timer2_irq);
-	ixp4xx_spkr_control(pin, 0);
-}
-
-static struct platform_driver ixp4xx_spkr_platform_driver = {
-	.driver		= {
-		.name	= "ixp4xx-beeper",
-	},
-	.probe		= ixp4xx_spkr_probe,
-	.remove		= ixp4xx_spkr_remove,
-	.shutdown	= ixp4xx_spkr_shutdown,
-};
-module_platform_driver(ixp4xx_spkr_platform_driver);
-
diff --git a/drivers/input/misc/pm8941-pwrkey.c b/drivers/input/misc/pm8941-pwrkey.c
index 10e3fc0..3360960 100644
--- a/drivers/input/misc/pm8941-pwrkey.c
+++ b/drivers/input/misc/pm8941-pwrkey.c
@@ -284,7 +284,7 @@
 	}
 
 	if (pwrkey->data->supports_ps_hold_poff_config) {
-		pwrkey->reboot_notifier.notifier_call = pm8941_reboot_notify,
+		pwrkey->reboot_notifier.notifier_call = pm8941_reboot_notify;
 		error = register_reboot_notifier(&pwrkey->reboot_notifier);
 		if (error) {
 			dev_err(&pdev->dev, "failed to register reboot notifier: %d\n",
diff --git a/drivers/input/misc/sirfsoc-onkey.c b/drivers/input/misc/sirfsoc-onkey.c
deleted file mode 100644
index 7982bf8..0000000
--- a/drivers/input/misc/sirfsoc-onkey.c
+++ /dev/null
@@ -1,207 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Power key driver for SiRF PrimaII
- *
- * Copyright (c) 2013 - 2014 Cambridge Silicon Radio Limited, a CSR plc group
- * company.
- */
-
-#include <linux/module.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/input.h>
-#include <linux/rtc/sirfsoc_rtciobrg.h>
-#include <linux/of.h>
-#include <linux/workqueue.h>
-
-struct sirfsoc_pwrc_drvdata {
-	u32			pwrc_base;
-	struct input_dev	*input;
-	struct delayed_work	work;
-};
-
-#define PWRC_ON_KEY_BIT			(1 << 0)
-
-#define PWRC_INT_STATUS			0xc
-#define PWRC_INT_MASK			0x10
-#define PWRC_PIN_STATUS			0x14
-#define PWRC_KEY_DETECT_UP_TIME		20	/* ms*/
-
-static int sirfsoc_pwrc_is_on_key_down(struct sirfsoc_pwrc_drvdata *pwrcdrv)
-{
-	u32 state = sirfsoc_rtc_iobrg_readl(pwrcdrv->pwrc_base +
-							PWRC_PIN_STATUS);
-	return !(state & PWRC_ON_KEY_BIT); /* ON_KEY is active low */
-}
-
-static void sirfsoc_pwrc_report_event(struct work_struct *work)
-{
-	struct sirfsoc_pwrc_drvdata *pwrcdrv =
-		container_of(work, struct sirfsoc_pwrc_drvdata, work.work);
-
-	if (sirfsoc_pwrc_is_on_key_down(pwrcdrv)) {
-		schedule_delayed_work(&pwrcdrv->work,
-			msecs_to_jiffies(PWRC_KEY_DETECT_UP_TIME));
-	} else {
-		input_event(pwrcdrv->input, EV_KEY, KEY_POWER, 0);
-		input_sync(pwrcdrv->input);
-	}
-}
-
-static irqreturn_t sirfsoc_pwrc_isr(int irq, void *dev_id)
-{
-	struct sirfsoc_pwrc_drvdata *pwrcdrv = dev_id;
-	u32 int_status;
-
-	int_status = sirfsoc_rtc_iobrg_readl(pwrcdrv->pwrc_base +
-							PWRC_INT_STATUS);
-	sirfsoc_rtc_iobrg_writel(int_status & ~PWRC_ON_KEY_BIT,
-				 pwrcdrv->pwrc_base + PWRC_INT_STATUS);
-
-	input_event(pwrcdrv->input, EV_KEY, KEY_POWER, 1);
-	input_sync(pwrcdrv->input);
-	schedule_delayed_work(&pwrcdrv->work,
-			      msecs_to_jiffies(PWRC_KEY_DETECT_UP_TIME));
-
-	return IRQ_HANDLED;
-}
-
-static void sirfsoc_pwrc_toggle_interrupts(struct sirfsoc_pwrc_drvdata *pwrcdrv,
-					   bool enable)
-{
-	u32 int_mask;
-
-	int_mask = sirfsoc_rtc_iobrg_readl(pwrcdrv->pwrc_base + PWRC_INT_MASK);
-	if (enable)
-		int_mask |= PWRC_ON_KEY_BIT;
-	else
-		int_mask &= ~PWRC_ON_KEY_BIT;
-	sirfsoc_rtc_iobrg_writel(int_mask, pwrcdrv->pwrc_base + PWRC_INT_MASK);
-}
-
-static int sirfsoc_pwrc_open(struct input_dev *input)
-{
-	struct sirfsoc_pwrc_drvdata *pwrcdrv = input_get_drvdata(input);
-
-	sirfsoc_pwrc_toggle_interrupts(pwrcdrv, true);
-
-	return 0;
-}
-
-static void sirfsoc_pwrc_close(struct input_dev *input)
-{
-	struct sirfsoc_pwrc_drvdata *pwrcdrv = input_get_drvdata(input);
-
-	sirfsoc_pwrc_toggle_interrupts(pwrcdrv, false);
-	cancel_delayed_work_sync(&pwrcdrv->work);
-}
-
-static const struct of_device_id sirfsoc_pwrc_of_match[] = {
-	{ .compatible = "sirf,prima2-pwrc" },
-	{},
-};
-MODULE_DEVICE_TABLE(of, sirfsoc_pwrc_of_match);
-
-static int sirfsoc_pwrc_probe(struct platform_device *pdev)
-{
-	struct device_node *np = pdev->dev.of_node;
-	struct sirfsoc_pwrc_drvdata *pwrcdrv;
-	int irq;
-	int error;
-
-	pwrcdrv = devm_kzalloc(&pdev->dev, sizeof(struct sirfsoc_pwrc_drvdata),
-			       GFP_KERNEL);
-	if (!pwrcdrv) {
-		dev_info(&pdev->dev, "Not enough memory for the device data\n");
-		return -ENOMEM;
-	}
-
-	/*
-	 * We can't use of_iomap because pwrc is not mapped in memory,
-	 * the so-called base address is only offset in rtciobrg
-	 */
-	error = of_property_read_u32(np, "reg", &pwrcdrv->pwrc_base);
-	if (error) {
-		dev_err(&pdev->dev,
-			"unable to find base address of pwrc node in dtb\n");
-		return error;
-	}
-
-	pwrcdrv->input = devm_input_allocate_device(&pdev->dev);
-	if (!pwrcdrv->input)
-		return -ENOMEM;
-
-	pwrcdrv->input->name = "sirfsoc pwrckey";
-	pwrcdrv->input->phys = "pwrc/input0";
-	pwrcdrv->input->evbit[0] = BIT_MASK(EV_KEY);
-	input_set_capability(pwrcdrv->input, EV_KEY, KEY_POWER);
-
-	INIT_DELAYED_WORK(&pwrcdrv->work, sirfsoc_pwrc_report_event);
-
-	pwrcdrv->input->open = sirfsoc_pwrc_open;
-	pwrcdrv->input->close = sirfsoc_pwrc_close;
-
-	input_set_drvdata(pwrcdrv->input, pwrcdrv);
-
-	/* Make sure the device is quiesced */
-	sirfsoc_pwrc_toggle_interrupts(pwrcdrv, false);
-
-	irq = platform_get_irq(pdev, 0);
-	error = devm_request_irq(&pdev->dev, irq,
-				 sirfsoc_pwrc_isr, 0,
-				 "sirfsoc_pwrc_int", pwrcdrv);
-	if (error) {
-		dev_err(&pdev->dev, "unable to claim irq %d, error: %d\n",
-			irq, error);
-		return error;
-	}
-
-	error = input_register_device(pwrcdrv->input);
-	if (error) {
-		dev_err(&pdev->dev,
-			"unable to register input device, error: %d\n",
-			error);
-		return error;
-	}
-
-	dev_set_drvdata(&pdev->dev, pwrcdrv);
-	device_init_wakeup(&pdev->dev, 1);
-
-	return 0;
-}
-
-static int __maybe_unused sirfsoc_pwrc_resume(struct device *dev)
-{
-	struct sirfsoc_pwrc_drvdata *pwrcdrv = dev_get_drvdata(dev);
-	struct input_dev *input = pwrcdrv->input;
-
-	/*
-	 * Do not mask pwrc interrupt as we want pwrc work as a wakeup source
-	 * if users touch X_ONKEY_B, see arch/arm/mach-prima2/pm.c
-	 */
-	mutex_lock(&input->mutex);
-	if (input_device_enabled(input))
-		sirfsoc_pwrc_toggle_interrupts(pwrcdrv, true);
-	mutex_unlock(&input->mutex);
-
-	return 0;
-}
-
-static SIMPLE_DEV_PM_OPS(sirfsoc_pwrc_pm_ops, NULL, sirfsoc_pwrc_resume);
-
-static struct platform_driver sirfsoc_pwrc_driver = {
-	.probe		= sirfsoc_pwrc_probe,
-	.driver		= {
-		.name	= "sirfsoc-pwrc",
-		.pm	= &sirfsoc_pwrc_pm_ops,
-		.of_match_table = sirfsoc_pwrc_of_match,
-	}
-};
-
-module_platform_driver(sirfsoc_pwrc_driver);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Binghua Duan <Binghua.Duan@csr.com>, Xianglong Du <Xianglong.Du@csr.com>");
-MODULE_DESCRIPTION("CSR Prima2 PWRC Driver");
-MODULE_ALIAS("platform:sirfsoc-pwrc");
diff --git a/drivers/input/mouse/elan_i2c.h b/drivers/input/mouse/elan_i2c.h
index dc4a240..3c84dee 100644
--- a/drivers/input/mouse/elan_i2c.h
+++ b/drivers/input/mouse/elan_i2c.h
@@ -55,8 +55,9 @@
 #define ETP_FW_PAGE_SIZE_512	512
 #define ETP_FW_SIGNATURE_SIZE	6
 
-#define ETP_PRODUCT_ID_DELBIN	0x00C2
+#define ETP_PRODUCT_ID_WHITEBOX	0x00B8
 #define ETP_PRODUCT_ID_VOXEL	0x00BF
+#define ETP_PRODUCT_ID_DELBIN	0x00C2
 #define ETP_PRODUCT_ID_MAGPIE	0x0120
 #define ETP_PRODUCT_ID_BOBBA	0x0121
 
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index dad22c1..47af62c 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -105,6 +105,7 @@
 		u32 quirks;
 	} elan_i2c_quirks[] = {
 		{ 0x0D, ETP_PRODUCT_ID_DELBIN, ETP_QUIRK_QUICK_WAKEUP },
+		{ 0x0D, ETP_PRODUCT_ID_WHITEBOX, ETP_QUIRK_QUICK_WAKEUP },
 		{ 0x10, ETP_PRODUCT_ID_VOXEL, ETP_QUIRK_QUICK_WAKEUP },
 		{ 0x14, ETP_PRODUCT_ID_MAGPIE, ETP_QUIRK_QUICK_WAKEUP },
 		{ 0x14, ETP_PRODUCT_ID_BOBBA, ETP_QUIRK_QUICK_WAKEUP },
diff --git a/drivers/input/serio/parkbd.c b/drivers/input/serio/parkbd.c
index 3ac57a9..51b6850 100644
--- a/drivers/input/serio/parkbd.c
+++ b/drivers/input/serio/parkbd.c
@@ -220,16 +220,4 @@
 	.detach = parkbd_detach,
 	.devmodel = true,
 };
-
-static int __init parkbd_init(void)
-{
-	return parport_register_driver(&parkbd_parport_driver);
-}
-
-static void __exit parkbd_exit(void)
-{
-	parport_unregister_driver(&parkbd_parport_driver);
-}
-
-module_init(parkbd_init);
-module_exit(parkbd_exit);
+module_parport_driver(parkbd_parport_driver);
diff --git a/drivers/input/touchscreen/Kconfig b/drivers/input/touchscreen/Kconfig
index ad454cd..d4e7473 100644
--- a/drivers/input/touchscreen/Kconfig
+++ b/drivers/input/touchscreen/Kconfig
@@ -932,7 +932,7 @@
 	  - JASTEC USB Touch Controller/DigiTech DTR-02U
 	  - Zytronic controllers
 	  - Elo TouchSystems 2700 IntelliTouch
-	  - EasyTouch USB Touch Controller from Data Modul
+	  - EasyTouch USB Touch Controller from Data Module
 	  - e2i (Mimo monitors)
 
 	  Have a look at <http://linux.chapter7.ch/touchkit/> for
diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
index 263de3b..bb2e1cb 100644
--- a/drivers/input/touchscreen/edt-ft5x06.c
+++ b/drivers/input/touchscreen/edt-ft5x06.c
@@ -899,6 +899,7 @@
 		 * the identification registers.
 		 */
 		switch (rdbuf[0]) {
+		case 0x11:   /* EDT EP0110M09 */
 		case 0x35:   /* EDT EP0350M09 */
 		case 0x43:   /* EDT EP0430M09 */
 		case 0x50:   /* EDT EP0500M09 */
diff --git a/drivers/input/touchscreen/mms114.c b/drivers/input/touchscreen/mms114.c
index 0efd1a1..9fa3b0e 100644
--- a/drivers/input/touchscreen/mms114.c
+++ b/drivers/input/touchscreen/mms114.c
@@ -54,6 +54,7 @@
 
 enum mms_type {
 	TYPE_MMS114	= 114,
+	TYPE_MMS134S	= 134,
 	TYPE_MMS136	= 136,
 	TYPE_MMS152	= 152,
 	TYPE_MMS345L	= 345,
@@ -212,7 +213,7 @@
 		goto out;
 
 	/* MMS136 has slightly different event size */
-	if (data->type == TYPE_MMS136)
+	if (data->type == TYPE_MMS134S || data->type == TYPE_MMS136)
 		touch_size = packet_size / MMS136_EVENT_SIZE;
 	else
 		touch_size = packet_size / MMS114_EVENT_SIZE;
@@ -281,6 +282,7 @@
 		break;
 
 	case TYPE_MMS114:
+	case TYPE_MMS134S:
 	case TYPE_MMS136:
 		error = __mms114_read_reg(data, MMS114_TSP_REV, 6, buf);
 		if (error)
@@ -304,8 +306,9 @@
 	if (error < 0)
 		return error;
 
-	/* Only MMS114 and MMS136 have configuration and power on registers */
-	if (data->type != TYPE_MMS114 && data->type != TYPE_MMS136)
+	/* MMS114, MMS134S and MMS136 have configuration and power on registers */
+	if (data->type != TYPE_MMS114 && data->type != TYPE_MMS134S &&
+	    data->type != TYPE_MMS136)
 		return 0;
 
 	error = mms114_set_active(data, true);
@@ -487,7 +490,8 @@
 				     0, data->props.max_y, 0, 0);
 	}
 
-	if (data->type == TYPE_MMS114 || data->type == TYPE_MMS136) {
+	if (data->type == TYPE_MMS114 || data->type == TYPE_MMS134S ||
+	    data->type == TYPE_MMS136) {
 		/*
 		 * The firmware handles movement and pressure fuzz, so
 		 * don't duplicate that in software.
@@ -612,6 +616,9 @@
 		.compatible = "melfas,mms114",
 		.data = (void *)TYPE_MMS114,
 	}, {
+		.compatible = "melfas,mms134s",
+		.data = (void *)TYPE_MMS134S,
+	}, {
 		.compatible = "melfas,mms136",
 		.data = (void *)TYPE_MMS136,
 	}, {
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 8ad8618..124c41a 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -82,7 +82,7 @@
 choice
 	prompt "IOMMU default domain type"
 	depends on IOMMU_API
-	default IOMMU_DEFAULT_DMA_LAZY if AMD_IOMMU || INTEL_IOMMU
+	default IOMMU_DEFAULT_DMA_LAZY if X86 || IA64
 	default IOMMU_DEFAULT_DMA_STRICT
 	help
 	  Choose the type of IOMMU domain used to manage DMA API usage by
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index bdcf167..2a822b2 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -297,6 +297,22 @@
 	return amd_iommus_present;
 }
 
+#ifdef CONFIG_IRQ_REMAP
+static bool check_feature_on_all_iommus(u64 mask)
+{
+	bool ret = false;
+	struct amd_iommu *iommu;
+
+	for_each_iommu(iommu) {
+		ret = iommu_feature(iommu, mask);
+		if (!ret)
+			return false;
+	}
+
+	return true;
+}
+#endif
+
 /*
  * For IVHD type 0x11/0x40, EFR is also available via IVHD.
  * Default to IVHD EFR since it is available sooner
@@ -813,9 +829,9 @@
 	return 0;
 }
 
-#ifdef CONFIG_IRQ_REMAP
 static int iommu_init_ga_log(struct amd_iommu *iommu)
 {
+#ifdef CONFIG_IRQ_REMAP
 	u64 entry;
 
 	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
@@ -845,25 +861,9 @@
 err_out:
 	free_ga_log(iommu);
 	return -EINVAL;
-}
+#else
+	return 0;
 #endif /* CONFIG_IRQ_REMAP */
-
-static int iommu_init_ga(struct amd_iommu *iommu)
-{
-	int ret = 0;
-
-#ifdef CONFIG_IRQ_REMAP
-	/* Note: We have already checked GASup from IVRS table.
-	 *       Now, we need to make sure that GAMSup is set.
-	 */
-	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
-	    !iommu_feature(iommu, FEATURE_GAM_VAPIC))
-		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
-
-	ret = iommu_init_ga_log(iommu);
-#endif /* CONFIG_IRQ_REMAP */
-
-	return ret;
 }
 
 static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
@@ -1845,7 +1845,7 @@
 	if (iommu_feature(iommu, FEATURE_PPR) && alloc_ppr_log(iommu))
 		return -ENOMEM;
 
-	ret = iommu_init_ga(iommu);
+	ret = iommu_init_ga_log(iommu);
 	if (ret)
 		return ret;
 
@@ -2479,6 +2479,14 @@
 	}
 
 #ifdef CONFIG_IRQ_REMAP
+	/*
+	 * Note: We have already checked GASup from IVRS table.
+	 *       Now, we need to make sure that GAMSup is set.
+	 */
+	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) &&
+	    !check_feature_on_all_iommus(FEATURE_GAM_VAPIC))
+		amd_iommu_guest_ir = AMD_IOMMU_GUEST_IR_LEGACY_GA;
+
 	if (AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir))
 		amd_iommu_irq_ops.capability |= (1 << IRQ_POSTING_CAP);
 #endif
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 2014fe8..0c22878 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -514,9 +514,6 @@
 {
 	mutex_lock(&mm->context.lock);
 
-	/* Synchronize with READ_ONCE in update_pasid(). */
-	smp_store_release(&mm->pasid, pasid);
-
 	/* Update PASID MSR on all CPUs running the mm's tasks. */
 	on_each_cpu_mask(mm_cpumask(mm), _load_pasid, NULL, true);
 
@@ -792,7 +789,19 @@
 		goto prq_retry;
 	}
 
+	/*
+	 * A work in IO page fault workqueue may try to lock pasid_mutex now.
+	 * Holding pasid_mutex while waiting in iopf_queue_flush_dev() for
+	 * all works in the workqueue to finish may cause deadlock.
+	 *
+	 * It's unnecessary to hold pasid_mutex in iopf_queue_flush_dev().
+	 * Unlock it to allow the works to be handled while waiting for
+	 * them to finish.
+	 */
+	lockdep_assert_held(&pasid_mutex);
+	mutex_unlock(&pasid_mutex);
 	iopf_queue_flush_dev(dev);
+	mutex_lock(&pasid_mutex);
 
 	/*
 	 * Perform steps described in VT-d spec CH7.10 to drain page
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 0af42fb..9e8bc80 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -519,6 +519,7 @@
 
 	return new_iova->pfn_lo;
 }
+EXPORT_SYMBOL_GPL(alloc_iova_fast);
 
 /**
  * free_iova_fast - free iova pfn range into rcache
@@ -536,6 +537,7 @@
 
 	free_iova(iovad, pfn);
 }
+EXPORT_SYMBOL_GPL(free_iova_fast);
 
 #define fq_ring_for_each(i, fq) \
 	for ((i) = (fq)->head; (i) != (fq)->tail; (i) = ((i) + 1) % IOVA_FQ_SIZE)
diff --git a/drivers/misc/habanalabs/common/Makefile b/drivers/misc/habanalabs/common/Makefile
index 5d8b482..6ebe3c7 100644
--- a/drivers/misc/habanalabs/common/Makefile
+++ b/drivers/misc/habanalabs/common/Makefile
@@ -10,4 +10,5 @@
 		common/asid.o common/habanalabs_ioctl.o \
 		common/command_buffer.o common/hw_queue.o common/irq.o \
 		common/sysfs.o common/hwmon.o common/memory.o \
-		common/command_submission.o common/firmware_if.o
+		common/command_submission.o common/firmware_if.o \
+		common/state_dump.o
diff --git a/drivers/misc/habanalabs/common/command_buffer.c b/drivers/misc/habanalabs/common/command_buffer.c
index 719168c..8132a84 100644
--- a/drivers/misc/habanalabs/common/command_buffer.c
+++ b/drivers/misc/habanalabs/common/command_buffer.c
@@ -314,8 +314,6 @@
 
 	spin_lock(&mgr->cb_lock);
 	rc = idr_alloc(&mgr->cb_handles, cb, 1, 0, GFP_ATOMIC);
-	if (rc < 0)
-		rc = idr_alloc(&mgr->cb_handles, cb, 1, 0, GFP_KERNEL);
 	spin_unlock(&mgr->cb_lock);
 
 	if (rc < 0) {
@@ -552,7 +550,7 @@
 
 	vma->vm_private_data = cb;
 
-	rc = hdev->asic_funcs->cb_mmap(hdev, vma, cb->kernel_address,
+	rc = hdev->asic_funcs->mmap(hdev, vma, cb->kernel_address,
 					cb->bus_address, cb->size);
 	if (rc) {
 		spin_lock(&cb->lock);
diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index 80c60fb..7b0516c 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -38,7 +38,11 @@
 							kref);
 	struct hl_device *hdev = hw_sob->hdev;
 
+	dev_dbg(hdev->dev, "reset sob id %u\n", hw_sob->sob_id);
+
 	hdev->asic_funcs->reset_sob(hdev, hw_sob);
+
+	hw_sob->need_reset = false;
 }
 
 void hl_sob_reset_error(struct kref *ref)
@@ -52,6 +56,24 @@
 		hw_sob->q_idx, hw_sob->sob_id);
 }
 
+void hw_sob_put(struct hl_hw_sob *hw_sob)
+{
+	if (hw_sob)
+		kref_put(&hw_sob->kref, hl_sob_reset);
+}
+
+static void hw_sob_put_err(struct hl_hw_sob *hw_sob)
+{
+	if (hw_sob)
+		kref_put(&hw_sob->kref, hl_sob_reset_error);
+}
+
+void hw_sob_get(struct hl_hw_sob *hw_sob)
+{
+	if (hw_sob)
+		kref_get(&hw_sob->kref);
+}
+
 /**
  * hl_gen_sob_mask() - Generates a sob mask to be used in a monitor arm packet
  * @sob_base: sob base id
@@ -84,76 +106,29 @@
 	return 0;
 }
 
-static void sob_reset_work(struct work_struct *work)
-{
-	struct hl_cs_compl *hl_cs_cmpl =
-		container_of(work, struct hl_cs_compl, sob_reset_work);
-	struct hl_device *hdev = hl_cs_cmpl->hdev;
-
-	/*
-	 * A signal CS can get completion while the corresponding wait
-	 * for signal CS is on its way to the PQ. The wait for signal CS
-	 * will get stuck if the signal CS incremented the SOB to its
-	 * max value and there are no pending (submitted) waits on this
-	 * SOB.
-	 * We do the following to void this situation:
-	 * 1. The wait for signal CS must get a ref for the signal CS as
-	 *    soon as possible in cs_ioctl_signal_wait() and put it
-	 *    before being submitted to the PQ but after it incremented
-	 *    the SOB refcnt in init_signal_wait_cs().
-	 * 2. Signal/Wait for signal CS will decrement the SOB refcnt
-	 *    here.
-	 * These two measures guarantee that the wait for signal CS will
-	 * reset the SOB upon completion rather than the signal CS and
-	 * hence the above scenario is avoided.
-	 */
-	kref_put(&hl_cs_cmpl->hw_sob->kref, hl_sob_reset);
-
-	if (hl_cs_cmpl->type == CS_TYPE_COLLECTIVE_WAIT)
-		hdev->asic_funcs->reset_sob_group(hdev,
-				hl_cs_cmpl->sob_group);
-
-	kfree(hl_cs_cmpl);
-}
-
 static void hl_fence_release(struct kref *kref)
 {
 	struct hl_fence *fence =
 		container_of(kref, struct hl_fence, refcount);
 	struct hl_cs_compl *hl_cs_cmpl =
 		container_of(fence, struct hl_cs_compl, base_fence);
-	struct hl_device *hdev = hl_cs_cmpl->hdev;
 
-	/* EBUSY means the CS was never submitted and hence we don't have
-	 * an attached hw_sob object that we should handle here
-	 */
-	if (fence->error == -EBUSY)
-		goto free;
-
-	if ((hl_cs_cmpl->type == CS_TYPE_SIGNAL) ||
-		(hl_cs_cmpl->type == CS_TYPE_WAIT) ||
-		(hl_cs_cmpl->type == CS_TYPE_COLLECTIVE_WAIT)) {
-
-		dev_dbg(hdev->dev,
-			"CS 0x%llx type %d finished, sob_id: %d, sob_val: 0x%x\n",
-			hl_cs_cmpl->cs_seq,
-			hl_cs_cmpl->type,
-			hl_cs_cmpl->hw_sob->sob_id,
-			hl_cs_cmpl->sob_val);
-
-		queue_work(hdev->sob_reset_wq, &hl_cs_cmpl->sob_reset_work);
-
-		return;
-	}
-
-free:
 	kfree(hl_cs_cmpl);
 }
 
 void hl_fence_put(struct hl_fence *fence)
 {
-	if (fence)
-		kref_put(&fence->refcount, hl_fence_release);
+	if (IS_ERR_OR_NULL(fence))
+		return;
+	kref_put(&fence->refcount, hl_fence_release);
+}
+
+void hl_fences_put(struct hl_fence **fence, int len)
+{
+	int i;
+
+	for (i = 0; i < len; i++, fence++)
+		hl_fence_put(*fence);
 }
 
 void hl_fence_get(struct hl_fence *fence)
@@ -473,11 +448,139 @@
 	spin_unlock(&hdev->cs_mirror_lock);
 }
 
+/*
+ * force_complete_multi_cs - complete all contexts that wait on multi-CS
+ *
+ * @hdev: pointer to habanalabs device structure
+ */
+static void force_complete_multi_cs(struct hl_device *hdev)
+{
+	int i;
+
+	for (i = 0; i < MULTI_CS_MAX_USER_CTX; i++) {
+		struct multi_cs_completion *mcs_compl;
+
+		mcs_compl = &hdev->multi_cs_completion[i];
+
+		spin_lock(&mcs_compl->lock);
+
+		if (!mcs_compl->used) {
+			spin_unlock(&mcs_compl->lock);
+			continue;
+		}
+
+		/* when calling force complete no context should be waiting on
+		 * multi-cS.
+		 * We are calling the function as a protection for such case
+		 * to free any pending context and print error message
+		 */
+		dev_err(hdev->dev,
+				"multi-CS completion context %d still waiting when calling force completion\n",
+				i);
+		complete_all(&mcs_compl->completion);
+		spin_unlock(&mcs_compl->lock);
+	}
+}
+
+/*
+ * complete_multi_cs - complete all waiting entities on multi-CS
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @cs: CS structure
+ * The function signals a waiting entity that has an overlapping stream masters
+ * with the completed CS.
+ * For example:
+ * - a completed CS worked on stream master QID 4, multi CS completion
+ *   is actively waiting on stream master QIDs 3, 5. don't send signal as no
+ *   common stream master QID
+ * - a completed CS worked on stream master QID 4, multi CS completion
+ *   is actively waiting on stream master QIDs 3, 4. send signal as stream
+ *   master QID 4 is common
+ */
+static void complete_multi_cs(struct hl_device *hdev, struct hl_cs *cs)
+{
+	struct hl_fence *fence = cs->fence;
+	int i;
+
+	/* in case of multi CS check for completion only for the first CS */
+	if (cs->staged_cs && !cs->staged_first)
+		return;
+
+	for (i = 0; i < MULTI_CS_MAX_USER_CTX; i++) {
+		struct multi_cs_completion *mcs_compl;
+
+		mcs_compl = &hdev->multi_cs_completion[i];
+		if (!mcs_compl->used)
+			continue;
+
+		spin_lock(&mcs_compl->lock);
+
+		/*
+		 * complete if:
+		 * 1. still waiting for completion
+		 * 2. the completed CS has at least one overlapping stream
+		 *    master with the stream masters in the completion
+		 */
+		if (mcs_compl->used &&
+				(fence->stream_master_qid_map &
+					mcs_compl->stream_master_qid_map)) {
+			/* extract the timestamp only of first completed CS */
+			if (!mcs_compl->timestamp)
+				mcs_compl->timestamp =
+						ktime_to_ns(fence->timestamp);
+			complete_all(&mcs_compl->completion);
+		}
+
+		spin_unlock(&mcs_compl->lock);
+	}
+}
+
+static inline void cs_release_sob_reset_handler(struct hl_device *hdev,
+					struct hl_cs *cs,
+					struct hl_cs_compl *hl_cs_cmpl)
+{
+	/* Skip this handler if the cs wasn't submitted, to avoid putting
+	 * the hw_sob twice, since this case already handled at this point,
+	 * also skip if the hw_sob pointer wasn't set.
+	 */
+	if (!hl_cs_cmpl->hw_sob || !cs->submitted)
+		return;
+
+	spin_lock(&hl_cs_cmpl->lock);
+
+	/*
+	 * we get refcount upon reservation of signals or signal/wait cs for the
+	 * hw_sob object, and need to put it when the first staged cs
+	 * (which cotains the encaps signals) or cs signal/wait is completed.
+	 */
+	if ((hl_cs_cmpl->type == CS_TYPE_SIGNAL) ||
+			(hl_cs_cmpl->type == CS_TYPE_WAIT) ||
+			(hl_cs_cmpl->type == CS_TYPE_COLLECTIVE_WAIT) ||
+			(!!hl_cs_cmpl->encaps_signals)) {
+		dev_dbg(hdev->dev,
+				"CS 0x%llx type %d finished, sob_id: %d, sob_val: %u\n",
+				hl_cs_cmpl->cs_seq,
+				hl_cs_cmpl->type,
+				hl_cs_cmpl->hw_sob->sob_id,
+				hl_cs_cmpl->sob_val);
+
+		hw_sob_put(hl_cs_cmpl->hw_sob);
+
+		if (hl_cs_cmpl->type == CS_TYPE_COLLECTIVE_WAIT)
+			hdev->asic_funcs->reset_sob_group(hdev,
+					hl_cs_cmpl->sob_group);
+	}
+
+	spin_unlock(&hl_cs_cmpl->lock);
+}
+
 static void cs_do_release(struct kref *ref)
 {
 	struct hl_cs *cs = container_of(ref, struct hl_cs, refcount);
 	struct hl_device *hdev = cs->ctx->hdev;
 	struct hl_cs_job *job, *tmp;
+	struct hl_cs_compl *hl_cs_cmpl =
+			container_of(cs->fence, struct hl_cs_compl, base_fence);
 
 	cs->completed = true;
 
@@ -493,8 +596,9 @@
 		complete_job(hdev, job);
 
 	if (!cs->submitted) {
-		/* In case the wait for signal CS was submitted, the put occurs
-		 * in init_signal_wait_cs() or collective_wait_init_cs()
+		/*
+		 * In case the wait for signal CS was submitted, the fence put
+		 * occurs in init_signal_wait_cs() or collective_wait_init_cs()
 		 * right before hanging on the PQ.
 		 */
 		if (cs->type == CS_TYPE_WAIT ||
@@ -535,8 +639,20 @@
 			list_del(&cs->staged_cs_node);
 			spin_unlock(&hdev->cs_mirror_lock);
 		}
+
+		/* decrement refcount to handle when first staged cs
+		 * with encaps signals is completed.
+		 */
+		if (hl_cs_cmpl->encaps_signals)
+			kref_put(&hl_cs_cmpl->encaps_sig_hdl->refcount,
+						hl_encaps_handle_do_release);
 	}
 
+	if ((cs->type == CS_TYPE_WAIT || cs->type == CS_TYPE_COLLECTIVE_WAIT)
+			&& cs->encaps_signals)
+		kref_put(&cs->encaps_sig_hdl->refcount,
+					hl_encaps_handle_do_release);
+
 out:
 	/* Must be called before hl_ctx_put because inside we use ctx to get
 	 * the device
@@ -566,6 +682,10 @@
 	if (cs->timestamp)
 		cs->fence->timestamp = ktime_get();
 	complete_all(&cs->fence->completion);
+	complete_multi_cs(hdev, cs);
+
+	cs_release_sob_reset_handler(hdev, cs, hl_cs_cmpl);
+
 	hl_fence_put(cs->fence);
 
 	kfree(cs->jobs_in_queue_cnt);
@@ -621,6 +741,10 @@
 		break;
 	}
 
+	rc = hl_state_dump(hdev);
+	if (rc)
+		dev_err(hdev->dev, "Error during system state dump %d\n", rc);
+
 	cs_put(cs);
 
 	if (likely(!skip_reset_on_timeout)) {
@@ -661,6 +785,7 @@
 	cs->completed = false;
 	cs->type = cs_type;
 	cs->timestamp = !!(flags & HL_CS_FLAGS_TIMESTAMP);
+	cs->encaps_signals = !!(flags & HL_CS_FLAGS_ENCAP_SIGNALS);
 	cs->timeout_jiffies = timeout;
 	cs->skip_reset_on_timeout =
 		hdev->skip_reset_on_timeout ||
@@ -671,9 +796,9 @@
 	kref_init(&cs->refcount);
 	spin_lock_init(&cs->job_lock);
 
-	cs_cmpl = kmalloc(sizeof(*cs_cmpl), GFP_ATOMIC);
+	cs_cmpl = kzalloc(sizeof(*cs_cmpl), GFP_ATOMIC);
 	if (!cs_cmpl)
-		cs_cmpl = kmalloc(sizeof(*cs_cmpl), GFP_KERNEL);
+		cs_cmpl = kzalloc(sizeof(*cs_cmpl), GFP_KERNEL);
 
 	if (!cs_cmpl) {
 		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
@@ -698,7 +823,6 @@
 	cs_cmpl->hdev = hdev;
 	cs_cmpl->type = cs->type;
 	spin_lock_init(&cs_cmpl->lock);
-	INIT_WORK(&cs_cmpl->sob_reset_work, sob_reset_work);
 	cs->fence = &cs_cmpl->base_fence;
 
 	spin_lock(&ctx->cs_lock);
@@ -791,31 +915,22 @@
 		cs_rollback(hdev, cs);
 		cs_put(cs);
 	}
-}
 
-void hl_pending_cb_list_flush(struct hl_ctx *ctx)
-{
-	struct hl_pending_cb *pending_cb, *tmp;
-
-	list_for_each_entry_safe(pending_cb, tmp,
-			&ctx->pending_cb_list, cb_node) {
-		list_del(&pending_cb->cb_node);
-		hl_cb_put(pending_cb->cb);
-		kfree(pending_cb);
-	}
+	force_complete_multi_cs(hdev);
 }
 
 static void
 wake_pending_user_interrupt_threads(struct hl_user_interrupt *interrupt)
 {
 	struct hl_user_pending_interrupt *pend;
+	unsigned long flags;
 
-	spin_lock(&interrupt->wait_list_lock);
+	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
 	list_for_each_entry(pend, &interrupt->wait_list_head, wait_list_node) {
 		pend->fence.error = -EIO;
 		complete_all(&pend->fence.completion);
 	}
-	spin_unlock(&interrupt->wait_list_lock);
+	spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 }
 
 void hl_release_pending_user_interrupts(struct hl_device *hdev)
@@ -981,6 +1096,10 @@
 		return CS_TYPE_WAIT;
 	else if (cs_type_flags & HL_CS_FLAGS_COLLECTIVE_WAIT)
 		return CS_TYPE_COLLECTIVE_WAIT;
+	else if (cs_type_flags & HL_CS_FLAGS_RESERVE_SIGNALS_ONLY)
+		return CS_RESERVE_SIGNALS;
+	else if (cs_type_flags & HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY)
+		return CS_UNRESERVE_SIGNALS;
 	else
 		return CS_TYPE_DEFAULT;
 }
@@ -1081,7 +1200,8 @@
 }
 
 static int cs_staged_submission(struct hl_device *hdev, struct hl_cs *cs,
-				u64 sequence, u32 flags)
+				u64 sequence, u32 flags,
+				u32 encaps_signal_handle)
 {
 	if (!(flags & HL_CS_FLAGS_STAGED_SUBMISSION))
 		return 0;
@@ -1093,6 +1213,9 @@
 		/* Staged CS sequence is the first CS sequence */
 		INIT_LIST_HEAD(&cs->staged_cs_node);
 		cs->staged_sequence = cs->sequence;
+
+		if (cs->encaps_signals)
+			cs->encaps_sig_hdl_id = encaps_signal_handle;
 	} else {
 		/* User sequence will be validated in 'hl_hw_queue_schedule_cs'
 		 * under the cs_mirror_lock
@@ -1108,9 +1231,20 @@
 	return 0;
 }
 
+static u32 get_stream_master_qid_mask(struct hl_device *hdev, u32 qid)
+{
+	int i;
+
+	for (i = 0; i < hdev->stream_master_qid_arr_size; i++)
+		if (qid == hdev->stream_master_qid_arr[i])
+			return BIT(i);
+
+	return 0;
+}
+
 static int cs_ioctl_default(struct hl_fpriv *hpriv, void __user *chunks,
 				u32 num_chunks, u64 *cs_seq, u32 flags,
-				u32 timeout)
+				u32 encaps_signals_handle, u32 timeout)
 {
 	bool staged_mid, int_queues_only = true;
 	struct hl_device *hdev = hpriv->hdev;
@@ -1121,6 +1255,7 @@
 	struct hl_cs *cs;
 	struct hl_cb *cb;
 	u64 user_sequence;
+	u8 stream_master_qid_map = 0;
 	int rc, i;
 
 	cntr = &hdev->aggregated_cs_counters;
@@ -1148,7 +1283,8 @@
 
 	hl_debugfs_add_cs(cs);
 
-	rc = cs_staged_submission(hdev, cs, user_sequence, flags);
+	rc = cs_staged_submission(hdev, cs, user_sequence, flags,
+						encaps_signals_handle);
 	if (rc)
 		goto free_cs_object;
 
@@ -1179,9 +1315,20 @@
 			cb = (struct hl_cb *) (uintptr_t) chunk->cb_handle;
 		}
 
-		if (queue_type == QUEUE_TYPE_EXT || queue_type == QUEUE_TYPE_HW)
+		if (queue_type == QUEUE_TYPE_EXT ||
+						queue_type == QUEUE_TYPE_HW) {
 			int_queues_only = false;
 
+			/*
+			 * store which stream are being used for external/HW
+			 * queues of this CS
+			 */
+			if (hdev->supports_wait_for_multi_cs)
+				stream_master_qid_map |=
+					get_stream_master_qid_mask(hdev,
+							chunk->queue_index);
+		}
+
 		job = hl_cs_allocate_job(hdev, queue_type,
 						is_kernel_allocated_cb);
 		if (!job) {
@@ -1242,6 +1389,13 @@
 		goto free_cs_object;
 	}
 
+	/*
+	 * store the (external/HW queues) streams used by the CS in the
+	 * fence object for multi-CS completion
+	 */
+	if (hdev->supports_wait_for_multi_cs)
+		cs->fence->stream_master_qid_map = stream_master_qid_map;
+
 	rc = hl_hw_queue_schedule_cs(cs);
 	if (rc) {
 		if (rc != -EAGAIN)
@@ -1270,130 +1424,6 @@
 	return rc;
 }
 
-static int pending_cb_create_job(struct hl_device *hdev, struct hl_ctx *ctx,
-		struct hl_cs *cs, struct hl_cb *cb, u32 size, u32 hw_queue_id)
-{
-	struct hw_queue_properties *hw_queue_prop;
-	struct hl_cs_counters_atomic *cntr;
-	struct hl_cs_job *job;
-
-	hw_queue_prop = &hdev->asic_prop.hw_queues_props[hw_queue_id];
-	cntr = &hdev->aggregated_cs_counters;
-
-	job = hl_cs_allocate_job(hdev, hw_queue_prop->type, true);
-	if (!job) {
-		atomic64_inc(&ctx->cs_counters.out_of_mem_drop_cnt);
-		atomic64_inc(&cntr->out_of_mem_drop_cnt);
-		dev_err(hdev->dev, "Failed to allocate a new job\n");
-		return -ENOMEM;
-	}
-
-	job->id = 0;
-	job->cs = cs;
-	job->user_cb = cb;
-	atomic_inc(&job->user_cb->cs_cnt);
-	job->user_cb_size = size;
-	job->hw_queue_id = hw_queue_id;
-	job->patched_cb = job->user_cb;
-	job->job_cb_size = job->user_cb_size;
-
-	/* increment refcount as for external queues we get completion */
-	cs_get(cs);
-
-	cs->jobs_in_queue_cnt[job->hw_queue_id]++;
-
-	list_add_tail(&job->cs_node, &cs->job_list);
-
-	hl_debugfs_add_job(hdev, job);
-
-	return 0;
-}
-
-static int hl_submit_pending_cb(struct hl_fpriv *hpriv)
-{
-	struct hl_device *hdev = hpriv->hdev;
-	struct hl_ctx *ctx = hpriv->ctx;
-	struct hl_pending_cb *pending_cb, *tmp;
-	struct list_head local_cb_list;
-	struct hl_cs *cs;
-	struct hl_cb *cb;
-	u32 hw_queue_id;
-	u32 cb_size;
-	int process_list, rc = 0;
-
-	if (list_empty(&ctx->pending_cb_list))
-		return 0;
-
-	process_list = atomic_cmpxchg(&ctx->thread_pending_cb_token, 1, 0);
-
-	/* Only a single thread is allowed to process the list */
-	if (!process_list)
-		return 0;
-
-	if (list_empty(&ctx->pending_cb_list))
-		goto free_pending_cb_token;
-
-	/* move all list elements to a local list */
-	INIT_LIST_HEAD(&local_cb_list);
-	spin_lock(&ctx->pending_cb_lock);
-	list_for_each_entry_safe(pending_cb, tmp, &ctx->pending_cb_list,
-								cb_node)
-		list_move_tail(&pending_cb->cb_node, &local_cb_list);
-	spin_unlock(&ctx->pending_cb_lock);
-
-	rc = allocate_cs(hdev, ctx, CS_TYPE_DEFAULT, ULLONG_MAX, &cs, 0,
-				hdev->timeout_jiffies);
-	if (rc)
-		goto add_list_elements;
-
-	hl_debugfs_add_cs(cs);
-
-	/* Iterate through pending cb list, create jobs and add to CS */
-	list_for_each_entry(pending_cb, &local_cb_list, cb_node) {
-		cb = pending_cb->cb;
-		cb_size = pending_cb->cb_size;
-		hw_queue_id = pending_cb->hw_queue_id;
-
-		rc = pending_cb_create_job(hdev, ctx, cs, cb, cb_size,
-								hw_queue_id);
-		if (rc)
-			goto free_cs_object;
-	}
-
-	rc = hl_hw_queue_schedule_cs(cs);
-	if (rc) {
-		if (rc != -EAGAIN)
-			dev_err(hdev->dev,
-				"Failed to submit CS %d.%llu (%d)\n",
-				ctx->asid, cs->sequence, rc);
-		goto free_cs_object;
-	}
-
-	/* pending cb was scheduled successfully */
-	list_for_each_entry_safe(pending_cb, tmp, &local_cb_list, cb_node) {
-		list_del(&pending_cb->cb_node);
-		kfree(pending_cb);
-	}
-
-	cs_put(cs);
-
-	goto free_pending_cb_token;
-
-free_cs_object:
-	cs_rollback(hdev, cs);
-	cs_put(cs);
-add_list_elements:
-	spin_lock(&ctx->pending_cb_lock);
-	list_for_each_entry_safe_reverse(pending_cb, tmp, &local_cb_list,
-								cb_node)
-		list_move(&pending_cb->cb_node, &ctx->pending_cb_list);
-	spin_unlock(&ctx->pending_cb_lock);
-free_pending_cb_token:
-	atomic_set(&ctx->thread_pending_cb_token, 1);
-
-	return rc;
-}
-
 static int hl_cs_ctx_switch(struct hl_fpriv *hpriv, union hl_cs_args *args,
 				u64 *cs_seq)
 {
@@ -1443,7 +1473,7 @@
 			rc = 0;
 		} else {
 			rc = cs_ioctl_default(hpriv, chunks, num_chunks,
-					cs_seq, 0, hdev->timeout_jiffies);
+					cs_seq, 0, 0, hdev->timeout_jiffies);
 		}
 
 		mutex_unlock(&hpriv->restore_phase_mutex);
@@ -1501,10 +1531,17 @@
  * hl_cs_signal_sob_wraparound_handler: handle SOB value wrapaound case.
  * if the SOB value reaches the max value move to the other SOB reserved
  * to the queue.
+ * @hdev: pointer to device structure
+ * @q_idx: stream queue index
+ * @hw_sob: the H/W SOB used in this signal CS.
+ * @count: signals count
+ * @encaps_sig: tells whether it's reservation for encaps signals or not.
+ *
  * Note that this function must be called while hw_queues_lock is taken.
  */
 int hl_cs_signal_sob_wraparound_handler(struct hl_device *hdev, u32 q_idx,
-			struct hl_hw_sob **hw_sob, u32 count)
+			struct hl_hw_sob **hw_sob, u32 count, bool encaps_sig)
+
 {
 	struct hl_sync_stream_properties *prop;
 	struct hl_hw_sob *sob = *hw_sob, *other_sob;
@@ -1512,7 +1549,7 @@
 
 	prop = &hdev->kernel_queues[q_idx].sync_stream_prop;
 
-	kref_get(&sob->kref);
+	hw_sob_get(sob);
 
 	/* check for wraparound */
 	if (prop->next_sob_val + count >= HL_MAX_SOB_VAL) {
@@ -1522,7 +1559,7 @@
 		 * just incremented the refcount right before calling this
 		 * function.
 		 */
-		kref_put(&sob->kref, hl_sob_reset_error);
+		hw_sob_put_err(sob);
 
 		/*
 		 * check the other sob value, if it still in use then fail
@@ -1537,12 +1574,42 @@
 			return -EINVAL;
 		}
 
-		prop->next_sob_val = 1;
+		/*
+		 * next_sob_val always points to the next available signal
+		 * in the sob, so in encaps signals it will be the next one
+		 * after reserving the required amount.
+		 */
+		if (encaps_sig)
+			prop->next_sob_val = count + 1;
+		else
+			prop->next_sob_val = count;
 
 		/* only two SOBs are currently in use */
 		prop->curr_sob_offset = other_sob_offset;
 		*hw_sob = other_sob;
 
+		/*
+		 * check if other_sob needs reset, then do it before using it
+		 * for the reservation or the next signal cs.
+		 * we do it here, and for both encaps and regular signal cs
+		 * cases in order to avoid possible races of two kref_put
+		 * of the sob which can occur at the same time if we move the
+		 * sob reset(kref_put) to cs_do_release function.
+		 * in addition, if we have combination of cs signal and
+		 * encaps, and at the point we need to reset the sob there was
+		 * no more reservations and only signal cs keep coming,
+		 * in such case we need signal_cs to put the refcount and
+		 * reset the sob.
+		 */
+		if (other_sob->need_reset)
+			hw_sob_put(other_sob);
+
+		if (encaps_sig) {
+			/* set reset indication for the sob */
+			sob->need_reset = true;
+			hw_sob_get(other_sob);
+		}
+
 		dev_dbg(hdev->dev, "switched to SOB %d, q_idx: %d\n",
 				prop->curr_sob_offset, q_idx);
 	} else {
@@ -1553,12 +1620,18 @@
 }
 
 static int cs_ioctl_extract_signal_seq(struct hl_device *hdev,
-		struct hl_cs_chunk *chunk, u64 *signal_seq, struct hl_ctx *ctx)
+		struct hl_cs_chunk *chunk, u64 *signal_seq, struct hl_ctx *ctx,
+		bool encaps_signals)
 {
 	u64 *signal_seq_arr = NULL;
 	u32 size_to_copy, signal_seq_arr_len;
 	int rc = 0;
 
+	if (encaps_signals) {
+		*signal_seq = chunk->encaps_signal_seq;
+		return 0;
+	}
+
 	signal_seq_arr_len = chunk->num_signal_seq_arr;
 
 	/* currently only one signal seq is supported */
@@ -1583,7 +1656,7 @@
 		return -ENOMEM;
 	}
 
-	size_to_copy = chunk->num_signal_seq_arr * sizeof(*signal_seq_arr);
+	size_to_copy = signal_seq_arr_len * sizeof(*signal_seq_arr);
 	if (copy_from_user(signal_seq_arr,
 				u64_to_user_ptr(chunk->signal_seq_arr),
 				size_to_copy)) {
@@ -1605,8 +1678,8 @@
 }
 
 static int cs_ioctl_signal_wait_create_jobs(struct hl_device *hdev,
-		struct hl_ctx *ctx, struct hl_cs *cs, enum hl_queue_type q_type,
-		u32 q_idx)
+		struct hl_ctx *ctx, struct hl_cs *cs,
+		enum hl_queue_type q_type, u32 q_idx, u32 encaps_signal_offset)
 {
 	struct hl_cs_counters_atomic *cntr;
 	struct hl_cs_job *job;
@@ -1644,6 +1717,9 @@
 	job->user_cb_size = cb_size;
 	job->hw_queue_id = q_idx;
 
+	if ((cs->type == CS_TYPE_WAIT || cs->type == CS_TYPE_COLLECTIVE_WAIT)
+			&& cs->encaps_signals)
+		job->encaps_sig_wait_offset = encaps_signal_offset;
 	/*
 	 * No need in parsing, user CB is the patched CB.
 	 * We call hl_cb_destroy() out of two reasons - we don't need the CB in
@@ -1666,11 +1742,196 @@
 	return 0;
 }
 
+static int cs_ioctl_reserve_signals(struct hl_fpriv *hpriv,
+				u32 q_idx, u32 count,
+				u32 *handle_id, u32 *sob_addr,
+				u32 *signals_count)
+{
+	struct hw_queue_properties *hw_queue_prop;
+	struct hl_sync_stream_properties *prop;
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_cs_encaps_sig_handle *handle;
+	struct hl_encaps_signals_mgr *mgr;
+	struct hl_hw_sob *hw_sob;
+	int hdl_id;
+	int rc = 0;
+
+	if (count >= HL_MAX_SOB_VAL) {
+		dev_err(hdev->dev, "signals count(%u) exceeds the max SOB value\n",
+						count);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (q_idx >= hdev->asic_prop.max_queues) {
+		dev_err(hdev->dev, "Queue index %d is invalid\n",
+			q_idx);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hw_queue_prop = &hdev->asic_prop.hw_queues_props[q_idx];
+
+	if (!hw_queue_prop->supports_sync_stream) {
+		dev_err(hdev->dev,
+			"Queue index %d does not support sync stream operations\n",
+									q_idx);
+		rc = -EINVAL;
+		goto out;
+	}
+
+	prop = &hdev->kernel_queues[q_idx].sync_stream_prop;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	handle->count = count;
+	mgr = &hpriv->ctx->sig_mgr;
+
+	spin_lock(&mgr->lock);
+	hdl_id = idr_alloc(&mgr->handles, handle, 1, 0, GFP_ATOMIC);
+	spin_unlock(&mgr->lock);
+
+	if (hdl_id < 0) {
+		dev_err(hdev->dev, "Failed to allocate IDR for a new signal reservation\n");
+		rc = -EINVAL;
+		goto out;
+	}
+
+	handle->id = hdl_id;
+	handle->q_idx = q_idx;
+	handle->hdev = hdev;
+	kref_init(&handle->refcount);
+
+	hdev->asic_funcs->hw_queues_lock(hdev);
+
+	hw_sob = &prop->hw_sob[prop->curr_sob_offset];
+
+	/*
+	 * Increment the SOB value by count by user request
+	 * to reserve those signals
+	 * check if the signals amount to reserve is not exceeding the max sob
+	 * value, if yes then switch sob.
+	 */
+	rc = hl_cs_signal_sob_wraparound_handler(hdev, q_idx, &hw_sob, count,
+								true);
+	if (rc) {
+		dev_err(hdev->dev, "Failed to switch SOB\n");
+		hdev->asic_funcs->hw_queues_unlock(hdev);
+		rc = -EINVAL;
+		goto remove_idr;
+	}
+	/* set the hw_sob to the handle after calling the sob wraparound handler
+	 * since sob could have changed.
+	 */
+	handle->hw_sob = hw_sob;
+
+	/* store the current sob value for unreserve validity check, and
+	 * signal offset support
+	 */
+	handle->pre_sob_val = prop->next_sob_val - handle->count;
+
+	*signals_count = prop->next_sob_val;
+	hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	*sob_addr = handle->hw_sob->sob_addr;
+	*handle_id = hdl_id;
+
+	dev_dbg(hdev->dev,
+		"Signals reserved, sob_id: %d, sob addr: 0x%x, last sob_val: %u, q_idx: %d, hdl_id: %d\n",
+			hw_sob->sob_id, handle->hw_sob->sob_addr,
+			prop->next_sob_val - 1, q_idx, hdl_id);
+	goto out;
+
+remove_idr:
+	spin_lock(&mgr->lock);
+	idr_remove(&mgr->handles, hdl_id);
+	spin_unlock(&mgr->lock);
+
+	kfree(handle);
+out:
+	return rc;
+}
+
+static int cs_ioctl_unreserve_signals(struct hl_fpriv *hpriv, u32 handle_id)
+{
+	struct hl_cs_encaps_sig_handle *encaps_sig_hdl;
+	struct hl_sync_stream_properties *prop;
+	struct hl_device *hdev = hpriv->hdev;
+	struct hl_encaps_signals_mgr *mgr;
+	struct hl_hw_sob *hw_sob;
+	u32 q_idx, sob_addr;
+	int rc = 0;
+
+	mgr = &hpriv->ctx->sig_mgr;
+
+	spin_lock(&mgr->lock);
+	encaps_sig_hdl = idr_find(&mgr->handles, handle_id);
+	if (encaps_sig_hdl) {
+		dev_dbg(hdev->dev, "unreserve signals, handle: %u, SOB:0x%x, count: %u\n",
+				handle_id, encaps_sig_hdl->hw_sob->sob_addr,
+					encaps_sig_hdl->count);
+
+		hdev->asic_funcs->hw_queues_lock(hdev);
+
+		q_idx = encaps_sig_hdl->q_idx;
+		prop = &hdev->kernel_queues[q_idx].sync_stream_prop;
+		hw_sob = &prop->hw_sob[prop->curr_sob_offset];
+		sob_addr = hdev->asic_funcs->get_sob_addr(hdev, hw_sob->sob_id);
+
+		/* Check if sob_val got out of sync due to other
+		 * signal submission requests which were handled
+		 * between the reserve-unreserve calls or SOB switch
+		 * upon reaching SOB max value.
+		 */
+		if (encaps_sig_hdl->pre_sob_val + encaps_sig_hdl->count
+				!= prop->next_sob_val ||
+				sob_addr != encaps_sig_hdl->hw_sob->sob_addr) {
+			dev_err(hdev->dev, "Cannot unreserve signals, SOB val ran out of sync, expected: %u, actual val: %u\n",
+				encaps_sig_hdl->pre_sob_val,
+				(prop->next_sob_val - encaps_sig_hdl->count));
+
+			hdev->asic_funcs->hw_queues_unlock(hdev);
+			rc = -EINVAL;
+			goto out;
+		}
+
+		/*
+		 * Decrement the SOB value by count by user request
+		 * to unreserve those signals
+		 */
+		prop->next_sob_val -= encaps_sig_hdl->count;
+
+		hdev->asic_funcs->hw_queues_unlock(hdev);
+
+		hw_sob_put(hw_sob);
+
+		/* Release the id and free allocated memory of the handle */
+		idr_remove(&mgr->handles, handle_id);
+		kfree(encaps_sig_hdl);
+	} else {
+		rc = -EINVAL;
+		dev_err(hdev->dev, "failed to unreserve signals, cannot find handler\n");
+	}
+out:
+	spin_unlock(&mgr->lock);
+
+	return rc;
+}
+
 static int cs_ioctl_signal_wait(struct hl_fpriv *hpriv, enum hl_cs_type cs_type,
 				void __user *chunks, u32 num_chunks,
 				u64 *cs_seq, u32 flags, u32 timeout)
 {
+	struct hl_cs_encaps_sig_handle *encaps_sig_hdl = NULL;
+	bool handle_found = false, is_wait_cs = false,
+			wait_cs_submitted = false,
+			cs_encaps_signals = false;
 	struct hl_cs_chunk *cs_chunk_array, *chunk;
+	bool staged_cs_with_encaps_signals = false;
 	struct hw_queue_properties *hw_queue_prop;
 	struct hl_device *hdev = hpriv->hdev;
 	struct hl_cs_compl *sig_waitcs_cmpl;
@@ -1730,11 +1991,58 @@
 		collective_engine_id = chunk->collective_engine_id;
 	}
 
-	if (cs_type == CS_TYPE_WAIT || cs_type == CS_TYPE_COLLECTIVE_WAIT) {
-		rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq, ctx);
+	is_wait_cs = !!(cs_type == CS_TYPE_WAIT ||
+			cs_type == CS_TYPE_COLLECTIVE_WAIT);
+
+	cs_encaps_signals = !!(flags & HL_CS_FLAGS_ENCAP_SIGNALS);
+
+	if (is_wait_cs) {
+		rc = cs_ioctl_extract_signal_seq(hdev, chunk, &signal_seq,
+				ctx, cs_encaps_signals);
 		if (rc)
 			goto free_cs_chunk_array;
 
+		if (cs_encaps_signals) {
+			/* check if cs sequence has encapsulated
+			 * signals handle
+			 */
+			struct idr *idp;
+			u32 id;
+
+			spin_lock(&ctx->sig_mgr.lock);
+			idp = &ctx->sig_mgr.handles;
+			idr_for_each_entry(idp, encaps_sig_hdl, id) {
+				if (encaps_sig_hdl->cs_seq == signal_seq) {
+					handle_found = true;
+					/* get refcount to protect removing
+					 * this handle from idr, needed when
+					 * multiple wait cs are used with offset
+					 * to wait on reserved encaps signals.
+					 */
+					kref_get(&encaps_sig_hdl->refcount);
+					break;
+				}
+			}
+			spin_unlock(&ctx->sig_mgr.lock);
+
+			if (!handle_found) {
+				dev_err(hdev->dev, "Cannot find encapsulated signals handle for seq 0x%llx\n",
+						signal_seq);
+				rc = -EINVAL;
+				goto free_cs_chunk_array;
+			}
+
+			/* validate also the signal offset value */
+			if (chunk->encaps_signal_offset >
+					encaps_sig_hdl->count) {
+				dev_err(hdev->dev, "offset(%u) value exceed max reserved signals count(%u)!\n",
+						chunk->encaps_signal_offset,
+						encaps_sig_hdl->count);
+				rc = -EINVAL;
+				goto free_cs_chunk_array;
+			}
+		}
+
 		sig_fence = hl_ctx_get_fence(ctx, signal_seq);
 		if (IS_ERR(sig_fence)) {
 			atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
@@ -1755,11 +2063,16 @@
 		sig_waitcs_cmpl =
 			container_of(sig_fence, struct hl_cs_compl, base_fence);
 
-		if (sig_waitcs_cmpl->type != CS_TYPE_SIGNAL) {
+		staged_cs_with_encaps_signals = !!
+				(sig_waitcs_cmpl->type == CS_TYPE_DEFAULT &&
+				(flags & HL_CS_FLAGS_ENCAP_SIGNALS));
+
+		if (sig_waitcs_cmpl->type != CS_TYPE_SIGNAL &&
+				!staged_cs_with_encaps_signals) {
 			atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
 			atomic64_inc(&cntr->validation_drop_cnt);
 			dev_err(hdev->dev,
-				"CS seq 0x%llx is not of a signal CS\n",
+				"CS seq 0x%llx is not of a signal/encaps-signal CS\n",
 				signal_seq);
 			hl_fence_put(sig_fence);
 			rc = -EINVAL;
@@ -1776,18 +2089,27 @@
 
 	rc = allocate_cs(hdev, ctx, cs_type, ULLONG_MAX, &cs, flags, timeout);
 	if (rc) {
-		if (cs_type == CS_TYPE_WAIT ||
-			cs_type == CS_TYPE_COLLECTIVE_WAIT)
+		if (is_wait_cs)
 			hl_fence_put(sig_fence);
+
 		goto free_cs_chunk_array;
 	}
 
 	/*
 	 * Save the signal CS fence for later initialization right before
 	 * hanging the wait CS on the queue.
+	 * for encaps signals case, we save the cs sequence and handle pointer
+	 * for later initialization.
 	 */
-	if (cs_type == CS_TYPE_WAIT || cs_type == CS_TYPE_COLLECTIVE_WAIT)
+	if (is_wait_cs) {
 		cs->signal_fence = sig_fence;
+		/* store the handle pointer, so we don't have to
+		 * look for it again, later on the flow
+		 * when we need to set SOB info in hw_queue.
+		 */
+		if (cs->encaps_signals)
+			cs->encaps_sig_hdl = encaps_sig_hdl;
+	}
 
 	hl_debugfs_add_cs(cs);
 
@@ -1795,10 +2117,11 @@
 
 	if (cs_type == CS_TYPE_WAIT || cs_type == CS_TYPE_SIGNAL)
 		rc = cs_ioctl_signal_wait_create_jobs(hdev, ctx, cs, q_type,
-				q_idx);
+				q_idx, chunk->encaps_signal_offset);
 	else if (cs_type == CS_TYPE_COLLECTIVE_WAIT)
 		rc = hdev->asic_funcs->collective_wait_create_jobs(hdev, ctx,
-				cs, q_idx, collective_engine_id);
+				cs, q_idx, collective_engine_id,
+				chunk->encaps_signal_offset);
 	else {
 		atomic64_inc(&ctx->cs_counters.validation_drop_cnt);
 		atomic64_inc(&cntr->validation_drop_cnt);
@@ -1810,7 +2133,13 @@
 
 	rc = hl_hw_queue_schedule_cs(cs);
 	if (rc) {
-		if (rc != -EAGAIN)
+		/* In case wait cs failed here, it means the signal cs
+		 * already completed. we want to free all it's related objects
+		 * but we don't want to fail the ioctl.
+		 */
+		if (is_wait_cs)
+			rc = 0;
+		else if (rc != -EAGAIN)
 			dev_err(hdev->dev,
 				"Failed to submit CS %d.%llu to H/W queues, error %d\n",
 				ctx->asid, cs->sequence, rc);
@@ -1818,6 +2147,8 @@
 	}
 
 	rc = HL_CS_STATUS_SUCCESS;
+	if (is_wait_cs)
+		wait_cs_submitted = true;
 	goto put_cs;
 
 free_cs_object:
@@ -1828,6 +2159,10 @@
 	/* We finished with the CS in this function, so put the ref */
 	cs_put(cs);
 free_cs_chunk_array:
+	if (!wait_cs_submitted && cs_encaps_signals && handle_found &&
+							is_wait_cs)
+		kref_put(&encaps_sig_hdl->refcount,
+				hl_encaps_handle_do_release);
 	kfree(cs_chunk_array);
 out:
 	return rc;
@@ -1836,10 +2171,11 @@
 int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data)
 {
 	union hl_cs_args *args = data;
-	enum hl_cs_type cs_type;
+	enum hl_cs_type cs_type = 0;
 	u64 cs_seq = ULONG_MAX;
 	void __user *chunks;
-	u32 num_chunks, flags, timeout;
+	u32 num_chunks, flags, timeout,
+		signals_count = 0, sob_addr = 0, handle_id = 0;
 	int rc;
 
 	rc = hl_cs_sanity_checks(hpriv, args);
@@ -1850,10 +2186,6 @@
 	if (rc)
 		goto out;
 
-	rc = hl_submit_pending_cb(hpriv);
-	if (rc)
-		goto out;
-
 	cs_type = hl_cs_get_cs_type(args->in.cs_flags &
 					~HL_CS_FLAGS_FORCE_RESTORE);
 	chunks = (void __user *) (uintptr_t) args->in.chunks_execute;
@@ -1876,82 +2208,450 @@
 		rc = cs_ioctl_signal_wait(hpriv, cs_type, chunks, num_chunks,
 					&cs_seq, args->in.cs_flags, timeout);
 		break;
+	case CS_RESERVE_SIGNALS:
+		rc = cs_ioctl_reserve_signals(hpriv,
+					args->in.encaps_signals_q_idx,
+					args->in.encaps_signals_count,
+					&handle_id, &sob_addr, &signals_count);
+		break;
+	case CS_UNRESERVE_SIGNALS:
+		rc = cs_ioctl_unreserve_signals(hpriv,
+					args->in.encaps_sig_handle_id);
+		break;
 	default:
 		rc = cs_ioctl_default(hpriv, chunks, num_chunks, &cs_seq,
-						args->in.cs_flags, timeout);
+						args->in.cs_flags,
+						args->in.encaps_sig_handle_id,
+						timeout);
 		break;
 	}
-
 out:
 	if (rc != -EAGAIN) {
 		memset(args, 0, sizeof(*args));
+
+		if (cs_type == CS_RESERVE_SIGNALS) {
+			args->out.handle_id = handle_id;
+			args->out.sob_base_addr_offset = sob_addr;
+			args->out.count = signals_count;
+		} else {
+			args->out.seq = cs_seq;
+		}
 		args->out.status = rc;
-		args->out.seq = cs_seq;
 	}
 
 	return rc;
 }
 
+static int hl_wait_for_fence(struct hl_ctx *ctx, u64 seq, struct hl_fence *fence,
+				enum hl_cs_wait_status *status, u64 timeout_us,
+				s64 *timestamp)
+{
+	struct hl_device *hdev = ctx->hdev;
+	long completion_rc;
+	int rc = 0;
+
+	if (IS_ERR(fence)) {
+		rc = PTR_ERR(fence);
+		if (rc == -EINVAL)
+			dev_notice_ratelimited(hdev->dev,
+				"Can't wait on CS %llu because current CS is at seq %llu\n",
+				seq, ctx->cs_sequence);
+		return rc;
+	}
+
+	if (!fence) {
+		dev_dbg(hdev->dev,
+			"Can't wait on seq %llu because current CS is at seq %llu (Fence is gone)\n",
+				seq, ctx->cs_sequence);
+
+		*status = CS_WAIT_STATUS_GONE;
+		return 0;
+	}
+
+	if (!timeout_us) {
+		completion_rc = completion_done(&fence->completion);
+	} else {
+		unsigned long timeout;
+
+		timeout = (timeout_us == MAX_SCHEDULE_TIMEOUT) ?
+				timeout_us : usecs_to_jiffies(timeout_us);
+		completion_rc =
+			wait_for_completion_interruptible_timeout(
+				&fence->completion, timeout);
+	}
+
+	if (completion_rc > 0) {
+		*status = CS_WAIT_STATUS_COMPLETED;
+		if (timestamp)
+			*timestamp = ktime_to_ns(fence->timestamp);
+	} else {
+		*status = CS_WAIT_STATUS_BUSY;
+	}
+
+	if (fence->error == -ETIMEDOUT)
+		rc = -ETIMEDOUT;
+	else if (fence->error == -EIO)
+		rc = -EIO;
+
+	return rc;
+}
+
+/*
+ * hl_cs_poll_fences - iterate CS fences to check for CS completion
+ *
+ * @mcs_data: multi-CS internal data
+ *
+ * @return 0 on success, otherwise non 0 error code
+ *
+ * The function iterates on all CS sequence in the list and set bit in
+ * completion_bitmap for each completed CS.
+ * while iterating, the function can extracts the stream map to be later
+ * used by the waiting function.
+ * this function shall be called after taking context ref
+ */
+static int hl_cs_poll_fences(struct multi_cs_data *mcs_data)
+{
+	struct hl_fence **fence_ptr = mcs_data->fence_arr;
+	struct hl_device *hdev = mcs_data->ctx->hdev;
+	int i, rc, arr_len = mcs_data->arr_len;
+	u64 *seq_arr = mcs_data->seq_arr;
+	ktime_t max_ktime, first_cs_time;
+	enum hl_cs_wait_status status;
+
+	memset(fence_ptr, 0, arr_len * sizeof(*fence_ptr));
+
+	/* get all fences under the same lock */
+	rc = hl_ctx_get_fences(mcs_data->ctx, seq_arr, fence_ptr, arr_len);
+	if (rc)
+		return rc;
+
+	/*
+	 * set to maximum time to verify timestamp is valid: if at the end
+	 * this value is maintained- no timestamp was updated
+	 */
+	max_ktime = ktime_set(KTIME_SEC_MAX, 0);
+	first_cs_time = max_ktime;
+
+	for (i = 0; i < arr_len; i++, fence_ptr++) {
+		struct hl_fence *fence = *fence_ptr;
+
+		/*
+		 * function won't sleep as it is called with timeout 0 (i.e.
+		 * poll the fence)
+		 */
+		rc = hl_wait_for_fence(mcs_data->ctx, seq_arr[i], fence,
+						&status, 0, NULL);
+		if (rc) {
+			dev_err(hdev->dev,
+				"wait_for_fence error :%d for CS seq %llu\n",
+								rc, seq_arr[i]);
+			break;
+		}
+
+		mcs_data->stream_master_qid_map |= fence->stream_master_qid_map;
+
+		if (status == CS_WAIT_STATUS_BUSY)
+			continue;
+
+		mcs_data->completion_bitmap |= BIT(i);
+
+		/*
+		 * best effort to extract timestamp. few notes:
+		 * - if even single fence is gone we cannot extract timestamp
+		 *   (as fence not exist anymore)
+		 * - for all completed CSs we take the earliest timestamp.
+		 *   for this we have to validate that:
+		 *       1. given timestamp was indeed set
+		 *       2. the timestamp is earliest of all timestamps so far
+		 */
+
+		if (status == CS_WAIT_STATUS_GONE) {
+			mcs_data->update_ts = false;
+			mcs_data->gone_cs = true;
+		} else if (mcs_data->update_ts &&
+			(ktime_compare(fence->timestamp,
+						ktime_set(0, 0)) > 0) &&
+			(ktime_compare(fence->timestamp, first_cs_time) < 0)) {
+			first_cs_time = fence->timestamp;
+		}
+	}
+
+	hl_fences_put(mcs_data->fence_arr, arr_len);
+
+	if (mcs_data->update_ts &&
+			(ktime_compare(first_cs_time, max_ktime) != 0))
+		mcs_data->timestamp = ktime_to_ns(first_cs_time);
+
+	return rc;
+}
+
 static int _hl_cs_wait_ioctl(struct hl_device *hdev, struct hl_ctx *ctx,
 				u64 timeout_us, u64 seq,
 				enum hl_cs_wait_status *status, s64 *timestamp)
 {
 	struct hl_fence *fence;
-	unsigned long timeout;
 	int rc = 0;
-	long completion_rc;
 
 	if (timestamp)
 		*timestamp = 0;
 
-	if (timeout_us == MAX_SCHEDULE_TIMEOUT)
-		timeout = timeout_us;
-	else
-		timeout = usecs_to_jiffies(timeout_us);
-
 	hl_ctx_get(hdev, ctx);
 
 	fence = hl_ctx_get_fence(ctx, seq);
-	if (IS_ERR(fence)) {
-		rc = PTR_ERR(fence);
-		if (rc == -EINVAL)
-			dev_notice_ratelimited(hdev->dev,
-				"Can't wait on CS %llu because current CS is at seq %llu\n",
-				seq, ctx->cs_sequence);
-	} else if (fence) {
-		if (!timeout_us)
-			completion_rc = completion_done(&fence->completion);
-		else
-			completion_rc =
-				wait_for_completion_interruptible_timeout(
-					&fence->completion, timeout);
 
-		if (completion_rc > 0) {
-			*status = CS_WAIT_STATUS_COMPLETED;
-			if (timestamp)
-				*timestamp = ktime_to_ns(fence->timestamp);
-		} else {
-			*status = CS_WAIT_STATUS_BUSY;
-		}
-
-		if (fence->error == -ETIMEDOUT)
-			rc = -ETIMEDOUT;
-		else if (fence->error == -EIO)
-			rc = -EIO;
-
-		hl_fence_put(fence);
-	} else {
-		dev_dbg(hdev->dev,
-			"Can't wait on seq %llu because current CS is at seq %llu (Fence is gone)\n",
-			seq, ctx->cs_sequence);
-		*status = CS_WAIT_STATUS_GONE;
-	}
-
+	rc = hl_wait_for_fence(ctx, seq, fence, status, timeout_us, timestamp);
+	hl_fence_put(fence);
 	hl_ctx_put(ctx);
 
 	return rc;
 }
 
+/*
+ * hl_wait_multi_cs_completion_init - init completion structure
+ *
+ * @hdev: pointer to habanalabs device structure
+ * @stream_master_bitmap: stream master QIDs map, set bit indicates stream
+ *                        master QID to wait on
+ *
+ * @return valid completion struct pointer on success, otherwise error pointer
+ *
+ * up to MULTI_CS_MAX_USER_CTX calls can be done concurrently to the driver.
+ * the function gets the first available completion (by marking it "used")
+ * and initialize its values.
+ */
+static struct multi_cs_completion *hl_wait_multi_cs_completion_init(
+							struct hl_device *hdev,
+							u8 stream_master_bitmap)
+{
+	struct multi_cs_completion *mcs_compl;
+	int i;
+
+	/* find free multi_cs completion structure */
+	for (i = 0; i < MULTI_CS_MAX_USER_CTX; i++) {
+		mcs_compl = &hdev->multi_cs_completion[i];
+		spin_lock(&mcs_compl->lock);
+		if (!mcs_compl->used) {
+			mcs_compl->used = 1;
+			mcs_compl->timestamp = 0;
+			mcs_compl->stream_master_qid_map = stream_master_bitmap;
+			reinit_completion(&mcs_compl->completion);
+			spin_unlock(&mcs_compl->lock);
+			break;
+		}
+		spin_unlock(&mcs_compl->lock);
+	}
+
+	if (i == MULTI_CS_MAX_USER_CTX) {
+		dev_err(hdev->dev,
+				"no available multi-CS completion structure\n");
+		return ERR_PTR(-ENOMEM);
+	}
+	return mcs_compl;
+}
+
+/*
+ * hl_wait_multi_cs_completion_fini - return completion structure and set as
+ *                                    unused
+ *
+ * @mcs_compl: pointer to the completion structure
+ */
+static void hl_wait_multi_cs_completion_fini(
+					struct multi_cs_completion *mcs_compl)
+{
+	/*
+	 * free completion structure, do it under lock to be in-sync with the
+	 * thread that signals completion
+	 */
+	spin_lock(&mcs_compl->lock);
+	mcs_compl->used = 0;
+	spin_unlock(&mcs_compl->lock);
+}
+
+/*
+ * hl_wait_multi_cs_completion - wait for first CS to complete
+ *
+ * @mcs_data: multi-CS internal data
+ *
+ * @return 0 on success, otherwise non 0 error code
+ */
+static int hl_wait_multi_cs_completion(struct multi_cs_data *mcs_data)
+{
+	struct hl_device *hdev = mcs_data->ctx->hdev;
+	struct multi_cs_completion *mcs_compl;
+	long completion_rc;
+
+	mcs_compl = hl_wait_multi_cs_completion_init(hdev,
+					mcs_data->stream_master_qid_map);
+	if (IS_ERR(mcs_compl))
+		return PTR_ERR(mcs_compl);
+
+	completion_rc = wait_for_completion_interruptible_timeout(
+					&mcs_compl->completion,
+					usecs_to_jiffies(mcs_data->timeout_us));
+
+	/* update timestamp */
+	if (completion_rc > 0)
+		mcs_data->timestamp = mcs_compl->timestamp;
+
+	hl_wait_multi_cs_completion_fini(mcs_compl);
+
+	mcs_data->wait_status = completion_rc;
+
+	return 0;
+}
+
+/*
+ * hl_multi_cs_completion_init - init array of multi-CS completion structures
+ *
+ * @hdev: pointer to habanalabs device structure
+ */
+void hl_multi_cs_completion_init(struct hl_device *hdev)
+{
+	struct multi_cs_completion *mcs_cmpl;
+	int i;
+
+	for (i = 0; i < MULTI_CS_MAX_USER_CTX; i++) {
+		mcs_cmpl = &hdev->multi_cs_completion[i];
+		mcs_cmpl->used = 0;
+		spin_lock_init(&mcs_cmpl->lock);
+		init_completion(&mcs_cmpl->completion);
+	}
+}
+
+/*
+ * hl_multi_cs_wait_ioctl - implementation of the multi-CS wait ioctl
+ *
+ * @hpriv: pointer to the private data of the fd
+ * @data: pointer to multi-CS wait ioctl in/out args
+ *
+ */
+static int hl_multi_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	struct multi_cs_data mcs_data = {0};
+	union hl_wait_cs_args *args = data;
+	struct hl_ctx *ctx = hpriv->ctx;
+	struct hl_fence **fence_arr;
+	void __user *seq_arr;
+	u32 size_to_copy;
+	u64 *cs_seq_arr;
+	u8 seq_arr_len;
+	int rc;
+
+	if (!hdev->supports_wait_for_multi_cs) {
+		dev_err(hdev->dev, "Wait for multi CS is not supported\n");
+		return -EPERM;
+	}
+
+	seq_arr_len = args->in.seq_arr_len;
+
+	if (seq_arr_len > HL_WAIT_MULTI_CS_LIST_MAX_LEN) {
+		dev_err(hdev->dev, "Can wait only up to %d CSs, input sequence is of length %u\n",
+				HL_WAIT_MULTI_CS_LIST_MAX_LEN, seq_arr_len);
+		return -EINVAL;
+	}
+
+	/* allocate memory for sequence array */
+	cs_seq_arr =
+		kmalloc_array(seq_arr_len, sizeof(*cs_seq_arr), GFP_KERNEL);
+	if (!cs_seq_arr)
+		return -ENOMEM;
+
+	/* copy CS sequence array from user */
+	seq_arr = (void __user *) (uintptr_t) args->in.seq;
+	size_to_copy = seq_arr_len * sizeof(*cs_seq_arr);
+	if (copy_from_user(cs_seq_arr, seq_arr, size_to_copy)) {
+		dev_err(hdev->dev, "Failed to copy multi-cs sequence array from user\n");
+		rc = -EFAULT;
+		goto free_seq_arr;
+	}
+
+	/* allocate array for the fences */
+	fence_arr = kmalloc_array(seq_arr_len, sizeof(*fence_arr), GFP_KERNEL);
+	if (!fence_arr) {
+		rc = -ENOMEM;
+		goto free_seq_arr;
+	}
+
+	/* initialize the multi-CS internal data */
+	mcs_data.ctx = ctx;
+	mcs_data.seq_arr = cs_seq_arr;
+	mcs_data.fence_arr = fence_arr;
+	mcs_data.arr_len = seq_arr_len;
+
+	hl_ctx_get(hdev, ctx);
+
+	/* poll all CS fences, extract timestamp */
+	mcs_data.update_ts = true;
+	rc = hl_cs_poll_fences(&mcs_data);
+	/*
+	 * skip wait for CS completion when one of the below is true:
+	 * - an error on the poll function
+	 * - one or more CS in the list completed
+	 * - the user called ioctl with timeout 0
+	 */
+	if (rc || mcs_data.completion_bitmap || !args->in.timeout_us)
+		goto put_ctx;
+
+	/* wait (with timeout) for the first CS to be completed */
+	mcs_data.timeout_us = args->in.timeout_us;
+	rc = hl_wait_multi_cs_completion(&mcs_data);
+	if (rc)
+		goto put_ctx;
+
+	if (mcs_data.wait_status > 0) {
+		/*
+		 * poll fences once again to update the CS map.
+		 * no timestamp should be updated this time.
+		 */
+		mcs_data.update_ts = false;
+		rc = hl_cs_poll_fences(&mcs_data);
+
+		/*
+		 * if hl_wait_multi_cs_completion returned before timeout (i.e.
+		 * it got a completion) we expect to see at least one CS
+		 * completed after the poll function.
+		 */
+		if (!mcs_data.completion_bitmap) {
+			dev_err(hdev->dev, "Multi-CS got completion on wait but no CS completed\n");
+			rc = -EFAULT;
+		}
+	}
+
+put_ctx:
+	hl_ctx_put(ctx);
+	kfree(fence_arr);
+
+free_seq_arr:
+	kfree(cs_seq_arr);
+
+	/* update output args */
+	memset(args, 0, sizeof(*args));
+	if (rc)
+		return rc;
+
+	if (mcs_data.completion_bitmap) {
+		args->out.status = HL_WAIT_CS_STATUS_COMPLETED;
+		args->out.cs_completion_map = mcs_data.completion_bitmap;
+
+		/* if timestamp not 0- it's valid */
+		if (mcs_data.timestamp) {
+			args->out.timestamp_nsec = mcs_data.timestamp;
+			args->out.flags |= HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD;
+		}
+
+		/* update if some CS was gone */
+		if (mcs_data.timestamp)
+			args->out.flags |= HL_WAIT_CS_STATUS_FLAG_GONE;
+	} else if (mcs_data.wait_status == -ERESTARTSYS) {
+		args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED;
+	} else {
+		args->out.status = HL_WAIT_CS_STATUS_BUSY;
+	}
+
+	return 0;
+}
+
 static int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
 {
 	struct hl_device *hdev = hpriv->hdev;
@@ -2015,9 +2715,9 @@
 {
 	struct hl_user_pending_interrupt *pend;
 	struct hl_user_interrupt *interrupt;
-	unsigned long timeout;
-	long completion_rc;
+	unsigned long timeout, flags;
 	u32 completion_value;
+	long completion_rc;
 	int rc = 0;
 
 	if (timeout_us == U32_MAX)
@@ -2040,17 +2740,10 @@
 	else
 		interrupt = &hdev->user_interrupt[interrupt_offset];
 
-	spin_lock(&interrupt->wait_list_lock);
-	if (!hl_device_operational(hdev, NULL)) {
-		rc = -EPERM;
-		goto unlock_and_free_fence;
-	}
-
 	if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) {
-		dev_err(hdev->dev,
-			"Failed to copy completion value from user\n");
+		dev_err(hdev->dev, "Failed to copy completion value from user\n");
 		rc = -EFAULT;
-		goto unlock_and_free_fence;
+		goto free_fence;
 	}
 
 	if (completion_value >= target_value)
@@ -2059,48 +2752,57 @@
 		*status = CS_WAIT_STATUS_BUSY;
 
 	if (!timeout_us || (*status == CS_WAIT_STATUS_COMPLETED))
-		goto unlock_and_free_fence;
+		goto free_fence;
 
 	/* Add pending user interrupt to relevant list for the interrupt
 	 * handler to monitor
 	 */
+	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
 	list_add_tail(&pend->wait_list_node, &interrupt->wait_list_head);
-	spin_unlock(&interrupt->wait_list_lock);
+	spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 
 wait_again:
 	/* Wait for interrupt handler to signal completion */
-	completion_rc =
-		wait_for_completion_interruptible_timeout(
-				&pend->fence.completion, timeout);
+	completion_rc = wait_for_completion_interruptible_timeout(&pend->fence.completion,
+										timeout);
 
 	/* If timeout did not expire we need to perform the comparison.
 	 * If comparison fails, keep waiting until timeout expires
 	 */
 	if (completion_rc > 0) {
-		if (copy_from_user(&completion_value,
-				u64_to_user_ptr(user_address), 4)) {
-			dev_err(hdev->dev,
-				"Failed to copy completion value from user\n");
+		if (copy_from_user(&completion_value, u64_to_user_ptr(user_address), 4)) {
+			dev_err(hdev->dev, "Failed to copy completion value from user\n");
 			rc = -EFAULT;
+
 			goto remove_pending_user_interrupt;
 		}
 
 		if (completion_value >= target_value) {
 			*status = CS_WAIT_STATUS_COMPLETED;
 		} else {
+			spin_lock_irqsave(&interrupt->wait_list_lock, flags);
+			reinit_completion(&pend->fence.completion);
 			timeout = completion_rc;
+
+			spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 			goto wait_again;
 		}
+	} else if (completion_rc == -ERESTARTSYS) {
+		dev_err_ratelimited(hdev->dev,
+			"user process got signal while waiting for interrupt ID %d\n",
+			interrupt->interrupt_id);
+		*status = HL_WAIT_CS_STATUS_INTERRUPTED;
+		rc = -EINTR;
 	} else {
 		*status = CS_WAIT_STATUS_BUSY;
 	}
 
 remove_pending_user_interrupt:
-	spin_lock(&interrupt->wait_list_lock);
+	spin_lock_irqsave(&interrupt->wait_list_lock, flags);
 	list_del(&pend->wait_list_node);
+	spin_unlock_irqrestore(&interrupt->wait_list_lock, flags);
 
-unlock_and_free_fence:
-	spin_unlock(&interrupt->wait_list_lock);
+free_fence:
 	kfree(pend);
 	hl_ctx_put(ctx);
 
@@ -2148,8 +2850,9 @@
 	memset(args, 0, sizeof(*args));
 
 	if (rc) {
-		dev_err_ratelimited(hdev->dev,
-			"interrupt_wait_ioctl failed (%d)\n", rc);
+		if (rc != -EINTR)
+			dev_err_ratelimited(hdev->dev,
+				"interrupt_wait_ioctl failed (%d)\n", rc);
 
 		return rc;
 	}
@@ -2173,8 +2876,16 @@
 	u32 flags = args->in.flags;
 	int rc;
 
+	/* If the device is not operational, no point in waiting for any command submission or
+	 * user interrupt
+	 */
+	if (!hl_device_operational(hpriv->hdev, NULL))
+		return -EPERM;
+
 	if (flags & HL_WAIT_CS_FLAGS_INTERRUPT)
 		rc = hl_interrupt_wait_ioctl(hpriv, data);
+	else if (flags & HL_WAIT_CS_FLAGS_MULTI_CS)
+		rc = hl_multi_cs_wait_ioctl(hpriv, data);
 	else
 		rc = hl_cs_wait_ioctl(hpriv, data);
 
diff --git a/drivers/misc/habanalabs/common/context.c b/drivers/misc/habanalabs/common/context.c
index 19b6b04..2297830 100644
--- a/drivers/misc/habanalabs/common/context.c
+++ b/drivers/misc/habanalabs/common/context.c
@@ -9,16 +9,70 @@
 
 #include <linux/slab.h>
 
+void hl_encaps_handle_do_release(struct kref *ref)
+{
+	struct hl_cs_encaps_sig_handle *handle =
+		container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
+	struct hl_ctx *ctx = handle->hdev->compute_ctx;
+	struct hl_encaps_signals_mgr *mgr = &ctx->sig_mgr;
+
+	spin_lock(&mgr->lock);
+	idr_remove(&mgr->handles, handle->id);
+	spin_unlock(&mgr->lock);
+
+	kfree(handle);
+}
+
+static void hl_encaps_handle_do_release_sob(struct kref *ref)
+{
+	struct hl_cs_encaps_sig_handle *handle =
+		container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
+	struct hl_ctx *ctx = handle->hdev->compute_ctx;
+	struct hl_encaps_signals_mgr *mgr = &ctx->sig_mgr;
+
+	/* if we're here, then there was a signals reservation but cs with
+	 * encaps signals wasn't submitted, so need to put refcount
+	 * to hw_sob taken at the reservation.
+	 */
+	hw_sob_put(handle->hw_sob);
+
+	spin_lock(&mgr->lock);
+	idr_remove(&mgr->handles, handle->id);
+	spin_unlock(&mgr->lock);
+
+	kfree(handle);
+}
+
+static void hl_encaps_sig_mgr_init(struct hl_encaps_signals_mgr *mgr)
+{
+	spin_lock_init(&mgr->lock);
+	idr_init(&mgr->handles);
+}
+
+static void hl_encaps_sig_mgr_fini(struct hl_device *hdev,
+			struct hl_encaps_signals_mgr *mgr)
+{
+	struct hl_cs_encaps_sig_handle *handle;
+	struct idr *idp;
+	u32 id;
+
+	idp = &mgr->handles;
+
+	if (!idr_is_empty(idp)) {
+		dev_warn(hdev->dev, "device released while some encaps signals handles are still allocated\n");
+		idr_for_each_entry(idp, handle, id)
+			kref_put(&handle->refcount,
+					hl_encaps_handle_do_release_sob);
+	}
+
+	idr_destroy(&mgr->handles);
+}
+
 static void hl_ctx_fini(struct hl_ctx *ctx)
 {
 	struct hl_device *hdev = ctx->hdev;
 	int i;
 
-	/* Release all allocated pending cb's, those cb's were never
-	 * scheduled so it is safe to release them here
-	 */
-	hl_pending_cb_list_flush(ctx);
-
 	/* Release all allocated HW block mapped list entries and destroy
 	 * the mutex.
 	 */
@@ -53,6 +107,7 @@
 		hl_cb_va_pool_fini(ctx);
 		hl_vm_ctx_fini(ctx);
 		hl_asid_free(hdev, ctx->asid);
+		hl_encaps_sig_mgr_fini(hdev, &ctx->sig_mgr);
 
 		/* Scrub both SRAM and DRAM */
 		hdev->asic_funcs->scrub_device_mem(hdev, 0, 0);
@@ -130,9 +185,6 @@
 {
 	if (kref_put(&ctx->refcount, hl_ctx_do_release) == 1)
 		return;
-
-	dev_warn(hdev->dev,
-		"user process released device but its command submissions are still executing\n");
 }
 
 int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx)
@@ -144,11 +196,8 @@
 	kref_init(&ctx->refcount);
 
 	ctx->cs_sequence = 1;
-	INIT_LIST_HEAD(&ctx->pending_cb_list);
-	spin_lock_init(&ctx->pending_cb_lock);
 	spin_lock_init(&ctx->cs_lock);
 	atomic_set(&ctx->thread_ctx_switch_token, 1);
-	atomic_set(&ctx->thread_pending_cb_token, 1);
 	ctx->thread_ctx_switch_wait_token = 0;
 	ctx->cs_pending = kcalloc(hdev->asic_prop.max_pending_cs,
 				sizeof(struct hl_fence *),
@@ -200,6 +249,8 @@
 			goto err_cb_va_pool_fini;
 		}
 
+		hl_encaps_sig_mgr_init(&ctx->sig_mgr);
+
 		dev_dbg(hdev->dev, "create user context %d\n", ctx->asid);
 	}
 
@@ -229,25 +280,40 @@
 	return kref_put(&ctx->refcount, hl_ctx_do_release);
 }
 
-struct hl_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq)
+/*
+ * hl_ctx_get_fence_locked - get CS fence under CS lock
+ *
+ * @ctx: pointer to the context structure.
+ * @seq: CS sequences number
+ *
+ * @return valid fence pointer on success, NULL if fence is gone, otherwise
+ *         error pointer.
+ *
+ * NOTE: this function shall be called with cs_lock locked
+ */
+static struct hl_fence *hl_ctx_get_fence_locked(struct hl_ctx *ctx, u64 seq)
 {
 	struct asic_fixed_properties *asic_prop = &ctx->hdev->asic_prop;
 	struct hl_fence *fence;
 
-	spin_lock(&ctx->cs_lock);
-
-	if (seq >= ctx->cs_sequence) {
-		spin_unlock(&ctx->cs_lock);
+	if (seq >= ctx->cs_sequence)
 		return ERR_PTR(-EINVAL);
-	}
 
-	if (seq + asic_prop->max_pending_cs < ctx->cs_sequence) {
-		spin_unlock(&ctx->cs_lock);
+	if (seq + asic_prop->max_pending_cs < ctx->cs_sequence)
 		return NULL;
-	}
 
 	fence = ctx->cs_pending[seq & (asic_prop->max_pending_cs - 1)];
 	hl_fence_get(fence);
+	return fence;
+}
+
+struct hl_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq)
+{
+	struct hl_fence *fence;
+
+	spin_lock(&ctx->cs_lock);
+
+	fence = hl_ctx_get_fence_locked(ctx, seq);
 
 	spin_unlock(&ctx->cs_lock);
 
@@ -255,6 +321,46 @@
 }
 
 /*
+ * hl_ctx_get_fences - get multiple CS fences under the same CS lock
+ *
+ * @ctx: pointer to the context structure.
+ * @seq_arr: array of CS sequences to wait for
+ * @fence: fence array to store the CS fences
+ * @arr_len: length of seq_arr and fence_arr
+ *
+ * @return 0 on success, otherwise non 0 error code
+ */
+int hl_ctx_get_fences(struct hl_ctx *ctx, u64 *seq_arr,
+				struct hl_fence **fence, u32 arr_len)
+{
+	struct hl_fence **fence_arr_base = fence;
+	int i, rc = 0;
+
+	spin_lock(&ctx->cs_lock);
+
+	for (i = 0; i < arr_len; i++, fence++) {
+		u64 seq = seq_arr[i];
+
+		*fence = hl_ctx_get_fence_locked(ctx, seq);
+
+		if (IS_ERR(*fence)) {
+			dev_err(ctx->hdev->dev,
+				"Failed to get fence for CS with seq 0x%llx\n",
+					seq);
+			rc = PTR_ERR(*fence);
+			break;
+		}
+	}
+
+	spin_unlock(&ctx->cs_lock);
+
+	if (rc)
+		hl_fences_put(fence_arr_base, i);
+
+	return rc;
+}
+
+/*
  * hl_ctx_mgr_init - initialize the context manager
  *
  * @mgr: pointer to context manager structure
diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c
index 703d79f..985f1f3d 100644
--- a/drivers/misc/habanalabs/common/debugfs.c
+++ b/drivers/misc/habanalabs/common/debugfs.c
@@ -209,12 +209,12 @@
 		if (first) {
 			first = false;
 			seq_puts(s, "\n");
-			seq_puts(s, " user virtual address     size             dma dir\n");
+			seq_puts(s, " pid      user virtual address     size             dma dir\n");
 			seq_puts(s, "----------------------------------------------------------\n");
 		}
-		seq_printf(s,
-			"    0x%-14llx      %-10u    %-30s\n",
-			userptr->addr, userptr->size, dma_dir[userptr->dir]);
+		seq_printf(s, " %-7d  0x%-14llx      %-10llu    %-30s\n",
+				userptr->pid, userptr->addr, userptr->size,
+				dma_dir[userptr->dir]);
 	}
 
 	spin_unlock(&dev_entry->userptr_spinlock);
@@ -235,7 +235,7 @@
 	struct hl_vm_hash_node *hnode;
 	struct hl_userptr *userptr;
 	struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
-	enum vm_type_t *vm_type;
+	enum vm_type *vm_type;
 	bool once = true;
 	u64 j;
 	int i;
@@ -261,7 +261,7 @@
 			if (*vm_type == VM_TYPE_USERPTR) {
 				userptr = hnode->ptr;
 				seq_printf(s,
-					"    0x%-14llx      %-10u\n",
+					"    0x%-14llx      %-10llu\n",
 					hnode->vaddr, userptr->size);
 			} else {
 				phys_pg_pack = hnode->ptr;
@@ -320,6 +320,77 @@
 	return 0;
 }
 
+static int userptr_lookup_show(struct seq_file *s, void *data)
+{
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	struct scatterlist *sg;
+	struct hl_userptr *userptr;
+	bool first = true;
+	u64 total_npages, npages, sg_start, sg_end;
+	dma_addr_t dma_addr;
+	int i;
+
+	spin_lock(&dev_entry->userptr_spinlock);
+
+	list_for_each_entry(userptr, &dev_entry->userptr_list, debugfs_list) {
+		if (dev_entry->userptr_lookup >= userptr->addr &&
+		dev_entry->userptr_lookup < userptr->addr + userptr->size) {
+			total_npages = 0;
+			for_each_sg(userptr->sgt->sgl, sg, userptr->sgt->nents,
+					i) {
+				npages = hl_get_sg_info(sg, &dma_addr);
+				sg_start = userptr->addr +
+					total_npages * PAGE_SIZE;
+				sg_end = userptr->addr +
+					(total_npages + npages) * PAGE_SIZE;
+
+				if (dev_entry->userptr_lookup >= sg_start &&
+				    dev_entry->userptr_lookup < sg_end) {
+					dma_addr += (dev_entry->userptr_lookup -
+							sg_start);
+					if (first) {
+						first = false;
+						seq_puts(s, "\n");
+						seq_puts(s, " user virtual address         dma address       pid        region start     region size\n");
+						seq_puts(s, "---------------------------------------------------------------------------------------\n");
+					}
+					seq_printf(s, " 0x%-18llx  0x%-16llx  %-8u  0x%-16llx %-12llu\n",
+						dev_entry->userptr_lookup,
+						(u64)dma_addr, userptr->pid,
+						userptr->addr, userptr->size);
+				}
+				total_npages += npages;
+			}
+		}
+	}
+
+	spin_unlock(&dev_entry->userptr_spinlock);
+
+	if (!first)
+		seq_puts(s, "\n");
+
+	return 0;
+}
+
+static ssize_t userptr_lookup_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *f_pos)
+{
+	struct seq_file *s = file->private_data;
+	struct hl_debugfs_entry *entry = s->private;
+	struct hl_dbg_device_entry *dev_entry = entry->dev_entry;
+	ssize_t rc;
+	u64 value;
+
+	rc = kstrtoull_from_user(buf, count, 16, &value);
+	if (rc)
+		return rc;
+
+	dev_entry->userptr_lookup = value;
+
+	return count;
+}
+
 static int mmu_show(struct seq_file *s, void *data)
 {
 	struct hl_debugfs_entry *entry = s->private;
@@ -349,7 +420,7 @@
 		return 0;
 	}
 
-	phys_addr = hops_info.hop_info[hops_info.used_hops - 1].hop_pte_val;
+	hl_mmu_va_to_pa(ctx, virt_addr, &phys_addr);
 
 	if (hops_info.scrambled_vaddr &&
 		(dev_entry->mmu_addr != hops_info.scrambled_vaddr))
@@ -491,11 +562,10 @@
 	struct hl_vm_phys_pg_pack *phys_pg_pack;
 	struct hl_ctx *ctx = hdev->compute_ctx;
 	struct hl_vm_hash_node *hnode;
+	u64 end_address, range_size;
 	struct hl_userptr *userptr;
-	enum vm_type_t *vm_type;
+	enum vm_type *vm_type;
 	bool valid = false;
-	u64 end_address;
-	u32 range_size;
 	int i, rc = 0;
 
 	if (!ctx) {
@@ -1043,6 +1113,60 @@
 	return 0;
 }
 
+static ssize_t hl_state_dump_read(struct file *f, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
+	ssize_t rc;
+
+	down_read(&entry->state_dump_sem);
+	if (!entry->state_dump[entry->state_dump_head])
+		rc = 0;
+	else
+		rc = simple_read_from_buffer(
+			buf, count, ppos,
+			entry->state_dump[entry->state_dump_head],
+			strlen(entry->state_dump[entry->state_dump_head]));
+	up_read(&entry->state_dump_sem);
+
+	return rc;
+}
+
+static ssize_t hl_state_dump_write(struct file *f, const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
+	struct hl_device *hdev = entry->hdev;
+	ssize_t rc;
+	u32 size;
+	int i;
+
+	rc = kstrtouint_from_user(buf, count, 10, &size);
+	if (rc)
+		return rc;
+
+	if (size <= 0 || size >= ARRAY_SIZE(entry->state_dump)) {
+		dev_err(hdev->dev, "Invalid number of dumps to skip\n");
+		return -EINVAL;
+	}
+
+	if (entry->state_dump[entry->state_dump_head]) {
+		down_write(&entry->state_dump_sem);
+		for (i = 0; i < size; ++i) {
+			vfree(entry->state_dump[entry->state_dump_head]);
+			entry->state_dump[entry->state_dump_head] = NULL;
+			if (entry->state_dump_head > 0)
+				entry->state_dump_head--;
+			else
+				entry->state_dump_head =
+					ARRAY_SIZE(entry->state_dump) - 1;
+		}
+		up_write(&entry->state_dump_sem);
+	}
+
+	return count;
+}
+
 static const struct file_operations hl_data32b_fops = {
 	.owner = THIS_MODULE,
 	.read = hl_data_read32,
@@ -1110,12 +1234,19 @@
 	.read = hl_security_violations_read
 };
 
+static const struct file_operations hl_state_dump_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_state_dump_read,
+	.write = hl_state_dump_write
+};
+
 static const struct hl_info_list hl_debugfs_list[] = {
 	{"command_buffers", command_buffers_show, NULL},
 	{"command_submission", command_submission_show, NULL},
 	{"command_submission_jobs", command_submission_jobs_show, NULL},
 	{"userptr", userptr_show, NULL},
 	{"vm", vm_show, NULL},
+	{"userptr_lookup", userptr_lookup_show, userptr_lookup_write},
 	{"mmu", mmu_show, mmu_asid_va_write},
 	{"engines", engines_show, NULL}
 };
@@ -1172,6 +1303,7 @@
 	INIT_LIST_HEAD(&dev_entry->userptr_list);
 	INIT_LIST_HEAD(&dev_entry->ctx_mem_hash_list);
 	mutex_init(&dev_entry->file_mutex);
+	init_rwsem(&dev_entry->state_dump_sem);
 	spin_lock_init(&dev_entry->cb_spinlock);
 	spin_lock_init(&dev_entry->cs_spinlock);
 	spin_lock_init(&dev_entry->cs_job_spinlock);
@@ -1283,6 +1415,12 @@
 				dev_entry->root,
 				&hdev->skip_reset_on_timeout);
 
+	debugfs_create_file("state_dump",
+				0600,
+				dev_entry->root,
+				dev_entry,
+				&hl_state_dump_fops);
+
 	for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
 		debugfs_create_file(hl_debugfs_list[i].name,
 					0444,
@@ -1297,6 +1435,7 @@
 void hl_debugfs_remove_device(struct hl_device *hdev)
 {
 	struct hl_dbg_device_entry *entry = &hdev->hl_debugfs;
+	int i;
 
 	debugfs_remove_recursive(entry->root);
 
@@ -1304,6 +1443,9 @@
 
 	vfree(entry->blob_desc.data);
 
+	for (i = 0; i < ARRAY_SIZE(entry->state_dump); ++i)
+		vfree(entry->state_dump[i]);
+
 	kfree(entry->entry_arr);
 }
 
@@ -1416,6 +1558,28 @@
 	spin_unlock(&dev_entry->ctx_mem_hash_spinlock);
 }
 
+/**
+ * hl_debugfs_set_state_dump - register state dump making it accessible via
+ *                             debugfs
+ * @hdev: pointer to the device structure
+ * @data: the actual dump data
+ * @length: the length of the data
+ */
+void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
+					unsigned long length)
+{
+	struct hl_dbg_device_entry *dev_entry = &hdev->hl_debugfs;
+
+	down_write(&dev_entry->state_dump_sem);
+
+	dev_entry->state_dump_head = (dev_entry->state_dump_head + 1) %
+					ARRAY_SIZE(dev_entry->state_dump);
+	vfree(dev_entry->state_dump[dev_entry->state_dump_head]);
+	dev_entry->state_dump[dev_entry->state_dump_head] = data;
+
+	up_write(&dev_entry->state_dump_sem);
+}
+
 void __init hl_debugfs_init(void)
 {
 	hl_debug_root = debugfs_create_dir("habanalabs", NULL);
diff --git a/drivers/misc/habanalabs/common/device.c b/drivers/misc/habanalabs/common/device.c
index ff4cbde..97c7c86 100644
--- a/drivers/misc/habanalabs/common/device.c
+++ b/drivers/misc/habanalabs/common/device.c
@@ -7,11 +7,11 @@
 
 #define pr_fmt(fmt)			"habanalabs: " fmt
 
+#include <uapi/misc/habanalabs.h>
 #include "habanalabs.h"
 
 #include <linux/pci.h>
 #include <linux/hwmon.h>
-#include <uapi/misc/habanalabs.h>
 
 enum hl_device_status hl_device_status(struct hl_device *hdev)
 {
@@ -23,6 +23,8 @@
 		status = HL_DEVICE_STATUS_NEEDS_RESET;
 	else if (hdev->disabled)
 		status = HL_DEVICE_STATUS_MALFUNCTION;
+	else if (!hdev->init_done)
+		status = HL_DEVICE_STATUS_IN_DEVICE_CREATION;
 	else
 		status = HL_DEVICE_STATUS_OPERATIONAL;
 
@@ -44,6 +46,7 @@
 	case HL_DEVICE_STATUS_NEEDS_RESET:
 		return false;
 	case HL_DEVICE_STATUS_OPERATIONAL:
+	case HL_DEVICE_STATUS_IN_DEVICE_CREATION:
 	default:
 		return true;
 	}
@@ -129,8 +132,8 @@
 	hl_ctx_mgr_fini(hdev, &hpriv->ctx_mgr);
 
 	if (!hl_hpriv_put(hpriv))
-		dev_warn(hdev->dev,
-			"Device is still in use because there are live CS and/or memory mappings\n");
+		dev_notice(hdev->dev,
+			"User process closed FD but device still in use\n");
 
 	hdev->last_open_session_duration_jif =
 		jiffies - hdev->last_successful_open_jif;
@@ -308,9 +311,15 @@
 		container_of(work, struct hl_device_reset_work,
 				reset_work.work);
 	struct hl_device *hdev = device_reset_work->hdev;
+	u32 flags;
 	int rc;
 
-	rc = hl_device_reset(hdev, HL_RESET_HARD | HL_RESET_FROM_RESET_THREAD);
+	flags = HL_RESET_HARD | HL_RESET_FROM_RESET_THREAD;
+
+	if (device_reset_work->fw_reset)
+		flags |= HL_RESET_FW;
+
+	rc = hl_device_reset(hdev, flags);
 	if ((rc == -EBUSY) && !hdev->device_fini_pending) {
 		dev_info(hdev->dev,
 			"Could not reset device. will try again in %u seconds",
@@ -682,6 +691,44 @@
 	return rc;
 }
 
+static void take_release_locks(struct hl_device *hdev)
+{
+	/* Flush anyone that is inside the critical section of enqueue
+	 * jobs to the H/W
+	 */
+	hdev->asic_funcs->hw_queues_lock(hdev);
+	hdev->asic_funcs->hw_queues_unlock(hdev);
+
+	/* Flush processes that are sending message to CPU */
+	mutex_lock(&hdev->send_cpu_message_lock);
+	mutex_unlock(&hdev->send_cpu_message_lock);
+
+	/* Flush anyone that is inside device open */
+	mutex_lock(&hdev->fpriv_list_lock);
+	mutex_unlock(&hdev->fpriv_list_lock);
+}
+
+static void cleanup_resources(struct hl_device *hdev, bool hard_reset, bool fw_reset)
+{
+	if (hard_reset)
+		device_late_fini(hdev);
+
+	/*
+	 * Halt the engines and disable interrupts so we won't get any more
+	 * completions from H/W and we won't have any accesses from the
+	 * H/W to the host machine
+	 */
+	hdev->asic_funcs->halt_engines(hdev, hard_reset, fw_reset);
+
+	/* Go over all the queues, release all CS and their jobs */
+	hl_cs_rollback_all(hdev);
+
+	/* Release all pending user interrupts, each pending user interrupt
+	 * holds a reference to user context
+	 */
+	hl_release_pending_user_interrupts(hdev);
+}
+
 /*
  * hl_device_suspend - initiate device suspend
  *
@@ -707,16 +754,7 @@
 	/* This blocks all other stuff that is not blocked by in_reset */
 	hdev->disabled = true;
 
-	/*
-	 * Flush anyone that is inside the critical section of enqueue
-	 * jobs to the H/W
-	 */
-	hdev->asic_funcs->hw_queues_lock(hdev);
-	hdev->asic_funcs->hw_queues_unlock(hdev);
-
-	/* Flush processes that are sending message to CPU */
-	mutex_lock(&hdev->send_cpu_message_lock);
-	mutex_unlock(&hdev->send_cpu_message_lock);
+	take_release_locks(hdev);
 
 	rc = hdev->asic_funcs->suspend(hdev);
 	if (rc)
@@ -819,6 +857,11 @@
 			usleep_range(1000, 10000);
 
 			put_task_struct(task);
+		} else {
+			dev_warn(hdev->dev,
+				"Can't get task struct for PID so giving up on killing process\n");
+			mutex_unlock(&hdev->fpriv_list_lock);
+			return -ETIME;
 		}
 	}
 
@@ -885,7 +928,7 @@
 int hl_device_reset(struct hl_device *hdev, u32 flags)
 {
 	u64 idle_mask[HL_BUSY_ENGINES_MASK_EXT_SIZE] = {0};
-	bool hard_reset, from_hard_reset_thread, hard_instead_soft = false;
+	bool hard_reset, from_hard_reset_thread, fw_reset, hard_instead_soft = false;
 	int i, rc;
 
 	if (!hdev->init_done) {
@@ -894,8 +937,9 @@
 		return 0;
 	}
 
-	hard_reset = (flags & HL_RESET_HARD) != 0;
-	from_hard_reset_thread = (flags & HL_RESET_FROM_RESET_THREAD) != 0;
+	hard_reset = !!(flags & HL_RESET_HARD);
+	from_hard_reset_thread = !!(flags & HL_RESET_FROM_RESET_THREAD);
+	fw_reset = !!(flags & HL_RESET_FW);
 
 	if (!hard_reset && !hdev->supports_soft_reset) {
 		hard_instead_soft = true;
@@ -947,11 +991,13 @@
 		else
 			hdev->curr_reset_cause = HL_RESET_CAUSE_UNKNOWN;
 
-		/*
-		 * if reset is due to heartbeat, device CPU is no responsive in
-		 * which case no point sending PCI disable message to it
+		/* If reset is due to heartbeat, device CPU is no responsive in
+		 * which case no point sending PCI disable message to it.
+		 *
+		 * If F/W is performing the reset, no need to send it a message to disable
+		 * PCI access
 		 */
-		if (hard_reset && !(flags & HL_RESET_HEARTBEAT)) {
+		if (hard_reset && !(flags & (HL_RESET_HEARTBEAT | HL_RESET_FW))) {
 			/* Disable PCI access from device F/W so he won't send
 			 * us additional interrupts. We disable MSI/MSI-X at
 			 * the halt_engines function and we can't have the F/W
@@ -970,15 +1016,7 @@
 		/* This also blocks future CS/VM/JOB completion operations */
 		hdev->disabled = true;
 
-		/* Flush anyone that is inside the critical section of enqueue
-		 * jobs to the H/W
-		 */
-		hdev->asic_funcs->hw_queues_lock(hdev);
-		hdev->asic_funcs->hw_queues_unlock(hdev);
-
-		/* Flush anyone that is inside device open */
-		mutex_lock(&hdev->fpriv_list_lock);
-		mutex_unlock(&hdev->fpriv_list_lock);
+		take_release_locks(hdev);
 
 		dev_err(hdev->dev, "Going to RESET device!\n");
 	}
@@ -989,6 +1027,8 @@
 
 		hdev->process_kill_trial_cnt = 0;
 
+		hdev->device_reset_work.fw_reset = fw_reset;
+
 		/*
 		 * Because the reset function can't run from heartbeat work,
 		 * we need to call the reset function from a dedicated work.
@@ -999,31 +1039,7 @@
 		return 0;
 	}
 
-	if (hard_reset) {
-		device_late_fini(hdev);
-
-		/*
-		 * Now that the heartbeat thread is closed, flush processes
-		 * which are sending messages to CPU
-		 */
-		mutex_lock(&hdev->send_cpu_message_lock);
-		mutex_unlock(&hdev->send_cpu_message_lock);
-	}
-
-	/*
-	 * Halt the engines and disable interrupts so we won't get any more
-	 * completions from H/W and we won't have any accesses from the
-	 * H/W to the host machine
-	 */
-	hdev->asic_funcs->halt_engines(hdev, hard_reset);
-
-	/* Go over all the queues, release all CS and their jobs */
-	hl_cs_rollback_all(hdev);
-
-	/* Release all pending user interrupts, each pending user interrupt
-	 * holds a reference to user context
-	 */
-	hl_release_pending_user_interrupts(hdev);
+	cleanup_resources(hdev, hard_reset, fw_reset);
 
 kill_processes:
 	if (hard_reset) {
@@ -1057,12 +1073,15 @@
 	}
 
 	/* Reset the H/W. It will be in idle state after this returns */
-	hdev->asic_funcs->hw_fini(hdev, hard_reset);
+	hdev->asic_funcs->hw_fini(hdev, hard_reset, fw_reset);
 
 	if (hard_reset) {
+		hdev->fw_loader.linux_loaded = false;
+
 		/* Release kernel context */
 		if (hdev->kernel_ctx && hl_ctx_put(hdev->kernel_ctx) == 1)
 			hdev->kernel_ctx = NULL;
+
 		hl_vm_fini(hdev);
 		hl_mmu_fini(hdev);
 		hl_eq_reset(hdev, &hdev->event_queue);
@@ -1292,6 +1311,10 @@
 	if (rc)
 		goto user_interrupts_fini;
 
+
+	/* initialize completion structure for multi CS wait */
+	hl_multi_cs_completion_init(hdev);
+
 	/*
 	 * Initialize the H/W queues. Must be done before hw_init, because
 	 * there the addresses of the kernel queue are being written to the
@@ -1361,6 +1384,8 @@
 
 	hdev->compute_ctx = NULL;
 
+	hdev->asic_funcs->state_dump_init(hdev);
+
 	hl_debugfs_add_device(hdev);
 
 	/* debugfs nodes are created in hl_ctx_init so it must be called after
@@ -1567,31 +1592,13 @@
 	/* Mark device as disabled */
 	hdev->disabled = true;
 
-	/* Flush anyone that is inside the critical section of enqueue
-	 * jobs to the H/W
-	 */
-	hdev->asic_funcs->hw_queues_lock(hdev);
-	hdev->asic_funcs->hw_queues_unlock(hdev);
-
-	/* Flush anyone that is inside device open */
-	mutex_lock(&hdev->fpriv_list_lock);
-	mutex_unlock(&hdev->fpriv_list_lock);
+	take_release_locks(hdev);
 
 	hdev->hard_reset_pending = true;
 
 	hl_hwmon_fini(hdev);
 
-	device_late_fini(hdev);
-
-	/*
-	 * Halt the engines and disable interrupts so we won't get any more
-	 * completions from H/W and we won't have any accesses from the
-	 * H/W to the host machine
-	 */
-	hdev->asic_funcs->halt_engines(hdev, true);
-
-	/* Go over all the queues, release all CS and their jobs */
-	hl_cs_rollback_all(hdev);
+	cleanup_resources(hdev, true, false);
 
 	/* Kill processes here after CS rollback. This is because the process
 	 * can't really exit until all its CSs are done, which is what we
@@ -1610,7 +1617,9 @@
 	hl_cb_pool_fini(hdev);
 
 	/* Reset the H/W. It will be in idle state after this returns */
-	hdev->asic_funcs->hw_fini(hdev, true);
+	hdev->asic_funcs->hw_fini(hdev, true, false);
+
+	hdev->fw_loader.linux_loaded = false;
 
 	/* Release kernel context */
 	if ((hdev->kernel_ctx) && (hl_ctx_put(hdev->kernel_ctx) != 1))
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 2e4d04e..8d2568c 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 /*
- * Copyright 2016-2019 HabanaLabs, Ltd.
+ * Copyright 2016-2021 HabanaLabs, Ltd.
  * All Rights Reserved.
  */
 
@@ -240,11 +240,15 @@
 	/* set fence to a non valid value */
 	pkt->fence = cpu_to_le32(UINT_MAX);
 
-	rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, len, pkt_dma_addr);
-	if (rc) {
-		dev_err(hdev->dev, "Failed to send CB on CPU PQ (%d)\n", rc);
-		goto out;
-	}
+	/*
+	 * The CPU queue is a synchronous queue with an effective depth of
+	 * a single entry (although it is allocated with room for multiple
+	 * entries). We lock on it using 'send_cpu_message_lock' which
+	 * serializes accesses to the CPU queue.
+	 * Which means that we don't need to lock the access to the entire H/W
+	 * queues module when submitting a JOB to the CPU queue.
+	 */
+	hl_hw_queue_submit_bd(hdev, queue, 0, len, pkt_dma_addr);
 
 	if (prop->fw_app_cpu_boot_dev_sts0 & CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN)
 		expected_ack_val = queue->pi;
@@ -663,17 +667,15 @@
 	hdev->event_queue.check_eqe_index = false;
 
 	/* Read FW application security bits again */
-	if (hdev->asic_prop.fw_cpu_boot_dev_sts0_valid) {
-		hdev->asic_prop.fw_app_cpu_boot_dev_sts0 =
-						RREG32(sts_boot_dev_sts0_reg);
-		if (hdev->asic_prop.fw_app_cpu_boot_dev_sts0 &
+	if (prop->fw_cpu_boot_dev_sts0_valid) {
+		prop->fw_app_cpu_boot_dev_sts0 = RREG32(sts_boot_dev_sts0_reg);
+		if (prop->fw_app_cpu_boot_dev_sts0 &
 				CPU_BOOT_DEV_STS0_EQ_INDEX_EN)
 			hdev->event_queue.check_eqe_index = true;
 	}
 
-	if (hdev->asic_prop.fw_cpu_boot_dev_sts1_valid)
-		hdev->asic_prop.fw_app_cpu_boot_dev_sts1 =
-						RREG32(sts_boot_dev_sts1_reg);
+	if (prop->fw_cpu_boot_dev_sts1_valid)
+		prop->fw_app_cpu_boot_dev_sts1 = RREG32(sts_boot_dev_sts1_reg);
 
 out:
 	hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev,
@@ -1008,6 +1010,11 @@
 	} else {
 		WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_GOTO_WFE);
 		msleep(static_loader->cpu_reset_wait_msec);
+
+		/* Must clear this register in order to prevent preboot
+		 * from reading WFE after reboot
+		 */
+		WREG32(static_loader->kmd_msg_to_cpu_reg, KMD_MSG_NA);
 	}
 
 	hdev->device_cpu_is_halted = true;
@@ -1055,6 +1062,10 @@
 		dev_err(hdev->dev,
 			"Device boot progress - Thermal Sensor initialization failed\n");
 		break;
+	case CPU_BOOT_STATUS_SECURITY_READY:
+		dev_err(hdev->dev,
+			"Device boot progress - Stuck in preboot after security initialization\n");
+		break;
 	default:
 		dev_err(hdev->dev,
 			"Device boot progress - Invalid status code %d\n",
@@ -1238,11 +1249,6 @@
 	 *               b. Check whether hard reset is done by boot cpu
 	 * 3. FW application - a. Fetch fw application security status
 	 *                     b. Check whether hard reset is done by fw app
-	 *
-	 * Preboot:
-	 * Check security status bit (CPU_BOOT_DEV_STS0_ENABLED). If set, then-
-	 * check security enabled bit (CPU_BOOT_DEV_STS0_SECURITY_EN)
-	 * If set, then mark GIC controller to be disabled.
 	 */
 	prop->hard_reset_done_by_fw =
 		!!(cpu_boot_dev_sts0 & CPU_BOOT_DEV_STS0_FW_HARD_RST_EN);
@@ -1953,8 +1959,8 @@
 	if (!hdev->asic_prop.gic_interrupts_enable &&
 			!(hdev->asic_prop.fw_app_cpu_boot_dev_sts0 &
 				CPU_BOOT_DEV_STS0_MULTI_IRQ_POLL_EN)) {
-		dyn_regs->gic_host_halt_irq = dyn_regs->gic_host_irq_ctrl;
-		dyn_regs->gic_host_ints_irq = dyn_regs->gic_host_irq_ctrl;
+		dyn_regs->gic_host_halt_irq = dyn_regs->gic_host_pi_upd_irq;
+		dyn_regs->gic_host_ints_irq = dyn_regs->gic_host_pi_upd_irq;
 
 		dev_warn(hdev->dev,
 			"Using a single interrupt interface towards cpucp");
@@ -2122,8 +2128,7 @@
 
 	/* Read FW application security bits */
 	if (prop->fw_cpu_boot_dev_sts0_valid) {
-		prop->fw_app_cpu_boot_dev_sts0 =
-				RREG32(cpu_boot_dev_sts0_reg);
+		prop->fw_app_cpu_boot_dev_sts0 = RREG32(cpu_boot_dev_sts0_reg);
 
 		if (prop->fw_app_cpu_boot_dev_sts0 &
 				CPU_BOOT_DEV_STS0_FW_HARD_RST_EN)
@@ -2143,8 +2148,7 @@
 	}
 
 	if (prop->fw_cpu_boot_dev_sts1_valid) {
-		prop->fw_app_cpu_boot_dev_sts1 =
-				RREG32(cpu_boot_dev_sts1_reg);
+		prop->fw_app_cpu_boot_dev_sts1 = RREG32(cpu_boot_dev_sts1_reg);
 
 		dev_dbg(hdev->dev,
 			"Firmware application CPU status1 %#x\n",
@@ -2235,6 +2239,10 @@
 	dev_info(hdev->dev,
 		"Loading firmware to device, may take some time...\n");
 
+	/*
+	 * In this stage, "cpu_dyn_regs" contains only LKD's hard coded values!
+	 * It will be updated from FW after hl_fw_dynamic_request_descriptor().
+	 */
 	dyn_regs = &fw_loader->dynamic_loader.comm_desc.cpu_dyn_regs;
 
 	rc = hl_fw_dynamic_send_protocol_cmd(hdev, fw_loader, COMMS_RST_STATE,
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 6b3cdd7..bebebcb 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -20,6 +20,7 @@
 #include <linux/scatterlist.h>
 #include <linux/hashtable.h>
 #include <linux/debugfs.h>
+#include <linux/rwsem.h>
 #include <linux/bitfield.h>
 #include <linux/genalloc.h>
 #include <linux/sched/signal.h>
@@ -65,6 +66,11 @@
 
 #define HL_COMMON_USER_INTERRUPT_ID	0xFFF
 
+#define HL_STATE_DUMP_HIST_LEN		5
+
+#define OBJ_NAMES_HASH_TABLE_BITS	7 /* 1 << 7 buckets */
+#define SYNC_TO_ENGINE_HASH_TABLE_BITS	7 /* 1 << 7 buckets */
+
 /* Memory */
 #define MEM_HASH_TABLE_BITS		7 /* 1 << 7 buckets */
 
@@ -122,12 +128,17 @@
  *
  * - HL_RESET_DEVICE_RELEASE
  *       Set if reset is due to device release
+ *
+ * - HL_RESET_FW
+ *       F/W will perform the reset. No need to ask it to reset the device. This is relevant
+ *       only when running with secured f/w
  */
 #define HL_RESET_HARD			(1 << 0)
 #define HL_RESET_FROM_RESET_THREAD	(1 << 1)
 #define HL_RESET_HEARTBEAT		(1 << 2)
 #define HL_RESET_TDR			(1 << 3)
 #define HL_RESET_DEVICE_RELEASE		(1 << 4)
+#define HL_RESET_FW			(1 << 5)
 
 #define HL_MAX_SOBS_PER_MONITOR	8
 
@@ -236,7 +247,9 @@
 	CS_TYPE_DEFAULT,
 	CS_TYPE_SIGNAL,
 	CS_TYPE_WAIT,
-	CS_TYPE_COLLECTIVE_WAIT
+	CS_TYPE_COLLECTIVE_WAIT,
+	CS_RESERVE_SIGNALS,
+	CS_UNRESERVE_SIGNALS
 };
 
 /*
@@ -281,13 +294,17 @@
  * @hdev: habanalabs device structure.
  * @kref: refcount of this SOB. The SOB will reset once the refcount is zero.
  * @sob_id: id of this SOB.
+ * @sob_addr: the sob offset from the base address.
  * @q_idx: the H/W queue that uses this SOB.
+ * @need_reset: reset indication set when switching to the other sob.
  */
 struct hl_hw_sob {
 	struct hl_device	*hdev;
 	struct kref		kref;
 	u32			sob_id;
+	u32			sob_addr;
 	u32			q_idx;
+	bool			need_reset;
 };
 
 enum hl_collective_mode {
@@ -317,11 +334,11 @@
 };
 
 /**
- * enum vm_type_t - virtual memory mapping request information.
+ * enum vm_type - virtual memory mapping request information.
  * @VM_TYPE_USERPTR: mapping of user memory to device virtual address.
  * @VM_TYPE_PHYS_PACK: mapping of DRAM memory to device virtual address.
  */
-enum vm_type_t {
+enum vm_type {
 	VM_TYPE_USERPTR = 0x1,
 	VM_TYPE_PHYS_PACK = 0x2
 };
@@ -382,6 +399,16 @@
 };
 
 /**
+ * struct hl_hints_range - hint addresses reserved va range.
+ * @start_addr: start address of the va range.
+ * @end_addr: end address of the va range.
+ */
+struct hl_hints_range {
+	u64 start_addr;
+	u64 end_addr;
+};
+
+/**
  * struct asic_fixed_properties - ASIC specific immutable properties.
  * @hw_queues_props: H/W queues properties.
  * @cpucp_info: received various information from CPU-CP regarding the H/W, e.g.
@@ -392,6 +419,10 @@
  * @pmmu: PCI (host) MMU address translation properties.
  * @pmmu_huge: PCI (host) MMU address translation properties for memory
  *              allocated with huge pages.
+ * @hints_dram_reserved_va_range: dram hint addresses reserved range.
+ * @hints_host_reserved_va_range: host hint addresses reserved range.
+ * @hints_host_hpage_reserved_va_range: host huge page hint addresses reserved
+ *                                      range.
  * @sram_base_address: SRAM physical start address.
  * @sram_end_address: SRAM physical end address.
  * @sram_user_base_address - SRAM physical start address for user access.
@@ -412,6 +443,10 @@
  *                    to the device's MMU.
  * @cb_va_end_addr: virtual end address of command buffers which are mapped to
  *                  the device's MMU.
+ * @dram_hints_align_mask: dram va hint addresses alignment mask which is used
+ *                  for hints validity check.
+ * device_dma_offset_for_host_access: the offset to add to host DMA addresses
+ *                                    to enable the device to access them.
  * @mmu_pgt_size: MMU page tables total size.
  * @mmu_pte_size: PTE size in MMU page tables.
  * @mmu_hop_table_size: MMU hop table size.
@@ -459,6 +494,8 @@
  *                                       reserved for the user
  * @first_available_cq: first available CQ for the user.
  * @user_interrupt_count: number of user interrupts.
+ * @server_type: Server type that the ASIC is currently installed in.
+ *               The value is according to enum hl_server_type in uapi file.
  * @tpc_enabled_mask: which TPCs are enabled.
  * @completion_queues_count: number of completion queues.
  * @fw_security_enabled: true if security measures are enabled in firmware,
@@ -470,6 +507,7 @@
  * @dram_supports_virtual_memory: is there an MMU towards the DRAM
  * @hard_reset_done_by_fw: true if firmware is handling hard reset flow
  * @num_functional_hbms: number of functional HBMs in each DCORE.
+ * @hints_range_reservation: device support hint addresses range reservation.
  * @iatu_done_by_fw: true if iATU configuration is being done by FW.
  * @dynamic_fw_load: is dynamic FW load is supported.
  * @gic_interrupts_enable: true if FW is not blocking GIC controller,
@@ -483,6 +521,9 @@
 	struct hl_mmu_properties	dmmu;
 	struct hl_mmu_properties	pmmu;
 	struct hl_mmu_properties	pmmu_huge;
+	struct hl_hints_range		hints_dram_reserved_va_range;
+	struct hl_hints_range		hints_host_reserved_va_range;
+	struct hl_hints_range		hints_host_hpage_reserved_va_range;
 	u64				sram_base_address;
 	u64				sram_end_address;
 	u64				sram_user_base_address;
@@ -500,6 +541,8 @@
 	u64				mmu_dram_default_page_addr;
 	u64				cb_va_start_addr;
 	u64				cb_va_end_addr;
+	u64				dram_hints_align_mask;
+	u64				device_dma_offset_for_host_access;
 	u32				mmu_pgt_size;
 	u32				mmu_pte_size;
 	u32				mmu_hop_table_size;
@@ -534,6 +577,7 @@
 	u16				first_available_user_msix_interrupt;
 	u16				first_available_cq[HL_MAX_DCORES];
 	u16				user_interrupt_count;
+	u16				server_type;
 	u8				tpc_enabled_mask;
 	u8				completion_queues_count;
 	u8				fw_security_enabled;
@@ -542,6 +586,7 @@
 	u8				dram_supports_virtual_memory;
 	u8				hard_reset_done_by_fw;
 	u8				num_functional_hbms;
+	u8				hints_range_reservation;
 	u8				iatu_done_by_fw;
 	u8				dynamic_fw_load;
 	u8				gic_interrupts_enable;
@@ -552,40 +597,45 @@
  * @completion: fence is implemented using completion
  * @refcount: refcount for this fence
  * @cs_sequence: sequence of the corresponding command submission
+ * @stream_master_qid_map: streams masters QID bitmap to represent all streams
+ *                         masters QIDs that multi cs is waiting on
  * @error: mark this fence with error
  * @timestamp: timestamp upon completion
- *
  */
 struct hl_fence {
 	struct completion	completion;
 	struct kref		refcount;
 	u64			cs_sequence;
+	u32			stream_master_qid_map;
 	int			error;
 	ktime_t			timestamp;
 };
 
 /**
  * struct hl_cs_compl - command submission completion object.
- * @sob_reset_work: workqueue object to run SOB reset flow.
  * @base_fence: hl fence object.
  * @lock: spinlock to protect fence.
  * @hdev: habanalabs device structure.
  * @hw_sob: the H/W SOB used in this signal/wait CS.
+ * @encaps_sig_hdl: encaps signals hanlder.
  * @cs_seq: command submission sequence number.
  * @type: type of the CS - signal/wait.
  * @sob_val: the SOB value that is used in this signal/wait CS.
  * @sob_group: the SOB group that is used in this collective wait CS.
+ * @encaps_signals: indication whether it's a completion object of cs with
+ * encaps signals or not.
  */
 struct hl_cs_compl {
-	struct work_struct	sob_reset_work;
 	struct hl_fence		base_fence;
 	spinlock_t		lock;
 	struct hl_device	*hdev;
 	struct hl_hw_sob	*hw_sob;
+	struct hl_cs_encaps_sig_handle *encaps_sig_hdl;
 	u64			cs_seq;
 	enum hl_cs_type		type;
 	u16			sob_val;
 	u16			sob_group;
+	bool			encaps_signals;
 };
 
 /*
@@ -698,6 +748,17 @@
 };
 
 /**
+ * struct hl_encaps_signals_mgr - describes sync stream encapsulated signals
+ * handlers manager
+ * @lock: protects handles.
+ * @handles: an idr to hold all encapsulated signals handles.
+ */
+struct hl_encaps_signals_mgr {
+	spinlock_t		lock;
+	struct idr		handles;
+};
+
+/**
  * struct hl_hw_queue - describes a H/W transport queue.
  * @shadow_queue: pointer to a shadow queue that holds pointers to jobs.
  * @sync_stream_prop: sync stream queue properties
@@ -875,7 +936,7 @@
 	u64 region_base;
 	u64 region_size;
 	u64 bar_size;
-	u32 offset_in_bar;
+	u64 offset_in_bar;
 	u8 bar_id;
 	u8 used;
 };
@@ -996,7 +1057,7 @@
  *                hw_fini and before CS rollback.
  * @suspend: handles IP specific H/W or SW changes for suspend.
  * @resume: handles IP specific H/W or SW changes for resume.
- * @cb_mmap: maps a CB.
+ * @mmap: maps a memory.
  * @ring_doorbell: increment PI on a given QMAN.
  * @pqe_write: Write the PQ entry to the PQ. This is ASIC-specific
  *             function because the PQs are located in different memory areas
@@ -1101,6 +1162,10 @@
  *                         generic f/w compatible PLL Indexes
  * @init_firmware_loader: initialize data for FW loader.
  * @init_cpu_scrambler_dram: Enable CPU specific DRAM scrambling
+ * @state_dump_init: initialize constants required for state dump
+ * @get_sob_addr: get SOB base address offset.
+ * @set_pci_memory_regions: setting properties of PCI memory regions
+ * @get_stream_master_qid_arr: get pointer to stream masters QID array
  */
 struct hl_asic_funcs {
 	int (*early_init)(struct hl_device *hdev);
@@ -1110,11 +1175,11 @@
 	int (*sw_init)(struct hl_device *hdev);
 	int (*sw_fini)(struct hl_device *hdev);
 	int (*hw_init)(struct hl_device *hdev);
-	void (*hw_fini)(struct hl_device *hdev, bool hard_reset);
-	void (*halt_engines)(struct hl_device *hdev, bool hard_reset);
+	void (*hw_fini)(struct hl_device *hdev, bool hard_reset, bool fw_reset);
+	void (*halt_engines)(struct hl_device *hdev, bool hard_reset, bool fw_reset);
 	int (*suspend)(struct hl_device *hdev);
 	int (*resume)(struct hl_device *hdev);
-	int (*cb_mmap)(struct hl_device *hdev, struct vm_area_struct *vma,
+	int (*mmap)(struct hl_device *hdev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size);
 	void (*ring_doorbell)(struct hl_device *hdev, u32 hw_queue_id, u32 pi);
 	void (*pqe_write)(struct hl_device *hdev, __le64 *pqe,
@@ -1210,10 +1275,11 @@
 	void (*reset_sob_group)(struct hl_device *hdev, u16 sob_group);
 	void (*set_dma_mask_from_fw)(struct hl_device *hdev);
 	u64 (*get_device_time)(struct hl_device *hdev);
-	void (*collective_wait_init_cs)(struct hl_cs *cs);
+	int (*collective_wait_init_cs)(struct hl_cs *cs);
 	int (*collective_wait_create_jobs)(struct hl_device *hdev,
-			struct hl_ctx *ctx, struct hl_cs *cs, u32 wait_queue_id,
-			u32 collective_engine_id);
+			struct hl_ctx *ctx, struct hl_cs *cs,
+			u32 wait_queue_id, u32 collective_engine_id,
+			u32 encaps_signal_offset);
 	u64 (*scramble_addr)(struct hl_device *hdev, u64 addr);
 	u64 (*descramble_addr)(struct hl_device *hdev, u64 addr);
 	void (*ack_protection_bits_errors)(struct hl_device *hdev);
@@ -1226,6 +1292,10 @@
 	int (*map_pll_idx_to_fw_idx)(u32 pll_idx);
 	void (*init_firmware_loader)(struct hl_device *hdev);
 	void (*init_cpu_scrambler_dram)(struct hl_device *hdev);
+	void (*state_dump_init)(struct hl_device *hdev);
+	u32 (*get_sob_addr)(struct hl_device *hdev, u32 sob_id);
+	void (*set_pci_memory_regions)(struct hl_device *hdev);
+	u32* (*get_stream_master_qid_arr)(void);
 };
 
 
@@ -1283,20 +1353,6 @@
 };
 
 /**
- * struct hl_pending_cb - pending command buffer structure
- * @cb_node: cb node in pending cb list
- * @cb: command buffer to send in next submission
- * @cb_size: command buffer size
- * @hw_queue_id: destination queue id
- */
-struct hl_pending_cb {
-	struct list_head	cb_node;
-	struct hl_cb		*cb;
-	u32			cb_size;
-	u32			hw_queue_id;
-};
-
-/**
  * struct hl_ctx - user/kernel context.
  * @mem_hash: holds mapping from virtual address to virtual memory area
  *		descriptor (hl_vm_phys_pg_list or hl_userptr).
@@ -1312,28 +1368,21 @@
  *            MMU hash or walking the PGT requires talking this lock.
  * @hw_block_list_lock: protects the HW block memory list.
  * @debugfs_list: node in debugfs list of contexts.
- * pending_cb_list: list of pending command buffers waiting to be sent upon
- *                  next user command submission context.
  * @hw_block_mem_list: list of HW block virtual mapped addresses.
  * @cs_counters: context command submission counters.
  * @cb_va_pool: device VA pool for command buffers which are mapped to the
  *              device's MMU.
+ * @sig_mgr: encaps signals handle manager.
  * @cs_sequence: sequence number for CS. Value is assigned to a CS and passed
  *			to user so user could inquire about CS. It is used as
  *			index to cs_pending array.
  * @dram_default_hops: array that holds all hops addresses needed for default
  *                     DRAM mapping.
- * @pending_cb_lock: spinlock to protect pending cb list
  * @cs_lock: spinlock to protect cs_sequence.
  * @dram_phys_mem: amount of used physical DRAM memory by this context.
  * @thread_ctx_switch_token: token to prevent multiple threads of the same
  *				context	from running the context switch phase.
  *				Only a single thread should run it.
- * @thread_pending_cb_token: token to prevent multiple threads from processing
- *				the pending CB list. Only a single thread should
- *				process the list since it is protected by a
- *				spinlock and we don't want to halt the entire
- *				command submission sequence.
  * @thread_ctx_switch_wait_token: token to prevent the threads that didn't run
  *				the context switch phase from moving to their
  *				execution phase before the context switch phase
@@ -1353,17 +1402,15 @@
 	struct mutex			mmu_lock;
 	struct mutex			hw_block_list_lock;
 	struct list_head		debugfs_list;
-	struct list_head		pending_cb_list;
 	struct list_head		hw_block_mem_list;
 	struct hl_cs_counters_atomic	cs_counters;
 	struct gen_pool			*cb_va_pool;
+	struct hl_encaps_signals_mgr	sig_mgr;
 	u64				cs_sequence;
 	u64				*dram_default_hops;
-	spinlock_t			pending_cb_lock;
 	spinlock_t			cs_lock;
 	atomic64_t			dram_phys_mem;
 	atomic_t			thread_ctx_switch_token;
-	atomic_t			thread_pending_cb_token;
 	u32				thread_ctx_switch_wait_token;
 	u32				asid;
 	u32				handle;
@@ -1394,20 +1441,22 @@
  * @sgt: pointer to the scatter-gather table that holds the pages.
  * @dir: for DMA unmapping, the direction must be supplied, so save it.
  * @debugfs_list: node in debugfs list of command submissions.
+ * @pid: the pid of the user process owning the memory
  * @addr: user-space virtual address of the start of the memory area.
  * @size: size of the memory area to pin & map.
  * @dma_mapped: true if the SG was mapped to DMA addresses, false otherwise.
  */
 struct hl_userptr {
-	enum vm_type_t		vm_type; /* must be first */
+	enum vm_type		vm_type; /* must be first */
 	struct list_head	job_node;
 	struct page		**pages;
 	unsigned int		npages;
 	struct sg_table		*sgt;
 	enum dma_data_direction dir;
 	struct list_head	debugfs_list;
+	pid_t			pid;
 	u64			addr;
-	u32			size;
+	u64			size;
 	u8			dma_mapped;
 };
 
@@ -1426,12 +1475,14 @@
  * @mirror_node : node in device mirror list of command submissions.
  * @staged_cs_node: node in the staged cs list.
  * @debugfs_list: node in debugfs list of command submissions.
+ * @encaps_sig_hdl: holds the encaps signals handle.
  * @sequence: the sequence number of this CS.
  * @staged_sequence: the sequence of the staged submission this CS is part of,
  *                   relevant only if staged_cs is set.
  * @timeout_jiffies: cs timeout in jiffies.
  * @submission_time_jiffies: submission time of the cs
  * @type: CS_TYPE_*.
+ * @encaps_sig_hdl_id: encaps signals handle id, set for the first staged cs.
  * @submitted: true if CS was submitted to H/W.
  * @completed: true if CS was completed by device.
  * @timedout : true if CS was timedout.
@@ -1445,6 +1496,7 @@
  * @staged_cs: true if this CS is part of a staged submission.
  * @skip_reset_on_timeout: true if we shall not reset the device in case
  *                         timeout occurs (debug scenario).
+ * @encaps_signals: true if this CS has encaps reserved signals.
  */
 struct hl_cs {
 	u16			*jobs_in_queue_cnt;
@@ -1459,11 +1511,13 @@
 	struct list_head	mirror_node;
 	struct list_head	staged_cs_node;
 	struct list_head	debugfs_list;
+	struct hl_cs_encaps_sig_handle *encaps_sig_hdl;
 	u64			sequence;
 	u64			staged_sequence;
 	u64			timeout_jiffies;
 	u64			submission_time_jiffies;
 	enum hl_cs_type		type;
+	u32			encaps_sig_hdl_id;
 	u8			submitted;
 	u8			completed;
 	u8			timedout;
@@ -1474,6 +1528,7 @@
 	u8			staged_first;
 	u8			staged_cs;
 	u8			skip_reset_on_timeout;
+	u8			encaps_signals;
 };
 
 /**
@@ -1493,6 +1548,8 @@
  * @hw_queue_id: the id of the H/W queue this job is submitted to.
  * @user_cb_size: the actual size of the CB we got from the user.
  * @job_cb_size: the actual size of the CB that we put on the queue.
+ * @encaps_sig_wait_offset: encapsulated signals offset, which allow user
+ *                          to wait on part of the reserved signals.
  * @is_kernel_allocated_cb: true if the CB handle we got from the user holds a
  *                          handle to a kernel-allocated CB object, false
  *                          otherwise (SRAM/DRAM/host address).
@@ -1517,6 +1574,7 @@
 	u32			hw_queue_id;
 	u32			user_cb_size;
 	u32			job_cb_size;
+	u32			encaps_sig_wait_offset;
 	u8			is_kernel_allocated_cb;
 	u8			contains_dma_pkt;
 };
@@ -1613,7 +1671,7 @@
  * @created_from_userptr: is product of host virtual address.
  */
 struct hl_vm_phys_pg_pack {
-	enum vm_type_t		vm_type; /* must be first */
+	enum vm_type		vm_type; /* must be first */
 	u64			*pages;
 	u64			npages;
 	u64			total_size;
@@ -1759,9 +1817,13 @@
  * @ctx_mem_hash_list: list of available contexts with MMU mappings.
  * @ctx_mem_hash_spinlock: protects cb_list.
  * @blob_desc: descriptor of blob
+ * @state_dump: data of the system states in case of a bad cs.
+ * @state_dump_sem: protects state_dump.
  * @addr: next address to read/write from/to in read/write32.
  * @mmu_addr: next virtual address to translate to physical address in mmu_show.
+ * @userptr_lookup: the target user ptr to look up for on demand.
  * @mmu_asid: ASID to use while translating in mmu_show.
+ * @state_dump_head: index of the latest state dump
  * @i2c_bus: generic u8 debugfs file for bus value to use in i2c_data_read.
  * @i2c_addr: generic u8 debugfs file for address value to use in i2c_data_read.
  * @i2c_reg: generic u8 debugfs file for register value to use in i2c_data_read.
@@ -1783,14 +1845,149 @@
 	struct list_head		ctx_mem_hash_list;
 	spinlock_t			ctx_mem_hash_spinlock;
 	struct debugfs_blob_wrapper	blob_desc;
+	char				*state_dump[HL_STATE_DUMP_HIST_LEN];
+	struct rw_semaphore		state_dump_sem;
 	u64				addr;
 	u64				mmu_addr;
+	u64				userptr_lookup;
 	u32				mmu_asid;
+	u32				state_dump_head;
 	u8				i2c_bus;
 	u8				i2c_addr;
 	u8				i2c_reg;
 };
 
+/**
+ * struct hl_hw_obj_name_entry - single hw object name, member of
+ * hl_state_dump_specs
+ * @node: link to the containing hash table
+ * @name: hw object name
+ * @id: object identifier
+ */
+struct hl_hw_obj_name_entry {
+	struct hlist_node	node;
+	const char		*name;
+	u32			id;
+};
+
+enum hl_state_dump_specs_props {
+	SP_SYNC_OBJ_BASE_ADDR,
+	SP_NEXT_SYNC_OBJ_ADDR,
+	SP_SYNC_OBJ_AMOUNT,
+	SP_MON_OBJ_WR_ADDR_LOW,
+	SP_MON_OBJ_WR_ADDR_HIGH,
+	SP_MON_OBJ_WR_DATA,
+	SP_MON_OBJ_ARM_DATA,
+	SP_MON_OBJ_STATUS,
+	SP_MONITORS_AMOUNT,
+	SP_TPC0_CMDQ,
+	SP_TPC0_CFG_SO,
+	SP_NEXT_TPC,
+	SP_MME_CMDQ,
+	SP_MME_CFG_SO,
+	SP_NEXT_MME,
+	SP_DMA_CMDQ,
+	SP_DMA_CFG_SO,
+	SP_DMA_QUEUES_OFFSET,
+	SP_NUM_OF_MME_ENGINES,
+	SP_SUB_MME_ENG_NUM,
+	SP_NUM_OF_DMA_ENGINES,
+	SP_NUM_OF_TPC_ENGINES,
+	SP_ENGINE_NUM_OF_QUEUES,
+	SP_ENGINE_NUM_OF_STREAMS,
+	SP_ENGINE_NUM_OF_FENCES,
+	SP_FENCE0_CNT_OFFSET,
+	SP_FENCE0_RDATA_OFFSET,
+	SP_CP_STS_OFFSET,
+	SP_NUM_CORES,
+
+	SP_MAX
+};
+
+enum hl_sync_engine_type {
+	ENGINE_TPC,
+	ENGINE_DMA,
+	ENGINE_MME,
+};
+
+/**
+ * struct hl_mon_state_dump - represents a state dump of a single monitor
+ * @id: monitor id
+ * @wr_addr_low: address monitor will write to, low bits
+ * @wr_addr_high: address monitor will write to, high bits
+ * @wr_data: data monitor will write
+ * @arm_data: register value containing monitor configuration
+ * @status: monitor status
+ */
+struct hl_mon_state_dump {
+	u32		id;
+	u32		wr_addr_low;
+	u32		wr_addr_high;
+	u32		wr_data;
+	u32		arm_data;
+	u32		status;
+};
+
+/**
+ * struct hl_sync_to_engine_map_entry - sync object id to engine mapping entry
+ * @engine_type: type of the engine
+ * @engine_id: id of the engine
+ * @sync_id: id of the sync object
+ */
+struct hl_sync_to_engine_map_entry {
+	struct hlist_node		node;
+	enum hl_sync_engine_type	engine_type;
+	u32				engine_id;
+	u32				sync_id;
+};
+
+/**
+ * struct hl_sync_to_engine_map - maps sync object id to associated engine id
+ * @tb: hash table containing the mapping, each element is of type
+ *      struct hl_sync_to_engine_map_entry
+ */
+struct hl_sync_to_engine_map {
+	DECLARE_HASHTABLE(tb, SYNC_TO_ENGINE_HASH_TABLE_BITS);
+};
+
+/**
+ * struct hl_state_dump_specs_funcs - virtual functions used by the state dump
+ * @gen_sync_to_engine_map: generate a hash map from sync obj id to its engine
+ * @print_single_monitor: format monitor data as string
+ * @monitor_valid: return true if given monitor dump is valid
+ * @print_fences_single_engine: format fences data as string
+ */
+struct hl_state_dump_specs_funcs {
+	int (*gen_sync_to_engine_map)(struct hl_device *hdev,
+				struct hl_sync_to_engine_map *map);
+	int (*print_single_monitor)(char **buf, size_t *size, size_t *offset,
+				    struct hl_device *hdev,
+				    struct hl_mon_state_dump *mon);
+	int (*monitor_valid)(struct hl_mon_state_dump *mon);
+	int (*print_fences_single_engine)(struct hl_device *hdev,
+					u64 base_offset,
+					u64 status_base_offset,
+					enum hl_sync_engine_type engine_type,
+					u32 engine_id, char **buf,
+					size_t *size, size_t *offset);
+};
+
+/**
+ * struct hl_state_dump_specs - defines ASIC known hw objects names
+ * @so_id_to_str_tb: sync objects names index table
+ * @monitor_id_to_str_tb: monitors names index table
+ * @funcs: virtual functions used for state dump
+ * @sync_namager_names: readable names for sync manager if available (ex: N_E)
+ * @props: pointer to a per asic const props array required for state dump
+ */
+struct hl_state_dump_specs {
+	DECLARE_HASHTABLE(so_id_to_str_tb, OBJ_NAMES_HASH_TABLE_BITS);
+	DECLARE_HASHTABLE(monitor_id_to_str_tb, OBJ_NAMES_HASH_TABLE_BITS);
+	struct hl_state_dump_specs_funcs	funcs;
+	const char * const			*sync_namager_names;
+	s64					*props;
+};
+
 
 /*
  * DEVICES
@@ -1798,7 +1995,7 @@
 
 #define HL_STR_MAX	32
 
-#define HL_DEV_STS_MAX (HL_DEVICE_STATUS_NEEDS_RESET + 1)
+#define HL_DEV_STS_MAX (HL_DEVICE_STATUS_LAST + 1)
 
 /* Theoretical limit only. A single host can only contain up to 4 or 8 PCIe
  * x16 cards. In extreme cases, there are hosts that can accommodate 16 cards.
@@ -1946,11 +2143,13 @@
  * @wq: work queue for device reset procedure.
  * @reset_work: reset work to be done.
  * @hdev: habanalabs device structure.
+ * @fw_reset: whether f/w will do the reset without us sending them a message to do it.
  */
 struct hl_device_reset_work {
 	struct workqueue_struct		*wq;
 	struct delayed_work		reset_work;
 	struct hl_device		*hdev;
+	bool				fw_reset;
 };
 
 /**
@@ -2065,6 +2264,58 @@
 };
 
 /**
+ * number of user contexts allowed to call wait_for_multi_cs ioctl in
+ * parallel
+ */
+#define MULTI_CS_MAX_USER_CTX	2
+
+/**
+ * struct multi_cs_completion - multi CS wait completion.
+ * @completion: completion of any of the CS in the list
+ * @lock: spinlock for the completion structure
+ * @timestamp: timestamp for the multi-CS completion
+ * @stream_master_qid_map: bitmap of all stream masters on which the multi-CS
+ *                        is waiting
+ * @used: 1 if in use, otherwise 0
+ */
+struct multi_cs_completion {
+	struct completion	completion;
+	spinlock_t		lock;
+	s64			timestamp;
+	u32			stream_master_qid_map;
+	u8			used;
+};
+
+/**
+ * struct multi_cs_data - internal data for multi CS call
+ * @ctx: pointer to the context structure
+ * @fence_arr: array of fences of all CSs
+ * @seq_arr: array of CS sequence numbers
+ * @timeout_us: timeout in usec for waiting for CS to complete
+ * @timestamp: timestamp of first completed CS
+ * @wait_status: wait for CS status
+ * @completion_bitmap: bitmap of completed CSs (1- completed, otherwise 0)
+ * @stream_master_qid_map: bitmap of all stream master QIDs on which the
+ *                         multi-CS is waiting
+ * @arr_len: fence_arr and seq_arr array length
+ * @gone_cs: indication of gone CS (1- there was gone CS, otherwise 0)
+ * @update_ts: update timestamp. 1- update the timestamp, otherwise 0.
+ */
+struct multi_cs_data {
+	struct hl_ctx	*ctx;
+	struct hl_fence	**fence_arr;
+	u64		*seq_arr;
+	s64		timeout_us;
+	s64		timestamp;
+	long		wait_status;
+	u32		completion_bitmap;
+	u32		stream_master_qid_map;
+	u8		arr_len;
+	u8		gone_cs;
+	u8		update_ts;
+};
+
+/**
  * struct hl_device - habanalabs device structure.
  * @pdev: pointer to PCI device, can be NULL in case of simulator device.
  * @pcie_bar_phys: array of available PCIe bars physical addresses.
@@ -2129,6 +2380,8 @@
  * @mmu_func: device-related MMU functions.
  * @fw_loader: FW loader manager.
  * @pci_mem_region: array of memory regions in the PCI
+ * @state_dump_specs: constants and dictionaries needed to dump system state.
+ * @multi_cs_completion: array of multi-CS completion.
  * @dram_used_mem: current DRAM memory consumption.
  * @timeout_jiffies: device CS timeout value.
  * @max_power: the max power of the device, as configured by the sysadmin. This
@@ -2205,6 +2458,7 @@
  *                        halted. We can't halt it again because the COMMS
  *                        protocol will throw an error. Relevant only for
  *                        cases where Linux was not loaded to device CPU
+ * @supports_wait_for_multi_cs: true if wait for multi CS is supported
  */
 struct hl_device {
 	struct pci_dev			*pdev;
@@ -2273,6 +2527,11 @@
 
 	struct pci_mem_region		pci_mem_region[PCI_REGION_NUMBER];
 
+	struct hl_state_dump_specs	state_dump_specs;
+
+	struct multi_cs_completion	multi_cs_completion[
+							MULTI_CS_MAX_USER_CTX];
+	u32				*stream_master_qid_arr;
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;
 	u64				max_power;
@@ -2322,6 +2581,8 @@
 	u8				curr_reset_cause;
 	u8				skip_reset_on_timeout;
 	u8				device_cpu_is_halted;
+	u8				supports_wait_for_multi_cs;
+	u8				stream_master_qid_arr_size;
 
 	/* Parameters for bring-up */
 	u64				nic_ports_mask;
@@ -2343,6 +2604,29 @@
 };
 
 
+/**
+ * struct hl_cs_encaps_sig_handle - encapsulated signals handle structure
+ * @refcount: refcount used to protect removing this id when several
+ *            wait cs are used to wait of the reserved encaps signals.
+ * @hdev: pointer to habanalabs device structure.
+ * @hw_sob: pointer to  H/W SOB used in the reservation.
+ * @cs_seq: staged cs sequence which contains encapsulated signals
+ * @id: idr handler id to be used to fetch the handler info
+ * @q_idx: stream queue index
+ * @pre_sob_val: current SOB value before reservation
+ * @count: signals number
+ */
+struct hl_cs_encaps_sig_handle {
+	struct kref refcount;
+	struct hl_device *hdev;
+	struct hl_hw_sob *hw_sob;
+	u64  cs_seq;
+	u32  id;
+	u32  q_idx;
+	u32  pre_sob_val;
+	u32  count;
+};
+
 /*
  * IOCTLs
  */
@@ -2373,6 +2657,23 @@
  */
 
 /**
+ * hl_get_sg_info() - get number of pages and the DMA address from SG list.
+ * @sg: the SG list.
+ * @dma_addr: pointer to DMA address to return.
+ *
+ * Calculate the number of consecutive pages described by the SG list. Take the
+ * offset of the address in the first page, add to it the length and round it up
+ * to the number of needed pages.
+ */
+static inline u32 hl_get_sg_info(struct scatterlist *sg, dma_addr_t *dma_addr)
+{
+	*dma_addr = sg_dma_address(sg);
+
+	return ((((*dma_addr) & (PAGE_SIZE - 1)) + sg_dma_len(sg)) +
+			(PAGE_SIZE - 1)) >> PAGE_SHIFT;
+}
+
+/**
  * hl_mem_area_inside_range() - Checks whether address+size are inside a range.
  * @address: The start address of the area we want to validate.
  * @size: The size in bytes of the area we want to validate.
@@ -2436,7 +2737,9 @@
 int hl_hw_queues_create(struct hl_device *hdev);
 void hl_hw_queues_destroy(struct hl_device *hdev);
 int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
-				u32 cb_size, u64 cb_ptr);
+		u32 cb_size, u64 cb_ptr);
+void hl_hw_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q,
+		u32 ctl, u32 len, u64 ptr);
 int hl_hw_queue_schedule_cs(struct hl_cs *cs);
 u32 hl_hw_queue_add_ptr(u32 ptr, u16 val);
 void hl_hw_queue_inc_ci_kernel(struct hl_device *hdev, u32 hw_queue_id);
@@ -2470,6 +2773,8 @@
 void hl_ctx_get(struct hl_device *hdev,	struct hl_ctx *ctx);
 int hl_ctx_put(struct hl_ctx *ctx);
 struct hl_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq);
+int hl_ctx_get_fences(struct hl_ctx *ctx, u64 *seq_arr,
+				struct hl_fence **fence, u32 arr_len);
 void hl_ctx_mgr_init(struct hl_ctx_mgr *mgr);
 void hl_ctx_mgr_fini(struct hl_device *hdev, struct hl_ctx_mgr *mgr);
 
@@ -2511,18 +2816,19 @@
 void hl_cb_va_pool_fini(struct hl_ctx *ctx);
 
 void hl_cs_rollback_all(struct hl_device *hdev);
-void hl_pending_cb_list_flush(struct hl_ctx *ctx);
 struct hl_cs_job *hl_cs_allocate_job(struct hl_device *hdev,
 		enum hl_queue_type queue_type, bool is_kernel_allocated_cb);
 void hl_sob_reset_error(struct kref *ref);
 int hl_gen_sob_mask(u16 sob_base, u8 sob_mask, u8 *mask);
 void hl_fence_put(struct hl_fence *fence);
+void hl_fences_put(struct hl_fence **fence, int len);
 void hl_fence_get(struct hl_fence *fence);
 void cs_get(struct hl_cs *cs);
 bool cs_needs_completion(struct hl_cs *cs);
 bool cs_needs_timeout(struct hl_cs *cs);
 bool is_staged_cs_last_exists(struct hl_device *hdev, struct hl_cs *cs);
 struct hl_cs *hl_staged_cs_find_first(struct hl_device *hdev, u64 cs_seq);
+void hl_multi_cs_completion_init(struct hl_device *hdev);
 
 void goya_set_asic_funcs(struct hl_device *hdev);
 void gaudi_set_asic_funcs(struct hl_device *hdev);
@@ -2650,9 +2956,25 @@
 			int sensor_index, u32 attr, long value);
 int hl_set_current(struct hl_device *hdev,
 			int sensor_index, u32 attr, long value);
+void hw_sob_get(struct hl_hw_sob *hw_sob);
+void hw_sob_put(struct hl_hw_sob *hw_sob);
+void hl_encaps_handle_do_release(struct kref *ref);
+void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev,
+			struct hl_cs *cs, struct hl_cs_job *job,
+			struct hl_cs_compl *cs_cmpl);
 void hl_release_pending_user_interrupts(struct hl_device *hdev);
 int hl_cs_signal_sob_wraparound_handler(struct hl_device *hdev, u32 q_idx,
-			struct hl_hw_sob **hw_sob, u32 count);
+			struct hl_hw_sob **hw_sob, u32 count, bool encaps_sig);
+
+int hl_state_dump(struct hl_device *hdev);
+const char *hl_state_dump_get_sync_name(struct hl_device *hdev, u32 sync_id);
+const char *hl_state_dump_get_monitor_name(struct hl_device *hdev,
+					struct hl_mon_state_dump *mon);
+void hl_state_dump_free_sync_to_engine_map(struct hl_sync_to_engine_map *map);
+__printf(4, 5) int hl_snprintf_resize(char **buf, size_t *size, size_t *offset,
+					const char *format, ...);
+char *hl_format_as_binary(char *buf, size_t buf_len, u32 n);
+const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type);
 
 #ifdef CONFIG_DEBUG_FS
 
@@ -2673,6 +2995,8 @@
 				struct hl_userptr *userptr);
 void hl_debugfs_add_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
 void hl_debugfs_remove_ctx_mem_hash(struct hl_device *hdev, struct hl_ctx *ctx);
+void hl_debugfs_set_state_dump(struct hl_device *hdev, char *data,
+					unsigned long length);
 
 #else
 
@@ -2746,6 +3070,11 @@
 {
 }
 
+static inline void hl_debugfs_set_state_dump(struct hl_device *hdev,
+					char *data, unsigned long length)
+{
+}
+
 #endif
 
 /* IOCTLs */
diff --git a/drivers/misc/habanalabs/common/habanalabs_drv.c b/drivers/misc/habanalabs/common/habanalabs_drv.c
index 4194cda2..a75e4fc 100644
--- a/drivers/misc/habanalabs/common/habanalabs_drv.c
+++ b/drivers/misc/habanalabs/common/habanalabs_drv.c
@@ -141,7 +141,7 @@
 	hl_cb_mgr_init(&hpriv->cb_mgr);
 	hl_ctx_mgr_init(&hpriv->ctx_mgr);
 
-	hpriv->taskpid = find_get_pid(current->pid);
+	hpriv->taskpid = get_task_pid(current, PIDTYPE_PID);
 
 	mutex_lock(&hdev->fpriv_list_lock);
 
@@ -194,7 +194,6 @@
 
 out_err:
 	mutex_unlock(&hdev->fpriv_list_lock);
-
 	hl_cb_mgr_fini(hpriv->hdev, &hpriv->cb_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
 	filp->private_data = NULL;
@@ -318,12 +317,16 @@
 		hdev->asic_prop.fw_security_enabled = false;
 
 	/* Assign status description string */
-	strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION],
-					"disabled", HL_STR_MAX);
+	strncpy(hdev->status[HL_DEVICE_STATUS_OPERATIONAL],
+					"operational", HL_STR_MAX);
 	strncpy(hdev->status[HL_DEVICE_STATUS_IN_RESET],
 					"in reset", HL_STR_MAX);
+	strncpy(hdev->status[HL_DEVICE_STATUS_MALFUNCTION],
+					"disabled", HL_STR_MAX);
 	strncpy(hdev->status[HL_DEVICE_STATUS_NEEDS_RESET],
 					"needs reset", HL_STR_MAX);
+	strncpy(hdev->status[HL_DEVICE_STATUS_IN_DEVICE_CREATION],
+					"in device creation", HL_STR_MAX);
 
 	hdev->major = hl_major;
 	hdev->reset_on_lockup = reset_on_lockup;
@@ -532,7 +535,7 @@
 		result = PCI_ERS_RESULT_NONE;
 	}
 
-	hdev->asic_funcs->halt_engines(hdev, true);
+	hdev->asic_funcs->halt_engines(hdev, true, false);
 
 	return result;
 }
diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index f4dda7b..86c3257 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -94,6 +94,8 @@
 
 	hw_ip.first_available_interrupt_id =
 			prop->first_available_user_msix_interrupt;
+	hw_ip.server_type = prop->server_type;
+
 	return copy_to_user(out, &hw_ip,
 		min((size_t) size, sizeof(hw_ip))) ? -EFAULT : 0;
 }
diff --git a/drivers/misc/habanalabs/common/hw_queue.c b/drivers/misc/habanalabs/common/hw_queue.c
index bcabfdb..76b7de8 100644
--- a/drivers/misc/habanalabs/common/hw_queue.c
+++ b/drivers/misc/habanalabs/common/hw_queue.c
@@ -65,7 +65,7 @@
 }
 
 /*
- * ext_and_hw_queue_submit_bd() - Submit a buffer descriptor to an external or a
+ * hl_hw_queue_submit_bd() - Submit a buffer descriptor to an external or a
  *                                H/W queue.
  * @hdev: pointer to habanalabs device structure
  * @q: pointer to habanalabs queue structure
@@ -80,8 +80,8 @@
  * This function must be called when the scheduler mutex is taken
  *
  */
-static void ext_and_hw_queue_submit_bd(struct hl_device *hdev,
-			struct hl_hw_queue *q, u32 ctl, u32 len, u64 ptr)
+void hl_hw_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q,
+		u32 ctl, u32 len, u64 ptr)
 {
 	struct hl_bd *bd;
 
@@ -222,8 +222,8 @@
  * @cb_size: size of CB
  * @cb_ptr: pointer to CB location
  *
- * This function sends a single CB, that must NOT generate a completion entry
- *
+ * This function sends a single CB, that must NOT generate a completion entry.
+ * Sending CPU messages can be done instead via 'hl_hw_queue_submit_bd()'
  */
 int hl_hw_queue_send_cb_no_cmpl(struct hl_device *hdev, u32 hw_queue_id,
 				u32 cb_size, u64 cb_ptr)
@@ -231,16 +231,7 @@
 	struct hl_hw_queue *q = &hdev->kernel_queues[hw_queue_id];
 	int rc = 0;
 
-	/*
-	 * The CPU queue is a synchronous queue with an effective depth of
-	 * a single entry (although it is allocated with room for multiple
-	 * entries). Therefore, there is a different lock, called
-	 * send_cpu_message_lock, that serializes accesses to the CPU queue.
-	 * As a result, we don't need to lock the access to the entire H/W
-	 * queues module when submitting a JOB to the CPU queue
-	 */
-	if (q->queue_type != QUEUE_TYPE_CPU)
-		hdev->asic_funcs->hw_queues_lock(hdev);
+	hdev->asic_funcs->hw_queues_lock(hdev);
 
 	if (hdev->disabled) {
 		rc = -EPERM;
@@ -258,11 +249,10 @@
 			goto out;
 	}
 
-	ext_and_hw_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
+	hl_hw_queue_submit_bd(hdev, q, 0, cb_size, cb_ptr);
 
 out:
-	if (q->queue_type != QUEUE_TYPE_CPU)
-		hdev->asic_funcs->hw_queues_unlock(hdev);
+	hdev->asic_funcs->hw_queues_unlock(hdev);
 
 	return rc;
 }
@@ -328,7 +318,7 @@
 	cq->pi = hl_cq_inc_ptr(cq->pi);
 
 submit_bd:
-	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+	hl_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
 }
 
 /*
@@ -407,7 +397,7 @@
 	else
 		ptr = (u64) (uintptr_t) job->user_cb;
 
-	ext_and_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
+	hl_hw_queue_submit_bd(hdev, q, ctl, len, ptr);
 }
 
 static int init_signal_cs(struct hl_device *hdev,
@@ -426,8 +416,9 @@
 	cs_cmpl->sob_val = prop->next_sob_val;
 
 	dev_dbg(hdev->dev,
-		"generate signal CB, sob_id: %d, sob val: 0x%x, q_idx: %d\n",
-		cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx);
+		"generate signal CB, sob_id: %d, sob val: %u, q_idx: %d, seq: %llu\n",
+		cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val, q_idx,
+		cs_cmpl->cs_seq);
 
 	/* we set an EB since we must make sure all oeprations are done
 	 * when sending the signal
@@ -435,17 +426,37 @@
 	hdev->asic_funcs->gen_signal_cb(hdev, job->patched_cb,
 				cs_cmpl->hw_sob->sob_id, 0, true);
 
-	rc = hl_cs_signal_sob_wraparound_handler(hdev, q_idx, &hw_sob, 1);
+	rc = hl_cs_signal_sob_wraparound_handler(hdev, q_idx, &hw_sob, 1,
+								false);
 
 	return rc;
 }
 
-static void init_wait_cs(struct hl_device *hdev, struct hl_cs *cs,
+void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev,
+			struct hl_cs *cs, struct hl_cs_job *job,
+			struct hl_cs_compl *cs_cmpl)
+{
+	struct hl_cs_encaps_sig_handle *handle = cs->encaps_sig_hdl;
+
+	cs_cmpl->hw_sob = handle->hw_sob;
+
+	/* Note that encaps_sig_wait_offset was validated earlier in the flow
+	 * for offset value which exceeds the max reserved signal count.
+	 * always decrement 1 of the offset since when the user
+	 * set offset 1 for example he mean to wait only for the first
+	 * signal only, which will be pre_sob_val, and if he set offset 2
+	 * then the value required is (pre_sob_val + 1) and so on...
+	 */
+	cs_cmpl->sob_val = handle->pre_sob_val +
+			(job->encaps_sig_wait_offset - 1);
+}
+
+static int init_wait_cs(struct hl_device *hdev, struct hl_cs *cs,
 		struct hl_cs_job *job, struct hl_cs_compl *cs_cmpl)
 {
-	struct hl_cs_compl *signal_cs_cmpl;
-	struct hl_sync_stream_properties *prop;
 	struct hl_gen_wait_properties wait_prop;
+	struct hl_sync_stream_properties *prop;
+	struct hl_cs_compl *signal_cs_cmpl;
 	u32 q_idx;
 
 	q_idx = job->hw_queue_id;
@@ -455,14 +466,51 @@
 					struct hl_cs_compl,
 					base_fence);
 
-	/* copy the SOB id and value of the signal CS */
-	cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
-	cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+	if (cs->encaps_signals) {
+		/* use the encaps signal handle stored earlier in the flow
+		 * and set the SOB information from the encaps
+		 * signals handle
+		 */
+		hl_hw_queue_encaps_sig_set_sob_info(hdev, cs, job, cs_cmpl);
+
+		dev_dbg(hdev->dev, "Wait for encaps signals handle, qidx(%u), CS sequence(%llu), sob val: 0x%x, offset: %u\n",
+				cs->encaps_sig_hdl->q_idx,
+				cs->encaps_sig_hdl->cs_seq,
+				cs_cmpl->sob_val,
+				job->encaps_sig_wait_offset);
+	} else {
+		/* Copy the SOB id and value of the signal CS */
+		cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
+		cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+	}
+
+	/* check again if the signal cs already completed.
+	 * if yes then don't send any wait cs since the hw_sob
+	 * could be in reset already. if signal is not completed
+	 * then get refcount to hw_sob to prevent resetting the sob
+	 * while wait cs is not submitted.
+	 * note that this check is protected by two locks,
+	 * hw queue lock and completion object lock,
+	 * and the same completion object lock also protects
+	 * the hw_sob reset handler function.
+	 * The hw_queue lock prevent out of sync of hw_sob
+	 * refcount value, changed by signal/wait flows.
+	 */
+	spin_lock(&signal_cs_cmpl->lock);
+
+	if (completion_done(&cs->signal_fence->completion)) {
+		spin_unlock(&signal_cs_cmpl->lock);
+		return -EINVAL;
+	}
+
+	kref_get(&cs_cmpl->hw_sob->kref);
+
+	spin_unlock(&signal_cs_cmpl->lock);
 
 	dev_dbg(hdev->dev,
-		"generate wait CB, sob_id: %d, sob_val: 0x%x, mon_id: %d, q_idx: %d\n",
+		"generate wait CB, sob_id: %d, sob_val: 0x%x, mon_id: %d, q_idx: %d, seq: %llu\n",
 		cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val,
-		prop->base_mon_id, q_idx);
+		prop->base_mon_id, q_idx, cs->sequence);
 
 	wait_prop.data = (void *) job->patched_cb;
 	wait_prop.sob_base = cs_cmpl->hw_sob->sob_id;
@@ -471,17 +519,14 @@
 	wait_prop.mon_id = prop->base_mon_id;
 	wait_prop.q_idx = q_idx;
 	wait_prop.size = 0;
+
 	hdev->asic_funcs->gen_wait_cb(hdev, &wait_prop);
 
-	kref_get(&cs_cmpl->hw_sob->kref);
-	/*
-	 * Must put the signal fence after the SOB refcnt increment so
-	 * the SOB refcnt won't turn 0 and reset the SOB before the
-	 * wait CS was submitted.
-	 */
 	mb();
 	hl_fence_put(cs->signal_fence);
 	cs->signal_fence = NULL;
+
+	return 0;
 }
 
 /*
@@ -506,7 +551,60 @@
 	if (cs->type & CS_TYPE_SIGNAL)
 		rc = init_signal_cs(hdev, job, cs_cmpl);
 	else if (cs->type & CS_TYPE_WAIT)
-		init_wait_cs(hdev, cs, job, cs_cmpl);
+		rc = init_wait_cs(hdev, cs, job, cs_cmpl);
+
+	return rc;
+}
+
+static int encaps_sig_first_staged_cs_handler
+			(struct hl_device *hdev, struct hl_cs *cs)
+{
+	struct hl_cs_compl *cs_cmpl =
+			container_of(cs->fence,
+					struct hl_cs_compl, base_fence);
+	struct hl_cs_encaps_sig_handle *encaps_sig_hdl;
+	struct hl_encaps_signals_mgr *mgr;
+	int rc = 0;
+
+	mgr = &hdev->compute_ctx->sig_mgr;
+
+	spin_lock(&mgr->lock);
+	encaps_sig_hdl = idr_find(&mgr->handles, cs->encaps_sig_hdl_id);
+	if (encaps_sig_hdl) {
+		/*
+		 * Set handler CS sequence,
+		 * the CS which contains the encapsulated signals.
+		 */
+		encaps_sig_hdl->cs_seq = cs->sequence;
+		/* store the handle and set encaps signal indication,
+		 * to be used later in cs_do_release to put the last
+		 * reference to encaps signals handlers.
+		 */
+		cs_cmpl->encaps_signals = true;
+		cs_cmpl->encaps_sig_hdl = encaps_sig_hdl;
+
+		/* set hw_sob pointer in completion object
+		 * since it's used in cs_do_release flow to put
+		 * refcount to sob
+		 */
+		cs_cmpl->hw_sob = encaps_sig_hdl->hw_sob;
+		cs_cmpl->sob_val = encaps_sig_hdl->pre_sob_val +
+						encaps_sig_hdl->count;
+
+		dev_dbg(hdev->dev, "CS seq (%llu) added to encaps signal handler id (%u), count(%u), qidx(%u), sob(%u), val(%u)\n",
+				cs->sequence, encaps_sig_hdl->id,
+				encaps_sig_hdl->count,
+				encaps_sig_hdl->q_idx,
+				cs_cmpl->hw_sob->sob_id,
+				cs_cmpl->sob_val);
+
+	} else {
+		dev_err(hdev->dev, "encaps handle id(%u) wasn't found!\n",
+				cs->encaps_sig_hdl_id);
+		rc = -EINVAL;
+	}
+
+	spin_unlock(&mgr->lock);
 
 	return rc;
 }
@@ -581,14 +679,21 @@
 
 	if ((cs->type == CS_TYPE_SIGNAL) || (cs->type == CS_TYPE_WAIT)) {
 		rc = init_signal_wait_cs(cs);
-		if (rc) {
-			dev_err(hdev->dev, "Failed to submit signal cs\n");
+		if (rc)
 			goto unroll_cq_resv;
-		}
-	} else if (cs->type == CS_TYPE_COLLECTIVE_WAIT)
-		hdev->asic_funcs->collective_wait_init_cs(cs);
+	} else if (cs->type == CS_TYPE_COLLECTIVE_WAIT) {
+		rc = hdev->asic_funcs->collective_wait_init_cs(cs);
+		if (rc)
+			goto unroll_cq_resv;
+	}
 
 
+	if (cs->encaps_signals && cs->staged_first) {
+		rc = encaps_sig_first_staged_cs_handler(hdev, cs);
+		if (rc)
+			goto unroll_cq_resv;
+	}
+
 	spin_lock(&hdev->cs_mirror_lock);
 
 	/* Verify staged CS exists and add to the staged list */
@@ -613,6 +718,11 @@
 		}
 
 		list_add_tail(&cs->staged_cs_node, &staged_cs->staged_cs_node);
+
+		/* update stream map of the first CS */
+		if (hdev->supports_wait_for_multi_cs)
+			staged_cs->fence->stream_master_qid_map |=
+					cs->fence->stream_master_qid_map;
 	}
 
 	list_add_tail(&cs->mirror_node, &hdev->cs_mirror_list);
@@ -834,6 +944,8 @@
 		hw_sob = &sync_stream_prop->hw_sob[sob];
 		hw_sob->hdev = hdev;
 		hw_sob->sob_id = sync_stream_prop->base_sob_id + sob;
+		hw_sob->sob_addr =
+			hdev->asic_funcs->get_sob_addr(hdev, hw_sob->sob_id);
 		hw_sob->q_idx = q_idx;
 		kref_init(&hw_sob->kref);
 	}
diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c
index af339ce..3398693 100644
--- a/drivers/misc/habanalabs/common/memory.c
+++ b/drivers/misc/habanalabs/common/memory.c
@@ -124,7 +124,7 @@
 
 	spin_lock(&vm->idr_lock);
 	handle = idr_alloc(&vm->phys_pg_pack_handles, phys_pg_pack, 1, 0,
-				GFP_KERNEL);
+				GFP_ATOMIC);
 	spin_unlock(&vm->idr_lock);
 
 	if (handle < 0) {
@@ -529,6 +529,33 @@
 }
 
 /**
+ * is_hint_crossing_range() - check if hint address crossing specified reserved
+ * range.
+ */
+static inline bool is_hint_crossing_range(enum hl_va_range_type range_type,
+		u64 start_addr, u32 size, struct asic_fixed_properties *prop) {
+	bool range_cross;
+
+	if (range_type == HL_VA_RANGE_TYPE_DRAM)
+		range_cross =
+			hl_mem_area_crosses_range(start_addr, size,
+			prop->hints_dram_reserved_va_range.start_addr,
+			prop->hints_dram_reserved_va_range.end_addr);
+	else if (range_type == HL_VA_RANGE_TYPE_HOST)
+		range_cross =
+			hl_mem_area_crosses_range(start_addr,	size,
+			prop->hints_host_reserved_va_range.start_addr,
+			prop->hints_host_reserved_va_range.end_addr);
+	else
+		range_cross =
+			hl_mem_area_crosses_range(start_addr, size,
+			prop->hints_host_hpage_reserved_va_range.start_addr,
+			prop->hints_host_hpage_reserved_va_range.end_addr);
+
+	return range_cross;
+}
+
+/**
  * get_va_block() - get a virtual block for the given size and alignment.
  *
  * @hdev: pointer to the habanalabs device structure.
@@ -536,6 +563,8 @@
  * @size: requested block size.
  * @hint_addr: hint for requested address by the user.
  * @va_block_align: required alignment of the virtual block start address.
+ * @range_type: va range type (host, dram)
+ * @flags: additional memory flags, currently only uses HL_MEM_FORCE_HINT
  *
  * This function does the following:
  * - Iterate on the virtual block list to find a suitable virtual block for the
@@ -545,13 +574,19 @@
  */
 static u64 get_va_block(struct hl_device *hdev,
 				struct hl_va_range *va_range,
-				u64 size, u64 hint_addr, u32 va_block_align)
+				u64 size, u64 hint_addr, u32 va_block_align,
+				enum hl_va_range_type range_type,
+				u32 flags)
 {
 	struct hl_vm_va_block *va_block, *new_va_block = NULL;
+	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	u64 tmp_hint_addr, valid_start, valid_size, prev_start, prev_end,
-		align_mask, reserved_valid_start = 0, reserved_valid_size = 0;
+		align_mask, reserved_valid_start = 0, reserved_valid_size = 0,
+		dram_hint_mask = prop->dram_hints_align_mask;
 	bool add_prev = false;
 	bool is_align_pow_2  = is_power_of_2(va_range->page_size);
+	bool is_hint_dram_addr = hl_is_dram_va(hdev, hint_addr);
+	bool force_hint = flags & HL_MEM_FORCE_HINT;
 
 	if (is_align_pow_2)
 		align_mask = ~((u64)va_block_align - 1);
@@ -564,12 +599,20 @@
 		size = DIV_ROUND_UP_ULL(size, va_range->page_size) *
 							va_range->page_size;
 
-	tmp_hint_addr = hint_addr;
+	tmp_hint_addr = hint_addr & ~dram_hint_mask;
 
 	/* Check if we need to ignore hint address */
 	if ((is_align_pow_2 && (hint_addr & (va_block_align - 1))) ||
-			(!is_align_pow_2 &&
-				do_div(tmp_hint_addr, va_range->page_size))) {
+		(!is_align_pow_2 && is_hint_dram_addr &&
+			do_div(tmp_hint_addr, va_range->page_size))) {
+
+		if (force_hint) {
+			/* Hint must be respected, so here we just fail */
+			dev_err(hdev->dev,
+				"Hint address 0x%llx is not page aligned - cannot be respected\n",
+				hint_addr);
+			return 0;
+		}
 
 		dev_dbg(hdev->dev,
 			"Hint address 0x%llx will be ignored because it is not aligned\n",
@@ -596,6 +639,16 @@
 		if (valid_size < size)
 			continue;
 
+		/*
+		 * In case hint address is 0, and arc_hints_range_reservation
+		 * property enabled, then avoid allocating va blocks from the
+		 * range reserved for hint addresses
+		 */
+		if (prop->hints_range_reservation && !hint_addr)
+			if (is_hint_crossing_range(range_type, valid_start,
+					size, prop))
+				continue;
+
 		/* Pick the minimal length block which has the required size */
 		if (!new_va_block || (valid_size < reserved_valid_size)) {
 			new_va_block = va_block;
@@ -618,6 +671,17 @@
 		goto out;
 	}
 
+	if (force_hint && reserved_valid_start != hint_addr) {
+		/* Hint address must be respected. If we are here - this means
+		 * we could not respect it.
+		 */
+		dev_err(hdev->dev,
+			"Hint address 0x%llx could not be respected\n",
+			hint_addr);
+		reserved_valid_start = 0;
+		goto out;
+	}
+
 	/*
 	 * Check if there is some leftover range due to reserving the new
 	 * va block, then return it to the main virtual addresses list.
@@ -670,7 +734,8 @@
 		enum hl_va_range_type type, u32 size, u32 alignment)
 {
 	return get_va_block(hdev, ctx->va_range[type], size, 0,
-			max(alignment, ctx->va_range[type]->page_size));
+			max(alignment, ctx->va_range[type]->page_size),
+			type, 0);
 }
 
 /**
@@ -732,28 +797,15 @@
 }
 
 /**
- * get_sg_info() - get number of pages and the DMA address from SG list.
- * @sg: the SG list.
- * @dma_addr: pointer to DMA address to return.
- *
- * Calculate the number of consecutive pages described by the SG list. Take the
- * offset of the address in the first page, add to it the length and round it up
- * to the number of needed pages.
- */
-static u32 get_sg_info(struct scatterlist *sg, dma_addr_t *dma_addr)
-{
-	*dma_addr = sg_dma_address(sg);
-
-	return ((((*dma_addr) & (PAGE_SIZE - 1)) + sg_dma_len(sg)) +
-			(PAGE_SIZE - 1)) >> PAGE_SHIFT;
-}
-
-/**
  * init_phys_pg_pack_from_userptr() - initialize physical page pack from host
  *                                    memory
  * @ctx: pointer to the context structure.
  * @userptr: userptr to initialize from.
  * @pphys_pg_pack: result pointer.
+ * @force_regular_page: tell the function to ignore huge page optimization,
+ *                      even if possible. Needed for cases where the device VA
+ *                      is allocated before we know the composition of the
+ *                      physical pages
  *
  * This function does the following:
  * - Pin the physical pages related to the given virtual block.
@@ -762,17 +814,18 @@
  */
 static int init_phys_pg_pack_from_userptr(struct hl_ctx *ctx,
 				struct hl_userptr *userptr,
-				struct hl_vm_phys_pg_pack **pphys_pg_pack)
+				struct hl_vm_phys_pg_pack **pphys_pg_pack,
+				bool force_regular_page)
 {
-	struct hl_vm_phys_pg_pack *phys_pg_pack;
-	struct scatterlist *sg;
-	dma_addr_t dma_addr;
-	u64 page_mask, total_npages;
 	u32 npages, page_size = PAGE_SIZE,
 		huge_page_size = ctx->hdev->asic_prop.pmmu_huge.page_size;
-	bool first = true, is_huge_page_opt = true;
-	int rc, i, j;
 	u32 pgs_in_huge_page = huge_page_size >> __ffs(page_size);
+	struct hl_vm_phys_pg_pack *phys_pg_pack;
+	bool first = true, is_huge_page_opt;
+	u64 page_mask, total_npages;
+	struct scatterlist *sg;
+	dma_addr_t dma_addr;
+	int rc, i, j;
 
 	phys_pg_pack = kzalloc(sizeof(*phys_pg_pack), GFP_KERNEL);
 	if (!phys_pg_pack)
@@ -783,6 +836,8 @@
 	phys_pg_pack->asid = ctx->asid;
 	atomic_set(&phys_pg_pack->mapping_cnt, 1);
 
+	is_huge_page_opt = (force_regular_page ? false : true);
+
 	/* Only if all dma_addrs are aligned to 2MB and their
 	 * sizes is at least 2MB, we can use huge page mapping.
 	 * We limit the 2MB optimization to this condition,
@@ -791,7 +846,7 @@
 	 */
 	total_npages = 0;
 	for_each_sg(userptr->sgt->sgl, sg, userptr->sgt->nents, i) {
-		npages = get_sg_info(sg, &dma_addr);
+		npages = hl_get_sg_info(sg, &dma_addr);
 
 		total_npages += npages;
 
@@ -820,7 +875,7 @@
 
 	j = 0;
 	for_each_sg(userptr->sgt->sgl, sg, userptr->sgt->nents, i) {
-		npages = get_sg_info(sg, &dma_addr);
+		npages = hl_get_sg_info(sg, &dma_addr);
 
 		/* align down to physical page size and save the offset */
 		if (first) {
@@ -1001,11 +1056,12 @@
 	struct hl_userptr *userptr = NULL;
 	struct hl_vm_hash_node *hnode;
 	struct hl_va_range *va_range;
-	enum vm_type_t *vm_type;
+	enum vm_type *vm_type;
 	u64 ret_vaddr, hint_addr;
 	u32 handle = 0, va_block_align;
 	int rc;
 	bool is_userptr = args->flags & HL_MEM_USERPTR;
+	enum hl_va_range_type va_range_type = 0;
 
 	/* Assume failure */
 	*device_addr = 0;
@@ -1023,7 +1079,7 @@
 		}
 
 		rc = init_phys_pg_pack_from_userptr(ctx, userptr,
-				&phys_pg_pack);
+				&phys_pg_pack, false);
 		if (rc) {
 			dev_err(hdev->dev,
 				"unable to init page pack for vaddr 0x%llx\n",
@@ -1031,14 +1087,14 @@
 			goto init_page_pack_err;
 		}
 
-		vm_type = (enum vm_type_t *) userptr;
+		vm_type = (enum vm_type *) userptr;
 		hint_addr = args->map_host.hint_addr;
 		handle = phys_pg_pack->handle;
 
 		/* get required alignment */
 		if (phys_pg_pack->page_size == page_size) {
 			va_range = ctx->va_range[HL_VA_RANGE_TYPE_HOST];
-
+			va_range_type = HL_VA_RANGE_TYPE_HOST;
 			/*
 			 * huge page alignment may be needed in case of regular
 			 * page mapping, depending on the host VA alignment
@@ -1053,6 +1109,7 @@
 			 * mapping
 			 */
 			va_range = ctx->va_range[HL_VA_RANGE_TYPE_HOST_HUGE];
+			va_range_type = HL_VA_RANGE_TYPE_HOST_HUGE;
 			va_block_align = huge_page_size;
 		}
 	} else {
@@ -1072,12 +1129,13 @@
 
 		spin_unlock(&vm->idr_lock);
 
-		vm_type = (enum vm_type_t *) phys_pg_pack;
+		vm_type = (enum vm_type *) phys_pg_pack;
 
 		hint_addr = args->map_device.hint_addr;
 
 		/* DRAM VA alignment is the same as the MMU page size */
 		va_range = ctx->va_range[HL_VA_RANGE_TYPE_DRAM];
+		va_range_type = HL_VA_RANGE_TYPE_DRAM;
 		va_block_align = hdev->asic_prop.dmmu.page_size;
 	}
 
@@ -1100,8 +1158,23 @@
 		goto hnode_err;
 	}
 
+	if (hint_addr && phys_pg_pack->offset) {
+		if (args->flags & HL_MEM_FORCE_HINT) {
+			/* Fail if hint must be respected but it can't be */
+			dev_err(hdev->dev,
+				"Hint address 0x%llx cannot be respected because source memory is not aligned 0x%x\n",
+				hint_addr, phys_pg_pack->offset);
+			rc = -EINVAL;
+			goto va_block_err;
+		}
+		dev_dbg(hdev->dev,
+			"Hint address 0x%llx will be ignored because source memory is not aligned 0x%x\n",
+			hint_addr, phys_pg_pack->offset);
+	}
+
 	ret_vaddr = get_va_block(hdev, va_range, phys_pg_pack->total_size,
-					hint_addr, va_block_align);
+					hint_addr, va_block_align,
+					va_range_type, args->flags);
 	if (!ret_vaddr) {
 		dev_err(hdev->dev, "no available va block for handle %u\n",
 				handle);
@@ -1181,17 +1254,19 @@
 static int unmap_device_va(struct hl_ctx *ctx, struct hl_mem_in *args,
 				bool ctx_free)
 {
-	struct hl_device *hdev = ctx->hdev;
-	struct asic_fixed_properties *prop = &hdev->asic_prop;
 	struct hl_vm_phys_pg_pack *phys_pg_pack = NULL;
+	u64 vaddr = args->unmap.device_virt_addr;
 	struct hl_vm_hash_node *hnode = NULL;
+	struct asic_fixed_properties *prop;
+	struct hl_device *hdev = ctx->hdev;
 	struct hl_userptr *userptr = NULL;
 	struct hl_va_range *va_range;
-	u64 vaddr = args->unmap.device_virt_addr;
-	enum vm_type_t *vm_type;
+	enum vm_type *vm_type;
 	bool is_userptr;
 	int rc = 0;
 
+	prop = &hdev->asic_prop;
+
 	/* protect from double entrance */
 	mutex_lock(&ctx->mem_hash_lock);
 	hash_for_each_possible(ctx->mem_hash, hnode, node, (unsigned long)vaddr)
@@ -1214,8 +1289,9 @@
 	if (*vm_type == VM_TYPE_USERPTR) {
 		is_userptr = true;
 		userptr = hnode->ptr;
-		rc = init_phys_pg_pack_from_userptr(ctx, userptr,
-							&phys_pg_pack);
+
+		rc = init_phys_pg_pack_from_userptr(ctx, userptr, &phys_pg_pack,
+							false);
 		if (rc) {
 			dev_err(hdev->dev,
 				"unable to init page pack for vaddr 0x%llx\n",
@@ -1299,7 +1375,7 @@
 	kfree(hnode);
 
 	if (is_userptr) {
-		rc = free_phys_pg_pack(hdev, phys_pg_pack);
+		free_phys_pg_pack(hdev, phys_pg_pack);
 		dma_unmap_host_va(hdev, userptr);
 	}
 
@@ -1669,6 +1745,7 @@
 		return -EINVAL;
 	}
 
+	userptr->pid = current->pid;
 	userptr->sgt = kzalloc(sizeof(*userptr->sgt), GFP_KERNEL);
 	if (!userptr->sgt)
 		return -ENOMEM;
@@ -2033,7 +2110,7 @@
 	 * another side effect error
 	 */
 	if (!hdev->hard_reset_pending && !hash_empty(ctx->mem_hash))
-		dev_notice(hdev->dev,
+		dev_dbg(hdev->dev,
 			"user released device without removing its memory mappings\n");
 
 	hash_for_each_safe(ctx->mem_hash, i, tmp_node, hnode, node) {
diff --git a/drivers/misc/habanalabs/common/mmu/mmu_v1.c b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
index c5e93ff..0f536f7 100644
--- a/drivers/misc/habanalabs/common/mmu/mmu_v1.c
+++ b/drivers/misc/habanalabs/common/mmu/mmu_v1.c
@@ -470,13 +470,13 @@
 	if (!ZERO_OR_NULL_PTR(hdev->mmu_priv.hr.mmu_shadow_hop0)) {
 		kvfree(hdev->mmu_priv.dr.mmu_shadow_hop0);
 		gen_pool_destroy(hdev->mmu_priv.dr.mmu_pgt_pool);
-	}
 
-	/* Make sure that if we arrive here again without init was called we
-	 * won't cause kernel panic. This can happen for example if we fail
-	 * during hard reset code at certain points
-	 */
-	hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL;
+		/* Make sure that if we arrive here again without init was
+		 * called we won't cause kernel panic. This can happen for
+		 * example if we fail during hard reset code at certain points
+		 */
+		hdev->mmu_priv.dr.mmu_shadow_hop0 = NULL;
+	}
 }
 
 /**
diff --git a/drivers/misc/habanalabs/common/pci/pci.c b/drivers/misc/habanalabs/common/pci/pci.c
index d5bedf5..0b5366c 100644
--- a/drivers/misc/habanalabs/common/pci/pci.c
+++ b/drivers/misc/habanalabs/common/pci/pci.c
@@ -436,6 +436,8 @@
 		goto unmap_pci_bars;
 	}
 
+	dma_set_max_seg_size(&pdev->dev, U32_MAX);
+
 	return 0;
 
 unmap_pci_bars:
diff --git a/drivers/misc/habanalabs/common/state_dump.c b/drivers/misc/habanalabs/common/state_dump.c
new file mode 100644
index 0000000..7472690
--- /dev/null
+++ b/drivers/misc/habanalabs/common/state_dump.c
@@ -0,0 +1,718 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2021 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ */
+
+#include <linux/vmalloc.h>
+#include <uapi/misc/habanalabs.h>
+#include "habanalabs.h"
+
+/**
+ * hl_format_as_binary - helper function, format an integer as binary
+ *                       using supplied scratch buffer
+ * @buf: the buffer to use
+ * @buf_len: buffer capacity
+ * @n: number to format
+ *
+ * Returns pointer to buffer
+ */
+char *hl_format_as_binary(char *buf, size_t buf_len, u32 n)
+{
+	int i;
+	u32 bit;
+	bool leading0 = true;
+	char *wrptr = buf;
+
+	if (buf_len > 0 && buf_len < 3) {
+		*wrptr = '\0';
+		return buf;
+	}
+
+	wrptr[0] = '0';
+	wrptr[1] = 'b';
+	wrptr += 2;
+	/* Remove 3 characters from length for '0b' and '\0' termination */
+	buf_len -= 3;
+
+	for (i = 0; i < sizeof(n) * BITS_PER_BYTE && buf_len; ++i, n <<= 1) {
+		/* Writing bit calculation in one line would cause a false
+		 * positive static code analysis error, so splitting.
+		 */
+		bit = n & (1 << (sizeof(n) * BITS_PER_BYTE - 1));
+		bit = !!bit;
+		leading0 &= !bit;
+		if (!leading0) {
+			*wrptr = '0' + bit;
+			++wrptr;
+		}
+	}
+
+	*wrptr = '\0';
+
+	return buf;
+}
+
+/**
+ * resize_to_fit - helper function, resize buffer to fit given amount of data
+ * @buf: destination buffer double pointer
+ * @size: pointer to the size container
+ * @desired_size: size the buffer must contain
+ *
+ * Returns 0 on success or error code on failure.
+ * On success, the size of buffer is at least desired_size. Buffer is allocated
+ * via vmalloc and must be freed with vfree.
+ */
+static int resize_to_fit(char **buf, size_t *size, size_t desired_size)
+{
+	char *resized_buf;
+	size_t new_size;
+
+	if (*size >= desired_size)
+		return 0;
+
+	/* Not enough space to print all, have to resize */
+	new_size = max_t(size_t, PAGE_SIZE, round_up(desired_size, PAGE_SIZE));
+	resized_buf = vmalloc(new_size);
+	if (!resized_buf)
+		return -ENOMEM;
+	memcpy(resized_buf, *buf, *size);
+	vfree(*buf);
+	*buf = resized_buf;
+	*size = new_size;
+
+	return 1;
+}
+
+/**
+ * hl_snprintf_resize() - print formatted data to buffer, resize as needed
+ * @buf: buffer double pointer, to be written to and resized, must be either
+ *       NULL or allocated with vmalloc.
+ * @size: current size of the buffer
+ * @offset: current offset to write to
+ * @format: format of the data
+ *
+ * This function will write formatted data into the buffer. If buffer is not
+ * large enough, it will be resized using vmalloc. Size may be modified if the
+ * buffer was resized, offset will be advanced by the number of bytes written
+ * not including the terminating character
+ *
+ * Returns 0 on success or error code on failure
+ *
+ * Note that the buffer has to be manually released using vfree.
+ */
+int hl_snprintf_resize(char **buf, size_t *size, size_t *offset,
+			   const char *format, ...)
+{
+	va_list args;
+	size_t length;
+	int rc;
+
+	if (*buf == NULL && (*size != 0 || *offset != 0))
+		return -EINVAL;
+
+	va_start(args, format);
+	length = vsnprintf(*buf + *offset, *size - *offset, format, args);
+	va_end(args);
+
+	rc = resize_to_fit(buf, size, *offset + length + 1);
+	if (rc < 0)
+		return rc;
+	else if (rc > 0) {
+		/* Resize was needed, write again */
+		va_start(args, format);
+		length = vsnprintf(*buf + *offset, *size - *offset, format,
+				   args);
+		va_end(args);
+	}
+
+	*offset += length;
+
+	return 0;
+}
+
+/**
+ * hl_sync_engine_to_string - convert engine type enum to string literal
+ * @engine_type: engine type (TPC/MME/DMA)
+ *
+ * Return the resolved string literal
+ */
+const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type)
+{
+	switch (engine_type) {
+	case ENGINE_DMA:
+		return "DMA";
+	case ENGINE_MME:
+		return "MME";
+	case ENGINE_TPC:
+		return "TPC";
+	}
+	return "Invalid Engine Type";
+}
+
+/**
+ * hl_print_resize_sync_engine - helper function, format engine name and ID
+ * using hl_snprintf_resize
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ * @engine_type: engine type (TPC/MME/DMA)
+ * @engine_id: engine numerical id
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_print_resize_sync_engine(char **buf, size_t *size, size_t *offset,
+				enum hl_sync_engine_type engine_type,
+				u32 engine_id)
+{
+	return hl_snprintf_resize(buf, size, offset, "%s%u",
+			hl_sync_engine_to_string(engine_type), engine_id);
+}
+
+/**
+ * hl_state_dump_get_sync_name - transform sync object id to name if available
+ * @hdev: pointer to the device
+ * @sync_id: sync object id
+ *
+ * Returns a name literal or NULL if not resolved.
+ * Note: returning NULL shall not be considered as a failure, as not all
+ * sync objects are named.
+ */
+const char *hl_state_dump_get_sync_name(struct hl_device *hdev, u32 sync_id)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	struct hl_hw_obj_name_entry *entry;
+
+	hash_for_each_possible(sds->so_id_to_str_tb, entry,
+				node, sync_id)
+		if (sync_id == entry->id)
+			return entry->name;
+
+	return NULL;
+}
+
+/**
+ * hl_state_dump_get_monitor_name - transform monitor object dump to monitor
+ * name if available
+ * @hdev: pointer to the device
+ * @mon: monitor state dump
+ *
+ * Returns a name literal or NULL if not resolved.
+ * Note: returning NULL shall not be considered as a failure, as not all
+ * monitors are named.
+ */
+const char *hl_state_dump_get_monitor_name(struct hl_device *hdev,
+					struct hl_mon_state_dump *mon)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	struct hl_hw_obj_name_entry *entry;
+
+	hash_for_each_possible(sds->monitor_id_to_str_tb,
+				entry, node, mon->id)
+		if (mon->id == entry->id)
+			return entry->name;
+
+	return NULL;
+}
+
+/**
+ * hl_state_dump_free_sync_to_engine_map - free sync object to engine map
+ * @map: sync object to engine map
+ *
+ * Note: generic free implementation, the allocation is implemented per ASIC.
+ */
+void hl_state_dump_free_sync_to_engine_map(struct hl_sync_to_engine_map *map)
+{
+	struct hl_sync_to_engine_map_entry *entry;
+	struct hlist_node *tmp_node;
+	int i;
+
+	hash_for_each_safe(map->tb, i, tmp_node, entry, node) {
+		hash_del(&entry->node);
+		kfree(entry);
+	}
+}
+
+/**
+ * hl_state_dump_get_sync_to_engine - transform sync_id to
+ * hl_sync_to_engine_map_entry if available for current id
+ * @map: sync object to engine map
+ * @sync_id: sync object id
+ *
+ * Returns the translation entry if found or NULL if not.
+ * Note, returned NULL shall not be considered as a failure as the map
+ * does not cover all possible, it is a best effort sync ids.
+ */
+static struct hl_sync_to_engine_map_entry *
+hl_state_dump_get_sync_to_engine(struct hl_sync_to_engine_map *map, u32 sync_id)
+{
+	struct hl_sync_to_engine_map_entry *entry;
+
+	hash_for_each_possible(map->tb, entry, node, sync_id)
+		if (entry->sync_id == sync_id)
+			return entry;
+	return NULL;
+}
+
+/**
+ * hl_state_dump_read_sync_objects - read sync objects array
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ *
+ * Returns array of size SP_SYNC_OBJ_AMOUNT on success or NULL on failure
+ */
+static u32 *hl_state_dump_read_sync_objects(struct hl_device *hdev, u32 index)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	u32 *sync_objects;
+	s64 base_addr; /* Base addr can be negative */
+	int i;
+
+	base_addr = sds->props[SP_SYNC_OBJ_BASE_ADDR] +
+			sds->props[SP_NEXT_SYNC_OBJ_ADDR] * index;
+
+	sync_objects = vmalloc(sds->props[SP_SYNC_OBJ_AMOUNT] * sizeof(u32));
+	if (!sync_objects)
+		return NULL;
+
+	for (i = 0; i < sds->props[SP_SYNC_OBJ_AMOUNT]; ++i)
+		sync_objects[i] = RREG32(base_addr + i * sizeof(u32));
+
+	return sync_objects;
+}
+
+/**
+ * hl_state_dump_free_sync_objects - free sync objects array allocated by
+ * hl_state_dump_read_sync_objects
+ * @sync_objects: sync objects array
+ */
+static void hl_state_dump_free_sync_objects(u32 *sync_objects)
+{
+	vfree(sync_objects);
+}
+
+
+/**
+ * hl_state_dump_print_syncs_single_block - print active sync objects on a
+ * single block
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ * @map: sync engines names map
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int
+hl_state_dump_print_syncs_single_block(struct hl_device *hdev, u32 index,
+				char **buf, size_t *size, size_t *offset,
+				struct hl_sync_to_engine_map *map)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	const char *sync_name;
+	u32 *sync_objects = NULL;
+	int rc = 0, i;
+
+	if (sds->sync_namager_names) {
+		rc = hl_snprintf_resize(
+			buf, size, offset, "%s\n",
+			sds->sync_namager_names[index]);
+		if (rc)
+			goto out;
+	}
+
+	sync_objects = hl_state_dump_read_sync_objects(hdev, index);
+	if (!sync_objects) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < sds->props[SP_SYNC_OBJ_AMOUNT]; ++i) {
+		struct hl_sync_to_engine_map_entry *entry;
+		u64 sync_object_addr;
+
+		if (!sync_objects[i])
+			continue;
+
+		sync_object_addr = sds->props[SP_SYNC_OBJ_BASE_ADDR] +
+				sds->props[SP_NEXT_SYNC_OBJ_ADDR] * index +
+				i * sizeof(u32);
+
+		rc = hl_snprintf_resize(buf, size, offset, "sync id: %u", i);
+		if (rc)
+			goto free_sync_objects;
+		sync_name = hl_state_dump_get_sync_name(hdev, i);
+		if (sync_name) {
+			rc = hl_snprintf_resize(buf, size, offset, " %s",
+						sync_name);
+			if (rc)
+				goto free_sync_objects;
+		}
+		rc = hl_snprintf_resize(buf, size, offset, ", value: %u",
+					sync_objects[i]);
+		if (rc)
+			goto free_sync_objects;
+
+		/* Append engine string */
+		entry = hl_state_dump_get_sync_to_engine(map,
+			(u32)sync_object_addr);
+		if (entry) {
+			rc = hl_snprintf_resize(buf, size, offset,
+						", Engine: ");
+			if (rc)
+				goto free_sync_objects;
+			rc = hl_print_resize_sync_engine(buf, size, offset,
+						entry->engine_type,
+						entry->engine_id);
+			if (rc)
+				goto free_sync_objects;
+		}
+
+		rc = hl_snprintf_resize(buf, size, offset, "\n");
+		if (rc)
+			goto free_sync_objects;
+	}
+
+free_sync_objects:
+	hl_state_dump_free_sync_objects(sync_objects);
+out:
+	return rc;
+}
+
+/**
+ * hl_state_dump_print_syncs - print active sync objects
+ * @hdev: pointer to the device
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_state_dump_print_syncs(struct hl_device *hdev,
+					char **buf, size_t *size,
+					size_t *offset)
+
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	struct hl_sync_to_engine_map *map;
+	u32 index;
+	int rc = 0;
+
+	map = kzalloc(sizeof(*map), GFP_KERNEL);
+	if (!map)
+		return -ENOMEM;
+
+	rc = sds->funcs.gen_sync_to_engine_map(hdev, map);
+	if (rc)
+		goto free_map_mem;
+
+	rc = hl_snprintf_resize(buf, size, offset, "Non zero sync objects:\n");
+	if (rc)
+		goto out;
+
+	if (sds->sync_namager_names) {
+		for (index = 0; sds->sync_namager_names[index]; ++index) {
+			rc = hl_state_dump_print_syncs_single_block(
+				hdev, index, buf, size, offset, map);
+			if (rc)
+				goto out;
+		}
+	} else {
+		for (index = 0; index < sds->props[SP_NUM_CORES]; ++index) {
+			rc = hl_state_dump_print_syncs_single_block(
+				hdev, index, buf, size, offset, map);
+			if (rc)
+				goto out;
+		}
+	}
+
+out:
+	hl_state_dump_free_sync_to_engine_map(map);
+free_map_mem:
+	kfree(map);
+
+	return rc;
+}
+
+/**
+ * hl_state_dump_alloc_read_sm_block_monitors - read monitors for a specific
+ * block
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ *
+ * Returns an array of monitor data of size SP_MONITORS_AMOUNT or NULL
+ * on error
+ */
+static struct hl_mon_state_dump *
+hl_state_dump_alloc_read_sm_block_monitors(struct hl_device *hdev, u32 index)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	struct hl_mon_state_dump *monitors;
+	s64 base_addr; /* Base addr can be negative */
+	int i;
+
+	monitors = vmalloc(sds->props[SP_MONITORS_AMOUNT] *
+			   sizeof(struct hl_mon_state_dump));
+	if (!monitors)
+		return NULL;
+
+	base_addr = sds->props[SP_NEXT_SYNC_OBJ_ADDR] * index;
+
+	for (i = 0; i < sds->props[SP_MONITORS_AMOUNT]; ++i) {
+		monitors[i].id = i;
+		monitors[i].wr_addr_low =
+			RREG32(base_addr + sds->props[SP_MON_OBJ_WR_ADDR_LOW] +
+				i * sizeof(u32));
+
+		monitors[i].wr_addr_high =
+			RREG32(base_addr + sds->props[SP_MON_OBJ_WR_ADDR_HIGH] +
+				i * sizeof(u32));
+
+		monitors[i].wr_data =
+			RREG32(base_addr + sds->props[SP_MON_OBJ_WR_DATA] +
+				i * sizeof(u32));
+
+		monitors[i].arm_data =
+			RREG32(base_addr + sds->props[SP_MON_OBJ_ARM_DATA] +
+				i * sizeof(u32));
+
+		monitors[i].status =
+			RREG32(base_addr + sds->props[SP_MON_OBJ_STATUS] +
+				i * sizeof(u32));
+	}
+
+	return monitors;
+}
+
+/**
+ * hl_state_dump_free_monitors - free the monitors structure
+ * @monitors: monitors array created with
+ *            hl_state_dump_alloc_read_sm_block_monitors
+ */
+static void hl_state_dump_free_monitors(struct hl_mon_state_dump *monitors)
+{
+	vfree(monitors);
+}
+
+/**
+ * hl_state_dump_print_monitors_single_block - print active monitors on a
+ * single block
+ * @hdev: pointer to the device
+ * @index: sync manager block index starting with E_N
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_state_dump_print_monitors_single_block(struct hl_device *hdev,
+						u32 index,
+						char **buf, size_t *size,
+						size_t *offset)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	struct hl_mon_state_dump *monitors = NULL;
+	int rc = 0, i;
+
+	if (sds->sync_namager_names) {
+		rc = hl_snprintf_resize(
+			buf, size, offset, "%s\n",
+			sds->sync_namager_names[index]);
+		if (rc)
+			goto out;
+	}
+
+	monitors = hl_state_dump_alloc_read_sm_block_monitors(hdev, index);
+	if (!monitors) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < sds->props[SP_MONITORS_AMOUNT]; ++i) {
+		if (!(sds->funcs.monitor_valid(&monitors[i])))
+			continue;
+
+		/* Monitor is valid, dump it */
+		rc = sds->funcs.print_single_monitor(buf, size, offset, hdev,
+							&monitors[i]);
+		if (rc)
+			goto free_monitors;
+
+		hl_snprintf_resize(buf, size, offset, "\n");
+	}
+
+free_monitors:
+	hl_state_dump_free_monitors(monitors);
+out:
+	return rc;
+}
+
+/**
+ * hl_state_dump_print_monitors - print active monitors
+ * @hdev: pointer to the device
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ *
+ * Returns 0 on success or error code on failure
+ */
+static int hl_state_dump_print_monitors(struct hl_device *hdev,
+					char **buf, size_t *size,
+					size_t *offset)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	u32 index;
+	int rc = 0;
+
+	rc = hl_snprintf_resize(buf, size, offset,
+		"Valid (armed) monitor objects:\n");
+	if (rc)
+		goto out;
+
+	if (sds->sync_namager_names) {
+		for (index = 0; sds->sync_namager_names[index]; ++index) {
+			rc = hl_state_dump_print_monitors_single_block(
+				hdev, index, buf, size, offset);
+			if (rc)
+				goto out;
+		}
+	} else {
+		for (index = 0; index < sds->props[SP_NUM_CORES]; ++index) {
+			rc = hl_state_dump_print_monitors_single_block(
+				hdev, index, buf, size, offset);
+			if (rc)
+				goto out;
+		}
+	}
+
+out:
+	return rc;
+}
+
+/**
+ * hl_state_dump_print_engine_fences - print active fences for a specific
+ * engine
+ * @hdev: pointer to the device
+ * @engine_type: engine type to use
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ */
+static int
+hl_state_dump_print_engine_fences(struct hl_device *hdev,
+				  enum hl_sync_engine_type engine_type,
+				  char **buf, size_t *size, size_t *offset)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	int rc = 0, i, n_fences;
+	u64 base_addr, next_fence;
+
+	switch (engine_type) {
+	case ENGINE_TPC:
+		n_fences = sds->props[SP_NUM_OF_TPC_ENGINES];
+		base_addr = sds->props[SP_TPC0_CMDQ];
+		next_fence = sds->props[SP_NEXT_TPC];
+		break;
+	case ENGINE_MME:
+		n_fences = sds->props[SP_NUM_OF_MME_ENGINES];
+		base_addr = sds->props[SP_MME_CMDQ];
+		next_fence = sds->props[SP_NEXT_MME];
+		break;
+	case ENGINE_DMA:
+		n_fences = sds->props[SP_NUM_OF_DMA_ENGINES];
+		base_addr = sds->props[SP_DMA_CMDQ];
+		next_fence = sds->props[SP_DMA_QUEUES_OFFSET];
+		break;
+	default:
+		return -EINVAL;
+	}
+	for (i = 0; i < n_fences; ++i) {
+		rc = sds->funcs.print_fences_single_engine(
+			hdev,
+			base_addr + next_fence * i +
+				sds->props[SP_FENCE0_CNT_OFFSET],
+			base_addr + next_fence * i +
+				sds->props[SP_CP_STS_OFFSET],
+			engine_type, i, buf, size, offset);
+		if (rc)
+			goto out;
+	}
+out:
+	return rc;
+}
+
+/**
+ * hl_state_dump_print_fences - print active fences
+ * @hdev: pointer to the device
+ * @buf: destination buffer double pointer to be used with hl_snprintf_resize
+ * @size: pointer to the size container
+ * @offset: pointer to the offset container
+ */
+static int hl_state_dump_print_fences(struct hl_device *hdev, char **buf,
+				      size_t *size, size_t *offset)
+{
+	int rc = 0;
+
+	rc = hl_snprintf_resize(buf, size, offset, "Valid (armed) fences:\n");
+	if (rc)
+		goto out;
+
+	rc = hl_state_dump_print_engine_fences(hdev, ENGINE_TPC, buf, size, offset);
+	if (rc)
+		goto out;
+
+	rc = hl_state_dump_print_engine_fences(hdev, ENGINE_MME, buf, size, offset);
+	if (rc)
+		goto out;
+
+	rc = hl_state_dump_print_engine_fences(hdev, ENGINE_DMA, buf, size, offset);
+	if (rc)
+		goto out;
+
+out:
+	return rc;
+}
+
+/**
+ * hl_state_dump() - dump system state
+ * @hdev: pointer to device structure
+ */
+int hl_state_dump(struct hl_device *hdev)
+{
+	char *buf = NULL;
+	size_t offset = 0, size = 0;
+	int rc;
+
+	rc = hl_snprintf_resize(&buf, &size, &offset,
+				"Timestamp taken on: %llu\n\n",
+				ktime_to_ns(ktime_get()));
+	if (rc)
+		goto err;
+
+	rc = hl_state_dump_print_syncs(hdev, &buf, &size, &offset);
+	if (rc)
+		goto err;
+
+	hl_snprintf_resize(&buf, &size, &offset, "\n");
+
+	rc = hl_state_dump_print_monitors(hdev, &buf, &size, &offset);
+	if (rc)
+		goto err;
+
+	hl_snprintf_resize(&buf, &size, &offset, "\n");
+
+	rc = hl_state_dump_print_fences(hdev, &buf, &size, &offset);
+	if (rc)
+		goto err;
+
+	hl_snprintf_resize(&buf, &size, &offset, "\n");
+
+	hl_debugfs_set_state_dump(hdev, buf, size);
+
+	return 0;
+err:
+	vfree(buf);
+	return rc;
+}
diff --git a/drivers/misc/habanalabs/common/sysfs.c b/drivers/misc/habanalabs/common/sysfs.c
index db72df2..34f9f27 100644
--- a/drivers/misc/habanalabs/common/sysfs.c
+++ b/drivers/misc/habanalabs/common/sysfs.c
@@ -9,8 +9,7 @@
 
 #include <linux/pci.h>
 
-long hl_get_frequency(struct hl_device *hdev, u32 pll_index,
-								bool curr)
+long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr)
 {
 	struct cpucp_packet pkt;
 	u32 used_pll_idx;
@@ -44,8 +43,7 @@
 	return (long) result;
 }
 
-void hl_set_frequency(struct hl_device *hdev, u32 pll_index,
-								u64 freq)
+void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq)
 {
 	struct cpucp_packet pkt;
 	u32 used_pll_idx;
@@ -285,16 +283,12 @@
 				char *buf)
 {
 	struct hl_device *hdev = dev_get_drvdata(dev);
-	char *str;
+	char str[HL_STR_MAX];
 
-	if (atomic_read(&hdev->in_reset))
-		str = "In reset";
-	else if (hdev->disabled)
-		str = "Malfunction";
-	else if (hdev->needs_reset)
-		str = "Needs Reset";
-	else
-		str = "Operational";
+	strscpy(str, hdev->status[hl_device_status(hdev)], HL_STR_MAX);
+
+	/* use uppercase for backward compatibility */
+	str[0] = 'A' + (str[0] - 'a');
 
 	return sprintf(buf, "%s\n", str);
 }
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index aa8a0ca..383865b 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -76,7 +76,7 @@
 #define GAUDI_PLDM_MMU_TIMEOUT_USEC	(MMU_CONFIG_TIMEOUT_USEC * 100)
 #define GAUDI_PLDM_QMAN0_TIMEOUT_USEC	(HL_DEVICE_TIMEOUT_USEC * 30)
 #define GAUDI_PLDM_TPC_KERNEL_WAIT_USEC	(HL_DEVICE_TIMEOUT_USEC * 30)
-#define GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC	1000000		/* 1s */
+#define GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC	4000000		/* 4s */
 #define GAUDI_MSG_TO_CPU_TIMEOUT_USEC	4000000		/* 4s */
 #define GAUDI_WAIT_FOR_BL_TIMEOUT_USEC	15000000	/* 15s */
 
@@ -106,6 +106,21 @@
 
 #define GAUDI_PLL_MAX 10
 
+#define BIN_REG_STRING_SIZE	sizeof("0b10101010101010101010101010101010")
+
+#define MONITOR_SOB_STRING_SIZE		256
+
+static u32 gaudi_stream_master[GAUDI_STREAM_MASTER_ARR_SIZE] = {
+	GAUDI_QUEUE_ID_DMA_0_0,
+	GAUDI_QUEUE_ID_DMA_0_1,
+	GAUDI_QUEUE_ID_DMA_0_2,
+	GAUDI_QUEUE_ID_DMA_0_3,
+	GAUDI_QUEUE_ID_DMA_1_0,
+	GAUDI_QUEUE_ID_DMA_1_1,
+	GAUDI_QUEUE_ID_DMA_1_2,
+	GAUDI_QUEUE_ID_DMA_1_3
+};
+
 static const char gaudi_irq_name[GAUDI_MSI_ENTRIES][GAUDI_MAX_STRING_LEN] = {
 		"gaudi cq 0_0", "gaudi cq 0_1", "gaudi cq 0_2", "gaudi cq 0_3",
 		"gaudi cq 1_0", "gaudi cq 1_1", "gaudi cq 1_2", "gaudi cq 1_3",
@@ -348,6 +363,97 @@
 	QUEUE_TYPE_INT, /* GAUDI_QUEUE_ID_NIC_9_3 */
 };
 
+static struct hl_hw_obj_name_entry gaudi_so_id_to_str[] = {
+	{ .id = 0,  .name = "SYNC_OBJ_DMA_DOWN_FEEDBACK" },
+	{ .id = 1,  .name = "SYNC_OBJ_DMA_UP_FEEDBACK" },
+	{ .id = 2,  .name = "SYNC_OBJ_DMA_STATIC_DRAM_SRAM_FEEDBACK" },
+	{ .id = 3,  .name = "SYNC_OBJ_DMA_SRAM_DRAM_FEEDBACK" },
+	{ .id = 4,  .name = "SYNC_OBJ_FIRST_COMPUTE_FINISH" },
+	{ .id = 5,  .name = "SYNC_OBJ_HOST_DRAM_DONE" },
+	{ .id = 6,  .name = "SYNC_OBJ_DBG_CTR_DEPRECATED" },
+	{ .id = 7,  .name = "SYNC_OBJ_DMA_ACTIVATIONS_DRAM_SRAM_FEEDBACK" },
+	{ .id = 8,  .name = "SYNC_OBJ_ENGINE_SEM_MME_0" },
+	{ .id = 9,  .name = "SYNC_OBJ_ENGINE_SEM_MME_1" },
+	{ .id = 10, .name = "SYNC_OBJ_ENGINE_SEM_TPC_0" },
+	{ .id = 11, .name = "SYNC_OBJ_ENGINE_SEM_TPC_1" },
+	{ .id = 12, .name = "SYNC_OBJ_ENGINE_SEM_TPC_2" },
+	{ .id = 13, .name = "SYNC_OBJ_ENGINE_SEM_TPC_3" },
+	{ .id = 14, .name = "SYNC_OBJ_ENGINE_SEM_TPC_4" },
+	{ .id = 15, .name = "SYNC_OBJ_ENGINE_SEM_TPC_5" },
+	{ .id = 16, .name = "SYNC_OBJ_ENGINE_SEM_TPC_6" },
+	{ .id = 17, .name = "SYNC_OBJ_ENGINE_SEM_TPC_7" },
+	{ .id = 18, .name = "SYNC_OBJ_ENGINE_SEM_DMA_1" },
+	{ .id = 19, .name = "SYNC_OBJ_ENGINE_SEM_DMA_2" },
+	{ .id = 20, .name = "SYNC_OBJ_ENGINE_SEM_DMA_3" },
+	{ .id = 21, .name = "SYNC_OBJ_ENGINE_SEM_DMA_4" },
+	{ .id = 22, .name = "SYNC_OBJ_ENGINE_SEM_DMA_5" },
+	{ .id = 23, .name = "SYNC_OBJ_ENGINE_SEM_DMA_6" },
+	{ .id = 24, .name = "SYNC_OBJ_ENGINE_SEM_DMA_7" },
+	{ .id = 25, .name = "SYNC_OBJ_DBG_CTR_0" },
+	{ .id = 26, .name = "SYNC_OBJ_DBG_CTR_1" },
+};
+
+static struct hl_hw_obj_name_entry gaudi_monitor_id_to_str[] = {
+	{ .id = 200, .name = "MON_OBJ_DMA_DOWN_FEEDBACK_RESET" },
+	{ .id = 201, .name = "MON_OBJ_DMA_UP_FEADBACK_RESET" },
+	{ .id = 203, .name = "MON_OBJ_DRAM_TO_SRAM_QUEUE_FENCE" },
+	{ .id = 204, .name = "MON_OBJ_TPC_0_CLK_GATE" },
+	{ .id = 205, .name = "MON_OBJ_TPC_1_CLK_GATE" },
+	{ .id = 206, .name = "MON_OBJ_TPC_2_CLK_GATE" },
+	{ .id = 207, .name = "MON_OBJ_TPC_3_CLK_GATE" },
+	{ .id = 208, .name = "MON_OBJ_TPC_4_CLK_GATE" },
+	{ .id = 209, .name = "MON_OBJ_TPC_5_CLK_GATE" },
+	{ .id = 210, .name = "MON_OBJ_TPC_6_CLK_GATE" },
+	{ .id = 211, .name = "MON_OBJ_TPC_7_CLK_GATE" },
+};
+
+static s64 gaudi_state_dump_specs_props[] = {
+	[SP_SYNC_OBJ_BASE_ADDR] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0,
+	[SP_NEXT_SYNC_OBJ_ADDR] = NEXT_SYNC_OBJ_ADDR_INTERVAL,
+	[SP_SYNC_OBJ_AMOUNT] = NUM_OF_SOB_IN_BLOCK,
+	[SP_MON_OBJ_WR_ADDR_LOW] =
+		mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0,
+	[SP_MON_OBJ_WR_ADDR_HIGH] =
+		mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0,
+	[SP_MON_OBJ_WR_DATA] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_DATA_0,
+	[SP_MON_OBJ_ARM_DATA] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_ARM_0,
+	[SP_MON_OBJ_STATUS] = mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_0,
+	[SP_MONITORS_AMOUNT] = NUM_OF_MONITORS_IN_BLOCK,
+	[SP_TPC0_CMDQ] = mmTPC0_QM_GLBL_CFG0,
+	[SP_TPC0_CFG_SO] = mmTPC0_CFG_QM_SYNC_OBJECT_ADDR,
+	[SP_NEXT_TPC] = mmTPC1_QM_GLBL_CFG0 - mmTPC0_QM_GLBL_CFG0,
+	[SP_MME_CMDQ] = mmMME0_QM_GLBL_CFG0,
+	[SP_MME_CFG_SO] = mmMME0_CTRL_ARCH_DESC_SYNC_OBJECT_ADDR_LOW_LOCAL,
+	[SP_NEXT_MME] = mmMME2_QM_GLBL_CFG0 - mmMME0_QM_GLBL_CFG0,
+	[SP_DMA_CMDQ] = mmDMA0_QM_GLBL_CFG0,
+	[SP_DMA_CFG_SO] = mmDMA0_CORE_WR_COMP_ADDR_LO,
+	[SP_DMA_QUEUES_OFFSET] = mmDMA1_QM_GLBL_CFG0 - mmDMA0_QM_GLBL_CFG0,
+	[SP_NUM_OF_MME_ENGINES] = NUM_OF_MME_ENGINES,
+	[SP_SUB_MME_ENG_NUM] = NUM_OF_MME_SUB_ENGINES,
+	[SP_NUM_OF_DMA_ENGINES] = NUM_OF_DMA_ENGINES,
+	[SP_NUM_OF_TPC_ENGINES] = NUM_OF_TPC_ENGINES,
+	[SP_ENGINE_NUM_OF_QUEUES] = NUM_OF_QUEUES,
+	[SP_ENGINE_NUM_OF_STREAMS] = NUM_OF_STREAMS,
+	[SP_ENGINE_NUM_OF_FENCES] = NUM_OF_FENCES,
+	[SP_FENCE0_CNT_OFFSET] =
+		mmDMA0_QM_CP_FENCE0_CNT_0 - mmDMA0_QM_GLBL_CFG0,
+	[SP_FENCE0_RDATA_OFFSET] =
+		mmDMA0_QM_CP_FENCE0_RDATA_0 - mmDMA0_QM_GLBL_CFG0,
+	[SP_CP_STS_OFFSET] = mmDMA0_QM_CP_STS_0 - mmDMA0_QM_GLBL_CFG0,
+	[SP_NUM_CORES] = 1,
+};
+
+/* The order here is opposite to the order of the indexing in the h/w.
+ * i.e. SYNC_MGR_W_S is actually 0, SYNC_MGR_E_S is 1, etc.
+ */
+static const char * const gaudi_sync_manager_names[] = {
+	"SYNC_MGR_E_N",
+	"SYNC_MGR_W_N",
+	"SYNC_MGR_E_S",
+	"SYNC_MGR_W_S",
+	NULL
+};
+
 struct ecc_info_extract_params {
 	u64 block_address;
 	u32 num_memories;
@@ -363,8 +469,6 @@
 					u32 size, u64 val);
 static int gaudi_memset_registers(struct hl_device *hdev, u64 reg_base,
 					u32 num_regs, u32 val);
-static int gaudi_schedule_register_memset(struct hl_device *hdev,
-		u32 hw_queue_id, u64 reg_base, u32 num_regs, u32 val);
 static int gaudi_run_tpc_kernel(struct hl_device *hdev, u64 tpc_kernel,
 				u32 tpc_id);
 static int gaudi_mmu_clear_pgt_range(struct hl_device *hdev);
@@ -375,7 +479,6 @@
 				u32 size, bool eb);
 static u32 gaudi_gen_wait_cb(struct hl_device *hdev,
 				struct hl_gen_wait_properties *prop);
-
 static inline enum hl_collective_mode
 get_collective_mode(struct hl_device *hdev, u32 queue_id)
 {
@@ -403,7 +506,11 @@
 
 	if (hdev->card_type == cpucp_card_type_pmc) {
 		prop->max_power_default = MAX_POWER_DEFAULT_PMC;
-		prop->dc_power_default = DC_POWER_DEFAULT_PMC;
+
+		if (prop->fw_security_enabled)
+			prop->dc_power_default = DC_POWER_DEFAULT_PMC_SEC;
+		else
+			prop->dc_power_default = DC_POWER_DEFAULT_PMC;
 	} else {
 		prop->max_power_default = MAX_POWER_DEFAULT_PCI;
 		prop->dc_power_default = DC_POWER_DEFAULT_PCI;
@@ -450,6 +557,7 @@
 						get_collective_mode(hdev, i);
 	}
 
+	prop->device_dma_offset_for_host_access = HOST_PHYS_BASE;
 	prop->completion_queues_count = NUMBER_OF_CMPLT_QUEUES;
 	prop->collective_first_sob = 0;
 	prop->collective_first_mon = 0;
@@ -551,6 +659,8 @@
 	prop->hard_reset_done_by_fw = false;
 	prop->gic_interrupts_enable = true;
 
+	prop->server_type = HL_SERVER_TYPE_UNKNOWN;
+
 	return 0;
 }
 
@@ -723,14 +833,14 @@
 					GAUDI_BOOT_FIT_REQ_TIMEOUT_USEC);
 	if (rc) {
 		if (hdev->reset_on_preboot_fail)
-			hdev->asic_funcs->hw_fini(hdev, true);
+			hdev->asic_funcs->hw_fini(hdev, true, false);
 		goto pci_fini;
 	}
 
 	if (gaudi_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
 		dev_info(hdev->dev,
 			"H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true);
+		hdev->asic_funcs->hw_fini(hdev, true, false);
 	}
 
 	return 0;
@@ -974,17 +1084,11 @@
 	struct gaudi_hw_sob_group *hw_sob_group =
 		container_of(ref, struct gaudi_hw_sob_group, kref);
 	struct hl_device *hdev = hw_sob_group->hdev;
-	u64 base_addr;
-	int rc;
+	int i;
 
-	base_addr = CFG_BASE + mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0 +
-			hw_sob_group->base_sob_id * 4;
-	rc = gaudi_schedule_register_memset(hdev, hw_sob_group->queue_id,
-			base_addr, NUMBER_OF_SOBS_IN_GRP, 0);
-	if (rc)
-		dev_err(hdev->dev,
-			"failed resetting sob group - sob base %u, count %u",
-			hw_sob_group->base_sob_id, NUMBER_OF_SOBS_IN_GRP);
+	for (i = 0 ; i < NUMBER_OF_SOBS_IN_GRP ; i++)
+		WREG32((mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0 +
+			(hw_sob_group->base_sob_id * 4) + (i * 4)), 0);
 
 	kref_init(&hw_sob_group->kref);
 }
@@ -1121,6 +1225,20 @@
 	queue_id = job->hw_queue_id;
 	prop = &hdev->kernel_queues[queue_id].sync_stream_prop;
 
+	if (job->cs->encaps_signals) {
+		/* use the encaps signal handle store earlier in the flow
+		 * and set the SOB information from the encaps
+		 * signals handle
+		 */
+		hl_hw_queue_encaps_sig_set_sob_info(hdev, job->cs, job,
+						cs_cmpl);
+
+		dev_dbg(hdev->dev, "collective wait: Sequence %llu found, sob_id: %u,  wait for sob_val: %u\n",
+				job->cs->sequence,
+				cs_cmpl->hw_sob->sob_id,
+				cs_cmpl->sob_val);
+	}
+
 	/* Add to wait CBs using slave monitor */
 	wait_prop.data = (void *) job->user_cb;
 	wait_prop.sob_base = cs_cmpl->hw_sob->sob_id;
@@ -1131,7 +1249,7 @@
 	wait_prop.size = cb_size;
 
 	dev_dbg(hdev->dev,
-		"Generate slave wait CB, sob %d, val:0x%x, mon %d, q %d\n",
+		"Generate slave wait CB, sob %d, val:%x, mon %d, q %d\n",
 		cs_cmpl->hw_sob->sob_id, cs_cmpl->sob_val,
 		prop->collective_slave_mon_id, queue_id);
 
@@ -1145,7 +1263,7 @@
 			prop->collective_sob_id, cb_size, false);
 }
 
-static void gaudi_collective_wait_init_cs(struct hl_cs *cs)
+static int gaudi_collective_wait_init_cs(struct hl_cs *cs)
 {
 	struct hl_cs_compl *signal_cs_cmpl =
 		container_of(cs->signal_fence, struct hl_cs_compl, base_fence);
@@ -1163,9 +1281,37 @@
 	gaudi = hdev->asic_specific;
 	cprop = &gaudi->collective_props;
 
-	/* copy the SOB id and value of the signal CS */
-	cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
-	cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+	/* In encaps signals case the SOB info will be retrieved from
+	 * the handle in gaudi_collective_slave_init_job.
+	 */
+	if (!cs->encaps_signals) {
+		/* copy the SOB id and value of the signal CS */
+		cs_cmpl->hw_sob = signal_cs_cmpl->hw_sob;
+		cs_cmpl->sob_val = signal_cs_cmpl->sob_val;
+	}
+
+	/* check again if the signal cs already completed.
+	 * if yes then don't send any wait cs since the hw_sob
+	 * could be in reset already. if signal is not completed
+	 * then get refcount to hw_sob to prevent resetting the sob
+	 * while wait cs is not submitted.
+	 * note that this check is protected by two locks,
+	 * hw queue lock and completion object lock,
+	 * and the same completion object lock also protects
+	 * the hw_sob reset handler function.
+	 * The hw_queue lock prevent out of sync of hw_sob
+	 * refcount value, changed by signal/wait flows.
+	 */
+	spin_lock(&signal_cs_cmpl->lock);
+
+	if (completion_done(&cs->signal_fence->completion)) {
+		spin_unlock(&signal_cs_cmpl->lock);
+		return -EINVAL;
+	}
+	/* Increment kref since all slave queues are now waiting on it */
+	kref_get(&cs_cmpl->hw_sob->kref);
+
+	spin_unlock(&signal_cs_cmpl->lock);
 
 	/* Calculate the stream from collective master queue (1st job) */
 	job = list_first_entry(&cs->job_list, struct hl_cs_job, cs_node);
@@ -1210,21 +1356,17 @@
 				cprop->curr_sob_group_idx[stream], stream);
 	}
 
-	/* Increment kref since all slave queues are now waiting on it */
-	kref_get(&cs_cmpl->hw_sob->kref);
-	/*
-	 * Must put the signal fence after the SOB refcnt increment so
-	 * the SOB refcnt won't turn 0 and reset the SOB before the
-	 * wait CS was submitted.
-	 */
 	mb();
 	hl_fence_put(cs->signal_fence);
 	cs->signal_fence = NULL;
+
+	return 0;
 }
 
 static int gaudi_collective_wait_create_job(struct hl_device *hdev,
 		struct hl_ctx *ctx, struct hl_cs *cs,
-		enum hl_collective_mode mode, u32 queue_id, u32 wait_queue_id)
+		enum hl_collective_mode mode, u32 queue_id, u32 wait_queue_id,
+		u32 encaps_signal_offset)
 {
 	struct hw_queue_properties *hw_queue_prop;
 	struct hl_cs_counters_atomic *cntr;
@@ -1284,6 +1426,13 @@
 	job->user_cb_size = cb_size;
 	job->hw_queue_id = queue_id;
 
+	/* since its guaranteed to have only one chunk in the collective wait
+	 * cs, we can use this chunk to set the encapsulated signal offset
+	 * in the jobs.
+	 */
+	if (cs->encaps_signals)
+		job->encaps_sig_wait_offset = encaps_signal_offset;
+
 	/*
 	 * No need in parsing, user CB is the patched CB.
 	 * We call hl_cb_destroy() out of two reasons - we don't need
@@ -1312,8 +1461,9 @@
 }
 
 static int gaudi_collective_wait_create_jobs(struct hl_device *hdev,
-		struct hl_ctx *ctx, struct hl_cs *cs, u32 wait_queue_id,
-		u32 collective_engine_id)
+		struct hl_ctx *ctx, struct hl_cs *cs,
+		u32 wait_queue_id, u32 collective_engine_id,
+		u32 encaps_signal_offset)
 {
 	struct gaudi_device *gaudi = hdev->asic_specific;
 	struct hw_queue_properties *hw_queue_prop;
@@ -1363,7 +1513,8 @@
 		if (i == 0) {
 			queue_id = wait_queue_id;
 			rc = gaudi_collective_wait_create_job(hdev, ctx, cs,
-				HL_COLLECTIVE_MASTER, queue_id, wait_queue_id);
+				HL_COLLECTIVE_MASTER, queue_id,
+				wait_queue_id, encaps_signal_offset);
 		} else {
 			if (nic_idx < NIC_NUMBER_OF_ENGINES) {
 				if (gaudi->hw_cap_initialized &
@@ -1383,7 +1534,8 @@
 			}
 
 			rc = gaudi_collective_wait_create_job(hdev, ctx, cs,
-				HL_COLLECTIVE_SLAVE, queue_id, wait_queue_id);
+				HL_COLLECTIVE_SLAVE, queue_id,
+				wait_queue_id, encaps_signal_offset);
 		}
 
 		if (rc)
@@ -1431,6 +1583,11 @@
 		return rc;
 	}
 
+	/* Scrub both SRAM and DRAM */
+	rc = hdev->asic_funcs->scrub_device_mem(hdev, 0, 0);
+	if (rc)
+		goto disable_pci_access;
+
 	rc = gaudi_fetch_psoc_frequency(hdev);
 	if (rc) {
 		dev_err(hdev->dev, "Failed to fetch psoc frequency\n");
@@ -1455,6 +1612,11 @@
 		goto disable_pci_access;
 	}
 
+	/* We only support a single ASID for the user, so for the sake of optimization, just
+	 * initialize the ASID one time during device initialization with the fixed value of 1
+	 */
+	gaudi_mmu_prepare(hdev, 1);
+
 	return 0;
 
 disable_pci_access:
@@ -1720,8 +1882,12 @@
 	hdev->supports_sync_stream = true;
 	hdev->supports_coresight = true;
 	hdev->supports_staged_submission = true;
+	hdev->supports_wait_for_multi_cs = true;
 
-	gaudi_set_pci_memory_regions(hdev);
+	hdev->asic_funcs->set_pci_memory_regions(hdev);
+	hdev->stream_master_qid_arr =
+				hdev->asic_funcs->get_stream_master_qid_arr();
+	hdev->stream_master_qid_arr_size = GAUDI_STREAM_MASTER_ARR_SIZE;
 
 	return 0;
 
@@ -2523,7 +2689,7 @@
 				tpc_id < TPC_NUMBER_OF_ENGINES;
 				tpc_id++, tpc_offset += TPC_CFG_OFFSET) {
 		/* Mask all arithmetic interrupts from TPC */
-		WREG32(mmTPC0_CFG_TPC_INTR_MASK + tpc_offset, 0x8FFF);
+		WREG32(mmTPC0_CFG_TPC_INTR_MASK + tpc_offset, 0x8FFE);
 		/* Set 16 cache lines */
 		WREG32_FIELD(TPC0_CFG_MSS_CONFIG, tpc_offset,
 				ICACHE_FETCH_LINE_NUM, 2);
@@ -3670,7 +3836,7 @@
 	WREG32(mmPSOC_TIMESTAMP_BASE - CFG_BASE, 0);
 }
 
-static void gaudi_halt_engines(struct hl_device *hdev, bool hard_reset)
+static void gaudi_halt_engines(struct hl_device *hdev, bool hard_reset, bool fw_reset)
 {
 	u32 wait_timeout_ms;
 
@@ -3682,6 +3848,9 @@
 	else
 		wait_timeout_ms = GAUDI_RESET_WAIT_MSEC;
 
+	if (fw_reset)
+		goto skip_engines;
+
 	gaudi_stop_nic_qmans(hdev);
 	gaudi_stop_mme_qmans(hdev);
 	gaudi_stop_tpc_qmans(hdev);
@@ -3707,6 +3876,7 @@
 
 	gaudi_disable_timestamp(hdev);
 
+skip_engines:
 	gaudi_disable_msi(hdev);
 }
 
@@ -3739,6 +3909,9 @@
 	WREG32(mmSTLB_CACHE_INV_BASE_39_8, MMU_CACHE_MNG_ADDR >> 8);
 	WREG32(mmSTLB_CACHE_INV_BASE_49_40, MMU_CACHE_MNG_ADDR >> 40);
 
+	/* mem cache invalidation */
+	WREG32(mmSTLB_MEM_CACHE_INVALIDATION, 1);
+
 	hdev->asic_funcs->mmu_invalidate_cache(hdev, true, 0);
 
 	WREG32(mmMMU_UP_MMU_ENABLE, 1);
@@ -4071,7 +4244,7 @@
 	return rc;
 }
 
-static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset)
+static void gaudi_hw_fini(struct hl_device *hdev, bool hard_reset, bool fw_reset)
 {
 	struct cpu_dyn_regs *dyn_regs =
 			&hdev->fw_loader.dynamic_loader.comm_desc.cpu_dyn_regs;
@@ -4092,6 +4265,14 @@
 		cpu_timeout_ms = GAUDI_CPU_RESET_WAIT_MSEC;
 	}
 
+	if (fw_reset) {
+		dev_info(hdev->dev,
+			"Firmware performs HARD reset, going to wait %dms\n",
+			reset_timeout_ms);
+
+		goto skip_reset;
+	}
+
 	driver_performs_reset = !!(!hdev->asic_prop.fw_security_enabled &&
 					!hdev->asic_prop.hard_reset_done_by_fw);
 
@@ -4168,6 +4349,7 @@
 			reset_timeout_ms);
 	}
 
+skip_reset:
 	/*
 	 * After hard reset, we can't poll the BTM_FSM register because the PSOC
 	 * itself is in reset. Need to wait until the reset is deasserted
@@ -4212,7 +4394,7 @@
 	return gaudi_init_iatu(hdev);
 }
 
-static int gaudi_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
+static int gaudi_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	int rc;
@@ -4621,8 +4803,8 @@
 				"Doing HBM scrubbing for 0x%09llx - 0x%09llx\n",
 				cur_addr, cur_addr + chunk_size);
 
-			WREG32(mmDMA0_CORE_SRC_BASE_LO + dma_offset, 0);
-			WREG32(mmDMA0_CORE_SRC_BASE_HI + dma_offset, 0);
+			WREG32(mmDMA0_CORE_SRC_BASE_LO + dma_offset, 0xdeadbeaf);
+			WREG32(mmDMA0_CORE_SRC_BASE_HI + dma_offset, 0xdeadbeaf);
 			WREG32(mmDMA0_CORE_DST_BASE_LO + dma_offset,
 						lower_32_bits(cur_addr));
 			WREG32(mmDMA0_CORE_DST_BASE_HI + dma_offset,
@@ -5796,78 +5978,6 @@
 	return rc;
 }
 
-static int gaudi_schedule_register_memset(struct hl_device *hdev,
-		u32 hw_queue_id, u64 reg_base, u32 num_regs, u32 val)
-{
-	struct hl_ctx *ctx;
-	struct hl_pending_cb *pending_cb;
-	struct packet_msg_long *pkt;
-	u32 cb_size, ctl;
-	struct hl_cb *cb;
-	int i, rc;
-
-	mutex_lock(&hdev->fpriv_list_lock);
-	ctx = hdev->compute_ctx;
-
-	/* If no compute context available or context is going down
-	 * memset registers directly
-	 */
-	if (!ctx || kref_read(&ctx->refcount) == 0) {
-		rc = gaudi_memset_registers(hdev, reg_base, num_regs, val);
-		mutex_unlock(&hdev->fpriv_list_lock);
-		return rc;
-	}
-
-	mutex_unlock(&hdev->fpriv_list_lock);
-
-	cb_size = (sizeof(*pkt) * num_regs) +
-			sizeof(struct packet_msg_prot) * 2;
-
-	if (cb_size > SZ_2M) {
-		dev_err(hdev->dev, "CB size must be smaller than %uMB", SZ_2M);
-		return -ENOMEM;
-	}
-
-	pending_cb = kzalloc(sizeof(*pending_cb), GFP_KERNEL);
-	if (!pending_cb)
-		return -ENOMEM;
-
-	cb = hl_cb_kernel_create(hdev, cb_size, false);
-	if (!cb) {
-		kfree(pending_cb);
-		return -EFAULT;
-	}
-
-	pkt = cb->kernel_address;
-
-	ctl = FIELD_PREP(GAUDI_PKT_LONG_CTL_OP_MASK, 0); /* write the value */
-	ctl |= FIELD_PREP(GAUDI_PKT_CTL_OPCODE_MASK, PACKET_MSG_LONG);
-	ctl |= FIELD_PREP(GAUDI_PKT_CTL_EB_MASK, 1);
-	ctl |= FIELD_PREP(GAUDI_PKT_CTL_RB_MASK, 1);
-	ctl |= FIELD_PREP(GAUDI_PKT_CTL_MB_MASK, 1);
-
-	for (i = 0; i < num_regs ; i++, pkt++) {
-		pkt->ctl = cpu_to_le32(ctl);
-		pkt->value = cpu_to_le32(val);
-		pkt->addr = cpu_to_le64(reg_base + (i * 4));
-	}
-
-	hl_cb_destroy(hdev, &hdev->kernel_cb_mgr, cb->id << PAGE_SHIFT);
-
-	pending_cb->cb = cb;
-	pending_cb->cb_size = cb_size;
-	/* The queue ID MUST be an external queue ID. Otherwise, we will
-	 * have undefined behavior
-	 */
-	pending_cb->hw_queue_id = hw_queue_id;
-
-	spin_lock(&ctx->pending_cb_lock);
-	list_add_tail(&pending_cb->cb_node, &ctx->pending_cb_list);
-	spin_unlock(&ctx->pending_cb_lock);
-
-	return 0;
-}
-
 static int gaudi_restore_sm_registers(struct hl_device *hdev)
 {
 	u64 base_addr;
@@ -6013,7 +6123,7 @@
 
 static int gaudi_context_switch(struct hl_device *hdev, u32 asid)
 {
-	return gaudi_restore_user_registers(hdev);
+	return 0;
 }
 
 static int gaudi_mmu_clear_pgt_range(struct hl_device *hdev)
@@ -6723,6 +6833,9 @@
 				asid);
 	}
 
+	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER, asid);
+	gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER, asid);
+
 	hdev->asic_funcs->set_clock_gating(hdev);
 
 	mutex_unlock(&gaudi->clk_gate_mutex);
@@ -6772,7 +6885,8 @@
 
 	dma_offset = gaudi_dma_assignment[GAUDI_PCI_DMA_1] * DMA_CORE_OFFSET;
 
-	WREG32_OR(mmDMA0_CORE_PROT + dma_offset, BIT(DMA0_CORE_PROT_VAL_SHIFT));
+	WREG32(mmDMA0_CORE_PROT + dma_offset,
+			BIT(DMA0_CORE_PROT_ERR_VAL_SHIFT) | BIT(DMA0_CORE_PROT_VAL_SHIFT));
 
 	rc = hl_hw_queue_send_cb_no_cmpl(hdev, GAUDI_QUEUE_ID_DMA_0_0,
 					job->job_cb_size, cb->bus_address);
@@ -6793,8 +6907,7 @@
 	}
 
 free_fence_ptr:
-	WREG32_AND(mmDMA0_CORE_PROT + dma_offset,
-			~BIT(DMA0_CORE_PROT_VAL_SHIFT));
+	WREG32(mmDMA0_CORE_PROT + dma_offset, BIT(DMA0_CORE_PROT_ERR_VAL_SHIFT));
 
 	hdev->asic_funcs->asic_dma_pool_free(hdev, (void *) fence_ptr,
 					fence_dma_addr);
@@ -7168,7 +7281,7 @@
 
 	cq_ptr = (((u64) RREG32(cq_ptr_hi)) << 32) | RREG32(cq_ptr_lo);
 	size = RREG32(cq_tsize);
-	dev_info(hdev->dev, "stop on err: stream: %u, addr: %#llx, size: %x\n",
+	dev_info(hdev->dev, "stop on err: stream: %u, addr: %#llx, size: %u\n",
 							stream, cq_ptr, size);
 }
 
@@ -7224,7 +7337,7 @@
 
 		addr = le64_to_cpu(bd->ptr);
 
-		dev_info(hdev->dev, "stop on err PQE(stream %u): ci: %u, addr: %#llx, size: %x\n",
+		dev_info(hdev->dev, "stop on err PQE(stream %u): ci: %u, addr: %#llx, size: %u\n",
 							stream, ci, addr, len);
 
 		/* get previous ci, wrap if needed */
@@ -7326,24 +7439,30 @@
 {
 	u32 index = event_type - GAUDI_EVENT_DMA_IF_SEI_0;
 
+	/* Flip the bits as the enum is ordered in the opposite way */
+	index = (index ^ 0x3) & 0x3;
+
 	switch (sei_data->sei_cause) {
 	case SM_SEI_SO_OVERFLOW:
-		dev_err(hdev->dev,
-			"SM %u SEI Error: SO %u overflow/underflow",
-			index, le32_to_cpu(sei_data->sei_log));
+		dev_err_ratelimited(hdev->dev,
+			"%s SEI Error: SOB Group %u overflow/underflow",
+			gaudi_sync_manager_names[index],
+			le32_to_cpu(sei_data->sei_log));
 		break;
 	case SM_SEI_LBW_4B_UNALIGNED:
-		dev_err(hdev->dev,
-			"SM %u SEI Error: Unaligned 4B LBW access, monitor agent address low - %#x",
-			index, le32_to_cpu(sei_data->sei_log));
+		dev_err_ratelimited(hdev->dev,
+			"%s SEI Error: Unaligned 4B LBW access, monitor agent address low - %#x",
+			gaudi_sync_manager_names[index],
+			le32_to_cpu(sei_data->sei_log));
 		break;
 	case SM_SEI_AXI_RESPONSE_ERR:
-		dev_err(hdev->dev,
-			"SM %u SEI Error: AXI ID %u response error",
-			index, le32_to_cpu(sei_data->sei_log));
+		dev_err_ratelimited(hdev->dev,
+			"%s SEI Error: AXI ID %u response error",
+			gaudi_sync_manager_names[index],
+			le32_to_cpu(sei_data->sei_log));
 		break;
 	default:
-		dev_err(hdev->dev, "Unknown SM SEI cause %u",
+		dev_err_ratelimited(hdev->dev, "Unknown SM SEI cause %u",
 				le32_to_cpu(sei_data->sei_log));
 		break;
 	}
@@ -7358,6 +7477,11 @@
 	bool extract_info_from_fw;
 	int rc;
 
+	if (hdev->asic_prop.fw_security_enabled) {
+		extract_info_from_fw = true;
+		goto extract_ecc_info;
+	}
+
 	switch (event_type) {
 	case GAUDI_EVENT_PCIE_CORE_SERR ... GAUDI_EVENT_PCIE_PHY_DERR:
 	case GAUDI_EVENT_DMA0_SERR_ECC ... GAUDI_EVENT_MMU_DERR:
@@ -7430,6 +7554,7 @@
 		return;
 	}
 
+extract_ecc_info:
 	if (extract_info_from_fw) {
 		ecc_address = le64_to_cpu(ecc_data->ecc_address);
 		ecc_syndrom = le64_to_cpu(ecc_data->ecc_syndrom);
@@ -7806,8 +7931,15 @@
 	u32 ctl = le32_to_cpu(eq_entry->hdr.ctl);
 	u16 event_type = ((ctl & EQ_CTL_EVENT_TYPE_MASK)
 			>> EQ_CTL_EVENT_TYPE_SHIFT);
-	u8 cause;
 	bool reset_required;
+	u8 cause;
+	int rc;
+
+	if (event_type >= GAUDI_EVENT_SIZE) {
+		dev_err(hdev->dev, "Event type %u exceeds maximum of %u",
+				event_type, GAUDI_EVENT_SIZE - 1);
+		return;
+	}
 
 	gaudi->events_stat[event_type]++;
 	gaudi->events_stat_aggregate[event_type]++;
@@ -7880,10 +8012,10 @@
 					tpc_dec_event_to_tpc_id(event_type),
 					"AXI_SLV_DEC_Error");
 		if (reset_required) {
-			dev_err(hdev->dev, "hard reset required due to %s\n",
+			dev_err(hdev->dev, "reset required due to %s\n",
 				gaudi_irq_map_table[event_type].name);
 
-			goto reset_device;
+			hl_device_reset(hdev, 0);
 		} else {
 			hl_fw_unmask_irq(hdev, event_type);
 		}
@@ -7902,10 +8034,10 @@
 					tpc_krn_event_to_tpc_id(event_type),
 					"KRN_ERR");
 		if (reset_required) {
-			dev_err(hdev->dev, "hard reset required due to %s\n",
+			dev_err(hdev->dev, "reset required due to %s\n",
 				gaudi_irq_map_table[event_type].name);
 
-			goto reset_device;
+			hl_device_reset(hdev, 0);
 		} else {
 			hl_fw_unmask_irq(hdev, event_type);
 		}
@@ -7993,6 +8125,10 @@
 		gaudi_print_irq_info(hdev, event_type, false);
 		gaudi_print_sm_sei_info(hdev, event_type,
 					&eq_entry->sm_sei_data);
+		rc = hl_state_dump(hdev);
+		if (rc)
+			dev_err(hdev->dev,
+				"Error during system state dump %d\n", rc);
 		hl_fw_unmask_irq(hdev, event_type);
 		break;
 
@@ -8031,7 +8167,9 @@
 	return;
 
 reset_device:
-	if (hdev->hard_reset_on_fw_events)
+	if (hdev->asic_prop.fw_security_enabled)
+		hl_device_reset(hdev, HL_RESET_HARD | HL_RESET_FW);
+	else if (hdev->hard_reset_on_fw_events)
 		hl_device_reset(hdev, HL_RESET_HARD);
 	else
 		hl_fw_unmask_irq(hdev, event_type);
@@ -8563,11 +8701,20 @@
 
 static int gaudi_ctx_init(struct hl_ctx *ctx)
 {
+	int rc;
+
 	if (ctx->asid == HL_KERNEL_ASID_ID)
 		return 0;
 
-	gaudi_mmu_prepare(ctx->hdev, ctx->asid);
-	return gaudi_internal_cb_pool_init(ctx->hdev, ctx);
+	rc = gaudi_internal_cb_pool_init(ctx->hdev, ctx);
+	if (rc)
+		return rc;
+
+	rc = gaudi_restore_user_registers(ctx->hdev);
+	if (rc)
+		gaudi_internal_cb_pool_fini(ctx->hdev, ctx);
+
+	return rc;
 }
 
 static void gaudi_ctx_fini(struct hl_ctx *ctx)
@@ -8596,6 +8743,11 @@
 			sizeof(struct packet_msg_prot) * 2;
 }
 
+static u32 gaudi_get_sob_addr(struct hl_device *hdev, u32 sob_id)
+{
+	return mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0 + (sob_id * 4);
+}
+
 static u32 gaudi_gen_signal_cb(struct hl_device *hdev, void *data, u16 sob_id,
 				u32 size, bool eb)
 {
@@ -8902,16 +9054,12 @@
 static void gaudi_reset_sob(struct hl_device *hdev, void *data)
 {
 	struct hl_hw_sob *hw_sob = (struct hl_hw_sob *) data;
-	int rc;
 
 	dev_dbg(hdev->dev, "reset SOB, q_idx: %d, sob_id: %d\n", hw_sob->q_idx,
 		hw_sob->sob_id);
 
-	rc = gaudi_schedule_register_memset(hdev, hw_sob->q_idx,
-			CFG_BASE + mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0 +
-			hw_sob->sob_id * 4, 1, 0);
-	if (rc)
-		dev_err(hdev->dev, "failed resetting sob %u", hw_sob->sob_id);
+	WREG32(mmSYNC_MNGR_W_S_SYNC_MNGR_OBJS_SOB_OBJ_0 +
+			hw_sob->sob_id * 4, 0);
 
 	kref_init(&hw_sob->kref);
 }
@@ -8977,6 +9125,280 @@
 	}
 }
 
+static int gaudi_add_sync_to_engine_map_entry(
+	struct hl_sync_to_engine_map *map, u32 reg_value,
+	enum hl_sync_engine_type engine_type, u32 engine_id)
+{
+	struct hl_sync_to_engine_map_entry *entry;
+
+	/* Reg value represents a partial address of sync object,
+	 * it is used as unique identifier. For this we need to
+	 * clear the cutoff cfg base bits from the value.
+	 */
+	if (reg_value == 0 || reg_value == 0xffffffff)
+		return 0;
+	reg_value -= (u32)CFG_BASE;
+
+	/* create a new hash entry */
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+	entry->engine_type = engine_type;
+	entry->engine_id = engine_id;
+	entry->sync_id = reg_value;
+	hash_add(map->tb, &entry->node, reg_value);
+
+	return 0;
+}
+
+static int gaudi_gen_sync_to_engine_map(struct hl_device *hdev,
+				struct hl_sync_to_engine_map *map)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	struct gaudi_device *gaudi = hdev->asic_specific;
+	int i, j, rc;
+	u32 reg_value;
+
+	/* Iterate over TPC engines */
+	for (i = 0; i < sds->props[SP_NUM_OF_TPC_ENGINES]; ++i) {
+		/* TPC registered must be accessed with clock gating disabled */
+		mutex_lock(&gaudi->clk_gate_mutex);
+		hdev->asic_funcs->disable_clock_gating(hdev);
+
+		reg_value = RREG32(sds->props[SP_TPC0_CFG_SO] +
+					sds->props[SP_NEXT_TPC] * i);
+
+		/* We can reenable clock_gating */
+		hdev->asic_funcs->set_clock_gating(hdev);
+		mutex_unlock(&gaudi->clk_gate_mutex);
+
+		rc = gaudi_add_sync_to_engine_map_entry(map, reg_value,
+							ENGINE_TPC, i);
+		if (rc)
+			goto free_sync_to_engine_map;
+	}
+
+	/* Iterate over MME engines */
+	for (i = 0; i < sds->props[SP_NUM_OF_MME_ENGINES]; ++i) {
+		for (j = 0; j < sds->props[SP_SUB_MME_ENG_NUM]; ++j) {
+			/* MME registered must be accessed with clock gating
+			 * disabled
+			 */
+			mutex_lock(&gaudi->clk_gate_mutex);
+			hdev->asic_funcs->disable_clock_gating(hdev);
+
+			reg_value = RREG32(sds->props[SP_MME_CFG_SO] +
+						sds->props[SP_NEXT_MME] * i +
+						j * sizeof(u32));
+
+			/* We can reenable clock_gating */
+			hdev->asic_funcs->set_clock_gating(hdev);
+			mutex_unlock(&gaudi->clk_gate_mutex);
+
+			rc = gaudi_add_sync_to_engine_map_entry(
+				map, reg_value, ENGINE_MME,
+				i * sds->props[SP_SUB_MME_ENG_NUM] + j);
+			if (rc)
+				goto free_sync_to_engine_map;
+		}
+	}
+
+	/* Iterate over DMA engines */
+	for (i = 0; i < sds->props[SP_NUM_OF_DMA_ENGINES]; ++i) {
+		reg_value = RREG32(sds->props[SP_DMA_CFG_SO] +
+					sds->props[SP_DMA_QUEUES_OFFSET] * i);
+		rc = gaudi_add_sync_to_engine_map_entry(map, reg_value,
+							ENGINE_DMA, i);
+		if (rc)
+			goto free_sync_to_engine_map;
+	}
+
+	return 0;
+
+free_sync_to_engine_map:
+	hl_state_dump_free_sync_to_engine_map(map);
+
+	return rc;
+}
+
+static int gaudi_monitor_valid(struct hl_mon_state_dump *mon)
+{
+	return FIELD_GET(
+		SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_VALID_MASK,
+		mon->status);
+}
+
+static void gaudi_fill_sobs_from_mon(char *sobs, struct hl_mon_state_dump *mon)
+{
+	const size_t max_write = 10;
+	u32 gid, mask, sob;
+	int i, offset;
+
+	/* Sync object ID is calculated as follows:
+	 * (8 * group_id + cleared bits in mask)
+	 */
+	gid = FIELD_GET(SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_MASK,
+			mon->arm_data);
+	mask = FIELD_GET(SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_MASK,
+			mon->arm_data);
+
+	for (i = 0, offset = 0; mask && offset < MONITOR_SOB_STRING_SIZE -
+		max_write; mask >>= 1, i++) {
+		if (!(mask & 1)) {
+			sob = gid * MONITOR_MAX_SOBS + i;
+
+			if (offset > 0)
+				offset += snprintf(sobs + offset, max_write,
+							", ");
+
+			offset += snprintf(sobs + offset, max_write, "%u", sob);
+		}
+	}
+}
+
+static int gaudi_print_single_monitor(char **buf, size_t *size, size_t *offset,
+				struct hl_device *hdev,
+				struct hl_mon_state_dump *mon)
+{
+	const char *name;
+	char scratch_buf1[BIN_REG_STRING_SIZE],
+		scratch_buf2[BIN_REG_STRING_SIZE];
+	char monitored_sobs[MONITOR_SOB_STRING_SIZE] = {0};
+
+	name = hl_state_dump_get_monitor_name(hdev, mon);
+	if (!name)
+		name = "";
+
+	gaudi_fill_sobs_from_mon(monitored_sobs, mon);
+
+	return hl_snprintf_resize(
+		buf, size, offset,
+		"Mon id: %u%s, wait for group id: %u mask %s to reach val: %u and write %u to address 0x%llx. Pending: %s. Means sync objects [%s] are being monitored.",
+		mon->id, name,
+		FIELD_GET(SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_MASK,
+				mon->arm_data),
+		hl_format_as_binary(
+			scratch_buf1, sizeof(scratch_buf1),
+			FIELD_GET(
+				SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_MASK,
+				mon->arm_data)),
+		FIELD_GET(SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOD_MASK,
+				mon->arm_data),
+		mon->wr_data,
+		(((u64)mon->wr_addr_high) << 32) | mon->wr_addr_low,
+		hl_format_as_binary(
+			scratch_buf2, sizeof(scratch_buf2),
+			FIELD_GET(
+				SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_PENDING_MASK,
+				mon->status)),
+		monitored_sobs);
+}
+
+
+static int gaudi_print_fences_single_engine(
+	struct hl_device *hdev, u64 base_offset, u64 status_base_offset,
+	enum hl_sync_engine_type engine_type, u32 engine_id, char **buf,
+	size_t *size, size_t *offset)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	int rc = -ENOMEM, i;
+	u32 *statuses, *fences;
+
+	statuses = kcalloc(sds->props[SP_ENGINE_NUM_OF_QUEUES],
+			sizeof(*statuses), GFP_KERNEL);
+	if (!statuses)
+		goto out;
+
+	fences = kcalloc(sds->props[SP_ENGINE_NUM_OF_FENCES] *
+				sds->props[SP_ENGINE_NUM_OF_QUEUES],
+			 sizeof(*fences), GFP_KERNEL);
+	if (!fences)
+		goto free_status;
+
+	for (i = 0; i < sds->props[SP_ENGINE_NUM_OF_FENCES]; ++i)
+		statuses[i] = RREG32(status_base_offset + i * sizeof(u32));
+
+	for (i = 0; i < sds->props[SP_ENGINE_NUM_OF_FENCES] *
+				sds->props[SP_ENGINE_NUM_OF_QUEUES]; ++i)
+		fences[i] = RREG32(base_offset + i * sizeof(u32));
+
+	/* The actual print */
+	for (i = 0; i < sds->props[SP_ENGINE_NUM_OF_QUEUES]; ++i) {
+		u32 fence_id;
+		u64 fence_cnt, fence_rdata;
+		const char *engine_name;
+
+		if (!FIELD_GET(TPC0_QM_CP_STS_0_FENCE_IN_PROGRESS_MASK,
+			statuses[i]))
+			continue;
+
+		fence_id =
+			FIELD_GET(TPC0_QM_CP_STS_0_FENCE_ID_MASK, statuses[i]);
+		fence_cnt = base_offset + CFG_BASE +
+			sizeof(u32) *
+			(i + fence_id * sds->props[SP_ENGINE_NUM_OF_QUEUES]);
+		fence_rdata = fence_cnt - sds->props[SP_FENCE0_CNT_OFFSET] +
+				sds->props[SP_FENCE0_RDATA_OFFSET];
+		engine_name = hl_sync_engine_to_string(engine_type);
+
+		rc = hl_snprintf_resize(
+			buf, size, offset,
+			"%s%u, stream %u: fence id %u cnt = 0x%llx (%s%u_QM.CP_FENCE%u_CNT_%u) rdata = 0x%llx (%s%u_QM.CP_FENCE%u_RDATA_%u) value = %u, cp_status = %u\n",
+			engine_name, engine_id,
+			i, fence_id,
+			fence_cnt, engine_name, engine_id, fence_id, i,
+			fence_rdata, engine_name, engine_id, fence_id, i,
+			fences[fence_id],
+			statuses[i]);
+		if (rc)
+			goto free_fences;
+	}
+
+	rc = 0;
+
+free_fences:
+	kfree(fences);
+free_status:
+	kfree(statuses);
+out:
+	return rc;
+}
+
+
+static struct hl_state_dump_specs_funcs gaudi_state_dump_funcs = {
+	.monitor_valid = gaudi_monitor_valid,
+	.print_single_monitor = gaudi_print_single_monitor,
+	.gen_sync_to_engine_map = gaudi_gen_sync_to_engine_map,
+	.print_fences_single_engine = gaudi_print_fences_single_engine,
+};
+
+static void gaudi_state_dump_init(struct hl_device *hdev)
+{
+	struct hl_state_dump_specs *sds = &hdev->state_dump_specs;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(gaudi_so_id_to_str); ++i)
+		hash_add(sds->so_id_to_str_tb,
+			&gaudi_so_id_to_str[i].node,
+			gaudi_so_id_to_str[i].id);
+
+	for (i = 0; i < ARRAY_SIZE(gaudi_monitor_id_to_str); ++i)
+		hash_add(sds->monitor_id_to_str_tb,
+			&gaudi_monitor_id_to_str[i].node,
+			gaudi_monitor_id_to_str[i].id);
+
+	sds->props = gaudi_state_dump_specs_props;
+
+	sds->sync_namager_names = gaudi_sync_manager_names;
+
+	sds->funcs = gaudi_state_dump_funcs;
+}
+
+static u32 *gaudi_get_stream_master_qid_arr(void)
+{
+	return gaudi_stream_master;
+}
+
 static const struct hl_asic_funcs gaudi_funcs = {
 	.early_init = gaudi_early_init,
 	.early_fini = gaudi_early_fini,
@@ -8989,7 +9411,7 @@
 	.halt_engines = gaudi_halt_engines,
 	.suspend = gaudi_suspend,
 	.resume = gaudi_resume,
-	.cb_mmap = gaudi_cb_mmap,
+	.mmap = gaudi_mmap,
 	.ring_doorbell = gaudi_ring_doorbell,
 	.pqe_write = gaudi_pqe_write,
 	.asic_dma_alloc_coherent = gaudi_dma_alloc_coherent,
@@ -9062,7 +9484,11 @@
 	.enable_events_from_fw = gaudi_enable_events_from_fw,
 	.map_pll_idx_to_fw_idx = gaudi_map_pll_idx_to_fw_idx,
 	.init_firmware_loader = gaudi_init_firmware_loader,
-	.init_cpu_scrambler_dram = gaudi_init_scrambler_hbm
+	.init_cpu_scrambler_dram = gaudi_init_scrambler_hbm,
+	.state_dump_init = gaudi_state_dump_init,
+	.get_sob_addr = gaudi_get_sob_addr,
+	.set_pci_memory_regions = gaudi_set_pci_memory_regions,
+	.get_stream_master_qid_arr = gaudi_get_stream_master_qid_arr
 };
 
 /**
diff --git a/drivers/misc/habanalabs/gaudi/gaudiP.h b/drivers/misc/habanalabs/gaudi/gaudiP.h
index 957bf37..bbbf1c3 100644
--- a/drivers/misc/habanalabs/gaudi/gaudiP.h
+++ b/drivers/misc/habanalabs/gaudi/gaudiP.h
@@ -36,6 +36,8 @@
 #define NUMBER_OF_INTERRUPTS		(NUMBER_OF_CMPLT_QUEUES + \
 						NUMBER_OF_CPU_HW_QUEUES)
 
+#define GAUDI_STREAM_MASTER_ARR_SIZE	8
+
 #if (NUMBER_OF_INTERRUPTS > GAUDI_MSI_ENTRIES)
 #error "Number of MSI interrupts must be smaller or equal to GAUDI_MSI_ENTRIES"
 #endif
@@ -50,6 +52,8 @@
 #define DC_POWER_DEFAULT_PCI		60000		/* 60W */
 #define DC_POWER_DEFAULT_PMC		60000		/* 60W */
 
+#define DC_POWER_DEFAULT_PMC_SEC	97000		/* 97W */
+
 #define GAUDI_CPU_TIMEOUT_USEC		30000000	/* 30s */
 
 #define TPC_ENABLED_MASK		0xFF
@@ -62,7 +66,7 @@
 
 #define DMA_MAX_TRANSFER_SIZE		U32_MAX
 
-#define GAUDI_DEFAULT_CARD_NAME		"HL2000"
+#define GAUDI_DEFAULT_CARD_NAME		"HL205"
 
 #define GAUDI_MAX_PENDING_CS		SZ_16K
 
@@ -117,6 +121,7 @@
 	(((mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_511 - \
 	mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_0) + 4) >> 2)
 
+#define MONITOR_MAX_SOBS	8
 
 /* DRAM Memory Map */
 
@@ -200,6 +205,18 @@
 #define HW_CAP_TPC_MASK		GENMASK(31, 24)
 #define HW_CAP_TPC_SHIFT	24
 
+#define NEXT_SYNC_OBJ_ADDR_INTERVAL \
+	(mmSYNC_MNGR_W_N_SYNC_MNGR_OBJS_SOB_OBJ_0 - \
+	 mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_0)
+#define NUM_OF_MME_ENGINES			2
+#define NUM_OF_MME_SUB_ENGINES		2
+#define NUM_OF_TPC_ENGINES			8
+#define NUM_OF_DMA_ENGINES			8
+#define NUM_OF_QUEUES				5
+#define NUM_OF_STREAMS				4
+#define NUM_OF_FENCES				4
+
+
 #define GAUDI_CPU_PCI_MSB_ADDR(addr)	(((addr) & GENMASK_ULL(49, 39)) >> 39)
 #define GAUDI_PCI_TO_CPU_ADDR(addr)			\
 	do {						\
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
index c2a27ed..5349c1b 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_coresight.c
@@ -622,11 +622,6 @@
 			return -EINVAL;
 		}
 
-		gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_ARUSER,
-						hdev->compute_ctx->asid);
-		gaudi_mmu_prepare_reg(hdev, mmPSOC_GLOBAL_CONF_TRACE_AWUSER,
-						hdev->compute_ctx->asid);
-
 		msb = upper_32_bits(input->buffer_address) >> 8;
 		msb &= PSOC_GLOBAL_CONF_TRACE_ADDR_MSB_MASK;
 		WREG32(mmPSOC_GLOBAL_CONF_TRACE_ADDR, msb);
diff --git a/drivers/misc/habanalabs/gaudi/gaudi_security.c b/drivers/misc/habanalabs/gaudi/gaudi_security.c
index 0d3240f..cb265c0 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi_security.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi_security.c
@@ -9559,6 +9559,7 @@
 	mask |= 1U << ((mmTPC0_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC0_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC0_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC0_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC0_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC0_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC0_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -10013,6 +10014,7 @@
 	mask |= 1U << ((mmTPC1_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC1_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC1_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC1_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC1_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC1_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC1_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -10466,6 +10468,7 @@
 	mask |= 1U << ((mmTPC2_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC2_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC2_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC2_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC2_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC2_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC2_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -10919,6 +10922,7 @@
 	mask |= 1U << ((mmTPC3_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC3_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC3_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC3_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC3_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC3_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC3_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -11372,6 +11376,7 @@
 	mask |= 1U << ((mmTPC4_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC4_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC4_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC4_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC4_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC4_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC4_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -11825,6 +11830,7 @@
 	mask |= 1U << ((mmTPC5_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC5_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC5_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC5_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC5_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC5_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC5_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -12280,6 +12286,7 @@
 	mask |= 1U << ((mmTPC6_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC6_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC6_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC6_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC6_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC6_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC6_CFG_MSS_CONFIG & 0x7F) >> 2);
@@ -12735,6 +12742,7 @@
 	mask |= 1U << ((mmTPC7_CFG_CFG_BASE_ADDRESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC7_CFG_CFG_SUBTRACT_VALUE & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC7_CFG_TPC_STALL & 0x7F) >> 2);
+	mask |= 1U << ((mmTPC7_CFG_ICACHE_BASE_ADDERESS_HIGH & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC7_CFG_RD_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC7_CFG_WR_RATE_LIMIT & 0x7F) >> 2);
 	mask |= 1U << ((mmTPC7_CFG_MSS_CONFIG & 0x7F) >> 2);
diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c
index 755e08c..031c184 100644
--- a/drivers/misc/habanalabs/goya/goya.c
+++ b/drivers/misc/habanalabs/goya/goya.c
@@ -350,6 +350,8 @@
 	GOYA_ASYNC_EVENT_ID_FIX_THERMAL_ENV_E
 };
 
+static s64 goya_state_dump_specs_props[SP_MAX] = {0};
+
 static int goya_mmu_clear_pgt_range(struct hl_device *hdev);
 static int goya_mmu_set_dram_default_page(struct hl_device *hdev);
 static int goya_mmu_add_mappings_for_device_cpu(struct hl_device *hdev);
@@ -387,6 +389,7 @@
 		prop->hw_queues_props[i].cb_alloc_flags = CB_ALLOC_USER;
 	}
 
+	prop->device_dma_offset_for_host_access = HOST_PHYS_BASE;
 	prop->completion_queues_count = NUMBER_OF_CMPLT_QUEUES;
 
 	prop->dram_base_address = DRAM_PHYS_BASE;
@@ -466,6 +469,8 @@
 	prop->hard_reset_done_by_fw = false;
 	prop->gic_interrupts_enable = true;
 
+	prop->server_type = HL_SERVER_TYPE_UNKNOWN;
+
 	return 0;
 }
 
@@ -649,14 +654,14 @@
 					GOYA_BOOT_FIT_REQ_TIMEOUT_USEC);
 	if (rc) {
 		if (hdev->reset_on_preboot_fail)
-			hdev->asic_funcs->hw_fini(hdev, true);
+			hdev->asic_funcs->hw_fini(hdev, true, false);
 		goto pci_fini;
 	}
 
 	if (goya_get_hw_state(hdev) == HL_DEVICE_HW_STATE_DIRTY) {
 		dev_info(hdev->dev,
 			"H/W state is dirty, must reset before initializing\n");
-		hdev->asic_funcs->hw_fini(hdev, true);
+		hdev->asic_funcs->hw_fini(hdev, true, false);
 	}
 
 	if (!hdev->pldm) {
@@ -955,8 +960,9 @@
 	hdev->supports_coresight = true;
 	hdev->supports_soft_reset = true;
 	hdev->allow_external_soft_reset = true;
+	hdev->supports_wait_for_multi_cs = false;
 
-	goya_set_pci_memory_regions(hdev);
+	hdev->asic_funcs->set_pci_memory_regions(hdev);
 
 	return 0;
 
@@ -2374,7 +2380,7 @@
 	WREG32(mmPSOC_TIMESTAMP_BASE - CFG_BASE, 0);
 }
 
-static void goya_halt_engines(struct hl_device *hdev, bool hard_reset)
+static void goya_halt_engines(struct hl_device *hdev, bool hard_reset, bool fw_reset)
 {
 	u32 wait_timeout_ms;
 
@@ -2493,6 +2499,7 @@
 	struct fw_load_mgr *fw_loader = &hdev->fw_loader;
 
 	/* fill common fields */
+	fw_loader->linux_loaded = false;
 	fw_loader->boot_fit_img.image_name = GOYA_BOOT_FIT_FILE;
 	fw_loader->linux_img.image_name = GOYA_LINUX_FW_FILE;
 	fw_loader->cpu_timeout = GOYA_CPU_TIMEOUT_USEC;
@@ -2696,14 +2703,7 @@
 	return rc;
 }
 
-/*
- * goya_hw_fini - Goya hardware tear-down code
- *
- * @hdev: pointer to hl_device structure
- * @hard_reset: should we do hard reset to all engines or just reset the
- *              compute/dma engines
- */
-static void goya_hw_fini(struct hl_device *hdev, bool hard_reset)
+static void goya_hw_fini(struct hl_device *hdev, bool hard_reset, bool fw_reset)
 {
 	struct goya_device *goya = hdev->asic_specific;
 	u32 reset_timeout_ms, cpu_timeout_ms, status;
@@ -2796,7 +2796,7 @@
 	return goya_init_iatu(hdev);
 }
 
-static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
+static int goya_mmap(struct hl_device *hdev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size)
 {
 	int rc;
@@ -4797,6 +4797,12 @@
 				>> EQ_CTL_EVENT_TYPE_SHIFT);
 	struct goya_device *goya = hdev->asic_specific;
 
+	if (event_type >= GOYA_ASYNC_EVENT_ID_SIZE) {
+		dev_err(hdev->dev, "Event type %u exceeds maximum of %u",
+				event_type, GOYA_ASYNC_EVENT_ID_SIZE - 1);
+		return;
+	}
+
 	goya->events_stat[event_type]++;
 	goya->events_stat_aggregate[event_type]++;
 
@@ -5475,14 +5481,14 @@
 	return device_time | RREG32(mmPSOC_TIMESTAMP_CNTCVL);
 }
 
-static void goya_collective_wait_init_cs(struct hl_cs *cs)
+static int goya_collective_wait_init_cs(struct hl_cs *cs)
 {
-
+	return 0;
 }
 
 static int goya_collective_wait_create_jobs(struct hl_device *hdev,
 		struct hl_ctx *ctx, struct hl_cs *cs, u32 wait_queue_id,
-		u32 collective_engine_id)
+		u32 collective_engine_id, u32 encaps_signal_offset)
 {
 	return -EINVAL;
 }
@@ -5524,6 +5530,62 @@
 	}
 }
 
+static int goya_gen_sync_to_engine_map(struct hl_device *hdev,
+				struct hl_sync_to_engine_map *map)
+{
+	/* Not implemented */
+	return 0;
+}
+
+static int goya_monitor_valid(struct hl_mon_state_dump *mon)
+{
+	/* Not implemented */
+	return 0;
+}
+
+static int goya_print_single_monitor(char **buf, size_t *size, size_t *offset,
+				struct hl_device *hdev,
+				struct hl_mon_state_dump *mon)
+{
+	/* Not implemented */
+	return 0;
+}
+
+
+static int goya_print_fences_single_engine(
+	struct hl_device *hdev, u64 base_offset, u64 status_base_offset,
+	enum hl_sync_engine_type engine_type, u32 engine_id, char **buf,
+	size_t *size, size_t *offset)
+{
+	/* Not implemented */
+	return 0;
+}
+
+
+static struct hl_state_dump_specs_funcs goya_state_dump_funcs = {
+	.monitor_valid = goya_monitor_valid,
+	.print_single_monitor = goya_print_single_monitor,
+	.gen_sync_to_engine_map = goya_gen_sync_to_engine_map,
+	.print_fences_single_engine = goya_print_fences_single_engine,
+};
+
+static void goya_state_dump_init(struct hl_device *hdev)
+{
+	/* Not implemented */
+	hdev->state_dump_specs.props = goya_state_dump_specs_props;
+	hdev->state_dump_specs.funcs = goya_state_dump_funcs;
+}
+
+static u32 goya_get_sob_addr(struct hl_device *hdev, u32 sob_id)
+{
+	return 0;
+}
+
+static u32 *goya_get_stream_master_qid_arr(void)
+{
+	return NULL;
+}
+
 static const struct hl_asic_funcs goya_funcs = {
 	.early_init = goya_early_init,
 	.early_fini = goya_early_fini,
@@ -5536,7 +5598,7 @@
 	.halt_engines = goya_halt_engines,
 	.suspend = goya_suspend,
 	.resume = goya_resume,
-	.cb_mmap = goya_cb_mmap,
+	.mmap = goya_mmap,
 	.ring_doorbell = goya_ring_doorbell,
 	.pqe_write = goya_pqe_write,
 	.asic_dma_alloc_coherent = goya_dma_alloc_coherent,
@@ -5609,7 +5671,11 @@
 	.enable_events_from_fw = goya_enable_events_from_fw,
 	.map_pll_idx_to_fw_idx = goya_map_pll_idx_to_fw_idx,
 	.init_firmware_loader = goya_init_firmware_loader,
-	.init_cpu_scrambler_dram = goya_cpu_init_scrambler_dram
+	.init_cpu_scrambler_dram = goya_cpu_init_scrambler_dram,
+	.state_dump_init = goya_state_dump_init,
+	.get_sob_addr = &goya_get_sob_addr,
+	.set_pci_memory_regions = goya_set_pci_memory_regions,
+	.get_stream_master_qid_arr = goya_get_stream_master_qid_arr,
 };
 
 /*
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index 80b1d5a..9ff6a44 100644
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -98,6 +98,18 @@
 	__u8 pad[7];
 };
 
+enum hl_pcie_addr_dec_cause {
+	PCIE_ADDR_DEC_HBW_ERR_RESP,
+	PCIE_ADDR_DEC_LBW_ERR_RESP,
+	PCIE_ADDR_DEC_TLP_BLOCKED_BY_RR
+};
+
+struct hl_eq_pcie_addr_dec_data {
+	/* enum hl_pcie_addr_dec_cause */
+	__u8 addr_dec_cause;
+	__u8 pad[7];
+};
+
 struct hl_eq_entry {
 	struct hl_eq_header hdr;
 	union {
@@ -106,6 +118,7 @@
 		struct hl_eq_sm_sei_data sm_sei_data;
 		struct cpucp_pkt_sync_err pkt_sync_err;
 		struct hl_eq_fw_alive fw_alive;
+		struct hl_eq_pcie_addr_dec_data pcie_addr_dec_data;
 		__le64 data[7];
 	};
 };
@@ -116,7 +129,7 @@
 #define EQ_CTL_READY_MASK		0x80000000
 
 #define EQ_CTL_EVENT_TYPE_SHIFT		16
-#define EQ_CTL_EVENT_TYPE_MASK		0x03FF0000
+#define EQ_CTL_EVENT_TYPE_MASK		0x0FFF0000
 
 #define EQ_CTL_INDEX_SHIFT		0
 #define EQ_CTL_INDEX_MASK		0x0000FFFF
@@ -300,7 +313,7 @@
  *       The packet's arguments specify the desired sensor and the field to
  *       set.
  *
- * CPUCP_PACKET_PCIE_THROUGHPUT_GET
+ * CPUCP_PACKET_PCIE_THROUGHPUT_GET -
  *       Get throughput of PCIe.
  *       The packet's arguments specify the transaction direction (TX/RX).
  *       The window measurement is 10[msec], and the return value is in KB/sec.
@@ -309,19 +322,19 @@
  *       Replay count measures number of "replay" events, which is basicly
  *       number of retries done by PCIe.
  *
- * CPUCP_PACKET_TOTAL_ENERGY_GET
+ * CPUCP_PACKET_TOTAL_ENERGY_GET -
  *       Total Energy is measurement of energy from the time FW Linux
  *       is loaded. It is calculated by multiplying the average power
  *       by time (passed from armcp start). The units are in MilliJouls.
  *
- * CPUCP_PACKET_PLL_INFO_GET
+ * CPUCP_PACKET_PLL_INFO_GET -
  *       Fetch frequencies of PLL from the required PLL IP.
  *       The packet's arguments specify the device PLL type
  *       Pll type is the PLL from device pll_index enum.
  *       The result is composed of 4 outputs, each is 16-bit
  *       frequency in MHz.
  *
- * CPUCP_PACKET_POWER_GET
+ * CPUCP_PACKET_POWER_GET -
  *       Fetch the present power consumption of the device (Current * Voltage).
  *
  * CPUCP_PACKET_NIC_PFC_SET -
@@ -345,6 +358,24 @@
  * CPUCP_PACKET_MSI_INFO_SET -
  *       set the index number for each supported msi type going from
  *       host to device
+ *
+ * CPUCP_PACKET_NIC_XPCS91_REGS_GET -
+ *       Fetch the un/correctable counters values from the NIC MAC.
+ *
+ * CPUCP_PACKET_NIC_STAT_REGS_GET -
+ *       Fetch various NIC MAC counters from the NIC STAT.
+ *
+ * CPUCP_PACKET_NIC_STAT_REGS_CLR -
+ *       Clear the various NIC MAC counters in the NIC STAT.
+ *
+ * CPUCP_PACKET_NIC_STAT_REGS_ALL_GET -
+ *       Fetch all NIC MAC counters from the NIC STAT.
+ *
+ * CPUCP_PACKET_IS_IDLE_CHECK -
+ *       Check if the device is IDLE in regard to the DMA/compute engines
+ *       and QMANs. The f/w will return a bitmask where each bit represents
+ *       a different engine or QMAN according to enum cpucp_idle_mask.
+ *       The bit will be 1 if the engine is NOT idle.
  */
 
 enum cpucp_packet_id {
@@ -385,6 +416,11 @@
 	CPUCP_PACKET_NIC_LPBK_SET,		/* internal */
 	CPUCP_PACKET_NIC_MAC_CFG,		/* internal */
 	CPUCP_PACKET_MSI_INFO_SET,		/* internal */
+	CPUCP_PACKET_NIC_XPCS91_REGS_GET,	/* internal */
+	CPUCP_PACKET_NIC_STAT_REGS_GET,		/* internal */
+	CPUCP_PACKET_NIC_STAT_REGS_CLR,		/* internal */
+	CPUCP_PACKET_NIC_STAT_REGS_ALL_GET,	/* internal */
+	CPUCP_PACKET_IS_IDLE_CHECK,		/* internal */
 };
 
 #define CPUCP_PACKET_FENCE_VAL	0xFE8CE7A5
@@ -414,6 +450,11 @@
 #define CPUCP_PKT_VAL_LPBK_IN2_SHIFT	1
 #define CPUCP_PKT_VAL_LPBK_IN2_MASK	0x000000000000001Eull
 
+#define CPUCP_PKT_VAL_MAC_CNT_IN1_SHIFT	0
+#define CPUCP_PKT_VAL_MAC_CNT_IN1_MASK	0x0000000000000001ull
+#define CPUCP_PKT_VAL_MAC_CNT_IN2_SHIFT	1
+#define CPUCP_PKT_VAL_MAC_CNT_IN2_MASK	0x00000000FFFFFFFEull
+
 /* heartbeat status bits */
 #define CPUCP_PKT_HB_STATUS_EQ_FAULT_SHIFT		0
 #define CPUCP_PKT_HB_STATUS_EQ_FAULT_MASK		0x00000001
@@ -467,7 +508,8 @@
 		__le32 status_mask;
 	};
 
-	__le32 reserved;
+	/* For NIC requests */
+	__le32 port_index;
 };
 
 struct cpucp_unmask_irq_arr_packet {
@@ -476,6 +518,12 @@
 	__le32 irqs[0];
 };
 
+struct cpucp_nic_status_packet {
+	struct cpucp_packet cpucp_pkt;
+	__le32 length;
+	__le32 data[0];
+};
+
 struct cpucp_array_data_packet {
 	struct cpucp_packet cpucp_pkt;
 	__le32 length;
@@ -595,6 +643,18 @@
 	PLL_MAX
 };
 
+enum rl_index {
+	TPC_RL = 0,
+	MME_RL,
+};
+
+enum pvt_index {
+	PVT_SW,
+	PVT_SE,
+	PVT_NW,
+	PVT_NE
+};
+
 /* Event Queue Packets */
 
 struct eq_generic_event {
@@ -700,6 +760,15 @@
 	__u8 mac_addr[ETH_ALEN];
 };
 
+enum cpucp_serdes_type {
+	TYPE_1_SERDES_TYPE,
+	TYPE_2_SERDES_TYPE,
+	HLS1_SERDES_TYPE,
+	HLS1H_SERDES_TYPE,
+	UNKNOWN_SERDES_TYPE,
+	MAX_NUM_SERDES_TYPE = UNKNOWN_SERDES_TYPE
+};
+
 struct cpucp_nic_info {
 	struct cpucp_mac_addr mac_addrs[CPUCP_MAX_NICS];
 	__le64 link_mask[CPUCP_NIC_MASK_ARR_LEN];
@@ -708,6 +777,40 @@
 	__le64 link_ext_mask[CPUCP_NIC_MASK_ARR_LEN];
 	__u8 qsfp_eeprom[CPUCP_NIC_QSFP_EEPROM_MAX_LEN];
 	__le64 auto_neg_mask[CPUCP_NIC_MASK_ARR_LEN];
+	__le16 serdes_type; /* enum cpucp_serdes_type */
+	__u8 reserved[6];
+};
+
+/*
+ * struct cpucp_nic_status - describes the status of a NIC port.
+ * @port: NIC port index.
+ * @bad_format_cnt: e.g. CRC.
+ * @responder_out_of_sequence_psn_cnt: e.g NAK.
+ * @high_ber_reinit_cnt: link reinit due to high BER.
+ * @correctable_err_cnt: e.g. bit-flip.
+ * @uncorrectable_err_cnt: e.g. MAC errors.
+ * @retraining_cnt: re-training counter.
+ * @up: is port up.
+ * @pcs_link: has PCS link.
+ * @phy_ready: is PHY ready.
+ * @auto_neg: is Autoneg enabled.
+ * @timeout_retransmission_cnt: timeout retransmission events
+ * @high_ber_cnt: high ber events
+ */
+struct cpucp_nic_status {
+	__le32 port;
+	__le32 bad_format_cnt;
+	__le32 responder_out_of_sequence_psn_cnt;
+	__le32 high_ber_reinit;
+	__le32 correctable_err_cnt;
+	__le32 uncorrectable_err_cnt;
+	__le32 retraining_cnt;
+	__u8 up;
+	__u8 pcs_link;
+	__u8 phy_ready;
+	__u8 auto_neg;
+	__le32 timeout_retransmission_cnt;
+	__le32 high_ber_cnt;
 };
 
 #endif /* CPUCP_IF_H */
diff --git a/drivers/misc/habanalabs/include/common/hl_boot_if.h b/drivers/misc/habanalabs/include/common/hl_boot_if.h
index fa8a5ad..3099653 100644
--- a/drivers/misc/habanalabs/include/common/hl_boot_if.h
+++ b/drivers/misc/habanalabs/include/common/hl_boot_if.h
@@ -78,6 +78,26 @@
  * CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL	Device is unusable and customer support
  *					should be contacted.
  *
+ * CPU_BOOT_ERR0_ARC0_HALT_ACK_NOT_RCVD	HALT ACK from ARC0 is not received
+ *					within specified retries after issuing
+ *					HALT request. ARC0 appears to be in bad
+ *					reset.
+ *
+ * CPU_BOOT_ERR0_ARC1_HALT_ACK_NOT_RCVD	HALT ACK from ARC1 is not received
+ *					within specified retries after issuing
+ *					HALT request. ARC1 appears to be in bad
+ *					reset.
+ *
+ * CPU_BOOT_ERR0_ARC0_RUN_ACK_NOT_RCVD	RUN ACK from ARC0 is not received
+ *					within specified timeout after issuing
+ *					RUN request. ARC0 appears to be in bad
+ *					reset.
+ *
+ * CPU_BOOT_ERR0_ARC1_RUN_ACK_NOT_RCVD	RUN ACK from ARC1 is not received
+ *					within specified timeout after issuing
+ *					RUN request. ARC1 appears to be in bad
+ *					reset.
+ *
  * CPU_BOOT_ERR0_ENABLED		Error registers enabled.
  *					This is a main indication that the
  *					running FW populates the error
@@ -98,6 +118,10 @@
 #define CPU_BOOT_ERR0_SEC_IMG_VER_FAIL		(1 << 11)
 #define CPU_BOOT_ERR0_PLL_FAIL			(1 << 12)
 #define CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL	(1 << 13)
+#define CPU_BOOT_ERR0_ARC0_HALT_ACK_NOT_RCVD	(1 << 14)
+#define CPU_BOOT_ERR0_ARC1_HALT_ACK_NOT_RCVD	(1 << 15)
+#define CPU_BOOT_ERR0_ARC0_RUN_ACK_NOT_RCVD	(1 << 16)
+#define CPU_BOOT_ERR0_ARC1_RUN_ACK_NOT_RCVD	(1 << 17)
 #define CPU_BOOT_ERR0_ENABLED			(1 << 31)
 #define CPU_BOOT_ERR1_ENABLED			(1 << 31)
 
@@ -186,6 +210,10 @@
  *					configured and is ready for use.
  *					Initialized in: ppboot
  *
+ * CPU_BOOT_DEV_STS0_FW_NIC_MAC_EN	NIC MAC channels init is done by FW and
+ *					any access to them is done via the FW.
+ *					Initialized in: linux
+ *
  * CPU_BOOT_DEV_STS0_DYN_PLL_EN		Dynamic PLL configuration is enabled.
  *					FW sends to host a bitmap of supported
  *					PLLs.
@@ -209,6 +237,21 @@
  *					prevent IRQs overriding each other.
  *					Initialized in: linux
  *
+ * CPU_BOOT_DEV_STS0_FW_NIC_STAT_XPCS91_EN
+ *					NIC STAT and XPCS91 access is restricted
+ *					and is done via FW only.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_FW_NIC_STAT_EXT_EN
+ *					NIC STAT get all is supported.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_IS_IDLE_CHECK_EN
+ *					F/W checks if the device is idle by reading defined set
+ *					of registers. It returns a bitmask of all the engines,
+ *					where a bit is set if the engine is not idle.
+ *					Initialized in: linux
+ *
  * CPU_BOOT_DEV_STS0_ENABLED		Device status register enabled.
  *					This is a main indication that the
  *					running FW populates the device status
@@ -236,10 +279,14 @@
 #define CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN			(1 << 15)
 #define CPU_BOOT_DEV_STS0_FW_LD_COM_EN			(1 << 16)
 #define CPU_BOOT_DEV_STS0_FW_IATU_CONF_EN		(1 << 17)
+#define CPU_BOOT_DEV_STS0_FW_NIC_MAC_EN			(1 << 18)
 #define CPU_BOOT_DEV_STS0_DYN_PLL_EN			(1 << 19)
 #define CPU_BOOT_DEV_STS0_GIC_PRIVILEGED_EN		(1 << 20)
 #define CPU_BOOT_DEV_STS0_EQ_INDEX_EN			(1 << 21)
 #define CPU_BOOT_DEV_STS0_MULTI_IRQ_POLL_EN		(1 << 22)
+#define CPU_BOOT_DEV_STS0_FW_NIC_STAT_XPCS91_EN		(1 << 23)
+#define CPU_BOOT_DEV_STS0_FW_NIC_STAT_EXT_EN		(1 << 24)
+#define CPU_BOOT_DEV_STS0_IS_IDLE_CHECK_EN		(1 << 25)
 #define CPU_BOOT_DEV_STS0_ENABLED			(1 << 31)
 #define CPU_BOOT_DEV_STS1_ENABLED			(1 << 31)
 
@@ -313,10 +360,7 @@
 	__le32 hw_state;
 	__le32 kmd_msg_to_cpu;
 	__le32 cpu_cmd_status_to_host;
-	union {
-		__le32 gic_host_irq_ctrl;
-		__le32 gic_host_pi_upd_irq;
-	};
+	__le32 gic_host_pi_upd_irq;
 	__le32 gic_tpc_qm_irq_ctrl;
 	__le32 gic_mme_qm_irq_ctrl;
 	__le32 gic_dma_qm_irq_ctrl;
@@ -324,7 +368,9 @@
 	__le32 gic_dma_core_irq_ctrl;
 	__le32 gic_host_halt_irq;
 	__le32 gic_host_ints_irq;
-	__le32 reserved1[24];		/* reserve for future use */
+	__le32 gic_host_soft_rst_irq;
+	__le32 gic_rot_qm_irq_ctrl;
+	__le32 reserved1[22];		/* reserve for future use */
 };
 
 /* TODO: remove the desc magic after the code is updated to use message */
@@ -462,6 +508,11 @@
  *				Do not wait for BMC response.
  *
  * COMMS_LOW_PLL_OPP		Initialize PLLs for low OPP.
+ *
+ * COMMS_PREP_DESC_ELBI		Same as COMMS_PREP_DESC only that the memory
+ *				space is allocated in a ELBI access only
+ *				address range.
+ *
  */
 enum comms_cmd {
 	COMMS_NOOP = 0,
@@ -474,6 +525,7 @@
 	COMMS_GOTO_WFE = 7,
 	COMMS_SKIP_BMC = 8,
 	COMMS_LOW_PLL_OPP = 9,
+	COMMS_PREP_DESC_ELBI = 10,
 	COMMS_INVLD_LAST
 };
 
diff --git a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h
index 5bb54b34..ffdfbd9 100644
--- a/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h
+++ b/drivers/misc/habanalabs/include/gaudi/asic_reg/gaudi_regs.h
@@ -126,6 +126,9 @@
 #define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_1                     0x4F2004
 #define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_SOB_OBJ_2047                  0x4F3FFC
 #define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRL_0               0x4F4000
+#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_ADDRH_0               0x4F4800
+#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_PAY_DATA_0                0x4F5000
+#define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_ARM_0                     0x4F5800
 #define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_0                  0x4F6000
 #define mmSYNC_MNGR_E_N_SYNC_MNGR_OBJS_MON_STATUS_511                0x4F67FC
 
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
index 9aea7e9..acc85d3 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_masks.h
@@ -449,4 +449,21 @@
 #define PCIE_AUX_FLR_CTRL_HW_CTRL_MASK                               0x1
 #define PCIE_AUX_FLR_CTRL_INT_MASK_MASK                              0x2
 
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_VALID_SHIFT        0
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_VALID_MASK         0x1
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_PENDING_SHIFT      1
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_STATUS_0_PENDING_MASK       0x1FE
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_SHIFT             0
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SID_MASK              0xFF
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_SHIFT            8
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_MASK_MASK             0xFF00
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOP_SHIFT             16
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOP_MASK              0x10000
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOD_SHIFT             17
+#define SYNC_MNGR_W_S_SYNC_MNGR_OBJS_MON_ARM_0_SOD_MASK              0xFFFE0000
+#define TPC0_QM_CP_STS_0_FENCE_ID_SHIFT                              20
+#define TPC0_QM_CP_STS_0_FENCE_ID_MASK                               0x300000
+#define TPC0_QM_CP_STS_0_FENCE_IN_PROGRESS_SHIFT                     22
+#define TPC0_QM_CP_STS_0_FENCE_IN_PROGRESS_MASK                      0x400000
+
 #endif /* GAUDI_MASKS_H_ */
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_reg_map.h b/drivers/misc/habanalabs/include/gaudi/gaudi_reg_map.h
index d95d416..b9bd5a7 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_reg_map.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_reg_map.h
@@ -12,8 +12,6 @@
  * PSOC scratch-pad registers
  */
 #define mmHW_STATE			mmPSOC_GLOBAL_CONF_SCRATCHPAD_0
-/* TODO: remove mmGIC_HOST_IRQ_CTRL_POLL_REG */
-#define mmGIC_HOST_IRQ_CTRL_POLL_REG	mmPSOC_GLOBAL_CONF_SCRATCHPAD_1
 #define mmGIC_HOST_PI_UPD_IRQ_POLL_REG	mmPSOC_GLOBAL_CONF_SCRATCHPAD_1
 #define mmGIC_TPC_QM_IRQ_CTRL_POLL_REG	mmPSOC_GLOBAL_CONF_SCRATCHPAD_2
 #define mmGIC_MME_QM_IRQ_CTRL_POLL_REG	mmPSOC_GLOBAL_CONF_SCRATCHPAD_3
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8679a108..7efb31b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -116,6 +116,8 @@
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
+static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
+				   struct nvme_command *cmd);
 
 /*
  * Prepare a queue for teardown.
@@ -1152,7 +1154,8 @@
 	return effects;
 }
 
-static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
+static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects,
+			      struct nvme_command *cmd, int status)
 {
 	if (effects & NVME_CMD_EFFECTS_CSE_MASK) {
 		nvme_unfreeze(ctrl);
@@ -1167,6 +1170,26 @@
 		nvme_queue_scan(ctrl);
 		flush_work(&ctrl->scan_work);
 	}
+
+	switch (cmd->common.opcode) {
+	case nvme_admin_set_features:
+		switch (le32_to_cpu(cmd->common.cdw10) & 0xFF) {
+		case NVME_FEAT_KATO:
+			/*
+			 * Keep alive commands interval on the host should be
+			 * updated when KATO is modified by Set Features
+			 * commands.
+			 */
+			if (!status)
+				nvme_update_keep_alive(ctrl, cmd);
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
 }
 
 int nvme_execute_passthru_rq(struct request *rq)
@@ -1181,7 +1204,7 @@
 	effects = nvme_passthru_start(ctrl, ns, cmd->common.opcode);
 	ret = nvme_execute_rq(disk, rq, false);
 	if (effects) /* nothing to be done for zero cmd effects */
-		nvme_passthru_end(ctrl, effects);
+		nvme_passthru_end(ctrl, effects, cmd, ret);
 
 	return ret;
 }
@@ -1269,6 +1292,21 @@
 }
 EXPORT_SYMBOL_GPL(nvme_stop_keep_alive);
 
+static void nvme_update_keep_alive(struct nvme_ctrl *ctrl,
+				   struct nvme_command *cmd)
+{
+	unsigned int new_kato =
+		DIV_ROUND_UP(le32_to_cpu(cmd->common.cdw11), 1000);
+
+	dev_info(ctrl->device,
+		 "keep alive interval updated from %u ms to %u ms\n",
+		 ctrl->kato * 1000 / 2, new_kato * 1000 / 2);
+
+	nvme_stop_keep_alive(ctrl);
+	ctrl->kato = new_kato;
+	nvme_start_keep_alive(ctrl);
+}
+
 /*
  * In NVMe 1.0 the CNS field was just a binary controller or namespace
  * flag, thus sending any new CNS opcodes has a big chance of not working.
@@ -1302,11 +1340,6 @@
 	return error;
 }
 
-static bool nvme_multi_css(struct nvme_ctrl *ctrl)
-{
-	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
-}
-
 static int nvme_process_ns_desc(struct nvme_ctrl *ctrl, struct nvme_ns_ids *ids,
 		struct nvme_ns_id_desc *cur, bool *csi_seen)
 {
@@ -1874,6 +1907,7 @@
 			goto out_unfreeze;
 	}
 
+	set_bit(NVME_NS_READY, &ns->flags);
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
@@ -1885,6 +1919,7 @@
 	if (nvme_ns_head_multipath(ns->head)) {
 		blk_mq_freeze_queue(ns->head->disk->queue);
 		nvme_update_disk_info(ns->head->disk, ns, id);
+		nvme_mpath_revalidate_paths(ns);
 		blk_stack_limits(&ns->head->disk->queue->limits,
 				 &ns->queue->limits, 0);
 		disk_update_readahead(ns->head->disk);
@@ -3763,7 +3798,9 @@
 
 	nvme_get_ctrl(ctrl);
 
-	device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);
+	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups))
+		goto out_cleanup_ns_from_list;
+
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_add_ns_cdev(ns);
 
@@ -3773,6 +3810,11 @@
 
 	return;
 
+ out_cleanup_ns_from_list:
+	nvme_put_ctrl(ctrl);
+	down_write(&ctrl->namespaces_rwsem);
+	list_del_init(&ns->list);
+	up_write(&ctrl->namespaces_rwsem);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
@@ -3795,6 +3837,7 @@
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
+	clear_bit(NVME_NS_READY, &ns->flags);
 	set_capacity(ns->disk, 0);
 	nvme_fault_inject_fini(&ns->fault_inject);
 
@@ -3802,9 +3845,12 @@
 	list_del_rcu(&ns->siblings);
 	mutex_unlock(&ns->ctrl->subsys->lock);
 
-	synchronize_rcu(); /* guarantee not available in head->list */
-	nvme_mpath_clear_current_path(ns);
-	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
+	/* guarantee not available in head->list */
+	synchronize_rcu();
+
+	/* wait for concurrent submissions */
+	if (nvme_mpath_clear_current_path(ns))
+		synchronize_srcu(&ns->head->srcu);
 
 	if (!nvme_ns_head_multipath(ns->head))
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 37ce3e8..5d7bc58 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -147,6 +147,21 @@
 	mutex_unlock(&ctrl->scan_lock);
 }
 
+void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
+{
+	struct nvme_ns_head *head = ns->head;
+	sector_t capacity = get_capacity(head->disk);
+	int node;
+
+	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		if (capacity != get_capacity(ns->disk))
+			clear_bit(NVME_NS_READY, &ns->flags);
+	}
+
+	for_each_node(node)
+		rcu_assign_pointer(head->current_path[node], NULL);
+}
+
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
 	/*
@@ -158,7 +173,7 @@
 	    ns->ctrl->state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
-	    test_bit(NVME_NS_REMOVING, &ns->flags))
+	    !test_bit(NVME_NS_READY, &ns->flags))
 		return true;
 	return false;
 }
@@ -465,6 +480,8 @@
 			ctrl->subsys->instance, head->instance);
 
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, head->disk->queue);
+	blk_queue_flag_set(QUEUE_FLAG_NOWAIT, head->disk->queue);
+
 	/* set to a default value of 512 until the disk is validated */
 	blk_queue_logical_block_size(head->disk->queue, 512);
 	blk_set_stacking_limits(&head->disk->queue->limits);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index a2e1f29..9871c0c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -456,6 +456,7 @@
 #define NVME_NS_DEAD     	1
 #define NVME_NS_ANA_PENDING	2
 #define NVME_NS_FORCE_RO	3
+#define NVME_NS_READY		4
 
 	struct cdev		cdev;
 	struct device		cdev_device;
@@ -748,6 +749,7 @@
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
+void nvme_mpath_revalidate_paths(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 void nvme_mpath_shutdown_disk(struct nvme_ns_head *head);
 
@@ -795,6 +797,9 @@
 {
 	return false;
 }
+static inline void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
+{
+}
 static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 }
@@ -887,4 +892,9 @@
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
 void nvme_put_ns(struct nvme_ns *ns);
 
+static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
+{
+	return (ctrl->ctrl_config & NVME_CC_CSS_MASK) == NVME_CC_CSS_CSI;
+}
+
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 6450256..e2ab12f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -45,6 +45,7 @@
 	u32			pdu_len;
 	u32			pdu_sent;
 	u16			ttag;
+	__le16			status;
 	struct list_head	entry;
 	struct llist_node	lentry;
 	__le32			ddgst;
@@ -485,6 +486,7 @@
 static int nvme_tcp_process_nvme_cqe(struct nvme_tcp_queue *queue,
 		struct nvme_completion *cqe)
 {
+	struct nvme_tcp_request *req;
 	struct request *rq;
 
 	rq = nvme_find_rq(nvme_tcp_tagset(queue), cqe->command_id);
@@ -496,7 +498,11 @@
 		return -EINVAL;
 	}
 
-	if (!nvme_try_complete_req(rq, cqe->status, cqe->result))
+	req = blk_mq_rq_to_pdu(rq);
+	if (req->status == cpu_to_le16(NVME_SC_SUCCESS))
+		req->status = cqe->status;
+
+	if (!nvme_try_complete_req(rq, req->status, cqe->result))
 		nvme_complete_rq(rq);
 	queue->nr_cqe++;
 
@@ -758,7 +764,8 @@
 			queue->ddgst_remaining = NVME_TCP_DIGEST_LENGTH;
 		} else {
 			if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
-				nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+				nvme_tcp_end_request(rq,
+						le16_to_cpu(req->status));
 				queue->nr_cqe++;
 			}
 			nvme_tcp_init_recv_ctx(queue);
@@ -788,18 +795,24 @@
 		return 0;
 
 	if (queue->recv_ddgst != queue->exp_ddgst) {
+		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
+					pdu->command_id);
+		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
+
+		req->status = cpu_to_le16(NVME_SC_DATA_XFER_ERROR);
+
 		dev_err(queue->ctrl->ctrl.device,
 			"data digest error: recv %#x expected %#x\n",
 			le32_to_cpu(queue->recv_ddgst),
 			le32_to_cpu(queue->exp_ddgst));
-		return -EIO;
 	}
 
 	if (pdu->hdr.flags & NVME_TCP_F_DATA_SUCCESS) {
 		struct request *rq = nvme_cid_to_rq(nvme_tcp_tagset(queue),
 					pdu->command_id);
+		struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
-		nvme_tcp_end_request(rq, NVME_SC_SUCCESS);
+		nvme_tcp_end_request(rq, le16_to_cpu(req->status));
 		queue->nr_cqe++;
 	}
 
@@ -2293,6 +2306,7 @@
 		return ret;
 
 	req->state = NVME_TCP_SEND_CMD_PDU;
+	req->status = cpu_to_le16(NVME_SC_SUCCESS);
 	req->offset = 0;
 	req->data_sent = 0;
 	req->pdu_len = 0;
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 0cb98f2..aa6d84d 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -1015,7 +1015,7 @@
 	if (unlikely(ret))
 		return ret;
 
-	if (nvmet_req_passthru_ctrl(req))
+	if (nvmet_is_passthru_req(req))
 		return nvmet_parse_passthru_admin_cmd(req);
 
 	switch (cmd->common.opcode) {
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 2735551..d784f3c 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1028,7 +1028,7 @@
 	}
 
 	/* passthru subsystems use the underlying controller's version */
-	if (nvmet_passthru_ctrl(subsys))
+	if (nvmet_is_passthru_subsys(subsys))
 		return -EINVAL;
 
 	ret = sscanf(page, "%d.%d.%d\n", &major, &minor, &tertiary);
@@ -1067,7 +1067,8 @@
 {
 	struct nvmet_subsys *subsys = to_subsys(item);
 
-	return snprintf(page, PAGE_SIZE, "%s\n", subsys->serial);
+	return snprintf(page, PAGE_SIZE, "%*s\n",
+			NVMET_SN_MAX_SIZE, subsys->serial);
 }
 
 static ssize_t
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 66d05ee..b8425fa 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -553,7 +553,7 @@
 	mutex_lock(&subsys->lock);
 	ret = 0;
 
-	if (nvmet_passthru_ctrl(subsys)) {
+	if (nvmet_is_passthru_subsys(subsys)) {
 		pr_info("cannot enable both passthru and regular namespaces for a single subsystem");
 		goto out_unlock;
 	}
@@ -869,7 +869,7 @@
 	if (unlikely(ret))
 		return ret;
 
-	if (nvmet_req_passthru_ctrl(req))
+	if (nvmet_is_passthru_req(req))
 		return nvmet_parse_passthru_io_cmd(req);
 
 	ret = nvmet_req_find_ns(req);
@@ -1206,6 +1206,9 @@
 	ctrl->cap |= (15ULL << 24);
 	/* maximum queue entries supported: */
 	ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+
+	if (nvmet_is_passthru_subsys(ctrl->subsys))
+		nvmet_passthrough_override_cap(ctrl);
 }
 
 struct nvmet_ctrl *nvmet_ctrl_find_get(const char *subsysnqn,
@@ -1363,8 +1366,6 @@
 		goto out_put_subsystem;
 	mutex_init(&ctrl->lock);
 
-	nvmet_init_cap(ctrl);
-
 	ctrl->port = req->port;
 
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
@@ -1378,6 +1379,7 @@
 
 	kref_init(&ctrl->ref);
 	ctrl->subsys = subsys;
+	nvmet_init_cap(ctrl);
 	WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
 
 	ctrl->changed_ns_list = kmalloc_array(NVME_MAX_CHANGED_NAMESPACES,
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 06dd3d5..7143c7f 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -582,7 +582,7 @@
 void nvmet_passthru_ctrl_disable(struct nvmet_subsys *subsys);
 u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req);
 u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req);
-static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys)
+static inline bool nvmet_is_passthru_subsys(struct nvmet_subsys *subsys)
 {
 	return subsys->passthru_ctrl;
 }
@@ -601,18 +601,19 @@
 {
 	return 0;
 }
-static inline struct nvme_ctrl *nvmet_passthru_ctrl(struct nvmet_subsys *subsys)
+static inline bool nvmet_is_passthru_subsys(struct nvmet_subsys *subsys)
 {
 	return NULL;
 }
 #endif /* CONFIG_NVME_TARGET_PASSTHRU */
 
-static inline struct nvme_ctrl *
-nvmet_req_passthru_ctrl(struct nvmet_req *req)
+static inline bool nvmet_is_passthru_req(struct nvmet_req *req)
 {
-	return nvmet_passthru_ctrl(nvmet_req_subsys(req));
+	return nvmet_is_passthru_subsys(nvmet_req_subsys(req));
 }
 
+void nvmet_passthrough_override_cap(struct nvmet_ctrl *ctrl);
+
 u16 errno_to_nvme_status(struct nvmet_req *req, int errno);
 u16 nvmet_report_invalid_opcode(struct nvmet_req *req);
 
diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
index 225cd1f..f0efb35 100644
--- a/drivers/nvme/target/passthru.c
+++ b/drivers/nvme/target/passthru.c
@@ -20,6 +20,16 @@
  */
 static DEFINE_XARRAY(passthru_subsystems);
 
+void nvmet_passthrough_override_cap(struct nvmet_ctrl *ctrl)
+{
+	/*
+	 * Multiple command set support can only be declared if the underlying
+	 * controller actually supports it.
+	 */
+	if (!nvme_multi_css(ctrl->subsys->passthru_ctrl))
+		ctrl->cap &= ~(1ULL << 43);
+}
+
 static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -218,7 +228,7 @@
 
 static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
 {
-	struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
+	struct nvme_ctrl *ctrl = nvmet_req_subsys(req)->passthru_ctrl;
 	struct request_queue *q = ctrl->admin_q;
 	struct nvme_ns *ns = NULL;
 	struct request *rq = NULL;
@@ -299,7 +309,7 @@
  */
 static void nvmet_passthru_set_host_behaviour(struct nvmet_req *req)
 {
-	struct nvme_ctrl *ctrl = nvmet_req_passthru_ctrl(req);
+	struct nvme_ctrl *ctrl = nvmet_req_subsys(req)->passthru_ctrl;
 	struct nvme_feat_host_behavior *host;
 	u16 status = NVME_SC_INTERNAL;
 	int ret;
diff --git a/drivers/of/property.c b/drivers/of/property.c
index 0c0dc2e..3fd74bb 100644
--- a/drivers/of/property.c
+++ b/drivers/of/property.c
@@ -1444,6 +1444,9 @@
 	struct property *p;
 	struct device_node *con_np = to_of_node(fwnode);
 
+	if (IS_ENABLED(CONFIG_X86))
+		return 0;
+
 	if (!con_np)
 		return -EINVAL;
 
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index 889d7ce..952a925 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -156,15 +156,6 @@
 	return container_of(hba, struct dino_device, hba);
 }
 
-/* Check if PCI device is behind a Card-mode Dino. */
-static int pci_dev_is_behind_card_dino(struct pci_dev *dev)
-{
-	struct dino_device *dino_dev;
-
-	dino_dev = DINO_DEV(parisc_walk_tree(dev->bus->bridge));
-	return is_card_dino(&dino_dev->hba.dev->id);
-}
-
 /*
  * Dino Configuration Space Accessor Functions
  */
@@ -447,6 +438,15 @@
 DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_CIRRUS, PCI_DEVICE_ID_CIRRUS_6832, quirk_cirrus_cardbus );
 
 #ifdef CONFIG_TULIP
+/* Check if PCI device is behind a Card-mode Dino. */
+static int pci_dev_is_behind_card_dino(struct pci_dev *dev)
+{
+	struct dino_device *dino_dev;
+
+	dino_dev = DINO_DEV(parisc_walk_tree(dev->bus->bridge));
+	return is_card_dino(&dino_dev->hba.dev->id);
+}
+
 static void pci_fixup_tulip(struct pci_dev *dev)
 {
 	if (!pci_dev_is_behind_card_dino(dev))
diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
index c76aded..aa29841 100644
--- a/drivers/pwm/Kconfig
+++ b/drivers/pwm/Kconfig
@@ -272,7 +272,7 @@
 
 config PWM_JZ4740
 	tristate "Ingenic JZ47xx PWM support"
-	depends on MIPS
+	depends on MIPS || COMPILE_TEST
 	depends on COMMON_CLK
 	select MFD_SYSCON
 	help
@@ -284,7 +284,8 @@
 
 config PWM_KEEMBAY
 	tristate "Intel Keem Bay PWM driver"
-	depends on ARCH_KEEMBAY || (ARM64 && COMPILE_TEST)
+	depends on ARCH_KEEMBAY || COMPILE_TEST
+	depends on COMMON_CLK && HAS_IOMEM
 	help
 	  The platform driver for Intel Keem Bay PWM controller.
 
diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 35e894f..4527f09 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -304,7 +304,7 @@
  *
  * Returns: 0 on success or a negative error code on failure.
  */
-int pwmchip_remove(struct pwm_chip *chip)
+void pwmchip_remove(struct pwm_chip *chip)
 {
 	pwmchip_sysfs_unexport(chip);
 
@@ -318,8 +318,6 @@
 	free_pwms(chip);
 
 	mutex_unlock(&pwm_lock);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(pwmchip_remove);
 
diff --git a/drivers/pwm/pwm-ab8500.c b/drivers/pwm/pwm-ab8500.c
index e2a26d9..ad37bc4 100644
--- a/drivers/pwm/pwm-ab8500.c
+++ b/drivers/pwm/pwm-ab8500.c
@@ -22,14 +22,21 @@
 
 struct ab8500_pwm_chip {
 	struct pwm_chip chip;
+	unsigned int hwid;
 };
 
+static struct ab8500_pwm_chip *ab8500_pwm_from_chip(struct pwm_chip *chip)
+{
+	return container_of(chip, struct ab8500_pwm_chip, chip);
+}
+
 static int ab8500_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
 			    const struct pwm_state *state)
 {
 	int ret;
 	u8 reg;
 	unsigned int higher_val, lower_val;
+	struct ab8500_pwm_chip *ab8500 = ab8500_pwm_from_chip(chip);
 
 	if (state->polarity != PWM_POLARITY_NORMAL)
 		return -EINVAL;
@@ -37,7 +44,7 @@
 	if (!state->enabled) {
 		ret = abx500_mask_and_set_register_interruptible(chip->dev,
 					AB8500_MISC, AB8500_PWM_OUT_CTRL7_REG,
-					1 << (chip->base - 1), 0);
+					1 << ab8500->hwid, 0);
 
 		if (ret < 0)
 			dev_err(chip->dev, "%s: Failed to disable PWM, Error %d\n",
@@ -56,7 +63,7 @@
 	 */
 	higher_val = ((state->duty_cycle & 0x0300) >> 8);
 
-	reg = AB8500_PWM_OUT_CTRL1_REG + ((chip->base - 1) * 2);
+	reg = AB8500_PWM_OUT_CTRL1_REG + (ab8500->hwid * 2);
 
 	ret = abx500_set_register_interruptible(chip->dev, AB8500_MISC,
 			reg, (u8)lower_val);
@@ -70,7 +77,7 @@
 
 	ret = abx500_mask_and_set_register_interruptible(chip->dev,
 				AB8500_MISC, AB8500_PWM_OUT_CTRL7_REG,
-				1 << (chip->base - 1), 1 << (chip->base - 1));
+				1 << ab8500->hwid, 1 << ab8500->hwid);
 	if (ret < 0)
 		dev_err(chip->dev, "%s: Failed to enable PWM, Error %d\n",
 							pwm->label, ret);
@@ -88,6 +95,9 @@
 	struct ab8500_pwm_chip *ab8500;
 	int err;
 
+	if (pdev->id < 1 || pdev->id > 31)
+		return dev_err_probe(&pdev->dev, EINVAL, "Invalid device id %d\n", pdev->id);
+
 	/*
 	 * Nothing to be done in probe, this is required to get the
 	 * device which is required for ab8500 read and write
@@ -99,27 +109,13 @@
 	ab8500->chip.dev = &pdev->dev;
 	ab8500->chip.ops = &ab8500_pwm_ops;
 	ab8500->chip.npwm = 1;
+	ab8500->hwid = pdev->id - 1;
 
-	err = pwmchip_add(&ab8500->chip);
+	err = devm_pwmchip_add(&pdev->dev, &ab8500->chip);
 	if (err < 0)
 		return dev_err_probe(&pdev->dev, err, "Failed to add pwm chip\n");
 
 	dev_dbg(&pdev->dev, "pwm probe successful\n");
-	platform_set_drvdata(pdev, ab8500);
-
-	return 0;
-}
-
-static int ab8500_pwm_remove(struct platform_device *pdev)
-{
-	struct ab8500_pwm_chip *ab8500 = platform_get_drvdata(pdev);
-	int err;
-
-	err = pwmchip_remove(&ab8500->chip);
-	if (err < 0)
-		return err;
-
-	dev_dbg(&pdev->dev, "pwm driver removed\n");
 
 	return 0;
 }
@@ -129,7 +125,6 @@
 		.name = "ab8500-pwm",
 	},
 	.probe = ab8500_pwm_probe,
-	.remove = ab8500_pwm_remove,
 };
 module_platform_driver(ab8500_pwm_driver);
 
diff --git a/drivers/pwm/pwm-atmel-hlcdc.c b/drivers/pwm/pwm-atmel-hlcdc.c
index 4459325..a43b2ba 100644
--- a/drivers/pwm/pwm-atmel-hlcdc.c
+++ b/drivers/pwm/pwm-atmel-hlcdc.c
@@ -281,11 +281,8 @@
 static int atmel_hlcdc_pwm_remove(struct platform_device *pdev)
 {
 	struct atmel_hlcdc_pwm *chip = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&chip->chip);
-	if (ret)
-		return ret;
+	pwmchip_remove(&chip->chip);
 
 	clk_disable_unprepare(chip->hlcdc->periph_clk);
 
diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
index bf398f2..36f7ea3 100644
--- a/drivers/pwm/pwm-atmel-tcb.c
+++ b/drivers/pwm/pwm-atmel-tcb.c
@@ -503,11 +503,8 @@
 static int atmel_tcb_pwm_remove(struct platform_device *pdev)
 {
 	struct atmel_tcb_pwm_chip *tcbpwm = platform_get_drvdata(pdev);
-	int err;
 
-	err = pwmchip_remove(&tcbpwm->chip);
-	if (err < 0)
-		return err;
+	pwmchip_remove(&tcbpwm->chip);
 
 	clk_disable_unprepare(tcbpwm->slow_clk);
 	clk_put(tcbpwm->slow_clk);
diff --git a/drivers/pwm/pwm-atmel.c b/drivers/pwm/pwm-atmel.c
index a8162ba..e748604 100644
--- a/drivers/pwm/pwm-atmel.c
+++ b/drivers/pwm/pwm-atmel.c
@@ -84,9 +84,19 @@
 	void __iomem *base;
 	const struct atmel_pwm_data *data;
 
-	unsigned int updated_pwms;
-	/* ISR is cleared when read, ensure only one thread does that */
-	struct mutex isr_lock;
+	/*
+	 * The hardware supports a mechanism to update a channel's duty cycle at
+	 * the end of the currently running period. When such an update is
+	 * pending we delay disabling the PWM until the new configuration is
+	 * active because otherwise pmw_config(duty_cycle=0); pwm_disable();
+	 * might not result in an inactive output.
+	 * This bitmask tracks for which channels an update is pending in
+	 * hardware.
+	 */
+	u32 update_pending;
+
+	/* Protects .update_pending */
+	spinlock_t lock;
 };
 
 static inline struct atmel_pwm_chip *to_atmel_pwm_chip(struct pwm_chip *chip)
@@ -123,6 +133,64 @@
 	atmel_pwm_writel(chip, base + offset, val);
 }
 
+static void atmel_pwm_update_pending(struct atmel_pwm_chip *chip)
+{
+	/*
+	 * Each channel that has its bit in ISR set started a new period since
+	 * ISR was cleared and so there is no more update pending.  Note that
+	 * reading ISR clears it, so this needs to handle all channels to not
+	 * loose information.
+	 */
+	u32 isr = atmel_pwm_readl(chip, PWM_ISR);
+
+	chip->update_pending &= ~isr;
+}
+
+static void atmel_pwm_set_pending(struct atmel_pwm_chip *chip, unsigned int ch)
+{
+	spin_lock(&chip->lock);
+
+	/*
+	 * Clear pending flags in hardware because otherwise there might still
+	 * be a stale flag in ISR.
+	 */
+	atmel_pwm_update_pending(chip);
+
+	chip->update_pending |= (1 << ch);
+
+	spin_unlock(&chip->lock);
+}
+
+static int atmel_pwm_test_pending(struct atmel_pwm_chip *chip, unsigned int ch)
+{
+	int ret = 0;
+
+	spin_lock(&chip->lock);
+
+	if (chip->update_pending & (1 << ch)) {
+		atmel_pwm_update_pending(chip);
+
+		if (chip->update_pending & (1 << ch))
+			ret = 1;
+	}
+
+	spin_unlock(&chip->lock);
+
+	return ret;
+}
+
+static int atmel_pwm_wait_nonpending(struct atmel_pwm_chip *chip, unsigned int ch)
+{
+	unsigned long timeout = jiffies + 2 * HZ;
+	int ret;
+
+	while ((ret = atmel_pwm_test_pending(chip, ch)) &&
+	       time_before(jiffies, timeout))
+		usleep_range(10, 100);
+
+	return ret ? -ETIMEDOUT : 0;
+}
+
 static int atmel_pwm_calculate_cprd_and_pres(struct pwm_chip *chip,
 					     unsigned long clkrate,
 					     const struct pwm_state *state,
@@ -185,6 +253,7 @@
 
 	atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm,
 			    atmel_pwm->data->regs.duty_upd, cdty);
+	atmel_pwm_set_pending(atmel_pwm, pwm->hwpwm);
 }
 
 static void atmel_pwm_set_cprd_cdty(struct pwm_chip *chip,
@@ -205,20 +274,8 @@
 	struct atmel_pwm_chip *atmel_pwm = to_atmel_pwm_chip(chip);
 	unsigned long timeout = jiffies + 2 * HZ;
 
-	/*
-	 * Wait for at least a complete period to have passed before disabling a
-	 * channel to be sure that CDTY has been updated
-	 */
-	mutex_lock(&atmel_pwm->isr_lock);
-	atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
+	atmel_pwm_wait_nonpending(atmel_pwm, pwm->hwpwm);
 
-	while (!(atmel_pwm->updated_pwms & (1 << pwm->hwpwm)) &&
-	       time_before(jiffies, timeout)) {
-		usleep_range(10, 100);
-		atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
-	}
-
-	mutex_unlock(&atmel_pwm->isr_lock);
 	atmel_pwm_writel(atmel_pwm, PWM_DIS, 1 << pwm->hwpwm);
 
 	/*
@@ -292,10 +349,6 @@
 			val |= PWM_CMR_CPOL;
 		atmel_pwm_ch_writel(atmel_pwm, pwm->hwpwm, PWM_CMR, val);
 		atmel_pwm_set_cprd_cdty(chip, pwm, cprd, cdty);
-		mutex_lock(&atmel_pwm->isr_lock);
-		atmel_pwm->updated_pwms |= atmel_pwm_readl(atmel_pwm, PWM_ISR);
-		atmel_pwm->updated_pwms &= ~(1 << pwm->hwpwm);
-		mutex_unlock(&atmel_pwm->isr_lock);
 		atmel_pwm_writel(atmel_pwm, PWM_ENA, 1 << pwm->hwpwm);
 	} else if (cstate.enabled) {
 		atmel_pwm_disable(chip, pwm, true);
@@ -326,6 +379,9 @@
 		tmp <<= pres;
 		state->period = DIV64_U64_ROUND_UP(tmp, rate);
 
+		/* Wait for an updated duty_cycle queued in hardware */
+		atmel_pwm_wait_nonpending(atmel_pwm, pwm->hwpwm);
+
 		cdty = atmel_pwm_ch_readl(atmel_pwm, pwm->hwpwm,
 					  atmel_pwm->data->regs.duty);
 		tmp = (u64)(cprd - cdty) * NSEC_PER_SEC;
@@ -416,9 +472,10 @@
 	if (!atmel_pwm)
 		return -ENOMEM;
 
-	mutex_init(&atmel_pwm->isr_lock);
 	atmel_pwm->data = of_device_get_match_data(&pdev->dev);
-	atmel_pwm->updated_pwms = 0;
+
+	atmel_pwm->update_pending = 0;
+	spin_lock_init(&atmel_pwm->lock);
 
 	atmel_pwm->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(atmel_pwm->base))
@@ -460,7 +517,6 @@
 	pwmchip_remove(&atmel_pwm->chip);
 
 	clk_unprepare(atmel_pwm->clk);
-	mutex_destroy(&atmel_pwm->isr_lock);
 
 	return 0;
 }
diff --git a/drivers/pwm/pwm-bcm-kona.c b/drivers/pwm/pwm-bcm-kona.c
index 8c85c66..64148f5 100644
--- a/drivers/pwm/pwm-bcm-kona.c
+++ b/drivers/pwm/pwm-bcm-kona.c
@@ -267,8 +267,6 @@
 	if (kp == NULL)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, kp);
-
 	kp->chip.dev = &pdev->dev;
 	kp->chip.ops = &kona_pwm_ops;
 	kp->chip.npwm = 6;
@@ -298,20 +296,13 @@
 
 	clk_disable_unprepare(kp->clk);
 
-	ret = pwmchip_add(&kp->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &kp->chip);
 	if (ret < 0)
 		dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret);
 
 	return ret;
 }
 
-static int kona_pwmc_remove(struct platform_device *pdev)
-{
-	struct kona_pwmc *kp = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&kp->chip);
-}
-
 static const struct of_device_id bcm_kona_pwmc_dt[] = {
 	{ .compatible = "brcm,kona-pwm" },
 	{ },
@@ -324,7 +315,6 @@
 		.of_match_table = bcm_kona_pwmc_dt,
 	},
 	.probe = kona_pwmc_probe,
-	.remove = kona_pwmc_remove,
 };
 module_platform_driver(kona_pwmc_driver);
 
diff --git a/drivers/pwm/pwm-brcmstb.c b/drivers/pwm/pwm-brcmstb.c
index 8b1d1e7a..3b529f8 100644
--- a/drivers/pwm/pwm-brcmstb.c
+++ b/drivers/pwm/pwm-brcmstb.c
@@ -282,12 +282,11 @@
 static int brcmstb_pwm_remove(struct platform_device *pdev)
 {
 	struct brcmstb_pwm *p = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&p->chip);
+	pwmchip_remove(&p->chip);
 	clk_disable_unprepare(p->clk);
 
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/pwm/pwm-cros-ec.c b/drivers/pwm/pwm-cros-ec.c
index 9fffb56..5e29d9c 100644
--- a/drivers/pwm/pwm-cros-ec.c
+++ b/drivers/pwm/pwm-cros-ec.c
@@ -280,7 +280,9 @@
 	struct cros_ec_pwm_device *ec_pwm = platform_get_drvdata(dev);
 	struct pwm_chip *chip = &ec_pwm->chip;
 
-	return pwmchip_remove(chip);
+	pwmchip_remove(chip);
+
+	return 0;
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/pwm/pwm-ep93xx.c b/drivers/pwm/pwm-ep93xx.c
index fc3cb7d..c45a75e 100644
--- a/drivers/pwm/pwm-ep93xx.c
+++ b/drivers/pwm/pwm-ep93xx.c
@@ -183,27 +183,18 @@
 	ep93xx_pwm->chip.ops = &ep93xx_pwm_ops;
 	ep93xx_pwm->chip.npwm = 1;
 
-	ret = pwmchip_add(&ep93xx_pwm->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &ep93xx_pwm->chip);
 	if (ret < 0)
 		return ret;
 
-	platform_set_drvdata(pdev, ep93xx_pwm);
 	return 0;
 }
 
-static int ep93xx_pwm_remove(struct platform_device *pdev)
-{
-	struct ep93xx_pwm *ep93xx_pwm = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&ep93xx_pwm->chip);
-}
-
 static struct platform_driver ep93xx_pwm_driver = {
 	.driver = {
 		.name = "ep93xx-pwm",
 	},
 	.probe = ep93xx_pwm_probe,
-	.remove = ep93xx_pwm_remove,
 };
 module_platform_driver(ep93xx_pwm_driver);
 
diff --git a/drivers/pwm/pwm-fsl-ftm.c b/drivers/pwm/pwm-fsl-ftm.c
index 96ccd772..0247757 100644
--- a/drivers/pwm/pwm-fsl-ftm.c
+++ b/drivers/pwm/pwm-fsl-ftm.c
@@ -453,7 +453,7 @@
 	fpc->chip.ops = &fsl_pwm_ops;
 	fpc->chip.npwm = 8;
 
-	ret = pwmchip_add(&fpc->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &fpc->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add PWM chip: %d\n", ret);
 		return ret;
@@ -464,13 +464,6 @@
 	return fsl_pwm_init(fpc);
 }
 
-static int fsl_pwm_remove(struct platform_device *pdev)
-{
-	struct fsl_pwm_chip *fpc = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&fpc->chip);
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int fsl_pwm_suspend(struct device *dev)
 {
@@ -552,7 +545,6 @@
 		.pm = &fsl_pwm_pm_ops,
 	},
 	.probe = fsl_pwm_probe,
-	.remove = fsl_pwm_remove,
 };
 module_platform_driver(fsl_pwm_driver);
 
diff --git a/drivers/pwm/pwm-hibvt.c b/drivers/pwm/pwm-hibvt.c
index 4a6e9ad..333f1b1 100644
--- a/drivers/pwm/pwm-hibvt.c
+++ b/drivers/pwm/pwm-hibvt.c
@@ -248,13 +248,15 @@
 
 	pwm_chip = platform_get_drvdata(pdev);
 
+	pwmchip_remove(&pwm_chip->chip);
+
 	reset_control_assert(pwm_chip->rstc);
 	msleep(30);
 	reset_control_deassert(pwm_chip->rstc);
 
 	clk_disable_unprepare(pwm_chip->clk);
 
-	return pwmchip_remove(&pwm_chip->chip);
+	return 0;
 }
 
 static const struct of_device_id hibvt_pwm_of_match[] = {
diff --git a/drivers/pwm/pwm-img.c b/drivers/pwm/pwm-img.c
index 11b16ec..f97f825 100644
--- a/drivers/pwm/pwm-img.c
+++ b/drivers/pwm/pwm-img.c
@@ -326,28 +326,14 @@
 static int img_pwm_remove(struct platform_device *pdev)
 {
 	struct img_pwm_chip *pwm_chip = platform_get_drvdata(pdev);
-	u32 val;
-	unsigned int i;
-	int ret;
 
-	ret = pm_runtime_get_sync(&pdev->dev);
-	if (ret < 0) {
-		pm_runtime_put(&pdev->dev);
-		return ret;
-	}
-
-	for (i = 0; i < pwm_chip->chip.npwm; i++) {
-		val = img_pwm_readl(pwm_chip, PWM_CTRL_CFG);
-		val &= ~BIT(i);
-		img_pwm_writel(pwm_chip, PWM_CTRL_CFG, val);
-	}
-
-	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	if (!pm_runtime_status_suspended(&pdev->dev))
 		img_pwm_runtime_suspend(&pdev->dev);
 
-	return pwmchip_remove(&pwm_chip->chip);
+	pwmchip_remove(&pwm_chip->chip);
+
+	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/pwm/pwm-imx-tpm.c b/drivers/pwm/pwm-imx-tpm.c
index dbb5049..e5e7b7c 100644
--- a/drivers/pwm/pwm-imx-tpm.c
+++ b/drivers/pwm/pwm-imx-tpm.c
@@ -382,11 +382,12 @@
 static int pwm_imx_tpm_remove(struct platform_device *pdev)
 {
 	struct imx_tpm_pwm_chip *tpm = platform_get_drvdata(pdev);
-	int ret = pwmchip_remove(&tpm->chip);
+
+	pwmchip_remove(&tpm->chip);
 
 	clk_disable_unprepare(tpm->clk);
 
-	return ret;
+	return 0;
 }
 
 static int __maybe_unused pwm_imx_tpm_suspend(struct device *dev)
diff --git a/drivers/pwm/pwm-imx27.c b/drivers/pwm/pwm-imx27.c
index f6588a9..ea91a2f 100644
--- a/drivers/pwm/pwm-imx27.c
+++ b/drivers/pwm/pwm-imx27.c
@@ -313,8 +313,6 @@
 	if (imx == NULL)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, imx);
-
 	imx->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
 	if (IS_ERR(imx->clk_ipg))
 		return dev_err_probe(&pdev->dev, PTR_ERR(imx->clk_ipg),
@@ -342,16 +340,7 @@
 	if (!(pwmcr & MX3_PWMCR_EN))
 		pwm_imx27_clk_disable_unprepare(imx);
 
-	return pwmchip_add(&imx->chip);
-}
-
-static int pwm_imx27_remove(struct platform_device *pdev)
-{
-	struct pwm_imx27_chip *imx;
-
-	imx = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&imx->chip);
+	return devm_pwmchip_add(&pdev->dev, &imx->chip);
 }
 
 static struct platform_driver imx_pwm_driver = {
@@ -360,7 +349,6 @@
 		.of_match_table = pwm_imx27_dt_ids,
 	},
 	.probe = pwm_imx27_probe,
-	.remove = pwm_imx27_remove,
 };
 module_platform_driver(imx_pwm_driver);
 
diff --git a/drivers/pwm/pwm-intel-lgm.c b/drivers/pwm/pwm-intel-lgm.c
index 015f5eb..b66c350 100644
--- a/drivers/pwm/pwm-intel-lgm.c
+++ b/drivers/pwm/pwm-intel-lgm.c
@@ -176,8 +176,6 @@
 	if (!pc)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, pc);
-
 	io_base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(io_base))
 		return PTR_ERR(io_base);
@@ -210,20 +208,13 @@
 
 	lgm_pwm_init(pc);
 
-	ret = pwmchip_add(&pc->chip);
+	ret = devm_pwmchip_add(dev, &pc->chip);
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "failed to add PWM chip\n");
 
 	return 0;
 }
 
-static int lgm_pwm_remove(struct platform_device *pdev)
-{
-	struct lgm_pwm_chip *pc = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&pc->chip);
-}
-
 static const struct of_device_id lgm_pwm_of_match[] = {
 	{ .compatible = "intel,lgm-pwm" },
 	{ }
@@ -236,7 +227,6 @@
 		.of_match_table = lgm_pwm_of_match,
 	},
 	.probe = lgm_pwm_probe,
-	.remove = lgm_pwm_remove,
 };
 module_platform_driver(lgm_pwm_driver);
 
diff --git a/drivers/pwm/pwm-iqs620a.c b/drivers/pwm/pwm-iqs620a.c
index 6c6e26d..54bd95a 100644
--- a/drivers/pwm/pwm-iqs620a.c
+++ b/drivers/pwm/pwm-iqs620a.c
@@ -189,7 +189,6 @@
 	if (!iqs620_pwm)
 		return -ENOMEM;
 
-	platform_set_drvdata(pdev, iqs620_pwm);
 	iqs620_pwm->iqs62x = iqs62x;
 
 	ret = regmap_read(iqs62x->regmap, IQS620_PWR_SETTINGS, &val);
@@ -224,31 +223,18 @@
 	if (ret)
 		return ret;
 
-	ret = pwmchip_add(&iqs620_pwm->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &iqs620_pwm->chip);
 	if (ret)
 		dev_err(&pdev->dev, "Failed to add device: %d\n", ret);
 
 	return ret;
 }
 
-static int iqs620_pwm_remove(struct platform_device *pdev)
-{
-	struct iqs620_pwm_private *iqs620_pwm = platform_get_drvdata(pdev);
-	int ret;
-
-	ret = pwmchip_remove(&iqs620_pwm->chip);
-	if (ret)
-		dev_err(&pdev->dev, "Failed to remove device: %d\n", ret);
-
-	return ret;
-}
-
 static struct platform_driver iqs620_pwm_platform_driver = {
 	.driver = {
 		.name = "iqs620a-pwm",
 	},
 	.probe = iqs620_pwm_probe,
-	.remove = iqs620_pwm_remove,
 };
 module_platform_driver(iqs620_pwm_platform_driver);
 
diff --git a/drivers/pwm/pwm-jz4740.c b/drivers/pwm/pwm-jz4740.c
index 990e790..23dc1fb 100644
--- a/drivers/pwm/pwm-jz4740.c
+++ b/drivers/pwm/pwm-jz4740.c
@@ -245,16 +245,7 @@
 	jz4740->chip.ops = &jz4740_pwm_ops;
 	jz4740->chip.npwm = info->num_pwms;
 
-	platform_set_drvdata(pdev, jz4740);
-
-	return pwmchip_add(&jz4740->chip);
-}
-
-static int jz4740_pwm_remove(struct platform_device *pdev)
-{
-	struct jz4740_pwm_chip *jz4740 = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&jz4740->chip);
+	return devm_pwmchip_add(dev, &jz4740->chip);
 }
 
 static const struct soc_info __maybe_unused jz4740_soc_info = {
@@ -280,7 +271,6 @@
 		.of_match_table = of_match_ptr(jz4740_pwm_dt_ids),
 	},
 	.probe = jz4740_pwm_probe,
-	.remove = jz4740_pwm_remove,
 };
 module_platform_driver(jz4740_pwm_driver);
 
diff --git a/drivers/pwm/pwm-keembay.c b/drivers/pwm/pwm-keembay.c
index 521a825..733811b 100644
--- a/drivers/pwm/pwm-keembay.c
+++ b/drivers/pwm/pwm-keembay.c
@@ -207,22 +207,13 @@
 	priv->chip.ops = &keembay_pwm_ops;
 	priv->chip.npwm = KMB_TOTAL_PWM_CHANNELS;
 
-	ret = pwmchip_add(&priv->chip);
+	ret = devm_pwmchip_add(dev, &priv->chip);
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to add PWM chip\n");
 
-	platform_set_drvdata(pdev, priv);
-
 	return 0;
 }
 
-static int keembay_pwm_remove(struct platform_device *pdev)
-{
-	struct keembay_pwm *priv = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&priv->chip);
-}
-
 static const struct of_device_id keembay_pwm_of_match[] = {
 	{ .compatible = "intel,keembay-pwm" },
 	{ }
@@ -231,7 +222,6 @@
 
 static struct platform_driver keembay_pwm_driver = {
 	.probe	= keembay_pwm_probe,
-	.remove	= keembay_pwm_remove,
 	.driver	= {
 		.name = "pwm-keembay",
 		.of_match_table = keembay_pwm_of_match,
diff --git a/drivers/pwm/pwm-lp3943.c b/drivers/pwm/pwm-lp3943.c
index 7551253..ea17d446 100644
--- a/drivers/pwm/pwm-lp3943.c
+++ b/drivers/pwm/pwm-lp3943.c
@@ -276,16 +276,7 @@
 	lp3943_pwm->chip.ops = &lp3943_pwm_ops;
 	lp3943_pwm->chip.npwm = LP3943_NUM_PWMS;
 
-	platform_set_drvdata(pdev, lp3943_pwm);
-
-	return pwmchip_add(&lp3943_pwm->chip);
-}
-
-static int lp3943_pwm_remove(struct platform_device *pdev)
-{
-	struct lp3943_pwm *lp3943_pwm = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&lp3943_pwm->chip);
+	return devm_pwmchip_add(&pdev->dev, &lp3943_pwm->chip);
 }
 
 #ifdef CONFIG_OF
@@ -298,7 +289,6 @@
 
 static struct platform_driver lp3943_pwm_driver = {
 	.probe = lp3943_pwm_probe,
-	.remove = lp3943_pwm_remove,
 	.driver = {
 		.name = "lp3943-pwm",
 		.of_match_table = of_match_ptr(lp3943_pwm_of_match),
diff --git a/drivers/pwm/pwm-lpc32xx.c b/drivers/pwm/pwm-lpc32xx.c
index 2834a0f..ddeab56 100644
--- a/drivers/pwm/pwm-lpc32xx.c
+++ b/drivers/pwm/pwm-lpc32xx.c
@@ -117,29 +117,20 @@
 	lpc32xx->chip.ops = &lpc32xx_pwm_ops;
 	lpc32xx->chip.npwm = 1;
 
-	ret = pwmchip_add(&lpc32xx->chip);
+	/* If PWM is disabled, configure the output to the default value */
+	val = readl(lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+	val &= ~PWM_PIN_LEVEL;
+	writel(val, lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
+
+	ret = devm_pwmchip_add(&pdev->dev, &lpc32xx->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add PWM chip, error %d\n", ret);
 		return ret;
 	}
 
-	/* When PWM is disable, configure the output to the default value */
-	val = readl(lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
-	val &= ~PWM_PIN_LEVEL;
-	writel(val, lpc32xx->base + (lpc32xx->chip.pwms[0].hwpwm << 2));
-
-	platform_set_drvdata(pdev, lpc32xx);
-
 	return 0;
 }
 
-static int lpc32xx_pwm_remove(struct platform_device *pdev)
-{
-	struct lpc32xx_pwm_chip *lpc32xx = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&lpc32xx->chip);
-}
-
 static const struct of_device_id lpc32xx_pwm_dt_ids[] = {
 	{ .compatible = "nxp,lpc3220-pwm", },
 	{ /* sentinel */ }
@@ -152,7 +143,6 @@
 		.of_match_table = lpc32xx_pwm_dt_ids,
 	},
 	.probe = lpc32xx_pwm_probe,
-	.remove = lpc32xx_pwm_remove,
 };
 module_platform_driver(lpc32xx_pwm_driver);
 
diff --git a/drivers/pwm/pwm-mediatek.c b/drivers/pwm/pwm-mediatek.c
index b4a3106..0d4dd80 100644
--- a/drivers/pwm/pwm-mediatek.c
+++ b/drivers/pwm/pwm-mediatek.c
@@ -253,13 +253,11 @@
 		}
 	}
 
-	platform_set_drvdata(pdev, pc);
-
 	pc->chip.dev = &pdev->dev;
 	pc->chip.ops = &pwm_mediatek_ops;
 	pc->chip.npwm = pc->soc->num_pwms;
 
-	ret = pwmchip_add(&pc->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &pc->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
 		return ret;
@@ -268,13 +266,6 @@
 	return 0;
 }
 
-static int pwm_mediatek_remove(struct platform_device *pdev)
-{
-	struct pwm_mediatek_chip *pc = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&pc->chip);
-}
-
 static const struct pwm_mediatek_of_data mt2712_pwm_data = {
 	.num_pwms = 8,
 	.pwm45_fixup = false,
@@ -335,7 +326,6 @@
 		.of_match_table = pwm_mediatek_of_match,
 	},
 	.probe = pwm_mediatek_probe,
-	.remove = pwm_mediatek_remove,
 };
 module_platform_driver(pwm_mediatek_driver);
 
diff --git a/drivers/pwm/pwm-mtk-disp.c b/drivers/pwm/pwm-mtk-disp.c
index 9b3ba40..c605013 100644
--- a/drivers/pwm/pwm-mtk-disp.c
+++ b/drivers/pwm/pwm-mtk-disp.c
@@ -5,6 +5,7 @@
  * Author: YH Huang <yh.huang@mediatek.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
@@ -47,6 +48,7 @@
 	struct clk *clk_main;
 	struct clk *clk_mm;
 	void __iomem *base;
+	bool enabled;
 };
 
 static inline struct mtk_disp_pwm *to_mtk_disp_pwm(struct pwm_chip *chip)
@@ -66,14 +68,47 @@
 	writel(value, address);
 }
 
-static int mtk_disp_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
-			       int duty_ns, int period_ns)
+static int mtk_disp_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+			      const struct pwm_state *state)
 {
 	struct mtk_disp_pwm *mdp = to_mtk_disp_pwm(chip);
 	u32 clk_div, period, high_width, value;
 	u64 div, rate;
 	int err;
 
+	if (state->polarity != PWM_POLARITY_NORMAL)
+		return -EINVAL;
+
+	if (!state->enabled) {
+		mtk_disp_pwm_update_bits(mdp, DISP_PWM_EN, mdp->data->enable_mask,
+					 0x0);
+
+		if (mdp->enabled) {
+			clk_disable_unprepare(mdp->clk_mm);
+			clk_disable_unprepare(mdp->clk_main);
+		}
+
+		mdp->enabled = false;
+		return 0;
+	}
+
+	if (!mdp->enabled) {
+		err = clk_prepare_enable(mdp->clk_main);
+		if (err < 0) {
+			dev_err(chip->dev, "Can't enable mdp->clk_main: %pe\n",
+				ERR_PTR(err));
+			return err;
+		}
+
+		err = clk_prepare_enable(mdp->clk_mm);
+		if (err < 0) {
+			dev_err(chip->dev, "Can't enable mdp->clk_mm: %pe\n",
+				ERR_PTR(err));
+			clk_disable_unprepare(mdp->clk_main);
+			return err;
+		}
+	}
+
 	/*
 	 * Find period, high_width and clk_div to suit duty_ns and period_ns.
 	 * Calculate proper div value to keep period value in the bound.
@@ -85,29 +120,24 @@
 	 * high_width = (PWM_CLK_RATE * duty_ns) / (10^9 * (clk_div + 1))
 	 */
 	rate = clk_get_rate(mdp->clk_main);
-	clk_div = div_u64(rate * period_ns, NSEC_PER_SEC) >>
+	clk_div = mul_u64_u64_div_u64(state->period, rate, NSEC_PER_SEC) >>
 			  PWM_PERIOD_BIT_WIDTH;
-	if (clk_div > PWM_CLKDIV_MAX)
+	if (clk_div > PWM_CLKDIV_MAX) {
+		if (!mdp->enabled) {
+			clk_disable_unprepare(mdp->clk_mm);
+			clk_disable_unprepare(mdp->clk_main);
+		}
 		return -EINVAL;
+	}
 
 	div = NSEC_PER_SEC * (clk_div + 1);
-	period = div64_u64(rate * period_ns, div);
+	period = mul_u64_u64_div_u64(state->period, rate, div);
 	if (period > 0)
 		period--;
 
-	high_width = div64_u64(rate * duty_ns, div);
+	high_width = mul_u64_u64_div_u64(state->duty_cycle, rate, div);
 	value = period | (high_width << PWM_HIGH_WIDTH_SHIFT);
 
-	err = clk_enable(mdp->clk_main);
-	if (err < 0)
-		return err;
-
-	err = clk_enable(mdp->clk_mm);
-	if (err < 0) {
-		clk_disable(mdp->clk_main);
-		return err;
-	}
-
 	mtk_disp_pwm_update_bits(mdp, mdp->data->con0,
 				 PWM_CLKDIV_MASK,
 				 clk_div << PWM_CLKDIV_SHIFT);
@@ -122,50 +152,70 @@
 		mtk_disp_pwm_update_bits(mdp, mdp->data->commit,
 					 mdp->data->commit_mask,
 					 0x0);
-	}
-
-	clk_disable(mdp->clk_mm);
-	clk_disable(mdp->clk_main);
-
-	return 0;
-}
-
-static int mtk_disp_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm)
-{
-	struct mtk_disp_pwm *mdp = to_mtk_disp_pwm(chip);
-	int err;
-
-	err = clk_enable(mdp->clk_main);
-	if (err < 0)
-		return err;
-
-	err = clk_enable(mdp->clk_mm);
-	if (err < 0) {
-		clk_disable(mdp->clk_main);
-		return err;
+	} else {
+		/*
+		 * For MT2701, disable double buffer before writing register
+		 * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH.
+		 */
+		mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug,
+					 mdp->data->bls_debug_mask,
+					 mdp->data->bls_debug_mask);
+		mtk_disp_pwm_update_bits(mdp, mdp->data->con0,
+					 mdp->data->con0_sel,
+					 mdp->data->con0_sel);
 	}
 
 	mtk_disp_pwm_update_bits(mdp, DISP_PWM_EN, mdp->data->enable_mask,
 				 mdp->data->enable_mask);
+	mdp->enabled = true;
 
 	return 0;
 }
 
-static void mtk_disp_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm)
+static void mtk_disp_pwm_get_state(struct pwm_chip *chip,
+				   struct pwm_device *pwm,
+				   struct pwm_state *state)
 {
 	struct mtk_disp_pwm *mdp = to_mtk_disp_pwm(chip);
+	u64 rate, period, high_width;
+	u32 clk_div, con0, con1;
+	int err;
 
-	mtk_disp_pwm_update_bits(mdp, DISP_PWM_EN, mdp->data->enable_mask,
-				 0x0);
+	err = clk_prepare_enable(mdp->clk_main);
+	if (err < 0) {
+		dev_err(chip->dev, "Can't enable mdp->clk_main: %pe\n", ERR_PTR(err));
+		return;
+	}
 
-	clk_disable(mdp->clk_mm);
-	clk_disable(mdp->clk_main);
+	err = clk_prepare_enable(mdp->clk_mm);
+	if (err < 0) {
+		dev_err(chip->dev, "Can't enable mdp->clk_mm: %pe\n", ERR_PTR(err));
+		clk_disable_unprepare(mdp->clk_main);
+		return;
+	}
+
+	rate = clk_get_rate(mdp->clk_main);
+	con0 = readl(mdp->base + mdp->data->con0);
+	con1 = readl(mdp->base + mdp->data->con1);
+	state->enabled = !!(con0 & BIT(0));
+	clk_div = FIELD_GET(PWM_CLKDIV_MASK, con0);
+	period = FIELD_GET(PWM_PERIOD_MASK, con1);
+	/*
+	 * period has 12 bits, clk_div 11 and NSEC_PER_SEC has 30,
+	 * so period * (clk_div + 1) * NSEC_PER_SEC doesn't overflow.
+	 */
+	state->period = DIV64_U64_ROUND_UP(period * (clk_div + 1) * NSEC_PER_SEC, rate);
+	high_width = FIELD_GET(PWM_HIGH_WIDTH_MASK, con1);
+	state->duty_cycle = DIV64_U64_ROUND_UP(high_width * (clk_div + 1) * NSEC_PER_SEC,
+					       rate);
+	state->polarity = PWM_POLARITY_NORMAL;
+	clk_disable_unprepare(mdp->clk_mm);
+	clk_disable_unprepare(mdp->clk_main);
 }
 
 static const struct pwm_ops mtk_disp_pwm_ops = {
-	.config = mtk_disp_pwm_config,
-	.enable = mtk_disp_pwm_enable,
-	.disable = mtk_disp_pwm_disable,
+	.apply = mtk_disp_pwm_apply,
+	.get_state = mtk_disp_pwm_get_state,
 	.owner = THIS_MODULE,
 };
 
@@ -192,58 +242,28 @@
 	if (IS_ERR(mdp->clk_mm))
 		return PTR_ERR(mdp->clk_mm);
 
-	ret = clk_prepare(mdp->clk_main);
-	if (ret < 0)
-		return ret;
-
-	ret = clk_prepare(mdp->clk_mm);
-	if (ret < 0)
-		goto disable_clk_main;
-
 	mdp->chip.dev = &pdev->dev;
 	mdp->chip.ops = &mtk_disp_pwm_ops;
 	mdp->chip.npwm = 1;
 
 	ret = pwmchip_add(&mdp->chip);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
-		goto disable_clk_mm;
+		dev_err(&pdev->dev, "pwmchip_add() failed: %pe\n", ERR_PTR(ret));
+		return ret;
 	}
 
 	platform_set_drvdata(pdev, mdp);
 
-	/*
-	 * For MT2701, disable double buffer before writing register
-	 * and select manual mode and use PWM_PERIOD/PWM_HIGH_WIDTH.
-	 */
-	if (!mdp->data->has_commit) {
-		mtk_disp_pwm_update_bits(mdp, mdp->data->bls_debug,
-					 mdp->data->bls_debug_mask,
-					 mdp->data->bls_debug_mask);
-		mtk_disp_pwm_update_bits(mdp, mdp->data->con0,
-					 mdp->data->con0_sel,
-					 mdp->data->con0_sel);
-	}
-
 	return 0;
-
-disable_clk_mm:
-	clk_unprepare(mdp->clk_mm);
-disable_clk_main:
-	clk_unprepare(mdp->clk_main);
-	return ret;
 }
 
 static int mtk_disp_pwm_remove(struct platform_device *pdev)
 {
 	struct mtk_disp_pwm *mdp = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&mdp->chip);
-	clk_unprepare(mdp->clk_mm);
-	clk_unprepare(mdp->clk_main);
+	pwmchip_remove(&mdp->chip);
 
-	return ret;
+	return 0;
 }
 
 static const struct mtk_pwm_data mt2701_pwm_data = {
diff --git a/drivers/pwm/pwm-mxs.c b/drivers/pwm/pwm-mxs.c
index a221808..766dbc58 100644
--- a/drivers/pwm/pwm-mxs.c
+++ b/drivers/pwm/pwm-mxs.c
@@ -145,30 +145,18 @@
 		return ret;
 	}
 
-	ret = pwmchip_add(&mxs->chip);
+	/* FIXME: Only do this if the PWM isn't already running */
+	ret = stmp_reset_block(mxs->base);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "failed to reset PWM\n");
+
+	ret = devm_pwmchip_add(&pdev->dev, &mxs->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "failed to add pwm chip %d\n", ret);
 		return ret;
 	}
 
-	platform_set_drvdata(pdev, mxs);
-
-	ret = stmp_reset_block(mxs->base);
-	if (ret)
-		goto pwm_remove;
-
 	return 0;
-
-pwm_remove:
-	pwmchip_remove(&mxs->chip);
-	return ret;
-}
-
-static int mxs_pwm_remove(struct platform_device *pdev)
-{
-	struct mxs_pwm_chip *mxs = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&mxs->chip);
 }
 
 static const struct of_device_id mxs_pwm_dt_ids[] = {
@@ -183,7 +171,6 @@
 		.of_match_table = mxs_pwm_dt_ids,
 	},
 	.probe = mxs_pwm_probe,
-	.remove = mxs_pwm_remove,
 };
 module_platform_driver(mxs_pwm_driver);
 
diff --git a/drivers/pwm/pwm-ntxec.c b/drivers/pwm/pwm-ntxec.c
index 50c454c..ab63b08 100644
--- a/drivers/pwm/pwm-ntxec.c
+++ b/drivers/pwm/pwm-ntxec.c
@@ -150,23 +150,12 @@
 	priv->ec = ec;
 	priv->dev = &pdev->dev;
 
-	platform_set_drvdata(pdev, priv);
-
 	chip = &priv->chip;
 	chip->dev = &pdev->dev;
 	chip->ops = &ntxec_pwm_ops;
-	chip->base = -1;
 	chip->npwm = 1;
 
-	return pwmchip_add(chip);
-}
-
-static int ntxec_pwm_remove(struct platform_device *pdev)
-{
-	struct ntxec_pwm *priv = platform_get_drvdata(pdev);
-	struct pwm_chip *chip = &priv->chip;
-
-	return pwmchip_remove(chip);
+	return devm_pwmchip_add(&pdev->dev, chip);
 }
 
 static struct platform_driver ntxec_pwm_driver = {
@@ -174,7 +163,6 @@
 		.name = "ntxec-pwm",
 	},
 	.probe = ntxec_pwm_probe,
-	.remove = ntxec_pwm_remove,
 };
 module_platform_driver(ntxec_pwm_driver);
 
diff --git a/drivers/pwm/pwm-omap-dmtimer.c b/drivers/pwm/pwm-omap-dmtimer.c
index 507a2d9..fa800fc 100644
--- a/drivers/pwm/pwm-omap-dmtimer.c
+++ b/drivers/pwm/pwm-omap-dmtimer.c
@@ -444,11 +444,8 @@
 static int pwm_omap_dmtimer_remove(struct platform_device *pdev)
 {
 	struct pwm_omap_dmtimer_chip *omap = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&omap->chip);
-	if (ret)
-		return ret;
+	pwmchip_remove(&omap->chip);
 
 	if (pm_runtime_active(&omap->dm_timer_pdev->dev))
 		omap->pdata->stop(omap->dm_timer);
diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c
index 42ed770..c56001a 100644
--- a/drivers/pwm/pwm-pca9685.c
+++ b/drivers/pwm/pwm-pca9685.c
@@ -601,11 +601,8 @@
 static int pca9685_pwm_remove(struct i2c_client *client)
 {
 	struct pca9685 *pca = i2c_get_clientdata(client);
-	int ret;
 
-	ret = pwmchip_remove(&pca->chip);
-	if (ret)
-		return ret;
+	pwmchip_remove(&pca->chip);
 
 	if (!pm_runtime_enabled(&client->dev)) {
 		/* Put chip in sleep state if runtime PM is disabled */
diff --git a/drivers/pwm/pwm-pxa.c b/drivers/pwm/pwm-pxa.c
index e091a52..a9efdcf8 100644
--- a/drivers/pwm/pwm-pxa.c
+++ b/drivers/pwm/pwm-pxa.c
@@ -195,32 +195,21 @@
 	if (IS_ERR(pc->mmio_base))
 		return PTR_ERR(pc->mmio_base);
 
-	ret = pwmchip_add(&pc->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &pc->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
 		return ret;
 	}
 
-	platform_set_drvdata(pdev, pc);
 	return 0;
 }
 
-static int pwm_remove(struct platform_device *pdev)
-{
-	struct pxa_pwm_chip *pc;
-
-	pc = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&pc->chip);
-}
-
 static struct platform_driver pwm_driver = {
 	.driver		= {
 		.name	= "pxa25x-pwm",
 		.of_match_table = pwm_of_match,
 	},
 	.probe		= pwm_probe,
-	.remove		= pwm_remove,
 	.id_table	= pwm_id_table,
 };
 
diff --git a/drivers/pwm/pwm-raspberrypi-poe.c b/drivers/pwm/pwm-raspberrypi-poe.c
index 043fc32..579a152 100644
--- a/drivers/pwm/pwm-raspberrypi-poe.c
+++ b/drivers/pwm/pwm-raspberrypi-poe.c
@@ -166,8 +166,6 @@
 	rpipwm->chip.base = -1;
 	rpipwm->chip.npwm = RASPBERRYPI_FIRMWARE_PWM_NUM;
 
-	platform_set_drvdata(pdev, rpipwm);
-
 	ret = raspberrypi_pwm_get_property(rpipwm->firmware, RPI_PWM_CUR_DUTY_REG,
 					   &rpipwm->duty_cycle);
 	if (ret) {
@@ -175,14 +173,7 @@
 		return ret;
 	}
 
-	return pwmchip_add(&rpipwm->chip);
-}
-
-static int raspberrypi_pwm_remove(struct platform_device *pdev)
-{
-	struct raspberrypi_pwm *rpipwm = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&rpipwm->chip);
+	return devm_pwmchip_add(dev, &rpipwm->chip);
 }
 
 static const struct of_device_id raspberrypi_pwm_of_match[] = {
@@ -197,7 +188,6 @@
 		.of_match_table = raspberrypi_pwm_of_match,
 	},
 	.probe = raspberrypi_pwm_probe,
-	.remove = raspberrypi_pwm_remove,
 };
 module_platform_driver(raspberrypi_pwm_driver);
 
diff --git a/drivers/pwm/pwm-rcar.c b/drivers/pwm/pwm-rcar.c
index 9daca0c..b437192 100644
--- a/drivers/pwm/pwm-rcar.c
+++ b/drivers/pwm/pwm-rcar.c
@@ -241,13 +241,12 @@
 static int rcar_pwm_remove(struct platform_device *pdev)
 {
 	struct rcar_pwm_chip *rcar_pwm = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&rcar_pwm->chip);
+	pwmchip_remove(&rcar_pwm->chip);
 
 	pm_runtime_disable(&pdev->dev);
 
-	return ret;
+	return 0;
 }
 
 static const struct of_device_id rcar_pwm_of_table[] = {
diff --git a/drivers/pwm/pwm-renesas-tpu.c b/drivers/pwm/pwm-renesas-tpu.c
index b853e79..4381df9 100644
--- a/drivers/pwm/pwm-renesas-tpu.c
+++ b/drivers/pwm/pwm-renesas-tpu.c
@@ -425,13 +425,12 @@
 static int tpu_remove(struct platform_device *pdev)
 {
 	struct tpu_device *tpu = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&tpu->chip);
+	pwmchip_remove(&tpu->chip);
 
 	pm_runtime_disable(&pdev->dev);
 
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_OF
diff --git a/drivers/pwm/pwm-rockchip.c b/drivers/pwm/pwm-rockchip.c
index cbe9008..f3647b3 100644
--- a/drivers/pwm/pwm-rockchip.c
+++ b/drivers/pwm/pwm-rockchip.c
@@ -384,24 +384,12 @@
 {
 	struct rockchip_pwm_chip *pc = platform_get_drvdata(pdev);
 
-	/*
-	 * Disable the PWM clk before unpreparing it if the PWM device is still
-	 * running. This should only happen when the last PWM user left it
-	 * enabled, or when nobody requested a PWM that was previously enabled
-	 * by the bootloader.
-	 *
-	 * FIXME: Maybe the core should disable all PWM devices in
-	 * pwmchip_remove(). In this case we'd only have to call
-	 * clk_unprepare() after pwmchip_remove().
-	 *
-	 */
-	if (pwm_is_enabled(pc->chip.pwms))
-		clk_disable(pc->clk);
+	pwmchip_remove(&pc->chip);
 
 	clk_unprepare(pc->pclk);
 	clk_unprepare(pc->clk);
 
-	return pwmchip_remove(&pc->chip);
+	return 0;
 }
 
 static struct platform_driver rockchip_pwm_driver = {
diff --git a/drivers/pwm/pwm-samsung.c b/drivers/pwm/pwm-samsung.c
index f6c528f..dd94c431 100644
--- a/drivers/pwm/pwm-samsung.c
+++ b/drivers/pwm/pwm-samsung.c
@@ -580,11 +580,8 @@
 static int pwm_samsung_remove(struct platform_device *pdev)
 {
 	struct samsung_pwm_chip *chip = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&chip->chip);
-	if (ret < 0)
-		return ret;
+	pwmchip_remove(&chip->chip);
 
 	clk_disable_unprepare(chip->base_clk);
 
diff --git a/drivers/pwm/pwm-sifive.c b/drivers/pwm/pwm-sifive.c
index 420edc4..253c4a1 100644
--- a/drivers/pwm/pwm-sifive.c
+++ b/drivers/pwm/pwm-sifive.c
@@ -291,7 +291,7 @@
 	struct pwm_sifive_ddata *ddata = platform_get_drvdata(dev);
 	bool is_enabled = false;
 	struct pwm_device *pwm;
-	int ret, ch;
+	int ch;
 
 	for (ch = 0; ch < ddata->chip.npwm; ch++) {
 		pwm = &ddata->chip.pwms[ch];
@@ -304,10 +304,10 @@
 		clk_disable(ddata->clk);
 
 	clk_disable_unprepare(ddata->clk);
-	ret = pwmchip_remove(&ddata->chip);
+	pwmchip_remove(&ddata->chip);
 	clk_notifier_unregister(ddata->clk, &ddata->notifier);
 
-	return ret;
+	return 0;
 }
 
 static const struct of_device_id pwm_sifive_of_match[] = {
diff --git a/drivers/pwm/pwm-sl28cpld.c b/drivers/pwm/pwm-sl28cpld.c
index 7a69c1a..589aeaa 100644
--- a/drivers/pwm/pwm-sl28cpld.c
+++ b/drivers/pwm/pwm-sl28cpld.c
@@ -231,9 +231,7 @@
 	chip->ops = &sl28cpld_pwm_ops;
 	chip->npwm = 1;
 
-	platform_set_drvdata(pdev, priv);
-
-	ret = pwmchip_add(&priv->pwm_chip);
+	ret = devm_pwmchip_add(&pdev->dev, &priv->pwm_chip);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to add PWM chip (%pe)",
 			ERR_PTR(ret));
@@ -243,13 +241,6 @@
 	return 0;
 }
 
-static int sl28cpld_pwm_remove(struct platform_device *pdev)
-{
-	struct sl28cpld_pwm *priv = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&priv->pwm_chip);
-}
-
 static const struct of_device_id sl28cpld_pwm_of_match[] = {
 	{ .compatible = "kontron,sl28cpld-pwm" },
 	{}
@@ -258,7 +249,6 @@
 
 static struct platform_driver sl28cpld_pwm_driver = {
 	.probe = sl28cpld_pwm_probe,
-	.remove	= sl28cpld_pwm_remove,
 	.driver = {
 		.name = "sl28cpld-pwm",
 		.of_match_table = sl28cpld_pwm_of_match,
diff --git a/drivers/pwm/pwm-stm32-lp.c b/drivers/pwm/pwm-stm32-lp.c
index 93dd036..3115abb 100644
--- a/drivers/pwm/pwm-stm32-lp.c
+++ b/drivers/pwm/pwm-stm32-lp.c
@@ -209,7 +209,7 @@
 	priv->chip.ops = &stm32_pwm_lp_ops;
 	priv->chip.npwm = 1;
 
-	ret = pwmchip_add(&priv->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &priv->chip);
 	if (ret < 0)
 		return ret;
 
@@ -218,15 +218,6 @@
 	return 0;
 }
 
-static int stm32_pwm_lp_remove(struct platform_device *pdev)
-{
-	struct stm32_pwm_lp *priv = platform_get_drvdata(pdev);
-
-	pwm_disable(&priv->chip.pwms[0]);
-
-	return pwmchip_remove(&priv->chip);
-}
-
 static int __maybe_unused stm32_pwm_lp_suspend(struct device *dev)
 {
 	struct stm32_pwm_lp *priv = dev_get_drvdata(dev);
@@ -258,7 +249,6 @@
 
 static struct platform_driver stm32_pwm_lp_driver = {
 	.probe	= stm32_pwm_lp_probe,
-	.remove	= stm32_pwm_lp_remove,
 	.driver	= {
 		.name = "stm32-pwm-lp",
 		.of_match_table = of_match_ptr(stm32_pwm_lp_of_match),
diff --git a/drivers/pwm/pwm-sun4i.c b/drivers/pwm/pwm-sun4i.c
index c952604..91ca676 100644
--- a/drivers/pwm/pwm-sun4i.c
+++ b/drivers/pwm/pwm-sun4i.c
@@ -484,11 +484,8 @@
 static int sun4i_pwm_remove(struct platform_device *pdev)
 {
 	struct sun4i_pwm_chip *pwm = platform_get_drvdata(pdev);
-	int ret;
 
-	ret = pwmchip_remove(&pwm->chip);
-	if (ret)
-		return ret;
+	pwmchip_remove(&pwm->chip);
 
 	clk_disable_unprepare(pwm->bus_clk);
 	reset_control_assert(pwm->rst);
diff --git a/drivers/pwm/pwm-tiecap.c b/drivers/pwm/pwm-tiecap.c
index 35eb19a..4701f0c 100644
--- a/drivers/pwm/pwm-tiecap.c
+++ b/drivers/pwm/pwm-tiecap.c
@@ -253,7 +253,7 @@
 	if (IS_ERR(pc->mmio_base))
 		return PTR_ERR(pc->mmio_base);
 
-	ret = pwmchip_add(&pc->chip);
+	ret = devm_pwmchip_add(&pdev->dev, &pc->chip);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "pwmchip_add() failed: %d\n", ret);
 		return ret;
@@ -267,11 +267,9 @@
 
 static int ecap_pwm_remove(struct platform_device *pdev)
 {
-	struct ecap_pwm_chip *pc = platform_get_drvdata(pdev);
-
 	pm_runtime_disable(&pdev->dev);
 
-	return pwmchip_remove(&pc->chip);
+	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/pwm/pwm-tiehrpwm.c b/drivers/pwm/pwm-tiehrpwm.c
index 17909fa..5b723a4 100644
--- a/drivers/pwm/pwm-tiehrpwm.c
+++ b/drivers/pwm/pwm-tiehrpwm.c
@@ -485,11 +485,13 @@
 {
 	struct ehrpwm_pwm_chip *pc = platform_get_drvdata(pdev);
 
+	pwmchip_remove(&pc->chip);
+
 	clk_unprepare(pc->tbclk);
 
 	pm_runtime_disable(&pdev->dev);
 
-	return pwmchip_remove(&pc->chip);
+	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/pwm/pwm-twl-led.c b/drivers/pwm/pwm-twl-led.c
index 6c8df5f..49d9f7a 100644
--- a/drivers/pwm/pwm-twl-led.c
+++ b/drivers/pwm/pwm-twl-led.c
@@ -276,7 +276,6 @@
 static int twl_pwmled_probe(struct platform_device *pdev)
 {
 	struct twl_pwmled_chip *twl;
-	int ret;
 
 	twl = devm_kzalloc(&pdev->dev, sizeof(*twl), GFP_KERNEL);
 	if (!twl)
@@ -294,20 +293,7 @@
 
 	mutex_init(&twl->mutex);
 
-	ret = pwmchip_add(&twl->chip);
-	if (ret < 0)
-		return ret;
-
-	platform_set_drvdata(pdev, twl);
-
-	return 0;
-}
-
-static int twl_pwmled_remove(struct platform_device *pdev)
-{
-	struct twl_pwmled_chip *twl = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&twl->chip);
+	return devm_pwmchip_add(&pdev->dev, &twl->chip);
 }
 
 #ifdef CONFIG_OF
@@ -325,7 +311,6 @@
 		.of_match_table = of_match_ptr(twl_pwmled_of_match),
 	},
 	.probe = twl_pwmled_probe,
-	.remove = twl_pwmled_remove,
 };
 module_platform_driver(twl_pwmled_driver);
 
diff --git a/drivers/pwm/pwm-twl.c b/drivers/pwm/pwm-twl.c
index e83a826..203194f 100644
--- a/drivers/pwm/pwm-twl.c
+++ b/drivers/pwm/pwm-twl.c
@@ -298,7 +298,6 @@
 static int twl_pwm_probe(struct platform_device *pdev)
 {
 	struct twl_pwm_chip *twl;
-	int ret;
 
 	twl = devm_kzalloc(&pdev->dev, sizeof(*twl), GFP_KERNEL);
 	if (!twl)
@@ -314,20 +313,7 @@
 
 	mutex_init(&twl->mutex);
 
-	ret = pwmchip_add(&twl->chip);
-	if (ret < 0)
-		return ret;
-
-	platform_set_drvdata(pdev, twl);
-
-	return 0;
-}
-
-static int twl_pwm_remove(struct platform_device *pdev)
-{
-	struct twl_pwm_chip *twl = platform_get_drvdata(pdev);
-
-	return pwmchip_remove(&twl->chip);
+	return devm_pwmchip_add(&pdev->dev, &twl->chip);
 }
 
 #ifdef CONFIG_OF
@@ -345,7 +331,6 @@
 		.of_match_table = of_match_ptr(twl_pwm_of_match),
 	},
 	.probe = twl_pwm_probe,
-	.remove = twl_pwm_remove,
 };
 module_platform_driver(twl_pwm_driver);
 
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 12153d5..e1bc521 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -75,6 +75,15 @@
 	  Say yes here to enable debugging support in the RTC framework
 	  and individual RTC drivers.
 
+config RTC_LIB_KUNIT_TEST
+	tristate "KUnit test for RTC lib functions" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Enable this option to test RTC library functions.
+
+	  If unsure, say N.
+
 config RTC_NVMEM
 	bool "RTC non volatile storage support"
 	select NVMEM
@@ -624,6 +633,7 @@
 
 config RTC_DRV_RX8010
 	tristate "Epson RX8010SJ"
+	select REGMAP_I2C
 	help
 	  If you say yes here you get support for the Epson RX8010SJ RTC
 	  chip.
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index 2dd0dd9..5ceeafe 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -15,6 +15,8 @@
 rtc-core-$(CONFIG_RTC_INTF_PROC)	+= proc.o
 rtc-core-$(CONFIG_RTC_INTF_SYSFS)	+= sysfs.o
 
+obj-$(CONFIG_RTC_LIB_KUNIT_TEST)	+= lib_test.o
+
 # Keep the list ordered.
 
 obj-$(CONFIG_RTC_DRV_88PM80X)	+= rtc-88pm80x.o
diff --git a/drivers/rtc/lib.c b/drivers/rtc/lib.c
index 2328458..fe36165 100644
--- a/drivers/rtc/lib.c
+++ b/drivers/rtc/lib.c
@@ -6,6 +6,8 @@
  * Author: Alessandro Zummo <a.zummo@towertech.it>
  *
  * based on arch/arm/common/rtctime.c and other bits
+ *
+ * Author: Cassio Neri <cassio.neri@gmail.com> (rtc_time64_to_tm)
  */
 
 #include <linux/export.h>
@@ -22,8 +24,6 @@
 	{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
 };
 
-#define LEAPS_THRU_END_OF(y) ((y) / 4 - (y) / 100 + (y) / 400)
-
 /*
  * The number of days in the month.
  */
@@ -42,42 +42,95 @@
 }
 EXPORT_SYMBOL(rtc_year_days);
 
-/*
- * rtc_time64_to_tm - Converts time64_t to rtc_time.
- * Convert seconds since 01-01-1970 00:00:00 to Gregorian date.
+/**
+ * rtc_time64_to_tm - converts time64_t to rtc_time.
+ *
+ * @time:	The number of seconds since 01-01-1970 00:00:00.
+ *		(Must be positive.)
+ * @tm:		Pointer to the struct rtc_time.
  */
 void rtc_time64_to_tm(time64_t time, struct rtc_time *tm)
 {
-	unsigned int month, year, secs;
+	unsigned int secs;
 	int days;
 
+	u64 u64tmp;
+	u32 u32tmp, udays, century, day_of_century, year_of_century, year,
+		day_of_year, month, day;
+	bool is_Jan_or_Feb, is_leap_year;
+
 	/* time must be positive */
 	days = div_s64_rem(time, 86400, &secs);
 
 	/* day of the week, 1970-01-01 was a Thursday */
 	tm->tm_wday = (days + 4) % 7;
 
-	year = 1970 + days / 365;
-	days -= (year - 1970) * 365
-		+ LEAPS_THRU_END_OF(year - 1)
-		- LEAPS_THRU_END_OF(1970 - 1);
-	while (days < 0) {
-		year -= 1;
-		days += 365 + is_leap_year(year);
-	}
-	tm->tm_year = year - 1900;
-	tm->tm_yday = days + 1;
+	/*
+	 * The following algorithm is, basically, Proposition 6.3 of Neri
+	 * and Schneider [1]. In a few words: it works on the computational
+	 * (fictitious) calendar where the year starts in March, month = 2
+	 * (*), and finishes in February, month = 13. This calendar is
+	 * mathematically convenient because the day of the year does not
+	 * depend on whether the year is leap or not. For instance:
+	 *
+	 * March 1st		0-th day of the year;
+	 * ...
+	 * April 1st		31-st day of the year;
+	 * ...
+	 * January 1st		306-th day of the year; (Important!)
+	 * ...
+	 * February 28th	364-th day of the year;
+	 * February 29th	365-th day of the year (if it exists).
+	 *
+	 * After having worked out the date in the computational calendar
+	 * (using just arithmetics) it's easy to convert it to the
+	 * corresponding date in the Gregorian calendar.
+	 *
+	 * [1] "Euclidean Affine Functions and Applications to Calendar
+	 * Algorithms". https://arxiv.org/abs/2102.06959
+	 *
+	 * (*) The numbering of months follows rtc_time more closely and
+	 * thus, is slightly different from [1].
+	 */
 
-	for (month = 0; month < 11; month++) {
-		int newdays;
+	udays		= ((u32) days) + 719468;
 
-		newdays = days - rtc_month_days(month, year);
-		if (newdays < 0)
-			break;
-		days = newdays;
-	}
-	tm->tm_mon = month;
-	tm->tm_mday = days + 1;
+	u32tmp		= 4 * udays + 3;
+	century		= u32tmp / 146097;
+	day_of_century	= u32tmp % 146097 / 4;
+
+	u32tmp		= 4 * day_of_century + 3;
+	u64tmp		= 2939745ULL * u32tmp;
+	year_of_century	= upper_32_bits(u64tmp);
+	day_of_year	= lower_32_bits(u64tmp) / 2939745 / 4;
+
+	year		= 100 * century + year_of_century;
+	is_leap_year	= year_of_century != 0 ?
+		year_of_century % 4 == 0 : century % 4 == 0;
+
+	u32tmp		= 2141 * day_of_year + 132377;
+	month		= u32tmp >> 16;
+	day		= ((u16) u32tmp) / 2141;
+
+	/*
+	 * Recall that January 01 is the 306-th day of the year in the
+	 * computational (not Gregorian) calendar.
+	 */
+	is_Jan_or_Feb	= day_of_year >= 306;
+
+	/* Converts to the Gregorian calendar. */
+	year		= year + is_Jan_or_Feb;
+	month		= is_Jan_or_Feb ? month - 12 : month;
+	day		= day + 1;
+
+	day_of_year	= is_Jan_or_Feb ?
+		day_of_year - 306 : day_of_year + 31 + 28 + is_leap_year;
+
+	/* Converts to rtc_time's format. */
+	tm->tm_year	= (int) (year - 1900);
+	tm->tm_mon	= (int) month;
+	tm->tm_mday	= (int) day;
+	tm->tm_yday	= (int) day_of_year + 1;
 
 	tm->tm_hour = secs / 3600;
 	secs -= tm->tm_hour * 3600;
diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/lib_test.c
new file mode 100644
index 0000000..d5caf36
--- /dev/null
+++ b/drivers/rtc/lib_test.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: LGPL-2.1+
+
+#include <kunit/test.h>
+#include <linux/rtc.h>
+
+/*
+ * Advance a date by one day.
+ */
+static void advance_date(int *year, int *month, int *mday, int *yday)
+{
+	if (*mday != rtc_month_days(*month - 1, *year)) {
+		++*mday;
+		++*yday;
+		return;
+	}
+
+	*mday = 1;
+	if (*month != 12) {
+		++*month;
+		++*yday;
+		return;
+	}
+
+	*month = 1;
+	*yday  = 1;
+	++*year;
+}
+
+/*
+ * Checks every day in a 160000 years interval starting on 1970-01-01
+ * against the expected result.
+ */
+static void rtc_time64_to_tm_test_date_range(struct kunit *test)
+{
+	/*
+	 * 160000 years	= (160000 / 400) * 400 years
+	 *		= (160000 / 400) * 146097 days
+	 *		= (160000 / 400) * 146097 * 86400 seconds
+	 */
+	time64_t total_secs = ((time64_t) 160000) / 400 * 146097 * 86400;
+
+	int year	= 1970;
+	int month	= 1;
+	int mday	= 1;
+	int yday	= 1;
+
+	struct rtc_time result;
+	time64_t secs;
+	s64 days;
+
+	for (secs = 0; secs <= total_secs; secs += 86400) {
+
+		rtc_time64_to_tm(secs, &result);
+
+		days = div_s64(secs, 86400);
+
+		#define FAIL_MSG "%d/%02d/%02d (%2d) : %ld", \
+			year, month, mday, yday, days
+
+		KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, month - 1, result.tm_mon, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, mday, result.tm_mday, FAIL_MSG);
+		KUNIT_ASSERT_EQ_MSG(test, yday, result.tm_yday, FAIL_MSG);
+
+		advance_date(&year, &month, &mday, &yday);
+	}
+}
+
+static struct kunit_case rtc_lib_test_cases[] = {
+	KUNIT_CASE(rtc_time64_to_tm_test_date_range),
+	{}
+};
+
+static struct kunit_suite rtc_lib_test_suite = {
+	.name = "rtc_lib_test_cases",
+	.test_cases = rtc_lib_test_cases,
+};
+
+kunit_test_suite(rtc_lib_test_suite);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 670fd8a..eb15067 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -229,19 +229,13 @@
 	if (!pm_trace_rtc_valid())
 		return -EIO;
 
-	/* REVISIT:  if the clock has a "century" register, use
-	 * that instead of the heuristic in mc146818_get_time().
-	 * That'll make Y3K compatility (year > 2070) easy!
-	 */
 	mc146818_get_time(t);
 	return 0;
 }
 
 static int cmos_set_time(struct device *dev, struct rtc_time *t)
 {
-	/* REVISIT:  set the "century" register if available
-	 *
-	 * NOTE: this ignores the issue whereby updating the seconds
+	/* NOTE: this ignores the issue whereby updating the seconds
 	 * takes effect exactly 500ms after we write the register.
 	 * (Also queueing and other delays before we get this far.)
 	 */
diff --git a/drivers/rtc/rtc-rx8025.c b/drivers/rtc/rtc-rx8025.c
index c914091..d38aaf0 100644
--- a/drivers/rtc/rtc-rx8025.c
+++ b/drivers/rtc/rtc-rx8025.c
@@ -60,14 +60,23 @@
 #define RX8025_ADJ_DATA_MAX	62
 #define RX8025_ADJ_DATA_MIN	-62
 
+enum rx_model {
+	model_rx_unknown,
+	model_rx_8025,
+	model_rx_8035,
+	model_last
+};
+
 static const struct i2c_device_id rx8025_id[] = {
-	{ "rx8025", 0 },
+	{ "rx8025", model_rx_8025 },
+	{ "rx8035", model_rx_8035 },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, rx8025_id);
 
 struct rx8025_data {
 	struct rtc_device *rtc;
+	enum rx_model model;
 	u8 ctrl1;
 };
 
@@ -100,10 +109,26 @@
 					      length, values);
 }
 
+static int rx8025_is_osc_stopped(enum rx_model model, int ctrl2)
+{
+	int xstp = ctrl2 & RX8025_BIT_CTRL2_XST;
+	/* XSTP bit has different polarity on RX-8025 vs RX-8035.
+	 * RX-8025: 0 == oscillator stopped
+	 * RX-8035: 1 == oscillator stopped
+	 */
+
+	if (model == model_rx_8025)
+		xstp = !xstp;
+
+	return xstp;
+}
+
 static int rx8025_check_validity(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
+	struct rx8025_data *drvdata = dev_get_drvdata(dev);
 	int ctrl2;
+	int xstp;
 
 	ctrl2 = rx8025_read_reg(client, RX8025_REG_CTRL2);
 	if (ctrl2 < 0)
@@ -117,7 +142,8 @@
 		return -EINVAL;
 	}
 
-	if (!(ctrl2 & RX8025_BIT_CTRL2_XST)) {
+	xstp = rx8025_is_osc_stopped(drvdata->model, ctrl2);
+	if (xstp) {
 		dev_warn(dev, "crystal stopped, date is invalid\n");
 		return -EINVAL;
 	}
@@ -127,6 +153,7 @@
 
 static int rx8025_reset_validity(struct i2c_client *client)
 {
+	struct rx8025_data *drvdata = i2c_get_clientdata(client);
 	int ctrl2 = rx8025_read_reg(client, RX8025_REG_CTRL2);
 
 	if (ctrl2 < 0)
@@ -134,22 +161,28 @@
 
 	ctrl2 &= ~(RX8025_BIT_CTRL2_PON | RX8025_BIT_CTRL2_VDET);
 
+	if (drvdata->model == model_rx_8025)
+		ctrl2 |= RX8025_BIT_CTRL2_XST;
+	else
+		ctrl2 &= ~(RX8025_BIT_CTRL2_XST);
+
 	return rx8025_write_reg(client, RX8025_REG_CTRL2,
-				ctrl2 | RX8025_BIT_CTRL2_XST);
+				ctrl2);
 }
 
 static irqreturn_t rx8025_handle_irq(int irq, void *dev_id)
 {
 	struct i2c_client *client = dev_id;
 	struct rx8025_data *rx8025 = i2c_get_clientdata(client);
-	int status;
+	int status, xstp;
 
 	rtc_lock(rx8025->rtc);
 	status = rx8025_read_reg(client, RX8025_REG_CTRL2);
 	if (status < 0)
 		goto out;
 
-	if (!(status & RX8025_BIT_CTRL2_XST))
+	xstp = rx8025_is_osc_stopped(rx8025->model, status);
+	if (xstp)
 		dev_warn(&client->dev, "Oscillation stop was detected,"
 			 "you may have to readjust the clock\n");
 
@@ -519,6 +552,9 @@
 
 	i2c_set_clientdata(client, rx8025);
 
+	if (id)
+		rx8025->model = id->driver_data;
+
 	err = rx8025_init_client(client);
 	if (err)
 		return err;
diff --git a/drivers/rtc/rtc-s5m.c b/drivers/rtc/rtc-s5m.c
index 6b56f8e..fb9c6b7 100644
--- a/drivers/rtc/rtc-s5m.c
+++ b/drivers/rtc/rtc-s5m.c
@@ -204,15 +204,9 @@
 	data[RTC_WEEKDAY] = 1 << tm->tm_wday;
 	data[RTC_DATE] = tm->tm_mday;
 	data[RTC_MONTH] = tm->tm_mon + 1;
-	data[RTC_YEAR1] = tm->tm_year > 100 ? (tm->tm_year - 100) : 0;
+	data[RTC_YEAR1] = tm->tm_year - 100;
 
-	if (tm->tm_year < 100) {
-		pr_err("RTC cannot handle the year %d\n",
-		       1900 + tm->tm_year);
-		return -EINVAL;
-	} else {
-		return 0;
-	}
+	return 0;
 }
 
 /*
@@ -786,29 +780,35 @@
 	if (ret)
 		return ret;
 
-	device_init_wakeup(&pdev->dev, 1);
-
-	info->rtc_dev = devm_rtc_device_register(&pdev->dev, "s5m-rtc",
-						 &s5m_rtc_ops, THIS_MODULE);
-
+	info->rtc_dev = devm_rtc_allocate_device(&pdev->dev);
 	if (IS_ERR(info->rtc_dev))
 		return PTR_ERR(info->rtc_dev);
 
+	info->rtc_dev->ops = &s5m_rtc_ops;
+
+	if (info->device_type == S5M8763X) {
+		info->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_0000;
+		info->rtc_dev->range_max = RTC_TIMESTAMP_END_9999;
+	} else {
+		info->rtc_dev->range_min = RTC_TIMESTAMP_BEGIN_2000;
+		info->rtc_dev->range_max = RTC_TIMESTAMP_END_2099;
+	}
+
 	if (!info->irq) {
-		dev_info(&pdev->dev, "Alarm IRQ not available\n");
-		return 0;
+		clear_bit(RTC_FEATURE_ALARM, info->rtc_dev->features);
+	} else {
+		ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
+						s5m_rtc_alarm_irq, 0, "rtc-alarm0",
+						info);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
+				info->irq, ret);
+			return ret;
+		}
+		device_init_wakeup(&pdev->dev, 1);
 	}
 
-	ret = devm_request_threaded_irq(&pdev->dev, info->irq, NULL,
-					s5m_rtc_alarm_irq, 0, "rtc-alarm0",
-					info);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "Failed to request alarm IRQ: %d: %d\n",
-			info->irq, ret);
-		return ret;
-	}
-
-	return 0;
+	return devm_rtc_register_device(info->rtc_dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/drivers/rtc/rtc-tps65910.c b/drivers/rtc/rtc-tps65910.c
index bc89c62c..75e4c2d 100644
--- a/drivers/rtc/rtc-tps65910.c
+++ b/drivers/rtc/rtc-tps65910.c
@@ -467,6 +467,6 @@
 };
 
 module_platform_driver(tps65910_rtc_driver);
-MODULE_ALIAS("platform:rtc-tps65910");
+MODULE_ALIAS("platform:tps65910-rtc");
 MODULE_AUTHOR("Venu Byravarasu <vbyravarasu@nvidia.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 823354a..19926be 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -108,9 +108,12 @@
 	NULL
 };
 
+static const struct attribute_group imok_attribute_group = {
+	.attrs = imok_attr,
+};
+
 static const struct attribute_group data_attribute_group = {
 	.bin_attrs = data_attributes,
-	.attrs = imok_attr,
 };
 
 static ssize_t available_uuids_show(struct device *dev,
@@ -522,6 +525,12 @@
 	if (result)
 		goto free_rel_misc;
 
+	if (acpi_has_method(priv->adev->handle, "IMOK")) {
+		result = sysfs_create_group(&pdev->dev.kobj, &imok_attribute_group);
+		if (result)
+			goto free_imok;
+	}
+
 	if (priv->data_vault) {
 		result = sysfs_create_group(&pdev->dev.kobj,
 					    &data_attribute_group);
@@ -545,6 +554,8 @@
 	}
 free_uuid:
 	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
+free_imok:
+	sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group);
 free_rel_misc:
 	if (!priv->rel_misc_dev_res)
 		acpi_thermal_rel_misc_device_remove(priv->adev->handle);
@@ -573,6 +584,7 @@
 	if (priv->data_vault)
 		sysfs_remove_group(&pdev->dev.kobj, &data_attribute_group);
 	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
+	sysfs_remove_group(&pdev->dev.kobj, &imok_attribute_group);
 	thermal_zone_device_unregister(priv->thermal);
 	kfree(priv->data_vault);
 	kfree(priv->trts);
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
index b0eb5ec..a5b58ea 100644
--- a/drivers/thermal/intel/intel_powerclamp.c
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -528,7 +528,7 @@
 
 	set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1);
 	/* prevent cpu hotplug */
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* prefer BSP */
 	control_cpu = 0;
@@ -542,7 +542,7 @@
 	for_each_online_cpu(cpu) {
 		start_power_clamp_worker(cpu);
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
diff --git a/drivers/thermal/intel/intel_tcc_cooling.c b/drivers/thermal/intel/intel_tcc_cooling.c
index 8ec10d5..cd80c7d 100644
--- a/drivers/thermal/intel/intel_tcc_cooling.c
+++ b/drivers/thermal/intel/intel_tcc_cooling.c
@@ -79,6 +79,8 @@
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(TIGERLAKE_L, NULL),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, NULL),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, NULL),
 	{}
 };
 
diff --git a/drivers/thermal/qcom/Kconfig b/drivers/thermal/qcom/Kconfig
index 8d5ac2d..7d942f7 100644
--- a/drivers/thermal/qcom/Kconfig
+++ b/drivers/thermal/qcom/Kconfig
@@ -31,3 +31,13 @@
 	  trip points. The temperature reported by the thermal sensor reflects the
 	  real time die temperature if an ADC is present or an estimate of the
 	  temperature based upon the over temperature stage value.
+
+config QCOM_LMH
+	tristate "Qualcomm Limits Management Hardware"
+	depends on ARCH_QCOM
+	help
+	  This enables initialization of Qualcomm limits management
+	  hardware(LMh). LMh allows for hardware-enforced mitigation for cpus based on
+	  input from temperature and current sensors.  On many newer Qualcomm SoCs
+	  LMh is configured in the firmware and this feature need not be enabled.
+	  However, on certain SoCs like sdm845 LMh has to be configured from kernel.
diff --git a/drivers/thermal/qcom/Makefile b/drivers/thermal/qcom/Makefile
index 252ea7d..0fa2512 100644
--- a/drivers/thermal/qcom/Makefile
+++ b/drivers/thermal/qcom/Makefile
@@ -5,3 +5,4 @@
 				   tsens-8960.o
 obj-$(CONFIG_QCOM_SPMI_ADC_TM5)	+= qcom-spmi-adc-tm5.o
 obj-$(CONFIG_QCOM_SPMI_TEMP_ALARM)	+= qcom-spmi-temp-alarm.o
+obj-$(CONFIG_QCOM_LMH)		+= lmh.o
diff --git a/drivers/thermal/qcom/lmh.c b/drivers/thermal/qcom/lmh.c
new file mode 100644
index 0000000..eafa752
--- /dev/null
+++ b/drivers/thermal/qcom/lmh.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright (C) 2021, Linaro Limited. All rights reserved.
+ */
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
+#include <linux/slab.h>
+#include <linux/qcom_scm.h>
+
+#define LMH_NODE_DCVS			0x44435653
+#define LMH_CLUSTER0_NODE_ID		0x6370302D
+#define LMH_CLUSTER1_NODE_ID		0x6370312D
+
+#define LMH_SUB_FN_THERMAL		0x54484D4C
+#define LMH_SUB_FN_CRNT			0x43524E54
+#define LMH_SUB_FN_REL			0x52454C00
+#define LMH_SUB_FN_BCL			0x42434C00
+
+#define LMH_ALGO_MODE_ENABLE		0x454E424C
+#define LMH_TH_HI_THRESHOLD		0x48494748
+#define LMH_TH_LOW_THRESHOLD		0x4C4F5700
+#define LMH_TH_ARM_THRESHOLD		0x41524D00
+
+#define LMH_REG_DCVS_INTR_CLR		0x8
+
+struct lmh_hw_data {
+	void __iomem *base;
+	struct irq_domain *domain;
+	int irq;
+};
+
+static irqreturn_t lmh_handle_irq(int hw_irq, void *data)
+{
+	struct lmh_hw_data *lmh_data = data;
+	int irq = irq_find_mapping(lmh_data->domain, 0);
+
+	/* Call the cpufreq driver to handle the interrupt */
+	if (irq)
+		generic_handle_irq(irq);
+
+	return 0;
+}
+
+static void lmh_enable_interrupt(struct irq_data *d)
+{
+	struct lmh_hw_data *lmh_data = irq_data_get_irq_chip_data(d);
+
+	/* Clear the existing interrupt */
+	writel(0xff, lmh_data->base + LMH_REG_DCVS_INTR_CLR);
+	enable_irq(lmh_data->irq);
+}
+
+static void lmh_disable_interrupt(struct irq_data *d)
+{
+	struct lmh_hw_data *lmh_data = irq_data_get_irq_chip_data(d);
+
+	disable_irq_nosync(lmh_data->irq);
+}
+
+static struct irq_chip lmh_irq_chip = {
+	.name           = "lmh",
+	.irq_enable	= lmh_enable_interrupt,
+	.irq_disable	= lmh_disable_interrupt
+};
+
+static int lmh_irq_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
+{
+	struct lmh_hw_data *lmh_data = d->host_data;
+
+	irq_set_chip_and_handler(irq, &lmh_irq_chip, handle_simple_irq);
+	irq_set_chip_data(irq, lmh_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops lmh_irq_ops = {
+	.map = lmh_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int lmh_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct device_node *cpu_node;
+	struct lmh_hw_data *lmh_data;
+	int temp_low, temp_high, temp_arm, cpu_id, ret;
+	u32 node_id;
+
+	lmh_data = devm_kzalloc(dev, sizeof(*lmh_data), GFP_KERNEL);
+	if (!lmh_data)
+		return -ENOMEM;
+
+	lmh_data->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(lmh_data->base))
+		return PTR_ERR(lmh_data->base);
+
+	cpu_node = of_parse_phandle(np, "cpus", 0);
+	if (!cpu_node)
+		return -EINVAL;
+	cpu_id = of_cpu_node_to_id(cpu_node);
+	of_node_put(cpu_node);
+
+	ret = of_property_read_u32(np, "qcom,lmh-temp-high-millicelsius", &temp_high);
+	if (ret) {
+		dev_err(dev, "missing qcom,lmh-temp-high-millicelsius property\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "qcom,lmh-temp-low-millicelsius", &temp_low);
+	if (ret) {
+		dev_err(dev, "missing qcom,lmh-temp-low-millicelsius property\n");
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "qcom,lmh-temp-arm-millicelsius", &temp_arm);
+	if (ret) {
+		dev_err(dev, "missing qcom,lmh-temp-arm-millicelsius property\n");
+		return ret;
+	}
+
+	/*
+	 * Only sdm845 has lmh hardware currently enabled from hlos. If this is needed
+	 * for other platforms, revisit this to check if the <cpu-id, node-id> should be part
+	 * of a dt match table.
+	 */
+	if (cpu_id == 0) {
+		node_id = LMH_CLUSTER0_NODE_ID;
+	} else if (cpu_id == 4) {
+		node_id = LMH_CLUSTER1_NODE_ID;
+	} else {
+		dev_err(dev, "Wrong CPU id associated with LMh node\n");
+		return -EINVAL;
+	}
+
+	if (!qcom_scm_lmh_dcvsh_available())
+		return -EINVAL;
+
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_CRNT, LMH_ALGO_MODE_ENABLE, 1,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret)
+		dev_err(dev, "Error %d enabling current subfunction\n", ret);
+
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_REL, LMH_ALGO_MODE_ENABLE, 1,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret)
+		dev_err(dev, "Error %d enabling reliability subfunction\n", ret);
+
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_BCL, LMH_ALGO_MODE_ENABLE, 1,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret)
+		dev_err(dev, "Error %d enabling BCL subfunction\n", ret);
+
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_THERMAL, LMH_ALGO_MODE_ENABLE, 1,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret) {
+		dev_err(dev, "Error %d enabling thermal subfunction\n", ret);
+		return ret;
+	}
+
+	ret = qcom_scm_lmh_profile_change(0x1);
+	if (ret) {
+		dev_err(dev, "Error %d changing profile\n", ret);
+		return ret;
+	}
+
+	/* Set default thermal trips */
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_THERMAL, LMH_TH_ARM_THRESHOLD, temp_arm,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret) {
+		dev_err(dev, "Error setting thermal ARM threshold%d\n", ret);
+		return ret;
+	}
+
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_THERMAL, LMH_TH_HI_THRESHOLD, temp_high,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret) {
+		dev_err(dev, "Error setting thermal HI threshold%d\n", ret);
+		return ret;
+	}
+
+	ret = qcom_scm_lmh_dcvsh(LMH_SUB_FN_THERMAL, LMH_TH_LOW_THRESHOLD, temp_low,
+				 LMH_NODE_DCVS, node_id, 0);
+	if (ret) {
+		dev_err(dev, "Error setting thermal ARM threshold%d\n", ret);
+		return ret;
+	}
+
+	lmh_data->irq = platform_get_irq(pdev, 0);
+	lmh_data->domain = irq_domain_add_linear(np, 1, &lmh_irq_ops, lmh_data);
+	if (!lmh_data->domain) {
+		dev_err(dev, "Error adding irq_domain\n");
+		return -EINVAL;
+	}
+
+	/* Disable the irq and let cpufreq enable it when ready to handle the interrupt */
+	irq_set_status_flags(lmh_data->irq, IRQ_NOAUTOEN);
+	ret = devm_request_irq(dev, lmh_data->irq, lmh_handle_irq,
+			       IRQF_ONESHOT | IRQF_NO_SUSPEND,
+			       "lmh-irq", lmh_data);
+	if (ret) {
+		dev_err(dev, "Error %d registering irq %x\n", ret, lmh_data->irq);
+		irq_domain_remove(lmh_data->domain);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id lmh_table[] = {
+	{ .compatible = "qcom,sdm845-lmh", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, lmh_table);
+
+static struct platform_driver lmh_driver = {
+	.probe = lmh_probe,
+	.driver = {
+		.name = "qcom-lmh",
+		.of_match_table = lmh_table,
+		.suppress_bind_attrs = true,
+	},
+};
+module_platform_driver(lmh_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("QCOM LMh driver");
diff --git a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
index 232fd0b3..8494cc0 100644
--- a/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
+++ b/drivers/thermal/qcom/qcom-spmi-adc-tm5.c
@@ -359,6 +359,12 @@
 							   &adc_tm->channels[i],
 							   &adc_tm5_ops);
 		if (IS_ERR(tzd)) {
+			if (PTR_ERR(tzd) == -ENODEV) {
+				dev_warn(adc_tm->dev, "thermal sensor on channel %d is not used\n",
+					 adc_tm->channels[i].channel);
+				continue;
+			}
+
 			dev_err(adc_tm->dev, "Error registering TZ zone for channel %d: %ld\n",
 				adc_tm->channels[i].channel, PTR_ERR(tzd));
 			return PTR_ERR(tzd);
diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c
index fdf16aa..85228d3 100644
--- a/drivers/thermal/rcar_gen3_thermal.c
+++ b/drivers/thermal/rcar_gen3_thermal.c
@@ -84,7 +84,7 @@
 	struct thermal_zone_device *zone;
 	struct equation_coefs coef;
 	int tj_t;
-	int id; /* thermal channel id */
+	unsigned int id; /* thermal channel id */
 };
 
 struct rcar_gen3_thermal_priv {
@@ -190,10 +190,64 @@
 	return 0;
 }
 
-static const struct thermal_zone_of_device_ops rcar_gen3_tz_of_ops = {
+static int rcar_gen3_thermal_mcelsius_to_temp(struct rcar_gen3_thermal_tsc *tsc,
+					      int mcelsius)
+{
+	int celsius, val;
+
+	celsius = DIV_ROUND_CLOSEST(mcelsius, 1000);
+	if (celsius <= INT_FIXPT(tsc->tj_t))
+		val = celsius * tsc->coef.a1 + tsc->coef.b1;
+	else
+		val = celsius * tsc->coef.a2 + tsc->coef.b2;
+
+	return INT_FIXPT(val);
+}
+
+static int rcar_gen3_thermal_set_trips(void *devdata, int low, int high)
+{
+	struct rcar_gen3_thermal_tsc *tsc = devdata;
+	u32 irqmsk = 0;
+
+	if (low != -INT_MAX) {
+		irqmsk |= IRQ_TEMPD1;
+		rcar_gen3_thermal_write(tsc, REG_GEN3_IRQTEMP1,
+					rcar_gen3_thermal_mcelsius_to_temp(tsc, low));
+	}
+
+	if (high != INT_MAX) {
+		irqmsk |= IRQ_TEMP2;
+		rcar_gen3_thermal_write(tsc, REG_GEN3_IRQTEMP2,
+					rcar_gen3_thermal_mcelsius_to_temp(tsc, high));
+	}
+
+	rcar_gen3_thermal_write(tsc, REG_GEN3_IRQMSK, irqmsk);
+
+	return 0;
+}
+
+static struct thermal_zone_of_device_ops rcar_gen3_tz_of_ops = {
 	.get_temp	= rcar_gen3_thermal_get_temp,
+	.set_trips	= rcar_gen3_thermal_set_trips,
 };
 
+static irqreturn_t rcar_gen3_thermal_irq(int irq, void *data)
+{
+	struct rcar_gen3_thermal_priv *priv = data;
+	unsigned int i;
+	u32 status;
+
+	for (i = 0; i < priv->num_tscs; i++) {
+		status = rcar_gen3_thermal_read(priv->tscs[i], REG_GEN3_IRQSTR);
+		rcar_gen3_thermal_write(priv->tscs[i], REG_GEN3_IRQSTR, 0);
+		if (status)
+			thermal_zone_device_update(priv->tscs[i]->zone,
+						   THERMAL_EVENT_UNSPECIFIED);
+	}
+
+	return IRQ_HANDLED;
+}
+
 static const struct soc_device_attribute r8a7795es1[] = {
 	{ .soc_id = "r8a7795", .revision = "ES1.*" },
 	{ /* sentinel */ }
@@ -210,6 +264,9 @@
 
 	rcar_gen3_thermal_write(tsc, REG_GEN3_IRQCTL, 0x3F);
 	rcar_gen3_thermal_write(tsc, REG_GEN3_IRQMSK, 0);
+	if (tsc->zone->ops->set_trips)
+		rcar_gen3_thermal_write(tsc, REG_GEN3_IRQEN,
+					IRQ_TEMPD1 | IRQ_TEMP2);
 
 	rcar_gen3_thermal_write(tsc, REG_GEN3_CTSR,
 				CTSR_PONM | CTSR_AOUT | CTSR_THBGR | CTSR_VMEN);
@@ -235,6 +292,9 @@
 
 	rcar_gen3_thermal_write(tsc, REG_GEN3_IRQCTL, 0);
 	rcar_gen3_thermal_write(tsc, REG_GEN3_IRQMSK, 0);
+	if (tsc->zone->ops->set_trips)
+		rcar_gen3_thermal_write(tsc, REG_GEN3_IRQEN,
+					IRQ_TEMPD1 | IRQ_TEMP2);
 
 	reg_val = rcar_gen3_thermal_read(tsc, REG_GEN3_THCTR);
 	reg_val |= THCTR_THSST;
@@ -303,6 +363,34 @@
 	thermal_remove_hwmon_sysfs(zone);
 }
 
+static int rcar_gen3_thermal_request_irqs(struct rcar_gen3_thermal_priv *priv,
+					  struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	unsigned int i;
+	char *irqname;
+	int ret, irq;
+
+	for (i = 0; i < 2; i++) {
+		irq = platform_get_irq_optional(pdev, i);
+		if (irq < 0)
+			return irq;
+
+		irqname = devm_kasprintf(dev, GFP_KERNEL, "%s:ch%d",
+					 dev_name(dev), i);
+		if (!irqname)
+			return -ENOMEM;
+
+		ret = devm_request_threaded_irq(dev, irq, NULL,
+						rcar_gen3_thermal_irq,
+						IRQF_ONESHOT, irqname, priv);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int rcar_gen3_thermal_probe(struct platform_device *pdev)
 {
 	struct rcar_gen3_thermal_priv *priv;
@@ -310,7 +398,8 @@
 	const int *ths_tj_1 = of_device_get_match_data(dev);
 	struct resource *res;
 	struct thermal_zone_device *zone;
-	int ret, i;
+	unsigned int i;
+	int ret;
 
 	/* default values if FUSEs are missing */
 	/* TODO: Read values from hardware on supported platforms */
@@ -326,6 +415,9 @@
 
 	platform_set_drvdata(pdev, priv);
 
+	if (rcar_gen3_thermal_request_irqs(priv, pdev))
+		rcar_gen3_tz_of_ops.set_trips = NULL;
+
 	pm_runtime_enable(dev);
 	pm_runtime_get_sync(dev);
 
@@ -351,9 +443,6 @@
 
 		priv->tscs[i] = tsc;
 
-		priv->thermal_init(tsc);
-		rcar_gen3_thermal_calc_coefs(tsc, ptat, thcodes[i], *ths_tj_1);
-
 		zone = devm_thermal_zone_of_sensor_register(dev, i, tsc,
 							    &rcar_gen3_tz_of_ops);
 		if (IS_ERR(zone)) {
@@ -363,6 +452,9 @@
 		}
 		tsc->zone = zone;
 
+		priv->thermal_init(tsc);
+		rcar_gen3_thermal_calc_coefs(tsc, ptat, thcodes[i], *ths_tj_1);
+
 		tsc->zone->tzp->no_hwmon = false;
 		ret = thermal_add_hwmon_sysfs(tsc->zone);
 		if (ret)
@@ -376,7 +468,7 @@
 		if (ret < 0)
 			goto error_unregister;
 
-		dev_info(dev, "TSC%d: Loaded %d trip points\n", i, ret);
+		dev_info(dev, "TSC%u: Loaded %d trip points\n", i, ret);
 	}
 
 	priv->num_tscs = i;
@@ -401,8 +493,12 @@
 
 	for (i = 0; i < priv->num_tscs; i++) {
 		struct rcar_gen3_thermal_tsc *tsc = priv->tscs[i];
+		struct thermal_zone_device *zone = tsc->zone;
 
 		priv->thermal_init(tsc);
+		if (zone->ops->set_trips)
+			rcar_gen3_thermal_set_trips(tsc, zone->prev_low_trip,
+						    zone->prev_high_trip);
 	}
 
 	return 0;
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index e9a90bc..f4ab4c5 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -1073,6 +1073,7 @@
 		data->sclk = devm_clk_get(&pdev->dev, "tmu_sclk");
 		if (IS_ERR(data->sclk)) {
 			dev_err(&pdev->dev, "Failed to get sclk\n");
+			ret = PTR_ERR(data->sclk);
 			goto err_clk;
 		} else {
 			ret = clk_prepare_enable(data->sclk);
diff --git a/drivers/thermal/tegra/Kconfig b/drivers/thermal/tegra/Kconfig
index 46c2215..cfa41d8 100644
--- a/drivers/thermal/tegra/Kconfig
+++ b/drivers/thermal/tegra/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 menu "NVIDIA Tegra thermal drivers"
-depends on ARCH_TEGRA
+depends on ARCH_TEGRA || COMPILE_TEST
 
 config TEGRA_SOCTHERM
 	tristate "Tegra SOCTHERM thermal management"
@@ -18,4 +18,11 @@
 	  Enable this option for support for sensing system temperature of NVIDIA
 	  Tegra systems-on-chip with the BPMP coprocessor (Tegra186).
 
+config TEGRA30_TSENSOR
+	tristate "Tegra30 Thermal Sensor"
+	depends on ARCH_TEGRA_3x_SOC || COMPILE_TEST
+	help
+	  Enable this option to support thermal management of NVIDIA Tegra30
+	  system-on-chip.
+
 endmenu
diff --git a/drivers/thermal/tegra/Makefile b/drivers/thermal/tegra/Makefile
index 0f2b66e..eb27d19 100644
--- a/drivers/thermal/tegra/Makefile
+++ b/drivers/thermal/tegra/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_TEGRA_SOCTHERM)		+= tegra-soctherm.o
 obj-$(CONFIG_TEGRA_BPMP_THERMAL)	+= tegra-bpmp-thermal.o
+obj-$(CONFIG_TEGRA30_TSENSOR)		+= tegra30-tsensor.o
 
 tegra-soctherm-y				:= soctherm.o soctherm-fuse.o
 tegra-soctherm-$(CONFIG_ARCH_TEGRA_124_SOC)	+= tegra124-soctherm.o
diff --git a/drivers/thermal/tegra/soctherm.c b/drivers/thermal/tegra/soctherm.c
index 8e303e9..210325f9 100644
--- a/drivers/thermal/tegra/soctherm.c
+++ b/drivers/thermal/tegra/soctherm.c
@@ -450,8 +450,8 @@
 
 	temp = clamp_val(trip_temp, min_low_temp, max_high_temp);
 	if (temp != trip_temp)
-		dev_info(dev, "soctherm: trip temperature %d forced to %d\n",
-			 trip_temp, temp);
+		dev_dbg(dev, "soctherm: trip temperature %d forced to %d\n",
+			trip_temp, temp);
 	return temp;
 }
 
diff --git a/drivers/thermal/tegra/tegra30-tsensor.c b/drivers/thermal/tegra/tegra30-tsensor.c
new file mode 100644
index 0000000..9b6b693
--- /dev/null
+++ b/drivers/thermal/tegra/tegra30-tsensor.c
@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Tegra30 SoC Thermal Sensor driver
+ *
+ * Based on downstream HWMON driver from NVIDIA.
+ * Copyright (C) 2011 NVIDIA Corporation
+ *
+ * Author: Dmitry Osipenko <digetx@gmail.com>
+ * Copyright (C) 2021 GRATE-DRIVER project
+ */
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+#include <linux/types.h>
+
+#include <soc/tegra/fuse.h>
+
+#include "../thermal_core.h"
+#include "../thermal_hwmon.h"
+
+#define TSENSOR_SENSOR0_CONFIG0				0x0
+#define TSENSOR_SENSOR0_CONFIG0_SENSOR_STOP		BIT(0)
+#define TSENSOR_SENSOR0_CONFIG0_HW_FREQ_DIV_EN		BIT(1)
+#define TSENSOR_SENSOR0_CONFIG0_THERMAL_RST_EN		BIT(2)
+#define TSENSOR_SENSOR0_CONFIG0_DVFS_EN			BIT(3)
+#define TSENSOR_SENSOR0_CONFIG0_INTR_OVERFLOW_EN	BIT(4)
+#define TSENSOR_SENSOR0_CONFIG0_INTR_HW_FREQ_DIV_EN	BIT(5)
+#define TSENSOR_SENSOR0_CONFIG0_INTR_THERMAL_RST_EN	BIT(6)
+#define TSENSOR_SENSOR0_CONFIG0_M			GENMASK(23,  8)
+#define TSENSOR_SENSOR0_CONFIG0_N			GENMASK(31, 24)
+
+#define TSENSOR_SENSOR0_CONFIG1				0x8
+#define TSENSOR_SENSOR0_CONFIG1_TH1			GENMASK(15,  0)
+#define TSENSOR_SENSOR0_CONFIG1_TH2			GENMASK(31, 16)
+
+#define TSENSOR_SENSOR0_CONFIG2				0xc
+#define TSENSOR_SENSOR0_CONFIG2_TH3			GENMASK(15,  0)
+
+#define TSENSOR_SENSOR0_STATUS0				0x18
+#define TSENSOR_SENSOR0_STATUS0_STATE			GENMASK(2, 0)
+#define TSENSOR_SENSOR0_STATUS0_INTR			BIT(8)
+#define TSENSOR_SENSOR0_STATUS0_CURRENT_VALID		BIT(9)
+
+#define TSENSOR_SENSOR0_TS_STATUS1			0x1c
+#define TSENSOR_SENSOR0_TS_STATUS1_CURRENT_COUNT	GENMASK(31, 16)
+
+#define TEGRA30_FUSE_TEST_PROG_VER			0x28
+
+#define TEGRA30_FUSE_TSENSOR_CALIB			0x98
+#define TEGRA30_FUSE_TSENSOR_CALIB_LOW			GENMASK(15,  0)
+#define TEGRA30_FUSE_TSENSOR_CALIB_HIGH			GENMASK(31, 16)
+
+#define TEGRA30_FUSE_SPARE_BIT				0x144
+
+struct tegra_tsensor;
+
+struct tegra_tsensor_calibration_data {
+	int a, b, m, n, p, r;
+};
+
+struct tegra_tsensor_channel {
+	void __iomem *regs;
+	unsigned int id;
+	struct tegra_tsensor *ts;
+	struct thermal_zone_device *tzd;
+};
+
+struct tegra_tsensor {
+	void __iomem *regs;
+	bool swap_channels;
+	struct clk *clk;
+	struct device *dev;
+	struct reset_control *rst;
+	struct tegra_tsensor_channel ch[2];
+	struct tegra_tsensor_calibration_data calib;
+};
+
+static int tegra_tsensor_hw_enable(const struct tegra_tsensor *ts)
+{
+	u32 val;
+	int err;
+
+	err = reset_control_assert(ts->rst);
+	if (err) {
+		dev_err(ts->dev, "failed to assert hardware reset: %d\n", err);
+		return err;
+	}
+
+	err = clk_prepare_enable(ts->clk);
+	if (err) {
+		dev_err(ts->dev, "failed to enable clock: %d\n", err);
+		return err;
+	}
+
+	fsleep(1000);
+
+	err = reset_control_deassert(ts->rst);
+	if (err) {
+		dev_err(ts->dev, "failed to deassert hardware reset: %d\n", err);
+		goto disable_clk;
+	}
+
+	/*
+	 * Sensors are enabled after reset by default, but not gauging
+	 * until clock counter is programmed.
+	 *
+	 * M: number of reference clock pulses after which every
+	 *    temperature / voltage measurement is made
+	 *
+	 * N: number of reference clock counts for which the counter runs
+	 */
+	val  = FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_M, 12500);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_N, 255);
+
+	/* apply the same configuration to both channels */
+	writel_relaxed(val, ts->regs + 0x40 + TSENSOR_SENSOR0_CONFIG0);
+	writel_relaxed(val, ts->regs + 0x80 + TSENSOR_SENSOR0_CONFIG0);
+
+	return 0;
+
+disable_clk:
+	clk_disable_unprepare(ts->clk);
+
+	return err;
+}
+
+static int tegra_tsensor_hw_disable(const struct tegra_tsensor *ts)
+{
+	int err;
+
+	err = reset_control_assert(ts->rst);
+	if (err) {
+		dev_err(ts->dev, "failed to assert hardware reset: %d\n", err);
+		return err;
+	}
+
+	clk_disable_unprepare(ts->clk);
+
+	return 0;
+}
+
+static void devm_tegra_tsensor_hw_disable(void *data)
+{
+	const struct tegra_tsensor *ts = data;
+
+	tegra_tsensor_hw_disable(ts);
+}
+
+static int tegra_tsensor_get_temp(void *data, int *temp)
+{
+	const struct tegra_tsensor_channel *tsc = data;
+	const struct tegra_tsensor *ts = tsc->ts;
+	int err, c1, c2, c3, c4, counter;
+	u32 val;
+
+	/*
+	 * Counter will be invalid if hardware is misprogrammed or not enough
+	 * time passed since the time when sensor was enabled.
+	 */
+	err = readl_relaxed_poll_timeout(tsc->regs + TSENSOR_SENSOR0_STATUS0, val,
+					 val & TSENSOR_SENSOR0_STATUS0_CURRENT_VALID,
+					 21 * USEC_PER_MSEC,
+					 21 * USEC_PER_MSEC * 50);
+	if (err) {
+		dev_err_once(ts->dev, "ch%u: counter invalid\n", tsc->id);
+		return err;
+	}
+
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_TS_STATUS1);
+	counter = FIELD_GET(TSENSOR_SENSOR0_TS_STATUS1_CURRENT_COUNT, val);
+
+	/*
+	 * This shouldn't happen with a valid counter status, nevertheless
+	 * lets verify the value since it's in a separate (from status)
+	 * register.
+	 */
+	if (counter == 0xffff) {
+		dev_err_once(ts->dev, "ch%u: counter overflow\n", tsc->id);
+		return -EINVAL;
+	}
+
+	/*
+	 * temperature = a * counter + b
+	 * temperature = m * (temperature ^ 2) + n * temperature + p
+	 */
+	c1 = DIV_ROUND_CLOSEST(ts->calib.a * counter + ts->calib.b, 1000000);
+	c1 = c1 ?: 1;
+	c2 = DIV_ROUND_CLOSEST(ts->calib.p, c1);
+	c3 = c1 * ts->calib.m;
+	c4 = ts->calib.n;
+
+	*temp = DIV_ROUND_CLOSEST(c1 * (c2 + c3 + c4), 1000);
+
+	return 0;
+}
+
+static int tegra_tsensor_temp_to_counter(const struct tegra_tsensor *ts, int temp)
+{
+	int c1, c2;
+
+	c1 = DIV_ROUND_CLOSEST(ts->calib.p - temp * 1000, ts->calib.m);
+	c2 = -ts->calib.r - int_sqrt(ts->calib.r * ts->calib.r - c1);
+
+	return DIV_ROUND_CLOSEST(c2 * 1000000 - ts->calib.b, ts->calib.a);
+}
+
+static int tegra_tsensor_set_trips(void *data, int low, int high)
+{
+	const struct tegra_tsensor_channel *tsc = data;
+	const struct tegra_tsensor *ts = tsc->ts;
+	u32 val;
+
+	/*
+	 * TSENSOR doesn't trigger interrupt on the "low" temperature breach,
+	 * hence bail out if high temperature is unspecified.
+	 */
+	if (high == INT_MAX)
+		return 0;
+
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_CONFIG1);
+	val &= ~TSENSOR_SENSOR0_CONFIG1_TH1;
+
+	high = tegra_tsensor_temp_to_counter(ts, high);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG1_TH1, high);
+	writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_CONFIG1);
+
+	return 0;
+}
+
+static const struct thermal_zone_of_device_ops ops = {
+	.get_temp = tegra_tsensor_get_temp,
+	.set_trips = tegra_tsensor_set_trips,
+};
+
+static bool
+tegra_tsensor_handle_channel_interrupt(const struct tegra_tsensor *ts,
+				       unsigned int id)
+{
+	const struct tegra_tsensor_channel *tsc = &ts->ch[id];
+	u32 val;
+
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_STATUS0);
+	writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_STATUS0);
+
+	if (FIELD_GET(TSENSOR_SENSOR0_STATUS0_STATE, val) == 5)
+		dev_err_ratelimited(ts->dev, "ch%u: counter overflowed\n", id);
+
+	if (!FIELD_GET(TSENSOR_SENSOR0_STATUS0_INTR, val))
+		return false;
+
+	thermal_zone_device_update(tsc->tzd, THERMAL_EVENT_UNSPECIFIED);
+
+	return true;
+}
+
+static irqreturn_t tegra_tsensor_isr(int irq, void *data)
+{
+	const struct tegra_tsensor *ts = data;
+	bool handled = false;
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(ts->ch); i++)
+		handled |= tegra_tsensor_handle_channel_interrupt(ts, i);
+
+	return handled ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static int tegra_tsensor_disable_hw_channel(const struct tegra_tsensor *ts,
+					    unsigned int id)
+{
+	const struct tegra_tsensor_channel *tsc = &ts->ch[id];
+	struct thermal_zone_device *tzd = tsc->tzd;
+	u32 val;
+	int err;
+
+	if (!tzd)
+		goto stop_channel;
+
+	err = thermal_zone_device_disable(tzd);
+	if (err) {
+		dev_err(ts->dev, "ch%u: failed to disable zone: %d\n", id, err);
+		return err;
+	}
+
+stop_channel:
+	/* stop channel gracefully */
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_CONFIG0);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_SENSOR_STOP, 1);
+	writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_CONFIG0);
+
+	return 0;
+}
+
+static void tegra_tsensor_get_hw_channel_trips(struct thermal_zone_device *tzd,
+					       int *hot_trip, int *crit_trip)
+{
+	unsigned int i;
+
+	/*
+	 * 90C is the maximal critical temperature of all Tegra30 SoC variants,
+	 * use it for the default trip if unspecified in a device-tree.
+	 */
+	*hot_trip  = 85000;
+	*crit_trip = 90000;
+
+	for (i = 0; i < tzd->trips; i++) {
+		enum thermal_trip_type type;
+		int trip_temp;
+
+		tzd->ops->get_trip_temp(tzd, i, &trip_temp);
+		tzd->ops->get_trip_type(tzd, i, &type);
+
+		if (type == THERMAL_TRIP_HOT)
+			*hot_trip = trip_temp;
+
+		if (type == THERMAL_TRIP_CRITICAL)
+			*crit_trip = trip_temp;
+	}
+
+	/* clamp hardware trips to the calibration limits */
+	*hot_trip = clamp(*hot_trip, 25000, 90000);
+
+	/*
+	 * Kernel will perform a normal system shut down if it will
+	 * see that critical temperature is breached, hence set the
+	 * hardware limit by 5C higher in order to allow system to
+	 * shut down gracefully before sending signal to the Power
+	 * Management controller.
+	 */
+	*crit_trip = clamp(*crit_trip + 5000, 25000, 90000);
+}
+
+static int tegra_tsensor_enable_hw_channel(const struct tegra_tsensor *ts,
+					   unsigned int id)
+{
+	const struct tegra_tsensor_channel *tsc = &ts->ch[id];
+	struct thermal_zone_device *tzd = tsc->tzd;
+	int err, hot_trip = 0, crit_trip = 0;
+	u32 val;
+
+	if (!tzd) {
+		val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_CONFIG0);
+		val &= ~TSENSOR_SENSOR0_CONFIG0_SENSOR_STOP;
+		writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_CONFIG0);
+
+		return 0;
+	}
+
+	tegra_tsensor_get_hw_channel_trips(tzd, &hot_trip, &crit_trip);
+
+	/* prevent potential racing with tegra_tsensor_set_trips() */
+	mutex_lock(&tzd->lock);
+
+	dev_info_once(ts->dev, "ch%u: PMC emergency shutdown trip set to %dC\n",
+		      id, DIV_ROUND_CLOSEST(crit_trip, 1000));
+
+	hot_trip  = tegra_tsensor_temp_to_counter(ts, hot_trip);
+	crit_trip = tegra_tsensor_temp_to_counter(ts, crit_trip);
+
+	/* program LEVEL2 counter threshold */
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_CONFIG1);
+	val &= ~TSENSOR_SENSOR0_CONFIG1_TH2;
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG1_TH2, hot_trip);
+	writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_CONFIG1);
+
+	/* program LEVEL3 counter threshold */
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_CONFIG2);
+	val &= ~TSENSOR_SENSOR0_CONFIG2_TH3;
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG2_TH3, crit_trip);
+	writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_CONFIG2);
+
+	/*
+	 * Enable sensor, emergency shutdown, interrupts for level 1/2/3
+	 * breaches and counter overflow condition.
+	 *
+	 * Disable DIV2 throttle for now since we need to figure out how
+	 * to integrate it properly with the thermal framework.
+	 *
+	 * Thermal levels supported by hardware:
+	 *
+	 *     Level 0 = cold
+	 *     Level 1 = passive cooling (cpufreq DVFS)
+	 *     Level 2 = passive cooling assisted by hardware (DIV2)
+	 *     Level 3 = emergency shutdown assisted by hardware (PMC)
+	 */
+	val = readl_relaxed(tsc->regs + TSENSOR_SENSOR0_CONFIG0);
+	val &= ~TSENSOR_SENSOR0_CONFIG0_SENSOR_STOP;
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_DVFS_EN, 1);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_HW_FREQ_DIV_EN, 0);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_THERMAL_RST_EN, 1);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_INTR_OVERFLOW_EN, 1);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_INTR_HW_FREQ_DIV_EN, 1);
+	val |= FIELD_PREP(TSENSOR_SENSOR0_CONFIG0_INTR_THERMAL_RST_EN, 1);
+	writel_relaxed(val, tsc->regs + TSENSOR_SENSOR0_CONFIG0);
+
+	mutex_unlock(&tzd->lock);
+
+	err = thermal_zone_device_enable(tzd);
+	if (err) {
+		dev_err(ts->dev, "ch%u: failed to enable zone: %d\n", id, err);
+		return err;
+	}
+
+	return 0;
+}
+
+static bool tegra_tsensor_fuse_read_spare(unsigned int spare)
+{
+	u32 val = 0;
+
+	tegra_fuse_readl(TEGRA30_FUSE_SPARE_BIT + spare * 4, &val);
+
+	return !!val;
+}
+
+static int tegra_tsensor_nvmem_setup(struct tegra_tsensor *ts)
+{
+	u32 i, ate_ver = 0, cal = 0, t1_25C = 0, t2_90C = 0;
+	int err, c1_25C, c2_90C;
+
+	err = tegra_fuse_readl(TEGRA30_FUSE_TEST_PROG_VER, &ate_ver);
+	if (err) {
+		dev_err_probe(ts->dev, err, "failed to get ATE version\n");
+		return err;
+	}
+
+	if (ate_ver < 8) {
+		dev_info(ts->dev, "unsupported ATE version: %u\n", ate_ver);
+		return -ENODEV;
+	}
+
+	/*
+	 * We have two TSENSOR channels in a two different spots on SoC.
+	 * Second channel provides more accurate data on older SoC versions,
+	 * use it as a primary channel.
+	 */
+	if (ate_ver <= 21) {
+		dev_info_once(ts->dev,
+			      "older ATE version detected, channels remapped\n");
+		ts->swap_channels = true;
+	}
+
+	err = tegra_fuse_readl(TEGRA30_FUSE_TSENSOR_CALIB, &cal);
+	if (err) {
+		dev_err(ts->dev, "failed to get calibration data: %d\n", err);
+		return err;
+	}
+
+	/* get calibrated counter values for 25C/90C thresholds */
+	c1_25C = FIELD_GET(TEGRA30_FUSE_TSENSOR_CALIB_LOW, cal);
+	c2_90C = FIELD_GET(TEGRA30_FUSE_TSENSOR_CALIB_HIGH, cal);
+
+	/* and calibrated temperatures corresponding to the counter values */
+	for (i = 0; i < 7; i++) {
+		t1_25C |= tegra_tsensor_fuse_read_spare(14 + i) << i;
+		t1_25C |= tegra_tsensor_fuse_read_spare(21 + i) << i;
+
+		t2_90C |= tegra_tsensor_fuse_read_spare(0 + i) << i;
+		t2_90C |= tegra_tsensor_fuse_read_spare(7 + i) << i;
+	}
+
+	if (c2_90C - c1_25C <= t2_90C - t1_25C) {
+		dev_err(ts->dev, "invalid calibration data: %d %d %u %u\n",
+			c2_90C, c1_25C, t2_90C, t1_25C);
+		return -EINVAL;
+	}
+
+	/* all calibration coefficients are premultiplied by 1000000 */
+
+	ts->calib.a = DIV_ROUND_CLOSEST((t2_90C - t1_25C) * 1000000,
+					(c2_90C - c1_25C));
+
+	ts->calib.b = t1_25C * 1000000 - ts->calib.a * c1_25C;
+
+	if (tegra_sku_info.revision == TEGRA_REVISION_A01) {
+		ts->calib.m =     -2775;
+		ts->calib.n =   1338811;
+		ts->calib.p =  -7300000;
+	} else {
+		ts->calib.m =     -3512;
+		ts->calib.n =   1528943;
+		ts->calib.p = -11100000;
+	}
+
+	/* except the coefficient of a reduced quadratic equation */
+	ts->calib.r = DIV_ROUND_CLOSEST(ts->calib.n, ts->calib.m * 2);
+
+	dev_info_once(ts->dev,
+		      "calibration: %d %d %u %u ATE ver: %u SoC rev: %u\n",
+		      c2_90C, c1_25C, t2_90C, t1_25C, ate_ver,
+		      tegra_sku_info.revision);
+
+	return 0;
+}
+
+static int tegra_tsensor_register_channel(struct tegra_tsensor *ts,
+					  unsigned int id)
+{
+	struct tegra_tsensor_channel *tsc = &ts->ch[id];
+	unsigned int hw_id = ts->swap_channels ? !id : id;
+
+	tsc->ts = ts;
+	tsc->id = id;
+	tsc->regs = ts->regs + 0x40 * (hw_id + 1);
+
+	tsc->tzd = devm_thermal_zone_of_sensor_register(ts->dev, id, tsc, &ops);
+	if (IS_ERR(tsc->tzd)) {
+		if (PTR_ERR(tsc->tzd) != -ENODEV)
+			return dev_err_probe(ts->dev, PTR_ERR(tsc->tzd),
+					     "failed to register thermal zone\n");
+
+		/*
+		 * It's okay if sensor isn't assigned to any thermal zone
+		 * in a device-tree.
+		 */
+		tsc->tzd = NULL;
+		return 0;
+	}
+
+	if (devm_thermal_add_hwmon_sysfs(tsc->tzd))
+		dev_warn(ts->dev, "failed to add hwmon sysfs attributes\n");
+
+	return 0;
+}
+
+static int tegra_tsensor_probe(struct platform_device *pdev)
+{
+	struct tegra_tsensor *ts;
+	unsigned int i;
+	int err, irq;
+
+	ts = devm_kzalloc(&pdev->dev, sizeof(*ts), GFP_KERNEL);
+	if (!ts)
+		return -ENOMEM;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	ts->dev = &pdev->dev;
+	platform_set_drvdata(pdev, ts);
+
+	ts->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(ts->regs))
+		return PTR_ERR(ts->regs);
+
+	ts->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(ts->clk))
+		return dev_err_probe(&pdev->dev, PTR_ERR(ts->clk),
+				     "failed to get clock\n");
+
+	ts->rst = devm_reset_control_get_exclusive(&pdev->dev, NULL);
+	if (IS_ERR(ts->rst))
+		return dev_err_probe(&pdev->dev, PTR_ERR(ts->rst),
+				     "failed to get reset control\n");
+
+	err = tegra_tsensor_nvmem_setup(ts);
+	if (err)
+		return err;
+
+	err = tegra_tsensor_hw_enable(ts);
+	if (err)
+		return err;
+
+	err = devm_add_action_or_reset(&pdev->dev,
+				       devm_tegra_tsensor_hw_disable,
+				       ts);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(ts->ch); i++) {
+		err = tegra_tsensor_register_channel(ts, i);
+		if (err)
+			return err;
+	}
+
+	err = devm_request_threaded_irq(&pdev->dev, irq, NULL,
+					tegra_tsensor_isr, IRQF_ONESHOT,
+					"tegra_tsensor", ts);
+	if (err)
+		return dev_err_probe(&pdev->dev, err,
+				     "failed to request interrupt\n");
+
+	for (i = 0; i < ARRAY_SIZE(ts->ch); i++) {
+		err = tegra_tsensor_enable_hw_channel(ts, i);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int __maybe_unused tegra_tsensor_suspend(struct device *dev)
+{
+	struct tegra_tsensor *ts = dev_get_drvdata(dev);
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < ARRAY_SIZE(ts->ch); i++) {
+		err = tegra_tsensor_disable_hw_channel(ts, i);
+		if (err)
+			goto enable_channel;
+	}
+
+	err = tegra_tsensor_hw_disable(ts);
+	if (err)
+		goto enable_channel;
+
+	return 0;
+
+enable_channel:
+	while (i--)
+		tegra_tsensor_enable_hw_channel(ts, i);
+
+	return err;
+}
+
+static int __maybe_unused tegra_tsensor_resume(struct device *dev)
+{
+	struct tegra_tsensor *ts = dev_get_drvdata(dev);
+	unsigned int i;
+	int err;
+
+	err = tegra_tsensor_hw_enable(ts);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(ts->ch); i++) {
+		err = tegra_tsensor_enable_hw_channel(ts, i);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const struct dev_pm_ops tegra_tsensor_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(tegra_tsensor_suspend,
+				      tegra_tsensor_resume)
+};
+
+static const struct of_device_id tegra_tsensor_of_match[] = {
+	{ .compatible = "nvidia,tegra30-tsensor", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, tegra_tsensor_of_match);
+
+static struct platform_driver tegra_tsensor_driver = {
+	.probe = tegra_tsensor_probe,
+	.driver = {
+		.name = "tegra30-tsensor",
+		.of_match_table = tegra_tsensor_of_match,
+		.pm = &tegra_tsensor_pm_ops,
+	},
+};
+module_platform_driver(tegra_tsensor_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra30 Thermal Sensor driver");
+MODULE_AUTHOR("Dmitry Osipenko <digetx@gmail.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/vdpa/Kconfig b/drivers/vdpa/Kconfig
index a503c1b..3d91982 100644
--- a/drivers/vdpa/Kconfig
+++ b/drivers/vdpa/Kconfig
@@ -33,6 +33,16 @@
 	  vDPA block device simulator which terminates IO request in a
 	  memory buffer.
 
+config VDPA_USER
+	tristate "VDUSE (vDPA Device in Userspace) support"
+	depends on EVENTFD && MMU && HAS_DMA
+	select DMA_OPS
+	select VHOST_IOTLB
+	select IOMMU_IOVA
+	help
+	  With VDUSE it is possible to emulate a vDPA Device
+	  in a userspace program.
+
 config IFCVF
 	tristate "Intel IFC VF vDPA driver"
 	depends on PCI_MSI
@@ -53,6 +63,7 @@
 config MLX5_VDPA_NET
 	tristate "vDPA driver for ConnectX devices"
 	select MLX5_VDPA
+	select VHOST_RING
 	depends on MLX5_CORE
 	help
 	  VDPA network driver for ConnectX6 and newer. Provides offloading
diff --git a/drivers/vdpa/Makefile b/drivers/vdpa/Makefile
index 67fe7f3..f02ebed 100644
--- a/drivers/vdpa/Makefile
+++ b/drivers/vdpa/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_VDPA) += vdpa.o
 obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
+obj-$(CONFIG_VDPA_USER) += vdpa_user/
 obj-$(CONFIG_IFCVF)    += ifcvf/
 obj-$(CONFIG_MLX5_VDPA) += mlx5/
 obj-$(CONFIG_VP_VDPA)    += virtio_pci/
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.c b/drivers/vdpa/ifcvf/ifcvf_base.c
index 6e197fe..2808f1b 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.c
+++ b/drivers/vdpa/ifcvf/ifcvf_base.c
@@ -158,7 +158,9 @@
 		return -EIO;
 	}
 
-	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+	hw->nr_vring = ifc_ioread16(&hw->common_cfg->num_queues);
+
+	for (i = 0; i < hw->nr_vring; i++) {
 		ifc_iowrite16(i, &hw->common_cfg->queue_select);
 		notify_off = ifc_ioread16(&hw->common_cfg->queue_notify_off);
 		hw->vring[i].notify_addr = hw->notify_base +
@@ -304,7 +306,7 @@
 	u32 q_pair_id;
 
 	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
-	q_pair_id = qid / (IFCVF_MAX_QUEUE_PAIRS * 2);
+	q_pair_id = qid / hw->nr_vring;
 	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
 	last_avail_idx = ifc_ioread16(avail_idx_addr);
 
@@ -318,7 +320,7 @@
 	u32 q_pair_id;
 
 	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
-	q_pair_id = qid / (IFCVF_MAX_QUEUE_PAIRS * 2);
+	q_pair_id = qid / hw->nr_vring;
 	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
 	hw->vring[qid].last_avail_idx = num;
 	ifc_iowrite16(num, avail_idx_addr);
diff --git a/drivers/vdpa/ifcvf/ifcvf_base.h b/drivers/vdpa/ifcvf/ifcvf_base.h
index 2996db0..09918af 100644
--- a/drivers/vdpa/ifcvf/ifcvf_base.h
+++ b/drivers/vdpa/ifcvf/ifcvf_base.h
@@ -22,17 +22,8 @@
 #define N3000_DEVICE_ID		0x1041
 #define N3000_SUBSYS_DEVICE_ID	0x001A
 
-#define IFCVF_NET_SUPPORTED_FEATURES \
-		((1ULL << VIRTIO_NET_F_MAC)			| \
-		 (1ULL << VIRTIO_F_ANY_LAYOUT)			| \
-		 (1ULL << VIRTIO_F_VERSION_1)			| \
-		 (1ULL << VIRTIO_NET_F_STATUS)			| \
-		 (1ULL << VIRTIO_F_ORDER_PLATFORM)		| \
-		 (1ULL << VIRTIO_F_ACCESS_PLATFORM)		| \
-		 (1ULL << VIRTIO_NET_F_MRG_RXBUF))
-
-/* Only one queue pair for now. */
-#define IFCVF_MAX_QUEUE_PAIRS	1
+/* Max 8 data queue pairs(16 queues) and one control vq for now. */
+#define IFCVF_MAX_QUEUES	17
 
 #define IFCVF_QUEUE_ALIGNMENT	PAGE_SIZE
 #define IFCVF_QUEUE_MAX		32768
@@ -51,8 +42,6 @@
 #define ifcvf_private_to_vf(adapter) \
 	(&((struct ifcvf_adapter *)adapter)->vf)
 
-#define IFCVF_MAX_INTR (IFCVF_MAX_QUEUE_PAIRS * 2 + 1)
-
 struct vring_info {
 	u64 desc;
 	u64 avail;
@@ -83,7 +72,7 @@
 	u32 dev_type;
 	struct virtio_pci_common_cfg __iomem *common_cfg;
 	void __iomem *net_cfg;
-	struct vring_info vring[IFCVF_MAX_QUEUE_PAIRS * 2];
+	struct vring_info vring[IFCVF_MAX_QUEUES];
 	void __iomem * const *base;
 	char config_msix_name[256];
 	struct vdpa_callback config_cb;
@@ -103,7 +92,13 @@
 
 struct ifcvf_lm_cfg {
 	u8 reserved[IFCVF_LM_RING_STATE_OFFSET];
-	struct ifcvf_vring_lm_cfg vring_lm_cfg[IFCVF_MAX_QUEUE_PAIRS];
+	struct ifcvf_vring_lm_cfg vring_lm_cfg[IFCVF_MAX_QUEUES];
+};
+
+struct ifcvf_vdpa_mgmt_dev {
+	struct vdpa_mgmt_dev mdev;
+	struct ifcvf_adapter *adapter;
+	struct pci_dev *pdev;
 };
 
 int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev);
diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
index 351c6cf..dcd648e 100644
--- a/drivers/vdpa/ifcvf/ifcvf_main.c
+++ b/drivers/vdpa/ifcvf/ifcvf_main.c
@@ -63,9 +63,13 @@
 	struct pci_dev *pdev = adapter->pdev;
 	struct ifcvf_hw *vf = &adapter->vf;
 	int vector, i, ret, irq;
+	u16 max_intr;
 
-	ret = pci_alloc_irq_vectors(pdev, IFCVF_MAX_INTR,
-				    IFCVF_MAX_INTR, PCI_IRQ_MSIX);
+	/* all queues and config interrupt  */
+	max_intr = vf->nr_vring + 1;
+
+	ret = pci_alloc_irq_vectors(pdev, max_intr,
+				    max_intr, PCI_IRQ_MSIX);
 	if (ret < 0) {
 		IFCVF_ERR(pdev, "Failed to alloc IRQ vectors\n");
 		return ret;
@@ -83,7 +87,7 @@
 		return ret;
 	}
 
-	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+	for (i = 0; i < vf->nr_vring; i++) {
 		snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n",
 			 pci_name(pdev), i);
 		vector = i + IFCVF_MSI_QUEUE_OFF;
@@ -112,7 +116,6 @@
 	u8 status;
 	int ret;
 
-	vf->nr_vring = IFCVF_MAX_QUEUE_PAIRS * 2;
 	ret = ifcvf_start_hw(vf);
 	if (ret < 0) {
 		status = ifcvf_get_status(vf);
@@ -128,7 +131,7 @@
 	struct ifcvf_hw *vf = ifcvf_private_to_vf(private);
 	int i;
 
-	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
+	for (i = 0; i < vf->nr_vring; i++)
 		vf->vring[i].cb.callback = NULL;
 
 	ifcvf_stop_hw(vf);
@@ -141,7 +144,7 @@
 	struct ifcvf_hw *vf = ifcvf_private_to_vf(adapter);
 	int i;
 
-	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+	for (i = 0; i < vf->nr_vring; i++) {
 		vf->vring[i].last_avail_idx = 0;
 		vf->vring[i].desc = 0;
 		vf->vring[i].avail = 0;
@@ -171,17 +174,12 @@
 	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
 	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
 	struct pci_dev *pdev = adapter->pdev;
-
+	u32 type = vf->dev_type;
 	u64 features;
 
-	switch (vf->dev_type) {
-	case VIRTIO_ID_NET:
-		features = ifcvf_get_features(vf) & IFCVF_NET_SUPPORTED_FEATURES;
-		break;
-	case VIRTIO_ID_BLOCK:
+	if (type == VIRTIO_ID_NET || type == VIRTIO_ID_BLOCK)
 		features = ifcvf_get_features(vf);
-		break;
-	default:
+	else {
 		features = 0;
 		IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", vf->dev_type);
 	}
@@ -218,23 +216,12 @@
 	int ret;
 
 	vf  = vdpa_to_vf(vdpa_dev);
-	adapter = dev_get_drvdata(vdpa_dev->dev.parent);
+	adapter = vdpa_to_adapter(vdpa_dev);
 	status_old = ifcvf_get_status(vf);
 
 	if (status_old == status)
 		return;
 
-	if ((status_old & VIRTIO_CONFIG_S_DRIVER_OK) &&
-	    !(status & VIRTIO_CONFIG_S_DRIVER_OK)) {
-		ifcvf_stop_datapath(adapter);
-		ifcvf_free_irq(adapter, IFCVF_MAX_QUEUE_PAIRS * 2);
-	}
-
-	if (status == 0) {
-		ifcvf_reset_vring(adapter);
-		return;
-	}
-
 	if ((status & VIRTIO_CONFIG_S_DRIVER_OK) &&
 	    !(status_old & VIRTIO_CONFIG_S_DRIVER_OK)) {
 		ret = ifcvf_request_irq(adapter);
@@ -254,6 +241,29 @@
 	ifcvf_set_status(vf, status);
 }
 
+static int ifcvf_vdpa_reset(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_adapter *adapter;
+	struct ifcvf_hw *vf;
+	u8 status_old;
+
+	vf  = vdpa_to_vf(vdpa_dev);
+	adapter = vdpa_to_adapter(vdpa_dev);
+	status_old = ifcvf_get_status(vf);
+
+	if (status_old == 0)
+		return 0;
+
+	if (status_old & VIRTIO_CONFIG_S_DRIVER_OK) {
+		ifcvf_stop_datapath(adapter);
+		ifcvf_free_irq(adapter, vf->nr_vring);
+	}
+
+	ifcvf_reset_vring(adapter);
+
+	return 0;
+}
+
 static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
 {
 	return IFCVF_QUEUE_MAX;
@@ -437,6 +447,7 @@
 	.set_features	= ifcvf_vdpa_set_features,
 	.get_status	= ifcvf_vdpa_get_status,
 	.set_status	= ifcvf_vdpa_set_status,
+	.reset		= ifcvf_vdpa_reset,
 	.get_vq_num_max	= ifcvf_vdpa_get_vq_num_max,
 	.get_vq_state	= ifcvf_vdpa_get_vq_state,
 	.set_vq_state	= ifcvf_vdpa_set_vq_state,
@@ -458,50 +469,19 @@
 	.get_vq_notification = ifcvf_get_vq_notification,
 };
 
-static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+static struct virtio_device_id id_table_net[] = {
+	{VIRTIO_ID_NET, VIRTIO_DEV_ANY_ID},
+	{0},
+};
+
+static struct virtio_device_id id_table_blk[] = {
+	{VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID},
+	{0},
+};
+
+static u32 get_dev_type(struct pci_dev *pdev)
 {
-	struct device *dev = &pdev->dev;
-	struct ifcvf_adapter *adapter;
-	struct ifcvf_hw *vf;
-	int ret, i;
-
-	ret = pcim_enable_device(pdev);
-	if (ret) {
-		IFCVF_ERR(pdev, "Failed to enable device\n");
-		return ret;
-	}
-
-	ret = pcim_iomap_regions(pdev, BIT(0) | BIT(2) | BIT(4),
-				 IFCVF_DRIVER_NAME);
-	if (ret) {
-		IFCVF_ERR(pdev, "Failed to request MMIO region\n");
-		return ret;
-	}
-
-	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
-	if (ret) {
-		IFCVF_ERR(pdev, "No usable DMA configuration\n");
-		return ret;
-	}
-
-	ret = devm_add_action_or_reset(dev, ifcvf_free_irq_vectors, pdev);
-	if (ret) {
-		IFCVF_ERR(pdev,
-			  "Failed for adding devres for freeing irq vectors\n");
-		return ret;
-	}
-
-	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
-				    dev, &ifc_vdpa_ops, NULL);
-	if (IS_ERR(adapter)) {
-		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
-		return PTR_ERR(adapter);
-	}
-
-	pci_set_master(pdev);
-	pci_set_drvdata(pdev, adapter);
-
-	vf = &adapter->vf;
+	u32 dev_type;
 
 	/* This drirver drives both modern virtio devices and transitional
 	 * devices in modern mode.
@@ -510,11 +490,42 @@
 	 * mode will not work for vDPA, this driver will not
 	 * drive devices with legacy interface.
 	 */
-	if (pdev->device < 0x1040)
-		vf->dev_type =  pdev->subsystem_device;
-	else
-		vf->dev_type =  pdev->device - 0x1040;
 
+	if (pdev->device < 0x1040)
+		dev_type =  pdev->subsystem_device;
+	else
+		dev_type =  pdev->device - 0x1040;
+
+	return dev_type;
+}
+
+static int ifcvf_vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+	struct ifcvf_adapter *adapter;
+	struct pci_dev *pdev;
+	struct ifcvf_hw *vf;
+	struct device *dev;
+	int ret, i;
+
+	ifcvf_mgmt_dev = container_of(mdev, struct ifcvf_vdpa_mgmt_dev, mdev);
+	if (ifcvf_mgmt_dev->adapter)
+		return -EOPNOTSUPP;
+
+	pdev = ifcvf_mgmt_dev->pdev;
+	dev = &pdev->dev;
+	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
+				    dev, &ifc_vdpa_ops, name, false);
+	if (IS_ERR(adapter)) {
+		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
+		return PTR_ERR(adapter);
+	}
+
+	ifcvf_mgmt_dev->adapter = adapter;
+	pci_set_drvdata(pdev, ifcvf_mgmt_dev);
+
+	vf = &adapter->vf;
+	vf->dev_type = get_dev_type(pdev);
 	vf->base = pcim_iomap_table(pdev);
 
 	adapter->pdev = pdev;
@@ -526,14 +537,15 @@
 		goto err;
 	}
 
-	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
+	for (i = 0; i < vf->nr_vring; i++)
 		vf->vring[i].irq = -EINVAL;
 
 	vf->hw_features = ifcvf_get_hw_features(vf);
 
-	ret = vdpa_register_device(&adapter->vdpa, IFCVF_MAX_QUEUE_PAIRS * 2);
+	adapter->vdpa.mdev = &ifcvf_mgmt_dev->mdev;
+	ret = _vdpa_register_device(&adapter->vdpa, vf->nr_vring);
 	if (ret) {
-		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
+		IFCVF_ERR(pdev, "Failed to register to vDPA bus");
 		goto err;
 	}
 
@@ -544,11 +556,100 @@
 	return ret;
 }
 
+static void ifcvf_vdpa_dev_del(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+
+	ifcvf_mgmt_dev = container_of(mdev, struct ifcvf_vdpa_mgmt_dev, mdev);
+	_vdpa_unregister_device(dev);
+	ifcvf_mgmt_dev->adapter = NULL;
+}
+
+static const struct vdpa_mgmtdev_ops ifcvf_vdpa_mgmt_dev_ops = {
+	.dev_add = ifcvf_vdpa_dev_add,
+	.dev_del = ifcvf_vdpa_dev_del
+};
+
+static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
+	struct device *dev = &pdev->dev;
+	u32 dev_type;
+	int ret;
+
+	ifcvf_mgmt_dev = kzalloc(sizeof(struct ifcvf_vdpa_mgmt_dev), GFP_KERNEL);
+	if (!ifcvf_mgmt_dev) {
+		IFCVF_ERR(pdev, "Failed to alloc memory for the vDPA management device\n");
+		return -ENOMEM;
+	}
+
+	dev_type = get_dev_type(pdev);
+	switch (dev_type) {
+	case VIRTIO_ID_NET:
+		ifcvf_mgmt_dev->mdev.id_table = id_table_net;
+		break;
+	case VIRTIO_ID_BLOCK:
+		ifcvf_mgmt_dev->mdev.id_table = id_table_blk;
+		break;
+	default:
+		IFCVF_ERR(pdev, "VIRTIO ID %u not supported\n", dev_type);
+		ret = -EOPNOTSUPP;
+		goto err;
+	}
+
+	ifcvf_mgmt_dev->mdev.ops = &ifcvf_vdpa_mgmt_dev_ops;
+	ifcvf_mgmt_dev->mdev.device = dev;
+	ifcvf_mgmt_dev->pdev = pdev;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to enable device\n");
+		goto err;
+	}
+
+	ret = pcim_iomap_regions(pdev, BIT(0) | BIT(2) | BIT(4),
+				 IFCVF_DRIVER_NAME);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request MMIO region\n");
+		goto err;
+	}
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		IFCVF_ERR(pdev, "No usable DMA configuration\n");
+		goto err;
+	}
+
+	ret = devm_add_action_or_reset(dev, ifcvf_free_irq_vectors, pdev);
+	if (ret) {
+		IFCVF_ERR(pdev,
+			  "Failed for adding devres for freeing irq vectors\n");
+		goto err;
+	}
+
+	pci_set_master(pdev);
+
+	ret = vdpa_mgmtdev_register(&ifcvf_mgmt_dev->mdev);
+	if (ret) {
+		IFCVF_ERR(pdev,
+			  "Failed to initialize the management interfaces\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	kfree(ifcvf_mgmt_dev);
+	return ret;
+}
+
 static void ifcvf_remove(struct pci_dev *pdev)
 {
-	struct ifcvf_adapter *adapter = pci_get_drvdata(pdev);
+	struct ifcvf_vdpa_mgmt_dev *ifcvf_mgmt_dev;
 
-	vdpa_unregister_device(&adapter->vdpa);
+	ifcvf_mgmt_dev = pci_get_drvdata(pdev);
+	vdpa_mgmtdev_unregister(&ifcvf_mgmt_dev->mdev);
+	kfree(ifcvf_mgmt_dev);
 }
 
 static struct pci_device_id ifcvf_pci_ids[] = {
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index 0002b21..01a848a 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -5,7 +5,7 @@
 #define __MLX5_VDPA_H__
 
 #include <linux/etherdevice.h>
-#include <linux/if_vlan.h>
+#include <linux/vringh.h>
 #include <linux/vdpa.h>
 #include <linux/mlx5/driver.h>
 
@@ -48,6 +48,26 @@
 	bool valid;
 };
 
+struct mlx5_control_vq {
+	struct vhost_iotlb *iotlb;
+	/* spinlock to synchronize iommu table */
+	spinlock_t iommu_lock;
+	struct vringh vring;
+	bool ready;
+	u64 desc_addr;
+	u64 device_addr;
+	u64 driver_addr;
+	struct vdpa_callback event_cb;
+	struct vringh_kiov riov;
+	struct vringh_kiov wiov;
+	unsigned short head;
+};
+
+struct mlx5_ctrl_wq_ent {
+	struct work_struct work;
+	struct mlx5_vdpa_dev *mvdev;
+};
+
 struct mlx5_vdpa_dev {
 	struct vdpa_device vdev;
 	struct mlx5_core_dev *mdev;
@@ -57,9 +77,12 @@
 	u64 actual_features;
 	u8 status;
 	u32 max_vqs;
+	u16 max_idx;
 	u32 generation;
 
 	struct mlx5_vdpa_mr mr;
+	struct mlx5_control_vq cvq;
+	struct workqueue_struct *wq;
 };
 
 int mlx5_vdpa_alloc_pd(struct mlx5_vdpa_dev *dev, u32 *pdn, u16 uid);
@@ -68,6 +91,7 @@
 int mlx5_vdpa_create_tis(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tisn);
 void mlx5_vdpa_destroy_tis(struct mlx5_vdpa_dev *mvdev, u32 tisn);
 int mlx5_vdpa_create_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 *rqtn);
+int mlx5_vdpa_modify_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 rqtn);
 void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn);
 int mlx5_vdpa_create_tir(struct mlx5_vdpa_dev *mvdev, void *in, u32 *tirn);
 void mlx5_vdpa_destroy_tir(struct mlx5_vdpa_dev *mvdev, u32 tirn);
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index e59135f..ff010c6 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2020 Mellanox Technologies Ltd. */
 
+#include <linux/vhost_types.h>
 #include <linux/vdpa.h>
 #include <linux/gcd.h>
 #include <linux/string.h>
@@ -451,33 +452,30 @@
 	mlx5_vdpa_destroy_mkey(mvdev, &mr->mkey);
 }
 
-static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static int dup_iotlb(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *src)
 {
-	struct mlx5_vdpa_mr *mr = &mvdev->mr;
+	struct vhost_iotlb_map *map;
+	u64 start = 0, last = ULLONG_MAX;
 	int err;
 
-	if (mr->initialized)
-		return 0;
+	if (!src) {
+		err = vhost_iotlb_add_range(mvdev->cvq.iotlb, start, last, start, VHOST_ACCESS_RW);
+		return err;
+	}
 
-	if (iotlb)
-		err = create_user_mr(mvdev, iotlb);
-	else
-		err = create_dma_mr(mvdev, mr);
-
-	if (!err)
-		mr->initialized = true;
-
-	return err;
+	for (map = vhost_iotlb_itree_first(src, start, last); map;
+		map = vhost_iotlb_itree_next(map, start, last)) {
+		err = vhost_iotlb_add_range(mvdev->cvq.iotlb, map->start, map->last,
+					    map->addr, map->perm);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
-int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+static void prune_iotlb(struct mlx5_vdpa_dev *mvdev)
 {
-	int err;
-
-	mutex_lock(&mvdev->mr.mkey_mtx);
-	err = _mlx5_vdpa_create_mr(mvdev, iotlb);
-	mutex_unlock(&mvdev->mr.mkey_mtx);
-	return err;
+	vhost_iotlb_del_range(mvdev->cvq.iotlb, 0, ULLONG_MAX);
 }
 
 static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_mr *mr)
@@ -501,6 +499,7 @@
 	if (!mr->initialized)
 		goto out;
 
+	prune_iotlb(mvdev);
 	if (mr->user_mr)
 		destroy_user_mr(mvdev, mr);
 	else
@@ -512,6 +511,48 @@
 	mutex_unlock(&mr->mkey_mtx);
 }
 
+static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+{
+	struct mlx5_vdpa_mr *mr = &mvdev->mr;
+	int err;
+
+	if (mr->initialized)
+		return 0;
+
+	if (iotlb)
+		err = create_user_mr(mvdev, iotlb);
+	else
+		err = create_dma_mr(mvdev, mr);
+
+	if (err)
+		return err;
+
+	err = dup_iotlb(mvdev, iotlb);
+	if (err)
+		goto out_err;
+
+	mr->initialized = true;
+	return 0;
+
+out_err:
+	if (iotlb)
+		destroy_user_mr(mvdev, mr);
+	else
+		destroy_dma_mr(mvdev, mr);
+
+	return err;
+}
+
+int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
+{
+	int err;
+
+	mutex_lock(&mvdev->mr.mkey_mtx);
+	err = _mlx5_vdpa_create_mr(mvdev, iotlb);
+	mutex_unlock(&mvdev->mr.mkey_mtx);
+	return err;
+}
+
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb,
 			     bool *change_map)
 {
diff --git a/drivers/vdpa/mlx5/core/resources.c b/drivers/vdpa/mlx5/core/resources.c
index d460621..15e266d 100644
--- a/drivers/vdpa/mlx5/core/resources.c
+++ b/drivers/vdpa/mlx5/core/resources.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 /* Copyright (c) 2020 Mellanox Technologies Ltd. */
 
+#include <linux/iova.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_vdpa.h"
 
@@ -128,6 +129,16 @@
 	return err;
 }
 
+int mlx5_vdpa_modify_rqt(struct mlx5_vdpa_dev *mvdev, void *in, int inlen, u32 rqtn)
+{
+	u32 out[MLX5_ST_SZ_DW(create_rqt_out)] = {};
+
+	MLX5_SET(modify_rqt_in, in, uid, mvdev->res.uid);
+	MLX5_SET(modify_rqt_in, in, rqtn, rqtn);
+	MLX5_SET(modify_rqt_in, in, opcode, MLX5_CMD_OP_MODIFY_RQT);
+	return mlx5_cmd_exec(mvdev->mdev, in, inlen, out, sizeof(out));
+}
+
 void mlx5_vdpa_destroy_rqt(struct mlx5_vdpa_dev *mvdev, u32 rqtn)
 {
 	u32 in[MLX5_ST_SZ_DW(destroy_rqt_in)] = {};
@@ -221,6 +232,22 @@
 	return mlx5_cmd_exec_in(mvdev->mdev, destroy_mkey, in);
 }
 
+static int init_ctrl_vq(struct mlx5_vdpa_dev *mvdev)
+{
+	mvdev->cvq.iotlb = vhost_iotlb_alloc(0, 0);
+	if (!mvdev->cvq.iotlb)
+		return -ENOMEM;
+
+	vringh_set_iotlb(&mvdev->cvq.vring, mvdev->cvq.iotlb, &mvdev->cvq.iommu_lock);
+
+	return 0;
+}
+
+static void cleanup_ctrl_vq(struct mlx5_vdpa_dev *mvdev)
+{
+	vhost_iotlb_free(mvdev->cvq.iotlb);
+}
+
 int mlx5_vdpa_alloc_resources(struct mlx5_vdpa_dev *mvdev)
 {
 	u64 offset = MLX5_CAP64_DEV_VDPA_EMULATION(mvdev->mdev, doorbell_bar_offset);
@@ -260,10 +287,17 @@
 		err = -ENOMEM;
 		goto err_key;
 	}
+
+	err = init_ctrl_vq(mvdev);
+	if (err)
+		goto err_ctrl;
+
 	res->valid = true;
 
 	return 0;
 
+err_ctrl:
+	iounmap(res->kick_addr);
 err_key:
 	dealloc_pd(mvdev, res->pdn, res->uid);
 err_pd:
@@ -282,6 +316,7 @@
 	if (!res->valid)
 		return;
 
+	cleanup_ctrl_vq(mvdev);
 	iounmap(res->kick_addr);
 	res->kick_addr = NULL;
 	dealloc_pd(mvdev, res->pdn, res->uid);
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 5906cad..294ba05 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -45,6 +45,8 @@
 	(VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER | VIRTIO_CONFIG_S_DRIVER_OK |        \
 	 VIRTIO_CONFIG_S_FEATURES_OK | VIRTIO_CONFIG_S_NEEDS_RESET | VIRTIO_CONFIG_S_FAILED)
 
+#define MLX5_FEATURE(_mvdev, _feature) (!!((_mvdev)->actual_features & BIT_ULL(_feature)))
+
 struct mlx5_vdpa_net_resources {
 	u32 tisn;
 	u32 tdn;
@@ -90,7 +92,6 @@
 	u16 avail_index;
 	u16 used_index;
 	bool ready;
-	struct vdpa_callback cb;
 	bool restore;
 };
 
@@ -100,7 +101,6 @@
 	u64 device_addr;
 	u64 driver_addr;
 	u32 num_ent;
-	struct vdpa_callback event_cb;
 
 	/* Resources for implementing the notification channel from the device
 	 * to the driver. fwqp is the firmware end of an RC connection; the
@@ -135,11 +135,20 @@
  */
 #define MLX5_MAX_SUPPORTED_VQS 16
 
+static bool is_index_valid(struct mlx5_vdpa_dev *mvdev, u16 idx)
+{
+	if (unlikely(idx > mvdev->max_idx))
+		return false;
+
+	return true;
+}
+
 struct mlx5_vdpa_net {
 	struct mlx5_vdpa_dev mvdev;
 	struct mlx5_vdpa_net_resources res;
 	struct virtio_net_config config;
 	struct mlx5_vdpa_virtqueue vqs[MLX5_MAX_SUPPORTED_VQS];
+	struct vdpa_callback event_cbs[MLX5_MAX_SUPPORTED_VQS + 1];
 
 	/* Serialize vq resources creation and destruction. This is required
 	 * since memory map might change and we need to destroy and create
@@ -151,15 +160,18 @@
 	struct mlx5_flow_handle *rx_rule;
 	bool setup;
 	u16 mtu;
+	u32 cur_num_vqs;
 };
 
 static void free_resources(struct mlx5_vdpa_net *ndev);
 static void init_mvqs(struct mlx5_vdpa_net *ndev);
-static int setup_driver(struct mlx5_vdpa_net *ndev);
+static int setup_driver(struct mlx5_vdpa_dev *mvdev);
 static void teardown_driver(struct mlx5_vdpa_net *ndev);
 
 static bool mlx5_vdpa_debug;
 
+#define MLX5_CVQ_MAX_ENT 16
+
 #define MLX5_LOG_VIO_FLAG(_feature)                                                                \
 	do {                                                                                       \
 		if (features & BIT_ULL(_feature))                                                  \
@@ -172,11 +184,41 @@
 			mlx5_vdpa_info(mvdev, "%s\n", #_status);                                   \
 	} while (0)
 
+/* TODO: cross-endian support */
+static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
+{
+	return virtio_legacy_is_little_endian() ||
+		(mvdev->actual_features & BIT_ULL(VIRTIO_F_VERSION_1));
+}
+
+static u16 mlx5vdpa16_to_cpu(struct mlx5_vdpa_dev *mvdev, __virtio16 val)
+{
+	return __virtio16_to_cpu(mlx5_vdpa_is_little_endian(mvdev), val);
+}
+
+static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val)
+{
+	return __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev), val);
+}
+
 static inline u32 mlx5_vdpa_max_qps(int max_vqs)
 {
 	return max_vqs / 2;
 }
 
+static u16 ctrl_vq_idx(struct mlx5_vdpa_dev *mvdev)
+{
+	if (!(mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_MQ)))
+		return 2;
+
+	return 2 * mlx5_vdpa_max_qps(mvdev->max_vqs);
+}
+
+static bool is_ctrl_vq_idx(struct mlx5_vdpa_dev *mvdev, u16 idx)
+{
+	return idx == ctrl_vq_idx(mvdev);
+}
+
 static void print_status(struct mlx5_vdpa_dev *mvdev, u8 status, bool set)
 {
 	if (status & ~VALID_STATUS_MASK)
@@ -481,6 +523,10 @@
 
 static void mlx5_vdpa_handle_completions(struct mlx5_vdpa_virtqueue *mvq, int num)
 {
+	struct mlx5_vdpa_net *ndev = mvq->ndev;
+	struct vdpa_callback *event_cb;
+
+	event_cb = &ndev->event_cbs[mvq->index];
 	mlx5_cq_set_ci(&mvq->cq.mcq);
 
 	/* make sure CQ cosumer update is visible to the hardware before updating
@@ -488,8 +534,8 @@
 	 */
 	dma_wmb();
 	rx_post(&mvq->vqqp, num);
-	if (mvq->event_cb.callback)
-		mvq->event_cb.callback(mvq->event_cb.private);
+	if (event_cb->callback)
+		event_cb->callback(event_cb->private);
 }
 
 static void mlx5_vdpa_cq_comp(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe)
@@ -1100,10 +1146,8 @@
 	if (!mvq->num_ent)
 		return 0;
 
-	if (mvq->initialized) {
-		mlx5_vdpa_warn(&ndev->mvdev, "attempt re init\n");
-		return -EINVAL;
-	}
+	if (mvq->initialized)
+		return 0;
 
 	err = cq_create(ndev, idx, mvq->num_ent);
 	if (err)
@@ -1190,19 +1234,20 @@
 
 static int create_rqt(struct mlx5_vdpa_net *ndev)
 {
-	int log_max_rqt;
 	__be32 *list;
+	int max_rqt;
 	void *rqtc;
 	int inlen;
 	void *in;
 	int i, j;
 	int err;
 
-	log_max_rqt = min_t(int, 1, MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size));
-	if (log_max_rqt < 1)
+	max_rqt = min_t(int, MLX5_MAX_SUPPORTED_VQS / 2,
+			1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size));
+	if (max_rqt < 1)
 		return -EOPNOTSUPP;
 
-	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + (1 << log_max_rqt) * MLX5_ST_SZ_BYTES(rq_num);
+	inlen = MLX5_ST_SZ_BYTES(create_rqt_in) + max_rqt * MLX5_ST_SZ_BYTES(rq_num);
 	in = kzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -1211,10 +1256,9 @@
 	rqtc = MLX5_ADDR_OF(create_rqt_in, in, rqt_context);
 
 	MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
-	MLX5_SET(rqtc, rqtc, rqt_max_size, 1 << log_max_rqt);
-	MLX5_SET(rqtc, rqtc, rqt_actual_size, 1);
+	MLX5_SET(rqtc, rqtc, rqt_max_size, max_rqt);
 	list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
-	for (i = 0, j = 0; j < ndev->mvdev.max_vqs; j++) {
+	for (i = 0, j = 0; j < max_rqt; j++) {
 		if (!ndev->vqs[j].initialized)
 			continue;
 
@@ -1223,6 +1267,7 @@
 			i++;
 		}
 	}
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, i);
 
 	err = mlx5_vdpa_create_rqt(&ndev->mvdev, in, inlen, &ndev->res.rqtn);
 	kfree(in);
@@ -1232,6 +1277,52 @@
 	return 0;
 }
 
+#define MLX5_MODIFY_RQT_NUM_RQS ((u64)1)
+
+static int modify_rqt(struct mlx5_vdpa_net *ndev, int num)
+{
+	__be32 *list;
+	int max_rqt;
+	void *rqtc;
+	int inlen;
+	void *in;
+	int i, j;
+	int err;
+
+	max_rqt = min_t(int, ndev->cur_num_vqs / 2,
+			1 << MLX5_CAP_GEN(ndev->mvdev.mdev, log_max_rqt_size));
+	if (max_rqt < 1)
+		return -EOPNOTSUPP;
+
+	inlen = MLX5_ST_SZ_BYTES(modify_rqt_in) + max_rqt * MLX5_ST_SZ_BYTES(rq_num);
+	in = kzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(modify_rqt_in, in, uid, ndev->mvdev.res.uid);
+	MLX5_SET64(modify_rqt_in, in, bitmask, MLX5_MODIFY_RQT_NUM_RQS);
+	rqtc = MLX5_ADDR_OF(modify_rqt_in, in, ctx);
+	MLX5_SET(rqtc, rqtc, list_q_type, MLX5_RQTC_LIST_Q_TYPE_VIRTIO_NET_Q);
+
+	list = MLX5_ADDR_OF(rqtc, rqtc, rq_num[0]);
+	for (i = 0, j = 0; j < num; j++) {
+		if (!ndev->vqs[j].initialized)
+			continue;
+
+		if (!vq_is_tx(ndev->vqs[j].index)) {
+			list[i] = cpu_to_be32(ndev->vqs[j].virtq_id);
+			i++;
+		}
+	}
+	MLX5_SET(rqtc, rqtc, rqt_actual_size, i);
+	err = mlx5_vdpa_modify_rqt(&ndev->mvdev, in, inlen, ndev->res.rqtn);
+	kfree(in);
+	if (err)
+		return err;
+
+	return 0;
+}
+
 static void destroy_rqt(struct mlx5_vdpa_net *ndev)
 {
 	mlx5_vdpa_destroy_rqt(&ndev->mvdev, ndev->res.rqtn);
@@ -1345,12 +1436,206 @@
 	ndev->rx_rule = NULL;
 }
 
+static virtio_net_ctrl_ack handle_ctrl_mac(struct mlx5_vdpa_dev *mvdev, u8 cmd)
+{
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	struct mlx5_control_vq *cvq = &mvdev->cvq;
+	virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
+	struct mlx5_core_dev *pfmdev;
+	size_t read;
+	u8 mac[ETH_ALEN];
+
+	pfmdev = pci_get_drvdata(pci_physfn(mvdev->mdev->pdev));
+	switch (cmd) {
+	case VIRTIO_NET_CTRL_MAC_ADDR_SET:
+		read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, (void *)mac, ETH_ALEN);
+		if (read != ETH_ALEN)
+			break;
+
+		if (!memcmp(ndev->config.mac, mac, 6)) {
+			status = VIRTIO_NET_OK;
+			break;
+		}
+
+		if (!is_zero_ether_addr(ndev->config.mac)) {
+			if (mlx5_mpfs_del_mac(pfmdev, ndev->config.mac)) {
+				mlx5_vdpa_warn(mvdev, "failed to delete old MAC %pM from MPFS table\n",
+					       ndev->config.mac);
+				break;
+			}
+		}
+
+		if (mlx5_mpfs_add_mac(pfmdev, mac)) {
+			mlx5_vdpa_warn(mvdev, "failed to insert new MAC %pM into MPFS table\n",
+				       mac);
+			break;
+		}
+
+		memcpy(ndev->config.mac, mac, ETH_ALEN);
+		status = VIRTIO_NET_OK;
+		break;
+
+	default:
+		break;
+	}
+
+	return status;
+}
+
+static int change_num_qps(struct mlx5_vdpa_dev *mvdev, int newqps)
+{
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	int cur_qps = ndev->cur_num_vqs / 2;
+	int err;
+	int i;
+
+	if (cur_qps > newqps) {
+		err = modify_rqt(ndev, 2 * newqps);
+		if (err)
+			return err;
+
+		for (i = ndev->cur_num_vqs - 1; i >= 2 * newqps; i--)
+			teardown_vq(ndev, &ndev->vqs[i]);
+
+		ndev->cur_num_vqs = 2 * newqps;
+	} else {
+		ndev->cur_num_vqs = 2 * newqps;
+		for (i = cur_qps * 2; i < 2 * newqps; i++) {
+			err = setup_vq(ndev, &ndev->vqs[i]);
+			if (err)
+				goto clean_added;
+		}
+		err = modify_rqt(ndev, 2 * newqps);
+		if (err)
+			goto clean_added;
+	}
+	return 0;
+
+clean_added:
+	for (--i; i >= cur_qps; --i)
+		teardown_vq(ndev, &ndev->vqs[i]);
+
+	return err;
+}
+
+static virtio_net_ctrl_ack handle_ctrl_mq(struct mlx5_vdpa_dev *mvdev, u8 cmd)
+{
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
+	struct mlx5_control_vq *cvq = &mvdev->cvq;
+	struct virtio_net_ctrl_mq mq;
+	size_t read;
+	u16 newqps;
+
+	switch (cmd) {
+	case VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET:
+		read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, (void *)&mq, sizeof(mq));
+		if (read != sizeof(mq))
+			break;
+
+		newqps = mlx5vdpa16_to_cpu(mvdev, mq.virtqueue_pairs);
+		if (ndev->cur_num_vqs == 2 * newqps) {
+			status = VIRTIO_NET_OK;
+			break;
+		}
+
+		if (newqps & (newqps - 1))
+			break;
+
+		if (!change_num_qps(mvdev, newqps))
+			status = VIRTIO_NET_OK;
+
+		break;
+	default:
+		break;
+	}
+
+	return status;
+}
+
+static void mlx5_cvq_kick_handler(struct work_struct *work)
+{
+	virtio_net_ctrl_ack status = VIRTIO_NET_ERR;
+	struct virtio_net_ctrl_hdr ctrl;
+	struct mlx5_ctrl_wq_ent *wqent;
+	struct mlx5_vdpa_dev *mvdev;
+	struct mlx5_control_vq *cvq;
+	struct mlx5_vdpa_net *ndev;
+	size_t read, write;
+	int err;
+
+	wqent = container_of(work, struct mlx5_ctrl_wq_ent, work);
+	mvdev = wqent->mvdev;
+	ndev = to_mlx5_vdpa_ndev(mvdev);
+	cvq = &mvdev->cvq;
+	if (!(ndev->mvdev.actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)))
+		goto out;
+
+	if (!cvq->ready)
+		goto out;
+
+	while (true) {
+		err = vringh_getdesc_iotlb(&cvq->vring, &cvq->riov, &cvq->wiov, &cvq->head,
+					   GFP_ATOMIC);
+		if (err <= 0)
+			break;
+
+		read = vringh_iov_pull_iotlb(&cvq->vring, &cvq->riov, &ctrl, sizeof(ctrl));
+		if (read != sizeof(ctrl))
+			break;
+
+		switch (ctrl.class) {
+		case VIRTIO_NET_CTRL_MAC:
+			status = handle_ctrl_mac(mvdev, ctrl.cmd);
+			break;
+		case VIRTIO_NET_CTRL_MQ:
+			status = handle_ctrl_mq(mvdev, ctrl.cmd);
+			break;
+
+		default:
+			break;
+		}
+
+		/* Make sure data is written before advancing index */
+		smp_wmb();
+
+		write = vringh_iov_push_iotlb(&cvq->vring, &cvq->wiov, &status, sizeof(status));
+		vringh_complete_iotlb(&cvq->vring, cvq->head, write);
+		vringh_kiov_cleanup(&cvq->riov);
+		vringh_kiov_cleanup(&cvq->wiov);
+
+		if (vringh_need_notify_iotlb(&cvq->vring))
+			vringh_notify(&cvq->vring);
+	}
+out:
+	kfree(wqent);
+}
+
 static void mlx5_vdpa_kick_vq(struct vdpa_device *vdev, u16 idx)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+	struct mlx5_vdpa_virtqueue *mvq;
+	struct mlx5_ctrl_wq_ent *wqent;
 
+	if (!is_index_valid(mvdev, idx))
+		return;
+
+	if (unlikely(is_ctrl_vq_idx(mvdev, idx))) {
+		if (!mvdev->cvq.ready)
+			return;
+
+		wqent = kzalloc(sizeof(*wqent), GFP_ATOMIC);
+		if (!wqent)
+			return;
+
+		wqent->mvdev = mvdev;
+		INIT_WORK(&wqent->work, mlx5_cvq_kick_handler);
+		queue_work(mvdev->wq, &wqent->work);
+		return;
+	}
+
+	mvq = &ndev->vqs[idx];
 	if (unlikely(!mvq->ready))
 		return;
 
@@ -1362,8 +1647,19 @@
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+	struct mlx5_vdpa_virtqueue *mvq;
 
+	if (!is_index_valid(mvdev, idx))
+		return -EINVAL;
+
+	if (is_ctrl_vq_idx(mvdev, idx)) {
+		mvdev->cvq.desc_addr = desc_area;
+		mvdev->cvq.device_addr = device_area;
+		mvdev->cvq.driver_addr = driver_area;
+		return 0;
+	}
+
+	mvq = &ndev->vqs[idx];
 	mvq->desc_addr = desc_area;
 	mvq->device_addr = device_area;
 	mvq->driver_addr = driver_area;
@@ -1376,6 +1672,9 @@
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	struct mlx5_vdpa_virtqueue *mvq;
 
+	if (!is_index_valid(mvdev, idx) || is_ctrl_vq_idx(mvdev, idx))
+		return;
+
 	mvq = &ndev->vqs[idx];
 	mvq->num_ent = num;
 }
@@ -1384,17 +1683,46 @@
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *vq = &ndev->vqs[idx];
 
-	vq->event_cb = *cb;
+	ndev->event_cbs[idx] = *cb;
+}
+
+static void mlx5_cvq_notify(struct vringh *vring)
+{
+	struct mlx5_control_vq *cvq = container_of(vring, struct mlx5_control_vq, vring);
+
+	if (!cvq->event_cb.callback)
+		return;
+
+	cvq->event_cb.callback(cvq->event_cb.private);
+}
+
+static void set_cvq_ready(struct mlx5_vdpa_dev *mvdev, bool ready)
+{
+	struct mlx5_control_vq *cvq = &mvdev->cvq;
+
+	cvq->ready = ready;
+	if (!ready)
+		return;
+
+	cvq->vring.notify = mlx5_cvq_notify;
 }
 
 static void mlx5_vdpa_set_vq_ready(struct vdpa_device *vdev, u16 idx, bool ready)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+	struct mlx5_vdpa_virtqueue *mvq;
 
+	if (!is_index_valid(mvdev, idx))
+		return;
+
+	if (is_ctrl_vq_idx(mvdev, idx)) {
+		set_cvq_ready(mvdev, ready);
+		return;
+	}
+
+	mvq = &ndev->vqs[idx];
 	if (!ready)
 		suspend_vq(ndev, mvq);
 
@@ -1405,9 +1733,14 @@
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
 
-	return mvq->ready;
+	if (!is_index_valid(mvdev, idx))
+		return false;
+
+	if (is_ctrl_vq_idx(mvdev, idx))
+		return mvdev->cvq.ready;
+
+	return ndev->vqs[idx].ready;
 }
 
 static int mlx5_vdpa_set_vq_state(struct vdpa_device *vdev, u16 idx,
@@ -1415,8 +1748,17 @@
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+	struct mlx5_vdpa_virtqueue *mvq;
 
+	if (!is_index_valid(mvdev, idx))
+		return -EINVAL;
+
+	if (is_ctrl_vq_idx(mvdev, idx)) {
+		mvdev->cvq.vring.last_avail_idx = state->split.avail_index;
+		return 0;
+	}
+
+	mvq = &ndev->vqs[idx];
 	if (mvq->fw_state == MLX5_VIRTIO_NET_Q_OBJECT_STATE_RDY) {
 		mlx5_vdpa_warn(mvdev, "can't modify available index\n");
 		return -EINVAL;
@@ -1431,10 +1773,19 @@
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
 	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
-	struct mlx5_vdpa_virtqueue *mvq = &ndev->vqs[idx];
+	struct mlx5_vdpa_virtqueue *mvq;
 	struct mlx5_virtq_attr attr;
 	int err;
 
+	if (!is_index_valid(mvdev, idx))
+		return -EINVAL;
+
+	if (is_ctrl_vq_idx(mvdev, idx)) {
+		state->split.avail_index = mvdev->cvq.vring.last_avail_idx;
+		return 0;
+	}
+
+	mvq = &ndev->vqs[idx];
 	/* If the virtq object was destroyed, use the value saved at
 	 * the last minute of suspend_vq. This caters for userspace
 	 * that cares about emulating the index after vq is stopped.
@@ -1491,10 +1842,14 @@
 	u16 dev_features;
 
 	dev_features = MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, device_features_bits_mask);
-	ndev->mvdev.mlx_features = mlx_to_vritio_features(dev_features);
+	ndev->mvdev.mlx_features |= mlx_to_vritio_features(dev_features);
 	if (MLX5_CAP_DEV_VDPA_EMULATION(mvdev->mdev, virtio_version_1_0))
 		ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_VERSION_1);
 	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_F_ACCESS_PLATFORM);
+	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_VQ);
+	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_CTRL_MAC_ADDR);
+	ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MQ);
+
 	print_features(mvdev, ndev->mvdev.mlx_features, false);
 	return ndev->mvdev.mlx_features;
 }
@@ -1507,17 +1862,29 @@
 	return 0;
 }
 
-static int setup_virtqueues(struct mlx5_vdpa_net *ndev)
+static int setup_virtqueues(struct mlx5_vdpa_dev *mvdev)
 {
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	struct mlx5_control_vq *cvq = &mvdev->cvq;
 	int err;
 	int i;
 
-	for (i = 0; i < 2 * mlx5_vdpa_max_qps(ndev->mvdev.max_vqs); i++) {
+	for (i = 0; i < 2 * mlx5_vdpa_max_qps(mvdev->max_vqs); i++) {
 		err = setup_vq(ndev, &ndev->vqs[i]);
 		if (err)
 			goto err_vq;
 	}
 
+	if (mvdev->actual_features & BIT_ULL(VIRTIO_NET_F_CTRL_VQ)) {
+		err = vringh_init_iotlb(&cvq->vring, mvdev->actual_features,
+					MLX5_CVQ_MAX_ENT, false,
+					(struct vring_desc *)(uintptr_t)cvq->desc_addr,
+					(struct vring_avail *)(uintptr_t)cvq->driver_addr,
+					(struct vring_used *)(uintptr_t)cvq->device_addr);
+		if (err)
+			goto err_vq;
+	}
+
 	return 0;
 
 err_vq:
@@ -1541,16 +1908,22 @@
 	}
 }
 
-/* TODO: cross-endian support */
-static inline bool mlx5_vdpa_is_little_endian(struct mlx5_vdpa_dev *mvdev)
+static void update_cvq_info(struct mlx5_vdpa_dev *mvdev)
 {
-	return virtio_legacy_is_little_endian() ||
-		(mvdev->actual_features & BIT_ULL(VIRTIO_F_VERSION_1));
-}
-
-static __virtio16 cpu_to_mlx5vdpa16(struct mlx5_vdpa_dev *mvdev, u16 val)
-{
-	return __cpu_to_virtio16(mlx5_vdpa_is_little_endian(mvdev), val);
+	if (MLX5_FEATURE(mvdev, VIRTIO_NET_F_CTRL_VQ)) {
+		if (MLX5_FEATURE(mvdev, VIRTIO_NET_F_MQ)) {
+			/* MQ supported. CVQ index is right above the last data virtqueue's */
+			mvdev->max_idx = mvdev->max_vqs;
+		} else {
+			/* Only CVQ supportted. data virtqueues occupy indices 0 and 1.
+			 * CVQ gets index 2
+			 */
+			mvdev->max_idx = 2;
+		}
+	} else {
+		/* Two data virtqueues only: one for rx and one for tx */
+		mvdev->max_idx = 1;
+	}
 }
 
 static int mlx5_vdpa_set_features(struct vdpa_device *vdev, u64 features)
@@ -1568,6 +1941,7 @@
 	ndev->mvdev.actual_features = features & ndev->mvdev.mlx_features;
 	ndev->config.mtu = cpu_to_mlx5vdpa16(mvdev, ndev->mtu);
 	ndev->config.status |= cpu_to_mlx5vdpa16(mvdev, VIRTIO_NET_S_LINK_UP);
+	update_cvq_info(mvdev);
 	return err;
 }
 
@@ -1605,15 +1979,14 @@
 static int save_channel_info(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq)
 {
 	struct mlx5_vq_restore_info *ri = &mvq->ri;
-	struct mlx5_virtq_attr attr;
+	struct mlx5_virtq_attr attr = {};
 	int err;
 
-	if (!mvq->initialized)
-		return 0;
-
-	err = query_virtqueue(ndev, mvq, &attr);
-	if (err)
-		return err;
+	if (mvq->initialized) {
+		err = query_virtqueue(ndev, mvq, &attr);
+		if (err)
+			return err;
+	}
 
 	ri->avail_index = attr.available_index;
 	ri->used_index = attr.used_index;
@@ -1622,7 +1995,6 @@
 	ri->desc_addr = mvq->desc_addr;
 	ri->device_addr = mvq->device_addr;
 	ri->driver_addr = mvq->driver_addr;
-	ri->cb = mvq->event_cb;
 	ri->restore = true;
 	return 0;
 }
@@ -1667,12 +2039,12 @@
 		mvq->desc_addr = ri->desc_addr;
 		mvq->device_addr = ri->device_addr;
 		mvq->driver_addr = ri->driver_addr;
-		mvq->event_cb = ri->cb;
 	}
 }
 
-static int mlx5_vdpa_change_map(struct mlx5_vdpa_net *ndev, struct vhost_iotlb *iotlb)
+static int mlx5_vdpa_change_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb)
 {
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	int err;
 
 	suspend_vqs(ndev);
@@ -1681,58 +2053,59 @@
 		goto err_mr;
 
 	teardown_driver(ndev);
-	mlx5_vdpa_destroy_mr(&ndev->mvdev);
-	err = mlx5_vdpa_create_mr(&ndev->mvdev, iotlb);
+	mlx5_vdpa_destroy_mr(mvdev);
+	err = mlx5_vdpa_create_mr(mvdev, iotlb);
 	if (err)
 		goto err_mr;
 
-	if (!(ndev->mvdev.status & VIRTIO_CONFIG_S_DRIVER_OK))
+	if (!(mvdev->status & VIRTIO_CONFIG_S_DRIVER_OK))
 		return 0;
 
 	restore_channels_info(ndev);
-	err = setup_driver(ndev);
+	err = setup_driver(mvdev);
 	if (err)
 		goto err_setup;
 
 	return 0;
 
 err_setup:
-	mlx5_vdpa_destroy_mr(&ndev->mvdev);
+	mlx5_vdpa_destroy_mr(mvdev);
 err_mr:
 	return err;
 }
 
-static int setup_driver(struct mlx5_vdpa_net *ndev)
+static int setup_driver(struct mlx5_vdpa_dev *mvdev)
 {
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	int err;
 
 	mutex_lock(&ndev->reslock);
 	if (ndev->setup) {
-		mlx5_vdpa_warn(&ndev->mvdev, "setup driver called for already setup driver\n");
+		mlx5_vdpa_warn(mvdev, "setup driver called for already setup driver\n");
 		err = 0;
 		goto out;
 	}
-	err = setup_virtqueues(ndev);
+	err = setup_virtqueues(mvdev);
 	if (err) {
-		mlx5_vdpa_warn(&ndev->mvdev, "setup_virtqueues\n");
+		mlx5_vdpa_warn(mvdev, "setup_virtqueues\n");
 		goto out;
 	}
 
 	err = create_rqt(ndev);
 	if (err) {
-		mlx5_vdpa_warn(&ndev->mvdev, "create_rqt\n");
+		mlx5_vdpa_warn(mvdev, "create_rqt\n");
 		goto err_rqt;
 	}
 
 	err = create_tir(ndev);
 	if (err) {
-		mlx5_vdpa_warn(&ndev->mvdev, "create_tir\n");
+		mlx5_vdpa_warn(mvdev, "create_tir\n");
 		goto err_tir;
 	}
 
 	err = add_fwd_to_tir(ndev);
 	if (err) {
-		mlx5_vdpa_warn(&ndev->mvdev, "add_fwd_to_tir\n");
+		mlx5_vdpa_warn(mvdev, "add_fwd_to_tir\n");
 		goto err_fwd;
 	}
 	ndev->setup = true;
@@ -1781,24 +2154,10 @@
 	int err;
 
 	print_status(mvdev, status, true);
-	if (!status) {
-		mlx5_vdpa_info(mvdev, "performing device reset\n");
-		teardown_driver(ndev);
-		clear_vqs_ready(ndev);
-		mlx5_vdpa_destroy_mr(&ndev->mvdev);
-		ndev->mvdev.status = 0;
-		ndev->mvdev.mlx_features = 0;
-		++mvdev->generation;
-		if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-			if (mlx5_vdpa_create_mr(mvdev, NULL))
-				mlx5_vdpa_warn(mvdev, "create MR failed\n");
-		}
-		return;
-	}
 
 	if ((status ^ ndev->mvdev.status) & VIRTIO_CONFIG_S_DRIVER_OK) {
 		if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
-			err = setup_driver(ndev);
+			err = setup_driver(mvdev);
 			if (err) {
 				mlx5_vdpa_warn(mvdev, "failed to setup driver\n");
 				goto err_setup;
@@ -1817,6 +2176,29 @@
 	ndev->mvdev.status |= VIRTIO_CONFIG_S_FAILED;
 }
 
+static int mlx5_vdpa_reset(struct vdpa_device *vdev)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+
+	print_status(mvdev, 0, true);
+	mlx5_vdpa_info(mvdev, "performing device reset\n");
+	teardown_driver(ndev);
+	clear_vqs_ready(ndev);
+	mlx5_vdpa_destroy_mr(&ndev->mvdev);
+	ndev->mvdev.status = 0;
+	ndev->mvdev.mlx_features = 0;
+	memset(ndev->event_cbs, 0, sizeof(ndev->event_cbs));
+	ndev->mvdev.actual_features = 0;
+	++mvdev->generation;
+	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
+		if (mlx5_vdpa_create_mr(mvdev, NULL))
+			mlx5_vdpa_warn(mvdev, "create MR failed\n");
+	}
+
+	return 0;
+}
+
 static size_t mlx5_vdpa_get_config_size(struct vdpa_device *vdev)
 {
 	return sizeof(struct virtio_net_config);
@@ -1848,7 +2230,6 @@
 static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
-	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
 	bool change_map;
 	int err;
 
@@ -1859,7 +2240,7 @@
 	}
 
 	if (change_map)
-		return mlx5_vdpa_change_map(ndev, iotlb);
+		return mlx5_vdpa_change_map(mvdev, iotlb);
 
 	return 0;
 }
@@ -1889,6 +2270,9 @@
 	struct mlx5_vdpa_net *ndev;
 	phys_addr_t addr;
 
+	if (!is_index_valid(mvdev, idx) || is_ctrl_vq_idx(mvdev, idx))
+		return ret;
+
 	/* If SF BAR size is smaller than PAGE_SIZE, do not use direct
 	 * notification to avoid the risk of mapping pages that contain BAR of more
 	 * than one SF
@@ -1928,6 +2312,7 @@
 	.get_vendor_id = mlx5_vdpa_get_vendor_id,
 	.get_status = mlx5_vdpa_get_status,
 	.set_status = mlx5_vdpa_set_status,
+	.reset = mlx5_vdpa_reset,
 	.get_config_size = mlx5_vdpa_get_config_size,
 	.get_config = mlx5_vdpa_get_config,
 	.set_config = mlx5_vdpa_set_config,
@@ -2040,7 +2425,7 @@
 	max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
 
 	ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
-				 name);
+				 name, false);
 	if (IS_ERR(ndev))
 		return PTR_ERR(ndev);
 
@@ -2063,8 +2448,11 @@
 		err = mlx5_mpfs_add_mac(pfmdev, config->mac);
 		if (err)
 			goto err_mtu;
+
+		ndev->mvdev.mlx_features |= BIT_ULL(VIRTIO_NET_F_MAC);
 	}
 
+	config->max_virtqueue_pairs = cpu_to_mlx5vdpa16(mvdev, mlx5_vdpa_max_qps(max_vqs));
 	mvdev->vdev.dma_dev = &mdev->pdev->dev;
 	err = mlx5_vdpa_alloc_resources(&ndev->mvdev);
 	if (err)
@@ -2080,8 +2468,15 @@
 	if (err)
 		goto err_mr;
 
+	mvdev->wq = create_singlethread_workqueue("mlx5_vdpa_ctrl_wq");
+	if (!mvdev->wq) {
+		err = -ENOMEM;
+		goto err_res2;
+	}
+
+	ndev->cur_num_vqs = 2 * mlx5_vdpa_max_qps(max_vqs);
 	mvdev->vdev.mdev = &mgtdev->mgtdev;
-	err = _vdpa_register_device(&mvdev->vdev, 2 * mlx5_vdpa_max_qps(max_vqs));
+	err = _vdpa_register_device(&mvdev->vdev, ndev->cur_num_vqs + 1);
 	if (err)
 		goto err_reg;
 
@@ -2089,6 +2484,8 @@
 	return 0;
 
 err_reg:
+	destroy_workqueue(mvdev->wq);
+err_res2:
 	free_resources(ndev);
 err_mr:
 	mlx5_vdpa_destroy_mr(mvdev);
@@ -2106,7 +2503,9 @@
 static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device *dev)
 {
 	struct mlx5_vdpa_mgmtdev *mgtdev = container_of(v_mdev, struct mlx5_vdpa_mgmtdev, mgtdev);
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(dev);
 
+	destroy_workqueue(mvdev->wq);
 	_vdpa_unregister_device(dev);
 	mgtdev->ndev = NULL;
 }
diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 3fc4525..1dc121a 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -69,6 +69,7 @@
  * @config: the bus operations that is supported by this device
  * @size: size of the parent structure that contains private data
  * @name: name of the vdpa device; optional.
+ * @use_va: indicate whether virtual address must be used by this device
  *
  * Driver should use vdpa_alloc_device() wrapper macro instead of
  * using this directly.
@@ -78,7 +79,8 @@
  */
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					size_t size, const char *name)
+					size_t size, const char *name,
+					bool use_va)
 {
 	struct vdpa_device *vdev;
 	int err = -EINVAL;
@@ -89,6 +91,10 @@
 	if (!!config->dma_map != !!config->dma_unmap)
 		goto err;
 
+	/* It should only work for the device that use on-chip IOMMU */
+	if (use_va && !(config->dma_map || config->set_map))
+		goto err;
+
 	err = -ENOMEM;
 	vdev = kzalloc(size, GFP_KERNEL);
 	if (!vdev)
@@ -104,6 +110,7 @@
 	vdev->index = err;
 	vdev->config = config;
 	vdev->features_valid = false;
+	vdev->use_va = use_va;
 
 	if (name)
 		err = dev_set_name(&vdev->dev, "%s", name);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index c621cf7..5f484fff 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -92,7 +92,7 @@
 	vq->vring.notify = NULL;
 }
 
-static void vdpasim_reset(struct vdpasim *vdpasim)
+static void vdpasim_do_reset(struct vdpasim *vdpasim)
 {
 	int i;
 
@@ -137,7 +137,8 @@
 	int ret;
 
 	/* We set the limit_pfn to the maximum (ULONG_MAX - 1) */
-	iova = alloc_iova(&vdpasim->iova, size, ULONG_MAX - 1, true);
+	iova = alloc_iova(&vdpasim->iova, size >> iova_shift(&vdpasim->iova),
+			  ULONG_MAX - 1, true);
 	if (!iova)
 		return DMA_MAPPING_ERROR;
 
@@ -250,7 +251,7 @@
 		ops = &vdpasim_config_ops;
 
 	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
-				    dev_attr->name);
+				    dev_attr->name, false);
 	if (IS_ERR(vdpasim)) {
 		ret = PTR_ERR(vdpasim);
 		goto err_alloc;
@@ -459,11 +460,21 @@
 
 	spin_lock(&vdpasim->lock);
 	vdpasim->status = status;
-	if (status == 0)
-		vdpasim_reset(vdpasim);
 	spin_unlock(&vdpasim->lock);
 }
 
+static int vdpasim_reset(struct vdpa_device *vdpa)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	spin_lock(&vdpasim->lock);
+	vdpasim->status = 0;
+	vdpasim_do_reset(vdpasim);
+	spin_unlock(&vdpasim->lock);
+
+	return 0;
+}
+
 static size_t vdpasim_get_config_size(struct vdpa_device *vdpa)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -544,14 +555,14 @@
 }
 
 static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
-			   u64 pa, u32 perm)
+			   u64 pa, u32 perm, void *opaque)
 {
 	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
 	int ret;
 
 	spin_lock(&vdpasim->iommu_lock);
-	ret = vhost_iotlb_add_range(vdpasim->iommu, iova, iova + size - 1, pa,
-				    perm);
+	ret = vhost_iotlb_add_range_ctx(vdpasim->iommu, iova, iova + size - 1,
+					pa, perm, opaque);
 	spin_unlock(&vdpasim->iommu_lock);
 
 	return ret;
@@ -607,6 +618,7 @@
 	.get_vendor_id          = vdpasim_get_vendor_id,
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
+	.reset			= vdpasim_reset,
 	.get_config_size        = vdpasim_get_config_size,
 	.get_config             = vdpasim_get_config,
 	.set_config             = vdpasim_set_config,
@@ -635,6 +647,7 @@
 	.get_vendor_id          = vdpasim_get_vendor_id,
 	.get_status             = vdpasim_get_status,
 	.set_status             = vdpasim_set_status,
+	.reset			= vdpasim_reset,
 	.get_config_size        = vdpasim_get_config_size,
 	.get_config             = vdpasim_get_config,
 	.set_config             = vdpasim_set_config,
diff --git a/drivers/vdpa/vdpa_user/Makefile b/drivers/vdpa/vdpa_user/Makefile
new file mode 100644
index 0000000..260e0b2
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+
+vduse-y := vduse_dev.o iova_domain.o
+
+obj-$(CONFIG_VDPA_USER) += vduse.o
diff --git a/drivers/vdpa/vdpa_user/iova_domain.c b/drivers/vdpa/vdpa_user/iova_domain.c
new file mode 100644
index 0000000..1daae26
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/iova_domain.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * MMU-based software IOTLB.
+ *
+ * Copyright (C) 2020-2021 Bytedance Inc. and/or its affiliates. All rights reserved.
+ *
+ * Author: Xie Yongji <xieyongji@bytedance.com>
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/file.h>
+#include <linux/anon_inodes.h>
+#include <linux/highmem.h>
+#include <linux/vmalloc.h>
+#include <linux/vdpa.h>
+
+#include "iova_domain.h"
+
+static int vduse_iotlb_add_range(struct vduse_iova_domain *domain,
+				 u64 start, u64 last,
+				 u64 addr, unsigned int perm,
+				 struct file *file, u64 offset)
+{
+	struct vdpa_map_file *map_file;
+	int ret;
+
+	map_file = kmalloc(sizeof(*map_file), GFP_ATOMIC);
+	if (!map_file)
+		return -ENOMEM;
+
+	map_file->file = get_file(file);
+	map_file->offset = offset;
+
+	ret = vhost_iotlb_add_range_ctx(domain->iotlb, start, last,
+					addr, perm, map_file);
+	if (ret) {
+		fput(map_file->file);
+		kfree(map_file);
+		return ret;
+	}
+	return 0;
+}
+
+static void vduse_iotlb_del_range(struct vduse_iova_domain *domain,
+				  u64 start, u64 last)
+{
+	struct vdpa_map_file *map_file;
+	struct vhost_iotlb_map *map;
+
+	while ((map = vhost_iotlb_itree_first(domain->iotlb, start, last))) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		fput(map_file->file);
+		kfree(map_file);
+		vhost_iotlb_map_free(domain->iotlb, map);
+	}
+}
+
+int vduse_domain_set_map(struct vduse_iova_domain *domain,
+			 struct vhost_iotlb *iotlb)
+{
+	struct vdpa_map_file *map_file;
+	struct vhost_iotlb_map *map;
+	u64 start = 0ULL, last = ULLONG_MAX;
+	int ret;
+
+	spin_lock(&domain->iotlb_lock);
+	vduse_iotlb_del_range(domain, start, last);
+
+	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
+	     map = vhost_iotlb_itree_next(map, start, last)) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		ret = vduse_iotlb_add_range(domain, map->start, map->last,
+					    map->addr, map->perm,
+					    map_file->file,
+					    map_file->offset);
+		if (ret)
+			goto err;
+	}
+	spin_unlock(&domain->iotlb_lock);
+
+	return 0;
+err:
+	vduse_iotlb_del_range(domain, start, last);
+	spin_unlock(&domain->iotlb_lock);
+	return ret;
+}
+
+void vduse_domain_clear_map(struct vduse_iova_domain *domain,
+			    struct vhost_iotlb *iotlb)
+{
+	struct vhost_iotlb_map *map;
+	u64 start = 0ULL, last = ULLONG_MAX;
+
+	spin_lock(&domain->iotlb_lock);
+	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
+	     map = vhost_iotlb_itree_next(map, start, last)) {
+		vduse_iotlb_del_range(domain, map->start, map->last);
+	}
+	spin_unlock(&domain->iotlb_lock);
+}
+
+static int vduse_domain_map_bounce_page(struct vduse_iova_domain *domain,
+					 u64 iova, u64 size, u64 paddr)
+{
+	struct vduse_bounce_map *map;
+	u64 last = iova + size - 1;
+
+	while (iova <= last) {
+		map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+		if (!map->bounce_page) {
+			map->bounce_page = alloc_page(GFP_ATOMIC);
+			if (!map->bounce_page)
+				return -ENOMEM;
+		}
+		map->orig_phys = paddr;
+		paddr += PAGE_SIZE;
+		iova += PAGE_SIZE;
+	}
+	return 0;
+}
+
+static void vduse_domain_unmap_bounce_page(struct vduse_iova_domain *domain,
+					   u64 iova, u64 size)
+{
+	struct vduse_bounce_map *map;
+	u64 last = iova + size - 1;
+
+	while (iova <= last) {
+		map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+		map->orig_phys = INVALID_PHYS_ADDR;
+		iova += PAGE_SIZE;
+	}
+}
+
+static void do_bounce(phys_addr_t orig, void *addr, size_t size,
+		      enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(orig);
+	unsigned int offset = offset_in_page(orig);
+	char *buffer;
+	unsigned int sz = 0;
+
+	while (size) {
+		sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+		buffer = kmap_atomic(pfn_to_page(pfn));
+		if (dir == DMA_TO_DEVICE)
+			memcpy(addr, buffer + offset, sz);
+		else
+			memcpy(buffer + offset, addr, sz);
+		kunmap_atomic(buffer);
+
+		size -= sz;
+		pfn++;
+		addr += sz;
+		offset = 0;
+	}
+}
+
+static void vduse_domain_bounce(struct vduse_iova_domain *domain,
+				dma_addr_t iova, size_t size,
+				enum dma_data_direction dir)
+{
+	struct vduse_bounce_map *map;
+	unsigned int offset;
+	void *addr;
+	size_t sz;
+
+	if (iova >= domain->bounce_size)
+		return;
+
+	while (size) {
+		map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+		offset = offset_in_page(iova);
+		sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+		if (WARN_ON(!map->bounce_page ||
+			    map->orig_phys == INVALID_PHYS_ADDR))
+			return;
+
+		addr = page_address(map->bounce_page) + offset;
+		do_bounce(map->orig_phys + offset, addr, sz, dir);
+		size -= sz;
+		iova += sz;
+	}
+}
+
+static struct page *
+vduse_domain_get_coherent_page(struct vduse_iova_domain *domain, u64 iova)
+{
+	u64 start = iova & PAGE_MASK;
+	u64 last = start + PAGE_SIZE - 1;
+	struct vhost_iotlb_map *map;
+	struct page *page = NULL;
+
+	spin_lock(&domain->iotlb_lock);
+	map = vhost_iotlb_itree_first(domain->iotlb, start, last);
+	if (!map)
+		goto out;
+
+	page = pfn_to_page((map->addr + iova - map->start) >> PAGE_SHIFT);
+	get_page(page);
+out:
+	spin_unlock(&domain->iotlb_lock);
+
+	return page;
+}
+
+static struct page *
+vduse_domain_get_bounce_page(struct vduse_iova_domain *domain, u64 iova)
+{
+	struct vduse_bounce_map *map;
+	struct page *page = NULL;
+
+	spin_lock(&domain->iotlb_lock);
+	map = &domain->bounce_maps[iova >> PAGE_SHIFT];
+	if (!map->bounce_page)
+		goto out;
+
+	page = map->bounce_page;
+	get_page(page);
+out:
+	spin_unlock(&domain->iotlb_lock);
+
+	return page;
+}
+
+static void
+vduse_domain_free_bounce_pages(struct vduse_iova_domain *domain)
+{
+	struct vduse_bounce_map *map;
+	unsigned long pfn, bounce_pfns;
+
+	bounce_pfns = domain->bounce_size >> PAGE_SHIFT;
+
+	for (pfn = 0; pfn < bounce_pfns; pfn++) {
+		map = &domain->bounce_maps[pfn];
+		if (WARN_ON(map->orig_phys != INVALID_PHYS_ADDR))
+			continue;
+
+		if (!map->bounce_page)
+			continue;
+
+		__free_page(map->bounce_page);
+		map->bounce_page = NULL;
+	}
+}
+
+void vduse_domain_reset_bounce_map(struct vduse_iova_domain *domain)
+{
+	if (!domain->bounce_map)
+		return;
+
+	spin_lock(&domain->iotlb_lock);
+	if (!domain->bounce_map)
+		goto unlock;
+
+	vduse_iotlb_del_range(domain, 0, domain->bounce_size - 1);
+	domain->bounce_map = 0;
+unlock:
+	spin_unlock(&domain->iotlb_lock);
+}
+
+static int vduse_domain_init_bounce_map(struct vduse_iova_domain *domain)
+{
+	int ret = 0;
+
+	if (domain->bounce_map)
+		return 0;
+
+	spin_lock(&domain->iotlb_lock);
+	if (domain->bounce_map)
+		goto unlock;
+
+	ret = vduse_iotlb_add_range(domain, 0, domain->bounce_size - 1,
+				    0, VHOST_MAP_RW, domain->file, 0);
+	if (ret)
+		goto unlock;
+
+	domain->bounce_map = 1;
+unlock:
+	spin_unlock(&domain->iotlb_lock);
+	return ret;
+}
+
+static dma_addr_t
+vduse_domain_alloc_iova(struct iova_domain *iovad,
+			unsigned long size, unsigned long limit)
+{
+	unsigned long shift = iova_shift(iovad);
+	unsigned long iova_len = iova_align(iovad, size) >> shift;
+	unsigned long iova_pfn;
+
+	/*
+	 * Freeing non-power-of-two-sized allocations back into the IOVA caches
+	 * will come back to bite us badly, so we have to waste a bit of space
+	 * rounding up anything cacheable to make sure that can't happen. The
+	 * order of the unadjusted size will still match upon freeing.
+	 */
+	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
+		iova_len = roundup_pow_of_two(iova_len);
+	iova_pfn = alloc_iova_fast(iovad, iova_len, limit >> shift, true);
+
+	return iova_pfn << shift;
+}
+
+static void vduse_domain_free_iova(struct iova_domain *iovad,
+				   dma_addr_t iova, size_t size)
+{
+	unsigned long shift = iova_shift(iovad);
+	unsigned long iova_len = iova_align(iovad, size) >> shift;
+
+	free_iova_fast(iovad, iova >> shift, iova_len);
+}
+
+dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
+				 struct page *page, unsigned long offset,
+				 size_t size, enum dma_data_direction dir,
+				 unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->stream_iovad;
+	unsigned long limit = domain->bounce_size - 1;
+	phys_addr_t pa = page_to_phys(page) + offset;
+	dma_addr_t iova = vduse_domain_alloc_iova(iovad, size, limit);
+
+	if (!iova)
+		return DMA_MAPPING_ERROR;
+
+	if (vduse_domain_init_bounce_map(domain))
+		goto err;
+
+	if (vduse_domain_map_bounce_page(domain, (u64)iova, (u64)size, pa))
+		goto err;
+
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+		vduse_domain_bounce(domain, iova, size, DMA_TO_DEVICE);
+
+	return iova;
+err:
+	vduse_domain_free_iova(iovad, iova, size);
+	return DMA_MAPPING_ERROR;
+}
+
+void vduse_domain_unmap_page(struct vduse_iova_domain *domain,
+			     dma_addr_t dma_addr, size_t size,
+			     enum dma_data_direction dir, unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->stream_iovad;
+
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+		vduse_domain_bounce(domain, dma_addr, size, DMA_FROM_DEVICE);
+
+	vduse_domain_unmap_bounce_page(domain, (u64)dma_addr, (u64)size);
+	vduse_domain_free_iova(iovad, dma_addr, size);
+}
+
+void *vduse_domain_alloc_coherent(struct vduse_iova_domain *domain,
+				  size_t size, dma_addr_t *dma_addr,
+				  gfp_t flag, unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->consistent_iovad;
+	unsigned long limit = domain->iova_limit;
+	dma_addr_t iova = vduse_domain_alloc_iova(iovad, size, limit);
+	void *orig = alloc_pages_exact(size, flag);
+
+	if (!iova || !orig)
+		goto err;
+
+	spin_lock(&domain->iotlb_lock);
+	if (vduse_iotlb_add_range(domain, (u64)iova, (u64)iova + size - 1,
+				  virt_to_phys(orig), VHOST_MAP_RW,
+				  domain->file, (u64)iova)) {
+		spin_unlock(&domain->iotlb_lock);
+		goto err;
+	}
+	spin_unlock(&domain->iotlb_lock);
+
+	*dma_addr = iova;
+
+	return orig;
+err:
+	*dma_addr = DMA_MAPPING_ERROR;
+	if (orig)
+		free_pages_exact(orig, size);
+	if (iova)
+		vduse_domain_free_iova(iovad, iova, size);
+
+	return NULL;
+}
+
+void vduse_domain_free_coherent(struct vduse_iova_domain *domain, size_t size,
+				void *vaddr, dma_addr_t dma_addr,
+				unsigned long attrs)
+{
+	struct iova_domain *iovad = &domain->consistent_iovad;
+	struct vhost_iotlb_map *map;
+	struct vdpa_map_file *map_file;
+	phys_addr_t pa;
+
+	spin_lock(&domain->iotlb_lock);
+	map = vhost_iotlb_itree_first(domain->iotlb, (u64)dma_addr,
+				      (u64)dma_addr + size - 1);
+	if (WARN_ON(!map)) {
+		spin_unlock(&domain->iotlb_lock);
+		return;
+	}
+	map_file = (struct vdpa_map_file *)map->opaque;
+	fput(map_file->file);
+	kfree(map_file);
+	pa = map->addr;
+	vhost_iotlb_map_free(domain->iotlb, map);
+	spin_unlock(&domain->iotlb_lock);
+
+	vduse_domain_free_iova(iovad, dma_addr, size);
+	free_pages_exact(phys_to_virt(pa), size);
+}
+
+static vm_fault_t vduse_domain_mmap_fault(struct vm_fault *vmf)
+{
+	struct vduse_iova_domain *domain = vmf->vma->vm_private_data;
+	unsigned long iova = vmf->pgoff << PAGE_SHIFT;
+	struct page *page;
+
+	if (!domain)
+		return VM_FAULT_SIGBUS;
+
+	if (iova < domain->bounce_size)
+		page = vduse_domain_get_bounce_page(domain, iova);
+	else
+		page = vduse_domain_get_coherent_page(domain, iova);
+
+	if (!page)
+		return VM_FAULT_SIGBUS;
+
+	vmf->page = page;
+
+	return 0;
+}
+
+static const struct vm_operations_struct vduse_domain_mmap_ops = {
+	.fault = vduse_domain_mmap_fault,
+};
+
+static int vduse_domain_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct vduse_iova_domain *domain = file->private_data;
+
+	vma->vm_flags |= VM_DONTDUMP | VM_DONTEXPAND;
+	vma->vm_private_data = domain;
+	vma->vm_ops = &vduse_domain_mmap_ops;
+
+	return 0;
+}
+
+static int vduse_domain_release(struct inode *inode, struct file *file)
+{
+	struct vduse_iova_domain *domain = file->private_data;
+
+	spin_lock(&domain->iotlb_lock);
+	vduse_iotlb_del_range(domain, 0, ULLONG_MAX);
+	vduse_domain_free_bounce_pages(domain);
+	spin_unlock(&domain->iotlb_lock);
+	put_iova_domain(&domain->stream_iovad);
+	put_iova_domain(&domain->consistent_iovad);
+	vhost_iotlb_free(domain->iotlb);
+	vfree(domain->bounce_maps);
+	kfree(domain);
+
+	return 0;
+}
+
+static const struct file_operations vduse_domain_fops = {
+	.owner = THIS_MODULE,
+	.mmap = vduse_domain_mmap,
+	.release = vduse_domain_release,
+};
+
+void vduse_domain_destroy(struct vduse_iova_domain *domain)
+{
+	fput(domain->file);
+}
+
+struct vduse_iova_domain *
+vduse_domain_create(unsigned long iova_limit, size_t bounce_size)
+{
+	struct vduse_iova_domain *domain;
+	struct file *file;
+	struct vduse_bounce_map *map;
+	unsigned long pfn, bounce_pfns;
+
+	bounce_pfns = PAGE_ALIGN(bounce_size) >> PAGE_SHIFT;
+	if (iova_limit <= bounce_size)
+		return NULL;
+
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		return NULL;
+
+	domain->iotlb = vhost_iotlb_alloc(0, 0);
+	if (!domain->iotlb)
+		goto err_iotlb;
+
+	domain->iova_limit = iova_limit;
+	domain->bounce_size = PAGE_ALIGN(bounce_size);
+	domain->bounce_maps = vzalloc(bounce_pfns *
+				sizeof(struct vduse_bounce_map));
+	if (!domain->bounce_maps)
+		goto err_map;
+
+	for (pfn = 0; pfn < bounce_pfns; pfn++) {
+		map = &domain->bounce_maps[pfn];
+		map->orig_phys = INVALID_PHYS_ADDR;
+	}
+	file = anon_inode_getfile("[vduse-domain]", &vduse_domain_fops,
+				domain, O_RDWR);
+	if (IS_ERR(file))
+		goto err_file;
+
+	domain->file = file;
+	spin_lock_init(&domain->iotlb_lock);
+	init_iova_domain(&domain->stream_iovad,
+			PAGE_SIZE, IOVA_START_PFN);
+	init_iova_domain(&domain->consistent_iovad,
+			PAGE_SIZE, bounce_pfns);
+
+	return domain;
+err_file:
+	vfree(domain->bounce_maps);
+err_map:
+	vhost_iotlb_free(domain->iotlb);
+err_iotlb:
+	kfree(domain);
+	return NULL;
+}
+
+int vduse_domain_init(void)
+{
+	return iova_cache_get();
+}
+
+void vduse_domain_exit(void)
+{
+	iova_cache_put();
+}
diff --git a/drivers/vdpa/vdpa_user/iova_domain.h b/drivers/vdpa/vdpa_user/iova_domain.h
new file mode 100644
index 0000000..2722d9b
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/iova_domain.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * MMU-based software IOTLB.
+ *
+ * Copyright (C) 2020-2021 Bytedance Inc. and/or its affiliates. All rights reserved.
+ *
+ * Author: Xie Yongji <xieyongji@bytedance.com>
+ *
+ */
+
+#ifndef _VDUSE_IOVA_DOMAIN_H
+#define _VDUSE_IOVA_DOMAIN_H
+
+#include <linux/iova.h>
+#include <linux/dma-mapping.h>
+#include <linux/vhost_iotlb.h>
+
+#define IOVA_START_PFN 1
+
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
+
+struct vduse_bounce_map {
+	struct page *bounce_page;
+	u64 orig_phys;
+};
+
+struct vduse_iova_domain {
+	struct iova_domain stream_iovad;
+	struct iova_domain consistent_iovad;
+	struct vduse_bounce_map *bounce_maps;
+	size_t bounce_size;
+	unsigned long iova_limit;
+	int bounce_map;
+	struct vhost_iotlb *iotlb;
+	spinlock_t iotlb_lock;
+	struct file *file;
+};
+
+int vduse_domain_set_map(struct vduse_iova_domain *domain,
+			 struct vhost_iotlb *iotlb);
+
+void vduse_domain_clear_map(struct vduse_iova_domain *domain,
+			    struct vhost_iotlb *iotlb);
+
+dma_addr_t vduse_domain_map_page(struct vduse_iova_domain *domain,
+				 struct page *page, unsigned long offset,
+				 size_t size, enum dma_data_direction dir,
+				 unsigned long attrs);
+
+void vduse_domain_unmap_page(struct vduse_iova_domain *domain,
+			     dma_addr_t dma_addr, size_t size,
+			     enum dma_data_direction dir, unsigned long attrs);
+
+void *vduse_domain_alloc_coherent(struct vduse_iova_domain *domain,
+				  size_t size, dma_addr_t *dma_addr,
+				  gfp_t flag, unsigned long attrs);
+
+void vduse_domain_free_coherent(struct vduse_iova_domain *domain, size_t size,
+				void *vaddr, dma_addr_t dma_addr,
+				unsigned long attrs);
+
+void vduse_domain_reset_bounce_map(struct vduse_iova_domain *domain);
+
+void vduse_domain_destroy(struct vduse_iova_domain *domain);
+
+struct vduse_iova_domain *vduse_domain_create(unsigned long iova_limit,
+					      size_t bounce_size);
+
+int vduse_domain_init(void);
+
+void vduse_domain_exit(void);
+
+#endif /* _VDUSE_IOVA_DOMAIN_H */
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
new file mode 100644
index 0000000..29a38ec
--- /dev/null
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -0,0 +1,1641 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VDUSE: vDPA Device in Userspace
+ *
+ * Copyright (C) 2020-2021 Bytedance Inc. and/or its affiliates. All rights reserved.
+ *
+ * Author: Xie Yongji <xieyongji@bytedance.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/eventfd.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/dma-map-ops.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/vdpa.h>
+#include <linux/nospec.h>
+#include <uapi/linux/vduse.h>
+#include <uapi/linux/vdpa.h>
+#include <uapi/linux/virtio_config.h>
+#include <uapi/linux/virtio_ids.h>
+#include <uapi/linux/virtio_blk.h>
+#include <linux/mod_devicetable.h>
+
+#include "iova_domain.h"
+
+#define DRV_AUTHOR   "Yongji Xie <xieyongji@bytedance.com>"
+#define DRV_DESC     "vDPA Device in Userspace"
+#define DRV_LICENSE  "GPL v2"
+
+#define VDUSE_DEV_MAX (1U << MINORBITS)
+#define VDUSE_BOUNCE_SIZE (64 * 1024 * 1024)
+#define VDUSE_IOVA_SIZE (128 * 1024 * 1024)
+#define VDUSE_MSG_DEFAULT_TIMEOUT 30
+
+struct vduse_virtqueue {
+	u16 index;
+	u16 num_max;
+	u32 num;
+	u64 desc_addr;
+	u64 driver_addr;
+	u64 device_addr;
+	struct vdpa_vq_state state;
+	bool ready;
+	bool kicked;
+	spinlock_t kick_lock;
+	spinlock_t irq_lock;
+	struct eventfd_ctx *kickfd;
+	struct vdpa_callback cb;
+	struct work_struct inject;
+	struct work_struct kick;
+};
+
+struct vduse_dev;
+
+struct vduse_vdpa {
+	struct vdpa_device vdpa;
+	struct vduse_dev *dev;
+};
+
+struct vduse_dev {
+	struct vduse_vdpa *vdev;
+	struct device *dev;
+	struct vduse_virtqueue *vqs;
+	struct vduse_iova_domain *domain;
+	char *name;
+	struct mutex lock;
+	spinlock_t msg_lock;
+	u64 msg_unique;
+	u32 msg_timeout;
+	wait_queue_head_t waitq;
+	struct list_head send_list;
+	struct list_head recv_list;
+	struct vdpa_callback config_cb;
+	struct work_struct inject;
+	spinlock_t irq_lock;
+	int minor;
+	bool broken;
+	bool connected;
+	u64 api_version;
+	u64 device_features;
+	u64 driver_features;
+	u32 device_id;
+	u32 vendor_id;
+	u32 generation;
+	u32 config_size;
+	void *config;
+	u8 status;
+	u32 vq_num;
+	u32 vq_align;
+};
+
+struct vduse_dev_msg {
+	struct vduse_dev_request req;
+	struct vduse_dev_response resp;
+	struct list_head list;
+	wait_queue_head_t waitq;
+	bool completed;
+};
+
+struct vduse_control {
+	u64 api_version;
+};
+
+static DEFINE_MUTEX(vduse_lock);
+static DEFINE_IDR(vduse_idr);
+
+static dev_t vduse_major;
+static struct class *vduse_class;
+static struct cdev vduse_ctrl_cdev;
+static struct cdev vduse_cdev;
+static struct workqueue_struct *vduse_irq_wq;
+
+static u32 allowed_device_id[] = {
+	VIRTIO_ID_BLOCK,
+};
+
+static inline struct vduse_dev *vdpa_to_vduse(struct vdpa_device *vdpa)
+{
+	struct vduse_vdpa *vdev = container_of(vdpa, struct vduse_vdpa, vdpa);
+
+	return vdev->dev;
+}
+
+static inline struct vduse_dev *dev_to_vduse(struct device *dev)
+{
+	struct vdpa_device *vdpa = dev_to_vdpa(dev);
+
+	return vdpa_to_vduse(vdpa);
+}
+
+static struct vduse_dev_msg *vduse_find_msg(struct list_head *head,
+					    uint32_t request_id)
+{
+	struct vduse_dev_msg *msg;
+
+	list_for_each_entry(msg, head, list) {
+		if (msg->req.request_id == request_id) {
+			list_del(&msg->list);
+			return msg;
+		}
+	}
+
+	return NULL;
+}
+
+static struct vduse_dev_msg *vduse_dequeue_msg(struct list_head *head)
+{
+	struct vduse_dev_msg *msg = NULL;
+
+	if (!list_empty(head)) {
+		msg = list_first_entry(head, struct vduse_dev_msg, list);
+		list_del(&msg->list);
+	}
+
+	return msg;
+}
+
+static void vduse_enqueue_msg(struct list_head *head,
+			      struct vduse_dev_msg *msg)
+{
+	list_add_tail(&msg->list, head);
+}
+
+static void vduse_dev_broken(struct vduse_dev *dev)
+{
+	struct vduse_dev_msg *msg, *tmp;
+
+	if (unlikely(dev->broken))
+		return;
+
+	list_splice_init(&dev->recv_list, &dev->send_list);
+	list_for_each_entry_safe(msg, tmp, &dev->send_list, list) {
+		list_del(&msg->list);
+		msg->completed = 1;
+		msg->resp.result = VDUSE_REQ_RESULT_FAILED;
+		wake_up(&msg->waitq);
+	}
+	dev->broken = true;
+	wake_up(&dev->waitq);
+}
+
+static int vduse_dev_msg_sync(struct vduse_dev *dev,
+			      struct vduse_dev_msg *msg)
+{
+	int ret;
+
+	if (unlikely(dev->broken))
+		return -EIO;
+
+	init_waitqueue_head(&msg->waitq);
+	spin_lock(&dev->msg_lock);
+	if (unlikely(dev->broken)) {
+		spin_unlock(&dev->msg_lock);
+		return -EIO;
+	}
+	msg->req.request_id = dev->msg_unique++;
+	vduse_enqueue_msg(&dev->send_list, msg);
+	wake_up(&dev->waitq);
+	spin_unlock(&dev->msg_lock);
+	if (dev->msg_timeout)
+		ret = wait_event_killable_timeout(msg->waitq, msg->completed,
+						  (long)dev->msg_timeout * HZ);
+	else
+		ret = wait_event_killable(msg->waitq, msg->completed);
+
+	spin_lock(&dev->msg_lock);
+	if (!msg->completed) {
+		list_del(&msg->list);
+		msg->resp.result = VDUSE_REQ_RESULT_FAILED;
+		/* Mark the device as malfunction when there is a timeout */
+		if (!ret)
+			vduse_dev_broken(dev);
+	}
+	ret = (msg->resp.result == VDUSE_REQ_RESULT_OK) ? 0 : -EIO;
+	spin_unlock(&dev->msg_lock);
+
+	return ret;
+}
+
+static int vduse_dev_get_vq_state_packed(struct vduse_dev *dev,
+					 struct vduse_virtqueue *vq,
+					 struct vdpa_vq_state_packed *packed)
+{
+	struct vduse_dev_msg msg = { 0 };
+	int ret;
+
+	msg.req.type = VDUSE_GET_VQ_STATE;
+	msg.req.vq_state.index = vq->index;
+
+	ret = vduse_dev_msg_sync(dev, &msg);
+	if (ret)
+		return ret;
+
+	packed->last_avail_counter =
+			msg.resp.vq_state.packed.last_avail_counter & 0x0001;
+	packed->last_avail_idx =
+			msg.resp.vq_state.packed.last_avail_idx & 0x7FFF;
+	packed->last_used_counter =
+			msg.resp.vq_state.packed.last_used_counter & 0x0001;
+	packed->last_used_idx =
+			msg.resp.vq_state.packed.last_used_idx & 0x7FFF;
+
+	return 0;
+}
+
+static int vduse_dev_get_vq_state_split(struct vduse_dev *dev,
+					struct vduse_virtqueue *vq,
+					struct vdpa_vq_state_split *split)
+{
+	struct vduse_dev_msg msg = { 0 };
+	int ret;
+
+	msg.req.type = VDUSE_GET_VQ_STATE;
+	msg.req.vq_state.index = vq->index;
+
+	ret = vduse_dev_msg_sync(dev, &msg);
+	if (ret)
+		return ret;
+
+	split->avail_index = msg.resp.vq_state.split.avail_index;
+
+	return 0;
+}
+
+static int vduse_dev_set_status(struct vduse_dev *dev, u8 status)
+{
+	struct vduse_dev_msg msg = { 0 };
+
+	msg.req.type = VDUSE_SET_STATUS;
+	msg.req.s.status = status;
+
+	return vduse_dev_msg_sync(dev, &msg);
+}
+
+static int vduse_dev_update_iotlb(struct vduse_dev *dev,
+				  u64 start, u64 last)
+{
+	struct vduse_dev_msg msg = { 0 };
+
+	if (last < start)
+		return -EINVAL;
+
+	msg.req.type = VDUSE_UPDATE_IOTLB;
+	msg.req.iova.start = start;
+	msg.req.iova.last = last;
+
+	return vduse_dev_msg_sync(dev, &msg);
+}
+
+static ssize_t vduse_dev_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct vduse_dev *dev = file->private_data;
+	struct vduse_dev_msg *msg;
+	int size = sizeof(struct vduse_dev_request);
+	ssize_t ret;
+
+	if (iov_iter_count(to) < size)
+		return -EINVAL;
+
+	spin_lock(&dev->msg_lock);
+	while (1) {
+		msg = vduse_dequeue_msg(&dev->send_list);
+		if (msg)
+			break;
+
+		ret = -EAGAIN;
+		if (file->f_flags & O_NONBLOCK)
+			goto unlock;
+
+		spin_unlock(&dev->msg_lock);
+		ret = wait_event_interruptible_exclusive(dev->waitq,
+					!list_empty(&dev->send_list));
+		if (ret)
+			return ret;
+
+		spin_lock(&dev->msg_lock);
+	}
+	spin_unlock(&dev->msg_lock);
+	ret = copy_to_iter(&msg->req, size, to);
+	spin_lock(&dev->msg_lock);
+	if (ret != size) {
+		ret = -EFAULT;
+		vduse_enqueue_msg(&dev->send_list, msg);
+		goto unlock;
+	}
+	vduse_enqueue_msg(&dev->recv_list, msg);
+unlock:
+	spin_unlock(&dev->msg_lock);
+
+	return ret;
+}
+
+static bool is_mem_zero(const char *ptr, int size)
+{
+	int i;
+
+	for (i = 0; i < size; i++) {
+		if (ptr[i])
+			return false;
+	}
+	return true;
+}
+
+static ssize_t vduse_dev_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vduse_dev *dev = file->private_data;
+	struct vduse_dev_response resp;
+	struct vduse_dev_msg *msg;
+	size_t ret;
+
+	ret = copy_from_iter(&resp, sizeof(resp), from);
+	if (ret != sizeof(resp))
+		return -EINVAL;
+
+	if (!is_mem_zero((const char *)resp.reserved, sizeof(resp.reserved)))
+		return -EINVAL;
+
+	spin_lock(&dev->msg_lock);
+	msg = vduse_find_msg(&dev->recv_list, resp.request_id);
+	if (!msg) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	memcpy(&msg->resp, &resp, sizeof(resp));
+	msg->completed = 1;
+	wake_up(&msg->waitq);
+unlock:
+	spin_unlock(&dev->msg_lock);
+
+	return ret;
+}
+
+static __poll_t vduse_dev_poll(struct file *file, poll_table *wait)
+{
+	struct vduse_dev *dev = file->private_data;
+	__poll_t mask = 0;
+
+	poll_wait(file, &dev->waitq, wait);
+
+	spin_lock(&dev->msg_lock);
+
+	if (unlikely(dev->broken))
+		mask |= EPOLLERR;
+	if (!list_empty(&dev->send_list))
+		mask |= EPOLLIN | EPOLLRDNORM;
+	if (!list_empty(&dev->recv_list))
+		mask |= EPOLLOUT | EPOLLWRNORM;
+
+	spin_unlock(&dev->msg_lock);
+
+	return mask;
+}
+
+static void vduse_dev_reset(struct vduse_dev *dev)
+{
+	int i;
+	struct vduse_iova_domain *domain = dev->domain;
+
+	/* The coherent mappings are handled in vduse_dev_free_coherent() */
+	if (domain->bounce_map)
+		vduse_domain_reset_bounce_map(domain);
+
+	dev->status = 0;
+	dev->driver_features = 0;
+	dev->generation++;
+	spin_lock(&dev->irq_lock);
+	dev->config_cb.callback = NULL;
+	dev->config_cb.private = NULL;
+	spin_unlock(&dev->irq_lock);
+	flush_work(&dev->inject);
+
+	for (i = 0; i < dev->vq_num; i++) {
+		struct vduse_virtqueue *vq = &dev->vqs[i];
+
+		vq->ready = false;
+		vq->desc_addr = 0;
+		vq->driver_addr = 0;
+		vq->device_addr = 0;
+		vq->num = 0;
+		memset(&vq->state, 0, sizeof(vq->state));
+
+		spin_lock(&vq->kick_lock);
+		vq->kicked = false;
+		if (vq->kickfd)
+			eventfd_ctx_put(vq->kickfd);
+		vq->kickfd = NULL;
+		spin_unlock(&vq->kick_lock);
+
+		spin_lock(&vq->irq_lock);
+		vq->cb.callback = NULL;
+		vq->cb.private = NULL;
+		spin_unlock(&vq->irq_lock);
+		flush_work(&vq->inject);
+		flush_work(&vq->kick);
+	}
+}
+
+static int vduse_vdpa_set_vq_address(struct vdpa_device *vdpa, u16 idx,
+				u64 desc_area, u64 driver_area,
+				u64 device_area)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	vq->desc_addr = desc_area;
+	vq->driver_addr = driver_area;
+	vq->device_addr = device_area;
+
+	return 0;
+}
+
+static void vduse_vq_kick(struct vduse_virtqueue *vq)
+{
+	spin_lock(&vq->kick_lock);
+	if (!vq->ready)
+		goto unlock;
+
+	if (vq->kickfd)
+		eventfd_signal(vq->kickfd, 1);
+	else
+		vq->kicked = true;
+unlock:
+	spin_unlock(&vq->kick_lock);
+}
+
+static void vduse_vq_kick_work(struct work_struct *work)
+{
+	struct vduse_virtqueue *vq = container_of(work,
+					struct vduse_virtqueue, kick);
+
+	vduse_vq_kick(vq);
+}
+
+static void vduse_vdpa_kick_vq(struct vdpa_device *vdpa, u16 idx)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	if (!eventfd_signal_allowed()) {
+		schedule_work(&vq->kick);
+		return;
+	}
+	vduse_vq_kick(vq);
+}
+
+static void vduse_vdpa_set_vq_cb(struct vdpa_device *vdpa, u16 idx,
+			      struct vdpa_callback *cb)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	spin_lock(&vq->irq_lock);
+	vq->cb.callback = cb->callback;
+	vq->cb.private = cb->private;
+	spin_unlock(&vq->irq_lock);
+}
+
+static void vduse_vdpa_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	vq->num = num;
+}
+
+static void vduse_vdpa_set_vq_ready(struct vdpa_device *vdpa,
+					u16 idx, bool ready)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	vq->ready = ready;
+}
+
+static bool vduse_vdpa_get_vq_ready(struct vdpa_device *vdpa, u16 idx)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	return vq->ready;
+}
+
+static int vduse_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 idx,
+				const struct vdpa_vq_state *state)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) {
+		vq->state.packed.last_avail_counter =
+				state->packed.last_avail_counter;
+		vq->state.packed.last_avail_idx = state->packed.last_avail_idx;
+		vq->state.packed.last_used_counter =
+				state->packed.last_used_counter;
+		vq->state.packed.last_used_idx = state->packed.last_used_idx;
+	} else
+		vq->state.split.avail_index = state->split.avail_index;
+
+	return 0;
+}
+
+static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx,
+				struct vdpa_vq_state *state)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	struct vduse_virtqueue *vq = &dev->vqs[idx];
+
+	if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED))
+		return vduse_dev_get_vq_state_packed(dev, vq, &state->packed);
+
+	return vduse_dev_get_vq_state_split(dev, vq, &state->split);
+}
+
+static u32 vduse_vdpa_get_vq_align(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->vq_align;
+}
+
+static u64 vduse_vdpa_get_features(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->device_features;
+}
+
+static int vduse_vdpa_set_features(struct vdpa_device *vdpa, u64 features)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	dev->driver_features = features;
+	return 0;
+}
+
+static void vduse_vdpa_set_config_cb(struct vdpa_device *vdpa,
+				  struct vdpa_callback *cb)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	spin_lock(&dev->irq_lock);
+	dev->config_cb.callback = cb->callback;
+	dev->config_cb.private = cb->private;
+	spin_unlock(&dev->irq_lock);
+}
+
+static u16 vduse_vdpa_get_vq_num_max(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	u16 num_max = 0;
+	int i;
+
+	for (i = 0; i < dev->vq_num; i++)
+		if (num_max < dev->vqs[i].num_max)
+			num_max = dev->vqs[i].num_max;
+
+	return num_max;
+}
+
+static u32 vduse_vdpa_get_device_id(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->device_id;
+}
+
+static u32 vduse_vdpa_get_vendor_id(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->vendor_id;
+}
+
+static u8 vduse_vdpa_get_status(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->status;
+}
+
+static void vduse_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	if (vduse_dev_set_status(dev, status))
+		return;
+
+	dev->status = status;
+}
+
+static size_t vduse_vdpa_get_config_size(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->config_size;
+}
+
+static void vduse_vdpa_get_config(struct vdpa_device *vdpa, unsigned int offset,
+				  void *buf, unsigned int len)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	if (len > dev->config_size - offset)
+		return;
+
+	memcpy(buf, dev->config + offset, len);
+}
+
+static void vduse_vdpa_set_config(struct vdpa_device *vdpa, unsigned int offset,
+			const void *buf, unsigned int len)
+{
+	/* Now we only support read-only configuration space */
+}
+
+static int vduse_vdpa_reset(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	if (vduse_dev_set_status(dev, 0))
+		return -EIO;
+
+	vduse_dev_reset(dev);
+
+	return 0;
+}
+
+static u32 vduse_vdpa_get_generation(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	return dev->generation;
+}
+
+static int vduse_vdpa_set_map(struct vdpa_device *vdpa,
+				struct vhost_iotlb *iotlb)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+	int ret;
+
+	ret = vduse_domain_set_map(dev->domain, iotlb);
+	if (ret)
+		return ret;
+
+	ret = vduse_dev_update_iotlb(dev, 0ULL, ULLONG_MAX);
+	if (ret) {
+		vduse_domain_clear_map(dev->domain, iotlb);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void vduse_vdpa_free(struct vdpa_device *vdpa)
+{
+	struct vduse_dev *dev = vdpa_to_vduse(vdpa);
+
+	dev->vdev = NULL;
+}
+
+static const struct vdpa_config_ops vduse_vdpa_config_ops = {
+	.set_vq_address		= vduse_vdpa_set_vq_address,
+	.kick_vq		= vduse_vdpa_kick_vq,
+	.set_vq_cb		= vduse_vdpa_set_vq_cb,
+	.set_vq_num             = vduse_vdpa_set_vq_num,
+	.set_vq_ready		= vduse_vdpa_set_vq_ready,
+	.get_vq_ready		= vduse_vdpa_get_vq_ready,
+	.set_vq_state		= vduse_vdpa_set_vq_state,
+	.get_vq_state		= vduse_vdpa_get_vq_state,
+	.get_vq_align		= vduse_vdpa_get_vq_align,
+	.get_features		= vduse_vdpa_get_features,
+	.set_features		= vduse_vdpa_set_features,
+	.set_config_cb		= vduse_vdpa_set_config_cb,
+	.get_vq_num_max		= vduse_vdpa_get_vq_num_max,
+	.get_device_id		= vduse_vdpa_get_device_id,
+	.get_vendor_id		= vduse_vdpa_get_vendor_id,
+	.get_status		= vduse_vdpa_get_status,
+	.set_status		= vduse_vdpa_set_status,
+	.get_config_size	= vduse_vdpa_get_config_size,
+	.get_config		= vduse_vdpa_get_config,
+	.set_config		= vduse_vdpa_set_config,
+	.get_generation		= vduse_vdpa_get_generation,
+	.reset			= vduse_vdpa_reset,
+	.set_map		= vduse_vdpa_set_map,
+	.free			= vduse_vdpa_free,
+};
+
+static dma_addr_t vduse_dev_map_page(struct device *dev, struct page *page,
+				     unsigned long offset, size_t size,
+				     enum dma_data_direction dir,
+				     unsigned long attrs)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+
+	return vduse_domain_map_page(domain, page, offset, size, dir, attrs);
+}
+
+static void vduse_dev_unmap_page(struct device *dev, dma_addr_t dma_addr,
+				size_t size, enum dma_data_direction dir,
+				unsigned long attrs)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+
+	return vduse_domain_unmap_page(domain, dma_addr, size, dir, attrs);
+}
+
+static void *vduse_dev_alloc_coherent(struct device *dev, size_t size,
+					dma_addr_t *dma_addr, gfp_t flag,
+					unsigned long attrs)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+	unsigned long iova;
+	void *addr;
+
+	*dma_addr = DMA_MAPPING_ERROR;
+	addr = vduse_domain_alloc_coherent(domain, size,
+				(dma_addr_t *)&iova, flag, attrs);
+	if (!addr)
+		return NULL;
+
+	*dma_addr = (dma_addr_t)iova;
+
+	return addr;
+}
+
+static void vduse_dev_free_coherent(struct device *dev, size_t size,
+					void *vaddr, dma_addr_t dma_addr,
+					unsigned long attrs)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+
+	vduse_domain_free_coherent(domain, size, vaddr, dma_addr, attrs);
+}
+
+static size_t vduse_dev_max_mapping_size(struct device *dev)
+{
+	struct vduse_dev *vdev = dev_to_vduse(dev);
+	struct vduse_iova_domain *domain = vdev->domain;
+
+	return domain->bounce_size;
+}
+
+static const struct dma_map_ops vduse_dev_dma_ops = {
+	.map_page = vduse_dev_map_page,
+	.unmap_page = vduse_dev_unmap_page,
+	.alloc = vduse_dev_alloc_coherent,
+	.free = vduse_dev_free_coherent,
+	.max_mapping_size = vduse_dev_max_mapping_size,
+};
+
+static unsigned int perm_to_file_flags(u8 perm)
+{
+	unsigned int flags = 0;
+
+	switch (perm) {
+	case VDUSE_ACCESS_WO:
+		flags |= O_WRONLY;
+		break;
+	case VDUSE_ACCESS_RO:
+		flags |= O_RDONLY;
+		break;
+	case VDUSE_ACCESS_RW:
+		flags |= O_RDWR;
+		break;
+	default:
+		WARN(1, "invalidate vhost IOTLB permission\n");
+		break;
+	}
+
+	return flags;
+}
+
+static int vduse_kickfd_setup(struct vduse_dev *dev,
+			struct vduse_vq_eventfd *eventfd)
+{
+	struct eventfd_ctx *ctx = NULL;
+	struct vduse_virtqueue *vq;
+	u32 index;
+
+	if (eventfd->index >= dev->vq_num)
+		return -EINVAL;
+
+	index = array_index_nospec(eventfd->index, dev->vq_num);
+	vq = &dev->vqs[index];
+	if (eventfd->fd >= 0) {
+		ctx = eventfd_ctx_fdget(eventfd->fd);
+		if (IS_ERR(ctx))
+			return PTR_ERR(ctx);
+	} else if (eventfd->fd != VDUSE_EVENTFD_DEASSIGN)
+		return 0;
+
+	spin_lock(&vq->kick_lock);
+	if (vq->kickfd)
+		eventfd_ctx_put(vq->kickfd);
+	vq->kickfd = ctx;
+	if (vq->ready && vq->kicked && vq->kickfd) {
+		eventfd_signal(vq->kickfd, 1);
+		vq->kicked = false;
+	}
+	spin_unlock(&vq->kick_lock);
+
+	return 0;
+}
+
+static bool vduse_dev_is_ready(struct vduse_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < dev->vq_num; i++)
+		if (!dev->vqs[i].num_max)
+			return false;
+
+	return true;
+}
+
+static void vduse_dev_irq_inject(struct work_struct *work)
+{
+	struct vduse_dev *dev = container_of(work, struct vduse_dev, inject);
+
+	spin_lock_irq(&dev->irq_lock);
+	if (dev->config_cb.callback)
+		dev->config_cb.callback(dev->config_cb.private);
+	spin_unlock_irq(&dev->irq_lock);
+}
+
+static void vduse_vq_irq_inject(struct work_struct *work)
+{
+	struct vduse_virtqueue *vq = container_of(work,
+					struct vduse_virtqueue, inject);
+
+	spin_lock_irq(&vq->irq_lock);
+	if (vq->ready && vq->cb.callback)
+		vq->cb.callback(vq->cb.private);
+	spin_unlock_irq(&vq->irq_lock);
+}
+
+static long vduse_dev_ioctl(struct file *file, unsigned int cmd,
+			    unsigned long arg)
+{
+	struct vduse_dev *dev = file->private_data;
+	void __user *argp = (void __user *)arg;
+	int ret;
+
+	if (unlikely(dev->broken))
+		return -EPERM;
+
+	switch (cmd) {
+	case VDUSE_IOTLB_GET_FD: {
+		struct vduse_iotlb_entry entry;
+		struct vhost_iotlb_map *map;
+		struct vdpa_map_file *map_file;
+		struct vduse_iova_domain *domain = dev->domain;
+		struct file *f = NULL;
+
+		ret = -EFAULT;
+		if (copy_from_user(&entry, argp, sizeof(entry)))
+			break;
+
+		ret = -EINVAL;
+		if (entry.start > entry.last)
+			break;
+
+		spin_lock(&domain->iotlb_lock);
+		map = vhost_iotlb_itree_first(domain->iotlb,
+					      entry.start, entry.last);
+		if (map) {
+			map_file = (struct vdpa_map_file *)map->opaque;
+			f = get_file(map_file->file);
+			entry.offset = map_file->offset;
+			entry.start = map->start;
+			entry.last = map->last;
+			entry.perm = map->perm;
+		}
+		spin_unlock(&domain->iotlb_lock);
+		ret = -EINVAL;
+		if (!f)
+			break;
+
+		ret = -EFAULT;
+		if (copy_to_user(argp, &entry, sizeof(entry))) {
+			fput(f);
+			break;
+		}
+		ret = receive_fd(f, perm_to_file_flags(entry.perm));
+		fput(f);
+		break;
+	}
+	case VDUSE_DEV_GET_FEATURES:
+		/*
+		 * Just mirror what driver wrote here.
+		 * The driver is expected to check FEATURE_OK later.
+		 */
+		ret = put_user(dev->driver_features, (u64 __user *)argp);
+		break;
+	case VDUSE_DEV_SET_CONFIG: {
+		struct vduse_config_data config;
+		unsigned long size = offsetof(struct vduse_config_data,
+					      buffer);
+
+		ret = -EFAULT;
+		if (copy_from_user(&config, argp, size))
+			break;
+
+		ret = -EINVAL;
+		if (config.length == 0 ||
+		    config.length > dev->config_size - config.offset)
+			break;
+
+		ret = -EFAULT;
+		if (copy_from_user(dev->config + config.offset, argp + size,
+				   config.length))
+			break;
+
+		ret = 0;
+		break;
+	}
+	case VDUSE_DEV_INJECT_CONFIG_IRQ:
+		ret = 0;
+		queue_work(vduse_irq_wq, &dev->inject);
+		break;
+	case VDUSE_VQ_SETUP: {
+		struct vduse_vq_config config;
+		u32 index;
+
+		ret = -EFAULT;
+		if (copy_from_user(&config, argp, sizeof(config)))
+			break;
+
+		ret = -EINVAL;
+		if (config.index >= dev->vq_num)
+			break;
+
+		if (!is_mem_zero((const char *)config.reserved,
+				 sizeof(config.reserved)))
+			break;
+
+		index = array_index_nospec(config.index, dev->vq_num);
+		dev->vqs[index].num_max = config.max_size;
+		ret = 0;
+		break;
+	}
+	case VDUSE_VQ_GET_INFO: {
+		struct vduse_vq_info vq_info;
+		struct vduse_virtqueue *vq;
+		u32 index;
+
+		ret = -EFAULT;
+		if (copy_from_user(&vq_info, argp, sizeof(vq_info)))
+			break;
+
+		ret = -EINVAL;
+		if (vq_info.index >= dev->vq_num)
+			break;
+
+		index = array_index_nospec(vq_info.index, dev->vq_num);
+		vq = &dev->vqs[index];
+		vq_info.desc_addr = vq->desc_addr;
+		vq_info.driver_addr = vq->driver_addr;
+		vq_info.device_addr = vq->device_addr;
+		vq_info.num = vq->num;
+
+		if (dev->driver_features & BIT_ULL(VIRTIO_F_RING_PACKED)) {
+			vq_info.packed.last_avail_counter =
+				vq->state.packed.last_avail_counter;
+			vq_info.packed.last_avail_idx =
+				vq->state.packed.last_avail_idx;
+			vq_info.packed.last_used_counter =
+				vq->state.packed.last_used_counter;
+			vq_info.packed.last_used_idx =
+				vq->state.packed.last_used_idx;
+		} else
+			vq_info.split.avail_index =
+				vq->state.split.avail_index;
+
+		vq_info.ready = vq->ready;
+
+		ret = -EFAULT;
+		if (copy_to_user(argp, &vq_info, sizeof(vq_info)))
+			break;
+
+		ret = 0;
+		break;
+	}
+	case VDUSE_VQ_SETUP_KICKFD: {
+		struct vduse_vq_eventfd eventfd;
+
+		ret = -EFAULT;
+		if (copy_from_user(&eventfd, argp, sizeof(eventfd)))
+			break;
+
+		ret = vduse_kickfd_setup(dev, &eventfd);
+		break;
+	}
+	case VDUSE_VQ_INJECT_IRQ: {
+		u32 index;
+
+		ret = -EFAULT;
+		if (get_user(index, (u32 __user *)argp))
+			break;
+
+		ret = -EINVAL;
+		if (index >= dev->vq_num)
+			break;
+
+		ret = 0;
+		index = array_index_nospec(index, dev->vq_num);
+		queue_work(vduse_irq_wq, &dev->vqs[index].inject);
+		break;
+	}
+	default:
+		ret = -ENOIOCTLCMD;
+		break;
+	}
+
+	return ret;
+}
+
+static int vduse_dev_release(struct inode *inode, struct file *file)
+{
+	struct vduse_dev *dev = file->private_data;
+
+	spin_lock(&dev->msg_lock);
+	/* Make sure the inflight messages can processed after reconncection */
+	list_splice_init(&dev->recv_list, &dev->send_list);
+	spin_unlock(&dev->msg_lock);
+	dev->connected = false;
+
+	return 0;
+}
+
+static struct vduse_dev *vduse_dev_get_from_minor(int minor)
+{
+	struct vduse_dev *dev;
+
+	mutex_lock(&vduse_lock);
+	dev = idr_find(&vduse_idr, minor);
+	mutex_unlock(&vduse_lock);
+
+	return dev;
+}
+
+static int vduse_dev_open(struct inode *inode, struct file *file)
+{
+	int ret;
+	struct vduse_dev *dev = vduse_dev_get_from_minor(iminor(inode));
+
+	if (!dev)
+		return -ENODEV;
+
+	ret = -EBUSY;
+	mutex_lock(&dev->lock);
+	if (dev->connected)
+		goto unlock;
+
+	ret = 0;
+	dev->connected = true;
+	file->private_data = dev;
+unlock:
+	mutex_unlock(&dev->lock);
+
+	return ret;
+}
+
+static const struct file_operations vduse_dev_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vduse_dev_open,
+	.release	= vduse_dev_release,
+	.read_iter	= vduse_dev_read_iter,
+	.write_iter	= vduse_dev_write_iter,
+	.poll		= vduse_dev_poll,
+	.unlocked_ioctl	= vduse_dev_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+	.llseek		= noop_llseek,
+};
+
+static struct vduse_dev *vduse_dev_create(void)
+{
+	struct vduse_dev *dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+
+	if (!dev)
+		return NULL;
+
+	mutex_init(&dev->lock);
+	spin_lock_init(&dev->msg_lock);
+	INIT_LIST_HEAD(&dev->send_list);
+	INIT_LIST_HEAD(&dev->recv_list);
+	spin_lock_init(&dev->irq_lock);
+
+	INIT_WORK(&dev->inject, vduse_dev_irq_inject);
+	init_waitqueue_head(&dev->waitq);
+
+	return dev;
+}
+
+static void vduse_dev_destroy(struct vduse_dev *dev)
+{
+	kfree(dev);
+}
+
+static struct vduse_dev *vduse_find_dev(const char *name)
+{
+	struct vduse_dev *dev;
+	int id;
+
+	idr_for_each_entry(&vduse_idr, dev, id)
+		if (!strcmp(dev->name, name))
+			return dev;
+
+	return NULL;
+}
+
+static int vduse_destroy_dev(char *name)
+{
+	struct vduse_dev *dev = vduse_find_dev(name);
+
+	if (!dev)
+		return -EINVAL;
+
+	mutex_lock(&dev->lock);
+	if (dev->vdev || dev->connected) {
+		mutex_unlock(&dev->lock);
+		return -EBUSY;
+	}
+	dev->connected = true;
+	mutex_unlock(&dev->lock);
+
+	vduse_dev_reset(dev);
+	device_destroy(vduse_class, MKDEV(MAJOR(vduse_major), dev->minor));
+	idr_remove(&vduse_idr, dev->minor);
+	kvfree(dev->config);
+	kfree(dev->vqs);
+	vduse_domain_destroy(dev->domain);
+	kfree(dev->name);
+	vduse_dev_destroy(dev);
+	module_put(THIS_MODULE);
+
+	return 0;
+}
+
+static bool device_is_allowed(u32 device_id)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(allowed_device_id); i++)
+		if (allowed_device_id[i] == device_id)
+			return true;
+
+	return false;
+}
+
+static bool features_is_valid(u64 features)
+{
+	if (!(features & (1ULL << VIRTIO_F_ACCESS_PLATFORM)))
+		return false;
+
+	/* Now we only support read-only configuration space */
+	if (features & (1ULL << VIRTIO_BLK_F_CONFIG_WCE))
+		return false;
+
+	return true;
+}
+
+static bool vduse_validate_config(struct vduse_dev_config *config)
+{
+	if (!is_mem_zero((const char *)config->reserved,
+			 sizeof(config->reserved)))
+		return false;
+
+	if (config->vq_align > PAGE_SIZE)
+		return false;
+
+	if (config->config_size > PAGE_SIZE)
+		return false;
+
+	if (!device_is_allowed(config->device_id))
+		return false;
+
+	if (!features_is_valid(config->features))
+		return false;
+
+	return true;
+}
+
+static ssize_t msg_timeout_show(struct device *device,
+				struct device_attribute *attr, char *buf)
+{
+	struct vduse_dev *dev = dev_get_drvdata(device);
+
+	return sysfs_emit(buf, "%u\n", dev->msg_timeout);
+}
+
+static ssize_t msg_timeout_store(struct device *device,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct vduse_dev *dev = dev_get_drvdata(device);
+	int ret;
+
+	ret = kstrtouint(buf, 10, &dev->msg_timeout);
+	if (ret < 0)
+		return ret;
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(msg_timeout);
+
+static struct attribute *vduse_dev_attrs[] = {
+	&dev_attr_msg_timeout.attr,
+	NULL
+};
+
+ATTRIBUTE_GROUPS(vduse_dev);
+
+static int vduse_create_dev(struct vduse_dev_config *config,
+			    void *config_buf, u64 api_version)
+{
+	int i, ret;
+	struct vduse_dev *dev;
+
+	ret = -EEXIST;
+	if (vduse_find_dev(config->name))
+		goto err;
+
+	ret = -ENOMEM;
+	dev = vduse_dev_create();
+	if (!dev)
+		goto err;
+
+	dev->api_version = api_version;
+	dev->device_features = config->features;
+	dev->device_id = config->device_id;
+	dev->vendor_id = config->vendor_id;
+	dev->name = kstrdup(config->name, GFP_KERNEL);
+	if (!dev->name)
+		goto err_str;
+
+	dev->domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1,
+					  VDUSE_BOUNCE_SIZE);
+	if (!dev->domain)
+		goto err_domain;
+
+	dev->config = config_buf;
+	dev->config_size = config->config_size;
+	dev->vq_align = config->vq_align;
+	dev->vq_num = config->vq_num;
+	dev->vqs = kcalloc(dev->vq_num, sizeof(*dev->vqs), GFP_KERNEL);
+	if (!dev->vqs)
+		goto err_vqs;
+
+	for (i = 0; i < dev->vq_num; i++) {
+		dev->vqs[i].index = i;
+		INIT_WORK(&dev->vqs[i].inject, vduse_vq_irq_inject);
+		INIT_WORK(&dev->vqs[i].kick, vduse_vq_kick_work);
+		spin_lock_init(&dev->vqs[i].kick_lock);
+		spin_lock_init(&dev->vqs[i].irq_lock);
+	}
+
+	ret = idr_alloc(&vduse_idr, dev, 1, VDUSE_DEV_MAX, GFP_KERNEL);
+	if (ret < 0)
+		goto err_idr;
+
+	dev->minor = ret;
+	dev->msg_timeout = VDUSE_MSG_DEFAULT_TIMEOUT;
+	dev->dev = device_create(vduse_class, NULL,
+				 MKDEV(MAJOR(vduse_major), dev->minor),
+				 dev, "%s", config->name);
+	if (IS_ERR(dev->dev)) {
+		ret = PTR_ERR(dev->dev);
+		goto err_dev;
+	}
+	__module_get(THIS_MODULE);
+
+	return 0;
+err_dev:
+	idr_remove(&vduse_idr, dev->minor);
+err_idr:
+	kfree(dev->vqs);
+err_vqs:
+	vduse_domain_destroy(dev->domain);
+err_domain:
+	kfree(dev->name);
+err_str:
+	vduse_dev_destroy(dev);
+err:
+	kvfree(config_buf);
+	return ret;
+}
+
+static long vduse_ioctl(struct file *file, unsigned int cmd,
+			unsigned long arg)
+{
+	int ret;
+	void __user *argp = (void __user *)arg;
+	struct vduse_control *control = file->private_data;
+
+	mutex_lock(&vduse_lock);
+	switch (cmd) {
+	case VDUSE_GET_API_VERSION:
+		ret = put_user(control->api_version, (u64 __user *)argp);
+		break;
+	case VDUSE_SET_API_VERSION: {
+		u64 api_version;
+
+		ret = -EFAULT;
+		if (get_user(api_version, (u64 __user *)argp))
+			break;
+
+		ret = -EINVAL;
+		if (api_version > VDUSE_API_VERSION)
+			break;
+
+		ret = 0;
+		control->api_version = api_version;
+		break;
+	}
+	case VDUSE_CREATE_DEV: {
+		struct vduse_dev_config config;
+		unsigned long size = offsetof(struct vduse_dev_config, config);
+		void *buf;
+
+		ret = -EFAULT;
+		if (copy_from_user(&config, argp, size))
+			break;
+
+		ret = -EINVAL;
+		if (vduse_validate_config(&config) == false)
+			break;
+
+		buf = vmemdup_user(argp + size, config.config_size);
+		if (IS_ERR(buf)) {
+			ret = PTR_ERR(buf);
+			break;
+		}
+		config.name[VDUSE_NAME_MAX - 1] = '\0';
+		ret = vduse_create_dev(&config, buf, control->api_version);
+		break;
+	}
+	case VDUSE_DESTROY_DEV: {
+		char name[VDUSE_NAME_MAX];
+
+		ret = -EFAULT;
+		if (copy_from_user(name, argp, VDUSE_NAME_MAX))
+			break;
+
+		name[VDUSE_NAME_MAX - 1] = '\0';
+		ret = vduse_destroy_dev(name);
+		break;
+	}
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	mutex_unlock(&vduse_lock);
+
+	return ret;
+}
+
+static int vduse_release(struct inode *inode, struct file *file)
+{
+	struct vduse_control *control = file->private_data;
+
+	kfree(control);
+	return 0;
+}
+
+static int vduse_open(struct inode *inode, struct file *file)
+{
+	struct vduse_control *control;
+
+	control = kmalloc(sizeof(struct vduse_control), GFP_KERNEL);
+	if (!control)
+		return -ENOMEM;
+
+	control->api_version = VDUSE_API_VERSION;
+	file->private_data = control;
+
+	return 0;
+}
+
+static const struct file_operations vduse_ctrl_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vduse_open,
+	.release	= vduse_release,
+	.unlocked_ioctl	= vduse_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+	.llseek		= noop_llseek,
+};
+
+static char *vduse_devnode(struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "vduse/%s", dev_name(dev));
+}
+
+static void vduse_mgmtdev_release(struct device *dev)
+{
+}
+
+static struct device vduse_mgmtdev = {
+	.init_name = "vduse",
+	.release = vduse_mgmtdev_release,
+};
+
+static struct vdpa_mgmt_dev mgmt_dev;
+
+static int vduse_dev_init_vdpa(struct vduse_dev *dev, const char *name)
+{
+	struct vduse_vdpa *vdev;
+	int ret;
+
+	if (dev->vdev)
+		return -EEXIST;
+
+	vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev,
+				 &vduse_vdpa_config_ops, name, true);
+	if (IS_ERR(vdev))
+		return PTR_ERR(vdev);
+
+	dev->vdev = vdev;
+	vdev->dev = dev;
+	vdev->vdpa.dev.dma_mask = &vdev->vdpa.dev.coherent_dma_mask;
+	ret = dma_set_mask_and_coherent(&vdev->vdpa.dev, DMA_BIT_MASK(64));
+	if (ret) {
+		put_device(&vdev->vdpa.dev);
+		return ret;
+	}
+	set_dma_ops(&vdev->vdpa.dev, &vduse_dev_dma_ops);
+	vdev->vdpa.dma_dev = &vdev->vdpa.dev;
+	vdev->vdpa.mdev = &mgmt_dev;
+
+	return 0;
+}
+
+static int vdpa_dev_add(struct vdpa_mgmt_dev *mdev, const char *name)
+{
+	struct vduse_dev *dev;
+	int ret;
+
+	mutex_lock(&vduse_lock);
+	dev = vduse_find_dev(name);
+	if (!dev || !vduse_dev_is_ready(dev)) {
+		mutex_unlock(&vduse_lock);
+		return -EINVAL;
+	}
+	ret = vduse_dev_init_vdpa(dev, name);
+	mutex_unlock(&vduse_lock);
+	if (ret)
+		return ret;
+
+	ret = _vdpa_register_device(&dev->vdev->vdpa, dev->vq_num);
+	if (ret) {
+		put_device(&dev->vdev->vdpa.dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void vdpa_dev_del(struct vdpa_mgmt_dev *mdev, struct vdpa_device *dev)
+{
+	_vdpa_unregister_device(dev);
+}
+
+static const struct vdpa_mgmtdev_ops vdpa_dev_mgmtdev_ops = {
+	.dev_add = vdpa_dev_add,
+	.dev_del = vdpa_dev_del,
+};
+
+static struct virtio_device_id id_table[] = {
+	{ VIRTIO_ID_BLOCK, VIRTIO_DEV_ANY_ID },
+	{ 0 },
+};
+
+static struct vdpa_mgmt_dev mgmt_dev = {
+	.device = &vduse_mgmtdev,
+	.id_table = id_table,
+	.ops = &vdpa_dev_mgmtdev_ops,
+};
+
+static int vduse_mgmtdev_init(void)
+{
+	int ret;
+
+	ret = device_register(&vduse_mgmtdev);
+	if (ret)
+		return ret;
+
+	ret = vdpa_mgmtdev_register(&mgmt_dev);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	device_unregister(&vduse_mgmtdev);
+	return ret;
+}
+
+static void vduse_mgmtdev_exit(void)
+{
+	vdpa_mgmtdev_unregister(&mgmt_dev);
+	device_unregister(&vduse_mgmtdev);
+}
+
+static int vduse_init(void)
+{
+	int ret;
+	struct device *dev;
+
+	vduse_class = class_create(THIS_MODULE, "vduse");
+	if (IS_ERR(vduse_class))
+		return PTR_ERR(vduse_class);
+
+	vduse_class->devnode = vduse_devnode;
+	vduse_class->dev_groups = vduse_dev_groups;
+
+	ret = alloc_chrdev_region(&vduse_major, 0, VDUSE_DEV_MAX, "vduse");
+	if (ret)
+		goto err_chardev_region;
+
+	/* /dev/vduse/control */
+	cdev_init(&vduse_ctrl_cdev, &vduse_ctrl_fops);
+	vduse_ctrl_cdev.owner = THIS_MODULE;
+	ret = cdev_add(&vduse_ctrl_cdev, vduse_major, 1);
+	if (ret)
+		goto err_ctrl_cdev;
+
+	dev = device_create(vduse_class, NULL, vduse_major, NULL, "control");
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		goto err_device;
+	}
+
+	/* /dev/vduse/$DEVICE */
+	cdev_init(&vduse_cdev, &vduse_dev_fops);
+	vduse_cdev.owner = THIS_MODULE;
+	ret = cdev_add(&vduse_cdev, MKDEV(MAJOR(vduse_major), 1),
+		       VDUSE_DEV_MAX - 1);
+	if (ret)
+		goto err_cdev;
+
+	vduse_irq_wq = alloc_workqueue("vduse-irq",
+				WQ_HIGHPRI | WQ_SYSFS | WQ_UNBOUND, 0);
+	if (!vduse_irq_wq)
+		goto err_wq;
+
+	ret = vduse_domain_init();
+	if (ret)
+		goto err_domain;
+
+	ret = vduse_mgmtdev_init();
+	if (ret)
+		goto err_mgmtdev;
+
+	return 0;
+err_mgmtdev:
+	vduse_domain_exit();
+err_domain:
+	destroy_workqueue(vduse_irq_wq);
+err_wq:
+	cdev_del(&vduse_cdev);
+err_cdev:
+	device_destroy(vduse_class, vduse_major);
+err_device:
+	cdev_del(&vduse_ctrl_cdev);
+err_ctrl_cdev:
+	unregister_chrdev_region(vduse_major, VDUSE_DEV_MAX);
+err_chardev_region:
+	class_destroy(vduse_class);
+	return ret;
+}
+module_init(vduse_init);
+
+static void vduse_exit(void)
+{
+	vduse_mgmtdev_exit();
+	vduse_domain_exit();
+	destroy_workqueue(vduse_irq_wq);
+	cdev_del(&vduse_cdev);
+	device_destroy(vduse_class, vduse_major);
+	cdev_del(&vduse_ctrl_cdev);
+	unregister_chrdev_region(vduse_major, VDUSE_DEV_MAX);
+	class_destroy(vduse_class);
+}
+module_exit(vduse_exit);
+
+MODULE_LICENSE(DRV_LICENSE);
+MODULE_AUTHOR(DRV_AUTHOR);
+MODULE_DESCRIPTION(DRV_DESC);
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index fe05273..5bcd002 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -189,10 +189,20 @@
 	}
 
 	vp_modern_set_status(mdev, status);
+}
 
-	if (!(status & VIRTIO_CONFIG_S_DRIVER_OK) &&
-	    (s & VIRTIO_CONFIG_S_DRIVER_OK))
+static int vp_vdpa_reset(struct vdpa_device *vdpa)
+{
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
+	struct virtio_pci_modern_device *mdev = &vp_vdpa->mdev;
+	u8 s = vp_vdpa_get_status(vdpa);
+
+	vp_modern_set_status(mdev, 0);
+
+	if (s & VIRTIO_CONFIG_S_DRIVER_OK)
 		vp_vdpa_free_irq(vp_vdpa);
+
+	return 0;
 }
 
 static u16 vp_vdpa_get_vq_num_max(struct vdpa_device *vdpa)
@@ -398,6 +408,7 @@
 	.set_features	= vp_vdpa_set_features,
 	.get_status	= vp_vdpa_get_status,
 	.set_status	= vp_vdpa_set_status,
+	.reset		= vp_vdpa_reset,
 	.get_vq_num_max	= vp_vdpa_get_vq_num_max,
 	.get_vq_state	= vp_vdpa_get_vq_state,
 	.get_vq_notification = vp_vdpa_get_vq_notification,
@@ -435,7 +446,7 @@
 		return ret;
 
 	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
-				    dev, &vp_vdpa_ops, NULL);
+				    dev, &vp_vdpa_ops, NULL, false);
 	if (IS_ERR(vp_vdpa)) {
 		dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n");
 		return PTR_ERR(vp_vdpa);
diff --git a/drivers/vhost/iotlb.c b/drivers/vhost/iotlb.c
index 0582079..670d56c 100644
--- a/drivers/vhost/iotlb.c
+++ b/drivers/vhost/iotlb.c
@@ -36,19 +36,21 @@
 EXPORT_SYMBOL_GPL(vhost_iotlb_map_free);
 
 /**
- * vhost_iotlb_add_range - add a new range to vhost IOTLB
+ * vhost_iotlb_add_range_ctx - add a new range to vhost IOTLB
  * @iotlb: the IOTLB
  * @start: start of the IOVA range
  * @last: last of IOVA range
  * @addr: the address that is mapped to @start
  * @perm: access permission of this range
+ * @opaque: the opaque pointer for the new mapping
  *
  * Returns an error last is smaller than start or memory allocation
  * fails
  */
-int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
-			  u64 start, u64 last,
-			  u64 addr, unsigned int perm)
+int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb,
+			      u64 start, u64 last,
+			      u64 addr, unsigned int perm,
+			      void *opaque)
 {
 	struct vhost_iotlb_map *map;
 
@@ -71,6 +73,7 @@
 	map->last = last;
 	map->addr = addr;
 	map->perm = perm;
+	map->opaque = opaque;
 
 	iotlb->nmaps++;
 	vhost_iotlb_itree_insert(map, &iotlb->root);
@@ -80,6 +83,15 @@
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vhost_iotlb_add_range_ctx);
+
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
+			  u64 start, u64 last,
+			  u64 addr, unsigned int perm)
+{
+	return vhost_iotlb_add_range_ctx(iotlb, start, last,
+					 addr, perm, NULL);
+}
 EXPORT_SYMBOL_GPL(vhost_iotlb_add_range);
 
 /**
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 46f897e..532e204 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1,24 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*******************************************************************************
  * Vhost kernel TCM fabric driver for virtio SCSI initiators
  *
  * (C) Copyright 2010-2013 Datera, Inc.
  * (C) Copyright 2010-2012 IBM Corp.
  *
- * Licensed to the Linux Foundation under the General Public License (GPL) version 2.
- *
  * Authors: Nicholas A. Bellinger <nab@daterainc.com>
  *          Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
  ****************************************************************************/
 
 #include <linux/module.h>
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 9479f7f..f41d081 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -116,12 +116,13 @@
 	irq_bypass_unregister_producer(&vq->call_ctx.producer);
 }
 
-static void vhost_vdpa_reset(struct vhost_vdpa *v)
+static int vhost_vdpa_reset(struct vhost_vdpa *v)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 
-	vdpa_reset(vdpa);
 	v->in_batch = 0;
+
+	return vdpa_reset(vdpa);
 }
 
 static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp)
@@ -157,7 +158,7 @@
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	u8 status, status_old;
-	int nvqs = v->nvqs;
+	int ret, nvqs = v->nvqs;
 	u16 i;
 
 	if (copy_from_user(&status, statusp, sizeof(status)))
@@ -172,7 +173,12 @@
 	if (status != 0 && (ops->get_status(vdpa) & ~status) != 0)
 		return -EINVAL;
 
-	ops->set_status(vdpa, status);
+	if (status == 0) {
+		ret = ops->reset(vdpa);
+		if (ret)
+			return ret;
+	} else
+		ops->set_status(vdpa, status);
 
 	if ((status & VIRTIO_CONFIG_S_DRIVER_OK) && !(status_old & VIRTIO_CONFIG_S_DRIVER_OK))
 		for (i = 0; i < nvqs; i++)
@@ -498,7 +504,7 @@
 	return r;
 }
 
-static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vhost_iotlb *iotlb = dev->iotlb;
@@ -507,19 +513,44 @@
 	unsigned long pfn, pinned;
 
 	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
-		pinned = map->size >> PAGE_SHIFT;
-		for (pfn = map->addr >> PAGE_SHIFT;
+		pinned = PFN_DOWN(map->size);
+		for (pfn = PFN_DOWN(map->addr);
 		     pinned > 0; pfn++, pinned--) {
 			page = pfn_to_page(pfn);
 			if (map->perm & VHOST_ACCESS_WO)
 				set_page_dirty_lock(page);
 			unpin_user_page(page);
 		}
-		atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm);
+		atomic64_sub(PFN_DOWN(map->size), &dev->mm->pinned_vm);
 		vhost_iotlb_map_free(iotlb, map);
 	}
 }
 
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+	struct vhost_iotlb_map *map;
+	struct vdpa_map_file *map_file;
+
+	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
+		map_file = (struct vdpa_map_file *)map->opaque;
+		fput(map_file->file);
+		kfree(map_file);
+		vhost_iotlb_map_free(iotlb, map);
+	}
+}
+
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+
+	if (vdpa->use_va)
+		return vhost_vdpa_va_unmap(v, start, last);
+
+	return vhost_vdpa_pa_unmap(v, start, last);
+}
+
 static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v)
 {
 	struct vhost_dev *dev = &v->vdev;
@@ -551,21 +582,21 @@
 	return flags | IOMMU_CACHE;
 }
 
-static int vhost_vdpa_map(struct vhost_vdpa *v,
-			  u64 iova, u64 size, u64 pa, u32 perm)
+static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova,
+			  u64 size, u64 pa, u32 perm, void *opaque)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
 	int r = 0;
 
-	r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1,
-				  pa, perm);
+	r = vhost_iotlb_add_range_ctx(dev->iotlb, iova, iova + size - 1,
+				      pa, perm, opaque);
 	if (r)
 		return r;
 
 	if (ops->dma_map) {
-		r = ops->dma_map(vdpa, iova, size, pa, perm);
+		r = ops->dma_map(vdpa, iova, size, pa, perm, opaque);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
 			r = ops->set_map(vdpa, dev->iotlb);
@@ -573,13 +604,15 @@
 		r = iommu_map(v->domain, iova, pa, size,
 			      perm_to_iommu_flags(perm));
 	}
-
-	if (r)
+	if (r) {
 		vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
-	else
-		atomic64_add(size >> PAGE_SHIFT, &dev->mm->pinned_vm);
+		return r;
+	}
 
-	return r;
+	if (!vdpa->use_va)
+		atomic64_add(PFN_DOWN(size), &dev->mm->pinned_vm);
+
+	return 0;
 }
 
 static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
@@ -600,38 +633,78 @@
 	}
 }
 
-static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
-					   struct vhost_iotlb_msg *msg)
+static int vhost_vdpa_va_map(struct vhost_vdpa *v,
+			     u64 iova, u64 size, u64 uaddr, u32 perm)
 {
 	struct vhost_dev *dev = &v->vdev;
-	struct vhost_iotlb *iotlb = dev->iotlb;
+	u64 offset, map_size, map_iova = iova;
+	struct vdpa_map_file *map_file;
+	struct vm_area_struct *vma;
+	int ret;
+
+	mmap_read_lock(dev->mm);
+
+	while (size) {
+		vma = find_vma(dev->mm, uaddr);
+		if (!vma) {
+			ret = -EINVAL;
+			break;
+		}
+		map_size = min(size, vma->vm_end - uaddr);
+		if (!(vma->vm_file && (vma->vm_flags & VM_SHARED) &&
+			!(vma->vm_flags & (VM_IO | VM_PFNMAP))))
+			goto next;
+
+		map_file = kzalloc(sizeof(*map_file), GFP_KERNEL);
+		if (!map_file) {
+			ret = -ENOMEM;
+			break;
+		}
+		offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start;
+		map_file->offset = offset;
+		map_file->file = get_file(vma->vm_file);
+		ret = vhost_vdpa_map(v, map_iova, map_size, uaddr,
+				     perm, map_file);
+		if (ret) {
+			fput(map_file->file);
+			kfree(map_file);
+			break;
+		}
+next:
+		size -= map_size;
+		uaddr += map_size;
+		map_iova += map_size;
+	}
+	if (ret)
+		vhost_vdpa_unmap(v, iova, map_iova - iova);
+
+	mmap_read_unlock(dev->mm);
+
+	return ret;
+}
+
+static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
+			     u64 iova, u64 size, u64 uaddr, u32 perm)
+{
+	struct vhost_dev *dev = &v->vdev;
 	struct page **page_list;
 	unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
 	unsigned int gup_flags = FOLL_LONGTERM;
 	unsigned long npages, cur_base, map_pfn, last_pfn = 0;
 	unsigned long lock_limit, sz2pin, nchunks, i;
-	u64 iova = msg->iova;
+	u64 start = iova;
 	long pinned;
 	int ret = 0;
 
-	if (msg->iova < v->range.first || !msg->size ||
-	    msg->iova > U64_MAX - msg->size + 1 ||
-	    msg->iova + msg->size - 1 > v->range.last)
-		return -EINVAL;
-
-	if (vhost_iotlb_itree_first(iotlb, msg->iova,
-				    msg->iova + msg->size - 1))
-		return -EEXIST;
-
 	/* Limit the use of memory for bookkeeping */
 	page_list = (struct page **) __get_free_page(GFP_KERNEL);
 	if (!page_list)
 		return -ENOMEM;
 
-	if (msg->perm & VHOST_ACCESS_WO)
+	if (perm & VHOST_ACCESS_WO)
 		gup_flags |= FOLL_WRITE;
 
-	npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT;
+	npages = PFN_UP(size + (iova & ~PAGE_MASK));
 	if (!npages) {
 		ret = -EINVAL;
 		goto free;
@@ -639,13 +712,13 @@
 
 	mmap_read_lock(dev->mm);
 
-	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	lock_limit = PFN_DOWN(rlimit(RLIMIT_MEMLOCK));
 	if (npages + atomic64_read(&dev->mm->pinned_vm) > lock_limit) {
 		ret = -ENOMEM;
 		goto unlock;
 	}
 
-	cur_base = msg->uaddr & PAGE_MASK;
+	cur_base = uaddr & PAGE_MASK;
 	iova &= PAGE_MASK;
 	nchunks = 0;
 
@@ -673,10 +746,10 @@
 
 			if (last_pfn && (this_pfn != last_pfn + 1)) {
 				/* Pin a contiguous chunk of memory */
-				csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
+				csize = PFN_PHYS(last_pfn - map_pfn + 1);
 				ret = vhost_vdpa_map(v, iova, csize,
-						     map_pfn << PAGE_SHIFT,
-						     msg->perm);
+						     PFN_PHYS(map_pfn),
+						     perm, NULL);
 				if (ret) {
 					/*
 					 * Unpin the pages that are left unmapped
@@ -699,13 +772,13 @@
 			last_pfn = this_pfn;
 		}
 
-		cur_base += pinned << PAGE_SHIFT;
+		cur_base += PFN_PHYS(pinned);
 		npages -= pinned;
 	}
 
 	/* Pin the rest chunk */
-	ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
-			     map_pfn << PAGE_SHIFT, msg->perm);
+	ret = vhost_vdpa_map(v, iova, PFN_PHYS(last_pfn - map_pfn + 1),
+			     PFN_PHYS(map_pfn), perm, NULL);
 out:
 	if (ret) {
 		if (nchunks) {
@@ -724,13 +797,38 @@
 			for (pfn = map_pfn; pfn <= last_pfn; pfn++)
 				unpin_user_page(pfn_to_page(pfn));
 		}
-		vhost_vdpa_unmap(v, msg->iova, msg->size);
+		vhost_vdpa_unmap(v, start, size);
 	}
 unlock:
 	mmap_read_unlock(dev->mm);
 free:
 	free_page((unsigned long)page_list);
 	return ret;
+
+}
+
+static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
+					   struct vhost_iotlb_msg *msg)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+
+	if (msg->iova < v->range.first || !msg->size ||
+	    msg->iova > U64_MAX - msg->size + 1 ||
+	    msg->iova + msg->size - 1 > v->range.last)
+		return -EINVAL;
+
+	if (vhost_iotlb_itree_first(iotlb, msg->iova,
+				    msg->iova + msg->size - 1))
+		return -EEXIST;
+
+	if (vdpa->use_va)
+		return vhost_vdpa_va_map(v, msg->iova, msg->size,
+					 msg->uaddr, msg->perm);
+
+	return vhost_vdpa_pa_map(v, msg->iova, msg->size, msg->uaddr,
+				 msg->perm);
 }
 
 static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
@@ -860,7 +958,9 @@
 		return -EBUSY;
 
 	nvqs = v->nvqs;
-	vhost_vdpa_reset(v);
+	r = vhost_vdpa_reset(v);
+	if (r)
+		goto err;
 
 	vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL);
 	if (!vqs) {
@@ -945,7 +1045,7 @@
 
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 	if (remap_pfn_range(vma, vmf->address & PAGE_MASK,
-			    notify.addr >> PAGE_SHIFT, PAGE_SIZE,
+			    PFN_DOWN(notify.addr), PAGE_SIZE,
 			    vma->vm_page_prot))
 		return VM_FAULT_SIGBUS;
 
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index f249622..938aefb 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -114,7 +114,7 @@
 		size_t nbytes;
 		size_t iov_len, payload_len;
 		int head;
-		bool restore_flag = false;
+		u32 flags_to_restore = 0;
 
 		spin_lock_bh(&vsock->send_pkt_list_lock);
 		if (list_empty(&vsock->send_pkt_list)) {
@@ -178,16 +178,21 @@
 			 * small rx buffers, headers of packets in rx queue are
 			 * created dynamically and are initialized with header
 			 * of current packet(except length). But in case of
-			 * SOCK_SEQPACKET, we also must clear record delimeter
-			 * bit(VIRTIO_VSOCK_SEQ_EOR). Otherwise, instead of one
-			 * packet with delimeter(which marks end of record),
-			 * there will be sequence of packets with delimeter
-			 * bit set. After initialized header will be copied to
-			 * rx buffer, this bit will be restored.
+			 * SOCK_SEQPACKET, we also must clear message delimeter
+			 * bit (VIRTIO_VSOCK_SEQ_EOM) and MSG_EOR bit
+			 * (VIRTIO_VSOCK_SEQ_EOR) if set. Otherwise,
+			 * there will be sequence of packets with these
+			 * bits set. After initialized header will be copied to
+			 * rx buffer, these required bits will be restored.
 			 */
-			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
-				pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
-				restore_flag = true;
+			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) {
+				pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
+				flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM;
+
+				if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
+					pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+					flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR;
+				}
 			}
 		}
 
@@ -224,8 +229,7 @@
 		 * to send it with the next available buffer.
 		 */
 		if (pkt->off < pkt->len) {
-			if (restore_flag)
-				pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+			pkt->hdr.flags |= cpu_to_le32(flags_to_restore);
 
 			/* We are queueing the same virtio_vsock_pkt to handle
 			 * the remaining bytes, and we want to deliver it
diff --git a/drivers/video/fbdev/core/fbmem.c b/drivers/video/fbdev/core/fbmem.c
index 71fb710..7420d2c 100644
--- a/drivers/video/fbdev/core/fbmem.c
+++ b/drivers/video/fbdev/core/fbmem.c
@@ -962,6 +962,7 @@
 	struct fb_var_screeninfo old_var;
 	struct fb_videomode mode;
 	struct fb_event event;
+	u32 unused;
 
 	if (var->activate & FB_ACTIVATE_INV_MODE) {
 		struct fb_videomode mode1, mode2;
@@ -1008,6 +1009,11 @@
 	if (var->xres < 8 || var->yres < 8)
 		return -EINVAL;
 
+	/* Too huge resolution causes multiplication overflow. */
+	if (check_mul_overflow(var->xres, var->yres, &unused) ||
+	    check_mul_overflow(var->xres_virtual, var->yres_virtual, &unused))
+		return -EINVAL;
+
 	ret = info->fbops->fb_check_var(var, info);
 
 	if (ret)
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 1ea0c1f..588e02f 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -4,6 +4,7 @@
 #include <linux/virtio_config.h>
 #include <linux/module.h>
 #include <linux/idr.h>
+#include <linux/of.h>
 #include <uapi/linux/virtio_ids.h>
 
 /* Unique numbering for virtio devices. */
@@ -292,6 +293,8 @@
 
 	/* Acknowledge the device's existence again. */
 	virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+
+	of_node_put(dev->dev.of_node);
 }
 
 static struct bus_type virtio_bus = {
@@ -318,6 +321,43 @@
 }
 EXPORT_SYMBOL_GPL(unregister_virtio_driver);
 
+static int virtio_device_of_init(struct virtio_device *dev)
+{
+	struct device_node *np, *pnode = dev_of_node(dev->dev.parent);
+	char compat[] = "virtio,deviceXXXXXXXX";
+	int ret, count;
+
+	if (!pnode)
+		return 0;
+
+	count = of_get_available_child_count(pnode);
+	if (!count)
+		return 0;
+
+	/* There can be only 1 child node */
+	if (WARN_ON(count > 1))
+		return -EINVAL;
+
+	np = of_get_next_available_child(pnode, NULL);
+	if (WARN_ON(!np))
+		return -ENODEV;
+
+	ret = snprintf(compat, sizeof(compat), "virtio,device%x", dev->id.device);
+	BUG_ON(ret >= sizeof(compat));
+
+	if (!of_device_is_compatible(np, compat)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	dev->dev.of_node = np;
+	return 0;
+
+out:
+	of_node_put(np);
+	return ret;
+}
+
 /**
  * register_virtio_device - register virtio device
  * @dev        : virtio device to be registered
@@ -342,6 +382,10 @@
 	dev->index = err;
 	dev_set_name(&dev->dev, "virtio%u", dev->index);
 
+	err = virtio_device_of_init(dev);
+	if (err)
+		goto out_ida_remove;
+
 	spin_lock_init(&dev->config_lock);
 	dev->config_enabled = false;
 	dev->config_change_pending = false;
@@ -362,10 +406,16 @@
 	 */
 	err = device_add(&dev->dev);
 	if (err)
-		ida_simple_remove(&virtio_index_ida, dev->index);
+		goto out_of_node_put;
+
+	return 0;
+
+out_of_node_put:
+	of_node_put(dev->dev.of_node);
+out_ida_remove:
+	ida_simple_remove(&virtio_index_ida, dev->index);
 out:
-	if (err)
-		virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
+	virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
 	return err;
 }
 EXPORT_SYMBOL_GPL(register_virtio_device);
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 47dce91f..c22ff01 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -531,8 +531,8 @@
 		callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack;
 	}
 
-	err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
-					 vqs, callbacks, names, NULL, NULL);
+	err = virtio_find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX, vqs,
+			      callbacks, names, NULL);
 	if (err)
 		return err;
 
diff --git a/fs/Kconfig b/fs/Kconfig
index 47af46a..a6313a9 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -367,7 +367,7 @@
 source "fs/cifs/Kconfig"
 source "fs/ksmbd/Kconfig"
 
-config CIFS_COMMON
+config SMBFS_COMMON
 	tristate
 	default y if CIFS=y
 	default m if CIFS=m
diff --git a/fs/Makefile b/fs/Makefile
index 2f21300..84c5e4c 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -17,7 +17,7 @@
 		kernel_read_file.o remap_range.o
 
 ifeq ($(CONFIG_BLOCK),y)
-obj-y +=	buffer.o block_dev.o direct-io.o mpage.o
+obj-y +=	buffer.o direct-io.o mpage.o
 else
 obj-y +=	no-block.o
 endif
@@ -96,7 +96,7 @@
 obj-$(CONFIG_NLS)		+= nls/
 obj-$(CONFIG_UNICODE)		+= unicode/
 obj-$(CONFIG_SYSV_FS)		+= sysv/
-obj-$(CONFIG_CIFS_COMMON)	+= cifs_common/
+obj-$(CONFIG_SMBFS_COMMON)	+= smbfs_common/
 obj-$(CONFIG_CIFS)		+= cifs/
 obj-$(CONFIG_SMB_SERVER)	+= ksmbd/
 obj-$(CONFIG_HPFS_FS)		+= hpfs/
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 6679e07..2e6f403 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -22,7 +22,7 @@
 #include <linux/random.h>
 #include <linux/highmem.h>
 #include <linux/fips.h>
-#include "../cifs_common/arc4.h"
+#include "../smbfs_common/arc4.h"
 #include <crypto/aead.h>
 
 int __cifs_calc_signature(struct smb_rqst *rqst,
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index dc920e2..98e8e5a 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -12,7 +12,7 @@
 
 #include <net/sock.h>
 #include <asm/unaligned.h>
-#include "smbfsctl.h"
+#include "../smbfs_common/smbfsctl.h"
 
 #define CIFS_PROT   0
 #define POSIX_PROT  (CIFS_PROT+1)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index ddc0e8f..bda606d 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -689,13 +689,19 @@
 		cifs_dbg(FYI, "clear cached root file handle\n");
 		SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid,
 			   cfid->fid->volatile_fid);
-		cfid->is_valid = false;
-		cfid->file_all_info_is_valid = false;
-		cfid->has_lease = false;
-		if (cfid->dentry) {
-			dput(cfid->dentry);
-			cfid->dentry = NULL;
-		}
+	}
+
+	/*
+	 * We only check validity above to send SMB2_close,
+	 * but we still need to invalidate these entries
+	 * when this function is called
+	 */
+	cfid->is_valid = false;
+	cfid->file_all_info_is_valid = false;
+	cfid->has_lease = false;
+	if (cfid->dentry) {
+		dput(cfid->dentry);
+		cfid->dentry = NULL;
 	}
 }
 
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 10047cc..4a04877 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -24,7 +24,7 @@
 #include "cifsglob.h"
 #include "cifs_debug.h"
 #include "cifsproto.h"
-#include "../cifs_common/md4.h"
+#include "../smbfs_common/md4.h"
 
 #ifndef false
 #define false 0
diff --git a/fs/file.c b/fs/file.c
index d8afa82..8627dac 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -1150,6 +1150,12 @@
 	return new_fd;
 }
 
+int receive_fd(struct file *file, unsigned int o_flags)
+{
+	return __receive_fd(file, NULL, o_flags);
+}
+EXPORT_SYMBOL_GPL(receive_fd);
+
 static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
 	int err = -EBADF;
diff --git a/fs/fs_parser.c b/fs/fs_parser.c
index 980d44fd..3df07c0 100644
--- a/fs/fs_parser.c
+++ b/fs/fs_parser.c
@@ -165,7 +165,6 @@
 		return invalf(fc, "%s: not usable as path", param->key);
 	}
 
-	f->refcnt++; /* filename_lookup() drops our ref. */
 	ret = filename_lookup(param->dirfd, f, flags, _path, NULL);
 	if (ret < 0) {
 		errorf(fc, "%s: Lookup failure for '%s'", param->key, f->name);
diff --git a/fs/internal.h b/fs/internal.h
index 68a2ae0..3cd065c 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -18,7 +18,7 @@
 struct pipe_inode_info;
 
 /*
- * block_dev.c
+ * block/bdev.c
  */
 #ifdef CONFIG_BLOCK
 extern void __init bdev_cache_init(void);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index d80e4a7..6c55362 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -709,6 +709,7 @@
 		}
 		raw_spin_unlock(&wqe->lock);
 		io_worker_ref_put(wqe->wq);
+		kfree(worker);
 		return;
 	}
 
@@ -725,6 +726,7 @@
 	if (!io_queue_worker_create(worker, acct, create_worker_cont)) {
 		clear_bit_unlock(0, &worker->create_state);
 		io_worker_release(worker);
+		kfree(worker);
 	}
 }
 
@@ -759,6 +761,7 @@
 	if (!IS_ERR(tsk)) {
 		io_init_new_worker(wqe, worker, tsk);
 	} else if (!io_should_retry_thread(PTR_ERR(tsk))) {
+		kfree(worker);
 		goto fail;
 	} else {
 		INIT_WORK(&worker->work, io_workqueue_create);
@@ -832,6 +835,11 @@
 	wq_list_add_after(&work->list, &tail->list, &acct->work_list);
 }
 
+static bool io_wq_work_match_item(struct io_wq_work *work, void *data)
+{
+	return work == data;
+}
+
 static void io_wqe_enqueue(struct io_wqe *wqe, struct io_wq_work *work)
 {
 	struct io_wqe_acct *acct = io_work_get_acct(wqe, work);
@@ -844,7 +852,6 @@
 	 */
 	if (test_bit(IO_WQ_BIT_EXIT, &wqe->wq->state) ||
 	    (work->flags & IO_WQ_WORK_CANCEL)) {
-run_cancel:
 		io_run_cancel(work, wqe);
 		return;
 	}
@@ -864,15 +871,22 @@
 		bool did_create;
 
 		did_create = io_wqe_create_worker(wqe, acct);
-		if (unlikely(!did_create)) {
-			raw_spin_lock(&wqe->lock);
-			/* fatal condition, failed to create the first worker */
-			if (!acct->nr_workers) {
-				raw_spin_unlock(&wqe->lock);
-				goto run_cancel;
-			}
-			raw_spin_unlock(&wqe->lock);
+		if (likely(did_create))
+			return;
+
+		raw_spin_lock(&wqe->lock);
+		/* fatal condition, failed to create the first worker */
+		if (!acct->nr_workers) {
+			struct io_cb_cancel_data match = {
+				.fn		= io_wq_work_match_item,
+				.data		= work,
+				.cancel_all	= false,
+			};
+
+			if (io_acct_cancel_pending_work(wqe, acct, &match))
+				raw_spin_lock(&wqe->lock);
 		}
+		raw_spin_unlock(&wqe->lock);
 	}
 }
 
@@ -1122,7 +1136,7 @@
 {
 	struct io_worker *worker;
 
-	if (cb->func != create_worker_cb || cb->func != create_worker_cont)
+	if (cb->func != create_worker_cb && cb->func != create_worker_cont)
 		return false;
 	worker = container_of(cb, struct io_worker, create_work);
 	return worker->wqe->wq == data;
@@ -1143,9 +1157,14 @@
 
 	while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) {
 		struct io_worker *worker;
+		struct io_wqe_acct *acct;
 
 		worker = container_of(cb, struct io_worker, create_work);
-		atomic_dec(&worker->wqe->acct[worker->create_index].nr_running);
+		acct = io_wqe_get_acct(worker);
+		atomic_dec(&acct->nr_running);
+		raw_spin_lock(&worker->wqe->lock);
+		acct->nr_workers--;
+		raw_spin_unlock(&worker->wqe->lock);
 		io_worker_ref_put(wq);
 		clear_bit_unlock(0, &worker->create_state);
 		io_worker_release(worker);
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 855ea54..16fb743 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1482,6 +1482,8 @@
 	struct io_timeout_data *io = req->async_data;
 
 	if (hrtimer_try_to_cancel(&io->timer) != -1) {
+		if (status)
+			req_set_fail(req);
 		atomic_set(&req->ctx->cq_timeouts,
 			atomic_read(&req->ctx->cq_timeouts) + 1);
 		list_del_init(&req->timeout.list);
@@ -1619,8 +1621,11 @@
 
 static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx)
 {
+	/* see waitqueue_active() comment */
+	smp_mb();
+
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
-		if (wq_has_sleeper(&ctx->cq_wait))
+		if (waitqueue_active(&ctx->cq_wait))
 			wake_up_all(&ctx->cq_wait);
 	}
 	if (io_should_trigger_evfd(ctx))
@@ -10550,7 +10555,14 @@
 	if (ctx->flags & IORING_SETUP_SQPOLL) {
 		sqd = ctx->sq_data;
 		if (sqd) {
+			/*
+			 * Observe the correct sqd->lock -> ctx->uring_lock
+			 * ordering. Fine to drop uring_lock here, we hold
+			 * a ref to the ctx.
+			 */
+			mutex_unlock(&ctx->uring_lock);
 			mutex_lock(&sqd->lock);
+			mutex_lock(&ctx->uring_lock);
 			tctx = sqd->thread->io_uring;
 		}
 	} else {
@@ -10853,7 +10865,7 @@
 	BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8));
 
 	BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST);
-	BUILD_BUG_ON(__REQ_F_LAST_BIT >= 8 * sizeof(int));
+	BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int));
 
 	req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC |
 				SLAB_ACCOUNT);
diff --git a/fs/namei.c b/fs/namei.c
index 95a881e..1946d96 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -255,7 +255,7 @@
 
 void putname(struct filename *name)
 {
-	if (IS_ERR_OR_NULL(name))
+	if (IS_ERR(name))
 		return;
 
 	BUG_ON(name->refcnt <= 0);
@@ -2467,7 +2467,7 @@
 	return err;
 }
 
-static int __filename_lookup(int dfd, struct filename *name, unsigned flags,
+int filename_lookup(int dfd, struct filename *name, unsigned flags,
 		    struct path *path, struct path *root)
 {
 	int retval;
@@ -2488,15 +2488,6 @@
 	return retval;
 }
 
-int filename_lookup(int dfd, struct filename *name, unsigned flags,
-		    struct path *path, struct path *root)
-{
-	int retval = __filename_lookup(dfd, name, flags, path, root);
-
-	putname(name);
-	return retval;
-}
-
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
 static int path_parentat(struct nameidata *nd, unsigned flags,
 				struct path *parent)
@@ -2514,9 +2505,10 @@
 	return err;
 }
 
-static int __filename_parentat(int dfd, struct filename *name,
-				unsigned int flags, struct path *parent,
-				struct qstr *last, int *type)
+/* Note: this does not consume "name" */
+static int filename_parentat(int dfd, struct filename *name,
+			     unsigned int flags, struct path *parent,
+			     struct qstr *last, int *type)
 {
 	int retval;
 	struct nameidata nd;
@@ -2538,25 +2530,14 @@
 	return retval;
 }
 
-static int filename_parentat(int dfd, struct filename *name,
-				unsigned int flags, struct path *parent,
-				struct qstr *last, int *type)
-{
-	int retval = __filename_parentat(dfd, name, flags, parent, last, type);
-
-	putname(name);
-	return retval;
-}
-
 /* does lookup, returns the object with parent locked */
-struct dentry *kern_path_locked(const char *name, struct path *path)
+static struct dentry *__kern_path_locked(struct filename *name, struct path *path)
 {
 	struct dentry *d;
 	struct qstr last;
 	int type, error;
 
-	error = filename_parentat(AT_FDCWD, getname_kernel(name), 0, path,
-				    &last, &type);
+	error = filename_parentat(AT_FDCWD, name, 0, path, &last, &type);
 	if (error)
 		return ERR_PTR(error);
 	if (unlikely(type != LAST_NORM)) {
@@ -2572,10 +2553,23 @@
 	return d;
 }
 
+struct dentry *kern_path_locked(const char *name, struct path *path)
+{
+	struct filename *filename = getname_kernel(name);
+	struct dentry *res = __kern_path_locked(filename, path);
+
+	putname(filename);
+	return res;
+}
+
 int kern_path(const char *name, unsigned int flags, struct path *path)
 {
-	return filename_lookup(AT_FDCWD, getname_kernel(name),
-			       flags, path, NULL);
+	struct filename *filename = getname_kernel(name);
+	int ret = filename_lookup(AT_FDCWD, filename, flags, path, NULL);
+
+	putname(filename);
+	return ret;
+
 }
 EXPORT_SYMBOL(kern_path);
 
@@ -2591,10 +2585,15 @@
 		    const char *name, unsigned int flags,
 		    struct path *path)
 {
+	struct filename *filename;
 	struct path root = {.mnt = mnt, .dentry = dentry};
+	int ret;
+
+	filename = getname_kernel(name);
 	/* the first argument of filename_lookup() is ignored with root */
-	return filename_lookup(AT_FDCWD, getname_kernel(name),
-			       flags , path, &root);
+	ret = filename_lookup(AT_FDCWD, filename, flags, path, &root);
+	putname(filename);
+	return ret;
 }
 EXPORT_SYMBOL(vfs_path_lookup);
 
@@ -2798,8 +2797,11 @@
 int user_path_at_empty(int dfd, const char __user *name, unsigned flags,
 		 struct path *path, int *empty)
 {
-	return filename_lookup(dfd, getname_flags(name, flags, empty),
-			       flags, path, NULL);
+	struct filename *filename = getname_flags(name, flags, empty);
+	int ret = filename_lookup(dfd, filename, flags, path, NULL);
+
+	putname(filename);
+	return ret;
 }
 EXPORT_SYMBOL(user_path_at_empty);
 
@@ -3618,8 +3620,8 @@
 	return file;
 }
 
-static struct dentry *__filename_create(int dfd, struct filename *name,
-				struct path *path, unsigned int lookup_flags)
+static struct dentry *filename_create(int dfd, struct filename *name,
+				      struct path *path, unsigned int lookup_flags)
 {
 	struct dentry *dentry = ERR_PTR(-EEXIST);
 	struct qstr last;
@@ -3634,7 +3636,7 @@
 	 */
 	lookup_flags &= LOOKUP_REVAL;
 
-	error = __filename_parentat(dfd, name, lookup_flags, path, &last, &type);
+	error = filename_parentat(dfd, name, lookup_flags, path, &last, &type);
 	if (error)
 		return ERR_PTR(error);
 
@@ -3687,20 +3689,14 @@
 	return dentry;
 }
 
-static inline struct dentry *filename_create(int dfd, struct filename *name,
-				struct path *path, unsigned int lookup_flags)
-{
-	struct dentry *res = __filename_create(dfd, name, path, lookup_flags);
-
-	putname(name);
-	return res;
-}
-
 struct dentry *kern_path_create(int dfd, const char *pathname,
 				struct path *path, unsigned int lookup_flags)
 {
-	return filename_create(dfd, getname_kernel(pathname),
-				path, lookup_flags);
+	struct filename *filename = getname_kernel(pathname);
+	struct dentry *res = filename_create(dfd, filename, path, lookup_flags);
+
+	putname(filename);
+	return res;
 }
 EXPORT_SYMBOL(kern_path_create);
 
@@ -3716,7 +3712,11 @@
 inline struct dentry *user_path_create(int dfd, const char __user *pathname,
 				struct path *path, unsigned int lookup_flags)
 {
-	return filename_create(dfd, getname(pathname), path, lookup_flags);
+	struct filename *filename = getname(pathname);
+	struct dentry *res = filename_create(dfd, filename, path, lookup_flags);
+
+	putname(filename);
+	return res;
 }
 EXPORT_SYMBOL(user_path_create);
 
@@ -3797,7 +3797,7 @@
 	if (error)
 		goto out1;
 retry:
-	dentry = __filename_create(dfd, name, &path, lookup_flags);
+	dentry = filename_create(dfd, name, &path, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out1;
@@ -3897,7 +3897,7 @@
 	unsigned int lookup_flags = LOOKUP_DIRECTORY;
 
 retry:
-	dentry = __filename_create(dfd, name, &path, lookup_flags);
+	dentry = filename_create(dfd, name, &path, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out_putname;
@@ -3996,7 +3996,7 @@
 	int type;
 	unsigned int lookup_flags = 0;
 retry:
-	error = __filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
+	error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
 	if (error)
 		goto exit1;
 
@@ -4137,7 +4137,7 @@
 	struct inode *delegated_inode = NULL;
 	unsigned int lookup_flags = 0;
 retry:
-	error = __filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
+	error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
 	if (error)
 		goto exit1;
 
@@ -4266,7 +4266,7 @@
 		goto out_putnames;
 	}
 retry:
-	dentry = __filename_create(newdfd, to, &path, lookup_flags);
+	dentry = filename_create(newdfd, to, &path, lookup_flags);
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto out_putnames;
@@ -4426,11 +4426,11 @@
 	if (flags & AT_SYMLINK_FOLLOW)
 		how |= LOOKUP_FOLLOW;
 retry:
-	error = __filename_lookup(olddfd, old, how, &old_path, NULL);
+	error = filename_lookup(olddfd, old, how, &old_path, NULL);
 	if (error)
 		goto out_putnames;
 
-	new_dentry = __filename_create(newdfd, new, &new_path,
+	new_dentry = filename_create(newdfd, new, &new_path,
 					(how & LOOKUP_REVAL));
 	error = PTR_ERR(new_dentry);
 	if (IS_ERR(new_dentry))
@@ -4689,13 +4689,13 @@
 		target_flags = 0;
 
 retry:
-	error = __filename_parentat(olddfd, from, lookup_flags, &old_path,
-					&old_last, &old_type);
+	error = filename_parentat(olddfd, from, lookup_flags, &old_path,
+				  &old_last, &old_type);
 	if (error)
 		goto put_names;
 
-	error = __filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last,
-				&new_type);
+	error = filename_parentat(newdfd, to, lookup_flags, &new_path, &new_last,
+				  &new_type);
 	if (error)
 		goto exit1;
 
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 95006d1..fa1d991 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -531,6 +531,7 @@
 		/* Someone else created list structure for us */
 		if (inode)
 			fsnotify_put_inode_ref(inode);
+		fsnotify_put_sb_connectors(conn);
 		kmem_cache_free(fsnotify_mark_connector_cachep, conn);
 	}
 
diff --git a/fs/cifs_common/Makefile b/fs/smbfs_common/Makefile
similarity index 60%
rename from fs/cifs_common/Makefile
rename to fs/smbfs_common/Makefile
index 6fedd2f..cafc61a 100644
--- a/fs/cifs_common/Makefile
+++ b/fs/smbfs_common/Makefile
@@ -3,5 +3,5 @@
 # Makefile for Linux filesystem routines that are shared by client and server.
 #
 
-obj-$(CONFIG_CIFS_COMMON) += cifs_arc4.o
-obj-$(CONFIG_CIFS_COMMON) += cifs_md4.o
+obj-$(CONFIG_SMBFS_COMMON) += cifs_arc4.o
+obj-$(CONFIG_SMBFS_COMMON) += cifs_md4.o
diff --git a/fs/cifs_common/arc4.h b/fs/smbfs_common/arc4.h
similarity index 100%
rename from fs/cifs_common/arc4.h
rename to fs/smbfs_common/arc4.h
diff --git a/fs/cifs_common/cifs_arc4.c b/fs/smbfs_common/cifs_arc4.c
similarity index 91%
rename from fs/cifs_common/cifs_arc4.c
rename to fs/smbfs_common/cifs_arc4.c
index b964cc6..85ba15a 100644
--- a/fs/cifs_common/cifs_arc4.c
+++ b/fs/smbfs_common/cifs_arc4.c
@@ -74,14 +74,14 @@
 EXPORT_SYMBOL_GPL(cifs_arc4_crypt);
 
 static int __init
-init_cifs_common(void)
+init_smbfs_common(void)
 {
 	return 0;
 }
 static void __init
-exit_cifs_common(void)
+exit_smbfs_common(void)
 {
 }
 
-module_init(init_cifs_common)
-module_exit(exit_cifs_common)
+module_init(init_smbfs_common)
+module_exit(exit_smbfs_common)
diff --git a/fs/cifs_common/cifs_md4.c b/fs/smbfs_common/cifs_md4.c
similarity index 100%
rename from fs/cifs_common/cifs_md4.c
rename to fs/smbfs_common/cifs_md4.c
diff --git a/fs/cifs_common/md4.h b/fs/smbfs_common/md4.h
similarity index 100%
rename from fs/cifs_common/md4.h
rename to fs/smbfs_common/md4.h
diff --git a/fs/cifs/smbfsctl.h b/fs/smbfs_common/smbfsctl.h
similarity index 92%
rename from fs/cifs/smbfsctl.h
rename to fs/smbfs_common/smbfsctl.h
index d0fc420..d01e8c9 100644
--- a/fs/cifs/smbfsctl.h
+++ b/fs/smbfs_common/smbfsctl.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: LGPL-2.1 */
+/* SPDX-License-Identifier: LGPL-2.1+ */
 /*
  *   fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions
  *
@@ -19,11 +19,14 @@
  * could be invoked from tools via a specialized hook into the VFS rather
  * than via the standard vfs entry points
  *
- * See MS-SMB2 Section 2.2.31 (last checked June 2013, all of that list are
+ * See MS-SMB2 Section 2.2.31 (last checked September 2021, all of that list are
  * below). Additional detail on less common ones can be found in MS-FSCC
  * section 2.3.
  */
 
+#ifndef __SMBFSCTL_H
+#define __SMBFSCTL_H
+
 /*
  * FSCTL values are 32 bits and are constructed as
  * <device 16bits> <access 2bits> <function 12bits> <method 2bits>
@@ -91,6 +94,7 @@
 #define FSCTL_SET_ZERO_ON_DEALLOC    0x00090194 /* BB add struct */
 #define FSCTL_SET_SHORT_NAME_BEHAVIOR 0x000901B4 /* BB add struct */
 #define FSCTL_GET_INTEGRITY_INFORMATION 0x0009027C
+#define FSCTL_GET_REFS_VOLUME_DATA   0x000902D8 /* See MS-FSCC 2.3.24 */
 #define FSCTL_GET_RETRIEVAL_POINTERS_AND_REFCOUNT 0x000903d3
 #define FSCTL_GET_RETRIEVAL_POINTER_COUNT 0x0009042b
 #define FSCTL_QUERY_ALLOCATED_RANGES 0x000940CF
@@ -146,7 +150,13 @@
 #define IO_REPARSE_TAG_LX_CHR	     0x80000025
 #define IO_REPARSE_TAG_LX_BLK	     0x80000026
 
+#define IO_REPARSE_TAG_LX_SYMLINK_LE	cpu_to_le32(0xA000001D)
+#define IO_REPARSE_TAG_AF_UNIX_LE	cpu_to_le32(0x80000023)
+#define IO_REPARSE_TAG_LX_FIFO_LE	cpu_to_le32(0x80000024)
+#define IO_REPARSE_TAG_LX_CHR_LE	cpu_to_le32(0x80000025)
+#define IO_REPARSE_TAG_LX_BLK_LE	cpu_to_le32(0x80000026)
+
 /* fsctl flags */
 /* If Flags is set to this value, the request is an FSCTL not ioctl request */
 #define SMB2_0_IOCTL_IS_FSCTL		0x00000001
-
+#endif /* __SMBFSCTL_H */
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 9f4985b..bc159a9 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -135,6 +135,7 @@
 
 #ifdef CONFIG_ACPI_CPPC_LIB
 extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
+extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf);
 extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
 extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_get_perf_caps(int cpu, struct cppc_perf_caps *caps);
@@ -149,6 +150,10 @@
 {
 	return -ENOTSUPP;
 }
+static inline int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
+{
+	return -ENOTSUPP;
+}
 static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 {
 	return -ENOTSUPP;
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 818680c..b20e89d 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -27,11 +27,12 @@
 #ifndef _TTM_TT_H_
 #define _TTM_TT_H_
 
+#include <linux/pagemap.h>
 #include <linux/types.h>
 #include <drm/ttm/ttm_caching.h>
 #include <drm/ttm/ttm_kmap_iter.h>
 
-struct ttm_bo_device;
+struct ttm_device;
 struct ttm_tt;
 struct ttm_resource;
 struct ttm_buffer_object;
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index abe089c..537e1b9 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -110,7 +110,7 @@
 }
 
 /* Tree-based key-value access APIs */
-struct xbc_node * __init xbc_node_find_child(struct xbc_node *parent,
+struct xbc_node * __init xbc_node_find_subkey(struct xbc_node *parent,
 					     const char *key);
 
 const char * __init xbc_node_find_value(struct xbc_node *parent,
@@ -148,7 +148,7 @@
  */
 static inline struct xbc_node * __init xbc_find_node(const char *key)
 {
-	return xbc_node_find_child(NULL, key);
+	return xbc_node_find_subkey(NULL, key);
 }
 
 /**
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 1834752..39dcadd 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -11,7 +11,7 @@
 #include <linux/types.h>
 
 /**
- * em_perf_state - Performance state of a performance domain
+ * struct em_perf_state - Performance state of a performance domain
  * @frequency:	The frequency in KHz, for consistency with CPUFreq
  * @power:	The power consumed at this level (by 1 CPU or by a registered
  *		device). It can be a total power: static and dynamic.
@@ -25,7 +25,7 @@
 };
 
 /**
- * em_perf_domain - Performance domain
+ * struct em_perf_domain - Performance domain
  * @table:		List of performance states, in ascending order
  * @nr_perf_states:	Number of performance states
  * @milliwatts:		Flag indicating the power values are in milli-Watts
@@ -103,12 +103,12 @@
 
 /**
  * em_cpu_energy() - Estimates the energy consumed by the CPUs of a
-		performance domain
+ *		performance domain
  * @pd		: performance domain for which energy has to be estimated
  * @max_util	: highest utilization among CPUs of the domain
  * @sum_util	: sum of the utilization of all CPUs in the domain
  * @allowed_cpu_cap	: maximum allowed CPU capacity for the @pd, which
-			  might reflect reduced frequency (due to thermal)
+ *			  might reflect reduced frequency (due to thermal)
  *
  * This function must be used only for CPU devices. There is no validation,
  * i.e. if the EM is a CPU type and has cpumask allocated. It is called from
diff --git a/include/linux/file.h b/include/linux/file.h
index 2de2e46..51e830b 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -94,6 +94,9 @@
 
 extern int __receive_fd(struct file *file, int __user *ufd,
 			unsigned int o_flags);
+
+extern int receive_fd(struct file *file, unsigned int o_flags);
+
 static inline int receive_fd_user(struct file *file, int __user *ufd,
 				  unsigned int o_flags)
 {
@@ -101,10 +104,6 @@
 		return -EFAULT;
 	return __receive_fd(file, ufd, o_flags);
 }
-static inline int receive_fd(struct file *file, unsigned int o_flags)
-{
-	return __receive_fd(file, NULL, o_flags);
-}
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
 extern void flush_delayed_fput(void);
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index a0b7e43..725c9b7 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -404,7 +404,7 @@
 void *pwm_get_chip_data(struct pwm_device *pwm);
 
 int pwmchip_add(struct pwm_chip *chip);
-int pwmchip_remove(struct pwm_chip *chip);
+void pwmchip_remove(struct pwm_chip *chip);
 
 int devm_pwmchip_add(struct device *dev, struct pwm_chip *chip);
 
diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index 0165824..c0475d1 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -109,6 +109,12 @@
 			     u32 *resp);
 
 extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en);
+
+extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
+			      u64 limit_node, u32 node_id, u64 version);
+extern int qcom_scm_lmh_profile_change(u32 profile_id);
+extern bool qcom_scm_lmh_dcvsh_available(void);
+
 #else
 
 #include <linux/errno.h>
@@ -170,5 +176,13 @@
 
 static inline int qcom_scm_qsmmu500_wait_safe_toggle(bool en)
 		{ return -ENODEV; }
+
+static inline int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
+				     u64 limit_node, u32 node_id, u64 version)
+		{ return -ENODEV; }
+
+static inline int qcom_scm_lmh_profile_change(u32 profile_id) { return -ENODEV; }
+
+static inline bool qcom_scm_lmh_dcvsh_available(void) { return -ENODEV; }
 #endif
 #endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 426e98e..352c612 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -142,22 +142,14 @@
 #define DECLARE_RWSEM(lockname) \
 	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+extern void  __init_rwsem(struct rw_semaphore *rwsem, const char *name,
 			  struct lock_class_key *key);
-#else
-static inline void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
-				 struct lock_class_key *key)
-{
-}
-#endif
 
 #define init_rwsem(sem)						\
 do {								\
 	static struct lock_class_key __key;			\
 								\
-	init_rwbase_rt(&(sem)->rwbase);			\
-	__rwsem_init((sem), #sem, &__key);			\
+	__init_rwsem((sem), #sem, &__key);			\
 } while (0)
 
 static __always_inline int rwsem_is_locked(struct rw_semaphore *sem)
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index d296f3b..c3148939 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -285,7 +285,7 @@
 };
 
 /**
- * struct thermal_zone_of_device_ops - scallbacks for handling DT based zones
+ * struct thermal_zone_of_device_ops - callbacks for handling DT based zones
  *
  * Mandatory:
  * @get_temp: a pointer to a function that reads the sensor temperature.
@@ -404,12 +404,13 @@
 	struct thermal_zone_device *tz)
 { }
 static inline struct thermal_cooling_device *
-thermal_cooling_device_register(char *type, void *devdata,
+thermal_cooling_device_register(const char *type, void *devdata,
 	const struct thermal_cooling_device_ops *ops)
 { return ERR_PTR(-ENODEV); }
 static inline struct thermal_cooling_device *
 thermal_of_cooling_device_register(struct device_node *np,
-	char *type, void *devdata, const struct thermal_cooling_device_ops *ops)
+	const char *type, void *devdata,
+	const struct thermal_cooling_device_ops *ops)
 { return ERR_PTR(-ENODEV); }
 static inline struct thermal_cooling_device *
 devm_thermal_of_cooling_device_register(struct device *dev,
diff --git a/include/linux/time64.h b/include/linux/time64.h
index 5117cb5..81b9686 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -25,7 +25,9 @@
 #define TIME64_MIN			(-TIME64_MAX - 1)
 
 #define KTIME_MAX			((s64)~((u64)1 << 63))
+#define KTIME_MIN			(-KTIME_MAX - 1)
 #define KTIME_SEC_MAX			(KTIME_MAX / NSEC_PER_SEC)
+#define KTIME_SEC_MIN			(KTIME_MIN / NSEC_PER_SEC)
 
 /*
  * Limits for settimeofday():
@@ -124,10 +126,13 @@
  */
 static inline s64 timespec64_to_ns(const struct timespec64 *ts)
 {
-	/* Prevent multiplication overflow */
-	if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX)
+	/* Prevent multiplication overflow / underflow */
+	if (ts->tv_sec >= KTIME_SEC_MAX)
 		return KTIME_MAX;
 
+	if (ts->tv_sec <= KTIME_SEC_MIN)
+		return KTIME_MIN;
+
 	return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec;
 }
 
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 8cfe49d..3972ab7 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -43,17 +43,17 @@
  * @last_used_idx: used index
  */
 struct vdpa_vq_state_packed {
-        u16	last_avail_counter:1;
-        u16	last_avail_idx:15;
-        u16	last_used_counter:1;
-        u16	last_used_idx:15;
+	u16	last_avail_counter:1;
+	u16	last_avail_idx:15;
+	u16	last_used_counter:1;
+	u16	last_used_idx:15;
 };
 
 struct vdpa_vq_state {
-     union {
-          struct vdpa_vq_state_split split;
-          struct vdpa_vq_state_packed packed;
-     };
+	union {
+		struct vdpa_vq_state_split split;
+		struct vdpa_vq_state_packed packed;
+	};
 };
 
 struct vdpa_mgmt_dev;
@@ -65,6 +65,7 @@
  * @config: the configuration ops for this device.
  * @index: device index
  * @features_valid: were features initialized? for legacy guests
+ * @use_va: indicate whether virtual address must be used by this device
  * @nvqs: maximum number of supported virtqueues
  * @mdev: management device pointer; caller must setup when registering device as part
  *	  of dev_add() mgmtdev ops callback before invoking _vdpa_register_device().
@@ -75,6 +76,7 @@
 	const struct vdpa_config_ops *config;
 	unsigned int index;
 	bool features_valid;
+	bool use_va;
 	int nvqs;
 	struct vdpa_mgmt_dev *mdev;
 };
@@ -90,6 +92,16 @@
 };
 
 /**
+ * Corresponding file area for device memory mapping
+ * @file: vma->vm_file for the mapping
+ * @offset: mapping offset in the vm_file
+ */
+struct vdpa_map_file {
+	struct file *file;
+	u64 offset;
+};
+
+/**
  * struct vdpa_config_ops - operations for configuring a vDPA device.
  * Note: vDPA device drivers are required to implement all of the
  * operations unless it is mentioned to be optional in the following
@@ -131,7 +143,7 @@
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				@state: pointer to returned state (last_avail_idx)
- * @get_vq_notification: 	Get the notification area for a virtqueue
+ * @get_vq_notification:	Get the notification area for a virtqueue
  *				@vdev: vdpa device
  *				@idx: virtqueue index
  *				Returns the notifcation area
@@ -171,6 +183,9 @@
  * @set_status:			Set the device status
  *				@vdev: vdpa device
  *				@status: virtio device status
+ * @reset:			Reset device
+ *				@vdev: vdpa device
+ *				Returns integer: success (0) or error (< 0)
  * @get_config_size:		Get the size of the configuration space
  *				@vdev: vdpa device
  *				Returns size_t: configuration size
@@ -255,6 +270,7 @@
 	u32 (*get_vendor_id)(struct vdpa_device *vdev);
 	u8 (*get_status)(struct vdpa_device *vdev);
 	void (*set_status)(struct vdpa_device *vdev, u8 status);
+	int (*reset)(struct vdpa_device *vdev);
 	size_t (*get_config_size)(struct vdpa_device *vdev);
 	void (*get_config)(struct vdpa_device *vdev, unsigned int offset,
 			   void *buf, unsigned int len);
@@ -266,7 +282,7 @@
 	/* DMA ops */
 	int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
 	int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
-		       u64 pa, u32 perm);
+		       u64 pa, u32 perm, void *opaque);
 	int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
 
 	/* Free device resources */
@@ -275,7 +291,8 @@
 
 struct vdpa_device *__vdpa_alloc_device(struct device *parent,
 					const struct vdpa_config_ops *config,
-					size_t size, const char *name);
+					size_t size, const char *name,
+					bool use_va);
 
 /**
  * vdpa_alloc_device - allocate and initilaize a vDPA device
@@ -285,15 +302,16 @@
  * @parent: the parent device
  * @config: the bus operations that is supported by this device
  * @name: name of the vdpa device
+ * @use_va: indicate whether virtual address must be used by this device
  *
  * Return allocated data structure or ERR_PTR upon error
  */
-#define vdpa_alloc_device(dev_struct, member, parent, config, name)   \
+#define vdpa_alloc_device(dev_struct, member, parent, config, name, use_va)   \
 			  container_of(__vdpa_alloc_device( \
 				       parent, config, \
 				       sizeof(dev_struct) + \
 				       BUILD_BUG_ON_ZERO(offsetof( \
-				       dev_struct, member)), name), \
+				       dev_struct, member)), name, use_va), \
 				       dev_struct, member)
 
 int vdpa_register_device(struct vdpa_device *vdev, int nvqs);
@@ -348,27 +366,27 @@
 	return vdev->dma_dev;
 }
 
-static inline void vdpa_reset(struct vdpa_device *vdev)
+static inline int vdpa_reset(struct vdpa_device *vdev)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	vdev->features_valid = false;
-        ops->set_status(vdev, 0);
+	return ops->reset(vdev);
 }
 
 static inline int vdpa_set_features(struct vdpa_device *vdev, u64 features)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	vdev->features_valid = true;
-        return ops->set_features(vdev, features);
+	return ops->set_features(vdev, features);
 }
 
-
-static inline void vdpa_get_config(struct vdpa_device *vdev, unsigned offset,
-				   void *buf, unsigned int len)
+static inline void vdpa_get_config(struct vdpa_device *vdev,
+				   unsigned int offset, void *buf,
+				   unsigned int len)
 {
-        const struct vdpa_config_ops *ops = vdev->config;
+	const struct vdpa_config_ops *ops = vdev->config;
 
 	/*
 	 * Config accesses aren't supposed to trigger before features are set.
diff --git a/include/linux/vhost_iotlb.h b/include/linux/vhost_iotlb.h
index 6b09b78..2d0e2f5 100644
--- a/include/linux/vhost_iotlb.h
+++ b/include/linux/vhost_iotlb.h
@@ -17,6 +17,7 @@
 	u32 perm;
 	u32 flags_padding;
 	u64 __subtree_last;
+	void *opaque;
 };
 
 #define VHOST_IOTLB_FLAG_RETIRE 0x1
@@ -29,6 +30,8 @@
 	unsigned int flags;
 };
 
+int vhost_iotlb_add_range_ctx(struct vhost_iotlb *iotlb, u64 start, u64 last,
+			      u64 addr, unsigned int perm, void *opaque);
 int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last,
 			  u64 addr, unsigned int perm);
 void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last);
diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h
new file mode 100644
index 0000000..7cfe1c1
--- /dev/null
+++ b/include/uapi/linux/vduse.h
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_VDUSE_H_
+#define _UAPI_VDUSE_H_
+
+#include <linux/types.h>
+
+#define VDUSE_BASE	0x81
+
+/* The ioctls for control device (/dev/vduse/control) */
+
+#define VDUSE_API_VERSION	0
+
+/*
+ * Get the version of VDUSE API that kernel supported (VDUSE_API_VERSION).
+ * This is used for future extension.
+ */
+#define VDUSE_GET_API_VERSION	_IOR(VDUSE_BASE, 0x00, __u64)
+
+/* Set the version of VDUSE API that userspace supported. */
+#define VDUSE_SET_API_VERSION	_IOW(VDUSE_BASE, 0x01, __u64)
+
+/**
+ * struct vduse_dev_config - basic configuration of a VDUSE device
+ * @name: VDUSE device name, needs to be NUL terminated
+ * @vendor_id: virtio vendor id
+ * @device_id: virtio device id
+ * @features: virtio features
+ * @vq_num: the number of virtqueues
+ * @vq_align: the allocation alignment of virtqueue's metadata
+ * @reserved: for future use, needs to be initialized to zero
+ * @config_size: the size of the configuration space
+ * @config: the buffer of the configuration space
+ *
+ * Structure used by VDUSE_CREATE_DEV ioctl to create VDUSE device.
+ */
+struct vduse_dev_config {
+#define VDUSE_NAME_MAX	256
+	char name[VDUSE_NAME_MAX];
+	__u32 vendor_id;
+	__u32 device_id;
+	__u64 features;
+	__u32 vq_num;
+	__u32 vq_align;
+	__u32 reserved[13];
+	__u32 config_size;
+	__u8 config[];
+};
+
+/* Create a VDUSE device which is represented by a char device (/dev/vduse/$NAME) */
+#define VDUSE_CREATE_DEV	_IOW(VDUSE_BASE, 0x02, struct vduse_dev_config)
+
+/*
+ * Destroy a VDUSE device. Make sure there are no more references
+ * to the char device (/dev/vduse/$NAME).
+ */
+#define VDUSE_DESTROY_DEV	_IOW(VDUSE_BASE, 0x03, char[VDUSE_NAME_MAX])
+
+/* The ioctls for VDUSE device (/dev/vduse/$NAME) */
+
+/**
+ * struct vduse_iotlb_entry - entry of IOTLB to describe one IOVA region [start, last]
+ * @offset: the mmap offset on returned file descriptor
+ * @start: start of the IOVA region
+ * @last: last of the IOVA region
+ * @perm: access permission of the IOVA region
+ *
+ * Structure used by VDUSE_IOTLB_GET_FD ioctl to find an overlapped IOVA region.
+ */
+struct vduse_iotlb_entry {
+	__u64 offset;
+	__u64 start;
+	__u64 last;
+#define VDUSE_ACCESS_RO 0x1
+#define VDUSE_ACCESS_WO 0x2
+#define VDUSE_ACCESS_RW 0x3
+	__u8 perm;
+};
+
+/*
+ * Find the first IOVA region that overlaps with the range [start, last]
+ * and return the corresponding file descriptor. Return -EINVAL means the
+ * IOVA region doesn't exist. Caller should set start and last fields.
+ */
+#define VDUSE_IOTLB_GET_FD	_IOWR(VDUSE_BASE, 0x10, struct vduse_iotlb_entry)
+
+/*
+ * Get the negotiated virtio features. It's a subset of the features in
+ * struct vduse_dev_config which can be accepted by virtio driver. It's
+ * only valid after FEATURES_OK status bit is set.
+ */
+#define VDUSE_DEV_GET_FEATURES	_IOR(VDUSE_BASE, 0x11, __u64)
+
+/**
+ * struct vduse_config_data - data used to update configuration space
+ * @offset: the offset from the beginning of configuration space
+ * @length: the length to write to configuration space
+ * @buffer: the buffer used to write from
+ *
+ * Structure used by VDUSE_DEV_SET_CONFIG ioctl to update device
+ * configuration space.
+ */
+struct vduse_config_data {
+	__u32 offset;
+	__u32 length;
+	__u8 buffer[];
+};
+
+/* Set device configuration space */
+#define VDUSE_DEV_SET_CONFIG	_IOW(VDUSE_BASE, 0x12, struct vduse_config_data)
+
+/*
+ * Inject a config interrupt. It's usually used to notify virtio driver
+ * that device configuration space has changed.
+ */
+#define VDUSE_DEV_INJECT_CONFIG_IRQ	_IO(VDUSE_BASE, 0x13)
+
+/**
+ * struct vduse_vq_config - basic configuration of a virtqueue
+ * @index: virtqueue index
+ * @max_size: the max size of virtqueue
+ * @reserved: for future use, needs to be initialized to zero
+ *
+ * Structure used by VDUSE_VQ_SETUP ioctl to setup a virtqueue.
+ */
+struct vduse_vq_config {
+	__u32 index;
+	__u16 max_size;
+	__u16 reserved[13];
+};
+
+/*
+ * Setup the specified virtqueue. Make sure all virtqueues have been
+ * configured before the device is attached to vDPA bus.
+ */
+#define VDUSE_VQ_SETUP		_IOW(VDUSE_BASE, 0x14, struct vduse_vq_config)
+
+/**
+ * struct vduse_vq_state_split - split virtqueue state
+ * @avail_index: available index
+ */
+struct vduse_vq_state_split {
+	__u16 avail_index;
+};
+
+/**
+ * struct vduse_vq_state_packed - packed virtqueue state
+ * @last_avail_counter: last driver ring wrap counter observed by device
+ * @last_avail_idx: device available index
+ * @last_used_counter: device ring wrap counter
+ * @last_used_idx: used index
+ */
+struct vduse_vq_state_packed {
+	__u16 last_avail_counter;
+	__u16 last_avail_idx;
+	__u16 last_used_counter;
+	__u16 last_used_idx;
+};
+
+/**
+ * struct vduse_vq_info - information of a virtqueue
+ * @index: virtqueue index
+ * @num: the size of virtqueue
+ * @desc_addr: address of desc area
+ * @driver_addr: address of driver area
+ * @device_addr: address of device area
+ * @split: split virtqueue state
+ * @packed: packed virtqueue state
+ * @ready: ready status of virtqueue
+ *
+ * Structure used by VDUSE_VQ_GET_INFO ioctl to get virtqueue's information.
+ */
+struct vduse_vq_info {
+	__u32 index;
+	__u32 num;
+	__u64 desc_addr;
+	__u64 driver_addr;
+	__u64 device_addr;
+	union {
+		struct vduse_vq_state_split split;
+		struct vduse_vq_state_packed packed;
+	};
+	__u8 ready;
+};
+
+/* Get the specified virtqueue's information. Caller should set index field. */
+#define VDUSE_VQ_GET_INFO	_IOWR(VDUSE_BASE, 0x15, struct vduse_vq_info)
+
+/**
+ * struct vduse_vq_eventfd - eventfd configuration for a virtqueue
+ * @index: virtqueue index
+ * @fd: eventfd, -1 means de-assigning the eventfd
+ *
+ * Structure used by VDUSE_VQ_SETUP_KICKFD ioctl to setup kick eventfd.
+ */
+struct vduse_vq_eventfd {
+	__u32 index;
+#define VDUSE_EVENTFD_DEASSIGN -1
+	int fd;
+};
+
+/*
+ * Setup kick eventfd for specified virtqueue. The kick eventfd is used
+ * by VDUSE kernel module to notify userspace to consume the avail vring.
+ */
+#define VDUSE_VQ_SETUP_KICKFD	_IOW(VDUSE_BASE, 0x16, struct vduse_vq_eventfd)
+
+/*
+ * Inject an interrupt for specific virtqueue. It's used to notify virtio driver
+ * to consume the used vring.
+ */
+#define VDUSE_VQ_INJECT_IRQ	_IOW(VDUSE_BASE, 0x17, __u32)
+
+/* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */
+
+/**
+ * enum vduse_req_type - request type
+ * @VDUSE_GET_VQ_STATE: get the state for specified virtqueue from userspace
+ * @VDUSE_SET_STATUS: set the device status
+ * @VDUSE_UPDATE_IOTLB: Notify userspace to update the memory mapping for
+ *                      specified IOVA range via VDUSE_IOTLB_GET_FD ioctl
+ */
+enum vduse_req_type {
+	VDUSE_GET_VQ_STATE,
+	VDUSE_SET_STATUS,
+	VDUSE_UPDATE_IOTLB,
+};
+
+/**
+ * struct vduse_vq_state - virtqueue state
+ * @index: virtqueue index
+ * @split: split virtqueue state
+ * @packed: packed virtqueue state
+ */
+struct vduse_vq_state {
+	__u32 index;
+	union {
+		struct vduse_vq_state_split split;
+		struct vduse_vq_state_packed packed;
+	};
+};
+
+/**
+ * struct vduse_dev_status - device status
+ * @status: device status
+ */
+struct vduse_dev_status {
+	__u8 status;
+};
+
+/**
+ * struct vduse_iova_range - IOVA range [start, last]
+ * @start: start of the IOVA range
+ * @last: last of the IOVA range
+ */
+struct vduse_iova_range {
+	__u64 start;
+	__u64 last;
+};
+
+/**
+ * struct vduse_dev_request - control request
+ * @type: request type
+ * @request_id: request id
+ * @reserved: for future use
+ * @vq_state: virtqueue state, only index field is available
+ * @s: device status
+ * @iova: IOVA range for updating
+ * @padding: padding
+ *
+ * Structure used by read(2) on /dev/vduse/$NAME.
+ */
+struct vduse_dev_request {
+	__u32 type;
+	__u32 request_id;
+	__u32 reserved[4];
+	union {
+		struct vduse_vq_state vq_state;
+		struct vduse_dev_status s;
+		struct vduse_iova_range iova;
+		__u32 padding[32];
+	};
+};
+
+/**
+ * struct vduse_dev_response - response to control request
+ * @request_id: corresponding request id
+ * @result: the result of request
+ * @reserved: for future use, needs to be initialized to zero
+ * @vq_state: virtqueue state
+ * @padding: padding
+ *
+ * Structure used by write(2) on /dev/vduse/$NAME.
+ */
+struct vduse_dev_response {
+	__u32 request_id;
+#define VDUSE_REQ_RESULT_OK	0x00
+#define VDUSE_REQ_RESULT_FAILED	0x01
+	__u32 result;
+	__u32 reserved[4];
+	union {
+		struct vduse_vq_state vq_state;
+		__u32 padding[32];
+	};
+};
+
+#endif /* _UAPI_VDUSE_H_ */
diff --git a/include/uapi/linux/virtio_ids.h b/include/uapi/linux/virtio_ids.h
index 50d352f..80d76b7 100644
--- a/include/uapi/linux/virtio_ids.h
+++ b/include/uapi/linux/virtio_ids.h
@@ -54,9 +54,18 @@
 #define VIRTIO_ID_SOUND			25 /* virtio sound */
 #define VIRTIO_ID_FS			26 /* virtio filesystem */
 #define VIRTIO_ID_PMEM			27 /* virtio pmem */
+#define VIRTIO_ID_RPMB			28 /* virtio rpmb */
 #define VIRTIO_ID_MAC80211_HWSIM	29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_VIDEO_ENCODER		30 /* virtio video encoder */
+#define VIRTIO_ID_VIDEO_DECODER		31 /* virtio video decoder */
 #define VIRTIO_ID_SCMI			32 /* virtio SCMI */
+#define VIRTIO_ID_NITRO_SEC_MOD		33 /* virtio nitro secure module*/
 #define VIRTIO_ID_I2C_ADAPTER		34 /* virtio i2c adapter */
+#define VIRTIO_ID_WATCHDOG		35 /* virtio watchdog */
+#define VIRTIO_ID_CAN			36 /* virtio can */
+#define VIRTIO_ID_DMABUF		37 /* virtio dmabuf */
+#define VIRTIO_ID_PARAM_SERV		38 /* virtio parameter server */
+#define VIRTIO_ID_AUDIO_POLICY		39 /* virtio audio policy */
 #define VIRTIO_ID_BT			40 /* virtio bluetooth */
 #define VIRTIO_ID_GPIO			41 /* virtio gpio */
 
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
index 3dd3555..6473883 100644
--- a/include/uapi/linux/virtio_vsock.h
+++ b/include/uapi/linux/virtio_vsock.h
@@ -97,7 +97,8 @@
 
 /* VIRTIO_VSOCK_OP_RW flags values */
 enum virtio_vsock_rw {
-	VIRTIO_VSOCK_SEQ_EOR = 1,
+	VIRTIO_VSOCK_SEQ_EOM = 1,
+	VIRTIO_VSOCK_SEQ_EOR = 2,
 };
 
 #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index a47a731..7cc2a0f 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include/uapi/misc/habanalabs.h
@@ -276,7 +276,17 @@
 	HL_DEVICE_STATUS_OPERATIONAL,
 	HL_DEVICE_STATUS_IN_RESET,
 	HL_DEVICE_STATUS_MALFUNCTION,
-	HL_DEVICE_STATUS_NEEDS_RESET
+	HL_DEVICE_STATUS_NEEDS_RESET,
+	HL_DEVICE_STATUS_IN_DEVICE_CREATION,
+	HL_DEVICE_STATUS_LAST = HL_DEVICE_STATUS_IN_DEVICE_CREATION
+};
+
+enum hl_server_type {
+	HL_SERVER_TYPE_UNKNOWN = 0,
+	HL_SERVER_GAUDI_HLS1 = 1,
+	HL_SERVER_GAUDI_HLS1H = 2,
+	HL_SERVER_GAUDI_TYPE1 = 3,
+	HL_SERVER_GAUDI_TYPE2 = 4
 };
 
 /* Opcode for management ioctl
@@ -337,17 +347,49 @@
 #define HL_INFO_VERSION_MAX_LEN	128
 #define HL_INFO_CARD_NAME_MAX_LEN	16
 
+/**
+ * struct hl_info_hw_ip_info - hardware information on various IPs in the ASIC
+ * @sram_base_address: The first SRAM physical base address that is free to be
+ *                     used by the user.
+ * @dram_base_address: The first DRAM virtual or physical base address that is
+ *                     free to be used by the user.
+ * @dram_size: The DRAM size that is available to the user.
+ * @sram_size: The SRAM size that is available to the user.
+ * @num_of_events: The number of events that can be received from the f/w. This
+ *                 is needed so the user can what is the size of the h/w events
+ *                 array he needs to pass to the kernel when he wants to fetch
+ *                 the event counters.
+ * @device_id: PCI device ID of the ASIC.
+ * @module_id: Module ID of the ASIC for mezzanine cards in servers
+ *             (From OCP spec).
+ * @first_available_interrupt_id: The first available interrupt ID for the user
+ *                                to be used when it works with user interrupts.
+ * @server_type: Server type that the Gaudi ASIC is currently installed in.
+ *               The value is according to enum hl_server_type
+ * @cpld_version: CPLD version on the board.
+ * @psoc_pci_pll_nr: PCI PLL NR value. Needed by the profiler in some ASICs.
+ * @psoc_pci_pll_nf: PCI PLL NF value. Needed by the profiler in some ASICs.
+ * @psoc_pci_pll_od: PCI PLL OD value. Needed by the profiler in some ASICs.
+ * @psoc_pci_pll_div_factor: PCI PLL DIV factor value. Needed by the profiler
+ *                           in some ASICs.
+ * @tpc_enabled_mask: Bit-mask that represents which TPCs are enabled. Relevant
+ *                    for Goya/Gaudi only.
+ * @dram_enabled: Whether the DRAM is enabled.
+ * @cpucp_version: The CPUCP f/w version.
+ * @card_name: The card name as passed by the f/w.
+ * @dram_page_size: The DRAM physical page size.
+ */
 struct hl_info_hw_ip_info {
 	__u64 sram_base_address;
 	__u64 dram_base_address;
 	__u64 dram_size;
 	__u32 sram_size;
 	__u32 num_of_events;
-	__u32 device_id; /* PCI Device ID */
-	__u32 module_id; /* For mezzanine cards in servers (From OCP spec.) */
+	__u32 device_id;
+	__u32 module_id;
 	__u32 reserved;
 	__u16 first_available_interrupt_id;
-	__u16 reserved2;
+	__u16 server_type;
 	__u32 cpld_version;
 	__u32 psoc_pci_pll_nr;
 	__u32 psoc_pci_pll_nf;
@@ -358,7 +400,7 @@
 	__u8 pad[2];
 	__u8 cpucp_version[HL_INFO_VERSION_MAX_LEN];
 	__u8 card_name[HL_INFO_CARD_NAME_MAX_LEN];
-	__u64 reserved3;
+	__u64 reserved2;
 	__u64 dram_page_size;
 };
 
@@ -628,12 +670,21 @@
 		__u64 cb_handle;
 
 		/* Relevant only when HL_CS_FLAGS_WAIT or
-		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set.
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set
 		 * This holds address of array of u64 values that contain
-		 * signal CS sequence numbers. The wait described by this job
-		 * will listen on all those signals (wait event per signal)
+		 * signal CS sequence numbers. The wait described by
+		 * this job will listen on all those signals
+		 * (wait event per signal)
 		 */
 		__u64 signal_seq_arr;
+
+		/*
+		 * Relevant only when HL_CS_FLAGS_WAIT or
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set
+		 * along with HL_CS_FLAGS_ENCAP_SIGNALS.
+		 * This is the CS sequence which has the encapsulated signals.
+		 */
+		__u64 encaps_signal_seq;
 	};
 
 	/* Index of queue to put the CB on */
@@ -651,6 +702,17 @@
 		 * Number of entries in signal_seq_arr
 		 */
 		__u32 num_signal_seq_arr;
+
+		/* Relevant only when HL_CS_FLAGS_WAIT or
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set along
+		 * with HL_CS_FLAGS_ENCAP_SIGNALS
+		 * This set the signals range that the user want to wait for
+		 * out of the whole reserved signals range.
+		 * e.g if the signals range is 20, and user don't want
+		 * to wait for signal 8, so he set this offset to 7, then
+		 * he call the API again with 9 and so on till 20.
+		 */
+		__u32 encaps_signal_offset;
 	};
 
 	/* HL_CS_CHUNK_FLAGS_* */
@@ -678,6 +740,28 @@
 #define HL_CS_FLAGS_CUSTOM_TIMEOUT		0x200
 #define HL_CS_FLAGS_SKIP_RESET_ON_TIMEOUT	0x400
 
+/*
+ * The encapsulated signals CS is merged into the existing CS ioctls.
+ * In order to use this feature need to follow the below procedure:
+ * 1. Reserve signals, set the CS type to HL_CS_FLAGS_RESERVE_SIGNALS_ONLY
+ *    the output of this API will be the SOB offset from CFG_BASE.
+ *    this address will be used to patch CB cmds to do the signaling for this
+ *    SOB by incrementing it's value.
+ *    for reverting the reservation use HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY
+ *    CS type, note that this might fail if out-of-sync happened to the SOB
+ *    value, in case other signaling request to the same SOB occurred between
+ *    reserve-unreserve calls.
+ * 2. Use the staged CS to do the encapsulated signaling jobs.
+ *    use HL_CS_FLAGS_STAGED_SUBMISSION and HL_CS_FLAGS_STAGED_SUBMISSION_FIRST
+ *    along with HL_CS_FLAGS_ENCAP_SIGNALS flag, and set encaps_signal_offset
+ *    field. This offset allows app to wait on part of the reserved signals.
+ * 3. Use WAIT/COLLECTIVE WAIT CS along with HL_CS_FLAGS_ENCAP_SIGNALS flag
+ *    to wait for the encapsulated signals.
+ */
+#define HL_CS_FLAGS_ENCAP_SIGNALS		0x800
+#define HL_CS_FLAGS_RESERVE_SIGNALS_ONLY	0x1000
+#define HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY	0x2000
+
 #define HL_CS_STATUS_SUCCESS		0
 
 #define HL_MAX_JOBS_PER_CS		512
@@ -690,10 +774,35 @@
 	/* holds address of array of hl_cs_chunk for execution phase */
 	__u64 chunks_execute;
 
-	/* Sequence number of a staged submission CS
-	 * valid only if HL_CS_FLAGS_STAGED_SUBMISSION is set
-	 */
-	__u64 seq;
+	union {
+		/*
+		 * Sequence number of a staged submission CS
+		 * valid only if HL_CS_FLAGS_STAGED_SUBMISSION is set and
+		 * HL_CS_FLAGS_STAGED_SUBMISSION_FIRST is unset.
+		 */
+		__u64 seq;
+
+		/*
+		 * Encapsulated signals handle id
+		 * Valid for two flows:
+		 * 1. CS with encapsulated signals:
+		 *    when HL_CS_FLAGS_STAGED_SUBMISSION and
+		 *    HL_CS_FLAGS_STAGED_SUBMISSION_FIRST
+		 *    and HL_CS_FLAGS_ENCAP_SIGNALS are set.
+		 * 2. unreserve signals:
+		 *    valid when HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY is set.
+		 */
+		__u32 encaps_sig_handle_id;
+
+		/* Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */
+		struct {
+			/* Encapsulated signals number */
+			__u32 encaps_signals_count;
+
+			/* Encapsulated signals queue index (stream) */
+			__u32 encaps_signals_q_idx;
+		};
+	};
 
 	/* Number of chunks in restore phase array. Maximum number is
 	 * HL_MAX_JOBS_PER_CS
@@ -718,14 +827,31 @@
 };
 
 struct hl_cs_out {
-	/*
-	 * seq holds the sequence number of the CS to pass to wait ioctl. All
-	 * values are valid except for 0 and ULLONG_MAX
-	 */
-	__u64 seq;
-	/* HL_CS_STATUS_* */
+	union {
+		/*
+		 * seq holds the sequence number of the CS to pass to wait
+		 * ioctl. All values are valid except for 0 and ULLONG_MAX
+		 */
+		__u64 seq;
+
+		/* Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */
+		struct {
+			/* This is the resereved signal handle id */
+			__u32 handle_id;
+
+			/* This is the signals count */
+			__u32 count;
+		};
+	};
+
+	/* HL_CS_STATUS */
 	__u32 status;
-	__u32 pad;
+
+	/*
+	 * SOB base address offset
+	 * Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set
+	 */
+	__u32 sob_base_addr_offset;
 };
 
 union hl_cs_args {
@@ -735,11 +861,18 @@
 
 #define HL_WAIT_CS_FLAGS_INTERRUPT	0x2
 #define HL_WAIT_CS_FLAGS_INTERRUPT_MASK 0xFFF00000
+#define HL_WAIT_CS_FLAGS_MULTI_CS	0x4
+
+#define HL_WAIT_MULTI_CS_LIST_MAX_LEN	32
 
 struct hl_wait_cs_in {
 	union {
 		struct {
-			/* Command submission sequence number */
+			/*
+			 * In case of wait_cs holds the CS sequence number.
+			 * In case of wait for multi CS hold a user pointer to
+			 * an array of CS sequence numbers
+			 */
 			__u64 seq;
 			/* Absolute timeout to wait for command submission
 			 * in microseconds
@@ -767,12 +900,17 @@
 
 	/* Context ID - Currently not in use */
 	__u32 ctx_id;
+
 	/* HL_WAIT_CS_FLAGS_*
 	 * If HL_WAIT_CS_FLAGS_INTERRUPT is set, this field should include
 	 * interrupt id according to HL_WAIT_CS_FLAGS_INTERRUPT_MASK, in order
 	 * not to specify an interrupt id ,set mask to all 1s.
 	 */
 	__u32 flags;
+
+	/* Multi CS API info- valid entries in multi-CS array */
+	__u8 seq_arr_len;
+	__u8 pad[7];
 };
 
 #define HL_WAIT_CS_STATUS_COMPLETED	0
@@ -789,8 +927,15 @@
 	__u32 status;
 	/* HL_WAIT_CS_STATUS_FLAG* */
 	__u32 flags;
-	/* valid only if HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD is set */
+	/*
+	 * valid only if HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD is set
+	 * for wait_cs: timestamp of CS completion
+	 * for wait_multi_cs: timestamp of FIRST CS completion
+	 */
 	__s64 timestamp_nsec;
+	/* multi CS completion bitmap */
+	__u32 cs_completion_map;
+	__u32 pad;
 };
 
 union hl_wait_cs_args {
@@ -813,6 +958,7 @@
 #define HL_MEM_CONTIGUOUS	0x1
 #define HL_MEM_SHARED		0x2
 #define HL_MEM_USERPTR		0x4
+#define HL_MEM_FORCE_HINT	0x8
 
 struct hl_mem_in {
 	union {
diff --git a/kernel/futex.c b/kernel/futex.c
index e7b4c61..c15ad27 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1263,6 +1263,36 @@
 	return -ESRCH;
 }
 
+static void __attach_to_pi_owner(struct task_struct *p, union futex_key *key,
+				 struct futex_pi_state **ps)
+{
+	/*
+	 * No existing pi state. First waiter. [2]
+	 *
+	 * This creates pi_state, we have hb->lock held, this means nothing can
+	 * observe this state, wait_lock is irrelevant.
+	 */
+	struct futex_pi_state *pi_state = alloc_pi_state();
+
+	/*
+	 * Initialize the pi_mutex in locked state and make @p
+	 * the owner of it:
+	 */
+	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
+
+	/* Store the key for possible exit cleanups: */
+	pi_state->key = *key;
+
+	WARN_ON(!list_empty(&pi_state->list));
+	list_add(&pi_state->list, &p->pi_state_list);
+	/*
+	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
+	 * because there is no concurrency as the object is not published yet.
+	 */
+	pi_state->owner = p;
+
+	*ps = pi_state;
+}
 /*
  * Lookup the task for the TID provided from user space and attach to
  * it after doing proper sanity checks.
@@ -1272,7 +1302,6 @@
 			      struct task_struct **exiting)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
-	struct futex_pi_state *pi_state;
 	struct task_struct *p;
 
 	/*
@@ -1324,36 +1353,11 @@
 		return ret;
 	}
 
-	/*
-	 * No existing pi state. First waiter. [2]
-	 *
-	 * This creates pi_state, we have hb->lock held, this means nothing can
-	 * observe this state, wait_lock is irrelevant.
-	 */
-	pi_state = alloc_pi_state();
-
-	/*
-	 * Initialize the pi_mutex in locked state and make @p
-	 * the owner of it:
-	 */
-	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
-
-	/* Store the key for possible exit cleanups: */
-	pi_state->key = *key;
-
-	WARN_ON(!list_empty(&pi_state->list));
-	list_add(&pi_state->list, &p->pi_state_list);
-	/*
-	 * Assignment without holding pi_state->pi_mutex.wait_lock is safe
-	 * because there is no concurrency as the object is not published yet.
-	 */
-	pi_state->owner = p;
+	__attach_to_pi_owner(p, key, ps);
 	raw_spin_unlock_irq(&p->pi_lock);
 
 	put_task_struct(p);
 
-	*ps = pi_state;
-
 	return 0;
 }
 
@@ -1454,8 +1458,26 @@
 			newval |= FUTEX_WAITERS;
 
 		ret = lock_pi_update_atomic(uaddr, uval, newval);
-		/* If the take over worked, return 1 */
-		return ret < 0 ? ret : 1;
+		if (ret)
+			return ret;
+
+		/*
+		 * If the waiter bit was requested the caller also needs PI
+		 * state attached to the new owner of the user space futex.
+		 *
+		 * @task is guaranteed to be alive and it cannot be exiting
+		 * because it is either sleeping or waiting in
+		 * futex_requeue_pi_wakeup_sync().
+		 *
+		 * No need to do the full attach_to_pi_owner() exercise
+		 * because @task is known and valid.
+		 */
+		if (set_waiters) {
+			raw_spin_lock_irq(&task->pi_lock);
+			__attach_to_pi_owner(task, key, ps);
+			raw_spin_unlock_irq(&task->pi_lock);
+		}
+		return 1;
 	}
 
 	/*
@@ -1939,12 +1961,26 @@
  * @hb:		the hash_bucket of the requeue target futex
  *
  * During futex_requeue, with requeue_pi=1, it is possible to acquire the
- * target futex if it is uncontended or via a lock steal.  Set the futex_q key
- * to the requeue target futex so the waiter can detect the wakeup on the right
- * futex, but remove it from the hb and NULL the rt_waiter so it can detect
- * atomic lock acquisition.  Set the q->lock_ptr to the requeue target hb->lock
- * to protect access to the pi_state to fixup the owner later.  Must be called
- * with both q->lock_ptr and hb->lock held.
+ * target futex if it is uncontended or via a lock steal.
+ *
+ * 1) Set @q::key to the requeue target futex key so the waiter can detect
+ *    the wakeup on the right futex.
+ *
+ * 2) Dequeue @q from the hash bucket.
+ *
+ * 3) Set @q::rt_waiter to NULL so the woken up task can detect atomic lock
+ *    acquisition.
+ *
+ * 4) Set the q->lock_ptr to the requeue target hb->lock for the case that
+ *    the waiter has to fixup the pi state.
+ *
+ * 5) Complete the requeue state so the waiter can make progress. After
+ *    this point the waiter task can return from the syscall immediately in
+ *    case that the pi state does not have to be fixed up.
+ *
+ * 6) Wake the waiter task.
+ *
+ * Must be called with both q->lock_ptr and hb->lock held.
  */
 static inline
 void requeue_pi_wake_futex(struct futex_q *q, union futex_key *key,
@@ -1998,7 +2034,7 @@
 {
 	struct futex_q *top_waiter = NULL;
 	u32 curval;
-	int ret, vpid;
+	int ret;
 
 	if (get_futex_value_locked(&curval, pifutex))
 		return -EFAULT;
@@ -2025,7 +2061,7 @@
 	 * and waiting on the 'waitqueue' futex which is always !PI.
 	 */
 	if (!top_waiter->rt_waiter || top_waiter->pi_state)
-		ret = -EINVAL;
+		return -EINVAL;
 
 	/* Ensure we requeue to the expected futex. */
 	if (!match_futex(top_waiter->requeue_pi_key, key2))
@@ -2036,17 +2072,23 @@
 		return -EAGAIN;
 
 	/*
-	 * Try to take the lock for top_waiter.  Set the FUTEX_WAITERS bit in
-	 * the contended case or if set_waiters is 1.  The pi_state is returned
-	 * in ps in contended cases.
+	 * Try to take the lock for top_waiter and set the FUTEX_WAITERS bit
+	 * in the contended case or if @set_waiters is true.
+	 *
+	 * In the contended case PI state is attached to the lock owner. If
+	 * the user space lock can be acquired then PI state is attached to
+	 * the new owner (@top_waiter->task) when @set_waiters is true.
 	 */
-	vpid = task_pid_vnr(top_waiter->task);
 	ret = futex_lock_pi_atomic(pifutex, hb2, key2, ps, top_waiter->task,
 				   exiting, set_waiters);
 	if (ret == 1) {
-		/* Dequeue, wake up and update top_waiter::requeue_state */
+		/*
+		 * Lock was acquired in user space and PI state was
+		 * attached to @top_waiter->task. That means state is fully
+		 * consistent and the waiter can return to user space
+		 * immediately after the wakeup.
+		 */
 		requeue_pi_wake_futex(top_waiter, key2, hb2);
-		return vpid;
 	} else if (ret < 0) {
 		/* Rewind top_waiter::requeue_state */
 		futex_requeue_pi_complete(top_waiter, ret);
@@ -2208,19 +2250,26 @@
 						 &exiting, nr_requeue);
 
 		/*
-		 * At this point the top_waiter has either taken uaddr2 or is
-		 * waiting on it.  If the former, then the pi_state will not
-		 * exist yet, look it up one more time to ensure we have a
-		 * reference to it. If the lock was taken, @ret contains the
-		 * VPID of the top waiter task.
-		 * If the lock was not taken, we have pi_state and an initial
-		 * refcount on it. In case of an error we have nothing.
+		 * At this point the top_waiter has either taken uaddr2 or
+		 * is waiting on it. In both cases pi_state has been
+		 * established and an initial refcount on it. In case of an
+		 * error there's nothing.
 		 *
 		 * The top waiter's requeue_state is up to date:
 		 *
-		 *  - If the lock was acquired atomically (ret > 0), then
+		 *  - If the lock was acquired atomically (ret == 1), then
 		 *    the state is Q_REQUEUE_PI_LOCKED.
 		 *
+		 *    The top waiter has been dequeued and woken up and can
+		 *    return to user space immediately. The kernel/user
+		 *    space state is consistent. In case that there must be
+		 *    more waiters requeued the WAITERS bit in the user
+		 *    space futex is set so the top waiter task has to go
+		 *    into the syscall slowpath to unlock the futex. This
+		 *    will block until this requeue operation has been
+		 *    completed and the hash bucket locks have been
+		 *    dropped.
+		 *
 		 *  - If the trylock failed with an error (ret < 0) then
 		 *    the state is either Q_REQUEUE_PI_NONE, i.e. "nothing
 		 *    happened", or Q_REQUEUE_PI_IGNORE when there was an
@@ -2234,36 +2283,20 @@
 		 *    the same sanity checks for requeue_pi as the loop
 		 *    below does.
 		 */
-		if (ret > 0) {
-			WARN_ON(pi_state);
-			task_count++;
-			/*
-			 * If futex_proxy_trylock_atomic() acquired the
-			 * user space futex, then the user space value
-			 * @uaddr2 has been set to the @hb1's top waiter
-			 * task VPID. This task is guaranteed to be alive
-			 * and cannot be exiting because it is either
-			 * sleeping or blocked on @hb2 lock.
-			 *
-			 * The @uaddr2 futex cannot have waiters either as
-			 * otherwise futex_proxy_trylock_atomic() would not
-			 * have succeeded.
-			 *
-			 * In order to requeue waiters to @hb2, pi state is
-			 * required. Hand in the VPID value (@ret) and
-			 * allocate PI state with an initial refcount on
-			 * it.
-			 */
-			ret = attach_to_pi_owner(uaddr2, ret, &key2, &pi_state,
-						 &exiting);
-			WARN_ON(ret);
-		}
-
 		switch (ret) {
 		case 0:
 			/* We hold a reference on the pi state. */
 			break;
 
+		case 1:
+			/*
+			 * futex_proxy_trylock_atomic() acquired the user space
+			 * futex. Adjust task_count.
+			 */
+			task_count++;
+			ret = 0;
+			break;
+
 		/*
 		 * If the above failed, then pi_state is NULL and
 		 * waiter::requeue_state is correct.
@@ -2395,9 +2428,8 @@
 	}
 
 	/*
-	 * We took an extra initial reference to the pi_state either in
-	 * futex_proxy_trylock_atomic() or in attach_to_pi_owner(). We need
-	 * to drop it here again.
+	 * We took an extra initial reference to the pi_state in
+	 * futex_proxy_trylock_atomic(). We need to drop it here again.
 	 */
 	put_pi_state(pi_state);
 
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 8eabdc7..6bb116c 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -753,7 +753,7 @@
 		 * other configuration and we fail to report; also, see
 		 * lockdep.
 		 */
-		if (IS_ENABLED(CONFIG_PREEMPT_RT) && orig_waiter->ww_ctx)
+		if (IS_ENABLED(CONFIG_PREEMPT_RT) && orig_waiter && orig_waiter->ww_ctx)
 			ret = 0;
 
 		raw_spin_unlock(&lock->wait_lock);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 9215b4d..000e8d5 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -1376,15 +1376,17 @@
 
 #include "rwbase_rt.c"
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-void __rwsem_init(struct rw_semaphore *sem, const char *name,
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
 		  struct lock_class_key *key)
 {
+	init_rwbase_rt(&(sem)->rwbase);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
 	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
 	lockdep_init_map_wait(&sem->dep_map, name, key, 0, LD_WAIT_SLEEP);
-}
-EXPORT_SYMBOL(__rwsem_init);
 #endif
+}
+EXPORT_SYMBOL(__init_rwsem);
 
 static inline void __down_read(struct rw_semaphore *sem)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c4462c4..1bba412 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8836,7 +8836,6 @@
 	struct task_struct *push_task = rq->curr;
 
 	lockdep_assert_rq_held(rq);
-	SCHED_WARN_ON(rq->cpu != smp_processor_id());
 
 	/*
 	 * Ensure the thing is persistent until balance_push_set(.on = false);
@@ -8844,9 +8843,10 @@
 	rq->balance_callback = &balance_push_callback;
 
 	/*
-	 * Only active while going offline.
+	 * Only active while going offline and when invoked on the outgoing
+	 * CPU.
 	 */
-	if (!cpu_dying(rq->cpu))
+	if (!cpu_dying(rq->cpu) || rq != this_rq())
 		return;
 
 	/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 912b47a..d17b0a5 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -379,10 +379,10 @@
 	cpuidle_use_deepest_state(latency_ns);
 
 	it.done = 0;
-	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	it.timer.function = idle_inject_timer_fn;
 	hrtimer_start(&it.timer, ns_to_ktime(duration_ns),
-		      HRTIMER_MODE_REL_PINNED);
+		      HRTIMER_MODE_REL_PINNED_HARD);
 
 	while (!READ_ONCE(it.done))
 		do_idle();
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 388e65d..8d252f6 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -219,13 +219,12 @@
 trace_boot_hist_add_array(struct xbc_node *hnode, char **bufp,
 			  char *end, const char *key)
 {
-	struct xbc_node *knode, *anode;
+	struct xbc_node *anode;
 	const char *p;
 	char sep;
 
-	knode = xbc_node_find_child(hnode, key);
-	if (knode) {
-		anode = xbc_node_get_child(knode);
+	p = xbc_node_find_value(hnode, key, &anode);
+	if (p) {
 		if (!anode) {
 			pr_err("hist.%s requires value(s).\n", key);
 			return -EINVAL;
@@ -263,9 +262,9 @@
 	append_printf(bufp, end, ":%s(%s)", handler, p);
 
 	/* Compose 'action' parameter */
-	knode = xbc_node_find_child(hnode, "trace");
+	knode = xbc_node_find_subkey(hnode, "trace");
 	if (!knode)
-		knode = xbc_node_find_child(hnode, "save");
+		knode = xbc_node_find_subkey(hnode, "save");
 
 	if (knode) {
 		anode = xbc_node_get_child(knode);
@@ -284,7 +283,7 @@
 				sep = ',';
 		}
 		append_printf(bufp, end, ")");
-	} else if (xbc_node_find_child(hnode, "snapshot")) {
+	} else if (xbc_node_find_subkey(hnode, "snapshot")) {
 		append_printf(bufp, end, ".snapshot()");
 	} else {
 		pr_err("hist.%s requires an action.\n",
@@ -315,7 +314,7 @@
 			break;
 	}
 
-	if (xbc_node_find_child(hnode, param))
+	if (xbc_node_find_subkey(hnode, param))
 		ret = trace_boot_hist_add_one_handler(hnode, bufp, end, handler, param);
 
 	return ret;
@@ -375,7 +374,7 @@
 	if (p)
 		append_printf(&buf, end, ":name=%s", p);
 
-	node = xbc_node_find_child(hnode, "var");
+	node = xbc_node_find_subkey(hnode, "var");
 	if (node) {
 		xbc_node_for_each_key_value(node, knode, p) {
 			/* Expression must not include spaces. */
@@ -386,21 +385,21 @@
 	}
 
 	/* Histogram control attributes (mutual exclusive) */
-	if (xbc_node_find_child(hnode, "pause"))
+	if (xbc_node_find_value(hnode, "pause", NULL))
 		append_printf(&buf, end, ":pause");
-	else if (xbc_node_find_child(hnode, "continue"))
+	else if (xbc_node_find_value(hnode, "continue", NULL))
 		append_printf(&buf, end, ":continue");
-	else if (xbc_node_find_child(hnode, "clear"))
+	else if (xbc_node_find_value(hnode, "clear", NULL))
 		append_printf(&buf, end, ":clear");
 
 	/* Histogram handler and actions */
-	node = xbc_node_find_child(hnode, "onmax");
+	node = xbc_node_find_subkey(hnode, "onmax");
 	if (node && trace_boot_hist_add_handlers(node, &buf, end, "var") < 0)
 		return -EINVAL;
-	node = xbc_node_find_child(hnode, "onchange");
+	node = xbc_node_find_subkey(hnode, "onchange");
 	if (node && trace_boot_hist_add_handlers(node, &buf, end, "var") < 0)
 		return -EINVAL;
-	node = xbc_node_find_child(hnode, "onmatch");
+	node = xbc_node_find_subkey(hnode, "onmatch");
 	if (node && trace_boot_hist_add_handlers(node, &buf, end, "event") < 0)
 		return -EINVAL;
 
@@ -437,7 +436,7 @@
 		}
 	}
 
-	if (xbc_node_find_child(hnode, "keys")) {
+	if (xbc_node_find_subkey(hnode, "keys")) {
 		if (trace_boot_compose_hist_cmd(hnode, buf, size) == 0) {
 			tmp = kstrdup(buf, GFP_KERNEL);
 			if (trigger_process_regex(file, buf) < 0)
@@ -496,7 +495,7 @@
 			else if (trigger_process_regex(file, buf) < 0)
 				pr_err("Failed to apply an action: %s\n", p);
 		}
-		anode = xbc_node_find_child(enode, "hist");
+		anode = xbc_node_find_subkey(enode, "hist");
 		if (anode)
 			trace_boot_init_histograms(file, anode, buf, ARRAY_SIZE(buf));
 	} else if (xbc_node_find_value(enode, "actions", NULL))
@@ -518,7 +517,7 @@
 	bool enable, enable_all = false;
 	const char *data;
 
-	node = xbc_node_find_child(node, "event");
+	node = xbc_node_find_subkey(node, "event");
 	if (!node)
 		return;
 	/* per-event key starts with "event.GROUP.EVENT" */
@@ -621,7 +620,7 @@
 	struct trace_array *tr;
 	const char *p;
 
-	node = xbc_node_find_child(node, "instance");
+	node = xbc_node_find_subkey(node, "instance");
 	if (!node)
 		return;
 
diff --git a/lib/bootconfig.c b/lib/bootconfig.c
index 9270174..f8419cf 100644
--- a/lib/bootconfig.c
+++ b/lib/bootconfig.c
@@ -142,16 +142,16 @@
 }
 
 /**
- * xbc_node_find_child() - Find a child node which matches given key
+ * xbc_node_find_subkey() - Find a subkey node which matches given key
  * @parent: An XBC node.
  * @key: A key string.
  *
- * Search a node under @parent which matches @key. The @key can contain
+ * Search a key node under @parent which matches @key. The @key can contain
  * several words jointed with '.'. If @parent is NULL, this searches the
  * node from whole tree. Return NULL if no node is matched.
  */
 struct xbc_node * __init
-xbc_node_find_child(struct xbc_node *parent, const char *key)
+xbc_node_find_subkey(struct xbc_node *parent, const char *key)
 {
 	struct xbc_node *node;
 
@@ -191,7 +191,7 @@
 xbc_node_find_value(struct xbc_node *parent, const char *key,
 		    struct xbc_node **vnode)
 {
-	struct xbc_node *node = xbc_node_find_child(parent, key);
+	struct xbc_node *node = xbc_node_find_subkey(parent, key);
 
 	if (!node || !xbc_node_is_key(node))
 		return NULL;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 3e02cc3..e2c0cfb 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2014,7 +2014,7 @@
 {
 	const struct vsock_transport *transport;
 	struct vsock_sock *vsk;
-	ssize_t record_len;
+	ssize_t msg_len;
 	long timeout;
 	int err = 0;
 	DEFINE_WAIT(wait);
@@ -2028,9 +2028,9 @@
 	if (err <= 0)
 		goto out;
 
-	record_len = transport->seqpacket_dequeue(vsk, msg, flags);
+	msg_len = transport->seqpacket_dequeue(vsk, msg, flags);
 
-	if (record_len < 0) {
+	if (msg_len < 0) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -2044,14 +2044,14 @@
 		 * packet.
 		 */
 		if (flags & MSG_TRUNC)
-			err = record_len;
+			err = msg_len;
 		else
 			err = len - msg_data_left(msg);
 
 		/* Always set MSG_TRUNC if real length of packet is
 		 * bigger than user's buffer.
 		 */
-		if (record_len > len)
+		if (msg_len > len)
 			msg->msg_flags |= MSG_TRUNC;
 	}
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 081e7ae..59ee1be 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -76,8 +76,12 @@
 			goto out;
 
 		if (msg_data_left(info->msg) == 0 &&
-		    info->type == VIRTIO_VSOCK_TYPE_SEQPACKET)
-			pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+		    info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) {
+			pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
+
+			if (info->msg->msg_flags & MSG_EOR)
+				pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+		}
 	}
 
 	trace_virtio_transport_alloc_pkt(src_cid, src_port,
@@ -457,9 +461,12 @@
 				dequeued_len += pkt_len;
 		}
 
-		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) {
+		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM) {
 			msg_ready = true;
 			vvs->msg_count--;
+
+			if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)
+				msg->msg_flags |= MSG_EOR;
 		}
 
 		virtio_transport_dec_rx_pkt(vvs, pkt);
@@ -1029,7 +1036,7 @@
 		goto out;
 	}
 
-	if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)
+	if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM)
 		vvs->msg_count++;
 
 	/* Try to copy small packets into the buffer of last packet queued,
@@ -1044,12 +1051,12 @@
 
 		/* If there is space in the last packet queued, we copy the
 		 * new packet in its buffer. We avoid this if the last packet
-		 * queued has VIRTIO_VSOCK_SEQ_EOR set, because this is
-		 * delimiter of SEQPACKET record, so 'pkt' is the first packet
-		 * of a new record.
+		 * queued has VIRTIO_VSOCK_SEQ_EOM set, because this is
+		 * delimiter of SEQPACKET message, so 'pkt' is the first packet
+		 * of a new message.
 		 */
 		if ((pkt->len <= last_pkt->buf_len - last_pkt->len) &&
-		    !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)) {
+		    !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOM)) {
 			memcpy(last_pkt->buf + last_pkt->len, pkt->buf,
 			       pkt->len);
 			last_pkt->len += pkt->len;
diff --git a/scripts/coccinelle/api/kvmalloc.cocci b/scripts/coccinelle/api/kvmalloc.cocci
index c30dab7..5ddcb76 100644
--- a/scripts/coccinelle/api/kvmalloc.cocci
+++ b/scripts/coccinelle/api/kvmalloc.cocci
@@ -79,7 +79,7 @@
   } else {
     ... when != krealloc(E, ...)
         when any
-*   \(kfree\|kzfree\)(E)
+*   \(kfree\|kfree_sensitive\)(E)
     ...
   }
 
diff --git a/scripts/coccinelle/iterators/use_after_iter.cocci b/scripts/coccinelle/iterators/use_after_iter.cocci
index 9be48b5..676edd5 100644
--- a/scripts/coccinelle/iterators/use_after_iter.cocci
+++ b/scripts/coccinelle/iterators/use_after_iter.cocci
@@ -123,6 +123,8 @@
 |
 list_remove_head(x,c,...)
 |
+list_entry_is_head(c,...)
+|
 sizeof(<+...c...+>)
 |
  &c->member
diff --git a/scripts/sorttable.c b/scripts/sorttable.c
index 0ef3abf..f355869 100644
--- a/scripts/sorttable.c
+++ b/scripts/sorttable.c
@@ -349,6 +349,7 @@
 	case EM_ARM:
 	case EM_MICROBLAZE:
 	case EM_MIPS:
+	case EM_RISCV:
 	case EM_XTENSA:
 		break;
 	default:
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 67766bf..2a3638c 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -282,6 +282,7 @@
 }
 
 #define MESSAGES_CNT 7
+#define MSG_EOR_IDX (MESSAGES_CNT / 2)
 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts)
 {
 	int fd;
@@ -294,7 +295,7 @@
 
 	/* Send several messages, one with MSG_EOR flag */
 	for (int i = 0; i < MESSAGES_CNT; i++)
-		send_byte(fd, 1, 0);
+		send_byte(fd, 1, (i == MSG_EOR_IDX) ? MSG_EOR : 0);
 
 	control_writeln("SENDDONE");
 	close(fd);
@@ -324,6 +325,11 @@
 			perror("message bound violated");
 			exit(EXIT_FAILURE);
 		}
+
+		if ((i == MSG_EOR_IDX) ^ !!(msg.msg_flags & MSG_EOR)) {
+			perror("MSG_EOR");
+			exit(EXIT_FAILURE);
+		}
 	}
 
 	close(fd);
diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile
index 9db867d..f9c52b7 100644
--- a/tools/thermal/tmon/Makefile
+++ b/tools/thermal/tmon/Makefile
@@ -10,10 +10,9 @@
 # Add "-fstack-protector" only if toolchain supports it.
 override CFLAGS+= $(call cc-option,-fstack-protector-strong)
 CC?= $(CROSS_COMPILE)gcc
-PKG_CONFIG?= pkg-config
+PKG_CONFIG?= $(CROSS_COMPILE)pkg-config
 
 override CFLAGS+=-D VERSION=\"$(VERSION)\"
-LDFLAGS+=
 TARGET=tmon
 
 INSTALL_PROGRAM=install -m 755 -p
@@ -33,7 +32,6 @@
 		     $(PKG_CONFIG) --cflags $(STATIC) panel ncurses 2> /dev/null)
 
 OBJS = tmon.o tui.o sysfs.o pid.o
-OBJS +=
 
 tmon: $(OBJS) Makefile tmon.h
 	$(CC) $(CFLAGS) $(LDFLAGS) $(OBJS)  -o $(TARGET) $(TMON_LIBS)
@@ -42,15 +40,13 @@
 	 sudo valgrind -v --track-origins=yes --tool=memcheck --leak-check=yes --show-reachable=yes --num-callers=20 --track-fds=yes ./$(TARGET)  1> /dev/null
 
 install:
-	- mkdir -p $(INSTALL_ROOT)/$(BINDIR)
-	- $(INSTALL_PROGRAM) "$(TARGET)" "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)"
+	- $(INSTALL_PROGRAM) -D "$(TARGET)" "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)"
 
 uninstall:
 	$(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)"
 
 clean:
-	find . -name "*.o" | xargs $(DEL_FILE)
-	rm -f $(TARGET)
+	rm -f $(TARGET) $(OBJS)
 
 dist:
 	git tag v$(VERSION)